{"current_steps": 5, "total_steps": 64460, "loss": 8.8099, "lr": 6.205398696866274e-09, "epoch": 0.0015513496742165685, "percentage": 0.01, "elapsed_time": "0:00:01", "remaining_time": "4:38:42", "throughput": 2417.44, "total_tokens": 3136} {"current_steps": 10, "total_steps": 64460, "loss": 8.8799, "lr": 1.3962147067949117e-08, "epoch": 0.003102699348433137, "percentage": 0.02, "elapsed_time": "0:00:01", "remaining_time": "3:18:30", "throughput": 3168.66, "total_tokens": 5856} {"current_steps": 15, "total_steps": 64460, "loss": 8.9107, "lr": 2.1718895439031957e-08, "epoch": 0.004654049022649705, "percentage": 0.02, "elapsed_time": "0:00:02", "remaining_time": "2:49:26", "throughput": 3786.28, "total_tokens": 8960} {"current_steps": 20, "total_steps": 64460, "loss": 8.8672, "lr": 2.9475643810114802e-08, "epoch": 0.006205398696866274, "percentage": 0.03, "elapsed_time": "0:00:02", "remaining_time": "2:34:25", "throughput": 4206.08, "total_tokens": 12096} {"current_steps": 25, "total_steps": 64460, "loss": 8.7785, "lr": 3.7232392181197643e-08, "epoch": 0.007756748371082842, "percentage": 0.04, "elapsed_time": "0:00:03", "remaining_time": "2:24:11", "throughput": 4366.05, "total_tokens": 14656} {"current_steps": 30, "total_steps": 64460, "loss": 8.4772, "lr": 4.498914055228049e-08, "epoch": 0.00930809804529941, "percentage": 0.05, "elapsed_time": "0:00:03", "remaining_time": "2:18:35", "throughput": 4322.68, "total_tokens": 16736} {"current_steps": 35, "total_steps": 64460, "loss": 8.6017, "lr": 5.274588892336333e-08, "epoch": 0.01085944771951598, "percentage": 0.05, "elapsed_time": "0:00:04", "remaining_time": "2:13:09", "throughput": 4467.49, "total_tokens": 19392} {"current_steps": 40, "total_steps": 64460, "loss": 8.6932, "lr": 6.050263729444618e-08, "epoch": 0.012410797393732548, "percentage": 0.06, "elapsed_time": "0:00:04", "remaining_time": "2:09:17", "throughput": 4643.58, "total_tokens": 22368} {"current_steps": 45, "total_steps": 64460, "loss": 8.5863, "lr": 6.825938566552902e-08, "epoch": 0.013962147067949116, "percentage": 0.07, "elapsed_time": "0:00:05", "remaining_time": "2:07:48", "throughput": 4826.21, "total_tokens": 25856} {"current_steps": 50, "total_steps": 64460, "loss": 8.3081, "lr": 7.601613403661185e-08, "epoch": 0.015513496742165685, "percentage": 0.08, "elapsed_time": "0:00:05", "remaining_time": "2:07:12", "throughput": 5011.72, "total_tokens": 29696} {"current_steps": 55, "total_steps": 64460, "loss": 8.108, "lr": 8.377288240769469e-08, "epoch": 0.017064846416382253, "percentage": 0.09, "elapsed_time": "0:00:06", "remaining_time": "2:04:27", "throughput": 5052.87, "total_tokens": 32224} {"current_steps": 60, "total_steps": 64460, "loss": 7.9731, "lr": 9.152963077877753e-08, "epoch": 0.01861619609059882, "percentage": 0.09, "elapsed_time": "0:00:06", "remaining_time": "2:03:37", "throughput": 5088.66, "total_tokens": 35168} {"current_steps": 65, "total_steps": 64460, "loss": 8.2764, "lr": 9.928637914986038e-08, "epoch": 0.02016754576481539, "percentage": 0.1, "elapsed_time": "0:00:07", "remaining_time": "2:03:46", "throughput": 5173.7, "total_tokens": 38784} {"current_steps": 70, "total_steps": 64460, "loss": 8.0645, "lr": 1.0704312752094322e-07, "epoch": 0.02171889543903196, "percentage": 0.11, "elapsed_time": "0:00:08", "remaining_time": "2:03:11", "throughput": 5264.97, "total_tokens": 42304} {"current_steps": 75, "total_steps": 64460, "loss": 7.5826, "lr": 1.1479987589202607e-07, "epoch": 0.023270245113248527, "percentage": 0.12, "elapsed_time": "0:00:08", "remaining_time": "2:01:27", "throughput": 5296.6, "total_tokens": 44960} {"current_steps": 80, "total_steps": 64460, "loss": 7.5741, "lr": 1.225566242631089e-07, "epoch": 0.024821594787465096, "percentage": 0.12, "elapsed_time": "0:00:08", "remaining_time": "2:00:31", "throughput": 5337.81, "total_tokens": 47968} {"current_steps": 85, "total_steps": 64460, "loss": 7.1172, "lr": 1.3031337263419176e-07, "epoch": 0.026372944461681664, "percentage": 0.13, "elapsed_time": "0:00:09", "remaining_time": "1:59:14", "throughput": 5345.17, "total_tokens": 50496} {"current_steps": 90, "total_steps": 64460, "loss": 7.2512, "lr": 1.380701210052746e-07, "epoch": 0.027924294135898232, "percentage": 0.14, "elapsed_time": "0:00:09", "remaining_time": "1:58:42", "throughput": 5411.51, "total_tokens": 53888} {"current_steps": 95, "total_steps": 64460, "loss": 6.6914, "lr": 1.4582686937635744e-07, "epoch": 0.0294756438101148, "percentage": 0.15, "elapsed_time": "0:00:10", "remaining_time": "1:57:45", "throughput": 5391.77, "total_tokens": 56224} {"current_steps": 100, "total_steps": 64460, "loss": 6.8742, "lr": 1.535836177474403e-07, "epoch": 0.03102699348433137, "percentage": 0.16, "elapsed_time": "0:00:10", "remaining_time": "1:57:16", "throughput": 5429.48, "total_tokens": 59360} {"current_steps": 105, "total_steps": 64460, "loss": 6.4364, "lr": 1.6134036611852314e-07, "epoch": 0.032578343158547934, "percentage": 0.16, "elapsed_time": "0:00:11", "remaining_time": "1:57:27", "throughput": 5421.12, "total_tokens": 62336} {"current_steps": 110, "total_steps": 64460, "loss": 6.1634, "lr": 1.6909711448960597e-07, "epoch": 0.034129692832764506, "percentage": 0.17, "elapsed_time": "0:00:11", "remaining_time": "1:56:54", "throughput": 5425.24, "total_tokens": 65056} {"current_steps": 115, "total_steps": 64460, "loss": 5.875, "lr": 1.7685386286068882e-07, "epoch": 0.03568104250698107, "percentage": 0.18, "elapsed_time": "0:00:12", "remaining_time": "1:56:15", "throughput": 5436.28, "total_tokens": 67776} {"current_steps": 120, "total_steps": 64460, "loss": 5.9362, "lr": 1.8461061123177164e-07, "epoch": 0.03723239218119764, "percentage": 0.19, "elapsed_time": "0:00:12", "remaining_time": "1:56:07", "throughput": 5451.72, "total_tokens": 70848} {"current_steps": 125, "total_steps": 64460, "loss": 5.6406, "lr": 1.9236735960285452e-07, "epoch": 0.03878374185541421, "percentage": 0.19, "elapsed_time": "0:00:13", "remaining_time": "1:55:33", "throughput": 5463.28, "total_tokens": 73600} {"current_steps": 130, "total_steps": 64460, "loss": 5.6974, "lr": 2.0012410797393735e-07, "epoch": 0.04033509152963078, "percentage": 0.2, "elapsed_time": "0:00:14", "remaining_time": "1:55:57", "throughput": 5505.76, "total_tokens": 77408} {"current_steps": 135, "total_steps": 64460, "loss": 5.3866, "lr": 2.078808563450202e-07, "epoch": 0.041886441203847345, "percentage": 0.21, "elapsed_time": "0:00:14", "remaining_time": "1:56:08", "throughput": 5531.7, "total_tokens": 80896} {"current_steps": 140, "total_steps": 64460, "loss": 5.2915, "lr": 2.1563760471610302e-07, "epoch": 0.04343779087806392, "percentage": 0.22, "elapsed_time": "0:00:15", "remaining_time": "1:55:21", "throughput": 5547.74, "total_tokens": 83584} {"current_steps": 145, "total_steps": 64460, "loss": 5.3407, "lr": 2.2339435308718587e-07, "epoch": 0.04498914055228048, "percentage": 0.22, "elapsed_time": "0:00:15", "remaining_time": "1:55:28", "throughput": 5573.99, "total_tokens": 87072} {"current_steps": 150, "total_steps": 64460, "loss": 4.7676, "lr": 2.311511014582687e-07, "epoch": 0.046540490226497054, "percentage": 0.23, "elapsed_time": "0:00:16", "remaining_time": "1:55:01", "throughput": 5571.97, "total_tokens": 89696} {"current_steps": 155, "total_steps": 64460, "loss": 5.1005, "lr": 2.3890784982935155e-07, "epoch": 0.04809183990071362, "percentage": 0.24, "elapsed_time": "0:00:16", "remaining_time": "1:55:22", "throughput": 5605.53, "total_tokens": 93536} {"current_steps": 160, "total_steps": 64460, "loss": 4.8372, "lr": 2.466645982004344e-07, "epoch": 0.04964318957493019, "percentage": 0.25, "elapsed_time": "0:00:17", "remaining_time": "1:55:07", "throughput": 5637.28, "total_tokens": 96896} {"current_steps": 165, "total_steps": 64460, "loss": 4.4734, "lr": 2.5442134657151725e-07, "epoch": 0.051194539249146756, "percentage": 0.26, "elapsed_time": "0:00:17", "remaining_time": "1:54:42", "throughput": 5638.22, "total_tokens": 99584} {"current_steps": 170, "total_steps": 64460, "loss": 4.7271, "lr": 2.621780949426001e-07, "epoch": 0.05274588892336333, "percentage": 0.26, "elapsed_time": "0:00:18", "remaining_time": "1:57:37", "throughput": 5697.81, "total_tokens": 106336} {"current_steps": 175, "total_steps": 64460, "loss": 4.1557, "lr": 2.6993484331368296e-07, "epoch": 0.05429723859757989, "percentage": 0.27, "elapsed_time": "0:00:19", "remaining_time": "1:57:09", "throughput": 5704.24, "total_tokens": 109152} {"current_steps": 180, "total_steps": 64460, "loss": 3.8712, "lr": 2.776915916847658e-07, "epoch": 0.055848588271796465, "percentage": 0.28, "elapsed_time": "0:00:19", "remaining_time": "1:56:32", "throughput": 5693.99, "total_tokens": 111488} {"current_steps": 185, "total_steps": 64460, "loss": 3.8641, "lr": 2.854483400558486e-07, "epoch": 0.05739993794601303, "percentage": 0.29, "elapsed_time": "0:00:20", "remaining_time": "1:56:07", "throughput": 5707.67, "total_tokens": 114464} {"current_steps": 190, "total_steps": 64460, "loss": 3.7816, "lr": 2.9320508842693143e-07, "epoch": 0.0589512876202296, "percentage": 0.29, "elapsed_time": "0:00:20", "remaining_time": "1:56:04", "throughput": 5730.77, "total_tokens": 117984} {"current_steps": 195, "total_steps": 64460, "loss": 3.3856, "lr": 3.0096183679801426e-07, "epoch": 0.06050263729444617, "percentage": 0.3, "elapsed_time": "0:00:21", "remaining_time": "1:55:28", "throughput": 5719.01, "total_tokens": 120224} {"current_steps": 200, "total_steps": 64460, "loss": 3.4033, "lr": 3.0871858516909713e-07, "epoch": 0.06205398696866274, "percentage": 0.31, "elapsed_time": "0:00:21", "remaining_time": "1:55:03", "throughput": 5719.35, "total_tokens": 122880} {"current_steps": 205, "total_steps": 64460, "loss": 3.342, "lr": 3.1647533354017996e-07, "epoch": 0.0636053366428793, "percentage": 0.32, "elapsed_time": "0:00:21", "remaining_time": "1:54:47", "throughput": 5737.33, "total_tokens": 126080} {"current_steps": 210, "total_steps": 64460, "loss": 2.863, "lr": 3.242320819112628e-07, "epoch": 0.06515668631709587, "percentage": 0.33, "elapsed_time": "0:00:22", "remaining_time": "1:54:15", "throughput": 5738.12, "total_tokens": 128576} {"current_steps": 215, "total_steps": 64460, "loss": 2.8464, "lr": 3.3198883028234566e-07, "epoch": 0.06670803599131245, "percentage": 0.33, "elapsed_time": "0:00:22", "remaining_time": "1:54:06", "throughput": 5748.43, "total_tokens": 131712} {"current_steps": 220, "total_steps": 64460, "loss": 2.5337, "lr": 3.397455786534285e-07, "epoch": 0.06825938566552901, "percentage": 0.34, "elapsed_time": "0:00:23", "remaining_time": "1:53:40", "throughput": 5740.54, "total_tokens": 134080} {"current_steps": 225, "total_steps": 64460, "loss": 2.5682, "lr": 3.475023270245113e-07, "epoch": 0.06981073533974558, "percentage": 0.35, "elapsed_time": "0:00:23", "remaining_time": "1:53:32", "throughput": 5741.29, "total_tokens": 136992} {"current_steps": 230, "total_steps": 64460, "loss": 2.4665, "lr": 3.5525907539559414e-07, "epoch": 0.07136208501396214, "percentage": 0.36, "elapsed_time": "0:00:24", "remaining_time": "1:53:11", "throughput": 5738.54, "total_tokens": 139552} {"current_steps": 235, "total_steps": 64460, "loss": 2.121, "lr": 3.6301582376667707e-07, "epoch": 0.07291343468817872, "percentage": 0.36, "elapsed_time": "0:00:24", "remaining_time": "1:52:42", "throughput": 5725.32, "total_tokens": 141664} {"current_steps": 240, "total_steps": 64460, "loss": 2.0984, "lr": 3.707725721377599e-07, "epoch": 0.07446478436239529, "percentage": 0.37, "elapsed_time": "0:00:25", "remaining_time": "1:52:23", "throughput": 5712.66, "total_tokens": 143968} {"current_steps": 245, "total_steps": 64460, "loss": 1.8893, "lr": 3.785293205088427e-07, "epoch": 0.07601613403661185, "percentage": 0.38, "elapsed_time": "0:00:25", "remaining_time": "1:51:57", "throughput": 5703.54, "total_tokens": 146176} {"current_steps": 250, "total_steps": 64460, "loss": 1.814, "lr": 3.8628606887992554e-07, "epoch": 0.07756748371082842, "percentage": 0.39, "elapsed_time": "0:00:26", "remaining_time": "1:51:36", "throughput": 5701.32, "total_tokens": 148640} {"current_steps": 255, "total_steps": 64460, "loss": 1.7127, "lr": 3.940428172510084e-07, "epoch": 0.079118833385045, "percentage": 0.4, "elapsed_time": "0:00:26", "remaining_time": "1:51:20", "throughput": 5707.28, "total_tokens": 151424} {"current_steps": 260, "total_steps": 64460, "loss": 1.6353, "lr": 4.0179956562209125e-07, "epoch": 0.08067018305926156, "percentage": 0.4, "elapsed_time": "0:00:27", "remaining_time": "1:51:08", "throughput": 5704.54, "total_tokens": 154048} {"current_steps": 265, "total_steps": 64460, "loss": 1.4098, "lr": 4.0955631399317407e-07, "epoch": 0.08222153273347813, "percentage": 0.41, "elapsed_time": "0:00:27", "remaining_time": "1:50:55", "throughput": 5693.48, "total_tokens": 156416} {"current_steps": 270, "total_steps": 64460, "loss": 1.4388, "lr": 4.173130623642569e-07, "epoch": 0.08377288240769469, "percentage": 0.42, "elapsed_time": "0:00:27", "remaining_time": "1:50:40", "throughput": 5696.35, "total_tokens": 159104} {"current_steps": 275, "total_steps": 64460, "loss": 1.2588, "lr": 4.2506981073533983e-07, "epoch": 0.08532423208191127, "percentage": 0.43, "elapsed_time": "0:00:28", "remaining_time": "1:50:31", "throughput": 5686.82, "total_tokens": 161568} {"current_steps": 280, "total_steps": 64460, "loss": 1.3577, "lr": 4.3282655910642265e-07, "epoch": 0.08687558175612783, "percentage": 0.43, "elapsed_time": "0:00:28", "remaining_time": "1:50:29", "throughput": 5693.7, "total_tokens": 164672} {"current_steps": 285, "total_steps": 64460, "loss": 1.1658, "lr": 4.405833074775055e-07, "epoch": 0.0884269314303444, "percentage": 0.44, "elapsed_time": "0:00:29", "remaining_time": "1:50:24", "throughput": 5704.99, "total_tokens": 167840} {"current_steps": 290, "total_steps": 64460, "loss": 1.069, "lr": 4.483400558485883e-07, "epoch": 0.08997828110456096, "percentage": 0.45, "elapsed_time": "0:00:29", "remaining_time": "1:50:11", "throughput": 5711.36, "total_tokens": 170656} {"current_steps": 295, "total_steps": 64460, "loss": 0.9351, "lr": 4.560968042196712e-07, "epoch": 0.09152963077877754, "percentage": 0.46, "elapsed_time": "0:00:30", "remaining_time": "1:49:58", "throughput": 5715.3, "total_tokens": 173376} {"current_steps": 300, "total_steps": 64460, "loss": 0.9717, "lr": 4.63853552590754e-07, "epoch": 0.09308098045299411, "percentage": 0.47, "elapsed_time": "0:00:30", "remaining_time": "1:50:02", "throughput": 5732.41, "total_tokens": 176960} {"current_steps": 305, "total_steps": 64460, "loss": 0.9049, "lr": 4.7161030096183683e-07, "epoch": 0.09463233012721067, "percentage": 0.47, "elapsed_time": "0:00:31", "remaining_time": "1:49:51", "throughput": 5733.49, "total_tokens": 179680} {"current_steps": 310, "total_steps": 64460, "loss": 0.8444, "lr": 4.793670493329197e-07, "epoch": 0.09618367980142724, "percentage": 0.48, "elapsed_time": "0:00:31", "remaining_time": "1:49:50", "throughput": 5743.52, "total_tokens": 182912} {"current_steps": 315, "total_steps": 64460, "loss": 0.7123, "lr": 4.871237977040025e-07, "epoch": 0.09773502947564382, "percentage": 0.49, "elapsed_time": "0:00:32", "remaining_time": "1:49:58", "throughput": 5756.74, "total_tokens": 186528} {"current_steps": 320, "total_steps": 64460, "loss": 0.5901, "lr": 4.948805460750854e-07, "epoch": 0.09928637914986038, "percentage": 0.5, "elapsed_time": "0:00:32", "remaining_time": "1:49:37", "throughput": 5748.3, "total_tokens": 188640} {"current_steps": 325, "total_steps": 64460, "loss": 0.5284, "lr": 5.026372944461682e-07, "epoch": 0.10083772882407695, "percentage": 0.5, "elapsed_time": "0:00:33", "remaining_time": "1:49:19", "throughput": 5739.05, "total_tokens": 190752} {"current_steps": 330, "total_steps": 64460, "loss": 0.5626, "lr": 5.103940428172511e-07, "epoch": 0.10238907849829351, "percentage": 0.51, "elapsed_time": "0:00:33", "remaining_time": "1:49:16", "throughput": 5735.58, "total_tokens": 193504} {"current_steps": 335, "total_steps": 64460, "loss": 0.4812, "lr": 5.181507911883339e-07, "epoch": 0.10394042817251008, "percentage": 0.52, "elapsed_time": "0:00:34", "remaining_time": "1:49:02", "throughput": 5733.79, "total_tokens": 195968} {"current_steps": 340, "total_steps": 64460, "loss": 0.4644, "lr": 5.259075395594167e-07, "epoch": 0.10549177784672666, "percentage": 0.53, "elapsed_time": "0:00:34", "remaining_time": "1:48:52", "throughput": 5734.15, "total_tokens": 198624} {"current_steps": 345, "total_steps": 64460, "loss": 0.4821, "lr": 5.336642879304996e-07, "epoch": 0.10704312752094322, "percentage": 0.54, "elapsed_time": "0:00:35", "remaining_time": "1:48:40", "throughput": 5732.18, "total_tokens": 201120} {"current_steps": 350, "total_steps": 64460, "loss": 0.4086, "lr": 5.414210363015824e-07, "epoch": 0.10859447719515979, "percentage": 0.54, "elapsed_time": "0:00:35", "remaining_time": "1:48:28", "throughput": 5725.55, "total_tokens": 203456} {"current_steps": 355, "total_steps": 64460, "loss": 0.5308, "lr": 5.491777846726652e-07, "epoch": 0.11014582686937635, "percentage": 0.55, "elapsed_time": "0:00:36", "remaining_time": "1:48:39", "throughput": 5731.85, "total_tokens": 206944} {"current_steps": 360, "total_steps": 64460, "loss": 0.4011, "lr": 5.569345330437481e-07, "epoch": 0.11169717654359293, "percentage": 0.56, "elapsed_time": "0:00:36", "remaining_time": "1:48:28", "throughput": 5734.83, "total_tokens": 209632} {"current_steps": 365, "total_steps": 64460, "loss": 0.4416, "lr": 5.646912814148309e-07, "epoch": 0.1132485262178095, "percentage": 0.57, "elapsed_time": "0:00:37", "remaining_time": "1:48:32", "throughput": 5746.66, "total_tokens": 213120} {"current_steps": 370, "total_steps": 64460, "loss": 0.3943, "lr": 5.724480297859138e-07, "epoch": 0.11479987589202606, "percentage": 0.57, "elapsed_time": "0:00:37", "remaining_time": "1:48:20", "throughput": 5746.41, "total_tokens": 215648} {"current_steps": 375, "total_steps": 64460, "loss": 0.4088, "lr": 5.802047781569966e-07, "epoch": 0.11635122556624262, "percentage": 0.58, "elapsed_time": "0:00:38", "remaining_time": "1:48:36", "throughput": 5765.32, "total_tokens": 219840} {"current_steps": 380, "total_steps": 64460, "loss": 0.3649, "lr": 5.879615265280795e-07, "epoch": 0.1179025752404592, "percentage": 0.59, "elapsed_time": "0:00:38", "remaining_time": "1:48:23", "throughput": 5760.44, "total_tokens": 222144} {"current_steps": 385, "total_steps": 64460, "loss": 0.3502, "lr": 5.957182748991623e-07, "epoch": 0.11945392491467577, "percentage": 0.6, "elapsed_time": "0:00:39", "remaining_time": "1:48:13", "throughput": 5759.89, "total_tokens": 224736} {"current_steps": 390, "total_steps": 64460, "loss": 0.3671, "lr": 6.034750232702452e-07, "epoch": 0.12100527458889233, "percentage": 0.61, "elapsed_time": "0:00:39", "remaining_time": "1:48:08", "throughput": 5766.35, "total_tokens": 227744} {"current_steps": 395, "total_steps": 64460, "loss": 0.311, "lr": 6.11231771641328e-07, "epoch": 0.1225566242631089, "percentage": 0.61, "elapsed_time": "0:00:40", "remaining_time": "1:48:16", "throughput": 5777.32, "total_tokens": 231424} {"current_steps": 400, "total_steps": 64460, "loss": 0.3029, "lr": 6.189885200124108e-07, "epoch": 0.12410797393732548, "percentage": 0.62, "elapsed_time": "0:00:40", "remaining_time": "1:48:14", "throughput": 5782.31, "total_tokens": 234496} {"current_steps": 405, "total_steps": 64460, "loss": 0.2854, "lr": 6.267452683834938e-07, "epoch": 0.12565932361154203, "percentage": 0.63, "elapsed_time": "0:00:41", "remaining_time": "1:48:09", "throughput": 5777.55, "total_tokens": 237056} {"current_steps": 410, "total_steps": 64460, "loss": 0.3084, "lr": 6.345020167545765e-07, "epoch": 0.1272106732857586, "percentage": 0.64, "elapsed_time": "0:00:41", "remaining_time": "1:48:07", "throughput": 5773.02, "total_tokens": 239744} {"current_steps": 415, "total_steps": 64460, "loss": 0.3168, "lr": 6.422587651256595e-07, "epoch": 0.1287620229599752, "percentage": 0.64, "elapsed_time": "0:00:41", "remaining_time": "1:48:01", "throughput": 5774.75, "total_tokens": 242528} {"current_steps": 420, "total_steps": 64460, "loss": 0.4239, "lr": 6.500155134967421e-07, "epoch": 0.13031337263419174, "percentage": 0.65, "elapsed_time": "0:00:42", "remaining_time": "1:48:15", "throughput": 5776.87, "total_tokens": 246080} {"current_steps": 425, "total_steps": 64460, "loss": 0.3253, "lr": 6.577722618678251e-07, "epoch": 0.13186472230840832, "percentage": 0.66, "elapsed_time": "0:00:43", "remaining_time": "1:48:17", "throughput": 5772.16, "total_tokens": 248928} {"current_steps": 430, "total_steps": 64460, "loss": 0.2718, "lr": 6.65529010238908e-07, "epoch": 0.1334160719826249, "percentage": 0.67, "elapsed_time": "0:00:43", "remaining_time": "1:48:18", "throughput": 5775.15, "total_tokens": 252032} {"current_steps": 435, "total_steps": 64460, "loss": 0.3391, "lr": 6.732857586099908e-07, "epoch": 0.13496742165684145, "percentage": 0.67, "elapsed_time": "0:00:44", "remaining_time": "1:48:17", "throughput": 5777.79, "total_tokens": 255072} {"current_steps": 440, "total_steps": 64460, "loss": 0.3208, "lr": 6.810425069810736e-07, "epoch": 0.13651877133105803, "percentage": 0.68, "elapsed_time": "0:00:44", "remaining_time": "1:48:09", "throughput": 5770.88, "total_tokens": 257376} {"current_steps": 445, "total_steps": 64460, "loss": 0.2555, "lr": 6.887992553521565e-07, "epoch": 0.13807012100527458, "percentage": 0.69, "elapsed_time": "0:00:45", "remaining_time": "1:48:22", "throughput": 5781.47, "total_tokens": 261344} {"current_steps": 450, "total_steps": 64460, "loss": 0.3094, "lr": 6.965560037232393e-07, "epoch": 0.13962147067949116, "percentage": 0.7, "elapsed_time": "0:00:45", "remaining_time": "1:48:16", "throughput": 5775.1, "total_tokens": 263744} {"current_steps": 455, "total_steps": 64460, "loss": 0.3539, "lr": 7.043127520943222e-07, "epoch": 0.14117282035370773, "percentage": 0.71, "elapsed_time": "0:00:46", "remaining_time": "1:48:09", "throughput": 5773.68, "total_tokens": 266368} {"current_steps": 460, "total_steps": 64460, "loss": 0.3232, "lr": 7.120695004654049e-07, "epoch": 0.14272417002792429, "percentage": 0.71, "elapsed_time": "0:00:46", "remaining_time": "1:48:02", "throughput": 5766.98, "total_tokens": 268704} {"current_steps": 465, "total_steps": 64460, "loss": 0.2834, "lr": 7.198262488364878e-07, "epoch": 0.14427551970214086, "percentage": 0.72, "elapsed_time": "0:00:47", "remaining_time": "1:47:57", "throughput": 5769.96, "total_tokens": 271584} {"current_steps": 470, "total_steps": 64460, "loss": 0.2718, "lr": 7.275829972075707e-07, "epoch": 0.14582686937635744, "percentage": 0.73, "elapsed_time": "0:00:47", "remaining_time": "1:47:51", "throughput": 5758.41, "total_tokens": 273728} {"current_steps": 475, "total_steps": 64460, "loss": 0.3183, "lr": 7.353397455786535e-07, "epoch": 0.147378219050574, "percentage": 0.74, "elapsed_time": "0:00:47", "remaining_time": "1:47:42", "throughput": 5752.41, "total_tokens": 275968} {"current_steps": 480, "total_steps": 64460, "loss": 0.2808, "lr": 7.430964939497363e-07, "epoch": 0.14892956872479057, "percentage": 0.74, "elapsed_time": "0:00:48", "remaining_time": "1:47:39", "throughput": 5747.76, "total_tokens": 278528} {"current_steps": 485, "total_steps": 64460, "loss": 0.3304, "lr": 7.508532423208192e-07, "epoch": 0.15048091839900712, "percentage": 0.75, "elapsed_time": "0:00:48", "remaining_time": "1:47:40", "throughput": 5753.32, "total_tokens": 281792} {"current_steps": 490, "total_steps": 64460, "loss": 0.2803, "lr": 7.58609990691902e-07, "epoch": 0.1520322680732237, "percentage": 0.76, "elapsed_time": "0:00:49", "remaining_time": "1:47:37", "throughput": 5743.85, "total_tokens": 284096} {"current_steps": 495, "total_steps": 64460, "loss": 0.266, "lr": 7.663667390629849e-07, "epoch": 0.15358361774744028, "percentage": 0.77, "elapsed_time": "0:00:49", "remaining_time": "1:47:33", "throughput": 5741.4, "total_tokens": 286720} {"current_steps": 500, "total_steps": 64460, "loss": 0.296, "lr": 7.741234874340676e-07, "epoch": 0.15513496742165683, "percentage": 0.78, "elapsed_time": "0:00:50", "remaining_time": "1:47:38", "throughput": 5749.62, "total_tokens": 290272} {"current_steps": 505, "total_steps": 64460, "loss": 0.2932, "lr": 7.818802358051505e-07, "epoch": 0.1566863170958734, "percentage": 0.78, "elapsed_time": "0:00:50", "remaining_time": "1:47:36", "throughput": 5747.14, "total_tokens": 292992} {"current_steps": 510, "total_steps": 64460, "loss": 0.2966, "lr": 7.896369841762334e-07, "epoch": 0.15823766677009, "percentage": 0.79, "elapsed_time": "0:00:51", "remaining_time": "1:47:36", "throughput": 5750.74, "total_tokens": 296128} {"current_steps": 515, "total_steps": 64460, "loss": 0.3017, "lr": 7.973937325473162e-07, "epoch": 0.15978901644430654, "percentage": 0.8, "elapsed_time": "0:00:52", "remaining_time": "1:47:45", "throughput": 5742.63, "total_tokens": 299040} {"current_steps": 520, "total_steps": 64460, "loss": 0.233, "lr": 8.05150480918399e-07, "epoch": 0.16134036611852312, "percentage": 0.81, "elapsed_time": "0:00:52", "remaining_time": "1:47:52", "throughput": 5734.46, "total_tokens": 301856} {"current_steps": 525, "total_steps": 64460, "loss": 0.4155, "lr": 8.129072292894818e-07, "epoch": 0.16289171579273967, "percentage": 0.81, "elapsed_time": "0:00:53", "remaining_time": "1:48:21", "throughput": 5743.79, "total_tokens": 306656} {"current_steps": 530, "total_steps": 64460, "loss": 0.2785, "lr": 8.206639776605647e-07, "epoch": 0.16444306546695625, "percentage": 0.82, "elapsed_time": "0:00:53", "remaining_time": "1:48:20", "throughput": 5746.23, "total_tokens": 309664} {"current_steps": 535, "total_steps": 64460, "loss": 0.2969, "lr": 8.284207260316477e-07, "epoch": 0.16599441514117283, "percentage": 0.83, "elapsed_time": "0:00:54", "remaining_time": "1:48:22", "throughput": 5747.45, "total_tokens": 312768} {"current_steps": 540, "total_steps": 64460, "loss": 0.2914, "lr": 8.361774744027303e-07, "epoch": 0.16754576481538938, "percentage": 0.84, "elapsed_time": "0:00:55", "remaining_time": "1:48:36", "throughput": 5757.18, "total_tokens": 316928} {"current_steps": 545, "total_steps": 64460, "loss": 0.2562, "lr": 8.439342227738133e-07, "epoch": 0.16909711448960596, "percentage": 0.85, "elapsed_time": "0:00:55", "remaining_time": "1:48:27", "throughput": 5757.28, "total_tokens": 319488} {"current_steps": 550, "total_steps": 64460, "loss": 0.2479, "lr": 8.516909711448962e-07, "epoch": 0.17064846416382254, "percentage": 0.85, "elapsed_time": "0:00:55", "remaining_time": "1:48:19", "throughput": 5753.84, "total_tokens": 321856} {"current_steps": 555, "total_steps": 64460, "loss": 0.2673, "lr": 8.59447719515979e-07, "epoch": 0.1721998138380391, "percentage": 0.86, "elapsed_time": "0:00:56", "remaining_time": "1:48:25", "throughput": 5762.1, "total_tokens": 325536} {"current_steps": 560, "total_steps": 64460, "loss": 0.278, "lr": 8.672044678870619e-07, "epoch": 0.17375116351225567, "percentage": 0.87, "elapsed_time": "0:00:57", "remaining_time": "1:48:28", "throughput": 5766.34, "total_tokens": 328928} {"current_steps": 565, "total_steps": 64460, "loss": 0.2649, "lr": 8.749612162581446e-07, "epoch": 0.17530251318647222, "percentage": 0.88, "elapsed_time": "0:00:57", "remaining_time": "1:48:32", "throughput": 5770.97, "total_tokens": 332320} {"current_steps": 570, "total_steps": 64460, "loss": 0.2517, "lr": 8.827179646292275e-07, "epoch": 0.1768538628606888, "percentage": 0.88, "elapsed_time": "0:00:58", "remaining_time": "1:48:30", "throughput": 5769.36, "total_tokens": 335104} {"current_steps": 575, "total_steps": 64460, "loss": 0.2831, "lr": 8.904747130003104e-07, "epoch": 0.17840521253490538, "percentage": 0.89, "elapsed_time": "0:00:58", "remaining_time": "1:48:39", "throughput": 5776.83, "total_tokens": 338976} {"current_steps": 580, "total_steps": 64460, "loss": 0.2574, "lr": 8.982314613713932e-07, "epoch": 0.17995656220912193, "percentage": 0.9, "elapsed_time": "0:00:59", "remaining_time": "1:48:45", "throughput": 5783.81, "total_tokens": 342688} {"current_steps": 585, "total_steps": 64460, "loss": 0.2738, "lr": 9.05988209742476e-07, "epoch": 0.1815079118833385, "percentage": 0.91, "elapsed_time": "0:00:59", "remaining_time": "1:48:41", "throughput": 5786.77, "total_tokens": 345632} {"current_steps": 590, "total_steps": 64460, "loss": 0.2512, "lr": 9.137449581135589e-07, "epoch": 0.1830592615575551, "percentage": 0.92, "elapsed_time": "0:01:00", "remaining_time": "1:48:39", "throughput": 5792.3, "total_tokens": 348832} {"current_steps": 595, "total_steps": 64460, "loss": 0.2642, "lr": 9.215017064846417e-07, "epoch": 0.18461061123177164, "percentage": 0.92, "elapsed_time": "0:01:00", "remaining_time": "1:48:39", "throughput": 5782.28, "total_tokens": 351200} {"current_steps": 600, "total_steps": 64460, "loss": 0.2423, "lr": 9.292584548557246e-07, "epoch": 0.18616196090598822, "percentage": 0.93, "elapsed_time": "0:01:01", "remaining_time": "1:48:36", "throughput": 5780.64, "total_tokens": 353952} {"current_steps": 605, "total_steps": 64460, "loss": 0.2595, "lr": 9.370152032268073e-07, "epoch": 0.18771331058020477, "percentage": 0.94, "elapsed_time": "0:01:01", "remaining_time": "1:48:38", "throughput": 5784.67, "total_tokens": 357248} {"current_steps": 610, "total_steps": 64460, "loss": 0.2758, "lr": 9.447719515978902e-07, "epoch": 0.18926466025442135, "percentage": 0.95, "elapsed_time": "0:01:02", "remaining_time": "1:48:33", "throughput": 5782.86, "total_tokens": 359840} {"current_steps": 615, "total_steps": 64460, "loss": 0.3061, "lr": 9.525286999689731e-07, "epoch": 0.19081600992863793, "percentage": 0.95, "elapsed_time": "0:01:03", "remaining_time": "1:49:04", "throughput": 5797.62, "total_tokens": 365504} {"current_steps": 620, "total_steps": 64460, "loss": 0.2767, "lr": 9.602854483400559e-07, "epoch": 0.19236735960285448, "percentage": 0.96, "elapsed_time": "0:01:03", "remaining_time": "1:49:02", "throughput": 5792.73, "total_tokens": 368064} {"current_steps": 625, "total_steps": 64460, "loss": 0.2517, "lr": 9.680421967111388e-07, "epoch": 0.19391870927707106, "percentage": 0.97, "elapsed_time": "0:01:04", "remaining_time": "1:49:03", "throughput": 5786.88, "total_tokens": 370752} {"current_steps": 630, "total_steps": 64460, "loss": 0.2757, "lr": 9.757989450822216e-07, "epoch": 0.19547005895128763, "percentage": 0.98, "elapsed_time": "0:01:04", "remaining_time": "1:49:01", "throughput": 5787.06, "total_tokens": 373664} {"current_steps": 635, "total_steps": 64460, "loss": 0.2733, "lr": 9.835556934533044e-07, "epoch": 0.19702140862550419, "percentage": 0.99, "elapsed_time": "0:01:05", "remaining_time": "1:49:00", "throughput": 5778.36, "total_tokens": 376032} {"current_steps": 640, "total_steps": 64460, "loss": 0.2611, "lr": 9.913124418243874e-07, "epoch": 0.19857275829972076, "percentage": 0.99, "elapsed_time": "0:01:05", "remaining_time": "1:48:57", "throughput": 5774.7, "total_tokens": 378560} {"current_steps": 645, "total_steps": 64460, "loss": 0.2577, "lr": 9.990691901954701e-07, "epoch": 0.20012410797393732, "percentage": 1.0, "elapsed_time": "0:01:06", "remaining_time": "1:48:57", "throughput": 5778.18, "total_tokens": 381824} {"current_steps": 650, "total_steps": 64460, "loss": 0.2434, "lr": 1.006825938566553e-06, "epoch": 0.2016754576481539, "percentage": 1.01, "elapsed_time": "0:01:06", "remaining_time": "1:48:51", "throughput": 5773.29, "total_tokens": 384096} {"current_steps": 655, "total_steps": 64460, "loss": 0.241, "lr": 1.014582686937636e-06, "epoch": 0.20322680732237047, "percentage": 1.02, "elapsed_time": "0:01:07", "remaining_time": "1:48:55", "throughput": 5778.57, "total_tokens": 387712} {"current_steps": 660, "total_steps": 64460, "loss": 0.2621, "lr": 1.0223394353087187e-06, "epoch": 0.20477815699658702, "percentage": 1.02, "elapsed_time": "0:01:07", "remaining_time": "1:49:11", "throughput": 5790.16, "total_tokens": 392448} {"current_steps": 665, "total_steps": 64460, "loss": 0.2543, "lr": 1.0300961836798014e-06, "epoch": 0.2063295066708036, "percentage": 1.03, "elapsed_time": "0:01:08", "remaining_time": "1:49:07", "throughput": 5790.77, "total_tokens": 395200} {"current_steps": 670, "total_steps": 64460, "loss": 0.2575, "lr": 1.0378529320508844e-06, "epoch": 0.20788085634502015, "percentage": 1.04, "elapsed_time": "0:01:08", "remaining_time": "1:49:04", "throughput": 5792.85, "total_tokens": 398176} {"current_steps": 675, "total_steps": 64460, "loss": 0.2525, "lr": 1.0456096804219672e-06, "epoch": 0.20943220601923673, "percentage": 1.05, "elapsed_time": "0:01:09", "remaining_time": "1:48:59", "throughput": 5788.04, "total_tokens": 400544} {"current_steps": 680, "total_steps": 64460, "loss": 0.2611, "lr": 1.05336642879305e-06, "epoch": 0.2109835556934533, "percentage": 1.05, "elapsed_time": "0:01:09", "remaining_time": "1:49:01", "throughput": 5796.74, "total_tokens": 404288} {"current_steps": 685, "total_steps": 64460, "loss": 0.2321, "lr": 1.0611231771641327e-06, "epoch": 0.21253490536766986, "percentage": 1.06, "elapsed_time": "0:01:10", "remaining_time": "1:48:57", "throughput": 5795.88, "total_tokens": 406976} {"current_steps": 690, "total_steps": 64460, "loss": 0.2551, "lr": 1.0688799255352157e-06, "epoch": 0.21408625504188644, "percentage": 1.07, "elapsed_time": "0:01:10", "remaining_time": "1:48:50", "throughput": 5792.93, "total_tokens": 409344} {"current_steps": 695, "total_steps": 64460, "loss": 0.2578, "lr": 1.0766366739062987e-06, "epoch": 0.21563760471610302, "percentage": 1.08, "elapsed_time": "0:01:11", "remaining_time": "1:48:56", "throughput": 5794.79, "total_tokens": 412864} {"current_steps": 700, "total_steps": 64460, "loss": 0.2611, "lr": 1.0843934222773813e-06, "epoch": 0.21718895439031957, "percentage": 1.09, "elapsed_time": "0:01:11", "remaining_time": "1:48:53", "throughput": 5795.16, "total_tokens": 415712} {"current_steps": 705, "total_steps": 64460, "loss": 0.232, "lr": 1.0921501706484643e-06, "epoch": 0.21874030406453615, "percentage": 1.09, "elapsed_time": "0:01:12", "remaining_time": "1:48:49", "throughput": 5794.84, "total_tokens": 418400} {"current_steps": 710, "total_steps": 64460, "loss": 0.2414, "lr": 1.0999069190195472e-06, "epoch": 0.2202916537387527, "percentage": 1.1, "elapsed_time": "0:01:12", "remaining_time": "1:48:42", "throughput": 5794.33, "total_tokens": 420928} {"current_steps": 715, "total_steps": 64460, "loss": 0.2563, "lr": 1.10766366739063e-06, "epoch": 0.22184300341296928, "percentage": 1.11, "elapsed_time": "0:01:13", "remaining_time": "1:48:39", "throughput": 5798.25, "total_tokens": 424032} {"current_steps": 720, "total_steps": 64460, "loss": 0.2362, "lr": 1.1154204157617128e-06, "epoch": 0.22339435308718586, "percentage": 1.12, "elapsed_time": "0:01:13", "remaining_time": "1:48:47", "throughput": 5801.63, "total_tokens": 427808} {"current_steps": 725, "total_steps": 64460, "loss": 0.2347, "lr": 1.1231771641327956e-06, "epoch": 0.2249457027614024, "percentage": 1.12, "elapsed_time": "0:01:14", "remaining_time": "1:48:46", "throughput": 5804.27, "total_tokens": 430944} {"current_steps": 730, "total_steps": 64460, "loss": 0.2423, "lr": 1.1309339125038785e-06, "epoch": 0.226497052435619, "percentage": 1.13, "elapsed_time": "0:01:14", "remaining_time": "1:48:42", "throughput": 5807.5, "total_tokens": 433920} {"current_steps": 735, "total_steps": 64460, "loss": 0.2535, "lr": 1.1386906608749613e-06, "epoch": 0.22804840210983557, "percentage": 1.14, "elapsed_time": "0:01:15", "remaining_time": "1:48:37", "throughput": 5806.87, "total_tokens": 436544} {"current_steps": 740, "total_steps": 64460, "loss": 0.2412, "lr": 1.146447409246044e-06, "epoch": 0.22959975178405212, "percentage": 1.15, "elapsed_time": "0:01:15", "remaining_time": "1:48:37", "throughput": 5810.71, "total_tokens": 439840} {"current_steps": 745, "total_steps": 64460, "loss": 0.2447, "lr": 1.154204157617127e-06, "epoch": 0.2311511014582687, "percentage": 1.16, "elapsed_time": "0:01:16", "remaining_time": "1:48:36", "throughput": 5812.96, "total_tokens": 442912} {"current_steps": 750, "total_steps": 64460, "loss": 0.2481, "lr": 1.1619609059882098e-06, "epoch": 0.23270245113248525, "percentage": 1.16, "elapsed_time": "0:01:16", "remaining_time": "1:48:37", "throughput": 5814.77, "total_tokens": 446144} {"current_steps": 755, "total_steps": 64460, "loss": 0.2684, "lr": 1.1697176543592926e-06, "epoch": 0.23425380080670183, "percentage": 1.17, "elapsed_time": "0:01:17", "remaining_time": "1:48:36", "throughput": 5810.88, "total_tokens": 448768} {"current_steps": 760, "total_steps": 64460, "loss": 0.2638, "lr": 1.1774744027303756e-06, "epoch": 0.2358051504809184, "percentage": 1.18, "elapsed_time": "0:01:17", "remaining_time": "1:48:43", "throughput": 5815.87, "total_tokens": 452640} {"current_steps": 765, "total_steps": 64460, "loss": 0.2464, "lr": 1.1852311511014584e-06, "epoch": 0.23735650015513496, "percentage": 1.19, "elapsed_time": "0:01:18", "remaining_time": "1:48:44", "throughput": 5817.58, "total_tokens": 455872} {"current_steps": 770, "total_steps": 64460, "loss": 0.246, "lr": 1.1929878994725411e-06, "epoch": 0.23890784982935154, "percentage": 1.19, "elapsed_time": "0:01:18", "remaining_time": "1:48:42", "throughput": 5816.12, "total_tokens": 458624} {"current_steps": 775, "total_steps": 64460, "loss": 0.2245, "lr": 1.2007446478436241e-06, "epoch": 0.24045919950356812, "percentage": 1.2, "elapsed_time": "0:01:19", "remaining_time": "1:48:37", "throughput": 5816.49, "total_tokens": 461312} {"current_steps": 780, "total_steps": 64460, "loss": 0.2393, "lr": 1.208501396214707e-06, "epoch": 0.24201054917778467, "percentage": 1.21, "elapsed_time": "0:01:19", "remaining_time": "1:48:32", "throughput": 5812.19, "total_tokens": 463616} {"current_steps": 785, "total_steps": 64460, "loss": 0.241, "lr": 1.2162581445857897e-06, "epoch": 0.24356189885200125, "percentage": 1.22, "elapsed_time": "0:01:20", "remaining_time": "1:48:29", "throughput": 5812.82, "total_tokens": 466464} {"current_steps": 790, "total_steps": 64460, "loss": 0.2541, "lr": 1.2240148929568727e-06, "epoch": 0.2451132485262178, "percentage": 1.23, "elapsed_time": "0:01:20", "remaining_time": "1:48:26", "throughput": 5809.4, "total_tokens": 469024} {"current_steps": 795, "total_steps": 64460, "loss": 0.2326, "lr": 1.2317716413279554e-06, "epoch": 0.24666459820043438, "percentage": 1.23, "elapsed_time": "0:01:21", "remaining_time": "1:48:23", "throughput": 5806.46, "total_tokens": 471520} {"current_steps": 800, "total_steps": 64460, "loss": 0.2409, "lr": 1.2395283896990382e-06, "epoch": 0.24821594787465096, "percentage": 1.24, "elapsed_time": "0:01:21", "remaining_time": "1:48:21", "throughput": 5804.55, "total_tokens": 474240} {"current_steps": 805, "total_steps": 64460, "loss": 0.2246, "lr": 1.247285138070121e-06, "epoch": 0.2497672975488675, "percentage": 1.25, "elapsed_time": "0:01:22", "remaining_time": "1:48:18", "throughput": 5805.44, "total_tokens": 477120} {"current_steps": 810, "total_steps": 64460, "loss": 0.2641, "lr": 1.255041886441204e-06, "epoch": 0.25131864722308406, "percentage": 1.26, "elapsed_time": "0:01:22", "remaining_time": "1:48:16", "throughput": 5803.55, "total_tokens": 479808} {"current_steps": 815, "total_steps": 64460, "loss": 0.264, "lr": 1.2627986348122867e-06, "epoch": 0.25286999689730066, "percentage": 1.26, "elapsed_time": "0:01:23", "remaining_time": "1:48:19", "throughput": 5804.79, "total_tokens": 483104} {"current_steps": 820, "total_steps": 64460, "loss": 0.2397, "lr": 1.2705553831833697e-06, "epoch": 0.2544213465715172, "percentage": 1.27, "elapsed_time": "0:01:23", "remaining_time": "1:48:13", "throughput": 5801.33, "total_tokens": 485376} {"current_steps": 825, "total_steps": 64460, "loss": 0.2461, "lr": 1.2783121315544525e-06, "epoch": 0.25597269624573377, "percentage": 1.28, "elapsed_time": "0:01:24", "remaining_time": "1:48:11", "throughput": 5804.51, "total_tokens": 488512} {"current_steps": 830, "total_steps": 64460, "loss": 0.2503, "lr": 1.2860688799255353e-06, "epoch": 0.2575240459199504, "percentage": 1.29, "elapsed_time": "0:01:24", "remaining_time": "1:48:14", "throughput": 5804.41, "total_tokens": 491712} {"current_steps": 835, "total_steps": 64460, "loss": 0.2347, "lr": 1.2938256282966182e-06, "epoch": 0.2590753955941669, "percentage": 1.3, "elapsed_time": "0:01:25", "remaining_time": "1:48:11", "throughput": 5803.29, "total_tokens": 494400} {"current_steps": 840, "total_steps": 64460, "loss": 0.3286, "lr": 1.301582376667701e-06, "epoch": 0.2606267452683835, "percentage": 1.3, "elapsed_time": "0:01:25", "remaining_time": "1:48:30", "throughput": 5814.29, "total_tokens": 499808} {"current_steps": 845, "total_steps": 64460, "loss": 0.2409, "lr": 1.3093391250387838e-06, "epoch": 0.2621780949426001, "percentage": 1.31, "elapsed_time": "0:01:26", "remaining_time": "1:48:33", "throughput": 5820.82, "total_tokens": 503648} {"current_steps": 850, "total_steps": 64460, "loss": 0.2522, "lr": 1.3170958734098666e-06, "epoch": 0.26372944461681663, "percentage": 1.32, "elapsed_time": "0:01:27", "remaining_time": "1:48:35", "throughput": 5823.59, "total_tokens": 507040} {"current_steps": 855, "total_steps": 64460, "loss": 0.2283, "lr": 1.3248526217809495e-06, "epoch": 0.2652807942910332, "percentage": 1.33, "elapsed_time": "0:01:27", "remaining_time": "1:48:32", "throughput": 5822.94, "total_tokens": 509760} {"current_steps": 860, "total_steps": 64460, "loss": 0.2292, "lr": 1.3326093701520323e-06, "epoch": 0.2668321439652498, "percentage": 1.33, "elapsed_time": "0:01:28", "remaining_time": "1:48:37", "throughput": 5821.2, "total_tokens": 512992} {"current_steps": 865, "total_steps": 64460, "loss": 0.2261, "lr": 1.340366118523115e-06, "epoch": 0.26838349363946634, "percentage": 1.34, "elapsed_time": "0:01:28", "remaining_time": "1:48:33", "throughput": 5820.57, "total_tokens": 515648} {"current_steps": 870, "total_steps": 64460, "loss": 0.2295, "lr": 1.348122866894198e-06, "epoch": 0.2699348433136829, "percentage": 1.35, "elapsed_time": "0:01:29", "remaining_time": "1:48:30", "throughput": 5819.17, "total_tokens": 518368} {"current_steps": 875, "total_steps": 64460, "loss": 0.2492, "lr": 1.3558796152652808e-06, "epoch": 0.2714861929878995, "percentage": 1.36, "elapsed_time": "0:01:29", "remaining_time": "1:48:33", "throughput": 5823.54, "total_tokens": 521952} {"current_steps": 880, "total_steps": 64460, "loss": 0.2231, "lr": 1.3636363636363636e-06, "epoch": 0.27303754266211605, "percentage": 1.37, "elapsed_time": "0:01:30", "remaining_time": "1:48:43", "throughput": 5832.96, "total_tokens": 526688} {"current_steps": 885, "total_steps": 64460, "loss": 0.2818, "lr": 1.3713931120074466e-06, "epoch": 0.2745888923363326, "percentage": 1.37, "elapsed_time": "0:01:30", "remaining_time": "1:48:53", "throughput": 5839.39, "total_tokens": 531104} {"current_steps": 890, "total_steps": 64460, "loss": 0.2431, "lr": 1.3791498603785294e-06, "epoch": 0.27614024201054915, "percentage": 1.38, "elapsed_time": "0:01:31", "remaining_time": "1:48:48", "throughput": 5836.43, "total_tokens": 533472} {"current_steps": 895, "total_steps": 64460, "loss": 0.2129, "lr": 1.3869066087496121e-06, "epoch": 0.27769159168476576, "percentage": 1.39, "elapsed_time": "0:01:31", "remaining_time": "1:48:47", "throughput": 5831.55, "total_tokens": 536000} {"current_steps": 900, "total_steps": 64460, "loss": 0.2338, "lr": 1.3946633571206951e-06, "epoch": 0.2792429413589823, "percentage": 1.4, "elapsed_time": "0:01:32", "remaining_time": "1:48:46", "throughput": 5824.51, "total_tokens": 538272} {"current_steps": 905, "total_steps": 64460, "loss": 0.2303, "lr": 1.402420105491778e-06, "epoch": 0.28079429103319886, "percentage": 1.4, "elapsed_time": "0:01:32", "remaining_time": "1:48:44", "throughput": 5823.69, "total_tokens": 541056} {"current_steps": 910, "total_steps": 64460, "loss": 0.2867, "lr": 1.4101768538628607e-06, "epoch": 0.28234564070741547, "percentage": 1.41, "elapsed_time": "0:01:33", "remaining_time": "1:48:43", "throughput": 5819.94, "total_tokens": 543616} {"current_steps": 915, "total_steps": 64460, "loss": 0.242, "lr": 1.4179336022339439e-06, "epoch": 0.283896990381632, "percentage": 1.42, "elapsed_time": "0:01:33", "remaining_time": "1:48:39", "throughput": 5816.29, "total_tokens": 546016} {"current_steps": 920, "total_steps": 64460, "loss": 0.2466, "lr": 1.4256903506050264e-06, "epoch": 0.28544834005584857, "percentage": 1.43, "elapsed_time": "0:01:34", "remaining_time": "1:48:35", "throughput": 5811.32, "total_tokens": 548192} {"current_steps": 925, "total_steps": 64460, "loss": 0.2557, "lr": 1.4334470989761092e-06, "epoch": 0.2869996897300652, "percentage": 1.43, "elapsed_time": "0:01:34", "remaining_time": "1:48:31", "throughput": 5811.77, "total_tokens": 550976} {"current_steps": 930, "total_steps": 64460, "loss": 0.2316, "lr": 1.441203847347192e-06, "epoch": 0.28855103940428173, "percentage": 1.44, "elapsed_time": "0:01:35", "remaining_time": "1:48:27", "throughput": 5810.62, "total_tokens": 553568} {"current_steps": 935, "total_steps": 64460, "loss": 0.2329, "lr": 1.4489605957182752e-06, "epoch": 0.2901023890784983, "percentage": 1.45, "elapsed_time": "0:01:35", "remaining_time": "1:48:31", "throughput": 5814.9, "total_tokens": 557280} {"current_steps": 940, "total_steps": 64460, "loss": 0.238, "lr": 1.456717344089358e-06, "epoch": 0.2916537387527149, "percentage": 1.46, "elapsed_time": "0:01:36", "remaining_time": "1:48:41", "throughput": 5819.87, "total_tokens": 561696} {"current_steps": 945, "total_steps": 64460, "loss": 0.2362, "lr": 1.4644740924604405e-06, "epoch": 0.29320508842693144, "percentage": 1.47, "elapsed_time": "0:01:37", "remaining_time": "1:48:39", "throughput": 5821.76, "total_tokens": 564736} {"current_steps": 950, "total_steps": 64460, "loss": 0.2275, "lr": 1.4722308408315237e-06, "epoch": 0.294756438101148, "percentage": 1.47, "elapsed_time": "0:01:37", "remaining_time": "1:48:39", "throughput": 5823.3, "total_tokens": 567872} {"current_steps": 955, "total_steps": 64460, "loss": 0.2568, "lr": 1.4799875892026065e-06, "epoch": 0.29630778777536454, "percentage": 1.48, "elapsed_time": "0:01:38", "remaining_time": "1:48:37", "throughput": 5824.27, "total_tokens": 570816} {"current_steps": 960, "total_steps": 64460, "loss": 0.2255, "lr": 1.4877443375736892e-06, "epoch": 0.29785913744958115, "percentage": 1.49, "elapsed_time": "0:01:38", "remaining_time": "1:48:33", "throughput": 5822.46, "total_tokens": 573344} {"current_steps": 965, "total_steps": 64460, "loss": 0.2325, "lr": 1.4955010859447722e-06, "epoch": 0.2994104871237977, "percentage": 1.5, "elapsed_time": "0:01:39", "remaining_time": "1:48:36", "throughput": 5824.08, "total_tokens": 576768} {"current_steps": 970, "total_steps": 64460, "loss": 0.2236, "lr": 1.503257834315855e-06, "epoch": 0.30096183679801425, "percentage": 1.5, "elapsed_time": "0:01:39", "remaining_time": "1:48:33", "throughput": 5823.75, "total_tokens": 579520} {"current_steps": 975, "total_steps": 64460, "loss": 0.2013, "lr": 1.5110145826869378e-06, "epoch": 0.30251318647223086, "percentage": 1.51, "elapsed_time": "0:01:40", "remaining_time": "1:48:34", "throughput": 5828.04, "total_tokens": 583136} {"current_steps": 980, "total_steps": 64460, "loss": 0.2766, "lr": 1.5187713310580207e-06, "epoch": 0.3040645361464474, "percentage": 1.52, "elapsed_time": "0:01:40", "remaining_time": "1:48:33", "throughput": 5828.64, "total_tokens": 586080} {"current_steps": 985, "total_steps": 64460, "loss": 0.3007, "lr": 1.5265280794291035e-06, "epoch": 0.30561588582066396, "percentage": 1.53, "elapsed_time": "0:01:41", "remaining_time": "1:48:31", "throughput": 5826.11, "total_tokens": 588704} {"current_steps": 990, "total_steps": 64460, "loss": 0.2586, "lr": 1.5342848278001863e-06, "epoch": 0.30716723549488056, "percentage": 1.54, "elapsed_time": "0:01:41", "remaining_time": "1:48:35", "throughput": 5828.22, "total_tokens": 592352} {"current_steps": 995, "total_steps": 64460, "loss": 0.248, "lr": 1.5420415761712693e-06, "epoch": 0.3087185851690971, "percentage": 1.54, "elapsed_time": "0:01:42", "remaining_time": "1:48:34", "throughput": 5829.92, "total_tokens": 595424} {"current_steps": 1000, "total_steps": 64460, "loss": 0.2307, "lr": 1.549798324542352e-06, "epoch": 0.31026993484331367, "percentage": 1.55, "elapsed_time": "0:01:42", "remaining_time": "1:48:33", "throughput": 5830.32, "total_tokens": 598400} {"current_steps": 1005, "total_steps": 64460, "loss": 0.2431, "lr": 1.5575550729134348e-06, "epoch": 0.3118212845175303, "percentage": 1.56, "elapsed_time": "0:01:43", "remaining_time": "1:48:40", "throughput": 5834.75, "total_tokens": 602592} {"current_steps": 1010, "total_steps": 64460, "loss": 0.243, "lr": 1.5653118212845176e-06, "epoch": 0.3133726341917468, "percentage": 1.57, "elapsed_time": "0:01:43", "remaining_time": "1:48:43", "throughput": 5836.84, "total_tokens": 606080} {"current_steps": 1015, "total_steps": 64460, "loss": 0.2287, "lr": 1.5730685696556006e-06, "epoch": 0.3149239838659634, "percentage": 1.57, "elapsed_time": "0:01:44", "remaining_time": "1:48:42", "throughput": 5840.03, "total_tokens": 609408} {"current_steps": 1020, "total_steps": 64460, "loss": 0.254, "lr": 1.5808253180266833e-06, "epoch": 0.31647533354018, "percentage": 1.58, "elapsed_time": "0:01:44", "remaining_time": "1:48:40", "throughput": 5840.1, "total_tokens": 612256} {"current_steps": 1025, "total_steps": 64460, "loss": 0.2326, "lr": 1.5885820663977661e-06, "epoch": 0.31802668321439653, "percentage": 1.59, "elapsed_time": "0:01:45", "remaining_time": "1:48:39", "throughput": 5842.12, "total_tokens": 615424} {"current_steps": 1030, "total_steps": 64460, "loss": 0.2304, "lr": 1.596338814768849e-06, "epoch": 0.3195780328886131, "percentage": 1.6, "elapsed_time": "0:01:45", "remaining_time": "1:48:39", "throughput": 5838.44, "total_tokens": 618048} {"current_steps": 1035, "total_steps": 64460, "loss": 0.2409, "lr": 1.6040955631399319e-06, "epoch": 0.32112938256282964, "percentage": 1.61, "elapsed_time": "0:01:46", "remaining_time": "1:48:49", "throughput": 5845.88, "total_tokens": 622880} {"current_steps": 1040, "total_steps": 64460, "loss": 0.233, "lr": 1.6118523115110146e-06, "epoch": 0.32268073223704624, "percentage": 1.61, "elapsed_time": "0:01:46", "remaining_time": "1:48:44", "throughput": 5842.35, "total_tokens": 625088} {"current_steps": 1045, "total_steps": 64460, "loss": 0.2372, "lr": 1.6196090598820976e-06, "epoch": 0.3242320819112628, "percentage": 1.62, "elapsed_time": "0:01:47", "remaining_time": "1:48:42", "throughput": 5843.1, "total_tokens": 628064} {"current_steps": 1050, "total_steps": 64460, "loss": 0.2355, "lr": 1.6273658082531804e-06, "epoch": 0.32578343158547934, "percentage": 1.63, "elapsed_time": "0:01:47", "remaining_time": "1:48:39", "throughput": 5841.66, "total_tokens": 630688} {"current_steps": 1055, "total_steps": 64460, "loss": 0.2273, "lr": 1.6351225566242632e-06, "epoch": 0.32733478125969595, "percentage": 1.64, "elapsed_time": "0:01:48", "remaining_time": "1:48:48", "throughput": 5846.48, "total_tokens": 635136} {"current_steps": 1060, "total_steps": 64460, "loss": 0.239, "lr": 1.6428793049953462e-06, "epoch": 0.3288861309339125, "percentage": 1.64, "elapsed_time": "0:01:49", "remaining_time": "1:48:45", "throughput": 5843.46, "total_tokens": 637536} {"current_steps": 1065, "total_steps": 64460, "loss": 0.2363, "lr": 1.650636053366429e-06, "epoch": 0.33043748060812905, "percentage": 1.65, "elapsed_time": "0:01:49", "remaining_time": "1:48:47", "throughput": 5847.4, "total_tokens": 641216} {"current_steps": 1070, "total_steps": 64460, "loss": 0.2167, "lr": 1.6583928017375117e-06, "epoch": 0.33198883028234566, "percentage": 1.66, "elapsed_time": "0:01:50", "remaining_time": "1:48:44", "throughput": 5847.32, "total_tokens": 644000} {"current_steps": 1075, "total_steps": 64460, "loss": 0.2365, "lr": 1.6661495501085947e-06, "epoch": 0.3335401799565622, "percentage": 1.67, "elapsed_time": "0:01:50", "remaining_time": "1:48:46", "throughput": 5847.58, "total_tokens": 647264} {"current_steps": 1080, "total_steps": 64460, "loss": 0.2133, "lr": 1.6739062984796775e-06, "epoch": 0.33509152963077876, "percentage": 1.68, "elapsed_time": "0:01:51", "remaining_time": "1:48:45", "throughput": 5845.68, "total_tokens": 650016} {"current_steps": 1085, "total_steps": 64460, "loss": 0.2252, "lr": 1.6816630468507602e-06, "epoch": 0.33664287930499537, "percentage": 1.68, "elapsed_time": "0:01:51", "remaining_time": "1:48:48", "throughput": 5845.56, "total_tokens": 653376} {"current_steps": 1090, "total_steps": 64460, "loss": 0.2224, "lr": 1.689419795221843e-06, "epoch": 0.3381942289792119, "percentage": 1.69, "elapsed_time": "0:01:52", "remaining_time": "1:48:57", "throughput": 5846.31, "total_tokens": 657376} {"current_steps": 1095, "total_steps": 64460, "loss": 0.2405, "lr": 1.697176543592926e-06, "epoch": 0.33974557865342847, "percentage": 1.7, "elapsed_time": "0:01:52", "remaining_time": "1:48:58", "throughput": 5848.48, "total_tokens": 660832} {"current_steps": 1100, "total_steps": 64460, "loss": 0.2433, "lr": 1.7049332919640088e-06, "epoch": 0.3412969283276451, "percentage": 1.71, "elapsed_time": "0:01:53", "remaining_time": "1:48:55", "throughput": 5848.41, "total_tokens": 663616} {"current_steps": 1105, "total_steps": 64460, "loss": 0.261, "lr": 1.7126900403350915e-06, "epoch": 0.34284827800186163, "percentage": 1.71, "elapsed_time": "0:01:53", "remaining_time": "1:48:53", "throughput": 5849.53, "total_tokens": 666528} {"current_steps": 1110, "total_steps": 64460, "loss": 0.279, "lr": 1.7204467887061745e-06, "epoch": 0.3443996276760782, "percentage": 1.72, "elapsed_time": "0:01:54", "remaining_time": "1:48:52", "throughput": 5851.92, "total_tokens": 669856} {"current_steps": 1115, "total_steps": 64460, "loss": 0.2245, "lr": 1.7282035370772573e-06, "epoch": 0.34595097735029473, "percentage": 1.73, "elapsed_time": "0:01:54", "remaining_time": "1:48:49", "throughput": 5852.13, "total_tokens": 672608} {"current_steps": 1120, "total_steps": 64460, "loss": 0.2739, "lr": 1.73596028544834e-06, "epoch": 0.34750232702451134, "percentage": 1.74, "elapsed_time": "0:01:55", "remaining_time": "1:48:51", "throughput": 5854.36, "total_tokens": 676160} {"current_steps": 1125, "total_steps": 64460, "loss": 0.2563, "lr": 1.743717033819423e-06, "epoch": 0.3490536766987279, "percentage": 1.75, "elapsed_time": "0:01:56", "remaining_time": "1:48:53", "throughput": 5858.99, "total_tokens": 679968} {"current_steps": 1130, "total_steps": 64460, "loss": 0.2405, "lr": 1.7514737821905058e-06, "epoch": 0.35060502637294444, "percentage": 1.75, "elapsed_time": "0:01:56", "remaining_time": "1:48:58", "throughput": 5861.25, "total_tokens": 683840} {"current_steps": 1135, "total_steps": 64460, "loss": 0.2369, "lr": 1.7592305305615886e-06, "epoch": 0.35215637604716105, "percentage": 1.76, "elapsed_time": "0:01:57", "remaining_time": "1:48:54", "throughput": 5862.02, "total_tokens": 686560} {"current_steps": 1140, "total_steps": 64460, "loss": 0.2442, "lr": 1.7669872789326718e-06, "epoch": 0.3537077257213776, "percentage": 1.77, "elapsed_time": "0:01:57", "remaining_time": "1:48:58", "throughput": 5864.44, "total_tokens": 690368} {"current_steps": 1145, "total_steps": 64460, "loss": 0.2482, "lr": 1.7747440273037543e-06, "epoch": 0.35525907539559415, "percentage": 1.78, "elapsed_time": "0:01:58", "remaining_time": "1:49:06", "throughput": 5868.84, "total_tokens": 694784} {"current_steps": 1150, "total_steps": 64460, "loss": 0.2263, "lr": 1.7825007756748371e-06, "epoch": 0.35681042506981075, "percentage": 1.78, "elapsed_time": "0:01:58", "remaining_time": "1:49:03", "throughput": 5867.32, "total_tokens": 697440} {"current_steps": 1155, "total_steps": 64460, "loss": 0.2533, "lr": 1.7902575240459199e-06, "epoch": 0.3583617747440273, "percentage": 1.79, "elapsed_time": "0:01:59", "remaining_time": "1:49:00", "throughput": 5867.44, "total_tokens": 700160} {"current_steps": 1160, "total_steps": 64460, "loss": 0.2512, "lr": 1.798014272417003e-06, "epoch": 0.35991312441824386, "percentage": 1.8, "elapsed_time": "0:01:59", "remaining_time": "1:49:05", "throughput": 5870.06, "total_tokens": 704064} {"current_steps": 1165, "total_steps": 64460, "loss": 0.2359, "lr": 1.8057710207880856e-06, "epoch": 0.36146447409246046, "percentage": 1.81, "elapsed_time": "0:02:00", "remaining_time": "1:49:11", "throughput": 5868.81, "total_tokens": 707648} {"current_steps": 1170, "total_steps": 64460, "loss": 0.2357, "lr": 1.8135277691591684e-06, "epoch": 0.363015823766677, "percentage": 1.82, "elapsed_time": "0:02:01", "remaining_time": "1:49:08", "throughput": 5870.26, "total_tokens": 710688} {"current_steps": 1175, "total_steps": 64460, "loss": 0.2287, "lr": 1.8212845175302516e-06, "epoch": 0.36456717344089357, "percentage": 1.82, "elapsed_time": "0:02:01", "remaining_time": "1:49:06", "throughput": 5870.39, "total_tokens": 713536} {"current_steps": 1180, "total_steps": 64460, "loss": 0.2452, "lr": 1.8290412659013344e-06, "epoch": 0.3661185231151102, "percentage": 1.83, "elapsed_time": "0:02:02", "remaining_time": "1:49:03", "throughput": 5867.83, "total_tokens": 716032} {"current_steps": 1185, "total_steps": 64460, "loss": 0.2283, "lr": 1.8367980142724172e-06, "epoch": 0.3676698727893267, "percentage": 1.84, "elapsed_time": "0:02:02", "remaining_time": "1:49:02", "throughput": 5866.16, "total_tokens": 718752} {"current_steps": 1190, "total_steps": 64460, "loss": 0.2302, "lr": 1.8445547626435001e-06, "epoch": 0.3692212224635433, "percentage": 1.85, "elapsed_time": "0:02:02", "remaining_time": "1:48:58", "throughput": 5863.86, "total_tokens": 721088} {"current_steps": 1195, "total_steps": 64460, "loss": 0.2277, "lr": 1.852311511014583e-06, "epoch": 0.3707725721377598, "percentage": 1.85, "elapsed_time": "0:02:03", "remaining_time": "1:48:55", "throughput": 5864.24, "total_tokens": 723968} {"current_steps": 1200, "total_steps": 64460, "loss": 0.2272, "lr": 1.8600682593856657e-06, "epoch": 0.37232392181197643, "percentage": 1.86, "elapsed_time": "0:02:03", "remaining_time": "1:48:54", "throughput": 5863.33, "total_tokens": 726784} {"current_steps": 1205, "total_steps": 64460, "loss": 0.2347, "lr": 1.8678250077567487e-06, "epoch": 0.373875271486193, "percentage": 1.87, "elapsed_time": "0:02:04", "remaining_time": "1:48:51", "throughput": 5861.47, "total_tokens": 729312} {"current_steps": 1210, "total_steps": 64460, "loss": 0.2168, "lr": 1.8755817561278314e-06, "epoch": 0.37542662116040953, "percentage": 1.88, "elapsed_time": "0:02:04", "remaining_time": "1:48:50", "throughput": 5863.15, "total_tokens": 732448} {"current_steps": 1215, "total_steps": 64460, "loss": 0.2543, "lr": 1.8833385044989142e-06, "epoch": 0.37697797083462614, "percentage": 1.88, "elapsed_time": "0:02:05", "remaining_time": "1:48:50", "throughput": 5864.8, "total_tokens": 735744} {"current_steps": 1220, "total_steps": 64460, "loss": 0.214, "lr": 1.8910952528699972e-06, "epoch": 0.3785293205088427, "percentage": 1.89, "elapsed_time": "0:02:05", "remaining_time": "1:48:48", "throughput": 5865.86, "total_tokens": 738752} {"current_steps": 1225, "total_steps": 64460, "loss": 0.2259, "lr": 1.89885200124108e-06, "epoch": 0.38008067018305924, "percentage": 1.9, "elapsed_time": "0:02:06", "remaining_time": "1:48:48", "throughput": 5865.81, "total_tokens": 741824} {"current_steps": 1230, "total_steps": 64460, "loss": 0.2424, "lr": 1.9066087496121627e-06, "epoch": 0.38163201985727585, "percentage": 1.91, "elapsed_time": "0:02:07", "remaining_time": "1:48:50", "throughput": 5867.17, "total_tokens": 745376} {"current_steps": 1235, "total_steps": 64460, "loss": 0.2268, "lr": 1.9143654979832455e-06, "epoch": 0.3831833695314924, "percentage": 1.92, "elapsed_time": "0:02:07", "remaining_time": "1:48:57", "throughput": 5868.99, "total_tokens": 749440} {"current_steps": 1240, "total_steps": 64460, "loss": 0.238, "lr": 1.9221222463543285e-06, "epoch": 0.38473471920570895, "percentage": 1.92, "elapsed_time": "0:02:08", "remaining_time": "1:48:55", "throughput": 5865.72, "total_tokens": 751936} {"current_steps": 1245, "total_steps": 64460, "loss": 0.2239, "lr": 1.929878994725411e-06, "epoch": 0.38628606887992556, "percentage": 1.93, "elapsed_time": "0:02:08", "remaining_time": "1:48:53", "throughput": 5863.49, "total_tokens": 754496} {"current_steps": 1250, "total_steps": 64460, "loss": 0.2312, "lr": 1.937635743096494e-06, "epoch": 0.3878374185541421, "percentage": 1.94, "elapsed_time": "0:02:09", "remaining_time": "1:48:52", "throughput": 5865.27, "total_tokens": 757632} {"current_steps": 1255, "total_steps": 64460, "loss": 0.2133, "lr": 1.945392491467577e-06, "epoch": 0.38938876822835866, "percentage": 1.95, "elapsed_time": "0:02:09", "remaining_time": "1:48:49", "throughput": 5864.57, "total_tokens": 760352} {"current_steps": 1260, "total_steps": 64460, "loss": 0.2338, "lr": 1.9531492398386596e-06, "epoch": 0.39094011790257527, "percentage": 1.95, "elapsed_time": "0:02:10", "remaining_time": "1:48:47", "throughput": 5863.92, "total_tokens": 763136} {"current_steps": 1265, "total_steps": 64460, "loss": 0.2832, "lr": 1.9609059882097426e-06, "epoch": 0.3924914675767918, "percentage": 1.96, "elapsed_time": "0:02:10", "remaining_time": "1:48:44", "throughput": 5861.02, "total_tokens": 765472} {"current_steps": 1270, "total_steps": 64460, "loss": 0.2272, "lr": 1.9686627365808256e-06, "epoch": 0.39404281725100837, "percentage": 1.97, "elapsed_time": "0:02:11", "remaining_time": "1:48:39", "throughput": 5856.85, "total_tokens": 767456} {"current_steps": 1275, "total_steps": 64460, "loss": 0.2482, "lr": 1.9764194849519085e-06, "epoch": 0.3955941669252249, "percentage": 1.98, "elapsed_time": "0:02:11", "remaining_time": "1:48:37", "throughput": 5855.8, "total_tokens": 770176} {"current_steps": 1280, "total_steps": 64460, "loss": 0.2277, "lr": 1.984176233322991e-06, "epoch": 0.39714551659944153, "percentage": 1.99, "elapsed_time": "0:02:12", "remaining_time": "1:48:35", "throughput": 5854.37, "total_tokens": 772800} {"current_steps": 1285, "total_steps": 64460, "loss": 0.2344, "lr": 1.991932981694074e-06, "epoch": 0.3986968662736581, "percentage": 1.99, "elapsed_time": "0:02:12", "remaining_time": "1:48:35", "throughput": 5851.92, "total_tokens": 775584} {"current_steps": 1290, "total_steps": 64460, "loss": 0.2373, "lr": 1.999689730065157e-06, "epoch": 0.40024821594787463, "percentage": 2.0, "elapsed_time": "0:02:13", "remaining_time": "1:48:38", "throughput": 5850.55, "total_tokens": 778816} {"current_steps": 1295, "total_steps": 64460, "loss": 0.1973, "lr": 2.0074464784362396e-06, "epoch": 0.40179956562209124, "percentage": 2.01, "elapsed_time": "0:02:13", "remaining_time": "1:48:36", "throughput": 5848.57, "total_tokens": 781376} {"current_steps": 1300, "total_steps": 64460, "loss": 0.2545, "lr": 2.0152032268073226e-06, "epoch": 0.4033509152963078, "percentage": 2.02, "elapsed_time": "0:02:14", "remaining_time": "1:48:40", "throughput": 5851.53, "total_tokens": 785280} {"current_steps": 1305, "total_steps": 64460, "loss": 0.2488, "lr": 2.0229599751784056e-06, "epoch": 0.40490226497052434, "percentage": 2.02, "elapsed_time": "0:02:14", "remaining_time": "1:48:37", "throughput": 5848.84, "total_tokens": 787712} {"current_steps": 1310, "total_steps": 64460, "loss": 0.2549, "lr": 2.030716723549488e-06, "epoch": 0.40645361464474095, "percentage": 2.03, "elapsed_time": "0:02:15", "remaining_time": "1:48:37", "throughput": 5846.81, "total_tokens": 790464} {"current_steps": 1315, "total_steps": 64460, "loss": 0.2497, "lr": 2.038473471920571e-06, "epoch": 0.4080049643189575, "percentage": 2.04, "elapsed_time": "0:02:15", "remaining_time": "1:48:36", "throughput": 5846.0, "total_tokens": 793312} {"current_steps": 1320, "total_steps": 64460, "loss": 0.2414, "lr": 2.046230220291654e-06, "epoch": 0.40955631399317405, "percentage": 2.05, "elapsed_time": "0:02:16", "remaining_time": "1:48:38", "throughput": 5848.92, "total_tokens": 797024} {"current_steps": 1325, "total_steps": 64460, "loss": 0.2368, "lr": 2.0539869686627367e-06, "epoch": 0.41110766366739065, "percentage": 2.06, "elapsed_time": "0:02:16", "remaining_time": "1:48:34", "throughput": 5847.33, "total_tokens": 799456} {"current_steps": 1330, "total_steps": 64460, "loss": 0.2364, "lr": 2.0617437170338197e-06, "epoch": 0.4126590133416072, "percentage": 2.06, "elapsed_time": "0:02:17", "remaining_time": "1:48:32", "throughput": 5847.7, "total_tokens": 802272} {"current_steps": 1335, "total_steps": 64460, "loss": 0.2367, "lr": 2.0695004654049026e-06, "epoch": 0.41421036301582376, "percentage": 2.07, "elapsed_time": "0:02:17", "remaining_time": "1:48:39", "throughput": 5850.36, "total_tokens": 806656} {"current_steps": 1340, "total_steps": 64460, "loss": 0.2326, "lr": 2.077257213775985e-06, "epoch": 0.4157617126900403, "percentage": 2.08, "elapsed_time": "0:02:18", "remaining_time": "1:48:37", "throughput": 5847.61, "total_tokens": 809056} {"current_steps": 1345, "total_steps": 64460, "loss": 0.2446, "lr": 2.085013962147068e-06, "epoch": 0.4173130623642569, "percentage": 2.09, "elapsed_time": "0:02:18", "remaining_time": "1:48:38", "throughput": 5846.98, "total_tokens": 812192} {"current_steps": 1350, "total_steps": 64460, "loss": 0.2355, "lr": 2.092770710518151e-06, "epoch": 0.41886441203847347, "percentage": 2.09, "elapsed_time": "0:02:19", "remaining_time": "1:48:37", "throughput": 5846.39, "total_tokens": 815104} {"current_steps": 1355, "total_steps": 64460, "loss": 0.2313, "lr": 2.1005274588892337e-06, "epoch": 0.42041576171269, "percentage": 2.1, "elapsed_time": "0:02:19", "remaining_time": "1:48:33", "throughput": 5842.62, "total_tokens": 817152} {"current_steps": 1360, "total_steps": 64460, "loss": 0.2506, "lr": 2.1082842072603167e-06, "epoch": 0.4219671113869066, "percentage": 2.11, "elapsed_time": "0:02:20", "remaining_time": "1:48:34", "throughput": 5840.97, "total_tokens": 820096} {"current_steps": 1365, "total_steps": 64460, "loss": 0.2309, "lr": 2.1160409556313997e-06, "epoch": 0.4235184610611232, "percentage": 2.12, "elapsed_time": "0:02:21", "remaining_time": "1:48:40", "throughput": 5845.0, "total_tokens": 824512} {"current_steps": 1370, "total_steps": 64460, "loss": 0.2073, "lr": 2.1237977040024823e-06, "epoch": 0.4250698107353397, "percentage": 2.13, "elapsed_time": "0:02:21", "remaining_time": "1:48:42", "throughput": 5844.31, "total_tokens": 827712} {"current_steps": 1375, "total_steps": 64460, "loss": 0.2202, "lr": 2.1315544523735652e-06, "epoch": 0.42662116040955633, "percentage": 2.13, "elapsed_time": "0:02:22", "remaining_time": "1:48:41", "throughput": 5845.3, "total_tokens": 830880} {"current_steps": 1380, "total_steps": 64460, "loss": 0.256, "lr": 2.1393112007446482e-06, "epoch": 0.4281725100837729, "percentage": 2.14, "elapsed_time": "0:02:22", "remaining_time": "1:48:39", "throughput": 5840.67, "total_tokens": 832992} {"current_steps": 1385, "total_steps": 64460, "loss": 0.2515, "lr": 2.147067949115731e-06, "epoch": 0.42972385975798943, "percentage": 2.15, "elapsed_time": "0:02:23", "remaining_time": "1:48:35", "throughput": 5839.44, "total_tokens": 835488} {"current_steps": 1390, "total_steps": 64460, "loss": 0.2384, "lr": 2.1548246974868138e-06, "epoch": 0.43127520943220604, "percentage": 2.16, "elapsed_time": "0:02:23", "remaining_time": "1:48:34", "throughput": 5839.42, "total_tokens": 838432} {"current_steps": 1395, "total_steps": 64460, "loss": 0.2498, "lr": 2.1625814458578963e-06, "epoch": 0.4328265591064226, "percentage": 2.16, "elapsed_time": "0:02:24", "remaining_time": "1:48:31", "throughput": 5836.22, "total_tokens": 840640} {"current_steps": 1400, "total_steps": 64460, "loss": 0.2233, "lr": 2.1703381942289793e-06, "epoch": 0.43437790878063914, "percentage": 2.17, "elapsed_time": "0:02:24", "remaining_time": "1:48:32", "throughput": 5837.46, "total_tokens": 843968} {"current_steps": 1405, "total_steps": 64460, "loss": 0.2285, "lr": 2.1780949426000623e-06, "epoch": 0.43592925845485575, "percentage": 2.18, "elapsed_time": "0:02:25", "remaining_time": "1:48:29", "throughput": 5836.2, "total_tokens": 846528} {"current_steps": 1410, "total_steps": 64460, "loss": 0.2359, "lr": 2.185851690971145e-06, "epoch": 0.4374806081290723, "percentage": 2.19, "elapsed_time": "0:02:25", "remaining_time": "1:48:30", "throughput": 5837.63, "total_tokens": 849888} {"current_steps": 1415, "total_steps": 64460, "loss": 0.2437, "lr": 2.193608439342228e-06, "epoch": 0.43903195780328885, "percentage": 2.2, "elapsed_time": "0:02:26", "remaining_time": "1:48:32", "throughput": 5841.15, "total_tokens": 853760} {"current_steps": 1420, "total_steps": 64460, "loss": 0.2225, "lr": 2.201365187713311e-06, "epoch": 0.4405833074775054, "percentage": 2.2, "elapsed_time": "0:02:26", "remaining_time": "1:48:28", "throughput": 5839.46, "total_tokens": 856064} {"current_steps": 1425, "total_steps": 64460, "loss": 0.2396, "lr": 2.2091219360843934e-06, "epoch": 0.442134657151722, "percentage": 2.21, "elapsed_time": "0:02:27", "remaining_time": "1:48:26", "throughput": 5840.72, "total_tokens": 859104} {"current_steps": 1430, "total_steps": 64460, "loss": 0.2335, "lr": 2.2168786844554764e-06, "epoch": 0.44368600682593856, "percentage": 2.22, "elapsed_time": "0:02:27", "remaining_time": "1:48:23", "throughput": 5837.89, "total_tokens": 861344} {"current_steps": 1435, "total_steps": 64460, "loss": 0.2324, "lr": 2.2246354328265594e-06, "epoch": 0.4452373565001551, "percentage": 2.23, "elapsed_time": "0:02:28", "remaining_time": "1:48:21", "throughput": 5837.14, "total_tokens": 864032} {"current_steps": 1440, "total_steps": 64460, "loss": 0.2307, "lr": 2.232392181197642e-06, "epoch": 0.4467887061743717, "percentage": 2.23, "elapsed_time": "0:02:28", "remaining_time": "1:48:23", "throughput": 5839.2, "total_tokens": 867744} {"current_steps": 1445, "total_steps": 64460, "loss": 0.2382, "lr": 2.240148929568725e-06, "epoch": 0.44834005584858827, "percentage": 2.24, "elapsed_time": "0:02:29", "remaining_time": "1:48:20", "throughput": 5837.81, "total_tokens": 870240} {"current_steps": 1450, "total_steps": 64460, "loss": 0.2316, "lr": 2.247905677939808e-06, "epoch": 0.4498914055228048, "percentage": 2.25, "elapsed_time": "0:02:29", "remaining_time": "1:48:25", "throughput": 5838.64, "total_tokens": 874016} {"current_steps": 1455, "total_steps": 64460, "loss": 0.2325, "lr": 2.2556624263108904e-06, "epoch": 0.45144275519702143, "percentage": 2.26, "elapsed_time": "0:02:30", "remaining_time": "1:48:27", "throughput": 5839.12, "total_tokens": 877536} {"current_steps": 1460, "total_steps": 64460, "loss": 0.2448, "lr": 2.2634191746819734e-06, "epoch": 0.452994104871238, "percentage": 2.26, "elapsed_time": "0:02:30", "remaining_time": "1:48:25", "throughput": 5837.84, "total_tokens": 880064} {"current_steps": 1465, "total_steps": 64460, "loss": 0.2467, "lr": 2.2711759230530564e-06, "epoch": 0.45454545454545453, "percentage": 2.27, "elapsed_time": "0:02:31", "remaining_time": "1:48:23", "throughput": 5837.27, "total_tokens": 882816} {"current_steps": 1470, "total_steps": 64460, "loss": 0.214, "lr": 2.278932671424139e-06, "epoch": 0.45609680421967114, "percentage": 2.28, "elapsed_time": "0:02:31", "remaining_time": "1:48:20", "throughput": 5837.0, "total_tokens": 885472} {"current_steps": 1475, "total_steps": 64460, "loss": 0.2447, "lr": 2.286689419795222e-06, "epoch": 0.4576481538938877, "percentage": 2.29, "elapsed_time": "0:02:32", "remaining_time": "1:48:19", "throughput": 5838.57, "total_tokens": 888736} {"current_steps": 1480, "total_steps": 64460, "loss": 0.2317, "lr": 2.294446168166305e-06, "epoch": 0.45919950356810424, "percentage": 2.3, "elapsed_time": "0:02:32", "remaining_time": "1:48:20", "throughput": 5838.28, "total_tokens": 891904} {"current_steps": 1485, "total_steps": 64460, "loss": 0.229, "lr": 2.3022029165373875e-06, "epoch": 0.46075085324232085, "percentage": 2.3, "elapsed_time": "0:02:33", "remaining_time": "1:48:17", "throughput": 5835.66, "total_tokens": 894112} {"current_steps": 1490, "total_steps": 64460, "loss": 0.2345, "lr": 2.3099596649084705e-06, "epoch": 0.4623022029165374, "percentage": 2.31, "elapsed_time": "0:02:33", "remaining_time": "1:48:15", "throughput": 5831.31, "total_tokens": 896320} {"current_steps": 1495, "total_steps": 64460, "loss": 0.2327, "lr": 2.3177164132795535e-06, "epoch": 0.46385355259075395, "percentage": 2.32, "elapsed_time": "0:02:34", "remaining_time": "1:48:18", "throughput": 5832.93, "total_tokens": 899936} {"current_steps": 1500, "total_steps": 64460, "loss": 0.2312, "lr": 2.3254731616506365e-06, "epoch": 0.4654049022649705, "percentage": 2.33, "elapsed_time": "0:02:34", "remaining_time": "1:48:15", "throughput": 5832.03, "total_tokens": 902592} {"current_steps": 1505, "total_steps": 64460, "loss": 0.254, "lr": 2.333229910021719e-06, "epoch": 0.4669562519391871, "percentage": 2.33, "elapsed_time": "0:02:35", "remaining_time": "1:48:15", "throughput": 5830.18, "total_tokens": 905312} {"current_steps": 1510, "total_steps": 64460, "loss": 0.2333, "lr": 2.340986658392802e-06, "epoch": 0.46850760161340366, "percentage": 2.34, "elapsed_time": "0:02:35", "remaining_time": "1:48:12", "throughput": 5828.31, "total_tokens": 907648} {"current_steps": 1515, "total_steps": 64460, "loss": 0.2324, "lr": 2.348743406763885e-06, "epoch": 0.4700589512876202, "percentage": 2.35, "elapsed_time": "0:02:36", "remaining_time": "1:48:14", "throughput": 5829.86, "total_tokens": 911264} {"current_steps": 1520, "total_steps": 64460, "loss": 0.2299, "lr": 2.3565001551349675e-06, "epoch": 0.4716103009618368, "percentage": 2.36, "elapsed_time": "0:02:36", "remaining_time": "1:48:12", "throughput": 5830.04, "total_tokens": 914144} {"current_steps": 1525, "total_steps": 64460, "loss": 0.2365, "lr": 2.3642569035060505e-06, "epoch": 0.47316165063605337, "percentage": 2.37, "elapsed_time": "0:02:37", "remaining_time": "1:48:10", "throughput": 5829.51, "total_tokens": 916832} {"current_steps": 1530, "total_steps": 64460, "loss": 0.2272, "lr": 2.3720136518771335e-06, "epoch": 0.4747130003102699, "percentage": 2.37, "elapsed_time": "0:02:37", "remaining_time": "1:48:07", "throughput": 5828.88, "total_tokens": 919424} {"current_steps": 1535, "total_steps": 64460, "loss": 0.2381, "lr": 2.379770400248216e-06, "epoch": 0.4762643499844865, "percentage": 2.38, "elapsed_time": "0:02:38", "remaining_time": "1:48:06", "throughput": 5828.98, "total_tokens": 922272} {"current_steps": 1540, "total_steps": 64460, "loss": 0.231, "lr": 2.387527148619299e-06, "epoch": 0.4778156996587031, "percentage": 2.39, "elapsed_time": "0:02:38", "remaining_time": "1:48:07", "throughput": 5830.61, "total_tokens": 925760} {"current_steps": 1545, "total_steps": 64460, "loss": 0.2391, "lr": 2.395283896990382e-06, "epoch": 0.4793670493329196, "percentage": 2.4, "elapsed_time": "0:02:39", "remaining_time": "1:48:08", "throughput": 5830.93, "total_tokens": 929024} {"current_steps": 1550, "total_steps": 64460, "loss": 0.2252, "lr": 2.4030406453614646e-06, "epoch": 0.48091839900713623, "percentage": 2.4, "elapsed_time": "0:02:39", "remaining_time": "1:48:07", "throughput": 5830.39, "total_tokens": 932000} {"current_steps": 1555, "total_steps": 64460, "loss": 0.2324, "lr": 2.4107973937325476e-06, "epoch": 0.4824697486813528, "percentage": 2.41, "elapsed_time": "0:02:40", "remaining_time": "1:48:07", "throughput": 5829.23, "total_tokens": 934784} {"current_steps": 1560, "total_steps": 64460, "loss": 0.2332, "lr": 2.4185541421036306e-06, "epoch": 0.48402109835556933, "percentage": 2.42, "elapsed_time": "0:02:40", "remaining_time": "1:48:06", "throughput": 5826.49, "total_tokens": 937344} {"current_steps": 1565, "total_steps": 64460, "loss": 0.2352, "lr": 2.426310890474713e-06, "epoch": 0.48557244802978594, "percentage": 2.43, "elapsed_time": "0:02:41", "remaining_time": "1:48:15", "throughput": 5829.79, "total_tokens": 942240} {"current_steps": 1570, "total_steps": 64460, "loss": 0.2321, "lr": 2.434067638845796e-06, "epoch": 0.4871237977040025, "percentage": 2.44, "elapsed_time": "0:02:42", "remaining_time": "1:48:14", "throughput": 5825.66, "total_tokens": 944448} {"current_steps": 1575, "total_steps": 64460, "loss": 0.2455, "lr": 2.441824387216879e-06, "epoch": 0.48867514737821904, "percentage": 2.44, "elapsed_time": "0:02:42", "remaining_time": "1:48:16", "throughput": 5827.79, "total_tokens": 948288} {"current_steps": 1580, "total_steps": 64460, "loss": 0.2395, "lr": 2.4495811355879617e-06, "epoch": 0.4902264970524356, "percentage": 2.45, "elapsed_time": "0:02:43", "remaining_time": "1:48:15", "throughput": 5822.65, "total_tokens": 950400} {"current_steps": 1585, "total_steps": 64460, "loss": 0.2405, "lr": 2.4573378839590446e-06, "epoch": 0.4917778467266522, "percentage": 2.46, "elapsed_time": "0:02:43", "remaining_time": "1:48:14", "throughput": 5820.8, "total_tokens": 952960} {"current_steps": 1590, "total_steps": 64460, "loss": 0.2257, "lr": 2.4650946323301276e-06, "epoch": 0.49332919640086875, "percentage": 2.47, "elapsed_time": "0:02:44", "remaining_time": "1:48:17", "throughput": 5821.69, "total_tokens": 956672} {"current_steps": 1595, "total_steps": 64460, "loss": 0.2247, "lr": 2.47285138070121e-06, "epoch": 0.4948805460750853, "percentage": 2.47, "elapsed_time": "0:02:44", "remaining_time": "1:48:21", "throughput": 5823.77, "total_tokens": 960672} {"current_steps": 1600, "total_steps": 64460, "loss": 0.2394, "lr": 2.480608129072293e-06, "epoch": 0.4964318957493019, "percentage": 2.48, "elapsed_time": "0:02:45", "remaining_time": "1:48:18", "throughput": 5823.83, "total_tokens": 963360} {"current_steps": 1605, "total_steps": 64460, "loss": 0.2421, "lr": 2.488364877443376e-06, "epoch": 0.49798324542351846, "percentage": 2.49, "elapsed_time": "0:02:45", "remaining_time": "1:48:17", "throughput": 5823.89, "total_tokens": 966336} {"current_steps": 1610, "total_steps": 64460, "loss": 0.251, "lr": 2.4961216258144587e-06, "epoch": 0.499534595097735, "percentage": 2.5, "elapsed_time": "0:02:46", "remaining_time": "1:48:16", "throughput": 5824.84, "total_tokens": 969408} {"current_steps": 1615, "total_steps": 64460, "loss": 0.2314, "lr": 2.5038783741855417e-06, "epoch": 0.5010859447719516, "percentage": 2.51, "elapsed_time": "0:02:46", "remaining_time": "1:48:18", "throughput": 5827.33, "total_tokens": 973152} {"current_steps": 1620, "total_steps": 64460, "loss": 0.2396, "lr": 2.5116351225566243e-06, "epoch": 0.5026372944461681, "percentage": 2.51, "elapsed_time": "0:02:47", "remaining_time": "1:48:16", "throughput": 5827.78, "total_tokens": 976096} {"current_steps": 1625, "total_steps": 64460, "loss": 0.2343, "lr": 2.5193918709277072e-06, "epoch": 0.5041886441203848, "percentage": 2.52, "elapsed_time": "0:02:47", "remaining_time": "1:48:14", "throughput": 5828.69, "total_tokens": 978912} {"current_steps": 1630, "total_steps": 64460, "loss": 0.2385, "lr": 2.5271486192987902e-06, "epoch": 0.5057399937946013, "percentage": 2.53, "elapsed_time": "0:02:48", "remaining_time": "1:48:14", "throughput": 5830.38, "total_tokens": 982336} {"current_steps": 1635, "total_steps": 64460, "loss": 0.233, "lr": 2.534905367669873e-06, "epoch": 0.5072913434688179, "percentage": 2.54, "elapsed_time": "0:02:49", "remaining_time": "1:48:14", "throughput": 5830.33, "total_tokens": 985440} {"current_steps": 1640, "total_steps": 64460, "loss": 0.2387, "lr": 2.5426621160409558e-06, "epoch": 0.5088426931430344, "percentage": 2.54, "elapsed_time": "0:02:49", "remaining_time": "1:48:12", "throughput": 5829.94, "total_tokens": 988192} {"current_steps": 1645, "total_steps": 64460, "loss": 0.2315, "lr": 2.5504188644120388e-06, "epoch": 0.510394042817251, "percentage": 2.55, "elapsed_time": "0:02:49", "remaining_time": "1:48:11", "throughput": 5831.01, "total_tokens": 991232} {"current_steps": 1650, "total_steps": 64460, "loss": 0.2302, "lr": 2.5581756127831213e-06, "epoch": 0.5119453924914675, "percentage": 2.56, "elapsed_time": "0:02:50", "remaining_time": "1:48:09", "throughput": 5826.31, "total_tokens": 993248} {"current_steps": 1655, "total_steps": 64460, "loss": 0.23, "lr": 2.5659323611542043e-06, "epoch": 0.5134967421656842, "percentage": 2.57, "elapsed_time": "0:02:50", "remaining_time": "1:48:08", "throughput": 5824.35, "total_tokens": 995808} {"current_steps": 1660, "total_steps": 64460, "loss": 0.2437, "lr": 2.573689109525287e-06, "epoch": 0.5150480918399007, "percentage": 2.58, "elapsed_time": "0:02:51", "remaining_time": "1:48:11", "throughput": 5825.18, "total_tokens": 999584} {"current_steps": 1665, "total_steps": 64460, "loss": 0.2372, "lr": 2.5814458578963703e-06, "epoch": 0.5165994415141173, "percentage": 2.58, "elapsed_time": "0:02:52", "remaining_time": "1:48:09", "throughput": 5825.25, "total_tokens": 1002336} {"current_steps": 1670, "total_steps": 64460, "loss": 0.2505, "lr": 2.589202606267453e-06, "epoch": 0.5181507911883338, "percentage": 2.59, "elapsed_time": "0:02:52", "remaining_time": "1:48:08", "throughput": 5824.74, "total_tokens": 1005152} {"current_steps": 1675, "total_steps": 64460, "loss": 0.2317, "lr": 2.596959354638536e-06, "epoch": 0.5197021408625504, "percentage": 2.6, "elapsed_time": "0:02:53", "remaining_time": "1:48:11", "throughput": 5826.54, "total_tokens": 1009024} {"current_steps": 1680, "total_steps": 64460, "loss": 0.2281, "lr": 2.6047161030096184e-06, "epoch": 0.521253490536767, "percentage": 2.61, "elapsed_time": "0:02:53", "remaining_time": "1:48:08", "throughput": 5824.79, "total_tokens": 1011328} {"current_steps": 1685, "total_steps": 64460, "loss": 0.2476, "lr": 2.6124728513807014e-06, "epoch": 0.5228048402109835, "percentage": 2.61, "elapsed_time": "0:02:54", "remaining_time": "1:48:14", "throughput": 5829.29, "total_tokens": 1016160} {"current_steps": 1690, "total_steps": 64460, "loss": 0.2408, "lr": 2.620229599751784e-06, "epoch": 0.5243561898852002, "percentage": 2.62, "elapsed_time": "0:02:54", "remaining_time": "1:48:12", "throughput": 5830.39, "total_tokens": 1019168} {"current_steps": 1695, "total_steps": 64460, "loss": 0.2411, "lr": 2.6279863481228673e-06, "epoch": 0.5259075395594167, "percentage": 2.63, "elapsed_time": "0:02:55", "remaining_time": "1:48:14", "throughput": 5831.61, "total_tokens": 1022720} {"current_steps": 1700, "total_steps": 64460, "loss": 0.2279, "lr": 2.6357430964939503e-06, "epoch": 0.5274588892336333, "percentage": 2.64, "elapsed_time": "0:02:55", "remaining_time": "1:48:13", "throughput": 5833.62, "total_tokens": 1026144} {"current_steps": 1705, "total_steps": 64460, "loss": 0.2356, "lr": 2.643499844865033e-06, "epoch": 0.5290102389078498, "percentage": 2.65, "elapsed_time": "0:02:56", "remaining_time": "1:48:20", "throughput": 5834.93, "total_tokens": 1030496} {"current_steps": 1710, "total_steps": 64460, "loss": 0.2263, "lr": 2.6512565932361154e-06, "epoch": 0.5305615885820664, "percentage": 2.65, "elapsed_time": "0:02:57", "remaining_time": "1:48:19", "throughput": 5834.07, "total_tokens": 1033312} {"current_steps": 1715, "total_steps": 64460, "loss": 0.2485, "lr": 2.6590133416071984e-06, "epoch": 0.5321129382562829, "percentage": 2.66, "elapsed_time": "0:02:57", "remaining_time": "1:48:19", "throughput": 5835.91, "total_tokens": 1036800} {"current_steps": 1720, "total_steps": 64460, "loss": 0.2256, "lr": 2.666770089978281e-06, "epoch": 0.5336642879304996, "percentage": 2.67, "elapsed_time": "0:02:58", "remaining_time": "1:48:17", "throughput": 5834.91, "total_tokens": 1039424} {"current_steps": 1725, "total_steps": 64460, "loss": 0.2266, "lr": 2.6745268383493644e-06, "epoch": 0.5352156376047161, "percentage": 2.68, "elapsed_time": "0:02:58", "remaining_time": "1:48:15", "throughput": 5835.7, "total_tokens": 1042304} {"current_steps": 1730, "total_steps": 64460, "loss": 0.2377, "lr": 2.6822835867204474e-06, "epoch": 0.5367669872789327, "percentage": 2.68, "elapsed_time": "0:02:59", "remaining_time": "1:48:15", "throughput": 5837.39, "total_tokens": 1045664} {"current_steps": 1735, "total_steps": 64460, "loss": 0.2251, "lr": 2.69004033509153e-06, "epoch": 0.5383183369531492, "percentage": 2.69, "elapsed_time": "0:02:59", "remaining_time": "1:48:14", "throughput": 5835.91, "total_tokens": 1048352} {"current_steps": 1740, "total_steps": 64460, "loss": 0.2342, "lr": 2.697797083462613e-06, "epoch": 0.5398696866273658, "percentage": 2.7, "elapsed_time": "0:03:00", "remaining_time": "1:48:16", "throughput": 5839.18, "total_tokens": 1052448} {"current_steps": 1745, "total_steps": 64460, "loss": 0.2379, "lr": 2.7055538318336955e-06, "epoch": 0.5414210363015823, "percentage": 2.71, "elapsed_time": "0:03:00", "remaining_time": "1:48:15", "throughput": 5839.6, "total_tokens": 1055328} {"current_steps": 1750, "total_steps": 64460, "loss": 0.2278, "lr": 2.713310580204778e-06, "epoch": 0.542972385975799, "percentage": 2.71, "elapsed_time": "0:03:01", "remaining_time": "1:48:13", "throughput": 5836.86, "total_tokens": 1057696} {"current_steps": 1755, "total_steps": 64460, "loss": 0.2332, "lr": 2.721067328575861e-06, "epoch": 0.5445237356500156, "percentage": 2.72, "elapsed_time": "0:03:01", "remaining_time": "1:48:17", "throughput": 5838.01, "total_tokens": 1061600} {"current_steps": 1760, "total_steps": 64460, "loss": 0.2298, "lr": 2.7288240769469444e-06, "epoch": 0.5460750853242321, "percentage": 2.73, "elapsed_time": "0:03:02", "remaining_time": "1:48:17", "throughput": 5837.22, "total_tokens": 1064576} {"current_steps": 1765, "total_steps": 64460, "loss": 0.2363, "lr": 2.736580825318027e-06, "epoch": 0.5476264349984487, "percentage": 2.74, "elapsed_time": "0:03:02", "remaining_time": "1:48:17", "throughput": 5838.8, "total_tokens": 1068096} {"current_steps": 1770, "total_steps": 64460, "loss": 0.2349, "lr": 2.74433757368911e-06, "epoch": 0.5491777846726652, "percentage": 2.75, "elapsed_time": "0:03:03", "remaining_time": "1:48:18", "throughput": 5838.41, "total_tokens": 1071264} {"current_steps": 1775, "total_steps": 64460, "loss": 0.2283, "lr": 2.7520943220601925e-06, "epoch": 0.5507291343468818, "percentage": 2.75, "elapsed_time": "0:03:04", "remaining_time": "1:48:18", "throughput": 5835.67, "total_tokens": 1073888} {"current_steps": 1780, "total_steps": 64460, "loss": 0.2406, "lr": 2.7598510704312755e-06, "epoch": 0.5522804840210983, "percentage": 2.76, "elapsed_time": "0:03:04", "remaining_time": "1:48:20", "throughput": 5837.22, "total_tokens": 1077536} {"current_steps": 1785, "total_steps": 64460, "loss": 0.2225, "lr": 2.767607818802358e-06, "epoch": 0.553831833695315, "percentage": 2.77, "elapsed_time": "0:03:05", "remaining_time": "1:48:19", "throughput": 5837.34, "total_tokens": 1080512} {"current_steps": 1790, "total_steps": 64460, "loss": 0.2498, "lr": 2.7753645671734415e-06, "epoch": 0.5553831833695315, "percentage": 2.78, "elapsed_time": "0:03:05", "remaining_time": "1:48:17", "throughput": 5835.68, "total_tokens": 1082944} {"current_steps": 1795, "total_steps": 64460, "loss": 0.2285, "lr": 2.783121315544524e-06, "epoch": 0.5569345330437481, "percentage": 2.78, "elapsed_time": "0:03:06", "remaining_time": "1:48:17", "throughput": 5837.35, "total_tokens": 1086432} {"current_steps": 1800, "total_steps": 64460, "loss": 0.2462, "lr": 2.790878063915607e-06, "epoch": 0.5584858827179646, "percentage": 2.79, "elapsed_time": "0:03:06", "remaining_time": "1:48:19", "throughput": 5838.86, "total_tokens": 1090176} {"current_steps": 1805, "total_steps": 64460, "loss": 0.2333, "lr": 2.7986348122866896e-06, "epoch": 0.5600372323921812, "percentage": 2.8, "elapsed_time": "0:03:07", "remaining_time": "1:48:17", "throughput": 5837.72, "total_tokens": 1092704} {"current_steps": 1810, "total_steps": 64460, "loss": 0.2295, "lr": 2.8063915606577726e-06, "epoch": 0.5615885820663977, "percentage": 2.81, "elapsed_time": "0:03:07", "remaining_time": "1:48:15", "throughput": 5836.28, "total_tokens": 1095264} {"current_steps": 1815, "total_steps": 64460, "loss": 0.2343, "lr": 2.814148309028855e-06, "epoch": 0.5631399317406144, "percentage": 2.82, "elapsed_time": "0:03:08", "remaining_time": "1:48:16", "throughput": 5834.91, "total_tokens": 1098336} {"current_steps": 1820, "total_steps": 64460, "loss": 0.2405, "lr": 2.821905057399938e-06, "epoch": 0.5646912814148309, "percentage": 2.82, "elapsed_time": "0:03:08", "remaining_time": "1:48:16", "throughput": 5835.52, "total_tokens": 1101504} {"current_steps": 1825, "total_steps": 64460, "loss": 0.2528, "lr": 2.829661805771021e-06, "epoch": 0.5662426310890475, "percentage": 2.83, "elapsed_time": "0:03:09", "remaining_time": "1:48:15", "throughput": 5835.36, "total_tokens": 1104320} {"current_steps": 1830, "total_steps": 64460, "loss": 0.2313, "lr": 2.837418554142104e-06, "epoch": 0.567793980763264, "percentage": 2.84, "elapsed_time": "0:03:09", "remaining_time": "1:48:12", "throughput": 5831.27, "total_tokens": 1106208} {"current_steps": 1835, "total_steps": 64460, "loss": 0.2305, "lr": 2.8451753025131866e-06, "epoch": 0.5693453304374806, "percentage": 2.85, "elapsed_time": "0:03:10", "remaining_time": "1:48:10", "throughput": 5831.2, "total_tokens": 1108992} {"current_steps": 1840, "total_steps": 64460, "loss": 0.2475, "lr": 2.8529320508842696e-06, "epoch": 0.5708966801116971, "percentage": 2.85, "elapsed_time": "0:03:10", "remaining_time": "1:48:11", "throughput": 5832.33, "total_tokens": 1112416} {"current_steps": 1845, "total_steps": 64460, "loss": 0.2329, "lr": 2.860688799255352e-06, "epoch": 0.5724480297859137, "percentage": 2.86, "elapsed_time": "0:03:11", "remaining_time": "1:48:15", "throughput": 5833.83, "total_tokens": 1116480} {"current_steps": 1850, "total_steps": 64460, "loss": 0.2339, "lr": 2.868445547626435e-06, "epoch": 0.5739993794601304, "percentage": 2.87, "elapsed_time": "0:03:11", "remaining_time": "1:48:13", "throughput": 5834.31, "total_tokens": 1119392} {"current_steps": 1855, "total_steps": 64460, "loss": 0.2351, "lr": 2.876202295997518e-06, "epoch": 0.5755507291343469, "percentage": 2.88, "elapsed_time": "0:03:12", "remaining_time": "1:48:12", "throughput": 5836.55, "total_tokens": 1122880} {"current_steps": 1860, "total_steps": 64460, "loss": 0.231, "lr": 2.883959044368601e-06, "epoch": 0.5771020788085635, "percentage": 2.89, "elapsed_time": "0:03:12", "remaining_time": "1:48:11", "throughput": 5836.32, "total_tokens": 1125760} {"current_steps": 1865, "total_steps": 64460, "loss": 0.2288, "lr": 2.8917157927396837e-06, "epoch": 0.57865342848278, "percentage": 2.89, "elapsed_time": "0:03:13", "remaining_time": "1:48:10", "throughput": 5837.13, "total_tokens": 1128736} {"current_steps": 1870, "total_steps": 64460, "loss": 0.2377, "lr": 2.8994725411107667e-06, "epoch": 0.5802047781569966, "percentage": 2.9, "elapsed_time": "0:03:13", "remaining_time": "1:48:10", "throughput": 5838.79, "total_tokens": 1132224} {"current_steps": 1875, "total_steps": 64460, "loss": 0.2372, "lr": 2.9072292894818492e-06, "epoch": 0.5817561278312131, "percentage": 2.91, "elapsed_time": "0:03:14", "remaining_time": "1:48:08", "throughput": 5838.14, "total_tokens": 1134816} {"current_steps": 1880, "total_steps": 64460, "loss": 0.2327, "lr": 2.9149860378529322e-06, "epoch": 0.5833074775054298, "percentage": 2.92, "elapsed_time": "0:03:14", "remaining_time": "1:48:07", "throughput": 5837.43, "total_tokens": 1137760} {"current_steps": 1885, "total_steps": 64460, "loss": 0.234, "lr": 2.9227427862240148e-06, "epoch": 0.5848588271796463, "percentage": 2.92, "elapsed_time": "0:03:15", "remaining_time": "1:48:07", "throughput": 5837.75, "total_tokens": 1140800} {"current_steps": 1890, "total_steps": 64460, "loss": 0.2311, "lr": 2.930499534595098e-06, "epoch": 0.5864101768538629, "percentage": 2.93, "elapsed_time": "0:03:15", "remaining_time": "1:48:05", "throughput": 5838.18, "total_tokens": 1143680} {"current_steps": 1895, "total_steps": 64460, "loss": 0.2325, "lr": 2.9382562829661807e-06, "epoch": 0.5879615265280794, "percentage": 2.94, "elapsed_time": "0:03:16", "remaining_time": "1:48:03", "throughput": 5837.14, "total_tokens": 1146240} {"current_steps": 1900, "total_steps": 64460, "loss": 0.2268, "lr": 2.9460130313372637e-06, "epoch": 0.589512876202296, "percentage": 2.95, "elapsed_time": "0:03:16", "remaining_time": "1:48:03", "throughput": 5837.54, "total_tokens": 1149504} {"current_steps": 1905, "total_steps": 64460, "loss": 0.2286, "lr": 2.9537697797083463e-06, "epoch": 0.5910642258765125, "percentage": 2.96, "elapsed_time": "0:03:17", "remaining_time": "1:48:00", "throughput": 5835.87, "total_tokens": 1151808} {"current_steps": 1910, "total_steps": 64460, "loss": 0.2319, "lr": 2.9615265280794293e-06, "epoch": 0.5926155755507291, "percentage": 2.96, "elapsed_time": "0:03:17", "remaining_time": "1:47:58", "throughput": 5835.65, "total_tokens": 1154464} {"current_steps": 1915, "total_steps": 64460, "loss": 0.2347, "lr": 2.969283276450512e-06, "epoch": 0.5941669252249457, "percentage": 2.97, "elapsed_time": "0:03:18", "remaining_time": "1:47:58", "throughput": 5836.12, "total_tokens": 1157696} {"current_steps": 1920, "total_steps": 64460, "loss": 0.2351, "lr": 2.9770400248215952e-06, "epoch": 0.5957182748991623, "percentage": 2.98, "elapsed_time": "0:03:18", "remaining_time": "1:47:59", "throughput": 5837.11, "total_tokens": 1161056} {"current_steps": 1925, "total_steps": 64460, "loss": 0.2319, "lr": 2.9847967731926782e-06, "epoch": 0.5972696245733788, "percentage": 2.99, "elapsed_time": "0:03:19", "remaining_time": "1:47:56", "throughput": 5836.85, "total_tokens": 1163744} {"current_steps": 1930, "total_steps": 64460, "loss": 0.2311, "lr": 2.9925535215637608e-06, "epoch": 0.5988209742475954, "percentage": 2.99, "elapsed_time": "0:03:19", "remaining_time": "1:47:57", "throughput": 5837.73, "total_tokens": 1167136} {"current_steps": 1935, "total_steps": 64460, "loss": 0.2341, "lr": 3.0003102699348433e-06, "epoch": 0.600372323921812, "percentage": 3.0, "elapsed_time": "0:03:20", "remaining_time": "1:47:55", "throughput": 5836.29, "total_tokens": 1169600} {"current_steps": 1940, "total_steps": 64460, "loss": 0.2496, "lr": 3.0080670183059263e-06, "epoch": 0.6019236735960285, "percentage": 3.01, "elapsed_time": "0:03:20", "remaining_time": "1:47:54", "throughput": 5835.87, "total_tokens": 1172384} {"current_steps": 1945, "total_steps": 64460, "loss": 0.2322, "lr": 3.015823766677009e-06, "epoch": 0.6034750232702452, "percentage": 3.02, "elapsed_time": "0:03:21", "remaining_time": "1:47:52", "throughput": 5835.85, "total_tokens": 1175168} {"current_steps": 1950, "total_steps": 64460, "loss": 0.232, "lr": 3.0235805150480923e-06, "epoch": 0.6050263729444617, "percentage": 3.03, "elapsed_time": "0:03:21", "remaining_time": "1:47:50", "throughput": 5834.52, "total_tokens": 1177664} {"current_steps": 1955, "total_steps": 64460, "loss": 0.226, "lr": 3.0313372634191753e-06, "epoch": 0.6065777226186783, "percentage": 3.03, "elapsed_time": "0:03:22", "remaining_time": "1:47:49", "throughput": 5834.69, "total_tokens": 1180736} {"current_steps": 1960, "total_steps": 64460, "loss": 0.223, "lr": 3.039094011790258e-06, "epoch": 0.6081290722928948, "percentage": 3.04, "elapsed_time": "0:03:22", "remaining_time": "1:47:47", "throughput": 5835.45, "total_tokens": 1183616} {"current_steps": 1965, "total_steps": 64460, "loss": 0.2396, "lr": 3.046850760161341e-06, "epoch": 0.6096804219671114, "percentage": 3.05, "elapsed_time": "0:03:23", "remaining_time": "1:47:45", "throughput": 5833.58, "total_tokens": 1185856} {"current_steps": 1970, "total_steps": 64460, "loss": 0.2204, "lr": 3.0546075085324234e-06, "epoch": 0.6112317716413279, "percentage": 3.06, "elapsed_time": "0:03:23", "remaining_time": "1:47:43", "throughput": 5832.36, "total_tokens": 1188416} {"current_steps": 1975, "total_steps": 64460, "loss": 0.2295, "lr": 3.062364256903506e-06, "epoch": 0.6127831213155446, "percentage": 3.06, "elapsed_time": "0:03:24", "remaining_time": "1:47:43", "throughput": 5833.84, "total_tokens": 1191744} {"current_steps": 1980, "total_steps": 64460, "loss": 0.2416, "lr": 3.070121005274589e-06, "epoch": 0.6143344709897611, "percentage": 3.07, "elapsed_time": "0:03:24", "remaining_time": "1:47:43", "throughput": 5834.17, "total_tokens": 1195072} {"current_steps": 1985, "total_steps": 64460, "loss": 0.2278, "lr": 3.0778777536456723e-06, "epoch": 0.6158858206639777, "percentage": 3.08, "elapsed_time": "0:03:25", "remaining_time": "1:47:41", "throughput": 5834.43, "total_tokens": 1197888} {"current_steps": 1990, "total_steps": 64460, "loss": 0.2437, "lr": 3.085634502016755e-06, "epoch": 0.6174371703381942, "percentage": 3.09, "elapsed_time": "0:03:25", "remaining_time": "1:47:40", "throughput": 5834.19, "total_tokens": 1200640} {"current_steps": 1995, "total_steps": 64460, "loss": 0.2328, "lr": 3.093391250387838e-06, "epoch": 0.6189885200124108, "percentage": 3.09, "elapsed_time": "0:03:26", "remaining_time": "1:47:38", "throughput": 5835.03, "total_tokens": 1203680} {"current_steps": 2000, "total_steps": 64460, "loss": 0.2339, "lr": 3.1011479987589204e-06, "epoch": 0.6205398696866273, "percentage": 3.1, "elapsed_time": "0:03:26", "remaining_time": "1:47:36", "throughput": 5834.04, "total_tokens": 1206080} {"current_steps": 2005, "total_steps": 64460, "loss": 0.2301, "lr": 3.1089047471300034e-06, "epoch": 0.6220912193608439, "percentage": 3.11, "elapsed_time": "0:03:27", "remaining_time": "1:47:33", "throughput": 5833.19, "total_tokens": 1208480} {"current_steps": 2010, "total_steps": 64460, "loss": 0.238, "lr": 3.116661495501086e-06, "epoch": 0.6236425690350605, "percentage": 3.12, "elapsed_time": "0:03:27", "remaining_time": "1:47:32", "throughput": 5834.25, "total_tokens": 1211616} {"current_steps": 2015, "total_steps": 64460, "loss": 0.2379, "lr": 3.1244182438721694e-06, "epoch": 0.6251939187092771, "percentage": 3.13, "elapsed_time": "0:03:28", "remaining_time": "1:47:31", "throughput": 5834.04, "total_tokens": 1214528} {"current_steps": 2020, "total_steps": 64460, "loss": 0.2335, "lr": 3.132174992243252e-06, "epoch": 0.6267452683834936, "percentage": 3.13, "elapsed_time": "0:03:28", "remaining_time": "1:47:31", "throughput": 5833.18, "total_tokens": 1217408} {"current_steps": 2025, "total_steps": 64460, "loss": 0.2393, "lr": 3.139931740614335e-06, "epoch": 0.6282966180577102, "percentage": 3.14, "elapsed_time": "0:03:29", "remaining_time": "1:47:30", "throughput": 5833.26, "total_tokens": 1220480} {"current_steps": 2030, "total_steps": 64460, "loss": 0.2392, "lr": 3.1476884889854175e-06, "epoch": 0.6298479677319268, "percentage": 3.15, "elapsed_time": "0:03:29", "remaining_time": "1:47:33", "throughput": 5835.24, "total_tokens": 1224544} {"current_steps": 2035, "total_steps": 64460, "loss": 0.2356, "lr": 3.1554452373565005e-06, "epoch": 0.6313993174061433, "percentage": 3.16, "elapsed_time": "0:03:30", "remaining_time": "1:47:37", "throughput": 5835.81, "total_tokens": 1228416} {"current_steps": 2040, "total_steps": 64460, "loss": 0.2347, "lr": 3.163201985727583e-06, "epoch": 0.63295066708036, "percentage": 3.16, "elapsed_time": "0:03:31", "remaining_time": "1:47:37", "throughput": 5835.65, "total_tokens": 1231584} {"current_steps": 2045, "total_steps": 64460, "loss": 0.2441, "lr": 3.170958734098666e-06, "epoch": 0.6345020167545765, "percentage": 3.17, "elapsed_time": "0:03:31", "remaining_time": "1:47:36", "throughput": 5835.78, "total_tokens": 1234432} {"current_steps": 2050, "total_steps": 64460, "loss": 0.2265, "lr": 3.178715482469749e-06, "epoch": 0.6360533664287931, "percentage": 3.18, "elapsed_time": "0:03:32", "remaining_time": "1:47:36", "throughput": 5837.55, "total_tokens": 1238112} {"current_steps": 2055, "total_steps": 64460, "loss": 0.2004, "lr": 3.186472230840832e-06, "epoch": 0.6376047161030096, "percentage": 3.19, "elapsed_time": "0:03:32", "remaining_time": "1:47:36", "throughput": 5838.72, "total_tokens": 1241312} {"current_steps": 2060, "total_steps": 64460, "loss": 0.2312, "lr": 3.1942289792119146e-06, "epoch": 0.6391560657772262, "percentage": 3.2, "elapsed_time": "0:03:33", "remaining_time": "1:47:36", "throughput": 5837.97, "total_tokens": 1244256} {"current_steps": 2065, "total_steps": 64460, "loss": 0.2837, "lr": 3.2019857275829975e-06, "epoch": 0.6407074154514427, "percentage": 3.2, "elapsed_time": "0:03:33", "remaining_time": "1:47:38", "throughput": 5840.23, "total_tokens": 1248256} {"current_steps": 2070, "total_steps": 64460, "loss": 0.2236, "lr": 3.20974247595408e-06, "epoch": 0.6422587651256593, "percentage": 3.21, "elapsed_time": "0:03:34", "remaining_time": "1:47:37", "throughput": 5841.46, "total_tokens": 1251456} {"current_steps": 2075, "total_steps": 64460, "loss": 0.261, "lr": 3.217499224325163e-06, "epoch": 0.6438101147998759, "percentage": 3.22, "elapsed_time": "0:03:34", "remaining_time": "1:47:35", "throughput": 5840.36, "total_tokens": 1254112} {"current_steps": 2080, "total_steps": 64460, "loss": 0.2581, "lr": 3.225255972696246e-06, "epoch": 0.6453614644740925, "percentage": 3.23, "elapsed_time": "0:03:35", "remaining_time": "1:47:36", "throughput": 5841.83, "total_tokens": 1257600} {"current_steps": 2085, "total_steps": 64460, "loss": 0.2391, "lr": 3.233012721067329e-06, "epoch": 0.646912814148309, "percentage": 3.23, "elapsed_time": "0:03:35", "remaining_time": "1:47:35", "throughput": 5842.7, "total_tokens": 1260832} {"current_steps": 2090, "total_steps": 64460, "loss": 0.214, "lr": 3.2407694694384116e-06, "epoch": 0.6484641638225256, "percentage": 3.24, "elapsed_time": "0:03:36", "remaining_time": "1:47:33", "throughput": 5843.22, "total_tokens": 1263648} {"current_steps": 2095, "total_steps": 64460, "loss": 0.21, "lr": 3.2485262178094946e-06, "epoch": 0.6500155134967421, "percentage": 3.25, "elapsed_time": "0:03:36", "remaining_time": "1:47:34", "throughput": 5843.15, "total_tokens": 1266976} {"current_steps": 2100, "total_steps": 64460, "loss": 0.2339, "lr": 3.256282966180577e-06, "epoch": 0.6515668631709587, "percentage": 3.26, "elapsed_time": "0:03:37", "remaining_time": "1:47:32", "throughput": 5842.03, "total_tokens": 1269376} {"current_steps": 2105, "total_steps": 64460, "loss": 0.2122, "lr": 3.26403971455166e-06, "epoch": 0.6531182128451753, "percentage": 3.27, "elapsed_time": "0:03:37", "remaining_time": "1:47:30", "throughput": 5842.89, "total_tokens": 1272352} {"current_steps": 2110, "total_steps": 64460, "loss": 0.2519, "lr": 3.2717964629227427e-06, "epoch": 0.6546695625193919, "percentage": 3.27, "elapsed_time": "0:03:38", "remaining_time": "1:47:29", "throughput": 5843.03, "total_tokens": 1275296} {"current_steps": 2115, "total_steps": 64460, "loss": 0.2381, "lr": 3.279553211293826e-06, "epoch": 0.6562209121936085, "percentage": 3.28, "elapsed_time": "0:03:38", "remaining_time": "1:47:29", "throughput": 5843.4, "total_tokens": 1278400} {"current_steps": 2120, "total_steps": 64460, "loss": 0.2312, "lr": 3.2873099596649087e-06, "epoch": 0.657772261867825, "percentage": 3.29, "elapsed_time": "0:03:39", "remaining_time": "1:47:28", "throughput": 5843.02, "total_tokens": 1281344} {"current_steps": 2125, "total_steps": 64460, "loss": 0.2309, "lr": 3.2950667080359916e-06, "epoch": 0.6593236115420416, "percentage": 3.3, "elapsed_time": "0:03:39", "remaining_time": "1:47:26", "throughput": 5842.66, "total_tokens": 1283968} {"current_steps": 2130, "total_steps": 64460, "loss": 0.2258, "lr": 3.302823456407074e-06, "epoch": 0.6608749612162581, "percentage": 3.3, "elapsed_time": "0:03:40", "remaining_time": "1:47:28", "throughput": 5844.25, "total_tokens": 1287904} {"current_steps": 2135, "total_steps": 64460, "loss": 0.2457, "lr": 3.310580204778157e-06, "epoch": 0.6624263108904748, "percentage": 3.31, "elapsed_time": "0:03:40", "remaining_time": "1:47:27", "throughput": 5845.27, "total_tokens": 1291104} {"current_steps": 2140, "total_steps": 64460, "loss": 0.2203, "lr": 3.3183369531492398e-06, "epoch": 0.6639776605646913, "percentage": 3.32, "elapsed_time": "0:03:41", "remaining_time": "1:47:26", "throughput": 5845.43, "total_tokens": 1293920} {"current_steps": 2145, "total_steps": 64460, "loss": 0.2152, "lr": 3.326093701520323e-06, "epoch": 0.6655290102389079, "percentage": 3.33, "elapsed_time": "0:03:42", "remaining_time": "1:47:32", "throughput": 5848.0, "total_tokens": 1298944} {"current_steps": 2150, "total_steps": 64460, "loss": 0.2283, "lr": 3.333850449891406e-06, "epoch": 0.6670803599131244, "percentage": 3.34, "elapsed_time": "0:03:42", "remaining_time": "1:47:37", "throughput": 5850.16, "total_tokens": 1303520} {"current_steps": 2155, "total_steps": 64460, "loss": 0.2005, "lr": 3.3416071982624887e-06, "epoch": 0.668631709587341, "percentage": 3.34, "elapsed_time": "0:03:43", "remaining_time": "1:47:38", "throughput": 5853.04, "total_tokens": 1307552} {"current_steps": 2160, "total_steps": 64460, "loss": 0.2569, "lr": 3.3493639466335713e-06, "epoch": 0.6701830592615575, "percentage": 3.35, "elapsed_time": "0:03:43", "remaining_time": "1:47:36", "throughput": 5852.42, "total_tokens": 1310048} {"current_steps": 2165, "total_steps": 64460, "loss": 0.266, "lr": 3.3571206950046542e-06, "epoch": 0.6717344089357741, "percentage": 3.36, "elapsed_time": "0:03:44", "remaining_time": "1:47:34", "throughput": 5852.91, "total_tokens": 1312896} {"current_steps": 2170, "total_steps": 64460, "loss": 0.216, "lr": 3.364877443375737e-06, "epoch": 0.6732857586099907, "percentage": 3.37, "elapsed_time": "0:03:44", "remaining_time": "1:47:35", "throughput": 5854.83, "total_tokens": 1316608} {"current_steps": 2175, "total_steps": 64460, "loss": 0.2428, "lr": 3.3726341917468202e-06, "epoch": 0.6748371082842073, "percentage": 3.37, "elapsed_time": "0:03:45", "remaining_time": "1:47:32", "throughput": 5852.38, "total_tokens": 1318752} {"current_steps": 2180, "total_steps": 64460, "loss": 0.2448, "lr": 3.380390940117903e-06, "epoch": 0.6763884579584238, "percentage": 3.38, "elapsed_time": "0:03:45", "remaining_time": "1:47:31", "throughput": 5852.44, "total_tokens": 1321568} {"current_steps": 2185, "total_steps": 64460, "loss": 0.2245, "lr": 3.3881476884889858e-06, "epoch": 0.6779398076326404, "percentage": 3.39, "elapsed_time": "0:03:46", "remaining_time": "1:47:31", "throughput": 5854.39, "total_tokens": 1325248} {"current_steps": 2190, "total_steps": 64460, "loss": 0.24, "lr": 3.3959044368600687e-06, "epoch": 0.6794911573068569, "percentage": 3.4, "elapsed_time": "0:03:46", "remaining_time": "1:47:30", "throughput": 5853.82, "total_tokens": 1327904} {"current_steps": 2195, "total_steps": 64460, "loss": 0.2219, "lr": 3.4036611852311513e-06, "epoch": 0.6810425069810735, "percentage": 3.41, "elapsed_time": "0:03:47", "remaining_time": "1:47:27", "throughput": 5853.25, "total_tokens": 1330464} {"current_steps": 2200, "total_steps": 64460, "loss": 0.2585, "lr": 3.411417933602234e-06, "epoch": 0.6825938566552902, "percentage": 3.41, "elapsed_time": "0:03:47", "remaining_time": "1:47:26", "throughput": 5852.73, "total_tokens": 1333216} {"current_steps": 2205, "total_steps": 64460, "loss": 0.2373, "lr": 3.419174681973317e-06, "epoch": 0.6841452063295067, "percentage": 3.42, "elapsed_time": "0:03:48", "remaining_time": "1:47:24", "throughput": 5852.45, "total_tokens": 1335776} {"current_steps": 2210, "total_steps": 64460, "loss": 0.2274, "lr": 3.4269314303444003e-06, "epoch": 0.6856965560037233, "percentage": 3.43, "elapsed_time": "0:03:48", "remaining_time": "1:47:21", "throughput": 5852.6, "total_tokens": 1338496} {"current_steps": 2215, "total_steps": 64460, "loss": 0.2391, "lr": 3.434688178715483e-06, "epoch": 0.6872479056779398, "percentage": 3.44, "elapsed_time": "0:03:49", "remaining_time": "1:47:19", "throughput": 5852.89, "total_tokens": 1341280} {"current_steps": 2220, "total_steps": 64460, "loss": 0.231, "lr": 3.442444927086566e-06, "epoch": 0.6887992553521564, "percentage": 3.44, "elapsed_time": "0:03:49", "remaining_time": "1:47:17", "throughput": 5851.56, "total_tokens": 1343680} {"current_steps": 2225, "total_steps": 64460, "loss": 0.2296, "lr": 3.4502016754576484e-06, "epoch": 0.6903506050263729, "percentage": 3.45, "elapsed_time": "0:03:50", "remaining_time": "1:47:17", "throughput": 5850.79, "total_tokens": 1346656} {"current_steps": 2230, "total_steps": 64460, "loss": 0.2338, "lr": 3.4579584238287313e-06, "epoch": 0.6919019547005895, "percentage": 3.46, "elapsed_time": "0:03:50", "remaining_time": "1:47:16", "throughput": 5848.17, "total_tokens": 1348800} {"current_steps": 2235, "total_steps": 64460, "loss": 0.2438, "lr": 3.465715172199814e-06, "epoch": 0.6934533043748061, "percentage": 3.47, "elapsed_time": "0:03:51", "remaining_time": "1:47:13", "throughput": 5847.38, "total_tokens": 1351200} {"current_steps": 2240, "total_steps": 64460, "loss": 0.2336, "lr": 3.4734719205708973e-06, "epoch": 0.6950046540490227, "percentage": 3.48, "elapsed_time": "0:03:51", "remaining_time": "1:47:10", "throughput": 5845.98, "total_tokens": 1353472} {"current_steps": 2245, "total_steps": 64460, "loss": 0.2247, "lr": 3.48122866894198e-06, "epoch": 0.6965560037232392, "percentage": 3.48, "elapsed_time": "0:03:51", "remaining_time": "1:47:08", "throughput": 5844.54, "total_tokens": 1355808} {"current_steps": 2250, "total_steps": 64460, "loss": 0.2415, "lr": 3.488985417313063e-06, "epoch": 0.6981073533974558, "percentage": 3.49, "elapsed_time": "0:03:52", "remaining_time": "1:47:06", "throughput": 5843.62, "total_tokens": 1358176} {"current_steps": 2255, "total_steps": 64460, "loss": 0.2296, "lr": 3.4967421656841454e-06, "epoch": 0.6996587030716723, "percentage": 3.5, "elapsed_time": "0:03:52", "remaining_time": "1:47:04", "throughput": 5842.74, "total_tokens": 1360736} {"current_steps": 2260, "total_steps": 64460, "loss": 0.2321, "lr": 3.5044989140552284e-06, "epoch": 0.7012100527458889, "percentage": 3.51, "elapsed_time": "0:03:53", "remaining_time": "1:47:02", "throughput": 5841.2, "total_tokens": 1363136} {"current_steps": 2265, "total_steps": 64460, "loss": 0.2303, "lr": 3.512255662426311e-06, "epoch": 0.7027614024201055, "percentage": 3.51, "elapsed_time": "0:03:53", "remaining_time": "1:47:00", "throughput": 5840.83, "total_tokens": 1365760} {"current_steps": 2270, "total_steps": 64460, "loss": 0.2432, "lr": 3.520012410797394e-06, "epoch": 0.7043127520943221, "percentage": 3.52, "elapsed_time": "0:03:54", "remaining_time": "1:47:00", "throughput": 5841.8, "total_tokens": 1369152} {"current_steps": 2275, "total_steps": 64460, "loss": 0.3713, "lr": 3.527769159168477e-06, "epoch": 0.7058641017685386, "percentage": 3.53, "elapsed_time": "0:03:55", "remaining_time": "1:47:06", "throughput": 5846.11, "total_tokens": 1374560} {"current_steps": 2280, "total_steps": 64460, "loss": 0.2393, "lr": 3.53552590753956e-06, "epoch": 0.7074154514427552, "percentage": 3.54, "elapsed_time": "0:03:55", "remaining_time": "1:47:06", "throughput": 5847.22, "total_tokens": 1377824} {"current_steps": 2285, "total_steps": 64460, "loss": 0.2371, "lr": 3.5432826559106425e-06, "epoch": 0.7089668011169717, "percentage": 3.54, "elapsed_time": "0:03:56", "remaining_time": "1:47:12", "throughput": 5850.5, "total_tokens": 1383072} {"current_steps": 2290, "total_steps": 64460, "loss": 0.232, "lr": 3.5510394042817255e-06, "epoch": 0.7105181507911883, "percentage": 3.55, "elapsed_time": "0:03:56", "remaining_time": "1:47:10", "throughput": 5849.07, "total_tokens": 1385504} {"current_steps": 2295, "total_steps": 64460, "loss": 0.2285, "lr": 3.558796152652808e-06, "epoch": 0.7120695004654048, "percentage": 3.56, "elapsed_time": "0:03:57", "remaining_time": "1:47:10", "throughput": 5848.52, "total_tokens": 1388352} {"current_steps": 2300, "total_steps": 64460, "loss": 0.241, "lr": 3.566552901023891e-06, "epoch": 0.7136208501396215, "percentage": 3.57, "elapsed_time": "0:03:57", "remaining_time": "1:47:08", "throughput": 5847.89, "total_tokens": 1390912} {"current_steps": 2305, "total_steps": 64460, "loss": 0.2286, "lr": 3.574309649394974e-06, "epoch": 0.7151721998138381, "percentage": 3.58, "elapsed_time": "0:03:58", "remaining_time": "1:47:08", "throughput": 5848.26, "total_tokens": 1394272} {"current_steps": 2310, "total_steps": 64460, "loss": 0.2315, "lr": 3.582066397766057e-06, "epoch": 0.7167235494880546, "percentage": 3.58, "elapsed_time": "0:03:58", "remaining_time": "1:47:07", "throughput": 5848.32, "total_tokens": 1397056} {"current_steps": 2315, "total_steps": 64460, "loss": 0.2263, "lr": 3.5898231461371395e-06, "epoch": 0.7182748991622712, "percentage": 3.59, "elapsed_time": "0:03:59", "remaining_time": "1:47:06", "throughput": 5847.98, "total_tokens": 1400000} {"current_steps": 2320, "total_steps": 64460, "loss": 0.2355, "lr": 3.5975798945082225e-06, "epoch": 0.7198262488364877, "percentage": 3.6, "elapsed_time": "0:03:59", "remaining_time": "1:47:07", "throughput": 5848.7, "total_tokens": 1403488} {"current_steps": 2325, "total_steps": 64460, "loss": 0.235, "lr": 3.605336642879305e-06, "epoch": 0.7213775985107043, "percentage": 3.61, "elapsed_time": "0:04:00", "remaining_time": "1:47:08", "throughput": 5851.03, "total_tokens": 1407424} {"current_steps": 2330, "total_steps": 64460, "loss": 0.2307, "lr": 3.613093391250388e-06, "epoch": 0.7229289481849209, "percentage": 3.61, "elapsed_time": "0:04:01", "remaining_time": "1:47:08", "throughput": 5850.8, "total_tokens": 1410560} {"current_steps": 2335, "total_steps": 64460, "loss": 0.224, "lr": 3.620850139621471e-06, "epoch": 0.7244802978591375, "percentage": 3.62, "elapsed_time": "0:04:01", "remaining_time": "1:47:07", "throughput": 5851.28, "total_tokens": 1413504} {"current_steps": 2340, "total_steps": 64460, "loss": 0.2411, "lr": 3.628606887992554e-06, "epoch": 0.726031647533354, "percentage": 3.63, "elapsed_time": "0:04:02", "remaining_time": "1:47:04", "throughput": 5850.32, "total_tokens": 1415904} {"current_steps": 2345, "total_steps": 64460, "loss": 0.2269, "lr": 3.6363636363636366e-06, "epoch": 0.7275829972075706, "percentage": 3.64, "elapsed_time": "0:04:02", "remaining_time": "1:47:03", "throughput": 5851.46, "total_tokens": 1419072} {"current_steps": 2350, "total_steps": 64460, "loss": 0.2295, "lr": 3.6441203847347196e-06, "epoch": 0.7291343468817871, "percentage": 3.65, "elapsed_time": "0:04:03", "remaining_time": "1:47:02", "throughput": 5852.33, "total_tokens": 1422208} {"current_steps": 2355, "total_steps": 64460, "loss": 0.2496, "lr": 3.651877133105802e-06, "epoch": 0.7306856965560037, "percentage": 3.65, "elapsed_time": "0:04:03", "remaining_time": "1:47:02", "throughput": 5852.87, "total_tokens": 1425376} {"current_steps": 2360, "total_steps": 64460, "loss": 0.227, "lr": 3.659633881476885e-06, "epoch": 0.7322370462302203, "percentage": 3.66, "elapsed_time": "0:04:03", "remaining_time": "1:46:59", "throughput": 5851.53, "total_tokens": 1427648} {"current_steps": 2365, "total_steps": 64460, "loss": 0.2456, "lr": 3.6673906298479677e-06, "epoch": 0.7337883959044369, "percentage": 3.67, "elapsed_time": "0:04:04", "remaining_time": "1:46:58", "throughput": 5849.29, "total_tokens": 1429824} {"current_steps": 2370, "total_steps": 64460, "loss": 0.2329, "lr": 3.675147378219051e-06, "epoch": 0.7353397455786534, "percentage": 3.68, "elapsed_time": "0:04:05", "remaining_time": "1:46:59", "throughput": 5848.94, "total_tokens": 1433088} {"current_steps": 2375, "total_steps": 64460, "loss": 0.2306, "lr": 3.682904126590134e-06, "epoch": 0.73689109525287, "percentage": 3.68, "elapsed_time": "0:04:05", "remaining_time": "1:46:57", "throughput": 5848.55, "total_tokens": 1435680} {"current_steps": 2380, "total_steps": 64460, "loss": 0.2369, "lr": 3.6906608749612166e-06, "epoch": 0.7384424449270865, "percentage": 3.69, "elapsed_time": "0:04:05", "remaining_time": "1:46:55", "throughput": 5848.79, "total_tokens": 1438464} {"current_steps": 2385, "total_steps": 64460, "loss": 0.2342, "lr": 3.698417623332299e-06, "epoch": 0.7399937946013031, "percentage": 3.7, "elapsed_time": "0:04:06", "remaining_time": "1:46:52", "throughput": 5848.33, "total_tokens": 1440992} {"current_steps": 2390, "total_steps": 64460, "loss": 0.2203, "lr": 3.706174371703382e-06, "epoch": 0.7415451442755197, "percentage": 3.71, "elapsed_time": "0:04:07", "remaining_time": "1:46:54", "throughput": 5849.63, "total_tokens": 1444896} {"current_steps": 2395, "total_steps": 64460, "loss": 0.2003, "lr": 3.7139311200744647e-06, "epoch": 0.7430964939497363, "percentage": 3.72, "elapsed_time": "0:04:07", "remaining_time": "1:46:52", "throughput": 5848.88, "total_tokens": 1447392} {"current_steps": 2400, "total_steps": 64460, "loss": 0.235, "lr": 3.721687868445548e-06, "epoch": 0.7446478436239529, "percentage": 3.72, "elapsed_time": "0:04:07", "remaining_time": "1:46:50", "throughput": 5847.73, "total_tokens": 1449728} {"current_steps": 2405, "total_steps": 64460, "loss": 0.1905, "lr": 3.729444616816631e-06, "epoch": 0.7461991932981694, "percentage": 3.73, "elapsed_time": "0:04:08", "remaining_time": "1:46:51", "throughput": 5849.13, "total_tokens": 1453440} {"current_steps": 2410, "total_steps": 64460, "loss": 0.2628, "lr": 3.7372013651877137e-06, "epoch": 0.747750542972386, "percentage": 3.74, "elapsed_time": "0:04:08", "remaining_time": "1:46:49", "throughput": 5847.28, "total_tokens": 1455584} {"current_steps": 2415, "total_steps": 64460, "loss": 0.2268, "lr": 3.7449581135587967e-06, "epoch": 0.7493018926466025, "percentage": 3.75, "elapsed_time": "0:04:09", "remaining_time": "1:46:47", "throughput": 5847.13, "total_tokens": 1458368} {"current_steps": 2420, "total_steps": 64460, "loss": 0.2531, "lr": 3.7527148619298792e-06, "epoch": 0.7508532423208191, "percentage": 3.75, "elapsed_time": "0:04:09", "remaining_time": "1:46:46", "throughput": 5847.71, "total_tokens": 1461376} {"current_steps": 2425, "total_steps": 64460, "loss": 0.2272, "lr": 3.7604716103009618e-06, "epoch": 0.7524045919950357, "percentage": 3.76, "elapsed_time": "0:04:10", "remaining_time": "1:46:48", "throughput": 5849.65, "total_tokens": 1465344} {"current_steps": 2430, "total_steps": 64460, "loss": 0.2571, "lr": 3.7682283586720448e-06, "epoch": 0.7539559416692523, "percentage": 3.77, "elapsed_time": "0:04:11", "remaining_time": "1:46:48", "throughput": 5850.71, "total_tokens": 1468928} {"current_steps": 2435, "total_steps": 64460, "loss": 0.247, "lr": 3.775985107043128e-06, "epoch": 0.7555072913434688, "percentage": 3.78, "elapsed_time": "0:04:11", "remaining_time": "1:46:47", "throughput": 5850.61, "total_tokens": 1471776} {"current_steps": 2440, "total_steps": 64460, "loss": 0.2302, "lr": 3.7837418554142107e-06, "epoch": 0.7570586410176854, "percentage": 3.79, "elapsed_time": "0:04:12", "remaining_time": "1:46:46", "throughput": 5850.05, "total_tokens": 1474592} {"current_steps": 2445, "total_steps": 64460, "loss": 0.2336, "lr": 3.7914986037852937e-06, "epoch": 0.7586099906919019, "percentage": 3.79, "elapsed_time": "0:04:12", "remaining_time": "1:46:46", "throughput": 5851.77, "total_tokens": 1478080} {"current_steps": 2450, "total_steps": 64460, "loss": 0.2534, "lr": 3.7992553521563763e-06, "epoch": 0.7601613403661185, "percentage": 3.8, "elapsed_time": "0:04:13", "remaining_time": "1:46:49", "throughput": 5854.29, "total_tokens": 1482560} {"current_steps": 2455, "total_steps": 64460, "loss": 0.2219, "lr": 3.8070121005274593e-06, "epoch": 0.761712690040335, "percentage": 3.81, "elapsed_time": "0:04:13", "remaining_time": "1:46:48", "throughput": 5854.56, "total_tokens": 1485536} {"current_steps": 2460, "total_steps": 64460, "loss": 0.2757, "lr": 3.814768848898542e-06, "epoch": 0.7632640397145517, "percentage": 3.82, "elapsed_time": "0:04:14", "remaining_time": "1:46:46", "throughput": 5854.47, "total_tokens": 1488224} {"current_steps": 2465, "total_steps": 64460, "loss": 0.2054, "lr": 3.822525597269625e-06, "epoch": 0.7648153893887683, "percentage": 3.82, "elapsed_time": "0:04:14", "remaining_time": "1:46:47", "throughput": 5855.5, "total_tokens": 1491840} {"current_steps": 2470, "total_steps": 64460, "loss": 0.2631, "lr": 3.830282345640708e-06, "epoch": 0.7663667390629848, "percentage": 3.83, "elapsed_time": "0:04:15", "remaining_time": "1:46:46", "throughput": 5855.99, "total_tokens": 1494880} {"current_steps": 2475, "total_steps": 64460, "loss": 0.232, "lr": 3.838039094011791e-06, "epoch": 0.7679180887372014, "percentage": 3.84, "elapsed_time": "0:04:15", "remaining_time": "1:46:45", "throughput": 5854.84, "total_tokens": 1497472} {"current_steps": 2480, "total_steps": 64460, "loss": 0.2384, "lr": 3.845795842382874e-06, "epoch": 0.7694694384114179, "percentage": 3.85, "elapsed_time": "0:04:16", "remaining_time": "1:46:45", "throughput": 5854.96, "total_tokens": 1500736} {"current_steps": 2485, "total_steps": 64460, "loss": 0.24, "lr": 3.853552590753956e-06, "epoch": 0.7710207880856345, "percentage": 3.86, "elapsed_time": "0:04:16", "remaining_time": "1:46:43", "throughput": 5853.99, "total_tokens": 1503072} {"current_steps": 2490, "total_steps": 64460, "loss": 0.231, "lr": 3.861309339125039e-06, "epoch": 0.7725721377598511, "percentage": 3.86, "elapsed_time": "0:04:17", "remaining_time": "1:46:42", "throughput": 5853.52, "total_tokens": 1505760} {"current_steps": 2495, "total_steps": 64460, "loss": 0.2364, "lr": 3.869066087496122e-06, "epoch": 0.7741234874340677, "percentage": 3.87, "elapsed_time": "0:04:17", "remaining_time": "1:46:43", "throughput": 5855.09, "total_tokens": 1509600} {"current_steps": 2500, "total_steps": 64460, "loss": 0.2164, "lr": 3.876822835867205e-06, "epoch": 0.7756748371082842, "percentage": 3.88, "elapsed_time": "0:04:18", "remaining_time": "1:46:42", "throughput": 5855.18, "total_tokens": 1512608} {"current_steps": 2505, "total_steps": 64460, "loss": 0.2372, "lr": 3.884579584238288e-06, "epoch": 0.7772261867825008, "percentage": 3.89, "elapsed_time": "0:04:18", "remaining_time": "1:46:41", "throughput": 5855.51, "total_tokens": 1515584} {"current_steps": 2510, "total_steps": 64460, "loss": 0.2374, "lr": 3.892336332609371e-06, "epoch": 0.7787775364567173, "percentage": 3.89, "elapsed_time": "0:04:19", "remaining_time": "1:46:39", "throughput": 5854.16, "total_tokens": 1518016} {"current_steps": 2515, "total_steps": 64460, "loss": 0.2591, "lr": 3.900093080980453e-06, "epoch": 0.7803288861309339, "percentage": 3.9, "elapsed_time": "0:04:19", "remaining_time": "1:46:41", "throughput": 5855.66, "total_tokens": 1521952} {"current_steps": 2520, "total_steps": 64460, "loss": 0.2434, "lr": 3.907849829351536e-06, "epoch": 0.7818802358051505, "percentage": 3.91, "elapsed_time": "0:04:20", "remaining_time": "1:46:40", "throughput": 5855.89, "total_tokens": 1524768} {"current_steps": 2525, "total_steps": 64460, "loss": 0.2288, "lr": 3.915606577722619e-06, "epoch": 0.7834315854793671, "percentage": 3.92, "elapsed_time": "0:04:20", "remaining_time": "1:46:39", "throughput": 5855.66, "total_tokens": 1527648} {"current_steps": 2530, "total_steps": 64460, "loss": 0.2464, "lr": 3.923363326093702e-06, "epoch": 0.7849829351535836, "percentage": 3.92, "elapsed_time": "0:04:21", "remaining_time": "1:46:37", "throughput": 5854.42, "total_tokens": 1529984} {"current_steps": 2535, "total_steps": 64460, "loss": 0.2385, "lr": 3.931120074464785e-06, "epoch": 0.7865342848278002, "percentage": 3.93, "elapsed_time": "0:04:21", "remaining_time": "1:46:36", "throughput": 5855.71, "total_tokens": 1533376} {"current_steps": 2540, "total_steps": 64460, "loss": 0.2299, "lr": 3.938876822835868e-06, "epoch": 0.7880856345020167, "percentage": 3.94, "elapsed_time": "0:04:22", "remaining_time": "1:46:38", "throughput": 5856.33, "total_tokens": 1537088} {"current_steps": 2545, "total_steps": 64460, "loss": 0.2485, "lr": 3.94663357120695e-06, "epoch": 0.7896369841762333, "percentage": 3.95, "elapsed_time": "0:04:22", "remaining_time": "1:46:35", "throughput": 5855.21, "total_tokens": 1539328} {"current_steps": 2550, "total_steps": 64460, "loss": 0.2356, "lr": 3.954390319578033e-06, "epoch": 0.7911883338504498, "percentage": 3.96, "elapsed_time": "0:04:23", "remaining_time": "1:46:35", "throughput": 5855.88, "total_tokens": 1542656} {"current_steps": 2555, "total_steps": 64460, "loss": 0.234, "lr": 3.962147067949116e-06, "epoch": 0.7927396835246665, "percentage": 3.96, "elapsed_time": "0:04:24", "remaining_time": "1:46:38", "throughput": 5858.43, "total_tokens": 1547136} {"current_steps": 2560, "total_steps": 64460, "loss": 0.2303, "lr": 3.969903816320199e-06, "epoch": 0.7942910331988831, "percentage": 3.97, "elapsed_time": "0:04:24", "remaining_time": "1:46:37", "throughput": 5858.25, "total_tokens": 1549920} {"current_steps": 2565, "total_steps": 64460, "loss": 0.2364, "lr": 3.977660564691282e-06, "epoch": 0.7958423828730996, "percentage": 3.98, "elapsed_time": "0:04:25", "remaining_time": "1:46:35", "throughput": 5858.28, "total_tokens": 1552736} {"current_steps": 2570, "total_steps": 64460, "loss": 0.2197, "lr": 3.985417313062365e-06, "epoch": 0.7973937325473162, "percentage": 3.99, "elapsed_time": "0:04:25", "remaining_time": "1:46:34", "throughput": 5856.85, "total_tokens": 1555072} {"current_steps": 2575, "total_steps": 64460, "loss": 0.2122, "lr": 3.993174061433447e-06, "epoch": 0.7989450822215327, "percentage": 3.99, "elapsed_time": "0:04:25", "remaining_time": "1:46:31", "throughput": 5856.28, "total_tokens": 1557504} {"current_steps": 2580, "total_steps": 64460, "loss": 0.196, "lr": 4.00093080980453e-06, "epoch": 0.8004964318957493, "percentage": 4.0, "elapsed_time": "0:04:26", "remaining_time": "1:46:29", "throughput": 5856.07, "total_tokens": 1560096} {"current_steps": 2585, "total_steps": 64460, "loss": 0.2891, "lr": 4.008687558175613e-06, "epoch": 0.8020477815699659, "percentage": 4.01, "elapsed_time": "0:04:26", "remaining_time": "1:46:28", "throughput": 5856.02, "total_tokens": 1562912} {"current_steps": 2590, "total_steps": 64460, "loss": 0.2386, "lr": 4.016444306546696e-06, "epoch": 0.8035991312441825, "percentage": 4.02, "elapsed_time": "0:04:27", "remaining_time": "1:46:26", "throughput": 5855.83, "total_tokens": 1565664} {"current_steps": 2595, "total_steps": 64460, "loss": 0.2505, "lr": 4.024201054917779e-06, "epoch": 0.805150480918399, "percentage": 4.03, "elapsed_time": "0:04:27", "remaining_time": "1:46:25", "throughput": 5855.62, "total_tokens": 1568384} {"current_steps": 2600, "total_steps": 64460, "loss": 0.2258, "lr": 4.031957803288862e-06, "epoch": 0.8067018305926156, "percentage": 4.03, "elapsed_time": "0:04:28", "remaining_time": "1:46:23", "throughput": 5855.14, "total_tokens": 1570912} {"current_steps": 2605, "total_steps": 64460, "loss": 0.2217, "lr": 4.039714551659944e-06, "epoch": 0.8082531802668321, "percentage": 4.04, "elapsed_time": "0:04:28", "remaining_time": "1:46:23", "throughput": 5855.88, "total_tokens": 1574176} {"current_steps": 2610, "total_steps": 64460, "loss": 0.2287, "lr": 4.047471300031027e-06, "epoch": 0.8098045299410487, "percentage": 4.05, "elapsed_time": "0:04:29", "remaining_time": "1:46:22", "throughput": 5855.72, "total_tokens": 1577152} {"current_steps": 2615, "total_steps": 64460, "loss": 0.2592, "lr": 4.05522804840211e-06, "epoch": 0.8113558796152652, "percentage": 4.06, "elapsed_time": "0:04:29", "remaining_time": "1:46:22", "throughput": 5855.65, "total_tokens": 1580192} {"current_steps": 2620, "total_steps": 64460, "loss": 0.2391, "lr": 4.062984796773193e-06, "epoch": 0.8129072292894819, "percentage": 4.06, "elapsed_time": "0:04:30", "remaining_time": "1:46:20", "throughput": 5856.02, "total_tokens": 1583072} {"current_steps": 2625, "total_steps": 64460, "loss": 0.2382, "lr": 4.070741545144276e-06, "epoch": 0.8144585789636984, "percentage": 4.07, "elapsed_time": "0:04:30", "remaining_time": "1:46:20", "throughput": 5855.89, "total_tokens": 1586048} {"current_steps": 2630, "total_steps": 64460, "loss": 0.239, "lr": 4.078498293515359e-06, "epoch": 0.816009928637915, "percentage": 4.08, "elapsed_time": "0:04:31", "remaining_time": "1:46:18", "throughput": 5854.01, "total_tokens": 1588384} {"current_steps": 2635, "total_steps": 64460, "loss": 0.2222, "lr": 4.086255041886442e-06, "epoch": 0.8175612783121315, "percentage": 4.09, "elapsed_time": "0:04:31", "remaining_time": "1:46:19", "throughput": 5854.26, "total_tokens": 1591712} {"current_steps": 2640, "total_steps": 64460, "loss": 0.2399, "lr": 4.094011790257524e-06, "epoch": 0.8191126279863481, "percentage": 4.1, "elapsed_time": "0:04:32", "remaining_time": "1:46:18", "throughput": 5853.79, "total_tokens": 1594464} {"current_steps": 2645, "total_steps": 64460, "loss": 0.2436, "lr": 4.101768538628607e-06, "epoch": 0.8206639776605646, "percentage": 4.1, "elapsed_time": "0:04:32", "remaining_time": "1:46:19", "throughput": 5853.8, "total_tokens": 1597920} {"current_steps": 2650, "total_steps": 64460, "loss": 0.2511, "lr": 4.10952528699969e-06, "epoch": 0.8222153273347813, "percentage": 4.11, "elapsed_time": "0:04:33", "remaining_time": "1:46:17", "throughput": 5852.69, "total_tokens": 1600320} {"current_steps": 2655, "total_steps": 64460, "loss": 0.223, "lr": 4.117282035370772e-06, "epoch": 0.8237666770089979, "percentage": 4.12, "elapsed_time": "0:04:33", "remaining_time": "1:46:15", "throughput": 5851.1, "total_tokens": 1602592} {"current_steps": 2660, "total_steps": 64460, "loss": 0.2346, "lr": 4.125038783741856e-06, "epoch": 0.8253180266832144, "percentage": 4.13, "elapsed_time": "0:04:34", "remaining_time": "1:46:16", "throughput": 5852.93, "total_tokens": 1606496} {"current_steps": 2665, "total_steps": 64460, "loss": 0.2314, "lr": 4.132795532112939e-06, "epoch": 0.826869376357431, "percentage": 4.13, "elapsed_time": "0:04:35", "remaining_time": "1:46:16", "throughput": 5854.17, "total_tokens": 1609984} {"current_steps": 2670, "total_steps": 64460, "loss": 0.237, "lr": 4.140552280484021e-06, "epoch": 0.8284207260316475, "percentage": 4.14, "elapsed_time": "0:04:35", "remaining_time": "1:46:14", "throughput": 5852.78, "total_tokens": 1612224} {"current_steps": 2675, "total_steps": 64460, "loss": 0.241, "lr": 4.148309028855104e-06, "epoch": 0.8299720757058641, "percentage": 4.15, "elapsed_time": "0:04:35", "remaining_time": "1:46:13", "throughput": 5853.2, "total_tokens": 1615264} {"current_steps": 2680, "total_steps": 64460, "loss": 0.2244, "lr": 4.156065777226187e-06, "epoch": 0.8315234253800806, "percentage": 4.16, "elapsed_time": "0:04:36", "remaining_time": "1:46:12", "throughput": 5853.52, "total_tokens": 1618048} {"current_steps": 2685, "total_steps": 64460, "loss": 0.235, "lr": 4.163822525597269e-06, "epoch": 0.8330747750542973, "percentage": 4.17, "elapsed_time": "0:04:36", "remaining_time": "1:46:10", "throughput": 5852.18, "total_tokens": 1620416} {"current_steps": 2690, "total_steps": 64460, "loss": 0.2382, "lr": 4.171579273968353e-06, "epoch": 0.8346261247285138, "percentage": 4.17, "elapsed_time": "0:04:37", "remaining_time": "1:46:10", "throughput": 5853.03, "total_tokens": 1623744} {"current_steps": 2695, "total_steps": 64460, "loss": 0.2411, "lr": 4.179336022339436e-06, "epoch": 0.8361774744027304, "percentage": 4.18, "elapsed_time": "0:04:37", "remaining_time": "1:46:10", "throughput": 5853.81, "total_tokens": 1627168} {"current_steps": 2700, "total_steps": 64460, "loss": 0.2363, "lr": 4.187092770710518e-06, "epoch": 0.8377288240769469, "percentage": 4.19, "elapsed_time": "0:04:38", "remaining_time": "1:46:09", "throughput": 5853.46, "total_tokens": 1629888} {"current_steps": 2705, "total_steps": 64460, "loss": 0.2245, "lr": 4.194849519081601e-06, "epoch": 0.8392801737511635, "percentage": 4.2, "elapsed_time": "0:04:38", "remaining_time": "1:46:08", "throughput": 5854.46, "total_tokens": 1633152} {"current_steps": 2710, "total_steps": 64460, "loss": 0.2358, "lr": 4.202606267452684e-06, "epoch": 0.84083152342538, "percentage": 4.2, "elapsed_time": "0:04:39", "remaining_time": "1:46:07", "throughput": 5853.01, "total_tokens": 1635488} {"current_steps": 2715, "total_steps": 64460, "loss": 0.2336, "lr": 4.210363015823767e-06, "epoch": 0.8423828730995967, "percentage": 4.21, "elapsed_time": "0:04:39", "remaining_time": "1:46:06", "throughput": 5852.45, "total_tokens": 1638272} {"current_steps": 2720, "total_steps": 64460, "loss": 0.233, "lr": 4.218119764194849e-06, "epoch": 0.8439342227738132, "percentage": 4.22, "elapsed_time": "0:04:40", "remaining_time": "1:46:07", "throughput": 5852.15, "total_tokens": 1641632} {"current_steps": 2725, "total_steps": 64460, "loss": 0.238, "lr": 4.225876512565933e-06, "epoch": 0.8454855724480298, "percentage": 4.23, "elapsed_time": "0:04:40", "remaining_time": "1:46:05", "throughput": 5852.18, "total_tokens": 1644384} {"current_steps": 2730, "total_steps": 64460, "loss": 0.2265, "lr": 4.233633260937015e-06, "epoch": 0.8470369221222463, "percentage": 4.24, "elapsed_time": "0:04:41", "remaining_time": "1:46:03", "throughput": 5850.92, "total_tokens": 1646688} {"current_steps": 2735, "total_steps": 64460, "loss": 0.2338, "lr": 4.241390009308098e-06, "epoch": 0.8485882717964629, "percentage": 4.24, "elapsed_time": "0:04:42", "remaining_time": "1:46:05", "throughput": 5851.76, "total_tokens": 1650400} {"current_steps": 2740, "total_steps": 64460, "loss": 0.2265, "lr": 4.249146757679181e-06, "epoch": 0.8501396214706795, "percentage": 4.25, "elapsed_time": "0:04:42", "remaining_time": "1:46:03", "throughput": 5851.84, "total_tokens": 1653216} {"current_steps": 2745, "total_steps": 64460, "loss": 0.245, "lr": 4.256903506050264e-06, "epoch": 0.8516909711448961, "percentage": 4.26, "elapsed_time": "0:04:42", "remaining_time": "1:46:01", "throughput": 5850.89, "total_tokens": 1655616} {"current_steps": 2750, "total_steps": 64460, "loss": 0.2276, "lr": 4.264660254421346e-06, "epoch": 0.8532423208191127, "percentage": 4.27, "elapsed_time": "0:04:43", "remaining_time": "1:46:09", "throughput": 5854.43, "total_tokens": 1661664} {"current_steps": 2755, "total_steps": 64460, "loss": 0.2382, "lr": 4.27241700279243e-06, "epoch": 0.8547936704933292, "percentage": 4.27, "elapsed_time": "0:04:44", "remaining_time": "1:46:08", "throughput": 5854.39, "total_tokens": 1664512} {"current_steps": 2760, "total_steps": 64460, "loss": 0.2309, "lr": 4.280173751163512e-06, "epoch": 0.8563450201675458, "percentage": 4.28, "elapsed_time": "0:04:44", "remaining_time": "1:46:07", "throughput": 5854.1, "total_tokens": 1667328} {"current_steps": 2765, "total_steps": 64460, "loss": 0.2325, "lr": 4.287930499534595e-06, "epoch": 0.8578963698417623, "percentage": 4.29, "elapsed_time": "0:04:45", "remaining_time": "1:46:07", "throughput": 5855.87, "total_tokens": 1671136} {"current_steps": 2770, "total_steps": 64460, "loss": 0.2267, "lr": 4.295687247905678e-06, "epoch": 0.8594477195159789, "percentage": 4.3, "elapsed_time": "0:04:45", "remaining_time": "1:46:06", "throughput": 5856.31, "total_tokens": 1674112} {"current_steps": 2775, "total_steps": 64460, "loss": 0.2488, "lr": 4.303443996276761e-06, "epoch": 0.8609990691901954, "percentage": 4.3, "elapsed_time": "0:04:46", "remaining_time": "1:46:05", "throughput": 5856.37, "total_tokens": 1676992} {"current_steps": 2780, "total_steps": 64460, "loss": 0.2277, "lr": 4.3112007446478435e-06, "epoch": 0.8625504188644121, "percentage": 4.31, "elapsed_time": "0:04:46", "remaining_time": "1:46:04", "throughput": 5855.8, "total_tokens": 1679648} {"current_steps": 2785, "total_steps": 64460, "loss": 0.2394, "lr": 4.318957493018927e-06, "epoch": 0.8641017685386286, "percentage": 4.32, "elapsed_time": "0:04:47", "remaining_time": "1:46:03", "throughput": 5856.45, "total_tokens": 1682944} {"current_steps": 2790, "total_steps": 64460, "loss": 0.2359, "lr": 4.3267142413900094e-06, "epoch": 0.8656531182128452, "percentage": 4.33, "elapsed_time": "0:04:47", "remaining_time": "1:46:03", "throughput": 5857.39, "total_tokens": 1686176} {"current_steps": 2795, "total_steps": 64460, "loss": 0.2344, "lr": 4.3344709897610924e-06, "epoch": 0.8672044678870617, "percentage": 4.34, "elapsed_time": "0:04:48", "remaining_time": "1:46:02", "throughput": 5857.65, "total_tokens": 1689120} {"current_steps": 2800, "total_steps": 64460, "loss": 0.2319, "lr": 4.342227738132175e-06, "epoch": 0.8687558175612783, "percentage": 4.34, "elapsed_time": "0:04:48", "remaining_time": "1:46:00", "throughput": 5856.78, "total_tokens": 1691552} {"current_steps": 2805, "total_steps": 64460, "loss": 0.2315, "lr": 4.349984486503258e-06, "epoch": 0.8703071672354948, "percentage": 4.35, "elapsed_time": "0:04:49", "remaining_time": "1:46:00", "throughput": 5857.87, "total_tokens": 1695040} {"current_steps": 2810, "total_steps": 64460, "loss": 0.2305, "lr": 4.3577412348743405e-06, "epoch": 0.8718585169097115, "percentage": 4.36, "elapsed_time": "0:04:49", "remaining_time": "1:45:59", "throughput": 5858.71, "total_tokens": 1698304} {"current_steps": 2815, "total_steps": 64460, "loss": 0.2318, "lr": 4.3654979832454235e-06, "epoch": 0.873409866583928, "percentage": 4.37, "elapsed_time": "0:04:50", "remaining_time": "1:45:58", "throughput": 5858.6, "total_tokens": 1701216} {"current_steps": 2820, "total_steps": 64460, "loss": 0.2278, "lr": 4.373254731616507e-06, "epoch": 0.8749612162581446, "percentage": 4.37, "elapsed_time": "0:04:50", "remaining_time": "1:45:57", "throughput": 5856.54, "total_tokens": 1703360} {"current_steps": 2825, "total_steps": 64460, "loss": 0.2326, "lr": 4.3810114799875895e-06, "epoch": 0.8765125659323612, "percentage": 4.38, "elapsed_time": "0:04:51", "remaining_time": "1:45:56", "throughput": 5855.43, "total_tokens": 1706048} {"current_steps": 2830, "total_steps": 64460, "loss": 0.2287, "lr": 4.3887682283586725e-06, "epoch": 0.8780639156065777, "percentage": 4.39, "elapsed_time": "0:04:51", "remaining_time": "1:45:56", "throughput": 5855.76, "total_tokens": 1709248} {"current_steps": 2835, "total_steps": 64460, "loss": 0.2346, "lr": 4.3965249767297554e-06, "epoch": 0.8796152652807943, "percentage": 4.4, "elapsed_time": "0:04:52", "remaining_time": "1:45:57", "throughput": 5856.42, "total_tokens": 1712736} {"current_steps": 2840, "total_steps": 64460, "loss": 0.2365, "lr": 4.404281725100838e-06, "epoch": 0.8811666149550108, "percentage": 4.41, "elapsed_time": "0:04:52", "remaining_time": "1:45:55", "throughput": 5855.5, "total_tokens": 1715232} {"current_steps": 2845, "total_steps": 64460, "loss": 0.2307, "lr": 4.4120384734719206e-06, "epoch": 0.8827179646292275, "percentage": 4.41, "elapsed_time": "0:04:53", "remaining_time": "1:45:56", "throughput": 5856.08, "total_tokens": 1718656} {"current_steps": 2850, "total_steps": 64460, "loss": 0.2229, "lr": 4.419795221843004e-06, "epoch": 0.884269314303444, "percentage": 4.42, "elapsed_time": "0:04:53", "remaining_time": "1:45:54", "throughput": 5856.13, "total_tokens": 1721376} {"current_steps": 2855, "total_steps": 64460, "loss": 0.2436, "lr": 4.4275519702140865e-06, "epoch": 0.8858206639776606, "percentage": 4.43, "elapsed_time": "0:04:54", "remaining_time": "1:45:53", "throughput": 5855.91, "total_tokens": 1724288} {"current_steps": 2860, "total_steps": 64460, "loss": 0.2441, "lr": 4.4353087185851695e-06, "epoch": 0.8873720136518771, "percentage": 4.44, "elapsed_time": "0:04:54", "remaining_time": "1:45:52", "throughput": 5855.83, "total_tokens": 1727232} {"current_steps": 2865, "total_steps": 64460, "loss": 0.2362, "lr": 4.4430654669562525e-06, "epoch": 0.8889233633260937, "percentage": 4.44, "elapsed_time": "0:04:55", "remaining_time": "1:45:52", "throughput": 5856.0, "total_tokens": 1730304} {"current_steps": 2870, "total_steps": 64460, "loss": 0.2369, "lr": 4.450822215327335e-06, "epoch": 0.8904747130003102, "percentage": 4.45, "elapsed_time": "0:04:55", "remaining_time": "1:45:50", "throughput": 5855.17, "total_tokens": 1732800} {"current_steps": 2875, "total_steps": 64460, "loss": 0.2305, "lr": 4.458578963698418e-06, "epoch": 0.8920260626745269, "percentage": 4.46, "elapsed_time": "0:04:56", "remaining_time": "1:45:51", "throughput": 5856.29, "total_tokens": 1736512} {"current_steps": 2880, "total_steps": 64460, "loss": 0.2295, "lr": 4.466335712069501e-06, "epoch": 0.8935774123487434, "percentage": 4.47, "elapsed_time": "0:04:57", "remaining_time": "1:45:51", "throughput": 5857.66, "total_tokens": 1739904} {"current_steps": 2885, "total_steps": 64460, "loss": 0.2315, "lr": 4.474092460440584e-06, "epoch": 0.89512876202296, "percentage": 4.48, "elapsed_time": "0:04:57", "remaining_time": "1:45:55", "throughput": 5859.71, "total_tokens": 1744768} {"current_steps": 2890, "total_steps": 64460, "loss": 0.2317, "lr": 4.4818492088116666e-06, "epoch": 0.8966801116971765, "percentage": 4.48, "elapsed_time": "0:04:58", "remaining_time": "1:45:56", "throughput": 5859.55, "total_tokens": 1748224} {"current_steps": 2895, "total_steps": 64460, "loss": 0.2361, "lr": 4.4896059571827496e-06, "epoch": 0.8982314613713931, "percentage": 4.49, "elapsed_time": "0:04:58", "remaining_time": "1:45:55", "throughput": 5860.54, "total_tokens": 1751488} {"current_steps": 2900, "total_steps": 64460, "loss": 0.2353, "lr": 4.4973627055538325e-06, "epoch": 0.8997828110456096, "percentage": 4.5, "elapsed_time": "0:04:59", "remaining_time": "1:45:53", "throughput": 5859.46, "total_tokens": 1753856} {"current_steps": 2905, "total_steps": 64460, "loss": 0.2317, "lr": 4.505119453924915e-06, "epoch": 0.9013341607198262, "percentage": 4.51, "elapsed_time": "0:04:59", "remaining_time": "1:45:52", "throughput": 5859.96, "total_tokens": 1756672} {"current_steps": 2910, "total_steps": 64460, "loss": 0.2347, "lr": 4.512876202295998e-06, "epoch": 0.9028855103940429, "percentage": 4.51, "elapsed_time": "0:05:00", "remaining_time": "1:45:51", "throughput": 5859.22, "total_tokens": 1759424} {"current_steps": 2915, "total_steps": 64460, "loss": 0.224, "lr": 4.520632950667081e-06, "epoch": 0.9044368600682594, "percentage": 4.52, "elapsed_time": "0:05:00", "remaining_time": "1:45:50", "throughput": 5858.91, "total_tokens": 1762336} {"current_steps": 2920, "total_steps": 64460, "loss": 0.237, "lr": 4.528389699038164e-06, "epoch": 0.905988209742476, "percentage": 4.53, "elapsed_time": "0:05:01", "remaining_time": "1:45:49", "throughput": 5858.72, "total_tokens": 1765024} {"current_steps": 2925, "total_steps": 64460, "loss": 0.2309, "lr": 4.536146447409247e-06, "epoch": 0.9075395594166925, "percentage": 4.54, "elapsed_time": "0:05:01", "remaining_time": "1:45:49", "throughput": 5860.14, "total_tokens": 1768640} {"current_steps": 2930, "total_steps": 64460, "loss": 0.2353, "lr": 4.54390319578033e-06, "epoch": 0.9090909090909091, "percentage": 4.55, "elapsed_time": "0:05:02", "remaining_time": "1:45:48", "throughput": 5861.17, "total_tokens": 1771936} {"current_steps": 2935, "total_steps": 64460, "loss": 0.2319, "lr": 4.551659944151412e-06, "epoch": 0.9106422587651256, "percentage": 4.55, "elapsed_time": "0:05:02", "remaining_time": "1:45:51", "throughput": 5862.97, "total_tokens": 1776416} {"current_steps": 2940, "total_steps": 64460, "loss": 0.2382, "lr": 4.559416692522495e-06, "epoch": 0.9121936084393423, "percentage": 4.56, "elapsed_time": "0:05:03", "remaining_time": "1:45:52", "throughput": 5863.22, "total_tokens": 1779840} {"current_steps": 2945, "total_steps": 64460, "loss": 0.2372, "lr": 4.567173440893578e-06, "epoch": 0.9137449581135588, "percentage": 4.57, "elapsed_time": "0:05:04", "remaining_time": "1:45:51", "throughput": 5863.18, "total_tokens": 1782816} {"current_steps": 2950, "total_steps": 64460, "loss": 0.2328, "lr": 4.574930189264661e-06, "epoch": 0.9152963077877754, "percentage": 4.58, "elapsed_time": "0:05:04", "remaining_time": "1:45:49", "throughput": 5862.48, "total_tokens": 1785248} {"current_steps": 2955, "total_steps": 64460, "loss": 0.2231, "lr": 4.582686937635744e-06, "epoch": 0.9168476574619919, "percentage": 4.58, "elapsed_time": "0:05:04", "remaining_time": "1:45:47", "throughput": 5861.51, "total_tokens": 1787680} {"current_steps": 2960, "total_steps": 64460, "loss": 0.242, "lr": 4.590443686006827e-06, "epoch": 0.9183990071362085, "percentage": 4.59, "elapsed_time": "0:05:05", "remaining_time": "1:45:49", "throughput": 5862.65, "total_tokens": 1791584} {"current_steps": 2965, "total_steps": 64460, "loss": 0.2352, "lr": 4.598200434377909e-06, "epoch": 0.919950356810425, "percentage": 4.6, "elapsed_time": "0:05:06", "remaining_time": "1:45:47", "throughput": 5862.33, "total_tokens": 1794176} {"current_steps": 2970, "total_steps": 64460, "loss": 0.2294, "lr": 4.605957182748992e-06, "epoch": 0.9215017064846417, "percentage": 4.61, "elapsed_time": "0:05:06", "remaining_time": "1:45:47", "throughput": 5863.76, "total_tokens": 1797728} {"current_steps": 2975, "total_steps": 64460, "loss": 0.2305, "lr": 4.613713931120075e-06, "epoch": 0.9230530561588582, "percentage": 4.62, "elapsed_time": "0:05:07", "remaining_time": "1:45:50", "throughput": 5864.0, "total_tokens": 1801952} {"current_steps": 2980, "total_steps": 64460, "loss": 0.245, "lr": 4.621470679491158e-06, "epoch": 0.9246044058330748, "percentage": 4.62, "elapsed_time": "0:05:07", "remaining_time": "1:45:51", "throughput": 5865.07, "total_tokens": 1805632} {"current_steps": 2985, "total_steps": 64460, "loss": 0.2351, "lr": 4.629227427862241e-06, "epoch": 0.9261557555072913, "percentage": 4.63, "elapsed_time": "0:05:08", "remaining_time": "1:45:49", "throughput": 5865.18, "total_tokens": 1808352} {"current_steps": 2990, "total_steps": 64460, "loss": 0.2308, "lr": 4.636984176233324e-06, "epoch": 0.9277071051815079, "percentage": 4.64, "elapsed_time": "0:05:08", "remaining_time": "1:45:48", "throughput": 5864.33, "total_tokens": 1810880} {"current_steps": 2995, "total_steps": 64460, "loss": 0.2329, "lr": 4.644740924604406e-06, "epoch": 0.9292584548557244, "percentage": 4.65, "elapsed_time": "0:05:09", "remaining_time": "1:45:47", "throughput": 5863.87, "total_tokens": 1813600} {"current_steps": 3000, "total_steps": 64460, "loss": 0.2365, "lr": 4.652497672975489e-06, "epoch": 0.930809804529941, "percentage": 4.65, "elapsed_time": "0:05:09", "remaining_time": "1:45:48", "throughput": 5864.01, "total_tokens": 1817024} {"current_steps": 3005, "total_steps": 64460, "loss": 0.2391, "lr": 4.660254421346572e-06, "epoch": 0.9323611542041577, "percentage": 4.66, "elapsed_time": "0:05:10", "remaining_time": "1:45:48", "throughput": 5862.95, "total_tokens": 1819872} {"current_steps": 3010, "total_steps": 64460, "loss": 0.2274, "lr": 4.668011169717655e-06, "epoch": 0.9339125038783742, "percentage": 4.67, "elapsed_time": "0:05:10", "remaining_time": "1:45:47", "throughput": 5861.45, "total_tokens": 1822528} {"current_steps": 3015, "total_steps": 64460, "loss": 0.2188, "lr": 4.675767918088738e-06, "epoch": 0.9354638535525908, "percentage": 4.68, "elapsed_time": "0:05:11", "remaining_time": "1:45:47", "throughput": 5861.26, "total_tokens": 1825664} {"current_steps": 3020, "total_steps": 64460, "loss": 0.2554, "lr": 4.683524666459821e-06, "epoch": 0.9370152032268073, "percentage": 4.69, "elapsed_time": "0:05:11", "remaining_time": "1:45:47", "throughput": 5861.46, "total_tokens": 1828704} {"current_steps": 3025, "total_steps": 64460, "loss": 0.2398, "lr": 4.691281414830903e-06, "epoch": 0.9385665529010239, "percentage": 4.69, "elapsed_time": "0:05:12", "remaining_time": "1:45:51", "throughput": 5863.02, "total_tokens": 1833536} {"current_steps": 3030, "total_steps": 64460, "loss": 0.2401, "lr": 4.699038163201986e-06, "epoch": 0.9401179025752404, "percentage": 4.7, "elapsed_time": "0:05:13", "remaining_time": "1:45:49", "throughput": 5862.36, "total_tokens": 1836064} {"current_steps": 3035, "total_steps": 64460, "loss": 0.2318, "lr": 4.706794911573069e-06, "epoch": 0.9416692522494571, "percentage": 4.71, "elapsed_time": "0:05:13", "remaining_time": "1:45:50", "throughput": 5862.89, "total_tokens": 1839776} {"current_steps": 3040, "total_steps": 64460, "loss": 0.2253, "lr": 4.714551659944152e-06, "epoch": 0.9432206019236736, "percentage": 4.72, "elapsed_time": "0:05:14", "remaining_time": "1:45:49", "throughput": 5862.22, "total_tokens": 1842336} {"current_steps": 3045, "total_steps": 64460, "loss": 0.2282, "lr": 4.722308408315235e-06, "epoch": 0.9447719515978902, "percentage": 4.72, "elapsed_time": "0:05:14", "remaining_time": "1:45:48", "throughput": 5860.82, "total_tokens": 1844640} {"current_steps": 3050, "total_steps": 64460, "loss": 0.2373, "lr": 4.730065156686318e-06, "epoch": 0.9463233012721067, "percentage": 4.73, "elapsed_time": "0:05:15", "remaining_time": "1:45:46", "throughput": 5860.29, "total_tokens": 1847200} {"current_steps": 3055, "total_steps": 64460, "loss": 0.2294, "lr": 4.7378219050574e-06, "epoch": 0.9478746509463233, "percentage": 4.74, "elapsed_time": "0:05:15", "remaining_time": "1:45:45", "throughput": 5859.76, "total_tokens": 1849792} {"current_steps": 3060, "total_steps": 64460, "loss": 0.2236, "lr": 4.745578653428483e-06, "epoch": 0.9494260006205398, "percentage": 4.75, "elapsed_time": "0:05:16", "remaining_time": "1:45:44", "throughput": 5859.61, "total_tokens": 1852864} {"current_steps": 3065, "total_steps": 64460, "loss": 0.2256, "lr": 4.753335401799566e-06, "epoch": 0.9509773502947564, "percentage": 4.75, "elapsed_time": "0:05:16", "remaining_time": "1:45:45", "throughput": 5860.27, "total_tokens": 1856416} {"current_steps": 3070, "total_steps": 64460, "loss": 0.2318, "lr": 4.761092150170649e-06, "epoch": 0.952528699968973, "percentage": 4.76, "elapsed_time": "0:05:17", "remaining_time": "1:45:45", "throughput": 5860.79, "total_tokens": 1859872} {"current_steps": 3075, "total_steps": 64460, "loss": 0.2337, "lr": 4.768848898541732e-06, "epoch": 0.9540800496431896, "percentage": 4.77, "elapsed_time": "0:05:17", "remaining_time": "1:45:44", "throughput": 5860.76, "total_tokens": 1862752} {"current_steps": 3080, "total_steps": 64460, "loss": 0.2273, "lr": 4.776605646912815e-06, "epoch": 0.9556313993174061, "percentage": 4.78, "elapsed_time": "0:05:18", "remaining_time": "1:45:44", "throughput": 5861.48, "total_tokens": 1865952} {"current_steps": 3085, "total_steps": 64460, "loss": 0.2317, "lr": 4.784362395283898e-06, "epoch": 0.9571827489916227, "percentage": 4.79, "elapsed_time": "0:05:18", "remaining_time": "1:45:44", "throughput": 5862.93, "total_tokens": 1869632} {"current_steps": 3090, "total_steps": 64460, "loss": 0.236, "lr": 4.79211914365498e-06, "epoch": 0.9587340986658393, "percentage": 4.79, "elapsed_time": "0:05:19", "remaining_time": "1:45:43", "throughput": 5862.23, "total_tokens": 1872256} {"current_steps": 3095, "total_steps": 64460, "loss": 0.2345, "lr": 4.799875892026063e-06, "epoch": 0.9602854483400558, "percentage": 4.8, "elapsed_time": "0:05:19", "remaining_time": "1:45:42", "throughput": 5861.51, "total_tokens": 1875008} {"current_steps": 3100, "total_steps": 64460, "loss": 0.2353, "lr": 4.807632640397146e-06, "epoch": 0.9618367980142725, "percentage": 4.81, "elapsed_time": "0:05:20", "remaining_time": "1:45:41", "throughput": 5861.37, "total_tokens": 1877888} {"current_steps": 3105, "total_steps": 64460, "loss": 0.226, "lr": 4.815389388768228e-06, "epoch": 0.963388147688489, "percentage": 4.82, "elapsed_time": "0:05:20", "remaining_time": "1:45:40", "throughput": 5861.74, "total_tokens": 1880928} {"current_steps": 3110, "total_steps": 64460, "loss": 0.2402, "lr": 4.823146137139312e-06, "epoch": 0.9649394973627056, "percentage": 4.82, "elapsed_time": "0:05:21", "remaining_time": "1:45:45", "throughput": 5864.85, "total_tokens": 1886688} {"current_steps": 3115, "total_steps": 64460, "loss": 0.2396, "lr": 4.830902885510395e-06, "epoch": 0.9664908470369221, "percentage": 4.83, "elapsed_time": "0:05:22", "remaining_time": "1:45:46", "throughput": 5864.61, "total_tokens": 1890080} {"current_steps": 3120, "total_steps": 64460, "loss": 0.2325, "lr": 4.838659633881477e-06, "epoch": 0.9680421967111387, "percentage": 4.84, "elapsed_time": "0:05:22", "remaining_time": "1:45:45", "throughput": 5863.73, "total_tokens": 1892544} {"current_steps": 3125, "total_steps": 64460, "loss": 0.2285, "lr": 4.84641638225256e-06, "epoch": 0.9695935463853552, "percentage": 4.85, "elapsed_time": "0:05:23", "remaining_time": "1:45:46", "throughput": 5864.46, "total_tokens": 1896288} {"current_steps": 3130, "total_steps": 64460, "loss": 0.2318, "lr": 4.854173130623643e-06, "epoch": 0.9711448960595719, "percentage": 4.86, "elapsed_time": "0:05:23", "remaining_time": "1:45:46", "throughput": 5865.62, "total_tokens": 1899808} {"current_steps": 3135, "total_steps": 64460, "loss": 0.2306, "lr": 4.861929878994725e-06, "epoch": 0.9726962457337884, "percentage": 4.86, "elapsed_time": "0:05:24", "remaining_time": "1:45:46", "throughput": 5866.85, "total_tokens": 1903392} {"current_steps": 3140, "total_steps": 64460, "loss": 0.2382, "lr": 4.869686627365809e-06, "epoch": 0.974247595408005, "percentage": 4.87, "elapsed_time": "0:05:24", "remaining_time": "1:45:46", "throughput": 5868.19, "total_tokens": 1906944} {"current_steps": 3145, "total_steps": 64460, "loss": 0.2415, "lr": 4.877443375736892e-06, "epoch": 0.9757989450822215, "percentage": 4.88, "elapsed_time": "0:05:25", "remaining_time": "1:45:46", "throughput": 5869.47, "total_tokens": 1910592} {"current_steps": 3150, "total_steps": 64460, "loss": 0.2307, "lr": 4.885200124107974e-06, "epoch": 0.9773502947564381, "percentage": 4.89, "elapsed_time": "0:05:26", "remaining_time": "1:45:51", "throughput": 5870.94, "total_tokens": 1915872} {"current_steps": 3155, "total_steps": 64460, "loss": 0.2286, "lr": 4.892956872479057e-06, "epoch": 0.9789016444306546, "percentage": 4.89, "elapsed_time": "0:05:26", "remaining_time": "1:45:50", "throughput": 5870.22, "total_tokens": 1918400} {"current_steps": 3160, "total_steps": 64460, "loss": 0.2339, "lr": 4.90071362085014e-06, "epoch": 0.9804529941048712, "percentage": 4.9, "elapsed_time": "0:05:27", "remaining_time": "1:45:48", "throughput": 5869.93, "total_tokens": 1921088} {"current_steps": 3165, "total_steps": 64460, "loss": 0.2353, "lr": 4.908470369221223e-06, "epoch": 0.9820043437790879, "percentage": 4.91, "elapsed_time": "0:05:27", "remaining_time": "1:45:48", "throughput": 5870.98, "total_tokens": 1924576} {"current_steps": 3170, "total_steps": 64460, "loss": 0.2295, "lr": 4.916227117592306e-06, "epoch": 0.9835556934533044, "percentage": 4.92, "elapsed_time": "0:05:28", "remaining_time": "1:45:47", "throughput": 5871.74, "total_tokens": 1927808} {"current_steps": 3175, "total_steps": 64460, "loss": 0.2263, "lr": 4.923983865963389e-06, "epoch": 0.985107043127521, "percentage": 4.93, "elapsed_time": "0:05:28", "remaining_time": "1:45:47", "throughput": 5872.06, "total_tokens": 1930880} {"current_steps": 3180, "total_steps": 64460, "loss": 0.2252, "lr": 4.931740614334471e-06, "epoch": 0.9866583928017375, "percentage": 4.93, "elapsed_time": "0:05:29", "remaining_time": "1:45:48", "throughput": 5872.31, "total_tokens": 1934464} {"current_steps": 3185, "total_steps": 64460, "loss": 0.2214, "lr": 4.939497362705554e-06, "epoch": 0.9882097424759541, "percentage": 4.94, "elapsed_time": "0:05:29", "remaining_time": "1:45:46", "throughput": 5871.79, "total_tokens": 1937120} {"current_steps": 3190, "total_steps": 64460, "loss": 0.2221, "lr": 4.947254111076637e-06, "epoch": 0.9897610921501706, "percentage": 4.95, "elapsed_time": "0:05:30", "remaining_time": "1:45:45", "throughput": 5871.42, "total_tokens": 1939680} {"current_steps": 3195, "total_steps": 64460, "loss": 0.2175, "lr": 4.95501085944772e-06, "epoch": 0.9913124418243873, "percentage": 4.96, "elapsed_time": "0:05:30", "remaining_time": "1:45:44", "throughput": 5871.56, "total_tokens": 1942656} {"current_steps": 3200, "total_steps": 64460, "loss": 0.2727, "lr": 4.962767607818802e-06, "epoch": 0.9928637914986038, "percentage": 4.96, "elapsed_time": "0:05:31", "remaining_time": "1:45:49", "throughput": 5874.43, "total_tokens": 1948256} {"current_steps": 3205, "total_steps": 64460, "loss": 0.2593, "lr": 4.970524356189886e-06, "epoch": 0.9944151411728204, "percentage": 4.97, "elapsed_time": "0:05:32", "remaining_time": "1:45:47", "throughput": 5873.06, "total_tokens": 1950496} {"current_steps": 3210, "total_steps": 64460, "loss": 0.2462, "lr": 4.978281104560968e-06, "epoch": 0.9959664908470369, "percentage": 4.98, "elapsed_time": "0:05:32", "remaining_time": "1:45:46", "throughput": 5873.11, "total_tokens": 1953376} {"current_steps": 3215, "total_steps": 64460, "loss": 0.2344, "lr": 4.986037852932051e-06, "epoch": 0.9975178405212535, "percentage": 4.99, "elapsed_time": "0:05:33", "remaining_time": "1:45:44", "throughput": 5871.11, "total_tokens": 1955392} {"current_steps": 3220, "total_steps": 64460, "loss": 0.2433, "lr": 4.993794601303134e-06, "epoch": 0.99906919019547, "percentage": 5.0, "elapsed_time": "0:05:33", "remaining_time": "1:45:43", "throughput": 5871.54, "total_tokens": 1958496} {"current_steps": 3225, "total_steps": 64460, "loss": 0.2308, "lr": 5.001551349674217e-06, "epoch": 1.0006205398696866, "percentage": 5.0, "elapsed_time": "0:05:34", "remaining_time": "1:45:48", "throughput": 5865.85, "total_tokens": 1961104} {"current_steps": 3230, "total_steps": 64460, "loss": 0.2357, "lr": 5.0093080980453e-06, "epoch": 1.0021718895439031, "percentage": 5.01, "elapsed_time": "0:05:34", "remaining_time": "1:45:46", "throughput": 5865.41, "total_tokens": 1963632} {"current_steps": 3235, "total_steps": 64460, "loss": 0.2287, "lr": 5.017064846416383e-06, "epoch": 1.0037232392181197, "percentage": 5.02, "elapsed_time": "0:05:35", "remaining_time": "1:45:44", "throughput": 5864.97, "total_tokens": 1966192} {"current_steps": 3240, "total_steps": 64460, "loss": 0.2322, "lr": 5.024821594787465e-06, "epoch": 1.0052745888923362, "percentage": 5.03, "elapsed_time": "0:05:35", "remaining_time": "1:45:43", "throughput": 5864.68, "total_tokens": 1968848} {"current_steps": 3245, "total_steps": 64460, "loss": 0.2105, "lr": 5.032578343158548e-06, "epoch": 1.006825938566553, "percentage": 5.03, "elapsed_time": "0:05:36", "remaining_time": "1:45:48", "throughput": 5866.52, "total_tokens": 1974256} {"current_steps": 3250, "total_steps": 64460, "loss": 0.2423, "lr": 5.040335091529631e-06, "epoch": 1.0083772882407696, "percentage": 5.04, "elapsed_time": "0:05:37", "remaining_time": "1:45:50", "throughput": 5867.53, "total_tokens": 1978384} {"current_steps": 3255, "total_steps": 64460, "loss": 0.232, "lr": 5.048091839900714e-06, "epoch": 1.009928637914986, "percentage": 5.05, "elapsed_time": "0:05:37", "remaining_time": "1:45:49", "throughput": 5866.69, "total_tokens": 1981072} {"current_steps": 3260, "total_steps": 64460, "loss": 0.2361, "lr": 5.055848588271796e-06, "epoch": 1.0114799875892027, "percentage": 5.06, "elapsed_time": "0:05:38", "remaining_time": "1:45:49", "throughput": 5867.04, "total_tokens": 1984368} {"current_steps": 3265, "total_steps": 64460, "loss": 0.2256, "lr": 5.063605336642879e-06, "epoch": 1.0130313372634192, "percentage": 5.07, "elapsed_time": "0:05:38", "remaining_time": "1:45:48", "throughput": 5866.61, "total_tokens": 1987088} {"current_steps": 3270, "total_steps": 64460, "loss": 0.2282, "lr": 5.071362085013962e-06, "epoch": 1.0145826869376358, "percentage": 5.07, "elapsed_time": "0:05:39", "remaining_time": "1:45:49", "throughput": 5867.17, "total_tokens": 1990960} {"current_steps": 3275, "total_steps": 64460, "loss": 0.2243, "lr": 5.079118833385045e-06, "epoch": 1.0161340366118523, "percentage": 5.08, "elapsed_time": "0:05:39", "remaining_time": "1:45:50", "throughput": 5867.9, "total_tokens": 1994512} {"current_steps": 3280, "total_steps": 64460, "loss": 0.2375, "lr": 5.0868755817561275e-06, "epoch": 1.0176853862860689, "percentage": 5.09, "elapsed_time": "0:05:40", "remaining_time": "1:45:49", "throughput": 5867.42, "total_tokens": 1997328} {"current_steps": 3285, "total_steps": 64460, "loss": 0.2275, "lr": 5.094632330127211e-06, "epoch": 1.0192367359602854, "percentage": 5.1, "elapsed_time": "0:05:40", "remaining_time": "1:45:47", "throughput": 5867.05, "total_tokens": 1999920} {"current_steps": 3290, "total_steps": 64460, "loss": 0.2194, "lr": 5.102389078498294e-06, "epoch": 1.020788085634502, "percentage": 5.1, "elapsed_time": "0:05:41", "remaining_time": "1:45:47", "throughput": 5867.49, "total_tokens": 2003120} {"current_steps": 3295, "total_steps": 64460, "loss": 0.216, "lr": 5.110145826869377e-06, "epoch": 1.0223394353087185, "percentage": 5.11, "elapsed_time": "0:05:41", "remaining_time": "1:45:45", "throughput": 5867.71, "total_tokens": 2005872} {"current_steps": 3300, "total_steps": 64460, "loss": 0.2404, "lr": 5.11790257524046e-06, "epoch": 1.023890784982935, "percentage": 5.12, "elapsed_time": "0:05:42", "remaining_time": "1:45:44", "throughput": 5867.96, "total_tokens": 2008912} {"current_steps": 3305, "total_steps": 64460, "loss": 0.2411, "lr": 5.125659323611542e-06, "epoch": 1.0254421346571516, "percentage": 5.13, "elapsed_time": "0:05:42", "remaining_time": "1:45:45", "throughput": 5869.42, "total_tokens": 2012816} {"current_steps": 3310, "total_steps": 64460, "loss": 0.2264, "lr": 5.133416071982625e-06, "epoch": 1.0269934843313684, "percentage": 5.13, "elapsed_time": "0:05:43", "remaining_time": "1:45:45", "throughput": 5870.46, "total_tokens": 2016240} {"current_steps": 3315, "total_steps": 64460, "loss": 0.2331, "lr": 5.141172820353708e-06, "epoch": 1.028544834005585, "percentage": 5.14, "elapsed_time": "0:05:43", "remaining_time": "1:45:43", "throughput": 5870.36, "total_tokens": 2019024} {"current_steps": 3320, "total_steps": 64460, "loss": 0.2358, "lr": 5.1489295687247905e-06, "epoch": 1.0300961836798015, "percentage": 5.15, "elapsed_time": "0:05:44", "remaining_time": "1:45:43", "throughput": 5871.34, "total_tokens": 2022352} {"current_steps": 3325, "total_steps": 64460, "loss": 0.2268, "lr": 5.1566863170958735e-06, "epoch": 1.031647533354018, "percentage": 5.16, "elapsed_time": "0:05:45", "remaining_time": "1:45:44", "throughput": 5872.26, "total_tokens": 2026224} {"current_steps": 3330, "total_steps": 64460, "loss": 0.2337, "lr": 5.1644430654669564e-06, "epoch": 1.0331988830282346, "percentage": 5.17, "elapsed_time": "0:05:45", "remaining_time": "1:45:42", "throughput": 5872.02, "total_tokens": 2028816} {"current_steps": 3335, "total_steps": 64460, "loss": 0.231, "lr": 5.1721998138380394e-06, "epoch": 1.0347502327024511, "percentage": 5.17, "elapsed_time": "0:05:46", "remaining_time": "1:45:42", "throughput": 5872.78, "total_tokens": 2032336} {"current_steps": 3340, "total_steps": 64460, "loss": 0.2294, "lr": 5.1799565622091216e-06, "epoch": 1.0363015823766677, "percentage": 5.18, "elapsed_time": "0:05:46", "remaining_time": "1:45:42", "throughput": 5874.02, "total_tokens": 2036016} {"current_steps": 3345, "total_steps": 64460, "loss": 0.2375, "lr": 5.1877133105802046e-06, "epoch": 1.0378529320508842, "percentage": 5.19, "elapsed_time": "0:05:47", "remaining_time": "1:45:40", "throughput": 5873.87, "total_tokens": 2038576} {"current_steps": 3350, "total_steps": 64460, "loss": 0.2394, "lr": 5.195470058951288e-06, "epoch": 1.0394042817251008, "percentage": 5.2, "elapsed_time": "0:05:47", "remaining_time": "1:45:41", "throughput": 5875.07, "total_tokens": 2042480} {"current_steps": 3355, "total_steps": 64460, "loss": 0.2376, "lr": 5.203226807322371e-06, "epoch": 1.0409556313993173, "percentage": 5.2, "elapsed_time": "0:05:48", "remaining_time": "1:45:41", "throughput": 5875.89, "total_tokens": 2045872} {"current_steps": 3360, "total_steps": 64460, "loss": 0.219, "lr": 5.210983555693454e-06, "epoch": 1.042506981073534, "percentage": 5.21, "elapsed_time": "0:05:48", "remaining_time": "1:45:39", "throughput": 5875.46, "total_tokens": 2048432} {"current_steps": 3365, "total_steps": 64460, "loss": 0.2333, "lr": 5.2187403040645365e-06, "epoch": 1.0440583307477505, "percentage": 5.22, "elapsed_time": "0:05:49", "remaining_time": "1:45:38", "throughput": 5874.37, "total_tokens": 2050800} {"current_steps": 3370, "total_steps": 64460, "loss": 0.2327, "lr": 5.2264970524356195e-06, "epoch": 1.045609680421967, "percentage": 5.23, "elapsed_time": "0:05:49", "remaining_time": "1:45:36", "throughput": 5873.71, "total_tokens": 2053296} {"current_steps": 3375, "total_steps": 64460, "loss": 0.2318, "lr": 5.2342538008067025e-06, "epoch": 1.0471610300961838, "percentage": 5.24, "elapsed_time": "0:05:50", "remaining_time": "1:45:35", "throughput": 5873.54, "total_tokens": 2056016} {"current_steps": 3380, "total_steps": 64460, "loss": 0.2338, "lr": 5.2420105491777854e-06, "epoch": 1.0487123797704003, "percentage": 5.24, "elapsed_time": "0:05:50", "remaining_time": "1:45:35", "throughput": 5874.0, "total_tokens": 2059440} {"current_steps": 3385, "total_steps": 64460, "loss": 0.2385, "lr": 5.2497672975488676e-06, "epoch": 1.0502637294446169, "percentage": 5.25, "elapsed_time": "0:05:51", "remaining_time": "1:45:33", "throughput": 5873.5, "total_tokens": 2061840} {"current_steps": 3390, "total_steps": 64460, "loss": 0.232, "lr": 5.2575240459199506e-06, "epoch": 1.0518150791188334, "percentage": 5.26, "elapsed_time": "0:05:51", "remaining_time": "1:45:32", "throughput": 5873.28, "total_tokens": 2064720} {"current_steps": 3395, "total_steps": 64460, "loss": 0.2398, "lr": 5.2652807942910335e-06, "epoch": 1.05336642879305, "percentage": 5.27, "elapsed_time": "0:05:52", "remaining_time": "1:45:31", "throughput": 5872.88, "total_tokens": 2067280} {"current_steps": 3400, "total_steps": 64460, "loss": 0.2654, "lr": 5.273037542662116e-06, "epoch": 1.0549177784672665, "percentage": 5.27, "elapsed_time": "0:05:52", "remaining_time": "1:45:31", "throughput": 5873.07, "total_tokens": 2070608} {"current_steps": 3405, "total_steps": 64460, "loss": 0.2411, "lr": 5.280794291033199e-06, "epoch": 1.056469128141483, "percentage": 5.28, "elapsed_time": "0:05:53", "remaining_time": "1:45:29", "throughput": 5872.74, "total_tokens": 2073136} {"current_steps": 3410, "total_steps": 64460, "loss": 0.2294, "lr": 5.288551039404282e-06, "epoch": 1.0580204778156996, "percentage": 5.29, "elapsed_time": "0:05:53", "remaining_time": "1:45:31", "throughput": 5874.56, "total_tokens": 2077680} {"current_steps": 3415, "total_steps": 64460, "loss": 0.2314, "lr": 5.2963077877753655e-06, "epoch": 1.0595718274899162, "percentage": 5.3, "elapsed_time": "0:05:54", "remaining_time": "1:45:29", "throughput": 5874.45, "total_tokens": 2080208} {"current_steps": 3420, "total_steps": 64460, "loss": 0.2357, "lr": 5.3040645361464485e-06, "epoch": 1.0611231771641327, "percentage": 5.31, "elapsed_time": "0:05:54", "remaining_time": "1:45:31", "throughput": 5875.39, "total_tokens": 2084112} {"current_steps": 3425, "total_steps": 64460, "loss": 0.2279, "lr": 5.311821284517531e-06, "epoch": 1.0626745268383493, "percentage": 5.31, "elapsed_time": "0:05:55", "remaining_time": "1:45:30", "throughput": 5874.96, "total_tokens": 2086864} {"current_steps": 3430, "total_steps": 64460, "loss": 0.2248, "lr": 5.319578032888614e-06, "epoch": 1.0642258765125658, "percentage": 5.32, "elapsed_time": "0:05:55", "remaining_time": "1:45:30", "throughput": 5876.0, "total_tokens": 2090480} {"current_steps": 3435, "total_steps": 64460, "loss": 0.218, "lr": 5.3273347812596966e-06, "epoch": 1.0657772261867824, "percentage": 5.33, "elapsed_time": "0:05:56", "remaining_time": "1:45:30", "throughput": 5877.1, "total_tokens": 2094224} {"current_steps": 3440, "total_steps": 64460, "loss": 0.2185, "lr": 5.3350915296307796e-06, "epoch": 1.0673285758609992, "percentage": 5.34, "elapsed_time": "0:05:57", "remaining_time": "1:45:32", "throughput": 5879.12, "total_tokens": 2098864} {"current_steps": 3445, "total_steps": 64460, "loss": 0.2318, "lr": 5.342848278001862e-06, "epoch": 1.0688799255352157, "percentage": 5.34, "elapsed_time": "0:05:57", "remaining_time": "1:45:31", "throughput": 5879.94, "total_tokens": 2102128} {"current_steps": 3450, "total_steps": 64460, "loss": 0.2398, "lr": 5.350605026372945e-06, "epoch": 1.0704312752094323, "percentage": 5.35, "elapsed_time": "0:05:57", "remaining_time": "1:45:30", "throughput": 5879.81, "total_tokens": 2104912} {"current_steps": 3455, "total_steps": 64460, "loss": 0.2233, "lr": 5.358361774744028e-06, "epoch": 1.0719826248836488, "percentage": 5.36, "elapsed_time": "0:05:58", "remaining_time": "1:45:29", "throughput": 5880.29, "total_tokens": 2107856} {"current_steps": 3460, "total_steps": 64460, "loss": 0.2346, "lr": 5.366118523115111e-06, "epoch": 1.0735339745578654, "percentage": 5.37, "elapsed_time": "0:05:58", "remaining_time": "1:45:27", "throughput": 5880.26, "total_tokens": 2110576} {"current_steps": 3465, "total_steps": 64460, "loss": 0.2247, "lr": 5.373875271486193e-06, "epoch": 1.075085324232082, "percentage": 5.38, "elapsed_time": "0:05:59", "remaining_time": "1:45:26", "throughput": 5880.38, "total_tokens": 2113392} {"current_steps": 3470, "total_steps": 64460, "loss": 0.2371, "lr": 5.381632019857276e-06, "epoch": 1.0766366739062985, "percentage": 5.38, "elapsed_time": "0:05:59", "remaining_time": "1:45:25", "throughput": 5880.04, "total_tokens": 2115984} {"current_steps": 3475, "total_steps": 64460, "loss": 0.2327, "lr": 5.38938876822836e-06, "epoch": 1.078188023580515, "percentage": 5.39, "elapsed_time": "0:06:00", "remaining_time": "1:45:24", "throughput": 5881.31, "total_tokens": 2119632} {"current_steps": 3480, "total_steps": 64460, "loss": 0.2403, "lr": 5.3971455165994426e-06, "epoch": 1.0797393732547316, "percentage": 5.4, "elapsed_time": "0:06:00", "remaining_time": "1:45:24", "throughput": 5881.83, "total_tokens": 2122960} {"current_steps": 3485, "total_steps": 64460, "loss": 0.2336, "lr": 5.4049022649705256e-06, "epoch": 1.0812907229289481, "percentage": 5.41, "elapsed_time": "0:06:01", "remaining_time": "1:45:25", "throughput": 5882.8, "total_tokens": 2126800} {"current_steps": 3490, "total_steps": 64460, "loss": 0.2256, "lr": 5.412659013341608e-06, "epoch": 1.0828420726031647, "percentage": 5.41, "elapsed_time": "0:06:01", "remaining_time": "1:45:23", "throughput": 5882.27, "total_tokens": 2129072} {"current_steps": 3495, "total_steps": 64460, "loss": 0.2216, "lr": 5.420415761712691e-06, "epoch": 1.0843934222773812, "percentage": 5.42, "elapsed_time": "0:06:02", "remaining_time": "1:45:22", "throughput": 5882.77, "total_tokens": 2132144} {"current_steps": 3500, "total_steps": 64460, "loss": 0.2759, "lr": 5.428172510083774e-06, "epoch": 1.0859447719515978, "percentage": 5.43, "elapsed_time": "0:06:02", "remaining_time": "1:45:20", "throughput": 5882.78, "total_tokens": 2134832} {"current_steps": 3505, "total_steps": 64460, "loss": 0.2813, "lr": 5.435929258454856e-06, "epoch": 1.0874961216258145, "percentage": 5.44, "elapsed_time": "0:06:03", "remaining_time": "1:45:19", "throughput": 5883.53, "total_tokens": 2138064} {"current_steps": 3510, "total_steps": 64460, "loss": 0.2366, "lr": 5.443686006825939e-06, "epoch": 1.089047471300031, "percentage": 5.45, "elapsed_time": "0:06:03", "remaining_time": "1:45:18", "throughput": 5883.2, "total_tokens": 2140656} {"current_steps": 3515, "total_steps": 64460, "loss": 0.2362, "lr": 5.451442755197022e-06, "epoch": 1.0905988209742477, "percentage": 5.45, "elapsed_time": "0:06:04", "remaining_time": "1:45:17", "throughput": 5883.95, "total_tokens": 2143760} {"current_steps": 3520, "total_steps": 64460, "loss": 0.2274, "lr": 5.459199503568105e-06, "epoch": 1.0921501706484642, "percentage": 5.46, "elapsed_time": "0:06:04", "remaining_time": "1:45:15", "throughput": 5883.12, "total_tokens": 2146128} {"current_steps": 3525, "total_steps": 64460, "loss": 0.2326, "lr": 5.466956251939187e-06, "epoch": 1.0937015203226808, "percentage": 5.47, "elapsed_time": "0:06:05", "remaining_time": "1:45:13", "throughput": 5882.72, "total_tokens": 2148624} {"current_steps": 3530, "total_steps": 64460, "loss": 0.2335, "lr": 5.47471300031027e-06, "epoch": 1.0952528699968973, "percentage": 5.48, "elapsed_time": "0:06:05", "remaining_time": "1:45:12", "throughput": 5882.61, "total_tokens": 2151344} {"current_steps": 3535, "total_steps": 64460, "loss": 0.2326, "lr": 5.482469748681353e-06, "epoch": 1.0968042196711139, "percentage": 5.48, "elapsed_time": "0:06:06", "remaining_time": "1:45:11", "throughput": 5882.99, "total_tokens": 2154352} {"current_steps": 3540, "total_steps": 64460, "loss": 0.234, "lr": 5.490226497052437e-06, "epoch": 1.0983555693453304, "percentage": 5.49, "elapsed_time": "0:06:06", "remaining_time": "1:45:09", "throughput": 5882.48, "total_tokens": 2156784} {"current_steps": 3545, "total_steps": 64460, "loss": 0.2308, "lr": 5.49798324542352e-06, "epoch": 1.099906919019547, "percentage": 5.5, "elapsed_time": "0:06:07", "remaining_time": "1:45:08", "throughput": 5882.95, "total_tokens": 2159856} {"current_steps": 3550, "total_steps": 64460, "loss": 0.2318, "lr": 5.505739993794602e-06, "epoch": 1.1014582686937635, "percentage": 5.51, "elapsed_time": "0:06:07", "remaining_time": "1:45:08", "throughput": 5883.85, "total_tokens": 2163216} {"current_steps": 3555, "total_steps": 64460, "loss": 0.2308, "lr": 5.513496742165685e-06, "epoch": 1.10300961836798, "percentage": 5.52, "elapsed_time": "0:06:08", "remaining_time": "1:45:08", "throughput": 5884.74, "total_tokens": 2166832} {"current_steps": 3560, "total_steps": 64460, "loss": 0.2349, "lr": 5.521253490536768e-06, "epoch": 1.1045609680421966, "percentage": 5.52, "elapsed_time": "0:06:08", "remaining_time": "1:45:08", "throughput": 5885.87, "total_tokens": 2170544} {"current_steps": 3565, "total_steps": 64460, "loss": 0.2284, "lr": 5.529010238907851e-06, "epoch": 1.1061123177164132, "percentage": 5.53, "elapsed_time": "0:06:09", "remaining_time": "1:45:07", "throughput": 5886.07, "total_tokens": 2173520} {"current_steps": 3570, "total_steps": 64460, "loss": 0.2321, "lr": 5.536766987278933e-06, "epoch": 1.10766366739063, "percentage": 5.54, "elapsed_time": "0:06:09", "remaining_time": "1:45:08", "throughput": 5887.37, "total_tokens": 2177616} {"current_steps": 3575, "total_steps": 64460, "loss": 0.2338, "lr": 5.544523735650016e-06, "epoch": 1.1092150170648465, "percentage": 5.55, "elapsed_time": "0:06:10", "remaining_time": "1:45:07", "throughput": 5887.31, "total_tokens": 2180400} {"current_steps": 3580, "total_steps": 64460, "loss": 0.229, "lr": 5.552280484021099e-06, "epoch": 1.110766366739063, "percentage": 5.55, "elapsed_time": "0:06:10", "remaining_time": "1:45:06", "throughput": 5887.09, "total_tokens": 2183152} {"current_steps": 3585, "total_steps": 64460, "loss": 0.2236, "lr": 5.560037232392181e-06, "epoch": 1.1123177164132796, "percentage": 5.56, "elapsed_time": "0:06:11", "remaining_time": "1:45:06", "throughput": 5886.77, "total_tokens": 2186160} {"current_steps": 3590, "total_steps": 64460, "loss": 0.2257, "lr": 5.567793980763264e-06, "epoch": 1.1138690660874961, "percentage": 5.57, "elapsed_time": "0:06:11", "remaining_time": "1:45:04", "throughput": 5886.61, "total_tokens": 2188784} {"current_steps": 3595, "total_steps": 64460, "loss": 0.2388, "lr": 5.575550729134347e-06, "epoch": 1.1154204157617127, "percentage": 5.58, "elapsed_time": "0:06:12", "remaining_time": "1:45:03", "throughput": 5887.53, "total_tokens": 2192048} {"current_steps": 3600, "total_steps": 64460, "loss": 0.2545, "lr": 5.58330747750543e-06, "epoch": 1.1169717654359292, "percentage": 5.58, "elapsed_time": "0:06:12", "remaining_time": "1:45:03", "throughput": 5888.52, "total_tokens": 2195664} {"current_steps": 3605, "total_steps": 64460, "loss": 0.237, "lr": 5.591064225876514e-06, "epoch": 1.1185231151101458, "percentage": 5.59, "elapsed_time": "0:06:13", "remaining_time": "1:45:02", "throughput": 5888.23, "total_tokens": 2198320} {"current_steps": 3610, "total_steps": 64460, "loss": 0.2285, "lr": 5.598820974247596e-06, "epoch": 1.1200744647843623, "percentage": 5.6, "elapsed_time": "0:06:13", "remaining_time": "1:45:04", "throughput": 5889.39, "total_tokens": 2202608} {"current_steps": 3615, "total_steps": 64460, "loss": 0.2304, "lr": 5.606577722618679e-06, "epoch": 1.121625814458579, "percentage": 5.61, "elapsed_time": "0:06:14", "remaining_time": "1:45:03", "throughput": 5889.89, "total_tokens": 2205808} {"current_steps": 3620, "total_steps": 64460, "loss": 0.2391, "lr": 5.614334470989762e-06, "epoch": 1.1231771641327954, "percentage": 5.62, "elapsed_time": "0:06:15", "remaining_time": "1:45:02", "throughput": 5890.23, "total_tokens": 2209008} {"current_steps": 3625, "total_steps": 64460, "loss": 0.2298, "lr": 5.622091219360845e-06, "epoch": 1.124728513807012, "percentage": 5.62, "elapsed_time": "0:06:15", "remaining_time": "1:45:01", "throughput": 5889.23, "total_tokens": 2211280} {"current_steps": 3630, "total_steps": 64460, "loss": 0.2234, "lr": 5.629847967731927e-06, "epoch": 1.1262798634812285, "percentage": 5.63, "elapsed_time": "0:06:15", "remaining_time": "1:45:00", "throughput": 5889.26, "total_tokens": 2214064} {"current_steps": 3635, "total_steps": 64460, "loss": 0.2363, "lr": 5.63760471610301e-06, "epoch": 1.1278312131554453, "percentage": 5.64, "elapsed_time": "0:06:16", "remaining_time": "1:44:58", "throughput": 5888.82, "total_tokens": 2216592} {"current_steps": 3640, "total_steps": 64460, "loss": 0.2388, "lr": 5.645361464474093e-06, "epoch": 1.1293825628296619, "percentage": 5.65, "elapsed_time": "0:06:16", "remaining_time": "1:44:56", "throughput": 5887.99, "total_tokens": 2218704} {"current_steps": 3645, "total_steps": 64460, "loss": 0.2329, "lr": 5.653118212845176e-06, "epoch": 1.1309339125038784, "percentage": 5.65, "elapsed_time": "0:06:17", "remaining_time": "1:44:56", "throughput": 5889.46, "total_tokens": 2222768} {"current_steps": 3650, "total_steps": 64460, "loss": 0.2341, "lr": 5.660874961216258e-06, "epoch": 1.132485262178095, "percentage": 5.66, "elapsed_time": "0:06:18", "remaining_time": "1:44:58", "throughput": 5890.99, "total_tokens": 2227056} {"current_steps": 3655, "total_steps": 64460, "loss": 0.2378, "lr": 5.668631709587341e-06, "epoch": 1.1340366118523115, "percentage": 5.67, "elapsed_time": "0:06:18", "remaining_time": "1:44:57", "throughput": 5891.51, "total_tokens": 2230160} {"current_steps": 3660, "total_steps": 64460, "loss": 0.2222, "lr": 5.676388457958424e-06, "epoch": 1.135587961526528, "percentage": 5.68, "elapsed_time": "0:06:19", "remaining_time": "1:44:56", "throughput": 5892.16, "total_tokens": 2233360} {"current_steps": 3665, "total_steps": 64460, "loss": 0.2336, "lr": 5.684145206329506e-06, "epoch": 1.1371393112007446, "percentage": 5.69, "elapsed_time": "0:06:19", "remaining_time": "1:44:56", "throughput": 5893.25, "total_tokens": 2236880} {"current_steps": 3670, "total_steps": 64460, "loss": 0.2165, "lr": 5.691901954700591e-06, "epoch": 1.1386906608749612, "percentage": 5.69, "elapsed_time": "0:06:20", "remaining_time": "1:44:56", "throughput": 5894.22, "total_tokens": 2240592} {"current_steps": 3675, "total_steps": 64460, "loss": 0.239, "lr": 5.699658703071673e-06, "epoch": 1.1402420105491777, "percentage": 5.7, "elapsed_time": "0:06:20", "remaining_time": "1:44:54", "throughput": 5894.16, "total_tokens": 2243120} {"current_steps": 3680, "total_steps": 64460, "loss": 0.2306, "lr": 5.707415451442756e-06, "epoch": 1.1417933602233943, "percentage": 5.71, "elapsed_time": "0:06:21", "remaining_time": "1:44:57", "throughput": 5895.37, "total_tokens": 2247952} {"current_steps": 3685, "total_steps": 64460, "loss": 0.226, "lr": 5.715172199813839e-06, "epoch": 1.1433447098976108, "percentage": 5.72, "elapsed_time": "0:06:21", "remaining_time": "1:44:55", "throughput": 5894.12, "total_tokens": 2249904} {"current_steps": 3690, "total_steps": 64460, "loss": 0.2432, "lr": 5.722928948184921e-06, "epoch": 1.1448960595718276, "percentage": 5.72, "elapsed_time": "0:06:22", "remaining_time": "1:44:55", "throughput": 5894.62, "total_tokens": 2253200} {"current_steps": 3695, "total_steps": 64460, "loss": 0.23, "lr": 5.730685696556004e-06, "epoch": 1.146447409246044, "percentage": 5.73, "elapsed_time": "0:06:22", "remaining_time": "1:44:53", "throughput": 5894.73, "total_tokens": 2256016} {"current_steps": 3700, "total_steps": 64460, "loss": 0.2304, "lr": 5.738442444927087e-06, "epoch": 1.1479987589202607, "percentage": 5.74, "elapsed_time": "0:06:23", "remaining_time": "1:44:52", "throughput": 5893.75, "total_tokens": 2258352} {"current_steps": 3705, "total_steps": 64460, "loss": 0.2373, "lr": 5.74619919329817e-06, "epoch": 1.1495501085944773, "percentage": 5.75, "elapsed_time": "0:06:23", "remaining_time": "1:44:50", "throughput": 5893.56, "total_tokens": 2260912} {"current_steps": 3710, "total_steps": 64460, "loss": 0.2331, "lr": 5.753955941669252e-06, "epoch": 1.1511014582686938, "percentage": 5.76, "elapsed_time": "0:06:24", "remaining_time": "1:44:49", "throughput": 5893.59, "total_tokens": 2263664} {"current_steps": 3715, "total_steps": 64460, "loss": 0.2316, "lr": 5.761712690040335e-06, "epoch": 1.1526528079429104, "percentage": 5.76, "elapsed_time": "0:06:24", "remaining_time": "1:44:47", "throughput": 5893.54, "total_tokens": 2266320} {"current_steps": 3720, "total_steps": 64460, "loss": 0.2268, "lr": 5.769469438411418e-06, "epoch": 1.154204157617127, "percentage": 5.77, "elapsed_time": "0:06:25", "remaining_time": "1:44:47", "throughput": 5892.79, "total_tokens": 2269008} {"current_steps": 3725, "total_steps": 64460, "loss": 0.2418, "lr": 5.777226186782501e-06, "epoch": 1.1557555072913435, "percentage": 5.78, "elapsed_time": "0:06:25", "remaining_time": "1:44:46", "throughput": 5892.5, "total_tokens": 2272080} {"current_steps": 3730, "total_steps": 64460, "loss": 0.2328, "lr": 5.784982935153583e-06, "epoch": 1.15730685696556, "percentage": 5.79, "elapsed_time": "0:06:26", "remaining_time": "1:44:46", "throughput": 5892.98, "total_tokens": 2275312} {"current_steps": 3735, "total_steps": 64460, "loss": 0.2274, "lr": 5.792739683524667e-06, "epoch": 1.1588582066397766, "percentage": 5.79, "elapsed_time": "0:06:26", "remaining_time": "1:44:47", "throughput": 5893.49, "total_tokens": 2279184} {"current_steps": 3740, "total_steps": 64460, "loss": 0.2317, "lr": 5.80049643189575e-06, "epoch": 1.1604095563139931, "percentage": 5.8, "elapsed_time": "0:06:27", "remaining_time": "1:44:48", "throughput": 5895.13, "total_tokens": 2283408} {"current_steps": 3745, "total_steps": 64460, "loss": 0.2343, "lr": 5.808253180266833e-06, "epoch": 1.1619609059882097, "percentage": 5.81, "elapsed_time": "0:06:27", "remaining_time": "1:44:47", "throughput": 5895.72, "total_tokens": 2286672} {"current_steps": 3750, "total_steps": 64460, "loss": 0.2356, "lr": 5.816009928637916e-06, "epoch": 1.1635122556624262, "percentage": 5.82, "elapsed_time": "0:06:28", "remaining_time": "1:44:48", "throughput": 5896.88, "total_tokens": 2290576} {"current_steps": 3755, "total_steps": 64460, "loss": 0.2357, "lr": 5.823766677008998e-06, "epoch": 1.165063605336643, "percentage": 5.83, "elapsed_time": "0:06:28", "remaining_time": "1:44:47", "throughput": 5896.69, "total_tokens": 2293264} {"current_steps": 3760, "total_steps": 64460, "loss": 0.232, "lr": 5.831523425380081e-06, "epoch": 1.1666149550108595, "percentage": 5.83, "elapsed_time": "0:06:29", "remaining_time": "1:44:51", "throughput": 5898.76, "total_tokens": 2298992} {"current_steps": 3765, "total_steps": 64460, "loss": 0.2359, "lr": 5.839280173751164e-06, "epoch": 1.168166304685076, "percentage": 5.84, "elapsed_time": "0:06:30", "remaining_time": "1:44:51", "throughput": 5898.99, "total_tokens": 2302384} {"current_steps": 3770, "total_steps": 64460, "loss": 0.2346, "lr": 5.847036922122246e-06, "epoch": 1.1697176543592926, "percentage": 5.85, "elapsed_time": "0:06:30", "remaining_time": "1:44:50", "throughput": 5899.53, "total_tokens": 2305424} {"current_steps": 3775, "total_steps": 64460, "loss": 0.2305, "lr": 5.854793670493329e-06, "epoch": 1.1712690040335092, "percentage": 5.86, "elapsed_time": "0:06:31", "remaining_time": "1:44:49", "throughput": 5899.05, "total_tokens": 2307952} {"current_steps": 3780, "total_steps": 64460, "loss": 0.2274, "lr": 5.862550418864412e-06, "epoch": 1.1728203537077257, "percentage": 5.86, "elapsed_time": "0:06:31", "remaining_time": "1:44:48", "throughput": 5899.22, "total_tokens": 2310928} {"current_steps": 3785, "total_steps": 64460, "loss": 0.2443, "lr": 5.870307167235495e-06, "epoch": 1.1743717033819423, "percentage": 5.87, "elapsed_time": "0:06:32", "remaining_time": "1:44:46", "throughput": 5897.67, "total_tokens": 2312912} {"current_steps": 3790, "total_steps": 64460, "loss": 0.2338, "lr": 5.878063915606577e-06, "epoch": 1.1759230530561589, "percentage": 5.88, "elapsed_time": "0:06:32", "remaining_time": "1:44:45", "throughput": 5897.79, "total_tokens": 2315824} {"current_steps": 3795, "total_steps": 64460, "loss": 0.2394, "lr": 5.88582066397766e-06, "epoch": 1.1774744027303754, "percentage": 5.89, "elapsed_time": "0:06:33", "remaining_time": "1:44:44", "throughput": 5896.86, "total_tokens": 2318096} {"current_steps": 3800, "total_steps": 64460, "loss": 0.2367, "lr": 5.893577412348744e-06, "epoch": 1.179025752404592, "percentage": 5.9, "elapsed_time": "0:06:33", "remaining_time": "1:44:44", "throughput": 5898.05, "total_tokens": 2321936} {"current_steps": 3805, "total_steps": 64460, "loss": 0.2269, "lr": 5.901334160719827e-06, "epoch": 1.1805771020788085, "percentage": 5.9, "elapsed_time": "0:06:34", "remaining_time": "1:44:44", "throughput": 5898.79, "total_tokens": 2325360} {"current_steps": 3810, "total_steps": 64460, "loss": 0.2258, "lr": 5.90909090909091e-06, "epoch": 1.182128451753025, "percentage": 5.91, "elapsed_time": "0:06:34", "remaining_time": "1:44:42", "throughput": 5897.77, "total_tokens": 2327664} {"current_steps": 3815, "total_steps": 64460, "loss": 0.2258, "lr": 5.916847657461992e-06, "epoch": 1.1836798014272416, "percentage": 5.92, "elapsed_time": "0:06:35", "remaining_time": "1:44:42", "throughput": 5898.16, "total_tokens": 2330896} {"current_steps": 3820, "total_steps": 64460, "loss": 0.238, "lr": 5.924604405833075e-06, "epoch": 1.1852311511014584, "percentage": 5.93, "elapsed_time": "0:06:35", "remaining_time": "1:44:41", "throughput": 5898.87, "total_tokens": 2334192} {"current_steps": 3825, "total_steps": 64460, "loss": 0.2333, "lr": 5.932361154204158e-06, "epoch": 1.186782500775675, "percentage": 5.93, "elapsed_time": "0:06:36", "remaining_time": "1:44:39", "throughput": 5898.18, "total_tokens": 2336560} {"current_steps": 3830, "total_steps": 64460, "loss": 0.2424, "lr": 5.940117902575241e-06, "epoch": 1.1883338504498915, "percentage": 5.94, "elapsed_time": "0:06:36", "remaining_time": "1:44:38", "throughput": 5896.73, "total_tokens": 2338768} {"current_steps": 3835, "total_steps": 64460, "loss": 0.2328, "lr": 5.947874650946323e-06, "epoch": 1.189885200124108, "percentage": 5.95, "elapsed_time": "0:06:37", "remaining_time": "1:44:38", "throughput": 5896.94, "total_tokens": 2341872} {"current_steps": 3840, "total_steps": 64460, "loss": 0.2316, "lr": 5.955631399317406e-06, "epoch": 1.1914365497983246, "percentage": 5.96, "elapsed_time": "0:06:37", "remaining_time": "1:44:37", "throughput": 5897.57, "total_tokens": 2345168} {"current_steps": 3845, "total_steps": 64460, "loss": 0.2271, "lr": 5.963388147688489e-06, "epoch": 1.1929878994725411, "percentage": 5.96, "elapsed_time": "0:06:38", "remaining_time": "1:44:35", "throughput": 5896.93, "total_tokens": 2347600} {"current_steps": 3850, "total_steps": 64460, "loss": 0.2196, "lr": 5.9711448960595715e-06, "epoch": 1.1945392491467577, "percentage": 5.97, "elapsed_time": "0:06:38", "remaining_time": "1:44:35", "throughput": 5896.81, "total_tokens": 2350448} {"current_steps": 3855, "total_steps": 64460, "loss": 0.2301, "lr": 5.9789016444306545e-06, "epoch": 1.1960905988209742, "percentage": 5.98, "elapsed_time": "0:06:39", "remaining_time": "1:44:33", "throughput": 5896.34, "total_tokens": 2353072} {"current_steps": 3860, "total_steps": 64460, "loss": 0.2116, "lr": 5.986658392801738e-06, "epoch": 1.1976419484951908, "percentage": 5.99, "elapsed_time": "0:06:39", "remaining_time": "1:44:33", "throughput": 5896.16, "total_tokens": 2356176} {"current_steps": 3865, "total_steps": 64460, "loss": 0.2399, "lr": 5.994415141172821e-06, "epoch": 1.1991932981694073, "percentage": 6.0, "elapsed_time": "0:06:40", "remaining_time": "1:44:32", "throughput": 5896.02, "total_tokens": 2358960} {"current_steps": 3870, "total_steps": 64460, "loss": 0.2393, "lr": 6.002171889543904e-06, "epoch": 1.200744647843624, "percentage": 6.0, "elapsed_time": "0:06:40", "remaining_time": "1:44:32", "throughput": 5896.45, "total_tokens": 2362256} {"current_steps": 3875, "total_steps": 64460, "loss": 0.2487, "lr": 6.0099286379149864e-06, "epoch": 1.2022959975178404, "percentage": 6.01, "elapsed_time": "0:06:41", "remaining_time": "1:44:30", "throughput": 5895.96, "total_tokens": 2364720} {"current_steps": 3880, "total_steps": 64460, "loss": 0.2256, "lr": 6.017685386286069e-06, "epoch": 1.203847347192057, "percentage": 6.02, "elapsed_time": "0:06:41", "remaining_time": "1:44:29", "throughput": 5895.42, "total_tokens": 2367376} {"current_steps": 3885, "total_steps": 64460, "loss": 0.2267, "lr": 6.025442134657152e-06, "epoch": 1.2053986968662738, "percentage": 6.03, "elapsed_time": "0:06:42", "remaining_time": "1:44:28", "throughput": 5894.34, "total_tokens": 2369648} {"current_steps": 3890, "total_steps": 64460, "loss": 0.2243, "lr": 6.033198883028235e-06, "epoch": 1.2069500465404903, "percentage": 6.03, "elapsed_time": "0:06:42", "remaining_time": "1:44:28", "throughput": 5894.88, "total_tokens": 2373200} {"current_steps": 3895, "total_steps": 64460, "loss": 0.2368, "lr": 6.0409556313993175e-06, "epoch": 1.2085013962147069, "percentage": 6.04, "elapsed_time": "0:06:43", "remaining_time": "1:44:27", "throughput": 5895.42, "total_tokens": 2376400} {"current_steps": 3900, "total_steps": 64460, "loss": 0.2426, "lr": 6.0487123797704005e-06, "epoch": 1.2100527458889234, "percentage": 6.05, "elapsed_time": "0:06:43", "remaining_time": "1:44:26", "throughput": 5895.41, "total_tokens": 2379216} {"current_steps": 3905, "total_steps": 64460, "loss": 0.2282, "lr": 6.0564691281414835e-06, "epoch": 1.21160409556314, "percentage": 6.06, "elapsed_time": "0:06:44", "remaining_time": "1:44:26", "throughput": 5895.95, "total_tokens": 2382448} {"current_steps": 3910, "total_steps": 64460, "loss": 0.2281, "lr": 6.0642258765125665e-06, "epoch": 1.2131554452373565, "percentage": 6.07, "elapsed_time": "0:06:44", "remaining_time": "1:44:24", "throughput": 5895.31, "total_tokens": 2384976} {"current_steps": 3915, "total_steps": 64460, "loss": 0.2274, "lr": 6.071982624883649e-06, "epoch": 1.214706794911573, "percentage": 6.07, "elapsed_time": "0:06:45", "remaining_time": "1:44:24", "throughput": 5895.97, "total_tokens": 2388240} {"current_steps": 3920, "total_steps": 64460, "loss": 0.2235, "lr": 6.079739373254732e-06, "epoch": 1.2162581445857896, "percentage": 6.08, "elapsed_time": "0:06:45", "remaining_time": "1:44:22", "throughput": 5894.83, "total_tokens": 2390384} {"current_steps": 3925, "total_steps": 64460, "loss": 0.2218, "lr": 6.0874961216258154e-06, "epoch": 1.2178094942600062, "percentage": 6.09, "elapsed_time": "0:06:46", "remaining_time": "1:44:23", "throughput": 5895.9, "total_tokens": 2394352} {"current_steps": 3930, "total_steps": 64460, "loss": 0.2449, "lr": 6.095252869996898e-06, "epoch": 1.2193608439342227, "percentage": 6.1, "elapsed_time": "0:06:46", "remaining_time": "1:44:22", "throughput": 5895.01, "total_tokens": 2397040} {"current_steps": 3935, "total_steps": 64460, "loss": 0.2365, "lr": 6.103009618367981e-06, "epoch": 1.2209121936084393, "percentage": 6.1, "elapsed_time": "0:06:47", "remaining_time": "1:44:22", "throughput": 5895.25, "total_tokens": 2400080} {"current_steps": 3940, "total_steps": 64460, "loss": 0.2339, "lr": 6.1107663667390635e-06, "epoch": 1.2224635432826558, "percentage": 6.11, "elapsed_time": "0:06:47", "remaining_time": "1:44:20", "throughput": 5894.34, "total_tokens": 2402384} {"current_steps": 3945, "total_steps": 64460, "loss": 0.2318, "lr": 6.1185231151101465e-06, "epoch": 1.2240148929568724, "percentage": 6.12, "elapsed_time": "0:06:48", "remaining_time": "1:44:20", "throughput": 5894.84, "total_tokens": 2405712} {"current_steps": 3950, "total_steps": 64460, "loss": 0.2304, "lr": 6.1262798634812295e-06, "epoch": 1.2255662426310892, "percentage": 6.13, "elapsed_time": "0:06:48", "remaining_time": "1:44:20", "throughput": 5895.71, "total_tokens": 2409520} {"current_steps": 3955, "total_steps": 64460, "loss": 0.2344, "lr": 6.134036611852312e-06, "epoch": 1.2271175923053057, "percentage": 6.14, "elapsed_time": "0:06:49", "remaining_time": "1:44:20", "throughput": 5896.22, "total_tokens": 2412944} {"current_steps": 3960, "total_steps": 64460, "loss": 0.2314, "lr": 6.141793360223395e-06, "epoch": 1.2286689419795223, "percentage": 6.14, "elapsed_time": "0:06:49", "remaining_time": "1:44:19", "throughput": 5897.01, "total_tokens": 2416240} {"current_steps": 3965, "total_steps": 64460, "loss": 0.2316, "lr": 6.149550108594478e-06, "epoch": 1.2302202916537388, "percentage": 6.15, "elapsed_time": "0:06:50", "remaining_time": "1:44:19", "throughput": 5897.91, "total_tokens": 2419824} {"current_steps": 3970, "total_steps": 64460, "loss": 0.2316, "lr": 6.157306856965561e-06, "epoch": 1.2317716413279554, "percentage": 6.16, "elapsed_time": "0:06:50", "remaining_time": "1:44:19", "throughput": 5898.68, "total_tokens": 2423408} {"current_steps": 3975, "total_steps": 64460, "loss": 0.2341, "lr": 6.165063605336643e-06, "epoch": 1.233322991002172, "percentage": 6.17, "elapsed_time": "0:06:51", "remaining_time": "1:44:19", "throughput": 5899.41, "total_tokens": 2426832} {"current_steps": 3980, "total_steps": 64460, "loss": 0.2321, "lr": 6.172820353707726e-06, "epoch": 1.2348743406763885, "percentage": 6.17, "elapsed_time": "0:06:51", "remaining_time": "1:44:19", "throughput": 5900.01, "total_tokens": 2430160} {"current_steps": 3985, "total_steps": 64460, "loss": 0.2324, "lr": 6.180577102078809e-06, "epoch": 1.236425690350605, "percentage": 6.18, "elapsed_time": "0:06:52", "remaining_time": "1:44:17", "throughput": 5899.21, "total_tokens": 2432400} {"current_steps": 3990, "total_steps": 64460, "loss": 0.2188, "lr": 6.1883338504498925e-06, "epoch": 1.2379770400248216, "percentage": 6.19, "elapsed_time": "0:06:52", "remaining_time": "1:44:15", "throughput": 5898.74, "total_tokens": 2434928} {"current_steps": 3995, "total_steps": 64460, "loss": 0.2358, "lr": 6.1960905988209755e-06, "epoch": 1.2395283896990381, "percentage": 6.2, "elapsed_time": "0:06:53", "remaining_time": "1:44:15", "throughput": 5898.73, "total_tokens": 2438160} {"current_steps": 4000, "total_steps": 64460, "loss": 0.2447, "lr": 6.203847347192058e-06, "epoch": 1.2410797393732547, "percentage": 6.21, "elapsed_time": "0:06:53", "remaining_time": "1:44:15", "throughput": 5899.63, "total_tokens": 2441648} {"current_steps": 4005, "total_steps": 64460, "loss": 0.2289, "lr": 6.211604095563141e-06, "epoch": 1.2426310890474712, "percentage": 6.21, "elapsed_time": "0:06:54", "remaining_time": "1:44:13", "throughput": 5898.93, "total_tokens": 2443984} {"current_steps": 4010, "total_steps": 64460, "loss": 0.2388, "lr": 6.219360843934224e-06, "epoch": 1.2441824387216878, "percentage": 6.22, "elapsed_time": "0:06:54", "remaining_time": "1:44:13", "throughput": 5897.6, "total_tokens": 2446384} {"current_steps": 4015, "total_steps": 64460, "loss": 0.2312, "lr": 6.227117592305307e-06, "epoch": 1.2457337883959045, "percentage": 6.23, "elapsed_time": "0:06:55", "remaining_time": "1:44:13", "throughput": 5898.6, "total_tokens": 2450032} {"current_steps": 4020, "total_steps": 64460, "loss": 0.2304, "lr": 6.234874340676389e-06, "epoch": 1.247285138070121, "percentage": 6.24, "elapsed_time": "0:06:55", "remaining_time": "1:44:11", "throughput": 5898.83, "total_tokens": 2452784} {"current_steps": 4025, "total_steps": 64460, "loss": 0.2426, "lr": 6.242631089047472e-06, "epoch": 1.2488364877443376, "percentage": 6.24, "elapsed_time": "0:06:56", "remaining_time": "1:44:10", "throughput": 5897.7, "total_tokens": 2454960} {"current_steps": 4030, "total_steps": 64460, "loss": 0.2342, "lr": 6.250387837418555e-06, "epoch": 1.2503878374185542, "percentage": 6.25, "elapsed_time": "0:06:56", "remaining_time": "1:44:08", "throughput": 5897.68, "total_tokens": 2457616} {"current_steps": 4035, "total_steps": 64460, "loss": 0.2317, "lr": 6.258144585789637e-06, "epoch": 1.2519391870927707, "percentage": 6.26, "elapsed_time": "0:06:57", "remaining_time": "1:44:11", "throughput": 5897.84, "total_tokens": 2461904} {"current_steps": 4040, "total_steps": 64460, "loss": 0.2495, "lr": 6.26590133416072e-06, "epoch": 1.2534905367669873, "percentage": 6.27, "elapsed_time": "0:06:57", "remaining_time": "1:44:10", "throughput": 5898.8, "total_tokens": 2465456} {"current_steps": 4045, "total_steps": 64460, "loss": 0.2192, "lr": 6.273658082531803e-06, "epoch": 1.2550418864412038, "percentage": 6.28, "elapsed_time": "0:06:58", "remaining_time": "1:44:14", "throughput": 5900.77, "total_tokens": 2470960} {"current_steps": 4050, "total_steps": 64460, "loss": 0.2186, "lr": 6.281414830902886e-06, "epoch": 1.2565932361154204, "percentage": 6.28, "elapsed_time": "0:06:59", "remaining_time": "1:44:13", "throughput": 5901.22, "total_tokens": 2474160} {"current_steps": 4055, "total_steps": 64460, "loss": 0.2359, "lr": 6.28917157927397e-06, "epoch": 1.258144585789637, "percentage": 6.29, "elapsed_time": "0:06:59", "remaining_time": "1:44:12", "throughput": 5900.77, "total_tokens": 2476688} {"current_steps": 4060, "total_steps": 64460, "loss": 0.2668, "lr": 6.296928327645052e-06, "epoch": 1.2596959354638535, "percentage": 6.3, "elapsed_time": "0:07:00", "remaining_time": "1:44:10", "throughput": 5900.73, "total_tokens": 2479376} {"current_steps": 4065, "total_steps": 64460, "loss": 0.2459, "lr": 6.304685076016135e-06, "epoch": 1.26124728513807, "percentage": 6.31, "elapsed_time": "0:07:00", "remaining_time": "1:44:09", "throughput": 5900.53, "total_tokens": 2482128} {"current_steps": 4070, "total_steps": 64460, "loss": 0.2189, "lr": 6.312441824387218e-06, "epoch": 1.2627986348122868, "percentage": 6.31, "elapsed_time": "0:07:01", "remaining_time": "1:44:08", "throughput": 5899.95, "total_tokens": 2484656} {"current_steps": 4075, "total_steps": 64460, "loss": 0.2352, "lr": 6.320198572758301e-06, "epoch": 1.2643499844865032, "percentage": 6.32, "elapsed_time": "0:07:01", "remaining_time": "1:44:07", "throughput": 5900.02, "total_tokens": 2487376} {"current_steps": 4080, "total_steps": 64460, "loss": 0.2387, "lr": 6.327955321129383e-06, "epoch": 1.26590133416072, "percentage": 6.33, "elapsed_time": "0:07:02", "remaining_time": "1:44:05", "throughput": 5899.38, "total_tokens": 2489776} {"current_steps": 4085, "total_steps": 64460, "loss": 0.2521, "lr": 6.335712069500466e-06, "epoch": 1.2674526838349365, "percentage": 6.34, "elapsed_time": "0:07:02", "remaining_time": "1:44:06", "throughput": 5899.58, "total_tokens": 2493488} {"current_steps": 4090, "total_steps": 64460, "loss": 0.2136, "lr": 6.343468817871549e-06, "epoch": 1.269004033509153, "percentage": 6.35, "elapsed_time": "0:07:03", "remaining_time": "1:44:05", "throughput": 5899.4, "total_tokens": 2496304} {"current_steps": 4095, "total_steps": 64460, "loss": 0.2611, "lr": 6.351225566242632e-06, "epoch": 1.2705553831833696, "percentage": 6.35, "elapsed_time": "0:07:03", "remaining_time": "1:44:05", "throughput": 5899.94, "total_tokens": 2499632} {"current_steps": 4100, "total_steps": 64460, "loss": 0.2354, "lr": 6.358982314613714e-06, "epoch": 1.2721067328575861, "percentage": 6.36, "elapsed_time": "0:07:04", "remaining_time": "1:44:05", "throughput": 5900.42, "total_tokens": 2503024} {"current_steps": 4105, "total_steps": 64460, "loss": 0.2219, "lr": 6.366739062984797e-06, "epoch": 1.2736580825318027, "percentage": 6.37, "elapsed_time": "0:07:04", "remaining_time": "1:44:04", "throughput": 5899.28, "total_tokens": 2505456} {"current_steps": 4110, "total_steps": 64460, "loss": 0.2514, "lr": 6.37449581135588e-06, "epoch": 1.2752094322060192, "percentage": 6.38, "elapsed_time": "0:07:05", "remaining_time": "1:44:04", "throughput": 5899.71, "total_tokens": 2508912} {"current_steps": 4115, "total_steps": 64460, "loss": 0.2335, "lr": 6.382252559726962e-06, "epoch": 1.2767607818802358, "percentage": 6.38, "elapsed_time": "0:07:05", "remaining_time": "1:44:03", "throughput": 5899.81, "total_tokens": 2511824} {"current_steps": 4120, "total_steps": 64460, "loss": 0.2364, "lr": 6.390009308098047e-06, "epoch": 1.2783121315544523, "percentage": 6.39, "elapsed_time": "0:07:06", "remaining_time": "1:44:02", "throughput": 5900.3, "total_tokens": 2515024} {"current_steps": 4125, "total_steps": 64460, "loss": 0.2234, "lr": 6.397766056469129e-06, "epoch": 1.2798634812286689, "percentage": 6.4, "elapsed_time": "0:07:06", "remaining_time": "1:44:01", "throughput": 5900.35, "total_tokens": 2517712} {"current_steps": 4130, "total_steps": 64460, "loss": 0.2318, "lr": 6.405522804840212e-06, "epoch": 1.2814148309028854, "percentage": 6.41, "elapsed_time": "0:07:07", "remaining_time": "1:44:00", "throughput": 5900.16, "total_tokens": 2520400} {"current_steps": 4135, "total_steps": 64460, "loss": 0.263, "lr": 6.413279553211295e-06, "epoch": 1.2829661805771022, "percentage": 6.41, "elapsed_time": "0:07:07", "remaining_time": "1:43:59", "throughput": 5900.85, "total_tokens": 2523760} {"current_steps": 4140, "total_steps": 64460, "loss": 0.2255, "lr": 6.421036301582377e-06, "epoch": 1.2845175302513185, "percentage": 6.42, "elapsed_time": "0:07:08", "remaining_time": "1:44:00", "throughput": 5900.79, "total_tokens": 2527344} {"current_steps": 4145, "total_steps": 64460, "loss": 0.2443, "lr": 6.42879304995346e-06, "epoch": 1.2860688799255353, "percentage": 6.43, "elapsed_time": "0:07:08", "remaining_time": "1:43:59", "throughput": 5900.88, "total_tokens": 2530320} {"current_steps": 4150, "total_steps": 64460, "loss": 0.2313, "lr": 6.436549798324543e-06, "epoch": 1.2876202295997519, "percentage": 6.44, "elapsed_time": "0:07:09", "remaining_time": "1:43:58", "throughput": 5899.96, "total_tokens": 2532752} {"current_steps": 4155, "total_steps": 64460, "loss": 0.2325, "lr": 6.444306546695626e-06, "epoch": 1.2891715792739684, "percentage": 6.45, "elapsed_time": "0:07:09", "remaining_time": "1:43:57", "throughput": 5898.84, "total_tokens": 2535056} {"current_steps": 4160, "total_steps": 64460, "loss": 0.2303, "lr": 6.452063295066708e-06, "epoch": 1.290722928948185, "percentage": 6.45, "elapsed_time": "0:07:10", "remaining_time": "1:43:58", "throughput": 5899.08, "total_tokens": 2538800} {"current_steps": 4165, "total_steps": 64460, "loss": 0.2357, "lr": 6.459820043437791e-06, "epoch": 1.2922742786224015, "percentage": 6.46, "elapsed_time": "0:07:10", "remaining_time": "1:43:57", "throughput": 5899.06, "total_tokens": 2541872} {"current_steps": 4170, "total_steps": 64460, "loss": 0.2316, "lr": 6.467576791808874e-06, "epoch": 1.293825628296618, "percentage": 6.47, "elapsed_time": "0:07:11", "remaining_time": "1:43:57", "throughput": 5899.33, "total_tokens": 2544912} {"current_steps": 4175, "total_steps": 64460, "loss": 0.2345, "lr": 6.475333540179957e-06, "epoch": 1.2953769779708346, "percentage": 6.48, "elapsed_time": "0:07:11", "remaining_time": "1:43:55", "throughput": 5898.84, "total_tokens": 2547376} {"current_steps": 4180, "total_steps": 64460, "loss": 0.2284, "lr": 6.483090288551039e-06, "epoch": 1.2969283276450512, "percentage": 6.48, "elapsed_time": "0:07:12", "remaining_time": "1:43:55", "throughput": 5899.57, "total_tokens": 2550704} {"current_steps": 4185, "total_steps": 64460, "loss": 0.2423, "lr": 6.490847036922123e-06, "epoch": 1.2984796773192677, "percentage": 6.49, "elapsed_time": "0:07:12", "remaining_time": "1:43:53", "throughput": 5899.6, "total_tokens": 2553392} {"current_steps": 4190, "total_steps": 64460, "loss": 0.2311, "lr": 6.498603785293206e-06, "epoch": 1.3000310269934843, "percentage": 6.5, "elapsed_time": "0:07:13", "remaining_time": "1:43:52", "throughput": 5899.04, "total_tokens": 2555888} {"current_steps": 4195, "total_steps": 64460, "loss": 0.2321, "lr": 6.506360533664289e-06, "epoch": 1.3015823766677008, "percentage": 6.51, "elapsed_time": "0:07:13", "remaining_time": "1:43:53", "throughput": 5899.0, "total_tokens": 2559440} {"current_steps": 4200, "total_steps": 64460, "loss": 0.2284, "lr": 6.514117282035372e-06, "epoch": 1.3031337263419176, "percentage": 6.52, "elapsed_time": "0:07:14", "remaining_time": "1:43:51", "throughput": 5898.35, "total_tokens": 2561840} {"current_steps": 4205, "total_steps": 64460, "loss": 0.233, "lr": 6.521874030406454e-06, "epoch": 1.304685076016134, "percentage": 6.52, "elapsed_time": "0:07:14", "remaining_time": "1:43:50", "throughput": 5898.75, "total_tokens": 2564976} {"current_steps": 4210, "total_steps": 64460, "loss": 0.23, "lr": 6.529630778777537e-06, "epoch": 1.3062364256903507, "percentage": 6.53, "elapsed_time": "0:07:15", "remaining_time": "1:43:50", "throughput": 5899.41, "total_tokens": 2568304} {"current_steps": 4215, "total_steps": 64460, "loss": 0.2393, "lr": 6.53738752714862e-06, "epoch": 1.3077877753645673, "percentage": 6.54, "elapsed_time": "0:07:15", "remaining_time": "1:43:48", "throughput": 5899.89, "total_tokens": 2571184} {"current_steps": 4220, "total_steps": 64460, "loss": 0.2346, "lr": 6.545144275519702e-06, "epoch": 1.3093391250387838, "percentage": 6.55, "elapsed_time": "0:07:16", "remaining_time": "1:43:47", "throughput": 5899.62, "total_tokens": 2573680} {"current_steps": 4225, "total_steps": 64460, "loss": 0.2346, "lr": 6.552901023890785e-06, "epoch": 1.3108904747130004, "percentage": 6.55, "elapsed_time": "0:07:16", "remaining_time": "1:43:46", "throughput": 5899.4, "total_tokens": 2576656} {"current_steps": 4230, "total_steps": 64460, "loss": 0.2346, "lr": 6.560657772261868e-06, "epoch": 1.312441824387217, "percentage": 6.56, "elapsed_time": "0:07:17", "remaining_time": "1:43:45", "throughput": 5898.87, "total_tokens": 2578960} {"current_steps": 4235, "total_steps": 64460, "loss": 0.2294, "lr": 6.568414520632951e-06, "epoch": 1.3139931740614335, "percentage": 6.57, "elapsed_time": "0:07:17", "remaining_time": "1:43:44", "throughput": 5899.66, "total_tokens": 2582288} {"current_steps": 4240, "total_steps": 64460, "loss": 0.2327, "lr": 6.576171269004033e-06, "epoch": 1.31554452373565, "percentage": 6.58, "elapsed_time": "0:07:18", "remaining_time": "1:43:42", "throughput": 5899.83, "total_tokens": 2584976} {"current_steps": 4245, "total_steps": 64460, "loss": 0.2294, "lr": 6.583928017375117e-06, "epoch": 1.3170958734098666, "percentage": 6.59, "elapsed_time": "0:07:18", "remaining_time": "1:43:42", "throughput": 5899.5, "total_tokens": 2587760} {"current_steps": 4250, "total_steps": 64460, "loss": 0.2307, "lr": 6.5916847657462e-06, "epoch": 1.318647223084083, "percentage": 6.59, "elapsed_time": "0:07:19", "remaining_time": "1:43:41", "throughput": 5899.88, "total_tokens": 2590768} {"current_steps": 4255, "total_steps": 64460, "loss": 0.2302, "lr": 6.599441514117283e-06, "epoch": 1.3201985727582997, "percentage": 6.6, "elapsed_time": "0:07:19", "remaining_time": "1:43:40", "throughput": 5900.45, "total_tokens": 2594160} {"current_steps": 4260, "total_steps": 64460, "loss": 0.223, "lr": 6.607198262488366e-06, "epoch": 1.3217499224325162, "percentage": 6.61, "elapsed_time": "0:07:20", "remaining_time": "1:43:40", "throughput": 5900.52, "total_tokens": 2597264} {"current_steps": 4265, "total_steps": 64460, "loss": 0.2429, "lr": 6.614955010859448e-06, "epoch": 1.323301272106733, "percentage": 6.62, "elapsed_time": "0:07:20", "remaining_time": "1:43:43", "throughput": 5901.89, "total_tokens": 2602256} {"current_steps": 4270, "total_steps": 64460, "loss": 0.223, "lr": 6.622711759230531e-06, "epoch": 1.3248526217809493, "percentage": 6.62, "elapsed_time": "0:07:21", "remaining_time": "1:43:43", "throughput": 5903.39, "total_tokens": 2606384} {"current_steps": 4275, "total_steps": 64460, "loss": 0.2363, "lr": 6.630468507601614e-06, "epoch": 1.326403971455166, "percentage": 6.63, "elapsed_time": "0:07:21", "remaining_time": "1:43:42", "throughput": 5903.06, "total_tokens": 2608944} {"current_steps": 4280, "total_steps": 64460, "loss": 0.2437, "lr": 6.638225255972697e-06, "epoch": 1.3279553211293826, "percentage": 6.64, "elapsed_time": "0:07:22", "remaining_time": "1:43:40", "throughput": 5903.09, "total_tokens": 2611696} {"current_steps": 4285, "total_steps": 64460, "loss": 0.2335, "lr": 6.645982004343779e-06, "epoch": 1.3295066708035992, "percentage": 6.65, "elapsed_time": "0:07:22", "remaining_time": "1:43:40", "throughput": 5903.32, "total_tokens": 2614768} {"current_steps": 4290, "total_steps": 64460, "loss": 0.2237, "lr": 6.653738752714862e-06, "epoch": 1.3310580204778157, "percentage": 6.66, "elapsed_time": "0:07:23", "remaining_time": "1:43:38", "throughput": 5903.01, "total_tokens": 2617232} {"current_steps": 4295, "total_steps": 64460, "loss": 0.2328, "lr": 6.661495501085945e-06, "epoch": 1.3326093701520323, "percentage": 6.66, "elapsed_time": "0:07:23", "remaining_time": "1:43:38", "throughput": 5903.39, "total_tokens": 2620464} {"current_steps": 4300, "total_steps": 64460, "loss": 0.2317, "lr": 6.669252249457027e-06, "epoch": 1.3341607198262488, "percentage": 6.67, "elapsed_time": "0:07:24", "remaining_time": "1:43:37", "throughput": 5903.97, "total_tokens": 2623920} {"current_steps": 4305, "total_steps": 64460, "loss": 0.2264, "lr": 6.67700899782811e-06, "epoch": 1.3357120695004654, "percentage": 6.68, "elapsed_time": "0:07:24", "remaining_time": "1:43:36", "throughput": 5903.55, "total_tokens": 2626480} {"current_steps": 4310, "total_steps": 64460, "loss": 0.2335, "lr": 6.684765746199194e-06, "epoch": 1.337263419174682, "percentage": 6.69, "elapsed_time": "0:07:25", "remaining_time": "1:43:35", "throughput": 5903.87, "total_tokens": 2629264} {"current_steps": 4315, "total_steps": 64460, "loss": 0.2266, "lr": 6.692522494570277e-06, "epoch": 1.3388147688488985, "percentage": 6.69, "elapsed_time": "0:07:25", "remaining_time": "1:43:34", "throughput": 5904.27, "total_tokens": 2632272} {"current_steps": 4320, "total_steps": 64460, "loss": 0.2348, "lr": 6.70027924294136e-06, "epoch": 1.340366118523115, "percentage": 6.7, "elapsed_time": "0:07:26", "remaining_time": "1:43:32", "throughput": 5904.0, "total_tokens": 2634704} {"current_steps": 4325, "total_steps": 64460, "loss": 0.2276, "lr": 6.708035991312442e-06, "epoch": 1.3419174681973316, "percentage": 6.71, "elapsed_time": "0:07:26", "remaining_time": "1:43:31", "throughput": 5904.44, "total_tokens": 2637744} {"current_steps": 4330, "total_steps": 64460, "loss": 0.2319, "lr": 6.715792739683525e-06, "epoch": 1.3434688178715484, "percentage": 6.72, "elapsed_time": "0:07:27", "remaining_time": "1:43:30", "throughput": 5904.6, "total_tokens": 2640528} {"current_steps": 4335, "total_steps": 64460, "loss": 0.2345, "lr": 6.723549488054608e-06, "epoch": 1.3450201675457647, "percentage": 6.73, "elapsed_time": "0:07:27", "remaining_time": "1:43:29", "throughput": 5904.55, "total_tokens": 2643376} {"current_steps": 4340, "total_steps": 64460, "loss": 0.2251, "lr": 6.731306236425691e-06, "epoch": 1.3465715172199815, "percentage": 6.73, "elapsed_time": "0:07:28", "remaining_time": "1:43:27", "throughput": 5904.35, "total_tokens": 2645936} {"current_steps": 4345, "total_steps": 64460, "loss": 0.2473, "lr": 6.739062984796773e-06, "epoch": 1.348122866894198, "percentage": 6.74, "elapsed_time": "0:07:28", "remaining_time": "1:43:27", "throughput": 5905.28, "total_tokens": 2649520} {"current_steps": 4350, "total_steps": 64460, "loss": 0.2098, "lr": 6.746819733167856e-06, "epoch": 1.3496742165684146, "percentage": 6.75, "elapsed_time": "0:07:29", "remaining_time": "1:43:26", "throughput": 5905.73, "total_tokens": 2652624} {"current_steps": 4355, "total_steps": 64460, "loss": 0.2245, "lr": 6.754576481538939e-06, "epoch": 1.3512255662426311, "percentage": 6.76, "elapsed_time": "0:07:29", "remaining_time": "1:43:25", "throughput": 5905.95, "total_tokens": 2655504} {"current_steps": 4360, "total_steps": 64460, "loss": 0.2247, "lr": 6.762333229910022e-06, "epoch": 1.3527769159168477, "percentage": 6.76, "elapsed_time": "0:07:30", "remaining_time": "1:43:24", "throughput": 5905.99, "total_tokens": 2658192} {"current_steps": 4365, "total_steps": 64460, "loss": 0.2753, "lr": 6.7700899782811045e-06, "epoch": 1.3543282655910642, "percentage": 6.77, "elapsed_time": "0:07:30", "remaining_time": "1:43:22", "throughput": 5906.29, "total_tokens": 2661104} {"current_steps": 4370, "total_steps": 64460, "loss": 0.2403, "lr": 6.7778467266521874e-06, "epoch": 1.3558796152652808, "percentage": 6.78, "elapsed_time": "0:07:31", "remaining_time": "1:43:21", "throughput": 5906.41, "total_tokens": 2663952} {"current_steps": 4375, "total_steps": 64460, "loss": 0.2397, "lr": 6.785603475023271e-06, "epoch": 1.3574309649394973, "percentage": 6.79, "elapsed_time": "0:07:31", "remaining_time": "1:43:25", "throughput": 5907.62, "total_tokens": 2669168} {"current_steps": 4380, "total_steps": 64460, "loss": 0.2268, "lr": 6.793360223394354e-06, "epoch": 1.3589823146137139, "percentage": 6.79, "elapsed_time": "0:07:32", "remaining_time": "1:43:24", "throughput": 5908.0, "total_tokens": 2672464} {"current_steps": 4385, "total_steps": 64460, "loss": 0.2273, "lr": 6.801116971765437e-06, "epoch": 1.3605336642879304, "percentage": 6.8, "elapsed_time": "0:07:32", "remaining_time": "1:43:23", "throughput": 5907.72, "total_tokens": 2674864} {"current_steps": 4390, "total_steps": 64460, "loss": 0.2363, "lr": 6.808873720136519e-06, "epoch": 1.362085013962147, "percentage": 6.81, "elapsed_time": "0:07:33", "remaining_time": "1:43:22", "throughput": 5908.48, "total_tokens": 2678448} {"current_steps": 4395, "total_steps": 64460, "loss": 0.2319, "lr": 6.816630468507602e-06, "epoch": 1.3636363636363638, "percentage": 6.82, "elapsed_time": "0:07:33", "remaining_time": "1:43:24", "throughput": 5909.51, "total_tokens": 2682640} {"current_steps": 4400, "total_steps": 64460, "loss": 0.2243, "lr": 6.824387216878685e-06, "epoch": 1.36518771331058, "percentage": 6.83, "elapsed_time": "0:07:34", "remaining_time": "1:43:25", "throughput": 5910.88, "total_tokens": 2686992} {"current_steps": 4405, "total_steps": 64460, "loss": 0.2341, "lr": 6.8321439652497675e-06, "epoch": 1.3667390629847969, "percentage": 6.83, "elapsed_time": "0:07:35", "remaining_time": "1:43:23", "throughput": 5910.59, "total_tokens": 2689616} {"current_steps": 4410, "total_steps": 64460, "loss": 0.2351, "lr": 6.8399007136208505e-06, "epoch": 1.3682904126590134, "percentage": 6.84, "elapsed_time": "0:07:35", "remaining_time": "1:43:22", "throughput": 5911.03, "total_tokens": 2692560} {"current_steps": 4415, "total_steps": 64460, "loss": 0.2269, "lr": 6.8476574619919334e-06, "epoch": 1.36984176233323, "percentage": 6.85, "elapsed_time": "0:07:35", "remaining_time": "1:43:21", "throughput": 5911.37, "total_tokens": 2695440} {"current_steps": 4420, "total_steps": 64460, "loss": 0.2302, "lr": 6.8554142103630164e-06, "epoch": 1.3713931120074465, "percentage": 6.86, "elapsed_time": "0:07:36", "remaining_time": "1:43:19", "throughput": 5911.29, "total_tokens": 2698064} {"current_steps": 4425, "total_steps": 64460, "loss": 0.2363, "lr": 6.8631709587340986e-06, "epoch": 1.372944461681663, "percentage": 6.86, "elapsed_time": "0:07:37", "remaining_time": "1:43:21", "throughput": 5911.64, "total_tokens": 2702320} {"current_steps": 4430, "total_steps": 64460, "loss": 0.2288, "lr": 6.8709277071051816e-06, "epoch": 1.3744958113558796, "percentage": 6.87, "elapsed_time": "0:07:37", "remaining_time": "1:43:21", "throughput": 5912.69, "total_tokens": 2706096} {"current_steps": 4435, "total_steps": 64460, "loss": 0.2239, "lr": 6.8786844554762645e-06, "epoch": 1.3760471610300962, "percentage": 6.88, "elapsed_time": "0:07:38", "remaining_time": "1:43:22", "throughput": 5913.27, "total_tokens": 2709840} {"current_steps": 4440, "total_steps": 64460, "loss": 0.2436, "lr": 6.886441203847348e-06, "epoch": 1.3775985107043127, "percentage": 6.89, "elapsed_time": "0:07:38", "remaining_time": "1:43:23", "throughput": 5914.6, "total_tokens": 2714256} {"current_steps": 4445, "total_steps": 64460, "loss": 0.2386, "lr": 6.894197952218431e-06, "epoch": 1.3791498603785293, "percentage": 6.9, "elapsed_time": "0:07:39", "remaining_time": "1:43:22", "throughput": 5914.84, "total_tokens": 2717136} {"current_steps": 4450, "total_steps": 64460, "loss": 0.237, "lr": 6.9019547005895135e-06, "epoch": 1.3807012100527458, "percentage": 6.9, "elapsed_time": "0:07:39", "remaining_time": "1:43:21", "throughput": 5914.77, "total_tokens": 2719920} {"current_steps": 4455, "total_steps": 64460, "loss": 0.231, "lr": 6.9097114489605965e-06, "epoch": 1.3822525597269624, "percentage": 6.91, "elapsed_time": "0:07:40", "remaining_time": "1:43:20", "throughput": 5915.5, "total_tokens": 2723408} {"current_steps": 4460, "total_steps": 64460, "loss": 0.2352, "lr": 6.9174681973316795e-06, "epoch": 1.3838039094011791, "percentage": 6.92, "elapsed_time": "0:07:40", "remaining_time": "1:43:19", "throughput": 5914.86, "total_tokens": 2725584} {"current_steps": 4465, "total_steps": 64460, "loss": 0.2358, "lr": 6.9252249457027624e-06, "epoch": 1.3853552590753955, "percentage": 6.93, "elapsed_time": "0:07:41", "remaining_time": "1:43:18", "throughput": 5914.28, "total_tokens": 2728144} {"current_steps": 4470, "total_steps": 64460, "loss": 0.2346, "lr": 6.9329816940738446e-06, "epoch": 1.3869066087496122, "percentage": 6.93, "elapsed_time": "0:07:41", "remaining_time": "1:43:17", "throughput": 5915.0, "total_tokens": 2731472} {"current_steps": 4475, "total_steps": 64460, "loss": 0.2379, "lr": 6.9407384424449276e-06, "epoch": 1.3884579584238288, "percentage": 6.94, "elapsed_time": "0:07:42", "remaining_time": "1:43:19", "throughput": 5915.42, "total_tokens": 2735664} {"current_steps": 4480, "total_steps": 64460, "loss": 0.2293, "lr": 6.9484951908160105e-06, "epoch": 1.3900093080980453, "percentage": 6.95, "elapsed_time": "0:07:42", "remaining_time": "1:43:17", "throughput": 5914.99, "total_tokens": 2738064} {"current_steps": 4485, "total_steps": 64460, "loss": 0.2304, "lr": 6.956251939187093e-06, "epoch": 1.391560657772262, "percentage": 6.96, "elapsed_time": "0:07:43", "remaining_time": "1:43:18", "throughput": 5915.86, "total_tokens": 2742096} {"current_steps": 4490, "total_steps": 64460, "loss": 0.2325, "lr": 6.964008687558176e-06, "epoch": 1.3931120074464785, "percentage": 6.97, "elapsed_time": "0:07:43", "remaining_time": "1:43:16", "throughput": 5915.8, "total_tokens": 2744560} {"current_steps": 4495, "total_steps": 64460, "loss": 0.2337, "lr": 6.971765435929259e-06, "epoch": 1.394663357120695, "percentage": 6.97, "elapsed_time": "0:07:44", "remaining_time": "1:43:15", "throughput": 5916.19, "total_tokens": 2747568} {"current_steps": 4500, "total_steps": 64460, "loss": 0.2295, "lr": 6.979522184300342e-06, "epoch": 1.3962147067949116, "percentage": 6.98, "elapsed_time": "0:07:44", "remaining_time": "1:43:14", "throughput": 5916.13, "total_tokens": 2750256} {"current_steps": 4505, "total_steps": 64460, "loss": 0.2298, "lr": 6.9872789326714255e-06, "epoch": 1.397766056469128, "percentage": 6.99, "elapsed_time": "0:07:45", "remaining_time": "1:43:13", "throughput": 5916.31, "total_tokens": 2753328} {"current_steps": 4510, "total_steps": 64460, "loss": 0.2288, "lr": 6.995035681042508e-06, "epoch": 1.3993174061433447, "percentage": 7.0, "elapsed_time": "0:07:45", "remaining_time": "1:43:13", "throughput": 5917.29, "total_tokens": 2757072} {"current_steps": 4515, "total_steps": 64460, "loss": 0.2354, "lr": 7.002792429413591e-06, "epoch": 1.4008687558175612, "percentage": 7.0, "elapsed_time": "0:07:46", "remaining_time": "1:43:13", "throughput": 5918.26, "total_tokens": 2760784} {"current_steps": 4520, "total_steps": 64460, "loss": 0.2363, "lr": 7.0105491777846736e-06, "epoch": 1.4024201054917778, "percentage": 7.01, "elapsed_time": "0:07:46", "remaining_time": "1:43:12", "throughput": 5918.27, "total_tokens": 2763472} {"current_steps": 4525, "total_steps": 64460, "loss": 0.2264, "lr": 7.0183059261557565e-06, "epoch": 1.4039714551659945, "percentage": 7.02, "elapsed_time": "0:07:47", "remaining_time": "1:43:11", "throughput": 5918.48, "total_tokens": 2766448} {"current_steps": 4530, "total_steps": 64460, "loss": 0.23, "lr": 7.026062674526839e-06, "epoch": 1.4055228048402109, "percentage": 7.03, "elapsed_time": "0:07:47", "remaining_time": "1:43:10", "throughput": 5918.37, "total_tokens": 2769168} {"current_steps": 4535, "total_steps": 64460, "loss": 0.2112, "lr": 7.033819422897922e-06, "epoch": 1.4070741545144276, "percentage": 7.04, "elapsed_time": "0:07:48", "remaining_time": "1:43:08", "throughput": 5918.45, "total_tokens": 2771952} {"current_steps": 4540, "total_steps": 64460, "loss": 0.2381, "lr": 7.041576171269005e-06, "epoch": 1.4086255041886442, "percentage": 7.04, "elapsed_time": "0:07:48", "remaining_time": "1:43:07", "throughput": 5918.13, "total_tokens": 2774320} {"current_steps": 4545, "total_steps": 64460, "loss": 0.2182, "lr": 7.049332919640088e-06, "epoch": 1.4101768538628607, "percentage": 7.05, "elapsed_time": "0:07:49", "remaining_time": "1:43:06", "throughput": 5918.35, "total_tokens": 2777264} {"current_steps": 4550, "total_steps": 64460, "loss": 0.2355, "lr": 7.05708966801117e-06, "epoch": 1.4117282035370773, "percentage": 7.06, "elapsed_time": "0:07:49", "remaining_time": "1:43:05", "throughput": 5918.24, "total_tokens": 2780208} {"current_steps": 4555, "total_steps": 64460, "loss": 0.2578, "lr": 7.064846416382253e-06, "epoch": 1.4132795532112938, "percentage": 7.07, "elapsed_time": "0:07:50", "remaining_time": "1:43:04", "throughput": 5917.41, "total_tokens": 2782704} {"current_steps": 4560, "total_steps": 64460, "loss": 0.2372, "lr": 7.072603164753336e-06, "epoch": 1.4148309028855104, "percentage": 7.07, "elapsed_time": "0:07:50", "remaining_time": "1:43:03", "throughput": 5917.46, "total_tokens": 2785456} {"current_steps": 4565, "total_steps": 64460, "loss": 0.2305, "lr": 7.080359913124418e-06, "epoch": 1.416382252559727, "percentage": 7.08, "elapsed_time": "0:07:51", "remaining_time": "1:43:01", "throughput": 5917.29, "total_tokens": 2787952} {"current_steps": 4570, "total_steps": 64460, "loss": 0.2252, "lr": 7.0881166614955026e-06, "epoch": 1.4179336022339435, "percentage": 7.09, "elapsed_time": "0:07:51", "remaining_time": "1:43:01", "throughput": 5917.88, "total_tokens": 2791248} {"current_steps": 4575, "total_steps": 64460, "loss": 0.2307, "lr": 7.095873409866585e-06, "epoch": 1.41948495190816, "percentage": 7.1, "elapsed_time": "0:07:52", "remaining_time": "1:43:00", "throughput": 5918.26, "total_tokens": 2794320} {"current_steps": 4580, "total_steps": 64460, "loss": 0.2317, "lr": 7.103630158237668e-06, "epoch": 1.4210363015823766, "percentage": 7.11, "elapsed_time": "0:07:52", "remaining_time": "1:42:58", "throughput": 5918.34, "total_tokens": 2797008} {"current_steps": 4585, "total_steps": 64460, "loss": 0.229, "lr": 7.111386906608751e-06, "epoch": 1.4225876512565931, "percentage": 7.11, "elapsed_time": "0:07:53", "remaining_time": "1:42:57", "throughput": 5919.04, "total_tokens": 2800208} {"current_steps": 4590, "total_steps": 64460, "loss": 0.2248, "lr": 7.119143654979833e-06, "epoch": 1.42413900093081, "percentage": 7.12, "elapsed_time": "0:07:53", "remaining_time": "1:42:56", "throughput": 5919.13, "total_tokens": 2803056} {"current_steps": 4595, "total_steps": 64460, "loss": 0.2393, "lr": 7.126900403350916e-06, "epoch": 1.4256903506050262, "percentage": 7.13, "elapsed_time": "0:07:54", "remaining_time": "1:42:56", "throughput": 5919.67, "total_tokens": 2806288} {"current_steps": 4600, "total_steps": 64460, "loss": 0.2327, "lr": 7.134657151721999e-06, "epoch": 1.427241700279243, "percentage": 7.14, "elapsed_time": "0:07:54", "remaining_time": "1:42:55", "throughput": 5919.64, "total_tokens": 2809200} {"current_steps": 4605, "total_steps": 64460, "loss": 0.2325, "lr": 7.142413900093082e-06, "epoch": 1.4287930499534596, "percentage": 7.14, "elapsed_time": "0:07:55", "remaining_time": "1:42:56", "throughput": 5920.64, "total_tokens": 2813680} {"current_steps": 4610, "total_steps": 64460, "loss": 0.2282, "lr": 7.150170648464164e-06, "epoch": 1.4303443996276761, "percentage": 7.15, "elapsed_time": "0:07:55", "remaining_time": "1:42:55", "throughput": 5920.36, "total_tokens": 2816272} {"current_steps": 4615, "total_steps": 64460, "loss": 0.2304, "lr": 7.157927396835247e-06, "epoch": 1.4318957493018927, "percentage": 7.16, "elapsed_time": "0:07:56", "remaining_time": "1:42:53", "throughput": 5919.72, "total_tokens": 2818416} {"current_steps": 4620, "total_steps": 64460, "loss": 0.2372, "lr": 7.16568414520633e-06, "epoch": 1.4334470989761092, "percentage": 7.17, "elapsed_time": "0:07:56", "remaining_time": "1:42:54", "throughput": 5920.62, "total_tokens": 2822352} {"current_steps": 4625, "total_steps": 64460, "loss": 0.2333, "lr": 7.173440893577413e-06, "epoch": 1.4349984486503258, "percentage": 7.17, "elapsed_time": "0:07:57", "remaining_time": "1:42:53", "throughput": 5921.21, "total_tokens": 2825744} {"current_steps": 4630, "total_steps": 64460, "loss": 0.2298, "lr": 7.181197641948495e-06, "epoch": 1.4365497983245423, "percentage": 7.18, "elapsed_time": "0:07:57", "remaining_time": "1:42:52", "throughput": 5920.78, "total_tokens": 2828208} {"current_steps": 4635, "total_steps": 64460, "loss": 0.2339, "lr": 7.188954390319579e-06, "epoch": 1.4381011479987589, "percentage": 7.19, "elapsed_time": "0:07:58", "remaining_time": "1:42:50", "throughput": 5920.42, "total_tokens": 2830544} {"current_steps": 4640, "total_steps": 64460, "loss": 0.2325, "lr": 7.196711138690662e-06, "epoch": 1.4396524976729754, "percentage": 7.2, "elapsed_time": "0:07:58", "remaining_time": "1:42:50", "throughput": 5920.73, "total_tokens": 2833904} {"current_steps": 4645, "total_steps": 64460, "loss": 0.2294, "lr": 7.204467887061745e-06, "epoch": 1.441203847347192, "percentage": 7.21, "elapsed_time": "0:07:59", "remaining_time": "1:42:50", "throughput": 5920.94, "total_tokens": 2837168} {"current_steps": 4650, "total_steps": 64460, "loss": 0.2314, "lr": 7.212224635432828e-06, "epoch": 1.4427551970214085, "percentage": 7.21, "elapsed_time": "0:07:59", "remaining_time": "1:42:49", "throughput": 5920.72, "total_tokens": 2839920} {"current_steps": 4655, "total_steps": 64460, "loss": 0.2295, "lr": 7.21998138380391e-06, "epoch": 1.4443065466956253, "percentage": 7.22, "elapsed_time": "0:08:00", "remaining_time": "1:42:49", "throughput": 5921.58, "total_tokens": 2843568} {"current_steps": 4660, "total_steps": 64460, "loss": 0.241, "lr": 7.227738132174993e-06, "epoch": 1.4458578963698416, "percentage": 7.23, "elapsed_time": "0:08:00", "remaining_time": "1:42:48", "throughput": 5921.82, "total_tokens": 2846480} {"current_steps": 4665, "total_steps": 64460, "loss": 0.2335, "lr": 7.235494880546076e-06, "epoch": 1.4474092460440584, "percentage": 7.24, "elapsed_time": "0:08:01", "remaining_time": "1:42:46", "throughput": 5921.37, "total_tokens": 2848912} {"current_steps": 4670, "total_steps": 64460, "loss": 0.2295, "lr": 7.243251628917158e-06, "epoch": 1.448960595718275, "percentage": 7.24, "elapsed_time": "0:08:01", "remaining_time": "1:42:46", "throughput": 5922.09, "total_tokens": 2852272} {"current_steps": 4675, "total_steps": 64460, "loss": 0.2368, "lr": 7.251008377288241e-06, "epoch": 1.4505119453924915, "percentage": 7.25, "elapsed_time": "0:08:02", "remaining_time": "1:42:46", "throughput": 5922.7, "total_tokens": 2855792} {"current_steps": 4680, "total_steps": 64460, "loss": 0.2308, "lr": 7.258765125659324e-06, "epoch": 1.452063295066708, "percentage": 7.26, "elapsed_time": "0:08:02", "remaining_time": "1:42:44", "throughput": 5922.68, "total_tokens": 2858448} {"current_steps": 4685, "total_steps": 64460, "loss": 0.2332, "lr": 7.266521874030407e-06, "epoch": 1.4536146447409246, "percentage": 7.27, "elapsed_time": "0:08:03", "remaining_time": "1:42:43", "throughput": 5922.47, "total_tokens": 2860944} {"current_steps": 4690, "total_steps": 64460, "loss": 0.2321, "lr": 7.274278622401489e-06, "epoch": 1.4551659944151412, "percentage": 7.28, "elapsed_time": "0:08:03", "remaining_time": "1:42:42", "throughput": 5922.46, "total_tokens": 2863664} {"current_steps": 4695, "total_steps": 64460, "loss": 0.2273, "lr": 7.282035370772573e-06, "epoch": 1.4567173440893577, "percentage": 7.28, "elapsed_time": "0:08:04", "remaining_time": "1:42:41", "throughput": 5922.78, "total_tokens": 2866672} {"current_steps": 4700, "total_steps": 64460, "loss": 0.2282, "lr": 7.289792119143656e-06, "epoch": 1.4582686937635743, "percentage": 7.29, "elapsed_time": "0:08:04", "remaining_time": "1:42:40", "throughput": 5921.5, "total_tokens": 2868848} {"current_steps": 4705, "total_steps": 64460, "loss": 0.2343, "lr": 7.297548867514739e-06, "epoch": 1.4598200434377908, "percentage": 7.3, "elapsed_time": "0:08:05", "remaining_time": "1:42:40", "throughput": 5922.03, "total_tokens": 2872368} {"current_steps": 4710, "total_steps": 64460, "loss": 0.2354, "lr": 7.305305615885822e-06, "epoch": 1.4613713931120074, "percentage": 7.31, "elapsed_time": "0:08:05", "remaining_time": "1:42:39", "throughput": 5922.56, "total_tokens": 2875664} {"current_steps": 4715, "total_steps": 64460, "loss": 0.2315, "lr": 7.313062364256904e-06, "epoch": 1.462922742786224, "percentage": 7.31, "elapsed_time": "0:08:06", "remaining_time": "1:42:40", "throughput": 5923.23, "total_tokens": 2879856} {"current_steps": 4720, "total_steps": 64460, "loss": 0.2187, "lr": 7.320819112627987e-06, "epoch": 1.4644740924604407, "percentage": 7.32, "elapsed_time": "0:08:06", "remaining_time": "1:42:39", "throughput": 5923.84, "total_tokens": 2883024} {"current_steps": 4725, "total_steps": 64460, "loss": 0.2383, "lr": 7.32857586099907e-06, "epoch": 1.466025442134657, "percentage": 7.33, "elapsed_time": "0:08:07", "remaining_time": "1:42:39", "throughput": 5924.77, "total_tokens": 2886704} {"current_steps": 4730, "total_steps": 64460, "loss": 0.2354, "lr": 7.336332609370153e-06, "epoch": 1.4675767918088738, "percentage": 7.34, "elapsed_time": "0:08:07", "remaining_time": "1:42:38", "throughput": 5924.46, "total_tokens": 2889168} {"current_steps": 4735, "total_steps": 64460, "loss": 0.2317, "lr": 7.344089357741235e-06, "epoch": 1.4691281414830903, "percentage": 7.35, "elapsed_time": "0:08:08", "remaining_time": "1:42:37", "throughput": 5924.38, "total_tokens": 2891952} {"current_steps": 4740, "total_steps": 64460, "loss": 0.2328, "lr": 7.351846106112318e-06, "epoch": 1.470679491157307, "percentage": 7.35, "elapsed_time": "0:08:08", "remaining_time": "1:42:36", "throughput": 5924.47, "total_tokens": 2894864} {"current_steps": 4745, "total_steps": 64460, "loss": 0.2337, "lr": 7.359602854483401e-06, "epoch": 1.4722308408315234, "percentage": 7.36, "elapsed_time": "0:08:09", "remaining_time": "1:42:35", "throughput": 5925.14, "total_tokens": 2898224} {"current_steps": 4750, "total_steps": 64460, "loss": 0.234, "lr": 7.367359602854483e-06, "epoch": 1.47378219050574, "percentage": 7.37, "elapsed_time": "0:08:09", "remaining_time": "1:42:35", "throughput": 5925.75, "total_tokens": 2901808} {"current_steps": 4755, "total_steps": 64460, "loss": 0.2317, "lr": 7.375116351225566e-06, "epoch": 1.4753335401799565, "percentage": 7.38, "elapsed_time": "0:08:10", "remaining_time": "1:42:38", "throughput": 5927.26, "total_tokens": 2907088} {"current_steps": 4760, "total_steps": 64460, "loss": 0.2324, "lr": 7.38287309959665e-06, "epoch": 1.476884889854173, "percentage": 7.38, "elapsed_time": "0:08:10", "remaining_time": "1:42:37", "throughput": 5927.33, "total_tokens": 2910160} {"current_steps": 4765, "total_steps": 64460, "loss": 0.2311, "lr": 7.390629847967733e-06, "epoch": 1.4784362395283897, "percentage": 7.39, "elapsed_time": "0:08:11", "remaining_time": "1:42:37", "throughput": 5927.27, "total_tokens": 2913168} {"current_steps": 4770, "total_steps": 64460, "loss": 0.2344, "lr": 7.398386596338816e-06, "epoch": 1.4799875892026062, "percentage": 7.4, "elapsed_time": "0:08:11", "remaining_time": "1:42:36", "throughput": 5926.85, "total_tokens": 2915760} {"current_steps": 4775, "total_steps": 64460, "loss": 0.2369, "lr": 7.406143344709898e-06, "epoch": 1.4815389388768228, "percentage": 7.41, "elapsed_time": "0:08:12", "remaining_time": "1:42:34", "throughput": 5926.22, "total_tokens": 2918192} {"current_steps": 4780, "total_steps": 64460, "loss": 0.229, "lr": 7.413900093080981e-06, "epoch": 1.4830902885510393, "percentage": 7.42, "elapsed_time": "0:08:12", "remaining_time": "1:42:34", "throughput": 5926.54, "total_tokens": 2921200} {"current_steps": 4785, "total_steps": 64460, "loss": 0.2202, "lr": 7.421656841452064e-06, "epoch": 1.484641638225256, "percentage": 7.42, "elapsed_time": "0:08:13", "remaining_time": "1:42:33", "throughput": 5926.23, "total_tokens": 2923984} {"current_steps": 4790, "total_steps": 64460, "loss": 0.2277, "lr": 7.429413589823147e-06, "epoch": 1.4861929878994724, "percentage": 7.43, "elapsed_time": "0:08:13", "remaining_time": "1:42:32", "throughput": 5925.5, "total_tokens": 2926704} {"current_steps": 4795, "total_steps": 64460, "loss": 0.2227, "lr": 7.437170338194229e-06, "epoch": 1.4877443375736892, "percentage": 7.44, "elapsed_time": "0:08:14", "remaining_time": "1:42:31", "throughput": 5924.64, "total_tokens": 2929136} {"current_steps": 4800, "total_steps": 64460, "loss": 0.2358, "lr": 7.444927086565312e-06, "epoch": 1.4892956872479057, "percentage": 7.45, "elapsed_time": "0:08:14", "remaining_time": "1:42:30", "throughput": 5922.98, "total_tokens": 2931120} {"current_steps": 4805, "total_steps": 64460, "loss": 0.2439, "lr": 7.452683834936395e-06, "epoch": 1.4908470369221223, "percentage": 7.45, "elapsed_time": "0:08:15", "remaining_time": "1:42:29", "throughput": 5922.27, "total_tokens": 2933520} {"current_steps": 4810, "total_steps": 64460, "loss": 0.2386, "lr": 7.460440583307478e-06, "epoch": 1.4923983865963388, "percentage": 7.46, "elapsed_time": "0:08:15", "remaining_time": "1:42:28", "throughput": 5922.28, "total_tokens": 2936432} {"current_steps": 4815, "total_steps": 64460, "loss": 0.2289, "lr": 7.46819733167856e-06, "epoch": 1.4939497362705554, "percentage": 7.47, "elapsed_time": "0:08:16", "remaining_time": "1:42:28", "throughput": 5922.17, "total_tokens": 2939344} {"current_steps": 4820, "total_steps": 64460, "loss": 0.2325, "lr": 7.475954080049643e-06, "epoch": 1.495501085944772, "percentage": 7.48, "elapsed_time": "0:08:16", "remaining_time": "1:42:28", "throughput": 5922.69, "total_tokens": 2942832} {"current_steps": 4825, "total_steps": 64460, "loss": 0.2327, "lr": 7.483710828420727e-06, "epoch": 1.4970524356189885, "percentage": 7.49, "elapsed_time": "0:08:17", "remaining_time": "1:42:26", "throughput": 5922.48, "total_tokens": 2945424} {"current_steps": 4830, "total_steps": 64460, "loss": 0.2339, "lr": 7.49146757679181e-06, "epoch": 1.498603785293205, "percentage": 7.49, "elapsed_time": "0:08:17", "remaining_time": "1:42:26", "throughput": 5922.22, "total_tokens": 2948304} {"current_steps": 4835, "total_steps": 64460, "loss": 0.2338, "lr": 7.499224325162893e-06, "epoch": 1.5001551349674216, "percentage": 7.5, "elapsed_time": "0:08:18", "remaining_time": "1:42:25", "throughput": 5922.44, "total_tokens": 2951184} {"current_steps": 4840, "total_steps": 64460, "loss": 0.2327, "lr": 7.506981073533975e-06, "epoch": 1.5017064846416384, "percentage": 7.51, "elapsed_time": "0:08:18", "remaining_time": "1:42:24", "throughput": 5923.01, "total_tokens": 2954384} {"current_steps": 4845, "total_steps": 64460, "loss": 0.2346, "lr": 7.514737821905058e-06, "epoch": 1.5032578343158547, "percentage": 7.52, "elapsed_time": "0:08:19", "remaining_time": "1:42:24", "throughput": 5923.45, "total_tokens": 2958032} {"current_steps": 4850, "total_steps": 64460, "loss": 0.2304, "lr": 7.522494570276141e-06, "epoch": 1.5048091839900715, "percentage": 7.52, "elapsed_time": "0:08:19", "remaining_time": "1:42:24", "throughput": 5924.24, "total_tokens": 2961584} {"current_steps": 4855, "total_steps": 64460, "loss": 0.2283, "lr": 7.530251318647223e-06, "epoch": 1.5063605336642878, "percentage": 7.53, "elapsed_time": "0:08:20", "remaining_time": "1:42:24", "throughput": 5925.31, "total_tokens": 2965520} {"current_steps": 4860, "total_steps": 64460, "loss": 0.2275, "lr": 7.538008067018306e-06, "epoch": 1.5079118833385046, "percentage": 7.54, "elapsed_time": "0:08:20", "remaining_time": "1:42:23", "throughput": 5925.51, "total_tokens": 2968656} {"current_steps": 4865, "total_steps": 64460, "loss": 0.2231, "lr": 7.545764815389389e-06, "epoch": 1.5094632330127211, "percentage": 7.55, "elapsed_time": "0:08:21", "remaining_time": "1:42:22", "throughput": 5925.65, "total_tokens": 2971472} {"current_steps": 4870, "total_steps": 64460, "loss": 0.2318, "lr": 7.553521563760472e-06, "epoch": 1.5110145826869377, "percentage": 7.56, "elapsed_time": "0:08:21", "remaining_time": "1:42:21", "throughput": 5925.22, "total_tokens": 2973808} {"current_steps": 4875, "total_steps": 64460, "loss": 0.2208, "lr": 7.561278312131554e-06, "epoch": 1.5125659323611542, "percentage": 7.56, "elapsed_time": "0:08:22", "remaining_time": "1:42:20", "throughput": 5925.37, "total_tokens": 2976784} {"current_steps": 4880, "total_steps": 64460, "loss": 0.2405, "lr": 7.569035060502637e-06, "epoch": 1.5141172820353708, "percentage": 7.57, "elapsed_time": "0:08:22", "remaining_time": "1:42:19", "throughput": 5925.48, "total_tokens": 2979600} {"current_steps": 4885, "total_steps": 64460, "loss": 0.2211, "lr": 7.57679180887372e-06, "epoch": 1.5156686317095873, "percentage": 7.58, "elapsed_time": "0:08:23", "remaining_time": "1:42:18", "throughput": 5926.04, "total_tokens": 2982992} {"current_steps": 4890, "total_steps": 64460, "loss": 0.2348, "lr": 7.584548557244804e-06, "epoch": 1.5172199813838039, "percentage": 7.59, "elapsed_time": "0:08:23", "remaining_time": "1:42:17", "throughput": 5925.98, "total_tokens": 2985808} {"current_steps": 4895, "total_steps": 64460, "loss": 0.2421, "lr": 7.592305305615887e-06, "epoch": 1.5187713310580204, "percentage": 7.59, "elapsed_time": "0:08:24", "remaining_time": "1:42:17", "throughput": 5926.75, "total_tokens": 2989392} {"current_steps": 4900, "total_steps": 64460, "loss": 0.2238, "lr": 7.600062053986969e-06, "epoch": 1.520322680732237, "percentage": 7.6, "elapsed_time": "0:08:24", "remaining_time": "1:42:16", "throughput": 5926.33, "total_tokens": 2991888} {"current_steps": 4905, "total_steps": 64460, "loss": 0.2383, "lr": 7.607818802358052e-06, "epoch": 1.5218740304064537, "percentage": 7.61, "elapsed_time": "0:08:25", "remaining_time": "1:42:15", "throughput": 5925.92, "total_tokens": 2994576} {"current_steps": 4910, "total_steps": 64460, "loss": 0.2366, "lr": 7.615575550729135e-06, "epoch": 1.52342538008067, "percentage": 7.62, "elapsed_time": "0:08:25", "remaining_time": "1:42:15", "throughput": 5926.06, "total_tokens": 2997744} {"current_steps": 4915, "total_steps": 64460, "loss": 0.2274, "lr": 7.623332299100218e-06, "epoch": 1.5249767297548869, "percentage": 7.62, "elapsed_time": "0:08:26", "remaining_time": "1:42:16", "throughput": 5926.2, "total_tokens": 3001648} {"current_steps": 4920, "total_steps": 64460, "loss": 0.233, "lr": 7.631089047471301e-06, "epoch": 1.5265280794291032, "percentage": 7.63, "elapsed_time": "0:08:26", "remaining_time": "1:42:15", "throughput": 5924.98, "total_tokens": 3003856} {"current_steps": 4925, "total_steps": 64460, "loss": 0.2347, "lr": 7.638845795842383e-06, "epoch": 1.52807942910332, "percentage": 7.64, "elapsed_time": "0:08:27", "remaining_time": "1:42:15", "throughput": 5925.5, "total_tokens": 3007696} {"current_steps": 4930, "total_steps": 64460, "loss": 0.2336, "lr": 7.646602544213466e-06, "epoch": 1.5296307787775365, "percentage": 7.65, "elapsed_time": "0:08:28", "remaining_time": "1:42:16", "throughput": 5926.31, "total_tokens": 3011856} {"current_steps": 4935, "total_steps": 64460, "loss": 0.2326, "lr": 7.654359292584549e-06, "epoch": 1.531182128451753, "percentage": 7.66, "elapsed_time": "0:08:28", "remaining_time": "1:42:17", "throughput": 5926.89, "total_tokens": 3015728} {"current_steps": 4940, "total_steps": 64460, "loss": 0.2236, "lr": 7.662116040955632e-06, "epoch": 1.5327334781259696, "percentage": 7.66, "elapsed_time": "0:08:29", "remaining_time": "1:42:16", "throughput": 5926.86, "total_tokens": 3018640} {"current_steps": 4945, "total_steps": 64460, "loss": 0.2339, "lr": 7.669872789326714e-06, "epoch": 1.5342848278001862, "percentage": 7.67, "elapsed_time": "0:08:29", "remaining_time": "1:42:16", "throughput": 5927.24, "total_tokens": 3022000} {"current_steps": 4950, "total_steps": 64460, "loss": 0.2351, "lr": 7.677629537697797e-06, "epoch": 1.5358361774744027, "percentage": 7.68, "elapsed_time": "0:08:30", "remaining_time": "1:42:15", "throughput": 5926.79, "total_tokens": 3024592} {"current_steps": 4955, "total_steps": 64460, "loss": 0.2285, "lr": 7.68538628606888e-06, "epoch": 1.5373875271486193, "percentage": 7.69, "elapsed_time": "0:08:30", "remaining_time": "1:42:14", "throughput": 5926.72, "total_tokens": 3027504} {"current_steps": 4960, "total_steps": 64460, "loss": 0.2338, "lr": 7.693143034439963e-06, "epoch": 1.538938876822836, "percentage": 7.69, "elapsed_time": "0:08:31", "remaining_time": "1:42:14", "throughput": 5927.15, "total_tokens": 3030960} {"current_steps": 4965, "total_steps": 64460, "loss": 0.2265, "lr": 7.700899782811046e-06, "epoch": 1.5404902264970524, "percentage": 7.7, "elapsed_time": "0:08:31", "remaining_time": "1:42:14", "throughput": 5926.77, "total_tokens": 3034096} {"current_steps": 4970, "total_steps": 64460, "loss": 0.2366, "lr": 7.70865653118213e-06, "epoch": 1.5420415761712691, "percentage": 7.71, "elapsed_time": "0:08:32", "remaining_time": "1:42:15", "throughput": 5927.64, "total_tokens": 3038192} {"current_steps": 4975, "total_steps": 64460, "loss": 0.2375, "lr": 7.716413279553212e-06, "epoch": 1.5435929258454855, "percentage": 7.72, "elapsed_time": "0:08:33", "remaining_time": "1:42:14", "throughput": 5927.35, "total_tokens": 3040848} {"current_steps": 4980, "total_steps": 64460, "loss": 0.2351, "lr": 7.724170027924295e-06, "epoch": 1.5451442755197022, "percentage": 7.73, "elapsed_time": "0:08:33", "remaining_time": "1:42:12", "throughput": 5926.9, "total_tokens": 3043248} {"current_steps": 4985, "total_steps": 64460, "loss": 0.2346, "lr": 7.731926776295378e-06, "epoch": 1.5466956251939186, "percentage": 7.73, "elapsed_time": "0:08:33", "remaining_time": "1:42:11", "throughput": 5926.51, "total_tokens": 3045776} {"current_steps": 4990, "total_steps": 64460, "loss": 0.2328, "lr": 7.73968352466646e-06, "epoch": 1.5482469748681353, "percentage": 7.74, "elapsed_time": "0:08:34", "remaining_time": "1:42:12", "throughput": 5927.74, "total_tokens": 3050352} {"current_steps": 4995, "total_steps": 64460, "loss": 0.2276, "lr": 7.747440273037543e-06, "epoch": 1.549798324542352, "percentage": 7.75, "elapsed_time": "0:08:35", "remaining_time": "1:42:11", "throughput": 5927.36, "total_tokens": 3052912} {"current_steps": 5000, "total_steps": 64460, "loss": 0.2342, "lr": 7.755197021408626e-06, "epoch": 1.5513496742165684, "percentage": 7.76, "elapsed_time": "0:08:36", "remaining_time": "1:42:16", "throughput": 5928.48, "total_tokens": 3059440} {"current_steps": 5005, "total_steps": 64460, "loss": 0.2376, "lr": 7.762953769779709e-06, "epoch": 1.552901023890785, "percentage": 7.76, "elapsed_time": "0:08:36", "remaining_time": "1:42:15", "throughput": 5927.92, "total_tokens": 3061840} {"current_steps": 5010, "total_steps": 64460, "loss": 0.2317, "lr": 7.770710518150792e-06, "epoch": 1.5544523735650015, "percentage": 7.77, "elapsed_time": "0:08:36", "remaining_time": "1:42:14", "throughput": 5927.37, "total_tokens": 3064304} {"current_steps": 5015, "total_steps": 64460, "loss": 0.2231, "lr": 7.778467266521875e-06, "epoch": 1.556003723239218, "percentage": 7.78, "elapsed_time": "0:08:37", "remaining_time": "1:42:13", "throughput": 5927.52, "total_tokens": 3067312} {"current_steps": 5020, "total_steps": 64460, "loss": 0.2363, "lr": 7.786224014892958e-06, "epoch": 1.5575550729134346, "percentage": 7.79, "elapsed_time": "0:08:37", "remaining_time": "1:42:12", "throughput": 5926.95, "total_tokens": 3069776} {"current_steps": 5025, "total_steps": 64460, "loss": 0.2355, "lr": 7.79398076326404e-06, "epoch": 1.5591064225876514, "percentage": 7.8, "elapsed_time": "0:08:38", "remaining_time": "1:42:11", "throughput": 5926.67, "total_tokens": 3072240} {"current_steps": 5030, "total_steps": 64460, "loss": 0.2308, "lr": 7.801737511635124e-06, "epoch": 1.5606577722618677, "percentage": 7.8, "elapsed_time": "0:08:38", "remaining_time": "1:42:10", "throughput": 5925.86, "total_tokens": 3074576} {"current_steps": 5035, "total_steps": 64460, "loss": 0.2286, "lr": 7.809494260006207e-06, "epoch": 1.5622091219360845, "percentage": 7.81, "elapsed_time": "0:08:39", "remaining_time": "1:42:08", "throughput": 5925.48, "total_tokens": 3077072} {"current_steps": 5040, "total_steps": 64460, "loss": 0.2268, "lr": 7.81725100837729e-06, "epoch": 1.5637604716103009, "percentage": 7.82, "elapsed_time": "0:08:39", "remaining_time": "1:42:08", "throughput": 5925.26, "total_tokens": 3080080} {"current_steps": 5045, "total_steps": 64460, "loss": 0.2279, "lr": 7.825007756748372e-06, "epoch": 1.5653118212845176, "percentage": 7.83, "elapsed_time": "0:08:40", "remaining_time": "1:42:07", "throughput": 5925.49, "total_tokens": 3083216} {"current_steps": 5050, "total_steps": 64460, "loss": 0.2186, "lr": 7.832764505119454e-06, "epoch": 1.566863170958734, "percentage": 7.83, "elapsed_time": "0:08:40", "remaining_time": "1:42:07", "throughput": 5925.0, "total_tokens": 3085872} {"current_steps": 5055, "total_steps": 64460, "loss": 0.247, "lr": 7.840521253490537e-06, "epoch": 1.5684145206329507, "percentage": 7.84, "elapsed_time": "0:08:41", "remaining_time": "1:42:05", "throughput": 5925.23, "total_tokens": 3088688} {"current_steps": 5060, "total_steps": 64460, "loss": 0.2446, "lr": 7.84827800186162e-06, "epoch": 1.5699658703071673, "percentage": 7.85, "elapsed_time": "0:08:41", "remaining_time": "1:42:05", "throughput": 5925.24, "total_tokens": 3091696} {"current_steps": 5065, "total_steps": 64460, "loss": 0.2378, "lr": 7.856034750232703e-06, "epoch": 1.5715172199813838, "percentage": 7.86, "elapsed_time": "0:08:42", "remaining_time": "1:42:04", "throughput": 5924.99, "total_tokens": 3094288} {"current_steps": 5070, "total_steps": 64460, "loss": 0.2328, "lr": 7.863791498603786e-06, "epoch": 1.5730685696556004, "percentage": 7.87, "elapsed_time": "0:08:42", "remaining_time": "1:42:02", "throughput": 5924.21, "total_tokens": 3096624} {"current_steps": 5075, "total_steps": 64460, "loss": 0.2314, "lr": 7.871548246974869e-06, "epoch": 1.574619919329817, "percentage": 7.87, "elapsed_time": "0:08:43", "remaining_time": "1:42:02", "throughput": 5923.91, "total_tokens": 3099664} {"current_steps": 5080, "total_steps": 64460, "loss": 0.2325, "lr": 7.879304995345952e-06, "epoch": 1.5761712690040335, "percentage": 7.88, "elapsed_time": "0:08:43", "remaining_time": "1:42:01", "throughput": 5923.5, "total_tokens": 3102128} {"current_steps": 5085, "total_steps": 64460, "loss": 0.2337, "lr": 7.887061743717035e-06, "epoch": 1.57772261867825, "percentage": 7.89, "elapsed_time": "0:08:44", "remaining_time": "1:42:00", "throughput": 5923.55, "total_tokens": 3104880} {"current_steps": 5090, "total_steps": 64460, "loss": 0.2304, "lr": 7.894818492088118e-06, "epoch": 1.5792739683524668, "percentage": 7.9, "elapsed_time": "0:08:44", "remaining_time": "1:41:59", "throughput": 5922.54, "total_tokens": 3107216} {"current_steps": 5095, "total_steps": 64460, "loss": 0.2326, "lr": 7.9025752404592e-06, "epoch": 1.5808253180266831, "percentage": 7.9, "elapsed_time": "0:08:45", "remaining_time": "1:41:58", "throughput": 5922.81, "total_tokens": 3110352} {"current_steps": 5100, "total_steps": 64460, "loss": 0.2316, "lr": 7.910331988830284e-06, "epoch": 1.5823766677009, "percentage": 7.91, "elapsed_time": "0:08:45", "remaining_time": "1:41:57", "throughput": 5922.34, "total_tokens": 3112752} {"current_steps": 5105, "total_steps": 64460, "loss": 0.2328, "lr": 7.918088737201367e-06, "epoch": 1.5839280173751162, "percentage": 7.92, "elapsed_time": "0:08:46", "remaining_time": "1:41:58", "throughput": 5923.12, "total_tokens": 3116752} {"current_steps": 5110, "total_steps": 64460, "loss": 0.2306, "lr": 7.925845485572448e-06, "epoch": 1.585479367049333, "percentage": 7.93, "elapsed_time": "0:08:46", "remaining_time": "1:41:57", "throughput": 5922.69, "total_tokens": 3119312} {"current_steps": 5115, "total_steps": 64460, "loss": 0.2301, "lr": 7.933602233943531e-06, "epoch": 1.5870307167235493, "percentage": 7.94, "elapsed_time": "0:08:47", "remaining_time": "1:41:57", "throughput": 5923.11, "total_tokens": 3122896} {"current_steps": 5120, "total_steps": 64460, "loss": 0.2252, "lr": 7.941358982314614e-06, "epoch": 1.5885820663977661, "percentage": 7.94, "elapsed_time": "0:08:47", "remaining_time": "1:41:56", "throughput": 5923.85, "total_tokens": 3126384} {"current_steps": 5125, "total_steps": 64460, "loss": 0.231, "lr": 7.949115730685697e-06, "epoch": 1.5901334160719827, "percentage": 7.95, "elapsed_time": "0:08:48", "remaining_time": "1:41:56", "throughput": 5924.58, "total_tokens": 3130128} {"current_steps": 5130, "total_steps": 64460, "loss": 0.2372, "lr": 7.95687247905678e-06, "epoch": 1.5916847657461992, "percentage": 7.96, "elapsed_time": "0:08:48", "remaining_time": "1:41:56", "throughput": 5925.16, "total_tokens": 3133584} {"current_steps": 5135, "total_steps": 64460, "loss": 0.23, "lr": 7.964629227427863e-06, "epoch": 1.5932361154204158, "percentage": 7.97, "elapsed_time": "0:08:49", "remaining_time": "1:41:56", "throughput": 5926.1, "total_tokens": 3137456} {"current_steps": 5140, "total_steps": 64460, "loss": 0.231, "lr": 7.972385975798946e-06, "epoch": 1.5947874650946323, "percentage": 7.97, "elapsed_time": "0:08:49", "remaining_time": "1:41:56", "throughput": 5926.76, "total_tokens": 3140880} {"current_steps": 5145, "total_steps": 64460, "loss": 0.2343, "lr": 7.980142724170029e-06, "epoch": 1.5963388147688489, "percentage": 7.98, "elapsed_time": "0:08:50", "remaining_time": "1:41:55", "throughput": 5926.08, "total_tokens": 3143312} {"current_steps": 5150, "total_steps": 64460, "loss": 0.2317, "lr": 7.987899472541112e-06, "epoch": 1.5978901644430654, "percentage": 7.99, "elapsed_time": "0:08:50", "remaining_time": "1:41:54", "throughput": 5926.44, "total_tokens": 3146608} {"current_steps": 5155, "total_steps": 64460, "loss": 0.237, "lr": 7.995656220912195e-06, "epoch": 1.5994415141172822, "percentage": 8.0, "elapsed_time": "0:08:51", "remaining_time": "1:41:54", "throughput": 5926.31, "total_tokens": 3149552} {"current_steps": 5160, "total_steps": 64460, "loss": 0.2265, "lr": 8.003412969283278e-06, "epoch": 1.6009928637914985, "percentage": 8.0, "elapsed_time": "0:08:52", "remaining_time": "1:41:54", "throughput": 5927.13, "total_tokens": 3153552} {"current_steps": 5165, "total_steps": 64460, "loss": 0.2359, "lr": 8.01116971765436e-06, "epoch": 1.6025442134657153, "percentage": 8.01, "elapsed_time": "0:08:52", "remaining_time": "1:41:54", "throughput": 5927.85, "total_tokens": 3157232} {"current_steps": 5170, "total_steps": 64460, "loss": 0.2327, "lr": 8.018926466025444e-06, "epoch": 1.6040955631399316, "percentage": 8.02, "elapsed_time": "0:08:53", "remaining_time": "1:41:53", "throughput": 5927.5, "total_tokens": 3159856} {"current_steps": 5175, "total_steps": 64460, "loss": 0.2327, "lr": 8.026683214396525e-06, "epoch": 1.6056469128141484, "percentage": 8.03, "elapsed_time": "0:08:53", "remaining_time": "1:41:52", "throughput": 5926.29, "total_tokens": 3161936} {"current_steps": 5180, "total_steps": 64460, "loss": 0.2342, "lr": 8.034439962767608e-06, "epoch": 1.6071982624883647, "percentage": 8.04, "elapsed_time": "0:08:54", "remaining_time": "1:41:52", "throughput": 5926.95, "total_tokens": 3165456} {"current_steps": 5185, "total_steps": 64460, "loss": 0.2326, "lr": 8.042196711138691e-06, "epoch": 1.6087496121625815, "percentage": 8.04, "elapsed_time": "0:08:54", "remaining_time": "1:41:50", "throughput": 5926.6, "total_tokens": 3168016} {"current_steps": 5190, "total_steps": 64460, "loss": 0.2296, "lr": 8.049953459509774e-06, "epoch": 1.610300961836798, "percentage": 8.05, "elapsed_time": "0:08:55", "remaining_time": "1:41:50", "throughput": 5927.43, "total_tokens": 3171600} {"current_steps": 5195, "total_steps": 64460, "loss": 0.2321, "lr": 8.057710207880857e-06, "epoch": 1.6118523115110146, "percentage": 8.06, "elapsed_time": "0:08:55", "remaining_time": "1:41:49", "throughput": 5927.36, "total_tokens": 3174352} {"current_steps": 5200, "total_steps": 64460, "loss": 0.228, "lr": 8.06546695625194e-06, "epoch": 1.6134036611852312, "percentage": 8.07, "elapsed_time": "0:08:56", "remaining_time": "1:41:49", "throughput": 5927.07, "total_tokens": 3177456} {"current_steps": 5205, "total_steps": 64460, "loss": 0.2274, "lr": 8.073223704623023e-06, "epoch": 1.6149550108594477, "percentage": 8.07, "elapsed_time": "0:08:56", "remaining_time": "1:41:47", "throughput": 5926.41, "total_tokens": 3179696} {"current_steps": 5210, "total_steps": 64460, "loss": 0.2246, "lr": 8.080980452994106e-06, "epoch": 1.6165063605336643, "percentage": 8.08, "elapsed_time": "0:08:57", "remaining_time": "1:41:47", "throughput": 5926.36, "total_tokens": 3182992} {"current_steps": 5215, "total_steps": 64460, "loss": 0.2322, "lr": 8.088737201365189e-06, "epoch": 1.6180577102078808, "percentage": 8.09, "elapsed_time": "0:08:57", "remaining_time": "1:41:46", "throughput": 5926.52, "total_tokens": 3185872} {"current_steps": 5220, "total_steps": 64460, "loss": 0.2391, "lr": 8.096493949736272e-06, "epoch": 1.6196090598820976, "percentage": 8.1, "elapsed_time": "0:08:58", "remaining_time": "1:41:48", "throughput": 5927.03, "total_tokens": 3190032} {"current_steps": 5225, "total_steps": 64460, "loss": 0.2311, "lr": 8.104250698107355e-06, "epoch": 1.621160409556314, "percentage": 8.11, "elapsed_time": "0:08:58", "remaining_time": "1:41:47", "throughput": 5926.52, "total_tokens": 3192784} {"current_steps": 5230, "total_steps": 64460, "loss": 0.2393, "lr": 8.112007446478438e-06, "epoch": 1.6227117592305307, "percentage": 8.11, "elapsed_time": "0:08:59", "remaining_time": "1:41:46", "throughput": 5925.86, "total_tokens": 3195312} {"current_steps": 5235, "total_steps": 64460, "loss": 0.2411, "lr": 8.119764194849519e-06, "epoch": 1.624263108904747, "percentage": 8.12, "elapsed_time": "0:08:59", "remaining_time": "1:41:47", "throughput": 5926.97, "total_tokens": 3199728} {"current_steps": 5240, "total_steps": 64460, "loss": 0.2281, "lr": 8.127520943220602e-06, "epoch": 1.6258144585789638, "percentage": 8.13, "elapsed_time": "0:09:00", "remaining_time": "1:41:47", "throughput": 5927.27, "total_tokens": 3202928} {"current_steps": 5245, "total_steps": 64460, "loss": 0.233, "lr": 8.135277691591685e-06, "epoch": 1.6273658082531801, "percentage": 8.14, "elapsed_time": "0:09:00", "remaining_time": "1:41:45", "throughput": 5927.05, "total_tokens": 3205456} {"current_steps": 5250, "total_steps": 64460, "loss": 0.2316, "lr": 8.143034439962768e-06, "epoch": 1.6289171579273969, "percentage": 8.14, "elapsed_time": "0:09:01", "remaining_time": "1:41:44", "throughput": 5926.98, "total_tokens": 3208272} {"current_steps": 5255, "total_steps": 64460, "loss": 0.2296, "lr": 8.150791188333851e-06, "epoch": 1.6304685076016134, "percentage": 8.15, "elapsed_time": "0:09:01", "remaining_time": "1:41:45", "throughput": 5927.55, "total_tokens": 3212368} {"current_steps": 5260, "total_steps": 64460, "loss": 0.2271, "lr": 8.158547936704934e-06, "epoch": 1.63201985727583, "percentage": 8.16, "elapsed_time": "0:09:02", "remaining_time": "1:41:46", "throughput": 5928.46, "total_tokens": 3216464} {"current_steps": 5265, "total_steps": 64460, "loss": 0.2432, "lr": 8.166304685076017e-06, "epoch": 1.6335712069500465, "percentage": 8.17, "elapsed_time": "0:09:03", "remaining_time": "1:41:45", "throughput": 5928.7, "total_tokens": 3219408} {"current_steps": 5270, "total_steps": 64460, "loss": 0.2273, "lr": 8.1740614334471e-06, "epoch": 1.635122556624263, "percentage": 8.18, "elapsed_time": "0:09:03", "remaining_time": "1:41:44", "throughput": 5928.95, "total_tokens": 3222416} {"current_steps": 5275, "total_steps": 64460, "loss": 0.2342, "lr": 8.181818181818183e-06, "epoch": 1.6366739062984796, "percentage": 8.18, "elapsed_time": "0:09:04", "remaining_time": "1:41:44", "throughput": 5928.77, "total_tokens": 3225648} {"current_steps": 5280, "total_steps": 64460, "loss": 0.2325, "lr": 8.189574930189266e-06, "epoch": 1.6382252559726962, "percentage": 8.19, "elapsed_time": "0:09:04", "remaining_time": "1:41:43", "throughput": 5928.84, "total_tokens": 3228464} {"current_steps": 5285, "total_steps": 64460, "loss": 0.2358, "lr": 8.197331678560349e-06, "epoch": 1.639776605646913, "percentage": 8.2, "elapsed_time": "0:09:05", "remaining_time": "1:41:43", "throughput": 5929.5, "total_tokens": 3232368} {"current_steps": 5290, "total_steps": 64460, "loss": 0.231, "lr": 8.205088426931432e-06, "epoch": 1.6413279553211293, "percentage": 8.21, "elapsed_time": "0:09:05", "remaining_time": "1:41:42", "throughput": 5928.96, "total_tokens": 3234640} {"current_steps": 5295, "total_steps": 64460, "loss": 0.2315, "lr": 8.212845175302513e-06, "epoch": 1.642879304995346, "percentage": 8.21, "elapsed_time": "0:09:06", "remaining_time": "1:41:42", "throughput": 5929.39, "total_tokens": 3238256} {"current_steps": 5300, "total_steps": 64460, "loss": 0.23, "lr": 8.220601923673596e-06, "epoch": 1.6444306546695624, "percentage": 8.22, "elapsed_time": "0:09:06", "remaining_time": "1:41:42", "throughput": 5929.14, "total_tokens": 3241264} {"current_steps": 5305, "total_steps": 64460, "loss": 0.2294, "lr": 8.22835867204468e-06, "epoch": 1.6459820043437792, "percentage": 8.23, "elapsed_time": "0:09:07", "remaining_time": "1:41:41", "throughput": 5929.43, "total_tokens": 3244528} {"current_steps": 5310, "total_steps": 64460, "loss": 0.2359, "lr": 8.236115420415762e-06, "epoch": 1.6475333540179955, "percentage": 8.24, "elapsed_time": "0:09:07", "remaining_time": "1:41:40", "throughput": 5929.21, "total_tokens": 3247152} {"current_steps": 5315, "total_steps": 64460, "loss": 0.2332, "lr": 8.243872168786845e-06, "epoch": 1.6490847036922123, "percentage": 8.25, "elapsed_time": "0:09:08", "remaining_time": "1:41:40", "throughput": 5929.63, "total_tokens": 3250576} {"current_steps": 5320, "total_steps": 64460, "loss": 0.2336, "lr": 8.251628917157928e-06, "epoch": 1.6506360533664288, "percentage": 8.25, "elapsed_time": "0:09:08", "remaining_time": "1:41:39", "throughput": 5929.52, "total_tokens": 3253552} {"current_steps": 5325, "total_steps": 64460, "loss": 0.2326, "lr": 8.259385665529011e-06, "epoch": 1.6521874030406454, "percentage": 8.26, "elapsed_time": "0:09:09", "remaining_time": "1:41:39", "throughput": 5929.19, "total_tokens": 3256656} {"current_steps": 5330, "total_steps": 64460, "loss": 0.2343, "lr": 8.267142413900094e-06, "epoch": 1.653738752714862, "percentage": 8.27, "elapsed_time": "0:09:09", "remaining_time": "1:41:38", "throughput": 5928.55, "total_tokens": 3259216} {"current_steps": 5335, "total_steps": 64460, "loss": 0.2302, "lr": 8.274899162271175e-06, "epoch": 1.6552901023890785, "percentage": 8.28, "elapsed_time": "0:09:10", "remaining_time": "1:41:38", "throughput": 5928.35, "total_tokens": 3262256} {"current_steps": 5340, "total_steps": 64460, "loss": 0.2346, "lr": 8.28265591064226e-06, "epoch": 1.656841452063295, "percentage": 8.28, "elapsed_time": "0:09:10", "remaining_time": "1:41:38", "throughput": 5928.26, "total_tokens": 3265424} {"current_steps": 5345, "total_steps": 64460, "loss": 0.228, "lr": 8.290412659013343e-06, "epoch": 1.6583928017375116, "percentage": 8.29, "elapsed_time": "0:09:11", "remaining_time": "1:41:38", "throughput": 5928.75, "total_tokens": 3269104} {"current_steps": 5350, "total_steps": 64460, "loss": 0.2301, "lr": 8.298169407384426e-06, "epoch": 1.6599441514117284, "percentage": 8.3, "elapsed_time": "0:09:11", "remaining_time": "1:41:37", "throughput": 5928.54, "total_tokens": 3271824} {"current_steps": 5355, "total_steps": 64460, "loss": 0.2275, "lr": 8.305926155755509e-06, "epoch": 1.6614955010859447, "percentage": 8.31, "elapsed_time": "0:09:12", "remaining_time": "1:41:37", "throughput": 5928.8, "total_tokens": 3275248} {"current_steps": 5360, "total_steps": 64460, "loss": 0.2283, "lr": 8.31368290412659e-06, "epoch": 1.6630468507601615, "percentage": 8.32, "elapsed_time": "0:09:12", "remaining_time": "1:41:36", "throughput": 5928.78, "total_tokens": 3277936} {"current_steps": 5365, "total_steps": 64460, "loss": 0.2223, "lr": 8.321439652497673e-06, "epoch": 1.6645982004343778, "percentage": 8.32, "elapsed_time": "0:09:13", "remaining_time": "1:41:35", "throughput": 5928.98, "total_tokens": 3281072} {"current_steps": 5370, "total_steps": 64460, "loss": 0.2409, "lr": 8.329196400868756e-06, "epoch": 1.6661495501085946, "percentage": 8.33, "elapsed_time": "0:09:13", "remaining_time": "1:41:35", "throughput": 5929.1, "total_tokens": 3284176} {"current_steps": 5375, "total_steps": 64460, "loss": 0.2326, "lr": 8.33695314923984e-06, "epoch": 1.6677008997828109, "percentage": 8.34, "elapsed_time": "0:09:14", "remaining_time": "1:41:34", "throughput": 5929.59, "total_tokens": 3287600} {"current_steps": 5380, "total_steps": 64460, "loss": 0.2284, "lr": 8.344709897610922e-06, "epoch": 1.6692522494570277, "percentage": 8.35, "elapsed_time": "0:09:14", "remaining_time": "1:41:34", "throughput": 5929.79, "total_tokens": 3290960} {"current_steps": 5385, "total_steps": 64460, "loss": 0.2255, "lr": 8.352466645982005e-06, "epoch": 1.6708035991312442, "percentage": 8.35, "elapsed_time": "0:09:15", "remaining_time": "1:41:33", "throughput": 5929.79, "total_tokens": 3293712} {"current_steps": 5390, "total_steps": 64460, "loss": 0.2433, "lr": 8.360223394353088e-06, "epoch": 1.6723549488054608, "percentage": 8.36, "elapsed_time": "0:09:15", "remaining_time": "1:41:32", "throughput": 5929.52, "total_tokens": 3296464} {"current_steps": 5395, "total_steps": 64460, "loss": 0.2507, "lr": 8.36798014272417e-06, "epoch": 1.6739062984796773, "percentage": 8.37, "elapsed_time": "0:09:16", "remaining_time": "1:41:31", "throughput": 5929.12, "total_tokens": 3298960} {"current_steps": 5400, "total_steps": 64460, "loss": 0.2287, "lr": 8.375736891095252e-06, "epoch": 1.6754576481538939, "percentage": 8.38, "elapsed_time": "0:09:16", "remaining_time": "1:41:30", "throughput": 5928.89, "total_tokens": 3301616} {"current_steps": 5405, "total_steps": 64460, "loss": 0.2356, "lr": 8.383493639466337e-06, "epoch": 1.6770089978281104, "percentage": 8.39, "elapsed_time": "0:09:17", "remaining_time": "1:41:29", "throughput": 5928.57, "total_tokens": 3304144} {"current_steps": 5410, "total_steps": 64460, "loss": 0.2185, "lr": 8.39125038783742e-06, "epoch": 1.678560347502327, "percentage": 8.39, "elapsed_time": "0:09:17", "remaining_time": "1:41:29", "throughput": 5929.0, "total_tokens": 3307696} {"current_steps": 5415, "total_steps": 64460, "loss": 0.2463, "lr": 8.399007136208503e-06, "epoch": 1.6801116971765437, "percentage": 8.4, "elapsed_time": "0:09:18", "remaining_time": "1:41:28", "throughput": 5928.89, "total_tokens": 3310352} {"current_steps": 5420, "total_steps": 64460, "loss": 0.2425, "lr": 8.406763884579584e-06, "epoch": 1.68166304685076, "percentage": 8.41, "elapsed_time": "0:09:18", "remaining_time": "1:41:27", "throughput": 5929.32, "total_tokens": 3313584} {"current_steps": 5425, "total_steps": 64460, "loss": 0.2291, "lr": 8.414520632950667e-06, "epoch": 1.6832143965249768, "percentage": 8.42, "elapsed_time": "0:09:19", "remaining_time": "1:41:26", "throughput": 5929.3, "total_tokens": 3316432} {"current_steps": 5430, "total_steps": 64460, "loss": 0.2331, "lr": 8.42227738132175e-06, "epoch": 1.6847657461991932, "percentage": 8.42, "elapsed_time": "0:09:19", "remaining_time": "1:41:25", "throughput": 5928.81, "total_tokens": 3318960} {"current_steps": 5435, "total_steps": 64460, "loss": 0.2303, "lr": 8.430034129692833e-06, "epoch": 1.68631709587341, "percentage": 8.43, "elapsed_time": "0:09:20", "remaining_time": "1:41:25", "throughput": 5929.27, "total_tokens": 3322608} {"current_steps": 5440, "total_steps": 64460, "loss": 0.2302, "lr": 8.437790878063916e-06, "epoch": 1.6878684455476263, "percentage": 8.44, "elapsed_time": "0:09:20", "remaining_time": "1:41:25", "throughput": 5928.92, "total_tokens": 3325488} {"current_steps": 5445, "total_steps": 64460, "loss": 0.2272, "lr": 8.445547626435e-06, "epoch": 1.689419795221843, "percentage": 8.45, "elapsed_time": "0:09:21", "remaining_time": "1:41:24", "throughput": 5928.28, "total_tokens": 3327792} {"current_steps": 5450, "total_steps": 64460, "loss": 0.2331, "lr": 8.453304374806082e-06, "epoch": 1.6909711448960596, "percentage": 8.45, "elapsed_time": "0:09:21", "remaining_time": "1:41:23", "throughput": 5929.06, "total_tokens": 3331312} {"current_steps": 5455, "total_steps": 64460, "loss": 0.2337, "lr": 8.461061123177164e-06, "epoch": 1.6925224945702761, "percentage": 8.46, "elapsed_time": "0:09:22", "remaining_time": "1:41:23", "throughput": 5929.5, "total_tokens": 3334928} {"current_steps": 5460, "total_steps": 64460, "loss": 0.2254, "lr": 8.468817871548247e-06, "epoch": 1.6940738442444927, "percentage": 8.47, "elapsed_time": "0:09:23", "remaining_time": "1:41:23", "throughput": 5930.4, "total_tokens": 3338928} {"current_steps": 5465, "total_steps": 64460, "loss": 0.2167, "lr": 8.476574619919331e-06, "epoch": 1.6956251939187093, "percentage": 8.48, "elapsed_time": "0:09:23", "remaining_time": "1:41:23", "throughput": 5930.42, "total_tokens": 3341904} {"current_steps": 5470, "total_steps": 64460, "loss": 0.2294, "lr": 8.484331368290414e-06, "epoch": 1.6971765435929258, "percentage": 8.49, "elapsed_time": "0:09:24", "remaining_time": "1:41:22", "throughput": 5930.82, "total_tokens": 3345104} {"current_steps": 5475, "total_steps": 64460, "loss": 0.2332, "lr": 8.492088116661497e-06, "epoch": 1.6987278932671424, "percentage": 8.49, "elapsed_time": "0:09:24", "remaining_time": "1:41:22", "throughput": 5931.22, "total_tokens": 3348624} {"current_steps": 5480, "total_steps": 64460, "loss": 0.2437, "lr": 8.499844865032579e-06, "epoch": 1.7002792429413591, "percentage": 8.5, "elapsed_time": "0:09:25", "remaining_time": "1:41:21", "throughput": 5930.74, "total_tokens": 3351376} {"current_steps": 5485, "total_steps": 64460, "loss": 0.2253, "lr": 8.507601613403661e-06, "epoch": 1.7018305926155755, "percentage": 8.51, "elapsed_time": "0:09:25", "remaining_time": "1:41:21", "throughput": 5929.94, "total_tokens": 3353776} {"current_steps": 5490, "total_steps": 64460, "loss": 0.2329, "lr": 8.515358361774744e-06, "epoch": 1.7033819422897922, "percentage": 8.52, "elapsed_time": "0:09:26", "remaining_time": "1:41:20", "throughput": 5930.07, "total_tokens": 3356880} {"current_steps": 5495, "total_steps": 64460, "loss": 0.2296, "lr": 8.523115110145827e-06, "epoch": 1.7049332919640086, "percentage": 8.52, "elapsed_time": "0:09:26", "remaining_time": "1:41:19", "throughput": 5929.8, "total_tokens": 3359472} {"current_steps": 5500, "total_steps": 64460, "loss": 0.236, "lr": 8.53087185851691e-06, "epoch": 1.7064846416382253, "percentage": 8.53, "elapsed_time": "0:09:27", "remaining_time": "1:41:18", "throughput": 5929.82, "total_tokens": 3362288} {"current_steps": 5505, "total_steps": 64460, "loss": 0.2295, "lr": 8.538628606887993e-06, "epoch": 1.7080359913124417, "percentage": 8.54, "elapsed_time": "0:09:27", "remaining_time": "1:41:17", "throughput": 5929.77, "total_tokens": 3364976} {"current_steps": 5510, "total_steps": 64460, "loss": 0.2293, "lr": 8.546385355259076e-06, "epoch": 1.7095873409866584, "percentage": 8.55, "elapsed_time": "0:09:27", "remaining_time": "1:41:16", "throughput": 5928.69, "total_tokens": 3367024} {"current_steps": 5515, "total_steps": 64460, "loss": 0.2325, "lr": 8.55414210363016e-06, "epoch": 1.711138690660875, "percentage": 8.56, "elapsed_time": "0:09:28", "remaining_time": "1:41:15", "throughput": 5927.9, "total_tokens": 3369520} {"current_steps": 5520, "total_steps": 64460, "loss": 0.2336, "lr": 8.56189885200124e-06, "epoch": 1.7126900403350915, "percentage": 8.56, "elapsed_time": "0:09:28", "remaining_time": "1:41:14", "throughput": 5927.64, "total_tokens": 3372080} {"current_steps": 5525, "total_steps": 64460, "loss": 0.2379, "lr": 8.569655600372324e-06, "epoch": 1.714241390009308, "percentage": 8.57, "elapsed_time": "0:09:29", "remaining_time": "1:41:13", "throughput": 5927.62, "total_tokens": 3374960} {"current_steps": 5530, "total_steps": 64460, "loss": 0.2289, "lr": 8.577412348743408e-06, "epoch": 1.7157927396835246, "percentage": 8.58, "elapsed_time": "0:09:29", "remaining_time": "1:41:13", "throughput": 5927.94, "total_tokens": 3378384} {"current_steps": 5535, "total_steps": 64460, "loss": 0.2353, "lr": 8.585169097114491e-06, "epoch": 1.7173440893577412, "percentage": 8.59, "elapsed_time": "0:09:30", "remaining_time": "1:41:12", "throughput": 5927.88, "total_tokens": 3381520} {"current_steps": 5540, "total_steps": 64460, "loss": 0.2294, "lr": 8.592925845485574e-06, "epoch": 1.7188954390319577, "percentage": 8.59, "elapsed_time": "0:09:30", "remaining_time": "1:41:11", "throughput": 5927.23, "total_tokens": 3383824} {"current_steps": 5545, "total_steps": 64460, "loss": 0.2304, "lr": 8.600682593856656e-06, "epoch": 1.7204467887061745, "percentage": 8.6, "elapsed_time": "0:09:31", "remaining_time": "1:41:10", "throughput": 5927.07, "total_tokens": 3386352} {"current_steps": 5550, "total_steps": 64460, "loss": 0.2305, "lr": 8.608439342227739e-06, "epoch": 1.7219981383803908, "percentage": 8.61, "elapsed_time": "0:09:31", "remaining_time": "1:41:09", "throughput": 5927.02, "total_tokens": 3389296} {"current_steps": 5555, "total_steps": 64460, "loss": 0.2336, "lr": 8.616196090598822e-06, "epoch": 1.7235494880546076, "percentage": 8.62, "elapsed_time": "0:09:32", "remaining_time": "1:41:08", "throughput": 5926.67, "total_tokens": 3391760} {"current_steps": 5560, "total_steps": 64460, "loss": 0.2369, "lr": 8.623952838969905e-06, "epoch": 1.725100837728824, "percentage": 8.63, "elapsed_time": "0:09:32", "remaining_time": "1:41:08", "throughput": 5927.76, "total_tokens": 3395920} {"current_steps": 5565, "total_steps": 64460, "loss": 0.2298, "lr": 8.631709587340988e-06, "epoch": 1.7266521874030407, "percentage": 8.63, "elapsed_time": "0:09:33", "remaining_time": "1:41:08", "throughput": 5927.78, "total_tokens": 3398800} {"current_steps": 5570, "total_steps": 64460, "loss": 0.2347, "lr": 8.63946633571207e-06, "epoch": 1.7282035370772573, "percentage": 8.64, "elapsed_time": "0:09:33", "remaining_time": "1:41:07", "throughput": 5928.01, "total_tokens": 3402224} {"current_steps": 5575, "total_steps": 64460, "loss": 0.2313, "lr": 8.647223084083154e-06, "epoch": 1.7297548867514738, "percentage": 8.65, "elapsed_time": "0:09:34", "remaining_time": "1:41:07", "throughput": 5928.57, "total_tokens": 3405744} {"current_steps": 5580, "total_steps": 64460, "loss": 0.2369, "lr": 8.654979832454235e-06, "epoch": 1.7313062364256904, "percentage": 8.66, "elapsed_time": "0:09:34", "remaining_time": "1:41:06", "throughput": 5928.31, "total_tokens": 3408496} {"current_steps": 5585, "total_steps": 64460, "loss": 0.2324, "lr": 8.662736580825318e-06, "epoch": 1.732857586099907, "percentage": 8.66, "elapsed_time": "0:09:35", "remaining_time": "1:41:06", "throughput": 5927.91, "total_tokens": 3411280} {"current_steps": 5590, "total_steps": 64460, "loss": 0.2299, "lr": 8.6704933291964e-06, "epoch": 1.7344089357741235, "percentage": 8.67, "elapsed_time": "0:09:36", "remaining_time": "1:41:06", "throughput": 5928.36, "total_tokens": 3414768} {"current_steps": 5595, "total_steps": 64460, "loss": 0.2304, "lr": 8.678250077567485e-06, "epoch": 1.73596028544834, "percentage": 8.68, "elapsed_time": "0:09:36", "remaining_time": "1:41:05", "throughput": 5928.27, "total_tokens": 3417456} {"current_steps": 5600, "total_steps": 64460, "loss": 0.2346, "lr": 8.686006825938568e-06, "epoch": 1.7375116351225566, "percentage": 8.69, "elapsed_time": "0:09:37", "remaining_time": "1:41:05", "throughput": 5928.76, "total_tokens": 3421264} {"current_steps": 5605, "total_steps": 64460, "loss": 0.2289, "lr": 8.69376357430965e-06, "epoch": 1.7390629847967731, "percentage": 8.7, "elapsed_time": "0:09:37", "remaining_time": "1:41:04", "throughput": 5928.08, "total_tokens": 3423952} {"current_steps": 5610, "total_steps": 64460, "loss": 0.2305, "lr": 8.701520322680733e-06, "epoch": 1.74061433447099, "percentage": 8.7, "elapsed_time": "0:09:38", "remaining_time": "1:41:03", "throughput": 5927.86, "total_tokens": 3426512} {"current_steps": 5615, "total_steps": 64460, "loss": 0.2305, "lr": 8.709277071051816e-06, "epoch": 1.7421656841452062, "percentage": 8.71, "elapsed_time": "0:09:38", "remaining_time": "1:41:03", "throughput": 5928.49, "total_tokens": 3429968} {"current_steps": 5620, "total_steps": 64460, "loss": 0.2326, "lr": 8.717033819422899e-06, "epoch": 1.743717033819423, "percentage": 8.72, "elapsed_time": "0:09:39", "remaining_time": "1:41:02", "throughput": 5928.61, "total_tokens": 3432784} {"current_steps": 5625, "total_steps": 64460, "loss": 0.2243, "lr": 8.724790567793982e-06, "epoch": 1.7452683834936393, "percentage": 8.73, "elapsed_time": "0:09:39", "remaining_time": "1:41:02", "throughput": 5928.96, "total_tokens": 3436656} {"current_steps": 5630, "total_steps": 64460, "loss": 0.24, "lr": 8.732547316165065e-06, "epoch": 1.746819733167856, "percentage": 8.73, "elapsed_time": "0:09:40", "remaining_time": "1:41:04", "throughput": 5930.01, "total_tokens": 3441456} {"current_steps": 5635, "total_steps": 64460, "loss": 0.2364, "lr": 8.740304064536148e-06, "epoch": 1.7483710828420727, "percentage": 8.74, "elapsed_time": "0:09:40", "remaining_time": "1:41:03", "throughput": 5929.97, "total_tokens": 3444144} {"current_steps": 5640, "total_steps": 64460, "loss": 0.2324, "lr": 8.748060812907229e-06, "epoch": 1.7499224325162892, "percentage": 8.75, "elapsed_time": "0:09:41", "remaining_time": "1:41:02", "throughput": 5930.21, "total_tokens": 3447504} {"current_steps": 5645, "total_steps": 64460, "loss": 0.2289, "lr": 8.755817561278312e-06, "epoch": 1.7514737821905058, "percentage": 8.76, "elapsed_time": "0:09:41", "remaining_time": "1:41:01", "throughput": 5930.36, "total_tokens": 3450352} {"current_steps": 5650, "total_steps": 64460, "loss": 0.2332, "lr": 8.763574309649395e-06, "epoch": 1.7530251318647223, "percentage": 8.77, "elapsed_time": "0:09:42", "remaining_time": "1:41:00", "throughput": 5929.68, "total_tokens": 3452496} {"current_steps": 5655, "total_steps": 64460, "loss": 0.2362, "lr": 8.771331058020478e-06, "epoch": 1.7545764815389389, "percentage": 8.77, "elapsed_time": "0:09:42", "remaining_time": "1:40:59", "throughput": 5929.33, "total_tokens": 3455152} {"current_steps": 5660, "total_steps": 64460, "loss": 0.2332, "lr": 8.779087806391563e-06, "epoch": 1.7561278312131554, "percentage": 8.78, "elapsed_time": "0:09:43", "remaining_time": "1:40:59", "throughput": 5929.56, "total_tokens": 3458480} {"current_steps": 5665, "total_steps": 64460, "loss": 0.2354, "lr": 8.786844554762644e-06, "epoch": 1.757679180887372, "percentage": 8.79, "elapsed_time": "0:09:43", "remaining_time": "1:40:58", "throughput": 5929.05, "total_tokens": 3460976} {"current_steps": 5670, "total_steps": 64460, "loss": 0.231, "lr": 8.794601303133727e-06, "epoch": 1.7592305305615885, "percentage": 8.8, "elapsed_time": "0:09:44", "remaining_time": "1:40:57", "throughput": 5928.98, "total_tokens": 3463632} {"current_steps": 5675, "total_steps": 64460, "loss": 0.231, "lr": 8.80235805150481e-06, "epoch": 1.7607818802358053, "percentage": 8.8, "elapsed_time": "0:09:44", "remaining_time": "1:40:56", "throughput": 5928.43, "total_tokens": 3466096} {"current_steps": 5680, "total_steps": 64460, "loss": 0.2231, "lr": 8.810114799875893e-06, "epoch": 1.7623332299100216, "percentage": 8.81, "elapsed_time": "0:09:45", "remaining_time": "1:40:55", "throughput": 5928.59, "total_tokens": 3469008} {"current_steps": 5685, "total_steps": 64460, "loss": 0.23, "lr": 8.817871548246976e-06, "epoch": 1.7638845795842384, "percentage": 8.82, "elapsed_time": "0:09:45", "remaining_time": "1:40:54", "throughput": 5928.69, "total_tokens": 3472240} {"current_steps": 5690, "total_steps": 64460, "loss": 0.2245, "lr": 8.825628296618059e-06, "epoch": 1.7654359292584547, "percentage": 8.83, "elapsed_time": "0:09:46", "remaining_time": "1:40:54", "throughput": 5928.34, "total_tokens": 3475248} {"current_steps": 5695, "total_steps": 64460, "loss": 0.2402, "lr": 8.833385044989142e-06, "epoch": 1.7669872789326715, "percentage": 8.83, "elapsed_time": "0:09:46", "remaining_time": "1:40:53", "throughput": 5927.67, "total_tokens": 3477456} {"current_steps": 5700, "total_steps": 64460, "loss": 0.2321, "lr": 8.841141793360225e-06, "epoch": 1.768538628606888, "percentage": 8.84, "elapsed_time": "0:09:47", "remaining_time": "1:40:52", "throughput": 5928.09, "total_tokens": 3480752} {"current_steps": 5705, "total_steps": 64460, "loss": 0.2215, "lr": 8.848898541731306e-06, "epoch": 1.7700899782811046, "percentage": 8.85, "elapsed_time": "0:09:47", "remaining_time": "1:40:52", "throughput": 5928.71, "total_tokens": 3484304} {"current_steps": 5710, "total_steps": 64460, "loss": 0.2247, "lr": 8.856655290102389e-06, "epoch": 1.7716413279553211, "percentage": 8.86, "elapsed_time": "0:09:48", "remaining_time": "1:40:52", "throughput": 5927.75, "total_tokens": 3486736} {"current_steps": 5715, "total_steps": 64460, "loss": 0.2336, "lr": 8.864412038473472e-06, "epoch": 1.7731926776295377, "percentage": 8.87, "elapsed_time": "0:09:48", "remaining_time": "1:40:51", "throughput": 5927.14, "total_tokens": 3489392} {"current_steps": 5720, "total_steps": 64460, "loss": 0.2273, "lr": 8.872168786844555e-06, "epoch": 1.7747440273037542, "percentage": 8.87, "elapsed_time": "0:09:49", "remaining_time": "1:40:50", "throughput": 5927.68, "total_tokens": 3492720} {"current_steps": 5725, "total_steps": 64460, "loss": 0.2344, "lr": 8.87992553521564e-06, "epoch": 1.7762953769779708, "percentage": 8.88, "elapsed_time": "0:09:49", "remaining_time": "1:40:51", "throughput": 5928.51, "total_tokens": 3497008} {"current_steps": 5730, "total_steps": 64460, "loss": 0.2435, "lr": 8.887682283586721e-06, "epoch": 1.7778467266521873, "percentage": 8.89, "elapsed_time": "0:09:50", "remaining_time": "1:40:50", "throughput": 5928.54, "total_tokens": 3499920} {"current_steps": 5735, "total_steps": 64460, "loss": 0.2247, "lr": 8.895439031957804e-06, "epoch": 1.779398076326404, "percentage": 8.9, "elapsed_time": "0:09:50", "remaining_time": "1:40:50", "throughput": 5928.26, "total_tokens": 3502672} {"current_steps": 5740, "total_steps": 64460, "loss": 0.2294, "lr": 8.903195780328887e-06, "epoch": 1.7809494260006207, "percentage": 8.9, "elapsed_time": "0:09:51", "remaining_time": "1:40:49", "throughput": 5928.37, "total_tokens": 3505456} {"current_steps": 5745, "total_steps": 64460, "loss": 0.244, "lr": 8.91095252869997e-06, "epoch": 1.782500775674837, "percentage": 8.91, "elapsed_time": "0:09:51", "remaining_time": "1:40:48", "throughput": 5928.9, "total_tokens": 3508976} {"current_steps": 5750, "total_steps": 64460, "loss": 0.232, "lr": 8.918709277071053e-06, "epoch": 1.7840521253490538, "percentage": 8.92, "elapsed_time": "0:09:52", "remaining_time": "1:40:48", "throughput": 5927.85, "total_tokens": 3511280} {"current_steps": 5755, "total_steps": 64460, "loss": 0.2324, "lr": 8.926466025442136e-06, "epoch": 1.78560347502327, "percentage": 8.93, "elapsed_time": "0:09:52", "remaining_time": "1:40:47", "throughput": 5927.66, "total_tokens": 3514512} {"current_steps": 5760, "total_steps": 64460, "loss": 0.2362, "lr": 8.934222773813219e-06, "epoch": 1.7871548246974869, "percentage": 8.94, "elapsed_time": "0:09:53", "remaining_time": "1:40:48", "throughput": 5927.77, "total_tokens": 3518064} {"current_steps": 5765, "total_steps": 64460, "loss": 0.2313, "lr": 8.9419795221843e-06, "epoch": 1.7887061743717034, "percentage": 8.94, "elapsed_time": "0:09:53", "remaining_time": "1:40:47", "throughput": 5927.36, "total_tokens": 3520688} {"current_steps": 5770, "total_steps": 64460, "loss": 0.2293, "lr": 8.949736270555383e-06, "epoch": 1.79025752404592, "percentage": 8.95, "elapsed_time": "0:09:54", "remaining_time": "1:40:47", "throughput": 5927.88, "total_tokens": 3524240} {"current_steps": 5775, "total_steps": 64460, "loss": 0.2271, "lr": 8.957493018926466e-06, "epoch": 1.7918088737201365, "percentage": 8.96, "elapsed_time": "0:09:55", "remaining_time": "1:40:46", "throughput": 5927.32, "total_tokens": 3527056} {"current_steps": 5780, "total_steps": 64460, "loss": 0.2296, "lr": 8.965249767297549e-06, "epoch": 1.793360223394353, "percentage": 8.97, "elapsed_time": "0:09:55", "remaining_time": "1:40:46", "throughput": 5927.22, "total_tokens": 3530224} {"current_steps": 5785, "total_steps": 64460, "loss": 0.2279, "lr": 8.973006515668632e-06, "epoch": 1.7949115730685696, "percentage": 8.97, "elapsed_time": "0:09:56", "remaining_time": "1:40:46", "throughput": 5926.95, "total_tokens": 3533072} {"current_steps": 5790, "total_steps": 64460, "loss": 0.2262, "lr": 8.980763264039715e-06, "epoch": 1.7964629227427862, "percentage": 8.98, "elapsed_time": "0:09:56", "remaining_time": "1:40:45", "throughput": 5926.97, "total_tokens": 3535984} {"current_steps": 5795, "total_steps": 64460, "loss": 0.2161, "lr": 8.988520012410798e-06, "epoch": 1.798014272417003, "percentage": 8.99, "elapsed_time": "0:09:57", "remaining_time": "1:40:44", "throughput": 5926.42, "total_tokens": 3538576} {"current_steps": 5800, "total_steps": 64460, "loss": 0.2533, "lr": 8.996276760781881e-06, "epoch": 1.7995656220912193, "percentage": 9.0, "elapsed_time": "0:09:57", "remaining_time": "1:40:44", "throughput": 5926.5, "total_tokens": 3541936} {"current_steps": 5805, "total_steps": 64460, "loss": 0.2391, "lr": 9.004033509152964e-06, "epoch": 1.801116971765436, "percentage": 9.01, "elapsed_time": "0:09:58", "remaining_time": "1:40:44", "throughput": 5926.92, "total_tokens": 3545680} {"current_steps": 5810, "total_steps": 64460, "loss": 0.2315, "lr": 9.011790257524047e-06, "epoch": 1.8026683214396524, "percentage": 9.01, "elapsed_time": "0:09:58", "remaining_time": "1:40:44", "throughput": 5925.47, "total_tokens": 3548048} {"current_steps": 5815, "total_steps": 64460, "loss": 0.232, "lr": 9.01954700589513e-06, "epoch": 1.8042196711138692, "percentage": 9.02, "elapsed_time": "0:09:59", "remaining_time": "1:40:43", "throughput": 5925.12, "total_tokens": 3550832} {"current_steps": 5820, "total_steps": 64460, "loss": 0.2317, "lr": 9.027303754266213e-06, "epoch": 1.8057710207880855, "percentage": 9.03, "elapsed_time": "0:09:59", "remaining_time": "1:40:42", "throughput": 5924.38, "total_tokens": 3553200} {"current_steps": 5825, "total_steps": 64460, "loss": 0.2366, "lr": 9.035060502637294e-06, "epoch": 1.8073223704623023, "percentage": 9.04, "elapsed_time": "0:10:00", "remaining_time": "1:40:41", "throughput": 5923.67, "total_tokens": 3555408} {"current_steps": 5830, "total_steps": 64460, "loss": 0.2336, "lr": 9.042817251008377e-06, "epoch": 1.8088737201365188, "percentage": 9.04, "elapsed_time": "0:10:00", "remaining_time": "1:40:41", "throughput": 5923.53, "total_tokens": 3558640} {"current_steps": 5835, "total_steps": 64460, "loss": 0.2346, "lr": 9.05057399937946e-06, "epoch": 1.8104250698107354, "percentage": 9.05, "elapsed_time": "0:10:01", "remaining_time": "1:40:40", "throughput": 5923.22, "total_tokens": 3561200} {"current_steps": 5840, "total_steps": 64460, "loss": 0.2368, "lr": 9.058330747750543e-06, "epoch": 1.811976419484952, "percentage": 9.06, "elapsed_time": "0:10:01", "remaining_time": "1:40:41", "throughput": 5923.93, "total_tokens": 3565552} {"current_steps": 5845, "total_steps": 64460, "loss": 0.2294, "lr": 9.066087496121626e-06, "epoch": 1.8135277691591685, "percentage": 9.07, "elapsed_time": "0:10:02", "remaining_time": "1:40:40", "throughput": 5923.3, "total_tokens": 3568016} {"current_steps": 5850, "total_steps": 64460, "loss": 0.2338, "lr": 9.073844244492709e-06, "epoch": 1.815079118833385, "percentage": 9.08, "elapsed_time": "0:10:03", "remaining_time": "1:40:41", "throughput": 5923.79, "total_tokens": 3572368} {"current_steps": 5855, "total_steps": 64460, "loss": 0.2178, "lr": 9.081600992863792e-06, "epoch": 1.8166304685076016, "percentage": 9.08, "elapsed_time": "0:10:03", "remaining_time": "1:40:41", "throughput": 5924.54, "total_tokens": 3576240} {"current_steps": 5860, "total_steps": 64460, "loss": 0.2423, "lr": 9.089357741234875e-06, "epoch": 1.8181818181818183, "percentage": 9.09, "elapsed_time": "0:10:04", "remaining_time": "1:40:41", "throughput": 5923.91, "total_tokens": 3578672} {"current_steps": 5865, "total_steps": 64460, "loss": 0.2365, "lr": 9.097114489605958e-06, "epoch": 1.8197331678560347, "percentage": 9.1, "elapsed_time": "0:10:04", "remaining_time": "1:40:40", "throughput": 5923.18, "total_tokens": 3581040} {"current_steps": 5870, "total_steps": 64460, "loss": 0.2422, "lr": 9.104871237977041e-06, "epoch": 1.8212845175302514, "percentage": 9.11, "elapsed_time": "0:10:05", "remaining_time": "1:40:39", "throughput": 5923.0, "total_tokens": 3583728} {"current_steps": 5875, "total_steps": 64460, "loss": 0.2215, "lr": 9.112627986348124e-06, "epoch": 1.8228358672044678, "percentage": 9.11, "elapsed_time": "0:10:05", "remaining_time": "1:40:38", "throughput": 5921.78, "total_tokens": 3585872} {"current_steps": 5880, "total_steps": 64460, "loss": 0.2353, "lr": 9.120384734719207e-06, "epoch": 1.8243872168786845, "percentage": 9.12, "elapsed_time": "0:10:05", "remaining_time": "1:40:37", "throughput": 5921.52, "total_tokens": 3588432} {"current_steps": 5885, "total_steps": 64460, "loss": 0.2328, "lr": 9.12814148309029e-06, "epoch": 1.8259385665529009, "percentage": 9.13, "elapsed_time": "0:10:06", "remaining_time": "1:40:36", "throughput": 5921.92, "total_tokens": 3591696} {"current_steps": 5890, "total_steps": 64460, "loss": 0.2316, "lr": 9.135898231461371e-06, "epoch": 1.8274899162271177, "percentage": 9.14, "elapsed_time": "0:10:07", "remaining_time": "1:40:39", "throughput": 5923.2, "total_tokens": 3597392} {"current_steps": 5895, "total_steps": 64460, "loss": 0.2347, "lr": 9.143654979832454e-06, "epoch": 1.8290412659013342, "percentage": 9.15, "elapsed_time": "0:10:07", "remaining_time": "1:40:38", "throughput": 5922.77, "total_tokens": 3599760} {"current_steps": 5900, "total_steps": 64460, "loss": 0.2263, "lr": 9.151411728203537e-06, "epoch": 1.8305926155755508, "percentage": 9.15, "elapsed_time": "0:10:08", "remaining_time": "1:40:37", "throughput": 5922.94, "total_tokens": 3602608} {"current_steps": 5905, "total_steps": 64460, "loss": 0.2315, "lr": 9.15916847657462e-06, "epoch": 1.8321439652497673, "percentage": 9.16, "elapsed_time": "0:10:08", "remaining_time": "1:40:36", "throughput": 5923.41, "total_tokens": 3606160} {"current_steps": 5910, "total_steps": 64460, "loss": 0.2379, "lr": 9.166925224945703e-06, "epoch": 1.8336953149239839, "percentage": 9.17, "elapsed_time": "0:10:09", "remaining_time": "1:40:36", "throughput": 5923.23, "total_tokens": 3609104} {"current_steps": 5915, "total_steps": 64460, "loss": 0.2274, "lr": 9.174681973316786e-06, "epoch": 1.8352466645982004, "percentage": 9.18, "elapsed_time": "0:10:09", "remaining_time": "1:40:35", "throughput": 5923.04, "total_tokens": 3611824} {"current_steps": 5920, "total_steps": 64460, "loss": 0.2264, "lr": 9.18243872168787e-06, "epoch": 1.836798014272417, "percentage": 9.18, "elapsed_time": "0:10:10", "remaining_time": "1:40:34", "throughput": 5923.03, "total_tokens": 3614800} {"current_steps": 5925, "total_steps": 64460, "loss": 0.233, "lr": 9.190195470058952e-06, "epoch": 1.8383493639466337, "percentage": 9.19, "elapsed_time": "0:10:10", "remaining_time": "1:40:34", "throughput": 5922.66, "total_tokens": 3617392} {"current_steps": 5930, "total_steps": 64460, "loss": 0.2277, "lr": 9.197952218430035e-06, "epoch": 1.83990071362085, "percentage": 9.2, "elapsed_time": "0:10:11", "remaining_time": "1:40:33", "throughput": 5922.39, "total_tokens": 3620368} {"current_steps": 5935, "total_steps": 64460, "loss": 0.2338, "lr": 9.205708966801118e-06, "epoch": 1.8414520632950668, "percentage": 9.21, "elapsed_time": "0:10:11", "remaining_time": "1:40:33", "throughput": 5922.51, "total_tokens": 3623984} {"current_steps": 5940, "total_steps": 64460, "loss": 0.224, "lr": 9.213465715172201e-06, "epoch": 1.8430034129692832, "percentage": 9.22, "elapsed_time": "0:10:12", "remaining_time": "1:40:33", "throughput": 5922.57, "total_tokens": 3626896} {"current_steps": 5945, "total_steps": 64460, "loss": 0.236, "lr": 9.221222463543284e-06, "epoch": 1.8445547626435, "percentage": 9.22, "elapsed_time": "0:10:12", "remaining_time": "1:40:32", "throughput": 5922.43, "total_tokens": 3629904} {"current_steps": 5950, "total_steps": 64460, "loss": 0.2343, "lr": 9.228979211914365e-06, "epoch": 1.8461061123177163, "percentage": 9.23, "elapsed_time": "0:10:13", "remaining_time": "1:40:31", "throughput": 5922.17, "total_tokens": 3632592} {"current_steps": 5955, "total_steps": 64460, "loss": 0.2296, "lr": 9.236735960285448e-06, "epoch": 1.847657461991933, "percentage": 9.24, "elapsed_time": "0:10:13", "remaining_time": "1:40:30", "throughput": 5921.56, "total_tokens": 3635056} {"current_steps": 5960, "total_steps": 64460, "loss": 0.2294, "lr": 9.244492708656531e-06, "epoch": 1.8492088116661496, "percentage": 9.25, "elapsed_time": "0:10:14", "remaining_time": "1:40:29", "throughput": 5920.7, "total_tokens": 3637296} {"current_steps": 5965, "total_steps": 64460, "loss": 0.2393, "lr": 9.252249457027614e-06, "epoch": 1.8507601613403661, "percentage": 9.25, "elapsed_time": "0:10:14", "remaining_time": "1:40:29", "throughput": 5920.11, "total_tokens": 3639728} {"current_steps": 5970, "total_steps": 64460, "loss": 0.2244, "lr": 9.260006205398697e-06, "epoch": 1.8523115110145827, "percentage": 9.26, "elapsed_time": "0:10:15", "remaining_time": "1:40:29", "throughput": 5920.91, "total_tokens": 3643760} {"current_steps": 5975, "total_steps": 64460, "loss": 0.2318, "lr": 9.26776295376978e-06, "epoch": 1.8538628606887992, "percentage": 9.27, "elapsed_time": "0:10:15", "remaining_time": "1:40:29", "throughput": 5921.37, "total_tokens": 3647376} {"current_steps": 5980, "total_steps": 64460, "loss": 0.232, "lr": 9.275519702140863e-06, "epoch": 1.8554142103630158, "percentage": 9.28, "elapsed_time": "0:10:16", "remaining_time": "1:40:28", "throughput": 5921.63, "total_tokens": 3650448} {"current_steps": 5985, "total_steps": 64460, "loss": 0.2299, "lr": 9.283276450511946e-06, "epoch": 1.8569655600372323, "percentage": 9.28, "elapsed_time": "0:10:17", "remaining_time": "1:40:28", "throughput": 5921.79, "total_tokens": 3653744} {"current_steps": 5990, "total_steps": 64460, "loss": 0.24, "lr": 9.29103319888303e-06, "epoch": 1.8585169097114491, "percentage": 9.29, "elapsed_time": "0:10:17", "remaining_time": "1:40:28", "throughput": 5922.33, "total_tokens": 3657296} {"current_steps": 5995, "total_steps": 64460, "loss": 0.2303, "lr": 9.298789947254112e-06, "epoch": 1.8600682593856654, "percentage": 9.3, "elapsed_time": "0:10:18", "remaining_time": "1:40:27", "throughput": 5921.92, "total_tokens": 3659984} {"current_steps": 6000, "total_steps": 64460, "loss": 0.23, "lr": 9.306546695625195e-06, "epoch": 1.8616196090598822, "percentage": 9.31, "elapsed_time": "0:10:18", "remaining_time": "1:40:26", "throughput": 5921.67, "total_tokens": 3662576} {"current_steps": 6005, "total_steps": 64460, "loss": 0.2346, "lr": 9.314303443996278e-06, "epoch": 1.8631709587340985, "percentage": 9.32, "elapsed_time": "0:10:18", "remaining_time": "1:40:25", "throughput": 5921.52, "total_tokens": 3665264} {"current_steps": 6010, "total_steps": 64460, "loss": 0.2296, "lr": 9.32206019236736e-06, "epoch": 1.8647223084083153, "percentage": 9.32, "elapsed_time": "0:10:19", "remaining_time": "1:40:24", "throughput": 5920.85, "total_tokens": 3667600} {"current_steps": 6015, "total_steps": 64460, "loss": 0.2275, "lr": 9.329816940738443e-06, "epoch": 1.8662736580825317, "percentage": 9.33, "elapsed_time": "0:10:19", "remaining_time": "1:40:23", "throughput": 5920.99, "total_tokens": 3670512} {"current_steps": 6020, "total_steps": 64460, "loss": 0.2313, "lr": 9.337573689109526e-06, "epoch": 1.8678250077567484, "percentage": 9.34, "elapsed_time": "0:10:20", "remaining_time": "1:40:22", "throughput": 5920.57, "total_tokens": 3673264} {"current_steps": 6025, "total_steps": 64460, "loss": 0.233, "lr": 9.345330437480609e-06, "epoch": 1.869376357430965, "percentage": 9.35, "elapsed_time": "0:10:20", "remaining_time": "1:40:21", "throughput": 5920.43, "total_tokens": 3675856} {"current_steps": 6030, "total_steps": 64460, "loss": 0.2272, "lr": 9.353087185851691e-06, "epoch": 1.8709277071051815, "percentage": 9.35, "elapsed_time": "0:10:21", "remaining_time": "1:40:20", "throughput": 5920.04, "total_tokens": 3678256} {"current_steps": 6035, "total_steps": 64460, "loss": 0.2386, "lr": 9.360843934222774e-06, "epoch": 1.872479056779398, "percentage": 9.36, "elapsed_time": "0:10:21", "remaining_time": "1:40:19", "throughput": 5920.58, "total_tokens": 3681552} {"current_steps": 6040, "total_steps": 64460, "loss": 0.2321, "lr": 9.368600682593857e-06, "epoch": 1.8740304064536146, "percentage": 9.37, "elapsed_time": "0:10:22", "remaining_time": "1:40:19", "throughput": 5920.4, "total_tokens": 3684624} {"current_steps": 6045, "total_steps": 64460, "loss": 0.2263, "lr": 9.37635743096494e-06, "epoch": 1.8755817561278312, "percentage": 9.38, "elapsed_time": "0:10:22", "remaining_time": "1:40:19", "throughput": 5920.67, "total_tokens": 3688048} {"current_steps": 6050, "total_steps": 64460, "loss": 0.232, "lr": 9.384114179336023e-06, "epoch": 1.8771331058020477, "percentage": 9.39, "elapsed_time": "0:10:23", "remaining_time": "1:40:18", "throughput": 5920.67, "total_tokens": 3690832} {"current_steps": 6055, "total_steps": 64460, "loss": 0.2326, "lr": 9.391870927707106e-06, "epoch": 1.8786844554762645, "percentage": 9.39, "elapsed_time": "0:10:23", "remaining_time": "1:40:17", "throughput": 5920.64, "total_tokens": 3693744} {"current_steps": 6060, "total_steps": 64460, "loss": 0.2304, "lr": 9.39962767607819e-06, "epoch": 1.8802358051504808, "percentage": 9.4, "elapsed_time": "0:10:24", "remaining_time": "1:40:18", "throughput": 5921.35, "total_tokens": 3697712} {"current_steps": 6065, "total_steps": 64460, "loss": 0.2254, "lr": 9.407384424449272e-06, "epoch": 1.8817871548246976, "percentage": 9.41, "elapsed_time": "0:10:24", "remaining_time": "1:40:17", "throughput": 5921.44, "total_tokens": 3700560} {"current_steps": 6070, "total_steps": 64460, "loss": 0.2272, "lr": 9.415141172820355e-06, "epoch": 1.883338504498914, "percentage": 9.42, "elapsed_time": "0:10:25", "remaining_time": "1:40:16", "throughput": 5920.99, "total_tokens": 3703120} {"current_steps": 6075, "total_steps": 64460, "loss": 0.2427, "lr": 9.422897921191437e-06, "epoch": 1.8848898541731307, "percentage": 9.42, "elapsed_time": "0:10:25", "remaining_time": "1:40:15", "throughput": 5921.2, "total_tokens": 3706416} {"current_steps": 6080, "total_steps": 64460, "loss": 0.2146, "lr": 9.43065466956252e-06, "epoch": 1.886441203847347, "percentage": 9.43, "elapsed_time": "0:10:26", "remaining_time": "1:40:15", "throughput": 5921.69, "total_tokens": 3709776} {"current_steps": 6085, "total_steps": 64460, "loss": 0.2539, "lr": 9.438411417933603e-06, "epoch": 1.8879925535215638, "percentage": 9.44, "elapsed_time": "0:10:27", "remaining_time": "1:40:15", "throughput": 5921.45, "total_tokens": 3712784} {"current_steps": 6090, "total_steps": 64460, "loss": 0.2242, "lr": 9.446168166304686e-06, "epoch": 1.8895439031957804, "percentage": 9.45, "elapsed_time": "0:10:27", "remaining_time": "1:40:15", "throughput": 5922.14, "total_tokens": 3716880} {"current_steps": 6095, "total_steps": 64460, "loss": 0.2257, "lr": 9.453924914675769e-06, "epoch": 1.891095252869997, "percentage": 9.46, "elapsed_time": "0:10:28", "remaining_time": "1:40:14", "throughput": 5921.4, "total_tokens": 3719024} {"current_steps": 6100, "total_steps": 64460, "loss": 0.2265, "lr": 9.461681663046852e-06, "epoch": 1.8926466025442135, "percentage": 9.46, "elapsed_time": "0:10:28", "remaining_time": "1:40:13", "throughput": 5921.48, "total_tokens": 3722256} {"current_steps": 6105, "total_steps": 64460, "loss": 0.2345, "lr": 9.469438411417935e-06, "epoch": 1.89419795221843, "percentage": 9.47, "elapsed_time": "0:10:29", "remaining_time": "1:40:12", "throughput": 5920.87, "total_tokens": 3724432} {"current_steps": 6110, "total_steps": 64460, "loss": 0.2291, "lr": 9.477195159789018e-06, "epoch": 1.8957493018926466, "percentage": 9.48, "elapsed_time": "0:10:29", "remaining_time": "1:40:12", "throughput": 5921.27, "total_tokens": 3728080} {"current_steps": 6115, "total_steps": 64460, "loss": 0.2285, "lr": 9.4849519081601e-06, "epoch": 1.8973006515668631, "percentage": 9.49, "elapsed_time": "0:10:30", "remaining_time": "1:40:11", "throughput": 5921.02, "total_tokens": 3730800} {"current_steps": 6120, "total_steps": 64460, "loss": 0.2331, "lr": 9.492708656531184e-06, "epoch": 1.89885200124108, "percentage": 9.49, "elapsed_time": "0:10:30", "remaining_time": "1:40:12", "throughput": 5921.68, "total_tokens": 3734928} {"current_steps": 6125, "total_steps": 64460, "loss": 0.2235, "lr": 9.500465404902266e-06, "epoch": 1.9004033509152962, "percentage": 9.5, "elapsed_time": "0:10:31", "remaining_time": "1:40:11", "throughput": 5921.73, "total_tokens": 3737808} {"current_steps": 6130, "total_steps": 64460, "loss": 0.2173, "lr": 9.50822215327335e-06, "epoch": 1.901954700589513, "percentage": 9.51, "elapsed_time": "0:10:31", "remaining_time": "1:40:11", "throughput": 5921.52, "total_tokens": 3740976} {"current_steps": 6135, "total_steps": 64460, "loss": 0.2373, "lr": 9.51597890164443e-06, "epoch": 1.9035060502637293, "percentage": 9.52, "elapsed_time": "0:10:32", "remaining_time": "1:40:11", "throughput": 5922.19, "total_tokens": 3744752} {"current_steps": 6140, "total_steps": 64460, "loss": 0.2354, "lr": 9.523735650015514e-06, "epoch": 1.905057399937946, "percentage": 9.53, "elapsed_time": "0:10:32", "remaining_time": "1:40:12", "throughput": 5923.23, "total_tokens": 3749264} {"current_steps": 6145, "total_steps": 64460, "loss": 0.2347, "lr": 9.531492398386597e-06, "epoch": 1.9066087496121624, "percentage": 9.53, "elapsed_time": "0:10:33", "remaining_time": "1:40:11", "throughput": 5923.05, "total_tokens": 3752240} {"current_steps": 6150, "total_steps": 64460, "loss": 0.2403, "lr": 9.53924914675768e-06, "epoch": 1.9081600992863792, "percentage": 9.54, "elapsed_time": "0:10:34", "remaining_time": "1:40:11", "throughput": 5923.58, "total_tokens": 3755792} {"current_steps": 6155, "total_steps": 64460, "loss": 0.2326, "lr": 9.547005895128763e-06, "epoch": 1.9097114489605957, "percentage": 9.55, "elapsed_time": "0:10:34", "remaining_time": "1:40:10", "throughput": 5923.89, "total_tokens": 3758960} {"current_steps": 6160, "total_steps": 64460, "loss": 0.2294, "lr": 9.554762643499846e-06, "epoch": 1.9112627986348123, "percentage": 9.56, "elapsed_time": "0:10:35", "remaining_time": "1:40:11", "throughput": 5924.49, "total_tokens": 3762928} {"current_steps": 6165, "total_steps": 64460, "loss": 0.2346, "lr": 9.562519391870929e-06, "epoch": 1.9128141483090288, "percentage": 9.56, "elapsed_time": "0:10:35", "remaining_time": "1:40:10", "throughput": 5924.33, "total_tokens": 3765680} {"current_steps": 6170, "total_steps": 64460, "loss": 0.2335, "lr": 9.57027614024201e-06, "epoch": 1.9143654979832454, "percentage": 9.57, "elapsed_time": "0:10:36", "remaining_time": "1:40:10", "throughput": 5924.9, "total_tokens": 3769296} {"current_steps": 6175, "total_steps": 64460, "loss": 0.2391, "lr": 9.578032888613095e-06, "epoch": 1.915916847657462, "percentage": 9.58, "elapsed_time": "0:10:36", "remaining_time": "1:40:10", "throughput": 5924.68, "total_tokens": 3772528} {"current_steps": 6180, "total_steps": 64460, "loss": 0.2333, "lr": 9.585789636984178e-06, "epoch": 1.9174681973316785, "percentage": 9.59, "elapsed_time": "0:10:37", "remaining_time": "1:40:09", "throughput": 5924.81, "total_tokens": 3775408} {"current_steps": 6185, "total_steps": 64460, "loss": 0.2338, "lr": 9.59354638535526e-06, "epoch": 1.9190195470058953, "percentage": 9.6, "elapsed_time": "0:10:37", "remaining_time": "1:40:09", "throughput": 5924.78, "total_tokens": 3778960} {"current_steps": 6190, "total_steps": 64460, "loss": 0.2277, "lr": 9.601303133726344e-06, "epoch": 1.9205708966801116, "percentage": 9.6, "elapsed_time": "0:10:38", "remaining_time": "1:40:09", "throughput": 5925.19, "total_tokens": 3782256} {"current_steps": 6195, "total_steps": 64460, "loss": 0.2218, "lr": 9.609059882097425e-06, "epoch": 1.9221222463543284, "percentage": 9.61, "elapsed_time": "0:10:38", "remaining_time": "1:40:08", "throughput": 5924.81, "total_tokens": 3784976} {"current_steps": 6200, "total_steps": 64460, "loss": 0.2584, "lr": 9.616816630468508e-06, "epoch": 1.9236735960285447, "percentage": 9.62, "elapsed_time": "0:10:39", "remaining_time": "1:40:07", "throughput": 5924.66, "total_tokens": 3787600} {"current_steps": 6205, "total_steps": 64460, "loss": 0.2382, "lr": 9.62457337883959e-06, "epoch": 1.9252249457027615, "percentage": 9.63, "elapsed_time": "0:10:39", "remaining_time": "1:40:06", "throughput": 5924.65, "total_tokens": 3790384} {"current_steps": 6210, "total_steps": 64460, "loss": 0.2256, "lr": 9.632330127210674e-06, "epoch": 1.9267762953769778, "percentage": 9.63, "elapsed_time": "0:10:40", "remaining_time": "1:40:05", "throughput": 5925.05, "total_tokens": 3793712} {"current_steps": 6215, "total_steps": 64460, "loss": 0.2337, "lr": 9.640086875581757e-06, "epoch": 1.9283276450511946, "percentage": 9.64, "elapsed_time": "0:10:40", "remaining_time": "1:40:05", "throughput": 5925.35, "total_tokens": 3797232} {"current_steps": 6220, "total_steps": 64460, "loss": 0.2315, "lr": 9.64784362395284e-06, "epoch": 1.9298789947254111, "percentage": 9.65, "elapsed_time": "0:10:41", "remaining_time": "1:40:04", "throughput": 5924.97, "total_tokens": 3799600} {"current_steps": 6225, "total_steps": 64460, "loss": 0.2312, "lr": 9.655600372323923e-06, "epoch": 1.9314303443996277, "percentage": 9.66, "elapsed_time": "0:10:41", "remaining_time": "1:40:03", "throughput": 5924.99, "total_tokens": 3802608} {"current_steps": 6230, "total_steps": 64460, "loss": 0.2316, "lr": 9.663357120695006e-06, "epoch": 1.9329816940738442, "percentage": 9.66, "elapsed_time": "0:10:42", "remaining_time": "1:40:02", "throughput": 5924.78, "total_tokens": 3805136} {"current_steps": 6235, "total_steps": 64460, "loss": 0.2277, "lr": 9.671113869066087e-06, "epoch": 1.9345330437480608, "percentage": 9.67, "elapsed_time": "0:10:42", "remaining_time": "1:40:01", "throughput": 5924.54, "total_tokens": 3807760} {"current_steps": 6240, "total_steps": 64460, "loss": 0.2372, "lr": 9.678870617437172e-06, "epoch": 1.9360843934222773, "percentage": 9.68, "elapsed_time": "0:10:43", "remaining_time": "1:40:01", "throughput": 5924.24, "total_tokens": 3810416} {"current_steps": 6245, "total_steps": 64460, "loss": 0.2236, "lr": 9.686627365808255e-06, "epoch": 1.937635743096494, "percentage": 9.69, "elapsed_time": "0:10:43", "remaining_time": "1:40:00", "throughput": 5924.28, "total_tokens": 3813360} {"current_steps": 6250, "total_steps": 64460, "loss": 0.2202, "lr": 9.694384114179338e-06, "epoch": 1.9391870927707107, "percentage": 9.7, "elapsed_time": "0:10:44", "remaining_time": "1:39:59", "throughput": 5923.64, "total_tokens": 3815632} {"current_steps": 6255, "total_steps": 64460, "loss": 0.2366, "lr": 9.70214086255042e-06, "epoch": 1.940738442444927, "percentage": 9.7, "elapsed_time": "0:10:44", "remaining_time": "1:39:58", "throughput": 5923.38, "total_tokens": 3818192} {"current_steps": 6260, "total_steps": 64460, "loss": 0.2516, "lr": 9.709897610921502e-06, "epoch": 1.9422897921191438, "percentage": 9.71, "elapsed_time": "0:10:45", "remaining_time": "1:39:57", "throughput": 5923.1, "total_tokens": 3820912} {"current_steps": 6265, "total_steps": 64460, "loss": 0.2477, "lr": 9.717654359292585e-06, "epoch": 1.94384114179336, "percentage": 9.72, "elapsed_time": "0:10:45", "remaining_time": "1:39:56", "throughput": 5923.11, "total_tokens": 3823824} {"current_steps": 6270, "total_steps": 64460, "loss": 0.2303, "lr": 9.725411107663668e-06, "epoch": 1.9453924914675769, "percentage": 9.73, "elapsed_time": "0:10:46", "remaining_time": "1:39:55", "throughput": 5922.31, "total_tokens": 3826192} {"current_steps": 6275, "total_steps": 64460, "loss": 0.2326, "lr": 9.733167856034751e-06, "epoch": 1.9469438411417932, "percentage": 9.73, "elapsed_time": "0:10:46", "remaining_time": "1:39:55", "throughput": 5922.83, "total_tokens": 3829744} {"current_steps": 6280, "total_steps": 64460, "loss": 0.2356, "lr": 9.740924604405834e-06, "epoch": 1.94849519081601, "percentage": 9.74, "elapsed_time": "0:10:47", "remaining_time": "1:39:55", "throughput": 5922.69, "total_tokens": 3832688} {"current_steps": 6285, "total_steps": 64460, "loss": 0.2305, "lr": 9.748681352776917e-06, "epoch": 1.9500465404902265, "percentage": 9.75, "elapsed_time": "0:10:47", "remaining_time": "1:39:55", "throughput": 5922.79, "total_tokens": 3836496} {"current_steps": 6290, "total_steps": 64460, "loss": 0.2342, "lr": 9.756438101148e-06, "epoch": 1.951597890164443, "percentage": 9.76, "elapsed_time": "0:10:48", "remaining_time": "1:39:54", "throughput": 5922.77, "total_tokens": 3839344} {"current_steps": 6295, "total_steps": 64460, "loss": 0.2294, "lr": 9.764194849519081e-06, "epoch": 1.9531492398386596, "percentage": 9.77, "elapsed_time": "0:10:48", "remaining_time": "1:39:55", "throughput": 5923.35, "total_tokens": 3843600} {"current_steps": 6300, "total_steps": 64460, "loss": 0.2283, "lr": 9.771951597890166e-06, "epoch": 1.9547005895128762, "percentage": 9.77, "elapsed_time": "0:10:49", "remaining_time": "1:39:55", "throughput": 5923.29, "total_tokens": 3846736} {"current_steps": 6305, "total_steps": 64460, "loss": 0.2315, "lr": 9.779708346261249e-06, "epoch": 1.9562519391870927, "percentage": 9.78, "elapsed_time": "0:10:50", "remaining_time": "1:39:55", "throughput": 5924.06, "total_tokens": 3850832} {"current_steps": 6310, "total_steps": 64460, "loss": 0.2346, "lr": 9.787465094632332e-06, "epoch": 1.9578032888613093, "percentage": 9.79, "elapsed_time": "0:10:50", "remaining_time": "1:39:56", "throughput": 5924.93, "total_tokens": 3855216} {"current_steps": 6315, "total_steps": 64460, "loss": 0.2316, "lr": 9.795221843003415e-06, "epoch": 1.959354638535526, "percentage": 9.8, "elapsed_time": "0:10:51", "remaining_time": "1:39:55", "throughput": 5924.05, "total_tokens": 3857520} {"current_steps": 6320, "total_steps": 64460, "loss": 0.2275, "lr": 9.802978591374496e-06, "epoch": 1.9609059882097424, "percentage": 9.8, "elapsed_time": "0:10:51", "remaining_time": "1:39:55", "throughput": 5924.25, "total_tokens": 3860720} {"current_steps": 6325, "total_steps": 64460, "loss": 0.2255, "lr": 9.810735339745579e-06, "epoch": 1.9624573378839592, "percentage": 9.81, "elapsed_time": "0:10:52", "remaining_time": "1:39:54", "throughput": 5924.37, "total_tokens": 3863536} {"current_steps": 6330, "total_steps": 64460, "loss": 0.2475, "lr": 9.818492088116662e-06, "epoch": 1.9640086875581755, "percentage": 9.82, "elapsed_time": "0:10:52", "remaining_time": "1:39:53", "throughput": 5924.21, "total_tokens": 3866384} {"current_steps": 6335, "total_steps": 64460, "loss": 0.2363, "lr": 9.826248836487745e-06, "epoch": 1.9655600372323923, "percentage": 9.83, "elapsed_time": "0:10:53", "remaining_time": "1:39:52", "throughput": 5924.07, "total_tokens": 3869168} {"current_steps": 6340, "total_steps": 64460, "loss": 0.2307, "lr": 9.834005584858828e-06, "epoch": 1.9671113869066086, "percentage": 9.84, "elapsed_time": "0:10:53", "remaining_time": "1:39:52", "throughput": 5924.53, "total_tokens": 3873008} {"current_steps": 6345, "total_steps": 64460, "loss": 0.2253, "lr": 9.841762333229911e-06, "epoch": 1.9686627365808254, "percentage": 9.84, "elapsed_time": "0:10:54", "remaining_time": "1:39:52", "throughput": 5924.31, "total_tokens": 3875824} {"current_steps": 6350, "total_steps": 64460, "loss": 0.2313, "lr": 9.849519081600994e-06, "epoch": 1.970214086255042, "percentage": 9.85, "elapsed_time": "0:10:54", "remaining_time": "1:39:52", "throughput": 5924.93, "total_tokens": 3879728} {"current_steps": 6355, "total_steps": 64460, "loss": 0.2276, "lr": 9.857275829972075e-06, "epoch": 1.9717654359292585, "percentage": 9.86, "elapsed_time": "0:10:55", "remaining_time": "1:39:51", "throughput": 5924.68, "total_tokens": 3882448} {"current_steps": 6360, "total_steps": 64460, "loss": 0.2294, "lr": 9.865032578343158e-06, "epoch": 1.973316785603475, "percentage": 9.87, "elapsed_time": "0:10:55", "remaining_time": "1:39:50", "throughput": 5924.31, "total_tokens": 3884848} {"current_steps": 6365, "total_steps": 64460, "loss": 0.2252, "lr": 9.872789326714243e-06, "epoch": 1.9748681352776916, "percentage": 9.87, "elapsed_time": "0:10:56", "remaining_time": "1:39:50", "throughput": 5924.67, "total_tokens": 3888304} {"current_steps": 6370, "total_steps": 64460, "loss": 0.243, "lr": 9.880546075085326e-06, "epoch": 1.9764194849519081, "percentage": 9.88, "elapsed_time": "0:10:56", "remaining_time": "1:39:49", "throughput": 5925.04, "total_tokens": 3891568} {"current_steps": 6375, "total_steps": 64460, "loss": 0.2341, "lr": 9.888302823456409e-06, "epoch": 1.9779708346261247, "percentage": 9.89, "elapsed_time": "0:10:57", "remaining_time": "1:39:48", "throughput": 5925.17, "total_tokens": 3894352} {"current_steps": 6380, "total_steps": 64460, "loss": 0.2369, "lr": 9.89605957182749e-06, "epoch": 1.9795221843003414, "percentage": 9.9, "elapsed_time": "0:10:57", "remaining_time": "1:39:47", "throughput": 5924.37, "total_tokens": 3896496} {"current_steps": 6385, "total_steps": 64460, "loss": 0.2061, "lr": 9.903816320198573e-06, "epoch": 1.9810735339745578, "percentage": 9.91, "elapsed_time": "0:10:58", "remaining_time": "1:39:46", "throughput": 5924.44, "total_tokens": 3899440} {"current_steps": 6390, "total_steps": 64460, "loss": 0.2567, "lr": 9.911573068569656e-06, "epoch": 1.9826248836487745, "percentage": 9.91, "elapsed_time": "0:10:58", "remaining_time": "1:39:45", "throughput": 5924.35, "total_tokens": 3902256} {"current_steps": 6395, "total_steps": 64460, "loss": 0.3153, "lr": 9.919329816940739e-06, "epoch": 1.9841762333229909, "percentage": 9.92, "elapsed_time": "0:10:59", "remaining_time": "1:39:46", "throughput": 5925.08, "total_tokens": 3906640} {"current_steps": 6400, "total_steps": 64460, "loss": 0.2427, "lr": 9.927086565311822e-06, "epoch": 1.9857275829972076, "percentage": 9.93, "elapsed_time": "0:10:59", "remaining_time": "1:39:45", "throughput": 5924.79, "total_tokens": 3909168} {"current_steps": 6405, "total_steps": 64460, "loss": 0.2202, "lr": 9.934843313682905e-06, "epoch": 1.9872789326714242, "percentage": 9.94, "elapsed_time": "0:11:00", "remaining_time": "1:39:44", "throughput": 5924.42, "total_tokens": 3911632} {"current_steps": 6410, "total_steps": 64460, "loss": 0.2458, "lr": 9.942600062053988e-06, "epoch": 1.9888302823456407, "percentage": 9.94, "elapsed_time": "0:11:00", "remaining_time": "1:39:43", "throughput": 5923.72, "total_tokens": 3913936} {"current_steps": 6415, "total_steps": 64460, "loss": 0.2326, "lr": 9.950356810425071e-06, "epoch": 1.9903816320198573, "percentage": 9.95, "elapsed_time": "0:11:01", "remaining_time": "1:39:43", "throughput": 5923.9, "total_tokens": 3917072} {"current_steps": 6420, "total_steps": 64460, "loss": 0.2861, "lr": 9.958113558796152e-06, "epoch": 1.9919329816940738, "percentage": 9.96, "elapsed_time": "0:11:01", "remaining_time": "1:39:41", "throughput": 5923.05, "total_tokens": 3919216} {"current_steps": 6425, "total_steps": 64460, "loss": 0.2326, "lr": 9.965870307167235e-06, "epoch": 1.9934843313682904, "percentage": 9.97, "elapsed_time": "0:11:02", "remaining_time": "1:39:40", "throughput": 5923.02, "total_tokens": 3921872} {"current_steps": 6430, "total_steps": 64460, "loss": 0.2366, "lr": 9.97362705553832e-06, "epoch": 1.995035681042507, "percentage": 9.98, "elapsed_time": "0:11:02", "remaining_time": "1:39:40", "throughput": 5922.99, "total_tokens": 3924656} {"current_steps": 6435, "total_steps": 64460, "loss": 0.2325, "lr": 9.981383803909403e-06, "epoch": 1.9965870307167235, "percentage": 9.98, "elapsed_time": "0:11:03", "remaining_time": "1:39:39", "throughput": 5923.21, "total_tokens": 3927728} {"current_steps": 6440, "total_steps": 64460, "loss": 0.2406, "lr": 9.989140552280486e-06, "epoch": 1.99813838039094, "percentage": 9.99, "elapsed_time": "0:11:03", "remaining_time": "1:39:38", "throughput": 5923.78, "total_tokens": 3931152} {"current_steps": 6445, "total_steps": 64460, "loss": 0.2264, "lr": 9.996897300651567e-06, "epoch": 1.9996897300651568, "percentage": 10.0, "elapsed_time": "0:11:04", "remaining_time": "1:39:37", "throughput": 5923.64, "total_tokens": 3933808} {"current_steps": 6446, "total_steps": 64460, "eval_loss": 0.23272447288036346, "epoch": 2.0, "percentage": 10.0, "elapsed_time": "0:11:38", "remaining_time": "1:44:48", "throughput": 5630.42, "total_tokens": 3934032} {"current_steps": 6450, "total_steps": 64460, "loss": 0.2295, "lr": 9.999999934019343e-06, "epoch": 2.001241079739373, "percentage": 10.01, "elapsed_time": "0:11:42", "remaining_time": "1:45:20", "throughput": 5601.5, "total_tokens": 3936528} {"current_steps": 6455, "total_steps": 64460, "loss": 0.2348, "lr": 9.99999953080422e-06, "epoch": 2.00279242941359, "percentage": 10.01, "elapsed_time": "0:11:43", "remaining_time": "1:45:19", "throughput": 5600.75, "total_tokens": 3938768} {"current_steps": 6460, "total_steps": 64460, "loss": 0.2323, "lr": 9.999998761029918e-06, "epoch": 2.0043437790878063, "percentage": 10.02, "elapsed_time": "0:11:43", "remaining_time": "1:45:18", "throughput": 5601.12, "total_tokens": 3941904} {"current_steps": 6465, "total_steps": 64460, "loss": 0.2237, "lr": 9.9999976246965e-06, "epoch": 2.005895128762023, "percentage": 10.03, "elapsed_time": "0:11:44", "remaining_time": "1:45:17", "throughput": 5600.54, "total_tokens": 3944336} {"current_steps": 6470, "total_steps": 64460, "loss": 0.2353, "lr": 9.99999612180405e-06, "epoch": 2.0074464784362394, "percentage": 10.04, "elapsed_time": "0:11:44", "remaining_time": "1:45:17", "throughput": 5600.31, "total_tokens": 3947088} {"current_steps": 6475, "total_steps": 64460, "loss": 0.2361, "lr": 9.999994252352671e-06, "epoch": 2.008997828110456, "percentage": 10.04, "elapsed_time": "0:11:45", "remaining_time": "1:45:16", "throughput": 5601.01, "total_tokens": 3950704} {"current_steps": 6480, "total_steps": 64460, "loss": 0.2315, "lr": 9.999992016342509e-06, "epoch": 2.0105491777846725, "percentage": 10.05, "elapsed_time": "0:11:45", "remaining_time": "1:45:15", "throughput": 5600.59, "total_tokens": 3953296} {"current_steps": 6485, "total_steps": 64460, "loss": 0.2357, "lr": 9.99998941377372e-06, "epoch": 2.0121005274588892, "percentage": 10.06, "elapsed_time": "0:11:46", "remaining_time": "1:45:14", "throughput": 5600.7, "total_tokens": 3956176} {"current_steps": 6490, "total_steps": 64460, "loss": 0.2365, "lr": 9.999986444646499e-06, "epoch": 2.013651877133106, "percentage": 10.07, "elapsed_time": "0:11:47", "remaining_time": "1:45:18", "throughput": 5602.81, "total_tokens": 3963376} {"current_steps": 6495, "total_steps": 64460, "loss": 0.2336, "lr": 9.999983108961064e-06, "epoch": 2.0152032268073223, "percentage": 10.08, "elapsed_time": "0:11:47", "remaining_time": "1:45:17", "throughput": 5602.93, "total_tokens": 3966256} {"current_steps": 6500, "total_steps": 64460, "loss": 0.234, "lr": 9.999979406717657e-06, "epoch": 2.016754576481539, "percentage": 10.08, "elapsed_time": "0:11:48", "remaining_time": "1:45:16", "throughput": 5602.47, "total_tokens": 3968848} {"current_steps": 6505, "total_steps": 64460, "loss": 0.238, "lr": 9.999975337916551e-06, "epoch": 2.0183059261557554, "percentage": 10.09, "elapsed_time": "0:11:48", "remaining_time": "1:45:15", "throughput": 5602.32, "total_tokens": 3971408} {"current_steps": 6510, "total_steps": 64460, "loss": 0.2316, "lr": 9.999970902558046e-06, "epoch": 2.019857275829972, "percentage": 10.1, "elapsed_time": "0:11:49", "remaining_time": "1:45:15", "throughput": 5602.16, "total_tokens": 3974448} {"current_steps": 6515, "total_steps": 64460, "loss": 0.2327, "lr": 9.999966100642464e-06, "epoch": 2.0214086255041885, "percentage": 10.11, "elapsed_time": "0:11:49", "remaining_time": "1:45:14", "throughput": 5602.23, "total_tokens": 3977328} {"current_steps": 6520, "total_steps": 64460, "loss": 0.2369, "lr": 9.999960932170158e-06, "epoch": 2.0229599751784053, "percentage": 10.11, "elapsed_time": "0:11:50", "remaining_time": "1:45:13", "throughput": 5601.77, "total_tokens": 3979696} {"current_steps": 6525, "total_steps": 64460, "loss": 0.2336, "lr": 9.999955397141509e-06, "epoch": 2.0245113248526216, "percentage": 10.12, "elapsed_time": "0:11:51", "remaining_time": "1:45:13", "throughput": 5602.44, "total_tokens": 3983440} {"current_steps": 6530, "total_steps": 64460, "loss": 0.2317, "lr": 9.99994949555692e-06, "epoch": 2.0260626745268384, "percentage": 10.13, "elapsed_time": "0:11:51", "remaining_time": "1:45:12", "throughput": 5602.78, "total_tokens": 3986704} {"current_steps": 6535, "total_steps": 64460, "loss": 0.2296, "lr": 9.999943227416823e-06, "epoch": 2.0276140242010547, "percentage": 10.14, "elapsed_time": "0:11:52", "remaining_time": "1:45:12", "throughput": 5603.1, "total_tokens": 3990352} {"current_steps": 6540, "total_steps": 64460, "loss": 0.227, "lr": 9.999936592721682e-06, "epoch": 2.0291653738752715, "percentage": 10.15, "elapsed_time": "0:11:52", "remaining_time": "1:45:11", "throughput": 5602.78, "total_tokens": 3992752} {"current_steps": 6545, "total_steps": 64460, "loss": 0.2369, "lr": 9.99992959147198e-06, "epoch": 2.030716723549488, "percentage": 10.15, "elapsed_time": "0:11:53", "remaining_time": "1:45:10", "throughput": 5602.91, "total_tokens": 3995568} {"current_steps": 6550, "total_steps": 64460, "loss": 0.2294, "lr": 9.99992222366823e-06, "epoch": 2.0322680732237046, "percentage": 10.16, "elapsed_time": "0:11:53", "remaining_time": "1:45:10", "throughput": 5603.52, "total_tokens": 3999408} {"current_steps": 6555, "total_steps": 64460, "loss": 0.2315, "lr": 9.999914489310973e-06, "epoch": 2.0338194228979214, "percentage": 10.17, "elapsed_time": "0:11:54", "remaining_time": "1:45:09", "throughput": 5603.02, "total_tokens": 4001680} {"current_steps": 6560, "total_steps": 64460, "loss": 0.2296, "lr": 9.999906388400777e-06, "epoch": 2.0353707725721377, "percentage": 10.18, "elapsed_time": "0:11:54", "remaining_time": "1:45:09", "throughput": 5603.65, "total_tokens": 4005552} {"current_steps": 6565, "total_steps": 64460, "loss": 0.2351, "lr": 9.999897920938235e-06, "epoch": 2.0369221222463545, "percentage": 10.18, "elapsed_time": "0:11:55", "remaining_time": "1:45:08", "throughput": 5603.7, "total_tokens": 4008336} {"current_steps": 6570, "total_steps": 64460, "loss": 0.2316, "lr": 9.999889086923967e-06, "epoch": 2.038473471920571, "percentage": 10.19, "elapsed_time": "0:11:55", "remaining_time": "1:45:06", "throughput": 5603.1, "total_tokens": 4010608} {"current_steps": 6575, "total_steps": 64460, "loss": 0.2258, "lr": 9.999879886358622e-06, "epoch": 2.0400248215947876, "percentage": 10.2, "elapsed_time": "0:11:56", "remaining_time": "1:45:07", "throughput": 5604.22, "total_tokens": 4015216} {"current_steps": 6580, "total_steps": 64460, "loss": 0.2309, "lr": 9.999870319242872e-06, "epoch": 2.041576171269004, "percentage": 10.21, "elapsed_time": "0:11:57", "remaining_time": "1:45:07", "throughput": 5604.98, "total_tokens": 4018800} {"current_steps": 6585, "total_steps": 64460, "loss": 0.2405, "lr": 9.999860385577422e-06, "epoch": 2.0431275209432207, "percentage": 10.22, "elapsed_time": "0:11:57", "remaining_time": "1:45:06", "throughput": 5605.81, "total_tokens": 4022416} {"current_steps": 6590, "total_steps": 64460, "loss": 0.2265, "lr": 9.999850085362998e-06, "epoch": 2.044678870617437, "percentage": 10.22, "elapsed_time": "0:11:58", "remaining_time": "1:45:06", "throughput": 5606.84, "total_tokens": 4026640} {"current_steps": 6595, "total_steps": 64460, "loss": 0.2315, "lr": 9.999839418600357e-06, "epoch": 2.046230220291654, "percentage": 10.23, "elapsed_time": "0:11:58", "remaining_time": "1:45:05", "throughput": 5606.99, "total_tokens": 4029552} {"current_steps": 6600, "total_steps": 64460, "loss": 0.2293, "lr": 9.999828385290279e-06, "epoch": 2.04778156996587, "percentage": 10.24, "elapsed_time": "0:11:59", "remaining_time": "1:45:05", "throughput": 5606.87, "total_tokens": 4032912} {"current_steps": 6605, "total_steps": 64460, "loss": 0.2253, "lr": 9.999816985433573e-06, "epoch": 2.049332919640087, "percentage": 10.25, "elapsed_time": "0:11:59", "remaining_time": "1:45:04", "throughput": 5607.01, "total_tokens": 4035792} {"current_steps": 6610, "total_steps": 64460, "loss": 0.2277, "lr": 9.999805219031076e-06, "epoch": 2.0508842693143032, "percentage": 10.25, "elapsed_time": "0:12:00", "remaining_time": "1:45:04", "throughput": 5606.13, "total_tokens": 4038160} {"current_steps": 6615, "total_steps": 64460, "loss": 0.2303, "lr": 9.99979308608365e-06, "epoch": 2.05243561898852, "percentage": 10.26, "elapsed_time": "0:12:00", "remaining_time": "1:45:03", "throughput": 5606.76, "total_tokens": 4041872} {"current_steps": 6620, "total_steps": 64460, "loss": 0.2409, "lr": 9.999780586592182e-06, "epoch": 2.053986968662737, "percentage": 10.27, "elapsed_time": "0:12:01", "remaining_time": "1:45:04", "throughput": 5607.8, "total_tokens": 4046224} {"current_steps": 6625, "total_steps": 64460, "loss": 0.2536, "lr": 9.999767720557593e-06, "epoch": 2.055538318336953, "percentage": 10.28, "elapsed_time": "0:12:02", "remaining_time": "1:45:03", "throughput": 5608.06, "total_tokens": 4049584} {"current_steps": 6630, "total_steps": 64460, "loss": 0.2225, "lr": 9.999754487980824e-06, "epoch": 2.05708966801117, "percentage": 10.29, "elapsed_time": "0:12:02", "remaining_time": "1:45:02", "throughput": 5607.91, "total_tokens": 4052304} {"current_steps": 6635, "total_steps": 64460, "loss": 0.234, "lr": 9.999740888862844e-06, "epoch": 2.058641017685386, "percentage": 10.29, "elapsed_time": "0:12:03", "remaining_time": "1:45:01", "throughput": 5608.09, "total_tokens": 4055152} {"current_steps": 6640, "total_steps": 64460, "loss": 0.2337, "lr": 9.999726923204651e-06, "epoch": 2.060192367359603, "percentage": 10.3, "elapsed_time": "0:12:03", "remaining_time": "1:45:01", "throughput": 5608.3, "total_tokens": 4058512} {"current_steps": 6645, "total_steps": 64460, "loss": 0.2335, "lr": 9.99971259100727e-06, "epoch": 2.0617437170338193, "percentage": 10.31, "elapsed_time": "0:12:04", "remaining_time": "1:45:00", "throughput": 5607.66, "total_tokens": 4060656} {"current_steps": 6650, "total_steps": 64460, "loss": 0.2296, "lr": 9.99969789227175e-06, "epoch": 2.063295066708036, "percentage": 10.32, "elapsed_time": "0:12:04", "remaining_time": "1:45:00", "throughput": 5608.66, "total_tokens": 4065232} {"current_steps": 6655, "total_steps": 64460, "loss": 0.2254, "lr": 9.999682826999169e-06, "epoch": 2.0648464163822524, "percentage": 10.32, "elapsed_time": "0:12:05", "remaining_time": "1:45:00", "throughput": 5608.4, "total_tokens": 4068048} {"current_steps": 6660, "total_steps": 64460, "loss": 0.2349, "lr": 9.999667395190633e-06, "epoch": 2.066397766056469, "percentage": 10.33, "elapsed_time": "0:12:05", "remaining_time": "1:44:59", "throughput": 5608.13, "total_tokens": 4070544} {"current_steps": 6665, "total_steps": 64460, "loss": 0.2327, "lr": 9.999651596847271e-06, "epoch": 2.0679491157306855, "percentage": 10.34, "elapsed_time": "0:12:06", "remaining_time": "1:44:58", "throughput": 5608.18, "total_tokens": 4073296} {"current_steps": 6670, "total_steps": 64460, "loss": 0.2284, "lr": 9.999635431970243e-06, "epoch": 2.0695004654049023, "percentage": 10.35, "elapsed_time": "0:12:06", "remaining_time": "1:44:57", "throughput": 5608.39, "total_tokens": 4076368} {"current_steps": 6675, "total_steps": 64460, "loss": 0.2336, "lr": 9.999618900560731e-06, "epoch": 2.0710518150791186, "percentage": 10.36, "elapsed_time": "0:12:07", "remaining_time": "1:44:56", "throughput": 5607.71, "total_tokens": 4078992} {"current_steps": 6680, "total_steps": 64460, "loss": 0.2295, "lr": 9.999602002619951e-06, "epoch": 2.0726031647533354, "percentage": 10.36, "elapsed_time": "0:12:07", "remaining_time": "1:44:56", "throughput": 5608.18, "total_tokens": 4082256} {"current_steps": 6685, "total_steps": 64460, "loss": 0.2317, "lr": 9.99958473814914e-06, "epoch": 2.074154514427552, "percentage": 10.37, "elapsed_time": "0:12:08", "remaining_time": "1:44:55", "throughput": 5608.11, "total_tokens": 4084912} {"current_steps": 6690, "total_steps": 64460, "loss": 0.2342, "lr": 9.999567107149564e-06, "epoch": 2.0757058641017685, "percentage": 10.38, "elapsed_time": "0:12:08", "remaining_time": "1:44:54", "throughput": 5608.86, "total_tokens": 4088656} {"current_steps": 6695, "total_steps": 64460, "loss": 0.2346, "lr": 9.999549109622515e-06, "epoch": 2.0772572137759853, "percentage": 10.39, "elapsed_time": "0:12:09", "remaining_time": "1:44:53", "throughput": 5609.05, "total_tokens": 4091536} {"current_steps": 6700, "total_steps": 64460, "loss": 0.2369, "lr": 9.999530745569312e-06, "epoch": 2.0788085634502016, "percentage": 10.39, "elapsed_time": "0:12:10", "remaining_time": "1:44:54", "throughput": 5609.56, "total_tokens": 4095504} {"current_steps": 6705, "total_steps": 64460, "loss": 0.2213, "lr": 9.999512014991303e-06, "epoch": 2.0803599131244184, "percentage": 10.4, "elapsed_time": "0:12:10", "remaining_time": "1:44:53", "throughput": 5609.63, "total_tokens": 4098448} {"current_steps": 6710, "total_steps": 64460, "loss": 0.2376, "lr": 9.99949291788986e-06, "epoch": 2.0819112627986347, "percentage": 10.41, "elapsed_time": "0:12:11", "remaining_time": "1:44:52", "throughput": 5610.1, "total_tokens": 4101488} {"current_steps": 6715, "total_steps": 64460, "loss": 0.2184, "lr": 9.999473454266384e-06, "epoch": 2.0834626124728515, "percentage": 10.42, "elapsed_time": "0:12:11", "remaining_time": "1:44:51", "throughput": 5610.61, "total_tokens": 4104656} {"current_steps": 6720, "total_steps": 64460, "loss": 0.2369, "lr": 9.9994536241223e-06, "epoch": 2.085013962147068, "percentage": 10.43, "elapsed_time": "0:12:12", "remaining_time": "1:44:50", "throughput": 5610.02, "total_tokens": 4106992} {"current_steps": 6725, "total_steps": 64460, "loss": 0.2388, "lr": 9.999433427459063e-06, "epoch": 2.0865653118212846, "percentage": 10.43, "elapsed_time": "0:12:12", "remaining_time": "1:44:49", "throughput": 5609.73, "total_tokens": 4109712} {"current_steps": 6730, "total_steps": 64460, "loss": 0.2329, "lr": 9.999412864278154e-06, "epoch": 2.088116661495501, "percentage": 10.44, "elapsed_time": "0:12:13", "remaining_time": "1:44:48", "throughput": 5610.3, "total_tokens": 4113168} {"current_steps": 6735, "total_steps": 64460, "loss": 0.2386, "lr": 9.99939193458108e-06, "epoch": 2.0896680111697177, "percentage": 10.45, "elapsed_time": "0:12:13", "remaining_time": "1:44:49", "throughput": 5611.43, "total_tokens": 4117904} {"current_steps": 6740, "total_steps": 64460, "loss": 0.2283, "lr": 9.999370638369377e-06, "epoch": 2.091219360843934, "percentage": 10.46, "elapsed_time": "0:12:14", "remaining_time": "1:44:50", "throughput": 5612.2, "total_tokens": 4122320} {"current_steps": 6745, "total_steps": 64460, "loss": 0.2293, "lr": 9.999348975644603e-06, "epoch": 2.092770710518151, "percentage": 10.46, "elapsed_time": "0:12:15", "remaining_time": "1:44:49", "throughput": 5612.01, "total_tokens": 4125008} {"current_steps": 6750, "total_steps": 64460, "loss": 0.2337, "lr": 9.999326946408347e-06, "epoch": 2.0943220601923676, "percentage": 10.47, "elapsed_time": "0:12:15", "remaining_time": "1:44:48", "throughput": 5611.6, "total_tokens": 4127408} {"current_steps": 6755, "total_steps": 64460, "loss": 0.2314, "lr": 9.999304550662228e-06, "epoch": 2.095873409866584, "percentage": 10.48, "elapsed_time": "0:12:16", "remaining_time": "1:44:47", "throughput": 5611.25, "total_tokens": 4129936} {"current_steps": 6760, "total_steps": 64460, "loss": 0.2289, "lr": 9.999281788407882e-06, "epoch": 2.0974247595408007, "percentage": 10.49, "elapsed_time": "0:12:16", "remaining_time": "1:44:46", "throughput": 5611.37, "total_tokens": 4132816} {"current_steps": 6765, "total_steps": 64460, "loss": 0.2295, "lr": 9.999258659646982e-06, "epoch": 2.098976109215017, "percentage": 10.49, "elapsed_time": "0:12:17", "remaining_time": "1:44:45", "throughput": 5611.35, "total_tokens": 4135728} {"current_steps": 6770, "total_steps": 64460, "loss": 0.2298, "lr": 9.999235164381222e-06, "epoch": 2.1005274588892338, "percentage": 10.5, "elapsed_time": "0:12:17", "remaining_time": "1:44:46", "throughput": 5612.54, "total_tokens": 4140496} {"current_steps": 6775, "total_steps": 64460, "loss": 0.2303, "lr": 9.999211302612323e-06, "epoch": 2.10207880856345, "percentage": 10.51, "elapsed_time": "0:12:18", "remaining_time": "1:44:45", "throughput": 5613.12, "total_tokens": 4143984} {"current_steps": 6780, "total_steps": 64460, "loss": 0.235, "lr": 9.999187074342039e-06, "epoch": 2.103630158237667, "percentage": 10.52, "elapsed_time": "0:12:18", "remaining_time": "1:44:45", "throughput": 5613.38, "total_tokens": 4147248} {"current_steps": 6785, "total_steps": 64460, "loss": 0.2288, "lr": 9.999162479572142e-06, "epoch": 2.105181507911883, "percentage": 10.53, "elapsed_time": "0:12:19", "remaining_time": "1:44:45", "throughput": 5614.0, "total_tokens": 4150928} {"current_steps": 6790, "total_steps": 64460, "loss": 0.2249, "lr": 9.999137518304436e-06, "epoch": 2.1067328575861, "percentage": 10.53, "elapsed_time": "0:12:19", "remaining_time": "1:44:44", "throughput": 5613.92, "total_tokens": 4153648} {"current_steps": 6795, "total_steps": 64460, "loss": 0.242, "lr": 9.999112190540751e-06, "epoch": 2.1082842072603163, "percentage": 10.54, "elapsed_time": "0:12:20", "remaining_time": "1:44:44", "throughput": 5614.87, "total_tokens": 4158032} {"current_steps": 6800, "total_steps": 64460, "loss": 0.231, "lr": 9.999086496282945e-06, "epoch": 2.109835556934533, "percentage": 10.55, "elapsed_time": "0:12:21", "remaining_time": "1:44:43", "throughput": 5615.03, "total_tokens": 4160976} {"current_steps": 6805, "total_steps": 64460, "loss": 0.2283, "lr": 9.9990604355329e-06, "epoch": 2.1113869066087494, "percentage": 10.56, "elapsed_time": "0:12:21", "remaining_time": "1:44:42", "throughput": 5615.27, "total_tokens": 4164016} {"current_steps": 6810, "total_steps": 64460, "loss": 0.2332, "lr": 9.999034008292527e-06, "epoch": 2.112938256282966, "percentage": 10.56, "elapsed_time": "0:12:22", "remaining_time": "1:44:41", "throughput": 5615.12, "total_tokens": 4166704} {"current_steps": 6815, "total_steps": 64460, "loss": 0.2176, "lr": 9.999007214563765e-06, "epoch": 2.114489605957183, "percentage": 10.57, "elapsed_time": "0:12:22", "remaining_time": "1:44:41", "throughput": 5615.77, "total_tokens": 4170640} {"current_steps": 6820, "total_steps": 64460, "loss": 0.2306, "lr": 9.998980054348575e-06, "epoch": 2.1160409556313993, "percentage": 10.58, "elapsed_time": "0:12:23", "remaining_time": "1:44:40", "throughput": 5615.44, "total_tokens": 4173104} {"current_steps": 6825, "total_steps": 64460, "loss": 0.2326, "lr": 9.998952527648953e-06, "epoch": 2.117592305305616, "percentage": 10.59, "elapsed_time": "0:12:23", "remaining_time": "1:44:40", "throughput": 5615.52, "total_tokens": 4176304} {"current_steps": 6830, "total_steps": 64460, "loss": 0.2214, "lr": 9.998924634466913e-06, "epoch": 2.1191436549798324, "percentage": 10.6, "elapsed_time": "0:12:24", "remaining_time": "1:44:40", "throughput": 5615.88, "total_tokens": 4179824} {"current_steps": 6835, "total_steps": 64460, "loss": 0.227, "lr": 9.9988963748045e-06, "epoch": 2.120695004654049, "percentage": 10.6, "elapsed_time": "0:12:24", "remaining_time": "1:44:39", "throughput": 5616.47, "total_tokens": 4183440} {"current_steps": 6840, "total_steps": 64460, "loss": 0.2365, "lr": 9.998867748663789e-06, "epoch": 2.1222463543282655, "percentage": 10.61, "elapsed_time": "0:12:25", "remaining_time": "1:44:39", "throughput": 5615.64, "total_tokens": 4185808} {"current_steps": 6845, "total_steps": 64460, "loss": 0.2616, "lr": 9.998838756046876e-06, "epoch": 2.1237977040024822, "percentage": 10.62, "elapsed_time": "0:12:26", "remaining_time": "1:44:39", "throughput": 5616.54, "total_tokens": 4190096} {"current_steps": 6850, "total_steps": 64460, "loss": 0.2393, "lr": 9.998809396955887e-06, "epoch": 2.1253490536766986, "percentage": 10.63, "elapsed_time": "0:12:26", "remaining_time": "1:44:38", "throughput": 5616.35, "total_tokens": 4192592} {"current_steps": 6855, "total_steps": 64460, "loss": 0.2301, "lr": 9.998779671392974e-06, "epoch": 2.1269004033509153, "percentage": 10.63, "elapsed_time": "0:12:26", "remaining_time": "1:44:37", "throughput": 5616.46, "total_tokens": 4195472} {"current_steps": 6860, "total_steps": 64460, "loss": 0.2281, "lr": 9.998749579360316e-06, "epoch": 2.1284517530251317, "percentage": 10.64, "elapsed_time": "0:12:27", "remaining_time": "1:44:36", "throughput": 5616.38, "total_tokens": 4198224} {"current_steps": 6865, "total_steps": 64460, "loss": 0.235, "lr": 9.998719120860121e-06, "epoch": 2.1300031026993484, "percentage": 10.65, "elapsed_time": "0:12:27", "remaining_time": "1:44:35", "throughput": 5616.32, "total_tokens": 4200848} {"current_steps": 6870, "total_steps": 64460, "loss": 0.2343, "lr": 9.99868829589462e-06, "epoch": 2.131554452373565, "percentage": 10.66, "elapsed_time": "0:12:28", "remaining_time": "1:44:34", "throughput": 5615.61, "total_tokens": 4203184} {"current_steps": 6875, "total_steps": 64460, "loss": 0.2256, "lr": 9.998657104466075e-06, "epoch": 2.1331058020477816, "percentage": 10.67, "elapsed_time": "0:12:29", "remaining_time": "1:44:33", "throughput": 5616.01, "total_tokens": 4206448} {"current_steps": 6880, "total_steps": 64460, "loss": 0.2261, "lr": 9.998625546576769e-06, "epoch": 2.1346571517219983, "percentage": 10.67, "elapsed_time": "0:12:29", "remaining_time": "1:44:32", "throughput": 5615.99, "total_tokens": 4209264} {"current_steps": 6885, "total_steps": 64460, "loss": 0.2255, "lr": 9.998593622229018e-06, "epoch": 2.1362085013962147, "percentage": 10.68, "elapsed_time": "0:12:29", "remaining_time": "1:44:31", "throughput": 5615.94, "total_tokens": 4211888} {"current_steps": 6890, "total_steps": 64460, "loss": 0.2455, "lr": 9.998561331425164e-06, "epoch": 2.1377598510704314, "percentage": 10.69, "elapsed_time": "0:12:30", "remaining_time": "1:44:30", "throughput": 5616.54, "total_tokens": 4215216} {"current_steps": 6895, "total_steps": 64460, "loss": 0.2258, "lr": 9.99852867416757e-06, "epoch": 2.1393112007446478, "percentage": 10.7, "elapsed_time": "0:12:31", "remaining_time": "1:44:30", "throughput": 5616.62, "total_tokens": 4218320} {"current_steps": 6900, "total_steps": 64460, "loss": 0.233, "lr": 9.998495650458637e-06, "epoch": 2.1408625504188645, "percentage": 10.7, "elapsed_time": "0:12:31", "remaining_time": "1:44:29", "throughput": 5616.43, "total_tokens": 4221008} {"current_steps": 6905, "total_steps": 64460, "loss": 0.2277, "lr": 9.998462260300779e-06, "epoch": 2.142413900093081, "percentage": 10.71, "elapsed_time": "0:12:32", "remaining_time": "1:44:32", "throughput": 5617.8, "total_tokens": 4227728} {"current_steps": 6910, "total_steps": 64460, "loss": 0.2185, "lr": 9.998428503696447e-06, "epoch": 2.1439652497672976, "percentage": 10.72, "elapsed_time": "0:12:33", "remaining_time": "1:44:32", "throughput": 5618.09, "total_tokens": 4231056} {"current_steps": 6915, "total_steps": 64460, "loss": 0.239, "lr": 9.998394380648115e-06, "epoch": 2.145516599441514, "percentage": 10.73, "elapsed_time": "0:12:33", "remaining_time": "1:44:31", "throughput": 5618.09, "total_tokens": 4233744} {"current_steps": 6920, "total_steps": 64460, "loss": 0.2432, "lr": 9.998359891158287e-06, "epoch": 2.1470679491157307, "percentage": 10.74, "elapsed_time": "0:12:34", "remaining_time": "1:44:31", "throughput": 5619.02, "total_tokens": 4237776} {"current_steps": 6925, "total_steps": 64460, "loss": 0.2293, "lr": 9.998325035229488e-06, "epoch": 2.148619298789947, "percentage": 10.74, "elapsed_time": "0:12:34", "remaining_time": "1:44:31", "throughput": 5619.33, "total_tokens": 4241456} {"current_steps": 6930, "total_steps": 64460, "loss": 0.2307, "lr": 9.998289812864276e-06, "epoch": 2.150170648464164, "percentage": 10.75, "elapsed_time": "0:12:35", "remaining_time": "1:44:30", "throughput": 5619.4, "total_tokens": 4244336} {"current_steps": 6935, "total_steps": 64460, "loss": 0.2304, "lr": 9.998254224065229e-06, "epoch": 2.15172199813838, "percentage": 10.76, "elapsed_time": "0:12:35", "remaining_time": "1:44:29", "throughput": 5619.0, "total_tokens": 4246736} {"current_steps": 6940, "total_steps": 64460, "loss": 0.2292, "lr": 9.998218268834962e-06, "epoch": 2.153273347812597, "percentage": 10.77, "elapsed_time": "0:12:36", "remaining_time": "1:44:28", "throughput": 5619.61, "total_tokens": 4250320} {"current_steps": 6945, "total_steps": 64460, "loss": 0.2272, "lr": 9.998181947176106e-06, "epoch": 2.1548246974868137, "percentage": 10.77, "elapsed_time": "0:12:36", "remaining_time": "1:44:27", "throughput": 5619.01, "total_tokens": 4252560} {"current_steps": 6950, "total_steps": 64460, "loss": 0.2333, "lr": 9.998145259091329e-06, "epoch": 2.15637604716103, "percentage": 10.78, "elapsed_time": "0:12:37", "remaining_time": "1:44:26", "throughput": 5619.07, "total_tokens": 4255344} {"current_steps": 6955, "total_steps": 64460, "loss": 0.2321, "lr": 9.998108204583316e-06, "epoch": 2.157927396835247, "percentage": 10.79, "elapsed_time": "0:12:37", "remaining_time": "1:44:25", "throughput": 5618.55, "total_tokens": 4257680} {"current_steps": 6960, "total_steps": 64460, "loss": 0.2299, "lr": 9.998070783654786e-06, "epoch": 2.159478746509463, "percentage": 10.8, "elapsed_time": "0:12:38", "remaining_time": "1:44:25", "throughput": 5619.0, "total_tokens": 4261232} {"current_steps": 6965, "total_steps": 64460, "loss": 0.2372, "lr": 9.99803299630848e-06, "epoch": 2.16103009618368, "percentage": 10.81, "elapsed_time": "0:12:38", "remaining_time": "1:44:24", "throughput": 5618.09, "total_tokens": 4263472} {"current_steps": 6970, "total_steps": 64460, "loss": 0.2394, "lr": 9.99799484254717e-06, "epoch": 2.1625814458578962, "percentage": 10.81, "elapsed_time": "0:12:39", "remaining_time": "1:44:23", "throughput": 5617.88, "total_tokens": 4265936} {"current_steps": 6975, "total_steps": 64460, "loss": 0.2284, "lr": 9.997956322373655e-06, "epoch": 2.164132795532113, "percentage": 10.82, "elapsed_time": "0:12:39", "remaining_time": "1:44:22", "throughput": 5617.6, "total_tokens": 4268496} {"current_steps": 6980, "total_steps": 64460, "loss": 0.2306, "lr": 9.997917435790753e-06, "epoch": 2.1656841452063293, "percentage": 10.83, "elapsed_time": "0:12:40", "remaining_time": "1:44:21", "throughput": 5617.4, "total_tokens": 4271056} {"current_steps": 6985, "total_steps": 64460, "loss": 0.2335, "lr": 9.997878182801322e-06, "epoch": 2.167235494880546, "percentage": 10.84, "elapsed_time": "0:12:40", "remaining_time": "1:44:20", "throughput": 5617.22, "total_tokens": 4273616} {"current_steps": 6990, "total_steps": 64460, "loss": 0.2294, "lr": 9.997838563408236e-06, "epoch": 2.1687868445547624, "percentage": 10.84, "elapsed_time": "0:12:41", "remaining_time": "1:44:19", "throughput": 5617.51, "total_tokens": 4276624} {"current_steps": 6995, "total_steps": 64460, "loss": 0.2374, "lr": 9.9977985776144e-06, "epoch": 2.1703381942289792, "percentage": 10.85, "elapsed_time": "0:12:41", "remaining_time": "1:44:18", "throughput": 5617.35, "total_tokens": 4279664} {"current_steps": 7000, "total_steps": 64460, "loss": 0.2329, "lr": 9.997758225422745e-06, "epoch": 2.1718895439031956, "percentage": 10.86, "elapsed_time": "0:12:42", "remaining_time": "1:44:17", "throughput": 5617.29, "total_tokens": 4282320} {"current_steps": 7005, "total_steps": 64460, "loss": 0.2269, "lr": 9.997717506836229e-06, "epoch": 2.1734408935774123, "percentage": 10.87, "elapsed_time": "0:12:42", "remaining_time": "1:44:16", "throughput": 5617.05, "total_tokens": 4284976} {"current_steps": 7010, "total_steps": 64460, "loss": 0.2295, "lr": 9.99767642185784e-06, "epoch": 2.174992243251629, "percentage": 10.87, "elapsed_time": "0:12:43", "remaining_time": "1:44:15", "throughput": 5617.16, "total_tokens": 4287728} {"current_steps": 7015, "total_steps": 64460, "loss": 0.2211, "lr": 9.997634970490586e-06, "epoch": 2.1765435929258454, "percentage": 10.88, "elapsed_time": "0:12:43", "remaining_time": "1:44:14", "throughput": 5616.8, "total_tokens": 4290096} {"current_steps": 7020, "total_steps": 64460, "loss": 0.2352, "lr": 9.997593152737508e-06, "epoch": 2.178094942600062, "percentage": 10.89, "elapsed_time": "0:12:44", "remaining_time": "1:44:15", "throughput": 5617.44, "total_tokens": 4294864} {"current_steps": 7025, "total_steps": 64460, "loss": 0.2393, "lr": 9.997550968601673e-06, "epoch": 2.1796462922742785, "percentage": 10.9, "elapsed_time": "0:12:45", "remaining_time": "1:44:15", "throughput": 5616.35, "total_tokens": 4297008} {"current_steps": 7030, "total_steps": 64460, "loss": 0.2365, "lr": 9.99750841808617e-06, "epoch": 2.1811976419484953, "percentage": 10.91, "elapsed_time": "0:12:45", "remaining_time": "1:44:14", "throughput": 5615.9, "total_tokens": 4299728} {"current_steps": 7035, "total_steps": 64460, "loss": 0.2348, "lr": 9.997465501194123e-06, "epoch": 2.1827489916227116, "percentage": 10.91, "elapsed_time": "0:12:46", "remaining_time": "1:44:14", "throughput": 5615.84, "total_tokens": 4302672} {"current_steps": 7040, "total_steps": 64460, "loss": 0.2304, "lr": 9.997422217928674e-06, "epoch": 2.1843003412969284, "percentage": 10.92, "elapsed_time": "0:12:46", "remaining_time": "1:44:13", "throughput": 5615.46, "total_tokens": 4305104} {"current_steps": 7045, "total_steps": 64460, "loss": 0.2303, "lr": 9.997378568292998e-06, "epoch": 2.1858516909711447, "percentage": 10.93, "elapsed_time": "0:12:47", "remaining_time": "1:44:12", "throughput": 5615.2, "total_tokens": 4307728} {"current_steps": 7050, "total_steps": 64460, "loss": 0.2357, "lr": 9.997334552290296e-06, "epoch": 2.1874030406453615, "percentage": 10.94, "elapsed_time": "0:12:47", "remaining_time": "1:44:11", "throughput": 5615.67, "total_tokens": 4311152} {"current_steps": 7055, "total_steps": 64460, "loss": 0.232, "lr": 9.997290169923794e-06, "epoch": 2.188954390319578, "percentage": 10.94, "elapsed_time": "0:12:48", "remaining_time": "1:44:10", "throughput": 5615.07, "total_tokens": 4313488} {"current_steps": 7060, "total_steps": 64460, "loss": 0.2305, "lr": 9.997245421196746e-06, "epoch": 2.1905057399937946, "percentage": 10.95, "elapsed_time": "0:12:48", "remaining_time": "1:44:09", "throughput": 5615.41, "total_tokens": 4316592} {"current_steps": 7065, "total_steps": 64460, "loss": 0.2368, "lr": 9.997200306112433e-06, "epoch": 2.192057089668011, "percentage": 10.96, "elapsed_time": "0:12:49", "remaining_time": "1:44:08", "throughput": 5615.74, "total_tokens": 4319536} {"current_steps": 7070, "total_steps": 64460, "loss": 0.2321, "lr": 9.99715482467416e-06, "epoch": 2.1936084393422277, "percentage": 10.97, "elapsed_time": "0:12:49", "remaining_time": "1:44:09", "throughput": 5615.43, "total_tokens": 4322928} {"current_steps": 7075, "total_steps": 64460, "loss": 0.2264, "lr": 9.997108976885266e-06, "epoch": 2.1951597890164445, "percentage": 10.98, "elapsed_time": "0:12:50", "remaining_time": "1:44:08", "throughput": 5615.72, "total_tokens": 4326384} {"current_steps": 7080, "total_steps": 64460, "loss": 0.2342, "lr": 9.997062762749107e-06, "epoch": 2.196711138690661, "percentage": 10.98, "elapsed_time": "0:12:50", "remaining_time": "1:44:07", "throughput": 5615.63, "total_tokens": 4329040} {"current_steps": 7085, "total_steps": 64460, "loss": 0.228, "lr": 9.997016182269074e-06, "epoch": 2.1982624883648776, "percentage": 10.99, "elapsed_time": "0:12:51", "remaining_time": "1:44:07", "throughput": 5615.85, "total_tokens": 4332720} {"current_steps": 7090, "total_steps": 64460, "loss": 0.2318, "lr": 9.99696923544858e-06, "epoch": 2.199813838039094, "percentage": 11.0, "elapsed_time": "0:12:52", "remaining_time": "1:44:06", "throughput": 5616.09, "total_tokens": 4335632} {"current_steps": 7095, "total_steps": 64460, "loss": 0.2307, "lr": 9.996921922291069e-06, "epoch": 2.2013651877133107, "percentage": 11.01, "elapsed_time": "0:12:52", "remaining_time": "1:44:05", "throughput": 5615.81, "total_tokens": 4338192} {"current_steps": 7100, "total_steps": 64460, "loss": 0.2282, "lr": 9.99687424280001e-06, "epoch": 2.202916537387527, "percentage": 11.01, "elapsed_time": "0:12:53", "remaining_time": "1:44:05", "throughput": 5615.3, "total_tokens": 4340976} {"current_steps": 7105, "total_steps": 64460, "loss": 0.2377, "lr": 9.996826196978898e-06, "epoch": 2.204467887061744, "percentage": 11.02, "elapsed_time": "0:12:53", "remaining_time": "1:44:04", "throughput": 5614.68, "total_tokens": 4343344} {"current_steps": 7110, "total_steps": 64460, "loss": 0.2293, "lr": 9.996777784831251e-06, "epoch": 2.20601923673596, "percentage": 11.03, "elapsed_time": "0:12:54", "remaining_time": "1:44:03", "throughput": 5615.23, "total_tokens": 4346736} {"current_steps": 7115, "total_steps": 64460, "loss": 0.2295, "lr": 9.996729006360624e-06, "epoch": 2.207570586410177, "percentage": 11.04, "elapsed_time": "0:12:54", "remaining_time": "1:44:04", "throughput": 5615.08, "total_tokens": 4350160} {"current_steps": 7120, "total_steps": 64460, "loss": 0.2321, "lr": 9.99667986157059e-06, "epoch": 2.2091219360843932, "percentage": 11.05, "elapsed_time": "0:12:55", "remaining_time": "1:44:03", "throughput": 5614.26, "total_tokens": 4352560} {"current_steps": 7125, "total_steps": 64460, "loss": 0.2315, "lr": 9.996630350464753e-06, "epoch": 2.21067328575861, "percentage": 11.05, "elapsed_time": "0:12:55", "remaining_time": "1:44:02", "throughput": 5614.87, "total_tokens": 4355952} {"current_steps": 7130, "total_steps": 64460, "loss": 0.2305, "lr": 9.996580473046743e-06, "epoch": 2.2122246354328263, "percentage": 11.06, "elapsed_time": "0:12:56", "remaining_time": "1:44:01", "throughput": 5614.96, "total_tokens": 4358768} {"current_steps": 7135, "total_steps": 64460, "loss": 0.2305, "lr": 9.996530229320213e-06, "epoch": 2.213775985107043, "percentage": 11.07, "elapsed_time": "0:12:56", "remaining_time": "1:44:00", "throughput": 5614.91, "total_tokens": 4361360} {"current_steps": 7140, "total_steps": 64460, "loss": 0.2238, "lr": 9.996479619288853e-06, "epoch": 2.21532733478126, "percentage": 11.08, "elapsed_time": "0:12:57", "remaining_time": "1:43:59", "throughput": 5614.38, "total_tokens": 4363792} {"current_steps": 7145, "total_steps": 64460, "loss": 0.234, "lr": 9.996428642956365e-06, "epoch": 2.216878684455476, "percentage": 11.08, "elapsed_time": "0:12:57", "remaining_time": "1:44:00", "throughput": 5614.25, "total_tokens": 4367312} {"current_steps": 7150, "total_steps": 64460, "loss": 0.2356, "lr": 9.996377300326496e-06, "epoch": 2.218430034129693, "percentage": 11.09, "elapsed_time": "0:12:58", "remaining_time": "1:43:59", "throughput": 5614.61, "total_tokens": 4370704} {"current_steps": 7155, "total_steps": 64460, "loss": 0.2354, "lr": 9.996325591403003e-06, "epoch": 2.2199813838039093, "percentage": 11.1, "elapsed_time": "0:12:59", "remaining_time": "1:43:59", "throughput": 5614.55, "total_tokens": 4373744} {"current_steps": 7160, "total_steps": 64460, "loss": 0.2326, "lr": 9.996273516189678e-06, "epoch": 2.221532733478126, "percentage": 11.11, "elapsed_time": "0:12:59", "remaining_time": "1:43:58", "throughput": 5615.01, "total_tokens": 4377328} {"current_steps": 7165, "total_steps": 64460, "loss": 0.2326, "lr": 9.99622107469034e-06, "epoch": 2.2230840831523424, "percentage": 11.12, "elapsed_time": "0:13:00", "remaining_time": "1:43:58", "throughput": 5615.36, "total_tokens": 4381072} {"current_steps": 7170, "total_steps": 64460, "loss": 0.2275, "lr": 9.996168266908835e-06, "epoch": 2.224635432826559, "percentage": 11.12, "elapsed_time": "0:13:00", "remaining_time": "1:43:58", "throughput": 5615.8, "total_tokens": 4384368} {"current_steps": 7175, "total_steps": 64460, "loss": 0.2279, "lr": 9.996115092849031e-06, "epoch": 2.2261867825007755, "percentage": 11.13, "elapsed_time": "0:13:01", "remaining_time": "1:43:57", "throughput": 5615.89, "total_tokens": 4387184} {"current_steps": 7180, "total_steps": 64460, "loss": 0.2333, "lr": 9.996061552514827e-06, "epoch": 2.2277381321749923, "percentage": 11.14, "elapsed_time": "0:13:01", "remaining_time": "1:43:56", "throughput": 5615.84, "total_tokens": 4389872} {"current_steps": 7185, "total_steps": 64460, "loss": 0.2149, "lr": 9.99600764591015e-06, "epoch": 2.2292894818492086, "percentage": 11.15, "elapsed_time": "0:13:02", "remaining_time": "1:43:55", "throughput": 5616.09, "total_tokens": 4392944} {"current_steps": 7190, "total_steps": 64460, "loss": 0.2225, "lr": 9.995953373038951e-06, "epoch": 2.2308408315234254, "percentage": 11.15, "elapsed_time": "0:13:02", "remaining_time": "1:43:54", "throughput": 5616.46, "total_tokens": 4396112} {"current_steps": 7195, "total_steps": 64460, "loss": 0.2203, "lr": 9.995898733905209e-06, "epoch": 2.232392181197642, "percentage": 11.16, "elapsed_time": "0:13:03", "remaining_time": "1:43:53", "throughput": 5616.68, "total_tokens": 4399184} {"current_steps": 7200, "total_steps": 64460, "loss": 0.229, "lr": 9.995843728512929e-06, "epoch": 2.2339435308718585, "percentage": 11.17, "elapsed_time": "0:13:03", "remaining_time": "1:43:52", "throughput": 5616.4, "total_tokens": 4401552} {"current_steps": 7205, "total_steps": 64460, "loss": 0.2148, "lr": 9.995788356866143e-06, "epoch": 2.2354948805460753, "percentage": 11.18, "elapsed_time": "0:13:04", "remaining_time": "1:43:51", "throughput": 5616.43, "total_tokens": 4404592} {"current_steps": 7210, "total_steps": 64460, "loss": 0.2515, "lr": 9.995732618968914e-06, "epoch": 2.2370462302202916, "percentage": 11.19, "elapsed_time": "0:13:04", "remaining_time": "1:43:51", "throughput": 5617.29, "total_tokens": 4408496} {"current_steps": 7215, "total_steps": 64460, "loss": 0.2467, "lr": 9.995676514825323e-06, "epoch": 2.2385975798945084, "percentage": 11.19, "elapsed_time": "0:13:05", "remaining_time": "1:43:50", "throughput": 5616.83, "total_tokens": 4410736} {"current_steps": 7220, "total_steps": 64460, "loss": 0.2273, "lr": 9.995620044439488e-06, "epoch": 2.2401489295687247, "percentage": 11.2, "elapsed_time": "0:13:05", "remaining_time": "1:43:49", "throughput": 5616.88, "total_tokens": 4413584} {"current_steps": 7225, "total_steps": 64460, "loss": 0.2282, "lr": 9.995563207815546e-06, "epoch": 2.2417002792429415, "percentage": 11.21, "elapsed_time": "0:13:06", "remaining_time": "1:43:48", "throughput": 5616.72, "total_tokens": 4416208} {"current_steps": 7230, "total_steps": 64460, "loss": 0.2382, "lr": 9.995506004957664e-06, "epoch": 2.243251628917158, "percentage": 11.22, "elapsed_time": "0:13:06", "remaining_time": "1:43:47", "throughput": 5616.71, "total_tokens": 4418864} {"current_steps": 7235, "total_steps": 64460, "loss": 0.2209, "lr": 9.995448435870036e-06, "epoch": 2.2448029785913746, "percentage": 11.22, "elapsed_time": "0:13:07", "remaining_time": "1:43:46", "throughput": 5615.86, "total_tokens": 4421200} {"current_steps": 7240, "total_steps": 64460, "loss": 0.2283, "lr": 9.995390500556883e-06, "epoch": 2.246354328265591, "percentage": 11.23, "elapsed_time": "0:13:07", "remaining_time": "1:43:46", "throughput": 5615.62, "total_tokens": 4424048} {"current_steps": 7245, "total_steps": 64460, "loss": 0.233, "lr": 9.995332199022454e-06, "epoch": 2.2479056779398077, "percentage": 11.24, "elapsed_time": "0:13:08", "remaining_time": "1:43:45", "throughput": 5616.23, "total_tokens": 4427472} {"current_steps": 7250, "total_steps": 64460, "loss": 0.2313, "lr": 9.99527353127102e-06, "epoch": 2.249457027614024, "percentage": 11.25, "elapsed_time": "0:13:08", "remaining_time": "1:43:44", "throughput": 5615.47, "total_tokens": 4429552} {"current_steps": 7255, "total_steps": 64460, "loss": 0.2338, "lr": 9.995214497306883e-06, "epoch": 2.2510083772882408, "percentage": 11.26, "elapsed_time": "0:13:09", "remaining_time": "1:43:43", "throughput": 5615.62, "total_tokens": 4432592} {"current_steps": 7260, "total_steps": 64460, "loss": 0.2337, "lr": 9.99515509713437e-06, "epoch": 2.252559726962457, "percentage": 11.26, "elapsed_time": "0:13:09", "remaining_time": "1:43:43", "throughput": 5615.39, "total_tokens": 4435472} {"current_steps": 7265, "total_steps": 64460, "loss": 0.2283, "lr": 9.995095330757838e-06, "epoch": 2.254111076636674, "percentage": 11.27, "elapsed_time": "0:13:10", "remaining_time": "1:43:42", "throughput": 5614.92, "total_tokens": 4437808} {"current_steps": 7270, "total_steps": 64460, "loss": 0.2347, "lr": 9.995035198181667e-06, "epoch": 2.2556624263108906, "percentage": 11.28, "elapsed_time": "0:13:10", "remaining_time": "1:43:41", "throughput": 5614.75, "total_tokens": 4440752} {"current_steps": 7275, "total_steps": 64460, "loss": 0.2281, "lr": 9.994974699410267e-06, "epoch": 2.257213775985107, "percentage": 11.29, "elapsed_time": "0:13:11", "remaining_time": "1:43:41", "throughput": 5614.96, "total_tokens": 4444432} {"current_steps": 7280, "total_steps": 64460, "loss": 0.237, "lr": 9.994913834448071e-06, "epoch": 2.2587651256593237, "percentage": 11.29, "elapsed_time": "0:13:12", "remaining_time": "1:43:40", "throughput": 5614.64, "total_tokens": 4447024} {"current_steps": 7285, "total_steps": 64460, "loss": 0.2303, "lr": 9.994852603299544e-06, "epoch": 2.26031647533354, "percentage": 11.3, "elapsed_time": "0:13:12", "remaining_time": "1:43:40", "throughput": 5614.83, "total_tokens": 4450096} {"current_steps": 7290, "total_steps": 64460, "loss": 0.2236, "lr": 9.994791005969172e-06, "epoch": 2.261867825007757, "percentage": 11.31, "elapsed_time": "0:13:13", "remaining_time": "1:43:39", "throughput": 5615.26, "total_tokens": 4453392} {"current_steps": 7295, "total_steps": 64460, "loss": 0.2306, "lr": 9.99472904246147e-06, "epoch": 2.263419174681973, "percentage": 11.32, "elapsed_time": "0:13:13", "remaining_time": "1:43:39", "throughput": 5615.63, "total_tokens": 4456944} {"current_steps": 7300, "total_steps": 64460, "loss": 0.2319, "lr": 9.994666712780986e-06, "epoch": 2.26497052435619, "percentage": 11.32, "elapsed_time": "0:13:14", "remaining_time": "1:43:38", "throughput": 5615.87, "total_tokens": 4460112} {"current_steps": 7305, "total_steps": 64460, "loss": 0.2311, "lr": 9.994604016932285e-06, "epoch": 2.2665218740304063, "percentage": 11.33, "elapsed_time": "0:13:14", "remaining_time": "1:43:37", "throughput": 5615.67, "total_tokens": 4462896} {"current_steps": 7310, "total_steps": 64460, "loss": 0.2559, "lr": 9.994540954919964e-06, "epoch": 2.268073223704623, "percentage": 11.34, "elapsed_time": "0:13:15", "remaining_time": "1:43:36", "throughput": 5615.54, "total_tokens": 4465520} {"current_steps": 7315, "total_steps": 64460, "loss": 0.2219, "lr": 9.994477526748649e-06, "epoch": 2.26962457337884, "percentage": 11.35, "elapsed_time": "0:13:15", "remaining_time": "1:43:36", "throughput": 5614.69, "total_tokens": 4467696} {"current_steps": 7320, "total_steps": 64460, "loss": 0.2378, "lr": 9.994413732422985e-06, "epoch": 2.271175923053056, "percentage": 11.36, "elapsed_time": "0:13:16", "remaining_time": "1:43:35", "throughput": 5614.55, "total_tokens": 4470288} {"current_steps": 7325, "total_steps": 64460, "loss": 0.2326, "lr": 9.994349571947655e-06, "epoch": 2.2727272727272725, "percentage": 11.36, "elapsed_time": "0:13:16", "remaining_time": "1:43:34", "throughput": 5614.56, "total_tokens": 4473392} {"current_steps": 7330, "total_steps": 64460, "loss": 0.2298, "lr": 9.994285045327356e-06, "epoch": 2.2742786224014893, "percentage": 11.37, "elapsed_time": "0:13:17", "remaining_time": "1:43:33", "throughput": 5614.44, "total_tokens": 4476048} {"current_steps": 7335, "total_steps": 64460, "loss": 0.232, "lr": 9.994220152566825e-06, "epoch": 2.275829972075706, "percentage": 11.38, "elapsed_time": "0:13:17", "remaining_time": "1:43:33", "throughput": 5614.75, "total_tokens": 4479376} {"current_steps": 7340, "total_steps": 64460, "loss": 0.2328, "lr": 9.994154893670813e-06, "epoch": 2.2773813217499224, "percentage": 11.39, "elapsed_time": "0:13:18", "remaining_time": "1:43:32", "throughput": 5615.0, "total_tokens": 4482352} {"current_steps": 7345, "total_steps": 64460, "loss": 0.2254, "lr": 9.99408926864411e-06, "epoch": 2.278932671424139, "percentage": 11.39, "elapsed_time": "0:13:18", "remaining_time": "1:43:31", "throughput": 5615.29, "total_tokens": 4485584} {"current_steps": 7350, "total_steps": 64460, "loss": 0.228, "lr": 9.994023277491525e-06, "epoch": 2.2804840210983555, "percentage": 11.4, "elapsed_time": "0:13:19", "remaining_time": "1:43:31", "throughput": 5615.0, "total_tokens": 4488432} {"current_steps": 7355, "total_steps": 64460, "loss": 0.2417, "lr": 9.993956920217896e-06, "epoch": 2.2820353707725722, "percentage": 11.41, "elapsed_time": "0:13:19", "remaining_time": "1:43:30", "throughput": 5614.77, "total_tokens": 4491056} {"current_steps": 7360, "total_steps": 64460, "loss": 0.2273, "lr": 9.993890196828084e-06, "epoch": 2.2835867204467886, "percentage": 11.42, "elapsed_time": "0:13:20", "remaining_time": "1:43:29", "throughput": 5615.09, "total_tokens": 4494160} {"current_steps": 7365, "total_steps": 64460, "loss": 0.2467, "lr": 9.993823107326988e-06, "epoch": 2.2851380701210053, "percentage": 11.43, "elapsed_time": "0:13:20", "remaining_time": "1:43:29", "throughput": 5615.33, "total_tokens": 4497680} {"current_steps": 7370, "total_steps": 64460, "loss": 0.2306, "lr": 9.99375565171952e-06, "epoch": 2.2866894197952217, "percentage": 11.43, "elapsed_time": "0:13:21", "remaining_time": "1:43:28", "throughput": 5615.8, "total_tokens": 4501136} {"current_steps": 7375, "total_steps": 64460, "loss": 0.2315, "lr": 9.99368783001063e-06, "epoch": 2.2882407694694384, "percentage": 11.44, "elapsed_time": "0:13:22", "remaining_time": "1:43:27", "throughput": 5615.04, "total_tokens": 4503312} {"current_steps": 7380, "total_steps": 64460, "loss": 0.2263, "lr": 9.993619642205285e-06, "epoch": 2.289792119143655, "percentage": 11.45, "elapsed_time": "0:13:22", "remaining_time": "1:43:26", "throughput": 5614.44, "total_tokens": 4505616} {"current_steps": 7385, "total_steps": 64460, "loss": 0.2353, "lr": 9.99355108830849e-06, "epoch": 2.2913434688178715, "percentage": 11.46, "elapsed_time": "0:13:22", "remaining_time": "1:43:25", "throughput": 5614.49, "total_tokens": 4508336} {"current_steps": 7390, "total_steps": 64460, "loss": 0.235, "lr": 9.993482168325266e-06, "epoch": 2.292894818492088, "percentage": 11.46, "elapsed_time": "0:13:23", "remaining_time": "1:43:24", "throughput": 5614.78, "total_tokens": 4511248} {"current_steps": 7395, "total_steps": 64460, "loss": 0.2341, "lr": 9.993412882260667e-06, "epoch": 2.2944461681663046, "percentage": 11.47, "elapsed_time": "0:13:24", "remaining_time": "1:43:24", "throughput": 5615.13, "total_tokens": 4514800} {"current_steps": 7400, "total_steps": 64460, "loss": 0.2315, "lr": 9.993343230119774e-06, "epoch": 2.2959975178405214, "percentage": 11.48, "elapsed_time": "0:13:24", "remaining_time": "1:43:23", "throughput": 5614.97, "total_tokens": 4517360} {"current_steps": 7405, "total_steps": 64460, "loss": 0.2278, "lr": 9.993273211907693e-06, "epoch": 2.2975488675147377, "percentage": 11.49, "elapsed_time": "0:13:25", "remaining_time": "1:43:23", "throughput": 5614.79, "total_tokens": 4520432} {"current_steps": 7410, "total_steps": 64460, "loss": 0.237, "lr": 9.993202827629555e-06, "epoch": 2.2991002171889545, "percentage": 11.5, "elapsed_time": "0:13:25", "remaining_time": "1:43:22", "throughput": 5614.23, "total_tokens": 4522640} {"current_steps": 7415, "total_steps": 64460, "loss": 0.2248, "lr": 9.993132077290522e-06, "epoch": 2.300651566863171, "percentage": 11.5, "elapsed_time": "0:13:26", "remaining_time": "1:43:21", "throughput": 5613.8, "total_tokens": 4525104} {"current_steps": 7420, "total_steps": 64460, "loss": 0.2322, "lr": 9.99306096089578e-06, "epoch": 2.3022029165373876, "percentage": 11.51, "elapsed_time": "0:13:26", "remaining_time": "1:43:20", "throughput": 5613.56, "total_tokens": 4527536} {"current_steps": 7425, "total_steps": 64460, "loss": 0.2361, "lr": 9.992989478450542e-06, "epoch": 2.303754266211604, "percentage": 11.52, "elapsed_time": "0:13:27", "remaining_time": "1:43:19", "throughput": 5613.37, "total_tokens": 4530352} {"current_steps": 7430, "total_steps": 64460, "loss": 0.2191, "lr": 9.99291762996005e-06, "epoch": 2.3053056158858207, "percentage": 11.53, "elapsed_time": "0:13:27", "remaining_time": "1:43:18", "throughput": 5613.56, "total_tokens": 4533328} {"current_steps": 7435, "total_steps": 64460, "loss": 0.237, "lr": 9.99284541542957e-06, "epoch": 2.306856965560037, "percentage": 11.53, "elapsed_time": "0:13:28", "remaining_time": "1:43:18", "throughput": 5613.87, "total_tokens": 4536816} {"current_steps": 7440, "total_steps": 64460, "loss": 0.2361, "lr": 9.9927728348644e-06, "epoch": 2.308408315234254, "percentage": 11.54, "elapsed_time": "0:13:28", "remaining_time": "1:43:17", "throughput": 5613.46, "total_tokens": 4539344} {"current_steps": 7445, "total_steps": 64460, "loss": 0.2275, "lr": 9.992699888269854e-06, "epoch": 2.3099596649084706, "percentage": 11.55, "elapsed_time": "0:13:29", "remaining_time": "1:43:17", "throughput": 5613.23, "total_tokens": 4542416} {"current_steps": 7450, "total_steps": 64460, "loss": 0.2414, "lr": 9.992626575651285e-06, "epoch": 2.311511014582687, "percentage": 11.56, "elapsed_time": "0:13:29", "remaining_time": "1:43:16", "throughput": 5612.77, "total_tokens": 4544944} {"current_steps": 7455, "total_steps": 64460, "loss": 0.2318, "lr": 9.992552897014068e-06, "epoch": 2.3130623642569033, "percentage": 11.57, "elapsed_time": "0:13:30", "remaining_time": "1:43:16", "throughput": 5612.82, "total_tokens": 4548208} {"current_steps": 7460, "total_steps": 64460, "loss": 0.2323, "lr": 9.992478852363601e-06, "epoch": 2.31461371393112, "percentage": 11.57, "elapsed_time": "0:13:30", "remaining_time": "1:43:15", "throughput": 5612.95, "total_tokens": 4551056} {"current_steps": 7465, "total_steps": 64460, "loss": 0.231, "lr": 9.992404441705317e-06, "epoch": 2.316165063605337, "percentage": 11.58, "elapsed_time": "0:13:31", "remaining_time": "1:43:14", "throughput": 5613.18, "total_tokens": 4554352} {"current_steps": 7470, "total_steps": 64460, "loss": 0.2304, "lr": 9.992329665044666e-06, "epoch": 2.317716413279553, "percentage": 11.59, "elapsed_time": "0:13:31", "remaining_time": "1:43:14", "throughput": 5612.62, "total_tokens": 4556848} {"current_steps": 7475, "total_steps": 64460, "loss": 0.2289, "lr": 9.992254522387133e-06, "epoch": 2.31926776295377, "percentage": 11.6, "elapsed_time": "0:13:32", "remaining_time": "1:43:13", "throughput": 5613.23, "total_tokens": 4560624} {"current_steps": 7480, "total_steps": 64460, "loss": 0.2277, "lr": 9.992179013738227e-06, "epoch": 2.3208191126279862, "percentage": 11.6, "elapsed_time": "0:13:32", "remaining_time": "1:43:12", "throughput": 5613.41, "total_tokens": 4563568} {"current_steps": 7485, "total_steps": 64460, "loss": 0.2447, "lr": 9.992103139103481e-06, "epoch": 2.322370462302203, "percentage": 11.61, "elapsed_time": "0:13:33", "remaining_time": "1:43:12", "throughput": 5613.44, "total_tokens": 4566608} {"current_steps": 7490, "total_steps": 64460, "loss": 0.2353, "lr": 9.992026898488462e-06, "epoch": 2.3239218119764193, "percentage": 11.62, "elapsed_time": "0:13:34", "remaining_time": "1:43:14", "throughput": 5615.03, "total_tokens": 4572720} {"current_steps": 7495, "total_steps": 64460, "loss": 0.2273, "lr": 9.991950291898757e-06, "epoch": 2.325473161650636, "percentage": 11.63, "elapsed_time": "0:13:34", "remaining_time": "1:43:13", "throughput": 5614.61, "total_tokens": 4575024} {"current_steps": 7500, "total_steps": 64460, "loss": 0.2245, "lr": 9.99187331933998e-06, "epoch": 2.3270245113248524, "percentage": 11.64, "elapsed_time": "0:13:35", "remaining_time": "1:43:12", "throughput": 5614.7, "total_tokens": 4577936} {"current_steps": 7505, "total_steps": 64460, "loss": 0.2324, "lr": 9.991795980817777e-06, "epoch": 2.328575860999069, "percentage": 11.64, "elapsed_time": "0:13:35", "remaining_time": "1:43:11", "throughput": 5614.94, "total_tokens": 4581072} {"current_steps": 7510, "total_steps": 64460, "loss": 0.2312, "lr": 9.991718276337818e-06, "epoch": 2.330127210673286, "percentage": 11.65, "elapsed_time": "0:13:36", "remaining_time": "1:43:10", "throughput": 5614.77, "total_tokens": 4583664} {"current_steps": 7515, "total_steps": 64460, "loss": 0.2249, "lr": 9.991640205905799e-06, "epoch": 2.3316785603475023, "percentage": 11.66, "elapsed_time": "0:13:36", "remaining_time": "1:43:09", "throughput": 5614.62, "total_tokens": 4586288} {"current_steps": 7520, "total_steps": 64460, "loss": 0.2385, "lr": 9.99156176952744e-06, "epoch": 2.333229910021719, "percentage": 11.67, "elapsed_time": "0:13:37", "remaining_time": "1:43:08", "throughput": 5614.39, "total_tokens": 4588880} {"current_steps": 7525, "total_steps": 64460, "loss": 0.2325, "lr": 9.991482967208496e-06, "epoch": 2.3347812596959354, "percentage": 11.67, "elapsed_time": "0:13:38", "remaining_time": "1:43:09", "throughput": 5615.2, "total_tokens": 4593488} {"current_steps": 7530, "total_steps": 64460, "loss": 0.2291, "lr": 9.991403798954744e-06, "epoch": 2.336332609370152, "percentage": 11.68, "elapsed_time": "0:13:38", "remaining_time": "1:43:08", "throughput": 5615.66, "total_tokens": 4596816} {"current_steps": 7535, "total_steps": 64460, "loss": 0.2312, "lr": 9.991324264771984e-06, "epoch": 2.3378839590443685, "percentage": 11.69, "elapsed_time": "0:13:39", "remaining_time": "1:43:07", "throughput": 5616.16, "total_tokens": 4600048} {"current_steps": 7540, "total_steps": 64460, "loss": 0.2342, "lr": 9.991244364666051e-06, "epoch": 2.3394353087185853, "percentage": 11.7, "elapsed_time": "0:13:39", "remaining_time": "1:43:07", "throughput": 5616.39, "total_tokens": 4603184} {"current_steps": 7545, "total_steps": 64460, "loss": 0.232, "lr": 9.9911640986428e-06, "epoch": 2.3409866583928016, "percentage": 11.7, "elapsed_time": "0:13:40", "remaining_time": "1:43:06", "throughput": 5616.11, "total_tokens": 4605872} {"current_steps": 7550, "total_steps": 64460, "loss": 0.2305, "lr": 9.991083466708117e-06, "epoch": 2.3425380080670184, "percentage": 11.71, "elapsed_time": "0:13:40", "remaining_time": "1:43:05", "throughput": 5615.92, "total_tokens": 4608304} {"current_steps": 7555, "total_steps": 64460, "loss": 0.2317, "lr": 9.991002468867912e-06, "epoch": 2.3440893577412347, "percentage": 11.72, "elapsed_time": "0:13:41", "remaining_time": "1:43:05", "throughput": 5616.73, "total_tokens": 4612560} {"current_steps": 7560, "total_steps": 64460, "loss": 0.2256, "lr": 9.990921105128124e-06, "epoch": 2.3456407074154515, "percentage": 11.73, "elapsed_time": "0:13:41", "remaining_time": "1:43:04", "throughput": 5616.87, "total_tokens": 4615504} {"current_steps": 7565, "total_steps": 64460, "loss": 0.2361, "lr": 9.99083937549472e-06, "epoch": 2.347192057089668, "percentage": 11.74, "elapsed_time": "0:13:42", "remaining_time": "1:43:03", "throughput": 5616.46, "total_tokens": 4617808} {"current_steps": 7570, "total_steps": 64460, "loss": 0.2357, "lr": 9.990757279973685e-06, "epoch": 2.3487434067638846, "percentage": 11.74, "elapsed_time": "0:13:42", "remaining_time": "1:43:03", "throughput": 5616.59, "total_tokens": 4621392} {"current_steps": 7575, "total_steps": 64460, "loss": 0.2222, "lr": 9.990674818571044e-06, "epoch": 2.3502947564381014, "percentage": 11.75, "elapsed_time": "0:13:43", "remaining_time": "1:43:03", "throughput": 5616.62, "total_tokens": 4624528} {"current_steps": 7580, "total_steps": 64460, "loss": 0.2232, "lr": 9.990591991292839e-06, "epoch": 2.3518461061123177, "percentage": 11.76, "elapsed_time": "0:13:43", "remaining_time": "1:43:03", "throughput": 5617.5, "total_tokens": 4628688} {"current_steps": 7585, "total_steps": 64460, "loss": 0.2268, "lr": 9.990508798145147e-06, "epoch": 2.3533974557865345, "percentage": 11.77, "elapsed_time": "0:13:44", "remaining_time": "1:43:02", "throughput": 5617.0, "total_tokens": 4630928} {"current_steps": 7590, "total_steps": 64460, "loss": 0.2419, "lr": 9.99042523913406e-06, "epoch": 2.354948805460751, "percentage": 11.77, "elapsed_time": "0:13:44", "remaining_time": "1:43:01", "throughput": 5616.79, "total_tokens": 4633488} {"current_steps": 7595, "total_steps": 64460, "loss": 0.2356, "lr": 9.99034131426571e-06, "epoch": 2.3565001551349676, "percentage": 11.78, "elapsed_time": "0:13:45", "remaining_time": "1:43:00", "throughput": 5617.25, "total_tokens": 4636880} {"current_steps": 7600, "total_steps": 64460, "loss": 0.2408, "lr": 9.990257023546246e-06, "epoch": 2.358051504809184, "percentage": 11.79, "elapsed_time": "0:13:46", "remaining_time": "1:43:00", "throughput": 5617.92, "total_tokens": 4640752} {"current_steps": 7605, "total_steps": 64460, "loss": 0.2342, "lr": 9.990172366981849e-06, "epoch": 2.3596028544834007, "percentage": 11.8, "elapsed_time": "0:13:46", "remaining_time": "1:42:59", "throughput": 5618.23, "total_tokens": 4644240} {"current_steps": 7610, "total_steps": 64460, "loss": 0.2346, "lr": 9.990087344578724e-06, "epoch": 2.361154204157617, "percentage": 11.81, "elapsed_time": "0:13:47", "remaining_time": "1:42:59", "throughput": 5618.25, "total_tokens": 4647088} {"current_steps": 7615, "total_steps": 64460, "loss": 0.2312, "lr": 9.990001956343107e-06, "epoch": 2.362705553831834, "percentage": 11.81, "elapsed_time": "0:13:47", "remaining_time": "1:42:58", "throughput": 5617.53, "total_tokens": 4649360} {"current_steps": 7620, "total_steps": 64460, "loss": 0.225, "lr": 9.989916202281256e-06, "epoch": 2.36425690350605, "percentage": 11.82, "elapsed_time": "0:13:48", "remaining_time": "1:42:58", "throughput": 5618.02, "total_tokens": 4653136} {"current_steps": 7625, "total_steps": 64460, "loss": 0.2334, "lr": 9.989830082399456e-06, "epoch": 2.365808253180267, "percentage": 11.83, "elapsed_time": "0:13:48", "remaining_time": "1:42:57", "throughput": 5617.95, "total_tokens": 4656176} {"current_steps": 7630, "total_steps": 64460, "loss": 0.227, "lr": 9.989743596704025e-06, "epoch": 2.367359602854483, "percentage": 11.84, "elapsed_time": "0:13:49", "remaining_time": "1:42:57", "throughput": 5617.52, "total_tokens": 4659024} {"current_steps": 7635, "total_steps": 64460, "loss": 0.2292, "lr": 9.9896567452013e-06, "epoch": 2.3689109525287, "percentage": 11.84, "elapsed_time": "0:13:49", "remaining_time": "1:42:56", "throughput": 5617.27, "total_tokens": 4661488} {"current_steps": 7640, "total_steps": 64460, "loss": 0.2305, "lr": 9.989569527897647e-06, "epoch": 2.3704623022029168, "percentage": 11.85, "elapsed_time": "0:13:50", "remaining_time": "1:42:55", "throughput": 5617.62, "total_tokens": 4664752} {"current_steps": 7645, "total_steps": 64460, "loss": 0.238, "lr": 9.989481944799465e-06, "epoch": 2.372013651877133, "percentage": 11.86, "elapsed_time": "0:13:50", "remaining_time": "1:42:54", "throughput": 5617.62, "total_tokens": 4667632} {"current_steps": 7650, "total_steps": 64460, "loss": 0.2302, "lr": 9.989393995913171e-06, "epoch": 2.37356500155135, "percentage": 11.87, "elapsed_time": "0:13:51", "remaining_time": "1:42:54", "throughput": 5617.37, "total_tokens": 4670288} {"current_steps": 7655, "total_steps": 64460, "loss": 0.2224, "lr": 9.989305681245214e-06, "epoch": 2.375116351225566, "percentage": 11.88, "elapsed_time": "0:13:51", "remaining_time": "1:42:53", "throughput": 5616.91, "total_tokens": 4672560} {"current_steps": 7660, "total_steps": 64460, "loss": 0.2372, "lr": 9.989217000802068e-06, "epoch": 2.376667700899783, "percentage": 11.88, "elapsed_time": "0:13:52", "remaining_time": "1:42:52", "throughput": 5617.31, "total_tokens": 4676240} {"current_steps": 7665, "total_steps": 64460, "loss": 0.2298, "lr": 9.989127954590236e-06, "epoch": 2.3782190505739993, "percentage": 11.89, "elapsed_time": "0:13:52", "remaining_time": "1:42:52", "throughput": 5617.63, "total_tokens": 4679344} {"current_steps": 7670, "total_steps": 64460, "loss": 0.2295, "lr": 9.989038542616243e-06, "epoch": 2.379770400248216, "percentage": 11.9, "elapsed_time": "0:13:53", "remaining_time": "1:42:50", "throughput": 5616.97, "total_tokens": 4681392} {"current_steps": 7675, "total_steps": 64460, "loss": 0.2265, "lr": 9.988948764886648e-06, "epoch": 2.3813217499224324, "percentage": 11.91, "elapsed_time": "0:13:53", "remaining_time": "1:42:50", "throughput": 5616.89, "total_tokens": 4684144} {"current_steps": 7680, "total_steps": 64460, "loss": 0.2246, "lr": 9.98885862140803e-06, "epoch": 2.382873099596649, "percentage": 11.91, "elapsed_time": "0:13:54", "remaining_time": "1:42:49", "throughput": 5616.72, "total_tokens": 4686864} {"current_steps": 7685, "total_steps": 64460, "loss": 0.2387, "lr": 9.988768112186996e-06, "epoch": 2.3844244492708655, "percentage": 11.92, "elapsed_time": "0:13:54", "remaining_time": "1:42:48", "throughput": 5616.92, "total_tokens": 4689840} {"current_steps": 7690, "total_steps": 64460, "loss": 0.2483, "lr": 9.988677237230185e-06, "epoch": 2.3859757989450823, "percentage": 11.93, "elapsed_time": "0:13:55", "remaining_time": "1:42:47", "throughput": 5617.21, "total_tokens": 4693232} {"current_steps": 7695, "total_steps": 64460, "loss": 0.2348, "lr": 9.988585996544258e-06, "epoch": 2.3875271486192986, "percentage": 11.94, "elapsed_time": "0:13:56", "remaining_time": "1:42:47", "throughput": 5617.32, "total_tokens": 4696176} {"current_steps": 7700, "total_steps": 64460, "loss": 0.2313, "lr": 9.988494390135903e-06, "epoch": 2.3890784982935154, "percentage": 11.95, "elapsed_time": "0:13:56", "remaining_time": "1:42:48", "throughput": 5617.82, "total_tokens": 4700784} {"current_steps": 7705, "total_steps": 64460, "loss": 0.2315, "lr": 9.988402418011836e-06, "epoch": 2.390629847967732, "percentage": 11.95, "elapsed_time": "0:13:57", "remaining_time": "1:42:47", "throughput": 5617.85, "total_tokens": 4703824} {"current_steps": 7710, "total_steps": 64460, "loss": 0.2335, "lr": 9.988310080178802e-06, "epoch": 2.3921811976419485, "percentage": 11.96, "elapsed_time": "0:13:57", "remaining_time": "1:42:46", "throughput": 5618.04, "total_tokens": 4706896} {"current_steps": 7715, "total_steps": 64460, "loss": 0.2293, "lr": 9.988217376643568e-06, "epoch": 2.3937325473161652, "percentage": 11.97, "elapsed_time": "0:13:58", "remaining_time": "1:42:46", "throughput": 5618.04, "total_tokens": 4710064} {"current_steps": 7720, "total_steps": 64460, "loss": 0.2298, "lr": 9.988124307412931e-06, "epoch": 2.3952838969903816, "percentage": 11.98, "elapsed_time": "0:13:58", "remaining_time": "1:42:45", "throughput": 5617.91, "total_tokens": 4712752} {"current_steps": 7725, "total_steps": 64460, "loss": 0.2294, "lr": 9.988030872493714e-06, "epoch": 2.3968352466645984, "percentage": 11.98, "elapsed_time": "0:13:59", "remaining_time": "1:42:44", "throughput": 5617.48, "total_tokens": 4715152} {"current_steps": 7730, "total_steps": 64460, "loss": 0.2343, "lr": 9.987937071892766e-06, "epoch": 2.3983865963388147, "percentage": 11.99, "elapsed_time": "0:13:59", "remaining_time": "1:42:44", "throughput": 5617.28, "total_tokens": 4718032} {"current_steps": 7735, "total_steps": 64460, "loss": 0.2251, "lr": 9.987842905616966e-06, "epoch": 2.3999379460130315, "percentage": 12.0, "elapsed_time": "0:14:00", "remaining_time": "1:42:43", "throughput": 5617.06, "total_tokens": 4720656} {"current_steps": 7740, "total_steps": 64460, "loss": 0.2467, "lr": 9.987748373673217e-06, "epoch": 2.401489295687248, "percentage": 12.01, "elapsed_time": "0:14:00", "remaining_time": "1:42:42", "throughput": 5616.71, "total_tokens": 4723120} {"current_steps": 7745, "total_steps": 64460, "loss": 0.2409, "lr": 9.987653476068447e-06, "epoch": 2.4030406453614646, "percentage": 12.02, "elapsed_time": "0:14:01", "remaining_time": "1:42:41", "throughput": 5616.4, "total_tokens": 4725616} {"current_steps": 7750, "total_steps": 64460, "loss": 0.2389, "lr": 9.987558212809614e-06, "epoch": 2.404591995035681, "percentage": 12.02, "elapsed_time": "0:14:01", "remaining_time": "1:42:40", "throughput": 5616.47, "total_tokens": 4728816} {"current_steps": 7755, "total_steps": 64460, "loss": 0.2273, "lr": 9.987462583903702e-06, "epoch": 2.4061433447098977, "percentage": 12.03, "elapsed_time": "0:14:02", "remaining_time": "1:42:40", "throughput": 5616.22, "total_tokens": 4731632} {"current_steps": 7760, "total_steps": 64460, "loss": 0.2318, "lr": 9.987366589357722e-06, "epoch": 2.407694694384114, "percentage": 12.04, "elapsed_time": "0:14:02", "remaining_time": "1:42:39", "throughput": 5616.01, "total_tokens": 4734288} {"current_steps": 7765, "total_steps": 64460, "loss": 0.2292, "lr": 9.987270229178714e-06, "epoch": 2.4092460440583308, "percentage": 12.05, "elapsed_time": "0:14:03", "remaining_time": "1:42:38", "throughput": 5615.69, "total_tokens": 4736976} {"current_steps": 7770, "total_steps": 64460, "loss": 0.2373, "lr": 9.98717350337374e-06, "epoch": 2.4107973937325475, "percentage": 12.05, "elapsed_time": "0:14:04", "remaining_time": "1:42:38", "throughput": 5615.92, "total_tokens": 4740240} {"current_steps": 7775, "total_steps": 64460, "loss": 0.2359, "lr": 9.98707641194989e-06, "epoch": 2.412348743406764, "percentage": 12.06, "elapsed_time": "0:14:04", "remaining_time": "1:42:37", "throughput": 5616.29, "total_tokens": 4743376} {"current_steps": 7780, "total_steps": 64460, "loss": 0.2384, "lr": 9.986978954914283e-06, "epoch": 2.4139000930809806, "percentage": 12.07, "elapsed_time": "0:14:05", "remaining_time": "1:42:37", "throughput": 5616.67, "total_tokens": 4747152} {"current_steps": 7785, "total_steps": 64460, "loss": 0.2326, "lr": 9.986881132274065e-06, "epoch": 2.415451442755197, "percentage": 12.08, "elapsed_time": "0:14:05", "remaining_time": "1:42:37", "throughput": 5616.38, "total_tokens": 4750000} {"current_steps": 7790, "total_steps": 64460, "loss": 0.2329, "lr": 9.986782944036407e-06, "epoch": 2.4170027924294137, "percentage": 12.09, "elapsed_time": "0:14:06", "remaining_time": "1:42:36", "throughput": 5616.4, "total_tokens": 4752976} {"current_steps": 7795, "total_steps": 64460, "loss": 0.2333, "lr": 9.986684390208504e-06, "epoch": 2.41855414210363, "percentage": 12.09, "elapsed_time": "0:14:06", "remaining_time": "1:42:35", "throughput": 5616.48, "total_tokens": 4755856} {"current_steps": 7800, "total_steps": 64460, "loss": 0.2297, "lr": 9.986585470797586e-06, "epoch": 2.420105491777847, "percentage": 12.1, "elapsed_time": "0:14:07", "remaining_time": "1:42:34", "throughput": 5616.59, "total_tokens": 4758864} {"current_steps": 7805, "total_steps": 64460, "loss": 0.2341, "lr": 9.986486185810904e-06, "epoch": 2.421656841452063, "percentage": 12.11, "elapsed_time": "0:14:07", "remaining_time": "1:42:33", "throughput": 5616.19, "total_tokens": 4761264} {"current_steps": 7810, "total_steps": 64460, "loss": 0.2368, "lr": 9.986386535255735e-06, "epoch": 2.42320819112628, "percentage": 12.12, "elapsed_time": "0:14:08", "remaining_time": "1:42:33", "throughput": 5615.62, "total_tokens": 4763632} {"current_steps": 7815, "total_steps": 64460, "loss": 0.2321, "lr": 9.986286519139383e-06, "epoch": 2.4247595408004963, "percentage": 12.12, "elapsed_time": "0:14:08", "remaining_time": "1:42:31", "throughput": 5615.75, "total_tokens": 4766384} {"current_steps": 7820, "total_steps": 64460, "loss": 0.2288, "lr": 9.986186137469184e-06, "epoch": 2.426310890474713, "percentage": 12.13, "elapsed_time": "0:14:09", "remaining_time": "1:42:31", "throughput": 5615.99, "total_tokens": 4769456} {"current_steps": 7825, "total_steps": 64460, "loss": 0.239, "lr": 9.986085390252499e-06, "epoch": 2.4278622401489294, "percentage": 12.14, "elapsed_time": "0:14:09", "remaining_time": "1:42:30", "throughput": 5616.42, "total_tokens": 4772880} {"current_steps": 7830, "total_steps": 64460, "loss": 0.23, "lr": 9.985984277496706e-06, "epoch": 2.429413589823146, "percentage": 12.15, "elapsed_time": "0:14:10", "remaining_time": "1:42:29", "throughput": 5616.08, "total_tokens": 4775408} {"current_steps": 7835, "total_steps": 64460, "loss": 0.2303, "lr": 9.985882799209226e-06, "epoch": 2.430964939497363, "percentage": 12.15, "elapsed_time": "0:14:10", "remaining_time": "1:42:29", "throughput": 5616.49, "total_tokens": 4779184} {"current_steps": 7840, "total_steps": 64460, "loss": 0.2288, "lr": 9.985780955397493e-06, "epoch": 2.4325162891715792, "percentage": 12.16, "elapsed_time": "0:14:11", "remaining_time": "1:42:29", "throughput": 5616.78, "total_tokens": 4782640} {"current_steps": 7845, "total_steps": 64460, "loss": 0.2327, "lr": 9.985678746068976e-06, "epoch": 2.434067638845796, "percentage": 12.17, "elapsed_time": "0:14:12", "remaining_time": "1:42:28", "throughput": 5617.13, "total_tokens": 4785840} {"current_steps": 7850, "total_steps": 64460, "loss": 0.2382, "lr": 9.985576171231169e-06, "epoch": 2.4356189885200124, "percentage": 12.18, "elapsed_time": "0:14:12", "remaining_time": "1:42:28", "throughput": 5617.62, "total_tokens": 4789424} {"current_steps": 7855, "total_steps": 64460, "loss": 0.2302, "lr": 9.985473230891589e-06, "epoch": 2.437170338194229, "percentage": 12.19, "elapsed_time": "0:14:13", "remaining_time": "1:42:27", "throughput": 5617.82, "total_tokens": 4792720} {"current_steps": 7860, "total_steps": 64460, "loss": 0.2347, "lr": 9.985369925057785e-06, "epoch": 2.4387216878684455, "percentage": 12.19, "elapsed_time": "0:14:13", "remaining_time": "1:42:26", "throughput": 5617.77, "total_tokens": 4795440} {"current_steps": 7865, "total_steps": 64460, "loss": 0.2285, "lr": 9.98526625373733e-06, "epoch": 2.4402730375426622, "percentage": 12.2, "elapsed_time": "0:14:14", "remaining_time": "1:42:25", "throughput": 5617.78, "total_tokens": 4798192} {"current_steps": 7870, "total_steps": 64460, "loss": 0.2275, "lr": 9.985162216937825e-06, "epoch": 2.4418243872168786, "percentage": 12.21, "elapsed_time": "0:14:14", "remaining_time": "1:42:25", "throughput": 5616.99, "total_tokens": 4800624} {"current_steps": 7875, "total_steps": 64460, "loss": 0.2275, "lr": 9.985057814666894e-06, "epoch": 2.4433757368910953, "percentage": 12.22, "elapsed_time": "0:14:15", "remaining_time": "1:42:25", "throughput": 5617.14, "total_tokens": 4804176} {"current_steps": 7880, "total_steps": 64460, "loss": 0.2355, "lr": 9.984953046932195e-06, "epoch": 2.4449270865653117, "percentage": 12.22, "elapsed_time": "0:14:15", "remaining_time": "1:42:24", "throughput": 5617.31, "total_tokens": 4807088} {"current_steps": 7885, "total_steps": 64460, "loss": 0.2306, "lr": 9.984847913741406e-06, "epoch": 2.4464784362395284, "percentage": 12.23, "elapsed_time": "0:14:16", "remaining_time": "1:42:23", "throughput": 5617.0, "total_tokens": 4809424} {"current_steps": 7890, "total_steps": 64460, "loss": 0.2326, "lr": 9.984742415102237e-06, "epoch": 2.4480297859137448, "percentage": 12.24, "elapsed_time": "0:14:16", "remaining_time": "1:42:24", "throughput": 5618.03, "total_tokens": 4814608} {"current_steps": 7895, "total_steps": 64460, "loss": 0.2326, "lr": 9.98463655102242e-06, "epoch": 2.4495811355879615, "percentage": 12.25, "elapsed_time": "0:14:17", "remaining_time": "1:42:23", "throughput": 5618.31, "total_tokens": 4817584} {"current_steps": 7900, "total_steps": 64460, "loss": 0.2311, "lr": 9.984530321509717e-06, "epoch": 2.4511324852621783, "percentage": 12.26, "elapsed_time": "0:14:18", "remaining_time": "1:42:23", "throughput": 5618.47, "total_tokens": 4820784} {"current_steps": 7905, "total_steps": 64460, "loss": 0.2267, "lr": 9.984423726571914e-06, "epoch": 2.4526838349363946, "percentage": 12.26, "elapsed_time": "0:14:18", "remaining_time": "1:42:22", "throughput": 5618.51, "total_tokens": 4823568} {"current_steps": 7910, "total_steps": 64460, "loss": 0.2319, "lr": 9.98431676621683e-06, "epoch": 2.4542351846106114, "percentage": 12.27, "elapsed_time": "0:14:19", "remaining_time": "1:42:21", "throughput": 5618.75, "total_tokens": 4826704} {"current_steps": 7915, "total_steps": 64460, "loss": 0.2292, "lr": 9.984209440452304e-06, "epoch": 2.4557865342848277, "percentage": 12.28, "elapsed_time": "0:14:19", "remaining_time": "1:42:20", "throughput": 5618.89, "total_tokens": 4829616} {"current_steps": 7920, "total_steps": 64460, "loss": 0.2279, "lr": 9.984101749286203e-06, "epoch": 2.4573378839590445, "percentage": 12.29, "elapsed_time": "0:14:20", "remaining_time": "1:42:19", "throughput": 5619.22, "total_tokens": 4832592} {"current_steps": 7925, "total_steps": 64460, "loss": 0.2308, "lr": 9.983993692726423e-06, "epoch": 2.458889233633261, "percentage": 12.29, "elapsed_time": "0:14:20", "remaining_time": "1:42:20", "throughput": 5620.11, "total_tokens": 4837328} {"current_steps": 7930, "total_steps": 64460, "loss": 0.2314, "lr": 9.983885270780887e-06, "epoch": 2.4604405833074776, "percentage": 12.3, "elapsed_time": "0:14:21", "remaining_time": "1:42:19", "throughput": 5620.14, "total_tokens": 4840208} {"current_steps": 7935, "total_steps": 64460, "loss": 0.2374, "lr": 9.983776483457541e-06, "epoch": 2.461991932981694, "percentage": 12.31, "elapsed_time": "0:14:21", "remaining_time": "1:42:18", "throughput": 5620.37, "total_tokens": 4843248} {"current_steps": 7940, "total_steps": 64460, "loss": 0.2206, "lr": 9.983667330764362e-06, "epoch": 2.4635432826559107, "percentage": 12.32, "elapsed_time": "0:14:22", "remaining_time": "1:42:17", "throughput": 5620.87, "total_tokens": 4846640} {"current_steps": 7945, "total_steps": 64460, "loss": 0.2414, "lr": 9.983557812709354e-06, "epoch": 2.465094632330127, "percentage": 12.33, "elapsed_time": "0:14:22", "remaining_time": "1:42:17", "throughput": 5620.88, "total_tokens": 4849456} {"current_steps": 7950, "total_steps": 64460, "loss": 0.252, "lr": 9.983447929300543e-06, "epoch": 2.466645982004344, "percentage": 12.33, "elapsed_time": "0:14:23", "remaining_time": "1:42:16", "throughput": 5620.69, "total_tokens": 4852304} {"current_steps": 7955, "total_steps": 64460, "loss": 0.2339, "lr": 9.983337680545987e-06, "epoch": 2.46819733167856, "percentage": 12.34, "elapsed_time": "0:14:23", "remaining_time": "1:42:15", "throughput": 5620.6, "total_tokens": 4854992} {"current_steps": 7960, "total_steps": 64460, "loss": 0.2327, "lr": 9.983227066453767e-06, "epoch": 2.469748681352777, "percentage": 12.35, "elapsed_time": "0:14:24", "remaining_time": "1:42:14", "throughput": 5620.22, "total_tokens": 4857488} {"current_steps": 7965, "total_steps": 64460, "loss": 0.2345, "lr": 9.983116087031991e-06, "epoch": 2.4713000310269937, "percentage": 12.36, "elapsed_time": "0:14:24", "remaining_time": "1:42:13", "throughput": 5620.56, "total_tokens": 4860688} {"current_steps": 7970, "total_steps": 64460, "loss": 0.2329, "lr": 9.983004742288799e-06, "epoch": 2.47285138070121, "percentage": 12.36, "elapsed_time": "0:14:25", "remaining_time": "1:42:12", "throughput": 5620.5, "total_tokens": 4863280} {"current_steps": 7975, "total_steps": 64460, "loss": 0.2287, "lr": 9.98289303223235e-06, "epoch": 2.474402730375427, "percentage": 12.37, "elapsed_time": "0:14:25", "remaining_time": "1:42:12", "throughput": 5620.79, "total_tokens": 4866672} {"current_steps": 7980, "total_steps": 64460, "loss": 0.234, "lr": 9.982780956870837e-06, "epoch": 2.475954080049643, "percentage": 12.38, "elapsed_time": "0:14:26", "remaining_time": "1:42:11", "throughput": 5621.05, "total_tokens": 4869776} {"current_steps": 7985, "total_steps": 64460, "loss": 0.2346, "lr": 9.982668516212476e-06, "epoch": 2.47750542972386, "percentage": 12.39, "elapsed_time": "0:14:26", "remaining_time": "1:42:11", "throughput": 5621.03, "total_tokens": 4872656} {"current_steps": 7990, "total_steps": 64460, "loss": 0.2308, "lr": 9.982555710265507e-06, "epoch": 2.4790567793980762, "percentage": 12.4, "elapsed_time": "0:14:27", "remaining_time": "1:42:10", "throughput": 5621.18, "total_tokens": 4875792} {"current_steps": 7995, "total_steps": 64460, "loss": 0.2284, "lr": 9.982442539038203e-06, "epoch": 2.480608129072293, "percentage": 12.4, "elapsed_time": "0:14:27", "remaining_time": "1:42:09", "throughput": 5621.18, "total_tokens": 4878576} {"current_steps": 8000, "total_steps": 64460, "loss": 0.2275, "lr": 9.98232900253886e-06, "epoch": 2.4821594787465093, "percentage": 12.41, "elapsed_time": "0:14:28", "remaining_time": "1:42:08", "throughput": 5620.66, "total_tokens": 4880912} {"current_steps": 8005, "total_steps": 64460, "loss": 0.2278, "lr": 9.982215100775801e-06, "epoch": 2.483710828420726, "percentage": 12.42, "elapsed_time": "0:14:29", "remaining_time": "1:42:10", "throughput": 5622.04, "total_tokens": 4886960} {"current_steps": 8010, "total_steps": 64460, "loss": 0.2256, "lr": 9.982100833757377e-06, "epoch": 2.4852621780949424, "percentage": 12.43, "elapsed_time": "0:14:29", "remaining_time": "1:42:09", "throughput": 5622.04, "total_tokens": 4889744} {"current_steps": 8015, "total_steps": 64460, "loss": 0.2354, "lr": 9.981986201491964e-06, "epoch": 2.486813527769159, "percentage": 12.43, "elapsed_time": "0:14:30", "remaining_time": "1:42:08", "throughput": 5622.06, "total_tokens": 4892688} {"current_steps": 8020, "total_steps": 64460, "loss": 0.2234, "lr": 9.981871203987969e-06, "epoch": 2.4883648774433755, "percentage": 12.44, "elapsed_time": "0:14:30", "remaining_time": "1:42:09", "throughput": 5622.75, "total_tokens": 4896976} {"current_steps": 8025, "total_steps": 64460, "loss": 0.238, "lr": 9.98175584125382e-06, "epoch": 2.4899162271175923, "percentage": 12.45, "elapsed_time": "0:14:31", "remaining_time": "1:42:08", "throughput": 5622.95, "total_tokens": 4900336} {"current_steps": 8030, "total_steps": 64460, "loss": 0.2401, "lr": 9.981640113297974e-06, "epoch": 2.491467576791809, "percentage": 12.46, "elapsed_time": "0:14:31", "remaining_time": "1:42:07", "throughput": 5622.75, "total_tokens": 4902896} {"current_steps": 8035, "total_steps": 64460, "loss": 0.2315, "lr": 9.981524020128916e-06, "epoch": 2.4930189264660254, "percentage": 12.47, "elapsed_time": "0:14:32", "remaining_time": "1:42:07", "throughput": 5623.32, "total_tokens": 4906928} {"current_steps": 8040, "total_steps": 64460, "loss": 0.2282, "lr": 9.98140756175516e-06, "epoch": 2.494570276140242, "percentage": 12.47, "elapsed_time": "0:14:33", "remaining_time": "1:42:07", "throughput": 5623.81, "total_tokens": 4910416} {"current_steps": 8045, "total_steps": 64460, "loss": 0.2343, "lr": 9.981290738185239e-06, "epoch": 2.4961216258144585, "percentage": 12.48, "elapsed_time": "0:14:33", "remaining_time": "1:42:06", "throughput": 5623.51, "total_tokens": 4912848} {"current_steps": 8050, "total_steps": 64460, "loss": 0.2329, "lr": 9.981173549427718e-06, "epoch": 2.4976729754886753, "percentage": 12.49, "elapsed_time": "0:14:34", "remaining_time": "1:42:05", "throughput": 5623.53, "total_tokens": 4916048} {"current_steps": 8055, "total_steps": 64460, "loss": 0.2378, "lr": 9.981055995491192e-06, "epoch": 2.4992243251628916, "percentage": 12.5, "elapsed_time": "0:14:34", "remaining_time": "1:42:06", "throughput": 5624.3, "total_tokens": 4920848} {"current_steps": 8060, "total_steps": 64460, "loss": 0.2293, "lr": 9.980938076384276e-06, "epoch": 2.5007756748371084, "percentage": 12.5, "elapsed_time": "0:14:35", "remaining_time": "1:42:05", "throughput": 5624.67, "total_tokens": 4924080} {"current_steps": 8065, "total_steps": 64460, "loss": 0.2293, "lr": 9.980819792115617e-06, "epoch": 2.5023270245113247, "percentage": 12.51, "elapsed_time": "0:14:35", "remaining_time": "1:42:05", "throughput": 5624.87, "total_tokens": 4927376} {"current_steps": 8070, "total_steps": 64460, "loss": 0.2295, "lr": 9.980701142693884e-06, "epoch": 2.5038783741855415, "percentage": 12.52, "elapsed_time": "0:14:36", "remaining_time": "1:42:04", "throughput": 5624.65, "total_tokens": 4930000} {"current_steps": 8075, "total_steps": 64460, "loss": 0.2228, "lr": 9.980582128127778e-06, "epoch": 2.5054297238597583, "percentage": 12.53, "elapsed_time": "0:14:36", "remaining_time": "1:42:03", "throughput": 5624.4, "total_tokens": 4932560} {"current_steps": 8080, "total_steps": 64460, "loss": 0.2385, "lr": 9.980462748426025e-06, "epoch": 2.5069810735339746, "percentage": 12.53, "elapsed_time": "0:14:37", "remaining_time": "1:42:03", "throughput": 5624.6, "total_tokens": 4935696} {"current_steps": 8085, "total_steps": 64460, "loss": 0.2364, "lr": 9.980343003597372e-06, "epoch": 2.508532423208191, "percentage": 12.54, "elapsed_time": "0:14:38", "remaining_time": "1:42:02", "throughput": 5624.49, "total_tokens": 4938672} {"current_steps": 8090, "total_steps": 64460, "loss": 0.2316, "lr": 9.980222893650601e-06, "epoch": 2.5100837728824077, "percentage": 12.55, "elapsed_time": "0:14:38", "remaining_time": "1:42:01", "throughput": 5623.7, "total_tokens": 4940752} {"current_steps": 8095, "total_steps": 64460, "loss": 0.2298, "lr": 9.98010241859452e-06, "epoch": 2.5116351225566245, "percentage": 12.56, "elapsed_time": "0:14:39", "remaining_time": "1:42:01", "throughput": 5624.03, "total_tokens": 4944528} {"current_steps": 8100, "total_steps": 64460, "loss": 0.2272, "lr": 9.979981578437957e-06, "epoch": 2.513186472230841, "percentage": 12.57, "elapsed_time": "0:14:39", "remaining_time": "1:42:01", "throughput": 5624.74, "total_tokens": 4948176} {"current_steps": 8105, "total_steps": 64460, "loss": 0.2331, "lr": 9.979860373189772e-06, "epoch": 2.514737821905057, "percentage": 12.57, "elapsed_time": "0:14:40", "remaining_time": "1:42:00", "throughput": 5624.91, "total_tokens": 4951440} {"current_steps": 8110, "total_steps": 64460, "loss": 0.2421, "lr": 9.979738802858848e-06, "epoch": 2.516289171579274, "percentage": 12.58, "elapsed_time": "0:14:40", "remaining_time": "1:41:59", "throughput": 5625.14, "total_tokens": 4954384} {"current_steps": 8115, "total_steps": 64460, "loss": 0.2369, "lr": 9.979616867454106e-06, "epoch": 2.5178405212534907, "percentage": 12.59, "elapsed_time": "0:14:41", "remaining_time": "1:41:58", "throughput": 5624.98, "total_tokens": 4956976} {"current_steps": 8120, "total_steps": 64460, "loss": 0.2347, "lr": 9.979494566984478e-06, "epoch": 2.519391870927707, "percentage": 12.6, "elapsed_time": "0:14:41", "remaining_time": "1:41:57", "throughput": 5624.2, "total_tokens": 4959088} {"current_steps": 8125, "total_steps": 64460, "loss": 0.2267, "lr": 9.979371901458931e-06, "epoch": 2.5209432206019238, "percentage": 12.6, "elapsed_time": "0:14:42", "remaining_time": "1:41:56", "throughput": 5624.26, "total_tokens": 4961776} {"current_steps": 8130, "total_steps": 64460, "loss": 0.2285, "lr": 9.979248870886463e-06, "epoch": 2.52249457027614, "percentage": 12.61, "elapsed_time": "0:14:42", "remaining_time": "1:41:56", "throughput": 5624.59, "total_tokens": 4964976} {"current_steps": 8135, "total_steps": 64460, "loss": 0.2205, "lr": 9.979125475276086e-06, "epoch": 2.524045919950357, "percentage": 12.62, "elapsed_time": "0:14:43", "remaining_time": "1:41:55", "throughput": 5624.99, "total_tokens": 4968688} {"current_steps": 8140, "total_steps": 64460, "loss": 0.2344, "lr": 9.97900171463685e-06, "epoch": 2.5255972696245736, "percentage": 12.63, "elapsed_time": "0:14:43", "remaining_time": "1:41:55", "throughput": 5625.51, "total_tokens": 4972176} {"current_steps": 8145, "total_steps": 64460, "loss": 0.2477, "lr": 9.978877588977832e-06, "epoch": 2.52714861929879, "percentage": 12.64, "elapsed_time": "0:14:44", "remaining_time": "1:41:54", "throughput": 5625.46, "total_tokens": 4975120} {"current_steps": 8150, "total_steps": 64460, "loss": 0.2265, "lr": 9.978753098308124e-06, "epoch": 2.5286999689730063, "percentage": 12.64, "elapsed_time": "0:14:44", "remaining_time": "1:41:53", "throughput": 5625.39, "total_tokens": 4977712} {"current_steps": 8155, "total_steps": 64460, "loss": 0.2394, "lr": 9.978628242636858e-06, "epoch": 2.530251318647223, "percentage": 12.65, "elapsed_time": "0:14:45", "remaining_time": "1:41:52", "throughput": 5625.39, "total_tokens": 4980400} {"current_steps": 8160, "total_steps": 64460, "loss": 0.2319, "lr": 9.978503021973184e-06, "epoch": 2.53180266832144, "percentage": 12.66, "elapsed_time": "0:14:45", "remaining_time": "1:41:51", "throughput": 5625.22, "total_tokens": 4983056} {"current_steps": 8165, "total_steps": 64460, "loss": 0.2349, "lr": 9.978377436326288e-06, "epoch": 2.533354017995656, "percentage": 12.67, "elapsed_time": "0:14:46", "remaining_time": "1:41:51", "throughput": 5625.76, "total_tokens": 4986832} {"current_steps": 8170, "total_steps": 64460, "loss": 0.2367, "lr": 9.97825148570537e-06, "epoch": 2.534905367669873, "percentage": 12.67, "elapsed_time": "0:14:46", "remaining_time": "1:41:50", "throughput": 5625.62, "total_tokens": 4989520} {"current_steps": 8175, "total_steps": 64460, "loss": 0.2263, "lr": 9.978125170119668e-06, "epoch": 2.5364567173440893, "percentage": 12.68, "elapsed_time": "0:14:47", "remaining_time": "1:41:50", "throughput": 5625.57, "total_tokens": 4992336} {"current_steps": 8180, "total_steps": 64460, "loss": 0.2346, "lr": 9.977998489578441e-06, "epoch": 2.538008067018306, "percentage": 12.69, "elapsed_time": "0:14:47", "remaining_time": "1:41:49", "throughput": 5625.38, "total_tokens": 4995152} {"current_steps": 8185, "total_steps": 64460, "loss": 0.231, "lr": 9.977871444090977e-06, "epoch": 2.5395594166925224, "percentage": 12.7, "elapsed_time": "0:14:48", "remaining_time": "1:41:48", "throughput": 5625.35, "total_tokens": 4997968} {"current_steps": 8190, "total_steps": 64460, "loss": 0.232, "lr": 9.97774403366659e-06, "epoch": 2.541110766366739, "percentage": 12.71, "elapsed_time": "0:14:48", "remaining_time": "1:41:47", "throughput": 5624.12, "total_tokens": 4999696} {"current_steps": 8195, "total_steps": 64460, "loss": 0.2314, "lr": 9.977616258314618e-06, "epoch": 2.5426621160409555, "percentage": 12.71, "elapsed_time": "0:14:49", "remaining_time": "1:41:46", "throughput": 5623.88, "total_tokens": 5002224} {"current_steps": 8200, "total_steps": 64460, "loss": 0.2304, "lr": 9.977488118044432e-06, "epoch": 2.5442134657151723, "percentage": 12.72, "elapsed_time": "0:14:49", "remaining_time": "1:41:45", "throughput": 5624.3, "total_tokens": 5005392} {"current_steps": 8205, "total_steps": 64460, "loss": 0.2336, "lr": 9.977359612865424e-06, "epoch": 2.545764815389389, "percentage": 12.73, "elapsed_time": "0:14:50", "remaining_time": "1:41:45", "throughput": 5624.83, "total_tokens": 5009264} {"current_steps": 8210, "total_steps": 64460, "loss": 0.2299, "lr": 9.977230742787017e-06, "epoch": 2.5473161650636054, "percentage": 12.74, "elapsed_time": "0:14:51", "remaining_time": "1:41:46", "throughput": 5625.44, "total_tokens": 5013520} {"current_steps": 8215, "total_steps": 64460, "loss": 0.2336, "lr": 9.977101507818653e-06, "epoch": 2.5488675147378217, "percentage": 12.74, "elapsed_time": "0:14:51", "remaining_time": "1:41:45", "throughput": 5624.95, "total_tokens": 5015792} {"current_steps": 8220, "total_steps": 64460, "loss": 0.2319, "lr": 9.976971907969814e-06, "epoch": 2.5504188644120385, "percentage": 12.75, "elapsed_time": "0:14:52", "remaining_time": "1:41:44", "throughput": 5624.93, "total_tokens": 5018768} {"current_steps": 8225, "total_steps": 64460, "loss": 0.2314, "lr": 9.97684194325e-06, "epoch": 2.5519702140862552, "percentage": 12.76, "elapsed_time": "0:14:52", "remaining_time": "1:41:43", "throughput": 5624.97, "total_tokens": 5021424} {"current_steps": 8230, "total_steps": 64460, "loss": 0.2314, "lr": 9.976711613668734e-06, "epoch": 2.5535215637604716, "percentage": 12.77, "elapsed_time": "0:14:53", "remaining_time": "1:41:42", "throughput": 5625.19, "total_tokens": 5024432} {"current_steps": 8235, "total_steps": 64460, "loss": 0.2315, "lr": 9.976580919235575e-06, "epoch": 2.5550729134346883, "percentage": 12.78, "elapsed_time": "0:14:53", "remaining_time": "1:41:41", "throughput": 5624.39, "total_tokens": 5026672} {"current_steps": 8240, "total_steps": 64460, "loss": 0.2325, "lr": 9.976449859960102e-06, "epoch": 2.5566242631089047, "percentage": 12.78, "elapsed_time": "0:14:54", "remaining_time": "1:41:41", "throughput": 5624.06, "total_tokens": 5029264} {"current_steps": 8245, "total_steps": 64460, "loss": 0.2263, "lr": 9.976318435851923e-06, "epoch": 2.5581756127831214, "percentage": 12.79, "elapsed_time": "0:14:54", "remaining_time": "1:41:40", "throughput": 5624.02, "total_tokens": 5032208} {"current_steps": 8250, "total_steps": 64460, "loss": 0.2323, "lr": 9.976186646920678e-06, "epoch": 2.5597269624573378, "percentage": 12.8, "elapsed_time": "0:14:55", "remaining_time": "1:41:39", "throughput": 5624.16, "total_tokens": 5035024} {"current_steps": 8255, "total_steps": 64460, "loss": 0.2314, "lr": 9.976054493176021e-06, "epoch": 2.5612783121315545, "percentage": 12.81, "elapsed_time": "0:14:55", "remaining_time": "1:41:38", "throughput": 5623.82, "total_tokens": 5037648} {"current_steps": 8260, "total_steps": 64460, "loss": 0.2276, "lr": 9.975921974627647e-06, "epoch": 2.562829661805771, "percentage": 12.81, "elapsed_time": "0:14:56", "remaining_time": "1:41:38", "throughput": 5624.08, "total_tokens": 5040752} {"current_steps": 8265, "total_steps": 64460, "loss": 0.2269, "lr": 9.975789091285268e-06, "epoch": 2.5643810114799876, "percentage": 12.82, "elapsed_time": "0:14:56", "remaining_time": "1:41:38", "throughput": 5624.53, "total_tokens": 5045136} {"current_steps": 8270, "total_steps": 64460, "loss": 0.2338, "lr": 9.975655843158627e-06, "epoch": 2.5659323611542044, "percentage": 12.83, "elapsed_time": "0:14:57", "remaining_time": "1:41:37", "throughput": 5624.17, "total_tokens": 5047408} {"current_steps": 8275, "total_steps": 64460, "loss": 0.23, "lr": 9.97552223025749e-06, "epoch": 2.5674837108284208, "percentage": 12.84, "elapsed_time": "0:14:57", "remaining_time": "1:41:37", "throughput": 5624.66, "total_tokens": 5050928} {"current_steps": 8280, "total_steps": 64460, "loss": 0.2354, "lr": 9.975388252591655e-06, "epoch": 2.569035060502637, "percentage": 12.85, "elapsed_time": "0:14:58", "remaining_time": "1:41:36", "throughput": 5625.14, "total_tokens": 5054224} {"current_steps": 8285, "total_steps": 64460, "loss": 0.2355, "lr": 9.975253910170946e-06, "epoch": 2.570586410176854, "percentage": 12.85, "elapsed_time": "0:14:59", "remaining_time": "1:41:35", "throughput": 5625.01, "total_tokens": 5057136} {"current_steps": 8290, "total_steps": 64460, "loss": 0.231, "lr": 9.975119203005207e-06, "epoch": 2.5721377598510706, "percentage": 12.86, "elapsed_time": "0:14:59", "remaining_time": "1:41:35", "throughput": 5625.36, "total_tokens": 5060912} {"current_steps": 8295, "total_steps": 64460, "loss": 0.2274, "lr": 9.974984131104318e-06, "epoch": 2.573689109525287, "percentage": 12.87, "elapsed_time": "0:15:00", "remaining_time": "1:41:34", "throughput": 5625.16, "total_tokens": 5063440} {"current_steps": 8300, "total_steps": 64460, "loss": 0.2341, "lr": 9.97484869447818e-06, "epoch": 2.5752404591995037, "percentage": 12.88, "elapsed_time": "0:15:00", "remaining_time": "1:41:34", "throughput": 5625.28, "total_tokens": 5066416} {"current_steps": 8305, "total_steps": 64460, "loss": 0.2299, "lr": 9.97471289313672e-06, "epoch": 2.57679180887372, "percentage": 12.88, "elapsed_time": "0:15:01", "remaining_time": "1:41:33", "throughput": 5626.25, "total_tokens": 5070704} {"current_steps": 8310, "total_steps": 64460, "loss": 0.2278, "lr": 9.974576727089896e-06, "epoch": 2.578343158547937, "percentage": 12.89, "elapsed_time": "0:15:01", "remaining_time": "1:41:33", "throughput": 5626.54, "total_tokens": 5073872} {"current_steps": 8315, "total_steps": 64460, "loss": 0.232, "lr": 9.97444019634769e-06, "epoch": 2.579894508222153, "percentage": 12.9, "elapsed_time": "0:15:02", "remaining_time": "1:41:32", "throughput": 5626.87, "total_tokens": 5076848} {"current_steps": 8320, "total_steps": 64460, "loss": 0.2363, "lr": 9.974303300920112e-06, "epoch": 2.58144585789637, "percentage": 12.91, "elapsed_time": "0:15:02", "remaining_time": "1:41:31", "throughput": 5627.01, "total_tokens": 5079696} {"current_steps": 8325, "total_steps": 64460, "loss": 0.2362, "lr": 9.974166040817195e-06, "epoch": 2.5829972075705863, "percentage": 12.91, "elapsed_time": "0:15:03", "remaining_time": "1:41:30", "throughput": 5627.23, "total_tokens": 5082768} {"current_steps": 8330, "total_steps": 64460, "loss": 0.2335, "lr": 9.974028416049007e-06, "epoch": 2.584548557244803, "percentage": 12.92, "elapsed_time": "0:15:03", "remaining_time": "1:41:29", "throughput": 5627.22, "total_tokens": 5085424} {"current_steps": 8335, "total_steps": 64460, "loss": 0.2299, "lr": 9.973890426625634e-06, "epoch": 2.58609990691902, "percentage": 12.93, "elapsed_time": "0:15:04", "remaining_time": "1:41:29", "throughput": 5627.4, "total_tokens": 5088848} {"current_steps": 8340, "total_steps": 64460, "loss": 0.2285, "lr": 9.973752072557194e-06, "epoch": 2.587651256593236, "percentage": 12.94, "elapsed_time": "0:15:04", "remaining_time": "1:41:28", "throughput": 5626.98, "total_tokens": 5091280} {"current_steps": 8345, "total_steps": 64460, "loss": 0.2286, "lr": 9.973613353853829e-06, "epoch": 2.5892026062674525, "percentage": 12.95, "elapsed_time": "0:15:05", "remaining_time": "1:41:27", "throughput": 5626.64, "total_tokens": 5093712} {"current_steps": 8350, "total_steps": 64460, "loss": 0.2365, "lr": 9.973474270525707e-06, "epoch": 2.5907539559416692, "percentage": 12.95, "elapsed_time": "0:15:05", "remaining_time": "1:41:26", "throughput": 5626.64, "total_tokens": 5096432} {"current_steps": 8355, "total_steps": 64460, "loss": 0.2399, "lr": 9.973334822583027e-06, "epoch": 2.592305305615886, "percentage": 12.96, "elapsed_time": "0:15:06", "remaining_time": "1:41:25", "throughput": 5626.75, "total_tokens": 5099504} {"current_steps": 8360, "total_steps": 64460, "loss": 0.2399, "lr": 9.973195010036012e-06, "epoch": 2.5938566552901023, "percentage": 12.97, "elapsed_time": "0:15:06", "remaining_time": "1:41:25", "throughput": 5626.41, "total_tokens": 5101968} {"current_steps": 8365, "total_steps": 64460, "loss": 0.232, "lr": 9.97305483289491e-06, "epoch": 2.595408004964319, "percentage": 12.98, "elapsed_time": "0:15:07", "remaining_time": "1:41:24", "throughput": 5626.19, "total_tokens": 5104464} {"current_steps": 8370, "total_steps": 64460, "loss": 0.2319, "lr": 9.97291429117e-06, "epoch": 2.5969593546385354, "percentage": 12.98, "elapsed_time": "0:15:07", "remaining_time": "1:41:23", "throughput": 5626.61, "total_tokens": 5107696} {"current_steps": 8375, "total_steps": 64460, "loss": 0.2308, "lr": 9.972773384871585e-06, "epoch": 2.598510704312752, "percentage": 12.99, "elapsed_time": "0:15:08", "remaining_time": "1:41:22", "throughput": 5627.09, "total_tokens": 5111088} {"current_steps": 8380, "total_steps": 64460, "loss": 0.2293, "lr": 9.972632114009992e-06, "epoch": 2.6000620539869685, "percentage": 13.0, "elapsed_time": "0:15:08", "remaining_time": "1:41:21", "throughput": 5626.84, "total_tokens": 5113552} {"current_steps": 8385, "total_steps": 64460, "loss": 0.2325, "lr": 9.972490478595583e-06, "epoch": 2.6016134036611853, "percentage": 13.01, "elapsed_time": "0:15:09", "remaining_time": "1:41:20", "throughput": 5627.11, "total_tokens": 5116560} {"current_steps": 8390, "total_steps": 64460, "loss": 0.232, "lr": 9.972348478638737e-06, "epoch": 2.6031647533354016, "percentage": 13.02, "elapsed_time": "0:15:09", "remaining_time": "1:41:20", "throughput": 5627.39, "total_tokens": 5119856} {"current_steps": 8395, "total_steps": 64460, "loss": 0.2289, "lr": 9.972206114149867e-06, "epoch": 2.6047161030096184, "percentage": 13.02, "elapsed_time": "0:15:10", "remaining_time": "1:41:19", "throughput": 5627.74, "total_tokens": 5123408} {"current_steps": 8400, "total_steps": 64460, "loss": 0.2321, "lr": 9.97206338513941e-06, "epoch": 2.606267452683835, "percentage": 13.03, "elapsed_time": "0:15:10", "remaining_time": "1:41:19", "throughput": 5627.71, "total_tokens": 5126416} {"current_steps": 8405, "total_steps": 64460, "loss": 0.2318, "lr": 9.971920291617828e-06, "epoch": 2.6078188023580515, "percentage": 13.04, "elapsed_time": "0:15:11", "remaining_time": "1:41:18", "throughput": 5627.47, "total_tokens": 5128816} {"current_steps": 8410, "total_steps": 64460, "loss": 0.2416, "lr": 9.971776833595612e-06, "epoch": 2.609370152032268, "percentage": 13.05, "elapsed_time": "0:15:12", "remaining_time": "1:41:18", "throughput": 5627.9, "total_tokens": 5132816} {"current_steps": 8415, "total_steps": 64460, "loss": 0.2341, "lr": 9.971633011083279e-06, "epoch": 2.6109215017064846, "percentage": 13.05, "elapsed_time": "0:15:12", "remaining_time": "1:41:17", "throughput": 5627.41, "total_tokens": 5135088} {"current_steps": 8420, "total_steps": 64460, "loss": 0.231, "lr": 9.971488824091373e-06, "epoch": 2.6124728513807014, "percentage": 13.06, "elapsed_time": "0:15:13", "remaining_time": "1:41:18", "throughput": 5628.43, "total_tokens": 5140816} {"current_steps": 8425, "total_steps": 64460, "loss": 0.2255, "lr": 9.971344272630467e-06, "epoch": 2.6140242010549177, "percentage": 13.07, "elapsed_time": "0:15:13", "remaining_time": "1:41:18", "throughput": 5628.23, "total_tokens": 5143376} {"current_steps": 8430, "total_steps": 64460, "loss": 0.2348, "lr": 9.971199356711154e-06, "epoch": 2.6155755507291345, "percentage": 13.08, "elapsed_time": "0:15:14", "remaining_time": "1:41:17", "throughput": 5628.05, "total_tokens": 5145936} {"current_steps": 8435, "total_steps": 64460, "loss": 0.2286, "lr": 9.971054076344061e-06, "epoch": 2.617126900403351, "percentage": 13.09, "elapsed_time": "0:15:14", "remaining_time": "1:41:16", "throughput": 5628.42, "total_tokens": 5149200} {"current_steps": 8440, "total_steps": 64460, "loss": 0.2248, "lr": 9.970908431539839e-06, "epoch": 2.6186782500775676, "percentage": 13.09, "elapsed_time": "0:15:15", "remaining_time": "1:41:15", "throughput": 5628.27, "total_tokens": 5152112} {"current_steps": 8445, "total_steps": 64460, "loss": 0.2396, "lr": 9.970762422309164e-06, "epoch": 2.620229599751784, "percentage": 13.1, "elapsed_time": "0:15:15", "remaining_time": "1:41:15", "throughput": 5628.88, "total_tokens": 5155920} {"current_steps": 8450, "total_steps": 64460, "loss": 0.242, "lr": 9.970616048662742e-06, "epoch": 2.6217809494260007, "percentage": 13.11, "elapsed_time": "0:15:16", "remaining_time": "1:41:14", "throughput": 5628.77, "total_tokens": 5158544} {"current_steps": 8455, "total_steps": 64460, "loss": 0.2329, "lr": 9.970469310611302e-06, "epoch": 2.623332299100217, "percentage": 13.12, "elapsed_time": "0:15:16", "remaining_time": "1:41:14", "throughput": 5628.78, "total_tokens": 5161520} {"current_steps": 8460, "total_steps": 64460, "loss": 0.2214, "lr": 9.970322208165601e-06, "epoch": 2.624883648774434, "percentage": 13.12, "elapsed_time": "0:15:17", "remaining_time": "1:41:13", "throughput": 5628.9, "total_tokens": 5164368} {"current_steps": 8465, "total_steps": 64460, "loss": 0.2306, "lr": 9.970174741336428e-06, "epoch": 2.6264349984486506, "percentage": 13.13, "elapsed_time": "0:15:18", "remaining_time": "1:41:13", "throughput": 5629.58, "total_tokens": 5168720} {"current_steps": 8470, "total_steps": 64460, "loss": 0.2376, "lr": 9.970026910134587e-06, "epoch": 2.627986348122867, "percentage": 13.14, "elapsed_time": "0:15:18", "remaining_time": "1:41:13", "throughput": 5630.14, "total_tokens": 5172816} {"current_steps": 8475, "total_steps": 64460, "loss": 0.2317, "lr": 9.969878714570922e-06, "epoch": 2.6295376977970832, "percentage": 13.15, "elapsed_time": "0:15:19", "remaining_time": "1:41:12", "throughput": 5630.14, "total_tokens": 5175504} {"current_steps": 8480, "total_steps": 64460, "loss": 0.2309, "lr": 9.969730154656294e-06, "epoch": 2.6310890474713, "percentage": 13.16, "elapsed_time": "0:15:19", "remaining_time": "1:41:11", "throughput": 5630.07, "total_tokens": 5178128} {"current_steps": 8485, "total_steps": 64460, "loss": 0.23, "lr": 9.969581230401595e-06, "epoch": 2.632640397145517, "percentage": 13.16, "elapsed_time": "0:15:20", "remaining_time": "1:41:10", "throughput": 5629.99, "total_tokens": 5180976} {"current_steps": 8490, "total_steps": 64460, "loss": 0.2318, "lr": 9.969431941817745e-06, "epoch": 2.634191746819733, "percentage": 13.17, "elapsed_time": "0:15:20", "remaining_time": "1:41:10", "throughput": 5630.28, "total_tokens": 5184208} {"current_steps": 8495, "total_steps": 64460, "loss": 0.2277, "lr": 9.969282288915685e-06, "epoch": 2.63574309649395, "percentage": 13.18, "elapsed_time": "0:15:21", "remaining_time": "1:41:09", "throughput": 5630.19, "total_tokens": 5186896} {"current_steps": 8500, "total_steps": 64460, "loss": 0.2349, "lr": 9.969132271706387e-06, "epoch": 2.637294446168166, "percentage": 13.19, "elapsed_time": "0:15:21", "remaining_time": "1:41:08", "throughput": 5630.06, "total_tokens": 5189552} {"current_steps": 8505, "total_steps": 64460, "loss": 0.2336, "lr": 9.968981890200853e-06, "epoch": 2.638845795842383, "percentage": 13.19, "elapsed_time": "0:15:22", "remaining_time": "1:41:07", "throughput": 5630.48, "total_tokens": 5192848} {"current_steps": 8510, "total_steps": 64460, "loss": 0.2264, "lr": 9.968831144410103e-06, "epoch": 2.6403971455165993, "percentage": 13.2, "elapsed_time": "0:15:22", "remaining_time": "1:41:06", "throughput": 5630.64, "total_tokens": 5195856} {"current_steps": 8515, "total_steps": 64460, "loss": 0.2357, "lr": 9.96868003434519e-06, "epoch": 2.641948495190816, "percentage": 13.21, "elapsed_time": "0:15:23", "remaining_time": "1:41:05", "throughput": 5629.87, "total_tokens": 5197776} {"current_steps": 8520, "total_steps": 64460, "loss": 0.2283, "lr": 9.968528560017195e-06, "epoch": 2.6434998448650324, "percentage": 13.22, "elapsed_time": "0:15:23", "remaining_time": "1:41:04", "throughput": 5629.83, "total_tokens": 5200464} {"current_steps": 8525, "total_steps": 64460, "loss": 0.2336, "lr": 9.968376721437218e-06, "epoch": 2.645051194539249, "percentage": 13.23, "elapsed_time": "0:15:24", "remaining_time": "1:41:04", "throughput": 5629.44, "total_tokens": 5202864} {"current_steps": 8530, "total_steps": 64460, "loss": 0.2337, "lr": 9.968224518616394e-06, "epoch": 2.646602544213466, "percentage": 13.23, "elapsed_time": "0:15:24", "remaining_time": "1:41:03", "throughput": 5629.61, "total_tokens": 5206320} {"current_steps": 8535, "total_steps": 64460, "loss": 0.232, "lr": 9.96807195156588e-06, "epoch": 2.6481538938876823, "percentage": 13.24, "elapsed_time": "0:15:25", "remaining_time": "1:41:02", "throughput": 5629.7, "total_tokens": 5209168} {"current_steps": 8540, "total_steps": 64460, "loss": 0.2319, "lr": 9.967919020296861e-06, "epoch": 2.6497052435618986, "percentage": 13.25, "elapsed_time": "0:15:25", "remaining_time": "1:41:02", "throughput": 5629.88, "total_tokens": 5212368} {"current_steps": 8545, "total_steps": 64460, "loss": 0.2324, "lr": 9.967765724820549e-06, "epoch": 2.6512565932361154, "percentage": 13.26, "elapsed_time": "0:15:26", "remaining_time": "1:41:01", "throughput": 5629.89, "total_tokens": 5215184} {"current_steps": 8550, "total_steps": 64460, "loss": 0.2329, "lr": 9.967612065148183e-06, "epoch": 2.652807942910332, "percentage": 13.26, "elapsed_time": "0:15:26", "remaining_time": "1:41:01", "throughput": 5630.18, "total_tokens": 5218480} {"current_steps": 8555, "total_steps": 64460, "loss": 0.2324, "lr": 9.967458041291026e-06, "epoch": 2.6543592925845485, "percentage": 13.27, "elapsed_time": "0:15:27", "remaining_time": "1:41:00", "throughput": 5630.28, "total_tokens": 5221552} {"current_steps": 8560, "total_steps": 64460, "loss": 0.2335, "lr": 9.967303653260371e-06, "epoch": 2.6559106422587653, "percentage": 13.28, "elapsed_time": "0:15:27", "remaining_time": "1:40:59", "throughput": 5630.28, "total_tokens": 5224528} {"current_steps": 8565, "total_steps": 64460, "loss": 0.2293, "lr": 9.967148901067538e-06, "epoch": 2.6574619919329816, "percentage": 13.29, "elapsed_time": "0:15:28", "remaining_time": "1:40:59", "throughput": 5630.01, "total_tokens": 5227248} {"current_steps": 8570, "total_steps": 64460, "loss": 0.2308, "lr": 9.96699378472387e-06, "epoch": 2.6590133416071984, "percentage": 13.3, "elapsed_time": "0:15:29", "remaining_time": "1:40:58", "throughput": 5630.22, "total_tokens": 5230832} {"current_steps": 8575, "total_steps": 64460, "loss": 0.2238, "lr": 9.96683830424074e-06, "epoch": 2.6605646912814147, "percentage": 13.3, "elapsed_time": "0:15:29", "remaining_time": "1:40:58", "throughput": 5630.71, "total_tokens": 5234064} {"current_steps": 8580, "total_steps": 64460, "loss": 0.2449, "lr": 9.966682459629543e-06, "epoch": 2.6621160409556315, "percentage": 13.31, "elapsed_time": "0:15:30", "remaining_time": "1:40:57", "throughput": 5631.23, "total_tokens": 5237904} {"current_steps": 8585, "total_steps": 64460, "loss": 0.2332, "lr": 9.966526250901711e-06, "epoch": 2.663667390629848, "percentage": 13.32, "elapsed_time": "0:15:30", "remaining_time": "1:40:57", "throughput": 5631.61, "total_tokens": 5241136} {"current_steps": 8590, "total_steps": 64460, "loss": 0.2301, "lr": 9.966369678068692e-06, "epoch": 2.6652187403040646, "percentage": 13.33, "elapsed_time": "0:15:31", "remaining_time": "1:40:56", "throughput": 5631.56, "total_tokens": 5244048} {"current_steps": 8595, "total_steps": 64460, "loss": 0.2294, "lr": 9.966212741141964e-06, "epoch": 2.6667700899782814, "percentage": 13.33, "elapsed_time": "0:15:31", "remaining_time": "1:40:55", "throughput": 5631.58, "total_tokens": 5246928} {"current_steps": 8600, "total_steps": 64460, "loss": 0.2335, "lr": 9.966055440133034e-06, "epoch": 2.6683214396524977, "percentage": 13.34, "elapsed_time": "0:15:32", "remaining_time": "1:40:55", "throughput": 5631.03, "total_tokens": 5249392} {"current_steps": 8605, "total_steps": 64460, "loss": 0.2345, "lr": 9.965897775053433e-06, "epoch": 2.669872789326714, "percentage": 13.35, "elapsed_time": "0:15:32", "remaining_time": "1:40:54", "throughput": 5630.58, "total_tokens": 5251760} {"current_steps": 8610, "total_steps": 64460, "loss": 0.2295, "lr": 9.96573974591472e-06, "epoch": 2.671424139000931, "percentage": 13.36, "elapsed_time": "0:15:33", "remaining_time": "1:40:53", "throughput": 5630.8, "total_tokens": 5254864} {"current_steps": 8615, "total_steps": 64460, "loss": 0.2293, "lr": 9.96558135272848e-06, "epoch": 2.6729754886751476, "percentage": 13.36, "elapsed_time": "0:15:33", "remaining_time": "1:40:52", "throughput": 5630.86, "total_tokens": 5257712} {"current_steps": 8620, "total_steps": 64460, "loss": 0.2325, "lr": 9.965422595506327e-06, "epoch": 2.674526838349364, "percentage": 13.37, "elapsed_time": "0:15:34", "remaining_time": "1:40:51", "throughput": 5630.99, "total_tokens": 5260624} {"current_steps": 8625, "total_steps": 64460, "loss": 0.2273, "lr": 9.965263474259896e-06, "epoch": 2.6760781880235807, "percentage": 13.38, "elapsed_time": "0:15:34", "remaining_time": "1:40:51", "throughput": 5630.71, "total_tokens": 5263184} {"current_steps": 8630, "total_steps": 64460, "loss": 0.2285, "lr": 9.965103989000857e-06, "epoch": 2.677629537697797, "percentage": 13.39, "elapsed_time": "0:15:35", "remaining_time": "1:40:50", "throughput": 5631.09, "total_tokens": 5266448} {"current_steps": 8635, "total_steps": 64460, "loss": 0.2357, "lr": 9.964944139740899e-06, "epoch": 2.6791808873720138, "percentage": 13.4, "elapsed_time": "0:15:35", "remaining_time": "1:40:49", "throughput": 5631.09, "total_tokens": 5269168} {"current_steps": 8640, "total_steps": 64460, "loss": 0.2294, "lr": 9.964783926491741e-06, "epoch": 2.68073223704623, "percentage": 13.4, "elapsed_time": "0:15:36", "remaining_time": "1:40:48", "throughput": 5631.17, "total_tokens": 5271984} {"current_steps": 8645, "total_steps": 64460, "loss": 0.2313, "lr": 9.96462334926513e-06, "epoch": 2.682283586720447, "percentage": 13.41, "elapsed_time": "0:15:36", "remaining_time": "1:40:47", "throughput": 5631.32, "total_tokens": 5275152} {"current_steps": 8650, "total_steps": 64460, "loss": 0.2298, "lr": 9.964462408072839e-06, "epoch": 2.683834936394663, "percentage": 13.42, "elapsed_time": "0:15:37", "remaining_time": "1:40:47", "throughput": 5630.58, "total_tokens": 5277360} {"current_steps": 8655, "total_steps": 64460, "loss": 0.2309, "lr": 9.964301102926663e-06, "epoch": 2.68538628606888, "percentage": 13.43, "elapsed_time": "0:15:37", "remaining_time": "1:40:46", "throughput": 5630.75, "total_tokens": 5280528} {"current_steps": 8660, "total_steps": 64460, "loss": 0.2314, "lr": 9.964139433838434e-06, "epoch": 2.6869376357430967, "percentage": 13.43, "elapsed_time": "0:15:38", "remaining_time": "1:40:45", "throughput": 5630.4, "total_tokens": 5282928} {"current_steps": 8665, "total_steps": 64460, "loss": 0.2277, "lr": 9.963977400819996e-06, "epoch": 2.688488985417313, "percentage": 13.44, "elapsed_time": "0:15:38", "remaining_time": "1:40:45", "throughput": 5630.53, "total_tokens": 5286064} {"current_steps": 8670, "total_steps": 64460, "loss": 0.2367, "lr": 9.963815003883235e-06, "epoch": 2.6900403350915294, "percentage": 13.45, "elapsed_time": "0:15:39", "remaining_time": "1:40:44", "throughput": 5630.6, "total_tokens": 5289040} {"current_steps": 8675, "total_steps": 64460, "loss": 0.233, "lr": 9.963652243040052e-06, "epoch": 2.691591684765746, "percentage": 13.46, "elapsed_time": "0:15:39", "remaining_time": "1:40:43", "throughput": 5630.62, "total_tokens": 5291792} {"current_steps": 8680, "total_steps": 64460, "loss": 0.2292, "lr": 9.963489118302382e-06, "epoch": 2.693143034439963, "percentage": 13.47, "elapsed_time": "0:15:40", "remaining_time": "1:40:43", "throughput": 5631.07, "total_tokens": 5295312} {"current_steps": 8685, "total_steps": 64460, "loss": 0.2321, "lr": 9.963325629682184e-06, "epoch": 2.6946943841141793, "percentage": 13.47, "elapsed_time": "0:15:40", "remaining_time": "1:40:42", "throughput": 5630.96, "total_tokens": 5298448} {"current_steps": 8690, "total_steps": 64460, "loss": 0.2268, "lr": 9.963161777191442e-06, "epoch": 2.696245733788396, "percentage": 13.48, "elapsed_time": "0:15:41", "remaining_time": "1:40:42", "throughput": 5631.24, "total_tokens": 5302288} {"current_steps": 8695, "total_steps": 64460, "loss": 0.2358, "lr": 9.962997560842167e-06, "epoch": 2.6977970834626124, "percentage": 13.49, "elapsed_time": "0:15:42", "remaining_time": "1:40:41", "throughput": 5631.13, "total_tokens": 5304784} {"current_steps": 8700, "total_steps": 64460, "loss": 0.2256, "lr": 9.962832980646403e-06, "epoch": 2.699348433136829, "percentage": 13.5, "elapsed_time": "0:15:42", "remaining_time": "1:40:41", "throughput": 5630.9, "total_tokens": 5307504} {"current_steps": 8705, "total_steps": 64460, "loss": 0.229, "lr": 9.962668036616212e-06, "epoch": 2.7008997828110455, "percentage": 13.5, "elapsed_time": "0:15:43", "remaining_time": "1:40:41", "throughput": 5630.75, "total_tokens": 5311056} {"current_steps": 8710, "total_steps": 64460, "loss": 0.2402, "lr": 9.962502728763687e-06, "epoch": 2.7024511324852623, "percentage": 13.51, "elapsed_time": "0:15:43", "remaining_time": "1:40:40", "throughput": 5630.45, "total_tokens": 5313520} {"current_steps": 8715, "total_steps": 64460, "loss": 0.2338, "lr": 9.962337057100946e-06, "epoch": 2.7040024821594786, "percentage": 13.52, "elapsed_time": "0:15:44", "remaining_time": "1:40:39", "throughput": 5630.53, "total_tokens": 5316560} {"current_steps": 8720, "total_steps": 64460, "loss": 0.2325, "lr": 9.962171021640137e-06, "epoch": 2.7055538318336954, "percentage": 13.53, "elapsed_time": "0:15:44", "remaining_time": "1:40:39", "throughput": 5630.04, "total_tokens": 5319312} {"current_steps": 8725, "total_steps": 64460, "loss": 0.233, "lr": 9.962004622393431e-06, "epoch": 2.707105181507912, "percentage": 13.54, "elapsed_time": "0:15:45", "remaining_time": "1:40:39", "throughput": 5628.97, "total_tokens": 5321744} {"current_steps": 8730, "total_steps": 64460, "loss": 0.23, "lr": 9.961837859373028e-06, "epoch": 2.7086565311821285, "percentage": 13.54, "elapsed_time": "0:15:46", "remaining_time": "1:40:39", "throughput": 5629.05, "total_tokens": 5325296} {"current_steps": 8735, "total_steps": 64460, "loss": 0.2312, "lr": 9.961670732591154e-06, "epoch": 2.710207880856345, "percentage": 13.55, "elapsed_time": "0:15:46", "remaining_time": "1:40:38", "throughput": 5629.21, "total_tokens": 5328304} {"current_steps": 8740, "total_steps": 64460, "loss": 0.2263, "lr": 9.961503242060057e-06, "epoch": 2.7117592305305616, "percentage": 13.56, "elapsed_time": "0:15:47", "remaining_time": "1:40:37", "throughput": 5629.2, "total_tokens": 5331376} {"current_steps": 8745, "total_steps": 64460, "loss": 0.2317, "lr": 9.961335387792022e-06, "epoch": 2.7133105802047783, "percentage": 13.57, "elapsed_time": "0:15:47", "remaining_time": "1:40:37", "throughput": 5629.29, "total_tokens": 5334480} {"current_steps": 8750, "total_steps": 64460, "loss": 0.2408, "lr": 9.96116716979935e-06, "epoch": 2.7148619298789947, "percentage": 13.57, "elapsed_time": "0:15:48", "remaining_time": "1:40:37", "throughput": 5629.77, "total_tokens": 5338288} {"current_steps": 8755, "total_steps": 64460, "loss": 0.2214, "lr": 9.960998588094377e-06, "epoch": 2.7164132795532114, "percentage": 13.58, "elapsed_time": "0:15:48", "remaining_time": "1:40:36", "throughput": 5629.52, "total_tokens": 5341040} {"current_steps": 8760, "total_steps": 64460, "loss": 0.2341, "lr": 9.96082964268946e-06, "epoch": 2.7179646292274278, "percentage": 13.59, "elapsed_time": "0:15:49", "remaining_time": "1:40:35", "throughput": 5629.45, "total_tokens": 5343920} {"current_steps": 8765, "total_steps": 64460, "loss": 0.2272, "lr": 9.960660333596986e-06, "epoch": 2.7195159789016445, "percentage": 13.6, "elapsed_time": "0:15:49", "remaining_time": "1:40:35", "throughput": 5630.01, "total_tokens": 5347504} {"current_steps": 8770, "total_steps": 64460, "loss": 0.243, "lr": 9.960490660829366e-06, "epoch": 2.721067328575861, "percentage": 13.61, "elapsed_time": "0:15:50", "remaining_time": "1:40:34", "throughput": 5630.42, "total_tokens": 5350832} {"current_steps": 8775, "total_steps": 64460, "loss": 0.2332, "lr": 9.960320624399038e-06, "epoch": 2.7226186782500776, "percentage": 13.61, "elapsed_time": "0:15:50", "remaining_time": "1:40:34", "throughput": 5630.65, "total_tokens": 5354224} {"current_steps": 8780, "total_steps": 64460, "loss": 0.2315, "lr": 9.960150224318471e-06, "epoch": 2.724170027924294, "percentage": 13.62, "elapsed_time": "0:15:51", "remaining_time": "1:40:33", "throughput": 5630.55, "total_tokens": 5357264} {"current_steps": 8785, "total_steps": 64460, "loss": 0.2244, "lr": 9.959979460600156e-06, "epoch": 2.7257213775985107, "percentage": 13.63, "elapsed_time": "0:15:51", "remaining_time": "1:40:32", "throughput": 5630.81, "total_tokens": 5360240} {"current_steps": 8790, "total_steps": 64460, "loss": 0.2332, "lr": 9.959808333256612e-06, "epoch": 2.7272727272727275, "percentage": 13.64, "elapsed_time": "0:15:52", "remaining_time": "1:40:32", "throughput": 5630.78, "total_tokens": 5362896} {"current_steps": 8795, "total_steps": 64460, "loss": 0.2353, "lr": 9.959636842300382e-06, "epoch": 2.728824076946944, "percentage": 13.64, "elapsed_time": "0:15:53", "remaining_time": "1:40:33", "throughput": 5631.76, "total_tokens": 5368912} {"current_steps": 8800, "total_steps": 64460, "loss": 0.225, "lr": 9.95946498774404e-06, "epoch": 2.73037542662116, "percentage": 13.65, "elapsed_time": "0:15:53", "remaining_time": "1:40:32", "throughput": 5631.9, "total_tokens": 5371856} {"current_steps": 8805, "total_steps": 64460, "loss": 0.2412, "lr": 9.959292769600188e-06, "epoch": 2.731926776295377, "percentage": 13.66, "elapsed_time": "0:15:54", "remaining_time": "1:40:32", "throughput": 5632.15, "total_tokens": 5375056} {"current_steps": 8810, "total_steps": 64460, "loss": 0.2275, "lr": 9.959120187881448e-06, "epoch": 2.7334781259695937, "percentage": 13.67, "elapsed_time": "0:15:54", "remaining_time": "1:40:31", "throughput": 5632.03, "total_tokens": 5377648} {"current_steps": 8815, "total_steps": 64460, "loss": 0.2357, "lr": 9.958947242600474e-06, "epoch": 2.73502947564381, "percentage": 13.68, "elapsed_time": "0:15:55", "remaining_time": "1:40:30", "throughput": 5631.55, "total_tokens": 5380176} {"current_steps": 8820, "total_steps": 64460, "loss": 0.2345, "lr": 9.958773933769946e-06, "epoch": 2.736580825318027, "percentage": 13.68, "elapsed_time": "0:15:55", "remaining_time": "1:40:30", "throughput": 5631.62, "total_tokens": 5383248} {"current_steps": 8825, "total_steps": 64460, "loss": 0.2366, "lr": 9.958600261402565e-06, "epoch": 2.738132174992243, "percentage": 13.69, "elapsed_time": "0:15:56", "remaining_time": "1:40:29", "throughput": 5631.18, "total_tokens": 5385584} {"current_steps": 8830, "total_steps": 64460, "loss": 0.2308, "lr": 9.958426225511066e-06, "epoch": 2.73968352466646, "percentage": 13.7, "elapsed_time": "0:15:57", "remaining_time": "1:40:29", "throughput": 5632.22, "total_tokens": 5390672} {"current_steps": 8835, "total_steps": 64460, "loss": 0.2328, "lr": 9.958251826108211e-06, "epoch": 2.7412348743406763, "percentage": 13.71, "elapsed_time": "0:15:57", "remaining_time": "1:40:29", "throughput": 5632.18, "total_tokens": 5393424} {"current_steps": 8840, "total_steps": 64460, "loss": 0.2341, "lr": 9.958077063206782e-06, "epoch": 2.742786224014893, "percentage": 13.71, "elapsed_time": "0:15:58", "remaining_time": "1:40:28", "throughput": 5631.96, "total_tokens": 5395824} {"current_steps": 8845, "total_steps": 64460, "loss": 0.2319, "lr": 9.95790193681959e-06, "epoch": 2.7443375736891094, "percentage": 13.72, "elapsed_time": "0:15:58", "remaining_time": "1:40:27", "throughput": 5632.23, "total_tokens": 5398992} {"current_steps": 8850, "total_steps": 64460, "loss": 0.2306, "lr": 9.957726446959477e-06, "epoch": 2.745888923363326, "percentage": 13.73, "elapsed_time": "0:15:59", "remaining_time": "1:40:26", "throughput": 5632.45, "total_tokens": 5402032} {"current_steps": 8855, "total_steps": 64460, "loss": 0.2327, "lr": 9.957550593639307e-06, "epoch": 2.747440273037543, "percentage": 13.74, "elapsed_time": "0:15:59", "remaining_time": "1:40:26", "throughput": 5633.04, "total_tokens": 5406512} {"current_steps": 8860, "total_steps": 64460, "loss": 0.2379, "lr": 9.957374376871973e-06, "epoch": 2.7489916227117592, "percentage": 13.74, "elapsed_time": "0:16:00", "remaining_time": "1:40:26", "throughput": 5633.15, "total_tokens": 5409360} {"current_steps": 8865, "total_steps": 64460, "loss": 0.2309, "lr": 9.957197796670391e-06, "epoch": 2.7505429723859756, "percentage": 13.75, "elapsed_time": "0:16:00", "remaining_time": "1:40:25", "throughput": 5633.23, "total_tokens": 5412336} {"current_steps": 8870, "total_steps": 64460, "loss": 0.232, "lr": 9.957020853047509e-06, "epoch": 2.7520943220601923, "percentage": 13.76, "elapsed_time": "0:16:01", "remaining_time": "1:40:24", "throughput": 5633.03, "total_tokens": 5414832} {"current_steps": 8875, "total_steps": 64460, "loss": 0.2296, "lr": 9.9568435460163e-06, "epoch": 2.753645671734409, "percentage": 13.77, "elapsed_time": "0:16:01", "remaining_time": "1:40:23", "throughput": 5632.65, "total_tokens": 5417328} {"current_steps": 8880, "total_steps": 64460, "loss": 0.2316, "lr": 9.956665875589762e-06, "epoch": 2.7551970214086254, "percentage": 13.78, "elapsed_time": "0:16:02", "remaining_time": "1:40:23", "throughput": 5633.17, "total_tokens": 5420880} {"current_steps": 8885, "total_steps": 64460, "loss": 0.2352, "lr": 9.956487841780918e-06, "epoch": 2.756748371082842, "percentage": 13.78, "elapsed_time": "0:16:02", "remaining_time": "1:40:22", "throughput": 5633.16, "total_tokens": 5423920} {"current_steps": 8890, "total_steps": 64460, "loss": 0.2368, "lr": 9.956309444602821e-06, "epoch": 2.7582997207570585, "percentage": 13.79, "elapsed_time": "0:16:03", "remaining_time": "1:40:21", "throughput": 5633.39, "total_tokens": 5426896} {"current_steps": 8895, "total_steps": 64460, "loss": 0.2373, "lr": 9.956130684068551e-06, "epoch": 2.7598510704312753, "percentage": 13.8, "elapsed_time": "0:16:03", "remaining_time": "1:40:21", "throughput": 5633.53, "total_tokens": 5430000} {"current_steps": 8900, "total_steps": 64460, "loss": 0.2322, "lr": 9.955951560191213e-06, "epoch": 2.7614024201054916, "percentage": 13.81, "elapsed_time": "0:16:04", "remaining_time": "1:40:20", "throughput": 5633.3, "total_tokens": 5432464} {"current_steps": 8905, "total_steps": 64460, "loss": 0.2316, "lr": 9.955772072983939e-06, "epoch": 2.7629537697797084, "percentage": 13.81, "elapsed_time": "0:16:04", "remaining_time": "1:40:19", "throughput": 5633.26, "total_tokens": 5435664} {"current_steps": 8910, "total_steps": 64460, "loss": 0.23, "lr": 9.955592222459885e-06, "epoch": 2.7645051194539247, "percentage": 13.82, "elapsed_time": "0:16:05", "remaining_time": "1:40:19", "throughput": 5633.33, "total_tokens": 5439312} {"current_steps": 8915, "total_steps": 64460, "loss": 0.2305, "lr": 9.955412008632239e-06, "epoch": 2.7660564691281415, "percentage": 13.83, "elapsed_time": "0:16:06", "remaining_time": "1:40:19", "throughput": 5633.72, "total_tokens": 5442576} {"current_steps": 8920, "total_steps": 64460, "loss": 0.2337, "lr": 9.955231431514212e-06, "epoch": 2.7676078188023583, "percentage": 13.84, "elapsed_time": "0:16:06", "remaining_time": "1:40:18", "throughput": 5633.92, "total_tokens": 5445872} {"current_steps": 8925, "total_steps": 64460, "loss": 0.2305, "lr": 9.955050491119041e-06, "epoch": 2.7691591684765746, "percentage": 13.85, "elapsed_time": "0:16:07", "remaining_time": "1:40:17", "throughput": 5633.75, "total_tokens": 5448432} {"current_steps": 8930, "total_steps": 64460, "loss": 0.2335, "lr": 9.954869187459994e-06, "epoch": 2.770710518150791, "percentage": 13.85, "elapsed_time": "0:16:07", "remaining_time": "1:40:16", "throughput": 5633.95, "total_tokens": 5451280} {"current_steps": 8935, "total_steps": 64460, "loss": 0.2309, "lr": 9.954687520550362e-06, "epoch": 2.7722618678250077, "percentage": 13.86, "elapsed_time": "0:16:08", "remaining_time": "1:40:15", "throughput": 5633.82, "total_tokens": 5454000} {"current_steps": 8940, "total_steps": 64460, "loss": 0.2346, "lr": 9.954505490403462e-06, "epoch": 2.7738132174992245, "percentage": 13.87, "elapsed_time": "0:16:08", "remaining_time": "1:40:15", "throughput": 5633.77, "total_tokens": 5456816} {"current_steps": 8945, "total_steps": 64460, "loss": 0.2321, "lr": 9.954323097032637e-06, "epoch": 2.775364567173441, "percentage": 13.88, "elapsed_time": "0:16:09", "remaining_time": "1:40:14", "throughput": 5633.29, "total_tokens": 5459344} {"current_steps": 8950, "total_steps": 64460, "loss": 0.2276, "lr": 9.954140340451262e-06, "epoch": 2.7769159168476576, "percentage": 13.88, "elapsed_time": "0:16:09", "remaining_time": "1:40:13", "throughput": 5632.93, "total_tokens": 5461776} {"current_steps": 8955, "total_steps": 64460, "loss": 0.2385, "lr": 9.953957220672736e-06, "epoch": 2.778467266521874, "percentage": 13.89, "elapsed_time": "0:16:10", "remaining_time": "1:40:13", "throughput": 5633.22, "total_tokens": 5465200} {"current_steps": 8960, "total_steps": 64460, "loss": 0.2389, "lr": 9.953773737710481e-06, "epoch": 2.7800186161960907, "percentage": 13.9, "elapsed_time": "0:16:10", "remaining_time": "1:40:12", "throughput": 5632.93, "total_tokens": 5467664} {"current_steps": 8965, "total_steps": 64460, "loss": 0.2322, "lr": 9.95358989157795e-06, "epoch": 2.781569965870307, "percentage": 13.91, "elapsed_time": "0:16:11", "remaining_time": "1:40:11", "throughput": 5633.28, "total_tokens": 5471024} {"current_steps": 8970, "total_steps": 64460, "loss": 0.2305, "lr": 9.95340568228862e-06, "epoch": 2.783121315544524, "percentage": 13.92, "elapsed_time": "0:16:11", "remaining_time": "1:40:11", "throughput": 5633.43, "total_tokens": 5474160} {"current_steps": 8975, "total_steps": 64460, "loss": 0.2322, "lr": 9.953221109855998e-06, "epoch": 2.78467266521874, "percentage": 13.92, "elapsed_time": "0:16:12", "remaining_time": "1:40:10", "throughput": 5633.62, "total_tokens": 5477616} {"current_steps": 8980, "total_steps": 64460, "loss": 0.2326, "lr": 9.953036174293612e-06, "epoch": 2.786224014892957, "percentage": 13.93, "elapsed_time": "0:16:12", "remaining_time": "1:40:11", "throughput": 5633.94, "total_tokens": 5481808} {"current_steps": 8985, "total_steps": 64460, "loss": 0.2314, "lr": 9.952850875615021e-06, "epoch": 2.7877753645671737, "percentage": 13.94, "elapsed_time": "0:16:13", "remaining_time": "1:40:10", "throughput": 5633.19, "total_tokens": 5483984} {"current_steps": 8990, "total_steps": 64460, "loss": 0.2335, "lr": 9.952665213833813e-06, "epoch": 2.78932671424139, "percentage": 13.95, "elapsed_time": "0:16:14", "remaining_time": "1:40:10", "throughput": 5632.37, "total_tokens": 5486192} {"current_steps": 8995, "total_steps": 64460, "loss": 0.2315, "lr": 9.952479188963593e-06, "epoch": 2.7908780639156063, "percentage": 13.95, "elapsed_time": "0:16:14", "remaining_time": "1:40:09", "throughput": 5632.44, "total_tokens": 5488976} {"current_steps": 9000, "total_steps": 64460, "loss": 0.2284, "lr": 9.952292801018004e-06, "epoch": 2.792429413589823, "percentage": 13.96, "elapsed_time": "0:16:15", "remaining_time": "1:40:08", "throughput": 5632.74, "total_tokens": 5492432} {"current_steps": 9005, "total_steps": 64460, "loss": 0.2279, "lr": 9.95210605001071e-06, "epoch": 2.79398076326404, "percentage": 13.97, "elapsed_time": "0:16:15", "remaining_time": "1:40:07", "throughput": 5632.85, "total_tokens": 5495312} {"current_steps": 9010, "total_steps": 64460, "loss": 0.2224, "lr": 9.9519189359554e-06, "epoch": 2.795532112938256, "percentage": 13.98, "elapsed_time": "0:16:16", "remaining_time": "1:40:06", "throughput": 5632.54, "total_tokens": 5497744} {"current_steps": 9015, "total_steps": 64460, "loss": 0.2387, "lr": 9.951731458865793e-06, "epoch": 2.797083462612473, "percentage": 13.99, "elapsed_time": "0:16:16", "remaining_time": "1:40:06", "throughput": 5632.11, "total_tokens": 5499984} {"current_steps": 9020, "total_steps": 64460, "loss": 0.2283, "lr": 9.95154361875563e-06, "epoch": 2.7986348122866893, "percentage": 13.99, "elapsed_time": "0:16:17", "remaining_time": "1:40:05", "throughput": 5632.13, "total_tokens": 5502704} {"current_steps": 9025, "total_steps": 64460, "loss": 0.2288, "lr": 9.951355415638689e-06, "epoch": 2.800186161960906, "percentage": 14.0, "elapsed_time": "0:16:17", "remaining_time": "1:40:04", "throughput": 5631.54, "total_tokens": 5505008} {"current_steps": 9030, "total_steps": 64460, "loss": 0.2179, "lr": 9.95116684952876e-06, "epoch": 2.8017375116351224, "percentage": 14.01, "elapsed_time": "0:16:17", "remaining_time": "1:40:03", "throughput": 5631.64, "total_tokens": 5507728} {"current_steps": 9035, "total_steps": 64460, "loss": 0.2223, "lr": 9.95097792043967e-06, "epoch": 2.803288861309339, "percentage": 14.02, "elapsed_time": "0:16:18", "remaining_time": "1:40:02", "throughput": 5630.47, "total_tokens": 5509776} {"current_steps": 9040, "total_steps": 64460, "loss": 0.2411, "lr": 9.950788628385273e-06, "epoch": 2.8048402109835555, "percentage": 14.02, "elapsed_time": "0:16:19", "remaining_time": "1:40:02", "throughput": 5630.53, "total_tokens": 5512752} {"current_steps": 9045, "total_steps": 64460, "loss": 0.2321, "lr": 9.950598973379442e-06, "epoch": 2.8063915606577723, "percentage": 14.03, "elapsed_time": "0:16:19", "remaining_time": "1:40:01", "throughput": 5630.77, "total_tokens": 5516112} {"current_steps": 9050, "total_steps": 64460, "loss": 0.2279, "lr": 9.950408955436082e-06, "epoch": 2.807942910331989, "percentage": 14.04, "elapsed_time": "0:16:20", "remaining_time": "1:40:00", "throughput": 5630.38, "total_tokens": 5518448} {"current_steps": 9055, "total_steps": 64460, "loss": 0.2079, "lr": 9.950218574569124e-06, "epoch": 2.8094942600062054, "percentage": 14.05, "elapsed_time": "0:16:20", "remaining_time": "1:40:00", "throughput": 5630.62, "total_tokens": 5521520} {"current_steps": 9060, "total_steps": 64460, "loss": 0.2492, "lr": 9.950027830792526e-06, "epoch": 2.8110456096804217, "percentage": 14.06, "elapsed_time": "0:16:21", "remaining_time": "1:40:00", "throughput": 5630.9, "total_tokens": 5525520} {"current_steps": 9065, "total_steps": 64460, "loss": 0.2366, "lr": 9.94983672412027e-06, "epoch": 2.8125969593546385, "percentage": 14.06, "elapsed_time": "0:16:21", "remaining_time": "1:39:59", "throughput": 5630.41, "total_tokens": 5527696} {"current_steps": 9070, "total_steps": 64460, "loss": 0.2458, "lr": 9.949645254566367e-06, "epoch": 2.8141483090288553, "percentage": 14.07, "elapsed_time": "0:16:22", "remaining_time": "1:39:59", "throughput": 5631.17, "total_tokens": 5531952} {"current_steps": 9075, "total_steps": 64460, "loss": 0.2343, "lr": 9.949453422144855e-06, "epoch": 2.8156996587030716, "percentage": 14.08, "elapsed_time": "0:16:22", "remaining_time": "1:39:58", "throughput": 5631.3, "total_tokens": 5535120} {"current_steps": 9080, "total_steps": 64460, "loss": 0.2249, "lr": 9.949261226869797e-06, "epoch": 2.8172510083772884, "percentage": 14.09, "elapsed_time": "0:16:23", "remaining_time": "1:39:57", "throughput": 5630.63, "total_tokens": 5537264} {"current_steps": 9085, "total_steps": 64460, "loss": 0.2313, "lr": 9.949068668755282e-06, "epoch": 2.8188023580515047, "percentage": 14.09, "elapsed_time": "0:16:23", "remaining_time": "1:39:56", "throughput": 5630.3, "total_tokens": 5539568} {"current_steps": 9090, "total_steps": 64460, "loss": 0.2514, "lr": 9.94887574781543e-06, "epoch": 2.8203537077257215, "percentage": 14.1, "elapsed_time": "0:16:24", "remaining_time": "1:39:56", "throughput": 5630.34, "total_tokens": 5542288} {"current_steps": 9095, "total_steps": 64460, "loss": 0.2321, "lr": 9.94868246406438e-06, "epoch": 2.821905057399938, "percentage": 14.11, "elapsed_time": "0:16:24", "remaining_time": "1:39:55", "throughput": 5630.19, "total_tokens": 5545040} {"current_steps": 9100, "total_steps": 64460, "loss": 0.2274, "lr": 9.948488817516304e-06, "epoch": 2.8234564070741546, "percentage": 14.12, "elapsed_time": "0:16:25", "remaining_time": "1:39:55", "throughput": 5630.58, "total_tokens": 5549072} {"current_steps": 9105, "total_steps": 64460, "loss": 0.2579, "lr": 9.9482948081854e-06, "epoch": 2.825007756748371, "percentage": 14.13, "elapsed_time": "0:16:25", "remaining_time": "1:39:54", "throughput": 5630.64, "total_tokens": 5551792} {"current_steps": 9110, "total_steps": 64460, "loss": 0.2313, "lr": 9.94810043608589e-06, "epoch": 2.8265591064225877, "percentage": 14.13, "elapsed_time": "0:16:26", "remaining_time": "1:39:54", "throughput": 5630.84, "total_tokens": 5555152} {"current_steps": 9115, "total_steps": 64460, "loss": 0.2393, "lr": 9.947905701232023e-06, "epoch": 2.8281104560968044, "percentage": 14.14, "elapsed_time": "0:16:27", "remaining_time": "1:39:53", "throughput": 5630.65, "total_tokens": 5557936} {"current_steps": 9120, "total_steps": 64460, "loss": 0.2288, "lr": 9.947710603638078e-06, "epoch": 2.8296618057710208, "percentage": 14.15, "elapsed_time": "0:16:27", "remaining_time": "1:39:52", "throughput": 5630.07, "total_tokens": 5559984} {"current_steps": 9125, "total_steps": 64460, "loss": 0.232, "lr": 9.947515143318354e-06, "epoch": 2.831213155445237, "percentage": 14.16, "elapsed_time": "0:16:28", "remaining_time": "1:39:51", "throughput": 5629.88, "total_tokens": 5562448} {"current_steps": 9130, "total_steps": 64460, "loss": 0.2354, "lr": 9.947319320287183e-06, "epoch": 2.832764505119454, "percentage": 14.16, "elapsed_time": "0:16:28", "remaining_time": "1:39:50", "throughput": 5629.61, "total_tokens": 5565200} {"current_steps": 9135, "total_steps": 64460, "loss": 0.2285, "lr": 9.947123134558922e-06, "epoch": 2.8343158547936707, "percentage": 14.17, "elapsed_time": "0:16:29", "remaining_time": "1:39:50", "throughput": 5629.41, "total_tokens": 5567792} {"current_steps": 9140, "total_steps": 64460, "loss": 0.227, "lr": 9.946926586147952e-06, "epoch": 2.835867204467887, "percentage": 14.18, "elapsed_time": "0:16:29", "remaining_time": "1:39:49", "throughput": 5629.9, "total_tokens": 5571184} {"current_steps": 9145, "total_steps": 64460, "loss": 0.215, "lr": 9.946729675068683e-06, "epoch": 2.8374185541421038, "percentage": 14.19, "elapsed_time": "0:16:30", "remaining_time": "1:39:48", "throughput": 5629.24, "total_tokens": 5573328} {"current_steps": 9150, "total_steps": 64460, "loss": 0.2354, "lr": 9.946532401335548e-06, "epoch": 2.83896990381632, "percentage": 14.19, "elapsed_time": "0:16:30", "remaining_time": "1:39:47", "throughput": 5629.21, "total_tokens": 5576208} {"current_steps": 9155, "total_steps": 64460, "loss": 0.2363, "lr": 9.946334764963017e-06, "epoch": 2.840521253490537, "percentage": 14.2, "elapsed_time": "0:16:31", "remaining_time": "1:39:47", "throughput": 5629.11, "total_tokens": 5579056} {"current_steps": 9160, "total_steps": 64460, "loss": 0.2413, "lr": 9.946136765965572e-06, "epoch": 2.842072603164753, "percentage": 14.21, "elapsed_time": "0:16:31", "remaining_time": "1:39:46", "throughput": 5629.03, "total_tokens": 5581648} {"current_steps": 9165, "total_steps": 64460, "loss": 0.228, "lr": 9.945938404357732e-06, "epoch": 2.84362395283897, "percentage": 14.22, "elapsed_time": "0:16:32", "remaining_time": "1:39:46", "throughput": 5629.29, "total_tokens": 5585360} {"current_steps": 9170, "total_steps": 64460, "loss": 0.2348, "lr": 9.945739680154037e-06, "epoch": 2.8451753025131863, "percentage": 14.23, "elapsed_time": "0:16:32", "remaining_time": "1:39:45", "throughput": 5628.88, "total_tokens": 5587920} {"current_steps": 9175, "total_steps": 64460, "loss": 0.2339, "lr": 9.945540593369056e-06, "epoch": 2.846726652187403, "percentage": 14.23, "elapsed_time": "0:16:33", "remaining_time": "1:39:45", "throughput": 5629.27, "total_tokens": 5591344} {"current_steps": 9180, "total_steps": 64460, "loss": 0.2337, "lr": 9.945341144017387e-06, "epoch": 2.84827800186162, "percentage": 14.24, "elapsed_time": "0:16:33", "remaining_time": "1:39:44", "throughput": 5629.47, "total_tokens": 5594224} {"current_steps": 9185, "total_steps": 64460, "loss": 0.2265, "lr": 9.945141332113651e-06, "epoch": 2.849829351535836, "percentage": 14.25, "elapsed_time": "0:16:34", "remaining_time": "1:39:43", "throughput": 5629.39, "total_tokens": 5597072} {"current_steps": 9190, "total_steps": 64460, "loss": 0.2326, "lr": 9.944941157672497e-06, "epoch": 2.8513807012100525, "percentage": 14.26, "elapsed_time": "0:16:34", "remaining_time": "1:39:42", "throughput": 5629.41, "total_tokens": 5599856} {"current_steps": 9195, "total_steps": 64460, "loss": 0.2332, "lr": 9.944740620708597e-06, "epoch": 2.8529320508842693, "percentage": 14.26, "elapsed_time": "0:16:35", "remaining_time": "1:39:41", "throughput": 5628.52, "total_tokens": 5601680} {"current_steps": 9200, "total_steps": 64460, "loss": 0.2275, "lr": 9.944539721236655e-06, "epoch": 2.854483400558486, "percentage": 14.27, "elapsed_time": "0:16:35", "remaining_time": "1:39:41", "throughput": 5628.68, "total_tokens": 5604944} {"current_steps": 9205, "total_steps": 64460, "loss": 0.2316, "lr": 9.944338459271401e-06, "epoch": 2.8560347502327024, "percentage": 14.28, "elapsed_time": "0:16:36", "remaining_time": "1:39:41", "throughput": 5629.57, "total_tokens": 5609328} {"current_steps": 9210, "total_steps": 64460, "loss": 0.2367, "lr": 9.944136834827587e-06, "epoch": 2.857586099906919, "percentage": 14.29, "elapsed_time": "0:16:36", "remaining_time": "1:39:40", "throughput": 5629.56, "total_tokens": 5612528} {"current_steps": 9215, "total_steps": 64460, "loss": 0.2314, "lr": 9.943934847919995e-06, "epoch": 2.8591374495811355, "percentage": 14.3, "elapsed_time": "0:16:37", "remaining_time": "1:39:39", "throughput": 5629.41, "total_tokens": 5615120} {"current_steps": 9220, "total_steps": 64460, "loss": 0.2347, "lr": 9.943732498563437e-06, "epoch": 2.8606887992553522, "percentage": 14.3, "elapsed_time": "0:16:37", "remaining_time": "1:39:39", "throughput": 5629.15, "total_tokens": 5617776} {"current_steps": 9225, "total_steps": 64460, "loss": 0.2304, "lr": 9.943529786772741e-06, "epoch": 2.8622401489295686, "percentage": 14.31, "elapsed_time": "0:16:38", "remaining_time": "1:39:38", "throughput": 5629.25, "total_tokens": 5620848} {"current_steps": 9230, "total_steps": 64460, "loss": 0.232, "lr": 9.943326712562773e-06, "epoch": 2.8637914986037853, "percentage": 14.32, "elapsed_time": "0:16:39", "remaining_time": "1:39:37", "throughput": 5629.35, "total_tokens": 5623824} {"current_steps": 9235, "total_steps": 64460, "loss": 0.232, "lr": 9.943123275948419e-06, "epoch": 2.8653428482780017, "percentage": 14.33, "elapsed_time": "0:16:39", "remaining_time": "1:39:36", "throughput": 5629.11, "total_tokens": 5626256} {"current_steps": 9240, "total_steps": 64460, "loss": 0.2315, "lr": 9.942919476944594e-06, "epoch": 2.8668941979522184, "percentage": 14.33, "elapsed_time": "0:16:40", "remaining_time": "1:39:36", "throughput": 5629.49, "total_tokens": 5629552} {"current_steps": 9245, "total_steps": 64460, "loss": 0.2298, "lr": 9.942715315566238e-06, "epoch": 2.868445547626435, "percentage": 14.34, "elapsed_time": "0:16:40", "remaining_time": "1:39:35", "throughput": 5629.83, "total_tokens": 5632880} {"current_steps": 9250, "total_steps": 64460, "loss": 0.2296, "lr": 9.942510791828318e-06, "epoch": 2.8699968973006516, "percentage": 14.35, "elapsed_time": "0:16:41", "remaining_time": "1:39:35", "throughput": 5629.24, "total_tokens": 5635376} {"current_steps": 9255, "total_steps": 64460, "loss": 0.2323, "lr": 9.94230590574583e-06, "epoch": 2.871548246974868, "percentage": 14.36, "elapsed_time": "0:16:41", "remaining_time": "1:39:34", "throughput": 5629.33, "total_tokens": 5638288} {"current_steps": 9260, "total_steps": 64460, "loss": 0.2338, "lr": 9.942100657333792e-06, "epoch": 2.8730995966490847, "percentage": 14.37, "elapsed_time": "0:16:42", "remaining_time": "1:39:33", "throughput": 5629.54, "total_tokens": 5641616} {"current_steps": 9265, "total_steps": 64460, "loss": 0.2303, "lr": 9.941895046607255e-06, "epoch": 2.8746509463233014, "percentage": 14.37, "elapsed_time": "0:16:42", "remaining_time": "1:39:33", "throughput": 5629.3, "total_tokens": 5644432} {"current_steps": 9270, "total_steps": 64460, "loss": 0.2292, "lr": 9.94168907358129e-06, "epoch": 2.8762022959975178, "percentage": 14.38, "elapsed_time": "0:16:43", "remaining_time": "1:39:32", "throughput": 5629.24, "total_tokens": 5647344} {"current_steps": 9275, "total_steps": 64460, "loss": 0.2347, "lr": 9.941482738270995e-06, "epoch": 2.8777536456717345, "percentage": 14.39, "elapsed_time": "0:16:43", "remaining_time": "1:39:32", "throughput": 5629.26, "total_tokens": 5650576} {"current_steps": 9280, "total_steps": 64460, "loss": 0.2418, "lr": 9.9412760406915e-06, "epoch": 2.879304995345951, "percentage": 14.4, "elapsed_time": "0:16:44", "remaining_time": "1:39:31", "throughput": 5629.7, "total_tokens": 5654192} {"current_steps": 9285, "total_steps": 64460, "loss": 0.2291, "lr": 9.941068980857959e-06, "epoch": 2.8808563450201676, "percentage": 14.4, "elapsed_time": "0:16:44", "remaining_time": "1:39:32", "throughput": 5630.32, "total_tokens": 5658416} {"current_steps": 9290, "total_steps": 64460, "loss": 0.231, "lr": 9.94086155878555e-06, "epoch": 2.882407694694384, "percentage": 14.41, "elapsed_time": "0:16:45", "remaining_time": "1:39:31", "throughput": 5629.93, "total_tokens": 5660816} {"current_steps": 9295, "total_steps": 64460, "loss": 0.2273, "lr": 9.940653774489482e-06, "epoch": 2.8839590443686007, "percentage": 14.42, "elapsed_time": "0:16:46", "remaining_time": "1:39:30", "throughput": 5630.13, "total_tokens": 5664304} {"current_steps": 9300, "total_steps": 64460, "loss": 0.2306, "lr": 9.940445627984984e-06, "epoch": 2.885510394042817, "percentage": 14.43, "elapsed_time": "0:16:46", "remaining_time": "1:39:30", "throughput": 5629.82, "total_tokens": 5666800} {"current_steps": 9305, "total_steps": 64460, "loss": 0.2343, "lr": 9.940237119287318e-06, "epoch": 2.887061743717034, "percentage": 14.44, "elapsed_time": "0:16:47", "remaining_time": "1:39:29", "throughput": 5629.52, "total_tokens": 5669296} {"current_steps": 9310, "total_steps": 64460, "loss": 0.229, "lr": 9.940028248411771e-06, "epoch": 2.8886130933912506, "percentage": 14.44, "elapsed_time": "0:16:47", "remaining_time": "1:39:29", "throughput": 5630.22, "total_tokens": 5673296} {"current_steps": 9315, "total_steps": 64460, "loss": 0.2338, "lr": 9.939819015373654e-06, "epoch": 2.890164443065467, "percentage": 14.45, "elapsed_time": "0:16:48", "remaining_time": "1:39:28", "throughput": 5630.24, "total_tokens": 5676016} {"current_steps": 9320, "total_steps": 64460, "loss": 0.2358, "lr": 9.939609420188307e-06, "epoch": 2.8917157927396833, "percentage": 14.46, "elapsed_time": "0:16:48", "remaining_time": "1:39:27", "throughput": 5629.94, "total_tokens": 5678448} {"current_steps": 9325, "total_steps": 64460, "loss": 0.2327, "lr": 9.939399462871095e-06, "epoch": 2.8932671424139, "percentage": 14.47, "elapsed_time": "0:16:49", "remaining_time": "1:39:26", "throughput": 5629.67, "total_tokens": 5680944} {"current_steps": 9330, "total_steps": 64460, "loss": 0.2315, "lr": 9.939189143437413e-06, "epoch": 2.894818492088117, "percentage": 14.47, "elapsed_time": "0:16:49", "remaining_time": "1:39:25", "throughput": 5630.03, "total_tokens": 5684240} {"current_steps": 9335, "total_steps": 64460, "loss": 0.2345, "lr": 9.938978461902678e-06, "epoch": 2.896369841762333, "percentage": 14.48, "elapsed_time": "0:16:50", "remaining_time": "1:39:25", "throughput": 5630.15, "total_tokens": 5687472} {"current_steps": 9340, "total_steps": 64460, "loss": 0.2309, "lr": 9.938767418282334e-06, "epoch": 2.89792119143655, "percentage": 14.49, "elapsed_time": "0:16:50", "remaining_time": "1:39:24", "throughput": 5629.83, "total_tokens": 5689872} {"current_steps": 9345, "total_steps": 64460, "loss": 0.2318, "lr": 9.938556012591856e-06, "epoch": 2.8994725411107662, "percentage": 14.5, "elapsed_time": "0:16:51", "remaining_time": "1:39:25", "throughput": 5630.59, "total_tokens": 5695088} {"current_steps": 9350, "total_steps": 64460, "loss": 0.2374, "lr": 9.93834424484674e-06, "epoch": 2.901023890784983, "percentage": 14.51, "elapsed_time": "0:16:51", "remaining_time": "1:39:24", "throughput": 5630.56, "total_tokens": 5698000} {"current_steps": 9355, "total_steps": 64460, "loss": 0.2325, "lr": 9.93813211506251e-06, "epoch": 2.9025752404591993, "percentage": 14.51, "elapsed_time": "0:16:52", "remaining_time": "1:39:23", "throughput": 5630.31, "total_tokens": 5700528} {"current_steps": 9360, "total_steps": 64460, "loss": 0.232, "lr": 9.937919623254724e-06, "epoch": 2.904126590133416, "percentage": 14.52, "elapsed_time": "0:16:52", "remaining_time": "1:39:23", "throughput": 5629.93, "total_tokens": 5702992} {"current_steps": 9365, "total_steps": 64460, "loss": 0.2299, "lr": 9.937706769438954e-06, "epoch": 2.9056779398076324, "percentage": 14.53, "elapsed_time": "0:16:53", "remaining_time": "1:39:22", "throughput": 5630.26, "total_tokens": 5706512} {"current_steps": 9370, "total_steps": 64460, "loss": 0.233, "lr": 9.937493553630806e-06, "epoch": 2.907229289481849, "percentage": 14.54, "elapsed_time": "0:16:54", "remaining_time": "1:39:22", "throughput": 5630.44, "total_tokens": 5709840} {"current_steps": 9375, "total_steps": 64460, "loss": 0.2283, "lr": 9.937279975845913e-06, "epoch": 2.908780639156066, "percentage": 14.54, "elapsed_time": "0:16:54", "remaining_time": "1:39:21", "throughput": 5630.39, "total_tokens": 5712432} {"current_steps": 9380, "total_steps": 64460, "loss": 0.2279, "lr": 9.93706603609993e-06, "epoch": 2.9103319888302823, "percentage": 14.55, "elapsed_time": "0:16:55", "remaining_time": "1:39:20", "throughput": 5630.17, "total_tokens": 5714928} {"current_steps": 9385, "total_steps": 64460, "loss": 0.2224, "lr": 9.936851734408544e-06, "epoch": 2.9118833385044987, "percentage": 14.56, "elapsed_time": "0:16:55", "remaining_time": "1:39:19", "throughput": 5629.98, "total_tokens": 5717808} {"current_steps": 9390, "total_steps": 64460, "loss": 0.245, "lr": 9.936637070787465e-06, "epoch": 2.9134346881787154, "percentage": 14.57, "elapsed_time": "0:16:56", "remaining_time": "1:39:19", "throughput": 5630.13, "total_tokens": 5720944} {"current_steps": 9395, "total_steps": 64460, "loss": 0.2275, "lr": 9.936422045252429e-06, "epoch": 2.914986037852932, "percentage": 14.57, "elapsed_time": "0:16:56", "remaining_time": "1:39:18", "throughput": 5630.01, "total_tokens": 5723696} {"current_steps": 9400, "total_steps": 64460, "loss": 0.2307, "lr": 9.936206657819203e-06, "epoch": 2.9165373875271485, "percentage": 14.58, "elapsed_time": "0:16:57", "remaining_time": "1:39:17", "throughput": 5629.46, "total_tokens": 5725872} {"current_steps": 9405, "total_steps": 64460, "loss": 0.2336, "lr": 9.935990908503574e-06, "epoch": 2.9180887372013653, "percentage": 14.59, "elapsed_time": "0:16:57", "remaining_time": "1:39:17", "throughput": 5630.08, "total_tokens": 5729712} {"current_steps": 9410, "total_steps": 64460, "loss": 0.2382, "lr": 9.93577479732136e-06, "epoch": 2.9196400868755816, "percentage": 14.6, "elapsed_time": "0:16:58", "remaining_time": "1:39:16", "throughput": 5629.86, "total_tokens": 5732208} {"current_steps": 9415, "total_steps": 64460, "loss": 0.226, "lr": 9.935558324288407e-06, "epoch": 2.9211914365497984, "percentage": 14.61, "elapsed_time": "0:16:58", "remaining_time": "1:39:15", "throughput": 5629.28, "total_tokens": 5734416} {"current_steps": 9420, "total_steps": 64460, "loss": 0.2273, "lr": 9.935341489420582e-06, "epoch": 2.9227427862240147, "percentage": 14.61, "elapsed_time": "0:16:59", "remaining_time": "1:39:16", "throughput": 5630.07, "total_tokens": 5739088} {"current_steps": 9425, "total_steps": 64460, "loss": 0.2422, "lr": 9.935124292733785e-06, "epoch": 2.9242941358982315, "percentage": 14.62, "elapsed_time": "0:16:59", "remaining_time": "1:39:15", "throughput": 5630.22, "total_tokens": 5741968} {"current_steps": 9430, "total_steps": 64460, "loss": 0.2314, "lr": 9.934906734243932e-06, "epoch": 2.925845485572448, "percentage": 14.63, "elapsed_time": "0:17:00", "remaining_time": "1:39:14", "throughput": 5630.41, "total_tokens": 5744880} {"current_steps": 9435, "total_steps": 64460, "loss": 0.2326, "lr": 9.934688813966982e-06, "epoch": 2.9273968352466646, "percentage": 14.64, "elapsed_time": "0:17:01", "remaining_time": "1:39:14", "throughput": 5631.08, "total_tokens": 5749392} {"current_steps": 9440, "total_steps": 64460, "loss": 0.2257, "lr": 9.934470531918902e-06, "epoch": 2.9289481849208814, "percentage": 14.64, "elapsed_time": "0:17:01", "remaining_time": "1:39:14", "throughput": 5631.0, "total_tokens": 5752688} {"current_steps": 9445, "total_steps": 64460, "loss": 0.2328, "lr": 9.934251888115702e-06, "epoch": 2.9304995345950977, "percentage": 14.65, "elapsed_time": "0:17:02", "remaining_time": "1:39:13", "throughput": 5631.31, "total_tokens": 5755984} {"current_steps": 9450, "total_steps": 64460, "loss": 0.2242, "lr": 9.934032882573409e-06, "epoch": 2.932050884269314, "percentage": 14.66, "elapsed_time": "0:17:02", "remaining_time": "1:39:12", "throughput": 5631.43, "total_tokens": 5758928} {"current_steps": 9455, "total_steps": 64460, "loss": 0.2251, "lr": 9.933813515308077e-06, "epoch": 2.933602233943531, "percentage": 14.67, "elapsed_time": "0:17:03", "remaining_time": "1:39:12", "throughput": 5631.53, "total_tokens": 5761936} {"current_steps": 9460, "total_steps": 64460, "loss": 0.2315, "lr": 9.93359378633579e-06, "epoch": 2.9351535836177476, "percentage": 14.68, "elapsed_time": "0:17:03", "remaining_time": "1:39:11", "throughput": 5631.34, "total_tokens": 5764720} {"current_steps": 9465, "total_steps": 64460, "loss": 0.2424, "lr": 9.933373695672654e-06, "epoch": 2.936704933291964, "percentage": 14.68, "elapsed_time": "0:17:04", "remaining_time": "1:39:10", "throughput": 5631.2, "total_tokens": 5767344} {"current_steps": 9470, "total_steps": 64460, "loss": 0.2292, "lr": 9.933153243334808e-06, "epoch": 2.9382562829661807, "percentage": 14.69, "elapsed_time": "0:17:04", "remaining_time": "1:39:10", "throughput": 5631.55, "total_tokens": 5770608} {"current_steps": 9475, "total_steps": 64460, "loss": 0.2331, "lr": 9.932932429338411e-06, "epoch": 2.939807632640397, "percentage": 14.7, "elapsed_time": "0:17:05", "remaining_time": "1:39:09", "throughput": 5631.17, "total_tokens": 5773200} {"current_steps": 9480, "total_steps": 64460, "loss": 0.2321, "lr": 9.932711253699652e-06, "epoch": 2.941358982314614, "percentage": 14.71, "elapsed_time": "0:17:05", "remaining_time": "1:39:09", "throughput": 5631.58, "total_tokens": 5776720} {"current_steps": 9485, "total_steps": 64460, "loss": 0.2309, "lr": 9.932489716434746e-06, "epoch": 2.94291033198883, "percentage": 14.71, "elapsed_time": "0:17:06", "remaining_time": "1:39:08", "throughput": 5631.7, "total_tokens": 5779856} {"current_steps": 9490, "total_steps": 64460, "loss": 0.2287, "lr": 9.932267817559936e-06, "epoch": 2.944461681663047, "percentage": 14.72, "elapsed_time": "0:17:06", "remaining_time": "1:39:07", "throughput": 5631.49, "total_tokens": 5782544} {"current_steps": 9495, "total_steps": 64460, "loss": 0.2348, "lr": 9.932045557091488e-06, "epoch": 2.946013031337263, "percentage": 14.73, "elapsed_time": "0:17:07", "remaining_time": "1:39:06", "throughput": 5631.36, "total_tokens": 5785040} {"current_steps": 9500, "total_steps": 64460, "loss": 0.2285, "lr": 9.931822935045693e-06, "epoch": 2.94756438101148, "percentage": 14.74, "elapsed_time": "0:17:07", "remaining_time": "1:39:06", "throughput": 5631.7, "total_tokens": 5788496} {"current_steps": 9505, "total_steps": 64460, "loss": 0.2336, "lr": 9.93159995143888e-06, "epoch": 2.9491157306856968, "percentage": 14.75, "elapsed_time": "0:17:08", "remaining_time": "1:39:05", "throughput": 5631.8, "total_tokens": 5791504} {"current_steps": 9510, "total_steps": 64460, "loss": 0.2289, "lr": 9.931376606287388e-06, "epoch": 2.950667080359913, "percentage": 14.75, "elapsed_time": "0:17:08", "remaining_time": "1:39:05", "throughput": 5632.1, "total_tokens": 5795120} {"current_steps": 9515, "total_steps": 64460, "loss": 0.2273, "lr": 9.931152899607597e-06, "epoch": 2.9522184300341294, "percentage": 14.76, "elapsed_time": "0:17:09", "remaining_time": "1:39:04", "throughput": 5631.85, "total_tokens": 5797968} {"current_steps": 9520, "total_steps": 64460, "loss": 0.2321, "lr": 9.930928831415904e-06, "epoch": 2.953769779708346, "percentage": 14.77, "elapsed_time": "0:17:09", "remaining_time": "1:39:03", "throughput": 5631.54, "total_tokens": 5800336} {"current_steps": 9525, "total_steps": 64460, "loss": 0.2331, "lr": 9.930704401728737e-06, "epoch": 2.955321129382563, "percentage": 14.78, "elapsed_time": "0:17:10", "remaining_time": "1:39:03", "throughput": 5632.04, "total_tokens": 5803888} {"current_steps": 9530, "total_steps": 64460, "loss": 0.2336, "lr": 9.93047961056255e-06, "epoch": 2.9568724790567793, "percentage": 14.78, "elapsed_time": "0:17:11", "remaining_time": "1:39:02", "throughput": 5632.06, "total_tokens": 5806800} {"current_steps": 9535, "total_steps": 64460, "loss": 0.2346, "lr": 9.93025445793382e-06, "epoch": 2.958423828730996, "percentage": 14.79, "elapsed_time": "0:17:11", "remaining_time": "1:39:01", "throughput": 5632.0, "total_tokens": 5809456} {"current_steps": 9540, "total_steps": 64460, "loss": 0.2319, "lr": 9.930028943859055e-06, "epoch": 2.9599751784052124, "percentage": 14.8, "elapsed_time": "0:17:12", "remaining_time": "1:39:01", "throughput": 5632.29, "total_tokens": 5812784} {"current_steps": 9545, "total_steps": 64460, "loss": 0.2335, "lr": 9.92980306835479e-06, "epoch": 2.961526528079429, "percentage": 14.81, "elapsed_time": "0:17:12", "remaining_time": "1:39:00", "throughput": 5632.11, "total_tokens": 5815504} {"current_steps": 9550, "total_steps": 64460, "loss": 0.2304, "lr": 9.929576831437582e-06, "epoch": 2.9630778777536455, "percentage": 14.82, "elapsed_time": "0:17:13", "remaining_time": "1:39:00", "throughput": 5632.33, "total_tokens": 5818928} {"current_steps": 9555, "total_steps": 64460, "loss": 0.2287, "lr": 9.929350233124018e-06, "epoch": 2.9646292274278623, "percentage": 14.82, "elapsed_time": "0:17:13", "remaining_time": "1:38:59", "throughput": 5632.54, "total_tokens": 5822064} {"current_steps": 9560, "total_steps": 64460, "loss": 0.2281, "lr": 9.929123273430708e-06, "epoch": 2.9661805771020786, "percentage": 14.83, "elapsed_time": "0:17:14", "remaining_time": "1:38:59", "throughput": 5632.97, "total_tokens": 5825712} {"current_steps": 9565, "total_steps": 64460, "loss": 0.2441, "lr": 9.928895952374293e-06, "epoch": 2.9677319267762954, "percentage": 14.84, "elapsed_time": "0:17:14", "remaining_time": "1:38:58", "throughput": 5632.51, "total_tokens": 5828176} {"current_steps": 9570, "total_steps": 64460, "loss": 0.2325, "lr": 9.928668269971438e-06, "epoch": 2.969283276450512, "percentage": 14.85, "elapsed_time": "0:17:15", "remaining_time": "1:38:57", "throughput": 5631.9, "total_tokens": 5830480} {"current_steps": 9575, "total_steps": 64460, "loss": 0.2348, "lr": 9.928440226238835e-06, "epoch": 2.9708346261247285, "percentage": 14.85, "elapsed_time": "0:17:15", "remaining_time": "1:38:57", "throughput": 5631.47, "total_tokens": 5832784} {"current_steps": 9580, "total_steps": 64460, "loss": 0.2321, "lr": 9.9282118211932e-06, "epoch": 2.972385975798945, "percentage": 14.86, "elapsed_time": "0:17:16", "remaining_time": "1:38:56", "throughput": 5631.5, "total_tokens": 5835472} {"current_steps": 9585, "total_steps": 64460, "loss": 0.2311, "lr": 9.927983054851283e-06, "epoch": 2.9739373254731616, "percentage": 14.87, "elapsed_time": "0:17:16", "remaining_time": "1:38:55", "throughput": 5631.39, "total_tokens": 5838096} {"current_steps": 9590, "total_steps": 64460, "loss": 0.2222, "lr": 9.92775392722985e-06, "epoch": 2.9754886751473784, "percentage": 14.88, "elapsed_time": "0:17:17", "remaining_time": "1:38:55", "throughput": 5631.62, "total_tokens": 5841936} {"current_steps": 9595, "total_steps": 64460, "loss": 0.2263, "lr": 9.927524438345701e-06, "epoch": 2.9770400248215947, "percentage": 14.89, "elapsed_time": "0:17:17", "remaining_time": "1:38:54", "throughput": 5631.63, "total_tokens": 5844624} {"current_steps": 9600, "total_steps": 64460, "loss": 0.229, "lr": 9.927294588215661e-06, "epoch": 2.9785913744958115, "percentage": 14.89, "elapsed_time": "0:17:18", "remaining_time": "1:38:53", "throughput": 5631.34, "total_tokens": 5846992} {"current_steps": 9605, "total_steps": 64460, "loss": 0.2351, "lr": 9.92706437685658e-06, "epoch": 2.980142724170028, "percentage": 14.9, "elapsed_time": "0:17:18", "remaining_time": "1:38:53", "throughput": 5631.13, "total_tokens": 5850000} {"current_steps": 9610, "total_steps": 64460, "loss": 0.2553, "lr": 9.926833804285332e-06, "epoch": 2.9816940738442446, "percentage": 14.91, "elapsed_time": "0:17:19", "remaining_time": "1:38:52", "throughput": 5631.73, "total_tokens": 5853968} {"current_steps": 9615, "total_steps": 64460, "loss": 0.2304, "lr": 9.926602870518826e-06, "epoch": 2.9832454235184613, "percentage": 14.92, "elapsed_time": "0:17:19", "remaining_time": "1:38:52", "throughput": 5631.55, "total_tokens": 5856656} {"current_steps": 9620, "total_steps": 64460, "loss": 0.2266, "lr": 9.92637157557399e-06, "epoch": 2.9847967731926777, "percentage": 14.92, "elapsed_time": "0:17:20", "remaining_time": "1:38:51", "throughput": 5631.93, "total_tokens": 5860496} {"current_steps": 9625, "total_steps": 64460, "loss": 0.2358, "lr": 9.926139919467781e-06, "epoch": 2.986348122866894, "percentage": 14.93, "elapsed_time": "0:17:21", "remaining_time": "1:38:51", "throughput": 5631.93, "total_tokens": 5863312} {"current_steps": 9630, "total_steps": 64460, "loss": 0.2326, "lr": 9.92590790221718e-06, "epoch": 2.9878994725411108, "percentage": 14.94, "elapsed_time": "0:17:21", "remaining_time": "1:38:50", "throughput": 5632.14, "total_tokens": 5866288} {"current_steps": 9635, "total_steps": 64460, "loss": 0.2302, "lr": 9.9256755238392e-06, "epoch": 2.9894508222153275, "percentage": 14.95, "elapsed_time": "0:17:22", "remaining_time": "1:38:49", "throughput": 5632.19, "total_tokens": 5869200} {"current_steps": 9640, "total_steps": 64460, "loss": 0.2316, "lr": 9.925442784350874e-06, "epoch": 2.991002171889544, "percentage": 14.96, "elapsed_time": "0:17:22", "remaining_time": "1:38:48", "throughput": 5631.87, "total_tokens": 5871472} {"current_steps": 9645, "total_steps": 64460, "loss": 0.2284, "lr": 9.925209683769267e-06, "epoch": 2.99255352156376, "percentage": 14.96, "elapsed_time": "0:17:23", "remaining_time": "1:38:48", "throughput": 5632.02, "total_tokens": 5874800} {"current_steps": 9650, "total_steps": 64460, "loss": 0.2301, "lr": 9.924976222111466e-06, "epoch": 2.994104871237977, "percentage": 14.97, "elapsed_time": "0:17:23", "remaining_time": "1:38:48", "throughput": 5632.22, "total_tokens": 5878736} {"current_steps": 9655, "total_steps": 64460, "loss": 0.2237, "lr": 9.92474239939459e-06, "epoch": 2.9956562209121937, "percentage": 14.98, "elapsed_time": "0:17:24", "remaining_time": "1:38:48", "throughput": 5632.66, "total_tokens": 5882608} {"current_steps": 9660, "total_steps": 64460, "loss": 0.2303, "lr": 9.924508215635776e-06, "epoch": 2.99720757058641, "percentage": 14.99, "elapsed_time": "0:17:24", "remaining_time": "1:38:47", "throughput": 5632.86, "total_tokens": 5885616} {"current_steps": 9665, "total_steps": 64460, "loss": 0.2196, "lr": 9.924273670852193e-06, "epoch": 2.998758920260627, "percentage": 14.99, "elapsed_time": "0:17:25", "remaining_time": "1:38:46", "throughput": 5633.03, "total_tokens": 5888944} {"current_steps": 9670, "total_steps": 64460, "loss": 0.2325, "lr": 9.924038765061042e-06, "epoch": 3.000310269934843, "percentage": 15.0, "elapsed_time": "0:17:26", "remaining_time": "1:38:47", "throughput": 5631.67, "total_tokens": 5891664} {"current_steps": 9675, "total_steps": 64460, "loss": 0.2326, "lr": 9.923803498279536e-06, "epoch": 3.00186161960906, "percentage": 15.01, "elapsed_time": "0:17:26", "remaining_time": "1:38:47", "throughput": 5631.49, "total_tokens": 5894544} {"current_steps": 9680, "total_steps": 64460, "loss": 0.2271, "lr": 9.92356787052493e-06, "epoch": 3.0034129692832763, "percentage": 15.02, "elapsed_time": "0:17:27", "remaining_time": "1:38:46", "throughput": 5631.38, "total_tokens": 5897136} {"current_steps": 9685, "total_steps": 64460, "loss": 0.2226, "lr": 9.923331881814495e-06, "epoch": 3.004964318957493, "percentage": 15.02, "elapsed_time": "0:17:27", "remaining_time": "1:38:45", "throughput": 5631.21, "total_tokens": 5899664} {"current_steps": 9690, "total_steps": 64460, "loss": 0.2467, "lr": 9.923095532165532e-06, "epoch": 3.0065156686317094, "percentage": 15.03, "elapsed_time": "0:17:28", "remaining_time": "1:38:44", "throughput": 5631.11, "total_tokens": 5902512} {"current_steps": 9695, "total_steps": 64460, "loss": 0.2283, "lr": 9.922858821595368e-06, "epoch": 3.008067018305926, "percentage": 15.04, "elapsed_time": "0:17:28", "remaining_time": "1:38:43", "throughput": 5631.24, "total_tokens": 5905584} {"current_steps": 9700, "total_steps": 64460, "loss": 0.2268, "lr": 9.922621750121358e-06, "epoch": 3.009618367980143, "percentage": 15.05, "elapsed_time": "0:17:29", "remaining_time": "1:38:44", "throughput": 5631.74, "total_tokens": 5910064} {"current_steps": 9705, "total_steps": 64460, "loss": 0.233, "lr": 9.92238431776088e-06, "epoch": 3.0111697176543593, "percentage": 15.06, "elapsed_time": "0:17:29", "remaining_time": "1:38:43", "throughput": 5632.05, "total_tokens": 5913328} {"current_steps": 9710, "total_steps": 64460, "loss": 0.2254, "lr": 9.922146524531341e-06, "epoch": 3.012721067328576, "percentage": 15.06, "elapsed_time": "0:17:30", "remaining_time": "1:38:43", "throughput": 5631.67, "total_tokens": 5915856} {"current_steps": 9715, "total_steps": 64460, "loss": 0.2338, "lr": 9.921908370450175e-06, "epoch": 3.0142724170027924, "percentage": 15.07, "elapsed_time": "0:17:30", "remaining_time": "1:38:42", "throughput": 5631.46, "total_tokens": 5918480} {"current_steps": 9720, "total_steps": 64460, "loss": 0.2285, "lr": 9.921669855534843e-06, "epoch": 3.015823766677009, "percentage": 15.08, "elapsed_time": "0:17:31", "remaining_time": "1:38:42", "throughput": 5632.03, "total_tokens": 5922736} {"current_steps": 9725, "total_steps": 64460, "loss": 0.2367, "lr": 9.921430979802829e-06, "epoch": 3.0173751163512255, "percentage": 15.09, "elapsed_time": "0:17:32", "remaining_time": "1:38:41", "throughput": 5631.95, "total_tokens": 5925392} {"current_steps": 9730, "total_steps": 64460, "loss": 0.2294, "lr": 9.921191743271645e-06, "epoch": 3.0189264660254422, "percentage": 15.09, "elapsed_time": "0:17:32", "remaining_time": "1:38:42", "throughput": 5632.17, "total_tokens": 5929936} {"current_steps": 9735, "total_steps": 64460, "loss": 0.2284, "lr": 9.920952145958831e-06, "epoch": 3.0204778156996586, "percentage": 15.1, "elapsed_time": "0:17:33", "remaining_time": "1:38:41", "throughput": 5632.3, "total_tokens": 5932848} {"current_steps": 9740, "total_steps": 64460, "loss": 0.2347, "lr": 9.920712187881951e-06, "epoch": 3.0220291653738753, "percentage": 15.11, "elapsed_time": "0:17:33", "remaining_time": "1:38:41", "throughput": 5632.67, "total_tokens": 5936624} {"current_steps": 9745, "total_steps": 64460, "loss": 0.2313, "lr": 9.920471869058599e-06, "epoch": 3.0235805150480917, "percentage": 15.12, "elapsed_time": "0:17:34", "remaining_time": "1:38:40", "throughput": 5632.41, "total_tokens": 5938960} {"current_steps": 9750, "total_steps": 64460, "loss": 0.2304, "lr": 9.92023118950639e-06, "epoch": 3.0251318647223084, "percentage": 15.13, "elapsed_time": "0:17:35", "remaining_time": "1:38:40", "throughput": 5632.72, "total_tokens": 5942960} {"current_steps": 9755, "total_steps": 64460, "loss": 0.2335, "lr": 9.919990149242973e-06, "epoch": 3.0266832143965248, "percentage": 15.13, "elapsed_time": "0:17:35", "remaining_time": "1:38:39", "throughput": 5632.95, "total_tokens": 5946128} {"current_steps": 9760, "total_steps": 64460, "loss": 0.2283, "lr": 9.919748748286015e-06, "epoch": 3.0282345640707415, "percentage": 15.14, "elapsed_time": "0:17:36", "remaining_time": "1:38:39", "throughput": 5633.44, "total_tokens": 5949872} {"current_steps": 9765, "total_steps": 64460, "loss": 0.2285, "lr": 9.919506986653215e-06, "epoch": 3.0297859137449583, "percentage": 15.15, "elapsed_time": "0:17:36", "remaining_time": "1:38:39", "throughput": 5634.04, "total_tokens": 5954416} {"current_steps": 9770, "total_steps": 64460, "loss": 0.2286, "lr": 9.919264864362298e-06, "epoch": 3.0313372634191746, "percentage": 15.16, "elapsed_time": "0:17:37", "remaining_time": "1:38:38", "throughput": 5633.62, "total_tokens": 5956816} {"current_steps": 9775, "total_steps": 64460, "loss": 0.2231, "lr": 9.919022381431014e-06, "epoch": 3.0328886130933914, "percentage": 15.16, "elapsed_time": "0:17:37", "remaining_time": "1:38:38", "throughput": 5633.59, "total_tokens": 5959856} {"current_steps": 9780, "total_steps": 64460, "loss": 0.2351, "lr": 9.91877953787714e-06, "epoch": 3.0344399627676077, "percentage": 15.17, "elapsed_time": "0:17:38", "remaining_time": "1:38:37", "throughput": 5633.75, "total_tokens": 5962832} {"current_steps": 9785, "total_steps": 64460, "loss": 0.2369, "lr": 9.918536333718476e-06, "epoch": 3.0359913124418245, "percentage": 15.18, "elapsed_time": "0:17:38", "remaining_time": "1:38:36", "throughput": 5633.88, "total_tokens": 5965840} {"current_steps": 9790, "total_steps": 64460, "loss": 0.2315, "lr": 9.918292768972857e-06, "epoch": 3.037542662116041, "percentage": 15.19, "elapsed_time": "0:17:39", "remaining_time": "1:38:36", "throughput": 5633.29, "total_tokens": 5968176} {"current_steps": 9795, "total_steps": 64460, "loss": 0.2337, "lr": 9.918048843658136e-06, "epoch": 3.0390940117902576, "percentage": 15.2, "elapsed_time": "0:17:39", "remaining_time": "1:38:35", "throughput": 5633.2, "total_tokens": 5970928} {"current_steps": 9800, "total_steps": 64460, "loss": 0.2388, "lr": 9.917804557792197e-06, "epoch": 3.040645361464474, "percentage": 15.2, "elapsed_time": "0:17:40", "remaining_time": "1:38:35", "throughput": 5632.86, "total_tokens": 5973808} {"current_steps": 9805, "total_steps": 64460, "loss": 0.2268, "lr": 9.917559911392946e-06, "epoch": 3.0421967111386907, "percentage": 15.21, "elapsed_time": "0:17:41", "remaining_time": "1:38:34", "throughput": 5633.16, "total_tokens": 5977008} {"current_steps": 9810, "total_steps": 64460, "loss": 0.2362, "lr": 9.917314904478323e-06, "epoch": 3.043748060812907, "percentage": 15.22, "elapsed_time": "0:17:41", "remaining_time": "1:38:34", "throughput": 5633.26, "total_tokens": 5980272} {"current_steps": 9815, "total_steps": 64460, "loss": 0.2294, "lr": 9.917069537066289e-06, "epoch": 3.045299410487124, "percentage": 15.23, "elapsed_time": "0:17:42", "remaining_time": "1:38:33", "throughput": 5633.36, "total_tokens": 5983344} {"current_steps": 9820, "total_steps": 64460, "loss": 0.2348, "lr": 9.916823809174828e-06, "epoch": 3.04685076016134, "percentage": 15.23, "elapsed_time": "0:17:42", "remaining_time": "1:38:32", "throughput": 5632.85, "total_tokens": 5985872} {"current_steps": 9825, "total_steps": 64460, "loss": 0.2355, "lr": 9.91657772082196e-06, "epoch": 3.048402109835557, "percentage": 15.24, "elapsed_time": "0:17:43", "remaining_time": "1:38:32", "throughput": 5632.77, "total_tokens": 5988752} {"current_steps": 9830, "total_steps": 64460, "loss": 0.2276, "lr": 9.916331272025724e-06, "epoch": 3.0499534595097737, "percentage": 15.25, "elapsed_time": "0:17:43", "remaining_time": "1:38:31", "throughput": 5632.75, "total_tokens": 5991728} {"current_steps": 9835, "total_steps": 64460, "loss": 0.2294, "lr": 9.916084462804187e-06, "epoch": 3.05150480918399, "percentage": 15.26, "elapsed_time": "0:17:44", "remaining_time": "1:38:31", "throughput": 5633.09, "total_tokens": 5995952} {"current_steps": 9840, "total_steps": 64460, "loss": 0.233, "lr": 9.915837293175444e-06, "epoch": 3.053056158858207, "percentage": 15.27, "elapsed_time": "0:17:44", "remaining_time": "1:38:30", "throughput": 5632.93, "total_tokens": 5998448} {"current_steps": 9845, "total_steps": 64460, "loss": 0.2305, "lr": 9.915589763157614e-06, "epoch": 3.054607508532423, "percentage": 15.27, "elapsed_time": "0:17:45", "remaining_time": "1:38:30", "throughput": 5632.89, "total_tokens": 6001072} {"current_steps": 9850, "total_steps": 64460, "loss": 0.2337, "lr": 9.915341872768846e-06, "epoch": 3.05615885820664, "percentage": 15.28, "elapsed_time": "0:17:45", "remaining_time": "1:38:29", "throughput": 5633.18, "total_tokens": 6004240} {"current_steps": 9855, "total_steps": 64460, "loss": 0.2285, "lr": 9.915093622027314e-06, "epoch": 3.0577102078808562, "percentage": 15.29, "elapsed_time": "0:17:46", "remaining_time": "1:38:28", "throughput": 5633.13, "total_tokens": 6006832} {"current_steps": 9860, "total_steps": 64460, "loss": 0.2194, "lr": 9.914845010951215e-06, "epoch": 3.059261557555073, "percentage": 15.3, "elapsed_time": "0:17:46", "remaining_time": "1:38:27", "throughput": 5633.23, "total_tokens": 6009872} {"current_steps": 9865, "total_steps": 64460, "loss": 0.2289, "lr": 9.914596039558775e-06, "epoch": 3.0608129072292893, "percentage": 15.3, "elapsed_time": "0:17:47", "remaining_time": "1:38:27", "throughput": 5633.13, "total_tokens": 6012624} {"current_steps": 9870, "total_steps": 64460, "loss": 0.2385, "lr": 9.914346707868248e-06, "epoch": 3.062364256903506, "percentage": 15.31, "elapsed_time": "0:17:47", "remaining_time": "1:38:26", "throughput": 5633.07, "total_tokens": 6015536} {"current_steps": 9875, "total_steps": 64460, "loss": 0.2363, "lr": 9.914097015897915e-06, "epoch": 3.0639156065777224, "percentage": 15.32, "elapsed_time": "0:17:48", "remaining_time": "1:38:26", "throughput": 5632.97, "total_tokens": 6018608} {"current_steps": 9880, "total_steps": 64460, "loss": 0.2381, "lr": 9.913846963666076e-06, "epoch": 3.065466956251939, "percentage": 15.33, "elapsed_time": "0:17:48", "remaining_time": "1:38:25", "throughput": 5632.74, "total_tokens": 6021136} {"current_steps": 9885, "total_steps": 64460, "loss": 0.23, "lr": 9.913596551191068e-06, "epoch": 3.0670183059261555, "percentage": 15.34, "elapsed_time": "0:17:49", "remaining_time": "1:38:24", "throughput": 5632.4, "total_tokens": 6023664} {"current_steps": 9890, "total_steps": 64460, "loss": 0.2296, "lr": 9.913345778491246e-06, "epoch": 3.0685696556003723, "percentage": 15.34, "elapsed_time": "0:17:49", "remaining_time": "1:38:23", "throughput": 5631.71, "total_tokens": 6025904} {"current_steps": 9895, "total_steps": 64460, "loss": 0.2304, "lr": 9.913094645584997e-06, "epoch": 3.070121005274589, "percentage": 15.35, "elapsed_time": "0:17:50", "remaining_time": "1:38:23", "throughput": 5631.66, "total_tokens": 6028624} {"current_steps": 9900, "total_steps": 64460, "loss": 0.2312, "lr": 9.91284315249073e-06, "epoch": 3.0716723549488054, "percentage": 15.36, "elapsed_time": "0:17:51", "remaining_time": "1:38:23", "throughput": 5631.26, "total_tokens": 6031696} {"current_steps": 9905, "total_steps": 64460, "loss": 0.2271, "lr": 9.912591299226883e-06, "epoch": 3.073223704623022, "percentage": 15.37, "elapsed_time": "0:17:51", "remaining_time": "1:38:22", "throughput": 5631.07, "total_tokens": 6034384} {"current_steps": 9910, "total_steps": 64460, "loss": 0.2289, "lr": 9.91233908581192e-06, "epoch": 3.0747750542972385, "percentage": 15.37, "elapsed_time": "0:17:52", "remaining_time": "1:38:21", "throughput": 5630.85, "total_tokens": 6037296} {"current_steps": 9915, "total_steps": 64460, "loss": 0.2375, "lr": 9.912086512264332e-06, "epoch": 3.0763264039714553, "percentage": 15.38, "elapsed_time": "0:17:52", "remaining_time": "1:38:21", "throughput": 5631.01, "total_tokens": 6040976} {"current_steps": 9920, "total_steps": 64460, "loss": 0.2319, "lr": 9.911833578602634e-06, "epoch": 3.0778777536456716, "percentage": 15.39, "elapsed_time": "0:17:53", "remaining_time": "1:38:20", "throughput": 5631.08, "total_tokens": 6043824} {"current_steps": 9925, "total_steps": 64460, "loss": 0.2281, "lr": 9.91158028484537e-06, "epoch": 3.0794291033198884, "percentage": 15.4, "elapsed_time": "0:17:53", "remaining_time": "1:38:20", "throughput": 5631.28, "total_tokens": 6046896} {"current_steps": 9930, "total_steps": 64460, "loss": 0.2315, "lr": 9.91132663101111e-06, "epoch": 3.0809804529941047, "percentage": 15.4, "elapsed_time": "0:17:54", "remaining_time": "1:38:19", "throughput": 5631.72, "total_tokens": 6050640} {"current_steps": 9935, "total_steps": 64460, "loss": 0.2303, "lr": 9.911072617118446e-06, "epoch": 3.0825318026683215, "percentage": 15.41, "elapsed_time": "0:17:54", "remaining_time": "1:38:19", "throughput": 5631.82, "total_tokens": 6054000} {"current_steps": 9940, "total_steps": 64460, "loss": 0.2284, "lr": 9.910818243186006e-06, "epoch": 3.084083152342538, "percentage": 15.42, "elapsed_time": "0:17:55", "remaining_time": "1:38:19", "throughput": 5632.05, "total_tokens": 6057712} {"current_steps": 9945, "total_steps": 64460, "loss": 0.2317, "lr": 9.910563509232437e-06, "epoch": 3.0856345020167546, "percentage": 15.43, "elapsed_time": "0:17:56", "remaining_time": "1:38:18", "throughput": 5631.89, "total_tokens": 6060368} {"current_steps": 9950, "total_steps": 64460, "loss": 0.238, "lr": 9.910308415276413e-06, "epoch": 3.087185851690971, "percentage": 15.44, "elapsed_time": "0:17:56", "remaining_time": "1:38:18", "throughput": 5631.9, "total_tokens": 6063376} {"current_steps": 9955, "total_steps": 64460, "loss": 0.2325, "lr": 9.910052961336634e-06, "epoch": 3.0887372013651877, "percentage": 15.44, "elapsed_time": "0:17:57", "remaining_time": "1:38:17", "throughput": 5631.52, "total_tokens": 6065936} {"current_steps": 9960, "total_steps": 64460, "loss": 0.2328, "lr": 9.909797147431829e-06, "epoch": 3.0902885510394045, "percentage": 15.45, "elapsed_time": "0:17:57", "remaining_time": "1:38:17", "throughput": 5632.35, "total_tokens": 6070640} {"current_steps": 9965, "total_steps": 64460, "loss": 0.2294, "lr": 9.909540973580752e-06, "epoch": 3.091839900713621, "percentage": 15.46, "elapsed_time": "0:17:58", "remaining_time": "1:38:17", "throughput": 5632.43, "total_tokens": 6073680} {"current_steps": 9970, "total_steps": 64460, "loss": 0.2287, "lr": 9.909284439802184e-06, "epoch": 3.0933912503878376, "percentage": 15.47, "elapsed_time": "0:17:58", "remaining_time": "1:38:16", "throughput": 5632.39, "total_tokens": 6076432} {"current_steps": 9975, "total_steps": 64460, "loss": 0.2269, "lr": 9.909027546114935e-06, "epoch": 3.094942600062054, "percentage": 15.47, "elapsed_time": "0:17:59", "remaining_time": "1:38:15", "throughput": 5632.51, "total_tokens": 6079408} {"current_steps": 9980, "total_steps": 64460, "loss": 0.2333, "lr": 9.908770292537833e-06, "epoch": 3.0964939497362707, "percentage": 15.48, "elapsed_time": "0:17:59", "remaining_time": "1:38:14", "throughput": 5632.26, "total_tokens": 6081872} {"current_steps": 9985, "total_steps": 64460, "loss": 0.2302, "lr": 9.908512679089739e-06, "epoch": 3.098045299410487, "percentage": 15.49, "elapsed_time": "0:18:00", "remaining_time": "1:38:13", "throughput": 5632.26, "total_tokens": 6084464} {"current_steps": 9990, "total_steps": 64460, "loss": 0.2274, "lr": 9.908254705789541e-06, "epoch": 3.099596649084704, "percentage": 15.5, "elapsed_time": "0:18:00", "remaining_time": "1:38:13", "throughput": 5632.52, "total_tokens": 6087664} {"current_steps": 9995, "total_steps": 64460, "loss": 0.2335, "lr": 9.907996372656153e-06, "epoch": 3.10114799875892, "percentage": 15.51, "elapsed_time": "0:18:01", "remaining_time": "1:38:12", "throughput": 5631.97, "total_tokens": 6089872} {"current_steps": 10000, "total_steps": 64460, "loss": 0.2274, "lr": 9.907737679708508e-06, "epoch": 3.102699348433137, "percentage": 15.51, "elapsed_time": "0:18:01", "remaining_time": "1:38:11", "throughput": 5631.95, "total_tokens": 6092688} {"current_steps": 10005, "total_steps": 64460, "loss": 0.2412, "lr": 9.907478626965576e-06, "epoch": 3.104250698107353, "percentage": 15.52, "elapsed_time": "0:18:02", "remaining_time": "1:38:10", "throughput": 5632.1, "total_tokens": 6095696} {"current_steps": 10010, "total_steps": 64460, "loss": 0.2252, "lr": 9.907219214446348e-06, "epoch": 3.10580204778157, "percentage": 15.53, "elapsed_time": "0:18:02", "remaining_time": "1:38:10", "throughput": 5632.28, "total_tokens": 6098768} {"current_steps": 10015, "total_steps": 64460, "loss": 0.2348, "lr": 9.906959442169841e-06, "epoch": 3.1073533974557863, "percentage": 15.54, "elapsed_time": "0:18:03", "remaining_time": "1:38:09", "throughput": 5632.34, "total_tokens": 6101456} {"current_steps": 10020, "total_steps": 64460, "loss": 0.2256, "lr": 9.906699310155098e-06, "epoch": 3.108904747130003, "percentage": 15.54, "elapsed_time": "0:18:03", "remaining_time": "1:38:08", "throughput": 5632.48, "total_tokens": 6104336} {"current_steps": 10025, "total_steps": 64460, "loss": 0.2296, "lr": 9.906438818421195e-06, "epoch": 3.11045609680422, "percentage": 15.55, "elapsed_time": "0:18:04", "remaining_time": "1:38:07", "throughput": 5632.63, "total_tokens": 6107568} {"current_steps": 10030, "total_steps": 64460, "loss": 0.2239, "lr": 9.906177966987225e-06, "epoch": 3.112007446478436, "percentage": 15.56, "elapsed_time": "0:18:04", "remaining_time": "1:38:07", "throughput": 5632.79, "total_tokens": 6110608} {"current_steps": 10035, "total_steps": 64460, "loss": 0.2223, "lr": 9.905916755872309e-06, "epoch": 3.113558796152653, "percentage": 15.57, "elapsed_time": "0:18:05", "remaining_time": "1:38:06", "throughput": 5632.32, "total_tokens": 6112848} {"current_steps": 10040, "total_steps": 64460, "loss": 0.2454, "lr": 9.905655185095602e-06, "epoch": 3.1151101458268693, "percentage": 15.58, "elapsed_time": "0:18:05", "remaining_time": "1:38:05", "throughput": 5632.35, "total_tokens": 6116176} {"current_steps": 10045, "total_steps": 64460, "loss": 0.2339, "lr": 9.905393254676279e-06, "epoch": 3.116661495501086, "percentage": 15.58, "elapsed_time": "0:18:06", "remaining_time": "1:38:05", "throughput": 5632.88, "total_tokens": 6120208} {"current_steps": 10050, "total_steps": 64460, "loss": 0.2295, "lr": 9.905130964633543e-06, "epoch": 3.1182128451753024, "percentage": 15.59, "elapsed_time": "0:18:06", "remaining_time": "1:38:04", "throughput": 5632.75, "total_tokens": 6122640} {"current_steps": 10055, "total_steps": 64460, "loss": 0.2336, "lr": 9.90486831498662e-06, "epoch": 3.119764194849519, "percentage": 15.6, "elapsed_time": "0:18:07", "remaining_time": "1:38:03", "throughput": 5632.7, "total_tokens": 6125360} {"current_steps": 10060, "total_steps": 64460, "loss": 0.2241, "lr": 9.904605305754766e-06, "epoch": 3.1213155445237355, "percentage": 15.61, "elapsed_time": "0:18:08", "remaining_time": "1:38:03", "throughput": 5633.15, "total_tokens": 6129104} {"current_steps": 10065, "total_steps": 64460, "loss": 0.2315, "lr": 9.904341936957267e-06, "epoch": 3.1228668941979523, "percentage": 15.61, "elapsed_time": "0:18:08", "remaining_time": "1:38:02", "throughput": 5633.01, "total_tokens": 6131824} {"current_steps": 10070, "total_steps": 64460, "loss": 0.2337, "lr": 9.904078208613426e-06, "epoch": 3.1244182438721686, "percentage": 15.62, "elapsed_time": "0:18:09", "remaining_time": "1:38:03", "throughput": 5633.39, "total_tokens": 6135952} {"current_steps": 10075, "total_steps": 64460, "loss": 0.2305, "lr": 9.903814120742578e-06, "epoch": 3.1259695935463854, "percentage": 15.63, "elapsed_time": "0:18:09", "remaining_time": "1:38:02", "throughput": 5633.46, "total_tokens": 6138768} {"current_steps": 10080, "total_steps": 64460, "loss": 0.2352, "lr": 9.903549673364088e-06, "epoch": 3.1275209432206017, "percentage": 15.64, "elapsed_time": "0:18:10", "remaining_time": "1:38:01", "throughput": 5633.86, "total_tokens": 6142480} {"current_steps": 10085, "total_steps": 64460, "loss": 0.2309, "lr": 9.903284866497338e-06, "epoch": 3.1290722928948185, "percentage": 15.65, "elapsed_time": "0:18:10", "remaining_time": "1:38:01", "throughput": 5633.67, "total_tokens": 6145008} {"current_steps": 10090, "total_steps": 64460, "loss": 0.2345, "lr": 9.903019700161744e-06, "epoch": 3.1306236425690352, "percentage": 15.65, "elapsed_time": "0:18:11", "remaining_time": "1:38:00", "throughput": 5633.91, "total_tokens": 6148368} {"current_steps": 10095, "total_steps": 64460, "loss": 0.2335, "lr": 9.902754174376747e-06, "epoch": 3.1321749922432516, "percentage": 15.66, "elapsed_time": "0:18:12", "remaining_time": "1:38:01", "throughput": 5634.69, "total_tokens": 6153328} {"current_steps": 10100, "total_steps": 64460, "loss": 0.2309, "lr": 9.902488289161811e-06, "epoch": 3.1337263419174683, "percentage": 15.67, "elapsed_time": "0:18:12", "remaining_time": "1:38:00", "throughput": 5634.47, "total_tokens": 6156048} {"current_steps": 10105, "total_steps": 64460, "loss": 0.2299, "lr": 9.90222204453643e-06, "epoch": 3.1352776915916847, "percentage": 15.68, "elapsed_time": "0:18:13", "remaining_time": "1:37:59", "throughput": 5634.51, "total_tokens": 6159024} {"current_steps": 10110, "total_steps": 64460, "loss": 0.2311, "lr": 9.901955440520121e-06, "epoch": 3.1368290412659015, "percentage": 15.68, "elapsed_time": "0:18:13", "remaining_time": "1:37:59", "throughput": 5634.29, "total_tokens": 6161680} {"current_steps": 10115, "total_steps": 64460, "loss": 0.2362, "lr": 9.90168847713243e-06, "epoch": 3.138380390940118, "percentage": 15.69, "elapsed_time": "0:18:14", "remaining_time": "1:37:58", "throughput": 5634.39, "total_tokens": 6164816} {"current_steps": 10120, "total_steps": 64460, "loss": 0.2301, "lr": 9.90142115439293e-06, "epoch": 3.1399317406143346, "percentage": 15.7, "elapsed_time": "0:18:14", "remaining_time": "1:37:57", "throughput": 5634.08, "total_tokens": 6167440} {"current_steps": 10125, "total_steps": 64460, "loss": 0.2384, "lr": 9.901153472321217e-06, "epoch": 3.141483090288551, "percentage": 15.71, "elapsed_time": "0:18:15", "remaining_time": "1:37:57", "throughput": 5634.03, "total_tokens": 6170256} {"current_steps": 10130, "total_steps": 64460, "loss": 0.2279, "lr": 9.900885430936917e-06, "epoch": 3.1430344399627677, "percentage": 15.72, "elapsed_time": "0:18:15", "remaining_time": "1:37:56", "throughput": 5633.99, "total_tokens": 6172976} {"current_steps": 10135, "total_steps": 64460, "loss": 0.2339, "lr": 9.900617030259679e-06, "epoch": 3.144585789636984, "percentage": 15.72, "elapsed_time": "0:18:16", "remaining_time": "1:37:55", "throughput": 5633.62, "total_tokens": 6175600} {"current_steps": 10140, "total_steps": 64460, "loss": 0.2399, "lr": 9.900348270309181e-06, "epoch": 3.1461371393112008, "percentage": 15.73, "elapsed_time": "0:18:16", "remaining_time": "1:37:55", "throughput": 5633.92, "total_tokens": 6178832} {"current_steps": 10145, "total_steps": 64460, "loss": 0.2351, "lr": 9.900079151105126e-06, "epoch": 3.147688488985417, "percentage": 15.74, "elapsed_time": "0:18:17", "remaining_time": "1:37:54", "throughput": 5633.82, "total_tokens": 6181392} {"current_steps": 10150, "total_steps": 64460, "loss": 0.2334, "lr": 9.899809672667243e-06, "epoch": 3.149239838659634, "percentage": 15.75, "elapsed_time": "0:18:17", "remaining_time": "1:37:53", "throughput": 5633.53, "total_tokens": 6183696} {"current_steps": 10155, "total_steps": 64460, "loss": 0.2352, "lr": 9.899539835015289e-06, "epoch": 3.1507911883338506, "percentage": 15.75, "elapsed_time": "0:18:18", "remaining_time": "1:37:52", "throughput": 5633.7, "total_tokens": 6187120} {"current_steps": 10160, "total_steps": 64460, "loss": 0.2383, "lr": 9.899269638169046e-06, "epoch": 3.152342538008067, "percentage": 15.76, "elapsed_time": "0:18:18", "remaining_time": "1:37:51", "throughput": 5633.63, "total_tokens": 6189648} {"current_steps": 10165, "total_steps": 64460, "loss": 0.2305, "lr": 9.898999082148323e-06, "epoch": 3.1538938876822837, "percentage": 15.77, "elapsed_time": "0:18:19", "remaining_time": "1:37:51", "throughput": 5633.74, "total_tokens": 6192848} {"current_steps": 10170, "total_steps": 64460, "loss": 0.2304, "lr": 9.898728166972954e-06, "epoch": 3.1554452373565, "percentage": 15.78, "elapsed_time": "0:18:19", "remaining_time": "1:37:51", "throughput": 5633.79, "total_tokens": 6196048} {"current_steps": 10175, "total_steps": 64460, "loss": 0.2289, "lr": 9.898456892662802e-06, "epoch": 3.156996587030717, "percentage": 15.78, "elapsed_time": "0:18:20", "remaining_time": "1:37:50", "throughput": 5633.93, "total_tokens": 6199120} {"current_steps": 10180, "total_steps": 64460, "loss": 0.2341, "lr": 9.89818525923775e-06, "epoch": 3.158547936704933, "percentage": 15.79, "elapsed_time": "0:18:20", "remaining_time": "1:37:49", "throughput": 5633.83, "total_tokens": 6201680} {"current_steps": 10185, "total_steps": 64460, "loss": 0.2352, "lr": 9.897913266717718e-06, "epoch": 3.16009928637915, "percentage": 15.8, "elapsed_time": "0:18:21", "remaining_time": "1:37:48", "throughput": 5634.05, "total_tokens": 6204784} {"current_steps": 10190, "total_steps": 64460, "loss": 0.2331, "lr": 9.897640915122644e-06, "epoch": 3.1616506360533663, "percentage": 15.81, "elapsed_time": "0:18:21", "remaining_time": "1:37:48", "throughput": 5634.15, "total_tokens": 6207856} {"current_steps": 10195, "total_steps": 64460, "loss": 0.2363, "lr": 9.897368204472493e-06, "epoch": 3.163201985727583, "percentage": 15.82, "elapsed_time": "0:18:22", "remaining_time": "1:37:47", "throughput": 5634.32, "total_tokens": 6210864} {"current_steps": 10200, "total_steps": 64460, "loss": 0.2325, "lr": 9.897095134787259e-06, "epoch": 3.1647533354017994, "percentage": 15.82, "elapsed_time": "0:18:22", "remaining_time": "1:37:46", "throughput": 5634.31, "total_tokens": 6213648} {"current_steps": 10205, "total_steps": 64460, "loss": 0.2342, "lr": 9.89682170608696e-06, "epoch": 3.166304685076016, "percentage": 15.83, "elapsed_time": "0:18:23", "remaining_time": "1:37:46", "throughput": 5633.64, "total_tokens": 6216016} {"current_steps": 10210, "total_steps": 64460, "loss": 0.2315, "lr": 9.896547918391646e-06, "epoch": 3.1678560347502325, "percentage": 15.84, "elapsed_time": "0:18:23", "remaining_time": "1:37:45", "throughput": 5633.59, "total_tokens": 6219280} {"current_steps": 10215, "total_steps": 64460, "loss": 0.2305, "lr": 9.896273771721384e-06, "epoch": 3.1694073844244492, "percentage": 15.85, "elapsed_time": "0:18:24", "remaining_time": "1:37:45", "throughput": 5633.29, "total_tokens": 6222000} {"current_steps": 10220, "total_steps": 64460, "loss": 0.2316, "lr": 9.895999266096275e-06, "epoch": 3.170958734098666, "percentage": 15.85, "elapsed_time": "0:18:25", "remaining_time": "1:37:44", "throughput": 5633.53, "total_tokens": 6225168} {"current_steps": 10225, "total_steps": 64460, "loss": 0.2306, "lr": 9.895724401536441e-06, "epoch": 3.1725100837728823, "percentage": 15.86, "elapsed_time": "0:18:25", "remaining_time": "1:37:43", "throughput": 5633.45, "total_tokens": 6227792} {"current_steps": 10230, "total_steps": 64460, "loss": 0.2326, "lr": 9.895449178062035e-06, "epoch": 3.174061433447099, "percentage": 15.87, "elapsed_time": "0:18:26", "remaining_time": "1:37:43", "throughput": 5633.65, "total_tokens": 6231056} {"current_steps": 10235, "total_steps": 64460, "loss": 0.2346, "lr": 9.895173595693234e-06, "epoch": 3.1756127831213155, "percentage": 15.88, "elapsed_time": "0:18:26", "remaining_time": "1:37:42", "throughput": 5633.4, "total_tokens": 6233552} {"current_steps": 10240, "total_steps": 64460, "loss": 0.2298, "lr": 9.89489765445024e-06, "epoch": 3.1771641327955322, "percentage": 15.89, "elapsed_time": "0:18:27", "remaining_time": "1:37:41", "throughput": 5633.05, "total_tokens": 6235952} {"current_steps": 10245, "total_steps": 64460, "loss": 0.2336, "lr": 9.894621354353285e-06, "epoch": 3.1787154824697486, "percentage": 15.89, "elapsed_time": "0:18:27", "remaining_time": "1:37:41", "throughput": 5632.92, "total_tokens": 6239152} {"current_steps": 10250, "total_steps": 64460, "loss": 0.2263, "lr": 9.894344695422621e-06, "epoch": 3.1802668321439653, "percentage": 15.9, "elapsed_time": "0:18:28", "remaining_time": "1:37:40", "throughput": 5632.84, "total_tokens": 6241872} {"current_steps": 10255, "total_steps": 64460, "loss": 0.2325, "lr": 9.894067677678535e-06, "epoch": 3.1818181818181817, "percentage": 15.91, "elapsed_time": "0:18:28", "remaining_time": "1:37:39", "throughput": 5633.09, "total_tokens": 6245072} {"current_steps": 10260, "total_steps": 64460, "loss": 0.2328, "lr": 9.893790301141335e-06, "epoch": 3.1833695314923984, "percentage": 15.92, "elapsed_time": "0:18:29", "remaining_time": "1:37:39", "throughput": 5633.45, "total_tokens": 6248592} {"current_steps": 10265, "total_steps": 64460, "loss": 0.2228, "lr": 9.893512565831353e-06, "epoch": 3.1849208811666148, "percentage": 15.92, "elapsed_time": "0:18:29", "remaining_time": "1:37:38", "throughput": 5633.75, "total_tokens": 6251984} {"current_steps": 10270, "total_steps": 64460, "loss": 0.2367, "lr": 9.893234471768954e-06, "epoch": 3.1864722308408315, "percentage": 15.93, "elapsed_time": "0:18:30", "remaining_time": "1:37:38", "throughput": 5633.46, "total_tokens": 6254704} {"current_steps": 10275, "total_steps": 64460, "loss": 0.2326, "lr": 9.892956018974522e-06, "epoch": 3.188023580515048, "percentage": 15.94, "elapsed_time": "0:18:30", "remaining_time": "1:37:37", "throughput": 5633.36, "total_tokens": 6257424} {"current_steps": 10280, "total_steps": 64460, "loss": 0.2267, "lr": 9.892677207468472e-06, "epoch": 3.1895749301892646, "percentage": 15.95, "elapsed_time": "0:18:31", "remaining_time": "1:37:36", "throughput": 5633.29, "total_tokens": 6260144} {"current_steps": 10285, "total_steps": 64460, "loss": 0.2319, "lr": 9.892398037271245e-06, "epoch": 3.1911262798634814, "percentage": 15.96, "elapsed_time": "0:18:31", "remaining_time": "1:37:36", "throughput": 5633.51, "total_tokens": 6263376} {"current_steps": 10290, "total_steps": 64460, "loss": 0.2366, "lr": 9.892118508403307e-06, "epoch": 3.1926776295376977, "percentage": 15.96, "elapsed_time": "0:18:32", "remaining_time": "1:37:35", "throughput": 5633.35, "total_tokens": 6266096} {"current_steps": 10295, "total_steps": 64460, "loss": 0.2311, "lr": 9.891838620885152e-06, "epoch": 3.1942289792119145, "percentage": 15.97, "elapsed_time": "0:18:32", "remaining_time": "1:37:35", "throughput": 5633.84, "total_tokens": 6270416} {"current_steps": 10300, "total_steps": 64460, "loss": 0.2331, "lr": 9.891558374737298e-06, "epoch": 3.195780328886131, "percentage": 15.98, "elapsed_time": "0:18:33", "remaining_time": "1:37:35", "throughput": 5633.87, "total_tokens": 6273776} {"current_steps": 10305, "total_steps": 64460, "loss": 0.2324, "lr": 9.89127776998029e-06, "epoch": 3.1973316785603476, "percentage": 15.99, "elapsed_time": "0:18:34", "remaining_time": "1:37:34", "throughput": 5633.77, "total_tokens": 6276400} {"current_steps": 10310, "total_steps": 64460, "loss": 0.2319, "lr": 9.8909968066347e-06, "epoch": 3.198883028234564, "percentage": 15.99, "elapsed_time": "0:18:34", "remaining_time": "1:37:34", "throughput": 5633.72, "total_tokens": 6279568} {"current_steps": 10315, "total_steps": 64460, "loss": 0.2366, "lr": 9.890715484721127e-06, "epoch": 3.2004343779087807, "percentage": 16.0, "elapsed_time": "0:18:35", "remaining_time": "1:37:33", "throughput": 5633.47, "total_tokens": 6282128} {"current_steps": 10320, "total_steps": 64460, "loss": 0.234, "lr": 9.890433804260194e-06, "epoch": 3.201985727582997, "percentage": 16.01, "elapsed_time": "0:18:35", "remaining_time": "1:37:33", "throughput": 5634.01, "total_tokens": 6286448} {"current_steps": 10325, "total_steps": 64460, "loss": 0.2299, "lr": 9.890151765272552e-06, "epoch": 3.203537077257214, "percentage": 16.02, "elapsed_time": "0:18:36", "remaining_time": "1:37:33", "throughput": 5634.33, "total_tokens": 6290096} {"current_steps": 10330, "total_steps": 64460, "loss": 0.2304, "lr": 9.889869367778875e-06, "epoch": 3.20508842693143, "percentage": 16.03, "elapsed_time": "0:18:36", "remaining_time": "1:37:32", "throughput": 5634.07, "total_tokens": 6292432} {"current_steps": 10335, "total_steps": 64460, "loss": 0.2331, "lr": 9.889586611799871e-06, "epoch": 3.206639776605647, "percentage": 16.03, "elapsed_time": "0:18:37", "remaining_time": "1:37:31", "throughput": 5634.24, "total_tokens": 6295600} {"current_steps": 10340, "total_steps": 64460, "loss": 0.2317, "lr": 9.889303497356266e-06, "epoch": 3.2081911262798632, "percentage": 16.04, "elapsed_time": "0:18:37", "remaining_time": "1:37:31", "throughput": 5634.8, "total_tokens": 6299408} {"current_steps": 10345, "total_steps": 64460, "loss": 0.229, "lr": 9.889020024468818e-06, "epoch": 3.20974247595408, "percentage": 16.05, "elapsed_time": "0:18:38", "remaining_time": "1:37:31", "throughput": 5635.28, "total_tokens": 6303312} {"current_steps": 10350, "total_steps": 64460, "loss": 0.2316, "lr": 9.888736193158306e-06, "epoch": 3.211293825628297, "percentage": 16.06, "elapsed_time": "0:18:39", "remaining_time": "1:37:30", "throughput": 5635.19, "total_tokens": 6306288} {"current_steps": 10355, "total_steps": 64460, "loss": 0.2326, "lr": 9.88845200344554e-06, "epoch": 3.212845175302513, "percentage": 16.06, "elapsed_time": "0:18:39", "remaining_time": "1:37:29", "throughput": 5634.92, "total_tokens": 6308720} {"current_steps": 10360, "total_steps": 64460, "loss": 0.231, "lr": 9.888167455351354e-06, "epoch": 3.21439652497673, "percentage": 16.07, "elapsed_time": "0:18:40", "remaining_time": "1:37:29", "throughput": 5634.43, "total_tokens": 6311120} {"current_steps": 10365, "total_steps": 64460, "loss": 0.234, "lr": 9.88788254889661e-06, "epoch": 3.2159478746509462, "percentage": 16.08, "elapsed_time": "0:18:40", "remaining_time": "1:37:28", "throughput": 5633.97, "total_tokens": 6313648} {"current_steps": 10370, "total_steps": 64460, "loss": 0.2278, "lr": 9.887597284102193e-06, "epoch": 3.217499224325163, "percentage": 16.09, "elapsed_time": "0:18:41", "remaining_time": "1:37:27", "throughput": 5633.53, "total_tokens": 6315952} {"current_steps": 10375, "total_steps": 64460, "loss": 0.2283, "lr": 9.887311660989019e-06, "epoch": 3.2190505739993793, "percentage": 16.1, "elapsed_time": "0:18:41", "remaining_time": "1:37:27", "throughput": 5633.45, "total_tokens": 6319184} {"current_steps": 10380, "total_steps": 64460, "loss": 0.2299, "lr": 9.887025679578024e-06, "epoch": 3.220601923673596, "percentage": 16.1, "elapsed_time": "0:18:42", "remaining_time": "1:37:27", "throughput": 5633.47, "total_tokens": 6322256} {"current_steps": 10385, "total_steps": 64460, "loss": 0.2269, "lr": 9.886739339890176e-06, "epoch": 3.2221532733478124, "percentage": 16.11, "elapsed_time": "0:18:42", "remaining_time": "1:37:26", "throughput": 5633.25, "total_tokens": 6324784} {"current_steps": 10390, "total_steps": 64460, "loss": 0.231, "lr": 9.886452641946467e-06, "epoch": 3.223704623022029, "percentage": 16.12, "elapsed_time": "0:18:43", "remaining_time": "1:37:26", "throughput": 5633.95, "total_tokens": 6329104} {"current_steps": 10395, "total_steps": 64460, "loss": 0.2333, "lr": 9.886165585767914e-06, "epoch": 3.2252559726962455, "percentage": 16.13, "elapsed_time": "0:18:43", "remaining_time": "1:37:25", "throughput": 5633.97, "total_tokens": 6331856} {"current_steps": 10400, "total_steps": 64460, "loss": 0.2302, "lr": 9.885878171375564e-06, "epoch": 3.2268073223704623, "percentage": 16.13, "elapsed_time": "0:18:44", "remaining_time": "1:37:24", "throughput": 5634.3, "total_tokens": 6335184} {"current_steps": 10405, "total_steps": 64460, "loss": 0.2317, "lr": 9.885590398790486e-06, "epoch": 3.228358672044679, "percentage": 16.14, "elapsed_time": "0:18:44", "remaining_time": "1:37:24", "throughput": 5634.45, "total_tokens": 6338416} {"current_steps": 10410, "total_steps": 64460, "loss": 0.2316, "lr": 9.885302268033778e-06, "epoch": 3.2299100217188954, "percentage": 16.15, "elapsed_time": "0:18:45", "remaining_time": "1:37:23", "throughput": 5634.28, "total_tokens": 6341264} {"current_steps": 10415, "total_steps": 64460, "loss": 0.2258, "lr": 9.885013779126565e-06, "epoch": 3.231461371393112, "percentage": 16.16, "elapsed_time": "0:18:45", "remaining_time": "1:37:22", "throughput": 5634.01, "total_tokens": 6343760} {"current_steps": 10420, "total_steps": 64460, "loss": 0.2349, "lr": 9.884724932089991e-06, "epoch": 3.2330127210673285, "percentage": 16.17, "elapsed_time": "0:18:46", "remaining_time": "1:37:22", "throughput": 5633.42, "total_tokens": 6346064} {"current_steps": 10425, "total_steps": 64460, "loss": 0.2379, "lr": 9.884435726945238e-06, "epoch": 3.2345640707415453, "percentage": 16.17, "elapsed_time": "0:18:47", "remaining_time": "1:37:22", "throughput": 5633.7, "total_tokens": 6349744} {"current_steps": 10430, "total_steps": 64460, "loss": 0.2291, "lr": 9.884146163713506e-06, "epoch": 3.2361154204157616, "percentage": 16.18, "elapsed_time": "0:18:47", "remaining_time": "1:37:21", "throughput": 5634.04, "total_tokens": 6353104} {"current_steps": 10435, "total_steps": 64460, "loss": 0.2311, "lr": 9.883856242416022e-06, "epoch": 3.2376667700899784, "percentage": 16.19, "elapsed_time": "0:18:48", "remaining_time": "1:37:20", "throughput": 5634.02, "total_tokens": 6355760} {"current_steps": 10440, "total_steps": 64460, "loss": 0.2329, "lr": 9.883565963074043e-06, "epoch": 3.2392181197641947, "percentage": 16.2, "elapsed_time": "0:18:48", "remaining_time": "1:37:19", "throughput": 5634.26, "total_tokens": 6359056} {"current_steps": 10445, "total_steps": 64460, "loss": 0.2303, "lr": 9.883275325708848e-06, "epoch": 3.2407694694384115, "percentage": 16.2, "elapsed_time": "0:18:49", "remaining_time": "1:37:20", "throughput": 5635.11, "total_tokens": 6364720} {"current_steps": 10450, "total_steps": 64460, "loss": 0.2329, "lr": 9.882984330341745e-06, "epoch": 3.242320819112628, "percentage": 16.21, "elapsed_time": "0:18:49", "remaining_time": "1:37:20", "throughput": 5634.86, "total_tokens": 6367248} {"current_steps": 10455, "total_steps": 64460, "loss": 0.2335, "lr": 9.882692976994069e-06, "epoch": 3.2438721687868446, "percentage": 16.22, "elapsed_time": "0:18:50", "remaining_time": "1:37:19", "throughput": 5634.53, "total_tokens": 6369648} {"current_steps": 10460, "total_steps": 64460, "loss": 0.2332, "lr": 9.882401265687176e-06, "epoch": 3.245423518461061, "percentage": 16.23, "elapsed_time": "0:18:51", "remaining_time": "1:37:19", "throughput": 5634.6, "total_tokens": 6373008} {"current_steps": 10465, "total_steps": 64460, "loss": 0.2253, "lr": 9.882109196442456e-06, "epoch": 3.2469748681352777, "percentage": 16.23, "elapsed_time": "0:18:51", "remaining_time": "1:37:18", "throughput": 5634.9, "total_tokens": 6376496} {"current_steps": 10470, "total_steps": 64460, "loss": 0.2245, "lr": 9.881816769281318e-06, "epoch": 3.2485262178094945, "percentage": 16.24, "elapsed_time": "0:18:52", "remaining_time": "1:37:20", "throughput": 5635.87, "total_tokens": 6383216} {"current_steps": 10475, "total_steps": 64460, "loss": 0.2267, "lr": 9.881523984225201e-06, "epoch": 3.250077567483711, "percentage": 16.25, "elapsed_time": "0:18:53", "remaining_time": "1:37:20", "throughput": 5636.11, "total_tokens": 6386928} {"current_steps": 10480, "total_steps": 64460, "loss": 0.2285, "lr": 9.881230841295571e-06, "epoch": 3.2516289171579276, "percentage": 16.26, "elapsed_time": "0:18:53", "remaining_time": "1:37:19", "throughput": 5635.92, "total_tokens": 6389488} {"current_steps": 10485, "total_steps": 64460, "loss": 0.245, "lr": 9.880937340513916e-06, "epoch": 3.253180266832144, "percentage": 16.27, "elapsed_time": "0:18:54", "remaining_time": "1:37:18", "throughput": 5635.56, "total_tokens": 6391696} {"current_steps": 10490, "total_steps": 64460, "loss": 0.2402, "lr": 9.880643481901758e-06, "epoch": 3.2547316165063607, "percentage": 16.27, "elapsed_time": "0:18:54", "remaining_time": "1:37:18", "throughput": 5635.45, "total_tokens": 6394832} {"current_steps": 10495, "total_steps": 64460, "loss": 0.2295, "lr": 9.880349265480634e-06, "epoch": 3.256282966180577, "percentage": 16.28, "elapsed_time": "0:18:55", "remaining_time": "1:37:17", "throughput": 5634.98, "total_tokens": 6396944} {"current_steps": 10500, "total_steps": 64460, "loss": 0.2325, "lr": 9.88005469127212e-06, "epoch": 3.2578343158547938, "percentage": 16.29, "elapsed_time": "0:18:55", "remaining_time": "1:37:16", "throughput": 5634.88, "total_tokens": 6399600} {"current_steps": 10505, "total_steps": 64460, "loss": 0.233, "lr": 9.879759759297808e-06, "epoch": 3.25938566552901, "percentage": 16.3, "elapsed_time": "0:18:56", "remaining_time": "1:37:15", "throughput": 5635.06, "total_tokens": 6402736} {"current_steps": 10510, "total_steps": 64460, "loss": 0.232, "lr": 9.879464469579319e-06, "epoch": 3.260937015203227, "percentage": 16.3, "elapsed_time": "0:18:56", "remaining_time": "1:37:15", "throughput": 5634.9, "total_tokens": 6405296} {"current_steps": 10515, "total_steps": 64460, "loss": 0.2357, "lr": 9.879168822138303e-06, "epoch": 3.262488364877443, "percentage": 16.31, "elapsed_time": "0:18:57", "remaining_time": "1:37:14", "throughput": 5635.07, "total_tokens": 6408432} {"current_steps": 10520, "total_steps": 64460, "loss": 0.233, "lr": 9.878872816996434e-06, "epoch": 3.26403971455166, "percentage": 16.32, "elapsed_time": "0:18:57", "remaining_time": "1:37:13", "throughput": 5635.29, "total_tokens": 6411696} {"current_steps": 10525, "total_steps": 64460, "loss": 0.2299, "lr": 9.878576454175416e-06, "epoch": 3.2655910642258767, "percentage": 16.33, "elapsed_time": "0:18:58", "remaining_time": "1:37:12", "throughput": 5635.1, "total_tokens": 6414224} {"current_steps": 10530, "total_steps": 64460, "loss": 0.2273, "lr": 9.87827973369697e-06, "epoch": 3.267142413900093, "percentage": 16.34, "elapsed_time": "0:18:58", "remaining_time": "1:37:12", "throughput": 5634.52, "total_tokens": 6416240} {"current_steps": 10535, "total_steps": 64460, "loss": 0.236, "lr": 9.877982655582852e-06, "epoch": 3.2686937635743094, "percentage": 16.34, "elapsed_time": "0:18:59", "remaining_time": "1:37:12", "throughput": 5635.09, "total_tokens": 6420752} {"current_steps": 10540, "total_steps": 64460, "loss": 0.239, "lr": 9.877685219854843e-06, "epoch": 3.270245113248526, "percentage": 16.35, "elapsed_time": "0:18:59", "remaining_time": "1:37:11", "throughput": 5635.28, "total_tokens": 6423888} {"current_steps": 10545, "total_steps": 64460, "loss": 0.2325, "lr": 9.877387426534746e-06, "epoch": 3.271796462922743, "percentage": 16.36, "elapsed_time": "0:19:00", "remaining_time": "1:37:10", "throughput": 5635.04, "total_tokens": 6426320} {"current_steps": 10550, "total_steps": 64460, "loss": 0.2296, "lr": 9.877089275644393e-06, "epoch": 3.2733478125969593, "percentage": 16.37, "elapsed_time": "0:19:01", "remaining_time": "1:37:10", "throughput": 5635.11, "total_tokens": 6429744} {"current_steps": 10555, "total_steps": 64460, "loss": 0.2253, "lr": 9.876790767205644e-06, "epoch": 3.274899162271176, "percentage": 16.37, "elapsed_time": "0:19:01", "remaining_time": "1:37:09", "throughput": 5635.01, "total_tokens": 6432432} {"current_steps": 10560, "total_steps": 64460, "loss": 0.2255, "lr": 9.876491901240382e-06, "epoch": 3.2764505119453924, "percentage": 16.38, "elapsed_time": "0:19:02", "remaining_time": "1:37:09", "throughput": 5635.1, "total_tokens": 6435536} {"current_steps": 10565, "total_steps": 64460, "loss": 0.2433, "lr": 9.876192677770518e-06, "epoch": 3.278001861619609, "percentage": 16.39, "elapsed_time": "0:19:02", "remaining_time": "1:37:08", "throughput": 5635.12, "total_tokens": 6438608} {"current_steps": 10570, "total_steps": 64460, "loss": 0.2335, "lr": 9.875893096817987e-06, "epoch": 3.2795532112938255, "percentage": 16.4, "elapsed_time": "0:19:03", "remaining_time": "1:37:08", "throughput": 5635.04, "total_tokens": 6441584} {"current_steps": 10575, "total_steps": 64460, "loss": 0.233, "lr": 9.875593158404753e-06, "epoch": 3.2811045609680423, "percentage": 16.41, "elapsed_time": "0:19:03", "remaining_time": "1:37:07", "throughput": 5634.91, "total_tokens": 6444400} {"current_steps": 10580, "total_steps": 64460, "loss": 0.2325, "lr": 9.875292862552803e-06, "epoch": 3.2826559106422586, "percentage": 16.41, "elapsed_time": "0:19:04", "remaining_time": "1:37:07", "throughput": 5634.99, "total_tokens": 6447696} {"current_steps": 10585, "total_steps": 64460, "loss": 0.2336, "lr": 9.874992209284156e-06, "epoch": 3.2842072603164754, "percentage": 16.42, "elapsed_time": "0:19:04", "remaining_time": "1:37:06", "throughput": 5634.57, "total_tokens": 6450032} {"current_steps": 10590, "total_steps": 64460, "loss": 0.2328, "lr": 9.874691198620852e-06, "epoch": 3.285758609990692, "percentage": 16.43, "elapsed_time": "0:19:05", "remaining_time": "1:37:05", "throughput": 5634.17, "total_tokens": 6452560} {"current_steps": 10595, "total_steps": 64460, "loss": 0.2292, "lr": 9.874389830584958e-06, "epoch": 3.2873099596649085, "percentage": 16.44, "elapsed_time": "0:19:05", "remaining_time": "1:37:04", "throughput": 5633.97, "total_tokens": 6455120} {"current_steps": 10600, "total_steps": 64460, "loss": 0.2287, "lr": 9.874088105198568e-06, "epoch": 3.288861309339125, "percentage": 16.44, "elapsed_time": "0:19:06", "remaining_time": "1:37:05", "throughput": 5634.38, "total_tokens": 6459312} {"current_steps": 10605, "total_steps": 64460, "loss": 0.2288, "lr": 9.8737860224838e-06, "epoch": 3.2904126590133416, "percentage": 16.45, "elapsed_time": "0:19:06", "remaining_time": "1:37:04", "throughput": 5633.76, "total_tokens": 6461392} {"current_steps": 10610, "total_steps": 64460, "loss": 0.2325, "lr": 9.873483582462804e-06, "epoch": 3.2919640086875583, "percentage": 16.46, "elapsed_time": "0:19:07", "remaining_time": "1:37:03", "throughput": 5633.28, "total_tokens": 6463824} {"current_steps": 10615, "total_steps": 64460, "loss": 0.2288, "lr": 9.87318078515775e-06, "epoch": 3.2935153583617747, "percentage": 16.47, "elapsed_time": "0:19:07", "remaining_time": "1:37:03", "throughput": 5633.18, "total_tokens": 6466640} {"current_steps": 10620, "total_steps": 64460, "loss": 0.2345, "lr": 9.872877630590839e-06, "epoch": 3.2950667080359914, "percentage": 16.48, "elapsed_time": "0:19:08", "remaining_time": "1:37:02", "throughput": 5632.99, "total_tokens": 6469264} {"current_steps": 10625, "total_steps": 64460, "loss": 0.2257, "lr": 9.872574118784292e-06, "epoch": 3.2966180577102078, "percentage": 16.48, "elapsed_time": "0:19:09", "remaining_time": "1:37:03", "throughput": 5633.72, "total_tokens": 6474576} {"current_steps": 10630, "total_steps": 64460, "loss": 0.2329, "lr": 9.872270249760363e-06, "epoch": 3.2981694073844245, "percentage": 16.49, "elapsed_time": "0:19:09", "remaining_time": "1:37:02", "throughput": 5633.51, "total_tokens": 6477104} {"current_steps": 10635, "total_steps": 64460, "loss": 0.2324, "lr": 9.87196602354133e-06, "epoch": 3.299720757058641, "percentage": 16.5, "elapsed_time": "0:19:10", "remaining_time": "1:37:01", "throughput": 5633.04, "total_tokens": 6479376} {"current_steps": 10640, "total_steps": 64460, "loss": 0.2291, "lr": 9.871661440149491e-06, "epoch": 3.3012721067328576, "percentage": 16.51, "elapsed_time": "0:19:10", "remaining_time": "1:37:00", "throughput": 5632.78, "total_tokens": 6482064} {"current_steps": 10645, "total_steps": 64460, "loss": 0.2335, "lr": 9.871356499607183e-06, "epoch": 3.302823456407074, "percentage": 16.51, "elapsed_time": "0:19:11", "remaining_time": "1:37:00", "throughput": 5633.23, "total_tokens": 6485840} {"current_steps": 10650, "total_steps": 64460, "loss": 0.2314, "lr": 9.871051201936756e-06, "epoch": 3.3043748060812907, "percentage": 16.52, "elapsed_time": "0:19:11", "remaining_time": "1:37:00", "throughput": 5633.42, "total_tokens": 6489168} {"current_steps": 10655, "total_steps": 64460, "loss": 0.2292, "lr": 9.870745547160594e-06, "epoch": 3.3059261557555075, "percentage": 16.53, "elapsed_time": "0:19:12", "remaining_time": "1:36:59", "throughput": 5633.8, "total_tokens": 6492496} {"current_steps": 10660, "total_steps": 64460, "loss": 0.2413, "lr": 9.870439535301107e-06, "epoch": 3.307477505429724, "percentage": 16.54, "elapsed_time": "0:19:12", "remaining_time": "1:36:58", "throughput": 5633.92, "total_tokens": 6495696} {"current_steps": 10665, "total_steps": 64460, "loss": 0.2336, "lr": 9.870133166380726e-06, "epoch": 3.30902885510394, "percentage": 16.55, "elapsed_time": "0:19:13", "remaining_time": "1:36:58", "throughput": 5633.53, "total_tokens": 6498000} {"current_steps": 10670, "total_steps": 64460, "loss": 0.2298, "lr": 9.869826440421912e-06, "epoch": 3.310580204778157, "percentage": 16.55, "elapsed_time": "0:19:14", "remaining_time": "1:36:58", "throughput": 5633.75, "total_tokens": 6502032} {"current_steps": 10675, "total_steps": 64460, "loss": 0.232, "lr": 9.869519357447155e-06, "epoch": 3.3121315544523737, "percentage": 16.56, "elapsed_time": "0:19:14", "remaining_time": "1:36:57", "throughput": 5633.57, "total_tokens": 6504688} {"current_steps": 10680, "total_steps": 64460, "loss": 0.232, "lr": 9.869211917478963e-06, "epoch": 3.31368290412659, "percentage": 16.57, "elapsed_time": "0:19:15", "remaining_time": "1:36:56", "throughput": 5633.28, "total_tokens": 6507248} {"current_steps": 10685, "total_steps": 64460, "loss": 0.2394, "lr": 9.868904120539879e-06, "epoch": 3.315234253800807, "percentage": 16.58, "elapsed_time": "0:19:15", "remaining_time": "1:36:56", "throughput": 5633.02, "total_tokens": 6509968} {"current_steps": 10690, "total_steps": 64460, "loss": 0.2289, "lr": 9.868595966652465e-06, "epoch": 3.316785603475023, "percentage": 16.58, "elapsed_time": "0:19:16", "remaining_time": "1:36:55", "throughput": 5632.8, "total_tokens": 6512560} {"current_steps": 10695, "total_steps": 64460, "loss": 0.2325, "lr": 9.868287455839316e-06, "epoch": 3.31833695314924, "percentage": 16.59, "elapsed_time": "0:19:16", "remaining_time": "1:36:54", "throughput": 5632.64, "total_tokens": 6515184} {"current_steps": 10700, "total_steps": 64460, "loss": 0.2299, "lr": 9.867978588123047e-06, "epoch": 3.3198883028234563, "percentage": 16.6, "elapsed_time": "0:19:17", "remaining_time": "1:36:54", "throughput": 5632.49, "total_tokens": 6517808} {"current_steps": 10705, "total_steps": 64460, "loss": 0.2299, "lr": 9.8676693635263e-06, "epoch": 3.321439652497673, "percentage": 16.61, "elapsed_time": "0:19:17", "remaining_time": "1:36:53", "throughput": 5632.53, "total_tokens": 6520752} {"current_steps": 10710, "total_steps": 64460, "loss": 0.2314, "lr": 9.867359782071749e-06, "epoch": 3.3229910021718894, "percentage": 16.61, "elapsed_time": "0:19:18", "remaining_time": "1:36:52", "throughput": 5632.42, "total_tokens": 6523376} {"current_steps": 10715, "total_steps": 64460, "loss": 0.2346, "lr": 9.867049843782087e-06, "epoch": 3.324542351846106, "percentage": 16.62, "elapsed_time": "0:19:18", "remaining_time": "1:36:51", "throughput": 5632.12, "total_tokens": 6525744} {"current_steps": 10720, "total_steps": 64460, "loss": 0.2289, "lr": 9.866739548680035e-06, "epoch": 3.326093701520323, "percentage": 16.63, "elapsed_time": "0:19:19", "remaining_time": "1:36:51", "throughput": 5632.14, "total_tokens": 6528976} {"current_steps": 10725, "total_steps": 64460, "loss": 0.2342, "lr": 9.866428896788346e-06, "epoch": 3.3276450511945392, "percentage": 16.64, "elapsed_time": "0:19:19", "remaining_time": "1:36:50", "throughput": 5632.09, "total_tokens": 6531920} {"current_steps": 10730, "total_steps": 64460, "loss": 0.2284, "lr": 9.86611788812979e-06, "epoch": 3.329196400868756, "percentage": 16.65, "elapsed_time": "0:19:20", "remaining_time": "1:36:49", "throughput": 5631.96, "total_tokens": 6534448} {"current_steps": 10735, "total_steps": 64460, "loss": 0.2321, "lr": 9.86580652272717e-06, "epoch": 3.3307477505429723, "percentage": 16.65, "elapsed_time": "0:19:20", "remaining_time": "1:36:49", "throughput": 5632.05, "total_tokens": 6537840} {"current_steps": 10740, "total_steps": 64460, "loss": 0.2367, "lr": 9.865494800603313e-06, "epoch": 3.332299100217189, "percentage": 16.66, "elapsed_time": "0:19:21", "remaining_time": "1:36:48", "throughput": 5631.93, "total_tokens": 6540432} {"current_steps": 10745, "total_steps": 64460, "loss": 0.233, "lr": 9.86518272178107e-06, "epoch": 3.3338504498914054, "percentage": 16.67, "elapsed_time": "0:19:21", "remaining_time": "1:36:48", "throughput": 5632.16, "total_tokens": 6543760} {"current_steps": 10750, "total_steps": 64460, "loss": 0.2351, "lr": 9.864870286283322e-06, "epoch": 3.335401799565622, "percentage": 16.68, "elapsed_time": "0:19:22", "remaining_time": "1:36:47", "throughput": 5632.24, "total_tokens": 6546800} {"current_steps": 10755, "total_steps": 64460, "loss": 0.2326, "lr": 9.864557494132971e-06, "epoch": 3.3369531492398385, "percentage": 16.68, "elapsed_time": "0:19:22", "remaining_time": "1:36:46", "throughput": 5632.29, "total_tokens": 6549648} {"current_steps": 10760, "total_steps": 64460, "loss": 0.228, "lr": 9.864244345352954e-06, "epoch": 3.3385044989140553, "percentage": 16.69, "elapsed_time": "0:19:23", "remaining_time": "1:36:46", "throughput": 5632.07, "total_tokens": 6552560} {"current_steps": 10765, "total_steps": 64460, "loss": 0.2265, "lr": 9.863930839966222e-06, "epoch": 3.3400558485882716, "percentage": 16.7, "elapsed_time": "0:19:23", "remaining_time": "1:36:45", "throughput": 5631.62, "total_tokens": 6555024} {"current_steps": 10770, "total_steps": 64460, "loss": 0.2317, "lr": 9.863616977995764e-06, "epoch": 3.3416071982624884, "percentage": 16.71, "elapsed_time": "0:19:24", "remaining_time": "1:36:45", "throughput": 5631.5, "total_tokens": 6557840} {"current_steps": 10775, "total_steps": 64460, "loss": 0.2348, "lr": 9.863302759464589e-06, "epoch": 3.3431585479367047, "percentage": 16.72, "elapsed_time": "0:19:25", "remaining_time": "1:36:44", "throughput": 5631.7, "total_tokens": 6561488} {"current_steps": 10780, "total_steps": 64460, "loss": 0.2321, "lr": 9.862988184395728e-06, "epoch": 3.3447098976109215, "percentage": 16.72, "elapsed_time": "0:19:25", "remaining_time": "1:36:44", "throughput": 5631.82, "total_tokens": 6565104} {"current_steps": 10785, "total_steps": 64460, "loss": 0.2309, "lr": 9.862673252812249e-06, "epoch": 3.3462612472851383, "percentage": 16.73, "elapsed_time": "0:19:26", "remaining_time": "1:36:44", "throughput": 5632.2, "total_tokens": 6568944} {"current_steps": 10790, "total_steps": 64460, "loss": 0.2268, "lr": 9.862357964737237e-06, "epoch": 3.3478125969593546, "percentage": 16.74, "elapsed_time": "0:19:26", "remaining_time": "1:36:44", "throughput": 5632.07, "total_tokens": 6572080} {"current_steps": 10795, "total_steps": 64460, "loss": 0.227, "lr": 9.862042320193807e-06, "epoch": 3.3493639466335714, "percentage": 16.75, "elapsed_time": "0:19:27", "remaining_time": "1:36:43", "throughput": 5632.19, "total_tokens": 6575120} {"current_steps": 10800, "total_steps": 64460, "loss": 0.2274, "lr": 9.8617263192051e-06, "epoch": 3.3509152963077877, "percentage": 16.75, "elapsed_time": "0:19:27", "remaining_time": "1:36:43", "throughput": 5632.15, "total_tokens": 6578320} {"current_steps": 10805, "total_steps": 64460, "loss": 0.2301, "lr": 9.861409961794283e-06, "epoch": 3.3524666459820045, "percentage": 16.76, "elapsed_time": "0:19:28", "remaining_time": "1:36:42", "throughput": 5632.55, "total_tokens": 6582096} {"current_steps": 10810, "total_steps": 64460, "loss": 0.2261, "lr": 9.861093247984547e-06, "epoch": 3.354017995656221, "percentage": 16.77, "elapsed_time": "0:19:29", "remaining_time": "1:36:42", "throughput": 5632.31, "total_tokens": 6584656} {"current_steps": 10815, "total_steps": 64460, "loss": 0.2402, "lr": 9.860776177799114e-06, "epoch": 3.3555693453304376, "percentage": 16.78, "elapsed_time": "0:19:29", "remaining_time": "1:36:41", "throughput": 5632.25, "total_tokens": 6587376} {"current_steps": 10820, "total_steps": 64460, "loss": 0.2282, "lr": 9.860458751261226e-06, "epoch": 3.357120695004654, "percentage": 16.79, "elapsed_time": "0:19:30", "remaining_time": "1:36:40", "throughput": 5631.94, "total_tokens": 6589808} {"current_steps": 10825, "total_steps": 64460, "loss": 0.2421, "lr": 9.860140968394154e-06, "epoch": 3.3586720446788707, "percentage": 16.79, "elapsed_time": "0:19:30", "remaining_time": "1:36:40", "throughput": 5632.11, "total_tokens": 6593520} {"current_steps": 10830, "total_steps": 64460, "loss": 0.2341, "lr": 9.859822829221196e-06, "epoch": 3.360223394353087, "percentage": 16.8, "elapsed_time": "0:19:31", "remaining_time": "1:36:39", "throughput": 5631.96, "total_tokens": 6596016} {"current_steps": 10835, "total_steps": 64460, "loss": 0.23, "lr": 9.859504333765678e-06, "epoch": 3.361774744027304, "percentage": 16.81, "elapsed_time": "0:19:31", "remaining_time": "1:36:39", "throughput": 5632.12, "total_tokens": 6599312} {"current_steps": 10840, "total_steps": 64460, "loss": 0.2294, "lr": 9.859185482050946e-06, "epoch": 3.36332609370152, "percentage": 16.82, "elapsed_time": "0:19:32", "remaining_time": "1:36:39", "throughput": 5632.56, "total_tokens": 6603504} {"current_steps": 10845, "total_steps": 64460, "loss": 0.2319, "lr": 9.858866274100377e-06, "epoch": 3.364877443375737, "percentage": 16.82, "elapsed_time": "0:19:32", "remaining_time": "1:36:38", "throughput": 5632.44, "total_tokens": 6606192} {"current_steps": 10850, "total_steps": 64460, "loss": 0.2273, "lr": 9.858546709937373e-06, "epoch": 3.3664287930499537, "percentage": 16.83, "elapsed_time": "0:19:33", "remaining_time": "1:36:37", "throughput": 5632.15, "total_tokens": 6608688} {"current_steps": 10855, "total_steps": 64460, "loss": 0.2336, "lr": 9.85822678958536e-06, "epoch": 3.36798014272417, "percentage": 16.84, "elapsed_time": "0:19:33", "remaining_time": "1:36:37", "throughput": 5632.13, "total_tokens": 6611600} {"current_steps": 10860, "total_steps": 64460, "loss": 0.2324, "lr": 9.857906513067794e-06, "epoch": 3.369531492398387, "percentage": 16.85, "elapsed_time": "0:19:34", "remaining_time": "1:36:36", "throughput": 5632.52, "total_tokens": 6615536} {"current_steps": 10865, "total_steps": 64460, "loss": 0.2269, "lr": 9.857585880408155e-06, "epoch": 3.371082842072603, "percentage": 16.86, "elapsed_time": "0:19:35", "remaining_time": "1:36:36", "throughput": 5632.57, "total_tokens": 6618352} {"current_steps": 10870, "total_steps": 64460, "loss": 0.2309, "lr": 9.857264891629948e-06, "epoch": 3.37263419174682, "percentage": 16.86, "elapsed_time": "0:19:35", "remaining_time": "1:36:35", "throughput": 5632.71, "total_tokens": 6621392} {"current_steps": 10875, "total_steps": 64460, "loss": 0.2245, "lr": 9.856943546756706e-06, "epoch": 3.374185541421036, "percentage": 16.87, "elapsed_time": "0:19:36", "remaining_time": "1:36:34", "throughput": 5632.46, "total_tokens": 6624048} {"current_steps": 10880, "total_steps": 64460, "loss": 0.2393, "lr": 9.856621845811987e-06, "epoch": 3.375736891095253, "percentage": 16.88, "elapsed_time": "0:19:36", "remaining_time": "1:36:34", "throughput": 5632.14, "total_tokens": 6626480} {"current_steps": 10885, "total_steps": 64460, "loss": 0.2447, "lr": 9.856299788819374e-06, "epoch": 3.3772882407694693, "percentage": 16.89, "elapsed_time": "0:19:37", "remaining_time": "1:36:33", "throughput": 5631.93, "total_tokens": 6629040} {"current_steps": 10890, "total_steps": 64460, "loss": 0.2323, "lr": 9.855977375802481e-06, "epoch": 3.378839590443686, "percentage": 16.89, "elapsed_time": "0:19:37", "remaining_time": "1:36:32", "throughput": 5631.88, "total_tokens": 6631920} {"current_steps": 10895, "total_steps": 64460, "loss": 0.2371, "lr": 9.855654606784944e-06, "epoch": 3.3803909401179024, "percentage": 16.9, "elapsed_time": "0:19:38", "remaining_time": "1:36:32", "throughput": 5631.47, "total_tokens": 6634448} {"current_steps": 10900, "total_steps": 64460, "loss": 0.2254, "lr": 9.855331481790423e-06, "epoch": 3.381942289792119, "percentage": 16.91, "elapsed_time": "0:19:38", "remaining_time": "1:36:31", "throughput": 5631.25, "total_tokens": 6637040} {"current_steps": 10905, "total_steps": 64460, "loss": 0.2323, "lr": 9.85500800084261e-06, "epoch": 3.3834936394663355, "percentage": 16.92, "elapsed_time": "0:19:39", "remaining_time": "1:36:30", "throughput": 5630.86, "total_tokens": 6639344} {"current_steps": 10910, "total_steps": 64460, "loss": 0.2286, "lr": 9.854684163965218e-06, "epoch": 3.3850449891405523, "percentage": 16.93, "elapsed_time": "0:19:39", "remaining_time": "1:36:29", "throughput": 5631.03, "total_tokens": 6642448} {"current_steps": 10915, "total_steps": 64460, "loss": 0.2274, "lr": 9.854359971181988e-06, "epoch": 3.386596338814769, "percentage": 16.93, "elapsed_time": "0:19:40", "remaining_time": "1:36:29", "throughput": 5631.33, "total_tokens": 6645936} {"current_steps": 10920, "total_steps": 64460, "loss": 0.2315, "lr": 9.854035422516688e-06, "epoch": 3.3881476884889854, "percentage": 16.94, "elapsed_time": "0:19:40", "remaining_time": "1:36:28", "throughput": 5631.41, "total_tokens": 6648784} {"current_steps": 10925, "total_steps": 64460, "loss": 0.2315, "lr": 9.853710517993113e-06, "epoch": 3.389699038163202, "percentage": 16.95, "elapsed_time": "0:19:41", "remaining_time": "1:36:28", "throughput": 5632.09, "total_tokens": 6653488} {"current_steps": 10930, "total_steps": 64460, "loss": 0.2353, "lr": 9.85338525763508e-06, "epoch": 3.3912503878374185, "percentage": 16.96, "elapsed_time": "0:19:41", "remaining_time": "1:36:28", "throughput": 5632.24, "total_tokens": 6656560} {"current_steps": 10935, "total_steps": 64460, "loss": 0.2298, "lr": 9.853059641466433e-06, "epoch": 3.3928017375116353, "percentage": 16.96, "elapsed_time": "0:19:42", "remaining_time": "1:36:28", "throughput": 5632.16, "total_tokens": 6659952} {"current_steps": 10940, "total_steps": 64460, "loss": 0.2315, "lr": 9.852733669511047e-06, "epoch": 3.3943530871858516, "percentage": 16.97, "elapsed_time": "0:19:42", "remaining_time": "1:36:27", "throughput": 5632.26, "total_tokens": 6662928} {"current_steps": 10945, "total_steps": 64460, "loss": 0.2284, "lr": 9.852407341792817e-06, "epoch": 3.3959044368600684, "percentage": 16.98, "elapsed_time": "0:19:43", "remaining_time": "1:36:26", "throughput": 5631.91, "total_tokens": 6665520} {"current_steps": 10950, "total_steps": 64460, "loss": 0.2336, "lr": 9.852080658335669e-06, "epoch": 3.3974557865342847, "percentage": 16.99, "elapsed_time": "0:19:44", "remaining_time": "1:36:26", "throughput": 5631.64, "total_tokens": 6668432} {"current_steps": 10955, "total_steps": 64460, "loss": 0.2365, "lr": 9.851753619163552e-06, "epoch": 3.3990071362085015, "percentage": 17.0, "elapsed_time": "0:19:44", "remaining_time": "1:36:25", "throughput": 5631.59, "total_tokens": 6671376} {"current_steps": 10960, "total_steps": 64460, "loss": 0.2324, "lr": 9.85142622430044e-06, "epoch": 3.400558485882718, "percentage": 17.0, "elapsed_time": "0:19:45", "remaining_time": "1:36:25", "throughput": 5631.5, "total_tokens": 6674128} {"current_steps": 10965, "total_steps": 64460, "loss": 0.2345, "lr": 9.851098473770336e-06, "epoch": 3.4021098355569346, "percentage": 17.01, "elapsed_time": "0:19:45", "remaining_time": "1:36:24", "throughput": 5631.48, "total_tokens": 6677136} {"current_steps": 10970, "total_steps": 64460, "loss": 0.2231, "lr": 9.85077036759727e-06, "epoch": 3.403661185231151, "percentage": 17.02, "elapsed_time": "0:19:46", "remaining_time": "1:36:24", "throughput": 5631.37, "total_tokens": 6680048} {"current_steps": 10975, "total_steps": 64460, "loss": 0.2284, "lr": 9.850441905805292e-06, "epoch": 3.4052125349053677, "percentage": 17.03, "elapsed_time": "0:19:46", "remaining_time": "1:36:23", "throughput": 5630.8, "total_tokens": 6682192} {"current_steps": 10980, "total_steps": 64460, "loss": 0.2281, "lr": 9.850113088418486e-06, "epoch": 3.4067638845795845, "percentage": 17.03, "elapsed_time": "0:19:47", "remaining_time": "1:36:22", "throughput": 5630.97, "total_tokens": 6685232} {"current_steps": 10985, "total_steps": 64460, "loss": 0.2396, "lr": 9.849783915460957e-06, "epoch": 3.408315234253801, "percentage": 17.04, "elapsed_time": "0:19:47", "remaining_time": "1:36:22", "throughput": 5630.29, "total_tokens": 6687504} {"current_steps": 10990, "total_steps": 64460, "loss": 0.2259, "lr": 9.849454386956836e-06, "epoch": 3.4098665839280176, "percentage": 17.05, "elapsed_time": "0:19:48", "remaining_time": "1:36:21", "throughput": 5629.94, "total_tokens": 6690160} {"current_steps": 10995, "total_steps": 64460, "loss": 0.2397, "lr": 9.849124502930282e-06, "epoch": 3.411417933602234, "percentage": 17.06, "elapsed_time": "0:19:48", "remaining_time": "1:36:20", "throughput": 5630.16, "total_tokens": 6693328} {"current_steps": 11000, "total_steps": 64460, "loss": 0.2321, "lr": 9.848794263405481e-06, "epoch": 3.4129692832764507, "percentage": 17.06, "elapsed_time": "0:19:49", "remaining_time": "1:36:20", "throughput": 5630.39, "total_tokens": 6696528} {"current_steps": 11005, "total_steps": 64460, "loss": 0.2323, "lr": 9.84846366840664e-06, "epoch": 3.414520632950667, "percentage": 17.07, "elapsed_time": "0:19:49", "remaining_time": "1:36:19", "throughput": 5630.48, "total_tokens": 6699472} {"current_steps": 11010, "total_steps": 64460, "loss": 0.2284, "lr": 9.848132717958002e-06, "epoch": 3.4160719826248838, "percentage": 17.08, "elapsed_time": "0:19:50", "remaining_time": "1:36:18", "throughput": 5630.26, "total_tokens": 6702064} {"current_steps": 11015, "total_steps": 64460, "loss": 0.2296, "lr": 9.847801412083821e-06, "epoch": 3.4176233322991, "percentage": 17.09, "elapsed_time": "0:19:50", "remaining_time": "1:36:18", "throughput": 5630.61, "total_tokens": 6705808} {"current_steps": 11020, "total_steps": 64460, "loss": 0.2341, "lr": 9.847469750808392e-06, "epoch": 3.419174681973317, "percentage": 17.1, "elapsed_time": "0:19:51", "remaining_time": "1:36:17", "throughput": 5630.82, "total_tokens": 6709040} {"current_steps": 11025, "total_steps": 64460, "loss": 0.2412, "lr": 9.847137734156028e-06, "epoch": 3.420726031647533, "percentage": 17.1, "elapsed_time": "0:19:52", "remaining_time": "1:36:17", "throughput": 5630.93, "total_tokens": 6712208} {"current_steps": 11030, "total_steps": 64460, "loss": 0.232, "lr": 9.846805362151067e-06, "epoch": 3.42227738132175, "percentage": 17.11, "elapsed_time": "0:19:52", "remaining_time": "1:36:16", "throughput": 5630.97, "total_tokens": 6715088} {"current_steps": 11035, "total_steps": 64460, "loss": 0.2303, "lr": 9.84647263481788e-06, "epoch": 3.4238287309959663, "percentage": 17.12, "elapsed_time": "0:19:53", "remaining_time": "1:36:16", "throughput": 5631.17, "total_tokens": 6718448} {"current_steps": 11040, "total_steps": 64460, "loss": 0.2264, "lr": 9.846139552180858e-06, "epoch": 3.425380080670183, "percentage": 17.13, "elapsed_time": "0:19:53", "remaining_time": "1:36:16", "throughput": 5631.33, "total_tokens": 6722224} {"current_steps": 11045, "total_steps": 64460, "loss": 0.2316, "lr": 9.845806114264419e-06, "epoch": 3.4269314303444, "percentage": 17.13, "elapsed_time": "0:19:54", "remaining_time": "1:36:15", "throughput": 5631.13, "total_tokens": 6724624} {"current_steps": 11050, "total_steps": 64460, "loss": 0.2328, "lr": 9.84547232109301e-06, "epoch": 3.428482780018616, "percentage": 17.14, "elapsed_time": "0:19:54", "remaining_time": "1:36:14", "throughput": 5631.09, "total_tokens": 6727856} {"current_steps": 11055, "total_steps": 64460, "loss": 0.2519, "lr": 9.8451381726911e-06, "epoch": 3.430034129692833, "percentage": 17.15, "elapsed_time": "0:19:55", "remaining_time": "1:36:14", "throughput": 5631.4, "total_tokens": 6731120} {"current_steps": 11060, "total_steps": 64460, "loss": 0.2349, "lr": 9.844803669083188e-06, "epoch": 3.4315854793670493, "percentage": 17.16, "elapsed_time": "0:19:55", "remaining_time": "1:36:14", "throughput": 5631.9, "total_tokens": 6735344} {"current_steps": 11065, "total_steps": 64460, "loss": 0.2343, "lr": 9.844468810293794e-06, "epoch": 3.433136829041266, "percentage": 17.17, "elapsed_time": "0:19:56", "remaining_time": "1:36:13", "throughput": 5632.03, "total_tokens": 6738320} {"current_steps": 11070, "total_steps": 64460, "loss": 0.2281, "lr": 9.844133596347471e-06, "epoch": 3.4346881787154824, "percentage": 17.17, "elapsed_time": "0:19:56", "remaining_time": "1:36:12", "throughput": 5632.18, "total_tokens": 6741296} {"current_steps": 11075, "total_steps": 64460, "loss": 0.2465, "lr": 9.843798027268791e-06, "epoch": 3.436239528389699, "percentage": 17.18, "elapsed_time": "0:19:57", "remaining_time": "1:36:11", "throughput": 5632.29, "total_tokens": 6744176} {"current_steps": 11080, "total_steps": 64460, "loss": 0.2308, "lr": 9.843462103082359e-06, "epoch": 3.4377908780639155, "percentage": 17.19, "elapsed_time": "0:19:57", "remaining_time": "1:36:11", "throughput": 5631.77, "total_tokens": 6746672} {"current_steps": 11085, "total_steps": 64460, "loss": 0.2299, "lr": 9.843125823812798e-06, "epoch": 3.4393422277381323, "percentage": 17.2, "elapsed_time": "0:19:58", "remaining_time": "1:36:10", "throughput": 5631.87, "total_tokens": 6749872} {"current_steps": 11090, "total_steps": 64460, "loss": 0.2327, "lr": 9.842789189484763e-06, "epoch": 3.4408935774123486, "percentage": 17.2, "elapsed_time": "0:19:59", "remaining_time": "1:36:10", "throughput": 5631.68, "total_tokens": 6752720} {"current_steps": 11095, "total_steps": 64460, "loss": 0.2247, "lr": 9.842452200122931e-06, "epoch": 3.4424449270865654, "percentage": 17.21, "elapsed_time": "0:19:59", "remaining_time": "1:36:09", "throughput": 5631.86, "total_tokens": 6755888} {"current_steps": 11100, "total_steps": 64460, "loss": 0.2276, "lr": 9.842114855752013e-06, "epoch": 3.4439962767607817, "percentage": 17.22, "elapsed_time": "0:20:00", "remaining_time": "1:36:09", "throughput": 5631.98, "total_tokens": 6759216} {"current_steps": 11105, "total_steps": 64460, "loss": 0.2338, "lr": 9.841777156396734e-06, "epoch": 3.4455476264349985, "percentage": 17.23, "elapsed_time": "0:20:00", "remaining_time": "1:36:08", "throughput": 5631.96, "total_tokens": 6762096} {"current_steps": 11110, "total_steps": 64460, "loss": 0.2373, "lr": 9.841439102081857e-06, "epoch": 3.4470989761092152, "percentage": 17.24, "elapsed_time": "0:20:01", "remaining_time": "1:36:08", "throughput": 5631.81, "total_tokens": 6764784} {"current_steps": 11115, "total_steps": 64460, "loss": 0.2322, "lr": 9.841100692832163e-06, "epoch": 3.4486503257834316, "percentage": 17.24, "elapsed_time": "0:20:01", "remaining_time": "1:36:08", "throughput": 5632.28, "total_tokens": 6769520} {"current_steps": 11120, "total_steps": 64460, "loss": 0.232, "lr": 9.840761928672458e-06, "epoch": 3.4502016754576483, "percentage": 17.25, "elapsed_time": "0:20:02", "remaining_time": "1:36:07", "throughput": 5631.98, "total_tokens": 6771888} {"current_steps": 11125, "total_steps": 64460, "loss": 0.2347, "lr": 9.840422809627581e-06, "epoch": 3.4517530251318647, "percentage": 17.26, "elapsed_time": "0:20:02", "remaining_time": "1:36:07", "throughput": 5632.31, "total_tokens": 6775472} {"current_steps": 11130, "total_steps": 64460, "loss": 0.2326, "lr": 9.840083335722394e-06, "epoch": 3.4533043748060814, "percentage": 17.27, "elapsed_time": "0:20:03", "remaining_time": "1:36:06", "throughput": 5632.21, "total_tokens": 6778544} {"current_steps": 11135, "total_steps": 64460, "loss": 0.2389, "lr": 9.839743506981783e-06, "epoch": 3.4548557244802978, "percentage": 17.27, "elapsed_time": "0:20:04", "remaining_time": "1:36:06", "throughput": 5632.18, "total_tokens": 6781776} {"current_steps": 11140, "total_steps": 64460, "loss": 0.2315, "lr": 9.83940332343066e-06, "epoch": 3.4564070741545145, "percentage": 17.28, "elapsed_time": "0:20:04", "remaining_time": "1:36:05", "throughput": 5631.85, "total_tokens": 6784336} {"current_steps": 11145, "total_steps": 64460, "loss": 0.2337, "lr": 9.83906278509397e-06, "epoch": 3.457958423828731, "percentage": 17.29, "elapsed_time": "0:20:05", "remaining_time": "1:36:05", "throughput": 5631.8, "total_tokens": 6787472} {"current_steps": 11150, "total_steps": 64460, "loss": 0.229, "lr": 9.838721891996672e-06, "epoch": 3.4595097735029476, "percentage": 17.3, "elapsed_time": "0:20:05", "remaining_time": "1:36:04", "throughput": 5631.77, "total_tokens": 6790224} {"current_steps": 11155, "total_steps": 64460, "loss": 0.2269, "lr": 9.838380644163761e-06, "epoch": 3.461061123177164, "percentage": 17.31, "elapsed_time": "0:20:06", "remaining_time": "1:36:03", "throughput": 5631.73, "total_tokens": 6792944} {"current_steps": 11160, "total_steps": 64460, "loss": 0.2384, "lr": 9.838039041620253e-06, "epoch": 3.4626124728513807, "percentage": 17.31, "elapsed_time": "0:20:06", "remaining_time": "1:36:03", "throughput": 5631.81, "total_tokens": 6796304} {"current_steps": 11165, "total_steps": 64460, "loss": 0.2397, "lr": 9.837697084391193e-06, "epoch": 3.464163822525597, "percentage": 17.32, "elapsed_time": "0:20:07", "remaining_time": "1:36:02", "throughput": 5631.73, "total_tokens": 6799216} {"current_steps": 11170, "total_steps": 64460, "loss": 0.2339, "lr": 9.83735477250165e-06, "epoch": 3.465715172199814, "percentage": 17.33, "elapsed_time": "0:20:07", "remaining_time": "1:36:02", "throughput": 5631.56, "total_tokens": 6802032} {"current_steps": 11175, "total_steps": 64460, "loss": 0.2284, "lr": 9.83701210597672e-06, "epoch": 3.4672665218740306, "percentage": 17.34, "elapsed_time": "0:20:08", "remaining_time": "1:36:01", "throughput": 5631.55, "total_tokens": 6804912} {"current_steps": 11180, "total_steps": 64460, "loss": 0.2366, "lr": 9.836669084841522e-06, "epoch": 3.468817871548247, "percentage": 17.34, "elapsed_time": "0:20:08", "remaining_time": "1:36:00", "throughput": 5631.28, "total_tokens": 6807312} {"current_steps": 11185, "total_steps": 64460, "loss": 0.234, "lr": 9.836325709121205e-06, "epoch": 3.4703692212224637, "percentage": 17.35, "elapsed_time": "0:20:09", "remaining_time": "1:36:01", "throughput": 5631.83, "total_tokens": 6812048} {"current_steps": 11190, "total_steps": 64460, "loss": 0.2335, "lr": 9.835981978840945e-06, "epoch": 3.47192057089668, "percentage": 17.36, "elapsed_time": "0:20:10", "remaining_time": "1:36:00", "throughput": 5631.83, "total_tokens": 6814896} {"current_steps": 11195, "total_steps": 64460, "loss": 0.2309, "lr": 9.83563789402594e-06, "epoch": 3.473471920570897, "percentage": 17.37, "elapsed_time": "0:20:10", "remaining_time": "1:36:00", "throughput": 5632.33, "total_tokens": 6818608} {"current_steps": 11200, "total_steps": 64460, "loss": 0.2298, "lr": 9.835293454701413e-06, "epoch": 3.475023270245113, "percentage": 17.38, "elapsed_time": "0:20:11", "remaining_time": "1:35:59", "throughput": 5632.34, "total_tokens": 6821520} {"current_steps": 11205, "total_steps": 64460, "loss": 0.231, "lr": 9.834948660892618e-06, "epoch": 3.47657461991933, "percentage": 17.38, "elapsed_time": "0:20:11", "remaining_time": "1:35:58", "throughput": 5632.64, "total_tokens": 6824816} {"current_steps": 11210, "total_steps": 64460, "loss": 0.2289, "lr": 9.834603512624832e-06, "epoch": 3.4781259695935463, "percentage": 17.39, "elapsed_time": "0:20:12", "remaining_time": "1:35:58", "throughput": 5632.67, "total_tokens": 6827792} {"current_steps": 11215, "total_steps": 64460, "loss": 0.2299, "lr": 9.834258009923357e-06, "epoch": 3.479677319267763, "percentage": 17.4, "elapsed_time": "0:20:12", "remaining_time": "1:35:57", "throughput": 5632.63, "total_tokens": 6830576} {"current_steps": 11220, "total_steps": 64460, "loss": 0.2315, "lr": 9.833912152813524e-06, "epoch": 3.4812286689419794, "percentage": 17.41, "elapsed_time": "0:20:13", "remaining_time": "1:35:56", "throughput": 5632.62, "total_tokens": 6833488} {"current_steps": 11225, "total_steps": 64460, "loss": 0.2326, "lr": 9.83356594132069e-06, "epoch": 3.482780018616196, "percentage": 17.41, "elapsed_time": "0:20:13", "remaining_time": "1:35:56", "throughput": 5632.11, "total_tokens": 6835760} {"current_steps": 11230, "total_steps": 64460, "loss": 0.2344, "lr": 9.833219375470234e-06, "epoch": 3.4843313682904125, "percentage": 17.42, "elapsed_time": "0:20:14", "remaining_time": "1:35:55", "throughput": 5632.22, "total_tokens": 6839120} {"current_steps": 11235, "total_steps": 64460, "loss": 0.2311, "lr": 9.832872455287562e-06, "epoch": 3.4858827179646292, "percentage": 17.43, "elapsed_time": "0:20:14", "remaining_time": "1:35:54", "throughput": 5632.14, "total_tokens": 6841808} {"current_steps": 11240, "total_steps": 64460, "loss": 0.2308, "lr": 9.83252518079811e-06, "epoch": 3.487434067638846, "percentage": 17.44, "elapsed_time": "0:20:15", "remaining_time": "1:35:54", "throughput": 5632.11, "total_tokens": 6844720} {"current_steps": 11245, "total_steps": 64460, "loss": 0.231, "lr": 9.832177552027338e-06, "epoch": 3.4889854173130623, "percentage": 17.44, "elapsed_time": "0:20:15", "remaining_time": "1:35:53", "throughput": 5631.9, "total_tokens": 6847280} {"current_steps": 11250, "total_steps": 64460, "loss": 0.2335, "lr": 9.831829569000729e-06, "epoch": 3.490536766987279, "percentage": 17.45, "elapsed_time": "0:20:16", "remaining_time": "1:35:53", "throughput": 5632.05, "total_tokens": 6850672} {"current_steps": 11255, "total_steps": 64460, "loss": 0.234, "lr": 9.831481231743793e-06, "epoch": 3.4920881166614954, "percentage": 17.46, "elapsed_time": "0:20:16", "remaining_time": "1:35:52", "throughput": 5632.05, "total_tokens": 6853520} {"current_steps": 11260, "total_steps": 64460, "loss": 0.2303, "lr": 9.831132540282072e-06, "epoch": 3.493639466335712, "percentage": 17.47, "elapsed_time": "0:20:17", "remaining_time": "1:35:51", "throughput": 5632.33, "total_tokens": 6856912} {"current_steps": 11265, "total_steps": 64460, "loss": 0.234, "lr": 9.830783494641126e-06, "epoch": 3.4951908160099285, "percentage": 17.48, "elapsed_time": "0:20:17", "remaining_time": "1:35:51", "throughput": 5632.41, "total_tokens": 6859792} {"current_steps": 11270, "total_steps": 64460, "loss": 0.2361, "lr": 9.830434094846544e-06, "epoch": 3.4967421656841453, "percentage": 17.48, "elapsed_time": "0:20:18", "remaining_time": "1:35:51", "throughput": 5632.87, "total_tokens": 6864592} {"current_steps": 11275, "total_steps": 64460, "loss": 0.2304, "lr": 9.830084340923945e-06, "epoch": 3.4982935153583616, "percentage": 17.49, "elapsed_time": "0:20:19", "remaining_time": "1:35:51", "throughput": 5632.76, "total_tokens": 6867536} {"current_steps": 11280, "total_steps": 64460, "loss": 0.2283, "lr": 9.829734232898964e-06, "epoch": 3.4998448650325784, "percentage": 17.5, "elapsed_time": "0:20:19", "remaining_time": "1:35:50", "throughput": 5632.74, "total_tokens": 6870480} {"current_steps": 11285, "total_steps": 64460, "loss": 0.2296, "lr": 9.829383770797271e-06, "epoch": 3.501396214706795, "percentage": 17.51, "elapsed_time": "0:20:20", "remaining_time": "1:35:49", "throughput": 5632.17, "total_tokens": 6872848} {"current_steps": 11290, "total_steps": 64460, "loss": 0.2214, "lr": 9.829032954644561e-06, "epoch": 3.5029475643810115, "percentage": 17.51, "elapsed_time": "0:20:20", "remaining_time": "1:35:49", "throughput": 5632.01, "total_tokens": 6875344} {"current_steps": 11295, "total_steps": 64460, "loss": 0.2324, "lr": 9.82868178446655e-06, "epoch": 3.504498914055228, "percentage": 17.52, "elapsed_time": "0:20:21", "remaining_time": "1:35:48", "throughput": 5631.67, "total_tokens": 6877648} {"current_steps": 11300, "total_steps": 64460, "loss": 0.2211, "lr": 9.828330260288984e-06, "epoch": 3.5060502637294446, "percentage": 17.53, "elapsed_time": "0:20:21", "remaining_time": "1:35:47", "throughput": 5631.48, "total_tokens": 6880144} {"current_steps": 11305, "total_steps": 64460, "loss": 0.2225, "lr": 9.827978382137635e-06, "epoch": 3.5076016134036614, "percentage": 17.54, "elapsed_time": "0:20:22", "remaining_time": "1:35:46", "throughput": 5631.52, "total_tokens": 6882960} {"current_steps": 11310, "total_steps": 64460, "loss": 0.2321, "lr": 9.827626150038297e-06, "epoch": 3.5091529630778777, "percentage": 17.55, "elapsed_time": "0:20:22", "remaining_time": "1:35:46", "throughput": 5631.55, "total_tokens": 6885968} {"current_steps": 11315, "total_steps": 64460, "loss": 0.2219, "lr": 9.827273564016796e-06, "epoch": 3.510704312752094, "percentage": 17.55, "elapsed_time": "0:20:23", "remaining_time": "1:35:45", "throughput": 5631.4, "total_tokens": 6888528} {"current_steps": 11320, "total_steps": 64460, "loss": 0.2642, "lr": 9.826920624098978e-06, "epoch": 3.512255662426311, "percentage": 17.56, "elapsed_time": "0:20:23", "remaining_time": "1:35:44", "throughput": 5631.56, "total_tokens": 6891600} {"current_steps": 11325, "total_steps": 64460, "loss": 0.2252, "lr": 9.826567330310721e-06, "epoch": 3.5138070121005276, "percentage": 17.57, "elapsed_time": "0:20:24", "remaining_time": "1:35:44", "throughput": 5631.47, "total_tokens": 6894448} {"current_steps": 11330, "total_steps": 64460, "loss": 0.2348, "lr": 9.826213682677921e-06, "epoch": 3.515358361774744, "percentage": 17.58, "elapsed_time": "0:20:24", "remaining_time": "1:35:43", "throughput": 5631.67, "total_tokens": 6897584} {"current_steps": 11335, "total_steps": 64460, "loss": 0.2198, "lr": 9.82585968122651e-06, "epoch": 3.5169097114489607, "percentage": 17.58, "elapsed_time": "0:20:25", "remaining_time": "1:35:42", "throughput": 5631.45, "total_tokens": 6900112} {"current_steps": 11340, "total_steps": 64460, "loss": 0.2375, "lr": 9.825505325982437e-06, "epoch": 3.518461061123177, "percentage": 17.59, "elapsed_time": "0:20:25", "remaining_time": "1:35:42", "throughput": 5631.73, "total_tokens": 6903600} {"current_steps": 11345, "total_steps": 64460, "loss": 0.2347, "lr": 9.825150616971679e-06, "epoch": 3.520012410797394, "percentage": 17.6, "elapsed_time": "0:20:26", "remaining_time": "1:35:41", "throughput": 5631.51, "total_tokens": 6906256} {"current_steps": 11350, "total_steps": 64460, "loss": 0.2337, "lr": 9.824795554220243e-06, "epoch": 3.5215637604716106, "percentage": 17.61, "elapsed_time": "0:20:26", "remaining_time": "1:35:40", "throughput": 5631.51, "total_tokens": 6908944} {"current_steps": 11355, "total_steps": 64460, "loss": 0.2362, "lr": 9.82444013775416e-06, "epoch": 3.523115110145827, "percentage": 17.62, "elapsed_time": "0:20:27", "remaining_time": "1:35:40", "throughput": 5631.34, "total_tokens": 6911632} {"current_steps": 11360, "total_steps": 64460, "loss": 0.2351, "lr": 9.824084367599484e-06, "epoch": 3.5246664598200432, "percentage": 17.62, "elapsed_time": "0:20:27", "remaining_time": "1:35:39", "throughput": 5631.4, "total_tokens": 6914576} {"current_steps": 11365, "total_steps": 64460, "loss": 0.235, "lr": 9.823728243782298e-06, "epoch": 3.52621780949426, "percentage": 17.63, "elapsed_time": "0:20:28", "remaining_time": "1:35:38", "throughput": 5631.57, "total_tokens": 6917680} {"current_steps": 11370, "total_steps": 64460, "loss": 0.2325, "lr": 9.82337176632871e-06, "epoch": 3.5277691591684768, "percentage": 17.64, "elapsed_time": "0:20:28", "remaining_time": "1:35:37", "throughput": 5631.06, "total_tokens": 6919696} {"current_steps": 11375, "total_steps": 64460, "loss": 0.231, "lr": 9.823014935264856e-06, "epoch": 3.529320508842693, "percentage": 17.65, "elapsed_time": "0:20:29", "remaining_time": "1:35:37", "throughput": 5630.86, "total_tokens": 6922544} {"current_steps": 11380, "total_steps": 64460, "loss": 0.2383, "lr": 9.822657750616894e-06, "epoch": 3.5308718585169094, "percentage": 17.65, "elapsed_time": "0:20:29", "remaining_time": "1:35:36", "throughput": 5630.6, "total_tokens": 6925008} {"current_steps": 11385, "total_steps": 64460, "loss": 0.232, "lr": 9.822300212411009e-06, "epoch": 3.532423208191126, "percentage": 17.66, "elapsed_time": "0:20:30", "remaining_time": "1:35:35", "throughput": 5630.7, "total_tokens": 6927920} {"current_steps": 11390, "total_steps": 64460, "loss": 0.2309, "lr": 9.821942320673414e-06, "epoch": 3.533974557865343, "percentage": 17.67, "elapsed_time": "0:20:30", "remaining_time": "1:35:35", "throughput": 5630.71, "total_tokens": 6930608} {"current_steps": 11395, "total_steps": 64460, "loss": 0.2304, "lr": 9.821584075430348e-06, "epoch": 3.5355259075395593, "percentage": 17.68, "elapsed_time": "0:20:31", "remaining_time": "1:35:34", "throughput": 5630.68, "total_tokens": 6933264} {"current_steps": 11400, "total_steps": 64460, "loss": 0.2304, "lr": 9.821225476708071e-06, "epoch": 3.537077257213776, "percentage": 17.69, "elapsed_time": "0:20:31", "remaining_time": "1:35:33", "throughput": 5630.78, "total_tokens": 6936208} {"current_steps": 11405, "total_steps": 64460, "loss": 0.2324, "lr": 9.820866524532876e-06, "epoch": 3.5386286068879924, "percentage": 17.69, "elapsed_time": "0:20:32", "remaining_time": "1:35:32", "throughput": 5630.71, "total_tokens": 6939024} {"current_steps": 11410, "total_steps": 64460, "loss": 0.2309, "lr": 9.820507218931077e-06, "epoch": 3.540179956562209, "percentage": 17.7, "elapsed_time": "0:20:32", "remaining_time": "1:35:32", "throughput": 5631.06, "total_tokens": 6942256} {"current_steps": 11415, "total_steps": 64460, "loss": 0.2325, "lr": 9.820147559929014e-06, "epoch": 3.541731306236426, "percentage": 17.71, "elapsed_time": "0:20:33", "remaining_time": "1:35:31", "throughput": 5631.43, "total_tokens": 6945712} {"current_steps": 11420, "total_steps": 64460, "loss": 0.2298, "lr": 9.819787547553058e-06, "epoch": 3.5432826559106423, "percentage": 17.72, "elapsed_time": "0:20:33", "remaining_time": "1:35:30", "throughput": 5631.15, "total_tokens": 6948176} {"current_steps": 11425, "total_steps": 64460, "loss": 0.2326, "lr": 9.819427181829598e-06, "epoch": 3.5448340055848586, "percentage": 17.72, "elapsed_time": "0:20:34", "remaining_time": "1:35:30", "throughput": 5631.26, "total_tokens": 6951344} {"current_steps": 11430, "total_steps": 64460, "loss": 0.2326, "lr": 9.819066462785056e-06, "epoch": 3.5463853552590754, "percentage": 17.73, "elapsed_time": "0:20:34", "remaining_time": "1:35:29", "throughput": 5631.5, "total_tokens": 6954672} {"current_steps": 11435, "total_steps": 64460, "loss": 0.2315, "lr": 9.818705390445876e-06, "epoch": 3.547936704933292, "percentage": 17.74, "elapsed_time": "0:20:35", "remaining_time": "1:35:28", "throughput": 5631.62, "total_tokens": 6957680} {"current_steps": 11440, "total_steps": 64460, "loss": 0.2304, "lr": 9.81834396483853e-06, "epoch": 3.5494880546075085, "percentage": 17.75, "elapsed_time": "0:20:35", "remaining_time": "1:35:28", "throughput": 5631.67, "total_tokens": 6960592} {"current_steps": 11445, "total_steps": 64460, "loss": 0.2314, "lr": 9.817982185989511e-06, "epoch": 3.5510394042817253, "percentage": 17.76, "elapsed_time": "0:20:36", "remaining_time": "1:35:27", "throughput": 5632.02, "total_tokens": 6964080} {"current_steps": 11450, "total_steps": 64460, "loss": 0.2299, "lr": 9.817620053925347e-06, "epoch": 3.5525907539559416, "percentage": 17.76, "elapsed_time": "0:20:37", "remaining_time": "1:35:27", "throughput": 5632.17, "total_tokens": 6967632} {"current_steps": 11455, "total_steps": 64460, "loss": 0.2337, "lr": 9.817257568672582e-06, "epoch": 3.5541421036301584, "percentage": 17.77, "elapsed_time": "0:20:37", "remaining_time": "1:35:26", "throughput": 5632.39, "total_tokens": 6970736} {"current_steps": 11460, "total_steps": 64460, "loss": 0.2358, "lr": 9.816894730257793e-06, "epoch": 3.5556934533043747, "percentage": 17.78, "elapsed_time": "0:20:38", "remaining_time": "1:35:26", "throughput": 5632.66, "total_tokens": 6974192} {"current_steps": 11465, "total_steps": 64460, "loss": 0.2284, "lr": 9.81653153870758e-06, "epoch": 3.5572448029785915, "percentage": 17.79, "elapsed_time": "0:20:38", "remaining_time": "1:35:25", "throughput": 5632.56, "total_tokens": 6976912} {"current_steps": 11470, "total_steps": 64460, "loss": 0.2305, "lr": 9.816167994048569e-06, "epoch": 3.558796152652808, "percentage": 17.79, "elapsed_time": "0:20:39", "remaining_time": "1:35:25", "throughput": 5632.75, "total_tokens": 6980784} {"current_steps": 11475, "total_steps": 64460, "loss": 0.2294, "lr": 9.81580409630741e-06, "epoch": 3.5603475023270246, "percentage": 17.8, "elapsed_time": "0:20:39", "remaining_time": "1:35:24", "throughput": 5632.86, "total_tokens": 6983792} {"current_steps": 11480, "total_steps": 64460, "loss": 0.2325, "lr": 9.815439845510786e-06, "epoch": 3.5618988520012413, "percentage": 17.81, "elapsed_time": "0:20:40", "remaining_time": "1:35:23", "throughput": 5632.48, "total_tokens": 6986000} {"current_steps": 11485, "total_steps": 64460, "loss": 0.2325, "lr": 9.815075241685397e-06, "epoch": 3.5634502016754577, "percentage": 17.82, "elapsed_time": "0:20:40", "remaining_time": "1:35:23", "throughput": 5632.39, "total_tokens": 6988688} {"current_steps": 11490, "total_steps": 64460, "loss": 0.2325, "lr": 9.814710284857973e-06, "epoch": 3.565001551349674, "percentage": 17.83, "elapsed_time": "0:20:41", "remaining_time": "1:35:22", "throughput": 5632.45, "total_tokens": 6991408} {"current_steps": 11495, "total_steps": 64460, "loss": 0.2319, "lr": 9.814344975055273e-06, "epoch": 3.5665529010238908, "percentage": 17.83, "elapsed_time": "0:20:41", "remaining_time": "1:35:21", "throughput": 5631.94, "total_tokens": 6993744} {"current_steps": 11500, "total_steps": 64460, "loss": 0.2283, "lr": 9.813979312304072e-06, "epoch": 3.5681042506981075, "percentage": 17.84, "elapsed_time": "0:20:42", "remaining_time": "1:35:20", "throughput": 5631.59, "total_tokens": 6996048} {"current_steps": 11505, "total_steps": 64460, "loss": 0.2299, "lr": 9.813613296631183e-06, "epoch": 3.569655600372324, "percentage": 17.85, "elapsed_time": "0:20:42", "remaining_time": "1:35:20", "throughput": 5631.13, "total_tokens": 6998704} {"current_steps": 11510, "total_steps": 64460, "loss": 0.2315, "lr": 9.81324692806344e-06, "epoch": 3.5712069500465407, "percentage": 17.86, "elapsed_time": "0:20:43", "remaining_time": "1:35:20", "throughput": 5630.83, "total_tokens": 7001488} {"current_steps": 11515, "total_steps": 64460, "loss": 0.2325, "lr": 9.812880206627698e-06, "epoch": 3.572758299720757, "percentage": 17.86, "elapsed_time": "0:20:43", "remaining_time": "1:35:19", "throughput": 5631.02, "total_tokens": 7004784} {"current_steps": 11520, "total_steps": 64460, "loss": 0.2325, "lr": 9.812513132350843e-06, "epoch": 3.5743096493949738, "percentage": 17.87, "elapsed_time": "0:20:44", "remaining_time": "1:35:18", "throughput": 5630.97, "total_tokens": 7007440} {"current_steps": 11525, "total_steps": 64460, "loss": 0.2351, "lr": 9.812145705259786e-06, "epoch": 3.57586099906919, "percentage": 17.88, "elapsed_time": "0:20:45", "remaining_time": "1:35:18", "throughput": 5631.19, "total_tokens": 7011024} {"current_steps": 11530, "total_steps": 64460, "loss": 0.233, "lr": 9.811777925381467e-06, "epoch": 3.577412348743407, "percentage": 17.89, "elapsed_time": "0:20:45", "remaining_time": "1:35:17", "throughput": 5631.11, "total_tokens": 7013616} {"current_steps": 11535, "total_steps": 64460, "loss": 0.2294, "lr": 9.811409792742845e-06, "epoch": 3.578963698417623, "percentage": 17.89, "elapsed_time": "0:20:46", "remaining_time": "1:35:17", "throughput": 5631.06, "total_tokens": 7016880} {"current_steps": 11540, "total_steps": 64460, "loss": 0.2337, "lr": 9.81104130737091e-06, "epoch": 3.58051504809184, "percentage": 17.9, "elapsed_time": "0:20:46", "remaining_time": "1:35:17", "throughput": 5631.68, "total_tokens": 7021904} {"current_steps": 11545, "total_steps": 64460, "loss": 0.2358, "lr": 9.810672469292674e-06, "epoch": 3.5820663977660567, "percentage": 17.91, "elapsed_time": "0:20:47", "remaining_time": "1:35:17", "throughput": 5631.81, "total_tokens": 7024880} {"current_steps": 11550, "total_steps": 64460, "loss": 0.2295, "lr": 9.810303278535182e-06, "epoch": 3.583617747440273, "percentage": 17.92, "elapsed_time": "0:20:47", "remaining_time": "1:35:16", "throughput": 5631.56, "total_tokens": 7027312} {"current_steps": 11555, "total_steps": 64460, "loss": 0.2253, "lr": 9.809933735125495e-06, "epoch": 3.5851690971144894, "percentage": 17.93, "elapsed_time": "0:20:48", "remaining_time": "1:35:15", "throughput": 5631.32, "total_tokens": 7029744} {"current_steps": 11560, "total_steps": 64460, "loss": 0.2397, "lr": 9.809563839090708e-06, "epoch": 3.586720446788706, "percentage": 17.93, "elapsed_time": "0:20:48", "remaining_time": "1:35:14", "throughput": 5631.35, "total_tokens": 7032496} {"current_steps": 11565, "total_steps": 64460, "loss": 0.2338, "lr": 9.809193590457936e-06, "epoch": 3.588271796462923, "percentage": 17.94, "elapsed_time": "0:20:49", "remaining_time": "1:35:13", "throughput": 5631.31, "total_tokens": 7035184} {"current_steps": 11570, "total_steps": 64460, "loss": 0.2295, "lr": 9.808822989254328e-06, "epoch": 3.5898231461371393, "percentage": 17.95, "elapsed_time": "0:20:49", "remaining_time": "1:35:13", "throughput": 5631.6, "total_tokens": 7038832} {"current_steps": 11575, "total_steps": 64460, "loss": 0.2259, "lr": 9.808452035507048e-06, "epoch": 3.591374495811356, "percentage": 17.96, "elapsed_time": "0:20:50", "remaining_time": "1:35:13", "throughput": 5631.76, "total_tokens": 7042032} {"current_steps": 11580, "total_steps": 64460, "loss": 0.2287, "lr": 9.808080729243292e-06, "epoch": 3.5929258454855724, "percentage": 17.96, "elapsed_time": "0:20:50", "remaining_time": "1:35:12", "throughput": 5631.54, "total_tokens": 7044560} {"current_steps": 11585, "total_steps": 64460, "loss": 0.2219, "lr": 9.807709070490284e-06, "epoch": 3.594477195159789, "percentage": 17.97, "elapsed_time": "0:20:51", "remaining_time": "1:35:12", "throughput": 5632.21, "total_tokens": 7049264} {"current_steps": 11590, "total_steps": 64460, "loss": 0.2217, "lr": 9.807337059275269e-06, "epoch": 3.5960285448340055, "percentage": 17.98, "elapsed_time": "0:20:52", "remaining_time": "1:35:12", "throughput": 5632.84, "total_tokens": 7053968} {"current_steps": 11595, "total_steps": 64460, "loss": 0.221, "lr": 9.806964695625521e-06, "epoch": 3.5975798945082222, "percentage": 17.99, "elapsed_time": "0:20:52", "remaining_time": "1:35:11", "throughput": 5632.68, "total_tokens": 7056496} {"current_steps": 11600, "total_steps": 64460, "loss": 0.2311, "lr": 9.806591979568335e-06, "epoch": 3.5991312441824386, "percentage": 18.0, "elapsed_time": "0:20:53", "remaining_time": "1:35:11", "throughput": 5632.67, "total_tokens": 7059376} {"current_steps": 11605, "total_steps": 64460, "loss": 0.2313, "lr": 9.806218911131041e-06, "epoch": 3.6006825938566553, "percentage": 18.0, "elapsed_time": "0:20:53", "remaining_time": "1:35:10", "throughput": 5632.49, "total_tokens": 7061744} {"current_steps": 11610, "total_steps": 64460, "loss": 0.2416, "lr": 9.805845490340987e-06, "epoch": 3.602233943530872, "percentage": 18.01, "elapsed_time": "0:20:54", "remaining_time": "1:35:09", "throughput": 5632.44, "total_tokens": 7064400} {"current_steps": 11615, "total_steps": 64460, "loss": 0.2589, "lr": 9.805471717225548e-06, "epoch": 3.6037852932050884, "percentage": 18.02, "elapsed_time": "0:20:54", "remaining_time": "1:35:09", "throughput": 5632.83, "total_tokens": 7068208} {"current_steps": 11620, "total_steps": 64460, "loss": 0.2322, "lr": 9.805097591812126e-06, "epoch": 3.6053366428793048, "percentage": 18.03, "elapsed_time": "0:20:55", "remaining_time": "1:35:08", "throughput": 5632.71, "total_tokens": 7070896} {"current_steps": 11625, "total_steps": 64460, "loss": 0.2298, "lr": 9.80472311412815e-06, "epoch": 3.6068879925535215, "percentage": 18.03, "elapsed_time": "0:20:55", "remaining_time": "1:35:07", "throughput": 5633.02, "total_tokens": 7074352} {"current_steps": 11630, "total_steps": 64460, "loss": 0.2244, "lr": 9.804348284201073e-06, "epoch": 3.6084393422277383, "percentage": 18.04, "elapsed_time": "0:20:56", "remaining_time": "1:35:07", "throughput": 5632.99, "total_tokens": 7077008} {"current_steps": 11635, "total_steps": 64460, "loss": 0.2335, "lr": 9.803973102058376e-06, "epoch": 3.6099906919019547, "percentage": 18.05, "elapsed_time": "0:20:56", "remaining_time": "1:35:06", "throughput": 5633.2, "total_tokens": 7080048} {"current_steps": 11640, "total_steps": 64460, "loss": 0.2345, "lr": 9.803597567727562e-06, "epoch": 3.6115420415761714, "percentage": 18.06, "elapsed_time": "0:20:57", "remaining_time": "1:35:05", "throughput": 5633.42, "total_tokens": 7083088} {"current_steps": 11645, "total_steps": 64460, "loss": 0.2323, "lr": 9.803221681236164e-06, "epoch": 3.6130933912503878, "percentage": 18.07, "elapsed_time": "0:20:57", "remaining_time": "1:35:05", "throughput": 5633.77, "total_tokens": 7086768} {"current_steps": 11650, "total_steps": 64460, "loss": 0.2322, "lr": 9.802845442611737e-06, "epoch": 3.6146447409246045, "percentage": 18.07, "elapsed_time": "0:20:58", "remaining_time": "1:35:04", "throughput": 5633.61, "total_tokens": 7089200} {"current_steps": 11655, "total_steps": 64460, "loss": 0.2309, "lr": 9.802468851881866e-06, "epoch": 3.616196090598821, "percentage": 18.08, "elapsed_time": "0:20:58", "remaining_time": "1:35:03", "throughput": 5633.23, "total_tokens": 7091280} {"current_steps": 11660, "total_steps": 64460, "loss": 0.2346, "lr": 9.802091909074158e-06, "epoch": 3.6177474402730376, "percentage": 18.09, "elapsed_time": "0:20:59", "remaining_time": "1:35:02", "throughput": 5633.47, "total_tokens": 7094480} {"current_steps": 11665, "total_steps": 64460, "loss": 0.2293, "lr": 9.801714614216246e-06, "epoch": 3.619298789947254, "percentage": 18.1, "elapsed_time": "0:20:59", "remaining_time": "1:35:01", "throughput": 5633.17, "total_tokens": 7096880} {"current_steps": 11670, "total_steps": 64460, "loss": 0.2309, "lr": 9.801336967335796e-06, "epoch": 3.6208501396214707, "percentage": 18.1, "elapsed_time": "0:21:00", "remaining_time": "1:35:01", "throughput": 5633.23, "total_tokens": 7100176} {"current_steps": 11675, "total_steps": 64460, "loss": 0.2299, "lr": 9.800958968460485e-06, "epoch": 3.6224014892956875, "percentage": 18.11, "elapsed_time": "0:21:01", "remaining_time": "1:35:01", "throughput": 5633.89, "total_tokens": 7105008} {"current_steps": 11680, "total_steps": 64460, "loss": 0.2311, "lr": 9.800580617618033e-06, "epoch": 3.623952838969904, "percentage": 18.12, "elapsed_time": "0:21:01", "remaining_time": "1:35:00", "throughput": 5633.55, "total_tokens": 7107216} {"current_steps": 11685, "total_steps": 64460, "loss": 0.2274, "lr": 9.800201914836174e-06, "epoch": 3.62550418864412, "percentage": 18.13, "elapsed_time": "0:21:02", "remaining_time": "1:35:00", "throughput": 5633.44, "total_tokens": 7109808} {"current_steps": 11690, "total_steps": 64460, "loss": 0.2371, "lr": 9.799822860142672e-06, "epoch": 3.627055538318337, "percentage": 18.14, "elapsed_time": "0:21:02", "remaining_time": "1:34:59", "throughput": 5633.49, "total_tokens": 7112848} {"current_steps": 11695, "total_steps": 64460, "loss": 0.2366, "lr": 9.799443453565315e-06, "epoch": 3.6286068879925537, "percentage": 18.14, "elapsed_time": "0:21:03", "remaining_time": "1:34:58", "throughput": 5633.22, "total_tokens": 7115152} {"current_steps": 11700, "total_steps": 64460, "loss": 0.2281, "lr": 9.79906369513192e-06, "epoch": 3.63015823766677, "percentage": 18.15, "elapsed_time": "0:21:03", "remaining_time": "1:34:57", "throughput": 5632.95, "total_tokens": 7117584} {"current_steps": 11705, "total_steps": 64460, "loss": 0.228, "lr": 9.798683584870326e-06, "epoch": 3.631709587340987, "percentage": 18.16, "elapsed_time": "0:21:04", "remaining_time": "1:34:57", "throughput": 5633.02, "total_tokens": 7120528} {"current_steps": 11710, "total_steps": 64460, "loss": 0.229, "lr": 9.798303122808399e-06, "epoch": 3.633260937015203, "percentage": 18.17, "elapsed_time": "0:21:04", "remaining_time": "1:34:56", "throughput": 5633.02, "total_tokens": 7123568} {"current_steps": 11715, "total_steps": 64460, "loss": 0.2337, "lr": 9.797922308974034e-06, "epoch": 3.63481228668942, "percentage": 18.17, "elapsed_time": "0:21:05", "remaining_time": "1:34:55", "throughput": 5632.82, "total_tokens": 7126064} {"current_steps": 11720, "total_steps": 64460, "loss": 0.23, "lr": 9.797541143395149e-06, "epoch": 3.6363636363636362, "percentage": 18.18, "elapsed_time": "0:21:05", "remaining_time": "1:34:55", "throughput": 5632.88, "total_tokens": 7129040} {"current_steps": 11725, "total_steps": 64460, "loss": 0.231, "lr": 9.797159626099686e-06, "epoch": 3.637914986037853, "percentage": 18.19, "elapsed_time": "0:21:06", "remaining_time": "1:34:54", "throughput": 5633.12, "total_tokens": 7132112} {"current_steps": 11730, "total_steps": 64460, "loss": 0.2352, "lr": 9.796777757115614e-06, "epoch": 3.6394663357120693, "percentage": 18.2, "elapsed_time": "0:21:06", "remaining_time": "1:34:53", "throughput": 5632.89, "total_tokens": 7134480} {"current_steps": 11735, "total_steps": 64460, "loss": 0.2321, "lr": 9.796395536470932e-06, "epoch": 3.641017685386286, "percentage": 18.21, "elapsed_time": "0:21:07", "remaining_time": "1:34:53", "throughput": 5633.33, "total_tokens": 7138416} {"current_steps": 11740, "total_steps": 64460, "loss": 0.23, "lr": 9.79601296419366e-06, "epoch": 3.642569035060503, "percentage": 18.21, "elapsed_time": "0:21:07", "remaining_time": "1:34:52", "throughput": 5633.7, "total_tokens": 7141904} {"current_steps": 11745, "total_steps": 64460, "loss": 0.2312, "lr": 9.795630040311842e-06, "epoch": 3.644120384734719, "percentage": 18.22, "elapsed_time": "0:21:08", "remaining_time": "1:34:52", "throughput": 5633.71, "total_tokens": 7145328} {"current_steps": 11750, "total_steps": 64460, "loss": 0.2297, "lr": 9.795246764853555e-06, "epoch": 3.6456717344089355, "percentage": 18.23, "elapsed_time": "0:21:08", "remaining_time": "1:34:52", "throughput": 5633.98, "total_tokens": 7149072} {"current_steps": 11755, "total_steps": 64460, "loss": 0.2327, "lr": 9.794863137846894e-06, "epoch": 3.6472230840831523, "percentage": 18.24, "elapsed_time": "0:21:09", "remaining_time": "1:34:52", "throughput": 5634.22, "total_tokens": 7153008} {"current_steps": 11760, "total_steps": 64460, "loss": 0.2328, "lr": 9.794479159319987e-06, "epoch": 3.648774433757369, "percentage": 18.24, "elapsed_time": "0:21:10", "remaining_time": "1:34:51", "throughput": 5633.79, "total_tokens": 7155280} {"current_steps": 11765, "total_steps": 64460, "loss": 0.2229, "lr": 9.794094829300982e-06, "epoch": 3.6503257834315854, "percentage": 18.25, "elapsed_time": "0:21:10", "remaining_time": "1:34:50", "throughput": 5633.8, "total_tokens": 7158000} {"current_steps": 11770, "total_steps": 64460, "loss": 0.2308, "lr": 9.793710147818056e-06, "epoch": 3.651877133105802, "percentage": 18.26, "elapsed_time": "0:21:11", "remaining_time": "1:34:50", "throughput": 5634.02, "total_tokens": 7161200} {"current_steps": 11775, "total_steps": 64460, "loss": 0.2392, "lr": 9.79332511489941e-06, "epoch": 3.6534284827800185, "percentage": 18.27, "elapsed_time": "0:21:11", "remaining_time": "1:34:49", "throughput": 5634.29, "total_tokens": 7164592} {"current_steps": 11780, "total_steps": 64460, "loss": 0.2218, "lr": 9.792939730573272e-06, "epoch": 3.6549798324542353, "percentage": 18.27, "elapsed_time": "0:21:12", "remaining_time": "1:34:48", "throughput": 5634.3, "total_tokens": 7167376} {"current_steps": 11785, "total_steps": 64460, "loss": 0.2308, "lr": 9.792553994867893e-06, "epoch": 3.6565311821284516, "percentage": 18.28, "elapsed_time": "0:21:12", "remaining_time": "1:34:47", "throughput": 5634.09, "total_tokens": 7169712} {"current_steps": 11790, "total_steps": 64460, "loss": 0.2221, "lr": 9.792167907811556e-06, "epoch": 3.6580825318026684, "percentage": 18.29, "elapsed_time": "0:21:13", "remaining_time": "1:34:47", "throughput": 5634.18, "total_tokens": 7172784} {"current_steps": 11795, "total_steps": 64460, "loss": 0.2232, "lr": 9.791781469432562e-06, "epoch": 3.6596338814768847, "percentage": 18.3, "elapsed_time": "0:21:13", "remaining_time": "1:34:46", "throughput": 5633.84, "total_tokens": 7175184} {"current_steps": 11800, "total_steps": 64460, "loss": 0.2243, "lr": 9.791394679759244e-06, "epoch": 3.6611852311511015, "percentage": 18.31, "elapsed_time": "0:21:14", "remaining_time": "1:34:46", "throughput": 5633.94, "total_tokens": 7178288} {"current_steps": 11805, "total_steps": 64460, "loss": 0.216, "lr": 9.791007538819956e-06, "epoch": 3.6627365808253183, "percentage": 18.31, "elapsed_time": "0:21:14", "remaining_time": "1:34:45", "throughput": 5634.38, "total_tokens": 7182000} {"current_steps": 11810, "total_steps": 64460, "loss": 0.253, "lr": 9.790620046643083e-06, "epoch": 3.6642879304995346, "percentage": 18.32, "elapsed_time": "0:21:15", "remaining_time": "1:34:45", "throughput": 5634.75, "total_tokens": 7186128} {"current_steps": 11815, "total_steps": 64460, "loss": 0.2482, "lr": 9.79023220325703e-06, "epoch": 3.665839280173751, "percentage": 18.33, "elapsed_time": "0:21:15", "remaining_time": "1:34:44", "throughput": 5634.84, "total_tokens": 7188912} {"current_steps": 11820, "total_steps": 64460, "loss": 0.2283, "lr": 9.789844008690234e-06, "epoch": 3.6673906298479677, "percentage": 18.34, "elapsed_time": "0:21:16", "remaining_time": "1:34:44", "throughput": 5635.06, "total_tokens": 7192304} {"current_steps": 11825, "total_steps": 64460, "loss": 0.2252, "lr": 9.789455462971148e-06, "epoch": 3.6689419795221845, "percentage": 18.34, "elapsed_time": "0:21:16", "remaining_time": "1:34:43", "throughput": 5634.65, "total_tokens": 7194416} {"current_steps": 11830, "total_steps": 64460, "loss": 0.235, "lr": 9.789066566128265e-06, "epoch": 3.670493329196401, "percentage": 18.35, "elapsed_time": "0:21:17", "remaining_time": "1:34:42", "throughput": 5634.78, "total_tokens": 7197264} {"current_steps": 11835, "total_steps": 64460, "loss": 0.2306, "lr": 9.78867731819009e-06, "epoch": 3.6720446788706176, "percentage": 18.36, "elapsed_time": "0:21:17", "remaining_time": "1:34:41", "throughput": 5634.39, "total_tokens": 7199728} {"current_steps": 11840, "total_steps": 64460, "loss": 0.2313, "lr": 9.78828771918516e-06, "epoch": 3.673596028544834, "percentage": 18.37, "elapsed_time": "0:21:18", "remaining_time": "1:34:41", "throughput": 5634.43, "total_tokens": 7203376} {"current_steps": 11845, "total_steps": 64460, "loss": 0.2323, "lr": 9.78789776914204e-06, "epoch": 3.6751473782190507, "percentage": 18.38, "elapsed_time": "0:21:18", "remaining_time": "1:34:41", "throughput": 5634.32, "total_tokens": 7206000} {"current_steps": 11850, "total_steps": 64460, "loss": 0.2308, "lr": 9.787507468089317e-06, "epoch": 3.676698727893267, "percentage": 18.38, "elapsed_time": "0:21:19", "remaining_time": "1:34:40", "throughput": 5633.97, "total_tokens": 7208240} {"current_steps": 11855, "total_steps": 64460, "loss": 0.2348, "lr": 9.787116816055603e-06, "epoch": 3.678250077567484, "percentage": 18.39, "elapsed_time": "0:21:19", "remaining_time": "1:34:39", "throughput": 5633.55, "total_tokens": 7210512} {"current_steps": 11860, "total_steps": 64460, "loss": 0.2335, "lr": 9.786725813069537e-06, "epoch": 3.6798014272417, "percentage": 18.4, "elapsed_time": "0:21:20", "remaining_time": "1:34:38", "throughput": 5633.41, "total_tokens": 7213360} {"current_steps": 11865, "total_steps": 64460, "loss": 0.2278, "lr": 9.786334459159787e-06, "epoch": 3.681352776915917, "percentage": 18.41, "elapsed_time": "0:21:20", "remaining_time": "1:34:38", "throughput": 5633.22, "total_tokens": 7215984} {"current_steps": 11870, "total_steps": 64460, "loss": 0.2352, "lr": 9.785942754355043e-06, "epoch": 3.6829041265901337, "percentage": 18.41, "elapsed_time": "0:21:21", "remaining_time": "1:34:37", "throughput": 5633.16, "total_tokens": 7218512} {"current_steps": 11875, "total_steps": 64460, "loss": 0.239, "lr": 9.785550698684019e-06, "epoch": 3.68445547626435, "percentage": 18.42, "elapsed_time": "0:21:21", "remaining_time": "1:34:36", "throughput": 5633.31, "total_tokens": 7221712} {"current_steps": 11880, "total_steps": 64460, "loss": 0.2312, "lr": 9.785158292175461e-06, "epoch": 3.6860068259385663, "percentage": 18.43, "elapsed_time": "0:21:22", "remaining_time": "1:34:36", "throughput": 5633.57, "total_tokens": 7225360} {"current_steps": 11885, "total_steps": 64460, "loss": 0.2362, "lr": 9.784765534858135e-06, "epoch": 3.687558175612783, "percentage": 18.44, "elapsed_time": "0:21:23", "remaining_time": "1:34:35", "throughput": 5633.68, "total_tokens": 7228560} {"current_steps": 11890, "total_steps": 64460, "loss": 0.2369, "lr": 9.784372426760836e-06, "epoch": 3.689109525287, "percentage": 18.45, "elapsed_time": "0:21:23", "remaining_time": "1:34:35", "throughput": 5633.79, "total_tokens": 7231632} {"current_steps": 11895, "total_steps": 64460, "loss": 0.2336, "lr": 9.78397896791238e-06, "epoch": 3.690660874961216, "percentage": 18.45, "elapsed_time": "0:21:24", "remaining_time": "1:34:35", "throughput": 5634.29, "total_tokens": 7236048} {"current_steps": 11900, "total_steps": 64460, "loss": 0.231, "lr": 9.783585158341618e-06, "epoch": 3.692212224635433, "percentage": 18.46, "elapsed_time": "0:21:24", "remaining_time": "1:34:34", "throughput": 5634.49, "total_tokens": 7239184} {"current_steps": 11905, "total_steps": 64460, "loss": 0.2351, "lr": 9.783190998077417e-06, "epoch": 3.6937635743096493, "percentage": 18.47, "elapsed_time": "0:21:25", "remaining_time": "1:34:33", "throughput": 5634.68, "total_tokens": 7242160} {"current_steps": 11910, "total_steps": 64460, "loss": 0.233, "lr": 9.782796487148673e-06, "epoch": 3.695314923983866, "percentage": 18.48, "elapsed_time": "0:21:25", "remaining_time": "1:34:33", "throughput": 5634.76, "total_tokens": 7244912} {"current_steps": 11915, "total_steps": 64460, "loss": 0.233, "lr": 9.78240162558431e-06, "epoch": 3.6968662736580824, "percentage": 18.48, "elapsed_time": "0:21:26", "remaining_time": "1:34:32", "throughput": 5634.73, "total_tokens": 7247792} {"current_steps": 11920, "total_steps": 64460, "loss": 0.2303, "lr": 9.782006413413278e-06, "epoch": 3.698417623332299, "percentage": 18.49, "elapsed_time": "0:21:26", "remaining_time": "1:34:31", "throughput": 5634.82, "total_tokens": 7250704} {"current_steps": 11925, "total_steps": 64460, "loss": 0.2297, "lr": 9.781610850664547e-06, "epoch": 3.6999689730065155, "percentage": 18.5, "elapsed_time": "0:21:27", "remaining_time": "1:34:31", "throughput": 5634.67, "total_tokens": 7253456} {"current_steps": 11930, "total_steps": 64460, "loss": 0.2339, "lr": 9.781214937367118e-06, "epoch": 3.7015203226807323, "percentage": 18.51, "elapsed_time": "0:21:27", "remaining_time": "1:34:30", "throughput": 5635.02, "total_tokens": 7257040} {"current_steps": 11935, "total_steps": 64460, "loss": 0.2319, "lr": 9.780818673550016e-06, "epoch": 3.703071672354949, "percentage": 18.52, "elapsed_time": "0:21:28", "remaining_time": "1:34:29", "throughput": 5635.3, "total_tokens": 7260304} {"current_steps": 11940, "total_steps": 64460, "loss": 0.2274, "lr": 9.780422059242291e-06, "epoch": 3.7046230220291654, "percentage": 18.52, "elapsed_time": "0:21:28", "remaining_time": "1:34:29", "throughput": 5635.42, "total_tokens": 7263280} {"current_steps": 11945, "total_steps": 64460, "loss": 0.2357, "lr": 9.780025094473021e-06, "epoch": 3.7061743717033817, "percentage": 18.53, "elapsed_time": "0:21:29", "remaining_time": "1:34:28", "throughput": 5635.72, "total_tokens": 7266448} {"current_steps": 11950, "total_steps": 64460, "loss": 0.2319, "lr": 9.779627779271308e-06, "epoch": 3.7077257213775985, "percentage": 18.54, "elapsed_time": "0:21:29", "remaining_time": "1:34:28", "throughput": 5635.82, "total_tokens": 7269840} {"current_steps": 11955, "total_steps": 64460, "loss": 0.2361, "lr": 9.77923011366628e-06, "epoch": 3.7092770710518153, "percentage": 18.55, "elapsed_time": "0:21:30", "remaining_time": "1:34:27", "throughput": 5636.11, "total_tokens": 7273072} {"current_steps": 11960, "total_steps": 64460, "loss": 0.2318, "lr": 9.778832097687088e-06, "epoch": 3.7108284207260316, "percentage": 18.55, "elapsed_time": "0:21:31", "remaining_time": "1:34:27", "throughput": 5636.09, "total_tokens": 7276240} {"current_steps": 11965, "total_steps": 64460, "loss": 0.2278, "lr": 9.778433731362915e-06, "epoch": 3.7123797704002484, "percentage": 18.56, "elapsed_time": "0:21:31", "remaining_time": "1:34:27", "throughput": 5636.75, "total_tokens": 7281264} {"current_steps": 11970, "total_steps": 64460, "loss": 0.2315, "lr": 9.778035014722963e-06, "epoch": 3.7139311200744647, "percentage": 18.57, "elapsed_time": "0:21:32", "remaining_time": "1:34:26", "throughput": 5636.75, "total_tokens": 7284208} {"current_steps": 11975, "total_steps": 64460, "loss": 0.225, "lr": 9.777635947796466e-06, "epoch": 3.7154824697486815, "percentage": 18.58, "elapsed_time": "0:21:32", "remaining_time": "1:34:26", "throughput": 5636.72, "total_tokens": 7287152} {"current_steps": 11980, "total_steps": 64460, "loss": 0.2319, "lr": 9.777236530612679e-06, "epoch": 3.717033819422898, "percentage": 18.59, "elapsed_time": "0:21:33", "remaining_time": "1:34:25", "throughput": 5636.85, "total_tokens": 7290576} {"current_steps": 11985, "total_steps": 64460, "loss": 0.2327, "lr": 9.776836763200881e-06, "epoch": 3.7185851690971146, "percentage": 18.59, "elapsed_time": "0:21:33", "remaining_time": "1:34:25", "throughput": 5636.82, "total_tokens": 7293456} {"current_steps": 11990, "total_steps": 64460, "loss": 0.216, "lr": 9.776436645590383e-06, "epoch": 3.720136518771331, "percentage": 18.6, "elapsed_time": "0:21:34", "remaining_time": "1:34:24", "throughput": 5636.88, "total_tokens": 7296560} {"current_steps": 11995, "total_steps": 64460, "loss": 0.2412, "lr": 9.776036177810518e-06, "epoch": 3.7216878684455477, "percentage": 18.61, "elapsed_time": "0:21:34", "remaining_time": "1:34:23", "throughput": 5637.15, "total_tokens": 7299792} {"current_steps": 12000, "total_steps": 64460, "loss": 0.2377, "lr": 9.775635359890643e-06, "epoch": 3.7232392181197644, "percentage": 18.62, "elapsed_time": "0:21:35", "remaining_time": "1:34:23", "throughput": 5637.31, "total_tokens": 7302800} {"current_steps": 12005, "total_steps": 64460, "loss": 0.2374, "lr": 9.775234191860144e-06, "epoch": 3.7247905677939808, "percentage": 18.62, "elapsed_time": "0:21:35", "remaining_time": "1:34:22", "throughput": 5637.31, "total_tokens": 7305584} {"current_steps": 12010, "total_steps": 64460, "loss": 0.2276, "lr": 9.774832673748433e-06, "epoch": 3.726341917468197, "percentage": 18.63, "elapsed_time": "0:21:36", "remaining_time": "1:34:21", "throughput": 5637.31, "total_tokens": 7308432} {"current_steps": 12015, "total_steps": 64460, "loss": 0.2321, "lr": 9.774430805584945e-06, "epoch": 3.727893267142414, "percentage": 18.64, "elapsed_time": "0:21:36", "remaining_time": "1:34:21", "throughput": 5637.31, "total_tokens": 7311184} {"current_steps": 12020, "total_steps": 64460, "loss": 0.2334, "lr": 9.77402858739914e-06, "epoch": 3.7294446168166306, "percentage": 18.65, "elapsed_time": "0:21:37", "remaining_time": "1:34:20", "throughput": 5637.5, "total_tokens": 7314576} {"current_steps": 12025, "total_steps": 64460, "loss": 0.2324, "lr": 9.773626019220506e-06, "epoch": 3.730995966490847, "percentage": 18.65, "elapsed_time": "0:21:38", "remaining_time": "1:34:20", "throughput": 5637.66, "total_tokens": 7318128} {"current_steps": 12030, "total_steps": 64460, "loss": 0.2288, "lr": 9.773223101078557e-06, "epoch": 3.7325473161650637, "percentage": 18.66, "elapsed_time": "0:21:38", "remaining_time": "1:34:19", "throughput": 5637.75, "total_tokens": 7320880} {"current_steps": 12035, "total_steps": 64460, "loss": 0.2268, "lr": 9.772819833002832e-06, "epoch": 3.73409866583928, "percentage": 18.67, "elapsed_time": "0:21:39", "remaining_time": "1:34:18", "throughput": 5637.91, "total_tokens": 7324016} {"current_steps": 12040, "total_steps": 64460, "loss": 0.2354, "lr": 9.772416215022893e-06, "epoch": 3.735650015513497, "percentage": 18.68, "elapsed_time": "0:21:39", "remaining_time": "1:34:18", "throughput": 5638.16, "total_tokens": 7327536} {"current_steps": 12045, "total_steps": 64460, "loss": 0.2255, "lr": 9.772012247168334e-06, "epoch": 3.737201365187713, "percentage": 18.69, "elapsed_time": "0:21:40", "remaining_time": "1:34:17", "throughput": 5637.76, "total_tokens": 7329968} {"current_steps": 12050, "total_steps": 64460, "loss": 0.2351, "lr": 9.771607929468768e-06, "epoch": 3.73875271486193, "percentage": 18.69, "elapsed_time": "0:21:40", "remaining_time": "1:34:17", "throughput": 5637.62, "total_tokens": 7332720} {"current_steps": 12055, "total_steps": 64460, "loss": 0.237, "lr": 9.771203261953835e-06, "epoch": 3.7403040645361463, "percentage": 18.7, "elapsed_time": "0:21:41", "remaining_time": "1:34:16", "throughput": 5637.78, "total_tokens": 7336432} {"current_steps": 12060, "total_steps": 64460, "loss": 0.2324, "lr": 9.770798244653203e-06, "epoch": 3.741855414210363, "percentage": 18.71, "elapsed_time": "0:21:41", "remaining_time": "1:34:16", "throughput": 5637.96, "total_tokens": 7339440} {"current_steps": 12065, "total_steps": 64460, "loss": 0.2322, "lr": 9.770392877596566e-06, "epoch": 3.74340676388458, "percentage": 18.72, "elapsed_time": "0:21:42", "remaining_time": "1:34:15", "throughput": 5638.02, "total_tokens": 7342640} {"current_steps": 12070, "total_steps": 64460, "loss": 0.2268, "lr": 9.769987160813641e-06, "epoch": 3.744958113558796, "percentage": 18.72, "elapsed_time": "0:21:42", "remaining_time": "1:34:14", "throughput": 5638.01, "total_tokens": 7345392} {"current_steps": 12075, "total_steps": 64460, "loss": 0.2327, "lr": 9.769581094334173e-06, "epoch": 3.7465094632330125, "percentage": 18.73, "elapsed_time": "0:21:43", "remaining_time": "1:34:14", "throughput": 5637.66, "total_tokens": 7348080} {"current_steps": 12080, "total_steps": 64460, "loss": 0.23, "lr": 9.769174678187929e-06, "epoch": 3.7480608129072293, "percentage": 18.74, "elapsed_time": "0:21:43", "remaining_time": "1:34:13", "throughput": 5637.76, "total_tokens": 7350992} {"current_steps": 12085, "total_steps": 64460, "loss": 0.2307, "lr": 9.768767912404706e-06, "epoch": 3.749612162581446, "percentage": 18.75, "elapsed_time": "0:21:44", "remaining_time": "1:34:13", "throughput": 5637.55, "total_tokens": 7353712} {"current_steps": 12090, "total_steps": 64460, "loss": 0.2276, "lr": 9.768360797014325e-06, "epoch": 3.7511635122556624, "percentage": 18.76, "elapsed_time": "0:21:45", "remaining_time": "1:34:13", "throughput": 5638.11, "total_tokens": 7358096} {"current_steps": 12095, "total_steps": 64460, "loss": 0.2364, "lr": 9.767953332046631e-06, "epoch": 3.752714861929879, "percentage": 18.76, "elapsed_time": "0:21:45", "remaining_time": "1:34:12", "throughput": 5638.17, "total_tokens": 7361104} {"current_steps": 12100, "total_steps": 64460, "loss": 0.2284, "lr": 9.767545517531495e-06, "epoch": 3.7542662116040955, "percentage": 18.77, "elapsed_time": "0:21:46", "remaining_time": "1:34:11", "throughput": 5637.93, "total_tokens": 7363568} {"current_steps": 12105, "total_steps": 64460, "loss": 0.24, "lr": 9.76713735349882e-06, "epoch": 3.7558175612783122, "percentage": 18.78, "elapsed_time": "0:21:46", "remaining_time": "1:34:11", "throughput": 5637.99, "total_tokens": 7366544} {"current_steps": 12110, "total_steps": 64460, "loss": 0.2313, "lr": 9.766728839978524e-06, "epoch": 3.7573689109525286, "percentage": 18.79, "elapsed_time": "0:21:47", "remaining_time": "1:34:10", "throughput": 5638.1, "total_tokens": 7369552} {"current_steps": 12115, "total_steps": 64460, "loss": 0.2365, "lr": 9.766319977000558e-06, "epoch": 3.7589202606267453, "percentage": 18.79, "elapsed_time": "0:21:47", "remaining_time": "1:34:09", "throughput": 5638.04, "total_tokens": 7372400} {"current_steps": 12120, "total_steps": 64460, "loss": 0.2291, "lr": 9.765910764594895e-06, "epoch": 3.7604716103009617, "percentage": 18.8, "elapsed_time": "0:21:48", "remaining_time": "1:34:09", "throughput": 5638.16, "total_tokens": 7375664} {"current_steps": 12125, "total_steps": 64460, "loss": 0.238, "lr": 9.765501202791537e-06, "epoch": 3.7620229599751784, "percentage": 18.81, "elapsed_time": "0:21:48", "remaining_time": "1:34:08", "throughput": 5637.7, "total_tokens": 7377840} {"current_steps": 12130, "total_steps": 64460, "loss": 0.2309, "lr": 9.765091291620507e-06, "epoch": 3.763574309649395, "percentage": 18.82, "elapsed_time": "0:21:49", "remaining_time": "1:34:07", "throughput": 5637.56, "total_tokens": 7380528} {"current_steps": 12135, "total_steps": 64460, "loss": 0.2319, "lr": 9.76468103111186e-06, "epoch": 3.7651256593236115, "percentage": 18.83, "elapsed_time": "0:21:49", "remaining_time": "1:34:07", "throughput": 5637.77, "total_tokens": 7383664} {"current_steps": 12140, "total_steps": 64460, "loss": 0.2283, "lr": 9.764270421295672e-06, "epoch": 3.766677008997828, "percentage": 18.83, "elapsed_time": "0:21:50", "remaining_time": "1:34:06", "throughput": 5637.86, "total_tokens": 7386672} {"current_steps": 12145, "total_steps": 64460, "loss": 0.2293, "lr": 9.763859462202043e-06, "epoch": 3.7682283586720446, "percentage": 18.84, "elapsed_time": "0:21:50", "remaining_time": "1:34:05", "throughput": 5637.88, "total_tokens": 7389328} {"current_steps": 12150, "total_steps": 64460, "loss": 0.231, "lr": 9.763448153861104e-06, "epoch": 3.7697797083462614, "percentage": 18.85, "elapsed_time": "0:21:51", "remaining_time": "1:34:04", "throughput": 5637.59, "total_tokens": 7391632} {"current_steps": 12155, "total_steps": 64460, "loss": 0.229, "lr": 9.763036496303007e-06, "epoch": 3.7713310580204777, "percentage": 18.86, "elapsed_time": "0:21:51", "remaining_time": "1:34:04", "throughput": 5637.93, "total_tokens": 7395088} {"current_steps": 12160, "total_steps": 64460, "loss": 0.2334, "lr": 9.762624489557933e-06, "epoch": 3.7728824076946945, "percentage": 18.86, "elapsed_time": "0:21:52", "remaining_time": "1:34:03", "throughput": 5637.98, "total_tokens": 7398000} {"current_steps": 12165, "total_steps": 64460, "loss": 0.2374, "lr": 9.762212133656084e-06, "epoch": 3.774433757368911, "percentage": 18.87, "elapsed_time": "0:21:52", "remaining_time": "1:34:02", "throughput": 5638.14, "total_tokens": 7401104} {"current_steps": 12170, "total_steps": 64460, "loss": 0.2382, "lr": 9.761799428627693e-06, "epoch": 3.7759851070431276, "percentage": 18.88, "elapsed_time": "0:21:53", "remaining_time": "1:34:02", "throughput": 5638.24, "total_tokens": 7404176} {"current_steps": 12175, "total_steps": 64460, "loss": 0.2236, "lr": 9.761386374503017e-06, "epoch": 3.777536456717344, "percentage": 18.89, "elapsed_time": "0:21:53", "remaining_time": "1:34:01", "throughput": 5638.32, "total_tokens": 7407280} {"current_steps": 12180, "total_steps": 64460, "loss": 0.2355, "lr": 9.760972971312337e-06, "epoch": 3.7790878063915607, "percentage": 18.9, "elapsed_time": "0:21:54", "remaining_time": "1:34:01", "throughput": 5638.57, "total_tokens": 7410384} {"current_steps": 12185, "total_steps": 64460, "loss": 0.2308, "lr": 9.760559219085958e-06, "epoch": 3.780639156065777, "percentage": 18.9, "elapsed_time": "0:21:54", "remaining_time": "1:34:00", "throughput": 5638.77, "total_tokens": 7413456} {"current_steps": 12190, "total_steps": 64460, "loss": 0.2288, "lr": 9.760145117854216e-06, "epoch": 3.782190505739994, "percentage": 18.91, "elapsed_time": "0:21:55", "remaining_time": "1:33:59", "throughput": 5638.76, "total_tokens": 7416016} {"current_steps": 12195, "total_steps": 64460, "loss": 0.2231, "lr": 9.759730667647467e-06, "epoch": 3.7837418554142106, "percentage": 18.92, "elapsed_time": "0:21:55", "remaining_time": "1:33:58", "throughput": 5638.81, "total_tokens": 7418864} {"current_steps": 12200, "total_steps": 64460, "loss": 0.2346, "lr": 9.759315868496097e-06, "epoch": 3.785293205088427, "percentage": 18.93, "elapsed_time": "0:21:56", "remaining_time": "1:33:57", "throughput": 5638.65, "total_tokens": 7421168} {"current_steps": 12205, "total_steps": 64460, "loss": 0.2319, "lr": 9.758900720430516e-06, "epoch": 3.7868445547626433, "percentage": 18.93, "elapsed_time": "0:21:56", "remaining_time": "1:33:57", "throughput": 5638.85, "total_tokens": 7424560} {"current_steps": 12210, "total_steps": 64460, "loss": 0.2364, "lr": 9.758485223481158e-06, "epoch": 3.78839590443686, "percentage": 18.94, "elapsed_time": "0:21:57", "remaining_time": "1:33:56", "throughput": 5639.11, "total_tokens": 7427824} {"current_steps": 12215, "total_steps": 64460, "loss": 0.2289, "lr": 9.758069377678485e-06, "epoch": 3.789947254111077, "percentage": 18.95, "elapsed_time": "0:21:57", "remaining_time": "1:33:56", "throughput": 5638.74, "total_tokens": 7430864} {"current_steps": 12220, "total_steps": 64460, "loss": 0.2343, "lr": 9.757653183052981e-06, "epoch": 3.791498603785293, "percentage": 18.96, "elapsed_time": "0:21:58", "remaining_time": "1:33:55", "throughput": 5639.08, "total_tokens": 7434416} {"current_steps": 12225, "total_steps": 64460, "loss": 0.2281, "lr": 9.75723663963516e-06, "epoch": 3.79304995345951, "percentage": 18.97, "elapsed_time": "0:21:58", "remaining_time": "1:33:55", "throughput": 5638.97, "total_tokens": 7436816} {"current_steps": 12230, "total_steps": 64460, "loss": 0.2326, "lr": 9.756819747455559e-06, "epoch": 3.7946013031337262, "percentage": 18.97, "elapsed_time": "0:21:59", "remaining_time": "1:33:54", "throughput": 5638.43, "total_tokens": 7439120} {"current_steps": 12235, "total_steps": 64460, "loss": 0.2331, "lr": 9.756402506544743e-06, "epoch": 3.796152652807943, "percentage": 18.98, "elapsed_time": "0:21:59", "remaining_time": "1:33:53", "throughput": 5638.26, "total_tokens": 7441584} {"current_steps": 12240, "total_steps": 64460, "loss": 0.23, "lr": 9.755984916933298e-06, "epoch": 3.7977040024821593, "percentage": 18.99, "elapsed_time": "0:22:00", "remaining_time": "1:33:53", "throughput": 5638.51, "total_tokens": 7445136} {"current_steps": 12245, "total_steps": 64460, "loss": 0.2324, "lr": 9.755566978651837e-06, "epoch": 3.799255352156376, "percentage": 19.0, "elapsed_time": "0:22:00", "remaining_time": "1:33:52", "throughput": 5638.51, "total_tokens": 7447952} {"current_steps": 12250, "total_steps": 64460, "loss": 0.2298, "lr": 9.755148691731007e-06, "epoch": 3.8008067018305924, "percentage": 19.0, "elapsed_time": "0:22:01", "remaining_time": "1:33:52", "throughput": 5638.99, "total_tokens": 7451664} {"current_steps": 12255, "total_steps": 64460, "loss": 0.2314, "lr": 9.754730056201465e-06, "epoch": 3.802358051504809, "percentage": 19.01, "elapsed_time": "0:22:02", "remaining_time": "1:33:51", "throughput": 5639.13, "total_tokens": 7455120} {"current_steps": 12260, "total_steps": 64460, "loss": 0.2325, "lr": 9.754311072093907e-06, "epoch": 3.803909401179026, "percentage": 19.02, "elapsed_time": "0:22:02", "remaining_time": "1:33:51", "throughput": 5639.3, "total_tokens": 7458192} {"current_steps": 12265, "total_steps": 64460, "loss": 0.2321, "lr": 9.753891739439047e-06, "epoch": 3.8054607508532423, "percentage": 19.03, "elapsed_time": "0:22:03", "remaining_time": "1:33:50", "throughput": 5639.3, "total_tokens": 7461040} {"current_steps": 12270, "total_steps": 64460, "loss": 0.2345, "lr": 9.753472058267628e-06, "epoch": 3.8070121005274586, "percentage": 19.04, "elapsed_time": "0:22:03", "remaining_time": "1:33:49", "throughput": 5639.1, "total_tokens": 7463664} {"current_steps": 12275, "total_steps": 64460, "loss": 0.232, "lr": 9.753052028610418e-06, "epoch": 3.8085634502016754, "percentage": 19.04, "elapsed_time": "0:22:04", "remaining_time": "1:33:49", "throughput": 5638.87, "total_tokens": 7466224} {"current_steps": 12280, "total_steps": 64460, "loss": 0.2305, "lr": 9.75263165049821e-06, "epoch": 3.810114799875892, "percentage": 19.05, "elapsed_time": "0:22:04", "remaining_time": "1:33:48", "throughput": 5639.12, "total_tokens": 7469680} {"current_steps": 12285, "total_steps": 64460, "loss": 0.2295, "lr": 9.752210923961821e-06, "epoch": 3.8116661495501085, "percentage": 19.06, "elapsed_time": "0:22:05", "remaining_time": "1:33:47", "throughput": 5639.21, "total_tokens": 7472720} {"current_steps": 12290, "total_steps": 64460, "loss": 0.2337, "lr": 9.751789849032098e-06, "epoch": 3.8132174992243253, "percentage": 19.07, "elapsed_time": "0:22:05", "remaining_time": "1:33:47", "throughput": 5639.35, "total_tokens": 7475632} {"current_steps": 12295, "total_steps": 64460, "loss": 0.2316, "lr": 9.751368425739908e-06, "epoch": 3.8147688488985416, "percentage": 19.07, "elapsed_time": "0:22:06", "remaining_time": "1:33:46", "throughput": 5639.45, "total_tokens": 7478736} {"current_steps": 12300, "total_steps": 64460, "loss": 0.233, "lr": 9.75094665411615e-06, "epoch": 3.8163201985727584, "percentage": 19.08, "elapsed_time": "0:22:06", "remaining_time": "1:33:46", "throughput": 5639.96, "total_tokens": 7483056} {"current_steps": 12305, "total_steps": 64460, "loss": 0.2288, "lr": 9.750524534191741e-06, "epoch": 3.8178715482469747, "percentage": 19.09, "elapsed_time": "0:22:07", "remaining_time": "1:33:45", "throughput": 5639.86, "total_tokens": 7485680} {"current_steps": 12310, "total_steps": 64460, "loss": 0.2294, "lr": 9.750102065997631e-06, "epoch": 3.8194228979211915, "percentage": 19.1, "elapsed_time": "0:22:07", "remaining_time": "1:33:45", "throughput": 5640.27, "total_tokens": 7489264} {"current_steps": 12315, "total_steps": 64460, "loss": 0.2259, "lr": 9.749679249564787e-06, "epoch": 3.820974247595408, "percentage": 19.1, "elapsed_time": "0:22:08", "remaining_time": "1:33:44", "throughput": 5640.11, "total_tokens": 7491728} {"current_steps": 12320, "total_steps": 64460, "loss": 0.2314, "lr": 9.749256084924212e-06, "epoch": 3.8225255972696246, "percentage": 19.11, "elapsed_time": "0:22:09", "remaining_time": "1:33:44", "throughput": 5640.74, "total_tokens": 7496848} {"current_steps": 12325, "total_steps": 64460, "loss": 0.232, "lr": 9.748832572106925e-06, "epoch": 3.8240769469438414, "percentage": 19.12, "elapsed_time": "0:22:09", "remaining_time": "1:33:44", "throughput": 5640.68, "total_tokens": 7499824} {"current_steps": 12330, "total_steps": 64460, "loss": 0.2338, "lr": 9.748408711143977e-06, "epoch": 3.8256282966180577, "percentage": 19.13, "elapsed_time": "0:22:10", "remaining_time": "1:33:44", "throughput": 5640.81, "total_tokens": 7503568} {"current_steps": 12335, "total_steps": 64460, "loss": 0.2265, "lr": 9.747984502066438e-06, "epoch": 3.827179646292274, "percentage": 19.14, "elapsed_time": "0:22:10", "remaining_time": "1:33:43", "throughput": 5640.56, "total_tokens": 7506416} {"current_steps": 12340, "total_steps": 64460, "loss": 0.2333, "lr": 9.747559944905413e-06, "epoch": 3.828730995966491, "percentage": 19.14, "elapsed_time": "0:22:11", "remaining_time": "1:33:42", "throughput": 5640.56, "total_tokens": 7509136} {"current_steps": 12345, "total_steps": 64460, "loss": 0.2318, "lr": 9.747135039692024e-06, "epoch": 3.8302823456407076, "percentage": 19.15, "elapsed_time": "0:22:11", "remaining_time": "1:33:42", "throughput": 5640.49, "total_tokens": 7512144} {"current_steps": 12350, "total_steps": 64460, "loss": 0.2324, "lr": 9.746709786457422e-06, "epoch": 3.831833695314924, "percentage": 19.16, "elapsed_time": "0:22:12", "remaining_time": "1:33:41", "throughput": 5640.56, "total_tokens": 7515440} {"current_steps": 12355, "total_steps": 64460, "loss": 0.2314, "lr": 9.746284185232783e-06, "epoch": 3.8333850449891407, "percentage": 19.17, "elapsed_time": "0:22:12", "remaining_time": "1:33:41", "throughput": 5640.71, "total_tokens": 7518384} {"current_steps": 12360, "total_steps": 64460, "loss": 0.2333, "lr": 9.74585823604931e-06, "epoch": 3.834936394663357, "percentage": 19.17, "elapsed_time": "0:22:13", "remaining_time": "1:33:40", "throughput": 5640.57, "total_tokens": 7520912} {"current_steps": 12365, "total_steps": 64460, "loss": 0.2341, "lr": 9.745431938938227e-06, "epoch": 3.836487744337574, "percentage": 19.18, "elapsed_time": "0:22:13", "remaining_time": "1:33:39", "throughput": 5640.47, "total_tokens": 7523632} {"current_steps": 12370, "total_steps": 64460, "loss": 0.232, "lr": 9.745005293930791e-06, "epoch": 3.83803909401179, "percentage": 19.19, "elapsed_time": "0:22:14", "remaining_time": "1:33:38", "throughput": 5640.28, "total_tokens": 7526064} {"current_steps": 12375, "total_steps": 64460, "loss": 0.2329, "lr": 9.744578301058276e-06, "epoch": 3.839590443686007, "percentage": 19.2, "elapsed_time": "0:22:14", "remaining_time": "1:33:38", "throughput": 5640.57, "total_tokens": 7529680} {"current_steps": 12380, "total_steps": 64460, "loss": 0.2299, "lr": 9.744150960351989e-06, "epoch": 3.841141793360223, "percentage": 19.21, "elapsed_time": "0:22:15", "remaining_time": "1:33:37", "throughput": 5640.29, "total_tokens": 7532176} {"current_steps": 12385, "total_steps": 64460, "loss": 0.233, "lr": 9.743723271843255e-06, "epoch": 3.84269314303444, "percentage": 19.21, "elapsed_time": "0:22:15", "remaining_time": "1:33:37", "throughput": 5640.41, "total_tokens": 7535216} {"current_steps": 12390, "total_steps": 64460, "loss": 0.2331, "lr": 9.743295235563432e-06, "epoch": 3.8442444927086568, "percentage": 19.22, "elapsed_time": "0:22:16", "remaining_time": "1:33:36", "throughput": 5640.3, "total_tokens": 7537840} {"current_steps": 12395, "total_steps": 64460, "loss": 0.231, "lr": 9.742866851543899e-06, "epoch": 3.845795842382873, "percentage": 19.23, "elapsed_time": "0:22:16", "remaining_time": "1:33:35", "throughput": 5640.01, "total_tokens": 7540112} {"current_steps": 12400, "total_steps": 64460, "loss": 0.2299, "lr": 9.742438119816062e-06, "epoch": 3.8473471920570894, "percentage": 19.24, "elapsed_time": "0:22:17", "remaining_time": "1:33:35", "throughput": 5640.71, "total_tokens": 7544592} {"current_steps": 12405, "total_steps": 64460, "loss": 0.2357, "lr": 9.742009040411353e-06, "epoch": 3.848898541731306, "percentage": 19.24, "elapsed_time": "0:22:18", "remaining_time": "1:33:34", "throughput": 5640.76, "total_tokens": 7547536} {"current_steps": 12410, "total_steps": 64460, "loss": 0.2342, "lr": 9.741579613361227e-06, "epoch": 3.850449891405523, "percentage": 19.25, "elapsed_time": "0:22:18", "remaining_time": "1:33:34", "throughput": 5640.93, "total_tokens": 7551184} {"current_steps": 12415, "total_steps": 64460, "loss": 0.2336, "lr": 9.741149838697165e-06, "epoch": 3.8520012410797393, "percentage": 19.26, "elapsed_time": "0:22:19", "remaining_time": "1:33:33", "throughput": 5640.72, "total_tokens": 7553616} {"current_steps": 12420, "total_steps": 64460, "loss": 0.2293, "lr": 9.740719716450679e-06, "epoch": 3.853552590753956, "percentage": 19.27, "elapsed_time": "0:22:19", "remaining_time": "1:33:33", "throughput": 5640.91, "total_tokens": 7556720} {"current_steps": 12425, "total_steps": 64460, "loss": 0.2299, "lr": 9.740289246653298e-06, "epoch": 3.8551039404281724, "percentage": 19.28, "elapsed_time": "0:22:20", "remaining_time": "1:33:32", "throughput": 5640.75, "total_tokens": 7559664} {"current_steps": 12430, "total_steps": 64460, "loss": 0.2309, "lr": 9.73985842933658e-06, "epoch": 3.856655290102389, "percentage": 19.28, "elapsed_time": "0:22:20", "remaining_time": "1:33:32", "throughput": 5640.96, "total_tokens": 7563056} {"current_steps": 12435, "total_steps": 64460, "loss": 0.2314, "lr": 9.739427264532114e-06, "epoch": 3.8582066397766055, "percentage": 19.29, "elapsed_time": "0:22:21", "remaining_time": "1:33:31", "throughput": 5641.06, "total_tokens": 7565904} {"current_steps": 12440, "total_steps": 64460, "loss": 0.2314, "lr": 9.738995752271505e-06, "epoch": 3.8597579894508223, "percentage": 19.3, "elapsed_time": "0:22:21", "remaining_time": "1:33:30", "throughput": 5640.9, "total_tokens": 7568400} {"current_steps": 12445, "total_steps": 64460, "loss": 0.2341, "lr": 9.738563892586388e-06, "epoch": 3.8613093391250386, "percentage": 19.31, "elapsed_time": "0:22:22", "remaining_time": "1:33:30", "throughput": 5641.14, "total_tokens": 7571760} {"current_steps": 12450, "total_steps": 64460, "loss": 0.233, "lr": 9.738131685508427e-06, "epoch": 3.8628606887992554, "percentage": 19.31, "elapsed_time": "0:22:22", "remaining_time": "1:33:29", "throughput": 5640.99, "total_tokens": 7574416} {"current_steps": 12455, "total_steps": 64460, "loss": 0.2304, "lr": 9.737699131069303e-06, "epoch": 3.864412038473472, "percentage": 19.32, "elapsed_time": "0:22:23", "remaining_time": "1:33:28", "throughput": 5640.99, "total_tokens": 7577232} {"current_steps": 12460, "total_steps": 64460, "loss": 0.2346, "lr": 9.73726622930073e-06, "epoch": 3.8659633881476885, "percentage": 19.33, "elapsed_time": "0:22:23", "remaining_time": "1:33:27", "throughput": 5640.63, "total_tokens": 7579376} {"current_steps": 12465, "total_steps": 64460, "loss": 0.2278, "lr": 9.736832980234447e-06, "epoch": 3.867514737821905, "percentage": 19.34, "elapsed_time": "0:22:24", "remaining_time": "1:33:27", "throughput": 5640.42, "total_tokens": 7581904} {"current_steps": 12470, "total_steps": 64460, "loss": 0.2294, "lr": 9.736399383902213e-06, "epoch": 3.8690660874961216, "percentage": 19.35, "elapsed_time": "0:22:24", "remaining_time": "1:33:26", "throughput": 5640.29, "total_tokens": 7584656} {"current_steps": 12475, "total_steps": 64460, "loss": 0.2303, "lr": 9.735965440335818e-06, "epoch": 3.8706174371703383, "percentage": 19.35, "elapsed_time": "0:22:25", "remaining_time": "1:33:26", "throughput": 5640.41, "total_tokens": 7588272} {"current_steps": 12480, "total_steps": 64460, "loss": 0.2304, "lr": 9.735531149567072e-06, "epoch": 3.8721687868445547, "percentage": 19.36, "elapsed_time": "0:22:25", "remaining_time": "1:33:26", "throughput": 5640.65, "total_tokens": 7592304} {"current_steps": 12485, "total_steps": 64460, "loss": 0.234, "lr": 9.735096511627817e-06, "epoch": 3.8737201365187715, "percentage": 19.37, "elapsed_time": "0:22:26", "remaining_time": "1:33:25", "throughput": 5640.81, "total_tokens": 7595504} {"current_steps": 12490, "total_steps": 64460, "loss": 0.2309, "lr": 9.734661526549916e-06, "epoch": 3.875271486192988, "percentage": 19.38, "elapsed_time": "0:22:27", "remaining_time": "1:33:25", "throughput": 5640.47, "total_tokens": 7598032} {"current_steps": 12495, "total_steps": 64460, "loss": 0.2274, "lr": 9.734226194365257e-06, "epoch": 3.8768228358672046, "percentage": 19.38, "elapsed_time": "0:22:27", "remaining_time": "1:33:24", "throughput": 5640.5, "total_tokens": 7600752} {"current_steps": 12500, "total_steps": 64460, "loss": 0.2306, "lr": 9.733790515105756e-06, "epoch": 3.878374185541421, "percentage": 19.39, "elapsed_time": "0:22:28", "remaining_time": "1:33:23", "throughput": 5640.41, "total_tokens": 7603536} {"current_steps": 12505, "total_steps": 64460, "loss": 0.2305, "lr": 9.733354488803356e-06, "epoch": 3.8799255352156377, "percentage": 19.4, "elapsed_time": "0:22:28", "remaining_time": "1:33:22", "throughput": 5640.18, "total_tokens": 7605936} {"current_steps": 12510, "total_steps": 64460, "loss": 0.2387, "lr": 9.732918115490017e-06, "epoch": 3.881476884889854, "percentage": 19.41, "elapsed_time": "0:22:29", "remaining_time": "1:33:22", "throughput": 5640.32, "total_tokens": 7609232} {"current_steps": 12515, "total_steps": 64460, "loss": 0.233, "lr": 9.732481395197736e-06, "epoch": 3.8830282345640708, "percentage": 19.42, "elapsed_time": "0:22:29", "remaining_time": "1:33:21", "throughput": 5640.1, "total_tokens": 7611696} {"current_steps": 12520, "total_steps": 64460, "loss": 0.2375, "lr": 9.73204432795853e-06, "epoch": 3.8845795842382875, "percentage": 19.42, "elapsed_time": "0:22:30", "remaining_time": "1:33:21", "throughput": 5639.82, "total_tokens": 7614480} {"current_steps": 12525, "total_steps": 64460, "loss": 0.2289, "lr": 9.731606913804437e-06, "epoch": 3.886130933912504, "percentage": 19.43, "elapsed_time": "0:22:30", "remaining_time": "1:33:20", "throughput": 5639.46, "total_tokens": 7617040} {"current_steps": 12530, "total_steps": 64460, "loss": 0.233, "lr": 9.731169152767526e-06, "epoch": 3.88768228358672, "percentage": 19.44, "elapsed_time": "0:22:31", "remaining_time": "1:33:19", "throughput": 5639.66, "total_tokens": 7620272} {"current_steps": 12535, "total_steps": 64460, "loss": 0.2304, "lr": 9.730731044879891e-06, "epoch": 3.889233633260937, "percentage": 19.45, "elapsed_time": "0:22:31", "remaining_time": "1:33:19", "throughput": 5639.85, "total_tokens": 7623632} {"current_steps": 12540, "total_steps": 64460, "loss": 0.2283, "lr": 9.73029259017365e-06, "epoch": 3.8907849829351537, "percentage": 19.45, "elapsed_time": "0:22:32", "remaining_time": "1:33:18", "throughput": 5640.07, "total_tokens": 7626928} {"current_steps": 12545, "total_steps": 64460, "loss": 0.233, "lr": 9.72985378868095e-06, "epoch": 3.89233633260937, "percentage": 19.46, "elapsed_time": "0:22:32", "remaining_time": "1:33:18", "throughput": 5639.71, "total_tokens": 7629296} {"current_steps": 12550, "total_steps": 64460, "loss": 0.2345, "lr": 9.729414640433955e-06, "epoch": 3.893887682283587, "percentage": 19.47, "elapsed_time": "0:22:33", "remaining_time": "1:33:17", "throughput": 5640.01, "total_tokens": 7632976} {"current_steps": 12555, "total_steps": 64460, "loss": 0.2336, "lr": 9.72897514546486e-06, "epoch": 3.895439031957803, "percentage": 19.48, "elapsed_time": "0:22:33", "remaining_time": "1:33:17", "throughput": 5639.75, "total_tokens": 7635600} {"current_steps": 12560, "total_steps": 64460, "loss": 0.231, "lr": 9.72853530380589e-06, "epoch": 3.89699038163202, "percentage": 19.48, "elapsed_time": "0:22:34", "remaining_time": "1:33:17", "throughput": 5640.36, "total_tokens": 7640272} {"current_steps": 12565, "total_steps": 64460, "loss": 0.2315, "lr": 9.728095115489289e-06, "epoch": 3.8985417313062363, "percentage": 19.49, "elapsed_time": "0:22:35", "remaining_time": "1:33:16", "throughput": 5640.31, "total_tokens": 7643280} {"current_steps": 12570, "total_steps": 64460, "loss": 0.2331, "lr": 9.727654580547325e-06, "epoch": 3.900093080980453, "percentage": 19.5, "elapsed_time": "0:22:35", "remaining_time": "1:33:17", "throughput": 5640.99, "total_tokens": 7648688} {"current_steps": 12575, "total_steps": 64460, "loss": 0.233, "lr": 9.727213699012296e-06, "epoch": 3.9016444306546694, "percentage": 19.51, "elapsed_time": "0:22:36", "remaining_time": "1:33:17", "throughput": 5641.26, "total_tokens": 7653296} {"current_steps": 12580, "total_steps": 64460, "loss": 0.2284, "lr": 9.726772470916527e-06, "epoch": 3.903195780328886, "percentage": 19.52, "elapsed_time": "0:22:37", "remaining_time": "1:33:17", "throughput": 5641.05, "total_tokens": 7656016} {"current_steps": 12585, "total_steps": 64460, "loss": 0.2299, "lr": 9.72633089629236e-06, "epoch": 3.904747130003103, "percentage": 19.52, "elapsed_time": "0:22:37", "remaining_time": "1:33:16", "throughput": 5641.07, "total_tokens": 7659120} {"current_steps": 12590, "total_steps": 64460, "loss": 0.2337, "lr": 9.725888975172171e-06, "epoch": 3.9062984796773192, "percentage": 19.53, "elapsed_time": "0:22:38", "remaining_time": "1:33:16", "throughput": 5641.52, "total_tokens": 7663440} {"current_steps": 12595, "total_steps": 64460, "loss": 0.2331, "lr": 9.725446707588357e-06, "epoch": 3.9078498293515356, "percentage": 19.54, "elapsed_time": "0:22:38", "remaining_time": "1:33:15", "throughput": 5641.58, "total_tokens": 7666352} {"current_steps": 12600, "total_steps": 64460, "loss": 0.2336, "lr": 9.725004093573343e-06, "epoch": 3.9094011790257523, "percentage": 19.55, "elapsed_time": "0:22:39", "remaining_time": "1:33:15", "throughput": 5641.53, "total_tokens": 7669072} {"current_steps": 12605, "total_steps": 64460, "loss": 0.2335, "lr": 9.724561133159576e-06, "epoch": 3.910952528699969, "percentage": 19.55, "elapsed_time": "0:22:39", "remaining_time": "1:33:14", "throughput": 5641.56, "total_tokens": 7671952} {"current_steps": 12610, "total_steps": 64460, "loss": 0.2315, "lr": 9.72411782637953e-06, "epoch": 3.9125038783741855, "percentage": 19.56, "elapsed_time": "0:22:40", "remaining_time": "1:33:14", "throughput": 5641.82, "total_tokens": 7675920} {"current_steps": 12615, "total_steps": 64460, "loss": 0.2357, "lr": 9.723674173265706e-06, "epoch": 3.9140552280484022, "percentage": 19.57, "elapsed_time": "0:22:41", "remaining_time": "1:33:13", "throughput": 5641.65, "total_tokens": 7678544} {"current_steps": 12620, "total_steps": 64460, "loss": 0.2363, "lr": 9.723230173850628e-06, "epoch": 3.9156065777226186, "percentage": 19.58, "elapsed_time": "0:22:41", "remaining_time": "1:33:13", "throughput": 5641.8, "total_tokens": 7682064} {"current_steps": 12625, "total_steps": 64460, "loss": 0.23, "lr": 9.722785828166847e-06, "epoch": 3.9171579273968353, "percentage": 19.59, "elapsed_time": "0:22:42", "remaining_time": "1:33:13", "throughput": 5642.38, "total_tokens": 7686480} {"current_steps": 12630, "total_steps": 64460, "loss": 0.2335, "lr": 9.722341136246937e-06, "epoch": 3.9187092770710517, "percentage": 19.59, "elapsed_time": "0:22:42", "remaining_time": "1:33:12", "throughput": 5641.91, "total_tokens": 7688624} {"current_steps": 12635, "total_steps": 64460, "loss": 0.232, "lr": 9.721896098123505e-06, "epoch": 3.9202606267452684, "percentage": 19.6, "elapsed_time": "0:22:43", "remaining_time": "1:33:12", "throughput": 5642.63, "total_tokens": 7693520} {"current_steps": 12640, "total_steps": 64460, "loss": 0.2332, "lr": 9.721450713829171e-06, "epoch": 3.9218119764194848, "percentage": 19.61, "elapsed_time": "0:22:43", "remaining_time": "1:33:11", "throughput": 5642.27, "total_tokens": 7695664} {"current_steps": 12645, "total_steps": 64460, "loss": 0.2311, "lr": 9.721004983396588e-06, "epoch": 3.9233633260937015, "percentage": 19.62, "elapsed_time": "0:22:44", "remaining_time": "1:33:11", "throughput": 5642.42, "total_tokens": 7698800} {"current_steps": 12650, "total_steps": 64460, "loss": 0.2272, "lr": 9.720558906858435e-06, "epoch": 3.9249146757679183, "percentage": 19.62, "elapsed_time": "0:22:44", "remaining_time": "1:33:10", "throughput": 5642.54, "total_tokens": 7701680} {"current_steps": 12655, "total_steps": 64460, "loss": 0.2299, "lr": 9.720112484247414e-06, "epoch": 3.9264660254421346, "percentage": 19.63, "elapsed_time": "0:22:45", "remaining_time": "1:33:09", "throughput": 5642.39, "total_tokens": 7704368} {"current_steps": 12660, "total_steps": 64460, "loss": 0.2356, "lr": 9.719665715596257e-06, "epoch": 3.928017375116351, "percentage": 19.64, "elapsed_time": "0:22:45", "remaining_time": "1:33:08", "throughput": 5642.21, "total_tokens": 7706960} {"current_steps": 12665, "total_steps": 64460, "loss": 0.235, "lr": 9.71921860093771e-06, "epoch": 3.9295687247905677, "percentage": 19.65, "elapsed_time": "0:22:46", "remaining_time": "1:33:08", "throughput": 5642.07, "total_tokens": 7709744} {"current_steps": 12670, "total_steps": 64460, "loss": 0.2366, "lr": 9.718771140304557e-06, "epoch": 3.9311200744647845, "percentage": 19.66, "elapsed_time": "0:22:46", "remaining_time": "1:33:07", "throughput": 5642.36, "total_tokens": 7712944} {"current_steps": 12675, "total_steps": 64460, "loss": 0.2342, "lr": 9.718323333729602e-06, "epoch": 3.932671424139001, "percentage": 19.66, "elapsed_time": "0:22:47", "remaining_time": "1:33:06", "throughput": 5642.31, "total_tokens": 7715728} {"current_steps": 12680, "total_steps": 64460, "loss": 0.2345, "lr": 9.717875181245671e-06, "epoch": 3.9342227738132176, "percentage": 19.67, "elapsed_time": "0:22:47", "remaining_time": "1:33:06", "throughput": 5642.47, "total_tokens": 7718608} {"current_steps": 12685, "total_steps": 64460, "loss": 0.2321, "lr": 9.717426682885623e-06, "epoch": 3.935774123487434, "percentage": 19.68, "elapsed_time": "0:22:48", "remaining_time": "1:33:05", "throughput": 5642.26, "total_tokens": 7721072} {"current_steps": 12690, "total_steps": 64460, "loss": 0.2299, "lr": 9.716977838682335e-06, "epoch": 3.9373254731616507, "percentage": 19.69, "elapsed_time": "0:22:48", "remaining_time": "1:33:04", "throughput": 5642.13, "total_tokens": 7723664} {"current_steps": 12695, "total_steps": 64460, "loss": 0.2409, "lr": 9.716528648668716e-06, "epoch": 3.938876822835867, "percentage": 19.69, "elapsed_time": "0:22:49", "remaining_time": "1:33:04", "throughput": 5642.02, "total_tokens": 7726704} {"current_steps": 12700, "total_steps": 64460, "loss": 0.2328, "lr": 9.716079112877695e-06, "epoch": 3.940428172510084, "percentage": 19.7, "elapsed_time": "0:22:50", "remaining_time": "1:33:04", "throughput": 5642.05, "total_tokens": 7730256} {"current_steps": 12705, "total_steps": 64460, "loss": 0.2321, "lr": 9.715629231342226e-06, "epoch": 3.9419795221843, "percentage": 19.71, "elapsed_time": "0:22:50", "remaining_time": "1:33:04", "throughput": 5642.31, "total_tokens": 7734384} {"current_steps": 12710, "total_steps": 64460, "loss": 0.2294, "lr": 9.715179004095295e-06, "epoch": 3.943530871858517, "percentage": 19.72, "elapsed_time": "0:22:51", "remaining_time": "1:33:03", "throughput": 5642.25, "total_tokens": 7737296} {"current_steps": 12715, "total_steps": 64460, "loss": 0.2304, "lr": 9.714728431169904e-06, "epoch": 3.9450822215327337, "percentage": 19.73, "elapsed_time": "0:22:51", "remaining_time": "1:33:03", "throughput": 5642.49, "total_tokens": 7741104} {"current_steps": 12720, "total_steps": 64460, "loss": 0.2314, "lr": 9.714277512599091e-06, "epoch": 3.94663357120695, "percentage": 19.73, "elapsed_time": "0:22:52", "remaining_time": "1:33:02", "throughput": 5642.45, "total_tokens": 7743792} {"current_steps": 12725, "total_steps": 64460, "loss": 0.2299, "lr": 9.713826248415911e-06, "epoch": 3.9481849208811663, "percentage": 19.74, "elapsed_time": "0:22:52", "remaining_time": "1:33:01", "throughput": 5642.68, "total_tokens": 7746832} {"current_steps": 12730, "total_steps": 64460, "loss": 0.2283, "lr": 9.713374638653445e-06, "epoch": 3.949736270555383, "percentage": 19.75, "elapsed_time": "0:22:53", "remaining_time": "1:33:01", "throughput": 5642.8, "total_tokens": 7750032} {"current_steps": 12735, "total_steps": 64460, "loss": 0.2312, "lr": 9.712922683344806e-06, "epoch": 3.9512876202296, "percentage": 19.76, "elapsed_time": "0:22:53", "remaining_time": "1:33:00", "throughput": 5642.57, "total_tokens": 7752304} {"current_steps": 12740, "total_steps": 64460, "loss": 0.2301, "lr": 9.712470382523123e-06, "epoch": 3.9528389699038162, "percentage": 19.76, "elapsed_time": "0:22:54", "remaining_time": "1:32:59", "throughput": 5642.59, "total_tokens": 7754896} {"current_steps": 12745, "total_steps": 64460, "loss": 0.2255, "lr": 9.712017736221557e-06, "epoch": 3.954390319578033, "percentage": 19.77, "elapsed_time": "0:22:54", "remaining_time": "1:32:58", "throughput": 5642.51, "total_tokens": 7757424} {"current_steps": 12750, "total_steps": 64460, "loss": 0.2269, "lr": 9.711564744473294e-06, "epoch": 3.9559416692522493, "percentage": 19.78, "elapsed_time": "0:22:55", "remaining_time": "1:32:57", "throughput": 5642.59, "total_tokens": 7760304} {"current_steps": 12755, "total_steps": 64460, "loss": 0.2383, "lr": 9.71111140731154e-06, "epoch": 3.957493018926466, "percentage": 19.79, "elapsed_time": "0:22:55", "remaining_time": "1:32:57", "throughput": 5642.71, "total_tokens": 7763312} {"current_steps": 12760, "total_steps": 64460, "loss": 0.2384, "lr": 9.710657724769532e-06, "epoch": 3.9590443686006824, "percentage": 19.8, "elapsed_time": "0:22:56", "remaining_time": "1:32:56", "throughput": 5642.77, "total_tokens": 7766512} {"current_steps": 12765, "total_steps": 64460, "loss": 0.2257, "lr": 9.710203696880532e-06, "epoch": 3.960595718274899, "percentage": 19.8, "elapsed_time": "0:22:56", "remaining_time": "1:32:55", "throughput": 5642.89, "total_tokens": 7769360} {"current_steps": 12770, "total_steps": 64460, "loss": 0.2344, "lr": 9.709749323677822e-06, "epoch": 3.9621470679491155, "percentage": 19.81, "elapsed_time": "0:22:57", "remaining_time": "1:32:55", "throughput": 5643.16, "total_tokens": 7772528} {"current_steps": 12775, "total_steps": 64460, "loss": 0.2324, "lr": 9.709294605194714e-06, "epoch": 3.9636984176233323, "percentage": 19.82, "elapsed_time": "0:22:57", "remaining_time": "1:32:54", "throughput": 5643.33, "total_tokens": 7776112} {"current_steps": 12780, "total_steps": 64460, "loss": 0.2287, "lr": 9.708839541464547e-06, "epoch": 3.965249767297549, "percentage": 19.83, "elapsed_time": "0:22:58", "remaining_time": "1:32:53", "throughput": 5643.2, "total_tokens": 7778544} {"current_steps": 12785, "total_steps": 64460, "loss": 0.2283, "lr": 9.708384132520681e-06, "epoch": 3.9668011169717654, "percentage": 19.83, "elapsed_time": "0:22:58", "remaining_time": "1:32:53", "throughput": 5643.31, "total_tokens": 7781584} {"current_steps": 12790, "total_steps": 64460, "loss": 0.228, "lr": 9.707928378396501e-06, "epoch": 3.9683524666459817, "percentage": 19.84, "elapsed_time": "0:22:59", "remaining_time": "1:32:53", "throughput": 5643.43, "total_tokens": 7785936} {"current_steps": 12795, "total_steps": 64460, "loss": 0.2371, "lr": 9.707472279125422e-06, "epoch": 3.9699038163201985, "percentage": 19.85, "elapsed_time": "0:23:00", "remaining_time": "1:32:53", "throughput": 5643.47, "total_tokens": 7789360} {"current_steps": 12800, "total_steps": 64460, "loss": 0.2325, "lr": 9.707015834740878e-06, "epoch": 3.9714551659944153, "percentage": 19.86, "elapsed_time": "0:23:00", "remaining_time": "1:32:52", "throughput": 5643.3, "total_tokens": 7791920} {"current_steps": 12805, "total_steps": 64460, "loss": 0.233, "lr": 9.706559045276336e-06, "epoch": 3.9730065156686316, "percentage": 19.87, "elapsed_time": "0:23:01", "remaining_time": "1:32:52", "throughput": 5643.76, "total_tokens": 7795856} {"current_steps": 12810, "total_steps": 64460, "loss": 0.2348, "lr": 9.706101910765283e-06, "epoch": 3.9745578653428484, "percentage": 19.87, "elapsed_time": "0:23:01", "remaining_time": "1:32:51", "throughput": 5643.55, "total_tokens": 7798096} {"current_steps": 12815, "total_steps": 64460, "loss": 0.2337, "lr": 9.705644431241227e-06, "epoch": 3.9761092150170647, "percentage": 19.88, "elapsed_time": "0:23:02", "remaining_time": "1:32:50", "throughput": 5643.68, "total_tokens": 7801040} {"current_steps": 12820, "total_steps": 64460, "loss": 0.2263, "lr": 9.705186606737715e-06, "epoch": 3.9776605646912815, "percentage": 19.89, "elapsed_time": "0:23:02", "remaining_time": "1:32:50", "throughput": 5644.16, "total_tokens": 7804880} {"current_steps": 12825, "total_steps": 64460, "loss": 0.2324, "lr": 9.704728437288305e-06, "epoch": 3.9792119143654983, "percentage": 19.9, "elapsed_time": "0:23:03", "remaining_time": "1:32:50", "throughput": 5645.02, "total_tokens": 7810704} {"current_steps": 12830, "total_steps": 64460, "loss": 0.2341, "lr": 9.704269922926591e-06, "epoch": 3.9807632640397146, "percentage": 19.9, "elapsed_time": "0:23:04", "remaining_time": "1:32:49", "throughput": 5645.1, "total_tokens": 7813520} {"current_steps": 12835, "total_steps": 64460, "loss": 0.2369, "lr": 9.703811063686182e-06, "epoch": 3.982314613713931, "percentage": 19.91, "elapsed_time": "0:23:04", "remaining_time": "1:32:49", "throughput": 5645.57, "total_tokens": 7817840} {"current_steps": 12840, "total_steps": 64460, "loss": 0.2322, "lr": 9.703351859600721e-06, "epoch": 3.9838659633881477, "percentage": 19.92, "elapsed_time": "0:23:05", "remaining_time": "1:32:49", "throughput": 5645.58, "total_tokens": 7820656} {"current_steps": 12845, "total_steps": 64460, "loss": 0.2352, "lr": 9.702892310703874e-06, "epoch": 3.9854173130623645, "percentage": 19.93, "elapsed_time": "0:23:05", "remaining_time": "1:32:49", "throughput": 5646.28, "total_tokens": 7825584} {"current_steps": 12850, "total_steps": 64460, "loss": 0.2325, "lr": 9.702432417029327e-06, "epoch": 3.986968662736581, "percentage": 19.93, "elapsed_time": "0:23:06", "remaining_time": "1:32:48", "throughput": 5646.17, "total_tokens": 7828272} {"current_steps": 12855, "total_steps": 64460, "loss": 0.2294, "lr": 9.701972178610802e-06, "epoch": 3.988520012410797, "percentage": 19.94, "elapsed_time": "0:23:06", "remaining_time": "1:32:47", "throughput": 5646.18, "total_tokens": 7831152} {"current_steps": 12860, "total_steps": 64460, "loss": 0.2335, "lr": 9.701511595482035e-06, "epoch": 3.990071362085014, "percentage": 19.95, "elapsed_time": "0:23:07", "remaining_time": "1:32:47", "throughput": 5646.19, "total_tokens": 7833872} {"current_steps": 12865, "total_steps": 64460, "loss": 0.2304, "lr": 9.701050667676793e-06, "epoch": 3.9916227117592307, "percentage": 19.96, "elapsed_time": "0:23:07", "remaining_time": "1:32:46", "throughput": 5645.89, "total_tokens": 7836368} {"current_steps": 12870, "total_steps": 64460, "loss": 0.2263, "lr": 9.70058939522887e-06, "epoch": 3.993174061433447, "percentage": 19.97, "elapsed_time": "0:23:08", "remaining_time": "1:32:45", "throughput": 5645.57, "total_tokens": 7838736} {"current_steps": 12875, "total_steps": 64460, "loss": 0.2304, "lr": 9.70012777817208e-06, "epoch": 3.9947254111076638, "percentage": 19.97, "elapsed_time": "0:23:08", "remaining_time": "1:32:45", "throughput": 5645.67, "total_tokens": 7841776} {"current_steps": 12880, "total_steps": 64460, "loss": 0.2335, "lr": 9.699665816540267e-06, "epoch": 3.99627676078188, "percentage": 19.98, "elapsed_time": "0:23:09", "remaining_time": "1:32:44", "throughput": 5645.26, "total_tokens": 7843824} {"current_steps": 12885, "total_steps": 64460, "loss": 0.2305, "lr": 9.699203510367297e-06, "epoch": 3.997828110456097, "percentage": 19.99, "elapsed_time": "0:23:09", "remaining_time": "1:32:43", "throughput": 5645.52, "total_tokens": 7846960} {"current_steps": 12890, "total_steps": 64460, "loss": 0.2373, "lr": 9.69874085968706e-06, "epoch": 3.9993794601303136, "percentage": 20.0, "elapsed_time": "0:23:10", "remaining_time": "1:32:43", "throughput": 5645.99, "total_tokens": 7850736} {"current_steps": 12892, "total_steps": 64460, "eval_loss": 0.23131409287452698, "epoch": 4.0, "percentage": 20.0, "elapsed_time": "0:23:45", "remaining_time": "1:35:01", "throughput": 5508.82, "total_tokens": 7851504} {"current_steps": 12895, "total_steps": 64460, "loss": 0.2326, "lr": 9.69827786453348e-06, "epoch": 4.0009308098045295, "percentage": 20.0, "elapsed_time": "0:23:49", "remaining_time": "1:35:15", "throughput": 5494.01, "total_tokens": 7853072} {"current_steps": 12900, "total_steps": 64460, "loss": 0.232, "lr": 9.697814524940496e-06, "epoch": 4.002482159478746, "percentage": 20.01, "elapsed_time": "0:23:49", "remaining_time": "1:35:15", "throughput": 5494.31, "total_tokens": 7856368} {"current_steps": 12905, "total_steps": 64460, "loss": 0.2324, "lr": 9.697350840942077e-06, "epoch": 4.004033509152963, "percentage": 20.02, "elapsed_time": "0:23:50", "remaining_time": "1:35:14", "throughput": 5494.73, "total_tokens": 7860208} {"current_steps": 12910, "total_steps": 64460, "loss": 0.2298, "lr": 9.696886812572217e-06, "epoch": 4.00558485882718, "percentage": 20.03, "elapsed_time": "0:23:50", "remaining_time": "1:35:14", "throughput": 5495.0, "total_tokens": 7863344} {"current_steps": 12915, "total_steps": 64460, "loss": 0.2283, "lr": 9.696422439864932e-06, "epoch": 4.007136208501397, "percentage": 20.04, "elapsed_time": "0:23:51", "remaining_time": "1:35:13", "throughput": 5495.3, "total_tokens": 7866640} {"current_steps": 12920, "total_steps": 64460, "loss": 0.2293, "lr": 9.695957722854269e-06, "epoch": 4.0086875581756125, "percentage": 20.04, "elapsed_time": "0:23:51", "remaining_time": "1:35:12", "throughput": 5495.39, "total_tokens": 7869360} {"current_steps": 12925, "total_steps": 64460, "loss": 0.2314, "lr": 9.695492661574298e-06, "epoch": 4.010238907849829, "percentage": 20.05, "elapsed_time": "0:23:52", "remaining_time": "1:35:12", "throughput": 5495.92, "total_tokens": 7873712} {"current_steps": 12930, "total_steps": 64460, "loss": 0.2341, "lr": 9.69502725605911e-06, "epoch": 4.011790257524046, "percentage": 20.06, "elapsed_time": "0:23:53", "remaining_time": "1:35:11", "throughput": 5495.81, "total_tokens": 7876112} {"current_steps": 12935, "total_steps": 64460, "loss": 0.2285, "lr": 9.694561506342828e-06, "epoch": 4.013341607198263, "percentage": 20.07, "elapsed_time": "0:23:53", "remaining_time": "1:35:10", "throughput": 5495.76, "total_tokens": 7878672} {"current_steps": 12940, "total_steps": 64460, "loss": 0.2262, "lr": 9.694095412459594e-06, "epoch": 4.014892956872479, "percentage": 20.07, "elapsed_time": "0:23:54", "remaining_time": "1:35:09", "throughput": 5495.8, "total_tokens": 7881456} {"current_steps": 12945, "total_steps": 64460, "loss": 0.2355, "lr": 9.69362897444358e-06, "epoch": 4.0164443065466955, "percentage": 20.08, "elapsed_time": "0:23:54", "remaining_time": "1:35:09", "throughput": 5495.99, "total_tokens": 7884624} {"current_steps": 12950, "total_steps": 64460, "loss": 0.2256, "lr": 9.693162192328983e-06, "epoch": 4.017995656220912, "percentage": 20.09, "elapsed_time": "0:23:55", "remaining_time": "1:35:08", "throughput": 5496.0, "total_tokens": 7887088} {"current_steps": 12955, "total_steps": 64460, "loss": 0.2296, "lr": 9.692695066150021e-06, "epoch": 4.019547005895129, "percentage": 20.1, "elapsed_time": "0:23:55", "remaining_time": "1:35:07", "throughput": 5495.95, "total_tokens": 7889552} {"current_steps": 12960, "total_steps": 64460, "loss": 0.2243, "lr": 9.692227595940942e-06, "epoch": 4.021098355569345, "percentage": 20.11, "elapsed_time": "0:23:56", "remaining_time": "1:35:06", "throughput": 5496.04, "total_tokens": 7892688} {"current_steps": 12965, "total_steps": 64460, "loss": 0.2476, "lr": 9.691759781736015e-06, "epoch": 4.022649705243562, "percentage": 20.11, "elapsed_time": "0:23:56", "remaining_time": "1:35:06", "throughput": 5496.4, "total_tokens": 7896464} {"current_steps": 12970, "total_steps": 64460, "loss": 0.2293, "lr": 9.691291623569537e-06, "epoch": 4.0242010549177785, "percentage": 20.12, "elapsed_time": "0:23:57", "remaining_time": "1:35:05", "throughput": 5496.58, "total_tokens": 7899408} {"current_steps": 12975, "total_steps": 64460, "loss": 0.2316, "lr": 9.69082312147583e-06, "epoch": 4.025752404591995, "percentage": 20.13, "elapsed_time": "0:23:57", "remaining_time": "1:35:04", "throughput": 5496.83, "total_tokens": 7902480} {"current_steps": 12980, "total_steps": 64460, "loss": 0.23, "lr": 9.69035427548924e-06, "epoch": 4.027303754266212, "percentage": 20.14, "elapsed_time": "0:23:58", "remaining_time": "1:35:03", "throughput": 5496.62, "total_tokens": 7904688} {"current_steps": 12985, "total_steps": 64460, "loss": 0.2298, "lr": 9.689885085644139e-06, "epoch": 4.028855103940428, "percentage": 20.14, "elapsed_time": "0:23:58", "remaining_time": "1:35:03", "throughput": 5497.06, "total_tokens": 7908688} {"current_steps": 12990, "total_steps": 64460, "loss": 0.2364, "lr": 9.689415551974927e-06, "epoch": 4.030406453614645, "percentage": 20.15, "elapsed_time": "0:23:59", "remaining_time": "1:35:02", "throughput": 5496.86, "total_tokens": 7910896} {"current_steps": 12995, "total_steps": 64460, "loss": 0.2332, "lr": 9.688945674516023e-06, "epoch": 4.031957803288861, "percentage": 20.16, "elapsed_time": "0:23:59", "remaining_time": "1:35:01", "throughput": 5497.08, "total_tokens": 7913872} {"current_steps": 13000, "total_steps": 64460, "loss": 0.23, "lr": 9.688475453301876e-06, "epoch": 4.033509152963078, "percentage": 20.17, "elapsed_time": "0:24:00", "remaining_time": "1:35:00", "throughput": 5497.34, "total_tokens": 7917168} {"current_steps": 13005, "total_steps": 64460, "loss": 0.2379, "lr": 9.688004888366956e-06, "epoch": 4.035060502637294, "percentage": 20.18, "elapsed_time": "0:24:00", "remaining_time": "1:35:00", "throughput": 5497.54, "total_tokens": 7920176} {"current_steps": 13010, "total_steps": 64460, "loss": 0.2332, "lr": 9.687533979745766e-06, "epoch": 4.036611852311511, "percentage": 20.18, "elapsed_time": "0:24:01", "remaining_time": "1:34:59", "throughput": 5497.58, "total_tokens": 7922800} {"current_steps": 13015, "total_steps": 64460, "loss": 0.2358, "lr": 9.687062727472826e-06, "epoch": 4.038163201985728, "percentage": 20.19, "elapsed_time": "0:24:01", "remaining_time": "1:34:58", "throughput": 5497.77, "total_tokens": 7925936} {"current_steps": 13020, "total_steps": 64460, "loss": 0.2259, "lr": 9.686591131582684e-06, "epoch": 4.039714551659944, "percentage": 20.2, "elapsed_time": "0:24:02", "remaining_time": "1:34:58", "throughput": 5497.68, "total_tokens": 7928912} {"current_steps": 13025, "total_steps": 64460, "loss": 0.2343, "lr": 9.686119192109916e-06, "epoch": 4.04126590133416, "percentage": 20.21, "elapsed_time": "0:24:02", "remaining_time": "1:34:57", "throughput": 5497.45, "total_tokens": 7931120} {"current_steps": 13030, "total_steps": 64460, "loss": 0.2412, "lr": 9.685646909089119e-06, "epoch": 4.042817251008377, "percentage": 20.21, "elapsed_time": "0:24:03", "remaining_time": "1:34:56", "throughput": 5497.31, "total_tokens": 7933520} {"current_steps": 13035, "total_steps": 64460, "loss": 0.2326, "lr": 9.685174282554915e-06, "epoch": 4.044368600682594, "percentage": 20.22, "elapsed_time": "0:24:03", "remaining_time": "1:34:55", "throughput": 5497.44, "total_tokens": 7936304} {"current_steps": 13040, "total_steps": 64460, "loss": 0.233, "lr": 9.684701312541957e-06, "epoch": 4.045919950356811, "percentage": 20.23, "elapsed_time": "0:24:04", "remaining_time": "1:34:54", "throughput": 5497.14, "total_tokens": 7938416} {"current_steps": 13045, "total_steps": 64460, "loss": 0.23, "lr": 9.68422799908492e-06, "epoch": 4.047471300031027, "percentage": 20.24, "elapsed_time": "0:24:04", "remaining_time": "1:34:53", "throughput": 5497.63, "total_tokens": 7942288} {"current_steps": 13050, "total_steps": 64460, "loss": 0.226, "lr": 9.683754342218496e-06, "epoch": 4.049022649705243, "percentage": 20.25, "elapsed_time": "0:24:05", "remaining_time": "1:34:53", "throughput": 5497.56, "total_tokens": 7944752} {"current_steps": 13055, "total_steps": 64460, "loss": 0.2422, "lr": 9.683280341977419e-06, "epoch": 4.05057399937946, "percentage": 20.25, "elapsed_time": "0:24:05", "remaining_time": "1:34:52", "throughput": 5497.62, "total_tokens": 7947536} {"current_steps": 13060, "total_steps": 64460, "loss": 0.2299, "lr": 9.682805998396432e-06, "epoch": 4.052125349053677, "percentage": 20.26, "elapsed_time": "0:24:06", "remaining_time": "1:34:51", "throughput": 5497.61, "total_tokens": 7950032} {"current_steps": 13065, "total_steps": 64460, "loss": 0.2294, "lr": 9.682331311510314e-06, "epoch": 4.053676698727894, "percentage": 20.27, "elapsed_time": "0:24:06", "remaining_time": "1:34:50", "throughput": 5497.54, "total_tokens": 7952432} {"current_steps": 13070, "total_steps": 64460, "loss": 0.2317, "lr": 9.681856281353865e-06, "epoch": 4.0552280484021095, "percentage": 20.28, "elapsed_time": "0:24:07", "remaining_time": "1:34:49", "throughput": 5497.52, "total_tokens": 7955024} {"current_steps": 13075, "total_steps": 64460, "loss": 0.2344, "lr": 9.681380907961906e-06, "epoch": 4.056779398076326, "percentage": 20.28, "elapsed_time": "0:24:07", "remaining_time": "1:34:48", "throughput": 5497.51, "total_tokens": 7957616} {"current_steps": 13080, "total_steps": 64460, "loss": 0.2309, "lr": 9.680905191369293e-06, "epoch": 4.058330747750543, "percentage": 20.29, "elapsed_time": "0:24:07", "remaining_time": "1:34:47", "throughput": 5497.79, "total_tokens": 7960720} {"current_steps": 13085, "total_steps": 64460, "loss": 0.228, "lr": 9.680429131610898e-06, "epoch": 4.05988209742476, "percentage": 20.3, "elapsed_time": "0:24:08", "remaining_time": "1:34:46", "throughput": 5497.85, "total_tokens": 7963344} {"current_steps": 13090, "total_steps": 64460, "loss": 0.2299, "lr": 9.679952728721624e-06, "epoch": 4.061433447098976, "percentage": 20.31, "elapsed_time": "0:24:08", "remaining_time": "1:34:46", "throughput": 5497.94, "total_tokens": 7966192} {"current_steps": 13095, "total_steps": 64460, "loss": 0.2343, "lr": 9.679475982736395e-06, "epoch": 4.0629847967731925, "percentage": 20.31, "elapsed_time": "0:24:09", "remaining_time": "1:34:45", "throughput": 5498.19, "total_tokens": 7969136} {"current_steps": 13100, "total_steps": 64460, "loss": 0.2231, "lr": 9.678998893690164e-06, "epoch": 4.064536146447409, "percentage": 20.32, "elapsed_time": "0:24:09", "remaining_time": "1:34:44", "throughput": 5498.22, "total_tokens": 7971824} {"current_steps": 13105, "total_steps": 64460, "loss": 0.2365, "lr": 9.678521461617908e-06, "epoch": 4.066087496121626, "percentage": 20.33, "elapsed_time": "0:24:10", "remaining_time": "1:34:43", "throughput": 5498.44, "total_tokens": 7975088} {"current_steps": 13110, "total_steps": 64460, "loss": 0.225, "lr": 9.678043686554624e-06, "epoch": 4.067638845795843, "percentage": 20.34, "elapsed_time": "0:24:10", "remaining_time": "1:34:43", "throughput": 5498.59, "total_tokens": 7978416} {"current_steps": 13115, "total_steps": 64460, "loss": 0.2122, "lr": 9.677565568535343e-06, "epoch": 4.069190195470059, "percentage": 20.35, "elapsed_time": "0:24:11", "remaining_time": "1:34:42", "throughput": 5498.5, "total_tokens": 7980816} {"current_steps": 13120, "total_steps": 64460, "loss": 0.2187, "lr": 9.677087107595113e-06, "epoch": 4.070741545144275, "percentage": 20.35, "elapsed_time": "0:24:11", "remaining_time": "1:34:41", "throughput": 5498.43, "total_tokens": 7983504} {"current_steps": 13125, "total_steps": 64460, "loss": 0.2463, "lr": 9.676608303769015e-06, "epoch": 4.072292894818492, "percentage": 20.36, "elapsed_time": "0:24:12", "remaining_time": "1:34:40", "throughput": 5498.58, "total_tokens": 7986448} {"current_steps": 13130, "total_steps": 64460, "loss": 0.2649, "lr": 9.67612915709215e-06, "epoch": 4.073844244492709, "percentage": 20.37, "elapsed_time": "0:24:12", "remaining_time": "1:34:40", "throughput": 5498.36, "total_tokens": 7988784} {"current_steps": 13135, "total_steps": 64460, "loss": 0.2535, "lr": 9.675649667599643e-06, "epoch": 4.075395594166925, "percentage": 20.38, "elapsed_time": "0:24:13", "remaining_time": "1:34:39", "throughput": 5498.99, "total_tokens": 7993232} {"current_steps": 13140, "total_steps": 64460, "loss": 0.2331, "lr": 9.675169835326647e-06, "epoch": 4.076946943841142, "percentage": 20.38, "elapsed_time": "0:24:14", "remaining_time": "1:34:39", "throughput": 5499.19, "total_tokens": 7996816} {"current_steps": 13145, "total_steps": 64460, "loss": 0.2361, "lr": 9.67468966030834e-06, "epoch": 4.078498293515358, "percentage": 20.39, "elapsed_time": "0:24:14", "remaining_time": "1:34:38", "throughput": 5499.14, "total_tokens": 7999376} {"current_steps": 13150, "total_steps": 64460, "loss": 0.2284, "lr": 9.674209142579925e-06, "epoch": 4.080049643189575, "percentage": 20.4, "elapsed_time": "0:24:15", "remaining_time": "1:34:37", "throughput": 5499.08, "total_tokens": 8002032} {"current_steps": 13155, "total_steps": 64460, "loss": 0.2377, "lr": 9.673728282176626e-06, "epoch": 4.081600992863791, "percentage": 20.41, "elapsed_time": "0:24:15", "remaining_time": "1:34:37", "throughput": 5499.51, "total_tokens": 8005904} {"current_steps": 13160, "total_steps": 64460, "loss": 0.2355, "lr": 9.673247079133702e-06, "epoch": 4.083152342538008, "percentage": 20.42, "elapsed_time": "0:24:16", "remaining_time": "1:34:36", "throughput": 5499.74, "total_tokens": 8009008} {"current_steps": 13165, "total_steps": 64460, "loss": 0.2314, "lr": 9.672765533486427e-06, "epoch": 4.084703692212225, "percentage": 20.42, "elapsed_time": "0:24:17", "remaining_time": "1:34:37", "throughput": 5500.57, "total_tokens": 8014576} {"current_steps": 13170, "total_steps": 64460, "loss": 0.2332, "lr": 9.672283645270105e-06, "epoch": 4.086255041886441, "percentage": 20.43, "elapsed_time": "0:24:17", "remaining_time": "1:34:36", "throughput": 5500.52, "total_tokens": 8017104} {"current_steps": 13175, "total_steps": 64460, "loss": 0.2339, "lr": 9.671801414520061e-06, "epoch": 4.087806391560658, "percentage": 20.44, "elapsed_time": "0:24:18", "remaining_time": "1:34:35", "throughput": 5500.76, "total_tokens": 8020144} {"current_steps": 13180, "total_steps": 64460, "loss": 0.233, "lr": 9.671318841271654e-06, "epoch": 4.089357741234874, "percentage": 20.45, "elapsed_time": "0:24:18", "remaining_time": "1:34:34", "throughput": 5501.17, "total_tokens": 8023536} {"current_steps": 13185, "total_steps": 64460, "loss": 0.2389, "lr": 9.670835925560257e-06, "epoch": 4.090909090909091, "percentage": 20.45, "elapsed_time": "0:24:19", "remaining_time": "1:34:34", "throughput": 5501.63, "total_tokens": 8027536} {"current_steps": 13190, "total_steps": 64460, "loss": 0.2305, "lr": 9.670352667421276e-06, "epoch": 4.092460440583308, "percentage": 20.46, "elapsed_time": "0:24:19", "remaining_time": "1:34:33", "throughput": 5501.55, "total_tokens": 8029872} {"current_steps": 13195, "total_steps": 64460, "loss": 0.2369, "lr": 9.66986906689014e-06, "epoch": 4.094011790257524, "percentage": 20.47, "elapsed_time": "0:24:20", "remaining_time": "1:34:32", "throughput": 5501.6, "total_tokens": 8032528} {"current_steps": 13200, "total_steps": 64460, "loss": 0.2295, "lr": 9.669385124002301e-06, "epoch": 4.09556313993174, "percentage": 20.48, "elapsed_time": "0:24:20", "remaining_time": "1:34:32", "throughput": 5502.1, "total_tokens": 8036784} {"current_steps": 13205, "total_steps": 64460, "loss": 0.2352, "lr": 9.668900838793241e-06, "epoch": 4.097114489605957, "percentage": 20.49, "elapsed_time": "0:24:21", "remaining_time": "1:34:32", "throughput": 5502.43, "total_tokens": 8040944} {"current_steps": 13210, "total_steps": 64460, "loss": 0.233, "lr": 9.66841621129846e-06, "epoch": 4.098665839280174, "percentage": 20.49, "elapsed_time": "0:24:21", "remaining_time": "1:34:31", "throughput": 5502.8, "total_tokens": 8044688} {"current_steps": 13215, "total_steps": 64460, "loss": 0.2294, "lr": 9.667931241553487e-06, "epoch": 4.100217188954391, "percentage": 20.5, "elapsed_time": "0:24:22", "remaining_time": "1:34:30", "throughput": 5502.63, "total_tokens": 8047120} {"current_steps": 13220, "total_steps": 64460, "loss": 0.2289, "lr": 9.66744592959388e-06, "epoch": 4.1017685386286065, "percentage": 20.51, "elapsed_time": "0:24:22", "remaining_time": "1:34:30", "throughput": 5502.94, "total_tokens": 8050256} {"current_steps": 13225, "total_steps": 64460, "loss": 0.225, "lr": 9.666960275455212e-06, "epoch": 4.103319888302823, "percentage": 20.52, "elapsed_time": "0:24:23", "remaining_time": "1:34:29", "throughput": 5503.17, "total_tokens": 8053552} {"current_steps": 13230, "total_steps": 64460, "loss": 0.2348, "lr": 9.666474279173095e-06, "epoch": 4.10487123797704, "percentage": 20.52, "elapsed_time": "0:24:23", "remaining_time": "1:34:28", "throughput": 5503.25, "total_tokens": 8056336} {"current_steps": 13235, "total_steps": 64460, "loss": 0.2361, "lr": 9.665987940783152e-06, "epoch": 4.106422587651257, "percentage": 20.53, "elapsed_time": "0:24:24", "remaining_time": "1:34:27", "throughput": 5503.43, "total_tokens": 8059216} {"current_steps": 13240, "total_steps": 64460, "loss": 0.2299, "lr": 9.665501260321038e-06, "epoch": 4.107973937325474, "percentage": 20.54, "elapsed_time": "0:24:25", "remaining_time": "1:34:27", "throughput": 5503.79, "total_tokens": 8063088} {"current_steps": 13245, "total_steps": 64460, "loss": 0.2265, "lr": 9.665014237822435e-06, "epoch": 4.109525286999689, "percentage": 20.55, "elapsed_time": "0:24:25", "remaining_time": "1:34:26", "throughput": 5503.74, "total_tokens": 8065648} {"current_steps": 13250, "total_steps": 64460, "loss": 0.2395, "lr": 9.664526873323047e-06, "epoch": 4.111076636673906, "percentage": 20.56, "elapsed_time": "0:24:26", "remaining_time": "1:34:27", "throughput": 5504.34, "total_tokens": 8070928} {"current_steps": 13255, "total_steps": 64460, "loss": 0.2355, "lr": 9.664039166858604e-06, "epoch": 4.112627986348123, "percentage": 20.56, "elapsed_time": "0:24:26", "remaining_time": "1:34:26", "throughput": 5504.01, "total_tokens": 8073104} {"current_steps": 13260, "total_steps": 64460, "loss": 0.2322, "lr": 9.663551118464855e-06, "epoch": 4.11417933602234, "percentage": 20.57, "elapsed_time": "0:24:27", "remaining_time": "1:34:25", "throughput": 5503.97, "total_tokens": 8075952} {"current_steps": 13265, "total_steps": 64460, "loss": 0.2377, "lr": 9.663062728177587e-06, "epoch": 4.115730685696556, "percentage": 20.58, "elapsed_time": "0:24:27", "remaining_time": "1:34:24", "throughput": 5504.06, "total_tokens": 8078960} {"current_steps": 13270, "total_steps": 64460, "loss": 0.2337, "lr": 9.662573996032603e-06, "epoch": 4.117282035370772, "percentage": 20.59, "elapsed_time": "0:24:28", "remaining_time": "1:34:24", "throughput": 5504.1, "total_tokens": 8081904} {"current_steps": 13275, "total_steps": 64460, "loss": 0.2351, "lr": 9.662084922065733e-06, "epoch": 4.118833385044989, "percentage": 20.59, "elapsed_time": "0:24:28", "remaining_time": "1:34:23", "throughput": 5504.0, "total_tokens": 8084368} {"current_steps": 13280, "total_steps": 64460, "loss": 0.2362, "lr": 9.661595506312828e-06, "epoch": 4.120384734719206, "percentage": 20.6, "elapsed_time": "0:24:29", "remaining_time": "1:34:22", "throughput": 5504.23, "total_tokens": 8087600} {"current_steps": 13285, "total_steps": 64460, "loss": 0.2346, "lr": 9.661105748809772e-06, "epoch": 4.121936084393422, "percentage": 20.61, "elapsed_time": "0:24:29", "remaining_time": "1:34:22", "throughput": 5504.19, "total_tokens": 8090448} {"current_steps": 13290, "total_steps": 64460, "loss": 0.2304, "lr": 9.660615649592469e-06, "epoch": 4.123487434067639, "percentage": 20.62, "elapsed_time": "0:24:30", "remaining_time": "1:34:21", "throughput": 5504.7, "total_tokens": 8094640} {"current_steps": 13295, "total_steps": 64460, "loss": 0.2324, "lr": 9.660125208696849e-06, "epoch": 4.125038783741855, "percentage": 20.63, "elapsed_time": "0:24:30", "remaining_time": "1:34:20", "throughput": 5504.66, "total_tokens": 8097168} {"current_steps": 13300, "total_steps": 64460, "loss": 0.2294, "lr": 9.659634426158867e-06, "epoch": 4.126590133416072, "percentage": 20.63, "elapsed_time": "0:24:31", "remaining_time": "1:34:20", "throughput": 5504.71, "total_tokens": 8099920} {"current_steps": 13305, "total_steps": 64460, "loss": 0.2332, "lr": 9.659143302014503e-06, "epoch": 4.128141483090289, "percentage": 20.64, "elapsed_time": "0:24:31", "remaining_time": "1:34:19", "throughput": 5504.85, "total_tokens": 8102768} {"current_steps": 13310, "total_steps": 64460, "loss": 0.2296, "lr": 9.658651836299763e-06, "epoch": 4.129692832764505, "percentage": 20.65, "elapsed_time": "0:24:32", "remaining_time": "1:34:18", "throughput": 5504.78, "total_tokens": 8105264} {"current_steps": 13315, "total_steps": 64460, "loss": 0.2305, "lr": 9.658160029050676e-06, "epoch": 4.131244182438722, "percentage": 20.66, "elapsed_time": "0:24:32", "remaining_time": "1:34:17", "throughput": 5504.57, "total_tokens": 8107696} {"current_steps": 13320, "total_steps": 64460, "loss": 0.2273, "lr": 9.657667880303299e-06, "epoch": 4.132795532112938, "percentage": 20.66, "elapsed_time": "0:24:33", "remaining_time": "1:34:17", "throughput": 5504.87, "total_tokens": 8111088} {"current_steps": 13325, "total_steps": 64460, "loss": 0.225, "lr": 9.657175390093708e-06, "epoch": 4.134346881787155, "percentage": 20.67, "elapsed_time": "0:24:34", "remaining_time": "1:34:17", "throughput": 5505.5, "total_tokens": 8116016} {"current_steps": 13330, "total_steps": 64460, "loss": 0.2297, "lr": 9.656682558458015e-06, "epoch": 4.135898231461371, "percentage": 20.68, "elapsed_time": "0:24:34", "remaining_time": "1:34:16", "throughput": 5505.42, "total_tokens": 8118768} {"current_steps": 13335, "total_steps": 64460, "loss": 0.24, "lr": 9.656189385432347e-06, "epoch": 4.137449581135588, "percentage": 20.69, "elapsed_time": "0:24:35", "remaining_time": "1:34:15", "throughput": 5505.24, "total_tokens": 8121136} {"current_steps": 13340, "total_steps": 64460, "loss": 0.2239, "lr": 9.65569587105286e-06, "epoch": 4.139000930809805, "percentage": 20.7, "elapsed_time": "0:24:35", "remaining_time": "1:34:14", "throughput": 5505.36, "total_tokens": 8123888} {"current_steps": 13345, "total_steps": 64460, "loss": 0.2288, "lr": 9.655202015355732e-06, "epoch": 4.140552280484021, "percentage": 20.7, "elapsed_time": "0:24:36", "remaining_time": "1:34:14", "throughput": 5505.31, "total_tokens": 8126896} {"current_steps": 13350, "total_steps": 64460, "loss": 0.2391, "lr": 9.654707818377172e-06, "epoch": 4.142103630158237, "percentage": 20.71, "elapsed_time": "0:24:36", "remaining_time": "1:34:13", "throughput": 5505.21, "total_tokens": 8129488} {"current_steps": 13355, "total_steps": 64460, "loss": 0.2315, "lr": 9.654213280153408e-06, "epoch": 4.143654979832454, "percentage": 20.72, "elapsed_time": "0:24:37", "remaining_time": "1:34:12", "throughput": 5505.04, "total_tokens": 8131952} {"current_steps": 13360, "total_steps": 64460, "loss": 0.2317, "lr": 9.653718400720696e-06, "epoch": 4.145206329506671, "percentage": 20.73, "elapsed_time": "0:24:37", "remaining_time": "1:34:11", "throughput": 5505.25, "total_tokens": 8135120} {"current_steps": 13365, "total_steps": 64460, "loss": 0.2306, "lr": 9.65322318011532e-06, "epoch": 4.146757679180888, "percentage": 20.73, "elapsed_time": "0:24:38", "remaining_time": "1:34:11", "throughput": 5505.1, "total_tokens": 8137680} {"current_steps": 13370, "total_steps": 64460, "loss": 0.2326, "lr": 9.652727618373578e-06, "epoch": 4.148309028855104, "percentage": 20.74, "elapsed_time": "0:24:38", "remaining_time": "1:34:10", "throughput": 5504.7, "total_tokens": 8139728} {"current_steps": 13375, "total_steps": 64460, "loss": 0.2319, "lr": 9.652231715531808e-06, "epoch": 4.14986037852932, "percentage": 20.75, "elapsed_time": "0:24:39", "remaining_time": "1:34:09", "throughput": 5504.71, "total_tokens": 8142480} {"current_steps": 13380, "total_steps": 64460, "loss": 0.2357, "lr": 9.651735471626361e-06, "epoch": 4.151411728203537, "percentage": 20.76, "elapsed_time": "0:24:39", "remaining_time": "1:34:09", "throughput": 5504.44, "total_tokens": 8145136} {"current_steps": 13385, "total_steps": 64460, "loss": 0.2348, "lr": 9.65123888669362e-06, "epoch": 4.152963077877754, "percentage": 20.76, "elapsed_time": "0:24:40", "remaining_time": "1:34:08", "throughput": 5504.36, "total_tokens": 8147920} {"current_steps": 13390, "total_steps": 64460, "loss": 0.2337, "lr": 9.65074196076999e-06, "epoch": 4.1545144275519705, "percentage": 20.77, "elapsed_time": "0:24:40", "remaining_time": "1:34:07", "throughput": 5504.32, "total_tokens": 8150768} {"current_steps": 13395, "total_steps": 64460, "loss": 0.2309, "lr": 9.650244693891901e-06, "epoch": 4.156065777226186, "percentage": 20.78, "elapsed_time": "0:24:41", "remaining_time": "1:34:07", "throughput": 5504.61, "total_tokens": 8154160} {"current_steps": 13400, "total_steps": 64460, "loss": 0.2293, "lr": 9.649747086095809e-06, "epoch": 4.157617126900403, "percentage": 20.79, "elapsed_time": "0:24:41", "remaining_time": "1:34:06", "throughput": 5504.4, "total_tokens": 8156432} {"current_steps": 13405, "total_steps": 64460, "loss": 0.2308, "lr": 9.649249137418193e-06, "epoch": 4.15916847657462, "percentage": 20.8, "elapsed_time": "0:24:42", "remaining_time": "1:34:05", "throughput": 5504.36, "total_tokens": 8159216} {"current_steps": 13410, "total_steps": 64460, "loss": 0.2304, "lr": 9.64875084789556e-06, "epoch": 4.160719826248837, "percentage": 20.8, "elapsed_time": "0:24:42", "remaining_time": "1:34:04", "throughput": 5504.3, "total_tokens": 8161904} {"current_steps": 13415, "total_steps": 64460, "loss": 0.227, "lr": 9.648252217564442e-06, "epoch": 4.162271175923053, "percentage": 20.81, "elapsed_time": "0:24:43", "remaining_time": "1:34:04", "throughput": 5504.84, "total_tokens": 8166576} {"current_steps": 13420, "total_steps": 64460, "loss": 0.2323, "lr": 9.647753246461393e-06, "epoch": 4.163822525597269, "percentage": 20.82, "elapsed_time": "0:24:44", "remaining_time": "1:34:04", "throughput": 5504.45, "total_tokens": 8168816} {"current_steps": 13425, "total_steps": 64460, "loss": 0.2269, "lr": 9.647253934622993e-06, "epoch": 4.165373875271486, "percentage": 20.83, "elapsed_time": "0:24:44", "remaining_time": "1:34:03", "throughput": 5504.22, "total_tokens": 8171216} {"current_steps": 13430, "total_steps": 64460, "loss": 0.2338, "lr": 9.646754282085846e-06, "epoch": 4.166925224945703, "percentage": 20.83, "elapsed_time": "0:24:45", "remaining_time": "1:34:02", "throughput": 5504.57, "total_tokens": 8174896} {"current_steps": 13435, "total_steps": 64460, "loss": 0.2387, "lr": 9.646254288886586e-06, "epoch": 4.16847657461992, "percentage": 20.84, "elapsed_time": "0:24:45", "remaining_time": "1:34:02", "throughput": 5504.27, "total_tokens": 8177392} {"current_steps": 13440, "total_steps": 64460, "loss": 0.2267, "lr": 9.645753955061867e-06, "epoch": 4.170027924294136, "percentage": 20.85, "elapsed_time": "0:24:46", "remaining_time": "1:34:01", "throughput": 5504.46, "total_tokens": 8180560} {"current_steps": 13445, "total_steps": 64460, "loss": 0.2314, "lr": 9.645253280648367e-06, "epoch": 4.171579273968352, "percentage": 20.86, "elapsed_time": "0:24:46", "remaining_time": "1:34:01", "throughput": 5504.75, "total_tokens": 8184080} {"current_steps": 13450, "total_steps": 64460, "loss": 0.2322, "lr": 9.644752265682797e-06, "epoch": 4.173130623642569, "percentage": 20.87, "elapsed_time": "0:24:47", "remaining_time": "1:34:00", "throughput": 5504.68, "total_tokens": 8186736} {"current_steps": 13455, "total_steps": 64460, "loss": 0.2242, "lr": 9.644250910201883e-06, "epoch": 4.174681973316786, "percentage": 20.87, "elapsed_time": "0:24:47", "remaining_time": "1:33:59", "throughput": 5504.81, "total_tokens": 8189552} {"current_steps": 13460, "total_steps": 64460, "loss": 0.2329, "lr": 9.643749214242379e-06, "epoch": 4.176233322991002, "percentage": 20.88, "elapsed_time": "0:24:48", "remaining_time": "1:33:59", "throughput": 5505.09, "total_tokens": 8192976} {"current_steps": 13465, "total_steps": 64460, "loss": 0.2391, "lr": 9.643247177841069e-06, "epoch": 4.177784672665219, "percentage": 20.89, "elapsed_time": "0:24:48", "remaining_time": "1:33:58", "throughput": 5505.07, "total_tokens": 8195632} {"current_steps": 13470, "total_steps": 64460, "loss": 0.2328, "lr": 9.642744801034756e-06, "epoch": 4.179336022339435, "percentage": 20.9, "elapsed_time": "0:24:49", "remaining_time": "1:33:58", "throughput": 5505.31, "total_tokens": 8199728} {"current_steps": 13475, "total_steps": 64460, "loss": 0.2289, "lr": 9.64224208386027e-06, "epoch": 4.180887372013652, "percentage": 20.9, "elapsed_time": "0:24:49", "remaining_time": "1:33:57", "throughput": 5505.55, "total_tokens": 8202992} {"current_steps": 13480, "total_steps": 64460, "loss": 0.2314, "lr": 9.64173902635447e-06, "epoch": 4.182438721687868, "percentage": 20.91, "elapsed_time": "0:24:50", "remaining_time": "1:33:56", "throughput": 5505.58, "total_tokens": 8205840} {"current_steps": 13485, "total_steps": 64460, "loss": 0.2292, "lr": 9.641235628554228e-06, "epoch": 4.183990071362085, "percentage": 20.92, "elapsed_time": "0:24:50", "remaining_time": "1:33:56", "throughput": 5505.4, "total_tokens": 8208336} {"current_steps": 13490, "total_steps": 64460, "loss": 0.2319, "lr": 9.640731890496458e-06, "epoch": 4.185541421036302, "percentage": 20.93, "elapsed_time": "0:24:51", "remaining_time": "1:33:55", "throughput": 5505.45, "total_tokens": 8211664} {"current_steps": 13495, "total_steps": 64460, "loss": 0.232, "lr": 9.640227812218084e-06, "epoch": 4.187092770710518, "percentage": 20.94, "elapsed_time": "0:24:52", "remaining_time": "1:33:54", "throughput": 5505.13, "total_tokens": 8213808} {"current_steps": 13500, "total_steps": 64460, "loss": 0.2384, "lr": 9.639723393756064e-06, "epoch": 4.188644120384735, "percentage": 20.94, "elapsed_time": "0:24:52", "remaining_time": "1:33:53", "throughput": 5505.08, "total_tokens": 8216368} {"current_steps": 13505, "total_steps": 64460, "loss": 0.235, "lr": 9.639218635147376e-06, "epoch": 4.190195470058951, "percentage": 20.95, "elapsed_time": "0:24:53", "remaining_time": "1:33:53", "throughput": 5505.18, "total_tokens": 8219280} {"current_steps": 13510, "total_steps": 64460, "loss": 0.2304, "lr": 9.638713536429025e-06, "epoch": 4.191746819733168, "percentage": 20.96, "elapsed_time": "0:24:53", "remaining_time": "1:33:52", "throughput": 5505.18, "total_tokens": 8222000} {"current_steps": 13515, "total_steps": 64460, "loss": 0.2345, "lr": 9.638208097638042e-06, "epoch": 4.1932981694073845, "percentage": 20.97, "elapsed_time": "0:24:54", "remaining_time": "1:33:51", "throughput": 5505.52, "total_tokens": 8225424} {"current_steps": 13520, "total_steps": 64460, "loss": 0.2298, "lr": 9.63770231881148e-06, "epoch": 4.194849519081601, "percentage": 20.97, "elapsed_time": "0:24:54", "remaining_time": "1:33:51", "throughput": 5506.11, "total_tokens": 8230384} {"current_steps": 13525, "total_steps": 64460, "loss": 0.2319, "lr": 9.63719619998642e-06, "epoch": 4.196400868755817, "percentage": 20.98, "elapsed_time": "0:24:55", "remaining_time": "1:33:51", "throughput": 5506.03, "total_tokens": 8233008} {"current_steps": 13530, "total_steps": 64460, "loss": 0.2293, "lr": 9.636689741199967e-06, "epoch": 4.197952218430034, "percentage": 20.99, "elapsed_time": "0:24:55", "remaining_time": "1:33:50", "throughput": 5506.06, "total_tokens": 8235824} {"current_steps": 13535, "total_steps": 64460, "loss": 0.2304, "lr": 9.636182942489247e-06, "epoch": 4.199503568104251, "percentage": 21.0, "elapsed_time": "0:24:56", "remaining_time": "1:33:49", "throughput": 5506.36, "total_tokens": 8239344} {"current_steps": 13540, "total_steps": 64460, "loss": 0.2336, "lr": 9.63567580389142e-06, "epoch": 4.2010549177784675, "percentage": 21.01, "elapsed_time": "0:24:57", "remaining_time": "1:33:50", "throughput": 5507.15, "total_tokens": 8245296} {"current_steps": 13545, "total_steps": 64460, "loss": 0.2335, "lr": 9.63516832544366e-06, "epoch": 4.202606267452683, "percentage": 21.01, "elapsed_time": "0:24:57", "remaining_time": "1:33:49", "throughput": 5506.99, "total_tokens": 8248016} {"current_steps": 13550, "total_steps": 64460, "loss": 0.2324, "lr": 9.634660507183171e-06, "epoch": 4.2041576171269, "percentage": 21.02, "elapsed_time": "0:24:58", "remaining_time": "1:33:49", "throughput": 5506.99, "total_tokens": 8250800} {"current_steps": 13555, "total_steps": 64460, "loss": 0.2309, "lr": 9.634152349147188e-06, "epoch": 4.205708966801117, "percentage": 21.03, "elapsed_time": "0:24:58", "remaining_time": "1:33:48", "throughput": 5507.02, "total_tokens": 8253520} {"current_steps": 13560, "total_steps": 64460, "loss": 0.2341, "lr": 9.633643851372959e-06, "epoch": 4.207260316475334, "percentage": 21.04, "elapsed_time": "0:24:59", "remaining_time": "1:33:47", "throughput": 5506.98, "total_tokens": 8256080} {"current_steps": 13565, "total_steps": 64460, "loss": 0.2314, "lr": 9.633135013897766e-06, "epoch": 4.2088116661495505, "percentage": 21.04, "elapsed_time": "0:24:59", "remaining_time": "1:33:46", "throughput": 5507.0, "total_tokens": 8258864} {"current_steps": 13570, "total_steps": 64460, "loss": 0.2294, "lr": 9.63262583675891e-06, "epoch": 4.210363015823766, "percentage": 21.05, "elapsed_time": "0:25:00", "remaining_time": "1:33:46", "throughput": 5507.03, "total_tokens": 8261744} {"current_steps": 13575, "total_steps": 64460, "loss": 0.2337, "lr": 9.632116319993726e-06, "epoch": 4.211914365497983, "percentage": 21.06, "elapsed_time": "0:25:00", "remaining_time": "1:33:45", "throughput": 5507.17, "total_tokens": 8265168} {"current_steps": 13580, "total_steps": 64460, "loss": 0.2321, "lr": 9.63160646363956e-06, "epoch": 4.2134657151722, "percentage": 21.07, "elapsed_time": "0:25:01", "remaining_time": "1:33:44", "throughput": 5507.29, "total_tokens": 8267952} {"current_steps": 13585, "total_steps": 64460, "loss": 0.2331, "lr": 9.631096267733793e-06, "epoch": 4.215017064846417, "percentage": 21.08, "elapsed_time": "0:25:01", "remaining_time": "1:33:44", "throughput": 5507.52, "total_tokens": 8271312} {"current_steps": 13590, "total_steps": 64460, "loss": 0.232, "lr": 9.63058573231383e-06, "epoch": 4.216568414520633, "percentage": 21.08, "elapsed_time": "0:25:02", "remaining_time": "1:33:43", "throughput": 5507.76, "total_tokens": 8274608} {"current_steps": 13595, "total_steps": 64460, "loss": 0.2269, "lr": 9.6300748574171e-06, "epoch": 4.218119764194849, "percentage": 21.09, "elapsed_time": "0:25:02", "remaining_time": "1:33:42", "throughput": 5507.65, "total_tokens": 8276976} {"current_steps": 13600, "total_steps": 64460, "loss": 0.2368, "lr": 9.629563643081055e-06, "epoch": 4.219671113869066, "percentage": 21.1, "elapsed_time": "0:25:03", "remaining_time": "1:33:42", "throughput": 5507.37, "total_tokens": 8279568} {"current_steps": 13605, "total_steps": 64460, "loss": 0.2353, "lr": 9.629052089343171e-06, "epoch": 4.221222463543283, "percentage": 21.11, "elapsed_time": "0:25:03", "remaining_time": "1:33:41", "throughput": 5507.21, "total_tokens": 8282000} {"current_steps": 13610, "total_steps": 64460, "loss": 0.2239, "lr": 9.628540196240953e-06, "epoch": 4.222773813217499, "percentage": 21.11, "elapsed_time": "0:25:04", "remaining_time": "1:33:41", "throughput": 5507.77, "total_tokens": 8286384} {"current_steps": 13615, "total_steps": 64460, "loss": 0.2365, "lr": 9.628027963811928e-06, "epoch": 4.224325162891716, "percentage": 21.12, "elapsed_time": "0:25:05", "remaining_time": "1:33:40", "throughput": 5508.02, "total_tokens": 8290384} {"current_steps": 13620, "total_steps": 64460, "loss": 0.2345, "lr": 9.62751539209365e-06, "epoch": 4.225876512565932, "percentage": 21.13, "elapsed_time": "0:25:05", "remaining_time": "1:33:40", "throughput": 5507.78, "total_tokens": 8292624} {"current_steps": 13625, "total_steps": 64460, "loss": 0.2395, "lr": 9.627002481123696e-06, "epoch": 4.227427862240149, "percentage": 21.14, "elapsed_time": "0:25:06", "remaining_time": "1:33:39", "throughput": 5507.84, "total_tokens": 8295760} {"current_steps": 13630, "total_steps": 64460, "loss": 0.235, "lr": 9.626489230939669e-06, "epoch": 4.228979211914366, "percentage": 21.14, "elapsed_time": "0:25:06", "remaining_time": "1:33:38", "throughput": 5507.88, "total_tokens": 8298704} {"current_steps": 13635, "total_steps": 64460, "loss": 0.2321, "lr": 9.625975641579193e-06, "epoch": 4.230530561588582, "percentage": 21.15, "elapsed_time": "0:25:07", "remaining_time": "1:33:38", "throughput": 5508.1, "total_tokens": 8302064} {"current_steps": 13640, "total_steps": 64460, "loss": 0.231, "lr": 9.625461713079924e-06, "epoch": 4.2320819112627985, "percentage": 21.16, "elapsed_time": "0:25:07", "remaining_time": "1:33:37", "throughput": 5508.11, "total_tokens": 8304688} {"current_steps": 13645, "total_steps": 64460, "loss": 0.2314, "lr": 9.624947445479538e-06, "epoch": 4.233633260937015, "percentage": 21.17, "elapsed_time": "0:25:08", "remaining_time": "1:33:37", "throughput": 5508.67, "total_tokens": 8309488} {"current_steps": 13650, "total_steps": 64460, "loss": 0.2299, "lr": 9.624432838815736e-06, "epoch": 4.235184610611232, "percentage": 21.18, "elapsed_time": "0:25:08", "remaining_time": "1:33:36", "throughput": 5508.81, "total_tokens": 8312496} {"current_steps": 13655, "total_steps": 64460, "loss": 0.2315, "lr": 9.623917893126247e-06, "epoch": 4.236735960285448, "percentage": 21.18, "elapsed_time": "0:25:09", "remaining_time": "1:33:36", "throughput": 5509.19, "total_tokens": 8316624} {"current_steps": 13660, "total_steps": 64460, "loss": 0.2315, "lr": 9.62340260844882e-06, "epoch": 4.238287309959665, "percentage": 21.19, "elapsed_time": "0:25:10", "remaining_time": "1:33:35", "throughput": 5509.01, "total_tokens": 8318992} {"current_steps": 13665, "total_steps": 64460, "loss": 0.2321, "lr": 9.622886984821234e-06, "epoch": 4.2398386596338815, "percentage": 21.2, "elapsed_time": "0:25:10", "remaining_time": "1:33:35", "throughput": 5509.19, "total_tokens": 8322512} {"current_steps": 13670, "total_steps": 64460, "loss": 0.2311, "lr": 9.622371022281287e-06, "epoch": 4.241390009308098, "percentage": 21.21, "elapsed_time": "0:25:11", "remaining_time": "1:33:35", "throughput": 5509.69, "total_tokens": 8326608} {"current_steps": 13675, "total_steps": 64460, "loss": 0.2274, "lr": 9.621854720866806e-06, "epoch": 4.242941358982314, "percentage": 21.21, "elapsed_time": "0:25:11", "remaining_time": "1:33:34", "throughput": 5509.79, "total_tokens": 8329424} {"current_steps": 13680, "total_steps": 64460, "loss": 0.226, "lr": 9.621338080615645e-06, "epoch": 4.244492708656531, "percentage": 21.22, "elapsed_time": "0:25:12", "remaining_time": "1:33:33", "throughput": 5509.8, "total_tokens": 8332144} {"current_steps": 13685, "total_steps": 64460, "loss": 0.237, "lr": 9.620821101565678e-06, "epoch": 4.246044058330748, "percentage": 21.23, "elapsed_time": "0:25:12", "remaining_time": "1:33:32", "throughput": 5509.75, "total_tokens": 8334864} {"current_steps": 13690, "total_steps": 64460, "loss": 0.2365, "lr": 9.620303783754805e-06, "epoch": 4.2475954080049645, "percentage": 21.24, "elapsed_time": "0:25:13", "remaining_time": "1:33:31", "throughput": 5509.51, "total_tokens": 8337168} {"current_steps": 13695, "total_steps": 64460, "loss": 0.2325, "lr": 9.619786127220951e-06, "epoch": 4.249146757679181, "percentage": 21.25, "elapsed_time": "0:25:13", "remaining_time": "1:33:31", "throughput": 5509.32, "total_tokens": 8339888} {"current_steps": 13700, "total_steps": 64460, "loss": 0.2299, "lr": 9.619268132002069e-06, "epoch": 4.250698107353397, "percentage": 21.25, "elapsed_time": "0:25:14", "remaining_time": "1:33:30", "throughput": 5509.16, "total_tokens": 8342192} {"current_steps": 13705, "total_steps": 64460, "loss": 0.2304, "lr": 9.618749798136131e-06, "epoch": 4.252249457027614, "percentage": 21.26, "elapsed_time": "0:25:14", "remaining_time": "1:33:30", "throughput": 5509.61, "total_tokens": 8346320} {"current_steps": 13710, "total_steps": 64460, "loss": 0.2315, "lr": 9.618231125661141e-06, "epoch": 4.253800806701831, "percentage": 21.27, "elapsed_time": "0:25:15", "remaining_time": "1:33:29", "throughput": 5509.92, "total_tokens": 8350128} {"current_steps": 13715, "total_steps": 64460, "loss": 0.2293, "lr": 9.617712114615119e-06, "epoch": 4.2553521563760475, "percentage": 21.28, "elapsed_time": "0:25:15", "remaining_time": "1:33:29", "throughput": 5510.1, "total_tokens": 8353200} {"current_steps": 13720, "total_steps": 64460, "loss": 0.2295, "lr": 9.617192765036119e-06, "epoch": 4.256903506050263, "percentage": 21.28, "elapsed_time": "0:25:16", "remaining_time": "1:33:28", "throughput": 5510.21, "total_tokens": 8356176} {"current_steps": 13725, "total_steps": 64460, "loss": 0.2257, "lr": 9.616673076962213e-06, "epoch": 4.25845485572448, "percentage": 21.29, "elapsed_time": "0:25:17", "remaining_time": "1:33:27", "throughput": 5510.36, "total_tokens": 8359344} {"current_steps": 13730, "total_steps": 64460, "loss": 0.2393, "lr": 9.6161530504315e-06, "epoch": 4.260006205398697, "percentage": 21.3, "elapsed_time": "0:25:17", "remaining_time": "1:33:27", "throughput": 5510.56, "total_tokens": 8362576} {"current_steps": 13735, "total_steps": 64460, "loss": 0.2309, "lr": 9.615632685482106e-06, "epoch": 4.261557555072914, "percentage": 21.31, "elapsed_time": "0:25:18", "remaining_time": "1:33:26", "throughput": 5511.27, "total_tokens": 8367152} {"current_steps": 13740, "total_steps": 64460, "loss": 0.2337, "lr": 9.615111982152177e-06, "epoch": 4.26310890474713, "percentage": 21.32, "elapsed_time": "0:25:18", "remaining_time": "1:33:26", "throughput": 5511.53, "total_tokens": 8370640} {"current_steps": 13745, "total_steps": 64460, "loss": 0.2355, "lr": 9.61459094047989e-06, "epoch": 4.264660254421346, "percentage": 21.32, "elapsed_time": "0:25:19", "remaining_time": "1:33:25", "throughput": 5511.56, "total_tokens": 8373584} {"current_steps": 13750, "total_steps": 64460, "loss": 0.2275, "lr": 9.614069560503443e-06, "epoch": 4.266211604095563, "percentage": 21.33, "elapsed_time": "0:25:19", "remaining_time": "1:33:25", "throughput": 5511.29, "total_tokens": 8376080} {"current_steps": 13755, "total_steps": 64460, "loss": 0.2311, "lr": 9.613547842261057e-06, "epoch": 4.26776295376978, "percentage": 21.34, "elapsed_time": "0:25:20", "remaining_time": "1:33:24", "throughput": 5511.47, "total_tokens": 8379792} {"current_steps": 13760, "total_steps": 64460, "loss": 0.2326, "lr": 9.613025785790984e-06, "epoch": 4.269314303443997, "percentage": 21.35, "elapsed_time": "0:25:20", "remaining_time": "1:33:24", "throughput": 5511.64, "total_tokens": 8382992} {"current_steps": 13765, "total_steps": 64460, "loss": 0.2243, "lr": 9.612503391131492e-06, "epoch": 4.2708656531182125, "percentage": 21.35, "elapsed_time": "0:25:21", "remaining_time": "1:33:23", "throughput": 5511.72, "total_tokens": 8385872} {"current_steps": 13770, "total_steps": 64460, "loss": 0.2294, "lr": 9.611980658320882e-06, "epoch": 4.272417002792429, "percentage": 21.36, "elapsed_time": "0:25:21", "remaining_time": "1:33:22", "throughput": 5511.62, "total_tokens": 8388432} {"current_steps": 13775, "total_steps": 64460, "loss": 0.2291, "lr": 9.611457587397474e-06, "epoch": 4.273968352466646, "percentage": 21.37, "elapsed_time": "0:25:22", "remaining_time": "1:33:22", "throughput": 5511.51, "total_tokens": 8391248} {"current_steps": 13780, "total_steps": 64460, "loss": 0.2295, "lr": 9.61093417839962e-06, "epoch": 4.275519702140863, "percentage": 21.38, "elapsed_time": "0:25:22", "remaining_time": "1:33:21", "throughput": 5511.49, "total_tokens": 8393840} {"current_steps": 13785, "total_steps": 64460, "loss": 0.2278, "lr": 9.610410431365688e-06, "epoch": 4.277071051815079, "percentage": 21.39, "elapsed_time": "0:25:23", "remaining_time": "1:33:20", "throughput": 5511.42, "total_tokens": 8396496} {"current_steps": 13790, "total_steps": 64460, "loss": 0.2369, "lr": 9.609886346334075e-06, "epoch": 4.2786224014892955, "percentage": 21.39, "elapsed_time": "0:25:23", "remaining_time": "1:33:19", "throughput": 5511.29, "total_tokens": 8398960} {"current_steps": 13795, "total_steps": 64460, "loss": 0.235, "lr": 9.609361923343206e-06, "epoch": 4.280173751163512, "percentage": 21.4, "elapsed_time": "0:25:24", "remaining_time": "1:33:19", "throughput": 5511.85, "total_tokens": 8403056} {"current_steps": 13800, "total_steps": 64460, "loss": 0.2358, "lr": 9.608837162431522e-06, "epoch": 4.281725100837729, "percentage": 21.41, "elapsed_time": "0:25:25", "remaining_time": "1:33:18", "throughput": 5511.95, "total_tokens": 8405936} {"current_steps": 13805, "total_steps": 64460, "loss": 0.2302, "lr": 9.6083120636375e-06, "epoch": 4.283276450511945, "percentage": 21.42, "elapsed_time": "0:25:25", "remaining_time": "1:33:17", "throughput": 5512.05, "total_tokens": 8408976} {"current_steps": 13810, "total_steps": 64460, "loss": 0.2346, "lr": 9.607786626999632e-06, "epoch": 4.284827800186162, "percentage": 21.42, "elapsed_time": "0:25:26", "remaining_time": "1:33:16", "throughput": 5511.88, "total_tokens": 8411376} {"current_steps": 13815, "total_steps": 64460, "loss": 0.2295, "lr": 9.607260852556438e-06, "epoch": 4.2863791498603785, "percentage": 21.43, "elapsed_time": "0:25:26", "remaining_time": "1:33:16", "throughput": 5512.04, "total_tokens": 8415056} {"current_steps": 13820, "total_steps": 64460, "loss": 0.2304, "lr": 9.606734740346466e-06, "epoch": 4.287930499534595, "percentage": 21.44, "elapsed_time": "0:25:27", "remaining_time": "1:33:15", "throughput": 5512.01, "total_tokens": 8417808} {"current_steps": 13825, "total_steps": 64460, "loss": 0.2309, "lr": 9.606208290408288e-06, "epoch": 4.289481849208812, "percentage": 21.45, "elapsed_time": "0:25:27", "remaining_time": "1:33:15", "throughput": 5512.15, "total_tokens": 8420688} {"current_steps": 13830, "total_steps": 64460, "loss": 0.2293, "lr": 9.605681502780495e-06, "epoch": 4.291033198883028, "percentage": 21.46, "elapsed_time": "0:25:28", "remaining_time": "1:33:14", "throughput": 5512.08, "total_tokens": 8423280} {"current_steps": 13835, "total_steps": 64460, "loss": 0.2283, "lr": 9.605154377501709e-06, "epoch": 4.292584548557245, "percentage": 21.46, "elapsed_time": "0:25:28", "remaining_time": "1:33:13", "throughput": 5512.22, "total_tokens": 8426224} {"current_steps": 13840, "total_steps": 64460, "loss": 0.2324, "lr": 9.604626914610573e-06, "epoch": 4.2941358982314615, "percentage": 21.47, "elapsed_time": "0:25:29", "remaining_time": "1:33:12", "throughput": 5512.35, "total_tokens": 8429232} {"current_steps": 13845, "total_steps": 64460, "loss": 0.2277, "lr": 9.604099114145757e-06, "epoch": 4.295687247905678, "percentage": 21.48, "elapsed_time": "0:25:29", "remaining_time": "1:33:12", "throughput": 5512.39, "total_tokens": 8431920} {"current_steps": 13850, "total_steps": 64460, "loss": 0.2278, "lr": 9.603570976145958e-06, "epoch": 4.297238597579894, "percentage": 21.49, "elapsed_time": "0:25:30", "remaining_time": "1:33:11", "throughput": 5512.82, "total_tokens": 8435888} {"current_steps": 13855, "total_steps": 64460, "loss": 0.2303, "lr": 9.603042500649888e-06, "epoch": 4.298789947254111, "percentage": 21.49, "elapsed_time": "0:25:30", "remaining_time": "1:33:11", "throughput": 5513.0, "total_tokens": 8440336} {"current_steps": 13860, "total_steps": 64460, "loss": 0.2323, "lr": 9.602513687696298e-06, "epoch": 4.300341296928328, "percentage": 21.5, "elapsed_time": "0:25:31", "remaining_time": "1:33:11", "throughput": 5513.09, "total_tokens": 8443088} {"current_steps": 13865, "total_steps": 64460, "loss": 0.232, "lr": 9.601984537323951e-06, "epoch": 4.3018926466025444, "percentage": 21.51, "elapsed_time": "0:25:31", "remaining_time": "1:33:10", "throughput": 5513.18, "total_tokens": 8446192} {"current_steps": 13870, "total_steps": 64460, "loss": 0.2346, "lr": 9.601455049571642e-06, "epoch": 4.30344399627676, "percentage": 21.52, "elapsed_time": "0:25:32", "remaining_time": "1:33:09", "throughput": 5513.27, "total_tokens": 8449040} {"current_steps": 13875, "total_steps": 64460, "loss": 0.2404, "lr": 9.600925224478188e-06, "epoch": 4.304995345950977, "percentage": 21.52, "elapsed_time": "0:25:33", "remaining_time": "1:33:09", "throughput": 5513.52, "total_tokens": 8452624} {"current_steps": 13880, "total_steps": 64460, "loss": 0.2314, "lr": 9.600395062082433e-06, "epoch": 4.306546695625194, "percentage": 21.53, "elapsed_time": "0:25:33", "remaining_time": "1:33:08", "throughput": 5513.5, "total_tokens": 8455280} {"current_steps": 13885, "total_steps": 64460, "loss": 0.2288, "lr": 9.599864562423242e-06, "epoch": 4.308098045299411, "percentage": 21.54, "elapsed_time": "0:25:34", "remaining_time": "1:33:07", "throughput": 5513.58, "total_tokens": 8458192} {"current_steps": 13890, "total_steps": 64460, "loss": 0.2325, "lr": 9.59933372553951e-06, "epoch": 4.309649394973627, "percentage": 21.55, "elapsed_time": "0:25:34", "remaining_time": "1:33:06", "throughput": 5513.63, "total_tokens": 8460944} {"current_steps": 13895, "total_steps": 64460, "loss": 0.2333, "lr": 9.59880255147015e-06, "epoch": 4.311200744647843, "percentage": 21.56, "elapsed_time": "0:25:35", "remaining_time": "1:33:06", "throughput": 5513.72, "total_tokens": 8463728} {"current_steps": 13900, "total_steps": 64460, "loss": 0.2318, "lr": 9.598271040254106e-06, "epoch": 4.31275209432206, "percentage": 21.56, "elapsed_time": "0:25:35", "remaining_time": "1:33:05", "throughput": 5513.9, "total_tokens": 8466800} {"current_steps": 13905, "total_steps": 64460, "loss": 0.2349, "lr": 9.597739191930342e-06, "epoch": 4.314303443996277, "percentage": 21.57, "elapsed_time": "0:25:36", "remaining_time": "1:33:04", "throughput": 5513.88, "total_tokens": 8469776} {"current_steps": 13910, "total_steps": 64460, "loss": 0.2274, "lr": 9.59720700653785e-06, "epoch": 4.315854793670494, "percentage": 21.58, "elapsed_time": "0:25:36", "remaining_time": "1:33:04", "throughput": 5513.59, "total_tokens": 8472176} {"current_steps": 13915, "total_steps": 64460, "loss": 0.2274, "lr": 9.596674484115646e-06, "epoch": 4.3174061433447095, "percentage": 21.59, "elapsed_time": "0:25:37", "remaining_time": "1:33:03", "throughput": 5513.98, "total_tokens": 8476080} {"current_steps": 13920, "total_steps": 64460, "loss": 0.2336, "lr": 9.596141624702769e-06, "epoch": 4.318957493018926, "percentage": 21.59, "elapsed_time": "0:25:37", "remaining_time": "1:33:03", "throughput": 5513.98, "total_tokens": 8478960} {"current_steps": 13925, "total_steps": 64460, "loss": 0.2305, "lr": 9.595608428338285e-06, "epoch": 4.320508842693143, "percentage": 21.6, "elapsed_time": "0:25:38", "remaining_time": "1:33:02", "throughput": 5514.18, "total_tokens": 8482064} {"current_steps": 13930, "total_steps": 64460, "loss": 0.228, "lr": 9.595074895061282e-06, "epoch": 4.32206019236736, "percentage": 21.61, "elapsed_time": "0:25:38", "remaining_time": "1:33:01", "throughput": 5514.27, "total_tokens": 8484880} {"current_steps": 13935, "total_steps": 64460, "loss": 0.2248, "lr": 9.594541024910876e-06, "epoch": 4.323611542041576, "percentage": 21.62, "elapsed_time": "0:25:39", "remaining_time": "1:33:00", "throughput": 5514.24, "total_tokens": 8487568} {"current_steps": 13940, "total_steps": 64460, "loss": 0.2316, "lr": 9.594006817926206e-06, "epoch": 4.3251628917157925, "percentage": 21.63, "elapsed_time": "0:25:39", "remaining_time": "1:33:00", "throughput": 5514.11, "total_tokens": 8490096} {"current_steps": 13945, "total_steps": 64460, "loss": 0.2304, "lr": 9.593472274146434e-06, "epoch": 4.326714241390009, "percentage": 21.63, "elapsed_time": "0:25:40", "remaining_time": "1:32:59", "throughput": 5514.17, "total_tokens": 8492912} {"current_steps": 13950, "total_steps": 64460, "loss": 0.2358, "lr": 9.592937393610751e-06, "epoch": 4.328265591064226, "percentage": 21.64, "elapsed_time": "0:25:40", "remaining_time": "1:32:59", "throughput": 5514.68, "total_tokens": 8497328} {"current_steps": 13955, "total_steps": 64460, "loss": 0.2291, "lr": 9.592402176358367e-06, "epoch": 4.329816940738443, "percentage": 21.65, "elapsed_time": "0:25:41", "remaining_time": "1:32:58", "throughput": 5514.68, "total_tokens": 8499920} {"current_steps": 13960, "total_steps": 64460, "loss": 0.2307, "lr": 9.591866622428521e-06, "epoch": 4.331368290412659, "percentage": 21.66, "elapsed_time": "0:25:41", "remaining_time": "1:32:57", "throughput": 5514.79, "total_tokens": 8502608} {"current_steps": 13965, "total_steps": 64460, "loss": 0.2288, "lr": 9.591330731860478e-06, "epoch": 4.3329196400868755, "percentage": 21.66, "elapsed_time": "0:25:42", "remaining_time": "1:32:56", "throughput": 5515.03, "total_tokens": 8506096} {"current_steps": 13970, "total_steps": 64460, "loss": 0.2381, "lr": 9.590794504693521e-06, "epoch": 4.334470989761092, "percentage": 21.67, "elapsed_time": "0:25:42", "remaining_time": "1:32:56", "throughput": 5515.44, "total_tokens": 8509840} {"current_steps": 13975, "total_steps": 64460, "loss": 0.2301, "lr": 9.590257940966964e-06, "epoch": 4.336022339435309, "percentage": 21.68, "elapsed_time": "0:25:43", "remaining_time": "1:32:56", "throughput": 5516.07, "total_tokens": 8515120} {"current_steps": 13980, "total_steps": 64460, "loss": 0.2354, "lr": 9.589721040720143e-06, "epoch": 4.337573689109525, "percentage": 21.69, "elapsed_time": "0:25:44", "remaining_time": "1:32:55", "throughput": 5516.38, "total_tokens": 8518448} {"current_steps": 13985, "total_steps": 64460, "loss": 0.2371, "lr": 9.58918380399242e-06, "epoch": 4.339125038783742, "percentage": 21.7, "elapsed_time": "0:25:44", "remaining_time": "1:32:55", "throughput": 5516.36, "total_tokens": 8521296} {"current_steps": 13990, "total_steps": 64460, "loss": 0.2347, "lr": 9.588646230823179e-06, "epoch": 4.3406763884579584, "percentage": 21.7, "elapsed_time": "0:25:45", "remaining_time": "1:32:54", "throughput": 5516.45, "total_tokens": 8524208} {"current_steps": 13995, "total_steps": 64460, "loss": 0.2294, "lr": 9.588108321251832e-06, "epoch": 4.342227738132175, "percentage": 21.71, "elapsed_time": "0:25:45", "remaining_time": "1:32:53", "throughput": 5516.3, "total_tokens": 8526544} {"current_steps": 14000, "total_steps": 64460, "loss": 0.2284, "lr": 9.587570075317813e-06, "epoch": 4.343779087806391, "percentage": 21.72, "elapsed_time": "0:25:46", "remaining_time": "1:32:52", "throughput": 5516.16, "total_tokens": 8528976} {"current_steps": 14005, "total_steps": 64460, "loss": 0.2327, "lr": 9.587031493060585e-06, "epoch": 4.345330437480608, "percentage": 21.73, "elapsed_time": "0:25:46", "remaining_time": "1:32:52", "throughput": 5516.35, "total_tokens": 8532080} {"current_steps": 14010, "total_steps": 64460, "loss": 0.229, "lr": 9.586492574519628e-06, "epoch": 4.346881787154825, "percentage": 21.73, "elapsed_time": "0:25:47", "remaining_time": "1:32:51", "throughput": 5516.06, "total_tokens": 8534192} {"current_steps": 14015, "total_steps": 64460, "loss": 0.2353, "lr": 9.585953319734454e-06, "epoch": 4.348433136829041, "percentage": 21.74, "elapsed_time": "0:25:47", "remaining_time": "1:32:50", "throughput": 5515.9, "total_tokens": 8536592} {"current_steps": 14020, "total_steps": 64460, "loss": 0.2294, "lr": 9.585413728744595e-06, "epoch": 4.349984486503258, "percentage": 21.75, "elapsed_time": "0:25:48", "remaining_time": "1:32:49", "throughput": 5515.79, "total_tokens": 8539216} {"current_steps": 14025, "total_steps": 64460, "loss": 0.2274, "lr": 9.58487380158961e-06, "epoch": 4.351535836177474, "percentage": 21.76, "elapsed_time": "0:25:48", "remaining_time": "1:32:49", "throughput": 5515.7, "total_tokens": 8542320} {"current_steps": 14030, "total_steps": 64460, "loss": 0.2295, "lr": 9.584333538309083e-06, "epoch": 4.353087185851691, "percentage": 21.77, "elapsed_time": "0:25:49", "remaining_time": "1:32:48", "throughput": 5515.58, "total_tokens": 8544784} {"current_steps": 14035, "total_steps": 64460, "loss": 0.2295, "lr": 9.583792938942622e-06, "epoch": 4.354638535525908, "percentage": 21.77, "elapsed_time": "0:25:49", "remaining_time": "1:32:47", "throughput": 5515.78, "total_tokens": 8547888} {"current_steps": 14040, "total_steps": 64460, "loss": 0.2336, "lr": 9.583252003529856e-06, "epoch": 4.356189885200124, "percentage": 21.78, "elapsed_time": "0:25:50", "remaining_time": "1:32:47", "throughput": 5515.32, "total_tokens": 8550192} {"current_steps": 14045, "total_steps": 64460, "loss": 0.231, "lr": 9.582710732110446e-06, "epoch": 4.35774123487434, "percentage": 21.79, "elapsed_time": "0:25:50", "remaining_time": "1:32:46", "throughput": 5515.43, "total_tokens": 8553680} {"current_steps": 14050, "total_steps": 64460, "loss": 0.23, "lr": 9.582169124724071e-06, "epoch": 4.359292584548557, "percentage": 21.8, "elapsed_time": "0:25:51", "remaining_time": "1:32:46", "throughput": 5515.38, "total_tokens": 8556368} {"current_steps": 14055, "total_steps": 64460, "loss": 0.2315, "lr": 9.58162718141044e-06, "epoch": 4.360843934222774, "percentage": 21.8, "elapsed_time": "0:25:52", "remaining_time": "1:32:46", "throughput": 5515.41, "total_tokens": 8560464} {"current_steps": 14060, "total_steps": 64460, "loss": 0.2316, "lr": 9.581084902209278e-06, "epoch": 4.362395283896991, "percentage": 21.81, "elapsed_time": "0:25:52", "remaining_time": "1:32:45", "throughput": 5515.29, "total_tokens": 8563216} {"current_steps": 14065, "total_steps": 64460, "loss": 0.2323, "lr": 9.580542287160348e-06, "epoch": 4.3639466335712065, "percentage": 21.82, "elapsed_time": "0:25:53", "remaining_time": "1:32:45", "throughput": 5515.55, "total_tokens": 8567280} {"current_steps": 14070, "total_steps": 64460, "loss": 0.2322, "lr": 9.579999336303427e-06, "epoch": 4.365497983245423, "percentage": 21.83, "elapsed_time": "0:25:53", "remaining_time": "1:32:44", "throughput": 5515.65, "total_tokens": 8570000} {"current_steps": 14075, "total_steps": 64460, "loss": 0.2308, "lr": 9.579456049678318e-06, "epoch": 4.36704933291964, "percentage": 21.84, "elapsed_time": "0:25:54", "remaining_time": "1:32:43", "throughput": 5515.66, "total_tokens": 8572784} {"current_steps": 14080, "total_steps": 64460, "loss": 0.2427, "lr": 9.578912427324851e-06, "epoch": 4.368600682593857, "percentage": 21.84, "elapsed_time": "0:25:54", "remaining_time": "1:32:43", "throughput": 5515.52, "total_tokens": 8575248} {"current_steps": 14085, "total_steps": 64460, "loss": 0.232, "lr": 9.578368469282882e-06, "epoch": 4.370152032268074, "percentage": 21.85, "elapsed_time": "0:25:55", "remaining_time": "1:32:42", "throughput": 5515.28, "total_tokens": 8577552} {"current_steps": 14090, "total_steps": 64460, "loss": 0.2282, "lr": 9.577824175592287e-06, "epoch": 4.3717033819422895, "percentage": 21.86, "elapsed_time": "0:25:55", "remaining_time": "1:32:41", "throughput": 5515.24, "total_tokens": 8580176} {"current_steps": 14095, "total_steps": 64460, "loss": 0.2325, "lr": 9.577279546292972e-06, "epoch": 4.373254731616506, "percentage": 21.87, "elapsed_time": "0:25:56", "remaining_time": "1:32:40", "throughput": 5515.49, "total_tokens": 8583504} {"current_steps": 14100, "total_steps": 64460, "loss": 0.2291, "lr": 9.576734581424863e-06, "epoch": 4.374806081290723, "percentage": 21.87, "elapsed_time": "0:25:56", "remaining_time": "1:32:40", "throughput": 5515.62, "total_tokens": 8586448} {"current_steps": 14105, "total_steps": 64460, "loss": 0.2297, "lr": 9.57618928102791e-06, "epoch": 4.37635743096494, "percentage": 21.88, "elapsed_time": "0:25:57", "remaining_time": "1:32:39", "throughput": 5515.39, "total_tokens": 8588976} {"current_steps": 14110, "total_steps": 64460, "loss": 0.2231, "lr": 9.575643645142095e-06, "epoch": 4.377908780639156, "percentage": 21.89, "elapsed_time": "0:25:57", "remaining_time": "1:32:38", "throughput": 5515.39, "total_tokens": 8591696} {"current_steps": 14115, "total_steps": 64460, "loss": 0.2361, "lr": 9.575097673807416e-06, "epoch": 4.3794601303133724, "percentage": 21.9, "elapsed_time": "0:25:58", "remaining_time": "1:32:37", "throughput": 5515.66, "total_tokens": 8594864} {"current_steps": 14120, "total_steps": 64460, "loss": 0.2352, "lr": 9.574551367063902e-06, "epoch": 4.381011479987589, "percentage": 21.91, "elapsed_time": "0:25:58", "remaining_time": "1:32:37", "throughput": 5515.8, "total_tokens": 8597936} {"current_steps": 14125, "total_steps": 64460, "loss": 0.2309, "lr": 9.5740047249516e-06, "epoch": 4.382562829661806, "percentage": 21.91, "elapsed_time": "0:25:59", "remaining_time": "1:32:36", "throughput": 5515.58, "total_tokens": 8600496} {"current_steps": 14130, "total_steps": 64460, "loss": 0.2278, "lr": 9.573457747510589e-06, "epoch": 4.384114179336022, "percentage": 21.92, "elapsed_time": "0:25:59", "remaining_time": "1:32:35", "throughput": 5515.78, "total_tokens": 8603568} {"current_steps": 14135, "total_steps": 64460, "loss": 0.2289, "lr": 9.572910434780965e-06, "epoch": 4.385665529010239, "percentage": 21.93, "elapsed_time": "0:26:00", "remaining_time": "1:32:35", "throughput": 5516.11, "total_tokens": 8606992} {"current_steps": 14140, "total_steps": 64460, "loss": 0.2307, "lr": 9.572362786802856e-06, "epoch": 4.387216878684455, "percentage": 21.94, "elapsed_time": "0:26:00", "remaining_time": "1:32:35", "throughput": 5516.26, "total_tokens": 8610736} {"current_steps": 14145, "total_steps": 64460, "loss": 0.2399, "lr": 9.57181480361641e-06, "epoch": 4.388768228358672, "percentage": 21.94, "elapsed_time": "0:26:01", "remaining_time": "1:32:34", "throughput": 5515.91, "total_tokens": 8612784} {"current_steps": 14150, "total_steps": 64460, "loss": 0.232, "lr": 9.5712664852618e-06, "epoch": 4.390319578032889, "percentage": 21.95, "elapsed_time": "0:26:01", "remaining_time": "1:32:33", "throughput": 5516.14, "total_tokens": 8616144} {"current_steps": 14155, "total_steps": 64460, "loss": 0.23, "lr": 9.570717831779225e-06, "epoch": 4.391870927707105, "percentage": 21.96, "elapsed_time": "0:26:02", "remaining_time": "1:32:32", "throughput": 5516.39, "total_tokens": 8619408} {"current_steps": 14160, "total_steps": 64460, "loss": 0.2321, "lr": 9.570168843208908e-06, "epoch": 4.393422277381322, "percentage": 21.97, "elapsed_time": "0:26:03", "remaining_time": "1:32:32", "throughput": 5516.8, "total_tokens": 8623024} {"current_steps": 14165, "total_steps": 64460, "loss": 0.2334, "lr": 9.569619519591095e-06, "epoch": 4.394973627055538, "percentage": 21.97, "elapsed_time": "0:26:03", "remaining_time": "1:32:31", "throughput": 5516.74, "total_tokens": 8625520} {"current_steps": 14170, "total_steps": 64460, "loss": 0.2308, "lr": 9.56906986096606e-06, "epoch": 4.396524976729755, "percentage": 21.98, "elapsed_time": "0:26:04", "remaining_time": "1:32:30", "throughput": 5516.76, "total_tokens": 8628304} {"current_steps": 14175, "total_steps": 64460, "loss": 0.2297, "lr": 9.568519867374098e-06, "epoch": 4.398076326403971, "percentage": 21.99, "elapsed_time": "0:26:04", "remaining_time": "1:32:30", "throughput": 5516.79, "total_tokens": 8631376} {"current_steps": 14180, "total_steps": 64460, "loss": 0.2342, "lr": 9.56796953885553e-06, "epoch": 4.399627676078188, "percentage": 22.0, "elapsed_time": "0:26:05", "remaining_time": "1:32:29", "throughput": 5516.94, "total_tokens": 8634384} {"current_steps": 14185, "total_steps": 64460, "loss": 0.2338, "lr": 9.567418875450701e-06, "epoch": 4.401179025752405, "percentage": 22.01, "elapsed_time": "0:26:05", "remaining_time": "1:32:28", "throughput": 5517.1, "total_tokens": 8637680} {"current_steps": 14190, "total_steps": 64460, "loss": 0.228, "lr": 9.566867877199983e-06, "epoch": 4.402730375426621, "percentage": 22.01, "elapsed_time": "0:26:06", "remaining_time": "1:32:28", "throughput": 5517.24, "total_tokens": 8640944} {"current_steps": 14195, "total_steps": 64460, "loss": 0.2311, "lr": 9.56631654414377e-06, "epoch": 4.404281725100837, "percentage": 22.02, "elapsed_time": "0:26:06", "remaining_time": "1:32:27", "throughput": 5517.56, "total_tokens": 8644720} {"current_steps": 14200, "total_steps": 64460, "loss": 0.2233, "lr": 9.565764876322482e-06, "epoch": 4.405833074775054, "percentage": 22.03, "elapsed_time": "0:26:07", "remaining_time": "1:32:27", "throughput": 5517.78, "total_tokens": 8648272} {"current_steps": 14205, "total_steps": 64460, "loss": 0.2347, "lr": 9.56521287377656e-06, "epoch": 4.407384424449271, "percentage": 22.04, "elapsed_time": "0:26:07", "remaining_time": "1:32:26", "throughput": 5517.71, "total_tokens": 8650768} {"current_steps": 14210, "total_steps": 64460, "loss": 0.2379, "lr": 9.564660536546475e-06, "epoch": 4.408935774123488, "percentage": 22.04, "elapsed_time": "0:26:08", "remaining_time": "1:32:26", "throughput": 5518.07, "total_tokens": 8654544} {"current_steps": 14215, "total_steps": 64460, "loss": 0.231, "lr": 9.564107864672718e-06, "epoch": 4.410487123797704, "percentage": 22.05, "elapsed_time": "0:26:08", "remaining_time": "1:32:25", "throughput": 5518.22, "total_tokens": 8657808} {"current_steps": 14220, "total_steps": 64460, "loss": 0.2263, "lr": 9.563554858195808e-06, "epoch": 4.41203847347192, "percentage": 22.06, "elapsed_time": "0:26:09", "remaining_time": "1:32:25", "throughput": 5518.5, "total_tokens": 8661296} {"current_steps": 14225, "total_steps": 64460, "loss": 0.2294, "lr": 9.563001517156287e-06, "epoch": 4.413589823146137, "percentage": 22.07, "elapsed_time": "0:26:10", "remaining_time": "1:32:24", "throughput": 5518.68, "total_tokens": 8664432} {"current_steps": 14230, "total_steps": 64460, "loss": 0.2315, "lr": 9.56244784159472e-06, "epoch": 4.415141172820354, "percentage": 22.08, "elapsed_time": "0:26:10", "remaining_time": "1:32:24", "throughput": 5518.95, "total_tokens": 8668400} {"current_steps": 14235, "total_steps": 64460, "loss": 0.2278, "lr": 9.561893831551699e-06, "epoch": 4.416692522494571, "percentage": 22.08, "elapsed_time": "0:26:11", "remaining_time": "1:32:23", "throughput": 5518.81, "total_tokens": 8670832} {"current_steps": 14240, "total_steps": 64460, "loss": 0.2324, "lr": 9.56133948706784e-06, "epoch": 4.4182438721687864, "percentage": 22.09, "elapsed_time": "0:26:11", "remaining_time": "1:32:23", "throughput": 5519.3, "total_tokens": 8675280} {"current_steps": 14245, "total_steps": 64460, "loss": 0.231, "lr": 9.56078480818378e-06, "epoch": 4.419795221843003, "percentage": 22.1, "elapsed_time": "0:26:12", "remaining_time": "1:32:23", "throughput": 5519.89, "total_tokens": 8679824} {"current_steps": 14250, "total_steps": 64460, "loss": 0.2295, "lr": 9.560229794940189e-06, "epoch": 4.42134657151722, "percentage": 22.11, "elapsed_time": "0:26:12", "remaining_time": "1:32:22", "throughput": 5519.94, "total_tokens": 8682672} {"current_steps": 14255, "total_steps": 64460, "loss": 0.2261, "lr": 9.55967444737775e-06, "epoch": 4.422897921191437, "percentage": 22.11, "elapsed_time": "0:26:13", "remaining_time": "1:32:22", "throughput": 5520.57, "total_tokens": 8687632} {"current_steps": 14260, "total_steps": 64460, "loss": 0.219, "lr": 9.55911876553718e-06, "epoch": 4.424449270865653, "percentage": 22.12, "elapsed_time": "0:26:14", "remaining_time": "1:32:22", "throughput": 5520.97, "total_tokens": 8691568} {"current_steps": 14265, "total_steps": 64460, "loss": 0.2433, "lr": 9.558562749459219e-06, "epoch": 4.426000620539869, "percentage": 22.13, "elapsed_time": "0:26:14", "remaining_time": "1:32:21", "throughput": 5520.93, "total_tokens": 8694192} {"current_steps": 14270, "total_steps": 64460, "loss": 0.23, "lr": 9.558006399184624e-06, "epoch": 4.427551970214086, "percentage": 22.14, "elapsed_time": "0:26:15", "remaining_time": "1:32:20", "throughput": 5521.06, "total_tokens": 8697328} {"current_steps": 14275, "total_steps": 64460, "loss": 0.2203, "lr": 9.557449714754187e-06, "epoch": 4.429103319888303, "percentage": 22.15, "elapsed_time": "0:26:15", "remaining_time": "1:32:19", "throughput": 5520.84, "total_tokens": 8699632} {"current_steps": 14280, "total_steps": 64460, "loss": 0.2275, "lr": 9.556892696208717e-06, "epoch": 4.43065466956252, "percentage": 22.15, "elapsed_time": "0:26:16", "remaining_time": "1:32:19", "throughput": 5520.6, "total_tokens": 8702128} {"current_steps": 14285, "total_steps": 64460, "loss": 0.2239, "lr": 9.55633534358905e-06, "epoch": 4.432206019236736, "percentage": 22.16, "elapsed_time": "0:26:16", "remaining_time": "1:32:18", "throughput": 5520.8, "total_tokens": 8705840} {"current_steps": 14290, "total_steps": 64460, "loss": 0.2302, "lr": 9.555777656936048e-06, "epoch": 4.433757368910952, "percentage": 22.17, "elapsed_time": "0:26:17", "remaining_time": "1:32:18", "throughput": 5520.94, "total_tokens": 8708848} {"current_steps": 14295, "total_steps": 64460, "loss": 0.2375, "lr": 9.555219636290594e-06, "epoch": 4.435308718585169, "percentage": 22.18, "elapsed_time": "0:26:17", "remaining_time": "1:32:17", "throughput": 5520.82, "total_tokens": 8711248} {"current_steps": 14300, "total_steps": 64460, "loss": 0.2414, "lr": 9.5546612816936e-06, "epoch": 4.436860068259386, "percentage": 22.18, "elapsed_time": "0:26:18", "remaining_time": "1:32:16", "throughput": 5521.0, "total_tokens": 8714608} {"current_steps": 14305, "total_steps": 64460, "loss": 0.2284, "lr": 9.554102593185998e-06, "epoch": 4.438411417933602, "percentage": 22.19, "elapsed_time": "0:26:18", "remaining_time": "1:32:16", "throughput": 5521.08, "total_tokens": 8717584} {"current_steps": 14310, "total_steps": 64460, "loss": 0.2307, "lr": 9.553543570808747e-06, "epoch": 4.439962767607819, "percentage": 22.2, "elapsed_time": "0:26:19", "remaining_time": "1:32:15", "throughput": 5521.28, "total_tokens": 8721168} {"current_steps": 14315, "total_steps": 64460, "loss": 0.2299, "lr": 9.552984214602832e-06, "epoch": 4.441514117282035, "percentage": 22.21, "elapsed_time": "0:26:20", "remaining_time": "1:32:15", "throughput": 5520.93, "total_tokens": 8723568} {"current_steps": 14320, "total_steps": 64460, "loss": 0.2287, "lr": 9.552424524609259e-06, "epoch": 4.443065466956252, "percentage": 22.22, "elapsed_time": "0:26:20", "remaining_time": "1:32:14", "throughput": 5520.89, "total_tokens": 8726704} {"current_steps": 14325, "total_steps": 64460, "loss": 0.2367, "lr": 9.551864500869056e-06, "epoch": 4.444616816630468, "percentage": 22.22, "elapsed_time": "0:26:21", "remaining_time": "1:32:13", "throughput": 5521.05, "total_tokens": 8729776} {"current_steps": 14330, "total_steps": 64460, "loss": 0.2318, "lr": 9.551304143423287e-06, "epoch": 4.446168166304685, "percentage": 22.23, "elapsed_time": "0:26:21", "remaining_time": "1:32:12", "throughput": 5520.9, "total_tokens": 8732080} {"current_steps": 14335, "total_steps": 64460, "loss": 0.2321, "lr": 9.550743452313026e-06, "epoch": 4.447719515978902, "percentage": 22.24, "elapsed_time": "0:26:22", "remaining_time": "1:32:12", "throughput": 5521.26, "total_tokens": 8735984} {"current_steps": 14340, "total_steps": 64460, "loss": 0.2285, "lr": 9.550182427579382e-06, "epoch": 4.449270865653118, "percentage": 22.25, "elapsed_time": "0:26:22", "remaining_time": "1:32:11", "throughput": 5521.05, "total_tokens": 8738256} {"current_steps": 14345, "total_steps": 64460, "loss": 0.2291, "lr": 9.549621069263483e-06, "epoch": 4.450822215327335, "percentage": 22.25, "elapsed_time": "0:26:23", "remaining_time": "1:32:10", "throughput": 5521.02, "total_tokens": 8740848} {"current_steps": 14350, "total_steps": 64460, "loss": 0.2348, "lr": 9.549059377406486e-06, "epoch": 4.452373565001551, "percentage": 22.26, "elapsed_time": "0:26:23", "remaining_time": "1:32:10", "throughput": 5521.25, "total_tokens": 8744016} {"current_steps": 14355, "total_steps": 64460, "loss": 0.2341, "lr": 9.548497352049567e-06, "epoch": 4.453924914675768, "percentage": 22.27, "elapsed_time": "0:26:24", "remaining_time": "1:32:09", "throughput": 5521.6, "total_tokens": 8747696} {"current_steps": 14360, "total_steps": 64460, "loss": 0.2295, "lr": 9.54793499323393e-06, "epoch": 4.455476264349985, "percentage": 22.28, "elapsed_time": "0:26:24", "remaining_time": "1:32:09", "throughput": 5521.8, "total_tokens": 8750864} {"current_steps": 14365, "total_steps": 64460, "loss": 0.2289, "lr": 9.547372301000801e-06, "epoch": 4.457027614024201, "percentage": 22.29, "elapsed_time": "0:26:25", "remaining_time": "1:32:08", "throughput": 5522.02, "total_tokens": 8754160} {"current_steps": 14370, "total_steps": 64460, "loss": 0.229, "lr": 9.546809275391436e-06, "epoch": 4.458578963698417, "percentage": 22.29, "elapsed_time": "0:26:25", "remaining_time": "1:32:07", "throughput": 5522.2, "total_tokens": 8757168} {"current_steps": 14375, "total_steps": 64460, "loss": 0.2265, "lr": 9.546245916447106e-06, "epoch": 4.460130313372634, "percentage": 22.3, "elapsed_time": "0:26:26", "remaining_time": "1:32:07", "throughput": 5522.58, "total_tokens": 8760976} {"current_steps": 14380, "total_steps": 64460, "loss": 0.2306, "lr": 9.545682224209116e-06, "epoch": 4.461681663046851, "percentage": 22.31, "elapsed_time": "0:26:26", "remaining_time": "1:32:06", "throughput": 5522.73, "total_tokens": 8764016} {"current_steps": 14385, "total_steps": 64460, "loss": 0.2259, "lr": 9.54511819871879e-06, "epoch": 4.4632330127210675, "percentage": 22.32, "elapsed_time": "0:26:27", "remaining_time": "1:32:05", "throughput": 5523.04, "total_tokens": 8767344} {"current_steps": 14390, "total_steps": 64460, "loss": 0.2387, "lr": 9.544553840017476e-06, "epoch": 4.464784362395284, "percentage": 22.32, "elapsed_time": "0:26:27", "remaining_time": "1:32:05", "throughput": 5522.9, "total_tokens": 8769744} {"current_steps": 14395, "total_steps": 64460, "loss": 0.2268, "lr": 9.543989148146552e-06, "epoch": 4.4663357120695, "percentage": 22.33, "elapsed_time": "0:26:28", "remaining_time": "1:32:04", "throughput": 5522.7, "total_tokens": 8772240} {"current_steps": 14400, "total_steps": 64460, "loss": 0.2257, "lr": 9.543424123147416e-06, "epoch": 4.467887061743717, "percentage": 22.34, "elapsed_time": "0:26:28", "remaining_time": "1:32:03", "throughput": 5523.07, "total_tokens": 8775920} {"current_steps": 14405, "total_steps": 64460, "loss": 0.2362, "lr": 9.542858765061486e-06, "epoch": 4.469438411417934, "percentage": 22.35, "elapsed_time": "0:26:29", "remaining_time": "1:32:03", "throughput": 5522.81, "total_tokens": 8778128} {"current_steps": 14410, "total_steps": 64460, "loss": 0.233, "lr": 9.542293073930216e-06, "epoch": 4.4709897610921505, "percentage": 22.35, "elapsed_time": "0:26:29", "remaining_time": "1:32:02", "throughput": 5522.94, "total_tokens": 8781200} {"current_steps": 14415, "total_steps": 64460, "loss": 0.2299, "lr": 9.541727049795072e-06, "epoch": 4.472541110766366, "percentage": 22.36, "elapsed_time": "0:26:30", "remaining_time": "1:32:01", "throughput": 5522.9, "total_tokens": 8783856} {"current_steps": 14420, "total_steps": 64460, "loss": 0.2407, "lr": 9.541160692697556e-06, "epoch": 4.474092460440583, "percentage": 22.37, "elapsed_time": "0:26:30", "remaining_time": "1:32:00", "throughput": 5523.07, "total_tokens": 8786864} {"current_steps": 14425, "total_steps": 64460, "loss": 0.2343, "lr": 9.540594002679184e-06, "epoch": 4.4756438101148, "percentage": 22.38, "elapsed_time": "0:26:31", "remaining_time": "1:32:00", "throughput": 5522.96, "total_tokens": 8789328} {"current_steps": 14430, "total_steps": 64460, "loss": 0.2282, "lr": 9.540026979781505e-06, "epoch": 4.477195159789017, "percentage": 22.39, "elapsed_time": "0:26:31", "remaining_time": "1:31:59", "throughput": 5523.38, "total_tokens": 8793200} {"current_steps": 14435, "total_steps": 64460, "loss": 0.2315, "lr": 9.539459624046083e-06, "epoch": 4.478746509463233, "percentage": 22.39, "elapsed_time": "0:26:32", "remaining_time": "1:31:58", "throughput": 5522.97, "total_tokens": 8795280} {"current_steps": 14440, "total_steps": 64460, "loss": 0.2344, "lr": 9.538891935514519e-06, "epoch": 4.480297859137449, "percentage": 22.4, "elapsed_time": "0:26:33", "remaining_time": "1:31:58", "throughput": 5522.5, "total_tokens": 8797552} {"current_steps": 14445, "total_steps": 64460, "loss": 0.2295, "lr": 9.538323914228426e-06, "epoch": 4.481849208811666, "percentage": 22.41, "elapsed_time": "0:26:33", "remaining_time": "1:31:57", "throughput": 5522.57, "total_tokens": 8800560} {"current_steps": 14450, "total_steps": 64460, "loss": 0.2268, "lr": 9.537755560229447e-06, "epoch": 4.483400558485883, "percentage": 22.42, "elapsed_time": "0:26:34", "remaining_time": "1:31:56", "throughput": 5522.52, "total_tokens": 8803280} {"current_steps": 14455, "total_steps": 64460, "loss": 0.2331, "lr": 9.537186873559252e-06, "epoch": 4.4849519081601, "percentage": 22.42, "elapsed_time": "0:26:34", "remaining_time": "1:31:56", "throughput": 5522.92, "total_tokens": 8807568} {"current_steps": 14460, "total_steps": 64460, "loss": 0.2326, "lr": 9.536617854259532e-06, "epoch": 4.486503257834316, "percentage": 22.43, "elapsed_time": "0:26:35", "remaining_time": "1:31:56", "throughput": 5523.25, "total_tokens": 8811344} {"current_steps": 14465, "total_steps": 64460, "loss": 0.2264, "lr": 9.536048502371998e-06, "epoch": 4.488054607508532, "percentage": 22.44, "elapsed_time": "0:26:35", "remaining_time": "1:31:55", "throughput": 5523.45, "total_tokens": 8814448} {"current_steps": 14470, "total_steps": 64460, "loss": 0.2309, "lr": 9.535478817938397e-06, "epoch": 4.489605957182749, "percentage": 22.45, "elapsed_time": "0:26:36", "remaining_time": "1:31:54", "throughput": 5523.74, "total_tokens": 8817680} {"current_steps": 14475, "total_steps": 64460, "loss": 0.2315, "lr": 9.534908801000489e-06, "epoch": 4.491157306856966, "percentage": 22.46, "elapsed_time": "0:26:36", "remaining_time": "1:31:54", "throughput": 5524.15, "total_tokens": 8821616} {"current_steps": 14480, "total_steps": 64460, "loss": 0.2311, "lr": 9.534338451600065e-06, "epoch": 4.492708656531182, "percentage": 22.46, "elapsed_time": "0:26:37", "remaining_time": "1:31:54", "throughput": 5524.73, "total_tokens": 8826512} {"current_steps": 14485, "total_steps": 64460, "loss": 0.2327, "lr": 9.53376776977894e-06, "epoch": 4.494260006205399, "percentage": 22.47, "elapsed_time": "0:26:38", "remaining_time": "1:31:53", "throughput": 5524.71, "total_tokens": 8829232} {"current_steps": 14490, "total_steps": 64460, "loss": 0.2243, "lr": 9.533196755578947e-06, "epoch": 4.495811355879615, "percentage": 22.48, "elapsed_time": "0:26:38", "remaining_time": "1:31:52", "throughput": 5524.67, "total_tokens": 8831888} {"current_steps": 14495, "total_steps": 64460, "loss": 0.2274, "lr": 9.53262540904195e-06, "epoch": 4.497362705553832, "percentage": 22.49, "elapsed_time": "0:26:39", "remaining_time": "1:31:52", "throughput": 5524.82, "total_tokens": 8834736} {"current_steps": 14500, "total_steps": 64460, "loss": 0.2311, "lr": 9.532053730209837e-06, "epoch": 4.498914055228048, "percentage": 22.49, "elapsed_time": "0:26:39", "remaining_time": "1:31:51", "throughput": 5524.89, "total_tokens": 8837744} {"current_steps": 14505, "total_steps": 64460, "loss": 0.2321, "lr": 9.53148171912452e-06, "epoch": 4.500465404902265, "percentage": 22.5, "elapsed_time": "0:26:40", "remaining_time": "1:31:51", "throughput": 5525.32, "total_tokens": 8841648} {"current_steps": 14510, "total_steps": 64460, "loss": 0.2321, "lr": 9.530909375827931e-06, "epoch": 4.5020167545764815, "percentage": 22.51, "elapsed_time": "0:26:40", "remaining_time": "1:31:50", "throughput": 5525.46, "total_tokens": 8844784} {"current_steps": 14515, "total_steps": 64460, "loss": 0.231, "lr": 9.53033670036203e-06, "epoch": 4.503568104250698, "percentage": 22.52, "elapsed_time": "0:26:41", "remaining_time": "1:31:49", "throughput": 5525.32, "total_tokens": 8847280} {"current_steps": 14520, "total_steps": 64460, "loss": 0.2284, "lr": 9.529763692768802e-06, "epoch": 4.505119453924914, "percentage": 22.53, "elapsed_time": "0:26:41", "remaining_time": "1:31:49", "throughput": 5525.75, "total_tokens": 8851344} {"current_steps": 14525, "total_steps": 64460, "loss": 0.2251, "lr": 9.529190353090256e-06, "epoch": 4.506670803599131, "percentage": 22.53, "elapsed_time": "0:26:42", "remaining_time": "1:31:48", "throughput": 5525.75, "total_tokens": 8854096} {"current_steps": 14530, "total_steps": 64460, "loss": 0.2231, "lr": 9.528616681368422e-06, "epoch": 4.508222153273348, "percentage": 22.54, "elapsed_time": "0:26:42", "remaining_time": "1:31:47", "throughput": 5525.72, "total_tokens": 8856784} {"current_steps": 14535, "total_steps": 64460, "loss": 0.2202, "lr": 9.52804267764536e-06, "epoch": 4.5097735029475645, "percentage": 22.55, "elapsed_time": "0:26:43", "remaining_time": "1:31:47", "throughput": 5525.81, "total_tokens": 8859760} {"current_steps": 14540, "total_steps": 64460, "loss": 0.2384, "lr": 9.527468341963148e-06, "epoch": 4.511324852621781, "percentage": 22.56, "elapsed_time": "0:26:43", "remaining_time": "1:31:46", "throughput": 5526.11, "total_tokens": 8863824} {"current_steps": 14545, "total_steps": 64460, "loss": 0.2285, "lr": 9.526893674363893e-06, "epoch": 4.512876202295997, "percentage": 22.56, "elapsed_time": "0:26:44", "remaining_time": "1:31:46", "throughput": 5526.23, "total_tokens": 8867184} {"current_steps": 14550, "total_steps": 64460, "loss": 0.2242, "lr": 9.526318674889728e-06, "epoch": 4.514427551970214, "percentage": 22.57, "elapsed_time": "0:26:45", "remaining_time": "1:31:46", "throughput": 5526.34, "total_tokens": 8870608} {"current_steps": 14555, "total_steps": 64460, "loss": 0.2291, "lr": 9.525743343582801e-06, "epoch": 4.515978901644431, "percentage": 22.58, "elapsed_time": "0:26:45", "remaining_time": "1:31:45", "throughput": 5526.26, "total_tokens": 8873232} {"current_steps": 14560, "total_steps": 64460, "loss": 0.2356, "lr": 9.525167680485297e-06, "epoch": 4.5175302513186475, "percentage": 22.59, "elapsed_time": "0:26:46", "remaining_time": "1:31:44", "throughput": 5526.55, "total_tokens": 8876816} {"current_steps": 14565, "total_steps": 64460, "loss": 0.245, "lr": 9.524591685639414e-06, "epoch": 4.519081600992864, "percentage": 22.6, "elapsed_time": "0:26:46", "remaining_time": "1:31:44", "throughput": 5526.41, "total_tokens": 8879408} {"current_steps": 14570, "total_steps": 64460, "loss": 0.235, "lr": 9.524015359087382e-06, "epoch": 4.52063295066708, "percentage": 22.6, "elapsed_time": "0:26:47", "remaining_time": "1:31:43", "throughput": 5526.44, "total_tokens": 8882352} {"current_steps": 14575, "total_steps": 64460, "loss": 0.2406, "lr": 9.523438700871452e-06, "epoch": 4.522184300341297, "percentage": 22.61, "elapsed_time": "0:26:47", "remaining_time": "1:31:42", "throughput": 5526.58, "total_tokens": 8885296} {"current_steps": 14580, "total_steps": 64460, "loss": 0.2286, "lr": 9.5228617110339e-06, "epoch": 4.523735650015514, "percentage": 22.62, "elapsed_time": "0:26:48", "remaining_time": "1:31:42", "throughput": 5526.49, "total_tokens": 8888304} {"current_steps": 14585, "total_steps": 64460, "loss": 0.2338, "lr": 9.522284389617024e-06, "epoch": 4.52528699968973, "percentage": 22.63, "elapsed_time": "0:26:49", "remaining_time": "1:31:42", "throughput": 5526.7, "total_tokens": 8893360} {"current_steps": 14590, "total_steps": 64460, "loss": 0.227, "lr": 9.521706736663154e-06, "epoch": 4.526838349363946, "percentage": 22.63, "elapsed_time": "0:26:49", "remaining_time": "1:31:42", "throughput": 5526.85, "total_tokens": 8896784} {"current_steps": 14595, "total_steps": 64460, "loss": 0.2333, "lr": 9.521128752214632e-06, "epoch": 4.528389699038163, "percentage": 22.64, "elapsed_time": "0:26:50", "remaining_time": "1:31:41", "throughput": 5526.67, "total_tokens": 8899216} {"current_steps": 14600, "total_steps": 64460, "loss": 0.2328, "lr": 9.520550436313835e-06, "epoch": 4.52994104871238, "percentage": 22.65, "elapsed_time": "0:26:50", "remaining_time": "1:31:40", "throughput": 5526.86, "total_tokens": 8902288} {"current_steps": 14605, "total_steps": 64460, "loss": 0.2278, "lr": 9.51997178900316e-06, "epoch": 4.531492398386597, "percentage": 22.66, "elapsed_time": "0:26:51", "remaining_time": "1:31:40", "throughput": 5526.9, "total_tokens": 8905232} {"current_steps": 14610, "total_steps": 64460, "loss": 0.2328, "lr": 9.519392810325028e-06, "epoch": 4.533043748060813, "percentage": 22.67, "elapsed_time": "0:26:51", "remaining_time": "1:31:39", "throughput": 5526.74, "total_tokens": 8907408} {"current_steps": 14615, "total_steps": 64460, "loss": 0.2356, "lr": 9.518813500321886e-06, "epoch": 4.534595097735029, "percentage": 22.67, "elapsed_time": "0:26:52", "remaining_time": "1:31:38", "throughput": 5526.95, "total_tokens": 8910416} {"current_steps": 14620, "total_steps": 64460, "loss": 0.2314, "lr": 9.518233859036204e-06, "epoch": 4.536146447409246, "percentage": 22.68, "elapsed_time": "0:26:52", "remaining_time": "1:31:37", "throughput": 5527.14, "total_tokens": 8913456} {"current_steps": 14625, "total_steps": 64460, "loss": 0.2304, "lr": 9.517653886510476e-06, "epoch": 4.537697797083463, "percentage": 22.69, "elapsed_time": "0:26:53", "remaining_time": "1:31:36", "throughput": 5527.27, "total_tokens": 8916432} {"current_steps": 14630, "total_steps": 64460, "loss": 0.2309, "lr": 9.517073582787221e-06, "epoch": 4.53924914675768, "percentage": 22.7, "elapsed_time": "0:26:53", "remaining_time": "1:31:36", "throughput": 5527.13, "total_tokens": 8919088} {"current_steps": 14635, "total_steps": 64460, "loss": 0.2263, "lr": 9.516492947908982e-06, "epoch": 4.5408004964318955, "percentage": 22.7, "elapsed_time": "0:26:54", "remaining_time": "1:31:35", "throughput": 5527.34, "total_tokens": 8922384} {"current_steps": 14640, "total_steps": 64460, "loss": 0.229, "lr": 9.515911981918326e-06, "epoch": 4.542351846106112, "percentage": 22.71, "elapsed_time": "0:26:54", "remaining_time": "1:31:34", "throughput": 5527.36, "total_tokens": 8924912} {"current_steps": 14645, "total_steps": 64460, "loss": 0.2267, "lr": 9.515330684857846e-06, "epoch": 4.543903195780329, "percentage": 22.72, "elapsed_time": "0:26:55", "remaining_time": "1:31:34", "throughput": 5527.56, "total_tokens": 8928144} {"current_steps": 14650, "total_steps": 64460, "loss": 0.224, "lr": 9.514749056770159e-06, "epoch": 4.545454545454545, "percentage": 22.73, "elapsed_time": "0:26:55", "remaining_time": "1:31:33", "throughput": 5527.57, "total_tokens": 8930800} {"current_steps": 14655, "total_steps": 64460, "loss": 0.233, "lr": 9.5141670976979e-06, "epoch": 4.547005895128762, "percentage": 22.74, "elapsed_time": "0:26:56", "remaining_time": "1:31:32", "throughput": 5527.93, "total_tokens": 8934320} {"current_steps": 14660, "total_steps": 64460, "loss": 0.2335, "lr": 9.51358480768374e-06, "epoch": 4.5485572448029785, "percentage": 22.74, "elapsed_time": "0:26:56", "remaining_time": "1:31:31", "throughput": 5527.96, "total_tokens": 8936912} {"current_steps": 14665, "total_steps": 64460, "loss": 0.229, "lr": 9.513002186770364e-06, "epoch": 4.550108594477195, "percentage": 22.75, "elapsed_time": "0:26:57", "remaining_time": "1:31:31", "throughput": 5528.0, "total_tokens": 8939600} {"current_steps": 14670, "total_steps": 64460, "loss": 0.2331, "lr": 9.512419235000485e-06, "epoch": 4.551659944151412, "percentage": 22.76, "elapsed_time": "0:26:57", "remaining_time": "1:31:30", "throughput": 5527.81, "total_tokens": 8941872} {"current_steps": 14675, "total_steps": 64460, "loss": 0.2384, "lr": 9.511835952416841e-06, "epoch": 4.553211293825628, "percentage": 22.77, "elapsed_time": "0:26:58", "remaining_time": "1:31:29", "throughput": 5527.98, "total_tokens": 8944976} {"current_steps": 14680, "total_steps": 64460, "loss": 0.2292, "lr": 9.511252339062193e-06, "epoch": 4.554762643499845, "percentage": 22.77, "elapsed_time": "0:26:58", "remaining_time": "1:31:28", "throughput": 5527.74, "total_tokens": 8947056} {"current_steps": 14685, "total_steps": 64460, "loss": 0.2351, "lr": 9.510668394979328e-06, "epoch": 4.5563139931740615, "percentage": 22.78, "elapsed_time": "0:26:59", "remaining_time": "1:31:27", "throughput": 5527.73, "total_tokens": 8949616} {"current_steps": 14690, "total_steps": 64460, "loss": 0.2277, "lr": 9.510084120211057e-06, "epoch": 4.557865342848278, "percentage": 22.79, "elapsed_time": "0:26:59", "remaining_time": "1:31:27", "throughput": 5528.18, "total_tokens": 8953808} {"current_steps": 14695, "total_steps": 64460, "loss": 0.2271, "lr": 9.509499514800211e-06, "epoch": 4.559416692522495, "percentage": 22.8, "elapsed_time": "0:27:00", "remaining_time": "1:31:26", "throughput": 5528.39, "total_tokens": 8957136} {"current_steps": 14700, "total_steps": 64460, "loss": 0.2319, "lr": 9.50891457878965e-06, "epoch": 4.560968042196711, "percentage": 22.8, "elapsed_time": "0:27:00", "remaining_time": "1:31:26", "throughput": 5528.51, "total_tokens": 8960080} {"current_steps": 14705, "total_steps": 64460, "loss": 0.2365, "lr": 9.508329312222258e-06, "epoch": 4.562519391870928, "percentage": 22.81, "elapsed_time": "0:27:01", "remaining_time": "1:31:25", "throughput": 5528.58, "total_tokens": 8962800} {"current_steps": 14710, "total_steps": 64460, "loss": 0.2342, "lr": 9.507743715140939e-06, "epoch": 4.5640707415451445, "percentage": 22.82, "elapsed_time": "0:27:01", "remaining_time": "1:31:24", "throughput": 5528.34, "total_tokens": 8965072} {"current_steps": 14715, "total_steps": 64460, "loss": 0.2353, "lr": 9.507157787588627e-06, "epoch": 4.56562209121936, "percentage": 22.83, "elapsed_time": "0:27:02", "remaining_time": "1:31:23", "throughput": 5528.32, "total_tokens": 8967824} {"current_steps": 14720, "total_steps": 64460, "loss": 0.2286, "lr": 9.506571529608277e-06, "epoch": 4.567173440893577, "percentage": 22.84, "elapsed_time": "0:27:02", "remaining_time": "1:31:23", "throughput": 5528.36, "total_tokens": 8970928} {"current_steps": 14725, "total_steps": 64460, "loss": 0.2304, "lr": 9.505984941242867e-06, "epoch": 4.568724790567794, "percentage": 22.84, "elapsed_time": "0:27:03", "remaining_time": "1:31:22", "throughput": 5528.12, "total_tokens": 8973008} {"current_steps": 14730, "total_steps": 64460, "loss": 0.2278, "lr": 9.505398022535403e-06, "epoch": 4.570276140242011, "percentage": 22.85, "elapsed_time": "0:27:03", "remaining_time": "1:31:21", "throughput": 5528.31, "total_tokens": 8975952} {"current_steps": 14735, "total_steps": 64460, "loss": 0.2377, "lr": 9.50481077352891e-06, "epoch": 4.5718274899162274, "percentage": 22.86, "elapsed_time": "0:27:04", "remaining_time": "1:31:20", "throughput": 5528.51, "total_tokens": 8979216} {"current_steps": 14740, "total_steps": 64460, "loss": 0.2269, "lr": 9.504223194266445e-06, "epoch": 4.573378839590443, "percentage": 22.87, "elapsed_time": "0:27:04", "remaining_time": "1:31:20", "throughput": 5528.79, "total_tokens": 8982384} {"current_steps": 14745, "total_steps": 64460, "loss": 0.2304, "lr": 9.50363528479108e-06, "epoch": 4.57493018926466, "percentage": 22.87, "elapsed_time": "0:27:05", "remaining_time": "1:31:19", "throughput": 5528.86, "total_tokens": 8985232} {"current_steps": 14750, "total_steps": 64460, "loss": 0.2319, "lr": 9.503047045145918e-06, "epoch": 4.576481538938877, "percentage": 22.88, "elapsed_time": "0:27:05", "remaining_time": "1:31:18", "throughput": 5529.06, "total_tokens": 8988624} {"current_steps": 14755, "total_steps": 64460, "loss": 0.2358, "lr": 9.502458475374085e-06, "epoch": 4.578032888613094, "percentage": 22.89, "elapsed_time": "0:27:06", "remaining_time": "1:31:18", "throughput": 5529.27, "total_tokens": 8991920} {"current_steps": 14760, "total_steps": 64460, "loss": 0.2315, "lr": 9.501869575518728e-06, "epoch": 4.57958423828731, "percentage": 22.9, "elapsed_time": "0:27:06", "remaining_time": "1:31:17", "throughput": 5529.02, "total_tokens": 8993968} {"current_steps": 14765, "total_steps": 64460, "loss": 0.2343, "lr": 9.501280345623019e-06, "epoch": 4.581135587961526, "percentage": 22.91, "elapsed_time": "0:27:07", "remaining_time": "1:31:16", "throughput": 5529.15, "total_tokens": 8997168} {"current_steps": 14770, "total_steps": 64460, "loss": 0.2296, "lr": 9.50069078573016e-06, "epoch": 4.582686937635743, "percentage": 22.91, "elapsed_time": "0:27:07", "remaining_time": "1:31:16", "throughput": 5529.07, "total_tokens": 8999856} {"current_steps": 14775, "total_steps": 64460, "loss": 0.2297, "lr": 9.50010089588337e-06, "epoch": 4.58423828730996, "percentage": 22.92, "elapsed_time": "0:27:08", "remaining_time": "1:31:15", "throughput": 5529.51, "total_tokens": 9003760} {"current_steps": 14780, "total_steps": 64460, "loss": 0.2289, "lr": 9.499510676125893e-06, "epoch": 4.585789636984176, "percentage": 22.93, "elapsed_time": "0:27:08", "remaining_time": "1:31:15", "throughput": 5529.85, "total_tokens": 9007248} {"current_steps": 14785, "total_steps": 64460, "loss": 0.2274, "lr": 9.498920126501004e-06, "epoch": 4.5873409866583925, "percentage": 22.94, "elapsed_time": "0:27:09", "remaining_time": "1:31:14", "throughput": 5529.98, "total_tokens": 9010192} {"current_steps": 14790, "total_steps": 64460, "loss": 0.2336, "lr": 9.498329247051994e-06, "epoch": 4.588892336332609, "percentage": 22.94, "elapsed_time": "0:27:09", "remaining_time": "1:31:13", "throughput": 5530.04, "total_tokens": 9012880} {"current_steps": 14795, "total_steps": 64460, "loss": 0.2266, "lr": 9.497738037822179e-06, "epoch": 4.590443686006826, "percentage": 22.95, "elapsed_time": "0:27:10", "remaining_time": "1:31:12", "throughput": 5530.24, "total_tokens": 9015824} {"current_steps": 14800, "total_steps": 64460, "loss": 0.2355, "lr": 9.497146498854908e-06, "epoch": 4.591995035681043, "percentage": 22.96, "elapsed_time": "0:27:10", "remaining_time": "1:31:11", "throughput": 5530.47, "total_tokens": 9018992} {"current_steps": 14805, "total_steps": 64460, "loss": 0.2234, "lr": 9.496554630193543e-06, "epoch": 4.593546385355259, "percentage": 22.97, "elapsed_time": "0:27:11", "remaining_time": "1:31:11", "throughput": 5530.71, "total_tokens": 9022128} {"current_steps": 14810, "total_steps": 64460, "loss": 0.227, "lr": 9.495962431881478e-06, "epoch": 4.5950977350294755, "percentage": 22.98, "elapsed_time": "0:27:11", "remaining_time": "1:31:10", "throughput": 5530.91, "total_tokens": 9025264} {"current_steps": 14815, "total_steps": 64460, "loss": 0.2241, "lr": 9.495369903962124e-06, "epoch": 4.596649084703692, "percentage": 22.98, "elapsed_time": "0:27:12", "remaining_time": "1:31:09", "throughput": 5531.13, "total_tokens": 9028560} {"current_steps": 14820, "total_steps": 64460, "loss": 0.217, "lr": 9.494777046478925e-06, "epoch": 4.598200434377909, "percentage": 22.99, "elapsed_time": "0:27:12", "remaining_time": "1:31:09", "throughput": 5531.2, "total_tokens": 9031408} {"current_steps": 14825, "total_steps": 64460, "loss": 0.2204, "lr": 9.494183859475341e-06, "epoch": 4.599751784052126, "percentage": 23.0, "elapsed_time": "0:27:13", "remaining_time": "1:31:08", "throughput": 5531.44, "total_tokens": 9034672} {"current_steps": 14830, "total_steps": 64460, "loss": 0.2051, "lr": 9.493590342994863e-06, "epoch": 4.601303133726342, "percentage": 23.01, "elapsed_time": "0:27:13", "remaining_time": "1:31:07", "throughput": 5531.81, "total_tokens": 9038256} {"current_steps": 14835, "total_steps": 64460, "loss": 0.2123, "lr": 9.492996497081e-06, "epoch": 4.6028544834005585, "percentage": 23.01, "elapsed_time": "0:27:14", "remaining_time": "1:31:07", "throughput": 5531.39, "total_tokens": 9040432} {"current_steps": 14840, "total_steps": 64460, "loss": 0.2671, "lr": 9.492402321777288e-06, "epoch": 4.604405833074775, "percentage": 23.02, "elapsed_time": "0:27:14", "remaining_time": "1:31:06", "throughput": 5531.28, "total_tokens": 9042704} {"current_steps": 14845, "total_steps": 64460, "loss": 0.2419, "lr": 9.491807817127287e-06, "epoch": 4.605957182748991, "percentage": 23.03, "elapsed_time": "0:27:15", "remaining_time": "1:31:05", "throughput": 5531.42, "total_tokens": 9045840} {"current_steps": 14850, "total_steps": 64460, "loss": 0.2335, "lr": 9.491212983174582e-06, "epoch": 4.607508532423208, "percentage": 23.04, "elapsed_time": "0:27:15", "remaining_time": "1:31:04", "throughput": 5531.5, "total_tokens": 9048528} {"current_steps": 14855, "total_steps": 64460, "loss": 0.2289, "lr": 9.490617819962784e-06, "epoch": 4.609059882097425, "percentage": 23.05, "elapsed_time": "0:27:16", "remaining_time": "1:31:04", "throughput": 5531.7, "total_tokens": 9051600} {"current_steps": 14860, "total_steps": 64460, "loss": 0.2396, "lr": 9.49002232753552e-06, "epoch": 4.6106112317716414, "percentage": 23.05, "elapsed_time": "0:27:16", "remaining_time": "1:31:03", "throughput": 5532.05, "total_tokens": 9055184} {"current_steps": 14865, "total_steps": 64460, "loss": 0.2145, "lr": 9.489426505936453e-06, "epoch": 4.612162581445858, "percentage": 23.06, "elapsed_time": "0:27:17", "remaining_time": "1:31:02", "throughput": 5532.11, "total_tokens": 9057840} {"current_steps": 14870, "total_steps": 64460, "loss": 0.234, "lr": 9.488830355209257e-06, "epoch": 4.613713931120074, "percentage": 23.07, "elapsed_time": "0:27:17", "remaining_time": "1:31:01", "throughput": 5532.17, "total_tokens": 9060752} {"current_steps": 14875, "total_steps": 64460, "loss": 0.2339, "lr": 9.488233875397642e-06, "epoch": 4.615265280794291, "percentage": 23.08, "elapsed_time": "0:27:18", "remaining_time": "1:31:01", "throughput": 5532.29, "total_tokens": 9063536} {"current_steps": 14880, "total_steps": 64460, "loss": 0.2342, "lr": 9.487637066545334e-06, "epoch": 4.616816630468508, "percentage": 23.08, "elapsed_time": "0:27:18", "remaining_time": "1:31:00", "throughput": 5532.47, "total_tokens": 9066576} {"current_steps": 14885, "total_steps": 64460, "loss": 0.2307, "lr": 9.487039928696089e-06, "epoch": 4.618367980142724, "percentage": 23.09, "elapsed_time": "0:27:19", "remaining_time": "1:30:59", "throughput": 5532.55, "total_tokens": 9069456} {"current_steps": 14890, "total_steps": 64460, "loss": 0.2296, "lr": 9.486442461893683e-06, "epoch": 4.619919329816941, "percentage": 23.1, "elapsed_time": "0:27:19", "remaining_time": "1:30:59", "throughput": 5532.88, "total_tokens": 9072880} {"current_steps": 14895, "total_steps": 64460, "loss": 0.2282, "lr": 9.485844666181916e-06, "epoch": 4.621470679491157, "percentage": 23.11, "elapsed_time": "0:27:20", "remaining_time": "1:30:58", "throughput": 5532.82, "total_tokens": 9075312} {"current_steps": 14900, "total_steps": 64460, "loss": 0.2238, "lr": 9.485246541604614e-06, "epoch": 4.623022029165374, "percentage": 23.12, "elapsed_time": "0:27:20", "remaining_time": "1:30:57", "throughput": 5533.1, "total_tokens": 9078608} {"current_steps": 14905, "total_steps": 64460, "loss": 0.236, "lr": 9.484648088205627e-06, "epoch": 4.624573378839591, "percentage": 23.12, "elapsed_time": "0:27:21", "remaining_time": "1:30:56", "throughput": 5533.34, "total_tokens": 9081712} {"current_steps": 14910, "total_steps": 64460, "loss": 0.2261, "lr": 9.484049306028831e-06, "epoch": 4.6261247285138065, "percentage": 23.13, "elapsed_time": "0:27:21", "remaining_time": "1:30:55", "throughput": 5533.44, "total_tokens": 9084528} {"current_steps": 14915, "total_steps": 64460, "loss": 0.2335, "lr": 9.483450195118122e-06, "epoch": 4.627676078188023, "percentage": 23.14, "elapsed_time": "0:27:22", "remaining_time": "1:30:55", "throughput": 5533.57, "total_tokens": 9087376} {"current_steps": 14920, "total_steps": 64460, "loss": 0.2241, "lr": 9.482850755517419e-06, "epoch": 4.62922742786224, "percentage": 23.15, "elapsed_time": "0:27:22", "remaining_time": "1:30:54", "throughput": 5533.59, "total_tokens": 9089904} {"current_steps": 14925, "total_steps": 64460, "loss": 0.2369, "lr": 9.482250987270672e-06, "epoch": 4.630778777536457, "percentage": 23.15, "elapsed_time": "0:27:23", "remaining_time": "1:30:53", "throughput": 5533.41, "total_tokens": 9092240} {"current_steps": 14930, "total_steps": 64460, "loss": 0.2418, "lr": 9.48165089042185e-06, "epoch": 4.632330127210674, "percentage": 23.16, "elapsed_time": "0:27:23", "remaining_time": "1:30:52", "throughput": 5533.52, "total_tokens": 9095408} {"current_steps": 14935, "total_steps": 64460, "loss": 0.2333, "lr": 9.481050465014947e-06, "epoch": 4.6338814768848895, "percentage": 23.17, "elapsed_time": "0:27:24", "remaining_time": "1:30:52", "throughput": 5533.82, "total_tokens": 9098832} {"current_steps": 14940, "total_steps": 64460, "loss": 0.2227, "lr": 9.480449711093982e-06, "epoch": 4.635432826559106, "percentage": 23.18, "elapsed_time": "0:27:24", "remaining_time": "1:30:51", "throughput": 5533.79, "total_tokens": 9101488} {"current_steps": 14945, "total_steps": 64460, "loss": 0.233, "lr": 9.479848628702997e-06, "epoch": 4.636984176233323, "percentage": 23.18, "elapsed_time": "0:27:25", "remaining_time": "1:30:50", "throughput": 5533.9, "total_tokens": 9104560} {"current_steps": 14950, "total_steps": 64460, "loss": 0.2381, "lr": 9.479247217886057e-06, "epoch": 4.63853552590754, "percentage": 23.19, "elapsed_time": "0:27:25", "remaining_time": "1:30:50", "throughput": 5534.48, "total_tokens": 9109168} {"current_steps": 14955, "total_steps": 64460, "loss": 0.2342, "lr": 9.478645478687254e-06, "epoch": 4.640086875581757, "percentage": 23.2, "elapsed_time": "0:27:26", "remaining_time": "1:30:50", "throughput": 5534.74, "total_tokens": 9112528} {"current_steps": 14960, "total_steps": 64460, "loss": 0.2298, "lr": 9.478043411150701e-06, "epoch": 4.6416382252559725, "percentage": 23.21, "elapsed_time": "0:27:26", "remaining_time": "1:30:49", "throughput": 5534.86, "total_tokens": 9115760} {"current_steps": 14965, "total_steps": 64460, "loss": 0.2283, "lr": 9.477441015320541e-06, "epoch": 4.643189574930189, "percentage": 23.22, "elapsed_time": "0:27:27", "remaining_time": "1:30:48", "throughput": 5534.96, "total_tokens": 9118864} {"current_steps": 14970, "total_steps": 64460, "loss": 0.232, "lr": 9.476838291240931e-06, "epoch": 4.644740924604406, "percentage": 23.22, "elapsed_time": "0:27:27", "remaining_time": "1:30:48", "throughput": 5535.04, "total_tokens": 9121680} {"current_steps": 14975, "total_steps": 64460, "loss": 0.2337, "lr": 9.476235238956061e-06, "epoch": 4.646292274278622, "percentage": 23.23, "elapsed_time": "0:27:28", "remaining_time": "1:30:47", "throughput": 5535.3, "total_tokens": 9125392} {"current_steps": 14980, "total_steps": 64460, "loss": 0.2284, "lr": 9.475631858510143e-06, "epoch": 4.647843623952839, "percentage": 23.24, "elapsed_time": "0:27:29", "remaining_time": "1:30:47", "throughput": 5535.71, "total_tokens": 9129680} {"current_steps": 14985, "total_steps": 64460, "loss": 0.2288, "lr": 9.47502814994741e-06, "epoch": 4.6493949736270554, "percentage": 23.25, "elapsed_time": "0:27:29", "remaining_time": "1:30:46", "throughput": 5535.47, "total_tokens": 9131984} {"current_steps": 14990, "total_steps": 64460, "loss": 0.2317, "lr": 9.47442411331212e-06, "epoch": 4.650946323301272, "percentage": 23.25, "elapsed_time": "0:27:30", "remaining_time": "1:30:46", "throughput": 5535.41, "total_tokens": 9135056} {"current_steps": 14995, "total_steps": 64460, "loss": 0.2288, "lr": 9.473819748648559e-06, "epoch": 4.652497672975489, "percentage": 23.26, "elapsed_time": "0:27:30", "remaining_time": "1:30:45", "throughput": 5535.64, "total_tokens": 9138320} {"current_steps": 15000, "total_steps": 64460, "loss": 0.2373, "lr": 9.47321505600103e-06, "epoch": 4.654049022649705, "percentage": 23.27, "elapsed_time": "0:27:31", "remaining_time": "1:30:45", "throughput": 5535.99, "total_tokens": 9142096} {"current_steps": 15005, "total_steps": 64460, "loss": 0.2226, "lr": 9.47261003541387e-06, "epoch": 4.655600372323922, "percentage": 23.28, "elapsed_time": "0:27:31", "remaining_time": "1:30:44", "throughput": 5535.63, "total_tokens": 9144304} {"current_steps": 15010, "total_steps": 64460, "loss": 0.2321, "lr": 9.472004686931429e-06, "epoch": 4.657151721998138, "percentage": 23.29, "elapsed_time": "0:27:32", "remaining_time": "1:30:43", "throughput": 5535.81, "total_tokens": 9147536} {"current_steps": 15015, "total_steps": 64460, "loss": 0.2214, "lr": 9.471399010598088e-06, "epoch": 4.658703071672355, "percentage": 23.29, "elapsed_time": "0:27:33", "remaining_time": "1:30:43", "throughput": 5536.21, "total_tokens": 9151600} {"current_steps": 15020, "total_steps": 64460, "loss": 0.2307, "lr": 9.47079300645825e-06, "epoch": 4.660254421346572, "percentage": 23.3, "elapsed_time": "0:27:33", "remaining_time": "1:30:42", "throughput": 5536.4, "total_tokens": 9154640} {"current_steps": 15025, "total_steps": 64460, "loss": 0.2291, "lr": 9.470186674556342e-06, "epoch": 4.661805771020788, "percentage": 23.31, "elapsed_time": "0:27:34", "remaining_time": "1:30:42", "throughput": 5536.7, "total_tokens": 9157968} {"current_steps": 15030, "total_steps": 64460, "loss": 0.2377, "lr": 9.469580014936816e-06, "epoch": 4.663357120695005, "percentage": 23.32, "elapsed_time": "0:27:34", "remaining_time": "1:30:41", "throughput": 5536.85, "total_tokens": 9161232} {"current_steps": 15035, "total_steps": 64460, "loss": 0.2268, "lr": 9.468973027644148e-06, "epoch": 4.664908470369221, "percentage": 23.32, "elapsed_time": "0:27:35", "remaining_time": "1:30:40", "throughput": 5536.86, "total_tokens": 9163920} {"current_steps": 15040, "total_steps": 64460, "loss": 0.2166, "lr": 9.468365712722838e-06, "epoch": 4.666459820043438, "percentage": 23.33, "elapsed_time": "0:27:35", "remaining_time": "1:30:39", "throughput": 5536.61, "total_tokens": 9166128} {"current_steps": 15045, "total_steps": 64460, "loss": 0.225, "lr": 9.467758070217406e-06, "epoch": 4.668011169717654, "percentage": 23.34, "elapsed_time": "0:27:36", "remaining_time": "1:30:39", "throughput": 5536.58, "total_tokens": 9169456} {"current_steps": 15050, "total_steps": 64460, "loss": 0.2285, "lr": 9.4671501001724e-06, "epoch": 4.669562519391871, "percentage": 23.35, "elapsed_time": "0:27:36", "remaining_time": "1:30:39", "throughput": 5536.44, "total_tokens": 9172176} {"current_steps": 15055, "total_steps": 64460, "loss": 0.2214, "lr": 9.466541802632394e-06, "epoch": 4.671113869066088, "percentage": 23.36, "elapsed_time": "0:27:37", "remaining_time": "1:30:38", "throughput": 5536.0, "total_tokens": 9174320} {"current_steps": 15060, "total_steps": 64460, "loss": 0.2578, "lr": 9.465933177641981e-06, "epoch": 4.672665218740304, "percentage": 23.36, "elapsed_time": "0:27:37", "remaining_time": "1:30:37", "throughput": 5535.8, "total_tokens": 9176560} {"current_steps": 15065, "total_steps": 64460, "loss": 0.2261, "lr": 9.465324225245784e-06, "epoch": 4.67421656841452, "percentage": 23.37, "elapsed_time": "0:27:38", "remaining_time": "1:30:36", "throughput": 5535.59, "total_tokens": 9178992} {"current_steps": 15070, "total_steps": 64460, "loss": 0.2483, "lr": 9.464714945488443e-06, "epoch": 4.675767918088737, "percentage": 23.38, "elapsed_time": "0:27:38", "remaining_time": "1:30:36", "throughput": 5535.75, "total_tokens": 9182224} {"current_steps": 15075, "total_steps": 64460, "loss": 0.2392, "lr": 9.464105338414626e-06, "epoch": 4.677319267762954, "percentage": 23.39, "elapsed_time": "0:27:39", "remaining_time": "1:30:35", "throughput": 5535.64, "total_tokens": 9184592} {"current_steps": 15080, "total_steps": 64460, "loss": 0.2343, "lr": 9.463495404069026e-06, "epoch": 4.678870617437171, "percentage": 23.39, "elapsed_time": "0:27:39", "remaining_time": "1:30:34", "throughput": 5535.42, "total_tokens": 9186832} {"current_steps": 15085, "total_steps": 64460, "loss": 0.2339, "lr": 9.462885142496354e-06, "epoch": 4.680421967111387, "percentage": 23.4, "elapsed_time": "0:27:40", "remaining_time": "1:30:33", "throughput": 5535.54, "total_tokens": 9189808} {"current_steps": 15090, "total_steps": 64460, "loss": 0.2259, "lr": 9.462274553741355e-06, "epoch": 4.681973316785603, "percentage": 23.41, "elapsed_time": "0:27:40", "remaining_time": "1:30:33", "throughput": 5535.55, "total_tokens": 9192496} {"current_steps": 15095, "total_steps": 64460, "loss": 0.2341, "lr": 9.461663637848791e-06, "epoch": 4.68352466645982, "percentage": 23.42, "elapsed_time": "0:27:41", "remaining_time": "1:30:32", "throughput": 5535.44, "total_tokens": 9195152} {"current_steps": 15100, "total_steps": 64460, "loss": 0.232, "lr": 9.461052394863447e-06, "epoch": 4.685076016134037, "percentage": 23.43, "elapsed_time": "0:27:41", "remaining_time": "1:30:31", "throughput": 5535.53, "total_tokens": 9198032} {"current_steps": 15105, "total_steps": 64460, "loss": 0.2347, "lr": 9.460440824830135e-06, "epoch": 4.686627365808254, "percentage": 23.43, "elapsed_time": "0:27:42", "remaining_time": "1:30:31", "throughput": 5535.37, "total_tokens": 9200624} {"current_steps": 15110, "total_steps": 64460, "loss": 0.23, "lr": 9.45982892779369e-06, "epoch": 4.6881787154824694, "percentage": 23.44, "elapsed_time": "0:27:42", "remaining_time": "1:30:30", "throughput": 5535.42, "total_tokens": 9203568} {"current_steps": 15115, "total_steps": 64460, "loss": 0.2307, "lr": 9.459216703798974e-06, "epoch": 4.689730065156686, "percentage": 23.45, "elapsed_time": "0:27:43", "remaining_time": "1:30:29", "throughput": 5535.53, "total_tokens": 9206576} {"current_steps": 15120, "total_steps": 64460, "loss": 0.2253, "lr": 9.458604152890869e-06, "epoch": 4.691281414830903, "percentage": 23.46, "elapsed_time": "0:27:43", "remaining_time": "1:30:29", "throughput": 5535.69, "total_tokens": 9209904} {"current_steps": 15125, "total_steps": 64460, "loss": 0.2208, "lr": 9.457991275114282e-06, "epoch": 4.69283276450512, "percentage": 23.46, "elapsed_time": "0:27:44", "remaining_time": "1:30:28", "throughput": 5535.83, "total_tokens": 9213328} {"current_steps": 15130, "total_steps": 64460, "loss": 0.2433, "lr": 9.457378070514143e-06, "epoch": 4.694384114179336, "percentage": 23.47, "elapsed_time": "0:27:44", "remaining_time": "1:30:27", "throughput": 5535.85, "total_tokens": 9216176} {"current_steps": 15135, "total_steps": 64460, "loss": 0.2338, "lr": 9.456764539135408e-06, "epoch": 4.695935463853552, "percentage": 23.48, "elapsed_time": "0:27:45", "remaining_time": "1:30:27", "throughput": 5535.82, "total_tokens": 9218928} {"current_steps": 15140, "total_steps": 64460, "loss": 0.2361, "lr": 9.456150681023057e-06, "epoch": 4.697486813527769, "percentage": 23.49, "elapsed_time": "0:27:45", "remaining_time": "1:30:26", "throughput": 5535.78, "total_tokens": 9221680} {"current_steps": 15145, "total_steps": 64460, "loss": 0.2371, "lr": 9.455536496222093e-06, "epoch": 4.699038163201986, "percentage": 23.5, "elapsed_time": "0:27:46", "remaining_time": "1:30:25", "throughput": 5536.08, "total_tokens": 9225104} {"current_steps": 15150, "total_steps": 64460, "loss": 0.2396, "lr": 9.45492198477754e-06, "epoch": 4.700589512876203, "percentage": 23.5, "elapsed_time": "0:27:46", "remaining_time": "1:30:25", "throughput": 5536.5, "total_tokens": 9228912} {"current_steps": 15155, "total_steps": 64460, "loss": 0.2297, "lr": 9.454307146734454e-06, "epoch": 4.702140862550419, "percentage": 23.51, "elapsed_time": "0:27:47", "remaining_time": "1:30:25", "throughput": 5536.7, "total_tokens": 9232720} {"current_steps": 15160, "total_steps": 64460, "loss": 0.2384, "lr": 9.453691982137905e-06, "epoch": 4.703692212224635, "percentage": 23.52, "elapsed_time": "0:27:48", "remaining_time": "1:30:24", "throughput": 5536.65, "total_tokens": 9235504} {"current_steps": 15165, "total_steps": 64460, "loss": 0.2379, "lr": 9.453076491032996e-06, "epoch": 4.705243561898852, "percentage": 23.53, "elapsed_time": "0:27:48", "remaining_time": "1:30:23", "throughput": 5536.29, "total_tokens": 9237872} {"current_steps": 15170, "total_steps": 64460, "loss": 0.2294, "lr": 9.452460673464848e-06, "epoch": 4.706794911573069, "percentage": 23.53, "elapsed_time": "0:27:49", "remaining_time": "1:30:23", "throughput": 5536.35, "total_tokens": 9240784} {"current_steps": 15175, "total_steps": 64460, "loss": 0.2264, "lr": 9.451844529478607e-06, "epoch": 4.708346261247285, "percentage": 23.54, "elapsed_time": "0:27:49", "remaining_time": "1:30:22", "throughput": 5536.36, "total_tokens": 9243760} {"current_steps": 15180, "total_steps": 64460, "loss": 0.2275, "lr": 9.451228059119444e-06, "epoch": 4.709897610921502, "percentage": 23.55, "elapsed_time": "0:27:50", "remaining_time": "1:30:21", "throughput": 5536.45, "total_tokens": 9246800} {"current_steps": 15185, "total_steps": 64460, "loss": 0.2342, "lr": 9.450611262432553e-06, "epoch": 4.711448960595718, "percentage": 23.56, "elapsed_time": "0:27:50", "remaining_time": "1:30:21", "throughput": 5536.73, "total_tokens": 9250640} {"current_steps": 15190, "total_steps": 64460, "loss": 0.2376, "lr": 9.449994139463154e-06, "epoch": 4.713000310269935, "percentage": 23.57, "elapsed_time": "0:27:51", "remaining_time": "1:30:20", "throughput": 5536.62, "total_tokens": 9253296} {"current_steps": 15195, "total_steps": 64460, "loss": 0.2316, "lr": 9.449376690256489e-06, "epoch": 4.714551659944151, "percentage": 23.57, "elapsed_time": "0:27:51", "remaining_time": "1:30:20", "throughput": 5536.84, "total_tokens": 9256592} {"current_steps": 15200, "total_steps": 64460, "loss": 0.2336, "lr": 9.448758914857825e-06, "epoch": 4.716103009618368, "percentage": 23.58, "elapsed_time": "0:27:52", "remaining_time": "1:30:19", "throughput": 5536.67, "total_tokens": 9258864} {"current_steps": 15205, "total_steps": 64460, "loss": 0.229, "lr": 9.44814081331245e-06, "epoch": 4.717654359292585, "percentage": 23.59, "elapsed_time": "0:27:52", "remaining_time": "1:30:18", "throughput": 5536.61, "total_tokens": 9261520} {"current_steps": 15210, "total_steps": 64460, "loss": 0.2296, "lr": 9.447522385665679e-06, "epoch": 4.719205708966801, "percentage": 23.6, "elapsed_time": "0:27:53", "remaining_time": "1:30:18", "throughput": 5536.23, "total_tokens": 9263760} {"current_steps": 15215, "total_steps": 64460, "loss": 0.2325, "lr": 9.446903631962853e-06, "epoch": 4.720757058641018, "percentage": 23.6, "elapsed_time": "0:27:53", "remaining_time": "1:30:17", "throughput": 5536.14, "total_tokens": 9266512} {"current_steps": 15220, "total_steps": 64460, "loss": 0.2353, "lr": 9.44628455224933e-06, "epoch": 4.722308408315234, "percentage": 23.61, "elapsed_time": "0:27:54", "remaining_time": "1:30:16", "throughput": 5535.95, "total_tokens": 9268848} {"current_steps": 15225, "total_steps": 64460, "loss": 0.237, "lr": 9.445665146570497e-06, "epoch": 4.723859757989451, "percentage": 23.62, "elapsed_time": "0:27:54", "remaining_time": "1:30:16", "throughput": 5536.15, "total_tokens": 9271984} {"current_steps": 15230, "total_steps": 64460, "loss": 0.2308, "lr": 9.445045414971764e-06, "epoch": 4.725411107663668, "percentage": 23.63, "elapsed_time": "0:27:55", "remaining_time": "1:30:15", "throughput": 5536.17, "total_tokens": 9274736} {"current_steps": 15235, "total_steps": 64460, "loss": 0.2269, "lr": 9.444425357498565e-06, "epoch": 4.726962457337884, "percentage": 23.63, "elapsed_time": "0:27:55", "remaining_time": "1:30:14", "throughput": 5536.34, "total_tokens": 9277776} {"current_steps": 15240, "total_steps": 64460, "loss": 0.2339, "lr": 9.44380497419636e-06, "epoch": 4.7285138070121, "percentage": 23.64, "elapsed_time": "0:27:56", "remaining_time": "1:30:14", "throughput": 5536.57, "total_tokens": 9281360} {"current_steps": 15245, "total_steps": 64460, "loss": 0.2354, "lr": 9.443184265110626e-06, "epoch": 4.730065156686317, "percentage": 23.65, "elapsed_time": "0:27:56", "remaining_time": "1:30:13", "throughput": 5536.69, "total_tokens": 9284496} {"current_steps": 15250, "total_steps": 64460, "loss": 0.2433, "lr": 9.44256323028687e-06, "epoch": 4.731616506360534, "percentage": 23.66, "elapsed_time": "0:27:57", "remaining_time": "1:30:13", "throughput": 5536.74, "total_tokens": 9287856} {"current_steps": 15255, "total_steps": 64460, "loss": 0.2351, "lr": 9.44194186977062e-06, "epoch": 4.7331678560347505, "percentage": 23.67, "elapsed_time": "0:27:58", "remaining_time": "1:30:12", "throughput": 5536.66, "total_tokens": 9290960} {"current_steps": 15260, "total_steps": 64460, "loss": 0.2332, "lr": 9.441320183607433e-06, "epoch": 4.734719205708966, "percentage": 23.67, "elapsed_time": "0:27:58", "remaining_time": "1:30:12", "throughput": 5536.32, "total_tokens": 9293520} {"current_steps": 15265, "total_steps": 64460, "loss": 0.233, "lr": 9.440698171842882e-06, "epoch": 4.736270555383183, "percentage": 23.68, "elapsed_time": "0:27:59", "remaining_time": "1:30:11", "throughput": 5536.47, "total_tokens": 9296560} {"current_steps": 15270, "total_steps": 64460, "loss": 0.2294, "lr": 9.44007583452257e-06, "epoch": 4.7378219050574, "percentage": 23.69, "elapsed_time": "0:27:59", "remaining_time": "1:30:10", "throughput": 5536.5, "total_tokens": 9299376} {"current_steps": 15275, "total_steps": 64460, "loss": 0.2326, "lr": 9.439453171692121e-06, "epoch": 4.739373254731617, "percentage": 23.7, "elapsed_time": "0:28:00", "remaining_time": "1:30:10", "throughput": 5536.56, "total_tokens": 9302448} {"current_steps": 15280, "total_steps": 64460, "loss": 0.2315, "lr": 9.438830183397182e-06, "epoch": 4.7409246044058335, "percentage": 23.7, "elapsed_time": "0:28:00", "remaining_time": "1:30:09", "throughput": 5536.47, "total_tokens": 9304944} {"current_steps": 15285, "total_steps": 64460, "loss": 0.2298, "lr": 9.438206869683428e-06, "epoch": 4.742475954080049, "percentage": 23.71, "elapsed_time": "0:28:01", "remaining_time": "1:30:08", "throughput": 5536.69, "total_tokens": 9308048} {"current_steps": 15290, "total_steps": 64460, "loss": 0.2396, "lr": 9.437583230596556e-06, "epoch": 4.744027303754266, "percentage": 23.72, "elapsed_time": "0:28:01", "remaining_time": "1:30:07", "throughput": 5536.87, "total_tokens": 9311120} {"current_steps": 15295, "total_steps": 64460, "loss": 0.2302, "lr": 9.436959266182281e-06, "epoch": 4.745578653428483, "percentage": 23.73, "elapsed_time": "0:28:02", "remaining_time": "1:30:07", "throughput": 5536.98, "total_tokens": 9314000} {"current_steps": 15300, "total_steps": 64460, "loss": 0.2379, "lr": 9.436334976486354e-06, "epoch": 4.7471300031027, "percentage": 23.74, "elapsed_time": "0:28:02", "remaining_time": "1:30:06", "throughput": 5537.13, "total_tokens": 9317168} {"current_steps": 15305, "total_steps": 64460, "loss": 0.2305, "lr": 9.435710361554537e-06, "epoch": 4.748681352776916, "percentage": 23.74, "elapsed_time": "0:28:03", "remaining_time": "1:30:05", "throughput": 5537.14, "total_tokens": 9319760} {"current_steps": 15310, "total_steps": 64460, "loss": 0.2253, "lr": 9.435085421432623e-06, "epoch": 4.750232702451132, "percentage": 23.75, "elapsed_time": "0:28:03", "remaining_time": "1:30:05", "throughput": 5537.26, "total_tokens": 9322832} {"current_steps": 15315, "total_steps": 64460, "loss": 0.2327, "lr": 9.43446015616643e-06, "epoch": 4.751784052125349, "percentage": 23.76, "elapsed_time": "0:28:04", "remaining_time": "1:30:04", "throughput": 5537.3, "total_tokens": 9325776} {"current_steps": 15320, "total_steps": 64460, "loss": 0.2303, "lr": 9.433834565801796e-06, "epoch": 4.753335401799566, "percentage": 23.77, "elapsed_time": "0:28:04", "remaining_time": "1:30:03", "throughput": 5537.46, "total_tokens": 9329104} {"current_steps": 15325, "total_steps": 64460, "loss": 0.2331, "lr": 9.433208650384582e-06, "epoch": 4.754886751473782, "percentage": 23.77, "elapsed_time": "0:28:05", "remaining_time": "1:30:03", "throughput": 5537.39, "total_tokens": 9331664} {"current_steps": 15330, "total_steps": 64460, "loss": 0.2306, "lr": 9.432582409960678e-06, "epoch": 4.756438101147999, "percentage": 23.78, "elapsed_time": "0:28:05", "remaining_time": "1:30:02", "throughput": 5537.36, "total_tokens": 9334416} {"current_steps": 15335, "total_steps": 64460, "loss": 0.229, "lr": 9.431955844575993e-06, "epoch": 4.757989450822215, "percentage": 23.79, "elapsed_time": "0:28:06", "remaining_time": "1:30:01", "throughput": 5537.23, "total_tokens": 9336976} {"current_steps": 15340, "total_steps": 64460, "loss": 0.2357, "lr": 9.431328954276464e-06, "epoch": 4.759540800496432, "percentage": 23.8, "elapsed_time": "0:28:06", "remaining_time": "1:30:01", "throughput": 5537.47, "total_tokens": 9340624} {"current_steps": 15345, "total_steps": 64460, "loss": 0.2305, "lr": 9.430701739108047e-06, "epoch": 4.761092150170649, "percentage": 23.81, "elapsed_time": "0:28:07", "remaining_time": "1:30:00", "throughput": 5537.61, "total_tokens": 9343760} {"current_steps": 15350, "total_steps": 64460, "loss": 0.2337, "lr": 9.430074199116723e-06, "epoch": 4.762643499844865, "percentage": 23.81, "elapsed_time": "0:28:07", "remaining_time": "1:29:59", "throughput": 5537.58, "total_tokens": 9346256} {"current_steps": 15355, "total_steps": 64460, "loss": 0.2367, "lr": 9.429446334348503e-06, "epoch": 4.764194849519082, "percentage": 23.82, "elapsed_time": "0:28:08", "remaining_time": "1:29:58", "throughput": 5537.29, "total_tokens": 9348336} {"current_steps": 15360, "total_steps": 64460, "loss": 0.23, "lr": 9.428818144849413e-06, "epoch": 4.765746199193298, "percentage": 23.83, "elapsed_time": "0:28:08", "remaining_time": "1:29:58", "throughput": 5537.55, "total_tokens": 9351888} {"current_steps": 15365, "total_steps": 64460, "loss": 0.2339, "lr": 9.428189630665508e-06, "epoch": 4.767297548867515, "percentage": 23.84, "elapsed_time": "0:28:09", "remaining_time": "1:29:57", "throughput": 5537.35, "total_tokens": 9354128} {"current_steps": 15370, "total_steps": 64460, "loss": 0.2329, "lr": 9.427560791842867e-06, "epoch": 4.768848898541731, "percentage": 23.84, "elapsed_time": "0:28:09", "remaining_time": "1:29:56", "throughput": 5537.49, "total_tokens": 9357200} {"current_steps": 15375, "total_steps": 64460, "loss": 0.2344, "lr": 9.426931628427588e-06, "epoch": 4.770400248215948, "percentage": 23.85, "elapsed_time": "0:28:10", "remaining_time": "1:29:56", "throughput": 5537.55, "total_tokens": 9360176} {"current_steps": 15380, "total_steps": 64460, "loss": 0.2326, "lr": 9.426302140465798e-06, "epoch": 4.7719515978901645, "percentage": 23.86, "elapsed_time": "0:28:10", "remaining_time": "1:29:55", "throughput": 5537.72, "total_tokens": 9363216} {"current_steps": 15385, "total_steps": 64460, "loss": 0.2269, "lr": 9.425672328003646e-06, "epoch": 4.773502947564381, "percentage": 23.87, "elapsed_time": "0:28:11", "remaining_time": "1:29:54", "throughput": 5537.78, "total_tokens": 9366160} {"current_steps": 15390, "total_steps": 64460, "loss": 0.2342, "lr": 9.425042191087306e-06, "epoch": 4.775054297238597, "percentage": 23.88, "elapsed_time": "0:28:11", "remaining_time": "1:29:54", "throughput": 5538.22, "total_tokens": 9370064} {"current_steps": 15395, "total_steps": 64460, "loss": 0.2315, "lr": 9.424411729762973e-06, "epoch": 4.776605646912814, "percentage": 23.88, "elapsed_time": "0:28:12", "remaining_time": "1:29:54", "throughput": 5538.83, "total_tokens": 9375248} {"current_steps": 15400, "total_steps": 64460, "loss": 0.236, "lr": 9.423780944076866e-06, "epoch": 4.778156996587031, "percentage": 23.89, "elapsed_time": "0:28:13", "remaining_time": "1:29:53", "throughput": 5539.04, "total_tokens": 9378416} {"current_steps": 15405, "total_steps": 64460, "loss": 0.2377, "lr": 9.423149834075229e-06, "epoch": 4.7797083462612475, "percentage": 23.9, "elapsed_time": "0:28:13", "remaining_time": "1:29:53", "throughput": 5538.99, "total_tokens": 9380976} {"current_steps": 15410, "total_steps": 64460, "loss": 0.2324, "lr": 9.422518399804333e-06, "epoch": 4.781259695935464, "percentage": 23.91, "elapsed_time": "0:28:14", "remaining_time": "1:29:52", "throughput": 5539.13, "total_tokens": 9384080} {"current_steps": 15415, "total_steps": 64460, "loss": 0.2333, "lr": 9.42188664131047e-06, "epoch": 4.78281104560968, "percentage": 23.91, "elapsed_time": "0:28:14", "remaining_time": "1:29:52", "throughput": 5539.67, "total_tokens": 9388688} {"current_steps": 15420, "total_steps": 64460, "loss": 0.2322, "lr": 9.42125455863995e-06, "epoch": 4.784362395283897, "percentage": 23.92, "elapsed_time": "0:28:15", "remaining_time": "1:29:51", "throughput": 5539.83, "total_tokens": 9391920} {"current_steps": 15425, "total_steps": 64460, "loss": 0.2326, "lr": 9.420622151839115e-06, "epoch": 4.785913744958114, "percentage": 23.93, "elapsed_time": "0:28:15", "remaining_time": "1:29:50", "throughput": 5539.91, "total_tokens": 9394704} {"current_steps": 15430, "total_steps": 64460, "loss": 0.2353, "lr": 9.41998942095433e-06, "epoch": 4.7874650946323305, "percentage": 23.94, "elapsed_time": "0:28:16", "remaining_time": "1:29:50", "throughput": 5540.16, "total_tokens": 9398672} {"current_steps": 15435, "total_steps": 64460, "loss": 0.2327, "lr": 9.41935636603198e-06, "epoch": 4.789016444306546, "percentage": 23.95, "elapsed_time": "0:28:17", "remaining_time": "1:29:50", "throughput": 5540.48, "total_tokens": 9402256} {"current_steps": 15440, "total_steps": 64460, "loss": 0.2342, "lr": 9.418722987118475e-06, "epoch": 4.790567793980763, "percentage": 23.95, "elapsed_time": "0:28:17", "remaining_time": "1:29:49", "throughput": 5540.55, "total_tokens": 9405136} {"current_steps": 15445, "total_steps": 64460, "loss": 0.2289, "lr": 9.41808928426025e-06, "epoch": 4.79211914365498, "percentage": 23.96, "elapsed_time": "0:28:18", "remaining_time": "1:29:49", "throughput": 5541.18, "total_tokens": 9410736} {"current_steps": 15450, "total_steps": 64460, "loss": 0.2304, "lr": 9.417455257503762e-06, "epoch": 4.793670493329197, "percentage": 23.97, "elapsed_time": "0:28:18", "remaining_time": "1:29:48", "throughput": 5540.77, "total_tokens": 9412624} {"current_steps": 15455, "total_steps": 64460, "loss": 0.2341, "lr": 9.416820906895492e-06, "epoch": 4.795221843003413, "percentage": 23.98, "elapsed_time": "0:28:19", "remaining_time": "1:29:48", "throughput": 5540.95, "total_tokens": 9415664} {"current_steps": 15460, "total_steps": 64460, "loss": 0.231, "lr": 9.416186232481948e-06, "epoch": 4.796773192677629, "percentage": 23.98, "elapsed_time": "0:28:19", "remaining_time": "1:29:47", "throughput": 5541.19, "total_tokens": 9418960} {"current_steps": 15465, "total_steps": 64460, "loss": 0.2341, "lr": 9.415551234309658e-06, "epoch": 4.798324542351846, "percentage": 23.99, "elapsed_time": "0:28:20", "remaining_time": "1:29:47", "throughput": 5541.23, "total_tokens": 9422320} {"current_steps": 15470, "total_steps": 64460, "loss": 0.2289, "lr": 9.414915912425173e-06, "epoch": 4.799875892026063, "percentage": 24.0, "elapsed_time": "0:28:20", "remaining_time": "1:29:46", "throughput": 5541.27, "total_tokens": 9425072} {"current_steps": 15475, "total_steps": 64460, "loss": 0.232, "lr": 9.414280266875073e-06, "epoch": 4.80142724170028, "percentage": 24.01, "elapsed_time": "0:28:21", "remaining_time": "1:29:47", "throughput": 5541.99, "total_tokens": 9432464} {"current_steps": 15480, "total_steps": 64460, "loss": 0.2343, "lr": 9.413644297705955e-06, "epoch": 4.802978591374496, "percentage": 24.01, "elapsed_time": "0:28:22", "remaining_time": "1:29:46", "throughput": 5541.89, "total_tokens": 9435248} {"current_steps": 15485, "total_steps": 64460, "loss": 0.2229, "lr": 9.413008004964446e-06, "epoch": 4.804529941048712, "percentage": 24.02, "elapsed_time": "0:28:23", "remaining_time": "1:29:46", "throughput": 5541.99, "total_tokens": 9438192} {"current_steps": 15490, "total_steps": 64460, "loss": 0.2341, "lr": 9.412371388697191e-06, "epoch": 4.806081290722929, "percentage": 24.03, "elapsed_time": "0:28:23", "remaining_time": "1:29:45", "throughput": 5541.8, "total_tokens": 9440496} {"current_steps": 15495, "total_steps": 64460, "loss": 0.2295, "lr": 9.411734448950864e-06, "epoch": 4.807632640397146, "percentage": 24.04, "elapsed_time": "0:28:24", "remaining_time": "1:29:45", "throughput": 5542.19, "total_tokens": 9445008} {"current_steps": 15500, "total_steps": 64460, "loss": 0.2268, "lr": 9.411097185772158e-06, "epoch": 4.809183990071362, "percentage": 24.05, "elapsed_time": "0:28:24", "remaining_time": "1:29:44", "throughput": 5542.12, "total_tokens": 9447568} {"current_steps": 15505, "total_steps": 64460, "loss": 0.2331, "lr": 9.410459599207794e-06, "epoch": 4.8107353397455785, "percentage": 24.05, "elapsed_time": "0:28:25", "remaining_time": "1:29:43", "throughput": 5541.8, "total_tokens": 9449584} {"current_steps": 15510, "total_steps": 64460, "loss": 0.2337, "lr": 9.409821689304513e-06, "epoch": 4.812286689419795, "percentage": 24.06, "elapsed_time": "0:28:25", "remaining_time": "1:29:43", "throughput": 5542.09, "total_tokens": 9452976} {"current_steps": 15515, "total_steps": 64460, "loss": 0.2352, "lr": 9.409183456109083e-06, "epoch": 4.813838039094012, "percentage": 24.07, "elapsed_time": "0:28:26", "remaining_time": "1:29:42", "throughput": 5542.37, "total_tokens": 9456688} {"current_steps": 15520, "total_steps": 64460, "loss": 0.2305, "lr": 9.408544899668293e-06, "epoch": 4.815389388768228, "percentage": 24.08, "elapsed_time": "0:28:26", "remaining_time": "1:29:42", "throughput": 5542.5, "total_tokens": 9460048} {"current_steps": 15525, "total_steps": 64460, "loss": 0.2279, "lr": 9.407906020028956e-06, "epoch": 4.816940738442445, "percentage": 24.08, "elapsed_time": "0:28:27", "remaining_time": "1:29:41", "throughput": 5542.49, "total_tokens": 9462576} {"current_steps": 15530, "total_steps": 64460, "loss": 0.2281, "lr": 9.40726681723791e-06, "epoch": 4.8184920881166615, "percentage": 24.09, "elapsed_time": "0:28:27", "remaining_time": "1:29:40", "throughput": 5542.59, "total_tokens": 9465456} {"current_steps": 15535, "total_steps": 64460, "loss": 0.2342, "lr": 9.406627291342018e-06, "epoch": 4.820043437790878, "percentage": 24.1, "elapsed_time": "0:28:28", "remaining_time": "1:29:39", "throughput": 5542.75, "total_tokens": 9468560} {"current_steps": 15540, "total_steps": 64460, "loss": 0.2225, "lr": 9.405987442388163e-06, "epoch": 4.821594787465095, "percentage": 24.11, "elapsed_time": "0:28:28", "remaining_time": "1:29:39", "throughput": 5542.81, "total_tokens": 9471344} {"current_steps": 15545, "total_steps": 64460, "loss": 0.2379, "lr": 9.405347270423252e-06, "epoch": 4.823146137139311, "percentage": 24.12, "elapsed_time": "0:28:29", "remaining_time": "1:29:38", "throughput": 5542.58, "total_tokens": 9473968} {"current_steps": 15550, "total_steps": 64460, "loss": 0.2292, "lr": 9.404706775494221e-06, "epoch": 4.824697486813528, "percentage": 24.12, "elapsed_time": "0:28:29", "remaining_time": "1:29:37", "throughput": 5542.45, "total_tokens": 9476496} {"current_steps": 15555, "total_steps": 64460, "loss": 0.2402, "lr": 9.404065957648023e-06, "epoch": 4.8262488364877445, "percentage": 24.13, "elapsed_time": "0:28:30", "remaining_time": "1:29:37", "throughput": 5542.47, "total_tokens": 9479440} {"current_steps": 15560, "total_steps": 64460, "loss": 0.2311, "lr": 9.403424816931639e-06, "epoch": 4.827800186161961, "percentage": 24.14, "elapsed_time": "0:28:30", "remaining_time": "1:29:36", "throughput": 5542.55, "total_tokens": 9482320} {"current_steps": 15565, "total_steps": 64460, "loss": 0.2299, "lr": 9.40278335339207e-06, "epoch": 4.829351535836177, "percentage": 24.15, "elapsed_time": "0:28:31", "remaining_time": "1:29:35", "throughput": 5542.65, "total_tokens": 9485296} {"current_steps": 15570, "total_steps": 64460, "loss": 0.2363, "lr": 9.402141567076345e-06, "epoch": 4.830902885510394, "percentage": 24.15, "elapsed_time": "0:28:31", "remaining_time": "1:29:35", "throughput": 5542.77, "total_tokens": 9488496} {"current_steps": 15575, "total_steps": 64460, "loss": 0.2316, "lr": 9.401499458031515e-06, "epoch": 4.832454235184611, "percentage": 24.16, "elapsed_time": "0:28:32", "remaining_time": "1:29:34", "throughput": 5542.71, "total_tokens": 9491056} {"current_steps": 15580, "total_steps": 64460, "loss": 0.2275, "lr": 9.400857026304655e-06, "epoch": 4.8340055848588275, "percentage": 24.17, "elapsed_time": "0:28:32", "remaining_time": "1:29:33", "throughput": 5542.46, "total_tokens": 9493424} {"current_steps": 15585, "total_steps": 64460, "loss": 0.2362, "lr": 9.400214271942859e-06, "epoch": 4.835556934533043, "percentage": 24.18, "elapsed_time": "0:28:33", "remaining_time": "1:29:33", "throughput": 5542.59, "total_tokens": 9496272} {"current_steps": 15590, "total_steps": 64460, "loss": 0.2312, "lr": 9.399571194993249e-06, "epoch": 4.83710828420726, "percentage": 24.19, "elapsed_time": "0:28:33", "remaining_time": "1:29:32", "throughput": 5542.64, "total_tokens": 9498960} {"current_steps": 15595, "total_steps": 64460, "loss": 0.226, "lr": 9.398927795502972e-06, "epoch": 4.838659633881477, "percentage": 24.19, "elapsed_time": "0:28:34", "remaining_time": "1:29:31", "throughput": 5542.75, "total_tokens": 9502160} {"current_steps": 15600, "total_steps": 64460, "loss": 0.2286, "lr": 9.398284073519198e-06, "epoch": 4.840210983555694, "percentage": 24.2, "elapsed_time": "0:28:34", "remaining_time": "1:29:31", "throughput": 5543.11, "total_tokens": 9506000} {"current_steps": 15605, "total_steps": 64460, "loss": 0.2234, "lr": 9.397640029089116e-06, "epoch": 4.8417623332299105, "percentage": 24.21, "elapsed_time": "0:28:35", "remaining_time": "1:29:30", "throughput": 5543.38, "total_tokens": 9509616} {"current_steps": 15610, "total_steps": 64460, "loss": 0.2284, "lr": 9.396995662259946e-06, "epoch": 4.843313682904126, "percentage": 24.22, "elapsed_time": "0:28:36", "remaining_time": "1:29:30", "throughput": 5543.66, "total_tokens": 9512976} {"current_steps": 15615, "total_steps": 64460, "loss": 0.2203, "lr": 9.396350973078926e-06, "epoch": 4.844865032578343, "percentage": 24.22, "elapsed_time": "0:28:36", "remaining_time": "1:29:29", "throughput": 5543.82, "total_tokens": 9515888} {"current_steps": 15620, "total_steps": 64460, "loss": 0.2294, "lr": 9.395705961593317e-06, "epoch": 4.84641638225256, "percentage": 24.23, "elapsed_time": "0:28:36", "remaining_time": "1:29:28", "throughput": 5543.38, "total_tokens": 9517904} {"current_steps": 15625, "total_steps": 64460, "loss": 0.227, "lr": 9.39506062785041e-06, "epoch": 4.847967731926777, "percentage": 24.24, "elapsed_time": "0:28:37", "remaining_time": "1:29:28", "throughput": 5543.53, "total_tokens": 9521168} {"current_steps": 15630, "total_steps": 64460, "loss": 0.2262, "lr": 9.394414971897514e-06, "epoch": 4.8495190816009925, "percentage": 24.25, "elapsed_time": "0:28:38", "remaining_time": "1:29:27", "throughput": 5543.38, "total_tokens": 9523728} {"current_steps": 15635, "total_steps": 64460, "loss": 0.2146, "lr": 9.393768993781962e-06, "epoch": 4.851070431275209, "percentage": 24.26, "elapsed_time": "0:28:38", "remaining_time": "1:29:26", "throughput": 5543.39, "total_tokens": 9526576} {"current_steps": 15640, "total_steps": 64460, "loss": 0.2366, "lr": 9.393122693551113e-06, "epoch": 4.852621780949426, "percentage": 24.26, "elapsed_time": "0:28:39", "remaining_time": "1:29:26", "throughput": 5543.49, "total_tokens": 9529648} {"current_steps": 15645, "total_steps": 64460, "loss": 0.254, "lr": 9.392476071252347e-06, "epoch": 4.854173130623643, "percentage": 24.27, "elapsed_time": "0:28:39", "remaining_time": "1:29:25", "throughput": 5543.84, "total_tokens": 9533776} {"current_steps": 15650, "total_steps": 64460, "loss": 0.2265, "lr": 9.391829126933069e-06, "epoch": 4.855724480297859, "percentage": 24.28, "elapsed_time": "0:28:40", "remaining_time": "1:29:25", "throughput": 5543.98, "total_tokens": 9536784} {"current_steps": 15655, "total_steps": 64460, "loss": 0.2313, "lr": 9.391181860640712e-06, "epoch": 4.8572758299720755, "percentage": 24.29, "elapsed_time": "0:28:40", "remaining_time": "1:29:24", "throughput": 5544.28, "total_tokens": 9540304} {"current_steps": 15660, "total_steps": 64460, "loss": 0.2285, "lr": 9.390534272422724e-06, "epoch": 4.858827179646292, "percentage": 24.29, "elapsed_time": "0:28:41", "remaining_time": "1:29:23", "throughput": 5544.31, "total_tokens": 9543216} {"current_steps": 15665, "total_steps": 64460, "loss": 0.2358, "lr": 9.389886362326583e-06, "epoch": 4.860378529320509, "percentage": 24.3, "elapsed_time": "0:28:41", "remaining_time": "1:29:23", "throughput": 5544.23, "total_tokens": 9546096} {"current_steps": 15670, "total_steps": 64460, "loss": 0.232, "lr": 9.389238130399788e-06, "epoch": 4.861929878994726, "percentage": 24.31, "elapsed_time": "0:28:42", "remaining_time": "1:29:22", "throughput": 5544.31, "total_tokens": 9549200} {"current_steps": 15675, "total_steps": 64460, "loss": 0.2316, "lr": 9.38858957668986e-06, "epoch": 4.863481228668942, "percentage": 24.32, "elapsed_time": "0:28:42", "remaining_time": "1:29:22", "throughput": 5544.29, "total_tokens": 9552528} {"current_steps": 15680, "total_steps": 64460, "loss": 0.2391, "lr": 9.387940701244348e-06, "epoch": 4.8650325783431585, "percentage": 24.33, "elapsed_time": "0:28:43", "remaining_time": "1:29:22", "throughput": 5544.82, "total_tokens": 9557488} {"current_steps": 15685, "total_steps": 64460, "loss": 0.2375, "lr": 9.387291504110823e-06, "epoch": 4.866583928017375, "percentage": 24.33, "elapsed_time": "0:28:44", "remaining_time": "1:29:22", "throughput": 5544.93, "total_tokens": 9561168} {"current_steps": 15690, "total_steps": 64460, "loss": 0.2331, "lr": 9.386641985336875e-06, "epoch": 4.868135277691592, "percentage": 24.34, "elapsed_time": "0:28:44", "remaining_time": "1:29:21", "throughput": 5544.63, "total_tokens": 9563536} {"current_steps": 15695, "total_steps": 64460, "loss": 0.2315, "lr": 9.385992144970124e-06, "epoch": 4.869686627365808, "percentage": 24.35, "elapsed_time": "0:28:45", "remaining_time": "1:29:20", "throughput": 5544.46, "total_tokens": 9566064} {"current_steps": 15700, "total_steps": 64460, "loss": 0.2358, "lr": 9.385341983058212e-06, "epoch": 4.871237977040025, "percentage": 24.36, "elapsed_time": "0:28:45", "remaining_time": "1:29:20", "throughput": 5544.32, "total_tokens": 9568880} {"current_steps": 15705, "total_steps": 64460, "loss": 0.2363, "lr": 9.384691499648803e-06, "epoch": 4.8727893267142415, "percentage": 24.36, "elapsed_time": "0:28:46", "remaining_time": "1:29:19", "throughput": 5544.16, "total_tokens": 9571376} {"current_steps": 15710, "total_steps": 64460, "loss": 0.2331, "lr": 9.384040694789585e-06, "epoch": 4.874340676388458, "percentage": 24.37, "elapsed_time": "0:28:47", "remaining_time": "1:29:19", "throughput": 5544.41, "total_tokens": 9575376} {"current_steps": 15715, "total_steps": 64460, "loss": 0.2322, "lr": 9.383389568528267e-06, "epoch": 4.875892026062674, "percentage": 24.38, "elapsed_time": "0:28:47", "remaining_time": "1:29:18", "throughput": 5544.41, "total_tokens": 9578128} {"current_steps": 15720, "total_steps": 64460, "loss": 0.2255, "lr": 9.382738120912588e-06, "epoch": 4.877443375736891, "percentage": 24.39, "elapsed_time": "0:28:48", "remaining_time": "1:29:17", "throughput": 5544.48, "total_tokens": 9581008} {"current_steps": 15725, "total_steps": 64460, "loss": 0.2371, "lr": 9.382086351990306e-06, "epoch": 4.878994725411108, "percentage": 24.39, "elapsed_time": "0:28:48", "remaining_time": "1:29:17", "throughput": 5544.45, "total_tokens": 9583952} {"current_steps": 15730, "total_steps": 64460, "loss": 0.2318, "lr": 9.3814342618092e-06, "epoch": 4.8805460750853245, "percentage": 24.4, "elapsed_time": "0:28:49", "remaining_time": "1:29:16", "throughput": 5544.34, "total_tokens": 9586352} {"current_steps": 15735, "total_steps": 64460, "loss": 0.2315, "lr": 9.38078185041708e-06, "epoch": 4.882097424759541, "percentage": 24.41, "elapsed_time": "0:28:49", "remaining_time": "1:29:15", "throughput": 5544.55, "total_tokens": 9589648} {"current_steps": 15740, "total_steps": 64460, "loss": 0.2294, "lr": 9.380129117861775e-06, "epoch": 4.883648774433757, "percentage": 24.42, "elapsed_time": "0:28:50", "remaining_time": "1:29:15", "throughput": 5544.31, "total_tokens": 9592144} {"current_steps": 15745, "total_steps": 64460, "loss": 0.2299, "lr": 9.379476064191137e-06, "epoch": 4.885200124107974, "percentage": 24.43, "elapsed_time": "0:28:50", "remaining_time": "1:29:14", "throughput": 5544.36, "total_tokens": 9595568} {"current_steps": 15750, "total_steps": 64460, "loss": 0.2316, "lr": 9.378822689453043e-06, "epoch": 4.886751473782191, "percentage": 24.43, "elapsed_time": "0:28:51", "remaining_time": "1:29:13", "throughput": 5544.51, "total_tokens": 9598416} {"current_steps": 15755, "total_steps": 64460, "loss": 0.2301, "lr": 9.378168993695391e-06, "epoch": 4.888302823456407, "percentage": 24.44, "elapsed_time": "0:28:51", "remaining_time": "1:29:13", "throughput": 5544.59, "total_tokens": 9601520} {"current_steps": 15760, "total_steps": 64460, "loss": 0.2334, "lr": 9.377514976966109e-06, "epoch": 4.889854173130623, "percentage": 24.45, "elapsed_time": "0:28:52", "remaining_time": "1:29:12", "throughput": 5544.48, "total_tokens": 9604400} {"current_steps": 15765, "total_steps": 64460, "loss": 0.2324, "lr": 9.376860639313139e-06, "epoch": 4.89140552280484, "percentage": 24.46, "elapsed_time": "0:28:52", "remaining_time": "1:29:12", "throughput": 5544.31, "total_tokens": 9606704} {"current_steps": 15770, "total_steps": 64460, "loss": 0.2273, "lr": 9.376205980784456e-06, "epoch": 4.892956872479057, "percentage": 24.46, "elapsed_time": "0:28:53", "remaining_time": "1:29:11", "throughput": 5544.34, "total_tokens": 9609488} {"current_steps": 15775, "total_steps": 64460, "loss": 0.233, "lr": 9.375551001428053e-06, "epoch": 4.894508222153274, "percentage": 24.47, "elapsed_time": "0:28:53", "remaining_time": "1:29:10", "throughput": 5544.59, "total_tokens": 9612944} {"current_steps": 15780, "total_steps": 64460, "loss": 0.2329, "lr": 9.374895701291945e-06, "epoch": 4.8960595718274895, "percentage": 24.48, "elapsed_time": "0:28:54", "remaining_time": "1:29:09", "throughput": 5544.71, "total_tokens": 9615856} {"current_steps": 15785, "total_steps": 64460, "loss": 0.2316, "lr": 9.374240080424178e-06, "epoch": 4.897610921501706, "percentage": 24.49, "elapsed_time": "0:28:54", "remaining_time": "1:29:09", "throughput": 5544.62, "total_tokens": 9618416} {"current_steps": 15790, "total_steps": 64460, "loss": 0.2323, "lr": 9.373584138872813e-06, "epoch": 4.899162271175923, "percentage": 24.5, "elapsed_time": "0:28:55", "remaining_time": "1:29:08", "throughput": 5544.52, "total_tokens": 9620880} {"current_steps": 15795, "total_steps": 64460, "loss": 0.2316, "lr": 9.372927876685941e-06, "epoch": 4.90071362085014, "percentage": 24.5, "elapsed_time": "0:28:55", "remaining_time": "1:29:07", "throughput": 5544.59, "total_tokens": 9623888} {"current_steps": 15800, "total_steps": 64460, "loss": 0.2314, "lr": 9.372271293911672e-06, "epoch": 4.902264970524357, "percentage": 24.51, "elapsed_time": "0:28:56", "remaining_time": "1:29:07", "throughput": 5544.28, "total_tokens": 9625936} {"current_steps": 15805, "total_steps": 64460, "loss": 0.2315, "lr": 9.371614390598141e-06, "epoch": 4.9038163201985725, "percentage": 24.52, "elapsed_time": "0:28:56", "remaining_time": "1:29:06", "throughput": 5544.28, "total_tokens": 9628528} {"current_steps": 15810, "total_steps": 64460, "loss": 0.228, "lr": 9.370957166793508e-06, "epoch": 4.905367669872789, "percentage": 24.53, "elapsed_time": "0:28:57", "remaining_time": "1:29:05", "throughput": 5544.67, "total_tokens": 9632528} {"current_steps": 15815, "total_steps": 64460, "loss": 0.2307, "lr": 9.370299622545955e-06, "epoch": 4.906919019547006, "percentage": 24.53, "elapsed_time": "0:28:57", "remaining_time": "1:29:05", "throughput": 5544.86, "total_tokens": 9635632} {"current_steps": 15820, "total_steps": 64460, "loss": 0.234, "lr": 9.369641757903687e-06, "epoch": 4.908470369221223, "percentage": 24.54, "elapsed_time": "0:28:58", "remaining_time": "1:29:04", "throughput": 5544.72, "total_tokens": 9637936} {"current_steps": 15825, "total_steps": 64460, "loss": 0.2323, "lr": 9.368983572914933e-06, "epoch": 4.910021718895439, "percentage": 24.55, "elapsed_time": "0:28:58", "remaining_time": "1:29:03", "throughput": 5544.78, "total_tokens": 9641072} {"current_steps": 15830, "total_steps": 64460, "loss": 0.2341, "lr": 9.368325067627949e-06, "epoch": 4.9115730685696555, "percentage": 24.56, "elapsed_time": "0:28:59", "remaining_time": "1:29:03", "throughput": 5544.74, "total_tokens": 9643696} {"current_steps": 15835, "total_steps": 64460, "loss": 0.2289, "lr": 9.367666242091007e-06, "epoch": 4.913124418243872, "percentage": 24.57, "elapsed_time": "0:28:59", "remaining_time": "1:29:02", "throughput": 5544.87, "total_tokens": 9646864} {"current_steps": 15840, "total_steps": 64460, "loss": 0.2299, "lr": 9.36700709635241e-06, "epoch": 4.914675767918089, "percentage": 24.57, "elapsed_time": "0:29:00", "remaining_time": "1:29:02", "throughput": 5545.09, "total_tokens": 9650576} {"current_steps": 15845, "total_steps": 64460, "loss": 0.2368, "lr": 9.366347630460477e-06, "epoch": 4.916227117592305, "percentage": 24.58, "elapsed_time": "0:29:01", "remaining_time": "1:29:01", "throughput": 5545.24, "total_tokens": 9654352} {"current_steps": 15850, "total_steps": 64460, "loss": 0.2346, "lr": 9.36568784446356e-06, "epoch": 4.917778467266522, "percentage": 24.59, "elapsed_time": "0:29:01", "remaining_time": "1:29:01", "throughput": 5545.1, "total_tokens": 9656880} {"current_steps": 15855, "total_steps": 64460, "loss": 0.2356, "lr": 9.365027738410026e-06, "epoch": 4.9193298169407385, "percentage": 24.6, "elapsed_time": "0:29:02", "remaining_time": "1:29:00", "throughput": 5545.11, "total_tokens": 9659792} {"current_steps": 15860, "total_steps": 64460, "loss": 0.2309, "lr": 9.364367312348267e-06, "epoch": 4.920881166614955, "percentage": 24.6, "elapsed_time": "0:29:02", "remaining_time": "1:28:59", "throughput": 5545.14, "total_tokens": 9662608} {"current_steps": 15865, "total_steps": 64460, "loss": 0.2358, "lr": 9.363706566326706e-06, "epoch": 4.922432516289172, "percentage": 24.61, "elapsed_time": "0:29:03", "remaining_time": "1:28:59", "throughput": 5545.03, "total_tokens": 9665552} {"current_steps": 15870, "total_steps": 64460, "loss": 0.231, "lr": 9.363045500393777e-06, "epoch": 4.923983865963388, "percentage": 24.62, "elapsed_time": "0:29:03", "remaining_time": "1:28:58", "throughput": 5545.03, "total_tokens": 9668496} {"current_steps": 15875, "total_steps": 64460, "loss": 0.2362, "lr": 9.362384114597947e-06, "epoch": 4.925535215637605, "percentage": 24.63, "elapsed_time": "0:29:04", "remaining_time": "1:28:57", "throughput": 5544.81, "total_tokens": 9670832} {"current_steps": 15880, "total_steps": 64460, "loss": 0.2284, "lr": 9.361722408987703e-06, "epoch": 4.927086565311821, "percentage": 24.64, "elapsed_time": "0:29:04", "remaining_time": "1:28:57", "throughput": 5544.97, "total_tokens": 9674160} {"current_steps": 15885, "total_steps": 64460, "loss": 0.2269, "lr": 9.361060383611557e-06, "epoch": 4.928637914986038, "percentage": 24.64, "elapsed_time": "0:29:05", "remaining_time": "1:28:56", "throughput": 5544.81, "total_tokens": 9676464} {"current_steps": 15890, "total_steps": 64460, "loss": 0.2305, "lr": 9.360398038518041e-06, "epoch": 4.930189264660254, "percentage": 24.65, "elapsed_time": "0:29:05", "remaining_time": "1:28:55", "throughput": 5544.72, "total_tokens": 9678992} {"current_steps": 15895, "total_steps": 64460, "loss": 0.2369, "lr": 9.359735373755716e-06, "epoch": 4.931740614334471, "percentage": 24.66, "elapsed_time": "0:29:06", "remaining_time": "1:28:55", "throughput": 5544.74, "total_tokens": 9682032} {"current_steps": 15900, "total_steps": 64460, "loss": 0.2268, "lr": 9.359072389373158e-06, "epoch": 4.933291964008688, "percentage": 24.67, "elapsed_time": "0:29:06", "remaining_time": "1:28:54", "throughput": 5544.87, "total_tokens": 9685072} {"current_steps": 15905, "total_steps": 64460, "loss": 0.233, "lr": 9.358409085418976e-06, "epoch": 4.934843313682904, "percentage": 24.67, "elapsed_time": "0:29:07", "remaining_time": "1:28:53", "throughput": 5544.74, "total_tokens": 9687600} {"current_steps": 15910, "total_steps": 64460, "loss": 0.2271, "lr": 9.357745461941798e-06, "epoch": 4.93639466335712, "percentage": 24.68, "elapsed_time": "0:29:07", "remaining_time": "1:28:53", "throughput": 5544.74, "total_tokens": 9690576} {"current_steps": 15915, "total_steps": 64460, "loss": 0.2319, "lr": 9.357081518990274e-06, "epoch": 4.937946013031337, "percentage": 24.69, "elapsed_time": "0:29:08", "remaining_time": "1:28:52", "throughput": 5544.75, "total_tokens": 9693392} {"current_steps": 15920, "total_steps": 64460, "loss": 0.2228, "lr": 9.356417256613077e-06, "epoch": 4.939497362705554, "percentage": 24.7, "elapsed_time": "0:29:08", "remaining_time": "1:28:52", "throughput": 5545.07, "total_tokens": 9697616} {"current_steps": 15925, "total_steps": 64460, "loss": 0.2304, "lr": 9.35575267485891e-06, "epoch": 4.941048712379771, "percentage": 24.71, "elapsed_time": "0:29:09", "remaining_time": "1:28:51", "throughput": 5545.03, "total_tokens": 9700432} {"current_steps": 15930, "total_steps": 64460, "loss": 0.2307, "lr": 9.35508777377649e-06, "epoch": 4.942600062053987, "percentage": 24.71, "elapsed_time": "0:29:09", "remaining_time": "1:28:51", "throughput": 5545.18, "total_tokens": 9703632} {"current_steps": 15935, "total_steps": 64460, "loss": 0.2332, "lr": 9.354422553414565e-06, "epoch": 4.944151411728203, "percentage": 24.72, "elapsed_time": "0:29:10", "remaining_time": "1:28:50", "throughput": 5545.1, "total_tokens": 9706224} {"current_steps": 15940, "total_steps": 64460, "loss": 0.2242, "lr": 9.353757013821903e-06, "epoch": 4.94570276140242, "percentage": 24.73, "elapsed_time": "0:29:10", "remaining_time": "1:28:49", "throughput": 5544.88, "total_tokens": 9708496} {"current_steps": 15945, "total_steps": 64460, "loss": 0.2379, "lr": 9.353091155047295e-06, "epoch": 4.947254111076637, "percentage": 24.74, "elapsed_time": "0:29:11", "remaining_time": "1:28:49", "throughput": 5545.11, "total_tokens": 9712304} {"current_steps": 15950, "total_steps": 64460, "loss": 0.2303, "lr": 9.352424977139559e-06, "epoch": 4.948805460750854, "percentage": 24.74, "elapsed_time": "0:29:11", "remaining_time": "1:28:48", "throughput": 5544.99, "total_tokens": 9714768} {"current_steps": 15955, "total_steps": 64460, "loss": 0.2281, "lr": 9.351758480147529e-06, "epoch": 4.9503568104250695, "percentage": 24.75, "elapsed_time": "0:29:12", "remaining_time": "1:28:47", "throughput": 5545.14, "total_tokens": 9717776} {"current_steps": 15960, "total_steps": 64460, "loss": 0.2432, "lr": 9.351091664120072e-06, "epoch": 4.951908160099286, "percentage": 24.76, "elapsed_time": "0:29:12", "remaining_time": "1:28:47", "throughput": 5545.38, "total_tokens": 9720976} {"current_steps": 15965, "total_steps": 64460, "loss": 0.2441, "lr": 9.35042452910607e-06, "epoch": 4.953459509773503, "percentage": 24.77, "elapsed_time": "0:29:13", "remaining_time": "1:28:46", "throughput": 5545.48, "total_tokens": 9723888} {"current_steps": 15970, "total_steps": 64460, "loss": 0.229, "lr": 9.349757075154434e-06, "epoch": 4.95501085944772, "percentage": 24.78, "elapsed_time": "0:29:13", "remaining_time": "1:28:45", "throughput": 5545.65, "total_tokens": 9726928} {"current_steps": 15975, "total_steps": 64460, "loss": 0.2295, "lr": 9.349089302314094e-06, "epoch": 4.956562209121936, "percentage": 24.78, "elapsed_time": "0:29:14", "remaining_time": "1:28:44", "throughput": 5545.74, "total_tokens": 9729904} {"current_steps": 15980, "total_steps": 64460, "loss": 0.2295, "lr": 9.348421210634008e-06, "epoch": 4.9581135587961525, "percentage": 24.79, "elapsed_time": "0:29:15", "remaining_time": "1:28:44", "throughput": 5545.98, "total_tokens": 9733392} {"current_steps": 15985, "total_steps": 64460, "loss": 0.2314, "lr": 9.347752800163156e-06, "epoch": 4.959664908470369, "percentage": 24.8, "elapsed_time": "0:29:15", "remaining_time": "1:28:43", "throughput": 5545.94, "total_tokens": 9736144} {"current_steps": 15990, "total_steps": 64460, "loss": 0.2304, "lr": 9.347084070950538e-06, "epoch": 4.961216258144586, "percentage": 24.81, "elapsed_time": "0:29:16", "remaining_time": "1:28:43", "throughput": 5545.87, "total_tokens": 9738928} {"current_steps": 15995, "total_steps": 64460, "loss": 0.2325, "lr": 9.346415023045178e-06, "epoch": 4.962767607818803, "percentage": 24.81, "elapsed_time": "0:29:16", "remaining_time": "1:28:42", "throughput": 5545.77, "total_tokens": 9741520} {"current_steps": 16000, "total_steps": 64460, "loss": 0.2345, "lr": 9.34574565649613e-06, "epoch": 4.964318957493019, "percentage": 24.82, "elapsed_time": "0:29:17", "remaining_time": "1:28:42", "throughput": 5546.12, "total_tokens": 9745552} {"current_steps": 16005, "total_steps": 64460, "loss": 0.2299, "lr": 9.345075971352464e-06, "epoch": 4.965870307167235, "percentage": 24.83, "elapsed_time": "0:29:17", "remaining_time": "1:28:41", "throughput": 5546.03, "total_tokens": 9748016} {"current_steps": 16010, "total_steps": 64460, "loss": 0.2303, "lr": 9.344405967663275e-06, "epoch": 4.967421656841452, "percentage": 24.84, "elapsed_time": "0:29:18", "remaining_time": "1:28:40", "throughput": 5546.17, "total_tokens": 9751664} {"current_steps": 16015, "total_steps": 64460, "loss": 0.2341, "lr": 9.343735645477684e-06, "epoch": 4.968973006515669, "percentage": 24.84, "elapsed_time": "0:29:18", "remaining_time": "1:28:40", "throughput": 5546.7, "total_tokens": 9756592} {"current_steps": 16020, "total_steps": 64460, "loss": 0.2288, "lr": 9.343065004844832e-06, "epoch": 4.970524356189885, "percentage": 24.85, "elapsed_time": "0:29:19", "remaining_time": "1:28:40", "throughput": 5546.76, "total_tokens": 9759664} {"current_steps": 16025, "total_steps": 64460, "loss": 0.2332, "lr": 9.342394045813887e-06, "epoch": 4.972075705864102, "percentage": 24.86, "elapsed_time": "0:29:20", "remaining_time": "1:28:39", "throughput": 5546.82, "total_tokens": 9762672} {"current_steps": 16030, "total_steps": 64460, "loss": 0.2283, "lr": 9.341722768434034e-06, "epoch": 4.973627055538318, "percentage": 24.87, "elapsed_time": "0:29:20", "remaining_time": "1:28:38", "throughput": 5547.02, "total_tokens": 9765744} {"current_steps": 16035, "total_steps": 64460, "loss": 0.2314, "lr": 9.34105117275449e-06, "epoch": 4.975178405212535, "percentage": 24.88, "elapsed_time": "0:29:21", "remaining_time": "1:28:38", "throughput": 5547.43, "total_tokens": 9770032} {"current_steps": 16040, "total_steps": 64460, "loss": 0.2303, "lr": 9.34037925882449e-06, "epoch": 4.976729754886751, "percentage": 24.88, "elapsed_time": "0:29:21", "remaining_time": "1:28:37", "throughput": 5547.35, "total_tokens": 9772592} {"current_steps": 16045, "total_steps": 64460, "loss": 0.2324, "lr": 9.339707026693292e-06, "epoch": 4.978281104560968, "percentage": 24.89, "elapsed_time": "0:29:22", "remaining_time": "1:28:37", "throughput": 5547.51, "total_tokens": 9775632} {"current_steps": 16050, "total_steps": 64460, "loss": 0.2293, "lr": 9.339034476410177e-06, "epoch": 4.979832454235185, "percentage": 24.9, "elapsed_time": "0:29:22", "remaining_time": "1:28:36", "throughput": 5548.0, "total_tokens": 9779760} {"current_steps": 16055, "total_steps": 64460, "loss": 0.2345, "lr": 9.338361608024456e-06, "epoch": 4.981383803909401, "percentage": 24.91, "elapsed_time": "0:29:23", "remaining_time": "1:28:36", "throughput": 5548.27, "total_tokens": 9783952} {"current_steps": 16060, "total_steps": 64460, "loss": 0.2258, "lr": 9.337688421585455e-06, "epoch": 4.982935153583618, "percentage": 24.91, "elapsed_time": "0:29:24", "remaining_time": "1:28:36", "throughput": 5548.63, "total_tokens": 9788144} {"current_steps": 16065, "total_steps": 64460, "loss": 0.2356, "lr": 9.337014917142526e-06, "epoch": 4.984486503257834, "percentage": 24.92, "elapsed_time": "0:29:24", "remaining_time": "1:28:35", "throughput": 5548.48, "total_tokens": 9790448} {"current_steps": 16070, "total_steps": 64460, "loss": 0.2373, "lr": 9.336341094745044e-06, "epoch": 4.986037852932051, "percentage": 24.93, "elapsed_time": "0:29:25", "remaining_time": "1:28:34", "throughput": 5548.32, "total_tokens": 9792816} {"current_steps": 16075, "total_steps": 64460, "loss": 0.2325, "lr": 9.335666954442413e-06, "epoch": 4.987589202606268, "percentage": 24.94, "elapsed_time": "0:29:25", "remaining_time": "1:28:34", "throughput": 5548.5, "total_tokens": 9796176} {"current_steps": 16080, "total_steps": 64460, "loss": 0.2345, "lr": 9.33499249628405e-06, "epoch": 4.989140552280484, "percentage": 24.95, "elapsed_time": "0:29:26", "remaining_time": "1:28:33", "throughput": 5548.43, "total_tokens": 9798736} {"current_steps": 16085, "total_steps": 64460, "loss": 0.2303, "lr": 9.334317720319403e-06, "epoch": 4.9906919019547, "percentage": 24.95, "elapsed_time": "0:29:26", "remaining_time": "1:28:33", "throughput": 5548.86, "total_tokens": 9802704} {"current_steps": 16090, "total_steps": 64460, "loss": 0.23, "lr": 9.333642626597942e-06, "epoch": 4.992243251628917, "percentage": 24.96, "elapsed_time": "0:29:27", "remaining_time": "1:28:32", "throughput": 5548.74, "total_tokens": 9805264} {"current_steps": 16095, "total_steps": 64460, "loss": 0.2313, "lr": 9.332967215169157e-06, "epoch": 4.993794601303134, "percentage": 24.97, "elapsed_time": "0:29:27", "remaining_time": "1:28:31", "throughput": 5548.94, "total_tokens": 9808528} {"current_steps": 16100, "total_steps": 64460, "loss": 0.2217, "lr": 9.332291486082568e-06, "epoch": 4.995345950977351, "percentage": 24.98, "elapsed_time": "0:29:28", "remaining_time": "1:28:31", "throughput": 5549.06, "total_tokens": 9812208} {"current_steps": 16105, "total_steps": 64460, "loss": 0.2364, "lr": 9.33161543938771e-06, "epoch": 4.9968973006515665, "percentage": 24.98, "elapsed_time": "0:29:28", "remaining_time": "1:28:30", "throughput": 5549.07, "total_tokens": 9814896} {"current_steps": 16110, "total_steps": 64460, "loss": 0.2451, "lr": 9.330939075134144e-06, "epoch": 4.998448650325783, "percentage": 24.99, "elapsed_time": "0:29:29", "remaining_time": "1:28:30", "throughput": 5549.22, "total_tokens": 9818352} {"current_steps": 16115, "total_steps": 64460, "loss": 0.2297, "lr": 9.330262393371461e-06, "epoch": 5.0, "percentage": 25.0, "elapsed_time": "0:29:30", "remaining_time": "1:28:30", "throughput": 5549.04, "total_tokens": 9821920} {"current_steps": 16120, "total_steps": 64460, "loss": 0.2295, "lr": 9.329585394149264e-06, "epoch": 5.001551349674217, "percentage": 25.01, "elapsed_time": "0:29:30", "remaining_time": "1:28:30", "throughput": 5549.0, "total_tokens": 9825824} {"current_steps": 16125, "total_steps": 64460, "loss": 0.2348, "lr": 9.328908077517189e-06, "epoch": 5.0031026993484335, "percentage": 25.02, "elapsed_time": "0:29:31", "remaining_time": "1:28:29", "throughput": 5549.12, "total_tokens": 9828864} {"current_steps": 16130, "total_steps": 64460, "loss": 0.2297, "lr": 9.32823044352489e-06, "epoch": 5.004654049022649, "percentage": 25.02, "elapsed_time": "0:29:31", "remaining_time": "1:28:28", "throughput": 5549.08, "total_tokens": 9831904} {"current_steps": 16135, "total_steps": 64460, "loss": 0.2301, "lr": 9.327552492222046e-06, "epoch": 5.006205398696866, "percentage": 25.03, "elapsed_time": "0:29:32", "remaining_time": "1:28:28", "throughput": 5549.21, "total_tokens": 9834848} {"current_steps": 16140, "total_steps": 64460, "loss": 0.2323, "lr": 9.326874223658356e-06, "epoch": 5.007756748371083, "percentage": 25.04, "elapsed_time": "0:29:32", "remaining_time": "1:28:27", "throughput": 5549.23, "total_tokens": 9837504} {"current_steps": 16145, "total_steps": 64460, "loss": 0.2285, "lr": 9.32619563788355e-06, "epoch": 5.0093080980453, "percentage": 25.05, "elapsed_time": "0:29:33", "remaining_time": "1:28:26", "throughput": 5549.61, "total_tokens": 9841440} {"current_steps": 16150, "total_steps": 64460, "loss": 0.2359, "lr": 9.325516734947372e-06, "epoch": 5.010859447719516, "percentage": 25.05, "elapsed_time": "0:29:33", "remaining_time": "1:28:26", "throughput": 5549.87, "total_tokens": 9844576} {"current_steps": 16155, "total_steps": 64460, "loss": 0.2295, "lr": 9.324837514899598e-06, "epoch": 5.012410797393732, "percentage": 25.06, "elapsed_time": "0:29:34", "remaining_time": "1:28:25", "throughput": 5550.09, "total_tokens": 9847616} {"current_steps": 16160, "total_steps": 64460, "loss": 0.2305, "lr": 9.324157977790018e-06, "epoch": 5.013962147067949, "percentage": 25.07, "elapsed_time": "0:29:35", "remaining_time": "1:28:25", "throughput": 5550.66, "total_tokens": 9853088} {"current_steps": 16165, "total_steps": 64460, "loss": 0.2325, "lr": 9.323478123668455e-06, "epoch": 5.015513496742166, "percentage": 25.08, "elapsed_time": "0:29:35", "remaining_time": "1:28:24", "throughput": 5550.76, "total_tokens": 9856128} {"current_steps": 16170, "total_steps": 64460, "loss": 0.235, "lr": 9.322797952584745e-06, "epoch": 5.017064846416382, "percentage": 25.09, "elapsed_time": "0:29:36", "remaining_time": "1:28:24", "throughput": 5550.94, "total_tokens": 9859360} {"current_steps": 16175, "total_steps": 64460, "loss": 0.2288, "lr": 9.322117464588757e-06, "epoch": 5.018616196090599, "percentage": 25.09, "elapsed_time": "0:29:36", "remaining_time": "1:28:23", "throughput": 5551.01, "total_tokens": 9862304} {"current_steps": 16180, "total_steps": 64460, "loss": 0.2347, "lr": 9.321436659730378e-06, "epoch": 5.020167545764815, "percentage": 25.1, "elapsed_time": "0:29:37", "remaining_time": "1:28:22", "throughput": 5550.94, "total_tokens": 9864832} {"current_steps": 16185, "total_steps": 64460, "loss": 0.2299, "lr": 9.320755538059519e-06, "epoch": 5.021718895439032, "percentage": 25.11, "elapsed_time": "0:29:37", "remaining_time": "1:28:22", "throughput": 5551.23, "total_tokens": 9868544} {"current_steps": 16190, "total_steps": 64460, "loss": 0.2298, "lr": 9.320074099626112e-06, "epoch": 5.023270245113249, "percentage": 25.12, "elapsed_time": "0:29:38", "remaining_time": "1:28:21", "throughput": 5551.05, "total_tokens": 9870848} {"current_steps": 16195, "total_steps": 64460, "loss": 0.2284, "lr": 9.319392344480116e-06, "epoch": 5.024821594787465, "percentage": 25.12, "elapsed_time": "0:29:38", "remaining_time": "1:28:21", "throughput": 5551.2, "total_tokens": 9874176} {"current_steps": 16200, "total_steps": 64460, "loss": 0.2285, "lr": 9.318710272671514e-06, "epoch": 5.026372944461682, "percentage": 25.13, "elapsed_time": "0:29:39", "remaining_time": "1:28:20", "throughput": 5551.34, "total_tokens": 9877504} {"current_steps": 16205, "total_steps": 64460, "loss": 0.2323, "lr": 9.318027884250304e-06, "epoch": 5.027924294135898, "percentage": 25.14, "elapsed_time": "0:29:39", "remaining_time": "1:28:20", "throughput": 5551.37, "total_tokens": 9880832} {"current_steps": 16210, "total_steps": 64460, "loss": 0.2338, "lr": 9.317345179266522e-06, "epoch": 5.029475643810115, "percentage": 25.15, "elapsed_time": "0:29:40", "remaining_time": "1:28:19", "throughput": 5551.47, "total_tokens": 9883744} {"current_steps": 16215, "total_steps": 64460, "loss": 0.224, "lr": 9.31666215777021e-06, "epoch": 5.031026993484331, "percentage": 25.16, "elapsed_time": "0:29:41", "remaining_time": "1:28:19", "throughput": 5551.92, "total_tokens": 9888736} {"current_steps": 16220, "total_steps": 64460, "loss": 0.2311, "lr": 9.315978819811445e-06, "epoch": 5.032578343158548, "percentage": 25.16, "elapsed_time": "0:29:41", "remaining_time": "1:28:18", "throughput": 5551.85, "total_tokens": 9891424} {"current_steps": 16225, "total_steps": 64460, "loss": 0.2257, "lr": 9.315295165440324e-06, "epoch": 5.034129692832765, "percentage": 25.17, "elapsed_time": "0:29:42", "remaining_time": "1:28:17", "throughput": 5551.7, "total_tokens": 9893728} {"current_steps": 16230, "total_steps": 64460, "loss": 0.2367, "lr": 9.314611194706966e-06, "epoch": 5.035681042506981, "percentage": 25.18, "elapsed_time": "0:29:42", "remaining_time": "1:28:17", "throughput": 5551.78, "total_tokens": 9896416} {"current_steps": 16235, "total_steps": 64460, "loss": 0.2263, "lr": 9.313926907661518e-06, "epoch": 5.037232392181197, "percentage": 25.19, "elapsed_time": "0:29:43", "remaining_time": "1:28:16", "throughput": 5551.75, "total_tokens": 9899072} {"current_steps": 16240, "total_steps": 64460, "loss": 0.2413, "lr": 9.31324230435414e-06, "epoch": 5.038783741855414, "percentage": 25.19, "elapsed_time": "0:29:43", "remaining_time": "1:28:15", "throughput": 5551.73, "total_tokens": 9901664} {"current_steps": 16245, "total_steps": 64460, "loss": 0.2329, "lr": 9.312557384835025e-06, "epoch": 5.040335091529631, "percentage": 25.2, "elapsed_time": "0:29:44", "remaining_time": "1:28:14", "throughput": 5551.86, "total_tokens": 9904704} {"current_steps": 16250, "total_steps": 64460, "loss": 0.2404, "lr": 9.311872149154386e-06, "epoch": 5.0418864412038475, "percentage": 25.21, "elapsed_time": "0:29:44", "remaining_time": "1:28:14", "throughput": 5552.11, "total_tokens": 9908672} {"current_steps": 16255, "total_steps": 64460, "loss": 0.233, "lr": 9.311186597362458e-06, "epoch": 5.043437790878064, "percentage": 25.22, "elapsed_time": "0:29:45", "remaining_time": "1:28:14", "throughput": 5551.75, "total_tokens": 9911072} {"current_steps": 16260, "total_steps": 64460, "loss": 0.2314, "lr": 9.3105007295095e-06, "epoch": 5.04498914055228, "percentage": 25.22, "elapsed_time": "0:29:45", "remaining_time": "1:28:13", "throughput": 5551.58, "total_tokens": 9913600} {"current_steps": 16265, "total_steps": 64460, "loss": 0.2267, "lr": 9.309814545645794e-06, "epoch": 5.046540490226497, "percentage": 25.23, "elapsed_time": "0:29:46", "remaining_time": "1:28:12", "throughput": 5551.55, "total_tokens": 9916448} {"current_steps": 16270, "total_steps": 64460, "loss": 0.2283, "lr": 9.309128045821649e-06, "epoch": 5.048091839900714, "percentage": 25.24, "elapsed_time": "0:29:46", "remaining_time": "1:28:12", "throughput": 5551.51, "total_tokens": 9919008} {"current_steps": 16275, "total_steps": 64460, "loss": 0.2299, "lr": 9.308441230087389e-06, "epoch": 5.0496431895749305, "percentage": 25.25, "elapsed_time": "0:29:47", "remaining_time": "1:28:11", "throughput": 5551.56, "total_tokens": 9921888} {"current_steps": 16280, "total_steps": 64460, "loss": 0.2295, "lr": 9.307754098493364e-06, "epoch": 5.051194539249146, "percentage": 25.26, "elapsed_time": "0:29:47", "remaining_time": "1:28:10", "throughput": 5551.5, "total_tokens": 9924416} {"current_steps": 16285, "total_steps": 64460, "loss": 0.2357, "lr": 9.307066651089955e-06, "epoch": 5.052745888923363, "percentage": 25.26, "elapsed_time": "0:29:48", "remaining_time": "1:28:10", "throughput": 5551.63, "total_tokens": 9927872} {"current_steps": 16290, "total_steps": 64460, "loss": 0.227, "lr": 9.306378887927558e-06, "epoch": 5.05429723859758, "percentage": 25.27, "elapsed_time": "0:29:48", "remaining_time": "1:28:09", "throughput": 5551.42, "total_tokens": 9930176} {"current_steps": 16295, "total_steps": 64460, "loss": 0.2373, "lr": 9.305690809056592e-06, "epoch": 5.055848588271797, "percentage": 25.28, "elapsed_time": "0:29:49", "remaining_time": "1:28:08", "throughput": 5551.16, "total_tokens": 9932384} {"current_steps": 16300, "total_steps": 64460, "loss": 0.2283, "lr": 9.305002414527505e-06, "epoch": 5.057399937946013, "percentage": 25.29, "elapsed_time": "0:29:49", "remaining_time": "1:28:08", "throughput": 5551.22, "total_tokens": 9935520} {"current_steps": 16305, "total_steps": 64460, "loss": 0.2326, "lr": 9.30431370439076e-06, "epoch": 5.058951287620229, "percentage": 25.29, "elapsed_time": "0:29:50", "remaining_time": "1:28:07", "throughput": 5551.44, "total_tokens": 9938848} {"current_steps": 16310, "total_steps": 64460, "loss": 0.2284, "lr": 9.303624678696849e-06, "epoch": 5.060502637294446, "percentage": 25.3, "elapsed_time": "0:29:50", "remaining_time": "1:28:06", "throughput": 5551.15, "total_tokens": 9940896} {"current_steps": 16315, "total_steps": 64460, "loss": 0.234, "lr": 9.302935337496288e-06, "epoch": 5.062053986968663, "percentage": 25.31, "elapsed_time": "0:29:51", "remaining_time": "1:28:06", "throughput": 5551.19, "total_tokens": 9944160} {"current_steps": 16320, "total_steps": 64460, "loss": 0.231, "lr": 9.302245680839611e-06, "epoch": 5.06360533664288, "percentage": 25.32, "elapsed_time": "0:29:51", "remaining_time": "1:28:05", "throughput": 5551.18, "total_tokens": 9946880} {"current_steps": 16325, "total_steps": 64460, "loss": 0.2275, "lr": 9.301555708777381e-06, "epoch": 5.065156686317096, "percentage": 25.33, "elapsed_time": "0:29:52", "remaining_time": "1:28:04", "throughput": 5551.12, "total_tokens": 9949536} {"current_steps": 16330, "total_steps": 64460, "loss": 0.2336, "lr": 9.300865421360179e-06, "epoch": 5.066708035991312, "percentage": 25.33, "elapsed_time": "0:29:52", "remaining_time": "1:28:04", "throughput": 5551.1, "total_tokens": 9952192} {"current_steps": 16335, "total_steps": 64460, "loss": 0.2311, "lr": 9.30017481863861e-06, "epoch": 5.068259385665529, "percentage": 25.34, "elapsed_time": "0:29:53", "remaining_time": "1:28:03", "throughput": 5551.16, "total_tokens": 9955136} {"current_steps": 16340, "total_steps": 64460, "loss": 0.2332, "lr": 9.299483900663307e-06, "epoch": 5.069810735339746, "percentage": 25.35, "elapsed_time": "0:29:53", "remaining_time": "1:28:02", "throughput": 5551.05, "total_tokens": 9957536} {"current_steps": 16345, "total_steps": 64460, "loss": 0.2312, "lr": 9.29879266748492e-06, "epoch": 5.071362085013962, "percentage": 25.36, "elapsed_time": "0:29:54", "remaining_time": "1:28:01", "throughput": 5551.12, "total_tokens": 9960288} {"current_steps": 16350, "total_steps": 64460, "loss": 0.2308, "lr": 9.298101119154126e-06, "epoch": 5.072913434688179, "percentage": 25.36, "elapsed_time": "0:29:54", "remaining_time": "1:28:01", "throughput": 5551.22, "total_tokens": 9963488} {"current_steps": 16355, "total_steps": 64460, "loss": 0.2359, "lr": 9.297409255721622e-06, "epoch": 5.074464784362395, "percentage": 25.37, "elapsed_time": "0:29:55", "remaining_time": "1:28:00", "throughput": 5551.33, "total_tokens": 9966400} {"current_steps": 16360, "total_steps": 64460, "loss": 0.2339, "lr": 9.296717077238131e-06, "epoch": 5.076016134036612, "percentage": 25.38, "elapsed_time": "0:29:55", "remaining_time": "1:27:59", "throughput": 5551.37, "total_tokens": 9969312} {"current_steps": 16365, "total_steps": 64460, "loss": 0.2357, "lr": 9.296024583754397e-06, "epoch": 5.077567483710828, "percentage": 25.39, "elapsed_time": "0:29:56", "remaining_time": "1:27:59", "throughput": 5551.22, "total_tokens": 9971712} {"current_steps": 16370, "total_steps": 64460, "loss": 0.23, "lr": 9.29533177532119e-06, "epoch": 5.079118833385045, "percentage": 25.4, "elapsed_time": "0:29:56", "remaining_time": "1:27:58", "throughput": 5550.89, "total_tokens": 9974016} {"current_steps": 16375, "total_steps": 64460, "loss": 0.2326, "lr": 9.294638651989298e-06, "epoch": 5.0806701830592615, "percentage": 25.4, "elapsed_time": "0:29:57", "remaining_time": "1:27:57", "throughput": 5550.79, "total_tokens": 9976544} {"current_steps": 16380, "total_steps": 64460, "loss": 0.23, "lr": 9.293945213809536e-06, "epoch": 5.082221532733478, "percentage": 25.41, "elapsed_time": "0:29:57", "remaining_time": "1:27:57", "throughput": 5550.94, "total_tokens": 9979680} {"current_steps": 16385, "total_steps": 64460, "loss": 0.2295, "lr": 9.293251460832744e-06, "epoch": 5.083772882407695, "percentage": 25.42, "elapsed_time": "0:29:58", "remaining_time": "1:27:56", "throughput": 5551.32, "total_tokens": 9983296} {"current_steps": 16390, "total_steps": 64460, "loss": 0.2332, "lr": 9.292557393109779e-06, "epoch": 5.085324232081911, "percentage": 25.43, "elapsed_time": "0:29:58", "remaining_time": "1:27:55", "throughput": 5551.09, "total_tokens": 9985568} {"current_steps": 16395, "total_steps": 64460, "loss": 0.2366, "lr": 9.291863010691525e-06, "epoch": 5.086875581756128, "percentage": 25.43, "elapsed_time": "0:29:59", "remaining_time": "1:27:55", "throughput": 5551.47, "total_tokens": 9989568} {"current_steps": 16400, "total_steps": 64460, "loss": 0.2333, "lr": 9.29116831362889e-06, "epoch": 5.0884269314303445, "percentage": 25.44, "elapsed_time": "0:29:59", "remaining_time": "1:27:54", "throughput": 5551.58, "total_tokens": 9992736} {"current_steps": 16405, "total_steps": 64460, "loss": 0.227, "lr": 9.290473301972802e-06, "epoch": 5.089978281104561, "percentage": 25.45, "elapsed_time": "0:30:00", "remaining_time": "1:27:54", "throughput": 5551.4, "total_tokens": 9995040} {"current_steps": 16410, "total_steps": 64460, "loss": 0.2333, "lr": 9.289777975774214e-06, "epoch": 5.091529630778777, "percentage": 25.46, "elapsed_time": "0:30:00", "remaining_time": "1:27:53", "throughput": 5551.57, "total_tokens": 9998208} {"current_steps": 16415, "total_steps": 64460, "loss": 0.2254, "lr": 9.289082335084102e-06, "epoch": 5.093080980452994, "percentage": 25.47, "elapsed_time": "0:30:01", "remaining_time": "1:27:52", "throughput": 5551.65, "total_tokens": 10001376} {"current_steps": 16420, "total_steps": 64460, "loss": 0.2302, "lr": 9.288386379953467e-06, "epoch": 5.094632330127211, "percentage": 25.47, "elapsed_time": "0:30:02", "remaining_time": "1:27:52", "throughput": 5551.92, "total_tokens": 10005088} {"current_steps": 16425, "total_steps": 64460, "loss": 0.2349, "lr": 9.287690110433325e-06, "epoch": 5.0961836798014275, "percentage": 25.48, "elapsed_time": "0:30:02", "remaining_time": "1:27:51", "throughput": 5552.35, "total_tokens": 10008992} {"current_steps": 16430, "total_steps": 64460, "loss": 0.2308, "lr": 9.286993526574725e-06, "epoch": 5.097735029475643, "percentage": 25.49, "elapsed_time": "0:30:03", "remaining_time": "1:27:51", "throughput": 5552.14, "total_tokens": 10011360} {"current_steps": 16435, "total_steps": 64460, "loss": 0.235, "lr": 9.286296628428735e-06, "epoch": 5.09928637914986, "percentage": 25.5, "elapsed_time": "0:30:03", "remaining_time": "1:27:50", "throughput": 5552.22, "total_tokens": 10014144} {"current_steps": 16440, "total_steps": 64460, "loss": 0.2285, "lr": 9.285599416046443e-06, "epoch": 5.100837728824077, "percentage": 25.5, "elapsed_time": "0:30:04", "remaining_time": "1:27:49", "throughput": 5552.39, "total_tokens": 10017152} {"current_steps": 16445, "total_steps": 64460, "loss": 0.2322, "lr": 9.284901889478965e-06, "epoch": 5.102389078498294, "percentage": 25.51, "elapsed_time": "0:30:04", "remaining_time": "1:27:49", "throughput": 5552.56, "total_tokens": 10020288} {"current_steps": 16450, "total_steps": 64460, "loss": 0.2279, "lr": 9.284204048777438e-06, "epoch": 5.1039404281725105, "percentage": 25.52, "elapsed_time": "0:30:05", "remaining_time": "1:27:48", "throughput": 5552.75, "total_tokens": 10024000} {"current_steps": 16455, "total_steps": 64460, "loss": 0.2304, "lr": 9.283505893993024e-06, "epoch": 5.105491777846726, "percentage": 25.53, "elapsed_time": "0:30:05", "remaining_time": "1:27:47", "throughput": 5552.7, "total_tokens": 10026784} {"current_steps": 16460, "total_steps": 64460, "loss": 0.2279, "lr": 9.2828074251769e-06, "epoch": 5.107043127520943, "percentage": 25.54, "elapsed_time": "0:30:06", "remaining_time": "1:27:47", "throughput": 5552.83, "total_tokens": 10029760} {"current_steps": 16465, "total_steps": 64460, "loss": 0.2319, "lr": 9.282108642380279e-06, "epoch": 5.10859447719516, "percentage": 25.54, "elapsed_time": "0:30:06", "remaining_time": "1:27:46", "throughput": 5553.08, "total_tokens": 10033376} {"current_steps": 16470, "total_steps": 64460, "loss": 0.2294, "lr": 9.281409545654385e-06, "epoch": 5.110145826869377, "percentage": 25.55, "elapsed_time": "0:30:07", "remaining_time": "1:27:46", "throughput": 5553.12, "total_tokens": 10036128} {"current_steps": 16475, "total_steps": 64460, "loss": 0.2333, "lr": 9.28071013505047e-06, "epoch": 5.111697176543593, "percentage": 25.56, "elapsed_time": "0:30:07", "remaining_time": "1:27:45", "throughput": 5553.09, "total_tokens": 10038656} {"current_steps": 16480, "total_steps": 64460, "loss": 0.2419, "lr": 9.280010410619812e-06, "epoch": 5.113248526217809, "percentage": 25.57, "elapsed_time": "0:30:08", "remaining_time": "1:27:44", "throughput": 5553.47, "total_tokens": 10042432} {"current_steps": 16485, "total_steps": 64460, "loss": 0.2285, "lr": 9.27931037241371e-06, "epoch": 5.114799875892026, "percentage": 25.57, "elapsed_time": "0:30:08", "remaining_time": "1:27:44", "throughput": 5553.77, "total_tokens": 10046048} {"current_steps": 16490, "total_steps": 64460, "loss": 0.2247, "lr": 9.278610020483483e-06, "epoch": 5.116351225566243, "percentage": 25.58, "elapsed_time": "0:30:09", "remaining_time": "1:27:43", "throughput": 5553.83, "total_tokens": 10048864} {"current_steps": 16495, "total_steps": 64460, "loss": 0.2336, "lr": 9.277909354880473e-06, "epoch": 5.117902575240459, "percentage": 25.59, "elapsed_time": "0:30:09", "remaining_time": "1:27:42", "throughput": 5554.01, "total_tokens": 10052000} {"current_steps": 16500, "total_steps": 64460, "loss": 0.2242, "lr": 9.277208375656051e-06, "epoch": 5.1194539249146755, "percentage": 25.6, "elapsed_time": "0:30:10", "remaining_time": "1:27:42", "throughput": 5554.05, "total_tokens": 10054816} {"current_steps": 16505, "total_steps": 64460, "loss": 0.2303, "lr": 9.276507082861604e-06, "epoch": 5.121005274588892, "percentage": 25.61, "elapsed_time": "0:30:10", "remaining_time": "1:27:41", "throughput": 5554.18, "total_tokens": 10058176} {"current_steps": 16510, "total_steps": 64460, "loss": 0.2283, "lr": 9.275805476548548e-06, "epoch": 5.122556624263109, "percentage": 25.61, "elapsed_time": "0:30:11", "remaining_time": "1:27:40", "throughput": 5554.15, "total_tokens": 10060672} {"current_steps": 16515, "total_steps": 64460, "loss": 0.2286, "lr": 9.275103556768316e-06, "epoch": 5.124107973937326, "percentage": 25.62, "elapsed_time": "0:30:11", "remaining_time": "1:27:40", "throughput": 5554.33, "total_tokens": 10063680} {"current_steps": 16520, "total_steps": 64460, "loss": 0.2256, "lr": 9.274401323572368e-06, "epoch": 5.125659323611542, "percentage": 25.63, "elapsed_time": "0:30:12", "remaining_time": "1:27:39", "throughput": 5554.61, "total_tokens": 10067584} {"current_steps": 16525, "total_steps": 64460, "loss": 0.2177, "lr": 9.273698777012188e-06, "epoch": 5.1272106732857585, "percentage": 25.64, "elapsed_time": "0:30:12", "remaining_time": "1:27:38", "throughput": 5554.59, "total_tokens": 10070080} {"current_steps": 16530, "total_steps": 64460, "loss": 0.2383, "lr": 9.272995917139278e-06, "epoch": 5.128762022959975, "percentage": 25.64, "elapsed_time": "0:30:13", "remaining_time": "1:27:38", "throughput": 5554.83, "total_tokens": 10073472} {"current_steps": 16535, "total_steps": 64460, "loss": 0.2286, "lr": 9.27229274400517e-06, "epoch": 5.130313372634192, "percentage": 25.65, "elapsed_time": "0:30:13", "remaining_time": "1:27:37", "throughput": 5554.89, "total_tokens": 10076256} {"current_steps": 16540, "total_steps": 64460, "loss": 0.2434, "lr": 9.27158925766141e-06, "epoch": 5.131864722308408, "percentage": 25.66, "elapsed_time": "0:30:14", "remaining_time": "1:27:36", "throughput": 5554.92, "total_tokens": 10078944} {"current_steps": 16545, "total_steps": 64460, "loss": 0.233, "lr": 9.270885458159576e-06, "epoch": 5.133416071982625, "percentage": 25.67, "elapsed_time": "0:30:14", "remaining_time": "1:27:35", "throughput": 5554.86, "total_tokens": 10081376} {"current_steps": 16550, "total_steps": 64460, "loss": 0.2297, "lr": 9.270181345551261e-06, "epoch": 5.1349674216568415, "percentage": 25.67, "elapsed_time": "0:30:15", "remaining_time": "1:27:36", "throughput": 5555.56, "total_tokens": 10087008} {"current_steps": 16555, "total_steps": 64460, "loss": 0.241, "lr": 9.269476919888087e-06, "epoch": 5.136518771331058, "percentage": 25.68, "elapsed_time": "0:30:16", "remaining_time": "1:27:35", "throughput": 5555.81, "total_tokens": 10090496} {"current_steps": 16560, "total_steps": 64460, "loss": 0.2276, "lr": 9.2687721812217e-06, "epoch": 5.138070121005274, "percentage": 25.69, "elapsed_time": "0:30:16", "remaining_time": "1:27:34", "throughput": 5556.11, "total_tokens": 10093984} {"current_steps": 16565, "total_steps": 64460, "loss": 0.2322, "lr": 9.268067129603759e-06, "epoch": 5.139621470679491, "percentage": 25.7, "elapsed_time": "0:30:17", "remaining_time": "1:27:34", "throughput": 5556.18, "total_tokens": 10096928} {"current_steps": 16570, "total_steps": 64460, "loss": 0.226, "lr": 9.267361765085956e-06, "epoch": 5.141172820353708, "percentage": 25.71, "elapsed_time": "0:30:17", "remaining_time": "1:27:33", "throughput": 5556.24, "total_tokens": 10099808} {"current_steps": 16575, "total_steps": 64460, "loss": 0.2369, "lr": 9.266656087720003e-06, "epoch": 5.1427241700279245, "percentage": 25.71, "elapsed_time": "0:30:18", "remaining_time": "1:27:32", "throughput": 5556.27, "total_tokens": 10102464} {"current_steps": 16580, "total_steps": 64460, "loss": 0.23, "lr": 9.265950097557634e-06, "epoch": 5.144275519702141, "percentage": 25.72, "elapsed_time": "0:30:18", "remaining_time": "1:27:32", "throughput": 5556.27, "total_tokens": 10105376} {"current_steps": 16585, "total_steps": 64460, "loss": 0.2309, "lr": 9.265243794650607e-06, "epoch": 5.145826869376357, "percentage": 25.73, "elapsed_time": "0:30:19", "remaining_time": "1:27:31", "throughput": 5556.16, "total_tokens": 10107840} {"current_steps": 16590, "total_steps": 64460, "loss": 0.2284, "lr": 9.2645371790507e-06, "epoch": 5.147378219050574, "percentage": 25.74, "elapsed_time": "0:30:19", "remaining_time": "1:27:30", "throughput": 5556.34, "total_tokens": 10111360} {"current_steps": 16595, "total_steps": 64460, "loss": 0.228, "lr": 9.263830250809722e-06, "epoch": 5.148929568724791, "percentage": 25.74, "elapsed_time": "0:30:20", "remaining_time": "1:27:30", "throughput": 5556.59, "total_tokens": 10115200} {"current_steps": 16600, "total_steps": 64460, "loss": 0.2297, "lr": 9.26312300997949e-06, "epoch": 5.1504809183990075, "percentage": 25.75, "elapsed_time": "0:30:20", "remaining_time": "1:27:30", "throughput": 5556.95, "total_tokens": 10119008} {"current_steps": 16605, "total_steps": 64460, "loss": 0.2373, "lr": 9.262415456611862e-06, "epoch": 5.152032268073223, "percentage": 25.76, "elapsed_time": "0:30:21", "remaining_time": "1:27:29", "throughput": 5556.82, "total_tokens": 10121280} {"current_steps": 16610, "total_steps": 64460, "loss": 0.2324, "lr": 9.261707590758706e-06, "epoch": 5.15358361774744, "percentage": 25.77, "elapsed_time": "0:30:21", "remaining_time": "1:27:28", "throughput": 5556.8, "total_tokens": 10123936} {"current_steps": 16615, "total_steps": 64460, "loss": 0.231, "lr": 9.260999412471918e-06, "epoch": 5.155134967421657, "percentage": 25.78, "elapsed_time": "0:30:22", "remaining_time": "1:27:27", "throughput": 5556.93, "total_tokens": 10126912} {"current_steps": 16620, "total_steps": 64460, "loss": 0.2249, "lr": 9.260290921803415e-06, "epoch": 5.156686317095874, "percentage": 25.78, "elapsed_time": "0:30:22", "remaining_time": "1:27:27", "throughput": 5557.06, "total_tokens": 10130112} {"current_steps": 16625, "total_steps": 64460, "loss": 0.2257, "lr": 9.259582118805137e-06, "epoch": 5.1582376667700895, "percentage": 25.79, "elapsed_time": "0:30:23", "remaining_time": "1:27:26", "throughput": 5557.44, "total_tokens": 10134112} {"current_steps": 16630, "total_steps": 64460, "loss": 0.2158, "lr": 9.258873003529049e-06, "epoch": 5.159789016444306, "percentage": 25.8, "elapsed_time": "0:30:23", "remaining_time": "1:27:26", "throughput": 5557.51, "total_tokens": 10136864} {"current_steps": 16635, "total_steps": 64460, "loss": 0.2344, "lr": 9.258163576027137e-06, "epoch": 5.161340366118523, "percentage": 25.81, "elapsed_time": "0:30:24", "remaining_time": "1:27:25", "throughput": 5557.8, "total_tokens": 10140576} {"current_steps": 16640, "total_steps": 64460, "loss": 0.2289, "lr": 9.257453836351412e-06, "epoch": 5.16289171579274, "percentage": 25.81, "elapsed_time": "0:30:25", "remaining_time": "1:27:24", "throughput": 5558.03, "total_tokens": 10143936} {"current_steps": 16645, "total_steps": 64460, "loss": 0.2331, "lr": 9.256743784553905e-06, "epoch": 5.164443065466957, "percentage": 25.82, "elapsed_time": "0:30:25", "remaining_time": "1:27:24", "throughput": 5558.09, "total_tokens": 10146688} {"current_steps": 16650, "total_steps": 64460, "loss": 0.2288, "lr": 9.25603342068667e-06, "epoch": 5.1659944151411725, "percentage": 25.83, "elapsed_time": "0:30:26", "remaining_time": "1:27:23", "throughput": 5558.2, "total_tokens": 10149760} {"current_steps": 16655, "total_steps": 64460, "loss": 0.242, "lr": 9.255322744801787e-06, "epoch": 5.167545764815389, "percentage": 25.84, "elapsed_time": "0:30:26", "remaining_time": "1:27:22", "throughput": 5558.32, "total_tokens": 10152736} {"current_steps": 16660, "total_steps": 64460, "loss": 0.2177, "lr": 9.254611756951355e-06, "epoch": 5.169097114489606, "percentage": 25.85, "elapsed_time": "0:30:27", "remaining_time": "1:27:22", "throughput": 5558.43, "total_tokens": 10155648} {"current_steps": 16665, "total_steps": 64460, "loss": 0.2199, "lr": 9.253900457187498e-06, "epoch": 5.170648464163823, "percentage": 25.85, "elapsed_time": "0:30:27", "remaining_time": "1:27:21", "throughput": 5558.54, "total_tokens": 10158688} {"current_steps": 16670, "total_steps": 64460, "loss": 0.2466, "lr": 9.253188845562368e-06, "epoch": 5.172199813838039, "percentage": 25.86, "elapsed_time": "0:30:28", "remaining_time": "1:27:20", "throughput": 5558.82, "total_tokens": 10162112} {"current_steps": 16675, "total_steps": 64460, "loss": 0.2273, "lr": 9.252476922128128e-06, "epoch": 5.1737511635122555, "percentage": 25.87, "elapsed_time": "0:30:28", "remaining_time": "1:27:20", "throughput": 5558.99, "total_tokens": 10165216} {"current_steps": 16680, "total_steps": 64460, "loss": 0.229, "lr": 9.251764686936973e-06, "epoch": 5.175302513186472, "percentage": 25.88, "elapsed_time": "0:30:29", "remaining_time": "1:27:19", "throughput": 5559.19, "total_tokens": 10168480} {"current_steps": 16685, "total_steps": 64460, "loss": 0.2476, "lr": 9.251052140041117e-06, "epoch": 5.176853862860689, "percentage": 25.88, "elapsed_time": "0:30:29", "remaining_time": "1:27:18", "throughput": 5559.02, "total_tokens": 10171008} {"current_steps": 16690, "total_steps": 64460, "loss": 0.2136, "lr": 9.250339281492801e-06, "epoch": 5.178405212534905, "percentage": 25.89, "elapsed_time": "0:30:30", "remaining_time": "1:27:18", "throughput": 5559.03, "total_tokens": 10173792} {"current_steps": 16695, "total_steps": 64460, "loss": 0.2285, "lr": 9.249626111344283e-06, "epoch": 5.179956562209122, "percentage": 25.9, "elapsed_time": "0:30:30", "remaining_time": "1:27:17", "throughput": 5558.97, "total_tokens": 10176224} {"current_steps": 16700, "total_steps": 64460, "loss": 0.2234, "lr": 9.248912629647849e-06, "epoch": 5.1815079118833385, "percentage": 25.91, "elapsed_time": "0:30:31", "remaining_time": "1:27:16", "throughput": 5558.92, "total_tokens": 10178688} {"current_steps": 16705, "total_steps": 64460, "loss": 0.2201, "lr": 9.248198836455801e-06, "epoch": 5.183059261557555, "percentage": 25.92, "elapsed_time": "0:30:31", "remaining_time": "1:27:15", "throughput": 5558.99, "total_tokens": 10181728} {"current_steps": 16710, "total_steps": 64460, "loss": 0.2405, "lr": 9.247484731820475e-06, "epoch": 5.184610611231772, "percentage": 25.92, "elapsed_time": "0:30:32", "remaining_time": "1:27:15", "throughput": 5559.18, "total_tokens": 10185248} {"current_steps": 16715, "total_steps": 64460, "loss": 0.2408, "lr": 9.24677031579422e-06, "epoch": 5.186161960905988, "percentage": 25.93, "elapsed_time": "0:30:32", "remaining_time": "1:27:14", "throughput": 5559.04, "total_tokens": 10187584} {"current_steps": 16720, "total_steps": 64460, "loss": 0.2284, "lr": 9.246055588429412e-06, "epoch": 5.187713310580205, "percentage": 25.94, "elapsed_time": "0:30:33", "remaining_time": "1:27:13", "throughput": 5559.04, "total_tokens": 10190176} {"current_steps": 16725, "total_steps": 64460, "loss": 0.2443, "lr": 9.24534054977845e-06, "epoch": 5.1892646602544215, "percentage": 25.95, "elapsed_time": "0:30:33", "remaining_time": "1:27:13", "throughput": 5558.94, "total_tokens": 10192576} {"current_steps": 16730, "total_steps": 64460, "loss": 0.2201, "lr": 9.244625199893751e-06, "epoch": 5.190816009928638, "percentage": 25.95, "elapsed_time": "0:30:34", "remaining_time": "1:27:12", "throughput": 5559.09, "total_tokens": 10195680} {"current_steps": 16735, "total_steps": 64460, "loss": 0.243, "lr": 9.24390953882776e-06, "epoch": 5.192367359602854, "percentage": 25.96, "elapsed_time": "0:30:34", "remaining_time": "1:27:11", "throughput": 5559.13, "total_tokens": 10198432} {"current_steps": 16740, "total_steps": 64460, "loss": 0.2222, "lr": 9.243193566632947e-06, "epoch": 5.193918709277071, "percentage": 25.97, "elapsed_time": "0:30:35", "remaining_time": "1:27:11", "throughput": 5559.15, "total_tokens": 10201152} {"current_steps": 16745, "total_steps": 64460, "loss": 0.2231, "lr": 9.242477283361796e-06, "epoch": 5.195470058951288, "percentage": 25.98, "elapsed_time": "0:30:35", "remaining_time": "1:27:10", "throughput": 5559.06, "total_tokens": 10203552} {"current_steps": 16750, "total_steps": 64460, "loss": 0.2272, "lr": 9.241760689066826e-06, "epoch": 5.197021408625504, "percentage": 25.99, "elapsed_time": "0:30:35", "remaining_time": "1:27:09", "throughput": 5558.96, "total_tokens": 10205888} {"current_steps": 16755, "total_steps": 64460, "loss": 0.2311, "lr": 9.241043783800563e-06, "epoch": 5.19857275829972, "percentage": 25.99, "elapsed_time": "0:30:36", "remaining_time": "1:27:08", "throughput": 5559.07, "total_tokens": 10209248} {"current_steps": 16760, "total_steps": 64460, "loss": 0.2352, "lr": 9.240326567615572e-06, "epoch": 5.200124107973937, "percentage": 26.0, "elapsed_time": "0:30:36", "remaining_time": "1:27:08", "throughput": 5559.16, "total_tokens": 10212000} {"current_steps": 16765, "total_steps": 64460, "loss": 0.2353, "lr": 9.23960904056443e-06, "epoch": 5.201675457648154, "percentage": 26.01, "elapsed_time": "0:30:37", "remaining_time": "1:27:07", "throughput": 5559.05, "total_tokens": 10214464} {"current_steps": 16770, "total_steps": 64460, "loss": 0.2198, "lr": 9.23889120269974e-06, "epoch": 5.203226807322371, "percentage": 26.02, "elapsed_time": "0:30:37", "remaining_time": "1:27:06", "throughput": 5558.94, "total_tokens": 10217056} {"current_steps": 16775, "total_steps": 64460, "loss": 0.2297, "lr": 9.23817305407413e-06, "epoch": 5.204778156996587, "percentage": 26.02, "elapsed_time": "0:30:38", "remaining_time": "1:27:06", "throughput": 5558.9, "total_tokens": 10219744} {"current_steps": 16780, "total_steps": 64460, "loss": 0.2361, "lr": 9.237454594740245e-06, "epoch": 5.206329506670803, "percentage": 26.03, "elapsed_time": "0:30:39", "remaining_time": "1:27:05", "throughput": 5558.63, "total_tokens": 10222752} {"current_steps": 16785, "total_steps": 64460, "loss": 0.2378, "lr": 9.236735824750763e-06, "epoch": 5.20788085634502, "percentage": 26.04, "elapsed_time": "0:30:39", "remaining_time": "1:27:05", "throughput": 5558.26, "total_tokens": 10225248} {"current_steps": 16790, "total_steps": 64460, "loss": 0.2368, "lr": 9.236016744158371e-06, "epoch": 5.209432206019237, "percentage": 26.05, "elapsed_time": "0:30:40", "remaining_time": "1:27:04", "throughput": 5558.13, "total_tokens": 10227744} {"current_steps": 16795, "total_steps": 64460, "loss": 0.2323, "lr": 9.235297353015793e-06, "epoch": 5.210983555693454, "percentage": 26.05, "elapsed_time": "0:30:40", "remaining_time": "1:27:03", "throughput": 5558.17, "total_tokens": 10230912} {"current_steps": 16800, "total_steps": 64460, "loss": 0.234, "lr": 9.234577651375763e-06, "epoch": 5.2125349053676695, "percentage": 26.06, "elapsed_time": "0:30:41", "remaining_time": "1:27:03", "throughput": 5558.21, "total_tokens": 10233824} {"current_steps": 16805, "total_steps": 64460, "loss": 0.2309, "lr": 9.233857639291048e-06, "epoch": 5.214086255041886, "percentage": 26.07, "elapsed_time": "0:30:41", "remaining_time": "1:27:02", "throughput": 5558.19, "total_tokens": 10236576} {"current_steps": 16810, "total_steps": 64460, "loss": 0.2339, "lr": 9.233137316814431e-06, "epoch": 5.215637604716103, "percentage": 26.08, "elapsed_time": "0:30:42", "remaining_time": "1:27:01", "throughput": 5558.16, "total_tokens": 10239264} {"current_steps": 16815, "total_steps": 64460, "loss": 0.2325, "lr": 9.23241668399872e-06, "epoch": 5.21718895439032, "percentage": 26.09, "elapsed_time": "0:30:42", "remaining_time": "1:27:01", "throughput": 5558.45, "total_tokens": 10243456} {"current_steps": 16820, "total_steps": 64460, "loss": 0.2303, "lr": 9.231695740896749e-06, "epoch": 5.218740304064536, "percentage": 26.09, "elapsed_time": "0:30:43", "remaining_time": "1:27:02", "throughput": 5558.52, "total_tokens": 10248448} {"current_steps": 16825, "total_steps": 64460, "loss": 0.2345, "lr": 9.230974487561367e-06, "epoch": 5.2202916537387525, "percentage": 26.1, "elapsed_time": "0:30:44", "remaining_time": "1:27:01", "throughput": 5558.35, "total_tokens": 10250784} {"current_steps": 16830, "total_steps": 64460, "loss": 0.2329, "lr": 9.230252924045455e-06, "epoch": 5.221843003412969, "percentage": 26.11, "elapsed_time": "0:30:44", "remaining_time": "1:27:00", "throughput": 5558.4, "total_tokens": 10253600} {"current_steps": 16835, "total_steps": 64460, "loss": 0.2298, "lr": 9.229531050401908e-06, "epoch": 5.223394353087186, "percentage": 26.12, "elapsed_time": "0:30:45", "remaining_time": "1:27:00", "throughput": 5558.61, "total_tokens": 10256960} {"current_steps": 16840, "total_steps": 64460, "loss": 0.2309, "lr": 9.22880886668365e-06, "epoch": 5.224945702761403, "percentage": 26.12, "elapsed_time": "0:30:45", "remaining_time": "1:26:59", "throughput": 5558.57, "total_tokens": 10259776} {"current_steps": 16845, "total_steps": 64460, "loss": 0.234, "lr": 9.228086372943627e-06, "epoch": 5.226497052435619, "percentage": 26.13, "elapsed_time": "0:30:46", "remaining_time": "1:26:58", "throughput": 5558.49, "total_tokens": 10262464} {"current_steps": 16850, "total_steps": 64460, "loss": 0.231, "lr": 9.227363569234804e-06, "epoch": 5.2280484021098355, "percentage": 26.14, "elapsed_time": "0:30:46", "remaining_time": "1:26:58", "throughput": 5558.69, "total_tokens": 10266240} {"current_steps": 16855, "total_steps": 64460, "loss": 0.2314, "lr": 9.226640455610173e-06, "epoch": 5.229599751784052, "percentage": 26.15, "elapsed_time": "0:30:47", "remaining_time": "1:26:58", "throughput": 5558.79, "total_tokens": 10269856} {"current_steps": 16860, "total_steps": 64460, "loss": 0.2301, "lr": 9.225917032122743e-06, "epoch": 5.231151101458269, "percentage": 26.16, "elapsed_time": "0:30:48", "remaining_time": "1:26:57", "throughput": 5558.75, "total_tokens": 10272768} {"current_steps": 16865, "total_steps": 64460, "loss": 0.23, "lr": 9.225193298825555e-06, "epoch": 5.232702451132485, "percentage": 26.16, "elapsed_time": "0:30:48", "remaining_time": "1:26:56", "throughput": 5558.38, "total_tokens": 10274880} {"current_steps": 16870, "total_steps": 64460, "loss": 0.2357, "lr": 9.224469255771663e-06, "epoch": 5.234253800806702, "percentage": 26.17, "elapsed_time": "0:30:49", "remaining_time": "1:26:56", "throughput": 5558.3, "total_tokens": 10277632} {"current_steps": 16875, "total_steps": 64460, "loss": 0.2309, "lr": 9.223744903014149e-06, "epoch": 5.235805150480918, "percentage": 26.18, "elapsed_time": "0:30:49", "remaining_time": "1:26:55", "throughput": 5558.15, "total_tokens": 10280480} {"current_steps": 16880, "total_steps": 64460, "loss": 0.2309, "lr": 9.223020240606118e-06, "epoch": 5.237356500155135, "percentage": 26.19, "elapsed_time": "0:30:50", "remaining_time": "1:26:54", "throughput": 5558.18, "total_tokens": 10283264} {"current_steps": 16885, "total_steps": 64460, "loss": 0.2298, "lr": 9.222295268600695e-06, "epoch": 5.238907849829351, "percentage": 26.19, "elapsed_time": "0:30:50", "remaining_time": "1:26:54", "throughput": 5558.12, "total_tokens": 10286016} {"current_steps": 16890, "total_steps": 64460, "loss": 0.2309, "lr": 9.221569987051029e-06, "epoch": 5.240459199503568, "percentage": 26.2, "elapsed_time": "0:30:51", "remaining_time": "1:26:53", "throughput": 5557.95, "total_tokens": 10288320} {"current_steps": 16895, "total_steps": 64460, "loss": 0.2373, "lr": 9.220844396010292e-06, "epoch": 5.242010549177785, "percentage": 26.21, "elapsed_time": "0:30:51", "remaining_time": "1:26:53", "throughput": 5558.24, "total_tokens": 10291968} {"current_steps": 16900, "total_steps": 64460, "loss": 0.233, "lr": 9.220118495531678e-06, "epoch": 5.243561898852001, "percentage": 26.22, "elapsed_time": "0:30:52", "remaining_time": "1:26:52", "throughput": 5558.27, "total_tokens": 10295008} {"current_steps": 16905, "total_steps": 64460, "loss": 0.2304, "lr": 9.219392285668407e-06, "epoch": 5.245113248526218, "percentage": 26.23, "elapsed_time": "0:30:52", "remaining_time": "1:26:51", "throughput": 5558.17, "total_tokens": 10297472} {"current_steps": 16910, "total_steps": 64460, "loss": 0.2315, "lr": 9.218665766473713e-06, "epoch": 5.246664598200434, "percentage": 26.23, "elapsed_time": "0:30:53", "remaining_time": "1:26:50", "throughput": 5558.04, "total_tokens": 10299840} {"current_steps": 16915, "total_steps": 64460, "loss": 0.2283, "lr": 9.217938938000865e-06, "epoch": 5.248215947874651, "percentage": 26.24, "elapsed_time": "0:30:53", "remaining_time": "1:26:50", "throughput": 5558.11, "total_tokens": 10302656} {"current_steps": 16920, "total_steps": 64460, "loss": 0.2309, "lr": 9.217211800303143e-06, "epoch": 5.249767297548868, "percentage": 26.25, "elapsed_time": "0:30:54", "remaining_time": "1:26:49", "throughput": 5558.06, "total_tokens": 10305312} {"current_steps": 16925, "total_steps": 64460, "loss": 0.2295, "lr": 9.216484353433857e-06, "epoch": 5.251318647223084, "percentage": 26.26, "elapsed_time": "0:30:54", "remaining_time": "1:26:48", "throughput": 5557.95, "total_tokens": 10307680} {"current_steps": 16930, "total_steps": 64460, "loss": 0.2363, "lr": 9.215756597446338e-06, "epoch": 5.2528699968973, "percentage": 26.26, "elapsed_time": "0:30:55", "remaining_time": "1:26:48", "throughput": 5558.33, "total_tokens": 10312000} {"current_steps": 16935, "total_steps": 64460, "loss": 0.2295, "lr": 9.215028532393939e-06, "epoch": 5.254421346571517, "percentage": 26.27, "elapsed_time": "0:30:55", "remaining_time": "1:26:48", "throughput": 5558.73, "total_tokens": 10316416} {"current_steps": 16940, "total_steps": 64460, "loss": 0.2348, "lr": 9.214300158330034e-06, "epoch": 5.255972696245734, "percentage": 26.28, "elapsed_time": "0:30:56", "remaining_time": "1:26:47", "throughput": 5558.44, "total_tokens": 10318432} {"current_steps": 16945, "total_steps": 64460, "loss": 0.2304, "lr": 9.213571475308024e-06, "epoch": 5.257524045919951, "percentage": 26.29, "elapsed_time": "0:30:56", "remaining_time": "1:26:46", "throughput": 5558.37, "total_tokens": 10320992} {"current_steps": 16950, "total_steps": 64460, "loss": 0.2326, "lr": 9.212842483381326e-06, "epoch": 5.2590753955941665, "percentage": 26.3, "elapsed_time": "0:30:57", "remaining_time": "1:26:45", "throughput": 5558.24, "total_tokens": 10323456} {"current_steps": 16955, "total_steps": 64460, "loss": 0.23, "lr": 9.212113182603388e-06, "epoch": 5.260626745268383, "percentage": 26.3, "elapsed_time": "0:30:58", "remaining_time": "1:26:45", "throughput": 5558.67, "total_tokens": 10328032} {"current_steps": 16960, "total_steps": 64460, "loss": 0.2299, "lr": 9.211383573027675e-06, "epoch": 5.2621780949426, "percentage": 26.31, "elapsed_time": "0:30:58", "remaining_time": "1:26:45", "throughput": 5558.56, "total_tokens": 10331136} {"current_steps": 16965, "total_steps": 64460, "loss": 0.2331, "lr": 9.210653654707675e-06, "epoch": 5.263729444616817, "percentage": 26.32, "elapsed_time": "0:30:59", "remaining_time": "1:26:44", "throughput": 5558.63, "total_tokens": 10334272} {"current_steps": 16970, "total_steps": 64460, "loss": 0.232, "lr": 9.2099234276969e-06, "epoch": 5.265280794291034, "percentage": 26.33, "elapsed_time": "0:30:59", "remaining_time": "1:26:44", "throughput": 5558.39, "total_tokens": 10336640} {"current_steps": 16975, "total_steps": 64460, "loss": 0.2335, "lr": 9.209192892048887e-06, "epoch": 5.2668321439652495, "percentage": 26.33, "elapsed_time": "0:31:00", "remaining_time": "1:26:43", "throughput": 5558.3, "total_tokens": 10339104} {"current_steps": 16980, "total_steps": 64460, "loss": 0.231, "lr": 9.208462047817191e-06, "epoch": 5.268383493639466, "percentage": 26.34, "elapsed_time": "0:31:00", "remaining_time": "1:26:43", "throughput": 5558.35, "total_tokens": 10342560} {"current_steps": 16985, "total_steps": 64460, "loss": 0.2325, "lr": 9.207730895055389e-06, "epoch": 5.269934843313683, "percentage": 26.35, "elapsed_time": "0:31:01", "remaining_time": "1:26:42", "throughput": 5558.13, "total_tokens": 10344768} {"current_steps": 16990, "total_steps": 64460, "loss": 0.2295, "lr": 9.206999433817086e-06, "epoch": 5.2714861929879, "percentage": 26.36, "elapsed_time": "0:31:01", "remaining_time": "1:26:41", "throughput": 5558.12, "total_tokens": 10347648} {"current_steps": 16995, "total_steps": 64460, "loss": 0.2347, "lr": 9.206267664155906e-06, "epoch": 5.273037542662116, "percentage": 26.37, "elapsed_time": "0:31:02", "remaining_time": "1:26:41", "throughput": 5558.41, "total_tokens": 10351232} {"current_steps": 17000, "total_steps": 64460, "loss": 0.2336, "lr": 9.205535586125498e-06, "epoch": 5.274588892336332, "percentage": 26.37, "elapsed_time": "0:31:02", "remaining_time": "1:26:40", "throughput": 5558.49, "total_tokens": 10354176} {"current_steps": 17005, "total_steps": 64460, "loss": 0.2278, "lr": 9.20480319977953e-06, "epoch": 5.276140242010549, "percentage": 26.38, "elapsed_time": "0:31:03", "remaining_time": "1:26:39", "throughput": 5558.7, "total_tokens": 10357376} {"current_steps": 17010, "total_steps": 64460, "loss": 0.2341, "lr": 9.204070505171693e-06, "epoch": 5.277691591684766, "percentage": 26.39, "elapsed_time": "0:31:03", "remaining_time": "1:26:39", "throughput": 5558.77, "total_tokens": 10360576} {"current_steps": 17015, "total_steps": 64460, "loss": 0.2299, "lr": 9.203337502355707e-06, "epoch": 5.279242941358982, "percentage": 26.4, "elapsed_time": "0:31:04", "remaining_time": "1:26:38", "throughput": 5558.66, "total_tokens": 10363104} {"current_steps": 17020, "total_steps": 64460, "loss": 0.2331, "lr": 9.202604191385307e-06, "epoch": 5.280794291033199, "percentage": 26.4, "elapsed_time": "0:31:04", "remaining_time": "1:26:37", "throughput": 5558.76, "total_tokens": 10365984} {"current_steps": 17025, "total_steps": 64460, "loss": 0.239, "lr": 9.201870572314252e-06, "epoch": 5.282345640707415, "percentage": 26.41, "elapsed_time": "0:31:05", "remaining_time": "1:26:37", "throughput": 5558.81, "total_tokens": 10368800} {"current_steps": 17030, "total_steps": 64460, "loss": 0.2284, "lr": 9.201136645196327e-06, "epoch": 5.283896990381632, "percentage": 26.42, "elapsed_time": "0:31:05", "remaining_time": "1:26:36", "throughput": 5559.0, "total_tokens": 10372000} {"current_steps": 17035, "total_steps": 64460, "loss": 0.2289, "lr": 9.200402410085338e-06, "epoch": 5.285448340055849, "percentage": 26.43, "elapsed_time": "0:31:06", "remaining_time": "1:26:35", "throughput": 5558.99, "total_tokens": 10374880} {"current_steps": 17040, "total_steps": 64460, "loss": 0.2305, "lr": 9.199667867035111e-06, "epoch": 5.286999689730065, "percentage": 26.43, "elapsed_time": "0:31:06", "remaining_time": "1:26:35", "throughput": 5558.94, "total_tokens": 10377568} {"current_steps": 17045, "total_steps": 64460, "loss": 0.2351, "lr": 9.198933016099499e-06, "epoch": 5.288551039404282, "percentage": 26.44, "elapsed_time": "0:31:07", "remaining_time": "1:26:34", "throughput": 5558.95, "total_tokens": 10380640} {"current_steps": 17050, "total_steps": 64460, "loss": 0.231, "lr": 9.198197857332371e-06, "epoch": 5.290102389078498, "percentage": 26.45, "elapsed_time": "0:31:07", "remaining_time": "1:26:33", "throughput": 5558.9, "total_tokens": 10383200} {"current_steps": 17055, "total_steps": 64460, "loss": 0.2309, "lr": 9.19746239078763e-06, "epoch": 5.291653738752715, "percentage": 26.46, "elapsed_time": "0:31:08", "remaining_time": "1:26:33", "throughput": 5559.23, "total_tokens": 10387968} {"current_steps": 17060, "total_steps": 64460, "loss": 0.2353, "lr": 9.196726616519188e-06, "epoch": 5.293205088426931, "percentage": 26.47, "elapsed_time": "0:31:09", "remaining_time": "1:26:33", "throughput": 5559.36, "total_tokens": 10390944} {"current_steps": 17065, "total_steps": 64460, "loss": 0.2294, "lr": 9.195990534580988e-06, "epoch": 5.294756438101148, "percentage": 26.47, "elapsed_time": "0:31:09", "remaining_time": "1:26:32", "throughput": 5559.61, "total_tokens": 10394688} {"current_steps": 17070, "total_steps": 64460, "loss": 0.2311, "lr": 9.195254145026995e-06, "epoch": 5.296307787775365, "percentage": 26.48, "elapsed_time": "0:31:10", "remaining_time": "1:26:32", "throughput": 5559.46, "total_tokens": 10397216} {"current_steps": 17075, "total_steps": 64460, "loss": 0.2322, "lr": 9.194517447911193e-06, "epoch": 5.297859137449581, "percentage": 26.49, "elapsed_time": "0:31:10", "remaining_time": "1:26:31", "throughput": 5559.43, "total_tokens": 10399808} {"current_steps": 17080, "total_steps": 64460, "loss": 0.2274, "lr": 9.193780443287593e-06, "epoch": 5.299410487123797, "percentage": 26.5, "elapsed_time": "0:31:11", "remaining_time": "1:26:30", "throughput": 5559.46, "total_tokens": 10402464} {"current_steps": 17085, "total_steps": 64460, "loss": 0.2296, "lr": 9.193043131210224e-06, "epoch": 5.300961836798014, "percentage": 26.5, "elapsed_time": "0:31:11", "remaining_time": "1:26:29", "throughput": 5559.72, "total_tokens": 10406016} {"current_steps": 17090, "total_steps": 64460, "loss": 0.231, "lr": 9.192305511733141e-06, "epoch": 5.302513186472231, "percentage": 26.51, "elapsed_time": "0:31:12", "remaining_time": "1:26:29", "throughput": 5560.02, "total_tokens": 10409536} {"current_steps": 17095, "total_steps": 64460, "loss": 0.2276, "lr": 9.191567584910418e-06, "epoch": 5.304064536146448, "percentage": 26.52, "elapsed_time": "0:31:12", "remaining_time": "1:26:28", "throughput": 5560.15, "total_tokens": 10412672} {"current_steps": 17100, "total_steps": 64460, "loss": 0.2309, "lr": 9.190829350796157e-06, "epoch": 5.305615885820664, "percentage": 26.53, "elapsed_time": "0:31:13", "remaining_time": "1:26:28", "throughput": 5560.15, "total_tokens": 10415392} {"current_steps": 17105, "total_steps": 64460, "loss": 0.2192, "lr": 9.190090809444476e-06, "epoch": 5.30716723549488, "percentage": 26.54, "elapsed_time": "0:31:13", "remaining_time": "1:26:27", "throughput": 5560.12, "total_tokens": 10418048} {"current_steps": 17110, "total_steps": 64460, "loss": 0.2184, "lr": 9.189351960909524e-06, "epoch": 5.308718585169097, "percentage": 26.54, "elapsed_time": "0:31:14", "remaining_time": "1:26:26", "throughput": 5560.0, "total_tokens": 10420608} {"current_steps": 17115, "total_steps": 64460, "loss": 0.2278, "lr": 9.188612805245461e-06, "epoch": 5.310269934843314, "percentage": 26.55, "elapsed_time": "0:31:14", "remaining_time": "1:26:26", "throughput": 5560.07, "total_tokens": 10423712} {"current_steps": 17120, "total_steps": 64460, "loss": 0.2364, "lr": 9.18787334250648e-06, "epoch": 5.3118212845175306, "percentage": 26.56, "elapsed_time": "0:31:15", "remaining_time": "1:26:26", "throughput": 5560.61, "total_tokens": 10430400} {"current_steps": 17125, "total_steps": 64460, "loss": 0.2161, "lr": 9.18713357274679e-06, "epoch": 5.313372634191746, "percentage": 26.57, "elapsed_time": "0:31:16", "remaining_time": "1:26:26", "throughput": 5560.59, "total_tokens": 10433248} {"current_steps": 17130, "total_steps": 64460, "loss": 0.2328, "lr": 9.186393496020627e-06, "epoch": 5.314923983865963, "percentage": 26.57, "elapsed_time": "0:31:16", "remaining_time": "1:26:25", "throughput": 5560.33, "total_tokens": 10435328} {"current_steps": 17135, "total_steps": 64460, "loss": 0.235, "lr": 9.185653112382245e-06, "epoch": 5.31647533354018, "percentage": 26.58, "elapsed_time": "0:31:17", "remaining_time": "1:26:24", "throughput": 5560.4, "total_tokens": 10438272} {"current_steps": 17140, "total_steps": 64460, "loss": 0.2285, "lr": 9.184912421885925e-06, "epoch": 5.318026683214397, "percentage": 26.59, "elapsed_time": "0:31:17", "remaining_time": "1:26:24", "throughput": 5560.65, "total_tokens": 10442016} {"current_steps": 17145, "total_steps": 64460, "loss": 0.2343, "lr": 9.184171424585968e-06, "epoch": 5.319578032888613, "percentage": 26.6, "elapsed_time": "0:31:18", "remaining_time": "1:26:23", "throughput": 5560.72, "total_tokens": 10445568} {"current_steps": 17150, "total_steps": 64460, "loss": 0.2374, "lr": 9.183430120536698e-06, "epoch": 5.321129382562829, "percentage": 26.61, "elapsed_time": "0:31:18", "remaining_time": "1:26:23", "throughput": 5560.53, "total_tokens": 10447904} {"current_steps": 17155, "total_steps": 64460, "loss": 0.2242, "lr": 9.182688509792461e-06, "epoch": 5.322680732237046, "percentage": 26.61, "elapsed_time": "0:31:19", "remaining_time": "1:26:22", "throughput": 5560.43, "total_tokens": 10450688} {"current_steps": 17160, "total_steps": 64460, "loss": 0.2414, "lr": 9.181946592407625e-06, "epoch": 5.324232081911263, "percentage": 26.62, "elapsed_time": "0:31:20", "remaining_time": "1:26:22", "throughput": 5560.71, "total_tokens": 10454240} {"current_steps": 17165, "total_steps": 64460, "loss": 0.2306, "lr": 9.181204368436583e-06, "epoch": 5.32578343158548, "percentage": 26.63, "elapsed_time": "0:31:20", "remaining_time": "1:26:21", "throughput": 5560.69, "total_tokens": 10456928} {"current_steps": 17170, "total_steps": 64460, "loss": 0.2297, "lr": 9.180461837933748e-06, "epoch": 5.327334781259696, "percentage": 26.64, "elapsed_time": "0:31:21", "remaining_time": "1:26:21", "throughput": 5561.17, "total_tokens": 10462496} {"current_steps": 17175, "total_steps": 64460, "loss": 0.2325, "lr": 9.179719000953556e-06, "epoch": 5.328886130933912, "percentage": 26.64, "elapsed_time": "0:31:21", "remaining_time": "1:26:21", "throughput": 5561.23, "total_tokens": 10465696} {"current_steps": 17180, "total_steps": 64460, "loss": 0.2184, "lr": 9.178975857550465e-06, "epoch": 5.330437480608129, "percentage": 26.65, "elapsed_time": "0:31:22", "remaining_time": "1:26:20", "throughput": 5561.24, "total_tokens": 10468352} {"current_steps": 17185, "total_steps": 64460, "loss": 0.2339, "lr": 9.178232407778958e-06, "epoch": 5.331988830282346, "percentage": 26.66, "elapsed_time": "0:31:22", "remaining_time": "1:26:19", "throughput": 5561.23, "total_tokens": 10470944} {"current_steps": 17190, "total_steps": 64460, "loss": 0.2345, "lr": 9.177488651693536e-06, "epoch": 5.333540179956562, "percentage": 26.67, "elapsed_time": "0:31:23", "remaining_time": "1:26:19", "throughput": 5561.31, "total_tokens": 10474432} {"current_steps": 17195, "total_steps": 64460, "loss": 0.2382, "lr": 9.17674458934873e-06, "epoch": 5.335091529630779, "percentage": 26.68, "elapsed_time": "0:31:23", "remaining_time": "1:26:18", "throughput": 5561.55, "total_tokens": 10477824} {"current_steps": 17200, "total_steps": 64460, "loss": 0.2311, "lr": 9.176000220799084e-06, "epoch": 5.336642879304995, "percentage": 26.68, "elapsed_time": "0:31:24", "remaining_time": "1:26:17", "throughput": 5561.21, "total_tokens": 10479872} {"current_steps": 17205, "total_steps": 64460, "loss": 0.2316, "lr": 9.175255546099172e-06, "epoch": 5.338194228979212, "percentage": 26.69, "elapsed_time": "0:31:25", "remaining_time": "1:26:17", "throughput": 5561.43, "total_tokens": 10484032} {"current_steps": 17210, "total_steps": 64460, "loss": 0.2381, "lr": 9.174510565303583e-06, "epoch": 5.339745578653428, "percentage": 26.7, "elapsed_time": "0:31:25", "remaining_time": "1:26:16", "throughput": 5561.33, "total_tokens": 10486560} {"current_steps": 17215, "total_steps": 64460, "loss": 0.222, "lr": 9.173765278466938e-06, "epoch": 5.341296928327645, "percentage": 26.71, "elapsed_time": "0:31:26", "remaining_time": "1:26:16", "throughput": 5561.17, "total_tokens": 10488992} {"current_steps": 17220, "total_steps": 64460, "loss": 0.2281, "lr": 9.173019685643874e-06, "epoch": 5.342848278001862, "percentage": 26.71, "elapsed_time": "0:31:26", "remaining_time": "1:26:15", "throughput": 5561.04, "total_tokens": 10491584} {"current_steps": 17225, "total_steps": 64460, "loss": 0.2254, "lr": 9.172273786889049e-06, "epoch": 5.344399627676078, "percentage": 26.72, "elapsed_time": "0:31:27", "remaining_time": "1:26:15", "throughput": 5561.24, "total_tokens": 10495168} {"current_steps": 17230, "total_steps": 64460, "loss": 0.232, "lr": 9.171527582257149e-06, "epoch": 5.345950977350295, "percentage": 26.73, "elapsed_time": "0:31:27", "remaining_time": "1:26:14", "throughput": 5561.41, "total_tokens": 10498304} {"current_steps": 17235, "total_steps": 64460, "loss": 0.2372, "lr": 9.17078107180288e-06, "epoch": 5.347502327024511, "percentage": 26.74, "elapsed_time": "0:31:28", "remaining_time": "1:26:13", "throughput": 5561.45, "total_tokens": 10501120} {"current_steps": 17240, "total_steps": 64460, "loss": 0.23, "lr": 9.170034255580969e-06, "epoch": 5.349053676698728, "percentage": 26.75, "elapsed_time": "0:31:28", "remaining_time": "1:26:13", "throughput": 5561.33, "total_tokens": 10503648} {"current_steps": 17245, "total_steps": 64460, "loss": 0.2255, "lr": 9.169287133646166e-06, "epoch": 5.3506050263729446, "percentage": 26.75, "elapsed_time": "0:31:29", "remaining_time": "1:26:12", "throughput": 5561.09, "total_tokens": 10506016} {"current_steps": 17250, "total_steps": 64460, "loss": 0.234, "lr": 9.168539706053243e-06, "epoch": 5.352156376047161, "percentage": 26.76, "elapsed_time": "0:31:29", "remaining_time": "1:26:11", "throughput": 5561.32, "total_tokens": 10509408} {"current_steps": 17255, "total_steps": 64460, "loss": 0.2349, "lr": 9.167791972856997e-06, "epoch": 5.353707725721377, "percentage": 26.77, "elapsed_time": "0:31:30", "remaining_time": "1:26:11", "throughput": 5561.57, "total_tokens": 10512992} {"current_steps": 17260, "total_steps": 64460, "loss": 0.2373, "lr": 9.167043934112247e-06, "epoch": 5.355259075395594, "percentage": 26.78, "elapsed_time": "0:31:30", "remaining_time": "1:26:10", "throughput": 5561.21, "total_tokens": 10514912} {"current_steps": 17265, "total_steps": 64460, "loss": 0.2331, "lr": 9.166295589873831e-06, "epoch": 5.356810425069811, "percentage": 26.78, "elapsed_time": "0:31:31", "remaining_time": "1:26:10", "throughput": 5561.49, "total_tokens": 10518656} {"current_steps": 17270, "total_steps": 64460, "loss": 0.234, "lr": 9.165546940196612e-06, "epoch": 5.3583617747440275, "percentage": 26.79, "elapsed_time": "0:31:31", "remaining_time": "1:26:09", "throughput": 5561.7, "total_tokens": 10522208} {"current_steps": 17275, "total_steps": 64460, "loss": 0.2247, "lr": 9.164797985135473e-06, "epoch": 5.359913124418243, "percentage": 26.8, "elapsed_time": "0:31:32", "remaining_time": "1:26:08", "throughput": 5561.64, "total_tokens": 10524832} {"current_steps": 17280, "total_steps": 64460, "loss": 0.2223, "lr": 9.164048724745325e-06, "epoch": 5.36146447409246, "percentage": 26.81, "elapsed_time": "0:31:32", "remaining_time": "1:26:08", "throughput": 5561.85, "total_tokens": 10528128} {"current_steps": 17285, "total_steps": 64460, "loss": 0.2349, "lr": 9.163299159081097e-06, "epoch": 5.363015823766677, "percentage": 26.82, "elapsed_time": "0:31:33", "remaining_time": "1:26:07", "throughput": 5561.94, "total_tokens": 10531296} {"current_steps": 17290, "total_steps": 64460, "loss": 0.2282, "lr": 9.162549288197736e-06, "epoch": 5.364567173440894, "percentage": 26.82, "elapsed_time": "0:31:34", "remaining_time": "1:26:07", "throughput": 5562.19, "total_tokens": 10535648} {"current_steps": 17295, "total_steps": 64460, "loss": 0.2461, "lr": 9.161799112150223e-06, "epoch": 5.3661185231151105, "percentage": 26.83, "elapsed_time": "0:31:34", "remaining_time": "1:26:06", "throughput": 5562.08, "total_tokens": 10538144} {"current_steps": 17300, "total_steps": 64460, "loss": 0.2245, "lr": 9.16104863099355e-06, "epoch": 5.367669872789326, "percentage": 26.84, "elapsed_time": "0:31:35", "remaining_time": "1:26:06", "throughput": 5562.13, "total_tokens": 10540928} {"current_steps": 17305, "total_steps": 64460, "loss": 0.2298, "lr": 9.160297844782741e-06, "epoch": 5.369221222463543, "percentage": 26.85, "elapsed_time": "0:31:35", "remaining_time": "1:26:05", "throughput": 5562.04, "total_tokens": 10543392} {"current_steps": 17310, "total_steps": 64460, "loss": 0.2291, "lr": 9.159546753572833e-06, "epoch": 5.37077257213776, "percentage": 26.85, "elapsed_time": "0:31:36", "remaining_time": "1:26:05", "throughput": 5562.54, "total_tokens": 10548416} {"current_steps": 17315, "total_steps": 64460, "loss": 0.2316, "lr": 9.158795357418892e-06, "epoch": 5.372323921811977, "percentage": 26.86, "elapsed_time": "0:31:36", "remaining_time": "1:26:04", "throughput": 5562.45, "total_tokens": 10550912} {"current_steps": 17320, "total_steps": 64460, "loss": 0.2248, "lr": 9.158043656376004e-06, "epoch": 5.373875271486193, "percentage": 26.87, "elapsed_time": "0:31:37", "remaining_time": "1:26:03", "throughput": 5562.47, "total_tokens": 10553568} {"current_steps": 17325, "total_steps": 64460, "loss": 0.2342, "lr": 9.157291650499275e-06, "epoch": 5.375426621160409, "percentage": 26.88, "elapsed_time": "0:31:37", "remaining_time": "1:26:03", "throughput": 5562.14, "total_tokens": 10555840} {"current_steps": 17330, "total_steps": 64460, "loss": 0.2338, "lr": 9.156539339843841e-06, "epoch": 5.376977970834626, "percentage": 26.88, "elapsed_time": "0:31:38", "remaining_time": "1:26:02", "throughput": 5562.38, "total_tokens": 10559328} {"current_steps": 17335, "total_steps": 64460, "loss": 0.2314, "lr": 9.155786724464852e-06, "epoch": 5.378529320508843, "percentage": 26.89, "elapsed_time": "0:31:38", "remaining_time": "1:26:02", "throughput": 5562.65, "total_tokens": 10563040} {"current_steps": 17340, "total_steps": 64460, "loss": 0.2262, "lr": 9.155033804417483e-06, "epoch": 5.380080670183059, "percentage": 26.9, "elapsed_time": "0:31:39", "remaining_time": "1:26:01", "throughput": 5562.85, "total_tokens": 10566240} {"current_steps": 17345, "total_steps": 64460, "loss": 0.2358, "lr": 9.154280579756935e-06, "epoch": 5.381632019857276, "percentage": 26.91, "elapsed_time": "0:31:39", "remaining_time": "1:26:01", "throughput": 5563.02, "total_tokens": 10569664} {"current_steps": 17350, "total_steps": 64460, "loss": 0.2359, "lr": 9.153527050538426e-06, "epoch": 5.383183369531492, "percentage": 26.92, "elapsed_time": "0:31:40", "remaining_time": "1:26:00", "throughput": 5563.29, "total_tokens": 10573312} {"current_steps": 17355, "total_steps": 64460, "loss": 0.2312, "lr": 9.1527732168172e-06, "epoch": 5.384734719205709, "percentage": 26.92, "elapsed_time": "0:31:41", "remaining_time": "1:25:59", "throughput": 5563.25, "total_tokens": 10575968} {"current_steps": 17360, "total_steps": 64460, "loss": 0.2289, "lr": 9.152019078648517e-06, "epoch": 5.386286068879926, "percentage": 26.93, "elapsed_time": "0:31:41", "remaining_time": "1:25:59", "throughput": 5563.05, "total_tokens": 10578432} {"current_steps": 17365, "total_steps": 64460, "loss": 0.2278, "lr": 9.151264636087672e-06, "epoch": 5.387837418554142, "percentage": 26.94, "elapsed_time": "0:31:42", "remaining_time": "1:25:58", "throughput": 5563.01, "total_tokens": 10581376} {"current_steps": 17370, "total_steps": 64460, "loss": 0.2213, "lr": 9.15050988918997e-06, "epoch": 5.3893887682283586, "percentage": 26.95, "elapsed_time": "0:31:42", "remaining_time": "1:25:57", "throughput": 5562.78, "total_tokens": 10583712} {"current_steps": 17375, "total_steps": 64460, "loss": 0.245, "lr": 9.149754838010745e-06, "epoch": 5.390940117902575, "percentage": 26.95, "elapsed_time": "0:31:43", "remaining_time": "1:25:57", "throughput": 5562.85, "total_tokens": 10587232} {"current_steps": 17380, "total_steps": 64460, "loss": 0.2336, "lr": 9.148999482605347e-06, "epoch": 5.392491467576792, "percentage": 26.96, "elapsed_time": "0:31:43", "remaining_time": "1:25:56", "throughput": 5562.84, "total_tokens": 10590176} {"current_steps": 17385, "total_steps": 64460, "loss": 0.248, "lr": 9.148243823029158e-06, "epoch": 5.394042817251008, "percentage": 26.97, "elapsed_time": "0:31:44", "remaining_time": "1:25:56", "throughput": 5562.84, "total_tokens": 10593024} {"current_steps": 17390, "total_steps": 64460, "loss": 0.2286, "lr": 9.14748785933757e-06, "epoch": 5.395594166925225, "percentage": 26.98, "elapsed_time": "0:31:44", "remaining_time": "1:25:55", "throughput": 5562.98, "total_tokens": 10596800} {"current_steps": 17395, "total_steps": 64460, "loss": 0.2302, "lr": 9.146731591586013e-06, "epoch": 5.3971455165994415, "percentage": 26.99, "elapsed_time": "0:31:45", "remaining_time": "1:25:55", "throughput": 5563.07, "total_tokens": 10601056} {"current_steps": 17400, "total_steps": 64460, "loss": 0.2329, "lr": 9.145975019829924e-06, "epoch": 5.398696866273658, "percentage": 26.99, "elapsed_time": "0:31:46", "remaining_time": "1:25:55", "throughput": 5563.04, "total_tokens": 10603680} {"current_steps": 17405, "total_steps": 64460, "loss": 0.2348, "lr": 9.145218144124771e-06, "epoch": 5.400248215947874, "percentage": 27.0, "elapsed_time": "0:31:46", "remaining_time": "1:25:54", "throughput": 5562.9, "total_tokens": 10606272} {"current_steps": 17410, "total_steps": 64460, "loss": 0.2275, "lr": 9.14446096452604e-06, "epoch": 5.401799565622091, "percentage": 27.01, "elapsed_time": "0:31:47", "remaining_time": "1:25:54", "throughput": 5562.86, "total_tokens": 10609184} {"current_steps": 17415, "total_steps": 64460, "loss": 0.2312, "lr": 9.143703481089244e-06, "epoch": 5.403350915296308, "percentage": 27.02, "elapsed_time": "0:31:47", "remaining_time": "1:25:53", "throughput": 5562.95, "total_tokens": 10612320} {"current_steps": 17420, "total_steps": 64460, "loss": 0.2337, "lr": 9.142945693869914e-06, "epoch": 5.4049022649705245, "percentage": 27.02, "elapsed_time": "0:31:48", "remaining_time": "1:25:52", "throughput": 5562.84, "total_tokens": 10614720} {"current_steps": 17425, "total_steps": 64460, "loss": 0.2321, "lr": 9.142187602923605e-06, "epoch": 5.406453614644741, "percentage": 27.03, "elapsed_time": "0:31:48", "remaining_time": "1:25:52", "throughput": 5562.78, "total_tokens": 10617504} {"current_steps": 17430, "total_steps": 64460, "loss": 0.2336, "lr": 9.141429208305893e-06, "epoch": 5.408004964318957, "percentage": 27.04, "elapsed_time": "0:31:49", "remaining_time": "1:25:51", "throughput": 5562.99, "total_tokens": 10620704} {"current_steps": 17435, "total_steps": 64460, "loss": 0.23, "lr": 9.140670510072379e-06, "epoch": 5.409556313993174, "percentage": 27.05, "elapsed_time": "0:31:49", "remaining_time": "1:25:50", "throughput": 5563.03, "total_tokens": 10623872} {"current_steps": 17440, "total_steps": 64460, "loss": 0.2314, "lr": 9.139911508278682e-06, "epoch": 5.411107663667391, "percentage": 27.06, "elapsed_time": "0:31:50", "remaining_time": "1:25:50", "throughput": 5562.82, "total_tokens": 10625984} {"current_steps": 17445, "total_steps": 64460, "loss": 0.2335, "lr": 9.139152202980449e-06, "epoch": 5.4126590133416075, "percentage": 27.06, "elapsed_time": "0:31:50", "remaining_time": "1:25:49", "throughput": 5562.99, "total_tokens": 10629152} {"current_steps": 17450, "total_steps": 64460, "loss": 0.232, "lr": 9.138392594233344e-06, "epoch": 5.414210363015823, "percentage": 27.07, "elapsed_time": "0:31:51", "remaining_time": "1:25:48", "throughput": 5562.79, "total_tokens": 10631296} {"current_steps": 17455, "total_steps": 64460, "loss": 0.2316, "lr": 9.137632682093055e-06, "epoch": 5.41576171269004, "percentage": 27.08, "elapsed_time": "0:31:51", "remaining_time": "1:25:48", "throughput": 5563.29, "total_tokens": 10636000} {"current_steps": 17460, "total_steps": 64460, "loss": 0.2283, "lr": 9.136872466615294e-06, "epoch": 5.417313062364257, "percentage": 27.09, "elapsed_time": "0:31:52", "remaining_time": "1:25:47", "throughput": 5563.32, "total_tokens": 10638880} {"current_steps": 17465, "total_steps": 64460, "loss": 0.231, "lr": 9.136111947855795e-06, "epoch": 5.418864412038474, "percentage": 27.09, "elapsed_time": "0:31:52", "remaining_time": "1:25:47", "throughput": 5563.35, "total_tokens": 10641856} {"current_steps": 17470, "total_steps": 64460, "loss": 0.2314, "lr": 9.13535112587031e-06, "epoch": 5.42041576171269, "percentage": 27.1, "elapsed_time": "0:31:53", "remaining_time": "1:25:46", "throughput": 5563.43, "total_tokens": 10645056} {"current_steps": 17475, "total_steps": 64460, "loss": 0.2315, "lr": 9.134590000714618e-06, "epoch": 5.421967111386906, "percentage": 27.11, "elapsed_time": "0:31:53", "remaining_time": "1:25:45", "throughput": 5563.55, "total_tokens": 10648224} {"current_steps": 17480, "total_steps": 64460, "loss": 0.2309, "lr": 9.133828572444519e-06, "epoch": 5.423518461061123, "percentage": 27.12, "elapsed_time": "0:31:54", "remaining_time": "1:25:45", "throughput": 5563.7, "total_tokens": 10651488} {"current_steps": 17485, "total_steps": 64460, "loss": 0.2253, "lr": 9.133066841115832e-06, "epoch": 5.42506981073534, "percentage": 27.13, "elapsed_time": "0:31:54", "remaining_time": "1:25:44", "throughput": 5563.77, "total_tokens": 10654400} {"current_steps": 17490, "total_steps": 64460, "loss": 0.2298, "lr": 9.132304806784403e-06, "epoch": 5.426621160409557, "percentage": 27.13, "elapsed_time": "0:31:55", "remaining_time": "1:25:44", "throughput": 5563.89, "total_tokens": 10657728} {"current_steps": 17495, "total_steps": 64460, "loss": 0.233, "lr": 9.1315424695061e-06, "epoch": 5.4281725100837726, "percentage": 27.14, "elapsed_time": "0:31:56", "remaining_time": "1:25:43", "throughput": 5564.14, "total_tokens": 10660960} {"current_steps": 17500, "total_steps": 64460, "loss": 0.233, "lr": 9.130779829336806e-06, "epoch": 5.429723859757989, "percentage": 27.15, "elapsed_time": "0:31:56", "remaining_time": "1:25:43", "throughput": 5564.57, "total_tokens": 10665440} {"current_steps": 17505, "total_steps": 64460, "loss": 0.2384, "lr": 9.130016886332436e-06, "epoch": 5.431275209432206, "percentage": 27.16, "elapsed_time": "0:31:57", "remaining_time": "1:25:42", "throughput": 5564.48, "total_tokens": 10667744} {"current_steps": 17510, "total_steps": 64460, "loss": 0.229, "lr": 9.129253640548923e-06, "epoch": 5.432826559106423, "percentage": 27.16, "elapsed_time": "0:31:57", "remaining_time": "1:25:41", "throughput": 5564.55, "total_tokens": 10670528} {"current_steps": 17515, "total_steps": 64460, "loss": 0.2362, "lr": 9.128490092042219e-06, "epoch": 5.434377908780639, "percentage": 27.17, "elapsed_time": "0:31:58", "remaining_time": "1:25:40", "throughput": 5564.66, "total_tokens": 10673472} {"current_steps": 17520, "total_steps": 64460, "loss": 0.2351, "lr": 9.127726240868301e-06, "epoch": 5.4359292584548555, "percentage": 27.18, "elapsed_time": "0:31:58", "remaining_time": "1:25:40", "throughput": 5564.94, "total_tokens": 10676992} {"current_steps": 17525, "total_steps": 64460, "loss": 0.2306, "lr": 9.126962087083173e-06, "epoch": 5.437480608129072, "percentage": 27.19, "elapsed_time": "0:31:59", "remaining_time": "1:25:39", "throughput": 5564.99, "total_tokens": 10679744} {"current_steps": 17530, "total_steps": 64460, "loss": 0.2346, "lr": 9.126197630742853e-06, "epoch": 5.439031957803289, "percentage": 27.2, "elapsed_time": "0:31:59", "remaining_time": "1:25:39", "throughput": 5565.23, "total_tokens": 10683264} {"current_steps": 17535, "total_steps": 64460, "loss": 0.2277, "lr": 9.125432871903383e-06, "epoch": 5.440583307477505, "percentage": 27.2, "elapsed_time": "0:32:00", "remaining_time": "1:25:38", "throughput": 5565.05, "total_tokens": 10685568} {"current_steps": 17540, "total_steps": 64460, "loss": 0.231, "lr": 9.124667810620833e-06, "epoch": 5.442134657151722, "percentage": 27.21, "elapsed_time": "0:32:00", "remaining_time": "1:25:37", "throughput": 5564.97, "total_tokens": 10688032} {"current_steps": 17545, "total_steps": 64460, "loss": 0.2322, "lr": 9.123902446951288e-06, "epoch": 5.4436860068259385, "percentage": 27.22, "elapsed_time": "0:32:01", "remaining_time": "1:25:36", "throughput": 5564.9, "total_tokens": 10690688} {"current_steps": 17550, "total_steps": 64460, "loss": 0.2338, "lr": 9.123136780950861e-06, "epoch": 5.445237356500155, "percentage": 27.23, "elapsed_time": "0:32:01", "remaining_time": "1:25:36", "throughput": 5564.9, "total_tokens": 10693376} {"current_steps": 17555, "total_steps": 64460, "loss": 0.2321, "lr": 9.12237081267568e-06, "epoch": 5.446788706174372, "percentage": 27.23, "elapsed_time": "0:32:02", "remaining_time": "1:25:35", "throughput": 5564.85, "total_tokens": 10695968} {"current_steps": 17560, "total_steps": 64460, "loss": 0.2288, "lr": 9.121604542181905e-06, "epoch": 5.448340055848588, "percentage": 27.24, "elapsed_time": "0:32:02", "remaining_time": "1:25:35", "throughput": 5565.03, "total_tokens": 10699552} {"current_steps": 17565, "total_steps": 64460, "loss": 0.2283, "lr": 9.12083796952571e-06, "epoch": 5.449891405522805, "percentage": 27.25, "elapsed_time": "0:32:03", "remaining_time": "1:25:34", "throughput": 5565.17, "total_tokens": 10702656} {"current_steps": 17570, "total_steps": 64460, "loss": 0.2288, "lr": 9.120071094763292e-06, "epoch": 5.4514427551970215, "percentage": 27.26, "elapsed_time": "0:32:03", "remaining_time": "1:25:33", "throughput": 5565.22, "total_tokens": 10705440} {"current_steps": 17575, "total_steps": 64460, "loss": 0.2243, "lr": 9.119303917950875e-06, "epoch": 5.452994104871238, "percentage": 27.26, "elapsed_time": "0:32:04", "remaining_time": "1:25:33", "throughput": 5565.37, "total_tokens": 10708768} {"current_steps": 17580, "total_steps": 64460, "loss": 0.2314, "lr": 9.1185364391447e-06, "epoch": 5.454545454545454, "percentage": 27.27, "elapsed_time": "0:32:04", "remaining_time": "1:25:32", "throughput": 5565.27, "total_tokens": 10711200} {"current_steps": 17585, "total_steps": 64460, "loss": 0.2277, "lr": 9.117768658401033e-06, "epoch": 5.456096804219671, "percentage": 27.28, "elapsed_time": "0:32:05", "remaining_time": "1:25:31", "throughput": 5565.42, "total_tokens": 10714176} {"current_steps": 17590, "total_steps": 64460, "loss": 0.2227, "lr": 9.117000575776163e-06, "epoch": 5.457648153893888, "percentage": 27.29, "elapsed_time": "0:32:05", "remaining_time": "1:25:31", "throughput": 5565.64, "total_tokens": 10717888} {"current_steps": 17595, "total_steps": 64460, "loss": 0.2425, "lr": 9.116232191326398e-06, "epoch": 5.4591995035681045, "percentage": 27.3, "elapsed_time": "0:32:06", "remaining_time": "1:25:30", "throughput": 5565.7, "total_tokens": 10720736} {"current_steps": 17600, "total_steps": 64460, "loss": 0.2277, "lr": 9.115463505108069e-06, "epoch": 5.460750853242321, "percentage": 27.3, "elapsed_time": "0:32:06", "remaining_time": "1:25:29", "throughput": 5565.85, "total_tokens": 10724032} {"current_steps": 17605, "total_steps": 64460, "loss": 0.2406, "lr": 9.114694517177531e-06, "epoch": 5.462302202916537, "percentage": 27.31, "elapsed_time": "0:32:07", "remaining_time": "1:25:29", "throughput": 5565.69, "total_tokens": 10726560} {"current_steps": 17610, "total_steps": 64460, "loss": 0.2298, "lr": 9.113925227591159e-06, "epoch": 5.463853552590754, "percentage": 27.32, "elapsed_time": "0:32:07", "remaining_time": "1:25:28", "throughput": 5565.63, "total_tokens": 10729248} {"current_steps": 17615, "total_steps": 64460, "loss": 0.2343, "lr": 9.113155636405353e-06, "epoch": 5.465404902264971, "percentage": 27.33, "elapsed_time": "0:32:08", "remaining_time": "1:25:28", "throughput": 5565.63, "total_tokens": 10732416} {"current_steps": 17620, "total_steps": 64460, "loss": 0.2333, "lr": 9.11238574367653e-06, "epoch": 5.466956251939187, "percentage": 27.33, "elapsed_time": "0:32:08", "remaining_time": "1:25:27", "throughput": 5565.78, "total_tokens": 10735616} {"current_steps": 17625, "total_steps": 64460, "loss": 0.2325, "lr": 9.111615549461137e-06, "epoch": 5.468507601613403, "percentage": 27.34, "elapsed_time": "0:32:09", "remaining_time": "1:25:27", "throughput": 5565.9, "total_tokens": 10738944} {"current_steps": 17630, "total_steps": 64460, "loss": 0.2258, "lr": 9.110845053815634e-06, "epoch": 5.47005895128762, "percentage": 27.35, "elapsed_time": "0:32:09", "remaining_time": "1:25:26", "throughput": 5565.91, "total_tokens": 10741664} {"current_steps": 17635, "total_steps": 64460, "loss": 0.2318, "lr": 9.110074256796508e-06, "epoch": 5.471610300961837, "percentage": 27.36, "elapsed_time": "0:32:10", "remaining_time": "1:25:25", "throughput": 5565.84, "total_tokens": 10744512} {"current_steps": 17640, "total_steps": 64460, "loss": 0.2309, "lr": 9.109303158460268e-06, "epoch": 5.473161650636054, "percentage": 27.37, "elapsed_time": "0:32:10", "remaining_time": "1:25:25", "throughput": 5565.84, "total_tokens": 10747424} {"current_steps": 17645, "total_steps": 64460, "loss": 0.2336, "lr": 9.108531758863445e-06, "epoch": 5.4747130003102695, "percentage": 27.37, "elapsed_time": "0:32:11", "remaining_time": "1:25:24", "throughput": 5565.73, "total_tokens": 10750080} {"current_steps": 17650, "total_steps": 64460, "loss": 0.2242, "lr": 9.107760058062594e-06, "epoch": 5.476264349984486, "percentage": 27.38, "elapsed_time": "0:32:12", "remaining_time": "1:25:24", "throughput": 5565.72, "total_tokens": 10753184} {"current_steps": 17655, "total_steps": 64460, "loss": 0.2408, "lr": 9.106988056114288e-06, "epoch": 5.477815699658703, "percentage": 27.39, "elapsed_time": "0:32:12", "remaining_time": "1:25:23", "throughput": 5566.1, "total_tokens": 10757184} {"current_steps": 17660, "total_steps": 64460, "loss": 0.2313, "lr": 9.10621575307512e-06, "epoch": 5.47936704933292, "percentage": 27.4, "elapsed_time": "0:32:13", "remaining_time": "1:25:22", "throughput": 5566.24, "total_tokens": 10760160} {"current_steps": 17665, "total_steps": 64460, "loss": 0.2322, "lr": 9.105443149001715e-06, "epoch": 5.480918399007137, "percentage": 27.4, "elapsed_time": "0:32:13", "remaining_time": "1:25:22", "throughput": 5565.97, "total_tokens": 10762272} {"current_steps": 17670, "total_steps": 64460, "loss": 0.2351, "lr": 9.10467024395071e-06, "epoch": 5.4824697486813525, "percentage": 27.41, "elapsed_time": "0:32:14", "remaining_time": "1:25:21", "throughput": 5565.99, "total_tokens": 10765152} {"current_steps": 17675, "total_steps": 64460, "loss": 0.2274, "lr": 9.10389703797877e-06, "epoch": 5.484021098355569, "percentage": 27.42, "elapsed_time": "0:32:14", "remaining_time": "1:25:20", "throughput": 5565.91, "total_tokens": 10767776} {"current_steps": 17680, "total_steps": 64460, "loss": 0.2279, "lr": 9.103123531142581e-06, "epoch": 5.485572448029786, "percentage": 27.43, "elapsed_time": "0:32:15", "remaining_time": "1:25:20", "throughput": 5566.1, "total_tokens": 10771168} {"current_steps": 17685, "total_steps": 64460, "loss": 0.2304, "lr": 9.102349723498848e-06, "epoch": 5.487123797704003, "percentage": 27.44, "elapsed_time": "0:32:15", "remaining_time": "1:25:19", "throughput": 5566.27, "total_tokens": 10774880} {"current_steps": 17690, "total_steps": 64460, "loss": 0.2335, "lr": 9.1015756151043e-06, "epoch": 5.488675147378219, "percentage": 27.44, "elapsed_time": "0:32:16", "remaining_time": "1:25:19", "throughput": 5566.15, "total_tokens": 10777312} {"current_steps": 17695, "total_steps": 64460, "loss": 0.2278, "lr": 9.100801206015693e-06, "epoch": 5.4902264970524355, "percentage": 27.45, "elapsed_time": "0:32:16", "remaining_time": "1:25:18", "throughput": 5566.26, "total_tokens": 10780448} {"current_steps": 17700, "total_steps": 64460, "loss": 0.2334, "lr": 9.100026496289793e-06, "epoch": 5.491777846726652, "percentage": 27.46, "elapsed_time": "0:32:17", "remaining_time": "1:25:17", "throughput": 5566.33, "total_tokens": 10783328} {"current_steps": 17705, "total_steps": 64460, "loss": 0.2318, "lr": 9.0992514859834e-06, "epoch": 5.493329196400869, "percentage": 27.47, "elapsed_time": "0:32:17", "remaining_time": "1:25:17", "throughput": 5566.33, "total_tokens": 10785952} {"current_steps": 17710, "total_steps": 64460, "loss": 0.2329, "lr": 9.098476175153332e-06, "epoch": 5.494880546075085, "percentage": 27.47, "elapsed_time": "0:32:18", "remaining_time": "1:25:16", "throughput": 5566.36, "total_tokens": 10788864} {"current_steps": 17715, "total_steps": 64460, "loss": 0.228, "lr": 9.097700563856427e-06, "epoch": 5.496431895749302, "percentage": 27.48, "elapsed_time": "0:32:18", "remaining_time": "1:25:15", "throughput": 5566.4, "total_tokens": 10791968} {"current_steps": 17720, "total_steps": 64460, "loss": 0.2309, "lr": 9.096924652149546e-06, "epoch": 5.4979832454235185, "percentage": 27.49, "elapsed_time": "0:32:19", "remaining_time": "1:25:15", "throughput": 5566.4, "total_tokens": 10794688} {"current_steps": 17725, "total_steps": 64460, "loss": 0.2369, "lr": 9.096148440089573e-06, "epoch": 5.499534595097735, "percentage": 27.5, "elapsed_time": "0:32:19", "remaining_time": "1:25:14", "throughput": 5566.6, "total_tokens": 10797856} {"current_steps": 17730, "total_steps": 64460, "loss": 0.2332, "lr": 9.095371927733413e-06, "epoch": 5.501085944771951, "percentage": 27.51, "elapsed_time": "0:32:20", "remaining_time": "1:25:13", "throughput": 5566.74, "total_tokens": 10801056} {"current_steps": 17735, "total_steps": 64460, "loss": 0.2301, "lr": 9.094595115137996e-06, "epoch": 5.502637294446168, "percentage": 27.51, "elapsed_time": "0:32:20", "remaining_time": "1:25:13", "throughput": 5566.59, "total_tokens": 10803424} {"current_steps": 17740, "total_steps": 64460, "loss": 0.2294, "lr": 9.09381800236027e-06, "epoch": 5.504188644120385, "percentage": 27.52, "elapsed_time": "0:32:21", "remaining_time": "1:25:12", "throughput": 5566.6, "total_tokens": 10806144} {"current_steps": 17745, "total_steps": 64460, "loss": 0.2357, "lr": 9.093040589457204e-06, "epoch": 5.505739993794601, "percentage": 27.53, "elapsed_time": "0:32:21", "remaining_time": "1:25:12", "throughput": 5567.04, "total_tokens": 10810944} {"current_steps": 17750, "total_steps": 64460, "loss": 0.2284, "lr": 9.092262876485796e-06, "epoch": 5.507291343468818, "percentage": 27.54, "elapsed_time": "0:32:22", "remaining_time": "1:25:11", "throughput": 5566.7, "total_tokens": 10813216} {"current_steps": 17755, "total_steps": 64460, "loss": 0.2353, "lr": 9.09148486350306e-06, "epoch": 5.508842693143034, "percentage": 27.54, "elapsed_time": "0:32:23", "remaining_time": "1:25:11", "throughput": 5566.95, "total_tokens": 10817056} {"current_steps": 17760, "total_steps": 64460, "loss": 0.2322, "lr": 9.090706550566031e-06, "epoch": 5.510394042817251, "percentage": 27.55, "elapsed_time": "0:32:23", "remaining_time": "1:25:10", "throughput": 5567.31, "total_tokens": 10821248} {"current_steps": 17765, "total_steps": 64460, "loss": 0.2286, "lr": 9.089927937731771e-06, "epoch": 5.511945392491468, "percentage": 27.56, "elapsed_time": "0:32:24", "remaining_time": "1:25:10", "throughput": 5567.28, "total_tokens": 10823936} {"current_steps": 17770, "total_steps": 64460, "loss": 0.2307, "lr": 9.089149025057362e-06, "epoch": 5.513496742165684, "percentage": 27.57, "elapsed_time": "0:32:24", "remaining_time": "1:25:09", "throughput": 5567.22, "total_tokens": 10826560} {"current_steps": 17775, "total_steps": 64460, "loss": 0.2318, "lr": 9.088369812599907e-06, "epoch": 5.515048091839901, "percentage": 27.58, "elapsed_time": "0:32:25", "remaining_time": "1:25:08", "throughput": 5567.0, "total_tokens": 10828864} {"current_steps": 17780, "total_steps": 64460, "loss": 0.2281, "lr": 9.087590300416532e-06, "epoch": 5.516599441514117, "percentage": 27.58, "elapsed_time": "0:32:25", "remaining_time": "1:25:08", "throughput": 5566.89, "total_tokens": 10831840} {"current_steps": 17785, "total_steps": 64460, "loss": 0.2371, "lr": 9.086810488564382e-06, "epoch": 5.518150791188334, "percentage": 27.59, "elapsed_time": "0:32:26", "remaining_time": "1:25:07", "throughput": 5567.02, "total_tokens": 10835072} {"current_steps": 17790, "total_steps": 64460, "loss": 0.229, "lr": 9.086030377100628e-06, "epoch": 5.519702140862551, "percentage": 27.6, "elapsed_time": "0:32:26", "remaining_time": "1:25:07", "throughput": 5567.26, "total_tokens": 10838592} {"current_steps": 17795, "total_steps": 64460, "loss": 0.2281, "lr": 9.08524996608246e-06, "epoch": 5.5212534905367665, "percentage": 27.61, "elapsed_time": "0:32:27", "remaining_time": "1:25:06", "throughput": 5567.12, "total_tokens": 10841120} {"current_steps": 17800, "total_steps": 64460, "loss": 0.2304, "lr": 9.084469255567097e-06, "epoch": 5.522804840210983, "percentage": 27.61, "elapsed_time": "0:32:27", "remaining_time": "1:25:05", "throughput": 5567.0, "total_tokens": 10843488} {"current_steps": 17805, "total_steps": 64460, "loss": 0.2333, "lr": 9.083688245611767e-06, "epoch": 5.5243561898852, "percentage": 27.62, "elapsed_time": "0:32:28", "remaining_time": "1:25:05", "throughput": 5566.96, "total_tokens": 10846176} {"current_steps": 17810, "total_steps": 64460, "loss": 0.2256, "lr": 9.082906936273732e-06, "epoch": 5.525907539559417, "percentage": 27.63, "elapsed_time": "0:32:28", "remaining_time": "1:25:04", "throughput": 5566.79, "total_tokens": 10848704} {"current_steps": 17815, "total_steps": 64460, "loss": 0.2275, "lr": 9.08212532761027e-06, "epoch": 5.527458889233634, "percentage": 27.64, "elapsed_time": "0:32:29", "remaining_time": "1:25:03", "throughput": 5566.58, "total_tokens": 10851040} {"current_steps": 17820, "total_steps": 64460, "loss": 0.2306, "lr": 9.081343419678679e-06, "epoch": 5.5290102389078495, "percentage": 27.65, "elapsed_time": "0:32:29", "remaining_time": "1:25:03", "throughput": 5566.74, "total_tokens": 10854560} {"current_steps": 17825, "total_steps": 64460, "loss": 0.2332, "lr": 9.080561212536288e-06, "epoch": 5.530561588582066, "percentage": 27.65, "elapsed_time": "0:32:30", "remaining_time": "1:25:02", "throughput": 5566.64, "total_tokens": 10857024} {"current_steps": 17830, "total_steps": 64460, "loss": 0.2328, "lr": 9.079778706240439e-06, "epoch": 5.532112938256283, "percentage": 27.66, "elapsed_time": "0:32:30", "remaining_time": "1:25:02", "throughput": 5566.54, "total_tokens": 10859776} {"current_steps": 17835, "total_steps": 64460, "loss": 0.2227, "lr": 9.078995900848498e-06, "epoch": 5.5336642879305, "percentage": 27.67, "elapsed_time": "0:32:31", "remaining_time": "1:25:01", "throughput": 5566.5, "total_tokens": 10862368} {"current_steps": 17840, "total_steps": 64460, "loss": 0.2359, "lr": 9.078212796417855e-06, "epoch": 5.535215637604717, "percentage": 27.68, "elapsed_time": "0:32:31", "remaining_time": "1:25:00", "throughput": 5566.32, "total_tokens": 10864736} {"current_steps": 17845, "total_steps": 64460, "loss": 0.2282, "lr": 9.077429393005922e-06, "epoch": 5.5367669872789325, "percentage": 27.68, "elapsed_time": "0:32:32", "remaining_time": "1:25:00", "throughput": 5566.45, "total_tokens": 10867840} {"current_steps": 17850, "total_steps": 64460, "loss": 0.2383, "lr": 9.076645690670127e-06, "epoch": 5.538318336953149, "percentage": 27.69, "elapsed_time": "0:32:32", "remaining_time": "1:24:59", "throughput": 5566.57, "total_tokens": 10870880} {"current_steps": 17855, "total_steps": 64460, "loss": 0.2259, "lr": 9.075861689467932e-06, "epoch": 5.539869686627366, "percentage": 27.7, "elapsed_time": "0:32:33", "remaining_time": "1:24:58", "throughput": 5566.75, "total_tokens": 10874272} {"current_steps": 17860, "total_steps": 64460, "loss": 0.2301, "lr": 9.075077389456807e-06, "epoch": 5.541421036301582, "percentage": 27.71, "elapsed_time": "0:32:33", "remaining_time": "1:24:58", "throughput": 5566.57, "total_tokens": 10876736} {"current_steps": 17865, "total_steps": 64460, "loss": 0.2321, "lr": 9.074292790694255e-06, "epoch": 5.542972385975799, "percentage": 27.71, "elapsed_time": "0:32:34", "remaining_time": "1:24:57", "throughput": 5566.64, "total_tokens": 10879680} {"current_steps": 17870, "total_steps": 64460, "loss": 0.2314, "lr": 9.073507893237795e-06, "epoch": 5.544523735650015, "percentage": 27.72, "elapsed_time": "0:32:34", "remaining_time": "1:24:56", "throughput": 5566.76, "total_tokens": 10882688} {"current_steps": 17875, "total_steps": 64460, "loss": 0.2251, "lr": 9.072722697144967e-06, "epoch": 5.546075085324232, "percentage": 27.73, "elapsed_time": "0:32:35", "remaining_time": "1:24:56", "throughput": 5566.73, "total_tokens": 10885344} {"current_steps": 17880, "total_steps": 64460, "loss": 0.2348, "lr": 9.07193720247334e-06, "epoch": 5.547626434998449, "percentage": 27.74, "elapsed_time": "0:32:35", "remaining_time": "1:24:55", "throughput": 5566.51, "total_tokens": 10887680} {"current_steps": 17885, "total_steps": 64460, "loss": 0.2267, "lr": 9.071151409280494e-06, "epoch": 5.549177784672665, "percentage": 27.75, "elapsed_time": "0:32:36", "remaining_time": "1:24:54", "throughput": 5566.25, "total_tokens": 10889760} {"current_steps": 17890, "total_steps": 64460, "loss": 0.2364, "lr": 9.070365317624041e-06, "epoch": 5.550729134346882, "percentage": 27.75, "elapsed_time": "0:32:36", "remaining_time": "1:24:53", "throughput": 5566.15, "total_tokens": 10892224} {"current_steps": 17895, "total_steps": 64460, "loss": 0.2418, "lr": 9.06957892756161e-06, "epoch": 5.552280484021098, "percentage": 27.76, "elapsed_time": "0:32:37", "remaining_time": "1:24:53", "throughput": 5566.2, "total_tokens": 10895296} {"current_steps": 17900, "total_steps": 64460, "loss": 0.2298, "lr": 9.068792239150852e-06, "epoch": 5.553831833695315, "percentage": 27.77, "elapsed_time": "0:32:37", "remaining_time": "1:24:52", "throughput": 5566.05, "total_tokens": 10897728} {"current_steps": 17905, "total_steps": 64460, "loss": 0.2249, "lr": 9.068005252449443e-06, "epoch": 5.555383183369532, "percentage": 27.78, "elapsed_time": "0:32:38", "remaining_time": "1:24:52", "throughput": 5566.36, "total_tokens": 10902080} {"current_steps": 17910, "total_steps": 64460, "loss": 0.2275, "lr": 9.067217967515075e-06, "epoch": 5.556934533043748, "percentage": 27.78, "elapsed_time": "0:32:39", "remaining_time": "1:24:51", "throughput": 5566.49, "total_tokens": 10905280} {"current_steps": 17915, "total_steps": 64460, "loss": 0.2364, "lr": 9.066430384405466e-06, "epoch": 5.558485882717965, "percentage": 27.79, "elapsed_time": "0:32:39", "remaining_time": "1:24:51", "throughput": 5566.74, "total_tokens": 10908704} {"current_steps": 17920, "total_steps": 64460, "loss": 0.2357, "lr": 9.065642503178359e-06, "epoch": 5.560037232392181, "percentage": 27.8, "elapsed_time": "0:32:40", "remaining_time": "1:24:50", "throughput": 5566.89, "total_tokens": 10912128} {"current_steps": 17925, "total_steps": 64460, "loss": 0.2346, "lr": 9.06485432389151e-06, "epoch": 5.561588582066397, "percentage": 27.81, "elapsed_time": "0:32:40", "remaining_time": "1:24:50", "throughput": 5566.93, "total_tokens": 10915040} {"current_steps": 17930, "total_steps": 64460, "loss": 0.2314, "lr": 9.064065846602705e-06, "epoch": 5.563139931740614, "percentage": 27.82, "elapsed_time": "0:32:41", "remaining_time": "1:24:49", "throughput": 5566.93, "total_tokens": 10917760} {"current_steps": 17935, "total_steps": 64460, "loss": 0.2325, "lr": 9.063277071369746e-06, "epoch": 5.564691281414831, "percentage": 27.82, "elapsed_time": "0:32:41", "remaining_time": "1:24:48", "throughput": 5566.96, "total_tokens": 10920768} {"current_steps": 17940, "total_steps": 64460, "loss": 0.2326, "lr": 9.062487998250464e-06, "epoch": 5.566242631089048, "percentage": 27.83, "elapsed_time": "0:32:42", "remaining_time": "1:24:48", "throughput": 5567.0, "total_tokens": 10923744} {"current_steps": 17945, "total_steps": 64460, "loss": 0.2311, "lr": 9.061698627302704e-06, "epoch": 5.567793980763264, "percentage": 27.84, "elapsed_time": "0:32:42", "remaining_time": "1:24:47", "throughput": 5567.05, "total_tokens": 10926784} {"current_steps": 17950, "total_steps": 64460, "loss": 0.238, "lr": 9.060908958584335e-06, "epoch": 5.56934533043748, "percentage": 27.85, "elapsed_time": "0:32:43", "remaining_time": "1:24:47", "throughput": 5567.23, "total_tokens": 10930752} {"current_steps": 17955, "total_steps": 64460, "loss": 0.2331, "lr": 9.060118992153251e-06, "epoch": 5.570896680111697, "percentage": 27.85, "elapsed_time": "0:32:43", "remaining_time": "1:24:46", "throughput": 5567.16, "total_tokens": 10933344} {"current_steps": 17960, "total_steps": 64460, "loss": 0.2316, "lr": 9.059328728067368e-06, "epoch": 5.572448029785914, "percentage": 27.86, "elapsed_time": "0:32:44", "remaining_time": "1:24:45", "throughput": 5566.95, "total_tokens": 10935680} {"current_steps": 17965, "total_steps": 64460, "loss": 0.2238, "lr": 9.058538166384619e-06, "epoch": 5.573999379460131, "percentage": 27.87, "elapsed_time": "0:32:44", "remaining_time": "1:24:45", "throughput": 5566.97, "total_tokens": 10938400} {"current_steps": 17970, "total_steps": 64460, "loss": 0.2287, "lr": 9.057747307162961e-06, "epoch": 5.575550729134347, "percentage": 27.88, "elapsed_time": "0:32:45", "remaining_time": "1:24:44", "throughput": 5567.02, "total_tokens": 10941504} {"current_steps": 17975, "total_steps": 64460, "loss": 0.2324, "lr": 9.056956150460375e-06, "epoch": 5.577102078808563, "percentage": 27.89, "elapsed_time": "0:32:46", "remaining_time": "1:24:44", "throughput": 5567.26, "total_tokens": 10945600} {"current_steps": 17980, "total_steps": 64460, "loss": 0.2353, "lr": 9.056164696334862e-06, "epoch": 5.57865342848278, "percentage": 27.89, "elapsed_time": "0:32:46", "remaining_time": "1:24:44", "throughput": 5567.53, "total_tokens": 10949568} {"current_steps": 17985, "total_steps": 64460, "loss": 0.2298, "lr": 9.055372944844444e-06, "epoch": 5.580204778156997, "percentage": 27.9, "elapsed_time": "0:32:47", "remaining_time": "1:24:43", "throughput": 5567.51, "total_tokens": 10952576} {"current_steps": 17990, "total_steps": 64460, "loss": 0.2286, "lr": 9.054580896047168e-06, "epoch": 5.581756127831213, "percentage": 27.91, "elapsed_time": "0:32:47", "remaining_time": "1:24:42", "throughput": 5567.46, "total_tokens": 10955200} {"current_steps": 17995, "total_steps": 64460, "loss": 0.2212, "lr": 9.053788550001097e-06, "epoch": 5.583307477505429, "percentage": 27.92, "elapsed_time": "0:32:48", "remaining_time": "1:24:42", "throughput": 5567.42, "total_tokens": 10957888} {"current_steps": 18000, "total_steps": 64460, "loss": 0.2397, "lr": 9.05299590676432e-06, "epoch": 5.584858827179646, "percentage": 27.92, "elapsed_time": "0:32:48", "remaining_time": "1:24:41", "throughput": 5567.56, "total_tokens": 10961216} {"current_steps": 18005, "total_steps": 64460, "loss": 0.2368, "lr": 9.052202966394951e-06, "epoch": 5.586410176853863, "percentage": 27.93, "elapsed_time": "0:32:49", "remaining_time": "1:24:41", "throughput": 5567.96, "total_tokens": 10965088} {"current_steps": 18010, "total_steps": 64460, "loss": 0.2221, "lr": 9.051409728951119e-06, "epoch": 5.58796152652808, "percentage": 27.94, "elapsed_time": "0:32:49", "remaining_time": "1:24:40", "throughput": 5568.1, "total_tokens": 10968128} {"current_steps": 18015, "total_steps": 64460, "loss": 0.2308, "lr": 9.050616194490977e-06, "epoch": 5.589512876202296, "percentage": 27.95, "elapsed_time": "0:32:50", "remaining_time": "1:24:39", "throughput": 5568.12, "total_tokens": 10971136} {"current_steps": 18020, "total_steps": 64460, "loss": 0.2347, "lr": 9.049822363072702e-06, "epoch": 5.591064225876512, "percentage": 27.96, "elapsed_time": "0:32:50", "remaining_time": "1:24:39", "throughput": 5567.9, "total_tokens": 10973280} {"current_steps": 18025, "total_steps": 64460, "loss": 0.235, "lr": 9.049028234754491e-06, "epoch": 5.592615575550729, "percentage": 27.96, "elapsed_time": "0:32:51", "remaining_time": "1:24:38", "throughput": 5568.15, "total_tokens": 10976928} {"current_steps": 18030, "total_steps": 64460, "loss": 0.2314, "lr": 9.048233809594561e-06, "epoch": 5.594166925224946, "percentage": 27.97, "elapsed_time": "0:32:51", "remaining_time": "1:24:37", "throughput": 5568.01, "total_tokens": 10979456} {"current_steps": 18035, "total_steps": 64460, "loss": 0.2314, "lr": 9.047439087651158e-06, "epoch": 5.595718274899163, "percentage": 27.98, "elapsed_time": "0:32:52", "remaining_time": "1:24:37", "throughput": 5568.26, "total_tokens": 10983648} {"current_steps": 18040, "total_steps": 64460, "loss": 0.2313, "lr": 9.046644068982539e-06, "epoch": 5.597269624573379, "percentage": 27.99, "elapsed_time": "0:32:53", "remaining_time": "1:24:37", "throughput": 5568.49, "total_tokens": 10987168} {"current_steps": 18045, "total_steps": 64460, "loss": 0.241, "lr": 9.04584875364699e-06, "epoch": 5.598820974247595, "percentage": 27.99, "elapsed_time": "0:32:53", "remaining_time": "1:24:36", "throughput": 5568.22, "total_tokens": 10989504} {"current_steps": 18050, "total_steps": 64460, "loss": 0.2369, "lr": 9.045053141702817e-06, "epoch": 5.600372323921812, "percentage": 28.0, "elapsed_time": "0:32:54", "remaining_time": "1:24:35", "throughput": 5568.27, "total_tokens": 10992608} {"current_steps": 18055, "total_steps": 64460, "loss": 0.237, "lr": 9.044257233208348e-06, "epoch": 5.601923673596028, "percentage": 28.01, "elapsed_time": "0:32:54", "remaining_time": "1:24:35", "throughput": 5568.2, "total_tokens": 10995328} {"current_steps": 18060, "total_steps": 64460, "loss": 0.2351, "lr": 9.043461028221934e-06, "epoch": 5.603475023270245, "percentage": 28.02, "elapsed_time": "0:32:55", "remaining_time": "1:24:34", "throughput": 5568.38, "total_tokens": 10998528} {"current_steps": 18065, "total_steps": 64460, "loss": 0.2257, "lr": 9.042664526801944e-06, "epoch": 5.605026372944462, "percentage": 28.03, "elapsed_time": "0:32:55", "remaining_time": "1:24:33", "throughput": 5568.59, "total_tokens": 11001760} {"current_steps": 18070, "total_steps": 64460, "loss": 0.2325, "lr": 9.041867729006772e-06, "epoch": 5.606577722618678, "percentage": 28.03, "elapsed_time": "0:32:56", "remaining_time": "1:24:33", "throughput": 5568.87, "total_tokens": 11005408} {"current_steps": 18075, "total_steps": 64460, "loss": 0.2268, "lr": 9.041070634894833e-06, "epoch": 5.608129072292895, "percentage": 28.04, "elapsed_time": "0:32:56", "remaining_time": "1:24:32", "throughput": 5569.08, "total_tokens": 11008832} {"current_steps": 18080, "total_steps": 64460, "loss": 0.2266, "lr": 9.040273244524563e-06, "epoch": 5.609680421967111, "percentage": 28.05, "elapsed_time": "0:32:57", "remaining_time": "1:24:32", "throughput": 5569.05, "total_tokens": 11011392} {"current_steps": 18085, "total_steps": 64460, "loss": 0.2295, "lr": 9.03947555795442e-06, "epoch": 5.611231771641328, "percentage": 28.06, "elapsed_time": "0:32:57", "remaining_time": "1:24:31", "throughput": 5569.24, "total_tokens": 11014880} {"current_steps": 18090, "total_steps": 64460, "loss": 0.2315, "lr": 9.038677575242884e-06, "epoch": 5.612783121315545, "percentage": 28.06, "elapsed_time": "0:32:58", "remaining_time": "1:24:31", "throughput": 5569.63, "total_tokens": 11019200} {"current_steps": 18095, "total_steps": 64460, "loss": 0.2379, "lr": 9.037879296448456e-06, "epoch": 5.614334470989761, "percentage": 28.07, "elapsed_time": "0:32:58", "remaining_time": "1:24:30", "throughput": 5569.9, "total_tokens": 11022656} {"current_steps": 18100, "total_steps": 64460, "loss": 0.2348, "lr": 9.03708072162966e-06, "epoch": 5.615885820663978, "percentage": 28.08, "elapsed_time": "0:32:59", "remaining_time": "1:24:29", "throughput": 5569.94, "total_tokens": 11025344} {"current_steps": 18105, "total_steps": 64460, "loss": 0.238, "lr": 9.036281850845043e-06, "epoch": 5.617437170338194, "percentage": 28.09, "elapsed_time": "0:32:59", "remaining_time": "1:24:29", "throughput": 5569.87, "total_tokens": 11027808} {"current_steps": 18110, "total_steps": 64460, "loss": 0.2327, "lr": 9.035482684153168e-06, "epoch": 5.618988520012411, "percentage": 28.09, "elapsed_time": "0:33:00", "remaining_time": "1:24:28", "throughput": 5570.14, "total_tokens": 11031488} {"current_steps": 18115, "total_steps": 64460, "loss": 0.2367, "lr": 9.034683221612623e-06, "epoch": 5.6205398696866276, "percentage": 28.1, "elapsed_time": "0:33:00", "remaining_time": "1:24:28", "throughput": 5570.2, "total_tokens": 11034336} {"current_steps": 18120, "total_steps": 64460, "loss": 0.233, "lr": 9.033883463282023e-06, "epoch": 5.622091219360843, "percentage": 28.11, "elapsed_time": "0:33:01", "remaining_time": "1:24:27", "throughput": 5570.43, "total_tokens": 11038048} {"current_steps": 18125, "total_steps": 64460, "loss": 0.2283, "lr": 9.033083409219996e-06, "epoch": 5.62364256903506, "percentage": 28.12, "elapsed_time": "0:33:02", "remaining_time": "1:24:27", "throughput": 5570.74, "total_tokens": 11042528} {"current_steps": 18130, "total_steps": 64460, "loss": 0.2273, "lr": 9.032283059485196e-06, "epoch": 5.625193918709277, "percentage": 28.13, "elapsed_time": "0:33:02", "remaining_time": "1:24:26", "throughput": 5570.51, "total_tokens": 11044640} {"current_steps": 18135, "total_steps": 64460, "loss": 0.2321, "lr": 9.0314824141363e-06, "epoch": 5.626745268383494, "percentage": 28.13, "elapsed_time": "0:33:03", "remaining_time": "1:24:25", "throughput": 5570.61, "total_tokens": 11047552} {"current_steps": 18140, "total_steps": 64460, "loss": 0.2318, "lr": 9.030681473232001e-06, "epoch": 5.6282966180577105, "percentage": 28.14, "elapsed_time": "0:33:03", "remaining_time": "1:24:25", "throughput": 5570.53, "total_tokens": 11049952} {"current_steps": 18145, "total_steps": 64460, "loss": 0.2385, "lr": 9.029880236831019e-06, "epoch": 5.629847967731926, "percentage": 28.15, "elapsed_time": "0:33:04", "remaining_time": "1:24:24", "throughput": 5570.42, "total_tokens": 11052384} {"current_steps": 18150, "total_steps": 64460, "loss": 0.2275, "lr": 9.029078704992096e-06, "epoch": 5.631399317406143, "percentage": 28.16, "elapsed_time": "0:33:04", "remaining_time": "1:24:23", "throughput": 5570.6, "total_tokens": 11055776} {"current_steps": 18155, "total_steps": 64460, "loss": 0.2332, "lr": 9.028276877773994e-06, "epoch": 5.63295066708036, "percentage": 28.16, "elapsed_time": "0:33:05", "remaining_time": "1:24:23", "throughput": 5570.77, "total_tokens": 11058912} {"current_steps": 18160, "total_steps": 64460, "loss": 0.231, "lr": 9.027474755235492e-06, "epoch": 5.634502016754577, "percentage": 28.17, "elapsed_time": "0:33:05", "remaining_time": "1:24:22", "throughput": 5570.91, "total_tokens": 11061856} {"current_steps": 18165, "total_steps": 64460, "loss": 0.2335, "lr": 9.0266723374354e-06, "epoch": 5.6360533664287935, "percentage": 28.18, "elapsed_time": "0:33:06", "remaining_time": "1:24:22", "throughput": 5571.23, "total_tokens": 11066112} {"current_steps": 18170, "total_steps": 64460, "loss": 0.2262, "lr": 9.025869624432541e-06, "epoch": 5.637604716103009, "percentage": 28.19, "elapsed_time": "0:33:06", "remaining_time": "1:24:21", "throughput": 5571.25, "total_tokens": 11068832} {"current_steps": 18175, "total_steps": 64460, "loss": 0.2294, "lr": 9.025066616285766e-06, "epoch": 5.639156065777226, "percentage": 28.2, "elapsed_time": "0:33:07", "remaining_time": "1:24:20", "throughput": 5571.33, "total_tokens": 11071872} {"current_steps": 18180, "total_steps": 64460, "loss": 0.2293, "lr": 9.024263313053946e-06, "epoch": 5.640707415451443, "percentage": 28.2, "elapsed_time": "0:33:07", "remaining_time": "1:24:20", "throughput": 5571.21, "total_tokens": 11074240} {"current_steps": 18185, "total_steps": 64460, "loss": 0.2357, "lr": 9.02345971479597e-06, "epoch": 5.642258765125659, "percentage": 28.21, "elapsed_time": "0:33:08", "remaining_time": "1:24:19", "throughput": 5571.42, "total_tokens": 11078240} {"current_steps": 18190, "total_steps": 64460, "loss": 0.2336, "lr": 9.02265582157075e-06, "epoch": 5.643810114799876, "percentage": 28.22, "elapsed_time": "0:33:08", "remaining_time": "1:24:19", "throughput": 5571.55, "total_tokens": 11081440} {"current_steps": 18195, "total_steps": 64460, "loss": 0.23, "lr": 9.021851633437223e-06, "epoch": 5.645361464474092, "percentage": 28.23, "elapsed_time": "0:33:09", "remaining_time": "1:24:18", "throughput": 5571.28, "total_tokens": 11083680} {"current_steps": 18200, "total_steps": 64460, "loss": 0.2306, "lr": 9.021047150454347e-06, "epoch": 5.646912814148309, "percentage": 28.23, "elapsed_time": "0:33:10", "remaining_time": "1:24:18", "throughput": 5571.48, "total_tokens": 11087488} {"current_steps": 18205, "total_steps": 64460, "loss": 0.2311, "lr": 9.020242372681099e-06, "epoch": 5.648464163822526, "percentage": 28.24, "elapsed_time": "0:33:10", "remaining_time": "1:24:17", "throughput": 5571.6, "total_tokens": 11090368} {"current_steps": 18210, "total_steps": 64460, "loss": 0.2316, "lr": 9.019437300176477e-06, "epoch": 5.650015513496742, "percentage": 28.25, "elapsed_time": "0:33:11", "remaining_time": "1:24:16", "throughput": 5571.72, "total_tokens": 11093568} {"current_steps": 18215, "total_steps": 64460, "loss": 0.2317, "lr": 9.018631932999504e-06, "epoch": 5.651566863170959, "percentage": 28.26, "elapsed_time": "0:33:11", "remaining_time": "1:24:16", "throughput": 5571.74, "total_tokens": 11096384} {"current_steps": 18220, "total_steps": 64460, "loss": 0.2302, "lr": 9.017826271209223e-06, "epoch": 5.653118212845175, "percentage": 28.27, "elapsed_time": "0:33:12", "remaining_time": "1:24:15", "throughput": 5571.86, "total_tokens": 11099360} {"current_steps": 18225, "total_steps": 64460, "loss": 0.2331, "lr": 9.017020314864698e-06, "epoch": 5.654669562519392, "percentage": 28.27, "elapsed_time": "0:33:12", "remaining_time": "1:24:14", "throughput": 5572.02, "total_tokens": 11102368} {"current_steps": 18230, "total_steps": 64460, "loss": 0.2316, "lr": 9.016214064025013e-06, "epoch": 5.656220912193609, "percentage": 28.28, "elapsed_time": "0:33:13", "remaining_time": "1:24:14", "throughput": 5572.26, "total_tokens": 11106400} {"current_steps": 18235, "total_steps": 64460, "loss": 0.2385, "lr": 9.01540751874928e-06, "epoch": 5.657772261867825, "percentage": 28.29, "elapsed_time": "0:33:13", "remaining_time": "1:24:13", "throughput": 5572.56, "total_tokens": 11110048} {"current_steps": 18240, "total_steps": 64460, "loss": 0.2305, "lr": 9.014600679096627e-06, "epoch": 5.6593236115420416, "percentage": 28.3, "elapsed_time": "0:33:14", "remaining_time": "1:24:13", "throughput": 5572.59, "total_tokens": 11112832} {"current_steps": 18245, "total_steps": 64460, "loss": 0.2263, "lr": 9.013793545126204e-06, "epoch": 5.660874961216258, "percentage": 28.3, "elapsed_time": "0:33:14", "remaining_time": "1:24:12", "throughput": 5572.6, "total_tokens": 11115552} {"current_steps": 18250, "total_steps": 64460, "loss": 0.2319, "lr": 9.012986116897182e-06, "epoch": 5.662426310890475, "percentage": 28.31, "elapsed_time": "0:33:15", "remaining_time": "1:24:12", "throughput": 5572.79, "total_tokens": 11118944} {"current_steps": 18255, "total_steps": 64460, "loss": 0.2264, "lr": 9.012178394468757e-06, "epoch": 5.663977660564691, "percentage": 28.32, "elapsed_time": "0:33:15", "remaining_time": "1:24:11", "throughput": 5572.71, "total_tokens": 11121376} {"current_steps": 18260, "total_steps": 64460, "loss": 0.2304, "lr": 9.011370377900147e-06, "epoch": 5.665529010238908, "percentage": 28.33, "elapsed_time": "0:33:16", "remaining_time": "1:24:10", "throughput": 5573.06, "total_tokens": 11125408} {"current_steps": 18265, "total_steps": 64460, "loss": 0.2349, "lr": 9.010562067250585e-06, "epoch": 5.6670803599131245, "percentage": 28.34, "elapsed_time": "0:33:16", "remaining_time": "1:24:10", "throughput": 5573.17, "total_tokens": 11128320} {"current_steps": 18270, "total_steps": 64460, "loss": 0.2331, "lr": 9.009753462579332e-06, "epoch": 5.668631709587341, "percentage": 28.34, "elapsed_time": "0:33:17", "remaining_time": "1:24:09", "throughput": 5573.45, "total_tokens": 11132448} {"current_steps": 18275, "total_steps": 64460, "loss": 0.2306, "lr": 9.008944563945666e-06, "epoch": 5.670183059261557, "percentage": 28.35, "elapsed_time": "0:33:17", "remaining_time": "1:24:09", "throughput": 5573.53, "total_tokens": 11135296} {"current_steps": 18280, "total_steps": 64460, "loss": 0.233, "lr": 9.008135371408892e-06, "epoch": 5.671734408935774, "percentage": 28.36, "elapsed_time": "0:33:18", "remaining_time": "1:24:08", "throughput": 5573.88, "total_tokens": 11139360} {"current_steps": 18285, "total_steps": 64460, "loss": 0.2378, "lr": 9.00732588502833e-06, "epoch": 5.673285758609991, "percentage": 28.37, "elapsed_time": "0:33:19", "remaining_time": "1:24:08", "throughput": 5574.34, "total_tokens": 11143808} {"current_steps": 18290, "total_steps": 64460, "loss": 0.2289, "lr": 9.006516104863329e-06, "epoch": 5.6748371082842075, "percentage": 28.37, "elapsed_time": "0:33:19", "remaining_time": "1:24:07", "throughput": 5574.43, "total_tokens": 11146752} {"current_steps": 18295, "total_steps": 64460, "loss": 0.2325, "lr": 9.005706030973251e-06, "epoch": 5.676388457958424, "percentage": 28.38, "elapsed_time": "0:33:20", "remaining_time": "1:24:07", "throughput": 5574.53, "total_tokens": 11149664} {"current_steps": 18300, "total_steps": 64460, "loss": 0.2299, "lr": 9.004895663417489e-06, "epoch": 5.67793980763264, "percentage": 28.39, "elapsed_time": "0:33:20", "remaining_time": "1:24:06", "throughput": 5574.53, "total_tokens": 11152576} {"current_steps": 18305, "total_steps": 64460, "loss": 0.2325, "lr": 9.004085002255447e-06, "epoch": 5.679491157306857, "percentage": 28.4, "elapsed_time": "0:33:21", "remaining_time": "1:24:05", "throughput": 5574.43, "total_tokens": 11154944} {"current_steps": 18310, "total_steps": 64460, "loss": 0.2274, "lr": 9.003274047546561e-06, "epoch": 5.681042506981074, "percentage": 28.41, "elapsed_time": "0:33:21", "remaining_time": "1:24:04", "throughput": 5574.5, "total_tokens": 11157600} {"current_steps": 18315, "total_steps": 64460, "loss": 0.2274, "lr": 9.00246279935028e-06, "epoch": 5.6825938566552905, "percentage": 28.41, "elapsed_time": "0:33:22", "remaining_time": "1:24:04", "throughput": 5574.72, "total_tokens": 11161184} {"current_steps": 18320, "total_steps": 64460, "loss": 0.229, "lr": 9.001651257726081e-06, "epoch": 5.684145206329506, "percentage": 28.42, "elapsed_time": "0:33:22", "remaining_time": "1:24:03", "throughput": 5574.53, "total_tokens": 11163520} {"current_steps": 18325, "total_steps": 64460, "loss": 0.2336, "lr": 9.000839422733458e-06, "epoch": 5.685696556003723, "percentage": 28.43, "elapsed_time": "0:33:23", "remaining_time": "1:24:02", "throughput": 5574.68, "total_tokens": 11166560} {"current_steps": 18330, "total_steps": 64460, "loss": 0.2361, "lr": 9.000027294431928e-06, "epoch": 5.68724790567794, "percentage": 28.44, "elapsed_time": "0:33:23", "remaining_time": "1:24:02", "throughput": 5574.57, "total_tokens": 11168896} {"current_steps": 18335, "total_steps": 64460, "loss": 0.2306, "lr": 8.999214872881029e-06, "epoch": 5.688799255352157, "percentage": 28.44, "elapsed_time": "0:33:23", "remaining_time": "1:24:01", "throughput": 5574.58, "total_tokens": 11171456} {"current_steps": 18340, "total_steps": 64460, "loss": 0.2295, "lr": 8.998402158140322e-06, "epoch": 5.690350605026373, "percentage": 28.45, "elapsed_time": "0:33:24", "remaining_time": "1:24:00", "throughput": 5574.58, "total_tokens": 11174176} {"current_steps": 18345, "total_steps": 64460, "loss": 0.233, "lr": 8.99758915026939e-06, "epoch": 5.691901954700589, "percentage": 28.46, "elapsed_time": "0:33:25", "remaining_time": "1:24:00", "throughput": 5574.93, "total_tokens": 11178400} {"current_steps": 18350, "total_steps": 64460, "loss": 0.233, "lr": 8.996775849327834e-06, "epoch": 5.693453304374806, "percentage": 28.47, "elapsed_time": "0:33:25", "remaining_time": "1:23:59", "throughput": 5575.19, "total_tokens": 11182304} {"current_steps": 18355, "total_steps": 64460, "loss": 0.2331, "lr": 8.99596225537528e-06, "epoch": 5.695004654049023, "percentage": 28.48, "elapsed_time": "0:33:26", "remaining_time": "1:23:59", "throughput": 5575.44, "total_tokens": 11186080} {"current_steps": 18360, "total_steps": 64460, "loss": 0.2305, "lr": 8.995148368471371e-06, "epoch": 5.69655600372324, "percentage": 28.48, "elapsed_time": "0:33:26", "remaining_time": "1:23:58", "throughput": 5575.47, "total_tokens": 11188672} {"current_steps": 18365, "total_steps": 64460, "loss": 0.233, "lr": 8.99433418867578e-06, "epoch": 5.6981073533974556, "percentage": 28.49, "elapsed_time": "0:33:27", "remaining_time": "1:23:58", "throughput": 5576.04, "total_tokens": 11194144} {"current_steps": 18370, "total_steps": 64460, "loss": 0.2336, "lr": 8.99351971604819e-06, "epoch": 5.699658703071672, "percentage": 28.5, "elapsed_time": "0:33:28", "remaining_time": "1:23:58", "throughput": 5576.02, "total_tokens": 11196736} {"current_steps": 18375, "total_steps": 64460, "loss": 0.2311, "lr": 8.992704950648316e-06, "epoch": 5.701210052745889, "percentage": 28.51, "elapsed_time": "0:33:28", "remaining_time": "1:23:57", "throughput": 5576.04, "total_tokens": 11199392} {"current_steps": 18380, "total_steps": 64460, "loss": 0.2337, "lr": 8.99188989253589e-06, "epoch": 5.702761402420106, "percentage": 28.51, "elapsed_time": "0:33:28", "remaining_time": "1:23:56", "throughput": 5576.11, "total_tokens": 11202336} {"current_steps": 18385, "total_steps": 64460, "loss": 0.2276, "lr": 8.991074541770662e-06, "epoch": 5.704312752094322, "percentage": 28.52, "elapsed_time": "0:33:29", "remaining_time": "1:23:55", "throughput": 5576.16, "total_tokens": 11204960} {"current_steps": 18390, "total_steps": 64460, "loss": 0.2274, "lr": 8.99025889841241e-06, "epoch": 5.7058641017685385, "percentage": 28.53, "elapsed_time": "0:33:29", "remaining_time": "1:23:55", "throughput": 5576.12, "total_tokens": 11207456} {"current_steps": 18395, "total_steps": 64460, "loss": 0.2369, "lr": 8.989442962520927e-06, "epoch": 5.707415451442755, "percentage": 28.54, "elapsed_time": "0:33:30", "remaining_time": "1:23:54", "throughput": 5576.42, "total_tokens": 11211040} {"current_steps": 18400, "total_steps": 64460, "loss": 0.2322, "lr": 8.988626734156034e-06, "epoch": 5.708966801116972, "percentage": 28.54, "elapsed_time": "0:33:30", "remaining_time": "1:23:53", "throughput": 5576.22, "total_tokens": 11213152} {"current_steps": 18405, "total_steps": 64460, "loss": 0.2249, "lr": 8.987810213377569e-06, "epoch": 5.710518150791188, "percentage": 28.55, "elapsed_time": "0:33:31", "remaining_time": "1:23:53", "throughput": 5576.28, "total_tokens": 11216000} {"current_steps": 18410, "total_steps": 64460, "loss": 0.2316, "lr": 8.986993400245392e-06, "epoch": 5.712069500465405, "percentage": 28.56, "elapsed_time": "0:33:31", "remaining_time": "1:23:52", "throughput": 5576.4, "total_tokens": 11218944} {"current_steps": 18415, "total_steps": 64460, "loss": 0.2255, "lr": 8.986176294819387e-06, "epoch": 5.7136208501396215, "percentage": 28.57, "elapsed_time": "0:33:32", "remaining_time": "1:23:51", "throughput": 5576.48, "total_tokens": 11221984} {"current_steps": 18420, "total_steps": 64460, "loss": 0.239, "lr": 8.985358897159455e-06, "epoch": 5.715172199813838, "percentage": 28.58, "elapsed_time": "0:33:32", "remaining_time": "1:23:51", "throughput": 5576.49, "total_tokens": 11224704} {"current_steps": 18425, "total_steps": 64460, "loss": 0.2306, "lr": 8.984541207325523e-06, "epoch": 5.716723549488055, "percentage": 28.58, "elapsed_time": "0:33:33", "remaining_time": "1:23:50", "throughput": 5576.65, "total_tokens": 11228352} {"current_steps": 18430, "total_steps": 64460, "loss": 0.23, "lr": 8.983723225377535e-06, "epoch": 5.718274899162271, "percentage": 28.59, "elapsed_time": "0:33:33", "remaining_time": "1:23:49", "throughput": 5576.65, "total_tokens": 11230944} {"current_steps": 18435, "total_steps": 64460, "loss": 0.2362, "lr": 8.982904951375462e-06, "epoch": 5.719826248836488, "percentage": 28.6, "elapsed_time": "0:33:34", "remaining_time": "1:23:49", "throughput": 5576.75, "total_tokens": 11234560} {"current_steps": 18440, "total_steps": 64460, "loss": 0.2315, "lr": 8.98208638537929e-06, "epoch": 5.7213775985107045, "percentage": 28.61, "elapsed_time": "0:33:35", "remaining_time": "1:23:49", "throughput": 5576.29, "total_tokens": 11236832} {"current_steps": 18445, "total_steps": 64460, "loss": 0.2325, "lr": 8.981267527449032e-06, "epoch": 5.722928948184921, "percentage": 28.61, "elapsed_time": "0:33:35", "remaining_time": "1:23:48", "throughput": 5576.35, "total_tokens": 11240768} {"current_steps": 18450, "total_steps": 64460, "loss": 0.2335, "lr": 8.980448377644718e-06, "epoch": 5.724480297859137, "percentage": 28.62, "elapsed_time": "0:33:36", "remaining_time": "1:23:48", "throughput": 5576.4, "total_tokens": 11243808} {"current_steps": 18455, "total_steps": 64460, "loss": 0.2343, "lr": 8.979628936026404e-06, "epoch": 5.726031647533354, "percentage": 28.63, "elapsed_time": "0:33:36", "remaining_time": "1:23:47", "throughput": 5576.21, "total_tokens": 11246464} {"current_steps": 18460, "total_steps": 64460, "loss": 0.2249, "lr": 8.978809202654161e-06, "epoch": 5.727582997207571, "percentage": 28.64, "elapsed_time": "0:33:37", "remaining_time": "1:23:46", "throughput": 5576.13, "total_tokens": 11248960} {"current_steps": 18465, "total_steps": 64460, "loss": 0.2277, "lr": 8.977989177588088e-06, "epoch": 5.7291343468817875, "percentage": 28.65, "elapsed_time": "0:33:37", "remaining_time": "1:23:46", "throughput": 5576.4, "total_tokens": 11252640} {"current_steps": 18470, "total_steps": 64460, "loss": 0.2382, "lr": 8.977168860888304e-06, "epoch": 5.730685696556003, "percentage": 28.65, "elapsed_time": "0:33:38", "remaining_time": "1:23:45", "throughput": 5576.46, "total_tokens": 11255456} {"current_steps": 18475, "total_steps": 64460, "loss": 0.2291, "lr": 8.976348252614944e-06, "epoch": 5.73223704623022, "percentage": 28.66, "elapsed_time": "0:33:38", "remaining_time": "1:23:45", "throughput": 5576.69, "total_tokens": 11258944} {"current_steps": 18480, "total_steps": 64460, "loss": 0.2262, "lr": 8.975527352828169e-06, "epoch": 5.733788395904437, "percentage": 28.67, "elapsed_time": "0:33:39", "remaining_time": "1:23:44", "throughput": 5576.66, "total_tokens": 11261536} {"current_steps": 18485, "total_steps": 64460, "loss": 0.2379, "lr": 8.974706161588162e-06, "epoch": 5.735339745578654, "percentage": 28.68, "elapsed_time": "0:33:39", "remaining_time": "1:23:43", "throughput": 5576.64, "total_tokens": 11264192} {"current_steps": 18490, "total_steps": 64460, "loss": 0.2304, "lr": 8.973884678955127e-06, "epoch": 5.73689109525287, "percentage": 28.68, "elapsed_time": "0:33:40", "remaining_time": "1:23:43", "throughput": 5576.73, "total_tokens": 11267072} {"current_steps": 18495, "total_steps": 64460, "loss": 0.2307, "lr": 8.973062904989288e-06, "epoch": 5.738442444927086, "percentage": 28.69, "elapsed_time": "0:33:40", "remaining_time": "1:23:42", "throughput": 5576.77, "total_tokens": 11270080} {"current_steps": 18500, "total_steps": 64460, "loss": 0.2342, "lr": 8.972240839750888e-06, "epoch": 5.739993794601303, "percentage": 28.7, "elapsed_time": "0:33:41", "remaining_time": "1:23:41", "throughput": 5576.8, "total_tokens": 11273024} {"current_steps": 18505, "total_steps": 64460, "loss": 0.2316, "lr": 8.971418483300197e-06, "epoch": 5.74154514427552, "percentage": 28.71, "elapsed_time": "0:33:41", "remaining_time": "1:23:41", "throughput": 5576.73, "total_tokens": 11275520} {"current_steps": 18510, "total_steps": 64460, "loss": 0.2329, "lr": 8.970595835697502e-06, "epoch": 5.743096493949737, "percentage": 28.72, "elapsed_time": "0:33:42", "remaining_time": "1:23:40", "throughput": 5576.56, "total_tokens": 11277824} {"current_steps": 18515, "total_steps": 64460, "loss": 0.2357, "lr": 8.969772897003116e-06, "epoch": 5.7446478436239525, "percentage": 28.72, "elapsed_time": "0:33:43", "remaining_time": "1:23:40", "throughput": 5576.99, "total_tokens": 11282848} {"current_steps": 18520, "total_steps": 64460, "loss": 0.2262, "lr": 8.968949667277364e-06, "epoch": 5.746199193298169, "percentage": 28.73, "elapsed_time": "0:33:43", "remaining_time": "1:23:39", "throughput": 5577.23, "total_tokens": 11286688} {"current_steps": 18525, "total_steps": 64460, "loss": 0.2316, "lr": 8.968126146580602e-06, "epoch": 5.747750542972386, "percentage": 28.74, "elapsed_time": "0:33:44", "remaining_time": "1:23:39", "throughput": 5577.09, "total_tokens": 11289440} {"current_steps": 18530, "total_steps": 64460, "loss": 0.2316, "lr": 8.967302334973206e-06, "epoch": 5.749301892646603, "percentage": 28.75, "elapsed_time": "0:33:44", "remaining_time": "1:23:38", "throughput": 5577.22, "total_tokens": 11292512} {"current_steps": 18535, "total_steps": 64460, "loss": 0.2337, "lr": 8.966478232515568e-06, "epoch": 5.750853242320819, "percentage": 28.75, "elapsed_time": "0:33:45", "remaining_time": "1:23:38", "throughput": 5576.96, "total_tokens": 11295104} {"current_steps": 18540, "total_steps": 64460, "loss": 0.228, "lr": 8.965653839268104e-06, "epoch": 5.7524045919950355, "percentage": 28.76, "elapsed_time": "0:33:45", "remaining_time": "1:23:37", "throughput": 5576.6, "total_tokens": 11297280} {"current_steps": 18545, "total_steps": 64460, "loss": 0.2324, "lr": 8.964829155291257e-06, "epoch": 5.753955941669252, "percentage": 28.77, "elapsed_time": "0:33:46", "remaining_time": "1:23:37", "throughput": 5576.72, "total_tokens": 11300544} {"current_steps": 18550, "total_steps": 64460, "loss": 0.2321, "lr": 8.964004180645478e-06, "epoch": 5.755507291343469, "percentage": 28.78, "elapsed_time": "0:33:46", "remaining_time": "1:23:36", "throughput": 5576.86, "total_tokens": 11303584} {"current_steps": 18555, "total_steps": 64460, "loss": 0.2346, "lr": 8.963178915391255e-06, "epoch": 5.757058641017686, "percentage": 28.79, "elapsed_time": "0:33:47", "remaining_time": "1:23:35", "throughput": 5577.05, "total_tokens": 11307200} {"current_steps": 18560, "total_steps": 64460, "loss": 0.23, "lr": 8.962353359589085e-06, "epoch": 5.758609990691902, "percentage": 28.79, "elapsed_time": "0:33:48", "remaining_time": "1:23:35", "throughput": 5577.23, "total_tokens": 11310656} {"current_steps": 18565, "total_steps": 64460, "loss": 0.2319, "lr": 8.961527513299492e-06, "epoch": 5.7601613403661185, "percentage": 28.8, "elapsed_time": "0:33:48", "remaining_time": "1:23:35", "throughput": 5577.65, "total_tokens": 11315200} {"current_steps": 18570, "total_steps": 64460, "loss": 0.2342, "lr": 8.960701376583022e-06, "epoch": 5.761712690040335, "percentage": 28.81, "elapsed_time": "0:33:49", "remaining_time": "1:23:34", "throughput": 5577.96, "total_tokens": 11319008} {"current_steps": 18575, "total_steps": 64460, "loss": 0.2321, "lr": 8.959874949500238e-06, "epoch": 5.763264039714552, "percentage": 28.82, "elapsed_time": "0:33:49", "remaining_time": "1:23:33", "throughput": 5577.86, "total_tokens": 11321664} {"current_steps": 18580, "total_steps": 64460, "loss": 0.2347, "lr": 8.959048232111728e-06, "epoch": 5.764815389388768, "percentage": 28.82, "elapsed_time": "0:33:50", "remaining_time": "1:23:33", "throughput": 5577.97, "total_tokens": 11324768} {"current_steps": 18585, "total_steps": 64460, "loss": 0.2253, "lr": 8.958221224478103e-06, "epoch": 5.766366739062985, "percentage": 28.83, "elapsed_time": "0:33:50", "remaining_time": "1:23:32", "throughput": 5577.98, "total_tokens": 11327456} {"current_steps": 18590, "total_steps": 64460, "loss": 0.2315, "lr": 8.957393926659988e-06, "epoch": 5.7679180887372015, "percentage": 28.84, "elapsed_time": "0:33:51", "remaining_time": "1:23:31", "throughput": 5578.02, "total_tokens": 11330208} {"current_steps": 18595, "total_steps": 64460, "loss": 0.2347, "lr": 8.956566338718035e-06, "epoch": 5.769469438411418, "percentage": 28.85, "elapsed_time": "0:33:51", "remaining_time": "1:23:31", "throughput": 5577.9, "total_tokens": 11332512} {"current_steps": 18600, "total_steps": 64460, "loss": 0.2315, "lr": 8.95573846071292e-06, "epoch": 5.771020788085634, "percentage": 28.86, "elapsed_time": "0:33:52", "remaining_time": "1:23:30", "throughput": 5578.02, "total_tokens": 11335424} {"current_steps": 18605, "total_steps": 64460, "loss": 0.2329, "lr": 8.95491029270533e-06, "epoch": 5.772572137759851, "percentage": 28.86, "elapsed_time": "0:33:52", "remaining_time": "1:23:29", "throughput": 5578.24, "total_tokens": 11339008} {"current_steps": 18610, "total_steps": 64460, "loss": 0.231, "lr": 8.954081834755981e-06, "epoch": 5.774123487434068, "percentage": 28.87, "elapsed_time": "0:33:53", "remaining_time": "1:23:29", "throughput": 5578.21, "total_tokens": 11341536} {"current_steps": 18615, "total_steps": 64460, "loss": 0.2309, "lr": 8.953253086925614e-06, "epoch": 5.775674837108284, "percentage": 28.88, "elapsed_time": "0:33:53", "remaining_time": "1:23:28", "throughput": 5578.28, "total_tokens": 11344640} {"current_steps": 18620, "total_steps": 64460, "loss": 0.2299, "lr": 8.95242404927498e-06, "epoch": 5.777226186782501, "percentage": 28.89, "elapsed_time": "0:33:54", "remaining_time": "1:23:27", "throughput": 5578.25, "total_tokens": 11347104} {"current_steps": 18625, "total_steps": 64460, "loss": 0.2254, "lr": 8.951594721864859e-06, "epoch": 5.778777536456717, "percentage": 28.89, "elapsed_time": "0:33:54", "remaining_time": "1:23:27", "throughput": 5578.64, "total_tokens": 11351264} {"current_steps": 18630, "total_steps": 64460, "loss": 0.2241, "lr": 8.950765104756051e-06, "epoch": 5.780328886130934, "percentage": 28.9, "elapsed_time": "0:33:55", "remaining_time": "1:23:26", "throughput": 5578.57, "total_tokens": 11354080} {"current_steps": 18635, "total_steps": 64460, "loss": 0.2315, "lr": 8.949935198009379e-06, "epoch": 5.781880235805151, "percentage": 28.91, "elapsed_time": "0:33:55", "remaining_time": "1:23:26", "throughput": 5578.5, "total_tokens": 11357472} {"current_steps": 18640, "total_steps": 64460, "loss": 0.223, "lr": 8.949105001685681e-06, "epoch": 5.783431585479367, "percentage": 28.92, "elapsed_time": "0:33:56", "remaining_time": "1:23:25", "throughput": 5578.64, "total_tokens": 11360480} {"current_steps": 18645, "total_steps": 64460, "loss": 0.237, "lr": 8.948274515845822e-06, "epoch": 5.784982935153583, "percentage": 28.92, "elapsed_time": "0:33:56", "remaining_time": "1:23:25", "throughput": 5578.47, "total_tokens": 11362848} {"current_steps": 18650, "total_steps": 64460, "loss": 0.2259, "lr": 8.947443740550687e-06, "epoch": 5.7865342848278, "percentage": 28.93, "elapsed_time": "0:33:57", "remaining_time": "1:23:24", "throughput": 5578.48, "total_tokens": 11365472} {"current_steps": 18655, "total_steps": 64460, "loss": 0.2246, "lr": 8.94661267586118e-06, "epoch": 5.788085634502017, "percentage": 28.94, "elapsed_time": "0:33:57", "remaining_time": "1:23:23", "throughput": 5578.47, "total_tokens": 11368064} {"current_steps": 18660, "total_steps": 64460, "loss": 0.2235, "lr": 8.94578132183823e-06, "epoch": 5.789636984176234, "percentage": 28.95, "elapsed_time": "0:33:58", "remaining_time": "1:23:22", "throughput": 5578.48, "total_tokens": 11370720} {"current_steps": 18665, "total_steps": 64460, "loss": 0.2315, "lr": 8.944949678542785e-06, "epoch": 5.7911883338504495, "percentage": 28.96, "elapsed_time": "0:33:58", "remaining_time": "1:23:22", "throughput": 5578.49, "total_tokens": 11373408} {"current_steps": 18670, "total_steps": 64460, "loss": 0.25, "lr": 8.944117746035811e-06, "epoch": 5.792739683524666, "percentage": 28.96, "elapsed_time": "0:33:59", "remaining_time": "1:23:21", "throughput": 5578.62, "total_tokens": 11376544} {"current_steps": 18675, "total_steps": 64460, "loss": 0.2376, "lr": 8.943285524378303e-06, "epoch": 5.794291033198883, "percentage": 28.97, "elapsed_time": "0:33:59", "remaining_time": "1:23:21", "throughput": 5578.84, "total_tokens": 11380000} {"current_steps": 18680, "total_steps": 64460, "loss": 0.2331, "lr": 8.94245301363127e-06, "epoch": 5.7958423828731, "percentage": 28.98, "elapsed_time": "0:34:00", "remaining_time": "1:23:20", "throughput": 5578.93, "total_tokens": 11382784} {"current_steps": 18685, "total_steps": 64460, "loss": 0.2246, "lr": 8.941620213855743e-06, "epoch": 5.797393732547317, "percentage": 28.99, "elapsed_time": "0:34:00", "remaining_time": "1:23:19", "throughput": 5578.83, "total_tokens": 11385184} {"current_steps": 18690, "total_steps": 64460, "loss": 0.2246, "lr": 8.940787125112782e-06, "epoch": 5.7989450822215325, "percentage": 28.99, "elapsed_time": "0:34:01", "remaining_time": "1:23:19", "throughput": 5579.06, "total_tokens": 11388832} {"current_steps": 18695, "total_steps": 64460, "loss": 0.2438, "lr": 8.939953747463457e-06, "epoch": 5.800496431895749, "percentage": 29.0, "elapsed_time": "0:34:01", "remaining_time": "1:23:18", "throughput": 5579.04, "total_tokens": 11391328} {"current_steps": 18700, "total_steps": 64460, "loss": 0.2318, "lr": 8.939120080968866e-06, "epoch": 5.802047781569966, "percentage": 29.01, "elapsed_time": "0:34:02", "remaining_time": "1:23:17", "throughput": 5579.32, "total_tokens": 11395008} {"current_steps": 18705, "total_steps": 64460, "loss": 0.2368, "lr": 8.938286125690129e-06, "epoch": 5.803599131244183, "percentage": 29.02, "elapsed_time": "0:34:02", "remaining_time": "1:23:17", "throughput": 5579.54, "total_tokens": 11398464} {"current_steps": 18710, "total_steps": 64460, "loss": 0.2304, "lr": 8.937451881688382e-06, "epoch": 5.805150480918399, "percentage": 29.03, "elapsed_time": "0:34:03", "remaining_time": "1:23:16", "throughput": 5579.53, "total_tokens": 11400928} {"current_steps": 18715, "total_steps": 64460, "loss": 0.2325, "lr": 8.936617349024783e-06, "epoch": 5.8067018305926155, "percentage": 29.03, "elapsed_time": "0:34:03", "remaining_time": "1:23:15", "throughput": 5579.84, "total_tokens": 11404864} {"current_steps": 18720, "total_steps": 64460, "loss": 0.2308, "lr": 8.93578252776052e-06, "epoch": 5.808253180266832, "percentage": 29.04, "elapsed_time": "0:34:04", "remaining_time": "1:23:15", "throughput": 5579.89, "total_tokens": 11407968} {"current_steps": 18725, "total_steps": 64460, "loss": 0.2309, "lr": 8.934947417956788e-06, "epoch": 5.809804529941049, "percentage": 29.05, "elapsed_time": "0:34:04", "remaining_time": "1:23:14", "throughput": 5579.79, "total_tokens": 11410272} {"current_steps": 18730, "total_steps": 64460, "loss": 0.2325, "lr": 8.934112019674814e-06, "epoch": 5.811355879615265, "percentage": 29.06, "elapsed_time": "0:34:05", "remaining_time": "1:23:13", "throughput": 5579.88, "total_tokens": 11413120} {"current_steps": 18735, "total_steps": 64460, "loss": 0.2389, "lr": 8.933276332975842e-06, "epoch": 5.812907229289482, "percentage": 29.06, "elapsed_time": "0:34:05", "remaining_time": "1:23:13", "throughput": 5579.97, "total_tokens": 11416064} {"current_steps": 18740, "total_steps": 64460, "loss": 0.2331, "lr": 8.93244035792114e-06, "epoch": 5.814458578963698, "percentage": 29.07, "elapsed_time": "0:34:06", "remaining_time": "1:23:12", "throughput": 5579.93, "total_tokens": 11418592} {"current_steps": 18745, "total_steps": 64460, "loss": 0.235, "lr": 8.931604094571991e-06, "epoch": 5.816009928637915, "percentage": 29.08, "elapsed_time": "0:34:06", "remaining_time": "1:23:11", "throughput": 5579.92, "total_tokens": 11421376} {"current_steps": 18750, "total_steps": 64460, "loss": 0.2295, "lr": 8.930767542989704e-06, "epoch": 5.817561278312132, "percentage": 29.09, "elapsed_time": "0:34:07", "remaining_time": "1:23:11", "throughput": 5579.68, "total_tokens": 11423712} {"current_steps": 18755, "total_steps": 64460, "loss": 0.2335, "lr": 8.929930703235609e-06, "epoch": 5.819112627986348, "percentage": 29.1, "elapsed_time": "0:34:07", "remaining_time": "1:23:10", "throughput": 5579.96, "total_tokens": 11427552} {"current_steps": 18760, "total_steps": 64460, "loss": 0.2277, "lr": 8.929093575371058e-06, "epoch": 5.820663977660565, "percentage": 29.1, "elapsed_time": "0:34:08", "remaining_time": "1:23:10", "throughput": 5580.05, "total_tokens": 11430656} {"current_steps": 18765, "total_steps": 64460, "loss": 0.2331, "lr": 8.928256159457419e-06, "epoch": 5.822215327334781, "percentage": 29.11, "elapsed_time": "0:34:09", "remaining_time": "1:23:09", "throughput": 5580.18, "total_tokens": 11434016} {"current_steps": 18770, "total_steps": 64460, "loss": 0.2263, "lr": 8.927418455556086e-06, "epoch": 5.823766677008998, "percentage": 29.12, "elapsed_time": "0:34:09", "remaining_time": "1:23:08", "throughput": 5580.11, "total_tokens": 11436416} {"current_steps": 18775, "total_steps": 64460, "loss": 0.2314, "lr": 8.926580463728472e-06, "epoch": 5.825318026683214, "percentage": 29.13, "elapsed_time": "0:34:09", "remaining_time": "1:23:08", "throughput": 5580.17, "total_tokens": 11439168} {"current_steps": 18780, "total_steps": 64460, "loss": 0.2342, "lr": 8.925742184036014e-06, "epoch": 5.826869376357431, "percentage": 29.13, "elapsed_time": "0:34:10", "remaining_time": "1:23:07", "throughput": 5580.51, "total_tokens": 11443744} {"current_steps": 18785, "total_steps": 64460, "loss": 0.2258, "lr": 8.924903616540164e-06, "epoch": 5.828420726031648, "percentage": 29.14, "elapsed_time": "0:34:11", "remaining_time": "1:23:07", "throughput": 5580.48, "total_tokens": 11446208} {"current_steps": 18790, "total_steps": 64460, "loss": 0.227, "lr": 8.924064761302403e-06, "epoch": 5.829972075705864, "percentage": 29.15, "elapsed_time": "0:34:11", "remaining_time": "1:23:06", "throughput": 5580.8, "total_tokens": 11450176} {"current_steps": 18795, "total_steps": 64460, "loss": 0.2281, "lr": 8.923225618384228e-06, "epoch": 5.83152342538008, "percentage": 29.16, "elapsed_time": "0:34:12", "remaining_time": "1:23:06", "throughput": 5580.78, "total_tokens": 11452704} {"current_steps": 18800, "total_steps": 64460, "loss": 0.2349, "lr": 8.922386187847155e-06, "epoch": 5.833074775054297, "percentage": 29.17, "elapsed_time": "0:34:12", "remaining_time": "1:23:05", "throughput": 5580.85, "total_tokens": 11455328} {"current_steps": 18805, "total_steps": 64460, "loss": 0.2239, "lr": 8.921546469752726e-06, "epoch": 5.834626124728514, "percentage": 29.17, "elapsed_time": "0:34:13", "remaining_time": "1:23:04", "throughput": 5581.01, "total_tokens": 11458720} {"current_steps": 18810, "total_steps": 64460, "loss": 0.2261, "lr": 8.920706464162506e-06, "epoch": 5.836177474402731, "percentage": 29.18, "elapsed_time": "0:34:13", "remaining_time": "1:23:03", "throughput": 5581.11, "total_tokens": 11461632} {"current_steps": 18815, "total_steps": 64460, "loss": 0.2291, "lr": 8.91986617113807e-06, "epoch": 5.837728824076947, "percentage": 29.19, "elapsed_time": "0:34:14", "remaining_time": "1:23:03", "throughput": 5581.34, "total_tokens": 11465312} {"current_steps": 18820, "total_steps": 64460, "loss": 0.2384, "lr": 8.919025590741029e-06, "epoch": 5.839280173751163, "percentage": 29.2, "elapsed_time": "0:34:14", "remaining_time": "1:23:02", "throughput": 5581.34, "total_tokens": 11468064} {"current_steps": 18825, "total_steps": 64460, "loss": 0.2305, "lr": 8.918184723033002e-06, "epoch": 5.84083152342538, "percentage": 29.2, "elapsed_time": "0:34:15", "remaining_time": "1:23:02", "throughput": 5581.45, "total_tokens": 11471200} {"current_steps": 18830, "total_steps": 64460, "loss": 0.226, "lr": 8.917343568075636e-06, "epoch": 5.842382873099597, "percentage": 29.21, "elapsed_time": "0:34:15", "remaining_time": "1:23:01", "throughput": 5581.62, "total_tokens": 11474656} {"current_steps": 18835, "total_steps": 64460, "loss": 0.229, "lr": 8.9165021259306e-06, "epoch": 5.843934222773814, "percentage": 29.22, "elapsed_time": "0:34:16", "remaining_time": "1:23:01", "throughput": 5581.6, "total_tokens": 11477280} {"current_steps": 18840, "total_steps": 64460, "loss": 0.232, "lr": 8.915660396659579e-06, "epoch": 5.8454855724480295, "percentage": 29.23, "elapsed_time": "0:34:16", "remaining_time": "1:23:00", "throughput": 5581.67, "total_tokens": 11480352} {"current_steps": 18845, "total_steps": 64460, "loss": 0.2283, "lr": 8.914818380324282e-06, "epoch": 5.847036922122246, "percentage": 29.24, "elapsed_time": "0:34:17", "remaining_time": "1:22:59", "throughput": 5581.71, "total_tokens": 11483104} {"current_steps": 18850, "total_steps": 64460, "loss": 0.2319, "lr": 8.91397607698644e-06, "epoch": 5.848588271796463, "percentage": 29.24, "elapsed_time": "0:34:17", "remaining_time": "1:22:59", "throughput": 5581.89, "total_tokens": 11486592} {"current_steps": 18855, "total_steps": 64460, "loss": 0.2348, "lr": 8.913133486707803e-06, "epoch": 5.85013962147068, "percentage": 29.25, "elapsed_time": "0:34:18", "remaining_time": "1:22:58", "throughput": 5582.17, "total_tokens": 11490272} {"current_steps": 18860, "total_steps": 64460, "loss": 0.2297, "lr": 8.912290609550144e-06, "epoch": 5.851690971144896, "percentage": 29.26, "elapsed_time": "0:34:18", "remaining_time": "1:22:57", "throughput": 5582.12, "total_tokens": 11492736} {"current_steps": 18865, "total_steps": 64460, "loss": 0.2329, "lr": 8.911447445575254e-06, "epoch": 5.853242320819112, "percentage": 29.27, "elapsed_time": "0:34:19", "remaining_time": "1:22:57", "throughput": 5582.05, "total_tokens": 11495072} {"current_steps": 18870, "total_steps": 64460, "loss": 0.2236, "lr": 8.910603994844947e-06, "epoch": 5.854793670493329, "percentage": 29.27, "elapsed_time": "0:34:19", "remaining_time": "1:22:56", "throughput": 5582.27, "total_tokens": 11499072} {"current_steps": 18875, "total_steps": 64460, "loss": 0.2409, "lr": 8.909760257421061e-06, "epoch": 5.856345020167546, "percentage": 29.28, "elapsed_time": "0:34:20", "remaining_time": "1:22:56", "throughput": 5582.77, "total_tokens": 11504192} {"current_steps": 18880, "total_steps": 64460, "loss": 0.2221, "lr": 8.908916233365448e-06, "epoch": 5.857896369841763, "percentage": 29.29, "elapsed_time": "0:34:21", "remaining_time": "1:22:56", "throughput": 5582.92, "total_tokens": 11507392} {"current_steps": 18885, "total_steps": 64460, "loss": 0.2358, "lr": 8.908071922739986e-06, "epoch": 5.859447719515979, "percentage": 29.3, "elapsed_time": "0:34:21", "remaining_time": "1:22:55", "throughput": 5583.13, "total_tokens": 11510528} {"current_steps": 18890, "total_steps": 64460, "loss": 0.2287, "lr": 8.907227325606574e-06, "epoch": 5.860999069190195, "percentage": 29.3, "elapsed_time": "0:34:22", "remaining_time": "1:22:54", "throughput": 5583.17, "total_tokens": 11513248} {"current_steps": 18895, "total_steps": 64460, "loss": 0.2355, "lr": 8.906382442027131e-06, "epoch": 5.862550418864412, "percentage": 29.31, "elapsed_time": "0:34:22", "remaining_time": "1:22:54", "throughput": 5583.41, "total_tokens": 11516800} {"current_steps": 18900, "total_steps": 64460, "loss": 0.2298, "lr": 8.905537272063595e-06, "epoch": 5.864101768538629, "percentage": 29.32, "elapsed_time": "0:34:23", "remaining_time": "1:22:53", "throughput": 5583.25, "total_tokens": 11518976} {"current_steps": 18905, "total_steps": 64460, "loss": 0.2281, "lr": 8.904691815777931e-06, "epoch": 5.865653118212845, "percentage": 29.33, "elapsed_time": "0:34:23", "remaining_time": "1:22:52", "throughput": 5583.49, "total_tokens": 11522464} {"current_steps": 18910, "total_steps": 64460, "loss": 0.2286, "lr": 8.903846073232116e-06, "epoch": 5.867204467887062, "percentage": 29.34, "elapsed_time": "0:34:24", "remaining_time": "1:22:52", "throughput": 5583.72, "total_tokens": 11526560} {"current_steps": 18915, "total_steps": 64460, "loss": 0.2323, "lr": 8.903000044488157e-06, "epoch": 5.868755817561278, "percentage": 29.34, "elapsed_time": "0:34:24", "remaining_time": "1:22:51", "throughput": 5583.88, "total_tokens": 11529696} {"current_steps": 18920, "total_steps": 64460, "loss": 0.2335, "lr": 8.902153729608076e-06, "epoch": 5.870307167235495, "percentage": 29.35, "elapsed_time": "0:34:25", "remaining_time": "1:22:51", "throughput": 5583.84, "total_tokens": 11532320} {"current_steps": 18925, "total_steps": 64460, "loss": 0.2277, "lr": 8.901307128653918e-06, "epoch": 5.871858516909711, "percentage": 29.36, "elapsed_time": "0:34:25", "remaining_time": "1:22:50", "throughput": 5583.82, "total_tokens": 11534976} {"current_steps": 18930, "total_steps": 64460, "loss": 0.2326, "lr": 8.900460241687749e-06, "epoch": 5.873409866583928, "percentage": 29.37, "elapsed_time": "0:34:26", "remaining_time": "1:22:49", "throughput": 5583.92, "total_tokens": 11537920} {"current_steps": 18935, "total_steps": 64460, "loss": 0.2254, "lr": 8.899613068771658e-06, "epoch": 5.874961216258145, "percentage": 29.37, "elapsed_time": "0:34:26", "remaining_time": "1:22:49", "throughput": 5583.72, "total_tokens": 11540192} {"current_steps": 18940, "total_steps": 64460, "loss": 0.2324, "lr": 8.898765609967747e-06, "epoch": 5.876512565932361, "percentage": 29.38, "elapsed_time": "0:34:27", "remaining_time": "1:22:48", "throughput": 5584.11, "total_tokens": 11545024} {"current_steps": 18945, "total_steps": 64460, "loss": 0.2278, "lr": 8.89791786533815e-06, "epoch": 5.878063915606578, "percentage": 29.39, "elapsed_time": "0:34:27", "remaining_time": "1:22:48", "throughput": 5584.03, "total_tokens": 11547552} {"current_steps": 18950, "total_steps": 64460, "loss": 0.2361, "lr": 8.897069834945016e-06, "epoch": 5.879615265280794, "percentage": 29.4, "elapsed_time": "0:34:28", "remaining_time": "1:22:47", "throughput": 5584.2, "total_tokens": 11551040} {"current_steps": 18955, "total_steps": 64460, "loss": 0.2354, "lr": 8.896221518850515e-06, "epoch": 5.881166614955011, "percentage": 29.41, "elapsed_time": "0:34:29", "remaining_time": "1:22:47", "throughput": 5584.31, "total_tokens": 11554016} {"current_steps": 18960, "total_steps": 64460, "loss": 0.2283, "lr": 8.895372917116838e-06, "epoch": 5.882717964629228, "percentage": 29.41, "elapsed_time": "0:34:29", "remaining_time": "1:22:46", "throughput": 5584.43, "total_tokens": 11556960} {"current_steps": 18965, "total_steps": 64460, "loss": 0.2305, "lr": 8.894524029806198e-06, "epoch": 5.884269314303444, "percentage": 29.42, "elapsed_time": "0:34:29", "remaining_time": "1:22:45", "throughput": 5584.56, "total_tokens": 11559968} {"current_steps": 18970, "total_steps": 64460, "loss": 0.2329, "lr": 8.893674856980829e-06, "epoch": 5.88582066397766, "percentage": 29.43, "elapsed_time": "0:34:30", "remaining_time": "1:22:45", "throughput": 5584.71, "total_tokens": 11563424} {"current_steps": 18975, "total_steps": 64460, "loss": 0.2278, "lr": 8.892825398702985e-06, "epoch": 5.887372013651877, "percentage": 29.44, "elapsed_time": "0:34:31", "remaining_time": "1:22:44", "throughput": 5584.89, "total_tokens": 11566752} {"current_steps": 18980, "total_steps": 64460, "loss": 0.2346, "lr": 8.89197565503494e-06, "epoch": 5.888923363326094, "percentage": 29.44, "elapsed_time": "0:34:31", "remaining_time": "1:22:44", "throughput": 5585.09, "total_tokens": 11570240} {"current_steps": 18985, "total_steps": 64460, "loss": 0.2257, "lr": 8.891125626038992e-06, "epoch": 5.890474713000311, "percentage": 29.45, "elapsed_time": "0:34:32", "remaining_time": "1:22:43", "throughput": 5584.95, "total_tokens": 11572448} {"current_steps": 18990, "total_steps": 64460, "loss": 0.2347, "lr": 8.89027531177746e-06, "epoch": 5.892026062674526, "percentage": 29.46, "elapsed_time": "0:34:32", "remaining_time": "1:22:42", "throughput": 5585.11, "total_tokens": 11575680} {"current_steps": 18995, "total_steps": 64460, "loss": 0.2315, "lr": 8.889424712312678e-06, "epoch": 5.893577412348743, "percentage": 29.47, "elapsed_time": "0:34:33", "remaining_time": "1:22:41", "throughput": 5585.04, "total_tokens": 11578016} {"current_steps": 19000, "total_steps": 64460, "loss": 0.2381, "lr": 8.888573827707006e-06, "epoch": 5.89512876202296, "percentage": 29.48, "elapsed_time": "0:34:33", "remaining_time": "1:22:41", "throughput": 5585.12, "total_tokens": 11580960} {"current_steps": 19005, "total_steps": 64460, "loss": 0.238, "lr": 8.887722658022825e-06, "epoch": 5.896680111697177, "percentage": 29.48, "elapsed_time": "0:34:34", "remaining_time": "1:22:40", "throughput": 5585.12, "total_tokens": 11583616} {"current_steps": 19010, "total_steps": 64460, "loss": 0.2305, "lr": 8.886871203322538e-06, "epoch": 5.8982314613713935, "percentage": 29.49, "elapsed_time": "0:34:34", "remaining_time": "1:22:39", "throughput": 5585.11, "total_tokens": 11586208} {"current_steps": 19015, "total_steps": 64460, "loss": 0.2265, "lr": 8.886019463668562e-06, "epoch": 5.899782811045609, "percentage": 29.5, "elapsed_time": "0:34:34", "remaining_time": "1:22:39", "throughput": 5585.21, "total_tokens": 11589088} {"current_steps": 19020, "total_steps": 64460, "loss": 0.2255, "lr": 8.885167439123343e-06, "epoch": 5.901334160719826, "percentage": 29.51, "elapsed_time": "0:34:35", "remaining_time": "1:22:38", "throughput": 5585.41, "total_tokens": 11592352} {"current_steps": 19025, "total_steps": 64460, "loss": 0.2306, "lr": 8.884315129749344e-06, "epoch": 5.902885510394043, "percentage": 29.51, "elapsed_time": "0:34:36", "remaining_time": "1:22:37", "throughput": 5585.74, "total_tokens": 11596224} {"current_steps": 19030, "total_steps": 64460, "loss": 0.2347, "lr": 8.883462535609046e-06, "epoch": 5.90443686006826, "percentage": 29.52, "elapsed_time": "0:34:36", "remaining_time": "1:22:37", "throughput": 5585.99, "total_tokens": 11600128} {"current_steps": 19035, "total_steps": 64460, "loss": 0.2359, "lr": 8.88260965676496e-06, "epoch": 5.905988209742476, "percentage": 29.53, "elapsed_time": "0:34:37", "remaining_time": "1:22:36", "throughput": 5585.78, "total_tokens": 11602144} {"current_steps": 19040, "total_steps": 64460, "loss": 0.2342, "lr": 8.881756493279608e-06, "epoch": 5.907539559416692, "percentage": 29.54, "elapsed_time": "0:34:37", "remaining_time": "1:22:35", "throughput": 5585.86, "total_tokens": 11604832} {"current_steps": 19045, "total_steps": 64460, "loss": 0.2296, "lr": 8.880903045215538e-06, "epoch": 5.909090909090909, "percentage": 29.55, "elapsed_time": "0:34:38", "remaining_time": "1:22:35", "throughput": 5585.87, "total_tokens": 11607616} {"current_steps": 19050, "total_steps": 64460, "loss": 0.2342, "lr": 8.88004931263532e-06, "epoch": 5.910642258765126, "percentage": 29.55, "elapsed_time": "0:34:38", "remaining_time": "1:22:34", "throughput": 5585.81, "total_tokens": 11609984} {"current_steps": 19055, "total_steps": 64460, "loss": 0.2324, "lr": 8.87919529560154e-06, "epoch": 5.912193608439342, "percentage": 29.56, "elapsed_time": "0:34:38", "remaining_time": "1:22:33", "throughput": 5585.96, "total_tokens": 11613152} {"current_steps": 19060, "total_steps": 64460, "loss": 0.237, "lr": 8.878340994176806e-06, "epoch": 5.913744958113559, "percentage": 29.57, "elapsed_time": "0:34:39", "remaining_time": "1:22:33", "throughput": 5585.85, "total_tokens": 11615616} {"current_steps": 19065, "total_steps": 64460, "loss": 0.2314, "lr": 8.877486408423752e-06, "epoch": 5.915296307787775, "percentage": 29.58, "elapsed_time": "0:34:40", "remaining_time": "1:22:32", "throughput": 5586.14, "total_tokens": 11619360} {"current_steps": 19070, "total_steps": 64460, "loss": 0.2304, "lr": 8.87663153840503e-06, "epoch": 5.916847657461992, "percentage": 29.58, "elapsed_time": "0:34:40", "remaining_time": "1:22:31", "throughput": 5586.13, "total_tokens": 11622016} {"current_steps": 19075, "total_steps": 64460, "loss": 0.2325, "lr": 8.875776384183308e-06, "epoch": 5.918399007136209, "percentage": 29.59, "elapsed_time": "0:34:40", "remaining_time": "1:22:31", "throughput": 5586.2, "total_tokens": 11624864} {"current_steps": 19080, "total_steps": 64460, "loss": 0.2363, "lr": 8.874920945821282e-06, "epoch": 5.919950356810425, "percentage": 29.6, "elapsed_time": "0:34:41", "remaining_time": "1:22:30", "throughput": 5586.17, "total_tokens": 11627424} {"current_steps": 19085, "total_steps": 64460, "loss": 0.237, "lr": 8.874065223381663e-06, "epoch": 5.921501706484642, "percentage": 29.61, "elapsed_time": "0:34:42", "remaining_time": "1:22:30", "throughput": 5586.69, "total_tokens": 11633056} {"current_steps": 19090, "total_steps": 64460, "loss": 0.2272, "lr": 8.873209216927187e-06, "epoch": 5.923053056158858, "percentage": 29.62, "elapsed_time": "0:34:42", "remaining_time": "1:22:29", "throughput": 5586.89, "total_tokens": 11636224} {"current_steps": 19095, "total_steps": 64460, "loss": 0.2337, "lr": 8.872352926520612e-06, "epoch": 5.924604405833075, "percentage": 29.62, "elapsed_time": "0:34:43", "remaining_time": "1:22:29", "throughput": 5586.79, "total_tokens": 11638560} {"current_steps": 19100, "total_steps": 64460, "loss": 0.2363, "lr": 8.871496352224711e-06, "epoch": 5.926155755507291, "percentage": 29.63, "elapsed_time": "0:34:43", "remaining_time": "1:22:28", "throughput": 5586.89, "total_tokens": 11641568} {"current_steps": 19105, "total_steps": 64460, "loss": 0.2351, "lr": 8.870639494102281e-06, "epoch": 5.927707105181508, "percentage": 29.64, "elapsed_time": "0:34:44", "remaining_time": "1:22:28", "throughput": 5587.21, "total_tokens": 11645536} {"current_steps": 19110, "total_steps": 64460, "loss": 0.2299, "lr": 8.869782352216144e-06, "epoch": 5.929258454855725, "percentage": 29.65, "elapsed_time": "0:34:44", "remaining_time": "1:22:27", "throughput": 5587.12, "total_tokens": 11648000} {"current_steps": 19115, "total_steps": 64460, "loss": 0.2321, "lr": 8.868924926629133e-06, "epoch": 5.930809804529941, "percentage": 29.65, "elapsed_time": "0:34:45", "remaining_time": "1:22:26", "throughput": 5587.11, "total_tokens": 11650656} {"current_steps": 19120, "total_steps": 64460, "loss": 0.2291, "lr": 8.86806721740411e-06, "epoch": 5.932361154204157, "percentage": 29.66, "elapsed_time": "0:34:45", "remaining_time": "1:22:26", "throughput": 5587.13, "total_tokens": 11653856} {"current_steps": 19125, "total_steps": 64460, "loss": 0.2408, "lr": 8.867209224603954e-06, "epoch": 5.933912503878374, "percentage": 29.67, "elapsed_time": "0:34:46", "remaining_time": "1:22:25", "throughput": 5586.79, "total_tokens": 11655936} {"current_steps": 19130, "total_steps": 64460, "loss": 0.2376, "lr": 8.866350948291569e-06, "epoch": 5.935463853552591, "percentage": 29.68, "elapsed_time": "0:34:47", "remaining_time": "1:22:25", "throughput": 5587.14, "total_tokens": 11660416} {"current_steps": 19135, "total_steps": 64460, "loss": 0.2354, "lr": 8.865492388529874e-06, "epoch": 5.9370152032268075, "percentage": 29.69, "elapsed_time": "0:34:47", "remaining_time": "1:22:24", "throughput": 5587.23, "total_tokens": 11663392} {"current_steps": 19140, "total_steps": 64460, "loss": 0.2264, "lr": 8.864633545381816e-06, "epoch": 5.938566552901024, "percentage": 29.69, "elapsed_time": "0:34:48", "remaining_time": "1:22:24", "throughput": 5587.51, "total_tokens": 11667264} {"current_steps": 19145, "total_steps": 64460, "loss": 0.2269, "lr": 8.863774418910351e-06, "epoch": 5.94011790257524, "percentage": 29.7, "elapsed_time": "0:34:48", "remaining_time": "1:22:23", "throughput": 5587.62, "total_tokens": 11670272} {"current_steps": 19150, "total_steps": 64460, "loss": 0.2283, "lr": 8.862915009178468e-06, "epoch": 5.941669252249457, "percentage": 29.71, "elapsed_time": "0:34:49", "remaining_time": "1:22:22", "throughput": 5587.66, "total_tokens": 11673024} {"current_steps": 19155, "total_steps": 64460, "loss": 0.2299, "lr": 8.862055316249171e-06, "epoch": 5.943220601923674, "percentage": 29.72, "elapsed_time": "0:34:49", "remaining_time": "1:22:22", "throughput": 5587.77, "total_tokens": 11676128} {"current_steps": 19160, "total_steps": 64460, "loss": 0.2299, "lr": 8.861195340185488e-06, "epoch": 5.9447719515978905, "percentage": 29.72, "elapsed_time": "0:34:50", "remaining_time": "1:22:21", "throughput": 5587.97, "total_tokens": 11679776} {"current_steps": 19165, "total_steps": 64460, "loss": 0.2325, "lr": 8.860335081050461e-06, "epoch": 5.946323301272106, "percentage": 29.73, "elapsed_time": "0:34:50", "remaining_time": "1:22:21", "throughput": 5588.09, "total_tokens": 11682848} {"current_steps": 19170, "total_steps": 64460, "loss": 0.2309, "lr": 8.85947453890716e-06, "epoch": 5.947874650946323, "percentage": 29.74, "elapsed_time": "0:34:51", "remaining_time": "1:22:20", "throughput": 5588.17, "total_tokens": 11685792} {"current_steps": 19175, "total_steps": 64460, "loss": 0.2356, "lr": 8.858613713818674e-06, "epoch": 5.94942600062054, "percentage": 29.75, "elapsed_time": "0:34:51", "remaining_time": "1:22:20", "throughput": 5588.36, "total_tokens": 11690592} {"current_steps": 19180, "total_steps": 64460, "loss": 0.2284, "lr": 8.857752605848107e-06, "epoch": 5.950977350294757, "percentage": 29.75, "elapsed_time": "0:34:52", "remaining_time": "1:22:19", "throughput": 5588.48, "total_tokens": 11693696} {"current_steps": 19185, "total_steps": 64460, "loss": 0.231, "lr": 8.856891215058593e-06, "epoch": 5.952528699968973, "percentage": 29.76, "elapsed_time": "0:34:52", "remaining_time": "1:22:19", "throughput": 5588.54, "total_tokens": 11696544} {"current_steps": 19190, "total_steps": 64460, "loss": 0.2268, "lr": 8.85602954151328e-06, "epoch": 5.954080049643189, "percentage": 29.77, "elapsed_time": "0:34:53", "remaining_time": "1:22:18", "throughput": 5588.79, "total_tokens": 11700096} {"current_steps": 19195, "total_steps": 64460, "loss": 0.2301, "lr": 8.855167585275339e-06, "epoch": 5.955631399317406, "percentage": 29.78, "elapsed_time": "0:34:54", "remaining_time": "1:22:18", "throughput": 5589.01, "total_tokens": 11704704} {"current_steps": 19200, "total_steps": 64460, "loss": 0.2365, "lr": 8.854305346407964e-06, "epoch": 5.957182748991623, "percentage": 29.79, "elapsed_time": "0:34:54", "remaining_time": "1:22:17", "throughput": 5589.06, "total_tokens": 11707680} {"current_steps": 19205, "total_steps": 64460, "loss": 0.2322, "lr": 8.853442824974363e-06, "epoch": 5.95873409866584, "percentage": 29.79, "elapsed_time": "0:34:55", "remaining_time": "1:22:17", "throughput": 5588.77, "total_tokens": 11709824} {"current_steps": 19210, "total_steps": 64460, "loss": 0.2342, "lr": 8.852580021037772e-06, "epoch": 5.960285448340056, "percentage": 29.8, "elapsed_time": "0:34:55", "remaining_time": "1:22:16", "throughput": 5588.74, "total_tokens": 11712448} {"current_steps": 19215, "total_steps": 64460, "loss": 0.2295, "lr": 8.851716934661442e-06, "epoch": 5.961836798014272, "percentage": 29.81, "elapsed_time": "0:34:56", "remaining_time": "1:22:16", "throughput": 5589.0, "total_tokens": 11716768} {"current_steps": 19220, "total_steps": 64460, "loss": 0.2218, "lr": 8.850853565908653e-06, "epoch": 5.963388147688489, "percentage": 29.82, "elapsed_time": "0:34:56", "remaining_time": "1:22:15", "throughput": 5589.21, "total_tokens": 11720448} {"current_steps": 19225, "total_steps": 64460, "loss": 0.2273, "lr": 8.849989914842697e-06, "epoch": 5.964939497362706, "percentage": 29.82, "elapsed_time": "0:34:57", "remaining_time": "1:22:15", "throughput": 5589.46, "total_tokens": 11723936} {"current_steps": 19230, "total_steps": 64460, "loss": 0.2341, "lr": 8.849125981526886e-06, "epoch": 5.966490847036922, "percentage": 29.83, "elapsed_time": "0:34:57", "remaining_time": "1:22:14", "throughput": 5589.52, "total_tokens": 11726784} {"current_steps": 19235, "total_steps": 64460, "loss": 0.2305, "lr": 8.848261766024562e-06, "epoch": 5.968042196711139, "percentage": 29.84, "elapsed_time": "0:34:58", "remaining_time": "1:22:13", "throughput": 5589.53, "total_tokens": 11729440} {"current_steps": 19240, "total_steps": 64460, "loss": 0.2362, "lr": 8.84739726839908e-06, "epoch": 5.969593546385355, "percentage": 29.85, "elapsed_time": "0:34:58", "remaining_time": "1:22:13", "throughput": 5589.55, "total_tokens": 11732448} {"current_steps": 19245, "total_steps": 64460, "loss": 0.2289, "lr": 8.84653248871382e-06, "epoch": 5.971144896059572, "percentage": 29.86, "elapsed_time": "0:34:59", "remaining_time": "1:22:12", "throughput": 5589.56, "total_tokens": 11735264} {"current_steps": 19250, "total_steps": 64460, "loss": 0.2347, "lr": 8.845667427032176e-06, "epoch": 5.972696245733788, "percentage": 29.86, "elapsed_time": "0:35:00", "remaining_time": "1:22:12", "throughput": 5589.91, "total_tokens": 11740032} {"current_steps": 19255, "total_steps": 64460, "loss": 0.231, "lr": 8.844802083417572e-06, "epoch": 5.974247595408005, "percentage": 29.87, "elapsed_time": "0:35:00", "remaining_time": "1:22:11", "throughput": 5589.99, "total_tokens": 11742912} {"current_steps": 19260, "total_steps": 64460, "loss": 0.2263, "lr": 8.843936457933447e-06, "epoch": 5.9757989450822215, "percentage": 29.88, "elapsed_time": "0:35:01", "remaining_time": "1:22:11", "throughput": 5590.16, "total_tokens": 11746304} {"current_steps": 19265, "total_steps": 64460, "loss": 0.229, "lr": 8.843070550643257e-06, "epoch": 5.977350294756438, "percentage": 29.89, "elapsed_time": "0:35:01", "remaining_time": "1:22:10", "throughput": 5590.08, "total_tokens": 11748768} {"current_steps": 19270, "total_steps": 64460, "loss": 0.2347, "lr": 8.842204361610489e-06, "epoch": 5.978901644430655, "percentage": 29.89, "elapsed_time": "0:35:02", "remaining_time": "1:22:10", "throughput": 5590.25, "total_tokens": 11752352} {"current_steps": 19275, "total_steps": 64460, "loss": 0.2301, "lr": 8.841337890898643e-06, "epoch": 5.980452994104871, "percentage": 29.9, "elapsed_time": "0:35:02", "remaining_time": "1:22:09", "throughput": 5590.23, "total_tokens": 11755136} {"current_steps": 19280, "total_steps": 64460, "loss": 0.2272, "lr": 8.840471138571241e-06, "epoch": 5.982004343779088, "percentage": 29.91, "elapsed_time": "0:35:03", "remaining_time": "1:22:08", "throughput": 5590.22, "total_tokens": 11758144} {"current_steps": 19285, "total_steps": 64460, "loss": 0.2331, "lr": 8.839604104691827e-06, "epoch": 5.9835556934533045, "percentage": 29.92, "elapsed_time": "0:35:03", "remaining_time": "1:22:08", "throughput": 5590.35, "total_tokens": 11761344} {"current_steps": 19290, "total_steps": 64460, "loss": 0.2342, "lr": 8.838736789323963e-06, "epoch": 5.985107043127521, "percentage": 29.93, "elapsed_time": "0:35:04", "remaining_time": "1:22:07", "throughput": 5590.39, "total_tokens": 11764448} {"current_steps": 19295, "total_steps": 64460, "loss": 0.2243, "lr": 8.837869192531237e-06, "epoch": 5.986658392801737, "percentage": 29.93, "elapsed_time": "0:35:04", "remaining_time": "1:22:06", "throughput": 5590.3, "total_tokens": 11766848} {"current_steps": 19300, "total_steps": 64460, "loss": 0.227, "lr": 8.837001314377252e-06, "epoch": 5.988209742475954, "percentage": 29.94, "elapsed_time": "0:35:05", "remaining_time": "1:22:06", "throughput": 5590.03, "total_tokens": 11769280} {"current_steps": 19305, "total_steps": 64460, "loss": 0.2298, "lr": 8.836133154925633e-06, "epoch": 5.989761092150171, "percentage": 29.95, "elapsed_time": "0:35:06", "remaining_time": "1:22:06", "throughput": 5590.05, "total_tokens": 11772704} {"current_steps": 19310, "total_steps": 64460, "loss": 0.2211, "lr": 8.835264714240026e-06, "epoch": 5.9913124418243875, "percentage": 29.96, "elapsed_time": "0:35:06", "remaining_time": "1:22:05", "throughput": 5590.35, "total_tokens": 11776992} {"current_steps": 19315, "total_steps": 64460, "loss": 0.2372, "lr": 8.8343959923841e-06, "epoch": 5.992863791498603, "percentage": 29.96, "elapsed_time": "0:35:07", "remaining_time": "1:22:05", "throughput": 5590.25, "total_tokens": 11779456} {"current_steps": 19320, "total_steps": 64460, "loss": 0.2358, "lr": 8.833526989421541e-06, "epoch": 5.99441514117282, "percentage": 29.97, "elapsed_time": "0:35:07", "remaining_time": "1:22:04", "throughput": 5590.07, "total_tokens": 11781760} {"current_steps": 19325, "total_steps": 64460, "loss": 0.2375, "lr": 8.832657705416059e-06, "epoch": 5.995966490847037, "percentage": 29.98, "elapsed_time": "0:35:08", "remaining_time": "1:22:03", "throughput": 5589.99, "total_tokens": 11784352} {"current_steps": 19330, "total_steps": 64460, "loss": 0.2271, "lr": 8.83178814043138e-06, "epoch": 5.997517840521254, "percentage": 29.99, "elapsed_time": "0:35:08", "remaining_time": "1:22:03", "throughput": 5589.98, "total_tokens": 11787136} {"current_steps": 19335, "total_steps": 64460, "loss": 0.2256, "lr": 8.830918294531258e-06, "epoch": 5.9990691901954705, "percentage": 30.0, "elapsed_time": "0:35:09", "remaining_time": "1:22:02", "throughput": 5590.25, "total_tokens": 11791424} {"current_steps": 19338, "total_steps": 64460, "eval_loss": 0.23222728073596954, "epoch": 6.0, "percentage": 30.0, "elapsed_time": "0:35:44", "remaining_time": "1:23:22", "throughput": 5500.23, "total_tokens": 11793056} {"current_steps": 19340, "total_steps": 64460, "loss": 0.2356, "lr": 8.83004816777946e-06, "epoch": 6.000620539869686, "percentage": 30.0, "elapsed_time": "0:35:48", "remaining_time": "1:23:31", "throughput": 5490.63, "total_tokens": 11794272} {"current_steps": 19345, "total_steps": 64460, "loss": 0.235, "lr": 8.829177760239774e-06, "epoch": 6.002171889543903, "percentage": 30.01, "elapsed_time": "0:35:48", "remaining_time": "1:23:30", "throughput": 5490.6, "total_tokens": 11797536} {"current_steps": 19350, "total_steps": 64460, "loss": 0.2337, "lr": 8.828307071976015e-06, "epoch": 6.00372323921812, "percentage": 30.02, "elapsed_time": "0:35:49", "remaining_time": "1:23:30", "throughput": 5490.56, "total_tokens": 11800384} {"current_steps": 19355, "total_steps": 64460, "loss": 0.2258, "lr": 8.827436103052013e-06, "epoch": 6.005274588892337, "percentage": 30.03, "elapsed_time": "0:35:49", "remaining_time": "1:23:29", "throughput": 5490.62, "total_tokens": 11803520} {"current_steps": 19360, "total_steps": 64460, "loss": 0.2304, "lr": 8.826564853531622e-06, "epoch": 6.006825938566553, "percentage": 30.03, "elapsed_time": "0:35:50", "remaining_time": "1:23:29", "throughput": 5490.48, "total_tokens": 11806048} {"current_steps": 19365, "total_steps": 64460, "loss": 0.233, "lr": 8.825693323478716e-06, "epoch": 6.008377288240769, "percentage": 30.04, "elapsed_time": "0:35:50", "remaining_time": "1:23:28", "throughput": 5490.65, "total_tokens": 11809280} {"current_steps": 19370, "total_steps": 64460, "loss": 0.2305, "lr": 8.824821512957184e-06, "epoch": 6.009928637914986, "percentage": 30.05, "elapsed_time": "0:35:51", "remaining_time": "1:23:27", "throughput": 5490.78, "total_tokens": 11812576} {"current_steps": 19375, "total_steps": 64460, "loss": 0.2337, "lr": 8.823949422030943e-06, "epoch": 6.011479987589203, "percentage": 30.06, "elapsed_time": "0:35:51", "remaining_time": "1:23:27", "throughput": 5490.9, "total_tokens": 11815552} {"current_steps": 19380, "total_steps": 64460, "loss": 0.227, "lr": 8.823077050763927e-06, "epoch": 6.013031337263419, "percentage": 30.07, "elapsed_time": "0:35:52", "remaining_time": "1:23:26", "throughput": 5491.0, "total_tokens": 11818784} {"current_steps": 19385, "total_steps": 64460, "loss": 0.2213, "lr": 8.822204399220092e-06, "epoch": 6.0145826869376355, "percentage": 30.07, "elapsed_time": "0:35:52", "remaining_time": "1:23:25", "throughput": 5490.94, "total_tokens": 11821216} {"current_steps": 19390, "total_steps": 64460, "loss": 0.2306, "lr": 8.82133146746341e-06, "epoch": 6.016134036611852, "percentage": 30.08, "elapsed_time": "0:35:53", "remaining_time": "1:23:25", "throughput": 5490.97, "total_tokens": 11824032} {"current_steps": 19395, "total_steps": 64460, "loss": 0.2396, "lr": 8.820458255557882e-06, "epoch": 6.017685386286069, "percentage": 30.09, "elapsed_time": "0:35:53", "remaining_time": "1:23:24", "throughput": 5490.97, "total_tokens": 11826912} {"current_steps": 19400, "total_steps": 64460, "loss": 0.2195, "lr": 8.819584763567524e-06, "epoch": 6.019236735960286, "percentage": 30.1, "elapsed_time": "0:35:54", "remaining_time": "1:23:23", "throughput": 5491.17, "total_tokens": 11830144} {"current_steps": 19405, "total_steps": 64460, "loss": 0.2272, "lr": 8.81871099155637e-06, "epoch": 6.020788085634502, "percentage": 30.1, "elapsed_time": "0:35:54", "remaining_time": "1:23:23", "throughput": 5491.38, "total_tokens": 11833344} {"current_steps": 19410, "total_steps": 64460, "loss": 0.2088, "lr": 8.81783693958848e-06, "epoch": 6.0223394353087185, "percentage": 30.11, "elapsed_time": "0:35:55", "remaining_time": "1:23:22", "throughput": 5491.19, "total_tokens": 11835808} {"current_steps": 19415, "total_steps": 64460, "loss": 0.2374, "lr": 8.816962607727935e-06, "epoch": 6.023890784982935, "percentage": 30.12, "elapsed_time": "0:35:55", "remaining_time": "1:23:22", "throughput": 5491.26, "total_tokens": 11838944} {"current_steps": 19420, "total_steps": 64460, "loss": 0.238, "lr": 8.816087996038829e-06, "epoch": 6.025442134657152, "percentage": 30.13, "elapsed_time": "0:35:56", "remaining_time": "1:23:21", "throughput": 5491.37, "total_tokens": 11842112} {"current_steps": 19425, "total_steps": 64460, "loss": 0.2295, "lr": 8.815213104585285e-06, "epoch": 6.026993484331368, "percentage": 30.13, "elapsed_time": "0:35:56", "remaining_time": "1:23:20", "throughput": 5491.47, "total_tokens": 11845088} {"current_steps": 19430, "total_steps": 64460, "loss": 0.2318, "lr": 8.81433793343144e-06, "epoch": 6.028544834005585, "percentage": 30.14, "elapsed_time": "0:35:57", "remaining_time": "1:23:20", "throughput": 5491.74, "total_tokens": 11848416} {"current_steps": 19435, "total_steps": 64460, "loss": 0.2283, "lr": 8.813462482641458e-06, "epoch": 6.0300961836798015, "percentage": 30.15, "elapsed_time": "0:35:58", "remaining_time": "1:23:19", "throughput": 5492.03, "total_tokens": 11852512} {"current_steps": 19440, "total_steps": 64460, "loss": 0.2237, "lr": 8.812586752279516e-06, "epoch": 6.031647533354018, "percentage": 30.16, "elapsed_time": "0:35:58", "remaining_time": "1:23:18", "throughput": 5492.1, "total_tokens": 11855296} {"current_steps": 19445, "total_steps": 64460, "loss": 0.2301, "lr": 8.811710742409817e-06, "epoch": 6.033198883028234, "percentage": 30.17, "elapsed_time": "0:35:59", "remaining_time": "1:23:18", "throughput": 5492.03, "total_tokens": 11857632} {"current_steps": 19450, "total_steps": 64460, "loss": 0.2423, "lr": 8.810834453096585e-06, "epoch": 6.034750232702451, "percentage": 30.17, "elapsed_time": "0:35:59", "remaining_time": "1:23:17", "throughput": 5492.08, "total_tokens": 11860352} {"current_steps": 19455, "total_steps": 64460, "loss": 0.23, "lr": 8.80995788440406e-06, "epoch": 6.036301582376668, "percentage": 30.18, "elapsed_time": "0:36:00", "remaining_time": "1:23:16", "throughput": 5492.1, "total_tokens": 11862976} {"current_steps": 19460, "total_steps": 64460, "loss": 0.2238, "lr": 8.809081036396506e-06, "epoch": 6.0378529320508845, "percentage": 30.19, "elapsed_time": "0:36:00", "remaining_time": "1:23:16", "throughput": 5492.4, "total_tokens": 11866752} {"current_steps": 19465, "total_steps": 64460, "loss": 0.2351, "lr": 8.808203909138204e-06, "epoch": 6.039404281725101, "percentage": 30.2, "elapsed_time": "0:36:01", "remaining_time": "1:23:15", "throughput": 5492.46, "total_tokens": 11869504} {"current_steps": 19470, "total_steps": 64460, "loss": 0.2345, "lr": 8.80732650269346e-06, "epoch": 6.040955631399317, "percentage": 30.2, "elapsed_time": "0:36:01", "remaining_time": "1:23:14", "throughput": 5492.47, "total_tokens": 11872224} {"current_steps": 19475, "total_steps": 64460, "loss": 0.225, "lr": 8.806448817126598e-06, "epoch": 6.042506981073534, "percentage": 30.21, "elapsed_time": "0:36:02", "remaining_time": "1:23:14", "throughput": 5492.57, "total_tokens": 11875264} {"current_steps": 19480, "total_steps": 64460, "loss": 0.2309, "lr": 8.805570852501963e-06, "epoch": 6.044058330747751, "percentage": 30.22, "elapsed_time": "0:36:02", "remaining_time": "1:23:13", "throughput": 5492.56, "total_tokens": 11877728} {"current_steps": 19485, "total_steps": 64460, "loss": 0.2333, "lr": 8.80469260888392e-06, "epoch": 6.0456096804219674, "percentage": 30.23, "elapsed_time": "0:36:03", "remaining_time": "1:23:12", "throughput": 5492.82, "total_tokens": 11881248} {"current_steps": 19490, "total_steps": 64460, "loss": 0.23, "lr": 8.803814086336856e-06, "epoch": 6.047161030096183, "percentage": 30.24, "elapsed_time": "0:36:03", "remaining_time": "1:23:11", "throughput": 5492.84, "total_tokens": 11883840} {"current_steps": 19495, "total_steps": 64460, "loss": 0.2312, "lr": 8.802935284925174e-06, "epoch": 6.0487123797704, "percentage": 30.24, "elapsed_time": "0:36:04", "remaining_time": "1:23:11", "throughput": 5493.1, "total_tokens": 11887328} {"current_steps": 19500, "total_steps": 64460, "loss": 0.2317, "lr": 8.8020562047133e-06, "epoch": 6.050263729444617, "percentage": 30.25, "elapsed_time": "0:36:04", "remaining_time": "1:23:10", "throughput": 5493.02, "total_tokens": 11889728} {"current_steps": 19505, "total_steps": 64460, "loss": 0.2321, "lr": 8.801176845765687e-06, "epoch": 6.051815079118834, "percentage": 30.26, "elapsed_time": "0:36:04", "remaining_time": "1:23:09", "throughput": 5493.1, "total_tokens": 11892512} {"current_steps": 19510, "total_steps": 64460, "loss": 0.2197, "lr": 8.800297208146794e-06, "epoch": 6.0533664287930495, "percentage": 30.27, "elapsed_time": "0:36:05", "remaining_time": "1:23:09", "throughput": 5493.27, "total_tokens": 11895680} {"current_steps": 19515, "total_steps": 64460, "loss": 0.2306, "lr": 8.799417291921117e-06, "epoch": 6.054917778467266, "percentage": 30.27, "elapsed_time": "0:36:06", "remaining_time": "1:23:08", "throughput": 5493.27, "total_tokens": 11898464} {"current_steps": 19520, "total_steps": 64460, "loss": 0.2326, "lr": 8.79853709715316e-06, "epoch": 6.056469128141483, "percentage": 30.28, "elapsed_time": "0:36:06", "remaining_time": "1:23:07", "throughput": 5493.4, "total_tokens": 11901376} {"current_steps": 19525, "total_steps": 64460, "loss": 0.2499, "lr": 8.797656623907452e-06, "epoch": 6.0580204778157, "percentage": 30.29, "elapsed_time": "0:36:06", "remaining_time": "1:23:07", "throughput": 5493.58, "total_tokens": 11904512} {"current_steps": 19530, "total_steps": 64460, "loss": 0.2376, "lr": 8.796775872248542e-06, "epoch": 6.059571827489917, "percentage": 30.3, "elapsed_time": "0:36:07", "remaining_time": "1:23:06", "throughput": 5493.81, "total_tokens": 11908288} {"current_steps": 19535, "total_steps": 64460, "loss": 0.2303, "lr": 8.795894842241003e-06, "epoch": 6.0611231771641325, "percentage": 30.31, "elapsed_time": "0:36:08", "remaining_time": "1:23:06", "throughput": 5493.83, "total_tokens": 11911520} {"current_steps": 19540, "total_steps": 64460, "loss": 0.2324, "lr": 8.795013533949418e-06, "epoch": 6.062674526838349, "percentage": 30.31, "elapsed_time": "0:36:08", "remaining_time": "1:23:05", "throughput": 5493.92, "total_tokens": 11914752} {"current_steps": 19545, "total_steps": 64460, "loss": 0.2317, "lr": 8.794131947438402e-06, "epoch": 6.064225876512566, "percentage": 30.32, "elapsed_time": "0:36:09", "remaining_time": "1:23:04", "throughput": 5493.9, "total_tokens": 11917216} {"current_steps": 19550, "total_steps": 64460, "loss": 0.2315, "lr": 8.793250082772586e-06, "epoch": 6.065777226186783, "percentage": 30.33, "elapsed_time": "0:36:09", "remaining_time": "1:23:04", "throughput": 5493.66, "total_tokens": 11919424} {"current_steps": 19555, "total_steps": 64460, "loss": 0.2298, "lr": 8.79236794001662e-06, "epoch": 6.067328575860999, "percentage": 30.34, "elapsed_time": "0:36:10", "remaining_time": "1:23:03", "throughput": 5493.68, "total_tokens": 11922368} {"current_steps": 19560, "total_steps": 64460, "loss": 0.2315, "lr": 8.791485519235175e-06, "epoch": 6.0688799255352155, "percentage": 30.34, "elapsed_time": "0:36:10", "remaining_time": "1:23:02", "throughput": 5493.72, "total_tokens": 11925312} {"current_steps": 19565, "total_steps": 64460, "loss": 0.2287, "lr": 8.790602820492944e-06, "epoch": 6.070431275209432, "percentage": 30.35, "elapsed_time": "0:36:11", "remaining_time": "1:23:02", "throughput": 5493.55, "total_tokens": 11928000} {"current_steps": 19570, "total_steps": 64460, "loss": 0.2418, "lr": 8.78971984385464e-06, "epoch": 6.071982624883649, "percentage": 30.36, "elapsed_time": "0:36:11", "remaining_time": "1:23:01", "throughput": 5493.81, "total_tokens": 11932064} {"current_steps": 19575, "total_steps": 64460, "loss": 0.2383, "lr": 8.788836589384993e-06, "epoch": 6.073533974557865, "percentage": 30.37, "elapsed_time": "0:36:12", "remaining_time": "1:23:01", "throughput": 5493.85, "total_tokens": 11934880} {"current_steps": 19580, "total_steps": 64460, "loss": 0.2244, "lr": 8.787953057148757e-06, "epoch": 6.075085324232082, "percentage": 30.38, "elapsed_time": "0:36:12", "remaining_time": "1:23:00", "throughput": 5494.06, "total_tokens": 11938240} {"current_steps": 19585, "total_steps": 64460, "loss": 0.2233, "lr": 8.787069247210707e-06, "epoch": 6.0766366739062985, "percentage": 30.38, "elapsed_time": "0:36:13", "remaining_time": "1:23:00", "throughput": 5494.09, "total_tokens": 11941248} {"current_steps": 19590, "total_steps": 64460, "loss": 0.2336, "lr": 8.786185159635635e-06, "epoch": 6.078188023580515, "percentage": 30.39, "elapsed_time": "0:36:13", "remaining_time": "1:22:59", "throughput": 5494.02, "total_tokens": 11943904} {"current_steps": 19595, "total_steps": 64460, "loss": 0.2291, "lr": 8.785300794488357e-06, "epoch": 6.079739373254732, "percentage": 30.4, "elapsed_time": "0:36:14", "remaining_time": "1:22:58", "throughput": 5494.02, "total_tokens": 11946560} {"current_steps": 19600, "total_steps": 64460, "loss": 0.2285, "lr": 8.784416151833704e-06, "epoch": 6.081290722928948, "percentage": 30.41, "elapsed_time": "0:36:14", "remaining_time": "1:22:58", "throughput": 5494.2, "total_tokens": 11949760} {"current_steps": 19605, "total_steps": 64460, "loss": 0.227, "lr": 8.783531231736533e-06, "epoch": 6.082842072603165, "percentage": 30.41, "elapsed_time": "0:36:15", "remaining_time": "1:22:57", "throughput": 5494.24, "total_tokens": 11952544} {"current_steps": 19610, "total_steps": 64460, "loss": 0.229, "lr": 8.78264603426172e-06, "epoch": 6.0843934222773814, "percentage": 30.42, "elapsed_time": "0:36:16", "remaining_time": "1:22:56", "throughput": 5494.36, "total_tokens": 11955776} {"current_steps": 19615, "total_steps": 64460, "loss": 0.2384, "lr": 8.781760559474159e-06, "epoch": 6.085944771951598, "percentage": 30.43, "elapsed_time": "0:36:16", "remaining_time": "1:22:56", "throughput": 5494.36, "total_tokens": 11958528} {"current_steps": 19620, "total_steps": 64460, "loss": 0.2257, "lr": 8.780874807438768e-06, "epoch": 6.087496121625814, "percentage": 30.44, "elapsed_time": "0:36:17", "remaining_time": "1:22:55", "throughput": 5494.55, "total_tokens": 11962112} {"current_steps": 19625, "total_steps": 64460, "loss": 0.2263, "lr": 8.779988778220478e-06, "epoch": 6.089047471300031, "percentage": 30.45, "elapsed_time": "0:36:17", "remaining_time": "1:22:55", "throughput": 5494.59, "total_tokens": 11965376} {"current_steps": 19630, "total_steps": 64460, "loss": 0.2421, "lr": 8.779102471884253e-06, "epoch": 6.090598820974248, "percentage": 30.45, "elapsed_time": "0:36:18", "remaining_time": "1:22:54", "throughput": 5494.67, "total_tokens": 11968224} {"current_steps": 19635, "total_steps": 64460, "loss": 0.2294, "lr": 8.778215888495064e-06, "epoch": 6.092150170648464, "percentage": 30.46, "elapsed_time": "0:36:18", "remaining_time": "1:22:53", "throughput": 5494.75, "total_tokens": 11970976} {"current_steps": 19640, "total_steps": 64460, "loss": 0.2316, "lr": 8.777329028117907e-06, "epoch": 6.09370152032268, "percentage": 30.47, "elapsed_time": "0:36:19", "remaining_time": "1:22:52", "throughput": 5495.05, "total_tokens": 11974464} {"current_steps": 19645, "total_steps": 64460, "loss": 0.2332, "lr": 8.776441890817803e-06, "epoch": 6.095252869996897, "percentage": 30.48, "elapsed_time": "0:36:19", "remaining_time": "1:22:52", "throughput": 5495.1, "total_tokens": 11977248} {"current_steps": 19650, "total_steps": 64460, "loss": 0.2314, "lr": 8.77555447665979e-06, "epoch": 6.096804219671114, "percentage": 30.48, "elapsed_time": "0:36:20", "remaining_time": "1:22:51", "throughput": 5495.16, "total_tokens": 11979936} {"current_steps": 19655, "total_steps": 64460, "loss": 0.23, "lr": 8.774666785708924e-06, "epoch": 6.098355569345331, "percentage": 30.49, "elapsed_time": "0:36:20", "remaining_time": "1:22:50", "throughput": 5495.25, "total_tokens": 11982880} {"current_steps": 19660, "total_steps": 64460, "loss": 0.23, "lr": 8.773778818030284e-06, "epoch": 6.099906919019547, "percentage": 30.5, "elapsed_time": "0:36:21", "remaining_time": "1:22:50", "throughput": 5495.45, "total_tokens": 11986560} {"current_steps": 19665, "total_steps": 64460, "loss": 0.2271, "lr": 8.772890573688967e-06, "epoch": 6.101458268693763, "percentage": 30.51, "elapsed_time": "0:36:21", "remaining_time": "1:22:49", "throughput": 5495.53, "total_tokens": 11989568} {"current_steps": 19670, "total_steps": 64460, "loss": 0.2331, "lr": 8.772002052750095e-06, "epoch": 6.10300961836798, "percentage": 30.52, "elapsed_time": "0:36:22", "remaining_time": "1:22:48", "throughput": 5495.6, "total_tokens": 11992320} {"current_steps": 19675, "total_steps": 64460, "loss": 0.2266, "lr": 8.771113255278805e-06, "epoch": 6.104560968042197, "percentage": 30.52, "elapsed_time": "0:36:22", "remaining_time": "1:22:48", "throughput": 5495.68, "total_tokens": 11995456} {"current_steps": 19680, "total_steps": 64460, "loss": 0.2344, "lr": 8.770224181340257e-06, "epoch": 6.106112317716414, "percentage": 30.53, "elapsed_time": "0:36:23", "remaining_time": "1:22:47", "throughput": 5495.73, "total_tokens": 11998592} {"current_steps": 19685, "total_steps": 64460, "loss": 0.2364, "lr": 8.76933483099963e-06, "epoch": 6.1076636673906295, "percentage": 30.54, "elapsed_time": "0:36:23", "remaining_time": "1:22:47", "throughput": 5495.82, "total_tokens": 12001856} {"current_steps": 19690, "total_steps": 64460, "loss": 0.2258, "lr": 8.768445204322125e-06, "epoch": 6.109215017064846, "percentage": 30.55, "elapsed_time": "0:36:24", "remaining_time": "1:22:46", "throughput": 5495.81, "total_tokens": 12004384} {"current_steps": 19695, "total_steps": 64460, "loss": 0.2344, "lr": 8.767555301372961e-06, "epoch": 6.110766366739063, "percentage": 30.55, "elapsed_time": "0:36:24", "remaining_time": "1:22:45", "throughput": 5495.96, "total_tokens": 12007552} {"current_steps": 19700, "total_steps": 64460, "loss": 0.2298, "lr": 8.766665122217379e-06, "epoch": 6.11231771641328, "percentage": 30.56, "elapsed_time": "0:36:25", "remaining_time": "1:22:45", "throughput": 5496.17, "total_tokens": 12011200} {"current_steps": 19705, "total_steps": 64460, "loss": 0.2308, "lr": 8.76577466692064e-06, "epoch": 6.113869066087496, "percentage": 30.57, "elapsed_time": "0:36:25", "remaining_time": "1:22:44", "throughput": 5495.91, "total_tokens": 12013248} {"current_steps": 19710, "total_steps": 64460, "loss": 0.233, "lr": 8.764883935548022e-06, "epoch": 6.1154204157617125, "percentage": 30.58, "elapsed_time": "0:36:26", "remaining_time": "1:22:43", "throughput": 5495.88, "total_tokens": 12015808} {"current_steps": 19715, "total_steps": 64460, "loss": 0.2363, "lr": 8.76399292816483e-06, "epoch": 6.116971765435929, "percentage": 30.58, "elapsed_time": "0:36:26", "remaining_time": "1:22:43", "throughput": 5495.98, "total_tokens": 12019136} {"current_steps": 19720, "total_steps": 64460, "loss": 0.2312, "lr": 8.763101644836385e-06, "epoch": 6.118523115110146, "percentage": 30.59, "elapsed_time": "0:36:27", "remaining_time": "1:22:42", "throughput": 5495.95, "total_tokens": 12021632} {"current_steps": 19725, "total_steps": 64460, "loss": 0.236, "lr": 8.762210085628027e-06, "epoch": 6.120074464784363, "percentage": 30.6, "elapsed_time": "0:36:27", "remaining_time": "1:22:42", "throughput": 5496.12, "total_tokens": 12025440} {"current_steps": 19730, "total_steps": 64460, "loss": 0.2268, "lr": 8.761318250605117e-06, "epoch": 6.121625814458579, "percentage": 30.61, "elapsed_time": "0:36:28", "remaining_time": "1:22:41", "throughput": 5496.13, "total_tokens": 12028000} {"current_steps": 19735, "total_steps": 64460, "loss": 0.2286, "lr": 8.76042613983304e-06, "epoch": 6.1231771641327954, "percentage": 30.62, "elapsed_time": "0:36:28", "remaining_time": "1:22:40", "throughput": 5496.19, "total_tokens": 12030688} {"current_steps": 19740, "total_steps": 64460, "loss": 0.2277, "lr": 8.759533753377199e-06, "epoch": 6.124728513807012, "percentage": 30.62, "elapsed_time": "0:36:29", "remaining_time": "1:22:40", "throughput": 5496.48, "total_tokens": 12034880} {"current_steps": 19745, "total_steps": 64460, "loss": 0.2393, "lr": 8.758641091303011e-06, "epoch": 6.126279863481229, "percentage": 30.63, "elapsed_time": "0:36:30", "remaining_time": "1:22:39", "throughput": 5496.81, "total_tokens": 12038848} {"current_steps": 19750, "total_steps": 64460, "loss": 0.2281, "lr": 8.757748153675923e-06, "epoch": 6.127831213155445, "percentage": 30.64, "elapsed_time": "0:36:30", "remaining_time": "1:22:39", "throughput": 5496.63, "total_tokens": 12041024} {"current_steps": 19755, "total_steps": 64460, "loss": 0.2333, "lr": 8.756854940561397e-06, "epoch": 6.129382562829662, "percentage": 30.65, "elapsed_time": "0:36:31", "remaining_time": "1:22:38", "throughput": 5496.73, "total_tokens": 12044000} {"current_steps": 19760, "total_steps": 64460, "loss": 0.2315, "lr": 8.755961452024916e-06, "epoch": 6.130933912503878, "percentage": 30.65, "elapsed_time": "0:36:31", "remaining_time": "1:22:37", "throughput": 5496.9, "total_tokens": 12047168} {"current_steps": 19765, "total_steps": 64460, "loss": 0.2343, "lr": 8.755067688131984e-06, "epoch": 6.132485262178095, "percentage": 30.66, "elapsed_time": "0:36:32", "remaining_time": "1:22:37", "throughput": 5496.72, "total_tokens": 12049600} {"current_steps": 19770, "total_steps": 64460, "loss": 0.2308, "lr": 8.754173648948124e-06, "epoch": 6.134036611852311, "percentage": 30.67, "elapsed_time": "0:36:32", "remaining_time": "1:22:36", "throughput": 5496.82, "total_tokens": 12052736} {"current_steps": 19775, "total_steps": 64460, "loss": 0.2316, "lr": 8.753279334538878e-06, "epoch": 6.135587961526528, "percentage": 30.68, "elapsed_time": "0:36:33", "remaining_time": "1:22:35", "throughput": 5496.86, "total_tokens": 12055424} {"current_steps": 19780, "total_steps": 64460, "loss": 0.2309, "lr": 8.752384744969813e-06, "epoch": 6.137139311200745, "percentage": 30.69, "elapsed_time": "0:36:33", "remaining_time": "1:22:35", "throughput": 5497.0, "total_tokens": 12058624} {"current_steps": 19785, "total_steps": 64460, "loss": 0.2267, "lr": 8.75148988030651e-06, "epoch": 6.138690660874961, "percentage": 30.69, "elapsed_time": "0:36:34", "remaining_time": "1:22:34", "throughput": 5497.21, "total_tokens": 12061824} {"current_steps": 19790, "total_steps": 64460, "loss": 0.2266, "lr": 8.750594740614575e-06, "epoch": 6.140242010549178, "percentage": 30.7, "elapsed_time": "0:36:34", "remaining_time": "1:22:33", "throughput": 5497.23, "total_tokens": 12064576} {"current_steps": 19795, "total_steps": 64460, "loss": 0.2329, "lr": 8.749699325959631e-06, "epoch": 6.141793360223394, "percentage": 30.71, "elapsed_time": "0:36:35", "remaining_time": "1:22:33", "throughput": 5497.19, "total_tokens": 12067168} {"current_steps": 19800, "total_steps": 64460, "loss": 0.2324, "lr": 8.748803636407324e-06, "epoch": 6.143344709897611, "percentage": 30.72, "elapsed_time": "0:36:35", "remaining_time": "1:22:32", "throughput": 5497.21, "total_tokens": 12069792} {"current_steps": 19805, "total_steps": 64460, "loss": 0.23, "lr": 8.747907672023318e-06, "epoch": 6.144896059571828, "percentage": 30.72, "elapsed_time": "0:36:36", "remaining_time": "1:22:31", "throughput": 5497.17, "total_tokens": 12072448} {"current_steps": 19810, "total_steps": 64460, "loss": 0.2296, "lr": 8.747011432873299e-06, "epoch": 6.146447409246044, "percentage": 30.73, "elapsed_time": "0:36:36", "remaining_time": "1:22:31", "throughput": 5497.16, "total_tokens": 12075296} {"current_steps": 19815, "total_steps": 64460, "loss": 0.2347, "lr": 8.746114919022968e-06, "epoch": 6.14799875892026, "percentage": 30.74, "elapsed_time": "0:36:37", "remaining_time": "1:22:30", "throughput": 5497.19, "total_tokens": 12078208} {"current_steps": 19820, "total_steps": 64460, "loss": 0.2367, "lr": 8.745218130538055e-06, "epoch": 6.149550108594477, "percentage": 30.75, "elapsed_time": "0:36:37", "remaining_time": "1:22:29", "throughput": 5497.26, "total_tokens": 12081344} {"current_steps": 19825, "total_steps": 64460, "loss": 0.2296, "lr": 8.744321067484302e-06, "epoch": 6.151101458268694, "percentage": 30.76, "elapsed_time": "0:36:38", "remaining_time": "1:22:29", "throughput": 5497.41, "total_tokens": 12084608} {"current_steps": 19830, "total_steps": 64460, "loss": 0.232, "lr": 8.743423729927476e-06, "epoch": 6.152652807942911, "percentage": 30.76, "elapsed_time": "0:36:38", "remaining_time": "1:22:28", "throughput": 5497.65, "total_tokens": 12088160} {"current_steps": 19835, "total_steps": 64460, "loss": 0.231, "lr": 8.74252611793336e-06, "epoch": 6.1542041576171265, "percentage": 30.77, "elapsed_time": "0:36:39", "remaining_time": "1:22:27", "throughput": 5497.92, "total_tokens": 12091520} {"current_steps": 19840, "total_steps": 64460, "loss": 0.2316, "lr": 8.741628231567765e-06, "epoch": 6.155755507291343, "percentage": 30.78, "elapsed_time": "0:36:39", "remaining_time": "1:22:27", "throughput": 5497.97, "total_tokens": 12094208} {"current_steps": 19845, "total_steps": 64460, "loss": 0.2289, "lr": 8.74073007089651e-06, "epoch": 6.15730685696556, "percentage": 30.79, "elapsed_time": "0:36:40", "remaining_time": "1:22:26", "throughput": 5497.89, "total_tokens": 12096704} {"current_steps": 19850, "total_steps": 64460, "loss": 0.2262, "lr": 8.739831635985444e-06, "epoch": 6.158858206639777, "percentage": 30.79, "elapsed_time": "0:36:40", "remaining_time": "1:22:25", "throughput": 5497.9, "total_tokens": 12099456} {"current_steps": 19855, "total_steps": 64460, "loss": 0.2325, "lr": 8.738932926900434e-06, "epoch": 6.160409556313994, "percentage": 30.8, "elapsed_time": "0:36:41", "remaining_time": "1:22:25", "throughput": 5498.0, "total_tokens": 12103008} {"current_steps": 19860, "total_steps": 64460, "loss": 0.2285, "lr": 8.738033943707364e-06, "epoch": 6.1619609059882094, "percentage": 30.81, "elapsed_time": "0:36:41", "remaining_time": "1:22:24", "throughput": 5498.12, "total_tokens": 12106528} {"current_steps": 19865, "total_steps": 64460, "loss": 0.2299, "lr": 8.737134686472144e-06, "epoch": 6.163512255662426, "percentage": 30.82, "elapsed_time": "0:36:42", "remaining_time": "1:22:24", "throughput": 5497.97, "total_tokens": 12108960} {"current_steps": 19870, "total_steps": 64460, "loss": 0.2435, "lr": 8.736235155260696e-06, "epoch": 6.165063605336643, "percentage": 30.83, "elapsed_time": "0:36:42", "remaining_time": "1:22:23", "throughput": 5497.96, "total_tokens": 12111936} {"current_steps": 19875, "total_steps": 64460, "loss": 0.2326, "lr": 8.735335350138965e-06, "epoch": 6.16661495501086, "percentage": 30.83, "elapsed_time": "0:36:43", "remaining_time": "1:22:23", "throughput": 5497.77, "total_tokens": 12114464} {"current_steps": 19880, "total_steps": 64460, "loss": 0.2386, "lr": 8.73443527117292e-06, "epoch": 6.168166304685076, "percentage": 30.84, "elapsed_time": "0:36:44", "remaining_time": "1:22:22", "throughput": 5497.86, "total_tokens": 12117536} {"current_steps": 19885, "total_steps": 64460, "loss": 0.2283, "lr": 8.73353491842855e-06, "epoch": 6.169717654359292, "percentage": 30.85, "elapsed_time": "0:36:45", "remaining_time": "1:22:22", "throughput": 5498.43, "total_tokens": 12124416} {"current_steps": 19890, "total_steps": 64460, "loss": 0.2273, "lr": 8.732634291971857e-06, "epoch": 6.171269004033509, "percentage": 30.86, "elapsed_time": "0:36:45", "remaining_time": "1:22:22", "throughput": 5498.61, "total_tokens": 12128256} {"current_steps": 19895, "total_steps": 64460, "loss": 0.2263, "lr": 8.731733391868868e-06, "epoch": 6.172820353707726, "percentage": 30.86, "elapsed_time": "0:36:46", "remaining_time": "1:22:22", "throughput": 5498.87, "total_tokens": 12132320} {"current_steps": 19900, "total_steps": 64460, "loss": 0.2273, "lr": 8.730832218185635e-06, "epoch": 6.174371703381942, "percentage": 30.87, "elapsed_time": "0:36:46", "remaining_time": "1:22:21", "throughput": 5499.05, "total_tokens": 12135680} {"current_steps": 19905, "total_steps": 64460, "loss": 0.2357, "lr": 8.729930770988218e-06, "epoch": 6.175923053056159, "percentage": 30.88, "elapsed_time": "0:36:47", "remaining_time": "1:22:20", "throughput": 5499.08, "total_tokens": 12138400} {"current_steps": 19910, "total_steps": 64460, "loss": 0.2337, "lr": 8.729029050342705e-06, "epoch": 6.177474402730375, "percentage": 30.89, "elapsed_time": "0:36:47", "remaining_time": "1:22:20", "throughput": 5499.22, "total_tokens": 12142016} {"current_steps": 19915, "total_steps": 64460, "loss": 0.234, "lr": 8.728127056315208e-06, "epoch": 6.179025752404592, "percentage": 30.9, "elapsed_time": "0:36:48", "remaining_time": "1:22:19", "throughput": 5499.32, "total_tokens": 12145184} {"current_steps": 19920, "total_steps": 64460, "loss": 0.23, "lr": 8.727224788971848e-06, "epoch": 6.180577102078809, "percentage": 30.9, "elapsed_time": "0:36:49", "remaining_time": "1:22:19", "throughput": 5499.16, "total_tokens": 12147968} {"current_steps": 19925, "total_steps": 64460, "loss": 0.2309, "lr": 8.726322248378775e-06, "epoch": 6.182128451753025, "percentage": 30.91, "elapsed_time": "0:36:49", "remaining_time": "1:22:19", "throughput": 5499.45, "total_tokens": 12152320} {"current_steps": 19930, "total_steps": 64460, "loss": 0.228, "lr": 8.725419434602154e-06, "epoch": 6.183679801427242, "percentage": 30.92, "elapsed_time": "0:36:50", "remaining_time": "1:22:18", "throughput": 5499.37, "total_tokens": 12155040} {"current_steps": 19935, "total_steps": 64460, "loss": 0.2259, "lr": 8.724516347708173e-06, "epoch": 6.185231151101458, "percentage": 30.93, "elapsed_time": "0:36:50", "remaining_time": "1:22:18", "throughput": 5499.38, "total_tokens": 12158592} {"current_steps": 19940, "total_steps": 64460, "loss": 0.2336, "lr": 8.72361298776304e-06, "epoch": 6.186782500775675, "percentage": 30.93, "elapsed_time": "0:36:51", "remaining_time": "1:22:17", "throughput": 5499.34, "total_tokens": 12161024} {"current_steps": 19945, "total_steps": 64460, "loss": 0.2334, "lr": 8.72270935483298e-06, "epoch": 6.188333850449891, "percentage": 30.94, "elapsed_time": "0:36:51", "remaining_time": "1:22:16", "throughput": 5499.55, "total_tokens": 12164576} {"current_steps": 19950, "total_steps": 64460, "loss": 0.2276, "lr": 8.721805448984239e-06, "epoch": 6.189885200124108, "percentage": 30.95, "elapsed_time": "0:36:52", "remaining_time": "1:22:16", "throughput": 5499.51, "total_tokens": 12167072} {"current_steps": 19955, "total_steps": 64460, "loss": 0.2415, "lr": 8.720901270283088e-06, "epoch": 6.191436549798325, "percentage": 30.96, "elapsed_time": "0:36:52", "remaining_time": "1:22:15", "throughput": 5499.63, "total_tokens": 12170368} {"current_steps": 19960, "total_steps": 64460, "loss": 0.2305, "lr": 8.719996818795812e-06, "epoch": 6.192987899472541, "percentage": 30.96, "elapsed_time": "0:36:53", "remaining_time": "1:22:14", "throughput": 5499.35, "total_tokens": 12172544} {"current_steps": 19965, "total_steps": 64460, "loss": 0.2311, "lr": 8.719092094588717e-06, "epoch": 6.194539249146757, "percentage": 30.97, "elapsed_time": "0:36:53", "remaining_time": "1:22:14", "throughput": 5499.3, "total_tokens": 12175136} {"current_steps": 19970, "total_steps": 64460, "loss": 0.231, "lr": 8.71818709772813e-06, "epoch": 6.196090598820974, "percentage": 30.98, "elapsed_time": "0:36:54", "remaining_time": "1:22:13", "throughput": 5499.49, "total_tokens": 12178464} {"current_steps": 19975, "total_steps": 64460, "loss": 0.2268, "lr": 8.7172818282804e-06, "epoch": 6.197641948495191, "percentage": 30.99, "elapsed_time": "0:36:54", "remaining_time": "1:22:12", "throughput": 5499.34, "total_tokens": 12180768} {"current_steps": 19980, "total_steps": 64460, "loss": 0.233, "lr": 8.716376286311894e-06, "epoch": 6.199193298169408, "percentage": 31.0, "elapsed_time": "0:36:55", "remaining_time": "1:22:12", "throughput": 5499.41, "total_tokens": 12183648} {"current_steps": 19985, "total_steps": 64460, "loss": 0.2293, "lr": 8.715470471888997e-06, "epoch": 6.200744647843624, "percentage": 31.0, "elapsed_time": "0:36:55", "remaining_time": "1:22:11", "throughput": 5499.63, "total_tokens": 12187072} {"current_steps": 19990, "total_steps": 64460, "loss": 0.2321, "lr": 8.714564385078114e-06, "epoch": 6.20229599751784, "percentage": 31.01, "elapsed_time": "0:36:56", "remaining_time": "1:22:10", "throughput": 5499.64, "total_tokens": 12189664} {"current_steps": 19995, "total_steps": 64460, "loss": 0.2326, "lr": 8.713658025945677e-06, "epoch": 6.203847347192057, "percentage": 31.02, "elapsed_time": "0:36:56", "remaining_time": "1:22:10", "throughput": 5499.64, "total_tokens": 12192288} {"current_steps": 20000, "total_steps": 64460, "loss": 0.229, "lr": 8.71275139455813e-06, "epoch": 6.205398696866274, "percentage": 31.03, "elapsed_time": "0:36:57", "remaining_time": "1:22:09", "throughput": 5499.65, "total_tokens": 12195200} {"current_steps": 20005, "total_steps": 64460, "loss": 0.2301, "lr": 8.71184449098194e-06, "epoch": 6.2069500465404905, "percentage": 31.03, "elapsed_time": "0:36:57", "remaining_time": "1:22:08", "throughput": 5499.92, "total_tokens": 12198720} {"current_steps": 20010, "total_steps": 64460, "loss": 0.2279, "lr": 8.710937315283594e-06, "epoch": 6.208501396214706, "percentage": 31.04, "elapsed_time": "0:36:58", "remaining_time": "1:22:08", "throughput": 5499.88, "total_tokens": 12201280} {"current_steps": 20015, "total_steps": 64460, "loss": 0.2306, "lr": 8.710029867529599e-06, "epoch": 6.210052745888923, "percentage": 31.05, "elapsed_time": "0:36:58", "remaining_time": "1:22:07", "throughput": 5499.87, "total_tokens": 12203936} {"current_steps": 20020, "total_steps": 64460, "loss": 0.2388, "lr": 8.709122147786481e-06, "epoch": 6.21160409556314, "percentage": 31.06, "elapsed_time": "0:36:59", "remaining_time": "1:22:06", "throughput": 5499.77, "total_tokens": 12206496} {"current_steps": 20025, "total_steps": 64460, "loss": 0.2304, "lr": 8.708214156120789e-06, "epoch": 6.213155445237357, "percentage": 31.07, "elapsed_time": "0:36:59", "remaining_time": "1:22:06", "throughput": 5500.02, "total_tokens": 12209984} {"current_steps": 20030, "total_steps": 64460, "loss": 0.2275, "lr": 8.707305892599085e-06, "epoch": 6.214706794911573, "percentage": 31.07, "elapsed_time": "0:37:00", "remaining_time": "1:22:05", "throughput": 5500.18, "total_tokens": 12213280} {"current_steps": 20035, "total_steps": 64460, "loss": 0.2306, "lr": 8.706397357287959e-06, "epoch": 6.216258144585789, "percentage": 31.08, "elapsed_time": "0:37:01", "remaining_time": "1:22:05", "throughput": 5500.36, "total_tokens": 12217152} {"current_steps": 20040, "total_steps": 64460, "loss": 0.2261, "lr": 8.705488550254016e-06, "epoch": 6.217809494260006, "percentage": 31.09, "elapsed_time": "0:37:01", "remaining_time": "1:22:04", "throughput": 5500.52, "total_tokens": 12220224} {"current_steps": 20045, "total_steps": 64460, "loss": 0.2314, "lr": 8.704579471563883e-06, "epoch": 6.219360843934223, "percentage": 31.1, "elapsed_time": "0:37:02", "remaining_time": "1:22:03", "throughput": 5500.86, "total_tokens": 12224320} {"current_steps": 20050, "total_steps": 64460, "loss": 0.2297, "lr": 8.703670121284206e-06, "epoch": 6.22091219360844, "percentage": 31.1, "elapsed_time": "0:37:02", "remaining_time": "1:22:03", "throughput": 5500.93, "total_tokens": 12227136} {"current_steps": 20055, "total_steps": 64460, "loss": 0.2378, "lr": 8.70276049948165e-06, "epoch": 6.222463543282656, "percentage": 31.11, "elapsed_time": "0:37:03", "remaining_time": "1:22:02", "throughput": 5500.97, "total_tokens": 12229888} {"current_steps": 20060, "total_steps": 64460, "loss": 0.2326, "lr": 8.701850606222904e-06, "epoch": 6.224014892956872, "percentage": 31.12, "elapsed_time": "0:37:03", "remaining_time": "1:22:01", "throughput": 5501.0, "total_tokens": 12232544} {"current_steps": 20065, "total_steps": 64460, "loss": 0.2327, "lr": 8.70094044157467e-06, "epoch": 6.225566242631089, "percentage": 31.13, "elapsed_time": "0:37:04", "remaining_time": "1:22:01", "throughput": 5500.97, "total_tokens": 12234976} {"current_steps": 20070, "total_steps": 64460, "loss": 0.2292, "lr": 8.700030005603679e-06, "epoch": 6.227117592305306, "percentage": 31.14, "elapsed_time": "0:37:04", "remaining_time": "1:22:00", "throughput": 5500.98, "total_tokens": 12237664} {"current_steps": 20075, "total_steps": 64460, "loss": 0.2413, "lr": 8.699119298376671e-06, "epoch": 6.228668941979522, "percentage": 31.14, "elapsed_time": "0:37:05", "remaining_time": "1:21:59", "throughput": 5501.01, "total_tokens": 12240736} {"current_steps": 20080, "total_steps": 64460, "loss": 0.228, "lr": 8.698208319960415e-06, "epoch": 6.230220291653739, "percentage": 31.15, "elapsed_time": "0:37:05", "remaining_time": "1:21:59", "throughput": 5500.86, "total_tokens": 12243776} {"current_steps": 20085, "total_steps": 64460, "loss": 0.231, "lr": 8.697297070421697e-06, "epoch": 6.231771641327955, "percentage": 31.16, "elapsed_time": "0:37:06", "remaining_time": "1:21:58", "throughput": 5500.92, "total_tokens": 12246560} {"current_steps": 20090, "total_steps": 64460, "loss": 0.2327, "lr": 8.69638554982732e-06, "epoch": 6.233322991002172, "percentage": 31.17, "elapsed_time": "0:37:06", "remaining_time": "1:21:58", "throughput": 5500.84, "total_tokens": 12249472} {"current_steps": 20095, "total_steps": 64460, "loss": 0.2339, "lr": 8.695473758244109e-06, "epoch": 6.234874340676388, "percentage": 31.17, "elapsed_time": "0:37:07", "remaining_time": "1:21:57", "throughput": 5501.05, "total_tokens": 12253408} {"current_steps": 20100, "total_steps": 64460, "loss": 0.2321, "lr": 8.694561695738912e-06, "epoch": 6.236425690350605, "percentage": 31.18, "elapsed_time": "0:37:07", "remaining_time": "1:21:56", "throughput": 5501.02, "total_tokens": 12255968} {"current_steps": 20105, "total_steps": 64460, "loss": 0.2336, "lr": 8.693649362378593e-06, "epoch": 6.237977040024822, "percentage": 31.19, "elapsed_time": "0:37:08", "remaining_time": "1:21:56", "throughput": 5500.8, "total_tokens": 12258496} {"current_steps": 20110, "total_steps": 64460, "loss": 0.2287, "lr": 8.692736758230038e-06, "epoch": 6.239528389699038, "percentage": 31.2, "elapsed_time": "0:37:09", "remaining_time": "1:21:56", "throughput": 5501.08, "total_tokens": 12262528} {"current_steps": 20115, "total_steps": 64460, "loss": 0.2273, "lr": 8.691823883360147e-06, "epoch": 6.241079739373255, "percentage": 31.21, "elapsed_time": "0:37:09", "remaining_time": "1:21:55", "throughput": 5501.23, "total_tokens": 12265408} {"current_steps": 20120, "total_steps": 64460, "loss": 0.2321, "lr": 8.690910737835849e-06, "epoch": 6.242631089047471, "percentage": 31.21, "elapsed_time": "0:37:10", "remaining_time": "1:21:54", "throughput": 5501.27, "total_tokens": 12268288} {"current_steps": 20125, "total_steps": 64460, "loss": 0.2306, "lr": 8.689997321724086e-06, "epoch": 6.244182438721688, "percentage": 31.22, "elapsed_time": "0:37:10", "remaining_time": "1:21:54", "throughput": 5501.48, "total_tokens": 12272352} {"current_steps": 20130, "total_steps": 64460, "loss": 0.2268, "lr": 8.689083635091824e-06, "epoch": 6.2457337883959045, "percentage": 31.23, "elapsed_time": "0:37:11", "remaining_time": "1:21:53", "throughput": 5501.4, "total_tokens": 12274976} {"current_steps": 20135, "total_steps": 64460, "loss": 0.233, "lr": 8.688169678006047e-06, "epoch": 6.247285138070121, "percentage": 31.24, "elapsed_time": "0:37:11", "remaining_time": "1:21:52", "throughput": 5501.27, "total_tokens": 12277472} {"current_steps": 20140, "total_steps": 64460, "loss": 0.2289, "lr": 8.687255450533758e-06, "epoch": 6.248836487744337, "percentage": 31.24, "elapsed_time": "0:37:12", "remaining_time": "1:21:52", "throughput": 5501.4, "total_tokens": 12280768} {"current_steps": 20145, "total_steps": 64460, "loss": 0.2277, "lr": 8.686340952741978e-06, "epoch": 6.250387837418554, "percentage": 31.25, "elapsed_time": "0:37:12", "remaining_time": "1:21:51", "throughput": 5501.39, "total_tokens": 12283584} {"current_steps": 20150, "total_steps": 64460, "loss": 0.231, "lr": 8.685426184697756e-06, "epoch": 6.251939187092771, "percentage": 31.26, "elapsed_time": "0:37:13", "remaining_time": "1:21:51", "throughput": 5501.57, "total_tokens": 12286976} {"current_steps": 20155, "total_steps": 64460, "loss": 0.2268, "lr": 8.684511146468153e-06, "epoch": 6.2534905367669875, "percentage": 31.27, "elapsed_time": "0:37:13", "remaining_time": "1:21:50", "throughput": 5501.84, "total_tokens": 12290528} {"current_steps": 20160, "total_steps": 64460, "loss": 0.224, "lr": 8.68359583812025e-06, "epoch": 6.255041886441203, "percentage": 31.28, "elapsed_time": "0:37:14", "remaining_time": "1:21:49", "throughput": 5501.94, "total_tokens": 12293632} {"current_steps": 20165, "total_steps": 64460, "loss": 0.2364, "lr": 8.682680259721155e-06, "epoch": 6.25659323611542, "percentage": 31.28, "elapsed_time": "0:37:14", "remaining_time": "1:21:49", "throughput": 5501.68, "total_tokens": 12295744} {"current_steps": 20170, "total_steps": 64460, "loss": 0.2369, "lr": 8.681764411337983e-06, "epoch": 6.258144585789637, "percentage": 31.29, "elapsed_time": "0:37:15", "remaining_time": "1:21:48", "throughput": 5501.91, "total_tokens": 12299648} {"current_steps": 20175, "total_steps": 64460, "loss": 0.2292, "lr": 8.680848293037885e-06, "epoch": 6.259695935463854, "percentage": 31.3, "elapsed_time": "0:37:16", "remaining_time": "1:21:48", "throughput": 5501.87, "total_tokens": 12302368} {"current_steps": 20180, "total_steps": 64460, "loss": 0.233, "lr": 8.679931904888018e-06, "epoch": 6.2612472851380705, "percentage": 31.31, "elapsed_time": "0:37:16", "remaining_time": "1:21:47", "throughput": 5501.99, "total_tokens": 12305440} {"current_steps": 20185, "total_steps": 64460, "loss": 0.2354, "lr": 8.679015246955565e-06, "epoch": 6.262798634812286, "percentage": 31.31, "elapsed_time": "0:37:17", "remaining_time": "1:21:46", "throughput": 5501.93, "total_tokens": 12307968} {"current_steps": 20190, "total_steps": 64460, "loss": 0.2414, "lr": 8.678098319307728e-06, "epoch": 6.264349984486503, "percentage": 31.32, "elapsed_time": "0:37:17", "remaining_time": "1:21:46", "throughput": 5502.16, "total_tokens": 12311776} {"current_steps": 20195, "total_steps": 64460, "loss": 0.2362, "lr": 8.67718112201173e-06, "epoch": 6.26590133416072, "percentage": 31.33, "elapsed_time": "0:37:18", "remaining_time": "1:21:45", "throughput": 5502.11, "total_tokens": 12314336} {"current_steps": 20200, "total_steps": 64460, "loss": 0.2279, "lr": 8.676263655134811e-06, "epoch": 6.267452683834937, "percentage": 31.34, "elapsed_time": "0:37:18", "remaining_time": "1:21:45", "throughput": 5501.93, "total_tokens": 12316704} {"current_steps": 20205, "total_steps": 64460, "loss": 0.2309, "lr": 8.675345918744232e-06, "epoch": 6.269004033509153, "percentage": 31.35, "elapsed_time": "0:37:19", "remaining_time": "1:21:44", "throughput": 5502.11, "total_tokens": 12320320} {"current_steps": 20210, "total_steps": 64460, "loss": 0.2338, "lr": 8.674427912907276e-06, "epoch": 6.270555383183369, "percentage": 31.35, "elapsed_time": "0:37:19", "remaining_time": "1:21:44", "throughput": 5502.36, "total_tokens": 12324224} {"current_steps": 20215, "total_steps": 64460, "loss": 0.2276, "lr": 8.67350963769124e-06, "epoch": 6.272106732857586, "percentage": 31.36, "elapsed_time": "0:37:20", "remaining_time": "1:21:43", "throughput": 5502.1, "total_tokens": 12326304} {"current_steps": 20220, "total_steps": 64460, "loss": 0.2393, "lr": 8.672591093163449e-06, "epoch": 6.273658082531803, "percentage": 31.37, "elapsed_time": "0:37:20", "remaining_time": "1:21:42", "throughput": 5502.22, "total_tokens": 12329920} {"current_steps": 20225, "total_steps": 64460, "loss": 0.2407, "lr": 8.67167227939124e-06, "epoch": 6.275209432206019, "percentage": 31.38, "elapsed_time": "0:37:21", "remaining_time": "1:21:42", "throughput": 5502.27, "total_tokens": 12332736} {"current_steps": 20230, "total_steps": 64460, "loss": 0.2362, "lr": 8.670753196441973e-06, "epoch": 6.276760781880236, "percentage": 31.38, "elapsed_time": "0:37:21", "remaining_time": "1:21:41", "throughput": 5502.17, "total_tokens": 12335040} {"current_steps": 20235, "total_steps": 64460, "loss": 0.2268, "lr": 8.66983384438303e-06, "epoch": 6.278312131554452, "percentage": 31.39, "elapsed_time": "0:37:22", "remaining_time": "1:21:40", "throughput": 5502.26, "total_tokens": 12338112} {"current_steps": 20240, "total_steps": 64460, "loss": 0.2278, "lr": 8.668914223281808e-06, "epoch": 6.279863481228669, "percentage": 31.4, "elapsed_time": "0:37:22", "remaining_time": "1:21:40", "throughput": 5502.52, "total_tokens": 12341760} {"current_steps": 20245, "total_steps": 64460, "loss": 0.2316, "lr": 8.667994333205727e-06, "epoch": 6.281414830902886, "percentage": 31.41, "elapsed_time": "0:37:23", "remaining_time": "1:21:39", "throughput": 5502.78, "total_tokens": 12345952} {"current_steps": 20250, "total_steps": 64460, "loss": 0.2319, "lr": 8.667074174222225e-06, "epoch": 6.282966180577102, "percentage": 31.41, "elapsed_time": "0:37:24", "remaining_time": "1:21:39", "throughput": 5502.74, "total_tokens": 12348480} {"current_steps": 20255, "total_steps": 64460, "loss": 0.2288, "lr": 8.666153746398763e-06, "epoch": 6.2845175302513185, "percentage": 31.42, "elapsed_time": "0:37:24", "remaining_time": "1:21:38", "throughput": 5502.83, "total_tokens": 12351424} {"current_steps": 20260, "total_steps": 64460, "loss": 0.2323, "lr": 8.665233049802817e-06, "epoch": 6.286068879925535, "percentage": 31.43, "elapsed_time": "0:37:25", "remaining_time": "1:21:38", "throughput": 5502.76, "total_tokens": 12354336} {"current_steps": 20265, "total_steps": 64460, "loss": 0.2291, "lr": 8.664312084501886e-06, "epoch": 6.287620229599752, "percentage": 31.44, "elapsed_time": "0:37:25", "remaining_time": "1:21:37", "throughput": 5502.85, "total_tokens": 12357504} {"current_steps": 20270, "total_steps": 64460, "loss": 0.2348, "lr": 8.663390850563487e-06, "epoch": 6.289171579273968, "percentage": 31.45, "elapsed_time": "0:37:26", "remaining_time": "1:21:36", "throughput": 5502.7, "total_tokens": 12359840} {"current_steps": 20275, "total_steps": 64460, "loss": 0.2296, "lr": 8.662469348055158e-06, "epoch": 6.290722928948185, "percentage": 31.45, "elapsed_time": "0:37:26", "remaining_time": "1:21:36", "throughput": 5502.82, "total_tokens": 12363232} {"current_steps": 20280, "total_steps": 64460, "loss": 0.2307, "lr": 8.661547577044453e-06, "epoch": 6.2922742786224015, "percentage": 31.46, "elapsed_time": "0:37:27", "remaining_time": "1:21:35", "throughput": 5502.71, "total_tokens": 12365760} {"current_steps": 20285, "total_steps": 64460, "loss": 0.2302, "lr": 8.660625537598955e-06, "epoch": 6.293825628296618, "percentage": 31.47, "elapsed_time": "0:37:27", "remaining_time": "1:21:34", "throughput": 5502.67, "total_tokens": 12368416} {"current_steps": 20290, "total_steps": 64460, "loss": 0.2292, "lr": 8.659703229786253e-06, "epoch": 6.295376977970834, "percentage": 31.48, "elapsed_time": "0:37:28", "remaining_time": "1:21:34", "throughput": 5502.71, "total_tokens": 12371232} {"current_steps": 20295, "total_steps": 64460, "loss": 0.2308, "lr": 8.65878065367397e-06, "epoch": 6.296928327645051, "percentage": 31.48, "elapsed_time": "0:37:28", "remaining_time": "1:21:33", "throughput": 5502.99, "total_tokens": 12374752} {"current_steps": 20300, "total_steps": 64460, "loss": 0.2285, "lr": 8.657857809329738e-06, "epoch": 6.298479677319268, "percentage": 31.49, "elapsed_time": "0:37:29", "remaining_time": "1:21:32", "throughput": 5502.97, "total_tokens": 12377440} {"current_steps": 20305, "total_steps": 64460, "loss": 0.2303, "lr": 8.656934696821213e-06, "epoch": 6.3000310269934845, "percentage": 31.5, "elapsed_time": "0:37:29", "remaining_time": "1:21:32", "throughput": 5502.97, "total_tokens": 12380064} {"current_steps": 20310, "total_steps": 64460, "loss": 0.2367, "lr": 8.656011316216071e-06, "epoch": 6.301582376667701, "percentage": 31.51, "elapsed_time": "0:37:30", "remaining_time": "1:21:31", "throughput": 5502.97, "total_tokens": 12382784} {"current_steps": 20315, "total_steps": 64460, "loss": 0.2288, "lr": 8.655087667582005e-06, "epoch": 6.303133726341917, "percentage": 31.52, "elapsed_time": "0:37:30", "remaining_time": "1:21:31", "throughput": 5503.05, "total_tokens": 12386208} {"current_steps": 20320, "total_steps": 64460, "loss": 0.2288, "lr": 8.654163750986729e-06, "epoch": 6.304685076016134, "percentage": 31.52, "elapsed_time": "0:37:31", "remaining_time": "1:21:30", "throughput": 5502.9, "total_tokens": 12388576} {"current_steps": 20325, "total_steps": 64460, "loss": 0.2319, "lr": 8.65323956649798e-06, "epoch": 6.306236425690351, "percentage": 31.53, "elapsed_time": "0:37:31", "remaining_time": "1:21:29", "throughput": 5503.17, "total_tokens": 12392256} {"current_steps": 20330, "total_steps": 64460, "loss": 0.2349, "lr": 8.652315114183509e-06, "epoch": 6.3077877753645675, "percentage": 31.54, "elapsed_time": "0:37:32", "remaining_time": "1:21:29", "throughput": 5503.25, "total_tokens": 12395072} {"current_steps": 20335, "total_steps": 64460, "loss": 0.2359, "lr": 8.65139039411109e-06, "epoch": 6.309339125038783, "percentage": 31.55, "elapsed_time": "0:37:32", "remaining_time": "1:21:28", "throughput": 5503.4, "total_tokens": 12398208} {"current_steps": 20340, "total_steps": 64460, "loss": 0.2265, "lr": 8.650465406348517e-06, "epoch": 6.310890474713, "percentage": 31.55, "elapsed_time": "0:37:33", "remaining_time": "1:21:27", "throughput": 5503.25, "total_tokens": 12400448} {"current_steps": 20345, "total_steps": 64460, "loss": 0.2336, "lr": 8.649540150963603e-06, "epoch": 6.312441824387217, "percentage": 31.56, "elapsed_time": "0:37:33", "remaining_time": "1:21:27", "throughput": 5503.32, "total_tokens": 12403488} {"current_steps": 20350, "total_steps": 64460, "loss": 0.2284, "lr": 8.648614628024177e-06, "epoch": 6.313993174061434, "percentage": 31.57, "elapsed_time": "0:37:34", "remaining_time": "1:21:26", "throughput": 5503.18, "total_tokens": 12405952} {"current_steps": 20355, "total_steps": 64460, "loss": 0.23, "lr": 8.647688837598092e-06, "epoch": 6.31554452373565, "percentage": 31.58, "elapsed_time": "0:37:34", "remaining_time": "1:21:26", "throughput": 5503.51, "total_tokens": 12410304} {"current_steps": 20360, "total_steps": 64460, "loss": 0.2338, "lr": 8.646762779753221e-06, "epoch": 6.317095873409866, "percentage": 31.59, "elapsed_time": "0:37:35", "remaining_time": "1:21:25", "throughput": 5503.51, "total_tokens": 12412896} {"current_steps": 20365, "total_steps": 64460, "loss": 0.2255, "lr": 8.645836454557454e-06, "epoch": 6.318647223084083, "percentage": 31.59, "elapsed_time": "0:37:36", "remaining_time": "1:21:24", "throughput": 5503.83, "total_tokens": 12416864} {"current_steps": 20370, "total_steps": 64460, "loss": 0.2336, "lr": 8.644909862078702e-06, "epoch": 6.3201985727583, "percentage": 31.6, "elapsed_time": "0:37:36", "remaining_time": "1:21:24", "throughput": 5503.84, "total_tokens": 12419776} {"current_steps": 20375, "total_steps": 64460, "loss": 0.2279, "lr": 8.643983002384897e-06, "epoch": 6.321749922432517, "percentage": 31.61, "elapsed_time": "0:37:37", "remaining_time": "1:21:23", "throughput": 5503.85, "total_tokens": 12422784} {"current_steps": 20380, "total_steps": 64460, "loss": 0.2276, "lr": 8.643055875543984e-06, "epoch": 6.3233012721067325, "percentage": 31.62, "elapsed_time": "0:37:37", "remaining_time": "1:21:23", "throughput": 5503.89, "total_tokens": 12425824} {"current_steps": 20385, "total_steps": 64460, "loss": 0.2327, "lr": 8.642128481623935e-06, "epoch": 6.324852621780949, "percentage": 31.62, "elapsed_time": "0:37:38", "remaining_time": "1:21:22", "throughput": 5503.85, "total_tokens": 12428384} {"current_steps": 20390, "total_steps": 64460, "loss": 0.2276, "lr": 8.641200820692741e-06, "epoch": 6.326403971455166, "percentage": 31.63, "elapsed_time": "0:37:38", "remaining_time": "1:21:21", "throughput": 5503.62, "total_tokens": 12430432} {"current_steps": 20395, "total_steps": 64460, "loss": 0.2349, "lr": 8.640272892818406e-06, "epoch": 6.327955321129383, "percentage": 31.64, "elapsed_time": "0:37:39", "remaining_time": "1:21:21", "throughput": 5503.56, "total_tokens": 12433280} {"current_steps": 20400, "total_steps": 64460, "loss": 0.2301, "lr": 8.639344698068963e-06, "epoch": 6.329506670803599, "percentage": 31.65, "elapsed_time": "0:37:39", "remaining_time": "1:21:20", "throughput": 5503.41, "total_tokens": 12435872} {"current_steps": 20405, "total_steps": 64460, "loss": 0.2254, "lr": 8.638416236512457e-06, "epoch": 6.3310580204778155, "percentage": 31.66, "elapsed_time": "0:37:40", "remaining_time": "1:21:19", "throughput": 5503.35, "total_tokens": 12438432} {"current_steps": 20410, "total_steps": 64460, "loss": 0.2348, "lr": 8.637487508216954e-06, "epoch": 6.332609370152032, "percentage": 31.66, "elapsed_time": "0:37:40", "remaining_time": "1:21:19", "throughput": 5503.27, "total_tokens": 12440960} {"current_steps": 20415, "total_steps": 64460, "loss": 0.2299, "lr": 8.636558513250544e-06, "epoch": 6.334160719826249, "percentage": 31.67, "elapsed_time": "0:37:41", "remaining_time": "1:21:18", "throughput": 5503.15, "total_tokens": 12443616} {"current_steps": 20420, "total_steps": 64460, "loss": 0.2233, "lr": 8.63562925168133e-06, "epoch": 6.335712069500465, "percentage": 31.68, "elapsed_time": "0:37:41", "remaining_time": "1:21:17", "throughput": 5503.31, "total_tokens": 12446752} {"current_steps": 20425, "total_steps": 64460, "loss": 0.2344, "lr": 8.63469972357744e-06, "epoch": 6.337263419174682, "percentage": 31.69, "elapsed_time": "0:37:42", "remaining_time": "1:21:17", "throughput": 5503.38, "total_tokens": 12449696} {"current_steps": 20430, "total_steps": 64460, "loss": 0.2304, "lr": 8.633769929007021e-06, "epoch": 6.3388147688488985, "percentage": 31.69, "elapsed_time": "0:37:42", "remaining_time": "1:21:16", "throughput": 5503.17, "total_tokens": 12451872} {"current_steps": 20435, "total_steps": 64460, "loss": 0.2299, "lr": 8.632839868038234e-06, "epoch": 6.340366118523115, "percentage": 31.7, "elapsed_time": "0:37:43", "remaining_time": "1:21:15", "throughput": 5503.02, "total_tokens": 12454048} {"current_steps": 20440, "total_steps": 64460, "loss": 0.2279, "lr": 8.631909540739266e-06, "epoch": 6.341917468197332, "percentage": 31.71, "elapsed_time": "0:37:43", "remaining_time": "1:21:15", "throughput": 5503.02, "total_tokens": 12456896} {"current_steps": 20445, "total_steps": 64460, "loss": 0.2296, "lr": 8.63097894717832e-06, "epoch": 6.343468817871548, "percentage": 31.72, "elapsed_time": "0:37:44", "remaining_time": "1:21:14", "throughput": 5502.92, "total_tokens": 12459488} {"current_steps": 20450, "total_steps": 64460, "loss": 0.2318, "lr": 8.63004808742362e-06, "epoch": 6.345020167545765, "percentage": 31.73, "elapsed_time": "0:37:44", "remaining_time": "1:21:13", "throughput": 5503.07, "total_tokens": 12463008} {"current_steps": 20455, "total_steps": 64460, "loss": 0.229, "lr": 8.629116961543408e-06, "epoch": 6.3465715172199815, "percentage": 31.73, "elapsed_time": "0:37:45", "remaining_time": "1:21:13", "throughput": 5503.0, "total_tokens": 12465696} {"current_steps": 20460, "total_steps": 64460, "loss": 0.2248, "lr": 8.62818556960595e-06, "epoch": 6.348122866894198, "percentage": 31.74, "elapsed_time": "0:37:45", "remaining_time": "1:21:12", "throughput": 5503.4, "total_tokens": 12470016} {"current_steps": 20465, "total_steps": 64460, "loss": 0.2316, "lr": 8.627253911679524e-06, "epoch": 6.349674216568414, "percentage": 31.75, "elapsed_time": "0:37:46", "remaining_time": "1:21:12", "throughput": 5503.39, "total_tokens": 12472992} {"current_steps": 20470, "total_steps": 64460, "loss": 0.2325, "lr": 8.626321987832434e-06, "epoch": 6.351225566242631, "percentage": 31.76, "elapsed_time": "0:37:46", "remaining_time": "1:21:11", "throughput": 5503.6, "total_tokens": 12476448} {"current_steps": 20475, "total_steps": 64460, "loss": 0.2351, "lr": 8.625389798133e-06, "epoch": 6.352776915916848, "percentage": 31.76, "elapsed_time": "0:37:47", "remaining_time": "1:21:11", "throughput": 5503.66, "total_tokens": 12479456} {"current_steps": 20480, "total_steps": 64460, "loss": 0.2276, "lr": 8.624457342649563e-06, "epoch": 6.3543282655910645, "percentage": 31.77, "elapsed_time": "0:37:47", "remaining_time": "1:21:10", "throughput": 5503.66, "total_tokens": 12482048} {"current_steps": 20485, "total_steps": 64460, "loss": 0.2334, "lr": 8.623524621450483e-06, "epoch": 6.35587961526528, "percentage": 31.78, "elapsed_time": "0:37:48", "remaining_time": "1:21:09", "throughput": 5503.59, "total_tokens": 12484608} {"current_steps": 20490, "total_steps": 64460, "loss": 0.2404, "lr": 8.622591634604138e-06, "epoch": 6.357430964939497, "percentage": 31.79, "elapsed_time": "0:37:48", "remaining_time": "1:21:09", "throughput": 5503.63, "total_tokens": 12487488} {"current_steps": 20495, "total_steps": 64460, "loss": 0.2296, "lr": 8.621658382178929e-06, "epoch": 6.358982314613714, "percentage": 31.79, "elapsed_time": "0:37:49", "remaining_time": "1:21:08", "throughput": 5503.49, "total_tokens": 12489792} {"current_steps": 20500, "total_steps": 64460, "loss": 0.2255, "lr": 8.620724864243272e-06, "epoch": 6.360533664287931, "percentage": 31.8, "elapsed_time": "0:37:49", "remaining_time": "1:21:07", "throughput": 5503.53, "total_tokens": 12492672} {"current_steps": 20505, "total_steps": 64460, "loss": 0.2317, "lr": 8.619791080865609e-06, "epoch": 6.362085013962147, "percentage": 31.81, "elapsed_time": "0:37:50", "remaining_time": "1:21:06", "throughput": 5503.53, "total_tokens": 12495328} {"current_steps": 20510, "total_steps": 64460, "loss": 0.2369, "lr": 8.618857032114396e-06, "epoch": 6.363636363636363, "percentage": 31.82, "elapsed_time": "0:37:50", "remaining_time": "1:21:06", "throughput": 5503.71, "total_tokens": 12498752} {"current_steps": 20515, "total_steps": 64460, "loss": 0.2327, "lr": 8.617922718058106e-06, "epoch": 6.36518771331058, "percentage": 31.83, "elapsed_time": "0:37:51", "remaining_time": "1:21:05", "throughput": 5503.64, "total_tokens": 12501408} {"current_steps": 20520, "total_steps": 64460, "loss": 0.2321, "lr": 8.61698813876524e-06, "epoch": 6.366739062984797, "percentage": 31.83, "elapsed_time": "0:37:51", "remaining_time": "1:21:05", "throughput": 5503.5, "total_tokens": 12503744} {"current_steps": 20525, "total_steps": 64460, "loss": 0.2316, "lr": 8.61605329430431e-06, "epoch": 6.368290412659014, "percentage": 31.84, "elapsed_time": "0:37:52", "remaining_time": "1:21:04", "throughput": 5503.55, "total_tokens": 12506656} {"current_steps": 20530, "total_steps": 64460, "loss": 0.2382, "lr": 8.615118184743857e-06, "epoch": 6.3698417623332295, "percentage": 31.85, "elapsed_time": "0:37:52", "remaining_time": "1:21:03", "throughput": 5503.45, "total_tokens": 12508992} {"current_steps": 20535, "total_steps": 64460, "loss": 0.2302, "lr": 8.614182810152427e-06, "epoch": 6.371393112007446, "percentage": 31.86, "elapsed_time": "0:37:53", "remaining_time": "1:21:03", "throughput": 5503.57, "total_tokens": 12512192} {"current_steps": 20540, "total_steps": 64460, "loss": 0.2318, "lr": 8.6132471705986e-06, "epoch": 6.372944461681663, "percentage": 31.86, "elapsed_time": "0:37:53", "remaining_time": "1:21:02", "throughput": 5503.73, "total_tokens": 12515424} {"current_steps": 20545, "total_steps": 64460, "loss": 0.2307, "lr": 8.61231126615097e-06, "epoch": 6.37449581135588, "percentage": 31.87, "elapsed_time": "0:37:54", "remaining_time": "1:21:01", "throughput": 5503.9, "total_tokens": 12518784} {"current_steps": 20550, "total_steps": 64460, "loss": 0.2334, "lr": 8.611375096878147e-06, "epoch": 6.376047161030096, "percentage": 31.88, "elapsed_time": "0:37:55", "remaining_time": "1:21:01", "throughput": 5504.02, "total_tokens": 12522112} {"current_steps": 20555, "total_steps": 64460, "loss": 0.237, "lr": 8.610438662848764e-06, "epoch": 6.3775985107043125, "percentage": 31.89, "elapsed_time": "0:37:55", "remaining_time": "1:21:00", "throughput": 5504.1, "total_tokens": 12524928} {"current_steps": 20560, "total_steps": 64460, "loss": 0.2321, "lr": 8.609501964131473e-06, "epoch": 6.379149860378529, "percentage": 31.9, "elapsed_time": "0:37:56", "remaining_time": "1:20:59", "throughput": 5504.07, "total_tokens": 12527456} {"current_steps": 20565, "total_steps": 64460, "loss": 0.2266, "lr": 8.608565000794944e-06, "epoch": 6.380701210052746, "percentage": 31.9, "elapsed_time": "0:37:56", "remaining_time": "1:20:59", "throughput": 5504.23, "total_tokens": 12530752} {"current_steps": 20570, "total_steps": 64460, "loss": 0.2312, "lr": 8.60762777290787e-06, "epoch": 6.382252559726963, "percentage": 31.91, "elapsed_time": "0:37:57", "remaining_time": "1:20:58", "throughput": 5504.19, "total_tokens": 12533728} {"current_steps": 20575, "total_steps": 64460, "loss": 0.2354, "lr": 8.60669028053896e-06, "epoch": 6.383803909401179, "percentage": 31.92, "elapsed_time": "0:37:57", "remaining_time": "1:20:57", "throughput": 5504.21, "total_tokens": 12536416} {"current_steps": 20580, "total_steps": 64460, "loss": 0.2305, "lr": 8.605752523756943e-06, "epoch": 6.3853552590753955, "percentage": 31.93, "elapsed_time": "0:37:58", "remaining_time": "1:20:57", "throughput": 5504.64, "total_tokens": 12541248} {"current_steps": 20585, "total_steps": 64460, "loss": 0.2353, "lr": 8.604814502630567e-06, "epoch": 6.386906608749612, "percentage": 31.93, "elapsed_time": "0:37:58", "remaining_time": "1:20:57", "throughput": 5504.71, "total_tokens": 12544096} {"current_steps": 20590, "total_steps": 64460, "loss": 0.2311, "lr": 8.6038762172286e-06, "epoch": 6.388457958423829, "percentage": 31.94, "elapsed_time": "0:37:59", "remaining_time": "1:20:56", "throughput": 5504.84, "total_tokens": 12547072} {"current_steps": 20595, "total_steps": 64460, "loss": 0.2307, "lr": 8.60293766761983e-06, "epoch": 6.390009308098045, "percentage": 31.95, "elapsed_time": "0:37:59", "remaining_time": "1:20:55", "throughput": 5504.92, "total_tokens": 12550176} {"current_steps": 20600, "total_steps": 64460, "loss": 0.2381, "lr": 8.601998853873063e-06, "epoch": 6.391560657772262, "percentage": 31.96, "elapsed_time": "0:38:00", "remaining_time": "1:20:55", "throughput": 5505.14, "total_tokens": 12553952} {"current_steps": 20605, "total_steps": 64460, "loss": 0.2281, "lr": 8.601059776057128e-06, "epoch": 6.3931120074464785, "percentage": 31.97, "elapsed_time": "0:38:00", "remaining_time": "1:20:54", "throughput": 5505.18, "total_tokens": 12556832} {"current_steps": 20610, "total_steps": 64460, "loss": 0.2255, "lr": 8.600120434240868e-06, "epoch": 6.394663357120695, "percentage": 31.97, "elapsed_time": "0:38:01", "remaining_time": "1:20:54", "throughput": 5505.18, "total_tokens": 12559808} {"current_steps": 20615, "total_steps": 64460, "loss": 0.2337, "lr": 8.599180828493147e-06, "epoch": 6.396214706794911, "percentage": 31.98, "elapsed_time": "0:38:01", "remaining_time": "1:20:53", "throughput": 5505.23, "total_tokens": 12562624} {"current_steps": 20620, "total_steps": 64460, "loss": 0.2388, "lr": 8.598240958882853e-06, "epoch": 6.397766056469128, "percentage": 31.99, "elapsed_time": "0:38:02", "remaining_time": "1:20:52", "throughput": 5505.22, "total_tokens": 12565376} {"current_steps": 20625, "total_steps": 64460, "loss": 0.2369, "lr": 8.597300825478884e-06, "epoch": 6.399317406143345, "percentage": 32.0, "elapsed_time": "0:38:02", "remaining_time": "1:20:52", "throughput": 5505.37, "total_tokens": 12568416} {"current_steps": 20630, "total_steps": 64460, "loss": 0.2329, "lr": 8.596360428350169e-06, "epoch": 6.400868755817561, "percentage": 32.0, "elapsed_time": "0:38:03", "remaining_time": "1:20:51", "throughput": 5505.46, "total_tokens": 12572096} {"current_steps": 20635, "total_steps": 64460, "loss": 0.2256, "lr": 8.595419767565645e-06, "epoch": 6.402420105491778, "percentage": 32.01, "elapsed_time": "0:38:04", "remaining_time": "1:20:51", "throughput": 5505.84, "total_tokens": 12576224} {"current_steps": 20640, "total_steps": 64460, "loss": 0.2301, "lr": 8.594478843194279e-06, "epoch": 6.403971455165994, "percentage": 32.02, "elapsed_time": "0:38:04", "remaining_time": "1:20:50", "throughput": 5506.0, "total_tokens": 12579328} {"current_steps": 20645, "total_steps": 64460, "loss": 0.2337, "lr": 8.593537655305047e-06, "epoch": 6.405522804840211, "percentage": 32.03, "elapsed_time": "0:38:05", "remaining_time": "1:20:49", "throughput": 5506.03, "total_tokens": 12582176} {"current_steps": 20650, "total_steps": 64460, "loss": 0.23, "lr": 8.59259620396695e-06, "epoch": 6.407074154514428, "percentage": 32.04, "elapsed_time": "0:38:05", "remaining_time": "1:20:49", "throughput": 5505.91, "total_tokens": 12584864} {"current_steps": 20655, "total_steps": 64460, "loss": 0.2289, "lr": 8.591654489249009e-06, "epoch": 6.408625504188644, "percentage": 32.04, "elapsed_time": "0:38:06", "remaining_time": "1:20:48", "throughput": 5506.04, "total_tokens": 12588096} {"current_steps": 20660, "total_steps": 64460, "loss": 0.2265, "lr": 8.590712511220262e-06, "epoch": 6.41017685386286, "percentage": 32.05, "elapsed_time": "0:38:06", "remaining_time": "1:20:47", "throughput": 5506.09, "total_tokens": 12591040} {"current_steps": 20665, "total_steps": 64460, "loss": 0.2393, "lr": 8.58977026994977e-06, "epoch": 6.411728203537077, "percentage": 32.06, "elapsed_time": "0:38:07", "remaining_time": "1:20:47", "throughput": 5505.99, "total_tokens": 12593440} {"current_steps": 20670, "total_steps": 64460, "loss": 0.2356, "lr": 8.588827765506606e-06, "epoch": 6.413279553211294, "percentage": 32.07, "elapsed_time": "0:38:07", "remaining_time": "1:20:46", "throughput": 5505.9, "total_tokens": 12595872} {"current_steps": 20675, "total_steps": 64460, "loss": 0.2322, "lr": 8.587884997959867e-06, "epoch": 6.414830902885511, "percentage": 32.07, "elapsed_time": "0:38:08", "remaining_time": "1:20:45", "throughput": 5505.81, "total_tokens": 12598208} {"current_steps": 20680, "total_steps": 64460, "loss": 0.2332, "lr": 8.586941967378675e-06, "epoch": 6.4163822525597265, "percentage": 32.08, "elapsed_time": "0:38:08", "remaining_time": "1:20:45", "throughput": 5505.9, "total_tokens": 12601632} {"current_steps": 20685, "total_steps": 64460, "loss": 0.2358, "lr": 8.585998673832158e-06, "epoch": 6.417933602233943, "percentage": 32.09, "elapsed_time": "0:38:09", "remaining_time": "1:20:44", "throughput": 5505.76, "total_tokens": 12603904} {"current_steps": 20690, "total_steps": 64460, "loss": 0.2326, "lr": 8.585055117389475e-06, "epoch": 6.41948495190816, "percentage": 32.1, "elapsed_time": "0:38:09", "remaining_time": "1:20:43", "throughput": 5505.95, "total_tokens": 12607168} {"current_steps": 20695, "total_steps": 64460, "loss": 0.2316, "lr": 8.584111298119797e-06, "epoch": 6.421036301582377, "percentage": 32.11, "elapsed_time": "0:38:10", "remaining_time": "1:20:43", "throughput": 5505.96, "total_tokens": 12610464} {"current_steps": 20700, "total_steps": 64460, "loss": 0.2331, "lr": 8.583167216092319e-06, "epoch": 6.422587651256594, "percentage": 32.11, "elapsed_time": "0:38:10", "remaining_time": "1:20:42", "throughput": 5506.14, "total_tokens": 12613792} {"current_steps": 20705, "total_steps": 64460, "loss": 0.2305, "lr": 8.582222871376253e-06, "epoch": 6.4241390009308095, "percentage": 32.12, "elapsed_time": "0:38:11", "remaining_time": "1:20:42", "throughput": 5506.36, "total_tokens": 12618528} {"current_steps": 20710, "total_steps": 64460, "loss": 0.2335, "lr": 8.581278264040832e-06, "epoch": 6.425690350605026, "percentage": 32.13, "elapsed_time": "0:38:12", "remaining_time": "1:20:42", "throughput": 5506.51, "total_tokens": 12621600} {"current_steps": 20715, "total_steps": 64460, "loss": 0.2284, "lr": 8.580333394155305e-06, "epoch": 6.427241700279243, "percentage": 32.14, "elapsed_time": "0:38:12", "remaining_time": "1:20:41", "throughput": 5506.66, "total_tokens": 12624832} {"current_steps": 20720, "total_steps": 64460, "loss": 0.2269, "lr": 8.579388261788943e-06, "epoch": 6.42879304995346, "percentage": 32.14, "elapsed_time": "0:38:13", "remaining_time": "1:20:40", "throughput": 5506.8, "total_tokens": 12628000} {"current_steps": 20725, "total_steps": 64460, "loss": 0.2269, "lr": 8.578442867011035e-06, "epoch": 6.430344399627676, "percentage": 32.15, "elapsed_time": "0:38:13", "remaining_time": "1:20:40", "throughput": 5506.89, "total_tokens": 12631008} {"current_steps": 20730, "total_steps": 64460, "loss": 0.233, "lr": 8.577497209890889e-06, "epoch": 6.4318957493018925, "percentage": 32.16, "elapsed_time": "0:38:14", "remaining_time": "1:20:39", "throughput": 5506.84, "total_tokens": 12633632} {"current_steps": 20735, "total_steps": 64460, "loss": 0.2341, "lr": 8.576551290497833e-06, "epoch": 6.433447098976109, "percentage": 32.17, "elapsed_time": "0:38:14", "remaining_time": "1:20:38", "throughput": 5506.97, "total_tokens": 12636768} {"current_steps": 20740, "total_steps": 64460, "loss": 0.2268, "lr": 8.575605108901217e-06, "epoch": 6.434998448650326, "percentage": 32.17, "elapsed_time": "0:38:15", "remaining_time": "1:20:38", "throughput": 5507.24, "total_tokens": 12640256} {"current_steps": 20745, "total_steps": 64460, "loss": 0.2349, "lr": 8.574658665170404e-06, "epoch": 6.436549798324542, "percentage": 32.18, "elapsed_time": "0:38:15", "remaining_time": "1:20:37", "throughput": 5507.11, "total_tokens": 12642528} {"current_steps": 20750, "total_steps": 64460, "loss": 0.2323, "lr": 8.57371195937478e-06, "epoch": 6.438101147998759, "percentage": 32.19, "elapsed_time": "0:38:16", "remaining_time": "1:20:36", "throughput": 5507.17, "total_tokens": 12645408} {"current_steps": 20755, "total_steps": 64460, "loss": 0.2304, "lr": 8.57276499158375e-06, "epoch": 6.439652497672975, "percentage": 32.2, "elapsed_time": "0:38:16", "remaining_time": "1:20:36", "throughput": 5507.22, "total_tokens": 12648320} {"current_steps": 20760, "total_steps": 64460, "loss": 0.2242, "lr": 8.571817761866739e-06, "epoch": 6.441203847347192, "percentage": 32.21, "elapsed_time": "0:38:17", "remaining_time": "1:20:35", "throughput": 5507.23, "total_tokens": 12651008} {"current_steps": 20765, "total_steps": 64460, "loss": 0.2218, "lr": 8.570870270293188e-06, "epoch": 6.442755197021409, "percentage": 32.21, "elapsed_time": "0:38:17", "remaining_time": "1:20:34", "throughput": 5507.37, "total_tokens": 12654144} {"current_steps": 20770, "total_steps": 64460, "loss": 0.2271, "lr": 8.569922516932564e-06, "epoch": 6.444306546695625, "percentage": 32.22, "elapsed_time": "0:38:18", "remaining_time": "1:20:34", "throughput": 5507.36, "total_tokens": 12656928} {"current_steps": 20775, "total_steps": 64460, "loss": 0.2387, "lr": 8.56897450185434e-06, "epoch": 6.445857896369842, "percentage": 32.23, "elapsed_time": "0:38:18", "remaining_time": "1:20:33", "throughput": 5507.57, "total_tokens": 12660384} {"current_steps": 20780, "total_steps": 64460, "loss": 0.2193, "lr": 8.568026225128028e-06, "epoch": 6.447409246044058, "percentage": 32.24, "elapsed_time": "0:38:19", "remaining_time": "1:20:33", "throughput": 5507.53, "total_tokens": 12663200} {"current_steps": 20785, "total_steps": 64460, "loss": 0.2467, "lr": 8.567077686823137e-06, "epoch": 6.448960595718275, "percentage": 32.24, "elapsed_time": "0:38:19", "remaining_time": "1:20:32", "throughput": 5507.66, "total_tokens": 12666272} {"current_steps": 20790, "total_steps": 64460, "loss": 0.2422, "lr": 8.566128887009213e-06, "epoch": 6.450511945392491, "percentage": 32.25, "elapsed_time": "0:38:20", "remaining_time": "1:20:31", "throughput": 5507.57, "total_tokens": 12668672} {"current_steps": 20795, "total_steps": 64460, "loss": 0.2379, "lr": 8.565179825755813e-06, "epoch": 6.452063295066708, "percentage": 32.26, "elapsed_time": "0:38:20", "remaining_time": "1:20:31", "throughput": 5507.83, "total_tokens": 12672736} {"current_steps": 20800, "total_steps": 64460, "loss": 0.2291, "lr": 8.564230503132513e-06, "epoch": 6.453614644740925, "percentage": 32.27, "elapsed_time": "0:38:21", "remaining_time": "1:20:30", "throughput": 5507.97, "total_tokens": 12675936} {"current_steps": 20805, "total_steps": 64460, "loss": 0.2392, "lr": 8.563280919208911e-06, "epoch": 6.455165994415141, "percentage": 32.28, "elapsed_time": "0:38:21", "remaining_time": "1:20:30", "throughput": 5508.2, "total_tokens": 12679296} {"current_steps": 20810, "total_steps": 64460, "loss": 0.2302, "lr": 8.562331074054621e-06, "epoch": 6.456717344089358, "percentage": 32.28, "elapsed_time": "0:38:22", "remaining_time": "1:20:29", "throughput": 5508.41, "total_tokens": 12683232} {"current_steps": 20815, "total_steps": 64460, "loss": 0.23, "lr": 8.561380967739282e-06, "epoch": 6.458268693763574, "percentage": 32.29, "elapsed_time": "0:38:23", "remaining_time": "1:20:28", "throughput": 5508.52, "total_tokens": 12686176} {"current_steps": 20820, "total_steps": 64460, "loss": 0.2315, "lr": 8.56043060033254e-06, "epoch": 6.459820043437791, "percentage": 32.3, "elapsed_time": "0:38:23", "remaining_time": "1:20:28", "throughput": 5508.58, "total_tokens": 12689216} {"current_steps": 20825, "total_steps": 64460, "loss": 0.2288, "lr": 8.559479971904077e-06, "epoch": 6.461371393112008, "percentage": 32.31, "elapsed_time": "0:38:24", "remaining_time": "1:20:27", "throughput": 5508.65, "total_tokens": 12692608} {"current_steps": 20830, "total_steps": 64460, "loss": 0.2293, "lr": 8.558529082523581e-06, "epoch": 6.462922742786224, "percentage": 32.31, "elapsed_time": "0:38:24", "remaining_time": "1:20:27", "throughput": 5508.42, "total_tokens": 12694688} {"current_steps": 20835, "total_steps": 64460, "loss": 0.231, "lr": 8.557577932260763e-06, "epoch": 6.46447409246044, "percentage": 32.32, "elapsed_time": "0:38:25", "remaining_time": "1:20:26", "throughput": 5508.36, "total_tokens": 12697344} {"current_steps": 20840, "total_steps": 64460, "loss": 0.2314, "lr": 8.556626521185356e-06, "epoch": 6.466025442134657, "percentage": 32.33, "elapsed_time": "0:38:25", "remaining_time": "1:20:25", "throughput": 5508.53, "total_tokens": 12700832} {"current_steps": 20845, "total_steps": 64460, "loss": 0.2269, "lr": 8.555674849367106e-06, "epoch": 6.467576791808874, "percentage": 32.34, "elapsed_time": "0:38:26", "remaining_time": "1:20:25", "throughput": 5508.69, "total_tokens": 12704096} {"current_steps": 20850, "total_steps": 64460, "loss": 0.2335, "lr": 8.554722916875786e-06, "epoch": 6.469128141483091, "percentage": 32.35, "elapsed_time": "0:38:26", "remaining_time": "1:20:24", "throughput": 5508.89, "total_tokens": 12707712} {"current_steps": 20855, "total_steps": 64460, "loss": 0.2331, "lr": 8.55377072378118e-06, "epoch": 6.4706794911573065, "percentage": 32.35, "elapsed_time": "0:38:27", "remaining_time": "1:20:24", "throughput": 5509.06, "total_tokens": 12711264} {"current_steps": 20860, "total_steps": 64460, "loss": 0.2279, "lr": 8.552818270153098e-06, "epoch": 6.472230840831523, "percentage": 32.36, "elapsed_time": "0:38:27", "remaining_time": "1:20:23", "throughput": 5509.11, "total_tokens": 12714016} {"current_steps": 20865, "total_steps": 64460, "loss": 0.2301, "lr": 8.551865556061364e-06, "epoch": 6.47378219050574, "percentage": 32.37, "elapsed_time": "0:38:28", "remaining_time": "1:20:23", "throughput": 5509.25, "total_tokens": 12717408} {"current_steps": 20870, "total_steps": 64460, "loss": 0.2389, "lr": 8.550912581575828e-06, "epoch": 6.475333540179957, "percentage": 32.38, "elapsed_time": "0:38:28", "remaining_time": "1:20:22", "throughput": 5509.26, "total_tokens": 12720352} {"current_steps": 20875, "total_steps": 64460, "loss": 0.2278, "lr": 8.549959346766348e-06, "epoch": 6.4768848898541735, "percentage": 32.38, "elapsed_time": "0:38:29", "remaining_time": "1:20:21", "throughput": 5509.3, "total_tokens": 12723008} {"current_steps": 20880, "total_steps": 64460, "loss": 0.2339, "lr": 8.54900585170281e-06, "epoch": 6.478436239528389, "percentage": 32.39, "elapsed_time": "0:38:30", "remaining_time": "1:20:21", "throughput": 5509.64, "total_tokens": 12727552} {"current_steps": 20885, "total_steps": 64460, "loss": 0.2332, "lr": 8.548052096455117e-06, "epoch": 6.479987589202606, "percentage": 32.4, "elapsed_time": "0:38:30", "remaining_time": "1:20:20", "throughput": 5509.48, "total_tokens": 12729760} {"current_steps": 20890, "total_steps": 64460, "loss": 0.23, "lr": 8.547098081093189e-06, "epoch": 6.481538938876823, "percentage": 32.41, "elapsed_time": "0:38:31", "remaining_time": "1:20:20", "throughput": 5509.42, "total_tokens": 12732320} {"current_steps": 20895, "total_steps": 64460, "loss": 0.2306, "lr": 8.546143805686969e-06, "epoch": 6.48309028855104, "percentage": 32.42, "elapsed_time": "0:38:31", "remaining_time": "1:20:19", "throughput": 5509.43, "total_tokens": 12734944} {"current_steps": 20900, "total_steps": 64460, "loss": 0.232, "lr": 8.545189270306415e-06, "epoch": 6.484641638225256, "percentage": 32.42, "elapsed_time": "0:38:31", "remaining_time": "1:20:18", "throughput": 5509.44, "total_tokens": 12737536} {"current_steps": 20905, "total_steps": 64460, "loss": 0.233, "lr": 8.544234475021506e-06, "epoch": 6.486192987899472, "percentage": 32.43, "elapsed_time": "0:38:32", "remaining_time": "1:20:17", "throughput": 5509.51, "total_tokens": 12740320} {"current_steps": 20910, "total_steps": 64460, "loss": 0.2289, "lr": 8.543279419902243e-06, "epoch": 6.487744337573689, "percentage": 32.44, "elapsed_time": "0:38:32", "remaining_time": "1:20:17", "throughput": 5509.27, "total_tokens": 12742400} {"current_steps": 20915, "total_steps": 64460, "loss": 0.2325, "lr": 8.542324105018636e-06, "epoch": 6.489295687247906, "percentage": 32.45, "elapsed_time": "0:38:33", "remaining_time": "1:20:16", "throughput": 5509.47, "total_tokens": 12745728} {"current_steps": 20920, "total_steps": 64460, "loss": 0.2311, "lr": 8.541368530440724e-06, "epoch": 6.490847036922122, "percentage": 32.45, "elapsed_time": "0:38:33", "remaining_time": "1:20:16", "throughput": 5509.66, "total_tokens": 12749344} {"current_steps": 20925, "total_steps": 64460, "loss": 0.2316, "lr": 8.540412696238565e-06, "epoch": 6.492398386596339, "percentage": 32.46, "elapsed_time": "0:38:34", "remaining_time": "1:20:15", "throughput": 5509.59, "total_tokens": 12751840} {"current_steps": 20930, "total_steps": 64460, "loss": 0.23, "lr": 8.53945660248223e-06, "epoch": 6.493949736270555, "percentage": 32.47, "elapsed_time": "0:38:35", "remaining_time": "1:20:14", "throughput": 5509.56, "total_tokens": 12755136} {"current_steps": 20935, "total_steps": 64460, "loss": 0.2273, "lr": 8.538500249241813e-06, "epoch": 6.495501085944772, "percentage": 32.48, "elapsed_time": "0:38:35", "remaining_time": "1:20:14", "throughput": 5509.48, "total_tokens": 12757600} {"current_steps": 20940, "total_steps": 64460, "loss": 0.2321, "lr": 8.537543636587425e-06, "epoch": 6.497052435618989, "percentage": 32.49, "elapsed_time": "0:38:36", "remaining_time": "1:20:13", "throughput": 5509.57, "total_tokens": 12760736} {"current_steps": 20945, "total_steps": 64460, "loss": 0.2284, "lr": 8.536586764589198e-06, "epoch": 6.498603785293205, "percentage": 32.49, "elapsed_time": "0:38:36", "remaining_time": "1:20:12", "throughput": 5509.53, "total_tokens": 12763424} {"current_steps": 20950, "total_steps": 64460, "loss": 0.2265, "lr": 8.535629633317281e-06, "epoch": 6.500155134967422, "percentage": 32.5, "elapsed_time": "0:38:37", "remaining_time": "1:20:12", "throughput": 5509.7, "total_tokens": 12766784} {"current_steps": 20955, "total_steps": 64460, "loss": 0.2361, "lr": 8.534672242841844e-06, "epoch": 6.501706484641638, "percentage": 32.51, "elapsed_time": "0:38:37", "remaining_time": "1:20:11", "throughput": 5509.74, "total_tokens": 12769504} {"current_steps": 20960, "total_steps": 64460, "loss": 0.2301, "lr": 8.533714593233076e-06, "epoch": 6.503257834315855, "percentage": 32.52, "elapsed_time": "0:38:38", "remaining_time": "1:20:11", "throughput": 5509.89, "total_tokens": 12773024} {"current_steps": 20965, "total_steps": 64460, "loss": 0.2331, "lr": 8.532756684561181e-06, "epoch": 6.504809183990071, "percentage": 32.52, "elapsed_time": "0:38:38", "remaining_time": "1:20:10", "throughput": 5509.87, "total_tokens": 12776064} {"current_steps": 20970, "total_steps": 64460, "loss": 0.228, "lr": 8.531798516896389e-06, "epoch": 6.506360533664288, "percentage": 32.53, "elapsed_time": "0:38:39", "remaining_time": "1:20:09", "throughput": 5509.82, "total_tokens": 12778592} {"current_steps": 20975, "total_steps": 64460, "loss": 0.2406, "lr": 8.530840090308943e-06, "epoch": 6.507911883338505, "percentage": 32.54, "elapsed_time": "0:38:39", "remaining_time": "1:20:09", "throughput": 5509.72, "total_tokens": 12780928} {"current_steps": 20980, "total_steps": 64460, "loss": 0.2312, "lr": 8.529881404869105e-06, "epoch": 6.509463233012721, "percentage": 32.55, "elapsed_time": "0:38:40", "remaining_time": "1:20:08", "throughput": 5509.97, "total_tokens": 12784864} {"current_steps": 20985, "total_steps": 64460, "loss": 0.2363, "lr": 8.528922460647161e-06, "epoch": 6.511014582686938, "percentage": 32.56, "elapsed_time": "0:38:40", "remaining_time": "1:20:08", "throughput": 5510.19, "total_tokens": 12788224} {"current_steps": 20990, "total_steps": 64460, "loss": 0.2361, "lr": 8.527963257713412e-06, "epoch": 6.512565932361154, "percentage": 32.56, "elapsed_time": "0:38:41", "remaining_time": "1:20:07", "throughput": 5509.99, "total_tokens": 12790400} {"current_steps": 20995, "total_steps": 64460, "loss": 0.2246, "lr": 8.527003796138178e-06, "epoch": 6.514117282035371, "percentage": 32.57, "elapsed_time": "0:38:41", "remaining_time": "1:20:06", "throughput": 5509.94, "total_tokens": 12793216} {"current_steps": 21000, "total_steps": 64460, "loss": 0.2348, "lr": 8.526044075991801e-06, "epoch": 6.5156686317095875, "percentage": 32.58, "elapsed_time": "0:38:42", "remaining_time": "1:20:06", "throughput": 5509.85, "total_tokens": 12795552} {"current_steps": 21005, "total_steps": 64460, "loss": 0.2321, "lr": 8.525084097344638e-06, "epoch": 6.517219981383803, "percentage": 32.59, "elapsed_time": "0:38:42", "remaining_time": "1:20:05", "throughput": 5510.01, "total_tokens": 12798784} {"current_steps": 21010, "total_steps": 64460, "loss": 0.2342, "lr": 8.524123860267068e-06, "epoch": 6.51877133105802, "percentage": 32.59, "elapsed_time": "0:38:43", "remaining_time": "1:20:04", "throughput": 5510.03, "total_tokens": 12801504} {"current_steps": 21015, "total_steps": 64460, "loss": 0.234, "lr": 8.523163364829486e-06, "epoch": 6.520322680732237, "percentage": 32.6, "elapsed_time": "0:38:43", "remaining_time": "1:20:04", "throughput": 5510.05, "total_tokens": 12804288} {"current_steps": 21020, "total_steps": 64460, "loss": 0.2367, "lr": 8.522202611102311e-06, "epoch": 6.521874030406454, "percentage": 32.61, "elapsed_time": "0:38:44", "remaining_time": "1:20:03", "throughput": 5509.95, "total_tokens": 12806784} {"current_steps": 21025, "total_steps": 64460, "loss": 0.2301, "lr": 8.521241599155973e-06, "epoch": 6.5234253800806705, "percentage": 32.62, "elapsed_time": "0:38:44", "remaining_time": "1:20:02", "throughput": 5510.17, "total_tokens": 12810720} {"current_steps": 21030, "total_steps": 64460, "loss": 0.23, "lr": 8.520280329060928e-06, "epoch": 6.524976729754886, "percentage": 32.62, "elapsed_time": "0:38:45", "remaining_time": "1:20:02", "throughput": 5510.17, "total_tokens": 12813440} {"current_steps": 21035, "total_steps": 64460, "loss": 0.2336, "lr": 8.51931880088765e-06, "epoch": 6.526528079429103, "percentage": 32.63, "elapsed_time": "0:38:46", "remaining_time": "1:20:01", "throughput": 5510.55, "total_tokens": 12817856} {"current_steps": 21040, "total_steps": 64460, "loss": 0.2289, "lr": 8.51835701470663e-06, "epoch": 6.52807942910332, "percentage": 32.64, "elapsed_time": "0:38:46", "remaining_time": "1:20:01", "throughput": 5510.44, "total_tokens": 12820192} {"current_steps": 21045, "total_steps": 64460, "loss": 0.2304, "lr": 8.517394970588375e-06, "epoch": 6.529630778777537, "percentage": 32.65, "elapsed_time": "0:38:47", "remaining_time": "1:20:00", "throughput": 5510.47, "total_tokens": 12822944} {"current_steps": 21050, "total_steps": 64460, "loss": 0.2316, "lr": 8.516432668603417e-06, "epoch": 6.5311821284517535, "percentage": 32.66, "elapsed_time": "0:38:47", "remaining_time": "1:20:00", "throughput": 5510.89, "total_tokens": 12827680} {"current_steps": 21055, "total_steps": 64460, "loss": 0.2341, "lr": 8.515470108822303e-06, "epoch": 6.532733478125969, "percentage": 32.66, "elapsed_time": "0:38:48", "remaining_time": "1:19:59", "throughput": 5510.99, "total_tokens": 12831040} {"current_steps": 21060, "total_steps": 64460, "loss": 0.2271, "lr": 8.514507291315603e-06, "epoch": 6.534284827800186, "percentage": 32.67, "elapsed_time": "0:38:48", "remaining_time": "1:19:59", "throughput": 5510.98, "total_tokens": 12833856} {"current_steps": 21065, "total_steps": 64460, "loss": 0.2249, "lr": 8.5135442161539e-06, "epoch": 6.535836177474403, "percentage": 32.68, "elapsed_time": "0:38:49", "remaining_time": "1:19:58", "throughput": 5511.2, "total_tokens": 12837216} {"current_steps": 21070, "total_steps": 64460, "loss": 0.2387, "lr": 8.512580883407797e-06, "epoch": 6.537387527148619, "percentage": 32.69, "elapsed_time": "0:38:49", "remaining_time": "1:19:57", "throughput": 5511.12, "total_tokens": 12839840} {"current_steps": 21075, "total_steps": 64460, "loss": 0.2251, "lr": 8.511617293147923e-06, "epoch": 6.538938876822836, "percentage": 32.69, "elapsed_time": "0:38:50", "remaining_time": "1:19:57", "throughput": 5511.02, "total_tokens": 12842240} {"current_steps": 21080, "total_steps": 64460, "loss": 0.2236, "lr": 8.510653445444914e-06, "epoch": 6.540490226497052, "percentage": 32.7, "elapsed_time": "0:38:50", "remaining_time": "1:19:56", "throughput": 5510.98, "total_tokens": 12844800} {"current_steps": 21085, "total_steps": 64460, "loss": 0.2457, "lr": 8.509689340369438e-06, "epoch": 6.542041576171269, "percentage": 32.71, "elapsed_time": "0:38:51", "remaining_time": "1:19:55", "throughput": 5511.0, "total_tokens": 12847520} {"current_steps": 21090, "total_steps": 64460, "loss": 0.2234, "lr": 8.50872497799217e-06, "epoch": 6.543592925845486, "percentage": 32.72, "elapsed_time": "0:38:51", "remaining_time": "1:19:54", "throughput": 5510.94, "total_tokens": 12849888} {"current_steps": 21095, "total_steps": 64460, "loss": 0.2339, "lr": 8.507760358383815e-06, "epoch": 6.545144275519702, "percentage": 32.73, "elapsed_time": "0:38:52", "remaining_time": "1:19:54", "throughput": 5511.31, "total_tokens": 12854816} {"current_steps": 21100, "total_steps": 64460, "loss": 0.2348, "lr": 8.506795481615086e-06, "epoch": 6.546695625193919, "percentage": 32.73, "elapsed_time": "0:38:52", "remaining_time": "1:19:54", "throughput": 5511.33, "total_tokens": 12857568} {"current_steps": 21105, "total_steps": 64460, "loss": 0.226, "lr": 8.50583034775672e-06, "epoch": 6.548246974868135, "percentage": 32.74, "elapsed_time": "0:38:53", "remaining_time": "1:19:53", "throughput": 5511.3, "total_tokens": 12860512} {"current_steps": 21110, "total_steps": 64460, "loss": 0.2332, "lr": 8.504864956879477e-06, "epoch": 6.549798324542352, "percentage": 32.75, "elapsed_time": "0:38:54", "remaining_time": "1:19:53", "throughput": 5511.61, "total_tokens": 12864960} {"current_steps": 21115, "total_steps": 64460, "loss": 0.2406, "lr": 8.503899309054127e-06, "epoch": 6.551349674216569, "percentage": 32.76, "elapsed_time": "0:38:54", "remaining_time": "1:19:52", "throughput": 5511.69, "total_tokens": 12867808} {"current_steps": 21120, "total_steps": 64460, "loss": 0.2299, "lr": 8.502933404351465e-06, "epoch": 6.552901023890785, "percentage": 32.76, "elapsed_time": "0:38:55", "remaining_time": "1:19:51", "throughput": 5511.85, "total_tokens": 12871072} {"current_steps": 21125, "total_steps": 64460, "loss": 0.2367, "lr": 8.501967242842305e-06, "epoch": 6.5544523735650015, "percentage": 32.77, "elapsed_time": "0:38:55", "remaining_time": "1:19:51", "throughput": 5511.99, "total_tokens": 12874720} {"current_steps": 21130, "total_steps": 64460, "loss": 0.2297, "lr": 8.501000824597476e-06, "epoch": 6.556003723239218, "percentage": 32.78, "elapsed_time": "0:38:56", "remaining_time": "1:19:50", "throughput": 5512.08, "total_tokens": 12877728} {"current_steps": 21135, "total_steps": 64460, "loss": 0.2298, "lr": 8.500034149687828e-06, "epoch": 6.557555072913434, "percentage": 32.79, "elapsed_time": "0:38:56", "remaining_time": "1:19:50", "throughput": 5512.07, "total_tokens": 12880576} {"current_steps": 21140, "total_steps": 64460, "loss": 0.229, "lr": 8.499067218184231e-06, "epoch": 6.559106422587651, "percentage": 32.8, "elapsed_time": "0:38:57", "remaining_time": "1:19:50", "throughput": 5512.34, "total_tokens": 12885280} {"current_steps": 21145, "total_steps": 64460, "loss": 0.2355, "lr": 8.498100030157572e-06, "epoch": 6.560657772261868, "percentage": 32.8, "elapsed_time": "0:38:58", "remaining_time": "1:19:49", "throughput": 5512.38, "total_tokens": 12888224} {"current_steps": 21150, "total_steps": 64460, "loss": 0.2275, "lr": 8.497132585678756e-06, "epoch": 6.5622091219360845, "percentage": 32.81, "elapsed_time": "0:38:58", "remaining_time": "1:19:48", "throughput": 5512.44, "total_tokens": 12890976} {"current_steps": 21155, "total_steps": 64460, "loss": 0.2358, "lr": 8.49616488481871e-06, "epoch": 6.563760471610301, "percentage": 32.82, "elapsed_time": "0:38:59", "remaining_time": "1:19:48", "throughput": 5512.47, "total_tokens": 12893856} {"current_steps": 21160, "total_steps": 64460, "loss": 0.2284, "lr": 8.495196927648377e-06, "epoch": 6.565311821284517, "percentage": 32.83, "elapsed_time": "0:38:59", "remaining_time": "1:19:47", "throughput": 5512.54, "total_tokens": 12896768} {"current_steps": 21165, "total_steps": 64460, "loss": 0.2278, "lr": 8.494228714238719e-06, "epoch": 6.566863170958734, "percentage": 32.83, "elapsed_time": "0:38:59", "remaining_time": "1:19:46", "throughput": 5512.49, "total_tokens": 12899200} {"current_steps": 21170, "total_steps": 64460, "loss": 0.2341, "lr": 8.49326024466072e-06, "epoch": 6.568414520632951, "percentage": 32.84, "elapsed_time": "0:39:00", "remaining_time": "1:19:46", "throughput": 5512.52, "total_tokens": 12902048} {"current_steps": 21175, "total_steps": 64460, "loss": 0.2284, "lr": 8.492291518985378e-06, "epoch": 6.5699658703071675, "percentage": 32.85, "elapsed_time": "0:39:01", "remaining_time": "1:19:45", "throughput": 5512.6, "total_tokens": 12905440} {"current_steps": 21180, "total_steps": 64460, "loss": 0.2341, "lr": 8.491322537283713e-06, "epoch": 6.571517219981384, "percentage": 32.86, "elapsed_time": "0:39:01", "remaining_time": "1:19:44", "throughput": 5512.7, "total_tokens": 12908416} {"current_steps": 21185, "total_steps": 64460, "loss": 0.232, "lr": 8.49035329962676e-06, "epoch": 6.5730685696556, "percentage": 32.87, "elapsed_time": "0:39:02", "remaining_time": "1:19:44", "throughput": 5512.85, "total_tokens": 12911712} {"current_steps": 21190, "total_steps": 64460, "loss": 0.229, "lr": 8.489383806085581e-06, "epoch": 6.574619919329817, "percentage": 32.87, "elapsed_time": "0:39:02", "remaining_time": "1:19:43", "throughput": 5513.23, "total_tokens": 12916384} {"current_steps": 21195, "total_steps": 64460, "loss": 0.2434, "lr": 8.488414056731248e-06, "epoch": 6.576171269004034, "percentage": 32.88, "elapsed_time": "0:39:03", "remaining_time": "1:19:43", "throughput": 5513.34, "total_tokens": 12919680} {"current_steps": 21200, "total_steps": 64460, "loss": 0.2287, "lr": 8.487444051634855e-06, "epoch": 6.57772261867825, "percentage": 32.89, "elapsed_time": "0:39:04", "remaining_time": "1:19:43", "throughput": 5513.78, "total_tokens": 12924384} {"current_steps": 21205, "total_steps": 64460, "loss": 0.2359, "lr": 8.486473790867516e-06, "epoch": 6.579273968352466, "percentage": 32.9, "elapsed_time": "0:39:04", "remaining_time": "1:19:42", "throughput": 5514.02, "total_tokens": 12928384} {"current_steps": 21210, "total_steps": 64460, "loss": 0.232, "lr": 8.485503274500363e-06, "epoch": 6.580825318026683, "percentage": 32.9, "elapsed_time": "0:39:05", "remaining_time": "1:19:42", "throughput": 5514.19, "total_tokens": 12932160} {"current_steps": 21215, "total_steps": 64460, "loss": 0.2285, "lr": 8.484532502604544e-06, "epoch": 6.5823766677009, "percentage": 32.91, "elapsed_time": "0:39:05", "remaining_time": "1:19:41", "throughput": 5514.19, "total_tokens": 12935168} {"current_steps": 21220, "total_steps": 64460, "loss": 0.2234, "lr": 8.48356147525123e-06, "epoch": 6.583928017375117, "percentage": 32.92, "elapsed_time": "0:39:06", "remaining_time": "1:19:41", "throughput": 5514.37, "total_tokens": 12938592} {"current_steps": 21225, "total_steps": 64460, "loss": 0.2298, "lr": 8.482590192511609e-06, "epoch": 6.585479367049333, "percentage": 32.93, "elapsed_time": "0:39:06", "remaining_time": "1:19:40", "throughput": 5514.37, "total_tokens": 12941376} {"current_steps": 21230, "total_steps": 64460, "loss": 0.2272, "lr": 8.481618654456884e-06, "epoch": 6.587030716723549, "percentage": 32.94, "elapsed_time": "0:39:07", "remaining_time": "1:19:40", "throughput": 5514.66, "total_tokens": 12946080} {"current_steps": 21235, "total_steps": 64460, "loss": 0.2358, "lr": 8.480646861158286e-06, "epoch": 6.588582066397766, "percentage": 32.94, "elapsed_time": "0:39:08", "remaining_time": "1:19:39", "throughput": 5514.69, "total_tokens": 12948928} {"current_steps": 21240, "total_steps": 64460, "loss": 0.2377, "lr": 8.479674812687056e-06, "epoch": 6.590133416071983, "percentage": 32.95, "elapsed_time": "0:39:08", "remaining_time": "1:19:39", "throughput": 5514.92, "total_tokens": 12953120} {"current_steps": 21245, "total_steps": 64460, "loss": 0.2319, "lr": 8.478702509114457e-06, "epoch": 6.5916847657462, "percentage": 32.96, "elapsed_time": "0:39:09", "remaining_time": "1:19:38", "throughput": 5515.21, "total_tokens": 12957344} {"current_steps": 21250, "total_steps": 64460, "loss": 0.2357, "lr": 8.477729950511769e-06, "epoch": 6.5932361154204155, "percentage": 32.97, "elapsed_time": "0:39:09", "remaining_time": "1:19:38", "throughput": 5515.18, "total_tokens": 12959936} {"current_steps": 21255, "total_steps": 64460, "loss": 0.2327, "lr": 8.476757136950292e-06, "epoch": 6.594787465094632, "percentage": 32.97, "elapsed_time": "0:39:10", "remaining_time": "1:19:37", "throughput": 5515.34, "total_tokens": 12963072} {"current_steps": 21260, "total_steps": 64460, "loss": 0.2316, "lr": 8.475784068501347e-06, "epoch": 6.596338814768849, "percentage": 32.98, "elapsed_time": "0:39:10", "remaining_time": "1:19:37", "throughput": 5515.53, "total_tokens": 12966656} {"current_steps": 21265, "total_steps": 64460, "loss": 0.2305, "lr": 8.47481074523627e-06, "epoch": 6.597890164443065, "percentage": 32.99, "elapsed_time": "0:39:11", "remaining_time": "1:19:36", "throughput": 5515.48, "total_tokens": 12969088} {"current_steps": 21270, "total_steps": 64460, "loss": 0.2259, "lr": 8.473837167226418e-06, "epoch": 6.599441514117282, "percentage": 33.0, "elapsed_time": "0:39:11", "remaining_time": "1:19:35", "throughput": 5515.66, "total_tokens": 12972256} {"current_steps": 21275, "total_steps": 64460, "loss": 0.2294, "lr": 8.472863334543166e-06, "epoch": 6.6009928637914985, "percentage": 33.0, "elapsed_time": "0:39:12", "remaining_time": "1:19:35", "throughput": 5515.6, "total_tokens": 12974912} {"current_steps": 21280, "total_steps": 64460, "loss": 0.2349, "lr": 8.471889247257907e-06, "epoch": 6.602544213465715, "percentage": 33.01, "elapsed_time": "0:39:12", "remaining_time": "1:19:34", "throughput": 5515.71, "total_tokens": 12978304} {"current_steps": 21285, "total_steps": 64460, "loss": 0.2358, "lr": 8.470914905442051e-06, "epoch": 6.604095563139932, "percentage": 33.02, "elapsed_time": "0:39:13", "remaining_time": "1:19:33", "throughput": 5515.9, "total_tokens": 12981856} {"current_steps": 21290, "total_steps": 64460, "loss": 0.2348, "lr": 8.469940309167032e-06, "epoch": 6.605646912814148, "percentage": 33.03, "elapsed_time": "0:39:14", "remaining_time": "1:19:33", "throughput": 5515.94, "total_tokens": 12984768} {"current_steps": 21295, "total_steps": 64460, "loss": 0.2305, "lr": 8.468965458504297e-06, "epoch": 6.607198262488365, "percentage": 33.04, "elapsed_time": "0:39:14", "remaining_time": "1:19:32", "throughput": 5515.88, "total_tokens": 12987328} {"current_steps": 21300, "total_steps": 64460, "loss": 0.2268, "lr": 8.467990353525315e-06, "epoch": 6.6087496121625815, "percentage": 33.04, "elapsed_time": "0:39:15", "remaining_time": "1:19:32", "throughput": 5516.42, "total_tokens": 12993984} {"current_steps": 21305, "total_steps": 64460, "loss": 0.2278, "lr": 8.467014994301574e-06, "epoch": 6.610300961836798, "percentage": 33.05, "elapsed_time": "0:39:15", "remaining_time": "1:19:32", "throughput": 5516.21, "total_tokens": 12996064} {"current_steps": 21310, "total_steps": 64460, "loss": 0.2299, "lr": 8.466039380904579e-06, "epoch": 6.611852311511015, "percentage": 33.06, "elapsed_time": "0:39:16", "remaining_time": "1:19:31", "throughput": 5516.24, "total_tokens": 12999040} {"current_steps": 21315, "total_steps": 64460, "loss": 0.23, "lr": 8.465063513405851e-06, "epoch": 6.613403661185231, "percentage": 33.07, "elapsed_time": "0:39:16", "remaining_time": "1:19:30", "throughput": 5516.26, "total_tokens": 13001760} {"current_steps": 21320, "total_steps": 64460, "loss": 0.2304, "lr": 8.464087391876937e-06, "epoch": 6.614955010859448, "percentage": 33.07, "elapsed_time": "0:39:17", "remaining_time": "1:19:30", "throughput": 5516.43, "total_tokens": 13005056} {"current_steps": 21325, "total_steps": 64460, "loss": 0.2296, "lr": 8.463111016389395e-06, "epoch": 6.6165063605336645, "percentage": 33.08, "elapsed_time": "0:39:17", "remaining_time": "1:19:29", "throughput": 5516.57, "total_tokens": 13008064} {"current_steps": 21330, "total_steps": 64460, "loss": 0.2303, "lr": 8.462134387014806e-06, "epoch": 6.61805771020788, "percentage": 33.09, "elapsed_time": "0:39:18", "remaining_time": "1:19:29", "throughput": 5516.82, "total_tokens": 13011776} {"current_steps": 21335, "total_steps": 64460, "loss": 0.235, "lr": 8.46115750382477e-06, "epoch": 6.619609059882097, "percentage": 33.1, "elapsed_time": "0:39:19", "remaining_time": "1:19:28", "throughput": 5517.0, "total_tokens": 13015008} {"current_steps": 21340, "total_steps": 64460, "loss": 0.2333, "lr": 8.460180366890903e-06, "epoch": 6.621160409556314, "percentage": 33.11, "elapsed_time": "0:39:19", "remaining_time": "1:19:27", "throughput": 5517.22, "total_tokens": 13018720} {"current_steps": 21345, "total_steps": 64460, "loss": 0.2332, "lr": 8.45920297628484e-06, "epoch": 6.622711759230531, "percentage": 33.11, "elapsed_time": "0:39:20", "remaining_time": "1:19:27", "throughput": 5517.16, "total_tokens": 13021280} {"current_steps": 21350, "total_steps": 64460, "loss": 0.2296, "lr": 8.458225332078235e-06, "epoch": 6.6242631089047475, "percentage": 33.12, "elapsed_time": "0:39:20", "remaining_time": "1:19:26", "throughput": 5517.14, "total_tokens": 13023936} {"current_steps": 21355, "total_steps": 64460, "loss": 0.2286, "lr": 8.457247434342762e-06, "epoch": 6.625814458578963, "percentage": 33.13, "elapsed_time": "0:39:21", "remaining_time": "1:19:25", "throughput": 5517.01, "total_tokens": 13026240} {"current_steps": 21360, "total_steps": 64460, "loss": 0.2306, "lr": 8.456269283150111e-06, "epoch": 6.62736580825318, "percentage": 33.14, "elapsed_time": "0:39:21", "remaining_time": "1:19:25", "throughput": 5517.06, "total_tokens": 13029120} {"current_steps": 21365, "total_steps": 64460, "loss": 0.2279, "lr": 8.455290878571995e-06, "epoch": 6.628917157927397, "percentage": 33.14, "elapsed_time": "0:39:22", "remaining_time": "1:19:24", "throughput": 5517.37, "total_tokens": 13033152} {"current_steps": 21370, "total_steps": 64460, "loss": 0.2335, "lr": 8.454312220680139e-06, "epoch": 6.630468507601614, "percentage": 33.15, "elapsed_time": "0:39:22", "remaining_time": "1:19:24", "throughput": 5517.2, "total_tokens": 13035360} {"current_steps": 21375, "total_steps": 64460, "loss": 0.2304, "lr": 8.453333309546294e-06, "epoch": 6.63201985727583, "percentage": 33.16, "elapsed_time": "0:39:23", "remaining_time": "1:19:23", "throughput": 5517.03, "total_tokens": 13037760} {"current_steps": 21380, "total_steps": 64460, "loss": 0.2286, "lr": 8.452354145242223e-06, "epoch": 6.633571206950046, "percentage": 33.17, "elapsed_time": "0:39:23", "remaining_time": "1:19:22", "throughput": 5516.95, "total_tokens": 13040224} {"current_steps": 21385, "total_steps": 64460, "loss": 0.2224, "lr": 8.45137472783971e-06, "epoch": 6.635122556624263, "percentage": 33.18, "elapsed_time": "0:39:24", "remaining_time": "1:19:22", "throughput": 5516.9, "total_tokens": 13042752} {"current_steps": 21390, "total_steps": 64460, "loss": 0.2297, "lr": 8.450395057410561e-06, "epoch": 6.63667390629848, "percentage": 33.18, "elapsed_time": "0:39:24", "remaining_time": "1:19:21", "throughput": 5516.85, "total_tokens": 13045376} {"current_steps": 21395, "total_steps": 64460, "loss": 0.2267, "lr": 8.449415134026594e-06, "epoch": 6.638225255972696, "percentage": 33.19, "elapsed_time": "0:39:25", "remaining_time": "1:19:20", "throughput": 5517.08, "total_tokens": 13048960} {"current_steps": 21400, "total_steps": 64460, "loss": 0.2283, "lr": 8.448434957759652e-06, "epoch": 6.6397766056469125, "percentage": 33.2, "elapsed_time": "0:39:25", "remaining_time": "1:19:20", "throughput": 5517.0, "total_tokens": 13051552} {"current_steps": 21405, "total_steps": 64460, "loss": 0.2323, "lr": 8.447454528681592e-06, "epoch": 6.641327955321129, "percentage": 33.21, "elapsed_time": "0:39:26", "remaining_time": "1:19:19", "throughput": 5517.01, "total_tokens": 13054336} {"current_steps": 21410, "total_steps": 64460, "loss": 0.2289, "lr": 8.44647384686429e-06, "epoch": 6.642879304995346, "percentage": 33.21, "elapsed_time": "0:39:26", "remaining_time": "1:19:19", "throughput": 5517.21, "total_tokens": 13058304} {"current_steps": 21415, "total_steps": 64460, "loss": 0.223, "lr": 8.445492912379642e-06, "epoch": 6.644430654669563, "percentage": 33.22, "elapsed_time": "0:39:27", "remaining_time": "1:19:18", "throughput": 5517.25, "total_tokens": 13061728} {"current_steps": 21420, "total_steps": 64460, "loss": 0.2324, "lr": 8.444511725299563e-06, "epoch": 6.645982004343779, "percentage": 33.23, "elapsed_time": "0:39:27", "remaining_time": "1:19:18", "throughput": 5517.26, "total_tokens": 13064608} {"current_steps": 21425, "total_steps": 64460, "loss": 0.2258, "lr": 8.443530285695987e-06, "epoch": 6.6475333540179955, "percentage": 33.24, "elapsed_time": "0:39:28", "remaining_time": "1:19:17", "throughput": 5517.17, "total_tokens": 13067104} {"current_steps": 21430, "total_steps": 64460, "loss": 0.2316, "lr": 8.442548593640863e-06, "epoch": 6.649084703692212, "percentage": 33.25, "elapsed_time": "0:39:28", "remaining_time": "1:19:16", "throughput": 5517.14, "total_tokens": 13069728} {"current_steps": 21435, "total_steps": 64460, "loss": 0.217, "lr": 8.44156664920616e-06, "epoch": 6.650636053366429, "percentage": 33.25, "elapsed_time": "0:39:29", "remaining_time": "1:19:15", "throughput": 5517.09, "total_tokens": 13072256} {"current_steps": 21440, "total_steps": 64460, "loss": 0.2244, "lr": 8.440584452463868e-06, "epoch": 6.652187403040646, "percentage": 33.26, "elapsed_time": "0:39:29", "remaining_time": "1:19:15", "throughput": 5517.15, "total_tokens": 13075584} {"current_steps": 21445, "total_steps": 64460, "loss": 0.2376, "lr": 8.439602003485993e-06, "epoch": 6.653738752714862, "percentage": 33.27, "elapsed_time": "0:39:30", "remaining_time": "1:19:14", "throughput": 5517.25, "total_tokens": 13078592} {"current_steps": 21450, "total_steps": 64460, "loss": 0.237, "lr": 8.438619302344561e-06, "epoch": 6.6552901023890785, "percentage": 33.28, "elapsed_time": "0:39:30", "remaining_time": "1:19:14", "throughput": 5517.18, "total_tokens": 13081088} {"current_steps": 21455, "total_steps": 64460, "loss": 0.2493, "lr": 8.437636349111614e-06, "epoch": 6.656841452063295, "percentage": 33.28, "elapsed_time": "0:39:31", "remaining_time": "1:19:13", "throughput": 5516.92, "total_tokens": 13083200} {"current_steps": 21460, "total_steps": 64460, "loss": 0.2367, "lr": 8.436653143859215e-06, "epoch": 6.658392801737512, "percentage": 33.29, "elapsed_time": "0:39:32", "remaining_time": "1:19:13", "throughput": 5517.14, "total_tokens": 13087168} {"current_steps": 21465, "total_steps": 64460, "loss": 0.2363, "lr": 8.435669686659444e-06, "epoch": 6.659944151411728, "percentage": 33.3, "elapsed_time": "0:39:32", "remaining_time": "1:19:12", "throughput": 5517.03, "total_tokens": 13089472} {"current_steps": 21470, "total_steps": 64460, "loss": 0.2191, "lr": 8.434685977584402e-06, "epoch": 6.661495501085945, "percentage": 33.31, "elapsed_time": "0:39:33", "remaining_time": "1:19:11", "throughput": 5517.02, "total_tokens": 13092064} {"current_steps": 21475, "total_steps": 64460, "loss": 0.233, "lr": 8.433702016706204e-06, "epoch": 6.6630468507601615, "percentage": 33.32, "elapsed_time": "0:39:33", "remaining_time": "1:19:10", "throughput": 5517.21, "total_tokens": 13095296} {"current_steps": 21480, "total_steps": 64460, "loss": 0.2265, "lr": 8.432717804096987e-06, "epoch": 6.664598200434378, "percentage": 33.32, "elapsed_time": "0:39:34", "remaining_time": "1:19:10", "throughput": 5517.07, "total_tokens": 13097920} {"current_steps": 21485, "total_steps": 64460, "loss": 0.2387, "lr": 8.431733339828906e-06, "epoch": 6.666149550108594, "percentage": 33.33, "elapsed_time": "0:39:34", "remaining_time": "1:19:09", "throughput": 5517.17, "total_tokens": 13100864} {"current_steps": 21490, "total_steps": 64460, "loss": 0.2382, "lr": 8.430748623974134e-06, "epoch": 6.667700899782811, "percentage": 33.34, "elapsed_time": "0:39:35", "remaining_time": "1:19:09", "throughput": 5517.1, "total_tokens": 13103520} {"current_steps": 21495, "total_steps": 64460, "loss": 0.2302, "lr": 8.42976365660486e-06, "epoch": 6.669252249457028, "percentage": 33.35, "elapsed_time": "0:39:35", "remaining_time": "1:19:08", "throughput": 5516.93, "total_tokens": 13105952} {"current_steps": 21500, "total_steps": 64460, "loss": 0.2431, "lr": 8.428778437793296e-06, "epoch": 6.670803599131244, "percentage": 33.35, "elapsed_time": "0:39:36", "remaining_time": "1:19:07", "throughput": 5517.04, "total_tokens": 13109152} {"current_steps": 21505, "total_steps": 64460, "loss": 0.2272, "lr": 8.42779296761167e-06, "epoch": 6.672354948805461, "percentage": 33.36, "elapsed_time": "0:39:36", "remaining_time": "1:19:07", "throughput": 5517.11, "total_tokens": 13112544} {"current_steps": 21510, "total_steps": 64460, "loss": 0.225, "lr": 8.42680724613223e-06, "epoch": 6.673906298479677, "percentage": 33.37, "elapsed_time": "0:39:37", "remaining_time": "1:19:06", "throughput": 5517.09, "total_tokens": 13115136} {"current_steps": 21515, "total_steps": 64460, "loss": 0.2257, "lr": 8.425821273427237e-06, "epoch": 6.675457648153894, "percentage": 33.38, "elapsed_time": "0:39:37", "remaining_time": "1:19:06", "throughput": 5517.32, "total_tokens": 13118560} {"current_steps": 21520, "total_steps": 64460, "loss": 0.242, "lr": 8.424835049568978e-06, "epoch": 6.677008997828111, "percentage": 33.39, "elapsed_time": "0:39:38", "remaining_time": "1:19:05", "throughput": 5517.4, "total_tokens": 13121792} {"current_steps": 21525, "total_steps": 64460, "loss": 0.2332, "lr": 8.423848574629752e-06, "epoch": 6.678560347502327, "percentage": 33.39, "elapsed_time": "0:39:38", "remaining_time": "1:19:04", "throughput": 5517.36, "total_tokens": 13124704} {"current_steps": 21530, "total_steps": 64460, "loss": 0.2333, "lr": 8.422861848681882e-06, "epoch": 6.680111697176543, "percentage": 33.4, "elapsed_time": "0:39:39", "remaining_time": "1:19:04", "throughput": 5517.58, "total_tokens": 13127936} {"current_steps": 21535, "total_steps": 64460, "loss": 0.2316, "lr": 8.421874871797707e-06, "epoch": 6.68166304685076, "percentage": 33.41, "elapsed_time": "0:39:39", "remaining_time": "1:19:03", "throughput": 5517.74, "total_tokens": 13131072} {"current_steps": 21540, "total_steps": 64460, "loss": 0.2276, "lr": 8.420887644049583e-06, "epoch": 6.683214396524977, "percentage": 33.42, "elapsed_time": "0:39:40", "remaining_time": "1:19:03", "throughput": 5518.02, "total_tokens": 13135168} {"current_steps": 21545, "total_steps": 64460, "loss": 0.2362, "lr": 8.419900165509884e-06, "epoch": 6.684765746199194, "percentage": 33.42, "elapsed_time": "0:39:40", "remaining_time": "1:19:02", "throughput": 5517.97, "total_tokens": 13137952} {"current_steps": 21550, "total_steps": 64460, "loss": 0.2337, "lr": 8.418912436251005e-06, "epoch": 6.6863170958734095, "percentage": 33.43, "elapsed_time": "0:39:41", "remaining_time": "1:19:01", "throughput": 5517.9, "total_tokens": 13140384} {"current_steps": 21555, "total_steps": 64460, "loss": 0.231, "lr": 8.417924456345358e-06, "epoch": 6.687868445547626, "percentage": 33.44, "elapsed_time": "0:39:41", "remaining_time": "1:19:01", "throughput": 5517.76, "total_tokens": 13142624} {"current_steps": 21560, "total_steps": 64460, "loss": 0.2316, "lr": 8.416936225865377e-06, "epoch": 6.689419795221843, "percentage": 33.45, "elapsed_time": "0:39:42", "remaining_time": "1:19:00", "throughput": 5517.57, "total_tokens": 13144896} {"current_steps": 21565, "total_steps": 64460, "loss": 0.2284, "lr": 8.415947744883505e-06, "epoch": 6.69097114489606, "percentage": 33.45, "elapsed_time": "0:39:42", "remaining_time": "1:18:59", "throughput": 5517.69, "total_tokens": 13148160} {"current_steps": 21570, "total_steps": 64460, "loss": 0.2237, "lr": 8.414959013472214e-06, "epoch": 6.692522494570277, "percentage": 33.46, "elapsed_time": "0:39:43", "remaining_time": "1:18:59", "throughput": 5517.64, "total_tokens": 13150656} {"current_steps": 21575, "total_steps": 64460, "loss": 0.2315, "lr": 8.413970031703988e-06, "epoch": 6.6940738442444925, "percentage": 33.47, "elapsed_time": "0:39:43", "remaining_time": "1:18:58", "throughput": 5517.44, "total_tokens": 13152736} {"current_steps": 21580, "total_steps": 64460, "loss": 0.2296, "lr": 8.412980799651331e-06, "epoch": 6.695625193918709, "percentage": 33.48, "elapsed_time": "0:39:44", "remaining_time": "1:18:57", "throughput": 5517.61, "total_tokens": 13155872} {"current_steps": 21585, "total_steps": 64460, "loss": 0.2373, "lr": 8.411991317386764e-06, "epoch": 6.697176543592926, "percentage": 33.49, "elapsed_time": "0:39:44", "remaining_time": "1:18:57", "throughput": 5517.5, "total_tokens": 13158464} {"current_steps": 21590, "total_steps": 64460, "loss": 0.2284, "lr": 8.411001584982831e-06, "epoch": 6.698727893267143, "percentage": 33.49, "elapsed_time": "0:39:45", "remaining_time": "1:18:56", "throughput": 5517.56, "total_tokens": 13161568} {"current_steps": 21595, "total_steps": 64460, "loss": 0.2238, "lr": 8.410011602512092e-06, "epoch": 6.700279242941359, "percentage": 33.5, "elapsed_time": "0:39:45", "remaining_time": "1:18:55", "throughput": 5517.63, "total_tokens": 13164480} {"current_steps": 21600, "total_steps": 64460, "loss": 0.2255, "lr": 8.409021370047118e-06, "epoch": 6.7018305926155755, "percentage": 33.51, "elapsed_time": "0:39:46", "remaining_time": "1:18:55", "throughput": 5517.54, "total_tokens": 13167072} {"current_steps": 21605, "total_steps": 64460, "loss": 0.2335, "lr": 8.408030887660512e-06, "epoch": 6.703381942289792, "percentage": 33.52, "elapsed_time": "0:39:46", "remaining_time": "1:18:54", "throughput": 5517.35, "total_tokens": 13169536} {"current_steps": 21610, "total_steps": 64460, "loss": 0.2317, "lr": 8.407040155424881e-06, "epoch": 6.704933291964009, "percentage": 33.52, "elapsed_time": "0:39:47", "remaining_time": "1:18:53", "throughput": 5517.42, "total_tokens": 13172480} {"current_steps": 21615, "total_steps": 64460, "loss": 0.2303, "lr": 8.406049173412865e-06, "epoch": 6.706484641638225, "percentage": 33.53, "elapsed_time": "0:39:47", "remaining_time": "1:18:53", "throughput": 5517.48, "total_tokens": 13175360} {"current_steps": 21620, "total_steps": 64460, "loss": 0.2357, "lr": 8.405057941697108e-06, "epoch": 6.708035991312442, "percentage": 33.54, "elapsed_time": "0:39:48", "remaining_time": "1:18:52", "throughput": 5517.51, "total_tokens": 13178336} {"current_steps": 21625, "total_steps": 64460, "loss": 0.232, "lr": 8.404066460350282e-06, "epoch": 6.709587340986658, "percentage": 33.55, "elapsed_time": "0:39:48", "remaining_time": "1:18:52", "throughput": 5517.51, "total_tokens": 13181184} {"current_steps": 21630, "total_steps": 64460, "loss": 0.2356, "lr": 8.403074729445077e-06, "epoch": 6.711138690660875, "percentage": 33.56, "elapsed_time": "0:39:49", "remaining_time": "1:18:51", "throughput": 5517.27, "total_tokens": 13183392} {"current_steps": 21635, "total_steps": 64460, "loss": 0.2331, "lr": 8.402082749054194e-06, "epoch": 6.712690040335092, "percentage": 33.56, "elapsed_time": "0:39:50", "remaining_time": "1:18:50", "throughput": 5517.32, "total_tokens": 13186432} {"current_steps": 21640, "total_steps": 64460, "loss": 0.2326, "lr": 8.40109051925036e-06, "epoch": 6.714241390009308, "percentage": 33.57, "elapsed_time": "0:39:50", "remaining_time": "1:18:50", "throughput": 5517.61, "total_tokens": 13190336} {"current_steps": 21645, "total_steps": 64460, "loss": 0.2332, "lr": 8.400098040106314e-06, "epoch": 6.715792739683525, "percentage": 33.58, "elapsed_time": "0:39:51", "remaining_time": "1:18:49", "throughput": 5517.63, "total_tokens": 13193120} {"current_steps": 21650, "total_steps": 64460, "loss": 0.227, "lr": 8.39910531169482e-06, "epoch": 6.717344089357741, "percentage": 33.59, "elapsed_time": "0:39:51", "remaining_time": "1:18:48", "throughput": 5517.54, "total_tokens": 13195520} {"current_steps": 21655, "total_steps": 64460, "loss": 0.2275, "lr": 8.398112334088656e-06, "epoch": 6.718895439031958, "percentage": 33.59, "elapsed_time": "0:39:52", "remaining_time": "1:18:48", "throughput": 5517.94, "total_tokens": 13200896} {"current_steps": 21660, "total_steps": 64460, "loss": 0.2284, "lr": 8.397119107360616e-06, "epoch": 6.720446788706174, "percentage": 33.6, "elapsed_time": "0:39:52", "remaining_time": "1:18:48", "throughput": 5517.72, "total_tokens": 13203104} {"current_steps": 21665, "total_steps": 64460, "loss": 0.234, "lr": 8.396125631583518e-06, "epoch": 6.721998138380391, "percentage": 33.61, "elapsed_time": "0:39:53", "remaining_time": "1:18:47", "throughput": 5517.78, "total_tokens": 13206208} {"current_steps": 21670, "total_steps": 64460, "loss": 0.2287, "lr": 8.395131906830195e-06, "epoch": 6.723549488054608, "percentage": 33.62, "elapsed_time": "0:39:53", "remaining_time": "1:18:47", "throughput": 5517.7, "total_tokens": 13208992} {"current_steps": 21675, "total_steps": 64460, "loss": 0.2241, "lr": 8.3941379331735e-06, "epoch": 6.725100837728824, "percentage": 33.63, "elapsed_time": "0:39:54", "remaining_time": "1:18:46", "throughput": 5517.81, "total_tokens": 13212256} {"current_steps": 21680, "total_steps": 64460, "loss": 0.2122, "lr": 8.393143710686303e-06, "epoch": 6.72665218740304, "percentage": 33.63, "elapsed_time": "0:39:54", "remaining_time": "1:18:45", "throughput": 5517.73, "total_tokens": 13214912} {"current_steps": 21685, "total_steps": 64460, "loss": 0.2339, "lr": 8.392149239441489e-06, "epoch": 6.728203537077257, "percentage": 33.64, "elapsed_time": "0:39:55", "remaining_time": "1:18:45", "throughput": 5518.01, "total_tokens": 13219040} {"current_steps": 21690, "total_steps": 64460, "loss": 0.2549, "lr": 8.391154519511965e-06, "epoch": 6.729754886751474, "percentage": 33.65, "elapsed_time": "0:39:56", "remaining_time": "1:18:44", "throughput": 5517.85, "total_tokens": 13221440} {"current_steps": 21695, "total_steps": 64460, "loss": 0.2279, "lr": 8.39015955097066e-06, "epoch": 6.731306236425691, "percentage": 33.66, "elapsed_time": "0:39:56", "remaining_time": "1:18:44", "throughput": 5517.69, "total_tokens": 13224096} {"current_steps": 21700, "total_steps": 64460, "loss": 0.2261, "lr": 8.389164333890516e-06, "epoch": 6.732857586099907, "percentage": 33.66, "elapsed_time": "0:39:57", "remaining_time": "1:18:43", "throughput": 5517.91, "total_tokens": 13227776} {"current_steps": 21705, "total_steps": 64460, "loss": 0.2234, "lr": 8.38816886834449e-06, "epoch": 6.734408935774123, "percentage": 33.67, "elapsed_time": "0:39:57", "remaining_time": "1:18:43", "throughput": 5518.07, "total_tokens": 13231040} {"current_steps": 21710, "total_steps": 64460, "loss": 0.2295, "lr": 8.387173154405564e-06, "epoch": 6.73596028544834, "percentage": 33.68, "elapsed_time": "0:39:58", "remaining_time": "1:18:42", "throughput": 5518.04, "total_tokens": 13233728} {"current_steps": 21715, "total_steps": 64460, "loss": 0.2242, "lr": 8.386177192146737e-06, "epoch": 6.737511635122557, "percentage": 33.69, "elapsed_time": "0:39:58", "remaining_time": "1:18:41", "throughput": 5517.93, "total_tokens": 13236192} {"current_steps": 21720, "total_steps": 64460, "loss": 0.2349, "lr": 8.385180981641024e-06, "epoch": 6.739062984796774, "percentage": 33.7, "elapsed_time": "0:39:59", "remaining_time": "1:18:41", "throughput": 5518.07, "total_tokens": 13239392} {"current_steps": 21725, "total_steps": 64460, "loss": 0.2396, "lr": 8.384184522961457e-06, "epoch": 6.7406143344709895, "percentage": 33.7, "elapsed_time": "0:39:59", "remaining_time": "1:18:41", "throughput": 5518.35, "total_tokens": 13244032} {"current_steps": 21730, "total_steps": 64460, "loss": 0.2374, "lr": 8.38318781618109e-06, "epoch": 6.742165684145206, "percentage": 33.71, "elapsed_time": "0:40:00", "remaining_time": "1:18:40", "throughput": 5518.47, "total_tokens": 13247040} {"current_steps": 21735, "total_steps": 64460, "loss": 0.2321, "lr": 8.382190861372992e-06, "epoch": 6.743717033819423, "percentage": 33.72, "elapsed_time": "0:40:00", "remaining_time": "1:18:39", "throughput": 5518.46, "total_tokens": 13249792} {"current_steps": 21740, "total_steps": 64460, "loss": 0.2315, "lr": 8.381193658610254e-06, "epoch": 6.74526838349364, "percentage": 33.73, "elapsed_time": "0:40:01", "remaining_time": "1:18:39", "throughput": 5518.32, "total_tokens": 13252192} {"current_steps": 21745, "total_steps": 64460, "loss": 0.2231, "lr": 8.380196207965983e-06, "epoch": 6.746819733167856, "percentage": 33.73, "elapsed_time": "0:40:02", "remaining_time": "1:18:38", "throughput": 5518.6, "total_tokens": 13256224} {"current_steps": 21750, "total_steps": 64460, "loss": 0.2283, "lr": 8.3791985095133e-06, "epoch": 6.748371082842072, "percentage": 33.74, "elapsed_time": "0:40:02", "remaining_time": "1:18:38", "throughput": 5518.55, "total_tokens": 13259104} {"current_steps": 21755, "total_steps": 64460, "loss": 0.2327, "lr": 8.378200563325352e-06, "epoch": 6.749922432516289, "percentage": 33.75, "elapsed_time": "0:40:03", "remaining_time": "1:18:37", "throughput": 5518.75, "total_tokens": 13262720} {"current_steps": 21760, "total_steps": 64460, "loss": 0.2378, "lr": 8.377202369475298e-06, "epoch": 6.751473782190506, "percentage": 33.76, "elapsed_time": "0:40:03", "remaining_time": "1:18:36", "throughput": 5518.6, "total_tokens": 13265024} {"current_steps": 21765, "total_steps": 64460, "loss": 0.2329, "lr": 8.376203928036318e-06, "epoch": 6.753025131864723, "percentage": 33.77, "elapsed_time": "0:40:04", "remaining_time": "1:18:36", "throughput": 5518.56, "total_tokens": 13267520} {"current_steps": 21770, "total_steps": 64460, "loss": 0.2337, "lr": 8.375205239081612e-06, "epoch": 6.754576481538939, "percentage": 33.77, "elapsed_time": "0:40:04", "remaining_time": "1:18:35", "throughput": 5518.76, "total_tokens": 13271200} {"current_steps": 21775, "total_steps": 64460, "loss": 0.231, "lr": 8.374206302684391e-06, "epoch": 6.756127831213155, "percentage": 33.78, "elapsed_time": "0:40:05", "remaining_time": "1:18:35", "throughput": 5518.67, "total_tokens": 13273984} {"current_steps": 21780, "total_steps": 64460, "loss": 0.2357, "lr": 8.373207118917892e-06, "epoch": 6.757679180887372, "percentage": 33.79, "elapsed_time": "0:40:05", "remaining_time": "1:18:34", "throughput": 5518.5, "total_tokens": 13276160} {"current_steps": 21785, "total_steps": 64460, "loss": 0.2299, "lr": 8.372207687855367e-06, "epoch": 6.759230530561589, "percentage": 33.8, "elapsed_time": "0:40:06", "remaining_time": "1:18:33", "throughput": 5518.19, "total_tokens": 13278080} {"current_steps": 21790, "total_steps": 64460, "loss": 0.2293, "lr": 8.371208009570084e-06, "epoch": 6.760781880235805, "percentage": 33.8, "elapsed_time": "0:40:06", "remaining_time": "1:18:32", "throughput": 5518.24, "total_tokens": 13280768} {"current_steps": 21795, "total_steps": 64460, "loss": 0.2309, "lr": 8.370208084135336e-06, "epoch": 6.762333229910022, "percentage": 33.81, "elapsed_time": "0:40:07", "remaining_time": "1:18:32", "throughput": 5518.24, "total_tokens": 13283712} {"current_steps": 21800, "total_steps": 64460, "loss": 0.2304, "lr": 8.369207911624424e-06, "epoch": 6.763884579584238, "percentage": 33.82, "elapsed_time": "0:40:07", "remaining_time": "1:18:31", "throughput": 5518.15, "total_tokens": 13286304} {"current_steps": 21805, "total_steps": 64460, "loss": 0.2337, "lr": 8.368207492110674e-06, "epoch": 6.765435929258455, "percentage": 33.83, "elapsed_time": "0:40:08", "remaining_time": "1:18:30", "throughput": 5518.16, "total_tokens": 13289024} {"current_steps": 21810, "total_steps": 64460, "loss": 0.2368, "lr": 8.36720682566743e-06, "epoch": 6.766987278932671, "percentage": 33.83, "elapsed_time": "0:40:08", "remaining_time": "1:18:30", "throughput": 5517.94, "total_tokens": 13291680} {"current_steps": 21815, "total_steps": 64460, "loss": 0.2329, "lr": 8.366205912368053e-06, "epoch": 6.768538628606888, "percentage": 33.84, "elapsed_time": "0:40:09", "remaining_time": "1:18:29", "throughput": 5517.91, "total_tokens": 13294144} {"current_steps": 21820, "total_steps": 64460, "loss": 0.2282, "lr": 8.36520475228592e-06, "epoch": 6.770089978281105, "percentage": 33.85, "elapsed_time": "0:40:09", "remaining_time": "1:18:29", "throughput": 5517.84, "total_tokens": 13296640} {"current_steps": 21825, "total_steps": 64460, "loss": 0.2268, "lr": 8.36420334549443e-06, "epoch": 6.771641327955321, "percentage": 33.86, "elapsed_time": "0:40:10", "remaining_time": "1:18:28", "throughput": 5517.8, "total_tokens": 13299232} {"current_steps": 21830, "total_steps": 64460, "loss": 0.2351, "lr": 8.363201692066995e-06, "epoch": 6.773192677629538, "percentage": 33.87, "elapsed_time": "0:40:10", "remaining_time": "1:18:27", "throughput": 5517.73, "total_tokens": 13301728} {"current_steps": 21835, "total_steps": 64460, "loss": 0.2388, "lr": 8.36219979207705e-06, "epoch": 6.774744027303754, "percentage": 33.87, "elapsed_time": "0:40:11", "remaining_time": "1:18:27", "throughput": 5517.97, "total_tokens": 13305760} {"current_steps": 21840, "total_steps": 64460, "loss": 0.2239, "lr": 8.361197645598045e-06, "epoch": 6.776295376977971, "percentage": 33.88, "elapsed_time": "0:40:11", "remaining_time": "1:18:26", "throughput": 5518.11, "total_tokens": 13309056} {"current_steps": 21845, "total_steps": 64460, "loss": 0.2309, "lr": 8.360195252703452e-06, "epoch": 6.777846726652188, "percentage": 33.89, "elapsed_time": "0:40:12", "remaining_time": "1:18:26", "throughput": 5518.22, "total_tokens": 13312064} {"current_steps": 21850, "total_steps": 64460, "loss": 0.2326, "lr": 8.359192613466756e-06, "epoch": 6.779398076326404, "percentage": 33.9, "elapsed_time": "0:40:12", "remaining_time": "1:18:25", "throughput": 5518.19, "total_tokens": 13314656} {"current_steps": 21855, "total_steps": 64460, "loss": 0.2383, "lr": 8.35818972796146e-06, "epoch": 6.78094942600062, "percentage": 33.9, "elapsed_time": "0:40:13", "remaining_time": "1:18:24", "throughput": 5518.19, "total_tokens": 13317280} {"current_steps": 21860, "total_steps": 64460, "loss": 0.2255, "lr": 8.357186596261093e-06, "epoch": 6.782500775674837, "percentage": 33.91, "elapsed_time": "0:40:13", "remaining_time": "1:18:24", "throughput": 5518.31, "total_tokens": 13320320} {"current_steps": 21865, "total_steps": 64460, "loss": 0.2315, "lr": 8.356183218439194e-06, "epoch": 6.784052125349054, "percentage": 33.92, "elapsed_time": "0:40:14", "remaining_time": "1:18:23", "throughput": 5518.28, "total_tokens": 13322912} {"current_steps": 21870, "total_steps": 64460, "loss": 0.2331, "lr": 8.35517959456932e-06, "epoch": 6.7856034750232705, "percentage": 33.93, "elapsed_time": "0:40:14", "remaining_time": "1:18:22", "throughput": 5518.14, "total_tokens": 13325216} {"current_steps": 21875, "total_steps": 64460, "loss": 0.2346, "lr": 8.354175724725051e-06, "epoch": 6.787154824697486, "percentage": 33.94, "elapsed_time": "0:40:15", "remaining_time": "1:18:22", "throughput": 5517.99, "total_tokens": 13327968} {"current_steps": 21880, "total_steps": 64460, "loss": 0.2299, "lr": 8.353171608979983e-06, "epoch": 6.788706174371703, "percentage": 33.94, "elapsed_time": "0:40:15", "remaining_time": "1:18:21", "throughput": 5517.97, "total_tokens": 13330688} {"current_steps": 21885, "total_steps": 64460, "loss": 0.2281, "lr": 8.352167247407725e-06, "epoch": 6.79025752404592, "percentage": 33.95, "elapsed_time": "0:40:16", "remaining_time": "1:18:20", "throughput": 5518.11, "total_tokens": 13333888} {"current_steps": 21890, "total_steps": 64460, "loss": 0.2364, "lr": 8.351162640081915e-06, "epoch": 6.791808873720137, "percentage": 33.96, "elapsed_time": "0:40:16", "remaining_time": "1:18:20", "throughput": 5518.15, "total_tokens": 13336736} {"current_steps": 21895, "total_steps": 64460, "loss": 0.2296, "lr": 8.3501577870762e-06, "epoch": 6.7933602233943535, "percentage": 33.97, "elapsed_time": "0:40:17", "remaining_time": "1:18:19", "throughput": 5518.28, "total_tokens": 13340000} {"current_steps": 21900, "total_steps": 64460, "loss": 0.2277, "lr": 8.349152688464246e-06, "epoch": 6.794911573068569, "percentage": 33.97, "elapsed_time": "0:40:17", "remaining_time": "1:18:19", "throughput": 5518.35, "total_tokens": 13343168} {"current_steps": 21905, "total_steps": 64460, "loss": 0.2305, "lr": 8.348147344319741e-06, "epoch": 6.796462922742786, "percentage": 33.98, "elapsed_time": "0:40:18", "remaining_time": "1:18:18", "throughput": 5518.46, "total_tokens": 13346816} {"current_steps": 21910, "total_steps": 64460, "loss": 0.2329, "lr": 8.347141754716387e-06, "epoch": 6.798014272417003, "percentage": 33.99, "elapsed_time": "0:40:19", "remaining_time": "1:18:17", "throughput": 5518.42, "total_tokens": 13349536} {"current_steps": 21915, "total_steps": 64460, "loss": 0.237, "lr": 8.346135919727909e-06, "epoch": 6.79956562209122, "percentage": 34.0, "elapsed_time": "0:40:19", "remaining_time": "1:18:17", "throughput": 5518.31, "total_tokens": 13351904} {"current_steps": 21920, "total_steps": 64460, "loss": 0.2337, "lr": 8.345129839428042e-06, "epoch": 6.801116971765436, "percentage": 34.01, "elapsed_time": "0:40:20", "remaining_time": "1:18:16", "throughput": 5518.37, "total_tokens": 13354944} {"current_steps": 21925, "total_steps": 64460, "loss": 0.2311, "lr": 8.344123513890544e-06, "epoch": 6.802668321439652, "percentage": 34.01, "elapsed_time": "0:40:20", "remaining_time": "1:18:15", "throughput": 5518.29, "total_tokens": 13357472} {"current_steps": 21930, "total_steps": 64460, "loss": 0.2336, "lr": 8.343116943189193e-06, "epoch": 6.804219671113869, "percentage": 34.02, "elapsed_time": "0:40:21", "remaining_time": "1:18:15", "throughput": 5518.23, "total_tokens": 13359968} {"current_steps": 21935, "total_steps": 64460, "loss": 0.231, "lr": 8.342110127397782e-06, "epoch": 6.805771020788086, "percentage": 34.03, "elapsed_time": "0:40:21", "remaining_time": "1:18:14", "throughput": 5518.42, "total_tokens": 13363360} {"current_steps": 21940, "total_steps": 64460, "loss": 0.2314, "lr": 8.341103066590122e-06, "epoch": 6.807322370462302, "percentage": 34.04, "elapsed_time": "0:40:22", "remaining_time": "1:18:14", "throughput": 5518.55, "total_tokens": 13366976} {"current_steps": 21945, "total_steps": 64460, "loss": 0.2362, "lr": 8.340095760840043e-06, "epoch": 6.808873720136519, "percentage": 34.04, "elapsed_time": "0:40:22", "remaining_time": "1:18:13", "throughput": 5518.68, "total_tokens": 13370432} {"current_steps": 21950, "total_steps": 64460, "loss": 0.2279, "lr": 8.33908821022139e-06, "epoch": 6.810425069810735, "percentage": 34.05, "elapsed_time": "0:40:23", "remaining_time": "1:18:13", "throughput": 5518.29, "total_tokens": 13372576} {"current_steps": 21955, "total_steps": 64460, "loss": 0.2286, "lr": 8.338080414808034e-06, "epoch": 6.811976419484952, "percentage": 34.06, "elapsed_time": "0:40:23", "remaining_time": "1:18:12", "throughput": 5518.41, "total_tokens": 13375584} {"current_steps": 21960, "total_steps": 64460, "loss": 0.2309, "lr": 8.337072374673852e-06, "epoch": 6.813527769159169, "percentage": 34.07, "elapsed_time": "0:40:24", "remaining_time": "1:18:11", "throughput": 5518.46, "total_tokens": 13378432} {"current_steps": 21965, "total_steps": 64460, "loss": 0.2317, "lr": 8.33606408989275e-06, "epoch": 6.815079118833385, "percentage": 34.08, "elapsed_time": "0:40:24", "remaining_time": "1:18:11", "throughput": 5518.38, "total_tokens": 13380896} {"current_steps": 21970, "total_steps": 64460, "loss": 0.2321, "lr": 8.335055560538645e-06, "epoch": 6.816630468507602, "percentage": 34.08, "elapsed_time": "0:40:25", "remaining_time": "1:18:10", "throughput": 5518.35, "total_tokens": 13383424} {"current_steps": 21975, "total_steps": 64460, "loss": 0.2306, "lr": 8.334046786685473e-06, "epoch": 6.818181818181818, "percentage": 34.09, "elapsed_time": "0:40:25", "remaining_time": "1:18:09", "throughput": 5518.25, "total_tokens": 13385856} {"current_steps": 21980, "total_steps": 64460, "loss": 0.2291, "lr": 8.333037768407191e-06, "epoch": 6.819733167856035, "percentage": 34.1, "elapsed_time": "0:40:26", "remaining_time": "1:18:09", "throughput": 5518.48, "total_tokens": 13389280} {"current_steps": 21985, "total_steps": 64460, "loss": 0.2289, "lr": 8.332028505777773e-06, "epoch": 6.821284517530251, "percentage": 34.11, "elapsed_time": "0:40:26", "remaining_time": "1:18:08", "throughput": 5518.49, "total_tokens": 13392352} {"current_steps": 21990, "total_steps": 64460, "loss": 0.2322, "lr": 8.331018998871207e-06, "epoch": 6.822835867204468, "percentage": 34.11, "elapsed_time": "0:40:27", "remaining_time": "1:18:08", "throughput": 5518.6, "total_tokens": 13395648} {"current_steps": 21995, "total_steps": 64460, "loss": 0.2338, "lr": 8.330009247761504e-06, "epoch": 6.8243872168786845, "percentage": 34.12, "elapsed_time": "0:40:27", "remaining_time": "1:18:07", "throughput": 5518.68, "total_tokens": 13398656} {"current_steps": 22000, "total_steps": 64460, "loss": 0.2279, "lr": 8.32899925252269e-06, "epoch": 6.825938566552901, "percentage": 34.13, "elapsed_time": "0:40:28", "remaining_time": "1:18:06", "throughput": 5518.99, "total_tokens": 13402784} {"current_steps": 22005, "total_steps": 64460, "loss": 0.2336, "lr": 8.327989013228807e-06, "epoch": 6.827489916227117, "percentage": 34.14, "elapsed_time": "0:40:29", "remaining_time": "1:18:06", "throughput": 5519.11, "total_tokens": 13405920} {"current_steps": 22010, "total_steps": 64460, "loss": 0.2361, "lr": 8.326978529953924e-06, "epoch": 6.829041265901334, "percentage": 34.15, "elapsed_time": "0:40:29", "remaining_time": "1:18:05", "throughput": 5519.12, "total_tokens": 13408544} {"current_steps": 22015, "total_steps": 64460, "loss": 0.2311, "lr": 8.325967802772114e-06, "epoch": 6.830592615575551, "percentage": 34.15, "elapsed_time": "0:40:29", "remaining_time": "1:18:04", "throughput": 5519.1, "total_tokens": 13411200} {"current_steps": 22020, "total_steps": 64460, "loss": 0.2321, "lr": 8.324956831757481e-06, "epoch": 6.8321439652497675, "percentage": 34.16, "elapsed_time": "0:40:30", "remaining_time": "1:18:04", "throughput": 5519.13, "total_tokens": 13414176} {"current_steps": 22025, "total_steps": 64460, "loss": 0.2321, "lr": 8.323945616984138e-06, "epoch": 6.833695314923984, "percentage": 34.17, "elapsed_time": "0:40:30", "remaining_time": "1:18:03", "throughput": 5519.16, "total_tokens": 13416832} {"current_steps": 22030, "total_steps": 64460, "loss": 0.2274, "lr": 8.32293415852622e-06, "epoch": 6.8352466645982, "percentage": 34.18, "elapsed_time": "0:40:31", "remaining_time": "1:18:03", "throughput": 5519.33, "total_tokens": 13420608} {"current_steps": 22035, "total_steps": 64460, "loss": 0.2316, "lr": 8.321922456457879e-06, "epoch": 6.836798014272417, "percentage": 34.18, "elapsed_time": "0:40:32", "remaining_time": "1:18:02", "throughput": 5519.44, "total_tokens": 13423616} {"current_steps": 22040, "total_steps": 64460, "loss": 0.2311, "lr": 8.320910510853285e-06, "epoch": 6.838349363946634, "percentage": 34.19, "elapsed_time": "0:40:32", "remaining_time": "1:18:01", "throughput": 5519.46, "total_tokens": 13426208} {"current_steps": 22045, "total_steps": 64460, "loss": 0.2333, "lr": 8.319898321786623e-06, "epoch": 6.8399007136208505, "percentage": 34.2, "elapsed_time": "0:40:33", "remaining_time": "1:18:01", "throughput": 5519.47, "total_tokens": 13429280} {"current_steps": 22050, "total_steps": 64460, "loss": 0.2301, "lr": 8.318885889332102e-06, "epoch": 6.841452063295066, "percentage": 34.21, "elapsed_time": "0:40:33", "remaining_time": "1:18:00", "throughput": 5519.29, "total_tokens": 13431488} {"current_steps": 22055, "total_steps": 64460, "loss": 0.2375, "lr": 8.317873213563943e-06, "epoch": 6.843003412969283, "percentage": 34.22, "elapsed_time": "0:40:34", "remaining_time": "1:18:00", "throughput": 5519.37, "total_tokens": 13435008} {"current_steps": 22060, "total_steps": 64460, "loss": 0.2337, "lr": 8.316860294556389e-06, "epoch": 6.8445547626435, "percentage": 34.22, "elapsed_time": "0:40:34", "remaining_time": "1:18:00", "throughput": 5519.79, "total_tokens": 13440448} {"current_steps": 22065, "total_steps": 64460, "loss": 0.2322, "lr": 8.315847132383697e-06, "epoch": 6.846106112317717, "percentage": 34.23, "elapsed_time": "0:40:35", "remaining_time": "1:17:59", "throughput": 5519.71, "total_tokens": 13442944} {"current_steps": 22070, "total_steps": 64460, "loss": 0.2295, "lr": 8.314833727120147e-06, "epoch": 6.847657461991933, "percentage": 34.24, "elapsed_time": "0:40:35", "remaining_time": "1:17:58", "throughput": 5519.83, "total_tokens": 13445984} {"current_steps": 22075, "total_steps": 64460, "loss": 0.2326, "lr": 8.313820078840029e-06, "epoch": 6.849208811666149, "percentage": 34.25, "elapsed_time": "0:40:36", "remaining_time": "1:17:58", "throughput": 5519.71, "total_tokens": 13448480} {"current_steps": 22080, "total_steps": 64460, "loss": 0.2321, "lr": 8.312806187617656e-06, "epoch": 6.850760161340366, "percentage": 34.25, "elapsed_time": "0:40:37", "remaining_time": "1:17:58", "throughput": 5519.98, "total_tokens": 13454720} {"current_steps": 22085, "total_steps": 64460, "loss": 0.2311, "lr": 8.311792053527363e-06, "epoch": 6.852311511014583, "percentage": 34.26, "elapsed_time": "0:40:37", "remaining_time": "1:17:57", "throughput": 5520.05, "total_tokens": 13457632} {"current_steps": 22090, "total_steps": 64460, "loss": 0.229, "lr": 8.310777676643494e-06, "epoch": 6.8538628606888, "percentage": 34.27, "elapsed_time": "0:40:38", "remaining_time": "1:17:57", "throughput": 5520.02, "total_tokens": 13460160} {"current_steps": 22095, "total_steps": 64460, "loss": 0.2306, "lr": 8.309763057040417e-06, "epoch": 6.855414210363016, "percentage": 34.28, "elapsed_time": "0:40:38", "remaining_time": "1:17:56", "throughput": 5520.11, "total_tokens": 13463296} {"current_steps": 22100, "total_steps": 64460, "loss": 0.2326, "lr": 8.308748194792513e-06, "epoch": 6.856965560037232, "percentage": 34.28, "elapsed_time": "0:40:39", "remaining_time": "1:17:56", "throughput": 5520.25, "total_tokens": 13466976} {"current_steps": 22105, "total_steps": 64460, "loss": 0.2292, "lr": 8.307733089974185e-06, "epoch": 6.858516909711449, "percentage": 34.29, "elapsed_time": "0:40:40", "remaining_time": "1:17:55", "throughput": 5520.31, "total_tokens": 13469888} {"current_steps": 22110, "total_steps": 64460, "loss": 0.23, "lr": 8.306717742659853e-06, "epoch": 6.860068259385666, "percentage": 34.3, "elapsed_time": "0:40:40", "remaining_time": "1:17:54", "throughput": 5520.06, "total_tokens": 13471936} {"current_steps": 22115, "total_steps": 64460, "loss": 0.2279, "lr": 8.305702152923951e-06, "epoch": 6.861619609059882, "percentage": 34.31, "elapsed_time": "0:40:41", "remaining_time": "1:17:54", "throughput": 5520.15, "total_tokens": 13474976} {"current_steps": 22120, "total_steps": 64460, "loss": 0.2289, "lr": 8.304686320840937e-06, "epoch": 6.8631709587340985, "percentage": 34.32, "elapsed_time": "0:40:41", "remaining_time": "1:17:53", "throughput": 5520.26, "total_tokens": 13478080} {"current_steps": 22125, "total_steps": 64460, "loss": 0.2331, "lr": 8.303670246485284e-06, "epoch": 6.864722308408315, "percentage": 34.32, "elapsed_time": "0:40:42", "remaining_time": "1:17:52", "throughput": 5520.34, "total_tokens": 13480960} {"current_steps": 22130, "total_steps": 64460, "loss": 0.2281, "lr": 8.30265392993148e-06, "epoch": 6.866273658082532, "percentage": 34.33, "elapsed_time": "0:40:42", "remaining_time": "1:17:52", "throughput": 5520.34, "total_tokens": 13483744} {"current_steps": 22135, "total_steps": 64460, "loss": 0.23, "lr": 8.301637371254032e-06, "epoch": 6.867825007756748, "percentage": 34.34, "elapsed_time": "0:40:43", "remaining_time": "1:17:51", "throughput": 5520.51, "total_tokens": 13486912} {"current_steps": 22140, "total_steps": 64460, "loss": 0.2354, "lr": 8.300620570527469e-06, "epoch": 6.869376357430965, "percentage": 34.35, "elapsed_time": "0:40:43", "remaining_time": "1:17:50", "throughput": 5520.54, "total_tokens": 13489984} {"current_steps": 22145, "total_steps": 64460, "loss": 0.2349, "lr": 8.299603527826332e-06, "epoch": 6.8709277071051815, "percentage": 34.35, "elapsed_time": "0:40:44", "remaining_time": "1:17:50", "throughput": 5520.24, "total_tokens": 13491872} {"current_steps": 22150, "total_steps": 64460, "loss": 0.2276, "lr": 8.298586243225183e-06, "epoch": 6.872479056779398, "percentage": 34.36, "elapsed_time": "0:40:44", "remaining_time": "1:17:49", "throughput": 5520.09, "total_tokens": 13494208} {"current_steps": 22155, "total_steps": 64460, "loss": 0.2386, "lr": 8.297568716798602e-06, "epoch": 6.874030406453615, "percentage": 34.37, "elapsed_time": "0:40:45", "remaining_time": "1:17:48", "throughput": 5520.15, "total_tokens": 13497152} {"current_steps": 22160, "total_steps": 64460, "loss": 0.2277, "lr": 8.296550948621184e-06, "epoch": 6.875581756127831, "percentage": 34.38, "elapsed_time": "0:40:45", "remaining_time": "1:17:48", "throughput": 5520.13, "total_tokens": 13499904} {"current_steps": 22165, "total_steps": 64460, "loss": 0.2371, "lr": 8.295532938767547e-06, "epoch": 6.877133105802048, "percentage": 34.39, "elapsed_time": "0:40:46", "remaining_time": "1:17:47", "throughput": 5520.43, "total_tokens": 13504096} {"current_steps": 22170, "total_steps": 64460, "loss": 0.2358, "lr": 8.294514687312318e-06, "epoch": 6.8786844554762645, "percentage": 34.39, "elapsed_time": "0:40:46", "remaining_time": "1:17:47", "throughput": 5520.44, "total_tokens": 13506784} {"current_steps": 22175, "total_steps": 64460, "loss": 0.2284, "lr": 8.293496194330151e-06, "epoch": 6.880235805150481, "percentage": 34.4, "elapsed_time": "0:40:47", "remaining_time": "1:17:46", "throughput": 5520.74, "total_tokens": 13510688} {"current_steps": 22180, "total_steps": 64460, "loss": 0.2369, "lr": 8.292477459895711e-06, "epoch": 6.881787154824697, "percentage": 34.41, "elapsed_time": "0:40:47", "remaining_time": "1:17:46", "throughput": 5520.92, "total_tokens": 13513984} {"current_steps": 22185, "total_steps": 64460, "loss": 0.2321, "lr": 8.291458484083685e-06, "epoch": 6.883338504498914, "percentage": 34.42, "elapsed_time": "0:40:48", "remaining_time": "1:17:45", "throughput": 5520.92, "total_tokens": 13516960} {"current_steps": 22190, "total_steps": 64460, "loss": 0.2337, "lr": 8.290439266968776e-06, "epoch": 6.884889854173131, "percentage": 34.42, "elapsed_time": "0:40:48", "remaining_time": "1:17:44", "throughput": 5521.14, "total_tokens": 13520576} {"current_steps": 22195, "total_steps": 64460, "loss": 0.2345, "lr": 8.289419808625705e-06, "epoch": 6.8864412038473475, "percentage": 34.43, "elapsed_time": "0:40:49", "remaining_time": "1:17:44", "throughput": 5521.34, "total_tokens": 13524000} {"current_steps": 22200, "total_steps": 64460, "loss": 0.2348, "lr": 8.288400109129206e-06, "epoch": 6.887992553521563, "percentage": 34.44, "elapsed_time": "0:40:49", "remaining_time": "1:17:43", "throughput": 5521.5, "total_tokens": 13527392} {"current_steps": 22205, "total_steps": 64460, "loss": 0.2288, "lr": 8.28738016855404e-06, "epoch": 6.88954390319578, "percentage": 34.45, "elapsed_time": "0:40:50", "remaining_time": "1:17:43", "throughput": 5521.47, "total_tokens": 13530016} {"current_steps": 22210, "total_steps": 64460, "loss": 0.2342, "lr": 8.286359986974981e-06, "epoch": 6.891095252869997, "percentage": 34.46, "elapsed_time": "0:40:50", "remaining_time": "1:17:42", "throughput": 5521.63, "total_tokens": 13533376} {"current_steps": 22215, "total_steps": 64460, "loss": 0.2363, "lr": 8.285339564466817e-06, "epoch": 6.892646602544214, "percentage": 34.46, "elapsed_time": "0:40:51", "remaining_time": "1:17:42", "throughput": 5521.73, "total_tokens": 13536992} {"current_steps": 22220, "total_steps": 64460, "loss": 0.233, "lr": 8.28431890110436e-06, "epoch": 6.8941979522184305, "percentage": 34.47, "elapsed_time": "0:40:52", "remaining_time": "1:17:41", "throughput": 5521.86, "total_tokens": 13539968} {"current_steps": 22225, "total_steps": 64460, "loss": 0.2315, "lr": 8.283297996962433e-06, "epoch": 6.895749301892646, "percentage": 34.48, "elapsed_time": "0:40:52", "remaining_time": "1:17:40", "throughput": 5522.22, "total_tokens": 13544160} {"current_steps": 22230, "total_steps": 64460, "loss": 0.231, "lr": 8.282276852115885e-06, "epoch": 6.897300651566863, "percentage": 34.49, "elapsed_time": "0:40:53", "remaining_time": "1:17:40", "throughput": 5522.54, "total_tokens": 13548096} {"current_steps": 22235, "total_steps": 64460, "loss": 0.2315, "lr": 8.281255466639575e-06, "epoch": 6.89885200124108, "percentage": 34.49, "elapsed_time": "0:40:53", "remaining_time": "1:17:39", "throughput": 5522.68, "total_tokens": 13551136} {"current_steps": 22240, "total_steps": 64460, "loss": 0.2336, "lr": 8.280233840608383e-06, "epoch": 6.900403350915297, "percentage": 34.5, "elapsed_time": "0:40:54", "remaining_time": "1:17:39", "throughput": 5522.88, "total_tokens": 13555072} {"current_steps": 22245, "total_steps": 64460, "loss": 0.23, "lr": 8.279211974097207e-06, "epoch": 6.9019547005895125, "percentage": 34.51, "elapsed_time": "0:40:54", "remaining_time": "1:17:38", "throughput": 5523.09, "total_tokens": 13558880} {"current_steps": 22250, "total_steps": 64460, "loss": 0.2311, "lr": 8.278189867180964e-06, "epoch": 6.903506050263729, "percentage": 34.52, "elapsed_time": "0:40:55", "remaining_time": "1:17:38", "throughput": 5523.19, "total_tokens": 13561856} {"current_steps": 22255, "total_steps": 64460, "loss": 0.2354, "lr": 8.277167519934582e-06, "epoch": 6.905057399937946, "percentage": 34.53, "elapsed_time": "0:40:55", "remaining_time": "1:17:37", "throughput": 5523.18, "total_tokens": 13564320} {"current_steps": 22260, "total_steps": 64460, "loss": 0.2296, "lr": 8.276144932433012e-06, "epoch": 6.906608749612163, "percentage": 34.53, "elapsed_time": "0:40:56", "remaining_time": "1:17:36", "throughput": 5523.27, "total_tokens": 13567264} {"current_steps": 22265, "total_steps": 64460, "loss": 0.2288, "lr": 8.275122104751225e-06, "epoch": 6.908160099286379, "percentage": 34.54, "elapsed_time": "0:40:57", "remaining_time": "1:17:36", "throughput": 5523.46, "total_tokens": 13571648} {"current_steps": 22270, "total_steps": 64460, "loss": 0.2359, "lr": 8.274099036964203e-06, "epoch": 6.9097114489605955, "percentage": 34.55, "elapsed_time": "0:40:57", "remaining_time": "1:17:36", "throughput": 5523.77, "total_tokens": 13575744} {"current_steps": 22275, "total_steps": 64460, "loss": 0.2275, "lr": 8.273075729146951e-06, "epoch": 6.911262798634812, "percentage": 34.56, "elapsed_time": "0:40:58", "remaining_time": "1:17:35", "throughput": 5523.86, "total_tokens": 13578560} {"current_steps": 22280, "total_steps": 64460, "loss": 0.2298, "lr": 8.272052181374491e-06, "epoch": 6.912814148309029, "percentage": 34.56, "elapsed_time": "0:40:58", "remaining_time": "1:17:34", "throughput": 5524.05, "total_tokens": 13582176} {"current_steps": 22285, "total_steps": 64460, "loss": 0.2333, "lr": 8.271028393721857e-06, "epoch": 6.914365497983246, "percentage": 34.57, "elapsed_time": "0:40:59", "remaining_time": "1:17:34", "throughput": 5523.97, "total_tokens": 13585664} {"current_steps": 22290, "total_steps": 64460, "loss": 0.2318, "lr": 8.270004366264107e-06, "epoch": 6.915916847657462, "percentage": 34.58, "elapsed_time": "0:40:59", "remaining_time": "1:17:33", "throughput": 5523.97, "total_tokens": 13588320} {"current_steps": 22295, "total_steps": 64460, "loss": 0.2184, "lr": 8.268980099076314e-06, "epoch": 6.9174681973316785, "percentage": 34.59, "elapsed_time": "0:41:00", "remaining_time": "1:17:33", "throughput": 5524.23, "total_tokens": 13591904} {"current_steps": 22300, "total_steps": 64460, "loss": 0.2358, "lr": 8.26795559223357e-06, "epoch": 6.919019547005895, "percentage": 34.6, "elapsed_time": "0:41:01", "remaining_time": "1:17:33", "throughput": 5524.64, "total_tokens": 13596960} {"current_steps": 22305, "total_steps": 64460, "loss": 0.239, "lr": 8.266930845810983e-06, "epoch": 6.920570896680112, "percentage": 34.6, "elapsed_time": "0:41:01", "remaining_time": "1:17:32", "throughput": 5524.94, "total_tokens": 13600928} {"current_steps": 22310, "total_steps": 64460, "loss": 0.2315, "lr": 8.265905859883679e-06, "epoch": 6.922122246354328, "percentage": 34.61, "elapsed_time": "0:41:02", "remaining_time": "1:17:31", "throughput": 5524.98, "total_tokens": 13603808} {"current_steps": 22315, "total_steps": 64460, "loss": 0.228, "lr": 8.2648806345268e-06, "epoch": 6.923673596028545, "percentage": 34.62, "elapsed_time": "0:41:02", "remaining_time": "1:17:31", "throughput": 5525.17, "total_tokens": 13607072} {"current_steps": 22320, "total_steps": 64460, "loss": 0.2324, "lr": 8.26385516981551e-06, "epoch": 6.9252249457027615, "percentage": 34.63, "elapsed_time": "0:41:03", "remaining_time": "1:17:30", "throughput": 5525.06, "total_tokens": 13609504} {"current_steps": 22325, "total_steps": 64460, "loss": 0.2331, "lr": 8.262829465824986e-06, "epoch": 6.926776295376978, "percentage": 34.63, "elapsed_time": "0:41:03", "remaining_time": "1:17:29", "throughput": 5525.14, "total_tokens": 13612608} {"current_steps": 22330, "total_steps": 64460, "loss": 0.2255, "lr": 8.261803522630424e-06, "epoch": 6.928327645051194, "percentage": 34.64, "elapsed_time": "0:41:04", "remaining_time": "1:17:29", "throughput": 5525.03, "total_tokens": 13615136} {"current_steps": 22335, "total_steps": 64460, "loss": 0.243, "lr": 8.260777340307038e-06, "epoch": 6.929878994725411, "percentage": 34.65, "elapsed_time": "0:41:04", "remaining_time": "1:17:28", "throughput": 5525.05, "total_tokens": 13617792} {"current_steps": 22340, "total_steps": 64460, "loss": 0.2239, "lr": 8.259750918930061e-06, "epoch": 6.931430344399628, "percentage": 34.66, "elapsed_time": "0:41:05", "remaining_time": "1:17:27", "throughput": 5525.14, "total_tokens": 13620640} {"current_steps": 22345, "total_steps": 64460, "loss": 0.2324, "lr": 8.258724258574739e-06, "epoch": 6.9329816940738445, "percentage": 34.66, "elapsed_time": "0:41:05", "remaining_time": "1:17:27", "throughput": 5525.17, "total_tokens": 13623328} {"current_steps": 22350, "total_steps": 64460, "loss": 0.2303, "lr": 8.257697359316339e-06, "epoch": 6.934533043748061, "percentage": 34.67, "elapsed_time": "0:41:06", "remaining_time": "1:17:26", "throughput": 5525.52, "total_tokens": 13627648} {"current_steps": 22355, "total_steps": 64460, "loss": 0.2346, "lr": 8.256670221230147e-06, "epoch": 6.936084393422277, "percentage": 34.68, "elapsed_time": "0:41:06", "remaining_time": "1:17:26", "throughput": 5525.52, "total_tokens": 13630496} {"current_steps": 22360, "total_steps": 64460, "loss": 0.2362, "lr": 8.255642844391462e-06, "epoch": 6.937635743096494, "percentage": 34.69, "elapsed_time": "0:41:07", "remaining_time": "1:17:25", "throughput": 5525.71, "total_tokens": 13633664} {"current_steps": 22365, "total_steps": 64460, "loss": 0.2313, "lr": 8.254615228875605e-06, "epoch": 6.939187092770711, "percentage": 34.7, "elapsed_time": "0:41:07", "remaining_time": "1:17:24", "throughput": 5525.81, "total_tokens": 13636832} {"current_steps": 22370, "total_steps": 64460, "loss": 0.229, "lr": 8.253587374757913e-06, "epoch": 6.940738442444927, "percentage": 34.7, "elapsed_time": "0:41:08", "remaining_time": "1:17:24", "throughput": 5525.74, "total_tokens": 13639200} {"current_steps": 22375, "total_steps": 64460, "loss": 0.2311, "lr": 8.252559282113734e-06, "epoch": 6.942289792119143, "percentage": 34.71, "elapsed_time": "0:41:08", "remaining_time": "1:17:23", "throughput": 5525.53, "total_tokens": 13641312} {"current_steps": 22380, "total_steps": 64460, "loss": 0.2291, "lr": 8.251530951018447e-06, "epoch": 6.94384114179336, "percentage": 34.72, "elapsed_time": "0:41:09", "remaining_time": "1:17:22", "throughput": 5525.49, "total_tokens": 13643840} {"current_steps": 22385, "total_steps": 64460, "loss": 0.2336, "lr": 8.250502381547437e-06, "epoch": 6.945392491467577, "percentage": 34.73, "elapsed_time": "0:41:09", "remaining_time": "1:17:22", "throughput": 5525.49, "total_tokens": 13646656} {"current_steps": 22390, "total_steps": 64460, "loss": 0.2333, "lr": 8.249473573776108e-06, "epoch": 6.946943841141794, "percentage": 34.73, "elapsed_time": "0:41:10", "remaining_time": "1:17:21", "throughput": 5525.64, "total_tokens": 13650464} {"current_steps": 22395, "total_steps": 64460, "loss": 0.2319, "lr": 8.248444527779888e-06, "epoch": 6.9484951908160095, "percentage": 34.74, "elapsed_time": "0:41:10", "remaining_time": "1:17:21", "throughput": 5525.71, "total_tokens": 13653280} {"current_steps": 22400, "total_steps": 64460, "loss": 0.2332, "lr": 8.247415243634219e-06, "epoch": 6.950046540490226, "percentage": 34.75, "elapsed_time": "0:41:11", "remaining_time": "1:17:20", "throughput": 5525.6, "total_tokens": 13655488} {"current_steps": 22405, "total_steps": 64460, "loss": 0.2304, "lr": 8.246385721414555e-06, "epoch": 6.951597890164443, "percentage": 34.76, "elapsed_time": "0:41:11", "remaining_time": "1:17:19", "throughput": 5525.53, "total_tokens": 13657920} {"current_steps": 22410, "total_steps": 64460, "loss": 0.2315, "lr": 8.245355961196376e-06, "epoch": 6.95314923983866, "percentage": 34.77, "elapsed_time": "0:41:12", "remaining_time": "1:17:19", "throughput": 5525.68, "total_tokens": 13661216} {"current_steps": 22415, "total_steps": 64460, "loss": 0.2253, "lr": 8.244325963055173e-06, "epoch": 6.954700589512877, "percentage": 34.77, "elapsed_time": "0:41:12", "remaining_time": "1:17:18", "throughput": 5525.62, "total_tokens": 13663552} {"current_steps": 22420, "total_steps": 64460, "loss": 0.2351, "lr": 8.243295727066459e-06, "epoch": 6.9562519391870925, "percentage": 34.78, "elapsed_time": "0:41:13", "remaining_time": "1:17:17", "throughput": 5525.87, "total_tokens": 13667072} {"current_steps": 22425, "total_steps": 64460, "loss": 0.2305, "lr": 8.242265253305762e-06, "epoch": 6.957803288861309, "percentage": 34.79, "elapsed_time": "0:41:13", "remaining_time": "1:17:17", "throughput": 5525.98, "total_tokens": 13670080} {"current_steps": 22430, "total_steps": 64460, "loss": 0.2325, "lr": 8.241234541848628e-06, "epoch": 6.959354638535526, "percentage": 34.8, "elapsed_time": "0:41:14", "remaining_time": "1:17:16", "throughput": 5526.13, "total_tokens": 13673152} {"current_steps": 22435, "total_steps": 64460, "loss": 0.2335, "lr": 8.240203592770619e-06, "epoch": 6.960905988209743, "percentage": 34.8, "elapsed_time": "0:41:14", "remaining_time": "1:17:15", "throughput": 5526.18, "total_tokens": 13675968} {"current_steps": 22440, "total_steps": 64460, "loss": 0.2263, "lr": 8.239172406147318e-06, "epoch": 6.962457337883959, "percentage": 34.81, "elapsed_time": "0:41:15", "remaining_time": "1:17:15", "throughput": 5526.26, "total_tokens": 13679584} {"current_steps": 22445, "total_steps": 64460, "loss": 0.2361, "lr": 8.238140982054322e-06, "epoch": 6.9640086875581755, "percentage": 34.82, "elapsed_time": "0:41:15", "remaining_time": "1:17:14", "throughput": 5526.44, "total_tokens": 13682880} {"current_steps": 22450, "total_steps": 64460, "loss": 0.2298, "lr": 8.237109320567245e-06, "epoch": 6.965560037232392, "percentage": 34.83, "elapsed_time": "0:41:16", "remaining_time": "1:17:13", "throughput": 5526.32, "total_tokens": 13685024} {"current_steps": 22455, "total_steps": 64460, "loss": 0.2268, "lr": 8.236077421761724e-06, "epoch": 6.967111386906609, "percentage": 34.84, "elapsed_time": "0:41:16", "remaining_time": "1:17:13", "throughput": 5526.52, "total_tokens": 13688544} {"current_steps": 22460, "total_steps": 64460, "loss": 0.2253, "lr": 8.235045285713405e-06, "epoch": 6.968662736580825, "percentage": 34.84, "elapsed_time": "0:41:17", "remaining_time": "1:17:12", "throughput": 5526.44, "total_tokens": 13690816} {"current_steps": 22465, "total_steps": 64460, "loss": 0.225, "lr": 8.23401291249796e-06, "epoch": 6.970214086255042, "percentage": 34.85, "elapsed_time": "0:41:17", "remaining_time": "1:17:11", "throughput": 5526.51, "total_tokens": 13693696} {"current_steps": 22470, "total_steps": 64460, "loss": 0.2347, "lr": 8.232980302191072e-06, "epoch": 6.9717654359292585, "percentage": 34.86, "elapsed_time": "0:41:18", "remaining_time": "1:17:11", "throughput": 5526.84, "total_tokens": 13698848} {"current_steps": 22475, "total_steps": 64460, "loss": 0.2377, "lr": 8.231947454868441e-06, "epoch": 6.973316785603475, "percentage": 34.87, "elapsed_time": "0:41:19", "remaining_time": "1:17:11", "throughput": 5526.77, "total_tokens": 13701152} {"current_steps": 22480, "total_steps": 64460, "loss": 0.2326, "lr": 8.23091437060579e-06, "epoch": 6.974868135277692, "percentage": 34.87, "elapsed_time": "0:41:19", "remaining_time": "1:17:10", "throughput": 5526.56, "total_tokens": 13703328} {"current_steps": 22485, "total_steps": 64460, "loss": 0.2308, "lr": 8.229881049478859e-06, "epoch": 6.976419484951908, "percentage": 34.88, "elapsed_time": "0:41:20", "remaining_time": "1:17:09", "throughput": 5526.8, "total_tokens": 13707104} {"current_steps": 22490, "total_steps": 64460, "loss": 0.233, "lr": 8.2288474915634e-06, "epoch": 6.977970834626125, "percentage": 34.89, "elapsed_time": "0:41:20", "remaining_time": "1:17:09", "throughput": 5526.98, "total_tokens": 13710368} {"current_steps": 22495, "total_steps": 64460, "loss": 0.2341, "lr": 8.22781369693518e-06, "epoch": 6.979522184300341, "percentage": 34.9, "elapsed_time": "0:41:21", "remaining_time": "1:17:08", "throughput": 5527.23, "total_tokens": 13714592} {"current_steps": 22500, "total_steps": 64460, "loss": 0.2316, "lr": 8.226779665669995e-06, "epoch": 6.981073533974558, "percentage": 34.91, "elapsed_time": "0:41:21", "remaining_time": "1:17:08", "throughput": 5527.01, "total_tokens": 13716704} {"current_steps": 22505, "total_steps": 64460, "loss": 0.2248, "lr": 8.22574539784365e-06, "epoch": 6.982624883648774, "percentage": 34.91, "elapsed_time": "0:41:22", "remaining_time": "1:17:07", "throughput": 5527.16, "total_tokens": 13720000} {"current_steps": 22510, "total_steps": 64460, "loss": 0.2268, "lr": 8.22471089353197e-06, "epoch": 6.984176233322991, "percentage": 34.92, "elapsed_time": "0:41:22", "remaining_time": "1:17:06", "throughput": 5527.17, "total_tokens": 13722592} {"current_steps": 22515, "total_steps": 64460, "loss": 0.226, "lr": 8.223676152810793e-06, "epoch": 6.985727582997208, "percentage": 34.93, "elapsed_time": "0:41:23", "remaining_time": "1:17:06", "throughput": 5527.22, "total_tokens": 13725504} {"current_steps": 22520, "total_steps": 64460, "loss": 0.2346, "lr": 8.222641175755983e-06, "epoch": 6.987278932671424, "percentage": 34.94, "elapsed_time": "0:41:23", "remaining_time": "1:17:05", "throughput": 5527.21, "total_tokens": 13728224} {"current_steps": 22525, "total_steps": 64460, "loss": 0.23, "lr": 8.22160596244341e-06, "epoch": 6.98883028234564, "percentage": 34.94, "elapsed_time": "0:41:24", "remaining_time": "1:17:04", "throughput": 5527.19, "total_tokens": 13730752} {"current_steps": 22530, "total_steps": 64460, "loss": 0.2307, "lr": 8.22057051294897e-06, "epoch": 6.990381632019857, "percentage": 34.95, "elapsed_time": "0:41:24", "remaining_time": "1:17:04", "throughput": 5527.29, "total_tokens": 13734272} {"current_steps": 22535, "total_steps": 64460, "loss": 0.2338, "lr": 8.219534827348577e-06, "epoch": 6.991932981694074, "percentage": 34.96, "elapsed_time": "0:41:25", "remaining_time": "1:17:03", "throughput": 5527.41, "total_tokens": 13737440} {"current_steps": 22540, "total_steps": 64460, "loss": 0.2308, "lr": 8.218498905718155e-06, "epoch": 6.993484331368291, "percentage": 34.97, "elapsed_time": "0:41:25", "remaining_time": "1:17:03", "throughput": 5527.51, "total_tokens": 13740256} {"current_steps": 22545, "total_steps": 64460, "loss": 0.2269, "lr": 8.217462748133651e-06, "epoch": 6.995035681042507, "percentage": 34.98, "elapsed_time": "0:41:26", "remaining_time": "1:17:02", "throughput": 5527.76, "total_tokens": 13744224} {"current_steps": 22550, "total_steps": 64460, "loss": 0.2358, "lr": 8.216426354671026e-06, "epoch": 6.996587030716723, "percentage": 34.98, "elapsed_time": "0:41:27", "remaining_time": "1:17:02", "throughput": 5528.02, "total_tokens": 13748448} {"current_steps": 22555, "total_steps": 64460, "loss": 0.2253, "lr": 8.21538972540626e-06, "epoch": 6.99813838039094, "percentage": 34.99, "elapsed_time": "0:41:27", "remaining_time": "1:17:01", "throughput": 5527.98, "total_tokens": 13750912} {"current_steps": 22560, "total_steps": 64460, "loss": 0.2286, "lr": 8.214352860415354e-06, "epoch": 6.999689730065157, "percentage": 35.0, "elapsed_time": "0:41:28", "remaining_time": "1:17:00", "throughput": 5528.2, "total_tokens": 13754240} {"current_steps": 22565, "total_steps": 64460, "loss": 0.238, "lr": 8.21331575977432e-06, "epoch": 7.001241079739374, "percentage": 35.01, "elapsed_time": "0:41:28", "remaining_time": "1:17:00", "throughput": 5527.43, "total_tokens": 13757088} {"current_steps": 22570, "total_steps": 64460, "loss": 0.2264, "lr": 8.212278423559185e-06, "epoch": 7.0027924294135895, "percentage": 35.01, "elapsed_time": "0:41:29", "remaining_time": "1:17:00", "throughput": 5527.76, "total_tokens": 13761792} {"current_steps": 22575, "total_steps": 64460, "loss": 0.2295, "lr": 8.211240851846007e-06, "epoch": 7.004343779087806, "percentage": 35.02, "elapsed_time": "0:41:30", "remaining_time": "1:17:00", "throughput": 5527.7, "total_tokens": 13764512} {"current_steps": 22580, "total_steps": 64460, "loss": 0.2294, "lr": 8.210203044710846e-06, "epoch": 7.005895128762023, "percentage": 35.03, "elapsed_time": "0:41:30", "remaining_time": "1:16:59", "throughput": 5527.61, "total_tokens": 13767552} {"current_steps": 22585, "total_steps": 64460, "loss": 0.2258, "lr": 8.209165002229786e-06, "epoch": 7.00744647843624, "percentage": 35.04, "elapsed_time": "0:41:31", "remaining_time": "1:16:58", "throughput": 5527.62, "total_tokens": 13770240} {"current_steps": 22590, "total_steps": 64460, "loss": 0.2328, "lr": 8.208126724478931e-06, "epoch": 7.008997828110456, "percentage": 35.04, "elapsed_time": "0:41:31", "remaining_time": "1:16:58", "throughput": 5527.74, "total_tokens": 13773824} {"current_steps": 22595, "total_steps": 64460, "loss": 0.2269, "lr": 8.207088211534397e-06, "epoch": 7.0105491777846725, "percentage": 35.05, "elapsed_time": "0:41:32", "remaining_time": "1:16:58", "throughput": 5527.86, "total_tokens": 13777568} {"current_steps": 22600, "total_steps": 64460, "loss": 0.2251, "lr": 8.206049463472319e-06, "epoch": 7.012100527458889, "percentage": 35.06, "elapsed_time": "0:41:32", "remaining_time": "1:16:57", "throughput": 5527.97, "total_tokens": 13780608} {"current_steps": 22605, "total_steps": 64460, "loss": 0.2357, "lr": 8.205010480368852e-06, "epoch": 7.013651877133106, "percentage": 35.07, "elapsed_time": "0:41:33", "remaining_time": "1:16:56", "throughput": 5528.12, "total_tokens": 13784064} {"current_steps": 22610, "total_steps": 64460, "loss": 0.2371, "lr": 8.203971262300161e-06, "epoch": 7.015203226807323, "percentage": 35.08, "elapsed_time": "0:41:34", "remaining_time": "1:16:56", "throughput": 5528.38, "total_tokens": 13788320} {"current_steps": 22615, "total_steps": 64460, "loss": 0.2252, "lr": 8.202931809342436e-06, "epoch": 7.016754576481539, "percentage": 35.08, "elapsed_time": "0:41:34", "remaining_time": "1:16:55", "throughput": 5528.47, "total_tokens": 13791328} {"current_steps": 22620, "total_steps": 64460, "loss": 0.2297, "lr": 8.201892121571881e-06, "epoch": 7.018305926155755, "percentage": 35.09, "elapsed_time": "0:41:35", "remaining_time": "1:16:55", "throughput": 5528.46, "total_tokens": 13793856} {"current_steps": 22625, "total_steps": 64460, "loss": 0.2285, "lr": 8.20085219906472e-06, "epoch": 7.019857275829972, "percentage": 35.1, "elapsed_time": "0:41:35", "remaining_time": "1:16:54", "throughput": 5528.51, "total_tokens": 13796960} {"current_steps": 22630, "total_steps": 64460, "loss": 0.2324, "lr": 8.199812041897186e-06, "epoch": 7.021408625504189, "percentage": 35.11, "elapsed_time": "0:41:36", "remaining_time": "1:16:53", "throughput": 5528.64, "total_tokens": 13800000} {"current_steps": 22635, "total_steps": 64460, "loss": 0.2337, "lr": 8.19877165014554e-06, "epoch": 7.022959975178405, "percentage": 35.11, "elapsed_time": "0:41:36", "remaining_time": "1:16:53", "throughput": 5528.76, "total_tokens": 13803168} {"current_steps": 22640, "total_steps": 64460, "loss": 0.2331, "lr": 8.197731023886052e-06, "epoch": 7.024511324852622, "percentage": 35.12, "elapsed_time": "0:41:37", "remaining_time": "1:16:52", "throughput": 5528.82, "total_tokens": 13806048} {"current_steps": 22645, "total_steps": 64460, "loss": 0.2276, "lr": 8.196690163195014e-06, "epoch": 7.026062674526838, "percentage": 35.13, "elapsed_time": "0:41:37", "remaining_time": "1:16:52", "throughput": 5528.93, "total_tokens": 13809280} {"current_steps": 22650, "total_steps": 64460, "loss": 0.2328, "lr": 8.19564906814873e-06, "epoch": 7.027614024201055, "percentage": 35.14, "elapsed_time": "0:41:38", "remaining_time": "1:16:51", "throughput": 5529.17, "total_tokens": 13813376} {"current_steps": 22655, "total_steps": 64460, "loss": 0.2383, "lr": 8.19460773882353e-06, "epoch": 7.029165373875271, "percentage": 35.15, "elapsed_time": "0:41:38", "remaining_time": "1:16:50", "throughput": 5529.35, "total_tokens": 13816640} {"current_steps": 22660, "total_steps": 64460, "loss": 0.2227, "lr": 8.193566175295751e-06, "epoch": 7.030716723549488, "percentage": 35.15, "elapsed_time": "0:41:39", "remaining_time": "1:16:50", "throughput": 5529.27, "total_tokens": 13819136} {"current_steps": 22665, "total_steps": 64460, "loss": 0.2414, "lr": 8.192524377641756e-06, "epoch": 7.032268073223705, "percentage": 35.16, "elapsed_time": "0:41:39", "remaining_time": "1:16:49", "throughput": 5529.32, "total_tokens": 13822240} {"current_steps": 22670, "total_steps": 64460, "loss": 0.2209, "lr": 8.191482345937915e-06, "epoch": 7.033819422897921, "percentage": 35.17, "elapsed_time": "0:41:40", "remaining_time": "1:16:49", "throughput": 5529.34, "total_tokens": 13824960} {"current_steps": 22675, "total_steps": 64460, "loss": 0.2462, "lr": 8.190440080260629e-06, "epoch": 7.035370772572138, "percentage": 35.18, "elapsed_time": "0:41:40", "remaining_time": "1:16:48", "throughput": 5529.42, "total_tokens": 13827904} {"current_steps": 22680, "total_steps": 64460, "loss": 0.2336, "lr": 8.189397580686305e-06, "epoch": 7.036922122246354, "percentage": 35.18, "elapsed_time": "0:41:41", "remaining_time": "1:16:47", "throughput": 5529.57, "total_tokens": 13831200} {"current_steps": 22685, "total_steps": 64460, "loss": 0.229, "lr": 8.188354847291367e-06, "epoch": 7.038473471920571, "percentage": 35.19, "elapsed_time": "0:41:41", "remaining_time": "1:16:47", "throughput": 5529.81, "total_tokens": 13834880} {"current_steps": 22690, "total_steps": 64460, "loss": 0.2269, "lr": 8.187311880152265e-06, "epoch": 7.040024821594788, "percentage": 35.2, "elapsed_time": "0:41:42", "remaining_time": "1:16:46", "throughput": 5530.0, "total_tokens": 13838784} {"current_steps": 22695, "total_steps": 64460, "loss": 0.2302, "lr": 8.18626867934546e-06, "epoch": 7.041576171269004, "percentage": 35.21, "elapsed_time": "0:41:43", "remaining_time": "1:16:46", "throughput": 5530.36, "total_tokens": 13843584} {"current_steps": 22700, "total_steps": 64460, "loss": 0.2289, "lr": 8.185225244947428e-06, "epoch": 7.04312752094322, "percentage": 35.22, "elapsed_time": "0:41:43", "remaining_time": "1:16:45", "throughput": 5530.41, "total_tokens": 13846496} {"current_steps": 22705, "total_steps": 64460, "loss": 0.2382, "lr": 8.184181577034666e-06, "epoch": 7.044678870617437, "percentage": 35.22, "elapsed_time": "0:41:44", "remaining_time": "1:16:45", "throughput": 5530.52, "total_tokens": 13849504} {"current_steps": 22710, "total_steps": 64460, "loss": 0.2271, "lr": 8.18313767568369e-06, "epoch": 7.046230220291654, "percentage": 35.23, "elapsed_time": "0:41:44", "remaining_time": "1:16:44", "throughput": 5530.54, "total_tokens": 13852224} {"current_steps": 22715, "total_steps": 64460, "loss": 0.2246, "lr": 8.182093540971027e-06, "epoch": 7.047781569965871, "percentage": 35.24, "elapsed_time": "0:41:45", "remaining_time": "1:16:43", "throughput": 5530.57, "total_tokens": 13854848} {"current_steps": 22720, "total_steps": 64460, "loss": 0.2281, "lr": 8.181049172973226e-06, "epoch": 7.0493329196400865, "percentage": 35.25, "elapsed_time": "0:41:45", "remaining_time": "1:16:43", "throughput": 5530.71, "total_tokens": 13857856} {"current_steps": 22725, "total_steps": 64460, "loss": 0.233, "lr": 8.180004571766852e-06, "epoch": 7.050884269314303, "percentage": 35.25, "elapsed_time": "0:41:46", "remaining_time": "1:16:42", "throughput": 5530.77, "total_tokens": 13860800} {"current_steps": 22730, "total_steps": 64460, "loss": 0.2246, "lr": 8.178959737428485e-06, "epoch": 7.05243561898852, "percentage": 35.26, "elapsed_time": "0:41:46", "remaining_time": "1:16:41", "throughput": 5530.98, "total_tokens": 13864288} {"current_steps": 22735, "total_steps": 64460, "loss": 0.2281, "lr": 8.177914670034725e-06, "epoch": 7.053986968662737, "percentage": 35.27, "elapsed_time": "0:41:47", "remaining_time": "1:16:41", "throughput": 5531.1, "total_tokens": 13867424} {"current_steps": 22740, "total_steps": 64460, "loss": 0.2342, "lr": 8.17686936966219e-06, "epoch": 7.0555383183369536, "percentage": 35.28, "elapsed_time": "0:41:47", "remaining_time": "1:16:40", "throughput": 5531.29, "total_tokens": 13870848} {"current_steps": 22745, "total_steps": 64460, "loss": 0.2282, "lr": 8.175823836387507e-06, "epoch": 7.057089668011169, "percentage": 35.29, "elapsed_time": "0:41:48", "remaining_time": "1:16:40", "throughput": 5531.5, "total_tokens": 13874816} {"current_steps": 22750, "total_steps": 64460, "loss": 0.236, "lr": 8.174778070287331e-06, "epoch": 7.058641017685386, "percentage": 35.29, "elapsed_time": "0:41:48", "remaining_time": "1:16:39", "throughput": 5531.6, "total_tokens": 13877696} {"current_steps": 22755, "total_steps": 64460, "loss": 0.227, "lr": 8.173732071438327e-06, "epoch": 7.060192367359603, "percentage": 35.3, "elapsed_time": "0:41:49", "remaining_time": "1:16:38", "throughput": 5531.73, "total_tokens": 13880640} {"current_steps": 22760, "total_steps": 64460, "loss": 0.2329, "lr": 8.17268583991718e-06, "epoch": 7.06174371703382, "percentage": 35.31, "elapsed_time": "0:41:49", "remaining_time": "1:16:38", "throughput": 5531.53, "total_tokens": 13882912} {"current_steps": 22765, "total_steps": 64460, "loss": 0.2273, "lr": 8.17163937580059e-06, "epoch": 7.063295066708036, "percentage": 35.32, "elapsed_time": "0:41:50", "remaining_time": "1:16:37", "throughput": 5531.47, "total_tokens": 13885696} {"current_steps": 22770, "total_steps": 64460, "loss": 0.2316, "lr": 8.170592679165277e-06, "epoch": 7.064846416382252, "percentage": 35.32, "elapsed_time": "0:41:50", "remaining_time": "1:16:37", "throughput": 5531.87, "total_tokens": 13890272} {"current_steps": 22775, "total_steps": 64460, "loss": 0.2234, "lr": 8.169545750087975e-06, "epoch": 7.066397766056469, "percentage": 35.33, "elapsed_time": "0:41:51", "remaining_time": "1:16:36", "throughput": 5531.86, "total_tokens": 13892768} {"current_steps": 22780, "total_steps": 64460, "loss": 0.2136, "lr": 8.168498588645436e-06, "epoch": 7.067949115730686, "percentage": 35.34, "elapsed_time": "0:41:51", "remaining_time": "1:16:35", "throughput": 5531.96, "total_tokens": 13895712} {"current_steps": 22785, "total_steps": 64460, "loss": 0.2264, "lr": 8.16745119491443e-06, "epoch": 7.069500465404902, "percentage": 35.35, "elapsed_time": "0:41:52", "remaining_time": "1:16:35", "throughput": 5532.03, "total_tokens": 13898624} {"current_steps": 22790, "total_steps": 64460, "loss": 0.232, "lr": 8.166403568971743e-06, "epoch": 7.071051815079119, "percentage": 35.36, "elapsed_time": "0:41:52", "remaining_time": "1:16:34", "throughput": 5532.22, "total_tokens": 13902336} {"current_steps": 22795, "total_steps": 64460, "loss": 0.2367, "lr": 8.165355710894178e-06, "epoch": 7.072603164753335, "percentage": 35.36, "elapsed_time": "0:41:53", "remaining_time": "1:16:34", "throughput": 5532.32, "total_tokens": 13905280} {"current_steps": 22800, "total_steps": 64460, "loss": 0.2449, "lr": 8.164307620758558e-06, "epoch": 7.074154514427552, "percentage": 35.37, "elapsed_time": "0:41:53", "remaining_time": "1:16:33", "throughput": 5532.41, "total_tokens": 13908288} {"current_steps": 22805, "total_steps": 64460, "loss": 0.2306, "lr": 8.163259298641716e-06, "epoch": 7.075705864101769, "percentage": 35.38, "elapsed_time": "0:41:54", "remaining_time": "1:16:32", "throughput": 5532.35, "total_tokens": 13910752} {"current_steps": 22810, "total_steps": 64460, "loss": 0.2305, "lr": 8.16221074462051e-06, "epoch": 7.077257213775985, "percentage": 35.39, "elapsed_time": "0:41:54", "remaining_time": "1:16:32", "throughput": 5532.26, "total_tokens": 13913024} {"current_steps": 22815, "total_steps": 64460, "loss": 0.2331, "lr": 8.16116195877181e-06, "epoch": 7.078808563450202, "percentage": 35.39, "elapsed_time": "0:41:55", "remaining_time": "1:16:31", "throughput": 5532.31, "total_tokens": 13915776} {"current_steps": 22820, "total_steps": 64460, "loss": 0.2257, "lr": 8.160112941172505e-06, "epoch": 7.080359913124418, "percentage": 35.4, "elapsed_time": "0:41:55", "remaining_time": "1:16:30", "throughput": 5532.42, "total_tokens": 13918848} {"current_steps": 22825, "total_steps": 64460, "loss": 0.2353, "lr": 8.1590636918995e-06, "epoch": 7.081911262798635, "percentage": 35.41, "elapsed_time": "0:41:56", "remaining_time": "1:16:30", "throughput": 5532.54, "total_tokens": 13922464} {"current_steps": 22830, "total_steps": 64460, "loss": 0.2333, "lr": 8.158014211029718e-06, "epoch": 7.083462612472851, "percentage": 35.42, "elapsed_time": "0:41:56", "remaining_time": "1:16:29", "throughput": 5532.57, "total_tokens": 13925408} {"current_steps": 22835, "total_steps": 64460, "loss": 0.235, "lr": 8.156964498640097e-06, "epoch": 7.085013962147068, "percentage": 35.43, "elapsed_time": "0:41:57", "remaining_time": "1:16:28", "throughput": 5532.56, "total_tokens": 13928032} {"current_steps": 22840, "total_steps": 64460, "loss": 0.231, "lr": 8.155914554807593e-06, "epoch": 7.086565311821285, "percentage": 35.43, "elapsed_time": "0:41:57", "remaining_time": "1:16:28", "throughput": 5532.42, "total_tokens": 13930176} {"current_steps": 22845, "total_steps": 64460, "loss": 0.2361, "lr": 8.154864379609183e-06, "epoch": 7.088116661495501, "percentage": 35.44, "elapsed_time": "0:41:58", "remaining_time": "1:16:27", "throughput": 5532.55, "total_tokens": 13933312} {"current_steps": 22850, "total_steps": 64460, "loss": 0.2274, "lr": 8.153813973121854e-06, "epoch": 7.089668011169717, "percentage": 35.45, "elapsed_time": "0:41:58", "remaining_time": "1:16:26", "throughput": 5532.32, "total_tokens": 13935392} {"current_steps": 22855, "total_steps": 64460, "loss": 0.228, "lr": 8.152763335422612e-06, "epoch": 7.091219360843934, "percentage": 35.46, "elapsed_time": "0:41:59", "remaining_time": "1:16:26", "throughput": 5532.2, "total_tokens": 13937568} {"current_steps": 22860, "total_steps": 64460, "loss": 0.2343, "lr": 8.151712466588487e-06, "epoch": 7.092770710518151, "percentage": 35.46, "elapsed_time": "0:41:59", "remaining_time": "1:16:25", "throughput": 5532.23, "total_tokens": 13940704} {"current_steps": 22865, "total_steps": 64460, "loss": 0.2339, "lr": 8.150661366696514e-06, "epoch": 7.0943220601923676, "percentage": 35.47, "elapsed_time": "0:42:00", "remaining_time": "1:16:24", "throughput": 5532.35, "total_tokens": 13943712} {"current_steps": 22870, "total_steps": 64460, "loss": 0.2313, "lr": 8.149610035823752e-06, "epoch": 7.095873409866584, "percentage": 35.48, "elapsed_time": "0:42:00", "remaining_time": "1:16:24", "throughput": 5532.45, "total_tokens": 13946752} {"current_steps": 22875, "total_steps": 64460, "loss": 0.235, "lr": 8.14855847404728e-06, "epoch": 7.0974247595408, "percentage": 35.49, "elapsed_time": "0:42:01", "remaining_time": "1:16:23", "throughput": 5532.39, "total_tokens": 13949216} {"current_steps": 22880, "total_steps": 64460, "loss": 0.232, "lr": 8.147506681444187e-06, "epoch": 7.098976109215017, "percentage": 35.49, "elapsed_time": "0:42:01", "remaining_time": "1:16:23", "throughput": 5532.58, "total_tokens": 13952928} {"current_steps": 22885, "total_steps": 64460, "loss": 0.2223, "lr": 8.146454658091582e-06, "epoch": 7.100527458889234, "percentage": 35.5, "elapsed_time": "0:42:02", "remaining_time": "1:16:22", "throughput": 5532.39, "total_tokens": 13955072} {"current_steps": 22890, "total_steps": 64460, "loss": 0.2326, "lr": 8.14540240406659e-06, "epoch": 7.1020788085634505, "percentage": 35.51, "elapsed_time": "0:42:02", "remaining_time": "1:16:21", "throughput": 5532.2, "total_tokens": 13957344} {"current_steps": 22895, "total_steps": 64460, "loss": 0.23, "lr": 8.144349919446355e-06, "epoch": 7.103630158237666, "percentage": 35.52, "elapsed_time": "0:42:03", "remaining_time": "1:16:21", "throughput": 5532.27, "total_tokens": 13960544} {"current_steps": 22900, "total_steps": 64460, "loss": 0.225, "lr": 8.143297204308035e-06, "epoch": 7.105181507911883, "percentage": 35.53, "elapsed_time": "0:42:04", "remaining_time": "1:16:20", "throughput": 5532.38, "total_tokens": 13963840} {"current_steps": 22905, "total_steps": 64460, "loss": 0.2293, "lr": 8.14224425872881e-06, "epoch": 7.1067328575861, "percentage": 35.53, "elapsed_time": "0:42:04", "remaining_time": "1:16:20", "throughput": 5532.37, "total_tokens": 13966528} {"current_steps": 22910, "total_steps": 64460, "loss": 0.2268, "lr": 8.141191082785871e-06, "epoch": 7.108284207260317, "percentage": 35.54, "elapsed_time": "0:42:05", "remaining_time": "1:16:19", "throughput": 5532.36, "total_tokens": 13969280} {"current_steps": 22915, "total_steps": 64460, "loss": 0.2352, "lr": 8.140137676556428e-06, "epoch": 7.109835556934533, "percentage": 35.55, "elapsed_time": "0:42:05", "remaining_time": "1:16:18", "throughput": 5532.47, "total_tokens": 13972288} {"current_steps": 22920, "total_steps": 64460, "loss": 0.2315, "lr": 8.139084040117709e-06, "epoch": 7.111386906608749, "percentage": 35.56, "elapsed_time": "0:42:05", "remaining_time": "1:16:18", "throughput": 5532.31, "total_tokens": 13974496} {"current_steps": 22925, "total_steps": 64460, "loss": 0.2253, "lr": 8.138030173546955e-06, "epoch": 7.112938256282966, "percentage": 35.56, "elapsed_time": "0:42:06", "remaining_time": "1:16:17", "throughput": 5532.41, "total_tokens": 13977792} {"current_steps": 22930, "total_steps": 64460, "loss": 0.2399, "lr": 8.136976076921433e-06, "epoch": 7.114489605957183, "percentage": 35.57, "elapsed_time": "0:42:07", "remaining_time": "1:16:16", "throughput": 5532.44, "total_tokens": 13980704} {"current_steps": 22935, "total_steps": 64460, "loss": 0.2249, "lr": 8.135921750318414e-06, "epoch": 7.1160409556314, "percentage": 35.58, "elapsed_time": "0:42:07", "remaining_time": "1:16:16", "throughput": 5532.5, "total_tokens": 13983648} {"current_steps": 22940, "total_steps": 64460, "loss": 0.2331, "lr": 8.134867193815196e-06, "epoch": 7.117592305305616, "percentage": 35.59, "elapsed_time": "0:42:08", "remaining_time": "1:16:15", "throughput": 5532.43, "total_tokens": 13986016} {"current_steps": 22945, "total_steps": 64460, "loss": 0.2302, "lr": 8.133812407489092e-06, "epoch": 7.119143654979832, "percentage": 35.6, "elapsed_time": "0:42:08", "remaining_time": "1:16:14", "throughput": 5532.51, "total_tokens": 13988928} {"current_steps": 22950, "total_steps": 64460, "loss": 0.2315, "lr": 8.132757391417427e-06, "epoch": 7.120695004654049, "percentage": 35.6, "elapsed_time": "0:42:09", "remaining_time": "1:16:14", "throughput": 5532.6, "total_tokens": 13992160} {"current_steps": 22955, "total_steps": 64460, "loss": 0.2243, "lr": 8.13170214567755e-06, "epoch": 7.122246354328266, "percentage": 35.61, "elapsed_time": "0:42:09", "remaining_time": "1:16:13", "throughput": 5532.7, "total_tokens": 13995008} {"current_steps": 22960, "total_steps": 64460, "loss": 0.2339, "lr": 8.13064667034682e-06, "epoch": 7.123797704002482, "percentage": 35.62, "elapsed_time": "0:42:10", "remaining_time": "1:16:12", "throughput": 5532.89, "total_tokens": 13998304} {"current_steps": 22965, "total_steps": 64460, "loss": 0.2262, "lr": 8.129590965502616e-06, "epoch": 7.125349053676699, "percentage": 35.63, "elapsed_time": "0:42:10", "remaining_time": "1:16:12", "throughput": 5533.01, "total_tokens": 14001536} {"current_steps": 22970, "total_steps": 64460, "loss": 0.2316, "lr": 8.128535031222335e-06, "epoch": 7.126900403350915, "percentage": 35.63, "elapsed_time": "0:42:11", "remaining_time": "1:16:11", "throughput": 5532.83, "total_tokens": 14003936} {"current_steps": 22975, "total_steps": 64460, "loss": 0.2272, "lr": 8.127478867583387e-06, "epoch": 7.128451753025132, "percentage": 35.64, "elapsed_time": "0:42:11", "remaining_time": "1:16:11", "throughput": 5532.97, "total_tokens": 14007104} {"current_steps": 22980, "total_steps": 64460, "loss": 0.2403, "lr": 8.126422474663205e-06, "epoch": 7.130003102699348, "percentage": 35.65, "elapsed_time": "0:42:12", "remaining_time": "1:16:10", "throughput": 5533.02, "total_tokens": 14009920} {"current_steps": 22985, "total_steps": 64460, "loss": 0.228, "lr": 8.125365852539235e-06, "epoch": 7.131554452373565, "percentage": 35.66, "elapsed_time": "0:42:12", "remaining_time": "1:16:09", "throughput": 5532.88, "total_tokens": 14012224} {"current_steps": 22990, "total_steps": 64460, "loss": 0.2339, "lr": 8.124309001288934e-06, "epoch": 7.1331058020477816, "percentage": 35.67, "elapsed_time": "0:42:13", "remaining_time": "1:16:09", "throughput": 5533.25, "total_tokens": 14016736} {"current_steps": 22995, "total_steps": 64460, "loss": 0.2351, "lr": 8.12325192098979e-06, "epoch": 7.134657151721998, "percentage": 35.67, "elapsed_time": "0:42:13", "remaining_time": "1:16:08", "throughput": 5533.39, "total_tokens": 14019808} {"current_steps": 23000, "total_steps": 64460, "loss": 0.2239, "lr": 8.122194611719292e-06, "epoch": 7.136208501396215, "percentage": 35.68, "elapsed_time": "0:42:14", "remaining_time": "1:16:08", "throughput": 5533.6, "total_tokens": 14023424} {"current_steps": 23005, "total_steps": 64460, "loss": 0.231, "lr": 8.12113707355496e-06, "epoch": 7.137759851070431, "percentage": 35.69, "elapsed_time": "0:42:14", "remaining_time": "1:16:07", "throughput": 5533.9, "total_tokens": 14027328} {"current_steps": 23010, "total_steps": 64460, "loss": 0.2368, "lr": 8.120079306574317e-06, "epoch": 7.139311200744648, "percentage": 35.7, "elapsed_time": "0:42:15", "remaining_time": "1:16:07", "throughput": 5533.81, "total_tokens": 14030208} {"current_steps": 23015, "total_steps": 64460, "loss": 0.2339, "lr": 8.119021310854916e-06, "epoch": 7.1408625504188645, "percentage": 35.7, "elapsed_time": "0:42:15", "remaining_time": "1:16:06", "throughput": 5533.74, "total_tokens": 14032768} {"current_steps": 23020, "total_steps": 64460, "loss": 0.2347, "lr": 8.117963086474317e-06, "epoch": 7.142413900093081, "percentage": 35.71, "elapsed_time": "0:42:16", "remaining_time": "1:16:05", "throughput": 5533.78, "total_tokens": 14035744} {"current_steps": 23025, "total_steps": 64460, "loss": 0.2296, "lr": 8.116904633510101e-06, "epoch": 7.143965249767297, "percentage": 35.72, "elapsed_time": "0:42:16", "remaining_time": "1:16:05", "throughput": 5533.79, "total_tokens": 14038464} {"current_steps": 23030, "total_steps": 64460, "loss": 0.2342, "lr": 8.115845952039867e-06, "epoch": 7.145516599441514, "percentage": 35.73, "elapsed_time": "0:42:17", "remaining_time": "1:16:04", "throughput": 5533.67, "total_tokens": 14040800} {"current_steps": 23035, "total_steps": 64460, "loss": 0.2284, "lr": 8.114787042141228e-06, "epoch": 7.147067949115731, "percentage": 35.74, "elapsed_time": "0:42:17", "remaining_time": "1:16:04", "throughput": 5533.74, "total_tokens": 14044160} {"current_steps": 23040, "total_steps": 64460, "loss": 0.2336, "lr": 8.113727903891813e-06, "epoch": 7.1486192987899475, "percentage": 35.74, "elapsed_time": "0:42:18", "remaining_time": "1:16:03", "throughput": 5533.89, "total_tokens": 14047936} {"current_steps": 23045, "total_steps": 64460, "loss": 0.2283, "lr": 8.11266853736927e-06, "epoch": 7.150170648464163, "percentage": 35.75, "elapsed_time": "0:42:18", "remaining_time": "1:16:02", "throughput": 5533.8, "total_tokens": 14050240} {"current_steps": 23050, "total_steps": 64460, "loss": 0.2374, "lr": 8.111608942651265e-06, "epoch": 7.15172199813838, "percentage": 35.76, "elapsed_time": "0:42:19", "remaining_time": "1:16:02", "throughput": 5533.74, "total_tokens": 14052736} {"current_steps": 23055, "total_steps": 64460, "loss": 0.2284, "lr": 8.110549119815477e-06, "epoch": 7.153273347812597, "percentage": 35.77, "elapsed_time": "0:42:19", "remaining_time": "1:16:01", "throughput": 5533.66, "total_tokens": 14055136} {"current_steps": 23060, "total_steps": 64460, "loss": 0.2304, "lr": 8.109489068939604e-06, "epoch": 7.154824697486814, "percentage": 35.77, "elapsed_time": "0:42:20", "remaining_time": "1:16:00", "throughput": 5533.6, "total_tokens": 14057664} {"current_steps": 23065, "total_steps": 64460, "loss": 0.2333, "lr": 8.10842879010136e-06, "epoch": 7.1563760471610305, "percentage": 35.78, "elapsed_time": "0:42:20", "remaining_time": "1:16:00", "throughput": 5533.63, "total_tokens": 14060352} {"current_steps": 23070, "total_steps": 64460, "loss": 0.2275, "lr": 8.107368283378478e-06, "epoch": 7.157927396835246, "percentage": 35.79, "elapsed_time": "0:42:21", "remaining_time": "1:15:59", "throughput": 5533.99, "total_tokens": 14065184} {"current_steps": 23075, "total_steps": 64460, "loss": 0.2316, "lr": 8.106307548848705e-06, "epoch": 7.159478746509463, "percentage": 35.8, "elapsed_time": "0:42:22", "remaining_time": "1:15:59", "throughput": 5534.01, "total_tokens": 14067840} {"current_steps": 23080, "total_steps": 64460, "loss": 0.2306, "lr": 8.105246586589802e-06, "epoch": 7.16103009618368, "percentage": 35.81, "elapsed_time": "0:42:22", "remaining_time": "1:15:58", "throughput": 5533.98, "total_tokens": 14070368} {"current_steps": 23085, "total_steps": 64460, "loss": 0.2363, "lr": 8.104185396679553e-06, "epoch": 7.162581445857897, "percentage": 35.81, "elapsed_time": "0:42:23", "remaining_time": "1:15:57", "throughput": 5533.91, "total_tokens": 14072928} {"current_steps": 23090, "total_steps": 64460, "loss": 0.2346, "lr": 8.103123979195755e-06, "epoch": 7.164132795532113, "percentage": 35.82, "elapsed_time": "0:42:23", "remaining_time": "1:15:57", "throughput": 5534.06, "total_tokens": 14076096} {"current_steps": 23095, "total_steps": 64460, "loss": 0.2362, "lr": 8.102062334216224e-06, "epoch": 7.165684145206329, "percentage": 35.83, "elapsed_time": "0:42:24", "remaining_time": "1:15:56", "throughput": 5534.27, "total_tokens": 14079904} {"current_steps": 23100, "total_steps": 64460, "loss": 0.2304, "lr": 8.10100046181879e-06, "epoch": 7.167235494880546, "percentage": 35.84, "elapsed_time": "0:42:24", "remaining_time": "1:15:56", "throughput": 5534.46, "total_tokens": 14083296} {"current_steps": 23105, "total_steps": 64460, "loss": 0.2368, "lr": 8.099938362081298e-06, "epoch": 7.168786844554763, "percentage": 35.84, "elapsed_time": "0:42:25", "remaining_time": "1:15:55", "throughput": 5534.54, "total_tokens": 14086144} {"current_steps": 23110, "total_steps": 64460, "loss": 0.2325, "lr": 8.098876035081618e-06, "epoch": 7.170338194228979, "percentage": 35.85, "elapsed_time": "0:42:25", "remaining_time": "1:15:54", "throughput": 5534.41, "total_tokens": 14088384} {"current_steps": 23115, "total_steps": 64460, "loss": 0.2269, "lr": 8.09781348089763e-06, "epoch": 7.1718895439031956, "percentage": 35.86, "elapsed_time": "0:42:26", "remaining_time": "1:15:54", "throughput": 5534.47, "total_tokens": 14091200} {"current_steps": 23120, "total_steps": 64460, "loss": 0.2336, "lr": 8.096750699607227e-06, "epoch": 7.173440893577412, "percentage": 35.87, "elapsed_time": "0:42:26", "remaining_time": "1:15:53", "throughput": 5534.6, "total_tokens": 14094240} {"current_steps": 23125, "total_steps": 64460, "loss": 0.2351, "lr": 8.095687691288327e-06, "epoch": 7.174992243251629, "percentage": 35.87, "elapsed_time": "0:42:27", "remaining_time": "1:15:52", "throughput": 5534.72, "total_tokens": 14097504} {"current_steps": 23130, "total_steps": 64460, "loss": 0.2273, "lr": 8.094624456018862e-06, "epoch": 7.176543592925846, "percentage": 35.88, "elapsed_time": "0:42:27", "remaining_time": "1:15:52", "throughput": 5534.75, "total_tokens": 14100352} {"current_steps": 23135, "total_steps": 64460, "loss": 0.2309, "lr": 8.093560993876778e-06, "epoch": 7.178094942600062, "percentage": 35.89, "elapsed_time": "0:42:28", "remaining_time": "1:15:51", "throughput": 5534.75, "total_tokens": 14102976} {"current_steps": 23140, "total_steps": 64460, "loss": 0.2283, "lr": 8.092497304940041e-06, "epoch": 7.1796462922742785, "percentage": 35.9, "elapsed_time": "0:42:28", "remaining_time": "1:15:50", "throughput": 5534.89, "total_tokens": 14106176} {"current_steps": 23145, "total_steps": 64460, "loss": 0.2203, "lr": 8.091433389286631e-06, "epoch": 7.181197641948495, "percentage": 35.91, "elapsed_time": "0:42:29", "remaining_time": "1:15:50", "throughput": 5535.04, "total_tokens": 14109280} {"current_steps": 23150, "total_steps": 64460, "loss": 0.226, "lr": 8.090369246994545e-06, "epoch": 7.182748991622712, "percentage": 35.91, "elapsed_time": "0:42:29", "remaining_time": "1:15:49", "throughput": 5534.89, "total_tokens": 14111584} {"current_steps": 23155, "total_steps": 64460, "loss": 0.2401, "lr": 8.089304878141796e-06, "epoch": 7.184300341296928, "percentage": 35.92, "elapsed_time": "0:42:30", "remaining_time": "1:15:48", "throughput": 5534.69, "total_tokens": 14113856} {"current_steps": 23160, "total_steps": 64460, "loss": 0.2289, "lr": 8.08824028280642e-06, "epoch": 7.185851690971145, "percentage": 35.93, "elapsed_time": "0:42:30", "remaining_time": "1:15:48", "throughput": 5534.63, "total_tokens": 14116288} {"current_steps": 23165, "total_steps": 64460, "loss": 0.2324, "lr": 8.087175461066457e-06, "epoch": 7.1874030406453615, "percentage": 35.94, "elapsed_time": "0:42:30", "remaining_time": "1:15:47", "throughput": 5534.68, "total_tokens": 14118976} {"current_steps": 23170, "total_steps": 64460, "loss": 0.2305, "lr": 8.086110412999976e-06, "epoch": 7.188954390319578, "percentage": 35.94, "elapsed_time": "0:42:31", "remaining_time": "1:15:47", "throughput": 5534.88, "total_tokens": 14122784} {"current_steps": 23175, "total_steps": 64460, "loss": 0.2302, "lr": 8.08504513868506e-06, "epoch": 7.190505739993794, "percentage": 35.95, "elapsed_time": "0:42:32", "remaining_time": "1:15:46", "throughput": 5535.03, "total_tokens": 14125920} {"current_steps": 23180, "total_steps": 64460, "loss": 0.2302, "lr": 8.0839796381998e-06, "epoch": 7.192057089668011, "percentage": 35.96, "elapsed_time": "0:42:32", "remaining_time": "1:15:45", "throughput": 5535.1, "total_tokens": 14128704} {"current_steps": 23185, "total_steps": 64460, "loss": 0.2264, "lr": 8.082913911622314e-06, "epoch": 7.193608439342228, "percentage": 35.97, "elapsed_time": "0:42:33", "remaining_time": "1:15:45", "throughput": 5535.2, "total_tokens": 14131872} {"current_steps": 23190, "total_steps": 64460, "loss": 0.2372, "lr": 8.08184795903073e-06, "epoch": 7.1951597890164445, "percentage": 35.98, "elapsed_time": "0:42:33", "remaining_time": "1:15:44", "throughput": 5535.21, "total_tokens": 14134464} {"current_steps": 23195, "total_steps": 64460, "loss": 0.2326, "lr": 8.080781780503197e-06, "epoch": 7.196711138690661, "percentage": 35.98, "elapsed_time": "0:42:34", "remaining_time": "1:15:43", "throughput": 5535.28, "total_tokens": 14137472} {"current_steps": 23200, "total_steps": 64460, "loss": 0.2323, "lr": 8.079715376117876e-06, "epoch": 7.198262488364877, "percentage": 35.99, "elapsed_time": "0:42:34", "remaining_time": "1:15:43", "throughput": 5535.02, "total_tokens": 14139456} {"current_steps": 23205, "total_steps": 64460, "loss": 0.2294, "lr": 8.07864874595295e-06, "epoch": 7.199813838039094, "percentage": 36.0, "elapsed_time": "0:42:35", "remaining_time": "1:15:42", "throughput": 5535.01, "total_tokens": 14142144} {"current_steps": 23210, "total_steps": 64460, "loss": 0.2445, "lr": 8.077581890086614e-06, "epoch": 7.201365187713311, "percentage": 36.01, "elapsed_time": "0:42:35", "remaining_time": "1:15:41", "throughput": 5535.07, "total_tokens": 14144896} {"current_steps": 23215, "total_steps": 64460, "loss": 0.229, "lr": 8.076514808597082e-06, "epoch": 7.2029165373875275, "percentage": 36.01, "elapsed_time": "0:42:35", "remaining_time": "1:15:41", "throughput": 5535.11, "total_tokens": 14147488} {"current_steps": 23220, "total_steps": 64460, "loss": 0.232, "lr": 8.075447501562583e-06, "epoch": 7.204467887061743, "percentage": 36.02, "elapsed_time": "0:42:36", "remaining_time": "1:15:40", "throughput": 5535.09, "total_tokens": 14150016} {"current_steps": 23225, "total_steps": 64460, "loss": 0.228, "lr": 8.074379969061363e-06, "epoch": 7.20601923673596, "percentage": 36.03, "elapsed_time": "0:42:36", "remaining_time": "1:15:39", "throughput": 5535.14, "total_tokens": 14152640} {"current_steps": 23230, "total_steps": 64460, "loss": 0.2296, "lr": 8.073312211171684e-06, "epoch": 7.207570586410177, "percentage": 36.04, "elapsed_time": "0:42:37", "remaining_time": "1:15:39", "throughput": 5535.31, "total_tokens": 14156384} {"current_steps": 23235, "total_steps": 64460, "loss": 0.2273, "lr": 8.072244227971829e-06, "epoch": 7.209121936084394, "percentage": 36.05, "elapsed_time": "0:42:37", "remaining_time": "1:15:38", "throughput": 5535.42, "total_tokens": 14159456} {"current_steps": 23240, "total_steps": 64460, "loss": 0.2311, "lr": 8.071176019540089e-06, "epoch": 7.2106732857586096, "percentage": 36.05, "elapsed_time": "0:42:38", "remaining_time": "1:15:37", "throughput": 5535.49, "total_tokens": 14162496} {"current_steps": 23245, "total_steps": 64460, "loss": 0.2364, "lr": 8.07010758595478e-06, "epoch": 7.212224635432826, "percentage": 36.06, "elapsed_time": "0:42:38", "remaining_time": "1:15:37", "throughput": 5535.51, "total_tokens": 14165184} {"current_steps": 23250, "total_steps": 64460, "loss": 0.235, "lr": 8.069038927294228e-06, "epoch": 7.213775985107043, "percentage": 36.07, "elapsed_time": "0:42:39", "remaining_time": "1:15:36", "throughput": 5535.42, "total_tokens": 14167424} {"current_steps": 23255, "total_steps": 64460, "loss": 0.2388, "lr": 8.067970043636782e-06, "epoch": 7.21532733478126, "percentage": 36.08, "elapsed_time": "0:42:39", "remaining_time": "1:15:35", "throughput": 5535.41, "total_tokens": 14170272} {"current_steps": 23260, "total_steps": 64460, "loss": 0.2364, "lr": 8.0669009350608e-06, "epoch": 7.216878684455477, "percentage": 36.08, "elapsed_time": "0:42:40", "remaining_time": "1:15:35", "throughput": 5535.34, "total_tokens": 14172896} {"current_steps": 23265, "total_steps": 64460, "loss": 0.2319, "lr": 8.065831601644663e-06, "epoch": 7.2184300341296925, "percentage": 36.09, "elapsed_time": "0:42:41", "remaining_time": "1:15:34", "throughput": 5535.49, "total_tokens": 14176416} {"current_steps": 23270, "total_steps": 64460, "loss": 0.23, "lr": 8.064762043466763e-06, "epoch": 7.219981383803909, "percentage": 36.1, "elapsed_time": "0:42:41", "remaining_time": "1:15:34", "throughput": 5535.57, "total_tokens": 14179136} {"current_steps": 23275, "total_steps": 64460, "loss": 0.2259, "lr": 8.063692260605514e-06, "epoch": 7.221532733478126, "percentage": 36.11, "elapsed_time": "0:42:42", "remaining_time": "1:15:33", "throughput": 5535.84, "total_tokens": 14183040} {"current_steps": 23280, "total_steps": 64460, "loss": 0.2322, "lr": 8.062622253139344e-06, "epoch": 7.223084083152343, "percentage": 36.12, "elapsed_time": "0:42:42", "remaining_time": "1:15:32", "throughput": 5535.82, "total_tokens": 14185632} {"current_steps": 23285, "total_steps": 64460, "loss": 0.2296, "lr": 8.061552021146694e-06, "epoch": 7.224635432826559, "percentage": 36.12, "elapsed_time": "0:42:43", "remaining_time": "1:15:32", "throughput": 5535.84, "total_tokens": 14188576} {"current_steps": 23290, "total_steps": 64460, "loss": 0.2325, "lr": 8.060481564706027e-06, "epoch": 7.2261867825007755, "percentage": 36.13, "elapsed_time": "0:42:43", "remaining_time": "1:15:31", "throughput": 5535.69, "total_tokens": 14190720} {"current_steps": 23295, "total_steps": 64460, "loss": 0.228, "lr": 8.05941088389582e-06, "epoch": 7.227738132174992, "percentage": 36.14, "elapsed_time": "0:42:43", "remaining_time": "1:15:30", "throughput": 5535.75, "total_tokens": 14193600} {"current_steps": 23300, "total_steps": 64460, "loss": 0.2343, "lr": 8.058339978794567e-06, "epoch": 7.229289481849209, "percentage": 36.15, "elapsed_time": "0:42:44", "remaining_time": "1:15:30", "throughput": 5535.54, "total_tokens": 14195680} {"current_steps": 23305, "total_steps": 64460, "loss": 0.2235, "lr": 8.057268849480777e-06, "epoch": 7.230840831523425, "percentage": 36.15, "elapsed_time": "0:42:45", "remaining_time": "1:15:29", "throughput": 5535.56, "total_tokens": 14198816} {"current_steps": 23310, "total_steps": 64460, "loss": 0.2353, "lr": 8.056197496032976e-06, "epoch": 7.232392181197642, "percentage": 36.16, "elapsed_time": "0:42:45", "remaining_time": "1:15:28", "throughput": 5535.54, "total_tokens": 14201440} {"current_steps": 23315, "total_steps": 64460, "loss": 0.2383, "lr": 8.05512591852971e-06, "epoch": 7.2339435308718585, "percentage": 36.17, "elapsed_time": "0:42:45", "remaining_time": "1:15:28", "throughput": 5535.59, "total_tokens": 14204288} {"current_steps": 23320, "total_steps": 64460, "loss": 0.2219, "lr": 8.054054117049535e-06, "epoch": 7.235494880546075, "percentage": 36.18, "elapsed_time": "0:42:46", "remaining_time": "1:15:27", "throughput": 5535.56, "total_tokens": 14206848} {"current_steps": 23325, "total_steps": 64460, "loss": 0.2359, "lr": 8.052982091671026e-06, "epoch": 7.237046230220292, "percentage": 36.19, "elapsed_time": "0:42:47", "remaining_time": "1:15:27", "throughput": 5535.77, "total_tokens": 14210400} {"current_steps": 23330, "total_steps": 64460, "loss": 0.2329, "lr": 8.051909842472779e-06, "epoch": 7.238597579894508, "percentage": 36.19, "elapsed_time": "0:42:47", "remaining_time": "1:15:26", "throughput": 5535.6, "total_tokens": 14212480} {"current_steps": 23335, "total_steps": 64460, "loss": 0.2259, "lr": 8.050837369533399e-06, "epoch": 7.240148929568725, "percentage": 36.2, "elapsed_time": "0:42:47", "remaining_time": "1:15:25", "throughput": 5535.57, "total_tokens": 14215136} {"current_steps": 23340, "total_steps": 64460, "loss": 0.2278, "lr": 8.049764672931515e-06, "epoch": 7.2417002792429415, "percentage": 36.21, "elapsed_time": "0:42:48", "remaining_time": "1:15:25", "throughput": 5535.57, "total_tokens": 14217984} {"current_steps": 23345, "total_steps": 64460, "loss": 0.2315, "lr": 8.048691752745763e-06, "epoch": 7.243251628917158, "percentage": 36.22, "elapsed_time": "0:42:49", "remaining_time": "1:15:24", "throughput": 5535.76, "total_tokens": 14221632} {"current_steps": 23350, "total_steps": 64460, "loss": 0.2364, "lr": 8.047618609054805e-06, "epoch": 7.244802978591374, "percentage": 36.22, "elapsed_time": "0:42:49", "remaining_time": "1:15:24", "throughput": 5536.0, "total_tokens": 14225632} {"current_steps": 23355, "total_steps": 64460, "loss": 0.2308, "lr": 8.046545241937314e-06, "epoch": 7.246354328265591, "percentage": 36.23, "elapsed_time": "0:42:50", "remaining_time": "1:15:23", "throughput": 5535.92, "total_tokens": 14228128} {"current_steps": 23360, "total_steps": 64460, "loss": 0.2289, "lr": 8.04547165147198e-06, "epoch": 7.247905677939808, "percentage": 36.24, "elapsed_time": "0:42:50", "remaining_time": "1:15:22", "throughput": 5535.95, "total_tokens": 14230944} {"current_steps": 23365, "total_steps": 64460, "loss": 0.232, "lr": 8.04439783773751e-06, "epoch": 7.249457027614024, "percentage": 36.25, "elapsed_time": "0:42:51", "remaining_time": "1:15:22", "throughput": 5536.13, "total_tokens": 14234720} {"current_steps": 23370, "total_steps": 64460, "loss": 0.2342, "lr": 8.043323800812629e-06, "epoch": 7.25100837728824, "percentage": 36.26, "elapsed_time": "0:42:51", "remaining_time": "1:15:22", "throughput": 5536.37, "total_tokens": 14239136} {"current_steps": 23375, "total_steps": 64460, "loss": 0.2315, "lr": 8.04224954077607e-06, "epoch": 7.252559726962457, "percentage": 36.26, "elapsed_time": "0:42:52", "remaining_time": "1:15:21", "throughput": 5536.45, "total_tokens": 14241952} {"current_steps": 23380, "total_steps": 64460, "loss": 0.2247, "lr": 8.0411750577066e-06, "epoch": 7.254111076636674, "percentage": 36.27, "elapsed_time": "0:42:52", "remaining_time": "1:15:20", "throughput": 5536.67, "total_tokens": 14245408} {"current_steps": 23385, "total_steps": 64460, "loss": 0.2378, "lr": 8.040100351682982e-06, "epoch": 7.255662426310891, "percentage": 36.28, "elapsed_time": "0:42:53", "remaining_time": "1:15:20", "throughput": 5536.75, "total_tokens": 14248448} {"current_steps": 23390, "total_steps": 64460, "loss": 0.2347, "lr": 8.03902542278401e-06, "epoch": 7.257213775985107, "percentage": 36.29, "elapsed_time": "0:42:53", "remaining_time": "1:15:19", "throughput": 5536.94, "total_tokens": 14251840} {"current_steps": 23395, "total_steps": 64460, "loss": 0.2356, "lr": 8.037950271088487e-06, "epoch": 7.258765125659323, "percentage": 36.29, "elapsed_time": "0:42:54", "remaining_time": "1:15:19", "throughput": 5537.22, "total_tokens": 14256064} {"current_steps": 23400, "total_steps": 64460, "loss": 0.2332, "lr": 8.036874896675232e-06, "epoch": 7.26031647533354, "percentage": 36.3, "elapsed_time": "0:42:55", "remaining_time": "1:15:18", "throughput": 5537.32, "total_tokens": 14258976} {"current_steps": 23405, "total_steps": 64460, "loss": 0.2307, "lr": 8.035799299623086e-06, "epoch": 7.261867825007757, "percentage": 36.31, "elapsed_time": "0:42:55", "remaining_time": "1:15:17", "throughput": 5537.47, "total_tokens": 14262176} {"current_steps": 23410, "total_steps": 64460, "loss": 0.2319, "lr": 8.034723480010904e-06, "epoch": 7.263419174681974, "percentage": 36.32, "elapsed_time": "0:42:56", "remaining_time": "1:15:17", "throughput": 5537.49, "total_tokens": 14264768} {"current_steps": 23415, "total_steps": 64460, "loss": 0.2276, "lr": 8.033647437917552e-06, "epoch": 7.2649705243561895, "percentage": 36.32, "elapsed_time": "0:42:56", "remaining_time": "1:15:16", "throughput": 5537.37, "total_tokens": 14266976} {"current_steps": 23420, "total_steps": 64460, "loss": 0.2274, "lr": 8.032571173421921e-06, "epoch": 7.266521874030406, "percentage": 36.33, "elapsed_time": "0:42:57", "remaining_time": "1:15:15", "throughput": 5537.66, "total_tokens": 14270912} {"current_steps": 23425, "total_steps": 64460, "loss": 0.2248, "lr": 8.031494686602911e-06, "epoch": 7.268073223704623, "percentage": 36.34, "elapsed_time": "0:42:57", "remaining_time": "1:15:15", "throughput": 5537.8, "total_tokens": 14274240} {"current_steps": 23430, "total_steps": 64460, "loss": 0.2356, "lr": 8.030417977539442e-06, "epoch": 7.26962457337884, "percentage": 36.35, "elapsed_time": "0:42:58", "remaining_time": "1:15:14", "throughput": 5537.83, "total_tokens": 14276928} {"current_steps": 23435, "total_steps": 64460, "loss": 0.2295, "lr": 8.02934104631045e-06, "epoch": 7.271175923053056, "percentage": 36.36, "elapsed_time": "0:42:58", "remaining_time": "1:15:14", "throughput": 5537.68, "total_tokens": 14279392} {"current_steps": 23440, "total_steps": 64460, "loss": 0.234, "lr": 8.028263892994886e-06, "epoch": 7.2727272727272725, "percentage": 36.36, "elapsed_time": "0:42:59", "remaining_time": "1:15:13", "throughput": 5537.71, "total_tokens": 14282464} {"current_steps": 23445, "total_steps": 64460, "loss": 0.2301, "lr": 8.02718651767172e-06, "epoch": 7.274278622401489, "percentage": 36.37, "elapsed_time": "0:42:59", "remaining_time": "1:15:12", "throughput": 5537.75, "total_tokens": 14285312} {"current_steps": 23450, "total_steps": 64460, "loss": 0.2276, "lr": 8.026108920419934e-06, "epoch": 7.275829972075706, "percentage": 36.38, "elapsed_time": "0:43:00", "remaining_time": "1:15:12", "throughput": 5537.77, "total_tokens": 14288192} {"current_steps": 23455, "total_steps": 64460, "loss": 0.2326, "lr": 8.02503110131853e-06, "epoch": 7.277381321749923, "percentage": 36.39, "elapsed_time": "0:43:00", "remaining_time": "1:15:11", "throughput": 5537.81, "total_tokens": 14290784} {"current_steps": 23460, "total_steps": 64460, "loss": 0.2294, "lr": 8.023953060446524e-06, "epoch": 7.278932671424139, "percentage": 36.39, "elapsed_time": "0:43:01", "remaining_time": "1:15:11", "throughput": 5538.18, "total_tokens": 14295776} {"current_steps": 23465, "total_steps": 64460, "loss": 0.2389, "lr": 8.02287479788295e-06, "epoch": 7.2804840210983555, "percentage": 36.4, "elapsed_time": "0:43:01", "remaining_time": "1:15:10", "throughput": 5538.22, "total_tokens": 14298432} {"current_steps": 23470, "total_steps": 64460, "loss": 0.2326, "lr": 8.021796313706857e-06, "epoch": 7.282035370772572, "percentage": 36.41, "elapsed_time": "0:43:02", "remaining_time": "1:15:09", "throughput": 5538.06, "total_tokens": 14300608} {"current_steps": 23475, "total_steps": 64460, "loss": 0.2276, "lr": 8.020717607997311e-06, "epoch": 7.283586720446789, "percentage": 36.42, "elapsed_time": "0:43:02", "remaining_time": "1:15:09", "throughput": 5537.91, "total_tokens": 14302816} {"current_steps": 23480, "total_steps": 64460, "loss": 0.2301, "lr": 8.019638680833395e-06, "epoch": 7.285138070121005, "percentage": 36.43, "elapsed_time": "0:43:03", "remaining_time": "1:15:08", "throughput": 5538.17, "total_tokens": 14306560} {"current_steps": 23485, "total_steps": 64460, "loss": 0.2391, "lr": 8.018559532294204e-06, "epoch": 7.286689419795222, "percentage": 36.43, "elapsed_time": "0:43:03", "remaining_time": "1:15:07", "throughput": 5538.22, "total_tokens": 14309312} {"current_steps": 23490, "total_steps": 64460, "loss": 0.2312, "lr": 8.017480162458855e-06, "epoch": 7.288240769469438, "percentage": 36.44, "elapsed_time": "0:43:04", "remaining_time": "1:15:07", "throughput": 5538.21, "total_tokens": 14311744} {"current_steps": 23495, "total_steps": 64460, "loss": 0.2275, "lr": 8.016400571406478e-06, "epoch": 7.289792119143655, "percentage": 36.45, "elapsed_time": "0:43:04", "remaining_time": "1:15:06", "throughput": 5538.47, "total_tokens": 14315968} {"current_steps": 23500, "total_steps": 64460, "loss": 0.2373, "lr": 8.01532075921622e-06, "epoch": 7.291343468817871, "percentage": 36.46, "elapsed_time": "0:43:05", "remaining_time": "1:15:06", "throughput": 5538.54, "total_tokens": 14318688} {"current_steps": 23505, "total_steps": 64460, "loss": 0.2337, "lr": 8.014240725967241e-06, "epoch": 7.292894818492088, "percentage": 36.46, "elapsed_time": "0:43:05", "remaining_time": "1:15:05", "throughput": 5538.73, "total_tokens": 14322144} {"current_steps": 23510, "total_steps": 64460, "loss": 0.2332, "lr": 8.013160471738724e-06, "epoch": 7.294446168166305, "percentage": 36.47, "elapsed_time": "0:43:06", "remaining_time": "1:15:04", "throughput": 5538.92, "total_tokens": 14325632} {"current_steps": 23515, "total_steps": 64460, "loss": 0.2306, "lr": 8.012079996609865e-06, "epoch": 7.295997517840521, "percentage": 36.48, "elapsed_time": "0:43:06", "remaining_time": "1:15:04", "throughput": 5538.93, "total_tokens": 14328384} {"current_steps": 23520, "total_steps": 64460, "loss": 0.2321, "lr": 8.010999300659871e-06, "epoch": 7.297548867514738, "percentage": 36.49, "elapsed_time": "0:43:07", "remaining_time": "1:15:03", "throughput": 5539.15, "total_tokens": 14332288} {"current_steps": 23525, "total_steps": 64460, "loss": 0.233, "lr": 8.009918383967975e-06, "epoch": 7.299100217188954, "percentage": 36.5, "elapsed_time": "0:43:07", "remaining_time": "1:15:03", "throughput": 5539.12, "total_tokens": 14334688} {"current_steps": 23530, "total_steps": 64460, "loss": 0.2345, "lr": 8.008837246613417e-06, "epoch": 7.300651566863171, "percentage": 36.5, "elapsed_time": "0:43:08", "remaining_time": "1:15:02", "throughput": 5539.14, "total_tokens": 14337248} {"current_steps": 23535, "total_steps": 64460, "loss": 0.2311, "lr": 8.007755888675462e-06, "epoch": 7.302202916537388, "percentage": 36.51, "elapsed_time": "0:43:08", "remaining_time": "1:15:01", "throughput": 5539.07, "total_tokens": 14339744} {"current_steps": 23540, "total_steps": 64460, "loss": 0.229, "lr": 8.00667431023338e-06, "epoch": 7.303754266211604, "percentage": 36.52, "elapsed_time": "0:43:09", "remaining_time": "1:15:01", "throughput": 5539.27, "total_tokens": 14343232} {"current_steps": 23545, "total_steps": 64460, "loss": 0.2285, "lr": 8.005592511366468e-06, "epoch": 7.30530561588582, "percentage": 36.53, "elapsed_time": "0:43:09", "remaining_time": "1:15:00", "throughput": 5539.37, "total_tokens": 14346496} {"current_steps": 23550, "total_steps": 64460, "loss": 0.2312, "lr": 8.004510492154033e-06, "epoch": 7.306856965560037, "percentage": 36.53, "elapsed_time": "0:43:10", "remaining_time": "1:15:00", "throughput": 5539.59, "total_tokens": 14350560} {"current_steps": 23555, "total_steps": 64460, "loss": 0.2302, "lr": 8.0034282526754e-06, "epoch": 7.308408315234254, "percentage": 36.54, "elapsed_time": "0:43:11", "remaining_time": "1:14:59", "throughput": 5539.66, "total_tokens": 14353408} {"current_steps": 23560, "total_steps": 64460, "loss": 0.2348, "lr": 8.002345793009912e-06, "epoch": 7.309959664908471, "percentage": 36.55, "elapsed_time": "0:43:11", "remaining_time": "1:14:58", "throughput": 5539.65, "total_tokens": 14356032} {"current_steps": 23565, "total_steps": 64460, "loss": 0.2385, "lr": 8.001263113236922e-06, "epoch": 7.3115110145826865, "percentage": 36.56, "elapsed_time": "0:43:12", "remaining_time": "1:14:58", "throughput": 5539.97, "total_tokens": 14361472} {"current_steps": 23570, "total_steps": 64460, "loss": 0.2286, "lr": 8.000180213435806e-06, "epoch": 7.313062364256903, "percentage": 36.57, "elapsed_time": "0:43:12", "remaining_time": "1:14:58", "throughput": 5540.1, "total_tokens": 14364928} {"current_steps": 23575, "total_steps": 64460, "loss": 0.2315, "lr": 7.999097093685953e-06, "epoch": 7.31461371393112, "percentage": 36.57, "elapsed_time": "0:43:13", "remaining_time": "1:14:57", "throughput": 5540.11, "total_tokens": 14367744} {"current_steps": 23580, "total_steps": 64460, "loss": 0.2275, "lr": 7.998013754066769e-06, "epoch": 7.316165063605337, "percentage": 36.58, "elapsed_time": "0:43:13", "remaining_time": "1:14:57", "throughput": 5540.29, "total_tokens": 14371072} {"current_steps": 23585, "total_steps": 64460, "loss": 0.2307, "lr": 7.996930194657675e-06, "epoch": 7.317716413279554, "percentage": 36.59, "elapsed_time": "0:43:14", "remaining_time": "1:14:56", "throughput": 5540.42, "total_tokens": 14374336} {"current_steps": 23590, "total_steps": 64460, "loss": 0.2291, "lr": 7.995846415538109e-06, "epoch": 7.3192677629537695, "percentage": 36.6, "elapsed_time": "0:43:15", "remaining_time": "1:14:56", "throughput": 5540.63, "total_tokens": 14378624} {"current_steps": 23595, "total_steps": 64460, "loss": 0.2274, "lr": 7.994762416787523e-06, "epoch": 7.320819112627986, "percentage": 36.6, "elapsed_time": "0:43:15", "remaining_time": "1:14:55", "throughput": 5540.74, "total_tokens": 14381760} {"current_steps": 23600, "total_steps": 64460, "loss": 0.2348, "lr": 7.99367819848539e-06, "epoch": 7.322370462302203, "percentage": 36.61, "elapsed_time": "0:43:16", "remaining_time": "1:14:54", "throughput": 5540.77, "total_tokens": 14384512} {"current_steps": 23605, "total_steps": 64460, "loss": 0.2338, "lr": 7.992593760711194e-06, "epoch": 7.32392181197642, "percentage": 36.62, "elapsed_time": "0:43:16", "remaining_time": "1:14:54", "throughput": 5540.81, "total_tokens": 14387264} {"current_steps": 23610, "total_steps": 64460, "loss": 0.2311, "lr": 7.991509103544439e-06, "epoch": 7.325473161650636, "percentage": 36.63, "elapsed_time": "0:43:17", "remaining_time": "1:14:53", "throughput": 5540.72, "total_tokens": 14389600} {"current_steps": 23615, "total_steps": 64460, "loss": 0.2338, "lr": 7.99042422706464e-06, "epoch": 7.327024511324852, "percentage": 36.64, "elapsed_time": "0:43:17", "remaining_time": "1:14:52", "throughput": 5540.93, "total_tokens": 14393536} {"current_steps": 23620, "total_steps": 64460, "loss": 0.2307, "lr": 7.989339131351335e-06, "epoch": 7.328575860999069, "percentage": 36.64, "elapsed_time": "0:43:18", "remaining_time": "1:14:52", "throughput": 5540.84, "total_tokens": 14396000} {"current_steps": 23625, "total_steps": 64460, "loss": 0.2377, "lr": 7.988253816484071e-06, "epoch": 7.330127210673286, "percentage": 36.65, "elapsed_time": "0:43:18", "remaining_time": "1:14:51", "throughput": 5540.83, "total_tokens": 14398528} {"current_steps": 23630, "total_steps": 64460, "loss": 0.2394, "lr": 7.987168282542416e-06, "epoch": 7.331678560347502, "percentage": 36.66, "elapsed_time": "0:43:19", "remaining_time": "1:14:50", "throughput": 5540.88, "total_tokens": 14401344} {"current_steps": 23635, "total_steps": 64460, "loss": 0.2345, "lr": 7.986082529605955e-06, "epoch": 7.333229910021719, "percentage": 36.67, "elapsed_time": "0:43:19", "remaining_time": "1:14:50", "throughput": 5540.74, "total_tokens": 14403584} {"current_steps": 23640, "total_steps": 64460, "loss": 0.2312, "lr": 7.984996557754282e-06, "epoch": 7.334781259695935, "percentage": 36.67, "elapsed_time": "0:43:20", "remaining_time": "1:14:49", "throughput": 5540.8, "total_tokens": 14406496} {"current_steps": 23645, "total_steps": 64460, "loss": 0.229, "lr": 7.983910367067014e-06, "epoch": 7.336332609370152, "percentage": 36.68, "elapsed_time": "0:43:20", "remaining_time": "1:14:48", "throughput": 5540.86, "total_tokens": 14409344} {"current_steps": 23650, "total_steps": 64460, "loss": 0.2347, "lr": 7.982823957623782e-06, "epoch": 7.337883959044369, "percentage": 36.69, "elapsed_time": "0:43:21", "remaining_time": "1:14:48", "throughput": 5540.9, "total_tokens": 14412384} {"current_steps": 23655, "total_steps": 64460, "loss": 0.2311, "lr": 7.98173732950423e-06, "epoch": 7.339435308718585, "percentage": 36.7, "elapsed_time": "0:43:21", "remaining_time": "1:14:47", "throughput": 5541.03, "total_tokens": 14415616} {"current_steps": 23660, "total_steps": 64460, "loss": 0.23, "lr": 7.980650482788025e-06, "epoch": 7.340986658392802, "percentage": 36.7, "elapsed_time": "0:43:22", "remaining_time": "1:14:47", "throughput": 5541.14, "total_tokens": 14418560} {"current_steps": 23665, "total_steps": 64460, "loss": 0.2321, "lr": 7.979563417554843e-06, "epoch": 7.342538008067018, "percentage": 36.71, "elapsed_time": "0:43:22", "remaining_time": "1:14:46", "throughput": 5541.18, "total_tokens": 14421248} {"current_steps": 23670, "total_steps": 64460, "loss": 0.2273, "lr": 7.978476133884378e-06, "epoch": 7.344089357741235, "percentage": 36.72, "elapsed_time": "0:43:23", "remaining_time": "1:14:45", "throughput": 5541.18, "total_tokens": 14423936} {"current_steps": 23675, "total_steps": 64460, "loss": 0.2309, "lr": 7.977388631856343e-06, "epoch": 7.345640707415451, "percentage": 36.73, "elapsed_time": "0:43:23", "remaining_time": "1:14:45", "throughput": 5541.13, "total_tokens": 14426432} {"current_steps": 23680, "total_steps": 64460, "loss": 0.233, "lr": 7.976300911550463e-06, "epoch": 7.347192057089668, "percentage": 36.74, "elapsed_time": "0:43:24", "remaining_time": "1:14:44", "throughput": 5541.24, "total_tokens": 14429568} {"current_steps": 23685, "total_steps": 64460, "loss": 0.2275, "lr": 7.975212973046482e-06, "epoch": 7.348743406763885, "percentage": 36.74, "elapsed_time": "0:43:24", "remaining_time": "1:14:44", "throughput": 5541.47, "total_tokens": 14433536} {"current_steps": 23690, "total_steps": 64460, "loss": 0.2313, "lr": 7.974124816424158e-06, "epoch": 7.350294756438101, "percentage": 36.75, "elapsed_time": "0:43:25", "remaining_time": "1:14:43", "throughput": 5541.54, "total_tokens": 14436416} {"current_steps": 23695, "total_steps": 64460, "loss": 0.2274, "lr": 7.973036441763267e-06, "epoch": 7.351846106112317, "percentage": 36.76, "elapsed_time": "0:43:25", "remaining_time": "1:14:42", "throughput": 5541.6, "total_tokens": 14439296} {"current_steps": 23700, "total_steps": 64460, "loss": 0.2268, "lr": 7.971947849143597e-06, "epoch": 7.353397455786534, "percentage": 36.77, "elapsed_time": "0:43:26", "remaining_time": "1:14:41", "throughput": 5541.46, "total_tokens": 14441408} {"current_steps": 23705, "total_steps": 64460, "loss": 0.2249, "lr": 7.970859038644958e-06, "epoch": 7.354948805460751, "percentage": 36.77, "elapsed_time": "0:43:26", "remaining_time": "1:14:41", "throughput": 5541.45, "total_tokens": 14443968} {"current_steps": 23710, "total_steps": 64460, "loss": 0.2358, "lr": 7.96977001034717e-06, "epoch": 7.356500155134968, "percentage": 36.78, "elapsed_time": "0:43:27", "remaining_time": "1:14:40", "throughput": 5541.46, "total_tokens": 14447168} {"current_steps": 23715, "total_steps": 64460, "loss": 0.2295, "lr": 7.968680764330074e-06, "epoch": 7.358051504809184, "percentage": 36.79, "elapsed_time": "0:43:27", "remaining_time": "1:14:40", "throughput": 5541.53, "total_tokens": 14450144} {"current_steps": 23720, "total_steps": 64460, "loss": 0.2334, "lr": 7.967591300673523e-06, "epoch": 7.3596028544834, "percentage": 36.8, "elapsed_time": "0:43:28", "remaining_time": "1:14:39", "throughput": 5541.6, "total_tokens": 14453280} {"current_steps": 23725, "total_steps": 64460, "loss": 0.2352, "lr": 7.96650161945739e-06, "epoch": 7.361154204157617, "percentage": 36.81, "elapsed_time": "0:43:28", "remaining_time": "1:14:38", "throughput": 5541.62, "total_tokens": 14456256} {"current_steps": 23730, "total_steps": 64460, "loss": 0.2321, "lr": 7.965411720761558e-06, "epoch": 7.362705553831834, "percentage": 36.81, "elapsed_time": "0:43:29", "remaining_time": "1:14:38", "throughput": 5541.7, "total_tokens": 14459200} {"current_steps": 23735, "total_steps": 64460, "loss": 0.2323, "lr": 7.96432160466593e-06, "epoch": 7.3642569035060506, "percentage": 36.82, "elapsed_time": "0:43:29", "remaining_time": "1:14:37", "throughput": 5541.89, "total_tokens": 14462592} {"current_steps": 23740, "total_steps": 64460, "loss": 0.2309, "lr": 7.963231271250426e-06, "epoch": 7.365808253180266, "percentage": 36.83, "elapsed_time": "0:43:30", "remaining_time": "1:14:37", "throughput": 5541.96, "total_tokens": 14465472} {"current_steps": 23745, "total_steps": 64460, "loss": 0.233, "lr": 7.962140720594981e-06, "epoch": 7.367359602854483, "percentage": 36.84, "elapsed_time": "0:43:30", "remaining_time": "1:14:36", "throughput": 5542.14, "total_tokens": 14469120} {"current_steps": 23750, "total_steps": 64460, "loss": 0.23, "lr": 7.961049952779545e-06, "epoch": 7.3689109525287, "percentage": 36.84, "elapsed_time": "0:43:31", "remaining_time": "1:14:36", "throughput": 5542.25, "total_tokens": 14473280} {"current_steps": 23755, "total_steps": 64460, "loss": 0.2244, "lr": 7.959958967884081e-06, "epoch": 7.370462302202917, "percentage": 36.85, "elapsed_time": "0:43:31", "remaining_time": "1:14:35", "throughput": 5542.27, "total_tokens": 14476064} {"current_steps": 23760, "total_steps": 64460, "loss": 0.2249, "lr": 7.958867765988575e-06, "epoch": 7.372013651877133, "percentage": 36.86, "elapsed_time": "0:43:32", "remaining_time": "1:14:34", "throughput": 5542.27, "total_tokens": 14478784} {"current_steps": 23765, "total_steps": 64460, "loss": 0.2311, "lr": 7.957776347173023e-06, "epoch": 7.373565001551349, "percentage": 36.87, "elapsed_time": "0:43:32", "remaining_time": "1:14:34", "throughput": 5542.16, "total_tokens": 14481216} {"current_steps": 23770, "total_steps": 64460, "loss": 0.2249, "lr": 7.95668471151744e-06, "epoch": 7.375116351225566, "percentage": 36.88, "elapsed_time": "0:43:33", "remaining_time": "1:14:33", "throughput": 5542.15, "total_tokens": 14483968} {"current_steps": 23775, "total_steps": 64460, "loss": 0.2318, "lr": 7.955592859101854e-06, "epoch": 7.376667700899783, "percentage": 36.88, "elapsed_time": "0:43:33", "remaining_time": "1:14:33", "throughput": 5542.09, "total_tokens": 14486816} {"current_steps": 23780, "total_steps": 64460, "loss": 0.2347, "lr": 7.954500790006315e-06, "epoch": 7.378219050574, "percentage": 36.89, "elapsed_time": "0:43:34", "remaining_time": "1:14:32", "throughput": 5541.94, "total_tokens": 14489120} {"current_steps": 23785, "total_steps": 64460, "loss": 0.2302, "lr": 7.953408504310878e-06, "epoch": 7.379770400248216, "percentage": 36.9, "elapsed_time": "0:43:34", "remaining_time": "1:14:31", "throughput": 5542.03, "total_tokens": 14492032} {"current_steps": 23790, "total_steps": 64460, "loss": 0.2368, "lr": 7.952316002095626e-06, "epoch": 7.381321749922432, "percentage": 36.91, "elapsed_time": "0:43:35", "remaining_time": "1:14:31", "throughput": 5541.97, "total_tokens": 14494464} {"current_steps": 23795, "total_steps": 64460, "loss": 0.2379, "lr": 7.95122328344065e-06, "epoch": 7.382873099596649, "percentage": 36.91, "elapsed_time": "0:43:36", "remaining_time": "1:14:30", "throughput": 5542.21, "total_tokens": 14498688} {"current_steps": 23800, "total_steps": 64460, "loss": 0.2237, "lr": 7.95013034842606e-06, "epoch": 7.384424449270866, "percentage": 36.92, "elapsed_time": "0:43:36", "remaining_time": "1:14:30", "throughput": 5542.23, "total_tokens": 14501248} {"current_steps": 23805, "total_steps": 64460, "loss": 0.2332, "lr": 7.94903719713198e-06, "epoch": 7.385975798945082, "percentage": 36.93, "elapsed_time": "0:43:37", "remaining_time": "1:14:29", "throughput": 5542.47, "total_tokens": 14504736} {"current_steps": 23810, "total_steps": 64460, "loss": 0.2365, "lr": 7.947943829638551e-06, "epoch": 7.387527148619299, "percentage": 36.94, "elapsed_time": "0:43:37", "remaining_time": "1:14:28", "throughput": 5542.48, "total_tokens": 14507328} {"current_steps": 23815, "total_steps": 64460, "loss": 0.228, "lr": 7.94685024602593e-06, "epoch": 7.389078498293515, "percentage": 36.95, "elapsed_time": "0:43:38", "remaining_time": "1:14:28", "throughput": 5542.76, "total_tokens": 14511456} {"current_steps": 23820, "total_steps": 64460, "loss": 0.2334, "lr": 7.945756446374292e-06, "epoch": 7.390629847967732, "percentage": 36.95, "elapsed_time": "0:43:38", "remaining_time": "1:14:27", "throughput": 5543.06, "total_tokens": 14515712} {"current_steps": 23825, "total_steps": 64460, "loss": 0.2288, "lr": 7.944662430763823e-06, "epoch": 7.392181197641948, "percentage": 36.96, "elapsed_time": "0:43:39", "remaining_time": "1:14:27", "throughput": 5543.06, "total_tokens": 14518432} {"current_steps": 23830, "total_steps": 64460, "loss": 0.2372, "lr": 7.943568199274727e-06, "epoch": 7.393732547316165, "percentage": 36.97, "elapsed_time": "0:43:39", "remaining_time": "1:14:26", "throughput": 5543.1, "total_tokens": 14521536} {"current_steps": 23835, "total_steps": 64460, "loss": 0.2261, "lr": 7.942473751987224e-06, "epoch": 7.395283896990382, "percentage": 36.98, "elapsed_time": "0:43:40", "remaining_time": "1:14:25", "throughput": 5543.17, "total_tokens": 14524352} {"current_steps": 23840, "total_steps": 64460, "loss": 0.2378, "lr": 7.941379088981554e-06, "epoch": 7.396835246664598, "percentage": 36.98, "elapsed_time": "0:43:40", "remaining_time": "1:14:25", "throughput": 5543.34, "total_tokens": 14527648} {"current_steps": 23845, "total_steps": 64460, "loss": 0.2307, "lr": 7.940284210337965e-06, "epoch": 7.398386596338815, "percentage": 36.99, "elapsed_time": "0:43:41", "remaining_time": "1:14:24", "throughput": 5543.5, "total_tokens": 14530976} {"current_steps": 23850, "total_steps": 64460, "loss": 0.2374, "lr": 7.939189116136723e-06, "epoch": 7.399937946013031, "percentage": 37.0, "elapsed_time": "0:43:41", "remaining_time": "1:14:24", "throughput": 5543.51, "total_tokens": 14533632} {"current_steps": 23855, "total_steps": 64460, "loss": 0.2342, "lr": 7.938093806458114e-06, "epoch": 7.401489295687248, "percentage": 37.01, "elapsed_time": "0:43:42", "remaining_time": "1:14:23", "throughput": 5543.66, "total_tokens": 14536800} {"current_steps": 23860, "total_steps": 64460, "loss": 0.2299, "lr": 7.936998281382437e-06, "epoch": 7.4030406453614646, "percentage": 37.02, "elapsed_time": "0:43:42", "remaining_time": "1:14:22", "throughput": 5543.63, "total_tokens": 14539680} {"current_steps": 23865, "total_steps": 64460, "loss": 0.2315, "lr": 7.935902540990008e-06, "epoch": 7.404591995035681, "percentage": 37.02, "elapsed_time": "0:43:43", "remaining_time": "1:14:22", "throughput": 5543.52, "total_tokens": 14542208} {"current_steps": 23870, "total_steps": 64460, "loss": 0.2326, "lr": 7.934806585361157e-06, "epoch": 7.406143344709897, "percentage": 37.03, "elapsed_time": "0:43:43", "remaining_time": "1:14:21", "throughput": 5543.82, "total_tokens": 14546144} {"current_steps": 23875, "total_steps": 64460, "loss": 0.232, "lr": 7.933710414576228e-06, "epoch": 7.407694694384114, "percentage": 37.04, "elapsed_time": "0:43:44", "remaining_time": "1:14:21", "throughput": 5544.1, "total_tokens": 14550336} {"current_steps": 23880, "total_steps": 64460, "loss": 0.2341, "lr": 7.932614028715587e-06, "epoch": 7.409246044058331, "percentage": 37.05, "elapsed_time": "0:43:44", "remaining_time": "1:14:20", "throughput": 5544.24, "total_tokens": 14553472} {"current_steps": 23885, "total_steps": 64460, "loss": 0.2303, "lr": 7.931517427859608e-06, "epoch": 7.4107973937325475, "percentage": 37.05, "elapsed_time": "0:43:45", "remaining_time": "1:14:20", "throughput": 5544.31, "total_tokens": 14556544} {"current_steps": 23890, "total_steps": 64460, "loss": 0.2357, "lr": 7.930420612088689e-06, "epoch": 7.412348743406763, "percentage": 37.06, "elapsed_time": "0:43:45", "remaining_time": "1:14:19", "throughput": 5544.38, "total_tokens": 14559456} {"current_steps": 23895, "total_steps": 64460, "loss": 0.2313, "lr": 7.929323581483238e-06, "epoch": 7.41390009308098, "percentage": 37.07, "elapsed_time": "0:43:46", "remaining_time": "1:14:18", "throughput": 5544.43, "total_tokens": 14562208} {"current_steps": 23900, "total_steps": 64460, "loss": 0.2295, "lr": 7.928226336123679e-06, "epoch": 7.415451442755197, "percentage": 37.08, "elapsed_time": "0:43:46", "remaining_time": "1:14:18", "throughput": 5544.45, "total_tokens": 14565120} {"current_steps": 23905, "total_steps": 64460, "loss": 0.2299, "lr": 7.927128876090454e-06, "epoch": 7.417002792429414, "percentage": 37.09, "elapsed_time": "0:43:47", "remaining_time": "1:14:17", "throughput": 5544.49, "total_tokens": 14567776} {"current_steps": 23910, "total_steps": 64460, "loss": 0.2281, "lr": 7.92603120146402e-06, "epoch": 7.4185541421036305, "percentage": 37.09, "elapsed_time": "0:43:47", "remaining_time": "1:14:16", "throughput": 5544.53, "total_tokens": 14570528} {"current_steps": 23915, "total_steps": 64460, "loss": 0.2288, "lr": 7.924933312324849e-06, "epoch": 7.420105491777846, "percentage": 37.1, "elapsed_time": "0:43:48", "remaining_time": "1:14:16", "throughput": 5544.48, "total_tokens": 14573408} {"current_steps": 23920, "total_steps": 64460, "loss": 0.2399, "lr": 7.923835208753432e-06, "epoch": 7.421656841452063, "percentage": 37.11, "elapsed_time": "0:43:48", "remaining_time": "1:14:15", "throughput": 5544.45, "total_tokens": 14576032} {"current_steps": 23925, "total_steps": 64460, "loss": 0.2273, "lr": 7.92273689083027e-06, "epoch": 7.42320819112628, "percentage": 37.12, "elapsed_time": "0:43:49", "remaining_time": "1:14:15", "throughput": 5544.61, "total_tokens": 14579552} {"current_steps": 23930, "total_steps": 64460, "loss": 0.2289, "lr": 7.921638358635884e-06, "epoch": 7.424759540800497, "percentage": 37.12, "elapsed_time": "0:43:50", "remaining_time": "1:14:14", "throughput": 5544.41, "total_tokens": 14581824} {"current_steps": 23935, "total_steps": 64460, "loss": 0.2373, "lr": 7.920539612250808e-06, "epoch": 7.426310890474713, "percentage": 37.13, "elapsed_time": "0:43:50", "remaining_time": "1:14:13", "throughput": 5544.46, "total_tokens": 14584704} {"current_steps": 23940, "total_steps": 64460, "loss": 0.2337, "lr": 7.919440651755595e-06, "epoch": 7.427862240148929, "percentage": 37.14, "elapsed_time": "0:43:51", "remaining_time": "1:14:13", "throughput": 5544.33, "total_tokens": 14587200} {"current_steps": 23945, "total_steps": 64460, "loss": 0.2241, "lr": 7.91834147723081e-06, "epoch": 7.429413589823146, "percentage": 37.15, "elapsed_time": "0:43:51", "remaining_time": "1:14:12", "throughput": 5544.4, "total_tokens": 14590048} {"current_steps": 23950, "total_steps": 64460, "loss": 0.2391, "lr": 7.917242088757036e-06, "epoch": 7.430964939497363, "percentage": 37.15, "elapsed_time": "0:43:52", "remaining_time": "1:14:11", "throughput": 5544.53, "total_tokens": 14593440} {"current_steps": 23955, "total_steps": 64460, "loss": 0.2337, "lr": 7.91614248641487e-06, "epoch": 7.432516289171579, "percentage": 37.16, "elapsed_time": "0:43:52", "remaining_time": "1:14:11", "throughput": 5544.58, "total_tokens": 14596608} {"current_steps": 23960, "total_steps": 64460, "loss": 0.2263, "lr": 7.915042670284931e-06, "epoch": 7.434067638845796, "percentage": 37.17, "elapsed_time": "0:43:53", "remaining_time": "1:14:10", "throughput": 5544.62, "total_tokens": 14599360} {"current_steps": 23965, "total_steps": 64460, "loss": 0.2261, "lr": 7.913942640447844e-06, "epoch": 7.435618988520012, "percentage": 37.18, "elapsed_time": "0:43:53", "remaining_time": "1:14:10", "throughput": 5544.76, "total_tokens": 14602496} {"current_steps": 23970, "total_steps": 64460, "loss": 0.2426, "lr": 7.912842396984256e-06, "epoch": 7.437170338194229, "percentage": 37.19, "elapsed_time": "0:43:54", "remaining_time": "1:14:09", "throughput": 5545.12, "total_tokens": 14607232} {"current_steps": 23975, "total_steps": 64460, "loss": 0.2297, "lr": 7.911741939974825e-06, "epoch": 7.438721687868446, "percentage": 37.19, "elapsed_time": "0:43:54", "remaining_time": "1:14:09", "throughput": 5545.32, "total_tokens": 14610752} {"current_steps": 23980, "total_steps": 64460, "loss": 0.229, "lr": 7.91064126950023e-06, "epoch": 7.440273037542662, "percentage": 37.2, "elapsed_time": "0:43:55", "remaining_time": "1:14:08", "throughput": 5545.27, "total_tokens": 14613248} {"current_steps": 23985, "total_steps": 64460, "loss": 0.232, "lr": 7.909540385641162e-06, "epoch": 7.4418243872168786, "percentage": 37.21, "elapsed_time": "0:43:55", "remaining_time": "1:14:08", "throughput": 5545.55, "total_tokens": 14617856} {"current_steps": 23990, "total_steps": 64460, "loss": 0.229, "lr": 7.908439288478331e-06, "epoch": 7.443375736891095, "percentage": 37.22, "elapsed_time": "0:43:56", "remaining_time": "1:14:07", "throughput": 5545.63, "total_tokens": 14620864} {"current_steps": 23995, "total_steps": 64460, "loss": 0.2294, "lr": 7.90733797809246e-06, "epoch": 7.444927086565312, "percentage": 37.22, "elapsed_time": "0:43:56", "remaining_time": "1:14:06", "throughput": 5545.77, "total_tokens": 14624096} {"current_steps": 24000, "total_steps": 64460, "loss": 0.2337, "lr": 7.906236454564286e-06, "epoch": 7.446478436239528, "percentage": 37.23, "elapsed_time": "0:43:57", "remaining_time": "1:14:06", "throughput": 5546.0, "total_tokens": 14628864} {"current_steps": 24005, "total_steps": 64460, "loss": 0.2336, "lr": 7.905134717974563e-06, "epoch": 7.448029785913745, "percentage": 37.24, "elapsed_time": "0:43:58", "remaining_time": "1:14:06", "throughput": 5546.36, "total_tokens": 14634496} {"current_steps": 24010, "total_steps": 64460, "loss": 0.228, "lr": 7.904032768404066e-06, "epoch": 7.4495811355879615, "percentage": 37.25, "elapsed_time": "0:43:59", "remaining_time": "1:14:06", "throughput": 5546.34, "total_tokens": 14637152} {"current_steps": 24015, "total_steps": 64460, "loss": 0.2331, "lr": 7.902930605933578e-06, "epoch": 7.451132485262178, "percentage": 37.26, "elapsed_time": "0:43:59", "remaining_time": "1:14:05", "throughput": 5546.26, "total_tokens": 14640000} {"current_steps": 24020, "total_steps": 64460, "loss": 0.2317, "lr": 7.9018282306439e-06, "epoch": 7.452683834936394, "percentage": 37.26, "elapsed_time": "0:44:00", "remaining_time": "1:14:04", "throughput": 5546.04, "total_tokens": 14642144} {"current_steps": 24025, "total_steps": 64460, "loss": 0.2262, "lr": 7.900725642615849e-06, "epoch": 7.454235184610611, "percentage": 37.27, "elapsed_time": "0:44:00", "remaining_time": "1:14:04", "throughput": 5546.03, "total_tokens": 14644960} {"current_steps": 24030, "total_steps": 64460, "loss": 0.2301, "lr": 7.899622841930261e-06, "epoch": 7.455786534284828, "percentage": 37.28, "elapsed_time": "0:44:01", "remaining_time": "1:14:03", "throughput": 5545.92, "total_tokens": 14647392} {"current_steps": 24035, "total_steps": 64460, "loss": 0.2326, "lr": 7.898519828667981e-06, "epoch": 7.4573378839590445, "percentage": 37.29, "elapsed_time": "0:44:01", "remaining_time": "1:14:03", "throughput": 5545.69, "total_tokens": 14649728} {"current_steps": 24040, "total_steps": 64460, "loss": 0.2225, "lr": 7.897416602909873e-06, "epoch": 7.458889233633261, "percentage": 37.29, "elapsed_time": "0:44:02", "remaining_time": "1:14:02", "throughput": 5545.59, "total_tokens": 14651968} {"current_steps": 24045, "total_steps": 64460, "loss": 0.2242, "lr": 7.896313164736817e-06, "epoch": 7.460440583307477, "percentage": 37.3, "elapsed_time": "0:44:02", "remaining_time": "1:14:01", "throughput": 5545.47, "total_tokens": 14654432} {"current_steps": 24050, "total_steps": 64460, "loss": 0.2328, "lr": 7.895209514229711e-06, "epoch": 7.461991932981694, "percentage": 37.31, "elapsed_time": "0:44:03", "remaining_time": "1:14:01", "throughput": 5545.53, "total_tokens": 14657472} {"current_steps": 24055, "total_steps": 64460, "loss": 0.2335, "lr": 7.894105651469462e-06, "epoch": 7.463543282655911, "percentage": 37.32, "elapsed_time": "0:44:03", "remaining_time": "1:14:00", "throughput": 5545.56, "total_tokens": 14660192} {"current_steps": 24060, "total_steps": 64460, "loss": 0.2363, "lr": 7.893001576536997e-06, "epoch": 7.4650946323301275, "percentage": 37.33, "elapsed_time": "0:44:04", "remaining_time": "1:13:59", "throughput": 5545.64, "total_tokens": 14663328} {"current_steps": 24065, "total_steps": 64460, "loss": 0.2239, "lr": 7.89189728951326e-06, "epoch": 7.466645982004343, "percentage": 37.33, "elapsed_time": "0:44:04", "remaining_time": "1:13:59", "throughput": 5545.72, "total_tokens": 14666112} {"current_steps": 24070, "total_steps": 64460, "loss": 0.2425, "lr": 7.890792790479204e-06, "epoch": 7.46819733167856, "percentage": 37.34, "elapsed_time": "0:44:05", "remaining_time": "1:13:58", "throughput": 5545.82, "total_tokens": 14669152} {"current_steps": 24075, "total_steps": 64460, "loss": 0.2213, "lr": 7.889688079515805e-06, "epoch": 7.469748681352777, "percentage": 37.35, "elapsed_time": "0:44:05", "remaining_time": "1:13:57", "throughput": 5545.88, "total_tokens": 14672256} {"current_steps": 24080, "total_steps": 64460, "loss": 0.2283, "lr": 7.888583156704051e-06, "epoch": 7.471300031026994, "percentage": 37.36, "elapsed_time": "0:44:06", "remaining_time": "1:13:57", "throughput": 5545.89, "total_tokens": 14675008} {"current_steps": 24085, "total_steps": 64460, "loss": 0.2321, "lr": 7.887478022124946e-06, "epoch": 7.4728513807012105, "percentage": 37.36, "elapsed_time": "0:44:06", "remaining_time": "1:13:56", "throughput": 5545.97, "total_tokens": 14677920} {"current_steps": 24090, "total_steps": 64460, "loss": 0.2308, "lr": 7.886372675859508e-06, "epoch": 7.474402730375426, "percentage": 37.37, "elapsed_time": "0:44:07", "remaining_time": "1:13:56", "throughput": 5546.06, "total_tokens": 14681056} {"current_steps": 24095, "total_steps": 64460, "loss": 0.2274, "lr": 7.885267117988774e-06, "epoch": 7.475954080049643, "percentage": 37.38, "elapsed_time": "0:44:07", "remaining_time": "1:13:55", "throughput": 5546.26, "total_tokens": 14685376} {"current_steps": 24100, "total_steps": 64460, "loss": 0.2271, "lr": 7.884161348593794e-06, "epoch": 7.47750542972386, "percentage": 37.39, "elapsed_time": "0:44:08", "remaining_time": "1:13:55", "throughput": 5546.47, "total_tokens": 14689376} {"current_steps": 24105, "total_steps": 64460, "loss": 0.2333, "lr": 7.883055367755632e-06, "epoch": 7.479056779398077, "percentage": 37.4, "elapsed_time": "0:44:08", "remaining_time": "1:13:54", "throughput": 5546.54, "total_tokens": 14692256} {"current_steps": 24110, "total_steps": 64460, "loss": 0.2322, "lr": 7.881949175555372e-06, "epoch": 7.4806081290722926, "percentage": 37.4, "elapsed_time": "0:44:09", "remaining_time": "1:13:53", "throughput": 5546.64, "total_tokens": 14695200} {"current_steps": 24115, "total_steps": 64460, "loss": 0.2339, "lr": 7.880842772074112e-06, "epoch": 7.482159478746509, "percentage": 37.41, "elapsed_time": "0:44:10", "remaining_time": "1:13:53", "throughput": 5546.9, "total_tokens": 14699456} {"current_steps": 24120, "total_steps": 64460, "loss": 0.2343, "lr": 7.879736157392959e-06, "epoch": 7.483710828420726, "percentage": 37.42, "elapsed_time": "0:44:10", "remaining_time": "1:13:53", "throughput": 5547.0, "total_tokens": 14703360} {"current_steps": 24125, "total_steps": 64460, "loss": 0.2311, "lr": 7.878629331593047e-06, "epoch": 7.485262178094943, "percentage": 37.43, "elapsed_time": "0:44:11", "remaining_time": "1:13:52", "throughput": 5546.98, "total_tokens": 14706176} {"current_steps": 24130, "total_steps": 64460, "loss": 0.228, "lr": 7.877522294755515e-06, "epoch": 7.486813527769159, "percentage": 37.43, "elapsed_time": "0:44:11", "remaining_time": "1:13:51", "throughput": 5546.83, "total_tokens": 14708544} {"current_steps": 24135, "total_steps": 64460, "loss": 0.2229, "lr": 7.876415046961525e-06, "epoch": 7.4883648774433755, "percentage": 37.44, "elapsed_time": "0:44:12", "remaining_time": "1:13:51", "throughput": 5547.06, "total_tokens": 14713536} {"current_steps": 24140, "total_steps": 64460, "loss": 0.2353, "lr": 7.87530758829225e-06, "epoch": 7.489916227117592, "percentage": 37.45, "elapsed_time": "0:44:12", "remaining_time": "1:13:51", "throughput": 5546.86, "total_tokens": 14715488} {"current_steps": 24145, "total_steps": 64460, "loss": 0.2322, "lr": 7.874199918828882e-06, "epoch": 7.491467576791809, "percentage": 37.46, "elapsed_time": "0:44:13", "remaining_time": "1:13:50", "throughput": 5547.14, "total_tokens": 14719424} {"current_steps": 24150, "total_steps": 64460, "loss": 0.2321, "lr": 7.873092038652621e-06, "epoch": 7.493018926466026, "percentage": 37.47, "elapsed_time": "0:44:14", "remaining_time": "1:13:49", "throughput": 5547.17, "total_tokens": 14722240} {"current_steps": 24155, "total_steps": 64460, "loss": 0.23, "lr": 7.871983947844693e-06, "epoch": 7.494570276140242, "percentage": 37.47, "elapsed_time": "0:44:14", "remaining_time": "1:13:49", "throughput": 5547.38, "total_tokens": 14725888} {"current_steps": 24160, "total_steps": 64460, "loss": 0.2377, "lr": 7.870875646486333e-06, "epoch": 7.4961216258144585, "percentage": 37.48, "elapsed_time": "0:44:15", "remaining_time": "1:13:48", "throughput": 5547.24, "total_tokens": 14728032} {"current_steps": 24165, "total_steps": 64460, "loss": 0.2339, "lr": 7.86976713465879e-06, "epoch": 7.497672975488675, "percentage": 37.49, "elapsed_time": "0:44:15", "remaining_time": "1:13:48", "throughput": 5547.29, "total_tokens": 14730848} {"current_steps": 24170, "total_steps": 64460, "loss": 0.2331, "lr": 7.868658412443334e-06, "epoch": 7.499224325162892, "percentage": 37.5, "elapsed_time": "0:44:16", "remaining_time": "1:13:47", "throughput": 5547.5, "total_tokens": 14734656} {"current_steps": 24175, "total_steps": 64460, "loss": 0.231, "lr": 7.867549479921246e-06, "epoch": 7.500775674837108, "percentage": 37.5, "elapsed_time": "0:44:16", "remaining_time": "1:13:46", "throughput": 5547.46, "total_tokens": 14737088} {"current_steps": 24180, "total_steps": 64460, "loss": 0.2315, "lr": 7.866440337173824e-06, "epoch": 7.502327024511325, "percentage": 37.51, "elapsed_time": "0:44:17", "remaining_time": "1:13:46", "throughput": 5547.44, "total_tokens": 14739616} {"current_steps": 24185, "total_steps": 64460, "loss": 0.2299, "lr": 7.865330984282383e-06, "epoch": 7.5038783741855415, "percentage": 37.52, "elapsed_time": "0:44:17", "remaining_time": "1:13:45", "throughput": 5547.6, "total_tokens": 14742912} {"current_steps": 24190, "total_steps": 64460, "loss": 0.23, "lr": 7.864221421328248e-06, "epoch": 7.505429723859758, "percentage": 37.53, "elapsed_time": "0:44:17", "remaining_time": "1:13:44", "throughput": 5547.57, "total_tokens": 14745408} {"current_steps": 24195, "total_steps": 64460, "loss": 0.2357, "lr": 7.863111648392767e-06, "epoch": 7.506981073533975, "percentage": 37.53, "elapsed_time": "0:44:18", "remaining_time": "1:13:44", "throughput": 5547.3, "total_tokens": 14747584} {"current_steps": 24200, "total_steps": 64460, "loss": 0.228, "lr": 7.862001665557297e-06, "epoch": 7.508532423208191, "percentage": 37.54, "elapsed_time": "0:44:19", "remaining_time": "1:13:43", "throughput": 5547.48, "total_tokens": 14751328} {"current_steps": 24205, "total_steps": 64460, "loss": 0.2294, "lr": 7.860891472903214e-06, "epoch": 7.510083772882408, "percentage": 37.55, "elapsed_time": "0:44:19", "remaining_time": "1:13:43", "throughput": 5547.64, "total_tokens": 14754656} {"current_steps": 24210, "total_steps": 64460, "loss": 0.2285, "lr": 7.859781070511907e-06, "epoch": 7.5116351225566245, "percentage": 37.56, "elapsed_time": "0:44:20", "remaining_time": "1:13:42", "throughput": 5547.77, "total_tokens": 14758368} {"current_steps": 24215, "total_steps": 64460, "loss": 0.2279, "lr": 7.858670458464783e-06, "epoch": 7.51318647223084, "percentage": 37.57, "elapsed_time": "0:44:20", "remaining_time": "1:13:42", "throughput": 5547.71, "total_tokens": 14760704} {"current_steps": 24220, "total_steps": 64460, "loss": 0.233, "lr": 7.857559636843263e-06, "epoch": 7.514737821905057, "percentage": 37.57, "elapsed_time": "0:44:21", "remaining_time": "1:13:41", "throughput": 5547.43, "total_tokens": 14762976} {"current_steps": 24225, "total_steps": 64460, "loss": 0.2266, "lr": 7.856448605728784e-06, "epoch": 7.516289171579274, "percentage": 37.58, "elapsed_time": "0:44:21", "remaining_time": "1:13:40", "throughput": 5547.53, "total_tokens": 14766240} {"current_steps": 24230, "total_steps": 64460, "loss": 0.232, "lr": 7.855337365202796e-06, "epoch": 7.517840521253491, "percentage": 37.59, "elapsed_time": "0:44:22", "remaining_time": "1:13:40", "throughput": 5547.32, "total_tokens": 14768160} {"current_steps": 24235, "total_steps": 64460, "loss": 0.2353, "lr": 7.854225915346768e-06, "epoch": 7.5193918709277074, "percentage": 37.6, "elapsed_time": "0:44:22", "remaining_time": "1:13:39", "throughput": 5547.48, "total_tokens": 14771488} {"current_steps": 24240, "total_steps": 64460, "loss": 0.2289, "lr": 7.85311425624218e-06, "epoch": 7.520943220601923, "percentage": 37.6, "elapsed_time": "0:44:23", "remaining_time": "1:13:38", "throughput": 5547.58, "total_tokens": 14774464} {"current_steps": 24245, "total_steps": 64460, "loss": 0.232, "lr": 7.852002387970532e-06, "epoch": 7.52249457027614, "percentage": 37.61, "elapsed_time": "0:44:23", "remaining_time": "1:13:38", "throughput": 5547.44, "total_tokens": 14776672} {"current_steps": 24250, "total_steps": 64460, "loss": 0.2238, "lr": 7.850890310613335e-06, "epoch": 7.524045919950357, "percentage": 37.62, "elapsed_time": "0:44:24", "remaining_time": "1:13:37", "throughput": 5547.51, "total_tokens": 14779680} {"current_steps": 24255, "total_steps": 64460, "loss": 0.2275, "lr": 7.849778024252119e-06, "epoch": 7.525597269624574, "percentage": 37.63, "elapsed_time": "0:44:24", "remaining_time": "1:13:37", "throughput": 5547.67, "total_tokens": 14782976} {"current_steps": 24260, "total_steps": 64460, "loss": 0.2275, "lr": 7.848665528968429e-06, "epoch": 7.52714861929879, "percentage": 37.64, "elapsed_time": "0:44:25", "remaining_time": "1:13:36", "throughput": 5547.7, "total_tokens": 14785984} {"current_steps": 24265, "total_steps": 64460, "loss": 0.2313, "lr": 7.847552824843821e-06, "epoch": 7.528699968973006, "percentage": 37.64, "elapsed_time": "0:44:25", "remaining_time": "1:13:35", "throughput": 5547.69, "total_tokens": 14788576} {"current_steps": 24270, "total_steps": 64460, "loss": 0.2258, "lr": 7.846439911959871e-06, "epoch": 7.530251318647223, "percentage": 37.65, "elapsed_time": "0:44:26", "remaining_time": "1:13:35", "throughput": 5547.63, "total_tokens": 14791040} {"current_steps": 24275, "total_steps": 64460, "loss": 0.2341, "lr": 7.845326790398168e-06, "epoch": 7.53180266832144, "percentage": 37.66, "elapsed_time": "0:44:26", "remaining_time": "1:13:34", "throughput": 5547.75, "total_tokens": 14794336} {"current_steps": 24280, "total_steps": 64460, "loss": 0.227, "lr": 7.844213460240318e-06, "epoch": 7.533354017995656, "percentage": 37.67, "elapsed_time": "0:44:27", "remaining_time": "1:13:34", "throughput": 5547.93, "total_tokens": 14798240} {"current_steps": 24285, "total_steps": 64460, "loss": 0.2302, "lr": 7.843099921567942e-06, "epoch": 7.5349053676698725, "percentage": 37.67, "elapsed_time": "0:44:27", "remaining_time": "1:13:33", "throughput": 5548.19, "total_tokens": 14802272} {"current_steps": 24290, "total_steps": 64460, "loss": 0.2363, "lr": 7.841986174462672e-06, "epoch": 7.536456717344089, "percentage": 37.68, "elapsed_time": "0:44:28", "remaining_time": "1:13:32", "throughput": 5548.12, "total_tokens": 14804768} {"current_steps": 24295, "total_steps": 64460, "loss": 0.2379, "lr": 7.840872219006164e-06, "epoch": 7.538008067018306, "percentage": 37.69, "elapsed_time": "0:44:28", "remaining_time": "1:13:32", "throughput": 5548.13, "total_tokens": 14807360} {"current_steps": 24300, "total_steps": 64460, "loss": 0.2309, "lr": 7.83975805528008e-06, "epoch": 7.539559416692523, "percentage": 37.7, "elapsed_time": "0:44:29", "remaining_time": "1:13:31", "throughput": 5548.03, "total_tokens": 14809728} {"current_steps": 24305, "total_steps": 64460, "loss": 0.231, "lr": 7.838643683366103e-06, "epoch": 7.541110766366739, "percentage": 37.71, "elapsed_time": "0:44:29", "remaining_time": "1:13:30", "throughput": 5548.08, "total_tokens": 14812448} {"current_steps": 24310, "total_steps": 64460, "loss": 0.2301, "lr": 7.83752910334593e-06, "epoch": 7.5426621160409555, "percentage": 37.71, "elapsed_time": "0:44:30", "remaining_time": "1:13:30", "throughput": 5548.17, "total_tokens": 14815424} {"current_steps": 24315, "total_steps": 64460, "loss": 0.2276, "lr": 7.83641431530127e-06, "epoch": 7.544213465715172, "percentage": 37.72, "elapsed_time": "0:44:30", "remaining_time": "1:13:29", "throughput": 5548.37, "total_tokens": 14819040} {"current_steps": 24320, "total_steps": 64460, "loss": 0.2302, "lr": 7.835299319313854e-06, "epoch": 7.545764815389389, "percentage": 37.73, "elapsed_time": "0:44:31", "remaining_time": "1:13:29", "throughput": 5548.47, "total_tokens": 14822368} {"current_steps": 24325, "total_steps": 64460, "loss": 0.2283, "lr": 7.834184115465424e-06, "epoch": 7.547316165063606, "percentage": 37.74, "elapsed_time": "0:44:31", "remaining_time": "1:13:28", "throughput": 5548.5, "total_tokens": 14825248} {"current_steps": 24330, "total_steps": 64460, "loss": 0.2355, "lr": 7.833068703837737e-06, "epoch": 7.548867514737822, "percentage": 37.74, "elapsed_time": "0:44:32", "remaining_time": "1:13:27", "throughput": 5548.38, "total_tokens": 14827360} {"current_steps": 24335, "total_steps": 64460, "loss": 0.2313, "lr": 7.831953084512562e-06, "epoch": 7.5504188644120385, "percentage": 37.75, "elapsed_time": "0:44:32", "remaining_time": "1:13:27", "throughput": 5548.49, "total_tokens": 14830432} {"current_steps": 24340, "total_steps": 64460, "loss": 0.2345, "lr": 7.830837257571693e-06, "epoch": 7.551970214086255, "percentage": 37.76, "elapsed_time": "0:44:33", "remaining_time": "1:13:26", "throughput": 5548.6, "total_tokens": 14833440} {"current_steps": 24345, "total_steps": 64460, "loss": 0.2272, "lr": 7.829721223096931e-06, "epoch": 7.553521563760471, "percentage": 37.77, "elapsed_time": "0:44:33", "remaining_time": "1:13:25", "throughput": 5548.84, "total_tokens": 14837056} {"current_steps": 24350, "total_steps": 64460, "loss": 0.2393, "lr": 7.828604981170094e-06, "epoch": 7.555072913434688, "percentage": 37.78, "elapsed_time": "0:44:34", "remaining_time": "1:13:25", "throughput": 5548.96, "total_tokens": 14840384} {"current_steps": 24355, "total_steps": 64460, "loss": 0.2339, "lr": 7.827488531873016e-06, "epoch": 7.556624263108905, "percentage": 37.78, "elapsed_time": "0:44:34", "remaining_time": "1:13:24", "throughput": 5549.15, "total_tokens": 14843968} {"current_steps": 24360, "total_steps": 64460, "loss": 0.2289, "lr": 7.826371875287546e-06, "epoch": 7.5581756127831214, "percentage": 37.79, "elapsed_time": "0:44:35", "remaining_time": "1:13:24", "throughput": 5549.3, "total_tokens": 14847328} {"current_steps": 24365, "total_steps": 64460, "loss": 0.2285, "lr": 7.82525501149555e-06, "epoch": 7.559726962457338, "percentage": 37.8, "elapsed_time": "0:44:36", "remaining_time": "1:13:23", "throughput": 5549.68, "total_tokens": 14852032} {"current_steps": 24370, "total_steps": 64460, "loss": 0.2306, "lr": 7.824137940578905e-06, "epoch": 7.561278312131554, "percentage": 37.81, "elapsed_time": "0:44:36", "remaining_time": "1:13:23", "throughput": 5549.61, "total_tokens": 14854496} {"current_steps": 24375, "total_steps": 64460, "loss": 0.2322, "lr": 7.823020662619503e-06, "epoch": 7.562829661805771, "percentage": 37.81, "elapsed_time": "0:44:37", "remaining_time": "1:13:22", "throughput": 5549.65, "total_tokens": 14857440} {"current_steps": 24380, "total_steps": 64460, "loss": 0.2373, "lr": 7.82190317769926e-06, "epoch": 7.564381011479988, "percentage": 37.82, "elapsed_time": "0:44:37", "remaining_time": "1:13:21", "throughput": 5549.73, "total_tokens": 14860288} {"current_steps": 24385, "total_steps": 64460, "loss": 0.2341, "lr": 7.820785485900098e-06, "epoch": 7.565932361154204, "percentage": 37.83, "elapsed_time": "0:44:38", "remaining_time": "1:13:21", "throughput": 5549.81, "total_tokens": 14863200} {"current_steps": 24390, "total_steps": 64460, "loss": 0.2332, "lr": 7.819667587303954e-06, "epoch": 7.567483710828421, "percentage": 37.84, "elapsed_time": "0:44:38", "remaining_time": "1:13:20", "throughput": 5549.67, "total_tokens": 14865312} {"current_steps": 24395, "total_steps": 64460, "loss": 0.2327, "lr": 7.818549481992788e-06, "epoch": 7.569035060502637, "percentage": 37.85, "elapsed_time": "0:44:39", "remaining_time": "1:13:19", "throughput": 5549.66, "total_tokens": 14867872} {"current_steps": 24400, "total_steps": 64460, "loss": 0.2296, "lr": 7.817431170048568e-06, "epoch": 7.570586410176854, "percentage": 37.85, "elapsed_time": "0:44:39", "remaining_time": "1:13:19", "throughput": 5549.83, "total_tokens": 14871040} {"current_steps": 24405, "total_steps": 64460, "loss": 0.2314, "lr": 7.816312651553279e-06, "epoch": 7.572137759851071, "percentage": 37.86, "elapsed_time": "0:44:40", "remaining_time": "1:13:18", "throughput": 5549.84, "total_tokens": 14873888} {"current_steps": 24410, "total_steps": 64460, "loss": 0.2347, "lr": 7.815193926588925e-06, "epoch": 7.5736891095252865, "percentage": 37.87, "elapsed_time": "0:44:40", "remaining_time": "1:13:18", "throughput": 5550.03, "total_tokens": 14877600} {"current_steps": 24415, "total_steps": 64460, "loss": 0.2325, "lr": 7.814074995237517e-06, "epoch": 7.575240459199503, "percentage": 37.88, "elapsed_time": "0:44:41", "remaining_time": "1:13:17", "throughput": 5549.93, "total_tokens": 14879872} {"current_steps": 24420, "total_steps": 64460, "loss": 0.2305, "lr": 7.812955857581089e-06, "epoch": 7.57679180887372, "percentage": 37.88, "elapsed_time": "0:44:41", "remaining_time": "1:13:16", "throughput": 5550.11, "total_tokens": 14883392} {"current_steps": 24425, "total_steps": 64460, "loss": 0.2249, "lr": 7.811836513701686e-06, "epoch": 7.578343158547937, "percentage": 37.89, "elapsed_time": "0:44:42", "remaining_time": "1:13:16", "throughput": 5550.31, "total_tokens": 14886944} {"current_steps": 24430, "total_steps": 64460, "loss": 0.2309, "lr": 7.810716963681371e-06, "epoch": 7.579894508222154, "percentage": 37.9, "elapsed_time": "0:44:42", "remaining_time": "1:13:15", "throughput": 5550.27, "total_tokens": 14889504} {"current_steps": 24435, "total_steps": 64460, "loss": 0.2329, "lr": 7.809597207602218e-06, "epoch": 7.5814458578963695, "percentage": 37.91, "elapsed_time": "0:44:43", "remaining_time": "1:13:15", "throughput": 5550.34, "total_tokens": 14892384} {"current_steps": 24440, "total_steps": 64460, "loss": 0.2325, "lr": 7.808477245546317e-06, "epoch": 7.582997207570586, "percentage": 37.91, "elapsed_time": "0:44:43", "remaining_time": "1:13:14", "throughput": 5550.26, "total_tokens": 14894720} {"current_steps": 24445, "total_steps": 64460, "loss": 0.2346, "lr": 7.807357077595778e-06, "epoch": 7.584548557244803, "percentage": 37.92, "elapsed_time": "0:44:44", "remaining_time": "1:13:13", "throughput": 5550.44, "total_tokens": 14898400} {"current_steps": 24450, "total_steps": 64460, "loss": 0.2275, "lr": 7.806236703832722e-06, "epoch": 7.58609990691902, "percentage": 37.93, "elapsed_time": "0:44:44", "remaining_time": "1:13:13", "throughput": 5550.31, "total_tokens": 14900928} {"current_steps": 24455, "total_steps": 64460, "loss": 0.2321, "lr": 7.805116124339283e-06, "epoch": 7.587651256593237, "percentage": 37.94, "elapsed_time": "0:44:45", "remaining_time": "1:13:12", "throughput": 5550.19, "total_tokens": 14903744} {"current_steps": 24460, "total_steps": 64460, "loss": 0.2354, "lr": 7.803995339197616e-06, "epoch": 7.5892026062674525, "percentage": 37.95, "elapsed_time": "0:44:45", "remaining_time": "1:13:12", "throughput": 5550.23, "total_tokens": 14906656} {"current_steps": 24465, "total_steps": 64460, "loss": 0.23, "lr": 7.802874348489887e-06, "epoch": 7.590753955941669, "percentage": 37.95, "elapsed_time": "0:44:46", "remaining_time": "1:13:11", "throughput": 5550.28, "total_tokens": 14909664} {"current_steps": 24470, "total_steps": 64460, "loss": 0.228, "lr": 7.801753152298274e-06, "epoch": 7.592305305615886, "percentage": 37.96, "elapsed_time": "0:44:46", "remaining_time": "1:13:10", "throughput": 5550.39, "total_tokens": 14912800} {"current_steps": 24475, "total_steps": 64460, "loss": 0.2269, "lr": 7.800631750704982e-06, "epoch": 7.593856655290102, "percentage": 37.97, "elapsed_time": "0:44:47", "remaining_time": "1:13:10", "throughput": 5550.38, "total_tokens": 14915488} {"current_steps": 24480, "total_steps": 64460, "loss": 0.2344, "lr": 7.799510143792214e-06, "epoch": 7.595408004964319, "percentage": 37.98, "elapsed_time": "0:44:47", "remaining_time": "1:13:09", "throughput": 5550.7, "total_tokens": 14919936} {"current_steps": 24485, "total_steps": 64460, "loss": 0.2337, "lr": 7.798388331642203e-06, "epoch": 7.5969593546385354, "percentage": 37.98, "elapsed_time": "0:44:48", "remaining_time": "1:13:09", "throughput": 5550.68, "total_tokens": 14922496} {"current_steps": 24490, "total_steps": 64460, "loss": 0.2349, "lr": 7.797266314337189e-06, "epoch": 7.598510704312752, "percentage": 37.99, "elapsed_time": "0:44:49", "remaining_time": "1:13:08", "throughput": 5550.87, "total_tokens": 14926816} {"current_steps": 24495, "total_steps": 64460, "loss": 0.2316, "lr": 7.79614409195943e-06, "epoch": 7.600062053986969, "percentage": 38.0, "elapsed_time": "0:44:49", "remaining_time": "1:13:08", "throughput": 5550.94, "total_tokens": 14929952} {"current_steps": 24500, "total_steps": 64460, "loss": 0.2294, "lr": 7.795021664591198e-06, "epoch": 7.601613403661185, "percentage": 38.01, "elapsed_time": "0:44:50", "remaining_time": "1:13:07", "throughput": 5550.87, "total_tokens": 14932576} {"current_steps": 24505, "total_steps": 64460, "loss": 0.2379, "lr": 7.79389903231478e-06, "epoch": 7.603164753335402, "percentage": 38.02, "elapsed_time": "0:44:50", "remaining_time": "1:13:07", "throughput": 5551.05, "total_tokens": 14936160} {"current_steps": 24510, "total_steps": 64460, "loss": 0.2358, "lr": 7.792776195212477e-06, "epoch": 7.604716103009618, "percentage": 38.02, "elapsed_time": "0:44:51", "remaining_time": "1:13:06", "throughput": 5551.36, "total_tokens": 14940320} {"current_steps": 24515, "total_steps": 64460, "loss": 0.2309, "lr": 7.791653153366608e-06, "epoch": 7.606267452683835, "percentage": 38.03, "elapsed_time": "0:44:51", "remaining_time": "1:13:05", "throughput": 5551.41, "total_tokens": 14943104} {"current_steps": 24520, "total_steps": 64460, "loss": 0.2331, "lr": 7.790529906859505e-06, "epoch": 7.607818802358052, "percentage": 38.04, "elapsed_time": "0:44:52", "remaining_time": "1:13:05", "throughput": 5551.41, "total_tokens": 14945792} {"current_steps": 24525, "total_steps": 64460, "loss": 0.2341, "lr": 7.789406455773516e-06, "epoch": 7.609370152032268, "percentage": 38.05, "elapsed_time": "0:44:52", "remaining_time": "1:13:04", "throughput": 5551.27, "total_tokens": 14948480} {"current_steps": 24530, "total_steps": 64460, "loss": 0.2196, "lr": 7.788282800191e-06, "epoch": 7.610921501706485, "percentage": 38.05, "elapsed_time": "0:44:53", "remaining_time": "1:13:04", "throughput": 5551.25, "total_tokens": 14951264} {"current_steps": 24535, "total_steps": 64460, "loss": 0.2389, "lr": 7.78715894019434e-06, "epoch": 7.612472851380701, "percentage": 38.06, "elapsed_time": "0:44:53", "remaining_time": "1:13:03", "throughput": 5551.35, "total_tokens": 14954368} {"current_steps": 24540, "total_steps": 64460, "loss": 0.2298, "lr": 7.786034875865921e-06, "epoch": 7.614024201054917, "percentage": 38.07, "elapsed_time": "0:44:54", "remaining_time": "1:13:02", "throughput": 5551.44, "total_tokens": 14957344} {"current_steps": 24545, "total_steps": 64460, "loss": 0.2304, "lr": 7.784910607288157e-06, "epoch": 7.615575550729134, "percentage": 38.08, "elapsed_time": "0:44:54", "remaining_time": "1:13:02", "throughput": 5551.68, "total_tokens": 14961152} {"current_steps": 24550, "total_steps": 64460, "loss": 0.2348, "lr": 7.783786134543465e-06, "epoch": 7.617126900403351, "percentage": 38.09, "elapsed_time": "0:44:55", "remaining_time": "1:13:01", "throughput": 5551.52, "total_tokens": 14963776} {"current_steps": 24555, "total_steps": 64460, "loss": 0.2365, "lr": 7.782661457714285e-06, "epoch": 7.618678250077568, "percentage": 38.09, "elapsed_time": "0:44:55", "remaining_time": "1:13:01", "throughput": 5551.62, "total_tokens": 14966752} {"current_steps": 24560, "total_steps": 64460, "loss": 0.2336, "lr": 7.781536576883068e-06, "epoch": 7.620229599751784, "percentage": 38.1, "elapsed_time": "0:44:56", "remaining_time": "1:13:00", "throughput": 5551.9, "total_tokens": 14971328} {"current_steps": 24565, "total_steps": 64460, "loss": 0.2279, "lr": 7.780411492132284e-06, "epoch": 7.621780949426, "percentage": 38.11, "elapsed_time": "0:44:57", "remaining_time": "1:13:00", "throughput": 5551.95, "total_tokens": 14974240} {"current_steps": 24570, "total_steps": 64460, "loss": 0.2343, "lr": 7.77928620354441e-06, "epoch": 7.623332299100217, "percentage": 38.12, "elapsed_time": "0:44:57", "remaining_time": "1:12:59", "throughput": 5552.0, "total_tokens": 14977024} {"current_steps": 24575, "total_steps": 64460, "loss": 0.2334, "lr": 7.778160711201948e-06, "epoch": 7.624883648774434, "percentage": 38.12, "elapsed_time": "0:44:58", "remaining_time": "1:12:58", "throughput": 5551.95, "total_tokens": 14979552} {"current_steps": 24580, "total_steps": 64460, "loss": 0.2278, "lr": 7.777035015187403e-06, "epoch": 7.626434998448651, "percentage": 38.13, "elapsed_time": "0:44:58", "remaining_time": "1:12:58", "throughput": 5552.03, "total_tokens": 14982368} {"current_steps": 24585, "total_steps": 64460, "loss": 0.227, "lr": 7.775909115583311e-06, "epoch": 7.627986348122867, "percentage": 38.14, "elapsed_time": "0:44:59", "remaining_time": "1:12:57", "throughput": 5552.08, "total_tokens": 14985248} {"current_steps": 24590, "total_steps": 64460, "loss": 0.2305, "lr": 7.774783012472208e-06, "epoch": 7.629537697797083, "percentage": 38.15, "elapsed_time": "0:44:59", "remaining_time": "1:12:57", "throughput": 5552.24, "total_tokens": 14988544} {"current_steps": 24595, "total_steps": 64460, "loss": 0.2297, "lr": 7.773656705936651e-06, "epoch": 7.6310890474713, "percentage": 38.16, "elapsed_time": "0:45:00", "remaining_time": "1:12:56", "throughput": 5552.15, "total_tokens": 14990880} {"current_steps": 24600, "total_steps": 64460, "loss": 0.2369, "lr": 7.772530196059214e-06, "epoch": 7.632640397145517, "percentage": 38.16, "elapsed_time": "0:45:00", "remaining_time": "1:12:55", "throughput": 5552.11, "total_tokens": 14993632} {"current_steps": 24605, "total_steps": 64460, "loss": 0.2379, "lr": 7.771403482922479e-06, "epoch": 7.634191746819733, "percentage": 38.17, "elapsed_time": "0:45:00", "remaining_time": "1:12:55", "throughput": 5552.0, "total_tokens": 14995872} {"current_steps": 24610, "total_steps": 64460, "loss": 0.2375, "lr": 7.770276566609055e-06, "epoch": 7.6357430964939494, "percentage": 38.18, "elapsed_time": "0:45:01", "remaining_time": "1:12:54", "throughput": 5552.2, "total_tokens": 14999488} {"current_steps": 24615, "total_steps": 64460, "loss": 0.2263, "lr": 7.76914944720155e-06, "epoch": 7.637294446168166, "percentage": 38.19, "elapsed_time": "0:45:02", "remaining_time": "1:12:54", "throughput": 5552.49, "total_tokens": 15003584} {"current_steps": 24620, "total_steps": 64460, "loss": 0.2377, "lr": 7.7680221247826e-06, "epoch": 7.638845795842383, "percentage": 38.19, "elapsed_time": "0:45:02", "remaining_time": "1:12:53", "throughput": 5552.38, "total_tokens": 15005856} {"current_steps": 24625, "total_steps": 64460, "loss": 0.226, "lr": 7.76689459943485e-06, "epoch": 7.6403971455166, "percentage": 38.2, "elapsed_time": "0:45:03", "remaining_time": "1:12:52", "throughput": 5552.43, "total_tokens": 15008768} {"current_steps": 24630, "total_steps": 64460, "loss": 0.239, "lr": 7.76576687124096e-06, "epoch": 7.641948495190816, "percentage": 38.21, "elapsed_time": "0:45:03", "remaining_time": "1:12:52", "throughput": 5552.46, "total_tokens": 15011488} {"current_steps": 24635, "total_steps": 64460, "loss": 0.2241, "lr": 7.764638940283606e-06, "epoch": 7.643499844865032, "percentage": 38.22, "elapsed_time": "0:45:04", "remaining_time": "1:12:51", "throughput": 5552.61, "total_tokens": 15014752} {"current_steps": 24640, "total_steps": 64460, "loss": 0.2353, "lr": 7.763510806645483e-06, "epoch": 7.645051194539249, "percentage": 38.23, "elapsed_time": "0:45:04", "remaining_time": "1:12:50", "throughput": 5552.63, "total_tokens": 15017504} {"current_steps": 24645, "total_steps": 64460, "loss": 0.2269, "lr": 7.762382470409291e-06, "epoch": 7.646602544213466, "percentage": 38.23, "elapsed_time": "0:45:05", "remaining_time": "1:12:50", "throughput": 5552.62, "total_tokens": 15020320} {"current_steps": 24650, "total_steps": 64460, "loss": 0.2324, "lr": 7.761253931657752e-06, "epoch": 7.648153893887683, "percentage": 38.24, "elapsed_time": "0:45:05", "remaining_time": "1:12:49", "throughput": 5552.79, "total_tokens": 15023936} {"current_steps": 24655, "total_steps": 64460, "loss": 0.2313, "lr": 7.760125190473602e-06, "epoch": 7.649705243561899, "percentage": 38.25, "elapsed_time": "0:45:06", "remaining_time": "1:12:49", "throughput": 5553.04, "total_tokens": 15027776} {"current_steps": 24660, "total_steps": 64460, "loss": 0.2313, "lr": 7.758996246939592e-06, "epoch": 7.651256593236115, "percentage": 38.26, "elapsed_time": "0:45:06", "remaining_time": "1:12:48", "throughput": 5553.03, "total_tokens": 15030720} {"current_steps": 24665, "total_steps": 64460, "loss": 0.2293, "lr": 7.757867101138484e-06, "epoch": 7.652807942910332, "percentage": 38.26, "elapsed_time": "0:45:07", "remaining_time": "1:12:48", "throughput": 5553.09, "total_tokens": 15034176} {"current_steps": 24670, "total_steps": 64460, "loss": 0.2303, "lr": 7.756737753153058e-06, "epoch": 7.654359292584548, "percentage": 38.27, "elapsed_time": "0:45:07", "remaining_time": "1:12:47", "throughput": 5552.82, "total_tokens": 15036448} {"current_steps": 24675, "total_steps": 64460, "loss": 0.233, "lr": 7.755608203066113e-06, "epoch": 7.655910642258765, "percentage": 38.28, "elapsed_time": "0:45:08", "remaining_time": "1:12:46", "throughput": 5552.59, "total_tokens": 15038784} {"current_steps": 24680, "total_steps": 64460, "loss": 0.2269, "lr": 7.754478450960453e-06, "epoch": 7.657461991932982, "percentage": 38.29, "elapsed_time": "0:45:08", "remaining_time": "1:12:46", "throughput": 5552.68, "total_tokens": 15041856} {"current_steps": 24685, "total_steps": 64460, "loss": 0.2324, "lr": 7.753348496918906e-06, "epoch": 7.659013341607198, "percentage": 38.3, "elapsed_time": "0:45:09", "remaining_time": "1:12:45", "throughput": 5552.77, "total_tokens": 15044992} {"current_steps": 24690, "total_steps": 64460, "loss": 0.2335, "lr": 7.75221834102431e-06, "epoch": 7.660564691281415, "percentage": 38.3, "elapsed_time": "0:45:09", "remaining_time": "1:12:45", "throughput": 5552.86, "total_tokens": 15048128} {"current_steps": 24695, "total_steps": 64460, "loss": 0.2315, "lr": 7.751087983359518e-06, "epoch": 7.662116040955631, "percentage": 38.31, "elapsed_time": "0:45:10", "remaining_time": "1:12:44", "throughput": 5552.94, "total_tokens": 15051232} {"current_steps": 24700, "total_steps": 64460, "loss": 0.2301, "lr": 7.7499574240074e-06, "epoch": 7.663667390629848, "percentage": 38.32, "elapsed_time": "0:45:11", "remaining_time": "1:12:44", "throughput": 5552.79, "total_tokens": 15053856} {"current_steps": 24705, "total_steps": 64460, "loss": 0.2364, "lr": 7.748826663050837e-06, "epoch": 7.665218740304065, "percentage": 38.33, "elapsed_time": "0:45:11", "remaining_time": "1:12:43", "throughput": 5552.7, "total_tokens": 15056288} {"current_steps": 24710, "total_steps": 64460, "loss": 0.2336, "lr": 7.74769570057273e-06, "epoch": 7.666770089978281, "percentage": 38.33, "elapsed_time": "0:45:11", "remaining_time": "1:12:42", "throughput": 5552.61, "total_tokens": 15058688} {"current_steps": 24715, "total_steps": 64460, "loss": 0.2279, "lr": 7.746564536655989e-06, "epoch": 7.668321439652498, "percentage": 38.34, "elapsed_time": "0:45:12", "remaining_time": "1:12:42", "throughput": 5552.48, "total_tokens": 15061152} {"current_steps": 24720, "total_steps": 64460, "loss": 0.2293, "lr": 7.745433171383545e-06, "epoch": 7.669872789326714, "percentage": 38.35, "elapsed_time": "0:45:13", "remaining_time": "1:12:41", "throughput": 5552.63, "total_tokens": 15064544} {"current_steps": 24725, "total_steps": 64460, "loss": 0.2273, "lr": 7.744301604838337e-06, "epoch": 7.671424139000931, "percentage": 38.36, "elapsed_time": "0:45:13", "remaining_time": "1:12:41", "throughput": 5552.88, "total_tokens": 15068736} {"current_steps": 24730, "total_steps": 64460, "loss": 0.2342, "lr": 7.743169837103327e-06, "epoch": 7.672975488675148, "percentage": 38.36, "elapsed_time": "0:45:14", "remaining_time": "1:12:40", "throughput": 5553.03, "total_tokens": 15072832} {"current_steps": 24735, "total_steps": 64460, "loss": 0.2275, "lr": 7.742037868261481e-06, "epoch": 7.674526838349364, "percentage": 38.37, "elapsed_time": "0:45:15", "remaining_time": "1:12:40", "throughput": 5553.09, "total_tokens": 15077024} {"current_steps": 24740, "total_steps": 64460, "loss": 0.2306, "lr": 7.740905698395788e-06, "epoch": 7.67607818802358, "percentage": 38.38, "elapsed_time": "0:45:15", "remaining_time": "1:12:40", "throughput": 5553.22, "total_tokens": 15081152} {"current_steps": 24745, "total_steps": 64460, "loss": 0.2345, "lr": 7.739773327589252e-06, "epoch": 7.677629537697797, "percentage": 38.39, "elapsed_time": "0:45:16", "remaining_time": "1:12:39", "throughput": 5553.48, "total_tokens": 15085536} {"current_steps": 24750, "total_steps": 64460, "loss": 0.2363, "lr": 7.738640755924886e-06, "epoch": 7.679180887372014, "percentage": 38.4, "elapsed_time": "0:45:16", "remaining_time": "1:12:39", "throughput": 5553.48, "total_tokens": 15088544} {"current_steps": 24755, "total_steps": 64460, "loss": 0.2361, "lr": 7.737507983485724e-06, "epoch": 7.6807322370462305, "percentage": 38.4, "elapsed_time": "0:45:17", "remaining_time": "1:12:38", "throughput": 5553.65, "total_tokens": 15092096} {"current_steps": 24760, "total_steps": 64460, "loss": 0.2303, "lr": 7.73637501035481e-06, "epoch": 7.682283586720446, "percentage": 38.41, "elapsed_time": "0:45:18", "remaining_time": "1:12:38", "throughput": 5553.57, "total_tokens": 15094656} {"current_steps": 24765, "total_steps": 64460, "loss": 0.2283, "lr": 7.735241836615202e-06, "epoch": 7.683834936394663, "percentage": 38.42, "elapsed_time": "0:45:18", "remaining_time": "1:12:37", "throughput": 5553.56, "total_tokens": 15097280} {"current_steps": 24770, "total_steps": 64460, "loss": 0.229, "lr": 7.734108462349978e-06, "epoch": 7.68538628606888, "percentage": 38.43, "elapsed_time": "0:45:18", "remaining_time": "1:12:36", "throughput": 5553.52, "total_tokens": 15100000} {"current_steps": 24775, "total_steps": 64460, "loss": 0.2299, "lr": 7.732974887642228e-06, "epoch": 7.686937635743097, "percentage": 38.43, "elapsed_time": "0:45:19", "remaining_time": "1:12:36", "throughput": 5553.47, "total_tokens": 15102752} {"current_steps": 24780, "total_steps": 64460, "loss": 0.2356, "lr": 7.731841112575056e-06, "epoch": 7.6884889854173135, "percentage": 38.44, "elapsed_time": "0:45:20", "remaining_time": "1:12:35", "throughput": 5553.61, "total_tokens": 15106464} {"current_steps": 24785, "total_steps": 64460, "loss": 0.234, "lr": 7.730707137231578e-06, "epoch": 7.690040335091529, "percentage": 38.45, "elapsed_time": "0:45:20", "remaining_time": "1:12:35", "throughput": 5553.67, "total_tokens": 15109280} {"current_steps": 24790, "total_steps": 64460, "loss": 0.2341, "lr": 7.729572961694933e-06, "epoch": 7.691591684765746, "percentage": 38.46, "elapsed_time": "0:45:21", "remaining_time": "1:12:34", "throughput": 5553.9, "total_tokens": 15112896} {"current_steps": 24795, "total_steps": 64460, "loss": 0.2295, "lr": 7.728438586048265e-06, "epoch": 7.693143034439963, "percentage": 38.47, "elapsed_time": "0:45:21", "remaining_time": "1:12:34", "throughput": 5554.13, "total_tokens": 15117056} {"current_steps": 24800, "total_steps": 64460, "loss": 0.2326, "lr": 7.727304010374741e-06, "epoch": 7.69469438411418, "percentage": 38.47, "elapsed_time": "0:45:22", "remaining_time": "1:12:33", "throughput": 5554.29, "total_tokens": 15120608} {"current_steps": 24805, "total_steps": 64460, "loss": 0.228, "lr": 7.726169234757535e-06, "epoch": 7.696245733788396, "percentage": 38.48, "elapsed_time": "0:45:22", "remaining_time": "1:12:33", "throughput": 5554.2, "total_tokens": 15123776} {"current_steps": 24810, "total_steps": 64460, "loss": 0.2296, "lr": 7.725034259279844e-06, "epoch": 7.697797083462612, "percentage": 38.49, "elapsed_time": "0:45:23", "remaining_time": "1:12:32", "throughput": 5554.36, "total_tokens": 15127232} {"current_steps": 24815, "total_steps": 64460, "loss": 0.2279, "lr": 7.72389908402487e-06, "epoch": 7.699348433136829, "percentage": 38.5, "elapsed_time": "0:45:23", "remaining_time": "1:12:31", "throughput": 5554.35, "total_tokens": 15130048} {"current_steps": 24820, "total_steps": 64460, "loss": 0.2313, "lr": 7.72276370907584e-06, "epoch": 7.700899782811046, "percentage": 38.5, "elapsed_time": "0:45:24", "remaining_time": "1:12:31", "throughput": 5554.57, "total_tokens": 15134304} {"current_steps": 24825, "total_steps": 64460, "loss": 0.2319, "lr": 7.721628134515983e-06, "epoch": 7.702451132485262, "percentage": 38.51, "elapsed_time": "0:45:25", "remaining_time": "1:12:31", "throughput": 5554.94, "total_tokens": 15141088} {"current_steps": 24830, "total_steps": 64460, "loss": 0.2344, "lr": 7.72049236042856e-06, "epoch": 7.704002482159479, "percentage": 38.52, "elapsed_time": "0:45:26", "remaining_time": "1:12:31", "throughput": 5554.7, "total_tokens": 15143232} {"current_steps": 24835, "total_steps": 64460, "loss": 0.2318, "lr": 7.71935638689683e-06, "epoch": 7.705553831833695, "percentage": 38.53, "elapsed_time": "0:45:26", "remaining_time": "1:12:30", "throughput": 5554.85, "total_tokens": 15146528} {"current_steps": 24840, "total_steps": 64460, "loss": 0.2275, "lr": 7.718220214004073e-06, "epoch": 7.707105181507912, "percentage": 38.54, "elapsed_time": "0:45:27", "remaining_time": "1:12:29", "throughput": 5554.7, "total_tokens": 15148896} {"current_steps": 24845, "total_steps": 64460, "loss": 0.2244, "lr": 7.717083841833587e-06, "epoch": 7.708656531182129, "percentage": 38.54, "elapsed_time": "0:45:27", "remaining_time": "1:12:29", "throughput": 5554.84, "total_tokens": 15152512} {"current_steps": 24850, "total_steps": 64460, "loss": 0.2363, "lr": 7.715947270468681e-06, "epoch": 7.710207880856345, "percentage": 38.55, "elapsed_time": "0:45:28", "remaining_time": "1:12:28", "throughput": 5555.05, "total_tokens": 15156384} {"current_steps": 24855, "total_steps": 64460, "loss": 0.2255, "lr": 7.714810499992678e-06, "epoch": 7.711759230530562, "percentage": 38.56, "elapsed_time": "0:45:28", "remaining_time": "1:12:28", "throughput": 5554.86, "total_tokens": 15158656} {"current_steps": 24860, "total_steps": 64460, "loss": 0.23, "lr": 7.713673530488917e-06, "epoch": 7.713310580204778, "percentage": 38.57, "elapsed_time": "0:45:29", "remaining_time": "1:12:27", "throughput": 5554.89, "total_tokens": 15161440} {"current_steps": 24865, "total_steps": 64460, "loss": 0.2338, "lr": 7.712536362040751e-06, "epoch": 7.714861929878995, "percentage": 38.57, "elapsed_time": "0:45:29", "remaining_time": "1:12:27", "throughput": 5554.68, "total_tokens": 15163456} {"current_steps": 24870, "total_steps": 64460, "loss": 0.2265, "lr": 7.71139899473155e-06, "epoch": 7.716413279553211, "percentage": 38.58, "elapsed_time": "0:45:30", "remaining_time": "1:12:26", "throughput": 5554.86, "total_tokens": 15167456} {"current_steps": 24875, "total_steps": 64460, "loss": 0.2358, "lr": 7.710261428644694e-06, "epoch": 7.717964629227428, "percentage": 38.59, "elapsed_time": "0:45:30", "remaining_time": "1:12:25", "throughput": 5554.76, "total_tokens": 15169792} {"current_steps": 24880, "total_steps": 64460, "loss": 0.2218, "lr": 7.70912366386358e-06, "epoch": 7.7195159789016445, "percentage": 38.6, "elapsed_time": "0:45:31", "remaining_time": "1:12:25", "throughput": 5554.99, "total_tokens": 15173536} {"current_steps": 24885, "total_steps": 64460, "loss": 0.2291, "lr": 7.707985700471621e-06, "epoch": 7.721067328575861, "percentage": 38.61, "elapsed_time": "0:45:32", "remaining_time": "1:12:24", "throughput": 5554.96, "total_tokens": 15176576} {"current_steps": 24890, "total_steps": 64460, "loss": 0.2373, "lr": 7.706847538552244e-06, "epoch": 7.722618678250077, "percentage": 38.61, "elapsed_time": "0:45:32", "remaining_time": "1:12:24", "throughput": 5555.23, "total_tokens": 15181472} {"current_steps": 24895, "total_steps": 64460, "loss": 0.2294, "lr": 7.705709178188887e-06, "epoch": 7.724170027924294, "percentage": 38.62, "elapsed_time": "0:45:33", "remaining_time": "1:12:24", "throughput": 5555.23, "total_tokens": 15184640} {"current_steps": 24900, "total_steps": 64460, "loss": 0.2311, "lr": 7.704570619465009e-06, "epoch": 7.725721377598511, "percentage": 38.63, "elapsed_time": "0:45:33", "remaining_time": "1:12:23", "throughput": 5555.28, "total_tokens": 15187904} {"current_steps": 24905, "total_steps": 64460, "loss": 0.2392, "lr": 7.703431862464076e-06, "epoch": 7.7272727272727275, "percentage": 38.64, "elapsed_time": "0:45:34", "remaining_time": "1:12:22", "throughput": 5555.39, "total_tokens": 15191040} {"current_steps": 24910, "total_steps": 64460, "loss": 0.234, "lr": 7.702292907269574e-06, "epoch": 7.728824076946944, "percentage": 38.64, "elapsed_time": "0:45:34", "remaining_time": "1:12:22", "throughput": 5555.44, "total_tokens": 15194016} {"current_steps": 24915, "total_steps": 64460, "loss": 0.2234, "lr": 7.701153753965002e-06, "epoch": 7.73037542662116, "percentage": 38.65, "elapsed_time": "0:45:35", "remaining_time": "1:12:21", "throughput": 5555.27, "total_tokens": 15196128} {"current_steps": 24920, "total_steps": 64460, "loss": 0.2336, "lr": 7.700014402633875e-06, "epoch": 7.731926776295377, "percentage": 38.66, "elapsed_time": "0:45:35", "remaining_time": "1:12:21", "throughput": 5555.23, "total_tokens": 15198656} {"current_steps": 24925, "total_steps": 64460, "loss": 0.2337, "lr": 7.698874853359717e-06, "epoch": 7.733478125969594, "percentage": 38.67, "elapsed_time": "0:45:36", "remaining_time": "1:12:20", "throughput": 5555.3, "total_tokens": 15201696} {"current_steps": 24930, "total_steps": 64460, "loss": 0.2331, "lr": 7.697735106226075e-06, "epoch": 7.7350294756438105, "percentage": 38.68, "elapsed_time": "0:45:36", "remaining_time": "1:12:19", "throughput": 5555.42, "total_tokens": 15204800} {"current_steps": 24935, "total_steps": 64460, "loss": 0.2391, "lr": 7.696595161316501e-06, "epoch": 7.736580825318026, "percentage": 38.68, "elapsed_time": "0:45:37", "remaining_time": "1:12:19", "throughput": 5555.65, "total_tokens": 15208672} {"current_steps": 24940, "total_steps": 64460, "loss": 0.2326, "lr": 7.695455018714571e-06, "epoch": 7.738132174992243, "percentage": 38.69, "elapsed_time": "0:45:38", "remaining_time": "1:12:18", "throughput": 5555.77, "total_tokens": 15212160} {"current_steps": 24945, "total_steps": 64460, "loss": 0.2274, "lr": 7.694314678503869e-06, "epoch": 7.73968352466646, "percentage": 38.7, "elapsed_time": "0:45:38", "remaining_time": "1:12:18", "throughput": 5555.96, "total_tokens": 15215488} {"current_steps": 24950, "total_steps": 64460, "loss": 0.2348, "lr": 7.693174140767996e-06, "epoch": 7.741234874340677, "percentage": 38.71, "elapsed_time": "0:45:39", "remaining_time": "1:12:17", "throughput": 5556.3, "total_tokens": 15220256} {"current_steps": 24955, "total_steps": 64460, "loss": 0.2284, "lr": 7.692033405590567e-06, "epoch": 7.742786224014893, "percentage": 38.71, "elapsed_time": "0:45:39", "remaining_time": "1:12:17", "throughput": 5556.32, "total_tokens": 15223040} {"current_steps": 24960, "total_steps": 64460, "loss": 0.238, "lr": 7.69089247305521e-06, "epoch": 7.744337573689109, "percentage": 38.72, "elapsed_time": "0:45:40", "remaining_time": "1:12:16", "throughput": 5556.54, "total_tokens": 15226912} {"current_steps": 24965, "total_steps": 64460, "loss": 0.2258, "lr": 7.68975134324557e-06, "epoch": 7.745888923363326, "percentage": 38.73, "elapsed_time": "0:45:40", "remaining_time": "1:12:16", "throughput": 5556.5, "total_tokens": 15229568} {"current_steps": 24970, "total_steps": 64460, "loss": 0.2356, "lr": 7.688610016245304e-06, "epoch": 7.747440273037543, "percentage": 38.74, "elapsed_time": "0:45:41", "remaining_time": "1:12:15", "throughput": 5556.57, "total_tokens": 15232416} {"current_steps": 24975, "total_steps": 64460, "loss": 0.2325, "lr": 7.687468492138085e-06, "epoch": 7.74899162271176, "percentage": 38.74, "elapsed_time": "0:45:41", "remaining_time": "1:12:14", "throughput": 5556.59, "total_tokens": 15235136} {"current_steps": 24980, "total_steps": 64460, "loss": 0.2357, "lr": 7.686326771007604e-06, "epoch": 7.750542972385976, "percentage": 38.75, "elapsed_time": "0:45:42", "remaining_time": "1:12:14", "throughput": 5556.55, "total_tokens": 15237696} {"current_steps": 24985, "total_steps": 64460, "loss": 0.23, "lr": 7.68518485293756e-06, "epoch": 7.752094322060192, "percentage": 38.76, "elapsed_time": "0:45:42", "remaining_time": "1:12:13", "throughput": 5556.52, "total_tokens": 15240256} {"current_steps": 24990, "total_steps": 64460, "loss": 0.2336, "lr": 7.684042738011668e-06, "epoch": 7.753645671734409, "percentage": 38.77, "elapsed_time": "0:45:43", "remaining_time": "1:12:12", "throughput": 5556.54, "total_tokens": 15243008} {"current_steps": 24995, "total_steps": 64460, "loss": 0.2285, "lr": 7.682900426313658e-06, "epoch": 7.755197021408626, "percentage": 38.78, "elapsed_time": "0:45:43", "remaining_time": "1:12:12", "throughput": 5556.55, "total_tokens": 15245952} {"current_steps": 25000, "total_steps": 64460, "loss": 0.2325, "lr": 7.68175791792728e-06, "epoch": 7.756748371082842, "percentage": 38.78, "elapsed_time": "0:45:44", "remaining_time": "1:12:11", "throughput": 5556.6, "total_tokens": 15248832} {"current_steps": 25005, "total_steps": 64460, "loss": 0.2361, "lr": 7.680615212936285e-06, "epoch": 7.7582997207570585, "percentage": 38.79, "elapsed_time": "0:45:45", "remaining_time": "1:12:11", "throughput": 5556.82, "total_tokens": 15253504} {"current_steps": 25010, "total_steps": 64460, "loss": 0.225, "lr": 7.679472311424453e-06, "epoch": 7.759851070431275, "percentage": 38.8, "elapsed_time": "0:45:45", "remaining_time": "1:12:10", "throughput": 5556.96, "total_tokens": 15257248} {"current_steps": 25015, "total_steps": 64460, "loss": 0.2268, "lr": 7.678329213475574e-06, "epoch": 7.761402420105492, "percentage": 38.81, "elapsed_time": "0:45:46", "remaining_time": "1:12:10", "throughput": 5557.0, "total_tokens": 15260096} {"current_steps": 25020, "total_steps": 64460, "loss": 0.2279, "lr": 7.677185919173446e-06, "epoch": 7.762953769779708, "percentage": 38.81, "elapsed_time": "0:45:46", "remaining_time": "1:12:09", "throughput": 5557.13, "total_tokens": 15263552} {"current_steps": 25025, "total_steps": 64460, "loss": 0.2401, "lr": 7.676042428601887e-06, "epoch": 7.764505119453925, "percentage": 38.82, "elapsed_time": "0:45:47", "remaining_time": "1:12:09", "throughput": 5557.08, "total_tokens": 15266112} {"current_steps": 25030, "total_steps": 64460, "loss": 0.2327, "lr": 7.67489874184473e-06, "epoch": 7.7660564691281415, "percentage": 38.83, "elapsed_time": "0:45:47", "remaining_time": "1:12:08", "throughput": 5557.04, "total_tokens": 15269536} {"current_steps": 25035, "total_steps": 64460, "loss": 0.2261, "lr": 7.673754858985817e-06, "epoch": 7.767607818802358, "percentage": 38.84, "elapsed_time": "0:45:48", "remaining_time": "1:12:08", "throughput": 5557.21, "total_tokens": 15273088} {"current_steps": 25040, "total_steps": 64460, "loss": 0.2364, "lr": 7.672610780109014e-06, "epoch": 7.769159168476575, "percentage": 38.85, "elapsed_time": "0:45:48", "remaining_time": "1:12:07", "throughput": 5557.21, "total_tokens": 15275776} {"current_steps": 25045, "total_steps": 64460, "loss": 0.2277, "lr": 7.67146650529819e-06, "epoch": 7.770710518150791, "percentage": 38.85, "elapsed_time": "0:45:49", "remaining_time": "1:12:06", "throughput": 5557.26, "total_tokens": 15278560} {"current_steps": 25050, "total_steps": 64460, "loss": 0.228, "lr": 7.670322034637237e-06, "epoch": 7.772261867825008, "percentage": 38.86, "elapsed_time": "0:45:49", "remaining_time": "1:12:06", "throughput": 5557.3, "total_tokens": 15281696} {"current_steps": 25055, "total_steps": 64460, "loss": 0.2258, "lr": 7.669177368210059e-06, "epoch": 7.7738132174992245, "percentage": 38.87, "elapsed_time": "0:45:50", "remaining_time": "1:12:05", "throughput": 5557.21, "total_tokens": 15284512} {"current_steps": 25060, "total_steps": 64460, "loss": 0.2214, "lr": 7.66803250610057e-06, "epoch": 7.775364567173441, "percentage": 38.88, "elapsed_time": "0:45:50", "remaining_time": "1:12:05", "throughput": 5557.13, "total_tokens": 15287040} {"current_steps": 25065, "total_steps": 64460, "loss": 0.2257, "lr": 7.666887448392704e-06, "epoch": 7.776915916847657, "percentage": 38.88, "elapsed_time": "0:45:51", "remaining_time": "1:12:04", "throughput": 5557.25, "total_tokens": 15290176} {"current_steps": 25070, "total_steps": 64460, "loss": 0.2346, "lr": 7.665742195170408e-06, "epoch": 7.778467266521874, "percentage": 38.89, "elapsed_time": "0:45:51", "remaining_time": "1:12:03", "throughput": 5557.28, "total_tokens": 15293216} {"current_steps": 25075, "total_steps": 64460, "loss": 0.2246, "lr": 7.664596746517643e-06, "epoch": 7.780018616196091, "percentage": 38.9, "elapsed_time": "0:45:52", "remaining_time": "1:12:03", "throughput": 5557.5, "total_tokens": 15297152} {"current_steps": 25080, "total_steps": 64460, "loss": 0.2344, "lr": 7.663451102518383e-06, "epoch": 7.7815699658703075, "percentage": 38.91, "elapsed_time": "0:45:53", "remaining_time": "1:12:02", "throughput": 5557.52, "total_tokens": 15300000} {"current_steps": 25085, "total_steps": 64460, "loss": 0.2276, "lr": 7.662305263256615e-06, "epoch": 7.783121315544523, "percentage": 38.92, "elapsed_time": "0:45:53", "remaining_time": "1:12:02", "throughput": 5557.58, "total_tokens": 15302912} {"current_steps": 25090, "total_steps": 64460, "loss": 0.2343, "lr": 7.661159228816345e-06, "epoch": 7.78467266521874, "percentage": 38.92, "elapsed_time": "0:45:53", "remaining_time": "1:12:01", "throughput": 5557.55, "total_tokens": 15305408} {"current_steps": 25095, "total_steps": 64460, "loss": 0.2262, "lr": 7.660012999281594e-06, "epoch": 7.786224014892957, "percentage": 38.93, "elapsed_time": "0:45:54", "remaining_time": "1:12:00", "throughput": 5557.75, "total_tokens": 15308928} {"current_steps": 25100, "total_steps": 64460, "loss": 0.2413, "lr": 7.658866574736387e-06, "epoch": 7.787775364567174, "percentage": 38.94, "elapsed_time": "0:45:55", "remaining_time": "1:12:00", "throughput": 5557.9, "total_tokens": 15312192} {"current_steps": 25105, "total_steps": 64460, "loss": 0.2292, "lr": 7.657719955264777e-06, "epoch": 7.7893267142413904, "percentage": 38.95, "elapsed_time": "0:45:55", "remaining_time": "1:11:59", "throughput": 5557.69, "total_tokens": 15314144} {"current_steps": 25110, "total_steps": 64460, "loss": 0.232, "lr": 7.656573140950823e-06, "epoch": 7.790878063915606, "percentage": 38.95, "elapsed_time": "0:45:55", "remaining_time": "1:11:58", "throughput": 5557.75, "total_tokens": 15316928} {"current_steps": 25115, "total_steps": 64460, "loss": 0.2283, "lr": 7.655426131878596e-06, "epoch": 7.792429413589823, "percentage": 38.96, "elapsed_time": "0:45:56", "remaining_time": "1:11:58", "throughput": 5557.81, "total_tokens": 15319776} {"current_steps": 25120, "total_steps": 64460, "loss": 0.2336, "lr": 7.65427892813219e-06, "epoch": 7.79398076326404, "percentage": 38.97, "elapsed_time": "0:45:56", "remaining_time": "1:11:57", "throughput": 5557.82, "total_tokens": 15322688} {"current_steps": 25125, "total_steps": 64460, "loss": 0.2294, "lr": 7.653131529795708e-06, "epoch": 7.795532112938257, "percentage": 38.98, "elapsed_time": "0:45:57", "remaining_time": "1:11:57", "throughput": 5558.07, "total_tokens": 15327072} {"current_steps": 25130, "total_steps": 64460, "loss": 0.2309, "lr": 7.651983936953266e-06, "epoch": 7.7970834626124725, "percentage": 38.99, "elapsed_time": "0:45:58", "remaining_time": "1:11:56", "throughput": 5558.25, "total_tokens": 15330496} {"current_steps": 25135, "total_steps": 64460, "loss": 0.2313, "lr": 7.650836149688997e-06, "epoch": 7.798634812286689, "percentage": 38.99, "elapsed_time": "0:45:58", "remaining_time": "1:11:56", "throughput": 5558.15, "total_tokens": 15332832} {"current_steps": 25140, "total_steps": 64460, "loss": 0.2265, "lr": 7.649688168087049e-06, "epoch": 7.800186161960906, "percentage": 39.0, "elapsed_time": "0:45:59", "remaining_time": "1:11:55", "throughput": 5558.1, "total_tokens": 15335456} {"current_steps": 25145, "total_steps": 64460, "loss": 0.2308, "lr": 7.64853999223158e-06, "epoch": 7.801737511635123, "percentage": 39.01, "elapsed_time": "0:45:59", "remaining_time": "1:11:54", "throughput": 5558.06, "total_tokens": 15337888} {"current_steps": 25150, "total_steps": 64460, "loss": 0.2259, "lr": 7.647391622206767e-06, "epoch": 7.803288861309339, "percentage": 39.02, "elapsed_time": "0:46:00", "remaining_time": "1:11:54", "throughput": 5558.12, "total_tokens": 15340960} {"current_steps": 25155, "total_steps": 64460, "loss": 0.2271, "lr": 7.646243058096798e-06, "epoch": 7.8048402109835555, "percentage": 39.02, "elapsed_time": "0:46:00", "remaining_time": "1:11:53", "throughput": 5558.17, "total_tokens": 15343968} {"current_steps": 25160, "total_steps": 64460, "loss": 0.2301, "lr": 7.645094299985877e-06, "epoch": 7.806391560657772, "percentage": 39.03, "elapsed_time": "0:46:01", "remaining_time": "1:11:52", "throughput": 5558.18, "total_tokens": 15346656} {"current_steps": 25165, "total_steps": 64460, "loss": 0.2314, "lr": 7.64394534795822e-06, "epoch": 7.807942910331989, "percentage": 39.04, "elapsed_time": "0:46:01", "remaining_time": "1:11:52", "throughput": 5558.44, "total_tokens": 15350528} {"current_steps": 25170, "total_steps": 64460, "loss": 0.2295, "lr": 7.642796202098061e-06, "epoch": 7.809494260006206, "percentage": 39.05, "elapsed_time": "0:46:02", "remaining_time": "1:11:51", "throughput": 5558.42, "total_tokens": 15353280} {"current_steps": 25175, "total_steps": 64460, "loss": 0.2303, "lr": 7.641646862489644e-06, "epoch": 7.811045609680422, "percentage": 39.06, "elapsed_time": "0:46:02", "remaining_time": "1:11:51", "throughput": 5558.39, "total_tokens": 15355936} {"current_steps": 25180, "total_steps": 64460, "loss": 0.233, "lr": 7.640497329217232e-06, "epoch": 7.8125969593546385, "percentage": 39.06, "elapsed_time": "0:46:03", "remaining_time": "1:11:50", "throughput": 5558.42, "total_tokens": 15358784} {"current_steps": 25185, "total_steps": 64460, "loss": 0.2325, "lr": 7.639347602365095e-06, "epoch": 7.814148309028855, "percentage": 39.07, "elapsed_time": "0:46:03", "remaining_time": "1:11:49", "throughput": 5558.32, "total_tokens": 15361184} {"current_steps": 25190, "total_steps": 64460, "loss": 0.2357, "lr": 7.638197682017527e-06, "epoch": 7.815699658703072, "percentage": 39.08, "elapsed_time": "0:46:04", "remaining_time": "1:11:49", "throughput": 5558.56, "total_tokens": 15365088} {"current_steps": 25195, "total_steps": 64460, "loss": 0.227, "lr": 7.637047568258826e-06, "epoch": 7.817251008377288, "percentage": 39.09, "elapsed_time": "0:46:04", "remaining_time": "1:11:48", "throughput": 5558.43, "total_tokens": 15367328} {"current_steps": 25200, "total_steps": 64460, "loss": 0.2279, "lr": 7.635897261173313e-06, "epoch": 7.818802358051505, "percentage": 39.09, "elapsed_time": "0:46:05", "remaining_time": "1:11:48", "throughput": 5558.51, "total_tokens": 15370400} {"current_steps": 25205, "total_steps": 64460, "loss": 0.236, "lr": 7.634746760845314e-06, "epoch": 7.8203537077257215, "percentage": 39.1, "elapsed_time": "0:46:05", "remaining_time": "1:11:47", "throughput": 5558.42, "total_tokens": 15372736} {"current_steps": 25210, "total_steps": 64460, "loss": 0.2312, "lr": 7.633596067359182e-06, "epoch": 7.821905057399938, "percentage": 39.11, "elapsed_time": "0:46:06", "remaining_time": "1:11:46", "throughput": 5558.39, "total_tokens": 15375328} {"current_steps": 25215, "total_steps": 64460, "loss": 0.2316, "lr": 7.632445180799269e-06, "epoch": 7.823456407074154, "percentage": 39.12, "elapsed_time": "0:46:06", "remaining_time": "1:11:46", "throughput": 5558.38, "total_tokens": 15377920} {"current_steps": 25220, "total_steps": 64460, "loss": 0.2334, "lr": 7.63129410124995e-06, "epoch": 7.825007756748371, "percentage": 39.13, "elapsed_time": "0:46:07", "remaining_time": "1:11:45", "throughput": 5558.51, "total_tokens": 15380992} {"current_steps": 25225, "total_steps": 64460, "loss": 0.233, "lr": 7.630142828795616e-06, "epoch": 7.826559106422588, "percentage": 39.13, "elapsed_time": "0:46:07", "remaining_time": "1:11:44", "throughput": 5558.39, "total_tokens": 15383232} {"current_steps": 25230, "total_steps": 64460, "loss": 0.2332, "lr": 7.6289913635206655e-06, "epoch": 7.8281104560968044, "percentage": 39.14, "elapsed_time": "0:46:08", "remaining_time": "1:11:44", "throughput": 5558.42, "total_tokens": 15386304} {"current_steps": 25235, "total_steps": 64460, "loss": 0.2336, "lr": 7.627839705509519e-06, "epoch": 7.829661805771021, "percentage": 39.15, "elapsed_time": "0:46:08", "remaining_time": "1:11:43", "throughput": 5558.51, "total_tokens": 15389312} {"current_steps": 25240, "total_steps": 64460, "loss": 0.2279, "lr": 7.626687854846601e-06, "epoch": 7.831213155445237, "percentage": 39.16, "elapsed_time": "0:46:09", "remaining_time": "1:11:42", "throughput": 5558.45, "total_tokens": 15391872} {"current_steps": 25245, "total_steps": 64460, "loss": 0.2367, "lr": 7.62553581161636e-06, "epoch": 7.832764505119454, "percentage": 39.16, "elapsed_time": "0:46:09", "remaining_time": "1:11:42", "throughput": 5558.6, "total_tokens": 15395392} {"current_steps": 25250, "total_steps": 64460, "loss": 0.2372, "lr": 7.624383575903253e-06, "epoch": 7.834315854793671, "percentage": 39.17, "elapsed_time": "0:46:10", "remaining_time": "1:11:41", "throughput": 5558.63, "total_tokens": 15398176} {"current_steps": 25255, "total_steps": 64460, "loss": 0.2328, "lr": 7.623231147791752e-06, "epoch": 7.835867204467887, "percentage": 39.18, "elapsed_time": "0:46:10", "remaining_time": "1:11:41", "throughput": 5558.63, "total_tokens": 15400896} {"current_steps": 25260, "total_steps": 64460, "loss": 0.2291, "lr": 7.622078527366343e-06, "epoch": 7.837418554142103, "percentage": 39.19, "elapsed_time": "0:46:11", "remaining_time": "1:11:40", "throughput": 5558.78, "total_tokens": 15404480} {"current_steps": 25265, "total_steps": 64460, "loss": 0.2355, "lr": 7.62092571471153e-06, "epoch": 7.83896990381632, "percentage": 39.19, "elapsed_time": "0:46:11", "remaining_time": "1:11:39", "throughput": 5558.81, "total_tokens": 15407680} {"current_steps": 25270, "total_steps": 64460, "loss": 0.2361, "lr": 7.619772709911825e-06, "epoch": 7.840521253490537, "percentage": 39.2, "elapsed_time": "0:46:12", "remaining_time": "1:11:39", "throughput": 5558.86, "total_tokens": 15410528} {"current_steps": 25275, "total_steps": 64460, "loss": 0.2318, "lr": 7.618619513051757e-06, "epoch": 7.842072603164754, "percentage": 39.21, "elapsed_time": "0:46:13", "remaining_time": "1:11:39", "throughput": 5559.27, "total_tokens": 15415936} {"current_steps": 25280, "total_steps": 64460, "loss": 0.2303, "lr": 7.617466124215871e-06, "epoch": 7.8436239528389695, "percentage": 39.22, "elapsed_time": "0:46:13", "remaining_time": "1:11:38", "throughput": 5559.47, "total_tokens": 15420000} {"current_steps": 25285, "total_steps": 64460, "loss": 0.2286, "lr": 7.616312543488722e-06, "epoch": 7.845175302513186, "percentage": 39.23, "elapsed_time": "0:46:14", "remaining_time": "1:11:38", "throughput": 5559.4, "total_tokens": 15422496} {"current_steps": 25290, "total_steps": 64460, "loss": 0.2351, "lr": 7.615158770954883e-06, "epoch": 7.846726652187403, "percentage": 39.23, "elapsed_time": "0:46:14", "remaining_time": "1:11:37", "throughput": 5559.35, "total_tokens": 15425024} {"current_steps": 25295, "total_steps": 64460, "loss": 0.2275, "lr": 7.614004806698936e-06, "epoch": 7.84827800186162, "percentage": 39.24, "elapsed_time": "0:46:15", "remaining_time": "1:11:36", "throughput": 5559.42, "total_tokens": 15428096} {"current_steps": 25300, "total_steps": 64460, "loss": 0.2294, "lr": 7.6128506508054825e-06, "epoch": 7.849829351535837, "percentage": 39.25, "elapsed_time": "0:46:15", "remaining_time": "1:11:36", "throughput": 5559.35, "total_tokens": 15431040} {"current_steps": 25305, "total_steps": 64460, "loss": 0.2352, "lr": 7.611696303359136e-06, "epoch": 7.8513807012100525, "percentage": 39.26, "elapsed_time": "0:46:16", "remaining_time": "1:11:35", "throughput": 5559.33, "total_tokens": 15433888} {"current_steps": 25310, "total_steps": 64460, "loss": 0.2383, "lr": 7.6105417644445234e-06, "epoch": 7.852932050884269, "percentage": 39.26, "elapsed_time": "0:46:16", "remaining_time": "1:11:35", "throughput": 5559.4, "total_tokens": 15436704} {"current_steps": 25315, "total_steps": 64460, "loss": 0.2353, "lr": 7.609387034146286e-06, "epoch": 7.854483400558486, "percentage": 39.27, "elapsed_time": "0:46:17", "remaining_time": "1:11:34", "throughput": 5559.02, "total_tokens": 15438592} {"current_steps": 25320, "total_steps": 64460, "loss": 0.228, "lr": 7.608232112549079e-06, "epoch": 7.856034750232703, "percentage": 39.28, "elapsed_time": "0:46:17", "remaining_time": "1:11:33", "throughput": 5559.05, "total_tokens": 15441600} {"current_steps": 25325, "total_steps": 64460, "loss": 0.2311, "lr": 7.607076999737571e-06, "epoch": 7.857586099906919, "percentage": 39.29, "elapsed_time": "0:46:18", "remaining_time": "1:11:33", "throughput": 5558.97, "total_tokens": 15444224} {"current_steps": 25330, "total_steps": 64460, "loss": 0.2213, "lr": 7.605921695796448e-06, "epoch": 7.8591374495811355, "percentage": 39.3, "elapsed_time": "0:46:18", "remaining_time": "1:11:32", "throughput": 5558.99, "total_tokens": 15446944} {"current_steps": 25335, "total_steps": 64460, "loss": 0.2307, "lr": 7.604766200810406e-06, "epoch": 7.860688799255352, "percentage": 39.3, "elapsed_time": "0:46:19", "remaining_time": "1:11:31", "throughput": 5559.08, "total_tokens": 15449952} {"current_steps": 25340, "total_steps": 64460, "loss": 0.231, "lr": 7.603610514864156e-06, "epoch": 7.862240148929569, "percentage": 39.31, "elapsed_time": "0:46:19", "remaining_time": "1:11:31", "throughput": 5559.04, "total_tokens": 15452448} {"current_steps": 25345, "total_steps": 64460, "loss": 0.2312, "lr": 7.602454638042425e-06, "epoch": 7.863791498603785, "percentage": 39.32, "elapsed_time": "0:46:20", "remaining_time": "1:11:30", "throughput": 5559.33, "total_tokens": 15456576} {"current_steps": 25350, "total_steps": 64460, "loss": 0.2341, "lr": 7.601298570429949e-06, "epoch": 7.865342848278002, "percentage": 39.33, "elapsed_time": "0:46:20", "remaining_time": "1:11:30", "throughput": 5559.54, "total_tokens": 15460480} {"current_steps": 25355, "total_steps": 64460, "loss": 0.2336, "lr": 7.600142312111486e-06, "epoch": 7.8668941979522184, "percentage": 39.33, "elapsed_time": "0:46:21", "remaining_time": "1:11:29", "throughput": 5559.61, "total_tokens": 15463552} {"current_steps": 25360, "total_steps": 64460, "loss": 0.2378, "lr": 7.598985863171801e-06, "epoch": 7.868445547626435, "percentage": 39.34, "elapsed_time": "0:46:21", "remaining_time": "1:11:29", "throughput": 5559.67, "total_tokens": 15466400} {"current_steps": 25365, "total_steps": 64460, "loss": 0.23, "lr": 7.597829223695674e-06, "epoch": 7.869996897300652, "percentage": 39.35, "elapsed_time": "0:46:22", "remaining_time": "1:11:28", "throughput": 5559.7, "total_tokens": 15469056} {"current_steps": 25370, "total_steps": 64460, "loss": 0.227, "lr": 7.596672393767903e-06, "epoch": 7.871548246974868, "percentage": 39.36, "elapsed_time": "0:46:22", "remaining_time": "1:11:27", "throughput": 5559.59, "total_tokens": 15471360} {"current_steps": 25375, "total_steps": 64460, "loss": 0.2244, "lr": 7.595515373473297e-06, "epoch": 7.873099596649085, "percentage": 39.37, "elapsed_time": "0:46:23", "remaining_time": "1:11:27", "throughput": 5559.75, "total_tokens": 15475424} {"current_steps": 25380, "total_steps": 64460, "loss": 0.2318, "lr": 7.594358162896678e-06, "epoch": 7.874650946323301, "percentage": 39.37, "elapsed_time": "0:46:23", "remaining_time": "1:11:26", "throughput": 5559.77, "total_tokens": 15478368} {"current_steps": 25385, "total_steps": 64460, "loss": 0.2311, "lr": 7.593200762122883e-06, "epoch": 7.876202295997518, "percentage": 39.38, "elapsed_time": "0:46:24", "remaining_time": "1:11:26", "throughput": 5559.91, "total_tokens": 15481760} {"current_steps": 25390, "total_steps": 64460, "loss": 0.2299, "lr": 7.592043171236765e-06, "epoch": 7.877753645671734, "percentage": 39.39, "elapsed_time": "0:46:25", "remaining_time": "1:11:25", "throughput": 5559.98, "total_tokens": 15484608} {"current_steps": 25395, "total_steps": 64460, "loss": 0.2281, "lr": 7.590885390323188e-06, "epoch": 7.879304995345951, "percentage": 39.4, "elapsed_time": "0:46:25", "remaining_time": "1:11:24", "throughput": 5560.15, "total_tokens": 15487808} {"current_steps": 25400, "total_steps": 64460, "loss": 0.2253, "lr": 7.589727419467032e-06, "epoch": 7.880856345020168, "percentage": 39.4, "elapsed_time": "0:46:26", "remaining_time": "1:11:24", "throughput": 5560.3, "total_tokens": 15491296} {"current_steps": 25405, "total_steps": 64460, "loss": 0.2299, "lr": 7.588569258753188e-06, "epoch": 7.882407694694384, "percentage": 39.41, "elapsed_time": "0:46:26", "remaining_time": "1:11:23", "throughput": 5560.28, "total_tokens": 15493760} {"current_steps": 25410, "total_steps": 64460, "loss": 0.2291, "lr": 7.587410908266564e-06, "epoch": 7.8839590443686, "percentage": 39.42, "elapsed_time": "0:46:26", "remaining_time": "1:11:23", "throughput": 5560.38, "total_tokens": 15496768} {"current_steps": 25415, "total_steps": 64460, "loss": 0.2262, "lr": 7.5862523680920815e-06, "epoch": 7.885510394042817, "percentage": 39.43, "elapsed_time": "0:46:27", "remaining_time": "1:11:22", "throughput": 5560.51, "total_tokens": 15499936} {"current_steps": 25420, "total_steps": 64460, "loss": 0.2293, "lr": 7.585093638314676e-06, "epoch": 7.887061743717034, "percentage": 39.44, "elapsed_time": "0:46:27", "remaining_time": "1:11:21", "throughput": 5560.58, "total_tokens": 15502784} {"current_steps": 25425, "total_steps": 64460, "loss": 0.2302, "lr": 7.583934719019293e-06, "epoch": 7.888613093391251, "percentage": 39.44, "elapsed_time": "0:46:28", "remaining_time": "1:11:21", "throughput": 5560.6, "total_tokens": 15505536} {"current_steps": 25430, "total_steps": 64460, "loss": 0.2264, "lr": 7.582775610290896e-06, "epoch": 7.890164443065467, "percentage": 39.45, "elapsed_time": "0:46:28", "remaining_time": "1:11:20", "throughput": 5560.62, "total_tokens": 15508224} {"current_steps": 25435, "total_steps": 64460, "loss": 0.2254, "lr": 7.581616312214464e-06, "epoch": 7.891715792739683, "percentage": 39.46, "elapsed_time": "0:46:29", "remaining_time": "1:11:19", "throughput": 5560.85, "total_tokens": 15512160} {"current_steps": 25440, "total_steps": 64460, "loss": 0.2277, "lr": 7.580456824874984e-06, "epoch": 7.8932671424139, "percentage": 39.47, "elapsed_time": "0:46:29", "remaining_time": "1:11:19", "throughput": 5560.79, "total_tokens": 15514528} {"current_steps": 25445, "total_steps": 64460, "loss": 0.2331, "lr": 7.579297148357462e-06, "epoch": 7.894818492088117, "percentage": 39.47, "elapsed_time": "0:46:30", "remaining_time": "1:11:19", "throughput": 5561.07, "total_tokens": 15519328} {"current_steps": 25450, "total_steps": 64460, "loss": 0.2348, "lr": 7.578137282746916e-06, "epoch": 7.896369841762334, "percentage": 39.48, "elapsed_time": "0:46:31", "remaining_time": "1:11:18", "throughput": 5561.17, "total_tokens": 15522304} {"current_steps": 25455, "total_steps": 64460, "loss": 0.2271, "lr": 7.576977228128377e-06, "epoch": 7.8979211914365495, "percentage": 39.49, "elapsed_time": "0:46:31", "remaining_time": "1:11:17", "throughput": 5561.22, "total_tokens": 15525472} {"current_steps": 25460, "total_steps": 64460, "loss": 0.2303, "lr": 7.5758169845868915e-06, "epoch": 7.899472541110766, "percentage": 39.5, "elapsed_time": "0:46:32", "remaining_time": "1:11:17", "throughput": 5561.24, "total_tokens": 15528416} {"current_steps": 25465, "total_steps": 64460, "loss": 0.225, "lr": 7.574656552207518e-06, "epoch": 7.901023890784983, "percentage": 39.51, "elapsed_time": "0:46:32", "remaining_time": "1:11:16", "throughput": 5561.11, "total_tokens": 15530784} {"current_steps": 25470, "total_steps": 64460, "loss": 0.2334, "lr": 7.573495931075332e-06, "epoch": 7.9025752404592, "percentage": 39.51, "elapsed_time": "0:46:33", "remaining_time": "1:11:16", "throughput": 5561.09, "total_tokens": 15533696} {"current_steps": 25475, "total_steps": 64460, "loss": 0.2334, "lr": 7.572335121275418e-06, "epoch": 7.904126590133416, "percentage": 39.52, "elapsed_time": "0:46:33", "remaining_time": "1:11:15", "throughput": 5561.14, "total_tokens": 15536768} {"current_steps": 25480, "total_steps": 64460, "loss": 0.235, "lr": 7.571174122892881e-06, "epoch": 7.9056779398076324, "percentage": 39.53, "elapsed_time": "0:46:34", "remaining_time": "1:11:14", "throughput": 5561.22, "total_tokens": 15540128} {"current_steps": 25485, "total_steps": 64460, "loss": 0.2364, "lr": 7.5700129360128316e-06, "epoch": 7.907229289481849, "percentage": 39.54, "elapsed_time": "0:46:34", "remaining_time": "1:11:14", "throughput": 5561.4, "total_tokens": 15543712} {"current_steps": 25490, "total_steps": 64460, "loss": 0.231, "lr": 7.568851560720401e-06, "epoch": 7.908780639156066, "percentage": 39.54, "elapsed_time": "0:46:35", "remaining_time": "1:11:13", "throughput": 5561.42, "total_tokens": 15546592} {"current_steps": 25495, "total_steps": 64460, "loss": 0.2319, "lr": 7.567689997100731e-06, "epoch": 7.910331988830283, "percentage": 39.55, "elapsed_time": "0:46:36", "remaining_time": "1:11:13", "throughput": 5561.26, "total_tokens": 15549280} {"current_steps": 25500, "total_steps": 64460, "loss": 0.2272, "lr": 7.566528245238978e-06, "epoch": 7.911883338504499, "percentage": 39.56, "elapsed_time": "0:46:36", "remaining_time": "1:11:12", "throughput": 5561.07, "total_tokens": 15551616} {"current_steps": 25505, "total_steps": 64460, "loss": 0.2282, "lr": 7.565366305220312e-06, "epoch": 7.913434688178715, "percentage": 39.57, "elapsed_time": "0:46:37", "remaining_time": "1:11:12", "throughput": 5561.19, "total_tokens": 15554912} {"current_steps": 25510, "total_steps": 64460, "loss": 0.2285, "lr": 7.564204177129919e-06, "epoch": 7.914986037852932, "percentage": 39.57, "elapsed_time": "0:46:37", "remaining_time": "1:11:11", "throughput": 5561.15, "total_tokens": 15557600} {"current_steps": 25515, "total_steps": 64460, "loss": 0.2186, "lr": 7.563041861052993e-06, "epoch": 7.916537387527149, "percentage": 39.58, "elapsed_time": "0:46:38", "remaining_time": "1:11:10", "throughput": 5561.01, "total_tokens": 15559936} {"current_steps": 25520, "total_steps": 64460, "loss": 0.222, "lr": 7.56187935707475e-06, "epoch": 7.918088737201365, "percentage": 39.59, "elapsed_time": "0:46:38", "remaining_time": "1:11:10", "throughput": 5561.18, "total_tokens": 15564032} {"current_steps": 25525, "total_steps": 64460, "loss": 0.2292, "lr": 7.560716665280412e-06, "epoch": 7.919640086875582, "percentage": 39.6, "elapsed_time": "0:46:39", "remaining_time": "1:11:09", "throughput": 5561.1, "total_tokens": 15566432} {"current_steps": 25530, "total_steps": 64460, "loss": 0.2433, "lr": 7.559553785755218e-06, "epoch": 7.921191436549798, "percentage": 39.61, "elapsed_time": "0:46:39", "remaining_time": "1:11:09", "throughput": 5561.3, "total_tokens": 15570144} {"current_steps": 25535, "total_steps": 64460, "loss": 0.2286, "lr": 7.558390718584423e-06, "epoch": 7.922742786224015, "percentage": 39.61, "elapsed_time": "0:46:40", "remaining_time": "1:11:08", "throughput": 5561.35, "total_tokens": 15573120} {"current_steps": 25540, "total_steps": 64460, "loss": 0.2285, "lr": 7.557227463853291e-06, "epoch": 7.924294135898231, "percentage": 39.62, "elapsed_time": "0:46:40", "remaining_time": "1:11:08", "throughput": 5561.46, "total_tokens": 15576256} {"current_steps": 25545, "total_steps": 64460, "loss": 0.2319, "lr": 7.556064021647105e-06, "epoch": 7.925845485572448, "percentage": 39.63, "elapsed_time": "0:46:41", "remaining_time": "1:11:07", "throughput": 5561.58, "total_tokens": 15579552} {"current_steps": 25550, "total_steps": 64460, "loss": 0.2191, "lr": 7.554900392051157e-06, "epoch": 7.927396835246665, "percentage": 39.64, "elapsed_time": "0:46:41", "remaining_time": "1:11:06", "throughput": 5561.58, "total_tokens": 15582336} {"current_steps": 25555, "total_steps": 64460, "loss": 0.2315, "lr": 7.553736575150757e-06, "epoch": 7.928948184920881, "percentage": 39.64, "elapsed_time": "0:46:42", "remaining_time": "1:11:06", "throughput": 5561.72, "total_tokens": 15586176} {"current_steps": 25560, "total_steps": 64460, "loss": 0.2266, "lr": 7.552572571031225e-06, "epoch": 7.930499534595098, "percentage": 39.65, "elapsed_time": "0:46:42", "remaining_time": "1:11:05", "throughput": 5561.75, "total_tokens": 15589536} {"current_steps": 25565, "total_steps": 64460, "loss": 0.2363, "lr": 7.551408379777896e-06, "epoch": 7.932050884269314, "percentage": 39.66, "elapsed_time": "0:46:43", "remaining_time": "1:11:05", "throughput": 5561.67, "total_tokens": 15592160} {"current_steps": 25570, "total_steps": 64460, "loss": 0.2333, "lr": 7.550244001476119e-06, "epoch": 7.933602233943531, "percentage": 39.67, "elapsed_time": "0:46:43", "remaining_time": "1:11:04", "throughput": 5561.54, "total_tokens": 15594464} {"current_steps": 25575, "total_steps": 64460, "loss": 0.2209, "lr": 7.54907943621126e-06, "epoch": 7.935153583617748, "percentage": 39.68, "elapsed_time": "0:46:44", "remaining_time": "1:11:04", "throughput": 5561.7, "total_tokens": 15597984} {"current_steps": 25580, "total_steps": 64460, "loss": 0.24, "lr": 7.547914684068689e-06, "epoch": 7.936704933291964, "percentage": 39.68, "elapsed_time": "0:46:45", "remaining_time": "1:11:03", "throughput": 5561.89, "total_tokens": 15602080} {"current_steps": 25585, "total_steps": 64460, "loss": 0.2239, "lr": 7.546749745133802e-06, "epoch": 7.93825628296618, "percentage": 39.69, "elapsed_time": "0:46:45", "remaining_time": "1:11:03", "throughput": 5561.96, "total_tokens": 15605088} {"current_steps": 25590, "total_steps": 64460, "loss": 0.2359, "lr": 7.545584619492001e-06, "epoch": 7.939807632640397, "percentage": 39.7, "elapsed_time": "0:46:46", "remaining_time": "1:11:02", "throughput": 5562.01, "total_tokens": 15607840} {"current_steps": 25595, "total_steps": 64460, "loss": 0.2295, "lr": 7.544419307228703e-06, "epoch": 7.941358982314614, "percentage": 39.71, "elapsed_time": "0:46:46", "remaining_time": "1:11:01", "throughput": 5562.11, "total_tokens": 15611264} {"current_steps": 25600, "total_steps": 64460, "loss": 0.2253, "lr": 7.5432538084293385e-06, "epoch": 7.942910331988831, "percentage": 39.71, "elapsed_time": "0:46:47", "remaining_time": "1:11:01", "throughput": 5562.02, "total_tokens": 15614336} {"current_steps": 25605, "total_steps": 64460, "loss": 0.2367, "lr": 7.5420881231793545e-06, "epoch": 7.9444616816630464, "percentage": 39.72, "elapsed_time": "0:46:47", "remaining_time": "1:11:00", "throughput": 5561.76, "total_tokens": 15616640} {"current_steps": 25610, "total_steps": 64460, "loss": 0.2182, "lr": 7.5409222515642065e-06, "epoch": 7.946013031337263, "percentage": 39.73, "elapsed_time": "0:46:48", "remaining_time": "1:11:00", "throughput": 5561.83, "total_tokens": 15620448} {"current_steps": 25615, "total_steps": 64460, "loss": 0.2282, "lr": 7.5397561936693695e-06, "epoch": 7.94756438101148, "percentage": 39.74, "elapsed_time": "0:46:49", "remaining_time": "1:11:00", "throughput": 5562.04, "total_tokens": 15624672} {"current_steps": 25620, "total_steps": 64460, "loss": 0.2253, "lr": 7.5385899495803285e-06, "epoch": 7.949115730685697, "percentage": 39.75, "elapsed_time": "0:46:49", "remaining_time": "1:10:59", "throughput": 5562.07, "total_tokens": 15627616} {"current_steps": 25625, "total_steps": 64460, "loss": 0.2384, "lr": 7.537423519382581e-06, "epoch": 7.9506670803599135, "percentage": 39.75, "elapsed_time": "0:46:50", "remaining_time": "1:10:58", "throughput": 5562.0, "total_tokens": 15630304} {"current_steps": 25630, "total_steps": 64460, "loss": 0.2247, "lr": 7.536256903161644e-06, "epoch": 7.952218430034129, "percentage": 39.76, "elapsed_time": "0:46:50", "remaining_time": "1:10:58", "throughput": 5561.82, "total_tokens": 15632640} {"current_steps": 25635, "total_steps": 64460, "loss": 0.2234, "lr": 7.5350901010030405e-06, "epoch": 7.953769779708346, "percentage": 39.77, "elapsed_time": "0:46:51", "remaining_time": "1:10:57", "throughput": 5561.89, "total_tokens": 15635520} {"current_steps": 25640, "total_steps": 64460, "loss": 0.2133, "lr": 7.533923112992314e-06, "epoch": 7.955321129382563, "percentage": 39.78, "elapsed_time": "0:46:51", "remaining_time": "1:10:57", "throughput": 5561.98, "total_tokens": 15639264} {"current_steps": 25645, "total_steps": 64460, "loss": 0.2322, "lr": 7.532755939215017e-06, "epoch": 7.95687247905678, "percentage": 39.78, "elapsed_time": "0:46:52", "remaining_time": "1:10:56", "throughput": 5561.81, "total_tokens": 15641792} {"current_steps": 25650, "total_steps": 64460, "loss": 0.2316, "lr": 7.5315885797567166e-06, "epoch": 7.958423828730996, "percentage": 39.79, "elapsed_time": "0:46:52", "remaining_time": "1:10:56", "throughput": 5561.88, "total_tokens": 15644800} {"current_steps": 25655, "total_steps": 64460, "loss": 0.2571, "lr": 7.530421034702996e-06, "epoch": 7.959975178405212, "percentage": 39.8, "elapsed_time": "0:46:53", "remaining_time": "1:10:55", "throughput": 5561.9, "total_tokens": 15647552} {"current_steps": 25660, "total_steps": 64460, "loss": 0.2334, "lr": 7.529253304139448e-06, "epoch": 7.961526528079429, "percentage": 39.81, "elapsed_time": "0:46:53", "remaining_time": "1:10:54", "throughput": 5561.86, "total_tokens": 15650112} {"current_steps": 25665, "total_steps": 64460, "loss": 0.2467, "lr": 7.528085388151682e-06, "epoch": 7.963077877753646, "percentage": 39.82, "elapsed_time": "0:46:54", "remaining_time": "1:10:54", "throughput": 5561.91, "total_tokens": 15653056} {"current_steps": 25670, "total_steps": 64460, "loss": 0.2153, "lr": 7.526917286825322e-06, "epoch": 7.964629227427862, "percentage": 39.82, "elapsed_time": "0:46:54", "remaining_time": "1:10:53", "throughput": 5562.15, "total_tokens": 15656960} {"current_steps": 25675, "total_steps": 64460, "loss": 0.229, "lr": 7.525749000245998e-06, "epoch": 7.966180577102079, "percentage": 39.83, "elapsed_time": "0:46:55", "remaining_time": "1:10:52", "throughput": 5562.22, "total_tokens": 15659872} {"current_steps": 25680, "total_steps": 64460, "loss": 0.2291, "lr": 7.524580528499365e-06, "epoch": 7.967731926776295, "percentage": 39.84, "elapsed_time": "0:46:55", "remaining_time": "1:10:52", "throughput": 5562.26, "total_tokens": 15663232} {"current_steps": 25685, "total_steps": 64460, "loss": 0.2301, "lr": 7.523411871671085e-06, "epoch": 7.969283276450512, "percentage": 39.85, "elapsed_time": "0:46:56", "remaining_time": "1:10:51", "throughput": 5562.13, "total_tokens": 15665600} {"current_steps": 25690, "total_steps": 64460, "loss": 0.2361, "lr": 7.522243029846832e-06, "epoch": 7.970834626124729, "percentage": 39.85, "elapsed_time": "0:46:56", "remaining_time": "1:10:51", "throughput": 5562.23, "total_tokens": 15668672} {"current_steps": 25695, "total_steps": 64460, "loss": 0.2302, "lr": 7.521074003112295e-06, "epoch": 7.972385975798945, "percentage": 39.86, "elapsed_time": "0:46:57", "remaining_time": "1:10:50", "throughput": 5562.26, "total_tokens": 15671872} {"current_steps": 25700, "total_steps": 64460, "loss": 0.2272, "lr": 7.519904791553182e-06, "epoch": 7.973937325473162, "percentage": 39.87, "elapsed_time": "0:46:58", "remaining_time": "1:10:50", "throughput": 5562.11, "total_tokens": 15674208} {"current_steps": 25705, "total_steps": 64460, "loss": 0.2336, "lr": 7.518735395255208e-06, "epoch": 7.975488675147378, "percentage": 39.88, "elapsed_time": "0:46:58", "remaining_time": "1:10:49", "throughput": 5562.2, "total_tokens": 15677088} {"current_steps": 25710, "total_steps": 64460, "loss": 0.2295, "lr": 7.517565814304102e-06, "epoch": 7.977040024821595, "percentage": 39.89, "elapsed_time": "0:46:59", "remaining_time": "1:10:48", "throughput": 5562.22, "total_tokens": 15679904} {"current_steps": 25715, "total_steps": 64460, "loss": 0.23, "lr": 7.516396048785609e-06, "epoch": 7.978591374495811, "percentage": 39.89, "elapsed_time": "0:46:59", "remaining_time": "1:10:48", "throughput": 5562.22, "total_tokens": 15682784} {"current_steps": 25720, "total_steps": 64460, "loss": 0.2306, "lr": 7.5152260987854885e-06, "epoch": 7.980142724170028, "percentage": 39.9, "elapsed_time": "0:47:00", "remaining_time": "1:10:47", "throughput": 5562.13, "total_tokens": 15685376} {"current_steps": 25725, "total_steps": 64460, "loss": 0.2302, "lr": 7.5140559643895095e-06, "epoch": 7.981694073844245, "percentage": 39.91, "elapsed_time": "0:47:00", "remaining_time": "1:10:46", "throughput": 5562.13, "total_tokens": 15688000} {"current_steps": 25730, "total_steps": 64460, "loss": 0.2195, "lr": 7.5128856456834565e-06, "epoch": 7.983245423518461, "percentage": 39.92, "elapsed_time": "0:47:00", "remaining_time": "1:10:46", "throughput": 5562.16, "total_tokens": 15690784} {"current_steps": 25735, "total_steps": 64460, "loss": 0.2248, "lr": 7.5117151427531305e-06, "epoch": 7.984796773192677, "percentage": 39.92, "elapsed_time": "0:47:01", "remaining_time": "1:10:45", "throughput": 5562.12, "total_tokens": 15693280} {"current_steps": 25740, "total_steps": 64460, "loss": 0.239, "lr": 7.510544455684341e-06, "epoch": 7.986348122866894, "percentage": 39.93, "elapsed_time": "0:47:01", "remaining_time": "1:10:45", "throughput": 5562.22, "total_tokens": 15696480} {"current_steps": 25745, "total_steps": 64460, "loss": 0.2267, "lr": 7.509373584562912e-06, "epoch": 7.987899472541111, "percentage": 39.94, "elapsed_time": "0:47:02", "remaining_time": "1:10:44", "throughput": 5562.47, "total_tokens": 15700320} {"current_steps": 25750, "total_steps": 64460, "loss": 0.2313, "lr": 7.5082025294746854e-06, "epoch": 7.9894508222153275, "percentage": 39.95, "elapsed_time": "0:47:03", "remaining_time": "1:10:44", "throughput": 5562.78, "total_tokens": 15704736} {"current_steps": 25755, "total_steps": 64460, "loss": 0.2325, "lr": 7.507031290505511e-06, "epoch": 7.991002171889544, "percentage": 39.96, "elapsed_time": "0:47:03", "remaining_time": "1:10:43", "throughput": 5562.92, "total_tokens": 15707872} {"current_steps": 25760, "total_steps": 64460, "loss": 0.228, "lr": 7.505859867741255e-06, "epoch": 7.99255352156376, "percentage": 39.96, "elapsed_time": "0:47:04", "remaining_time": "1:10:42", "throughput": 5562.96, "total_tokens": 15710688} {"current_steps": 25765, "total_steps": 64460, "loss": 0.2337, "lr": 7.504688261267799e-06, "epoch": 7.994104871237977, "percentage": 39.97, "elapsed_time": "0:47:04", "remaining_time": "1:10:42", "throughput": 5562.88, "total_tokens": 15713056} {"current_steps": 25770, "total_steps": 64460, "loss": 0.2323, "lr": 7.503516471171031e-06, "epoch": 7.995656220912194, "percentage": 39.98, "elapsed_time": "0:47:05", "remaining_time": "1:10:41", "throughput": 5562.86, "total_tokens": 15715680} {"current_steps": 25775, "total_steps": 64460, "loss": 0.2232, "lr": 7.50234449753686e-06, "epoch": 7.9972075705864105, "percentage": 39.99, "elapsed_time": "0:47:05", "remaining_time": "1:10:40", "throughput": 5562.75, "total_tokens": 15717920} {"current_steps": 25780, "total_steps": 64460, "loss": 0.2268, "lr": 7.501172340451206e-06, "epoch": 7.998758920260626, "percentage": 39.99, "elapsed_time": "0:47:06", "remaining_time": "1:10:40", "throughput": 5562.89, "total_tokens": 15721792} {"current_steps": 25784, "total_steps": 64460, "eval_loss": 0.2319650948047638, "epoch": 8.0, "percentage": 40.0, "elapsed_time": "0:47:41", "remaining_time": "1:11:32", "throughput": 5495.2, "total_tokens": 15724160} {"current_steps": 25785, "total_steps": 64460, "loss": 0.2337, "lr": 7.500000000000001e-06, "epoch": 8.000310269934843, "percentage": 40.0, "elapsed_time": "0:47:45", "remaining_time": "1:11:37", "throughput": 5487.82, "total_tokens": 15724544} {"current_steps": 25790, "total_steps": 64460, "loss": 0.2303, "lr": 7.4988274762691915e-06, "epoch": 8.001861619609059, "percentage": 40.01, "elapsed_time": "0:47:45", "remaining_time": "1:11:37", "throughput": 5487.81, "total_tokens": 15727456} {"current_steps": 25795, "total_steps": 64460, "loss": 0.2362, "lr": 7.497654769344737e-06, "epoch": 8.003412969283277, "percentage": 40.02, "elapsed_time": "0:47:46", "remaining_time": "1:11:36", "throughput": 5487.66, "total_tokens": 15729792} {"current_steps": 25800, "total_steps": 64460, "loss": 0.2318, "lr": 7.496481879312613e-06, "epoch": 8.004964318957493, "percentage": 40.02, "elapsed_time": "0:47:46", "remaining_time": "1:11:35", "throughput": 5487.55, "total_tokens": 15732256} {"current_steps": 25805, "total_steps": 64460, "loss": 0.2227, "lr": 7.495308806258803e-06, "epoch": 8.00651566863171, "percentage": 40.03, "elapsed_time": "0:47:47", "remaining_time": "1:11:35", "throughput": 5487.5, "total_tokens": 15734720} {"current_steps": 25810, "total_steps": 64460, "loss": 0.228, "lr": 7.494135550269308e-06, "epoch": 8.008067018305926, "percentage": 40.04, "elapsed_time": "0:47:47", "remaining_time": "1:11:34", "throughput": 5487.56, "total_tokens": 15737952} {"current_steps": 25815, "total_steps": 64460, "loss": 0.2268, "lr": 7.492962111430142e-06, "epoch": 8.009618367980142, "percentage": 40.05, "elapsed_time": "0:47:48", "remaining_time": "1:11:34", "throughput": 5487.49, "total_tokens": 15740896} {"current_steps": 25820, "total_steps": 64460, "loss": 0.2258, "lr": 7.491788489827333e-06, "epoch": 8.01116971765436, "percentage": 40.06, "elapsed_time": "0:47:49", "remaining_time": "1:11:33", "throughput": 5487.35, "total_tokens": 15743584} {"current_steps": 25825, "total_steps": 64460, "loss": 0.2216, "lr": 7.490614685546921e-06, "epoch": 8.012721067328576, "percentage": 40.06, "elapsed_time": "0:47:49", "remaining_time": "1:11:32", "throughput": 5487.27, "total_tokens": 15746208} {"current_steps": 25830, "total_steps": 64460, "loss": 0.2262, "lr": 7.489440698674959e-06, "epoch": 8.014272417002793, "percentage": 40.07, "elapsed_time": "0:47:50", "remaining_time": "1:11:32", "throughput": 5487.18, "total_tokens": 15748960} {"current_steps": 25835, "total_steps": 64460, "loss": 0.2299, "lr": 7.4882665292975135e-06, "epoch": 8.01582376667701, "percentage": 40.08, "elapsed_time": "0:47:50", "remaining_time": "1:11:32", "throughput": 5487.42, "total_tokens": 15753632} {"current_steps": 25840, "total_steps": 64460, "loss": 0.2404, "lr": 7.4870921775006665e-06, "epoch": 8.017375116351225, "percentage": 40.09, "elapsed_time": "0:47:51", "remaining_time": "1:11:31", "throughput": 5487.4, "total_tokens": 15756384} {"current_steps": 25845, "total_steps": 64460, "loss": 0.2298, "lr": 7.485917643370512e-06, "epoch": 8.018926466025443, "percentage": 40.09, "elapsed_time": "0:47:51", "remaining_time": "1:11:30", "throughput": 5487.47, "total_tokens": 15759232} {"current_steps": 25850, "total_steps": 64460, "loss": 0.2259, "lr": 7.484742926993156e-06, "epoch": 8.020477815699659, "percentage": 40.1, "elapsed_time": "0:47:52", "remaining_time": "1:11:30", "throughput": 5487.46, "total_tokens": 15761824} {"current_steps": 25855, "total_steps": 64460, "loss": 0.2312, "lr": 7.48356802845472e-06, "epoch": 8.022029165373874, "percentage": 40.11, "elapsed_time": "0:47:52", "remaining_time": "1:11:29", "throughput": 5487.7, "total_tokens": 15765600} {"current_steps": 25860, "total_steps": 64460, "loss": 0.2243, "lr": 7.482392947841337e-06, "epoch": 8.023580515048092, "percentage": 40.12, "elapsed_time": "0:47:53", "remaining_time": "1:11:29", "throughput": 5487.56, "total_tokens": 15768096} {"current_steps": 25865, "total_steps": 64460, "loss": 0.2298, "lr": 7.481217685239155e-06, "epoch": 8.025131864722308, "percentage": 40.13, "elapsed_time": "0:47:53", "remaining_time": "1:11:28", "throughput": 5487.49, "total_tokens": 15770880} {"current_steps": 25870, "total_steps": 64460, "loss": 0.2399, "lr": 7.4800422407343355e-06, "epoch": 8.026683214396526, "percentage": 40.13, "elapsed_time": "0:47:54", "remaining_time": "1:11:27", "throughput": 5487.56, "total_tokens": 15773760} {"current_steps": 25875, "total_steps": 64460, "loss": 0.2393, "lr": 7.478866614413052e-06, "epoch": 8.028234564070742, "percentage": 40.14, "elapsed_time": "0:47:55", "remaining_time": "1:11:27", "throughput": 5487.6, "total_tokens": 15776992} {"current_steps": 25880, "total_steps": 64460, "loss": 0.2416, "lr": 7.477690806361489e-06, "epoch": 8.029785913744957, "percentage": 40.15, "elapsed_time": "0:47:55", "remaining_time": "1:11:26", "throughput": 5487.72, "total_tokens": 15780128} {"current_steps": 25885, "total_steps": 64460, "loss": 0.2336, "lr": 7.476514816665852e-06, "epoch": 8.031337263419175, "percentage": 40.16, "elapsed_time": "0:47:56", "remaining_time": "1:11:26", "throughput": 5487.7, "total_tokens": 15783232} {"current_steps": 25890, "total_steps": 64460, "loss": 0.226, "lr": 7.4753386454123514e-06, "epoch": 8.032888613093391, "percentage": 40.16, "elapsed_time": "0:47:56", "remaining_time": "1:11:25", "throughput": 5487.63, "total_tokens": 15785888} {"current_steps": 25895, "total_steps": 64460, "loss": 0.2218, "lr": 7.474162292687216e-06, "epoch": 8.034439962767609, "percentage": 40.17, "elapsed_time": "0:47:57", "remaining_time": "1:11:24", "throughput": 5487.83, "total_tokens": 15789280} {"current_steps": 25900, "total_steps": 64460, "loss": 0.2267, "lr": 7.472985758576686e-06, "epoch": 8.035991312441825, "percentage": 40.18, "elapsed_time": "0:47:57", "remaining_time": "1:11:24", "throughput": 5487.89, "total_tokens": 15792928} {"current_steps": 25905, "total_steps": 64460, "loss": 0.2375, "lr": 7.471809043167016e-06, "epoch": 8.03754266211604, "percentage": 40.19, "elapsed_time": "0:47:58", "remaining_time": "1:11:23", "throughput": 5487.98, "total_tokens": 15795936} {"current_steps": 25910, "total_steps": 64460, "loss": 0.2302, "lr": 7.470632146544472e-06, "epoch": 8.039094011790258, "percentage": 40.2, "elapsed_time": "0:47:58", "remaining_time": "1:11:23", "throughput": 5487.93, "total_tokens": 15798592} {"current_steps": 25915, "total_steps": 64460, "loss": 0.2288, "lr": 7.469455068795336e-06, "epoch": 8.040645361464474, "percentage": 40.2, "elapsed_time": "0:47:59", "remaining_time": "1:11:22", "throughput": 5488.03, "total_tokens": 15801632} {"current_steps": 25920, "total_steps": 64460, "loss": 0.2235, "lr": 7.4682778100058995e-06, "epoch": 8.04219671113869, "percentage": 40.21, "elapsed_time": "0:47:59", "remaining_time": "1:11:22", "throughput": 5488.23, "total_tokens": 15805344} {"current_steps": 25925, "total_steps": 64460, "loss": 0.2267, "lr": 7.467100370262472e-06, "epoch": 8.043748060812907, "percentage": 40.22, "elapsed_time": "0:48:00", "remaining_time": "1:11:21", "throughput": 5488.2, "total_tokens": 15808800} {"current_steps": 25930, "total_steps": 64460, "loss": 0.2371, "lr": 7.465922749651371e-06, "epoch": 8.045299410487123, "percentage": 40.23, "elapsed_time": "0:48:00", "remaining_time": "1:11:20", "throughput": 5488.15, "total_tokens": 15811200} {"current_steps": 25935, "total_steps": 64460, "loss": 0.2284, "lr": 7.464744948258933e-06, "epoch": 8.046850760161341, "percentage": 40.23, "elapsed_time": "0:48:01", "remaining_time": "1:11:20", "throughput": 5488.14, "total_tokens": 15813792} {"current_steps": 25940, "total_steps": 64460, "loss": 0.2376, "lr": 7.463566966171503e-06, "epoch": 8.048402109835557, "percentage": 40.24, "elapsed_time": "0:48:02", "remaining_time": "1:11:19", "throughput": 5488.3, "total_tokens": 15817760} {"current_steps": 25945, "total_steps": 64460, "loss": 0.2428, "lr": 7.46238880347544e-06, "epoch": 8.049953459509773, "percentage": 40.25, "elapsed_time": "0:48:03", "remaining_time": "1:11:19", "throughput": 5488.79, "total_tokens": 15824480} {"current_steps": 25950, "total_steps": 64460, "loss": 0.2242, "lr": 7.46121046025712e-06, "epoch": 8.05150480918399, "percentage": 40.26, "elapsed_time": "0:48:03", "remaining_time": "1:11:19", "throughput": 5488.89, "total_tokens": 15827808} {"current_steps": 25955, "total_steps": 64460, "loss": 0.2185, "lr": 7.460031936602927e-06, "epoch": 8.053056158858206, "percentage": 40.27, "elapsed_time": "0:48:04", "remaining_time": "1:11:18", "throughput": 5489.05, "total_tokens": 15831584} {"current_steps": 25960, "total_steps": 64460, "loss": 0.2329, "lr": 7.4588532325992636e-06, "epoch": 8.054607508532424, "percentage": 40.27, "elapsed_time": "0:48:04", "remaining_time": "1:11:18", "throughput": 5489.18, "total_tokens": 15835104} {"current_steps": 25965, "total_steps": 64460, "loss": 0.2317, "lr": 7.4576743483325395e-06, "epoch": 8.05615885820664, "percentage": 40.28, "elapsed_time": "0:48:05", "remaining_time": "1:11:17", "throughput": 5489.45, "total_tokens": 15839200} {"current_steps": 25970, "total_steps": 64460, "loss": 0.2381, "lr": 7.4564952838891835e-06, "epoch": 8.057710207880856, "percentage": 40.29, "elapsed_time": "0:48:05", "remaining_time": "1:11:17", "throughput": 5489.38, "total_tokens": 15841568} {"current_steps": 25975, "total_steps": 64460, "loss": 0.2236, "lr": 7.455316039355633e-06, "epoch": 8.059261557555073, "percentage": 40.3, "elapsed_time": "0:48:06", "remaining_time": "1:11:16", "throughput": 5489.51, "total_tokens": 15844992} {"current_steps": 25980, "total_steps": 64460, "loss": 0.2322, "lr": 7.454136614818343e-06, "epoch": 8.06081290722929, "percentage": 40.3, "elapsed_time": "0:48:06", "remaining_time": "1:11:15", "throughput": 5489.4, "total_tokens": 15847456} {"current_steps": 25985, "total_steps": 64460, "loss": 0.2303, "lr": 7.452957010363777e-06, "epoch": 8.062364256903505, "percentage": 40.31, "elapsed_time": "0:48:07", "remaining_time": "1:11:15", "throughput": 5489.54, "total_tokens": 15850848} {"current_steps": 25990, "total_steps": 64460, "loss": 0.2406, "lr": 7.451777226078415e-06, "epoch": 8.063915606577723, "percentage": 40.32, "elapsed_time": "0:48:07", "remaining_time": "1:11:14", "throughput": 5489.65, "total_tokens": 15854080} {"current_steps": 25995, "total_steps": 64460, "loss": 0.2334, "lr": 7.450597262048749e-06, "epoch": 8.065466956251939, "percentage": 40.33, "elapsed_time": "0:48:08", "remaining_time": "1:11:14", "throughput": 5489.53, "total_tokens": 15856384} {"current_steps": 26000, "total_steps": 64460, "loss": 0.231, "lr": 7.449417118361284e-06, "epoch": 8.067018305926156, "percentage": 40.34, "elapsed_time": "0:48:08", "remaining_time": "1:11:13", "throughput": 5489.55, "total_tokens": 15859200} {"current_steps": 26005, "total_steps": 64460, "loss": 0.2292, "lr": 7.448236795102537e-06, "epoch": 8.068569655600372, "percentage": 40.34, "elapsed_time": "0:48:09", "remaining_time": "1:11:12", "throughput": 5489.65, "total_tokens": 15862432} {"current_steps": 26010, "total_steps": 64460, "loss": 0.2251, "lr": 7.4470562923590425e-06, "epoch": 8.070121005274588, "percentage": 40.35, "elapsed_time": "0:48:09", "remaining_time": "1:11:12", "throughput": 5489.58, "total_tokens": 15864832} {"current_steps": 26015, "total_steps": 64460, "loss": 0.2372, "lr": 7.445875610217346e-06, "epoch": 8.071672354948806, "percentage": 40.36, "elapsed_time": "0:48:10", "remaining_time": "1:11:11", "throughput": 5489.55, "total_tokens": 15867296} {"current_steps": 26020, "total_steps": 64460, "loss": 0.2317, "lr": 7.4446947487640035e-06, "epoch": 8.073223704623022, "percentage": 40.37, "elapsed_time": "0:48:10", "remaining_time": "1:11:10", "throughput": 5489.59, "total_tokens": 15870176} {"current_steps": 26025, "total_steps": 64460, "loss": 0.2244, "lr": 7.443513708085586e-06, "epoch": 8.07477505429724, "percentage": 40.37, "elapsed_time": "0:48:11", "remaining_time": "1:11:10", "throughput": 5489.8, "total_tokens": 15873824} {"current_steps": 26030, "total_steps": 64460, "loss": 0.2306, "lr": 7.442332488268678e-06, "epoch": 8.076326403971455, "percentage": 40.38, "elapsed_time": "0:48:12", "remaining_time": "1:11:09", "throughput": 5489.9, "total_tokens": 15877088} {"current_steps": 26035, "total_steps": 64460, "loss": 0.2277, "lr": 7.4411510893998766e-06, "epoch": 8.077877753645671, "percentage": 40.39, "elapsed_time": "0:48:12", "remaining_time": "1:11:09", "throughput": 5490.16, "total_tokens": 15881216} {"current_steps": 26040, "total_steps": 64460, "loss": 0.2261, "lr": 7.4399695115657926e-06, "epoch": 8.079429103319889, "percentage": 40.4, "elapsed_time": "0:48:13", "remaining_time": "1:11:08", "throughput": 5490.13, "total_tokens": 15883776} {"current_steps": 26045, "total_steps": 64460, "loss": 0.2279, "lr": 7.4387877548530495e-06, "epoch": 8.080980452994105, "percentage": 40.4, "elapsed_time": "0:48:13", "remaining_time": "1:11:07", "throughput": 5490.05, "total_tokens": 15886304} {"current_steps": 26050, "total_steps": 64460, "loss": 0.2315, "lr": 7.437605819348286e-06, "epoch": 8.08253180266832, "percentage": 40.41, "elapsed_time": "0:48:14", "remaining_time": "1:11:07", "throughput": 5490.12, "total_tokens": 15889408} {"current_steps": 26055, "total_steps": 64460, "loss": 0.2365, "lr": 7.43642370513815e-06, "epoch": 8.084083152342538, "percentage": 40.42, "elapsed_time": "0:48:14", "remaining_time": "1:11:06", "throughput": 5490.13, "total_tokens": 15892192} {"current_steps": 26060, "total_steps": 64460, "loss": 0.2355, "lr": 7.4352414123093045e-06, "epoch": 8.085634502016754, "percentage": 40.43, "elapsed_time": "0:48:15", "remaining_time": "1:11:06", "throughput": 5490.12, "total_tokens": 15895232} {"current_steps": 26065, "total_steps": 64460, "loss": 0.234, "lr": 7.434058940948424e-06, "epoch": 8.087185851690972, "percentage": 40.44, "elapsed_time": "0:48:15", "remaining_time": "1:11:05", "throughput": 5490.17, "total_tokens": 15898432} {"current_steps": 26070, "total_steps": 64460, "loss": 0.227, "lr": 7.432876291142202e-06, "epoch": 8.088737201365188, "percentage": 40.44, "elapsed_time": "0:48:16", "remaining_time": "1:11:05", "throughput": 5490.06, "total_tokens": 15900960} {"current_steps": 26075, "total_steps": 64460, "loss": 0.2328, "lr": 7.431693462977338e-06, "epoch": 8.090288551039404, "percentage": 40.45, "elapsed_time": "0:48:16", "remaining_time": "1:11:04", "throughput": 5490.16, "total_tokens": 15903872} {"current_steps": 26080, "total_steps": 64460, "loss": 0.2254, "lr": 7.430510456540547e-06, "epoch": 8.091839900713621, "percentage": 40.46, "elapsed_time": "0:48:17", "remaining_time": "1:11:03", "throughput": 5490.23, "total_tokens": 15906912} {"current_steps": 26085, "total_steps": 64460, "loss": 0.2288, "lr": 7.429327271918559e-06, "epoch": 8.093391250387837, "percentage": 40.47, "elapsed_time": "0:48:17", "remaining_time": "1:11:03", "throughput": 5490.39, "total_tokens": 15910848} {"current_steps": 26090, "total_steps": 64460, "loss": 0.2214, "lr": 7.428143909198113e-06, "epoch": 8.094942600062055, "percentage": 40.47, "elapsed_time": "0:48:18", "remaining_time": "1:11:02", "throughput": 5490.48, "total_tokens": 15913984} {"current_steps": 26095, "total_steps": 64460, "loss": 0.2311, "lr": 7.426960368465965e-06, "epoch": 8.09649394973627, "percentage": 40.48, "elapsed_time": "0:48:18", "remaining_time": "1:11:02", "throughput": 5490.52, "total_tokens": 15916672} {"current_steps": 26100, "total_steps": 64460, "loss": 0.2223, "lr": 7.425776649808885e-06, "epoch": 8.098045299410487, "percentage": 40.49, "elapsed_time": "0:48:19", "remaining_time": "1:11:01", "throughput": 5490.52, "total_tokens": 15919296} {"current_steps": 26105, "total_steps": 64460, "loss": 0.2252, "lr": 7.424592753313649e-06, "epoch": 8.099596649084704, "percentage": 40.5, "elapsed_time": "0:48:19", "remaining_time": "1:11:00", "throughput": 5490.61, "total_tokens": 15922336} {"current_steps": 26110, "total_steps": 64460, "loss": 0.2271, "lr": 7.423408679067053e-06, "epoch": 8.10114799875892, "percentage": 40.51, "elapsed_time": "0:48:20", "remaining_time": "1:11:00", "throughput": 5490.82, "total_tokens": 15926208} {"current_steps": 26115, "total_steps": 64460, "loss": 0.2342, "lr": 7.422224427155903e-06, "epoch": 8.102699348433136, "percentage": 40.51, "elapsed_time": "0:48:21", "remaining_time": "1:10:59", "throughput": 5490.94, "total_tokens": 15929408} {"current_steps": 26120, "total_steps": 64460, "loss": 0.2266, "lr": 7.421039997667019e-06, "epoch": 8.104250698107354, "percentage": 40.52, "elapsed_time": "0:48:21", "remaining_time": "1:10:59", "throughput": 5491.12, "total_tokens": 15933024} {"current_steps": 26125, "total_steps": 64460, "loss": 0.2228, "lr": 7.419855390687234e-06, "epoch": 8.10580204778157, "percentage": 40.53, "elapsed_time": "0:48:22", "remaining_time": "1:10:58", "throughput": 5491.23, "total_tokens": 15936448} {"current_steps": 26130, "total_steps": 64460, "loss": 0.2403, "lr": 7.418670606303393e-06, "epoch": 8.107353397455787, "percentage": 40.54, "elapsed_time": "0:48:22", "remaining_time": "1:10:57", "throughput": 5491.25, "total_tokens": 15939168} {"current_steps": 26135, "total_steps": 64460, "loss": 0.2326, "lr": 7.417485644602355e-06, "epoch": 8.108904747130003, "percentage": 40.54, "elapsed_time": "0:48:23", "remaining_time": "1:10:57", "throughput": 5491.38, "total_tokens": 15942784} {"current_steps": 26140, "total_steps": 64460, "loss": 0.2367, "lr": 7.4163005056709925e-06, "epoch": 8.110456096804219, "percentage": 40.55, "elapsed_time": "0:48:23", "remaining_time": "1:10:56", "throughput": 5491.32, "total_tokens": 15945248} {"current_steps": 26145, "total_steps": 64460, "loss": 0.2182, "lr": 7.41511518959619e-06, "epoch": 8.112007446478437, "percentage": 40.56, "elapsed_time": "0:48:24", "remaining_time": "1:10:56", "throughput": 5491.6, "total_tokens": 15949440} {"current_steps": 26150, "total_steps": 64460, "loss": 0.2379, "lr": 7.413929696464845e-06, "epoch": 8.113558796152653, "percentage": 40.57, "elapsed_time": "0:48:24", "remaining_time": "1:10:55", "throughput": 5491.57, "total_tokens": 15952224} {"current_steps": 26155, "total_steps": 64460, "loss": 0.2306, "lr": 7.412744026363867e-06, "epoch": 8.11511014582687, "percentage": 40.58, "elapsed_time": "0:48:25", "remaining_time": "1:10:54", "throughput": 5491.59, "total_tokens": 15954976} {"current_steps": 26160, "total_steps": 64460, "loss": 0.2353, "lr": 7.411558179380183e-06, "epoch": 8.116661495501086, "percentage": 40.58, "elapsed_time": "0:48:25", "remaining_time": "1:10:54", "throughput": 5491.68, "total_tokens": 15957952} {"current_steps": 26165, "total_steps": 64460, "loss": 0.2225, "lr": 7.410372155600724e-06, "epoch": 8.118212845175302, "percentage": 40.59, "elapsed_time": "0:48:26", "remaining_time": "1:10:53", "throughput": 5491.83, "total_tokens": 15961024} {"current_steps": 26170, "total_steps": 64460, "loss": 0.2317, "lr": 7.4091859551124454e-06, "epoch": 8.11976419484952, "percentage": 40.6, "elapsed_time": "0:48:26", "remaining_time": "1:10:53", "throughput": 5491.77, "total_tokens": 15963808} {"current_steps": 26175, "total_steps": 64460, "loss": 0.2264, "lr": 7.407999578002307e-06, "epoch": 8.121315544523735, "percentage": 40.61, "elapsed_time": "0:48:27", "remaining_time": "1:10:52", "throughput": 5491.64, "total_tokens": 15965984} {"current_steps": 26180, "total_steps": 64460, "loss": 0.2299, "lr": 7.406813024357284e-06, "epoch": 8.122866894197951, "percentage": 40.61, "elapsed_time": "0:48:27", "remaining_time": "1:10:51", "throughput": 5491.73, "total_tokens": 15969312} {"current_steps": 26185, "total_steps": 64460, "loss": 0.2442, "lr": 7.405626294264366e-06, "epoch": 8.124418243872169, "percentage": 40.62, "elapsed_time": "0:48:28", "remaining_time": "1:10:51", "throughput": 5491.77, "total_tokens": 15972032} {"current_steps": 26190, "total_steps": 64460, "loss": 0.241, "lr": 7.404439387810553e-06, "epoch": 8.125969593546385, "percentage": 40.63, "elapsed_time": "0:48:28", "remaining_time": "1:10:50", "throughput": 5491.75, "total_tokens": 15974688} {"current_steps": 26195, "total_steps": 64460, "loss": 0.2246, "lr": 7.403252305082861e-06, "epoch": 8.127520943220603, "percentage": 40.64, "elapsed_time": "0:48:29", "remaining_time": "1:10:49", "throughput": 5491.76, "total_tokens": 15977408} {"current_steps": 26200, "total_steps": 64460, "loss": 0.2244, "lr": 7.402065046168314e-06, "epoch": 8.129072292894818, "percentage": 40.65, "elapsed_time": "0:48:29", "remaining_time": "1:10:49", "throughput": 5491.78, "total_tokens": 15980160} {"current_steps": 26205, "total_steps": 64460, "loss": 0.2409, "lr": 7.4008776111539575e-06, "epoch": 8.130623642569034, "percentage": 40.65, "elapsed_time": "0:48:30", "remaining_time": "1:10:48", "throughput": 5491.61, "total_tokens": 15982272} {"current_steps": 26210, "total_steps": 64460, "loss": 0.2355, "lr": 7.399690000126839e-06, "epoch": 8.132174992243252, "percentage": 40.66, "elapsed_time": "0:48:30", "remaining_time": "1:10:47", "throughput": 5491.47, "total_tokens": 15984512} {"current_steps": 26215, "total_steps": 64460, "loss": 0.2314, "lr": 7.398502213174028e-06, "epoch": 8.133726341917468, "percentage": 40.67, "elapsed_time": "0:48:31", "remaining_time": "1:10:47", "throughput": 5491.8, "total_tokens": 15989344} {"current_steps": 26220, "total_steps": 64460, "loss": 0.2333, "lr": 7.397314250382602e-06, "epoch": 8.135277691591686, "percentage": 40.68, "elapsed_time": "0:48:31", "remaining_time": "1:10:46", "throughput": 5491.79, "total_tokens": 15991840} {"current_steps": 26225, "total_steps": 64460, "loss": 0.227, "lr": 7.396126111839654e-06, "epoch": 8.136829041265901, "percentage": 40.68, "elapsed_time": "0:48:32", "remaining_time": "1:10:46", "throughput": 5491.85, "total_tokens": 15994688} {"current_steps": 26230, "total_steps": 64460, "loss": 0.2227, "lr": 7.394937797632286e-06, "epoch": 8.138380390940117, "percentage": 40.69, "elapsed_time": "0:48:32", "remaining_time": "1:10:45", "throughput": 5491.91, "total_tokens": 15997760} {"current_steps": 26235, "total_steps": 64460, "loss": 0.2333, "lr": 7.3937493078476185e-06, "epoch": 8.139931740614335, "percentage": 40.7, "elapsed_time": "0:48:33", "remaining_time": "1:10:45", "throughput": 5492.08, "total_tokens": 16001184} {"current_steps": 26240, "total_steps": 64460, "loss": 0.2286, "lr": 7.39256064257278e-06, "epoch": 8.14148309028855, "percentage": 40.71, "elapsed_time": "0:48:34", "remaining_time": "1:10:44", "throughput": 5492.27, "total_tokens": 16004832} {"current_steps": 26245, "total_steps": 64460, "loss": 0.236, "lr": 7.391371801894915e-06, "epoch": 8.143034439962767, "percentage": 40.72, "elapsed_time": "0:48:34", "remaining_time": "1:10:43", "throughput": 5492.31, "total_tokens": 16007584} {"current_steps": 26250, "total_steps": 64460, "loss": 0.2286, "lr": 7.3901827859011775e-06, "epoch": 8.144585789636984, "percentage": 40.72, "elapsed_time": "0:48:35", "remaining_time": "1:10:43", "throughput": 5492.5, "total_tokens": 16010976} {"current_steps": 26255, "total_steps": 64460, "loss": 0.2306, "lr": 7.388993594678739e-06, "epoch": 8.1461371393112, "percentage": 40.73, "elapsed_time": "0:48:35", "remaining_time": "1:10:42", "throughput": 5492.57, "total_tokens": 16014080} {"current_steps": 26260, "total_steps": 64460, "loss": 0.2309, "lr": 7.387804228314778e-06, "epoch": 8.147688488985418, "percentage": 40.74, "elapsed_time": "0:48:36", "remaining_time": "1:10:41", "throughput": 5492.57, "total_tokens": 16016640} {"current_steps": 26265, "total_steps": 64460, "loss": 0.2228, "lr": 7.386614686896493e-06, "epoch": 8.149239838659634, "percentage": 40.75, "elapsed_time": "0:48:36", "remaining_time": "1:10:41", "throughput": 5492.82, "total_tokens": 16020960} {"current_steps": 26270, "total_steps": 64460, "loss": 0.2258, "lr": 7.385424970511088e-06, "epoch": 8.15079118833385, "percentage": 40.75, "elapsed_time": "0:48:37", "remaining_time": "1:10:40", "throughput": 5492.94, "total_tokens": 16024320} {"current_steps": 26275, "total_steps": 64460, "loss": 0.2286, "lr": 7.384235079245787e-06, "epoch": 8.152342538008067, "percentage": 40.76, "elapsed_time": "0:48:37", "remaining_time": "1:10:40", "throughput": 5492.98, "total_tokens": 16027168} {"current_steps": 26280, "total_steps": 64460, "loss": 0.2254, "lr": 7.38304501318782e-06, "epoch": 8.153893887682283, "percentage": 40.77, "elapsed_time": "0:48:38", "remaining_time": "1:10:39", "throughput": 5492.99, "total_tokens": 16029696} {"current_steps": 26285, "total_steps": 64460, "loss": 0.2335, "lr": 7.381854772424435e-06, "epoch": 8.155445237356501, "percentage": 40.78, "elapsed_time": "0:48:38", "remaining_time": "1:10:38", "throughput": 5492.85, "total_tokens": 16031808} {"current_steps": 26290, "total_steps": 64460, "loss": 0.2196, "lr": 7.380664357042889e-06, "epoch": 8.156996587030717, "percentage": 40.78, "elapsed_time": "0:48:39", "remaining_time": "1:10:38", "throughput": 5492.78, "total_tokens": 16034112} {"current_steps": 26295, "total_steps": 64460, "loss": 0.2295, "lr": 7.379473767130455e-06, "epoch": 8.158547936704933, "percentage": 40.79, "elapsed_time": "0:48:39", "remaining_time": "1:10:37", "throughput": 5492.96, "total_tokens": 16037504} {"current_steps": 26300, "total_steps": 64460, "loss": 0.2254, "lr": 7.378283002774417e-06, "epoch": 8.16009928637915, "percentage": 40.8, "elapsed_time": "0:48:40", "remaining_time": "1:10:37", "throughput": 5492.99, "total_tokens": 16040384} {"current_steps": 26305, "total_steps": 64460, "loss": 0.2241, "lr": 7.3770920640620715e-06, "epoch": 8.161650636053366, "percentage": 40.81, "elapsed_time": "0:48:40", "remaining_time": "1:10:36", "throughput": 5493.07, "total_tokens": 16043200} {"current_steps": 26310, "total_steps": 64460, "loss": 0.2273, "lr": 7.375900951080728e-06, "epoch": 8.163201985727582, "percentage": 40.82, "elapsed_time": "0:48:41", "remaining_time": "1:10:35", "throughput": 5493.04, "total_tokens": 16045728} {"current_steps": 26315, "total_steps": 64460, "loss": 0.2401, "lr": 7.374709663917711e-06, "epoch": 8.1647533354018, "percentage": 40.82, "elapsed_time": "0:48:41", "remaining_time": "1:10:35", "throughput": 5493.23, "total_tokens": 16049472} {"current_steps": 26320, "total_steps": 64460, "loss": 0.2326, "lr": 7.373518202660352e-06, "epoch": 8.166304685076016, "percentage": 40.83, "elapsed_time": "0:48:42", "remaining_time": "1:10:34", "throughput": 5493.37, "total_tokens": 16052992} {"current_steps": 26325, "total_steps": 64460, "loss": 0.2305, "lr": 7.372326567396004e-06, "epoch": 8.167856034750233, "percentage": 40.84, "elapsed_time": "0:48:42", "remaining_time": "1:10:33", "throughput": 5493.48, "total_tokens": 16056192} {"current_steps": 26330, "total_steps": 64460, "loss": 0.2382, "lr": 7.371134758212027e-06, "epoch": 8.16940738442445, "percentage": 40.85, "elapsed_time": "0:48:43", "remaining_time": "1:10:33", "throughput": 5493.53, "total_tokens": 16059296} {"current_steps": 26335, "total_steps": 64460, "loss": 0.2382, "lr": 7.369942775195793e-06, "epoch": 8.170958734098665, "percentage": 40.85, "elapsed_time": "0:48:43", "remaining_time": "1:10:32", "throughput": 5493.62, "total_tokens": 16062368} {"current_steps": 26340, "total_steps": 64460, "loss": 0.2283, "lr": 7.36875061843469e-06, "epoch": 8.172510083772883, "percentage": 40.86, "elapsed_time": "0:48:44", "remaining_time": "1:10:32", "throughput": 5493.7, "total_tokens": 16065408} {"current_steps": 26345, "total_steps": 64460, "loss": 0.2321, "lr": 7.3675582880161155e-06, "epoch": 8.174061433447099, "percentage": 40.87, "elapsed_time": "0:48:44", "remaining_time": "1:10:31", "throughput": 5493.74, "total_tokens": 16068416} {"current_steps": 26350, "total_steps": 64460, "loss": 0.2248, "lr": 7.366365784027483e-06, "epoch": 8.175612783121316, "percentage": 40.88, "elapsed_time": "0:48:45", "remaining_time": "1:10:30", "throughput": 5493.82, "total_tokens": 16071456} {"current_steps": 26355, "total_steps": 64460, "loss": 0.2264, "lr": 7.365173106556216e-06, "epoch": 8.177164132795532, "percentage": 40.89, "elapsed_time": "0:48:45", "remaining_time": "1:10:30", "throughput": 5493.9, "total_tokens": 16074400} {"current_steps": 26360, "total_steps": 64460, "loss": 0.2228, "lr": 7.3639802556897535e-06, "epoch": 8.178715482469748, "percentage": 40.89, "elapsed_time": "0:48:46", "remaining_time": "1:10:29", "throughput": 5493.9, "total_tokens": 16077216} {"current_steps": 26365, "total_steps": 64460, "loss": 0.2312, "lr": 7.362787231515543e-06, "epoch": 8.180266832143966, "percentage": 40.9, "elapsed_time": "0:48:46", "remaining_time": "1:10:29", "throughput": 5493.77, "total_tokens": 16079552} {"current_steps": 26370, "total_steps": 64460, "loss": 0.2307, "lr": 7.3615940341210505e-06, "epoch": 8.181818181818182, "percentage": 40.91, "elapsed_time": "0:48:47", "remaining_time": "1:10:28", "throughput": 5493.7, "total_tokens": 16081920} {"current_steps": 26375, "total_steps": 64460, "loss": 0.2227, "lr": 7.360400663593748e-06, "epoch": 8.183369531492398, "percentage": 40.92, "elapsed_time": "0:48:47", "remaining_time": "1:10:27", "throughput": 5493.94, "total_tokens": 16085920} {"current_steps": 26380, "total_steps": 64460, "loss": 0.2283, "lr": 7.359207120021126e-06, "epoch": 8.184920881166615, "percentage": 40.92, "elapsed_time": "0:48:48", "remaining_time": "1:10:27", "throughput": 5494.08, "total_tokens": 16089120} {"current_steps": 26385, "total_steps": 64460, "loss": 0.2364, "lr": 7.3580134034906855e-06, "epoch": 8.186472230840831, "percentage": 40.93, "elapsed_time": "0:48:49", "remaining_time": "1:10:26", "throughput": 5494.39, "total_tokens": 16093824} {"current_steps": 26390, "total_steps": 64460, "loss": 0.2319, "lr": 7.356819514089939e-06, "epoch": 8.188023580515049, "percentage": 40.94, "elapsed_time": "0:48:49", "remaining_time": "1:10:26", "throughput": 5494.45, "total_tokens": 16096736} {"current_steps": 26395, "total_steps": 64460, "loss": 0.2279, "lr": 7.355625451906414e-06, "epoch": 8.189574930189265, "percentage": 40.95, "elapsed_time": "0:48:50", "remaining_time": "1:10:25", "throughput": 5494.37, "total_tokens": 16099392} {"current_steps": 26400, "total_steps": 64460, "loss": 0.2339, "lr": 7.354431217027649e-06, "epoch": 8.19112627986348, "percentage": 40.96, "elapsed_time": "0:48:50", "remaining_time": "1:10:25", "throughput": 5494.29, "total_tokens": 16101888} {"current_steps": 26405, "total_steps": 64460, "loss": 0.2286, "lr": 7.353236809541193e-06, "epoch": 8.192677629537698, "percentage": 40.96, "elapsed_time": "0:48:51", "remaining_time": "1:10:24", "throughput": 5494.4, "total_tokens": 16105152} {"current_steps": 26410, "total_steps": 64460, "loss": 0.2397, "lr": 7.352042229534615e-06, "epoch": 8.194228979211914, "percentage": 40.97, "elapsed_time": "0:48:51", "remaining_time": "1:10:23", "throughput": 5494.59, "total_tokens": 16108608} {"current_steps": 26415, "total_steps": 64460, "loss": 0.2322, "lr": 7.350847477095486e-06, "epoch": 8.195780328886132, "percentage": 40.98, "elapsed_time": "0:48:52", "remaining_time": "1:10:23", "throughput": 5494.71, "total_tokens": 16111520} {"current_steps": 26420, "total_steps": 64460, "loss": 0.2305, "lr": 7.3496525523114015e-06, "epoch": 8.197331678560348, "percentage": 40.99, "elapsed_time": "0:48:52", "remaining_time": "1:10:22", "throughput": 5494.91, "total_tokens": 16115104} {"current_steps": 26425, "total_steps": 64460, "loss": 0.2203, "lr": 7.348457455269959e-06, "epoch": 8.198883028234563, "percentage": 40.99, "elapsed_time": "0:48:53", "remaining_time": "1:10:21", "throughput": 5495.02, "total_tokens": 16118240} {"current_steps": 26430, "total_steps": 64460, "loss": 0.226, "lr": 7.347262186058777e-06, "epoch": 8.200434377908781, "percentage": 41.0, "elapsed_time": "0:48:53", "remaining_time": "1:10:21", "throughput": 5494.91, "total_tokens": 16120864} {"current_steps": 26435, "total_steps": 64460, "loss": 0.2281, "lr": 7.346066744765481e-06, "epoch": 8.201985727582997, "percentage": 41.01, "elapsed_time": "0:48:54", "remaining_time": "1:10:20", "throughput": 5494.86, "total_tokens": 16123424} {"current_steps": 26440, "total_steps": 64460, "loss": 0.2313, "lr": 7.34487113147771e-06, "epoch": 8.203537077257213, "percentage": 41.02, "elapsed_time": "0:48:54", "remaining_time": "1:10:20", "throughput": 5495.08, "total_tokens": 16127616} {"current_steps": 26445, "total_steps": 64460, "loss": 0.2318, "lr": 7.343675346283118e-06, "epoch": 8.20508842693143, "percentage": 41.03, "elapsed_time": "0:48:55", "remaining_time": "1:10:19", "throughput": 5495.11, "total_tokens": 16130400} {"current_steps": 26450, "total_steps": 64460, "loss": 0.2236, "lr": 7.342479389269369e-06, "epoch": 8.206639776605646, "percentage": 41.03, "elapsed_time": "0:48:56", "remaining_time": "1:10:19", "throughput": 5495.31, "total_tokens": 16134272} {"current_steps": 26455, "total_steps": 64460, "loss": 0.2493, "lr": 7.341283260524142e-06, "epoch": 8.208191126279864, "percentage": 41.04, "elapsed_time": "0:48:56", "remaining_time": "1:10:18", "throughput": 5495.3, "total_tokens": 16136800} {"current_steps": 26460, "total_steps": 64460, "loss": 0.2304, "lr": 7.340086960135127e-06, "epoch": 8.20974247595408, "percentage": 41.05, "elapsed_time": "0:48:57", "remaining_time": "1:10:18", "throughput": 5495.53, "total_tokens": 16140992} {"current_steps": 26465, "total_steps": 64460, "loss": 0.2264, "lr": 7.338890488190027e-06, "epoch": 8.211293825628296, "percentage": 41.06, "elapsed_time": "0:48:57", "remaining_time": "1:10:17", "throughput": 5495.75, "total_tokens": 16145120} {"current_steps": 26470, "total_steps": 64460, "loss": 0.2235, "lr": 7.337693844776559e-06, "epoch": 8.212845175302514, "percentage": 41.06, "elapsed_time": "0:48:58", "remaining_time": "1:10:17", "throughput": 5495.85, "total_tokens": 16148320} {"current_steps": 26475, "total_steps": 64460, "loss": 0.2305, "lr": 7.336497029982448e-06, "epoch": 8.21439652497673, "percentage": 41.07, "elapsed_time": "0:48:58", "remaining_time": "1:10:16", "throughput": 5495.86, "total_tokens": 16150944} {"current_steps": 26480, "total_steps": 64460, "loss": 0.2313, "lr": 7.335300043895438e-06, "epoch": 8.215947874650947, "percentage": 41.08, "elapsed_time": "0:48:59", "remaining_time": "1:10:15", "throughput": 5496.08, "total_tokens": 16154784} {"current_steps": 26485, "total_steps": 64460, "loss": 0.2306, "lr": 7.33410288660328e-06, "epoch": 8.217499224325163, "percentage": 41.09, "elapsed_time": "0:48:59", "remaining_time": "1:10:15", "throughput": 5496.11, "total_tokens": 16157440} {"current_steps": 26490, "total_steps": 64460, "loss": 0.2202, "lr": 7.33290555819374e-06, "epoch": 8.219050573999379, "percentage": 41.1, "elapsed_time": "0:49:00", "remaining_time": "1:10:14", "throughput": 5496.21, "total_tokens": 16160768} {"current_steps": 26495, "total_steps": 64460, "loss": 0.2298, "lr": 7.331708058754598e-06, "epoch": 8.220601923673597, "percentage": 41.1, "elapsed_time": "0:49:00", "remaining_time": "1:10:13", "throughput": 5496.2, "total_tokens": 16163296} {"current_steps": 26500, "total_steps": 64460, "loss": 0.2383, "lr": 7.330510388373643e-06, "epoch": 8.222153273347812, "percentage": 41.11, "elapsed_time": "0:49:01", "remaining_time": "1:10:13", "throughput": 5496.29, "total_tokens": 16166240} {"current_steps": 26505, "total_steps": 64460, "loss": 0.2436, "lr": 7.329312547138678e-06, "epoch": 8.223704623022028, "percentage": 41.12, "elapsed_time": "0:49:01", "remaining_time": "1:10:12", "throughput": 5496.39, "total_tokens": 16169472} {"current_steps": 26510, "total_steps": 64460, "loss": 0.2306, "lr": 7.328114535137523e-06, "epoch": 8.225255972696246, "percentage": 41.13, "elapsed_time": "0:49:02", "remaining_time": "1:10:12", "throughput": 5496.48, "total_tokens": 16172320} {"current_steps": 26515, "total_steps": 64460, "loss": 0.2288, "lr": 7.326916352458e-06, "epoch": 8.226807322370462, "percentage": 41.13, "elapsed_time": "0:49:02", "remaining_time": "1:10:11", "throughput": 5496.6, "total_tokens": 16175360} {"current_steps": 26520, "total_steps": 64460, "loss": 0.2394, "lr": 7.3257179991879555e-06, "epoch": 8.22835867204468, "percentage": 41.14, "elapsed_time": "0:49:03", "remaining_time": "1:10:10", "throughput": 5496.78, "total_tokens": 16179136} {"current_steps": 26525, "total_steps": 64460, "loss": 0.2342, "lr": 7.324519475415241e-06, "epoch": 8.229910021718895, "percentage": 41.15, "elapsed_time": "0:49:03", "remaining_time": "1:10:10", "throughput": 5496.79, "total_tokens": 16181920} {"current_steps": 26530, "total_steps": 64460, "loss": 0.2262, "lr": 7.323320781227723e-06, "epoch": 8.231461371393111, "percentage": 41.16, "elapsed_time": "0:49:04", "remaining_time": "1:10:09", "throughput": 5496.88, "total_tokens": 16185120} {"current_steps": 26535, "total_steps": 64460, "loss": 0.2322, "lr": 7.322121916713278e-06, "epoch": 8.233012721067329, "percentage": 41.17, "elapsed_time": "0:49:04", "remaining_time": "1:10:08", "throughput": 5496.79, "total_tokens": 16187296} {"current_steps": 26540, "total_steps": 64460, "loss": 0.2324, "lr": 7.3209228819598e-06, "epoch": 8.234564070741545, "percentage": 41.17, "elapsed_time": "0:49:05", "remaining_time": "1:10:08", "throughput": 5496.93, "total_tokens": 16191168} {"current_steps": 26545, "total_steps": 64460, "loss": 0.2359, "lr": 7.319723677055191e-06, "epoch": 8.236115420415763, "percentage": 41.18, "elapsed_time": "0:49:05", "remaining_time": "1:10:07", "throughput": 5496.95, "total_tokens": 16193728} {"current_steps": 26550, "total_steps": 64460, "loss": 0.2245, "lr": 7.318524302087366e-06, "epoch": 8.237666770089978, "percentage": 41.19, "elapsed_time": "0:49:06", "remaining_time": "1:10:07", "throughput": 5497.04, "total_tokens": 16196576} {"current_steps": 26555, "total_steps": 64460, "loss": 0.23, "lr": 7.317324757144254e-06, "epoch": 8.239218119764194, "percentage": 41.2, "elapsed_time": "0:49:06", "remaining_time": "1:10:06", "throughput": 5497.13, "total_tokens": 16199488} {"current_steps": 26560, "total_steps": 64460, "loss": 0.2211, "lr": 7.316125042313798e-06, "epoch": 8.240769469438412, "percentage": 41.2, "elapsed_time": "0:49:07", "remaining_time": "1:10:05", "throughput": 5497.21, "total_tokens": 16202496} {"current_steps": 26565, "total_steps": 64460, "loss": 0.2328, "lr": 7.314925157683947e-06, "epoch": 8.242320819112628, "percentage": 41.21, "elapsed_time": "0:49:07", "remaining_time": "1:10:05", "throughput": 5497.25, "total_tokens": 16205472} {"current_steps": 26570, "total_steps": 64460, "loss": 0.2215, "lr": 7.313725103342671e-06, "epoch": 8.243872168786844, "percentage": 41.22, "elapsed_time": "0:49:08", "remaining_time": "1:10:04", "throughput": 5497.46, "total_tokens": 16209184} {"current_steps": 26575, "total_steps": 64460, "loss": 0.2276, "lr": 7.3125248793779436e-06, "epoch": 8.245423518461061, "percentage": 41.23, "elapsed_time": "0:49:09", "remaining_time": "1:10:04", "throughput": 5497.63, "total_tokens": 16212960} {"current_steps": 26580, "total_steps": 64460, "loss": 0.2228, "lr": 7.31132448587776e-06, "epoch": 8.246974868135277, "percentage": 41.23, "elapsed_time": "0:49:09", "remaining_time": "1:10:03", "throughput": 5497.74, "total_tokens": 16215968} {"current_steps": 26585, "total_steps": 64460, "loss": 0.2337, "lr": 7.310123922930122e-06, "epoch": 8.248526217809495, "percentage": 41.24, "elapsed_time": "0:49:10", "remaining_time": "1:10:02", "throughput": 5497.69, "total_tokens": 16218752} {"current_steps": 26590, "total_steps": 64460, "loss": 0.2281, "lr": 7.308923190623043e-06, "epoch": 8.25007756748371, "percentage": 41.25, "elapsed_time": "0:49:10", "remaining_time": "1:10:02", "throughput": 5497.53, "total_tokens": 16220992} {"current_steps": 26595, "total_steps": 64460, "loss": 0.223, "lr": 7.307722289044553e-06, "epoch": 8.251628917157927, "percentage": 41.26, "elapsed_time": "0:49:11", "remaining_time": "1:10:01", "throughput": 5497.44, "total_tokens": 16223648} {"current_steps": 26600, "total_steps": 64460, "loss": 0.2213, "lr": 7.306521218282691e-06, "epoch": 8.253180266832144, "percentage": 41.27, "elapsed_time": "0:49:11", "remaining_time": "1:10:01", "throughput": 5497.56, "total_tokens": 16227104} {"current_steps": 26605, "total_steps": 64460, "loss": 0.2263, "lr": 7.3053199784255125e-06, "epoch": 8.25473161650636, "percentage": 41.27, "elapsed_time": "0:49:12", "remaining_time": "1:10:00", "throughput": 5497.46, "total_tokens": 16229472} {"current_steps": 26610, "total_steps": 64460, "loss": 0.2325, "lr": 7.304118569561078e-06, "epoch": 8.256282966180578, "percentage": 41.28, "elapsed_time": "0:49:12", "remaining_time": "1:09:59", "throughput": 5497.41, "total_tokens": 16231968} {"current_steps": 26615, "total_steps": 64460, "loss": 0.2447, "lr": 7.30291699177747e-06, "epoch": 8.257834315854794, "percentage": 41.29, "elapsed_time": "0:49:13", "remaining_time": "1:09:59", "throughput": 5497.56, "total_tokens": 16235648} {"current_steps": 26620, "total_steps": 64460, "loss": 0.2225, "lr": 7.301715245162775e-06, "epoch": 8.25938566552901, "percentage": 41.3, "elapsed_time": "0:49:13", "remaining_time": "1:09:58", "throughput": 5497.73, "total_tokens": 16239072} {"current_steps": 26625, "total_steps": 64460, "loss": 0.2347, "lr": 7.300513329805095e-06, "epoch": 8.260937015203227, "percentage": 41.3, "elapsed_time": "0:49:14", "remaining_time": "1:09:58", "throughput": 5497.92, "total_tokens": 16242656} {"current_steps": 26630, "total_steps": 64460, "loss": 0.2237, "lr": 7.2993112457925465e-06, "epoch": 8.262488364877443, "percentage": 41.31, "elapsed_time": "0:49:14", "remaining_time": "1:09:57", "throughput": 5498.02, "total_tokens": 16245728} {"current_steps": 26635, "total_steps": 64460, "loss": 0.2297, "lr": 7.298108993213255e-06, "epoch": 8.264039714551659, "percentage": 41.32, "elapsed_time": "0:49:15", "remaining_time": "1:09:57", "throughput": 5498.15, "total_tokens": 16249216} {"current_steps": 26640, "total_steps": 64460, "loss": 0.2279, "lr": 7.296906572155362e-06, "epoch": 8.265591064225877, "percentage": 41.33, "elapsed_time": "0:49:15", "remaining_time": "1:09:56", "throughput": 5498.11, "total_tokens": 16251968} {"current_steps": 26645, "total_steps": 64460, "loss": 0.2286, "lr": 7.295703982707016e-06, "epoch": 8.267142413900093, "percentage": 41.34, "elapsed_time": "0:49:16", "remaining_time": "1:09:55", "throughput": 5498.26, "total_tokens": 16255104} {"current_steps": 26650, "total_steps": 64460, "loss": 0.2307, "lr": 7.294501224956385e-06, "epoch": 8.26869376357431, "percentage": 41.34, "elapsed_time": "0:49:17", "remaining_time": "1:09:55", "throughput": 5498.66, "total_tokens": 16260992} {"current_steps": 26655, "total_steps": 64460, "loss": 0.2351, "lr": 7.293298298991642e-06, "epoch": 8.270245113248526, "percentage": 41.35, "elapsed_time": "0:49:17", "remaining_time": "1:09:55", "throughput": 5498.73, "total_tokens": 16264064} {"current_steps": 26660, "total_steps": 64460, "loss": 0.2354, "lr": 7.292095204900977e-06, "epoch": 8.271796462922742, "percentage": 41.36, "elapsed_time": "0:49:18", "remaining_time": "1:09:54", "throughput": 5498.89, "total_tokens": 16267808} {"current_steps": 26665, "total_steps": 64460, "loss": 0.2251, "lr": 7.290891942772592e-06, "epoch": 8.27334781259696, "percentage": 41.37, "elapsed_time": "0:49:18", "remaining_time": "1:09:53", "throughput": 5498.76, "total_tokens": 16270048} {"current_steps": 26670, "total_steps": 64460, "loss": 0.2292, "lr": 7.289688512694699e-06, "epoch": 8.274899162271176, "percentage": 41.37, "elapsed_time": "0:49:19", "remaining_time": "1:09:53", "throughput": 5498.64, "total_tokens": 16272480} {"current_steps": 26675, "total_steps": 64460, "loss": 0.2281, "lr": 7.288484914755524e-06, "epoch": 8.276450511945393, "percentage": 41.38, "elapsed_time": "0:49:20", "remaining_time": "1:09:52", "throughput": 5498.8, "total_tokens": 16276576} {"current_steps": 26680, "total_steps": 64460, "loss": 0.2309, "lr": 7.287281149043305e-06, "epoch": 8.27800186161961, "percentage": 41.39, "elapsed_time": "0:49:20", "remaining_time": "1:09:52", "throughput": 5498.91, "total_tokens": 16280032} {"current_steps": 26685, "total_steps": 64460, "loss": 0.2262, "lr": 7.2860772156462925e-06, "epoch": 8.279553211293825, "percentage": 41.4, "elapsed_time": "0:49:21", "remaining_time": "1:09:51", "throughput": 5499.01, "total_tokens": 16282912} {"current_steps": 26690, "total_steps": 64460, "loss": 0.2184, "lr": 7.284873114652748e-06, "epoch": 8.281104560968043, "percentage": 41.41, "elapsed_time": "0:49:21", "remaining_time": "1:09:50", "throughput": 5498.91, "total_tokens": 16285120} {"current_steps": 26695, "total_steps": 64460, "loss": 0.2309, "lr": 7.2836688461509465e-06, "epoch": 8.282655910642259, "percentage": 41.41, "elapsed_time": "0:49:22", "remaining_time": "1:09:50", "throughput": 5499.13, "total_tokens": 16289088} {"current_steps": 26700, "total_steps": 64460, "loss": 0.2239, "lr": 7.282464410229178e-06, "epoch": 8.284207260316474, "percentage": 41.42, "elapsed_time": "0:49:22", "remaining_time": "1:09:49", "throughput": 5499.06, "total_tokens": 16291648} {"current_steps": 26705, "total_steps": 64460, "loss": 0.2412, "lr": 7.281259806975739e-06, "epoch": 8.285758609990692, "percentage": 41.43, "elapsed_time": "0:49:23", "remaining_time": "1:09:49", "throughput": 5499.01, "total_tokens": 16294272} {"current_steps": 26710, "total_steps": 64460, "loss": 0.229, "lr": 7.280055036478941e-06, "epoch": 8.287309959664908, "percentage": 41.44, "elapsed_time": "0:49:23", "remaining_time": "1:09:48", "throughput": 5498.83, "total_tokens": 16296480} {"current_steps": 26715, "total_steps": 64460, "loss": 0.2259, "lr": 7.278850098827109e-06, "epoch": 8.288861309339126, "percentage": 41.44, "elapsed_time": "0:49:24", "remaining_time": "1:09:47", "throughput": 5498.81, "total_tokens": 16298976} {"current_steps": 26720, "total_steps": 64460, "loss": 0.2436, "lr": 7.27764499410858e-06, "epoch": 8.290412659013342, "percentage": 41.45, "elapsed_time": "0:49:24", "remaining_time": "1:09:47", "throughput": 5498.7, "total_tokens": 16301312} {"current_steps": 26725, "total_steps": 64460, "loss": 0.2313, "lr": 7.276439722411702e-06, "epoch": 8.291964008687557, "percentage": 41.46, "elapsed_time": "0:49:25", "remaining_time": "1:09:46", "throughput": 5498.75, "total_tokens": 16304192} {"current_steps": 26730, "total_steps": 64460, "loss": 0.2327, "lr": 7.275234283824835e-06, "epoch": 8.293515358361775, "percentage": 41.47, "elapsed_time": "0:49:25", "remaining_time": "1:09:45", "throughput": 5498.76, "total_tokens": 16306816} {"current_steps": 26735, "total_steps": 64460, "loss": 0.2303, "lr": 7.274028678436353e-06, "epoch": 8.295066708035991, "percentage": 41.48, "elapsed_time": "0:49:26", "remaining_time": "1:09:45", "throughput": 5498.9, "total_tokens": 16310816} {"current_steps": 26740, "total_steps": 64460, "loss": 0.2229, "lr": 7.272822906334639e-06, "epoch": 8.296618057710209, "percentage": 41.48, "elapsed_time": "0:49:26", "remaining_time": "1:09:44", "throughput": 5499.1, "total_tokens": 16314144} {"current_steps": 26745, "total_steps": 64460, "loss": 0.2316, "lr": 7.271616967608092e-06, "epoch": 8.298169407384425, "percentage": 41.49, "elapsed_time": "0:49:27", "remaining_time": "1:09:44", "throughput": 5499.17, "total_tokens": 16316928} {"current_steps": 26750, "total_steps": 64460, "loss": 0.2315, "lr": 7.270410862345121e-06, "epoch": 8.29972075705864, "percentage": 41.5, "elapsed_time": "0:49:27", "remaining_time": "1:09:43", "throughput": 5499.22, "total_tokens": 16319808} {"current_steps": 26755, "total_steps": 64460, "loss": 0.2368, "lr": 7.269204590634149e-06, "epoch": 8.301272106732858, "percentage": 41.51, "elapsed_time": "0:49:28", "remaining_time": "1:09:43", "throughput": 5499.55, "total_tokens": 16324992} {"current_steps": 26760, "total_steps": 64460, "loss": 0.2302, "lr": 7.267998152563609e-06, "epoch": 8.302823456407074, "percentage": 41.51, "elapsed_time": "0:49:28", "remaining_time": "1:09:42", "throughput": 5499.56, "total_tokens": 16328000} {"current_steps": 26765, "total_steps": 64460, "loss": 0.2123, "lr": 7.266791548221946e-06, "epoch": 8.304374806081292, "percentage": 41.52, "elapsed_time": "0:49:29", "remaining_time": "1:09:42", "throughput": 5499.68, "total_tokens": 16331680} {"current_steps": 26770, "total_steps": 64460, "loss": 0.2298, "lr": 7.265584777697621e-06, "epoch": 8.305926155755508, "percentage": 41.53, "elapsed_time": "0:49:30", "remaining_time": "1:09:41", "throughput": 5499.56, "total_tokens": 16334208} {"current_steps": 26775, "total_steps": 64460, "loss": 0.2245, "lr": 7.2643778410791025e-06, "epoch": 8.307477505429723, "percentage": 41.54, "elapsed_time": "0:49:30", "remaining_time": "1:09:40", "throughput": 5499.6, "total_tokens": 16336960} {"current_steps": 26780, "total_steps": 64460, "loss": 0.2179, "lr": 7.263170738454874e-06, "epoch": 8.309028855103941, "percentage": 41.55, "elapsed_time": "0:49:31", "remaining_time": "1:09:40", "throughput": 5499.58, "total_tokens": 16339520} {"current_steps": 26785, "total_steps": 64460, "loss": 0.2363, "lr": 7.2619634699134315e-06, "epoch": 8.310580204778157, "percentage": 41.55, "elapsed_time": "0:49:31", "remaining_time": "1:09:39", "throughput": 5499.7, "total_tokens": 16342592} {"current_steps": 26790, "total_steps": 64460, "loss": 0.2388, "lr": 7.260756035543279e-06, "epoch": 8.312131554452373, "percentage": 41.56, "elapsed_time": "0:49:32", "remaining_time": "1:09:39", "throughput": 5499.78, "total_tokens": 16345472} {"current_steps": 26795, "total_steps": 64460, "loss": 0.2377, "lr": 7.259548435432941e-06, "epoch": 8.31368290412659, "percentage": 41.57, "elapsed_time": "0:49:32", "remaining_time": "1:09:38", "throughput": 5499.68, "total_tokens": 16348128} {"current_steps": 26800, "total_steps": 64460, "loss": 0.2305, "lr": 7.258340669670942e-06, "epoch": 8.315234253800806, "percentage": 41.58, "elapsed_time": "0:49:33", "remaining_time": "1:09:37", "throughput": 5499.64, "total_tokens": 16350720} {"current_steps": 26805, "total_steps": 64460, "loss": 0.2306, "lr": 7.257132738345831e-06, "epoch": 8.316785603475024, "percentage": 41.58, "elapsed_time": "0:49:33", "remaining_time": "1:09:37", "throughput": 5499.71, "total_tokens": 16353984} {"current_steps": 26810, "total_steps": 64460, "loss": 0.2352, "lr": 7.255924641546163e-06, "epoch": 8.31833695314924, "percentage": 41.59, "elapsed_time": "0:49:34", "remaining_time": "1:09:36", "throughput": 5499.65, "total_tokens": 16356320} {"current_steps": 26815, "total_steps": 64460, "loss": 0.2293, "lr": 7.254716379360503e-06, "epoch": 8.319888302823456, "percentage": 41.6, "elapsed_time": "0:49:34", "remaining_time": "1:09:35", "throughput": 5499.64, "total_tokens": 16359008} {"current_steps": 26820, "total_steps": 64460, "loss": 0.2321, "lr": 7.253507951877432e-06, "epoch": 8.321439652497673, "percentage": 41.61, "elapsed_time": "0:49:35", "remaining_time": "1:09:35", "throughput": 5499.77, "total_tokens": 16362176} {"current_steps": 26825, "total_steps": 64460, "loss": 0.2225, "lr": 7.252299359185544e-06, "epoch": 8.32299100217189, "percentage": 41.61, "elapsed_time": "0:49:35", "remaining_time": "1:09:34", "throughput": 5500.02, "total_tokens": 16366208} {"current_steps": 26830, "total_steps": 64460, "loss": 0.2239, "lr": 7.251090601373441e-06, "epoch": 8.324542351846105, "percentage": 41.62, "elapsed_time": "0:49:36", "remaining_time": "1:09:34", "throughput": 5500.11, "total_tokens": 16369152} {"current_steps": 26835, "total_steps": 64460, "loss": 0.252, "lr": 7.24988167852974e-06, "epoch": 8.326093701520323, "percentage": 41.63, "elapsed_time": "0:49:36", "remaining_time": "1:09:33", "throughput": 5500.18, "total_tokens": 16372192} {"current_steps": 26840, "total_steps": 64460, "loss": 0.2364, "lr": 7.248672590743069e-06, "epoch": 8.327645051194539, "percentage": 41.64, "elapsed_time": "0:49:37", "remaining_time": "1:09:32", "throughput": 5500.26, "total_tokens": 16375264} {"current_steps": 26845, "total_steps": 64460, "loss": 0.2383, "lr": 7.2474633381020694e-06, "epoch": 8.329196400868756, "percentage": 41.65, "elapsed_time": "0:49:37", "remaining_time": "1:09:32", "throughput": 5500.04, "total_tokens": 16377344} {"current_steps": 26850, "total_steps": 64460, "loss": 0.2394, "lr": 7.246253920695394e-06, "epoch": 8.330747750542972, "percentage": 41.65, "elapsed_time": "0:49:38", "remaining_time": "1:09:31", "throughput": 5500.14, "total_tokens": 16380672} {"current_steps": 26855, "total_steps": 64460, "loss": 0.234, "lr": 7.245044338611705e-06, "epoch": 8.332299100217188, "percentage": 41.66, "elapsed_time": "0:49:38", "remaining_time": "1:09:31", "throughput": 5500.15, "total_tokens": 16383328} {"current_steps": 26860, "total_steps": 64460, "loss": 0.2338, "lr": 7.243834591939682e-06, "epoch": 8.333850449891406, "percentage": 41.67, "elapsed_time": "0:49:39", "remaining_time": "1:09:30", "throughput": 5500.11, "total_tokens": 16385824} {"current_steps": 26865, "total_steps": 64460, "loss": 0.2294, "lr": 7.242624680768012e-06, "epoch": 8.335401799565622, "percentage": 41.68, "elapsed_time": "0:49:39", "remaining_time": "1:09:29", "throughput": 5500.41, "total_tokens": 16390048} {"current_steps": 26870, "total_steps": 64460, "loss": 0.2377, "lr": 7.241414605185396e-06, "epoch": 8.33695314923984, "percentage": 41.68, "elapsed_time": "0:49:40", "remaining_time": "1:09:29", "throughput": 5500.5, "total_tokens": 16393056} {"current_steps": 26875, "total_steps": 64460, "loss": 0.2312, "lr": 7.240204365280548e-06, "epoch": 8.338504498914055, "percentage": 41.69, "elapsed_time": "0:49:40", "remaining_time": "1:09:28", "throughput": 5500.53, "total_tokens": 16395744} {"current_steps": 26880, "total_steps": 64460, "loss": 0.2297, "lr": 7.2389939611421915e-06, "epoch": 8.340055848588271, "percentage": 41.7, "elapsed_time": "0:49:41", "remaining_time": "1:09:28", "throughput": 5500.58, "total_tokens": 16398784} {"current_steps": 26885, "total_steps": 64460, "loss": 0.2376, "lr": 7.237783392859064e-06, "epoch": 8.341607198262489, "percentage": 41.71, "elapsed_time": "0:49:41", "remaining_time": "1:09:27", "throughput": 5500.77, "total_tokens": 16402496} {"current_steps": 26890, "total_steps": 64460, "loss": 0.2364, "lr": 7.236572660519913e-06, "epoch": 8.343158547936705, "percentage": 41.72, "elapsed_time": "0:49:42", "remaining_time": "1:09:26", "throughput": 5500.86, "total_tokens": 16405504} {"current_steps": 26895, "total_steps": 64460, "loss": 0.2372, "lr": 7.235361764213502e-06, "epoch": 8.344709897610922, "percentage": 41.72, "elapsed_time": "0:49:42", "remaining_time": "1:09:26", "throughput": 5501.07, "total_tokens": 16409440} {"current_steps": 26900, "total_steps": 64460, "loss": 0.2366, "lr": 7.234150704028603e-06, "epoch": 8.346261247285138, "percentage": 41.73, "elapsed_time": "0:49:43", "remaining_time": "1:09:25", "throughput": 5501.33, "total_tokens": 16413600} {"current_steps": 26905, "total_steps": 64460, "loss": 0.2295, "lr": 7.232939480054002e-06, "epoch": 8.347812596959354, "percentage": 41.74, "elapsed_time": "0:49:44", "remaining_time": "1:09:25", "throughput": 5501.46, "total_tokens": 16416896} {"current_steps": 26910, "total_steps": 64460, "loss": 0.2242, "lr": 7.231728092378494e-06, "epoch": 8.349363946633572, "percentage": 41.75, "elapsed_time": "0:49:44", "remaining_time": "1:09:24", "throughput": 5501.57, "total_tokens": 16420224} {"current_steps": 26915, "total_steps": 64460, "loss": 0.2314, "lr": 7.23051654109089e-06, "epoch": 8.350915296307788, "percentage": 41.75, "elapsed_time": "0:49:45", "remaining_time": "1:09:24", "throughput": 5501.69, "total_tokens": 16423648} {"current_steps": 26920, "total_steps": 64460, "loss": 0.2186, "lr": 7.22930482628001e-06, "epoch": 8.352466645982004, "percentage": 41.76, "elapsed_time": "0:49:45", "remaining_time": "1:09:23", "throughput": 5501.91, "total_tokens": 16427840} {"current_steps": 26925, "total_steps": 64460, "loss": 0.2305, "lr": 7.228092948034687e-06, "epoch": 8.354017995656221, "percentage": 41.77, "elapsed_time": "0:49:46", "remaining_time": "1:09:23", "throughput": 5501.93, "total_tokens": 16430752} {"current_steps": 26930, "total_steps": 64460, "loss": 0.2292, "lr": 7.2268809064437675e-06, "epoch": 8.355569345330437, "percentage": 41.78, "elapsed_time": "0:49:47", "remaining_time": "1:09:22", "throughput": 5502.09, "total_tokens": 16434848} {"current_steps": 26935, "total_steps": 64460, "loss": 0.2287, "lr": 7.225668701596107e-06, "epoch": 8.357120695004655, "percentage": 41.79, "elapsed_time": "0:49:47", "remaining_time": "1:09:22", "throughput": 5502.13, "total_tokens": 16437824} {"current_steps": 26940, "total_steps": 64460, "loss": 0.2327, "lr": 7.224456333580574e-06, "epoch": 8.35867204467887, "percentage": 41.79, "elapsed_time": "0:49:48", "remaining_time": "1:09:21", "throughput": 5502.11, "total_tokens": 16440512} {"current_steps": 26945, "total_steps": 64460, "loss": 0.2298, "lr": 7.22324380248605e-06, "epoch": 8.360223394353087, "percentage": 41.8, "elapsed_time": "0:49:48", "remaining_time": "1:09:20", "throughput": 5502.12, "total_tokens": 16443072} {"current_steps": 26950, "total_steps": 64460, "loss": 0.2329, "lr": 7.222031108401429e-06, "epoch": 8.361774744027304, "percentage": 41.81, "elapsed_time": "0:49:49", "remaining_time": "1:09:20", "throughput": 5502.2, "total_tokens": 16446720} {"current_steps": 26955, "total_steps": 64460, "loss": 0.2302, "lr": 7.220818251415614e-06, "epoch": 8.36332609370152, "percentage": 41.82, "elapsed_time": "0:49:49", "remaining_time": "1:09:19", "throughput": 5502.16, "total_tokens": 16449376} {"current_steps": 26960, "total_steps": 64460, "loss": 0.2325, "lr": 7.219605231617524e-06, "epoch": 8.364877443375736, "percentage": 41.82, "elapsed_time": "0:49:50", "remaining_time": "1:09:19", "throughput": 5502.33, "total_tokens": 16454112} {"current_steps": 26965, "total_steps": 64460, "loss": 0.2454, "lr": 7.218392049096085e-06, "epoch": 8.366428793049954, "percentage": 41.83, "elapsed_time": "0:49:50", "remaining_time": "1:09:18", "throughput": 5502.41, "total_tokens": 16457504} {"current_steps": 26970, "total_steps": 64460, "loss": 0.2323, "lr": 7.217178703940241e-06, "epoch": 8.36798014272417, "percentage": 41.84, "elapsed_time": "0:49:51", "remaining_time": "1:09:18", "throughput": 5502.4, "total_tokens": 16460256} {"current_steps": 26975, "total_steps": 64460, "loss": 0.2298, "lr": 7.215965196238941e-06, "epoch": 8.369531492398387, "percentage": 41.85, "elapsed_time": "0:49:51", "remaining_time": "1:09:17", "throughput": 5502.45, "total_tokens": 16463136} {"current_steps": 26980, "total_steps": 64460, "loss": 0.232, "lr": 7.214751526081152e-06, "epoch": 8.371082842072603, "percentage": 41.86, "elapsed_time": "0:49:52", "remaining_time": "1:09:17", "throughput": 5502.36, "total_tokens": 16465920} {"current_steps": 26985, "total_steps": 64460, "loss": 0.2336, "lr": 7.21353769355585e-06, "epoch": 8.372634191746819, "percentage": 41.86, "elapsed_time": "0:49:53", "remaining_time": "1:09:16", "throughput": 5502.13, "total_tokens": 16468000} {"current_steps": 26990, "total_steps": 64460, "loss": 0.2265, "lr": 7.212323698752022e-06, "epoch": 8.374185541421037, "percentage": 41.87, "elapsed_time": "0:49:53", "remaining_time": "1:09:15", "throughput": 5502.07, "total_tokens": 16470592} {"current_steps": 26995, "total_steps": 64460, "loss": 0.2263, "lr": 7.211109541758669e-06, "epoch": 8.375736891095253, "percentage": 41.88, "elapsed_time": "0:49:54", "remaining_time": "1:09:15", "throughput": 5502.16, "total_tokens": 16473696} {"current_steps": 27000, "total_steps": 64460, "loss": 0.2284, "lr": 7.209895222664803e-06, "epoch": 8.37728824076947, "percentage": 41.89, "elapsed_time": "0:49:54", "remaining_time": "1:09:14", "throughput": 5502.05, "total_tokens": 16475936} {"current_steps": 27005, "total_steps": 64460, "loss": 0.2328, "lr": 7.208680741559449e-06, "epoch": 8.378839590443686, "percentage": 41.89, "elapsed_time": "0:49:55", "remaining_time": "1:09:14", "throughput": 5502.07, "total_tokens": 16478880} {"current_steps": 27010, "total_steps": 64460, "loss": 0.2275, "lr": 7.207466098531642e-06, "epoch": 8.380390940117902, "percentage": 41.9, "elapsed_time": "0:49:55", "remaining_time": "1:09:13", "throughput": 5502.25, "total_tokens": 16482432} {"current_steps": 27015, "total_steps": 64460, "loss": 0.2287, "lr": 7.2062512936704284e-06, "epoch": 8.38194228979212, "percentage": 41.91, "elapsed_time": "0:49:56", "remaining_time": "1:09:12", "throughput": 5502.2, "total_tokens": 16485088} {"current_steps": 27020, "total_steps": 64460, "loss": 0.228, "lr": 7.205036327064869e-06, "epoch": 8.383493639466336, "percentage": 41.92, "elapsed_time": "0:49:56", "remaining_time": "1:09:12", "throughput": 5502.01, "total_tokens": 16487040} {"current_steps": 27025, "total_steps": 64460, "loss": 0.2306, "lr": 7.203821198804036e-06, "epoch": 8.385044989140553, "percentage": 41.93, "elapsed_time": "0:49:57", "remaining_time": "1:09:11", "throughput": 5502.1, "total_tokens": 16490208} {"current_steps": 27030, "total_steps": 64460, "loss": 0.2287, "lr": 7.202605908977013e-06, "epoch": 8.386596338814769, "percentage": 41.93, "elapsed_time": "0:49:57", "remaining_time": "1:09:11", "throughput": 5502.28, "total_tokens": 16494944} {"current_steps": 27035, "total_steps": 64460, "loss": 0.2347, "lr": 7.201390457672892e-06, "epoch": 8.388147688488985, "percentage": 41.94, "elapsed_time": "0:49:58", "remaining_time": "1:09:10", "throughput": 5502.39, "total_tokens": 16498048} {"current_steps": 27040, "total_steps": 64460, "loss": 0.226, "lr": 7.200174844980784e-06, "epoch": 8.389699038163203, "percentage": 41.95, "elapsed_time": "0:49:58", "remaining_time": "1:09:10", "throughput": 5502.35, "total_tokens": 16500608} {"current_steps": 27045, "total_steps": 64460, "loss": 0.2284, "lr": 7.198959070989805e-06, "epoch": 8.391250387837419, "percentage": 41.96, "elapsed_time": "0:49:59", "remaining_time": "1:09:09", "throughput": 5502.48, "total_tokens": 16504352} {"current_steps": 27050, "total_steps": 64460, "loss": 0.227, "lr": 7.197743135789087e-06, "epoch": 8.392801737511634, "percentage": 41.96, "elapsed_time": "0:49:59", "remaining_time": "1:09:08", "throughput": 5502.57, "total_tokens": 16507264} {"current_steps": 27055, "total_steps": 64460, "loss": 0.236, "lr": 7.196527039467772e-06, "epoch": 8.394353087185852, "percentage": 41.97, "elapsed_time": "0:50:00", "remaining_time": "1:09:08", "throughput": 5502.43, "total_tokens": 16509408} {"current_steps": 27060, "total_steps": 64460, "loss": 0.2217, "lr": 7.195310782115013e-06, "epoch": 8.395904436860068, "percentage": 41.98, "elapsed_time": "0:50:00", "remaining_time": "1:09:07", "throughput": 5502.51, "total_tokens": 16512832} {"current_steps": 27065, "total_steps": 64460, "loss": 0.2369, "lr": 7.194094363819979e-06, "epoch": 8.397455786534286, "percentage": 41.99, "elapsed_time": "0:50:01", "remaining_time": "1:09:06", "throughput": 5502.51, "total_tokens": 16515392} {"current_steps": 27070, "total_steps": 64460, "loss": 0.2303, "lr": 7.1928777846718454e-06, "epoch": 8.399007136208501, "percentage": 42.0, "elapsed_time": "0:50:01", "remaining_time": "1:09:06", "throughput": 5502.62, "total_tokens": 16518624} {"current_steps": 27075, "total_steps": 64460, "loss": 0.2363, "lr": 7.191661044759804e-06, "epoch": 8.400558485882717, "percentage": 42.0, "elapsed_time": "0:50:02", "remaining_time": "1:09:06", "throughput": 5503.04, "total_tokens": 16524224} {"current_steps": 27080, "total_steps": 64460, "loss": 0.2271, "lr": 7.190444144173052e-06, "epoch": 8.402109835556935, "percentage": 42.01, "elapsed_time": "0:50:03", "remaining_time": "1:09:05", "throughput": 5502.99, "total_tokens": 16526624} {"current_steps": 27085, "total_steps": 64460, "loss": 0.2279, "lr": 7.189227083000807e-06, "epoch": 8.403661185231151, "percentage": 42.02, "elapsed_time": "0:50:03", "remaining_time": "1:09:04", "throughput": 5502.99, "total_tokens": 16529280} {"current_steps": 27090, "total_steps": 64460, "loss": 0.2289, "lr": 7.1880098613322924e-06, "epoch": 8.405212534905367, "percentage": 42.03, "elapsed_time": "0:50:04", "remaining_time": "1:09:04", "throughput": 5503.08, "total_tokens": 16532256} {"current_steps": 27095, "total_steps": 64460, "loss": 0.2327, "lr": 7.186792479256746e-06, "epoch": 8.406763884579584, "percentage": 42.03, "elapsed_time": "0:50:04", "remaining_time": "1:09:03", "throughput": 5503.12, "total_tokens": 16535008} {"current_steps": 27100, "total_steps": 64460, "loss": 0.2273, "lr": 7.185574936863413e-06, "epoch": 8.4083152342538, "percentage": 42.04, "elapsed_time": "0:50:05", "remaining_time": "1:09:02", "throughput": 5503.2, "total_tokens": 16538176} {"current_steps": 27105, "total_steps": 64460, "loss": 0.2319, "lr": 7.1843572342415576e-06, "epoch": 8.409866583928018, "percentage": 42.05, "elapsed_time": "0:50:05", "remaining_time": "1:09:02", "throughput": 5503.41, "total_tokens": 16542400} {"current_steps": 27110, "total_steps": 64460, "loss": 0.2272, "lr": 7.183139371480451e-06, "epoch": 8.411417933602234, "percentage": 42.06, "elapsed_time": "0:50:06", "remaining_time": "1:09:01", "throughput": 5503.54, "total_tokens": 16545600} {"current_steps": 27115, "total_steps": 64460, "loss": 0.2331, "lr": 7.181921348669375e-06, "epoch": 8.41296928327645, "percentage": 42.06, "elapsed_time": "0:50:06", "remaining_time": "1:09:01", "throughput": 5503.36, "total_tokens": 16547968} {"current_steps": 27120, "total_steps": 64460, "loss": 0.2307, "lr": 7.180703165897627e-06, "epoch": 8.414520632950667, "percentage": 42.07, "elapsed_time": "0:50:07", "remaining_time": "1:09:00", "throughput": 5503.41, "total_tokens": 16550848} {"current_steps": 27125, "total_steps": 64460, "loss": 0.2258, "lr": 7.179484823254513e-06, "epoch": 8.416071982624883, "percentage": 42.08, "elapsed_time": "0:50:07", "remaining_time": "1:09:00", "throughput": 5503.61, "total_tokens": 16554752} {"current_steps": 27130, "total_steps": 64460, "loss": 0.2278, "lr": 7.178266320829354e-06, "epoch": 8.417623332299101, "percentage": 42.09, "elapsed_time": "0:50:08", "remaining_time": "1:08:59", "throughput": 5503.49, "total_tokens": 16556960} {"current_steps": 27135, "total_steps": 64460, "loss": 0.2204, "lr": 7.177047658711478e-06, "epoch": 8.419174681973317, "percentage": 42.1, "elapsed_time": "0:50:08", "remaining_time": "1:08:58", "throughput": 5503.24, "total_tokens": 16558784} {"current_steps": 27140, "total_steps": 64460, "loss": 0.2248, "lr": 7.175828836990227e-06, "epoch": 8.420726031647533, "percentage": 42.1, "elapsed_time": "0:50:09", "remaining_time": "1:08:58", "throughput": 5503.19, "total_tokens": 16561216} {"current_steps": 27145, "total_steps": 64460, "loss": 0.2297, "lr": 7.1746098557549585e-06, "epoch": 8.42227738132175, "percentage": 42.11, "elapsed_time": "0:50:09", "remaining_time": "1:08:57", "throughput": 5503.03, "total_tokens": 16563520} {"current_steps": 27150, "total_steps": 64460, "loss": 0.2374, "lr": 7.1733907150950355e-06, "epoch": 8.423828730995966, "percentage": 42.12, "elapsed_time": "0:50:10", "remaining_time": "1:08:56", "throughput": 5502.98, "total_tokens": 16566080} {"current_steps": 27155, "total_steps": 64460, "loss": 0.2311, "lr": 7.172171415099837e-06, "epoch": 8.425380080670184, "percentage": 42.13, "elapsed_time": "0:50:10", "remaining_time": "1:08:56", "throughput": 5502.76, "total_tokens": 16568096} {"current_steps": 27160, "total_steps": 64460, "loss": 0.2272, "lr": 7.1709519558587516e-06, "epoch": 8.4269314303444, "percentage": 42.13, "elapsed_time": "0:50:11", "remaining_time": "1:08:55", "throughput": 5502.66, "total_tokens": 16570368} {"current_steps": 27165, "total_steps": 64460, "loss": 0.2238, "lr": 7.169732337461179e-06, "epoch": 8.428482780018616, "percentage": 42.14, "elapsed_time": "0:50:11", "remaining_time": "1:08:54", "throughput": 5502.65, "total_tokens": 16572960} {"current_steps": 27170, "total_steps": 64460, "loss": 0.2246, "lr": 7.168512559996533e-06, "epoch": 8.430034129692833, "percentage": 42.15, "elapsed_time": "0:50:12", "remaining_time": "1:08:54", "throughput": 5502.65, "total_tokens": 16575648} {"current_steps": 27175, "total_steps": 64460, "loss": 0.2359, "lr": 7.167292623554237e-06, "epoch": 8.43158547936705, "percentage": 42.16, "elapsed_time": "0:50:12", "remaining_time": "1:08:53", "throughput": 5502.81, "total_tokens": 16578880} {"current_steps": 27180, "total_steps": 64460, "loss": 0.2171, "lr": 7.166072528223729e-06, "epoch": 8.433136829041265, "percentage": 42.17, "elapsed_time": "0:50:13", "remaining_time": "1:08:53", "throughput": 5503.07, "total_tokens": 16582880} {"current_steps": 27185, "total_steps": 64460, "loss": 0.2465, "lr": 7.164852274094453e-06, "epoch": 8.434688178715483, "percentage": 42.17, "elapsed_time": "0:50:13", "remaining_time": "1:08:52", "throughput": 5503.12, "total_tokens": 16585792} {"current_steps": 27190, "total_steps": 64460, "loss": 0.2154, "lr": 7.163631861255869e-06, "epoch": 8.436239528389699, "percentage": 42.18, "elapsed_time": "0:50:14", "remaining_time": "1:08:51", "throughput": 5503.07, "total_tokens": 16588576} {"current_steps": 27195, "total_steps": 64460, "loss": 0.2375, "lr": 7.1624112897974485e-06, "epoch": 8.437790878063916, "percentage": 42.19, "elapsed_time": "0:50:14", "remaining_time": "1:08:51", "throughput": 5503.04, "total_tokens": 16591296} {"current_steps": 27200, "total_steps": 64460, "loss": 0.2251, "lr": 7.161190559808675e-06, "epoch": 8.439342227738132, "percentage": 42.2, "elapsed_time": "0:50:15", "remaining_time": "1:08:50", "throughput": 5503.11, "total_tokens": 16594304} {"current_steps": 27205, "total_steps": 64460, "loss": 0.2434, "lr": 7.159969671379039e-06, "epoch": 8.440893577412348, "percentage": 42.2, "elapsed_time": "0:50:15", "remaining_time": "1:08:50", "throughput": 5503.04, "total_tokens": 16596640} {"current_steps": 27210, "total_steps": 64460, "loss": 0.226, "lr": 7.15874862459805e-06, "epoch": 8.442444927086566, "percentage": 42.21, "elapsed_time": "0:50:16", "remaining_time": "1:08:49", "throughput": 5503.12, "total_tokens": 16599712} {"current_steps": 27215, "total_steps": 64460, "loss": 0.2414, "lr": 7.157527419555223e-06, "epoch": 8.443996276760782, "percentage": 42.22, "elapsed_time": "0:50:16", "remaining_time": "1:08:48", "throughput": 5503.17, "total_tokens": 16602592} {"current_steps": 27220, "total_steps": 64460, "loss": 0.2333, "lr": 7.156306056340087e-06, "epoch": 8.445547626434998, "percentage": 42.23, "elapsed_time": "0:50:17", "remaining_time": "1:08:48", "throughput": 5503.09, "total_tokens": 16605376} {"current_steps": 27225, "total_steps": 64460, "loss": 0.2371, "lr": 7.155084535042183e-06, "epoch": 8.447098976109215, "percentage": 42.24, "elapsed_time": "0:50:18", "remaining_time": "1:08:47", "throughput": 5503.48, "total_tokens": 16610720} {"current_steps": 27230, "total_steps": 64460, "loss": 0.2273, "lr": 7.1538628557510614e-06, "epoch": 8.448650325783431, "percentage": 42.24, "elapsed_time": "0:50:18", "remaining_time": "1:08:47", "throughput": 5503.54, "total_tokens": 16613568} {"current_steps": 27235, "total_steps": 64460, "loss": 0.2427, "lr": 7.1526410185562875e-06, "epoch": 8.450201675457649, "percentage": 42.25, "elapsed_time": "0:50:19", "remaining_time": "1:08:46", "throughput": 5503.58, "total_tokens": 16616416} {"current_steps": 27240, "total_steps": 64460, "loss": 0.2324, "lr": 7.1514190235474365e-06, "epoch": 8.451753025131865, "percentage": 42.26, "elapsed_time": "0:50:19", "remaining_time": "1:08:46", "throughput": 5503.61, "total_tokens": 16619392} {"current_steps": 27245, "total_steps": 64460, "loss": 0.2271, "lr": 7.150196870814095e-06, "epoch": 8.45330437480608, "percentage": 42.27, "elapsed_time": "0:50:20", "remaining_time": "1:08:45", "throughput": 5503.67, "total_tokens": 16622240} {"current_steps": 27250, "total_steps": 64460, "loss": 0.2246, "lr": 7.148974560445859e-06, "epoch": 8.454855724480298, "percentage": 42.27, "elapsed_time": "0:50:20", "remaining_time": "1:08:44", "throughput": 5503.81, "total_tokens": 16625952} {"current_steps": 27255, "total_steps": 64460, "loss": 0.2528, "lr": 7.147752092532341e-06, "epoch": 8.456407074154514, "percentage": 42.28, "elapsed_time": "0:50:21", "remaining_time": "1:08:44", "throughput": 5503.76, "total_tokens": 16628448} {"current_steps": 27260, "total_steps": 64460, "loss": 0.2352, "lr": 7.146529467163161e-06, "epoch": 8.457958423828732, "percentage": 42.29, "elapsed_time": "0:50:21", "remaining_time": "1:08:43", "throughput": 5503.66, "total_tokens": 16630752} {"current_steps": 27265, "total_steps": 64460, "loss": 0.2271, "lr": 7.1453066844279525e-06, "epoch": 8.459509773502948, "percentage": 42.3, "elapsed_time": "0:50:22", "remaining_time": "1:08:43", "throughput": 5503.83, "total_tokens": 16634464} {"current_steps": 27270, "total_steps": 64460, "loss": 0.2363, "lr": 7.14408374441636e-06, "epoch": 8.461061123177164, "percentage": 42.31, "elapsed_time": "0:50:22", "remaining_time": "1:08:42", "throughput": 5503.76, "total_tokens": 16636800} {"current_steps": 27275, "total_steps": 64460, "loss": 0.2315, "lr": 7.14286064721804e-06, "epoch": 8.462612472851381, "percentage": 42.31, "elapsed_time": "0:50:23", "remaining_time": "1:08:41", "throughput": 5503.9, "total_tokens": 16640096} {"current_steps": 27280, "total_steps": 64460, "loss": 0.2374, "lr": 7.1416373929226565e-06, "epoch": 8.464163822525597, "percentage": 42.32, "elapsed_time": "0:50:23", "remaining_time": "1:08:41", "throughput": 5503.97, "total_tokens": 16642944} {"current_steps": 27285, "total_steps": 64460, "loss": 0.226, "lr": 7.1404139816198935e-06, "epoch": 8.465715172199815, "percentage": 42.33, "elapsed_time": "0:50:24", "remaining_time": "1:08:40", "throughput": 5503.97, "total_tokens": 16645824} {"current_steps": 27290, "total_steps": 64460, "loss": 0.2319, "lr": 7.13919041339944e-06, "epoch": 8.46726652187403, "percentage": 42.34, "elapsed_time": "0:50:24", "remaining_time": "1:08:39", "throughput": 5503.99, "total_tokens": 16648672} {"current_steps": 27295, "total_steps": 64460, "loss": 0.2225, "lr": 7.1379666883509964e-06, "epoch": 8.468817871548247, "percentage": 42.34, "elapsed_time": "0:50:25", "remaining_time": "1:08:39", "throughput": 5504.1, "total_tokens": 16651936} {"current_steps": 27300, "total_steps": 64460, "loss": 0.2272, "lr": 7.1367428065642775e-06, "epoch": 8.470369221222464, "percentage": 42.35, "elapsed_time": "0:50:25", "remaining_time": "1:08:38", "throughput": 5504.19, "total_tokens": 16655104} {"current_steps": 27305, "total_steps": 64460, "loss": 0.2334, "lr": 7.135518768129008e-06, "epoch": 8.47192057089668, "percentage": 42.36, "elapsed_time": "0:50:26", "remaining_time": "1:08:38", "throughput": 5504.39, "total_tokens": 16658528} {"current_steps": 27310, "total_steps": 64460, "loss": 0.2236, "lr": 7.134294573134925e-06, "epoch": 8.473471920570896, "percentage": 42.37, "elapsed_time": "0:50:26", "remaining_time": "1:08:37", "throughput": 5504.42, "total_tokens": 16661440} {"current_steps": 27315, "total_steps": 64460, "loss": 0.2368, "lr": 7.133070221671775e-06, "epoch": 8.475023270245114, "percentage": 42.38, "elapsed_time": "0:50:27", "remaining_time": "1:08:36", "throughput": 5504.31, "total_tokens": 16663648} {"current_steps": 27320, "total_steps": 64460, "loss": 0.2254, "lr": 7.131845713829318e-06, "epoch": 8.47657461991933, "percentage": 42.38, "elapsed_time": "0:50:27", "remaining_time": "1:08:36", "throughput": 5504.32, "total_tokens": 16666464} {"current_steps": 27325, "total_steps": 64460, "loss": 0.2331, "lr": 7.130621049697327e-06, "epoch": 8.478125969593547, "percentage": 42.39, "elapsed_time": "0:50:28", "remaining_time": "1:08:35", "throughput": 5504.46, "total_tokens": 16670688} {"current_steps": 27330, "total_steps": 64460, "loss": 0.231, "lr": 7.129396229365582e-06, "epoch": 8.479677319267763, "percentage": 42.4, "elapsed_time": "0:50:29", "remaining_time": "1:08:35", "throughput": 5504.55, "total_tokens": 16673632} {"current_steps": 27335, "total_steps": 64460, "loss": 0.2367, "lr": 7.128171252923877e-06, "epoch": 8.481228668941979, "percentage": 42.41, "elapsed_time": "0:50:29", "remaining_time": "1:08:34", "throughput": 5504.71, "total_tokens": 16677120} {"current_steps": 27340, "total_steps": 64460, "loss": 0.229, "lr": 7.126946120462018e-06, "epoch": 8.482780018616197, "percentage": 42.41, "elapsed_time": "0:50:30", "remaining_time": "1:08:34", "throughput": 5504.85, "total_tokens": 16681088} {"current_steps": 27345, "total_steps": 64460, "loss": 0.2266, "lr": 7.125720832069822e-06, "epoch": 8.484331368290412, "percentage": 42.42, "elapsed_time": "0:50:30", "remaining_time": "1:08:33", "throughput": 5504.87, "total_tokens": 16683776} {"current_steps": 27350, "total_steps": 64460, "loss": 0.2343, "lr": 7.1244953878371155e-06, "epoch": 8.485882717964628, "percentage": 42.43, "elapsed_time": "0:50:31", "remaining_time": "1:08:33", "throughput": 5505.19, "total_tokens": 16688992} {"current_steps": 27355, "total_steps": 64460, "loss": 0.2359, "lr": 7.123269787853741e-06, "epoch": 8.487434067638846, "percentage": 42.44, "elapsed_time": "0:50:32", "remaining_time": "1:08:32", "throughput": 5505.37, "total_tokens": 16692672} {"current_steps": 27360, "total_steps": 64460, "loss": 0.2353, "lr": 7.122044032209548e-06, "epoch": 8.488985417313062, "percentage": 42.44, "elapsed_time": "0:50:32", "remaining_time": "1:08:32", "throughput": 5505.5, "total_tokens": 16696000} {"current_steps": 27365, "total_steps": 64460, "loss": 0.2244, "lr": 7.120818120994397e-06, "epoch": 8.49053676698728, "percentage": 42.45, "elapsed_time": "0:50:33", "remaining_time": "1:08:31", "throughput": 5505.43, "total_tokens": 16698400} {"current_steps": 27370, "total_steps": 64460, "loss": 0.231, "lr": 7.1195920542981655e-06, "epoch": 8.492088116661495, "percentage": 42.46, "elapsed_time": "0:50:33", "remaining_time": "1:08:30", "throughput": 5505.5, "total_tokens": 16701440} {"current_steps": 27375, "total_steps": 64460, "loss": 0.2277, "lr": 7.118365832210735e-06, "epoch": 8.493639466335711, "percentage": 42.47, "elapsed_time": "0:50:34", "remaining_time": "1:08:30", "throughput": 5505.55, "total_tokens": 16704256} {"current_steps": 27380, "total_steps": 64460, "loss": 0.2236, "lr": 7.117139454822004e-06, "epoch": 8.495190816009929, "percentage": 42.48, "elapsed_time": "0:50:34", "remaining_time": "1:08:29", "throughput": 5505.67, "total_tokens": 16707488} {"current_steps": 27385, "total_steps": 64460, "loss": 0.2319, "lr": 7.115912922221881e-06, "epoch": 8.496742165684145, "percentage": 42.48, "elapsed_time": "0:50:35", "remaining_time": "1:08:28", "throughput": 5505.62, "total_tokens": 16709888} {"current_steps": 27390, "total_steps": 64460, "loss": 0.2258, "lr": 7.114686234500284e-06, "epoch": 8.498293515358363, "percentage": 42.49, "elapsed_time": "0:50:35", "remaining_time": "1:08:28", "throughput": 5505.76, "total_tokens": 16713856} {"current_steps": 27395, "total_steps": 64460, "loss": 0.2328, "lr": 7.1134593917471435e-06, "epoch": 8.499844865032578, "percentage": 42.5, "elapsed_time": "0:50:36", "remaining_time": "1:08:27", "throughput": 5505.69, "total_tokens": 16716320} {"current_steps": 27400, "total_steps": 64460, "loss": 0.2208, "lr": 7.112232394052404e-06, "epoch": 8.501396214706794, "percentage": 42.51, "elapsed_time": "0:50:36", "remaining_time": "1:08:27", "throughput": 5505.81, "total_tokens": 16720672} {"current_steps": 27405, "total_steps": 64460, "loss": 0.2311, "lr": 7.1110052415060175e-06, "epoch": 8.502947564381012, "percentage": 42.51, "elapsed_time": "0:50:37", "remaining_time": "1:08:27", "throughput": 5505.93, "total_tokens": 16724128} {"current_steps": 27410, "total_steps": 64460, "loss": 0.234, "lr": 7.109777934197948e-06, "epoch": 8.504498914055228, "percentage": 42.52, "elapsed_time": "0:50:38", "remaining_time": "1:08:26", "throughput": 5505.99, "total_tokens": 16727264} {"current_steps": 27415, "total_steps": 64460, "loss": 0.2217, "lr": 7.108550472218173e-06, "epoch": 8.506050263729446, "percentage": 42.53, "elapsed_time": "0:50:38", "remaining_time": "1:08:25", "throughput": 5506.07, "total_tokens": 16730176} {"current_steps": 27420, "total_steps": 64460, "loss": 0.233, "lr": 7.1073228556566785e-06, "epoch": 8.507601613403661, "percentage": 42.54, "elapsed_time": "0:50:38", "remaining_time": "1:08:25", "throughput": 5506.02, "total_tokens": 16732640} {"current_steps": 27425, "total_steps": 64460, "loss": 0.2294, "lr": 7.106095084603466e-06, "epoch": 8.509152963077877, "percentage": 42.55, "elapsed_time": "0:50:39", "remaining_time": "1:08:24", "throughput": 5506.2, "total_tokens": 16736384} {"current_steps": 27430, "total_steps": 64460, "loss": 0.2181, "lr": 7.104867159148542e-06, "epoch": 8.510704312752095, "percentage": 42.55, "elapsed_time": "0:50:40", "remaining_time": "1:08:24", "throughput": 5506.32, "total_tokens": 16739936} {"current_steps": 27435, "total_steps": 64460, "loss": 0.2354, "lr": 7.103639079381931e-06, "epoch": 8.51225566242631, "percentage": 42.56, "elapsed_time": "0:50:40", "remaining_time": "1:08:23", "throughput": 5506.46, "total_tokens": 16743104} {"current_steps": 27440, "total_steps": 64460, "loss": 0.2235, "lr": 7.102410845393665e-06, "epoch": 8.513807012100527, "percentage": 42.57, "elapsed_time": "0:50:41", "remaining_time": "1:08:22", "throughput": 5506.37, "total_tokens": 16745568} {"current_steps": 27445, "total_steps": 64460, "loss": 0.2239, "lr": 7.1011824572737865e-06, "epoch": 8.515358361774744, "percentage": 42.58, "elapsed_time": "0:50:41", "remaining_time": "1:08:22", "throughput": 5506.37, "total_tokens": 16748288} {"current_steps": 27450, "total_steps": 64460, "loss": 0.2222, "lr": 7.099953915112353e-06, "epoch": 8.51690971144896, "percentage": 42.58, "elapsed_time": "0:50:42", "remaining_time": "1:08:21", "throughput": 5506.47, "total_tokens": 16751424} {"current_steps": 27455, "total_steps": 64460, "loss": 0.2297, "lr": 7.0987252189994295e-06, "epoch": 8.518461061123178, "percentage": 42.59, "elapsed_time": "0:50:42", "remaining_time": "1:08:20", "throughput": 5506.42, "total_tokens": 16753792} {"current_steps": 27460, "total_steps": 64460, "loss": 0.2356, "lr": 7.097496369025094e-06, "epoch": 8.520012410797394, "percentage": 42.6, "elapsed_time": "0:50:43", "remaining_time": "1:08:20", "throughput": 5506.52, "total_tokens": 16756960} {"current_steps": 27465, "total_steps": 64460, "loss": 0.2261, "lr": 7.096267365279439e-06, "epoch": 8.52156376047161, "percentage": 42.61, "elapsed_time": "0:50:43", "remaining_time": "1:08:19", "throughput": 5506.49, "total_tokens": 16759616} {"current_steps": 27470, "total_steps": 64460, "loss": 0.2245, "lr": 7.0950382078525616e-06, "epoch": 8.523115110145827, "percentage": 42.62, "elapsed_time": "0:50:44", "remaining_time": "1:08:19", "throughput": 5506.58, "total_tokens": 16762496} {"current_steps": 27475, "total_steps": 64460, "loss": 0.242, "lr": 7.093808896834574e-06, "epoch": 8.524666459820043, "percentage": 42.62, "elapsed_time": "0:50:44", "remaining_time": "1:08:18", "throughput": 5506.56, "total_tokens": 16765184} {"current_steps": 27480, "total_steps": 64460, "loss": 0.2257, "lr": 7.092579432315601e-06, "epoch": 8.52621780949426, "percentage": 42.63, "elapsed_time": "0:50:45", "remaining_time": "1:08:18", "throughput": 5506.84, "total_tokens": 16769984} {"current_steps": 27485, "total_steps": 64460, "loss": 0.2414, "lr": 7.091349814385775e-06, "epoch": 8.527769159168477, "percentage": 42.64, "elapsed_time": "0:50:45", "remaining_time": "1:08:17", "throughput": 5506.87, "total_tokens": 16772640} {"current_steps": 27490, "total_steps": 64460, "loss": 0.2304, "lr": 7.0901200431352424e-06, "epoch": 8.529320508842693, "percentage": 42.65, "elapsed_time": "0:50:46", "remaining_time": "1:08:16", "throughput": 5506.88, "total_tokens": 16775488} {"current_steps": 27495, "total_steps": 64460, "loss": 0.2341, "lr": 7.08889011865416e-06, "epoch": 8.53087185851691, "percentage": 42.65, "elapsed_time": "0:50:46", "remaining_time": "1:08:16", "throughput": 5506.77, "total_tokens": 16777888} {"current_steps": 27500, "total_steps": 64460, "loss": 0.2242, "lr": 7.0876600410326964e-06, "epoch": 8.532423208191126, "percentage": 42.66, "elapsed_time": "0:50:47", "remaining_time": "1:08:15", "throughput": 5506.65, "total_tokens": 16780608} {"current_steps": 27505, "total_steps": 64460, "loss": 0.2389, "lr": 7.08642981036103e-06, "epoch": 8.533974557865342, "percentage": 42.67, "elapsed_time": "0:50:47", "remaining_time": "1:08:15", "throughput": 5506.84, "total_tokens": 16784096} {"current_steps": 27510, "total_steps": 64460, "loss": 0.2401, "lr": 7.085199426729351e-06, "epoch": 8.53552590753956, "percentage": 42.68, "elapsed_time": "0:50:48", "remaining_time": "1:08:14", "throughput": 5506.76, "total_tokens": 16786496} {"current_steps": 27515, "total_steps": 64460, "loss": 0.2325, "lr": 7.08396889022786e-06, "epoch": 8.537077257213776, "percentage": 42.69, "elapsed_time": "0:50:48", "remaining_time": "1:08:13", "throughput": 5506.65, "total_tokens": 16788832} {"current_steps": 27520, "total_steps": 64460, "loss": 0.23, "lr": 7.082738200946774e-06, "epoch": 8.538628606887993, "percentage": 42.69, "elapsed_time": "0:50:49", "remaining_time": "1:08:13", "throughput": 5506.64, "total_tokens": 16791488} {"current_steps": 27525, "total_steps": 64460, "loss": 0.2233, "lr": 7.0815073589763136e-06, "epoch": 8.54017995656221, "percentage": 42.7, "elapsed_time": "0:50:49", "remaining_time": "1:08:12", "throughput": 5506.82, "total_tokens": 16795392} {"current_steps": 27530, "total_steps": 64460, "loss": 0.2338, "lr": 7.080276364406716e-06, "epoch": 8.541731306236425, "percentage": 42.71, "elapsed_time": "0:50:50", "remaining_time": "1:08:12", "throughput": 5506.86, "total_tokens": 16798368} {"current_steps": 27535, "total_steps": 64460, "loss": 0.2297, "lr": 7.079045217328224e-06, "epoch": 8.543282655910643, "percentage": 42.72, "elapsed_time": "0:50:50", "remaining_time": "1:08:11", "throughput": 5506.72, "total_tokens": 16800640} {"current_steps": 27540, "total_steps": 64460, "loss": 0.2289, "lr": 7.0778139178311e-06, "epoch": 8.544834005584859, "percentage": 42.72, "elapsed_time": "0:50:51", "remaining_time": "1:08:10", "throughput": 5506.73, "total_tokens": 16803520} {"current_steps": 27545, "total_steps": 64460, "loss": 0.2297, "lr": 7.0765824660056114e-06, "epoch": 8.546385355259076, "percentage": 42.73, "elapsed_time": "0:50:51", "remaining_time": "1:08:10", "throughput": 5506.8, "total_tokens": 16806336} {"current_steps": 27550, "total_steps": 64460, "loss": 0.2364, "lr": 7.075350861942037e-06, "epoch": 8.547936704933292, "percentage": 42.74, "elapsed_time": "0:50:52", "remaining_time": "1:08:09", "throughput": 5507.02, "total_tokens": 16810368} {"current_steps": 27555, "total_steps": 64460, "loss": 0.2247, "lr": 7.074119105730668e-06, "epoch": 8.549488054607508, "percentage": 42.75, "elapsed_time": "0:50:53", "remaining_time": "1:08:08", "throughput": 5507.12, "total_tokens": 16813312} {"current_steps": 27560, "total_steps": 64460, "loss": 0.2281, "lr": 7.072887197461809e-06, "epoch": 8.551039404281726, "percentage": 42.76, "elapsed_time": "0:50:53", "remaining_time": "1:08:08", "throughput": 5507.13, "total_tokens": 16815968} {"current_steps": 27565, "total_steps": 64460, "loss": 0.2312, "lr": 7.0716551372257705e-06, "epoch": 8.552590753955942, "percentage": 42.76, "elapsed_time": "0:50:53", "remaining_time": "1:08:07", "throughput": 5507.29, "total_tokens": 16819200} {"current_steps": 27570, "total_steps": 64460, "loss": 0.2256, "lr": 7.070422925112877e-06, "epoch": 8.554142103630157, "percentage": 42.77, "elapsed_time": "0:50:54", "remaining_time": "1:08:07", "throughput": 5507.5, "total_tokens": 16822944} {"current_steps": 27575, "total_steps": 64460, "loss": 0.2264, "lr": 7.069190561213467e-06, "epoch": 8.555693453304375, "percentage": 42.78, "elapsed_time": "0:50:55", "remaining_time": "1:08:06", "throughput": 5507.52, "total_tokens": 16825888} {"current_steps": 27580, "total_steps": 64460, "loss": 0.2306, "lr": 7.067958045617886e-06, "epoch": 8.557244802978591, "percentage": 42.79, "elapsed_time": "0:50:55", "remaining_time": "1:08:05", "throughput": 5507.55, "total_tokens": 16828576} {"current_steps": 27585, "total_steps": 64460, "loss": 0.2367, "lr": 7.066725378416492e-06, "epoch": 8.558796152652809, "percentage": 42.79, "elapsed_time": "0:50:55", "remaining_time": "1:08:05", "throughput": 5507.58, "total_tokens": 16831168} {"current_steps": 27590, "total_steps": 64460, "loss": 0.2236, "lr": 7.065492559699653e-06, "epoch": 8.560347502327025, "percentage": 42.8, "elapsed_time": "0:50:56", "remaining_time": "1:08:04", "throughput": 5507.6, "total_tokens": 16833728} {"current_steps": 27595, "total_steps": 64460, "loss": 0.2346, "lr": 7.064259589557752e-06, "epoch": 8.56189885200124, "percentage": 42.81, "elapsed_time": "0:50:56", "remaining_time": "1:08:03", "throughput": 5507.68, "total_tokens": 16836864} {"current_steps": 27600, "total_steps": 64460, "loss": 0.2334, "lr": 7.063026468081178e-06, "epoch": 8.563450201675458, "percentage": 42.82, "elapsed_time": "0:50:57", "remaining_time": "1:08:03", "throughput": 5507.75, "total_tokens": 16839776} {"current_steps": 27605, "total_steps": 64460, "loss": 0.2318, "lr": 7.061793195360334e-06, "epoch": 8.565001551349674, "percentage": 42.83, "elapsed_time": "0:50:58", "remaining_time": "1:08:02", "throughput": 5507.96, "total_tokens": 16843712} {"current_steps": 27610, "total_steps": 64460, "loss": 0.231, "lr": 7.060559771485633e-06, "epoch": 8.56655290102389, "percentage": 42.83, "elapsed_time": "0:50:58", "remaining_time": "1:08:02", "throughput": 5508.07, "total_tokens": 16846848} {"current_steps": 27615, "total_steps": 64460, "loss": 0.2312, "lr": 7.0593261965475e-06, "epoch": 8.568104250698108, "percentage": 42.84, "elapsed_time": "0:50:59", "remaining_time": "1:08:01", "throughput": 5508.13, "total_tokens": 16849696} {"current_steps": 27620, "total_steps": 64460, "loss": 0.2382, "lr": 7.058092470636372e-06, "epoch": 8.569655600372323, "percentage": 42.85, "elapsed_time": "0:50:59", "remaining_time": "1:08:00", "throughput": 5508.32, "total_tokens": 16853216} {"current_steps": 27625, "total_steps": 64460, "loss": 0.2287, "lr": 7.056858593842694e-06, "epoch": 8.571206950046541, "percentage": 42.86, "elapsed_time": "0:51:00", "remaining_time": "1:08:00", "throughput": 5508.56, "total_tokens": 16857408} {"current_steps": 27630, "total_steps": 64460, "loss": 0.2254, "lr": 7.055624566256923e-06, "epoch": 8.572758299720757, "percentage": 42.86, "elapsed_time": "0:51:00", "remaining_time": "1:07:59", "throughput": 5508.81, "total_tokens": 16861376} {"current_steps": 27635, "total_steps": 64460, "loss": 0.2245, "lr": 7.05439038796953e-06, "epoch": 8.574309649394973, "percentage": 42.87, "elapsed_time": "0:51:01", "remaining_time": "1:07:59", "throughput": 5508.82, "total_tokens": 16863968} {"current_steps": 27640, "total_steps": 64460, "loss": 0.2249, "lr": 7.0531560590709945e-06, "epoch": 8.57586099906919, "percentage": 42.88, "elapsed_time": "0:51:01", "remaining_time": "1:07:58", "throughput": 5508.87, "total_tokens": 16866784} {"current_steps": 27645, "total_steps": 64460, "loss": 0.2319, "lr": 7.051921579651806e-06, "epoch": 8.577412348743406, "percentage": 42.89, "elapsed_time": "0:51:02", "remaining_time": "1:07:58", "throughput": 5508.87, "total_tokens": 16869728} {"current_steps": 27650, "total_steps": 64460, "loss": 0.2308, "lr": 7.050686949802466e-06, "epoch": 8.578963698417624, "percentage": 42.89, "elapsed_time": "0:51:02", "remaining_time": "1:07:57", "throughput": 5508.89, "total_tokens": 16872288} {"current_steps": 27655, "total_steps": 64460, "loss": 0.2167, "lr": 7.049452169613491e-06, "epoch": 8.58051504809184, "percentage": 42.9, "elapsed_time": "0:51:03", "remaining_time": "1:07:56", "throughput": 5508.95, "total_tokens": 16875232} {"current_steps": 27660, "total_steps": 64460, "loss": 0.2311, "lr": 7.048217239175402e-06, "epoch": 8.582066397766056, "percentage": 42.91, "elapsed_time": "0:51:03", "remaining_time": "1:07:56", "throughput": 5508.86, "total_tokens": 16877440} {"current_steps": 27665, "total_steps": 64460, "loss": 0.2329, "lr": 7.046982158578736e-06, "epoch": 8.583617747440274, "percentage": 42.92, "elapsed_time": "0:51:04", "remaining_time": "1:07:55", "throughput": 5508.89, "total_tokens": 16880576} {"current_steps": 27670, "total_steps": 64460, "loss": 0.2261, "lr": 7.0457469279140364e-06, "epoch": 8.58516909711449, "percentage": 42.93, "elapsed_time": "0:51:04", "remaining_time": "1:07:54", "throughput": 5508.97, "total_tokens": 16883552} {"current_steps": 27675, "total_steps": 64460, "loss": 0.2314, "lr": 7.044511547271862e-06, "epoch": 8.586720446788707, "percentage": 42.93, "elapsed_time": "0:51:05", "remaining_time": "1:07:54", "throughput": 5509.02, "total_tokens": 16886400} {"current_steps": 27680, "total_steps": 64460, "loss": 0.2397, "lr": 7.043276016742781e-06, "epoch": 8.588271796462923, "percentage": 42.94, "elapsed_time": "0:51:05", "remaining_time": "1:07:53", "throughput": 5509.16, "total_tokens": 16889600} {"current_steps": 27685, "total_steps": 64460, "loss": 0.2359, "lr": 7.0420403364173715e-06, "epoch": 8.589823146137139, "percentage": 42.95, "elapsed_time": "0:51:06", "remaining_time": "1:07:52", "throughput": 5509.08, "total_tokens": 16891776} {"current_steps": 27690, "total_steps": 64460, "loss": 0.2401, "lr": 7.0408045063862255e-06, "epoch": 8.591374495811356, "percentage": 42.96, "elapsed_time": "0:51:06", "remaining_time": "1:07:52", "throughput": 5509.23, "total_tokens": 16895968} {"current_steps": 27695, "total_steps": 64460, "loss": 0.2305, "lr": 7.039568526739941e-06, "epoch": 8.592925845485572, "percentage": 42.96, "elapsed_time": "0:51:07", "remaining_time": "1:07:51", "throughput": 5509.19, "total_tokens": 16898400} {"current_steps": 27700, "total_steps": 64460, "loss": 0.236, "lr": 7.038332397569131e-06, "epoch": 8.594477195159788, "percentage": 42.97, "elapsed_time": "0:51:07", "remaining_time": "1:07:51", "throughput": 5509.36, "total_tokens": 16902272} {"current_steps": 27705, "total_steps": 64460, "loss": 0.2395, "lr": 7.0370961189644195e-06, "epoch": 8.596028544834006, "percentage": 42.98, "elapsed_time": "0:51:08", "remaining_time": "1:07:50", "throughput": 5509.43, "total_tokens": 16905440} {"current_steps": 27710, "total_steps": 64460, "loss": 0.2281, "lr": 7.035859691016439e-06, "epoch": 8.597579894508222, "percentage": 42.99, "elapsed_time": "0:51:08", "remaining_time": "1:07:50", "throughput": 5509.47, "total_tokens": 16908160} {"current_steps": 27715, "total_steps": 64460, "loss": 0.2331, "lr": 7.034623113815835e-06, "epoch": 8.59913124418244, "percentage": 43.0, "elapsed_time": "0:51:09", "remaining_time": "1:07:49", "throughput": 5509.76, "total_tokens": 16912192} {"current_steps": 27720, "total_steps": 64460, "loss": 0.2316, "lr": 7.0333863874532636e-06, "epoch": 8.600682593856655, "percentage": 43.0, "elapsed_time": "0:51:10", "remaining_time": "1:07:48", "throughput": 5509.81, "total_tokens": 16915232} {"current_steps": 27725, "total_steps": 64460, "loss": 0.2276, "lr": 7.032149512019392e-06, "epoch": 8.602233943530871, "percentage": 43.01, "elapsed_time": "0:51:10", "remaining_time": "1:07:48", "throughput": 5509.97, "total_tokens": 16918528} {"current_steps": 27730, "total_steps": 64460, "loss": 0.2275, "lr": 7.030912487604895e-06, "epoch": 8.603785293205089, "percentage": 43.02, "elapsed_time": "0:51:11", "remaining_time": "1:07:47", "throughput": 5510.3, "total_tokens": 16923232} {"current_steps": 27735, "total_steps": 64460, "loss": 0.2356, "lr": 7.0296753143004644e-06, "epoch": 8.605336642879305, "percentage": 43.03, "elapsed_time": "0:51:11", "remaining_time": "1:07:47", "throughput": 5510.34, "total_tokens": 16925984} {"current_steps": 27740, "total_steps": 64460, "loss": 0.2286, "lr": 7.028437992196798e-06, "epoch": 8.60688799255352, "percentage": 43.03, "elapsed_time": "0:51:12", "remaining_time": "1:07:46", "throughput": 5510.46, "total_tokens": 16929216} {"current_steps": 27745, "total_steps": 64460, "loss": 0.2224, "lr": 7.027200521384607e-06, "epoch": 8.608439342227738, "percentage": 43.04, "elapsed_time": "0:51:12", "remaining_time": "1:07:46", "throughput": 5510.67, "total_tokens": 16933088} {"current_steps": 27750, "total_steps": 64460, "loss": 0.2372, "lr": 7.025962901954611e-06, "epoch": 8.609990691901954, "percentage": 43.05, "elapsed_time": "0:51:13", "remaining_time": "1:07:45", "throughput": 5510.84, "total_tokens": 16936576} {"current_steps": 27755, "total_steps": 64460, "loss": 0.2297, "lr": 7.024725133997545e-06, "epoch": 8.611542041576172, "percentage": 43.06, "elapsed_time": "0:51:13", "remaining_time": "1:07:45", "throughput": 5511.1, "total_tokens": 16940704} {"current_steps": 27760, "total_steps": 64460, "loss": 0.2319, "lr": 7.023487217604149e-06, "epoch": 8.613093391250388, "percentage": 43.07, "elapsed_time": "0:51:14", "remaining_time": "1:07:44", "throughput": 5511.14, "total_tokens": 16943360} {"current_steps": 27765, "total_steps": 64460, "loss": 0.222, "lr": 7.02224915286518e-06, "epoch": 8.614644740924604, "percentage": 43.07, "elapsed_time": "0:51:14", "remaining_time": "1:07:43", "throughput": 5511.14, "total_tokens": 16945984} {"current_steps": 27770, "total_steps": 64460, "loss": 0.2287, "lr": 7.021010939871398e-06, "epoch": 8.616196090598821, "percentage": 43.08, "elapsed_time": "0:51:15", "remaining_time": "1:07:43", "throughput": 5511.21, "total_tokens": 16949056} {"current_steps": 27775, "total_steps": 64460, "loss": 0.2254, "lr": 7.019772578713583e-06, "epoch": 8.617747440273037, "percentage": 43.09, "elapsed_time": "0:51:15", "remaining_time": "1:07:42", "throughput": 5511.27, "total_tokens": 16952256} {"current_steps": 27780, "total_steps": 64460, "loss": 0.2333, "lr": 7.018534069482521e-06, "epoch": 8.619298789947255, "percentage": 43.1, "elapsed_time": "0:51:16", "remaining_time": "1:07:42", "throughput": 5511.37, "total_tokens": 16955200} {"current_steps": 27785, "total_steps": 64460, "loss": 0.2254, "lr": 7.017295412269009e-06, "epoch": 8.62085013962147, "percentage": 43.1, "elapsed_time": "0:51:16", "remaining_time": "1:07:41", "throughput": 5511.41, "total_tokens": 16957824} {"current_steps": 27790, "total_steps": 64460, "loss": 0.2251, "lr": 7.016056607163854e-06, "epoch": 8.622401489295687, "percentage": 43.11, "elapsed_time": "0:51:17", "remaining_time": "1:07:40", "throughput": 5511.31, "total_tokens": 16960000} {"current_steps": 27795, "total_steps": 64460, "loss": 0.2386, "lr": 7.014817654257876e-06, "epoch": 8.623952838969904, "percentage": 43.12, "elapsed_time": "0:51:17", "remaining_time": "1:07:40", "throughput": 5511.3, "total_tokens": 16962752} {"current_steps": 27800, "total_steps": 64460, "loss": 0.2301, "lr": 7.013578553641906e-06, "epoch": 8.62550418864412, "percentage": 43.13, "elapsed_time": "0:51:18", "remaining_time": "1:07:39", "throughput": 5511.24, "total_tokens": 16965184} {"current_steps": 27805, "total_steps": 64460, "loss": 0.2348, "lr": 7.012339305406782e-06, "epoch": 8.627055538318338, "percentage": 43.14, "elapsed_time": "0:51:18", "remaining_time": "1:07:38", "throughput": 5511.26, "total_tokens": 16968064} {"current_steps": 27810, "total_steps": 64460, "loss": 0.2348, "lr": 7.011099909643359e-06, "epoch": 8.628606887992554, "percentage": 43.14, "elapsed_time": "0:51:19", "remaining_time": "1:07:38", "throughput": 5511.27, "total_tokens": 16970496} {"current_steps": 27815, "total_steps": 64460, "loss": 0.2276, "lr": 7.009860366442497e-06, "epoch": 8.63015823766677, "percentage": 43.15, "elapsed_time": "0:51:19", "remaining_time": "1:07:37", "throughput": 5511.29, "total_tokens": 16973152} {"current_steps": 27820, "total_steps": 64460, "loss": 0.2225, "lr": 7.008620675895069e-06, "epoch": 8.631709587340987, "percentage": 43.16, "elapsed_time": "0:51:20", "remaining_time": "1:07:36", "throughput": 5511.31, "total_tokens": 16975776} {"current_steps": 27825, "total_steps": 64460, "loss": 0.2373, "lr": 7.007380838091961e-06, "epoch": 8.633260937015203, "percentage": 43.17, "elapsed_time": "0:51:20", "remaining_time": "1:07:36", "throughput": 5511.35, "total_tokens": 16978496} {"current_steps": 27830, "total_steps": 64460, "loss": 0.2296, "lr": 7.0061408531240645e-06, "epoch": 8.634812286689419, "percentage": 43.17, "elapsed_time": "0:51:21", "remaining_time": "1:07:35", "throughput": 5511.26, "total_tokens": 16980672} {"current_steps": 27835, "total_steps": 64460, "loss": 0.2325, "lr": 7.004900721082289e-06, "epoch": 8.636363636363637, "percentage": 43.18, "elapsed_time": "0:51:21", "remaining_time": "1:07:34", "throughput": 5511.27, "total_tokens": 16983232} {"current_steps": 27840, "total_steps": 64460, "loss": 0.231, "lr": 7.003660442057549e-06, "epoch": 8.637914986037853, "percentage": 43.19, "elapsed_time": "0:51:22", "remaining_time": "1:07:34", "throughput": 5511.33, "total_tokens": 16986112} {"current_steps": 27845, "total_steps": 64460, "loss": 0.2398, "lr": 7.002420016140772e-06, "epoch": 8.63946633571207, "percentage": 43.2, "elapsed_time": "0:51:22", "remaining_time": "1:07:33", "throughput": 5511.37, "total_tokens": 16988928} {"current_steps": 27850, "total_steps": 64460, "loss": 0.2288, "lr": 7.001179443422896e-06, "epoch": 8.641017685386286, "percentage": 43.21, "elapsed_time": "0:51:22", "remaining_time": "1:07:32", "throughput": 5511.33, "total_tokens": 16991328} {"current_steps": 27855, "total_steps": 64460, "loss": 0.2235, "lr": 6.999938723994868e-06, "epoch": 8.642569035060502, "percentage": 43.21, "elapsed_time": "0:51:23", "remaining_time": "1:07:32", "throughput": 5511.4, "total_tokens": 16994240} {"current_steps": 27860, "total_steps": 64460, "loss": 0.2284, "lr": 6.998697857947648e-06, "epoch": 8.64412038473472, "percentage": 43.22, "elapsed_time": "0:51:23", "remaining_time": "1:07:31", "throughput": 5511.47, "total_tokens": 16997280} {"current_steps": 27865, "total_steps": 64460, "loss": 0.2339, "lr": 6.997456845372208e-06, "epoch": 8.645671734408936, "percentage": 43.23, "elapsed_time": "0:51:24", "remaining_time": "1:07:30", "throughput": 5511.57, "total_tokens": 17000512} {"current_steps": 27870, "total_steps": 64460, "loss": 0.2305, "lr": 6.996215686359529e-06, "epoch": 8.647223084083151, "percentage": 43.24, "elapsed_time": "0:51:25", "remaining_time": "1:07:30", "throughput": 5511.71, "total_tokens": 17003776} {"current_steps": 27875, "total_steps": 64460, "loss": 0.2305, "lr": 6.9949743810006e-06, "epoch": 8.648774433757369, "percentage": 43.24, "elapsed_time": "0:51:25", "remaining_time": "1:07:29", "throughput": 5511.84, "total_tokens": 17007296} {"current_steps": 27880, "total_steps": 64460, "loss": 0.2303, "lr": 6.993732929386426e-06, "epoch": 8.650325783431585, "percentage": 43.25, "elapsed_time": "0:51:26", "remaining_time": "1:07:29", "throughput": 5511.88, "total_tokens": 17010272} {"current_steps": 27885, "total_steps": 64460, "loss": 0.2285, "lr": 6.992491331608018e-06, "epoch": 8.651877133105803, "percentage": 43.26, "elapsed_time": "0:51:26", "remaining_time": "1:07:28", "throughput": 5511.78, "total_tokens": 17012448} {"current_steps": 27890, "total_steps": 64460, "loss": 0.2355, "lr": 6.9912495877564e-06, "epoch": 8.653428482780019, "percentage": 43.27, "elapsed_time": "0:51:27", "remaining_time": "1:07:27", "throughput": 5511.85, "total_tokens": 17015392} {"current_steps": 27895, "total_steps": 64460, "loss": 0.2245, "lr": 6.99000769792261e-06, "epoch": 8.654979832454234, "percentage": 43.27, "elapsed_time": "0:51:27", "remaining_time": "1:07:27", "throughput": 5511.98, "total_tokens": 17018688} {"current_steps": 27900, "total_steps": 64460, "loss": 0.2322, "lr": 6.988765662197687e-06, "epoch": 8.656531182128452, "percentage": 43.28, "elapsed_time": "0:51:28", "remaining_time": "1:07:26", "throughput": 5512.02, "total_tokens": 17021504} {"current_steps": 27905, "total_steps": 64460, "loss": 0.2142, "lr": 6.9875234806726925e-06, "epoch": 8.658082531802668, "percentage": 43.29, "elapsed_time": "0:51:28", "remaining_time": "1:07:25", "throughput": 5512.07, "total_tokens": 17024288} {"current_steps": 27910, "total_steps": 64460, "loss": 0.2166, "lr": 6.9862811534386894e-06, "epoch": 8.659633881476886, "percentage": 43.3, "elapsed_time": "0:51:29", "remaining_time": "1:07:25", "throughput": 5512.07, "total_tokens": 17026848} {"current_steps": 27915, "total_steps": 64460, "loss": 0.222, "lr": 6.985038680586759e-06, "epoch": 8.661185231151102, "percentage": 43.31, "elapsed_time": "0:51:29", "remaining_time": "1:07:24", "throughput": 5512.06, "total_tokens": 17029568} {"current_steps": 27920, "total_steps": 64460, "loss": 0.2326, "lr": 6.983796062207986e-06, "epoch": 8.662736580825317, "percentage": 43.31, "elapsed_time": "0:51:29", "remaining_time": "1:07:23", "throughput": 5512.08, "total_tokens": 17032096} {"current_steps": 27925, "total_steps": 64460, "loss": 0.2446, "lr": 6.982553298393469e-06, "epoch": 8.664287930499535, "percentage": 43.32, "elapsed_time": "0:51:30", "remaining_time": "1:07:23", "throughput": 5512.05, "total_tokens": 17034560} {"current_steps": 27930, "total_steps": 64460, "loss": 0.2268, "lr": 6.9813103892343205e-06, "epoch": 8.665839280173751, "percentage": 43.33, "elapsed_time": "0:51:30", "remaining_time": "1:07:22", "throughput": 5512.09, "total_tokens": 17037472} {"current_steps": 27935, "total_steps": 64460, "loss": 0.2335, "lr": 6.9800673348216564e-06, "epoch": 8.667390629847969, "percentage": 43.34, "elapsed_time": "0:51:31", "remaining_time": "1:07:21", "throughput": 5512.19, "total_tokens": 17040320} {"current_steps": 27940, "total_steps": 64460, "loss": 0.2212, "lr": 6.97882413524661e-06, "epoch": 8.668941979522184, "percentage": 43.34, "elapsed_time": "0:51:31", "remaining_time": "1:07:21", "throughput": 5512.3, "total_tokens": 17043520} {"current_steps": 27945, "total_steps": 64460, "loss": 0.2346, "lr": 6.977580790600323e-06, "epoch": 8.6704933291964, "percentage": 43.35, "elapsed_time": "0:51:32", "remaining_time": "1:07:20", "throughput": 5512.39, "total_tokens": 17046464} {"current_steps": 27950, "total_steps": 64460, "loss": 0.2217, "lr": 6.976337300973943e-06, "epoch": 8.672044678870618, "percentage": 43.36, "elapsed_time": "0:51:32", "remaining_time": "1:07:20", "throughput": 5512.51, "total_tokens": 17049472} {"current_steps": 27955, "total_steps": 64460, "loss": 0.2285, "lr": 6.975093666458637e-06, "epoch": 8.673596028544834, "percentage": 43.37, "elapsed_time": "0:51:33", "remaining_time": "1:07:19", "throughput": 5512.46, "total_tokens": 17051744} {"current_steps": 27960, "total_steps": 64460, "loss": 0.2306, "lr": 6.973849887145577e-06, "epoch": 8.67514737821905, "percentage": 43.38, "elapsed_time": "0:51:34", "remaining_time": "1:07:19", "throughput": 5512.69, "total_tokens": 17056672} {"current_steps": 27965, "total_steps": 64460, "loss": 0.2296, "lr": 6.972605963125945e-06, "epoch": 8.676698727893267, "percentage": 43.38, "elapsed_time": "0:51:34", "remaining_time": "1:07:18", "throughput": 5512.91, "total_tokens": 17060672} {"current_steps": 27970, "total_steps": 64460, "loss": 0.233, "lr": 6.971361894490938e-06, "epoch": 8.678250077567483, "percentage": 43.39, "elapsed_time": "0:51:35", "remaining_time": "1:07:18", "throughput": 5512.89, "total_tokens": 17063360} {"current_steps": 27975, "total_steps": 64460, "loss": 0.2236, "lr": 6.9701176813317596e-06, "epoch": 8.679801427241701, "percentage": 43.4, "elapsed_time": "0:51:35", "remaining_time": "1:07:17", "throughput": 5512.84, "total_tokens": 17065792} {"current_steps": 27980, "total_steps": 64460, "loss": 0.2285, "lr": 6.968873323739624e-06, "epoch": 8.681352776915917, "percentage": 43.41, "elapsed_time": "0:51:36", "remaining_time": "1:07:17", "throughput": 5513.2, "total_tokens": 17072704} {"current_steps": 27985, "total_steps": 64460, "loss": 0.2371, "lr": 6.967628821805761e-06, "epoch": 8.682904126590133, "percentage": 43.41, "elapsed_time": "0:51:37", "remaining_time": "1:07:16", "throughput": 5513.19, "total_tokens": 17075264} {"current_steps": 27990, "total_steps": 64460, "loss": 0.2309, "lr": 6.966384175621404e-06, "epoch": 8.68445547626435, "percentage": 43.42, "elapsed_time": "0:51:37", "remaining_time": "1:07:16", "throughput": 5513.29, "total_tokens": 17078272} {"current_steps": 27995, "total_steps": 64460, "loss": 0.2354, "lr": 6.965139385277803e-06, "epoch": 8.686006825938566, "percentage": 43.43, "elapsed_time": "0:51:38", "remaining_time": "1:07:15", "throughput": 5513.22, "total_tokens": 17080896} {"current_steps": 28000, "total_steps": 64460, "loss": 0.2334, "lr": 6.963894450866212e-06, "epoch": 8.687558175612782, "percentage": 43.44, "elapsed_time": "0:51:38", "remaining_time": "1:07:14", "throughput": 5513.25, "total_tokens": 17083712} {"current_steps": 28005, "total_steps": 64460, "loss": 0.231, "lr": 6.962649372477903e-06, "epoch": 8.689109525287, "percentage": 43.45, "elapsed_time": "0:51:39", "remaining_time": "1:07:14", "throughput": 5513.39, "total_tokens": 17087040} {"current_steps": 28010, "total_steps": 64460, "loss": 0.232, "lr": 6.961404150204154e-06, "epoch": 8.690660874961216, "percentage": 43.45, "elapsed_time": "0:51:39", "remaining_time": "1:07:13", "throughput": 5513.52, "total_tokens": 17090496} {"current_steps": 28015, "total_steps": 64460, "loss": 0.2392, "lr": 6.960158784136254e-06, "epoch": 8.692212224635433, "percentage": 43.46, "elapsed_time": "0:51:40", "remaining_time": "1:07:13", "throughput": 5513.55, "total_tokens": 17093344} {"current_steps": 28020, "total_steps": 64460, "loss": 0.2306, "lr": 6.958913274365503e-06, "epoch": 8.69376357430965, "percentage": 43.47, "elapsed_time": "0:51:40", "remaining_time": "1:07:12", "throughput": 5513.61, "total_tokens": 17096480} {"current_steps": 28025, "total_steps": 64460, "loss": 0.2198, "lr": 6.9576676209832115e-06, "epoch": 8.695314923983865, "percentage": 43.48, "elapsed_time": "0:51:41", "remaining_time": "1:07:11", "throughput": 5513.57, "total_tokens": 17098912} {"current_steps": 28030, "total_steps": 64460, "loss": 0.232, "lr": 6.9564218240807015e-06, "epoch": 8.696866273658083, "percentage": 43.48, "elapsed_time": "0:51:41", "remaining_time": "1:07:11", "throughput": 5513.76, "total_tokens": 17102688} {"current_steps": 28035, "total_steps": 64460, "loss": 0.229, "lr": 6.9551758837493055e-06, "epoch": 8.698417623332299, "percentage": 43.49, "elapsed_time": "0:51:42", "remaining_time": "1:07:10", "throughput": 5513.63, "total_tokens": 17104896} {"current_steps": 28040, "total_steps": 64460, "loss": 0.2272, "lr": 6.953929800080363e-06, "epoch": 8.699968973006516, "percentage": 43.5, "elapsed_time": "0:51:42", "remaining_time": "1:07:10", "throughput": 5513.71, "total_tokens": 17108128} {"current_steps": 28045, "total_steps": 64460, "loss": 0.232, "lr": 6.952683573165229e-06, "epoch": 8.701520322680732, "percentage": 43.51, "elapsed_time": "0:51:43", "remaining_time": "1:07:09", "throughput": 5513.76, "total_tokens": 17110848} {"current_steps": 28050, "total_steps": 64460, "loss": 0.2342, "lr": 6.951437203095266e-06, "epoch": 8.703071672354948, "percentage": 43.52, "elapsed_time": "0:51:43", "remaining_time": "1:07:08", "throughput": 5513.84, "total_tokens": 17113632} {"current_steps": 28055, "total_steps": 64460, "loss": 0.225, "lr": 6.950190689961847e-06, "epoch": 8.704623022029166, "percentage": 43.52, "elapsed_time": "0:51:44", "remaining_time": "1:07:08", "throughput": 5513.86, "total_tokens": 17116512} {"current_steps": 28060, "total_steps": 64460, "loss": 0.221, "lr": 6.9489440338563575e-06, "epoch": 8.706174371703382, "percentage": 43.53, "elapsed_time": "0:51:44", "remaining_time": "1:07:07", "throughput": 5514.0, "total_tokens": 17119744} {"current_steps": 28065, "total_steps": 64460, "loss": 0.2403, "lr": 6.9476972348701895e-06, "epoch": 8.7077257213776, "percentage": 43.54, "elapsed_time": "0:51:45", "remaining_time": "1:07:06", "throughput": 5514.1, "total_tokens": 17122688} {"current_steps": 28070, "total_steps": 64460, "loss": 0.2264, "lr": 6.946450293094752e-06, "epoch": 8.709277071051815, "percentage": 43.55, "elapsed_time": "0:51:45", "remaining_time": "1:07:06", "throughput": 5514.19, "total_tokens": 17125760} {"current_steps": 28075, "total_steps": 64460, "loss": 0.2399, "lr": 6.9452032086214585e-06, "epoch": 8.710828420726031, "percentage": 43.55, "elapsed_time": "0:51:46", "remaining_time": "1:07:05", "throughput": 5514.27, "total_tokens": 17128672} {"current_steps": 28080, "total_steps": 64460, "loss": 0.2305, "lr": 6.9439559815417345e-06, "epoch": 8.712379770400249, "percentage": 43.56, "elapsed_time": "0:51:46", "remaining_time": "1:07:05", "throughput": 5514.33, "total_tokens": 17131648} {"current_steps": 28085, "total_steps": 64460, "loss": 0.2303, "lr": 6.9427086119470155e-06, "epoch": 8.713931120074465, "percentage": 43.57, "elapsed_time": "0:51:47", "remaining_time": "1:07:04", "throughput": 5514.37, "total_tokens": 17134368} {"current_steps": 28090, "total_steps": 64460, "loss": 0.2477, "lr": 6.941461099928752e-06, "epoch": 8.71548246974868, "percentage": 43.58, "elapsed_time": "0:51:47", "remaining_time": "1:07:03", "throughput": 5514.5, "total_tokens": 17137600} {"current_steps": 28095, "total_steps": 64460, "loss": 0.2296, "lr": 6.9402134455783994e-06, "epoch": 8.717033819422898, "percentage": 43.59, "elapsed_time": "0:51:48", "remaining_time": "1:07:03", "throughput": 5514.48, "total_tokens": 17140384} {"current_steps": 28100, "total_steps": 64460, "loss": 0.2343, "lr": 6.938965648987426e-06, "epoch": 8.718585169097114, "percentage": 43.59, "elapsed_time": "0:51:48", "remaining_time": "1:07:02", "throughput": 5514.5, "total_tokens": 17143296} {"current_steps": 28105, "total_steps": 64460, "loss": 0.2246, "lr": 6.93771771024731e-06, "epoch": 8.720136518771332, "percentage": 43.6, "elapsed_time": "0:51:49", "remaining_time": "1:07:01", "throughput": 5514.52, "total_tokens": 17145888} {"current_steps": 28110, "total_steps": 64460, "loss": 0.2387, "lr": 6.9364696294495384e-06, "epoch": 8.721687868445548, "percentage": 43.61, "elapsed_time": "0:51:49", "remaining_time": "1:07:01", "throughput": 5514.52, "total_tokens": 17148672} {"current_steps": 28115, "total_steps": 64460, "loss": 0.2302, "lr": 6.935221406685613e-06, "epoch": 8.723239218119764, "percentage": 43.62, "elapsed_time": "0:51:50", "remaining_time": "1:07:00", "throughput": 5514.57, "total_tokens": 17151744} {"current_steps": 28120, "total_steps": 64460, "loss": 0.2251, "lr": 6.933973042047042e-06, "epoch": 8.724790567793981, "percentage": 43.62, "elapsed_time": "0:51:50", "remaining_time": "1:07:00", "throughput": 5514.48, "total_tokens": 17154080} {"current_steps": 28125, "total_steps": 64460, "loss": 0.2392, "lr": 6.932724535625344e-06, "epoch": 8.726341917468197, "percentage": 43.63, "elapsed_time": "0:51:51", "remaining_time": "1:06:59", "throughput": 5514.53, "total_tokens": 17156960} {"current_steps": 28130, "total_steps": 64460, "loss": 0.2297, "lr": 6.9314758875120525e-06, "epoch": 8.727893267142413, "percentage": 43.64, "elapsed_time": "0:51:51", "remaining_time": "1:06:58", "throughput": 5514.36, "total_tokens": 17159264} {"current_steps": 28135, "total_steps": 64460, "loss": 0.2286, "lr": 6.930227097798705e-06, "epoch": 8.72944461681663, "percentage": 43.65, "elapsed_time": "0:51:52", "remaining_time": "1:06:58", "throughput": 5514.5, "total_tokens": 17162400} {"current_steps": 28140, "total_steps": 64460, "loss": 0.2288, "lr": 6.928978166576854e-06, "epoch": 8.730995966490847, "percentage": 43.65, "elapsed_time": "0:51:52", "remaining_time": "1:06:57", "throughput": 5514.59, "total_tokens": 17165408} {"current_steps": 28145, "total_steps": 64460, "loss": 0.2308, "lr": 6.92772909393806e-06, "epoch": 8.732547316165064, "percentage": 43.66, "elapsed_time": "0:51:53", "remaining_time": "1:06:57", "throughput": 5514.59, "total_tokens": 17168512} {"current_steps": 28150, "total_steps": 64460, "loss": 0.2359, "lr": 6.926479879973897e-06, "epoch": 8.73409866583928, "percentage": 43.67, "elapsed_time": "0:51:53", "remaining_time": "1:06:56", "throughput": 5514.72, "total_tokens": 17172256} {"current_steps": 28155, "total_steps": 64460, "loss": 0.2331, "lr": 6.925230524775945e-06, "epoch": 8.735650015513496, "percentage": 43.68, "elapsed_time": "0:51:54", "remaining_time": "1:06:56", "throughput": 5514.94, "total_tokens": 17176608} {"current_steps": 28160, "total_steps": 64460, "loss": 0.2311, "lr": 6.923981028435799e-06, "epoch": 8.737201365187714, "percentage": 43.69, "elapsed_time": "0:51:55", "remaining_time": "1:06:55", "throughput": 5514.95, "total_tokens": 17179360} {"current_steps": 28165, "total_steps": 64460, "loss": 0.2284, "lr": 6.922731391045059e-06, "epoch": 8.73875271486193, "percentage": 43.69, "elapsed_time": "0:51:55", "remaining_time": "1:06:54", "throughput": 5515.01, "total_tokens": 17182368} {"current_steps": 28170, "total_steps": 64460, "loss": 0.2348, "lr": 6.92148161269534e-06, "epoch": 8.740304064536147, "percentage": 43.7, "elapsed_time": "0:51:56", "remaining_time": "1:06:54", "throughput": 5515.1, "total_tokens": 17185920} {"current_steps": 28175, "total_steps": 64460, "loss": 0.2268, "lr": 6.920231693478265e-06, "epoch": 8.741855414210363, "percentage": 43.71, "elapsed_time": "0:51:56", "remaining_time": "1:06:53", "throughput": 5515.15, "total_tokens": 17188800} {"current_steps": 28180, "total_steps": 64460, "loss": 0.2331, "lr": 6.918981633485468e-06, "epoch": 8.743406763884579, "percentage": 43.72, "elapsed_time": "0:51:57", "remaining_time": "1:06:53", "throughput": 5515.16, "total_tokens": 17191520} {"current_steps": 28185, "total_steps": 64460, "loss": 0.2238, "lr": 6.917731432808593e-06, "epoch": 8.744958113558797, "percentage": 43.72, "elapsed_time": "0:51:57", "remaining_time": "1:06:52", "throughput": 5515.22, "total_tokens": 17194336} {"current_steps": 28190, "total_steps": 64460, "loss": 0.2333, "lr": 6.916481091539296e-06, "epoch": 8.746509463233012, "percentage": 43.73, "elapsed_time": "0:51:58", "remaining_time": "1:06:51", "throughput": 5515.33, "total_tokens": 17197280} {"current_steps": 28195, "total_steps": 64460, "loss": 0.224, "lr": 6.915230609769239e-06, "epoch": 8.74806081290723, "percentage": 43.74, "elapsed_time": "0:51:58", "remaining_time": "1:06:51", "throughput": 5515.45, "total_tokens": 17200768} {"current_steps": 28200, "total_steps": 64460, "loss": 0.2296, "lr": 6.913979987590098e-06, "epoch": 8.749612162581446, "percentage": 43.75, "elapsed_time": "0:51:59", "remaining_time": "1:06:50", "throughput": 5515.51, "total_tokens": 17203648} {"current_steps": 28205, "total_steps": 64460, "loss": 0.2349, "lr": 6.912729225093559e-06, "epoch": 8.751163512255662, "percentage": 43.76, "elapsed_time": "0:51:59", "remaining_time": "1:06:50", "throughput": 5515.65, "total_tokens": 17206816} {"current_steps": 28210, "total_steps": 64460, "loss": 0.2326, "lr": 6.911478322371319e-06, "epoch": 8.75271486192988, "percentage": 43.76, "elapsed_time": "0:52:00", "remaining_time": "1:06:49", "throughput": 5515.75, "total_tokens": 17209792} {"current_steps": 28215, "total_steps": 64460, "loss": 0.2308, "lr": 6.910227279515082e-06, "epoch": 8.754266211604095, "percentage": 43.77, "elapsed_time": "0:52:00", "remaining_time": "1:06:48", "throughput": 5515.75, "total_tokens": 17212480} {"current_steps": 28220, "total_steps": 64460, "loss": 0.2336, "lr": 6.9089760966165645e-06, "epoch": 8.755817561278311, "percentage": 43.78, "elapsed_time": "0:52:01", "remaining_time": "1:06:48", "throughput": 5515.76, "total_tokens": 17215040} {"current_steps": 28225, "total_steps": 64460, "loss": 0.227, "lr": 6.907724773767495e-06, "epoch": 8.757368910952529, "percentage": 43.79, "elapsed_time": "0:52:01", "remaining_time": "1:06:47", "throughput": 5515.77, "total_tokens": 17217632} {"current_steps": 28230, "total_steps": 64460, "loss": 0.2284, "lr": 6.9064733110596075e-06, "epoch": 8.758920260626745, "percentage": 43.79, "elapsed_time": "0:52:02", "remaining_time": "1:06:46", "throughput": 5516.0, "total_tokens": 17221504} {"current_steps": 28235, "total_steps": 64460, "loss": 0.2246, "lr": 6.905221708584649e-06, "epoch": 8.760471610300963, "percentage": 43.8, "elapsed_time": "0:52:02", "remaining_time": "1:06:46", "throughput": 5516.03, "total_tokens": 17224128} {"current_steps": 28240, "total_steps": 64460, "loss": 0.2308, "lr": 6.9039699664343805e-06, "epoch": 8.762022959975178, "percentage": 43.81, "elapsed_time": "0:52:03", "remaining_time": "1:06:45", "throughput": 5516.17, "total_tokens": 17227360} {"current_steps": 28245, "total_steps": 64460, "loss": 0.2344, "lr": 6.902718084700566e-06, "epoch": 8.763574309649394, "percentage": 43.82, "elapsed_time": "0:52:03", "remaining_time": "1:06:45", "throughput": 5516.39, "total_tokens": 17231104} {"current_steps": 28250, "total_steps": 64460, "loss": 0.24, "lr": 6.901466063474984e-06, "epoch": 8.765125659323612, "percentage": 43.83, "elapsed_time": "0:52:04", "remaining_time": "1:06:44", "throughput": 5516.53, "total_tokens": 17234400} {"current_steps": 28255, "total_steps": 64460, "loss": 0.2348, "lr": 6.900213902849424e-06, "epoch": 8.766677008997828, "percentage": 43.83, "elapsed_time": "0:52:04", "remaining_time": "1:06:43", "throughput": 5516.68, "total_tokens": 17237824} {"current_steps": 28260, "total_steps": 64460, "loss": 0.2329, "lr": 6.898961602915682e-06, "epoch": 8.768228358672044, "percentage": 43.84, "elapsed_time": "0:52:05", "remaining_time": "1:06:43", "throughput": 5516.77, "total_tokens": 17240704} {"current_steps": 28265, "total_steps": 64460, "loss": 0.228, "lr": 6.897709163765568e-06, "epoch": 8.769779708346261, "percentage": 43.85, "elapsed_time": "0:52:05", "remaining_time": "1:06:42", "throughput": 5516.87, "total_tokens": 17243872} {"current_steps": 28270, "total_steps": 64460, "loss": 0.2257, "lr": 6.896456585490901e-06, "epoch": 8.771331058020477, "percentage": 43.86, "elapsed_time": "0:52:06", "remaining_time": "1:06:41", "throughput": 5516.77, "total_tokens": 17246112} {"current_steps": 28275, "total_steps": 64460, "loss": 0.2355, "lr": 6.895203868183507e-06, "epoch": 8.772882407694695, "percentage": 43.86, "elapsed_time": "0:52:06", "remaining_time": "1:06:41", "throughput": 5516.93, "total_tokens": 17249504} {"current_steps": 28280, "total_steps": 64460, "loss": 0.2185, "lr": 6.893951011935227e-06, "epoch": 8.77443375736891, "percentage": 43.87, "elapsed_time": "0:52:07", "remaining_time": "1:06:40", "throughput": 5516.87, "total_tokens": 17251744} {"current_steps": 28285, "total_steps": 64460, "loss": 0.2385, "lr": 6.89269801683791e-06, "epoch": 8.775985107043127, "percentage": 43.88, "elapsed_time": "0:52:07", "remaining_time": "1:06:40", "throughput": 5517.08, "total_tokens": 17255584} {"current_steps": 28290, "total_steps": 64460, "loss": 0.2251, "lr": 6.891444882983416e-06, "epoch": 8.777536456717344, "percentage": 43.89, "elapsed_time": "0:52:08", "remaining_time": "1:06:39", "throughput": 5517.18, "total_tokens": 17258720} {"current_steps": 28295, "total_steps": 64460, "loss": 0.2204, "lr": 6.8901916104636146e-06, "epoch": 8.77908780639156, "percentage": 43.9, "elapsed_time": "0:52:08", "remaining_time": "1:06:38", "throughput": 5517.14, "total_tokens": 17261088} {"current_steps": 28300, "total_steps": 64460, "loss": 0.2298, "lr": 6.888938199370385e-06, "epoch": 8.780639156065778, "percentage": 43.9, "elapsed_time": "0:52:09", "remaining_time": "1:06:38", "throughput": 5517.27, "total_tokens": 17264576} {"current_steps": 28305, "total_steps": 64460, "loss": 0.2267, "lr": 6.887684649795616e-06, "epoch": 8.782190505739994, "percentage": 43.91, "elapsed_time": "0:52:09", "remaining_time": "1:06:37", "throughput": 5517.46, "total_tokens": 17268160} {"current_steps": 28310, "total_steps": 64460, "loss": 0.2216, "lr": 6.886430961831209e-06, "epoch": 8.78374185541421, "percentage": 43.92, "elapsed_time": "0:52:10", "remaining_time": "1:06:37", "throughput": 5517.4, "total_tokens": 17270560} {"current_steps": 28315, "total_steps": 64460, "loss": 0.2334, "lr": 6.885177135569074e-06, "epoch": 8.785293205088427, "percentage": 43.93, "elapsed_time": "0:52:10", "remaining_time": "1:06:36", "throughput": 5517.23, "total_tokens": 17272544} {"current_steps": 28320, "total_steps": 64460, "loss": 0.2418, "lr": 6.883923171101131e-06, "epoch": 8.786844554762643, "percentage": 43.93, "elapsed_time": "0:52:11", "remaining_time": "1:06:35", "throughput": 5517.24, "total_tokens": 17275392} {"current_steps": 28325, "total_steps": 64460, "loss": 0.2308, "lr": 6.882669068519311e-06, "epoch": 8.788395904436861, "percentage": 43.94, "elapsed_time": "0:52:11", "remaining_time": "1:06:35", "throughput": 5517.3, "total_tokens": 17278240} {"current_steps": 28330, "total_steps": 64460, "loss": 0.2347, "lr": 6.881414827915553e-06, "epoch": 8.789947254111077, "percentage": 43.95, "elapsed_time": "0:52:12", "remaining_time": "1:06:34", "throughput": 5517.42, "total_tokens": 17281280} {"current_steps": 28335, "total_steps": 64460, "loss": 0.2243, "lr": 6.880160449381811e-06, "epoch": 8.791498603785293, "percentage": 43.96, "elapsed_time": "0:52:12", "remaining_time": "1:06:33", "throughput": 5517.5, "total_tokens": 17284192} {"current_steps": 28340, "total_steps": 64460, "loss": 0.228, "lr": 6.8789059330100404e-06, "epoch": 8.79304995345951, "percentage": 43.97, "elapsed_time": "0:52:13", "remaining_time": "1:06:33", "throughput": 5517.51, "total_tokens": 17286816} {"current_steps": 28345, "total_steps": 64460, "loss": 0.2297, "lr": 6.877651278892218e-06, "epoch": 8.794601303133726, "percentage": 43.97, "elapsed_time": "0:52:13", "remaining_time": "1:06:32", "throughput": 5517.47, "total_tokens": 17289152} {"current_steps": 28350, "total_steps": 64460, "loss": 0.2329, "lr": 6.8763964871203214e-06, "epoch": 8.796152652807942, "percentage": 43.98, "elapsed_time": "0:52:14", "remaining_time": "1:06:31", "throughput": 5517.37, "total_tokens": 17291552} {"current_steps": 28355, "total_steps": 64460, "loss": 0.2264, "lr": 6.8751415577863425e-06, "epoch": 8.79770400248216, "percentage": 43.99, "elapsed_time": "0:52:14", "remaining_time": "1:06:31", "throughput": 5517.43, "total_tokens": 17294432} {"current_steps": 28360, "total_steps": 64460, "loss": 0.2168, "lr": 6.873886490982282e-06, "epoch": 8.799255352156376, "percentage": 44.0, "elapsed_time": "0:52:15", "remaining_time": "1:06:30", "throughput": 5517.64, "total_tokens": 17298176} {"current_steps": 28365, "total_steps": 64460, "loss": 0.2314, "lr": 6.8726312868001525e-06, "epoch": 8.800806701830593, "percentage": 44.0, "elapsed_time": "0:52:15", "remaining_time": "1:06:30", "throughput": 5517.91, "total_tokens": 17302592} {"current_steps": 28370, "total_steps": 64460, "loss": 0.2378, "lr": 6.871375945331973e-06, "epoch": 8.80235805150481, "percentage": 44.01, "elapsed_time": "0:52:16", "remaining_time": "1:06:29", "throughput": 5517.87, "total_tokens": 17305024} {"current_steps": 28375, "total_steps": 64460, "loss": 0.223, "lr": 6.870120466669778e-06, "epoch": 8.803909401179025, "percentage": 44.02, "elapsed_time": "0:52:16", "remaining_time": "1:06:29", "throughput": 5518.01, "total_tokens": 17308384} {"current_steps": 28380, "total_steps": 64460, "loss": 0.2324, "lr": 6.868864850905606e-06, "epoch": 8.805460750853243, "percentage": 44.03, "elapsed_time": "0:52:17", "remaining_time": "1:06:28", "throughput": 5517.94, "total_tokens": 17310752} {"current_steps": 28385, "total_steps": 64460, "loss": 0.235, "lr": 6.86760909813151e-06, "epoch": 8.807012100527459, "percentage": 44.04, "elapsed_time": "0:52:17", "remaining_time": "1:06:27", "throughput": 5518.17, "total_tokens": 17314656} {"current_steps": 28390, "total_steps": 64460, "loss": 0.234, "lr": 6.866353208439551e-06, "epoch": 8.808563450201675, "percentage": 44.04, "elapsed_time": "0:52:18", "remaining_time": "1:06:27", "throughput": 5518.16, "total_tokens": 17317312} {"current_steps": 28395, "total_steps": 64460, "loss": 0.2162, "lr": 6.865097181921802e-06, "epoch": 8.810114799875892, "percentage": 44.05, "elapsed_time": "0:52:18", "remaining_time": "1:06:26", "throughput": 5518.17, "total_tokens": 17319808} {"current_steps": 28400, "total_steps": 64460, "loss": 0.2289, "lr": 6.863841018670341e-06, "epoch": 8.811666149550108, "percentage": 44.06, "elapsed_time": "0:52:19", "remaining_time": "1:06:25", "throughput": 5518.27, "total_tokens": 17322816} {"current_steps": 28405, "total_steps": 64460, "loss": 0.2303, "lr": 6.8625847187772645e-06, "epoch": 8.813217499224326, "percentage": 44.07, "elapsed_time": "0:52:19", "remaining_time": "1:06:25", "throughput": 5518.41, "total_tokens": 17326432} {"current_steps": 28410, "total_steps": 64460, "loss": 0.2339, "lr": 6.861328282334672e-06, "epoch": 8.814768848898542, "percentage": 44.07, "elapsed_time": "0:52:20", "remaining_time": "1:06:24", "throughput": 5518.39, "total_tokens": 17328896} {"current_steps": 28415, "total_steps": 64460, "loss": 0.2178, "lr": 6.860071709434674e-06, "epoch": 8.816320198572758, "percentage": 44.08, "elapsed_time": "0:52:20", "remaining_time": "1:06:24", "throughput": 5518.44, "total_tokens": 17331712} {"current_steps": 28420, "total_steps": 64460, "loss": 0.2368, "lr": 6.8588150001693935e-06, "epoch": 8.817871548246975, "percentage": 44.09, "elapsed_time": "0:52:21", "remaining_time": "1:06:23", "throughput": 5518.64, "total_tokens": 17335488} {"current_steps": 28425, "total_steps": 64460, "loss": 0.2292, "lr": 6.8575581546309614e-06, "epoch": 8.819422897921191, "percentage": 44.1, "elapsed_time": "0:52:21", "remaining_time": "1:06:22", "throughput": 5518.73, "total_tokens": 17338496} {"current_steps": 28430, "total_steps": 64460, "loss": 0.2304, "lr": 6.8563011729115204e-06, "epoch": 8.820974247595409, "percentage": 44.1, "elapsed_time": "0:52:22", "remaining_time": "1:06:22", "throughput": 5518.83, "total_tokens": 17341728} {"current_steps": 28435, "total_steps": 64460, "loss": 0.2361, "lr": 6.855044055103219e-06, "epoch": 8.822525597269625, "percentage": 44.11, "elapsed_time": "0:52:22", "remaining_time": "1:06:21", "throughput": 5519.03, "total_tokens": 17345440} {"current_steps": 28440, "total_steps": 64460, "loss": 0.2282, "lr": 6.8537868012982244e-06, "epoch": 8.82407694694384, "percentage": 44.12, "elapsed_time": "0:52:23", "remaining_time": "1:06:21", "throughput": 5519.04, "total_tokens": 17348096} {"current_steps": 28445, "total_steps": 64460, "loss": 0.2275, "lr": 6.852529411588704e-06, "epoch": 8.825628296618058, "percentage": 44.13, "elapsed_time": "0:52:23", "remaining_time": "1:06:20", "throughput": 5519.11, "total_tokens": 17351040} {"current_steps": 28450, "total_steps": 64460, "loss": 0.2258, "lr": 6.851271886066842e-06, "epoch": 8.827179646292274, "percentage": 44.14, "elapsed_time": "0:52:24", "remaining_time": "1:06:19", "throughput": 5519.34, "total_tokens": 17354784} {"current_steps": 28455, "total_steps": 64460, "loss": 0.2337, "lr": 6.850014224824827e-06, "epoch": 8.828730995966492, "percentage": 44.14, "elapsed_time": "0:52:24", "remaining_time": "1:06:19", "throughput": 5519.44, "total_tokens": 17357952} {"current_steps": 28460, "total_steps": 64460, "loss": 0.2291, "lr": 6.848756427954861e-06, "epoch": 8.830282345640708, "percentage": 44.15, "elapsed_time": "0:52:25", "remaining_time": "1:06:18", "throughput": 5519.73, "total_tokens": 17362592} {"current_steps": 28465, "total_steps": 64460, "loss": 0.2159, "lr": 6.847498495549159e-06, "epoch": 8.831833695314923, "percentage": 44.16, "elapsed_time": "0:52:26", "remaining_time": "1:06:18", "throughput": 5519.84, "total_tokens": 17365792} {"current_steps": 28470, "total_steps": 64460, "loss": 0.2398, "lr": 6.846240427699936e-06, "epoch": 8.833385044989141, "percentage": 44.17, "elapsed_time": "0:52:26", "remaining_time": "1:06:17", "throughput": 5519.89, "total_tokens": 17368704} {"current_steps": 28475, "total_steps": 64460, "loss": 0.2312, "lr": 6.844982224499429e-06, "epoch": 8.834936394663357, "percentage": 44.17, "elapsed_time": "0:52:27", "remaining_time": "1:06:17", "throughput": 5519.8, "total_tokens": 17371328} {"current_steps": 28480, "total_steps": 64460, "loss": 0.2252, "lr": 6.843723886039877e-06, "epoch": 8.836487744337573, "percentage": 44.18, "elapsed_time": "0:52:27", "remaining_time": "1:06:16", "throughput": 5519.81, "total_tokens": 17374112} {"current_steps": 28485, "total_steps": 64460, "loss": 0.2352, "lr": 6.842465412413531e-06, "epoch": 8.83803909401179, "percentage": 44.19, "elapsed_time": "0:52:28", "remaining_time": "1:06:15", "throughput": 5519.97, "total_tokens": 17377824} {"current_steps": 28490, "total_steps": 64460, "loss": 0.2458, "lr": 6.841206803712652e-06, "epoch": 8.839590443686006, "percentage": 44.2, "elapsed_time": "0:52:28", "remaining_time": "1:06:15", "throughput": 5520.26, "total_tokens": 17382080} {"current_steps": 28495, "total_steps": 64460, "loss": 0.2302, "lr": 6.839948060029512e-06, "epoch": 8.841141793360224, "percentage": 44.21, "elapsed_time": "0:52:29", "remaining_time": "1:06:14", "throughput": 5520.34, "total_tokens": 17384992} {"current_steps": 28500, "total_steps": 64460, "loss": 0.228, "lr": 6.8386891814563906e-06, "epoch": 8.84269314303444, "percentage": 44.21, "elapsed_time": "0:52:29", "remaining_time": "1:06:14", "throughput": 5520.49, "total_tokens": 17388480} {"current_steps": 28505, "total_steps": 64460, "loss": 0.2399, "lr": 6.837430168085579e-06, "epoch": 8.844244492708656, "percentage": 44.22, "elapsed_time": "0:52:30", "remaining_time": "1:06:13", "throughput": 5520.46, "total_tokens": 17390816} {"current_steps": 28510, "total_steps": 64460, "loss": 0.2347, "lr": 6.836171020009378e-06, "epoch": 8.845795842382874, "percentage": 44.23, "elapsed_time": "0:52:30", "remaining_time": "1:06:13", "throughput": 5520.57, "total_tokens": 17394720} {"current_steps": 28515, "total_steps": 64460, "loss": 0.2372, "lr": 6.834911737320097e-06, "epoch": 8.84734719205709, "percentage": 44.24, "elapsed_time": "0:52:31", "remaining_time": "1:06:12", "throughput": 5520.66, "total_tokens": 17397952} {"current_steps": 28520, "total_steps": 64460, "loss": 0.227, "lr": 6.833652320110057e-06, "epoch": 8.848898541731305, "percentage": 44.24, "elapsed_time": "0:52:31", "remaining_time": "1:06:12", "throughput": 5520.58, "total_tokens": 17400768} {"current_steps": 28525, "total_steps": 64460, "loss": 0.2258, "lr": 6.832392768471588e-06, "epoch": 8.850449891405523, "percentage": 44.25, "elapsed_time": "0:52:32", "remaining_time": "1:06:11", "throughput": 5520.61, "total_tokens": 17403712} {"current_steps": 28530, "total_steps": 64460, "loss": 0.2356, "lr": 6.8311330824970305e-06, "epoch": 8.852001241079739, "percentage": 44.26, "elapsed_time": "0:52:33", "remaining_time": "1:06:10", "throughput": 5520.63, "total_tokens": 17406720} {"current_steps": 28535, "total_steps": 64460, "loss": 0.2297, "lr": 6.829873262278734e-06, "epoch": 8.853552590753957, "percentage": 44.27, "elapsed_time": "0:52:33", "remaining_time": "1:06:10", "throughput": 5520.62, "total_tokens": 17409408} {"current_steps": 28540, "total_steps": 64460, "loss": 0.2395, "lr": 6.828613307909059e-06, "epoch": 8.855103940428172, "percentage": 44.28, "elapsed_time": "0:52:34", "remaining_time": "1:06:09", "throughput": 5520.64, "total_tokens": 17412160} {"current_steps": 28545, "total_steps": 64460, "loss": 0.2239, "lr": 6.827353219480375e-06, "epoch": 8.856655290102388, "percentage": 44.28, "elapsed_time": "0:52:34", "remaining_time": "1:06:08", "throughput": 5520.62, "total_tokens": 17414688} {"current_steps": 28550, "total_steps": 64460, "loss": 0.2255, "lr": 6.8260929970850595e-06, "epoch": 8.858206639776606, "percentage": 44.29, "elapsed_time": "0:52:35", "remaining_time": "1:06:08", "throughput": 5520.67, "total_tokens": 17417888} {"current_steps": 28555, "total_steps": 64460, "loss": 0.2237, "lr": 6.824832640815504e-06, "epoch": 8.859757989450822, "percentage": 44.3, "elapsed_time": "0:52:35", "remaining_time": "1:06:07", "throughput": 5520.89, "total_tokens": 17421824} {"current_steps": 28560, "total_steps": 64460, "loss": 0.2379, "lr": 6.823572150764106e-06, "epoch": 8.86130933912504, "percentage": 44.31, "elapsed_time": "0:52:36", "remaining_time": "1:06:07", "throughput": 5521.11, "total_tokens": 17425824} {"current_steps": 28565, "total_steps": 64460, "loss": 0.2288, "lr": 6.822311527023276e-06, "epoch": 8.862860688799255, "percentage": 44.31, "elapsed_time": "0:52:36", "remaining_time": "1:06:06", "throughput": 5521.19, "total_tokens": 17428672} {"current_steps": 28570, "total_steps": 64460, "loss": 0.2339, "lr": 6.821050769685431e-06, "epoch": 8.864412038473471, "percentage": 44.32, "elapsed_time": "0:52:37", "remaining_time": "1:06:06", "throughput": 5521.35, "total_tokens": 17431936} {"current_steps": 28575, "total_steps": 64460, "loss": 0.2311, "lr": 6.819789878843001e-06, "epoch": 8.865963388147689, "percentage": 44.33, "elapsed_time": "0:52:37", "remaining_time": "1:06:05", "throughput": 5521.22, "total_tokens": 17434272} {"current_steps": 28580, "total_steps": 64460, "loss": 0.241, "lr": 6.8185288545884235e-06, "epoch": 8.867514737821905, "percentage": 44.34, "elapsed_time": "0:52:38", "remaining_time": "1:06:04", "throughput": 5521.14, "total_tokens": 17436480} {"current_steps": 28585, "total_steps": 64460, "loss": 0.2323, "lr": 6.8172676970141446e-06, "epoch": 8.869066087496122, "percentage": 44.35, "elapsed_time": "0:52:38", "remaining_time": "1:06:04", "throughput": 5521.29, "total_tokens": 17439968} {"current_steps": 28590, "total_steps": 64460, "loss": 0.2352, "lr": 6.816006406212624e-06, "epoch": 8.870617437170338, "percentage": 44.35, "elapsed_time": "0:52:39", "remaining_time": "1:06:03", "throughput": 5521.3, "total_tokens": 17442912} {"current_steps": 28595, "total_steps": 64460, "loss": 0.2323, "lr": 6.81474498227633e-06, "epoch": 8.872168786844554, "percentage": 44.36, "elapsed_time": "0:52:39", "remaining_time": "1:06:03", "throughput": 5521.27, "total_tokens": 17445472} {"current_steps": 28600, "total_steps": 64460, "loss": 0.2295, "lr": 6.81348342529774e-06, "epoch": 8.873720136518772, "percentage": 44.37, "elapsed_time": "0:52:40", "remaining_time": "1:06:02", "throughput": 5521.19, "total_tokens": 17447968} {"current_steps": 28605, "total_steps": 64460, "loss": 0.2254, "lr": 6.812221735369339e-06, "epoch": 8.875271486192988, "percentage": 44.38, "elapsed_time": "0:52:40", "remaining_time": "1:06:01", "throughput": 5521.29, "total_tokens": 17451168} {"current_steps": 28610, "total_steps": 64460, "loss": 0.2265, "lr": 6.810959912583624e-06, "epoch": 8.876822835867204, "percentage": 44.38, "elapsed_time": "0:52:41", "remaining_time": "1:06:01", "throughput": 5521.2, "total_tokens": 17453312} {"current_steps": 28615, "total_steps": 64460, "loss": 0.2331, "lr": 6.809697957033103e-06, "epoch": 8.878374185541421, "percentage": 44.39, "elapsed_time": "0:52:41", "remaining_time": "1:06:00", "throughput": 5521.28, "total_tokens": 17456160} {"current_steps": 28620, "total_steps": 64460, "loss": 0.2264, "lr": 6.808435868810293e-06, "epoch": 8.879925535215637, "percentage": 44.4, "elapsed_time": "0:52:42", "remaining_time": "1:05:59", "throughput": 5521.4, "total_tokens": 17459264} {"current_steps": 28625, "total_steps": 64460, "loss": 0.2289, "lr": 6.807173648007718e-06, "epoch": 8.881476884889855, "percentage": 44.41, "elapsed_time": "0:52:42", "remaining_time": "1:05:59", "throughput": 5521.52, "total_tokens": 17462560} {"current_steps": 28630, "total_steps": 64460, "loss": 0.2274, "lr": 6.805911294717914e-06, "epoch": 8.88302823456407, "percentage": 44.42, "elapsed_time": "0:52:43", "remaining_time": "1:05:58", "throughput": 5521.48, "total_tokens": 17465184} {"current_steps": 28635, "total_steps": 64460, "loss": 0.238, "lr": 6.804648809033428e-06, "epoch": 8.884579584238287, "percentage": 44.42, "elapsed_time": "0:52:43", "remaining_time": "1:05:57", "throughput": 5521.49, "total_tokens": 17467936} {"current_steps": 28640, "total_steps": 64460, "loss": 0.2235, "lr": 6.8033861910468125e-06, "epoch": 8.886130933912504, "percentage": 44.43, "elapsed_time": "0:52:44", "remaining_time": "1:05:57", "throughput": 5521.5, "total_tokens": 17470496} {"current_steps": 28645, "total_steps": 64460, "loss": 0.2398, "lr": 6.8021234408506345e-06, "epoch": 8.88768228358672, "percentage": 44.44, "elapsed_time": "0:52:44", "remaining_time": "1:05:56", "throughput": 5521.5, "total_tokens": 17473600} {"current_steps": 28650, "total_steps": 64460, "loss": 0.2328, "lr": 6.800860558537467e-06, "epoch": 8.889233633260936, "percentage": 44.45, "elapsed_time": "0:52:45", "remaining_time": "1:05:56", "throughput": 5521.51, "total_tokens": 17476416} {"current_steps": 28655, "total_steps": 64460, "loss": 0.2325, "lr": 6.799597544199896e-06, "epoch": 8.890784982935154, "percentage": 44.45, "elapsed_time": "0:52:45", "remaining_time": "1:05:55", "throughput": 5521.46, "total_tokens": 17478816} {"current_steps": 28660, "total_steps": 64460, "loss": 0.2359, "lr": 6.798334397930515e-06, "epoch": 8.89233633260937, "percentage": 44.46, "elapsed_time": "0:52:46", "remaining_time": "1:05:54", "throughput": 5521.35, "total_tokens": 17480928} {"current_steps": 28665, "total_steps": 64460, "loss": 0.2353, "lr": 6.797071119821927e-06, "epoch": 8.893887682283587, "percentage": 44.47, "elapsed_time": "0:52:46", "remaining_time": "1:05:54", "throughput": 5521.39, "total_tokens": 17483712} {"current_steps": 28670, "total_steps": 64460, "loss": 0.2341, "lr": 6.795807709966745e-06, "epoch": 8.895439031957803, "percentage": 44.48, "elapsed_time": "0:52:47", "remaining_time": "1:05:53", "throughput": 5521.4, "total_tokens": 17486368} {"current_steps": 28675, "total_steps": 64460, "loss": 0.2407, "lr": 6.794544168457593e-06, "epoch": 8.896990381632019, "percentage": 44.48, "elapsed_time": "0:52:47", "remaining_time": "1:05:52", "throughput": 5521.46, "total_tokens": 17489216} {"current_steps": 28680, "total_steps": 64460, "loss": 0.2235, "lr": 6.7932804953871024e-06, "epoch": 8.898541731306237, "percentage": 44.49, "elapsed_time": "0:52:47", "remaining_time": "1:05:52", "throughput": 5521.52, "total_tokens": 17492096} {"current_steps": 28685, "total_steps": 64460, "loss": 0.2291, "lr": 6.792016690847917e-06, "epoch": 8.900093080980453, "percentage": 44.5, "elapsed_time": "0:52:48", "remaining_time": "1:05:52", "throughput": 5521.92, "total_tokens": 17498432} {"current_steps": 28690, "total_steps": 64460, "loss": 0.2267, "lr": 6.7907527549326855e-06, "epoch": 8.90164443065467, "percentage": 44.51, "elapsed_time": "0:52:49", "remaining_time": "1:05:51", "throughput": 5521.89, "total_tokens": 17501056} {"current_steps": 28695, "total_steps": 64460, "loss": 0.2299, "lr": 6.789488687734074e-06, "epoch": 8.903195780328886, "percentage": 44.52, "elapsed_time": "0:52:49", "remaining_time": "1:05:50", "throughput": 5522.08, "total_tokens": 17504640} {"current_steps": 28700, "total_steps": 64460, "loss": 0.2373, "lr": 6.788224489344748e-06, "epoch": 8.904747130003102, "percentage": 44.52, "elapsed_time": "0:52:50", "remaining_time": "1:05:50", "throughput": 5522.16, "total_tokens": 17507840} {"current_steps": 28705, "total_steps": 64460, "loss": 0.2366, "lr": 6.786960159857393e-06, "epoch": 8.90629847967732, "percentage": 44.53, "elapsed_time": "0:52:50", "remaining_time": "1:05:49", "throughput": 5522.24, "total_tokens": 17510848} {"current_steps": 28710, "total_steps": 64460, "loss": 0.2302, "lr": 6.785695699364696e-06, "epoch": 8.907849829351536, "percentage": 44.54, "elapsed_time": "0:52:51", "remaining_time": "1:05:49", "throughput": 5522.3, "total_tokens": 17513664} {"current_steps": 28715, "total_steps": 64460, "loss": 0.2288, "lr": 6.78443110795936e-06, "epoch": 8.909401179025753, "percentage": 44.55, "elapsed_time": "0:52:51", "remaining_time": "1:05:48", "throughput": 5522.31, "total_tokens": 17516256} {"current_steps": 28720, "total_steps": 64460, "loss": 0.2361, "lr": 6.783166385734092e-06, "epoch": 8.91095252869997, "percentage": 44.55, "elapsed_time": "0:52:52", "remaining_time": "1:05:47", "throughput": 5522.22, "total_tokens": 17518528} {"current_steps": 28725, "total_steps": 64460, "loss": 0.2338, "lr": 6.781901532781612e-06, "epoch": 8.912503878374185, "percentage": 44.56, "elapsed_time": "0:52:52", "remaining_time": "1:05:47", "throughput": 5522.22, "total_tokens": 17521600} {"current_steps": 28730, "total_steps": 64460, "loss": 0.2275, "lr": 6.780636549194649e-06, "epoch": 8.914055228048403, "percentage": 44.57, "elapsed_time": "0:52:53", "remaining_time": "1:05:46", "throughput": 5522.03, "total_tokens": 17523648} {"current_steps": 28735, "total_steps": 64460, "loss": 0.23, "lr": 6.779371435065942e-06, "epoch": 8.915606577722619, "percentage": 44.58, "elapsed_time": "0:52:53", "remaining_time": "1:05:45", "throughput": 5522.02, "total_tokens": 17526208} {"current_steps": 28740, "total_steps": 64460, "loss": 0.2326, "lr": 6.778106190488238e-06, "epoch": 8.917157927396834, "percentage": 44.59, "elapsed_time": "0:52:54", "remaining_time": "1:05:45", "throughput": 5522.18, "total_tokens": 17529920} {"current_steps": 28745, "total_steps": 64460, "loss": 0.2247, "lr": 6.776840815554293e-06, "epoch": 8.918709277071052, "percentage": 44.59, "elapsed_time": "0:52:55", "remaining_time": "1:05:44", "throughput": 5522.33, "total_tokens": 17533728} {"current_steps": 28750, "total_steps": 64460, "loss": 0.2265, "lr": 6.775575310356876e-06, "epoch": 8.920260626745268, "percentage": 44.6, "elapsed_time": "0:52:55", "remaining_time": "1:05:44", "throughput": 5522.56, "total_tokens": 17537440} {"current_steps": 28755, "total_steps": 64460, "loss": 0.2257, "lr": 6.7743096749887626e-06, "epoch": 8.921811976419486, "percentage": 44.61, "elapsed_time": "0:52:56", "remaining_time": "1:05:43", "throughput": 5522.6, "total_tokens": 17540096} {"current_steps": 28760, "total_steps": 64460, "loss": 0.2242, "lr": 6.773043909542739e-06, "epoch": 8.923363326093702, "percentage": 44.62, "elapsed_time": "0:52:56", "remaining_time": "1:05:43", "throughput": 5522.84, "total_tokens": 17543968} {"current_steps": 28765, "total_steps": 64460, "loss": 0.2277, "lr": 6.771778014111601e-06, "epoch": 8.924914675767917, "percentage": 44.62, "elapsed_time": "0:52:57", "remaining_time": "1:05:42", "throughput": 5522.82, "total_tokens": 17546592} {"current_steps": 28770, "total_steps": 64460, "loss": 0.2363, "lr": 6.770511988788153e-06, "epoch": 8.926466025442135, "percentage": 44.63, "elapsed_time": "0:52:57", "remaining_time": "1:05:41", "throughput": 5522.82, "total_tokens": 17549152} {"current_steps": 28775, "total_steps": 64460, "loss": 0.2323, "lr": 6.769245833665212e-06, "epoch": 8.928017375116351, "percentage": 44.64, "elapsed_time": "0:52:58", "remaining_time": "1:05:41", "throughput": 5522.76, "total_tokens": 17551488} {"current_steps": 28780, "total_steps": 64460, "loss": 0.224, "lr": 6.767979548835599e-06, "epoch": 8.929568724790569, "percentage": 44.65, "elapsed_time": "0:52:58", "remaining_time": "1:05:40", "throughput": 5522.87, "total_tokens": 17554464} {"current_steps": 28785, "total_steps": 64460, "loss": 0.237, "lr": 6.766713134392148e-06, "epoch": 8.931120074464785, "percentage": 44.66, "elapsed_time": "0:52:59", "remaining_time": "1:05:39", "throughput": 5522.8, "total_tokens": 17557056} {"current_steps": 28790, "total_steps": 64460, "loss": 0.2322, "lr": 6.7654465904277045e-06, "epoch": 8.932671424139, "percentage": 44.66, "elapsed_time": "0:52:59", "remaining_time": "1:05:39", "throughput": 5522.89, "total_tokens": 17560128} {"current_steps": 28795, "total_steps": 64460, "loss": 0.238, "lr": 6.76417991703512e-06, "epoch": 8.934222773813218, "percentage": 44.67, "elapsed_time": "0:53:00", "remaining_time": "1:05:38", "throughput": 5522.99, "total_tokens": 17563168} {"current_steps": 28800, "total_steps": 64460, "loss": 0.2366, "lr": 6.762913114307257e-06, "epoch": 8.935774123487434, "percentage": 44.68, "elapsed_time": "0:53:00", "remaining_time": "1:05:38", "throughput": 5523.07, "total_tokens": 17566144} {"current_steps": 28805, "total_steps": 64460, "loss": 0.2258, "lr": 6.761646182336986e-06, "epoch": 8.93732547316165, "percentage": 44.69, "elapsed_time": "0:53:01", "remaining_time": "1:05:37", "throughput": 5523.21, "total_tokens": 17569664} {"current_steps": 28810, "total_steps": 64460, "loss": 0.2337, "lr": 6.760379121217189e-06, "epoch": 8.938876822835867, "percentage": 44.69, "elapsed_time": "0:53:01", "remaining_time": "1:05:36", "throughput": 5523.21, "total_tokens": 17572224} {"current_steps": 28815, "total_steps": 64460, "loss": 0.2279, "lr": 6.759111931040756e-06, "epoch": 8.940428172510083, "percentage": 44.7, "elapsed_time": "0:53:02", "remaining_time": "1:05:36", "throughput": 5523.26, "total_tokens": 17575168} {"current_steps": 28820, "total_steps": 64460, "loss": 0.2289, "lr": 6.757844611900588e-06, "epoch": 8.941979522184301, "percentage": 44.71, "elapsed_time": "0:53:02", "remaining_time": "1:05:35", "throughput": 5523.28, "total_tokens": 17577696} {"current_steps": 28825, "total_steps": 64460, "loss": 0.2339, "lr": 6.756577163889594e-06, "epoch": 8.943530871858517, "percentage": 44.72, "elapsed_time": "0:53:02", "remaining_time": "1:05:34", "throughput": 5523.36, "total_tokens": 17580736} {"current_steps": 28830, "total_steps": 64460, "loss": 0.2264, "lr": 6.755309587100692e-06, "epoch": 8.945082221532733, "percentage": 44.73, "elapsed_time": "0:53:03", "remaining_time": "1:05:34", "throughput": 5523.5, "total_tokens": 17584480} {"current_steps": 28835, "total_steps": 64460, "loss": 0.2284, "lr": 6.754041881626813e-06, "epoch": 8.94663357120695, "percentage": 44.73, "elapsed_time": "0:53:04", "remaining_time": "1:05:33", "throughput": 5523.42, "total_tokens": 17586688} {"current_steps": 28840, "total_steps": 64460, "loss": 0.2297, "lr": 6.752774047560892e-06, "epoch": 8.948184920881166, "percentage": 44.74, "elapsed_time": "0:53:04", "remaining_time": "1:05:33", "throughput": 5523.39, "total_tokens": 17589056} {"current_steps": 28845, "total_steps": 64460, "loss": 0.2316, "lr": 6.751506084995875e-06, "epoch": 8.949736270555384, "percentage": 44.75, "elapsed_time": "0:53:04", "remaining_time": "1:05:32", "throughput": 5523.45, "total_tokens": 17591968} {"current_steps": 28850, "total_steps": 64460, "loss": 0.2334, "lr": 6.750237994024725e-06, "epoch": 8.9512876202296, "percentage": 44.76, "elapsed_time": "0:53:05", "remaining_time": "1:05:31", "throughput": 5523.48, "total_tokens": 17594720} {"current_steps": 28855, "total_steps": 64460, "loss": 0.2339, "lr": 6.7489697747404024e-06, "epoch": 8.952838969903816, "percentage": 44.76, "elapsed_time": "0:53:06", "remaining_time": "1:05:31", "throughput": 5523.81, "total_tokens": 17599232} {"current_steps": 28860, "total_steps": 64460, "loss": 0.2386, "lr": 6.747701427235884e-06, "epoch": 8.954390319578033, "percentage": 44.77, "elapsed_time": "0:53:06", "remaining_time": "1:05:30", "throughput": 5524.06, "total_tokens": 17603584} {"current_steps": 28865, "total_steps": 64460, "loss": 0.242, "lr": 6.746432951604156e-06, "epoch": 8.95594166925225, "percentage": 44.78, "elapsed_time": "0:53:07", "remaining_time": "1:05:30", "throughput": 5524.09, "total_tokens": 17606368} {"current_steps": 28870, "total_steps": 64460, "loss": 0.2196, "lr": 6.745164347938212e-06, "epoch": 8.957493018926465, "percentage": 44.79, "elapsed_time": "0:53:07", "remaining_time": "1:05:29", "throughput": 5524.16, "total_tokens": 17609312} {"current_steps": 28875, "total_steps": 64460, "loss": 0.23, "lr": 6.743895616331055e-06, "epoch": 8.959044368600683, "percentage": 44.8, "elapsed_time": "0:53:08", "remaining_time": "1:05:29", "throughput": 5524.5, "total_tokens": 17615168} {"current_steps": 28880, "total_steps": 64460, "loss": 0.233, "lr": 6.742626756875699e-06, "epoch": 8.960595718274899, "percentage": 44.8, "elapsed_time": "0:53:09", "remaining_time": "1:05:29", "throughput": 5524.7, "total_tokens": 17619296} {"current_steps": 28885, "total_steps": 64460, "loss": 0.2306, "lr": 6.741357769665165e-06, "epoch": 8.962147067949116, "percentage": 44.81, "elapsed_time": "0:53:09", "remaining_time": "1:05:28", "throughput": 5524.91, "total_tokens": 17623392} {"current_steps": 28890, "total_steps": 64460, "loss": 0.2356, "lr": 6.740088654792486e-06, "epoch": 8.963698417623332, "percentage": 44.82, "elapsed_time": "0:53:10", "remaining_time": "1:05:28", "throughput": 5525.1, "total_tokens": 17627104} {"current_steps": 28895, "total_steps": 64460, "loss": 0.228, "lr": 6.738819412350703e-06, "epoch": 8.965249767297548, "percentage": 44.83, "elapsed_time": "0:53:10", "remaining_time": "1:05:27", "throughput": 5525.14, "total_tokens": 17629760} {"current_steps": 28900, "total_steps": 64460, "loss": 0.2355, "lr": 6.737550042432866e-06, "epoch": 8.966801116971766, "percentage": 44.83, "elapsed_time": "0:53:11", "remaining_time": "1:05:26", "throughput": 5525.27, "total_tokens": 17632992} {"current_steps": 28905, "total_steps": 64460, "loss": 0.2314, "lr": 6.736280545132035e-06, "epoch": 8.968352466645982, "percentage": 44.84, "elapsed_time": "0:53:11", "remaining_time": "1:05:26", "throughput": 5525.32, "total_tokens": 17635776} {"current_steps": 28910, "total_steps": 64460, "loss": 0.2228, "lr": 6.735010920541281e-06, "epoch": 8.9699038163202, "percentage": 44.85, "elapsed_time": "0:53:12", "remaining_time": "1:05:25", "throughput": 5525.4, "total_tokens": 17638720} {"current_steps": 28915, "total_steps": 64460, "loss": 0.2296, "lr": 6.733741168753679e-06, "epoch": 8.971455165994415, "percentage": 44.86, "elapsed_time": "0:53:12", "remaining_time": "1:05:24", "throughput": 5525.36, "total_tokens": 17641088} {"current_steps": 28920, "total_steps": 64460, "loss": 0.2411, "lr": 6.73247128986232e-06, "epoch": 8.973006515668631, "percentage": 44.87, "elapsed_time": "0:53:13", "remaining_time": "1:05:24", "throughput": 5525.43, "total_tokens": 17644416} {"current_steps": 28925, "total_steps": 64460, "loss": 0.2318, "lr": 6.7312012839603004e-06, "epoch": 8.974557865342849, "percentage": 44.87, "elapsed_time": "0:53:13", "remaining_time": "1:05:23", "throughput": 5525.53, "total_tokens": 17647424} {"current_steps": 28930, "total_steps": 64460, "loss": 0.2295, "lr": 6.729931151140725e-06, "epoch": 8.976109215017065, "percentage": 44.88, "elapsed_time": "0:53:14", "remaining_time": "1:05:23", "throughput": 5525.66, "total_tokens": 17650880} {"current_steps": 28935, "total_steps": 64460, "loss": 0.2338, "lr": 6.728660891496711e-06, "epoch": 8.97766056469128, "percentage": 44.89, "elapsed_time": "0:53:14", "remaining_time": "1:05:22", "throughput": 5525.72, "total_tokens": 17653696} {"current_steps": 28940, "total_steps": 64460, "loss": 0.2343, "lr": 6.727390505121383e-06, "epoch": 8.979211914365498, "percentage": 44.9, "elapsed_time": "0:53:15", "remaining_time": "1:05:21", "throughput": 5525.79, "total_tokens": 17656608} {"current_steps": 28945, "total_steps": 64460, "loss": 0.232, "lr": 6.726119992107877e-06, "epoch": 8.980763264039714, "percentage": 44.9, "elapsed_time": "0:53:15", "remaining_time": "1:05:21", "throughput": 5525.89, "total_tokens": 17659936} {"current_steps": 28950, "total_steps": 64460, "loss": 0.2276, "lr": 6.724849352549334e-06, "epoch": 8.982314613713932, "percentage": 44.91, "elapsed_time": "0:53:16", "remaining_time": "1:05:20", "throughput": 5526.04, "total_tokens": 17663328} {"current_steps": 28955, "total_steps": 64460, "loss": 0.2336, "lr": 6.723578586538908e-06, "epoch": 8.983865963388148, "percentage": 44.92, "elapsed_time": "0:53:16", "remaining_time": "1:05:20", "throughput": 5525.97, "total_tokens": 17665760} {"current_steps": 28960, "total_steps": 64460, "loss": 0.2343, "lr": 6.722307694169762e-06, "epoch": 8.985417313062364, "percentage": 44.93, "elapsed_time": "0:53:17", "remaining_time": "1:05:19", "throughput": 5525.88, "total_tokens": 17667936} {"current_steps": 28965, "total_steps": 64460, "loss": 0.2249, "lr": 6.721036675535066e-06, "epoch": 8.986968662736581, "percentage": 44.93, "elapsed_time": "0:53:17", "remaining_time": "1:05:18", "throughput": 5526.02, "total_tokens": 17671104} {"current_steps": 28970, "total_steps": 64460, "loss": 0.2269, "lr": 6.719765530728002e-06, "epoch": 8.988520012410797, "percentage": 44.94, "elapsed_time": "0:53:18", "remaining_time": "1:05:18", "throughput": 5526.12, "total_tokens": 17674272} {"current_steps": 28975, "total_steps": 64460, "loss": 0.2349, "lr": 6.71849425984176e-06, "epoch": 8.990071362085015, "percentage": 44.95, "elapsed_time": "0:53:18", "remaining_time": "1:05:17", "throughput": 5526.18, "total_tokens": 17677152} {"current_steps": 28980, "total_steps": 64460, "loss": 0.2328, "lr": 6.717222862969539e-06, "epoch": 8.99162271175923, "percentage": 44.96, "elapsed_time": "0:53:19", "remaining_time": "1:05:16", "throughput": 5526.29, "total_tokens": 17680224} {"current_steps": 28985, "total_steps": 64460, "loss": 0.2297, "lr": 6.7159513402045464e-06, "epoch": 8.993174061433447, "percentage": 44.97, "elapsed_time": "0:53:19", "remaining_time": "1:05:16", "throughput": 5526.37, "total_tokens": 17683264} {"current_steps": 28990, "total_steps": 64460, "loss": 0.2352, "lr": 6.714679691640001e-06, "epoch": 8.994725411107664, "percentage": 44.97, "elapsed_time": "0:53:20", "remaining_time": "1:05:15", "throughput": 5526.24, "total_tokens": 17685408} {"current_steps": 28995, "total_steps": 64460, "loss": 0.2268, "lr": 6.713407917369129e-06, "epoch": 8.99627676078188, "percentage": 44.98, "elapsed_time": "0:53:20", "remaining_time": "1:05:14", "throughput": 5526.27, "total_tokens": 17688192} {"current_steps": 29000, "total_steps": 64460, "loss": 0.2302, "lr": 6.712136017485168e-06, "epoch": 8.997828110456096, "percentage": 44.99, "elapsed_time": "0:53:21", "remaining_time": "1:05:14", "throughput": 5526.2, "total_tokens": 17690560} {"current_steps": 29005, "total_steps": 64460, "loss": 0.2286, "lr": 6.710863992081361e-06, "epoch": 8.999379460130314, "percentage": 45.0, "elapsed_time": "0:53:21", "remaining_time": "1:05:13", "throughput": 5526.17, "total_tokens": 17692960} {"current_steps": 29010, "total_steps": 64460, "loss": 0.2311, "lr": 6.7095918412509645e-06, "epoch": 9.00093080980453, "percentage": 45.0, "elapsed_time": "0:53:22", "remaining_time": "1:05:13", "throughput": 5525.65, "total_tokens": 17695376} {"current_steps": 29015, "total_steps": 64460, "loss": 0.2285, "lr": 6.7083195650872405e-06, "epoch": 9.002482159478747, "percentage": 45.01, "elapsed_time": "0:53:22", "remaining_time": "1:05:12", "throughput": 5525.62, "total_tokens": 17698192} {"current_steps": 29020, "total_steps": 64460, "loss": 0.2346, "lr": 6.707047163683462e-06, "epoch": 9.004033509152963, "percentage": 45.02, "elapsed_time": "0:53:23", "remaining_time": "1:05:12", "throughput": 5525.61, "total_tokens": 17700624} {"current_steps": 29025, "total_steps": 64460, "loss": 0.2345, "lr": 6.7057746371329135e-06, "epoch": 9.005584858827179, "percentage": 45.03, "elapsed_time": "0:53:23", "remaining_time": "1:05:11", "throughput": 5525.79, "total_tokens": 17704016} {"current_steps": 29030, "total_steps": 64460, "loss": 0.2302, "lr": 6.7045019855288855e-06, "epoch": 9.007136208501397, "percentage": 45.04, "elapsed_time": "0:53:24", "remaining_time": "1:05:10", "throughput": 5525.89, "total_tokens": 17706960} {"current_steps": 29035, "total_steps": 64460, "loss": 0.2284, "lr": 6.703229208964677e-06, "epoch": 9.008687558175613, "percentage": 45.04, "elapsed_time": "0:53:24", "remaining_time": "1:05:10", "throughput": 5525.74, "total_tokens": 17709264} {"current_steps": 29040, "total_steps": 64460, "loss": 0.2356, "lr": 6.701956307533597e-06, "epoch": 9.01023890784983, "percentage": 45.05, "elapsed_time": "0:53:25", "remaining_time": "1:05:09", "throughput": 5525.89, "total_tokens": 17712848} {"current_steps": 29045, "total_steps": 64460, "loss": 0.2286, "lr": 6.7006832813289654e-06, "epoch": 9.011790257524046, "percentage": 45.06, "elapsed_time": "0:53:25", "remaining_time": "1:05:09", "throughput": 5525.86, "total_tokens": 17715568} {"current_steps": 29050, "total_steps": 64460, "loss": 0.2352, "lr": 6.699410130444112e-06, "epoch": 9.013341607198262, "percentage": 45.07, "elapsed_time": "0:53:26", "remaining_time": "1:05:08", "throughput": 5525.94, "total_tokens": 17718576} {"current_steps": 29055, "total_steps": 64460, "loss": 0.2257, "lr": 6.6981368549723705e-06, "epoch": 9.01489295687248, "percentage": 45.07, "elapsed_time": "0:53:26", "remaining_time": "1:05:07", "throughput": 5526.1, "total_tokens": 17721968} {"current_steps": 29060, "total_steps": 64460, "loss": 0.2353, "lr": 6.69686345500709e-06, "epoch": 9.016444306546695, "percentage": 45.08, "elapsed_time": "0:53:27", "remaining_time": "1:05:07", "throughput": 5526.03, "total_tokens": 17724624} {"current_steps": 29065, "total_steps": 64460, "loss": 0.2356, "lr": 6.695589930641624e-06, "epoch": 9.017995656220911, "percentage": 45.09, "elapsed_time": "0:53:27", "remaining_time": "1:05:06", "throughput": 5526.01, "total_tokens": 17727216} {"current_steps": 29070, "total_steps": 64460, "loss": 0.2256, "lr": 6.6943162819693366e-06, "epoch": 9.019547005895129, "percentage": 45.1, "elapsed_time": "0:53:28", "remaining_time": "1:05:06", "throughput": 5526.11, "total_tokens": 17730608} {"current_steps": 29075, "total_steps": 64460, "loss": 0.2269, "lr": 6.693042509083603e-06, "epoch": 9.021098355569345, "percentage": 45.11, "elapsed_time": "0:53:29", "remaining_time": "1:05:05", "throughput": 5526.24, "total_tokens": 17733808} {"current_steps": 29080, "total_steps": 64460, "loss": 0.229, "lr": 6.6917686120778035e-06, "epoch": 9.022649705243563, "percentage": 45.11, "elapsed_time": "0:53:29", "remaining_time": "1:05:04", "throughput": 5526.22, "total_tokens": 17736528} {"current_steps": 29085, "total_steps": 64460, "loss": 0.2321, "lr": 6.690494591045331e-06, "epoch": 9.024201054917778, "percentage": 45.12, "elapsed_time": "0:53:29", "remaining_time": "1:05:04", "throughput": 5526.13, "total_tokens": 17738768} {"current_steps": 29090, "total_steps": 64460, "loss": 0.2338, "lr": 6.689220446079588e-06, "epoch": 9.025752404591994, "percentage": 45.13, "elapsed_time": "0:53:30", "remaining_time": "1:05:03", "throughput": 5526.2, "total_tokens": 17742064} {"current_steps": 29095, "total_steps": 64460, "loss": 0.2294, "lr": 6.687946177273983e-06, "epoch": 9.027303754266212, "percentage": 45.14, "elapsed_time": "0:53:31", "remaining_time": "1:05:02", "throughput": 5526.04, "total_tokens": 17744144} {"current_steps": 29100, "total_steps": 64460, "loss": 0.2294, "lr": 6.686671784721933e-06, "epoch": 9.028855103940428, "percentage": 45.14, "elapsed_time": "0:53:31", "remaining_time": "1:05:02", "throughput": 5526.06, "total_tokens": 17746928} {"current_steps": 29105, "total_steps": 64460, "loss": 0.2301, "lr": 6.685397268516869e-06, "epoch": 9.030406453614646, "percentage": 45.15, "elapsed_time": "0:53:32", "remaining_time": "1:05:01", "throughput": 5526.06, "total_tokens": 17749840} {"current_steps": 29110, "total_steps": 64460, "loss": 0.2224, "lr": 6.6841226287522275e-06, "epoch": 9.031957803288861, "percentage": 45.16, "elapsed_time": "0:53:32", "remaining_time": "1:05:01", "throughput": 5526.09, "total_tokens": 17752688} {"current_steps": 29115, "total_steps": 64460, "loss": 0.227, "lr": 6.682847865521455e-06, "epoch": 9.033509152963077, "percentage": 45.17, "elapsed_time": "0:53:33", "remaining_time": "1:05:00", "throughput": 5525.96, "total_tokens": 17755088} {"current_steps": 29120, "total_steps": 64460, "loss": 0.235, "lr": 6.681572978918005e-06, "epoch": 9.035060502637295, "percentage": 45.18, "elapsed_time": "0:53:33", "remaining_time": "1:05:00", "throughput": 5526.06, "total_tokens": 17758640} {"current_steps": 29125, "total_steps": 64460, "loss": 0.2317, "lr": 6.680297969035343e-06, "epoch": 9.03661185231151, "percentage": 45.18, "elapsed_time": "0:53:34", "remaining_time": "1:04:59", "throughput": 5526.12, "total_tokens": 17761712} {"current_steps": 29130, "total_steps": 64460, "loss": 0.2274, "lr": 6.679022835966943e-06, "epoch": 9.038163201985727, "percentage": 45.19, "elapsed_time": "0:53:34", "remaining_time": "1:04:58", "throughput": 5526.24, "total_tokens": 17764912} {"current_steps": 29135, "total_steps": 64460, "loss": 0.2264, "lr": 6.677747579806285e-06, "epoch": 9.039714551659944, "percentage": 45.2, "elapsed_time": "0:53:35", "remaining_time": "1:04:58", "throughput": 5526.36, "total_tokens": 17768176} {"current_steps": 29140, "total_steps": 64460, "loss": 0.2332, "lr": 6.676472200646863e-06, "epoch": 9.04126590133416, "percentage": 45.21, "elapsed_time": "0:53:35", "remaining_time": "1:04:57", "throughput": 5526.43, "total_tokens": 17771056} {"current_steps": 29145, "total_steps": 64460, "loss": 0.2253, "lr": 6.675196698582176e-06, "epoch": 9.042817251008378, "percentage": 45.21, "elapsed_time": "0:53:36", "remaining_time": "1:04:56", "throughput": 5526.52, "total_tokens": 17774000} {"current_steps": 29150, "total_steps": 64460, "loss": 0.2308, "lr": 6.673921073705734e-06, "epoch": 9.044368600682594, "percentage": 45.22, "elapsed_time": "0:53:36", "remaining_time": "1:04:56", "throughput": 5526.75, "total_tokens": 17778160} {"current_steps": 29155, "total_steps": 64460, "loss": 0.2249, "lr": 6.672645326111056e-06, "epoch": 9.04591995035681, "percentage": 45.23, "elapsed_time": "0:53:37", "remaining_time": "1:04:55", "throughput": 5526.76, "total_tokens": 17780880} {"current_steps": 29160, "total_steps": 64460, "loss": 0.2204, "lr": 6.671369455891666e-06, "epoch": 9.047471300031027, "percentage": 45.24, "elapsed_time": "0:53:37", "remaining_time": "1:04:55", "throughput": 5526.83, "total_tokens": 17783920} {"current_steps": 29165, "total_steps": 64460, "loss": 0.2294, "lr": 6.670093463141104e-06, "epoch": 9.049022649705243, "percentage": 45.25, "elapsed_time": "0:53:38", "remaining_time": "1:04:54", "throughput": 5526.95, "total_tokens": 17788080} {"current_steps": 29170, "total_steps": 64460, "loss": 0.2437, "lr": 6.668817347952914e-06, "epoch": 9.050573999379461, "percentage": 45.25, "elapsed_time": "0:53:38", "remaining_time": "1:04:54", "throughput": 5526.85, "total_tokens": 17790640} {"current_steps": 29175, "total_steps": 64460, "loss": 0.2182, "lr": 6.667541110420652e-06, "epoch": 9.052125349053677, "percentage": 45.26, "elapsed_time": "0:53:39", "remaining_time": "1:04:53", "throughput": 5526.76, "total_tokens": 17792976} {"current_steps": 29180, "total_steps": 64460, "loss": 0.2303, "lr": 6.666264750637879e-06, "epoch": 9.053676698727893, "percentage": 45.27, "elapsed_time": "0:53:39", "remaining_time": "1:04:53", "throughput": 5526.8, "total_tokens": 17795760} {"current_steps": 29185, "total_steps": 64460, "loss": 0.2389, "lr": 6.6649882686981685e-06, "epoch": 9.05522804840211, "percentage": 45.28, "elapsed_time": "0:53:40", "remaining_time": "1:04:52", "throughput": 5526.81, "total_tokens": 17798640} {"current_steps": 29190, "total_steps": 64460, "loss": 0.2275, "lr": 6.663711664695101e-06, "epoch": 9.056779398076326, "percentage": 45.28, "elapsed_time": "0:53:40", "remaining_time": "1:04:51", "throughput": 5526.85, "total_tokens": 17801520} {"current_steps": 29195, "total_steps": 64460, "loss": 0.2305, "lr": 6.662434938722268e-06, "epoch": 9.058330747750542, "percentage": 45.29, "elapsed_time": "0:53:41", "remaining_time": "1:04:51", "throughput": 5526.96, "total_tokens": 17805328} {"current_steps": 29200, "total_steps": 64460, "loss": 0.2412, "lr": 6.661158090873267e-06, "epoch": 9.05988209742476, "percentage": 45.3, "elapsed_time": "0:53:42", "remaining_time": "1:04:50", "throughput": 5526.73, "total_tokens": 17807600} {"current_steps": 29205, "total_steps": 64460, "loss": 0.2237, "lr": 6.659881121241707e-06, "epoch": 9.061433447098976, "percentage": 45.31, "elapsed_time": "0:53:42", "remaining_time": "1:04:50", "throughput": 5526.82, "total_tokens": 17811152} {"current_steps": 29210, "total_steps": 64460, "loss": 0.2309, "lr": 6.658604029921205e-06, "epoch": 9.062984796773193, "percentage": 45.31, "elapsed_time": "0:53:43", "remaining_time": "1:04:49", "throughput": 5526.86, "total_tokens": 17813968} {"current_steps": 29215, "total_steps": 64460, "loss": 0.2344, "lr": 6.657326817005387e-06, "epoch": 9.06453614644741, "percentage": 45.32, "elapsed_time": "0:53:43", "remaining_time": "1:04:48", "throughput": 5526.79, "total_tokens": 17816336} {"current_steps": 29220, "total_steps": 64460, "loss": 0.2288, "lr": 6.6560494825878875e-06, "epoch": 9.066087496121625, "percentage": 45.33, "elapsed_time": "0:53:44", "remaining_time": "1:04:48", "throughput": 5526.89, "total_tokens": 17819504} {"current_steps": 29225, "total_steps": 64460, "loss": 0.2262, "lr": 6.65477202676235e-06, "epoch": 9.067638845795843, "percentage": 45.34, "elapsed_time": "0:53:44", "remaining_time": "1:04:47", "throughput": 5526.91, "total_tokens": 17822448} {"current_steps": 29230, "total_steps": 64460, "loss": 0.2163, "lr": 6.653494449622428e-06, "epoch": 9.069190195470059, "percentage": 45.35, "elapsed_time": "0:53:45", "remaining_time": "1:04:47", "throughput": 5526.96, "total_tokens": 17825584} {"current_steps": 29235, "total_steps": 64460, "loss": 0.2384, "lr": 6.652216751261783e-06, "epoch": 9.070741545144276, "percentage": 45.35, "elapsed_time": "0:53:45", "remaining_time": "1:04:46", "throughput": 5527.11, "total_tokens": 17829136} {"current_steps": 29240, "total_steps": 64460, "loss": 0.2262, "lr": 6.650938931774085e-06, "epoch": 9.072292894818492, "percentage": 45.36, "elapsed_time": "0:53:46", "remaining_time": "1:04:46", "throughput": 5527.08, "total_tokens": 17832688} {"current_steps": 29245, "total_steps": 64460, "loss": 0.236, "lr": 6.649660991253012e-06, "epoch": 9.073844244492708, "percentage": 45.37, "elapsed_time": "0:53:46", "remaining_time": "1:04:45", "throughput": 5527.19, "total_tokens": 17835952} {"current_steps": 29250, "total_steps": 64460, "loss": 0.2262, "lr": 6.6483829297922544e-06, "epoch": 9.075395594166926, "percentage": 45.38, "elapsed_time": "0:53:47", "remaining_time": "1:04:45", "throughput": 5527.04, "total_tokens": 17838032} {"current_steps": 29255, "total_steps": 64460, "loss": 0.2289, "lr": 6.647104747485508e-06, "epoch": 9.076946943841142, "percentage": 45.38, "elapsed_time": "0:53:47", "remaining_time": "1:04:44", "throughput": 5526.92, "total_tokens": 17840208} {"current_steps": 29260, "total_steps": 64460, "loss": 0.2312, "lr": 6.64582644442648e-06, "epoch": 9.078498293515358, "percentage": 45.39, "elapsed_time": "0:53:48", "remaining_time": "1:04:43", "throughput": 5527.04, "total_tokens": 17843600} {"current_steps": 29265, "total_steps": 64460, "loss": 0.2371, "lr": 6.644548020708882e-06, "epoch": 9.080049643189575, "percentage": 45.4, "elapsed_time": "0:53:48", "remaining_time": "1:04:43", "throughput": 5526.85, "total_tokens": 17845904} {"current_steps": 29270, "total_steps": 64460, "loss": 0.2486, "lr": 6.6432694764264415e-06, "epoch": 9.081600992863791, "percentage": 45.41, "elapsed_time": "0:53:49", "remaining_time": "1:04:42", "throughput": 5527.1, "total_tokens": 17850256} {"current_steps": 29275, "total_steps": 64460, "loss": 0.2375, "lr": 6.641990811672888e-06, "epoch": 9.083152342538009, "percentage": 45.42, "elapsed_time": "0:53:50", "remaining_time": "1:04:42", "throughput": 5527.28, "total_tokens": 17854192} {"current_steps": 29280, "total_steps": 64460, "loss": 0.2215, "lr": 6.640712026541963e-06, "epoch": 9.084703692212225, "percentage": 45.42, "elapsed_time": "0:53:50", "remaining_time": "1:04:41", "throughput": 5527.3, "total_tokens": 17856976} {"current_steps": 29285, "total_steps": 64460, "loss": 0.2357, "lr": 6.63943312112742e-06, "epoch": 9.08625504188644, "percentage": 45.43, "elapsed_time": "0:53:51", "remaining_time": "1:04:41", "throughput": 5527.53, "total_tokens": 17861712} {"current_steps": 29290, "total_steps": 64460, "loss": 0.2201, "lr": 6.638154095523014e-06, "epoch": 9.087806391560658, "percentage": 45.44, "elapsed_time": "0:53:51", "remaining_time": "1:04:40", "throughput": 5527.58, "total_tokens": 17864624} {"current_steps": 29295, "total_steps": 64460, "loss": 0.2304, "lr": 6.636874949822515e-06, "epoch": 9.089357741234874, "percentage": 45.45, "elapsed_time": "0:53:52", "remaining_time": "1:04:40", "throughput": 5527.71, "total_tokens": 17867792} {"current_steps": 29300, "total_steps": 64460, "loss": 0.2265, "lr": 6.635595684119698e-06, "epoch": 9.090909090909092, "percentage": 45.45, "elapsed_time": "0:53:52", "remaining_time": "1:04:39", "throughput": 5527.61, "total_tokens": 17870192} {"current_steps": 29305, "total_steps": 64460, "loss": 0.2336, "lr": 6.6343162985083474e-06, "epoch": 9.092460440583308, "percentage": 45.46, "elapsed_time": "0:53:53", "remaining_time": "1:04:38", "throughput": 5527.7, "total_tokens": 17873648} {"current_steps": 29310, "total_steps": 64460, "loss": 0.2327, "lr": 6.633036793082261e-06, "epoch": 9.094011790257523, "percentage": 45.47, "elapsed_time": "0:53:54", "remaining_time": "1:04:38", "throughput": 5527.92, "total_tokens": 17877776} {"current_steps": 29315, "total_steps": 64460, "loss": 0.2301, "lr": 6.63175716793524e-06, "epoch": 9.095563139931741, "percentage": 45.48, "elapsed_time": "0:53:54", "remaining_time": "1:04:37", "throughput": 5527.96, "total_tokens": 17880624} {"current_steps": 29320, "total_steps": 64460, "loss": 0.2287, "lr": 6.630477423161095e-06, "epoch": 9.097114489605957, "percentage": 45.49, "elapsed_time": "0:53:55", "remaining_time": "1:04:37", "throughput": 5528.1, "total_tokens": 17883984} {"current_steps": 29325, "total_steps": 64460, "loss": 0.2289, "lr": 6.629197558853647e-06, "epoch": 9.098665839280173, "percentage": 45.49, "elapsed_time": "0:53:55", "remaining_time": "1:04:36", "throughput": 5528.26, "total_tokens": 17888016} {"current_steps": 29330, "total_steps": 64460, "loss": 0.2273, "lr": 6.627917575106726e-06, "epoch": 9.10021718895439, "percentage": 45.5, "elapsed_time": "0:53:56", "remaining_time": "1:04:36", "throughput": 5528.72, "total_tokens": 17895824} {"current_steps": 29335, "total_steps": 64460, "loss": 0.2287, "lr": 6.626637472014168e-06, "epoch": 9.101768538628606, "percentage": 45.51, "elapsed_time": "0:53:57", "remaining_time": "1:04:36", "throughput": 5528.78, "total_tokens": 17898832} {"current_steps": 29340, "total_steps": 64460, "loss": 0.2323, "lr": 6.625357249669823e-06, "epoch": 9.103319888302824, "percentage": 45.52, "elapsed_time": "0:53:57", "remaining_time": "1:04:35", "throughput": 5528.85, "total_tokens": 17901840} {"current_steps": 29345, "total_steps": 64460, "loss": 0.2242, "lr": 6.624076908167543e-06, "epoch": 9.10487123797704, "percentage": 45.52, "elapsed_time": "0:53:58", "remaining_time": "1:04:35", "throughput": 5528.91, "total_tokens": 17904848} {"current_steps": 29350, "total_steps": 64460, "loss": 0.2251, "lr": 6.622796447601194e-06, "epoch": 9.106422587651256, "percentage": 45.53, "elapsed_time": "0:53:59", "remaining_time": "1:04:34", "throughput": 5529.03, "total_tokens": 17908560} {"current_steps": 29355, "total_steps": 64460, "loss": 0.2238, "lr": 6.621515868064648e-06, "epoch": 9.107973937325474, "percentage": 45.54, "elapsed_time": "0:53:59", "remaining_time": "1:04:34", "throughput": 5528.94, "total_tokens": 17911024} {"current_steps": 29360, "total_steps": 64460, "loss": 0.2434, "lr": 6.620235169651787e-06, "epoch": 9.10952528699969, "percentage": 45.55, "elapsed_time": "0:53:59", "remaining_time": "1:04:33", "throughput": 5529.04, "total_tokens": 17914000} {"current_steps": 29365, "total_steps": 64460, "loss": 0.2289, "lr": 6.6189543524565026e-06, "epoch": 9.111076636673907, "percentage": 45.56, "elapsed_time": "0:54:00", "remaining_time": "1:04:32", "throughput": 5528.97, "total_tokens": 17916336} {"current_steps": 29370, "total_steps": 64460, "loss": 0.2362, "lr": 6.617673416572693e-06, "epoch": 9.112627986348123, "percentage": 45.56, "elapsed_time": "0:54:00", "remaining_time": "1:04:32", "throughput": 5528.93, "total_tokens": 17918768} {"current_steps": 29375, "total_steps": 64460, "loss": 0.2281, "lr": 6.616392362094266e-06, "epoch": 9.114179336022339, "percentage": 45.57, "elapsed_time": "0:54:01", "remaining_time": "1:04:31", "throughput": 5529.0, "total_tokens": 17921744} {"current_steps": 29380, "total_steps": 64460, "loss": 0.2216, "lr": 6.6151111891151374e-06, "epoch": 9.115730685696557, "percentage": 45.58, "elapsed_time": "0:54:02", "remaining_time": "1:04:30", "throughput": 5529.24, "total_tokens": 17925808} {"current_steps": 29385, "total_steps": 64460, "loss": 0.2184, "lr": 6.613829897729234e-06, "epoch": 9.117282035370772, "percentage": 45.59, "elapsed_time": "0:54:02", "remaining_time": "1:04:30", "throughput": 5529.27, "total_tokens": 17928656} {"current_steps": 29390, "total_steps": 64460, "loss": 0.2305, "lr": 6.612548488030487e-06, "epoch": 9.118833385044988, "percentage": 45.59, "elapsed_time": "0:54:02", "remaining_time": "1:04:29", "throughput": 5529.27, "total_tokens": 17931216} {"current_steps": 29395, "total_steps": 64460, "loss": 0.2236, "lr": 6.611266960112841e-06, "epoch": 9.120384734719206, "percentage": 45.6, "elapsed_time": "0:54:03", "remaining_time": "1:04:29", "throughput": 5529.34, "total_tokens": 17934512} {"current_steps": 29400, "total_steps": 64460, "loss": 0.2219, "lr": 6.609985314070246e-06, "epoch": 9.121936084393422, "percentage": 45.61, "elapsed_time": "0:54:03", "remaining_time": "1:04:28", "throughput": 5529.28, "total_tokens": 17936944} {"current_steps": 29405, "total_steps": 64460, "loss": 0.2297, "lr": 6.608703549996662e-06, "epoch": 9.12348743406764, "percentage": 45.62, "elapsed_time": "0:54:04", "remaining_time": "1:04:27", "throughput": 5529.34, "total_tokens": 17940048} {"current_steps": 29410, "total_steps": 64460, "loss": 0.23, "lr": 6.60742166798606e-06, "epoch": 9.125038783741855, "percentage": 45.63, "elapsed_time": "0:54:05", "remaining_time": "1:04:27", "throughput": 5529.32, "total_tokens": 17942864} {"current_steps": 29415, "total_steps": 64460, "loss": 0.2322, "lr": 6.606139668132412e-06, "epoch": 9.126590133416071, "percentage": 45.63, "elapsed_time": "0:54:05", "remaining_time": "1:04:26", "throughput": 5529.34, "total_tokens": 17945648} {"current_steps": 29420, "total_steps": 64460, "loss": 0.2166, "lr": 6.604857550529709e-06, "epoch": 9.128141483090289, "percentage": 45.64, "elapsed_time": "0:54:06", "remaining_time": "1:04:26", "throughput": 5529.55, "total_tokens": 17949552} {"current_steps": 29425, "total_steps": 64460, "loss": 0.2253, "lr": 6.6035753152719426e-06, "epoch": 9.129692832764505, "percentage": 45.65, "elapsed_time": "0:54:06", "remaining_time": "1:04:25", "throughput": 5529.62, "total_tokens": 17953456} {"current_steps": 29430, "total_steps": 64460, "loss": 0.2279, "lr": 6.602292962453116e-06, "epoch": 9.131244182438722, "percentage": 45.66, "elapsed_time": "0:54:07", "remaining_time": "1:04:25", "throughput": 5529.41, "total_tokens": 17955536} {"current_steps": 29435, "total_steps": 64460, "loss": 0.2187, "lr": 6.601010492167243e-06, "epoch": 9.132795532112938, "percentage": 45.66, "elapsed_time": "0:54:07", "remaining_time": "1:04:24", "throughput": 5529.43, "total_tokens": 17958288} {"current_steps": 29440, "total_steps": 64460, "loss": 0.2289, "lr": 6.599727904508341e-06, "epoch": 9.134346881787154, "percentage": 45.67, "elapsed_time": "0:54:08", "remaining_time": "1:04:24", "throughput": 5529.66, "total_tokens": 17962384} {"current_steps": 29445, "total_steps": 64460, "loss": 0.2323, "lr": 6.59844519957044e-06, "epoch": 9.135898231461372, "percentage": 45.68, "elapsed_time": "0:54:08", "remaining_time": "1:04:23", "throughput": 5529.5, "total_tokens": 17964688} {"current_steps": 29450, "total_steps": 64460, "loss": 0.2286, "lr": 6.597162377447577e-06, "epoch": 9.137449581135588, "percentage": 45.69, "elapsed_time": "0:54:09", "remaining_time": "1:04:22", "throughput": 5529.58, "total_tokens": 17967600} {"current_steps": 29455, "total_steps": 64460, "loss": 0.2353, "lr": 6.595879438233799e-06, "epoch": 9.139000930809804, "percentage": 45.7, "elapsed_time": "0:54:09", "remaining_time": "1:04:22", "throughput": 5529.67, "total_tokens": 17970832} {"current_steps": 29460, "total_steps": 64460, "loss": 0.2435, "lr": 6.59459638202316e-06, "epoch": 9.140552280484021, "percentage": 45.7, "elapsed_time": "0:54:10", "remaining_time": "1:04:21", "throughput": 5529.6, "total_tokens": 17973296} {"current_steps": 29465, "total_steps": 64460, "loss": 0.236, "lr": 6.593313208909724e-06, "epoch": 9.142103630158237, "percentage": 45.71, "elapsed_time": "0:54:10", "remaining_time": "1:04:21", "throughput": 5529.7, "total_tokens": 17976848} {"current_steps": 29470, "total_steps": 64460, "loss": 0.2281, "lr": 6.592029918987562e-06, "epoch": 9.143654979832455, "percentage": 45.72, "elapsed_time": "0:54:11", "remaining_time": "1:04:20", "throughput": 5529.74, "total_tokens": 17979888} {"current_steps": 29475, "total_steps": 64460, "loss": 0.2296, "lr": 6.590746512350752e-06, "epoch": 9.14520632950667, "percentage": 45.73, "elapsed_time": "0:54:12", "remaining_time": "1:04:20", "throughput": 5530.01, "total_tokens": 17985168} {"current_steps": 29480, "total_steps": 64460, "loss": 0.2263, "lr": 6.589462989093387e-06, "epoch": 9.146757679180887, "percentage": 45.73, "elapsed_time": "0:54:12", "remaining_time": "1:04:19", "throughput": 5530.14, "total_tokens": 17988496} {"current_steps": 29485, "total_steps": 64460, "loss": 0.2306, "lr": 6.588179349309564e-06, "epoch": 9.148309028855104, "percentage": 45.74, "elapsed_time": "0:54:13", "remaining_time": "1:04:19", "throughput": 5530.15, "total_tokens": 17991376} {"current_steps": 29490, "total_steps": 64460, "loss": 0.2219, "lr": 6.586895593093386e-06, "epoch": 9.14986037852932, "percentage": 45.75, "elapsed_time": "0:54:13", "remaining_time": "1:04:18", "throughput": 5530.19, "total_tokens": 17994096} {"current_steps": 29495, "total_steps": 64460, "loss": 0.2324, "lr": 6.5856117205389716e-06, "epoch": 9.151411728203538, "percentage": 45.76, "elapsed_time": "0:54:14", "remaining_time": "1:04:17", "throughput": 5530.23, "total_tokens": 17996848} {"current_steps": 29500, "total_steps": 64460, "loss": 0.2305, "lr": 6.584327731740441e-06, "epoch": 9.152963077877754, "percentage": 45.76, "elapsed_time": "0:54:14", "remaining_time": "1:04:17", "throughput": 5530.46, "total_tokens": 18001040} {"current_steps": 29505, "total_steps": 64460, "loss": 0.2167, "lr": 6.583043626791925e-06, "epoch": 9.15451442755197, "percentage": 45.77, "elapsed_time": "0:54:15", "remaining_time": "1:04:16", "throughput": 5530.63, "total_tokens": 18004560} {"current_steps": 29510, "total_steps": 64460, "loss": 0.2263, "lr": 6.581759405787566e-06, "epoch": 9.156065777226187, "percentage": 45.78, "elapsed_time": "0:54:15", "remaining_time": "1:04:16", "throughput": 5530.7, "total_tokens": 18007504} {"current_steps": 29515, "total_steps": 64460, "loss": 0.2253, "lr": 6.580475068821512e-06, "epoch": 9.157617126900403, "percentage": 45.79, "elapsed_time": "0:54:16", "remaining_time": "1:04:15", "throughput": 5530.63, "total_tokens": 18009840} {"current_steps": 29520, "total_steps": 64460, "loss": 0.2287, "lr": 6.579190615987919e-06, "epoch": 9.159168476574619, "percentage": 45.8, "elapsed_time": "0:54:16", "remaining_time": "1:04:14", "throughput": 5530.59, "total_tokens": 18012432} {"current_steps": 29525, "total_steps": 64460, "loss": 0.2316, "lr": 6.5779060473809545e-06, "epoch": 9.160719826248837, "percentage": 45.8, "elapsed_time": "0:54:17", "remaining_time": "1:04:14", "throughput": 5530.76, "total_tokens": 18016784} {"current_steps": 29530, "total_steps": 64460, "loss": 0.2186, "lr": 6.576621363094791e-06, "epoch": 9.162271175923053, "percentage": 45.81, "elapsed_time": "0:54:18", "remaining_time": "1:04:13", "throughput": 5530.85, "total_tokens": 18020016} {"current_steps": 29535, "total_steps": 64460, "loss": 0.2372, "lr": 6.575336563223611e-06, "epoch": 9.16382252559727, "percentage": 45.82, "elapsed_time": "0:54:18", "remaining_time": "1:04:13", "throughput": 5530.85, "total_tokens": 18022704} {"current_steps": 29540, "total_steps": 64460, "loss": 0.2217, "lr": 6.574051647861607e-06, "epoch": 9.165373875271486, "percentage": 45.83, "elapsed_time": "0:54:19", "remaining_time": "1:04:12", "throughput": 5530.77, "total_tokens": 18025168} {"current_steps": 29545, "total_steps": 64460, "loss": 0.2237, "lr": 6.572766617102977e-06, "epoch": 9.166925224945702, "percentage": 45.83, "elapsed_time": "0:54:19", "remaining_time": "1:04:11", "throughput": 5530.79, "total_tokens": 18027920} {"current_steps": 29550, "total_steps": 64460, "loss": 0.215, "lr": 6.57148147104193e-06, "epoch": 9.16847657461992, "percentage": 45.84, "elapsed_time": "0:54:20", "remaining_time": "1:04:11", "throughput": 5530.67, "total_tokens": 18030256} {"current_steps": 29555, "total_steps": 64460, "loss": 0.2183, "lr": 6.570196209772682e-06, "epoch": 9.170027924294136, "percentage": 45.85, "elapsed_time": "0:54:20", "remaining_time": "1:04:10", "throughput": 5530.65, "total_tokens": 18032784} {"current_steps": 29560, "total_steps": 64460, "loss": 0.2347, "lr": 6.568910833389458e-06, "epoch": 9.171579273968353, "percentage": 45.86, "elapsed_time": "0:54:21", "remaining_time": "1:04:10", "throughput": 5530.48, "total_tokens": 18034992} {"current_steps": 29565, "total_steps": 64460, "loss": 0.2269, "lr": 6.567625341986491e-06, "epoch": 9.17313062364257, "percentage": 45.87, "elapsed_time": "0:54:21", "remaining_time": "1:04:09", "throughput": 5530.49, "total_tokens": 18037872} {"current_steps": 29570, "total_steps": 64460, "loss": 0.2238, "lr": 6.5663397356580234e-06, "epoch": 9.174681973316785, "percentage": 45.87, "elapsed_time": "0:54:22", "remaining_time": "1:04:08", "throughput": 5530.59, "total_tokens": 18040944} {"current_steps": 29575, "total_steps": 64460, "loss": 0.2258, "lr": 6.565054014498305e-06, "epoch": 9.176233322991003, "percentage": 45.88, "elapsed_time": "0:54:22", "remaining_time": "1:04:08", "throughput": 5530.69, "total_tokens": 18044368} {"current_steps": 29580, "total_steps": 64460, "loss": 0.2333, "lr": 6.563768178601594e-06, "epoch": 9.177784672665219, "percentage": 45.89, "elapsed_time": "0:54:23", "remaining_time": "1:04:07", "throughput": 5530.65, "total_tokens": 18046992} {"current_steps": 29585, "total_steps": 64460, "loss": 0.2376, "lr": 6.562482228062158e-06, "epoch": 9.179336022339434, "percentage": 45.9, "elapsed_time": "0:54:23", "remaining_time": "1:04:07", "throughput": 5530.62, "total_tokens": 18049648} {"current_steps": 29590, "total_steps": 64460, "loss": 0.2379, "lr": 6.56119616297427e-06, "epoch": 9.180887372013652, "percentage": 45.9, "elapsed_time": "0:54:24", "remaining_time": "1:04:06", "throughput": 5530.72, "total_tokens": 18053136} {"current_steps": 29595, "total_steps": 64460, "loss": 0.2257, "lr": 6.559909983432218e-06, "epoch": 9.182438721687868, "percentage": 45.91, "elapsed_time": "0:54:24", "remaining_time": "1:04:06", "throughput": 5530.76, "total_tokens": 18056464} {"current_steps": 29600, "total_steps": 64460, "loss": 0.2411, "lr": 6.558623689530293e-06, "epoch": 9.183990071362086, "percentage": 45.92, "elapsed_time": "0:54:25", "remaining_time": "1:04:05", "throughput": 5530.8, "total_tokens": 18059312} {"current_steps": 29605, "total_steps": 64460, "loss": 0.2355, "lr": 6.557337281362793e-06, "epoch": 9.185541421036302, "percentage": 45.93, "elapsed_time": "0:54:25", "remaining_time": "1:04:04", "throughput": 5530.89, "total_tokens": 18062352} {"current_steps": 29610, "total_steps": 64460, "loss": 0.2247, "lr": 6.556050759024028e-06, "epoch": 9.187092770710517, "percentage": 45.94, "elapsed_time": "0:54:26", "remaining_time": "1:04:04", "throughput": 5530.93, "total_tokens": 18065488} {"current_steps": 29615, "total_steps": 64460, "loss": 0.2224, "lr": 6.554764122608317e-06, "epoch": 9.188644120384735, "percentage": 45.94, "elapsed_time": "0:54:26", "remaining_time": "1:04:03", "throughput": 5530.88, "total_tokens": 18067952} {"current_steps": 29620, "total_steps": 64460, "loss": 0.224, "lr": 6.553477372209985e-06, "epoch": 9.190195470058951, "percentage": 45.95, "elapsed_time": "0:54:27", "remaining_time": "1:04:03", "throughput": 5530.88, "total_tokens": 18071120} {"current_steps": 29625, "total_steps": 64460, "loss": 0.2342, "lr": 6.552190507923366e-06, "epoch": 9.191746819733169, "percentage": 45.96, "elapsed_time": "0:54:27", "remaining_time": "1:04:02", "throughput": 5530.85, "total_tokens": 18073680} {"current_steps": 29630, "total_steps": 64460, "loss": 0.2386, "lr": 6.550903529842803e-06, "epoch": 9.193298169407385, "percentage": 45.97, "elapsed_time": "0:54:28", "remaining_time": "1:04:01", "throughput": 5530.8, "total_tokens": 18076720} {"current_steps": 29635, "total_steps": 64460, "loss": 0.2367, "lr": 6.549616438062644e-06, "epoch": 9.1948495190816, "percentage": 45.97, "elapsed_time": "0:54:28", "remaining_time": "1:04:01", "throughput": 5530.76, "total_tokens": 18079248} {"current_steps": 29640, "total_steps": 64460, "loss": 0.2314, "lr": 6.548329232677249e-06, "epoch": 9.196400868755818, "percentage": 45.98, "elapsed_time": "0:54:29", "remaining_time": "1:04:00", "throughput": 5530.63, "total_tokens": 18081456} {"current_steps": 29645, "total_steps": 64460, "loss": 0.228, "lr": 6.547041913780988e-06, "epoch": 9.197952218430034, "percentage": 45.99, "elapsed_time": "0:54:29", "remaining_time": "1:04:00", "throughput": 5530.8, "total_tokens": 18084944} {"current_steps": 29650, "total_steps": 64460, "loss": 0.2325, "lr": 6.545754481468235e-06, "epoch": 9.19950356810425, "percentage": 46.0, "elapsed_time": "0:54:30", "remaining_time": "1:03:59", "throughput": 5530.88, "total_tokens": 18088048} {"current_steps": 29655, "total_steps": 64460, "loss": 0.2204, "lr": 6.5444669358333735e-06, "epoch": 9.201054917778468, "percentage": 46.01, "elapsed_time": "0:54:30", "remaining_time": "1:03:58", "throughput": 5530.93, "total_tokens": 18091088} {"current_steps": 29660, "total_steps": 64460, "loss": 0.2339, "lr": 6.543179276970797e-06, "epoch": 9.202606267452683, "percentage": 46.01, "elapsed_time": "0:54:31", "remaining_time": "1:03:58", "throughput": 5530.91, "total_tokens": 18093776} {"current_steps": 29665, "total_steps": 64460, "loss": 0.2356, "lr": 6.541891504974904e-06, "epoch": 9.204157617126901, "percentage": 46.02, "elapsed_time": "0:54:31", "remaining_time": "1:03:57", "throughput": 5530.77, "total_tokens": 18095984} {"current_steps": 29670, "total_steps": 64460, "loss": 0.2319, "lr": 6.540603619940107e-06, "epoch": 9.205708966801117, "percentage": 46.03, "elapsed_time": "0:54:32", "remaining_time": "1:03:57", "throughput": 5530.83, "total_tokens": 18098992} {"current_steps": 29675, "total_steps": 64460, "loss": 0.2184, "lr": 6.53931562196082e-06, "epoch": 9.207260316475333, "percentage": 46.04, "elapsed_time": "0:54:32", "remaining_time": "1:03:56", "throughput": 5530.91, "total_tokens": 18102000} {"current_steps": 29680, "total_steps": 64460, "loss": 0.2287, "lr": 6.538027511131469e-06, "epoch": 9.20881166614955, "percentage": 46.04, "elapsed_time": "0:54:33", "remaining_time": "1:03:55", "throughput": 5530.78, "total_tokens": 18104240} {"current_steps": 29685, "total_steps": 64460, "loss": 0.2261, "lr": 6.53673928754649e-06, "epoch": 9.210363015823766, "percentage": 46.05, "elapsed_time": "0:54:33", "remaining_time": "1:03:55", "throughput": 5530.84, "total_tokens": 18107376} {"current_steps": 29690, "total_steps": 64460, "loss": 0.2283, "lr": 6.535450951300323e-06, "epoch": 9.211914365497984, "percentage": 46.06, "elapsed_time": "0:54:34", "remaining_time": "1:03:54", "throughput": 5530.91, "total_tokens": 18110256} {"current_steps": 29695, "total_steps": 64460, "loss": 0.2193, "lr": 6.534162502487419e-06, "epoch": 9.2134657151722, "percentage": 46.07, "elapsed_time": "0:54:34", "remaining_time": "1:03:53", "throughput": 5530.95, "total_tokens": 18113104} {"current_steps": 29700, "total_steps": 64460, "loss": 0.2335, "lr": 6.532873941202236e-06, "epoch": 9.215017064846416, "percentage": 46.08, "elapsed_time": "0:54:35", "remaining_time": "1:03:53", "throughput": 5531.07, "total_tokens": 18117136} {"current_steps": 29705, "total_steps": 64460, "loss": 0.2337, "lr": 6.531585267539241e-06, "epoch": 9.216568414520633, "percentage": 46.08, "elapsed_time": "0:54:36", "remaining_time": "1:03:52", "throughput": 5531.12, "total_tokens": 18120048} {"current_steps": 29710, "total_steps": 64460, "loss": 0.226, "lr": 6.530296481592909e-06, "epoch": 9.21811976419485, "percentage": 46.09, "elapsed_time": "0:54:36", "remaining_time": "1:03:52", "throughput": 5531.03, "total_tokens": 18122320} {"current_steps": 29715, "total_steps": 64460, "loss": 0.2339, "lr": 6.5290075834577245e-06, "epoch": 9.219671113869065, "percentage": 46.1, "elapsed_time": "0:54:37", "remaining_time": "1:03:51", "throughput": 5531.13, "total_tokens": 18125744} {"current_steps": 29720, "total_steps": 64460, "loss": 0.2148, "lr": 6.527718573228177e-06, "epoch": 9.221222463543283, "percentage": 46.11, "elapsed_time": "0:54:37", "remaining_time": "1:03:51", "throughput": 5531.24, "total_tokens": 18129264} {"current_steps": 29725, "total_steps": 64460, "loss": 0.2429, "lr": 6.526429450998767e-06, "epoch": 9.222773813217499, "percentage": 46.11, "elapsed_time": "0:54:38", "remaining_time": "1:03:50", "throughput": 5531.3, "total_tokens": 18132592} {"current_steps": 29730, "total_steps": 64460, "loss": 0.2285, "lr": 6.525140216864003e-06, "epoch": 9.224325162891716, "percentage": 46.12, "elapsed_time": "0:54:38", "remaining_time": "1:03:50", "throughput": 5531.33, "total_tokens": 18135536} {"current_steps": 29735, "total_steps": 64460, "loss": 0.2182, "lr": 6.523850870918402e-06, "epoch": 9.225876512565932, "percentage": 46.13, "elapsed_time": "0:54:39", "remaining_time": "1:03:49", "throughput": 5531.23, "total_tokens": 18137776} {"current_steps": 29740, "total_steps": 64460, "loss": 0.2223, "lr": 6.5225614132564855e-06, "epoch": 9.227427862240148, "percentage": 46.14, "elapsed_time": "0:54:39", "remaining_time": "1:03:49", "throughput": 5531.39, "total_tokens": 18141968} {"current_steps": 29745, "total_steps": 64460, "loss": 0.2307, "lr": 6.521271843972787e-06, "epoch": 9.228979211914366, "percentage": 46.14, "elapsed_time": "0:54:40", "remaining_time": "1:03:48", "throughput": 5531.25, "total_tokens": 18144304} {"current_steps": 29750, "total_steps": 64460, "loss": 0.2356, "lr": 6.51998216316185e-06, "epoch": 9.230530561588582, "percentage": 46.15, "elapsed_time": "0:54:40", "remaining_time": "1:03:47", "throughput": 5531.21, "total_tokens": 18146768} {"current_steps": 29755, "total_steps": 64460, "loss": 0.2207, "lr": 6.518692370918219e-06, "epoch": 9.2320819112628, "percentage": 46.16, "elapsed_time": "0:54:41", "remaining_time": "1:03:47", "throughput": 5531.19, "total_tokens": 18149360} {"current_steps": 29760, "total_steps": 64460, "loss": 0.2226, "lr": 6.517402467336455e-06, "epoch": 9.233633260937015, "percentage": 46.17, "elapsed_time": "0:54:41", "remaining_time": "1:03:46", "throughput": 5531.16, "total_tokens": 18152080} {"current_steps": 29765, "total_steps": 64460, "loss": 0.2178, "lr": 6.516112452511121e-06, "epoch": 9.235184610611231, "percentage": 46.18, "elapsed_time": "0:54:42", "remaining_time": "1:03:45", "throughput": 5531.24, "total_tokens": 18155248} {"current_steps": 29770, "total_steps": 64460, "loss": 0.2188, "lr": 6.514822326536789e-06, "epoch": 9.236735960285449, "percentage": 46.18, "elapsed_time": "0:54:42", "remaining_time": "1:03:45", "throughput": 5531.36, "total_tokens": 18158704} {"current_steps": 29775, "total_steps": 64460, "loss": 0.2367, "lr": 6.513532089508045e-06, "epoch": 9.238287309959665, "percentage": 46.19, "elapsed_time": "0:54:43", "remaining_time": "1:03:44", "throughput": 5531.41, "total_tokens": 18161552} {"current_steps": 29780, "total_steps": 64460, "loss": 0.2102, "lr": 6.512241741519474e-06, "epoch": 9.23983865963388, "percentage": 46.2, "elapsed_time": "0:54:43", "remaining_time": "1:03:44", "throughput": 5531.4, "total_tokens": 18164304} {"current_steps": 29785, "total_steps": 64460, "loss": 0.2281, "lr": 6.5109512826656765e-06, "epoch": 9.241390009308098, "percentage": 46.21, "elapsed_time": "0:54:44", "remaining_time": "1:03:43", "throughput": 5531.47, "total_tokens": 18167568} {"current_steps": 29790, "total_steps": 64460, "loss": 0.2248, "lr": 6.509660713041257e-06, "epoch": 9.242941358982314, "percentage": 46.21, "elapsed_time": "0:54:44", "remaining_time": "1:03:43", "throughput": 5531.54, "total_tokens": 18170544} {"current_steps": 29795, "total_steps": 64460, "loss": 0.2443, "lr": 6.50837003274083e-06, "epoch": 9.244492708656532, "percentage": 46.22, "elapsed_time": "0:54:45", "remaining_time": "1:03:42", "throughput": 5531.7, "total_tokens": 18174672} {"current_steps": 29800, "total_steps": 64460, "loss": 0.221, "lr": 6.507079241859019e-06, "epoch": 9.246044058330748, "percentage": 46.23, "elapsed_time": "0:54:46", "remaining_time": "1:03:42", "throughput": 5531.89, "total_tokens": 18178736} {"current_steps": 29805, "total_steps": 64460, "loss": 0.2461, "lr": 6.505788340490453e-06, "epoch": 9.247595408004964, "percentage": 46.24, "elapsed_time": "0:54:46", "remaining_time": "1:03:41", "throughput": 5531.85, "total_tokens": 18181328} {"current_steps": 29810, "total_steps": 64460, "loss": 0.2309, "lr": 6.5044973287297695e-06, "epoch": 9.249146757679181, "percentage": 46.25, "elapsed_time": "0:54:47", "remaining_time": "1:03:40", "throughput": 5531.85, "total_tokens": 18183920} {"current_steps": 29815, "total_steps": 64460, "loss": 0.2277, "lr": 6.503206206671617e-06, "epoch": 9.250698107353397, "percentage": 46.25, "elapsed_time": "0:54:47", "remaining_time": "1:03:40", "throughput": 5532.13, "total_tokens": 18188784} {"current_steps": 29820, "total_steps": 64460, "loss": 0.2364, "lr": 6.501914974410648e-06, "epoch": 9.252249457027615, "percentage": 46.26, "elapsed_time": "0:54:48", "remaining_time": "1:03:40", "throughput": 5532.36, "total_tokens": 18193264} {"current_steps": 29825, "total_steps": 64460, "loss": 0.2216, "lr": 6.500623632041527e-06, "epoch": 9.25380080670183, "percentage": 46.27, "elapsed_time": "0:54:49", "remaining_time": "1:03:39", "throughput": 5532.28, "total_tokens": 18196048} {"current_steps": 29830, "total_steps": 64460, "loss": 0.2246, "lr": 6.499332179658923e-06, "epoch": 9.255352156376047, "percentage": 46.28, "elapsed_time": "0:54:49", "remaining_time": "1:03:38", "throughput": 5532.22, "total_tokens": 18198800} {"current_steps": 29835, "total_steps": 64460, "loss": 0.2201, "lr": 6.498040617357515e-06, "epoch": 9.256903506050264, "percentage": 46.28, "elapsed_time": "0:54:50", "remaining_time": "1:03:38", "throughput": 5532.36, "total_tokens": 18202192} {"current_steps": 29840, "total_steps": 64460, "loss": 0.2293, "lr": 6.496748945231991e-06, "epoch": 9.25845485572448, "percentage": 46.29, "elapsed_time": "0:54:50", "remaining_time": "1:03:37", "throughput": 5532.33, "total_tokens": 18205072} {"current_steps": 29845, "total_steps": 64460, "loss": 0.2203, "lr": 6.495457163377046e-06, "epoch": 9.260006205398696, "percentage": 46.3, "elapsed_time": "0:54:51", "remaining_time": "1:03:37", "throughput": 5532.41, "total_tokens": 18208592} {"current_steps": 29850, "total_steps": 64460, "loss": 0.2326, "lr": 6.494165271887379e-06, "epoch": 9.261557555072914, "percentage": 46.31, "elapsed_time": "0:54:51", "remaining_time": "1:03:36", "throughput": 5532.26, "total_tokens": 18210736} {"current_steps": 29855, "total_steps": 64460, "loss": 0.2261, "lr": 6.492873270857707e-06, "epoch": 9.26310890474713, "percentage": 46.32, "elapsed_time": "0:54:52", "remaining_time": "1:03:36", "throughput": 5532.07, "total_tokens": 18212752} {"current_steps": 29860, "total_steps": 64460, "loss": 0.2369, "lr": 6.491581160382745e-06, "epoch": 9.264660254421347, "percentage": 46.32, "elapsed_time": "0:54:52", "remaining_time": "1:03:35", "throughput": 5532.16, "total_tokens": 18216272} {"current_steps": 29865, "total_steps": 64460, "loss": 0.2169, "lr": 6.490288940557221e-06, "epoch": 9.266211604095563, "percentage": 46.33, "elapsed_time": "0:54:53", "remaining_time": "1:03:34", "throughput": 5532.15, "total_tokens": 18218832} {"current_steps": 29870, "total_steps": 64460, "loss": 0.2328, "lr": 6.4889966114758704e-06, "epoch": 9.267762953769779, "percentage": 46.34, "elapsed_time": "0:54:53", "remaining_time": "1:03:34", "throughput": 5532.2, "total_tokens": 18221872} {"current_steps": 29875, "total_steps": 64460, "loss": 0.2193, "lr": 6.487704173233436e-06, "epoch": 9.269314303443997, "percentage": 46.35, "elapsed_time": "0:54:54", "remaining_time": "1:03:33", "throughput": 5532.15, "total_tokens": 18224272} {"current_steps": 29880, "total_steps": 64460, "loss": 0.2378, "lr": 6.4864116259246665e-06, "epoch": 9.270865653118213, "percentage": 46.35, "elapsed_time": "0:54:54", "remaining_time": "1:03:32", "throughput": 5532.21, "total_tokens": 18227216} {"current_steps": 29885, "total_steps": 64460, "loss": 0.2222, "lr": 6.485118969644324e-06, "epoch": 9.27241700279243, "percentage": 46.36, "elapsed_time": "0:54:55", "remaining_time": "1:03:32", "throughput": 5532.26, "total_tokens": 18230128} {"current_steps": 29890, "total_steps": 64460, "loss": 0.2243, "lr": 6.4838262044871755e-06, "epoch": 9.273968352466646, "percentage": 46.37, "elapsed_time": "0:54:55", "remaining_time": "1:03:31", "throughput": 5532.33, "total_tokens": 18233264} {"current_steps": 29895, "total_steps": 64460, "loss": 0.2241, "lr": 6.482533330547995e-06, "epoch": 9.275519702140862, "percentage": 46.38, "elapsed_time": "0:54:56", "remaining_time": "1:03:31", "throughput": 5532.37, "total_tokens": 18236240} {"current_steps": 29900, "total_steps": 64460, "loss": 0.2296, "lr": 6.481240347921566e-06, "epoch": 9.27707105181508, "percentage": 46.39, "elapsed_time": "0:54:56", "remaining_time": "1:03:30", "throughput": 5532.42, "total_tokens": 18239408} {"current_steps": 29905, "total_steps": 64460, "loss": 0.2389, "lr": 6.479947256702679e-06, "epoch": 9.278622401489296, "percentage": 46.39, "elapsed_time": "0:54:57", "remaining_time": "1:03:29", "throughput": 5532.32, "total_tokens": 18241680} {"current_steps": 29910, "total_steps": 64460, "loss": 0.2162, "lr": 6.4786540569861315e-06, "epoch": 9.280173751163511, "percentage": 46.4, "elapsed_time": "0:54:57", "remaining_time": "1:03:29", "throughput": 5532.49, "total_tokens": 18245328} {"current_steps": 29915, "total_steps": 64460, "loss": 0.2261, "lr": 6.477360748866732e-06, "epoch": 9.281725100837729, "percentage": 46.41, "elapsed_time": "0:54:58", "remaining_time": "1:03:28", "throughput": 5532.61, "total_tokens": 18248432} {"current_steps": 29920, "total_steps": 64460, "loss": 0.2351, "lr": 6.476067332439295e-06, "epoch": 9.283276450511945, "percentage": 46.42, "elapsed_time": "0:54:58", "remaining_time": "1:03:28", "throughput": 5532.72, "total_tokens": 18251888} {"current_steps": 29925, "total_steps": 64460, "loss": 0.2233, "lr": 6.474773807798644e-06, "epoch": 9.284827800186163, "percentage": 46.42, "elapsed_time": "0:54:59", "remaining_time": "1:03:27", "throughput": 5532.76, "total_tokens": 18254864} {"current_steps": 29930, "total_steps": 64460, "loss": 0.2336, "lr": 6.4734801750396095e-06, "epoch": 9.286379149860378, "percentage": 46.43, "elapsed_time": "0:54:59", "remaining_time": "1:03:27", "throughput": 5532.61, "total_tokens": 18257040} {"current_steps": 29935, "total_steps": 64460, "loss": 0.2203, "lr": 6.472186434257028e-06, "epoch": 9.287930499534594, "percentage": 46.44, "elapsed_time": "0:55:00", "remaining_time": "1:03:26", "throughput": 5532.47, "total_tokens": 18259728} {"current_steps": 29940, "total_steps": 64460, "loss": 0.2424, "lr": 6.470892585545749e-06, "epoch": 9.289481849208812, "percentage": 46.45, "elapsed_time": "0:55:01", "remaining_time": "1:03:26", "throughput": 5532.7, "total_tokens": 18264144} {"current_steps": 29945, "total_steps": 64460, "loss": 0.2243, "lr": 6.469598629000625e-06, "epoch": 9.291033198883028, "percentage": 46.46, "elapsed_time": "0:55:01", "remaining_time": "1:03:25", "throughput": 5532.8, "total_tokens": 18267408} {"current_steps": 29950, "total_steps": 64460, "loss": 0.2303, "lr": 6.468304564716519e-06, "epoch": 9.292584548557246, "percentage": 46.46, "elapsed_time": "0:55:02", "remaining_time": "1:03:24", "throughput": 5532.82, "total_tokens": 18270192} {"current_steps": 29955, "total_steps": 64460, "loss": 0.2405, "lr": 6.467010392788301e-06, "epoch": 9.294135898231461, "percentage": 46.47, "elapsed_time": "0:55:02", "remaining_time": "1:03:24", "throughput": 5532.87, "total_tokens": 18273456} {"current_steps": 29960, "total_steps": 64460, "loss": 0.2342, "lr": 6.465716113310849e-06, "epoch": 9.295687247905677, "percentage": 46.48, "elapsed_time": "0:55:03", "remaining_time": "1:03:23", "throughput": 5532.8, "total_tokens": 18275792} {"current_steps": 29965, "total_steps": 64460, "loss": 0.2452, "lr": 6.464421726379049e-06, "epoch": 9.297238597579895, "percentage": 46.49, "elapsed_time": "0:55:03", "remaining_time": "1:03:23", "throughput": 5532.9, "total_tokens": 18279152} {"current_steps": 29970, "total_steps": 64460, "loss": 0.2302, "lr": 6.4631272320877955e-06, "epoch": 9.298789947254111, "percentage": 46.49, "elapsed_time": "0:55:04", "remaining_time": "1:03:22", "throughput": 5532.87, "total_tokens": 18281680} {"current_steps": 29975, "total_steps": 64460, "loss": 0.2249, "lr": 6.46183263053199e-06, "epoch": 9.300341296928327, "percentage": 46.5, "elapsed_time": "0:55:04", "remaining_time": "1:03:21", "throughput": 5532.83, "total_tokens": 18284240} {"current_steps": 29980, "total_steps": 64460, "loss": 0.2524, "lr": 6.46053792180654e-06, "epoch": 9.301892646602544, "percentage": 46.51, "elapsed_time": "0:55:05", "remaining_time": "1:03:21", "throughput": 5532.95, "total_tokens": 18288208} {"current_steps": 29985, "total_steps": 64460, "loss": 0.2265, "lr": 6.459243106006367e-06, "epoch": 9.30344399627676, "percentage": 46.52, "elapsed_time": "0:55:05", "remaining_time": "1:03:20", "throughput": 5532.85, "total_tokens": 18290576} {"current_steps": 29990, "total_steps": 64460, "loss": 0.2275, "lr": 6.4579481832263946e-06, "epoch": 9.304995345950978, "percentage": 46.52, "elapsed_time": "0:55:06", "remaining_time": "1:03:20", "throughput": 5533.04, "total_tokens": 18294832} {"current_steps": 29995, "total_steps": 64460, "loss": 0.2334, "lr": 6.456653153561555e-06, "epoch": 9.306546695625194, "percentage": 46.53, "elapsed_time": "0:55:06", "remaining_time": "1:03:19", "throughput": 5533.05, "total_tokens": 18297584} {"current_steps": 30000, "total_steps": 64460, "loss": 0.23, "lr": 6.455358017106789e-06, "epoch": 9.30809804529941, "percentage": 46.54, "elapsed_time": "0:55:07", "remaining_time": "1:03:19", "throughput": 5533.27, "total_tokens": 18301424} {"current_steps": 30005, "total_steps": 64460, "loss": 0.2307, "lr": 6.454062773957048e-06, "epoch": 9.309649394973627, "percentage": 46.55, "elapsed_time": "0:55:08", "remaining_time": "1:03:18", "throughput": 5533.19, "total_tokens": 18303824} {"current_steps": 30010, "total_steps": 64460, "loss": 0.2274, "lr": 6.452767424207287e-06, "epoch": 9.311200744647843, "percentage": 46.56, "elapsed_time": "0:55:08", "remaining_time": "1:03:18", "throughput": 5533.18, "total_tokens": 18306576} {"current_steps": 30015, "total_steps": 64460, "loss": 0.2316, "lr": 6.4514719679524695e-06, "epoch": 9.312752094322061, "percentage": 46.56, "elapsed_time": "0:55:09", "remaining_time": "1:03:17", "throughput": 5533.23, "total_tokens": 18309552} {"current_steps": 30020, "total_steps": 64460, "loss": 0.2289, "lr": 6.450176405287569e-06, "epoch": 9.314303443996277, "percentage": 46.57, "elapsed_time": "0:55:09", "remaining_time": "1:03:16", "throughput": 5533.38, "total_tokens": 18312944} {"current_steps": 30025, "total_steps": 64460, "loss": 0.2336, "lr": 6.448880736307566e-06, "epoch": 9.315854793670493, "percentage": 46.58, "elapsed_time": "0:55:10", "remaining_time": "1:03:16", "throughput": 5533.43, "total_tokens": 18316016} {"current_steps": 30030, "total_steps": 64460, "loss": 0.2267, "lr": 6.447584961107447e-06, "epoch": 9.31740614334471, "percentage": 46.59, "elapsed_time": "0:55:10", "remaining_time": "1:03:15", "throughput": 5533.45, "total_tokens": 18318672} {"current_steps": 30035, "total_steps": 64460, "loss": 0.2289, "lr": 6.446289079782209e-06, "epoch": 9.318957493018926, "percentage": 46.59, "elapsed_time": "0:55:11", "remaining_time": "1:03:14", "throughput": 5533.49, "total_tokens": 18321616} {"current_steps": 30040, "total_steps": 64460, "loss": 0.2218, "lr": 6.444993092426852e-06, "epoch": 9.320508842693144, "percentage": 46.6, "elapsed_time": "0:55:11", "remaining_time": "1:03:14", "throughput": 5533.49, "total_tokens": 18324272} {"current_steps": 30045, "total_steps": 64460, "loss": 0.244, "lr": 6.443696999136393e-06, "epoch": 9.32206019236736, "percentage": 46.61, "elapsed_time": "0:55:12", "remaining_time": "1:03:13", "throughput": 5533.56, "total_tokens": 18327408} {"current_steps": 30050, "total_steps": 64460, "loss": 0.2389, "lr": 6.442400800005848e-06, "epoch": 9.323611542041576, "percentage": 46.62, "elapsed_time": "0:55:12", "remaining_time": "1:03:13", "throughput": 5533.68, "total_tokens": 18330672} {"current_steps": 30055, "total_steps": 64460, "loss": 0.229, "lr": 6.441104495130242e-06, "epoch": 9.325162891715793, "percentage": 46.63, "elapsed_time": "0:55:13", "remaining_time": "1:03:12", "throughput": 5533.67, "total_tokens": 18333584} {"current_steps": 30060, "total_steps": 64460, "loss": 0.2377, "lr": 6.439808084604613e-06, "epoch": 9.32671424139001, "percentage": 46.63, "elapsed_time": "0:55:13", "remaining_time": "1:03:12", "throughput": 5533.77, "total_tokens": 18338064} {"current_steps": 30065, "total_steps": 64460, "loss": 0.2222, "lr": 6.4385115685240016e-06, "epoch": 9.328265591064225, "percentage": 46.64, "elapsed_time": "0:55:14", "remaining_time": "1:03:11", "throughput": 5533.58, "total_tokens": 18340304} {"current_steps": 30070, "total_steps": 64460, "loss": 0.2259, "lr": 6.437214946983457e-06, "epoch": 9.329816940738443, "percentage": 46.65, "elapsed_time": "0:55:14", "remaining_time": "1:03:11", "throughput": 5533.51, "total_tokens": 18342864} {"current_steps": 30075, "total_steps": 64460, "loss": 0.2315, "lr": 6.435918220078038e-06, "epoch": 9.331368290412659, "percentage": 46.66, "elapsed_time": "0:55:15", "remaining_time": "1:03:10", "throughput": 5533.82, "total_tokens": 18348624} {"current_steps": 30080, "total_steps": 64460, "loss": 0.2261, "lr": 6.434621387902808e-06, "epoch": 9.332919640086876, "percentage": 46.66, "elapsed_time": "0:55:16", "remaining_time": "1:03:10", "throughput": 5533.92, "total_tokens": 18351760} {"current_steps": 30085, "total_steps": 64460, "loss": 0.2302, "lr": 6.433324450552845e-06, "epoch": 9.334470989761092, "percentage": 46.67, "elapsed_time": "0:55:16", "remaining_time": "1:03:09", "throughput": 5533.79, "total_tokens": 18354096} {"current_steps": 30090, "total_steps": 64460, "loss": 0.24, "lr": 6.432027408123224e-06, "epoch": 9.336022339435308, "percentage": 46.68, "elapsed_time": "0:55:17", "remaining_time": "1:03:09", "throughput": 5533.9, "total_tokens": 18357392} {"current_steps": 30095, "total_steps": 64460, "loss": 0.232, "lr": 6.430730260709037e-06, "epoch": 9.337573689109526, "percentage": 46.69, "elapsed_time": "0:55:17", "remaining_time": "1:03:08", "throughput": 5533.99, "total_tokens": 18360432} {"current_steps": 30100, "total_steps": 64460, "loss": 0.2192, "lr": 6.429433008405379e-06, "epoch": 9.339125038783742, "percentage": 46.7, "elapsed_time": "0:55:18", "remaining_time": "1:03:07", "throughput": 5534.05, "total_tokens": 18363216} {"current_steps": 30105, "total_steps": 64460, "loss": 0.2349, "lr": 6.4281356513073545e-06, "epoch": 9.340676388457958, "percentage": 46.7, "elapsed_time": "0:55:18", "remaining_time": "1:03:07", "throughput": 5534.02, "total_tokens": 18365840} {"current_steps": 30110, "total_steps": 64460, "loss": 0.2398, "lr": 6.426838189510076e-06, "epoch": 9.342227738132175, "percentage": 46.71, "elapsed_time": "0:55:19", "remaining_time": "1:03:06", "throughput": 5534.02, "total_tokens": 18368816} {"current_steps": 30115, "total_steps": 64460, "loss": 0.2322, "lr": 6.425540623108662e-06, "epoch": 9.343779087806391, "percentage": 46.72, "elapsed_time": "0:55:19", "remaining_time": "1:03:06", "throughput": 5533.86, "total_tokens": 18371024} {"current_steps": 30120, "total_steps": 64460, "loss": 0.215, "lr": 6.424242952198239e-06, "epoch": 9.345330437480609, "percentage": 46.73, "elapsed_time": "0:55:20", "remaining_time": "1:03:05", "throughput": 5533.96, "total_tokens": 18374256} {"current_steps": 30125, "total_steps": 64460, "loss": 0.2422, "lr": 6.422945176873942e-06, "epoch": 9.346881787154825, "percentage": 46.73, "elapsed_time": "0:55:20", "remaining_time": "1:03:04", "throughput": 5534.0, "total_tokens": 18377136} {"current_steps": 30130, "total_steps": 64460, "loss": 0.2312, "lr": 6.421647297230913e-06, "epoch": 9.34843313682904, "percentage": 46.74, "elapsed_time": "0:55:21", "remaining_time": "1:03:04", "throughput": 5534.09, "total_tokens": 18380496} {"current_steps": 30135, "total_steps": 64460, "loss": 0.2265, "lr": 6.420349313364303e-06, "epoch": 9.349984486503258, "percentage": 46.75, "elapsed_time": "0:55:21", "remaining_time": "1:03:03", "throughput": 5534.1, "total_tokens": 18383344} {"current_steps": 30140, "total_steps": 64460, "loss": 0.2359, "lr": 6.419051225369268e-06, "epoch": 9.351535836177474, "percentage": 46.76, "elapsed_time": "0:55:22", "remaining_time": "1:03:03", "throughput": 5533.96, "total_tokens": 18385584} {"current_steps": 30145, "total_steps": 64460, "loss": 0.2375, "lr": 6.417753033340974e-06, "epoch": 9.353087185851692, "percentage": 46.77, "elapsed_time": "0:55:22", "remaining_time": "1:03:02", "throughput": 5534.13, "total_tokens": 18389456} {"current_steps": 30150, "total_steps": 64460, "loss": 0.243, "lr": 6.416454737374595e-06, "epoch": 9.354638535525908, "percentage": 46.77, "elapsed_time": "0:55:23", "remaining_time": "1:03:01", "throughput": 5534.12, "total_tokens": 18392272} {"current_steps": 30155, "total_steps": 64460, "loss": 0.2426, "lr": 6.41515633756531e-06, "epoch": 9.356189885200124, "percentage": 46.78, "elapsed_time": "0:55:24", "remaining_time": "1:03:01", "throughput": 5534.29, "total_tokens": 18396432} {"current_steps": 30160, "total_steps": 64460, "loss": 0.2336, "lr": 6.413857834008307e-06, "epoch": 9.357741234874341, "percentage": 46.79, "elapsed_time": "0:55:24", "remaining_time": "1:03:00", "throughput": 5534.32, "total_tokens": 18399472} {"current_steps": 30165, "total_steps": 64460, "loss": 0.2217, "lr": 6.412559226798782e-06, "epoch": 9.359292584548557, "percentage": 46.8, "elapsed_time": "0:55:25", "remaining_time": "1:03:00", "throughput": 5534.4, "total_tokens": 18402576} {"current_steps": 30170, "total_steps": 64460, "loss": 0.2201, "lr": 6.411260516031939e-06, "epoch": 9.360843934222775, "percentage": 46.8, "elapsed_time": "0:55:25", "remaining_time": "1:02:59", "throughput": 5534.47, "total_tokens": 18405744} {"current_steps": 30175, "total_steps": 64460, "loss": 0.2321, "lr": 6.409961701802988e-06, "epoch": 9.36239528389699, "percentage": 46.81, "elapsed_time": "0:55:26", "remaining_time": "1:02:59", "throughput": 5534.59, "total_tokens": 18409392} {"current_steps": 30180, "total_steps": 64460, "loss": 0.2338, "lr": 6.408662784207149e-06, "epoch": 9.363946633571206, "percentage": 46.82, "elapsed_time": "0:55:26", "remaining_time": "1:02:58", "throughput": 5534.57, "total_tokens": 18412208} {"current_steps": 30185, "total_steps": 64460, "loss": 0.233, "lr": 6.407363763339646e-06, "epoch": 9.365497983245424, "percentage": 46.83, "elapsed_time": "0:55:27", "remaining_time": "1:02:58", "throughput": 5534.55, "total_tokens": 18414768} {"current_steps": 30190, "total_steps": 64460, "loss": 0.2251, "lr": 6.4060646392957124e-06, "epoch": 9.36704933291964, "percentage": 46.84, "elapsed_time": "0:55:27", "remaining_time": "1:02:57", "throughput": 5534.57, "total_tokens": 18417488} {"current_steps": 30195, "total_steps": 64460, "loss": 0.2274, "lr": 6.404765412170593e-06, "epoch": 9.368600682593856, "percentage": 46.84, "elapsed_time": "0:55:28", "remaining_time": "1:02:56", "throughput": 5534.5, "total_tokens": 18420016} {"current_steps": 30200, "total_steps": 64460, "loss": 0.2351, "lr": 6.403466082059533e-06, "epoch": 9.370152032268074, "percentage": 46.85, "elapsed_time": "0:55:28", "remaining_time": "1:02:56", "throughput": 5534.53, "total_tokens": 18423056} {"current_steps": 30205, "total_steps": 64460, "loss": 0.2341, "lr": 6.402166649057788e-06, "epoch": 9.37170338194229, "percentage": 46.86, "elapsed_time": "0:55:29", "remaining_time": "1:02:55", "throughput": 5534.71, "total_tokens": 18426960} {"current_steps": 30210, "total_steps": 64460, "loss": 0.233, "lr": 6.400867113260625e-06, "epoch": 9.373254731616507, "percentage": 46.87, "elapsed_time": "0:55:29", "remaining_time": "1:02:55", "throughput": 5534.83, "total_tokens": 18430352} {"current_steps": 30215, "total_steps": 64460, "loss": 0.2404, "lr": 6.399567474763314e-06, "epoch": 9.374806081290723, "percentage": 46.87, "elapsed_time": "0:55:30", "remaining_time": "1:02:54", "throughput": 5535.13, "total_tokens": 18435152} {"current_steps": 30220, "total_steps": 64460, "loss": 0.2328, "lr": 6.398267733661133e-06, "epoch": 9.376357430964939, "percentage": 46.88, "elapsed_time": "0:55:31", "remaining_time": "1:02:54", "throughput": 5535.04, "total_tokens": 18437456} {"current_steps": 30225, "total_steps": 64460, "loss": 0.2281, "lr": 6.39696789004937e-06, "epoch": 9.377908780639157, "percentage": 46.89, "elapsed_time": "0:55:31", "remaining_time": "1:02:53", "throughput": 5534.91, "total_tokens": 18439600} {"current_steps": 30230, "total_steps": 64460, "loss": 0.2359, "lr": 6.395667944023318e-06, "epoch": 9.379460130313372, "percentage": 46.9, "elapsed_time": "0:55:32", "remaining_time": "1:02:52", "throughput": 5534.8, "total_tokens": 18442000} {"current_steps": 30235, "total_steps": 64460, "loss": 0.2267, "lr": 6.394367895678277e-06, "epoch": 9.381011479987588, "percentage": 46.91, "elapsed_time": "0:55:32", "remaining_time": "1:02:52", "throughput": 5534.88, "total_tokens": 18445360} {"current_steps": 30240, "total_steps": 64460, "loss": 0.2298, "lr": 6.393067745109558e-06, "epoch": 9.382562829661806, "percentage": 46.91, "elapsed_time": "0:55:33", "remaining_time": "1:02:51", "throughput": 5535.03, "total_tokens": 18449136} {"current_steps": 30245, "total_steps": 64460, "loss": 0.2245, "lr": 6.3917674924124785e-06, "epoch": 9.384114179336022, "percentage": 46.92, "elapsed_time": "0:55:33", "remaining_time": "1:02:51", "throughput": 5535.37, "total_tokens": 18454896} {"current_steps": 30250, "total_steps": 64460, "loss": 0.2356, "lr": 6.390467137682359e-06, "epoch": 9.38566552901024, "percentage": 46.93, "elapsed_time": "0:55:34", "remaining_time": "1:02:51", "throughput": 5535.39, "total_tokens": 18458160} {"current_steps": 30255, "total_steps": 64460, "loss": 0.2205, "lr": 6.389166681014534e-06, "epoch": 9.387216878684455, "percentage": 46.94, "elapsed_time": "0:55:35", "remaining_time": "1:02:50", "throughput": 5535.49, "total_tokens": 18461520} {"current_steps": 30260, "total_steps": 64460, "loss": 0.2333, "lr": 6.38786612250434e-06, "epoch": 9.388768228358671, "percentage": 46.94, "elapsed_time": "0:55:35", "remaining_time": "1:02:49", "throughput": 5535.6, "total_tokens": 18464560} {"current_steps": 30265, "total_steps": 64460, "loss": 0.2346, "lr": 6.3865654622471255e-06, "epoch": 9.390319578032889, "percentage": 46.95, "elapsed_time": "0:55:36", "remaining_time": "1:02:49", "throughput": 5535.58, "total_tokens": 18467152} {"current_steps": 30270, "total_steps": 64460, "loss": 0.2261, "lr": 6.385264700338243e-06, "epoch": 9.391870927707105, "percentage": 46.96, "elapsed_time": "0:55:36", "remaining_time": "1:02:48", "throughput": 5535.62, "total_tokens": 18470800} {"current_steps": 30275, "total_steps": 64460, "loss": 0.2356, "lr": 6.383963836873054e-06, "epoch": 9.393422277381323, "percentage": 46.97, "elapsed_time": "0:55:37", "remaining_time": "1:02:48", "throughput": 5535.58, "total_tokens": 18473328} {"current_steps": 30280, "total_steps": 64460, "loss": 0.227, "lr": 6.3826628719469265e-06, "epoch": 9.394973627055538, "percentage": 46.97, "elapsed_time": "0:55:37", "remaining_time": "1:02:47", "throughput": 5535.66, "total_tokens": 18476336} {"current_steps": 30285, "total_steps": 64460, "loss": 0.222, "lr": 6.381361805655237e-06, "epoch": 9.396524976729754, "percentage": 46.98, "elapsed_time": "0:55:38", "remaining_time": "1:02:47", "throughput": 5535.74, "total_tokens": 18479888} {"current_steps": 30290, "total_steps": 64460, "loss": 0.2283, "lr": 6.380060638093371e-06, "epoch": 9.398076326403972, "percentage": 46.99, "elapsed_time": "0:55:38", "remaining_time": "1:02:46", "throughput": 5535.91, "total_tokens": 18483664} {"current_steps": 30295, "total_steps": 64460, "loss": 0.237, "lr": 6.378759369356716e-06, "epoch": 9.399627676078188, "percentage": 47.0, "elapsed_time": "0:55:39", "remaining_time": "1:02:45", "throughput": 5535.93, "total_tokens": 18486512} {"current_steps": 30300, "total_steps": 64460, "loss": 0.2292, "lr": 6.377457999540672e-06, "epoch": 9.401179025752405, "percentage": 47.01, "elapsed_time": "0:55:39", "remaining_time": "1:02:45", "throughput": 5536.03, "total_tokens": 18489648} {"current_steps": 30305, "total_steps": 64460, "loss": 0.2429, "lr": 6.376156528740648e-06, "epoch": 9.402730375426621, "percentage": 47.01, "elapsed_time": "0:55:40", "remaining_time": "1:02:44", "throughput": 5536.1, "total_tokens": 18492880} {"current_steps": 30310, "total_steps": 64460, "loss": 0.2314, "lr": 6.3748549570520524e-06, "epoch": 9.404281725100837, "percentage": 47.02, "elapsed_time": "0:55:40", "remaining_time": "1:02:44", "throughput": 5536.15, "total_tokens": 18495824} {"current_steps": 30315, "total_steps": 64460, "loss": 0.2325, "lr": 6.373553284570309e-06, "epoch": 9.405833074775055, "percentage": 47.03, "elapsed_time": "0:55:41", "remaining_time": "1:02:43", "throughput": 5536.15, "total_tokens": 18498416} {"current_steps": 30320, "total_steps": 64460, "loss": 0.2216, "lr": 6.372251511390842e-06, "epoch": 9.40738442444927, "percentage": 47.04, "elapsed_time": "0:55:41", "remaining_time": "1:02:42", "throughput": 5536.24, "total_tokens": 18501680} {"current_steps": 30325, "total_steps": 64460, "loss": 0.2294, "lr": 6.370949637609092e-06, "epoch": 9.408935774123487, "percentage": 47.04, "elapsed_time": "0:55:42", "remaining_time": "1:02:42", "throughput": 5536.13, "total_tokens": 18504048} {"current_steps": 30330, "total_steps": 64460, "loss": 0.22, "lr": 6.3696476633204975e-06, "epoch": 9.410487123797704, "percentage": 47.05, "elapsed_time": "0:55:42", "remaining_time": "1:02:41", "throughput": 5536.12, "total_tokens": 18506832} {"current_steps": 30335, "total_steps": 64460, "loss": 0.2406, "lr": 6.36834558862051e-06, "epoch": 9.41203847347192, "percentage": 47.06, "elapsed_time": "0:55:43", "remaining_time": "1:02:41", "throughput": 5536.14, "total_tokens": 18509584} {"current_steps": 30340, "total_steps": 64460, "loss": 0.2243, "lr": 6.3670434136045876e-06, "epoch": 9.413589823146138, "percentage": 47.07, "elapsed_time": "0:55:43", "remaining_time": "1:02:40", "throughput": 5536.25, "total_tokens": 18512848} {"current_steps": 30345, "total_steps": 64460, "loss": 0.2302, "lr": 6.365741138368196e-06, "epoch": 9.415141172820354, "percentage": 47.08, "elapsed_time": "0:55:44", "remaining_time": "1:02:39", "throughput": 5536.23, "total_tokens": 18515504} {"current_steps": 30350, "total_steps": 64460, "loss": 0.2212, "lr": 6.364438763006805e-06, "epoch": 9.41669252249457, "percentage": 47.08, "elapsed_time": "0:55:44", "remaining_time": "1:02:39", "throughput": 5536.31, "total_tokens": 18518832} {"current_steps": 30355, "total_steps": 64460, "loss": 0.2335, "lr": 6.363136287615894e-06, "epoch": 9.418243872168787, "percentage": 47.09, "elapsed_time": "0:55:45", "remaining_time": "1:02:38", "throughput": 5536.31, "total_tokens": 18521552} {"current_steps": 30360, "total_steps": 64460, "loss": 0.2239, "lr": 6.361833712290953e-06, "epoch": 9.419795221843003, "percentage": 47.1, "elapsed_time": "0:55:46", "remaining_time": "1:02:38", "throughput": 5536.38, "total_tokens": 18524784} {"current_steps": 30365, "total_steps": 64460, "loss": 0.2317, "lr": 6.360531037127474e-06, "epoch": 9.421346571517219, "percentage": 47.11, "elapsed_time": "0:55:46", "remaining_time": "1:02:37", "throughput": 5536.36, "total_tokens": 18528400} {"current_steps": 30370, "total_steps": 64460, "loss": 0.2274, "lr": 6.359228262220959e-06, "epoch": 9.422897921191437, "percentage": 47.11, "elapsed_time": "0:55:47", "remaining_time": "1:02:37", "throughput": 5536.13, "total_tokens": 18530704} {"current_steps": 30375, "total_steps": 64460, "loss": 0.2333, "lr": 6.357925387666917e-06, "epoch": 9.424449270865653, "percentage": 47.12, "elapsed_time": "0:55:47", "remaining_time": "1:02:36", "throughput": 5536.12, "total_tokens": 18534224} {"current_steps": 30380, "total_steps": 64460, "loss": 0.2241, "lr": 6.356622413560863e-06, "epoch": 9.42600062053987, "percentage": 47.13, "elapsed_time": "0:55:48", "remaining_time": "1:02:36", "throughput": 5536.17, "total_tokens": 18537136} {"current_steps": 30385, "total_steps": 64460, "loss": 0.2337, "lr": 6.355319339998322e-06, "epoch": 9.427551970214086, "percentage": 47.14, "elapsed_time": "0:55:48", "remaining_time": "1:02:35", "throughput": 5536.37, "total_tokens": 18540720} {"current_steps": 30390, "total_steps": 64460, "loss": 0.2302, "lr": 6.354016167074824e-06, "epoch": 9.429103319888302, "percentage": 47.15, "elapsed_time": "0:55:49", "remaining_time": "1:02:34", "throughput": 5536.24, "total_tokens": 18542928} {"current_steps": 30395, "total_steps": 64460, "loss": 0.2265, "lr": 6.352712894885906e-06, "epoch": 9.43065466956252, "percentage": 47.15, "elapsed_time": "0:55:49", "remaining_time": "1:02:34", "throughput": 5536.1, "total_tokens": 18545264} {"current_steps": 30400, "total_steps": 64460, "loss": 0.2338, "lr": 6.351409523527115e-06, "epoch": 9.432206019236736, "percentage": 47.16, "elapsed_time": "0:55:50", "remaining_time": "1:02:33", "throughput": 5536.25, "total_tokens": 18549232} {"current_steps": 30405, "total_steps": 64460, "loss": 0.2338, "lr": 6.350106053094004e-06, "epoch": 9.433757368910953, "percentage": 47.17, "elapsed_time": "0:55:50", "remaining_time": "1:02:33", "throughput": 5536.35, "total_tokens": 18552272} {"current_steps": 30410, "total_steps": 64460, "loss": 0.2334, "lr": 6.348802483682131e-06, "epoch": 9.43530871858517, "percentage": 47.18, "elapsed_time": "0:55:51", "remaining_time": "1:02:32", "throughput": 5536.44, "total_tokens": 18555344} {"current_steps": 30415, "total_steps": 64460, "loss": 0.2296, "lr": 6.347498815387061e-06, "epoch": 9.436860068259385, "percentage": 47.18, "elapsed_time": "0:55:51", "remaining_time": "1:02:32", "throughput": 5536.55, "total_tokens": 18558448} {"current_steps": 30420, "total_steps": 64460, "loss": 0.2259, "lr": 6.346195048304373e-06, "epoch": 9.438411417933603, "percentage": 47.19, "elapsed_time": "0:55:52", "remaining_time": "1:02:31", "throughput": 5536.72, "total_tokens": 18561904} {"current_steps": 30425, "total_steps": 64460, "loss": 0.2303, "lr": 6.344891182529648e-06, "epoch": 9.439962767607819, "percentage": 47.2, "elapsed_time": "0:55:53", "remaining_time": "1:02:31", "throughput": 5536.97, "total_tokens": 18566576} {"current_steps": 30430, "total_steps": 64460, "loss": 0.2333, "lr": 6.343587218158472e-06, "epoch": 9.441514117282036, "percentage": 47.21, "elapsed_time": "0:55:53", "remaining_time": "1:02:30", "throughput": 5537.05, "total_tokens": 18569680} {"current_steps": 30435, "total_steps": 64460, "loss": 0.2236, "lr": 6.342283155286443e-06, "epoch": 9.443065466956252, "percentage": 47.22, "elapsed_time": "0:55:54", "remaining_time": "1:02:29", "throughput": 5537.07, "total_tokens": 18572272} {"current_steps": 30440, "total_steps": 64460, "loss": 0.2272, "lr": 6.340978994009164e-06, "epoch": 9.444616816630468, "percentage": 47.22, "elapsed_time": "0:55:54", "remaining_time": "1:02:29", "throughput": 5537.11, "total_tokens": 18575408} {"current_steps": 30445, "total_steps": 64460, "loss": 0.2256, "lr": 6.339674734422244e-06, "epoch": 9.446168166304686, "percentage": 47.23, "elapsed_time": "0:55:55", "remaining_time": "1:02:28", "throughput": 5537.31, "total_tokens": 18579600} {"current_steps": 30450, "total_steps": 64460, "loss": 0.2318, "lr": 6.338370376621303e-06, "epoch": 9.447719515978902, "percentage": 47.24, "elapsed_time": "0:55:55", "remaining_time": "1:02:28", "throughput": 5537.33, "total_tokens": 18582320} {"current_steps": 30455, "total_steps": 64460, "loss": 0.2235, "lr": 6.337065920701963e-06, "epoch": 9.449270865653117, "percentage": 47.25, "elapsed_time": "0:55:56", "remaining_time": "1:02:27", "throughput": 5537.38, "total_tokens": 18585296} {"current_steps": 30460, "total_steps": 64460, "loss": 0.2175, "lr": 6.335761366759859e-06, "epoch": 9.450822215327335, "percentage": 47.25, "elapsed_time": "0:55:56", "remaining_time": "1:02:26", "throughput": 5537.22, "total_tokens": 18587472} {"current_steps": 30465, "total_steps": 64460, "loss": 0.2233, "lr": 6.3344567148906284e-06, "epoch": 9.452373565001551, "percentage": 47.26, "elapsed_time": "0:55:57", "remaining_time": "1:02:26", "throughput": 5537.29, "total_tokens": 18591696} {"current_steps": 30470, "total_steps": 64460, "loss": 0.2262, "lr": 6.33315196518992e-06, "epoch": 9.453924914675769, "percentage": 47.27, "elapsed_time": "0:55:58", "remaining_time": "1:02:25", "throughput": 5537.36, "total_tokens": 18594608} {"current_steps": 30475, "total_steps": 64460, "loss": 0.2342, "lr": 6.331847117753385e-06, "epoch": 9.455476264349985, "percentage": 47.28, "elapsed_time": "0:55:58", "remaining_time": "1:02:25", "throughput": 5537.37, "total_tokens": 18597424} {"current_steps": 30480, "total_steps": 64460, "loss": 0.2357, "lr": 6.3305421726766835e-06, "epoch": 9.4570276140242, "percentage": 47.29, "elapsed_time": "0:55:59", "remaining_time": "1:02:24", "throughput": 5537.25, "total_tokens": 18600016} {"current_steps": 30485, "total_steps": 64460, "loss": 0.2247, "lr": 6.329237130055487e-06, "epoch": 9.458578963698418, "percentage": 47.29, "elapsed_time": "0:55:59", "remaining_time": "1:02:24", "throughput": 5537.29, "total_tokens": 18602832} {"current_steps": 30490, "total_steps": 64460, "loss": 0.2263, "lr": 6.327931989985465e-06, "epoch": 9.460130313372634, "percentage": 47.3, "elapsed_time": "0:56:00", "remaining_time": "1:02:23", "throughput": 5537.41, "total_tokens": 18606288} {"current_steps": 30495, "total_steps": 64460, "loss": 0.2302, "lr": 6.3266267525623055e-06, "epoch": 9.46168166304685, "percentage": 47.31, "elapsed_time": "0:56:00", "remaining_time": "1:02:22", "throughput": 5537.41, "total_tokens": 18608912} {"current_steps": 30500, "total_steps": 64460, "loss": 0.2281, "lr": 6.3253214178816955e-06, "epoch": 9.463233012721068, "percentage": 47.32, "elapsed_time": "0:56:01", "remaining_time": "1:02:22", "throughput": 5537.52, "total_tokens": 18612656} {"current_steps": 30505, "total_steps": 64460, "loss": 0.2263, "lr": 6.324015986039331e-06, "epoch": 9.464784362395283, "percentage": 47.32, "elapsed_time": "0:56:01", "remaining_time": "1:02:21", "throughput": 5537.41, "total_tokens": 18614864} {"current_steps": 30510, "total_steps": 64460, "loss": 0.2295, "lr": 6.322710457130916e-06, "epoch": 9.466335712069501, "percentage": 47.33, "elapsed_time": "0:56:02", "remaining_time": "1:02:21", "throughput": 5537.38, "total_tokens": 18617968} {"current_steps": 30515, "total_steps": 64460, "loss": 0.2285, "lr": 6.3214048312521604e-06, "epoch": 9.467887061743717, "percentage": 47.34, "elapsed_time": "0:56:02", "remaining_time": "1:02:20", "throughput": 5537.18, "total_tokens": 18620176} {"current_steps": 30520, "total_steps": 64460, "loss": 0.2315, "lr": 6.320099108498785e-06, "epoch": 9.469438411417933, "percentage": 47.35, "elapsed_time": "0:56:03", "remaining_time": "1:02:20", "throughput": 5537.08, "total_tokens": 18622640} {"current_steps": 30525, "total_steps": 64460, "loss": 0.2213, "lr": 6.31879328896651e-06, "epoch": 9.47098976109215, "percentage": 47.35, "elapsed_time": "0:56:03", "remaining_time": "1:02:19", "throughput": 5536.96, "total_tokens": 18625072} {"current_steps": 30530, "total_steps": 64460, "loss": 0.2276, "lr": 6.317487372751072e-06, "epoch": 9.472541110766366, "percentage": 47.36, "elapsed_time": "0:56:04", "remaining_time": "1:02:18", "throughput": 5536.97, "total_tokens": 18627760} {"current_steps": 30535, "total_steps": 64460, "loss": 0.2296, "lr": 6.316181359948208e-06, "epoch": 9.474092460440584, "percentage": 47.37, "elapsed_time": "0:56:04", "remaining_time": "1:02:18", "throughput": 5536.94, "total_tokens": 18630384} {"current_steps": 30540, "total_steps": 64460, "loss": 0.2293, "lr": 6.314875250653665e-06, "epoch": 9.4756438101148, "percentage": 47.38, "elapsed_time": "0:56:05", "remaining_time": "1:02:17", "throughput": 5536.94, "total_tokens": 18633456} {"current_steps": 30545, "total_steps": 64460, "loss": 0.2303, "lr": 6.313569044963193e-06, "epoch": 9.477195159789016, "percentage": 47.39, "elapsed_time": "0:56:05", "remaining_time": "1:02:17", "throughput": 5536.98, "total_tokens": 18636368} {"current_steps": 30550, "total_steps": 64460, "loss": 0.2383, "lr": 6.312262742972557e-06, "epoch": 9.478746509463233, "percentage": 47.39, "elapsed_time": "0:56:06", "remaining_time": "1:02:16", "throughput": 5537.13, "total_tokens": 18639984} {"current_steps": 30555, "total_steps": 64460, "loss": 0.2291, "lr": 6.3109563447775214e-06, "epoch": 9.48029785913745, "percentage": 47.4, "elapsed_time": "0:56:06", "remaining_time": "1:02:15", "throughput": 5537.03, "total_tokens": 18642224} {"current_steps": 30560, "total_steps": 64460, "loss": 0.2129, "lr": 6.309649850473862e-06, "epoch": 9.481849208811667, "percentage": 47.41, "elapsed_time": "0:56:07", "remaining_time": "1:02:15", "throughput": 5537.02, "total_tokens": 18645040} {"current_steps": 30565, "total_steps": 64460, "loss": 0.2338, "lr": 6.308343260157361e-06, "epoch": 9.483400558485883, "percentage": 47.42, "elapsed_time": "0:56:07", "remaining_time": "1:02:14", "throughput": 5537.0, "total_tokens": 18647664} {"current_steps": 30570, "total_steps": 64460, "loss": 0.2441, "lr": 6.307036573923806e-06, "epoch": 9.484951908160099, "percentage": 47.42, "elapsed_time": "0:56:08", "remaining_time": "1:02:14", "throughput": 5537.07, "total_tokens": 18650512} {"current_steps": 30575, "total_steps": 64460, "loss": 0.2354, "lr": 6.305729791868992e-06, "epoch": 9.486503257834316, "percentage": 47.43, "elapsed_time": "0:56:08", "remaining_time": "1:02:13", "throughput": 5536.95, "total_tokens": 18652720} {"current_steps": 30580, "total_steps": 64460, "loss": 0.2266, "lr": 6.304422914088722e-06, "epoch": 9.488054607508532, "percentage": 47.44, "elapsed_time": "0:56:09", "remaining_time": "1:02:12", "throughput": 5536.96, "total_tokens": 18655696} {"current_steps": 30585, "total_steps": 64460, "loss": 0.2344, "lr": 6.303115940678806e-06, "epoch": 9.489605957182748, "percentage": 47.45, "elapsed_time": "0:56:09", "remaining_time": "1:02:12", "throughput": 5537.15, "total_tokens": 18660016} {"current_steps": 30590, "total_steps": 64460, "loss": 0.2335, "lr": 6.30180887173506e-06, "epoch": 9.491157306856966, "percentage": 47.46, "elapsed_time": "0:56:10", "remaining_time": "1:02:11", "throughput": 5537.12, "total_tokens": 18662800} {"current_steps": 30595, "total_steps": 64460, "loss": 0.2239, "lr": 6.300501707353308e-06, "epoch": 9.492708656531182, "percentage": 47.46, "elapsed_time": "0:56:11", "remaining_time": "1:02:11", "throughput": 5537.16, "total_tokens": 18665808} {"current_steps": 30600, "total_steps": 64460, "loss": 0.2277, "lr": 6.29919444762938e-06, "epoch": 9.4942600062054, "percentage": 47.47, "elapsed_time": "0:56:11", "remaining_time": "1:02:10", "throughput": 5537.21, "total_tokens": 18668688} {"current_steps": 30605, "total_steps": 64460, "loss": 0.2263, "lr": 6.297887092659115e-06, "epoch": 9.495811355879615, "percentage": 47.48, "elapsed_time": "0:56:12", "remaining_time": "1:02:10", "throughput": 5537.26, "total_tokens": 18671696} {"current_steps": 30610, "total_steps": 64460, "loss": 0.2331, "lr": 6.296579642538356e-06, "epoch": 9.497362705553831, "percentage": 47.49, "elapsed_time": "0:56:12", "remaining_time": "1:02:09", "throughput": 5537.08, "total_tokens": 18673904} {"current_steps": 30615, "total_steps": 64460, "loss": 0.2348, "lr": 6.295272097362956e-06, "epoch": 9.498914055228049, "percentage": 47.49, "elapsed_time": "0:56:13", "remaining_time": "1:02:08", "throughput": 5537.07, "total_tokens": 18676656} {"current_steps": 30620, "total_steps": 64460, "loss": 0.2311, "lr": 6.293964457228773e-06, "epoch": 9.500465404902265, "percentage": 47.5, "elapsed_time": "0:56:13", "remaining_time": "1:02:08", "throughput": 5537.1, "total_tokens": 18679600} {"current_steps": 30625, "total_steps": 64460, "loss": 0.2234, "lr": 6.292656722231672e-06, "epoch": 9.50201675457648, "percentage": 47.51, "elapsed_time": "0:56:14", "remaining_time": "1:02:07", "throughput": 5537.21, "total_tokens": 18683120} {"current_steps": 30630, "total_steps": 64460, "loss": 0.2356, "lr": 6.291348892467527e-06, "epoch": 9.503568104250698, "percentage": 47.52, "elapsed_time": "0:56:14", "remaining_time": "1:02:07", "throughput": 5537.21, "total_tokens": 18686000} {"current_steps": 30635, "total_steps": 64460, "loss": 0.2236, "lr": 6.290040968032216e-06, "epoch": 9.505119453924914, "percentage": 47.53, "elapsed_time": "0:56:15", "remaining_time": "1:02:06", "throughput": 5537.29, "total_tokens": 18688944} {"current_steps": 30640, "total_steps": 64460, "loss": 0.2298, "lr": 6.288732949021625e-06, "epoch": 9.506670803599132, "percentage": 47.53, "elapsed_time": "0:56:15", "remaining_time": "1:02:06", "throughput": 5537.39, "total_tokens": 18692304} {"current_steps": 30645, "total_steps": 64460, "loss": 0.2207, "lr": 6.287424835531648e-06, "epoch": 9.508222153273348, "percentage": 47.54, "elapsed_time": "0:56:16", "remaining_time": "1:02:05", "throughput": 5537.38, "total_tokens": 18695792} {"current_steps": 30650, "total_steps": 64460, "loss": 0.2291, "lr": 6.286116627658185e-06, "epoch": 9.509773502947564, "percentage": 47.55, "elapsed_time": "0:56:16", "remaining_time": "1:02:04", "throughput": 5537.41, "total_tokens": 18698896} {"current_steps": 30655, "total_steps": 64460, "loss": 0.2366, "lr": 6.284808325497145e-06, "epoch": 9.511324852621781, "percentage": 47.56, "elapsed_time": "0:56:17", "remaining_time": "1:02:04", "throughput": 5537.24, "total_tokens": 18701296} {"current_steps": 30660, "total_steps": 64460, "loss": 0.2371, "lr": 6.283499929144439e-06, "epoch": 9.512876202295997, "percentage": 47.56, "elapsed_time": "0:56:17", "remaining_time": "1:02:03", "throughput": 5537.2, "total_tokens": 18703888} {"current_steps": 30665, "total_steps": 64460, "loss": 0.2391, "lr": 6.2821914386959894e-06, "epoch": 9.514427551970215, "percentage": 47.57, "elapsed_time": "0:56:18", "remaining_time": "1:02:03", "throughput": 5537.27, "total_tokens": 18706800} {"current_steps": 30670, "total_steps": 64460, "loss": 0.2343, "lr": 6.2808828542477225e-06, "epoch": 9.51597890164443, "percentage": 47.58, "elapsed_time": "0:56:18", "remaining_time": "1:02:02", "throughput": 5537.29, "total_tokens": 18709776} {"current_steps": 30675, "total_steps": 64460, "loss": 0.2274, "lr": 6.279574175895576e-06, "epoch": 9.517530251318647, "percentage": 47.59, "elapsed_time": "0:56:19", "remaining_time": "1:02:01", "throughput": 5537.36, "total_tokens": 18712784} {"current_steps": 30680, "total_steps": 64460, "loss": 0.2315, "lr": 6.278265403735491e-06, "epoch": 9.519081600992864, "percentage": 47.6, "elapsed_time": "0:56:19", "remaining_time": "1:02:01", "throughput": 5537.44, "total_tokens": 18715920} {"current_steps": 30685, "total_steps": 64460, "loss": 0.221, "lr": 6.276956537863413e-06, "epoch": 9.52063295066708, "percentage": 47.6, "elapsed_time": "0:56:20", "remaining_time": "1:02:00", "throughput": 5537.35, "total_tokens": 18718448} {"current_steps": 30690, "total_steps": 64460, "loss": 0.2251, "lr": 6.2756475783753e-06, "epoch": 9.522184300341298, "percentage": 47.61, "elapsed_time": "0:56:20", "remaining_time": "1:02:00", "throughput": 5537.54, "total_tokens": 18722128} {"current_steps": 30695, "total_steps": 64460, "loss": 0.2185, "lr": 6.274338525367114e-06, "epoch": 9.523735650015514, "percentage": 47.62, "elapsed_time": "0:56:21", "remaining_time": "1:01:59", "throughput": 5537.7, "total_tokens": 18725776} {"current_steps": 30700, "total_steps": 64460, "loss": 0.2361, "lr": 6.273029378934824e-06, "epoch": 9.52528699968973, "percentage": 47.63, "elapsed_time": "0:56:21", "remaining_time": "1:01:59", "throughput": 5537.7, "total_tokens": 18728368} {"current_steps": 30705, "total_steps": 64460, "loss": 0.225, "lr": 6.271720139174404e-06, "epoch": 9.526838349363947, "percentage": 47.63, "elapsed_time": "0:56:22", "remaining_time": "1:01:58", "throughput": 5537.75, "total_tokens": 18731216} {"current_steps": 30710, "total_steps": 64460, "loss": 0.2276, "lr": 6.27041080618184e-06, "epoch": 9.528389699038163, "percentage": 47.64, "elapsed_time": "0:56:22", "remaining_time": "1:01:57", "throughput": 5537.89, "total_tokens": 18734672} {"current_steps": 30715, "total_steps": 64460, "loss": 0.233, "lr": 6.26910138005312e-06, "epoch": 9.529941048712379, "percentage": 47.65, "elapsed_time": "0:56:23", "remaining_time": "1:01:57", "throughput": 5537.79, "total_tokens": 18736944} {"current_steps": 30720, "total_steps": 64460, "loss": 0.2167, "lr": 6.267791860884241e-06, "epoch": 9.531492398386597, "percentage": 47.66, "elapsed_time": "0:56:23", "remaining_time": "1:01:56", "throughput": 5537.79, "total_tokens": 18739600} {"current_steps": 30725, "total_steps": 64460, "loss": 0.2248, "lr": 6.266482248771203e-06, "epoch": 9.533043748060813, "percentage": 47.67, "elapsed_time": "0:56:24", "remaining_time": "1:01:55", "throughput": 5537.71, "total_tokens": 18741968} {"current_steps": 30730, "total_steps": 64460, "loss": 0.2314, "lr": 6.26517254381002e-06, "epoch": 9.53459509773503, "percentage": 47.67, "elapsed_time": "0:56:24", "remaining_time": "1:01:55", "throughput": 5537.88, "total_tokens": 18745520} {"current_steps": 30735, "total_steps": 64460, "loss": 0.2395, "lr": 6.263862746096707e-06, "epoch": 9.536146447409246, "percentage": 47.68, "elapsed_time": "0:56:25", "remaining_time": "1:01:54", "throughput": 5537.82, "total_tokens": 18747920} {"current_steps": 30740, "total_steps": 64460, "loss": 0.2177, "lr": 6.262552855727289e-06, "epoch": 9.537697797083462, "percentage": 47.69, "elapsed_time": "0:56:25", "remaining_time": "1:01:54", "throughput": 5537.77, "total_tokens": 18750736} {"current_steps": 30745, "total_steps": 64460, "loss": 0.2243, "lr": 6.261242872797796e-06, "epoch": 9.53924914675768, "percentage": 47.7, "elapsed_time": "0:56:26", "remaining_time": "1:01:53", "throughput": 5537.78, "total_tokens": 18753552} {"current_steps": 30750, "total_steps": 64460, "loss": 0.2265, "lr": 6.259932797404265e-06, "epoch": 9.540800496431896, "percentage": 47.7, "elapsed_time": "0:56:27", "remaining_time": "1:01:53", "throughput": 5537.81, "total_tokens": 18756656} {"current_steps": 30755, "total_steps": 64460, "loss": 0.2258, "lr": 6.258622629642741e-06, "epoch": 9.542351846106111, "percentage": 47.71, "elapsed_time": "0:56:27", "remaining_time": "1:01:52", "throughput": 5537.82, "total_tokens": 18759280} {"current_steps": 30760, "total_steps": 64460, "loss": 0.2268, "lr": 6.257312369609273e-06, "epoch": 9.543903195780329, "percentage": 47.72, "elapsed_time": "0:56:28", "remaining_time": "1:01:51", "throughput": 5537.92, "total_tokens": 18762736} {"current_steps": 30765, "total_steps": 64460, "loss": 0.2262, "lr": 6.256002017399921e-06, "epoch": 9.545454545454545, "percentage": 47.73, "elapsed_time": "0:56:28", "remaining_time": "1:01:51", "throughput": 5537.96, "total_tokens": 18765424} {"current_steps": 30770, "total_steps": 64460, "loss": 0.2384, "lr": 6.254691573110745e-06, "epoch": 9.547005895128763, "percentage": 47.74, "elapsed_time": "0:56:29", "remaining_time": "1:01:50", "throughput": 5538.02, "total_tokens": 18768368} {"current_steps": 30775, "total_steps": 64460, "loss": 0.2185, "lr": 6.253381036837821e-06, "epoch": 9.548557244802979, "percentage": 47.74, "elapsed_time": "0:56:29", "remaining_time": "1:01:50", "throughput": 5538.06, "total_tokens": 18771312} {"current_steps": 30780, "total_steps": 64460, "loss": 0.2189, "lr": 6.252070408677224e-06, "epoch": 9.550108594477194, "percentage": 47.75, "elapsed_time": "0:56:30", "remaining_time": "1:01:49", "throughput": 5538.11, "total_tokens": 18774224} {"current_steps": 30785, "total_steps": 64460, "loss": 0.2249, "lr": 6.25075968872504e-06, "epoch": 9.551659944151412, "percentage": 47.76, "elapsed_time": "0:56:30", "remaining_time": "1:01:48", "throughput": 5538.03, "total_tokens": 18776624} {"current_steps": 30790, "total_steps": 64460, "loss": 0.2227, "lr": 6.249448877077359e-06, "epoch": 9.553211293825628, "percentage": 47.77, "elapsed_time": "0:56:31", "remaining_time": "1:01:48", "throughput": 5538.08, "total_tokens": 18779728} {"current_steps": 30795, "total_steps": 64460, "loss": 0.2404, "lr": 6.2481379738302794e-06, "epoch": 9.554762643499846, "percentage": 47.77, "elapsed_time": "0:56:31", "remaining_time": "1:01:47", "throughput": 5538.08, "total_tokens": 18782256} {"current_steps": 30800, "total_steps": 64460, "loss": 0.2325, "lr": 6.246826979079907e-06, "epoch": 9.556313993174061, "percentage": 47.78, "elapsed_time": "0:56:31", "remaining_time": "1:01:46", "throughput": 5538.08, "total_tokens": 18784784} {"current_steps": 30805, "total_steps": 64460, "loss": 0.2259, "lr": 6.245515892922351e-06, "epoch": 9.557865342848277, "percentage": 47.79, "elapsed_time": "0:56:32", "remaining_time": "1:01:46", "throughput": 5538.15, "total_tokens": 18787856} {"current_steps": 30810, "total_steps": 64460, "loss": 0.2345, "lr": 6.244204715453732e-06, "epoch": 9.559416692522495, "percentage": 47.8, "elapsed_time": "0:56:32", "remaining_time": "1:01:45", "throughput": 5538.14, "total_tokens": 18790416} {"current_steps": 30815, "total_steps": 64460, "loss": 0.2156, "lr": 6.242893446770173e-06, "epoch": 9.560968042196711, "percentage": 47.8, "elapsed_time": "0:56:33", "remaining_time": "1:01:45", "throughput": 5538.2, "total_tokens": 18793296} {"current_steps": 30820, "total_steps": 64460, "loss": 0.2289, "lr": 6.241582086967808e-06, "epoch": 9.562519391870929, "percentage": 47.81, "elapsed_time": "0:56:33", "remaining_time": "1:01:44", "throughput": 5538.26, "total_tokens": 18796112} {"current_steps": 30825, "total_steps": 64460, "loss": 0.2431, "lr": 6.2402706361427725e-06, "epoch": 9.564070741545144, "percentage": 47.82, "elapsed_time": "0:56:34", "remaining_time": "1:01:43", "throughput": 5538.4, "total_tokens": 18799344} {"current_steps": 30830, "total_steps": 64460, "loss": 0.2199, "lr": 6.2389590943912114e-06, "epoch": 9.56562209121936, "percentage": 47.83, "elapsed_time": "0:56:34", "remaining_time": "1:01:43", "throughput": 5538.4, "total_tokens": 18801968} {"current_steps": 30835, "total_steps": 64460, "loss": 0.2283, "lr": 6.2376474618092785e-06, "epoch": 9.567173440893578, "percentage": 47.84, "elapsed_time": "0:56:35", "remaining_time": "1:01:42", "throughput": 5538.48, "total_tokens": 18804880} {"current_steps": 30840, "total_steps": 64460, "loss": 0.2203, "lr": 6.23633573849313e-06, "epoch": 9.568724790567794, "percentage": 47.84, "elapsed_time": "0:56:35", "remaining_time": "1:01:41", "throughput": 5538.53, "total_tokens": 18808144} {"current_steps": 30845, "total_steps": 64460, "loss": 0.2412, "lr": 6.235023924538932e-06, "epoch": 9.57027614024201, "percentage": 47.85, "elapsed_time": "0:56:36", "remaining_time": "1:01:41", "throughput": 5538.63, "total_tokens": 18811184} {"current_steps": 30850, "total_steps": 64460, "loss": 0.2303, "lr": 6.233712020042856e-06, "epoch": 9.571827489916227, "percentage": 47.86, "elapsed_time": "0:56:36", "remaining_time": "1:01:40", "throughput": 5538.86, "total_tokens": 18815280} {"current_steps": 30855, "total_steps": 64460, "loss": 0.245, "lr": 6.232400025101078e-06, "epoch": 9.573378839590443, "percentage": 47.87, "elapsed_time": "0:56:37", "remaining_time": "1:01:40", "throughput": 5538.94, "total_tokens": 18818544} {"current_steps": 30860, "total_steps": 64460, "loss": 0.2408, "lr": 6.2310879398097854e-06, "epoch": 9.574930189264661, "percentage": 47.87, "elapsed_time": "0:56:37", "remaining_time": "1:01:39", "throughput": 5539.07, "total_tokens": 18821616} {"current_steps": 30865, "total_steps": 64460, "loss": 0.2243, "lr": 6.229775764265167e-06, "epoch": 9.576481538938877, "percentage": 47.88, "elapsed_time": "0:56:38", "remaining_time": "1:01:39", "throughput": 5539.12, "total_tokens": 18824624} {"current_steps": 30870, "total_steps": 64460, "loss": 0.2199, "lr": 6.228463498563424e-06, "epoch": 9.578032888613093, "percentage": 47.89, "elapsed_time": "0:56:38", "remaining_time": "1:01:38", "throughput": 5539.2, "total_tokens": 18827536} {"current_steps": 30875, "total_steps": 64460, "loss": 0.231, "lr": 6.227151142800759e-06, "epoch": 9.57958423828731, "percentage": 47.9, "elapsed_time": "0:56:39", "remaining_time": "1:01:37", "throughput": 5539.3, "total_tokens": 18830672} {"current_steps": 30880, "total_steps": 64460, "loss": 0.2243, "lr": 6.225838697073384e-06, "epoch": 9.581135587961526, "percentage": 47.91, "elapsed_time": "0:56:39", "remaining_time": "1:01:37", "throughput": 5539.31, "total_tokens": 18833552} {"current_steps": 30885, "total_steps": 64460, "loss": 0.2237, "lr": 6.2245261614775155e-06, "epoch": 9.582686937635742, "percentage": 47.91, "elapsed_time": "0:56:40", "remaining_time": "1:01:36", "throughput": 5539.36, "total_tokens": 18837232} {"current_steps": 30890, "total_steps": 64460, "loss": 0.2337, "lr": 6.223213536109381e-06, "epoch": 9.58423828730996, "percentage": 47.92, "elapsed_time": "0:56:41", "remaining_time": "1:01:36", "throughput": 5539.54, "total_tokens": 18840752} {"current_steps": 30895, "total_steps": 64460, "loss": 0.2197, "lr": 6.221900821065206e-06, "epoch": 9.585789636984176, "percentage": 47.93, "elapsed_time": "0:56:41", "remaining_time": "1:01:35", "throughput": 5539.59, "total_tokens": 18843568} {"current_steps": 30900, "total_steps": 64460, "loss": 0.241, "lr": 6.220588016441234e-06, "epoch": 9.587340986658393, "percentage": 47.94, "elapsed_time": "0:56:42", "remaining_time": "1:01:34", "throughput": 5539.64, "total_tokens": 18846320} {"current_steps": 30905, "total_steps": 64460, "loss": 0.224, "lr": 6.219275122333706e-06, "epoch": 9.58889233633261, "percentage": 47.94, "elapsed_time": "0:56:42", "remaining_time": "1:01:34", "throughput": 5539.78, "total_tokens": 18850064} {"current_steps": 30910, "total_steps": 64460, "loss": 0.215, "lr": 6.217962138838872e-06, "epoch": 9.590443686006825, "percentage": 47.95, "elapsed_time": "0:56:43", "remaining_time": "1:01:33", "throughput": 5539.82, "total_tokens": 18853136} {"current_steps": 30915, "total_steps": 64460, "loss": 0.2328, "lr": 6.216649066052991e-06, "epoch": 9.591995035681043, "percentage": 47.96, "elapsed_time": "0:56:43", "remaining_time": "1:01:33", "throughput": 5540.02, "total_tokens": 18856912} {"current_steps": 30920, "total_steps": 64460, "loss": 0.2143, "lr": 6.215335904072326e-06, "epoch": 9.593546385355259, "percentage": 47.97, "elapsed_time": "0:56:44", "remaining_time": "1:01:32", "throughput": 5540.05, "total_tokens": 18859760} {"current_steps": 30925, "total_steps": 64460, "loss": 0.2383, "lr": 6.214022652993147e-06, "epoch": 9.595097735029476, "percentage": 47.98, "elapsed_time": "0:56:44", "remaining_time": "1:01:32", "throughput": 5540.18, "total_tokens": 18863216} {"current_steps": 30930, "total_steps": 64460, "loss": 0.2137, "lr": 6.2127093129117324e-06, "epoch": 9.596649084703692, "percentage": 47.98, "elapsed_time": "0:56:45", "remaining_time": "1:01:31", "throughput": 5540.16, "total_tokens": 18865680} {"current_steps": 30935, "total_steps": 64460, "loss": 0.2236, "lr": 6.211395883924364e-06, "epoch": 9.598200434377908, "percentage": 47.99, "elapsed_time": "0:56:45", "remaining_time": "1:01:30", "throughput": 5540.22, "total_tokens": 18868784} {"current_steps": 30940, "total_steps": 64460, "loss": 0.2217, "lr": 6.210082366127333e-06, "epoch": 9.599751784052126, "percentage": 48.0, "elapsed_time": "0:56:46", "remaining_time": "1:01:30", "throughput": 5540.19, "total_tokens": 18871408} {"current_steps": 30945, "total_steps": 64460, "loss": 0.2273, "lr": 6.2087687596169335e-06, "epoch": 9.601303133726342, "percentage": 48.01, "elapsed_time": "0:56:46", "remaining_time": "1:01:29", "throughput": 5540.28, "total_tokens": 18874576} {"current_steps": 30950, "total_steps": 64460, "loss": 0.2176, "lr": 6.2074550644894714e-06, "epoch": 9.60285448340056, "percentage": 48.01, "elapsed_time": "0:56:47", "remaining_time": "1:01:29", "throughput": 5540.55, "total_tokens": 18878960} {"current_steps": 30955, "total_steps": 64460, "loss": 0.2335, "lr": 6.206141280841253e-06, "epoch": 9.604405833074775, "percentage": 48.02, "elapsed_time": "0:56:47", "remaining_time": "1:01:28", "throughput": 5540.62, "total_tokens": 18882064} {"current_steps": 30960, "total_steps": 64460, "loss": 0.2259, "lr": 6.2048274087685975e-06, "epoch": 9.605957182748991, "percentage": 48.03, "elapsed_time": "0:56:48", "remaining_time": "1:01:28", "throughput": 5540.76, "total_tokens": 18885328} {"current_steps": 30965, "total_steps": 64460, "loss": 0.2388, "lr": 6.203513448367826e-06, "epoch": 9.607508532423209, "percentage": 48.04, "elapsed_time": "0:56:48", "remaining_time": "1:01:27", "throughput": 5540.68, "total_tokens": 18887664} {"current_steps": 30970, "total_steps": 64460, "loss": 0.2362, "lr": 6.202199399735266e-06, "epoch": 9.609059882097425, "percentage": 48.05, "elapsed_time": "0:56:49", "remaining_time": "1:01:26", "throughput": 5540.72, "total_tokens": 18890512} {"current_steps": 30975, "total_steps": 64460, "loss": 0.2478, "lr": 6.200885262967254e-06, "epoch": 9.61061123177164, "percentage": 48.05, "elapsed_time": "0:56:49", "remaining_time": "1:01:26", "throughput": 5540.77, "total_tokens": 18893936} {"current_steps": 30980, "total_steps": 64460, "loss": 0.2068, "lr": 6.199571038160132e-06, "epoch": 9.612162581445858, "percentage": 48.06, "elapsed_time": "0:56:50", "remaining_time": "1:01:25", "throughput": 5540.86, "total_tokens": 18897232} {"current_steps": 30985, "total_steps": 64460, "loss": 0.2391, "lr": 6.198256725410247e-06, "epoch": 9.613713931120074, "percentage": 48.07, "elapsed_time": "0:56:51", "remaining_time": "1:01:25", "throughput": 5540.79, "total_tokens": 18899920} {"current_steps": 30990, "total_steps": 64460, "loss": 0.2376, "lr": 6.196942324813955e-06, "epoch": 9.615265280794292, "percentage": 48.08, "elapsed_time": "0:56:51", "remaining_time": "1:01:24", "throughput": 5540.9, "total_tokens": 18903024} {"current_steps": 30995, "total_steps": 64460, "loss": 0.2219, "lr": 6.195627836467616e-06, "epoch": 9.616816630468508, "percentage": 48.08, "elapsed_time": "0:56:52", "remaining_time": "1:01:23", "throughput": 5541.01, "total_tokens": 18906320} {"current_steps": 31000, "total_steps": 64460, "loss": 0.2252, "lr": 6.194313260467599e-06, "epoch": 9.618367980142724, "percentage": 48.09, "elapsed_time": "0:56:52", "remaining_time": "1:01:23", "throughput": 5540.96, "total_tokens": 18909200} {"current_steps": 31005, "total_steps": 64460, "loss": 0.2291, "lr": 6.192998596910278e-06, "epoch": 9.619919329816941, "percentage": 48.1, "elapsed_time": "0:56:53", "remaining_time": "1:01:22", "throughput": 5541.08, "total_tokens": 18912368} {"current_steps": 31010, "total_steps": 64460, "loss": 0.2407, "lr": 6.191683845892032e-06, "epoch": 9.621470679491157, "percentage": 48.11, "elapsed_time": "0:56:53", "remaining_time": "1:01:22", "throughput": 5541.14, "total_tokens": 18915312} {"current_steps": 31015, "total_steps": 64460, "loss": 0.2219, "lr": 6.190369007509247e-06, "epoch": 9.623022029165373, "percentage": 48.12, "elapsed_time": "0:56:54", "remaining_time": "1:01:21", "throughput": 5541.24, "total_tokens": 18918640} {"current_steps": 31020, "total_steps": 64460, "loss": 0.2214, "lr": 6.189054081858319e-06, "epoch": 9.62457337883959, "percentage": 48.12, "elapsed_time": "0:56:54", "remaining_time": "1:01:21", "throughput": 5541.27, "total_tokens": 18921584} {"current_steps": 31025, "total_steps": 64460, "loss": 0.2326, "lr": 6.187739069035647e-06, "epoch": 9.626124728513807, "percentage": 48.13, "elapsed_time": "0:56:55", "remaining_time": "1:01:20", "throughput": 5541.28, "total_tokens": 18924240} {"current_steps": 31030, "total_steps": 64460, "loss": 0.227, "lr": 6.186423969137635e-06, "epoch": 9.627676078188024, "percentage": 48.14, "elapsed_time": "0:56:55", "remaining_time": "1:01:19", "throughput": 5541.35, "total_tokens": 18927344} {"current_steps": 31035, "total_steps": 64460, "loss": 0.2129, "lr": 6.185108782260696e-06, "epoch": 9.62922742786224, "percentage": 48.15, "elapsed_time": "0:56:56", "remaining_time": "1:01:19", "throughput": 5541.4, "total_tokens": 18930128} {"current_steps": 31040, "total_steps": 64460, "loss": 0.2326, "lr": 6.183793508501251e-06, "epoch": 9.630778777536456, "percentage": 48.15, "elapsed_time": "0:56:56", "remaining_time": "1:01:18", "throughput": 5541.4, "total_tokens": 18932784} {"current_steps": 31045, "total_steps": 64460, "loss": 0.2445, "lr": 6.1824781479557235e-06, "epoch": 9.632330127210674, "percentage": 48.16, "elapsed_time": "0:56:57", "remaining_time": "1:01:17", "throughput": 5541.34, "total_tokens": 18935216} {"current_steps": 31050, "total_steps": 64460, "loss": 0.2564, "lr": 6.1811627007205455e-06, "epoch": 9.63388147688489, "percentage": 48.17, "elapsed_time": "0:56:57", "remaining_time": "1:01:17", "throughput": 5541.35, "total_tokens": 18938288} {"current_steps": 31055, "total_steps": 64460, "loss": 0.2431, "lr": 6.179847166892153e-06, "epoch": 9.635432826559107, "percentage": 48.18, "elapsed_time": "0:56:58", "remaining_time": "1:01:16", "throughput": 5541.41, "total_tokens": 18941296} {"current_steps": 31060, "total_steps": 64460, "loss": 0.2265, "lr": 6.178531546566993e-06, "epoch": 9.636984176233323, "percentage": 48.18, "elapsed_time": "0:56:58", "remaining_time": "1:01:16", "throughput": 5541.59, "total_tokens": 18945936} {"current_steps": 31065, "total_steps": 64460, "loss": 0.2533, "lr": 6.177215839841514e-06, "epoch": 9.638535525907539, "percentage": 48.19, "elapsed_time": "0:56:59", "remaining_time": "1:01:15", "throughput": 5541.5, "total_tokens": 18948272} {"current_steps": 31070, "total_steps": 64460, "loss": 0.2246, "lr": 6.175900046812173e-06, "epoch": 9.640086875581757, "percentage": 48.2, "elapsed_time": "0:56:59", "remaining_time": "1:01:15", "throughput": 5541.38, "total_tokens": 18950416} {"current_steps": 31075, "total_steps": 64460, "loss": 0.2276, "lr": 6.174584167575434e-06, "epoch": 9.641638225255972, "percentage": 48.21, "elapsed_time": "0:57:00", "remaining_time": "1:01:14", "throughput": 5541.35, "total_tokens": 18952848} {"current_steps": 31080, "total_steps": 64460, "loss": 0.2233, "lr": 6.173268202227769e-06, "epoch": 9.64318957493019, "percentage": 48.22, "elapsed_time": "0:57:00", "remaining_time": "1:01:13", "throughput": 5541.45, "total_tokens": 18956400} {"current_steps": 31085, "total_steps": 64460, "loss": 0.2309, "lr": 6.171952150865649e-06, "epoch": 9.644740924604406, "percentage": 48.22, "elapsed_time": "0:57:01", "remaining_time": "1:01:13", "throughput": 5541.41, "total_tokens": 18958960} {"current_steps": 31090, "total_steps": 64460, "loss": 0.2363, "lr": 6.170636013585558e-06, "epoch": 9.646292274278622, "percentage": 48.23, "elapsed_time": "0:57:01", "remaining_time": "1:01:12", "throughput": 5541.52, "total_tokens": 18962128} {"current_steps": 31095, "total_steps": 64460, "loss": 0.2375, "lr": 6.1693197904839865e-06, "epoch": 9.64784362395284, "percentage": 48.24, "elapsed_time": "0:57:02", "remaining_time": "1:01:12", "throughput": 5541.5, "total_tokens": 18964624} {"current_steps": 31100, "total_steps": 64460, "loss": 0.2263, "lr": 6.168003481657427e-06, "epoch": 9.649394973627055, "percentage": 48.25, "elapsed_time": "0:57:02", "remaining_time": "1:01:11", "throughput": 5541.4, "total_tokens": 18966832} {"current_steps": 31105, "total_steps": 64460, "loss": 0.2328, "lr": 6.16668708720238e-06, "epoch": 9.650946323301271, "percentage": 48.25, "elapsed_time": "0:57:03", "remaining_time": "1:01:10", "throughput": 5541.4, "total_tokens": 18969552} {"current_steps": 31110, "total_steps": 64460, "loss": 0.2286, "lr": 6.165370607215354e-06, "epoch": 9.652497672975489, "percentage": 48.26, "elapsed_time": "0:57:03", "remaining_time": "1:01:10", "throughput": 5541.32, "total_tokens": 18971984} {"current_steps": 31115, "total_steps": 64460, "loss": 0.2395, "lr": 6.164054041792861e-06, "epoch": 9.654049022649705, "percentage": 48.27, "elapsed_time": "0:57:04", "remaining_time": "1:01:09", "throughput": 5541.11, "total_tokens": 18973936} {"current_steps": 31120, "total_steps": 64460, "loss": 0.2232, "lr": 6.162737391031426e-06, "epoch": 9.655600372323923, "percentage": 48.28, "elapsed_time": "0:57:04", "remaining_time": "1:01:09", "throughput": 5541.23, "total_tokens": 18977360} {"current_steps": 31125, "total_steps": 64460, "loss": 0.2306, "lr": 6.161420655027569e-06, "epoch": 9.657151721998138, "percentage": 48.29, "elapsed_time": "0:57:05", "remaining_time": "1:01:08", "throughput": 5541.29, "total_tokens": 18980368} {"current_steps": 31130, "total_steps": 64460, "loss": 0.2228, "lr": 6.1601038338778255e-06, "epoch": 9.658703071672354, "percentage": 48.29, "elapsed_time": "0:57:05", "remaining_time": "1:01:08", "throughput": 5541.57, "total_tokens": 18985008} {"current_steps": 31135, "total_steps": 64460, "loss": 0.2382, "lr": 6.1587869276787325e-06, "epoch": 9.660254421346572, "percentage": 48.3, "elapsed_time": "0:57:06", "remaining_time": "1:01:07", "throughput": 5541.5, "total_tokens": 18987344} {"current_steps": 31140, "total_steps": 64460, "loss": 0.2302, "lr": 6.157469936526837e-06, "epoch": 9.661805771020788, "percentage": 48.31, "elapsed_time": "0:57:06", "remaining_time": "1:01:06", "throughput": 5541.69, "total_tokens": 18991280} {"current_steps": 31145, "total_steps": 64460, "loss": 0.2287, "lr": 6.156152860518687e-06, "epoch": 9.663357120695004, "percentage": 48.32, "elapsed_time": "0:57:07", "remaining_time": "1:01:06", "throughput": 5541.68, "total_tokens": 18993872} {"current_steps": 31150, "total_steps": 64460, "loss": 0.225, "lr": 6.154835699750843e-06, "epoch": 9.664908470369221, "percentage": 48.32, "elapsed_time": "0:57:07", "remaining_time": "1:01:05", "throughput": 5541.61, "total_tokens": 18996336} {"current_steps": 31155, "total_steps": 64460, "loss": 0.2157, "lr": 6.153518454319866e-06, "epoch": 9.666459820043437, "percentage": 48.33, "elapsed_time": "0:57:08", "remaining_time": "1:01:05", "throughput": 5541.44, "total_tokens": 18998448} {"current_steps": 31160, "total_steps": 64460, "loss": 0.2274, "lr": 6.152201124322327e-06, "epoch": 9.668011169717655, "percentage": 48.34, "elapsed_time": "0:57:09", "remaining_time": "1:01:04", "throughput": 5541.54, "total_tokens": 19002256} {"current_steps": 31165, "total_steps": 64460, "loss": 0.2353, "lr": 6.150883709854801e-06, "epoch": 9.66956251939187, "percentage": 48.35, "elapsed_time": "0:57:09", "remaining_time": "1:01:04", "throughput": 5541.58, "total_tokens": 19005584} {"current_steps": 31170, "total_steps": 64460, "loss": 0.2567, "lr": 6.149566211013871e-06, "epoch": 9.671113869066087, "percentage": 48.36, "elapsed_time": "0:57:10", "remaining_time": "1:01:03", "throughput": 5541.64, "total_tokens": 19008656} {"current_steps": 31175, "total_steps": 64460, "loss": 0.2187, "lr": 6.148248627896123e-06, "epoch": 9.672665218740304, "percentage": 48.36, "elapsed_time": "0:57:10", "remaining_time": "1:01:02", "throughput": 5541.7, "total_tokens": 19011952} {"current_steps": 31180, "total_steps": 64460, "loss": 0.2214, "lr": 6.146930960598155e-06, "epoch": 9.67421656841452, "percentage": 48.37, "elapsed_time": "0:57:11", "remaining_time": "1:01:02", "throughput": 5541.82, "total_tokens": 19015856} {"current_steps": 31185, "total_steps": 64460, "loss": 0.2252, "lr": 6.145613209216567e-06, "epoch": 9.675767918088738, "percentage": 48.38, "elapsed_time": "0:57:11", "remaining_time": "1:01:01", "throughput": 5541.76, "total_tokens": 19018224} {"current_steps": 31190, "total_steps": 64460, "loss": 0.2305, "lr": 6.144295373847963e-06, "epoch": 9.677319267762954, "percentage": 48.39, "elapsed_time": "0:57:12", "remaining_time": "1:01:01", "throughput": 5541.89, "total_tokens": 19021584} {"current_steps": 31195, "total_steps": 64460, "loss": 0.2234, "lr": 6.142977454588957e-06, "epoch": 9.67887061743717, "percentage": 48.39, "elapsed_time": "0:57:12", "remaining_time": "1:01:00", "throughput": 5542.08, "total_tokens": 19025936} {"current_steps": 31200, "total_steps": 64460, "loss": 0.2293, "lr": 6.1416594515361706e-06, "epoch": 9.680421967111387, "percentage": 48.4, "elapsed_time": "0:57:13", "remaining_time": "1:01:00", "throughput": 5542.28, "total_tokens": 19030064} {"current_steps": 31205, "total_steps": 64460, "loss": 0.2203, "lr": 6.140341364786226e-06, "epoch": 9.681973316785603, "percentage": 48.41, "elapsed_time": "0:57:14", "remaining_time": "1:00:59", "throughput": 5542.36, "total_tokens": 19033392} {"current_steps": 31210, "total_steps": 64460, "loss": 0.2319, "lr": 6.139023194435756e-06, "epoch": 9.683524666459821, "percentage": 48.42, "elapsed_time": "0:57:14", "remaining_time": "1:00:59", "throughput": 5542.29, "total_tokens": 19036112} {"current_steps": 31215, "total_steps": 64460, "loss": 0.2305, "lr": 6.137704940581399e-06, "epoch": 9.685076016134037, "percentage": 48.43, "elapsed_time": "0:57:15", "remaining_time": "1:00:58", "throughput": 5542.29, "total_tokens": 19039248} {"current_steps": 31220, "total_steps": 64460, "loss": 0.2336, "lr": 6.136386603319795e-06, "epoch": 9.686627365808253, "percentage": 48.43, "elapsed_time": "0:57:15", "remaining_time": "1:00:58", "throughput": 5542.19, "total_tokens": 19041648} {"current_steps": 31225, "total_steps": 64460, "loss": 0.2252, "lr": 6.135068182747598e-06, "epoch": 9.68817871548247, "percentage": 48.44, "elapsed_time": "0:57:16", "remaining_time": "1:00:57", "throughput": 5542.08, "total_tokens": 19043856} {"current_steps": 31230, "total_steps": 64460, "loss": 0.2198, "lr": 6.133749678961461e-06, "epoch": 9.689730065156686, "percentage": 48.45, "elapsed_time": "0:57:16", "remaining_time": "1:00:56", "throughput": 5542.07, "total_tokens": 19046544} {"current_steps": 31235, "total_steps": 64460, "loss": 0.2234, "lr": 6.132431092058047e-06, "epoch": 9.691281414830902, "percentage": 48.46, "elapsed_time": "0:57:17", "remaining_time": "1:00:56", "throughput": 5542.14, "total_tokens": 19049776} {"current_steps": 31240, "total_steps": 64460, "loss": 0.2171, "lr": 6.1311124221340235e-06, "epoch": 9.69283276450512, "percentage": 48.46, "elapsed_time": "0:57:17", "remaining_time": "1:00:55", "throughput": 5542.17, "total_tokens": 19052944} {"current_steps": 31245, "total_steps": 64460, "loss": 0.2227, "lr": 6.129793669286066e-06, "epoch": 9.694384114179336, "percentage": 48.47, "elapsed_time": "0:57:18", "remaining_time": "1:00:55", "throughput": 5542.08, "total_tokens": 19055376} {"current_steps": 31250, "total_steps": 64460, "loss": 0.227, "lr": 6.128474833610853e-06, "epoch": 9.695935463853553, "percentage": 48.48, "elapsed_time": "0:57:18", "remaining_time": "1:00:54", "throughput": 5541.96, "total_tokens": 19057872} {"current_steps": 31255, "total_steps": 64460, "loss": 0.2146, "lr": 6.127155915205073e-06, "epoch": 9.69748681352777, "percentage": 48.49, "elapsed_time": "0:57:19", "remaining_time": "1:00:53", "throughput": 5542.1, "total_tokens": 19061584} {"current_steps": 31260, "total_steps": 64460, "loss": 0.2319, "lr": 6.125836914165416e-06, "epoch": 9.699038163201985, "percentage": 48.5, "elapsed_time": "0:57:19", "remaining_time": "1:00:53", "throughput": 5542.1, "total_tokens": 19064144} {"current_steps": 31265, "total_steps": 64460, "loss": 0.2332, "lr": 6.124517830588581e-06, "epoch": 9.700589512876203, "percentage": 48.5, "elapsed_time": "0:57:20", "remaining_time": "1:00:52", "throughput": 5542.23, "total_tokens": 19067536} {"current_steps": 31270, "total_steps": 64460, "loss": 0.2184, "lr": 6.123198664571274e-06, "epoch": 9.702140862550419, "percentage": 48.51, "elapsed_time": "0:57:20", "remaining_time": "1:00:52", "throughput": 5542.18, "total_tokens": 19070032} {"current_steps": 31275, "total_steps": 64460, "loss": 0.2193, "lr": 6.121879416210204e-06, "epoch": 9.703692212224635, "percentage": 48.52, "elapsed_time": "0:57:21", "remaining_time": "1:00:51", "throughput": 5542.29, "total_tokens": 19073552} {"current_steps": 31280, "total_steps": 64460, "loss": 0.2417, "lr": 6.1205600856020865e-06, "epoch": 9.705243561898852, "percentage": 48.53, "elapsed_time": "0:57:22", "remaining_time": "1:00:51", "throughput": 5542.58, "total_tokens": 19078736} {"current_steps": 31285, "total_steps": 64460, "loss": 0.216, "lr": 6.119240672843646e-06, "epoch": 9.706794911573068, "percentage": 48.53, "elapsed_time": "0:57:22", "remaining_time": "1:00:50", "throughput": 5542.7, "total_tokens": 19082000} {"current_steps": 31290, "total_steps": 64460, "loss": 0.2285, "lr": 6.1179211780316094e-06, "epoch": 9.708346261247286, "percentage": 48.54, "elapsed_time": "0:57:23", "remaining_time": "1:00:50", "throughput": 5542.69, "total_tokens": 19084592} {"current_steps": 31295, "total_steps": 64460, "loss": 0.2301, "lr": 6.1166016012627126e-06, "epoch": 9.709897610921502, "percentage": 48.55, "elapsed_time": "0:57:23", "remaining_time": "1:00:49", "throughput": 5542.89, "total_tokens": 19089360} {"current_steps": 31300, "total_steps": 64460, "loss": 0.2411, "lr": 6.115281942633696e-06, "epoch": 9.711448960595717, "percentage": 48.56, "elapsed_time": "0:57:24", "remaining_time": "1:00:49", "throughput": 5542.97, "total_tokens": 19092784} {"current_steps": 31305, "total_steps": 64460, "loss": 0.2385, "lr": 6.113962202241307e-06, "epoch": 9.713000310269935, "percentage": 48.57, "elapsed_time": "0:57:25", "remaining_time": "1:00:48", "throughput": 5543.14, "total_tokens": 19097424} {"current_steps": 31310, "total_steps": 64460, "loss": 0.2406, "lr": 6.1126423801822965e-06, "epoch": 9.714551659944151, "percentage": 48.57, "elapsed_time": "0:57:25", "remaining_time": "1:00:48", "throughput": 5543.14, "total_tokens": 19100400} {"current_steps": 31315, "total_steps": 64460, "loss": 0.2357, "lr": 6.111322476553425e-06, "epoch": 9.716103009618369, "percentage": 48.58, "elapsed_time": "0:57:26", "remaining_time": "1:00:47", "throughput": 5543.23, "total_tokens": 19104144} {"current_steps": 31320, "total_steps": 64460, "loss": 0.2189, "lr": 6.110002491451455e-06, "epoch": 9.717654359292585, "percentage": 48.59, "elapsed_time": "0:57:26", "remaining_time": "1:00:47", "throughput": 5543.22, "total_tokens": 19106864} {"current_steps": 31325, "total_steps": 64460, "loss": 0.2237, "lr": 6.108682424973157e-06, "epoch": 9.7192057089668, "percentage": 48.6, "elapsed_time": "0:57:27", "remaining_time": "1:00:46", "throughput": 5543.15, "total_tokens": 19109200} {"current_steps": 31330, "total_steps": 64460, "loss": 0.2291, "lr": 6.1073622772153094e-06, "epoch": 9.720757058641018, "percentage": 48.6, "elapsed_time": "0:57:28", "remaining_time": "1:00:46", "throughput": 5543.35, "total_tokens": 19113712} {"current_steps": 31335, "total_steps": 64460, "loss": 0.2349, "lr": 6.106042048274694e-06, "epoch": 9.722308408315234, "percentage": 48.61, "elapsed_time": "0:57:28", "remaining_time": "1:00:45", "throughput": 5543.26, "total_tokens": 19116112} {"current_steps": 31340, "total_steps": 64460, "loss": 0.2336, "lr": 6.104721738248099e-06, "epoch": 9.723859757989452, "percentage": 48.62, "elapsed_time": "0:57:29", "remaining_time": "1:00:44", "throughput": 5543.17, "total_tokens": 19118416} {"current_steps": 31345, "total_steps": 64460, "loss": 0.2376, "lr": 6.103401347232318e-06, "epoch": 9.725411107663668, "percentage": 48.63, "elapsed_time": "0:57:29", "remaining_time": "1:00:44", "throughput": 5543.15, "total_tokens": 19121008} {"current_steps": 31350, "total_steps": 64460, "loss": 0.2286, "lr": 6.102080875324153e-06, "epoch": 9.726962457337883, "percentage": 48.63, "elapsed_time": "0:57:30", "remaining_time": "1:00:43", "throughput": 5543.28, "total_tokens": 19125136} {"current_steps": 31355, "total_steps": 64460, "loss": 0.226, "lr": 6.100760322620409e-06, "epoch": 9.728513807012101, "percentage": 48.64, "elapsed_time": "0:57:30", "remaining_time": "1:00:43", "throughput": 5543.18, "total_tokens": 19127440} {"current_steps": 31360, "total_steps": 64460, "loss": 0.2369, "lr": 6.099439689217898e-06, "epoch": 9.730065156686317, "percentage": 48.65, "elapsed_time": "0:57:31", "remaining_time": "1:00:42", "throughput": 5543.18, "total_tokens": 19130064} {"current_steps": 31365, "total_steps": 64460, "loss": 0.2261, "lr": 6.09811897521344e-06, "epoch": 9.731616506360533, "percentage": 48.66, "elapsed_time": "0:57:31", "remaining_time": "1:00:41", "throughput": 5543.22, "total_tokens": 19132816} {"current_steps": 31370, "total_steps": 64460, "loss": 0.2271, "lr": 6.096798180703854e-06, "epoch": 9.73316785603475, "percentage": 48.67, "elapsed_time": "0:57:32", "remaining_time": "1:00:41", "throughput": 5543.36, "total_tokens": 19136720} {"current_steps": 31375, "total_steps": 64460, "loss": 0.2314, "lr": 6.095477305785976e-06, "epoch": 9.734719205708966, "percentage": 48.67, "elapsed_time": "0:57:32", "remaining_time": "1:00:40", "throughput": 5543.45, "total_tokens": 19139792} {"current_steps": 31380, "total_steps": 64460, "loss": 0.2324, "lr": 6.094156350556639e-06, "epoch": 9.736270555383184, "percentage": 48.68, "elapsed_time": "0:57:33", "remaining_time": "1:00:40", "throughput": 5543.46, "total_tokens": 19142704} {"current_steps": 31385, "total_steps": 64460, "loss": 0.2317, "lr": 6.092835315112684e-06, "epoch": 9.7378219050574, "percentage": 48.69, "elapsed_time": "0:57:33", "remaining_time": "1:00:39", "throughput": 5543.43, "total_tokens": 19145616} {"current_steps": 31390, "total_steps": 64460, "loss": 0.2321, "lr": 6.09151419955096e-06, "epoch": 9.739373254731616, "percentage": 48.7, "elapsed_time": "0:57:34", "remaining_time": "1:00:39", "throughput": 5543.42, "total_tokens": 19148720} {"current_steps": 31395, "total_steps": 64460, "loss": 0.2326, "lr": 6.090193003968319e-06, "epoch": 9.740924604405834, "percentage": 48.7, "elapsed_time": "0:57:34", "remaining_time": "1:00:38", "throughput": 5543.31, "total_tokens": 19151216} {"current_steps": 31400, "total_steps": 64460, "loss": 0.2495, "lr": 6.088871728461621e-06, "epoch": 9.74247595408005, "percentage": 48.71, "elapsed_time": "0:57:35", "remaining_time": "1:00:37", "throughput": 5543.39, "total_tokens": 19154224} {"current_steps": 31405, "total_steps": 64460, "loss": 0.2343, "lr": 6.087550373127732e-06, "epoch": 9.744027303754265, "percentage": 48.72, "elapsed_time": "0:57:35", "remaining_time": "1:00:37", "throughput": 5543.48, "total_tokens": 19157648} {"current_steps": 31410, "total_steps": 64460, "loss": 0.2341, "lr": 6.086228938063522e-06, "epoch": 9.745578653428483, "percentage": 48.73, "elapsed_time": "0:57:36", "remaining_time": "1:00:36", "throughput": 5543.61, "total_tokens": 19161040} {"current_steps": 31415, "total_steps": 64460, "loss": 0.2376, "lr": 6.084907423365868e-06, "epoch": 9.747130003102699, "percentage": 48.74, "elapsed_time": "0:57:36", "remaining_time": "1:00:36", "throughput": 5543.78, "total_tokens": 19164496} {"current_steps": 31420, "total_steps": 64460, "loss": 0.2404, "lr": 6.083585829131652e-06, "epoch": 9.748681352776916, "percentage": 48.74, "elapsed_time": "0:57:37", "remaining_time": "1:00:35", "throughput": 5543.84, "total_tokens": 19167568} {"current_steps": 31425, "total_steps": 64460, "loss": 0.2332, "lr": 6.082264155457764e-06, "epoch": 9.750232702451132, "percentage": 48.75, "elapsed_time": "0:57:37", "remaining_time": "1:00:35", "throughput": 5543.76, "total_tokens": 19170128} {"current_steps": 31430, "total_steps": 64460, "loss": 0.2277, "lr": 6.080942402441095e-06, "epoch": 9.751784052125348, "percentage": 48.76, "elapsed_time": "0:57:38", "remaining_time": "1:00:34", "throughput": 5543.86, "total_tokens": 19173488} {"current_steps": 31435, "total_steps": 64460, "loss": 0.224, "lr": 6.0796205701785495e-06, "epoch": 9.753335401799566, "percentage": 48.77, "elapsed_time": "0:57:39", "remaining_time": "1:00:34", "throughput": 5543.83, "total_tokens": 19176688} {"current_steps": 31440, "total_steps": 64460, "loss": 0.2353, "lr": 6.078298658767032e-06, "epoch": 9.754886751473782, "percentage": 48.77, "elapsed_time": "0:57:39", "remaining_time": "1:00:33", "throughput": 5543.89, "total_tokens": 19179856} {"current_steps": 31445, "total_steps": 64460, "loss": 0.2244, "lr": 6.076976668303454e-06, "epoch": 9.756438101148, "percentage": 48.78, "elapsed_time": "0:57:40", "remaining_time": "1:00:32", "throughput": 5544.04, "total_tokens": 19183344} {"current_steps": 31450, "total_steps": 64460, "loss": 0.228, "lr": 6.075654598884732e-06, "epoch": 9.757989450822215, "percentage": 48.79, "elapsed_time": "0:57:40", "remaining_time": "1:00:32", "throughput": 5544.04, "total_tokens": 19186000} {"current_steps": 31455, "total_steps": 64460, "loss": 0.2334, "lr": 6.07433245060779e-06, "epoch": 9.759540800496431, "percentage": 48.8, "elapsed_time": "0:57:41", "remaining_time": "1:00:31", "throughput": 5544.09, "total_tokens": 19188944} {"current_steps": 31460, "total_steps": 64460, "loss": 0.22, "lr": 6.073010223569559e-06, "epoch": 9.761092150170649, "percentage": 48.81, "elapsed_time": "0:57:41", "remaining_time": "1:00:31", "throughput": 5544.12, "total_tokens": 19191856} {"current_steps": 31465, "total_steps": 64460, "loss": 0.222, "lr": 6.07168791786697e-06, "epoch": 9.762643499844865, "percentage": 48.81, "elapsed_time": "0:57:42", "remaining_time": "1:00:30", "throughput": 5544.11, "total_tokens": 19194672} {"current_steps": 31470, "total_steps": 64460, "loss": 0.223, "lr": 6.070365533596968e-06, "epoch": 9.764194849519082, "percentage": 48.82, "elapsed_time": "0:57:42", "remaining_time": "1:00:29", "throughput": 5544.21, "total_tokens": 19197744} {"current_steps": 31475, "total_steps": 64460, "loss": 0.233, "lr": 6.069043070856496e-06, "epoch": 9.765746199193298, "percentage": 48.83, "elapsed_time": "0:57:43", "remaining_time": "1:00:29", "throughput": 5544.13, "total_tokens": 19200496} {"current_steps": 31480, "total_steps": 64460, "loss": 0.2365, "lr": 6.067720529742509e-06, "epoch": 9.767297548867514, "percentage": 48.84, "elapsed_time": "0:57:43", "remaining_time": "1:00:28", "throughput": 5544.27, "total_tokens": 19204144} {"current_steps": 31485, "total_steps": 64460, "loss": 0.2235, "lr": 6.066397910351962e-06, "epoch": 9.768848898541732, "percentage": 48.84, "elapsed_time": "0:57:44", "remaining_time": "1:00:28", "throughput": 5544.39, "total_tokens": 19207536} {"current_steps": 31490, "total_steps": 64460, "loss": 0.2407, "lr": 6.065075212781819e-06, "epoch": 9.770400248215948, "percentage": 48.85, "elapsed_time": "0:57:44", "remaining_time": "1:00:27", "throughput": 5544.36, "total_tokens": 19210224} {"current_steps": 31495, "total_steps": 64460, "loss": 0.2361, "lr": 6.063752437129053e-06, "epoch": 9.771951597890164, "percentage": 48.86, "elapsed_time": "0:57:45", "remaining_time": "1:00:27", "throughput": 5544.27, "total_tokens": 19212656} {"current_steps": 31500, "total_steps": 64460, "loss": 0.2195, "lr": 6.062429583490635e-06, "epoch": 9.773502947564381, "percentage": 48.87, "elapsed_time": "0:57:45", "remaining_time": "1:00:26", "throughput": 5544.17, "total_tokens": 19215088} {"current_steps": 31505, "total_steps": 64460, "loss": 0.2451, "lr": 6.061106651963548e-06, "epoch": 9.775054297238597, "percentage": 48.88, "elapsed_time": "0:57:46", "remaining_time": "1:00:25", "throughput": 5544.16, "total_tokens": 19218096} {"current_steps": 31510, "total_steps": 64460, "loss": 0.2283, "lr": 6.05978364264478e-06, "epoch": 9.776605646912815, "percentage": 48.88, "elapsed_time": "0:57:46", "remaining_time": "1:00:25", "throughput": 5544.11, "total_tokens": 19220624} {"current_steps": 31515, "total_steps": 64460, "loss": 0.2293, "lr": 6.058460555631319e-06, "epoch": 9.77815699658703, "percentage": 48.89, "elapsed_time": "0:57:47", "remaining_time": "1:00:24", "throughput": 5544.14, "total_tokens": 19223504} {"current_steps": 31520, "total_steps": 64460, "loss": 0.2239, "lr": 6.057137391020166e-06, "epoch": 9.779708346261247, "percentage": 48.9, "elapsed_time": "0:57:47", "remaining_time": "1:00:24", "throughput": 5544.19, "total_tokens": 19226576} {"current_steps": 31525, "total_steps": 64460, "loss": 0.2407, "lr": 6.055814148908323e-06, "epoch": 9.781259695935464, "percentage": 48.91, "elapsed_time": "0:57:48", "remaining_time": "1:00:23", "throughput": 5544.14, "total_tokens": 19229584} {"current_steps": 31530, "total_steps": 64460, "loss": 0.2231, "lr": 6.054490829392802e-06, "epoch": 9.78281104560968, "percentage": 48.91, "elapsed_time": "0:57:49", "remaining_time": "1:00:23", "throughput": 5544.3, "total_tokens": 19233904} {"current_steps": 31535, "total_steps": 64460, "loss": 0.2179, "lr": 6.053167432570614e-06, "epoch": 9.784362395283896, "percentage": 48.92, "elapsed_time": "0:57:49", "remaining_time": "1:00:22", "throughput": 5544.43, "total_tokens": 19237648} {"current_steps": 31540, "total_steps": 64460, "loss": 0.226, "lr": 6.051843958538783e-06, "epoch": 9.785913744958114, "percentage": 48.93, "elapsed_time": "0:57:50", "remaining_time": "1:00:22", "throughput": 5544.31, "total_tokens": 19240016} {"current_steps": 31545, "total_steps": 64460, "loss": 0.2439, "lr": 6.0505204073943344e-06, "epoch": 9.78746509463233, "percentage": 48.94, "elapsed_time": "0:57:50", "remaining_time": "1:00:21", "throughput": 5544.4, "total_tokens": 19243440} {"current_steps": 31550, "total_steps": 64460, "loss": 0.2225, "lr": 6.0491967792342985e-06, "epoch": 9.789016444306547, "percentage": 48.95, "elapsed_time": "0:57:51", "remaining_time": "1:00:20", "throughput": 5544.39, "total_tokens": 19246256} {"current_steps": 31555, "total_steps": 64460, "loss": 0.2387, "lr": 6.047873074155716e-06, "epoch": 9.790567793980763, "percentage": 48.95, "elapsed_time": "0:57:52", "remaining_time": "1:00:20", "throughput": 5544.53, "total_tokens": 19250672} {"current_steps": 31560, "total_steps": 64460, "loss": 0.2173, "lr": 6.046549292255628e-06, "epoch": 9.792119143654979, "percentage": 48.96, "elapsed_time": "0:57:52", "remaining_time": "1:00:19", "throughput": 5544.46, "total_tokens": 19253136} {"current_steps": 31565, "total_steps": 64460, "loss": 0.2252, "lr": 6.045225433631083e-06, "epoch": 9.793670493329197, "percentage": 48.97, "elapsed_time": "0:57:52", "remaining_time": "1:00:19", "throughput": 5544.46, "total_tokens": 19255824} {"current_steps": 31570, "total_steps": 64460, "loss": 0.2252, "lr": 6.043901498379138e-06, "epoch": 9.795221843003413, "percentage": 48.98, "elapsed_time": "0:57:53", "remaining_time": "1:00:18", "throughput": 5544.57, "total_tokens": 19259248} {"current_steps": 31575, "total_steps": 64460, "loss": 0.2279, "lr": 6.04257748659685e-06, "epoch": 9.79677319267763, "percentage": 48.98, "elapsed_time": "0:57:54", "remaining_time": "1:00:18", "throughput": 5544.56, "total_tokens": 19262256} {"current_steps": 31580, "total_steps": 64460, "loss": 0.2397, "lr": 6.0412533983812874e-06, "epoch": 9.798324542351846, "percentage": 48.99, "elapsed_time": "0:57:54", "remaining_time": "1:00:17", "throughput": 5544.59, "total_tokens": 19265008} {"current_steps": 31585, "total_steps": 64460, "loss": 0.2429, "lr": 6.03992923382952e-06, "epoch": 9.799875892026062, "percentage": 49.0, "elapsed_time": "0:57:55", "remaining_time": "1:00:17", "throughput": 5544.74, "total_tokens": 19268976} {"current_steps": 31590, "total_steps": 64460, "loss": 0.2277, "lr": 6.038604993038625e-06, "epoch": 9.80142724170028, "percentage": 49.01, "elapsed_time": "0:57:55", "remaining_time": "1:00:16", "throughput": 5544.91, "total_tokens": 19272912} {"current_steps": 31595, "total_steps": 64460, "loss": 0.2277, "lr": 6.037280676105685e-06, "epoch": 9.802978591374496, "percentage": 49.01, "elapsed_time": "0:57:56", "remaining_time": "1:00:16", "throughput": 5545.0, "total_tokens": 19276304} {"current_steps": 31600, "total_steps": 64460, "loss": 0.2208, "lr": 6.035956283127789e-06, "epoch": 9.804529941048713, "percentage": 49.02, "elapsed_time": "0:57:56", "remaining_time": "1:00:15", "throughput": 5544.88, "total_tokens": 19278672} {"current_steps": 31605, "total_steps": 64460, "loss": 0.2356, "lr": 6.034631814202029e-06, "epoch": 9.806081290722929, "percentage": 49.03, "elapsed_time": "0:57:57", "remaining_time": "1:00:14", "throughput": 5544.82, "total_tokens": 19281200} {"current_steps": 31610, "total_steps": 64460, "loss": 0.2296, "lr": 6.033307269425503e-06, "epoch": 9.807632640397145, "percentage": 49.04, "elapsed_time": "0:57:57", "remaining_time": "1:00:14", "throughput": 5544.9, "total_tokens": 19284464} {"current_steps": 31615, "total_steps": 64460, "loss": 0.2401, "lr": 6.031982648895321e-06, "epoch": 9.809183990071363, "percentage": 49.05, "elapsed_time": "0:57:58", "remaining_time": "1:00:13", "throughput": 5545.04, "total_tokens": 19287952} {"current_steps": 31620, "total_steps": 64460, "loss": 0.2324, "lr": 6.030657952708591e-06, "epoch": 9.810735339745579, "percentage": 49.05, "elapsed_time": "0:57:58", "remaining_time": "1:00:13", "throughput": 5544.81, "total_tokens": 19289840} {"current_steps": 31625, "total_steps": 64460, "loss": 0.2195, "lr": 6.029333180962426e-06, "epoch": 9.812286689419794, "percentage": 49.06, "elapsed_time": "0:57:59", "remaining_time": "1:00:12", "throughput": 5544.82, "total_tokens": 19292624} {"current_steps": 31630, "total_steps": 64460, "loss": 0.2393, "lr": 6.028008333753949e-06, "epoch": 9.813838039094012, "percentage": 49.07, "elapsed_time": "0:57:59", "remaining_time": "1:00:11", "throughput": 5544.76, "total_tokens": 19295120} {"current_steps": 31635, "total_steps": 64460, "loss": 0.2128, "lr": 6.02668341118029e-06, "epoch": 9.815389388768228, "percentage": 49.08, "elapsed_time": "0:58:00", "remaining_time": "1:00:11", "throughput": 5544.84, "total_tokens": 19298416} {"current_steps": 31640, "total_steps": 64460, "loss": 0.2288, "lr": 6.025358413338579e-06, "epoch": 9.816940738442446, "percentage": 49.08, "elapsed_time": "0:58:00", "remaining_time": "1:00:10", "throughput": 5544.79, "total_tokens": 19301008} {"current_steps": 31645, "total_steps": 64460, "loss": 0.2224, "lr": 6.024033340325954e-06, "epoch": 9.818492088116662, "percentage": 49.09, "elapsed_time": "0:58:01", "remaining_time": "1:00:10", "throughput": 5544.76, "total_tokens": 19303792} {"current_steps": 31650, "total_steps": 64460, "loss": 0.2304, "lr": 6.022708192239558e-06, "epoch": 9.820043437790877, "percentage": 49.1, "elapsed_time": "0:58:01", "remaining_time": "1:00:09", "throughput": 5544.77, "total_tokens": 19306768} {"current_steps": 31655, "total_steps": 64460, "loss": 0.2377, "lr": 6.021382969176541e-06, "epoch": 9.821594787465095, "percentage": 49.11, "elapsed_time": "0:58:02", "remaining_time": "1:00:08", "throughput": 5544.76, "total_tokens": 19309552} {"current_steps": 31660, "total_steps": 64460, "loss": 0.2234, "lr": 6.0200576712340585e-06, "epoch": 9.823146137139311, "percentage": 49.12, "elapsed_time": "0:58:03", "remaining_time": "1:00:08", "throughput": 5544.92, "total_tokens": 19313808} {"current_steps": 31665, "total_steps": 64460, "loss": 0.2196, "lr": 6.018732298509269e-06, "epoch": 9.824697486813527, "percentage": 49.12, "elapsed_time": "0:58:03", "remaining_time": "1:00:08", "throughput": 5544.9, "total_tokens": 19316752} {"current_steps": 31670, "total_steps": 64460, "loss": 0.2319, "lr": 6.017406851099338e-06, "epoch": 9.826248836487744, "percentage": 49.13, "elapsed_time": "0:58:04", "remaining_time": "1:00:07", "throughput": 5544.93, "total_tokens": 19319536} {"current_steps": 31675, "total_steps": 64460, "loss": 0.2354, "lr": 6.0160813291014375e-06, "epoch": 9.82780018616196, "percentage": 49.14, "elapsed_time": "0:58:04", "remaining_time": "1:00:06", "throughput": 5545.01, "total_tokens": 19322704} {"current_steps": 31680, "total_steps": 64460, "loss": 0.227, "lr": 6.014755732612742e-06, "epoch": 9.829351535836178, "percentage": 49.15, "elapsed_time": "0:58:05", "remaining_time": "1:00:06", "throughput": 5544.96, "total_tokens": 19325552} {"current_steps": 31685, "total_steps": 64460, "loss": 0.2303, "lr": 6.013430061730435e-06, "epoch": 9.830902885510394, "percentage": 49.15, "elapsed_time": "0:58:05", "remaining_time": "1:00:05", "throughput": 5544.91, "total_tokens": 19328112} {"current_steps": 31690, "total_steps": 64460, "loss": 0.2392, "lr": 6.012104316551704e-06, "epoch": 9.83245423518461, "percentage": 49.16, "elapsed_time": "0:58:06", "remaining_time": "1:00:05", "throughput": 5545.14, "total_tokens": 19332880} {"current_steps": 31695, "total_steps": 64460, "loss": 0.2266, "lr": 6.010778497173743e-06, "epoch": 9.834005584858827, "percentage": 49.17, "elapsed_time": "0:58:06", "remaining_time": "1:00:04", "throughput": 5545.1, "total_tokens": 19335376} {"current_steps": 31700, "total_steps": 64460, "loss": 0.2359, "lr": 6.009452603693747e-06, "epoch": 9.835556934533043, "percentage": 49.18, "elapsed_time": "0:58:07", "remaining_time": "1:00:04", "throughput": 5545.23, "total_tokens": 19339376} {"current_steps": 31705, "total_steps": 64460, "loss": 0.2405, "lr": 6.008126636208922e-06, "epoch": 9.837108284207261, "percentage": 49.19, "elapsed_time": "0:58:08", "remaining_time": "1:00:03", "throughput": 5545.2, "total_tokens": 19341840} {"current_steps": 31710, "total_steps": 64460, "loss": 0.2333, "lr": 6.006800594816478e-06, "epoch": 9.838659633881477, "percentage": 49.19, "elapsed_time": "0:58:08", "remaining_time": "1:00:02", "throughput": 5545.23, "total_tokens": 19344624} {"current_steps": 31715, "total_steps": 64460, "loss": 0.2318, "lr": 6.005474479613625e-06, "epoch": 9.840210983555693, "percentage": 49.2, "elapsed_time": "0:58:09", "remaining_time": "1:00:02", "throughput": 5545.37, "total_tokens": 19348016} {"current_steps": 31720, "total_steps": 64460, "loss": 0.214, "lr": 6.004148290697589e-06, "epoch": 9.84176233322991, "percentage": 49.21, "elapsed_time": "0:58:09", "remaining_time": "1:00:01", "throughput": 5545.49, "total_tokens": 19351408} {"current_steps": 31725, "total_steps": 64460, "loss": 0.237, "lr": 6.002822028165591e-06, "epoch": 9.843313682904126, "percentage": 49.22, "elapsed_time": "0:58:10", "remaining_time": "1:00:01", "throughput": 5545.66, "total_tokens": 19355312} {"current_steps": 31730, "total_steps": 64460, "loss": 0.2352, "lr": 6.001495692114863e-06, "epoch": 9.844865032578344, "percentage": 49.22, "elapsed_time": "0:58:10", "remaining_time": "1:00:00", "throughput": 5545.61, "total_tokens": 19357872} {"current_steps": 31735, "total_steps": 64460, "loss": 0.226, "lr": 6.000169282642641e-06, "epoch": 9.84641638225256, "percentage": 49.23, "elapsed_time": "0:58:11", "remaining_time": "1:00:00", "throughput": 5545.52, "total_tokens": 19360112} {"current_steps": 31740, "total_steps": 64460, "loss": 0.2275, "lr": 5.998842799846168e-06, "epoch": 9.847967731926776, "percentage": 49.24, "elapsed_time": "0:58:11", "remaining_time": "0:59:59", "throughput": 5545.63, "total_tokens": 19363280} {"current_steps": 31745, "total_steps": 64460, "loss": 0.2238, "lr": 5.997516243822689e-06, "epoch": 9.849519081600993, "percentage": 49.25, "elapsed_time": "0:58:12", "remaining_time": "0:59:58", "throughput": 5545.66, "total_tokens": 19366064} {"current_steps": 31750, "total_steps": 64460, "loss": 0.2434, "lr": 5.996189614669457e-06, "epoch": 9.85107043127521, "percentage": 49.26, "elapsed_time": "0:58:12", "remaining_time": "0:59:58", "throughput": 5545.75, "total_tokens": 19369520} {"current_steps": 31755, "total_steps": 64460, "loss": 0.229, "lr": 5.994862912483729e-06, "epoch": 9.852621780949425, "percentage": 49.26, "elapsed_time": "0:58:13", "remaining_time": "0:59:57", "throughput": 5545.75, "total_tokens": 19372176} {"current_steps": 31760, "total_steps": 64460, "loss": 0.234, "lr": 5.99353613736277e-06, "epoch": 9.854173130623643, "percentage": 49.27, "elapsed_time": "0:58:13", "remaining_time": "0:59:57", "throughput": 5545.8, "total_tokens": 19375632} {"current_steps": 31765, "total_steps": 64460, "loss": 0.216, "lr": 5.992209289403845e-06, "epoch": 9.855724480297859, "percentage": 49.28, "elapsed_time": "0:58:14", "remaining_time": "0:59:56", "throughput": 5545.79, "total_tokens": 19378320} {"current_steps": 31770, "total_steps": 64460, "loss": 0.2391, "lr": 5.990882368704232e-06, "epoch": 9.857275829972076, "percentage": 49.29, "elapsed_time": "0:58:14", "remaining_time": "0:59:55", "throughput": 5545.8, "total_tokens": 19381328} {"current_steps": 31775, "total_steps": 64460, "loss": 0.2285, "lr": 5.989555375361206e-06, "epoch": 9.858827179646292, "percentage": 49.29, "elapsed_time": "0:58:15", "remaining_time": "0:59:55", "throughput": 5545.81, "total_tokens": 19384496} {"current_steps": 31780, "total_steps": 64460, "loss": 0.2303, "lr": 5.988228309472053e-06, "epoch": 9.860378529320508, "percentage": 49.3, "elapsed_time": "0:58:15", "remaining_time": "0:59:54", "throughput": 5545.84, "total_tokens": 19387664} {"current_steps": 31785, "total_steps": 64460, "loss": 0.2271, "lr": 5.986901171134063e-06, "epoch": 9.861929878994726, "percentage": 49.31, "elapsed_time": "0:58:16", "remaining_time": "0:59:54", "throughput": 5545.86, "total_tokens": 19390768} {"current_steps": 31790, "total_steps": 64460, "loss": 0.2285, "lr": 5.985573960444529e-06, "epoch": 9.863481228668942, "percentage": 49.32, "elapsed_time": "0:58:16", "remaining_time": "0:59:53", "throughput": 5545.71, "total_tokens": 19393008} {"current_steps": 31795, "total_steps": 64460, "loss": 0.2206, "lr": 5.984246677500755e-06, "epoch": 9.865032578343158, "percentage": 49.33, "elapsed_time": "0:58:17", "remaining_time": "0:59:53", "throughput": 5545.71, "total_tokens": 19395920} {"current_steps": 31800, "total_steps": 64460, "loss": 0.2265, "lr": 5.982919322400044e-06, "epoch": 9.866583928017375, "percentage": 49.33, "elapsed_time": "0:58:18", "remaining_time": "0:59:52", "throughput": 5545.75, "total_tokens": 19399120} {"current_steps": 31805, "total_steps": 64460, "loss": 0.2374, "lr": 5.981591895239705e-06, "epoch": 9.868135277691591, "percentage": 49.34, "elapsed_time": "0:58:18", "remaining_time": "0:59:52", "throughput": 5545.93, "total_tokens": 19403312} {"current_steps": 31810, "total_steps": 64460, "loss": 0.2196, "lr": 5.980264396117057e-06, "epoch": 9.869686627365809, "percentage": 49.35, "elapsed_time": "0:58:19", "remaining_time": "0:59:51", "throughput": 5545.96, "total_tokens": 19406288} {"current_steps": 31815, "total_steps": 64460, "loss": 0.2157, "lr": 5.978936825129422e-06, "epoch": 9.871237977040025, "percentage": 49.36, "elapsed_time": "0:58:19", "remaining_time": "0:59:51", "throughput": 5546.01, "total_tokens": 19409392} {"current_steps": 31820, "total_steps": 64460, "loss": 0.2242, "lr": 5.977609182374124e-06, "epoch": 9.87278932671424, "percentage": 49.36, "elapsed_time": "0:58:20", "remaining_time": "0:59:50", "throughput": 5545.9, "total_tokens": 19411728} {"current_steps": 31825, "total_steps": 64460, "loss": 0.2149, "lr": 5.976281467948498e-06, "epoch": 9.874340676388458, "percentage": 49.37, "elapsed_time": "0:58:20", "remaining_time": "0:59:49", "throughput": 5545.98, "total_tokens": 19414896} {"current_steps": 31830, "total_steps": 64460, "loss": 0.2375, "lr": 5.974953681949878e-06, "epoch": 9.875892026062674, "percentage": 49.38, "elapsed_time": "0:58:21", "remaining_time": "0:59:49", "throughput": 5545.96, "total_tokens": 19417488} {"current_steps": 31835, "total_steps": 64460, "loss": 0.2311, "lr": 5.973625824475609e-06, "epoch": 9.877443375736892, "percentage": 49.39, "elapsed_time": "0:58:21", "remaining_time": "0:59:48", "throughput": 5545.99, "total_tokens": 19420400} {"current_steps": 31840, "total_steps": 64460, "loss": 0.2412, "lr": 5.9722978956230385e-06, "epoch": 9.878994725411108, "percentage": 49.39, "elapsed_time": "0:58:22", "remaining_time": "0:59:48", "throughput": 5546.04, "total_tokens": 19423536} {"current_steps": 31845, "total_steps": 64460, "loss": 0.2368, "lr": 5.970969895489517e-06, "epoch": 9.880546075085324, "percentage": 49.4, "elapsed_time": "0:58:22", "remaining_time": "0:59:47", "throughput": 5546.04, "total_tokens": 19426128} {"current_steps": 31850, "total_steps": 64460, "loss": 0.2509, "lr": 5.969641824172404e-06, "epoch": 9.882097424759541, "percentage": 49.41, "elapsed_time": "0:58:23", "remaining_time": "0:59:46", "throughput": 5546.03, "total_tokens": 19428784} {"current_steps": 31855, "total_steps": 64460, "loss": 0.2378, "lr": 5.968313681769064e-06, "epoch": 9.883648774433757, "percentage": 49.42, "elapsed_time": "0:58:23", "remaining_time": "0:59:46", "throughput": 5546.09, "total_tokens": 19432336} {"current_steps": 31860, "total_steps": 64460, "loss": 0.2309, "lr": 5.966985468376864e-06, "epoch": 9.885200124107975, "percentage": 49.43, "elapsed_time": "0:58:24", "remaining_time": "0:59:45", "throughput": 5545.99, "total_tokens": 19434640} {"current_steps": 31865, "total_steps": 64460, "loss": 0.2369, "lr": 5.965657184093176e-06, "epoch": 9.88675147378219, "percentage": 49.43, "elapsed_time": "0:58:24", "remaining_time": "0:59:45", "throughput": 5546.05, "total_tokens": 19437616} {"current_steps": 31870, "total_steps": 64460, "loss": 0.239, "lr": 5.964328829015385e-06, "epoch": 9.888302823456407, "percentage": 49.44, "elapsed_time": "0:58:25", "remaining_time": "0:59:44", "throughput": 5546.02, "total_tokens": 19440592} {"current_steps": 31875, "total_steps": 64460, "loss": 0.2356, "lr": 5.963000403240869e-06, "epoch": 9.889854173130624, "percentage": 49.45, "elapsed_time": "0:58:25", "remaining_time": "0:59:43", "throughput": 5546.2, "total_tokens": 19444304} {"current_steps": 31880, "total_steps": 64460, "loss": 0.2334, "lr": 5.961671906867022e-06, "epoch": 9.89140552280484, "percentage": 49.46, "elapsed_time": "0:58:26", "remaining_time": "0:59:43", "throughput": 5546.06, "total_tokens": 19446384} {"current_steps": 31885, "total_steps": 64460, "loss": 0.2294, "lr": 5.9603433399912345e-06, "epoch": 9.892956872479056, "percentage": 49.46, "elapsed_time": "0:58:26", "remaining_time": "0:59:42", "throughput": 5546.25, "total_tokens": 19450640} {"current_steps": 31890, "total_steps": 64460, "loss": 0.2234, "lr": 5.959014702710908e-06, "epoch": 9.894508222153274, "percentage": 49.47, "elapsed_time": "0:58:27", "remaining_time": "0:59:42", "throughput": 5546.36, "total_tokens": 19454288} {"current_steps": 31895, "total_steps": 64460, "loss": 0.2366, "lr": 5.957685995123449e-06, "epoch": 9.89605957182749, "percentage": 49.48, "elapsed_time": "0:58:28", "remaining_time": "0:59:41", "throughput": 5546.38, "total_tokens": 19457040} {"current_steps": 31900, "total_steps": 64460, "loss": 0.238, "lr": 5.956357217326265e-06, "epoch": 9.897610921501707, "percentage": 49.49, "elapsed_time": "0:58:28", "remaining_time": "0:59:41", "throughput": 5546.38, "total_tokens": 19459696} {"current_steps": 31905, "total_steps": 64460, "loss": 0.2234, "lr": 5.955028369416771e-06, "epoch": 9.899162271175923, "percentage": 49.5, "elapsed_time": "0:58:29", "remaining_time": "0:59:40", "throughput": 5546.33, "total_tokens": 19462192} {"current_steps": 31910, "total_steps": 64460, "loss": 0.2233, "lr": 5.953699451492389e-06, "epoch": 9.900713620850139, "percentage": 49.5, "elapsed_time": "0:58:29", "remaining_time": "0:59:40", "throughput": 5546.68, "total_tokens": 19468368} {"current_steps": 31915, "total_steps": 64460, "loss": 0.2338, "lr": 5.952370463650544e-06, "epoch": 9.902264970524357, "percentage": 49.51, "elapsed_time": "0:58:30", "remaining_time": "0:59:39", "throughput": 5546.58, "total_tokens": 19470800} {"current_steps": 31920, "total_steps": 64460, "loss": 0.2198, "lr": 5.951041405988666e-06, "epoch": 9.903816320198572, "percentage": 49.52, "elapsed_time": "0:58:30", "remaining_time": "0:59:39", "throughput": 5546.67, "total_tokens": 19474192} {"current_steps": 31925, "total_steps": 64460, "loss": 0.2261, "lr": 5.949712278604192e-06, "epoch": 9.905367669872788, "percentage": 49.53, "elapsed_time": "0:58:31", "remaining_time": "0:59:38", "throughput": 5546.63, "total_tokens": 19476624} {"current_steps": 31930, "total_steps": 64460, "loss": 0.2356, "lr": 5.94838308159456e-06, "epoch": 9.906919019547006, "percentage": 49.53, "elapsed_time": "0:58:31", "remaining_time": "0:59:37", "throughput": 5546.56, "total_tokens": 19479024} {"current_steps": 31935, "total_steps": 64460, "loss": 0.2292, "lr": 5.947053815057219e-06, "epoch": 9.908470369221222, "percentage": 49.54, "elapsed_time": "0:58:32", "remaining_time": "0:59:37", "throughput": 5546.55, "total_tokens": 19481552} {"current_steps": 31940, "total_steps": 64460, "loss": 0.2321, "lr": 5.945724479089616e-06, "epoch": 9.91002171889544, "percentage": 49.55, "elapsed_time": "0:58:32", "remaining_time": "0:59:36", "throughput": 5546.57, "total_tokens": 19484336} {"current_steps": 31945, "total_steps": 64460, "loss": 0.2296, "lr": 5.944395073789212e-06, "epoch": 9.911573068569655, "percentage": 49.56, "elapsed_time": "0:58:33", "remaining_time": "0:59:36", "throughput": 5546.53, "total_tokens": 19486768} {"current_steps": 31950, "total_steps": 64460, "loss": 0.2273, "lr": 5.9430655992534654e-06, "epoch": 9.913124418243871, "percentage": 49.57, "elapsed_time": "0:58:33", "remaining_time": "0:59:35", "throughput": 5546.55, "total_tokens": 19489648} {"current_steps": 31955, "total_steps": 64460, "loss": 0.2365, "lr": 5.9417360555798434e-06, "epoch": 9.914675767918089, "percentage": 49.57, "elapsed_time": "0:58:34", "remaining_time": "0:59:34", "throughput": 5546.6, "total_tokens": 19492784} {"current_steps": 31960, "total_steps": 64460, "loss": 0.2322, "lr": 5.940406442865816e-06, "epoch": 9.916227117592305, "percentage": 49.58, "elapsed_time": "0:58:34", "remaining_time": "0:59:34", "throughput": 5546.56, "total_tokens": 19495280} {"current_steps": 31965, "total_steps": 64460, "loss": 0.229, "lr": 5.939076761208861e-06, "epoch": 9.917778467266523, "percentage": 49.59, "elapsed_time": "0:58:35", "remaining_time": "0:59:33", "throughput": 5546.76, "total_tokens": 19499280} {"current_steps": 31970, "total_steps": 64460, "loss": 0.2262, "lr": 5.937747010706457e-06, "epoch": 9.919329816940738, "percentage": 49.6, "elapsed_time": "0:58:35", "remaining_time": "0:59:33", "throughput": 5546.94, "total_tokens": 19502960} {"current_steps": 31975, "total_steps": 64460, "loss": 0.2259, "lr": 5.936417191456094e-06, "epoch": 9.920881166614954, "percentage": 49.6, "elapsed_time": "0:58:36", "remaining_time": "0:59:32", "throughput": 5547.03, "total_tokens": 19507248} {"current_steps": 31980, "total_steps": 64460, "loss": 0.2281, "lr": 5.935087303555263e-06, "epoch": 9.922432516289172, "percentage": 49.61, "elapsed_time": "0:58:37", "remaining_time": "0:59:32", "throughput": 5547.08, "total_tokens": 19510128} {"current_steps": 31985, "total_steps": 64460, "loss": 0.22, "lr": 5.933757347101459e-06, "epoch": 9.923983865963388, "percentage": 49.62, "elapsed_time": "0:58:37", "remaining_time": "0:59:31", "throughput": 5547.04, "total_tokens": 19512560} {"current_steps": 31990, "total_steps": 64460, "loss": 0.229, "lr": 5.932427322192182e-06, "epoch": 9.925535215637606, "percentage": 49.63, "elapsed_time": "0:58:38", "remaining_time": "0:59:31", "throughput": 5547.05, "total_tokens": 19516080} {"current_steps": 31995, "total_steps": 64460, "loss": 0.2284, "lr": 5.931097228924943e-06, "epoch": 9.927086565311821, "percentage": 49.64, "elapsed_time": "0:58:38", "remaining_time": "0:59:30", "throughput": 5547.14, "total_tokens": 19519248} {"current_steps": 32000, "total_steps": 64460, "loss": 0.24, "lr": 5.92976706739725e-06, "epoch": 9.928637914986037, "percentage": 49.64, "elapsed_time": "0:58:39", "remaining_time": "0:59:29", "throughput": 5547.24, "total_tokens": 19522448} {"current_steps": 32005, "total_steps": 64460, "loss": 0.2274, "lr": 5.9284368377066215e-06, "epoch": 9.930189264660255, "percentage": 49.65, "elapsed_time": "0:58:39", "remaining_time": "0:59:29", "throughput": 5547.3, "total_tokens": 19525584} {"current_steps": 32010, "total_steps": 64460, "loss": 0.2312, "lr": 5.927106539950579e-06, "epoch": 9.93174061433447, "percentage": 49.66, "elapsed_time": "0:58:40", "remaining_time": "0:59:28", "throughput": 5547.36, "total_tokens": 19528688} {"current_steps": 32015, "total_steps": 64460, "loss": 0.2338, "lr": 5.925776174226648e-06, "epoch": 9.933291964008687, "percentage": 49.67, "elapsed_time": "0:58:40", "remaining_time": "0:59:28", "throughput": 5547.3, "total_tokens": 19531088} {"current_steps": 32020, "total_steps": 64460, "loss": 0.232, "lr": 5.924445740632361e-06, "epoch": 9.934843313682904, "percentage": 49.67, "elapsed_time": "0:58:41", "remaining_time": "0:59:27", "throughput": 5547.25, "total_tokens": 19533520} {"current_steps": 32025, "total_steps": 64460, "loss": 0.2337, "lr": 5.9231152392652534e-06, "epoch": 9.93639466335712, "percentage": 49.68, "elapsed_time": "0:58:41", "remaining_time": "0:59:26", "throughput": 5547.32, "total_tokens": 19536720} {"current_steps": 32030, "total_steps": 64460, "loss": 0.234, "lr": 5.921784670222867e-06, "epoch": 9.937946013031338, "percentage": 49.69, "elapsed_time": "0:58:42", "remaining_time": "0:59:26", "throughput": 5547.19, "total_tokens": 19539024} {"current_steps": 32035, "total_steps": 64460, "loss": 0.2378, "lr": 5.92045403360275e-06, "epoch": 9.939497362705554, "percentage": 49.7, "elapsed_time": "0:58:42", "remaining_time": "0:59:25", "throughput": 5547.1, "total_tokens": 19541360} {"current_steps": 32040, "total_steps": 64460, "loss": 0.2418, "lr": 5.919123329502452e-06, "epoch": 9.94104871237977, "percentage": 49.71, "elapsed_time": "0:58:43", "remaining_time": "0:59:25", "throughput": 5547.05, "total_tokens": 19544208} {"current_steps": 32045, "total_steps": 64460, "loss": 0.2261, "lr": 5.917792558019531e-06, "epoch": 9.942600062053987, "percentage": 49.71, "elapsed_time": "0:58:43", "remaining_time": "0:59:24", "throughput": 5547.26, "total_tokens": 19548240} {"current_steps": 32050, "total_steps": 64460, "loss": 0.2342, "lr": 5.916461719251545e-06, "epoch": 9.944151411728203, "percentage": 49.72, "elapsed_time": "0:58:44", "remaining_time": "0:59:24", "throughput": 5547.2, "total_tokens": 19550768} {"current_steps": 32055, "total_steps": 64460, "loss": 0.2336, "lr": 5.915130813296064e-06, "epoch": 9.945702761402421, "percentage": 49.73, "elapsed_time": "0:58:44", "remaining_time": "0:59:23", "throughput": 5547.18, "total_tokens": 19553360} {"current_steps": 32060, "total_steps": 64460, "loss": 0.2264, "lr": 5.913799840250656e-06, "epoch": 9.947254111076637, "percentage": 49.74, "elapsed_time": "0:58:45", "remaining_time": "0:59:22", "throughput": 5547.27, "total_tokens": 19556304} {"current_steps": 32065, "total_steps": 64460, "loss": 0.2369, "lr": 5.9124688002129e-06, "epoch": 9.948805460750853, "percentage": 49.74, "elapsed_time": "0:58:45", "remaining_time": "0:59:22", "throughput": 5547.17, "total_tokens": 19558512} {"current_steps": 32070, "total_steps": 64460, "loss": 0.2357, "lr": 5.911137693280376e-06, "epoch": 9.95035681042507, "percentage": 49.75, "elapsed_time": "0:58:46", "remaining_time": "0:59:21", "throughput": 5547.07, "total_tokens": 19561296} {"current_steps": 32075, "total_steps": 64460, "loss": 0.2339, "lr": 5.909806519550669e-06, "epoch": 9.951908160099286, "percentage": 49.76, "elapsed_time": "0:58:46", "remaining_time": "0:59:21", "throughput": 5547.18, "total_tokens": 19564784} {"current_steps": 32080, "total_steps": 64460, "loss": 0.2212, "lr": 5.9084752791213706e-06, "epoch": 9.953459509773502, "percentage": 49.77, "elapsed_time": "0:58:47", "remaining_time": "0:59:20", "throughput": 5547.19, "total_tokens": 19567536} {"current_steps": 32085, "total_steps": 64460, "loss": 0.2288, "lr": 5.907143972090076e-06, "epoch": 9.95501085944772, "percentage": 49.78, "elapsed_time": "0:58:47", "remaining_time": "0:59:19", "throughput": 5547.24, "total_tokens": 19570480} {"current_steps": 32090, "total_steps": 64460, "loss": 0.2349, "lr": 5.905812598554387e-06, "epoch": 9.956562209121936, "percentage": 49.78, "elapsed_time": "0:58:48", "remaining_time": "0:59:19", "throughput": 5547.23, "total_tokens": 19573200} {"current_steps": 32095, "total_steps": 64460, "loss": 0.2231, "lr": 5.904481158611906e-06, "epoch": 9.958113558796153, "percentage": 49.79, "elapsed_time": "0:58:48", "remaining_time": "0:59:18", "throughput": 5547.23, "total_tokens": 19576112} {"current_steps": 32100, "total_steps": 64460, "loss": 0.226, "lr": 5.903149652360249e-06, "epoch": 9.95966490847037, "percentage": 49.8, "elapsed_time": "0:58:49", "remaining_time": "0:59:18", "throughput": 5547.28, "total_tokens": 19579440} {"current_steps": 32105, "total_steps": 64460, "loss": 0.2299, "lr": 5.901818079897024e-06, "epoch": 9.961216258144585, "percentage": 49.81, "elapsed_time": "0:58:50", "remaining_time": "0:59:17", "throughput": 5547.1, "total_tokens": 19581552} {"current_steps": 32110, "total_steps": 64460, "loss": 0.2282, "lr": 5.900486441319857e-06, "epoch": 9.962767607818803, "percentage": 49.81, "elapsed_time": "0:58:50", "remaining_time": "0:59:16", "throughput": 5547.11, "total_tokens": 19584208} {"current_steps": 32115, "total_steps": 64460, "loss": 0.2408, "lr": 5.899154736726369e-06, "epoch": 9.964318957493019, "percentage": 49.82, "elapsed_time": "0:58:51", "remaining_time": "0:59:16", "throughput": 5547.12, "total_tokens": 19587440} {"current_steps": 32120, "total_steps": 64460, "loss": 0.2328, "lr": 5.89782296621419e-06, "epoch": 9.965870307167236, "percentage": 49.83, "elapsed_time": "0:58:51", "remaining_time": "0:59:15", "throughput": 5547.11, "total_tokens": 19590096} {"current_steps": 32125, "total_steps": 64460, "loss": 0.2275, "lr": 5.896491129880958e-06, "epoch": 9.967421656841452, "percentage": 49.84, "elapsed_time": "0:58:52", "remaining_time": "0:59:15", "throughput": 5547.1, "total_tokens": 19592688} {"current_steps": 32130, "total_steps": 64460, "loss": 0.2429, "lr": 5.89515922782431e-06, "epoch": 9.968973006515668, "percentage": 49.84, "elapsed_time": "0:58:52", "remaining_time": "0:59:14", "throughput": 5547.27, "total_tokens": 19596464} {"current_steps": 32135, "total_steps": 64460, "loss": 0.2302, "lr": 5.89382726014189e-06, "epoch": 9.970524356189886, "percentage": 49.85, "elapsed_time": "0:58:53", "remaining_time": "0:59:14", "throughput": 5547.28, "total_tokens": 19599504} {"current_steps": 32140, "total_steps": 64460, "loss": 0.2285, "lr": 5.892495226931348e-06, "epoch": 9.972075705864102, "percentage": 49.86, "elapsed_time": "0:58:53", "remaining_time": "0:59:13", "throughput": 5547.35, "total_tokens": 19602544} {"current_steps": 32145, "total_steps": 64460, "loss": 0.2311, "lr": 5.8911631282903355e-06, "epoch": 9.973627055538318, "percentage": 49.87, "elapsed_time": "0:58:54", "remaining_time": "0:59:12", "throughput": 5547.28, "total_tokens": 19605200} {"current_steps": 32150, "total_steps": 64460, "loss": 0.2309, "lr": 5.889830964316514e-06, "epoch": 9.975178405212535, "percentage": 49.88, "elapsed_time": "0:58:54", "remaining_time": "0:59:12", "throughput": 5547.27, "total_tokens": 19607952} {"current_steps": 32155, "total_steps": 64460, "loss": 0.2452, "lr": 5.888498735107545e-06, "epoch": 9.976729754886751, "percentage": 49.88, "elapsed_time": "0:58:55", "remaining_time": "0:59:11", "throughput": 5547.4, "total_tokens": 19611248} {"current_steps": 32160, "total_steps": 64460, "loss": 0.2305, "lr": 5.8871664407610984e-06, "epoch": 9.978281104560969, "percentage": 49.89, "elapsed_time": "0:58:55", "remaining_time": "0:59:11", "throughput": 5547.32, "total_tokens": 19613520} {"current_steps": 32165, "total_steps": 64460, "loss": 0.2253, "lr": 5.885834081374845e-06, "epoch": 9.979832454235185, "percentage": 49.9, "elapsed_time": "0:58:56", "remaining_time": "0:59:10", "throughput": 5547.32, "total_tokens": 19616304} {"current_steps": 32170, "total_steps": 64460, "loss": 0.2291, "lr": 5.8845016570464645e-06, "epoch": 9.9813838039094, "percentage": 49.91, "elapsed_time": "0:58:56", "remaining_time": "0:59:09", "throughput": 5547.36, "total_tokens": 19619184} {"current_steps": 32175, "total_steps": 64460, "loss": 0.2341, "lr": 5.883169167873638e-06, "epoch": 9.982935153583618, "percentage": 49.91, "elapsed_time": "0:58:57", "remaining_time": "0:59:09", "throughput": 5547.47, "total_tokens": 19622832} {"current_steps": 32180, "total_steps": 64460, "loss": 0.2225, "lr": 5.881836613954052e-06, "epoch": 9.984486503257834, "percentage": 49.92, "elapsed_time": "0:58:57", "remaining_time": "0:59:08", "throughput": 5547.43, "total_tokens": 19625552} {"current_steps": 32185, "total_steps": 64460, "loss": 0.2277, "lr": 5.8805039953854e-06, "epoch": 9.986037852932052, "percentage": 49.93, "elapsed_time": "0:58:58", "remaining_time": "0:59:08", "throughput": 5547.6, "total_tokens": 19629616} {"current_steps": 32190, "total_steps": 64460, "loss": 0.2285, "lr": 5.8791713122653785e-06, "epoch": 9.987589202606268, "percentage": 49.94, "elapsed_time": "0:58:58", "remaining_time": "0:59:07", "throughput": 5547.7, "total_tokens": 19633008} {"current_steps": 32195, "total_steps": 64460, "loss": 0.2329, "lr": 5.87783856469169e-06, "epoch": 9.989140552280483, "percentage": 49.95, "elapsed_time": "0:58:59", "remaining_time": "0:59:07", "throughput": 5547.71, "total_tokens": 19635760} {"current_steps": 32200, "total_steps": 64460, "loss": 0.2223, "lr": 5.876505752762038e-06, "epoch": 9.990691901954701, "percentage": 49.95, "elapsed_time": "0:58:59", "remaining_time": "0:59:06", "throughput": 5547.71, "total_tokens": 19638640} {"current_steps": 32205, "total_steps": 64460, "loss": 0.233, "lr": 5.875172876574137e-06, "epoch": 9.992243251628917, "percentage": 49.96, "elapsed_time": "0:59:00", "remaining_time": "0:59:05", "throughput": 5547.67, "total_tokens": 19641264} {"current_steps": 32210, "total_steps": 64460, "loss": 0.2228, "lr": 5.873839936225699e-06, "epoch": 9.993794601303133, "percentage": 49.97, "elapsed_time": "0:59:00", "remaining_time": "0:59:05", "throughput": 5547.66, "total_tokens": 19643856} {"current_steps": 32215, "total_steps": 64460, "loss": 0.2307, "lr": 5.872506931814447e-06, "epoch": 9.99534595097735, "percentage": 49.98, "elapsed_time": "0:59:01", "remaining_time": "0:59:04", "throughput": 5547.72, "total_tokens": 19646992} {"current_steps": 32220, "total_steps": 64460, "loss": 0.2234, "lr": 5.8711738634381045e-06, "epoch": 9.996897300651566, "percentage": 49.98, "elapsed_time": "0:59:01", "remaining_time": "0:59:04", "throughput": 5547.65, "total_tokens": 19649392} {"current_steps": 32225, "total_steps": 64460, "loss": 0.2374, "lr": 5.869840731194401e-06, "epoch": 9.998448650325784, "percentage": 49.99, "elapsed_time": "0:59:02", "remaining_time": "0:59:03", "throughput": 5547.72, "total_tokens": 19652464} {"current_steps": 32230, "total_steps": 64460, "loss": 0.248, "lr": 5.8685075351810725e-06, "epoch": 10.0, "percentage": 50.0, "elapsed_time": "0:59:03", "remaining_time": "0:59:03", "throughput": 5547.73, "total_tokens": 19655824} {"current_steps": 32230, "total_steps": 64460, "eval_loss": 0.2318788319826126, "epoch": 10.0, "percentage": 50.0, "elapsed_time": "0:59:37", "remaining_time": "0:59:37", "throughput": 5494.29, "total_tokens": 19655824} {"current_steps": 32235, "total_steps": 64460, "loss": 0.2324, "lr": 5.867174275495856e-06, "epoch": 10.001551349674216, "percentage": 50.01, "elapsed_time": "0:59:41", "remaining_time": "0:59:40", "throughput": 5488.55, "total_tokens": 19659056} {"current_steps": 32240, "total_steps": 64460, "loss": 0.2261, "lr": 5.865840952236497e-06, "epoch": 10.003102699348434, "percentage": 50.02, "elapsed_time": "0:59:42", "remaining_time": "0:59:40", "throughput": 5488.69, "total_tokens": 19662736} {"current_steps": 32245, "total_steps": 64460, "loss": 0.2297, "lr": 5.864507565500742e-06, "epoch": 10.00465404902265, "percentage": 50.02, "elapsed_time": "0:59:42", "remaining_time": "0:59:39", "throughput": 5488.54, "total_tokens": 19664944} {"current_steps": 32250, "total_steps": 64460, "loss": 0.2287, "lr": 5.8631741153863455e-06, "epoch": 10.006205398696867, "percentage": 50.03, "elapsed_time": "0:59:43", "remaining_time": "0:59:38", "throughput": 5488.43, "total_tokens": 19667472} {"current_steps": 32255, "total_steps": 64460, "loss": 0.2203, "lr": 5.8618406019910655e-06, "epoch": 10.007756748371083, "percentage": 50.04, "elapsed_time": "0:59:44", "remaining_time": "0:59:38", "throughput": 5488.44, "total_tokens": 19670576} {"current_steps": 32260, "total_steps": 64460, "loss": 0.2175, "lr": 5.860507025412663e-06, "epoch": 10.009308098045299, "percentage": 50.05, "elapsed_time": "0:59:44", "remaining_time": "0:59:37", "throughput": 5488.53, "total_tokens": 19673840} {"current_steps": 32265, "total_steps": 64460, "loss": 0.2347, "lr": 5.859173385748907e-06, "epoch": 10.010859447719517, "percentage": 50.05, "elapsed_time": "0:59:45", "remaining_time": "0:59:37", "throughput": 5488.35, "total_tokens": 19676048} {"current_steps": 32270, "total_steps": 64460, "loss": 0.2392, "lr": 5.857839683097566e-06, "epoch": 10.012410797393732, "percentage": 50.06, "elapsed_time": "0:59:45", "remaining_time": "0:59:36", "throughput": 5488.38, "total_tokens": 19679600} {"current_steps": 32275, "total_steps": 64460, "loss": 0.2287, "lr": 5.856505917556418e-06, "epoch": 10.013962147067948, "percentage": 50.07, "elapsed_time": "0:59:46", "remaining_time": "0:59:36", "throughput": 5488.21, "total_tokens": 19681904} {"current_steps": 32280, "total_steps": 64460, "loss": 0.2267, "lr": 5.855172089223244e-06, "epoch": 10.015513496742166, "percentage": 50.08, "elapsed_time": "0:59:47", "remaining_time": "0:59:35", "throughput": 5488.41, "total_tokens": 19687024} {"current_steps": 32285, "total_steps": 64460, "loss": 0.2318, "lr": 5.853838198195829e-06, "epoch": 10.017064846416382, "percentage": 50.09, "elapsed_time": "0:59:47", "remaining_time": "0:59:35", "throughput": 5488.39, "total_tokens": 19689840} {"current_steps": 32290, "total_steps": 64460, "loss": 0.2246, "lr": 5.852504244571964e-06, "epoch": 10.0186161960906, "percentage": 50.09, "elapsed_time": "0:59:48", "remaining_time": "0:59:34", "throughput": 5488.33, "total_tokens": 19692240} {"current_steps": 32295, "total_steps": 64460, "loss": 0.2306, "lr": 5.8511702284494424e-06, "epoch": 10.020167545764815, "percentage": 50.1, "elapsed_time": "0:59:48", "remaining_time": "0:59:34", "throughput": 5488.28, "total_tokens": 19695280} {"current_steps": 32300, "total_steps": 64460, "loss": 0.2246, "lr": 5.849836149926064e-06, "epoch": 10.021718895439031, "percentage": 50.11, "elapsed_time": "0:59:49", "remaining_time": "0:59:33", "throughput": 5488.24, "total_tokens": 19697808} {"current_steps": 32305, "total_steps": 64460, "loss": 0.2261, "lr": 5.848502009099631e-06, "epoch": 10.023270245113249, "percentage": 50.12, "elapsed_time": "0:59:49", "remaining_time": "0:59:32", "throughput": 5488.23, "total_tokens": 19700656} {"current_steps": 32310, "total_steps": 64460, "loss": 0.2295, "lr": 5.847167806067952e-06, "epoch": 10.024821594787465, "percentage": 50.12, "elapsed_time": "0:59:50", "remaining_time": "0:59:32", "throughput": 5488.38, "total_tokens": 19704464} {"current_steps": 32315, "total_steps": 64460, "loss": 0.2273, "lr": 5.845833540928844e-06, "epoch": 10.026372944461682, "percentage": 50.13, "elapsed_time": "0:59:50", "remaining_time": "0:59:31", "throughput": 5488.45, "total_tokens": 19707600} {"current_steps": 32320, "total_steps": 64460, "loss": 0.2222, "lr": 5.844499213780119e-06, "epoch": 10.027924294135898, "percentage": 50.14, "elapsed_time": "0:59:51", "remaining_time": "0:59:31", "throughput": 5488.49, "total_tokens": 19710608} {"current_steps": 32325, "total_steps": 64460, "loss": 0.2322, "lr": 5.8431648247196025e-06, "epoch": 10.029475643810114, "percentage": 50.15, "elapsed_time": "0:59:51", "remaining_time": "0:59:30", "throughput": 5488.55, "total_tokens": 19713520} {"current_steps": 32330, "total_steps": 64460, "loss": 0.2356, "lr": 5.841830373845119e-06, "epoch": 10.031026993484332, "percentage": 50.16, "elapsed_time": "0:59:52", "remaining_time": "0:59:30", "throughput": 5488.54, "total_tokens": 19716048} {"current_steps": 32335, "total_steps": 64460, "loss": 0.2363, "lr": 5.840495861254501e-06, "epoch": 10.032578343158548, "percentage": 50.16, "elapsed_time": "0:59:52", "remaining_time": "0:59:29", "throughput": 5488.53, "total_tokens": 19718576} {"current_steps": 32340, "total_steps": 64460, "loss": 0.228, "lr": 5.839161287045583e-06, "epoch": 10.034129692832764, "percentage": 50.17, "elapsed_time": "0:59:53", "remaining_time": "0:59:28", "throughput": 5488.54, "total_tokens": 19721200} {"current_steps": 32345, "total_steps": 64460, "loss": 0.2357, "lr": 5.8378266513162055e-06, "epoch": 10.035681042506981, "percentage": 50.18, "elapsed_time": "0:59:53", "remaining_time": "0:59:28", "throughput": 5488.53, "total_tokens": 19723792} {"current_steps": 32350, "total_steps": 64460, "loss": 0.2307, "lr": 5.836491954164213e-06, "epoch": 10.037232392181197, "percentage": 50.19, "elapsed_time": "0:59:54", "remaining_time": "0:59:27", "throughput": 5488.42, "total_tokens": 19726320} {"current_steps": 32355, "total_steps": 64460, "loss": 0.2322, "lr": 5.835157195687456e-06, "epoch": 10.038783741855415, "percentage": 50.19, "elapsed_time": "0:59:54", "remaining_time": "0:59:27", "throughput": 5488.58, "total_tokens": 19730288} {"current_steps": 32360, "total_steps": 64460, "loss": 0.2318, "lr": 5.833822375983785e-06, "epoch": 10.04033509152963, "percentage": 50.2, "elapsed_time": "0:59:55", "remaining_time": "0:59:26", "throughput": 5488.64, "total_tokens": 19733808} {"current_steps": 32365, "total_steps": 64460, "loss": 0.2224, "lr": 5.83248749515106e-06, "epoch": 10.041886441203847, "percentage": 50.21, "elapsed_time": "0:59:55", "remaining_time": "0:59:25", "throughput": 5488.72, "total_tokens": 19736880} {"current_steps": 32370, "total_steps": 64460, "loss": 0.2258, "lr": 5.8311525532871445e-06, "epoch": 10.043437790878064, "percentage": 50.22, "elapsed_time": "0:59:56", "remaining_time": "0:59:25", "throughput": 5488.74, "total_tokens": 19739952} {"current_steps": 32375, "total_steps": 64460, "loss": 0.2232, "lr": 5.8298175504899035e-06, "epoch": 10.04498914055228, "percentage": 50.22, "elapsed_time": "0:59:56", "remaining_time": "0:59:24", "throughput": 5488.72, "total_tokens": 19742416} {"current_steps": 32380, "total_steps": 64460, "loss": 0.2251, "lr": 5.82848248685721e-06, "epoch": 10.046540490226498, "percentage": 50.23, "elapsed_time": "0:59:57", "remaining_time": "0:59:24", "throughput": 5488.67, "total_tokens": 19745040} {"current_steps": 32385, "total_steps": 64460, "loss": 0.243, "lr": 5.82714736248694e-06, "epoch": 10.048091839900714, "percentage": 50.24, "elapsed_time": "0:59:57", "remaining_time": "0:59:23", "throughput": 5488.72, "total_tokens": 19748048} {"current_steps": 32390, "total_steps": 64460, "loss": 0.2235, "lr": 5.8258121774769725e-06, "epoch": 10.04964318957493, "percentage": 50.25, "elapsed_time": "0:59:58", "remaining_time": "0:59:22", "throughput": 5488.76, "total_tokens": 19751024} {"current_steps": 32395, "total_steps": 64460, "loss": 0.2224, "lr": 5.824476931925195e-06, "epoch": 10.051194539249147, "percentage": 50.26, "elapsed_time": "0:59:58", "remaining_time": "0:59:22", "throughput": 5488.62, "total_tokens": 19753168} {"current_steps": 32400, "total_steps": 64460, "loss": 0.2164, "lr": 5.823141625929494e-06, "epoch": 10.052745888923363, "percentage": 50.26, "elapsed_time": "0:59:59", "remaining_time": "0:59:21", "throughput": 5488.65, "total_tokens": 19756112} {"current_steps": 32405, "total_steps": 64460, "loss": 0.2304, "lr": 5.821806259587764e-06, "epoch": 10.054297238597579, "percentage": 50.27, "elapsed_time": "0:59:59", "remaining_time": "0:59:21", "throughput": 5488.68, "total_tokens": 19759184} {"current_steps": 32410, "total_steps": 64460, "loss": 0.2352, "lr": 5.820470832997904e-06, "epoch": 10.055848588271797, "percentage": 50.28, "elapsed_time": "1:00:00", "remaining_time": "0:59:20", "throughput": 5488.87, "total_tokens": 19763024} {"current_steps": 32415, "total_steps": 64460, "loss": 0.2363, "lr": 5.819135346257816e-06, "epoch": 10.057399937946013, "percentage": 50.29, "elapsed_time": "1:00:01", "remaining_time": "0:59:19", "throughput": 5488.87, "total_tokens": 19765680} {"current_steps": 32420, "total_steps": 64460, "loss": 0.229, "lr": 5.817799799465407e-06, "epoch": 10.05895128762023, "percentage": 50.29, "elapsed_time": "1:00:01", "remaining_time": "0:59:19", "throughput": 5488.86, "total_tokens": 19768336} {"current_steps": 32425, "total_steps": 64460, "loss": 0.2249, "lr": 5.8164641927185896e-06, "epoch": 10.060502637294446, "percentage": 50.3, "elapsed_time": "1:00:02", "remaining_time": "0:59:18", "throughput": 5488.89, "total_tokens": 19771216} {"current_steps": 32430, "total_steps": 64460, "loss": 0.2311, "lr": 5.815128526115277e-06, "epoch": 10.062053986968662, "percentage": 50.31, "elapsed_time": "1:00:02", "remaining_time": "0:59:18", "throughput": 5488.87, "total_tokens": 19774000} {"current_steps": 32435, "total_steps": 64460, "loss": 0.2199, "lr": 5.813792799753391e-06, "epoch": 10.06360533664288, "percentage": 50.32, "elapsed_time": "1:00:03", "remaining_time": "0:59:17", "throughput": 5488.95, "total_tokens": 19777456} {"current_steps": 32440, "total_steps": 64460, "loss": 0.2252, "lr": 5.812457013730855e-06, "epoch": 10.065156686317096, "percentage": 50.33, "elapsed_time": "1:00:03", "remaining_time": "0:59:17", "throughput": 5488.94, "total_tokens": 19780336} {"current_steps": 32445, "total_steps": 64460, "loss": 0.223, "lr": 5.8111211681456014e-06, "epoch": 10.066708035991313, "percentage": 50.33, "elapsed_time": "1:00:04", "remaining_time": "0:59:16", "throughput": 5489.05, "total_tokens": 19783952} {"current_steps": 32450, "total_steps": 64460, "loss": 0.2167, "lr": 5.80978526309556e-06, "epoch": 10.06825938566553, "percentage": 50.34, "elapsed_time": "1:00:04", "remaining_time": "0:59:15", "throughput": 5489.14, "total_tokens": 19787056} {"current_steps": 32455, "total_steps": 64460, "loss": 0.2289, "lr": 5.808449298678669e-06, "epoch": 10.069810735339745, "percentage": 50.35, "elapsed_time": "1:00:05", "remaining_time": "0:59:15", "throughput": 5489.25, "total_tokens": 19790384} {"current_steps": 32460, "total_steps": 64460, "loss": 0.2194, "lr": 5.807113274992873e-06, "epoch": 10.071362085013963, "percentage": 50.36, "elapsed_time": "1:00:05", "remaining_time": "0:59:14", "throughput": 5489.16, "total_tokens": 19792624} {"current_steps": 32465, "total_steps": 64460, "loss": 0.2214, "lr": 5.805777192136114e-06, "epoch": 10.072913434688179, "percentage": 50.36, "elapsed_time": "1:00:06", "remaining_time": "0:59:14", "throughput": 5489.25, "total_tokens": 19795920} {"current_steps": 32470, "total_steps": 64460, "loss": 0.2198, "lr": 5.804441050206346e-06, "epoch": 10.074464784362394, "percentage": 50.37, "elapsed_time": "1:00:06", "remaining_time": "0:59:13", "throughput": 5489.24, "total_tokens": 19799088} {"current_steps": 32475, "total_steps": 64460, "loss": 0.214, "lr": 5.803104849301523e-06, "epoch": 10.076016134036612, "percentage": 50.38, "elapsed_time": "1:00:07", "remaining_time": "0:59:13", "throughput": 5489.21, "total_tokens": 19801936} {"current_steps": 32480, "total_steps": 64460, "loss": 0.2173, "lr": 5.801768589519603e-06, "epoch": 10.077567483710828, "percentage": 50.39, "elapsed_time": "1:00:07", "remaining_time": "0:59:12", "throughput": 5489.13, "total_tokens": 19804272} {"current_steps": 32485, "total_steps": 64460, "loss": 0.2224, "lr": 5.8004322709585515e-06, "epoch": 10.079118833385046, "percentage": 50.4, "elapsed_time": "1:00:08", "remaining_time": "0:59:11", "throughput": 5489.15, "total_tokens": 19807248} {"current_steps": 32490, "total_steps": 64460, "loss": 0.2296, "lr": 5.799095893716338e-06, "epoch": 10.080670183059262, "percentage": 50.4, "elapsed_time": "1:00:09", "remaining_time": "0:59:11", "throughput": 5489.15, "total_tokens": 19810352} {"current_steps": 32495, "total_steps": 64460, "loss": 0.2288, "lr": 5.797759457890932e-06, "epoch": 10.082221532733477, "percentage": 50.41, "elapsed_time": "1:00:09", "remaining_time": "0:59:10", "throughput": 5489.09, "total_tokens": 19812848} {"current_steps": 32500, "total_steps": 64460, "loss": 0.2303, "lr": 5.7964229635803095e-06, "epoch": 10.083772882407695, "percentage": 50.42, "elapsed_time": "1:00:10", "remaining_time": "0:59:10", "throughput": 5489.08, "total_tokens": 19815600} {"current_steps": 32505, "total_steps": 64460, "loss": 0.2297, "lr": 5.795086410882452e-06, "epoch": 10.085324232081911, "percentage": 50.43, "elapsed_time": "1:00:10", "remaining_time": "0:59:09", "throughput": 5489.1, "total_tokens": 19818416} {"current_steps": 32510, "total_steps": 64460, "loss": 0.2102, "lr": 5.793749799895348e-06, "epoch": 10.086875581756129, "percentage": 50.43, "elapsed_time": "1:00:11", "remaining_time": "0:59:08", "throughput": 5489.25, "total_tokens": 19822224} {"current_steps": 32515, "total_steps": 64460, "loss": 0.224, "lr": 5.792413130716983e-06, "epoch": 10.088426931430345, "percentage": 50.44, "elapsed_time": "1:00:11", "remaining_time": "0:59:08", "throughput": 5489.39, "total_tokens": 19825584} {"current_steps": 32520, "total_steps": 64460, "loss": 0.2233, "lr": 5.791076403445352e-06, "epoch": 10.08997828110456, "percentage": 50.45, "elapsed_time": "1:00:12", "remaining_time": "0:59:07", "throughput": 5489.26, "total_tokens": 19827632} {"current_steps": 32525, "total_steps": 64460, "loss": 0.2381, "lr": 5.789739618178453e-06, "epoch": 10.091529630778778, "percentage": 50.46, "elapsed_time": "1:00:12", "remaining_time": "0:59:07", "throughput": 5489.22, "total_tokens": 19830288} {"current_steps": 32530, "total_steps": 64460, "loss": 0.2287, "lr": 5.788402775014288e-06, "epoch": 10.093080980452994, "percentage": 50.47, "elapsed_time": "1:00:13", "remaining_time": "0:59:06", "throughput": 5489.27, "total_tokens": 19833168} {"current_steps": 32535, "total_steps": 64460, "loss": 0.2361, "lr": 5.787065874050863e-06, "epoch": 10.09463233012721, "percentage": 50.47, "elapsed_time": "1:00:13", "remaining_time": "0:59:05", "throughput": 5489.24, "total_tokens": 19835760} {"current_steps": 32540, "total_steps": 64460, "loss": 0.2367, "lr": 5.785728915386191e-06, "epoch": 10.096183679801428, "percentage": 50.48, "elapsed_time": "1:00:14", "remaining_time": "0:59:05", "throughput": 5489.32, "total_tokens": 19838800} {"current_steps": 32545, "total_steps": 64460, "loss": 0.2103, "lr": 5.784391899118283e-06, "epoch": 10.097735029475643, "percentage": 50.49, "elapsed_time": "1:00:14", "remaining_time": "0:59:04", "throughput": 5489.42, "total_tokens": 19842192} {"current_steps": 32550, "total_steps": 64460, "loss": 0.2375, "lr": 5.783054825345161e-06, "epoch": 10.099286379149861, "percentage": 50.5, "elapsed_time": "1:00:15", "remaining_time": "0:59:04", "throughput": 5489.45, "total_tokens": 19845136} {"current_steps": 32555, "total_steps": 64460, "loss": 0.2403, "lr": 5.781717694164848e-06, "epoch": 10.100837728824077, "percentage": 50.5, "elapsed_time": "1:00:15", "remaining_time": "0:59:03", "throughput": 5489.46, "total_tokens": 19847792} {"current_steps": 32560, "total_steps": 64460, "loss": 0.2358, "lr": 5.78038050567537e-06, "epoch": 10.102389078498293, "percentage": 50.51, "elapsed_time": "1:00:16", "remaining_time": "0:59:02", "throughput": 5489.64, "total_tokens": 19851440} {"current_steps": 32565, "total_steps": 64460, "loss": 0.2064, "lr": 5.779043259974759e-06, "epoch": 10.10394042817251, "percentage": 50.52, "elapsed_time": "1:00:16", "remaining_time": "0:59:02", "throughput": 5489.66, "total_tokens": 19854896} {"current_steps": 32570, "total_steps": 64460, "loss": 0.232, "lr": 5.777705957161054e-06, "epoch": 10.105491777846726, "percentage": 50.53, "elapsed_time": "1:00:17", "remaining_time": "0:59:01", "throughput": 5489.6, "total_tokens": 19857232} {"current_steps": 32575, "total_steps": 64460, "loss": 0.1991, "lr": 5.7763685973322925e-06, "epoch": 10.107043127520944, "percentage": 50.54, "elapsed_time": "1:00:17", "remaining_time": "0:59:01", "throughput": 5489.81, "total_tokens": 19861328} {"current_steps": 32580, "total_steps": 64460, "loss": 0.2328, "lr": 5.775031180586519e-06, "epoch": 10.10859447719516, "percentage": 50.54, "elapsed_time": "1:00:18", "remaining_time": "0:59:00", "throughput": 5489.83, "total_tokens": 19864112} {"current_steps": 32585, "total_steps": 64460, "loss": 0.2206, "lr": 5.773693707021783e-06, "epoch": 10.110145826869376, "percentage": 50.55, "elapsed_time": "1:00:18", "remaining_time": "0:59:00", "throughput": 5489.97, "total_tokens": 19867472} {"current_steps": 32590, "total_steps": 64460, "loss": 0.2179, "lr": 5.7723561767361346e-06, "epoch": 10.111697176543593, "percentage": 50.56, "elapsed_time": "1:00:19", "remaining_time": "0:58:59", "throughput": 5490.05, "total_tokens": 19870384} {"current_steps": 32595, "total_steps": 64460, "loss": 0.2187, "lr": 5.771018589827634e-06, "epoch": 10.11324852621781, "percentage": 50.57, "elapsed_time": "1:00:19", "remaining_time": "0:58:58", "throughput": 5490.02, "total_tokens": 19873104} {"current_steps": 32600, "total_steps": 64460, "loss": 0.2337, "lr": 5.76968094639434e-06, "epoch": 10.114799875892025, "percentage": 50.57, "elapsed_time": "1:00:20", "remaining_time": "0:58:58", "throughput": 5490.0, "total_tokens": 19875824} {"current_steps": 32605, "total_steps": 64460, "loss": 0.2187, "lr": 5.768343246534318e-06, "epoch": 10.116351225566243, "percentage": 50.58, "elapsed_time": "1:00:20", "remaining_time": "0:58:57", "throughput": 5490.02, "total_tokens": 19878640} {"current_steps": 32610, "total_steps": 64460, "loss": 0.2388, "lr": 5.767005490345637e-06, "epoch": 10.117902575240459, "percentage": 50.59, "elapsed_time": "1:00:21", "remaining_time": "0:58:56", "throughput": 5489.91, "total_tokens": 19880784} {"current_steps": 32615, "total_steps": 64460, "loss": 0.2415, "lr": 5.765667677926372e-06, "epoch": 10.119453924914676, "percentage": 50.6, "elapsed_time": "1:00:21", "remaining_time": "0:58:56", "throughput": 5490.03, "total_tokens": 19884144} {"current_steps": 32620, "total_steps": 64460, "loss": 0.256, "lr": 5.7643298093745995e-06, "epoch": 10.121005274588892, "percentage": 50.61, "elapsed_time": "1:00:22", "remaining_time": "0:58:55", "throughput": 5490.15, "total_tokens": 19887344} {"current_steps": 32625, "total_steps": 64460, "loss": 0.2644, "lr": 5.762991884788398e-06, "epoch": 10.122556624263108, "percentage": 50.61, "elapsed_time": "1:00:22", "remaining_time": "0:58:55", "throughput": 5490.18, "total_tokens": 19890192} {"current_steps": 32630, "total_steps": 64460, "loss": 0.2233, "lr": 5.761653904265859e-06, "epoch": 10.124107973937326, "percentage": 50.62, "elapsed_time": "1:00:23", "remaining_time": "0:58:54", "throughput": 5490.16, "total_tokens": 19892784} {"current_steps": 32635, "total_steps": 64460, "loss": 0.2302, "lr": 5.760315867905069e-06, "epoch": 10.125659323611542, "percentage": 50.63, "elapsed_time": "1:00:23", "remaining_time": "0:58:53", "throughput": 5490.17, "total_tokens": 19895504} {"current_steps": 32640, "total_steps": 64460, "loss": 0.2335, "lr": 5.758977775804122e-06, "epoch": 10.12721067328576, "percentage": 50.64, "elapsed_time": "1:00:24", "remaining_time": "0:58:53", "throughput": 5490.15, "total_tokens": 19898384} {"current_steps": 32645, "total_steps": 64460, "loss": 0.2267, "lr": 5.757639628061117e-06, "epoch": 10.128762022959975, "percentage": 50.64, "elapsed_time": "1:00:24", "remaining_time": "0:58:52", "throughput": 5490.24, "total_tokens": 19901424} {"current_steps": 32650, "total_steps": 64460, "loss": 0.2347, "lr": 5.7563014247741554e-06, "epoch": 10.130313372634191, "percentage": 50.65, "elapsed_time": "1:00:25", "remaining_time": "0:58:52", "throughput": 5490.24, "total_tokens": 19904208} {"current_steps": 32655, "total_steps": 64460, "loss": 0.2242, "lr": 5.754963166041343e-06, "epoch": 10.131864722308409, "percentage": 50.66, "elapsed_time": "1:00:25", "remaining_time": "0:58:51", "throughput": 5490.29, "total_tokens": 19907632} {"current_steps": 32660, "total_steps": 64460, "loss": 0.2347, "lr": 5.753624851960791e-06, "epoch": 10.133416071982625, "percentage": 50.67, "elapsed_time": "1:00:26", "remaining_time": "0:58:51", "throughput": 5490.5, "total_tokens": 19912208} {"current_steps": 32665, "total_steps": 64460, "loss": 0.2169, "lr": 5.7522864826306125e-06, "epoch": 10.13496742165684, "percentage": 50.67, "elapsed_time": "1:00:27", "remaining_time": "0:58:50", "throughput": 5490.57, "total_tokens": 19915248} {"current_steps": 32670, "total_steps": 64460, "loss": 0.2136, "lr": 5.750948058148926e-06, "epoch": 10.136518771331058, "percentage": 50.68, "elapsed_time": "1:00:27", "remaining_time": "0:58:49", "throughput": 5490.56, "total_tokens": 19917936} {"current_steps": 32675, "total_steps": 64460, "loss": 0.2347, "lr": 5.749609578613855e-06, "epoch": 10.138070121005274, "percentage": 50.69, "elapsed_time": "1:00:28", "remaining_time": "0:58:49", "throughput": 5490.56, "total_tokens": 19920816} {"current_steps": 32680, "total_steps": 64460, "loss": 0.2092, "lr": 5.7482710441235254e-06, "epoch": 10.139621470679492, "percentage": 50.7, "elapsed_time": "1:00:28", "remaining_time": "0:58:48", "throughput": 5490.47, "total_tokens": 19923344} {"current_steps": 32685, "total_steps": 64460, "loss": 0.2235, "lr": 5.746932454776066e-06, "epoch": 10.141172820353708, "percentage": 50.71, "elapsed_time": "1:00:29", "remaining_time": "0:58:48", "throughput": 5490.44, "total_tokens": 19925904} {"current_steps": 32690, "total_steps": 64460, "loss": 0.221, "lr": 5.745593810669614e-06, "epoch": 10.142724170027924, "percentage": 50.71, "elapsed_time": "1:00:29", "remaining_time": "0:58:47", "throughput": 5490.33, "total_tokens": 19928144} {"current_steps": 32695, "total_steps": 64460, "loss": 0.2248, "lr": 5.744255111902306e-06, "epoch": 10.144275519702141, "percentage": 50.72, "elapsed_time": "1:00:30", "remaining_time": "0:58:46", "throughput": 5490.35, "total_tokens": 19931216} {"current_steps": 32700, "total_steps": 64460, "loss": 0.2317, "lr": 5.742916358572286e-06, "epoch": 10.145826869376357, "percentage": 50.73, "elapsed_time": "1:00:30", "remaining_time": "0:58:46", "throughput": 5490.25, "total_tokens": 19933712} {"current_steps": 32705, "total_steps": 64460, "loss": 0.2216, "lr": 5.7415775507776985e-06, "epoch": 10.147378219050575, "percentage": 50.74, "elapsed_time": "1:00:31", "remaining_time": "0:58:45", "throughput": 5490.19, "total_tokens": 19936080} {"current_steps": 32710, "total_steps": 64460, "loss": 0.2576, "lr": 5.740238688616695e-06, "epoch": 10.14892956872479, "percentage": 50.74, "elapsed_time": "1:00:31", "remaining_time": "0:58:45", "throughput": 5490.43, "total_tokens": 19940560} {"current_steps": 32715, "total_steps": 64460, "loss": 0.2346, "lr": 5.7388997721874304e-06, "epoch": 10.150480918399007, "percentage": 50.75, "elapsed_time": "1:00:32", "remaining_time": "0:58:44", "throughput": 5490.51, "total_tokens": 19943824} {"current_steps": 32720, "total_steps": 64460, "loss": 0.2309, "lr": 5.737560801588062e-06, "epoch": 10.152032268073224, "percentage": 50.76, "elapsed_time": "1:00:32", "remaining_time": "0:58:44", "throughput": 5490.48, "total_tokens": 19946384} {"current_steps": 32725, "total_steps": 64460, "loss": 0.2274, "lr": 5.7362217769167535e-06, "epoch": 10.15358361774744, "percentage": 50.77, "elapsed_time": "1:00:33", "remaining_time": "0:58:43", "throughput": 5490.54, "total_tokens": 19949456} {"current_steps": 32730, "total_steps": 64460, "loss": 0.2497, "lr": 5.734882698271671e-06, "epoch": 10.155134967421656, "percentage": 50.78, "elapsed_time": "1:00:34", "remaining_time": "0:58:43", "throughput": 5490.7, "total_tokens": 19954064} {"current_steps": 32735, "total_steps": 64460, "loss": 0.2323, "lr": 5.7335435657509834e-06, "epoch": 10.156686317095874, "percentage": 50.78, "elapsed_time": "1:00:34", "remaining_time": "0:58:42", "throughput": 5490.85, "total_tokens": 19957680} {"current_steps": 32740, "total_steps": 64460, "loss": 0.222, "lr": 5.732204379452866e-06, "epoch": 10.15823766677009, "percentage": 50.79, "elapsed_time": "1:00:35", "remaining_time": "0:58:41", "throughput": 5490.95, "total_tokens": 19960816} {"current_steps": 32745, "total_steps": 64460, "loss": 0.2236, "lr": 5.730865139475497e-06, "epoch": 10.159789016444307, "percentage": 50.8, "elapsed_time": "1:00:35", "remaining_time": "0:58:41", "throughput": 5490.79, "total_tokens": 19962800} {"current_steps": 32750, "total_steps": 64460, "loss": 0.2206, "lr": 5.729525845917058e-06, "epoch": 10.161340366118523, "percentage": 50.81, "elapsed_time": "1:00:36", "remaining_time": "0:58:40", "throughput": 5490.88, "total_tokens": 19966160} {"current_steps": 32755, "total_steps": 64460, "loss": 0.2425, "lr": 5.728186498875736e-06, "epoch": 10.162891715792739, "percentage": 50.81, "elapsed_time": "1:00:36", "remaining_time": "0:58:40", "throughput": 5490.98, "total_tokens": 19969552} {"current_steps": 32760, "total_steps": 64460, "loss": 0.22, "lr": 5.7268470984497215e-06, "epoch": 10.164443065466957, "percentage": 50.82, "elapsed_time": "1:00:37", "remaining_time": "0:58:39", "throughput": 5491.1, "total_tokens": 19973328} {"current_steps": 32765, "total_steps": 64460, "loss": 0.2384, "lr": 5.725507644737207e-06, "epoch": 10.165994415141173, "percentage": 50.83, "elapsed_time": "1:00:37", "remaining_time": "0:58:39", "throughput": 5491.04, "total_tokens": 19975792} {"current_steps": 32770, "total_steps": 64460, "loss": 0.2312, "lr": 5.72416813783639e-06, "epoch": 10.16754576481539, "percentage": 50.84, "elapsed_time": "1:00:38", "remaining_time": "0:58:38", "throughput": 5491.05, "total_tokens": 19978416} {"current_steps": 32775, "total_steps": 64460, "loss": 0.2293, "lr": 5.722828577845474e-06, "epoch": 10.169097114489606, "percentage": 50.85, "elapsed_time": "1:00:38", "remaining_time": "0:58:37", "throughput": 5491.11, "total_tokens": 19981424} {"current_steps": 32780, "total_steps": 64460, "loss": 0.2206, "lr": 5.721488964862663e-06, "epoch": 10.170648464163822, "percentage": 50.85, "elapsed_time": "1:00:39", "remaining_time": "0:58:37", "throughput": 5491.12, "total_tokens": 19984240} {"current_steps": 32785, "total_steps": 64460, "loss": 0.2206, "lr": 5.720149298986167e-06, "epoch": 10.17219981383804, "percentage": 50.86, "elapsed_time": "1:00:39", "remaining_time": "0:58:36", "throughput": 5491.29, "total_tokens": 19987664} {"current_steps": 32790, "total_steps": 64460, "loss": 0.2393, "lr": 5.718809580314201e-06, "epoch": 10.173751163512256, "percentage": 50.87, "elapsed_time": "1:00:40", "remaining_time": "0:58:36", "throughput": 5491.28, "total_tokens": 19990320} {"current_steps": 32795, "total_steps": 64460, "loss": 0.2151, "lr": 5.71746980894498e-06, "epoch": 10.175302513186471, "percentage": 50.88, "elapsed_time": "1:00:40", "remaining_time": "0:58:35", "throughput": 5491.17, "total_tokens": 19993040} {"current_steps": 32800, "total_steps": 64460, "loss": 0.2385, "lr": 5.716129984976726e-06, "epoch": 10.176853862860689, "percentage": 50.88, "elapsed_time": "1:00:41", "remaining_time": "0:58:34", "throughput": 5491.15, "total_tokens": 19996208} {"current_steps": 32805, "total_steps": 64460, "loss": 0.2305, "lr": 5.714790108507664e-06, "epoch": 10.178405212534905, "percentage": 50.89, "elapsed_time": "1:00:42", "remaining_time": "0:58:34", "throughput": 5491.05, "total_tokens": 19998512} {"current_steps": 32810, "total_steps": 64460, "loss": 0.2296, "lr": 5.713450179636022e-06, "epoch": 10.179956562209123, "percentage": 50.9, "elapsed_time": "1:00:42", "remaining_time": "0:58:33", "throughput": 5491.09, "total_tokens": 20001744} {"current_steps": 32815, "total_steps": 64460, "loss": 0.2307, "lr": 5.7121101984600345e-06, "epoch": 10.181507911883338, "percentage": 50.91, "elapsed_time": "1:00:43", "remaining_time": "0:58:33", "throughput": 5491.0, "total_tokens": 20004080} {"current_steps": 32820, "total_steps": 64460, "loss": 0.2325, "lr": 5.710770165077934e-06, "epoch": 10.183059261557554, "percentage": 50.92, "elapsed_time": "1:00:43", "remaining_time": "0:58:32", "throughput": 5490.87, "total_tokens": 20006192} {"current_steps": 32825, "total_steps": 64460, "loss": 0.2471, "lr": 5.7094300795879665e-06, "epoch": 10.184610611231772, "percentage": 50.92, "elapsed_time": "1:00:44", "remaining_time": "0:58:32", "throughput": 5491.03, "total_tokens": 20010480} {"current_steps": 32830, "total_steps": 64460, "loss": 0.2221, "lr": 5.708089942088373e-06, "epoch": 10.186161960905988, "percentage": 50.93, "elapsed_time": "1:00:44", "remaining_time": "0:58:31", "throughput": 5490.83, "total_tokens": 20012848} {"current_steps": 32835, "total_steps": 64460, "loss": 0.2281, "lr": 5.706749752677401e-06, "epoch": 10.187713310580206, "percentage": 50.94, "elapsed_time": "1:00:45", "remaining_time": "0:58:30", "throughput": 5490.87, "total_tokens": 20015920} {"current_steps": 32840, "total_steps": 64460, "loss": 0.2493, "lr": 5.705409511453302e-06, "epoch": 10.189264660254421, "percentage": 50.95, "elapsed_time": "1:00:45", "remaining_time": "0:58:30", "throughput": 5491.03, "total_tokens": 20019984} {"current_steps": 32845, "total_steps": 64460, "loss": 0.235, "lr": 5.704069218514335e-06, "epoch": 10.190816009928637, "percentage": 50.95, "elapsed_time": "1:00:46", "remaining_time": "0:58:29", "throughput": 5490.96, "total_tokens": 20022608} {"current_steps": 32850, "total_steps": 64460, "loss": 0.2029, "lr": 5.7027288739587545e-06, "epoch": 10.192367359602855, "percentage": 50.96, "elapsed_time": "1:00:46", "remaining_time": "0:58:29", "throughput": 5491.09, "total_tokens": 20025776} {"current_steps": 32855, "total_steps": 64460, "loss": 0.233, "lr": 5.701388477884827e-06, "epoch": 10.193918709277071, "percentage": 50.97, "elapsed_time": "1:00:47", "remaining_time": "0:58:29", "throughput": 5491.42, "total_tokens": 20032528} {"current_steps": 32860, "total_steps": 64460, "loss": 0.2291, "lr": 5.700048030390819e-06, "epoch": 10.195470058951287, "percentage": 50.98, "elapsed_time": "1:00:48", "remaining_time": "0:58:28", "throughput": 5491.45, "total_tokens": 20035472} {"current_steps": 32865, "total_steps": 64460, "loss": 0.2243, "lr": 5.6987075315749995e-06, "epoch": 10.197021408625504, "percentage": 50.99, "elapsed_time": "1:00:48", "remaining_time": "0:58:27", "throughput": 5491.47, "total_tokens": 20038288} {"current_steps": 32870, "total_steps": 64460, "loss": 0.2387, "lr": 5.697366981535644e-06, "epoch": 10.19857275829972, "percentage": 50.99, "elapsed_time": "1:00:49", "remaining_time": "0:58:27", "throughput": 5491.35, "total_tokens": 20040848} {"current_steps": 32875, "total_steps": 64460, "loss": 0.2196, "lr": 5.696026380371032e-06, "epoch": 10.200124107973938, "percentage": 51.0, "elapsed_time": "1:00:50", "remaining_time": "0:58:26", "throughput": 5491.55, "total_tokens": 20045008} {"current_steps": 32880, "total_steps": 64460, "loss": 0.2294, "lr": 5.694685728179442e-06, "epoch": 10.201675457648154, "percentage": 51.01, "elapsed_time": "1:00:50", "remaining_time": "0:58:26", "throughput": 5491.48, "total_tokens": 20047440} {"current_steps": 32885, "total_steps": 64460, "loss": 0.2338, "lr": 5.693345025059164e-06, "epoch": 10.20322680732237, "percentage": 51.02, "elapsed_time": "1:00:51", "remaining_time": "0:58:25", "throughput": 5491.56, "total_tokens": 20051088} {"current_steps": 32890, "total_steps": 64460, "loss": 0.2194, "lr": 5.6920042711084836e-06, "epoch": 10.204778156996587, "percentage": 51.02, "elapsed_time": "1:00:51", "remaining_time": "0:58:25", "throughput": 5491.46, "total_tokens": 20053584} {"current_steps": 32895, "total_steps": 64460, "loss": 0.2366, "lr": 5.6906634664256966e-06, "epoch": 10.206329506670803, "percentage": 51.03, "elapsed_time": "1:00:52", "remaining_time": "0:58:24", "throughput": 5491.39, "total_tokens": 20056208} {"current_steps": 32900, "total_steps": 64460, "loss": 0.2219, "lr": 5.6893226111090985e-06, "epoch": 10.207880856345021, "percentage": 51.04, "elapsed_time": "1:00:52", "remaining_time": "0:58:24", "throughput": 5491.56, "total_tokens": 20060528} {"current_steps": 32905, "total_steps": 64460, "loss": 0.2427, "lr": 5.687981705256989e-06, "epoch": 10.209432206019237, "percentage": 51.05, "elapsed_time": "1:00:53", "remaining_time": "0:58:23", "throughput": 5491.6, "total_tokens": 20063472} {"current_steps": 32910, "total_steps": 64460, "loss": 0.2198, "lr": 5.686640748967676e-06, "epoch": 10.210983555693453, "percentage": 51.05, "elapsed_time": "1:00:54", "remaining_time": "0:58:23", "throughput": 5491.69, "total_tokens": 20066672} {"current_steps": 32915, "total_steps": 64460, "loss": 0.2161, "lr": 5.685299742339464e-06, "epoch": 10.21253490536767, "percentage": 51.06, "elapsed_time": "1:00:54", "remaining_time": "0:58:22", "throughput": 5491.55, "total_tokens": 20068912} {"current_steps": 32920, "total_steps": 64460, "loss": 0.2302, "lr": 5.683958685470665e-06, "epoch": 10.214086255041886, "percentage": 51.07, "elapsed_time": "1:00:55", "remaining_time": "0:58:21", "throughput": 5491.34, "total_tokens": 20070960} {"current_steps": 32925, "total_steps": 64460, "loss": 0.2274, "lr": 5.682617578459596e-06, "epoch": 10.215637604716102, "percentage": 51.08, "elapsed_time": "1:00:55", "remaining_time": "0:58:21", "throughput": 5491.4, "total_tokens": 20074768} {"current_steps": 32930, "total_steps": 64460, "loss": 0.2361, "lr": 5.681276421404574e-06, "epoch": 10.21718895439032, "percentage": 51.09, "elapsed_time": "1:00:56", "remaining_time": "0:58:20", "throughput": 5491.25, "total_tokens": 20076944} {"current_steps": 32935, "total_steps": 64460, "loss": 0.2292, "lr": 5.679935214403924e-06, "epoch": 10.218740304064536, "percentage": 51.09, "elapsed_time": "1:00:56", "remaining_time": "0:58:20", "throughput": 5491.18, "total_tokens": 20079600} {"current_steps": 32940, "total_steps": 64460, "loss": 0.2306, "lr": 5.67859395755597e-06, "epoch": 10.220291653738753, "percentage": 51.1, "elapsed_time": "1:00:57", "remaining_time": "0:58:19", "throughput": 5491.12, "total_tokens": 20082128} {"current_steps": 32945, "total_steps": 64460, "loss": 0.2278, "lr": 5.677252650959044e-06, "epoch": 10.22184300341297, "percentage": 51.11, "elapsed_time": "1:00:57", "remaining_time": "0:58:18", "throughput": 5490.95, "total_tokens": 20084144} {"current_steps": 32950, "total_steps": 64460, "loss": 0.2259, "lr": 5.675911294711478e-06, "epoch": 10.223394353087185, "percentage": 51.12, "elapsed_time": "1:00:58", "remaining_time": "0:58:18", "throughput": 5491.15, "total_tokens": 20088656} {"current_steps": 32955, "total_steps": 64460, "loss": 0.2384, "lr": 5.6745698889116115e-06, "epoch": 10.224945702761403, "percentage": 51.12, "elapsed_time": "1:00:58", "remaining_time": "0:58:17", "throughput": 5491.17, "total_tokens": 20091472} {"current_steps": 32960, "total_steps": 64460, "loss": 0.2506, "lr": 5.673228433657784e-06, "epoch": 10.226497052435619, "percentage": 51.13, "elapsed_time": "1:00:59", "remaining_time": "0:58:17", "throughput": 5491.28, "total_tokens": 20095216} {"current_steps": 32965, "total_steps": 64460, "loss": 0.2214, "lr": 5.6718869290483395e-06, "epoch": 10.228048402109836, "percentage": 51.14, "elapsed_time": "1:01:00", "remaining_time": "0:58:16", "throughput": 5491.36, "total_tokens": 20098576} {"current_steps": 32970, "total_steps": 64460, "loss": 0.2336, "lr": 5.670545375181626e-06, "epoch": 10.229599751784052, "percentage": 51.15, "elapsed_time": "1:01:00", "remaining_time": "0:58:16", "throughput": 5491.43, "total_tokens": 20101840} {"current_steps": 32975, "total_steps": 64460, "loss": 0.2346, "lr": 5.669203772155997e-06, "epoch": 10.231151101458268, "percentage": 51.16, "elapsed_time": "1:01:01", "remaining_time": "0:58:15", "throughput": 5491.47, "total_tokens": 20104592} {"current_steps": 32980, "total_steps": 64460, "loss": 0.2282, "lr": 5.667862120069807e-06, "epoch": 10.232702451132486, "percentage": 51.16, "elapsed_time": "1:01:01", "remaining_time": "0:58:15", "throughput": 5491.55, "total_tokens": 20107952} {"current_steps": 32985, "total_steps": 64460, "loss": 0.2293, "lr": 5.666520419021414e-06, "epoch": 10.234253800806702, "percentage": 51.17, "elapsed_time": "1:01:02", "remaining_time": "0:58:14", "throughput": 5491.59, "total_tokens": 20110704} {"current_steps": 32990, "total_steps": 64460, "loss": 0.242, "lr": 5.6651786691091826e-06, "epoch": 10.235805150480918, "percentage": 51.18, "elapsed_time": "1:01:02", "remaining_time": "0:58:13", "throughput": 5491.7, "total_tokens": 20114672} {"current_steps": 32995, "total_steps": 64460, "loss": 0.2351, "lr": 5.663836870431477e-06, "epoch": 10.237356500155135, "percentage": 51.19, "elapsed_time": "1:01:03", "remaining_time": "0:58:13", "throughput": 5491.77, "total_tokens": 20117840} {"current_steps": 33000, "total_steps": 64460, "loss": 0.227, "lr": 5.662495023086667e-06, "epoch": 10.238907849829351, "percentage": 51.19, "elapsed_time": "1:01:03", "remaining_time": "0:58:12", "throughput": 5491.78, "total_tokens": 20120944} {"current_steps": 33005, "total_steps": 64460, "loss": 0.2268, "lr": 5.661153127173128e-06, "epoch": 10.240459199503569, "percentage": 51.2, "elapsed_time": "1:01:04", "remaining_time": "0:58:12", "throughput": 5491.77, "total_tokens": 20124176} {"current_steps": 33010, "total_steps": 64460, "loss": 0.2291, "lr": 5.659811182789235e-06, "epoch": 10.242010549177785, "percentage": 51.21, "elapsed_time": "1:01:05", "remaining_time": "0:58:11", "throughput": 5491.88, "total_tokens": 20127984} {"current_steps": 33015, "total_steps": 64460, "loss": 0.2293, "lr": 5.65846919003337e-06, "epoch": 10.243561898852, "percentage": 51.22, "elapsed_time": "1:01:05", "remaining_time": "0:58:11", "throughput": 5491.86, "total_tokens": 20130480} {"current_steps": 33020, "total_steps": 64460, "loss": 0.2393, "lr": 5.657127149003915e-06, "epoch": 10.245113248526218, "percentage": 51.23, "elapsed_time": "1:01:06", "remaining_time": "0:58:10", "throughput": 5491.73, "total_tokens": 20132880} {"current_steps": 33025, "total_steps": 64460, "loss": 0.2316, "lr": 5.655785059799259e-06, "epoch": 10.246664598200434, "percentage": 51.23, "elapsed_time": "1:01:06", "remaining_time": "0:58:10", "throughput": 5491.8, "total_tokens": 20135952} {"current_steps": 33030, "total_steps": 64460, "loss": 0.2307, "lr": 5.654442922517792e-06, "epoch": 10.248215947874652, "percentage": 51.24, "elapsed_time": "1:01:07", "remaining_time": "0:58:09", "throughput": 5491.98, "total_tokens": 20140048} {"current_steps": 33035, "total_steps": 64460, "loss": 0.2208, "lr": 5.653100737257909e-06, "epoch": 10.249767297548868, "percentage": 51.25, "elapsed_time": "1:01:07", "remaining_time": "0:58:08", "throughput": 5491.95, "total_tokens": 20142672} {"current_steps": 33040, "total_steps": 64460, "loss": 0.2233, "lr": 5.651758504118009e-06, "epoch": 10.251318647223084, "percentage": 51.26, "elapsed_time": "1:01:08", "remaining_time": "0:58:08", "throughput": 5492.06, "total_tokens": 20146192} {"current_steps": 33045, "total_steps": 64460, "loss": 0.2278, "lr": 5.650416223196492e-06, "epoch": 10.252869996897301, "percentage": 51.26, "elapsed_time": "1:01:08", "remaining_time": "0:58:07", "throughput": 5491.91, "total_tokens": 20148336} {"current_steps": 33050, "total_steps": 64460, "loss": 0.2143, "lr": 5.649073894591764e-06, "epoch": 10.254421346571517, "percentage": 51.27, "elapsed_time": "1:01:09", "remaining_time": "0:58:07", "throughput": 5492.0, "total_tokens": 20151440} {"current_steps": 33055, "total_steps": 64460, "loss": 0.2379, "lr": 5.647731518402233e-06, "epoch": 10.255972696245733, "percentage": 51.28, "elapsed_time": "1:01:09", "remaining_time": "0:58:06", "throughput": 5492.05, "total_tokens": 20154608} {"current_steps": 33060, "total_steps": 64460, "loss": 0.2326, "lr": 5.64638909472631e-06, "epoch": 10.25752404591995, "percentage": 51.29, "elapsed_time": "1:01:10", "remaining_time": "0:58:06", "throughput": 5492.14, "total_tokens": 20157776} {"current_steps": 33065, "total_steps": 64460, "loss": 0.2274, "lr": 5.645046623662413e-06, "epoch": 10.259075395594166, "percentage": 51.3, "elapsed_time": "1:01:10", "remaining_time": "0:58:05", "throughput": 5492.12, "total_tokens": 20160624} {"current_steps": 33070, "total_steps": 64460, "loss": 0.2206, "lr": 5.64370410530896e-06, "epoch": 10.260626745268384, "percentage": 51.3, "elapsed_time": "1:01:11", "remaining_time": "0:58:04", "throughput": 5492.14, "total_tokens": 20163312} {"current_steps": 33075, "total_steps": 64460, "loss": 0.226, "lr": 5.6423615397643734e-06, "epoch": 10.2621780949426, "percentage": 51.31, "elapsed_time": "1:01:11", "remaining_time": "0:58:04", "throughput": 5492.06, "total_tokens": 20165776} {"current_steps": 33080, "total_steps": 64460, "loss": 0.2389, "lr": 5.64101892712708e-06, "epoch": 10.263729444616816, "percentage": 51.32, "elapsed_time": "1:01:12", "remaining_time": "0:58:03", "throughput": 5492.17, "total_tokens": 20168880} {"current_steps": 33085, "total_steps": 64460, "loss": 0.2246, "lr": 5.639676267495508e-06, "epoch": 10.265280794291034, "percentage": 51.33, "elapsed_time": "1:01:12", "remaining_time": "0:58:02", "throughput": 5492.37, "total_tokens": 20172464} {"current_steps": 33090, "total_steps": 64460, "loss": 0.2159, "lr": 5.638333560968091e-06, "epoch": 10.26683214396525, "percentage": 51.33, "elapsed_time": "1:01:13", "remaining_time": "0:58:02", "throughput": 5492.36, "total_tokens": 20175120} {"current_steps": 33095, "total_steps": 64460, "loss": 0.2306, "lr": 5.636990807643265e-06, "epoch": 10.268383493639467, "percentage": 51.34, "elapsed_time": "1:01:13", "remaining_time": "0:58:01", "throughput": 5492.39, "total_tokens": 20178000} {"current_steps": 33100, "total_steps": 64460, "loss": 0.2297, "lr": 5.63564800761947e-06, "epoch": 10.269934843313683, "percentage": 51.35, "elapsed_time": "1:01:14", "remaining_time": "0:58:01", "throughput": 5492.2, "total_tokens": 20179856} {"current_steps": 33105, "total_steps": 64460, "loss": 0.2205, "lr": 5.634305160995148e-06, "epoch": 10.271486192987899, "percentage": 51.36, "elapsed_time": "1:01:14", "remaining_time": "0:58:00", "throughput": 5492.23, "total_tokens": 20183088} {"current_steps": 33110, "total_steps": 64460, "loss": 0.2243, "lr": 5.632962267868747e-06, "epoch": 10.273037542662117, "percentage": 51.37, "elapsed_time": "1:01:15", "remaining_time": "0:58:00", "throughput": 5492.32, "total_tokens": 20187024} {"current_steps": 33115, "total_steps": 64460, "loss": 0.2272, "lr": 5.631619328338717e-06, "epoch": 10.274588892336332, "percentage": 51.37, "elapsed_time": "1:01:16", "remaining_time": "0:57:59", "throughput": 5492.3, "total_tokens": 20189712} {"current_steps": 33120, "total_steps": 64460, "loss": 0.2244, "lr": 5.630276342503509e-06, "epoch": 10.276140242010548, "percentage": 51.38, "elapsed_time": "1:01:16", "remaining_time": "0:57:58", "throughput": 5492.27, "total_tokens": 20192496} {"current_steps": 33125, "total_steps": 64460, "loss": 0.2281, "lr": 5.6289333104615825e-06, "epoch": 10.277691591684766, "percentage": 51.39, "elapsed_time": "1:01:17", "remaining_time": "0:57:58", "throughput": 5492.36, "total_tokens": 20195856} {"current_steps": 33130, "total_steps": 64460, "loss": 0.2042, "lr": 5.6275902323113975e-06, "epoch": 10.279242941358982, "percentage": 51.4, "elapsed_time": "1:01:17", "remaining_time": "0:57:57", "throughput": 5492.42, "total_tokens": 20198832} {"current_steps": 33135, "total_steps": 64460, "loss": 0.2085, "lr": 5.626247108151414e-06, "epoch": 10.2807942910332, "percentage": 51.4, "elapsed_time": "1:01:18", "remaining_time": "0:57:57", "throughput": 5492.29, "total_tokens": 20200976} {"current_steps": 33140, "total_steps": 64460, "loss": 0.2492, "lr": 5.624903938080103e-06, "epoch": 10.282345640707415, "percentage": 51.41, "elapsed_time": "1:01:18", "remaining_time": "0:57:56", "throughput": 5492.27, "total_tokens": 20203440} {"current_steps": 33145, "total_steps": 64460, "loss": 0.2307, "lr": 5.623560722195934e-06, "epoch": 10.283896990381631, "percentage": 51.42, "elapsed_time": "1:01:19", "remaining_time": "0:57:55", "throughput": 5492.21, "total_tokens": 20206000} {"current_steps": 33150, "total_steps": 64460, "loss": 0.2313, "lr": 5.62221746059738e-06, "epoch": 10.285448340055849, "percentage": 51.43, "elapsed_time": "1:01:19", "remaining_time": "0:57:55", "throughput": 5492.3, "total_tokens": 20209392} {"current_steps": 33155, "total_steps": 64460, "loss": 0.2389, "lr": 5.620874153382918e-06, "epoch": 10.286999689730065, "percentage": 51.43, "elapsed_time": "1:01:20", "remaining_time": "0:57:54", "throughput": 5492.4, "total_tokens": 20212528} {"current_steps": 33160, "total_steps": 64460, "loss": 0.2234, "lr": 5.619530800651027e-06, "epoch": 10.288551039404283, "percentage": 51.44, "elapsed_time": "1:01:20", "remaining_time": "0:57:54", "throughput": 5492.62, "total_tokens": 20216496} {"current_steps": 33165, "total_steps": 64460, "loss": 0.2089, "lr": 5.618187402500194e-06, "epoch": 10.290102389078498, "percentage": 51.45, "elapsed_time": "1:01:21", "remaining_time": "0:57:53", "throughput": 5492.57, "total_tokens": 20219024} {"current_steps": 33170, "total_steps": 64460, "loss": 0.2279, "lr": 5.6168439590289025e-06, "epoch": 10.291653738752714, "percentage": 51.46, "elapsed_time": "1:01:21", "remaining_time": "0:57:53", "throughput": 5492.66, "total_tokens": 20222480} {"current_steps": 33175, "total_steps": 64460, "loss": 0.2457, "lr": 5.615500470335645e-06, "epoch": 10.293205088426932, "percentage": 51.47, "elapsed_time": "1:01:22", "remaining_time": "0:57:52", "throughput": 5492.67, "total_tokens": 20225072} {"current_steps": 33180, "total_steps": 64460, "loss": 0.2046, "lr": 5.6141569365189144e-06, "epoch": 10.294756438101148, "percentage": 51.47, "elapsed_time": "1:01:22", "remaining_time": "0:57:52", "throughput": 5492.98, "total_tokens": 20230288} {"current_steps": 33185, "total_steps": 64460, "loss": 0.2196, "lr": 5.612813357677207e-06, "epoch": 10.296307787775364, "percentage": 51.48, "elapsed_time": "1:01:23", "remaining_time": "0:57:51", "throughput": 5493.08, "total_tokens": 20233488} {"current_steps": 33190, "total_steps": 64460, "loss": 0.2214, "lr": 5.611469733909024e-06, "epoch": 10.297859137449581, "percentage": 51.49, "elapsed_time": "1:01:23", "remaining_time": "0:57:50", "throughput": 5493.19, "total_tokens": 20236848} {"current_steps": 33195, "total_steps": 64460, "loss": 0.2118, "lr": 5.610126065312868e-06, "epoch": 10.299410487123797, "percentage": 51.5, "elapsed_time": "1:01:24", "remaining_time": "0:57:50", "throughput": 5493.33, "total_tokens": 20240336} {"current_steps": 33200, "total_steps": 64460, "loss": 0.2284, "lr": 5.608782351987248e-06, "epoch": 10.300961836798015, "percentage": 51.5, "elapsed_time": "1:01:25", "remaining_time": "0:57:49", "throughput": 5493.39, "total_tokens": 20243184} {"current_steps": 33205, "total_steps": 64460, "loss": 0.2301, "lr": 5.607438594030671e-06, "epoch": 10.30251318647223, "percentage": 51.51, "elapsed_time": "1:01:25", "remaining_time": "0:57:49", "throughput": 5493.39, "total_tokens": 20245744} {"current_steps": 33210, "total_steps": 64460, "loss": 0.2204, "lr": 5.606094791541653e-06, "epoch": 10.304064536146447, "percentage": 51.52, "elapsed_time": "1:01:25", "remaining_time": "0:57:48", "throughput": 5493.47, "total_tokens": 20248848} {"current_steps": 33215, "total_steps": 64460, "loss": 0.2228, "lr": 5.6047509446187085e-06, "epoch": 10.305615885820664, "percentage": 51.53, "elapsed_time": "1:01:26", "remaining_time": "0:57:47", "throughput": 5493.43, "total_tokens": 20251504} {"current_steps": 33220, "total_steps": 64460, "loss": 0.213, "lr": 5.603407053360359e-06, "epoch": 10.30716723549488, "percentage": 51.54, "elapsed_time": "1:01:27", "remaining_time": "0:57:47", "throughput": 5493.58, "total_tokens": 20255152} {"current_steps": 33225, "total_steps": 64460, "loss": 0.2395, "lr": 5.602063117865127e-06, "epoch": 10.308718585169098, "percentage": 51.54, "elapsed_time": "1:01:27", "remaining_time": "0:57:46", "throughput": 5493.59, "total_tokens": 20258032} {"current_steps": 33230, "total_steps": 64460, "loss": 0.2287, "lr": 5.600719138231539e-06, "epoch": 10.310269934843314, "percentage": 51.55, "elapsed_time": "1:01:28", "remaining_time": "0:57:46", "throughput": 5493.72, "total_tokens": 20261680} {"current_steps": 33235, "total_steps": 64460, "loss": 0.2291, "lr": 5.5993751145581255e-06, "epoch": 10.31182128451753, "percentage": 51.56, "elapsed_time": "1:01:28", "remaining_time": "0:57:45", "throughput": 5493.79, "total_tokens": 20265424} {"current_steps": 33240, "total_steps": 64460, "loss": 0.2244, "lr": 5.5980310469434174e-06, "epoch": 10.313372634191747, "percentage": 51.57, "elapsed_time": "1:01:29", "remaining_time": "0:57:45", "throughput": 5493.86, "total_tokens": 20268528} {"current_steps": 33245, "total_steps": 64460, "loss": 0.235, "lr": 5.596686935485952e-06, "epoch": 10.314923983865963, "percentage": 51.57, "elapsed_time": "1:01:29", "remaining_time": "0:57:44", "throughput": 5493.94, "total_tokens": 20271760} {"current_steps": 33250, "total_steps": 64460, "loss": 0.2389, "lr": 5.595342780284269e-06, "epoch": 10.316475333540179, "percentage": 51.58, "elapsed_time": "1:01:30", "remaining_time": "0:57:43", "throughput": 5493.89, "total_tokens": 20274448} {"current_steps": 33255, "total_steps": 64460, "loss": 0.2259, "lr": 5.593998581436908e-06, "epoch": 10.318026683214397, "percentage": 51.59, "elapsed_time": "1:01:30", "remaining_time": "0:57:43", "throughput": 5494.0, "total_tokens": 20277712} {"current_steps": 33260, "total_steps": 64460, "loss": 0.2157, "lr": 5.592654339042419e-06, "epoch": 10.319578032888613, "percentage": 51.6, "elapsed_time": "1:01:31", "remaining_time": "0:57:42", "throughput": 5493.98, "total_tokens": 20280368} {"current_steps": 33265, "total_steps": 64460, "loss": 0.2246, "lr": 5.591310053199349e-06, "epoch": 10.32112938256283, "percentage": 51.61, "elapsed_time": "1:01:31", "remaining_time": "0:57:42", "throughput": 5494.11, "total_tokens": 20283888} {"current_steps": 33270, "total_steps": 64460, "loss": 0.2168, "lr": 5.58996572400625e-06, "epoch": 10.322680732237046, "percentage": 51.61, "elapsed_time": "1:01:32", "remaining_time": "0:57:41", "throughput": 5494.11, "total_tokens": 20286608} {"current_steps": 33275, "total_steps": 64460, "loss": 0.2364, "lr": 5.588621351561676e-06, "epoch": 10.324232081911262, "percentage": 51.62, "elapsed_time": "1:01:32", "remaining_time": "0:57:40", "throughput": 5494.18, "total_tokens": 20289520} {"current_steps": 33280, "total_steps": 64460, "loss": 0.2367, "lr": 5.5872769359641875e-06, "epoch": 10.32578343158548, "percentage": 51.63, "elapsed_time": "1:01:33", "remaining_time": "0:57:40", "throughput": 5494.23, "total_tokens": 20292400} {"current_steps": 33285, "total_steps": 64460, "loss": 0.2318, "lr": 5.585932477312344e-06, "epoch": 10.327334781259696, "percentage": 51.64, "elapsed_time": "1:01:33", "remaining_time": "0:57:39", "throughput": 5494.32, "total_tokens": 20295568} {"current_steps": 33290, "total_steps": 64460, "loss": 0.2084, "lr": 5.584587975704714e-06, "epoch": 10.328886130933913, "percentage": 51.64, "elapsed_time": "1:01:34", "remaining_time": "0:57:39", "throughput": 5494.4, "total_tokens": 20298960} {"current_steps": 33295, "total_steps": 64460, "loss": 0.2234, "lr": 5.583243431239861e-06, "epoch": 10.33043748060813, "percentage": 51.65, "elapsed_time": "1:01:34", "remaining_time": "0:57:38", "throughput": 5494.46, "total_tokens": 20301904} {"current_steps": 33300, "total_steps": 64460, "loss": 0.2369, "lr": 5.581898844016358e-06, "epoch": 10.331988830282345, "percentage": 51.66, "elapsed_time": "1:01:35", "remaining_time": "0:57:38", "throughput": 5494.64, "total_tokens": 20305872} {"current_steps": 33305, "total_steps": 64460, "loss": 0.2157, "lr": 5.58055421413278e-06, "epoch": 10.333540179956563, "percentage": 51.67, "elapsed_time": "1:01:36", "remaining_time": "0:57:37", "throughput": 5494.82, "total_tokens": 20309776} {"current_steps": 33310, "total_steps": 64460, "loss": 0.2265, "lr": 5.579209541687702e-06, "epoch": 10.335091529630779, "percentage": 51.68, "elapsed_time": "1:01:36", "remaining_time": "0:57:37", "throughput": 5494.95, "total_tokens": 20313456} {"current_steps": 33315, "total_steps": 64460, "loss": 0.2609, "lr": 5.577864826779705e-06, "epoch": 10.336642879304996, "percentage": 51.68, "elapsed_time": "1:01:37", "remaining_time": "0:57:36", "throughput": 5495.02, "total_tokens": 20316336} {"current_steps": 33320, "total_steps": 64460, "loss": 0.2263, "lr": 5.576520069507374e-06, "epoch": 10.338194228979212, "percentage": 51.69, "elapsed_time": "1:01:37", "remaining_time": "0:57:35", "throughput": 5495.04, "total_tokens": 20319216} {"current_steps": 33325, "total_steps": 64460, "loss": 0.2273, "lr": 5.575175269969297e-06, "epoch": 10.339745578653428, "percentage": 51.7, "elapsed_time": "1:01:38", "remaining_time": "0:57:35", "throughput": 5495.18, "total_tokens": 20322704} {"current_steps": 33330, "total_steps": 64460, "loss": 0.2335, "lr": 5.573830428264059e-06, "epoch": 10.341296928327646, "percentage": 51.71, "elapsed_time": "1:01:38", "remaining_time": "0:57:34", "throughput": 5495.14, "total_tokens": 20325072} {"current_steps": 33335, "total_steps": 64460, "loss": 0.2324, "lr": 5.5724855444902556e-06, "epoch": 10.342848278001862, "percentage": 51.71, "elapsed_time": "1:01:39", "remaining_time": "0:57:34", "throughput": 5495.25, "total_tokens": 20328400} {"current_steps": 33340, "total_steps": 64460, "loss": 0.2231, "lr": 5.571140618746485e-06, "epoch": 10.344399627676077, "percentage": 51.72, "elapsed_time": "1:01:39", "remaining_time": "0:57:33", "throughput": 5495.35, "total_tokens": 20331984} {"current_steps": 33345, "total_steps": 64460, "loss": 0.2326, "lr": 5.56979565113134e-06, "epoch": 10.345950977350295, "percentage": 51.73, "elapsed_time": "1:01:40", "remaining_time": "0:57:32", "throughput": 5495.32, "total_tokens": 20334576} {"current_steps": 33350, "total_steps": 64460, "loss": 0.2301, "lr": 5.568450641743429e-06, "epoch": 10.347502327024511, "percentage": 51.74, "elapsed_time": "1:01:40", "remaining_time": "0:57:32", "throughput": 5495.2, "total_tokens": 20336752} {"current_steps": 33355, "total_steps": 64460, "loss": 0.2351, "lr": 5.567105590681354e-06, "epoch": 10.349053676698729, "percentage": 51.75, "elapsed_time": "1:01:41", "remaining_time": "0:57:31", "throughput": 5495.25, "total_tokens": 20339952} {"current_steps": 33360, "total_steps": 64460, "loss": 0.2339, "lr": 5.565760498043723e-06, "epoch": 10.350605026372945, "percentage": 51.75, "elapsed_time": "1:01:42", "remaining_time": "0:57:31", "throughput": 5495.39, "total_tokens": 20343952} {"current_steps": 33365, "total_steps": 64460, "loss": 0.2517, "lr": 5.564415363929149e-06, "epoch": 10.35215637604716, "percentage": 51.76, "elapsed_time": "1:01:42", "remaining_time": "0:57:30", "throughput": 5495.37, "total_tokens": 20346576} {"current_steps": 33370, "total_steps": 64460, "loss": 0.2246, "lr": 5.563070188436245e-06, "epoch": 10.353707725721378, "percentage": 51.77, "elapsed_time": "1:01:43", "remaining_time": "0:57:30", "throughput": 5495.64, "total_tokens": 20351728} {"current_steps": 33375, "total_steps": 64460, "loss": 0.2388, "lr": 5.561724971663628e-06, "epoch": 10.355259075395594, "percentage": 51.78, "elapsed_time": "1:01:43", "remaining_time": "0:57:29", "throughput": 5495.66, "total_tokens": 20354448} {"current_steps": 33380, "total_steps": 64460, "loss": 0.2382, "lr": 5.560379713709919e-06, "epoch": 10.35681042506981, "percentage": 51.78, "elapsed_time": "1:01:44", "remaining_time": "0:57:29", "throughput": 5495.65, "total_tokens": 20357296} {"current_steps": 33385, "total_steps": 64460, "loss": 0.2245, "lr": 5.55903441467374e-06, "epoch": 10.358361774744028, "percentage": 51.79, "elapsed_time": "1:01:44", "remaining_time": "0:57:28", "throughput": 5495.6, "total_tokens": 20360112} {"current_steps": 33390, "total_steps": 64460, "loss": 0.2264, "lr": 5.557689074653719e-06, "epoch": 10.359913124418243, "percentage": 51.8, "elapsed_time": "1:01:45", "remaining_time": "0:57:27", "throughput": 5495.65, "total_tokens": 20363024} {"current_steps": 33395, "total_steps": 64460, "loss": 0.2392, "lr": 5.5563436937484845e-06, "epoch": 10.361464474092461, "percentage": 51.81, "elapsed_time": "1:01:45", "remaining_time": "0:57:27", "throughput": 5495.76, "total_tokens": 20366320} {"current_steps": 33400, "total_steps": 64460, "loss": 0.2326, "lr": 5.554998272056671e-06, "epoch": 10.363015823766677, "percentage": 51.82, "elapsed_time": "1:01:46", "remaining_time": "0:57:26", "throughput": 5495.8, "total_tokens": 20369680} {"current_steps": 33405, "total_steps": 64460, "loss": 0.2208, "lr": 5.553652809676911e-06, "epoch": 10.364567173440893, "percentage": 51.82, "elapsed_time": "1:01:46", "remaining_time": "0:57:26", "throughput": 5495.86, "total_tokens": 20372912} {"current_steps": 33410, "total_steps": 64460, "loss": 0.2311, "lr": 5.552307306707844e-06, "epoch": 10.36611852311511, "percentage": 51.83, "elapsed_time": "1:01:47", "remaining_time": "0:57:25", "throughput": 5495.99, "total_tokens": 20376432} {"current_steps": 33415, "total_steps": 64460, "loss": 0.2315, "lr": 5.5509617632481105e-06, "epoch": 10.367669872789326, "percentage": 51.84, "elapsed_time": "1:01:47", "remaining_time": "0:57:24", "throughput": 5496.02, "total_tokens": 20379120} {"current_steps": 33420, "total_steps": 64460, "loss": 0.2294, "lr": 5.549616179396355e-06, "epoch": 10.369221222463544, "percentage": 51.85, "elapsed_time": "1:01:48", "remaining_time": "0:57:24", "throughput": 5496.13, "total_tokens": 20382288} {"current_steps": 33425, "total_steps": 64460, "loss": 0.2343, "lr": 5.5482705552512265e-06, "epoch": 10.37077257213776, "percentage": 51.85, "elapsed_time": "1:01:49", "remaining_time": "0:57:23", "throughput": 5496.08, "total_tokens": 20385008} {"current_steps": 33430, "total_steps": 64460, "loss": 0.2312, "lr": 5.546924890911372e-06, "epoch": 10.372323921811976, "percentage": 51.86, "elapsed_time": "1:01:49", "remaining_time": "0:57:23", "throughput": 5495.91, "total_tokens": 20387152} {"current_steps": 33435, "total_steps": 64460, "loss": 0.2337, "lr": 5.5455791864754485e-06, "epoch": 10.373875271486193, "percentage": 51.87, "elapsed_time": "1:01:49", "remaining_time": "0:57:22", "throughput": 5495.84, "total_tokens": 20389488} {"current_steps": 33440, "total_steps": 64460, "loss": 0.2357, "lr": 5.54423344204211e-06, "epoch": 10.37542662116041, "percentage": 51.88, "elapsed_time": "1:01:50", "remaining_time": "0:57:22", "throughput": 5496.07, "total_tokens": 20394128} {"current_steps": 33445, "total_steps": 64460, "loss": 0.2333, "lr": 5.542887657710013e-06, "epoch": 10.376977970834627, "percentage": 51.88, "elapsed_time": "1:01:51", "remaining_time": "0:57:21", "throughput": 5496.2, "total_tokens": 20397744} {"current_steps": 33450, "total_steps": 64460, "loss": 0.2322, "lr": 5.541541833577823e-06, "epoch": 10.378529320508843, "percentage": 51.89, "elapsed_time": "1:01:51", "remaining_time": "0:57:20", "throughput": 5496.14, "total_tokens": 20400112} {"current_steps": 33455, "total_steps": 64460, "loss": 0.2256, "lr": 5.540195969744204e-06, "epoch": 10.380080670183059, "percentage": 51.9, "elapsed_time": "1:01:52", "remaining_time": "0:57:20", "throughput": 5496.08, "total_tokens": 20402416} {"current_steps": 33460, "total_steps": 64460, "loss": 0.2312, "lr": 5.538850066307824e-06, "epoch": 10.381632019857276, "percentage": 51.91, "elapsed_time": "1:01:52", "remaining_time": "0:57:19", "throughput": 5496.05, "total_tokens": 20405200} {"current_steps": 33465, "total_steps": 64460, "loss": 0.2319, "lr": 5.537504123367353e-06, "epoch": 10.383183369531492, "percentage": 51.92, "elapsed_time": "1:01:53", "remaining_time": "0:57:19", "throughput": 5496.2, "total_tokens": 20408592} {"current_steps": 33470, "total_steps": 64460, "loss": 0.2246, "lr": 5.536158141021465e-06, "epoch": 10.384734719205708, "percentage": 51.92, "elapsed_time": "1:01:53", "remaining_time": "0:57:18", "throughput": 5496.17, "total_tokens": 20410928} {"current_steps": 33475, "total_steps": 64460, "loss": 0.2371, "lr": 5.534812119368837e-06, "epoch": 10.386286068879926, "percentage": 51.93, "elapsed_time": "1:01:54", "remaining_time": "0:57:17", "throughput": 5496.14, "total_tokens": 20413328} {"current_steps": 33480, "total_steps": 64460, "loss": 0.2199, "lr": 5.533466058508146e-06, "epoch": 10.387837418554142, "percentage": 51.94, "elapsed_time": "1:01:54", "remaining_time": "0:57:17", "throughput": 5496.21, "total_tokens": 20416240} {"current_steps": 33485, "total_steps": 64460, "loss": 0.2245, "lr": 5.532119958538076e-06, "epoch": 10.38938876822836, "percentage": 51.95, "elapsed_time": "1:01:55", "remaining_time": "0:57:16", "throughput": 5496.13, "total_tokens": 20418352} {"current_steps": 33490, "total_steps": 64460, "loss": 0.2214, "lr": 5.530773819557313e-06, "epoch": 10.390940117902575, "percentage": 51.95, "elapsed_time": "1:01:55", "remaining_time": "0:57:16", "throughput": 5496.22, "total_tokens": 20421840} {"current_steps": 33495, "total_steps": 64460, "loss": 0.2231, "lr": 5.529427641664542e-06, "epoch": 10.392491467576791, "percentage": 51.96, "elapsed_time": "1:01:56", "remaining_time": "0:57:15", "throughput": 5496.38, "total_tokens": 20425840} {"current_steps": 33500, "total_steps": 64460, "loss": 0.2459, "lr": 5.528081424958456e-06, "epoch": 10.394042817251009, "percentage": 51.97, "elapsed_time": "1:01:56", "remaining_time": "0:57:14", "throughput": 5496.47, "total_tokens": 20429232} {"current_steps": 33505, "total_steps": 64460, "loss": 0.2292, "lr": 5.526735169537749e-06, "epoch": 10.395594166925225, "percentage": 51.98, "elapsed_time": "1:01:57", "remaining_time": "0:57:14", "throughput": 5496.4, "total_tokens": 20431568} {"current_steps": 33510, "total_steps": 64460, "loss": 0.2192, "lr": 5.525388875501114e-06, "epoch": 10.39714551659944, "percentage": 51.99, "elapsed_time": "1:01:57", "remaining_time": "0:57:13", "throughput": 5496.57, "total_tokens": 20435696} {"current_steps": 33515, "total_steps": 64460, "loss": 0.2357, "lr": 5.524042542947256e-06, "epoch": 10.398696866273658, "percentage": 51.99, "elapsed_time": "1:01:58", "remaining_time": "0:57:13", "throughput": 5496.5, "total_tokens": 20437936} {"current_steps": 33520, "total_steps": 64460, "loss": 0.2362, "lr": 5.5226961719748725e-06, "epoch": 10.400248215947874, "percentage": 52.0, "elapsed_time": "1:01:58", "remaining_time": "0:57:12", "throughput": 5496.42, "total_tokens": 20440080} {"current_steps": 33525, "total_steps": 64460, "loss": 0.2286, "lr": 5.52134976268267e-06, "epoch": 10.401799565622092, "percentage": 52.01, "elapsed_time": "1:01:59", "remaining_time": "0:57:11", "throughput": 5496.37, "total_tokens": 20442448} {"current_steps": 33530, "total_steps": 64460, "loss": 0.2271, "lr": 5.5200033151693566e-06, "epoch": 10.403350915296308, "percentage": 52.02, "elapsed_time": "1:01:59", "remaining_time": "0:57:11", "throughput": 5496.43, "total_tokens": 20445328} {"current_steps": 33535, "total_steps": 64460, "loss": 0.2202, "lr": 5.518656829533643e-06, "epoch": 10.404902264970524, "percentage": 52.02, "elapsed_time": "1:02:00", "remaining_time": "0:57:10", "throughput": 5496.34, "total_tokens": 20447728} {"current_steps": 33540, "total_steps": 64460, "loss": 0.2187, "lr": 5.5173103058742414e-06, "epoch": 10.406453614644741, "percentage": 52.03, "elapsed_time": "1:02:00", "remaining_time": "0:57:10", "throughput": 5496.51, "total_tokens": 20451632} {"current_steps": 33545, "total_steps": 64460, "loss": 0.2455, "lr": 5.515963744289868e-06, "epoch": 10.408004964318957, "percentage": 52.04, "elapsed_time": "1:02:01", "remaining_time": "0:57:09", "throughput": 5496.72, "total_tokens": 20455952} {"current_steps": 33550, "total_steps": 64460, "loss": 0.2286, "lr": 5.514617144879243e-06, "epoch": 10.409556313993175, "percentage": 52.05, "elapsed_time": "1:02:01", "remaining_time": "0:57:09", "throughput": 5496.69, "total_tokens": 20458352} {"current_steps": 33555, "total_steps": 64460, "loss": 0.2237, "lr": 5.513270507741086e-06, "epoch": 10.41110766366739, "percentage": 52.06, "elapsed_time": "1:02:02", "remaining_time": "0:57:08", "throughput": 5496.74, "total_tokens": 20461392} {"current_steps": 33560, "total_steps": 64460, "loss": 0.2249, "lr": 5.511923832974124e-06, "epoch": 10.412659013341607, "percentage": 52.06, "elapsed_time": "1:02:02", "remaining_time": "0:57:07", "throughput": 5496.86, "total_tokens": 20464656} {"current_steps": 33565, "total_steps": 64460, "loss": 0.2345, "lr": 5.510577120677083e-06, "epoch": 10.414210363015824, "percentage": 52.07, "elapsed_time": "1:02:03", "remaining_time": "0:57:07", "throughput": 5496.98, "total_tokens": 20467920} {"current_steps": 33570, "total_steps": 64460, "loss": 0.2345, "lr": 5.509230370948692e-06, "epoch": 10.41576171269004, "percentage": 52.08, "elapsed_time": "1:02:04", "remaining_time": "0:57:06", "throughput": 5497.11, "total_tokens": 20471440} {"current_steps": 33575, "total_steps": 64460, "loss": 0.214, "lr": 5.507883583887685e-06, "epoch": 10.417313062364258, "percentage": 52.09, "elapsed_time": "1:02:04", "remaining_time": "0:57:06", "throughput": 5497.2, "total_tokens": 20474800} {"current_steps": 33580, "total_steps": 64460, "loss": 0.2358, "lr": 5.5065367595927975e-06, "epoch": 10.418864412038474, "percentage": 52.09, "elapsed_time": "1:02:05", "remaining_time": "0:57:05", "throughput": 5497.22, "total_tokens": 20477488} {"current_steps": 33585, "total_steps": 64460, "loss": 0.2214, "lr": 5.505189898162767e-06, "epoch": 10.42041576171269, "percentage": 52.1, "elapsed_time": "1:02:05", "remaining_time": "0:57:04", "throughput": 5497.25, "total_tokens": 20480496} {"current_steps": 33590, "total_steps": 64460, "loss": 0.2308, "lr": 5.503842999696335e-06, "epoch": 10.421967111386907, "percentage": 52.11, "elapsed_time": "1:02:06", "remaining_time": "0:57:04", "throughput": 5497.33, "total_tokens": 20483632} {"current_steps": 33595, "total_steps": 64460, "loss": 0.2358, "lr": 5.5024960642922445e-06, "epoch": 10.423518461061123, "percentage": 52.12, "elapsed_time": "1:02:06", "remaining_time": "0:57:03", "throughput": 5497.31, "total_tokens": 20486192} {"current_steps": 33600, "total_steps": 64460, "loss": 0.2195, "lr": 5.501149092049242e-06, "epoch": 10.425069810735339, "percentage": 52.13, "elapsed_time": "1:02:07", "remaining_time": "0:57:03", "throughput": 5497.36, "total_tokens": 20489936} {"current_steps": 33605, "total_steps": 64460, "loss": 0.2199, "lr": 5.499802083066076e-06, "epoch": 10.426621160409557, "percentage": 52.13, "elapsed_time": "1:02:07", "remaining_time": "0:57:02", "throughput": 5497.44, "total_tokens": 20493136} {"current_steps": 33610, "total_steps": 64460, "loss": 0.2208, "lr": 5.498455037441499e-06, "epoch": 10.428172510083773, "percentage": 52.14, "elapsed_time": "1:02:08", "remaining_time": "0:57:02", "throughput": 5497.43, "total_tokens": 20495696} {"current_steps": 33615, "total_steps": 64460, "loss": 0.2218, "lr": 5.4971079552742655e-06, "epoch": 10.42972385975799, "percentage": 52.15, "elapsed_time": "1:02:08", "remaining_time": "0:57:01", "throughput": 5497.63, "total_tokens": 20499920} {"current_steps": 33620, "total_steps": 64460, "loss": 0.2189, "lr": 5.495760836663132e-06, "epoch": 10.431275209432206, "percentage": 52.16, "elapsed_time": "1:02:09", "remaining_time": "0:57:01", "throughput": 5497.78, "total_tokens": 20503472} {"current_steps": 33625, "total_steps": 64460, "loss": 0.226, "lr": 5.494413681706859e-06, "epoch": 10.432826559106422, "percentage": 52.16, "elapsed_time": "1:02:10", "remaining_time": "0:57:00", "throughput": 5497.97, "total_tokens": 20507536} {"current_steps": 33630, "total_steps": 64460, "loss": 0.2341, "lr": 5.4930664905042076e-06, "epoch": 10.43437790878064, "percentage": 52.17, "elapsed_time": "1:02:10", "remaining_time": "0:56:59", "throughput": 5497.94, "total_tokens": 20510096} {"current_steps": 33635, "total_steps": 64460, "loss": 0.2254, "lr": 5.491719263153944e-06, "epoch": 10.435929258454856, "percentage": 52.18, "elapsed_time": "1:02:11", "remaining_time": "0:56:59", "throughput": 5498.15, "total_tokens": 20514000} {"current_steps": 33640, "total_steps": 64460, "loss": 0.2296, "lr": 5.490371999754834e-06, "epoch": 10.437480608129071, "percentage": 52.19, "elapsed_time": "1:02:11", "remaining_time": "0:56:58", "throughput": 5498.29, "total_tokens": 20517680} {"current_steps": 33645, "total_steps": 64460, "loss": 0.2264, "lr": 5.489024700405652e-06, "epoch": 10.439031957803289, "percentage": 52.2, "elapsed_time": "1:02:12", "remaining_time": "0:56:58", "throughput": 5498.39, "total_tokens": 20520784} {"current_steps": 33650, "total_steps": 64460, "loss": 0.225, "lr": 5.487677365205167e-06, "epoch": 10.440583307477505, "percentage": 52.2, "elapsed_time": "1:02:12", "remaining_time": "0:56:57", "throughput": 5498.41, "total_tokens": 20523312} {"current_steps": 33655, "total_steps": 64460, "loss": 0.2262, "lr": 5.486329994252157e-06, "epoch": 10.442134657151723, "percentage": 52.21, "elapsed_time": "1:02:13", "remaining_time": "0:56:56", "throughput": 5498.34, "total_tokens": 20525648} {"current_steps": 33660, "total_steps": 64460, "loss": 0.2152, "lr": 5.4849825876454e-06, "epoch": 10.443686006825939, "percentage": 52.22, "elapsed_time": "1:02:13", "remaining_time": "0:56:56", "throughput": 5498.53, "total_tokens": 20530032} {"current_steps": 33665, "total_steps": 64460, "loss": 0.2242, "lr": 5.4836351454836755e-06, "epoch": 10.445237356500154, "percentage": 52.23, "elapsed_time": "1:02:14", "remaining_time": "0:56:56", "throughput": 5498.73, "total_tokens": 20534352} {"current_steps": 33670, "total_steps": 64460, "loss": 0.2305, "lr": 5.482287667865768e-06, "epoch": 10.446788706174372, "percentage": 52.23, "elapsed_time": "1:02:14", "remaining_time": "0:56:55", "throughput": 5498.78, "total_tokens": 20537488} {"current_steps": 33675, "total_steps": 64460, "loss": 0.2409, "lr": 5.480940154890463e-06, "epoch": 10.448340055848588, "percentage": 52.24, "elapsed_time": "1:02:15", "remaining_time": "0:56:54", "throughput": 5498.8, "total_tokens": 20540080} {"current_steps": 33680, "total_steps": 64460, "loss": 0.2419, "lr": 5.479592606656549e-06, "epoch": 10.449891405522806, "percentage": 52.25, "elapsed_time": "1:02:15", "remaining_time": "0:56:54", "throughput": 5498.89, "total_tokens": 20543088} {"current_steps": 33685, "total_steps": 64460, "loss": 0.2232, "lr": 5.478245023262819e-06, "epoch": 10.451442755197021, "percentage": 52.26, "elapsed_time": "1:02:16", "remaining_time": "0:56:53", "throughput": 5499.0, "total_tokens": 20546256} {"current_steps": 33690, "total_steps": 64460, "loss": 0.224, "lr": 5.476897404808065e-06, "epoch": 10.452994104871237, "percentage": 52.26, "elapsed_time": "1:02:16", "remaining_time": "0:56:52", "throughput": 5499.14, "total_tokens": 20549616} {"current_steps": 33695, "total_steps": 64460, "loss": 0.2199, "lr": 5.475549751391084e-06, "epoch": 10.454545454545455, "percentage": 52.27, "elapsed_time": "1:02:17", "remaining_time": "0:56:52", "throughput": 5499.39, "total_tokens": 20554384} {"current_steps": 33700, "total_steps": 64460, "loss": 0.2311, "lr": 5.474202063110673e-06, "epoch": 10.456096804219671, "percentage": 52.28, "elapsed_time": "1:02:18", "remaining_time": "0:56:51", "throughput": 5499.45, "total_tokens": 20557232} {"current_steps": 33705, "total_steps": 64460, "loss": 0.2246, "lr": 5.472854340065637e-06, "epoch": 10.457648153893889, "percentage": 52.29, "elapsed_time": "1:02:18", "remaining_time": "0:56:51", "throughput": 5499.49, "total_tokens": 20560304} {"current_steps": 33710, "total_steps": 64460, "loss": 0.2335, "lr": 5.4715065823547785e-06, "epoch": 10.459199503568104, "percentage": 52.3, "elapsed_time": "1:02:19", "remaining_time": "0:56:50", "throughput": 5499.65, "total_tokens": 20563824} {"current_steps": 33715, "total_steps": 64460, "loss": 0.2184, "lr": 5.470158790076903e-06, "epoch": 10.46075085324232, "percentage": 52.3, "elapsed_time": "1:02:19", "remaining_time": "0:56:50", "throughput": 5499.72, "total_tokens": 20566608} {"current_steps": 33720, "total_steps": 64460, "loss": 0.2284, "lr": 5.468810963330823e-06, "epoch": 10.462302202916538, "percentage": 52.31, "elapsed_time": "1:02:20", "remaining_time": "0:56:49", "throughput": 5499.74, "total_tokens": 20569360} {"current_steps": 33725, "total_steps": 64460, "loss": 0.2323, "lr": 5.467463102215347e-06, "epoch": 10.463853552590754, "percentage": 52.32, "elapsed_time": "1:02:20", "remaining_time": "0:56:48", "throughput": 5499.82, "total_tokens": 20572656} {"current_steps": 33730, "total_steps": 64460, "loss": 0.2266, "lr": 5.466115206829289e-06, "epoch": 10.46540490226497, "percentage": 52.33, "elapsed_time": "1:02:21", "remaining_time": "0:56:48", "throughput": 5499.81, "total_tokens": 20575376} {"current_steps": 33735, "total_steps": 64460, "loss": 0.2367, "lr": 5.464767277271468e-06, "epoch": 10.466956251939187, "percentage": 52.33, "elapsed_time": "1:02:21", "remaining_time": "0:56:47", "throughput": 5499.95, "total_tokens": 20579056} {"current_steps": 33740, "total_steps": 64460, "loss": 0.2312, "lr": 5.463419313640701e-06, "epoch": 10.468507601613403, "percentage": 52.34, "elapsed_time": "1:02:22", "remaining_time": "0:56:47", "throughput": 5499.87, "total_tokens": 20581392} {"current_steps": 33745, "total_steps": 64460, "loss": 0.2087, "lr": 5.462071316035811e-06, "epoch": 10.470058951287621, "percentage": 52.35, "elapsed_time": "1:02:22", "remaining_time": "0:56:46", "throughput": 5500.01, "total_tokens": 20584880} {"current_steps": 33750, "total_steps": 64460, "loss": 0.2311, "lr": 5.460723284555622e-06, "epoch": 10.471610300961837, "percentage": 52.36, "elapsed_time": "1:02:23", "remaining_time": "0:56:46", "throughput": 5500.1, "total_tokens": 20587920} {"current_steps": 33755, "total_steps": 64460, "loss": 0.2301, "lr": 5.459375219298959e-06, "epoch": 10.473161650636053, "percentage": 52.37, "elapsed_time": "1:02:23", "remaining_time": "0:56:45", "throughput": 5500.11, "total_tokens": 20590544} {"current_steps": 33760, "total_steps": 64460, "loss": 0.2221, "lr": 5.458027120364653e-06, "epoch": 10.47471300031027, "percentage": 52.37, "elapsed_time": "1:02:24", "remaining_time": "0:56:44", "throughput": 5500.04, "total_tokens": 20592816} {"current_steps": 33765, "total_steps": 64460, "loss": 0.2318, "lr": 5.456678987851536e-06, "epoch": 10.476264349984486, "percentage": 52.38, "elapsed_time": "1:02:24", "remaining_time": "0:56:44", "throughput": 5500.12, "total_tokens": 20595952} {"current_steps": 33770, "total_steps": 64460, "loss": 0.2236, "lr": 5.45533082185844e-06, "epoch": 10.477815699658702, "percentage": 52.39, "elapsed_time": "1:02:25", "remaining_time": "0:56:43", "throughput": 5500.16, "total_tokens": 20598704} {"current_steps": 33775, "total_steps": 64460, "loss": 0.2313, "lr": 5.453982622484204e-06, "epoch": 10.47936704933292, "percentage": 52.4, "elapsed_time": "1:02:25", "remaining_time": "0:56:42", "throughput": 5500.2, "total_tokens": 20601616} {"current_steps": 33780, "total_steps": 64460, "loss": 0.2217, "lr": 5.452634389827667e-06, "epoch": 10.480918399007136, "percentage": 52.4, "elapsed_time": "1:02:26", "remaining_time": "0:56:42", "throughput": 5500.28, "total_tokens": 20604688} {"current_steps": 33785, "total_steps": 64460, "loss": 0.2318, "lr": 5.451286123987667e-06, "epoch": 10.482469748681353, "percentage": 52.41, "elapsed_time": "1:02:26", "remaining_time": "0:56:41", "throughput": 5500.39, "total_tokens": 20607760} {"current_steps": 33790, "total_steps": 64460, "loss": 0.2254, "lr": 5.449937825063052e-06, "epoch": 10.48402109835557, "percentage": 52.42, "elapsed_time": "1:02:27", "remaining_time": "0:56:41", "throughput": 5500.43, "total_tokens": 20610512} {"current_steps": 33795, "total_steps": 64460, "loss": 0.2199, "lr": 5.448589493152665e-06, "epoch": 10.485572448029785, "percentage": 52.43, "elapsed_time": "1:02:27", "remaining_time": "0:56:40", "throughput": 5500.5, "total_tokens": 20613488} {"current_steps": 33800, "total_steps": 64460, "loss": 0.2198, "lr": 5.447241128355356e-06, "epoch": 10.487123797704003, "percentage": 52.44, "elapsed_time": "1:02:28", "remaining_time": "0:56:39", "throughput": 5500.62, "total_tokens": 20616784} {"current_steps": 33805, "total_steps": 64460, "loss": 0.2356, "lr": 5.445892730769977e-06, "epoch": 10.488675147378219, "percentage": 52.44, "elapsed_time": "1:02:28", "remaining_time": "0:56:39", "throughput": 5500.64, "total_tokens": 20619408} {"current_steps": 33810, "total_steps": 64460, "loss": 0.2325, "lr": 5.44454430049538e-06, "epoch": 10.490226497052436, "percentage": 52.45, "elapsed_time": "1:02:29", "remaining_time": "0:56:38", "throughput": 5500.67, "total_tokens": 20622608} {"current_steps": 33815, "total_steps": 64460, "loss": 0.2251, "lr": 5.443195837630423e-06, "epoch": 10.491777846726652, "percentage": 52.46, "elapsed_time": "1:02:29", "remaining_time": "0:56:38", "throughput": 5500.81, "total_tokens": 20626448} {"current_steps": 33820, "total_steps": 64460, "loss": 0.2275, "lr": 5.44184734227396e-06, "epoch": 10.493329196400868, "percentage": 52.47, "elapsed_time": "1:02:30", "remaining_time": "0:56:37", "throughput": 5500.82, "total_tokens": 20628976} {"current_steps": 33825, "total_steps": 64460, "loss": 0.2024, "lr": 5.440498814524857e-06, "epoch": 10.494880546075086, "percentage": 52.47, "elapsed_time": "1:02:30", "remaining_time": "0:56:37", "throughput": 5501.04, "total_tokens": 20633040} {"current_steps": 33830, "total_steps": 64460, "loss": 0.2238, "lr": 5.439150254481974e-06, "epoch": 10.496431895749302, "percentage": 52.48, "elapsed_time": "1:02:31", "remaining_time": "0:56:36", "throughput": 5501.2, "total_tokens": 20637232} {"current_steps": 33835, "total_steps": 64460, "loss": 0.2276, "lr": 5.437801662244177e-06, "epoch": 10.49798324542352, "percentage": 52.49, "elapsed_time": "1:02:31", "remaining_time": "0:56:35", "throughput": 5501.22, "total_tokens": 20639760} {"current_steps": 33840, "total_steps": 64460, "loss": 0.2247, "lr": 5.4364530379103344e-06, "epoch": 10.499534595097735, "percentage": 52.5, "elapsed_time": "1:02:32", "remaining_time": "0:56:35", "throughput": 5501.18, "total_tokens": 20642064} {"current_steps": 33845, "total_steps": 64460, "loss": 0.2458, "lr": 5.435104381579315e-06, "epoch": 10.501085944771951, "percentage": 52.51, "elapsed_time": "1:02:32", "remaining_time": "0:56:34", "throughput": 5501.09, "total_tokens": 20644144} {"current_steps": 33850, "total_steps": 64460, "loss": 0.2243, "lr": 5.433755693349991e-06, "epoch": 10.502637294446169, "percentage": 52.51, "elapsed_time": "1:02:33", "remaining_time": "0:56:33", "throughput": 5501.18, "total_tokens": 20647248} {"current_steps": 33855, "total_steps": 64460, "loss": 0.2176, "lr": 5.43240697332124e-06, "epoch": 10.504188644120385, "percentage": 52.52, "elapsed_time": "1:02:33", "remaining_time": "0:56:33", "throughput": 5501.19, "total_tokens": 20650032} {"current_steps": 33860, "total_steps": 64460, "loss": 0.2241, "lr": 5.4310582215919375e-06, "epoch": 10.5057399937946, "percentage": 52.53, "elapsed_time": "1:02:34", "remaining_time": "0:56:32", "throughput": 5501.3, "total_tokens": 20653232} {"current_steps": 33865, "total_steps": 64460, "loss": 0.2302, "lr": 5.429709438260962e-06, "epoch": 10.507291343468818, "percentage": 52.54, "elapsed_time": "1:02:34", "remaining_time": "0:56:32", "throughput": 5501.39, "total_tokens": 20656528} {"current_steps": 33870, "total_steps": 64460, "loss": 0.2206, "lr": 5.4283606234271955e-06, "epoch": 10.508842693143034, "percentage": 52.54, "elapsed_time": "1:02:35", "remaining_time": "0:56:31", "throughput": 5501.34, "total_tokens": 20658768} {"current_steps": 33875, "total_steps": 64460, "loss": 0.2285, "lr": 5.427011777189525e-06, "epoch": 10.510394042817252, "percentage": 52.55, "elapsed_time": "1:02:35", "remaining_time": "0:56:30", "throughput": 5501.35, "total_tokens": 20661328} {"current_steps": 33880, "total_steps": 64460, "loss": 0.2365, "lr": 5.425662899646832e-06, "epoch": 10.511945392491468, "percentage": 52.56, "elapsed_time": "1:02:36", "remaining_time": "0:56:30", "throughput": 5501.28, "total_tokens": 20663568} {"current_steps": 33885, "total_steps": 64460, "loss": 0.2261, "lr": 5.424313990898009e-06, "epoch": 10.513496742165684, "percentage": 52.57, "elapsed_time": "1:02:36", "remaining_time": "0:56:29", "throughput": 5501.29, "total_tokens": 20666416} {"current_steps": 33890, "total_steps": 64460, "loss": 0.2383, "lr": 5.422965051041945e-06, "epoch": 10.515048091839901, "percentage": 52.58, "elapsed_time": "1:02:37", "remaining_time": "0:56:29", "throughput": 5501.25, "total_tokens": 20668848} {"current_steps": 33895, "total_steps": 64460, "loss": 0.23, "lr": 5.421616080177535e-06, "epoch": 10.516599441514117, "percentage": 52.58, "elapsed_time": "1:02:37", "remaining_time": "0:56:28", "throughput": 5501.31, "total_tokens": 20671824} {"current_steps": 33900, "total_steps": 64460, "loss": 0.2463, "lr": 5.4202670784036745e-06, "epoch": 10.518150791188333, "percentage": 52.59, "elapsed_time": "1:02:38", "remaining_time": "0:56:27", "throughput": 5501.17, "total_tokens": 20674288} {"current_steps": 33905, "total_steps": 64460, "loss": 0.2317, "lr": 5.418918045819259e-06, "epoch": 10.51970214086255, "percentage": 52.6, "elapsed_time": "1:02:38", "remaining_time": "0:56:27", "throughput": 5501.23, "total_tokens": 20677168} {"current_steps": 33910, "total_steps": 64460, "loss": 0.2208, "lr": 5.417568982523191e-06, "epoch": 10.521253490536767, "percentage": 52.61, "elapsed_time": "1:02:39", "remaining_time": "0:56:26", "throughput": 5501.34, "total_tokens": 20680336} {"current_steps": 33915, "total_steps": 64460, "loss": 0.2266, "lr": 5.416219888614372e-06, "epoch": 10.522804840210984, "percentage": 52.61, "elapsed_time": "1:02:39", "remaining_time": "0:56:26", "throughput": 5501.46, "total_tokens": 20683760} {"current_steps": 33920, "total_steps": 64460, "loss": 0.2354, "lr": 5.4148707641917054e-06, "epoch": 10.5243561898852, "percentage": 52.62, "elapsed_time": "1:02:40", "remaining_time": "0:56:25", "throughput": 5501.49, "total_tokens": 20686832} {"current_steps": 33925, "total_steps": 64460, "loss": 0.2145, "lr": 5.413521609354099e-06, "epoch": 10.525907539559416, "percentage": 52.63, "elapsed_time": "1:02:40", "remaining_time": "0:56:24", "throughput": 5501.54, "total_tokens": 20689680} {"current_steps": 33930, "total_steps": 64460, "loss": 0.2229, "lr": 5.412172424200462e-06, "epoch": 10.527458889233634, "percentage": 52.64, "elapsed_time": "1:02:41", "remaining_time": "0:56:24", "throughput": 5501.59, "total_tokens": 20692528} {"current_steps": 33935, "total_steps": 64460, "loss": 0.2191, "lr": 5.4108232088297055e-06, "epoch": 10.52901023890785, "percentage": 52.65, "elapsed_time": "1:02:41", "remaining_time": "0:56:23", "throughput": 5501.67, "total_tokens": 20695568} {"current_steps": 33940, "total_steps": 64460, "loss": 0.22, "lr": 5.409473963340744e-06, "epoch": 10.530561588582067, "percentage": 52.65, "elapsed_time": "1:02:42", "remaining_time": "0:56:23", "throughput": 5501.65, "total_tokens": 20698032} {"current_steps": 33945, "total_steps": 64460, "loss": 0.2346, "lr": 5.40812468783249e-06, "epoch": 10.532112938256283, "percentage": 52.66, "elapsed_time": "1:02:42", "remaining_time": "0:56:22", "throughput": 5501.75, "total_tokens": 20701360} {"current_steps": 33950, "total_steps": 64460, "loss": 0.2409, "lr": 5.406775382403865e-06, "epoch": 10.533664287930499, "percentage": 52.67, "elapsed_time": "1:02:43", "remaining_time": "0:56:21", "throughput": 5501.75, "total_tokens": 20703856} {"current_steps": 33955, "total_steps": 64460, "loss": 0.2277, "lr": 5.4054260471537866e-06, "epoch": 10.535215637604717, "percentage": 52.68, "elapsed_time": "1:02:43", "remaining_time": "0:56:21", "throughput": 5501.79, "total_tokens": 20706768} {"current_steps": 33960, "total_steps": 64460, "loss": 0.2318, "lr": 5.404076682181178e-06, "epoch": 10.536766987278932, "percentage": 52.68, "elapsed_time": "1:02:44", "remaining_time": "0:56:20", "throughput": 5501.84, "total_tokens": 20709648} {"current_steps": 33965, "total_steps": 64460, "loss": 0.2205, "lr": 5.402727287584965e-06, "epoch": 10.53831833695315, "percentage": 52.69, "elapsed_time": "1:02:44", "remaining_time": "0:56:19", "throughput": 5501.85, "total_tokens": 20712176} {"current_steps": 33970, "total_steps": 64460, "loss": 0.2172, "lr": 5.401377863464071e-06, "epoch": 10.539869686627366, "percentage": 52.7, "elapsed_time": "1:02:45", "remaining_time": "0:56:19", "throughput": 5501.83, "total_tokens": 20714608} {"current_steps": 33975, "total_steps": 64460, "loss": 0.2456, "lr": 5.400028409917428e-06, "epoch": 10.541421036301582, "percentage": 52.71, "elapsed_time": "1:02:45", "remaining_time": "0:56:18", "throughput": 5501.83, "total_tokens": 20717296} {"current_steps": 33980, "total_steps": 64460, "loss": 0.2254, "lr": 5.398678927043965e-06, "epoch": 10.5429723859758, "percentage": 52.71, "elapsed_time": "1:02:46", "remaining_time": "0:56:18", "throughput": 5501.84, "total_tokens": 20720080} {"current_steps": 33985, "total_steps": 64460, "loss": 0.2044, "lr": 5.397329414942616e-06, "epoch": 10.544523735650015, "percentage": 52.72, "elapsed_time": "1:02:46", "remaining_time": "0:56:17", "throughput": 5501.94, "total_tokens": 20723504} {"current_steps": 33990, "total_steps": 64460, "loss": 0.233, "lr": 5.3959798737123156e-06, "epoch": 10.546075085324231, "percentage": 52.73, "elapsed_time": "1:02:47", "remaining_time": "0:56:16", "throughput": 5501.95, "total_tokens": 20726096} {"current_steps": 33995, "total_steps": 64460, "loss": 0.2378, "lr": 5.394630303452001e-06, "epoch": 10.547626434998449, "percentage": 52.74, "elapsed_time": "1:02:47", "remaining_time": "0:56:16", "throughput": 5501.95, "total_tokens": 20728752} {"current_steps": 34000, "total_steps": 64460, "loss": 0.2421, "lr": 5.3932807042606125e-06, "epoch": 10.549177784672665, "percentage": 52.75, "elapsed_time": "1:02:48", "remaining_time": "0:56:15", "throughput": 5501.99, "total_tokens": 20731664} {"current_steps": 34005, "total_steps": 64460, "loss": 0.2248, "lr": 5.391931076237091e-06, "epoch": 10.550729134346883, "percentage": 52.75, "elapsed_time": "1:02:48", "remaining_time": "0:56:15", "throughput": 5502.09, "total_tokens": 20734800} {"current_steps": 34010, "total_steps": 64460, "loss": 0.2237, "lr": 5.3905814194803805e-06, "epoch": 10.552280484021098, "percentage": 52.76, "elapsed_time": "1:02:49", "remaining_time": "0:56:14", "throughput": 5502.23, "total_tokens": 20738800} {"current_steps": 34015, "total_steps": 64460, "loss": 0.2245, "lr": 5.3892317340894265e-06, "epoch": 10.553831833695314, "percentage": 52.77, "elapsed_time": "1:02:49", "remaining_time": "0:56:13", "throughput": 5502.2, "total_tokens": 20741232} {"current_steps": 34020, "total_steps": 64460, "loss": 0.2177, "lr": 5.387882020163177e-06, "epoch": 10.555383183369532, "percentage": 52.78, "elapsed_time": "1:02:50", "remaining_time": "0:56:13", "throughput": 5502.27, "total_tokens": 20744304} {"current_steps": 34025, "total_steps": 64460, "loss": 0.2219, "lr": 5.386532277800583e-06, "epoch": 10.556934533043748, "percentage": 52.78, "elapsed_time": "1:02:50", "remaining_time": "0:56:12", "throughput": 5502.32, "total_tokens": 20747696} {"current_steps": 34030, "total_steps": 64460, "loss": 0.2196, "lr": 5.385182507100594e-06, "epoch": 10.558485882717964, "percentage": 52.79, "elapsed_time": "1:02:51", "remaining_time": "0:56:12", "throughput": 5502.16, "total_tokens": 20749648} {"current_steps": 34035, "total_steps": 64460, "loss": 0.2125, "lr": 5.383832708162169e-06, "epoch": 10.560037232392181, "percentage": 52.8, "elapsed_time": "1:02:51", "remaining_time": "0:56:11", "throughput": 5502.28, "total_tokens": 20753200} {"current_steps": 34040, "total_steps": 64460, "loss": 0.2292, "lr": 5.382482881084259e-06, "epoch": 10.561588582066397, "percentage": 52.81, "elapsed_time": "1:02:52", "remaining_time": "0:56:11", "throughput": 5502.46, "total_tokens": 20757904} {"current_steps": 34045, "total_steps": 64460, "loss": 0.2208, "lr": 5.381133025965826e-06, "epoch": 10.563139931740615, "percentage": 52.82, "elapsed_time": "1:02:52", "remaining_time": "0:56:10", "throughput": 5502.59, "total_tokens": 20761168} {"current_steps": 34050, "total_steps": 64460, "loss": 0.2308, "lr": 5.379783142905828e-06, "epoch": 10.56469128141483, "percentage": 52.82, "elapsed_time": "1:02:53", "remaining_time": "0:56:10", "throughput": 5502.82, "total_tokens": 20765968} {"current_steps": 34055, "total_steps": 64460, "loss": 0.2328, "lr": 5.378433232003228e-06, "epoch": 10.566242631089047, "percentage": 52.83, "elapsed_time": "1:02:54", "remaining_time": "0:56:09", "throughput": 5502.95, "total_tokens": 20769584} {"current_steps": 34060, "total_steps": 64460, "loss": 0.2195, "lr": 5.377083293356991e-06, "epoch": 10.567793980763264, "percentage": 52.84, "elapsed_time": "1:02:54", "remaining_time": "0:56:09", "throughput": 5503.01, "total_tokens": 20772624} {"current_steps": 34065, "total_steps": 64460, "loss": 0.2279, "lr": 5.375733327066084e-06, "epoch": 10.56934533043748, "percentage": 52.85, "elapsed_time": "1:02:55", "remaining_time": "0:56:08", "throughput": 5503.17, "total_tokens": 20776144} {"current_steps": 34070, "total_steps": 64460, "loss": 0.2376, "lr": 5.374383333229474e-06, "epoch": 10.570896680111698, "percentage": 52.85, "elapsed_time": "1:02:55", "remaining_time": "0:56:08", "throughput": 5503.23, "total_tokens": 20779344} {"current_steps": 34075, "total_steps": 64460, "loss": 0.2307, "lr": 5.373033311946132e-06, "epoch": 10.572448029785914, "percentage": 52.86, "elapsed_time": "1:02:56", "remaining_time": "0:56:07", "throughput": 5503.26, "total_tokens": 20782320} {"current_steps": 34080, "total_steps": 64460, "loss": 0.2129, "lr": 5.371683263315031e-06, "epoch": 10.57399937946013, "percentage": 52.87, "elapsed_time": "1:02:56", "remaining_time": "0:56:06", "throughput": 5503.21, "total_tokens": 20784976} {"current_steps": 34085, "total_steps": 64460, "loss": 0.2338, "lr": 5.370333187435146e-06, "epoch": 10.575550729134347, "percentage": 52.88, "elapsed_time": "1:02:57", "remaining_time": "0:56:06", "throughput": 5503.3, "total_tokens": 20788176} {"current_steps": 34090, "total_steps": 64460, "loss": 0.2378, "lr": 5.3689830844054525e-06, "epoch": 10.577102078808563, "percentage": 52.89, "elapsed_time": "1:02:58", "remaining_time": "0:56:05", "throughput": 5503.4, "total_tokens": 20792208} {"current_steps": 34095, "total_steps": 64460, "loss": 0.2379, "lr": 5.36763295432493e-06, "epoch": 10.578653428482781, "percentage": 52.89, "elapsed_time": "1:02:58", "remaining_time": "0:56:05", "throughput": 5503.41, "total_tokens": 20795248} {"current_steps": 34100, "total_steps": 64460, "loss": 0.2363, "lr": 5.366282797292558e-06, "epoch": 10.580204778156997, "percentage": 52.9, "elapsed_time": "1:02:59", "remaining_time": "0:56:04", "throughput": 5503.29, "total_tokens": 20797424} {"current_steps": 34105, "total_steps": 64460, "loss": 0.2481, "lr": 5.36493261340732e-06, "epoch": 10.581756127831213, "percentage": 52.91, "elapsed_time": "1:02:59", "remaining_time": "0:56:03", "throughput": 5503.38, "total_tokens": 20800464} {"current_steps": 34110, "total_steps": 64460, "loss": 0.2381, "lr": 5.3635824027682005e-06, "epoch": 10.58330747750543, "percentage": 52.92, "elapsed_time": "1:03:00", "remaining_time": "0:56:03", "throughput": 5503.6, "total_tokens": 20805104} {"current_steps": 34115, "total_steps": 64460, "loss": 0.2272, "lr": 5.362232165474185e-06, "epoch": 10.584858827179646, "percentage": 52.92, "elapsed_time": "1:03:00", "remaining_time": "0:56:02", "throughput": 5503.54, "total_tokens": 20807440} {"current_steps": 34120, "total_steps": 64460, "loss": 0.2226, "lr": 5.360881901624262e-06, "epoch": 10.586410176853862, "percentage": 52.93, "elapsed_time": "1:03:01", "remaining_time": "0:56:02", "throughput": 5503.68, "total_tokens": 20811568} {"current_steps": 34125, "total_steps": 64460, "loss": 0.2258, "lr": 5.359531611317421e-06, "epoch": 10.58796152652808, "percentage": 52.94, "elapsed_time": "1:03:01", "remaining_time": "0:56:01", "throughput": 5503.58, "total_tokens": 20813808} {"current_steps": 34130, "total_steps": 64460, "loss": 0.2316, "lr": 5.358181294652658e-06, "epoch": 10.589512876202296, "percentage": 52.95, "elapsed_time": "1:03:02", "remaining_time": "0:56:01", "throughput": 5503.6, "total_tokens": 20816432} {"current_steps": 34135, "total_steps": 64460, "loss": 0.2321, "lr": 5.356830951728962e-06, "epoch": 10.591064225876513, "percentage": 52.96, "elapsed_time": "1:03:02", "remaining_time": "0:56:00", "throughput": 5503.66, "total_tokens": 20819856} {"current_steps": 34140, "total_steps": 64460, "loss": 0.21, "lr": 5.355480582645332e-06, "epoch": 10.59261557555073, "percentage": 52.96, "elapsed_time": "1:03:03", "remaining_time": "0:56:00", "throughput": 5503.68, "total_tokens": 20822672} {"current_steps": 34145, "total_steps": 64460, "loss": 0.2083, "lr": 5.354130187500766e-06, "epoch": 10.594166925224945, "percentage": 52.97, "elapsed_time": "1:03:03", "remaining_time": "0:55:59", "throughput": 5503.88, "total_tokens": 20826608} {"current_steps": 34150, "total_steps": 64460, "loss": 0.2112, "lr": 5.352779766394266e-06, "epoch": 10.595718274899163, "percentage": 52.98, "elapsed_time": "1:03:04", "remaining_time": "0:55:58", "throughput": 5503.97, "total_tokens": 20829552} {"current_steps": 34155, "total_steps": 64460, "loss": 0.2252, "lr": 5.3514293194248305e-06, "epoch": 10.597269624573379, "percentage": 52.99, "elapsed_time": "1:03:05", "remaining_time": "0:55:58", "throughput": 5504.05, "total_tokens": 20833104} {"current_steps": 34160, "total_steps": 64460, "loss": 0.2265, "lr": 5.350078846691463e-06, "epoch": 10.598820974247595, "percentage": 52.99, "elapsed_time": "1:03:05", "remaining_time": "0:55:57", "throughput": 5504.0, "total_tokens": 20835536} {"current_steps": 34165, "total_steps": 64460, "loss": 0.234, "lr": 5.348728348293172e-06, "epoch": 10.600372323921812, "percentage": 53.0, "elapsed_time": "1:03:05", "remaining_time": "0:55:57", "throughput": 5504.05, "total_tokens": 20838352} {"current_steps": 34170, "total_steps": 64460, "loss": 0.2184, "lr": 5.347377824328962e-06, "epoch": 10.601923673596028, "percentage": 53.01, "elapsed_time": "1:03:06", "remaining_time": "0:55:56", "throughput": 5504.03, "total_tokens": 20840880} {"current_steps": 34175, "total_steps": 64460, "loss": 0.2309, "lr": 5.3460272748978445e-06, "epoch": 10.603475023270246, "percentage": 53.02, "elapsed_time": "1:03:07", "remaining_time": "0:55:55", "throughput": 5504.14, "total_tokens": 20844304} {"current_steps": 34180, "total_steps": 64460, "loss": 0.2299, "lr": 5.3446767000988306e-06, "epoch": 10.605026372944462, "percentage": 53.03, "elapsed_time": "1:03:07", "remaining_time": "0:55:55", "throughput": 5504.26, "total_tokens": 20847920} {"current_steps": 34185, "total_steps": 64460, "loss": 0.2349, "lr": 5.343326100030933e-06, "epoch": 10.606577722618677, "percentage": 53.03, "elapsed_time": "1:03:08", "remaining_time": "0:55:54", "throughput": 5504.33, "total_tokens": 20850896} {"current_steps": 34190, "total_steps": 64460, "loss": 0.2142, "lr": 5.341975474793166e-06, "epoch": 10.608129072292895, "percentage": 53.04, "elapsed_time": "1:03:08", "remaining_time": "0:55:54", "throughput": 5504.32, "total_tokens": 20853488} {"current_steps": 34195, "total_steps": 64460, "loss": 0.2371, "lr": 5.340624824484547e-06, "epoch": 10.609680421967111, "percentage": 53.05, "elapsed_time": "1:03:09", "remaining_time": "0:55:53", "throughput": 5504.3, "total_tokens": 20856304} {"current_steps": 34200, "total_steps": 64460, "loss": 0.2134, "lr": 5.339274149204096e-06, "epoch": 10.611231771641329, "percentage": 53.06, "elapsed_time": "1:03:09", "remaining_time": "0:55:52", "throughput": 5504.19, "total_tokens": 20858384} {"current_steps": 34205, "total_steps": 64460, "loss": 0.2116, "lr": 5.337923449050831e-06, "epoch": 10.612783121315545, "percentage": 53.06, "elapsed_time": "1:03:10", "remaining_time": "0:55:52", "throughput": 5504.31, "total_tokens": 20861808} {"current_steps": 34210, "total_steps": 64460, "loss": 0.2494, "lr": 5.3365727241237765e-06, "epoch": 10.61433447098976, "percentage": 53.07, "elapsed_time": "1:03:10", "remaining_time": "0:55:51", "throughput": 5504.3, "total_tokens": 20864496} {"current_steps": 34215, "total_steps": 64460, "loss": 0.2139, "lr": 5.335221974521953e-06, "epoch": 10.615885820663978, "percentage": 53.08, "elapsed_time": "1:03:11", "remaining_time": "0:55:51", "throughput": 5504.37, "total_tokens": 20867632} {"current_steps": 34220, "total_steps": 64460, "loss": 0.2481, "lr": 5.333871200344393e-06, "epoch": 10.617437170338194, "percentage": 53.09, "elapsed_time": "1:03:11", "remaining_time": "0:55:50", "throughput": 5504.48, "total_tokens": 20870928} {"current_steps": 34225, "total_steps": 64460, "loss": 0.229, "lr": 5.332520401690119e-06, "epoch": 10.618988520012412, "percentage": 53.09, "elapsed_time": "1:03:12", "remaining_time": "0:55:50", "throughput": 5504.61, "total_tokens": 20874256} {"current_steps": 34230, "total_steps": 64460, "loss": 0.2298, "lr": 5.331169578658162e-06, "epoch": 10.620539869686628, "percentage": 53.1, "elapsed_time": "1:03:12", "remaining_time": "0:55:49", "throughput": 5504.74, "total_tokens": 20877648} {"current_steps": 34235, "total_steps": 64460, "loss": 0.2244, "lr": 5.3298187313475525e-06, "epoch": 10.622091219360843, "percentage": 53.11, "elapsed_time": "1:03:13", "remaining_time": "0:55:48", "throughput": 5504.94, "total_tokens": 20881392} {"current_steps": 34240, "total_steps": 64460, "loss": 0.2343, "lr": 5.328467859857325e-06, "epoch": 10.623642569035061, "percentage": 53.12, "elapsed_time": "1:03:13", "remaining_time": "0:55:48", "throughput": 5505.02, "total_tokens": 20884592} {"current_steps": 34245, "total_steps": 64460, "loss": 0.2185, "lr": 5.327116964286514e-06, "epoch": 10.625193918709277, "percentage": 53.13, "elapsed_time": "1:03:14", "remaining_time": "0:55:47", "throughput": 5505.11, "total_tokens": 20887440} {"current_steps": 34250, "total_steps": 64460, "loss": 0.2214, "lr": 5.325766044734156e-06, "epoch": 10.626745268383493, "percentage": 53.13, "elapsed_time": "1:03:14", "remaining_time": "0:55:47", "throughput": 5505.12, "total_tokens": 20890896} {"current_steps": 34255, "total_steps": 64460, "loss": 0.2369, "lr": 5.324415101299289e-06, "epoch": 10.62829661805771, "percentage": 53.14, "elapsed_time": "1:03:15", "remaining_time": "0:55:46", "throughput": 5505.14, "total_tokens": 20893840} {"current_steps": 34260, "total_steps": 64460, "loss": 0.2411, "lr": 5.323064134080953e-06, "epoch": 10.629847967731926, "percentage": 53.15, "elapsed_time": "1:03:15", "remaining_time": "0:55:46", "throughput": 5505.17, "total_tokens": 20896688} {"current_steps": 34265, "total_steps": 64460, "loss": 0.2288, "lr": 5.32171314317819e-06, "epoch": 10.631399317406144, "percentage": 53.16, "elapsed_time": "1:03:16", "remaining_time": "0:55:45", "throughput": 5505.21, "total_tokens": 20900176} {"current_steps": 34270, "total_steps": 64460, "loss": 0.2255, "lr": 5.3203621286900445e-06, "epoch": 10.63295066708036, "percentage": 53.16, "elapsed_time": "1:03:17", "remaining_time": "0:55:45", "throughput": 5505.53, "total_tokens": 20905616} {"current_steps": 34275, "total_steps": 64460, "loss": 0.2392, "lr": 5.31901109071556e-06, "epoch": 10.634502016754576, "percentage": 53.17, "elapsed_time": "1:03:17", "remaining_time": "0:55:44", "throughput": 5505.55, "total_tokens": 20908208} {"current_steps": 34280, "total_steps": 64460, "loss": 0.2472, "lr": 5.3176600293537875e-06, "epoch": 10.636053366428794, "percentage": 53.18, "elapsed_time": "1:03:18", "remaining_time": "0:55:43", "throughput": 5505.51, "total_tokens": 20910480} {"current_steps": 34285, "total_steps": 64460, "loss": 0.2321, "lr": 5.3163089447037705e-06, "epoch": 10.63760471610301, "percentage": 53.19, "elapsed_time": "1:03:18", "remaining_time": "0:55:43", "throughput": 5505.5, "total_tokens": 20913168} {"current_steps": 34290, "total_steps": 64460, "loss": 0.2347, "lr": 5.314957836864565e-06, "epoch": 10.639156065777225, "percentage": 53.2, "elapsed_time": "1:03:19", "remaining_time": "0:55:42", "throughput": 5505.73, "total_tokens": 20917936} {"current_steps": 34295, "total_steps": 64460, "loss": 0.2198, "lr": 5.313606705935218e-06, "epoch": 10.640707415451443, "percentage": 53.2, "elapsed_time": "1:03:19", "remaining_time": "0:55:42", "throughput": 5505.72, "total_tokens": 20920688} {"current_steps": 34300, "total_steps": 64460, "loss": 0.2355, "lr": 5.312255552014786e-06, "epoch": 10.642258765125659, "percentage": 53.21, "elapsed_time": "1:03:20", "remaining_time": "0:55:41", "throughput": 5505.75, "total_tokens": 20923280} {"current_steps": 34305, "total_steps": 64460, "loss": 0.2161, "lr": 5.310904375202326e-06, "epoch": 10.643810114799876, "percentage": 53.22, "elapsed_time": "1:03:20", "remaining_time": "0:55:40", "throughput": 5505.77, "total_tokens": 20925840} {"current_steps": 34310, "total_steps": 64460, "loss": 0.2334, "lr": 5.309553175596893e-06, "epoch": 10.645361464474092, "percentage": 53.23, "elapsed_time": "1:03:21", "remaining_time": "0:55:40", "throughput": 5505.88, "total_tokens": 20928976} {"current_steps": 34315, "total_steps": 64460, "loss": 0.2245, "lr": 5.3082019532975475e-06, "epoch": 10.646912814148308, "percentage": 53.23, "elapsed_time": "1:03:21", "remaining_time": "0:55:39", "throughput": 5505.9, "total_tokens": 20931664} {"current_steps": 34320, "total_steps": 64460, "loss": 0.2146, "lr": 5.306850708403347e-06, "epoch": 10.648464163822526, "percentage": 53.24, "elapsed_time": "1:03:22", "remaining_time": "0:55:39", "throughput": 5505.8, "total_tokens": 20933744} {"current_steps": 34325, "total_steps": 64460, "loss": 0.2319, "lr": 5.305499441013358e-06, "epoch": 10.650015513496742, "percentage": 53.25, "elapsed_time": "1:03:22", "remaining_time": "0:55:38", "throughput": 5505.91, "total_tokens": 20937232} {"current_steps": 34330, "total_steps": 64460, "loss": 0.2215, "lr": 5.30414815122664e-06, "epoch": 10.65156686317096, "percentage": 53.26, "elapsed_time": "1:03:23", "remaining_time": "0:55:37", "throughput": 5505.9, "total_tokens": 20940208} {"current_steps": 34335, "total_steps": 64460, "loss": 0.2403, "lr": 5.302796839142261e-06, "epoch": 10.653118212845175, "percentage": 53.27, "elapsed_time": "1:03:23", "remaining_time": "0:55:37", "throughput": 5505.77, "total_tokens": 20942640} {"current_steps": 34340, "total_steps": 64460, "loss": 0.2312, "lr": 5.301445504859291e-06, "epoch": 10.654669562519391, "percentage": 53.27, "elapsed_time": "1:03:24", "remaining_time": "0:55:36", "throughput": 5505.85, "total_tokens": 20945680} {"current_steps": 34345, "total_steps": 64460, "loss": 0.2316, "lr": 5.300094148476793e-06, "epoch": 10.656220912193609, "percentage": 53.28, "elapsed_time": "1:03:24", "remaining_time": "0:55:36", "throughput": 5505.85, "total_tokens": 20948528} {"current_steps": 34350, "total_steps": 64460, "loss": 0.2385, "lr": 5.298742770093841e-06, "epoch": 10.657772261867825, "percentage": 53.29, "elapsed_time": "1:03:25", "remaining_time": "0:55:35", "throughput": 5505.89, "total_tokens": 20951472} {"current_steps": 34355, "total_steps": 64460, "loss": 0.2135, "lr": 5.297391369809507e-06, "epoch": 10.659323611542042, "percentage": 53.3, "elapsed_time": "1:03:25", "remaining_time": "0:55:34", "throughput": 5505.91, "total_tokens": 20954384} {"current_steps": 34360, "total_steps": 64460, "loss": 0.233, "lr": 5.296039947722864e-06, "epoch": 10.660874961216258, "percentage": 53.3, "elapsed_time": "1:03:26", "remaining_time": "0:55:34", "throughput": 5505.78, "total_tokens": 20956752} {"current_steps": 34365, "total_steps": 64460, "loss": 0.2045, "lr": 5.294688503932986e-06, "epoch": 10.662426310890474, "percentage": 53.31, "elapsed_time": "1:03:26", "remaining_time": "0:55:33", "throughput": 5505.87, "total_tokens": 20960240} {"current_steps": 34370, "total_steps": 64460, "loss": 0.21, "lr": 5.293337038538952e-06, "epoch": 10.663977660564692, "percentage": 53.32, "elapsed_time": "1:03:27", "remaining_time": "0:55:33", "throughput": 5505.97, "total_tokens": 20963504} {"current_steps": 34375, "total_steps": 64460, "loss": 0.2201, "lr": 5.29198555163984e-06, "epoch": 10.665529010238908, "percentage": 53.33, "elapsed_time": "1:03:27", "remaining_time": "0:55:32", "throughput": 5506.12, "total_tokens": 20967152} {"current_steps": 34380, "total_steps": 64460, "loss": 0.2137, "lr": 5.290634043334728e-06, "epoch": 10.667080359913124, "percentage": 53.34, "elapsed_time": "1:03:28", "remaining_time": "0:55:32", "throughput": 5506.3, "total_tokens": 20971248} {"current_steps": 34385, "total_steps": 64460, "loss": 0.246, "lr": 5.2892825137227e-06, "epoch": 10.668631709587341, "percentage": 53.34, "elapsed_time": "1:03:29", "remaining_time": "0:55:31", "throughput": 5506.38, "total_tokens": 20974640} {"current_steps": 34390, "total_steps": 64460, "loss": 0.2225, "lr": 5.287930962902836e-06, "epoch": 10.670183059261557, "percentage": 53.35, "elapsed_time": "1:03:29", "remaining_time": "0:55:31", "throughput": 5506.37, "total_tokens": 20977552} {"current_steps": 34395, "total_steps": 64460, "loss": 0.2281, "lr": 5.2865793909742254e-06, "epoch": 10.671734408935775, "percentage": 53.36, "elapsed_time": "1:03:30", "remaining_time": "0:55:30", "throughput": 5506.33, "total_tokens": 20980176} {"current_steps": 34400, "total_steps": 64460, "loss": 0.2148, "lr": 5.2852277980359515e-06, "epoch": 10.67328575860999, "percentage": 53.37, "elapsed_time": "1:03:30", "remaining_time": "0:55:29", "throughput": 5506.23, "total_tokens": 20982896} {"current_steps": 34405, "total_steps": 64460, "loss": 0.2323, "lr": 5.283876184187102e-06, "epoch": 10.674837108284207, "percentage": 53.37, "elapsed_time": "1:03:31", "remaining_time": "0:55:29", "throughput": 5506.28, "total_tokens": 20986256} {"current_steps": 34410, "total_steps": 64460, "loss": 0.2296, "lr": 5.282524549526766e-06, "epoch": 10.676388457958424, "percentage": 53.38, "elapsed_time": "1:03:31", "remaining_time": "0:55:28", "throughput": 5506.3, "total_tokens": 20989104} {"current_steps": 34415, "total_steps": 64460, "loss": 0.2262, "lr": 5.281172894154036e-06, "epoch": 10.67793980763264, "percentage": 53.39, "elapsed_time": "1:03:32", "remaining_time": "0:55:28", "throughput": 5506.3, "total_tokens": 20992336} {"current_steps": 34420, "total_steps": 64460, "loss": 0.2206, "lr": 5.279821218168003e-06, "epoch": 10.679491157306856, "percentage": 53.4, "elapsed_time": "1:03:32", "remaining_time": "0:55:27", "throughput": 5506.24, "total_tokens": 20994640} {"current_steps": 34425, "total_steps": 64460, "loss": 0.2463, "lr": 5.27846952166776e-06, "epoch": 10.681042506981074, "percentage": 53.41, "elapsed_time": "1:03:33", "remaining_time": "0:55:27", "throughput": 5506.31, "total_tokens": 20997712} {"current_steps": 34430, "total_steps": 64460, "loss": 0.2331, "lr": 5.2771178047524054e-06, "epoch": 10.68259385665529, "percentage": 53.41, "elapsed_time": "1:03:33", "remaining_time": "0:55:26", "throughput": 5506.37, "total_tokens": 21000880} {"current_steps": 34435, "total_steps": 64460, "loss": 0.2066, "lr": 5.275766067521033e-06, "epoch": 10.684145206329507, "percentage": 53.42, "elapsed_time": "1:03:34", "remaining_time": "0:55:25", "throughput": 5506.41, "total_tokens": 21003760} {"current_steps": 34440, "total_steps": 64460, "loss": 0.2459, "lr": 5.274414310072742e-06, "epoch": 10.685696556003723, "percentage": 53.43, "elapsed_time": "1:03:34", "remaining_time": "0:55:25", "throughput": 5506.46, "total_tokens": 21006864} {"current_steps": 34445, "total_steps": 64460, "loss": 0.2083, "lr": 5.273062532506633e-06, "epoch": 10.687247905677939, "percentage": 53.44, "elapsed_time": "1:03:35", "remaining_time": "0:55:24", "throughput": 5506.46, "total_tokens": 21009488} {"current_steps": 34450, "total_steps": 64460, "loss": 0.2377, "lr": 5.271710734921806e-06, "epoch": 10.688799255352157, "percentage": 53.44, "elapsed_time": "1:03:35", "remaining_time": "0:55:24", "throughput": 5506.41, "total_tokens": 21012272} {"current_steps": 34455, "total_steps": 64460, "loss": 0.2132, "lr": 5.270358917417366e-06, "epoch": 10.690350605026373, "percentage": 53.45, "elapsed_time": "1:03:36", "remaining_time": "0:55:23", "throughput": 5506.36, "total_tokens": 21014800} {"current_steps": 34460, "total_steps": 64460, "loss": 0.2193, "lr": 5.269007080092414e-06, "epoch": 10.69190195470059, "percentage": 53.46, "elapsed_time": "1:03:37", "remaining_time": "0:55:23", "throughput": 5506.44, "total_tokens": 21018608} {"current_steps": 34465, "total_steps": 64460, "loss": 0.2344, "lr": 5.2676552230460586e-06, "epoch": 10.693453304374806, "percentage": 53.47, "elapsed_time": "1:03:37", "remaining_time": "0:55:22", "throughput": 5506.47, "total_tokens": 21021360} {"current_steps": 34470, "total_steps": 64460, "loss": 0.239, "lr": 5.266303346377406e-06, "epoch": 10.695004654049022, "percentage": 53.48, "elapsed_time": "1:03:38", "remaining_time": "0:55:21", "throughput": 5506.59, "total_tokens": 21025232} {"current_steps": 34475, "total_steps": 64460, "loss": 0.2185, "lr": 5.264951450185565e-06, "epoch": 10.69655600372324, "percentage": 53.48, "elapsed_time": "1:03:38", "remaining_time": "0:55:21", "throughput": 5506.56, "total_tokens": 21027760} {"current_steps": 34480, "total_steps": 64460, "loss": 0.2158, "lr": 5.263599534569644e-06, "epoch": 10.698107353397456, "percentage": 53.49, "elapsed_time": "1:03:39", "remaining_time": "0:55:20", "throughput": 5506.67, "total_tokens": 21031312} {"current_steps": 34485, "total_steps": 64460, "loss": 0.2389, "lr": 5.262247599628757e-06, "epoch": 10.699658703071673, "percentage": 53.5, "elapsed_time": "1:03:39", "remaining_time": "0:55:20", "throughput": 5506.78, "total_tokens": 21034640} {"current_steps": 34490, "total_steps": 64460, "loss": 0.2248, "lr": 5.260895645462015e-06, "epoch": 10.701210052745889, "percentage": 53.51, "elapsed_time": "1:03:40", "remaining_time": "0:55:19", "throughput": 5506.86, "total_tokens": 21037616} {"current_steps": 34495, "total_steps": 64460, "loss": 0.2069, "lr": 5.259543672168532e-06, "epoch": 10.702761402420105, "percentage": 53.51, "elapsed_time": "1:03:40", "remaining_time": "0:55:18", "throughput": 5506.87, "total_tokens": 21040272} {"current_steps": 34500, "total_steps": 64460, "loss": 0.271, "lr": 5.258191679847425e-06, "epoch": 10.704312752094323, "percentage": 53.52, "elapsed_time": "1:03:41", "remaining_time": "0:55:18", "throughput": 5506.84, "total_tokens": 21042896} {"current_steps": 34505, "total_steps": 64460, "loss": 0.2196, "lr": 5.256839668597809e-06, "epoch": 10.705864101768539, "percentage": 53.53, "elapsed_time": "1:03:41", "remaining_time": "0:55:17", "throughput": 5506.81, "total_tokens": 21045328} {"current_steps": 34510, "total_steps": 64460, "loss": 0.2405, "lr": 5.255487638518806e-06, "epoch": 10.707415451442754, "percentage": 53.54, "elapsed_time": "1:03:42", "remaining_time": "0:55:17", "throughput": 5506.94, "total_tokens": 21048720} {"current_steps": 34515, "total_steps": 64460, "loss": 0.2225, "lr": 5.254135589709533e-06, "epoch": 10.708966801116972, "percentage": 53.54, "elapsed_time": "1:03:42", "remaining_time": "0:55:16", "throughput": 5506.95, "total_tokens": 21051472} {"current_steps": 34520, "total_steps": 64460, "loss": 0.2134, "lr": 5.252783522269112e-06, "epoch": 10.710518150791188, "percentage": 53.55, "elapsed_time": "1:03:43", "remaining_time": "0:55:16", "throughput": 5506.82, "total_tokens": 21054096} {"current_steps": 34525, "total_steps": 64460, "loss": 0.2346, "lr": 5.2514314362966635e-06, "epoch": 10.712069500465406, "percentage": 53.56, "elapsed_time": "1:03:43", "remaining_time": "0:55:15", "throughput": 5506.9, "total_tokens": 21057456} {"current_steps": 34530, "total_steps": 64460, "loss": 0.2287, "lr": 5.2500793318913154e-06, "epoch": 10.713620850139622, "percentage": 53.57, "elapsed_time": "1:03:44", "remaining_time": "0:55:14", "throughput": 5506.93, "total_tokens": 21060208} {"current_steps": 34535, "total_steps": 64460, "loss": 0.2315, "lr": 5.24872720915219e-06, "epoch": 10.715172199813837, "percentage": 53.58, "elapsed_time": "1:03:44", "remaining_time": "0:55:14", "throughput": 5506.88, "total_tokens": 21063024} {"current_steps": 34540, "total_steps": 64460, "loss": 0.2017, "lr": 5.247375068178415e-06, "epoch": 10.716723549488055, "percentage": 53.58, "elapsed_time": "1:03:45", "remaining_time": "0:55:13", "throughput": 5507.06, "total_tokens": 21067152} {"current_steps": 34545, "total_steps": 64460, "loss": 0.223, "lr": 5.24602290906912e-06, "epoch": 10.718274899162271, "percentage": 53.59, "elapsed_time": "1:03:45", "remaining_time": "0:55:13", "throughput": 5507.17, "total_tokens": 21070352} {"current_steps": 34550, "total_steps": 64460, "loss": 0.2177, "lr": 5.24467073192343e-06, "epoch": 10.719826248836487, "percentage": 53.6, "elapsed_time": "1:03:46", "remaining_time": "0:55:12", "throughput": 5507.22, "total_tokens": 21073264} {"current_steps": 34555, "total_steps": 64460, "loss": 0.2352, "lr": 5.243318536840479e-06, "epoch": 10.721377598510704, "percentage": 53.61, "elapsed_time": "1:03:46", "remaining_time": "0:55:11", "throughput": 5507.21, "total_tokens": 21075888} {"current_steps": 34560, "total_steps": 64460, "loss": 0.2133, "lr": 5.241966323919397e-06, "epoch": 10.72292894818492, "percentage": 53.61, "elapsed_time": "1:03:47", "remaining_time": "0:55:11", "throughput": 5507.23, "total_tokens": 21078608} {"current_steps": 34565, "total_steps": 64460, "loss": 0.2271, "lr": 5.24061409325932e-06, "epoch": 10.724480297859138, "percentage": 53.62, "elapsed_time": "1:03:47", "remaining_time": "0:55:10", "throughput": 5507.21, "total_tokens": 21081136} {"current_steps": 34570, "total_steps": 64460, "loss": 0.2289, "lr": 5.239261844959379e-06, "epoch": 10.726031647533354, "percentage": 53.63, "elapsed_time": "1:03:48", "remaining_time": "0:55:10", "throughput": 5507.22, "total_tokens": 21083856} {"current_steps": 34575, "total_steps": 64460, "loss": 0.2272, "lr": 5.237909579118713e-06, "epoch": 10.72758299720757, "percentage": 53.64, "elapsed_time": "1:03:48", "remaining_time": "0:55:09", "throughput": 5507.17, "total_tokens": 21086352} {"current_steps": 34580, "total_steps": 64460, "loss": 0.2236, "lr": 5.236557295836457e-06, "epoch": 10.729134346881787, "percentage": 53.65, "elapsed_time": "1:03:49", "remaining_time": "0:55:09", "throughput": 5507.26, "total_tokens": 21090128} {"current_steps": 34585, "total_steps": 64460, "loss": 0.2066, "lr": 5.235204995211748e-06, "epoch": 10.730685696556003, "percentage": 53.65, "elapsed_time": "1:03:50", "remaining_time": "0:55:08", "throughput": 5507.42, "total_tokens": 21093840} {"current_steps": 34590, "total_steps": 64460, "loss": 0.229, "lr": 5.2338526773437295e-06, "epoch": 10.732237046230221, "percentage": 53.66, "elapsed_time": "1:03:50", "remaining_time": "0:55:07", "throughput": 5507.46, "total_tokens": 21096784} {"current_steps": 34595, "total_steps": 64460, "loss": 0.2223, "lr": 5.23250034233154e-06, "epoch": 10.733788395904437, "percentage": 53.67, "elapsed_time": "1:03:51", "remaining_time": "0:55:07", "throughput": 5507.5, "total_tokens": 21099632} {"current_steps": 34600, "total_steps": 64460, "loss": 0.2233, "lr": 5.231147990274322e-06, "epoch": 10.735339745578653, "percentage": 53.68, "elapsed_time": "1:03:51", "remaining_time": "0:55:06", "throughput": 5507.63, "total_tokens": 21103696} {"current_steps": 34605, "total_steps": 64460, "loss": 0.2346, "lr": 5.2297956212712195e-06, "epoch": 10.73689109525287, "percentage": 53.68, "elapsed_time": "1:03:52", "remaining_time": "0:55:06", "throughput": 5507.72, "total_tokens": 21106768} {"current_steps": 34610, "total_steps": 64460, "loss": 0.2444, "lr": 5.228443235421377e-06, "epoch": 10.738442444927086, "percentage": 53.69, "elapsed_time": "1:03:52", "remaining_time": "0:55:05", "throughput": 5507.76, "total_tokens": 21110032} {"current_steps": 34615, "total_steps": 64460, "loss": 0.2266, "lr": 5.22709083282394e-06, "epoch": 10.739993794601304, "percentage": 53.7, "elapsed_time": "1:03:53", "remaining_time": "0:55:05", "throughput": 5507.9, "total_tokens": 21114512} {"current_steps": 34620, "total_steps": 64460, "loss": 0.2251, "lr": 5.225738413578055e-06, "epoch": 10.74154514427552, "percentage": 53.71, "elapsed_time": "1:03:53", "remaining_time": "0:55:04", "throughput": 5507.89, "total_tokens": 21117136} {"current_steps": 34625, "total_steps": 64460, "loss": 0.2236, "lr": 5.224385977782873e-06, "epoch": 10.743096493949736, "percentage": 53.72, "elapsed_time": "1:03:54", "remaining_time": "0:55:04", "throughput": 5507.95, "total_tokens": 21120496} {"current_steps": 34630, "total_steps": 64460, "loss": 0.2284, "lr": 5.223033525537541e-06, "epoch": 10.744647843623953, "percentage": 53.72, "elapsed_time": "1:03:55", "remaining_time": "0:55:03", "throughput": 5507.88, "total_tokens": 21122832} {"current_steps": 34635, "total_steps": 64460, "loss": 0.2221, "lr": 5.221681056941209e-06, "epoch": 10.74619919329817, "percentage": 53.73, "elapsed_time": "1:03:55", "remaining_time": "0:55:02", "throughput": 5507.98, "total_tokens": 21125968} {"current_steps": 34640, "total_steps": 64460, "loss": 0.203, "lr": 5.220328572093032e-06, "epoch": 10.747750542972385, "percentage": 53.74, "elapsed_time": "1:03:56", "remaining_time": "0:55:02", "throughput": 5507.99, "total_tokens": 21128752} {"current_steps": 34645, "total_steps": 64460, "loss": 0.2306, "lr": 5.21897607109216e-06, "epoch": 10.749301892646603, "percentage": 53.75, "elapsed_time": "1:03:56", "remaining_time": "0:55:01", "throughput": 5508.06, "total_tokens": 21131664} {"current_steps": 34650, "total_steps": 64460, "loss": 0.2343, "lr": 5.217623554037751e-06, "epoch": 10.750853242320819, "percentage": 53.75, "elapsed_time": "1:03:57", "remaining_time": "0:55:01", "throughput": 5508.16, "total_tokens": 21135056} {"current_steps": 34655, "total_steps": 64460, "loss": 0.2301, "lr": 5.216271021028957e-06, "epoch": 10.752404591995036, "percentage": 53.76, "elapsed_time": "1:03:57", "remaining_time": "0:55:00", "throughput": 5508.27, "total_tokens": 21138288} {"current_steps": 34660, "total_steps": 64460, "loss": 0.2466, "lr": 5.214918472164936e-06, "epoch": 10.753955941669252, "percentage": 53.77, "elapsed_time": "1:03:58", "remaining_time": "0:54:59", "throughput": 5508.32, "total_tokens": 21141264} {"current_steps": 34665, "total_steps": 64460, "loss": 0.2237, "lr": 5.213565907544847e-06, "epoch": 10.755507291343468, "percentage": 53.78, "elapsed_time": "1:03:58", "remaining_time": "0:54:59", "throughput": 5508.38, "total_tokens": 21144368} {"current_steps": 34670, "total_steps": 64460, "loss": 0.2215, "lr": 5.2122133272678475e-06, "epoch": 10.757058641017686, "percentage": 53.79, "elapsed_time": "1:03:59", "remaining_time": "0:54:58", "throughput": 5508.42, "total_tokens": 21147152} {"current_steps": 34675, "total_steps": 64460, "loss": 0.2112, "lr": 5.2108607314330984e-06, "epoch": 10.758609990691902, "percentage": 53.79, "elapsed_time": "1:03:59", "remaining_time": "0:54:58", "throughput": 5508.39, "total_tokens": 21149808} {"current_steps": 34680, "total_steps": 64460, "loss": 0.2442, "lr": 5.20950812013976e-06, "epoch": 10.760161340366118, "percentage": 53.8, "elapsed_time": "1:04:00", "remaining_time": "0:54:57", "throughput": 5508.6, "total_tokens": 21154192} {"current_steps": 34685, "total_steps": 64460, "loss": 0.2375, "lr": 5.208155493486996e-06, "epoch": 10.761712690040335, "percentage": 53.81, "elapsed_time": "1:04:00", "remaining_time": "0:54:56", "throughput": 5508.58, "total_tokens": 21156656} {"current_steps": 34690, "total_steps": 64460, "loss": 0.2323, "lr": 5.20680285157397e-06, "epoch": 10.763264039714551, "percentage": 53.82, "elapsed_time": "1:04:01", "remaining_time": "0:54:56", "throughput": 5508.55, "total_tokens": 21159344} {"current_steps": 34695, "total_steps": 64460, "loss": 0.2502, "lr": 5.205450194499845e-06, "epoch": 10.764815389388769, "percentage": 53.82, "elapsed_time": "1:04:01", "remaining_time": "0:54:55", "throughput": 5508.59, "total_tokens": 21162224} {"current_steps": 34700, "total_steps": 64460, "loss": 0.2366, "lr": 5.204097522363788e-06, "epoch": 10.766366739062985, "percentage": 53.83, "elapsed_time": "1:04:02", "remaining_time": "0:54:55", "throughput": 5508.47, "total_tokens": 21164336} {"current_steps": 34705, "total_steps": 64460, "loss": 0.2101, "lr": 5.202744835264966e-06, "epoch": 10.7679180887372, "percentage": 53.84, "elapsed_time": "1:04:02", "remaining_time": "0:54:54", "throughput": 5508.53, "total_tokens": 21167440} {"current_steps": 34710, "total_steps": 64460, "loss": 0.2448, "lr": 5.201392133302547e-06, "epoch": 10.769469438411418, "percentage": 53.85, "elapsed_time": "1:04:03", "remaining_time": "0:54:53", "throughput": 5508.48, "total_tokens": 21169872} {"current_steps": 34715, "total_steps": 64460, "loss": 0.2306, "lr": 5.200039416575699e-06, "epoch": 10.771020788085634, "percentage": 53.86, "elapsed_time": "1:04:03", "remaining_time": "0:54:53", "throughput": 5508.67, "total_tokens": 21173808} {"current_steps": 34720, "total_steps": 64460, "loss": 0.2164, "lr": 5.1986866851835925e-06, "epoch": 10.772572137759852, "percentage": 53.86, "elapsed_time": "1:04:04", "remaining_time": "0:54:52", "throughput": 5508.82, "total_tokens": 21177360} {"current_steps": 34725, "total_steps": 64460, "loss": 0.2373, "lr": 5.197333939225401e-06, "epoch": 10.774123487434068, "percentage": 53.87, "elapsed_time": "1:04:04", "remaining_time": "0:54:52", "throughput": 5508.88, "total_tokens": 21180304} {"current_steps": 34730, "total_steps": 64460, "loss": 0.2412, "lr": 5.195981178800294e-06, "epoch": 10.775674837108284, "percentage": 53.88, "elapsed_time": "1:04:05", "remaining_time": "0:54:51", "throughput": 5509.02, "total_tokens": 21183920} {"current_steps": 34735, "total_steps": 64460, "loss": 0.2373, "lr": 5.194628404007446e-06, "epoch": 10.777226186782501, "percentage": 53.89, "elapsed_time": "1:04:05", "remaining_time": "0:54:51", "throughput": 5509.18, "total_tokens": 21187984} {"current_steps": 34740, "total_steps": 64460, "loss": 0.2449, "lr": 5.1932756149460305e-06, "epoch": 10.778777536456717, "percentage": 53.89, "elapsed_time": "1:04:06", "remaining_time": "0:54:50", "throughput": 5509.23, "total_tokens": 21190832} {"current_steps": 34745, "total_steps": 64460, "loss": 0.2203, "lr": 5.1919228117152245e-06, "epoch": 10.780328886130935, "percentage": 53.9, "elapsed_time": "1:04:06", "remaining_time": "0:54:49", "throughput": 5509.26, "total_tokens": 21193488} {"current_steps": 34750, "total_steps": 64460, "loss": 0.234, "lr": 5.190569994414204e-06, "epoch": 10.78188023580515, "percentage": 53.91, "elapsed_time": "1:04:07", "remaining_time": "0:54:49", "throughput": 5509.25, "total_tokens": 21196112} {"current_steps": 34755, "total_steps": 64460, "loss": 0.2316, "lr": 5.1892171631421464e-06, "epoch": 10.783431585479367, "percentage": 53.92, "elapsed_time": "1:04:07", "remaining_time": "0:54:48", "throughput": 5509.24, "total_tokens": 21198672} {"current_steps": 34760, "total_steps": 64460, "loss": 0.2189, "lr": 5.187864317998229e-06, "epoch": 10.784982935153584, "percentage": 53.92, "elapsed_time": "1:04:08", "remaining_time": "0:54:48", "throughput": 5509.3, "total_tokens": 21201552} {"current_steps": 34765, "total_steps": 64460, "loss": 0.2034, "lr": 5.1865114590816315e-06, "epoch": 10.7865342848278, "percentage": 53.93, "elapsed_time": "1:04:08", "remaining_time": "0:54:47", "throughput": 5509.37, "total_tokens": 21204528} {"current_steps": 34770, "total_steps": 64460, "loss": 0.2318, "lr": 5.185158586491537e-06, "epoch": 10.788085634502016, "percentage": 53.94, "elapsed_time": "1:04:09", "remaining_time": "0:54:47", "throughput": 5509.51, "total_tokens": 21208368} {"current_steps": 34775, "total_steps": 64460, "loss": 0.2134, "lr": 5.183805700327124e-06, "epoch": 10.789636984176234, "percentage": 53.95, "elapsed_time": "1:04:09", "remaining_time": "0:54:46", "throughput": 5509.52, "total_tokens": 21211504} {"current_steps": 34780, "total_steps": 64460, "loss": 0.209, "lr": 5.18245280068758e-06, "epoch": 10.79118833385045, "percentage": 53.96, "elapsed_time": "1:04:10", "remaining_time": "0:54:45", "throughput": 5509.59, "total_tokens": 21214672} {"current_steps": 34785, "total_steps": 64460, "loss": 0.2298, "lr": 5.181099887672082e-06, "epoch": 10.792739683524667, "percentage": 53.96, "elapsed_time": "1:04:10", "remaining_time": "0:54:45", "throughput": 5509.67, "total_tokens": 21217584} {"current_steps": 34790, "total_steps": 64460, "loss": 0.2294, "lr": 5.179746961379818e-06, "epoch": 10.794291033198883, "percentage": 53.97, "elapsed_time": "1:04:11", "remaining_time": "0:54:44", "throughput": 5509.66, "total_tokens": 21220272} {"current_steps": 34795, "total_steps": 64460, "loss": 0.2131, "lr": 5.178394021909974e-06, "epoch": 10.795842382873099, "percentage": 53.98, "elapsed_time": "1:04:11", "remaining_time": "0:54:44", "throughput": 5509.76, "total_tokens": 21223248} {"current_steps": 34800, "total_steps": 64460, "loss": 0.2378, "lr": 5.177041069361736e-06, "epoch": 10.797393732547317, "percentage": 53.99, "elapsed_time": "1:04:12", "remaining_time": "0:54:43", "throughput": 5509.66, "total_tokens": 21225328} {"current_steps": 34805, "total_steps": 64460, "loss": 0.2084, "lr": 5.17568810383429e-06, "epoch": 10.798945082221532, "percentage": 53.99, "elapsed_time": "1:04:12", "remaining_time": "0:54:42", "throughput": 5509.7, "total_tokens": 21228528} {"current_steps": 34810, "total_steps": 64460, "loss": 0.2193, "lr": 5.174335125426827e-06, "epoch": 10.800496431895748, "percentage": 54.0, "elapsed_time": "1:04:13", "remaining_time": "0:54:42", "throughput": 5509.81, "total_tokens": 21231920} {"current_steps": 34815, "total_steps": 64460, "loss": 0.2169, "lr": 5.172982134238533e-06, "epoch": 10.802047781569966, "percentage": 54.01, "elapsed_time": "1:04:13", "remaining_time": "0:54:41", "throughput": 5509.84, "total_tokens": 21234672} {"current_steps": 34820, "total_steps": 64460, "loss": 0.2303, "lr": 5.171629130368602e-06, "epoch": 10.803599131244182, "percentage": 54.02, "elapsed_time": "1:04:14", "remaining_time": "0:54:41", "throughput": 5509.93, "total_tokens": 21237776} {"current_steps": 34825, "total_steps": 64460, "loss": 0.2254, "lr": 5.170276113916222e-06, "epoch": 10.8051504809184, "percentage": 54.03, "elapsed_time": "1:04:15", "remaining_time": "0:54:40", "throughput": 5510.09, "total_tokens": 21241936} {"current_steps": 34830, "total_steps": 64460, "loss": 0.2302, "lr": 5.168923084980588e-06, "epoch": 10.806701830592615, "percentage": 54.03, "elapsed_time": "1:04:15", "remaining_time": "0:54:39", "throughput": 5510.11, "total_tokens": 21244720} {"current_steps": 34835, "total_steps": 64460, "loss": 0.2378, "lr": 5.16757004366089e-06, "epoch": 10.808253180266831, "percentage": 54.04, "elapsed_time": "1:04:16", "remaining_time": "0:54:39", "throughput": 5510.14, "total_tokens": 21247312} {"current_steps": 34840, "total_steps": 64460, "loss": 0.2181, "lr": 5.166216990056324e-06, "epoch": 10.809804529941049, "percentage": 54.05, "elapsed_time": "1:04:16", "remaining_time": "0:54:38", "throughput": 5510.22, "total_tokens": 21250320} {"current_steps": 34845, "total_steps": 64460, "loss": 0.2136, "lr": 5.164863924266085e-06, "epoch": 10.811355879615265, "percentage": 54.06, "elapsed_time": "1:04:17", "remaining_time": "0:54:38", "throughput": 5510.34, "total_tokens": 21253616} {"current_steps": 34850, "total_steps": 64460, "loss": 0.2321, "lr": 5.163510846389367e-06, "epoch": 10.812907229289483, "percentage": 54.06, "elapsed_time": "1:04:17", "remaining_time": "0:54:37", "throughput": 5510.36, "total_tokens": 21256720} {"current_steps": 34855, "total_steps": 64460, "loss": 0.1973, "lr": 5.162157756525368e-06, "epoch": 10.814458578963698, "percentage": 54.07, "elapsed_time": "1:04:18", "remaining_time": "0:54:36", "throughput": 5510.41, "total_tokens": 21259664} {"current_steps": 34860, "total_steps": 64460, "loss": 0.2283, "lr": 5.160804654773286e-06, "epoch": 10.816009928637914, "percentage": 54.08, "elapsed_time": "1:04:18", "remaining_time": "0:54:36", "throughput": 5510.47, "total_tokens": 21262480} {"current_steps": 34865, "total_steps": 64460, "loss": 0.224, "lr": 5.159451541232318e-06, "epoch": 10.817561278312132, "percentage": 54.09, "elapsed_time": "1:04:19", "remaining_time": "0:54:35", "throughput": 5510.64, "total_tokens": 21267120} {"current_steps": 34870, "total_steps": 64460, "loss": 0.2119, "lr": 5.1580984160016635e-06, "epoch": 10.819112627986348, "percentage": 54.1, "elapsed_time": "1:04:19", "remaining_time": "0:54:35", "throughput": 5510.56, "total_tokens": 21269232} {"current_steps": 34875, "total_steps": 64460, "loss": 0.2452, "lr": 5.156745279180524e-06, "epoch": 10.820663977660566, "percentage": 54.1, "elapsed_time": "1:04:20", "remaining_time": "0:54:34", "throughput": 5510.54, "total_tokens": 21271696} {"current_steps": 34880, "total_steps": 64460, "loss": 0.2272, "lr": 5.1553921308680985e-06, "epoch": 10.822215327334781, "percentage": 54.11, "elapsed_time": "1:04:20", "remaining_time": "0:54:34", "throughput": 5510.63, "total_tokens": 21275056} {"current_steps": 34885, "total_steps": 64460, "loss": 0.2443, "lr": 5.154038971163589e-06, "epoch": 10.823766677008997, "percentage": 54.12, "elapsed_time": "1:04:21", "remaining_time": "0:54:33", "throughput": 5510.63, "total_tokens": 21277680} {"current_steps": 34890, "total_steps": 64460, "loss": 0.2327, "lr": 5.1526858001662005e-06, "epoch": 10.825318026683215, "percentage": 54.13, "elapsed_time": "1:04:21", "remaining_time": "0:54:32", "throughput": 5510.57, "total_tokens": 21280336} {"current_steps": 34895, "total_steps": 64460, "loss": 0.2296, "lr": 5.151332617975133e-06, "epoch": 10.82686937635743, "percentage": 54.13, "elapsed_time": "1:04:22", "remaining_time": "0:54:32", "throughput": 5510.63, "total_tokens": 21283152} {"current_steps": 34900, "total_steps": 64460, "loss": 0.2373, "lr": 5.149979424689594e-06, "epoch": 10.828420726031647, "percentage": 54.14, "elapsed_time": "1:04:22", "remaining_time": "0:54:31", "throughput": 5510.63, "total_tokens": 21285712} {"current_steps": 34905, "total_steps": 64460, "loss": 0.2362, "lr": 5.1486262204087865e-06, "epoch": 10.829972075705864, "percentage": 54.15, "elapsed_time": "1:04:23", "remaining_time": "0:54:31", "throughput": 5510.57, "total_tokens": 21287952} {"current_steps": 34910, "total_steps": 64460, "loss": 0.2185, "lr": 5.147273005231918e-06, "epoch": 10.83152342538008, "percentage": 54.16, "elapsed_time": "1:04:23", "remaining_time": "0:54:30", "throughput": 5510.56, "total_tokens": 21290576} {"current_steps": 34915, "total_steps": 64460, "loss": 0.224, "lr": 5.145919779258193e-06, "epoch": 10.833074775054298, "percentage": 54.17, "elapsed_time": "1:04:24", "remaining_time": "0:54:29", "throughput": 5510.44, "total_tokens": 21292848} {"current_steps": 34920, "total_steps": 64460, "loss": 0.2314, "lr": 5.144566542586821e-06, "epoch": 10.834626124728514, "percentage": 54.17, "elapsed_time": "1:04:24", "remaining_time": "0:54:29", "throughput": 5510.33, "total_tokens": 21294896} {"current_steps": 34925, "total_steps": 64460, "loss": 0.2162, "lr": 5.143213295317009e-06, "epoch": 10.83617747440273, "percentage": 54.18, "elapsed_time": "1:04:25", "remaining_time": "0:54:28", "throughput": 5510.4, "total_tokens": 21297808} {"current_steps": 34930, "total_steps": 64460, "loss": 0.2309, "lr": 5.141860037547966e-06, "epoch": 10.837728824076947, "percentage": 54.19, "elapsed_time": "1:04:25", "remaining_time": "0:54:27", "throughput": 5510.35, "total_tokens": 21300208} {"current_steps": 34935, "total_steps": 64460, "loss": 0.2145, "lr": 5.140506769378904e-06, "epoch": 10.839280173751163, "percentage": 54.2, "elapsed_time": "1:04:25", "remaining_time": "0:54:27", "throughput": 5510.47, "total_tokens": 21303440} {"current_steps": 34940, "total_steps": 64460, "loss": 0.2205, "lr": 5.139153490909031e-06, "epoch": 10.84083152342538, "percentage": 54.2, "elapsed_time": "1:04:26", "remaining_time": "0:54:26", "throughput": 5510.62, "total_tokens": 21306992} {"current_steps": 34945, "total_steps": 64460, "loss": 0.231, "lr": 5.1378002022375596e-06, "epoch": 10.842382873099597, "percentage": 54.21, "elapsed_time": "1:04:27", "remaining_time": "0:54:26", "throughput": 5510.77, "total_tokens": 21311024} {"current_steps": 34950, "total_steps": 64460, "loss": 0.2364, "lr": 5.136446903463701e-06, "epoch": 10.843934222773813, "percentage": 54.22, "elapsed_time": "1:04:27", "remaining_time": "0:54:25", "throughput": 5510.69, "total_tokens": 21313520} {"current_steps": 34955, "total_steps": 64460, "loss": 0.2326, "lr": 5.135093594686669e-06, "epoch": 10.84548557244803, "percentage": 54.23, "elapsed_time": "1:04:28", "remaining_time": "0:54:25", "throughput": 5510.75, "total_tokens": 21316592} {"current_steps": 34960, "total_steps": 64460, "loss": 0.234, "lr": 5.133740276005676e-06, "epoch": 10.847036922122246, "percentage": 54.24, "elapsed_time": "1:04:28", "remaining_time": "0:54:24", "throughput": 5510.87, "total_tokens": 21319760} {"current_steps": 34965, "total_steps": 64460, "loss": 0.2328, "lr": 5.132386947519937e-06, "epoch": 10.848588271796462, "percentage": 54.24, "elapsed_time": "1:04:29", "remaining_time": "0:54:23", "throughput": 5510.98, "total_tokens": 21323088} {"current_steps": 34970, "total_steps": 64460, "loss": 0.2142, "lr": 5.131033609328668e-06, "epoch": 10.85013962147068, "percentage": 54.25, "elapsed_time": "1:04:29", "remaining_time": "0:54:23", "throughput": 5511.06, "total_tokens": 21326288} {"current_steps": 34975, "total_steps": 64460, "loss": 0.2215, "lr": 5.129680261531083e-06, "epoch": 10.851690971144896, "percentage": 54.26, "elapsed_time": "1:04:30", "remaining_time": "0:54:22", "throughput": 5511.17, "total_tokens": 21330032} {"current_steps": 34980, "total_steps": 64460, "loss": 0.2302, "lr": 5.128326904226401e-06, "epoch": 10.853242320819113, "percentage": 54.27, "elapsed_time": "1:04:30", "remaining_time": "0:54:22", "throughput": 5511.25, "total_tokens": 21333264} {"current_steps": 34985, "total_steps": 64460, "loss": 0.2346, "lr": 5.126973537513837e-06, "epoch": 10.85479367049333, "percentage": 54.27, "elapsed_time": "1:04:31", "remaining_time": "0:54:21", "throughput": 5511.19, "total_tokens": 21335504} {"current_steps": 34990, "total_steps": 64460, "loss": 0.2334, "lr": 5.125620161492607e-06, "epoch": 10.856345020167545, "percentage": 54.28, "elapsed_time": "1:04:31", "remaining_time": "0:54:20", "throughput": 5511.28, "total_tokens": 21338576} {"current_steps": 34995, "total_steps": 64460, "loss": 0.2322, "lr": 5.124266776261934e-06, "epoch": 10.857896369841763, "percentage": 54.29, "elapsed_time": "1:04:32", "remaining_time": "0:54:20", "throughput": 5511.39, "total_tokens": 21341808} {"current_steps": 35000, "total_steps": 64460, "loss": 0.2292, "lr": 5.122913381921033e-06, "epoch": 10.859447719515979, "percentage": 54.3, "elapsed_time": "1:04:32", "remaining_time": "0:54:19", "throughput": 5511.42, "total_tokens": 21344592} {"current_steps": 35005, "total_steps": 64460, "loss": 0.2259, "lr": 5.121559978569126e-06, "epoch": 10.860999069190196, "percentage": 54.3, "elapsed_time": "1:04:33", "remaining_time": "0:54:19", "throughput": 5511.52, "total_tokens": 21347824} {"current_steps": 35010, "total_steps": 64460, "loss": 0.2371, "lr": 5.120206566305433e-06, "epoch": 10.862550418864412, "percentage": 54.31, "elapsed_time": "1:04:33", "remaining_time": "0:54:18", "throughput": 5511.38, "total_tokens": 21349808} {"current_steps": 35015, "total_steps": 64460, "loss": 0.2408, "lr": 5.118853145229176e-06, "epoch": 10.864101768538628, "percentage": 54.32, "elapsed_time": "1:04:34", "remaining_time": "0:54:17", "throughput": 5511.35, "total_tokens": 21352272} {"current_steps": 35020, "total_steps": 64460, "loss": 0.2178, "lr": 5.117499715439574e-06, "epoch": 10.865653118212846, "percentage": 54.33, "elapsed_time": "1:04:34", "remaining_time": "0:54:17", "throughput": 5511.36, "total_tokens": 21354800} {"current_steps": 35025, "total_steps": 64460, "loss": 0.2117, "lr": 5.1161462770358524e-06, "epoch": 10.867204467887062, "percentage": 54.34, "elapsed_time": "1:04:35", "remaining_time": "0:54:16", "throughput": 5511.42, "total_tokens": 21358256} {"current_steps": 35030, "total_steps": 64460, "loss": 0.2358, "lr": 5.114792830117235e-06, "epoch": 10.868755817561278, "percentage": 54.34, "elapsed_time": "1:04:35", "remaining_time": "0:54:16", "throughput": 5511.41, "total_tokens": 21360912} {"current_steps": 35035, "total_steps": 64460, "loss": 0.2152, "lr": 5.113439374782942e-06, "epoch": 10.870307167235495, "percentage": 54.35, "elapsed_time": "1:04:36", "remaining_time": "0:54:15", "throughput": 5511.3, "total_tokens": 21362960} {"current_steps": 35040, "total_steps": 64460, "loss": 0.2208, "lr": 5.112085911132201e-06, "epoch": 10.871858516909711, "percentage": 54.36, "elapsed_time": "1:04:36", "remaining_time": "0:54:15", "throughput": 5511.48, "total_tokens": 21367792} {"current_steps": 35045, "total_steps": 64460, "loss": 0.227, "lr": 5.110732439264234e-06, "epoch": 10.873409866583929, "percentage": 54.37, "elapsed_time": "1:04:37", "remaining_time": "0:54:14", "throughput": 5511.53, "total_tokens": 21370576} {"current_steps": 35050, "total_steps": 64460, "loss": 0.2294, "lr": 5.109378959278268e-06, "epoch": 10.874961216258145, "percentage": 54.37, "elapsed_time": "1:04:37", "remaining_time": "0:54:13", "throughput": 5511.54, "total_tokens": 21373424} {"current_steps": 35055, "total_steps": 64460, "loss": 0.2273, "lr": 5.10802547127353e-06, "epoch": 10.87651256593236, "percentage": 54.38, "elapsed_time": "1:04:38", "remaining_time": "0:54:13", "throughput": 5511.51, "total_tokens": 21375856} {"current_steps": 35060, "total_steps": 64460, "loss": 0.2261, "lr": 5.1066719753492455e-06, "epoch": 10.878063915606578, "percentage": 54.39, "elapsed_time": "1:04:38", "remaining_time": "0:54:12", "throughput": 5511.64, "total_tokens": 21379184} {"current_steps": 35065, "total_steps": 64460, "loss": 0.2356, "lr": 5.1053184716046424e-06, "epoch": 10.879615265280794, "percentage": 54.4, "elapsed_time": "1:04:39", "remaining_time": "0:54:12", "throughput": 5511.58, "total_tokens": 21381488} {"current_steps": 35070, "total_steps": 64460, "loss": 0.2306, "lr": 5.103964960138947e-06, "epoch": 10.88116661495501, "percentage": 54.41, "elapsed_time": "1:04:39", "remaining_time": "0:54:11", "throughput": 5511.65, "total_tokens": 21384688} {"current_steps": 35075, "total_steps": 64460, "loss": 0.212, "lr": 5.102611441051389e-06, "epoch": 10.882717964629228, "percentage": 54.41, "elapsed_time": "1:04:40", "remaining_time": "0:54:10", "throughput": 5511.63, "total_tokens": 21387344} {"current_steps": 35080, "total_steps": 64460, "loss": 0.2202, "lr": 5.101257914441198e-06, "epoch": 10.884269314303443, "percentage": 54.42, "elapsed_time": "1:04:40", "remaining_time": "0:54:10", "throughput": 5511.57, "total_tokens": 21389712} {"current_steps": 35085, "total_steps": 64460, "loss": 0.2203, "lr": 5.099904380407602e-06, "epoch": 10.885820663977661, "percentage": 54.43, "elapsed_time": "1:04:41", "remaining_time": "0:54:09", "throughput": 5511.69, "total_tokens": 21393136} {"current_steps": 35090, "total_steps": 64460, "loss": 0.2349, "lr": 5.098550839049832e-06, "epoch": 10.887372013651877, "percentage": 54.44, "elapsed_time": "1:04:41", "remaining_time": "0:54:09", "throughput": 5511.67, "total_tokens": 21395664} {"current_steps": 35095, "total_steps": 64460, "loss": 0.2403, "lr": 5.0971972904671186e-06, "epoch": 10.888923363326093, "percentage": 54.44, "elapsed_time": "1:04:42", "remaining_time": "0:54:08", "throughput": 5511.79, "total_tokens": 21399280} {"current_steps": 35100, "total_steps": 64460, "loss": 0.2042, "lr": 5.095843734758693e-06, "epoch": 10.89047471300031, "percentage": 54.45, "elapsed_time": "1:04:42", "remaining_time": "0:54:07", "throughput": 5511.84, "total_tokens": 21402448} {"current_steps": 35105, "total_steps": 64460, "loss": 0.2384, "lr": 5.094490172023787e-06, "epoch": 10.892026062674526, "percentage": 54.46, "elapsed_time": "1:04:43", "remaining_time": "0:54:07", "throughput": 5511.93, "total_tokens": 21405712} {"current_steps": 35110, "total_steps": 64460, "loss": 0.2205, "lr": 5.093136602361632e-06, "epoch": 10.893577412348744, "percentage": 54.47, "elapsed_time": "1:04:43", "remaining_time": "0:54:06", "throughput": 5511.91, "total_tokens": 21408144} {"current_steps": 35115, "total_steps": 64460, "loss": 0.2181, "lr": 5.091783025871462e-06, "epoch": 10.89512876202296, "percentage": 54.48, "elapsed_time": "1:04:44", "remaining_time": "0:54:06", "throughput": 5511.89, "total_tokens": 21410608} {"current_steps": 35120, "total_steps": 64460, "loss": 0.2118, "lr": 5.090429442652508e-06, "epoch": 10.896680111697176, "percentage": 54.48, "elapsed_time": "1:04:44", "remaining_time": "0:54:05", "throughput": 5511.97, "total_tokens": 21413552} {"current_steps": 35125, "total_steps": 64460, "loss": 0.2487, "lr": 5.089075852804006e-06, "epoch": 10.898231461371394, "percentage": 54.49, "elapsed_time": "1:04:45", "remaining_time": "0:54:04", "throughput": 5512.02, "total_tokens": 21416368} {"current_steps": 35130, "total_steps": 64460, "loss": 0.232, "lr": 5.087722256425189e-06, "epoch": 10.89978281104561, "percentage": 54.5, "elapsed_time": "1:04:45", "remaining_time": "0:54:04", "throughput": 5512.14, "total_tokens": 21419632} {"current_steps": 35135, "total_steps": 64460, "loss": 0.2248, "lr": 5.086368653615292e-06, "epoch": 10.901334160719827, "percentage": 54.51, "elapsed_time": "1:04:46", "remaining_time": "0:54:03", "throughput": 5512.12, "total_tokens": 21422256} {"current_steps": 35140, "total_steps": 64460, "loss": 0.2477, "lr": 5.08501504447355e-06, "epoch": 10.902885510394043, "percentage": 54.51, "elapsed_time": "1:04:46", "remaining_time": "0:54:03", "throughput": 5512.1, "total_tokens": 21424880} {"current_steps": 35145, "total_steps": 64460, "loss": 0.2336, "lr": 5.0836614290991984e-06, "epoch": 10.904436860068259, "percentage": 54.52, "elapsed_time": "1:04:47", "remaining_time": "0:54:02", "throughput": 5512.16, "total_tokens": 21427888} {"current_steps": 35150, "total_steps": 64460, "loss": 0.2165, "lr": 5.082307807591473e-06, "epoch": 10.905988209742477, "percentage": 54.53, "elapsed_time": "1:04:47", "remaining_time": "0:54:01", "throughput": 5512.2, "total_tokens": 21430704} {"current_steps": 35155, "total_steps": 64460, "loss": 0.2211, "lr": 5.08095418004961e-06, "epoch": 10.907539559416692, "percentage": 54.54, "elapsed_time": "1:04:48", "remaining_time": "0:54:01", "throughput": 5512.21, "total_tokens": 21433520} {"current_steps": 35160, "total_steps": 64460, "loss": 0.2224, "lr": 5.079600546572847e-06, "epoch": 10.909090909090908, "percentage": 54.55, "elapsed_time": "1:04:48", "remaining_time": "0:54:00", "throughput": 5512.26, "total_tokens": 21436496} {"current_steps": 35165, "total_steps": 64460, "loss": 0.2191, "lr": 5.078246907260423e-06, "epoch": 10.910642258765126, "percentage": 54.55, "elapsed_time": "1:04:49", "remaining_time": "0:54:00", "throughput": 5512.24, "total_tokens": 21439216} {"current_steps": 35170, "total_steps": 64460, "loss": 0.2401, "lr": 5.076893262211573e-06, "epoch": 10.912193608439342, "percentage": 54.56, "elapsed_time": "1:04:49", "remaining_time": "0:53:59", "throughput": 5512.4, "total_tokens": 21442928} {"current_steps": 35175, "total_steps": 64460, "loss": 0.2148, "lr": 5.075539611525536e-06, "epoch": 10.91374495811356, "percentage": 54.57, "elapsed_time": "1:04:50", "remaining_time": "0:53:58", "throughput": 5512.45, "total_tokens": 21445680} {"current_steps": 35180, "total_steps": 64460, "loss": 0.2237, "lr": 5.074185955301552e-06, "epoch": 10.915296307787775, "percentage": 54.58, "elapsed_time": "1:04:50", "remaining_time": "0:53:58", "throughput": 5512.56, "total_tokens": 21449168} {"current_steps": 35185, "total_steps": 64460, "loss": 0.2141, "lr": 5.072832293638859e-06, "epoch": 10.916847657461991, "percentage": 54.58, "elapsed_time": "1:04:51", "remaining_time": "0:53:57", "throughput": 5512.71, "total_tokens": 21453296} {"current_steps": 35190, "total_steps": 64460, "loss": 0.2216, "lr": 5.071478626636696e-06, "epoch": 10.918399007136209, "percentage": 54.59, "elapsed_time": "1:04:52", "remaining_time": "0:53:57", "throughput": 5512.86, "total_tokens": 21458288} {"current_steps": 35195, "total_steps": 64460, "loss": 0.22, "lr": 5.070124954394302e-06, "epoch": 10.919950356810425, "percentage": 54.6, "elapsed_time": "1:04:52", "remaining_time": "0:53:57", "throughput": 5512.97, "total_tokens": 21461936} {"current_steps": 35200, "total_steps": 64460, "loss": 0.2259, "lr": 5.0687712770109195e-06, "epoch": 10.921501706484642, "percentage": 54.61, "elapsed_time": "1:04:53", "remaining_time": "0:53:56", "throughput": 5513.01, "total_tokens": 21464624} {"current_steps": 35205, "total_steps": 64460, "loss": 0.249, "lr": 5.0674175945857886e-06, "epoch": 10.923053056158858, "percentage": 54.62, "elapsed_time": "1:04:53", "remaining_time": "0:53:55", "throughput": 5513.01, "total_tokens": 21467472} {"current_steps": 35210, "total_steps": 64460, "loss": 0.2333, "lr": 5.066063907218148e-06, "epoch": 10.924604405833074, "percentage": 54.62, "elapsed_time": "1:04:54", "remaining_time": "0:53:55", "throughput": 5513.06, "total_tokens": 21470288} {"current_steps": 35215, "total_steps": 64460, "loss": 0.2305, "lr": 5.0647102150072416e-06, "epoch": 10.926155755507292, "percentage": 54.63, "elapsed_time": "1:04:54", "remaining_time": "0:53:54", "throughput": 5513.09, "total_tokens": 21472976} {"current_steps": 35220, "total_steps": 64460, "loss": 0.23, "lr": 5.06335651805231e-06, "epoch": 10.927707105181508, "percentage": 54.64, "elapsed_time": "1:04:55", "remaining_time": "0:53:53", "throughput": 5513.12, "total_tokens": 21475696} {"current_steps": 35225, "total_steps": 64460, "loss": 0.2082, "lr": 5.062002816452596e-06, "epoch": 10.929258454855724, "percentage": 54.65, "elapsed_time": "1:04:55", "remaining_time": "0:53:53", "throughput": 5513.2, "total_tokens": 21478960} {"current_steps": 35230, "total_steps": 64460, "loss": 0.2107, "lr": 5.060649110307342e-06, "epoch": 10.930809804529941, "percentage": 54.65, "elapsed_time": "1:04:56", "remaining_time": "0:53:52", "throughput": 5513.15, "total_tokens": 21481360} {"current_steps": 35235, "total_steps": 64460, "loss": 0.2254, "lr": 5.059295399715789e-06, "epoch": 10.932361154204157, "percentage": 54.66, "elapsed_time": "1:04:56", "remaining_time": "0:53:52", "throughput": 5513.07, "total_tokens": 21483600} {"current_steps": 35240, "total_steps": 64460, "loss": 0.256, "lr": 5.057941684777181e-06, "epoch": 10.933912503878375, "percentage": 54.67, "elapsed_time": "1:04:57", "remaining_time": "0:53:51", "throughput": 5513.04, "total_tokens": 21486416} {"current_steps": 35245, "total_steps": 64460, "loss": 0.2032, "lr": 5.056587965590761e-06, "epoch": 10.93546385355259, "percentage": 54.68, "elapsed_time": "1:04:57", "remaining_time": "0:53:51", "throughput": 5513.06, "total_tokens": 21489360} {"current_steps": 35250, "total_steps": 64460, "loss": 0.2396, "lr": 5.055234242255774e-06, "epoch": 10.937015203226807, "percentage": 54.69, "elapsed_time": "1:04:58", "remaining_time": "0:53:50", "throughput": 5513.0, "total_tokens": 21491952} {"current_steps": 35255, "total_steps": 64460, "loss": 0.2386, "lr": 5.053880514871462e-06, "epoch": 10.938566552901024, "percentage": 54.69, "elapsed_time": "1:04:59", "remaining_time": "0:53:49", "throughput": 5513.09, "total_tokens": 21495536} {"current_steps": 35260, "total_steps": 64460, "loss": 0.2381, "lr": 5.052526783537072e-06, "epoch": 10.94011790257524, "percentage": 54.7, "elapsed_time": "1:04:59", "remaining_time": "0:53:49", "throughput": 5513.31, "total_tokens": 21500752} {"current_steps": 35265, "total_steps": 64460, "loss": 0.2267, "lr": 5.051173048351845e-06, "epoch": 10.941669252249458, "percentage": 54.71, "elapsed_time": "1:05:00", "remaining_time": "0:53:48", "throughput": 5513.3, "total_tokens": 21503408} {"current_steps": 35270, "total_steps": 64460, "loss": 0.2414, "lr": 5.0498193094150275e-06, "epoch": 10.943220601923674, "percentage": 54.72, "elapsed_time": "1:05:00", "remaining_time": "0:53:48", "throughput": 5513.4, "total_tokens": 21506480} {"current_steps": 35275, "total_steps": 64460, "loss": 0.2581, "lr": 5.048465566825865e-06, "epoch": 10.94477195159789, "percentage": 54.72, "elapsed_time": "1:05:01", "remaining_time": "0:53:47", "throughput": 5513.47, "total_tokens": 21509328} {"current_steps": 35280, "total_steps": 64460, "loss": 0.2355, "lr": 5.047111820683603e-06, "epoch": 10.946323301272107, "percentage": 54.73, "elapsed_time": "1:05:01", "remaining_time": "0:53:47", "throughput": 5513.42, "total_tokens": 21511984} {"current_steps": 35285, "total_steps": 64460, "loss": 0.2226, "lr": 5.045758071087485e-06, "epoch": 10.947874650946323, "percentage": 54.74, "elapsed_time": "1:05:02", "remaining_time": "0:53:46", "throughput": 5513.48, "total_tokens": 21515248} {"current_steps": 35290, "total_steps": 64460, "loss": 0.2244, "lr": 5.04440431813676e-06, "epoch": 10.949426000620539, "percentage": 54.75, "elapsed_time": "1:05:02", "remaining_time": "0:53:45", "throughput": 5513.53, "total_tokens": 21518064} {"current_steps": 35295, "total_steps": 64460, "loss": 0.2317, "lr": 5.043050561930674e-06, "epoch": 10.950977350294757, "percentage": 54.75, "elapsed_time": "1:05:03", "remaining_time": "0:53:45", "throughput": 5513.47, "total_tokens": 21520336} {"current_steps": 35300, "total_steps": 64460, "loss": 0.1951, "lr": 5.04169680256847e-06, "epoch": 10.952528699968973, "percentage": 54.76, "elapsed_time": "1:05:03", "remaining_time": "0:53:44", "throughput": 5513.54, "total_tokens": 21523216} {"current_steps": 35305, "total_steps": 64460, "loss": 0.2448, "lr": 5.040343040149397e-06, "epoch": 10.95408004964319, "percentage": 54.77, "elapsed_time": "1:05:04", "remaining_time": "0:53:44", "throughput": 5513.53, "total_tokens": 21525648} {"current_steps": 35310, "total_steps": 64460, "loss": 0.239, "lr": 5.038989274772702e-06, "epoch": 10.955631399317406, "percentage": 54.78, "elapsed_time": "1:05:04", "remaining_time": "0:53:43", "throughput": 5513.52, "total_tokens": 21528240} {"current_steps": 35315, "total_steps": 64460, "loss": 0.2315, "lr": 5.037635506537632e-06, "epoch": 10.957182748991622, "percentage": 54.79, "elapsed_time": "1:05:05", "remaining_time": "0:53:42", "throughput": 5513.62, "total_tokens": 21531536} {"current_steps": 35320, "total_steps": 64460, "loss": 0.237, "lr": 5.0362817355434325e-06, "epoch": 10.95873409866584, "percentage": 54.79, "elapsed_time": "1:05:05", "remaining_time": "0:53:42", "throughput": 5513.71, "total_tokens": 21535280} {"current_steps": 35325, "total_steps": 64460, "loss": 0.2169, "lr": 5.034927961889352e-06, "epoch": 10.960285448340056, "percentage": 54.8, "elapsed_time": "1:05:06", "remaining_time": "0:53:41", "throughput": 5513.72, "total_tokens": 21537712} {"current_steps": 35330, "total_steps": 64460, "loss": 0.2247, "lr": 5.033574185674638e-06, "epoch": 10.961836798014273, "percentage": 54.81, "elapsed_time": "1:05:06", "remaining_time": "0:53:41", "throughput": 5513.81, "total_tokens": 21540880} {"current_steps": 35335, "total_steps": 64460, "loss": 0.2354, "lr": 5.03222040699854e-06, "epoch": 10.96338814768849, "percentage": 54.82, "elapsed_time": "1:05:07", "remaining_time": "0:53:40", "throughput": 5513.77, "total_tokens": 21543152} {"current_steps": 35340, "total_steps": 64460, "loss": 0.2284, "lr": 5.030866625960303e-06, "epoch": 10.964939497362705, "percentage": 54.82, "elapsed_time": "1:05:07", "remaining_time": "0:53:39", "throughput": 5513.84, "total_tokens": 21546512} {"current_steps": 35345, "total_steps": 64460, "loss": 0.2379, "lr": 5.029512842659178e-06, "epoch": 10.966490847036923, "percentage": 54.83, "elapsed_time": "1:05:08", "remaining_time": "0:53:39", "throughput": 5513.93, "total_tokens": 21550128} {"current_steps": 35350, "total_steps": 64460, "loss": 0.2306, "lr": 5.0281590571944114e-06, "epoch": 10.968042196711139, "percentage": 54.84, "elapsed_time": "1:05:08", "remaining_time": "0:53:38", "throughput": 5513.97, "total_tokens": 21552848} {"current_steps": 35355, "total_steps": 64460, "loss": 0.212, "lr": 5.026805269665254e-06, "epoch": 10.969593546385354, "percentage": 54.85, "elapsed_time": "1:05:09", "remaining_time": "0:53:38", "throughput": 5513.99, "total_tokens": 21555472} {"current_steps": 35360, "total_steps": 64460, "loss": 0.2467, "lr": 5.0254514801709505e-06, "epoch": 10.971144896059572, "percentage": 54.86, "elapsed_time": "1:05:09", "remaining_time": "0:53:37", "throughput": 5513.91, "total_tokens": 21557776} {"current_steps": 35365, "total_steps": 64460, "loss": 0.2111, "lr": 5.024097688810754e-06, "epoch": 10.972696245733788, "percentage": 54.86, "elapsed_time": "1:05:10", "remaining_time": "0:53:36", "throughput": 5514.0, "total_tokens": 21560784} {"current_steps": 35370, "total_steps": 64460, "loss": 0.2242, "lr": 5.02274389568391e-06, "epoch": 10.974247595408006, "percentage": 54.87, "elapsed_time": "1:05:10", "remaining_time": "0:53:36", "throughput": 5514.04, "total_tokens": 21563696} {"current_steps": 35375, "total_steps": 64460, "loss": 0.2328, "lr": 5.02139010088967e-06, "epoch": 10.975798945082222, "percentage": 54.88, "elapsed_time": "1:05:11", "remaining_time": "0:53:35", "throughput": 5513.98, "total_tokens": 21565904} {"current_steps": 35380, "total_steps": 64460, "loss": 0.2189, "lr": 5.020036304527283e-06, "epoch": 10.977350294756437, "percentage": 54.89, "elapsed_time": "1:05:11", "remaining_time": "0:53:35", "throughput": 5514.1, "total_tokens": 21569552} {"current_steps": 35385, "total_steps": 64460, "loss": 0.2234, "lr": 5.018682506695997e-06, "epoch": 10.978901644430655, "percentage": 54.89, "elapsed_time": "1:05:12", "remaining_time": "0:53:34", "throughput": 5514.16, "total_tokens": 21572400} {"current_steps": 35390, "total_steps": 64460, "loss": 0.2344, "lr": 5.017328707495063e-06, "epoch": 10.980452994104871, "percentage": 54.9, "elapsed_time": "1:05:12", "remaining_time": "0:53:33", "throughput": 5514.15, "total_tokens": 21575312} {"current_steps": 35395, "total_steps": 64460, "loss": 0.2267, "lr": 5.015974907023728e-06, "epoch": 10.982004343779089, "percentage": 54.91, "elapsed_time": "1:05:13", "remaining_time": "0:53:33", "throughput": 5514.25, "total_tokens": 21578512} {"current_steps": 35400, "total_steps": 64460, "loss": 0.2066, "lr": 5.0146211053812445e-06, "epoch": 10.983555693453305, "percentage": 54.92, "elapsed_time": "1:05:13", "remaining_time": "0:53:32", "throughput": 5514.34, "total_tokens": 21581712} {"current_steps": 35405, "total_steps": 64460, "loss": 0.2394, "lr": 5.013267302666859e-06, "epoch": 10.98510704312752, "percentage": 54.93, "elapsed_time": "1:05:14", "remaining_time": "0:53:32", "throughput": 5514.41, "total_tokens": 21584784} {"current_steps": 35410, "total_steps": 64460, "loss": 0.2327, "lr": 5.011913498979824e-06, "epoch": 10.986658392801738, "percentage": 54.93, "elapsed_time": "1:05:14", "remaining_time": "0:53:31", "throughput": 5514.57, "total_tokens": 21589168} {"current_steps": 35415, "total_steps": 64460, "loss": 0.2276, "lr": 5.010559694419388e-06, "epoch": 10.988209742475954, "percentage": 54.94, "elapsed_time": "1:05:15", "remaining_time": "0:53:31", "throughput": 5514.55, "total_tokens": 21591856} {"current_steps": 35420, "total_steps": 64460, "loss": 0.2218, "lr": 5.009205889084803e-06, "epoch": 10.98976109215017, "percentage": 54.95, "elapsed_time": "1:05:15", "remaining_time": "0:53:30", "throughput": 5514.71, "total_tokens": 21595280} {"current_steps": 35425, "total_steps": 64460, "loss": 0.2356, "lr": 5.007852083075316e-06, "epoch": 10.991312441824387, "percentage": 54.96, "elapsed_time": "1:05:16", "remaining_time": "0:53:29", "throughput": 5514.77, "total_tokens": 21598096} {"current_steps": 35430, "total_steps": 64460, "loss": 0.2487, "lr": 5.006498276490178e-06, "epoch": 10.992863791498603, "percentage": 54.96, "elapsed_time": "1:05:17", "remaining_time": "0:53:29", "throughput": 5514.96, "total_tokens": 21602960} {"current_steps": 35435, "total_steps": 64460, "loss": 0.2173, "lr": 5.005144469428641e-06, "epoch": 10.994415141172821, "percentage": 54.97, "elapsed_time": "1:05:17", "remaining_time": "0:53:28", "throughput": 5514.96, "total_tokens": 21605840} {"current_steps": 35440, "total_steps": 64460, "loss": 0.2351, "lr": 5.003790661989952e-06, "epoch": 10.995966490847037, "percentage": 54.98, "elapsed_time": "1:05:18", "remaining_time": "0:53:28", "throughput": 5514.96, "total_tokens": 21608880} {"current_steps": 35445, "total_steps": 64460, "loss": 0.2053, "lr": 5.002436854273364e-06, "epoch": 10.997517840521253, "percentage": 54.99, "elapsed_time": "1:05:19", "remaining_time": "0:53:28", "throughput": 5515.17, "total_tokens": 21614064} {"current_steps": 35450, "total_steps": 64460, "loss": 0.234, "lr": 5.001083046378125e-06, "epoch": 10.99906919019547, "percentage": 55.0, "elapsed_time": "1:05:19", "remaining_time": "0:53:27", "throughput": 5515.23, "total_tokens": 21617040} {"current_steps": 35455, "total_steps": 64460, "loss": 0.2223, "lr": 4.999729238403485e-06, "epoch": 11.000620539869686, "percentage": 55.0, "elapsed_time": "1:05:20", "remaining_time": "0:53:27", "throughput": 5514.88, "total_tokens": 21619664} {"current_steps": 35460, "total_steps": 64460, "loss": 0.2255, "lr": 4.998375430448696e-06, "epoch": 11.002171889543904, "percentage": 55.01, "elapsed_time": "1:05:20", "remaining_time": "0:53:26", "throughput": 5514.94, "total_tokens": 21622640} {"current_steps": 35465, "total_steps": 64460, "loss": 0.2101, "lr": 4.997021622613007e-06, "epoch": 11.00372323921812, "percentage": 55.02, "elapsed_time": "1:05:21", "remaining_time": "0:53:25", "throughput": 5515.04, "total_tokens": 21625808} {"current_steps": 35470, "total_steps": 64460, "loss": 0.2221, "lr": 4.995667814995668e-06, "epoch": 11.005274588892336, "percentage": 55.03, "elapsed_time": "1:05:21", "remaining_time": "0:53:25", "throughput": 5515.15, "total_tokens": 21629104} {"current_steps": 35475, "total_steps": 64460, "loss": 0.225, "lr": 4.99431400769593e-06, "epoch": 11.006825938566553, "percentage": 55.03, "elapsed_time": "1:05:22", "remaining_time": "0:53:24", "throughput": 5515.05, "total_tokens": 21631440} {"current_steps": 35480, "total_steps": 64460, "loss": 0.2374, "lr": 4.992960200813042e-06, "epoch": 11.00837728824077, "percentage": 55.04, "elapsed_time": "1:05:22", "remaining_time": "0:53:24", "throughput": 5515.08, "total_tokens": 21634608} {"current_steps": 35485, "total_steps": 64460, "loss": 0.2197, "lr": 4.991606394446255e-06, "epoch": 11.009928637914985, "percentage": 55.05, "elapsed_time": "1:05:23", "remaining_time": "0:53:23", "throughput": 5515.22, "total_tokens": 21637968} {"current_steps": 35490, "total_steps": 64460, "loss": 0.2267, "lr": 4.990252588694819e-06, "epoch": 11.011479987589203, "percentage": 55.06, "elapsed_time": "1:05:23", "remaining_time": "0:53:22", "throughput": 5515.36, "total_tokens": 21641424} {"current_steps": 35495, "total_steps": 64460, "loss": 0.2262, "lr": 4.988898783657983e-06, "epoch": 11.013031337263419, "percentage": 55.07, "elapsed_time": "1:05:24", "remaining_time": "0:53:22", "throughput": 5515.39, "total_tokens": 21644624} {"current_steps": 35500, "total_steps": 64460, "loss": 0.2255, "lr": 4.987544979434999e-06, "epoch": 11.014582686937636, "percentage": 55.07, "elapsed_time": "1:05:24", "remaining_time": "0:53:21", "throughput": 5515.39, "total_tokens": 21647280} {"current_steps": 35505, "total_steps": 64460, "loss": 0.2238, "lr": 4.9861911761251135e-06, "epoch": 11.016134036611852, "percentage": 55.08, "elapsed_time": "1:05:25", "remaining_time": "0:53:21", "throughput": 5515.42, "total_tokens": 21650224} {"current_steps": 35510, "total_steps": 64460, "loss": 0.2211, "lr": 4.984837373827578e-06, "epoch": 11.017685386286068, "percentage": 55.09, "elapsed_time": "1:05:25", "remaining_time": "0:53:20", "throughput": 5515.37, "total_tokens": 21652848} {"current_steps": 35515, "total_steps": 64460, "loss": 0.2312, "lr": 4.9834835726416435e-06, "epoch": 11.019236735960286, "percentage": 55.1, "elapsed_time": "1:05:26", "remaining_time": "0:53:20", "throughput": 5515.37, "total_tokens": 21655824} {"current_steps": 35520, "total_steps": 64460, "loss": 0.2298, "lr": 4.982129772666558e-06, "epoch": 11.020788085634502, "percentage": 55.1, "elapsed_time": "1:05:26", "remaining_time": "0:53:19", "throughput": 5515.27, "total_tokens": 21658064} {"current_steps": 35525, "total_steps": 64460, "loss": 0.2315, "lr": 4.980775974001573e-06, "epoch": 11.02233943530872, "percentage": 55.11, "elapsed_time": "1:05:27", "remaining_time": "0:53:18", "throughput": 5515.15, "total_tokens": 21660176} {"current_steps": 35530, "total_steps": 64460, "loss": 0.2234, "lr": 4.979422176745937e-06, "epoch": 11.023890784982935, "percentage": 55.12, "elapsed_time": "1:05:27", "remaining_time": "0:53:18", "throughput": 5515.18, "total_tokens": 21663344} {"current_steps": 35535, "total_steps": 64460, "loss": 0.2282, "lr": 4.978068380998899e-06, "epoch": 11.025442134657151, "percentage": 55.13, "elapsed_time": "1:05:28", "remaining_time": "0:53:17", "throughput": 5515.27, "total_tokens": 21666736} {"current_steps": 35540, "total_steps": 64460, "loss": 0.2316, "lr": 4.976714586859707e-06, "epoch": 11.026993484331369, "percentage": 55.13, "elapsed_time": "1:05:29", "remaining_time": "0:53:17", "throughput": 5515.45, "total_tokens": 21670928} {"current_steps": 35545, "total_steps": 64460, "loss": 0.2113, "lr": 4.9753607944276124e-06, "epoch": 11.028544834005585, "percentage": 55.14, "elapsed_time": "1:05:29", "remaining_time": "0:53:16", "throughput": 5515.43, "total_tokens": 21674192} {"current_steps": 35550, "total_steps": 64460, "loss": 0.2276, "lr": 4.9740070038018635e-06, "epoch": 11.0300961836798, "percentage": 55.15, "elapsed_time": "1:05:30", "remaining_time": "0:53:16", "throughput": 5515.52, "total_tokens": 21677648} {"current_steps": 35555, "total_steps": 64460, "loss": 0.2261, "lr": 4.972653215081708e-06, "epoch": 11.031647533354018, "percentage": 55.16, "elapsed_time": "1:05:30", "remaining_time": "0:53:15", "throughput": 5515.53, "total_tokens": 21680368} {"current_steps": 35560, "total_steps": 64460, "loss": 0.2205, "lr": 4.971299428366397e-06, "epoch": 11.033198883028234, "percentage": 55.17, "elapsed_time": "1:05:31", "remaining_time": "0:53:14", "throughput": 5515.58, "total_tokens": 21683216} {"current_steps": 35565, "total_steps": 64460, "loss": 0.2222, "lr": 4.969945643755178e-06, "epoch": 11.034750232702452, "percentage": 55.17, "elapsed_time": "1:05:31", "remaining_time": "0:53:14", "throughput": 5515.56, "total_tokens": 21685936} {"current_steps": 35570, "total_steps": 64460, "loss": 0.2208, "lr": 4.968591861347299e-06, "epoch": 11.036301582376668, "percentage": 55.18, "elapsed_time": "1:05:32", "remaining_time": "0:53:13", "throughput": 5515.55, "total_tokens": 21689008} {"current_steps": 35575, "total_steps": 64460, "loss": 0.2308, "lr": 4.9672380812420075e-06, "epoch": 11.037852932050884, "percentage": 55.19, "elapsed_time": "1:05:32", "remaining_time": "0:53:13", "throughput": 5515.63, "total_tokens": 21691952} {"current_steps": 35580, "total_steps": 64460, "loss": 0.2197, "lr": 4.965884303538553e-06, "epoch": 11.039404281725101, "percentage": 55.2, "elapsed_time": "1:05:33", "remaining_time": "0:53:12", "throughput": 5515.76, "total_tokens": 21695824} {"current_steps": 35585, "total_steps": 64460, "loss": 0.195, "lr": 4.964530528336184e-06, "epoch": 11.040955631399317, "percentage": 55.2, "elapsed_time": "1:05:33", "remaining_time": "0:53:12", "throughput": 5515.77, "total_tokens": 21698800} {"current_steps": 35590, "total_steps": 64460, "loss": 0.207, "lr": 4.963176755734146e-06, "epoch": 11.042506981073535, "percentage": 55.21, "elapsed_time": "1:05:34", "remaining_time": "0:53:11", "throughput": 5515.86, "total_tokens": 21702064} {"current_steps": 35595, "total_steps": 64460, "loss": 0.2428, "lr": 4.961822985831689e-06, "epoch": 11.04405833074775, "percentage": 55.22, "elapsed_time": "1:05:34", "remaining_time": "0:53:10", "throughput": 5515.73, "total_tokens": 21704144} {"current_steps": 35600, "total_steps": 64460, "loss": 0.2316, "lr": 4.960469218728058e-06, "epoch": 11.045609680421967, "percentage": 55.23, "elapsed_time": "1:05:35", "remaining_time": "0:53:10", "throughput": 5515.73, "total_tokens": 21707056} {"current_steps": 35605, "total_steps": 64460, "loss": 0.2314, "lr": 4.959115454522502e-06, "epoch": 11.047161030096184, "percentage": 55.24, "elapsed_time": "1:05:35", "remaining_time": "0:53:09", "throughput": 5515.65, "total_tokens": 21709328} {"current_steps": 35610, "total_steps": 64460, "loss": 0.2171, "lr": 4.957761693314268e-06, "epoch": 11.0487123797704, "percentage": 55.24, "elapsed_time": "1:05:36", "remaining_time": "0:53:09", "throughput": 5515.75, "total_tokens": 21712624} {"current_steps": 35615, "total_steps": 64460, "loss": 0.2307, "lr": 4.9564079352026e-06, "epoch": 11.050263729444616, "percentage": 55.25, "elapsed_time": "1:05:37", "remaining_time": "0:53:08", "throughput": 5515.77, "total_tokens": 21715632} {"current_steps": 35620, "total_steps": 64460, "loss": 0.1969, "lr": 4.955054180286748e-06, "epoch": 11.051815079118834, "percentage": 55.26, "elapsed_time": "1:05:37", "remaining_time": "0:53:08", "throughput": 5515.89, "total_tokens": 21718960} {"current_steps": 35625, "total_steps": 64460, "loss": 0.2122, "lr": 4.953700428665958e-06, "epoch": 11.05336642879305, "percentage": 55.27, "elapsed_time": "1:05:38", "remaining_time": "0:53:07", "throughput": 5515.87, "total_tokens": 21721712} {"current_steps": 35630, "total_steps": 64460, "loss": 0.2209, "lr": 4.952346680439473e-06, "epoch": 11.054917778467267, "percentage": 55.27, "elapsed_time": "1:05:38", "remaining_time": "0:53:06", "throughput": 5515.92, "total_tokens": 21724944} {"current_steps": 35635, "total_steps": 64460, "loss": 0.2297, "lr": 4.9509929357065415e-06, "epoch": 11.056469128141483, "percentage": 55.28, "elapsed_time": "1:05:39", "remaining_time": "0:53:06", "throughput": 5515.91, "total_tokens": 21727536} {"current_steps": 35640, "total_steps": 64460, "loss": 0.2201, "lr": 4.949639194566408e-06, "epoch": 11.058020477815699, "percentage": 55.29, "elapsed_time": "1:05:39", "remaining_time": "0:53:05", "throughput": 5516.0, "total_tokens": 21730896} {"current_steps": 35645, "total_steps": 64460, "loss": 0.2354, "lr": 4.9482854571183184e-06, "epoch": 11.059571827489917, "percentage": 55.3, "elapsed_time": "1:05:40", "remaining_time": "0:53:05", "throughput": 5516.03, "total_tokens": 21733616} {"current_steps": 35650, "total_steps": 64460, "loss": 0.2198, "lr": 4.946931723461516e-06, "epoch": 11.061123177164133, "percentage": 55.31, "elapsed_time": "1:05:40", "remaining_time": "0:53:04", "throughput": 5516.0, "total_tokens": 21736240} {"current_steps": 35655, "total_steps": 64460, "loss": 0.202, "lr": 4.945577993695248e-06, "epoch": 11.06267452683835, "percentage": 55.31, "elapsed_time": "1:05:41", "remaining_time": "0:53:03", "throughput": 5515.86, "total_tokens": 21738640} {"current_steps": 35660, "total_steps": 64460, "loss": 0.2212, "lr": 4.9442242679187555e-06, "epoch": 11.064225876512566, "percentage": 55.32, "elapsed_time": "1:05:41", "remaining_time": "0:53:03", "throughput": 5515.86, "total_tokens": 21741680} {"current_steps": 35665, "total_steps": 64460, "loss": 0.2307, "lr": 4.942870546231286e-06, "epoch": 11.065777226186782, "percentage": 55.33, "elapsed_time": "1:05:42", "remaining_time": "0:53:02", "throughput": 5515.93, "total_tokens": 21744848} {"current_steps": 35670, "total_steps": 64460, "loss": 0.2117, "lr": 4.941516828732082e-06, "epoch": 11.067328575861, "percentage": 55.34, "elapsed_time": "1:05:42", "remaining_time": "0:53:02", "throughput": 5515.85, "total_tokens": 21747312} {"current_steps": 35675, "total_steps": 64460, "loss": 0.2256, "lr": 4.940163115520386e-06, "epoch": 11.068879925535215, "percentage": 55.34, "elapsed_time": "1:05:43", "remaining_time": "0:53:01", "throughput": 5515.78, "total_tokens": 21749616} {"current_steps": 35680, "total_steps": 64460, "loss": 0.2495, "lr": 4.938809406695444e-06, "epoch": 11.070431275209431, "percentage": 55.35, "elapsed_time": "1:05:43", "remaining_time": "0:53:00", "throughput": 5515.77, "total_tokens": 21752176} {"current_steps": 35685, "total_steps": 64460, "loss": 0.2299, "lr": 4.937455702356496e-06, "epoch": 11.071982624883649, "percentage": 55.36, "elapsed_time": "1:05:44", "remaining_time": "0:53:00", "throughput": 5515.92, "total_tokens": 21756048} {"current_steps": 35690, "total_steps": 64460, "loss": 0.2176, "lr": 4.936102002602786e-06, "epoch": 11.073533974557865, "percentage": 55.37, "elapsed_time": "1:05:44", "remaining_time": "0:52:59", "throughput": 5515.98, "total_tokens": 21759088} {"current_steps": 35695, "total_steps": 64460, "loss": 0.2277, "lr": 4.934748307533556e-06, "epoch": 11.075085324232083, "percentage": 55.38, "elapsed_time": "1:05:45", "remaining_time": "0:52:59", "throughput": 5516.09, "total_tokens": 21762864} {"current_steps": 35700, "total_steps": 64460, "loss": 0.2306, "lr": 4.933394617248047e-06, "epoch": 11.076636673906298, "percentage": 55.38, "elapsed_time": "1:05:46", "remaining_time": "0:52:58", "throughput": 5516.28, "total_tokens": 21767376} {"current_steps": 35705, "total_steps": 64460, "loss": 0.2425, "lr": 4.932040931845502e-06, "epoch": 11.078188023580514, "percentage": 55.39, "elapsed_time": "1:05:46", "remaining_time": "0:52:58", "throughput": 5516.21, "total_tokens": 21769744} {"current_steps": 35710, "total_steps": 64460, "loss": 0.208, "lr": 4.930687251425162e-06, "epoch": 11.079739373254732, "percentage": 55.4, "elapsed_time": "1:05:47", "remaining_time": "0:52:57", "throughput": 5516.32, "total_tokens": 21773168} {"current_steps": 35715, "total_steps": 64460, "loss": 0.21, "lr": 4.929333576086266e-06, "epoch": 11.081290722928948, "percentage": 55.41, "elapsed_time": "1:05:47", "remaining_time": "0:52:57", "throughput": 5516.29, "total_tokens": 21775984} {"current_steps": 35720, "total_steps": 64460, "loss": 0.2158, "lr": 4.927979905928055e-06, "epoch": 11.082842072603166, "percentage": 55.41, "elapsed_time": "1:05:48", "remaining_time": "0:52:56", "throughput": 5516.3, "total_tokens": 21778864} {"current_steps": 35725, "total_steps": 64460, "loss": 0.2108, "lr": 4.926626241049771e-06, "epoch": 11.084393422277381, "percentage": 55.42, "elapsed_time": "1:05:48", "remaining_time": "0:52:56", "throughput": 5516.34, "total_tokens": 21782064} {"current_steps": 35730, "total_steps": 64460, "loss": 0.2071, "lr": 4.925272581550652e-06, "epoch": 11.085944771951597, "percentage": 55.43, "elapsed_time": "1:05:49", "remaining_time": "0:52:55", "throughput": 5516.35, "total_tokens": 21785104} {"current_steps": 35735, "total_steps": 64460, "loss": 0.2071, "lr": 4.923918927529939e-06, "epoch": 11.087496121625815, "percentage": 55.44, "elapsed_time": "1:05:49", "remaining_time": "0:52:54", "throughput": 5516.37, "total_tokens": 21788272} {"current_steps": 35740, "total_steps": 64460, "loss": 0.2205, "lr": 4.922565279086868e-06, "epoch": 11.08904747130003, "percentage": 55.45, "elapsed_time": "1:05:50", "remaining_time": "0:52:54", "throughput": 5516.43, "total_tokens": 21791248} {"current_steps": 35745, "total_steps": 64460, "loss": 0.2211, "lr": 4.921211636320681e-06, "epoch": 11.090598820974247, "percentage": 55.45, "elapsed_time": "1:05:50", "remaining_time": "0:52:53", "throughput": 5516.62, "total_tokens": 21795664} {"current_steps": 35750, "total_steps": 64460, "loss": 0.2298, "lr": 4.919857999330612e-06, "epoch": 11.092150170648464, "percentage": 55.46, "elapsed_time": "1:05:51", "remaining_time": "0:52:53", "throughput": 5516.6, "total_tokens": 21798384} {"current_steps": 35755, "total_steps": 64460, "loss": 0.2237, "lr": 4.918504368215901e-06, "epoch": 11.09370152032268, "percentage": 55.47, "elapsed_time": "1:05:51", "remaining_time": "0:52:52", "throughput": 5516.47, "total_tokens": 21800784} {"current_steps": 35760, "total_steps": 64460, "loss": 0.2523, "lr": 4.9171507430757856e-06, "epoch": 11.095252869996898, "percentage": 55.48, "elapsed_time": "1:05:52", "remaining_time": "0:52:52", "throughput": 5516.52, "total_tokens": 21803600} {"current_steps": 35765, "total_steps": 64460, "loss": 0.2265, "lr": 4.915797124009501e-06, "epoch": 11.096804219671114, "percentage": 55.48, "elapsed_time": "1:05:52", "remaining_time": "0:52:51", "throughput": 5516.52, "total_tokens": 21806288} {"current_steps": 35770, "total_steps": 64460, "loss": 0.2044, "lr": 4.914443511116285e-06, "epoch": 11.09835556934533, "percentage": 55.49, "elapsed_time": "1:05:53", "remaining_time": "0:52:50", "throughput": 5516.51, "total_tokens": 21808816} {"current_steps": 35775, "total_steps": 64460, "loss": 0.2455, "lr": 4.913089904495372e-06, "epoch": 11.099906919019547, "percentage": 55.5, "elapsed_time": "1:05:53", "remaining_time": "0:52:50", "throughput": 5516.54, "total_tokens": 21811792} {"current_steps": 35780, "total_steps": 64460, "loss": 0.2154, "lr": 4.911736304245997e-06, "epoch": 11.101458268693763, "percentage": 55.51, "elapsed_time": "1:05:54", "remaining_time": "0:52:49", "throughput": 5516.58, "total_tokens": 21814768} {"current_steps": 35785, "total_steps": 64460, "loss": 0.2356, "lr": 4.9103827104673985e-06, "epoch": 11.103009618367981, "percentage": 55.52, "elapsed_time": "1:05:55", "remaining_time": "0:52:49", "throughput": 5516.78, "total_tokens": 21819568} {"current_steps": 35790, "total_steps": 64460, "loss": 0.2164, "lr": 4.909029123258808e-06, "epoch": 11.104560968042197, "percentage": 55.52, "elapsed_time": "1:05:55", "remaining_time": "0:52:48", "throughput": 5516.74, "total_tokens": 21822192} {"current_steps": 35795, "total_steps": 64460, "loss": 0.2268, "lr": 4.90767554271946e-06, "epoch": 11.106112317716413, "percentage": 55.53, "elapsed_time": "1:05:56", "remaining_time": "0:52:48", "throughput": 5516.73, "total_tokens": 21825008} {"current_steps": 35800, "total_steps": 64460, "loss": 0.2242, "lr": 4.906321968948587e-06, "epoch": 11.10766366739063, "percentage": 55.54, "elapsed_time": "1:05:56", "remaining_time": "0:52:47", "throughput": 5516.53, "total_tokens": 21827088} {"current_steps": 35805, "total_steps": 64460, "loss": 0.2323, "lr": 4.904968402045425e-06, "epoch": 11.109215017064846, "percentage": 55.55, "elapsed_time": "1:05:57", "remaining_time": "0:52:47", "throughput": 5516.58, "total_tokens": 21830640} {"current_steps": 35810, "total_steps": 64460, "loss": 0.2198, "lr": 4.903614842109203e-06, "epoch": 11.110766366739062, "percentage": 55.55, "elapsed_time": "1:05:57", "remaining_time": "0:52:46", "throughput": 5516.54, "total_tokens": 21833040} {"current_steps": 35815, "total_steps": 64460, "loss": 0.2359, "lr": 4.902261289239155e-06, "epoch": 11.11231771641328, "percentage": 55.56, "elapsed_time": "1:05:58", "remaining_time": "0:52:45", "throughput": 5516.58, "total_tokens": 21835888} {"current_steps": 35820, "total_steps": 64460, "loss": 0.2269, "lr": 4.9009077435345114e-06, "epoch": 11.113869066087496, "percentage": 55.57, "elapsed_time": "1:05:58", "remaining_time": "0:52:45", "throughput": 5516.64, "total_tokens": 21839056} {"current_steps": 35825, "total_steps": 64460, "loss": 0.2053, "lr": 4.899554205094504e-06, "epoch": 11.115420415761713, "percentage": 55.58, "elapsed_time": "1:05:59", "remaining_time": "0:52:44", "throughput": 5516.79, "total_tokens": 21842832} {"current_steps": 35830, "total_steps": 64460, "loss": 0.2526, "lr": 4.8982006740183625e-06, "epoch": 11.11697176543593, "percentage": 55.58, "elapsed_time": "1:05:59", "remaining_time": "0:52:44", "throughput": 5516.8, "total_tokens": 21845776} {"current_steps": 35835, "total_steps": 64460, "loss": 0.2349, "lr": 4.8968471504053176e-06, "epoch": 11.118523115110145, "percentage": 55.59, "elapsed_time": "1:06:00", "remaining_time": "0:52:43", "throughput": 5516.89, "total_tokens": 21849008} {"current_steps": 35840, "total_steps": 64460, "loss": 0.2163, "lr": 4.895493634354596e-06, "epoch": 11.120074464784363, "percentage": 55.6, "elapsed_time": "1:06:00", "remaining_time": "0:52:42", "throughput": 5516.98, "total_tokens": 21852240} {"current_steps": 35845, "total_steps": 64460, "loss": 0.2317, "lr": 4.894140125965431e-06, "epoch": 11.121625814458579, "percentage": 55.61, "elapsed_time": "1:06:01", "remaining_time": "0:52:42", "throughput": 5516.9, "total_tokens": 21854480} {"current_steps": 35850, "total_steps": 64460, "loss": 0.2164, "lr": 4.892786625337047e-06, "epoch": 11.123177164132796, "percentage": 55.62, "elapsed_time": "1:06:01", "remaining_time": "0:52:41", "throughput": 5516.89, "total_tokens": 21857456} {"current_steps": 35855, "total_steps": 64460, "loss": 0.2009, "lr": 4.891433132568674e-06, "epoch": 11.124728513807012, "percentage": 55.62, "elapsed_time": "1:06:02", "remaining_time": "0:52:41", "throughput": 5516.89, "total_tokens": 21860112} {"current_steps": 35860, "total_steps": 64460, "loss": 0.2008, "lr": 4.890079647759537e-06, "epoch": 11.126279863481228, "percentage": 55.63, "elapsed_time": "1:06:02", "remaining_time": "0:52:40", "throughput": 5516.95, "total_tokens": 21862992} {"current_steps": 35865, "total_steps": 64460, "loss": 0.2214, "lr": 4.888726171008865e-06, "epoch": 11.127831213155446, "percentage": 55.64, "elapsed_time": "1:06:03", "remaining_time": "0:52:40", "throughput": 5517.11, "total_tokens": 21866672} {"current_steps": 35870, "total_steps": 64460, "loss": 0.2507, "lr": 4.887372702415882e-06, "epoch": 11.129382562829662, "percentage": 55.65, "elapsed_time": "1:06:03", "remaining_time": "0:52:39", "throughput": 5517.12, "total_tokens": 21869360} {"current_steps": 35875, "total_steps": 64460, "loss": 0.2568, "lr": 4.886019242079812e-06, "epoch": 11.130933912503878, "percentage": 55.65, "elapsed_time": "1:06:04", "remaining_time": "0:52:38", "throughput": 5517.23, "total_tokens": 21873360} {"current_steps": 35880, "total_steps": 64460, "loss": 0.2118, "lr": 4.884665790099882e-06, "epoch": 11.132485262178095, "percentage": 55.66, "elapsed_time": "1:06:05", "remaining_time": "0:52:38", "throughput": 5517.25, "total_tokens": 21876432} {"current_steps": 35885, "total_steps": 64460, "loss": 0.2175, "lr": 4.883312346575317e-06, "epoch": 11.134036611852311, "percentage": 55.67, "elapsed_time": "1:06:05", "remaining_time": "0:52:37", "throughput": 5517.31, "total_tokens": 21879504} {"current_steps": 35890, "total_steps": 64460, "loss": 0.2456, "lr": 4.881958911605337e-06, "epoch": 11.135587961526529, "percentage": 55.68, "elapsed_time": "1:06:06", "remaining_time": "0:52:37", "throughput": 5517.14, "total_tokens": 21881488} {"current_steps": 35895, "total_steps": 64460, "loss": 0.2452, "lr": 4.880605485289167e-06, "epoch": 11.137139311200745, "percentage": 55.69, "elapsed_time": "1:06:06", "remaining_time": "0:52:36", "throughput": 5517.29, "total_tokens": 21885360} {"current_steps": 35900, "total_steps": 64460, "loss": 0.1917, "lr": 4.879252067726027e-06, "epoch": 11.13869066087496, "percentage": 55.69, "elapsed_time": "1:06:07", "remaining_time": "0:52:36", "throughput": 5517.34, "total_tokens": 21888336} {"current_steps": 35905, "total_steps": 64460, "loss": 0.2499, "lr": 4.877898659015143e-06, "epoch": 11.140242010549178, "percentage": 55.7, "elapsed_time": "1:06:07", "remaining_time": "0:52:35", "throughput": 5517.4, "total_tokens": 21891248} {"current_steps": 35910, "total_steps": 64460, "loss": 0.219, "lr": 4.876545259255732e-06, "epoch": 11.141793360223394, "percentage": 55.71, "elapsed_time": "1:06:08", "remaining_time": "0:52:34", "throughput": 5517.44, "total_tokens": 21894064} {"current_steps": 35915, "total_steps": 64460, "loss": 0.2451, "lr": 4.875191868547016e-06, "epoch": 11.143344709897612, "percentage": 55.72, "elapsed_time": "1:06:08", "remaining_time": "0:52:34", "throughput": 5517.48, "total_tokens": 21896976} {"current_steps": 35920, "total_steps": 64460, "loss": 0.2437, "lr": 4.873838486988213e-06, "epoch": 11.144896059571828, "percentage": 55.72, "elapsed_time": "1:06:09", "remaining_time": "0:52:33", "throughput": 5517.47, "total_tokens": 21899792} {"current_steps": 35925, "total_steps": 64460, "loss": 0.2278, "lr": 4.872485114678544e-06, "epoch": 11.146447409246043, "percentage": 55.73, "elapsed_time": "1:06:09", "remaining_time": "0:52:33", "throughput": 5517.4, "total_tokens": 21902256} {"current_steps": 35930, "total_steps": 64460, "loss": 0.2254, "lr": 4.8711317517172255e-06, "epoch": 11.147998758920261, "percentage": 55.74, "elapsed_time": "1:06:10", "remaining_time": "0:52:32", "throughput": 5517.51, "total_tokens": 21905488} {"current_steps": 35935, "total_steps": 64460, "loss": 0.2042, "lr": 4.869778398203476e-06, "epoch": 11.149550108594477, "percentage": 55.75, "elapsed_time": "1:06:10", "remaining_time": "0:52:31", "throughput": 5517.54, "total_tokens": 21908336} {"current_steps": 35940, "total_steps": 64460, "loss": 0.2135, "lr": 4.868425054236512e-06, "epoch": 11.151101458268693, "percentage": 55.76, "elapsed_time": "1:06:11", "remaining_time": "0:52:31", "throughput": 5517.59, "total_tokens": 21911760} {"current_steps": 35945, "total_steps": 64460, "loss": 0.2093, "lr": 4.867071719915549e-06, "epoch": 11.15265280794291, "percentage": 55.76, "elapsed_time": "1:06:11", "remaining_time": "0:52:30", "throughput": 5517.54, "total_tokens": 21914352} {"current_steps": 35950, "total_steps": 64460, "loss": 0.2313, "lr": 4.865718395339803e-06, "epoch": 11.154204157617126, "percentage": 55.77, "elapsed_time": "1:06:12", "remaining_time": "0:52:30", "throughput": 5517.51, "total_tokens": 21916880} {"current_steps": 35955, "total_steps": 64460, "loss": 0.2036, "lr": 4.864365080608491e-06, "epoch": 11.155755507291344, "percentage": 55.78, "elapsed_time": "1:06:12", "remaining_time": "0:52:29", "throughput": 5517.45, "total_tokens": 21919344} {"current_steps": 35960, "total_steps": 64460, "loss": 0.1818, "lr": 4.8630117758208206e-06, "epoch": 11.15730685696556, "percentage": 55.79, "elapsed_time": "1:06:13", "remaining_time": "0:52:29", "throughput": 5517.45, "total_tokens": 21922608} {"current_steps": 35965, "total_steps": 64460, "loss": 0.198, "lr": 4.861658481076012e-06, "epoch": 11.158858206639776, "percentage": 55.79, "elapsed_time": "1:06:13", "remaining_time": "0:52:28", "throughput": 5517.49, "total_tokens": 21925968} {"current_steps": 35970, "total_steps": 64460, "loss": 0.2477, "lr": 4.860305196473274e-06, "epoch": 11.160409556313994, "percentage": 55.8, "elapsed_time": "1:06:14", "remaining_time": "0:52:27", "throughput": 5517.48, "total_tokens": 21928656} {"current_steps": 35975, "total_steps": 64460, "loss": 0.2294, "lr": 4.8589519221118205e-06, "epoch": 11.16196090598821, "percentage": 55.81, "elapsed_time": "1:06:15", "remaining_time": "0:52:27", "throughput": 5517.63, "total_tokens": 21933040} {"current_steps": 35980, "total_steps": 64460, "loss": 0.2007, "lr": 4.85759865809086e-06, "epoch": 11.163512255662427, "percentage": 55.82, "elapsed_time": "1:06:15", "remaining_time": "0:52:26", "throughput": 5517.68, "total_tokens": 21936080} {"current_steps": 35985, "total_steps": 64460, "loss": 0.235, "lr": 4.856245404509606e-06, "epoch": 11.165063605336643, "percentage": 55.83, "elapsed_time": "1:06:16", "remaining_time": "0:52:26", "throughput": 5517.67, "total_tokens": 21938768} {"current_steps": 35990, "total_steps": 64460, "loss": 0.2317, "lr": 4.854892161467265e-06, "epoch": 11.166614955010859, "percentage": 55.83, "elapsed_time": "1:06:16", "remaining_time": "0:52:25", "throughput": 5517.59, "total_tokens": 21941136} {"current_steps": 35995, "total_steps": 64460, "loss": 0.205, "lr": 4.853538929063047e-06, "epoch": 11.168166304685077, "percentage": 55.84, "elapsed_time": "1:06:17", "remaining_time": "0:52:25", "throughput": 5517.63, "total_tokens": 21944272} {"current_steps": 36000, "total_steps": 64460, "loss": 0.2771, "lr": 4.852185707396159e-06, "epoch": 11.169717654359292, "percentage": 55.85, "elapsed_time": "1:06:17", "remaining_time": "0:52:24", "throughput": 5517.78, "total_tokens": 21948624} {"current_steps": 36005, "total_steps": 64460, "loss": 0.2494, "lr": 4.85083249656581e-06, "epoch": 11.171269004033508, "percentage": 55.86, "elapsed_time": "1:06:18", "remaining_time": "0:52:24", "throughput": 5517.85, "total_tokens": 21951792} {"current_steps": 36010, "total_steps": 64460, "loss": 0.2148, "lr": 4.849479296671205e-06, "epoch": 11.172820353707726, "percentage": 55.86, "elapsed_time": "1:06:18", "remaining_time": "0:52:23", "throughput": 5517.97, "total_tokens": 21955440} {"current_steps": 36015, "total_steps": 64460, "loss": 0.2317, "lr": 4.84812610781155e-06, "epoch": 11.174371703381942, "percentage": 55.87, "elapsed_time": "1:06:19", "remaining_time": "0:52:22", "throughput": 5517.94, "total_tokens": 21958096} {"current_steps": 36020, "total_steps": 64460, "loss": 0.2042, "lr": 4.846772930086049e-06, "epoch": 11.17592305305616, "percentage": 55.88, "elapsed_time": "1:06:19", "remaining_time": "0:52:22", "throughput": 5518.06, "total_tokens": 21961552} {"current_steps": 36025, "total_steps": 64460, "loss": 0.2182, "lr": 4.845419763593907e-06, "epoch": 11.177474402730375, "percentage": 55.89, "elapsed_time": "1:06:20", "remaining_time": "0:52:21", "throughput": 5518.01, "total_tokens": 21964016} {"current_steps": 36030, "total_steps": 64460, "loss": 0.201, "lr": 4.844066608434328e-06, "epoch": 11.179025752404591, "percentage": 55.9, "elapsed_time": "1:06:20", "remaining_time": "0:52:21", "throughput": 5517.98, "total_tokens": 21966832} {"current_steps": 36035, "total_steps": 64460, "loss": 0.2235, "lr": 4.842713464706513e-06, "epoch": 11.180577102078809, "percentage": 55.9, "elapsed_time": "1:06:21", "remaining_time": "0:52:20", "throughput": 5517.99, "total_tokens": 21969904} {"current_steps": 36040, "total_steps": 64460, "loss": 0.2151, "lr": 4.841360332509663e-06, "epoch": 11.182128451753025, "percentage": 55.91, "elapsed_time": "1:06:21", "remaining_time": "0:52:20", "throughput": 5517.98, "total_tokens": 21972464} {"current_steps": 36045, "total_steps": 64460, "loss": 0.2254, "lr": 4.84000721194298e-06, "epoch": 11.183679801427242, "percentage": 55.92, "elapsed_time": "1:06:22", "remaining_time": "0:52:19", "throughput": 5517.91, "total_tokens": 21974832} {"current_steps": 36050, "total_steps": 64460, "loss": 0.2015, "lr": 4.8386541031056614e-06, "epoch": 11.185231151101458, "percentage": 55.93, "elapsed_time": "1:06:22", "remaining_time": "0:52:18", "throughput": 5517.88, "total_tokens": 21977456} {"current_steps": 36055, "total_steps": 64460, "loss": 0.2288, "lr": 4.837301006096909e-06, "epoch": 11.186782500775674, "percentage": 55.93, "elapsed_time": "1:06:23", "remaining_time": "0:52:18", "throughput": 5517.81, "total_tokens": 21979888} {"current_steps": 36060, "total_steps": 64460, "loss": 0.225, "lr": 4.835947921015919e-06, "epoch": 11.188333850449892, "percentage": 55.94, "elapsed_time": "1:06:23", "remaining_time": "0:52:17", "throughput": 5517.84, "total_tokens": 21982672} {"current_steps": 36065, "total_steps": 64460, "loss": 0.2106, "lr": 4.83459484796189e-06, "epoch": 11.189885200124108, "percentage": 55.95, "elapsed_time": "1:06:24", "remaining_time": "0:52:17", "throughput": 5517.98, "total_tokens": 21986960} {"current_steps": 36070, "total_steps": 64460, "loss": 0.2183, "lr": 4.833241787034016e-06, "epoch": 11.191436549798324, "percentage": 55.96, "elapsed_time": "1:06:25", "remaining_time": "0:52:16", "throughput": 5517.86, "total_tokens": 21989200} {"current_steps": 36075, "total_steps": 64460, "loss": 0.2312, "lr": 4.831888738331495e-06, "epoch": 11.192987899472541, "percentage": 55.96, "elapsed_time": "1:06:25", "remaining_time": "0:52:16", "throughput": 5517.92, "total_tokens": 21992496} {"current_steps": 36080, "total_steps": 64460, "loss": 0.2378, "lr": 4.830535701953517e-06, "epoch": 11.194539249146757, "percentage": 55.97, "elapsed_time": "1:06:26", "remaining_time": "0:52:15", "throughput": 5517.96, "total_tokens": 21995440} {"current_steps": 36085, "total_steps": 64460, "loss": 0.2245, "lr": 4.829182677999282e-06, "epoch": 11.196090598820975, "percentage": 55.98, "elapsed_time": "1:06:26", "remaining_time": "0:52:14", "throughput": 5518.0, "total_tokens": 21998640} {"current_steps": 36090, "total_steps": 64460, "loss": 0.2024, "lr": 4.8278296665679775e-06, "epoch": 11.19764194849519, "percentage": 55.99, "elapsed_time": "1:06:27", "remaining_time": "0:52:14", "throughput": 5518.08, "total_tokens": 22001808} {"current_steps": 36095, "total_steps": 64460, "loss": 0.2136, "lr": 4.826476667758798e-06, "epoch": 11.199193298169407, "percentage": 56.0, "elapsed_time": "1:06:27", "remaining_time": "0:52:13", "throughput": 5518.0, "total_tokens": 22004464} {"current_steps": 36100, "total_steps": 64460, "loss": 0.2093, "lr": 4.825123681670934e-06, "epoch": 11.200744647843624, "percentage": 56.0, "elapsed_time": "1:06:28", "remaining_time": "0:52:13", "throughput": 5517.87, "total_tokens": 22006704} {"current_steps": 36105, "total_steps": 64460, "loss": 0.2401, "lr": 4.823770708403574e-06, "epoch": 11.20229599751784, "percentage": 56.01, "elapsed_time": "1:06:28", "remaining_time": "0:52:12", "throughput": 5517.87, "total_tokens": 22009712} {"current_steps": 36110, "total_steps": 64460, "loss": 0.2745, "lr": 4.8224177480559095e-06, "epoch": 11.203847347192058, "percentage": 56.02, "elapsed_time": "1:06:29", "remaining_time": "0:52:11", "throughput": 5517.87, "total_tokens": 22012272} {"current_steps": 36115, "total_steps": 64460, "loss": 0.2342, "lr": 4.821064800727127e-06, "epoch": 11.205398696866274, "percentage": 56.03, "elapsed_time": "1:06:29", "remaining_time": "0:52:11", "throughput": 5517.95, "total_tokens": 22015664} {"current_steps": 36120, "total_steps": 64460, "loss": 0.2497, "lr": 4.8197118665164125e-06, "epoch": 11.20695004654049, "percentage": 56.03, "elapsed_time": "1:06:30", "remaining_time": "0:52:10", "throughput": 5518.0, "total_tokens": 22018736} {"current_steps": 36125, "total_steps": 64460, "loss": 0.2426, "lr": 4.818358945522954e-06, "epoch": 11.208501396214707, "percentage": 56.04, "elapsed_time": "1:06:30", "remaining_time": "0:52:10", "throughput": 5518.03, "total_tokens": 22021968} {"current_steps": 36130, "total_steps": 64460, "loss": 0.2151, "lr": 4.817006037845935e-06, "epoch": 11.210052745888923, "percentage": 56.05, "elapsed_time": "1:06:31", "remaining_time": "0:52:09", "throughput": 5518.14, "total_tokens": 22025360} {"current_steps": 36135, "total_steps": 64460, "loss": 0.2431, "lr": 4.81565314358454e-06, "epoch": 11.211604095563139, "percentage": 56.06, "elapsed_time": "1:06:32", "remaining_time": "0:52:09", "throughput": 5518.26, "total_tokens": 22029200} {"current_steps": 36140, "total_steps": 64460, "loss": 0.2253, "lr": 4.814300262837954e-06, "epoch": 11.213155445237357, "percentage": 56.07, "elapsed_time": "1:06:32", "remaining_time": "0:52:08", "throughput": 5518.29, "total_tokens": 22032048} {"current_steps": 36145, "total_steps": 64460, "loss": 0.2113, "lr": 4.812947395705357e-06, "epoch": 11.214706794911573, "percentage": 56.07, "elapsed_time": "1:06:33", "remaining_time": "0:52:08", "throughput": 5518.34, "total_tokens": 22035152} {"current_steps": 36150, "total_steps": 64460, "loss": 0.2058, "lr": 4.811594542285931e-06, "epoch": 11.21625814458579, "percentage": 56.08, "elapsed_time": "1:06:33", "remaining_time": "0:52:07", "throughput": 5518.38, "total_tokens": 22038288} {"current_steps": 36155, "total_steps": 64460, "loss": 0.208, "lr": 4.810241702678856e-06, "epoch": 11.217809494260006, "percentage": 56.09, "elapsed_time": "1:06:34", "remaining_time": "0:52:06", "throughput": 5518.36, "total_tokens": 22041072} {"current_steps": 36160, "total_steps": 64460, "loss": 0.2313, "lr": 4.808888876983312e-06, "epoch": 11.219360843934222, "percentage": 56.1, "elapsed_time": "1:06:34", "remaining_time": "0:52:06", "throughput": 5518.33, "total_tokens": 22043632} {"current_steps": 36165, "total_steps": 64460, "loss": 0.2249, "lr": 4.807536065298474e-06, "epoch": 11.22091219360844, "percentage": 56.1, "elapsed_time": "1:06:35", "remaining_time": "0:52:05", "throughput": 5518.24, "total_tokens": 22045904} {"current_steps": 36170, "total_steps": 64460, "loss": 0.2039, "lr": 4.806183267723523e-06, "epoch": 11.222463543282656, "percentage": 56.11, "elapsed_time": "1:06:35", "remaining_time": "0:52:05", "throughput": 5518.33, "total_tokens": 22049488} {"current_steps": 36175, "total_steps": 64460, "loss": 0.2121, "lr": 4.8048304843576344e-06, "epoch": 11.224014892956873, "percentage": 56.12, "elapsed_time": "1:06:36", "remaining_time": "0:52:04", "throughput": 5518.4, "total_tokens": 22053008} {"current_steps": 36180, "total_steps": 64460, "loss": 0.2436, "lr": 4.803477715299981e-06, "epoch": 11.22556624263109, "percentage": 56.13, "elapsed_time": "1:06:36", "remaining_time": "0:52:04", "throughput": 5518.4, "total_tokens": 22055856} {"current_steps": 36185, "total_steps": 64460, "loss": 0.218, "lr": 4.80212496064974e-06, "epoch": 11.227117592305305, "percentage": 56.14, "elapsed_time": "1:06:37", "remaining_time": "0:52:03", "throughput": 5518.35, "total_tokens": 22058416} {"current_steps": 36190, "total_steps": 64460, "loss": 0.2242, "lr": 4.800772220506081e-06, "epoch": 11.228668941979523, "percentage": 56.14, "elapsed_time": "1:06:37", "remaining_time": "0:52:02", "throughput": 5518.44, "total_tokens": 22062096} {"current_steps": 36195, "total_steps": 64460, "loss": 0.2393, "lr": 4.799419494968179e-06, "epoch": 11.230220291653739, "percentage": 56.15, "elapsed_time": "1:06:38", "remaining_time": "0:52:02", "throughput": 5518.39, "total_tokens": 22064432} {"current_steps": 36200, "total_steps": 64460, "loss": 0.2419, "lr": 4.798066784135202e-06, "epoch": 11.231771641327954, "percentage": 56.16, "elapsed_time": "1:06:38", "remaining_time": "0:52:01", "throughput": 5518.42, "total_tokens": 22067824} {"current_steps": 36205, "total_steps": 64460, "loss": 0.1986, "lr": 4.796714088106322e-06, "epoch": 11.233322991002172, "percentage": 56.17, "elapsed_time": "1:06:39", "remaining_time": "0:52:01", "throughput": 5518.45, "total_tokens": 22070864} {"current_steps": 36210, "total_steps": 64460, "loss": 0.2104, "lr": 4.795361406980706e-06, "epoch": 11.234874340676388, "percentage": 56.17, "elapsed_time": "1:06:40", "remaining_time": "0:52:00", "throughput": 5518.42, "total_tokens": 22073936} {"current_steps": 36215, "total_steps": 64460, "loss": 0.2106, "lr": 4.794008740857522e-06, "epoch": 11.236425690350606, "percentage": 56.18, "elapsed_time": "1:06:40", "remaining_time": "0:52:00", "throughput": 5518.56, "total_tokens": 22078128} {"current_steps": 36220, "total_steps": 64460, "loss": 0.2251, "lr": 4.792656089835936e-06, "epoch": 11.237977040024822, "percentage": 56.19, "elapsed_time": "1:06:41", "remaining_time": "0:51:59", "throughput": 5518.63, "total_tokens": 22081456} {"current_steps": 36225, "total_steps": 64460, "loss": 0.2349, "lr": 4.791303454015115e-06, "epoch": 11.239528389699037, "percentage": 56.2, "elapsed_time": "1:06:41", "remaining_time": "0:51:59", "throughput": 5518.79, "total_tokens": 22085616} {"current_steps": 36230, "total_steps": 64460, "loss": 0.2262, "lr": 4.789950833494221e-06, "epoch": 11.241079739373255, "percentage": 56.21, "elapsed_time": "1:06:42", "remaining_time": "0:51:58", "throughput": 5518.79, "total_tokens": 22088432} {"current_steps": 36235, "total_steps": 64460, "loss": 0.1863, "lr": 4.788598228372419e-06, "epoch": 11.242631089047471, "percentage": 56.21, "elapsed_time": "1:06:43", "remaining_time": "0:51:58", "throughput": 5518.98, "total_tokens": 22093104} {"current_steps": 36240, "total_steps": 64460, "loss": 0.2022, "lr": 4.7872456387488706e-06, "epoch": 11.244182438721689, "percentage": 56.22, "elapsed_time": "1:06:43", "remaining_time": "0:51:57", "throughput": 5519.15, "total_tokens": 22097232} {"current_steps": 36245, "total_steps": 64460, "loss": 0.218, "lr": 4.7858930647227356e-06, "epoch": 11.245733788395905, "percentage": 56.23, "elapsed_time": "1:06:44", "remaining_time": "0:51:57", "throughput": 5519.21, "total_tokens": 22100560} {"current_steps": 36250, "total_steps": 64460, "loss": 0.1978, "lr": 4.784540506393175e-06, "epoch": 11.24728513807012, "percentage": 56.24, "elapsed_time": "1:06:44", "remaining_time": "0:51:56", "throughput": 5519.18, "total_tokens": 22103312} {"current_steps": 36255, "total_steps": 64460, "loss": 0.2385, "lr": 4.783187963859346e-06, "epoch": 11.248836487744338, "percentage": 56.24, "elapsed_time": "1:06:45", "remaining_time": "0:51:55", "throughput": 5519.07, "total_tokens": 22105488} {"current_steps": 36260, "total_steps": 64460, "loss": 0.2168, "lr": 4.7818354372204075e-06, "epoch": 11.250387837418554, "percentage": 56.25, "elapsed_time": "1:06:45", "remaining_time": "0:51:55", "throughput": 5519.05, "total_tokens": 22108272} {"current_steps": 36265, "total_steps": 64460, "loss": 0.2374, "lr": 4.780482926575515e-06, "epoch": 11.25193918709277, "percentage": 56.26, "elapsed_time": "1:06:46", "remaining_time": "0:51:54", "throughput": 5519.01, "total_tokens": 22110768} {"current_steps": 36270, "total_steps": 64460, "loss": 0.2137, "lr": 4.779130432023823e-06, "epoch": 11.253490536766988, "percentage": 56.27, "elapsed_time": "1:06:46", "remaining_time": "0:51:54", "throughput": 5519.1, "total_tokens": 22114160} {"current_steps": 36275, "total_steps": 64460, "loss": 0.2559, "lr": 4.777777953664486e-06, "epoch": 11.255041886441203, "percentage": 56.28, "elapsed_time": "1:06:47", "remaining_time": "0:51:53", "throughput": 5519.13, "total_tokens": 22117328} {"current_steps": 36280, "total_steps": 64460, "loss": 0.2242, "lr": 4.776425491596656e-06, "epoch": 11.256593236115421, "percentage": 56.28, "elapsed_time": "1:06:48", "remaining_time": "0:51:53", "throughput": 5519.14, "total_tokens": 22120720} {"current_steps": 36285, "total_steps": 64460, "loss": 0.2348, "lr": 4.7750730459194845e-06, "epoch": 11.258144585789637, "percentage": 56.29, "elapsed_time": "1:06:48", "remaining_time": "0:51:52", "throughput": 5519.09, "total_tokens": 22123152} {"current_steps": 36290, "total_steps": 64460, "loss": 0.2125, "lr": 4.7737206167321236e-06, "epoch": 11.259695935463853, "percentage": 56.3, "elapsed_time": "1:06:48", "remaining_time": "0:51:51", "throughput": 5519.09, "total_tokens": 22125840} {"current_steps": 36295, "total_steps": 64460, "loss": 0.2314, "lr": 4.77236820413372e-06, "epoch": 11.26124728513807, "percentage": 56.31, "elapsed_time": "1:06:49", "remaining_time": "0:51:51", "throughput": 5519.16, "total_tokens": 22128944} {"current_steps": 36300, "total_steps": 64460, "loss": 0.2164, "lr": 4.771015808223423e-06, "epoch": 11.262798634812286, "percentage": 56.31, "elapsed_time": "1:06:50", "remaining_time": "0:51:50", "throughput": 5519.09, "total_tokens": 22131600} {"current_steps": 36305, "total_steps": 64460, "loss": 0.2102, "lr": 4.769663429100379e-06, "epoch": 11.264349984486504, "percentage": 56.32, "elapsed_time": "1:06:50", "remaining_time": "0:51:50", "throughput": 5519.05, "total_tokens": 22134160} {"current_steps": 36310, "total_steps": 64460, "loss": 0.2259, "lr": 4.768311066863734e-06, "epoch": 11.26590133416072, "percentage": 56.33, "elapsed_time": "1:06:50", "remaining_time": "0:51:49", "throughput": 5519.04, "total_tokens": 22136752} {"current_steps": 36315, "total_steps": 64460, "loss": 0.1961, "lr": 4.76695872161263e-06, "epoch": 11.267452683834936, "percentage": 56.34, "elapsed_time": "1:06:51", "remaining_time": "0:51:48", "throughput": 5519.06, "total_tokens": 22139472} {"current_steps": 36320, "total_steps": 64460, "loss": 0.1965, "lr": 4.765606393446212e-06, "epoch": 11.269004033509153, "percentage": 56.35, "elapsed_time": "1:06:51", "remaining_time": "0:51:48", "throughput": 5518.95, "total_tokens": 22141776} {"current_steps": 36325, "total_steps": 64460, "loss": 0.2455, "lr": 4.7642540824636205e-06, "epoch": 11.27055538318337, "percentage": 56.35, "elapsed_time": "1:06:52", "remaining_time": "0:51:47", "throughput": 5518.95, "total_tokens": 22144784} {"current_steps": 36330, "total_steps": 64460, "loss": 0.2447, "lr": 4.762901788763997e-06, "epoch": 11.272106732857585, "percentage": 56.36, "elapsed_time": "1:06:53", "remaining_time": "0:51:47", "throughput": 5519.18, "total_tokens": 22151312} {"current_steps": 36335, "total_steps": 64460, "loss": 0.2104, "lr": 4.76154951244648e-06, "epoch": 11.273658082531803, "percentage": 56.37, "elapsed_time": "1:06:53", "remaining_time": "0:51:47", "throughput": 5519.16, "total_tokens": 22153904} {"current_steps": 36340, "total_steps": 64460, "loss": 0.1965, "lr": 4.7601972536102075e-06, "epoch": 11.275209432206019, "percentage": 56.38, "elapsed_time": "1:06:54", "remaining_time": "0:51:46", "throughput": 5519.21, "total_tokens": 22156816} {"current_steps": 36345, "total_steps": 64460, "loss": 0.2138, "lr": 4.758845012354314e-06, "epoch": 11.276760781880236, "percentage": 56.38, "elapsed_time": "1:06:55", "remaining_time": "0:51:46", "throughput": 5519.4, "total_tokens": 22161968} {"current_steps": 36350, "total_steps": 64460, "loss": 0.2139, "lr": 4.757492788777939e-06, "epoch": 11.278312131554452, "percentage": 56.39, "elapsed_time": "1:06:55", "remaining_time": "0:51:45", "throughput": 5519.39, "total_tokens": 22164688} {"current_steps": 36355, "total_steps": 64460, "loss": 0.2681, "lr": 4.756140582980215e-06, "epoch": 11.279863481228668, "percentage": 56.4, "elapsed_time": "1:06:56", "remaining_time": "0:51:44", "throughput": 5519.4, "total_tokens": 22167440} {"current_steps": 36360, "total_steps": 64460, "loss": 0.1856, "lr": 4.7547883950602725e-06, "epoch": 11.281414830902886, "percentage": 56.41, "elapsed_time": "1:06:56", "remaining_time": "0:51:44", "throughput": 5519.59, "total_tokens": 22171824} {"current_steps": 36365, "total_steps": 64460, "loss": 0.2226, "lr": 4.753436225117244e-06, "epoch": 11.282966180577102, "percentage": 56.41, "elapsed_time": "1:06:57", "remaining_time": "0:51:43", "throughput": 5519.41, "total_tokens": 22173744} {"current_steps": 36370, "total_steps": 64460, "loss": 0.1891, "lr": 4.752084073250262e-06, "epoch": 11.28451753025132, "percentage": 56.42, "elapsed_time": "1:06:58", "remaining_time": "0:51:43", "throughput": 5519.52, "total_tokens": 22177680} {"current_steps": 36375, "total_steps": 64460, "loss": 0.2234, "lr": 4.750731939558451e-06, "epoch": 11.286068879925535, "percentage": 56.43, "elapsed_time": "1:06:58", "remaining_time": "0:51:42", "throughput": 5519.59, "total_tokens": 22180816} {"current_steps": 36380, "total_steps": 64460, "loss": 0.2547, "lr": 4.7493798241409415e-06, "epoch": 11.287620229599751, "percentage": 56.44, "elapsed_time": "1:06:59", "remaining_time": "0:51:42", "throughput": 5519.64, "total_tokens": 22183792} {"current_steps": 36385, "total_steps": 64460, "loss": 0.2028, "lr": 4.748027727096859e-06, "epoch": 11.289171579273969, "percentage": 56.45, "elapsed_time": "1:06:59", "remaining_time": "0:51:41", "throughput": 5519.62, "total_tokens": 22186576} {"current_steps": 36390, "total_steps": 64460, "loss": 0.212, "lr": 4.746675648525328e-06, "epoch": 11.290722928948185, "percentage": 56.45, "elapsed_time": "1:07:00", "remaining_time": "0:51:40", "throughput": 5519.53, "total_tokens": 22188912} {"current_steps": 36395, "total_steps": 64460, "loss": 0.2838, "lr": 4.745323588525471e-06, "epoch": 11.2922742786224, "percentage": 56.46, "elapsed_time": "1:07:00", "remaining_time": "0:51:40", "throughput": 5519.44, "total_tokens": 22191312} {"current_steps": 36400, "total_steps": 64460, "loss": 0.2141, "lr": 4.743971547196411e-06, "epoch": 11.293825628296618, "percentage": 56.47, "elapsed_time": "1:07:01", "remaining_time": "0:51:39", "throughput": 5519.46, "total_tokens": 22194064} {"current_steps": 36405, "total_steps": 64460, "loss": 0.2283, "lr": 4.742619524637267e-06, "epoch": 11.295376977970834, "percentage": 56.48, "elapsed_time": "1:07:01", "remaining_time": "0:51:39", "throughput": 5519.59, "total_tokens": 22198480} {"current_steps": 36410, "total_steps": 64460, "loss": 0.2133, "lr": 4.741267520947162e-06, "epoch": 11.296928327645052, "percentage": 56.48, "elapsed_time": "1:07:02", "remaining_time": "0:51:38", "throughput": 5519.6, "total_tokens": 22201232} {"current_steps": 36415, "total_steps": 64460, "loss": 0.2111, "lr": 4.7399155362252106e-06, "epoch": 11.298479677319268, "percentage": 56.49, "elapsed_time": "1:07:02", "remaining_time": "0:51:38", "throughput": 5519.65, "total_tokens": 22204432} {"current_steps": 36420, "total_steps": 64460, "loss": 0.2183, "lr": 4.7385635705705305e-06, "epoch": 11.300031026993484, "percentage": 56.5, "elapsed_time": "1:07:03", "remaining_time": "0:51:37", "throughput": 5519.79, "total_tokens": 22208176} {"current_steps": 36425, "total_steps": 64460, "loss": 0.2529, "lr": 4.737211624082237e-06, "epoch": 11.301582376667701, "percentage": 56.51, "elapsed_time": "1:07:03", "remaining_time": "0:51:37", "throughput": 5519.86, "total_tokens": 22211504} {"current_steps": 36430, "total_steps": 64460, "loss": 0.1918, "lr": 4.735859696859443e-06, "epoch": 11.303133726341917, "percentage": 56.52, "elapsed_time": "1:07:04", "remaining_time": "0:51:36", "throughput": 5519.84, "total_tokens": 22214160} {"current_steps": 36435, "total_steps": 64460, "loss": 0.2092, "lr": 4.734507789001261e-06, "epoch": 11.304685076016135, "percentage": 56.52, "elapsed_time": "1:07:04", "remaining_time": "0:51:35", "throughput": 5519.82, "total_tokens": 22216976} {"current_steps": 36440, "total_steps": 64460, "loss": 0.2481, "lr": 4.733155900606802e-06, "epoch": 11.30623642569035, "percentage": 56.53, "elapsed_time": "1:07:05", "remaining_time": "0:51:35", "throughput": 5519.72, "total_tokens": 22219376} {"current_steps": 36445, "total_steps": 64460, "loss": 0.216, "lr": 4.731804031775175e-06, "epoch": 11.307787775364567, "percentage": 56.54, "elapsed_time": "1:07:06", "remaining_time": "0:51:34", "throughput": 5519.97, "total_tokens": 22224176} {"current_steps": 36450, "total_steps": 64460, "loss": 0.2369, "lr": 4.730452182605489e-06, "epoch": 11.309339125038784, "percentage": 56.55, "elapsed_time": "1:07:06", "remaining_time": "0:51:34", "throughput": 5519.91, "total_tokens": 22226896} {"current_steps": 36455, "total_steps": 64460, "loss": 0.2031, "lr": 4.72910035319685e-06, "epoch": 11.310890474713, "percentage": 56.55, "elapsed_time": "1:07:07", "remaining_time": "0:51:33", "throughput": 5519.88, "total_tokens": 22229808} {"current_steps": 36460, "total_steps": 64460, "loss": 0.2456, "lr": 4.727748543648362e-06, "epoch": 11.312441824387218, "percentage": 56.56, "elapsed_time": "1:07:07", "remaining_time": "0:51:33", "throughput": 5520.14, "total_tokens": 22235024} {"current_steps": 36465, "total_steps": 64460, "loss": 0.2205, "lr": 4.72639675405913e-06, "epoch": 11.313993174061434, "percentage": 56.57, "elapsed_time": "1:07:08", "remaining_time": "0:51:32", "throughput": 5520.19, "total_tokens": 22237872} {"current_steps": 36470, "total_steps": 64460, "loss": 0.2351, "lr": 4.725044984528256e-06, "epoch": 11.31554452373565, "percentage": 56.58, "elapsed_time": "1:07:08", "remaining_time": "0:51:32", "throughput": 5520.27, "total_tokens": 22240784} {"current_steps": 36475, "total_steps": 64460, "loss": 0.2294, "lr": 4.7236932351548405e-06, "epoch": 11.317095873409867, "percentage": 56.59, "elapsed_time": "1:07:09", "remaining_time": "0:51:31", "throughput": 5520.31, "total_tokens": 22243504} {"current_steps": 36480, "total_steps": 64460, "loss": 0.2099, "lr": 4.722341506037984e-06, "epoch": 11.318647223084083, "percentage": 56.59, "elapsed_time": "1:07:09", "remaining_time": "0:51:30", "throughput": 5520.38, "total_tokens": 22246320} {"current_steps": 36485, "total_steps": 64460, "loss": 0.2073, "lr": 4.720989797276782e-06, "epoch": 11.320198572758299, "percentage": 56.6, "elapsed_time": "1:07:10", "remaining_time": "0:51:30", "throughput": 5520.45, "total_tokens": 22249680} {"current_steps": 36490, "total_steps": 64460, "loss": 0.2133, "lr": 4.7196381089703316e-06, "epoch": 11.321749922432517, "percentage": 56.61, "elapsed_time": "1:07:10", "remaining_time": "0:51:29", "throughput": 5520.52, "total_tokens": 22252848} {"current_steps": 36495, "total_steps": 64460, "loss": 0.2046, "lr": 4.718286441217728e-06, "epoch": 11.323301272106733, "percentage": 56.62, "elapsed_time": "1:07:11", "remaining_time": "0:51:29", "throughput": 5520.57, "total_tokens": 22256112} {"current_steps": 36500, "total_steps": 64460, "loss": 0.2126, "lr": 4.716934794118065e-06, "epoch": 11.32485262178095, "percentage": 56.62, "elapsed_time": "1:07:11", "remaining_time": "0:51:28", "throughput": 5520.56, "total_tokens": 22258896} {"current_steps": 36505, "total_steps": 64460, "loss": 0.2407, "lr": 4.715583167770433e-06, "epoch": 11.326403971455166, "percentage": 56.63, "elapsed_time": "1:07:12", "remaining_time": "0:51:28", "throughput": 5520.57, "total_tokens": 22261712} {"current_steps": 36510, "total_steps": 64460, "loss": 0.2289, "lr": 4.714231562273923e-06, "epoch": 11.327955321129382, "percentage": 56.64, "elapsed_time": "1:07:12", "remaining_time": "0:51:27", "throughput": 5520.64, "total_tokens": 22264592} {"current_steps": 36515, "total_steps": 64460, "loss": 0.218, "lr": 4.712879977727623e-06, "epoch": 11.3295066708036, "percentage": 56.65, "elapsed_time": "1:07:13", "remaining_time": "0:51:26", "throughput": 5520.76, "total_tokens": 22268464} {"current_steps": 36520, "total_steps": 64460, "loss": 0.2289, "lr": 4.711528414230621e-06, "epoch": 11.331058020477816, "percentage": 56.66, "elapsed_time": "1:07:14", "remaining_time": "0:51:26", "throughput": 5520.82, "total_tokens": 22271792} {"current_steps": 36525, "total_steps": 64460, "loss": 0.2483, "lr": 4.710176871882002e-06, "epoch": 11.332609370152031, "percentage": 56.66, "elapsed_time": "1:07:14", "remaining_time": "0:51:25", "throughput": 5520.74, "total_tokens": 22274320} {"current_steps": 36530, "total_steps": 64460, "loss": 0.2593, "lr": 4.7088253507808504e-06, "epoch": 11.334160719826249, "percentage": 56.67, "elapsed_time": "1:07:15", "remaining_time": "0:51:25", "throughput": 5520.8, "total_tokens": 22277648} {"current_steps": 36535, "total_steps": 64460, "loss": 0.2146, "lr": 4.707473851026248e-06, "epoch": 11.335712069500465, "percentage": 56.68, "elapsed_time": "1:07:15", "remaining_time": "0:51:24", "throughput": 5520.78, "total_tokens": 22280336} {"current_steps": 36540, "total_steps": 64460, "loss": 0.2523, "lr": 4.706122372717278e-06, "epoch": 11.337263419174683, "percentage": 56.69, "elapsed_time": "1:07:16", "remaining_time": "0:51:24", "throughput": 5520.83, "total_tokens": 22283344} {"current_steps": 36545, "total_steps": 64460, "loss": 0.2146, "lr": 4.704770915953018e-06, "epoch": 11.338814768848898, "percentage": 56.69, "elapsed_time": "1:07:16", "remaining_time": "0:51:23", "throughput": 5520.85, "total_tokens": 22286512} {"current_steps": 36550, "total_steps": 64460, "loss": 0.2077, "lr": 4.7034194808325445e-06, "epoch": 11.340366118523114, "percentage": 56.7, "elapsed_time": "1:07:17", "remaining_time": "0:51:22", "throughput": 5520.89, "total_tokens": 22289456} {"current_steps": 36555, "total_steps": 64460, "loss": 0.2118, "lr": 4.702068067454936e-06, "epoch": 11.341917468197332, "percentage": 56.71, "elapsed_time": "1:07:17", "remaining_time": "0:51:22", "throughput": 5520.88, "total_tokens": 22292432} {"current_steps": 36560, "total_steps": 64460, "loss": 0.1837, "lr": 4.7007166759192656e-06, "epoch": 11.343468817871548, "percentage": 56.72, "elapsed_time": "1:07:18", "remaining_time": "0:51:21", "throughput": 5521.02, "total_tokens": 22296176} {"current_steps": 36565, "total_steps": 64460, "loss": 0.2278, "lr": 4.699365306324607e-06, "epoch": 11.345020167545766, "percentage": 56.73, "elapsed_time": "1:07:18", "remaining_time": "0:51:21", "throughput": 5521.02, "total_tokens": 22299024} {"current_steps": 36570, "total_steps": 64460, "loss": 0.2368, "lr": 4.698013958770032e-06, "epoch": 11.346571517219981, "percentage": 56.73, "elapsed_time": "1:07:19", "remaining_time": "0:51:20", "throughput": 5521.15, "total_tokens": 22302352} {"current_steps": 36575, "total_steps": 64460, "loss": 0.2497, "lr": 4.69666263335461e-06, "epoch": 11.348122866894197, "percentage": 56.74, "elapsed_time": "1:07:19", "remaining_time": "0:51:20", "throughput": 5521.14, "total_tokens": 22305264} {"current_steps": 36580, "total_steps": 64460, "loss": 0.1939, "lr": 4.6953113301774085e-06, "epoch": 11.349674216568415, "percentage": 56.75, "elapsed_time": "1:07:20", "remaining_time": "0:51:19", "throughput": 5521.03, "total_tokens": 22307504} {"current_steps": 36585, "total_steps": 64460, "loss": 0.2205, "lr": 4.693960049337495e-06, "epoch": 11.351225566242631, "percentage": 56.76, "elapsed_time": "1:07:20", "remaining_time": "0:51:18", "throughput": 5521.05, "total_tokens": 22310256} {"current_steps": 36590, "total_steps": 64460, "loss": 0.227, "lr": 4.692608790933932e-06, "epoch": 11.352776915916849, "percentage": 56.76, "elapsed_time": "1:07:21", "remaining_time": "0:51:18", "throughput": 5521.18, "total_tokens": 22313776} {"current_steps": 36595, "total_steps": 64460, "loss": 0.1942, "lr": 4.691257555065787e-06, "epoch": 11.354328265591064, "percentage": 56.77, "elapsed_time": "1:07:21", "remaining_time": "0:51:17", "throughput": 5521.15, "total_tokens": 22316432} {"current_steps": 36600, "total_steps": 64460, "loss": 0.2324, "lr": 4.689906341832118e-06, "epoch": 11.35587961526528, "percentage": 56.78, "elapsed_time": "1:07:22", "remaining_time": "0:51:17", "throughput": 5521.23, "total_tokens": 22319888} {"current_steps": 36605, "total_steps": 64460, "loss": 0.2109, "lr": 4.688555151331987e-06, "epoch": 11.357430964939498, "percentage": 56.79, "elapsed_time": "1:07:23", "remaining_time": "0:51:16", "throughput": 5521.28, "total_tokens": 22322832} {"current_steps": 36610, "total_steps": 64460, "loss": 0.1851, "lr": 4.687203983664451e-06, "epoch": 11.358982314613714, "percentage": 56.79, "elapsed_time": "1:07:23", "remaining_time": "0:51:16", "throughput": 5521.36, "total_tokens": 22326416} {"current_steps": 36615, "total_steps": 64460, "loss": 0.2437, "lr": 4.685852838928568e-06, "epoch": 11.36053366428793, "percentage": 56.8, "elapsed_time": "1:07:24", "remaining_time": "0:51:15", "throughput": 5521.37, "total_tokens": 22329232} {"current_steps": 36620, "total_steps": 64460, "loss": 0.2223, "lr": 4.6845017172233905e-06, "epoch": 11.362085013962147, "percentage": 56.81, "elapsed_time": "1:07:24", "remaining_time": "0:51:14", "throughput": 5521.33, "total_tokens": 22331856} {"current_steps": 36625, "total_steps": 64460, "loss": 0.2531, "lr": 4.683150618647975e-06, "epoch": 11.363636363636363, "percentage": 56.82, "elapsed_time": "1:07:25", "remaining_time": "0:51:14", "throughput": 5521.25, "total_tokens": 22334224} {"current_steps": 36630, "total_steps": 64460, "loss": 0.2488, "lr": 4.68179954330137e-06, "epoch": 11.365187713310581, "percentage": 56.83, "elapsed_time": "1:07:25", "remaining_time": "0:51:13", "throughput": 5521.21, "total_tokens": 22336816} {"current_steps": 36635, "total_steps": 64460, "loss": 0.2185, "lr": 4.680448491282627e-06, "epoch": 11.366739062984797, "percentage": 56.83, "elapsed_time": "1:07:26", "remaining_time": "0:51:13", "throughput": 5521.41, "total_tokens": 22341264} {"current_steps": 36640, "total_steps": 64460, "loss": 0.2161, "lr": 4.679097462690793e-06, "epoch": 11.368290412659013, "percentage": 56.84, "elapsed_time": "1:07:26", "remaining_time": "0:51:12", "throughput": 5521.3, "total_tokens": 22343536} {"current_steps": 36645, "total_steps": 64460, "loss": 0.2222, "lr": 4.677746457624915e-06, "epoch": 11.36984176233323, "percentage": 56.85, "elapsed_time": "1:07:27", "remaining_time": "0:51:12", "throughput": 5521.27, "total_tokens": 22346416} {"current_steps": 36650, "total_steps": 64460, "loss": 0.2036, "lr": 4.676395476184037e-06, "epoch": 11.371393112007446, "percentage": 56.86, "elapsed_time": "1:07:27", "remaining_time": "0:51:11", "throughput": 5521.22, "total_tokens": 22349360} {"current_steps": 36655, "total_steps": 64460, "loss": 0.2381, "lr": 4.675044518467205e-06, "epoch": 11.372944461681662, "percentage": 56.86, "elapsed_time": "1:07:28", "remaining_time": "0:51:10", "throughput": 5521.26, "total_tokens": 22352368} {"current_steps": 36660, "total_steps": 64460, "loss": 0.2112, "lr": 4.673693584573456e-06, "epoch": 11.37449581135588, "percentage": 56.87, "elapsed_time": "1:07:29", "remaining_time": "0:51:10", "throughput": 5521.29, "total_tokens": 22355856} {"current_steps": 36665, "total_steps": 64460, "loss": 0.2179, "lr": 4.672342674601832e-06, "epoch": 11.376047161030096, "percentage": 56.88, "elapsed_time": "1:07:29", "remaining_time": "0:51:10", "throughput": 5521.49, "total_tokens": 22360432} {"current_steps": 36670, "total_steps": 64460, "loss": 0.194, "lr": 4.6709917886513684e-06, "epoch": 11.377598510704313, "percentage": 56.89, "elapsed_time": "1:07:30", "remaining_time": "0:51:09", "throughput": 5521.59, "total_tokens": 22363600} {"current_steps": 36675, "total_steps": 64460, "loss": 0.2343, "lr": 4.669640926821103e-06, "epoch": 11.37914986037853, "percentage": 56.9, "elapsed_time": "1:07:30", "remaining_time": "0:51:08", "throughput": 5521.55, "total_tokens": 22366000} {"current_steps": 36680, "total_steps": 64460, "loss": 0.2015, "lr": 4.6682900892100716e-06, "epoch": 11.380701210052745, "percentage": 56.9, "elapsed_time": "1:07:31", "remaining_time": "0:51:08", "throughput": 5521.5, "total_tokens": 22368368} {"current_steps": 36685, "total_steps": 64460, "loss": 0.2467, "lr": 4.666939275917304e-06, "epoch": 11.382252559726963, "percentage": 56.91, "elapsed_time": "1:07:31", "remaining_time": "0:51:07", "throughput": 5521.54, "total_tokens": 22371376} {"current_steps": 36690, "total_steps": 64460, "loss": 0.2039, "lr": 4.665588487041831e-06, "epoch": 11.383803909401179, "percentage": 56.92, "elapsed_time": "1:07:32", "remaining_time": "0:51:07", "throughput": 5521.47, "total_tokens": 22373872} {"current_steps": 36695, "total_steps": 64460, "loss": 0.1976, "lr": 4.664237722682683e-06, "epoch": 11.385355259075396, "percentage": 56.93, "elapsed_time": "1:07:32", "remaining_time": "0:51:06", "throughput": 5521.53, "total_tokens": 22377040} {"current_steps": 36700, "total_steps": 64460, "loss": 0.2485, "lr": 4.6628869829388855e-06, "epoch": 11.386906608749612, "percentage": 56.93, "elapsed_time": "1:07:33", "remaining_time": "0:51:05", "throughput": 5521.62, "total_tokens": 22380368} {"current_steps": 36705, "total_steps": 64460, "loss": 0.2731, "lr": 4.661536267909464e-06, "epoch": 11.388457958423828, "percentage": 56.94, "elapsed_time": "1:07:33", "remaining_time": "0:51:05", "throughput": 5521.57, "total_tokens": 22382896} {"current_steps": 36710, "total_steps": 64460, "loss": 0.2631, "lr": 4.660185577693442e-06, "epoch": 11.390009308098046, "percentage": 56.95, "elapsed_time": "1:07:34", "remaining_time": "0:51:04", "throughput": 5521.55, "total_tokens": 22385552} {"current_steps": 36715, "total_steps": 64460, "loss": 0.2224, "lr": 4.658834912389842e-06, "epoch": 11.391560657772262, "percentage": 56.96, "elapsed_time": "1:07:34", "remaining_time": "0:51:04", "throughput": 5521.51, "total_tokens": 22388112} {"current_steps": 36720, "total_steps": 64460, "loss": 0.2548, "lr": 4.657484272097681e-06, "epoch": 11.39311200744648, "percentage": 56.97, "elapsed_time": "1:07:35", "remaining_time": "0:51:03", "throughput": 5521.46, "total_tokens": 22390544} {"current_steps": 36725, "total_steps": 64460, "loss": 0.249, "lr": 4.65613365691598e-06, "epoch": 11.394663357120695, "percentage": 56.97, "elapsed_time": "1:07:35", "remaining_time": "0:51:02", "throughput": 5521.43, "total_tokens": 22393040} {"current_steps": 36730, "total_steps": 64460, "loss": 0.2124, "lr": 4.654783066943754e-06, "epoch": 11.396214706794911, "percentage": 56.98, "elapsed_time": "1:07:36", "remaining_time": "0:51:02", "throughput": 5521.43, "total_tokens": 22395792} {"current_steps": 36735, "total_steps": 64460, "loss": 0.2209, "lr": 4.653432502280016e-06, "epoch": 11.397766056469129, "percentage": 56.99, "elapsed_time": "1:07:36", "remaining_time": "0:51:01", "throughput": 5521.43, "total_tokens": 22399184} {"current_steps": 36740, "total_steps": 64460, "loss": 0.2203, "lr": 4.652081963023781e-06, "epoch": 11.399317406143345, "percentage": 57.0, "elapsed_time": "1:07:37", "remaining_time": "0:51:01", "throughput": 5521.41, "total_tokens": 22401904} {"current_steps": 36745, "total_steps": 64460, "loss": 0.2245, "lr": 4.650731449274059e-06, "epoch": 11.40086875581756, "percentage": 57.0, "elapsed_time": "1:07:38", "remaining_time": "0:51:00", "throughput": 5521.68, "total_tokens": 22407120} {"current_steps": 36750, "total_steps": 64460, "loss": 0.2413, "lr": 4.649380961129856e-06, "epoch": 11.402420105491778, "percentage": 57.01, "elapsed_time": "1:07:38", "remaining_time": "0:51:00", "throughput": 5521.74, "total_tokens": 22410672} {"current_steps": 36755, "total_steps": 64460, "loss": 0.206, "lr": 4.648030498690181e-06, "epoch": 11.403971455165994, "percentage": 57.02, "elapsed_time": "1:07:39", "remaining_time": "0:50:59", "throughput": 5521.68, "total_tokens": 22413104} {"current_steps": 36760, "total_steps": 64460, "loss": 0.2538, "lr": 4.646680062054038e-06, "epoch": 11.405522804840212, "percentage": 57.03, "elapsed_time": "1:07:39", "remaining_time": "0:50:59", "throughput": 5521.58, "total_tokens": 22415600} {"current_steps": 36765, "total_steps": 64460, "loss": 0.2361, "lr": 4.645329651320431e-06, "epoch": 11.407074154514428, "percentage": 57.04, "elapsed_time": "1:07:40", "remaining_time": "0:50:58", "throughput": 5521.58, "total_tokens": 22418320} {"current_steps": 36770, "total_steps": 64460, "loss": 0.2359, "lr": 4.64397926658836e-06, "epoch": 11.408625504188644, "percentage": 57.04, "elapsed_time": "1:07:40", "remaining_time": "0:50:57", "throughput": 5521.59, "total_tokens": 22421104} {"current_steps": 36775, "total_steps": 64460, "loss": 0.2237, "lr": 4.6426289079568255e-06, "epoch": 11.410176853862861, "percentage": 57.05, "elapsed_time": "1:07:41", "remaining_time": "0:50:57", "throughput": 5521.57, "total_tokens": 22423696} {"current_steps": 36780, "total_steps": 64460, "loss": 0.2269, "lr": 4.641278575524823e-06, "epoch": 11.411728203537077, "percentage": 57.06, "elapsed_time": "1:07:41", "remaining_time": "0:50:56", "throughput": 5521.7, "total_tokens": 22427600} {"current_steps": 36785, "total_steps": 64460, "loss": 0.2366, "lr": 4.63992826939135e-06, "epoch": 11.413279553211293, "percentage": 57.07, "elapsed_time": "1:07:42", "remaining_time": "0:50:56", "throughput": 5521.62, "total_tokens": 22429840} {"current_steps": 36790, "total_steps": 64460, "loss": 0.2374, "lr": 4.638577989655398e-06, "epoch": 11.41483090288551, "percentage": 57.07, "elapsed_time": "1:07:42", "remaining_time": "0:50:55", "throughput": 5521.65, "total_tokens": 22433104} {"current_steps": 36795, "total_steps": 64460, "loss": 0.2196, "lr": 4.637227736415958e-06, "epoch": 11.416382252559726, "percentage": 57.08, "elapsed_time": "1:07:43", "remaining_time": "0:50:55", "throughput": 5521.54, "total_tokens": 22435440} {"current_steps": 36800, "total_steps": 64460, "loss": 0.2173, "lr": 4.635877509772022e-06, "epoch": 11.417933602233944, "percentage": 57.09, "elapsed_time": "1:07:43", "remaining_time": "0:50:54", "throughput": 5521.6, "total_tokens": 22438448} {"current_steps": 36805, "total_steps": 64460, "loss": 0.2193, "lr": 4.634527309822576e-06, "epoch": 11.41948495190816, "percentage": 57.1, "elapsed_time": "1:07:44", "remaining_time": "0:50:53", "throughput": 5521.57, "total_tokens": 22441040} {"current_steps": 36810, "total_steps": 64460, "loss": 0.2258, "lr": 4.6331771366666065e-06, "epoch": 11.421036301582376, "percentage": 57.11, "elapsed_time": "1:07:44", "remaining_time": "0:50:53", "throughput": 5521.71, "total_tokens": 22445488} {"current_steps": 36815, "total_steps": 64460, "loss": 0.2468, "lr": 4.631826990403096e-06, "epoch": 11.422587651256594, "percentage": 57.11, "elapsed_time": "1:07:45", "remaining_time": "0:50:52", "throughput": 5521.72, "total_tokens": 22448176} {"current_steps": 36820, "total_steps": 64460, "loss": 0.2236, "lr": 4.630476871131028e-06, "epoch": 11.42413900093081, "percentage": 57.12, "elapsed_time": "1:07:45", "remaining_time": "0:50:52", "throughput": 5521.72, "total_tokens": 22450800} {"current_steps": 36825, "total_steps": 64460, "loss": 0.216, "lr": 4.629126778949381e-06, "epoch": 11.425690350605027, "percentage": 57.13, "elapsed_time": "1:07:46", "remaining_time": "0:50:51", "throughput": 5521.74, "total_tokens": 22454000} {"current_steps": 36830, "total_steps": 64460, "loss": 0.2183, "lr": 4.6277767139571325e-06, "epoch": 11.427241700279243, "percentage": 57.14, "elapsed_time": "1:07:47", "remaining_time": "0:50:51", "throughput": 5521.88, "total_tokens": 22457648} {"current_steps": 36835, "total_steps": 64460, "loss": 0.2222, "lr": 4.626426676253259e-06, "epoch": 11.428793049953459, "percentage": 57.14, "elapsed_time": "1:07:47", "remaining_time": "0:50:50", "throughput": 5521.89, "total_tokens": 22460368} {"current_steps": 36840, "total_steps": 64460, "loss": 0.2154, "lr": 4.625076665936733e-06, "epoch": 11.430344399627677, "percentage": 57.15, "elapsed_time": "1:07:48", "remaining_time": "0:50:49", "throughput": 5521.95, "total_tokens": 22463344} {"current_steps": 36845, "total_steps": 64460, "loss": 0.217, "lr": 4.623726683106529e-06, "epoch": 11.431895749301892, "percentage": 57.16, "elapsed_time": "1:07:48", "remaining_time": "0:50:49", "throughput": 5521.95, "total_tokens": 22466064} {"current_steps": 36850, "total_steps": 64460, "loss": 0.2281, "lr": 4.622376727861613e-06, "epoch": 11.43344709897611, "percentage": 57.17, "elapsed_time": "1:07:49", "remaining_time": "0:50:48", "throughput": 5522.03, "total_tokens": 22469456} {"current_steps": 36855, "total_steps": 64460, "loss": 0.2121, "lr": 4.621026800300954e-06, "epoch": 11.434998448650326, "percentage": 57.17, "elapsed_time": "1:07:49", "remaining_time": "0:50:48", "throughput": 5522.03, "total_tokens": 22472272} {"current_steps": 36860, "total_steps": 64460, "loss": 0.2241, "lr": 4.61967690052352e-06, "epoch": 11.436549798324542, "percentage": 57.18, "elapsed_time": "1:07:50", "remaining_time": "0:50:47", "throughput": 5521.83, "total_tokens": 22474576} {"current_steps": 36865, "total_steps": 64460, "loss": 0.2386, "lr": 4.618327028628272e-06, "epoch": 11.43810114799876, "percentage": 57.19, "elapsed_time": "1:07:50", "remaining_time": "0:50:47", "throughput": 5521.92, "total_tokens": 22477904} {"current_steps": 36870, "total_steps": 64460, "loss": 0.221, "lr": 4.616977184714173e-06, "epoch": 11.439652497672975, "percentage": 57.2, "elapsed_time": "1:07:51", "remaining_time": "0:50:46", "throughput": 5521.85, "total_tokens": 22480336} {"current_steps": 36875, "total_steps": 64460, "loss": 0.1973, "lr": 4.615627368880182e-06, "epoch": 11.441203847347191, "percentage": 57.21, "elapsed_time": "1:07:51", "remaining_time": "0:50:45", "throughput": 5521.92, "total_tokens": 22483888} {"current_steps": 36880, "total_steps": 64460, "loss": 0.2288, "lr": 4.6142775812252565e-06, "epoch": 11.442755197021409, "percentage": 57.21, "elapsed_time": "1:07:52", "remaining_time": "0:50:45", "throughput": 5521.91, "total_tokens": 22486704} {"current_steps": 36885, "total_steps": 64460, "loss": 0.2348, "lr": 4.612927821848352e-06, "epoch": 11.444306546695625, "percentage": 57.22, "elapsed_time": "1:07:52", "remaining_time": "0:50:44", "throughput": 5521.98, "total_tokens": 22489712} {"current_steps": 36890, "total_steps": 64460, "loss": 0.2404, "lr": 4.611578090848422e-06, "epoch": 11.445857896369843, "percentage": 57.23, "elapsed_time": "1:07:53", "remaining_time": "0:50:44", "throughput": 5521.93, "total_tokens": 22492144} {"current_steps": 36895, "total_steps": 64460, "loss": 0.2264, "lr": 4.6102283883244166e-06, "epoch": 11.447409246044058, "percentage": 57.24, "elapsed_time": "1:07:53", "remaining_time": "0:50:43", "throughput": 5521.74, "total_tokens": 22494416} {"current_steps": 36900, "total_steps": 64460, "loss": 0.1903, "lr": 4.608878714375287e-06, "epoch": 11.448960595718274, "percentage": 57.24, "elapsed_time": "1:07:54", "remaining_time": "0:50:43", "throughput": 5521.63, "total_tokens": 22497008} {"current_steps": 36905, "total_steps": 64460, "loss": 0.2304, "lr": 4.6075290690999785e-06, "epoch": 11.450511945392492, "percentage": 57.25, "elapsed_time": "1:07:54", "remaining_time": "0:50:42", "throughput": 5521.6, "total_tokens": 22499600} {"current_steps": 36910, "total_steps": 64460, "loss": 0.2191, "lr": 4.6061794525974365e-06, "epoch": 11.452063295066708, "percentage": 57.26, "elapsed_time": "1:07:55", "remaining_time": "0:50:41", "throughput": 5521.63, "total_tokens": 22502416} {"current_steps": 36915, "total_steps": 64460, "loss": 0.219, "lr": 4.604829864966604e-06, "epoch": 11.453614644740924, "percentage": 57.27, "elapsed_time": "1:07:55", "remaining_time": "0:50:41", "throughput": 5521.68, "total_tokens": 22505520} {"current_steps": 36920, "total_steps": 64460, "loss": 0.2359, "lr": 4.603480306306423e-06, "epoch": 11.455165994415141, "percentage": 57.28, "elapsed_time": "1:07:56", "remaining_time": "0:50:40", "throughput": 5521.73, "total_tokens": 22508400} {"current_steps": 36925, "total_steps": 64460, "loss": 0.2725, "lr": 4.60213077671583e-06, "epoch": 11.456717344089357, "percentage": 57.28, "elapsed_time": "1:07:56", "remaining_time": "0:50:40", "throughput": 5521.77, "total_tokens": 22511792} {"current_steps": 36930, "total_steps": 64460, "loss": 0.2174, "lr": 4.600781276293764e-06, "epoch": 11.458268693763575, "percentage": 57.29, "elapsed_time": "1:07:57", "remaining_time": "0:50:39", "throughput": 5521.95, "total_tokens": 22515824} {"current_steps": 36935, "total_steps": 64460, "loss": 0.2347, "lr": 4.599431805139157e-06, "epoch": 11.45982004343779, "percentage": 57.3, "elapsed_time": "1:07:57", "remaining_time": "0:50:39", "throughput": 5521.94, "total_tokens": 22518448} {"current_steps": 36940, "total_steps": 64460, "loss": 0.222, "lr": 4.5980823633509416e-06, "epoch": 11.461371393112007, "percentage": 57.31, "elapsed_time": "1:07:58", "remaining_time": "0:50:38", "throughput": 5521.87, "total_tokens": 22520752} {"current_steps": 36945, "total_steps": 64460, "loss": 0.2202, "lr": 4.596732951028049e-06, "epoch": 11.462922742786224, "percentage": 57.31, "elapsed_time": "1:07:58", "remaining_time": "0:50:37", "throughput": 5521.86, "total_tokens": 22523504} {"current_steps": 36950, "total_steps": 64460, "loss": 0.2284, "lr": 4.595383568269406e-06, "epoch": 11.46447409246044, "percentage": 57.32, "elapsed_time": "1:07:59", "remaining_time": "0:50:37", "throughput": 5521.88, "total_tokens": 22526416} {"current_steps": 36955, "total_steps": 64460, "loss": 0.232, "lr": 4.59403421517394e-06, "epoch": 11.466025442134658, "percentage": 57.33, "elapsed_time": "1:08:00", "remaining_time": "0:50:36", "throughput": 5521.79, "total_tokens": 22528976} {"current_steps": 36960, "total_steps": 64460, "loss": 0.2868, "lr": 4.592684891840572e-06, "epoch": 11.467576791808874, "percentage": 57.34, "elapsed_time": "1:08:00", "remaining_time": "0:50:36", "throughput": 5521.82, "total_tokens": 22532176} {"current_steps": 36965, "total_steps": 64460, "loss": 0.2194, "lr": 4.5913355983682266e-06, "epoch": 11.46912814148309, "percentage": 57.35, "elapsed_time": "1:08:01", "remaining_time": "0:50:35", "throughput": 5521.86, "total_tokens": 22535280} {"current_steps": 36970, "total_steps": 64460, "loss": 0.2491, "lr": 4.589986334855819e-06, "epoch": 11.470679491157307, "percentage": 57.35, "elapsed_time": "1:08:01", "remaining_time": "0:50:34", "throughput": 5521.92, "total_tokens": 22538288} {"current_steps": 36975, "total_steps": 64460, "loss": 0.2328, "lr": 4.588637101402269e-06, "epoch": 11.472230840831523, "percentage": 57.36, "elapsed_time": "1:08:02", "remaining_time": "0:50:34", "throughput": 5521.96, "total_tokens": 22541328} {"current_steps": 36980, "total_steps": 64460, "loss": 0.2265, "lr": 4.587287898106491e-06, "epoch": 11.47378219050574, "percentage": 57.37, "elapsed_time": "1:08:02", "remaining_time": "0:50:33", "throughput": 5521.98, "total_tokens": 22544016} {"current_steps": 36985, "total_steps": 64460, "loss": 0.2162, "lr": 4.585938725067397e-06, "epoch": 11.475333540179957, "percentage": 57.38, "elapsed_time": "1:08:03", "remaining_time": "0:50:33", "throughput": 5522.07, "total_tokens": 22547216} {"current_steps": 36990, "total_steps": 64460, "loss": 0.2114, "lr": 4.584589582383898e-06, "epoch": 11.476884889854173, "percentage": 57.38, "elapsed_time": "1:08:03", "remaining_time": "0:50:32", "throughput": 5521.88, "total_tokens": 22549552} {"current_steps": 36995, "total_steps": 64460, "loss": 0.2093, "lr": 4.583240470154902e-06, "epoch": 11.47843623952839, "percentage": 57.39, "elapsed_time": "1:08:04", "remaining_time": "0:50:32", "throughput": 5521.77, "total_tokens": 22551920} {"current_steps": 37000, "total_steps": 64460, "loss": 0.2046, "lr": 4.5818913884793146e-06, "epoch": 11.479987589202606, "percentage": 57.4, "elapsed_time": "1:08:04", "remaining_time": "0:50:31", "throughput": 5521.79, "total_tokens": 22554736} {"current_steps": 37005, "total_steps": 64460, "loss": 0.2362, "lr": 4.580542337456039e-06, "epoch": 11.481538938876822, "percentage": 57.41, "elapsed_time": "1:08:05", "remaining_time": "0:50:30", "throughput": 5521.82, "total_tokens": 22557520} {"current_steps": 37010, "total_steps": 64460, "loss": 0.2455, "lr": 4.5791933171839784e-06, "epoch": 11.48309028855104, "percentage": 57.42, "elapsed_time": "1:08:05", "remaining_time": "0:50:30", "throughput": 5521.88, "total_tokens": 22560528} {"current_steps": 37015, "total_steps": 64460, "loss": 0.231, "lr": 4.57784432776203e-06, "epoch": 11.484641638225256, "percentage": 57.42, "elapsed_time": "1:08:06", "remaining_time": "0:50:29", "throughput": 5521.81, "total_tokens": 22562864} {"current_steps": 37020, "total_steps": 64460, "loss": 0.2291, "lr": 4.576495369289091e-06, "epoch": 11.486192987899473, "percentage": 57.43, "elapsed_time": "1:08:06", "remaining_time": "0:50:29", "throughput": 5521.83, "total_tokens": 22565680} {"current_steps": 37025, "total_steps": 64460, "loss": 0.2549, "lr": 4.575146441864057e-06, "epoch": 11.48774433757369, "percentage": 57.44, "elapsed_time": "1:08:07", "remaining_time": "0:50:28", "throughput": 5521.79, "total_tokens": 22568176} {"current_steps": 37030, "total_steps": 64460, "loss": 0.2081, "lr": 4.57379754558582e-06, "epoch": 11.489295687247905, "percentage": 57.45, "elapsed_time": "1:08:07", "remaining_time": "0:50:27", "throughput": 5521.84, "total_tokens": 22571440} {"current_steps": 37035, "total_steps": 64460, "loss": 0.1916, "lr": 4.572448680553268e-06, "epoch": 11.490847036922123, "percentage": 57.45, "elapsed_time": "1:08:08", "remaining_time": "0:50:27", "throughput": 5521.93, "total_tokens": 22574832} {"current_steps": 37040, "total_steps": 64460, "loss": 0.2172, "lr": 4.571099846865293e-06, "epoch": 11.492398386596339, "percentage": 57.46, "elapsed_time": "1:08:08", "remaining_time": "0:50:26", "throughput": 5521.91, "total_tokens": 22577520} {"current_steps": 37045, "total_steps": 64460, "loss": 0.2177, "lr": 4.5697510446207775e-06, "epoch": 11.493949736270554, "percentage": 57.47, "elapsed_time": "1:08:09", "remaining_time": "0:50:26", "throughput": 5521.97, "total_tokens": 22580752} {"current_steps": 37050, "total_steps": 64460, "loss": 0.2212, "lr": 4.568402273918606e-06, "epoch": 11.495501085944772, "percentage": 57.48, "elapsed_time": "1:08:09", "remaining_time": "0:50:25", "throughput": 5521.92, "total_tokens": 22583344} {"current_steps": 37055, "total_steps": 64460, "loss": 0.2287, "lr": 4.567053534857658e-06, "epoch": 11.497052435618988, "percentage": 57.49, "elapsed_time": "1:08:10", "remaining_time": "0:50:25", "throughput": 5521.89, "total_tokens": 22585872} {"current_steps": 37060, "total_steps": 64460, "loss": 0.254, "lr": 4.565704827536813e-06, "epoch": 11.498603785293206, "percentage": 57.49, "elapsed_time": "1:08:10", "remaining_time": "0:50:24", "throughput": 5521.96, "total_tokens": 22589776} {"current_steps": 37065, "total_steps": 64460, "loss": 0.2019, "lr": 4.564356152054946e-06, "epoch": 11.500155134967422, "percentage": 57.5, "elapsed_time": "1:08:11", "remaining_time": "0:50:24", "throughput": 5522.07, "total_tokens": 22593488} {"current_steps": 37070, "total_steps": 64460, "loss": 0.2658, "lr": 4.5630075085109336e-06, "epoch": 11.501706484641637, "percentage": 57.51, "elapsed_time": "1:08:12", "remaining_time": "0:50:23", "throughput": 5522.16, "total_tokens": 22596848} {"current_steps": 37075, "total_steps": 64460, "loss": 0.2259, "lr": 4.561658897003644e-06, "epoch": 11.503257834315855, "percentage": 57.52, "elapsed_time": "1:08:12", "remaining_time": "0:50:22", "throughput": 5522.15, "total_tokens": 22599792} {"current_steps": 37080, "total_steps": 64460, "loss": 0.2275, "lr": 4.560310317631949e-06, "epoch": 11.504809183990071, "percentage": 57.52, "elapsed_time": "1:08:13", "remaining_time": "0:50:22", "throughput": 5522.12, "total_tokens": 22602416} {"current_steps": 37085, "total_steps": 64460, "loss": 0.2168, "lr": 4.558961770494714e-06, "epoch": 11.506360533664289, "percentage": 57.53, "elapsed_time": "1:08:13", "remaining_time": "0:50:21", "throughput": 5522.15, "total_tokens": 22605392} {"current_steps": 37090, "total_steps": 64460, "loss": 0.2194, "lr": 4.557613255690803e-06, "epoch": 11.507911883338505, "percentage": 57.54, "elapsed_time": "1:08:14", "remaining_time": "0:50:21", "throughput": 5522.16, "total_tokens": 22608208} {"current_steps": 37095, "total_steps": 64460, "loss": 0.2185, "lr": 4.55626477331908e-06, "epoch": 11.50946323301272, "percentage": 57.55, "elapsed_time": "1:08:14", "remaining_time": "0:50:20", "throughput": 5522.13, "total_tokens": 22611056} {"current_steps": 37100, "total_steps": 64460, "loss": 0.2171, "lr": 4.554916323478404e-06, "epoch": 11.511014582686938, "percentage": 57.56, "elapsed_time": "1:08:15", "remaining_time": "0:50:20", "throughput": 5522.05, "total_tokens": 22613552} {"current_steps": 37105, "total_steps": 64460, "loss": 0.227, "lr": 4.55356790626763e-06, "epoch": 11.512565932361154, "percentage": 57.56, "elapsed_time": "1:08:15", "remaining_time": "0:50:19", "throughput": 5522.23, "total_tokens": 22617520} {"current_steps": 37110, "total_steps": 64460, "loss": 0.215, "lr": 4.552219521785618e-06, "epoch": 11.514117282035372, "percentage": 57.57, "elapsed_time": "1:08:16", "remaining_time": "0:50:18", "throughput": 5522.4, "total_tokens": 22621584} {"current_steps": 37115, "total_steps": 64460, "loss": 0.2295, "lr": 4.550871170131216e-06, "epoch": 11.515668631709588, "percentage": 57.58, "elapsed_time": "1:08:16", "remaining_time": "0:50:18", "throughput": 5522.45, "total_tokens": 22624848} {"current_steps": 37120, "total_steps": 64460, "loss": 0.2261, "lr": 4.549522851403276e-06, "epoch": 11.517219981383803, "percentage": 57.59, "elapsed_time": "1:08:17", "remaining_time": "0:50:17", "throughput": 5522.29, "total_tokens": 22627024} {"current_steps": 37125, "total_steps": 64460, "loss": 0.2127, "lr": 4.548174565700645e-06, "epoch": 11.518771331058021, "percentage": 57.59, "elapsed_time": "1:08:18", "remaining_time": "0:50:17", "throughput": 5522.59, "total_tokens": 22632816} {"current_steps": 37130, "total_steps": 64460, "loss": 0.2246, "lr": 4.54682631312217e-06, "epoch": 11.520322680732237, "percentage": 57.6, "elapsed_time": "1:08:18", "remaining_time": "0:50:16", "throughput": 5522.57, "total_tokens": 22635632} {"current_steps": 37135, "total_steps": 64460, "loss": 0.2334, "lr": 4.545478093766692e-06, "epoch": 11.521874030406453, "percentage": 57.61, "elapsed_time": "1:08:19", "remaining_time": "0:50:16", "throughput": 5522.67, "total_tokens": 22639568} {"current_steps": 37140, "total_steps": 64460, "loss": 0.2304, "lr": 4.5441299077330515e-06, "epoch": 11.52342538008067, "percentage": 57.62, "elapsed_time": "1:08:20", "remaining_time": "0:50:15", "throughput": 5522.77, "total_tokens": 22643408} {"current_steps": 37145, "total_steps": 64460, "loss": 0.239, "lr": 4.542781755120087e-06, "epoch": 11.524976729754886, "percentage": 57.62, "elapsed_time": "1:08:20", "remaining_time": "0:50:15", "throughput": 5522.67, "total_tokens": 22645840} {"current_steps": 37150, "total_steps": 64460, "loss": 0.2186, "lr": 4.541433636026636e-06, "epoch": 11.526528079429104, "percentage": 57.63, "elapsed_time": "1:08:21", "remaining_time": "0:50:14", "throughput": 5522.69, "total_tokens": 22648688} {"current_steps": 37155, "total_steps": 64460, "loss": 0.2144, "lr": 4.540085550551527e-06, "epoch": 11.52807942910332, "percentage": 57.64, "elapsed_time": "1:08:21", "remaining_time": "0:50:14", "throughput": 5522.71, "total_tokens": 22651632} {"current_steps": 37160, "total_steps": 64460, "loss": 0.2176, "lr": 4.538737498793594e-06, "epoch": 11.529630778777536, "percentage": 57.65, "elapsed_time": "1:08:22", "remaining_time": "0:50:13", "throughput": 5522.79, "total_tokens": 22654800} {"current_steps": 37165, "total_steps": 64460, "loss": 0.2063, "lr": 4.537389480851665e-06, "epoch": 11.531182128451753, "percentage": 57.66, "elapsed_time": "1:08:22", "remaining_time": "0:50:13", "throughput": 5522.81, "total_tokens": 22657840} {"current_steps": 37170, "total_steps": 64460, "loss": 0.227, "lr": 4.5360414968245654e-06, "epoch": 11.53273347812597, "percentage": 57.66, "elapsed_time": "1:08:23", "remaining_time": "0:50:12", "throughput": 5522.8, "total_tokens": 22660656} {"current_steps": 37175, "total_steps": 64460, "loss": 0.2328, "lr": 4.534693546811119e-06, "epoch": 11.534284827800185, "percentage": 57.67, "elapsed_time": "1:08:23", "remaining_time": "0:50:11", "throughput": 5522.85, "total_tokens": 22663920} {"current_steps": 37180, "total_steps": 64460, "loss": 0.2245, "lr": 4.5333456309101445e-06, "epoch": 11.535836177474403, "percentage": 57.68, "elapsed_time": "1:08:24", "remaining_time": "0:50:11", "throughput": 5522.92, "total_tokens": 22666960} {"current_steps": 37185, "total_steps": 64460, "loss": 0.219, "lr": 4.531997749220462e-06, "epoch": 11.537387527148619, "percentage": 57.69, "elapsed_time": "1:08:24", "remaining_time": "0:50:10", "throughput": 5522.89, "total_tokens": 22669552} {"current_steps": 37190, "total_steps": 64460, "loss": 0.217, "lr": 4.530649901840886e-06, "epoch": 11.538938876822836, "percentage": 57.69, "elapsed_time": "1:08:25", "remaining_time": "0:50:10", "throughput": 5522.86, "total_tokens": 22672112} {"current_steps": 37195, "total_steps": 64460, "loss": 0.2216, "lr": 4.52930208887023e-06, "epoch": 11.540490226497052, "percentage": 57.7, "elapsed_time": "1:08:25", "remaining_time": "0:50:09", "throughput": 5522.92, "total_tokens": 22675184} {"current_steps": 37200, "total_steps": 64460, "loss": 0.2331, "lr": 4.5279543104073044e-06, "epoch": 11.542041576171268, "percentage": 57.71, "elapsed_time": "1:08:26", "remaining_time": "0:50:09", "throughput": 5523.11, "total_tokens": 22680560} {"current_steps": 37205, "total_steps": 64460, "loss": 0.2522, "lr": 4.526606566550918e-06, "epoch": 11.543592925845486, "percentage": 57.72, "elapsed_time": "1:08:26", "remaining_time": "0:50:08", "throughput": 5523.06, "total_tokens": 22682992} {"current_steps": 37210, "total_steps": 64460, "loss": 0.2369, "lr": 4.5252588573998765e-06, "epoch": 11.545144275519702, "percentage": 57.73, "elapsed_time": "1:08:27", "remaining_time": "0:50:08", "throughput": 5523.09, "total_tokens": 22685808} {"current_steps": 37215, "total_steps": 64460, "loss": 0.2354, "lr": 4.5239111830529815e-06, "epoch": 11.54669562519392, "percentage": 57.73, "elapsed_time": "1:08:27", "remaining_time": "0:50:07", "throughput": 5523.2, "total_tokens": 22689136} {"current_steps": 37220, "total_steps": 64460, "loss": 0.2279, "lr": 4.5225635436090354e-06, "epoch": 11.548246974868135, "percentage": 57.74, "elapsed_time": "1:08:28", "remaining_time": "0:50:06", "throughput": 5523.1, "total_tokens": 22691472} {"current_steps": 37225, "total_steps": 64460, "loss": 0.2389, "lr": 4.521215939166835e-06, "epoch": 11.549798324542351, "percentage": 57.75, "elapsed_time": "1:08:29", "remaining_time": "0:50:06", "throughput": 5523.0, "total_tokens": 22694064} {"current_steps": 37230, "total_steps": 64460, "loss": 0.2201, "lr": 4.519868369825177e-06, "epoch": 11.551349674216569, "percentage": 57.76, "elapsed_time": "1:08:29", "remaining_time": "0:50:05", "throughput": 5522.99, "total_tokens": 22696816} {"current_steps": 37235, "total_steps": 64460, "loss": 0.2555, "lr": 4.518520835682852e-06, "epoch": 11.552901023890785, "percentage": 57.76, "elapsed_time": "1:08:30", "remaining_time": "0:50:05", "throughput": 5523.0, "total_tokens": 22699664} {"current_steps": 37240, "total_steps": 64460, "loss": 0.2332, "lr": 4.517173336838652e-06, "epoch": 11.554452373565002, "percentage": 57.77, "elapsed_time": "1:08:30", "remaining_time": "0:50:04", "throughput": 5523.14, "total_tokens": 22703600} {"current_steps": 37245, "total_steps": 64460, "loss": 0.2063, "lr": 4.515825873391363e-06, "epoch": 11.556003723239218, "percentage": 57.78, "elapsed_time": "1:08:31", "remaining_time": "0:50:03", "throughput": 5523.13, "total_tokens": 22706128} {"current_steps": 37250, "total_steps": 64460, "loss": 0.2216, "lr": 4.5144784454397695e-06, "epoch": 11.557555072913434, "percentage": 57.79, "elapsed_time": "1:08:31", "remaining_time": "0:50:03", "throughput": 5523.14, "total_tokens": 22709232} {"current_steps": 37255, "total_steps": 64460, "loss": 0.2307, "lr": 4.513131053082657e-06, "epoch": 11.559106422587652, "percentage": 57.8, "elapsed_time": "1:08:32", "remaining_time": "0:50:02", "throughput": 5523.21, "total_tokens": 22712720} {"current_steps": 37260, "total_steps": 64460, "loss": 0.1993, "lr": 4.511783696418804e-06, "epoch": 11.560657772261868, "percentage": 57.8, "elapsed_time": "1:08:32", "remaining_time": "0:50:02", "throughput": 5523.42, "total_tokens": 22717264} {"current_steps": 37265, "total_steps": 64460, "loss": 0.1989, "lr": 4.510436375546988e-06, "epoch": 11.562209121936084, "percentage": 57.81, "elapsed_time": "1:08:33", "remaining_time": "0:50:01", "throughput": 5523.47, "total_tokens": 22720368} {"current_steps": 37270, "total_steps": 64460, "loss": 0.2215, "lr": 4.509089090565982e-06, "epoch": 11.563760471610301, "percentage": 57.82, "elapsed_time": "1:08:34", "remaining_time": "0:50:01", "throughput": 5523.69, "total_tokens": 22725232} {"current_steps": 37275, "total_steps": 64460, "loss": 0.2308, "lr": 4.507741841574559e-06, "epoch": 11.565311821284517, "percentage": 57.83, "elapsed_time": "1:08:34", "remaining_time": "0:50:00", "throughput": 5523.65, "total_tokens": 22728368} {"current_steps": 37280, "total_steps": 64460, "loss": 0.2503, "lr": 4.506394628671489e-06, "epoch": 11.566863170958735, "percentage": 57.83, "elapsed_time": "1:08:35", "remaining_time": "0:50:00", "throughput": 5523.57, "total_tokens": 22730704} {"current_steps": 37285, "total_steps": 64460, "loss": 0.219, "lr": 4.505047451955537e-06, "epoch": 11.56841452063295, "percentage": 57.84, "elapsed_time": "1:08:35", "remaining_time": "0:49:59", "throughput": 5523.62, "total_tokens": 22734416} {"current_steps": 37290, "total_steps": 64460, "loss": 0.2164, "lr": 4.5037003115254685e-06, "epoch": 11.569965870307167, "percentage": 57.85, "elapsed_time": "1:08:36", "remaining_time": "0:49:59", "throughput": 5523.64, "total_tokens": 22737360} {"current_steps": 37295, "total_steps": 64460, "loss": 0.2364, "lr": 4.502353207480044e-06, "epoch": 11.571517219981384, "percentage": 57.86, "elapsed_time": "1:08:36", "remaining_time": "0:49:58", "throughput": 5523.71, "total_tokens": 22740816} {"current_steps": 37300, "total_steps": 64460, "loss": 0.238, "lr": 4.501006139918021e-06, "epoch": 11.5730685696556, "percentage": 57.87, "elapsed_time": "1:08:37", "remaining_time": "0:49:58", "throughput": 5523.87, "total_tokens": 22744592} {"current_steps": 37305, "total_steps": 64460, "loss": 0.1981, "lr": 4.499659108938159e-06, "epoch": 11.574619919329816, "percentage": 57.87, "elapsed_time": "1:08:38", "remaining_time": "0:49:57", "throughput": 5523.92, "total_tokens": 22747824} {"current_steps": 37310, "total_steps": 64460, "loss": 0.2092, "lr": 4.498312114639209e-06, "epoch": 11.576171269004034, "percentage": 57.88, "elapsed_time": "1:08:38", "remaining_time": "0:49:57", "throughput": 5524.12, "total_tokens": 22753296} {"current_steps": 37315, "total_steps": 64460, "loss": 0.2166, "lr": 4.496965157119921e-06, "epoch": 11.57772261867825, "percentage": 57.89, "elapsed_time": "1:08:39", "remaining_time": "0:49:56", "throughput": 5524.03, "total_tokens": 22755760} {"current_steps": 37320, "total_steps": 64460, "loss": 0.24, "lr": 4.495618236479045e-06, "epoch": 11.579273968352467, "percentage": 57.9, "elapsed_time": "1:08:39", "remaining_time": "0:49:56", "throughput": 5523.91, "total_tokens": 22758320} {"current_steps": 37325, "total_steps": 64460, "loss": 0.2206, "lr": 4.494271352815324e-06, "epoch": 11.580825318026683, "percentage": 57.9, "elapsed_time": "1:08:40", "remaining_time": "0:49:55", "throughput": 5523.96, "total_tokens": 22761360} {"current_steps": 37330, "total_steps": 64460, "loss": 0.2989, "lr": 4.4929245062275016e-06, "epoch": 11.582376667700899, "percentage": 57.91, "elapsed_time": "1:08:41", "remaining_time": "0:49:54", "throughput": 5524.08, "total_tokens": 22764816} {"current_steps": 37335, "total_steps": 64460, "loss": 0.2119, "lr": 4.491577696814318e-06, "epoch": 11.583928017375117, "percentage": 57.92, "elapsed_time": "1:08:41", "remaining_time": "0:49:54", "throughput": 5524.1, "total_tokens": 22768080} {"current_steps": 37340, "total_steps": 64460, "loss": 0.2434, "lr": 4.49023092467451e-06, "epoch": 11.585479367049333, "percentage": 57.93, "elapsed_time": "1:08:42", "remaining_time": "0:49:54", "throughput": 5524.28, "total_tokens": 22773360} {"current_steps": 37345, "total_steps": 64460, "loss": 0.2164, "lr": 4.488884189906811e-06, "epoch": 11.58703071672355, "percentage": 57.94, "elapsed_time": "1:08:42", "remaining_time": "0:49:53", "throughput": 5524.31, "total_tokens": 22776208} {"current_steps": 37350, "total_steps": 64460, "loss": 0.2405, "lr": 4.487537492609954e-06, "epoch": 11.588582066397766, "percentage": 57.94, "elapsed_time": "1:08:43", "remaining_time": "0:49:52", "throughput": 5524.26, "total_tokens": 22778960} {"current_steps": 37355, "total_steps": 64460, "loss": 0.2267, "lr": 4.486190832882667e-06, "epoch": 11.590133416071982, "percentage": 57.95, "elapsed_time": "1:08:43", "remaining_time": "0:49:52", "throughput": 5524.18, "total_tokens": 22781328} {"current_steps": 37360, "total_steps": 64460, "loss": 0.2404, "lr": 4.484844210823676e-06, "epoch": 11.5916847657462, "percentage": 57.96, "elapsed_time": "1:08:44", "remaining_time": "0:49:51", "throughput": 5524.16, "total_tokens": 22783824} {"current_steps": 37365, "total_steps": 64460, "loss": 0.2505, "lr": 4.483497626531705e-06, "epoch": 11.593236115420416, "percentage": 57.97, "elapsed_time": "1:08:44", "remaining_time": "0:49:51", "throughput": 5524.14, "total_tokens": 22786384} {"current_steps": 37370, "total_steps": 64460, "loss": 0.2407, "lr": 4.482151080105475e-06, "epoch": 11.594787465094633, "percentage": 57.97, "elapsed_time": "1:08:45", "remaining_time": "0:49:50", "throughput": 5524.2, "total_tokens": 22789232} {"current_steps": 37375, "total_steps": 64460, "loss": 0.2478, "lr": 4.480804571643702e-06, "epoch": 11.596338814768849, "percentage": 57.98, "elapsed_time": "1:08:45", "remaining_time": "0:49:49", "throughput": 5524.23, "total_tokens": 22792304} {"current_steps": 37380, "total_steps": 64460, "loss": 0.1947, "lr": 4.479458101245103e-06, "epoch": 11.597890164443065, "percentage": 57.99, "elapsed_time": "1:08:46", "remaining_time": "0:49:49", "throughput": 5524.35, "total_tokens": 22796464} {"current_steps": 37385, "total_steps": 64460, "loss": 0.2123, "lr": 4.478111669008388e-06, "epoch": 11.599441514117283, "percentage": 58.0, "elapsed_time": "1:08:47", "remaining_time": "0:49:48", "throughput": 5524.34, "total_tokens": 22799248} {"current_steps": 37390, "total_steps": 64460, "loss": 0.2537, "lr": 4.476765275032269e-06, "epoch": 11.600992863791499, "percentage": 58.0, "elapsed_time": "1:08:47", "remaining_time": "0:49:48", "throughput": 5524.34, "total_tokens": 22801904} {"current_steps": 37395, "total_steps": 64460, "loss": 0.2391, "lr": 4.475418919415451e-06, "epoch": 11.602544213465714, "percentage": 58.01, "elapsed_time": "1:08:48", "remaining_time": "0:49:47", "throughput": 5524.32, "total_tokens": 22804656} {"current_steps": 37400, "total_steps": 64460, "loss": 0.2116, "lr": 4.474072602256639e-06, "epoch": 11.604095563139932, "percentage": 58.02, "elapsed_time": "1:08:48", "remaining_time": "0:49:47", "throughput": 5524.45, "total_tokens": 22808432} {"current_steps": 37405, "total_steps": 64460, "loss": 0.2242, "lr": 4.472726323654532e-06, "epoch": 11.605646912814148, "percentage": 58.03, "elapsed_time": "1:08:49", "remaining_time": "0:49:46", "throughput": 5524.41, "total_tokens": 22811024} {"current_steps": 37410, "total_steps": 64460, "loss": 0.2378, "lr": 4.47138008370783e-06, "epoch": 11.607198262488366, "percentage": 58.04, "elapsed_time": "1:08:49", "remaining_time": "0:49:46", "throughput": 5524.44, "total_tokens": 22814032} {"current_steps": 37415, "total_steps": 64460, "loss": 0.2317, "lr": 4.4700338825152275e-06, "epoch": 11.608749612162581, "percentage": 58.04, "elapsed_time": "1:08:50", "remaining_time": "0:49:45", "throughput": 5524.48, "total_tokens": 22817072} {"current_steps": 37420, "total_steps": 64460, "loss": 0.2133, "lr": 4.468687720175416e-06, "epoch": 11.610300961836797, "percentage": 58.05, "elapsed_time": "1:08:50", "remaining_time": "0:49:44", "throughput": 5524.37, "total_tokens": 22819472} {"current_steps": 37425, "total_steps": 64460, "loss": 0.2392, "lr": 4.467341596787087e-06, "epoch": 11.611852311511015, "percentage": 58.06, "elapsed_time": "1:08:51", "remaining_time": "0:49:44", "throughput": 5524.36, "total_tokens": 22822416} {"current_steps": 37430, "total_steps": 64460, "loss": 0.2184, "lr": 4.4659955124489265e-06, "epoch": 11.613403661185231, "percentage": 58.07, "elapsed_time": "1:08:51", "remaining_time": "0:49:43", "throughput": 5524.34, "total_tokens": 22825072} {"current_steps": 37435, "total_steps": 64460, "loss": 0.2361, "lr": 4.464649467259619e-06, "epoch": 11.614955010859447, "percentage": 58.07, "elapsed_time": "1:08:52", "remaining_time": "0:49:43", "throughput": 5524.4, "total_tokens": 22828144} {"current_steps": 37440, "total_steps": 64460, "loss": 0.2221, "lr": 4.463303461317846e-06, "epoch": 11.616506360533664, "percentage": 58.08, "elapsed_time": "1:08:52", "remaining_time": "0:49:42", "throughput": 5524.43, "total_tokens": 22831024} {"current_steps": 37445, "total_steps": 64460, "loss": 0.2356, "lr": 4.461957494722284e-06, "epoch": 11.61805771020788, "percentage": 58.09, "elapsed_time": "1:08:53", "remaining_time": "0:49:42", "throughput": 5524.47, "total_tokens": 22834768} {"current_steps": 37450, "total_steps": 64460, "loss": 0.234, "lr": 4.460611567571608e-06, "epoch": 11.619609059882098, "percentage": 58.1, "elapsed_time": "1:08:53", "remaining_time": "0:49:41", "throughput": 5524.55, "total_tokens": 22838096} {"current_steps": 37455, "total_steps": 64460, "loss": 0.2284, "lr": 4.459265679964491e-06, "epoch": 11.621160409556314, "percentage": 58.11, "elapsed_time": "1:08:54", "remaining_time": "0:49:41", "throughput": 5524.67, "total_tokens": 22842384} {"current_steps": 37460, "total_steps": 64460, "loss": 0.2345, "lr": 4.457919831999605e-06, "epoch": 11.62271175923053, "percentage": 58.11, "elapsed_time": "1:08:55", "remaining_time": "0:49:40", "throughput": 5524.7, "total_tokens": 22845392} {"current_steps": 37465, "total_steps": 64460, "loss": 0.2094, "lr": 4.456574023775614e-06, "epoch": 11.624263108904747, "percentage": 58.12, "elapsed_time": "1:08:55", "remaining_time": "0:49:39", "throughput": 5524.73, "total_tokens": 22848464} {"current_steps": 37470, "total_steps": 64460, "loss": 0.2222, "lr": 4.455228255391182e-06, "epoch": 11.625814458578963, "percentage": 58.13, "elapsed_time": "1:08:56", "remaining_time": "0:49:39", "throughput": 5524.67, "total_tokens": 22851376} {"current_steps": 37475, "total_steps": 64460, "loss": 0.2179, "lr": 4.45388252694497e-06, "epoch": 11.627365808253181, "percentage": 58.14, "elapsed_time": "1:08:56", "remaining_time": "0:49:38", "throughput": 5524.54, "total_tokens": 22853520} {"current_steps": 37480, "total_steps": 64460, "loss": 0.2165, "lr": 4.452536838535633e-06, "epoch": 11.628917157927397, "percentage": 58.14, "elapsed_time": "1:08:57", "remaining_time": "0:49:38", "throughput": 5524.51, "total_tokens": 22856560} {"current_steps": 37485, "total_steps": 64460, "loss": 0.229, "lr": 4.451191190261832e-06, "epoch": 11.630468507601613, "percentage": 58.15, "elapsed_time": "1:08:57", "remaining_time": "0:49:37", "throughput": 5524.69, "total_tokens": 22860272} {"current_steps": 37490, "total_steps": 64460, "loss": 0.2137, "lr": 4.4498455822222146e-06, "epoch": 11.63201985727583, "percentage": 58.16, "elapsed_time": "1:08:58", "remaining_time": "0:49:37", "throughput": 5524.74, "total_tokens": 22863248} {"current_steps": 37495, "total_steps": 64460, "loss": 0.2586, "lr": 4.448500014515431e-06, "epoch": 11.633571206950046, "percentage": 58.17, "elapsed_time": "1:08:58", "remaining_time": "0:49:36", "throughput": 5524.8, "total_tokens": 22866384} {"current_steps": 37500, "total_steps": 64460, "loss": 0.2027, "lr": 4.447154487240126e-06, "epoch": 11.635122556624264, "percentage": 58.18, "elapsed_time": "1:08:59", "remaining_time": "0:49:36", "throughput": 5524.86, "total_tokens": 22870384} {"current_steps": 37505, "total_steps": 64460, "loss": 0.2308, "lr": 4.445809000494945e-06, "epoch": 11.63667390629848, "percentage": 58.18, "elapsed_time": "1:09:00", "remaining_time": "0:49:35", "throughput": 5524.81, "total_tokens": 22872848} {"current_steps": 37510, "total_steps": 64460, "loss": 0.2512, "lr": 4.444463554378527e-06, "epoch": 11.638225255972696, "percentage": 58.19, "elapsed_time": "1:09:00", "remaining_time": "0:49:34", "throughput": 5524.76, "total_tokens": 22875568} {"current_steps": 37515, "total_steps": 64460, "loss": 0.2173, "lr": 4.443118148989509e-06, "epoch": 11.639776605646913, "percentage": 58.2, "elapsed_time": "1:09:01", "remaining_time": "0:49:34", "throughput": 5524.89, "total_tokens": 22879536} {"current_steps": 37520, "total_steps": 64460, "loss": 0.2421, "lr": 4.441772784426524e-06, "epoch": 11.64132795532113, "percentage": 58.21, "elapsed_time": "1:09:01", "remaining_time": "0:49:33", "throughput": 5524.91, "total_tokens": 22882480} {"current_steps": 37525, "total_steps": 64460, "loss": 0.21, "lr": 4.440427460788206e-06, "epoch": 11.642879304995345, "percentage": 58.21, "elapsed_time": "1:09:02", "remaining_time": "0:49:33", "throughput": 5524.92, "total_tokens": 22885200} {"current_steps": 37530, "total_steps": 64460, "loss": 0.2104, "lr": 4.43908217817318e-06, "epoch": 11.644430654669563, "percentage": 58.22, "elapsed_time": "1:09:02", "remaining_time": "0:49:32", "throughput": 5524.89, "total_tokens": 22887696} {"current_steps": 37535, "total_steps": 64460, "loss": 0.2055, "lr": 4.4377369366800735e-06, "epoch": 11.645982004343779, "percentage": 58.23, "elapsed_time": "1:09:03", "remaining_time": "0:49:32", "throughput": 5524.96, "total_tokens": 22890768} {"current_steps": 37540, "total_steps": 64460, "loss": 0.2199, "lr": 4.436391736407507e-06, "epoch": 11.647533354017996, "percentage": 58.24, "elapsed_time": "1:09:03", "remaining_time": "0:49:31", "throughput": 5524.98, "total_tokens": 22893744} {"current_steps": 37545, "total_steps": 64460, "loss": 0.2156, "lr": 4.4350465774541e-06, "epoch": 11.649084703692212, "percentage": 58.25, "elapsed_time": "1:09:04", "remaining_time": "0:49:30", "throughput": 5525.03, "total_tokens": 22896784} {"current_steps": 37550, "total_steps": 64460, "loss": 0.1928, "lr": 4.43370145991847e-06, "epoch": 11.650636053366428, "percentage": 58.25, "elapsed_time": "1:09:04", "remaining_time": "0:49:30", "throughput": 5525.03, "total_tokens": 22899376} {"current_steps": 37555, "total_steps": 64460, "loss": 0.226, "lr": 4.432356383899229e-06, "epoch": 11.652187403040646, "percentage": 58.26, "elapsed_time": "1:09:05", "remaining_time": "0:49:29", "throughput": 5524.95, "total_tokens": 22901680} {"current_steps": 37560, "total_steps": 64460, "loss": 0.2262, "lr": 4.431011349494986e-06, "epoch": 11.653738752714862, "percentage": 58.27, "elapsed_time": "1:09:05", "remaining_time": "0:49:29", "throughput": 5525.02, "total_tokens": 22904816} {"current_steps": 37565, "total_steps": 64460, "loss": 0.2252, "lr": 4.42966635680435e-06, "epoch": 11.655290102389078, "percentage": 58.28, "elapsed_time": "1:09:06", "remaining_time": "0:49:28", "throughput": 5525.04, "total_tokens": 22907504} {"current_steps": 37570, "total_steps": 64460, "loss": 0.2422, "lr": 4.428321405925923e-06, "epoch": 11.656841452063295, "percentage": 58.28, "elapsed_time": "1:09:06", "remaining_time": "0:49:27", "throughput": 5525.13, "total_tokens": 22910736} {"current_steps": 37575, "total_steps": 64460, "loss": 0.2273, "lr": 4.426976496958306e-06, "epoch": 11.658392801737511, "percentage": 58.29, "elapsed_time": "1:09:07", "remaining_time": "0:49:27", "throughput": 5525.16, "total_tokens": 22913424} {"current_steps": 37580, "total_steps": 64460, "loss": 0.2057, "lr": 4.425631630000099e-06, "epoch": 11.659944151411729, "percentage": 58.3, "elapsed_time": "1:09:07", "remaining_time": "0:49:26", "throughput": 5525.22, "total_tokens": 22916624} {"current_steps": 37585, "total_steps": 64460, "loss": 0.2285, "lr": 4.424286805149895e-06, "epoch": 11.661495501085945, "percentage": 58.31, "elapsed_time": "1:09:08", "remaining_time": "0:49:26", "throughput": 5525.27, "total_tokens": 22919472} {"current_steps": 37590, "total_steps": 64460, "loss": 0.2098, "lr": 4.422942022506285e-06, "epoch": 11.66304685076016, "percentage": 58.32, "elapsed_time": "1:09:08", "remaining_time": "0:49:25", "throughput": 5525.29, "total_tokens": 22922192} {"current_steps": 37595, "total_steps": 64460, "loss": 0.2616, "lr": 4.421597282167858e-06, "epoch": 11.664598200434378, "percentage": 58.32, "elapsed_time": "1:09:09", "remaining_time": "0:49:24", "throughput": 5525.37, "total_tokens": 22925392} {"current_steps": 37600, "total_steps": 64460, "loss": 0.2298, "lr": 4.4202525842332e-06, "epoch": 11.666149550108594, "percentage": 58.33, "elapsed_time": "1:09:09", "remaining_time": "0:49:24", "throughput": 5525.27, "total_tokens": 22927600} {"current_steps": 37605, "total_steps": 64460, "loss": 0.2164, "lr": 4.418907928800891e-06, "epoch": 11.667700899782812, "percentage": 58.34, "elapsed_time": "1:09:10", "remaining_time": "0:49:23", "throughput": 5525.28, "total_tokens": 22930608} {"current_steps": 37610, "total_steps": 64460, "loss": 0.2269, "lr": 4.417563315969513e-06, "epoch": 11.669252249457028, "percentage": 58.35, "elapsed_time": "1:09:10", "remaining_time": "0:49:23", "throughput": 5525.36, "total_tokens": 22933776} {"current_steps": 37615, "total_steps": 64460, "loss": 0.2057, "lr": 4.416218745837642e-06, "epoch": 11.670803599131244, "percentage": 58.35, "elapsed_time": "1:09:11", "remaining_time": "0:49:22", "throughput": 5525.44, "total_tokens": 22937136} {"current_steps": 37620, "total_steps": 64460, "loss": 0.2437, "lr": 4.414874218503849e-06, "epoch": 11.672354948805461, "percentage": 58.36, "elapsed_time": "1:09:11", "remaining_time": "0:49:22", "throughput": 5525.47, "total_tokens": 22940304} {"current_steps": 37625, "total_steps": 64460, "loss": 0.1588, "lr": 4.413529734066705e-06, "epoch": 11.673906298479677, "percentage": 58.37, "elapsed_time": "1:09:12", "remaining_time": "0:49:21", "throughput": 5525.5, "total_tokens": 22943152} {"current_steps": 37630, "total_steps": 64460, "loss": 0.225, "lr": 4.412185292624777e-06, "epoch": 11.675457648153895, "percentage": 58.38, "elapsed_time": "1:09:12", "remaining_time": "0:49:20", "throughput": 5525.62, "total_tokens": 22947344} {"current_steps": 37635, "total_steps": 64460, "loss": 0.2622, "lr": 4.410840894276627e-06, "epoch": 11.67700899782811, "percentage": 58.39, "elapsed_time": "1:09:13", "remaining_time": "0:49:20", "throughput": 5525.69, "total_tokens": 22950832} {"current_steps": 37640, "total_steps": 64460, "loss": 0.2123, "lr": 4.409496539120817e-06, "epoch": 11.678560347502327, "percentage": 58.39, "elapsed_time": "1:09:13", "remaining_time": "0:49:19", "throughput": 5525.74, "total_tokens": 22953904} {"current_steps": 37645, "total_steps": 64460, "loss": 0.2539, "lr": 4.408152227255902e-06, "epoch": 11.680111697176544, "percentage": 58.4, "elapsed_time": "1:09:14", "remaining_time": "0:49:19", "throughput": 5525.78, "total_tokens": 22957232} {"current_steps": 37650, "total_steps": 64460, "loss": 0.2517, "lr": 4.4068079587804385e-06, "epoch": 11.68166304685076, "percentage": 58.41, "elapsed_time": "1:09:15", "remaining_time": "0:49:18", "throughput": 5525.86, "total_tokens": 22960336} {"current_steps": 37655, "total_steps": 64460, "loss": 0.2716, "lr": 4.405463733792975e-06, "epoch": 11.683214396524976, "percentage": 58.42, "elapsed_time": "1:09:15", "remaining_time": "0:49:18", "throughput": 5525.97, "total_tokens": 22964016} {"current_steps": 37660, "total_steps": 64460, "loss": 0.2196, "lr": 4.404119552392061e-06, "epoch": 11.684765746199194, "percentage": 58.42, "elapsed_time": "1:09:16", "remaining_time": "0:49:17", "throughput": 5526.05, "total_tokens": 22967792} {"current_steps": 37665, "total_steps": 64460, "loss": 0.2389, "lr": 4.402775414676239e-06, "epoch": 11.68631709587341, "percentage": 58.43, "elapsed_time": "1:09:16", "remaining_time": "0:49:17", "throughput": 5525.95, "total_tokens": 22969904} {"current_steps": 37670, "total_steps": 64460, "loss": 0.2075, "lr": 4.401431320744052e-06, "epoch": 11.687868445547627, "percentage": 58.44, "elapsed_time": "1:09:17", "remaining_time": "0:49:16", "throughput": 5525.85, "total_tokens": 22972208} {"current_steps": 37675, "total_steps": 64460, "loss": 0.2349, "lr": 4.400087270694038e-06, "epoch": 11.689419795221843, "percentage": 58.45, "elapsed_time": "1:09:17", "remaining_time": "0:49:15", "throughput": 5525.96, "total_tokens": 22975920} {"current_steps": 37680, "total_steps": 64460, "loss": 0.2235, "lr": 4.39874326462473e-06, "epoch": 11.690971144896059, "percentage": 58.45, "elapsed_time": "1:09:18", "remaining_time": "0:49:15", "throughput": 5525.98, "total_tokens": 22978864} {"current_steps": 37685, "total_steps": 64460, "loss": 0.2089, "lr": 4.397399302634661e-06, "epoch": 11.692522494570277, "percentage": 58.46, "elapsed_time": "1:09:18", "remaining_time": "0:49:14", "throughput": 5525.97, "total_tokens": 22981808} {"current_steps": 37690, "total_steps": 64460, "loss": 0.1924, "lr": 4.39605538482236e-06, "epoch": 11.694073844244492, "percentage": 58.47, "elapsed_time": "1:09:19", "remaining_time": "0:49:14", "throughput": 5526.19, "total_tokens": 22986416} {"current_steps": 37695, "total_steps": 64460, "loss": 0.2303, "lr": 4.39471151128635e-06, "epoch": 11.695625193918708, "percentage": 58.48, "elapsed_time": "1:09:20", "remaining_time": "0:49:14", "throughput": 5526.43, "total_tokens": 22991952} {"current_steps": 37700, "total_steps": 64460, "loss": 0.2291, "lr": 4.393367682125154e-06, "epoch": 11.697176543592926, "percentage": 58.49, "elapsed_time": "1:09:20", "remaining_time": "0:49:13", "throughput": 5526.54, "total_tokens": 22995472} {"current_steps": 37705, "total_steps": 64460, "loss": 0.235, "lr": 4.392023897437291e-06, "epoch": 11.698727893267142, "percentage": 58.49, "elapsed_time": "1:09:21", "remaining_time": "0:49:12", "throughput": 5526.61, "total_tokens": 22998736} {"current_steps": 37710, "total_steps": 64460, "loss": 0.2438, "lr": 4.390680157321275e-06, "epoch": 11.70027924294136, "percentage": 58.5, "elapsed_time": "1:09:21", "remaining_time": "0:49:12", "throughput": 5526.56, "total_tokens": 23001360} {"current_steps": 37715, "total_steps": 64460, "loss": 0.2269, "lr": 4.38933646187562e-06, "epoch": 11.701830592615575, "percentage": 58.51, "elapsed_time": "1:09:22", "remaining_time": "0:49:11", "throughput": 5526.51, "total_tokens": 23003792} {"current_steps": 37720, "total_steps": 64460, "loss": 0.2276, "lr": 4.387992811198832e-06, "epoch": 11.703381942289791, "percentage": 58.52, "elapsed_time": "1:09:23", "remaining_time": "0:49:11", "throughput": 5526.59, "total_tokens": 23007696} {"current_steps": 37725, "total_steps": 64460, "loss": 0.2318, "lr": 4.3866492053894185e-06, "epoch": 11.704933291964009, "percentage": 58.52, "elapsed_time": "1:09:23", "remaining_time": "0:49:10", "throughput": 5526.57, "total_tokens": 23010448} {"current_steps": 37730, "total_steps": 64460, "loss": 0.1904, "lr": 4.385305644545882e-06, "epoch": 11.706484641638225, "percentage": 58.53, "elapsed_time": "1:09:24", "remaining_time": "0:49:10", "throughput": 5526.48, "total_tokens": 23012688} {"current_steps": 37735, "total_steps": 64460, "loss": 0.2293, "lr": 4.383962128766721e-06, "epoch": 11.708035991312443, "percentage": 58.54, "elapsed_time": "1:09:24", "remaining_time": "0:49:09", "throughput": 5526.41, "total_tokens": 23015376} {"current_steps": 37740, "total_steps": 64460, "loss": 0.2171, "lr": 4.382618658150431e-06, "epoch": 11.709587340986658, "percentage": 58.55, "elapsed_time": "1:09:25", "remaining_time": "0:49:08", "throughput": 5526.26, "total_tokens": 23017712} {"current_steps": 37745, "total_steps": 64460, "loss": 0.2297, "lr": 4.381275232795504e-06, "epoch": 11.711138690660874, "percentage": 58.56, "elapsed_time": "1:09:25", "remaining_time": "0:49:08", "throughput": 5526.33, "total_tokens": 23020848} {"current_steps": 37750, "total_steps": 64460, "loss": 0.2002, "lr": 4.37993185280043e-06, "epoch": 11.712690040335092, "percentage": 58.56, "elapsed_time": "1:09:26", "remaining_time": "0:49:07", "throughput": 5526.32, "total_tokens": 23023632} {"current_steps": 37755, "total_steps": 64460, "loss": 0.2308, "lr": 4.378588518263693e-06, "epoch": 11.714241390009308, "percentage": 58.57, "elapsed_time": "1:09:26", "remaining_time": "0:49:07", "throughput": 5526.47, "total_tokens": 23027664} {"current_steps": 37760, "total_steps": 64460, "loss": 0.227, "lr": 4.377245229283776e-06, "epoch": 11.715792739683526, "percentage": 58.58, "elapsed_time": "1:09:27", "remaining_time": "0:49:06", "throughput": 5526.63, "total_tokens": 23031312} {"current_steps": 37765, "total_steps": 64460, "loss": 0.2161, "lr": 4.375901985959159e-06, "epoch": 11.717344089357741, "percentage": 58.59, "elapsed_time": "1:09:27", "remaining_time": "0:49:06", "throughput": 5526.77, "total_tokens": 23034800} {"current_steps": 37770, "total_steps": 64460, "loss": 0.2147, "lr": 4.374558788388317e-06, "epoch": 11.718895439031957, "percentage": 58.59, "elapsed_time": "1:09:28", "remaining_time": "0:49:05", "throughput": 5526.85, "total_tokens": 23037968} {"current_steps": 37775, "total_steps": 64460, "loss": 0.1971, "lr": 4.373215636669721e-06, "epoch": 11.720446788706175, "percentage": 58.6, "elapsed_time": "1:09:28", "remaining_time": "0:49:05", "throughput": 5526.9, "total_tokens": 23041264} {"current_steps": 37780, "total_steps": 64460, "loss": 0.2423, "lr": 4.3718725309018424e-06, "epoch": 11.72199813838039, "percentage": 58.61, "elapsed_time": "1:09:29", "remaining_time": "0:49:04", "throughput": 5526.94, "total_tokens": 23044240} {"current_steps": 37785, "total_steps": 64460, "loss": 0.2302, "lr": 4.3705294711831435e-06, "epoch": 11.723549488054607, "percentage": 58.62, "elapsed_time": "1:09:29", "remaining_time": "0:49:03", "throughput": 5526.94, "total_tokens": 23046832} {"current_steps": 37790, "total_steps": 64460, "loss": 0.2174, "lr": 4.3691864576120905e-06, "epoch": 11.725100837728824, "percentage": 58.63, "elapsed_time": "1:09:30", "remaining_time": "0:49:03", "throughput": 5526.84, "total_tokens": 23049040} {"current_steps": 37795, "total_steps": 64460, "loss": 0.212, "lr": 4.367843490287139e-06, "epoch": 11.72665218740304, "percentage": 58.63, "elapsed_time": "1:09:30", "remaining_time": "0:49:02", "throughput": 5526.79, "total_tokens": 23051600} {"current_steps": 37800, "total_steps": 64460, "loss": 0.2096, "lr": 4.366500569306746e-06, "epoch": 11.728203537077258, "percentage": 58.64, "elapsed_time": "1:09:31", "remaining_time": "0:49:02", "throughput": 5526.82, "total_tokens": 23054640} {"current_steps": 37805, "total_steps": 64460, "loss": 0.2347, "lr": 4.365157694769363e-06, "epoch": 11.729754886751474, "percentage": 58.65, "elapsed_time": "1:09:31", "remaining_time": "0:49:01", "throughput": 5526.85, "total_tokens": 23057488} {"current_steps": 37810, "total_steps": 64460, "loss": 0.2288, "lr": 4.3638148667734385e-06, "epoch": 11.73130623642569, "percentage": 58.66, "elapsed_time": "1:09:32", "remaining_time": "0:49:00", "throughput": 5526.93, "total_tokens": 23060816} {"current_steps": 37815, "total_steps": 64460, "loss": 0.2416, "lr": 4.3624720854174174e-06, "epoch": 11.732857586099907, "percentage": 58.66, "elapsed_time": "1:09:33", "remaining_time": "0:49:00", "throughput": 5527.05, "total_tokens": 23064720} {"current_steps": 37820, "total_steps": 64460, "loss": 0.2293, "lr": 4.361129350799742e-06, "epoch": 11.734408935774123, "percentage": 58.67, "elapsed_time": "1:09:33", "remaining_time": "0:48:59", "throughput": 5527.05, "total_tokens": 23067952} {"current_steps": 37825, "total_steps": 64460, "loss": 0.2171, "lr": 4.359786663018849e-06, "epoch": 11.73596028544834, "percentage": 58.68, "elapsed_time": "1:09:34", "remaining_time": "0:48:59", "throughput": 5527.03, "total_tokens": 23070800} {"current_steps": 37830, "total_steps": 64460, "loss": 0.2438, "lr": 4.358444022173177e-06, "epoch": 11.737511635122557, "percentage": 58.69, "elapsed_time": "1:09:34", "remaining_time": "0:48:58", "throughput": 5527.03, "total_tokens": 23073520} {"current_steps": 37835, "total_steps": 64460, "loss": 0.2129, "lr": 4.357101428361154e-06, "epoch": 11.739062984796773, "percentage": 58.7, "elapsed_time": "1:09:35", "remaining_time": "0:48:58", "throughput": 5527.05, "total_tokens": 23076656} {"current_steps": 37840, "total_steps": 64460, "loss": 0.217, "lr": 4.355758881681211e-06, "epoch": 11.74061433447099, "percentage": 58.7, "elapsed_time": "1:09:35", "remaining_time": "0:48:57", "throughput": 5527.16, "total_tokens": 23079824} {"current_steps": 37845, "total_steps": 64460, "loss": 0.1949, "lr": 4.354416382231771e-06, "epoch": 11.742165684145206, "percentage": 58.71, "elapsed_time": "1:09:36", "remaining_time": "0:48:56", "throughput": 5527.17, "total_tokens": 23082768} {"current_steps": 37850, "total_steps": 64460, "loss": 0.215, "lr": 4.353073930111254e-06, "epoch": 11.743717033819422, "percentage": 58.72, "elapsed_time": "1:09:36", "remaining_time": "0:48:56", "throughput": 5527.14, "total_tokens": 23085552} {"current_steps": 37855, "total_steps": 64460, "loss": 0.2067, "lr": 4.3517315254180795e-06, "epoch": 11.74526838349364, "percentage": 58.73, "elapsed_time": "1:09:37", "remaining_time": "0:48:55", "throughput": 5527.06, "total_tokens": 23087792} {"current_steps": 37860, "total_steps": 64460, "loss": 0.2316, "lr": 4.35038916825066e-06, "epoch": 11.746819733167856, "percentage": 58.73, "elapsed_time": "1:09:37", "remaining_time": "0:48:55", "throughput": 5527.14, "total_tokens": 23090992} {"current_steps": 37865, "total_steps": 64460, "loss": 0.1966, "lr": 4.349046858707408e-06, "epoch": 11.748371082842073, "percentage": 58.74, "elapsed_time": "1:09:38", "remaining_time": "0:48:54", "throughput": 5527.14, "total_tokens": 23094448} {"current_steps": 37870, "total_steps": 64460, "loss": 0.2106, "lr": 4.3477045968867275e-06, "epoch": 11.74992243251629, "percentage": 58.75, "elapsed_time": "1:09:38", "remaining_time": "0:48:54", "throughput": 5527.11, "total_tokens": 23097296} {"current_steps": 37875, "total_steps": 64460, "loss": 0.2044, "lr": 4.346362382887026e-06, "epoch": 11.751473782190505, "percentage": 58.76, "elapsed_time": "1:09:39", "remaining_time": "0:48:53", "throughput": 5527.32, "total_tokens": 23101584} {"current_steps": 37880, "total_steps": 64460, "loss": 0.2381, "lr": 4.345020216806702e-06, "epoch": 11.753025131864723, "percentage": 58.77, "elapsed_time": "1:09:40", "remaining_time": "0:48:53", "throughput": 5527.39, "total_tokens": 23105360} {"current_steps": 37885, "total_steps": 64460, "loss": 0.2298, "lr": 4.343678098744153e-06, "epoch": 11.754576481538939, "percentage": 58.77, "elapsed_time": "1:09:40", "remaining_time": "0:48:52", "throughput": 5527.44, "total_tokens": 23108432} {"current_steps": 37890, "total_steps": 64460, "loss": 0.2236, "lr": 4.34233602879777e-06, "epoch": 11.756127831213156, "percentage": 58.78, "elapsed_time": "1:09:41", "remaining_time": "0:48:51", "throughput": 5527.33, "total_tokens": 23110512} {"current_steps": 37895, "total_steps": 64460, "loss": 0.2147, "lr": 4.3409940070659445e-06, "epoch": 11.757679180887372, "percentage": 58.79, "elapsed_time": "1:09:41", "remaining_time": "0:48:51", "throughput": 5527.26, "total_tokens": 23112784} {"current_steps": 37900, "total_steps": 64460, "loss": 0.1875, "lr": 4.339652033647062e-06, "epoch": 11.759230530561588, "percentage": 58.8, "elapsed_time": "1:09:42", "remaining_time": "0:48:50", "throughput": 5527.37, "total_tokens": 23116208} {"current_steps": 37905, "total_steps": 64460, "loss": 0.1956, "lr": 4.338310108639506e-06, "epoch": 11.760781880235806, "percentage": 58.8, "elapsed_time": "1:09:42", "remaining_time": "0:48:50", "throughput": 5527.33, "total_tokens": 23118768} {"current_steps": 37910, "total_steps": 64460, "loss": 0.2083, "lr": 4.336968232141654e-06, "epoch": 11.762333229910022, "percentage": 58.81, "elapsed_time": "1:09:43", "remaining_time": "0:48:49", "throughput": 5527.42, "total_tokens": 23122064} {"current_steps": 37915, "total_steps": 64460, "loss": 0.2627, "lr": 4.3356264042518815e-06, "epoch": 11.763884579584237, "percentage": 58.82, "elapsed_time": "1:09:43", "remaining_time": "0:48:49", "throughput": 5527.42, "total_tokens": 23125072} {"current_steps": 37920, "total_steps": 64460, "loss": 0.2223, "lr": 4.334284625068562e-06, "epoch": 11.765435929258455, "percentage": 58.83, "elapsed_time": "1:09:44", "remaining_time": "0:48:48", "throughput": 5527.36, "total_tokens": 23127408} {"current_steps": 37925, "total_steps": 64460, "loss": 0.2018, "lr": 4.332942894690062e-06, "epoch": 11.766987278932671, "percentage": 58.83, "elapsed_time": "1:09:44", "remaining_time": "0:48:47", "throughput": 5527.38, "total_tokens": 23130384} {"current_steps": 37930, "total_steps": 64460, "loss": 0.1962, "lr": 4.331601213214746e-06, "epoch": 11.768538628606889, "percentage": 58.84, "elapsed_time": "1:09:45", "remaining_time": "0:48:47", "throughput": 5527.41, "total_tokens": 23133552} {"current_steps": 37935, "total_steps": 64460, "loss": 0.2377, "lr": 4.330259580740977e-06, "epoch": 11.770089978281105, "percentage": 58.85, "elapsed_time": "1:09:45", "remaining_time": "0:48:46", "throughput": 5527.4, "total_tokens": 23136272} {"current_steps": 37940, "total_steps": 64460, "loss": 0.1882, "lr": 4.328917997367112e-06, "epoch": 11.77164132795532, "percentage": 58.86, "elapsed_time": "1:09:46", "remaining_time": "0:48:46", "throughput": 5527.62, "total_tokens": 23141008} {"current_steps": 37945, "total_steps": 64460, "loss": 0.2097, "lr": 4.3275764631915046e-06, "epoch": 11.773192677629538, "percentage": 58.87, "elapsed_time": "1:09:46", "remaining_time": "0:48:45", "throughput": 5527.62, "total_tokens": 23143856} {"current_steps": 37950, "total_steps": 64460, "loss": 0.2452, "lr": 4.326234978312505e-06, "epoch": 11.774744027303754, "percentage": 58.87, "elapsed_time": "1:09:47", "remaining_time": "0:48:45", "throughput": 5527.65, "total_tokens": 23146736} {"current_steps": 37955, "total_steps": 64460, "loss": 0.2015, "lr": 4.32489354282846e-06, "epoch": 11.77629537697797, "percentage": 58.88, "elapsed_time": "1:09:47", "remaining_time": "0:48:44", "throughput": 5527.61, "total_tokens": 23149200} {"current_steps": 37960, "total_steps": 64460, "loss": 0.205, "lr": 4.323552156837712e-06, "epoch": 11.777846726652188, "percentage": 58.89, "elapsed_time": "1:09:48", "remaining_time": "0:48:43", "throughput": 5527.61, "total_tokens": 23151824} {"current_steps": 37965, "total_steps": 64460, "loss": 0.2278, "lr": 4.322210820438603e-06, "epoch": 11.779398076326403, "percentage": 58.9, "elapsed_time": "1:09:48", "remaining_time": "0:48:43", "throughput": 5527.67, "total_tokens": 23154704} {"current_steps": 37970, "total_steps": 64460, "loss": 0.2155, "lr": 4.3208695337294655e-06, "epoch": 11.780949426000621, "percentage": 58.9, "elapsed_time": "1:09:49", "remaining_time": "0:48:42", "throughput": 5527.68, "total_tokens": 23157936} {"current_steps": 37975, "total_steps": 64460, "loss": 0.2305, "lr": 4.3195282968086344e-06, "epoch": 11.782500775674837, "percentage": 58.91, "elapsed_time": "1:09:49", "remaining_time": "0:48:42", "throughput": 5527.67, "total_tokens": 23160784} {"current_steps": 37980, "total_steps": 64460, "loss": 0.19, "lr": 4.3181871097744364e-06, "epoch": 11.784052125349053, "percentage": 58.92, "elapsed_time": "1:09:50", "remaining_time": "0:48:41", "throughput": 5527.62, "total_tokens": 23163120} {"current_steps": 37985, "total_steps": 64460, "loss": 0.2339, "lr": 4.316845972725198e-06, "epoch": 11.78560347502327, "percentage": 58.93, "elapsed_time": "1:09:50", "remaining_time": "0:48:41", "throughput": 5527.59, "total_tokens": 23165968} {"current_steps": 37990, "total_steps": 64460, "loss": 0.2225, "lr": 4.315504885759237e-06, "epoch": 11.787154824697486, "percentage": 58.94, "elapsed_time": "1:09:51", "remaining_time": "0:48:40", "throughput": 5527.66, "total_tokens": 23168880} {"current_steps": 37995, "total_steps": 64460, "loss": 0.2213, "lr": 4.314163848974876e-06, "epoch": 11.788706174371704, "percentage": 58.94, "elapsed_time": "1:09:51", "remaining_time": "0:48:39", "throughput": 5527.61, "total_tokens": 23171568} {"current_steps": 38000, "total_steps": 64460, "loss": 0.2353, "lr": 4.312822862470426e-06, "epoch": 11.79025752404592, "percentage": 58.95, "elapsed_time": "1:09:52", "remaining_time": "0:48:39", "throughput": 5527.49, "total_tokens": 23173584} {"current_steps": 38005, "total_steps": 64460, "loss": 0.246, "lr": 4.311481926344198e-06, "epoch": 11.791808873720136, "percentage": 58.96, "elapsed_time": "1:09:52", "remaining_time": "0:48:38", "throughput": 5527.5, "total_tokens": 23176304} {"current_steps": 38010, "total_steps": 64460, "loss": 0.2179, "lr": 4.310141040694497e-06, "epoch": 11.793360223394354, "percentage": 58.97, "elapsed_time": "1:09:53", "remaining_time": "0:48:38", "throughput": 5527.53, "total_tokens": 23179280} {"current_steps": 38015, "total_steps": 64460, "loss": 0.2623, "lr": 4.308800205619627e-06, "epoch": 11.79491157306857, "percentage": 58.97, "elapsed_time": "1:09:53", "remaining_time": "0:48:37", "throughput": 5527.6, "total_tokens": 23182544} {"current_steps": 38020, "total_steps": 64460, "loss": 0.2208, "lr": 4.307459421217888e-06, "epoch": 11.796462922742787, "percentage": 58.98, "elapsed_time": "1:09:54", "remaining_time": "0:48:36", "throughput": 5527.59, "total_tokens": 23185360} {"current_steps": 38025, "total_steps": 64460, "loss": 0.1952, "lr": 4.306118687587574e-06, "epoch": 11.798014272417003, "percentage": 58.99, "elapsed_time": "1:09:55", "remaining_time": "0:48:36", "throughput": 5527.68, "total_tokens": 23188688} {"current_steps": 38030, "total_steps": 64460, "loss": 0.2189, "lr": 4.304778004826976e-06, "epoch": 11.799565622091219, "percentage": 59.0, "elapsed_time": "1:09:55", "remaining_time": "0:48:35", "throughput": 5527.66, "total_tokens": 23191536} {"current_steps": 38035, "total_steps": 64460, "loss": 0.2706, "lr": 4.303437373034384e-06, "epoch": 11.801116971765437, "percentage": 59.01, "elapsed_time": "1:09:56", "remaining_time": "0:48:35", "throughput": 5527.75, "total_tokens": 23194928} {"current_steps": 38040, "total_steps": 64460, "loss": 0.2241, "lr": 4.30209679230808e-06, "epoch": 11.802668321439652, "percentage": 59.01, "elapsed_time": "1:09:56", "remaining_time": "0:48:34", "throughput": 5527.89, "total_tokens": 23199056} {"current_steps": 38045, "total_steps": 64460, "loss": 0.2254, "lr": 4.3007562627463465e-06, "epoch": 11.804219671113868, "percentage": 59.02, "elapsed_time": "1:09:57", "remaining_time": "0:48:34", "throughput": 5527.91, "total_tokens": 23201808} {"current_steps": 38050, "total_steps": 64460, "loss": 0.218, "lr": 4.299415784447457e-06, "epoch": 11.805771020788086, "percentage": 59.03, "elapsed_time": "1:09:57", "remaining_time": "0:48:33", "throughput": 5527.84, "total_tokens": 23204112} {"current_steps": 38055, "total_steps": 64460, "loss": 0.214, "lr": 4.298075357509689e-06, "epoch": 11.807322370462302, "percentage": 59.04, "elapsed_time": "1:09:58", "remaining_time": "0:48:32", "throughput": 5527.79, "total_tokens": 23206512} {"current_steps": 38060, "total_steps": 64460, "loss": 0.2053, "lr": 4.29673498203131e-06, "epoch": 11.80887372013652, "percentage": 59.04, "elapsed_time": "1:09:58", "remaining_time": "0:48:32", "throughput": 5527.81, "total_tokens": 23209360} {"current_steps": 38065, "total_steps": 64460, "loss": 0.2219, "lr": 4.295394658110583e-06, "epoch": 11.810425069810735, "percentage": 59.05, "elapsed_time": "1:09:59", "remaining_time": "0:48:31", "throughput": 5527.75, "total_tokens": 23211696} {"current_steps": 38070, "total_steps": 64460, "loss": 0.1796, "lr": 4.294054385845772e-06, "epoch": 11.811976419484951, "percentage": 59.06, "elapsed_time": "1:09:59", "remaining_time": "0:48:31", "throughput": 5527.77, "total_tokens": 23214544} {"current_steps": 38075, "total_steps": 64460, "loss": 0.214, "lr": 4.292714165335134e-06, "epoch": 11.813527769159169, "percentage": 59.07, "elapsed_time": "1:10:00", "remaining_time": "0:48:30", "throughput": 5527.87, "total_tokens": 23218096} {"current_steps": 38080, "total_steps": 64460, "loss": 0.2043, "lr": 4.2913739966769235e-06, "epoch": 11.815079118833385, "percentage": 59.08, "elapsed_time": "1:10:00", "remaining_time": "0:48:30", "throughput": 5527.89, "total_tokens": 23221040} {"current_steps": 38085, "total_steps": 64460, "loss": 0.248, "lr": 4.2900338799693904e-06, "epoch": 11.8166304685076, "percentage": 59.08, "elapsed_time": "1:10:01", "remaining_time": "0:48:29", "throughput": 5527.88, "total_tokens": 23224144} {"current_steps": 38090, "total_steps": 64460, "loss": 0.2324, "lr": 4.288693815310781e-06, "epoch": 11.818181818181818, "percentage": 59.09, "elapsed_time": "1:10:01", "remaining_time": "0:48:28", "throughput": 5527.81, "total_tokens": 23226512} {"current_steps": 38095, "total_steps": 64460, "loss": 0.1766, "lr": 4.287353802799338e-06, "epoch": 11.819733167856034, "percentage": 59.1, "elapsed_time": "1:10:02", "remaining_time": "0:48:28", "throughput": 5527.87, "total_tokens": 23229744} {"current_steps": 38100, "total_steps": 64460, "loss": 0.2586, "lr": 4.2860138425333006e-06, "epoch": 11.821284517530252, "percentage": 59.11, "elapsed_time": "1:10:02", "remaining_time": "0:48:27", "throughput": 5527.85, "total_tokens": 23232336} {"current_steps": 38105, "total_steps": 64460, "loss": 0.2477, "lr": 4.2846739346109025e-06, "epoch": 11.822835867204468, "percentage": 59.11, "elapsed_time": "1:10:03", "remaining_time": "0:48:27", "throughput": 5527.89, "total_tokens": 23235280} {"current_steps": 38110, "total_steps": 64460, "loss": 0.2496, "lr": 4.283334079130376e-06, "epoch": 11.824387216878684, "percentage": 59.12, "elapsed_time": "1:10:03", "remaining_time": "0:48:26", "throughput": 5527.84, "total_tokens": 23237680} {"current_steps": 38115, "total_steps": 64460, "loss": 0.2319, "lr": 4.281994276189948e-06, "epoch": 11.825938566552901, "percentage": 59.13, "elapsed_time": "1:10:04", "remaining_time": "0:48:25", "throughput": 5527.69, "total_tokens": 23240016} {"current_steps": 38120, "total_steps": 64460, "loss": 0.253, "lr": 4.280654525887843e-06, "epoch": 11.827489916227117, "percentage": 59.14, "elapsed_time": "1:10:04", "remaining_time": "0:48:25", "throughput": 5527.7, "total_tokens": 23242608} {"current_steps": 38125, "total_steps": 64460, "loss": 0.2755, "lr": 4.279314828322279e-06, "epoch": 11.829041265901335, "percentage": 59.15, "elapsed_time": "1:10:05", "remaining_time": "0:48:24", "throughput": 5527.71, "total_tokens": 23245680} {"current_steps": 38130, "total_steps": 64460, "loss": 0.2247, "lr": 4.277975183591472e-06, "epoch": 11.83059261557555, "percentage": 59.15, "elapsed_time": "1:10:05", "remaining_time": "0:48:24", "throughput": 5527.64, "total_tokens": 23248208} {"current_steps": 38135, "total_steps": 64460, "loss": 0.1939, "lr": 4.276635591793634e-06, "epoch": 11.832143965249767, "percentage": 59.16, "elapsed_time": "1:10:06", "remaining_time": "0:48:23", "throughput": 5527.67, "total_tokens": 23251632} {"current_steps": 38140, "total_steps": 64460, "loss": 0.2223, "lr": 4.275296053026974e-06, "epoch": 11.833695314923984, "percentage": 59.17, "elapsed_time": "1:10:06", "remaining_time": "0:48:23", "throughput": 5527.63, "total_tokens": 23254192} {"current_steps": 38145, "total_steps": 64460, "loss": 0.2177, "lr": 4.273956567389694e-06, "epoch": 11.8352466645982, "percentage": 59.18, "elapsed_time": "1:10:07", "remaining_time": "0:48:22", "throughput": 5527.67, "total_tokens": 23257104} {"current_steps": 38150, "total_steps": 64460, "loss": 0.2668, "lr": 4.272617134979996e-06, "epoch": 11.836798014272418, "percentage": 59.18, "elapsed_time": "1:10:07", "remaining_time": "0:48:21", "throughput": 5527.66, "total_tokens": 23259632} {"current_steps": 38155, "total_steps": 64460, "loss": 0.2219, "lr": 4.271277755896075e-06, "epoch": 11.838349363946634, "percentage": 59.19, "elapsed_time": "1:10:08", "remaining_time": "0:48:21", "throughput": 5527.71, "total_tokens": 23262672} {"current_steps": 38160, "total_steps": 64460, "loss": 0.2582, "lr": 4.269938430236124e-06, "epoch": 11.83990071362085, "percentage": 59.2, "elapsed_time": "1:10:09", "remaining_time": "0:48:20", "throughput": 5527.87, "total_tokens": 23266832} {"current_steps": 38165, "total_steps": 64460, "loss": 0.2398, "lr": 4.268599158098332e-06, "epoch": 11.841452063295067, "percentage": 59.21, "elapsed_time": "1:10:09", "remaining_time": "0:48:20", "throughput": 5527.89, "total_tokens": 23270384} {"current_steps": 38170, "total_steps": 64460, "loss": 0.2179, "lr": 4.26725993958088e-06, "epoch": 11.843003412969283, "percentage": 59.22, "elapsed_time": "1:10:10", "remaining_time": "0:48:19", "throughput": 5527.85, "total_tokens": 23272848} {"current_steps": 38175, "total_steps": 64460, "loss": 0.2132, "lr": 4.265920774781954e-06, "epoch": 11.844554762643499, "percentage": 59.22, "elapsed_time": "1:10:10", "remaining_time": "0:48:19", "throughput": 5527.79, "total_tokens": 23275344} {"current_steps": 38180, "total_steps": 64460, "loss": 0.2277, "lr": 4.264581663799728e-06, "epoch": 11.846106112317717, "percentage": 59.23, "elapsed_time": "1:10:11", "remaining_time": "0:48:18", "throughput": 5527.82, "total_tokens": 23278288} {"current_steps": 38185, "total_steps": 64460, "loss": 0.1991, "lr": 4.263242606732374e-06, "epoch": 11.847657461991933, "percentage": 59.24, "elapsed_time": "1:10:11", "remaining_time": "0:48:18", "throughput": 5527.85, "total_tokens": 23281392} {"current_steps": 38190, "total_steps": 64460, "loss": 0.2195, "lr": 4.261903603678062e-06, "epoch": 11.84920881166615, "percentage": 59.25, "elapsed_time": "1:10:12", "remaining_time": "0:48:17", "throughput": 5528.04, "total_tokens": 23285424} {"current_steps": 38195, "total_steps": 64460, "loss": 0.2167, "lr": 4.260564654734956e-06, "epoch": 11.850760161340366, "percentage": 59.25, "elapsed_time": "1:10:12", "remaining_time": "0:48:17", "throughput": 5528.13, "total_tokens": 23289744} {"current_steps": 38200, "total_steps": 64460, "loss": 0.209, "lr": 4.259225760001217e-06, "epoch": 11.852311511014582, "percentage": 59.26, "elapsed_time": "1:10:13", "remaining_time": "0:48:16", "throughput": 5528.28, "total_tokens": 23293424} {"current_steps": 38205, "total_steps": 64460, "loss": 0.2128, "lr": 4.2578869195750016e-06, "epoch": 11.8538628606888, "percentage": 59.27, "elapsed_time": "1:10:13", "remaining_time": "0:48:15", "throughput": 5528.19, "total_tokens": 23295792} {"current_steps": 38210, "total_steps": 64460, "loss": 0.2473, "lr": 4.256548133554463e-06, "epoch": 11.855414210363016, "percentage": 59.28, "elapsed_time": "1:10:14", "remaining_time": "0:48:15", "throughput": 5528.3, "total_tokens": 23298928} {"current_steps": 38215, "total_steps": 64460, "loss": 0.1946, "lr": 4.25520940203775e-06, "epoch": 11.856965560037231, "percentage": 59.28, "elapsed_time": "1:10:14", "remaining_time": "0:48:14", "throughput": 5528.29, "total_tokens": 23301584} {"current_steps": 38220, "total_steps": 64460, "loss": 0.2443, "lr": 4.253870725123008e-06, "epoch": 11.85851690971145, "percentage": 59.29, "elapsed_time": "1:10:15", "remaining_time": "0:48:14", "throughput": 5528.39, "total_tokens": 23304912} {"current_steps": 38225, "total_steps": 64460, "loss": 0.2794, "lr": 4.252532102908377e-06, "epoch": 11.860068259385665, "percentage": 59.3, "elapsed_time": "1:10:16", "remaining_time": "0:48:13", "throughput": 5528.32, "total_tokens": 23307408} {"current_steps": 38230, "total_steps": 64460, "loss": 0.224, "lr": 4.251193535491993e-06, "epoch": 11.861619609059883, "percentage": 59.31, "elapsed_time": "1:10:16", "remaining_time": "0:48:12", "throughput": 5528.26, "total_tokens": 23309872} {"current_steps": 38235, "total_steps": 64460, "loss": 0.2489, "lr": 4.249855022971992e-06, "epoch": 11.863170958734099, "percentage": 59.32, "elapsed_time": "1:10:17", "remaining_time": "0:48:12", "throughput": 5528.35, "total_tokens": 23313264} {"current_steps": 38240, "total_steps": 64460, "loss": 0.2147, "lr": 4.2485165654465e-06, "epoch": 11.864722308408314, "percentage": 59.32, "elapsed_time": "1:10:17", "remaining_time": "0:48:11", "throughput": 5528.45, "total_tokens": 23316656} {"current_steps": 38245, "total_steps": 64460, "loss": 0.2011, "lr": 4.247178163013643e-06, "epoch": 11.866273658082532, "percentage": 59.33, "elapsed_time": "1:10:18", "remaining_time": "0:48:11", "throughput": 5528.51, "total_tokens": 23319664} {"current_steps": 38250, "total_steps": 64460, "loss": 0.213, "lr": 4.2458398157715405e-06, "epoch": 11.867825007756748, "percentage": 59.34, "elapsed_time": "1:10:18", "remaining_time": "0:48:10", "throughput": 5528.65, "total_tokens": 23323184} {"current_steps": 38255, "total_steps": 64460, "loss": 0.218, "lr": 4.24450152381831e-06, "epoch": 11.869376357430966, "percentage": 59.35, "elapsed_time": "1:10:19", "remaining_time": "0:48:10", "throughput": 5528.6, "total_tokens": 23325520} {"current_steps": 38260, "total_steps": 64460, "loss": 0.2155, "lr": 4.243163287252066e-06, "epoch": 11.870927707105182, "percentage": 59.35, "elapsed_time": "1:10:19", "remaining_time": "0:48:09", "throughput": 5528.6, "total_tokens": 23328496} {"current_steps": 38265, "total_steps": 64460, "loss": 0.2087, "lr": 4.241825106170914e-06, "epoch": 11.872479056779397, "percentage": 59.36, "elapsed_time": "1:10:20", "remaining_time": "0:48:08", "throughput": 5528.59, "total_tokens": 23331280} {"current_steps": 38270, "total_steps": 64460, "loss": 0.2229, "lr": 4.24048698067296e-06, "epoch": 11.874030406453615, "percentage": 59.37, "elapsed_time": "1:10:20", "remaining_time": "0:48:08", "throughput": 5528.55, "total_tokens": 23333840} {"current_steps": 38275, "total_steps": 64460, "loss": 0.2093, "lr": 4.239148910856305e-06, "epoch": 11.875581756127831, "percentage": 59.38, "elapsed_time": "1:10:21", "remaining_time": "0:48:07", "throughput": 5528.48, "total_tokens": 23336208} {"current_steps": 38280, "total_steps": 64460, "loss": 0.2424, "lr": 4.237810896819044e-06, "epoch": 11.877133105802049, "percentage": 59.39, "elapsed_time": "1:10:21", "remaining_time": "0:48:07", "throughput": 5528.42, "total_tokens": 23338480} {"current_steps": 38285, "total_steps": 64460, "loss": 0.2056, "lr": 4.23647293865927e-06, "epoch": 11.878684455476265, "percentage": 59.39, "elapsed_time": "1:10:22", "remaining_time": "0:48:06", "throughput": 5528.5, "total_tokens": 23341904} {"current_steps": 38290, "total_steps": 64460, "loss": 0.2375, "lr": 4.23513503647507e-06, "epoch": 11.88023580515048, "percentage": 59.4, "elapsed_time": "1:10:22", "remaining_time": "0:48:05", "throughput": 5528.43, "total_tokens": 23344176} {"current_steps": 38295, "total_steps": 64460, "loss": 0.2246, "lr": 4.23379719036453e-06, "epoch": 11.881787154824698, "percentage": 59.41, "elapsed_time": "1:10:23", "remaining_time": "0:48:05", "throughput": 5528.37, "total_tokens": 23346768} {"current_steps": 38300, "total_steps": 64460, "loss": 0.2471, "lr": 4.2324594004257304e-06, "epoch": 11.883338504498914, "percentage": 59.42, "elapsed_time": "1:10:23", "remaining_time": "0:48:04", "throughput": 5528.45, "total_tokens": 23349968} {"current_steps": 38305, "total_steps": 64460, "loss": 0.2308, "lr": 4.231121666756745e-06, "epoch": 11.88488985417313, "percentage": 59.42, "elapsed_time": "1:10:24", "remaining_time": "0:48:04", "throughput": 5528.38, "total_tokens": 23352400} {"current_steps": 38310, "total_steps": 64460, "loss": 0.2042, "lr": 4.229783989455646e-06, "epoch": 11.886441203847347, "percentage": 59.43, "elapsed_time": "1:10:24", "remaining_time": "0:48:03", "throughput": 5528.51, "total_tokens": 23356176} {"current_steps": 38315, "total_steps": 64460, "loss": 0.2063, "lr": 4.228446368620501e-06, "epoch": 11.887992553521563, "percentage": 59.44, "elapsed_time": "1:10:25", "remaining_time": "0:48:03", "throughput": 5528.45, "total_tokens": 23358800} {"current_steps": 38320, "total_steps": 64460, "loss": 0.2041, "lr": 4.227108804349375e-06, "epoch": 11.889543903195781, "percentage": 59.45, "elapsed_time": "1:10:25", "remaining_time": "0:48:02", "throughput": 5528.45, "total_tokens": 23361712} {"current_steps": 38325, "total_steps": 64460, "loss": 0.2552, "lr": 4.225771296740325e-06, "epoch": 11.891095252869997, "percentage": 59.46, "elapsed_time": "1:10:26", "remaining_time": "0:48:01", "throughput": 5528.4, "total_tokens": 23364048} {"current_steps": 38330, "total_steps": 64460, "loss": 0.2225, "lr": 4.224433845891407e-06, "epoch": 11.892646602544213, "percentage": 59.46, "elapsed_time": "1:10:26", "remaining_time": "0:48:01", "throughput": 5528.42, "total_tokens": 23367120} {"current_steps": 38335, "total_steps": 64460, "loss": 0.2429, "lr": 4.223096451900673e-06, "epoch": 11.89419795221843, "percentage": 59.47, "elapsed_time": "1:10:27", "remaining_time": "0:48:00", "throughput": 5528.51, "total_tokens": 23370288} {"current_steps": 38340, "total_steps": 64460, "loss": 0.2076, "lr": 4.221759114866169e-06, "epoch": 11.895749301892646, "percentage": 59.48, "elapsed_time": "1:10:27", "remaining_time": "0:48:00", "throughput": 5528.63, "total_tokens": 23374096} {"current_steps": 38345, "total_steps": 64460, "loss": 0.2634, "lr": 4.220421834885937e-06, "epoch": 11.897300651566862, "percentage": 59.49, "elapsed_time": "1:10:28", "remaining_time": "0:47:59", "throughput": 5528.86, "total_tokens": 23379984} {"current_steps": 38350, "total_steps": 64460, "loss": 0.2007, "lr": 4.219084612058015e-06, "epoch": 11.89885200124108, "percentage": 59.49, "elapsed_time": "1:10:29", "remaining_time": "0:47:59", "throughput": 5528.87, "total_tokens": 23382640} {"current_steps": 38355, "total_steps": 64460, "loss": 0.2257, "lr": 4.2177474464804394e-06, "epoch": 11.900403350915296, "percentage": 59.5, "elapsed_time": "1:10:29", "remaining_time": "0:47:58", "throughput": 5528.9, "total_tokens": 23385904} {"current_steps": 38360, "total_steps": 64460, "loss": 0.2143, "lr": 4.216410338251239e-06, "epoch": 11.901954700589513, "percentage": 59.51, "elapsed_time": "1:10:30", "remaining_time": "0:47:58", "throughput": 5528.87, "total_tokens": 23388816} {"current_steps": 38365, "total_steps": 64460, "loss": 0.2303, "lr": 4.2150732874684404e-06, "epoch": 11.90350605026373, "percentage": 59.52, "elapsed_time": "1:10:30", "remaining_time": "0:47:57", "throughput": 5528.78, "total_tokens": 23391216} {"current_steps": 38370, "total_steps": 64460, "loss": 0.2099, "lr": 4.213736294230065e-06, "epoch": 11.905057399937945, "percentage": 59.53, "elapsed_time": "1:10:31", "remaining_time": "0:47:57", "throughput": 5528.84, "total_tokens": 23394480} {"current_steps": 38375, "total_steps": 64460, "loss": 0.2296, "lr": 4.2123993586341305e-06, "epoch": 11.906608749612163, "percentage": 59.53, "elapsed_time": "1:10:31", "remaining_time": "0:47:56", "throughput": 5528.79, "total_tokens": 23396880} {"current_steps": 38380, "total_steps": 64460, "loss": 0.199, "lr": 4.211062480778649e-06, "epoch": 11.908160099286379, "percentage": 59.54, "elapsed_time": "1:10:32", "remaining_time": "0:47:55", "throughput": 5528.81, "total_tokens": 23399760} {"current_steps": 38385, "total_steps": 64460, "loss": 0.211, "lr": 4.209725660761629e-06, "epoch": 11.909711448960596, "percentage": 59.55, "elapsed_time": "1:10:32", "remaining_time": "0:47:55", "throughput": 5528.81, "total_tokens": 23402384} {"current_steps": 38390, "total_steps": 64460, "loss": 0.2202, "lr": 4.2083888986810776e-06, "epoch": 11.911262798634812, "percentage": 59.56, "elapsed_time": "1:10:33", "remaining_time": "0:47:54", "throughput": 5528.88, "total_tokens": 23405744} {"current_steps": 38395, "total_steps": 64460, "loss": 0.2098, "lr": 4.207052194634994e-06, "epoch": 11.912814148309028, "percentage": 59.56, "elapsed_time": "1:10:33", "remaining_time": "0:47:54", "throughput": 5528.85, "total_tokens": 23408368} {"current_steps": 38400, "total_steps": 64460, "loss": 0.2314, "lr": 4.205715548721374e-06, "epoch": 11.914365497983246, "percentage": 59.57, "elapsed_time": "1:10:34", "remaining_time": "0:47:53", "throughput": 5528.86, "total_tokens": 23411664} {"current_steps": 38405, "total_steps": 64460, "loss": 0.2016, "lr": 4.204378961038208e-06, "epoch": 11.915916847657462, "percentage": 59.58, "elapsed_time": "1:10:35", "remaining_time": "0:47:53", "throughput": 5528.79, "total_tokens": 23414576} {"current_steps": 38410, "total_steps": 64460, "loss": 0.2202, "lr": 4.2030424316834875e-06, "epoch": 11.91746819733168, "percentage": 59.59, "elapsed_time": "1:10:35", "remaining_time": "0:47:52", "throughput": 5528.76, "total_tokens": 23417520} {"current_steps": 38415, "total_steps": 64460, "loss": 0.2394, "lr": 4.201705960755195e-06, "epoch": 11.919019547005895, "percentage": 59.6, "elapsed_time": "1:10:36", "remaining_time": "0:47:51", "throughput": 5528.73, "total_tokens": 23419952} {"current_steps": 38420, "total_steps": 64460, "loss": 0.2087, "lr": 4.200369548351308e-06, "epoch": 11.920570896680111, "percentage": 59.6, "elapsed_time": "1:10:36", "remaining_time": "0:47:51", "throughput": 5528.85, "total_tokens": 23423376} {"current_steps": 38425, "total_steps": 64460, "loss": 0.246, "lr": 4.199033194569802e-06, "epoch": 11.922122246354329, "percentage": 59.61, "elapsed_time": "1:10:37", "remaining_time": "0:47:50", "throughput": 5528.83, "total_tokens": 23426000} {"current_steps": 38430, "total_steps": 64460, "loss": 0.2555, "lr": 4.197696899508649e-06, "epoch": 11.923673596028545, "percentage": 59.62, "elapsed_time": "1:10:37", "remaining_time": "0:47:50", "throughput": 5528.88, "total_tokens": 23429360} {"current_steps": 38435, "total_steps": 64460, "loss": 0.2125, "lr": 4.196360663265812e-06, "epoch": 11.92522494570276, "percentage": 59.63, "elapsed_time": "1:10:38", "remaining_time": "0:47:49", "throughput": 5528.85, "total_tokens": 23432016} {"current_steps": 38440, "total_steps": 64460, "loss": 0.2126, "lr": 4.195024485939256e-06, "epoch": 11.926776295376978, "percentage": 59.63, "elapsed_time": "1:10:38", "remaining_time": "0:47:49", "throughput": 5528.8, "total_tokens": 23434704} {"current_steps": 38445, "total_steps": 64460, "loss": 0.2099, "lr": 4.1936883676269365e-06, "epoch": 11.928327645051194, "percentage": 59.64, "elapsed_time": "1:10:39", "remaining_time": "0:47:48", "throughput": 5529.01, "total_tokens": 23439856} {"current_steps": 38450, "total_steps": 64460, "loss": 0.2003, "lr": 4.192352308426809e-06, "epoch": 11.929878994725412, "percentage": 59.65, "elapsed_time": "1:10:39", "remaining_time": "0:47:48", "throughput": 5529.02, "total_tokens": 23442896} {"current_steps": 38455, "total_steps": 64460, "loss": 0.2188, "lr": 4.191016308436821e-06, "epoch": 11.931430344399628, "percentage": 59.66, "elapsed_time": "1:10:40", "remaining_time": "0:47:47", "throughput": 5529.11, "total_tokens": 23446192} {"current_steps": 38460, "total_steps": 64460, "loss": 0.2111, "lr": 4.1896803677549185e-06, "epoch": 11.932981694073844, "percentage": 59.66, "elapsed_time": "1:10:40", "remaining_time": "0:47:47", "throughput": 5529.09, "total_tokens": 23448720} {"current_steps": 38465, "total_steps": 64460, "loss": 0.2263, "lr": 4.188344486479039e-06, "epoch": 11.934533043748061, "percentage": 59.67, "elapsed_time": "1:10:41", "remaining_time": "0:47:46", "throughput": 5529.21, "total_tokens": 23452208} {"current_steps": 38470, "total_steps": 64460, "loss": 0.2516, "lr": 4.187008664707121e-06, "epoch": 11.936084393422277, "percentage": 59.68, "elapsed_time": "1:10:42", "remaining_time": "0:47:45", "throughput": 5529.28, "total_tokens": 23455312} {"current_steps": 38475, "total_steps": 64460, "loss": 0.2005, "lr": 4.185672902537095e-06, "epoch": 11.937635743096495, "percentage": 59.69, "elapsed_time": "1:10:42", "remaining_time": "0:47:45", "throughput": 5529.3, "total_tokens": 23458224} {"current_steps": 38480, "total_steps": 64460, "loss": 0.2256, "lr": 4.184337200066888e-06, "epoch": 11.93918709277071, "percentage": 59.7, "elapsed_time": "1:10:43", "remaining_time": "0:47:44", "throughput": 5529.15, "total_tokens": 23460240} {"current_steps": 38485, "total_steps": 64460, "loss": 0.2033, "lr": 4.183001557394423e-06, "epoch": 11.940738442444927, "percentage": 59.7, "elapsed_time": "1:10:43", "remaining_time": "0:47:44", "throughput": 5529.07, "total_tokens": 23462576} {"current_steps": 38490, "total_steps": 64460, "loss": 0.2419, "lr": 4.181665974617619e-06, "epoch": 11.942289792119144, "percentage": 59.71, "elapsed_time": "1:10:43", "remaining_time": "0:47:43", "throughput": 5528.93, "total_tokens": 23464784} {"current_steps": 38495, "total_steps": 64460, "loss": 0.2512, "lr": 4.180330451834388e-06, "epoch": 11.94384114179336, "percentage": 59.72, "elapsed_time": "1:10:44", "remaining_time": "0:47:42", "throughput": 5528.81, "total_tokens": 23467312} {"current_steps": 38500, "total_steps": 64460, "loss": 0.228, "lr": 4.1789949891426425e-06, "epoch": 11.945392491467576, "percentage": 59.73, "elapsed_time": "1:10:45", "remaining_time": "0:47:42", "throughput": 5528.78, "total_tokens": 23469936} {"current_steps": 38505, "total_steps": 64460, "loss": 0.228, "lr": 4.177659586640287e-06, "epoch": 11.946943841141794, "percentage": 59.73, "elapsed_time": "1:10:45", "remaining_time": "0:47:41", "throughput": 5528.88, "total_tokens": 23473744} {"current_steps": 38510, "total_steps": 64460, "loss": 0.2023, "lr": 4.176324244425222e-06, "epoch": 11.94849519081601, "percentage": 59.74, "elapsed_time": "1:10:46", "remaining_time": "0:47:41", "throughput": 5528.85, "total_tokens": 23476304} {"current_steps": 38515, "total_steps": 64460, "loss": 0.2437, "lr": 4.1749889625953424e-06, "epoch": 11.950046540490227, "percentage": 59.75, "elapsed_time": "1:10:46", "remaining_time": "0:47:40", "throughput": 5528.76, "total_tokens": 23478640} {"current_steps": 38520, "total_steps": 64460, "loss": 0.2189, "lr": 4.1736537412485425e-06, "epoch": 11.951597890164443, "percentage": 59.76, "elapsed_time": "1:10:47", "remaining_time": "0:47:40", "throughput": 5528.76, "total_tokens": 23481200} {"current_steps": 38525, "total_steps": 64460, "loss": 0.2002, "lr": 4.172318580482708e-06, "epoch": 11.953149239838659, "percentage": 59.77, "elapsed_time": "1:10:47", "remaining_time": "0:47:39", "throughput": 5528.79, "total_tokens": 23484048} {"current_steps": 38530, "total_steps": 64460, "loss": 0.2374, "lr": 4.1709834803957225e-06, "epoch": 11.954700589512877, "percentage": 59.77, "elapsed_time": "1:10:48", "remaining_time": "0:47:38", "throughput": 5528.78, "total_tokens": 23486832} {"current_steps": 38535, "total_steps": 64460, "loss": 0.2229, "lr": 4.169648441085466e-06, "epoch": 11.956251939187093, "percentage": 59.78, "elapsed_time": "1:10:48", "remaining_time": "0:47:38", "throughput": 5528.72, "total_tokens": 23489200} {"current_steps": 38540, "total_steps": 64460, "loss": 0.1981, "lr": 4.168313462649811e-06, "epoch": 11.95780328886131, "percentage": 59.79, "elapsed_time": "1:10:49", "remaining_time": "0:47:37", "throughput": 5528.71, "total_tokens": 23491920} {"current_steps": 38545, "total_steps": 64460, "loss": 0.2246, "lr": 4.166978545186628e-06, "epoch": 11.959354638535526, "percentage": 59.8, "elapsed_time": "1:10:49", "remaining_time": "0:47:37", "throughput": 5528.68, "total_tokens": 23494640} {"current_steps": 38550, "total_steps": 64460, "loss": 0.2831, "lr": 4.165643688793782e-06, "epoch": 11.960905988209742, "percentage": 59.8, "elapsed_time": "1:10:50", "remaining_time": "0:47:36", "throughput": 5528.78, "total_tokens": 23498576} {"current_steps": 38555, "total_steps": 64460, "loss": 0.2249, "lr": 4.164308893569134e-06, "epoch": 11.96245733788396, "percentage": 59.81, "elapsed_time": "1:10:50", "remaining_time": "0:47:36", "throughput": 5528.8, "total_tokens": 23501552} {"current_steps": 38560, "total_steps": 64460, "loss": 0.2336, "lr": 4.1629741596105386e-06, "epoch": 11.964008687558175, "percentage": 59.82, "elapsed_time": "1:10:51", "remaining_time": "0:47:35", "throughput": 5528.8, "total_tokens": 23504176} {"current_steps": 38565, "total_steps": 64460, "loss": 0.2197, "lr": 4.161639487015851e-06, "epoch": 11.965560037232391, "percentage": 59.83, "elapsed_time": "1:10:51", "remaining_time": "0:47:34", "throughput": 5528.66, "total_tokens": 23506512} {"current_steps": 38570, "total_steps": 64460, "loss": 0.2551, "lr": 4.1603048758829164e-06, "epoch": 11.967111386906609, "percentage": 59.84, "elapsed_time": "1:10:52", "remaining_time": "0:47:34", "throughput": 5528.62, "total_tokens": 23509392} {"current_steps": 38575, "total_steps": 64460, "loss": 0.232, "lr": 4.1589703263095775e-06, "epoch": 11.968662736580825, "percentage": 59.84, "elapsed_time": "1:10:53", "remaining_time": "0:47:33", "throughput": 5528.71, "total_tokens": 23514000} {"current_steps": 38580, "total_steps": 64460, "loss": 0.2241, "lr": 4.157635838393673e-06, "epoch": 11.970214086255043, "percentage": 59.85, "elapsed_time": "1:10:53", "remaining_time": "0:47:33", "throughput": 5528.78, "total_tokens": 23517168} {"current_steps": 38585, "total_steps": 64460, "loss": 0.2173, "lr": 4.156301412233037e-06, "epoch": 11.971765435929258, "percentage": 59.86, "elapsed_time": "1:10:54", "remaining_time": "0:47:32", "throughput": 5528.77, "total_tokens": 23519984} {"current_steps": 38590, "total_steps": 64460, "loss": 0.2039, "lr": 4.154967047925499e-06, "epoch": 11.973316785603474, "percentage": 59.87, "elapsed_time": "1:10:54", "remaining_time": "0:47:32", "throughput": 5528.93, "total_tokens": 23524112} {"current_steps": 38595, "total_steps": 64460, "loss": 0.2306, "lr": 4.153632745568882e-06, "epoch": 11.974868135277692, "percentage": 59.87, "elapsed_time": "1:10:55", "remaining_time": "0:47:31", "throughput": 5529.0, "total_tokens": 23527152} {"current_steps": 38600, "total_steps": 64460, "loss": 0.2134, "lr": 4.152298505261007e-06, "epoch": 11.976419484951908, "percentage": 59.88, "elapsed_time": "1:10:55", "remaining_time": "0:47:31", "throughput": 5529.1, "total_tokens": 23530640} {"current_steps": 38605, "total_steps": 64460, "loss": 0.2557, "lr": 4.150964327099691e-06, "epoch": 11.977970834626126, "percentage": 59.89, "elapsed_time": "1:10:56", "remaining_time": "0:47:30", "throughput": 5529.16, "total_tokens": 23534160} {"current_steps": 38610, "total_steps": 64460, "loss": 0.202, "lr": 4.149630211182743e-06, "epoch": 11.979522184300341, "percentage": 59.9, "elapsed_time": "1:10:56", "remaining_time": "0:47:30", "throughput": 5529.22, "total_tokens": 23537648} {"current_steps": 38615, "total_steps": 64460, "loss": 0.2241, "lr": 4.148296157607971e-06, "epoch": 11.981073533974557, "percentage": 59.91, "elapsed_time": "1:10:57", "remaining_time": "0:47:29", "throughput": 5529.34, "total_tokens": 23540976} {"current_steps": 38620, "total_steps": 64460, "loss": 0.1964, "lr": 4.146962166473175e-06, "epoch": 11.982624883648775, "percentage": 59.91, "elapsed_time": "1:10:57", "remaining_time": "0:47:28", "throughput": 5529.36, "total_tokens": 23543632} {"current_steps": 38625, "total_steps": 64460, "loss": 0.2177, "lr": 4.145628237876154e-06, "epoch": 11.98417623332299, "percentage": 59.92, "elapsed_time": "1:10:58", "remaining_time": "0:47:28", "throughput": 5529.21, "total_tokens": 23545680} {"current_steps": 38630, "total_steps": 64460, "loss": 0.214, "lr": 4.144294371914702e-06, "epoch": 11.985727582997207, "percentage": 59.93, "elapsed_time": "1:10:59", "remaining_time": "0:47:27", "throughput": 5529.35, "total_tokens": 23550288} {"current_steps": 38635, "total_steps": 64460, "loss": 0.227, "lr": 4.142960568686605e-06, "epoch": 11.987278932671424, "percentage": 59.94, "elapsed_time": "1:10:59", "remaining_time": "0:47:27", "throughput": 5529.35, "total_tokens": 23553040} {"current_steps": 38640, "total_steps": 64460, "loss": 0.225, "lr": 4.141626828289647e-06, "epoch": 11.98883028234564, "percentage": 59.94, "elapsed_time": "1:11:00", "remaining_time": "0:47:26", "throughput": 5529.29, "total_tokens": 23555376} {"current_steps": 38645, "total_steps": 64460, "loss": 0.2036, "lr": 4.140293150821607e-06, "epoch": 11.990381632019858, "percentage": 59.95, "elapsed_time": "1:11:00", "remaining_time": "0:47:26", "throughput": 5529.46, "total_tokens": 23559568} {"current_steps": 38650, "total_steps": 64460, "loss": 0.1837, "lr": 4.13895953638026e-06, "epoch": 11.991932981694074, "percentage": 59.96, "elapsed_time": "1:11:01", "remaining_time": "0:47:25", "throughput": 5529.45, "total_tokens": 23562288} {"current_steps": 38655, "total_steps": 64460, "loss": 0.2193, "lr": 4.137625985063374e-06, "epoch": 11.99348433136829, "percentage": 59.97, "elapsed_time": "1:11:01", "remaining_time": "0:47:25", "throughput": 5529.48, "total_tokens": 23565040} {"current_steps": 38660, "total_steps": 64460, "loss": 0.2453, "lr": 4.136292496968716e-06, "epoch": 11.995035681042507, "percentage": 59.98, "elapsed_time": "1:11:02", "remaining_time": "0:47:24", "throughput": 5529.45, "total_tokens": 23567504} {"current_steps": 38665, "total_steps": 64460, "loss": 0.2091, "lr": 4.134959072194047e-06, "epoch": 11.996587030716723, "percentage": 59.98, "elapsed_time": "1:11:02", "remaining_time": "0:47:23", "throughput": 5529.41, "total_tokens": 23569968} {"current_steps": 38670, "total_steps": 64460, "loss": 0.2238, "lr": 4.13362571083712e-06, "epoch": 11.998138380390941, "percentage": 59.99, "elapsed_time": "1:11:03", "remaining_time": "0:47:23", "throughput": 5529.28, "total_tokens": 23571984} {"current_steps": 38675, "total_steps": 64460, "loss": 0.1983, "lr": 4.132292412995688e-06, "epoch": 11.999689730065157, "percentage": 60.0, "elapsed_time": "1:11:03", "remaining_time": "0:47:22", "throughput": 5529.31, "total_tokens": 23574704} {"current_steps": 38676, "total_steps": 64460, "eval_loss": 0.24983832240104675, "epoch": 12.0, "percentage": 60.0, "elapsed_time": "1:11:38", "remaining_time": "0:47:45", "throughput": 5484.93, "total_tokens": 23574992} {"current_steps": 38680, "total_steps": 64460, "loss": 0.2425, "lr": 4.130959178767497e-06, "epoch": 12.001241079739373, "percentage": 60.01, "elapsed_time": "1:11:42", "remaining_time": "0:47:47", "throughput": 5480.16, "total_tokens": 23579472} {"current_steps": 38685, "total_steps": 64460, "loss": 0.2026, "lr": 4.1296260082502895e-06, "epoch": 12.00279242941359, "percentage": 60.01, "elapsed_time": "1:11:43", "remaining_time": "0:47:47", "throughput": 5480.22, "total_tokens": 23582512} {"current_steps": 38690, "total_steps": 64460, "loss": 0.2309, "lr": 4.128292901541802e-06, "epoch": 12.004343779087806, "percentage": 60.02, "elapsed_time": "1:11:43", "remaining_time": "0:47:46", "throughput": 5480.29, "total_tokens": 23585680} {"current_steps": 38695, "total_steps": 64460, "loss": 0.1927, "lr": 4.126959858739769e-06, "epoch": 12.005895128762022, "percentage": 60.03, "elapsed_time": "1:11:44", "remaining_time": "0:47:46", "throughput": 5480.41, "total_tokens": 23589296} {"current_steps": 38700, "total_steps": 64460, "loss": 0.2008, "lr": 4.125626879941916e-06, "epoch": 12.00744647843624, "percentage": 60.04, "elapsed_time": "1:11:44", "remaining_time": "0:47:45", "throughput": 5480.42, "total_tokens": 23591856} {"current_steps": 38705, "total_steps": 64460, "loss": 0.2444, "lr": 4.124293965245967e-06, "epoch": 12.008997828110456, "percentage": 60.04, "elapsed_time": "1:11:45", "remaining_time": "0:47:44", "throughput": 5480.46, "total_tokens": 23594928} {"current_steps": 38710, "total_steps": 64460, "loss": 0.2639, "lr": 4.12296111474964e-06, "epoch": 12.010549177784673, "percentage": 60.05, "elapsed_time": "1:11:45", "remaining_time": "0:47:44", "throughput": 5480.43, "total_tokens": 23597776} {"current_steps": 38715, "total_steps": 64460, "loss": 0.2069, "lr": 4.121628328550648e-06, "epoch": 12.01210052745889, "percentage": 60.06, "elapsed_time": "1:11:46", "remaining_time": "0:47:43", "throughput": 5480.38, "total_tokens": 23600112} {"current_steps": 38720, "total_steps": 64460, "loss": 0.2025, "lr": 4.1202956067467024e-06, "epoch": 12.013651877133105, "percentage": 60.07, "elapsed_time": "1:11:46", "remaining_time": "0:47:43", "throughput": 5480.34, "total_tokens": 23602768} {"current_steps": 38725, "total_steps": 64460, "loss": 0.2092, "lr": 4.118962949435505e-06, "epoch": 12.015203226807323, "percentage": 60.08, "elapsed_time": "1:11:47", "remaining_time": "0:47:42", "throughput": 5480.42, "total_tokens": 23605968} {"current_steps": 38730, "total_steps": 64460, "loss": 0.2196, "lr": 4.1176303567147575e-06, "epoch": 12.016754576481539, "percentage": 60.08, "elapsed_time": "1:11:47", "remaining_time": "0:47:41", "throughput": 5480.37, "total_tokens": 23608688} {"current_steps": 38735, "total_steps": 64460, "loss": 0.1943, "lr": 4.116297828682153e-06, "epoch": 12.018305926155756, "percentage": 60.09, "elapsed_time": "1:11:48", "remaining_time": "0:47:41", "throughput": 5480.39, "total_tokens": 23611856} {"current_steps": 38740, "total_steps": 64460, "loss": 0.1758, "lr": 4.114965365435382e-06, "epoch": 12.019857275829972, "percentage": 60.1, "elapsed_time": "1:11:48", "remaining_time": "0:47:40", "throughput": 5480.47, "total_tokens": 23614864} {"current_steps": 38745, "total_steps": 64460, "loss": 0.2293, "lr": 4.11363296707213e-06, "epoch": 12.021408625504188, "percentage": 60.11, "elapsed_time": "1:11:49", "remaining_time": "0:47:40", "throughput": 5480.43, "total_tokens": 23617168} {"current_steps": 38750, "total_steps": 64460, "loss": 0.2212, "lr": 4.112300633690078e-06, "epoch": 12.022959975178406, "percentage": 60.11, "elapsed_time": "1:11:49", "remaining_time": "0:47:39", "throughput": 5480.46, "total_tokens": 23620176} {"current_steps": 38755, "total_steps": 64460, "loss": 0.178, "lr": 4.110968365386902e-06, "epoch": 12.024511324852622, "percentage": 60.12, "elapsed_time": "1:11:50", "remaining_time": "0:47:38", "throughput": 5480.61, "total_tokens": 23623920} {"current_steps": 38760, "total_steps": 64460, "loss": 0.2114, "lr": 4.109636162260272e-06, "epoch": 12.026062674526838, "percentage": 60.13, "elapsed_time": "1:11:51", "remaining_time": "0:47:38", "throughput": 5480.79, "total_tokens": 23627984} {"current_steps": 38765, "total_steps": 64460, "loss": 0.2007, "lr": 4.108304024407855e-06, "epoch": 12.027614024201055, "percentage": 60.14, "elapsed_time": "1:11:51", "remaining_time": "0:47:37", "throughput": 5480.85, "total_tokens": 23631312} {"current_steps": 38770, "total_steps": 64460, "loss": 0.2191, "lr": 4.1069719519273124e-06, "epoch": 12.029165373875271, "percentage": 60.15, "elapsed_time": "1:11:52", "remaining_time": "0:47:37", "throughput": 5480.84, "total_tokens": 23633904} {"current_steps": 38775, "total_steps": 64460, "loss": 0.23, "lr": 4.105639944916301e-06, "epoch": 12.030716723549489, "percentage": 60.15, "elapsed_time": "1:11:52", "remaining_time": "0:47:36", "throughput": 5480.82, "total_tokens": 23636752} {"current_steps": 38780, "total_steps": 64460, "loss": 0.2617, "lr": 4.104308003472472e-06, "epoch": 12.032268073223705, "percentage": 60.16, "elapsed_time": "1:11:53", "remaining_time": "0:47:36", "throughput": 5480.88, "total_tokens": 23639984} {"current_steps": 38785, "total_steps": 64460, "loss": 0.1906, "lr": 4.1029761276934725e-06, "epoch": 12.03381942289792, "percentage": 60.17, "elapsed_time": "1:11:53", "remaining_time": "0:47:35", "throughput": 5480.82, "total_tokens": 23642512} {"current_steps": 38790, "total_steps": 64460, "loss": 0.2048, "lr": 4.101644317676946e-06, "epoch": 12.035370772572138, "percentage": 60.18, "elapsed_time": "1:11:54", "remaining_time": "0:47:35", "throughput": 5480.9, "total_tokens": 23645776} {"current_steps": 38795, "total_steps": 64460, "loss": 0.2402, "lr": 4.100312573520529e-06, "epoch": 12.036922122246354, "percentage": 60.18, "elapsed_time": "1:11:54", "remaining_time": "0:47:34", "throughput": 5480.97, "total_tokens": 23648944} {"current_steps": 38800, "total_steps": 64460, "loss": 0.2277, "lr": 4.098980895321853e-06, "epoch": 12.038473471920572, "percentage": 60.19, "elapsed_time": "1:11:55", "remaining_time": "0:47:33", "throughput": 5480.98, "total_tokens": 23651760} {"current_steps": 38805, "total_steps": 64460, "loss": 0.2121, "lr": 4.097649283178548e-06, "epoch": 12.040024821594788, "percentage": 60.2, "elapsed_time": "1:11:55", "remaining_time": "0:47:33", "throughput": 5481.14, "total_tokens": 23656080} {"current_steps": 38810, "total_steps": 64460, "loss": 0.2243, "lr": 4.0963177371882365e-06, "epoch": 12.041576171269003, "percentage": 60.21, "elapsed_time": "1:11:56", "remaining_time": "0:47:32", "throughput": 5481.24, "total_tokens": 23659536} {"current_steps": 38815, "total_steps": 64460, "loss": 0.2272, "lr": 4.0949862574485355e-06, "epoch": 12.043127520943221, "percentage": 60.22, "elapsed_time": "1:11:56", "remaining_time": "0:47:32", "throughput": 5481.24, "total_tokens": 23662160} {"current_steps": 38820, "total_steps": 64460, "loss": 0.2219, "lr": 4.093654844057059e-06, "epoch": 12.044678870617437, "percentage": 60.22, "elapsed_time": "1:11:57", "remaining_time": "0:47:31", "throughput": 5481.29, "total_tokens": 23665008} {"current_steps": 38825, "total_steps": 64460, "loss": 0.1608, "lr": 4.092323497111414e-06, "epoch": 12.046230220291653, "percentage": 60.23, "elapsed_time": "1:11:58", "remaining_time": "0:47:31", "throughput": 5481.42, "total_tokens": 23668816} {"current_steps": 38830, "total_steps": 64460, "loss": 0.257, "lr": 4.090992216709207e-06, "epoch": 12.04778156996587, "percentage": 60.24, "elapsed_time": "1:11:58", "remaining_time": "0:47:30", "throughput": 5481.39, "total_tokens": 23671312} {"current_steps": 38835, "total_steps": 64460, "loss": 0.2388, "lr": 4.089661002948035e-06, "epoch": 12.049332919640086, "percentage": 60.25, "elapsed_time": "1:11:59", "remaining_time": "0:47:29", "throughput": 5481.53, "total_tokens": 23675216} {"current_steps": 38840, "total_steps": 64460, "loss": 0.2219, "lr": 4.08832985592549e-06, "epoch": 12.050884269314304, "percentage": 60.25, "elapsed_time": "1:11:59", "remaining_time": "0:47:29", "throughput": 5481.51, "total_tokens": 23677776} {"current_steps": 38845, "total_steps": 64460, "loss": 0.2514, "lr": 4.086998775739163e-06, "epoch": 12.05243561898852, "percentage": 60.26, "elapsed_time": "1:12:00", "remaining_time": "0:47:28", "throughput": 5481.36, "total_tokens": 23680304} {"current_steps": 38850, "total_steps": 64460, "loss": 0.1961, "lr": 4.085667762486637e-06, "epoch": 12.053986968662736, "percentage": 60.27, "elapsed_time": "1:12:00", "remaining_time": "0:47:28", "throughput": 5481.39, "total_tokens": 23683664} {"current_steps": 38855, "total_steps": 64460, "loss": 0.2318, "lr": 4.084336816265492e-06, "epoch": 12.055538318336954, "percentage": 60.28, "elapsed_time": "1:12:01", "remaining_time": "0:47:27", "throughput": 5481.46, "total_tokens": 23686800} {"current_steps": 38860, "total_steps": 64460, "loss": 0.2091, "lr": 4.083005937173299e-06, "epoch": 12.05708966801117, "percentage": 60.29, "elapsed_time": "1:12:01", "remaining_time": "0:47:27", "throughput": 5481.71, "total_tokens": 23691664} {"current_steps": 38865, "total_steps": 64460, "loss": 0.2467, "lr": 4.081675125307632e-06, "epoch": 12.058641017685387, "percentage": 60.29, "elapsed_time": "1:12:02", "remaining_time": "0:47:26", "throughput": 5481.74, "total_tokens": 23694608} {"current_steps": 38870, "total_steps": 64460, "loss": 0.2296, "lr": 4.0803443807660525e-06, "epoch": 12.060192367359603, "percentage": 60.3, "elapsed_time": "1:12:02", "remaining_time": "0:47:26", "throughput": 5481.75, "total_tokens": 23697424} {"current_steps": 38875, "total_steps": 64460, "loss": 0.1963, "lr": 4.079013703646121e-06, "epoch": 12.061743717033819, "percentage": 60.31, "elapsed_time": "1:12:03", "remaining_time": "0:47:25", "throughput": 5481.71, "total_tokens": 23699856} {"current_steps": 38880, "total_steps": 64460, "loss": 0.2274, "lr": 4.077683094045389e-06, "epoch": 12.063295066708037, "percentage": 60.32, "elapsed_time": "1:12:04", "remaining_time": "0:47:24", "throughput": 5481.82, "total_tokens": 23703472} {"current_steps": 38885, "total_steps": 64460, "loss": 0.1803, "lr": 4.07635255206141e-06, "epoch": 12.064846416382252, "percentage": 60.32, "elapsed_time": "1:12:04", "remaining_time": "0:47:24", "throughput": 5481.95, "total_tokens": 23707024} {"current_steps": 38890, "total_steps": 64460, "loss": 0.1906, "lr": 4.075022077791726e-06, "epoch": 12.066397766056468, "percentage": 60.33, "elapsed_time": "1:12:05", "remaining_time": "0:47:23", "throughput": 5481.96, "total_tokens": 23709904} {"current_steps": 38895, "total_steps": 64460, "loss": 0.2097, "lr": 4.073691671333877e-06, "epoch": 12.067949115730686, "percentage": 60.34, "elapsed_time": "1:12:05", "remaining_time": "0:47:23", "throughput": 5481.95, "total_tokens": 23712752} {"current_steps": 38900, "total_steps": 64460, "loss": 0.1888, "lr": 4.072361332785398e-06, "epoch": 12.069500465404902, "percentage": 60.35, "elapsed_time": "1:12:06", "remaining_time": "0:47:22", "throughput": 5482.08, "total_tokens": 23716208} {"current_steps": 38905, "total_steps": 64460, "loss": 0.2203, "lr": 4.0710310622438175e-06, "epoch": 12.07105181507912, "percentage": 60.36, "elapsed_time": "1:12:06", "remaining_time": "0:47:21", "throughput": 5481.98, "total_tokens": 23718288} {"current_steps": 38910, "total_steps": 64460, "loss": 0.2135, "lr": 4.069700859806661e-06, "epoch": 12.072603164753335, "percentage": 60.36, "elapsed_time": "1:12:07", "remaining_time": "0:47:21", "throughput": 5482.02, "total_tokens": 23721136} {"current_steps": 38915, "total_steps": 64460, "loss": 0.2355, "lr": 4.0683707255714485e-06, "epoch": 12.074154514427551, "percentage": 60.37, "elapsed_time": "1:12:07", "remaining_time": "0:47:20", "throughput": 5481.98, "total_tokens": 23723664} {"current_steps": 38920, "total_steps": 64460, "loss": 0.1901, "lr": 4.067040659635693e-06, "epoch": 12.075705864101769, "percentage": 60.38, "elapsed_time": "1:12:08", "remaining_time": "0:47:20", "throughput": 5481.98, "total_tokens": 23726352} {"current_steps": 38925, "total_steps": 64460, "loss": 0.2489, "lr": 4.065710662096905e-06, "epoch": 12.077257213775985, "percentage": 60.39, "elapsed_time": "1:12:08", "remaining_time": "0:47:19", "throughput": 5482.03, "total_tokens": 23729264} {"current_steps": 38930, "total_steps": 64460, "loss": 0.2688, "lr": 4.06438073305259e-06, "epoch": 12.078808563450202, "percentage": 60.39, "elapsed_time": "1:12:09", "remaining_time": "0:47:18", "throughput": 5482.02, "total_tokens": 23731984} {"current_steps": 38935, "total_steps": 64460, "loss": 0.1965, "lr": 4.063050872600246e-06, "epoch": 12.080359913124418, "percentage": 60.4, "elapsed_time": "1:12:09", "remaining_time": "0:47:18", "throughput": 5481.96, "total_tokens": 23734544} {"current_steps": 38940, "total_steps": 64460, "loss": 0.2083, "lr": 4.061721080837369e-06, "epoch": 12.081911262798634, "percentage": 60.41, "elapsed_time": "1:12:10", "remaining_time": "0:47:17", "throughput": 5482.0, "total_tokens": 23737648} {"current_steps": 38945, "total_steps": 64460, "loss": 0.229, "lr": 4.060391357861447e-06, "epoch": 12.083462612472852, "percentage": 60.42, "elapsed_time": "1:12:10", "remaining_time": "0:47:17", "throughput": 5482.04, "total_tokens": 23740400} {"current_steps": 38950, "total_steps": 64460, "loss": 0.2006, "lr": 4.059061703769965e-06, "epoch": 12.085013962147068, "percentage": 60.43, "elapsed_time": "1:12:11", "remaining_time": "0:47:16", "throughput": 5482.17, "total_tokens": 23744208} {"current_steps": 38955, "total_steps": 64460, "loss": 0.241, "lr": 4.057732118660403e-06, "epoch": 12.086565311821284, "percentage": 60.43, "elapsed_time": "1:12:11", "remaining_time": "0:47:16", "throughput": 5482.15, "total_tokens": 23746928} {"current_steps": 38960, "total_steps": 64460, "loss": 0.2141, "lr": 4.056402602630235e-06, "epoch": 12.088116661495501, "percentage": 60.44, "elapsed_time": "1:12:12", "remaining_time": "0:47:15", "throughput": 5482.13, "total_tokens": 23749584} {"current_steps": 38965, "total_steps": 64460, "loss": 0.2405, "lr": 4.055073155776929e-06, "epoch": 12.089668011169717, "percentage": 60.45, "elapsed_time": "1:12:12", "remaining_time": "0:47:14", "throughput": 5482.09, "total_tokens": 23752240} {"current_steps": 38970, "total_steps": 64460, "loss": 0.179, "lr": 4.053743778197951e-06, "epoch": 12.091219360843935, "percentage": 60.46, "elapsed_time": "1:12:13", "remaining_time": "0:47:14", "throughput": 5482.18, "total_tokens": 23755312} {"current_steps": 38975, "total_steps": 64460, "loss": 0.2056, "lr": 4.0524144699907594e-06, "epoch": 12.09277071051815, "percentage": 60.46, "elapsed_time": "1:12:13", "remaining_time": "0:47:13", "throughput": 5482.08, "total_tokens": 23757648} {"current_steps": 38980, "total_steps": 64460, "loss": 0.1978, "lr": 4.051085231252806e-06, "epoch": 12.094322060192367, "percentage": 60.47, "elapsed_time": "1:12:14", "remaining_time": "0:47:13", "throughput": 5482.09, "total_tokens": 23760656} {"current_steps": 38985, "total_steps": 64460, "loss": 0.2016, "lr": 4.049756062081544e-06, "epoch": 12.095873409866584, "percentage": 60.48, "elapsed_time": "1:12:14", "remaining_time": "0:47:12", "throughput": 5482.02, "total_tokens": 23762928} {"current_steps": 38990, "total_steps": 64460, "loss": 0.2519, "lr": 4.048426962574416e-06, "epoch": 12.0974247595408, "percentage": 60.49, "elapsed_time": "1:12:15", "remaining_time": "0:47:11", "throughput": 5482.01, "total_tokens": 23765520} {"current_steps": 38995, "total_steps": 64460, "loss": 0.2087, "lr": 4.047097932828859e-06, "epoch": 12.098976109215018, "percentage": 60.49, "elapsed_time": "1:12:15", "remaining_time": "0:47:11", "throughput": 5482.05, "total_tokens": 23768432} {"current_steps": 39000, "total_steps": 64460, "loss": 0.2193, "lr": 4.045768972942308e-06, "epoch": 12.100527458889234, "percentage": 60.5, "elapsed_time": "1:12:16", "remaining_time": "0:47:10", "throughput": 5482.06, "total_tokens": 23771408} {"current_steps": 39005, "total_steps": 64460, "loss": 0.19, "lr": 4.04444008301219e-06, "epoch": 12.10207880856345, "percentage": 60.51, "elapsed_time": "1:12:16", "remaining_time": "0:47:10", "throughput": 5482.2, "total_tokens": 23775792} {"current_steps": 39010, "total_steps": 64460, "loss": 0.227, "lr": 4.04311126313593e-06, "epoch": 12.103630158237667, "percentage": 60.52, "elapsed_time": "1:12:17", "remaining_time": "0:47:09", "throughput": 5482.26, "total_tokens": 23778832} {"current_steps": 39015, "total_steps": 64460, "loss": 0.2109, "lr": 4.041782513410946e-06, "epoch": 12.105181507911883, "percentage": 60.53, "elapsed_time": "1:12:17", "remaining_time": "0:47:09", "throughput": 5482.34, "total_tokens": 23782192} {"current_steps": 39020, "total_steps": 64460, "loss": 0.2601, "lr": 4.040453833934651e-06, "epoch": 12.106732857586099, "percentage": 60.53, "elapsed_time": "1:12:18", "remaining_time": "0:47:08", "throughput": 5482.45, "total_tokens": 23785904} {"current_steps": 39025, "total_steps": 64460, "loss": 0.2099, "lr": 4.039125224804453e-06, "epoch": 12.108284207260317, "percentage": 60.54, "elapsed_time": "1:12:19", "remaining_time": "0:47:08", "throughput": 5482.43, "total_tokens": 23788752} {"current_steps": 39030, "total_steps": 64460, "loss": 0.2003, "lr": 4.037796686117753e-06, "epoch": 12.109835556934533, "percentage": 60.55, "elapsed_time": "1:12:19", "remaining_time": "0:47:07", "throughput": 5482.44, "total_tokens": 23791440} {"current_steps": 39035, "total_steps": 64460, "loss": 0.2181, "lr": 4.036468217971951e-06, "epoch": 12.11138690660875, "percentage": 60.56, "elapsed_time": "1:12:20", "remaining_time": "0:47:06", "throughput": 5482.43, "total_tokens": 23794192} {"current_steps": 39040, "total_steps": 64460, "loss": 0.2225, "lr": 4.03513982046444e-06, "epoch": 12.112938256282966, "percentage": 60.56, "elapsed_time": "1:12:20", "remaining_time": "0:47:06", "throughput": 5482.29, "total_tokens": 23796432} {"current_steps": 39045, "total_steps": 64460, "loss": 0.2193, "lr": 4.033811493692604e-06, "epoch": 12.114489605957182, "percentage": 60.57, "elapsed_time": "1:12:21", "remaining_time": "0:47:05", "throughput": 5482.41, "total_tokens": 23800304} {"current_steps": 39050, "total_steps": 64460, "loss": 0.2087, "lr": 4.032483237753827e-06, "epoch": 12.1160409556314, "percentage": 60.58, "elapsed_time": "1:12:21", "remaining_time": "0:47:05", "throughput": 5482.41, "total_tokens": 23803280} {"current_steps": 39055, "total_steps": 64460, "loss": 0.2281, "lr": 4.031155052745487e-06, "epoch": 12.117592305305616, "percentage": 60.59, "elapsed_time": "1:12:22", "remaining_time": "0:47:04", "throughput": 5482.3, "total_tokens": 23805360} {"current_steps": 39060, "total_steps": 64460, "loss": 0.2244, "lr": 4.029826938764954e-06, "epoch": 12.119143654979833, "percentage": 60.6, "elapsed_time": "1:12:22", "remaining_time": "0:47:03", "throughput": 5482.34, "total_tokens": 23808272} {"current_steps": 39065, "total_steps": 64460, "loss": 0.2795, "lr": 4.028498895909593e-06, "epoch": 12.12069500465405, "percentage": 60.6, "elapsed_time": "1:12:23", "remaining_time": "0:47:03", "throughput": 5482.34, "total_tokens": 23811024} {"current_steps": 39070, "total_steps": 64460, "loss": 0.2214, "lr": 4.027170924276769e-06, "epoch": 12.122246354328265, "percentage": 60.61, "elapsed_time": "1:12:23", "remaining_time": "0:47:02", "throughput": 5482.34, "total_tokens": 23813744} {"current_steps": 39075, "total_steps": 64460, "loss": 0.1973, "lr": 4.025843023963836e-06, "epoch": 12.123797704002483, "percentage": 60.62, "elapsed_time": "1:12:24", "remaining_time": "0:47:02", "throughput": 5482.34, "total_tokens": 23816368} {"current_steps": 39080, "total_steps": 64460, "loss": 0.2348, "lr": 4.024515195068145e-06, "epoch": 12.125349053676699, "percentage": 60.63, "elapsed_time": "1:12:24", "remaining_time": "0:47:01", "throughput": 5482.22, "total_tokens": 23818416} {"current_steps": 39085, "total_steps": 64460, "loss": 0.2035, "lr": 4.023187437687042e-06, "epoch": 12.126900403350914, "percentage": 60.63, "elapsed_time": "1:12:25", "remaining_time": "0:47:00", "throughput": 5482.22, "total_tokens": 23821040} {"current_steps": 39090, "total_steps": 64460, "loss": 0.2161, "lr": 4.021859751917867e-06, "epoch": 12.128451753025132, "percentage": 60.64, "elapsed_time": "1:12:25", "remaining_time": "0:47:00", "throughput": 5482.14, "total_tokens": 23823248} {"current_steps": 39095, "total_steps": 64460, "loss": 0.2669, "lr": 4.0205321378579545e-06, "epoch": 12.130003102699348, "percentage": 60.65, "elapsed_time": "1:12:26", "remaining_time": "0:46:59", "throughput": 5482.21, "total_tokens": 23826416} {"current_steps": 39100, "total_steps": 64460, "loss": 0.2115, "lr": 4.019204595604635e-06, "epoch": 12.131554452373566, "percentage": 60.66, "elapsed_time": "1:12:26", "remaining_time": "0:46:59", "throughput": 5482.44, "total_tokens": 23831472} {"current_steps": 39105, "total_steps": 64460, "loss": 0.1943, "lr": 4.017877125255234e-06, "epoch": 12.133105802047782, "percentage": 60.67, "elapsed_time": "1:12:27", "remaining_time": "0:46:58", "throughput": 5482.48, "total_tokens": 23834320} {"current_steps": 39110, "total_steps": 64460, "loss": 0.2114, "lr": 4.0165497269070695e-06, "epoch": 12.134657151721997, "percentage": 60.67, "elapsed_time": "1:12:27", "remaining_time": "0:46:58", "throughput": 5482.53, "total_tokens": 23837488} {"current_steps": 39115, "total_steps": 64460, "loss": 0.236, "lr": 4.015222400657455e-06, "epoch": 12.136208501396215, "percentage": 60.68, "elapsed_time": "1:12:28", "remaining_time": "0:46:57", "throughput": 5482.58, "total_tokens": 23840368} {"current_steps": 39120, "total_steps": 64460, "loss": 0.2553, "lr": 4.0138951466037005e-06, "epoch": 12.137759851070431, "percentage": 60.69, "elapsed_time": "1:12:28", "remaining_time": "0:46:57", "throughput": 5482.63, "total_tokens": 23843408} {"current_steps": 39125, "total_steps": 64460, "loss": 0.1912, "lr": 4.012567964843108e-06, "epoch": 12.139311200744649, "percentage": 60.7, "elapsed_time": "1:12:29", "remaining_time": "0:46:56", "throughput": 5482.66, "total_tokens": 23846544} {"current_steps": 39130, "total_steps": 64460, "loss": 0.2062, "lr": 4.011240855472978e-06, "epoch": 12.140862550418865, "percentage": 60.7, "elapsed_time": "1:12:29", "remaining_time": "0:46:55", "throughput": 5482.69, "total_tokens": 23849488} {"current_steps": 39135, "total_steps": 64460, "loss": 0.2155, "lr": 4.009913818590602e-06, "epoch": 12.14241390009308, "percentage": 60.71, "elapsed_time": "1:12:30", "remaining_time": "0:46:55", "throughput": 5482.67, "total_tokens": 23852240} {"current_steps": 39140, "total_steps": 64460, "loss": 0.2092, "lr": 4.0085868542932665e-06, "epoch": 12.143965249767298, "percentage": 60.72, "elapsed_time": "1:12:31", "remaining_time": "0:46:54", "throughput": 5482.79, "total_tokens": 23856144} {"current_steps": 39145, "total_steps": 64460, "loss": 0.2061, "lr": 4.007259962678256e-06, "epoch": 12.145516599441514, "percentage": 60.73, "elapsed_time": "1:12:31", "remaining_time": "0:46:54", "throughput": 5482.84, "total_tokens": 23859632} {"current_steps": 39150, "total_steps": 64460, "loss": 0.1978, "lr": 4.005933143842845e-06, "epoch": 12.14706794911573, "percentage": 60.74, "elapsed_time": "1:12:32", "remaining_time": "0:46:53", "throughput": 5482.87, "total_tokens": 23862448} {"current_steps": 39155, "total_steps": 64460, "loss": 0.2262, "lr": 4.004606397884306e-06, "epoch": 12.148619298789948, "percentage": 60.74, "elapsed_time": "1:12:32", "remaining_time": "0:46:53", "throughput": 5482.88, "total_tokens": 23865200} {"current_steps": 39160, "total_steps": 64460, "loss": 0.2543, "lr": 4.003279724899906e-06, "epoch": 12.150170648464163, "percentage": 60.75, "elapsed_time": "1:12:33", "remaining_time": "0:46:52", "throughput": 5482.93, "total_tokens": 23868240} {"current_steps": 39165, "total_steps": 64460, "loss": 0.2131, "lr": 4.001953124986904e-06, "epoch": 12.151721998138381, "percentage": 60.76, "elapsed_time": "1:12:33", "remaining_time": "0:46:51", "throughput": 5482.94, "total_tokens": 23870864} {"current_steps": 39170, "total_steps": 64460, "loss": 0.193, "lr": 4.000626598242558e-06, "epoch": 12.153273347812597, "percentage": 60.77, "elapsed_time": "1:12:34", "remaining_time": "0:46:51", "throughput": 5483.16, "total_tokens": 23875376} {"current_steps": 39175, "total_steps": 64460, "loss": 0.2528, "lr": 3.999300144764116e-06, "epoch": 12.154824697486813, "percentage": 60.77, "elapsed_time": "1:12:34", "remaining_time": "0:46:50", "throughput": 5483.2, "total_tokens": 23878192} {"current_steps": 39180, "total_steps": 64460, "loss": 0.224, "lr": 3.997973764648823e-06, "epoch": 12.15637604716103, "percentage": 60.78, "elapsed_time": "1:12:35", "remaining_time": "0:46:50", "throughput": 5483.16, "total_tokens": 23880656} {"current_steps": 39185, "total_steps": 64460, "loss": 0.1943, "lr": 3.996647457993918e-06, "epoch": 12.157927396835246, "percentage": 60.79, "elapsed_time": "1:12:35", "remaining_time": "0:46:49", "throughput": 5483.12, "total_tokens": 23883280} {"current_steps": 39190, "total_steps": 64460, "loss": 0.1783, "lr": 3.995321224896637e-06, "epoch": 12.159478746509464, "percentage": 60.8, "elapsed_time": "1:12:36", "remaining_time": "0:46:49", "throughput": 5483.19, "total_tokens": 23886768} {"current_steps": 39195, "total_steps": 64460, "loss": 0.1907, "lr": 3.9939950654542074e-06, "epoch": 12.16103009618368, "percentage": 60.81, "elapsed_time": "1:12:36", "remaining_time": "0:46:48", "throughput": 5483.3, "total_tokens": 23890192} {"current_steps": 39200, "total_steps": 64460, "loss": 0.1993, "lr": 3.992668979763853e-06, "epoch": 12.162581445857896, "percentage": 60.81, "elapsed_time": "1:12:37", "remaining_time": "0:46:47", "throughput": 5483.43, "total_tokens": 23894096} {"current_steps": 39205, "total_steps": 64460, "loss": 0.1886, "lr": 3.99134296792279e-06, "epoch": 12.164132795532113, "percentage": 60.82, "elapsed_time": "1:12:38", "remaining_time": "0:46:47", "throughput": 5483.54, "total_tokens": 23897424} {"current_steps": 39210, "total_steps": 64460, "loss": 0.2239, "lr": 3.990017030028232e-06, "epoch": 12.16568414520633, "percentage": 60.83, "elapsed_time": "1:12:38", "remaining_time": "0:46:46", "throughput": 5483.62, "total_tokens": 23901200} {"current_steps": 39215, "total_steps": 64460, "loss": 0.2367, "lr": 3.9886911661773864e-06, "epoch": 12.167235494880545, "percentage": 60.84, "elapsed_time": "1:12:39", "remaining_time": "0:46:46", "throughput": 5483.61, "total_tokens": 23903760} {"current_steps": 39220, "total_steps": 64460, "loss": 0.236, "lr": 3.987365376467453e-06, "epoch": 12.168786844554763, "percentage": 60.84, "elapsed_time": "1:12:39", "remaining_time": "0:46:45", "throughput": 5483.63, "total_tokens": 23906864} {"current_steps": 39225, "total_steps": 64460, "loss": 0.2122, "lr": 3.9860396609956295e-06, "epoch": 12.170338194228979, "percentage": 60.85, "elapsed_time": "1:12:40", "remaining_time": "0:46:45", "throughput": 5483.58, "total_tokens": 23909264} {"current_steps": 39230, "total_steps": 64460, "loss": 0.1807, "lr": 3.984714019859105e-06, "epoch": 12.171889543903196, "percentage": 60.86, "elapsed_time": "1:12:40", "remaining_time": "0:46:44", "throughput": 5483.63, "total_tokens": 23912432} {"current_steps": 39235, "total_steps": 64460, "loss": 0.2595, "lr": 3.983388453155067e-06, "epoch": 12.173440893577412, "percentage": 60.87, "elapsed_time": "1:12:41", "remaining_time": "0:46:43", "throughput": 5483.67, "total_tokens": 23915408} {"current_steps": 39240, "total_steps": 64460, "loss": 0.232, "lr": 3.982062960980693e-06, "epoch": 12.174992243251628, "percentage": 60.87, "elapsed_time": "1:12:41", "remaining_time": "0:46:43", "throughput": 5483.65, "total_tokens": 23917968} {"current_steps": 39245, "total_steps": 64460, "loss": 0.1984, "lr": 3.980737543433158e-06, "epoch": 12.176543592925846, "percentage": 60.88, "elapsed_time": "1:12:42", "remaining_time": "0:46:42", "throughput": 5483.61, "total_tokens": 23920272} {"current_steps": 39250, "total_steps": 64460, "loss": 0.2023, "lr": 3.9794122006096305e-06, "epoch": 12.178094942600062, "percentage": 60.89, "elapsed_time": "1:12:42", "remaining_time": "0:46:42", "throughput": 5483.57, "total_tokens": 23922800} {"current_steps": 39255, "total_steps": 64460, "loss": 0.1836, "lr": 3.978086932607276e-06, "epoch": 12.17964629227428, "percentage": 60.9, "elapsed_time": "1:12:43", "remaining_time": "0:46:41", "throughput": 5483.58, "total_tokens": 23925680} {"current_steps": 39260, "total_steps": 64460, "loss": 0.2003, "lr": 3.9767617395232495e-06, "epoch": 12.181197641948495, "percentage": 60.91, "elapsed_time": "1:12:43", "remaining_time": "0:46:40", "throughput": 5483.72, "total_tokens": 23929616} {"current_steps": 39265, "total_steps": 64460, "loss": 0.2202, "lr": 3.975436621454705e-06, "epoch": 12.182748991622711, "percentage": 60.91, "elapsed_time": "1:12:44", "remaining_time": "0:46:40", "throughput": 5483.78, "total_tokens": 23932688} {"current_steps": 39270, "total_steps": 64460, "loss": 0.1911, "lr": 3.974111578498788e-06, "epoch": 12.184300341296929, "percentage": 60.92, "elapsed_time": "1:12:44", "remaining_time": "0:46:39", "throughput": 5483.73, "total_tokens": 23935056} {"current_steps": 39275, "total_steps": 64460, "loss": 0.2071, "lr": 3.972786610752641e-06, "epoch": 12.185851690971145, "percentage": 60.93, "elapsed_time": "1:12:45", "remaining_time": "0:46:39", "throughput": 5483.86, "total_tokens": 23938832} {"current_steps": 39280, "total_steps": 64460, "loss": 0.1365, "lr": 3.9714617183134e-06, "epoch": 12.18740304064536, "percentage": 60.94, "elapsed_time": "1:12:45", "remaining_time": "0:46:38", "throughput": 5483.9, "total_tokens": 23941808} {"current_steps": 39285, "total_steps": 64460, "loss": 0.2114, "lr": 3.970136901278194e-06, "epoch": 12.188954390319578, "percentage": 60.94, "elapsed_time": "1:12:46", "remaining_time": "0:46:38", "throughput": 5483.93, "total_tokens": 23945200} {"current_steps": 39290, "total_steps": 64460, "loss": 0.1934, "lr": 3.968812159744149e-06, "epoch": 12.190505739993794, "percentage": 60.95, "elapsed_time": "1:12:46", "remaining_time": "0:46:37", "throughput": 5483.84, "total_tokens": 23947600} {"current_steps": 39295, "total_steps": 64460, "loss": 0.2251, "lr": 3.967487493808383e-06, "epoch": 12.192057089668012, "percentage": 60.96, "elapsed_time": "1:12:47", "remaining_time": "0:46:36", "throughput": 5483.93, "total_tokens": 23950928} {"current_steps": 39300, "total_steps": 64460, "loss": 0.1996, "lr": 3.966162903568012e-06, "epoch": 12.193608439342228, "percentage": 60.97, "elapsed_time": "1:12:47", "remaining_time": "0:46:36", "throughput": 5483.88, "total_tokens": 23953296} {"current_steps": 39305, "total_steps": 64460, "loss": 0.236, "lr": 3.96483838912014e-06, "epoch": 12.195159789016444, "percentage": 60.98, "elapsed_time": "1:12:48", "remaining_time": "0:46:35", "throughput": 5483.86, "total_tokens": 23955824} {"current_steps": 39310, "total_steps": 64460, "loss": 0.1933, "lr": 3.963513950561874e-06, "epoch": 12.196711138690661, "percentage": 60.98, "elapsed_time": "1:12:49", "remaining_time": "0:46:35", "throughput": 5483.81, "total_tokens": 23959024} {"current_steps": 39315, "total_steps": 64460, "loss": 0.1926, "lr": 3.96218958799031e-06, "epoch": 12.198262488364877, "percentage": 60.99, "elapsed_time": "1:12:49", "remaining_time": "0:46:34", "throughput": 5483.92, "total_tokens": 23962672} {"current_steps": 39320, "total_steps": 64460, "loss": 0.3275, "lr": 3.960865301502537e-06, "epoch": 12.199813838039095, "percentage": 61.0, "elapsed_time": "1:12:50", "remaining_time": "0:46:34", "throughput": 5483.75, "total_tokens": 23964880} {"current_steps": 39325, "total_steps": 64460, "loss": 0.2111, "lr": 3.9595410911956435e-06, "epoch": 12.20136518771331, "percentage": 61.01, "elapsed_time": "1:12:50", "remaining_time": "0:46:33", "throughput": 5483.75, "total_tokens": 23967632} {"current_steps": 39330, "total_steps": 64460, "loss": 0.2014, "lr": 3.958216957166709e-06, "epoch": 12.202916537387527, "percentage": 61.01, "elapsed_time": "1:12:51", "remaining_time": "0:46:33", "throughput": 5483.93, "total_tokens": 23972944} {"current_steps": 39335, "total_steps": 64460, "loss": 0.2266, "lr": 3.956892899512808e-06, "epoch": 12.204467887061744, "percentage": 61.02, "elapsed_time": "1:12:52", "remaining_time": "0:46:32", "throughput": 5484.1, "total_tokens": 23976944} {"current_steps": 39340, "total_steps": 64460, "loss": 0.2905, "lr": 3.9555689183310095e-06, "epoch": 12.20601923673596, "percentage": 61.03, "elapsed_time": "1:12:52", "remaining_time": "0:46:32", "throughput": 5484.16, "total_tokens": 23979952} {"current_steps": 39345, "total_steps": 64460, "loss": 0.2128, "lr": 3.954245013718378e-06, "epoch": 12.207570586410176, "percentage": 61.04, "elapsed_time": "1:12:53", "remaining_time": "0:46:31", "throughput": 5484.21, "total_tokens": 23983088} {"current_steps": 39350, "total_steps": 64460, "loss": 0.1961, "lr": 3.95292118577197e-06, "epoch": 12.209121936084394, "percentage": 61.05, "elapsed_time": "1:12:53", "remaining_time": "0:46:30", "throughput": 5484.24, "total_tokens": 23986128} {"current_steps": 39355, "total_steps": 64460, "loss": 0.1425, "lr": 3.951597434588837e-06, "epoch": 12.21067328575861, "percentage": 61.05, "elapsed_time": "1:12:54", "remaining_time": "0:46:30", "throughput": 5484.43, "total_tokens": 23990768} {"current_steps": 39360, "total_steps": 64460, "loss": 0.1841, "lr": 3.950273760266029e-06, "epoch": 12.212224635432827, "percentage": 61.06, "elapsed_time": "1:12:54", "remaining_time": "0:46:29", "throughput": 5484.41, "total_tokens": 23993424} {"current_steps": 39365, "total_steps": 64460, "loss": 0.2291, "lr": 3.948950162900583e-06, "epoch": 12.213775985107043, "percentage": 61.07, "elapsed_time": "1:12:55", "remaining_time": "0:46:29", "throughput": 5484.34, "total_tokens": 23996048} {"current_steps": 39370, "total_steps": 64460, "loss": 0.2991, "lr": 3.947626642589538e-06, "epoch": 12.215327334781259, "percentage": 61.08, "elapsed_time": "1:12:55", "remaining_time": "0:46:28", "throughput": 5484.4, "total_tokens": 23998928} {"current_steps": 39375, "total_steps": 64460, "loss": 0.1824, "lr": 3.946303199429922e-06, "epoch": 12.216878684455477, "percentage": 61.08, "elapsed_time": "1:12:56", "remaining_time": "0:46:28", "throughput": 5484.36, "total_tokens": 24001456} {"current_steps": 39380, "total_steps": 64460, "loss": 0.2347, "lr": 3.944979833518758e-06, "epoch": 12.218430034129693, "percentage": 61.09, "elapsed_time": "1:12:56", "remaining_time": "0:46:27", "throughput": 5484.36, "total_tokens": 24004304} {"current_steps": 39385, "total_steps": 64460, "loss": 0.2071, "lr": 3.943656544953067e-06, "epoch": 12.21998138380391, "percentage": 61.1, "elapsed_time": "1:12:57", "remaining_time": "0:46:26", "throughput": 5484.36, "total_tokens": 24007088} {"current_steps": 39390, "total_steps": 64460, "loss": 0.1848, "lr": 3.942333333829859e-06, "epoch": 12.221532733478126, "percentage": 61.11, "elapsed_time": "1:12:57", "remaining_time": "0:46:26", "throughput": 5484.33, "total_tokens": 24009616} {"current_steps": 39395, "total_steps": 64460, "loss": 0.2637, "lr": 3.941010200246143e-06, "epoch": 12.223084083152342, "percentage": 61.12, "elapsed_time": "1:12:58", "remaining_time": "0:46:25", "throughput": 5484.49, "total_tokens": 24014032} {"current_steps": 39400, "total_steps": 64460, "loss": 0.2424, "lr": 3.93968714429892e-06, "epoch": 12.22463543282656, "percentage": 61.12, "elapsed_time": "1:12:59", "remaining_time": "0:46:25", "throughput": 5484.66, "total_tokens": 24017872} {"current_steps": 39405, "total_steps": 64460, "loss": 0.1782, "lr": 3.9383641660851845e-06, "epoch": 12.226186782500776, "percentage": 61.13, "elapsed_time": "1:12:59", "remaining_time": "0:46:24", "throughput": 5484.61, "total_tokens": 24020336} {"current_steps": 39410, "total_steps": 64460, "loss": 0.1832, "lr": 3.937041265701928e-06, "epoch": 12.227738132174991, "percentage": 61.14, "elapsed_time": "1:13:00", "remaining_time": "0:46:24", "throughput": 5484.71, "total_tokens": 24023600} {"current_steps": 39415, "total_steps": 64460, "loss": 0.2495, "lr": 3.935718443246134e-06, "epoch": 12.229289481849209, "percentage": 61.15, "elapsed_time": "1:13:00", "remaining_time": "0:46:23", "throughput": 5484.66, "total_tokens": 24026064} {"current_steps": 39420, "total_steps": 64460, "loss": 0.1771, "lr": 3.93439569881478e-06, "epoch": 12.230840831523425, "percentage": 61.15, "elapsed_time": "1:13:01", "remaining_time": "0:46:23", "throughput": 5484.8, "total_tokens": 24030416} {"current_steps": 39425, "total_steps": 64460, "loss": 0.227, "lr": 3.93307303250484e-06, "epoch": 12.232392181197643, "percentage": 61.16, "elapsed_time": "1:13:01", "remaining_time": "0:46:22", "throughput": 5484.9, "total_tokens": 24034192} {"current_steps": 39430, "total_steps": 64460, "loss": 0.1958, "lr": 3.931750444413281e-06, "epoch": 12.233943530871858, "percentage": 61.17, "elapsed_time": "1:13:02", "remaining_time": "0:46:21", "throughput": 5484.9, "total_tokens": 24036912} {"current_steps": 39435, "total_steps": 64460, "loss": 0.2768, "lr": 3.930427934637066e-06, "epoch": 12.235494880546074, "percentage": 61.18, "elapsed_time": "1:13:02", "remaining_time": "0:46:21", "throughput": 5484.99, "total_tokens": 24039952} {"current_steps": 39440, "total_steps": 64460, "loss": 0.2115, "lr": 3.929105503273147e-06, "epoch": 12.237046230220292, "percentage": 61.19, "elapsed_time": "1:13:03", "remaining_time": "0:46:20", "throughput": 5484.89, "total_tokens": 24042064} {"current_steps": 39445, "total_steps": 64460, "loss": 0.2265, "lr": 3.9277831504184774e-06, "epoch": 12.238597579894508, "percentage": 61.19, "elapsed_time": "1:13:04", "remaining_time": "0:46:20", "throughput": 5484.97, "total_tokens": 24046352} {"current_steps": 39450, "total_steps": 64460, "loss": 0.2182, "lr": 3.92646087617e-06, "epoch": 12.240148929568726, "percentage": 61.2, "elapsed_time": "1:13:04", "remaining_time": "0:46:19", "throughput": 5484.9, "total_tokens": 24048688} {"current_steps": 39455, "total_steps": 64460, "loss": 0.2367, "lr": 3.925138680624652e-06, "epoch": 12.241700279242941, "percentage": 61.21, "elapsed_time": "1:13:05", "remaining_time": "0:46:19", "throughput": 5484.92, "total_tokens": 24051408} {"current_steps": 39460, "total_steps": 64460, "loss": 0.2004, "lr": 3.923816563879367e-06, "epoch": 12.243251628917157, "percentage": 61.22, "elapsed_time": "1:13:05", "remaining_time": "0:46:18", "throughput": 5484.94, "total_tokens": 24054512} {"current_steps": 39465, "total_steps": 64460, "loss": 0.1647, "lr": 3.9224945260310725e-06, "epoch": 12.244802978591375, "percentage": 61.22, "elapsed_time": "1:13:06", "remaining_time": "0:46:17", "throughput": 5485.02, "total_tokens": 24057968} {"current_steps": 39470, "total_steps": 64460, "loss": 0.1993, "lr": 3.9211725671766885e-06, "epoch": 12.246354328265591, "percentage": 61.23, "elapsed_time": "1:13:06", "remaining_time": "0:46:17", "throughput": 5485.22, "total_tokens": 24062832} {"current_steps": 39475, "total_steps": 64460, "loss": 0.2106, "lr": 3.91985068741313e-06, "epoch": 12.247905677939807, "percentage": 61.24, "elapsed_time": "1:13:07", "remaining_time": "0:46:16", "throughput": 5485.22, "total_tokens": 24065840} {"current_steps": 39480, "total_steps": 64460, "loss": 0.2275, "lr": 3.918528886837308e-06, "epoch": 12.249457027614024, "percentage": 61.25, "elapsed_time": "1:13:07", "remaining_time": "0:46:16", "throughput": 5485.26, "total_tokens": 24068688} {"current_steps": 39485, "total_steps": 64460, "loss": 0.2401, "lr": 3.917207165546124e-06, "epoch": 12.25100837728824, "percentage": 61.26, "elapsed_time": "1:13:08", "remaining_time": "0:46:15", "throughput": 5485.27, "total_tokens": 24071376} {"current_steps": 39490, "total_steps": 64460, "loss": 0.2726, "lr": 3.915885523636477e-06, "epoch": 12.252559726962458, "percentage": 61.26, "elapsed_time": "1:13:08", "remaining_time": "0:46:15", "throughput": 5485.33, "total_tokens": 24074384} {"current_steps": 39495, "total_steps": 64460, "loss": 0.1787, "lr": 3.91456396120526e-06, "epoch": 12.254111076636674, "percentage": 61.27, "elapsed_time": "1:13:09", "remaining_time": "0:46:14", "throughput": 5485.5, "total_tokens": 24078352} {"current_steps": 39500, "total_steps": 64460, "loss": 0.2509, "lr": 3.913242478349357e-06, "epoch": 12.25566242631089, "percentage": 61.28, "elapsed_time": "1:13:09", "remaining_time": "0:46:13", "throughput": 5485.46, "total_tokens": 24080784} {"current_steps": 39505, "total_steps": 64460, "loss": 0.2369, "lr": 3.91192107516565e-06, "epoch": 12.257213775985107, "percentage": 61.29, "elapsed_time": "1:13:10", "remaining_time": "0:46:13", "throughput": 5485.48, "total_tokens": 24083536} {"current_steps": 39510, "total_steps": 64460, "loss": 0.232, "lr": 3.910599751751013e-06, "epoch": 12.258765125659323, "percentage": 61.29, "elapsed_time": "1:13:10", "remaining_time": "0:46:12", "throughput": 5485.52, "total_tokens": 24086512} {"current_steps": 39515, "total_steps": 64460, "loss": 0.2129, "lr": 3.909278508202315e-06, "epoch": 12.260316475333541, "percentage": 61.3, "elapsed_time": "1:13:11", "remaining_time": "0:46:12", "throughput": 5485.54, "total_tokens": 24089200} {"current_steps": 39520, "total_steps": 64460, "loss": 0.1939, "lr": 3.907957344616418e-06, "epoch": 12.261867825007757, "percentage": 61.31, "elapsed_time": "1:13:11", "remaining_time": "0:46:11", "throughput": 5485.59, "total_tokens": 24092688} {"current_steps": 39525, "total_steps": 64460, "loss": 0.1867, "lr": 3.9066362610901795e-06, "epoch": 12.263419174681973, "percentage": 61.32, "elapsed_time": "1:13:12", "remaining_time": "0:46:11", "throughput": 5485.56, "total_tokens": 24095120} {"current_steps": 39530, "total_steps": 64460, "loss": 0.1858, "lr": 3.905315257720451e-06, "epoch": 12.26497052435619, "percentage": 61.32, "elapsed_time": "1:13:12", "remaining_time": "0:46:10", "throughput": 5485.53, "total_tokens": 24097648} {"current_steps": 39535, "total_steps": 64460, "loss": 0.2076, "lr": 3.903994334604076e-06, "epoch": 12.266521874030406, "percentage": 61.33, "elapsed_time": "1:13:13", "remaining_time": "0:46:09", "throughput": 5485.41, "total_tokens": 24099952} {"current_steps": 39540, "total_steps": 64460, "loss": 0.2092, "lr": 3.9026734918378964e-06, "epoch": 12.268073223704622, "percentage": 61.34, "elapsed_time": "1:13:13", "remaining_time": "0:46:09", "throughput": 5485.43, "total_tokens": 24102672} {"current_steps": 39545, "total_steps": 64460, "loss": 0.214, "lr": 3.901352729518741e-06, "epoch": 12.26962457337884, "percentage": 61.35, "elapsed_time": "1:13:14", "remaining_time": "0:46:08", "throughput": 5485.41, "total_tokens": 24105200} {"current_steps": 39550, "total_steps": 64460, "loss": 0.1921, "lr": 3.900032047743443e-06, "epoch": 12.271175923053056, "percentage": 61.36, "elapsed_time": "1:13:14", "remaining_time": "0:46:08", "throughput": 5485.47, "total_tokens": 24108240} {"current_steps": 39555, "total_steps": 64460, "loss": 0.1723, "lr": 3.898711446608822e-06, "epoch": 12.272727272727273, "percentage": 61.36, "elapsed_time": "1:13:15", "remaining_time": "0:46:07", "throughput": 5485.63, "total_tokens": 24112240} {"current_steps": 39560, "total_steps": 64460, "loss": 0.2224, "lr": 3.89739092621169e-06, "epoch": 12.27427862240149, "percentage": 61.37, "elapsed_time": "1:13:16", "remaining_time": "0:46:06", "throughput": 5485.68, "total_tokens": 24115248} {"current_steps": 39565, "total_steps": 64460, "loss": 0.1808, "lr": 3.896070486648863e-06, "epoch": 12.275829972075705, "percentage": 61.38, "elapsed_time": "1:13:16", "remaining_time": "0:46:06", "throughput": 5485.7, "total_tokens": 24117968} {"current_steps": 39570, "total_steps": 64460, "loss": 0.2186, "lr": 3.8947501280171405e-06, "epoch": 12.277381321749923, "percentage": 61.39, "elapsed_time": "1:13:17", "remaining_time": "0:46:05", "throughput": 5485.76, "total_tokens": 24121264} {"current_steps": 39575, "total_steps": 64460, "loss": 0.2264, "lr": 3.893429850413322e-06, "epoch": 12.278932671424139, "percentage": 61.39, "elapsed_time": "1:13:17", "remaining_time": "0:46:05", "throughput": 5485.89, "total_tokens": 24124848} {"current_steps": 39580, "total_steps": 64460, "loss": 0.1734, "lr": 3.892109653934199e-06, "epoch": 12.280484021098356, "percentage": 61.4, "elapsed_time": "1:13:18", "remaining_time": "0:46:04", "throughput": 5485.95, "total_tokens": 24128016} {"current_steps": 39585, "total_steps": 64460, "loss": 0.2917, "lr": 3.890789538676558e-06, "epoch": 12.282035370772572, "percentage": 61.41, "elapsed_time": "1:13:18", "remaining_time": "0:46:04", "throughput": 5485.98, "total_tokens": 24130768} {"current_steps": 39590, "total_steps": 64460, "loss": 0.2214, "lr": 3.88946950473718e-06, "epoch": 12.283586720446788, "percentage": 61.42, "elapsed_time": "1:13:19", "remaining_time": "0:46:03", "throughput": 5485.95, "total_tokens": 24133616} {"current_steps": 39595, "total_steps": 64460, "loss": 0.1892, "lr": 3.888149552212837e-06, "epoch": 12.285138070121006, "percentage": 61.43, "elapsed_time": "1:13:19", "remaining_time": "0:46:02", "throughput": 5486.03, "total_tokens": 24136784} {"current_steps": 39600, "total_steps": 64460, "loss": 0.2567, "lr": 3.886829681200297e-06, "epoch": 12.286689419795222, "percentage": 61.43, "elapsed_time": "1:13:20", "remaining_time": "0:46:02", "throughput": 5486.05, "total_tokens": 24139696} {"current_steps": 39605, "total_steps": 64460, "loss": 0.2185, "lr": 3.885509891796325e-06, "epoch": 12.288240769469438, "percentage": 61.44, "elapsed_time": "1:13:20", "remaining_time": "0:46:01", "throughput": 5486.17, "total_tokens": 24143088} {"current_steps": 39610, "total_steps": 64460, "loss": 0.2215, "lr": 3.884190184097675e-06, "epoch": 12.289792119143655, "percentage": 61.45, "elapsed_time": "1:13:21", "remaining_time": "0:46:01", "throughput": 5486.3, "total_tokens": 24146576} {"current_steps": 39615, "total_steps": 64460, "loss": 0.183, "lr": 3.882870558201098e-06, "epoch": 12.291343468817871, "percentage": 61.46, "elapsed_time": "1:13:21", "remaining_time": "0:46:00", "throughput": 5486.24, "total_tokens": 24148848} {"current_steps": 39620, "total_steps": 64460, "loss": 0.1924, "lr": 3.881551014203338e-06, "epoch": 12.292894818492089, "percentage": 61.46, "elapsed_time": "1:13:22", "remaining_time": "0:45:59", "throughput": 5486.14, "total_tokens": 24150960} {"current_steps": 39625, "total_steps": 64460, "loss": 0.2644, "lr": 3.880231552201131e-06, "epoch": 12.294446168166305, "percentage": 61.47, "elapsed_time": "1:13:22", "remaining_time": "0:45:59", "throughput": 5486.11, "total_tokens": 24153584} {"current_steps": 39630, "total_steps": 64460, "loss": 0.2127, "lr": 3.878912172291214e-06, "epoch": 12.29599751784052, "percentage": 61.48, "elapsed_time": "1:13:23", "remaining_time": "0:45:58", "throughput": 5486.11, "total_tokens": 24156336} {"current_steps": 39635, "total_steps": 64460, "loss": 0.2213, "lr": 3.877592874570307e-06, "epoch": 12.297548867514738, "percentage": 61.49, "elapsed_time": "1:13:23", "remaining_time": "0:45:58", "throughput": 5486.25, "total_tokens": 24159952} {"current_steps": 39640, "total_steps": 64460, "loss": 0.1903, "lr": 3.876273659135136e-06, "epoch": 12.299100217188954, "percentage": 61.5, "elapsed_time": "1:13:24", "remaining_time": "0:45:57", "throughput": 5486.23, "total_tokens": 24162352} {"current_steps": 39645, "total_steps": 64460, "loss": 0.2351, "lr": 3.874954526082413e-06, "epoch": 12.300651566863172, "percentage": 61.5, "elapsed_time": "1:13:24", "remaining_time": "0:45:57", "throughput": 5486.26, "total_tokens": 24165648} {"current_steps": 39650, "total_steps": 64460, "loss": 0.2067, "lr": 3.873635475508845e-06, "epoch": 12.302202916537388, "percentage": 61.51, "elapsed_time": "1:13:25", "remaining_time": "0:45:56", "throughput": 5486.33, "total_tokens": 24168528} {"current_steps": 39655, "total_steps": 64460, "loss": 0.239, "lr": 3.872316507511135e-06, "epoch": 12.303754266211604, "percentage": 61.52, "elapsed_time": "1:13:25", "remaining_time": "0:45:55", "throughput": 5486.53, "total_tokens": 24173264} {"current_steps": 39660, "total_steps": 64460, "loss": 0.2056, "lr": 3.870997622185979e-06, "epoch": 12.305305615885821, "percentage": 61.53, "elapsed_time": "1:13:26", "remaining_time": "0:45:55", "throughput": 5486.49, "total_tokens": 24175728} {"current_steps": 39665, "total_steps": 64460, "loss": 0.2073, "lr": 3.869678819630067e-06, "epoch": 12.306856965560037, "percentage": 61.53, "elapsed_time": "1:13:26", "remaining_time": "0:45:54", "throughput": 5486.57, "total_tokens": 24179024} {"current_steps": 39670, "total_steps": 64460, "loss": 0.2177, "lr": 3.8683600999400815e-06, "epoch": 12.308408315234253, "percentage": 61.54, "elapsed_time": "1:13:27", "remaining_time": "0:45:54", "throughput": 5486.67, "total_tokens": 24182352} {"current_steps": 39675, "total_steps": 64460, "loss": 0.2118, "lr": 3.8670414632127016e-06, "epoch": 12.30995966490847, "percentage": 61.55, "elapsed_time": "1:13:27", "remaining_time": "0:45:53", "throughput": 5486.71, "total_tokens": 24185264} {"current_steps": 39680, "total_steps": 64460, "loss": 0.2173, "lr": 3.865722909544599e-06, "epoch": 12.311511014582686, "percentage": 61.56, "elapsed_time": "1:13:28", "remaining_time": "0:45:53", "throughput": 5486.85, "total_tokens": 24188912} {"current_steps": 39685, "total_steps": 64460, "loss": 0.2405, "lr": 3.864404439032439e-06, "epoch": 12.313062364256904, "percentage": 61.57, "elapsed_time": "1:13:29", "remaining_time": "0:45:52", "throughput": 5487.0, "total_tokens": 24192688} {"current_steps": 39690, "total_steps": 64460, "loss": 0.2325, "lr": 3.863086051772881e-06, "epoch": 12.31461371393112, "percentage": 61.57, "elapsed_time": "1:13:29", "remaining_time": "0:45:51", "throughput": 5486.99, "total_tokens": 24195248} {"current_steps": 39695, "total_steps": 64460, "loss": 0.2032, "lr": 3.861767747862578e-06, "epoch": 12.316165063605336, "percentage": 61.58, "elapsed_time": "1:13:30", "remaining_time": "0:45:51", "throughput": 5487.1, "total_tokens": 24198864} {"current_steps": 39700, "total_steps": 64460, "loss": 0.1879, "lr": 3.860449527398178e-06, "epoch": 12.317716413279554, "percentage": 61.59, "elapsed_time": "1:13:30", "remaining_time": "0:45:50", "throughput": 5487.04, "total_tokens": 24201264} {"current_steps": 39705, "total_steps": 64460, "loss": 0.2577, "lr": 3.859131390476322e-06, "epoch": 12.31926776295377, "percentage": 61.6, "elapsed_time": "1:13:31", "remaining_time": "0:45:50", "throughput": 5487.08, "total_tokens": 24204368} {"current_steps": 39710, "total_steps": 64460, "loss": 0.2006, "lr": 3.8578133371936454e-06, "epoch": 12.320819112627987, "percentage": 61.6, "elapsed_time": "1:13:31", "remaining_time": "0:45:49", "throughput": 5487.15, "total_tokens": 24207536} {"current_steps": 39715, "total_steps": 64460, "loss": 0.1958, "lr": 3.856495367646777e-06, "epoch": 12.322370462302203, "percentage": 61.61, "elapsed_time": "1:13:32", "remaining_time": "0:45:49", "throughput": 5487.11, "total_tokens": 24209936} {"current_steps": 39720, "total_steps": 64460, "loss": 0.1909, "lr": 3.8551774819323375e-06, "epoch": 12.323921811976419, "percentage": 61.62, "elapsed_time": "1:13:32", "remaining_time": "0:45:48", "throughput": 5487.17, "total_tokens": 24213040} {"current_steps": 39725, "total_steps": 64460, "loss": 0.2506, "lr": 3.8538596801469474e-06, "epoch": 12.325473161650637, "percentage": 61.63, "elapsed_time": "1:13:33", "remaining_time": "0:45:47", "throughput": 5487.3, "total_tokens": 24217072} {"current_steps": 39730, "total_steps": 64460, "loss": 0.214, "lr": 3.852541962387214e-06, "epoch": 12.327024511324852, "percentage": 61.64, "elapsed_time": "1:13:33", "remaining_time": "0:45:47", "throughput": 5487.31, "total_tokens": 24219824} {"current_steps": 39735, "total_steps": 64460, "loss": 0.2072, "lr": 3.851224328749743e-06, "epoch": 12.32857586099907, "percentage": 61.64, "elapsed_time": "1:13:34", "remaining_time": "0:45:46", "throughput": 5487.32, "total_tokens": 24222480} {"current_steps": 39740, "total_steps": 64460, "loss": 0.2359, "lr": 3.849906779331132e-06, "epoch": 12.330127210673286, "percentage": 61.65, "elapsed_time": "1:13:34", "remaining_time": "0:45:46", "throughput": 5487.43, "total_tokens": 24226672} {"current_steps": 39745, "total_steps": 64460, "loss": 0.2515, "lr": 3.848589314227974e-06, "epoch": 12.331678560347502, "percentage": 61.66, "elapsed_time": "1:13:35", "remaining_time": "0:45:45", "throughput": 5487.57, "total_tokens": 24230384} {"current_steps": 39750, "total_steps": 64460, "loss": 0.2174, "lr": 3.847271933536852e-06, "epoch": 12.33322991002172, "percentage": 61.67, "elapsed_time": "1:13:35", "remaining_time": "0:45:45", "throughput": 5487.61, "total_tokens": 24233264} {"current_steps": 39755, "total_steps": 64460, "loss": 0.2308, "lr": 3.845954637354349e-06, "epoch": 12.334781259695935, "percentage": 61.67, "elapsed_time": "1:13:36", "remaining_time": "0:45:44", "throughput": 5487.77, "total_tokens": 24237552} {"current_steps": 39760, "total_steps": 64460, "loss": 0.1916, "lr": 3.844637425777037e-06, "epoch": 12.336332609370151, "percentage": 61.68, "elapsed_time": "1:13:37", "remaining_time": "0:45:44", "throughput": 5487.82, "total_tokens": 24240816} {"current_steps": 39765, "total_steps": 64460, "loss": 0.2374, "lr": 3.843320298901483e-06, "epoch": 12.337883959044369, "percentage": 61.69, "elapsed_time": "1:13:37", "remaining_time": "0:45:43", "throughput": 5487.66, "total_tokens": 24242704} {"current_steps": 39770, "total_steps": 64460, "loss": 0.1897, "lr": 3.842003256824248e-06, "epoch": 12.339435308718585, "percentage": 61.7, "elapsed_time": "1:13:38", "remaining_time": "0:45:42", "throughput": 5487.76, "total_tokens": 24246096} {"current_steps": 39775, "total_steps": 64460, "loss": 0.2101, "lr": 3.840686299641888e-06, "epoch": 12.340986658392803, "percentage": 61.7, "elapsed_time": "1:13:38", "remaining_time": "0:45:42", "throughput": 5487.77, "total_tokens": 24249040} {"current_steps": 39780, "total_steps": 64460, "loss": 0.2356, "lr": 3.8393694274509495e-06, "epoch": 12.342538008067018, "percentage": 61.71, "elapsed_time": "1:13:39", "remaining_time": "0:45:41", "throughput": 5487.78, "total_tokens": 24251760} {"current_steps": 39785, "total_steps": 64460, "loss": 0.2113, "lr": 3.838052640347977e-06, "epoch": 12.344089357741234, "percentage": 61.72, "elapsed_time": "1:13:39", "remaining_time": "0:45:41", "throughput": 5487.7, "total_tokens": 24254032} {"current_steps": 39790, "total_steps": 64460, "loss": 0.2262, "lr": 3.836735938429505e-06, "epoch": 12.345640707415452, "percentage": 61.73, "elapsed_time": "1:13:40", "remaining_time": "0:45:40", "throughput": 5487.62, "total_tokens": 24256368} {"current_steps": 39795, "total_steps": 64460, "loss": 0.216, "lr": 3.835419321792063e-06, "epoch": 12.347192057089668, "percentage": 61.74, "elapsed_time": "1:13:40", "remaining_time": "0:45:39", "throughput": 5487.62, "total_tokens": 24258992} {"current_steps": 39800, "total_steps": 64460, "loss": 0.1882, "lr": 3.834102790532177e-06, "epoch": 12.348743406763884, "percentage": 61.74, "elapsed_time": "1:13:41", "remaining_time": "0:45:39", "throughput": 5487.55, "total_tokens": 24261584} {"current_steps": 39805, "total_steps": 64460, "loss": 0.2193, "lr": 3.832786344746362e-06, "epoch": 12.350294756438101, "percentage": 61.75, "elapsed_time": "1:13:41", "remaining_time": "0:45:38", "throughput": 5487.54, "total_tokens": 24264208} {"current_steps": 39810, "total_steps": 64460, "loss": 0.1809, "lr": 3.8314699845311295e-06, "epoch": 12.351846106112317, "percentage": 61.76, "elapsed_time": "1:13:42", "remaining_time": "0:45:38", "throughput": 5487.6, "total_tokens": 24267216} {"current_steps": 39815, "total_steps": 64460, "loss": 0.215, "lr": 3.830153709982983e-06, "epoch": 12.353397455786535, "percentage": 61.77, "elapsed_time": "1:13:42", "remaining_time": "0:45:37", "throughput": 5487.56, "total_tokens": 24269744} {"current_steps": 39820, "total_steps": 64460, "loss": 0.2112, "lr": 3.828837521198425e-06, "epoch": 12.35494880546075, "percentage": 61.77, "elapsed_time": "1:13:43", "remaining_time": "0:45:37", "throughput": 5487.66, "total_tokens": 24273040} {"current_steps": 39825, "total_steps": 64460, "loss": 0.2484, "lr": 3.827521418273945e-06, "epoch": 12.356500155134967, "percentage": 61.78, "elapsed_time": "1:13:43", "remaining_time": "0:45:36", "throughput": 5487.71, "total_tokens": 24276048} {"current_steps": 39830, "total_steps": 64460, "loss": 0.2062, "lr": 3.826205401306028e-06, "epoch": 12.358051504809184, "percentage": 61.79, "elapsed_time": "1:13:44", "remaining_time": "0:45:35", "throughput": 5487.82, "total_tokens": 24279600} {"current_steps": 39835, "total_steps": 64460, "loss": 0.2323, "lr": 3.824889470391156e-06, "epoch": 12.3596028544834, "percentage": 61.8, "elapsed_time": "1:13:44", "remaining_time": "0:45:35", "throughput": 5487.88, "total_tokens": 24282512} {"current_steps": 39840, "total_steps": 64460, "loss": 0.2615, "lr": 3.823573625625802e-06, "epoch": 12.361154204157618, "percentage": 61.81, "elapsed_time": "1:13:45", "remaining_time": "0:45:34", "throughput": 5487.83, "total_tokens": 24284848} {"current_steps": 39845, "total_steps": 64460, "loss": 0.1953, "lr": 3.822257867106431e-06, "epoch": 12.362705553831834, "percentage": 61.81, "elapsed_time": "1:13:45", "remaining_time": "0:45:34", "throughput": 5487.79, "total_tokens": 24287344} {"current_steps": 39850, "total_steps": 64460, "loss": 0.2569, "lr": 3.820942194929505e-06, "epoch": 12.36425690350605, "percentage": 61.82, "elapsed_time": "1:13:46", "remaining_time": "0:45:33", "throughput": 5487.83, "total_tokens": 24290256} {"current_steps": 39855, "total_steps": 64460, "loss": 0.1779, "lr": 3.819626609191479e-06, "epoch": 12.365808253180267, "percentage": 61.83, "elapsed_time": "1:13:46", "remaining_time": "0:45:32", "throughput": 5487.84, "total_tokens": 24293136} {"current_steps": 39860, "total_steps": 64460, "loss": 0.2298, "lr": 3.818311109988799e-06, "epoch": 12.367359602854483, "percentage": 61.84, "elapsed_time": "1:13:47", "remaining_time": "0:45:32", "throughput": 5487.89, "total_tokens": 24296112} {"current_steps": 39865, "total_steps": 64460, "loss": 0.2354, "lr": 3.816995697417909e-06, "epoch": 12.3689109525287, "percentage": 61.84, "elapsed_time": "1:13:47", "remaining_time": "0:45:31", "throughput": 5487.96, "total_tokens": 24299184} {"current_steps": 39870, "total_steps": 64460, "loss": 0.2477, "lr": 3.815680371575243e-06, "epoch": 12.370462302202917, "percentage": 61.85, "elapsed_time": "1:13:48", "remaining_time": "0:45:31", "throughput": 5487.95, "total_tokens": 24301744} {"current_steps": 39875, "total_steps": 64460, "loss": 0.2365, "lr": 3.8143651325572282e-06, "epoch": 12.372013651877133, "percentage": 61.86, "elapsed_time": "1:13:48", "remaining_time": "0:45:30", "throughput": 5487.85, "total_tokens": 24303920} {"current_steps": 39880, "total_steps": 64460, "loss": 0.1968, "lr": 3.8130499804602915e-06, "epoch": 12.37356500155135, "percentage": 61.87, "elapsed_time": "1:13:49", "remaining_time": "0:45:29", "throughput": 5487.96, "total_tokens": 24307376} {"current_steps": 39885, "total_steps": 64460, "loss": 0.233, "lr": 3.8117349153808463e-06, "epoch": 12.375116351225566, "percentage": 61.88, "elapsed_time": "1:13:49", "remaining_time": "0:45:29", "throughput": 5487.95, "total_tokens": 24310000} {"current_steps": 39890, "total_steps": 64460, "loss": 0.2339, "lr": 3.8104199374153034e-06, "epoch": 12.376667700899782, "percentage": 61.88, "elapsed_time": "1:13:50", "remaining_time": "0:45:28", "throughput": 5488.15, "total_tokens": 24314480} {"current_steps": 39895, "total_steps": 64460, "loss": 0.2211, "lr": 3.8091050466600652e-06, "epoch": 12.378219050574, "percentage": 61.89, "elapsed_time": "1:13:50", "remaining_time": "0:45:28", "throughput": 5488.27, "total_tokens": 24317936} {"current_steps": 39900, "total_steps": 64460, "loss": 0.2118, "lr": 3.80779024321153e-06, "epoch": 12.379770400248216, "percentage": 61.9, "elapsed_time": "1:13:51", "remaining_time": "0:45:27", "throughput": 5488.26, "total_tokens": 24320656} {"current_steps": 39905, "total_steps": 64460, "loss": 0.1824, "lr": 3.8064755271660877e-06, "epoch": 12.381321749922433, "percentage": 61.91, "elapsed_time": "1:13:51", "remaining_time": "0:45:27", "throughput": 5488.33, "total_tokens": 24323600} {"current_steps": 39910, "total_steps": 64460, "loss": 0.2564, "lr": 3.805160898620122e-06, "epoch": 12.38287309959665, "percentage": 61.91, "elapsed_time": "1:13:52", "remaining_time": "0:45:26", "throughput": 5488.32, "total_tokens": 24326160} {"current_steps": 39915, "total_steps": 64460, "loss": 0.2211, "lr": 3.8038463576700126e-06, "epoch": 12.384424449270865, "percentage": 61.92, "elapsed_time": "1:13:52", "remaining_time": "0:45:25", "throughput": 5488.35, "total_tokens": 24328752} {"current_steps": 39920, "total_steps": 64460, "loss": 0.2338, "lr": 3.802531904412129e-06, "epoch": 12.385975798945083, "percentage": 61.93, "elapsed_time": "1:13:53", "remaining_time": "0:45:25", "throughput": 5488.33, "total_tokens": 24331248} {"current_steps": 39925, "total_steps": 64460, "loss": 0.2383, "lr": 3.801217538942837e-06, "epoch": 12.387527148619299, "percentage": 61.94, "elapsed_time": "1:13:53", "remaining_time": "0:45:24", "throughput": 5488.38, "total_tokens": 24334224} {"current_steps": 39930, "total_steps": 64460, "loss": 0.2263, "lr": 3.7999032613584954e-06, "epoch": 12.389078498293514, "percentage": 61.95, "elapsed_time": "1:13:54", "remaining_time": "0:45:24", "throughput": 5488.42, "total_tokens": 24336848} {"current_steps": 39935, "total_steps": 64460, "loss": 0.1941, "lr": 3.798589071755454e-06, "epoch": 12.390629847967732, "percentage": 61.95, "elapsed_time": "1:13:54", "remaining_time": "0:45:23", "throughput": 5488.41, "total_tokens": 24339376} {"current_steps": 39940, "total_steps": 64460, "loss": 0.1992, "lr": 3.7972749702300627e-06, "epoch": 12.392181197641948, "percentage": 61.96, "elapsed_time": "1:13:55", "remaining_time": "0:45:22", "throughput": 5488.42, "total_tokens": 24341904} {"current_steps": 39945, "total_steps": 64460, "loss": 0.176, "lr": 3.795960956878658e-06, "epoch": 12.393732547316166, "percentage": 61.97, "elapsed_time": "1:13:55", "remaining_time": "0:45:22", "throughput": 5488.46, "total_tokens": 24345456} {"current_steps": 39950, "total_steps": 64460, "loss": 0.2662, "lr": 3.794647031797573e-06, "epoch": 12.395283896990382, "percentage": 61.98, "elapsed_time": "1:13:56", "remaining_time": "0:45:21", "throughput": 5488.55, "total_tokens": 24348720} {"current_steps": 39955, "total_steps": 64460, "loss": 0.1958, "lr": 3.793333195083134e-06, "epoch": 12.396835246664597, "percentage": 61.98, "elapsed_time": "1:13:56", "remaining_time": "0:45:21", "throughput": 5488.58, "total_tokens": 24351376} {"current_steps": 39960, "total_steps": 64460, "loss": 0.236, "lr": 3.7920194468316617e-06, "epoch": 12.398386596338815, "percentage": 61.99, "elapsed_time": "1:13:57", "remaining_time": "0:45:20", "throughput": 5488.58, "total_tokens": 24354000} {"current_steps": 39965, "total_steps": 64460, "loss": 0.1977, "lr": 3.790705787139468e-06, "epoch": 12.399937946013031, "percentage": 62.0, "elapsed_time": "1:13:57", "remaining_time": "0:45:19", "throughput": 5488.62, "total_tokens": 24357456} {"current_steps": 39970, "total_steps": 64460, "loss": 0.2309, "lr": 3.78939221610286e-06, "epoch": 12.401489295687249, "percentage": 62.01, "elapsed_time": "1:13:58", "remaining_time": "0:45:19", "throughput": 5488.7, "total_tokens": 24360368} {"current_steps": 39975, "total_steps": 64460, "loss": 0.2143, "lr": 3.788078733818139e-06, "epoch": 12.403040645361465, "percentage": 62.02, "elapsed_time": "1:13:58", "remaining_time": "0:45:18", "throughput": 5488.65, "total_tokens": 24362672} {"current_steps": 39980, "total_steps": 64460, "loss": 0.2186, "lr": 3.786765340381597e-06, "epoch": 12.40459199503568, "percentage": 62.02, "elapsed_time": "1:13:59", "remaining_time": "0:45:18", "throughput": 5488.66, "total_tokens": 24365200} {"current_steps": 39985, "total_steps": 64460, "loss": 0.2057, "lr": 3.7854520358895237e-06, "epoch": 12.406143344709898, "percentage": 62.03, "elapsed_time": "1:13:59", "remaining_time": "0:45:17", "throughput": 5488.8, "total_tokens": 24369392} {"current_steps": 39990, "total_steps": 64460, "loss": 0.2101, "lr": 3.7841388204381978e-06, "epoch": 12.407694694384114, "percentage": 62.04, "elapsed_time": "1:14:00", "remaining_time": "0:45:17", "throughput": 5488.82, "total_tokens": 24372336} {"current_steps": 39995, "total_steps": 64460, "loss": 0.2093, "lr": 3.782825694123894e-06, "epoch": 12.409246044058332, "percentage": 62.05, "elapsed_time": "1:14:00", "remaining_time": "0:45:16", "throughput": 5488.76, "total_tokens": 24374480} {"current_steps": 40000, "total_steps": 64460, "loss": 0.2272, "lr": 3.781512657042881e-06, "epoch": 12.410797393732548, "percentage": 62.05, "elapsed_time": "1:14:01", "remaining_time": "0:45:15", "throughput": 5488.71, "total_tokens": 24376784} {"current_steps": 40005, "total_steps": 64460, "loss": 0.2173, "lr": 3.780199709291419e-06, "epoch": 12.412348743406763, "percentage": 62.06, "elapsed_time": "1:14:01", "remaining_time": "0:45:15", "throughput": 5488.83, "total_tokens": 24380688} {"current_steps": 40010, "total_steps": 64460, "loss": 0.2001, "lr": 3.7788868509657627e-06, "epoch": 12.413900093080981, "percentage": 62.07, "elapsed_time": "1:14:02", "remaining_time": "0:45:14", "throughput": 5489.0, "total_tokens": 24385488} {"current_steps": 40015, "total_steps": 64460, "loss": 0.2489, "lr": 3.7775740821621605e-06, "epoch": 12.415451442755197, "percentage": 62.08, "elapsed_time": "1:14:03", "remaining_time": "0:45:14", "throughput": 5489.11, "total_tokens": 24388944} {"current_steps": 40020, "total_steps": 64460, "loss": 0.227, "lr": 3.776261402976854e-06, "epoch": 12.417002792429413, "percentage": 62.09, "elapsed_time": "1:14:03", "remaining_time": "0:45:13", "throughput": 5489.18, "total_tokens": 24392080} {"current_steps": 40025, "total_steps": 64460, "loss": 0.2065, "lr": 3.7749488135060776e-06, "epoch": 12.41855414210363, "percentage": 62.09, "elapsed_time": "1:14:04", "remaining_time": "0:45:13", "throughput": 5489.1, "total_tokens": 24394608} {"current_steps": 40030, "total_steps": 64460, "loss": 0.2251, "lr": 3.77363631384606e-06, "epoch": 12.420105491777846, "percentage": 62.1, "elapsed_time": "1:14:04", "remaining_time": "0:45:12", "throughput": 5489.16, "total_tokens": 24397744} {"current_steps": 40035, "total_steps": 64460, "loss": 0.1791, "lr": 3.772323904093024e-06, "epoch": 12.421656841452064, "percentage": 62.11, "elapsed_time": "1:14:05", "remaining_time": "0:45:11", "throughput": 5489.13, "total_tokens": 24400080} {"current_steps": 40040, "total_steps": 64460, "loss": 0.2549, "lr": 3.7710115843431822e-06, "epoch": 12.42320819112628, "percentage": 62.12, "elapsed_time": "1:14:05", "remaining_time": "0:45:11", "throughput": 5489.12, "total_tokens": 24402736} {"current_steps": 40045, "total_steps": 64460, "loss": 0.2009, "lr": 3.769699354692745e-06, "epoch": 12.424759540800496, "percentage": 62.12, "elapsed_time": "1:14:06", "remaining_time": "0:45:10", "throughput": 5489.11, "total_tokens": 24405232} {"current_steps": 40050, "total_steps": 64460, "loss": 0.1983, "lr": 3.7683872152379147e-06, "epoch": 12.426310890474713, "percentage": 62.13, "elapsed_time": "1:14:06", "remaining_time": "0:45:10", "throughput": 5489.12, "total_tokens": 24407856} {"current_steps": 40055, "total_steps": 64460, "loss": 0.1911, "lr": 3.7670751660748843e-06, "epoch": 12.42786224014893, "percentage": 62.14, "elapsed_time": "1:14:07", "remaining_time": "0:45:09", "throughput": 5489.11, "total_tokens": 24410320} {"current_steps": 40060, "total_steps": 64460, "loss": 0.2027, "lr": 3.7657632072998455e-06, "epoch": 12.429413589823145, "percentage": 62.15, "elapsed_time": "1:14:07", "remaining_time": "0:45:08", "throughput": 5489.19, "total_tokens": 24413552} {"current_steps": 40065, "total_steps": 64460, "loss": 0.2303, "lr": 3.7644513390089793e-06, "epoch": 12.430964939497363, "percentage": 62.15, "elapsed_time": "1:14:08", "remaining_time": "0:45:08", "throughput": 5489.1, "total_tokens": 24415760} {"current_steps": 40070, "total_steps": 64460, "loss": 0.2476, "lr": 3.7631395612984612e-06, "epoch": 12.432516289171579, "percentage": 62.16, "elapsed_time": "1:14:08", "remaining_time": "0:45:07", "throughput": 5489.1, "total_tokens": 24418800} {"current_steps": 40075, "total_steps": 64460, "loss": 0.2186, "lr": 3.761827874264459e-06, "epoch": 12.434067638845796, "percentage": 62.17, "elapsed_time": "1:14:09", "remaining_time": "0:45:07", "throughput": 5489.11, "total_tokens": 24421552} {"current_steps": 40080, "total_steps": 64460, "loss": 0.2503, "lr": 3.7605162780031368e-06, "epoch": 12.435618988520012, "percentage": 62.18, "elapsed_time": "1:14:09", "remaining_time": "0:45:06", "throughput": 5489.25, "total_tokens": 24425744} {"current_steps": 40085, "total_steps": 64460, "loss": 0.2273, "lr": 3.7592047726106484e-06, "epoch": 12.437170338194228, "percentage": 62.19, "elapsed_time": "1:14:10", "remaining_time": "0:45:06", "throughput": 5489.28, "total_tokens": 24428592} {"current_steps": 40090, "total_steps": 64460, "loss": 0.2731, "lr": 3.757893358183144e-06, "epoch": 12.438721687868446, "percentage": 62.19, "elapsed_time": "1:14:10", "remaining_time": "0:45:05", "throughput": 5489.48, "total_tokens": 24433200} {"current_steps": 40095, "total_steps": 64460, "loss": 0.2455, "lr": 3.7565820348167647e-06, "epoch": 12.440273037542662, "percentage": 62.2, "elapsed_time": "1:14:11", "remaining_time": "0:45:05", "throughput": 5489.56, "total_tokens": 24436272} {"current_steps": 40100, "total_steps": 64460, "loss": 0.2473, "lr": 3.7552708026076466e-06, "epoch": 12.44182438721688, "percentage": 62.21, "elapsed_time": "1:14:12", "remaining_time": "0:45:04", "throughput": 5489.75, "total_tokens": 24440784} {"current_steps": 40105, "total_steps": 64460, "loss": 0.2104, "lr": 3.7539596616519186e-06, "epoch": 12.443375736891095, "percentage": 62.22, "elapsed_time": "1:14:12", "remaining_time": "0:45:03", "throughput": 5489.81, "total_tokens": 24443792} {"current_steps": 40110, "total_steps": 64460, "loss": 0.2209, "lr": 3.752648612045703e-06, "epoch": 12.444927086565311, "percentage": 62.22, "elapsed_time": "1:14:13", "remaining_time": "0:45:03", "throughput": 5489.86, "total_tokens": 24446832} {"current_steps": 40115, "total_steps": 64460, "loss": 0.1936, "lr": 3.751337653885113e-06, "epoch": 12.446478436239529, "percentage": 62.23, "elapsed_time": "1:14:13", "remaining_time": "0:45:02", "throughput": 5489.89, "total_tokens": 24449456} {"current_steps": 40120, "total_steps": 64460, "loss": 0.2388, "lr": 3.750026787266261e-06, "epoch": 12.448029785913745, "percentage": 62.24, "elapsed_time": "1:14:14", "remaining_time": "0:45:02", "throughput": 5489.9, "total_tokens": 24452080} {"current_steps": 40125, "total_steps": 64460, "loss": 0.2036, "lr": 3.748716012285247e-06, "epoch": 12.449581135587962, "percentage": 62.25, "elapsed_time": "1:14:14", "remaining_time": "0:45:01", "throughput": 5490.01, "total_tokens": 24455760} {"current_steps": 40130, "total_steps": 64460, "loss": 0.2186, "lr": 3.7474053290381674e-06, "epoch": 12.451132485262178, "percentage": 62.26, "elapsed_time": "1:14:15", "remaining_time": "0:45:01", "throughput": 5490.03, "total_tokens": 24458480} {"current_steps": 40135, "total_steps": 64460, "loss": 0.2122, "lr": 3.746094737621109e-06, "epoch": 12.452683834936394, "percentage": 62.26, "elapsed_time": "1:14:15", "remaining_time": "0:45:00", "throughput": 5490.13, "total_tokens": 24461968} {"current_steps": 40140, "total_steps": 64460, "loss": 0.2384, "lr": 3.7447842381301546e-06, "epoch": 12.454235184610612, "percentage": 62.27, "elapsed_time": "1:14:16", "remaining_time": "0:44:59", "throughput": 5490.24, "total_tokens": 24465584} {"current_steps": 40145, "total_steps": 64460, "loss": 0.203, "lr": 3.7434738306613807e-06, "epoch": 12.455786534284828, "percentage": 62.28, "elapsed_time": "1:14:16", "remaining_time": "0:44:59", "throughput": 5490.33, "total_tokens": 24468816} {"current_steps": 40150, "total_steps": 64460, "loss": 0.2085, "lr": 3.7421635153108537e-06, "epoch": 12.457337883959044, "percentage": 62.29, "elapsed_time": "1:14:17", "remaining_time": "0:44:58", "throughput": 5490.33, "total_tokens": 24471280} {"current_steps": 40155, "total_steps": 64460, "loss": 0.2119, "lr": 3.740853292174637e-06, "epoch": 12.458889233633261, "percentage": 62.29, "elapsed_time": "1:14:17", "remaining_time": "0:44:58", "throughput": 5490.37, "total_tokens": 24474096} {"current_steps": 40160, "total_steps": 64460, "loss": 0.2354, "lr": 3.739543161348784e-06, "epoch": 12.460440583307477, "percentage": 62.3, "elapsed_time": "1:14:18", "remaining_time": "0:44:57", "throughput": 5490.32, "total_tokens": 24476336} {"current_steps": 40165, "total_steps": 64460, "loss": 0.203, "lr": 3.7382331229293435e-06, "epoch": 12.461991932981695, "percentage": 62.31, "elapsed_time": "1:14:18", "remaining_time": "0:44:56", "throughput": 5490.29, "total_tokens": 24478704} {"current_steps": 40170, "total_steps": 64460, "loss": 0.203, "lr": 3.7369231770123572e-06, "epoch": 12.46354328265591, "percentage": 62.32, "elapsed_time": "1:14:19", "remaining_time": "0:44:56", "throughput": 5490.52, "total_tokens": 24483344} {"current_steps": 40175, "total_steps": 64460, "loss": 0.207, "lr": 3.7356133236938585e-06, "epoch": 12.465094632330127, "percentage": 62.33, "elapsed_time": "1:14:19", "remaining_time": "0:44:55", "throughput": 5490.52, "total_tokens": 24485936} {"current_steps": 40180, "total_steps": 64460, "loss": 0.2244, "lr": 3.7343035630698754e-06, "epoch": 12.466645982004344, "percentage": 62.33, "elapsed_time": "1:14:20", "remaining_time": "0:44:55", "throughput": 5490.43, "total_tokens": 24488080} {"current_steps": 40185, "total_steps": 64460, "loss": 0.202, "lr": 3.73299389523643e-06, "epoch": 12.46819733167856, "percentage": 62.34, "elapsed_time": "1:14:20", "remaining_time": "0:44:54", "throughput": 5490.57, "total_tokens": 24491792} {"current_steps": 40190, "total_steps": 64460, "loss": 0.1915, "lr": 3.7316843202895346e-06, "epoch": 12.469748681352776, "percentage": 62.35, "elapsed_time": "1:14:21", "remaining_time": "0:44:54", "throughput": 5490.59, "total_tokens": 24494672} {"current_steps": 40195, "total_steps": 64460, "loss": 0.2487, "lr": 3.7303748383251987e-06, "epoch": 12.471300031026994, "percentage": 62.36, "elapsed_time": "1:14:21", "remaining_time": "0:44:53", "throughput": 5490.69, "total_tokens": 24497872} {"current_steps": 40200, "total_steps": 64460, "loss": 0.2436, "lr": 3.7290654494394207e-06, "epoch": 12.47285138070121, "percentage": 62.36, "elapsed_time": "1:14:22", "remaining_time": "0:44:52", "throughput": 5490.85, "total_tokens": 24501968} {"current_steps": 40205, "total_steps": 64460, "loss": 0.2, "lr": 3.7277561537281957e-06, "epoch": 12.474402730375427, "percentage": 62.37, "elapsed_time": "1:14:22", "remaining_time": "0:44:52", "throughput": 5490.87, "total_tokens": 24504944} {"current_steps": 40210, "total_steps": 64460, "loss": 0.238, "lr": 3.7264469512875107e-06, "epoch": 12.475954080049643, "percentage": 62.38, "elapsed_time": "1:14:23", "remaining_time": "0:44:51", "throughput": 5490.86, "total_tokens": 24507824} {"current_steps": 40215, "total_steps": 64460, "loss": 0.2261, "lr": 3.7251378422133455e-06, "epoch": 12.477505429723859, "percentage": 62.39, "elapsed_time": "1:14:23", "remaining_time": "0:44:51", "throughput": 5490.78, "total_tokens": 24510192} {"current_steps": 40220, "total_steps": 64460, "loss": 0.2002, "lr": 3.723828826601672e-06, "epoch": 12.479056779398077, "percentage": 62.4, "elapsed_time": "1:14:24", "remaining_time": "0:44:50", "throughput": 5490.79, "total_tokens": 24512848} {"current_steps": 40225, "total_steps": 64460, "loss": 0.2267, "lr": 3.722519904548459e-06, "epoch": 12.480608129072293, "percentage": 62.4, "elapsed_time": "1:14:24", "remaining_time": "0:44:50", "throughput": 5490.8, "total_tokens": 24515600} {"current_steps": 40230, "total_steps": 64460, "loss": 0.2158, "lr": 3.721211076149664e-06, "epoch": 12.48215947874651, "percentage": 62.41, "elapsed_time": "1:14:25", "remaining_time": "0:44:49", "throughput": 5490.82, "total_tokens": 24518416} {"current_steps": 40235, "total_steps": 64460, "loss": 0.2448, "lr": 3.7199023415012403e-06, "epoch": 12.483710828420726, "percentage": 62.42, "elapsed_time": "1:14:25", "remaining_time": "0:44:48", "throughput": 5490.97, "total_tokens": 24522000} {"current_steps": 40240, "total_steps": 64460, "loss": 0.2134, "lr": 3.7185937006991337e-06, "epoch": 12.485262178094942, "percentage": 62.43, "elapsed_time": "1:14:26", "remaining_time": "0:44:48", "throughput": 5491.13, "total_tokens": 24528112} {"current_steps": 40245, "total_steps": 64460, "loss": 0.2203, "lr": 3.717285153839283e-06, "epoch": 12.48681352776916, "percentage": 62.43, "elapsed_time": "1:14:27", "remaining_time": "0:44:47", "throughput": 5491.05, "total_tokens": 24530352} {"current_steps": 40250, "total_steps": 64460, "loss": 0.2046, "lr": 3.7159767010176197e-06, "epoch": 12.488364877443376, "percentage": 62.44, "elapsed_time": "1:14:27", "remaining_time": "0:44:47", "throughput": 5491.11, "total_tokens": 24533200} {"current_steps": 40255, "total_steps": 64460, "loss": 0.2104, "lr": 3.7146683423300696e-06, "epoch": 12.489916227117593, "percentage": 62.45, "elapsed_time": "1:14:28", "remaining_time": "0:44:46", "throughput": 5491.2, "total_tokens": 24536688} {"current_steps": 40260, "total_steps": 64460, "loss": 0.2852, "lr": 3.7133600778725496e-06, "epoch": 12.491467576791809, "percentage": 62.46, "elapsed_time": "1:14:28", "remaining_time": "0:44:46", "throughput": 5491.36, "total_tokens": 24540880} {"current_steps": 40265, "total_steps": 64460, "loss": 0.1955, "lr": 3.7120519077409727e-06, "epoch": 12.493018926466025, "percentage": 62.47, "elapsed_time": "1:14:29", "remaining_time": "0:44:45", "throughput": 5491.32, "total_tokens": 24543440} {"current_steps": 40270, "total_steps": 64460, "loss": 0.2469, "lr": 3.710743832031243e-06, "epoch": 12.494570276140243, "percentage": 62.47, "elapsed_time": "1:14:29", "remaining_time": "0:44:45", "throughput": 5491.25, "total_tokens": 24545776} {"current_steps": 40275, "total_steps": 64460, "loss": 0.2118, "lr": 3.709435850839257e-06, "epoch": 12.496121625814459, "percentage": 62.48, "elapsed_time": "1:14:30", "remaining_time": "0:44:44", "throughput": 5491.21, "total_tokens": 24548304} {"current_steps": 40280, "total_steps": 64460, "loss": 0.2415, "lr": 3.7081279642609064e-06, "epoch": 12.497672975488674, "percentage": 62.49, "elapsed_time": "1:14:31", "remaining_time": "0:44:43", "throughput": 5491.2, "total_tokens": 24551248} {"current_steps": 40285, "total_steps": 64460, "loss": 0.2136, "lr": 3.706820172392074e-06, "epoch": 12.499224325162892, "percentage": 62.5, "elapsed_time": "1:14:31", "remaining_time": "0:44:43", "throughput": 5491.27, "total_tokens": 24554544} {"current_steps": 40290, "total_steps": 64460, "loss": 0.2355, "lr": 3.705512475328636e-06, "epoch": 12.500775674837108, "percentage": 62.5, "elapsed_time": "1:14:32", "remaining_time": "0:44:42", "throughput": 5491.28, "total_tokens": 24557456} {"current_steps": 40295, "total_steps": 64460, "loss": 0.172, "lr": 3.7042048731664626e-06, "epoch": 12.502327024511326, "percentage": 62.51, "elapsed_time": "1:14:32", "remaining_time": "0:44:42", "throughput": 5491.33, "total_tokens": 24560464} {"current_steps": 40300, "total_steps": 64460, "loss": 0.2086, "lr": 3.702897366001417e-06, "epoch": 12.503878374185541, "percentage": 62.52, "elapsed_time": "1:14:33", "remaining_time": "0:44:41", "throughput": 5491.45, "total_tokens": 24564240} {"current_steps": 40305, "total_steps": 64460, "loss": 0.2747, "lr": 3.701589953929354e-06, "epoch": 12.505429723859757, "percentage": 62.53, "elapsed_time": "1:14:33", "remaining_time": "0:44:41", "throughput": 5491.53, "total_tokens": 24567344} {"current_steps": 40310, "total_steps": 64460, "loss": 0.1974, "lr": 3.700282637046123e-06, "epoch": 12.506981073533975, "percentage": 62.53, "elapsed_time": "1:14:34", "remaining_time": "0:44:40", "throughput": 5491.44, "total_tokens": 24569648} {"current_steps": 40315, "total_steps": 64460, "loss": 0.1885, "lr": 3.6989754154475654e-06, "epoch": 12.508532423208191, "percentage": 62.54, "elapsed_time": "1:14:34", "remaining_time": "0:44:39", "throughput": 5491.46, "total_tokens": 24572624} {"current_steps": 40320, "total_steps": 64460, "loss": 0.2495, "lr": 3.6976682892295157e-06, "epoch": 12.510083772882407, "percentage": 62.55, "elapsed_time": "1:14:35", "remaining_time": "0:44:39", "throughput": 5491.55, "total_tokens": 24575824} {"current_steps": 40325, "total_steps": 64460, "loss": 0.1906, "lr": 3.6963612584878035e-06, "epoch": 12.511635122556624, "percentage": 62.56, "elapsed_time": "1:14:35", "remaining_time": "0:44:38", "throughput": 5491.64, "total_tokens": 24579728} {"current_steps": 40330, "total_steps": 64460, "loss": 0.2347, "lr": 3.695054323318248e-06, "epoch": 12.51318647223084, "percentage": 62.57, "elapsed_time": "1:14:36", "remaining_time": "0:44:38", "throughput": 5491.67, "total_tokens": 24583056} {"current_steps": 40335, "total_steps": 64460, "loss": 0.1944, "lr": 3.6937474838166637e-06, "epoch": 12.514737821905058, "percentage": 62.57, "elapsed_time": "1:14:36", "remaining_time": "0:44:37", "throughput": 5491.69, "total_tokens": 24585904} {"current_steps": 40340, "total_steps": 64460, "loss": 0.1826, "lr": 3.692440740078857e-06, "epoch": 12.516289171579274, "percentage": 62.58, "elapsed_time": "1:14:37", "remaining_time": "0:44:37", "throughput": 5491.88, "total_tokens": 24590128} {"current_steps": 40345, "total_steps": 64460, "loss": 0.1987, "lr": 3.691134092200628e-06, "epoch": 12.51784052125349, "percentage": 62.59, "elapsed_time": "1:14:38", "remaining_time": "0:44:36", "throughput": 5492.06, "total_tokens": 24594128} {"current_steps": 40350, "total_steps": 64460, "loss": 0.2306, "lr": 3.6898275402777694e-06, "epoch": 12.519391870927707, "percentage": 62.6, "elapsed_time": "1:14:38", "remaining_time": "0:44:36", "throughput": 5491.95, "total_tokens": 24596560} {"current_steps": 40355, "total_steps": 64460, "loss": 0.1862, "lr": 3.688521084406067e-06, "epoch": 12.520943220601923, "percentage": 62.6, "elapsed_time": "1:14:39", "remaining_time": "0:44:35", "throughput": 5492.07, "total_tokens": 24600272} {"current_steps": 40360, "total_steps": 64460, "loss": 0.1833, "lr": 3.6872147246812983e-06, "epoch": 12.522494570276141, "percentage": 62.61, "elapsed_time": "1:14:39", "remaining_time": "0:44:34", "throughput": 5492.15, "total_tokens": 24603504} {"current_steps": 40365, "total_steps": 64460, "loss": 0.2039, "lr": 3.685908461199237e-06, "epoch": 12.524045919950357, "percentage": 62.62, "elapsed_time": "1:14:40", "remaining_time": "0:44:34", "throughput": 5492.26, "total_tokens": 24607088} {"current_steps": 40370, "total_steps": 64460, "loss": 0.2075, "lr": 3.684602294055647e-06, "epoch": 12.525597269624573, "percentage": 62.63, "elapsed_time": "1:14:40", "remaining_time": "0:44:33", "throughput": 5492.23, "total_tokens": 24609584} {"current_steps": 40375, "total_steps": 64460, "loss": 0.189, "lr": 3.6832962233462843e-06, "epoch": 12.52714861929879, "percentage": 62.64, "elapsed_time": "1:14:41", "remaining_time": "0:44:33", "throughput": 5492.35, "total_tokens": 24613008} {"current_steps": 40380, "total_steps": 64460, "loss": 0.1768, "lr": 3.6819902491669004e-06, "epoch": 12.528699968973006, "percentage": 62.64, "elapsed_time": "1:14:41", "remaining_time": "0:44:32", "throughput": 5492.25, "total_tokens": 24615152} {"current_steps": 40385, "total_steps": 64460, "loss": 0.2144, "lr": 3.6806843716132395e-06, "epoch": 12.530251318647224, "percentage": 62.65, "elapsed_time": "1:14:42", "remaining_time": "0:44:32", "throughput": 5492.4, "total_tokens": 24618896} {"current_steps": 40390, "total_steps": 64460, "loss": 0.1943, "lr": 3.6793785907810376e-06, "epoch": 12.53180266832144, "percentage": 62.66, "elapsed_time": "1:14:43", "remaining_time": "0:44:31", "throughput": 5492.5, "total_tokens": 24623152} {"current_steps": 40395, "total_steps": 64460, "loss": 0.2277, "lr": 3.6780729067660225e-06, "epoch": 12.533354017995656, "percentage": 62.67, "elapsed_time": "1:14:43", "remaining_time": "0:44:31", "throughput": 5492.53, "total_tokens": 24626192} {"current_steps": 40400, "total_steps": 64460, "loss": 0.2141, "lr": 3.6767673196639186e-06, "epoch": 12.534905367669873, "percentage": 62.67, "elapsed_time": "1:14:44", "remaining_time": "0:44:30", "throughput": 5492.43, "total_tokens": 24628336} {"current_steps": 40405, "total_steps": 64460, "loss": 0.2471, "lr": 3.6754618295704387e-06, "epoch": 12.53645671734409, "percentage": 62.68, "elapsed_time": "1:14:44", "remaining_time": "0:44:29", "throughput": 5492.38, "total_tokens": 24630640} {"current_steps": 40410, "total_steps": 64460, "loss": 0.221, "lr": 3.674156436581292e-06, "epoch": 12.538008067018305, "percentage": 62.69, "elapsed_time": "1:14:45", "remaining_time": "0:44:29", "throughput": 5492.31, "total_tokens": 24633104} {"current_steps": 40415, "total_steps": 64460, "loss": 0.2397, "lr": 3.6728511407921785e-06, "epoch": 12.539559416692523, "percentage": 62.7, "elapsed_time": "1:14:45", "remaining_time": "0:44:28", "throughput": 5492.25, "total_tokens": 24635632} {"current_steps": 40420, "total_steps": 64460, "loss": 0.2235, "lr": 3.671545942298792e-06, "epoch": 12.541110766366739, "percentage": 62.71, "elapsed_time": "1:14:46", "remaining_time": "0:44:28", "throughput": 5492.34, "total_tokens": 24638800} {"current_steps": 40425, "total_steps": 64460, "loss": 0.2386, "lr": 3.67024084119682e-06, "epoch": 12.542662116040956, "percentage": 62.71, "elapsed_time": "1:14:46", "remaining_time": "0:44:27", "throughput": 5492.28, "total_tokens": 24641200} {"current_steps": 40430, "total_steps": 64460, "loss": 0.2626, "lr": 3.6689358375819404e-06, "epoch": 12.544213465715172, "percentage": 62.72, "elapsed_time": "1:14:47", "remaining_time": "0:44:26", "throughput": 5492.35, "total_tokens": 24644272} {"current_steps": 40435, "total_steps": 64460, "loss": 0.2692, "lr": 3.667630931549826e-06, "epoch": 12.545764815389388, "percentage": 62.73, "elapsed_time": "1:14:47", "remaining_time": "0:44:26", "throughput": 5492.51, "total_tokens": 24648208} {"current_steps": 40440, "total_steps": 64460, "loss": 0.2123, "lr": 3.666326123196141e-06, "epoch": 12.547316165063606, "percentage": 62.74, "elapsed_time": "1:14:48", "remaining_time": "0:44:25", "throughput": 5492.51, "total_tokens": 24651024} {"current_steps": 40445, "total_steps": 64460, "loss": 0.177, "lr": 3.6650214126165458e-06, "epoch": 12.548867514737822, "percentage": 62.74, "elapsed_time": "1:14:48", "remaining_time": "0:44:25", "throughput": 5492.65, "total_tokens": 24654704} {"current_steps": 40450, "total_steps": 64460, "loss": 0.2638, "lr": 3.6637167999066893e-06, "epoch": 12.550418864412038, "percentage": 62.75, "elapsed_time": "1:14:49", "remaining_time": "0:44:24", "throughput": 5492.6, "total_tokens": 24657136} {"current_steps": 40455, "total_steps": 64460, "loss": 0.2334, "lr": 3.6624122851622147e-06, "epoch": 12.551970214086255, "percentage": 62.76, "elapsed_time": "1:14:49", "remaining_time": "0:44:24", "throughput": 5492.68, "total_tokens": 24660528} {"current_steps": 40460, "total_steps": 64460, "loss": 0.229, "lr": 3.6611078684787593e-06, "epoch": 12.553521563760471, "percentage": 62.77, "elapsed_time": "1:14:50", "remaining_time": "0:44:23", "throughput": 5492.63, "total_tokens": 24662864} {"current_steps": 40465, "total_steps": 64460, "loss": 0.255, "lr": 3.6598035499519525e-06, "epoch": 12.555072913434689, "percentage": 62.78, "elapsed_time": "1:14:50", "remaining_time": "0:44:22", "throughput": 5492.7, "total_tokens": 24665968} {"current_steps": 40470, "total_steps": 64460, "loss": 0.2261, "lr": 3.6584993296774152e-06, "epoch": 12.556624263108905, "percentage": 62.78, "elapsed_time": "1:14:51", "remaining_time": "0:44:22", "throughput": 5492.74, "total_tokens": 24668720} {"current_steps": 40475, "total_steps": 64460, "loss": 0.2262, "lr": 3.6571952077507634e-06, "epoch": 12.55817561278312, "percentage": 62.79, "elapsed_time": "1:14:51", "remaining_time": "0:44:21", "throughput": 5492.76, "total_tokens": 24671760} {"current_steps": 40480, "total_steps": 64460, "loss": 0.1816, "lr": 3.6558911842676038e-06, "epoch": 12.559726962457338, "percentage": 62.8, "elapsed_time": "1:14:52", "remaining_time": "0:44:21", "throughput": 5492.86, "total_tokens": 24675600} {"current_steps": 40485, "total_steps": 64460, "loss": 0.209, "lr": 3.6545872593235367e-06, "epoch": 12.561278312131554, "percentage": 62.81, "elapsed_time": "1:14:52", "remaining_time": "0:44:20", "throughput": 5492.81, "total_tokens": 24677968} {"current_steps": 40490, "total_steps": 64460, "loss": 0.1992, "lr": 3.6532834330141554e-06, "epoch": 12.562829661805772, "percentage": 62.81, "elapsed_time": "1:14:53", "remaining_time": "0:44:20", "throughput": 5492.82, "total_tokens": 24680720} {"current_steps": 40495, "total_steps": 64460, "loss": 0.1919, "lr": 3.651979705435047e-06, "epoch": 12.564381011479988, "percentage": 62.82, "elapsed_time": "1:14:53", "remaining_time": "0:44:19", "throughput": 5492.94, "total_tokens": 24684528} {"current_steps": 40500, "total_steps": 64460, "loss": 0.231, "lr": 3.650676076681787e-06, "epoch": 12.565932361154204, "percentage": 62.83, "elapsed_time": "1:14:54", "remaining_time": "0:44:18", "throughput": 5492.86, "total_tokens": 24686800} {"current_steps": 40505, "total_steps": 64460, "loss": 0.2361, "lr": 3.649372546849951e-06, "epoch": 12.567483710828421, "percentage": 62.84, "elapsed_time": "1:14:54", "remaining_time": "0:44:18", "throughput": 5492.86, "total_tokens": 24689776} {"current_steps": 40510, "total_steps": 64460, "loss": 0.2299, "lr": 3.6480691160351002e-06, "epoch": 12.569035060502637, "percentage": 62.85, "elapsed_time": "1:14:55", "remaining_time": "0:44:17", "throughput": 5492.85, "total_tokens": 24692432} {"current_steps": 40515, "total_steps": 64460, "loss": 0.2269, "lr": 3.6467657843327933e-06, "epoch": 12.570586410176855, "percentage": 62.85, "elapsed_time": "1:14:55", "remaining_time": "0:44:17", "throughput": 5492.83, "total_tokens": 24695088} {"current_steps": 40520, "total_steps": 64460, "loss": 0.2145, "lr": 3.6454625518385777e-06, "epoch": 12.57213775985107, "percentage": 62.86, "elapsed_time": "1:14:56", "remaining_time": "0:44:16", "throughput": 5492.95, "total_tokens": 24699216} {"current_steps": 40525, "total_steps": 64460, "loss": 0.2122, "lr": 3.6441594186479986e-06, "epoch": 12.573689109525287, "percentage": 62.87, "elapsed_time": "1:14:57", "remaining_time": "0:44:16", "throughput": 5493.12, "total_tokens": 24703888} {"current_steps": 40530, "total_steps": 64460, "loss": 0.2274, "lr": 3.642856384856589e-06, "epoch": 12.575240459199504, "percentage": 62.88, "elapsed_time": "1:14:57", "remaining_time": "0:44:15", "throughput": 5493.16, "total_tokens": 24706640} {"current_steps": 40535, "total_steps": 64460, "loss": 0.2049, "lr": 3.6415534505598777e-06, "epoch": 12.57679180887372, "percentage": 62.88, "elapsed_time": "1:14:58", "remaining_time": "0:44:14", "throughput": 5493.23, "total_tokens": 24709744} {"current_steps": 40540, "total_steps": 64460, "loss": 0.1865, "lr": 3.6402506158533846e-06, "epoch": 12.578343158547936, "percentage": 62.89, "elapsed_time": "1:14:58", "remaining_time": "0:44:14", "throughput": 5493.13, "total_tokens": 24712080} {"current_steps": 40545, "total_steps": 64460, "loss": 0.2641, "lr": 3.6389478808326233e-06, "epoch": 12.579894508222154, "percentage": 62.9, "elapsed_time": "1:14:59", "remaining_time": "0:44:13", "throughput": 5493.22, "total_tokens": 24715216} {"current_steps": 40550, "total_steps": 64460, "loss": 0.2218, "lr": 3.6376452455931e-06, "epoch": 12.58144585789637, "percentage": 62.91, "elapsed_time": "1:14:59", "remaining_time": "0:44:13", "throughput": 5493.14, "total_tokens": 24717520} {"current_steps": 40555, "total_steps": 64460, "loss": 0.2353, "lr": 3.6363427102303124e-06, "epoch": 12.582997207570587, "percentage": 62.91, "elapsed_time": "1:15:00", "remaining_time": "0:44:12", "throughput": 5493.15, "total_tokens": 24720304} {"current_steps": 40560, "total_steps": 64460, "loss": 0.238, "lr": 3.635040274839751e-06, "epoch": 12.584548557244803, "percentage": 62.92, "elapsed_time": "1:15:00", "remaining_time": "0:44:12", "throughput": 5493.26, "total_tokens": 24724240} {"current_steps": 40565, "total_steps": 64460, "loss": 0.1706, "lr": 3.6337379395169024e-06, "epoch": 12.586099906919019, "percentage": 62.93, "elapsed_time": "1:15:01", "remaining_time": "0:44:11", "throughput": 5493.27, "total_tokens": 24727152} {"current_steps": 40570, "total_steps": 64460, "loss": 0.2172, "lr": 3.632435704357242e-06, "epoch": 12.587651256593237, "percentage": 62.94, "elapsed_time": "1:15:01", "remaining_time": "0:44:10", "throughput": 5493.24, "total_tokens": 24729776} {"current_steps": 40575, "total_steps": 64460, "loss": 0.1807, "lr": 3.631133569456239e-06, "epoch": 12.589202606267452, "percentage": 62.95, "elapsed_time": "1:15:02", "remaining_time": "0:44:10", "throughput": 5493.15, "total_tokens": 24731920} {"current_steps": 40580, "total_steps": 64460, "loss": 0.1937, "lr": 3.6298315349093545e-06, "epoch": 12.590753955941668, "percentage": 62.95, "elapsed_time": "1:15:02", "remaining_time": "0:44:09", "throughput": 5493.23, "total_tokens": 24735056} {"current_steps": 40585, "total_steps": 64460, "loss": 0.2092, "lr": 3.628529600812044e-06, "epoch": 12.592305305615886, "percentage": 62.96, "elapsed_time": "1:15:03", "remaining_time": "0:44:09", "throughput": 5493.19, "total_tokens": 24737488} {"current_steps": 40590, "total_steps": 64460, "loss": 0.2162, "lr": 3.6272277672597543e-06, "epoch": 12.593856655290102, "percentage": 62.97, "elapsed_time": "1:15:03", "remaining_time": "0:44:08", "throughput": 5493.26, "total_tokens": 24740400} {"current_steps": 40595, "total_steps": 64460, "loss": 0.229, "lr": 3.6259260343479252e-06, "epoch": 12.59540800496432, "percentage": 62.98, "elapsed_time": "1:15:04", "remaining_time": "0:44:08", "throughput": 5493.36, "total_tokens": 24744176} {"current_steps": 40600, "total_steps": 64460, "loss": 0.2115, "lr": 3.6246244021719902e-06, "epoch": 12.596959354638535, "percentage": 62.98, "elapsed_time": "1:15:04", "remaining_time": "0:44:07", "throughput": 5493.29, "total_tokens": 24746608} {"current_steps": 40605, "total_steps": 64460, "loss": 0.1707, "lr": 3.6233228708273723e-06, "epoch": 12.598510704312751, "percentage": 62.99, "elapsed_time": "1:15:05", "remaining_time": "0:44:06", "throughput": 5493.36, "total_tokens": 24749904} {"current_steps": 40610, "total_steps": 64460, "loss": 0.2563, "lr": 3.6220214404094905e-06, "epoch": 12.600062053986969, "percentage": 63.0, "elapsed_time": "1:15:05", "remaining_time": "0:44:06", "throughput": 5493.46, "total_tokens": 24753456} {"current_steps": 40615, "total_steps": 64460, "loss": 0.2204, "lr": 3.6207201110137547e-06, "epoch": 12.601613403661185, "percentage": 63.01, "elapsed_time": "1:15:06", "remaining_time": "0:44:05", "throughput": 5493.43, "total_tokens": 24755920} {"current_steps": 40620, "total_steps": 64460, "loss": 0.2321, "lr": 3.6194188827355673e-06, "epoch": 12.603164753335403, "percentage": 63.02, "elapsed_time": "1:15:06", "remaining_time": "0:44:05", "throughput": 5493.42, "total_tokens": 24758448} {"current_steps": 40625, "total_steps": 64460, "loss": 0.2052, "lr": 3.618117755670325e-06, "epoch": 12.604716103009618, "percentage": 63.02, "elapsed_time": "1:15:07", "remaining_time": "0:44:04", "throughput": 5493.49, "total_tokens": 24761584} {"current_steps": 40630, "total_steps": 64460, "loss": 0.179, "lr": 3.616816729913416e-06, "epoch": 12.606267452683834, "percentage": 63.03, "elapsed_time": "1:15:08", "remaining_time": "0:44:04", "throughput": 5493.67, "total_tokens": 24766288} {"current_steps": 40635, "total_steps": 64460, "loss": 0.256, "lr": 3.615515805560219e-06, "epoch": 12.607818802358052, "percentage": 63.04, "elapsed_time": "1:15:08", "remaining_time": "0:44:03", "throughput": 5493.78, "total_tokens": 24769904} {"current_steps": 40640, "total_steps": 64460, "loss": 0.1893, "lr": 3.6142149827061087e-06, "epoch": 12.609370152032268, "percentage": 63.05, "elapsed_time": "1:15:09", "remaining_time": "0:44:02", "throughput": 5493.79, "total_tokens": 24773136} {"current_steps": 40645, "total_steps": 64460, "loss": 0.2017, "lr": 3.6129142614464496e-06, "epoch": 12.610921501706486, "percentage": 63.05, "elapsed_time": "1:15:09", "remaining_time": "0:44:02", "throughput": 5493.8, "total_tokens": 24775760} {"current_steps": 40650, "total_steps": 64460, "loss": 0.2319, "lr": 3.6116136418766017e-06, "epoch": 12.612472851380701, "percentage": 63.06, "elapsed_time": "1:15:10", "remaining_time": "0:44:01", "throughput": 5493.69, "total_tokens": 24778192} {"current_steps": 40655, "total_steps": 64460, "loss": 0.2132, "lr": 3.6103131240919142e-06, "epoch": 12.614024201054917, "percentage": 63.07, "elapsed_time": "1:15:10", "remaining_time": "0:44:01", "throughput": 5493.69, "total_tokens": 24781296} {"current_steps": 40660, "total_steps": 64460, "loss": 0.23, "lr": 3.6090127081877313e-06, "epoch": 12.615575550729135, "percentage": 63.08, "elapsed_time": "1:15:11", "remaining_time": "0:44:00", "throughput": 5493.65, "total_tokens": 24783792} {"current_steps": 40665, "total_steps": 64460, "loss": 0.202, "lr": 3.6077123942593882e-06, "epoch": 12.61712690040335, "percentage": 63.09, "elapsed_time": "1:15:11", "remaining_time": "0:44:00", "throughput": 5493.58, "total_tokens": 24786256} {"current_steps": 40670, "total_steps": 64460, "loss": 0.2077, "lr": 3.6064121824022147e-06, "epoch": 12.618678250077567, "percentage": 63.09, "elapsed_time": "1:15:12", "remaining_time": "0:43:59", "throughput": 5493.72, "total_tokens": 24791216} {"current_steps": 40675, "total_steps": 64460, "loss": 0.2071, "lr": 3.6051120727115303e-06, "epoch": 12.620229599751784, "percentage": 63.1, "elapsed_time": "1:15:13", "remaining_time": "0:43:59", "throughput": 5493.71, "total_tokens": 24793808} {"current_steps": 40680, "total_steps": 64460, "loss": 0.2456, "lr": 3.6038120652826474e-06, "epoch": 12.621780949426, "percentage": 63.11, "elapsed_time": "1:15:13", "remaining_time": "0:43:58", "throughput": 5493.7, "total_tokens": 24796496} {"current_steps": 40685, "total_steps": 64460, "loss": 0.2224, "lr": 3.6025121602108747e-06, "epoch": 12.623332299100218, "percentage": 63.12, "elapsed_time": "1:15:14", "remaining_time": "0:43:57", "throughput": 5493.7, "total_tokens": 24799344} {"current_steps": 40690, "total_steps": 64460, "loss": 0.2065, "lr": 3.60121235759151e-06, "epoch": 12.624883648774434, "percentage": 63.12, "elapsed_time": "1:15:14", "remaining_time": "0:43:57", "throughput": 5493.78, "total_tokens": 24803024} {"current_steps": 40695, "total_steps": 64460, "loss": 0.2211, "lr": 3.599912657519843e-06, "epoch": 12.62643499844865, "percentage": 63.13, "elapsed_time": "1:15:15", "remaining_time": "0:43:56", "throughput": 5493.9, "total_tokens": 24806672} {"current_steps": 40700, "total_steps": 64460, "loss": 0.2178, "lr": 3.5986130600911578e-06, "epoch": 12.627986348122867, "percentage": 63.14, "elapsed_time": "1:15:15", "remaining_time": "0:43:56", "throughput": 5493.86, "total_tokens": 24809168} {"current_steps": 40705, "total_steps": 64460, "loss": 0.1965, "lr": 3.5973135654007307e-06, "epoch": 12.629537697797083, "percentage": 63.15, "elapsed_time": "1:15:16", "remaining_time": "0:43:55", "throughput": 5493.83, "total_tokens": 24811760} {"current_steps": 40710, "total_steps": 64460, "loss": 0.2107, "lr": 3.596014173543829e-06, "epoch": 12.6310890474713, "percentage": 63.16, "elapsed_time": "1:15:16", "remaining_time": "0:43:55", "throughput": 5493.81, "total_tokens": 24814192} {"current_steps": 40715, "total_steps": 64460, "loss": 0.2466, "lr": 3.594714884615712e-06, "epoch": 12.632640397145517, "percentage": 63.16, "elapsed_time": "1:15:17", "remaining_time": "0:43:54", "throughput": 5493.85, "total_tokens": 24817040} {"current_steps": 40720, "total_steps": 64460, "loss": 0.2328, "lr": 3.5934156987116374e-06, "epoch": 12.634191746819733, "percentage": 63.17, "elapsed_time": "1:15:17", "remaining_time": "0:43:53", "throughput": 5493.9, "total_tokens": 24820080} {"current_steps": 40725, "total_steps": 64460, "loss": 0.2425, "lr": 3.5921166159268486e-06, "epoch": 12.63574309649395, "percentage": 63.18, "elapsed_time": "1:15:18", "remaining_time": "0:43:53", "throughput": 5493.76, "total_tokens": 24822160} {"current_steps": 40730, "total_steps": 64460, "loss": 0.216, "lr": 3.5908176363565827e-06, "epoch": 12.637294446168166, "percentage": 63.19, "elapsed_time": "1:15:18", "remaining_time": "0:43:52", "throughput": 5493.87, "total_tokens": 24825456} {"current_steps": 40735, "total_steps": 64460, "loss": 0.1976, "lr": 3.5895187600960726e-06, "epoch": 12.638845795842382, "percentage": 63.19, "elapsed_time": "1:15:19", "remaining_time": "0:43:52", "throughput": 5493.84, "total_tokens": 24828080} {"current_steps": 40740, "total_steps": 64460, "loss": 0.2421, "lr": 3.5882199872405387e-06, "epoch": 12.6403971455166, "percentage": 63.2, "elapsed_time": "1:15:19", "remaining_time": "0:43:51", "throughput": 5493.8, "total_tokens": 24831600} {"current_steps": 40745, "total_steps": 64460, "loss": 0.248, "lr": 3.586921317885199e-06, "epoch": 12.641948495190816, "percentage": 63.21, "elapsed_time": "1:15:20", "remaining_time": "0:43:51", "throughput": 5493.88, "total_tokens": 24834640} {"current_steps": 40750, "total_steps": 64460, "loss": 0.2132, "lr": 3.5856227521252596e-06, "epoch": 12.643499844865033, "percentage": 63.22, "elapsed_time": "1:15:20", "remaining_time": "0:43:50", "throughput": 5493.92, "total_tokens": 24837680} {"current_steps": 40755, "total_steps": 64460, "loss": 0.2316, "lr": 3.5843242900559206e-06, "epoch": 12.64505119453925, "percentage": 63.23, "elapsed_time": "1:15:21", "remaining_time": "0:43:49", "throughput": 5493.91, "total_tokens": 24840048} {"current_steps": 40760, "total_steps": 64460, "loss": 0.2227, "lr": 3.583025931772376e-06, "epoch": 12.646602544213465, "percentage": 63.23, "elapsed_time": "1:15:21", "remaining_time": "0:43:49", "throughput": 5493.86, "total_tokens": 24842288} {"current_steps": 40765, "total_steps": 64460, "loss": 0.2407, "lr": 3.5817276773698094e-06, "epoch": 12.648153893887683, "percentage": 63.24, "elapsed_time": "1:15:22", "remaining_time": "0:43:48", "throughput": 5493.94, "total_tokens": 24845520} {"current_steps": 40770, "total_steps": 64460, "loss": 0.198, "lr": 3.5804295269433984e-06, "epoch": 12.649705243561899, "percentage": 63.25, "elapsed_time": "1:15:22", "remaining_time": "0:43:48", "throughput": 5494.06, "total_tokens": 24848944} {"current_steps": 40775, "total_steps": 64460, "loss": 0.2337, "lr": 3.5791314805883144e-06, "epoch": 12.651256593236116, "percentage": 63.26, "elapsed_time": "1:15:23", "remaining_time": "0:43:47", "throughput": 5494.19, "total_tokens": 24852784} {"current_steps": 40780, "total_steps": 64460, "loss": 0.1931, "lr": 3.577833538399718e-06, "epoch": 12.652807942910332, "percentage": 63.26, "elapsed_time": "1:15:24", "remaining_time": "0:43:47", "throughput": 5494.41, "total_tokens": 24858032} {"current_steps": 40785, "total_steps": 64460, "loss": 0.2111, "lr": 3.5765357004727645e-06, "epoch": 12.654359292584548, "percentage": 63.27, "elapsed_time": "1:15:24", "remaining_time": "0:43:46", "throughput": 5494.44, "total_tokens": 24860816} {"current_steps": 40790, "total_steps": 64460, "loss": 0.2119, "lr": 3.5752379669026004e-06, "epoch": 12.655910642258766, "percentage": 63.28, "elapsed_time": "1:15:25", "remaining_time": "0:43:45", "throughput": 5494.52, "total_tokens": 24863792} {"current_steps": 40795, "total_steps": 64460, "loss": 0.2357, "lr": 3.573940337784365e-06, "epoch": 12.657461991932982, "percentage": 63.29, "elapsed_time": "1:15:25", "remaining_time": "0:43:45", "throughput": 5494.53, "total_tokens": 24866320} {"current_steps": 40800, "total_steps": 64460, "loss": 0.2103, "lr": 3.5726428132131902e-06, "epoch": 12.659013341607197, "percentage": 63.3, "elapsed_time": "1:15:26", "remaining_time": "0:43:44", "throughput": 5494.59, "total_tokens": 24869616} {"current_steps": 40805, "total_steps": 64460, "loss": 0.2249, "lr": 3.5713453932841997e-06, "epoch": 12.660564691281415, "percentage": 63.3, "elapsed_time": "1:15:26", "remaining_time": "0:43:44", "throughput": 5494.51, "total_tokens": 24872272} {"current_steps": 40810, "total_steps": 64460, "loss": 0.2335, "lr": 3.5700480780925094e-06, "epoch": 12.662116040955631, "percentage": 63.31, "elapsed_time": "1:15:27", "remaining_time": "0:43:43", "throughput": 5494.55, "total_tokens": 24875536} {"current_steps": 40815, "total_steps": 64460, "loss": 0.1842, "lr": 3.5687508677332284e-06, "epoch": 12.663667390629849, "percentage": 63.32, "elapsed_time": "1:15:27", "remaining_time": "0:43:43", "throughput": 5494.51, "total_tokens": 24878288} {"current_steps": 40820, "total_steps": 64460, "loss": 0.19, "lr": 3.5674537623014564e-06, "epoch": 12.665218740304065, "percentage": 63.33, "elapsed_time": "1:15:28", "remaining_time": "0:43:42", "throughput": 5494.71, "total_tokens": 24882704} {"current_steps": 40825, "total_steps": 64460, "loss": 0.1852, "lr": 3.5661567618922887e-06, "epoch": 12.66677008997828, "percentage": 63.33, "elapsed_time": "1:15:28", "remaining_time": "0:43:41", "throughput": 5494.68, "total_tokens": 24885296} {"current_steps": 40830, "total_steps": 64460, "loss": 0.2175, "lr": 3.564859866600808e-06, "epoch": 12.668321439652498, "percentage": 63.34, "elapsed_time": "1:15:29", "remaining_time": "0:43:41", "throughput": 5494.67, "total_tokens": 24888208} {"current_steps": 40835, "total_steps": 64460, "loss": 0.1893, "lr": 3.5635630765220945e-06, "epoch": 12.669872789326714, "percentage": 63.35, "elapsed_time": "1:15:30", "remaining_time": "0:43:40", "throughput": 5494.68, "total_tokens": 24891248} {"current_steps": 40840, "total_steps": 64460, "loss": 0.1991, "lr": 3.5622663917512178e-06, "epoch": 12.67142413900093, "percentage": 63.36, "elapsed_time": "1:15:30", "remaining_time": "0:43:40", "throughput": 5494.73, "total_tokens": 24894288} {"current_steps": 40845, "total_steps": 64460, "loss": 0.2267, "lr": 3.5609698123832397e-06, "epoch": 12.672975488675148, "percentage": 63.36, "elapsed_time": "1:15:31", "remaining_time": "0:43:39", "throughput": 5494.77, "total_tokens": 24897200} {"current_steps": 40850, "total_steps": 64460, "loss": 0.2723, "lr": 3.559673338513215e-06, "epoch": 12.674526838349363, "percentage": 63.37, "elapsed_time": "1:15:31", "remaining_time": "0:43:39", "throughput": 5494.77, "total_tokens": 24900368} {"current_steps": 40855, "total_steps": 64460, "loss": 0.2637, "lr": 3.5583769702361907e-06, "epoch": 12.676078188023581, "percentage": 63.38, "elapsed_time": "1:15:32", "remaining_time": "0:43:38", "throughput": 5494.84, "total_tokens": 24903664} {"current_steps": 40860, "total_steps": 64460, "loss": 0.2421, "lr": 3.557080707647206e-06, "epoch": 12.677629537697797, "percentage": 63.39, "elapsed_time": "1:15:32", "remaining_time": "0:43:38", "throughput": 5494.9, "total_tokens": 24906896} {"current_steps": 40865, "total_steps": 64460, "loss": 0.2146, "lr": 3.5557845508412926e-06, "epoch": 12.679180887372013, "percentage": 63.4, "elapsed_time": "1:15:33", "remaining_time": "0:43:37", "throughput": 5494.93, "total_tokens": 24909680} {"current_steps": 40870, "total_steps": 64460, "loss": 0.1744, "lr": 3.554488499913473e-06, "epoch": 12.68073223704623, "percentage": 63.4, "elapsed_time": "1:15:33", "remaining_time": "0:43:36", "throughput": 5494.95, "total_tokens": 24913264} {"current_steps": 40875, "total_steps": 64460, "loss": 0.2265, "lr": 3.553192554958764e-06, "epoch": 12.682283586720446, "percentage": 63.41, "elapsed_time": "1:15:34", "remaining_time": "0:43:36", "throughput": 5494.99, "total_tokens": 24916368} {"current_steps": 40880, "total_steps": 64460, "loss": 0.2298, "lr": 3.551896716072173e-06, "epoch": 12.683834936394664, "percentage": 63.42, "elapsed_time": "1:15:34", "remaining_time": "0:43:35", "throughput": 5495.0, "total_tokens": 24919280} {"current_steps": 40885, "total_steps": 64460, "loss": 0.2499, "lr": 3.550600983348701e-06, "epoch": 12.68538628606888, "percentage": 63.43, "elapsed_time": "1:15:35", "remaining_time": "0:43:35", "throughput": 5495.04, "total_tokens": 24922352} {"current_steps": 40890, "total_steps": 64460, "loss": 0.2577, "lr": 3.54930535688334e-06, "epoch": 12.686937635743096, "percentage": 63.43, "elapsed_time": "1:15:35", "remaining_time": "0:43:34", "throughput": 5495.06, "total_tokens": 24925296} {"current_steps": 40895, "total_steps": 64460, "loss": 0.2005, "lr": 3.548009836771076e-06, "epoch": 12.688488985417314, "percentage": 63.44, "elapsed_time": "1:15:36", "remaining_time": "0:43:34", "throughput": 5495.01, "total_tokens": 24927728} {"current_steps": 40900, "total_steps": 64460, "loss": 0.2546, "lr": 3.546714423106884e-06, "epoch": 12.69004033509153, "percentage": 63.45, "elapsed_time": "1:15:36", "remaining_time": "0:43:33", "throughput": 5495.04, "total_tokens": 24930736} {"current_steps": 40905, "total_steps": 64460, "loss": 0.2483, "lr": 3.5454191159857354e-06, "epoch": 12.691591684765747, "percentage": 63.46, "elapsed_time": "1:15:37", "remaining_time": "0:43:32", "throughput": 5494.96, "total_tokens": 24932912} {"current_steps": 40910, "total_steps": 64460, "loss": 0.2302, "lr": 3.54412391550259e-06, "epoch": 12.693143034439963, "percentage": 63.47, "elapsed_time": "1:15:37", "remaining_time": "0:43:32", "throughput": 5494.97, "total_tokens": 24935920} {"current_steps": 40915, "total_steps": 64460, "loss": 0.2577, "lr": 3.542828821752402e-06, "epoch": 12.694694384114179, "percentage": 63.47, "elapsed_time": "1:15:38", "remaining_time": "0:43:31", "throughput": 5495.0, "total_tokens": 24939152} {"current_steps": 40920, "total_steps": 64460, "loss": 0.2116, "lr": 3.5415338348301164e-06, "epoch": 12.696245733788396, "percentage": 63.48, "elapsed_time": "1:15:38", "remaining_time": "0:43:31", "throughput": 5494.85, "total_tokens": 24941040} {"current_steps": 40925, "total_steps": 64460, "loss": 0.2433, "lr": 3.540238954830672e-06, "epoch": 12.697797083462612, "percentage": 63.49, "elapsed_time": "1:15:39", "remaining_time": "0:43:30", "throughput": 5494.86, "total_tokens": 24943632} {"current_steps": 40930, "total_steps": 64460, "loss": 0.2287, "lr": 3.5389441818489983e-06, "epoch": 12.699348433136828, "percentage": 63.5, "elapsed_time": "1:15:39", "remaining_time": "0:43:29", "throughput": 5494.88, "total_tokens": 24946480} {"current_steps": 40935, "total_steps": 64460, "loss": 0.2228, "lr": 3.537649515980017e-06, "epoch": 12.700899782811046, "percentage": 63.5, "elapsed_time": "1:15:40", "remaining_time": "0:43:29", "throughput": 5494.91, "total_tokens": 24949360} {"current_steps": 40940, "total_steps": 64460, "loss": 0.1994, "lr": 3.536354957318644e-06, "epoch": 12.702451132485262, "percentage": 63.51, "elapsed_time": "1:15:40", "remaining_time": "0:43:28", "throughput": 5494.77, "total_tokens": 24951536} {"current_steps": 40945, "total_steps": 64460, "loss": 0.2253, "lr": 3.535060505959784e-06, "epoch": 12.70400248215948, "percentage": 63.52, "elapsed_time": "1:15:41", "remaining_time": "0:43:28", "throughput": 5494.85, "total_tokens": 24955024} {"current_steps": 40950, "total_steps": 64460, "loss": 0.2078, "lr": 3.5337661619983354e-06, "epoch": 12.705553831833695, "percentage": 63.53, "elapsed_time": "1:15:42", "remaining_time": "0:43:27", "throughput": 5494.89, "total_tokens": 24957936} {"current_steps": 40955, "total_steps": 64460, "loss": 0.2578, "lr": 3.5324719255291916e-06, "epoch": 12.707105181507911, "percentage": 63.54, "elapsed_time": "1:15:42", "remaining_time": "0:43:27", "throughput": 5494.97, "total_tokens": 24961264} {"current_steps": 40960, "total_steps": 64460, "loss": 0.2303, "lr": 3.5311777966472332e-06, "epoch": 12.708656531182129, "percentage": 63.54, "elapsed_time": "1:15:43", "remaining_time": "0:43:26", "throughput": 5494.79, "total_tokens": 24963184} {"current_steps": 40965, "total_steps": 64460, "loss": 0.2105, "lr": 3.529883775447336e-06, "epoch": 12.710207880856345, "percentage": 63.55, "elapsed_time": "1:15:43", "remaining_time": "0:43:25", "throughput": 5494.74, "total_tokens": 24965648} {"current_steps": 40970, "total_steps": 64460, "loss": 0.2647, "lr": 3.5285898620243664e-06, "epoch": 12.71175923053056, "percentage": 63.56, "elapsed_time": "1:15:44", "remaining_time": "0:43:25", "throughput": 5494.55, "total_tokens": 24967824} {"current_steps": 40975, "total_steps": 64460, "loss": 0.2087, "lr": 3.527296056473185e-06, "epoch": 12.713310580204778, "percentage": 63.57, "elapsed_time": "1:15:44", "remaining_time": "0:43:24", "throughput": 5494.5, "total_tokens": 24970320} {"current_steps": 40980, "total_steps": 64460, "loss": 0.2567, "lr": 3.526002358888641e-06, "epoch": 12.714861929878994, "percentage": 63.57, "elapsed_time": "1:15:45", "remaining_time": "0:43:24", "throughput": 5494.46, "total_tokens": 24973072} {"current_steps": 40985, "total_steps": 64460, "loss": 0.2265, "lr": 3.524708769365579e-06, "epoch": 12.716413279553212, "percentage": 63.58, "elapsed_time": "1:15:45", "remaining_time": "0:43:23", "throughput": 5494.5, "total_tokens": 24976048} {"current_steps": 40990, "total_steps": 64460, "loss": 0.2302, "lr": 3.523415287998835e-06, "epoch": 12.717964629227428, "percentage": 63.59, "elapsed_time": "1:15:46", "remaining_time": "0:43:23", "throughput": 5494.52, "total_tokens": 24978864} {"current_steps": 40995, "total_steps": 64460, "loss": 0.203, "lr": 3.5221219148832353e-06, "epoch": 12.719515978901644, "percentage": 63.6, "elapsed_time": "1:15:46", "remaining_time": "0:43:22", "throughput": 5494.58, "total_tokens": 24982096} {"current_steps": 41000, "total_steps": 64460, "loss": 0.252, "lr": 3.5208286501136e-06, "epoch": 12.721067328575861, "percentage": 63.61, "elapsed_time": "1:15:47", "remaining_time": "0:43:21", "throughput": 5494.73, "total_tokens": 24986512} {"current_steps": 41005, "total_steps": 64460, "loss": 0.2868, "lr": 3.5195354937847403e-06, "epoch": 12.722618678250077, "percentage": 63.61, "elapsed_time": "1:15:47", "remaining_time": "0:43:21", "throughput": 5494.71, "total_tokens": 24989232} {"current_steps": 41010, "total_steps": 64460, "loss": 0.2016, "lr": 3.51824244599146e-06, "epoch": 12.724170027924295, "percentage": 63.62, "elapsed_time": "1:15:48", "remaining_time": "0:43:20", "throughput": 5494.68, "total_tokens": 24992112} {"current_steps": 41015, "total_steps": 64460, "loss": 0.1854, "lr": 3.5169495068285553e-06, "epoch": 12.72572137759851, "percentage": 63.63, "elapsed_time": "1:15:48", "remaining_time": "0:43:20", "throughput": 5494.69, "total_tokens": 24994896} {"current_steps": 41020, "total_steps": 64460, "loss": 0.2501, "lr": 3.515656676390814e-06, "epoch": 12.727272727272727, "percentage": 63.64, "elapsed_time": "1:15:49", "remaining_time": "0:43:19", "throughput": 5494.68, "total_tokens": 24997744} {"current_steps": 41025, "total_steps": 64460, "loss": 0.191, "lr": 3.514363954773016e-06, "epoch": 12.728824076946944, "percentage": 63.64, "elapsed_time": "1:15:49", "remaining_time": "0:43:19", "throughput": 5494.59, "total_tokens": 25000176} {"current_steps": 41030, "total_steps": 64460, "loss": 0.2158, "lr": 3.5130713420699314e-06, "epoch": 12.73037542662116, "percentage": 63.65, "elapsed_time": "1:15:50", "remaining_time": "0:43:18", "throughput": 5494.49, "total_tokens": 25002704} {"current_steps": 41035, "total_steps": 64460, "loss": 0.209, "lr": 3.5117788383763262e-06, "epoch": 12.731926776295378, "percentage": 63.66, "elapsed_time": "1:15:51", "remaining_time": "0:43:18", "throughput": 5494.62, "total_tokens": 25006896} {"current_steps": 41040, "total_steps": 64460, "loss": 0.1961, "lr": 3.5104864437869556e-06, "epoch": 12.733478125969594, "percentage": 63.67, "elapsed_time": "1:15:51", "remaining_time": "0:43:17", "throughput": 5494.57, "total_tokens": 25009392} {"current_steps": 41045, "total_steps": 64460, "loss": 0.2185, "lr": 3.5091941583965673e-06, "epoch": 12.73502947564381, "percentage": 63.68, "elapsed_time": "1:15:52", "remaining_time": "0:43:16", "throughput": 5494.63, "total_tokens": 25012848} {"current_steps": 41050, "total_steps": 64460, "loss": 0.1971, "lr": 3.5079019822999e-06, "epoch": 12.736580825318027, "percentage": 63.68, "elapsed_time": "1:15:52", "remaining_time": "0:43:16", "throughput": 5494.68, "total_tokens": 25016144} {"current_steps": 41055, "total_steps": 64460, "loss": 0.2006, "lr": 3.5066099155916865e-06, "epoch": 12.738132174992243, "percentage": 63.69, "elapsed_time": "1:15:53", "remaining_time": "0:43:15", "throughput": 5494.77, "total_tokens": 25019312} {"current_steps": 41060, "total_steps": 64460, "loss": 0.1832, "lr": 3.505317958366651e-06, "epoch": 12.739683524666459, "percentage": 63.7, "elapsed_time": "1:15:53", "remaining_time": "0:43:15", "throughput": 5494.84, "total_tokens": 25022544} {"current_steps": 41065, "total_steps": 64460, "loss": 0.2647, "lr": 3.5040261107195095e-06, "epoch": 12.741234874340677, "percentage": 63.71, "elapsed_time": "1:15:54", "remaining_time": "0:43:14", "throughput": 5494.85, "total_tokens": 25025648} {"current_steps": 41070, "total_steps": 64460, "loss": 0.2309, "lr": 3.502734372744967e-06, "epoch": 12.742786224014893, "percentage": 63.71, "elapsed_time": "1:15:54", "remaining_time": "0:43:14", "throughput": 5495.01, "total_tokens": 25029616} {"current_steps": 41075, "total_steps": 64460, "loss": 0.1819, "lr": 3.501442744537727e-06, "epoch": 12.74433757368911, "percentage": 63.72, "elapsed_time": "1:15:55", "remaining_time": "0:43:13", "throughput": 5495.01, "total_tokens": 25032464} {"current_steps": 41080, "total_steps": 64460, "loss": 0.2039, "lr": 3.5001512261924788e-06, "epoch": 12.745888923363326, "percentage": 63.73, "elapsed_time": "1:15:56", "remaining_time": "0:43:12", "throughput": 5495.02, "total_tokens": 25035312} {"current_steps": 41085, "total_steps": 64460, "loss": 0.2483, "lr": 3.498859817803907e-06, "epoch": 12.747440273037542, "percentage": 63.74, "elapsed_time": "1:15:56", "remaining_time": "0:43:12", "throughput": 5494.87, "total_tokens": 25037456} {"current_steps": 41090, "total_steps": 64460, "loss": 0.2352, "lr": 3.4975685194666864e-06, "epoch": 12.74899162271176, "percentage": 63.74, "elapsed_time": "1:15:57", "remaining_time": "0:43:11", "throughput": 5494.83, "total_tokens": 25040240} {"current_steps": 41095, "total_steps": 64460, "loss": 0.2022, "lr": 3.496277331275485e-06, "epoch": 12.750542972385976, "percentage": 63.75, "elapsed_time": "1:15:57", "remaining_time": "0:43:11", "throughput": 5494.79, "total_tokens": 25042704} {"current_steps": 41100, "total_steps": 64460, "loss": 0.2412, "lr": 3.4949862533249625e-06, "epoch": 12.752094322060191, "percentage": 63.76, "elapsed_time": "1:15:58", "remaining_time": "0:43:10", "throughput": 5494.78, "total_tokens": 25045328} {"current_steps": 41105, "total_steps": 64460, "loss": 0.2383, "lr": 3.4936952857097686e-06, "epoch": 12.753645671734409, "percentage": 63.77, "elapsed_time": "1:15:58", "remaining_time": "0:43:10", "throughput": 5494.73, "total_tokens": 25047824} {"current_steps": 41110, "total_steps": 64460, "loss": 0.2432, "lr": 3.4924044285245482e-06, "epoch": 12.755197021408625, "percentage": 63.78, "elapsed_time": "1:15:59", "remaining_time": "0:43:09", "throughput": 5494.81, "total_tokens": 25051344} {"current_steps": 41115, "total_steps": 64460, "loss": 0.1948, "lr": 3.491113681863936e-06, "epoch": 12.756748371082843, "percentage": 63.78, "elapsed_time": "1:15:59", "remaining_time": "0:43:08", "throughput": 5494.79, "total_tokens": 25054160} {"current_steps": 41120, "total_steps": 64460, "loss": 0.2475, "lr": 3.489823045822558e-06, "epoch": 12.758299720757059, "percentage": 63.79, "elapsed_time": "1:16:00", "remaining_time": "0:43:08", "throughput": 5494.78, "total_tokens": 25057104} {"current_steps": 41125, "total_steps": 64460, "loss": 0.2067, "lr": 3.4885325204950344e-06, "epoch": 12.759851070431274, "percentage": 63.8, "elapsed_time": "1:16:00", "remaining_time": "0:43:07", "throughput": 5494.89, "total_tokens": 25060720} {"current_steps": 41130, "total_steps": 64460, "loss": 0.2395, "lr": 3.4872421059759742e-06, "epoch": 12.761402420105492, "percentage": 63.81, "elapsed_time": "1:16:01", "remaining_time": "0:43:07", "throughput": 5494.87, "total_tokens": 25063248} {"current_steps": 41135, "total_steps": 64460, "loss": 0.2607, "lr": 3.4859518023599827e-06, "epoch": 12.762953769779708, "percentage": 63.81, "elapsed_time": "1:16:01", "remaining_time": "0:43:06", "throughput": 5494.9, "total_tokens": 25066576} {"current_steps": 41140, "total_steps": 64460, "loss": 0.2055, "lr": 3.484661609741653e-06, "epoch": 12.764505119453926, "percentage": 63.82, "elapsed_time": "1:16:02", "remaining_time": "0:43:06", "throughput": 5494.88, "total_tokens": 25069552} {"current_steps": 41145, "total_steps": 64460, "loss": 0.214, "lr": 3.4833715282155716e-06, "epoch": 12.766056469128142, "percentage": 63.83, "elapsed_time": "1:16:02", "remaining_time": "0:43:05", "throughput": 5494.88, "total_tokens": 25072336} {"current_steps": 41150, "total_steps": 64460, "loss": 0.2174, "lr": 3.4820815578763166e-06, "epoch": 12.767607818802357, "percentage": 63.84, "elapsed_time": "1:16:03", "remaining_time": "0:43:05", "throughput": 5494.75, "total_tokens": 25074832} {"current_steps": 41155, "total_steps": 64460, "loss": 0.2031, "lr": 3.4807916988184587e-06, "epoch": 12.769159168476575, "percentage": 63.85, "elapsed_time": "1:16:03", "remaining_time": "0:43:04", "throughput": 5494.74, "total_tokens": 25077392} {"current_steps": 41160, "total_steps": 64460, "loss": 0.2094, "lr": 3.479501951136559e-06, "epoch": 12.770710518150791, "percentage": 63.85, "elapsed_time": "1:16:04", "remaining_time": "0:43:03", "throughput": 5494.7, "total_tokens": 25079824} {"current_steps": 41165, "total_steps": 64460, "loss": 0.2409, "lr": 3.4782123149251717e-06, "epoch": 12.772261867825009, "percentage": 63.86, "elapsed_time": "1:16:04", "remaining_time": "0:43:03", "throughput": 5494.63, "total_tokens": 25082352} {"current_steps": 41170, "total_steps": 64460, "loss": 0.2145, "lr": 3.476922790278843e-06, "epoch": 12.773813217499224, "percentage": 63.87, "elapsed_time": "1:16:05", "remaining_time": "0:43:02", "throughput": 5494.58, "total_tokens": 25085424} {"current_steps": 41175, "total_steps": 64460, "loss": 0.1939, "lr": 3.475633377292109e-06, "epoch": 12.77536456717344, "percentage": 63.88, "elapsed_time": "1:16:05", "remaining_time": "0:43:02", "throughput": 5494.5, "total_tokens": 25087728} {"current_steps": 41180, "total_steps": 64460, "loss": 0.2105, "lr": 3.474344076059499e-06, "epoch": 12.776915916847658, "percentage": 63.88, "elapsed_time": "1:16:06", "remaining_time": "0:43:01", "throughput": 5494.52, "total_tokens": 25090960} {"current_steps": 41185, "total_steps": 64460, "loss": 0.2038, "lr": 3.4730548866755366e-06, "epoch": 12.778467266521874, "percentage": 63.89, "elapsed_time": "1:16:07", "remaining_time": "0:43:01", "throughput": 5494.64, "total_tokens": 25094832} {"current_steps": 41190, "total_steps": 64460, "loss": 0.2894, "lr": 3.47176580923473e-06, "epoch": 12.78001861619609, "percentage": 63.9, "elapsed_time": "1:16:07", "remaining_time": "0:43:00", "throughput": 5494.67, "total_tokens": 25097616} {"current_steps": 41195, "total_steps": 64460, "loss": 0.2305, "lr": 3.470476843831588e-06, "epoch": 12.781569965870307, "percentage": 63.91, "elapsed_time": "1:16:08", "remaining_time": "0:42:59", "throughput": 5494.6, "total_tokens": 25099920} {"current_steps": 41200, "total_steps": 64460, "loss": 0.2136, "lr": 3.4691879905606062e-06, "epoch": 12.783121315544523, "percentage": 63.92, "elapsed_time": "1:16:08", "remaining_time": "0:42:59", "throughput": 5494.71, "total_tokens": 25103728} {"current_steps": 41205, "total_steps": 64460, "loss": 0.2275, "lr": 3.467899249516272e-06, "epoch": 12.784672665218741, "percentage": 63.92, "elapsed_time": "1:16:09", "remaining_time": "0:42:58", "throughput": 5494.84, "total_tokens": 25107280} {"current_steps": 41210, "total_steps": 64460, "loss": 0.1755, "lr": 3.466610620793065e-06, "epoch": 12.786224014892957, "percentage": 63.93, "elapsed_time": "1:16:09", "remaining_time": "0:42:58", "throughput": 5494.93, "total_tokens": 25110544} {"current_steps": 41215, "total_steps": 64460, "loss": 0.2082, "lr": 3.465322104485458e-06, "epoch": 12.787775364567173, "percentage": 63.94, "elapsed_time": "1:16:10", "remaining_time": "0:42:57", "throughput": 5494.92, "total_tokens": 25113264} {"current_steps": 41220, "total_steps": 64460, "loss": 0.2412, "lr": 3.4640337006879145e-06, "epoch": 12.78932671424139, "percentage": 63.95, "elapsed_time": "1:16:10", "remaining_time": "0:42:57", "throughput": 5494.99, "total_tokens": 25116784} {"current_steps": 41225, "total_steps": 64460, "loss": 0.2199, "lr": 3.4627454094948885e-06, "epoch": 12.790878063915606, "percentage": 63.95, "elapsed_time": "1:16:11", "remaining_time": "0:42:56", "throughput": 5494.97, "total_tokens": 25119408} {"current_steps": 41230, "total_steps": 64460, "loss": 0.184, "lr": 3.4614572310008286e-06, "epoch": 12.792429413589822, "percentage": 63.96, "elapsed_time": "1:16:11", "remaining_time": "0:42:55", "throughput": 5494.92, "total_tokens": 25121968} {"current_steps": 41235, "total_steps": 64460, "loss": 0.2451, "lr": 3.460169165300172e-06, "epoch": 12.79398076326404, "percentage": 63.97, "elapsed_time": "1:16:12", "remaining_time": "0:42:55", "throughput": 5494.92, "total_tokens": 25124944} {"current_steps": 41240, "total_steps": 64460, "loss": 0.258, "lr": 3.4588812124873506e-06, "epoch": 12.795532112938256, "percentage": 63.98, "elapsed_time": "1:16:12", "remaining_time": "0:42:54", "throughput": 5494.92, "total_tokens": 25127728} {"current_steps": 41245, "total_steps": 64460, "loss": 0.2058, "lr": 3.457593372656785e-06, "epoch": 12.797083462612473, "percentage": 63.99, "elapsed_time": "1:16:13", "remaining_time": "0:42:54", "throughput": 5494.98, "total_tokens": 25130960} {"current_steps": 41250, "total_steps": 64460, "loss": 0.2048, "lr": 3.45630564590289e-06, "epoch": 12.79863481228669, "percentage": 63.99, "elapsed_time": "1:16:14", "remaining_time": "0:42:53", "throughput": 5495.1, "total_tokens": 25134672} {"current_steps": 41255, "total_steps": 64460, "loss": 0.2046, "lr": 3.455018032320071e-06, "epoch": 12.800186161960905, "percentage": 64.0, "elapsed_time": "1:16:14", "remaining_time": "0:42:53", "throughput": 5495.09, "total_tokens": 25137360} {"current_steps": 41260, "total_steps": 64460, "loss": 0.2497, "lr": 3.453730532002727e-06, "epoch": 12.801737511635123, "percentage": 64.01, "elapsed_time": "1:16:15", "remaining_time": "0:42:52", "throughput": 5495.1, "total_tokens": 25140624} {"current_steps": 41265, "total_steps": 64460, "loss": 0.2064, "lr": 3.4524431450452446e-06, "epoch": 12.803288861309339, "percentage": 64.02, "elapsed_time": "1:16:15", "remaining_time": "0:42:51", "throughput": 5494.99, "total_tokens": 25143152} {"current_steps": 41270, "total_steps": 64460, "loss": 0.2106, "lr": 3.4511558715420056e-06, "epoch": 12.804840210983556, "percentage": 64.02, "elapsed_time": "1:16:16", "remaining_time": "0:42:51", "throughput": 5494.97, "total_tokens": 25145968} {"current_steps": 41275, "total_steps": 64460, "loss": 0.2317, "lr": 3.4498687115873825e-06, "epoch": 12.806391560657772, "percentage": 64.03, "elapsed_time": "1:16:16", "remaining_time": "0:42:50", "throughput": 5495.12, "total_tokens": 25150128} {"current_steps": 41280, "total_steps": 64460, "loss": 0.1892, "lr": 3.448581665275739e-06, "epoch": 12.807942910331988, "percentage": 64.04, "elapsed_time": "1:16:17", "remaining_time": "0:42:50", "throughput": 5495.13, "total_tokens": 25152912} {"current_steps": 41285, "total_steps": 64460, "loss": 0.2482, "lr": 3.447294732701431e-06, "epoch": 12.809494260006206, "percentage": 64.05, "elapsed_time": "1:16:17", "remaining_time": "0:42:49", "throughput": 5495.17, "total_tokens": 25155760} {"current_steps": 41290, "total_steps": 64460, "loss": 0.1859, "lr": 3.446007913958806e-06, "epoch": 12.811045609680422, "percentage": 64.06, "elapsed_time": "1:16:18", "remaining_time": "0:42:49", "throughput": 5495.19, "total_tokens": 25158576} {"current_steps": 41295, "total_steps": 64460, "loss": 0.2066, "lr": 3.444721209142201e-06, "epoch": 12.81259695935464, "percentage": 64.06, "elapsed_time": "1:16:18", "remaining_time": "0:42:48", "throughput": 5495.3, "total_tokens": 25162352} {"current_steps": 41300, "total_steps": 64460, "loss": 0.2427, "lr": 3.44343461834595e-06, "epoch": 12.814148309028855, "percentage": 64.07, "elapsed_time": "1:16:19", "remaining_time": "0:42:48", "throughput": 5495.56, "total_tokens": 25168304} {"current_steps": 41305, "total_steps": 64460, "loss": 0.242, "lr": 3.442148141664375e-06, "epoch": 12.815699658703071, "percentage": 64.08, "elapsed_time": "1:16:20", "remaining_time": "0:42:47", "throughput": 5495.61, "total_tokens": 25171984} {"current_steps": 41310, "total_steps": 64460, "loss": 0.2305, "lr": 3.440861779191788e-06, "epoch": 12.817251008377289, "percentage": 64.09, "elapsed_time": "1:16:20", "remaining_time": "0:42:47", "throughput": 5495.65, "total_tokens": 25175440} {"current_steps": 41315, "total_steps": 64460, "loss": 0.182, "lr": 3.439575531022496e-06, "epoch": 12.818802358051505, "percentage": 64.09, "elapsed_time": "1:16:21", "remaining_time": "0:42:46", "throughput": 5495.65, "total_tokens": 25178096} {"current_steps": 41320, "total_steps": 64460, "loss": 0.1959, "lr": 3.4382893972507956e-06, "epoch": 12.82035370772572, "percentage": 64.1, "elapsed_time": "1:16:22", "remaining_time": "0:42:46", "throughput": 5495.67, "total_tokens": 25181200} {"current_steps": 41325, "total_steps": 64460, "loss": 0.2104, "lr": 3.437003377970976e-06, "epoch": 12.821905057399938, "percentage": 64.11, "elapsed_time": "1:16:22", "remaining_time": "0:42:45", "throughput": 5495.6, "total_tokens": 25183504} {"current_steps": 41330, "total_steps": 64460, "loss": 0.1927, "lr": 3.4357174732773175e-06, "epoch": 12.823456407074154, "percentage": 64.12, "elapsed_time": "1:16:23", "remaining_time": "0:42:44", "throughput": 5495.64, "total_tokens": 25186544} {"current_steps": 41335, "total_steps": 64460, "loss": 0.2055, "lr": 3.4344316832640913e-06, "epoch": 12.825007756748372, "percentage": 64.13, "elapsed_time": "1:16:23", "remaining_time": "0:42:44", "throughput": 5495.72, "total_tokens": 25189904} {"current_steps": 41340, "total_steps": 64460, "loss": 0.228, "lr": 3.433146008025562e-06, "epoch": 12.826559106422588, "percentage": 64.13, "elapsed_time": "1:16:24", "remaining_time": "0:42:43", "throughput": 5495.91, "total_tokens": 25194192} {"current_steps": 41345, "total_steps": 64460, "loss": 0.2085, "lr": 3.4318604476559846e-06, "epoch": 12.828110456096804, "percentage": 64.14, "elapsed_time": "1:16:24", "remaining_time": "0:42:43", "throughput": 5496.03, "total_tokens": 25197840} {"current_steps": 41350, "total_steps": 64460, "loss": 0.1792, "lr": 3.4305750022496066e-06, "epoch": 12.829661805771021, "percentage": 64.15, "elapsed_time": "1:16:25", "remaining_time": "0:42:42", "throughput": 5496.01, "total_tokens": 25200304} {"current_steps": 41355, "total_steps": 64460, "loss": 0.2214, "lr": 3.4292896719006656e-06, "epoch": 12.831213155445237, "percentage": 64.16, "elapsed_time": "1:16:25", "remaining_time": "0:42:42", "throughput": 5496.07, "total_tokens": 25203312} {"current_steps": 41360, "total_steps": 64460, "loss": 0.2143, "lr": 3.428004456703392e-06, "epoch": 12.832764505119453, "percentage": 64.16, "elapsed_time": "1:16:26", "remaining_time": "0:42:41", "throughput": 5496.0, "total_tokens": 25206000} {"current_steps": 41365, "total_steps": 64460, "loss": 0.2109, "lr": 3.426719356752006e-06, "epoch": 12.83431585479367, "percentage": 64.17, "elapsed_time": "1:16:26", "remaining_time": "0:42:40", "throughput": 5496.02, "total_tokens": 25208816} {"current_steps": 41370, "total_steps": 64460, "loss": 0.2373, "lr": 3.4254343721407223e-06, "epoch": 12.835867204467887, "percentage": 64.18, "elapsed_time": "1:16:27", "remaining_time": "0:42:40", "throughput": 5496.13, "total_tokens": 25212368} {"current_steps": 41375, "total_steps": 64460, "loss": 0.2199, "lr": 3.4241495029637445e-06, "epoch": 12.837418554142104, "percentage": 64.19, "elapsed_time": "1:16:27", "remaining_time": "0:42:39", "throughput": 5496.21, "total_tokens": 25215696} {"current_steps": 41380, "total_steps": 64460, "loss": 0.2553, "lr": 3.422864749315269e-06, "epoch": 12.83896990381632, "percentage": 64.19, "elapsed_time": "1:16:28", "remaining_time": "0:42:39", "throughput": 5496.29, "total_tokens": 25219152} {"current_steps": 41385, "total_steps": 64460, "loss": 0.2267, "lr": 3.4215801112894836e-06, "epoch": 12.840521253490536, "percentage": 64.2, "elapsed_time": "1:16:28", "remaining_time": "0:42:38", "throughput": 5496.18, "total_tokens": 25221200} {"current_steps": 41390, "total_steps": 64460, "loss": 0.2151, "lr": 3.420295588980567e-06, "epoch": 12.842072603164754, "percentage": 64.21, "elapsed_time": "1:16:29", "remaining_time": "0:42:38", "throughput": 5496.16, "total_tokens": 25223920} {"current_steps": 41395, "total_steps": 64460, "loss": 0.2455, "lr": 3.41901118248269e-06, "epoch": 12.84362395283897, "percentage": 64.22, "elapsed_time": "1:16:29", "remaining_time": "0:42:37", "throughput": 5496.14, "total_tokens": 25226512} {"current_steps": 41400, "total_steps": 64460, "loss": 0.1937, "lr": 3.4177268918900154e-06, "epoch": 12.845175302513187, "percentage": 64.23, "elapsed_time": "1:16:30", "remaining_time": "0:42:36", "throughput": 5496.22, "total_tokens": 25229872} {"current_steps": 41405, "total_steps": 64460, "loss": 0.1943, "lr": 3.4164427172966964e-06, "epoch": 12.846726652187403, "percentage": 64.23, "elapsed_time": "1:16:30", "remaining_time": "0:42:36", "throughput": 5496.28, "total_tokens": 25232944} {"current_steps": 41410, "total_steps": 64460, "loss": 0.2512, "lr": 3.415158658796879e-06, "epoch": 12.848278001861619, "percentage": 64.24, "elapsed_time": "1:16:31", "remaining_time": "0:42:35", "throughput": 5496.22, "total_tokens": 25235248} {"current_steps": 41415, "total_steps": 64460, "loss": 0.1959, "lr": 3.4138747164846987e-06, "epoch": 12.849829351535837, "percentage": 64.25, "elapsed_time": "1:16:32", "remaining_time": "0:42:35", "throughput": 5496.28, "total_tokens": 25238928} {"current_steps": 41420, "total_steps": 64460, "loss": 0.2179, "lr": 3.4125908904542836e-06, "epoch": 12.851380701210052, "percentage": 64.26, "elapsed_time": "1:16:32", "remaining_time": "0:42:34", "throughput": 5496.3, "total_tokens": 25241776} {"current_steps": 41425, "total_steps": 64460, "loss": 0.2348, "lr": 3.411307180799755e-06, "epoch": 12.85293205088427, "percentage": 64.26, "elapsed_time": "1:16:32", "remaining_time": "0:42:33", "throughput": 5496.21, "total_tokens": 25243920} {"current_steps": 41430, "total_steps": 64460, "loss": 0.2142, "lr": 3.4100235876152226e-06, "epoch": 12.854483400558486, "percentage": 64.27, "elapsed_time": "1:16:33", "remaining_time": "0:42:33", "throughput": 5496.11, "total_tokens": 25245968} {"current_steps": 41435, "total_steps": 64460, "loss": 0.1603, "lr": 3.4087401109947895e-06, "epoch": 12.856034750232702, "percentage": 64.28, "elapsed_time": "1:16:34", "remaining_time": "0:42:32", "throughput": 5496.2, "total_tokens": 25249744} {"current_steps": 41440, "total_steps": 64460, "loss": 0.1962, "lr": 3.4074567510325497e-06, "epoch": 12.85758609990692, "percentage": 64.29, "elapsed_time": "1:16:34", "remaining_time": "0:42:32", "throughput": 5496.06, "total_tokens": 25251984} {"current_steps": 41445, "total_steps": 64460, "loss": 0.2402, "lr": 3.4061735078225887e-06, "epoch": 12.859137449581135, "percentage": 64.3, "elapsed_time": "1:16:35", "remaining_time": "0:42:31", "throughput": 5496.15, "total_tokens": 25255408} {"current_steps": 41450, "total_steps": 64460, "loss": 0.1696, "lr": 3.404890381458983e-06, "epoch": 12.860688799255351, "percentage": 64.3, "elapsed_time": "1:16:35", "remaining_time": "0:42:31", "throughput": 5496.23, "total_tokens": 25258800} {"current_steps": 41455, "total_steps": 64460, "loss": 0.2323, "lr": 3.4036073720358e-06, "epoch": 12.862240148929569, "percentage": 64.31, "elapsed_time": "1:16:36", "remaining_time": "0:42:30", "throughput": 5496.18, "total_tokens": 25261168} {"current_steps": 41460, "total_steps": 64460, "loss": 0.1742, "lr": 3.4023244796471022e-06, "epoch": 12.863791498603785, "percentage": 64.32, "elapsed_time": "1:16:36", "remaining_time": "0:42:30", "throughput": 5496.19, "total_tokens": 25264112} {"current_steps": 41465, "total_steps": 64460, "loss": 0.204, "lr": 3.4010417043869393e-06, "epoch": 12.865342848278003, "percentage": 64.33, "elapsed_time": "1:16:37", "remaining_time": "0:42:29", "throughput": 5496.12, "total_tokens": 25266352} {"current_steps": 41470, "total_steps": 64460, "loss": 0.2233, "lr": 3.3997590463493536e-06, "epoch": 12.866894197952218, "percentage": 64.33, "elapsed_time": "1:16:37", "remaining_time": "0:42:28", "throughput": 5495.97, "total_tokens": 25268560} {"current_steps": 41475, "total_steps": 64460, "loss": 0.2717, "lr": 3.39847650562838e-06, "epoch": 12.868445547626434, "percentage": 64.34, "elapsed_time": "1:16:38", "remaining_time": "0:42:28", "throughput": 5496.03, "total_tokens": 25271376} {"current_steps": 41480, "total_steps": 64460, "loss": 0.2378, "lr": 3.397194082318043e-06, "epoch": 12.869996897300652, "percentage": 64.35, "elapsed_time": "1:16:38", "remaining_time": "0:42:27", "throughput": 5496.03, "total_tokens": 25273968} {"current_steps": 41485, "total_steps": 64460, "loss": 0.1799, "lr": 3.39591177651236e-06, "epoch": 12.871548246974868, "percentage": 64.36, "elapsed_time": "1:16:39", "remaining_time": "0:42:27", "throughput": 5496.11, "total_tokens": 25277616} {"current_steps": 41490, "total_steps": 64460, "loss": 0.1919, "lr": 3.394629588305339e-06, "epoch": 12.873099596649084, "percentage": 64.37, "elapsed_time": "1:16:39", "remaining_time": "0:42:26", "throughput": 5496.18, "total_tokens": 25280816} {"current_steps": 41495, "total_steps": 64460, "loss": 0.2293, "lr": 3.3933475177909794e-06, "epoch": 12.874650946323301, "percentage": 64.37, "elapsed_time": "1:16:40", "remaining_time": "0:42:26", "throughput": 5496.32, "total_tokens": 25285424} {"current_steps": 41500, "total_steps": 64460, "loss": 0.234, "lr": 3.392065565063273e-06, "epoch": 12.876202295997517, "percentage": 64.38, "elapsed_time": "1:16:40", "remaining_time": "0:42:25", "throughput": 5496.26, "total_tokens": 25288112} {"current_steps": 41505, "total_steps": 64460, "loss": 0.2331, "lr": 3.3907837302162004e-06, "epoch": 12.877753645671735, "percentage": 64.39, "elapsed_time": "1:16:41", "remaining_time": "0:42:24", "throughput": 5496.36, "total_tokens": 25291504} {"current_steps": 41510, "total_steps": 64460, "loss": 0.265, "lr": 3.3895020133437373e-06, "epoch": 12.87930499534595, "percentage": 64.4, "elapsed_time": "1:16:42", "remaining_time": "0:42:24", "throughput": 5496.39, "total_tokens": 25294704} {"current_steps": 41515, "total_steps": 64460, "loss": 0.1867, "lr": 3.388220414539847e-06, "epoch": 12.880856345020167, "percentage": 64.4, "elapsed_time": "1:16:42", "remaining_time": "0:42:23", "throughput": 5496.46, "total_tokens": 25298448} {"current_steps": 41520, "total_steps": 64460, "loss": 0.2044, "lr": 3.386938933898487e-06, "epoch": 12.882407694694384, "percentage": 64.41, "elapsed_time": "1:16:43", "remaining_time": "0:42:23", "throughput": 5496.41, "total_tokens": 25301136} {"current_steps": 41525, "total_steps": 64460, "loss": 0.2274, "lr": 3.3856575715136043e-06, "epoch": 12.8839590443686, "percentage": 64.42, "elapsed_time": "1:16:43", "remaining_time": "0:42:22", "throughput": 5496.42, "total_tokens": 25304208} {"current_steps": 41530, "total_steps": 64460, "loss": 0.3087, "lr": 3.3843763274791385e-06, "epoch": 12.885510394042818, "percentage": 64.43, "elapsed_time": "1:16:44", "remaining_time": "0:42:22", "throughput": 5496.38, "total_tokens": 25306832} {"current_steps": 41535, "total_steps": 64460, "loss": 0.2138, "lr": 3.3830952018890205e-06, "epoch": 12.887061743717034, "percentage": 64.44, "elapsed_time": "1:16:44", "remaining_time": "0:42:21", "throughput": 5496.44, "total_tokens": 25309840} {"current_steps": 41540, "total_steps": 64460, "loss": 0.2149, "lr": 3.381814194837171e-06, "epoch": 12.88861309339125, "percentage": 64.44, "elapsed_time": "1:16:45", "remaining_time": "0:42:21", "throughput": 5496.35, "total_tokens": 25312336} {"current_steps": 41545, "total_steps": 64460, "loss": 0.1918, "lr": 3.380533306417503e-06, "epoch": 12.890164443065467, "percentage": 64.45, "elapsed_time": "1:16:45", "remaining_time": "0:42:20", "throughput": 5496.42, "total_tokens": 25315408} {"current_steps": 41550, "total_steps": 64460, "loss": 0.2035, "lr": 3.3792525367239203e-06, "epoch": 12.891715792739683, "percentage": 64.46, "elapsed_time": "1:16:46", "remaining_time": "0:42:19", "throughput": 5496.44, "total_tokens": 25318192} {"current_steps": 41555, "total_steps": 64460, "loss": 0.2446, "lr": 3.3779718858503195e-06, "epoch": 12.893267142413901, "percentage": 64.47, "elapsed_time": "1:16:46", "remaining_time": "0:42:19", "throughput": 5496.59, "total_tokens": 25322448} {"current_steps": 41560, "total_steps": 64460, "loss": 0.202, "lr": 3.3766913538905875e-06, "epoch": 12.894818492088117, "percentage": 64.47, "elapsed_time": "1:16:47", "remaining_time": "0:42:18", "throughput": 5496.69, "total_tokens": 25325808} {"current_steps": 41565, "total_steps": 64460, "loss": 0.1932, "lr": 3.3754109409386025e-06, "epoch": 12.896369841762333, "percentage": 64.48, "elapsed_time": "1:16:47", "remaining_time": "0:42:18", "throughput": 5496.66, "total_tokens": 25328400} {"current_steps": 41570, "total_steps": 64460, "loss": 0.2506, "lr": 3.374130647088233e-06, "epoch": 12.89792119143655, "percentage": 64.49, "elapsed_time": "1:16:48", "remaining_time": "0:42:17", "throughput": 5496.73, "total_tokens": 25331408} {"current_steps": 41575, "total_steps": 64460, "loss": 0.214, "lr": 3.372850472433339e-06, "epoch": 12.899472541110766, "percentage": 64.5, "elapsed_time": "1:16:48", "remaining_time": "0:42:17", "throughput": 5496.77, "total_tokens": 25334512} {"current_steps": 41580, "total_steps": 64460, "loss": 0.2192, "lr": 3.3715704170677755e-06, "epoch": 12.901023890784982, "percentage": 64.51, "elapsed_time": "1:16:49", "remaining_time": "0:42:16", "throughput": 5496.77, "total_tokens": 25337360} {"current_steps": 41585, "total_steps": 64460, "loss": 0.2401, "lr": 3.3702904810853833e-06, "epoch": 12.9025752404592, "percentage": 64.51, "elapsed_time": "1:16:50", "remaining_time": "0:42:15", "throughput": 5496.7, "total_tokens": 25340048} {"current_steps": 41590, "total_steps": 64460, "loss": 0.2392, "lr": 3.3690106645799973e-06, "epoch": 12.904126590133416, "percentage": 64.52, "elapsed_time": "1:16:50", "remaining_time": "0:42:15", "throughput": 5496.71, "total_tokens": 25342992} {"current_steps": 41595, "total_steps": 64460, "loss": 0.2268, "lr": 3.367730967645444e-06, "epoch": 12.905677939807633, "percentage": 64.53, "elapsed_time": "1:16:51", "remaining_time": "0:42:14", "throughput": 5496.74, "total_tokens": 25345808} {"current_steps": 41600, "total_steps": 64460, "loss": 0.1581, "lr": 3.366451390375539e-06, "epoch": 12.90722928948185, "percentage": 64.54, "elapsed_time": "1:16:51", "remaining_time": "0:42:14", "throughput": 5496.8, "total_tokens": 25348752} {"current_steps": 41605, "total_steps": 64460, "loss": 0.2255, "lr": 3.365171932864092e-06, "epoch": 12.908780639156065, "percentage": 64.54, "elapsed_time": "1:16:52", "remaining_time": "0:42:13", "throughput": 5496.85, "total_tokens": 25352688} {"current_steps": 41610, "total_steps": 64460, "loss": 0.166, "lr": 3.363892595204902e-06, "epoch": 12.910331988830283, "percentage": 64.55, "elapsed_time": "1:16:52", "remaining_time": "0:42:13", "throughput": 5496.93, "total_tokens": 25356272} {"current_steps": 41615, "total_steps": 64460, "loss": 0.2097, "lr": 3.362613377491758e-06, "epoch": 12.911883338504499, "percentage": 64.56, "elapsed_time": "1:16:53", "remaining_time": "0:42:12", "throughput": 5497.14, "total_tokens": 25361840} {"current_steps": 41620, "total_steps": 64460, "loss": 0.225, "lr": 3.3613342798184433e-06, "epoch": 12.913434688178716, "percentage": 64.57, "elapsed_time": "1:16:54", "remaining_time": "0:42:12", "throughput": 5497.18, "total_tokens": 25364880} {"current_steps": 41625, "total_steps": 64460, "loss": 0.204, "lr": 3.3600553022787307e-06, "epoch": 12.914986037852932, "percentage": 64.57, "elapsed_time": "1:16:54", "remaining_time": "0:42:11", "throughput": 5497.18, "total_tokens": 25367600} {"current_steps": 41630, "total_steps": 64460, "loss": 0.2057, "lr": 3.358776444966384e-06, "epoch": 12.916537387527148, "percentage": 64.58, "elapsed_time": "1:16:55", "remaining_time": "0:42:11", "throughput": 5497.23, "total_tokens": 25371344} {"current_steps": 41635, "total_steps": 64460, "loss": 0.1936, "lr": 3.357497707975158e-06, "epoch": 12.918088737201366, "percentage": 64.59, "elapsed_time": "1:16:56", "remaining_time": "0:42:10", "throughput": 5497.38, "total_tokens": 25376432} {"current_steps": 41640, "total_steps": 64460, "loss": 0.2479, "lr": 3.3562190913988014e-06, "epoch": 12.919640086875582, "percentage": 64.6, "elapsed_time": "1:16:56", "remaining_time": "0:42:10", "throughput": 5497.39, "total_tokens": 25379152} {"current_steps": 41645, "total_steps": 64460, "loss": 0.2267, "lr": 3.354940595331051e-06, "epoch": 12.921191436549798, "percentage": 64.61, "elapsed_time": "1:16:57", "remaining_time": "0:42:09", "throughput": 5497.48, "total_tokens": 25382384} {"current_steps": 41650, "total_steps": 64460, "loss": 0.2064, "lr": 3.353662219865635e-06, "epoch": 12.922742786224015, "percentage": 64.61, "elapsed_time": "1:16:57", "remaining_time": "0:42:08", "throughput": 5497.56, "total_tokens": 25385552} {"current_steps": 41655, "total_steps": 64460, "loss": 0.2102, "lr": 3.352383965096274e-06, "epoch": 12.924294135898231, "percentage": 64.62, "elapsed_time": "1:16:58", "remaining_time": "0:42:08", "throughput": 5497.53, "total_tokens": 25388336} {"current_steps": 41660, "total_steps": 64460, "loss": 0.2141, "lr": 3.351105831116679e-06, "epoch": 12.925845485572449, "percentage": 64.63, "elapsed_time": "1:16:58", "remaining_time": "0:42:07", "throughput": 5497.56, "total_tokens": 25391216} {"current_steps": 41665, "total_steps": 64460, "loss": 0.2462, "lr": 3.349827818020552e-06, "epoch": 12.927396835246665, "percentage": 64.64, "elapsed_time": "1:16:59", "remaining_time": "0:42:07", "throughput": 5497.45, "total_tokens": 25393296} {"current_steps": 41670, "total_steps": 64460, "loss": 0.2192, "lr": 3.348549925901587e-06, "epoch": 12.92894818492088, "percentage": 64.64, "elapsed_time": "1:16:59", "remaining_time": "0:42:06", "throughput": 5497.55, "total_tokens": 25397008} {"current_steps": 41675, "total_steps": 64460, "loss": 0.2259, "lr": 3.347272154853469e-06, "epoch": 12.930499534595098, "percentage": 64.65, "elapsed_time": "1:17:00", "remaining_time": "0:42:05", "throughput": 5497.5, "total_tokens": 25399376} {"current_steps": 41680, "total_steps": 64460, "loss": 0.2164, "lr": 3.345994504969873e-06, "epoch": 12.932050884269314, "percentage": 64.66, "elapsed_time": "1:17:00", "remaining_time": "0:42:05", "throughput": 5497.5, "total_tokens": 25402064} {"current_steps": 41685, "total_steps": 64460, "loss": 0.236, "lr": 3.3447169763444655e-06, "epoch": 12.933602233943532, "percentage": 64.67, "elapsed_time": "1:17:01", "remaining_time": "0:42:04", "throughput": 5497.58, "total_tokens": 25405136} {"current_steps": 41690, "total_steps": 64460, "loss": 0.1818, "lr": 3.343439569070906e-06, "epoch": 12.935153583617748, "percentage": 64.68, "elapsed_time": "1:17:01", "remaining_time": "0:42:04", "throughput": 5497.63, "total_tokens": 25408208} {"current_steps": 41695, "total_steps": 64460, "loss": 0.2289, "lr": 3.3421622832428414e-06, "epoch": 12.936704933291963, "percentage": 64.68, "elapsed_time": "1:17:02", "remaining_time": "0:42:03", "throughput": 5497.65, "total_tokens": 25411024} {"current_steps": 41700, "total_steps": 64460, "loss": 0.2039, "lr": 3.3408851189539138e-06, "epoch": 12.938256282966181, "percentage": 64.69, "elapsed_time": "1:17:02", "remaining_time": "0:42:03", "throughput": 5497.74, "total_tokens": 25414192} {"current_steps": 41705, "total_steps": 64460, "loss": 0.2632, "lr": 3.3396080762977544e-06, "epoch": 12.939807632640397, "percentage": 64.7, "elapsed_time": "1:17:03", "remaining_time": "0:42:02", "throughput": 5497.66, "total_tokens": 25416720} {"current_steps": 41710, "total_steps": 64460, "loss": 0.231, "lr": 3.3383311553679853e-06, "epoch": 12.941358982314613, "percentage": 64.71, "elapsed_time": "1:17:03", "remaining_time": "0:42:01", "throughput": 5497.65, "total_tokens": 25419632} {"current_steps": 41715, "total_steps": 64460, "loss": 0.1885, "lr": 3.337054356258219e-06, "epoch": 12.94291033198883, "percentage": 64.71, "elapsed_time": "1:17:04", "remaining_time": "0:42:01", "throughput": 5497.64, "total_tokens": 25422256} {"current_steps": 41720, "total_steps": 64460, "loss": 0.2058, "lr": 3.3357776790620603e-06, "epoch": 12.944461681663046, "percentage": 64.72, "elapsed_time": "1:17:04", "remaining_time": "0:42:00", "throughput": 5497.68, "total_tokens": 25425392} {"current_steps": 41725, "total_steps": 64460, "loss": 0.1946, "lr": 3.3345011238731063e-06, "epoch": 12.946013031337264, "percentage": 64.73, "elapsed_time": "1:17:05", "remaining_time": "0:42:00", "throughput": 5497.68, "total_tokens": 25428080} {"current_steps": 41730, "total_steps": 64460, "loss": 0.2315, "lr": 3.333224690784941e-06, "epoch": 12.94756438101148, "percentage": 64.74, "elapsed_time": "1:17:05", "remaining_time": "0:41:59", "throughput": 5497.72, "total_tokens": 25431184} {"current_steps": 41735, "total_steps": 64460, "loss": 0.2315, "lr": 3.3319483798911444e-06, "epoch": 12.949115730685696, "percentage": 64.75, "elapsed_time": "1:17:06", "remaining_time": "0:41:59", "throughput": 5497.64, "total_tokens": 25433488} {"current_steps": 41740, "total_steps": 64460, "loss": 0.1952, "lr": 3.3306721912852834e-06, "epoch": 12.950667080359914, "percentage": 64.75, "elapsed_time": "1:17:06", "remaining_time": "0:41:58", "throughput": 5497.62, "total_tokens": 25436112} {"current_steps": 41745, "total_steps": 64460, "loss": 0.2231, "lr": 3.3293961250609195e-06, "epoch": 12.95221843003413, "percentage": 64.76, "elapsed_time": "1:17:07", "remaining_time": "0:41:57", "throughput": 5497.62, "total_tokens": 25438864} {"current_steps": 41750, "total_steps": 64460, "loss": 0.2429, "lr": 3.3281201813116016e-06, "epoch": 12.953769779708347, "percentage": 64.77, "elapsed_time": "1:17:07", "remaining_time": "0:41:57", "throughput": 5497.73, "total_tokens": 25442704} {"current_steps": 41755, "total_steps": 64460, "loss": 0.2514, "lr": 3.326844360130873e-06, "epoch": 12.955321129382563, "percentage": 64.78, "elapsed_time": "1:17:08", "remaining_time": "0:41:56", "throughput": 5497.75, "total_tokens": 25445520} {"current_steps": 41760, "total_steps": 64460, "loss": 0.2182, "lr": 3.325568661612265e-06, "epoch": 12.956872479056779, "percentage": 64.78, "elapsed_time": "1:17:09", "remaining_time": "0:41:56", "throughput": 5497.86, "total_tokens": 25449904} {"current_steps": 41765, "total_steps": 64460, "loss": 0.2121, "lr": 3.3242930858493033e-06, "epoch": 12.958423828730997, "percentage": 64.79, "elapsed_time": "1:17:09", "remaining_time": "0:41:55", "throughput": 5498.03, "total_tokens": 25454192} {"current_steps": 41770, "total_steps": 64460, "loss": 0.2081, "lr": 3.323017632935501e-06, "epoch": 12.959975178405212, "percentage": 64.8, "elapsed_time": "1:17:10", "remaining_time": "0:41:55", "throughput": 5498.03, "total_tokens": 25457040} {"current_steps": 41775, "total_steps": 64460, "loss": 0.1749, "lr": 3.321742302964366e-06, "epoch": 12.961526528079428, "percentage": 64.81, "elapsed_time": "1:17:10", "remaining_time": "0:41:54", "throughput": 5498.06, "total_tokens": 25460112} {"current_steps": 41780, "total_steps": 64460, "loss": 0.2052, "lr": 3.3204670960293928e-06, "epoch": 12.963077877753646, "percentage": 64.82, "elapsed_time": "1:17:11", "remaining_time": "0:41:54", "throughput": 5498.09, "total_tokens": 25463152} {"current_steps": 41785, "total_steps": 64460, "loss": 0.2025, "lr": 3.3191920122240704e-06, "epoch": 12.964629227427862, "percentage": 64.82, "elapsed_time": "1:17:11", "remaining_time": "0:41:53", "throughput": 5498.09, "total_tokens": 25466160} {"current_steps": 41790, "total_steps": 64460, "loss": 0.2185, "lr": 3.3179170516418766e-06, "epoch": 12.96618057710208, "percentage": 64.83, "elapsed_time": "1:17:12", "remaining_time": "0:41:52", "throughput": 5498.21, "total_tokens": 25470128} {"current_steps": 41795, "total_steps": 64460, "loss": 0.2098, "lr": 3.316642214376283e-06, "epoch": 12.967731926776295, "percentage": 64.84, "elapsed_time": "1:17:12", "remaining_time": "0:41:52", "throughput": 5498.21, "total_tokens": 25472688} {"current_steps": 41800, "total_steps": 64460, "loss": 0.1797, "lr": 3.3153675005207486e-06, "epoch": 12.969283276450511, "percentage": 64.85, "elapsed_time": "1:17:13", "remaining_time": "0:41:51", "throughput": 5498.2, "total_tokens": 25475216} {"current_steps": 41805, "total_steps": 64460, "loss": 0.1559, "lr": 3.314092910168725e-06, "epoch": 12.970834626124729, "percentage": 64.85, "elapsed_time": "1:17:13", "remaining_time": "0:41:51", "throughput": 5498.33, "total_tokens": 25478832} {"current_steps": 41810, "total_steps": 64460, "loss": 0.1831, "lr": 3.3128184434136557e-06, "epoch": 12.972385975798945, "percentage": 64.86, "elapsed_time": "1:17:14", "remaining_time": "0:41:50", "throughput": 5498.46, "total_tokens": 25483024} {"current_steps": 41815, "total_steps": 64460, "loss": 0.2297, "lr": 3.3115441003489736e-06, "epoch": 12.973937325473162, "percentage": 64.87, "elapsed_time": "1:17:15", "remaining_time": "0:41:50", "throughput": 5498.36, "total_tokens": 25485168} {"current_steps": 41820, "total_steps": 64460, "loss": 0.2268, "lr": 3.3102698810681012e-06, "epoch": 12.975488675147378, "percentage": 64.88, "elapsed_time": "1:17:15", "remaining_time": "0:41:49", "throughput": 5498.43, "total_tokens": 25488368} {"current_steps": 41825, "total_steps": 64460, "loss": 0.2231, "lr": 3.3089957856644582e-06, "epoch": 12.977040024821594, "percentage": 64.89, "elapsed_time": "1:17:16", "remaining_time": "0:41:48", "throughput": 5498.46, "total_tokens": 25491344} {"current_steps": 41830, "total_steps": 64460, "loss": 0.2234, "lr": 3.307721814231448e-06, "epoch": 12.978591374495812, "percentage": 64.89, "elapsed_time": "1:17:16", "remaining_time": "0:41:48", "throughput": 5498.41, "total_tokens": 25493648} {"current_steps": 41835, "total_steps": 64460, "loss": 0.2308, "lr": 3.3064479668624684e-06, "epoch": 12.980142724170028, "percentage": 64.9, "elapsed_time": "1:17:17", "remaining_time": "0:41:47", "throughput": 5498.45, "total_tokens": 25496688} {"current_steps": 41840, "total_steps": 64460, "loss": 0.193, "lr": 3.3051742436509084e-06, "epoch": 12.981694073844244, "percentage": 64.91, "elapsed_time": "1:17:17", "remaining_time": "0:41:47", "throughput": 5498.47, "total_tokens": 25499760} {"current_steps": 41845, "total_steps": 64460, "loss": 0.2147, "lr": 3.3039006446901443e-06, "epoch": 12.983245423518461, "percentage": 64.92, "elapsed_time": "1:17:18", "remaining_time": "0:41:46", "throughput": 5498.44, "total_tokens": 25502224} {"current_steps": 41850, "total_steps": 64460, "loss": 0.1915, "lr": 3.302627170073549e-06, "epoch": 12.984796773192677, "percentage": 64.92, "elapsed_time": "1:17:18", "remaining_time": "0:41:46", "throughput": 5498.44, "total_tokens": 25505072} {"current_steps": 41855, "total_steps": 64460, "loss": 0.1912, "lr": 3.301353819894482e-06, "epoch": 12.986348122866895, "percentage": 64.93, "elapsed_time": "1:17:19", "remaining_time": "0:41:45", "throughput": 5498.43, "total_tokens": 25508016} {"current_steps": 41860, "total_steps": 64460, "loss": 0.2405, "lr": 3.3000805942462957e-06, "epoch": 12.98789947254111, "percentage": 64.94, "elapsed_time": "1:17:19", "remaining_time": "0:41:44", "throughput": 5498.39, "total_tokens": 25510480} {"current_steps": 41865, "total_steps": 64460, "loss": 0.2189, "lr": 3.29880749322233e-06, "epoch": 12.989450822215327, "percentage": 64.95, "elapsed_time": "1:17:20", "remaining_time": "0:41:44", "throughput": 5498.35, "total_tokens": 25513104} {"current_steps": 41870, "total_steps": 64460, "loss": 0.2538, "lr": 3.2975345169159196e-06, "epoch": 12.991002171889544, "percentage": 64.96, "elapsed_time": "1:17:20", "remaining_time": "0:41:43", "throughput": 5498.38, "total_tokens": 25516176} {"current_steps": 41875, "total_steps": 64460, "loss": 0.2052, "lr": 3.2962616654203903e-06, "epoch": 12.99255352156376, "percentage": 64.96, "elapsed_time": "1:17:21", "remaining_time": "0:41:43", "throughput": 5498.33, "total_tokens": 25518480} {"current_steps": 41880, "total_steps": 64460, "loss": 0.2381, "lr": 3.2949889388290573e-06, "epoch": 12.994104871237978, "percentage": 64.97, "elapsed_time": "1:17:21", "remaining_time": "0:41:42", "throughput": 5498.41, "total_tokens": 25521904} {"current_steps": 41885, "total_steps": 64460, "loss": 0.1978, "lr": 3.2937163372352255e-06, "epoch": 12.995656220912194, "percentage": 64.98, "elapsed_time": "1:17:22", "remaining_time": "0:41:42", "throughput": 5498.3, "total_tokens": 25524144} {"current_steps": 41890, "total_steps": 64460, "loss": 0.2434, "lr": 3.292443860732191e-06, "epoch": 12.99720757058641, "percentage": 64.99, "elapsed_time": "1:17:22", "remaining_time": "0:41:41", "throughput": 5498.43, "total_tokens": 25527664} {"current_steps": 41895, "total_steps": 64460, "loss": 0.2633, "lr": 3.2911715094132418e-06, "epoch": 12.998758920260627, "percentage": 64.99, "elapsed_time": "1:17:23", "remaining_time": "0:41:40", "throughput": 5498.55, "total_tokens": 25531216} {"current_steps": 41900, "total_steps": 64460, "loss": 0.213, "lr": 3.289899283371657e-06, "epoch": 13.000310269934843, "percentage": 65.0, "elapsed_time": "1:17:24", "remaining_time": "0:41:40", "throughput": 5498.2, "total_tokens": 25533920} {"current_steps": 41905, "total_steps": 64460, "loss": 0.1943, "lr": 3.2886271827007036e-06, "epoch": 13.001861619609059, "percentage": 65.01, "elapsed_time": "1:17:24", "remaining_time": "0:41:39", "throughput": 5498.14, "total_tokens": 25536544} {"current_steps": 41910, "total_steps": 64460, "loss": 0.2194, "lr": 3.2873552074936456e-06, "epoch": 13.003412969283277, "percentage": 65.02, "elapsed_time": "1:17:25", "remaining_time": "0:41:39", "throughput": 5498.21, "total_tokens": 25539808} {"current_steps": 41915, "total_steps": 64460, "loss": 0.2104, "lr": 3.28608335784373e-06, "epoch": 13.004964318957493, "percentage": 65.02, "elapsed_time": "1:17:25", "remaining_time": "0:41:38", "throughput": 5498.3, "total_tokens": 25543424} {"current_steps": 41920, "total_steps": 64460, "loss": 0.1676, "lr": 3.2848116338442014e-06, "epoch": 13.00651566863171, "percentage": 65.03, "elapsed_time": "1:17:26", "remaining_time": "0:41:38", "throughput": 5498.26, "total_tokens": 25545920} {"current_steps": 41925, "total_steps": 64460, "loss": 0.2006, "lr": 3.2835400355882907e-06, "epoch": 13.008067018305926, "percentage": 65.04, "elapsed_time": "1:17:26", "remaining_time": "0:41:37", "throughput": 5498.2, "total_tokens": 25548384} {"current_steps": 41930, "total_steps": 64460, "loss": 0.1944, "lr": 3.282268563169221e-06, "epoch": 13.009618367980142, "percentage": 65.05, "elapsed_time": "1:17:27", "remaining_time": "0:41:37", "throughput": 5498.26, "total_tokens": 25551648} {"current_steps": 41935, "total_steps": 64460, "loss": 0.1806, "lr": 3.2809972166802073e-06, "epoch": 13.01116971765436, "percentage": 65.06, "elapsed_time": "1:17:27", "remaining_time": "0:41:36", "throughput": 5498.35, "total_tokens": 25555200} {"current_steps": 41940, "total_steps": 64460, "loss": 0.1892, "lr": 3.279725996214453e-06, "epoch": 13.012721067328576, "percentage": 65.06, "elapsed_time": "1:17:28", "remaining_time": "0:41:35", "throughput": 5498.2, "total_tokens": 25557152} {"current_steps": 41945, "total_steps": 64460, "loss": 0.1794, "lr": 3.2784549018651546e-06, "epoch": 13.014272417002793, "percentage": 65.07, "elapsed_time": "1:17:28", "remaining_time": "0:41:35", "throughput": 5498.24, "total_tokens": 25560032} {"current_steps": 41950, "total_steps": 64460, "loss": 0.2401, "lr": 3.2771839337254975e-06, "epoch": 13.01582376667701, "percentage": 65.08, "elapsed_time": "1:17:29", "remaining_time": "0:41:34", "throughput": 5498.19, "total_tokens": 25562432} {"current_steps": 41955, "total_steps": 64460, "loss": 0.229, "lr": 3.2759130918886595e-06, "epoch": 13.017375116351225, "percentage": 65.09, "elapsed_time": "1:17:29", "remaining_time": "0:41:34", "throughput": 5498.22, "total_tokens": 25565376} {"current_steps": 41960, "total_steps": 64460, "loss": 0.184, "lr": 3.2746423764478085e-06, "epoch": 13.018926466025443, "percentage": 65.09, "elapsed_time": "1:17:30", "remaining_time": "0:41:33", "throughput": 5498.23, "total_tokens": 25568032} {"current_steps": 41965, "total_steps": 64460, "loss": 0.1824, "lr": 3.2733717874961014e-06, "epoch": 13.020477815699659, "percentage": 65.1, "elapsed_time": "1:17:30", "remaining_time": "0:41:32", "throughput": 5498.21, "total_tokens": 25570624} {"current_steps": 41970, "total_steps": 64460, "loss": 0.2311, "lr": 3.272101325126689e-06, "epoch": 13.022029165373874, "percentage": 65.11, "elapsed_time": "1:17:31", "remaining_time": "0:41:32", "throughput": 5498.13, "total_tokens": 25572992} {"current_steps": 41975, "total_steps": 64460, "loss": 0.1998, "lr": 3.2708309894327116e-06, "epoch": 13.023580515048092, "percentage": 65.12, "elapsed_time": "1:17:31", "remaining_time": "0:41:31", "throughput": 5498.14, "total_tokens": 25575680} {"current_steps": 41980, "total_steps": 64460, "loss": 0.2447, "lr": 3.2695607805072987e-06, "epoch": 13.025131864722308, "percentage": 65.13, "elapsed_time": "1:17:32", "remaining_time": "0:41:31", "throughput": 5498.12, "total_tokens": 25578656} {"current_steps": 41985, "total_steps": 64460, "loss": 0.2424, "lr": 3.2682906984435726e-06, "epoch": 13.026683214396526, "percentage": 65.13, "elapsed_time": "1:17:32", "remaining_time": "0:41:30", "throughput": 5498.25, "total_tokens": 25582368} {"current_steps": 41990, "total_steps": 64460, "loss": 0.2026, "lr": 3.267020743334644e-06, "epoch": 13.028234564070742, "percentage": 65.14, "elapsed_time": "1:17:33", "remaining_time": "0:41:30", "throughput": 5498.19, "total_tokens": 25584960} {"current_steps": 41995, "total_steps": 64460, "loss": 0.1844, "lr": 3.2657509152736167e-06, "epoch": 13.029785913744957, "percentage": 65.15, "elapsed_time": "1:17:33", "remaining_time": "0:41:29", "throughput": 5498.23, "total_tokens": 25587872} {"current_steps": 42000, "total_steps": 64460, "loss": 0.1916, "lr": 3.2644812143535842e-06, "epoch": 13.031337263419175, "percentage": 65.16, "elapsed_time": "1:17:34", "remaining_time": "0:41:28", "throughput": 5498.17, "total_tokens": 25590208} {"current_steps": 42005, "total_steps": 64460, "loss": 0.189, "lr": 3.2632116406676308e-06, "epoch": 13.032888613093391, "percentage": 65.16, "elapsed_time": "1:17:34", "remaining_time": "0:41:28", "throughput": 5498.26, "total_tokens": 25593696} {"current_steps": 42010, "total_steps": 64460, "loss": 0.1908, "lr": 3.26194219430883e-06, "epoch": 13.034439962767609, "percentage": 65.17, "elapsed_time": "1:17:35", "remaining_time": "0:41:27", "throughput": 5498.23, "total_tokens": 25596288} {"current_steps": 42015, "total_steps": 64460, "loss": 0.1828, "lr": 3.2606728753702478e-06, "epoch": 13.035991312441825, "percentage": 65.18, "elapsed_time": "1:17:35", "remaining_time": "0:41:27", "throughput": 5498.32, "total_tokens": 25599488} {"current_steps": 42020, "total_steps": 64460, "loss": 0.2537, "lr": 3.259403683944941e-06, "epoch": 13.03754266211604, "percentage": 65.19, "elapsed_time": "1:17:36", "remaining_time": "0:41:26", "throughput": 5498.44, "total_tokens": 25603296} {"current_steps": 42025, "total_steps": 64460, "loss": 0.2052, "lr": 3.258134620125955e-06, "epoch": 13.039094011790258, "percentage": 65.2, "elapsed_time": "1:17:37", "remaining_time": "0:41:26", "throughput": 5498.5, "total_tokens": 25606592} {"current_steps": 42030, "total_steps": 64460, "loss": 0.2384, "lr": 3.256865684006329e-06, "epoch": 13.040645361464474, "percentage": 65.2, "elapsed_time": "1:17:37", "remaining_time": "0:41:25", "throughput": 5498.62, "total_tokens": 25609984} {"current_steps": 42035, "total_steps": 64460, "loss": 0.2334, "lr": 3.25559687567909e-06, "epoch": 13.04219671113869, "percentage": 65.21, "elapsed_time": "1:17:38", "remaining_time": "0:41:24", "throughput": 5498.63, "total_tokens": 25612768} {"current_steps": 42040, "total_steps": 64460, "loss": 0.1944, "lr": 3.2543281952372575e-06, "epoch": 13.043748060812907, "percentage": 65.22, "elapsed_time": "1:17:38", "remaining_time": "0:41:24", "throughput": 5498.71, "total_tokens": 25616192} {"current_steps": 42045, "total_steps": 64460, "loss": 0.2282, "lr": 3.2530596427738393e-06, "epoch": 13.045299410487123, "percentage": 65.23, "elapsed_time": "1:17:39", "remaining_time": "0:41:23", "throughput": 5498.68, "total_tokens": 25618848} {"current_steps": 42050, "total_steps": 64460, "loss": 0.2064, "lr": 3.2517912183818366e-06, "epoch": 13.046850760161341, "percentage": 65.23, "elapsed_time": "1:17:39", "remaining_time": "0:41:23", "throughput": 5498.83, "total_tokens": 25622784} {"current_steps": 42055, "total_steps": 64460, "loss": 0.186, "lr": 3.2505229221542387e-06, "epoch": 13.048402109835557, "percentage": 65.24, "elapsed_time": "1:17:40", "remaining_time": "0:41:22", "throughput": 5498.99, "total_tokens": 25627360} {"current_steps": 42060, "total_steps": 64460, "loss": 0.2027, "lr": 3.2492547541840284e-06, "epoch": 13.049953459509773, "percentage": 65.25, "elapsed_time": "1:17:40", "remaining_time": "0:41:22", "throughput": 5498.96, "total_tokens": 25629952} {"current_steps": 42065, "total_steps": 64460, "loss": 0.2025, "lr": 3.2479867145641764e-06, "epoch": 13.05150480918399, "percentage": 65.26, "elapsed_time": "1:17:41", "remaining_time": "0:41:21", "throughput": 5498.9, "total_tokens": 25632224} {"current_steps": 42070, "total_steps": 64460, "loss": 0.1761, "lr": 3.246718803387645e-06, "epoch": 13.053056158858206, "percentage": 65.27, "elapsed_time": "1:17:41", "remaining_time": "0:41:21", "throughput": 5499.0, "total_tokens": 25635776} {"current_steps": 42075, "total_steps": 64460, "loss": 0.2645, "lr": 3.245451020747388e-06, "epoch": 13.054607508532424, "percentage": 65.27, "elapsed_time": "1:17:42", "remaining_time": "0:41:20", "throughput": 5498.97, "total_tokens": 25638368} {"current_steps": 42080, "total_steps": 64460, "loss": 0.1967, "lr": 3.244183366736347e-06, "epoch": 13.05615885820664, "percentage": 65.28, "elapsed_time": "1:17:42", "remaining_time": "0:41:19", "throughput": 5499.04, "total_tokens": 25641984} {"current_steps": 42085, "total_steps": 64460, "loss": 0.1773, "lr": 3.242915841447457e-06, "epoch": 13.057710207880856, "percentage": 65.29, "elapsed_time": "1:17:43", "remaining_time": "0:41:19", "throughput": 5499.14, "total_tokens": 25645600} {"current_steps": 42090, "total_steps": 64460, "loss": 0.2019, "lr": 3.2416484449736428e-06, "epoch": 13.059261557555073, "percentage": 65.3, "elapsed_time": "1:17:44", "remaining_time": "0:41:18", "throughput": 5499.18, "total_tokens": 25648608} {"current_steps": 42095, "total_steps": 64460, "loss": 0.2026, "lr": 3.2403811774078207e-06, "epoch": 13.06081290722929, "percentage": 65.3, "elapsed_time": "1:17:44", "remaining_time": "0:41:18", "throughput": 5499.12, "total_tokens": 25651072} {"current_steps": 42100, "total_steps": 64460, "loss": 0.2113, "lr": 3.2391140388428947e-06, "epoch": 13.062364256903505, "percentage": 65.31, "elapsed_time": "1:17:45", "remaining_time": "0:41:17", "throughput": 5499.13, "total_tokens": 25654048} {"current_steps": 42105, "total_steps": 64460, "loss": 0.208, "lr": 3.2378470293717623e-06, "epoch": 13.063915606577723, "percentage": 65.32, "elapsed_time": "1:17:45", "remaining_time": "0:41:17", "throughput": 5499.08, "total_tokens": 25656512} {"current_steps": 42110, "total_steps": 64460, "loss": 0.1949, "lr": 3.2365801490873087e-06, "epoch": 13.065466956251939, "percentage": 65.33, "elapsed_time": "1:17:46", "remaining_time": "0:41:16", "throughput": 5499.23, "total_tokens": 25661376} {"current_steps": 42115, "total_steps": 64460, "loss": 0.2187, "lr": 3.2353133980824124e-06, "epoch": 13.067018305926156, "percentage": 65.34, "elapsed_time": "1:17:46", "remaining_time": "0:41:16", "throughput": 5499.27, "total_tokens": 25664768} {"current_steps": 42120, "total_steps": 64460, "loss": 0.2054, "lr": 3.2340467764499415e-06, "epoch": 13.068569655600372, "percentage": 65.34, "elapsed_time": "1:17:47", "remaining_time": "0:41:15", "throughput": 5499.35, "total_tokens": 25668096} {"current_steps": 42125, "total_steps": 64460, "loss": 0.1759, "lr": 3.232780284282754e-06, "epoch": 13.070121005274588, "percentage": 65.35, "elapsed_time": "1:17:47", "remaining_time": "0:41:14", "throughput": 5499.3, "total_tokens": 25670464} {"current_steps": 42130, "total_steps": 64460, "loss": 0.183, "lr": 3.2315139216736986e-06, "epoch": 13.071672354948806, "percentage": 65.36, "elapsed_time": "1:17:48", "remaining_time": "0:41:14", "throughput": 5499.31, "total_tokens": 25673440} {"current_steps": 42135, "total_steps": 64460, "loss": 0.1828, "lr": 3.2302476887156143e-06, "epoch": 13.073223704623022, "percentage": 65.37, "elapsed_time": "1:17:49", "remaining_time": "0:41:13", "throughput": 5499.34, "total_tokens": 25676480} {"current_steps": 42140, "total_steps": 64460, "loss": 0.1589, "lr": 3.2289815855013316e-06, "epoch": 13.07477505429724, "percentage": 65.37, "elapsed_time": "1:17:49", "remaining_time": "0:41:13", "throughput": 5499.3, "total_tokens": 25678944} {"current_steps": 42145, "total_steps": 64460, "loss": 0.2024, "lr": 3.2277156121236697e-06, "epoch": 13.076326403971455, "percentage": 65.38, "elapsed_time": "1:17:50", "remaining_time": "0:41:12", "throughput": 5499.13, "total_tokens": 25681088} {"current_steps": 42150, "total_steps": 64460, "loss": 0.175, "lr": 3.2264497686754413e-06, "epoch": 13.077877753645671, "percentage": 65.39, "elapsed_time": "1:17:50", "remaining_time": "0:41:12", "throughput": 5499.28, "total_tokens": 25685440} {"current_steps": 42155, "total_steps": 64460, "loss": 0.2183, "lr": 3.2251840552494473e-06, "epoch": 13.079429103319889, "percentage": 65.4, "elapsed_time": "1:17:51", "remaining_time": "0:41:11", "throughput": 5499.36, "total_tokens": 25688608} {"current_steps": 42160, "total_steps": 64460, "loss": 0.2022, "lr": 3.2239184719384786e-06, "epoch": 13.080980452994105, "percentage": 65.4, "elapsed_time": "1:17:51", "remaining_time": "0:41:11", "throughput": 5499.31, "total_tokens": 25690912} {"current_steps": 42165, "total_steps": 64460, "loss": 0.2707, "lr": 3.222653018835318e-06, "epoch": 13.08253180266832, "percentage": 65.41, "elapsed_time": "1:17:52", "remaining_time": "0:41:10", "throughput": 5499.3, "total_tokens": 25693504} {"current_steps": 42170, "total_steps": 64460, "loss": 0.2188, "lr": 3.2213876960327383e-06, "epoch": 13.084083152342538, "percentage": 65.42, "elapsed_time": "1:17:52", "remaining_time": "0:41:09", "throughput": 5499.26, "total_tokens": 25696512} {"current_steps": 42175, "total_steps": 64460, "loss": 0.2012, "lr": 3.2201225036235017e-06, "epoch": 13.085634502016754, "percentage": 65.43, "elapsed_time": "1:17:53", "remaining_time": "0:41:09", "throughput": 5499.2, "total_tokens": 25699072} {"current_steps": 42180, "total_steps": 64460, "loss": 0.1787, "lr": 3.218857441700363e-06, "epoch": 13.087185851690972, "percentage": 65.44, "elapsed_time": "1:17:53", "remaining_time": "0:41:08", "throughput": 5499.26, "total_tokens": 25702400} {"current_steps": 42185, "total_steps": 64460, "loss": 0.2156, "lr": 3.2175925103560656e-06, "epoch": 13.088737201365188, "percentage": 65.44, "elapsed_time": "1:17:54", "remaining_time": "0:41:08", "throughput": 5499.22, "total_tokens": 25704832} {"current_steps": 42190, "total_steps": 64460, "loss": 0.2294, "lr": 3.2163277096833443e-06, "epoch": 13.090288551039404, "percentage": 65.45, "elapsed_time": "1:17:54", "remaining_time": "0:41:07", "throughput": 5499.18, "total_tokens": 25707328} {"current_steps": 42195, "total_steps": 64460, "loss": 0.2774, "lr": 3.215063039774924e-06, "epoch": 13.091839900713621, "percentage": 65.46, "elapsed_time": "1:17:55", "remaining_time": "0:41:06", "throughput": 5499.16, "total_tokens": 25709920} {"current_steps": 42200, "total_steps": 64460, "loss": 0.2256, "lr": 3.213798500723519e-06, "epoch": 13.093391250387837, "percentage": 65.47, "elapsed_time": "1:17:55", "remaining_time": "0:41:06", "throughput": 5499.11, "total_tokens": 25712704} {"current_steps": 42205, "total_steps": 64460, "loss": 0.2485, "lr": 3.2125340926218346e-06, "epoch": 13.094942600062055, "percentage": 65.47, "elapsed_time": "1:17:56", "remaining_time": "0:41:05", "throughput": 5499.04, "total_tokens": 25715008} {"current_steps": 42210, "total_steps": 64460, "loss": 0.1994, "lr": 3.211269815562569e-06, "epoch": 13.09649394973627, "percentage": 65.48, "elapsed_time": "1:17:56", "remaining_time": "0:41:05", "throughput": 5499.08, "total_tokens": 25717856} {"current_steps": 42215, "total_steps": 64460, "loss": 0.1645, "lr": 3.2100056696384086e-06, "epoch": 13.098045299410487, "percentage": 65.49, "elapsed_time": "1:17:57", "remaining_time": "0:41:04", "throughput": 5499.0, "total_tokens": 25720352} {"current_steps": 42220, "total_steps": 64460, "loss": 0.2327, "lr": 3.208741654942028e-06, "epoch": 13.099596649084704, "percentage": 65.5, "elapsed_time": "1:17:57", "remaining_time": "0:41:04", "throughput": 5499.06, "total_tokens": 25723328} {"current_steps": 42225, "total_steps": 64460, "loss": 0.194, "lr": 3.2074777715660964e-06, "epoch": 13.10114799875892, "percentage": 65.51, "elapsed_time": "1:17:58", "remaining_time": "0:41:03", "throughput": 5499.07, "total_tokens": 25726336} {"current_steps": 42230, "total_steps": 64460, "loss": 0.1488, "lr": 3.206214019603271e-06, "epoch": 13.102699348433136, "percentage": 65.51, "elapsed_time": "1:17:58", "remaining_time": "0:41:02", "throughput": 5499.12, "total_tokens": 25729440} {"current_steps": 42235, "total_steps": 64460, "loss": 0.1607, "lr": 3.2049503991461996e-06, "epoch": 13.104250698107354, "percentage": 65.52, "elapsed_time": "1:17:59", "remaining_time": "0:41:02", "throughput": 5499.08, "total_tokens": 25731968} {"current_steps": 42240, "total_steps": 64460, "loss": 0.2011, "lr": 3.20368691028752e-06, "epoch": 13.10580204778157, "percentage": 65.53, "elapsed_time": "1:17:59", "remaining_time": "0:41:01", "throughput": 5499.09, "total_tokens": 25734784} {"current_steps": 42245, "total_steps": 64460, "loss": 0.2765, "lr": 3.2024235531198618e-06, "epoch": 13.107353397455787, "percentage": 65.54, "elapsed_time": "1:18:00", "remaining_time": "0:41:01", "throughput": 5499.14, "total_tokens": 25738112} {"current_steps": 42250, "total_steps": 64460, "loss": 0.2645, "lr": 3.201160327735844e-06, "epoch": 13.108904747130003, "percentage": 65.54, "elapsed_time": "1:18:00", "remaining_time": "0:41:00", "throughput": 5499.14, "total_tokens": 25740896} {"current_steps": 42255, "total_steps": 64460, "loss": 0.1945, "lr": 3.199897234228074e-06, "epoch": 13.110456096804219, "percentage": 65.55, "elapsed_time": "1:18:01", "remaining_time": "0:41:00", "throughput": 5499.05, "total_tokens": 25743168} {"current_steps": 42260, "total_steps": 64460, "loss": 0.1823, "lr": 3.198634272689155e-06, "epoch": 13.112007446478437, "percentage": 65.56, "elapsed_time": "1:18:01", "remaining_time": "0:40:59", "throughput": 5498.96, "total_tokens": 25745472} {"current_steps": 42265, "total_steps": 64460, "loss": 0.1962, "lr": 3.197371443211673e-06, "epoch": 13.113558796152653, "percentage": 65.57, "elapsed_time": "1:18:02", "remaining_time": "0:40:58", "throughput": 5499.02, "total_tokens": 25748544} {"current_steps": 42270, "total_steps": 64460, "loss": 0.1749, "lr": 3.1961087458882124e-06, "epoch": 13.11511014582687, "percentage": 65.58, "elapsed_time": "1:18:02", "remaining_time": "0:40:58", "throughput": 5499.07, "total_tokens": 25751648} {"current_steps": 42275, "total_steps": 64460, "loss": 0.1837, "lr": 3.1948461808113416e-06, "epoch": 13.116661495501086, "percentage": 65.58, "elapsed_time": "1:18:03", "remaining_time": "0:40:57", "throughput": 5499.11, "total_tokens": 25755008} {"current_steps": 42280, "total_steps": 64460, "loss": 0.1414, "lr": 3.193583748073622e-06, "epoch": 13.118212845175302, "percentage": 65.59, "elapsed_time": "1:18:03", "remaining_time": "0:40:57", "throughput": 5499.1, "total_tokens": 25757600} {"current_steps": 42285, "total_steps": 64460, "loss": 0.2506, "lr": 3.1923214477676044e-06, "epoch": 13.11976419484952, "percentage": 65.6, "elapsed_time": "1:18:04", "remaining_time": "0:40:56", "throughput": 5499.03, "total_tokens": 25759840} {"current_steps": 42290, "total_steps": 64460, "loss": 0.2095, "lr": 3.1910592799858316e-06, "epoch": 13.121315544523735, "percentage": 65.61, "elapsed_time": "1:18:05", "remaining_time": "0:40:56", "throughput": 5499.09, "total_tokens": 25763392} {"current_steps": 42295, "total_steps": 64460, "loss": 0.2436, "lr": 3.1897972448208335e-06, "epoch": 13.122866894197951, "percentage": 65.61, "elapsed_time": "1:18:05", "remaining_time": "0:40:55", "throughput": 5499.1, "total_tokens": 25766336} {"current_steps": 42300, "total_steps": 64460, "loss": 0.2528, "lr": 3.1885353423651344e-06, "epoch": 13.124418243872169, "percentage": 65.62, "elapsed_time": "1:18:06", "remaining_time": "0:40:54", "throughput": 5499.13, "total_tokens": 25769312} {"current_steps": 42305, "total_steps": 64460, "loss": 0.2521, "lr": 3.1872735727112457e-06, "epoch": 13.125969593546385, "percentage": 65.63, "elapsed_time": "1:18:06", "remaining_time": "0:40:54", "throughput": 5499.11, "total_tokens": 25772032} {"current_steps": 42310, "total_steps": 64460, "loss": 0.2035, "lr": 3.1860119359516693e-06, "epoch": 13.127520943220603, "percentage": 65.64, "elapsed_time": "1:18:07", "remaining_time": "0:40:53", "throughput": 5499.01, "total_tokens": 25774592} {"current_steps": 42315, "total_steps": 64460, "loss": 0.2474, "lr": 3.184750432178899e-06, "epoch": 13.129072292894818, "percentage": 65.65, "elapsed_time": "1:18:07", "remaining_time": "0:40:53", "throughput": 5499.04, "total_tokens": 25777312} {"current_steps": 42320, "total_steps": 64460, "loss": 0.2247, "lr": 3.1834890614854186e-06, "epoch": 13.130623642569034, "percentage": 65.65, "elapsed_time": "1:18:08", "remaining_time": "0:40:52", "throughput": 5498.86, "total_tokens": 25779456} {"current_steps": 42325, "total_steps": 64460, "loss": 0.1772, "lr": 3.182227823963698e-06, "epoch": 13.132174992243252, "percentage": 65.66, "elapsed_time": "1:18:08", "remaining_time": "0:40:52", "throughput": 5498.85, "total_tokens": 25782144} {"current_steps": 42330, "total_steps": 64460, "loss": 0.2008, "lr": 3.1809667197062067e-06, "epoch": 13.133726341917468, "percentage": 65.67, "elapsed_time": "1:18:09", "remaining_time": "0:40:51", "throughput": 5498.83, "total_tokens": 25784768} {"current_steps": 42335, "total_steps": 64460, "loss": 0.2017, "lr": 3.179705748805394e-06, "epoch": 13.135277691591686, "percentage": 65.68, "elapsed_time": "1:18:09", "remaining_time": "0:40:50", "throughput": 5498.67, "total_tokens": 25786688} {"current_steps": 42340, "total_steps": 64460, "loss": 0.2136, "lr": 3.178444911353705e-06, "epoch": 13.136829041265901, "percentage": 65.68, "elapsed_time": "1:18:10", "remaining_time": "0:40:50", "throughput": 5498.62, "total_tokens": 25789120} {"current_steps": 42345, "total_steps": 64460, "loss": 0.2349, "lr": 3.1771842074435753e-06, "epoch": 13.138380390940117, "percentage": 65.69, "elapsed_time": "1:18:10", "remaining_time": "0:40:49", "throughput": 5498.64, "total_tokens": 25792032} {"current_steps": 42350, "total_steps": 64460, "loss": 0.2368, "lr": 3.1759236371674292e-06, "epoch": 13.139931740614335, "percentage": 65.7, "elapsed_time": "1:18:11", "remaining_time": "0:40:49", "throughput": 5498.6, "total_tokens": 25794464} {"current_steps": 42355, "total_steps": 64460, "loss": 0.2029, "lr": 3.17466320061768e-06, "epoch": 13.14148309028855, "percentage": 65.71, "elapsed_time": "1:18:11", "remaining_time": "0:40:48", "throughput": 5498.73, "total_tokens": 25798432} {"current_steps": 42360, "total_steps": 64460, "loss": 0.2262, "lr": 3.173402897886733e-06, "epoch": 13.143034439962767, "percentage": 65.72, "elapsed_time": "1:18:12", "remaining_time": "0:40:48", "throughput": 5498.8, "total_tokens": 25801504} {"current_steps": 42365, "total_steps": 64460, "loss": 0.2251, "lr": 3.172142729066984e-06, "epoch": 13.144585789636984, "percentage": 65.72, "elapsed_time": "1:18:12", "remaining_time": "0:40:47", "throughput": 5498.86, "total_tokens": 25804736} {"current_steps": 42370, "total_steps": 64460, "loss": 0.1747, "lr": 3.1708826942508184e-06, "epoch": 13.1461371393112, "percentage": 65.73, "elapsed_time": "1:18:13", "remaining_time": "0:40:46", "throughput": 5498.79, "total_tokens": 25807040} {"current_steps": 42375, "total_steps": 64460, "loss": 0.2123, "lr": 3.169622793530611e-06, "epoch": 13.147688488985418, "percentage": 65.74, "elapsed_time": "1:18:13", "remaining_time": "0:40:46", "throughput": 5498.76, "total_tokens": 25809472} {"current_steps": 42380, "total_steps": 64460, "loss": 0.2311, "lr": 3.168363026998728e-06, "epoch": 13.149239838659634, "percentage": 65.75, "elapsed_time": "1:18:14", "remaining_time": "0:40:45", "throughput": 5498.95, "total_tokens": 25813952} {"current_steps": 42385, "total_steps": 64460, "loss": 0.2629, "lr": 3.167103394747524e-06, "epoch": 13.15079118833385, "percentage": 65.75, "elapsed_time": "1:18:14", "remaining_time": "0:40:45", "throughput": 5498.96, "total_tokens": 25816736} {"current_steps": 42390, "total_steps": 64460, "loss": 0.2859, "lr": 3.1658438968693466e-06, "epoch": 13.152342538008067, "percentage": 65.76, "elapsed_time": "1:18:15", "remaining_time": "0:40:44", "throughput": 5498.99, "total_tokens": 25819648} {"current_steps": 42395, "total_steps": 64460, "loss": 0.1989, "lr": 3.1645845334565316e-06, "epoch": 13.153893887682283, "percentage": 65.77, "elapsed_time": "1:18:15", "remaining_time": "0:40:44", "throughput": 5499.03, "total_tokens": 25823008} {"current_steps": 42400, "total_steps": 64460, "loss": 0.1936, "lr": 3.1633253046014046e-06, "epoch": 13.155445237356501, "percentage": 65.78, "elapsed_time": "1:18:16", "remaining_time": "0:40:43", "throughput": 5498.94, "total_tokens": 25825248} {"current_steps": 42405, "total_steps": 64460, "loss": 0.2151, "lr": 3.1620662103962816e-06, "epoch": 13.156996587030717, "percentage": 65.78, "elapsed_time": "1:18:16", "remaining_time": "0:40:42", "throughput": 5498.92, "total_tokens": 25828096} {"current_steps": 42410, "total_steps": 64460, "loss": 0.2253, "lr": 3.1608072509334707e-06, "epoch": 13.158547936704933, "percentage": 65.79, "elapsed_time": "1:18:17", "remaining_time": "0:40:42", "throughput": 5499.02, "total_tokens": 25831680} {"current_steps": 42415, "total_steps": 64460, "loss": 0.2453, "lr": 3.159548426305268e-06, "epoch": 13.16009928637915, "percentage": 65.8, "elapsed_time": "1:18:17", "remaining_time": "0:40:41", "throughput": 5498.96, "total_tokens": 25833984} {"current_steps": 42420, "total_steps": 64460, "loss": 0.2133, "lr": 3.158289736603959e-06, "epoch": 13.161650636053366, "percentage": 65.81, "elapsed_time": "1:18:18", "remaining_time": "0:40:41", "throughput": 5499.04, "total_tokens": 25837632} {"current_steps": 42425, "total_steps": 64460, "loss": 0.1962, "lr": 3.1570311819218212e-06, "epoch": 13.163201985727582, "percentage": 65.82, "elapsed_time": "1:18:19", "remaining_time": "0:40:40", "throughput": 5499.13, "total_tokens": 25841152} {"current_steps": 42430, "total_steps": 64460, "loss": 0.2508, "lr": 3.1557727623511227e-06, "epoch": 13.1647533354018, "percentage": 65.82, "elapsed_time": "1:18:19", "remaining_time": "0:40:40", "throughput": 5499.17, "total_tokens": 25844384} {"current_steps": 42435, "total_steps": 64460, "loss": 0.2333, "lr": 3.1545144779841184e-06, "epoch": 13.166304685076016, "percentage": 65.83, "elapsed_time": "1:18:20", "remaining_time": "0:40:39", "throughput": 5499.18, "total_tokens": 25847040} {"current_steps": 42440, "total_steps": 64460, "loss": 0.2, "lr": 3.153256328913058e-06, "epoch": 13.167856034750233, "percentage": 65.84, "elapsed_time": "1:18:20", "remaining_time": "0:40:38", "throughput": 5499.13, "total_tokens": 25849568} {"current_steps": 42445, "total_steps": 64460, "loss": 0.2386, "lr": 3.1519983152301757e-06, "epoch": 13.16940738442445, "percentage": 65.85, "elapsed_time": "1:18:21", "remaining_time": "0:40:38", "throughput": 5499.22, "total_tokens": 25853344} {"current_steps": 42450, "total_steps": 64460, "loss": 0.1769, "lr": 3.1507404370277007e-06, "epoch": 13.170958734098665, "percentage": 65.85, "elapsed_time": "1:18:21", "remaining_time": "0:40:37", "throughput": 5499.15, "total_tokens": 25855648} {"current_steps": 42455, "total_steps": 64460, "loss": 0.2155, "lr": 3.1494826943978507e-06, "epoch": 13.172510083772883, "percentage": 65.86, "elapsed_time": "1:18:22", "remaining_time": "0:40:37", "throughput": 5499.28, "total_tokens": 25860256} {"current_steps": 42460, "total_steps": 64460, "loss": 0.1904, "lr": 3.1482250874328337e-06, "epoch": 13.174061433447099, "percentage": 65.87, "elapsed_time": "1:18:22", "remaining_time": "0:40:36", "throughput": 5499.24, "total_tokens": 25862752} {"current_steps": 42465, "total_steps": 64460, "loss": 0.1995, "lr": 3.146967616224845e-06, "epoch": 13.175612783121316, "percentage": 65.88, "elapsed_time": "1:18:23", "remaining_time": "0:40:36", "throughput": 5499.31, "total_tokens": 25866400} {"current_steps": 42470, "total_steps": 64460, "loss": 0.2051, "lr": 3.1457102808660724e-06, "epoch": 13.177164132795532, "percentage": 65.89, "elapsed_time": "1:18:24", "remaining_time": "0:40:35", "throughput": 5499.33, "total_tokens": 25869312} {"current_steps": 42475, "total_steps": 64460, "loss": 0.1692, "lr": 3.144453081448695e-06, "epoch": 13.178715482469748, "percentage": 65.89, "elapsed_time": "1:18:24", "remaining_time": "0:40:35", "throughput": 5499.36, "total_tokens": 25872160} {"current_steps": 42480, "total_steps": 64460, "loss": 0.22, "lr": 3.1431960180648806e-06, "epoch": 13.180266832143966, "percentage": 65.9, "elapsed_time": "1:18:25", "remaining_time": "0:40:34", "throughput": 5499.47, "total_tokens": 25875584} {"current_steps": 42485, "total_steps": 64460, "loss": 0.2094, "lr": 3.141939090806786e-06, "epoch": 13.181818181818182, "percentage": 65.91, "elapsed_time": "1:18:25", "remaining_time": "0:40:33", "throughput": 5499.56, "total_tokens": 25878944} {"current_steps": 42490, "total_steps": 64460, "loss": 0.1603, "lr": 3.1406822997665577e-06, "epoch": 13.183369531492398, "percentage": 65.92, "elapsed_time": "1:18:26", "remaining_time": "0:40:33", "throughput": 5499.69, "total_tokens": 25882912} {"current_steps": 42495, "total_steps": 64460, "loss": 0.1874, "lr": 3.1394256450363353e-06, "epoch": 13.184920881166615, "percentage": 65.92, "elapsed_time": "1:18:26", "remaining_time": "0:40:32", "throughput": 5499.77, "total_tokens": 25886368} {"current_steps": 42500, "total_steps": 64460, "loss": 0.2196, "lr": 3.1381691267082452e-06, "epoch": 13.186472230840831, "percentage": 65.93, "elapsed_time": "1:18:27", "remaining_time": "0:40:32", "throughput": 5499.84, "total_tokens": 25889504} {"current_steps": 42505, "total_steps": 64460, "loss": 0.2351, "lr": 3.1369127448744057e-06, "epoch": 13.188023580515049, "percentage": 65.94, "elapsed_time": "1:18:27", "remaining_time": "0:40:31", "throughput": 5499.83, "total_tokens": 25892000} {"current_steps": 42510, "total_steps": 64460, "loss": 0.2639, "lr": 3.1356564996269244e-06, "epoch": 13.189574930189265, "percentage": 65.95, "elapsed_time": "1:18:28", "remaining_time": "0:40:31", "throughput": 5499.92, "total_tokens": 25895712} {"current_steps": 42515, "total_steps": 64460, "loss": 0.1753, "lr": 3.134400391057898e-06, "epoch": 13.19112627986348, "percentage": 65.96, "elapsed_time": "1:18:28", "remaining_time": "0:40:30", "throughput": 5500.01, "total_tokens": 25898880} {"current_steps": 42520, "total_steps": 64460, "loss": 0.244, "lr": 3.133144419259416e-06, "epoch": 13.192677629537698, "percentage": 65.96, "elapsed_time": "1:18:29", "remaining_time": "0:40:30", "throughput": 5500.1, "total_tokens": 25902560} {"current_steps": 42525, "total_steps": 64460, "loss": 0.2112, "lr": 3.131888584323555e-06, "epoch": 13.194228979211914, "percentage": 65.97, "elapsed_time": "1:18:30", "remaining_time": "0:40:29", "throughput": 5500.22, "total_tokens": 25906464} {"current_steps": 42530, "total_steps": 64460, "loss": 0.2115, "lr": 3.1306328863423807e-06, "epoch": 13.195780328886132, "percentage": 65.98, "elapsed_time": "1:18:30", "remaining_time": "0:40:28", "throughput": 5500.31, "total_tokens": 25909824} {"current_steps": 42535, "total_steps": 64460, "loss": 0.1976, "lr": 3.1293773254079534e-06, "epoch": 13.197331678560348, "percentage": 65.99, "elapsed_time": "1:18:31", "remaining_time": "0:40:28", "throughput": 5500.22, "total_tokens": 25911872} {"current_steps": 42540, "total_steps": 64460, "loss": 0.2086, "lr": 3.12812190161232e-06, "epoch": 13.198883028234563, "percentage": 65.99, "elapsed_time": "1:18:31", "remaining_time": "0:40:27", "throughput": 5500.15, "total_tokens": 25913984} {"current_steps": 42545, "total_steps": 64460, "loss": 0.2395, "lr": 3.1268666150475175e-06, "epoch": 13.200434377908781, "percentage": 66.0, "elapsed_time": "1:18:32", "remaining_time": "0:40:27", "throughput": 5500.09, "total_tokens": 25916480} {"current_steps": 42550, "total_steps": 64460, "loss": 0.1838, "lr": 3.125611465805574e-06, "epoch": 13.201985727582997, "percentage": 66.01, "elapsed_time": "1:18:32", "remaining_time": "0:40:26", "throughput": 5500.19, "total_tokens": 25920032} {"current_steps": 42555, "total_steps": 64460, "loss": 0.2211, "lr": 3.1243564539785047e-06, "epoch": 13.203537077257213, "percentage": 66.02, "elapsed_time": "1:18:33", "remaining_time": "0:40:26", "throughput": 5500.22, "total_tokens": 25922752} {"current_steps": 42560, "total_steps": 64460, "loss": 0.2099, "lr": 3.1231015796583192e-06, "epoch": 13.20508842693143, "percentage": 66.03, "elapsed_time": "1:18:33", "remaining_time": "0:40:25", "throughput": 5500.24, "total_tokens": 25925632} {"current_steps": 42565, "total_steps": 64460, "loss": 0.1761, "lr": 3.1218468429370143e-06, "epoch": 13.206639776605646, "percentage": 66.03, "elapsed_time": "1:18:34", "remaining_time": "0:40:24", "throughput": 5500.3, "total_tokens": 25929376} {"current_steps": 42570, "total_steps": 64460, "loss": 0.1945, "lr": 3.120592243906575e-06, "epoch": 13.208191126279864, "percentage": 66.04, "elapsed_time": "1:18:34", "remaining_time": "0:40:24", "throughput": 5500.37, "total_tokens": 25932416} {"current_steps": 42575, "total_steps": 64460, "loss": 0.2039, "lr": 3.119337782658981e-06, "epoch": 13.20974247595408, "percentage": 66.05, "elapsed_time": "1:18:35", "remaining_time": "0:40:23", "throughput": 5500.38, "total_tokens": 25935328} {"current_steps": 42580, "total_steps": 64460, "loss": 0.1469, "lr": 3.1180834592861977e-06, "epoch": 13.211293825628296, "percentage": 66.06, "elapsed_time": "1:18:35", "remaining_time": "0:40:23", "throughput": 5500.44, "total_tokens": 25938304} {"current_steps": 42585, "total_steps": 64460, "loss": 0.1923, "lr": 3.116829273880181e-06, "epoch": 13.212845175302514, "percentage": 66.06, "elapsed_time": "1:18:36", "remaining_time": "0:40:22", "throughput": 5500.53, "total_tokens": 25941664} {"current_steps": 42590, "total_steps": 64460, "loss": 0.183, "lr": 3.1155752265328786e-06, "epoch": 13.21439652497673, "percentage": 66.07, "elapsed_time": "1:18:36", "remaining_time": "0:40:22", "throughput": 5500.56, "total_tokens": 25944352} {"current_steps": 42595, "total_steps": 64460, "loss": 0.2133, "lr": 3.1143213173362273e-06, "epoch": 13.215947874650947, "percentage": 66.08, "elapsed_time": "1:18:37", "remaining_time": "0:40:21", "throughput": 5500.7, "total_tokens": 25948096} {"current_steps": 42600, "total_steps": 64460, "loss": 0.1954, "lr": 3.1130675463821543e-06, "epoch": 13.217499224325163, "percentage": 66.09, "elapsed_time": "1:18:37", "remaining_time": "0:40:20", "throughput": 5500.73, "total_tokens": 25950944} {"current_steps": 42605, "total_steps": 64460, "loss": 0.2423, "lr": 3.111813913762574e-06, "epoch": 13.219050573999379, "percentage": 66.1, "elapsed_time": "1:18:38", "remaining_time": "0:40:20", "throughput": 5500.84, "total_tokens": 25954688} {"current_steps": 42610, "total_steps": 64460, "loss": 0.1832, "lr": 3.1105604195693938e-06, "epoch": 13.220601923673597, "percentage": 66.1, "elapsed_time": "1:18:38", "remaining_time": "0:40:19", "throughput": 5500.83, "total_tokens": 25957248} {"current_steps": 42615, "total_steps": 64460, "loss": 0.1985, "lr": 3.109307063894509e-06, "epoch": 13.222153273347812, "percentage": 66.11, "elapsed_time": "1:18:39", "remaining_time": "0:40:19", "throughput": 5500.81, "total_tokens": 25959872} {"current_steps": 42620, "total_steps": 64460, "loss": 0.1934, "lr": 3.1080538468298047e-06, "epoch": 13.223704623022028, "percentage": 66.12, "elapsed_time": "1:18:39", "remaining_time": "0:40:18", "throughput": 5500.83, "total_tokens": 25962784} {"current_steps": 42625, "total_steps": 64460, "loss": 0.2175, "lr": 3.1068007684671584e-06, "epoch": 13.225255972696246, "percentage": 66.13, "elapsed_time": "1:18:40", "remaining_time": "0:40:18", "throughput": 5500.96, "total_tokens": 25966400} {"current_steps": 42630, "total_steps": 64460, "loss": 0.1804, "lr": 3.1055478288984343e-06, "epoch": 13.226807322370462, "percentage": 66.13, "elapsed_time": "1:18:40", "remaining_time": "0:40:17", "throughput": 5501.02, "total_tokens": 25969440} {"current_steps": 42635, "total_steps": 64460, "loss": 0.1768, "lr": 3.1042950282154884e-06, "epoch": 13.22835867204468, "percentage": 66.14, "elapsed_time": "1:18:41", "remaining_time": "0:40:16", "throughput": 5501.1, "total_tokens": 25972576} {"current_steps": 42640, "total_steps": 64460, "loss": 0.2326, "lr": 3.103042366510165e-06, "epoch": 13.229910021718895, "percentage": 66.15, "elapsed_time": "1:18:41", "remaining_time": "0:40:16", "throughput": 5501.03, "total_tokens": 25975008} {"current_steps": 42645, "total_steps": 64460, "loss": 0.2399, "lr": 3.1017898438742996e-06, "epoch": 13.231461371393111, "percentage": 66.16, "elapsed_time": "1:18:42", "remaining_time": "0:40:15", "throughput": 5500.97, "total_tokens": 25977376} {"current_steps": 42650, "total_steps": 64460, "loss": 0.1595, "lr": 3.100537460399715e-06, "epoch": 13.233012721067329, "percentage": 66.17, "elapsed_time": "1:18:42", "remaining_time": "0:40:15", "throughput": 5500.95, "total_tokens": 25979936} {"current_steps": 42655, "total_steps": 64460, "loss": 0.2104, "lr": 3.0992852161782296e-06, "epoch": 13.234564070741545, "percentage": 66.17, "elapsed_time": "1:18:43", "remaining_time": "0:40:14", "throughput": 5500.96, "total_tokens": 25982944} {"current_steps": 42660, "total_steps": 64460, "loss": 0.1618, "lr": 3.098033111301646e-06, "epoch": 13.236115420415763, "percentage": 66.18, "elapsed_time": "1:18:43", "remaining_time": "0:40:13", "throughput": 5501.0, "total_tokens": 25985696} {"current_steps": 42665, "total_steps": 64460, "loss": 0.1843, "lr": 3.0967811458617568e-06, "epoch": 13.237666770089978, "percentage": 66.19, "elapsed_time": "1:18:44", "remaining_time": "0:40:13", "throughput": 5501.04, "total_tokens": 25988736} {"current_steps": 42670, "total_steps": 64460, "loss": 0.1449, "lr": 3.0955293199503477e-06, "epoch": 13.239218119764194, "percentage": 66.2, "elapsed_time": "1:18:44", "remaining_time": "0:40:12", "throughput": 5501.03, "total_tokens": 25991360} {"current_steps": 42675, "total_steps": 64460, "loss": 0.2081, "lr": 3.0942776336591918e-06, "epoch": 13.240769469438412, "percentage": 66.2, "elapsed_time": "1:18:45", "remaining_time": "0:40:12", "throughput": 5501.18, "total_tokens": 25995424} {"current_steps": 42680, "total_steps": 64460, "loss": 0.268, "lr": 3.093026087080053e-06, "epoch": 13.242320819112628, "percentage": 66.21, "elapsed_time": "1:18:45", "remaining_time": "0:40:11", "throughput": 5501.25, "total_tokens": 25998624} {"current_steps": 42685, "total_steps": 64460, "loss": 0.187, "lr": 3.0917746803046835e-06, "epoch": 13.243872168786844, "percentage": 66.22, "elapsed_time": "1:18:46", "remaining_time": "0:40:11", "throughput": 5501.21, "total_tokens": 26000992} {"current_steps": 42690, "total_steps": 64460, "loss": 0.1768, "lr": 3.0905234134248264e-06, "epoch": 13.245423518461061, "percentage": 66.23, "elapsed_time": "1:18:46", "remaining_time": "0:40:10", "throughput": 5501.2, "total_tokens": 26003712} {"current_steps": 42695, "total_steps": 64460, "loss": 0.2674, "lr": 3.0892722865322144e-06, "epoch": 13.246974868135277, "percentage": 66.23, "elapsed_time": "1:18:47", "remaining_time": "0:40:09", "throughput": 5501.1, "total_tokens": 26005920} {"current_steps": 42700, "total_steps": 64460, "loss": 0.2452, "lr": 3.088021299718571e-06, "epoch": 13.248526217809495, "percentage": 66.24, "elapsed_time": "1:18:47", "remaining_time": "0:40:09", "throughput": 5501.18, "total_tokens": 26009056} {"current_steps": 42705, "total_steps": 64460, "loss": 0.215, "lr": 3.086770453075607e-06, "epoch": 13.25007756748371, "percentage": 66.25, "elapsed_time": "1:18:48", "remaining_time": "0:40:08", "throughput": 5501.22, "total_tokens": 26011936} {"current_steps": 42710, "total_steps": 64460, "loss": 0.1889, "lr": 3.085519746695025e-06, "epoch": 13.251628917157927, "percentage": 66.26, "elapsed_time": "1:18:48", "remaining_time": "0:40:08", "throughput": 5501.2, "total_tokens": 26014464} {"current_steps": 42715, "total_steps": 64460, "loss": 0.2366, "lr": 3.0842691806685155e-06, "epoch": 13.253180266832144, "percentage": 66.27, "elapsed_time": "1:18:49", "remaining_time": "0:40:07", "throughput": 5501.25, "total_tokens": 26017312} {"current_steps": 42720, "total_steps": 64460, "loss": 0.2637, "lr": 3.0830187550877614e-06, "epoch": 13.25473161650636, "percentage": 66.27, "elapsed_time": "1:18:49", "remaining_time": "0:40:07", "throughput": 5501.19, "total_tokens": 26019936} {"current_steps": 42725, "total_steps": 64460, "loss": 0.2068, "lr": 3.0817684700444337e-06, "epoch": 13.256282966180578, "percentage": 66.28, "elapsed_time": "1:18:50", "remaining_time": "0:40:06", "throughput": 5501.21, "total_tokens": 26022816} {"current_steps": 42730, "total_steps": 64460, "loss": 0.2206, "lr": 3.080518325630192e-06, "epoch": 13.257834315854794, "percentage": 66.29, "elapsed_time": "1:18:50", "remaining_time": "0:40:05", "throughput": 5501.24, "total_tokens": 26025792} {"current_steps": 42735, "total_steps": 64460, "loss": 0.2459, "lr": 3.0792683219366872e-06, "epoch": 13.25938566552901, "percentage": 66.3, "elapsed_time": "1:18:51", "remaining_time": "0:40:05", "throughput": 5501.43, "total_tokens": 26031040} {"current_steps": 42740, "total_steps": 64460, "loss": 0.1954, "lr": 3.0780184590555583e-06, "epoch": 13.260937015203227, "percentage": 66.3, "elapsed_time": "1:18:52", "remaining_time": "0:40:04", "throughput": 5501.55, "total_tokens": 26034720} {"current_steps": 42745, "total_steps": 64460, "loss": 0.1897, "lr": 3.0767687370784373e-06, "epoch": 13.262488364877443, "percentage": 66.31, "elapsed_time": "1:18:52", "remaining_time": "0:40:04", "throughput": 5501.66, "total_tokens": 26038272} {"current_steps": 42750, "total_steps": 64460, "loss": 0.2426, "lr": 3.075519156096942e-06, "epoch": 13.264039714551659, "percentage": 66.32, "elapsed_time": "1:18:53", "remaining_time": "0:40:03", "throughput": 5501.79, "total_tokens": 26041952} {"current_steps": 42755, "total_steps": 64460, "loss": 0.2014, "lr": 3.074269716202681e-06, "epoch": 13.265591064225877, "percentage": 66.33, "elapsed_time": "1:18:53", "remaining_time": "0:40:03", "throughput": 5501.76, "total_tokens": 26044640} {"current_steps": 42760, "total_steps": 64460, "loss": 0.198, "lr": 3.073020417487255e-06, "epoch": 13.267142413900093, "percentage": 66.34, "elapsed_time": "1:18:54", "remaining_time": "0:40:02", "throughput": 5501.81, "total_tokens": 26047520} {"current_steps": 42765, "total_steps": 64460, "loss": 0.2671, "lr": 3.071771260042251e-06, "epoch": 13.26869376357431, "percentage": 66.34, "elapsed_time": "1:18:54", "remaining_time": "0:40:02", "throughput": 5501.78, "total_tokens": 26050080} {"current_steps": 42770, "total_steps": 64460, "loss": 0.2197, "lr": 3.0705222439592474e-06, "epoch": 13.270245113248526, "percentage": 66.35, "elapsed_time": "1:18:55", "remaining_time": "0:40:01", "throughput": 5501.9, "total_tokens": 26053568} {"current_steps": 42775, "total_steps": 64460, "loss": 0.1733, "lr": 3.0692733693298103e-06, "epoch": 13.271796462922742, "percentage": 66.36, "elapsed_time": "1:18:55", "remaining_time": "0:40:00", "throughput": 5501.91, "total_tokens": 26056736} {"current_steps": 42780, "total_steps": 64460, "loss": 0.2365, "lr": 3.068024636245499e-06, "epoch": 13.27334781259696, "percentage": 66.37, "elapsed_time": "1:18:56", "remaining_time": "0:40:00", "throughput": 5501.8, "total_tokens": 26058656} {"current_steps": 42785, "total_steps": 64460, "loss": 0.2011, "lr": 3.0667760447978613e-06, "epoch": 13.274899162271176, "percentage": 66.37, "elapsed_time": "1:18:56", "remaining_time": "0:39:59", "throughput": 5501.91, "total_tokens": 26061952} {"current_steps": 42790, "total_steps": 64460, "loss": 0.2284, "lr": 3.0655275950784314e-06, "epoch": 13.276450511945393, "percentage": 66.38, "elapsed_time": "1:18:57", "remaining_time": "0:39:59", "throughput": 5501.87, "total_tokens": 26064256} {"current_steps": 42795, "total_steps": 64460, "loss": 0.2621, "lr": 3.064279287178736e-06, "epoch": 13.27800186161961, "percentage": 66.39, "elapsed_time": "1:18:57", "remaining_time": "0:39:58", "throughput": 5501.94, "total_tokens": 26067232} {"current_steps": 42800, "total_steps": 64460, "loss": 0.1708, "lr": 3.0630311211902917e-06, "epoch": 13.279553211293825, "percentage": 66.4, "elapsed_time": "1:18:58", "remaining_time": "0:39:57", "throughput": 5501.9, "total_tokens": 26069664} {"current_steps": 42805, "total_steps": 64460, "loss": 0.208, "lr": 3.061783097204604e-06, "epoch": 13.281104560968043, "percentage": 66.41, "elapsed_time": "1:18:58", "remaining_time": "0:39:57", "throughput": 5502.0, "total_tokens": 26073120} {"current_steps": 42810, "total_steps": 64460, "loss": 0.2033, "lr": 3.0605352153131664e-06, "epoch": 13.282655910642259, "percentage": 66.41, "elapsed_time": "1:18:59", "remaining_time": "0:39:56", "throughput": 5502.04, "total_tokens": 26075904} {"current_steps": 42815, "total_steps": 64460, "loss": 0.2539, "lr": 3.059287475607464e-06, "epoch": 13.284207260316474, "percentage": 66.42, "elapsed_time": "1:19:00", "remaining_time": "0:39:56", "throughput": 5502.27, "total_tokens": 26081056} {"current_steps": 42820, "total_steps": 64460, "loss": 0.2404, "lr": 3.058039878178971e-06, "epoch": 13.285758609990692, "percentage": 66.43, "elapsed_time": "1:19:00", "remaining_time": "0:39:55", "throughput": 5502.29, "total_tokens": 26084608} {"current_steps": 42825, "total_steps": 64460, "loss": 0.1801, "lr": 3.056792423119152e-06, "epoch": 13.287309959664908, "percentage": 66.44, "elapsed_time": "1:19:01", "remaining_time": "0:39:55", "throughput": 5502.41, "total_tokens": 26088576} {"current_steps": 42830, "total_steps": 64460, "loss": 0.2167, "lr": 3.055545110519459e-06, "epoch": 13.288861309339126, "percentage": 66.44, "elapsed_time": "1:19:01", "remaining_time": "0:39:54", "throughput": 5502.53, "total_tokens": 26092000} {"current_steps": 42835, "total_steps": 64460, "loss": 0.1949, "lr": 3.0542979404713347e-06, "epoch": 13.290412659013342, "percentage": 66.45, "elapsed_time": "1:19:02", "remaining_time": "0:39:54", "throughput": 5502.67, "total_tokens": 26096096} {"current_steps": 42840, "total_steps": 64460, "loss": 0.2235, "lr": 3.0530509130662123e-06, "epoch": 13.291964008687557, "percentage": 66.46, "elapsed_time": "1:19:02", "remaining_time": "0:39:53", "throughput": 5502.68, "total_tokens": 26099104} {"current_steps": 42845, "total_steps": 64460, "loss": 0.2172, "lr": 3.051804028395513e-06, "epoch": 13.293515358361775, "percentage": 66.47, "elapsed_time": "1:19:03", "remaining_time": "0:39:53", "throughput": 5502.64, "total_tokens": 26101376} {"current_steps": 42850, "total_steps": 64460, "loss": 0.1814, "lr": 3.0505572865506493e-06, "epoch": 13.295066708035991, "percentage": 66.48, "elapsed_time": "1:19:03", "remaining_time": "0:39:52", "throughput": 5502.62, "total_tokens": 26104096} {"current_steps": 42855, "total_steps": 64460, "loss": 0.1879, "lr": 3.0493106876230204e-06, "epoch": 13.296618057710209, "percentage": 66.48, "elapsed_time": "1:19:04", "remaining_time": "0:39:51", "throughput": 5502.65, "total_tokens": 26106848} {"current_steps": 42860, "total_steps": 64460, "loss": 0.2419, "lr": 3.0480642317040187e-06, "epoch": 13.298169407384425, "percentage": 66.49, "elapsed_time": "1:19:04", "remaining_time": "0:39:51", "throughput": 5502.68, "total_tokens": 26109536} {"current_steps": 42865, "total_steps": 64460, "loss": 0.1825, "lr": 3.0468179188850226e-06, "epoch": 13.29972075705864, "percentage": 66.5, "elapsed_time": "1:19:05", "remaining_time": "0:39:50", "throughput": 5502.67, "total_tokens": 26112288} {"current_steps": 42870, "total_steps": 64460, "loss": 0.2214, "lr": 3.0455717492574027e-06, "epoch": 13.301272106732858, "percentage": 66.51, "elapsed_time": "1:19:05", "remaining_time": "0:39:50", "throughput": 5502.68, "total_tokens": 26115136} {"current_steps": 42875, "total_steps": 64460, "loss": 0.2299, "lr": 3.044325722912517e-06, "epoch": 13.302823456407074, "percentage": 66.51, "elapsed_time": "1:19:06", "remaining_time": "0:39:49", "throughput": 5502.63, "total_tokens": 26117792} {"current_steps": 42880, "total_steps": 64460, "loss": 0.1953, "lr": 3.043079839941715e-06, "epoch": 13.304374806081292, "percentage": 66.52, "elapsed_time": "1:19:06", "remaining_time": "0:39:48", "throughput": 5502.61, "total_tokens": 26120864} {"current_steps": 42885, "total_steps": 64460, "loss": 0.205, "lr": 3.041834100436334e-06, "epoch": 13.305926155755508, "percentage": 66.53, "elapsed_time": "1:19:07", "remaining_time": "0:39:48", "throughput": 5502.52, "total_tokens": 26123456} {"current_steps": 42890, "total_steps": 64460, "loss": 0.1956, "lr": 3.0405885044877008e-06, "epoch": 13.307477505429723, "percentage": 66.54, "elapsed_time": "1:19:08", "remaining_time": "0:39:47", "throughput": 5502.58, "total_tokens": 26127040} {"current_steps": 42895, "total_steps": 64460, "loss": 0.1706, "lr": 3.0393430521871326e-06, "epoch": 13.309028855103941, "percentage": 66.55, "elapsed_time": "1:19:08", "remaining_time": "0:39:47", "throughput": 5502.55, "total_tokens": 26129728} {"current_steps": 42900, "total_steps": 64460, "loss": 0.1831, "lr": 3.038097743625937e-06, "epoch": 13.310580204778157, "percentage": 66.55, "elapsed_time": "1:19:09", "remaining_time": "0:39:46", "throughput": 5502.51, "total_tokens": 26132224} {"current_steps": 42905, "total_steps": 64460, "loss": 0.177, "lr": 3.03685257889541e-06, "epoch": 13.312131554452373, "percentage": 66.56, "elapsed_time": "1:19:09", "remaining_time": "0:39:46", "throughput": 5502.54, "total_tokens": 26135328} {"current_steps": 42910, "total_steps": 64460, "loss": 0.2085, "lr": 3.035607558086836e-06, "epoch": 13.31368290412659, "percentage": 66.57, "elapsed_time": "1:19:10", "remaining_time": "0:39:45", "throughput": 5502.51, "total_tokens": 26137824} {"current_steps": 42915, "total_steps": 64460, "loss": 0.1979, "lr": 3.0343626812914896e-06, "epoch": 13.315234253800806, "percentage": 66.58, "elapsed_time": "1:19:10", "remaining_time": "0:39:45", "throughput": 5502.48, "total_tokens": 26140512} {"current_steps": 42920, "total_steps": 64460, "loss": 0.1848, "lr": 3.033117948600635e-06, "epoch": 13.316785603475024, "percentage": 66.58, "elapsed_time": "1:19:11", "remaining_time": "0:39:44", "throughput": 5502.49, "total_tokens": 26143520} {"current_steps": 42925, "total_steps": 64460, "loss": 0.2126, "lr": 3.031873360105526e-06, "epoch": 13.31833695314924, "percentage": 66.59, "elapsed_time": "1:19:11", "remaining_time": "0:39:43", "throughput": 5502.42, "total_tokens": 26145984} {"current_steps": 42930, "total_steps": 64460, "loss": 0.1677, "lr": 3.0306289158974066e-06, "epoch": 13.319888302823456, "percentage": 66.6, "elapsed_time": "1:19:12", "remaining_time": "0:39:43", "throughput": 5502.49, "total_tokens": 26149440} {"current_steps": 42935, "total_steps": 64460, "loss": 0.2199, "lr": 3.029384616067508e-06, "epoch": 13.321439652497673, "percentage": 66.61, "elapsed_time": "1:19:12", "remaining_time": "0:39:42", "throughput": 5502.49, "total_tokens": 26152160} {"current_steps": 42940, "total_steps": 64460, "loss": 0.2081, "lr": 3.0281404607070532e-06, "epoch": 13.32299100217189, "percentage": 66.61, "elapsed_time": "1:19:13", "remaining_time": "0:39:42", "throughput": 5502.33, "total_tokens": 26154144} {"current_steps": 42945, "total_steps": 64460, "loss": 0.206, "lr": 3.0268964499072522e-06, "epoch": 13.324542351846105, "percentage": 66.62, "elapsed_time": "1:19:13", "remaining_time": "0:39:41", "throughput": 5502.4, "total_tokens": 26157728} {"current_steps": 42950, "total_steps": 64460, "loss": 0.1791, "lr": 3.0256525837593063e-06, "epoch": 13.326093701520323, "percentage": 66.63, "elapsed_time": "1:19:14", "remaining_time": "0:39:41", "throughput": 5502.5, "total_tokens": 26161312} {"current_steps": 42955, "total_steps": 64460, "loss": 0.2105, "lr": 3.0244088623544053e-06, "epoch": 13.327645051194539, "percentage": 66.64, "elapsed_time": "1:19:14", "remaining_time": "0:39:40", "throughput": 5502.44, "total_tokens": 26164032} {"current_steps": 42960, "total_steps": 64460, "loss": 0.1629, "lr": 3.0231652857837302e-06, "epoch": 13.329196400868756, "percentage": 66.65, "elapsed_time": "1:19:15", "remaining_time": "0:39:39", "throughput": 5502.5, "total_tokens": 26167520} {"current_steps": 42965, "total_steps": 64460, "loss": 0.1559, "lr": 3.021921854138449e-06, "epoch": 13.330747750542972, "percentage": 66.65, "elapsed_time": "1:19:16", "remaining_time": "0:39:39", "throughput": 5502.59, "total_tokens": 26171008} {"current_steps": 42970, "total_steps": 64460, "loss": 0.2305, "lr": 3.0206785675097195e-06, "epoch": 13.332299100217188, "percentage": 66.66, "elapsed_time": "1:19:16", "remaining_time": "0:39:38", "throughput": 5502.6, "total_tokens": 26173952} {"current_steps": 42975, "total_steps": 64460, "loss": 0.225, "lr": 3.0194354259886906e-06, "epoch": 13.333850449891406, "percentage": 66.67, "elapsed_time": "1:19:17", "remaining_time": "0:39:38", "throughput": 5502.48, "total_tokens": 26176000} {"current_steps": 42980, "total_steps": 64460, "loss": 0.2313, "lr": 3.0181924296664965e-06, "epoch": 13.335401799565622, "percentage": 66.68, "elapsed_time": "1:19:17", "remaining_time": "0:39:37", "throughput": 5502.6, "total_tokens": 26180256} {"current_steps": 42985, "total_steps": 64460, "loss": 0.1947, "lr": 3.016949578634267e-06, "epoch": 13.33695314923984, "percentage": 66.68, "elapsed_time": "1:19:18", "remaining_time": "0:39:37", "throughput": 5502.63, "total_tokens": 26183424} {"current_steps": 42990, "total_steps": 64460, "loss": 0.1992, "lr": 3.0157068729831157e-06, "epoch": 13.338504498914055, "percentage": 66.69, "elapsed_time": "1:19:18", "remaining_time": "0:39:36", "throughput": 5502.68, "total_tokens": 26186560} {"current_steps": 42995, "total_steps": 64460, "loss": 0.2058, "lr": 3.0144643128041483e-06, "epoch": 13.340055848588271, "percentage": 66.7, "elapsed_time": "1:19:19", "remaining_time": "0:39:36", "throughput": 5502.76, "total_tokens": 26190208} {"current_steps": 43000, "total_steps": 64460, "loss": 0.1622, "lr": 3.0132218981884587e-06, "epoch": 13.341607198262489, "percentage": 66.71, "elapsed_time": "1:19:20", "remaining_time": "0:39:35", "throughput": 5502.84, "total_tokens": 26193696} {"current_steps": 43005, "total_steps": 64460, "loss": 0.1737, "lr": 3.011979629227131e-06, "epoch": 13.343158547936705, "percentage": 66.72, "elapsed_time": "1:19:20", "remaining_time": "0:39:35", "throughput": 5503.0, "total_tokens": 26198144} {"current_steps": 43010, "total_steps": 64460, "loss": 0.2251, "lr": 3.0107375060112386e-06, "epoch": 13.344709897610922, "percentage": 66.72, "elapsed_time": "1:19:21", "remaining_time": "0:39:34", "throughput": 5503.03, "total_tokens": 26200992} {"current_steps": 43015, "total_steps": 64460, "loss": 0.1973, "lr": 3.0094955286318417e-06, "epoch": 13.346261247285138, "percentage": 66.73, "elapsed_time": "1:19:21", "remaining_time": "0:39:33", "throughput": 5502.91, "total_tokens": 26203392} {"current_steps": 43020, "total_steps": 64460, "loss": 0.2071, "lr": 3.0082536971799955e-06, "epoch": 13.347812596959354, "percentage": 66.74, "elapsed_time": "1:19:22", "remaining_time": "0:39:33", "throughput": 5502.92, "total_tokens": 26206304} {"current_steps": 43025, "total_steps": 64460, "loss": 0.1714, "lr": 3.0070120117467373e-06, "epoch": 13.349363946633572, "percentage": 66.75, "elapsed_time": "1:19:22", "remaining_time": "0:39:32", "throughput": 5502.91, "total_tokens": 26208960} {"current_steps": 43030, "total_steps": 64460, "loss": 0.1871, "lr": 3.0057704724231007e-06, "epoch": 13.350915296307788, "percentage": 66.75, "elapsed_time": "1:19:23", "remaining_time": "0:39:32", "throughput": 5502.88, "total_tokens": 26211552} {"current_steps": 43035, "total_steps": 64460, "loss": 0.2536, "lr": 3.0045290793001037e-06, "epoch": 13.352466645982004, "percentage": 66.76, "elapsed_time": "1:19:23", "remaining_time": "0:39:31", "throughput": 5502.83, "total_tokens": 26214176} {"current_steps": 43040, "total_steps": 64460, "loss": 0.1855, "lr": 3.0032878324687536e-06, "epoch": 13.354017995656221, "percentage": 66.77, "elapsed_time": "1:19:24", "remaining_time": "0:39:31", "throughput": 5502.81, "total_tokens": 26216896} {"current_steps": 43045, "total_steps": 64460, "loss": 0.2159, "lr": 3.0020467320200513e-06, "epoch": 13.355569345330437, "percentage": 66.78, "elapsed_time": "1:19:24", "remaining_time": "0:39:30", "throughput": 5502.86, "total_tokens": 26220192} {"current_steps": 43050, "total_steps": 64460, "loss": 0.2252, "lr": 3.0008057780449827e-06, "epoch": 13.357120695004655, "percentage": 66.79, "elapsed_time": "1:19:25", "remaining_time": "0:39:29", "throughput": 5502.75, "total_tokens": 26222688} {"current_steps": 43055, "total_steps": 64460, "loss": 0.1624, "lr": 2.999564970634525e-06, "epoch": 13.35867204467887, "percentage": 66.79, "elapsed_time": "1:19:25", "remaining_time": "0:39:29", "throughput": 5502.86, "total_tokens": 26226240} {"current_steps": 43060, "total_steps": 64460, "loss": 0.2448, "lr": 2.9983243098796434e-06, "epoch": 13.360223394353087, "percentage": 66.8, "elapsed_time": "1:19:26", "remaining_time": "0:39:28", "throughput": 5502.81, "total_tokens": 26228864} {"current_steps": 43065, "total_steps": 64460, "loss": 0.1986, "lr": 2.9970837958712927e-06, "epoch": 13.361774744027304, "percentage": 66.81, "elapsed_time": "1:19:26", "remaining_time": "0:39:28", "throughput": 5502.86, "total_tokens": 26231808} {"current_steps": 43070, "total_steps": 64460, "loss": 0.2186, "lr": 2.995843428700419e-06, "epoch": 13.36332609370152, "percentage": 66.82, "elapsed_time": "1:19:27", "remaining_time": "0:39:27", "throughput": 5502.89, "total_tokens": 26234656} {"current_steps": 43075, "total_steps": 64460, "loss": 0.2086, "lr": 2.9946032084579533e-06, "epoch": 13.364877443375736, "percentage": 66.82, "elapsed_time": "1:19:28", "remaining_time": "0:39:27", "throughput": 5502.98, "total_tokens": 26238656} {"current_steps": 43080, "total_steps": 64460, "loss": 0.2192, "lr": 2.9933631352348215e-06, "epoch": 13.366428793049954, "percentage": 66.83, "elapsed_time": "1:19:28", "remaining_time": "0:39:26", "throughput": 5502.96, "total_tokens": 26241248} {"current_steps": 43085, "total_steps": 64460, "loss": 0.1841, "lr": 2.992123209121933e-06, "epoch": 13.36798014272417, "percentage": 66.84, "elapsed_time": "1:19:29", "remaining_time": "0:39:26", "throughput": 5503.03, "total_tokens": 26244736} {"current_steps": 43090, "total_steps": 64460, "loss": 0.221, "lr": 2.99088343021019e-06, "epoch": 13.369531492398387, "percentage": 66.85, "elapsed_time": "1:19:29", "remaining_time": "0:39:25", "throughput": 5502.96, "total_tokens": 26247168} {"current_steps": 43095, "total_steps": 64460, "loss": 0.2296, "lr": 2.9896437985904836e-06, "epoch": 13.371082842072603, "percentage": 66.86, "elapsed_time": "1:19:30", "remaining_time": "0:39:24", "throughput": 5502.83, "total_tokens": 26249664} {"current_steps": 43100, "total_steps": 64460, "loss": 0.1893, "lr": 2.988404314353691e-06, "epoch": 13.372634191746819, "percentage": 66.86, "elapsed_time": "1:19:30", "remaining_time": "0:39:24", "throughput": 5502.91, "total_tokens": 26253248} {"current_steps": 43105, "total_steps": 64460, "loss": 0.1591, "lr": 2.987164977590685e-06, "epoch": 13.374185541421037, "percentage": 66.87, "elapsed_time": "1:19:31", "remaining_time": "0:39:23", "throughput": 5502.96, "total_tokens": 26256608} {"current_steps": 43110, "total_steps": 64460, "loss": 0.2092, "lr": 2.9859257883923215e-06, "epoch": 13.375736891095253, "percentage": 66.88, "elapsed_time": "1:19:32", "remaining_time": "0:39:23", "throughput": 5503.08, "total_tokens": 26260832} {"current_steps": 43115, "total_steps": 64460, "loss": 0.235, "lr": 2.984686746849448e-06, "epoch": 13.37728824076947, "percentage": 66.89, "elapsed_time": "1:19:32", "remaining_time": "0:39:22", "throughput": 5503.1, "total_tokens": 26264032} {"current_steps": 43120, "total_steps": 64460, "loss": 0.1886, "lr": 2.9834478530529005e-06, "epoch": 13.378839590443686, "percentage": 66.89, "elapsed_time": "1:19:33", "remaining_time": "0:39:22", "throughput": 5503.08, "total_tokens": 26266688} {"current_steps": 43125, "total_steps": 64460, "loss": 0.2034, "lr": 2.982209107093505e-06, "epoch": 13.380390940117902, "percentage": 66.9, "elapsed_time": "1:19:33", "remaining_time": "0:39:21", "throughput": 5503.14, "total_tokens": 26269920} {"current_steps": 43130, "total_steps": 64460, "loss": 0.2611, "lr": 2.980970509062076e-06, "epoch": 13.38194228979212, "percentage": 66.91, "elapsed_time": "1:19:34", "remaining_time": "0:39:21", "throughput": 5503.26, "total_tokens": 26273280} {"current_steps": 43135, "total_steps": 64460, "loss": 0.1721, "lr": 2.9797320590494176e-06, "epoch": 13.383493639466336, "percentage": 66.92, "elapsed_time": "1:19:34", "remaining_time": "0:39:20", "throughput": 5503.31, "total_tokens": 26276192} {"current_steps": 43140, "total_steps": 64460, "loss": 0.2086, "lr": 2.9784937571463233e-06, "epoch": 13.385044989140553, "percentage": 66.93, "elapsed_time": "1:19:35", "remaining_time": "0:39:19", "throughput": 5503.4, "total_tokens": 26279424} {"current_steps": 43145, "total_steps": 64460, "loss": 0.1774, "lr": 2.9772556034435745e-06, "epoch": 13.386596338814769, "percentage": 66.93, "elapsed_time": "1:19:35", "remaining_time": "0:39:19", "throughput": 5503.45, "total_tokens": 26282880} {"current_steps": 43150, "total_steps": 64460, "loss": 0.2294, "lr": 2.976017598031943e-06, "epoch": 13.388147688488985, "percentage": 66.94, "elapsed_time": "1:19:36", "remaining_time": "0:39:18", "throughput": 5503.52, "total_tokens": 26286112} {"current_steps": 43155, "total_steps": 64460, "loss": 0.2132, "lr": 2.9747797410021887e-06, "epoch": 13.389699038163203, "percentage": 66.95, "elapsed_time": "1:19:36", "remaining_time": "0:39:18", "throughput": 5503.5, "total_tokens": 26288672} {"current_steps": 43160, "total_steps": 64460, "loss": 0.2285, "lr": 2.9735420324450608e-06, "epoch": 13.391250387837419, "percentage": 66.96, "elapsed_time": "1:19:37", "remaining_time": "0:39:17", "throughput": 5503.7, "total_tokens": 26293856} {"current_steps": 43165, "total_steps": 64460, "loss": 0.1563, "lr": 2.9723044724513e-06, "epoch": 13.392801737511634, "percentage": 66.96, "elapsed_time": "1:19:37", "remaining_time": "0:39:17", "throughput": 5503.59, "total_tokens": 26296000} {"current_steps": 43170, "total_steps": 64460, "loss": 0.2062, "lr": 2.9710670611116327e-06, "epoch": 13.394353087185852, "percentage": 66.97, "elapsed_time": "1:19:38", "remaining_time": "0:39:16", "throughput": 5503.66, "total_tokens": 26299264} {"current_steps": 43175, "total_steps": 64460, "loss": 0.1983, "lr": 2.9698297985167755e-06, "epoch": 13.395904436860068, "percentage": 66.98, "elapsed_time": "1:19:39", "remaining_time": "0:39:16", "throughput": 5503.7, "total_tokens": 26302336} {"current_steps": 43180, "total_steps": 64460, "loss": 0.2297, "lr": 2.968592684757436e-06, "epoch": 13.397455786534286, "percentage": 66.99, "elapsed_time": "1:19:39", "remaining_time": "0:39:15", "throughput": 5503.71, "total_tokens": 26305216} {"current_steps": 43185, "total_steps": 64460, "loss": 0.1858, "lr": 2.9673557199243075e-06, "epoch": 13.399007136208501, "percentage": 67.0, "elapsed_time": "1:19:40", "remaining_time": "0:39:14", "throughput": 5503.75, "total_tokens": 26308512} {"current_steps": 43190, "total_steps": 64460, "loss": 0.1635, "lr": 2.9661189041080753e-06, "epoch": 13.400558485882717, "percentage": 67.0, "elapsed_time": "1:19:40", "remaining_time": "0:39:14", "throughput": 5503.76, "total_tokens": 26311136} {"current_steps": 43195, "total_steps": 64460, "loss": 0.1794, "lr": 2.9648822373994112e-06, "epoch": 13.402109835556935, "percentage": 67.01, "elapsed_time": "1:19:41", "remaining_time": "0:39:13", "throughput": 5503.81, "total_tokens": 26314144} {"current_steps": 43200, "total_steps": 64460, "loss": 0.2093, "lr": 2.963645719888979e-06, "epoch": 13.403661185231151, "percentage": 67.02, "elapsed_time": "1:19:41", "remaining_time": "0:39:13", "throughput": 5503.92, "total_tokens": 26318432} {"current_steps": 43205, "total_steps": 64460, "loss": 0.1685, "lr": 2.9624093516674297e-06, "epoch": 13.405212534905367, "percentage": 67.03, "elapsed_time": "1:19:42", "remaining_time": "0:39:12", "throughput": 5503.9, "total_tokens": 26320832} {"current_steps": 43210, "total_steps": 64460, "loss": 0.2151, "lr": 2.9611731328254036e-06, "epoch": 13.406763884579584, "percentage": 67.03, "elapsed_time": "1:19:42", "remaining_time": "0:39:12", "throughput": 5503.91, "total_tokens": 26323648} {"current_steps": 43215, "total_steps": 64460, "loss": 0.1723, "lr": 2.9599370634535304e-06, "epoch": 13.4083152342538, "percentage": 67.04, "elapsed_time": "1:19:43", "remaining_time": "0:39:11", "throughput": 5503.92, "total_tokens": 26326688} {"current_steps": 43220, "total_steps": 64460, "loss": 0.1923, "lr": 2.958701143642427e-06, "epoch": 13.409866583928018, "percentage": 67.05, "elapsed_time": "1:19:43", "remaining_time": "0:39:10", "throughput": 5503.86, "total_tokens": 26328896} {"current_steps": 43225, "total_steps": 64460, "loss": 0.192, "lr": 2.957465373482703e-06, "epoch": 13.411417933602234, "percentage": 67.06, "elapsed_time": "1:19:44", "remaining_time": "0:39:10", "throughput": 5503.83, "total_tokens": 26331328} {"current_steps": 43230, "total_steps": 64460, "loss": 0.2162, "lr": 2.956229753064955e-06, "epoch": 13.41296928327645, "percentage": 67.06, "elapsed_time": "1:19:44", "remaining_time": "0:39:09", "throughput": 5503.78, "total_tokens": 26333696} {"current_steps": 43235, "total_steps": 64460, "loss": 0.3198, "lr": 2.954994282479768e-06, "epoch": 13.414520632950667, "percentage": 67.07, "elapsed_time": "1:19:45", "remaining_time": "0:39:09", "throughput": 5503.83, "total_tokens": 26336864} {"current_steps": 43240, "total_steps": 64460, "loss": 0.1978, "lr": 2.9537589618177164e-06, "epoch": 13.416071982624883, "percentage": 67.08, "elapsed_time": "1:19:45", "remaining_time": "0:39:08", "throughput": 5504.03, "total_tokens": 26341248} {"current_steps": 43245, "total_steps": 64460, "loss": 0.2102, "lr": 2.952523791169364e-06, "epoch": 13.417623332299101, "percentage": 67.09, "elapsed_time": "1:19:46", "remaining_time": "0:39:08", "throughput": 5504.11, "total_tokens": 26344640} {"current_steps": 43250, "total_steps": 64460, "loss": 0.1776, "lr": 2.9512887706252634e-06, "epoch": 13.419174681973317, "percentage": 67.1, "elapsed_time": "1:19:46", "remaining_time": "0:39:07", "throughput": 5504.13, "total_tokens": 26347872} {"current_steps": 43255, "total_steps": 64460, "loss": 0.2362, "lr": 2.9500539002759565e-06, "epoch": 13.420726031647533, "percentage": 67.1, "elapsed_time": "1:19:47", "remaining_time": "0:39:06", "throughput": 5504.21, "total_tokens": 26351040} {"current_steps": 43260, "total_steps": 64460, "loss": 0.1815, "lr": 2.9488191802119735e-06, "epoch": 13.42227738132175, "percentage": 67.11, "elapsed_time": "1:19:47", "remaining_time": "0:39:06", "throughput": 5504.3, "total_tokens": 26354400} {"current_steps": 43265, "total_steps": 64460, "loss": 0.1992, "lr": 2.947584610523834e-06, "epoch": 13.423828730995966, "percentage": 67.12, "elapsed_time": "1:19:48", "remaining_time": "0:39:05", "throughput": 5504.29, "total_tokens": 26356864} {"current_steps": 43270, "total_steps": 64460, "loss": 0.2081, "lr": 2.946350191302047e-06, "epoch": 13.425380080670184, "percentage": 67.13, "elapsed_time": "1:19:48", "remaining_time": "0:39:05", "throughput": 5504.38, "total_tokens": 26360032} {"current_steps": 43275, "total_steps": 64460, "loss": 0.2562, "lr": 2.9451159226371097e-06, "epoch": 13.4269314303444, "percentage": 67.13, "elapsed_time": "1:19:49", "remaining_time": "0:39:04", "throughput": 5504.36, "total_tokens": 26362528} {"current_steps": 43280, "total_steps": 64460, "loss": 0.1754, "lr": 2.9438818046195084e-06, "epoch": 13.428482780018616, "percentage": 67.14, "elapsed_time": "1:19:49", "remaining_time": "0:39:04", "throughput": 5504.31, "total_tokens": 26365184} {"current_steps": 43285, "total_steps": 64460, "loss": 0.2427, "lr": 2.9426478373397193e-06, "epoch": 13.430034129692833, "percentage": 67.15, "elapsed_time": "1:19:50", "remaining_time": "0:39:03", "throughput": 5504.34, "total_tokens": 26368160} {"current_steps": 43290, "total_steps": 64460, "loss": 0.2734, "lr": 2.9414140208882063e-06, "epoch": 13.43158547936705, "percentage": 67.16, "elapsed_time": "1:19:50", "remaining_time": "0:39:02", "throughput": 5504.33, "total_tokens": 26370880} {"current_steps": 43295, "total_steps": 64460, "loss": 0.2303, "lr": 2.9401803553554233e-06, "epoch": 13.433136829041265, "percentage": 67.17, "elapsed_time": "1:19:51", "remaining_time": "0:39:02", "throughput": 5504.3, "total_tokens": 26373504} {"current_steps": 43300, "total_steps": 64460, "loss": 0.2053, "lr": 2.938946840831812e-06, "epoch": 13.434688178715483, "percentage": 67.17, "elapsed_time": "1:19:52", "remaining_time": "0:39:01", "throughput": 5504.47, "total_tokens": 26377728} {"current_steps": 43305, "total_steps": 64460, "loss": 0.2304, "lr": 2.9377134774078035e-06, "epoch": 13.436239528389699, "percentage": 67.18, "elapsed_time": "1:19:52", "remaining_time": "0:39:01", "throughput": 5504.63, "total_tokens": 26382464} {"current_steps": 43310, "total_steps": 64460, "loss": 0.1775, "lr": 2.936480265173819e-06, "epoch": 13.437790878063916, "percentage": 67.19, "elapsed_time": "1:19:53", "remaining_time": "0:39:00", "throughput": 5504.61, "total_tokens": 26384992} {"current_steps": 43315, "total_steps": 64460, "loss": 0.2206, "lr": 2.9352472042202663e-06, "epoch": 13.439342227738132, "percentage": 67.2, "elapsed_time": "1:19:53", "remaining_time": "0:39:00", "throughput": 5504.73, "total_tokens": 26389184} {"current_steps": 43320, "total_steps": 64460, "loss": 0.1855, "lr": 2.9340142946375432e-06, "epoch": 13.440893577412348, "percentage": 67.2, "elapsed_time": "1:19:54", "remaining_time": "0:38:59", "throughput": 5504.75, "total_tokens": 26392384} {"current_steps": 43325, "total_steps": 64460, "loss": 0.2304, "lr": 2.9327815365160384e-06, "epoch": 13.442444927086566, "percentage": 67.21, "elapsed_time": "1:19:54", "remaining_time": "0:38:59", "throughput": 5504.67, "total_tokens": 26394880} {"current_steps": 43330, "total_steps": 64460, "loss": 0.1967, "lr": 2.9315489299461254e-06, "epoch": 13.443996276760782, "percentage": 67.22, "elapsed_time": "1:19:55", "remaining_time": "0:38:58", "throughput": 5504.72, "total_tokens": 26398400} {"current_steps": 43335, "total_steps": 64460, "loss": 0.1969, "lr": 2.9303164750181704e-06, "epoch": 13.445547626434998, "percentage": 67.23, "elapsed_time": "1:19:56", "remaining_time": "0:38:58", "throughput": 5504.66, "total_tokens": 26401472} {"current_steps": 43340, "total_steps": 64460, "loss": 0.22, "lr": 2.929084171822526e-06, "epoch": 13.447098976109215, "percentage": 67.24, "elapsed_time": "1:19:56", "remaining_time": "0:38:57", "throughput": 5504.67, "total_tokens": 26404160} {"current_steps": 43345, "total_steps": 64460, "loss": 0.1696, "lr": 2.927852020449536e-06, "epoch": 13.448650325783431, "percentage": 67.24, "elapsed_time": "1:19:57", "remaining_time": "0:38:56", "throughput": 5504.72, "total_tokens": 26407232} {"current_steps": 43350, "total_steps": 64460, "loss": 0.1774, "lr": 2.92662002098953e-06, "epoch": 13.450201675457649, "percentage": 67.25, "elapsed_time": "1:19:57", "remaining_time": "0:38:56", "throughput": 5504.72, "total_tokens": 26410112} {"current_steps": 43355, "total_steps": 64460, "loss": 0.1846, "lr": 2.92538817353283e-06, "epoch": 13.451753025131865, "percentage": 67.26, "elapsed_time": "1:19:58", "remaining_time": "0:38:55", "throughput": 5504.76, "total_tokens": 26413248} {"current_steps": 43360, "total_steps": 64460, "loss": 0.1738, "lr": 2.924156478169743e-06, "epoch": 13.45330437480608, "percentage": 67.27, "elapsed_time": "1:19:58", "remaining_time": "0:38:55", "throughput": 5504.85, "total_tokens": 26416576} {"current_steps": 43365, "total_steps": 64460, "loss": 0.1872, "lr": 2.9229249349905686e-06, "epoch": 13.454855724480298, "percentage": 67.27, "elapsed_time": "1:19:59", "remaining_time": "0:38:54", "throughput": 5504.93, "total_tokens": 26420224} {"current_steps": 43370, "total_steps": 64460, "loss": 0.3048, "lr": 2.921693544085592e-06, "epoch": 13.456407074154514, "percentage": 67.28, "elapsed_time": "1:19:59", "remaining_time": "0:38:54", "throughput": 5504.91, "total_tokens": 26422784} {"current_steps": 43375, "total_steps": 64460, "loss": 0.1923, "lr": 2.9204623055450896e-06, "epoch": 13.457958423828732, "percentage": 67.29, "elapsed_time": "1:20:00", "remaining_time": "0:38:53", "throughput": 5504.9, "total_tokens": 26425536} {"current_steps": 43380, "total_steps": 64460, "loss": 0.1803, "lr": 2.9192312194593263e-06, "epoch": 13.459509773502948, "percentage": 67.3, "elapsed_time": "1:20:00", "remaining_time": "0:38:52", "throughput": 5504.9, "total_tokens": 26428288} {"current_steps": 43385, "total_steps": 64460, "loss": 0.1827, "lr": 2.918000285918553e-06, "epoch": 13.461061123177164, "percentage": 67.31, "elapsed_time": "1:20:01", "remaining_time": "0:38:52", "throughput": 5504.93, "total_tokens": 26431648} {"current_steps": 43390, "total_steps": 64460, "loss": 0.2058, "lr": 2.9167695050130155e-06, "epoch": 13.462612472851381, "percentage": 67.31, "elapsed_time": "1:20:01", "remaining_time": "0:38:51", "throughput": 5504.86, "total_tokens": 26434016} {"current_steps": 43395, "total_steps": 64460, "loss": 0.2193, "lr": 2.9155388768329407e-06, "epoch": 13.464163822525597, "percentage": 67.32, "elapsed_time": "1:20:02", "remaining_time": "0:38:51", "throughput": 5504.76, "total_tokens": 26436416} {"current_steps": 43400, "total_steps": 64460, "loss": 0.2038, "lr": 2.914308401468552e-06, "epoch": 13.465715172199815, "percentage": 67.33, "elapsed_time": "1:20:03", "remaining_time": "0:38:50", "throughput": 5504.9, "total_tokens": 26440320} {"current_steps": 43405, "total_steps": 64460, "loss": 0.2041, "lr": 2.9130780790100533e-06, "epoch": 13.46726652187403, "percentage": 67.34, "elapsed_time": "1:20:03", "remaining_time": "0:38:50", "throughput": 5505.01, "total_tokens": 26444448} {"current_steps": 43410, "total_steps": 64460, "loss": 0.1901, "lr": 2.911847909547646e-06, "epoch": 13.468817871548247, "percentage": 67.34, "elapsed_time": "1:20:04", "remaining_time": "0:38:49", "throughput": 5505.09, "total_tokens": 26447936} {"current_steps": 43415, "total_steps": 64460, "loss": 0.2131, "lr": 2.9106178931715125e-06, "epoch": 13.470369221222464, "percentage": 67.35, "elapsed_time": "1:20:04", "remaining_time": "0:38:49", "throughput": 5505.13, "total_tokens": 26451168} {"current_steps": 43420, "total_steps": 64460, "loss": 0.1974, "lr": 2.909388029971832e-06, "epoch": 13.47192057089668, "percentage": 67.36, "elapsed_time": "1:20:05", "remaining_time": "0:38:48", "throughput": 5505.14, "total_tokens": 26453888} {"current_steps": 43425, "total_steps": 64460, "loss": 0.2332, "lr": 2.908158320038763e-06, "epoch": 13.473471920570896, "percentage": 67.37, "elapsed_time": "1:20:05", "remaining_time": "0:38:47", "throughput": 5505.27, "total_tokens": 26457632} {"current_steps": 43430, "total_steps": 64460, "loss": 0.1501, "lr": 2.90692876346246e-06, "epoch": 13.475023270245114, "percentage": 67.38, "elapsed_time": "1:20:06", "remaining_time": "0:38:47", "throughput": 5505.36, "total_tokens": 26460992} {"current_steps": 43435, "total_steps": 64460, "loss": 0.1816, "lr": 2.9056993603330667e-06, "epoch": 13.47657461991933, "percentage": 67.38, "elapsed_time": "1:20:06", "remaining_time": "0:38:46", "throughput": 5505.35, "total_tokens": 26463584} {"current_steps": 43440, "total_steps": 64460, "loss": 0.2613, "lr": 2.904470110740709e-06, "epoch": 13.478125969593547, "percentage": 67.39, "elapsed_time": "1:20:07", "remaining_time": "0:38:46", "throughput": 5505.44, "total_tokens": 26466848} {"current_steps": 43445, "total_steps": 64460, "loss": 0.1749, "lr": 2.903241014775508e-06, "epoch": 13.479677319267763, "percentage": 67.4, "elapsed_time": "1:20:07", "remaining_time": "0:38:45", "throughput": 5505.45, "total_tokens": 26469632} {"current_steps": 43450, "total_steps": 64460, "loss": 0.2502, "lr": 2.902012072527568e-06, "epoch": 13.481228668941979, "percentage": 67.41, "elapsed_time": "1:20:08", "remaining_time": "0:38:45", "throughput": 5505.42, "total_tokens": 26472064} {"current_steps": 43455, "total_steps": 64460, "loss": 0.2257, "lr": 2.90078328408699e-06, "epoch": 13.482780018616197, "percentage": 67.41, "elapsed_time": "1:20:08", "remaining_time": "0:38:44", "throughput": 5505.49, "total_tokens": 26475200} {"current_steps": 43460, "total_steps": 64460, "loss": 0.2129, "lr": 2.899554649543853e-06, "epoch": 13.484331368290412, "percentage": 67.42, "elapsed_time": "1:20:09", "remaining_time": "0:38:43", "throughput": 5505.53, "total_tokens": 26478464} {"current_steps": 43465, "total_steps": 64460, "loss": 0.2134, "lr": 2.8983261689882345e-06, "epoch": 13.485882717964628, "percentage": 67.43, "elapsed_time": "1:20:09", "remaining_time": "0:38:43", "throughput": 5505.36, "total_tokens": 26480448} {"current_steps": 43470, "total_steps": 64460, "loss": 0.1694, "lr": 2.897097842510195e-06, "epoch": 13.487434067638846, "percentage": 67.44, "elapsed_time": "1:20:10", "remaining_time": "0:38:42", "throughput": 5505.35, "total_tokens": 26482944} {"current_steps": 43475, "total_steps": 64460, "loss": 0.1701, "lr": 2.8958696701997867e-06, "epoch": 13.488985417313062, "percentage": 67.44, "elapsed_time": "1:20:10", "remaining_time": "0:38:42", "throughput": 5505.37, "total_tokens": 26485920} {"current_steps": 43480, "total_steps": 64460, "loss": 0.1461, "lr": 2.894641652147046e-06, "epoch": 13.49053676698728, "percentage": 67.45, "elapsed_time": "1:20:11", "remaining_time": "0:38:41", "throughput": 5505.41, "total_tokens": 26488800} {"current_steps": 43485, "total_steps": 64460, "loss": 0.1559, "lr": 2.893413788442006e-06, "epoch": 13.492088116661495, "percentage": 67.46, "elapsed_time": "1:20:11", "remaining_time": "0:38:41", "throughput": 5505.41, "total_tokens": 26491520} {"current_steps": 43490, "total_steps": 64460, "loss": 0.2355, "lr": 2.8921860791746786e-06, "epoch": 13.493639466335711, "percentage": 67.47, "elapsed_time": "1:20:12", "remaining_time": "0:38:40", "throughput": 5505.49, "total_tokens": 26494784} {"current_steps": 43495, "total_steps": 64460, "loss": 0.2187, "lr": 2.8909585244350724e-06, "epoch": 13.495190816009929, "percentage": 67.48, "elapsed_time": "1:20:12", "remaining_time": "0:38:39", "throughput": 5505.54, "total_tokens": 26497856} {"current_steps": 43500, "total_steps": 64460, "loss": 0.1825, "lr": 2.889731124313182e-06, "epoch": 13.496742165684145, "percentage": 67.48, "elapsed_time": "1:20:13", "remaining_time": "0:38:39", "throughput": 5505.62, "total_tokens": 26501120} {"current_steps": 43505, "total_steps": 64460, "loss": 0.2269, "lr": 2.8885038788989885e-06, "epoch": 13.498293515358363, "percentage": 67.49, "elapsed_time": "1:20:13", "remaining_time": "0:38:38", "throughput": 5505.6, "total_tokens": 26503648} {"current_steps": 43510, "total_steps": 64460, "loss": 0.2672, "lr": 2.8872767882824664e-06, "epoch": 13.499844865032578, "percentage": 67.5, "elapsed_time": "1:20:14", "remaining_time": "0:38:38", "throughput": 5505.55, "total_tokens": 26505952} {"current_steps": 43515, "total_steps": 64460, "loss": 0.1797, "lr": 2.886049852553572e-06, "epoch": 13.501396214706794, "percentage": 67.51, "elapsed_time": "1:20:14", "remaining_time": "0:38:37", "throughput": 5505.64, "total_tokens": 26509184} {"current_steps": 43520, "total_steps": 64460, "loss": 0.2241, "lr": 2.8848230718022586e-06, "epoch": 13.502947564381012, "percentage": 67.51, "elapsed_time": "1:20:15", "remaining_time": "0:38:36", "throughput": 5505.67, "total_tokens": 26512032} {"current_steps": 43525, "total_steps": 64460, "loss": 0.2312, "lr": 2.8835964461184587e-06, "epoch": 13.504498914055228, "percentage": 67.52, "elapsed_time": "1:20:15", "remaining_time": "0:38:36", "throughput": 5505.61, "total_tokens": 26514816} {"current_steps": 43530, "total_steps": 64460, "loss": 0.2757, "lr": 2.882369975592104e-06, "epoch": 13.506050263729446, "percentage": 67.53, "elapsed_time": "1:20:16", "remaining_time": "0:38:35", "throughput": 5505.7, "total_tokens": 26518144} {"current_steps": 43535, "total_steps": 64460, "loss": 0.1644, "lr": 2.8811436603131043e-06, "epoch": 13.507601613403661, "percentage": 67.54, "elapsed_time": "1:20:16", "remaining_time": "0:38:35", "throughput": 5505.67, "total_tokens": 26520704} {"current_steps": 43540, "total_steps": 64460, "loss": 0.1935, "lr": 2.8799175003713677e-06, "epoch": 13.509152963077877, "percentage": 67.55, "elapsed_time": "1:20:17", "remaining_time": "0:38:34", "throughput": 5505.71, "total_tokens": 26523616} {"current_steps": 43545, "total_steps": 64460, "loss": 0.214, "lr": 2.8786914958567813e-06, "epoch": 13.510704312752095, "percentage": 67.55, "elapsed_time": "1:20:17", "remaining_time": "0:38:34", "throughput": 5505.65, "total_tokens": 26526016} {"current_steps": 43550, "total_steps": 64460, "loss": 0.2828, "lr": 2.877465646859228e-06, "epoch": 13.51225566242631, "percentage": 67.56, "elapsed_time": "1:20:18", "remaining_time": "0:38:33", "throughput": 5505.5, "total_tokens": 26528096} {"current_steps": 43555, "total_steps": 64460, "loss": 0.2185, "lr": 2.8762399534685804e-06, "epoch": 13.513807012100527, "percentage": 67.57, "elapsed_time": "1:20:19", "remaining_time": "0:38:33", "throughput": 5505.58, "total_tokens": 26532128} {"current_steps": 43560, "total_steps": 64460, "loss": 0.2015, "lr": 2.8750144157746907e-06, "epoch": 13.515358361774744, "percentage": 67.58, "elapsed_time": "1:20:19", "remaining_time": "0:38:32", "throughput": 5505.64, "total_tokens": 26535328} {"current_steps": 43565, "total_steps": 64460, "loss": 0.1928, "lr": 2.8737890338674094e-06, "epoch": 13.51690971144896, "percentage": 67.58, "elapsed_time": "1:20:20", "remaining_time": "0:38:31", "throughput": 5505.55, "total_tokens": 26537472} {"current_steps": 43570, "total_steps": 64460, "loss": 0.1664, "lr": 2.872563807836569e-06, "epoch": 13.518461061123178, "percentage": 67.59, "elapsed_time": "1:20:20", "remaining_time": "0:38:31", "throughput": 5505.6, "total_tokens": 26540800} {"current_steps": 43575, "total_steps": 64460, "loss": 0.2046, "lr": 2.8713387377719957e-06, "epoch": 13.520012410797394, "percentage": 67.6, "elapsed_time": "1:20:21", "remaining_time": "0:38:30", "throughput": 5505.74, "total_tokens": 26545664} {"current_steps": 43580, "total_steps": 64460, "loss": 0.265, "lr": 2.870113823763498e-06, "epoch": 13.52156376047161, "percentage": 67.61, "elapsed_time": "1:20:21", "remaining_time": "0:38:30", "throughput": 5505.62, "total_tokens": 26547712} {"current_steps": 43585, "total_steps": 64460, "loss": 0.1544, "lr": 2.8688890659008807e-06, "epoch": 13.523115110145827, "percentage": 67.62, "elapsed_time": "1:20:22", "remaining_time": "0:38:29", "throughput": 5505.66, "total_tokens": 26551168} {"current_steps": 43590, "total_steps": 64460, "loss": 0.178, "lr": 2.8676644642739287e-06, "epoch": 13.524666459820043, "percentage": 67.62, "elapsed_time": "1:20:23", "remaining_time": "0:38:29", "throughput": 5505.72, "total_tokens": 26554368} {"current_steps": 43595, "total_steps": 64460, "loss": 0.1632, "lr": 2.8664400189724246e-06, "epoch": 13.52621780949426, "percentage": 67.63, "elapsed_time": "1:20:23", "remaining_time": "0:38:28", "throughput": 5505.7, "total_tokens": 26556992} {"current_steps": 43600, "total_steps": 64460, "loss": 0.1859, "lr": 2.86521573008613e-06, "epoch": 13.527769159168477, "percentage": 67.64, "elapsed_time": "1:20:24", "remaining_time": "0:38:28", "throughput": 5505.79, "total_tokens": 26560384} {"current_steps": 43605, "total_steps": 64460, "loss": 0.1793, "lr": 2.8639915977048016e-06, "epoch": 13.529320508842693, "percentage": 67.65, "elapsed_time": "1:20:24", "remaining_time": "0:38:27", "throughput": 5505.75, "total_tokens": 26562880} {"current_steps": 43610, "total_steps": 64460, "loss": 0.1754, "lr": 2.862767621918184e-06, "epoch": 13.53087185851691, "percentage": 67.65, "elapsed_time": "1:20:25", "remaining_time": "0:38:26", "throughput": 5505.77, "total_tokens": 26565728} {"current_steps": 43615, "total_steps": 64460, "loss": 0.1887, "lr": 2.86154380281601e-06, "epoch": 13.532423208191126, "percentage": 67.66, "elapsed_time": "1:20:25", "remaining_time": "0:38:26", "throughput": 5505.7, "total_tokens": 26568128} {"current_steps": 43620, "total_steps": 64460, "loss": 0.1724, "lr": 2.8603201404879966e-06, "epoch": 13.533974557865342, "percentage": 67.67, "elapsed_time": "1:20:26", "remaining_time": "0:38:25", "throughput": 5505.82, "total_tokens": 26571936} {"current_steps": 43625, "total_steps": 64460, "loss": 0.1786, "lr": 2.859096635023856e-06, "epoch": 13.53552590753956, "percentage": 67.68, "elapsed_time": "1:20:26", "remaining_time": "0:38:25", "throughput": 5505.81, "total_tokens": 26574528} {"current_steps": 43630, "total_steps": 64460, "loss": 0.2677, "lr": 2.8578732865132817e-06, "epoch": 13.537077257213776, "percentage": 67.69, "elapsed_time": "1:20:27", "remaining_time": "0:38:24", "throughput": 5505.9, "total_tokens": 26578048} {"current_steps": 43635, "total_steps": 64460, "loss": 0.2933, "lr": 2.856650095045963e-06, "epoch": 13.538628606887993, "percentage": 67.69, "elapsed_time": "1:20:27", "remaining_time": "0:38:24", "throughput": 5505.8, "total_tokens": 26580256} {"current_steps": 43640, "total_steps": 64460, "loss": 0.2919, "lr": 2.855427060711575e-06, "epoch": 13.54017995656221, "percentage": 67.7, "elapsed_time": "1:20:28", "remaining_time": "0:38:23", "throughput": 5505.77, "total_tokens": 26582880} {"current_steps": 43645, "total_steps": 64460, "loss": 0.1928, "lr": 2.8542041835997774e-06, "epoch": 13.541731306236425, "percentage": 67.71, "elapsed_time": "1:20:28", "remaining_time": "0:38:22", "throughput": 5505.78, "total_tokens": 26585952} {"current_steps": 43650, "total_steps": 64460, "loss": 0.1938, "lr": 2.8529814638002253e-06, "epoch": 13.543282655910643, "percentage": 67.72, "elapsed_time": "1:20:29", "remaining_time": "0:38:22", "throughput": 5505.91, "total_tokens": 26590336} {"current_steps": 43655, "total_steps": 64460, "loss": 0.1587, "lr": 2.851758901402554e-06, "epoch": 13.544834005584859, "percentage": 67.72, "elapsed_time": "1:20:30", "remaining_time": "0:38:21", "throughput": 5506.04, "total_tokens": 26594432} {"current_steps": 43660, "total_steps": 64460, "loss": 0.244, "lr": 2.8505364964963955e-06, "epoch": 13.546385355259076, "percentage": 67.73, "elapsed_time": "1:20:30", "remaining_time": "0:38:21", "throughput": 5506.21, "total_tokens": 26598560} {"current_steps": 43665, "total_steps": 64460, "loss": 0.278, "lr": 2.8493142491713644e-06, "epoch": 13.547936704933292, "percentage": 67.74, "elapsed_time": "1:20:31", "remaining_time": "0:38:20", "throughput": 5506.24, "total_tokens": 26601504} {"current_steps": 43670, "total_steps": 64460, "loss": 0.1949, "lr": 2.8480921595170686e-06, "epoch": 13.549488054607508, "percentage": 67.75, "elapsed_time": "1:20:31", "remaining_time": "0:38:20", "throughput": 5506.12, "total_tokens": 26603648} {"current_steps": 43675, "total_steps": 64460, "loss": 0.2274, "lr": 2.8468702276230977e-06, "epoch": 13.551039404281726, "percentage": 67.76, "elapsed_time": "1:20:32", "remaining_time": "0:38:19", "throughput": 5506.23, "total_tokens": 26607520} {"current_steps": 43680, "total_steps": 64460, "loss": 0.2186, "lr": 2.8456484535790375e-06, "epoch": 13.552590753955942, "percentage": 67.76, "elapsed_time": "1:20:32", "remaining_time": "0:38:19", "throughput": 5506.38, "total_tokens": 26611648} {"current_steps": 43685, "total_steps": 64460, "loss": 0.2546, "lr": 2.8444268374744554e-06, "epoch": 13.554142103630157, "percentage": 67.77, "elapsed_time": "1:20:33", "remaining_time": "0:38:18", "throughput": 5506.33, "total_tokens": 26613984} {"current_steps": 43690, "total_steps": 64460, "loss": 0.1763, "lr": 2.843205379398914e-06, "epoch": 13.555693453304375, "percentage": 67.78, "elapsed_time": "1:20:33", "remaining_time": "0:38:17", "throughput": 5506.28, "total_tokens": 26616352} {"current_steps": 43695, "total_steps": 64460, "loss": 0.161, "lr": 2.8419840794419564e-06, "epoch": 13.557244802978591, "percentage": 67.79, "elapsed_time": "1:20:34", "remaining_time": "0:38:17", "throughput": 5506.31, "total_tokens": 26619552} {"current_steps": 43700, "total_steps": 64460, "loss": 0.218, "lr": 2.840762937693121e-06, "epoch": 13.558796152652809, "percentage": 67.79, "elapsed_time": "1:20:34", "remaining_time": "0:38:16", "throughput": 5506.42, "total_tokens": 26623552} {"current_steps": 43705, "total_steps": 64460, "loss": 0.2217, "lr": 2.839541954241933e-06, "epoch": 13.560347502327025, "percentage": 67.8, "elapsed_time": "1:20:35", "remaining_time": "0:38:16", "throughput": 5506.64, "total_tokens": 26629536} {"current_steps": 43710, "total_steps": 64460, "loss": 0.1847, "lr": 2.838321129177901e-06, "epoch": 13.56189885200124, "percentage": 67.81, "elapsed_time": "1:20:36", "remaining_time": "0:38:15", "throughput": 5506.78, "total_tokens": 26633248} {"current_steps": 43715, "total_steps": 64460, "loss": 0.2744, "lr": 2.8371004625905307e-06, "epoch": 13.563450201675458, "percentage": 67.82, "elapsed_time": "1:20:36", "remaining_time": "0:38:15", "throughput": 5506.81, "total_tokens": 26636384} {"current_steps": 43720, "total_steps": 64460, "loss": 0.2265, "lr": 2.835879954569307e-06, "epoch": 13.565001551349674, "percentage": 67.83, "elapsed_time": "1:20:37", "remaining_time": "0:38:14", "throughput": 5506.8, "total_tokens": 26639136} {"current_steps": 43725, "total_steps": 64460, "loss": 0.2646, "lr": 2.8346596052037123e-06, "epoch": 13.56655290102389, "percentage": 67.83, "elapsed_time": "1:20:38", "remaining_time": "0:38:14", "throughput": 5506.78, "total_tokens": 26642080} {"current_steps": 43730, "total_steps": 64460, "loss": 0.241, "lr": 2.833439414583208e-06, "epoch": 13.568104250698108, "percentage": 67.84, "elapsed_time": "1:20:38", "remaining_time": "0:38:13", "throughput": 5506.86, "total_tokens": 26645568} {"current_steps": 43735, "total_steps": 64460, "loss": 0.17, "lr": 2.8322193827972515e-06, "epoch": 13.569655600372323, "percentage": 67.85, "elapsed_time": "1:20:39", "remaining_time": "0:38:13", "throughput": 5506.94, "total_tokens": 26648896} {"current_steps": 43740, "total_steps": 64460, "loss": 0.1857, "lr": 2.830999509935283e-06, "epoch": 13.571206950046541, "percentage": 67.86, "elapsed_time": "1:20:39", "remaining_time": "0:38:12", "throughput": 5506.85, "total_tokens": 26651232} {"current_steps": 43745, "total_steps": 64460, "loss": 0.251, "lr": 2.829779796086738e-06, "epoch": 13.572758299720757, "percentage": 67.86, "elapsed_time": "1:20:40", "remaining_time": "0:38:12", "throughput": 5506.99, "total_tokens": 26655648} {"current_steps": 43750, "total_steps": 64460, "loss": 0.186, "lr": 2.8285602413410303e-06, "epoch": 13.574309649394973, "percentage": 67.87, "elapsed_time": "1:20:40", "remaining_time": "0:38:11", "throughput": 5507.03, "total_tokens": 26658688} {"current_steps": 43755, "total_steps": 64460, "loss": 0.2033, "lr": 2.8273408457875728e-06, "epoch": 13.57586099906919, "percentage": 67.88, "elapsed_time": "1:20:41", "remaining_time": "0:38:10", "throughput": 5506.98, "total_tokens": 26660960} {"current_steps": 43760, "total_steps": 64460, "loss": 0.1556, "lr": 2.8261216095157574e-06, "epoch": 13.577412348743406, "percentage": 67.89, "elapsed_time": "1:20:41", "remaining_time": "0:38:10", "throughput": 5506.94, "total_tokens": 26663424} {"current_steps": 43765, "total_steps": 64460, "loss": 0.3081, "lr": 2.82490253261497e-06, "epoch": 13.578963698417624, "percentage": 67.89, "elapsed_time": "1:20:42", "remaining_time": "0:38:09", "throughput": 5506.99, "total_tokens": 26666432} {"current_steps": 43770, "total_steps": 64460, "loss": 0.298, "lr": 2.823683615174587e-06, "epoch": 13.58051504809184, "percentage": 67.9, "elapsed_time": "1:20:42", "remaining_time": "0:38:09", "throughput": 5506.99, "total_tokens": 26669152} {"current_steps": 43775, "total_steps": 64460, "loss": 0.1951, "lr": 2.822464857283965e-06, "epoch": 13.582066397766056, "percentage": 67.91, "elapsed_time": "1:20:43", "remaining_time": "0:38:08", "throughput": 5506.95, "total_tokens": 26671872} {"current_steps": 43780, "total_steps": 64460, "loss": 0.1568, "lr": 2.8212462590324553e-06, "epoch": 13.583617747440274, "percentage": 67.92, "elapsed_time": "1:20:43", "remaining_time": "0:38:08", "throughput": 5507.05, "total_tokens": 26675136} {"current_steps": 43785, "total_steps": 64460, "loss": 0.212, "lr": 2.820027820509394e-06, "epoch": 13.58516909711449, "percentage": 67.93, "elapsed_time": "1:20:44", "remaining_time": "0:38:07", "throughput": 5507.07, "total_tokens": 26678144} {"current_steps": 43790, "total_steps": 64460, "loss": 0.2938, "lr": 2.81880954180411e-06, "epoch": 13.586720446788707, "percentage": 67.93, "elapsed_time": "1:20:44", "remaining_time": "0:38:06", "throughput": 5507.06, "total_tokens": 26681152} {"current_steps": 43795, "total_steps": 64460, "loss": 0.22, "lr": 2.817591423005914e-06, "epoch": 13.588271796462923, "percentage": 67.94, "elapsed_time": "1:20:45", "remaining_time": "0:38:06", "throughput": 5507.1, "total_tokens": 26684416} {"current_steps": 43800, "total_steps": 64460, "loss": 0.212, "lr": 2.8163734642041118e-06, "epoch": 13.589823146137139, "percentage": 67.95, "elapsed_time": "1:20:45", "remaining_time": "0:38:05", "throughput": 5507.18, "total_tokens": 26687776} {"current_steps": 43805, "total_steps": 64460, "loss": 0.2309, "lr": 2.8151556654879907e-06, "epoch": 13.591374495811356, "percentage": 67.96, "elapsed_time": "1:20:46", "remaining_time": "0:38:05", "throughput": 5507.18, "total_tokens": 26690496} {"current_steps": 43810, "total_steps": 64460, "loss": 0.2034, "lr": 2.813938026946834e-06, "epoch": 13.592925845485572, "percentage": 67.96, "elapsed_time": "1:20:46", "remaining_time": "0:38:04", "throughput": 5507.19, "total_tokens": 26693312} {"current_steps": 43815, "total_steps": 64460, "loss": 0.2391, "lr": 2.812720548669905e-06, "epoch": 13.594477195159788, "percentage": 67.97, "elapsed_time": "1:20:47", "remaining_time": "0:38:04", "throughput": 5507.27, "total_tokens": 26696960} {"current_steps": 43820, "total_steps": 64460, "loss": 0.1437, "lr": 2.8115032307464607e-06, "epoch": 13.596028544834006, "percentage": 67.98, "elapsed_time": "1:20:48", "remaining_time": "0:38:03", "throughput": 5507.35, "total_tokens": 26700320} {"current_steps": 43825, "total_steps": 64460, "loss": 0.1964, "lr": 2.8102860732657466e-06, "epoch": 13.597579894508222, "percentage": 67.99, "elapsed_time": "1:20:48", "remaining_time": "0:38:02", "throughput": 5507.42, "total_tokens": 26703456} {"current_steps": 43830, "total_steps": 64460, "loss": 0.1781, "lr": 2.8090690763169927e-06, "epoch": 13.59913124418244, "percentage": 68.0, "elapsed_time": "1:20:49", "remaining_time": "0:38:02", "throughput": 5507.43, "total_tokens": 26706240} {"current_steps": 43835, "total_steps": 64460, "loss": 0.2013, "lr": 2.8078522399894216e-06, "epoch": 13.600682593856655, "percentage": 68.0, "elapsed_time": "1:20:49", "remaining_time": "0:38:01", "throughput": 5507.39, "total_tokens": 26708768} {"current_steps": 43840, "total_steps": 64460, "loss": 0.1763, "lr": 2.8066355643722377e-06, "epoch": 13.602233943530871, "percentage": 68.01, "elapsed_time": "1:20:50", "remaining_time": "0:38:01", "throughput": 5507.41, "total_tokens": 26711776} {"current_steps": 43845, "total_steps": 64460, "loss": 0.1447, "lr": 2.805419049554643e-06, "epoch": 13.603785293205089, "percentage": 68.02, "elapsed_time": "1:20:50", "remaining_time": "0:38:00", "throughput": 5507.5, "total_tokens": 26714976} {"current_steps": 43850, "total_steps": 64460, "loss": 0.1805, "lr": 2.804202695625817e-06, "epoch": 13.605336642879305, "percentage": 68.03, "elapsed_time": "1:20:51", "remaining_time": "0:38:00", "throughput": 5507.49, "total_tokens": 26717824} {"current_steps": 43855, "total_steps": 64460, "loss": 0.1995, "lr": 2.802986502674938e-06, "epoch": 13.60688799255352, "percentage": 68.03, "elapsed_time": "1:20:51", "remaining_time": "0:37:59", "throughput": 5507.49, "total_tokens": 26720576} {"current_steps": 43860, "total_steps": 64460, "loss": 0.2167, "lr": 2.8017704707911625e-06, "epoch": 13.608439342227738, "percentage": 68.04, "elapsed_time": "1:20:52", "remaining_time": "0:37:58", "throughput": 5507.48, "total_tokens": 26723360} {"current_steps": 43865, "total_steps": 64460, "loss": 0.1847, "lr": 2.8005546000636448e-06, "epoch": 13.609990691901954, "percentage": 68.05, "elapsed_time": "1:20:52", "remaining_time": "0:37:58", "throughput": 5507.49, "total_tokens": 26726208} {"current_steps": 43870, "total_steps": 64460, "loss": 0.2138, "lr": 2.7993388905815176e-06, "epoch": 13.611542041576172, "percentage": 68.06, "elapsed_time": "1:20:53", "remaining_time": "0:37:57", "throughput": 5507.57, "total_tokens": 26729536} {"current_steps": 43875, "total_steps": 64460, "loss": 0.1785, "lr": 2.7981233424339122e-06, "epoch": 13.613093391250388, "percentage": 68.07, "elapsed_time": "1:20:53", "remaining_time": "0:37:57", "throughput": 5507.59, "total_tokens": 26732544} {"current_steps": 43880, "total_steps": 64460, "loss": 0.2014, "lr": 2.7969079557099377e-06, "epoch": 13.614644740924604, "percentage": 68.07, "elapsed_time": "1:20:54", "remaining_time": "0:37:56", "throughput": 5507.51, "total_tokens": 26734784} {"current_steps": 43885, "total_steps": 64460, "loss": 0.2573, "lr": 2.7956927304986986e-06, "epoch": 13.616196090598821, "percentage": 68.08, "elapsed_time": "1:20:54", "remaining_time": "0:37:56", "throughput": 5507.54, "total_tokens": 26737536} {"current_steps": 43890, "total_steps": 64460, "loss": 0.1507, "lr": 2.794477666889287e-06, "epoch": 13.617747440273037, "percentage": 68.09, "elapsed_time": "1:20:55", "remaining_time": "0:37:55", "throughput": 5507.54, "total_tokens": 26740352} {"current_steps": 43895, "total_steps": 64460, "loss": 0.2008, "lr": 2.7932627649707777e-06, "epoch": 13.619298789947255, "percentage": 68.1, "elapsed_time": "1:20:55", "remaining_time": "0:37:54", "throughput": 5507.56, "total_tokens": 26743424} {"current_steps": 43900, "total_steps": 64460, "loss": 0.2863, "lr": 2.792048024832242e-06, "epoch": 13.62085013962147, "percentage": 68.1, "elapsed_time": "1:20:56", "remaining_time": "0:37:54", "throughput": 5507.59, "total_tokens": 26746432} {"current_steps": 43905, "total_steps": 64460, "loss": 0.2598, "lr": 2.7908334465627297e-06, "epoch": 13.622401489295687, "percentage": 68.11, "elapsed_time": "1:20:56", "remaining_time": "0:37:53", "throughput": 5507.62, "total_tokens": 26749472} {"current_steps": 43910, "total_steps": 64460, "loss": 0.2263, "lr": 2.789619030251288e-06, "epoch": 13.623952838969904, "percentage": 68.12, "elapsed_time": "1:20:57", "remaining_time": "0:37:53", "throughput": 5507.63, "total_tokens": 26752160} {"current_steps": 43915, "total_steps": 64460, "loss": 0.2677, "lr": 2.788404775986945e-06, "epoch": 13.62550418864412, "percentage": 68.13, "elapsed_time": "1:20:57", "remaining_time": "0:37:52", "throughput": 5507.64, "total_tokens": 26754784} {"current_steps": 43920, "total_steps": 64460, "loss": 0.1899, "lr": 2.787190683858722e-06, "epoch": 13.627055538318338, "percentage": 68.14, "elapsed_time": "1:20:58", "remaining_time": "0:37:52", "throughput": 5507.63, "total_tokens": 26757856} {"current_steps": 43925, "total_steps": 64460, "loss": 0.2293, "lr": 2.785976753955624e-06, "epoch": 13.628606887992554, "percentage": 68.14, "elapsed_time": "1:20:58", "remaining_time": "0:37:51", "throughput": 5507.72, "total_tokens": 26761696} {"current_steps": 43930, "total_steps": 64460, "loss": 0.2267, "lr": 2.7847629863666503e-06, "epoch": 13.63015823766677, "percentage": 68.15, "elapsed_time": "1:20:59", "remaining_time": "0:37:50", "throughput": 5507.64, "total_tokens": 26764032} {"current_steps": 43935, "total_steps": 64460, "loss": 0.1981, "lr": 2.7835493811807797e-06, "epoch": 13.631709587340987, "percentage": 68.16, "elapsed_time": "1:20:59", "remaining_time": "0:37:50", "throughput": 5507.66, "total_tokens": 26766720} {"current_steps": 43940, "total_steps": 64460, "loss": 0.165, "lr": 2.7823359384869857e-06, "epoch": 13.633260937015203, "percentage": 68.17, "elapsed_time": "1:21:00", "remaining_time": "0:37:49", "throughput": 5507.63, "total_tokens": 26769184} {"current_steps": 43945, "total_steps": 64460, "loss": 0.2304, "lr": 2.781122658374231e-06, "epoch": 13.634812286689419, "percentage": 68.17, "elapsed_time": "1:21:00", "remaining_time": "0:37:49", "throughput": 5507.77, "total_tokens": 26773088} {"current_steps": 43950, "total_steps": 64460, "loss": 0.2185, "lr": 2.779909540931459e-06, "epoch": 13.636363636363637, "percentage": 68.18, "elapsed_time": "1:21:01", "remaining_time": "0:37:48", "throughput": 5507.75, "total_tokens": 26775744} {"current_steps": 43955, "total_steps": 64460, "loss": 0.1622, "lr": 2.7786965862476088e-06, "epoch": 13.637914986037853, "percentage": 68.19, "elapsed_time": "1:21:02", "remaining_time": "0:37:48", "throughput": 5507.93, "total_tokens": 26780192} {"current_steps": 43960, "total_steps": 64460, "loss": 0.2178, "lr": 2.7774837944116016e-06, "epoch": 13.63946633571207, "percentage": 68.2, "elapsed_time": "1:21:02", "remaining_time": "0:37:47", "throughput": 5507.91, "total_tokens": 26782752} {"current_steps": 43965, "total_steps": 64460, "loss": 0.1578, "lr": 2.776271165512353e-06, "epoch": 13.641017685386286, "percentage": 68.21, "elapsed_time": "1:21:03", "remaining_time": "0:37:47", "throughput": 5508.01, "total_tokens": 26786464} {"current_steps": 43970, "total_steps": 64460, "loss": 0.2421, "lr": 2.7750586996387587e-06, "epoch": 13.642569035060502, "percentage": 68.21, "elapsed_time": "1:21:03", "remaining_time": "0:37:46", "throughput": 5507.86, "total_tokens": 26788832} {"current_steps": 43975, "total_steps": 64460, "loss": 0.2025, "lr": 2.7738463968797104e-06, "epoch": 13.64412038473472, "percentage": 68.22, "elapsed_time": "1:21:04", "remaining_time": "0:37:45", "throughput": 5507.78, "total_tokens": 26791584} {"current_steps": 43980, "total_steps": 64460, "loss": 0.2612, "lr": 2.772634257324081e-06, "epoch": 13.645671734408936, "percentage": 68.23, "elapsed_time": "1:21:04", "remaining_time": "0:37:45", "throughput": 5507.74, "total_tokens": 26794208} {"current_steps": 43985, "total_steps": 64460, "loss": 0.1769, "lr": 2.7714222810607387e-06, "epoch": 13.647223084083151, "percentage": 68.24, "elapsed_time": "1:21:05", "remaining_time": "0:37:44", "throughput": 5507.83, "total_tokens": 26797728} {"current_steps": 43990, "total_steps": 64460, "loss": 0.2107, "lr": 2.7702104681785313e-06, "epoch": 13.648774433757369, "percentage": 68.24, "elapsed_time": "1:21:05", "remaining_time": "0:37:44", "throughput": 5507.76, "total_tokens": 26800096} {"current_steps": 43995, "total_steps": 64460, "loss": 0.1944, "lr": 2.7689988187663038e-06, "epoch": 13.650325783431585, "percentage": 68.25, "elapsed_time": "1:21:06", "remaining_time": "0:37:43", "throughput": 5507.78, "total_tokens": 26802944} {"current_steps": 44000, "total_steps": 64460, "loss": 0.3058, "lr": 2.767787332912879e-06, "epoch": 13.651877133105803, "percentage": 68.26, "elapsed_time": "1:21:06", "remaining_time": "0:37:43", "throughput": 5507.75, "total_tokens": 26805632} {"current_steps": 44005, "total_steps": 64460, "loss": 0.2102, "lr": 2.766576010707077e-06, "epoch": 13.653428482780019, "percentage": 68.27, "elapsed_time": "1:21:07", "remaining_time": "0:37:42", "throughput": 5507.8, "total_tokens": 26808896} {"current_steps": 44010, "total_steps": 64460, "loss": 0.1588, "lr": 2.7653648522377027e-06, "epoch": 13.654979832454234, "percentage": 68.27, "elapsed_time": "1:21:08", "remaining_time": "0:37:42", "throughput": 5507.88, "total_tokens": 26812896} {"current_steps": 44015, "total_steps": 64460, "loss": 0.2102, "lr": 2.7641538575935443e-06, "epoch": 13.656531182128452, "percentage": 68.28, "elapsed_time": "1:21:08", "remaining_time": "0:37:41", "throughput": 5508.01, "total_tokens": 26817216} {"current_steps": 44020, "total_steps": 64460, "loss": 0.1777, "lr": 2.7629430268633873e-06, "epoch": 13.658082531802668, "percentage": 68.29, "elapsed_time": "1:21:09", "remaining_time": "0:37:40", "throughput": 5507.96, "total_tokens": 26820000} {"current_steps": 44025, "total_steps": 64460, "loss": 0.21, "lr": 2.7617323601359948e-06, "epoch": 13.659633881476886, "percentage": 68.3, "elapsed_time": "1:21:09", "remaining_time": "0:37:40", "throughput": 5508.03, "total_tokens": 26823424} {"current_steps": 44030, "total_steps": 64460, "loss": 0.262, "lr": 2.760521857500127e-06, "epoch": 13.661185231151102, "percentage": 68.31, "elapsed_time": "1:21:10", "remaining_time": "0:37:39", "throughput": 5508.17, "total_tokens": 26827584} {"current_steps": 44035, "total_steps": 64460, "loss": 0.27, "lr": 2.759311519044525e-06, "epoch": 13.662736580825317, "percentage": 68.31, "elapsed_time": "1:21:11", "remaining_time": "0:37:39", "throughput": 5508.19, "total_tokens": 26831232} {"current_steps": 44040, "total_steps": 64460, "loss": 0.2378, "lr": 2.7581013448579242e-06, "epoch": 13.664287930499535, "percentage": 68.32, "elapsed_time": "1:21:11", "remaining_time": "0:37:38", "throughput": 5508.17, "total_tokens": 26833696} {"current_steps": 44045, "total_steps": 64460, "loss": 0.2674, "lr": 2.7568913350290404e-06, "epoch": 13.665839280173751, "percentage": 68.33, "elapsed_time": "1:21:12", "remaining_time": "0:37:38", "throughput": 5508.22, "total_tokens": 26836832} {"current_steps": 44050, "total_steps": 64460, "loss": 0.2267, "lr": 2.7556814896465866e-06, "epoch": 13.667390629847969, "percentage": 68.34, "elapsed_time": "1:21:12", "remaining_time": "0:37:37", "throughput": 5508.2, "total_tokens": 26839488} {"current_steps": 44055, "total_steps": 64460, "loss": 0.1913, "lr": 2.754471808799255e-06, "epoch": 13.668941979522184, "percentage": 68.34, "elapsed_time": "1:21:13", "remaining_time": "0:37:37", "throughput": 5508.17, "total_tokens": 26841984} {"current_steps": 44060, "total_steps": 64460, "loss": 0.2042, "lr": 2.7532622925757295e-06, "epoch": 13.6704933291964, "percentage": 68.35, "elapsed_time": "1:21:13", "remaining_time": "0:37:36", "throughput": 5508.25, "total_tokens": 26845280} {"current_steps": 44065, "total_steps": 64460, "loss": 0.1856, "lr": 2.7520529410646864e-06, "epoch": 13.672044678870618, "percentage": 68.36, "elapsed_time": "1:21:14", "remaining_time": "0:37:35", "throughput": 5508.21, "total_tokens": 26848096} {"current_steps": 44070, "total_steps": 64460, "loss": 0.2238, "lr": 2.7508437543547794e-06, "epoch": 13.673596028544834, "percentage": 68.37, "elapsed_time": "1:21:14", "remaining_time": "0:37:35", "throughput": 5508.18, "total_tokens": 26850656} {"current_steps": 44075, "total_steps": 64460, "loss": 0.22, "lr": 2.7496347325346617e-06, "epoch": 13.67514737821905, "percentage": 68.38, "elapsed_time": "1:21:15", "remaining_time": "0:37:34", "throughput": 5508.21, "total_tokens": 26853824} {"current_steps": 44080, "total_steps": 64460, "loss": 0.1983, "lr": 2.748425875692965e-06, "epoch": 13.676698727893267, "percentage": 68.38, "elapsed_time": "1:21:15", "remaining_time": "0:37:34", "throughput": 5508.16, "total_tokens": 26856192} {"current_steps": 44085, "total_steps": 64460, "loss": 0.1796, "lr": 2.7472171839183153e-06, "epoch": 13.678250077567483, "percentage": 68.39, "elapsed_time": "1:21:16", "remaining_time": "0:37:33", "throughput": 5508.01, "total_tokens": 26858176} {"current_steps": 44090, "total_steps": 64460, "loss": 0.1783, "lr": 2.7460086572993215e-06, "epoch": 13.679801427241701, "percentage": 68.4, "elapsed_time": "1:21:17", "remaining_time": "0:37:33", "throughput": 5508.21, "total_tokens": 26863712} {"current_steps": 44095, "total_steps": 64460, "loss": 0.2071, "lr": 2.7448002959245863e-06, "epoch": 13.681352776915917, "percentage": 68.41, "elapsed_time": "1:21:17", "remaining_time": "0:37:32", "throughput": 5508.25, "total_tokens": 26866688} {"current_steps": 44100, "total_steps": 64460, "loss": 0.2182, "lr": 2.7435920998826927e-06, "epoch": 13.682904126590133, "percentage": 68.41, "elapsed_time": "1:21:18", "remaining_time": "0:37:32", "throughput": 5508.25, "total_tokens": 26869696} {"current_steps": 44105, "total_steps": 64460, "loss": 0.2217, "lr": 2.7423840692622206e-06, "epoch": 13.68445547626435, "percentage": 68.42, "elapsed_time": "1:21:18", "remaining_time": "0:37:31", "throughput": 5508.15, "total_tokens": 26871968} {"current_steps": 44110, "total_steps": 64460, "loss": 0.1912, "lr": 2.7411762041517275e-06, "epoch": 13.686006825938566, "percentage": 68.43, "elapsed_time": "1:21:19", "remaining_time": "0:37:30", "throughput": 5508.14, "total_tokens": 26874720} {"current_steps": 44115, "total_steps": 64460, "loss": 0.1697, "lr": 2.7399685046397696e-06, "epoch": 13.687558175612782, "percentage": 68.44, "elapsed_time": "1:21:19", "remaining_time": "0:37:30", "throughput": 5508.26, "total_tokens": 26878432} {"current_steps": 44120, "total_steps": 64460, "loss": 0.2536, "lr": 2.738760970814881e-06, "epoch": 13.689109525287, "percentage": 68.45, "elapsed_time": "1:21:20", "remaining_time": "0:37:29", "throughput": 5508.4, "total_tokens": 26883296} {"current_steps": 44125, "total_steps": 64460, "loss": 0.2217, "lr": 2.7375536027655906e-06, "epoch": 13.690660874961216, "percentage": 68.45, "elapsed_time": "1:21:20", "remaining_time": "0:37:29", "throughput": 5508.27, "total_tokens": 26885472} {"current_steps": 44130, "total_steps": 64460, "loss": 0.1976, "lr": 2.7363464005804142e-06, "epoch": 13.692212224635433, "percentage": 68.46, "elapsed_time": "1:21:21", "remaining_time": "0:37:28", "throughput": 5508.26, "total_tokens": 26888832} {"current_steps": 44135, "total_steps": 64460, "loss": 0.1937, "lr": 2.735139364347851e-06, "epoch": 13.69376357430965, "percentage": 68.47, "elapsed_time": "1:21:22", "remaining_time": "0:37:28", "throughput": 5508.25, "total_tokens": 26891808} {"current_steps": 44140, "total_steps": 64460, "loss": 0.2111, "lr": 2.7339324941563937e-06, "epoch": 13.695314923983865, "percentage": 68.48, "elapsed_time": "1:21:22", "remaining_time": "0:37:27", "throughput": 5508.42, "total_tokens": 26896032} {"current_steps": 44145, "total_steps": 64460, "loss": 0.1997, "lr": 2.732725790094517e-06, "epoch": 13.696866273658083, "percentage": 68.48, "elapsed_time": "1:21:23", "remaining_time": "0:37:27", "throughput": 5508.4, "total_tokens": 26898720} {"current_steps": 44150, "total_steps": 64460, "loss": 0.2173, "lr": 2.73151925225069e-06, "epoch": 13.698417623332299, "percentage": 68.49, "elapsed_time": "1:21:23", "remaining_time": "0:37:26", "throughput": 5508.41, "total_tokens": 26901664} {"current_steps": 44155, "total_steps": 64460, "loss": 0.2279, "lr": 2.7303128807133627e-06, "epoch": 13.699968973006516, "percentage": 68.5, "elapsed_time": "1:21:24", "remaining_time": "0:37:26", "throughput": 5508.39, "total_tokens": 26904160} {"current_steps": 44160, "total_steps": 64460, "loss": 0.226, "lr": 2.729106675570981e-06, "epoch": 13.701520322680732, "percentage": 68.51, "elapsed_time": "1:21:24", "remaining_time": "0:37:25", "throughput": 5508.46, "total_tokens": 26907488} {"current_steps": 44165, "total_steps": 64460, "loss": 0.2417, "lr": 2.7279006369119686e-06, "epoch": 13.703071672354948, "percentage": 68.52, "elapsed_time": "1:21:25", "remaining_time": "0:37:24", "throughput": 5508.53, "total_tokens": 26910816} {"current_steps": 44170, "total_steps": 64460, "loss": 0.2647, "lr": 2.7266947648247477e-06, "epoch": 13.704623022029166, "percentage": 68.52, "elapsed_time": "1:21:25", "remaining_time": "0:37:24", "throughput": 5508.59, "total_tokens": 26914240} {"current_steps": 44175, "total_steps": 64460, "loss": 0.2324, "lr": 2.725489059397719e-06, "epoch": 13.706174371703382, "percentage": 68.53, "elapsed_time": "1:21:26", "remaining_time": "0:37:23", "throughput": 5508.61, "total_tokens": 26917088} {"current_steps": 44180, "total_steps": 64460, "loss": 0.1806, "lr": 2.7242835207192752e-06, "epoch": 13.7077257213776, "percentage": 68.54, "elapsed_time": "1:21:26", "remaining_time": "0:37:23", "throughput": 5508.54, "total_tokens": 26919360} {"current_steps": 44185, "total_steps": 64460, "loss": 0.1965, "lr": 2.723078148877799e-06, "epoch": 13.709277071051815, "percentage": 68.55, "elapsed_time": "1:21:27", "remaining_time": "0:37:22", "throughput": 5508.55, "total_tokens": 26922112} {"current_steps": 44190, "total_steps": 64460, "loss": 0.1859, "lr": 2.721872943961659e-06, "epoch": 13.710828420726031, "percentage": 68.55, "elapsed_time": "1:21:27", "remaining_time": "0:37:22", "throughput": 5508.57, "total_tokens": 26924992} {"current_steps": 44195, "total_steps": 64460, "loss": 0.2308, "lr": 2.7206679060592066e-06, "epoch": 13.712379770400249, "percentage": 68.56, "elapsed_time": "1:21:28", "remaining_time": "0:37:21", "throughput": 5508.58, "total_tokens": 26927648} {"current_steps": 44200, "total_steps": 64460, "loss": 0.241, "lr": 2.719463035258791e-06, "epoch": 13.713931120074465, "percentage": 68.57, "elapsed_time": "1:21:28", "remaining_time": "0:37:20", "throughput": 5508.57, "total_tokens": 26930432} {"current_steps": 44205, "total_steps": 64460, "loss": 0.2071, "lr": 2.7182583316487375e-06, "epoch": 13.71548246974868, "percentage": 68.58, "elapsed_time": "1:21:29", "remaining_time": "0:37:20", "throughput": 5508.49, "total_tokens": 26932672} {"current_steps": 44210, "total_steps": 64460, "loss": 0.1799, "lr": 2.7170537953173693e-06, "epoch": 13.717033819422898, "percentage": 68.59, "elapsed_time": "1:21:29", "remaining_time": "0:37:19", "throughput": 5508.43, "total_tokens": 26934976} {"current_steps": 44215, "total_steps": 64460, "loss": 0.1945, "lr": 2.715849426352993e-06, "epoch": 13.718585169097114, "percentage": 68.59, "elapsed_time": "1:21:30", "remaining_time": "0:37:19", "throughput": 5508.3, "total_tokens": 26937056} {"current_steps": 44220, "total_steps": 64460, "loss": 0.1878, "lr": 2.7146452248439e-06, "epoch": 13.720136518771332, "percentage": 68.6, "elapsed_time": "1:21:30", "remaining_time": "0:37:18", "throughput": 5508.28, "total_tokens": 26939680} {"current_steps": 44225, "total_steps": 64460, "loss": 0.2063, "lr": 2.7134411908783777e-06, "epoch": 13.721687868445548, "percentage": 68.61, "elapsed_time": "1:21:31", "remaining_time": "0:37:17", "throughput": 5508.34, "total_tokens": 26942944} {"current_steps": 44230, "total_steps": 64460, "loss": 0.1576, "lr": 2.712237324544691e-06, "epoch": 13.723239218119764, "percentage": 68.62, "elapsed_time": "1:21:31", "remaining_time": "0:37:17", "throughput": 5508.32, "total_tokens": 26945600} {"current_steps": 44235, "total_steps": 64460, "loss": 0.1818, "lr": 2.711033625931101e-06, "epoch": 13.724790567793981, "percentage": 68.62, "elapsed_time": "1:21:32", "remaining_time": "0:37:16", "throughput": 5508.34, "total_tokens": 26948704} {"current_steps": 44240, "total_steps": 64460, "loss": 0.2591, "lr": 2.7098300951258495e-06, "epoch": 13.726341917468197, "percentage": 68.63, "elapsed_time": "1:21:32", "remaining_time": "0:37:16", "throughput": 5508.31, "total_tokens": 26951168} {"current_steps": 44245, "total_steps": 64460, "loss": 0.1837, "lr": 2.7086267322171744e-06, "epoch": 13.727893267142413, "percentage": 68.64, "elapsed_time": "1:21:33", "remaining_time": "0:37:15", "throughput": 5508.33, "total_tokens": 26954112} {"current_steps": 44250, "total_steps": 64460, "loss": 0.1928, "lr": 2.707423537293291e-06, "epoch": 13.72944461681663, "percentage": 68.65, "elapsed_time": "1:21:33", "remaining_time": "0:37:15", "throughput": 5508.4, "total_tokens": 26957312} {"current_steps": 44255, "total_steps": 64460, "loss": 0.2259, "lr": 2.7062205104424126e-06, "epoch": 13.730995966490847, "percentage": 68.65, "elapsed_time": "1:21:34", "remaining_time": "0:37:14", "throughput": 5508.51, "total_tokens": 26961312} {"current_steps": 44260, "total_steps": 64460, "loss": 0.2461, "lr": 2.7050176517527316e-06, "epoch": 13.732547316165064, "percentage": 68.66, "elapsed_time": "1:21:35", "remaining_time": "0:37:14", "throughput": 5508.53, "total_tokens": 26964416} {"current_steps": 44265, "total_steps": 64460, "loss": 0.1995, "lr": 2.703814961312433e-06, "epoch": 13.73409866583928, "percentage": 68.67, "elapsed_time": "1:21:35", "remaining_time": "0:37:13", "throughput": 5508.6, "total_tokens": 26967552} {"current_steps": 44270, "total_steps": 64460, "loss": 0.198, "lr": 2.7026124392096907e-06, "epoch": 13.735650015513496, "percentage": 68.68, "elapsed_time": "1:21:36", "remaining_time": "0:37:12", "throughput": 5508.48, "total_tokens": 26969984} {"current_steps": 44275, "total_steps": 64460, "loss": 0.1957, "lr": 2.7014100855326598e-06, "epoch": 13.737201365187714, "percentage": 68.69, "elapsed_time": "1:21:36", "remaining_time": "0:37:12", "throughput": 5508.6, "total_tokens": 26974048} {"current_steps": 44280, "total_steps": 64460, "loss": 0.2135, "lr": 2.7002079003694913e-06, "epoch": 13.73875271486193, "percentage": 68.69, "elapsed_time": "1:21:37", "remaining_time": "0:37:11", "throughput": 5508.65, "total_tokens": 26977152} {"current_steps": 44285, "total_steps": 64460, "loss": 0.1463, "lr": 2.699005883808315e-06, "epoch": 13.740304064536147, "percentage": 68.7, "elapsed_time": "1:21:37", "remaining_time": "0:37:11", "throughput": 5508.79, "total_tokens": 26981376} {"current_steps": 44290, "total_steps": 64460, "loss": 0.1871, "lr": 2.697804035937257e-06, "epoch": 13.741855414210363, "percentage": 68.71, "elapsed_time": "1:21:38", "remaining_time": "0:37:10", "throughput": 5508.79, "total_tokens": 26984064} {"current_steps": 44295, "total_steps": 64460, "loss": 0.193, "lr": 2.696602356844424e-06, "epoch": 13.743406763884579, "percentage": 68.72, "elapsed_time": "1:21:38", "remaining_time": "0:37:10", "throughput": 5508.73, "total_tokens": 26986528} {"current_steps": 44300, "total_steps": 64460, "loss": 0.1921, "lr": 2.695400846617916e-06, "epoch": 13.744958113558797, "percentage": 68.72, "elapsed_time": "1:21:39", "remaining_time": "0:37:09", "throughput": 5508.72, "total_tokens": 26989568} {"current_steps": 44305, "total_steps": 64460, "loss": 0.2882, "lr": 2.694199505345815e-06, "epoch": 13.746509463233012, "percentage": 68.73, "elapsed_time": "1:21:39", "remaining_time": "0:37:09", "throughput": 5508.67, "total_tokens": 26991904} {"current_steps": 44310, "total_steps": 64460, "loss": 0.1346, "lr": 2.6929983331161956e-06, "epoch": 13.74806081290723, "percentage": 68.74, "elapsed_time": "1:21:40", "remaining_time": "0:37:08", "throughput": 5508.74, "total_tokens": 26995104} {"current_steps": 44315, "total_steps": 64460, "loss": 0.184, "lr": 2.691797330017117e-06, "epoch": 13.749612162581446, "percentage": 68.75, "elapsed_time": "1:21:40", "remaining_time": "0:37:07", "throughput": 5508.76, "total_tokens": 26997888} {"current_steps": 44320, "total_steps": 64460, "loss": 0.1648, "lr": 2.6905964961366282e-06, "epoch": 13.751163512255662, "percentage": 68.76, "elapsed_time": "1:21:41", "remaining_time": "0:37:07", "throughput": 5508.84, "total_tokens": 27001408} {"current_steps": 44325, "total_steps": 64460, "loss": 0.1693, "lr": 2.689395831562762e-06, "epoch": 13.75271486192988, "percentage": 68.76, "elapsed_time": "1:21:41", "remaining_time": "0:37:06", "throughput": 5508.82, "total_tokens": 27004064} {"current_steps": 44330, "total_steps": 64460, "loss": 0.2152, "lr": 2.6881953363835433e-06, "epoch": 13.754266211604095, "percentage": 68.77, "elapsed_time": "1:21:42", "remaining_time": "0:37:06", "throughput": 5508.79, "total_tokens": 27006592} {"current_steps": 44335, "total_steps": 64460, "loss": 0.2369, "lr": 2.6869950106869846e-06, "epoch": 13.755817561278311, "percentage": 68.78, "elapsed_time": "1:21:42", "remaining_time": "0:37:05", "throughput": 5508.8, "total_tokens": 27009536} {"current_steps": 44340, "total_steps": 64460, "loss": 0.1931, "lr": 2.6857948545610792e-06, "epoch": 13.757368910952529, "percentage": 68.79, "elapsed_time": "1:21:43", "remaining_time": "0:37:05", "throughput": 5508.8, "total_tokens": 27012288} {"current_steps": 44345, "total_steps": 64460, "loss": 0.216, "lr": 2.684594868093817e-06, "epoch": 13.758920260626745, "percentage": 68.79, "elapsed_time": "1:21:44", "remaining_time": "0:37:04", "throughput": 5508.85, "total_tokens": 27015712} {"current_steps": 44350, "total_steps": 64460, "loss": 0.1497, "lr": 2.6833950513731684e-06, "epoch": 13.760471610300963, "percentage": 68.8, "elapsed_time": "1:21:44", "remaining_time": "0:37:03", "throughput": 5508.7, "total_tokens": 27017696} {"current_steps": 44355, "total_steps": 64460, "loss": 0.2078, "lr": 2.6821954044870962e-06, "epoch": 13.762022959975178, "percentage": 68.81, "elapsed_time": "1:21:45", "remaining_time": "0:37:03", "throughput": 5508.82, "total_tokens": 27022048} {"current_steps": 44360, "total_steps": 64460, "loss": 0.2025, "lr": 2.6809959275235464e-06, "epoch": 13.763574309649394, "percentage": 68.82, "elapsed_time": "1:21:45", "remaining_time": "0:37:02", "throughput": 5508.83, "total_tokens": 27025280} {"current_steps": 44365, "total_steps": 64460, "loss": 0.2013, "lr": 2.679796620570458e-06, "epoch": 13.765125659323612, "percentage": 68.83, "elapsed_time": "1:21:46", "remaining_time": "0:37:02", "throughput": 5508.85, "total_tokens": 27028576} {"current_steps": 44370, "total_steps": 64460, "loss": 0.2075, "lr": 2.6785974837157504e-06, "epoch": 13.766677008997828, "percentage": 68.83, "elapsed_time": "1:21:46", "remaining_time": "0:37:01", "throughput": 5508.83, "total_tokens": 27031200} {"current_steps": 44375, "total_steps": 64460, "loss": 0.2002, "lr": 2.6773985170473394e-06, "epoch": 13.768228358672044, "percentage": 68.84, "elapsed_time": "1:21:47", "remaining_time": "0:37:01", "throughput": 5508.87, "total_tokens": 27034080} {"current_steps": 44380, "total_steps": 64460, "loss": 0.1651, "lr": 2.676199720653118e-06, "epoch": 13.769779708346261, "percentage": 68.85, "elapsed_time": "1:21:47", "remaining_time": "0:37:00", "throughput": 5508.97, "total_tokens": 27037792} {"current_steps": 44385, "total_steps": 64460, "loss": 0.1785, "lr": 2.6750010946209757e-06, "epoch": 13.771331058020477, "percentage": 68.86, "elapsed_time": "1:21:48", "remaining_time": "0:37:00", "throughput": 5509.06, "total_tokens": 27041312} {"current_steps": 44390, "total_steps": 64460, "loss": 0.2067, "lr": 2.6738026390387874e-06, "epoch": 13.772882407694695, "percentage": 68.86, "elapsed_time": "1:21:49", "remaining_time": "0:36:59", "throughput": 5509.11, "total_tokens": 27044288} {"current_steps": 44395, "total_steps": 64460, "loss": 0.2315, "lr": 2.672604353994409e-06, "epoch": 13.77443375736891, "percentage": 68.87, "elapsed_time": "1:21:49", "remaining_time": "0:36:58", "throughput": 5509.11, "total_tokens": 27047168} {"current_steps": 44400, "total_steps": 64460, "loss": 0.3464, "lr": 2.6714062395756947e-06, "epoch": 13.775985107043127, "percentage": 68.88, "elapsed_time": "1:21:50", "remaining_time": "0:36:58", "throughput": 5509.15, "total_tokens": 27050496} {"current_steps": 44405, "total_steps": 64460, "loss": 0.2067, "lr": 2.6702082958704754e-06, "epoch": 13.777536456717344, "percentage": 68.89, "elapsed_time": "1:21:50", "remaining_time": "0:36:57", "throughput": 5509.1, "total_tokens": 27052896} {"current_steps": 44410, "total_steps": 64460, "loss": 0.2035, "lr": 2.6690105229665786e-06, "epoch": 13.77908780639156, "percentage": 68.9, "elapsed_time": "1:21:51", "remaining_time": "0:36:57", "throughput": 5509.09, "total_tokens": 27055744} {"current_steps": 44415, "total_steps": 64460, "loss": 0.2244, "lr": 2.667812920951812e-06, "epoch": 13.780639156065778, "percentage": 68.9, "elapsed_time": "1:21:51", "remaining_time": "0:36:56", "throughput": 5509.09, "total_tokens": 27058464} {"current_steps": 44420, "total_steps": 64460, "loss": 0.2426, "lr": 2.6666154899139775e-06, "epoch": 13.782190505739994, "percentage": 68.91, "elapsed_time": "1:21:52", "remaining_time": "0:36:56", "throughput": 5509.02, "total_tokens": 27060896} {"current_steps": 44425, "total_steps": 64460, "loss": 0.1981, "lr": 2.665418229940857e-06, "epoch": 13.78374185541421, "percentage": 68.92, "elapsed_time": "1:21:52", "remaining_time": "0:36:55", "throughput": 5509.03, "total_tokens": 27063808} {"current_steps": 44430, "total_steps": 64460, "loss": 0.1722, "lr": 2.664221141120228e-06, "epoch": 13.785293205088427, "percentage": 68.93, "elapsed_time": "1:21:53", "remaining_time": "0:36:54", "throughput": 5509.05, "total_tokens": 27066720} {"current_steps": 44435, "total_steps": 64460, "loss": 0.1903, "lr": 2.6630242235398463e-06, "epoch": 13.786844554762643, "percentage": 68.93, "elapsed_time": "1:21:53", "remaining_time": "0:36:54", "throughput": 5509.03, "total_tokens": 27069536} {"current_steps": 44440, "total_steps": 64460, "loss": 0.3417, "lr": 2.6618274772874653e-06, "epoch": 13.788395904436861, "percentage": 68.94, "elapsed_time": "1:21:54", "remaining_time": "0:36:53", "throughput": 5509.09, "total_tokens": 27073440} {"current_steps": 44445, "total_steps": 64460, "loss": 0.1759, "lr": 2.660630902450817e-06, "epoch": 13.789947254111077, "percentage": 68.95, "elapsed_time": "1:21:54", "remaining_time": "0:36:53", "throughput": 5509.17, "total_tokens": 27077024} {"current_steps": 44450, "total_steps": 64460, "loss": 0.2235, "lr": 2.659434499117625e-06, "epoch": 13.791498603785293, "percentage": 68.96, "elapsed_time": "1:21:55", "remaining_time": "0:36:52", "throughput": 5509.1, "total_tokens": 27079232} {"current_steps": 44455, "total_steps": 64460, "loss": 0.2278, "lr": 2.658238267375603e-06, "epoch": 13.79304995345951, "percentage": 68.97, "elapsed_time": "1:21:55", "remaining_time": "0:36:52", "throughput": 5509.22, "total_tokens": 27082976} {"current_steps": 44460, "total_steps": 64460, "loss": 0.1996, "lr": 2.6570422073124447e-06, "epoch": 13.794601303133726, "percentage": 68.97, "elapsed_time": "1:21:56", "remaining_time": "0:36:51", "throughput": 5509.15, "total_tokens": 27085312} {"current_steps": 44465, "total_steps": 64460, "loss": 0.2158, "lr": 2.655846319015839e-06, "epoch": 13.796152652807942, "percentage": 68.98, "elapsed_time": "1:21:56", "remaining_time": "0:36:51", "throughput": 5509.2, "total_tokens": 27088288} {"current_steps": 44470, "total_steps": 64460, "loss": 0.2235, "lr": 2.654650602573455e-06, "epoch": 13.79770400248216, "percentage": 68.99, "elapsed_time": "1:21:57", "remaining_time": "0:36:50", "throughput": 5509.13, "total_tokens": 27090720} {"current_steps": 44475, "total_steps": 64460, "loss": 0.2034, "lr": 2.653455058072958e-06, "epoch": 13.799255352156376, "percentage": 69.0, "elapsed_time": "1:21:57", "remaining_time": "0:36:49", "throughput": 5509.16, "total_tokens": 27093952} {"current_steps": 44480, "total_steps": 64460, "loss": 0.2421, "lr": 2.6522596856019895e-06, "epoch": 13.800806701830593, "percentage": 69.0, "elapsed_time": "1:21:58", "remaining_time": "0:36:49", "throughput": 5509.11, "total_tokens": 27096544} {"current_steps": 44485, "total_steps": 64460, "loss": 0.1642, "lr": 2.6510644852481893e-06, "epoch": 13.80235805150481, "percentage": 69.01, "elapsed_time": "1:21:58", "remaining_time": "0:36:48", "throughput": 5509.14, "total_tokens": 27099424} {"current_steps": 44490, "total_steps": 64460, "loss": 0.2152, "lr": 2.649869457099177e-06, "epoch": 13.803909401179025, "percentage": 69.02, "elapsed_time": "1:21:59", "remaining_time": "0:36:48", "throughput": 5509.08, "total_tokens": 27102016} {"current_steps": 44495, "total_steps": 64460, "loss": 0.2315, "lr": 2.6486746012425642e-06, "epoch": 13.805460750853243, "percentage": 69.03, "elapsed_time": "1:22:00", "remaining_time": "0:36:47", "throughput": 5509.11, "total_tokens": 27105120} {"current_steps": 44500, "total_steps": 64460, "loss": 0.1895, "lr": 2.6474799177659447e-06, "epoch": 13.807012100527459, "percentage": 69.04, "elapsed_time": "1:22:00", "remaining_time": "0:36:47", "throughput": 5509.07, "total_tokens": 27107616} {"current_steps": 44505, "total_steps": 64460, "loss": 0.228, "lr": 2.6462854067569067e-06, "epoch": 13.808563450201675, "percentage": 69.04, "elapsed_time": "1:22:01", "remaining_time": "0:36:46", "throughput": 5509.05, "total_tokens": 27110240} {"current_steps": 44510, "total_steps": 64460, "loss": 0.2182, "lr": 2.645091068303021e-06, "epoch": 13.810114799875892, "percentage": 69.05, "elapsed_time": "1:22:01", "remaining_time": "0:36:45", "throughput": 5509.02, "total_tokens": 27113824} {"current_steps": 44515, "total_steps": 64460, "loss": 0.2198, "lr": 2.6438969024918447e-06, "epoch": 13.811666149550108, "percentage": 69.06, "elapsed_time": "1:22:02", "remaining_time": "0:36:45", "throughput": 5509.06, "total_tokens": 27116608} {"current_steps": 44520, "total_steps": 64460, "loss": 0.2306, "lr": 2.6427029094109287e-06, "epoch": 13.813217499224326, "percentage": 69.07, "elapsed_time": "1:22:02", "remaining_time": "0:36:44", "throughput": 5509.04, "total_tokens": 27119168} {"current_steps": 44525, "total_steps": 64460, "loss": 0.2612, "lr": 2.641509089147801e-06, "epoch": 13.814768848898542, "percentage": 69.07, "elapsed_time": "1:22:03", "remaining_time": "0:36:44", "throughput": 5509.12, "total_tokens": 27122336} {"current_steps": 44530, "total_steps": 64460, "loss": 0.231, "lr": 2.6403154417899886e-06, "epoch": 13.816320198572758, "percentage": 69.08, "elapsed_time": "1:22:03", "remaining_time": "0:36:43", "throughput": 5509.17, "total_tokens": 27125280} {"current_steps": 44535, "total_steps": 64460, "loss": 0.272, "lr": 2.6391219674249946e-06, "epoch": 13.817871548246975, "percentage": 69.09, "elapsed_time": "1:22:04", "remaining_time": "0:36:43", "throughput": 5509.34, "total_tokens": 27129568} {"current_steps": 44540, "total_steps": 64460, "loss": 0.2574, "lr": 2.6379286661403193e-06, "epoch": 13.819422897921191, "percentage": 69.1, "elapsed_time": "1:22:04", "remaining_time": "0:36:42", "throughput": 5509.34, "total_tokens": 27132192} {"current_steps": 44545, "total_steps": 64460, "loss": 0.2023, "lr": 2.636735538023442e-06, "epoch": 13.820974247595409, "percentage": 69.1, "elapsed_time": "1:22:05", "remaining_time": "0:36:41", "throughput": 5509.45, "total_tokens": 27135616} {"current_steps": 44550, "total_steps": 64460, "loss": 0.2298, "lr": 2.6355425831618375e-06, "epoch": 13.822525597269625, "percentage": 69.11, "elapsed_time": "1:22:05", "remaining_time": "0:36:41", "throughput": 5509.55, "total_tokens": 27139008} {"current_steps": 44555, "total_steps": 64460, "loss": 0.1984, "lr": 2.634349801642958e-06, "epoch": 13.82407694694384, "percentage": 69.12, "elapsed_time": "1:22:06", "remaining_time": "0:36:40", "throughput": 5509.68, "total_tokens": 27142656} {"current_steps": 44560, "total_steps": 64460, "loss": 0.2462, "lr": 2.6331571935542544e-06, "epoch": 13.825628296618058, "percentage": 69.13, "elapsed_time": "1:22:06", "remaining_time": "0:36:40", "throughput": 5509.67, "total_tokens": 27145056} {"current_steps": 44565, "total_steps": 64460, "loss": 0.1917, "lr": 2.6319647589831543e-06, "epoch": 13.827179646292274, "percentage": 69.14, "elapsed_time": "1:22:07", "remaining_time": "0:36:39", "throughput": 5509.63, "total_tokens": 27147584} {"current_steps": 44570, "total_steps": 64460, "loss": 0.2333, "lr": 2.6307724980170786e-06, "epoch": 13.828730995966492, "percentage": 69.14, "elapsed_time": "1:22:07", "remaining_time": "0:36:39", "throughput": 5509.74, "total_tokens": 27151456} {"current_steps": 44575, "total_steps": 64460, "loss": 0.2216, "lr": 2.6295804107434362e-06, "epoch": 13.830282345640708, "percentage": 69.15, "elapsed_time": "1:22:08", "remaining_time": "0:36:38", "throughput": 5509.77, "total_tokens": 27154272} {"current_steps": 44580, "total_steps": 64460, "loss": 0.207, "lr": 2.6283884972496187e-06, "epoch": 13.831833695314923, "percentage": 69.16, "elapsed_time": "1:22:08", "remaining_time": "0:36:37", "throughput": 5509.67, "total_tokens": 27156256} {"current_steps": 44585, "total_steps": 64460, "loss": 0.1772, "lr": 2.6271967576230097e-06, "epoch": 13.833385044989141, "percentage": 69.17, "elapsed_time": "1:22:09", "remaining_time": "0:36:37", "throughput": 5509.69, "total_tokens": 27159136} {"current_steps": 44590, "total_steps": 64460, "loss": 0.1989, "lr": 2.6260051919509747e-06, "epoch": 13.834936394663357, "percentage": 69.17, "elapsed_time": "1:22:09", "remaining_time": "0:36:36", "throughput": 5509.71, "total_tokens": 27162080} {"current_steps": 44595, "total_steps": 64460, "loss": 0.2023, "lr": 2.6248138003208734e-06, "epoch": 13.836487744337573, "percentage": 69.18, "elapsed_time": "1:22:10", "remaining_time": "0:36:36", "throughput": 5509.72, "total_tokens": 27164928} {"current_steps": 44600, "total_steps": 64460, "loss": 0.1978, "lr": 2.6236225828200458e-06, "epoch": 13.83803909401179, "percentage": 69.19, "elapsed_time": "1:22:10", "remaining_time": "0:36:35", "throughput": 5509.79, "total_tokens": 27168128} {"current_steps": 44605, "total_steps": 64460, "loss": 0.1734, "lr": 2.622431539535824e-06, "epoch": 13.839590443686006, "percentage": 69.2, "elapsed_time": "1:22:11", "remaining_time": "0:36:35", "throughput": 5509.83, "total_tokens": 27171072} {"current_steps": 44610, "total_steps": 64460, "loss": 0.2132, "lr": 2.621240670555524e-06, "epoch": 13.841141793360224, "percentage": 69.21, "elapsed_time": "1:22:11", "remaining_time": "0:36:34", "throughput": 5509.92, "total_tokens": 27174592} {"current_steps": 44615, "total_steps": 64460, "loss": 0.2024, "lr": 2.620049975966453e-06, "epoch": 13.84269314303444, "percentage": 69.21, "elapsed_time": "1:22:12", "remaining_time": "0:36:33", "throughput": 5509.94, "total_tokens": 27177728} {"current_steps": 44620, "total_steps": 64460, "loss": 0.2038, "lr": 2.6188594558559e-06, "epoch": 13.844244492708656, "percentage": 69.22, "elapsed_time": "1:22:12", "remaining_time": "0:36:33", "throughput": 5509.95, "total_tokens": 27180352} {"current_steps": 44625, "total_steps": 64460, "loss": 0.2678, "lr": 2.617669110311145e-06, "epoch": 13.845795842382874, "percentage": 69.23, "elapsed_time": "1:22:13", "remaining_time": "0:36:32", "throughput": 5509.96, "total_tokens": 27182976} {"current_steps": 44630, "total_steps": 64460, "loss": 0.1959, "lr": 2.6164789394194577e-06, "epoch": 13.84734719205709, "percentage": 69.24, "elapsed_time": "1:22:13", "remaining_time": "0:36:32", "throughput": 5509.95, "total_tokens": 27185504} {"current_steps": 44635, "total_steps": 64460, "loss": 0.1974, "lr": 2.6152889432680876e-06, "epoch": 13.848898541731305, "percentage": 69.24, "elapsed_time": "1:22:14", "remaining_time": "0:36:31", "throughput": 5510.15, "total_tokens": 27192224} {"current_steps": 44640, "total_steps": 64460, "loss": 0.2501, "lr": 2.614099121944279e-06, "epoch": 13.850449891405523, "percentage": 69.25, "elapsed_time": "1:22:15", "remaining_time": "0:36:31", "throughput": 5510.27, "total_tokens": 27195776} {"current_steps": 44645, "total_steps": 64460, "loss": 0.2124, "lr": 2.612909475535256e-06, "epoch": 13.852001241079739, "percentage": 69.26, "elapsed_time": "1:22:15", "remaining_time": "0:36:30", "throughput": 5510.26, "total_tokens": 27198304} {"current_steps": 44650, "total_steps": 64460, "loss": 0.2093, "lr": 2.6117200041282375e-06, "epoch": 13.853552590753957, "percentage": 69.27, "elapsed_time": "1:22:16", "remaining_time": "0:36:30", "throughput": 5510.3, "total_tokens": 27201312} {"current_steps": 44655, "total_steps": 64460, "loss": 0.216, "lr": 2.6105307078104233e-06, "epoch": 13.855103940428172, "percentage": 69.28, "elapsed_time": "1:22:16", "remaining_time": "0:36:29", "throughput": 5510.17, "total_tokens": 27203200} {"current_steps": 44660, "total_steps": 64460, "loss": 0.2045, "lr": 2.609341586669005e-06, "epoch": 13.856655290102388, "percentage": 69.28, "elapsed_time": "1:22:17", "remaining_time": "0:36:29", "throughput": 5510.21, "total_tokens": 27206368} {"current_steps": 44665, "total_steps": 64460, "loss": 0.2122, "lr": 2.6081526407911555e-06, "epoch": 13.858206639776606, "percentage": 69.29, "elapsed_time": "1:22:17", "remaining_time": "0:36:28", "throughput": 5510.23, "total_tokens": 27209120} {"current_steps": 44670, "total_steps": 64460, "loss": 0.2018, "lr": 2.6069638702640437e-06, "epoch": 13.859757989450822, "percentage": 69.3, "elapsed_time": "1:22:18", "remaining_time": "0:36:27", "throughput": 5510.23, "total_tokens": 27211776} {"current_steps": 44675, "total_steps": 64460, "loss": 0.1732, "lr": 2.6057752751748156e-06, "epoch": 13.86130933912504, "percentage": 69.31, "elapsed_time": "1:22:18", "remaining_time": "0:36:27", "throughput": 5510.29, "total_tokens": 27214912} {"current_steps": 44680, "total_steps": 64460, "loss": 0.2329, "lr": 2.6045868556106145e-06, "epoch": 13.862860688799255, "percentage": 69.31, "elapsed_time": "1:22:19", "remaining_time": "0:36:26", "throughput": 5510.36, "total_tokens": 27218048} {"current_steps": 44685, "total_steps": 64460, "loss": 0.1926, "lr": 2.60339861165856e-06, "epoch": 13.864412038473471, "percentage": 69.32, "elapsed_time": "1:22:20", "remaining_time": "0:36:26", "throughput": 5510.45, "total_tokens": 27221728} {"current_steps": 44690, "total_steps": 64460, "loss": 0.2052, "lr": 2.602210543405768e-06, "epoch": 13.865963388147689, "percentage": 69.33, "elapsed_time": "1:22:20", "remaining_time": "0:36:25", "throughput": 5510.48, "total_tokens": 27224512} {"current_steps": 44695, "total_steps": 64460, "loss": 0.2413, "lr": 2.6010226509393387e-06, "epoch": 13.867514737821905, "percentage": 69.34, "elapsed_time": "1:22:20", "remaining_time": "0:36:24", "throughput": 5510.47, "total_tokens": 27227104} {"current_steps": 44700, "total_steps": 64460, "loss": 0.2429, "lr": 2.599834934346355e-06, "epoch": 13.869066087496122, "percentage": 69.35, "elapsed_time": "1:22:21", "remaining_time": "0:36:24", "throughput": 5510.59, "total_tokens": 27230720} {"current_steps": 44705, "total_steps": 64460, "loss": 0.215, "lr": 2.5986473937138957e-06, "epoch": 13.870617437170338, "percentage": 69.35, "elapsed_time": "1:22:22", "remaining_time": "0:36:23", "throughput": 5510.69, "total_tokens": 27234432} {"current_steps": 44710, "total_steps": 64460, "loss": 0.2195, "lr": 2.5974600291290157e-06, "epoch": 13.872168786844554, "percentage": 69.36, "elapsed_time": "1:22:22", "remaining_time": "0:36:23", "throughput": 5510.61, "total_tokens": 27236512} {"current_steps": 44715, "total_steps": 64460, "loss": 0.2203, "lr": 2.5962728406787683e-06, "epoch": 13.873720136518772, "percentage": 69.37, "elapsed_time": "1:22:23", "remaining_time": "0:36:22", "throughput": 5510.66, "total_tokens": 27239488} {"current_steps": 44720, "total_steps": 64460, "loss": 0.1988, "lr": 2.5950858284501847e-06, "epoch": 13.875271486192988, "percentage": 69.38, "elapsed_time": "1:22:23", "remaining_time": "0:36:22", "throughput": 5510.8, "total_tokens": 27243840} {"current_steps": 44725, "total_steps": 64460, "loss": 0.2306, "lr": 2.5938989925302892e-06, "epoch": 13.876822835867204, "percentage": 69.38, "elapsed_time": "1:22:24", "remaining_time": "0:36:21", "throughput": 5510.95, "total_tokens": 27248288} {"current_steps": 44730, "total_steps": 64460, "loss": 0.1983, "lr": 2.592712333006089e-06, "epoch": 13.878374185541421, "percentage": 69.39, "elapsed_time": "1:22:24", "remaining_time": "0:36:21", "throughput": 5510.97, "total_tokens": 27250944} {"current_steps": 44735, "total_steps": 64460, "loss": 0.2057, "lr": 2.591525849964583e-06, "epoch": 13.879925535215637, "percentage": 69.4, "elapsed_time": "1:22:25", "remaining_time": "0:36:20", "throughput": 5511.04, "total_tokens": 27254048} {"current_steps": 44740, "total_steps": 64460, "loss": 0.2199, "lr": 2.5903395434927504e-06, "epoch": 13.881476884889855, "percentage": 69.41, "elapsed_time": "1:22:25", "remaining_time": "0:36:20", "throughput": 5511.04, "total_tokens": 27257504} {"current_steps": 44745, "total_steps": 64460, "loss": 0.2258, "lr": 2.589153413677564e-06, "epoch": 13.88302823456407, "percentage": 69.42, "elapsed_time": "1:22:26", "remaining_time": "0:36:19", "throughput": 5511.16, "total_tokens": 27261248} {"current_steps": 44750, "total_steps": 64460, "loss": 0.1607, "lr": 2.587967460605984e-06, "epoch": 13.884579584238287, "percentage": 69.42, "elapsed_time": "1:22:27", "remaining_time": "0:36:18", "throughput": 5511.2, "total_tokens": 27264032} {"current_steps": 44755, "total_steps": 64460, "loss": 0.2294, "lr": 2.5867816843649492e-06, "epoch": 13.886130933912504, "percentage": 69.43, "elapsed_time": "1:22:27", "remaining_time": "0:36:18", "throughput": 5511.32, "total_tokens": 27267936} {"current_steps": 44760, "total_steps": 64460, "loss": 0.2117, "lr": 2.5855960850413936e-06, "epoch": 13.88768228358672, "percentage": 69.44, "elapsed_time": "1:22:28", "remaining_time": "0:36:17", "throughput": 5511.37, "total_tokens": 27270656} {"current_steps": 44765, "total_steps": 64460, "loss": 0.1881, "lr": 2.5844106627222376e-06, "epoch": 13.889233633260936, "percentage": 69.45, "elapsed_time": "1:22:28", "remaining_time": "0:36:17", "throughput": 5511.39, "total_tokens": 27273472} {"current_steps": 44770, "total_steps": 64460, "loss": 0.2726, "lr": 2.5832254174943838e-06, "epoch": 13.890784982935154, "percentage": 69.45, "elapsed_time": "1:22:29", "remaining_time": "0:36:16", "throughput": 5511.38, "total_tokens": 27276320} {"current_steps": 44775, "total_steps": 64460, "loss": 0.1808, "lr": 2.5820403494447255e-06, "epoch": 13.89233633260937, "percentage": 69.46, "elapsed_time": "1:22:29", "remaining_time": "0:36:16", "throughput": 5511.52, "total_tokens": 27280384} {"current_steps": 44780, "total_steps": 64460, "loss": 0.2112, "lr": 2.5808554586601437e-06, "epoch": 13.893887682283587, "percentage": 69.47, "elapsed_time": "1:22:30", "remaining_time": "0:36:15", "throughput": 5511.54, "total_tokens": 27283040} {"current_steps": 44785, "total_steps": 64460, "loss": 0.2586, "lr": 2.5796707452275026e-06, "epoch": 13.895439031957803, "percentage": 69.48, "elapsed_time": "1:22:30", "remaining_time": "0:36:14", "throughput": 5511.56, "total_tokens": 27285888} {"current_steps": 44790, "total_steps": 64460, "loss": 0.2175, "lr": 2.578486209233658e-06, "epoch": 13.896990381632019, "percentage": 69.48, "elapsed_time": "1:22:31", "remaining_time": "0:36:14", "throughput": 5511.63, "total_tokens": 27290016} {"current_steps": 44795, "total_steps": 64460, "loss": 0.2715, "lr": 2.577301850765448e-06, "epoch": 13.898541731306237, "percentage": 69.49, "elapsed_time": "1:22:31", "remaining_time": "0:36:13", "throughput": 5511.62, "total_tokens": 27292576} {"current_steps": 44800, "total_steps": 64460, "loss": 0.2339, "lr": 2.5761176699097035e-06, "epoch": 13.900093080980453, "percentage": 69.5, "elapsed_time": "1:22:32", "remaining_time": "0:36:13", "throughput": 5511.63, "total_tokens": 27295072} {"current_steps": 44805, "total_steps": 64460, "loss": 0.1936, "lr": 2.5749336667532343e-06, "epoch": 13.90164443065467, "percentage": 69.51, "elapsed_time": "1:22:32", "remaining_time": "0:36:12", "throughput": 5511.61, "total_tokens": 27297472} {"current_steps": 44810, "total_steps": 64460, "loss": 0.1742, "lr": 2.5737498413828465e-06, "epoch": 13.903195780328886, "percentage": 69.52, "elapsed_time": "1:22:33", "remaining_time": "0:36:12", "throughput": 5511.57, "total_tokens": 27300032} {"current_steps": 44815, "total_steps": 64460, "loss": 0.1838, "lr": 2.572566193885324e-06, "epoch": 13.904747130003102, "percentage": 69.52, "elapsed_time": "1:22:33", "remaining_time": "0:36:11", "throughput": 5511.72, "total_tokens": 27304704} {"current_steps": 44820, "total_steps": 64460, "loss": 0.2684, "lr": 2.5713827243474475e-06, "epoch": 13.90629847967732, "percentage": 69.53, "elapsed_time": "1:22:34", "remaining_time": "0:36:11", "throughput": 5511.82, "total_tokens": 27307872} {"current_steps": 44825, "total_steps": 64460, "loss": 0.2332, "lr": 2.5701994328559743e-06, "epoch": 13.907849829351536, "percentage": 69.54, "elapsed_time": "1:22:34", "remaining_time": "0:36:10", "throughput": 5511.79, "total_tokens": 27310272} {"current_steps": 44830, "total_steps": 64460, "loss": 0.1472, "lr": 2.5690163194976576e-06, "epoch": 13.909401179025753, "percentage": 69.55, "elapsed_time": "1:22:35", "remaining_time": "0:36:09", "throughput": 5511.84, "total_tokens": 27313344} {"current_steps": 44835, "total_steps": 64460, "loss": 0.2194, "lr": 2.5678333843592294e-06, "epoch": 13.91095252869997, "percentage": 69.55, "elapsed_time": "1:22:35", "remaining_time": "0:36:09", "throughput": 5511.85, "total_tokens": 27315840} {"current_steps": 44840, "total_steps": 64460, "loss": 0.2462, "lr": 2.566650627527416e-06, "epoch": 13.912503878374185, "percentage": 69.56, "elapsed_time": "1:22:36", "remaining_time": "0:36:08", "throughput": 5511.91, "total_tokens": 27318816} {"current_steps": 44845, "total_steps": 64460, "loss": 0.2094, "lr": 2.565468049088928e-06, "epoch": 13.914055228048403, "percentage": 69.57, "elapsed_time": "1:22:36", "remaining_time": "0:36:08", "throughput": 5512.08, "total_tokens": 27323136} {"current_steps": 44850, "total_steps": 64460, "loss": 0.1967, "lr": 2.56428564913046e-06, "epoch": 13.915606577722619, "percentage": 69.58, "elapsed_time": "1:22:37", "remaining_time": "0:36:07", "throughput": 5512.07, "total_tokens": 27325568} {"current_steps": 44855, "total_steps": 64460, "loss": 0.2327, "lr": 2.563103427738699e-06, "epoch": 13.917157927396834, "percentage": 69.59, "elapsed_time": "1:22:37", "remaining_time": "0:36:06", "throughput": 5512.13, "total_tokens": 27328704} {"current_steps": 44860, "total_steps": 64460, "loss": 0.1908, "lr": 2.5619213850003117e-06, "epoch": 13.918709277071052, "percentage": 69.59, "elapsed_time": "1:22:38", "remaining_time": "0:36:06", "throughput": 5512.13, "total_tokens": 27331264} {"current_steps": 44865, "total_steps": 64460, "loss": 0.1819, "lr": 2.5607395210019605e-06, "epoch": 13.920260626745268, "percentage": 69.6, "elapsed_time": "1:22:38", "remaining_time": "0:36:05", "throughput": 5512.2, "total_tokens": 27334464} {"current_steps": 44870, "total_steps": 64460, "loss": 0.2322, "lr": 2.5595578358302846e-06, "epoch": 13.921811976419486, "percentage": 69.61, "elapsed_time": "1:22:39", "remaining_time": "0:36:05", "throughput": 5512.31, "total_tokens": 27338432} {"current_steps": 44875, "total_steps": 64460, "loss": 0.2066, "lr": 2.5583763295719212e-06, "epoch": 13.923363326093702, "percentage": 69.62, "elapsed_time": "1:22:40", "remaining_time": "0:36:04", "throughput": 5512.24, "total_tokens": 27340960} {"current_steps": 44880, "total_steps": 64460, "loss": 0.2046, "lr": 2.557195002313484e-06, "epoch": 13.924914675767917, "percentage": 69.62, "elapsed_time": "1:22:40", "remaining_time": "0:36:04", "throughput": 5512.21, "total_tokens": 27343552} {"current_steps": 44885, "total_steps": 64460, "loss": 0.1932, "lr": 2.5560138541415814e-06, "epoch": 13.926466025442135, "percentage": 69.63, "elapsed_time": "1:22:41", "remaining_time": "0:36:03", "throughput": 5512.3, "total_tokens": 27347040} {"current_steps": 44890, "total_steps": 64460, "loss": 0.2046, "lr": 2.5548328851428032e-06, "epoch": 13.928017375116351, "percentage": 69.64, "elapsed_time": "1:22:41", "remaining_time": "0:36:03", "throughput": 5512.42, "total_tokens": 27350976} {"current_steps": 44895, "total_steps": 64460, "loss": 0.1881, "lr": 2.5536520954037295e-06, "epoch": 13.929568724790569, "percentage": 69.65, "elapsed_time": "1:22:42", "remaining_time": "0:36:02", "throughput": 5512.55, "total_tokens": 27355232} {"current_steps": 44900, "total_steps": 64460, "loss": 0.1853, "lr": 2.5524714850109288e-06, "epoch": 13.931120074464785, "percentage": 69.66, "elapsed_time": "1:22:42", "remaining_time": "0:36:02", "throughput": 5512.64, "total_tokens": 27358720} {"current_steps": 44905, "total_steps": 64460, "loss": 0.2698, "lr": 2.551291054050948e-06, "epoch": 13.932671424139, "percentage": 69.66, "elapsed_time": "1:22:43", "remaining_time": "0:36:01", "throughput": 5512.79, "total_tokens": 27363104} {"current_steps": 44910, "total_steps": 64460, "loss": 0.2571, "lr": 2.5501108026103334e-06, "epoch": 13.934222773813218, "percentage": 69.67, "elapsed_time": "1:22:44", "remaining_time": "0:36:00", "throughput": 5512.79, "total_tokens": 27365728} {"current_steps": 44915, "total_steps": 64460, "loss": 0.1846, "lr": 2.548930730775605e-06, "epoch": 13.935774123487434, "percentage": 69.68, "elapsed_time": "1:22:44", "remaining_time": "0:36:00", "throughput": 5512.87, "total_tokens": 27369312} {"current_steps": 44920, "total_steps": 64460, "loss": 0.1667, "lr": 2.547750838633282e-06, "epoch": 13.93732547316165, "percentage": 69.69, "elapsed_time": "1:22:45", "remaining_time": "0:35:59", "throughput": 5512.96, "total_tokens": 27372736} {"current_steps": 44925, "total_steps": 64460, "loss": 0.2421, "lr": 2.5465711262698587e-06, "epoch": 13.938876822835867, "percentage": 69.69, "elapsed_time": "1:22:45", "remaining_time": "0:35:59", "throughput": 5513.05, "total_tokens": 27376320} {"current_steps": 44930, "total_steps": 64460, "loss": 0.1577, "lr": 2.545391593771827e-06, "epoch": 13.940428172510083, "percentage": 69.7, "elapsed_time": "1:22:46", "remaining_time": "0:35:58", "throughput": 5513.0, "total_tokens": 27379008} {"current_steps": 44935, "total_steps": 64460, "loss": 0.1885, "lr": 2.5442122412256563e-06, "epoch": 13.941979522184301, "percentage": 69.71, "elapsed_time": "1:22:46", "remaining_time": "0:35:58", "throughput": 5513.01, "total_tokens": 27381856} {"current_steps": 44940, "total_steps": 64460, "loss": 0.2231, "lr": 2.543033068717812e-06, "epoch": 13.943530871858517, "percentage": 69.72, "elapsed_time": "1:22:47", "remaining_time": "0:35:57", "throughput": 5513.06, "total_tokens": 27385024} {"current_steps": 44945, "total_steps": 64460, "loss": 0.2337, "lr": 2.5418540763347356e-06, "epoch": 13.945082221532733, "percentage": 69.73, "elapsed_time": "1:22:47", "remaining_time": "0:35:56", "throughput": 5513.02, "total_tokens": 27387392} {"current_steps": 44950, "total_steps": 64460, "loss": 0.1918, "lr": 2.5406752641628664e-06, "epoch": 13.94663357120695, "percentage": 69.73, "elapsed_time": "1:22:48", "remaining_time": "0:35:56", "throughput": 5513.05, "total_tokens": 27390528} {"current_steps": 44955, "total_steps": 64460, "loss": 0.1908, "lr": 2.5394966322886215e-06, "epoch": 13.948184920881166, "percentage": 69.74, "elapsed_time": "1:22:49", "remaining_time": "0:35:56", "throughput": 5513.29, "total_tokens": 27396448} {"current_steps": 44960, "total_steps": 64460, "loss": 0.2317, "lr": 2.5383181807984097e-06, "epoch": 13.949736270555384, "percentage": 69.75, "elapsed_time": "1:22:49", "remaining_time": "0:35:55", "throughput": 5513.19, "total_tokens": 27398912} {"current_steps": 44965, "total_steps": 64460, "loss": 0.1953, "lr": 2.5371399097786283e-06, "epoch": 13.9512876202296, "percentage": 69.76, "elapsed_time": "1:22:50", "remaining_time": "0:35:54", "throughput": 5513.3, "total_tokens": 27402784} {"current_steps": 44970, "total_steps": 64460, "loss": 0.1994, "lr": 2.5359618193156536e-06, "epoch": 13.952838969903816, "percentage": 69.76, "elapsed_time": "1:22:50", "remaining_time": "0:35:54", "throughput": 5513.45, "total_tokens": 27406496} {"current_steps": 44975, "total_steps": 64460, "loss": 0.2322, "lr": 2.534783909495859e-06, "epoch": 13.954390319578033, "percentage": 69.77, "elapsed_time": "1:22:51", "remaining_time": "0:35:53", "throughput": 5513.47, "total_tokens": 27409280} {"current_steps": 44980, "total_steps": 64460, "loss": 0.1814, "lr": 2.5336061804055934e-06, "epoch": 13.95594166925225, "percentage": 69.78, "elapsed_time": "1:22:51", "remaining_time": "0:35:53", "throughput": 5513.49, "total_tokens": 27412128} {"current_steps": 44985, "total_steps": 64460, "loss": 0.1445, "lr": 2.5324286321312043e-06, "epoch": 13.957493018926465, "percentage": 69.79, "elapsed_time": "1:22:52", "remaining_time": "0:35:52", "throughput": 5513.61, "total_tokens": 27416160} {"current_steps": 44990, "total_steps": 64460, "loss": 0.1657, "lr": 2.5312512647590136e-06, "epoch": 13.959044368600683, "percentage": 69.8, "elapsed_time": "1:22:53", "remaining_time": "0:35:52", "throughput": 5513.77, "total_tokens": 27421184} {"current_steps": 44995, "total_steps": 64460, "loss": 0.181, "lr": 2.5300740783753427e-06, "epoch": 13.960595718274899, "percentage": 69.8, "elapsed_time": "1:22:53", "remaining_time": "0:35:51", "throughput": 5513.77, "total_tokens": 27424096} {"current_steps": 45000, "total_steps": 64460, "loss": 0.1815, "lr": 2.5288970730664873e-06, "epoch": 13.962147067949116, "percentage": 69.81, "elapsed_time": "1:22:54", "remaining_time": "0:35:51", "throughput": 5513.76, "total_tokens": 27426752} {"current_steps": 45005, "total_steps": 64460, "loss": 0.2311, "lr": 2.527720248918741e-06, "epoch": 13.963698417623332, "percentage": 69.82, "elapsed_time": "1:22:54", "remaining_time": "0:35:50", "throughput": 5513.71, "total_tokens": 27429152} {"current_steps": 45010, "total_steps": 64460, "loss": 0.2007, "lr": 2.526543606018375e-06, "epoch": 13.965249767297548, "percentage": 69.83, "elapsed_time": "1:22:55", "remaining_time": "0:35:49", "throughput": 5513.79, "total_tokens": 27432608} {"current_steps": 45015, "total_steps": 64460, "loss": 0.2608, "lr": 2.5253671444516526e-06, "epoch": 13.966801116971766, "percentage": 69.83, "elapsed_time": "1:22:55", "remaining_time": "0:35:49", "throughput": 5513.75, "total_tokens": 27434976} {"current_steps": 45020, "total_steps": 64460, "loss": 0.2092, "lr": 2.524190864304824e-06, "epoch": 13.968352466645982, "percentage": 69.84, "elapsed_time": "1:22:56", "remaining_time": "0:35:48", "throughput": 5513.76, "total_tokens": 27437696} {"current_steps": 45025, "total_steps": 64460, "loss": 0.1493, "lr": 2.523014765664122e-06, "epoch": 13.9699038163202, "percentage": 69.85, "elapsed_time": "1:22:56", "remaining_time": "0:35:48", "throughput": 5513.86, "total_tokens": 27441280} {"current_steps": 45030, "total_steps": 64460, "loss": 0.3052, "lr": 2.521838848615771e-06, "epoch": 13.971455165994415, "percentage": 69.86, "elapsed_time": "1:22:57", "remaining_time": "0:35:47", "throughput": 5513.9, "total_tokens": 27444128} {"current_steps": 45035, "total_steps": 64460, "loss": 0.1736, "lr": 2.5206631132459756e-06, "epoch": 13.973006515668631, "percentage": 69.87, "elapsed_time": "1:22:57", "remaining_time": "0:35:47", "throughput": 5513.94, "total_tokens": 27447040} {"current_steps": 45040, "total_steps": 64460, "loss": 0.18, "lr": 2.5194875596409368e-06, "epoch": 13.974557865342849, "percentage": 69.87, "elapsed_time": "1:22:58", "remaining_time": "0:35:46", "throughput": 5513.95, "total_tokens": 27449696} {"current_steps": 45045, "total_steps": 64460, "loss": 0.2463, "lr": 2.518312187886831e-06, "epoch": 13.976109215017065, "percentage": 69.88, "elapsed_time": "1:22:58", "remaining_time": "0:35:45", "throughput": 5513.91, "total_tokens": 27452480} {"current_steps": 45050, "total_steps": 64460, "loss": 0.1692, "lr": 2.5171369980698313e-06, "epoch": 13.97766056469128, "percentage": 69.89, "elapsed_time": "1:22:59", "remaining_time": "0:35:45", "throughput": 5513.9, "total_tokens": 27455360} {"current_steps": 45055, "total_steps": 64460, "loss": 0.1979, "lr": 2.5159619902760897e-06, "epoch": 13.979211914365498, "percentage": 69.9, "elapsed_time": "1:22:59", "remaining_time": "0:35:44", "throughput": 5513.89, "total_tokens": 27458240} {"current_steps": 45060, "total_steps": 64460, "loss": 0.2397, "lr": 2.514787164591751e-06, "epoch": 13.980763264039714, "percentage": 69.9, "elapsed_time": "1:23:00", "remaining_time": "0:35:44", "throughput": 5513.94, "total_tokens": 27461184} {"current_steps": 45065, "total_steps": 64460, "loss": 0.2215, "lr": 2.513612521102941e-06, "epoch": 13.982314613713932, "percentage": 69.91, "elapsed_time": "1:23:00", "remaining_time": "0:35:43", "throughput": 5513.91, "total_tokens": 27463616} {"current_steps": 45070, "total_steps": 64460, "loss": 0.1703, "lr": 2.512438059895778e-06, "epoch": 13.983865963388148, "percentage": 69.92, "elapsed_time": "1:23:01", "remaining_time": "0:35:43", "throughput": 5513.91, "total_tokens": 27466240} {"current_steps": 45075, "total_steps": 64460, "loss": 0.2031, "lr": 2.5112637810563605e-06, "epoch": 13.985417313062364, "percentage": 69.93, "elapsed_time": "1:23:01", "remaining_time": "0:35:42", "throughput": 5513.86, "total_tokens": 27468640} {"current_steps": 45080, "total_steps": 64460, "loss": 0.1812, "lr": 2.510089684670779e-06, "epoch": 13.986968662736581, "percentage": 69.93, "elapsed_time": "1:23:02", "remaining_time": "0:35:41", "throughput": 5513.98, "total_tokens": 27472864} {"current_steps": 45085, "total_steps": 64460, "loss": 0.1781, "lr": 2.5089157708251105e-06, "epoch": 13.988520012410797, "percentage": 69.94, "elapsed_time": "1:23:02", "remaining_time": "0:35:41", "throughput": 5514.01, "total_tokens": 27475744} {"current_steps": 45090, "total_steps": 64460, "loss": 0.2188, "lr": 2.5077420396054133e-06, "epoch": 13.990071362085015, "percentage": 69.95, "elapsed_time": "1:23:03", "remaining_time": "0:35:40", "throughput": 5513.9, "total_tokens": 27477728} {"current_steps": 45095, "total_steps": 64460, "loss": 0.1975, "lr": 2.5065684910977383e-06, "epoch": 13.99162271175923, "percentage": 69.96, "elapsed_time": "1:23:03", "remaining_time": "0:35:40", "throughput": 5513.96, "total_tokens": 27480832} {"current_steps": 45100, "total_steps": 64460, "loss": 0.1998, "lr": 2.5053951253881183e-06, "epoch": 13.993174061433447, "percentage": 69.97, "elapsed_time": "1:23:04", "remaining_time": "0:35:39", "throughput": 5514.14, "total_tokens": 27486016} {"current_steps": 45105, "total_steps": 64460, "loss": 0.3088, "lr": 2.504221942562578e-06, "epoch": 13.994725411107664, "percentage": 69.97, "elapsed_time": "1:23:05", "remaining_time": "0:35:39", "throughput": 5514.04, "total_tokens": 27488256} {"current_steps": 45110, "total_steps": 64460, "loss": 0.2112, "lr": 2.503048942707121e-06, "epoch": 13.99627676078188, "percentage": 69.98, "elapsed_time": "1:23:05", "remaining_time": "0:35:38", "throughput": 5514.12, "total_tokens": 27491840} {"current_steps": 45115, "total_steps": 64460, "loss": 0.1966, "lr": 2.5018761259077485e-06, "epoch": 13.997828110456096, "percentage": 69.99, "elapsed_time": "1:23:06", "remaining_time": "0:35:38", "throughput": 5514.15, "total_tokens": 27494848} {"current_steps": 45120, "total_steps": 64460, "loss": 0.2071, "lr": 2.5007034922504346e-06, "epoch": 13.999379460130314, "percentage": 70.0, "elapsed_time": "1:23:06", "remaining_time": "0:35:37", "throughput": 5514.1, "total_tokens": 27497120} {"current_steps": 45122, "total_steps": 64460, "eval_loss": 0.2693102955818176, "epoch": 14.0, "percentage": 70.0, "elapsed_time": "1:23:41", "remaining_time": "0:35:52", "throughput": 5476.05, "total_tokens": 27497648} {"current_steps": 45125, "total_steps": 64460, "loss": 0.1561, "lr": 2.4995310418211538e-06, "epoch": 14.00093080980453, "percentage": 70.0, "elapsed_time": "1:23:45", "remaining_time": "0:35:53", "throughput": 5471.91, "total_tokens": 27499440} {"current_steps": 45130, "total_steps": 64460, "loss": 0.1769, "lr": 2.4983587747058553e-06, "epoch": 14.002482159478747, "percentage": 70.01, "elapsed_time": "1:23:46", "remaining_time": "0:35:52", "throughput": 5471.94, "total_tokens": 27502448} {"current_steps": 45135, "total_steps": 64460, "loss": 0.2093, "lr": 2.4971866909904824e-06, "epoch": 14.004033509152963, "percentage": 70.02, "elapsed_time": "1:23:46", "remaining_time": "0:35:52", "throughput": 5471.88, "total_tokens": 27504944} {"current_steps": 45140, "total_steps": 64460, "loss": 0.1591, "lr": 2.496014790760965e-06, "epoch": 14.005584858827179, "percentage": 70.03, "elapsed_time": "1:23:47", "remaining_time": "0:35:51", "throughput": 5472.01, "total_tokens": 27508496} {"current_steps": 45145, "total_steps": 64460, "loss": 0.1957, "lr": 2.4948430741032127e-06, "epoch": 14.007136208501397, "percentage": 70.04, "elapsed_time": "1:23:47", "remaining_time": "0:35:51", "throughput": 5471.92, "total_tokens": 27510640} {"current_steps": 45150, "total_steps": 64460, "loss": 0.2088, "lr": 2.493671541103131e-06, "epoch": 14.008687558175613, "percentage": 70.04, "elapsed_time": "1:23:48", "remaining_time": "0:35:50", "throughput": 5472.04, "total_tokens": 27514192} {"current_steps": 45155, "total_steps": 64460, "loss": 0.2, "lr": 2.4925001918466025e-06, "epoch": 14.01023890784983, "percentage": 70.05, "elapsed_time": "1:23:48", "remaining_time": "0:35:49", "throughput": 5471.98, "total_tokens": 27516944} {"current_steps": 45160, "total_steps": 64460, "loss": 0.1922, "lr": 2.491329026419505e-06, "epoch": 14.011790257524046, "percentage": 70.06, "elapsed_time": "1:23:49", "remaining_time": "0:35:49", "throughput": 5471.91, "total_tokens": 27519632} {"current_steps": 45165, "total_steps": 64460, "loss": 0.2171, "lr": 2.490158044907695e-06, "epoch": 14.013341607198262, "percentage": 70.07, "elapsed_time": "1:23:49", "remaining_time": "0:35:48", "throughput": 5471.9, "total_tokens": 27522576} {"current_steps": 45170, "total_steps": 64460, "loss": 0.1576, "lr": 2.488987247397023e-06, "epoch": 14.01489295687248, "percentage": 70.07, "elapsed_time": "1:23:50", "remaining_time": "0:35:48", "throughput": 5471.79, "total_tokens": 27524880} {"current_steps": 45175, "total_steps": 64460, "loss": 0.1974, "lr": 2.4878166339733194e-06, "epoch": 14.016444306546695, "percentage": 70.08, "elapsed_time": "1:23:50", "remaining_time": "0:35:47", "throughput": 5471.71, "total_tokens": 27527408} {"current_steps": 45180, "total_steps": 64460, "loss": 0.1309, "lr": 2.4866462047224064e-06, "epoch": 14.017995656220911, "percentage": 70.09, "elapsed_time": "1:23:51", "remaining_time": "0:35:47", "throughput": 5471.71, "total_tokens": 27530064} {"current_steps": 45185, "total_steps": 64460, "loss": 0.1515, "lr": 2.485475959730088e-06, "epoch": 14.019547005895129, "percentage": 70.1, "elapsed_time": "1:23:51", "remaining_time": "0:35:46", "throughput": 5471.68, "total_tokens": 27532656} {"current_steps": 45190, "total_steps": 64460, "loss": 0.172, "lr": 2.4843058990821596e-06, "epoch": 14.021098355569345, "percentage": 70.11, "elapsed_time": "1:23:52", "remaining_time": "0:35:45", "throughput": 5471.7, "total_tokens": 27535888} {"current_steps": 45195, "total_steps": 64460, "loss": 0.1779, "lr": 2.4831360228643976e-06, "epoch": 14.022649705243563, "percentage": 70.11, "elapsed_time": "1:23:52", "remaining_time": "0:35:45", "throughput": 5471.75, "total_tokens": 27539120} {"current_steps": 45200, "total_steps": 64460, "loss": 0.1885, "lr": 2.4819663311625686e-06, "epoch": 14.024201054917778, "percentage": 70.12, "elapsed_time": "1:23:53", "remaining_time": "0:35:44", "throughput": 5471.73, "total_tokens": 27541744} {"current_steps": 45205, "total_steps": 64460, "loss": 0.1985, "lr": 2.4807968240624275e-06, "epoch": 14.025752404591994, "percentage": 70.13, "elapsed_time": "1:23:53", "remaining_time": "0:35:44", "throughput": 5471.7, "total_tokens": 27544400} {"current_steps": 45210, "total_steps": 64460, "loss": 0.1942, "lr": 2.4796275016497095e-06, "epoch": 14.027303754266212, "percentage": 70.14, "elapsed_time": "1:23:54", "remaining_time": "0:35:43", "throughput": 5471.64, "total_tokens": 27547056} {"current_steps": 45215, "total_steps": 64460, "loss": 0.1389, "lr": 2.4784583640101435e-06, "epoch": 14.028855103940428, "percentage": 70.14, "elapsed_time": "1:23:55", "remaining_time": "0:35:43", "throughput": 5471.66, "total_tokens": 27550128} {"current_steps": 45220, "total_steps": 64460, "loss": 0.1727, "lr": 2.477289411229436e-06, "epoch": 14.030406453614646, "percentage": 70.15, "elapsed_time": "1:23:55", "remaining_time": "0:35:42", "throughput": 5471.62, "total_tokens": 27552688} {"current_steps": 45225, "total_steps": 64460, "loss": 0.1422, "lr": 2.476120643393291e-06, "epoch": 14.031957803288861, "percentage": 70.16, "elapsed_time": "1:23:56", "remaining_time": "0:35:41", "throughput": 5471.7, "total_tokens": 27555952} {"current_steps": 45230, "total_steps": 64460, "loss": 0.206, "lr": 2.474952060587387e-06, "epoch": 14.033509152963077, "percentage": 70.17, "elapsed_time": "1:23:56", "remaining_time": "0:35:41", "throughput": 5471.77, "total_tokens": 27559632} {"current_steps": 45235, "total_steps": 64460, "loss": 0.202, "lr": 2.473783662897401e-06, "epoch": 14.035060502637295, "percentage": 70.18, "elapsed_time": "1:23:57", "remaining_time": "0:35:40", "throughput": 5471.75, "total_tokens": 27562448} {"current_steps": 45240, "total_steps": 64460, "loss": 0.1604, "lr": 2.472615450408985e-06, "epoch": 14.03661185231151, "percentage": 70.18, "elapsed_time": "1:23:57", "remaining_time": "0:35:40", "throughput": 5471.82, "total_tokens": 27565552} {"current_steps": 45245, "total_steps": 64460, "loss": 0.2465, "lr": 2.4714474232077873e-06, "epoch": 14.038163201985727, "percentage": 70.19, "elapsed_time": "1:23:58", "remaining_time": "0:35:39", "throughput": 5471.75, "total_tokens": 27567952} {"current_steps": 45250, "total_steps": 64460, "loss": 0.1727, "lr": 2.4702795813794337e-06, "epoch": 14.039714551659944, "percentage": 70.2, "elapsed_time": "1:23:58", "remaining_time": "0:35:39", "throughput": 5471.77, "total_tokens": 27570992} {"current_steps": 45255, "total_steps": 64460, "loss": 0.2494, "lr": 2.4691119250095437e-06, "epoch": 14.04126590133416, "percentage": 70.21, "elapsed_time": "1:23:59", "remaining_time": "0:35:38", "throughput": 5471.75, "total_tokens": 27573648} {"current_steps": 45260, "total_steps": 64460, "loss": 0.1734, "lr": 2.4679444541837213e-06, "epoch": 14.042817251008378, "percentage": 70.21, "elapsed_time": "1:23:59", "remaining_time": "0:35:38", "throughput": 5471.75, "total_tokens": 27577168} {"current_steps": 45265, "total_steps": 64460, "loss": 0.2539, "lr": 2.4667771689875523e-06, "epoch": 14.044368600682594, "percentage": 70.22, "elapsed_time": "1:24:00", "remaining_time": "0:35:37", "throughput": 5471.69, "total_tokens": 27579536} {"current_steps": 45270, "total_steps": 64460, "loss": 0.197, "lr": 2.465610069506617e-06, "epoch": 14.04591995035681, "percentage": 70.23, "elapsed_time": "1:24:01", "remaining_time": "0:35:36", "throughput": 5471.6, "total_tokens": 27582640} {"current_steps": 45275, "total_steps": 64460, "loss": 0.134, "lr": 2.4644431558264738e-06, "epoch": 14.047471300031027, "percentage": 70.24, "elapsed_time": "1:24:01", "remaining_time": "0:35:36", "throughput": 5471.63, "total_tokens": 27585680} {"current_steps": 45280, "total_steps": 64460, "loss": 0.142, "lr": 2.4632764280326737e-06, "epoch": 14.049022649705243, "percentage": 70.25, "elapsed_time": "1:24:02", "remaining_time": "0:35:35", "throughput": 5471.73, "total_tokens": 27589040} {"current_steps": 45285, "total_steps": 64460, "loss": 0.2248, "lr": 2.4621098862107496e-06, "epoch": 14.050573999379461, "percentage": 70.25, "elapsed_time": "1:24:02", "remaining_time": "0:35:35", "throughput": 5471.78, "total_tokens": 27592688} {"current_steps": 45290, "total_steps": 64460, "loss": 0.1908, "lr": 2.460943530446225e-06, "epoch": 14.052125349053677, "percentage": 70.26, "elapsed_time": "1:24:03", "remaining_time": "0:35:34", "throughput": 5471.78, "total_tokens": 27595312} {"current_steps": 45295, "total_steps": 64460, "loss": 0.1837, "lr": 2.459777360824606e-06, "epoch": 14.053676698727893, "percentage": 70.27, "elapsed_time": "1:24:03", "remaining_time": "0:35:34", "throughput": 5471.77, "total_tokens": 27598096} {"current_steps": 45300, "total_steps": 64460, "loss": 0.2102, "lr": 2.458611377431388e-06, "epoch": 14.05522804840211, "percentage": 70.28, "elapsed_time": "1:24:04", "remaining_time": "0:35:33", "throughput": 5471.85, "total_tokens": 27601392} {"current_steps": 45305, "total_steps": 64460, "loss": 0.1363, "lr": 2.4574455803520486e-06, "epoch": 14.056779398076326, "percentage": 70.28, "elapsed_time": "1:24:04", "remaining_time": "0:35:32", "throughput": 5471.91, "total_tokens": 27604432} {"current_steps": 45310, "total_steps": 64460, "loss": 0.157, "lr": 2.456279969672059e-06, "epoch": 14.058330747750542, "percentage": 70.29, "elapsed_time": "1:24:05", "remaining_time": "0:35:32", "throughput": 5471.9, "total_tokens": 27606960} {"current_steps": 45315, "total_steps": 64460, "loss": 0.2234, "lr": 2.455114545476868e-06, "epoch": 14.05988209742476, "percentage": 70.3, "elapsed_time": "1:24:05", "remaining_time": "0:35:31", "throughput": 5471.97, "total_tokens": 27610192} {"current_steps": 45320, "total_steps": 64460, "loss": 0.2314, "lr": 2.4539493078519163e-06, "epoch": 14.061433447098976, "percentage": 70.31, "elapsed_time": "1:24:06", "remaining_time": "0:35:31", "throughput": 5471.88, "total_tokens": 27612304} {"current_steps": 45325, "total_steps": 64460, "loss": 0.1784, "lr": 2.4527842568826317e-06, "epoch": 14.062984796773193, "percentage": 70.31, "elapsed_time": "1:24:06", "remaining_time": "0:35:30", "throughput": 5471.91, "total_tokens": 27615920} {"current_steps": 45330, "total_steps": 64460, "loss": 0.1541, "lr": 2.451619392654423e-06, "epoch": 14.06453614644741, "percentage": 70.32, "elapsed_time": "1:24:07", "remaining_time": "0:35:30", "throughput": 5472.03, "total_tokens": 27620336} {"current_steps": 45335, "total_steps": 64460, "loss": 0.1888, "lr": 2.4504547152526905e-06, "epoch": 14.066087496121625, "percentage": 70.33, "elapsed_time": "1:24:08", "remaining_time": "0:35:29", "throughput": 5472.09, "total_tokens": 27623312} {"current_steps": 45340, "total_steps": 64460, "loss": 0.1525, "lr": 2.449290224762818e-06, "epoch": 14.067638845795843, "percentage": 70.34, "elapsed_time": "1:24:08", "remaining_time": "0:35:29", "throughput": 5472.11, "total_tokens": 27626480} {"current_steps": 45345, "total_steps": 64460, "loss": 0.195, "lr": 2.448125921270179e-06, "epoch": 14.069190195470059, "percentage": 70.35, "elapsed_time": "1:24:09", "remaining_time": "0:35:28", "throughput": 5472.17, "total_tokens": 27630128} {"current_steps": 45350, "total_steps": 64460, "loss": 0.1851, "lr": 2.4469618048601268e-06, "epoch": 14.070741545144276, "percentage": 70.35, "elapsed_time": "1:24:09", "remaining_time": "0:35:27", "throughput": 5472.25, "total_tokens": 27633328} {"current_steps": 45355, "total_steps": 64460, "loss": 0.1678, "lr": 2.4457978756180088e-06, "epoch": 14.072292894818492, "percentage": 70.36, "elapsed_time": "1:24:10", "remaining_time": "0:35:27", "throughput": 5472.29, "total_tokens": 27636336} {"current_steps": 45360, "total_steps": 64460, "loss": 0.2018, "lr": 2.4446341336291514e-06, "epoch": 14.073844244492708, "percentage": 70.37, "elapsed_time": "1:24:10", "remaining_time": "0:35:26", "throughput": 5472.17, "total_tokens": 27638608} {"current_steps": 45365, "total_steps": 64460, "loss": 0.1787, "lr": 2.4434705789788734e-06, "epoch": 14.075395594166926, "percentage": 70.38, "elapsed_time": "1:24:11", "remaining_time": "0:35:26", "throughput": 5472.17, "total_tokens": 27641648} {"current_steps": 45370, "total_steps": 64460, "loss": 0.2617, "lr": 2.442307211752474e-06, "epoch": 14.076946943841142, "percentage": 70.38, "elapsed_time": "1:24:11", "remaining_time": "0:35:25", "throughput": 5472.15, "total_tokens": 27644336} {"current_steps": 45375, "total_steps": 64460, "loss": 0.1648, "lr": 2.4411440320352453e-06, "epoch": 14.078498293515358, "percentage": 70.39, "elapsed_time": "1:24:12", "remaining_time": "0:35:25", "throughput": 5472.2, "total_tokens": 27647952} {"current_steps": 45380, "total_steps": 64460, "loss": 0.1937, "lr": 2.4399810399124585e-06, "epoch": 14.080049643189575, "percentage": 70.4, "elapsed_time": "1:24:12", "remaining_time": "0:35:24", "throughput": 5472.14, "total_tokens": 27650352} {"current_steps": 45385, "total_steps": 64460, "loss": 0.1878, "lr": 2.4388182354693783e-06, "epoch": 14.081600992863791, "percentage": 70.41, "elapsed_time": "1:24:13", "remaining_time": "0:35:24", "throughput": 5472.35, "total_tokens": 27655472} {"current_steps": 45390, "total_steps": 64460, "loss": 0.1672, "lr": 2.437655618791249e-06, "epoch": 14.083152342538009, "percentage": 70.42, "elapsed_time": "1:24:14", "remaining_time": "0:35:23", "throughput": 5472.5, "total_tokens": 27659472} {"current_steps": 45395, "total_steps": 64460, "loss": 0.2394, "lr": 2.4364931899633078e-06, "epoch": 14.084703692212225, "percentage": 70.42, "elapsed_time": "1:24:14", "remaining_time": "0:35:22", "throughput": 5472.58, "total_tokens": 27662608} {"current_steps": 45400, "total_steps": 64460, "loss": 0.1758, "lr": 2.4353309490707693e-06, "epoch": 14.08625504188644, "percentage": 70.43, "elapsed_time": "1:24:15", "remaining_time": "0:35:22", "throughput": 5472.73, "total_tokens": 27666608} {"current_steps": 45405, "total_steps": 64460, "loss": 0.2513, "lr": 2.4341688961988437e-06, "epoch": 14.087806391560658, "percentage": 70.44, "elapsed_time": "1:24:15", "remaining_time": "0:35:21", "throughput": 5472.72, "total_tokens": 27669328} {"current_steps": 45410, "total_steps": 64460, "loss": 0.1762, "lr": 2.4330070314327225e-06, "epoch": 14.089357741234874, "percentage": 70.45, "elapsed_time": "1:24:16", "remaining_time": "0:35:21", "throughput": 5472.69, "total_tokens": 27671888} {"current_steps": 45415, "total_steps": 64460, "loss": 0.1299, "lr": 2.4318453548575825e-06, "epoch": 14.090909090909092, "percentage": 70.45, "elapsed_time": "1:24:16", "remaining_time": "0:35:20", "throughput": 5472.79, "total_tokens": 27675184} {"current_steps": 45420, "total_steps": 64460, "loss": 0.1556, "lr": 2.4306838665585915e-06, "epoch": 14.092460440583308, "percentage": 70.46, "elapsed_time": "1:24:17", "remaining_time": "0:35:20", "throughput": 5472.89, "total_tokens": 27678608} {"current_steps": 45425, "total_steps": 64460, "loss": 0.2742, "lr": 2.4295225666208964e-06, "epoch": 14.094011790257523, "percentage": 70.47, "elapsed_time": "1:24:18", "remaining_time": "0:35:19", "throughput": 5473.0, "total_tokens": 27682512} {"current_steps": 45430, "total_steps": 64460, "loss": 0.2701, "lr": 2.428361455129638e-06, "epoch": 14.095563139931741, "percentage": 70.48, "elapsed_time": "1:24:18", "remaining_time": "0:35:18", "throughput": 5473.01, "total_tokens": 27685456} {"current_steps": 45435, "total_steps": 64460, "loss": 0.2854, "lr": 2.4272005321699356e-06, "epoch": 14.097114489605957, "percentage": 70.49, "elapsed_time": "1:24:19", "remaining_time": "0:35:18", "throughput": 5473.08, "total_tokens": 27689008} {"current_steps": 45440, "total_steps": 64460, "loss": 0.2891, "lr": 2.4260397978269028e-06, "epoch": 14.098665839280173, "percentage": 70.49, "elapsed_time": "1:24:19", "remaining_time": "0:35:17", "throughput": 5473.18, "total_tokens": 27692624} {"current_steps": 45445, "total_steps": 64460, "loss": 0.2236, "lr": 2.424879252185631e-06, "epoch": 14.10021718895439, "percentage": 70.5, "elapsed_time": "1:24:20", "remaining_time": "0:35:17", "throughput": 5473.25, "total_tokens": 27695888} {"current_steps": 45450, "total_steps": 64460, "loss": 0.1662, "lr": 2.423718895331206e-06, "epoch": 14.101768538628606, "percentage": 70.51, "elapsed_time": "1:24:20", "remaining_time": "0:35:16", "throughput": 5473.32, "total_tokens": 27699184} {"current_steps": 45455, "total_steps": 64460, "loss": 0.2121, "lr": 2.4225587273486915e-06, "epoch": 14.103319888302824, "percentage": 70.52, "elapsed_time": "1:24:21", "remaining_time": "0:35:16", "throughput": 5473.32, "total_tokens": 27702032} {"current_steps": 45460, "total_steps": 64460, "loss": 0.2274, "lr": 2.4213987483231443e-06, "epoch": 14.10487123797704, "percentage": 70.52, "elapsed_time": "1:24:21", "remaining_time": "0:35:15", "throughput": 5473.41, "total_tokens": 27705200} {"current_steps": 45465, "total_steps": 64460, "loss": 0.2193, "lr": 2.420238958339606e-06, "epoch": 14.106422587651256, "percentage": 70.53, "elapsed_time": "1:24:22", "remaining_time": "0:35:15", "throughput": 5473.37, "total_tokens": 27707952} {"current_steps": 45470, "total_steps": 64460, "loss": 0.2604, "lr": 2.419079357483099e-06, "epoch": 14.107973937325474, "percentage": 70.54, "elapsed_time": "1:24:22", "remaining_time": "0:35:14", "throughput": 5473.34, "total_tokens": 27710608} {"current_steps": 45475, "total_steps": 64460, "loss": 0.2364, "lr": 2.4179199458386393e-06, "epoch": 14.10952528699969, "percentage": 70.55, "elapsed_time": "1:24:23", "remaining_time": "0:35:13", "throughput": 5473.4, "total_tokens": 27714352} {"current_steps": 45480, "total_steps": 64460, "loss": 0.198, "lr": 2.416760723491222e-06, "epoch": 14.111076636673907, "percentage": 70.56, "elapsed_time": "1:24:23", "remaining_time": "0:35:13", "throughput": 5473.47, "total_tokens": 27717520} {"current_steps": 45485, "total_steps": 64460, "loss": 0.2288, "lr": 2.415601690525836e-06, "epoch": 14.112627986348123, "percentage": 70.56, "elapsed_time": "1:24:24", "remaining_time": "0:35:12", "throughput": 5473.48, "total_tokens": 27720496} {"current_steps": 45490, "total_steps": 64460, "loss": 0.1445, "lr": 2.4144428470274483e-06, "epoch": 14.114179336022339, "percentage": 70.57, "elapsed_time": "1:24:25", "remaining_time": "0:35:12", "throughput": 5473.43, "total_tokens": 27723024} {"current_steps": 45495, "total_steps": 64460, "loss": 0.1697, "lr": 2.413284193081019e-06, "epoch": 14.115730685696557, "percentage": 70.58, "elapsed_time": "1:24:25", "remaining_time": "0:35:11", "throughput": 5473.45, "total_tokens": 27726256} {"current_steps": 45500, "total_steps": 64460, "loss": 0.2, "lr": 2.4121257287714877e-06, "epoch": 14.117282035370772, "percentage": 70.59, "elapsed_time": "1:24:26", "remaining_time": "0:35:11", "throughput": 5473.59, "total_tokens": 27730544} {"current_steps": 45505, "total_steps": 64460, "loss": 0.1659, "lr": 2.4109674541837873e-06, "epoch": 14.118833385044988, "percentage": 70.59, "elapsed_time": "1:24:26", "remaining_time": "0:35:10", "throughput": 5473.5, "total_tokens": 27732976} {"current_steps": 45510, "total_steps": 64460, "loss": 0.2493, "lr": 2.4098093694028296e-06, "epoch": 14.120384734719206, "percentage": 70.6, "elapsed_time": "1:24:27", "remaining_time": "0:35:09", "throughput": 5473.52, "total_tokens": 27735920} {"current_steps": 45515, "total_steps": 64460, "loss": 0.1725, "lr": 2.40865147451352e-06, "epoch": 14.121936084393422, "percentage": 70.61, "elapsed_time": "1:24:27", "remaining_time": "0:35:09", "throughput": 5473.59, "total_tokens": 27739248} {"current_steps": 45520, "total_steps": 64460, "loss": 0.2144, "lr": 2.4074937696007407e-06, "epoch": 14.12348743406764, "percentage": 70.62, "elapsed_time": "1:24:28", "remaining_time": "0:35:08", "throughput": 5473.62, "total_tokens": 27742192} {"current_steps": 45525, "total_steps": 64460, "loss": 0.2129, "lr": 2.4063362547493685e-06, "epoch": 14.125038783741855, "percentage": 70.63, "elapsed_time": "1:24:28", "remaining_time": "0:35:08", "throughput": 5473.64, "total_tokens": 27744944} {"current_steps": 45530, "total_steps": 64460, "loss": 0.1968, "lr": 2.405178930044264e-06, "epoch": 14.126590133416071, "percentage": 70.63, "elapsed_time": "1:24:29", "remaining_time": "0:35:07", "throughput": 5473.68, "total_tokens": 27747984} {"current_steps": 45535, "total_steps": 64460, "loss": 0.1646, "lr": 2.4040217955702693e-06, "epoch": 14.128141483090289, "percentage": 70.64, "elapsed_time": "1:24:29", "remaining_time": "0:35:07", "throughput": 5473.73, "total_tokens": 27751088} {"current_steps": 45540, "total_steps": 64460, "loss": 0.2239, "lr": 2.40286485141222e-06, "epoch": 14.129692832764505, "percentage": 70.65, "elapsed_time": "1:24:30", "remaining_time": "0:35:06", "throughput": 5473.75, "total_tokens": 27753808} {"current_steps": 45545, "total_steps": 64460, "loss": 0.1858, "lr": 2.4017080976549295e-06, "epoch": 14.131244182438722, "percentage": 70.66, "elapsed_time": "1:24:30", "remaining_time": "0:35:05", "throughput": 5473.76, "total_tokens": 27757168} {"current_steps": 45550, "total_steps": 64460, "loss": 0.1623, "lr": 2.4005515343832063e-06, "epoch": 14.132795532112938, "percentage": 70.66, "elapsed_time": "1:24:31", "remaining_time": "0:35:05", "throughput": 5473.74, "total_tokens": 27759952} {"current_steps": 45555, "total_steps": 64460, "loss": 0.2002, "lr": 2.3993951616818357e-06, "epoch": 14.134346881787154, "percentage": 70.67, "elapsed_time": "1:24:31", "remaining_time": "0:35:04", "throughput": 5473.67, "total_tokens": 27762384} {"current_steps": 45560, "total_steps": 64460, "loss": 0.169, "lr": 2.3982389796355972e-06, "epoch": 14.135898231461372, "percentage": 70.68, "elapsed_time": "1:24:32", "remaining_time": "0:35:04", "throughput": 5473.66, "total_tokens": 27765008} {"current_steps": 45565, "total_steps": 64460, "loss": 0.1824, "lr": 2.397082988329249e-06, "epoch": 14.137449581135588, "percentage": 70.69, "elapsed_time": "1:24:33", "remaining_time": "0:35:03", "throughput": 5473.8, "total_tokens": 27769584} {"current_steps": 45570, "total_steps": 64460, "loss": 0.1668, "lr": 2.3959271878475427e-06, "epoch": 14.139000930809804, "percentage": 70.7, "elapsed_time": "1:24:33", "remaining_time": "0:35:03", "throughput": 5473.8, "total_tokens": 27772560} {"current_steps": 45575, "total_steps": 64460, "loss": 0.2009, "lr": 2.394771578275209e-06, "epoch": 14.140552280484021, "percentage": 70.7, "elapsed_time": "1:24:34", "remaining_time": "0:35:02", "throughput": 5473.69, "total_tokens": 27774928} {"current_steps": 45580, "total_steps": 64460, "loss": 0.256, "lr": 2.393616159696969e-06, "epoch": 14.142103630158237, "percentage": 70.71, "elapsed_time": "1:24:34", "remaining_time": "0:35:02", "throughput": 5473.64, "total_tokens": 27777328} {"current_steps": 45585, "total_steps": 64460, "loss": 0.1617, "lr": 2.39246093219753e-06, "epoch": 14.143654979832455, "percentage": 70.72, "elapsed_time": "1:24:35", "remaining_time": "0:35:01", "throughput": 5473.78, "total_tokens": 27781168} {"current_steps": 45590, "total_steps": 64460, "loss": 0.2385, "lr": 2.391305895861581e-06, "epoch": 14.14520632950667, "percentage": 70.73, "elapsed_time": "1:24:35", "remaining_time": "0:35:00", "throughput": 5473.8, "total_tokens": 27784432} {"current_steps": 45595, "total_steps": 64460, "loss": 0.1474, "lr": 2.3901510507738037e-06, "epoch": 14.146757679180887, "percentage": 70.73, "elapsed_time": "1:24:36", "remaining_time": "0:35:00", "throughput": 5473.76, "total_tokens": 27786928} {"current_steps": 45600, "total_steps": 64460, "loss": 0.1904, "lr": 2.3889963970188574e-06, "epoch": 14.148309028855104, "percentage": 70.74, "elapsed_time": "1:24:36", "remaining_time": "0:34:59", "throughput": 5473.77, "total_tokens": 27790032} {"current_steps": 45605, "total_steps": 64460, "loss": 0.2024, "lr": 2.3878419346813958e-06, "epoch": 14.14986037852932, "percentage": 70.75, "elapsed_time": "1:24:37", "remaining_time": "0:34:59", "throughput": 5473.71, "total_tokens": 27792432} {"current_steps": 45610, "total_steps": 64460, "loss": 0.2468, "lr": 2.386687663846051e-06, "epoch": 14.151411728203538, "percentage": 70.76, "elapsed_time": "1:24:37", "remaining_time": "0:34:58", "throughput": 5473.67, "total_tokens": 27795024} {"current_steps": 45615, "total_steps": 64460, "loss": 0.1935, "lr": 2.3855335845974493e-06, "epoch": 14.152963077877754, "percentage": 70.76, "elapsed_time": "1:24:38", "remaining_time": "0:34:58", "throughput": 5473.66, "total_tokens": 27797648} {"current_steps": 45620, "total_steps": 64460, "loss": 0.2108, "lr": 2.384379697020193e-06, "epoch": 14.15451442755197, "percentage": 70.77, "elapsed_time": "1:24:38", "remaining_time": "0:34:57", "throughput": 5473.64, "total_tokens": 27800080} {"current_steps": 45625, "total_steps": 64460, "loss": 0.1762, "lr": 2.3832260011988813e-06, "epoch": 14.156065777226187, "percentage": 70.78, "elapsed_time": "1:24:39", "remaining_time": "0:34:56", "throughput": 5473.6, "total_tokens": 27802608} {"current_steps": 45630, "total_steps": 64460, "loss": 0.2747, "lr": 2.3820724972180882e-06, "epoch": 14.157617126900403, "percentage": 70.79, "elapsed_time": "1:24:39", "remaining_time": "0:34:56", "throughput": 5473.59, "total_tokens": 27805264} {"current_steps": 45635, "total_steps": 64460, "loss": 0.2109, "lr": 2.3809191851623842e-06, "epoch": 14.159168476574619, "percentage": 70.8, "elapsed_time": "1:24:40", "remaining_time": "0:34:55", "throughput": 5473.63, "total_tokens": 27808272} {"current_steps": 45640, "total_steps": 64460, "loss": 0.1518, "lr": 2.3797660651163164e-06, "epoch": 14.160719826248837, "percentage": 70.8, "elapsed_time": "1:24:40", "remaining_time": "0:34:55", "throughput": 5473.62, "total_tokens": 27811344} {"current_steps": 45645, "total_steps": 64460, "loss": 0.1807, "lr": 2.3786131371644244e-06, "epoch": 14.162271175923053, "percentage": 70.81, "elapsed_time": "1:24:41", "remaining_time": "0:34:54", "throughput": 5473.62, "total_tokens": 27814288} {"current_steps": 45650, "total_steps": 64460, "loss": 0.1734, "lr": 2.3774604013912334e-06, "epoch": 14.16382252559727, "percentage": 70.82, "elapsed_time": "1:24:42", "remaining_time": "0:34:54", "throughput": 5473.64, "total_tokens": 27817296} {"current_steps": 45655, "total_steps": 64460, "loss": 0.2845, "lr": 2.376307857881248e-06, "epoch": 14.165373875271486, "percentage": 70.83, "elapsed_time": "1:24:42", "remaining_time": "0:34:53", "throughput": 5473.69, "total_tokens": 27820240} {"current_steps": 45660, "total_steps": 64460, "loss": 0.2018, "lr": 2.3751555067189687e-06, "epoch": 14.166925224945702, "percentage": 70.83, "elapsed_time": "1:24:43", "remaining_time": "0:34:52", "throughput": 5473.67, "total_tokens": 27823024} {"current_steps": 45665, "total_steps": 64460, "loss": 0.1982, "lr": 2.3740033479888708e-06, "epoch": 14.16847657461992, "percentage": 70.84, "elapsed_time": "1:24:43", "remaining_time": "0:34:52", "throughput": 5473.71, "total_tokens": 27825808} {"current_steps": 45670, "total_steps": 64460, "loss": 0.2458, "lr": 2.3728513817754264e-06, "epoch": 14.170027924294136, "percentage": 70.85, "elapsed_time": "1:24:44", "remaining_time": "0:34:51", "throughput": 5473.63, "total_tokens": 27828080} {"current_steps": 45675, "total_steps": 64460, "loss": 0.2001, "lr": 2.3716996081630834e-06, "epoch": 14.171579273968353, "percentage": 70.86, "elapsed_time": "1:24:44", "remaining_time": "0:34:51", "throughput": 5473.64, "total_tokens": 27830704} {"current_steps": 45680, "total_steps": 64460, "loss": 0.1963, "lr": 2.3705480272362848e-06, "epoch": 14.17313062364257, "percentage": 70.87, "elapsed_time": "1:24:44", "remaining_time": "0:34:50", "throughput": 5473.64, "total_tokens": 27833264} {"current_steps": 45685, "total_steps": 64460, "loss": 0.2392, "lr": 2.3693966390794516e-06, "epoch": 14.174681973316785, "percentage": 70.87, "elapsed_time": "1:24:45", "remaining_time": "0:34:49", "throughput": 5473.54, "total_tokens": 27835600} {"current_steps": 45690, "total_steps": 64460, "loss": 0.1729, "lr": 2.3682454437769975e-06, "epoch": 14.176233322991003, "percentage": 70.88, "elapsed_time": "1:24:45", "remaining_time": "0:34:49", "throughput": 5473.61, "total_tokens": 27838736} {"current_steps": 45695, "total_steps": 64460, "loss": 0.1602, "lr": 2.367094441413315e-06, "epoch": 14.177784672665219, "percentage": 70.89, "elapsed_time": "1:24:46", "remaining_time": "0:34:48", "throughput": 5473.63, "total_tokens": 27841520} {"current_steps": 45700, "total_steps": 64460, "loss": 0.2134, "lr": 2.3659436320727885e-06, "epoch": 14.179336022339434, "percentage": 70.9, "elapsed_time": "1:24:47", "remaining_time": "0:34:48", "throughput": 5473.74, "total_tokens": 27845424} {"current_steps": 45705, "total_steps": 64460, "loss": 0.2035, "lr": 2.364793015839787e-06, "epoch": 14.180887372013652, "percentage": 70.9, "elapsed_time": "1:24:47", "remaining_time": "0:34:47", "throughput": 5473.85, "total_tokens": 27849296} {"current_steps": 45710, "total_steps": 64460, "loss": 0.1561, "lr": 2.363642592798662e-06, "epoch": 14.182438721687868, "percentage": 70.91, "elapsed_time": "1:24:48", "remaining_time": "0:34:47", "throughput": 5473.9, "total_tokens": 27852336} {"current_steps": 45715, "total_steps": 64460, "loss": 0.1211, "lr": 2.362492363033755e-06, "epoch": 14.183990071362086, "percentage": 70.92, "elapsed_time": "1:24:48", "remaining_time": "0:34:46", "throughput": 5474.07, "total_tokens": 27857328} {"current_steps": 45720, "total_steps": 64460, "loss": 0.2506, "lr": 2.361342326629389e-06, "epoch": 14.185541421036302, "percentage": 70.93, "elapsed_time": "1:24:49", "remaining_time": "0:34:46", "throughput": 5473.98, "total_tokens": 27859568} {"current_steps": 45725, "total_steps": 64460, "loss": 0.2321, "lr": 2.360192483669879e-06, "epoch": 14.187092770710517, "percentage": 70.94, "elapsed_time": "1:24:49", "remaining_time": "0:34:45", "throughput": 5473.94, "total_tokens": 27862352} {"current_steps": 45730, "total_steps": 64460, "loss": 0.171, "lr": 2.3590428342395176e-06, "epoch": 14.188644120384735, "percentage": 70.94, "elapsed_time": "1:24:50", "remaining_time": "0:34:44", "throughput": 5473.94, "total_tokens": 27865136} {"current_steps": 45735, "total_steps": 64460, "loss": 0.1879, "lr": 2.3578933784225926e-06, "epoch": 14.190195470058951, "percentage": 70.95, "elapsed_time": "1:24:51", "remaining_time": "0:34:44", "throughput": 5473.96, "total_tokens": 27868112} {"current_steps": 45740, "total_steps": 64460, "loss": 0.2796, "lr": 2.3567441163033676e-06, "epoch": 14.191746819733169, "percentage": 70.96, "elapsed_time": "1:24:51", "remaining_time": "0:34:43", "throughput": 5473.93, "total_tokens": 27870832} {"current_steps": 45745, "total_steps": 64460, "loss": 0.2094, "lr": 2.3555950479661024e-06, "epoch": 14.193298169407385, "percentage": 70.97, "elapsed_time": "1:24:52", "remaining_time": "0:34:43", "throughput": 5473.95, "total_tokens": 27873584} {"current_steps": 45750, "total_steps": 64460, "loss": 0.2084, "lr": 2.354446173495032e-06, "epoch": 14.1948495190816, "percentage": 70.97, "elapsed_time": "1:24:52", "remaining_time": "0:34:42", "throughput": 5474.13, "total_tokens": 27878672} {"current_steps": 45755, "total_steps": 64460, "loss": 0.2034, "lr": 2.3532974929743875e-06, "epoch": 14.196400868755818, "percentage": 70.98, "elapsed_time": "1:24:53", "remaining_time": "0:34:42", "throughput": 5474.16, "total_tokens": 27882192} {"current_steps": 45760, "total_steps": 64460, "loss": 0.1297, "lr": 2.3521490064883763e-06, "epoch": 14.197952218430034, "percentage": 70.99, "elapsed_time": "1:24:53", "remaining_time": "0:34:41", "throughput": 5474.22, "total_tokens": 27885328} {"current_steps": 45765, "total_steps": 64460, "loss": 0.1921, "lr": 2.3510007141211976e-06, "epoch": 14.19950356810425, "percentage": 71.0, "elapsed_time": "1:24:54", "remaining_time": "0:34:41", "throughput": 5474.25, "total_tokens": 27888464} {"current_steps": 45770, "total_steps": 64460, "loss": 0.2383, "lr": 2.349852615957038e-06, "epoch": 14.201054917778468, "percentage": 71.01, "elapsed_time": "1:24:54", "remaining_time": "0:34:40", "throughput": 5474.24, "total_tokens": 27891088} {"current_steps": 45775, "total_steps": 64460, "loss": 0.15, "lr": 2.348704712080062e-06, "epoch": 14.202606267452683, "percentage": 71.01, "elapsed_time": "1:24:55", "remaining_time": "0:34:39", "throughput": 5474.25, "total_tokens": 27893808} {"current_steps": 45780, "total_steps": 64460, "loss": 0.1385, "lr": 2.347557002574429e-06, "epoch": 14.204157617126901, "percentage": 71.02, "elapsed_time": "1:24:55", "remaining_time": "0:34:39", "throughput": 5474.19, "total_tokens": 27896080} {"current_steps": 45785, "total_steps": 64460, "loss": 0.2161, "lr": 2.3464094875242747e-06, "epoch": 14.205708966801117, "percentage": 71.03, "elapsed_time": "1:24:56", "remaining_time": "0:34:38", "throughput": 5474.38, "total_tokens": 27901168} {"current_steps": 45790, "total_steps": 64460, "loss": 0.1934, "lr": 2.3452621670137303e-06, "epoch": 14.207260316475333, "percentage": 71.04, "elapsed_time": "1:24:57", "remaining_time": "0:34:38", "throughput": 5474.3, "total_tokens": 27903504} {"current_steps": 45795, "total_steps": 64460, "loss": 0.2186, "lr": 2.344115041126904e-06, "epoch": 14.20881166614955, "percentage": 71.04, "elapsed_time": "1:24:57", "remaining_time": "0:34:37", "throughput": 5474.28, "total_tokens": 27906160} {"current_steps": 45800, "total_steps": 64460, "loss": 0.1748, "lr": 2.3429681099478977e-06, "epoch": 14.210363015823766, "percentage": 71.05, "elapsed_time": "1:24:58", "remaining_time": "0:34:37", "throughput": 5474.18, "total_tokens": 27908272} {"current_steps": 45805, "total_steps": 64460, "loss": 0.1727, "lr": 2.341821373560791e-06, "epoch": 14.211914365497984, "percentage": 71.06, "elapsed_time": "1:24:58", "remaining_time": "0:34:36", "throughput": 5474.2, "total_tokens": 27911440} {"current_steps": 45810, "total_steps": 64460, "loss": 0.1948, "lr": 2.340674832049657e-06, "epoch": 14.2134657151722, "percentage": 71.07, "elapsed_time": "1:24:59", "remaining_time": "0:34:36", "throughput": 5474.28, "total_tokens": 27915056} {"current_steps": 45815, "total_steps": 64460, "loss": 0.2365, "lr": 2.3395284854985468e-06, "epoch": 14.215017064846416, "percentage": 71.08, "elapsed_time": "1:24:59", "remaining_time": "0:34:35", "throughput": 5474.32, "total_tokens": 27918224} {"current_steps": 45820, "total_steps": 64460, "loss": 0.1997, "lr": 2.3383823339915034e-06, "epoch": 14.216568414520633, "percentage": 71.08, "elapsed_time": "1:25:00", "remaining_time": "0:34:34", "throughput": 5474.32, "total_tokens": 27920944} {"current_steps": 45825, "total_steps": 64460, "loss": 0.2241, "lr": 2.337236377612555e-06, "epoch": 14.21811976419485, "percentage": 71.09, "elapsed_time": "1:25:01", "remaining_time": "0:34:34", "throughput": 5474.51, "total_tokens": 27926224} {"current_steps": 45830, "total_steps": 64460, "loss": 0.1748, "lr": 2.3360906164457102e-06, "epoch": 14.219671113869065, "percentage": 71.1, "elapsed_time": "1:25:01", "remaining_time": "0:34:33", "throughput": 5474.53, "total_tokens": 27929008} {"current_steps": 45835, "total_steps": 64460, "loss": 0.1668, "lr": 2.3349450505749706e-06, "epoch": 14.221222463543283, "percentage": 71.11, "elapsed_time": "1:25:02", "remaining_time": "0:34:33", "throughput": 5474.74, "total_tokens": 27934032} {"current_steps": 45840, "total_steps": 64460, "loss": 0.1871, "lr": 2.3337996800843155e-06, "epoch": 14.222773813217499, "percentage": 71.11, "elapsed_time": "1:25:02", "remaining_time": "0:34:32", "throughput": 5474.77, "total_tokens": 27936976} {"current_steps": 45845, "total_steps": 64460, "loss": 0.2138, "lr": 2.3326545050577187e-06, "epoch": 14.224325162891716, "percentage": 71.12, "elapsed_time": "1:25:03", "remaining_time": "0:34:32", "throughput": 5474.73, "total_tokens": 27939728} {"current_steps": 45850, "total_steps": 64460, "loss": 0.2072, "lr": 2.331509525579131e-06, "epoch": 14.225876512565932, "percentage": 71.13, "elapsed_time": "1:25:03", "remaining_time": "0:34:31", "throughput": 5474.64, "total_tokens": 27941776} {"current_steps": 45855, "total_steps": 64460, "loss": 0.1568, "lr": 2.330364741732496e-06, "epoch": 14.227427862240148, "percentage": 71.14, "elapsed_time": "1:25:04", "remaining_time": "0:34:31", "throughput": 5474.68, "total_tokens": 27944720} {"current_steps": 45860, "total_steps": 64460, "loss": 0.236, "lr": 2.329220153601737e-06, "epoch": 14.228979211914366, "percentage": 71.14, "elapsed_time": "1:25:04", "remaining_time": "0:34:30", "throughput": 5474.62, "total_tokens": 27947312} {"current_steps": 45865, "total_steps": 64460, "loss": 0.134, "lr": 2.3280757612707696e-06, "epoch": 14.230530561588582, "percentage": 71.15, "elapsed_time": "1:25:05", "remaining_time": "0:34:29", "throughput": 5474.75, "total_tokens": 27950992} {"current_steps": 45870, "total_steps": 64460, "loss": 0.2081, "lr": 2.3269315648234874e-06, "epoch": 14.2320819112628, "percentage": 71.16, "elapsed_time": "1:25:05", "remaining_time": "0:34:29", "throughput": 5474.76, "total_tokens": 27953840} {"current_steps": 45875, "total_steps": 64460, "loss": 0.2241, "lr": 2.3257875643437772e-06, "epoch": 14.233633260937015, "percentage": 71.17, "elapsed_time": "1:25:06", "remaining_time": "0:34:28", "throughput": 5474.85, "total_tokens": 27957360} {"current_steps": 45880, "total_steps": 64460, "loss": 0.1744, "lr": 2.3246437599155035e-06, "epoch": 14.235184610611231, "percentage": 71.18, "elapsed_time": "1:25:07", "remaining_time": "0:34:28", "throughput": 5474.88, "total_tokens": 27960336} {"current_steps": 45885, "total_steps": 64460, "loss": 0.2, "lr": 2.3235001516225236e-06, "epoch": 14.236735960285449, "percentage": 71.18, "elapsed_time": "1:25:07", "remaining_time": "0:34:27", "throughput": 5474.99, "total_tokens": 27964240} {"current_steps": 45890, "total_steps": 64460, "loss": 0.2098, "lr": 2.322356739548679e-06, "epoch": 14.238287309959665, "percentage": 71.19, "elapsed_time": "1:25:08", "remaining_time": "0:34:27", "throughput": 5474.99, "total_tokens": 27966896} {"current_steps": 45895, "total_steps": 64460, "loss": 0.1789, "lr": 2.3212135237777917e-06, "epoch": 14.23983865963388, "percentage": 71.2, "elapsed_time": "1:25:08", "remaining_time": "0:34:26", "throughput": 5474.87, "total_tokens": 27969296} {"current_steps": 45900, "total_steps": 64460, "loss": 0.2042, "lr": 2.320070504393676e-06, "epoch": 14.241390009308098, "percentage": 71.21, "elapsed_time": "1:25:09", "remaining_time": "0:34:25", "throughput": 5475.04, "total_tokens": 27973648} {"current_steps": 45905, "total_steps": 64460, "loss": 0.2212, "lr": 2.3189276814801265e-06, "epoch": 14.242941358982314, "percentage": 71.21, "elapsed_time": "1:25:09", "remaining_time": "0:34:25", "throughput": 5475.04, "total_tokens": 27976336} {"current_steps": 45910, "total_steps": 64460, "loss": 0.1651, "lr": 2.3177850551209273e-06, "epoch": 14.244492708656532, "percentage": 71.22, "elapsed_time": "1:25:10", "remaining_time": "0:34:24", "throughput": 5474.94, "total_tokens": 27978704} {"current_steps": 45915, "total_steps": 64460, "loss": 0.1869, "lr": 2.316642625399843e-06, "epoch": 14.246044058330748, "percentage": 71.23, "elapsed_time": "1:25:10", "remaining_time": "0:34:24", "throughput": 5474.87, "total_tokens": 27981040} {"current_steps": 45920, "total_steps": 64460, "loss": 0.1592, "lr": 2.315500392400633e-06, "epoch": 14.247595408004964, "percentage": 71.24, "elapsed_time": "1:25:11", "remaining_time": "0:34:23", "throughput": 5474.89, "total_tokens": 27983760} {"current_steps": 45925, "total_steps": 64460, "loss": 0.1846, "lr": 2.314358356207032e-06, "epoch": 14.249146757679181, "percentage": 71.25, "elapsed_time": "1:25:11", "remaining_time": "0:34:23", "throughput": 5474.92, "total_tokens": 27986800} {"current_steps": 45930, "total_steps": 64460, "loss": 0.1602, "lr": 2.313216516902768e-06, "epoch": 14.250698107353397, "percentage": 71.25, "elapsed_time": "1:25:12", "remaining_time": "0:34:22", "throughput": 5474.88, "total_tokens": 27989232} {"current_steps": 45935, "total_steps": 64460, "loss": 0.203, "lr": 2.3120748745715477e-06, "epoch": 14.252249457027615, "percentage": 71.26, "elapsed_time": "1:25:12", "remaining_time": "0:34:21", "throughput": 5474.9, "total_tokens": 27992144} {"current_steps": 45940, "total_steps": 64460, "loss": 0.1826, "lr": 2.3109334292970708e-06, "epoch": 14.25380080670183, "percentage": 71.27, "elapsed_time": "1:25:13", "remaining_time": "0:34:21", "throughput": 5475.0, "total_tokens": 27995792} {"current_steps": 45945, "total_steps": 64460, "loss": 0.2523, "lr": 2.309792181163015e-06, "epoch": 14.255352156376047, "percentage": 71.28, "elapsed_time": "1:25:13", "remaining_time": "0:34:20", "throughput": 5474.94, "total_tokens": 27998128} {"current_steps": 45950, "total_steps": 64460, "loss": 0.1882, "lr": 2.308651130253051e-06, "epoch": 14.256903506050264, "percentage": 71.28, "elapsed_time": "1:25:14", "remaining_time": "0:34:20", "throughput": 5475.04, "total_tokens": 28002064} {"current_steps": 45955, "total_steps": 64460, "loss": 0.1608, "lr": 2.307510276650828e-06, "epoch": 14.25845485572448, "percentage": 71.29, "elapsed_time": "1:25:15", "remaining_time": "0:34:19", "throughput": 5475.03, "total_tokens": 28004784} {"current_steps": 45960, "total_steps": 64460, "loss": 0.2194, "lr": 2.3063696204399866e-06, "epoch": 14.260006205398696, "percentage": 71.3, "elapsed_time": "1:25:15", "remaining_time": "0:34:19", "throughput": 5475.02, "total_tokens": 28007472} {"current_steps": 45965, "total_steps": 64460, "loss": 0.1791, "lr": 2.3052291617041484e-06, "epoch": 14.261557555072914, "percentage": 71.31, "elapsed_time": "1:25:16", "remaining_time": "0:34:18", "throughput": 5475.05, "total_tokens": 28010736} {"current_steps": 45970, "total_steps": 64460, "loss": 0.1834, "lr": 2.3040889005269227e-06, "epoch": 14.26310890474713, "percentage": 71.32, "elapsed_time": "1:25:16", "remaining_time": "0:34:18", "throughput": 5475.11, "total_tokens": 28014128} {"current_steps": 45975, "total_steps": 64460, "loss": 0.1626, "lr": 2.3029488369919075e-06, "epoch": 14.264660254421347, "percentage": 71.32, "elapsed_time": "1:25:17", "remaining_time": "0:34:17", "throughput": 5475.08, "total_tokens": 28016784} {"current_steps": 45980, "total_steps": 64460, "loss": 0.223, "lr": 2.301808971182678e-06, "epoch": 14.266211604095563, "percentage": 71.33, "elapsed_time": "1:25:17", "remaining_time": "0:34:16", "throughput": 5475.09, "total_tokens": 28019536} {"current_steps": 45985, "total_steps": 64460, "loss": 0.1788, "lr": 2.300669303182804e-06, "epoch": 14.267762953769779, "percentage": 71.34, "elapsed_time": "1:25:18", "remaining_time": "0:34:16", "throughput": 5475.18, "total_tokens": 28023024} {"current_steps": 45990, "total_steps": 64460, "loss": 0.179, "lr": 2.2995298330758335e-06, "epoch": 14.269314303443997, "percentage": 71.35, "elapsed_time": "1:25:18", "remaining_time": "0:34:15", "throughput": 5475.13, "total_tokens": 28025584} {"current_steps": 45995, "total_steps": 64460, "loss": 0.1604, "lr": 2.2983905609453065e-06, "epoch": 14.270865653118213, "percentage": 71.35, "elapsed_time": "1:25:19", "remaining_time": "0:34:15", "throughput": 5475.19, "total_tokens": 28028464} {"current_steps": 46000, "total_steps": 64460, "loss": 0.229, "lr": 2.2972514868747415e-06, "epoch": 14.27241700279243, "percentage": 71.36, "elapsed_time": "1:25:19", "remaining_time": "0:34:14", "throughput": 5475.03, "total_tokens": 28030448} {"current_steps": 46005, "total_steps": 64460, "loss": 0.1901, "lr": 2.2961126109476496e-06, "epoch": 14.273968352466646, "percentage": 71.37, "elapsed_time": "1:25:20", "remaining_time": "0:34:13", "throughput": 5475.0, "total_tokens": 28032848} {"current_steps": 46010, "total_steps": 64460, "loss": 0.1674, "lr": 2.2949739332475202e-06, "epoch": 14.275519702140862, "percentage": 71.38, "elapsed_time": "1:25:20", "remaining_time": "0:34:13", "throughput": 5475.0, "total_tokens": 28035632} {"current_steps": 46015, "total_steps": 64460, "loss": 0.2315, "lr": 2.2938354538578357e-06, "epoch": 14.27707105181508, "percentage": 71.39, "elapsed_time": "1:25:21", "remaining_time": "0:34:12", "throughput": 5475.0, "total_tokens": 28038160} {"current_steps": 46020, "total_steps": 64460, "loss": 0.1373, "lr": 2.2926971728620555e-06, "epoch": 14.278622401489296, "percentage": 71.39, "elapsed_time": "1:25:21", "remaining_time": "0:34:12", "throughput": 5475.14, "total_tokens": 28042256} {"current_steps": 46025, "total_steps": 64460, "loss": 0.1803, "lr": 2.2915590903436347e-06, "epoch": 14.280173751163511, "percentage": 71.4, "elapsed_time": "1:25:22", "remaining_time": "0:34:11", "throughput": 5475.17, "total_tokens": 28045232} {"current_steps": 46030, "total_steps": 64460, "loss": 0.2508, "lr": 2.2904212063860033e-06, "epoch": 14.281725100837729, "percentage": 71.41, "elapsed_time": "1:25:22", "remaining_time": "0:34:11", "throughput": 5475.08, "total_tokens": 28047408} {"current_steps": 46035, "total_steps": 64460, "loss": 0.1576, "lr": 2.289283521072583e-06, "epoch": 14.283276450511945, "percentage": 71.42, "elapsed_time": "1:25:23", "remaining_time": "0:34:10", "throughput": 5475.15, "total_tokens": 28050672} {"current_steps": 46040, "total_steps": 64460, "loss": 0.1794, "lr": 2.2881460344867827e-06, "epoch": 14.284827800186163, "percentage": 71.42, "elapsed_time": "1:25:23", "remaining_time": "0:34:09", "throughput": 5475.16, "total_tokens": 28053520} {"current_steps": 46045, "total_steps": 64460, "loss": 0.1732, "lr": 2.2870087467119893e-06, "epoch": 14.286379149860378, "percentage": 71.43, "elapsed_time": "1:25:24", "remaining_time": "0:34:09", "throughput": 5475.17, "total_tokens": 28056112} {"current_steps": 46050, "total_steps": 64460, "loss": 0.2241, "lr": 2.285871657831584e-06, "epoch": 14.287930499534594, "percentage": 71.44, "elapsed_time": "1:25:24", "remaining_time": "0:34:08", "throughput": 5475.14, "total_tokens": 28058512} {"current_steps": 46055, "total_steps": 64460, "loss": 0.1564, "lr": 2.284734767928923e-06, "epoch": 14.289481849208812, "percentage": 71.45, "elapsed_time": "1:25:25", "remaining_time": "0:34:08", "throughput": 5475.14, "total_tokens": 28061360} {"current_steps": 46060, "total_steps": 64460, "loss": 0.1668, "lr": 2.28359807708736e-06, "epoch": 14.291033198883028, "percentage": 71.46, "elapsed_time": "1:25:25", "remaining_time": "0:34:07", "throughput": 5475.06, "total_tokens": 28063696} {"current_steps": 46065, "total_steps": 64460, "loss": 0.1509, "lr": 2.2824615853902226e-06, "epoch": 14.292584548557246, "percentage": 71.46, "elapsed_time": "1:25:26", "remaining_time": "0:34:07", "throughput": 5475.05, "total_tokens": 28066256} {"current_steps": 46070, "total_steps": 64460, "loss": 0.27, "lr": 2.2813252929208336e-06, "epoch": 14.294135898231461, "percentage": 71.47, "elapsed_time": "1:25:26", "remaining_time": "0:34:06", "throughput": 5475.2, "total_tokens": 28070224} {"current_steps": 46075, "total_steps": 64460, "loss": 0.2128, "lr": 2.2801891997624924e-06, "epoch": 14.295687247905677, "percentage": 71.48, "elapsed_time": "1:25:27", "remaining_time": "0:34:05", "throughput": 5475.32, "total_tokens": 28074416} {"current_steps": 46080, "total_steps": 64460, "loss": 0.1677, "lr": 2.2790533059984924e-06, "epoch": 14.297238597579895, "percentage": 71.49, "elapsed_time": "1:25:28", "remaining_time": "0:34:05", "throughput": 5475.44, "total_tokens": 28078416} {"current_steps": 46085, "total_steps": 64460, "loss": 0.2144, "lr": 2.277917611712104e-06, "epoch": 14.298789947254111, "percentage": 71.49, "elapsed_time": "1:25:28", "remaining_time": "0:34:04", "throughput": 5475.47, "total_tokens": 28081264} {"current_steps": 46090, "total_steps": 64460, "loss": 0.1965, "lr": 2.2767821169865887e-06, "epoch": 14.300341296928327, "percentage": 71.5, "elapsed_time": "1:25:29", "remaining_time": "0:34:04", "throughput": 5475.56, "total_tokens": 28084880} {"current_steps": 46095, "total_steps": 64460, "loss": 0.2182, "lr": 2.2756468219051942e-06, "epoch": 14.301892646602544, "percentage": 71.51, "elapsed_time": "1:25:29", "remaining_time": "0:34:03", "throughput": 5475.62, "total_tokens": 28087920} {"current_steps": 46100, "total_steps": 64460, "loss": 0.1929, "lr": 2.274511726551146e-06, "epoch": 14.30344399627676, "percentage": 71.52, "elapsed_time": "1:25:30", "remaining_time": "0:34:03", "throughput": 5475.59, "total_tokens": 28090544} {"current_steps": 46105, "total_steps": 64460, "loss": 0.2362, "lr": 2.273376831007666e-06, "epoch": 14.304995345950978, "percentage": 71.52, "elapsed_time": "1:25:30", "remaining_time": "0:34:02", "throughput": 5475.63, "total_tokens": 28093552} {"current_steps": 46110, "total_steps": 64460, "loss": 0.2163, "lr": 2.27224213535795e-06, "epoch": 14.306546695625194, "percentage": 71.53, "elapsed_time": "1:25:31", "remaining_time": "0:34:02", "throughput": 5475.69, "total_tokens": 28096688} {"current_steps": 46115, "total_steps": 64460, "loss": 0.1959, "lr": 2.2711076396851883e-06, "epoch": 14.30809804529941, "percentage": 71.54, "elapsed_time": "1:25:31", "remaining_time": "0:34:01", "throughput": 5475.68, "total_tokens": 28099248} {"current_steps": 46120, "total_steps": 64460, "loss": 0.1889, "lr": 2.2699733440725502e-06, "epoch": 14.309649394973627, "percentage": 71.55, "elapsed_time": "1:25:32", "remaining_time": "0:34:00", "throughput": 5475.83, "total_tokens": 28104080} {"current_steps": 46125, "total_steps": 64460, "loss": 0.2847, "lr": 2.268839248603196e-06, "epoch": 14.311200744647843, "percentage": 71.56, "elapsed_time": "1:25:32", "remaining_time": "0:34:00", "throughput": 5475.74, "total_tokens": 28106448} {"current_steps": 46130, "total_steps": 64460, "loss": 0.2468, "lr": 2.267705353360265e-06, "epoch": 14.312752094322061, "percentage": 71.56, "elapsed_time": "1:25:33", "remaining_time": "0:33:59", "throughput": 5475.75, "total_tokens": 28109232} {"current_steps": 46135, "total_steps": 64460, "loss": 0.2442, "lr": 2.266571658426888e-06, "epoch": 14.314303443996277, "percentage": 71.57, "elapsed_time": "1:25:33", "remaining_time": "0:33:59", "throughput": 5475.73, "total_tokens": 28111952} {"current_steps": 46140, "total_steps": 64460, "loss": 0.1505, "lr": 2.265438163886176e-06, "epoch": 14.315854793670493, "percentage": 71.58, "elapsed_time": "1:25:34", "remaining_time": "0:33:58", "throughput": 5475.75, "total_tokens": 28115152} {"current_steps": 46145, "total_steps": 64460, "loss": 0.2132, "lr": 2.2643048698212305e-06, "epoch": 14.31740614334471, "percentage": 71.59, "elapsed_time": "1:25:34", "remaining_time": "0:33:58", "throughput": 5475.75, "total_tokens": 28117840} {"current_steps": 46150, "total_steps": 64460, "loss": 0.1643, "lr": 2.2631717763151313e-06, "epoch": 14.318957493018926, "percentage": 71.59, "elapsed_time": "1:25:35", "remaining_time": "0:33:57", "throughput": 5475.84, "total_tokens": 28121232} {"current_steps": 46155, "total_steps": 64460, "loss": 0.1833, "lr": 2.26203888345095e-06, "epoch": 14.320508842693144, "percentage": 71.6, "elapsed_time": "1:25:36", "remaining_time": "0:33:56", "throughput": 5475.85, "total_tokens": 28124016} {"current_steps": 46160, "total_steps": 64460, "loss": 0.1758, "lr": 2.2609061913117424e-06, "epoch": 14.32206019236736, "percentage": 71.61, "elapsed_time": "1:25:36", "remaining_time": "0:33:56", "throughput": 5475.73, "total_tokens": 28125968} {"current_steps": 46165, "total_steps": 64460, "loss": 0.1956, "lr": 2.259773699980545e-06, "epoch": 14.323611542041576, "percentage": 71.62, "elapsed_time": "1:25:36", "remaining_time": "0:33:55", "throughput": 5475.63, "total_tokens": 28128208} {"current_steps": 46170, "total_steps": 64460, "loss": 0.2071, "lr": 2.2586414095403863e-06, "epoch": 14.325162891715793, "percentage": 71.63, "elapsed_time": "1:25:37", "remaining_time": "0:33:55", "throughput": 5475.64, "total_tokens": 28130864} {"current_steps": 46175, "total_steps": 64460, "loss": 0.171, "lr": 2.2575093200742733e-06, "epoch": 14.32671424139001, "percentage": 71.63, "elapsed_time": "1:25:37", "remaining_time": "0:33:54", "throughput": 5475.62, "total_tokens": 28133424} {"current_steps": 46180, "total_steps": 64460, "loss": 0.2293, "lr": 2.2563774316652047e-06, "epoch": 14.328265591064225, "percentage": 71.64, "elapsed_time": "1:25:38", "remaining_time": "0:33:54", "throughput": 5475.67, "total_tokens": 28136464} {"current_steps": 46185, "total_steps": 64460, "loss": 0.1815, "lr": 2.2552457443961577e-06, "epoch": 14.329816940738443, "percentage": 71.65, "elapsed_time": "1:25:38", "remaining_time": "0:33:53", "throughput": 5475.55, "total_tokens": 28138608} {"current_steps": 46190, "total_steps": 64460, "loss": 0.1993, "lr": 2.254114258350103e-06, "epoch": 14.331368290412659, "percentage": 71.66, "elapsed_time": "1:25:39", "remaining_time": "0:33:52", "throughput": 5475.52, "total_tokens": 28141328} {"current_steps": 46195, "total_steps": 64460, "loss": 0.1442, "lr": 2.2529829736099868e-06, "epoch": 14.332919640086876, "percentage": 71.66, "elapsed_time": "1:25:40", "remaining_time": "0:33:52", "throughput": 5475.4, "total_tokens": 28143600} {"current_steps": 46200, "total_steps": 64460, "loss": 0.1614, "lr": 2.25185189025875e-06, "epoch": 14.334470989761092, "percentage": 71.67, "elapsed_time": "1:25:40", "remaining_time": "0:33:51", "throughput": 5475.36, "total_tokens": 28146192} {"current_steps": 46205, "total_steps": 64460, "loss": 0.2398, "lr": 2.2507210083793105e-06, "epoch": 14.336022339435308, "percentage": 71.68, "elapsed_time": "1:25:40", "remaining_time": "0:33:51", "throughput": 5475.32, "total_tokens": 28148560} {"current_steps": 46210, "total_steps": 64460, "loss": 0.1432, "lr": 2.2495903280545782e-06, "epoch": 14.337573689109526, "percentage": 71.69, "elapsed_time": "1:25:41", "remaining_time": "0:33:50", "throughput": 5475.33, "total_tokens": 28151376} {"current_steps": 46215, "total_steps": 64460, "loss": 0.3112, "lr": 2.248459849367446e-06, "epoch": 14.339125038783742, "percentage": 71.7, "elapsed_time": "1:25:42", "remaining_time": "0:33:49", "throughput": 5475.32, "total_tokens": 28154096} {"current_steps": 46220, "total_steps": 64460, "loss": 0.2613, "lr": 2.2473295724007882e-06, "epoch": 14.340676388457958, "percentage": 71.7, "elapsed_time": "1:25:42", "remaining_time": "0:33:49", "throughput": 5475.43, "total_tokens": 28157936} {"current_steps": 46225, "total_steps": 64460, "loss": 0.1916, "lr": 2.2461994972374707e-06, "epoch": 14.342227738132175, "percentage": 71.71, "elapsed_time": "1:25:43", "remaining_time": "0:33:48", "throughput": 5475.34, "total_tokens": 28159984} {"current_steps": 46230, "total_steps": 64460, "loss": 0.2344, "lr": 2.2450696239603388e-06, "epoch": 14.343779087806391, "percentage": 71.72, "elapsed_time": "1:25:43", "remaining_time": "0:33:48", "throughput": 5475.43, "total_tokens": 28163280} {"current_steps": 46235, "total_steps": 64460, "loss": 0.2314, "lr": 2.2439399526522284e-06, "epoch": 14.345330437480609, "percentage": 71.73, "elapsed_time": "1:25:44", "remaining_time": "0:33:47", "throughput": 5475.51, "total_tokens": 28166608} {"current_steps": 46240, "total_steps": 64460, "loss": 0.2578, "lr": 2.2428104833959536e-06, "epoch": 14.346881787154825, "percentage": 71.73, "elapsed_time": "1:25:44", "remaining_time": "0:33:47", "throughput": 5475.52, "total_tokens": 28169456} {"current_steps": 46245, "total_steps": 64460, "loss": 0.1717, "lr": 2.2416812162743223e-06, "epoch": 14.34843313682904, "percentage": 71.74, "elapsed_time": "1:25:45", "remaining_time": "0:33:46", "throughput": 5475.57, "total_tokens": 28172528} {"current_steps": 46250, "total_steps": 64460, "loss": 0.2174, "lr": 2.24055215137012e-06, "epoch": 14.349984486503258, "percentage": 71.75, "elapsed_time": "1:25:45", "remaining_time": "0:33:45", "throughput": 5475.52, "total_tokens": 28175120} {"current_steps": 46255, "total_steps": 64460, "loss": 0.1992, "lr": 2.2394232887661234e-06, "epoch": 14.351535836177474, "percentage": 71.76, "elapsed_time": "1:25:46", "remaining_time": "0:33:45", "throughput": 5475.58, "total_tokens": 28178576} {"current_steps": 46260, "total_steps": 64460, "loss": 0.1888, "lr": 2.238294628545088e-06, "epoch": 14.353087185851692, "percentage": 71.77, "elapsed_time": "1:25:46", "remaining_time": "0:33:44", "throughput": 5475.65, "total_tokens": 28181744} {"current_steps": 46265, "total_steps": 64460, "loss": 0.2249, "lr": 2.2371661707897615e-06, "epoch": 14.354638535525908, "percentage": 71.77, "elapsed_time": "1:25:47", "remaining_time": "0:33:44", "throughput": 5475.59, "total_tokens": 28184048} {"current_steps": 46270, "total_steps": 64460, "loss": 0.2709, "lr": 2.23603791558287e-06, "epoch": 14.356189885200124, "percentage": 71.78, "elapsed_time": "1:25:47", "remaining_time": "0:33:43", "throughput": 5475.6, "total_tokens": 28186832} {"current_steps": 46275, "total_steps": 64460, "loss": 0.1779, "lr": 2.2349098630071293e-06, "epoch": 14.357741234874341, "percentage": 71.79, "elapsed_time": "1:25:48", "remaining_time": "0:33:43", "throughput": 5475.57, "total_tokens": 28189200} {"current_steps": 46280, "total_steps": 64460, "loss": 0.1436, "lr": 2.2337820131452407e-06, "epoch": 14.359292584548557, "percentage": 71.8, "elapsed_time": "1:25:48", "remaining_time": "0:33:42", "throughput": 5475.57, "total_tokens": 28191984} {"current_steps": 46285, "total_steps": 64460, "loss": 0.2161, "lr": 2.232654366079886e-06, "epoch": 14.360843934222775, "percentage": 71.8, "elapsed_time": "1:25:49", "remaining_time": "0:33:41", "throughput": 5475.64, "total_tokens": 28195024} {"current_steps": 46290, "total_steps": 64460, "loss": 0.1597, "lr": 2.2315269218937378e-06, "epoch": 14.36239528389699, "percentage": 71.81, "elapsed_time": "1:25:49", "remaining_time": "0:33:41", "throughput": 5475.7, "total_tokens": 28198928} {"current_steps": 46295, "total_steps": 64460, "loss": 0.188, "lr": 2.230399680669449e-06, "epoch": 14.363946633571206, "percentage": 71.82, "elapsed_time": "1:25:50", "remaining_time": "0:33:40", "throughput": 5475.64, "total_tokens": 28201488} {"current_steps": 46300, "total_steps": 64460, "loss": 0.1903, "lr": 2.229272642489662e-06, "epoch": 14.365497983245424, "percentage": 71.83, "elapsed_time": "1:25:50", "remaining_time": "0:33:40", "throughput": 5475.65, "total_tokens": 28204880} {"current_steps": 46305, "total_steps": 64460, "loss": 0.2117, "lr": 2.228145807436999e-06, "epoch": 14.36704933291964, "percentage": 71.84, "elapsed_time": "1:25:51", "remaining_time": "0:33:39", "throughput": 5475.67, "total_tokens": 28207600} {"current_steps": 46310, "total_steps": 64460, "loss": 0.2306, "lr": 2.2270191755940727e-06, "epoch": 14.368600682593856, "percentage": 71.84, "elapsed_time": "1:25:51", "remaining_time": "0:33:39", "throughput": 5475.65, "total_tokens": 28210160} {"current_steps": 46315, "total_steps": 64460, "loss": 0.199, "lr": 2.225892747043477e-06, "epoch": 14.370152032268074, "percentage": 71.85, "elapsed_time": "1:25:52", "remaining_time": "0:33:38", "throughput": 5475.68, "total_tokens": 28213104} {"current_steps": 46320, "total_steps": 64460, "loss": 0.1446, "lr": 2.2247665218677957e-06, "epoch": 14.37170338194229, "percentage": 71.86, "elapsed_time": "1:25:53", "remaining_time": "0:33:38", "throughput": 5475.83, "total_tokens": 28217232} {"current_steps": 46325, "total_steps": 64460, "loss": 0.1733, "lr": 2.223640500149589e-06, "epoch": 14.373254731616507, "percentage": 71.87, "elapsed_time": "1:25:53", "remaining_time": "0:33:37", "throughput": 5475.82, "total_tokens": 28219824} {"current_steps": 46330, "total_steps": 64460, "loss": 0.2485, "lr": 2.222514681971411e-06, "epoch": 14.374806081290723, "percentage": 71.87, "elapsed_time": "1:25:54", "remaining_time": "0:33:36", "throughput": 5475.82, "total_tokens": 28222576} {"current_steps": 46335, "total_steps": 64460, "loss": 0.2025, "lr": 2.221389067415799e-06, "epoch": 14.376357430964939, "percentage": 71.88, "elapsed_time": "1:25:54", "remaining_time": "0:33:36", "throughput": 5475.73, "total_tokens": 28225040} {"current_steps": 46340, "total_steps": 64460, "loss": 0.2557, "lr": 2.220263656565271e-06, "epoch": 14.377908780639157, "percentage": 71.89, "elapsed_time": "1:25:55", "remaining_time": "0:33:35", "throughput": 5475.68, "total_tokens": 28227472} {"current_steps": 46345, "total_steps": 64460, "loss": 0.1968, "lr": 2.2191384495023343e-06, "epoch": 14.379460130313372, "percentage": 71.9, "elapsed_time": "1:25:55", "remaining_time": "0:33:35", "throughput": 5475.94, "total_tokens": 28233776} {"current_steps": 46350, "total_steps": 64460, "loss": 0.1902, "lr": 2.2180134463094788e-06, "epoch": 14.381011479987588, "percentage": 71.91, "elapsed_time": "1:25:56", "remaining_time": "0:33:34", "throughput": 5476.02, "total_tokens": 28237072} {"current_steps": 46355, "total_steps": 64460, "loss": 0.1792, "lr": 2.216888647069183e-06, "epoch": 14.382562829661806, "percentage": 71.91, "elapsed_time": "1:25:56", "remaining_time": "0:33:34", "throughput": 5476.04, "total_tokens": 28239824} {"current_steps": 46360, "total_steps": 64460, "loss": 0.1619, "lr": 2.2157640518639043e-06, "epoch": 14.384114179336022, "percentage": 71.92, "elapsed_time": "1:25:57", "remaining_time": "0:33:33", "throughput": 5476.11, "total_tokens": 28243056} {"current_steps": 46365, "total_steps": 64460, "loss": 0.1721, "lr": 2.214639660776093e-06, "epoch": 14.38566552901024, "percentage": 71.93, "elapsed_time": "1:25:58", "remaining_time": "0:33:33", "throughput": 5476.15, "total_tokens": 28246032} {"current_steps": 46370, "total_steps": 64460, "loss": 0.1728, "lr": 2.2135154738881765e-06, "epoch": 14.387216878684455, "percentage": 71.94, "elapsed_time": "1:25:58", "remaining_time": "0:33:32", "throughput": 5476.24, "total_tokens": 28250000} {"current_steps": 46375, "total_steps": 64460, "loss": 0.2276, "lr": 2.212391491282574e-06, "epoch": 14.388768228358671, "percentage": 71.94, "elapsed_time": "1:25:59", "remaining_time": "0:33:31", "throughput": 5476.22, "total_tokens": 28252592} {"current_steps": 46380, "total_steps": 64460, "loss": 0.1943, "lr": 2.2112677130416838e-06, "epoch": 14.390319578032889, "percentage": 71.95, "elapsed_time": "1:25:59", "remaining_time": "0:33:31", "throughput": 5476.18, "total_tokens": 28255024} {"current_steps": 46385, "total_steps": 64460, "loss": 0.1517, "lr": 2.2101441392478956e-06, "epoch": 14.391870927707105, "percentage": 71.96, "elapsed_time": "1:26:00", "remaining_time": "0:33:30", "throughput": 5476.26, "total_tokens": 28258416} {"current_steps": 46390, "total_steps": 64460, "loss": 0.2249, "lr": 2.209020769983577e-06, "epoch": 14.393422277381323, "percentage": 71.97, "elapsed_time": "1:26:00", "remaining_time": "0:33:30", "throughput": 5476.27, "total_tokens": 28261264} {"current_steps": 46395, "total_steps": 64460, "loss": 0.2465, "lr": 2.207897605331086e-06, "epoch": 14.394973627055538, "percentage": 71.97, "elapsed_time": "1:26:01", "remaining_time": "0:33:29", "throughput": 5476.25, "total_tokens": 28263664} {"current_steps": 46400, "total_steps": 64460, "loss": 0.1987, "lr": 2.2067746453727657e-06, "epoch": 14.396524976729754, "percentage": 71.98, "elapsed_time": "1:26:01", "remaining_time": "0:33:29", "throughput": 5476.27, "total_tokens": 28266576} {"current_steps": 46405, "total_steps": 64460, "loss": 0.1747, "lr": 2.205651890190939e-06, "epoch": 14.398076326403972, "percentage": 71.99, "elapsed_time": "1:26:02", "remaining_time": "0:33:28", "throughput": 5476.26, "total_tokens": 28269200} {"current_steps": 46410, "total_steps": 64460, "loss": 0.2133, "lr": 2.204529339867921e-06, "epoch": 14.399627676078188, "percentage": 72.0, "elapsed_time": "1:26:02", "remaining_time": "0:33:27", "throughput": 5476.39, "total_tokens": 28272816} {"current_steps": 46415, "total_steps": 64460, "loss": 0.1911, "lr": 2.203406994486003e-06, "epoch": 14.401179025752405, "percentage": 72.01, "elapsed_time": "1:26:03", "remaining_time": "0:33:27", "throughput": 5476.45, "total_tokens": 28276176} {"current_steps": 46420, "total_steps": 64460, "loss": 0.21, "lr": 2.2022848541274712e-06, "epoch": 14.402730375426621, "percentage": 72.01, "elapsed_time": "1:26:03", "remaining_time": "0:33:26", "throughput": 5476.52, "total_tokens": 28280144} {"current_steps": 46425, "total_steps": 64460, "loss": 0.1655, "lr": 2.2011629188745875e-06, "epoch": 14.404281725100837, "percentage": 72.02, "elapsed_time": "1:26:04", "remaining_time": "0:33:26", "throughput": 5476.61, "total_tokens": 28283536} {"current_steps": 46430, "total_steps": 64460, "loss": 0.2065, "lr": 2.2000411888096072e-06, "epoch": 14.405833074775055, "percentage": 72.03, "elapsed_time": "1:26:04", "remaining_time": "0:33:25", "throughput": 5476.61, "total_tokens": 28286480} {"current_steps": 46435, "total_steps": 64460, "loss": 0.1952, "lr": 2.1989196640147625e-06, "epoch": 14.40738442444927, "percentage": 72.04, "elapsed_time": "1:26:05", "remaining_time": "0:33:25", "throughput": 5476.48, "total_tokens": 28288368} {"current_steps": 46440, "total_steps": 64460, "loss": 0.2036, "lr": 2.1977983445722778e-06, "epoch": 14.408935774123487, "percentage": 72.04, "elapsed_time": "1:26:05", "remaining_time": "0:33:24", "throughput": 5476.38, "total_tokens": 28290416} {"current_steps": 46445, "total_steps": 64460, "loss": 0.1646, "lr": 2.196677230564355e-06, "epoch": 14.410487123797704, "percentage": 72.05, "elapsed_time": "1:26:06", "remaining_time": "0:33:23", "throughput": 5476.33, "total_tokens": 28292880} {"current_steps": 46450, "total_steps": 64460, "loss": 0.2306, "lr": 2.1955563220731887e-06, "epoch": 14.41203847347192, "percentage": 72.06, "elapsed_time": "1:26:06", "remaining_time": "0:33:23", "throughput": 5476.37, "total_tokens": 28295920} {"current_steps": 46455, "total_steps": 64460, "loss": 0.1451, "lr": 2.1944356191809544e-06, "epoch": 14.413589823146138, "percentage": 72.07, "elapsed_time": "1:26:07", "remaining_time": "0:33:22", "throughput": 5476.44, "total_tokens": 28299312} {"current_steps": 46460, "total_steps": 64460, "loss": 0.1724, "lr": 2.1933151219698107e-06, "epoch": 14.415141172820354, "percentage": 72.08, "elapsed_time": "1:26:07", "remaining_time": "0:33:22", "throughput": 5476.33, "total_tokens": 28301360} {"current_steps": 46465, "total_steps": 64460, "loss": 0.1954, "lr": 2.1921948305219066e-06, "epoch": 14.41669252249457, "percentage": 72.08, "elapsed_time": "1:26:08", "remaining_time": "0:33:21", "throughput": 5476.44, "total_tokens": 28305008} {"current_steps": 46470, "total_steps": 64460, "loss": 0.2, "lr": 2.1910747449193687e-06, "epoch": 14.418243872168787, "percentage": 72.09, "elapsed_time": "1:26:08", "remaining_time": "0:33:21", "throughput": 5476.4, "total_tokens": 28307472} {"current_steps": 46475, "total_steps": 64460, "loss": 0.1799, "lr": 2.189954865244317e-06, "epoch": 14.419795221843003, "percentage": 72.1, "elapsed_time": "1:26:09", "remaining_time": "0:33:20", "throughput": 5476.42, "total_tokens": 28310320} {"current_steps": 46480, "total_steps": 64460, "loss": 0.1856, "lr": 2.188835191578847e-06, "epoch": 14.421346571517219, "percentage": 72.11, "elapsed_time": "1:26:09", "remaining_time": "0:33:19", "throughput": 5476.49, "total_tokens": 28313360} {"current_steps": 46485, "total_steps": 64460, "loss": 0.2055, "lr": 2.187715724005049e-06, "epoch": 14.422897921191437, "percentage": 72.11, "elapsed_time": "1:26:10", "remaining_time": "0:33:19", "throughput": 5476.47, "total_tokens": 28315952} {"current_steps": 46490, "total_steps": 64460, "loss": 0.1788, "lr": 2.186596462604989e-06, "epoch": 14.424449270865653, "percentage": 72.12, "elapsed_time": "1:26:11", "remaining_time": "0:33:18", "throughput": 5476.58, "total_tokens": 28319536} {"current_steps": 46495, "total_steps": 64460, "loss": 0.1805, "lr": 2.1854774074607236e-06, "epoch": 14.42600062053987, "percentage": 72.13, "elapsed_time": "1:26:11", "remaining_time": "0:33:18", "throughput": 5476.68, "total_tokens": 28323184} {"current_steps": 46500, "total_steps": 64460, "loss": 0.1823, "lr": 2.1843585586542936e-06, "epoch": 14.427551970214086, "percentage": 72.14, "elapsed_time": "1:26:12", "remaining_time": "0:33:17", "throughput": 5476.69, "total_tokens": 28325968} {"current_steps": 46505, "total_steps": 64460, "loss": 0.1959, "lr": 2.1832399162677247e-06, "epoch": 14.429103319888302, "percentage": 72.15, "elapsed_time": "1:26:12", "remaining_time": "0:33:17", "throughput": 5476.78, "total_tokens": 28329456} {"current_steps": 46510, "total_steps": 64460, "loss": 0.1861, "lr": 2.1821214803830243e-06, "epoch": 14.43065466956252, "percentage": 72.15, "elapsed_time": "1:26:13", "remaining_time": "0:33:16", "throughput": 5476.91, "total_tokens": 28333296} {"current_steps": 46515, "total_steps": 64460, "loss": 0.1945, "lr": 2.1810032510821893e-06, "epoch": 14.432206019236736, "percentage": 72.16, "elapsed_time": "1:26:13", "remaining_time": "0:33:15", "throughput": 5476.9, "total_tokens": 28335856} {"current_steps": 46520, "total_steps": 64460, "loss": 0.1852, "lr": 2.179885228447197e-06, "epoch": 14.433757368910953, "percentage": 72.17, "elapsed_time": "1:26:14", "remaining_time": "0:33:15", "throughput": 5476.89, "total_tokens": 28338864} {"current_steps": 46525, "total_steps": 64460, "loss": 0.1551, "lr": 2.1787674125600135e-06, "epoch": 14.43530871858517, "percentage": 72.18, "elapsed_time": "1:26:14", "remaining_time": "0:33:14", "throughput": 5476.95, "total_tokens": 28341968} {"current_steps": 46530, "total_steps": 64460, "loss": 0.2112, "lr": 2.177649803502585e-06, "epoch": 14.436860068259385, "percentage": 72.18, "elapsed_time": "1:26:15", "remaining_time": "0:33:14", "throughput": 5476.97, "total_tokens": 28345008} {"current_steps": 46535, "total_steps": 64460, "loss": 0.2505, "lr": 2.1765324013568477e-06, "epoch": 14.438411417933603, "percentage": 72.19, "elapsed_time": "1:26:15", "remaining_time": "0:33:13", "throughput": 5476.97, "total_tokens": 28347760} {"current_steps": 46540, "total_steps": 64460, "loss": 0.2162, "lr": 2.175415206204723e-06, "epoch": 14.439962767607819, "percentage": 72.2, "elapsed_time": "1:26:16", "remaining_time": "0:33:13", "throughput": 5477.06, "total_tokens": 28351056} {"current_steps": 46545, "total_steps": 64460, "loss": 0.2714, "lr": 2.1742982181281093e-06, "epoch": 14.441514117282036, "percentage": 72.21, "elapsed_time": "1:26:16", "remaining_time": "0:33:12", "throughput": 5477.07, "total_tokens": 28353904} {"current_steps": 46550, "total_steps": 64460, "loss": 0.1868, "lr": 2.1731814372088988e-06, "epoch": 14.443065466956252, "percentage": 72.22, "elapsed_time": "1:26:17", "remaining_time": "0:33:11", "throughput": 5477.01, "total_tokens": 28356144} {"current_steps": 46555, "total_steps": 64460, "loss": 0.1869, "lr": 2.172064863528963e-06, "epoch": 14.444616816630468, "percentage": 72.22, "elapsed_time": "1:26:17", "remaining_time": "0:33:11", "throughput": 5477.0, "total_tokens": 28358992} {"current_steps": 46560, "total_steps": 64460, "loss": 0.1977, "lr": 2.170948497170161e-06, "epoch": 14.446168166304686, "percentage": 72.23, "elapsed_time": "1:26:18", "remaining_time": "0:33:10", "throughput": 5477.03, "total_tokens": 28361776} {"current_steps": 46565, "total_steps": 64460, "loss": 0.1662, "lr": 2.169832338214334e-06, "epoch": 14.447719515978902, "percentage": 72.24, "elapsed_time": "1:26:18", "remaining_time": "0:33:10", "throughput": 5477.0, "total_tokens": 28364432} {"current_steps": 46570, "total_steps": 64460, "loss": 0.1986, "lr": 2.168716386743312e-06, "epoch": 14.449270865653117, "percentage": 72.25, "elapsed_time": "1:26:19", "remaining_time": "0:33:09", "throughput": 5477.0, "total_tokens": 28366992} {"current_steps": 46575, "total_steps": 64460, "loss": 0.1734, "lr": 2.167600642838905e-06, "epoch": 14.450822215327335, "percentage": 72.25, "elapsed_time": "1:26:19", "remaining_time": "0:33:09", "throughput": 5476.96, "total_tokens": 28369424} {"current_steps": 46580, "total_steps": 64460, "loss": 0.149, "lr": 2.1664851065829136e-06, "epoch": 14.452373565001551, "percentage": 72.26, "elapsed_time": "1:26:20", "remaining_time": "0:33:08", "throughput": 5476.95, "total_tokens": 28372400} {"current_steps": 46585, "total_steps": 64460, "loss": 0.2394, "lr": 2.1653697780571153e-06, "epoch": 14.453924914675769, "percentage": 72.27, "elapsed_time": "1:26:20", "remaining_time": "0:33:07", "throughput": 5476.89, "total_tokens": 28374704} {"current_steps": 46590, "total_steps": 64460, "loss": 0.1723, "lr": 2.164254657343281e-06, "epoch": 14.455476264349985, "percentage": 72.28, "elapsed_time": "1:26:21", "remaining_time": "0:33:07", "throughput": 5476.96, "total_tokens": 28377968} {"current_steps": 46595, "total_steps": 64460, "loss": 0.2061, "lr": 2.1631397445231596e-06, "epoch": 14.4570276140242, "percentage": 72.29, "elapsed_time": "1:26:21", "remaining_time": "0:33:06", "throughput": 5476.99, "total_tokens": 28381136} {"current_steps": 46600, "total_steps": 64460, "loss": 0.2404, "lr": 2.1620250396784875e-06, "epoch": 14.458578963698418, "percentage": 72.29, "elapsed_time": "1:26:22", "remaining_time": "0:33:06", "throughput": 5476.9, "total_tokens": 28383152} {"current_steps": 46605, "total_steps": 64460, "loss": 0.2212, "lr": 2.1609105428909887e-06, "epoch": 14.460130313372634, "percentage": 72.3, "elapsed_time": "1:26:22", "remaining_time": "0:33:05", "throughput": 5476.8, "total_tokens": 28385520} {"current_steps": 46610, "total_steps": 64460, "loss": 0.1834, "lr": 2.1597962542423656e-06, "epoch": 14.46168166304685, "percentage": 72.31, "elapsed_time": "1:26:23", "remaining_time": "0:33:05", "throughput": 5476.88, "total_tokens": 28388880} {"current_steps": 46615, "total_steps": 64460, "loss": 0.1525, "lr": 2.1586821738143114e-06, "epoch": 14.463233012721068, "percentage": 72.32, "elapsed_time": "1:26:23", "remaining_time": "0:33:04", "throughput": 5476.92, "total_tokens": 28391792} {"current_steps": 46620, "total_steps": 64460, "loss": 0.212, "lr": 2.1575683016884984e-06, "epoch": 14.464784362395283, "percentage": 72.32, "elapsed_time": "1:26:24", "remaining_time": "0:33:03", "throughput": 5476.95, "total_tokens": 28394960} {"current_steps": 46625, "total_steps": 64460, "loss": 0.1468, "lr": 2.15645463794659e-06, "epoch": 14.466335712069501, "percentage": 72.33, "elapsed_time": "1:26:25", "remaining_time": "0:33:03", "throughput": 5477.11, "total_tokens": 28399536} {"current_steps": 46630, "total_steps": 64460, "loss": 0.196, "lr": 2.155341182670228e-06, "epoch": 14.467887061743717, "percentage": 72.34, "elapsed_time": "1:26:25", "remaining_time": "0:33:02", "throughput": 5477.07, "total_tokens": 28401968} {"current_steps": 46635, "total_steps": 64460, "loss": 0.2394, "lr": 2.1542279359410446e-06, "epoch": 14.469438411417933, "percentage": 72.35, "elapsed_time": "1:26:26", "remaining_time": "0:33:02", "throughput": 5477.16, "total_tokens": 28405456} {"current_steps": 46640, "total_steps": 64460, "loss": 0.2227, "lr": 2.153114897840651e-06, "epoch": 14.47098976109215, "percentage": 72.35, "elapsed_time": "1:26:26", "remaining_time": "0:33:01", "throughput": 5477.1, "total_tokens": 28407888} {"current_steps": 46645, "total_steps": 64460, "loss": 0.2157, "lr": 2.152002068450649e-06, "epoch": 14.472541110766366, "percentage": 72.36, "elapsed_time": "1:26:27", "remaining_time": "0:33:01", "throughput": 5477.06, "total_tokens": 28410352} {"current_steps": 46650, "total_steps": 64460, "loss": 0.2186, "lr": 2.1508894478526182e-06, "epoch": 14.474092460440584, "percentage": 72.37, "elapsed_time": "1:26:27", "remaining_time": "0:33:00", "throughput": 5476.97, "total_tokens": 28412592} {"current_steps": 46655, "total_steps": 64460, "loss": 0.2754, "lr": 2.1497770361281305e-06, "epoch": 14.4756438101148, "percentage": 72.38, "elapsed_time": "1:26:28", "remaining_time": "0:32:59", "throughput": 5477.05, "total_tokens": 28415664} {"current_steps": 46660, "total_steps": 64460, "loss": 0.1377, "lr": 2.148664833358739e-06, "epoch": 14.477195159789016, "percentage": 72.39, "elapsed_time": "1:26:28", "remaining_time": "0:32:59", "throughput": 5477.16, "total_tokens": 28419504} {"current_steps": 46665, "total_steps": 64460, "loss": 0.2136, "lr": 2.1475528396259782e-06, "epoch": 14.478746509463233, "percentage": 72.39, "elapsed_time": "1:26:29", "remaining_time": "0:32:58", "throughput": 5477.08, "total_tokens": 28421712} {"current_steps": 46670, "total_steps": 64460, "loss": 0.1355, "lr": 2.1464410550113747e-06, "epoch": 14.48029785913745, "percentage": 72.4, "elapsed_time": "1:26:29", "remaining_time": "0:32:58", "throughput": 5477.06, "total_tokens": 28424304} {"current_steps": 46675, "total_steps": 64460, "loss": 0.1964, "lr": 2.145329479596431e-06, "epoch": 14.481849208811667, "percentage": 72.41, "elapsed_time": "1:26:30", "remaining_time": "0:32:57", "throughput": 5477.08, "total_tokens": 28427792} {"current_steps": 46680, "total_steps": 64460, "loss": 0.1797, "lr": 2.1442181134626423e-06, "epoch": 14.483400558485883, "percentage": 72.42, "elapsed_time": "1:26:30", "remaining_time": "0:32:57", "throughput": 5477.15, "total_tokens": 28431376} {"current_steps": 46685, "total_steps": 64460, "loss": 0.1544, "lr": 2.1431069566914814e-06, "epoch": 14.484951908160099, "percentage": 72.42, "elapsed_time": "1:26:31", "remaining_time": "0:32:56", "throughput": 5477.27, "total_tokens": 28435536} {"current_steps": 46690, "total_steps": 64460, "loss": 0.17, "lr": 2.1419960093644137e-06, "epoch": 14.486503257834316, "percentage": 72.43, "elapsed_time": "1:26:32", "remaining_time": "0:32:56", "throughput": 5477.29, "total_tokens": 28438576} {"current_steps": 46695, "total_steps": 64460, "loss": 0.1478, "lr": 2.1408852715628802e-06, "epoch": 14.488054607508532, "percentage": 72.44, "elapsed_time": "1:26:32", "remaining_time": "0:32:55", "throughput": 5477.28, "total_tokens": 28441104} {"current_steps": 46700, "total_steps": 64460, "loss": 0.2354, "lr": 2.139774743368315e-06, "epoch": 14.489605957182748, "percentage": 72.45, "elapsed_time": "1:26:33", "remaining_time": "0:32:55", "throughput": 5477.46, "total_tokens": 28446192} {"current_steps": 46705, "total_steps": 64460, "loss": 0.2549, "lr": 2.1386644248621297e-06, "epoch": 14.491157306856966, "percentage": 72.46, "elapsed_time": "1:26:33", "remaining_time": "0:32:54", "throughput": 5477.54, "total_tokens": 28449296} {"current_steps": 46710, "total_steps": 64460, "loss": 0.1917, "lr": 2.1375543161257268e-06, "epoch": 14.492708656531182, "percentage": 72.46, "elapsed_time": "1:26:34", "remaining_time": "0:32:53", "throughput": 5477.63, "total_tokens": 28452784} {"current_steps": 46715, "total_steps": 64460, "loss": 0.2122, "lr": 2.1364444172404875e-06, "epoch": 14.4942600062054, "percentage": 72.47, "elapsed_time": "1:26:34", "remaining_time": "0:32:53", "throughput": 5477.68, "total_tokens": 28455632} {"current_steps": 46720, "total_steps": 64460, "loss": 0.2256, "lr": 2.135334728287782e-06, "epoch": 14.495811355879615, "percentage": 72.48, "elapsed_time": "1:26:35", "remaining_time": "0:32:52", "throughput": 5477.83, "total_tokens": 28459600} {"current_steps": 46725, "total_steps": 64460, "loss": 0.1465, "lr": 2.134225249348965e-06, "epoch": 14.497362705553831, "percentage": 72.49, "elapsed_time": "1:26:35", "remaining_time": "0:32:52", "throughput": 5477.86, "total_tokens": 28462576} {"current_steps": 46730, "total_steps": 64460, "loss": 0.2077, "lr": 2.133115980505372e-06, "epoch": 14.498914055228049, "percentage": 72.49, "elapsed_time": "1:26:36", "remaining_time": "0:32:51", "throughput": 5477.79, "total_tokens": 28464848} {"current_steps": 46735, "total_steps": 64460, "loss": 0.1586, "lr": 2.1320069218383277e-06, "epoch": 14.500465404902265, "percentage": 72.5, "elapsed_time": "1:26:36", "remaining_time": "0:32:51", "throughput": 5477.82, "total_tokens": 28467920} {"current_steps": 46740, "total_steps": 64460, "loss": 0.14, "lr": 2.130898073429137e-06, "epoch": 14.50201675457648, "percentage": 72.51, "elapsed_time": "1:26:37", "remaining_time": "0:32:50", "throughput": 5477.87, "total_tokens": 28470704} {"current_steps": 46745, "total_steps": 64460, "loss": 0.2247, "lr": 2.1297894353590935e-06, "epoch": 14.503568104250698, "percentage": 72.52, "elapsed_time": "1:26:37", "remaining_time": "0:32:49", "throughput": 5477.99, "total_tokens": 28474480} {"current_steps": 46750, "total_steps": 64460, "loss": 0.2009, "lr": 2.128681007709472e-06, "epoch": 14.505119453924914, "percentage": 72.53, "elapsed_time": "1:26:38", "remaining_time": "0:32:49", "throughput": 5478.0, "total_tokens": 28477168} {"current_steps": 46755, "total_steps": 64460, "loss": 0.1938, "lr": 2.1275727905615358e-06, "epoch": 14.506670803599132, "percentage": 72.53, "elapsed_time": "1:26:38", "remaining_time": "0:32:48", "throughput": 5478.03, "total_tokens": 28479760} {"current_steps": 46760, "total_steps": 64460, "loss": 0.2533, "lr": 2.1264647839965264e-06, "epoch": 14.508222153273348, "percentage": 72.54, "elapsed_time": "1:26:39", "remaining_time": "0:32:48", "throughput": 5478.09, "total_tokens": 28482736} {"current_steps": 46765, "total_steps": 64460, "loss": 0.1928, "lr": 2.125356988095678e-06, "epoch": 14.509773502947564, "percentage": 72.55, "elapsed_time": "1:26:39", "remaining_time": "0:32:47", "throughput": 5478.09, "total_tokens": 28485296} {"current_steps": 46770, "total_steps": 64460, "loss": 0.1661, "lr": 2.1242494029402017e-06, "epoch": 14.511324852621781, "percentage": 72.56, "elapsed_time": "1:26:40", "remaining_time": "0:32:46", "throughput": 5478.17, "total_tokens": 28488368} {"current_steps": 46775, "total_steps": 64460, "loss": 0.2006, "lr": 2.1231420286112982e-06, "epoch": 14.512876202295997, "percentage": 72.56, "elapsed_time": "1:26:40", "remaining_time": "0:32:46", "throughput": 5478.28, "total_tokens": 28491696} {"current_steps": 46780, "total_steps": 64460, "loss": 0.1597, "lr": 2.122034865190153e-06, "epoch": 14.514427551970215, "percentage": 72.57, "elapsed_time": "1:26:41", "remaining_time": "0:32:45", "throughput": 5478.25, "total_tokens": 28494608} {"current_steps": 46785, "total_steps": 64460, "loss": 0.1511, "lr": 2.12092791275793e-06, "epoch": 14.51597890164443, "percentage": 72.58, "elapsed_time": "1:26:41", "remaining_time": "0:32:45", "throughput": 5478.2, "total_tokens": 28497072} {"current_steps": 46790, "total_steps": 64460, "loss": 0.2014, "lr": 2.1198211713957866e-06, "epoch": 14.517530251318647, "percentage": 72.59, "elapsed_time": "1:26:42", "remaining_time": "0:32:44", "throughput": 5478.26, "total_tokens": 28500112} {"current_steps": 46795, "total_steps": 64460, "loss": 0.1794, "lr": 2.118714641184856e-06, "epoch": 14.519081600992864, "percentage": 72.6, "elapsed_time": "1:26:42", "remaining_time": "0:32:44", "throughput": 5478.21, "total_tokens": 28502384} {"current_steps": 46800, "total_steps": 64460, "loss": 0.2298, "lr": 2.1176083222062633e-06, "epoch": 14.52063295066708, "percentage": 72.6, "elapsed_time": "1:26:43", "remaining_time": "0:32:43", "throughput": 5478.29, "total_tokens": 28505424} {"current_steps": 46805, "total_steps": 64460, "loss": 0.1655, "lr": 2.116502214541111e-06, "epoch": 14.522184300341298, "percentage": 72.61, "elapsed_time": "1:26:43", "remaining_time": "0:32:42", "throughput": 5478.33, "total_tokens": 28508240} {"current_steps": 46810, "total_steps": 64460, "loss": 0.2287, "lr": 2.1153963182704946e-06, "epoch": 14.523735650015514, "percentage": 72.62, "elapsed_time": "1:26:44", "remaining_time": "0:32:42", "throughput": 5478.33, "total_tokens": 28510768} {"current_steps": 46815, "total_steps": 64460, "loss": 0.2395, "lr": 2.114290633475485e-06, "epoch": 14.52528699968973, "percentage": 72.63, "elapsed_time": "1:26:44", "remaining_time": "0:32:41", "throughput": 5478.35, "total_tokens": 28513552} {"current_steps": 46820, "total_steps": 64460, "loss": 0.186, "lr": 2.113185160237145e-06, "epoch": 14.526838349363947, "percentage": 72.63, "elapsed_time": "1:26:45", "remaining_time": "0:32:41", "throughput": 5478.54, "total_tokens": 28518736} {"current_steps": 46825, "total_steps": 64460, "loss": 0.2316, "lr": 2.1120798986365167e-06, "epoch": 14.528389699038163, "percentage": 72.64, "elapsed_time": "1:26:46", "remaining_time": "0:32:40", "throughput": 5478.56, "total_tokens": 28521520} {"current_steps": 46830, "total_steps": 64460, "loss": 0.2586, "lr": 2.110974848754631e-06, "epoch": 14.529941048712379, "percentage": 72.65, "elapsed_time": "1:26:46", "remaining_time": "0:32:40", "throughput": 5478.58, "total_tokens": 28524208} {"current_steps": 46835, "total_steps": 64460, "loss": 0.2223, "lr": 2.109870010672499e-06, "epoch": 14.531492398386597, "percentage": 72.66, "elapsed_time": "1:26:46", "remaining_time": "0:32:39", "throughput": 5478.63, "total_tokens": 28527088} {"current_steps": 46840, "total_steps": 64460, "loss": 0.1905, "lr": 2.108765384471119e-06, "epoch": 14.533043748060813, "percentage": 72.67, "elapsed_time": "1:26:47", "remaining_time": "0:32:38", "throughput": 5478.54, "total_tokens": 28529232} {"current_steps": 46845, "total_steps": 64460, "loss": 0.1998, "lr": 2.107660970231476e-06, "epoch": 14.53459509773503, "percentage": 72.67, "elapsed_time": "1:26:47", "remaining_time": "0:32:38", "throughput": 5478.6, "total_tokens": 28532528} {"current_steps": 46850, "total_steps": 64460, "loss": 0.1626, "lr": 2.1065567680345324e-06, "epoch": 14.536146447409246, "percentage": 72.68, "elapsed_time": "1:26:48", "remaining_time": "0:32:37", "throughput": 5478.59, "total_tokens": 28534992} {"current_steps": 46855, "total_steps": 64460, "loss": 0.2133, "lr": 2.1054527779612428e-06, "epoch": 14.537697797083462, "percentage": 72.69, "elapsed_time": "1:26:48", "remaining_time": "0:32:37", "throughput": 5478.54, "total_tokens": 28537232} {"current_steps": 46860, "total_steps": 64460, "loss": 0.1905, "lr": 2.1043490000925386e-06, "epoch": 14.53924914675768, "percentage": 72.7, "elapsed_time": "1:26:49", "remaining_time": "0:32:36", "throughput": 5478.53, "total_tokens": 28539792} {"current_steps": 46865, "total_steps": 64460, "loss": 0.1779, "lr": 2.103245434509345e-06, "epoch": 14.540800496431896, "percentage": 72.7, "elapsed_time": "1:26:49", "remaining_time": "0:32:36", "throughput": 5478.57, "total_tokens": 28542736} {"current_steps": 46870, "total_steps": 64460, "loss": 0.1862, "lr": 2.102142081292562e-06, "epoch": 14.542351846106111, "percentage": 72.71, "elapsed_time": "1:26:50", "remaining_time": "0:32:35", "throughput": 5478.57, "total_tokens": 28545360} {"current_steps": 46875, "total_steps": 64460, "loss": 0.1759, "lr": 2.101038940523082e-06, "epoch": 14.543903195780329, "percentage": 72.72, "elapsed_time": "1:26:50", "remaining_time": "0:32:34", "throughput": 5478.62, "total_tokens": 28548560} {"current_steps": 46880, "total_steps": 64460, "loss": 0.2189, "lr": 2.099936012281774e-06, "epoch": 14.545454545454545, "percentage": 72.73, "elapsed_time": "1:26:51", "remaining_time": "0:32:34", "throughput": 5478.71, "total_tokens": 28551728} {"current_steps": 46885, "total_steps": 64460, "loss": 0.1474, "lr": 2.098833296649501e-06, "epoch": 14.547005895128763, "percentage": 72.74, "elapsed_time": "1:26:51", "remaining_time": "0:32:33", "throughput": 5478.8, "total_tokens": 28554992} {"current_steps": 46890, "total_steps": 64460, "loss": 0.1859, "lr": 2.0977307937070993e-06, "epoch": 14.548557244802979, "percentage": 72.74, "elapsed_time": "1:26:52", "remaining_time": "0:32:33", "throughput": 5478.79, "total_tokens": 28557712} {"current_steps": 46895, "total_steps": 64460, "loss": 0.1966, "lr": 2.096628503535401e-06, "epoch": 14.550108594477194, "percentage": 72.75, "elapsed_time": "1:26:52", "remaining_time": "0:32:32", "throughput": 5478.82, "total_tokens": 28560720} {"current_steps": 46900, "total_steps": 64460, "loss": 0.172, "lr": 2.095526426215213e-06, "epoch": 14.551659944151412, "percentage": 72.76, "elapsed_time": "1:26:53", "remaining_time": "0:32:32", "throughput": 5479.0, "total_tokens": 28565808} {"current_steps": 46905, "total_steps": 64460, "loss": 0.2374, "lr": 2.0944245618273317e-06, "epoch": 14.553211293825628, "percentage": 72.77, "elapsed_time": "1:26:54", "remaining_time": "0:32:31", "throughput": 5479.15, "total_tokens": 28569904} {"current_steps": 46910, "total_steps": 64460, "loss": 0.2463, "lr": 2.0933229104525386e-06, "epoch": 14.554762643499846, "percentage": 72.77, "elapsed_time": "1:26:54", "remaining_time": "0:32:30", "throughput": 5479.12, "total_tokens": 28572336} {"current_steps": 46915, "total_steps": 64460, "loss": 0.1452, "lr": 2.092221472171595e-06, "epoch": 14.556313993174061, "percentage": 72.78, "elapsed_time": "1:26:55", "remaining_time": "0:32:30", "throughput": 5479.14, "total_tokens": 28575024} {"current_steps": 46920, "total_steps": 64460, "loss": 0.1937, "lr": 2.0911202470652525e-06, "epoch": 14.557865342848277, "percentage": 72.79, "elapsed_time": "1:26:55", "remaining_time": "0:32:29", "throughput": 5479.17, "total_tokens": 28577936} {"current_steps": 46925, "total_steps": 64460, "loss": 0.1461, "lr": 2.0900192352142408e-06, "epoch": 14.559416692522495, "percentage": 72.8, "elapsed_time": "1:26:56", "remaining_time": "0:32:29", "throughput": 5479.41, "total_tokens": 28583504} {"current_steps": 46930, "total_steps": 64460, "loss": 0.1587, "lr": 2.0889184366992795e-06, "epoch": 14.560968042196711, "percentage": 72.8, "elapsed_time": "1:26:56", "remaining_time": "0:32:28", "throughput": 5479.35, "total_tokens": 28585744} {"current_steps": 46935, "total_steps": 64460, "loss": 0.1406, "lr": 2.087817851601068e-06, "epoch": 14.562519391870929, "percentage": 72.81, "elapsed_time": "1:26:57", "remaining_time": "0:32:28", "throughput": 5479.42, "total_tokens": 28589008} {"current_steps": 46940, "total_steps": 64460, "loss": 0.2039, "lr": 2.086717480000294e-06, "epoch": 14.564070741545144, "percentage": 72.82, "elapsed_time": "1:26:58", "remaining_time": "0:32:27", "throughput": 5479.6, "total_tokens": 28594032} {"current_steps": 46945, "total_steps": 64460, "loss": 0.2017, "lr": 2.0856173219776264e-06, "epoch": 14.56562209121936, "percentage": 72.83, "elapsed_time": "1:26:58", "remaining_time": "0:32:27", "throughput": 5479.52, "total_tokens": 28596048} {"current_steps": 46950, "total_steps": 64460, "loss": 0.1504, "lr": 2.0845173776137223e-06, "epoch": 14.567173440893578, "percentage": 72.84, "elapsed_time": "1:26:59", "remaining_time": "0:32:26", "throughput": 5479.56, "total_tokens": 28598960} {"current_steps": 46955, "total_steps": 64460, "loss": 0.1786, "lr": 2.083417646989217e-06, "epoch": 14.568724790567794, "percentage": 72.84, "elapsed_time": "1:26:59", "remaining_time": "0:32:25", "throughput": 5479.57, "total_tokens": 28601648} {"current_steps": 46960, "total_steps": 64460, "loss": 0.2462, "lr": 2.0823181301847356e-06, "epoch": 14.57027614024201, "percentage": 72.85, "elapsed_time": "1:27:00", "remaining_time": "0:32:25", "throughput": 5479.6, "total_tokens": 28604432} {"current_steps": 46965, "total_steps": 64460, "loss": 0.2197, "lr": 2.0812188272808874e-06, "epoch": 14.571827489916227, "percentage": 72.86, "elapsed_time": "1:27:00", "remaining_time": "0:32:24", "throughput": 5479.62, "total_tokens": 28607152} {"current_steps": 46970, "total_steps": 64460, "loss": 0.2459, "lr": 2.080119738358261e-06, "epoch": 14.573378839590443, "percentage": 72.87, "elapsed_time": "1:27:01", "remaining_time": "0:32:24", "throughput": 5479.73, "total_tokens": 28610960} {"current_steps": 46975, "total_steps": 64460, "loss": 0.1411, "lr": 2.079020863497436e-06, "epoch": 14.574930189264661, "percentage": 72.87, "elapsed_time": "1:27:01", "remaining_time": "0:32:23", "throughput": 5479.74, "total_tokens": 28613936} {"current_steps": 46980, "total_steps": 64460, "loss": 0.1431, "lr": 2.0779222027789704e-06, "epoch": 14.576481538938877, "percentage": 72.88, "elapsed_time": "1:27:02", "remaining_time": "0:32:23", "throughput": 5479.87, "total_tokens": 28617648} {"current_steps": 46985, "total_steps": 64460, "loss": 0.2209, "lr": 2.076823756283411e-06, "epoch": 14.578032888613093, "percentage": 72.89, "elapsed_time": "1:27:02", "remaining_time": "0:32:22", "throughput": 5480.01, "total_tokens": 28621584} {"current_steps": 46990, "total_steps": 64460, "loss": 0.1642, "lr": 2.0757255240912836e-06, "epoch": 14.57958423828731, "percentage": 72.9, "elapsed_time": "1:27:03", "remaining_time": "0:32:21", "throughput": 5479.99, "total_tokens": 28624240} {"current_steps": 46995, "total_steps": 64460, "loss": 0.1335, "lr": 2.074627506283106e-06, "epoch": 14.581135587961526, "percentage": 72.91, "elapsed_time": "1:27:03", "remaining_time": "0:32:21", "throughput": 5480.06, "total_tokens": 28627504} {"current_steps": 47000, "total_steps": 64460, "loss": 0.1369, "lr": 2.0735297029393723e-06, "epoch": 14.582686937635742, "percentage": 72.91, "elapsed_time": "1:27:04", "remaining_time": "0:32:20", "throughput": 5480.12, "total_tokens": 28630704} {"current_steps": 47005, "total_steps": 64460, "loss": 0.3367, "lr": 2.0724321141405677e-06, "epoch": 14.58423828730996, "percentage": 72.92, "elapsed_time": "1:27:05", "remaining_time": "0:32:20", "throughput": 5480.26, "total_tokens": 28636720} {"current_steps": 47010, "total_steps": 64460, "loss": 0.2567, "lr": 2.071334739967155e-06, "epoch": 14.585789636984176, "percentage": 72.93, "elapsed_time": "1:27:05", "remaining_time": "0:32:19", "throughput": 5480.24, "total_tokens": 28639088} {"current_steps": 47015, "total_steps": 64460, "loss": 0.1496, "lr": 2.0702375804995877e-06, "epoch": 14.587340986658393, "percentage": 72.94, "elapsed_time": "1:27:06", "remaining_time": "0:32:19", "throughput": 5480.3, "total_tokens": 28642128} {"current_steps": 47020, "total_steps": 64460, "loss": 0.1459, "lr": 2.069140635818298e-06, "epoch": 14.58889233633261, "percentage": 72.94, "elapsed_time": "1:27:06", "remaining_time": "0:32:18", "throughput": 5480.39, "total_tokens": 28645648} {"current_steps": 47025, "total_steps": 64460, "loss": 0.2673, "lr": 2.068043906003706e-06, "epoch": 14.590443686006825, "percentage": 72.95, "elapsed_time": "1:27:07", "remaining_time": "0:32:18", "throughput": 5480.43, "total_tokens": 28648560} {"current_steps": 47030, "total_steps": 64460, "loss": 0.2002, "lr": 2.0669473911362174e-06, "epoch": 14.591995035681043, "percentage": 72.96, "elapsed_time": "1:27:07", "remaining_time": "0:32:17", "throughput": 5480.51, "total_tokens": 28651920} {"current_steps": 47035, "total_steps": 64460, "loss": 0.2144, "lr": 2.0658510912962156e-06, "epoch": 14.593546385355259, "percentage": 72.97, "elapsed_time": "1:27:08", "remaining_time": "0:32:16", "throughput": 5480.59, "total_tokens": 28655056} {"current_steps": 47040, "total_steps": 64460, "loss": 0.2215, "lr": 2.064755006564076e-06, "epoch": 14.595097735029476, "percentage": 72.98, "elapsed_time": "1:27:08", "remaining_time": "0:32:16", "throughput": 5480.52, "total_tokens": 28657168} {"current_steps": 47045, "total_steps": 64460, "loss": 0.1563, "lr": 2.0636591370201515e-06, "epoch": 14.596649084703692, "percentage": 72.98, "elapsed_time": "1:27:09", "remaining_time": "0:32:15", "throughput": 5480.55, "total_tokens": 28659984} {"current_steps": 47050, "total_steps": 64460, "loss": 0.234, "lr": 2.062563482744785e-06, "epoch": 14.598200434377908, "percentage": 72.99, "elapsed_time": "1:27:09", "remaining_time": "0:32:15", "throughput": 5480.56, "total_tokens": 28662672} {"current_steps": 47055, "total_steps": 64460, "loss": 0.34, "lr": 2.061468043818298e-06, "epoch": 14.599751784052126, "percentage": 73.0, "elapsed_time": "1:27:10", "remaining_time": "0:32:14", "throughput": 5480.64, "total_tokens": 28666768} {"current_steps": 47060, "total_steps": 64460, "loss": 0.2831, "lr": 2.060372820321003e-06, "epoch": 14.601303133726342, "percentage": 73.01, "elapsed_time": "1:27:11", "remaining_time": "0:32:14", "throughput": 5480.75, "total_tokens": 28670512} {"current_steps": 47065, "total_steps": 64460, "loss": 0.139, "lr": 2.0592778123331888e-06, "epoch": 14.60285448340056, "percentage": 73.01, "elapsed_time": "1:27:11", "remaining_time": "0:32:13", "throughput": 5480.73, "total_tokens": 28672848} {"current_steps": 47070, "total_steps": 64460, "loss": 0.1979, "lr": 2.0581830199351337e-06, "epoch": 14.604405833074775, "percentage": 73.02, "elapsed_time": "1:27:12", "remaining_time": "0:32:13", "throughput": 5480.86, "total_tokens": 28676688} {"current_steps": 47075, "total_steps": 64460, "loss": 0.2968, "lr": 2.0570884432071e-06, "epoch": 14.605957182748991, "percentage": 73.03, "elapsed_time": "1:27:12", "remaining_time": "0:32:12", "throughput": 5480.89, "total_tokens": 28679440} {"current_steps": 47080, "total_steps": 64460, "loss": 0.2118, "lr": 2.0559940822293344e-06, "epoch": 14.607508532423209, "percentage": 73.04, "elapsed_time": "1:27:13", "remaining_time": "0:32:11", "throughput": 5480.92, "total_tokens": 28682224} {"current_steps": 47085, "total_steps": 64460, "loss": 0.1611, "lr": 2.054899937082063e-06, "epoch": 14.609059882097425, "percentage": 73.05, "elapsed_time": "1:27:13", "remaining_time": "0:32:11", "throughput": 5481.08, "total_tokens": 28687152} {"current_steps": 47090, "total_steps": 64460, "loss": 0.1817, "lr": 2.0538060078455036e-06, "epoch": 14.61061123177164, "percentage": 73.05, "elapsed_time": "1:27:14", "remaining_time": "0:32:10", "throughput": 5481.15, "total_tokens": 28690480} {"current_steps": 47095, "total_steps": 64460, "loss": 0.1571, "lr": 2.0527122945998494e-06, "epoch": 14.612162581445858, "percentage": 73.06, "elapsed_time": "1:27:14", "remaining_time": "0:32:10", "throughput": 5481.09, "total_tokens": 28692752} {"current_steps": 47100, "total_steps": 64460, "loss": 0.2258, "lr": 2.0516187974252875e-06, "epoch": 14.613713931120074, "percentage": 73.07, "elapsed_time": "1:27:15", "remaining_time": "0:32:09", "throughput": 5481.22, "total_tokens": 28696656} {"current_steps": 47105, "total_steps": 64460, "loss": 0.1953, "lr": 2.05052551640198e-06, "epoch": 14.615265280794292, "percentage": 73.08, "elapsed_time": "1:27:15", "remaining_time": "0:32:09", "throughput": 5481.23, "total_tokens": 28699312} {"current_steps": 47110, "total_steps": 64460, "loss": 0.2686, "lr": 2.0494324516100788e-06, "epoch": 14.616816630468508, "percentage": 73.08, "elapsed_time": "1:27:16", "remaining_time": "0:32:08", "throughput": 5481.26, "total_tokens": 28702256} {"current_steps": 47115, "total_steps": 64460, "loss": 0.1843, "lr": 2.048339603129721e-06, "epoch": 14.618367980142724, "percentage": 73.09, "elapsed_time": "1:27:17", "remaining_time": "0:32:07", "throughput": 5481.4, "total_tokens": 28706256} {"current_steps": 47120, "total_steps": 64460, "loss": 0.1645, "lr": 2.0472469710410213e-06, "epoch": 14.619919329816941, "percentage": 73.1, "elapsed_time": "1:27:17", "remaining_time": "0:32:07", "throughput": 5481.52, "total_tokens": 28710064} {"current_steps": 47125, "total_steps": 64460, "loss": 0.2212, "lr": 2.0461545554240865e-06, "epoch": 14.621470679491157, "percentage": 73.11, "elapsed_time": "1:27:18", "remaining_time": "0:32:06", "throughput": 5481.59, "total_tokens": 28713104} {"current_steps": 47130, "total_steps": 64460, "loss": 0.238, "lr": 2.0450623563589996e-06, "epoch": 14.623022029165373, "percentage": 73.12, "elapsed_time": "1:27:18", "remaining_time": "0:32:06", "throughput": 5481.64, "total_tokens": 28715856} {"current_steps": 47135, "total_steps": 64460, "loss": 0.164, "lr": 2.0439703739258348e-06, "epoch": 14.62457337883959, "percentage": 73.12, "elapsed_time": "1:27:19", "remaining_time": "0:32:05", "throughput": 5481.54, "total_tokens": 28717904} {"current_steps": 47140, "total_steps": 64460, "loss": 0.2012, "lr": 2.042878608204645e-06, "epoch": 14.626124728513807, "percentage": 73.13, "elapsed_time": "1:27:19", "remaining_time": "0:32:05", "throughput": 5481.55, "total_tokens": 28720528} {"current_steps": 47145, "total_steps": 64460, "loss": 0.1766, "lr": 2.0417870592754727e-06, "epoch": 14.627676078188024, "percentage": 73.14, "elapsed_time": "1:27:19", "remaining_time": "0:32:04", "throughput": 5481.58, "total_tokens": 28723216} {"current_steps": 47150, "total_steps": 64460, "loss": 0.2284, "lr": 2.0406957272183376e-06, "epoch": 14.62922742786224, "percentage": 73.15, "elapsed_time": "1:27:20", "remaining_time": "0:32:03", "throughput": 5481.58, "total_tokens": 28725744} {"current_steps": 47155, "total_steps": 64460, "loss": 0.3218, "lr": 2.0396046121132506e-06, "epoch": 14.630778777536456, "percentage": 73.15, "elapsed_time": "1:27:20", "remaining_time": "0:32:03", "throughput": 5481.51, "total_tokens": 28727824} {"current_steps": 47160, "total_steps": 64460, "loss": 0.2121, "lr": 2.0385137140402006e-06, "epoch": 14.632330127210674, "percentage": 73.16, "elapsed_time": "1:27:21", "remaining_time": "0:32:02", "throughput": 5481.55, "total_tokens": 28730608} {"current_steps": 47165, "total_steps": 64460, "loss": 0.1967, "lr": 2.037423033079164e-06, "epoch": 14.63388147688489, "percentage": 73.17, "elapsed_time": "1:27:21", "remaining_time": "0:32:02", "throughput": 5481.62, "total_tokens": 28733744} {"current_steps": 47170, "total_steps": 64460, "loss": 0.2421, "lr": 2.036332569310103e-06, "epoch": 14.635432826559107, "percentage": 73.18, "elapsed_time": "1:27:22", "remaining_time": "0:32:01", "throughput": 5481.68, "total_tokens": 28736880} {"current_steps": 47175, "total_steps": 64460, "loss": 0.167, "lr": 2.0352423228129585e-06, "epoch": 14.636984176233323, "percentage": 73.18, "elapsed_time": "1:27:22", "remaining_time": "0:32:00", "throughput": 5481.67, "total_tokens": 28739536} {"current_steps": 47180, "total_steps": 64460, "loss": 0.1612, "lr": 2.034152293667661e-06, "epoch": 14.638535525907539, "percentage": 73.19, "elapsed_time": "1:27:23", "remaining_time": "0:32:00", "throughput": 5481.66, "total_tokens": 28742512} {"current_steps": 47185, "total_steps": 64460, "loss": 0.1619, "lr": 2.03306248195412e-06, "epoch": 14.640086875581757, "percentage": 73.2, "elapsed_time": "1:27:23", "remaining_time": "0:31:59", "throughput": 5481.64, "total_tokens": 28745232} {"current_steps": 47190, "total_steps": 64460, "loss": 0.1677, "lr": 2.0319728877522345e-06, "epoch": 14.641638225255972, "percentage": 73.21, "elapsed_time": "1:27:24", "remaining_time": "0:31:59", "throughput": 5481.67, "total_tokens": 28748400} {"current_steps": 47195, "total_steps": 64460, "loss": 0.1881, "lr": 2.0308835111418805e-06, "epoch": 14.64318957493019, "percentage": 73.22, "elapsed_time": "1:27:24", "remaining_time": "0:31:58", "throughput": 5481.7, "total_tokens": 28751280} {"current_steps": 47200, "total_steps": 64460, "loss": 0.2632, "lr": 2.0297943522029274e-06, "epoch": 14.644740924604406, "percentage": 73.22, "elapsed_time": "1:27:25", "remaining_time": "0:31:58", "throughput": 5481.75, "total_tokens": 28754480} {"current_steps": 47205, "total_steps": 64460, "loss": 0.1275, "lr": 2.0287054110152186e-06, "epoch": 14.646292274278622, "percentage": 73.23, "elapsed_time": "1:27:26", "remaining_time": "0:31:57", "throughput": 5481.68, "total_tokens": 28756912} {"current_steps": 47210, "total_steps": 64460, "loss": 0.28, "lr": 2.0276166876585905e-06, "epoch": 14.64784362395284, "percentage": 73.24, "elapsed_time": "1:27:26", "remaining_time": "0:31:57", "throughput": 5481.73, "total_tokens": 28759824} {"current_steps": 47215, "total_steps": 64460, "loss": 0.2079, "lr": 2.026528182212856e-06, "epoch": 14.649394973627055, "percentage": 73.25, "elapsed_time": "1:27:26", "remaining_time": "0:31:56", "throughput": 5481.74, "total_tokens": 28762480} {"current_steps": 47220, "total_steps": 64460, "loss": 0.217, "lr": 2.025439894757818e-06, "epoch": 14.650946323301271, "percentage": 73.25, "elapsed_time": "1:27:27", "remaining_time": "0:31:55", "throughput": 5481.69, "total_tokens": 28764816} {"current_steps": 47225, "total_steps": 64460, "loss": 0.1355, "lr": 2.0243518253732587e-06, "epoch": 14.652497672975489, "percentage": 73.26, "elapsed_time": "1:27:27", "remaining_time": "0:31:55", "throughput": 5481.65, "total_tokens": 28767184} {"current_steps": 47230, "total_steps": 64460, "loss": 0.1983, "lr": 2.023263974138947e-06, "epoch": 14.654049022649705, "percentage": 73.27, "elapsed_time": "1:27:28", "remaining_time": "0:31:54", "throughput": 5481.75, "total_tokens": 28771056} {"current_steps": 47235, "total_steps": 64460, "loss": 0.2355, "lr": 2.022176341134638e-06, "epoch": 14.655600372323923, "percentage": 73.28, "elapsed_time": "1:27:29", "remaining_time": "0:31:54", "throughput": 5481.82, "total_tokens": 28774352} {"current_steps": 47240, "total_steps": 64460, "loss": 0.3106, "lr": 2.0210889264400635e-06, "epoch": 14.657151721998138, "percentage": 73.29, "elapsed_time": "1:27:29", "remaining_time": "0:31:53", "throughput": 5481.82, "total_tokens": 28776944} {"current_steps": 47245, "total_steps": 64460, "loss": 0.1393, "lr": 2.020001730134949e-06, "epoch": 14.658703071672354, "percentage": 73.29, "elapsed_time": "1:27:30", "remaining_time": "0:31:52", "throughput": 5481.92, "total_tokens": 28780304} {"current_steps": 47250, "total_steps": 64460, "loss": 0.1296, "lr": 2.0189147522989937e-06, "epoch": 14.660254421346572, "percentage": 73.3, "elapsed_time": "1:27:30", "remaining_time": "0:31:52", "throughput": 5482.09, "total_tokens": 28784688} {"current_steps": 47255, "total_steps": 64460, "loss": 0.1793, "lr": 2.0178279930118904e-06, "epoch": 14.661805771020788, "percentage": 73.31, "elapsed_time": "1:27:31", "remaining_time": "0:31:51", "throughput": 5482.12, "total_tokens": 28787504} {"current_steps": 47260, "total_steps": 64460, "loss": 0.1934, "lr": 2.0167414523533073e-06, "epoch": 14.663357120695004, "percentage": 73.32, "elapsed_time": "1:27:31", "remaining_time": "0:31:51", "throughput": 5482.09, "total_tokens": 28789840} {"current_steps": 47265, "total_steps": 64460, "loss": 0.2746, "lr": 2.015655130402905e-06, "epoch": 14.664908470369221, "percentage": 73.32, "elapsed_time": "1:27:32", "remaining_time": "0:31:50", "throughput": 5482.12, "total_tokens": 28792688} {"current_steps": 47270, "total_steps": 64460, "loss": 0.1694, "lr": 2.0145690272403195e-06, "epoch": 14.666459820043437, "percentage": 73.33, "elapsed_time": "1:27:32", "remaining_time": "0:31:50", "throughput": 5482.17, "total_tokens": 28795600} {"current_steps": 47275, "total_steps": 64460, "loss": 0.194, "lr": 2.013483142945179e-06, "epoch": 14.668011169717655, "percentage": 73.34, "elapsed_time": "1:27:33", "remaining_time": "0:31:49", "throughput": 5482.31, "total_tokens": 28799536} {"current_steps": 47280, "total_steps": 64460, "loss": 0.2282, "lr": 2.012397477597088e-06, "epoch": 14.66956251939187, "percentage": 73.35, "elapsed_time": "1:27:33", "remaining_time": "0:31:49", "throughput": 5482.37, "total_tokens": 28802768} {"current_steps": 47285, "total_steps": 64460, "loss": 0.2078, "lr": 2.01131203127564e-06, "epoch": 14.671113869066087, "percentage": 73.36, "elapsed_time": "1:27:34", "remaining_time": "0:31:48", "throughput": 5482.37, "total_tokens": 28805360} {"current_steps": 47290, "total_steps": 64460, "loss": 0.2166, "lr": 2.010226804060414e-06, "epoch": 14.672665218740304, "percentage": 73.36, "elapsed_time": "1:27:34", "remaining_time": "0:31:47", "throughput": 5482.34, "total_tokens": 28807824} {"current_steps": 47295, "total_steps": 64460, "loss": 0.2021, "lr": 2.0091417960309658e-06, "epoch": 14.67421656841452, "percentage": 73.37, "elapsed_time": "1:27:35", "remaining_time": "0:31:47", "throughput": 5482.36, "total_tokens": 28810640} {"current_steps": 47300, "total_steps": 64460, "loss": 0.1504, "lr": 2.008057007266842e-06, "epoch": 14.675767918088738, "percentage": 73.38, "elapsed_time": "1:27:35", "remaining_time": "0:31:46", "throughput": 5482.38, "total_tokens": 28813456} {"current_steps": 47305, "total_steps": 64460, "loss": 0.2074, "lr": 2.006972437847568e-06, "epoch": 14.677319267762954, "percentage": 73.39, "elapsed_time": "1:27:36", "remaining_time": "0:31:46", "throughput": 5482.35, "total_tokens": 28815856} {"current_steps": 47310, "total_steps": 64460, "loss": 0.2075, "lr": 2.0058880878526587e-06, "epoch": 14.67887061743717, "percentage": 73.39, "elapsed_time": "1:27:36", "remaining_time": "0:31:45", "throughput": 5482.44, "total_tokens": 28819056} {"current_steps": 47315, "total_steps": 64460, "loss": 0.2516, "lr": 2.004803957361607e-06, "epoch": 14.680421967111387, "percentage": 73.4, "elapsed_time": "1:27:37", "remaining_time": "0:31:44", "throughput": 5482.48, "total_tokens": 28821872} {"current_steps": 47320, "total_steps": 64460, "loss": 0.1723, "lr": 2.0037200464538945e-06, "epoch": 14.681973316785603, "percentage": 73.41, "elapsed_time": "1:27:37", "remaining_time": "0:31:44", "throughput": 5482.52, "total_tokens": 28824816} {"current_steps": 47325, "total_steps": 64460, "loss": 0.2094, "lr": 2.002636355208983e-06, "epoch": 14.683524666459821, "percentage": 73.42, "elapsed_time": "1:27:38", "remaining_time": "0:31:43", "throughput": 5482.51, "total_tokens": 28827504} {"current_steps": 47330, "total_steps": 64460, "loss": 0.1919, "lr": 2.001552883706321e-06, "epoch": 14.685076016134037, "percentage": 73.43, "elapsed_time": "1:27:38", "remaining_time": "0:31:43", "throughput": 5482.56, "total_tokens": 28830800} {"current_steps": 47335, "total_steps": 64460, "loss": 0.1783, "lr": 2.0004696320253395e-06, "epoch": 14.686627365808253, "percentage": 73.43, "elapsed_time": "1:27:39", "remaining_time": "0:31:42", "throughput": 5482.57, "total_tokens": 28833552} {"current_steps": 47340, "total_steps": 64460, "loss": 0.2505, "lr": 1.999386600245455e-06, "epoch": 14.68817871548247, "percentage": 73.44, "elapsed_time": "1:27:39", "remaining_time": "0:31:42", "throughput": 5482.58, "total_tokens": 28836464} {"current_steps": 47345, "total_steps": 64460, "loss": 0.1355, "lr": 1.9983037884460634e-06, "epoch": 14.689730065156686, "percentage": 73.45, "elapsed_time": "1:27:40", "remaining_time": "0:31:41", "throughput": 5482.63, "total_tokens": 28839632} {"current_steps": 47350, "total_steps": 64460, "loss": 0.16, "lr": 1.997221196706549e-06, "epoch": 14.691281414830902, "percentage": 73.46, "elapsed_time": "1:27:40", "remaining_time": "0:31:40", "throughput": 5482.63, "total_tokens": 28842448} {"current_steps": 47355, "total_steps": 64460, "loss": 0.2124, "lr": 1.9961388251062814e-06, "epoch": 14.69283276450512, "percentage": 73.46, "elapsed_time": "1:27:41", "remaining_time": "0:31:40", "throughput": 5482.66, "total_tokens": 28845200} {"current_steps": 47360, "total_steps": 64460, "loss": 0.2277, "lr": 1.9950566737246075e-06, "epoch": 14.694384114179336, "percentage": 73.47, "elapsed_time": "1:27:41", "remaining_time": "0:31:39", "throughput": 5482.77, "total_tokens": 28848720} {"current_steps": 47365, "total_steps": 64460, "loss": 0.2471, "lr": 1.9939747426408647e-06, "epoch": 14.695935463853553, "percentage": 73.48, "elapsed_time": "1:27:42", "remaining_time": "0:31:39", "throughput": 5482.8, "total_tokens": 28851568} {"current_steps": 47370, "total_steps": 64460, "loss": 0.1793, "lr": 1.9928930319343674e-06, "epoch": 14.69748681352777, "percentage": 73.49, "elapsed_time": "1:27:42", "remaining_time": "0:31:38", "throughput": 5482.79, "total_tokens": 28854032} {"current_steps": 47375, "total_steps": 64460, "loss": 0.224, "lr": 1.991811541684423e-06, "epoch": 14.699038163201985, "percentage": 73.5, "elapsed_time": "1:27:43", "remaining_time": "0:31:38", "throughput": 5482.84, "total_tokens": 28857424} {"current_steps": 47380, "total_steps": 64460, "loss": 0.193, "lr": 1.990730271970313e-06, "epoch": 14.700589512876203, "percentage": 73.5, "elapsed_time": "1:27:43", "remaining_time": "0:31:37", "throughput": 5482.83, "total_tokens": 28860080} {"current_steps": 47385, "total_steps": 64460, "loss": 0.1761, "lr": 1.989649222871311e-06, "epoch": 14.702140862550419, "percentage": 73.51, "elapsed_time": "1:27:44", "remaining_time": "0:31:36", "throughput": 5482.83, "total_tokens": 28862864} {"current_steps": 47390, "total_steps": 64460, "loss": 0.1567, "lr": 1.9885683944666667e-06, "epoch": 14.703692212224635, "percentage": 73.52, "elapsed_time": "1:27:44", "remaining_time": "0:31:36", "throughput": 5482.97, "total_tokens": 28867376} {"current_steps": 47395, "total_steps": 64460, "loss": 0.2212, "lr": 1.9874877868356217e-06, "epoch": 14.705243561898852, "percentage": 73.53, "elapsed_time": "1:27:45", "remaining_time": "0:31:35", "throughput": 5483.11, "total_tokens": 28871312} {"current_steps": 47400, "total_steps": 64460, "loss": 0.1377, "lr": 1.986407400057394e-06, "epoch": 14.706794911573068, "percentage": 73.53, "elapsed_time": "1:27:46", "remaining_time": "0:31:35", "throughput": 5483.22, "total_tokens": 28875216} {"current_steps": 47405, "total_steps": 64460, "loss": 0.2616, "lr": 1.98532723421119e-06, "epoch": 14.708346261247286, "percentage": 73.54, "elapsed_time": "1:27:46", "remaining_time": "0:31:34", "throughput": 5483.22, "total_tokens": 28877904} {"current_steps": 47410, "total_steps": 64460, "loss": 0.2909, "lr": 1.9842472893762003e-06, "epoch": 14.709897610921502, "percentage": 73.55, "elapsed_time": "1:27:47", "remaining_time": "0:31:34", "throughput": 5483.26, "total_tokens": 28880752} {"current_steps": 47415, "total_steps": 64460, "loss": 0.2014, "lr": 1.9831675656315947e-06, "epoch": 14.711448960595717, "percentage": 73.56, "elapsed_time": "1:27:47", "remaining_time": "0:31:33", "throughput": 5483.34, "total_tokens": 28883920} {"current_steps": 47420, "total_steps": 64460, "loss": 0.1993, "lr": 1.9820880630565327e-06, "epoch": 14.713000310269935, "percentage": 73.57, "elapsed_time": "1:27:48", "remaining_time": "0:31:33", "throughput": 5483.43, "total_tokens": 28887568} {"current_steps": 47425, "total_steps": 64460, "loss": 0.1677, "lr": 1.981008781730151e-06, "epoch": 14.714551659944151, "percentage": 73.57, "elapsed_time": "1:27:48", "remaining_time": "0:31:32", "throughput": 5483.43, "total_tokens": 28890256} {"current_steps": 47430, "total_steps": 64460, "loss": 0.1838, "lr": 1.979929721731578e-06, "epoch": 14.716103009618369, "percentage": 73.58, "elapsed_time": "1:27:49", "remaining_time": "0:31:31", "throughput": 5483.44, "total_tokens": 28892944} {"current_steps": 47435, "total_steps": 64460, "loss": 0.2247, "lr": 1.9788508831399176e-06, "epoch": 14.717654359292585, "percentage": 73.59, "elapsed_time": "1:27:49", "remaining_time": "0:31:31", "throughput": 5483.53, "total_tokens": 28896144} {"current_steps": 47440, "total_steps": 64460, "loss": 0.1408, "lr": 1.9777722660342654e-06, "epoch": 14.7192057089668, "percentage": 73.6, "elapsed_time": "1:27:50", "remaining_time": "0:31:30", "throughput": 5483.57, "total_tokens": 28899440} {"current_steps": 47445, "total_steps": 64460, "loss": 0.2606, "lr": 1.9766938704936924e-06, "epoch": 14.720757058641018, "percentage": 73.6, "elapsed_time": "1:27:50", "remaining_time": "0:31:30", "throughput": 5483.5, "total_tokens": 28901680} {"current_steps": 47450, "total_steps": 64460, "loss": 0.181, "lr": 1.975615696597261e-06, "epoch": 14.722308408315234, "percentage": 73.61, "elapsed_time": "1:27:51", "remaining_time": "0:31:29", "throughput": 5483.55, "total_tokens": 28904720} {"current_steps": 47455, "total_steps": 64460, "loss": 0.1898, "lr": 1.974537744424013e-06, "epoch": 14.723859757989452, "percentage": 73.62, "elapsed_time": "1:27:51", "remaining_time": "0:31:29", "throughput": 5483.48, "total_tokens": 28907184} {"current_steps": 47460, "total_steps": 64460, "loss": 0.157, "lr": 1.973460014052976e-06, "epoch": 14.725411107663668, "percentage": 73.63, "elapsed_time": "1:27:52", "remaining_time": "0:31:28", "throughput": 5483.46, "total_tokens": 28909840} {"current_steps": 47465, "total_steps": 64460, "loss": 0.1795, "lr": 1.9723825055631574e-06, "epoch": 14.726962457337883, "percentage": 73.63, "elapsed_time": "1:27:52", "remaining_time": "0:31:27", "throughput": 5483.48, "total_tokens": 28912560} {"current_steps": 47470, "total_steps": 64460, "loss": 0.245, "lr": 1.971305219033554e-06, "epoch": 14.728513807012101, "percentage": 73.64, "elapsed_time": "1:27:53", "remaining_time": "0:31:27", "throughput": 5483.38, "total_tokens": 28914832} {"current_steps": 47475, "total_steps": 64460, "loss": 0.2225, "lr": 1.970228154543145e-06, "epoch": 14.730065156686317, "percentage": 73.65, "elapsed_time": "1:27:53", "remaining_time": "0:31:26", "throughput": 5483.37, "total_tokens": 28917584} {"current_steps": 47480, "total_steps": 64460, "loss": 0.1761, "lr": 1.969151312170888e-06, "epoch": 14.731616506360533, "percentage": 73.66, "elapsed_time": "1:27:54", "remaining_time": "0:31:26", "throughput": 5483.39, "total_tokens": 28920208} {"current_steps": 47485, "total_steps": 64460, "loss": 0.1596, "lr": 1.9680746919957326e-06, "epoch": 14.73316785603475, "percentage": 73.67, "elapsed_time": "1:27:54", "remaining_time": "0:31:25", "throughput": 5483.45, "total_tokens": 28923280} {"current_steps": 47490, "total_steps": 64460, "loss": 0.2151, "lr": 1.9669982940966036e-06, "epoch": 14.734719205708966, "percentage": 73.67, "elapsed_time": "1:27:55", "remaining_time": "0:31:25", "throughput": 5483.51, "total_tokens": 28926416} {"current_steps": 47495, "total_steps": 64460, "loss": 0.2138, "lr": 1.9659221185524176e-06, "epoch": 14.736270555383184, "percentage": 73.68, "elapsed_time": "1:27:55", "remaining_time": "0:31:24", "throughput": 5483.55, "total_tokens": 28929616} {"current_steps": 47500, "total_steps": 64460, "loss": 0.2029, "lr": 1.9648461654420676e-06, "epoch": 14.7378219050574, "percentage": 73.69, "elapsed_time": "1:27:56", "remaining_time": "0:31:23", "throughput": 5483.59, "total_tokens": 28932464} {"current_steps": 47505, "total_steps": 64460, "loss": 0.1739, "lr": 1.963770434844437e-06, "epoch": 14.739373254731616, "percentage": 73.7, "elapsed_time": "1:27:56", "remaining_time": "0:31:23", "throughput": 5483.61, "total_tokens": 28935152} {"current_steps": 47510, "total_steps": 64460, "loss": 0.1347, "lr": 1.962694926838386e-06, "epoch": 14.740924604405834, "percentage": 73.7, "elapsed_time": "1:27:57", "remaining_time": "0:31:22", "throughput": 5483.69, "total_tokens": 28938256} {"current_steps": 47515, "total_steps": 64460, "loss": 0.1219, "lr": 1.9616196415027657e-06, "epoch": 14.74247595408005, "percentage": 73.71, "elapsed_time": "1:27:57", "remaining_time": "0:31:22", "throughput": 5483.75, "total_tokens": 28941552} {"current_steps": 47520, "total_steps": 64460, "loss": 0.1728, "lr": 1.9605445789164035e-06, "epoch": 14.744027303754265, "percentage": 73.72, "elapsed_time": "1:27:58", "remaining_time": "0:31:21", "throughput": 5483.73, "total_tokens": 28943920} {"current_steps": 47525, "total_steps": 64460, "loss": 0.2599, "lr": 1.959469739158116e-06, "epoch": 14.745578653428483, "percentage": 73.73, "elapsed_time": "1:27:58", "remaining_time": "0:31:21", "throughput": 5483.98, "total_tokens": 28949456} {"current_steps": 47530, "total_steps": 64460, "loss": 0.173, "lr": 1.9583951223067043e-06, "epoch": 14.747130003102699, "percentage": 73.74, "elapsed_time": "1:27:59", "remaining_time": "0:31:20", "throughput": 5483.99, "total_tokens": 28952112} {"current_steps": 47535, "total_steps": 64460, "loss": 0.2241, "lr": 1.9573207284409464e-06, "epoch": 14.748681352776916, "percentage": 73.74, "elapsed_time": "1:27:59", "remaining_time": "0:31:19", "throughput": 5484.05, "total_tokens": 28955216} {"current_steps": 47540, "total_steps": 64460, "loss": 0.2041, "lr": 1.9562465576396113e-06, "epoch": 14.750232702451132, "percentage": 73.75, "elapsed_time": "1:28:00", "remaining_time": "0:31:19", "throughput": 5484.03, "total_tokens": 28957744} {"current_steps": 47545, "total_steps": 64460, "loss": 0.1363, "lr": 1.9551726099814448e-06, "epoch": 14.751784052125348, "percentage": 73.76, "elapsed_time": "1:28:01", "remaining_time": "0:31:18", "throughput": 5484.14, "total_tokens": 28961840} {"current_steps": 47550, "total_steps": 64460, "loss": 0.2029, "lr": 1.9540988855451844e-06, "epoch": 14.753335401799566, "percentage": 73.77, "elapsed_time": "1:28:01", "remaining_time": "0:31:18", "throughput": 5484.1, "total_tokens": 28964464} {"current_steps": 47555, "total_steps": 64460, "loss": 0.2154, "lr": 1.9530253844095425e-06, "epoch": 14.754886751473782, "percentage": 73.77, "elapsed_time": "1:28:02", "remaining_time": "0:31:17", "throughput": 5484.15, "total_tokens": 28967440} {"current_steps": 47560, "total_steps": 64460, "loss": 0.248, "lr": 1.9519521066532236e-06, "epoch": 14.756438101148, "percentage": 73.78, "elapsed_time": "1:28:02", "remaining_time": "0:31:17", "throughput": 5484.18, "total_tokens": 28970288} {"current_steps": 47565, "total_steps": 64460, "loss": 0.1521, "lr": 1.9508790523549077e-06, "epoch": 14.757989450822215, "percentage": 73.79, "elapsed_time": "1:28:03", "remaining_time": "0:31:16", "throughput": 5484.17, "total_tokens": 28972944} {"current_steps": 47570, "total_steps": 64460, "loss": 0.2171, "lr": 1.949806221593266e-06, "epoch": 14.759540800496431, "percentage": 73.8, "elapsed_time": "1:28:03", "remaining_time": "0:31:15", "throughput": 5484.16, "total_tokens": 28975952} {"current_steps": 47575, "total_steps": 64460, "loss": 0.2034, "lr": 1.948733614446946e-06, "epoch": 14.761092150170649, "percentage": 73.81, "elapsed_time": "1:28:04", "remaining_time": "0:31:15", "throughput": 5484.24, "total_tokens": 28979888} {"current_steps": 47580, "total_steps": 64460, "loss": 0.1514, "lr": 1.9476612309945863e-06, "epoch": 14.762643499844865, "percentage": 73.81, "elapsed_time": "1:28:04", "remaining_time": "0:31:14", "throughput": 5484.3, "total_tokens": 28983152} {"current_steps": 47585, "total_steps": 64460, "loss": 0.228, "lr": 1.9465890713148023e-06, "epoch": 14.764194849519082, "percentage": 73.82, "elapsed_time": "1:28:05", "remaining_time": "0:31:14", "throughput": 5484.29, "total_tokens": 28985712} {"current_steps": 47590, "total_steps": 64460, "loss": 0.1644, "lr": 1.9455171354861963e-06, "epoch": 14.765746199193298, "percentage": 73.83, "elapsed_time": "1:28:05", "remaining_time": "0:31:13", "throughput": 5484.3, "total_tokens": 28988752} {"current_steps": 47595, "total_steps": 64460, "loss": 0.1764, "lr": 1.9444454235873573e-06, "epoch": 14.767297548867514, "percentage": 73.84, "elapsed_time": "1:28:06", "remaining_time": "0:31:13", "throughput": 5484.37, "total_tokens": 28991952} {"current_steps": 47600, "total_steps": 64460, "loss": 0.1855, "lr": 1.9433739356968497e-06, "epoch": 14.768848898541732, "percentage": 73.84, "elapsed_time": "1:28:06", "remaining_time": "0:31:12", "throughput": 5484.43, "total_tokens": 28995248} {"current_steps": 47605, "total_steps": 64460, "loss": 0.1853, "lr": 1.9423026718932298e-06, "epoch": 14.770400248215948, "percentage": 73.85, "elapsed_time": "1:28:07", "remaining_time": "0:31:12", "throughput": 5484.47, "total_tokens": 28998320} {"current_steps": 47610, "total_steps": 64460, "loss": 0.1884, "lr": 1.9412316322550316e-06, "epoch": 14.771951597890164, "percentage": 73.86, "elapsed_time": "1:28:07", "remaining_time": "0:31:11", "throughput": 5484.59, "total_tokens": 29002000} {"current_steps": 47615, "total_steps": 64460, "loss": 0.1684, "lr": 1.940160816860777e-06, "epoch": 14.773502947564381, "percentage": 73.87, "elapsed_time": "1:28:08", "remaining_time": "0:31:10", "throughput": 5484.64, "total_tokens": 29005296} {"current_steps": 47620, "total_steps": 64460, "loss": 0.238, "lr": 1.9390902257889678e-06, "epoch": 14.775054297238597, "percentage": 73.88, "elapsed_time": "1:28:08", "remaining_time": "0:31:10", "throughput": 5484.66, "total_tokens": 29008048} {"current_steps": 47625, "total_steps": 64460, "loss": 0.1868, "lr": 1.9380198591180925e-06, "epoch": 14.776605646912815, "percentage": 73.88, "elapsed_time": "1:28:09", "remaining_time": "0:31:09", "throughput": 5484.67, "total_tokens": 29011024} {"current_steps": 47630, "total_steps": 64460, "loss": 0.1834, "lr": 1.9369497169266193e-06, "epoch": 14.77815699658703, "percentage": 73.89, "elapsed_time": "1:28:09", "remaining_time": "0:31:09", "throughput": 5484.68, "total_tokens": 29013872} {"current_steps": 47635, "total_steps": 64460, "loss": 0.1937, "lr": 1.9358797992930057e-06, "epoch": 14.779708346261247, "percentage": 73.9, "elapsed_time": "1:28:10", "remaining_time": "0:31:08", "throughput": 5484.76, "total_tokens": 29017360} {"current_steps": 47640, "total_steps": 64460, "loss": 0.1861, "lr": 1.9348101062956853e-06, "epoch": 14.781259695935464, "percentage": 73.91, "elapsed_time": "1:28:11", "remaining_time": "0:31:08", "throughput": 5484.83, "total_tokens": 29020528} {"current_steps": 47645, "total_steps": 64460, "loss": 0.208, "lr": 1.933740638013082e-06, "epoch": 14.78281104560968, "percentage": 73.91, "elapsed_time": "1:28:11", "remaining_time": "0:31:07", "throughput": 5484.77, "total_tokens": 29023056} {"current_steps": 47650, "total_steps": 64460, "loss": 0.1363, "lr": 1.9326713945235993e-06, "epoch": 14.784362395283896, "percentage": 73.92, "elapsed_time": "1:28:12", "remaining_time": "0:31:06", "throughput": 5484.71, "total_tokens": 29025520} {"current_steps": 47655, "total_steps": 64460, "loss": 0.1645, "lr": 1.931602375905628e-06, "epoch": 14.785913744958114, "percentage": 73.93, "elapsed_time": "1:28:12", "remaining_time": "0:31:06", "throughput": 5484.71, "total_tokens": 29028336} {"current_steps": 47660, "total_steps": 64460, "loss": 0.197, "lr": 1.930533582237536e-06, "epoch": 14.78746509463233, "percentage": 73.94, "elapsed_time": "1:28:13", "remaining_time": "0:31:05", "throughput": 5484.76, "total_tokens": 29031568} {"current_steps": 47665, "total_steps": 64460, "loss": 0.1115, "lr": 1.9294650135976816e-06, "epoch": 14.789016444306547, "percentage": 73.95, "elapsed_time": "1:28:13", "remaining_time": "0:31:05", "throughput": 5484.84, "total_tokens": 29034736} {"current_steps": 47670, "total_steps": 64460, "loss": 0.168, "lr": 1.9283966700644012e-06, "epoch": 14.790567793980763, "percentage": 73.95, "elapsed_time": "1:28:14", "remaining_time": "0:31:04", "throughput": 5484.68, "total_tokens": 29036816} {"current_steps": 47675, "total_steps": 64460, "loss": 0.1708, "lr": 1.9273285517160178e-06, "epoch": 14.792119143654979, "percentage": 73.96, "elapsed_time": "1:28:14", "remaining_time": "0:31:04", "throughput": 5484.67, "total_tokens": 29039632} {"current_steps": 47680, "total_steps": 64460, "loss": 0.2813, "lr": 1.9262606586308395e-06, "epoch": 14.793670493329197, "percentage": 73.97, "elapsed_time": "1:28:15", "remaining_time": "0:31:03", "throughput": 5484.73, "total_tokens": 29042704} {"current_steps": 47685, "total_steps": 64460, "loss": 0.2038, "lr": 1.9251929908871514e-06, "epoch": 14.795221843003413, "percentage": 73.98, "elapsed_time": "1:28:15", "remaining_time": "0:31:02", "throughput": 5484.7, "total_tokens": 29045616} {"current_steps": 47690, "total_steps": 64460, "loss": 0.1596, "lr": 1.9241255485632306e-06, "epoch": 14.79677319267763, "percentage": 73.98, "elapsed_time": "1:28:16", "remaining_time": "0:31:02", "throughput": 5484.67, "total_tokens": 29048368} {"current_steps": 47695, "total_steps": 64460, "loss": 0.2457, "lr": 1.923058331737328e-06, "epoch": 14.798324542351846, "percentage": 73.99, "elapsed_time": "1:28:16", "remaining_time": "0:31:01", "throughput": 5484.59, "total_tokens": 29050832} {"current_steps": 47700, "total_steps": 64460, "loss": 0.1505, "lr": 1.921991340487689e-06, "epoch": 14.799875892026062, "percentage": 74.0, "elapsed_time": "1:28:17", "remaining_time": "0:31:01", "throughput": 5484.69, "total_tokens": 29054128} {"current_steps": 47705, "total_steps": 64460, "loss": 0.1717, "lr": 1.920924574892531e-06, "epoch": 14.80142724170028, "percentage": 74.01, "elapsed_time": "1:28:17", "remaining_time": "0:31:00", "throughput": 5484.67, "total_tokens": 29056688} {"current_steps": 47710, "total_steps": 64460, "loss": 0.3282, "lr": 1.9198580350300662e-06, "epoch": 14.802978591374496, "percentage": 74.01, "elapsed_time": "1:28:18", "remaining_time": "0:31:00", "throughput": 5484.75, "total_tokens": 29060496} {"current_steps": 47715, "total_steps": 64460, "loss": 0.1834, "lr": 1.918791720978479e-06, "epoch": 14.804529941048713, "percentage": 74.02, "elapsed_time": "1:28:18", "remaining_time": "0:30:59", "throughput": 5484.78, "total_tokens": 29063312} {"current_steps": 47720, "total_steps": 64460, "loss": 0.228, "lr": 1.917725632815948e-06, "epoch": 14.806081290722929, "percentage": 74.03, "elapsed_time": "1:28:19", "remaining_time": "0:30:59", "throughput": 5484.83, "total_tokens": 29066352} {"current_steps": 47725, "total_steps": 64460, "loss": 0.1923, "lr": 1.916659770620626e-06, "epoch": 14.807632640397145, "percentage": 74.04, "elapsed_time": "1:28:19", "remaining_time": "0:30:58", "throughput": 5484.84, "total_tokens": 29069200} {"current_steps": 47730, "total_steps": 64460, "loss": 0.1686, "lr": 1.9155941344706547e-06, "epoch": 14.809183990071363, "percentage": 74.05, "elapsed_time": "1:28:20", "remaining_time": "0:30:57", "throughput": 5484.81, "total_tokens": 29071728} {"current_steps": 47735, "total_steps": 64460, "loss": 0.2078, "lr": 1.91452872444416e-06, "epoch": 14.810735339745579, "percentage": 74.05, "elapsed_time": "1:28:20", "remaining_time": "0:30:57", "throughput": 5484.8, "total_tokens": 29074416} {"current_steps": 47740, "total_steps": 64460, "loss": 0.1123, "lr": 1.9134635406192453e-06, "epoch": 14.812286689419794, "percentage": 74.06, "elapsed_time": "1:28:21", "remaining_time": "0:30:56", "throughput": 5484.81, "total_tokens": 29077200} {"current_steps": 47745, "total_steps": 64460, "loss": 0.2195, "lr": 1.9123985830740054e-06, "epoch": 14.813838039094012, "percentage": 74.07, "elapsed_time": "1:28:21", "remaining_time": "0:30:56", "throughput": 5484.72, "total_tokens": 29079440} {"current_steps": 47750, "total_steps": 64460, "loss": 0.2603, "lr": 1.91133385188651e-06, "epoch": 14.815389388768228, "percentage": 74.08, "elapsed_time": "1:28:22", "remaining_time": "0:30:55", "throughput": 5484.71, "total_tokens": 29082224} {"current_steps": 47755, "total_steps": 64460, "loss": 0.213, "lr": 1.9102693471348206e-06, "epoch": 14.816940738442446, "percentage": 74.08, "elapsed_time": "1:28:22", "remaining_time": "0:30:55", "throughput": 5484.72, "total_tokens": 29085136} {"current_steps": 47760, "total_steps": 64460, "loss": 0.2413, "lr": 1.9092050688969736e-06, "epoch": 14.818492088116662, "percentage": 74.09, "elapsed_time": "1:28:23", "remaining_time": "0:30:54", "throughput": 5484.73, "total_tokens": 29087856} {"current_steps": 47765, "total_steps": 64460, "loss": 0.3179, "lr": 1.9081410172509975e-06, "epoch": 14.820043437790877, "percentage": 74.1, "elapsed_time": "1:28:23", "remaining_time": "0:30:53", "throughput": 5484.71, "total_tokens": 29090416} {"current_steps": 47770, "total_steps": 64460, "loss": 0.1733, "lr": 1.9070771922748965e-06, "epoch": 14.821594787465095, "percentage": 74.11, "elapsed_time": "1:28:24", "remaining_time": "0:30:53", "throughput": 5484.73, "total_tokens": 29093328} {"current_steps": 47775, "total_steps": 64460, "loss": 0.2452, "lr": 1.9060135940466645e-06, "epoch": 14.823146137139311, "percentage": 74.12, "elapsed_time": "1:28:24", "remaining_time": "0:30:52", "throughput": 5484.7, "total_tokens": 29096112} {"current_steps": 47780, "total_steps": 64460, "loss": 0.176, "lr": 1.9049502226442724e-06, "epoch": 14.824697486813527, "percentage": 74.12, "elapsed_time": "1:28:25", "remaining_time": "0:30:52", "throughput": 5484.79, "total_tokens": 29099664} {"current_steps": 47785, "total_steps": 64460, "loss": 0.224, "lr": 1.903887078145682e-06, "epoch": 14.826248836487744, "percentage": 74.13, "elapsed_time": "1:28:26", "remaining_time": "0:30:51", "throughput": 5484.69, "total_tokens": 29101968} {"current_steps": 47790, "total_steps": 64460, "loss": 0.1703, "lr": 1.90282416062883e-06, "epoch": 14.82780018616196, "percentage": 74.14, "elapsed_time": "1:28:26", "remaining_time": "0:30:51", "throughput": 5484.68, "total_tokens": 29104976} {"current_steps": 47795, "total_steps": 64460, "loss": 0.1994, "lr": 1.9017614701716435e-06, "epoch": 14.829351535836178, "percentage": 74.15, "elapsed_time": "1:28:27", "remaining_time": "0:30:50", "throughput": 5484.63, "total_tokens": 29107440} {"current_steps": 47800, "total_steps": 64460, "loss": 0.1426, "lr": 1.9006990068520314e-06, "epoch": 14.830902885510394, "percentage": 74.15, "elapsed_time": "1:28:27", "remaining_time": "0:30:49", "throughput": 5484.63, "total_tokens": 29110256} {"current_steps": 47805, "total_steps": 64460, "loss": 0.2328, "lr": 1.8996367707478814e-06, "epoch": 14.83245423518461, "percentage": 74.16, "elapsed_time": "1:28:28", "remaining_time": "0:30:49", "throughput": 5484.61, "total_tokens": 29113520} {"current_steps": 47810, "total_steps": 64460, "loss": 0.2004, "lr": 1.898574761937072e-06, "epoch": 14.834005584858827, "percentage": 74.17, "elapsed_time": "1:28:29", "remaining_time": "0:30:48", "throughput": 5484.67, "total_tokens": 29118192} {"current_steps": 47815, "total_steps": 64460, "loss": 0.1856, "lr": 1.8975129804974569e-06, "epoch": 14.835556934533043, "percentage": 74.18, "elapsed_time": "1:28:29", "remaining_time": "0:30:48", "throughput": 5484.64, "total_tokens": 29120784} {"current_steps": 47820, "total_steps": 64460, "loss": 0.2252, "lr": 1.8964514265068812e-06, "epoch": 14.837108284207261, "percentage": 74.19, "elapsed_time": "1:28:30", "remaining_time": "0:30:47", "throughput": 5484.59, "total_tokens": 29123248} {"current_steps": 47825, "total_steps": 64460, "loss": 0.155, "lr": 1.8953901000431656e-06, "epoch": 14.838659633881477, "percentage": 74.19, "elapsed_time": "1:28:30", "remaining_time": "0:30:47", "throughput": 5484.63, "total_tokens": 29126352} {"current_steps": 47830, "total_steps": 64460, "loss": 0.1407, "lr": 1.894329001184122e-06, "epoch": 14.840210983555693, "percentage": 74.2, "elapsed_time": "1:28:31", "remaining_time": "0:30:46", "throughput": 5484.55, "total_tokens": 29128784} {"current_steps": 47835, "total_steps": 64460, "loss": 0.2023, "lr": 1.8932681300075366e-06, "epoch": 14.84176233322991, "percentage": 74.21, "elapsed_time": "1:28:31", "remaining_time": "0:30:46", "throughput": 5484.54, "total_tokens": 29131632} {"current_steps": 47840, "total_steps": 64460, "loss": 0.1206, "lr": 1.8922074865911889e-06, "epoch": 14.843313682904126, "percentage": 74.22, "elapsed_time": "1:28:32", "remaining_time": "0:30:45", "throughput": 5484.5, "total_tokens": 29134224} {"current_steps": 47845, "total_steps": 64460, "loss": 0.2362, "lr": 1.891147071012832e-06, "epoch": 14.844865032578344, "percentage": 74.22, "elapsed_time": "1:28:32", "remaining_time": "0:30:44", "throughput": 5484.47, "total_tokens": 29136752} {"current_steps": 47850, "total_steps": 64460, "loss": 0.1861, "lr": 1.8900868833502095e-06, "epoch": 14.84641638225256, "percentage": 74.23, "elapsed_time": "1:28:33", "remaining_time": "0:30:44", "throughput": 5484.51, "total_tokens": 29139632} {"current_steps": 47855, "total_steps": 64460, "loss": 0.1863, "lr": 1.889026923681047e-06, "epoch": 14.847967731926776, "percentage": 74.24, "elapsed_time": "1:28:33", "remaining_time": "0:30:43", "throughput": 5484.56, "total_tokens": 29143152} {"current_steps": 47860, "total_steps": 64460, "loss": 0.269, "lr": 1.887967192083049e-06, "epoch": 14.849519081600993, "percentage": 74.25, "elapsed_time": "1:28:34", "remaining_time": "0:30:43", "throughput": 5484.63, "total_tokens": 29146608} {"current_steps": 47865, "total_steps": 64460, "loss": 0.1755, "lr": 1.886907688633909e-06, "epoch": 14.85107043127521, "percentage": 74.26, "elapsed_time": "1:28:34", "remaining_time": "0:30:42", "throughput": 5484.67, "total_tokens": 29150192} {"current_steps": 47870, "total_steps": 64460, "loss": 0.182, "lr": 1.885848413411298e-06, "epoch": 14.852621780949425, "percentage": 74.26, "elapsed_time": "1:28:35", "remaining_time": "0:30:42", "throughput": 5484.7, "total_tokens": 29153456} {"current_steps": 47875, "total_steps": 64460, "loss": 0.1773, "lr": 1.884789366492878e-06, "epoch": 14.854173130623643, "percentage": 74.27, "elapsed_time": "1:28:36", "remaining_time": "0:30:41", "throughput": 5484.82, "total_tokens": 29157680} {"current_steps": 47880, "total_steps": 64460, "loss": 0.179, "lr": 1.8837305479562845e-06, "epoch": 14.855724480297859, "percentage": 74.28, "elapsed_time": "1:28:36", "remaining_time": "0:30:41", "throughput": 5484.76, "total_tokens": 29160400} {"current_steps": 47885, "total_steps": 64460, "loss": 0.2071, "lr": 1.8826719578791463e-06, "epoch": 14.857275829972076, "percentage": 74.29, "elapsed_time": "1:28:37", "remaining_time": "0:30:40", "throughput": 5484.69, "total_tokens": 29162832} {"current_steps": 47890, "total_steps": 64460, "loss": 0.202, "lr": 1.8816135963390663e-06, "epoch": 14.858827179646292, "percentage": 74.29, "elapsed_time": "1:28:37", "remaining_time": "0:30:39", "throughput": 5484.81, "total_tokens": 29167120} {"current_steps": 47895, "total_steps": 64460, "loss": 0.2479, "lr": 1.8805554634136385e-06, "epoch": 14.860378529320508, "percentage": 74.3, "elapsed_time": "1:28:38", "remaining_time": "0:30:39", "throughput": 5484.85, "total_tokens": 29170576} {"current_steps": 47900, "total_steps": 64460, "loss": 0.1794, "lr": 1.8794975591804332e-06, "epoch": 14.861929878994726, "percentage": 74.31, "elapsed_time": "1:28:38", "remaining_time": "0:30:38", "throughput": 5484.86, "total_tokens": 29173584} {"current_steps": 47905, "total_steps": 64460, "loss": 0.1496, "lr": 1.8784398837170109e-06, "epoch": 14.863481228668942, "percentage": 74.32, "elapsed_time": "1:28:39", "remaining_time": "0:30:38", "throughput": 5484.99, "total_tokens": 29177360} {"current_steps": 47910, "total_steps": 64460, "loss": 0.2425, "lr": 1.8773824371009087e-06, "epoch": 14.865032578343158, "percentage": 74.33, "elapsed_time": "1:28:40", "remaining_time": "0:30:37", "throughput": 5485.02, "total_tokens": 29180368} {"current_steps": 47915, "total_steps": 64460, "loss": 0.2029, "lr": 1.8763252194096504e-06, "epoch": 14.866583928017375, "percentage": 74.33, "elapsed_time": "1:28:40", "remaining_time": "0:30:37", "throughput": 5485.02, "total_tokens": 29183312} {"current_steps": 47920, "total_steps": 64460, "loss": 0.1627, "lr": 1.8752682307207454e-06, "epoch": 14.868135277691591, "percentage": 74.34, "elapsed_time": "1:28:41", "remaining_time": "0:30:36", "throughput": 5484.95, "total_tokens": 29185552} {"current_steps": 47925, "total_steps": 64460, "loss": 0.2372, "lr": 1.8742114711116798e-06, "epoch": 14.869686627365809, "percentage": 74.35, "elapsed_time": "1:28:41", "remaining_time": "0:30:36", "throughput": 5484.93, "total_tokens": 29188144} {"current_steps": 47930, "total_steps": 64460, "loss": 0.2716, "lr": 1.8731549406599303e-06, "epoch": 14.871237977040025, "percentage": 74.36, "elapsed_time": "1:28:42", "remaining_time": "0:30:35", "throughput": 5485.03, "total_tokens": 29191632} {"current_steps": 47935, "total_steps": 64460, "loss": 0.1874, "lr": 1.8720986394429485e-06, "epoch": 14.87278932671424, "percentage": 74.36, "elapsed_time": "1:28:42", "remaining_time": "0:30:34", "throughput": 5484.96, "total_tokens": 29194032} {"current_steps": 47940, "total_steps": 64460, "loss": 0.2166, "lr": 1.8710425675381788e-06, "epoch": 14.874340676388458, "percentage": 74.37, "elapsed_time": "1:28:43", "remaining_time": "0:30:34", "throughput": 5484.95, "total_tokens": 29196720} {"current_steps": 47945, "total_steps": 64460, "loss": 0.1525, "lr": 1.8699867250230392e-06, "epoch": 14.875892026062674, "percentage": 74.38, "elapsed_time": "1:28:43", "remaining_time": "0:30:33", "throughput": 5485.07, "total_tokens": 29201808} {"current_steps": 47950, "total_steps": 64460, "loss": 0.1417, "lr": 1.8689311119749393e-06, "epoch": 14.877443375736892, "percentage": 74.39, "elapsed_time": "1:28:44", "remaining_time": "0:30:33", "throughput": 5485.14, "total_tokens": 29205072} {"current_steps": 47955, "total_steps": 64460, "loss": 0.155, "lr": 1.8678757284712646e-06, "epoch": 14.878994725411108, "percentage": 74.39, "elapsed_time": "1:28:44", "remaining_time": "0:30:32", "throughput": 5485.09, "total_tokens": 29207568} {"current_steps": 47960, "total_steps": 64460, "loss": 0.2251, "lr": 1.8668205745893909e-06, "epoch": 14.880546075085324, "percentage": 74.4, "elapsed_time": "1:28:45", "remaining_time": "0:30:32", "throughput": 5485.1, "total_tokens": 29210256} {"current_steps": 47965, "total_steps": 64460, "loss": 0.1686, "lr": 1.865765650406669e-06, "epoch": 14.882097424759541, "percentage": 74.41, "elapsed_time": "1:28:46", "remaining_time": "0:30:31", "throughput": 5485.23, "total_tokens": 29214512} {"current_steps": 47970, "total_steps": 64460, "loss": 0.2166, "lr": 1.8647109560004422e-06, "epoch": 14.883648774433757, "percentage": 74.42, "elapsed_time": "1:28:46", "remaining_time": "0:30:31", "throughput": 5485.26, "total_tokens": 29217424} {"current_steps": 47975, "total_steps": 64460, "loss": 0.1604, "lr": 1.8636564914480282e-06, "epoch": 14.885200124107975, "percentage": 74.43, "elapsed_time": "1:28:47", "remaining_time": "0:30:30", "throughput": 5485.27, "total_tokens": 29220272} {"current_steps": 47980, "total_steps": 64460, "loss": 0.1774, "lr": 1.8626022568267326e-06, "epoch": 14.88675147378219, "percentage": 74.43, "elapsed_time": "1:28:47", "remaining_time": "0:30:29", "throughput": 5485.28, "total_tokens": 29223152} {"current_steps": 47985, "total_steps": 64460, "loss": 0.2501, "lr": 1.8615482522138455e-06, "epoch": 14.888302823456407, "percentage": 74.44, "elapsed_time": "1:28:48", "remaining_time": "0:30:29", "throughput": 5485.34, "total_tokens": 29226128} {"current_steps": 47990, "total_steps": 64460, "loss": 0.185, "lr": 1.8604944776866352e-06, "epoch": 14.889854173130624, "percentage": 74.45, "elapsed_time": "1:28:48", "remaining_time": "0:30:28", "throughput": 5485.43, "total_tokens": 29229744} {"current_steps": 47995, "total_steps": 64460, "loss": 0.1761, "lr": 1.859440933322359e-06, "epoch": 14.89140552280484, "percentage": 74.46, "elapsed_time": "1:28:49", "remaining_time": "0:30:28", "throughput": 5485.62, "total_tokens": 29234384} {"current_steps": 48000, "total_steps": 64460, "loss": 0.198, "lr": 1.8583876191982497e-06, "epoch": 14.892956872479056, "percentage": 74.46, "elapsed_time": "1:28:49", "remaining_time": "0:30:27", "throughput": 5485.53, "total_tokens": 29236848} {"current_steps": 48005, "total_steps": 64460, "loss": 0.2419, "lr": 1.8573345353915323e-06, "epoch": 14.894508222153274, "percentage": 74.47, "elapsed_time": "1:28:50", "remaining_time": "0:30:27", "throughput": 5485.69, "total_tokens": 29241648} {"current_steps": 48010, "total_steps": 64460, "loss": 0.2396, "lr": 1.856281681979406e-06, "epoch": 14.89605957182749, "percentage": 74.48, "elapsed_time": "1:28:51", "remaining_time": "0:30:26", "throughput": 5485.75, "total_tokens": 29244720} {"current_steps": 48015, "total_steps": 64460, "loss": 0.1437, "lr": 1.855229059039062e-06, "epoch": 14.897610921501707, "percentage": 74.49, "elapsed_time": "1:28:51", "remaining_time": "0:30:26", "throughput": 5485.93, "total_tokens": 29249488} {"current_steps": 48020, "total_steps": 64460, "loss": 0.184, "lr": 1.8541766666476658e-06, "epoch": 14.899162271175923, "percentage": 74.5, "elapsed_time": "1:28:52", "remaining_time": "0:30:25", "throughput": 5485.96, "total_tokens": 29252592} {"current_steps": 48025, "total_steps": 64460, "loss": 0.1767, "lr": 1.8531245048823731e-06, "epoch": 14.900713620850139, "percentage": 74.5, "elapsed_time": "1:28:52", "remaining_time": "0:30:24", "throughput": 5485.99, "total_tokens": 29255440} {"current_steps": 48030, "total_steps": 64460, "loss": 0.2323, "lr": 1.8520725738203177e-06, "epoch": 14.902264970524357, "percentage": 74.51, "elapsed_time": "1:28:53", "remaining_time": "0:30:24", "throughput": 5485.92, "total_tokens": 29257808} {"current_steps": 48035, "total_steps": 64460, "loss": 0.1408, "lr": 1.8510208735386193e-06, "epoch": 14.903816320198572, "percentage": 74.52, "elapsed_time": "1:28:53", "remaining_time": "0:30:23", "throughput": 5485.9, "total_tokens": 29260368} {"current_steps": 48040, "total_steps": 64460, "loss": 0.1949, "lr": 1.8499694041143823e-06, "epoch": 14.905367669872788, "percentage": 74.53, "elapsed_time": "1:28:54", "remaining_time": "0:30:23", "throughput": 5485.8, "total_tokens": 29262608} {"current_steps": 48045, "total_steps": 64460, "loss": 0.2553, "lr": 1.848918165624688e-06, "epoch": 14.906919019547006, "percentage": 74.53, "elapsed_time": "1:28:54", "remaining_time": "0:30:22", "throughput": 5485.73, "total_tokens": 29265200} {"current_steps": 48050, "total_steps": 64460, "loss": 0.1899, "lr": 1.8478671581466085e-06, "epoch": 14.908470369221222, "percentage": 74.54, "elapsed_time": "1:28:55", "remaining_time": "0:30:22", "throughput": 5485.77, "total_tokens": 29268144} {"current_steps": 48055, "total_steps": 64460, "loss": 0.1737, "lr": 1.8468163817571916e-06, "epoch": 14.91002171889544, "percentage": 74.55, "elapsed_time": "1:28:56", "remaining_time": "0:30:21", "throughput": 5485.91, "total_tokens": 29272944} {"current_steps": 48060, "total_steps": 64460, "loss": 0.2513, "lr": 1.8457658365334746e-06, "epoch": 14.911573068569655, "percentage": 74.56, "elapsed_time": "1:28:56", "remaining_time": "0:30:21", "throughput": 5485.81, "total_tokens": 29275056} {"current_steps": 48065, "total_steps": 64460, "loss": 0.1885, "lr": 1.844715522552472e-06, "epoch": 14.913124418243871, "percentage": 74.57, "elapsed_time": "1:28:57", "remaining_time": "0:30:20", "throughput": 5485.88, "total_tokens": 29278800} {"current_steps": 48070, "total_steps": 64460, "loss": 0.2176, "lr": 1.8436654398911874e-06, "epoch": 14.914675767918089, "percentage": 74.57, "elapsed_time": "1:28:57", "remaining_time": "0:30:19", "throughput": 5485.81, "total_tokens": 29281104} {"current_steps": 48075, "total_steps": 64460, "loss": 0.1738, "lr": 1.8426155886266006e-06, "epoch": 14.916227117592305, "percentage": 74.58, "elapsed_time": "1:28:58", "remaining_time": "0:30:19", "throughput": 5485.85, "total_tokens": 29284240} {"current_steps": 48080, "total_steps": 64460, "loss": 0.1442, "lr": 1.8415659688356824e-06, "epoch": 14.917778467266523, "percentage": 74.59, "elapsed_time": "1:28:58", "remaining_time": "0:30:18", "throughput": 5485.84, "total_tokens": 29286928} {"current_steps": 48085, "total_steps": 64460, "loss": 0.186, "lr": 1.8405165805953778e-06, "epoch": 14.919329816940738, "percentage": 74.6, "elapsed_time": "1:28:59", "remaining_time": "0:30:18", "throughput": 5485.77, "total_tokens": 29289136} {"current_steps": 48090, "total_steps": 64460, "loss": 0.1952, "lr": 1.8394674239826239e-06, "epoch": 14.920881166614954, "percentage": 74.6, "elapsed_time": "1:28:59", "remaining_time": "0:30:17", "throughput": 5485.78, "total_tokens": 29291952} {"current_steps": 48095, "total_steps": 64460, "loss": 0.2576, "lr": 1.8384184990743326e-06, "epoch": 14.922432516289172, "percentage": 74.61, "elapsed_time": "1:29:00", "remaining_time": "0:30:17", "throughput": 5485.82, "total_tokens": 29295056} {"current_steps": 48100, "total_steps": 64460, "loss": 0.1789, "lr": 1.8373698059474038e-06, "epoch": 14.923983865963388, "percentage": 74.62, "elapsed_time": "1:29:00", "remaining_time": "0:30:16", "throughput": 5485.85, "total_tokens": 29297872} {"current_steps": 48105, "total_steps": 64460, "loss": 0.2284, "lr": 1.836321344678721e-06, "epoch": 14.925535215637606, "percentage": 74.63, "elapsed_time": "1:29:01", "remaining_time": "0:30:15", "throughput": 5486.02, "total_tokens": 29302160} {"current_steps": 48110, "total_steps": 64460, "loss": 0.1813, "lr": 1.8352731153451452e-06, "epoch": 14.927086565311821, "percentage": 74.64, "elapsed_time": "1:29:01", "remaining_time": "0:30:15", "throughput": 5486.05, "total_tokens": 29305392} {"current_steps": 48115, "total_steps": 64460, "loss": 0.2011, "lr": 1.8342251180235283e-06, "epoch": 14.928637914986037, "percentage": 74.64, "elapsed_time": "1:29:02", "remaining_time": "0:30:14", "throughput": 5486.11, "total_tokens": 29308784} {"current_steps": 48120, "total_steps": 64460, "loss": 0.2458, "lr": 1.8331773527906965e-06, "epoch": 14.930189264660255, "percentage": 74.65, "elapsed_time": "1:29:02", "remaining_time": "0:30:14", "throughput": 5486.15, "total_tokens": 29311728} {"current_steps": 48125, "total_steps": 64460, "loss": 0.2076, "lr": 1.8321298197234676e-06, "epoch": 14.93174061433447, "percentage": 74.66, "elapsed_time": "1:29:03", "remaining_time": "0:30:13", "throughput": 5486.21, "total_tokens": 29314896} {"current_steps": 48130, "total_steps": 64460, "loss": 0.1372, "lr": 1.8310825188986342e-06, "epoch": 14.933291964008687, "percentage": 74.67, "elapsed_time": "1:29:03", "remaining_time": "0:30:13", "throughput": 5486.3, "total_tokens": 29318544} {"current_steps": 48135, "total_steps": 64460, "loss": 0.1836, "lr": 1.8300354503929796e-06, "epoch": 14.934843313682904, "percentage": 74.67, "elapsed_time": "1:29:04", "remaining_time": "0:30:12", "throughput": 5486.29, "total_tokens": 29321392} {"current_steps": 48140, "total_steps": 64460, "loss": 0.153, "lr": 1.8289886142832624e-06, "epoch": 14.93639466335712, "percentage": 74.68, "elapsed_time": "1:29:04", "remaining_time": "0:30:12", "throughput": 5486.34, "total_tokens": 29324464} {"current_steps": 48145, "total_steps": 64460, "loss": 0.2227, "lr": 1.8279420106462326e-06, "epoch": 14.937946013031338, "percentage": 74.69, "elapsed_time": "1:29:05", "remaining_time": "0:30:11", "throughput": 5486.25, "total_tokens": 29326448} {"current_steps": 48150, "total_steps": 64460, "loss": 0.1618, "lr": 1.826895639558614e-06, "epoch": 14.939497362705554, "percentage": 74.7, "elapsed_time": "1:29:06", "remaining_time": "0:30:10", "throughput": 5486.38, "total_tokens": 29330960} {"current_steps": 48155, "total_steps": 64460, "loss": 0.2042, "lr": 1.82584950109712e-06, "epoch": 14.94104871237977, "percentage": 74.71, "elapsed_time": "1:29:06", "remaining_time": "0:30:10", "throughput": 5486.42, "total_tokens": 29333712} {"current_steps": 48160, "total_steps": 64460, "loss": 0.2194, "lr": 1.8248035953384474e-06, "epoch": 14.942600062053987, "percentage": 74.71, "elapsed_time": "1:29:07", "remaining_time": "0:30:09", "throughput": 5486.46, "total_tokens": 29336400} {"current_steps": 48165, "total_steps": 64460, "loss": 0.1663, "lr": 1.8237579223592689e-06, "epoch": 14.944151411728203, "percentage": 74.72, "elapsed_time": "1:29:07", "remaining_time": "0:30:09", "throughput": 5486.48, "total_tokens": 29339248} {"current_steps": 48170, "total_steps": 64460, "loss": 0.2339, "lr": 1.822712482236249e-06, "epoch": 14.945702761402421, "percentage": 74.73, "elapsed_time": "1:29:08", "remaining_time": "0:30:08", "throughput": 5486.46, "total_tokens": 29341680} {"current_steps": 48175, "total_steps": 64460, "loss": 0.1605, "lr": 1.8216672750460274e-06, "epoch": 14.947254111076637, "percentage": 74.74, "elapsed_time": "1:29:08", "remaining_time": "0:30:07", "throughput": 5486.5, "total_tokens": 29344560} {"current_steps": 48180, "total_steps": 64460, "loss": 0.1817, "lr": 1.820622300865233e-06, "epoch": 14.948805460750853, "percentage": 74.74, "elapsed_time": "1:29:08", "remaining_time": "0:30:07", "throughput": 5486.53, "total_tokens": 29347344} {"current_steps": 48185, "total_steps": 64460, "loss": 0.1591, "lr": 1.8195775597704719e-06, "epoch": 14.95035681042507, "percentage": 74.75, "elapsed_time": "1:29:09", "remaining_time": "0:30:06", "throughput": 5486.6, "total_tokens": 29350544} {"current_steps": 48190, "total_steps": 64460, "loss": 0.1732, "lr": 1.8185330518383392e-06, "epoch": 14.951908160099286, "percentage": 74.76, "elapsed_time": "1:29:09", "remaining_time": "0:30:06", "throughput": 5486.68, "total_tokens": 29353680} {"current_steps": 48195, "total_steps": 64460, "loss": 0.3606, "lr": 1.817488777145406e-06, "epoch": 14.953459509773502, "percentage": 74.77, "elapsed_time": "1:29:10", "remaining_time": "0:30:05", "throughput": 5486.86, "total_tokens": 29358448} {"current_steps": 48200, "total_steps": 64460, "loss": 0.2351, "lr": 1.8164447357682342e-06, "epoch": 14.95501085944772, "percentage": 74.78, "elapsed_time": "1:29:11", "remaining_time": "0:30:05", "throughput": 5486.83, "total_tokens": 29361040} {"current_steps": 48205, "total_steps": 64460, "loss": 0.1508, "lr": 1.81540092778336e-06, "epoch": 14.956562209121936, "percentage": 74.78, "elapsed_time": "1:29:11", "remaining_time": "0:30:04", "throughput": 5486.97, "total_tokens": 29364912} {"current_steps": 48210, "total_steps": 64460, "loss": 0.2718, "lr": 1.8143573532673108e-06, "epoch": 14.958113558796153, "percentage": 74.79, "elapsed_time": "1:29:12", "remaining_time": "0:30:04", "throughput": 5486.9, "total_tokens": 29366960} {"current_steps": 48215, "total_steps": 64460, "loss": 0.2515, "lr": 1.8133140122965904e-06, "epoch": 14.95966490847037, "percentage": 74.8, "elapsed_time": "1:29:12", "remaining_time": "0:30:03", "throughput": 5486.92, "total_tokens": 29369552} {"current_steps": 48220, "total_steps": 64460, "loss": 0.2302, "lr": 1.8122709049476877e-06, "epoch": 14.961216258144585, "percentage": 74.81, "elapsed_time": "1:29:13", "remaining_time": "0:30:02", "throughput": 5486.97, "total_tokens": 29372368} {"current_steps": 48225, "total_steps": 64460, "loss": 0.2201, "lr": 1.811228031297077e-06, "epoch": 14.962767607818803, "percentage": 74.81, "elapsed_time": "1:29:13", "remaining_time": "0:30:02", "throughput": 5487.12, "total_tokens": 29377008} {"current_steps": 48230, "total_steps": 64460, "loss": 0.2049, "lr": 1.8101853914212137e-06, "epoch": 14.964318957493019, "percentage": 74.82, "elapsed_time": "1:29:14", "remaining_time": "0:30:01", "throughput": 5487.09, "total_tokens": 29379408} {"current_steps": 48235, "total_steps": 64460, "loss": 0.1599, "lr": 1.8091429853965325e-06, "epoch": 14.965870307167236, "percentage": 74.83, "elapsed_time": "1:29:14", "remaining_time": "0:30:01", "throughput": 5487.19, "total_tokens": 29382800} {"current_steps": 48240, "total_steps": 64460, "loss": 0.1667, "lr": 1.808100813299456e-06, "epoch": 14.967421656841452, "percentage": 74.84, "elapsed_time": "1:29:15", "remaining_time": "0:30:00", "throughput": 5487.16, "total_tokens": 29385136} {"current_steps": 48245, "total_steps": 64460, "loss": 0.1781, "lr": 1.807058875206389e-06, "epoch": 14.968973006515668, "percentage": 74.84, "elapsed_time": "1:29:15", "remaining_time": "0:30:00", "throughput": 5487.19, "total_tokens": 29388112} {"current_steps": 48250, "total_steps": 64460, "loss": 0.1062, "lr": 1.8060171711937152e-06, "epoch": 14.970524356189886, "percentage": 74.85, "elapsed_time": "1:29:16", "remaining_time": "0:29:59", "throughput": 5487.32, "total_tokens": 29391920} {"current_steps": 48255, "total_steps": 64460, "loss": 0.1405, "lr": 1.8049757013378066e-06, "epoch": 14.972075705864102, "percentage": 74.86, "elapsed_time": "1:29:16", "remaining_time": "0:29:58", "throughput": 5487.29, "total_tokens": 29394320} {"current_steps": 48260, "total_steps": 64460, "loss": 0.1982, "lr": 1.803934465715012e-06, "epoch": 14.973627055538318, "percentage": 74.87, "elapsed_time": "1:29:17", "remaining_time": "0:29:58", "throughput": 5487.36, "total_tokens": 29397424} {"current_steps": 48265, "total_steps": 64460, "loss": 0.2144, "lr": 1.80289346440167e-06, "epoch": 14.975178405212535, "percentage": 74.88, "elapsed_time": "1:29:17", "remaining_time": "0:29:57", "throughput": 5487.36, "total_tokens": 29400432} {"current_steps": 48270, "total_steps": 64460, "loss": 0.2494, "lr": 1.8018526974740952e-06, "epoch": 14.976729754886751, "percentage": 74.88, "elapsed_time": "1:29:18", "remaining_time": "0:29:57", "throughput": 5487.38, "total_tokens": 29403152} {"current_steps": 48275, "total_steps": 64460, "loss": 0.2137, "lr": 1.8008121650085908e-06, "epoch": 14.978281104560969, "percentage": 74.89, "elapsed_time": "1:29:18", "remaining_time": "0:29:56", "throughput": 5487.4, "total_tokens": 29405776} {"current_steps": 48280, "total_steps": 64460, "loss": 0.1874, "lr": 1.7997718670814367e-06, "epoch": 14.979832454235185, "percentage": 74.9, "elapsed_time": "1:29:19", "remaining_time": "0:29:56", "throughput": 5487.43, "total_tokens": 29408816} {"current_steps": 48285, "total_steps": 64460, "loss": 0.2021, "lr": 1.7987318037689034e-06, "epoch": 14.9813838039094, "percentage": 74.91, "elapsed_time": "1:29:19", "remaining_time": "0:29:55", "throughput": 5487.48, "total_tokens": 29411760} {"current_steps": 48290, "total_steps": 64460, "loss": 0.1853, "lr": 1.7976919751472355e-06, "epoch": 14.982935153583618, "percentage": 74.91, "elapsed_time": "1:29:20", "remaining_time": "0:29:54", "throughput": 5487.66, "total_tokens": 29416112} {"current_steps": 48295, "total_steps": 64460, "loss": 0.168, "lr": 1.7966523812926684e-06, "epoch": 14.984486503257834, "percentage": 74.92, "elapsed_time": "1:29:20", "remaining_time": "0:29:54", "throughput": 5487.66, "total_tokens": 29418704} {"current_steps": 48300, "total_steps": 64460, "loss": 0.1621, "lr": 1.7956130222814138e-06, "epoch": 14.986037852932052, "percentage": 74.93, "elapsed_time": "1:29:21", "remaining_time": "0:29:53", "throughput": 5487.77, "total_tokens": 29422128} {"current_steps": 48305, "total_steps": 64460, "loss": 0.1901, "lr": 1.7945738981896699e-06, "epoch": 14.987589202606268, "percentage": 74.94, "elapsed_time": "1:29:22", "remaining_time": "0:29:53", "throughput": 5487.93, "total_tokens": 29426992} {"current_steps": 48310, "total_steps": 64460, "loss": 0.194, "lr": 1.7935350090936189e-06, "epoch": 14.989140552280483, "percentage": 74.95, "elapsed_time": "1:29:22", "remaining_time": "0:29:52", "throughput": 5487.95, "total_tokens": 29429904} {"current_steps": 48315, "total_steps": 64460, "loss": 0.1999, "lr": 1.7924963550694207e-06, "epoch": 14.990691901954701, "percentage": 74.95, "elapsed_time": "1:29:23", "remaining_time": "0:29:52", "throughput": 5488.1, "total_tokens": 29433840} {"current_steps": 48320, "total_steps": 64460, "loss": 0.1536, "lr": 1.7914579361932233e-06, "epoch": 14.992243251628917, "percentage": 74.96, "elapsed_time": "1:29:23", "remaining_time": "0:29:51", "throughput": 5488.11, "total_tokens": 29436464} {"current_steps": 48325, "total_steps": 64460, "loss": 0.2701, "lr": 1.7904197525411525e-06, "epoch": 14.993794601303133, "percentage": 74.97, "elapsed_time": "1:29:24", "remaining_time": "0:29:51", "throughput": 5488.19, "total_tokens": 29440144} {"current_steps": 48330, "total_steps": 64460, "loss": 0.1864, "lr": 1.789381804189323e-06, "epoch": 14.99534595097735, "percentage": 74.98, "elapsed_time": "1:29:24", "remaining_time": "0:29:50", "throughput": 5488.2, "total_tokens": 29442736} {"current_steps": 48335, "total_steps": 64460, "loss": 0.1444, "lr": 1.7883440912138244e-06, "epoch": 14.996897300651566, "percentage": 74.98, "elapsed_time": "1:29:25", "remaining_time": "0:29:49", "throughput": 5488.32, "total_tokens": 29446352} {"current_steps": 48340, "total_steps": 64460, "loss": 0.2042, "lr": 1.787306613690738e-06, "epoch": 14.998448650325784, "percentage": 74.99, "elapsed_time": "1:29:26", "remaining_time": "0:29:49", "throughput": 5488.58, "total_tokens": 29452656} {"current_steps": 48345, "total_steps": 64460, "loss": 0.2538, "lr": 1.786269371696119e-06, "epoch": 15.0, "percentage": 75.0, "elapsed_time": "1:29:26", "remaining_time": "0:29:48", "throughput": 5488.37, "total_tokens": 29454800} {"current_steps": 48350, "total_steps": 64460, "loss": 0.1631, "lr": 1.785232365306012e-06, "epoch": 15.001551349674216, "percentage": 75.01, "elapsed_time": "1:29:27", "remaining_time": "0:29:48", "throughput": 5488.23, "total_tokens": 29458352} {"current_steps": 48355, "total_steps": 64460, "loss": 0.2492, "lr": 1.7841955945964407e-06, "epoch": 15.003102699348434, "percentage": 75.02, "elapsed_time": "1:29:28", "remaining_time": "0:29:47", "throughput": 5488.27, "total_tokens": 29461648} {"current_steps": 48360, "total_steps": 64460, "loss": 0.1573, "lr": 1.7831590596434128e-06, "epoch": 15.00465404902265, "percentage": 75.02, "elapsed_time": "1:29:28", "remaining_time": "0:29:47", "throughput": 5488.31, "total_tokens": 29464560} {"current_steps": 48365, "total_steps": 64460, "loss": 0.1834, "lr": 1.7821227605229203e-06, "epoch": 15.006205398696867, "percentage": 75.03, "elapsed_time": "1:29:29", "remaining_time": "0:29:46", "throughput": 5488.34, "total_tokens": 29467216} {"current_steps": 48370, "total_steps": 64460, "loss": 0.2054, "lr": 1.781086697310933e-06, "epoch": 15.007756748371083, "percentage": 75.04, "elapsed_time": "1:29:29", "remaining_time": "0:29:46", "throughput": 5488.31, "total_tokens": 29470000} {"current_steps": 48375, "total_steps": 64460, "loss": 0.1621, "lr": 1.7800508700834107e-06, "epoch": 15.009308098045299, "percentage": 75.05, "elapsed_time": "1:29:30", "remaining_time": "0:29:45", "throughput": 5488.38, "total_tokens": 29473136} {"current_steps": 48380, "total_steps": 64460, "loss": 0.2324, "lr": 1.7790152789162874e-06, "epoch": 15.010859447719517, "percentage": 75.05, "elapsed_time": "1:29:30", "remaining_time": "0:29:45", "throughput": 5488.35, "total_tokens": 29475824} {"current_steps": 48385, "total_steps": 64460, "loss": 0.1597, "lr": 1.7779799238854883e-06, "epoch": 15.012410797393732, "percentage": 75.06, "elapsed_time": "1:29:31", "remaining_time": "0:29:44", "throughput": 5488.34, "total_tokens": 29478256} {"current_steps": 48390, "total_steps": 64460, "loss": 0.1961, "lr": 1.7769448050669136e-06, "epoch": 15.013962147067948, "percentage": 75.07, "elapsed_time": "1:29:31", "remaining_time": "0:29:43", "throughput": 5488.41, "total_tokens": 29482000} {"current_steps": 48395, "total_steps": 64460, "loss": 0.1205, "lr": 1.7759099225364522e-06, "epoch": 15.015513496742166, "percentage": 75.08, "elapsed_time": "1:29:32", "remaining_time": "0:29:43", "throughput": 5488.5, "total_tokens": 29485296} {"current_steps": 48400, "total_steps": 64460, "loss": 0.1407, "lr": 1.7748752763699717e-06, "epoch": 15.017064846416382, "percentage": 75.09, "elapsed_time": "1:29:32", "remaining_time": "0:29:42", "throughput": 5488.59, "total_tokens": 29489744} {"current_steps": 48405, "total_steps": 64460, "loss": 0.2302, "lr": 1.773840866643326e-06, "epoch": 15.0186161960906, "percentage": 75.09, "elapsed_time": "1:29:33", "remaining_time": "0:29:42", "throughput": 5488.59, "total_tokens": 29492304} {"current_steps": 48410, "total_steps": 64460, "loss": 0.1726, "lr": 1.7728066934323462e-06, "epoch": 15.020167545764815, "percentage": 75.1, "elapsed_time": "1:29:33", "remaining_time": "0:29:41", "throughput": 5488.58, "total_tokens": 29494800} {"current_steps": 48415, "total_steps": 64460, "loss": 0.1736, "lr": 1.771772756812854e-06, "epoch": 15.021718895439031, "percentage": 75.11, "elapsed_time": "1:29:34", "remaining_time": "0:29:41", "throughput": 5488.61, "total_tokens": 29497744} {"current_steps": 48420, "total_steps": 64460, "loss": 0.1781, "lr": 1.7707390568606442e-06, "epoch": 15.023270245113249, "percentage": 75.12, "elapsed_time": "1:29:34", "remaining_time": "0:29:40", "throughput": 5488.55, "total_tokens": 29500016} {"current_steps": 48425, "total_steps": 64460, "loss": 0.1785, "lr": 1.7697055936515018e-06, "epoch": 15.024821594787465, "percentage": 75.12, "elapsed_time": "1:29:35", "remaining_time": "0:29:39", "throughput": 5488.55, "total_tokens": 29502480} {"current_steps": 48430, "total_steps": 64460, "loss": 0.2136, "lr": 1.7686723672611938e-06, "epoch": 15.026372944461682, "percentage": 75.13, "elapsed_time": "1:29:35", "remaining_time": "0:29:39", "throughput": 5488.51, "total_tokens": 29504752} {"current_steps": 48435, "total_steps": 64460, "loss": 0.1789, "lr": 1.7676393777654637e-06, "epoch": 15.027924294135898, "percentage": 75.14, "elapsed_time": "1:29:36", "remaining_time": "0:29:38", "throughput": 5488.62, "total_tokens": 29508496} {"current_steps": 48440, "total_steps": 64460, "loss": 0.187, "lr": 1.7666066252400465e-06, "epoch": 15.029475643810114, "percentage": 75.15, "elapsed_time": "1:29:36", "remaining_time": "0:29:38", "throughput": 5488.65, "total_tokens": 29511120} {"current_steps": 48445, "total_steps": 64460, "loss": 0.153, "lr": 1.7655741097606505e-06, "epoch": 15.031026993484332, "percentage": 75.16, "elapsed_time": "1:29:37", "remaining_time": "0:29:37", "throughput": 5488.74, "total_tokens": 29514736} {"current_steps": 48450, "total_steps": 64460, "loss": 0.1699, "lr": 1.7645418314029755e-06, "epoch": 15.032578343158548, "percentage": 75.16, "elapsed_time": "1:29:37", "remaining_time": "0:29:37", "throughput": 5488.8, "total_tokens": 29517808} {"current_steps": 48455, "total_steps": 64460, "loss": 0.1034, "lr": 1.7635097902426962e-06, "epoch": 15.034129692832764, "percentage": 75.17, "elapsed_time": "1:29:38", "remaining_time": "0:29:36", "throughput": 5488.86, "total_tokens": 29520912} {"current_steps": 48460, "total_steps": 64460, "loss": 0.1602, "lr": 1.7624779863554765e-06, "epoch": 15.035681042506981, "percentage": 75.18, "elapsed_time": "1:29:38", "remaining_time": "0:29:35", "throughput": 5488.85, "total_tokens": 29523344} {"current_steps": 48465, "total_steps": 64460, "loss": 0.1798, "lr": 1.7614464198169568e-06, "epoch": 15.037232392181197, "percentage": 75.19, "elapsed_time": "1:29:39", "remaining_time": "0:29:35", "throughput": 5488.93, "total_tokens": 29526640} {"current_steps": 48470, "total_steps": 64460, "loss": 0.1282, "lr": 1.7604150907027667e-06, "epoch": 15.038783741855415, "percentage": 75.19, "elapsed_time": "1:29:39", "remaining_time": "0:29:34", "throughput": 5489.0, "total_tokens": 29529744} {"current_steps": 48475, "total_steps": 64460, "loss": 0.2171, "lr": 1.7593839990885108e-06, "epoch": 15.04033509152963, "percentage": 75.2, "elapsed_time": "1:29:40", "remaining_time": "0:29:34", "throughput": 5489.03, "total_tokens": 29532656} {"current_steps": 48480, "total_steps": 64460, "loss": 0.15, "lr": 1.7583531450497826e-06, "epoch": 15.041886441203847, "percentage": 75.21, "elapsed_time": "1:29:40", "remaining_time": "0:29:33", "throughput": 5489.06, "total_tokens": 29535568} {"current_steps": 48485, "total_steps": 64460, "loss": 0.1655, "lr": 1.7573225286621575e-06, "epoch": 15.043437790878064, "percentage": 75.22, "elapsed_time": "1:29:41", "remaining_time": "0:29:33", "throughput": 5489.1, "total_tokens": 29538704} {"current_steps": 48490, "total_steps": 64460, "loss": 0.1518, "lr": 1.756292150001188e-06, "epoch": 15.04498914055228, "percentage": 75.22, "elapsed_time": "1:29:41", "remaining_time": "0:29:32", "throughput": 5489.15, "total_tokens": 29541744} {"current_steps": 48495, "total_steps": 64460, "loss": 0.165, "lr": 1.7552620091424173e-06, "epoch": 15.046540490226498, "percentage": 75.23, "elapsed_time": "1:29:42", "remaining_time": "0:29:31", "throughput": 5489.18, "total_tokens": 29544560} {"current_steps": 48500, "total_steps": 64460, "loss": 0.1055, "lr": 1.7542321061613632e-06, "epoch": 15.048091839900714, "percentage": 75.24, "elapsed_time": "1:29:42", "remaining_time": "0:29:31", "throughput": 5489.24, "total_tokens": 29547632} {"current_steps": 48505, "total_steps": 64460, "loss": 0.1397, "lr": 1.7532024411335325e-06, "epoch": 15.04964318957493, "percentage": 75.25, "elapsed_time": "1:29:43", "remaining_time": "0:29:30", "throughput": 5489.25, "total_tokens": 29550192} {"current_steps": 48510, "total_steps": 64460, "loss": 0.1387, "lr": 1.752173014134409e-06, "epoch": 15.051194539249147, "percentage": 75.26, "elapsed_time": "1:29:43", "remaining_time": "0:29:30", "throughput": 5489.24, "total_tokens": 29552848} {"current_steps": 48515, "total_steps": 64460, "loss": 0.1969, "lr": 1.7511438252394659e-06, "epoch": 15.052745888923363, "percentage": 75.26, "elapsed_time": "1:29:44", "remaining_time": "0:29:29", "throughput": 5489.36, "total_tokens": 29557072} {"current_steps": 48520, "total_steps": 64460, "loss": 0.178, "lr": 1.7501148745241503e-06, "epoch": 15.054297238597579, "percentage": 75.27, "elapsed_time": "1:29:44", "remaining_time": "0:29:29", "throughput": 5489.42, "total_tokens": 29560240} {"current_steps": 48525, "total_steps": 64460, "loss": 0.1884, "lr": 1.7490861620639011e-06, "epoch": 15.055848588271797, "percentage": 75.28, "elapsed_time": "1:29:45", "remaining_time": "0:29:28", "throughput": 5489.53, "total_tokens": 29564080} {"current_steps": 48530, "total_steps": 64460, "loss": 0.111, "lr": 1.7480576879341304e-06, "epoch": 15.057399937946013, "percentage": 75.29, "elapsed_time": "1:29:46", "remaining_time": "0:29:27", "throughput": 5489.6, "total_tokens": 29567312} {"current_steps": 48535, "total_steps": 64460, "loss": 0.1295, "lr": 1.7470294522102421e-06, "epoch": 15.05895128762023, "percentage": 75.29, "elapsed_time": "1:29:46", "remaining_time": "0:29:27", "throughput": 5489.58, "total_tokens": 29569872} {"current_steps": 48540, "total_steps": 64460, "loss": 0.1482, "lr": 1.746001454967614e-06, "epoch": 15.060502637294446, "percentage": 75.3, "elapsed_time": "1:29:47", "remaining_time": "0:29:26", "throughput": 5489.64, "total_tokens": 29572944} {"current_steps": 48545, "total_steps": 64460, "loss": 0.2567, "lr": 1.7449736962816127e-06, "epoch": 15.062053986968662, "percentage": 75.31, "elapsed_time": "1:29:47", "remaining_time": "0:29:26", "throughput": 5489.69, "total_tokens": 29576016} {"current_steps": 48550, "total_steps": 64460, "loss": 0.1315, "lr": 1.743946176227586e-06, "epoch": 15.06360533664288, "percentage": 75.32, "elapsed_time": "1:29:48", "remaining_time": "0:29:25", "throughput": 5489.73, "total_tokens": 29578896} {"current_steps": 48555, "total_steps": 64460, "loss": 0.2179, "lr": 1.7429188948808607e-06, "epoch": 15.065156686317096, "percentage": 75.33, "elapsed_time": "1:29:48", "remaining_time": "0:29:25", "throughput": 5489.8, "total_tokens": 29582064} {"current_steps": 48560, "total_steps": 64460, "loss": 0.2288, "lr": 1.7418918523167517e-06, "epoch": 15.066708035991313, "percentage": 75.33, "elapsed_time": "1:29:49", "remaining_time": "0:29:24", "throughput": 5489.8, "total_tokens": 29584560} {"current_steps": 48565, "total_steps": 64460, "loss": 0.1347, "lr": 1.7408650486105494e-06, "epoch": 15.06825938566553, "percentage": 75.34, "elapsed_time": "1:29:49", "remaining_time": "0:29:23", "throughput": 5489.75, "total_tokens": 29586832} {"current_steps": 48570, "total_steps": 64460, "loss": 0.2199, "lr": 1.7398384838375354e-06, "epoch": 15.069810735339745, "percentage": 75.35, "elapsed_time": "1:29:49", "remaining_time": "0:29:23", "throughput": 5489.71, "total_tokens": 29589232} {"current_steps": 48575, "total_steps": 64460, "loss": 0.1449, "lr": 1.7388121580729645e-06, "epoch": 15.071362085013963, "percentage": 75.36, "elapsed_time": "1:29:50", "remaining_time": "0:29:22", "throughput": 5489.77, "total_tokens": 29592368} {"current_steps": 48580, "total_steps": 64460, "loss": 0.1676, "lr": 1.7377860713920825e-06, "epoch": 15.072913434688179, "percentage": 75.36, "elapsed_time": "1:29:50", "remaining_time": "0:29:22", "throughput": 5489.73, "total_tokens": 29594768} {"current_steps": 48585, "total_steps": 64460, "loss": 0.1479, "lr": 1.7367602238701104e-06, "epoch": 15.074464784362394, "percentage": 75.37, "elapsed_time": "1:29:51", "remaining_time": "0:29:21", "throughput": 5489.72, "total_tokens": 29597168} {"current_steps": 48590, "total_steps": 64460, "loss": 0.1352, "lr": 1.7357346155822575e-06, "epoch": 15.076016134036612, "percentage": 75.38, "elapsed_time": "1:29:51", "remaining_time": "0:29:21", "throughput": 5489.67, "total_tokens": 29599536} {"current_steps": 48595, "total_steps": 64460, "loss": 0.2272, "lr": 1.7347092466037108e-06, "epoch": 15.077567483710828, "percentage": 75.39, "elapsed_time": "1:29:52", "remaining_time": "0:29:20", "throughput": 5489.73, "total_tokens": 29602608} {"current_steps": 48600, "total_steps": 64460, "loss": 0.155, "lr": 1.733684117009643e-06, "epoch": 15.079118833385046, "percentage": 75.4, "elapsed_time": "1:29:52", "remaining_time": "0:29:19", "throughput": 5489.78, "total_tokens": 29605648} {"current_steps": 48605, "total_steps": 64460, "loss": 0.2587, "lr": 1.7326592268752102e-06, "epoch": 15.080670183059262, "percentage": 75.4, "elapsed_time": "1:29:53", "remaining_time": "0:29:19", "throughput": 5489.77, "total_tokens": 29608176} {"current_steps": 48610, "total_steps": 64460, "loss": 0.1456, "lr": 1.7316345762755448e-06, "epoch": 15.082221532733477, "percentage": 75.41, "elapsed_time": "1:29:54", "remaining_time": "0:29:18", "throughput": 5489.9, "total_tokens": 29612752} {"current_steps": 48615, "total_steps": 64460, "loss": 0.2541, "lr": 1.7306101652857704e-06, "epoch": 15.083772882407695, "percentage": 75.42, "elapsed_time": "1:29:54", "remaining_time": "0:29:18", "throughput": 5489.95, "total_tokens": 29615824} {"current_steps": 48620, "total_steps": 64460, "loss": 0.131, "lr": 1.7295859939809851e-06, "epoch": 15.085324232081911, "percentage": 75.43, "elapsed_time": "1:29:55", "remaining_time": "0:29:17", "throughput": 5489.94, "total_tokens": 29618512} {"current_steps": 48625, "total_steps": 64460, "loss": 0.1567, "lr": 1.7285620624362748e-06, "epoch": 15.086875581756129, "percentage": 75.43, "elapsed_time": "1:29:55", "remaining_time": "0:29:17", "throughput": 5489.87, "total_tokens": 29620720} {"current_steps": 48630, "total_steps": 64460, "loss": 0.2836, "lr": 1.7275383707267035e-06, "epoch": 15.088426931430345, "percentage": 75.44, "elapsed_time": "1:29:56", "remaining_time": "0:29:16", "throughput": 5489.97, "total_tokens": 29624112} {"current_steps": 48635, "total_steps": 64460, "loss": 0.1002, "lr": 1.7265149189273234e-06, "epoch": 15.08997828110456, "percentage": 75.45, "elapsed_time": "1:29:56", "remaining_time": "0:29:15", "throughput": 5490.0, "total_tokens": 29626736} {"current_steps": 48640, "total_steps": 64460, "loss": 0.1179, "lr": 1.7254917071131616e-06, "epoch": 15.091529630778778, "percentage": 75.46, "elapsed_time": "1:29:56", "remaining_time": "0:29:15", "throughput": 5490.05, "total_tokens": 29629744} {"current_steps": 48645, "total_steps": 64460, "loss": 0.2097, "lr": 1.7244687353592355e-06, "epoch": 15.093080980452994, "percentage": 75.47, "elapsed_time": "1:29:57", "remaining_time": "0:29:14", "throughput": 5490.11, "total_tokens": 29632752} {"current_steps": 48650, "total_steps": 64460, "loss": 0.1305, "lr": 1.723446003740537e-06, "epoch": 15.09463233012721, "percentage": 75.47, "elapsed_time": "1:29:57", "remaining_time": "0:29:14", "throughput": 5490.11, "total_tokens": 29635440} {"current_steps": 48655, "total_steps": 64460, "loss": 0.1694, "lr": 1.7224235123320487e-06, "epoch": 15.096183679801428, "percentage": 75.48, "elapsed_time": "1:29:58", "remaining_time": "0:29:13", "throughput": 5490.16, "total_tokens": 29638320} {"current_steps": 48660, "total_steps": 64460, "loss": 0.1694, "lr": 1.7214012612087277e-06, "epoch": 15.097735029475643, "percentage": 75.49, "elapsed_time": "1:29:58", "remaining_time": "0:29:13", "throughput": 5490.21, "total_tokens": 29641648} {"current_steps": 48665, "total_steps": 64460, "loss": 0.1942, "lr": 1.7203792504455186e-06, "epoch": 15.099286379149861, "percentage": 75.5, "elapsed_time": "1:29:59", "remaining_time": "0:29:12", "throughput": 5490.23, "total_tokens": 29644464} {"current_steps": 48670, "total_steps": 64460, "loss": 0.1738, "lr": 1.7193574801173485e-06, "epoch": 15.100837728824077, "percentage": 75.5, "elapsed_time": "1:29:59", "remaining_time": "0:29:11", "throughput": 5490.23, "total_tokens": 29647216} {"current_steps": 48675, "total_steps": 64460, "loss": 0.1195, "lr": 1.718335950299122e-06, "epoch": 15.102389078498293, "percentage": 75.51, "elapsed_time": "1:30:00", "remaining_time": "0:29:11", "throughput": 5490.25, "total_tokens": 29650032} {"current_steps": 48680, "total_steps": 64460, "loss": 0.1871, "lr": 1.7173146610657331e-06, "epoch": 15.10394042817251, "percentage": 75.52, "elapsed_time": "1:30:01", "remaining_time": "0:29:10", "throughput": 5490.34, "total_tokens": 29653392} {"current_steps": 48685, "total_steps": 64460, "loss": 0.1602, "lr": 1.7162936124920504e-06, "epoch": 15.105491777846726, "percentage": 75.53, "elapsed_time": "1:30:01", "remaining_time": "0:29:10", "throughput": 5490.4, "total_tokens": 29656400} {"current_steps": 48690, "total_steps": 64460, "loss": 0.1646, "lr": 1.7152728046529327e-06, "epoch": 15.107043127520944, "percentage": 75.54, "elapsed_time": "1:30:02", "remaining_time": "0:29:09", "throughput": 5490.47, "total_tokens": 29659632} {"current_steps": 48695, "total_steps": 64460, "loss": 0.1768, "lr": 1.7142522376232135e-06, "epoch": 15.10859447719516, "percentage": 75.54, "elapsed_time": "1:30:02", "remaining_time": "0:29:09", "throughput": 5490.49, "total_tokens": 29662480} {"current_steps": 48700, "total_steps": 64460, "loss": 0.1409, "lr": 1.7132319114777162e-06, "epoch": 15.110145826869376, "percentage": 75.55, "elapsed_time": "1:30:03", "remaining_time": "0:29:08", "throughput": 5490.42, "total_tokens": 29664784} {"current_steps": 48705, "total_steps": 64460, "loss": 0.1195, "lr": 1.712211826291239e-06, "epoch": 15.111697176543593, "percentage": 75.56, "elapsed_time": "1:30:03", "remaining_time": "0:29:07", "throughput": 5490.51, "total_tokens": 29668336} {"current_steps": 48710, "total_steps": 64460, "loss": 0.1683, "lr": 1.7111919821385703e-06, "epoch": 15.11324852621781, "percentage": 75.57, "elapsed_time": "1:30:04", "remaining_time": "0:29:07", "throughput": 5490.58, "total_tokens": 29671280} {"current_steps": 48715, "total_steps": 64460, "loss": 0.1604, "lr": 1.7101723790944724e-06, "epoch": 15.114799875892025, "percentage": 75.57, "elapsed_time": "1:30:04", "remaining_time": "0:29:06", "throughput": 5490.64, "total_tokens": 29674448} {"current_steps": 48720, "total_steps": 64460, "loss": 0.1551, "lr": 1.7091530172336968e-06, "epoch": 15.116351225566243, "percentage": 75.58, "elapsed_time": "1:30:05", "remaining_time": "0:29:06", "throughput": 5490.66, "total_tokens": 29677168} {"current_steps": 48725, "total_steps": 64460, "loss": 0.2383, "lr": 1.7081338966309764e-06, "epoch": 15.117902575240459, "percentage": 75.59, "elapsed_time": "1:30:05", "remaining_time": "0:29:05", "throughput": 5490.71, "total_tokens": 29680080} {"current_steps": 48730, "total_steps": 64460, "loss": 0.2166, "lr": 1.7071150173610208e-06, "epoch": 15.119453924914676, "percentage": 75.6, "elapsed_time": "1:30:05", "remaining_time": "0:29:05", "throughput": 5490.69, "total_tokens": 29682640} {"current_steps": 48735, "total_steps": 64460, "loss": 0.15, "lr": 1.7060963794985297e-06, "epoch": 15.121005274588892, "percentage": 75.61, "elapsed_time": "1:30:06", "remaining_time": "0:29:04", "throughput": 5490.77, "total_tokens": 29685744} {"current_steps": 48740, "total_steps": 64460, "loss": 0.1816, "lr": 1.7050779831181779e-06, "epoch": 15.122556624263108, "percentage": 75.61, "elapsed_time": "1:30:06", "remaining_time": "0:29:03", "throughput": 5490.72, "total_tokens": 29687888} {"current_steps": 48745, "total_steps": 64460, "loss": 0.1426, "lr": 1.7040598282946297e-06, "epoch": 15.124107973937326, "percentage": 75.62, "elapsed_time": "1:30:07", "remaining_time": "0:29:03", "throughput": 5490.77, "total_tokens": 29690928} {"current_steps": 48750, "total_steps": 64460, "loss": 0.2048, "lr": 1.703041915102524e-06, "epoch": 15.125659323611542, "percentage": 75.63, "elapsed_time": "1:30:07", "remaining_time": "0:29:02", "throughput": 5490.8, "total_tokens": 29693840} {"current_steps": 48755, "total_steps": 64460, "loss": 0.2033, "lr": 1.7020242436164896e-06, "epoch": 15.12721067328576, "percentage": 75.64, "elapsed_time": "1:30:08", "remaining_time": "0:29:02", "throughput": 5490.91, "total_tokens": 29697296} {"current_steps": 48760, "total_steps": 64460, "loss": 0.1771, "lr": 1.7010068139111302e-06, "epoch": 15.128762022959975, "percentage": 75.64, "elapsed_time": "1:30:08", "remaining_time": "0:29:01", "throughput": 5490.98, "total_tokens": 29700464} {"current_steps": 48765, "total_steps": 64460, "loss": 0.1428, "lr": 1.6999896260610388e-06, "epoch": 15.130313372634191, "percentage": 75.65, "elapsed_time": "1:30:09", "remaining_time": "0:29:01", "throughput": 5491.04, "total_tokens": 29703664} {"current_steps": 48770, "total_steps": 64460, "loss": 0.1702, "lr": 1.698972680140784e-06, "epoch": 15.131864722308409, "percentage": 75.66, "elapsed_time": "1:30:09", "remaining_time": "0:29:00", "throughput": 5491.1, "total_tokens": 29706608} {"current_steps": 48775, "total_steps": 64460, "loss": 0.1638, "lr": 1.6979559762249237e-06, "epoch": 15.133416071982625, "percentage": 75.67, "elapsed_time": "1:30:10", "remaining_time": "0:28:59", "throughput": 5491.13, "total_tokens": 29709616} {"current_steps": 48780, "total_steps": 64460, "loss": 0.1795, "lr": 1.6969395143879908e-06, "epoch": 15.13496742165684, "percentage": 75.67, "elapsed_time": "1:30:11", "remaining_time": "0:28:59", "throughput": 5491.2, "total_tokens": 29713264} {"current_steps": 48785, "total_steps": 64460, "loss": 0.2939, "lr": 1.6959232947045056e-06, "epoch": 15.136518771331058, "percentage": 75.68, "elapsed_time": "1:30:11", "remaining_time": "0:28:58", "throughput": 5491.28, "total_tokens": 29717264} {"current_steps": 48790, "total_steps": 64460, "loss": 0.1582, "lr": 1.6949073172489705e-06, "epoch": 15.138070121005274, "percentage": 75.69, "elapsed_time": "1:30:12", "remaining_time": "0:28:58", "throughput": 5491.3, "total_tokens": 29720048} {"current_steps": 48795, "total_steps": 64460, "loss": 0.1529, "lr": 1.6938915820958657e-06, "epoch": 15.139621470679492, "percentage": 75.7, "elapsed_time": "1:30:12", "remaining_time": "0:28:57", "throughput": 5491.46, "total_tokens": 29724400} {"current_steps": 48800, "total_steps": 64460, "loss": 0.1402, "lr": 1.6928760893196593e-06, "epoch": 15.141172820353708, "percentage": 75.71, "elapsed_time": "1:30:13", "remaining_time": "0:28:57", "throughput": 5491.55, "total_tokens": 29727952} {"current_steps": 48805, "total_steps": 64460, "loss": 0.1344, "lr": 1.691860838994795e-06, "epoch": 15.142724170027924, "percentage": 75.71, "elapsed_time": "1:30:13", "remaining_time": "0:28:56", "throughput": 5491.56, "total_tokens": 29730672} {"current_steps": 48810, "total_steps": 64460, "loss": 0.1657, "lr": 1.6908458311957088e-06, "epoch": 15.144275519702141, "percentage": 75.72, "elapsed_time": "1:30:14", "remaining_time": "0:28:56", "throughput": 5491.47, "total_tokens": 29732976} {"current_steps": 48815, "total_steps": 64460, "loss": 0.1806, "lr": 1.6898310659968077e-06, "epoch": 15.145826869376357, "percentage": 75.73, "elapsed_time": "1:30:14", "remaining_time": "0:28:55", "throughput": 5491.43, "total_tokens": 29735376} {"current_steps": 48820, "total_steps": 64460, "loss": 0.1389, "lr": 1.688816543472489e-06, "epoch": 15.147378219050575, "percentage": 75.74, "elapsed_time": "1:30:15", "remaining_time": "0:28:54", "throughput": 5491.43, "total_tokens": 29738096} {"current_steps": 48825, "total_steps": 64460, "loss": 0.2088, "lr": 1.6878022636971263e-06, "epoch": 15.14892956872479, "percentage": 75.74, "elapsed_time": "1:30:15", "remaining_time": "0:28:54", "throughput": 5491.37, "total_tokens": 29740432} {"current_steps": 48830, "total_steps": 64460, "loss": 0.2091, "lr": 1.6867882267450819e-06, "epoch": 15.150480918399007, "percentage": 75.75, "elapsed_time": "1:30:16", "remaining_time": "0:28:53", "throughput": 5491.39, "total_tokens": 29743216} {"current_steps": 48835, "total_steps": 64460, "loss": 0.1871, "lr": 1.6857744326906933e-06, "epoch": 15.152032268073224, "percentage": 75.76, "elapsed_time": "1:30:16", "remaining_time": "0:28:53", "throughput": 5491.4, "total_tokens": 29745872} {"current_steps": 48840, "total_steps": 64460, "loss": 0.1713, "lr": 1.6847608816082861e-06, "epoch": 15.15358361774744, "percentage": 75.77, "elapsed_time": "1:30:17", "remaining_time": "0:28:52", "throughput": 5491.29, "total_tokens": 29747728} {"current_steps": 48845, "total_steps": 64460, "loss": 0.1514, "lr": 1.683747573572163e-06, "epoch": 15.155134967421656, "percentage": 75.78, "elapsed_time": "1:30:17", "remaining_time": "0:28:51", "throughput": 5491.32, "total_tokens": 29750928} {"current_steps": 48850, "total_steps": 64460, "loss": 0.1816, "lr": 1.6827345086566155e-06, "epoch": 15.156686317095874, "percentage": 75.78, "elapsed_time": "1:30:18", "remaining_time": "0:28:51", "throughput": 5491.34, "total_tokens": 29753648} {"current_steps": 48855, "total_steps": 64460, "loss": 0.1954, "lr": 1.6817216869359088e-06, "epoch": 15.15823766677009, "percentage": 75.79, "elapsed_time": "1:30:18", "remaining_time": "0:28:50", "throughput": 5491.34, "total_tokens": 29756304} {"current_steps": 48860, "total_steps": 64460, "loss": 0.1773, "lr": 1.680709108484298e-06, "epoch": 15.159789016444307, "percentage": 75.8, "elapsed_time": "1:30:19", "remaining_time": "0:28:50", "throughput": 5491.4, "total_tokens": 29759344} {"current_steps": 48865, "total_steps": 64460, "loss": 0.1709, "lr": 1.6796967733760145e-06, "epoch": 15.161340366118523, "percentage": 75.81, "elapsed_time": "1:30:19", "remaining_time": "0:28:49", "throughput": 5491.37, "total_tokens": 29761872} {"current_steps": 48870, "total_steps": 64460, "loss": 0.1506, "lr": 1.6786846816852758e-06, "epoch": 15.162891715792739, "percentage": 75.81, "elapsed_time": "1:30:20", "remaining_time": "0:28:49", "throughput": 5491.42, "total_tokens": 29764688} {"current_steps": 48875, "total_steps": 64460, "loss": 0.1959, "lr": 1.677672833486282e-06, "epoch": 15.164443065466957, "percentage": 75.82, "elapsed_time": "1:30:20", "remaining_time": "0:28:48", "throughput": 5491.36, "total_tokens": 29766928} {"current_steps": 48880, "total_steps": 64460, "loss": 0.2019, "lr": 1.6766612288532097e-06, "epoch": 15.165994415141173, "percentage": 75.83, "elapsed_time": "1:30:21", "remaining_time": "0:28:47", "throughput": 5491.27, "total_tokens": 29768880} {"current_steps": 48885, "total_steps": 64460, "loss": 0.1271, "lr": 1.6756498678602251e-06, "epoch": 15.16754576481539, "percentage": 75.84, "elapsed_time": "1:30:21", "remaining_time": "0:28:47", "throughput": 5491.3, "total_tokens": 29771664} {"current_steps": 48890, "total_steps": 64460, "loss": 0.2081, "lr": 1.6746387505814699e-06, "epoch": 15.169097114489606, "percentage": 75.85, "elapsed_time": "1:30:22", "remaining_time": "0:28:46", "throughput": 5491.39, "total_tokens": 29775536} {"current_steps": 48895, "total_steps": 64460, "loss": 0.2493, "lr": 1.673627877091074e-06, "epoch": 15.170648464163822, "percentage": 75.85, "elapsed_time": "1:30:22", "remaining_time": "0:28:46", "throughput": 5491.52, "total_tokens": 29779632} {"current_steps": 48900, "total_steps": 64460, "loss": 0.1746, "lr": 1.6726172474631435e-06, "epoch": 15.17219981383804, "percentage": 75.86, "elapsed_time": "1:30:23", "remaining_time": "0:28:45", "throughput": 5491.47, "total_tokens": 29782064} {"current_steps": 48905, "total_steps": 64460, "loss": 0.1869, "lr": 1.6716068617717728e-06, "epoch": 15.173751163512256, "percentage": 75.87, "elapsed_time": "1:30:23", "remaining_time": "0:28:45", "throughput": 5491.5, "total_tokens": 29784976} {"current_steps": 48910, "total_steps": 64460, "loss": 0.1678, "lr": 1.6705967200910312e-06, "epoch": 15.175302513186471, "percentage": 75.88, "elapsed_time": "1:30:24", "remaining_time": "0:28:44", "throughput": 5491.58, "total_tokens": 29788176} {"current_steps": 48915, "total_steps": 64460, "loss": 0.139, "lr": 1.6695868224949774e-06, "epoch": 15.176853862860689, "percentage": 75.88, "elapsed_time": "1:30:24", "remaining_time": "0:28:43", "throughput": 5491.57, "total_tokens": 29790736} {"current_steps": 48920, "total_steps": 64460, "loss": 0.2278, "lr": 1.6685771690576464e-06, "epoch": 15.178405212534905, "percentage": 75.89, "elapsed_time": "1:30:25", "remaining_time": "0:28:43", "throughput": 5491.61, "total_tokens": 29793712} {"current_steps": 48925, "total_steps": 64460, "loss": 0.2527, "lr": 1.6675677598530598e-06, "epoch": 15.179956562209123, "percentage": 75.9, "elapsed_time": "1:30:25", "remaining_time": "0:28:42", "throughput": 5491.49, "total_tokens": 29795984} {"current_steps": 48930, "total_steps": 64460, "loss": 0.1702, "lr": 1.666558594955217e-06, "epoch": 15.181507911883338, "percentage": 75.91, "elapsed_time": "1:30:26", "remaining_time": "0:28:42", "throughput": 5491.54, "total_tokens": 29799152} {"current_steps": 48935, "total_steps": 64460, "loss": 0.1683, "lr": 1.6655496744381034e-06, "epoch": 15.183059261557554, "percentage": 75.92, "elapsed_time": "1:30:26", "remaining_time": "0:28:41", "throughput": 5491.56, "total_tokens": 29801936} {"current_steps": 48940, "total_steps": 64460, "loss": 0.1646, "lr": 1.664540998375686e-06, "epoch": 15.184610611231772, "percentage": 75.92, "elapsed_time": "1:30:27", "remaining_time": "0:28:41", "throughput": 5491.64, "total_tokens": 29805040} {"current_steps": 48945, "total_steps": 64460, "loss": 0.1815, "lr": 1.6635325668419088e-06, "epoch": 15.186161960905988, "percentage": 75.93, "elapsed_time": "1:30:27", "remaining_time": "0:28:40", "throughput": 5491.72, "total_tokens": 29808240} {"current_steps": 48950, "total_steps": 64460, "loss": 0.1859, "lr": 1.6625243799107065e-06, "epoch": 15.187713310580206, "percentage": 75.94, "elapsed_time": "1:30:28", "remaining_time": "0:28:40", "throughput": 5491.78, "total_tokens": 29811440} {"current_steps": 48955, "total_steps": 64460, "loss": 0.1866, "lr": 1.6615164376559873e-06, "epoch": 15.189264660254421, "percentage": 75.95, "elapsed_time": "1:30:28", "remaining_time": "0:28:39", "throughput": 5491.89, "total_tokens": 29815408} {"current_steps": 48960, "total_steps": 64460, "loss": 0.169, "lr": 1.6605087401516479e-06, "epoch": 15.190816009928637, "percentage": 75.95, "elapsed_time": "1:30:29", "remaining_time": "0:28:38", "throughput": 5491.89, "total_tokens": 29818096} {"current_steps": 48965, "total_steps": 64460, "loss": 0.2888, "lr": 1.6595012874715622e-06, "epoch": 15.192367359602855, "percentage": 75.96, "elapsed_time": "1:30:29", "remaining_time": "0:28:38", "throughput": 5491.91, "total_tokens": 29820912} {"current_steps": 48970, "total_steps": 64460, "loss": 0.1913, "lr": 1.6584940796895904e-06, "epoch": 15.193918709277071, "percentage": 75.97, "elapsed_time": "1:30:30", "remaining_time": "0:28:37", "throughput": 5491.95, "total_tokens": 29823760} {"current_steps": 48975, "total_steps": 64460, "loss": 0.2282, "lr": 1.657487116879571e-06, "epoch": 15.195470058951287, "percentage": 75.98, "elapsed_time": "1:30:30", "remaining_time": "0:28:37", "throughput": 5491.97, "total_tokens": 29826416} {"current_steps": 48980, "total_steps": 64460, "loss": 0.2074, "lr": 1.6564803991153283e-06, "epoch": 15.197021408625504, "percentage": 75.99, "elapsed_time": "1:30:31", "remaining_time": "0:28:36", "throughput": 5491.94, "total_tokens": 29828848} {"current_steps": 48985, "total_steps": 64460, "loss": 0.1571, "lr": 1.6554739264706644e-06, "epoch": 15.19857275829972, "percentage": 75.99, "elapsed_time": "1:30:31", "remaining_time": "0:28:36", "throughput": 5491.95, "total_tokens": 29831824} {"current_steps": 48990, "total_steps": 64460, "loss": 0.1848, "lr": 1.6544676990193664e-06, "epoch": 15.200124107973938, "percentage": 76.0, "elapsed_time": "1:30:32", "remaining_time": "0:28:35", "throughput": 5491.9, "total_tokens": 29833968} {"current_steps": 48995, "total_steps": 64460, "loss": 0.1424, "lr": 1.6534617168352052e-06, "epoch": 15.201675457648154, "percentage": 76.01, "elapsed_time": "1:30:32", "remaining_time": "0:28:34", "throughput": 5491.96, "total_tokens": 29837072} {"current_steps": 49000, "total_steps": 64460, "loss": 0.1744, "lr": 1.6524559799919272e-06, "epoch": 15.20322680732237, "percentage": 76.02, "elapsed_time": "1:30:33", "remaining_time": "0:28:34", "throughput": 5492.02, "total_tokens": 29840336} {"current_steps": 49005, "total_steps": 64460, "loss": 0.1446, "lr": 1.6514504885632682e-06, "epoch": 15.204778156996587, "percentage": 76.02, "elapsed_time": "1:30:33", "remaining_time": "0:28:33", "throughput": 5492.01, "total_tokens": 29843056} {"current_steps": 49010, "total_steps": 64460, "loss": 0.1801, "lr": 1.6504452426229395e-06, "epoch": 15.206329506670803, "percentage": 76.03, "elapsed_time": "1:30:34", "remaining_time": "0:28:33", "throughput": 5492.02, "total_tokens": 29845904} {"current_steps": 49015, "total_steps": 64460, "loss": 0.1753, "lr": 1.649440242244641e-06, "epoch": 15.207880856345021, "percentage": 76.04, "elapsed_time": "1:30:34", "remaining_time": "0:28:32", "throughput": 5491.98, "total_tokens": 29848432} {"current_steps": 49020, "total_steps": 64460, "loss": 0.236, "lr": 1.6484354875020475e-06, "epoch": 15.209432206019237, "percentage": 76.05, "elapsed_time": "1:30:35", "remaining_time": "0:28:32", "throughput": 5491.99, "total_tokens": 29851120} {"current_steps": 49025, "total_steps": 64460, "loss": 0.2092, "lr": 1.647430978468823e-06, "epoch": 15.210983555693453, "percentage": 76.05, "elapsed_time": "1:30:35", "remaining_time": "0:28:31", "throughput": 5491.97, "total_tokens": 29853936} {"current_steps": 49030, "total_steps": 64460, "loss": 0.2772, "lr": 1.6464267152186063e-06, "epoch": 15.21253490536767, "percentage": 76.06, "elapsed_time": "1:30:36", "remaining_time": "0:28:30", "throughput": 5491.94, "total_tokens": 29856304} {"current_steps": 49035, "total_steps": 64460, "loss": 0.23, "lr": 1.645422697825026e-06, "epoch": 15.214086255041886, "percentage": 76.07, "elapsed_time": "1:30:36", "remaining_time": "0:28:30", "throughput": 5492.02, "total_tokens": 29859632} {"current_steps": 49040, "total_steps": 64460, "loss": 0.2044, "lr": 1.6444189263616838e-06, "epoch": 15.215637604716102, "percentage": 76.08, "elapsed_time": "1:30:37", "remaining_time": "0:28:29", "throughput": 5492.02, "total_tokens": 29862096} {"current_steps": 49045, "total_steps": 64460, "loss": 0.1968, "lr": 1.6434154009021718e-06, "epoch": 15.21718895439032, "percentage": 76.09, "elapsed_time": "1:30:37", "remaining_time": "0:28:29", "throughput": 5492.1, "total_tokens": 29865552} {"current_steps": 49050, "total_steps": 64460, "loss": 0.1709, "lr": 1.6424121215200579e-06, "epoch": 15.218740304064536, "percentage": 76.09, "elapsed_time": "1:30:38", "remaining_time": "0:28:28", "throughput": 5492.22, "total_tokens": 29870192} {"current_steps": 49055, "total_steps": 64460, "loss": 0.2159, "lr": 1.6414090882888944e-06, "epoch": 15.220291653738753, "percentage": 76.1, "elapsed_time": "1:30:39", "remaining_time": "0:28:28", "throughput": 5492.27, "total_tokens": 29873168} {"current_steps": 49060, "total_steps": 64460, "loss": 0.2069, "lr": 1.6404063012822186e-06, "epoch": 15.22184300341297, "percentage": 76.11, "elapsed_time": "1:30:39", "remaining_time": "0:28:27", "throughput": 5492.24, "total_tokens": 29875632} {"current_steps": 49065, "total_steps": 64460, "loss": 0.1586, "lr": 1.6394037605735425e-06, "epoch": 15.223394353087185, "percentage": 76.12, "elapsed_time": "1:30:40", "remaining_time": "0:28:26", "throughput": 5492.37, "total_tokens": 29879856} {"current_steps": 49070, "total_steps": 64460, "loss": 0.15, "lr": 1.6384014662363684e-06, "epoch": 15.224945702761403, "percentage": 76.12, "elapsed_time": "1:30:40", "remaining_time": "0:28:26", "throughput": 5492.46, "total_tokens": 29883152} {"current_steps": 49075, "total_steps": 64460, "loss": 0.2201, "lr": 1.6373994183441715e-06, "epoch": 15.226497052435619, "percentage": 76.13, "elapsed_time": "1:30:41", "remaining_time": "0:28:25", "throughput": 5492.5, "total_tokens": 29886160} {"current_steps": 49080, "total_steps": 64460, "loss": 0.1529, "lr": 1.6363976169704187e-06, "epoch": 15.228048402109836, "percentage": 76.14, "elapsed_time": "1:30:41", "remaining_time": "0:28:25", "throughput": 5492.51, "total_tokens": 29889072} {"current_steps": 49085, "total_steps": 64460, "loss": 0.2315, "lr": 1.6353960621885501e-06, "epoch": 15.229599751784052, "percentage": 76.15, "elapsed_time": "1:30:42", "remaining_time": "0:28:24", "throughput": 5492.57, "total_tokens": 29892688} {"current_steps": 49090, "total_steps": 64460, "loss": 0.1565, "lr": 1.6343947540719946e-06, "epoch": 15.231151101458268, "percentage": 76.16, "elapsed_time": "1:30:43", "remaining_time": "0:28:24", "throughput": 5492.64, "total_tokens": 29896560} {"current_steps": 49095, "total_steps": 64460, "loss": 0.1302, "lr": 1.6333936926941563e-06, "epoch": 15.232702451132486, "percentage": 76.16, "elapsed_time": "1:30:43", "remaining_time": "0:28:23", "throughput": 5492.61, "total_tokens": 29899472} {"current_steps": 49100, "total_steps": 64460, "loss": 0.1206, "lr": 1.6323928781284286e-06, "epoch": 15.234253800806702, "percentage": 76.17, "elapsed_time": "1:30:44", "remaining_time": "0:28:23", "throughput": 5492.72, "total_tokens": 29903440} {"current_steps": 49105, "total_steps": 64460, "loss": 0.1433, "lr": 1.63139231044818e-06, "epoch": 15.235805150480918, "percentage": 76.18, "elapsed_time": "1:30:44", "remaining_time": "0:28:22", "throughput": 5492.67, "total_tokens": 29905872} {"current_steps": 49110, "total_steps": 64460, "loss": 0.1435, "lr": 1.630391989726765e-06, "epoch": 15.237356500155135, "percentage": 76.19, "elapsed_time": "1:30:45", "remaining_time": "0:28:21", "throughput": 5492.71, "total_tokens": 29908816} {"current_steps": 49115, "total_steps": 64460, "loss": 0.2242, "lr": 1.629391916037521e-06, "epoch": 15.238907849829351, "percentage": 76.19, "elapsed_time": "1:30:45", "remaining_time": "0:28:21", "throughput": 5492.77, "total_tokens": 29912080} {"current_steps": 49120, "total_steps": 64460, "loss": 0.1246, "lr": 1.6283920894537618e-06, "epoch": 15.240459199503569, "percentage": 76.2, "elapsed_time": "1:30:46", "remaining_time": "0:28:20", "throughput": 5492.78, "total_tokens": 29915088} {"current_steps": 49125, "total_steps": 64460, "loss": 0.2129, "lr": 1.6273925100487904e-06, "epoch": 15.242010549177785, "percentage": 76.21, "elapsed_time": "1:30:46", "remaining_time": "0:28:20", "throughput": 5492.79, "total_tokens": 29917840} {"current_steps": 49130, "total_steps": 64460, "loss": 0.1288, "lr": 1.6263931778958836e-06, "epoch": 15.243561898852, "percentage": 76.22, "elapsed_time": "1:30:47", "remaining_time": "0:28:19", "throughput": 5492.8, "total_tokens": 29920528} {"current_steps": 49135, "total_steps": 64460, "loss": 0.1594, "lr": 1.6253940930683081e-06, "epoch": 15.245113248526218, "percentage": 76.23, "elapsed_time": "1:30:47", "remaining_time": "0:28:19", "throughput": 5492.85, "total_tokens": 29923536} {"current_steps": 49140, "total_steps": 64460, "loss": 0.082, "lr": 1.6243952556393056e-06, "epoch": 15.246664598200434, "percentage": 76.23, "elapsed_time": "1:30:48", "remaining_time": "0:28:18", "throughput": 5492.92, "total_tokens": 29926576} {"current_steps": 49145, "total_steps": 64460, "loss": 0.1911, "lr": 1.623396665682105e-06, "epoch": 15.248215947874652, "percentage": 76.24, "elapsed_time": "1:30:48", "remaining_time": "0:28:17", "throughput": 5492.9, "total_tokens": 29928880} {"current_steps": 49150, "total_steps": 64460, "loss": 0.3317, "lr": 1.6223983232699126e-06, "epoch": 15.249767297548868, "percentage": 76.25, "elapsed_time": "1:30:49", "remaining_time": "0:28:17", "throughput": 5493.0, "total_tokens": 29932176} {"current_steps": 49155, "total_steps": 64460, "loss": 0.1961, "lr": 1.6214002284759212e-06, "epoch": 15.251318647223084, "percentage": 76.26, "elapsed_time": "1:30:49", "remaining_time": "0:28:16", "throughput": 5492.99, "total_tokens": 29934800} {"current_steps": 49160, "total_steps": 64460, "loss": 0.1873, "lr": 1.6204023813733e-06, "epoch": 15.252869996897301, "percentage": 76.26, "elapsed_time": "1:30:50", "remaining_time": "0:28:16", "throughput": 5492.94, "total_tokens": 29937072} {"current_steps": 49165, "total_steps": 64460, "loss": 0.2917, "lr": 1.6194047820352066e-06, "epoch": 15.254421346571517, "percentage": 76.27, "elapsed_time": "1:30:50", "remaining_time": "0:28:15", "throughput": 5493.03, "total_tokens": 29940592} {"current_steps": 49170, "total_steps": 64460, "loss": 0.1984, "lr": 1.618407430534773e-06, "epoch": 15.255972696245733, "percentage": 76.28, "elapsed_time": "1:30:51", "remaining_time": "0:28:15", "throughput": 5493.09, "total_tokens": 29943856} {"current_steps": 49175, "total_steps": 64460, "loss": 0.262, "lr": 1.617410326945119e-06, "epoch": 15.25752404591995, "percentage": 76.29, "elapsed_time": "1:30:51", "remaining_time": "0:28:14", "throughput": 5493.08, "total_tokens": 29946512} {"current_steps": 49180, "total_steps": 64460, "loss": 0.2466, "lr": 1.616413471339346e-06, "epoch": 15.259075395594166, "percentage": 76.3, "elapsed_time": "1:30:52", "remaining_time": "0:28:13", "throughput": 5493.09, "total_tokens": 29949328} {"current_steps": 49185, "total_steps": 64460, "loss": 0.2258, "lr": 1.6154168637905304e-06, "epoch": 15.260626745268384, "percentage": 76.3, "elapsed_time": "1:30:52", "remaining_time": "0:28:13", "throughput": 5493.05, "total_tokens": 29951760} {"current_steps": 49190, "total_steps": 64460, "loss": 0.1435, "lr": 1.614420504371741e-06, "epoch": 15.2621780949426, "percentage": 76.31, "elapsed_time": "1:30:53", "remaining_time": "0:28:12", "throughput": 5493.11, "total_tokens": 29954928} {"current_steps": 49195, "total_steps": 64460, "loss": 0.2694, "lr": 1.6134243931560173e-06, "epoch": 15.263729444616816, "percentage": 76.32, "elapsed_time": "1:30:53", "remaining_time": "0:28:12", "throughput": 5493.26, "total_tokens": 29959344} {"current_steps": 49200, "total_steps": 64460, "loss": 0.2028, "lr": 1.6124285302163906e-06, "epoch": 15.265280794291034, "percentage": 76.33, "elapsed_time": "1:30:54", "remaining_time": "0:28:11", "throughput": 5493.32, "total_tokens": 29962512} {"current_steps": 49205, "total_steps": 64460, "loss": 0.2178, "lr": 1.6114329156258663e-06, "epoch": 15.26683214396525, "percentage": 76.33, "elapsed_time": "1:30:54", "remaining_time": "0:28:11", "throughput": 5493.36, "total_tokens": 29965296} {"current_steps": 49210, "total_steps": 64460, "loss": 0.1489, "lr": 1.610437549457437e-06, "epoch": 15.268383493639467, "percentage": 76.34, "elapsed_time": "1:30:55", "remaining_time": "0:28:10", "throughput": 5493.32, "total_tokens": 29967600} {"current_steps": 49215, "total_steps": 64460, "loss": 0.1842, "lr": 1.6094424317840724e-06, "epoch": 15.269934843313683, "percentage": 76.35, "elapsed_time": "1:30:55", "remaining_time": "0:28:10", "throughput": 5493.39, "total_tokens": 29970736} {"current_steps": 49220, "total_steps": 64460, "loss": 0.17, "lr": 1.6084475626787289e-06, "epoch": 15.271486192987899, "percentage": 76.36, "elapsed_time": "1:30:56", "remaining_time": "0:28:09", "throughput": 5493.45, "total_tokens": 29974544} {"current_steps": 49225, "total_steps": 64460, "loss": 0.1908, "lr": 1.6074529422143398e-06, "epoch": 15.273037542662117, "percentage": 76.37, "elapsed_time": "1:30:56", "remaining_time": "0:28:08", "throughput": 5493.54, "total_tokens": 29977744} {"current_steps": 49230, "total_steps": 64460, "loss": 0.2083, "lr": 1.6064585704638236e-06, "epoch": 15.274588892336332, "percentage": 76.37, "elapsed_time": "1:30:57", "remaining_time": "0:28:08", "throughput": 5493.61, "total_tokens": 29981104} {"current_steps": 49235, "total_steps": 64460, "loss": 0.2104, "lr": 1.605464447500082e-06, "epoch": 15.276140242010548, "percentage": 76.38, "elapsed_time": "1:30:58", "remaining_time": "0:28:07", "throughput": 5493.7, "total_tokens": 29985488} {"current_steps": 49240, "total_steps": 64460, "loss": 0.119, "lr": 1.6044705733959914e-06, "epoch": 15.277691591684766, "percentage": 76.39, "elapsed_time": "1:30:58", "remaining_time": "0:28:07", "throughput": 5493.8, "total_tokens": 29988912} {"current_steps": 49245, "total_steps": 64460, "loss": 0.1411, "lr": 1.6034769482244188e-06, "epoch": 15.279242941358982, "percentage": 76.4, "elapsed_time": "1:30:59", "remaining_time": "0:28:06", "throughput": 5493.87, "total_tokens": 29992592} {"current_steps": 49250, "total_steps": 64460, "loss": 0.2398, "lr": 1.602483572058205e-06, "epoch": 15.2807942910332, "percentage": 76.4, "elapsed_time": "1:30:59", "remaining_time": "0:28:06", "throughput": 5493.88, "total_tokens": 29995312} {"current_steps": 49255, "total_steps": 64460, "loss": 0.2764, "lr": 1.6014904449701796e-06, "epoch": 15.282345640707415, "percentage": 76.41, "elapsed_time": "1:31:00", "remaining_time": "0:28:05", "throughput": 5493.92, "total_tokens": 29998128} {"current_steps": 49260, "total_steps": 64460, "loss": 0.2878, "lr": 1.6004975670331475e-06, "epoch": 15.283896990381631, "percentage": 76.42, "elapsed_time": "1:31:00", "remaining_time": "0:28:05", "throughput": 5493.87, "total_tokens": 30000560} {"current_steps": 49265, "total_steps": 64460, "loss": 0.2088, "lr": 1.5995049383199013e-06, "epoch": 15.285448340055849, "percentage": 76.43, "elapsed_time": "1:31:01", "remaining_time": "0:28:04", "throughput": 5493.9, "total_tokens": 30003280} {"current_steps": 49270, "total_steps": 64460, "loss": 0.1964, "lr": 1.598512558903209e-06, "epoch": 15.286999689730065, "percentage": 76.43, "elapsed_time": "1:31:01", "remaining_time": "0:28:03", "throughput": 5493.95, "total_tokens": 30006192} {"current_steps": 49275, "total_steps": 64460, "loss": 0.2146, "lr": 1.5975204288558283e-06, "epoch": 15.288551039404283, "percentage": 76.44, "elapsed_time": "1:31:02", "remaining_time": "0:28:03", "throughput": 5493.97, "total_tokens": 30009168} {"current_steps": 49280, "total_steps": 64460, "loss": 0.2044, "lr": 1.5965285482504893e-06, "epoch": 15.290102389078498, "percentage": 76.45, "elapsed_time": "1:31:02", "remaining_time": "0:28:02", "throughput": 5493.99, "total_tokens": 30011952} {"current_steps": 49285, "total_steps": 64460, "loss": 0.1587, "lr": 1.5955369171599128e-06, "epoch": 15.291653738752714, "percentage": 76.46, "elapsed_time": "1:31:03", "remaining_time": "0:28:02", "throughput": 5494.04, "total_tokens": 30015216} {"current_steps": 49290, "total_steps": 64460, "loss": 0.1726, "lr": 1.594545535656793e-06, "epoch": 15.293205088426932, "percentage": 76.47, "elapsed_time": "1:31:03", "remaining_time": "0:28:01", "throughput": 5494.0, "total_tokens": 30017424} {"current_steps": 49295, "total_steps": 64460, "loss": 0.1605, "lr": 1.5935544038138123e-06, "epoch": 15.294756438101148, "percentage": 76.47, "elapsed_time": "1:31:04", "remaining_time": "0:28:00", "throughput": 5494.04, "total_tokens": 30020208} {"current_steps": 49300, "total_steps": 64460, "loss": 0.1878, "lr": 1.592563521703634e-06, "epoch": 15.296307787775364, "percentage": 76.48, "elapsed_time": "1:31:04", "remaining_time": "0:28:00", "throughput": 5494.08, "total_tokens": 30023440} {"current_steps": 49305, "total_steps": 64460, "loss": 0.2084, "lr": 1.591572889398898e-06, "epoch": 15.297859137449581, "percentage": 76.49, "elapsed_time": "1:31:05", "remaining_time": "0:27:59", "throughput": 5494.09, "total_tokens": 30026032} {"current_steps": 49310, "total_steps": 64460, "loss": 0.1595, "lr": 1.5905825069722324e-06, "epoch": 15.299410487123797, "percentage": 76.5, "elapsed_time": "1:31:05", "remaining_time": "0:27:59", "throughput": 5494.08, "total_tokens": 30028880} {"current_steps": 49315, "total_steps": 64460, "loss": 0.179, "lr": 1.589592374496241e-06, "epoch": 15.300961836798015, "percentage": 76.5, "elapsed_time": "1:31:06", "remaining_time": "0:27:58", "throughput": 5494.15, "total_tokens": 30032336} {"current_steps": 49320, "total_steps": 64460, "loss": 0.2834, "lr": 1.5886024920435155e-06, "epoch": 15.30251318647223, "percentage": 76.51, "elapsed_time": "1:31:06", "remaining_time": "0:27:58", "throughput": 5494.24, "total_tokens": 30035600} {"current_steps": 49325, "total_steps": 64460, "loss": 0.1902, "lr": 1.5876128596866231e-06, "epoch": 15.304064536146447, "percentage": 76.52, "elapsed_time": "1:31:07", "remaining_time": "0:27:57", "throughput": 5494.34, "total_tokens": 30039184} {"current_steps": 49330, "total_steps": 64460, "loss": 0.1796, "lr": 1.5866234774981175e-06, "epoch": 15.305615885820664, "percentage": 76.53, "elapsed_time": "1:31:07", "remaining_time": "0:27:57", "throughput": 5494.33, "total_tokens": 30041584} {"current_steps": 49335, "total_steps": 64460, "loss": 0.1946, "lr": 1.5856343455505308e-06, "epoch": 15.30716723549488, "percentage": 76.54, "elapsed_time": "1:31:08", "remaining_time": "0:27:56", "throughput": 5494.29, "total_tokens": 30043984} {"current_steps": 49340, "total_steps": 64460, "loss": 0.2281, "lr": 1.58464546391638e-06, "epoch": 15.308718585169098, "percentage": 76.54, "elapsed_time": "1:31:08", "remaining_time": "0:27:55", "throughput": 5494.35, "total_tokens": 30047152} {"current_steps": 49345, "total_steps": 64460, "loss": 0.1555, "lr": 1.5836568326681583e-06, "epoch": 15.310269934843314, "percentage": 76.55, "elapsed_time": "1:31:09", "remaining_time": "0:27:55", "throughput": 5494.43, "total_tokens": 30050640} {"current_steps": 49350, "total_steps": 64460, "loss": 0.2417, "lr": 1.582668451878347e-06, "epoch": 15.31182128451753, "percentage": 76.56, "elapsed_time": "1:31:09", "remaining_time": "0:27:54", "throughput": 5494.51, "total_tokens": 30054000} {"current_steps": 49355, "total_steps": 64460, "loss": 0.143, "lr": 1.5816803216194071e-06, "epoch": 15.313372634191747, "percentage": 76.57, "elapsed_time": "1:31:10", "remaining_time": "0:27:54", "throughput": 5494.65, "total_tokens": 30058160} {"current_steps": 49360, "total_steps": 64460, "loss": 0.149, "lr": 1.5806924419637765e-06, "epoch": 15.314923983865963, "percentage": 76.57, "elapsed_time": "1:31:10", "remaining_time": "0:27:53", "throughput": 5494.75, "total_tokens": 30061552} {"current_steps": 49365, "total_steps": 64460, "loss": 0.2009, "lr": 1.5797048129838827e-06, "epoch": 15.316475333540179, "percentage": 76.58, "elapsed_time": "1:31:11", "remaining_time": "0:27:53", "throughput": 5494.78, "total_tokens": 30064560} {"current_steps": 49370, "total_steps": 64460, "loss": 0.1619, "lr": 1.5787174347521267e-06, "epoch": 15.318026683214397, "percentage": 76.59, "elapsed_time": "1:31:12", "remaining_time": "0:27:52", "throughput": 5494.83, "total_tokens": 30067856} {"current_steps": 49375, "total_steps": 64460, "loss": 0.1804, "lr": 1.5777303073408978e-06, "epoch": 15.319578032888613, "percentage": 76.6, "elapsed_time": "1:31:12", "remaining_time": "0:27:51", "throughput": 5494.87, "total_tokens": 30071024} {"current_steps": 49380, "total_steps": 64460, "loss": 0.2746, "lr": 1.5767434308225603e-06, "epoch": 15.32112938256283, "percentage": 76.61, "elapsed_time": "1:31:13", "remaining_time": "0:27:51", "throughput": 5494.86, "total_tokens": 30074352} {"current_steps": 49385, "total_steps": 64460, "loss": 0.1864, "lr": 1.5757568052694705e-06, "epoch": 15.322680732237046, "percentage": 76.61, "elapsed_time": "1:31:13", "remaining_time": "0:27:50", "throughput": 5494.87, "total_tokens": 30077168} {"current_steps": 49390, "total_steps": 64460, "loss": 0.1405, "lr": 1.5747704307539536e-06, "epoch": 15.324232081911262, "percentage": 76.62, "elapsed_time": "1:31:14", "remaining_time": "0:27:50", "throughput": 5494.89, "total_tokens": 30080080} {"current_steps": 49395, "total_steps": 64460, "loss": 0.1374, "lr": 1.5737843073483266e-06, "epoch": 15.32578343158548, "percentage": 76.63, "elapsed_time": "1:31:14", "remaining_time": "0:27:49", "throughput": 5495.01, "total_tokens": 30084592} {"current_steps": 49400, "total_steps": 64460, "loss": 0.1684, "lr": 1.572798435124881e-06, "epoch": 15.327334781259696, "percentage": 76.64, "elapsed_time": "1:31:15", "remaining_time": "0:27:49", "throughput": 5495.0, "total_tokens": 30087088} {"current_steps": 49405, "total_steps": 64460, "loss": 0.1862, "lr": 1.5718128141558958e-06, "epoch": 15.328886130933913, "percentage": 76.64, "elapsed_time": "1:31:15", "remaining_time": "0:27:48", "throughput": 5495.09, "total_tokens": 30090608} {"current_steps": 49410, "total_steps": 64460, "loss": 0.2016, "lr": 1.5708274445136256e-06, "epoch": 15.33043748060813, "percentage": 76.65, "elapsed_time": "1:31:16", "remaining_time": "0:27:48", "throughput": 5495.05, "total_tokens": 30093200} {"current_steps": 49415, "total_steps": 64460, "loss": 0.1955, "lr": 1.5698423262703128e-06, "epoch": 15.331988830282345, "percentage": 76.66, "elapsed_time": "1:31:17", "remaining_time": "0:27:47", "throughput": 5495.16, "total_tokens": 30097776} {"current_steps": 49420, "total_steps": 64460, "loss": 0.2253, "lr": 1.5688574594981749e-06, "epoch": 15.333540179956563, "percentage": 76.67, "elapsed_time": "1:31:17", "remaining_time": "0:27:47", "throughput": 5495.2, "total_tokens": 30101040} {"current_steps": 49425, "total_steps": 64460, "loss": 0.2026, "lr": 1.567872844269418e-06, "epoch": 15.335091529630779, "percentage": 76.68, "elapsed_time": "1:31:18", "remaining_time": "0:27:46", "throughput": 5495.22, "total_tokens": 30104560} {"current_steps": 49430, "total_steps": 64460, "loss": 0.172, "lr": 1.5668884806562217e-06, "epoch": 15.336642879304996, "percentage": 76.68, "elapsed_time": "1:31:18", "remaining_time": "0:27:45", "throughput": 5495.22, "total_tokens": 30107248} {"current_steps": 49435, "total_steps": 64460, "loss": 0.1882, "lr": 1.5659043687307547e-06, "epoch": 15.338194228979212, "percentage": 76.69, "elapsed_time": "1:31:19", "remaining_time": "0:27:45", "throughput": 5495.21, "total_tokens": 30110192} {"current_steps": 49440, "total_steps": 64460, "loss": 0.2053, "lr": 1.5649205085651642e-06, "epoch": 15.339745578653428, "percentage": 76.7, "elapsed_time": "1:31:19", "remaining_time": "0:27:44", "throughput": 5495.29, "total_tokens": 30113680} {"current_steps": 49445, "total_steps": 64460, "loss": 0.193, "lr": 1.5639369002315769e-06, "epoch": 15.341296928327646, "percentage": 76.71, "elapsed_time": "1:31:20", "remaining_time": "0:27:44", "throughput": 5495.34, "total_tokens": 30118096} {"current_steps": 49450, "total_steps": 64460, "loss": 0.1628, "lr": 1.5629535438021049e-06, "epoch": 15.342848278001862, "percentage": 76.71, "elapsed_time": "1:31:21", "remaining_time": "0:27:43", "throughput": 5495.43, "total_tokens": 30121456} {"current_steps": 49455, "total_steps": 64460, "loss": 0.1848, "lr": 1.5619704393488372e-06, "epoch": 15.344399627676077, "percentage": 76.72, "elapsed_time": "1:31:21", "remaining_time": "0:27:43", "throughput": 5495.39, "total_tokens": 30123952} {"current_steps": 49460, "total_steps": 64460, "loss": 0.1699, "lr": 1.5609875869438508e-06, "epoch": 15.345950977350295, "percentage": 76.73, "elapsed_time": "1:31:22", "remaining_time": "0:27:42", "throughput": 5495.35, "total_tokens": 30126544} {"current_steps": 49465, "total_steps": 64460, "loss": 0.1721, "lr": 1.5600049866591966e-06, "epoch": 15.347502327024511, "percentage": 76.74, "elapsed_time": "1:31:22", "remaining_time": "0:27:42", "throughput": 5495.42, "total_tokens": 30129904} {"current_steps": 49470, "total_steps": 64460, "loss": 0.1919, "lr": 1.5590226385669138e-06, "epoch": 15.349053676698729, "percentage": 76.75, "elapsed_time": "1:31:23", "remaining_time": "0:27:41", "throughput": 5495.41, "total_tokens": 30132496} {"current_steps": 49475, "total_steps": 64460, "loss": 0.1487, "lr": 1.5580405427390172e-06, "epoch": 15.350605026372945, "percentage": 76.75, "elapsed_time": "1:31:23", "remaining_time": "0:27:40", "throughput": 5495.48, "total_tokens": 30135888} {"current_steps": 49480, "total_steps": 64460, "loss": 0.164, "lr": 1.5570586992475095e-06, "epoch": 15.35215637604716, "percentage": 76.76, "elapsed_time": "1:31:24", "remaining_time": "0:27:40", "throughput": 5495.42, "total_tokens": 30138608} {"current_steps": 49485, "total_steps": 64460, "loss": 0.1662, "lr": 1.5560771081643682e-06, "epoch": 15.353707725721378, "percentage": 76.77, "elapsed_time": "1:31:24", "remaining_time": "0:27:39", "throughput": 5495.46, "total_tokens": 30141424} {"current_steps": 49490, "total_steps": 64460, "loss": 0.1456, "lr": 1.5550957695615582e-06, "epoch": 15.355259075395594, "percentage": 76.78, "elapsed_time": "1:31:25", "remaining_time": "0:27:39", "throughput": 5495.43, "total_tokens": 30143952} {"current_steps": 49495, "total_steps": 64460, "loss": 0.1902, "lr": 1.554114683511021e-06, "epoch": 15.35681042506981, "percentage": 76.78, "elapsed_time": "1:31:25", "remaining_time": "0:27:38", "throughput": 5495.54, "total_tokens": 30147888} {"current_steps": 49500, "total_steps": 64460, "loss": 0.1828, "lr": 1.5531338500846827e-06, "epoch": 15.358361774744028, "percentage": 76.79, "elapsed_time": "1:31:26", "remaining_time": "0:27:38", "throughput": 5495.48, "total_tokens": 30150256} {"current_steps": 49505, "total_steps": 64460, "loss": 0.1902, "lr": 1.5521532693544517e-06, "epoch": 15.359913124418243, "percentage": 76.8, "elapsed_time": "1:31:26", "remaining_time": "0:27:37", "throughput": 5495.53, "total_tokens": 30153776} {"current_steps": 49510, "total_steps": 64460, "loss": 0.1619, "lr": 1.5511729413922134e-06, "epoch": 15.361464474092461, "percentage": 76.81, "elapsed_time": "1:31:27", "remaining_time": "0:27:36", "throughput": 5495.49, "total_tokens": 30156080} {"current_steps": 49515, "total_steps": 64460, "loss": 0.184, "lr": 1.5501928662698397e-06, "epoch": 15.363015823766677, "percentage": 76.82, "elapsed_time": "1:31:27", "remaining_time": "0:27:36", "throughput": 5495.51, "total_tokens": 30159184} {"current_steps": 49520, "total_steps": 64460, "loss": 0.1447, "lr": 1.5492130440591797e-06, "epoch": 15.364567173440893, "percentage": 76.82, "elapsed_time": "1:31:28", "remaining_time": "0:27:35", "throughput": 5495.58, "total_tokens": 30162896} {"current_steps": 49525, "total_steps": 64460, "loss": 0.09, "lr": 1.5482334748320681e-06, "epoch": 15.36611852311511, "percentage": 76.83, "elapsed_time": "1:31:29", "remaining_time": "0:27:35", "throughput": 5495.68, "total_tokens": 30166896} {"current_steps": 49530, "total_steps": 64460, "loss": 0.1585, "lr": 1.5472541586603163e-06, "epoch": 15.367669872789326, "percentage": 76.84, "elapsed_time": "1:31:29", "remaining_time": "0:27:34", "throughput": 5495.66, "total_tokens": 30169552} {"current_steps": 49535, "total_steps": 64460, "loss": 0.2198, "lr": 1.546275095615723e-06, "epoch": 15.369221222463544, "percentage": 76.85, "elapsed_time": "1:31:30", "remaining_time": "0:27:34", "throughput": 5495.5, "total_tokens": 30171600} {"current_steps": 49540, "total_steps": 64460, "loss": 0.2174, "lr": 1.545296285770062e-06, "epoch": 15.37077257213776, "percentage": 76.85, "elapsed_time": "1:31:30", "remaining_time": "0:27:33", "throughput": 5495.39, "total_tokens": 30174096} {"current_steps": 49545, "total_steps": 64460, "loss": 0.172, "lr": 1.5443177291950946e-06, "epoch": 15.372323921811976, "percentage": 76.86, "elapsed_time": "1:31:31", "remaining_time": "0:27:33", "throughput": 5495.35, "total_tokens": 30176496} {"current_steps": 49550, "total_steps": 64460, "loss": 0.1764, "lr": 1.5433394259625573e-06, "epoch": 15.373875271486193, "percentage": 76.87, "elapsed_time": "1:31:31", "remaining_time": "0:27:32", "throughput": 5495.32, "total_tokens": 30179152} {"current_steps": 49555, "total_steps": 64460, "loss": 0.1741, "lr": 1.542361376144173e-06, "epoch": 15.37542662116041, "percentage": 76.88, "elapsed_time": "1:31:32", "remaining_time": "0:27:32", "throughput": 5495.34, "total_tokens": 30183088} {"current_steps": 49560, "total_steps": 64460, "loss": 0.1823, "lr": 1.5413835798116467e-06, "epoch": 15.376977970834627, "percentage": 76.88, "elapsed_time": "1:31:33", "remaining_time": "0:27:31", "throughput": 5495.41, "total_tokens": 30186416} {"current_steps": 49565, "total_steps": 64460, "loss": 0.1516, "lr": 1.5404060370366576e-06, "epoch": 15.378529320508843, "percentage": 76.89, "elapsed_time": "1:31:33", "remaining_time": "0:27:30", "throughput": 5495.46, "total_tokens": 30189712} {"current_steps": 49570, "total_steps": 64460, "loss": 0.2612, "lr": 1.539428747890876e-06, "epoch": 15.380080670183059, "percentage": 76.9, "elapsed_time": "1:31:34", "remaining_time": "0:27:30", "throughput": 5495.47, "total_tokens": 30192592} {"current_steps": 49575, "total_steps": 64460, "loss": 0.1905, "lr": 1.5384517124459441e-06, "epoch": 15.381632019857276, "percentage": 76.91, "elapsed_time": "1:31:34", "remaining_time": "0:27:29", "throughput": 5495.43, "total_tokens": 30195056} {"current_steps": 49580, "total_steps": 64460, "loss": 0.1589, "lr": 1.5374749307734948e-06, "epoch": 15.383183369531492, "percentage": 76.92, "elapsed_time": "1:31:35", "remaining_time": "0:27:29", "throughput": 5495.4, "total_tokens": 30197648} {"current_steps": 49585, "total_steps": 64460, "loss": 0.1848, "lr": 1.5364984029451341e-06, "epoch": 15.384734719205708, "percentage": 76.92, "elapsed_time": "1:31:35", "remaining_time": "0:27:28", "throughput": 5495.36, "total_tokens": 30200304} {"current_steps": 49590, "total_steps": 64460, "loss": 0.223, "lr": 1.5355221290324556e-06, "epoch": 15.386286068879926, "percentage": 76.93, "elapsed_time": "1:31:36", "remaining_time": "0:27:28", "throughput": 5495.44, "total_tokens": 30203824} {"current_steps": 49595, "total_steps": 64460, "loss": 0.1659, "lr": 1.5345461091070291e-06, "epoch": 15.387837418554142, "percentage": 76.94, "elapsed_time": "1:31:36", "remaining_time": "0:27:27", "throughput": 5495.39, "total_tokens": 30206192} {"current_steps": 49600, "total_steps": 64460, "loss": 0.1431, "lr": 1.5335703432404114e-06, "epoch": 15.38938876822836, "percentage": 76.95, "elapsed_time": "1:31:37", "remaining_time": "0:27:26", "throughput": 5495.49, "total_tokens": 30210064} {"current_steps": 49605, "total_steps": 64460, "loss": 0.1952, "lr": 1.5325948315041345e-06, "epoch": 15.390940117902575, "percentage": 76.95, "elapsed_time": "1:31:37", "remaining_time": "0:27:26", "throughput": 5495.46, "total_tokens": 30212528} {"current_steps": 49610, "total_steps": 64460, "loss": 0.1449, "lr": 1.5316195739697187e-06, "epoch": 15.392491467576791, "percentage": 76.96, "elapsed_time": "1:31:38", "remaining_time": "0:27:25", "throughput": 5495.57, "total_tokens": 30216624} {"current_steps": 49615, "total_steps": 64460, "loss": 0.2517, "lr": 1.5306445707086582e-06, "epoch": 15.394042817251009, "percentage": 76.97, "elapsed_time": "1:31:38", "remaining_time": "0:27:25", "throughput": 5495.56, "total_tokens": 30219376} {"current_steps": 49620, "total_steps": 64460, "loss": 0.1872, "lr": 1.5296698217924339e-06, "epoch": 15.395594166925225, "percentage": 76.98, "elapsed_time": "1:31:39", "remaining_time": "0:27:24", "throughput": 5495.55, "total_tokens": 30222128} {"current_steps": 49625, "total_steps": 64460, "loss": 0.2086, "lr": 1.5286953272925082e-06, "epoch": 15.39714551659944, "percentage": 76.99, "elapsed_time": "1:31:39", "remaining_time": "0:27:24", "throughput": 5495.52, "total_tokens": 30224656} {"current_steps": 49630, "total_steps": 64460, "loss": 0.2622, "lr": 1.5277210872803194e-06, "epoch": 15.398696866273658, "percentage": 76.99, "elapsed_time": "1:31:40", "remaining_time": "0:27:23", "throughput": 5495.42, "total_tokens": 30226864} {"current_steps": 49635, "total_steps": 64460, "loss": 0.1666, "lr": 1.5267471018272945e-06, "epoch": 15.400248215947874, "percentage": 77.0, "elapsed_time": "1:31:41", "remaining_time": "0:27:23", "throughput": 5495.58, "total_tokens": 30232240} {"current_steps": 49640, "total_steps": 64460, "loss": 0.1948, "lr": 1.525773371004835e-06, "epoch": 15.401799565622092, "percentage": 77.01, "elapsed_time": "1:31:41", "remaining_time": "0:27:22", "throughput": 5495.54, "total_tokens": 30234832} {"current_steps": 49645, "total_steps": 64460, "loss": 0.1965, "lr": 1.5247998948843306e-06, "epoch": 15.403350915296308, "percentage": 77.02, "elapsed_time": "1:31:42", "remaining_time": "0:27:21", "throughput": 5495.41, "total_tokens": 30236912} {"current_steps": 49650, "total_steps": 64460, "loss": 0.2347, "lr": 1.5238266735371443e-06, "epoch": 15.404902264970524, "percentage": 77.02, "elapsed_time": "1:31:42", "remaining_time": "0:27:21", "throughput": 5495.34, "total_tokens": 30239664} {"current_steps": 49655, "total_steps": 64460, "loss": 0.1371, "lr": 1.5228537070346284e-06, "epoch": 15.406453614644741, "percentage": 77.03, "elapsed_time": "1:31:43", "remaining_time": "0:27:20", "throughput": 5495.38, "total_tokens": 30242864} {"current_steps": 49660, "total_steps": 64460, "loss": 0.1579, "lr": 1.52188099544811e-06, "epoch": 15.408004964318957, "percentage": 77.04, "elapsed_time": "1:31:43", "remaining_time": "0:27:20", "throughput": 5495.37, "total_tokens": 30245648} {"current_steps": 49665, "total_steps": 64460, "loss": 0.137, "lr": 1.5209085388489032e-06, "epoch": 15.409556313993175, "percentage": 77.05, "elapsed_time": "1:31:44", "remaining_time": "0:27:19", "throughput": 5495.41, "total_tokens": 30248784} {"current_steps": 49670, "total_steps": 64460, "loss": 0.1735, "lr": 1.5199363373082976e-06, "epoch": 15.41110766366739, "percentage": 77.06, "elapsed_time": "1:31:44", "remaining_time": "0:27:19", "throughput": 5495.4, "total_tokens": 30251472} {"current_steps": 49675, "total_steps": 64460, "loss": 0.1682, "lr": 1.5189643908975682e-06, "epoch": 15.412659013341607, "percentage": 77.06, "elapsed_time": "1:31:45", "remaining_time": "0:27:18", "throughput": 5495.38, "total_tokens": 30254064} {"current_steps": 49680, "total_steps": 64460, "loss": 0.1752, "lr": 1.5179926996879729e-06, "epoch": 15.414210363015824, "percentage": 77.07, "elapsed_time": "1:31:45", "remaining_time": "0:27:18", "throughput": 5495.3, "total_tokens": 30256336} {"current_steps": 49685, "total_steps": 64460, "loss": 0.177, "lr": 1.5170212637507437e-06, "epoch": 15.41576171269004, "percentage": 77.08, "elapsed_time": "1:31:46", "remaining_time": "0:27:17", "throughput": 5495.3, "total_tokens": 30259184} {"current_steps": 49690, "total_steps": 64460, "loss": 0.156, "lr": 1.5160500831571024e-06, "epoch": 15.417313062364258, "percentage": 77.09, "elapsed_time": "1:31:46", "remaining_time": "0:27:16", "throughput": 5495.39, "total_tokens": 30262960} {"current_steps": 49695, "total_steps": 64460, "loss": 0.1943, "lr": 1.5150791579782443e-06, "epoch": 15.418864412038474, "percentage": 77.09, "elapsed_time": "1:31:47", "remaining_time": "0:27:16", "throughput": 5495.42, "total_tokens": 30266000} {"current_steps": 49700, "total_steps": 64460, "loss": 0.19, "lr": 1.514108488285353e-06, "epoch": 15.42041576171269, "percentage": 77.1, "elapsed_time": "1:31:47", "remaining_time": "0:27:15", "throughput": 5495.33, "total_tokens": 30268144} {"current_steps": 49705, "total_steps": 64460, "loss": 0.1353, "lr": 1.513138074149587e-06, "epoch": 15.421967111386907, "percentage": 77.11, "elapsed_time": "1:31:48", "remaining_time": "0:27:15", "throughput": 5495.4, "total_tokens": 30272304} {"current_steps": 49710, "total_steps": 64460, "loss": 0.2476, "lr": 1.5121679156420932e-06, "epoch": 15.423518461061123, "percentage": 77.12, "elapsed_time": "1:31:49", "remaining_time": "0:27:14", "throughput": 5495.41, "total_tokens": 30275024} {"current_steps": 49715, "total_steps": 64460, "loss": 0.1914, "lr": 1.511198012833991e-06, "epoch": 15.425069810735339, "percentage": 77.13, "elapsed_time": "1:31:49", "remaining_time": "0:27:14", "throughput": 5495.34, "total_tokens": 30277360} {"current_steps": 49720, "total_steps": 64460, "loss": 0.2763, "lr": 1.5102283657963895e-06, "epoch": 15.426621160409557, "percentage": 77.13, "elapsed_time": "1:31:50", "remaining_time": "0:27:13", "throughput": 5495.39, "total_tokens": 30280752} {"current_steps": 49725, "total_steps": 64460, "loss": 0.1469, "lr": 1.5092589746003727e-06, "epoch": 15.428172510083773, "percentage": 77.14, "elapsed_time": "1:31:50", "remaining_time": "0:27:13", "throughput": 5495.44, "total_tokens": 30284112} {"current_steps": 49730, "total_steps": 64460, "loss": 0.1781, "lr": 1.5082898393170115e-06, "epoch": 15.42972385975799, "percentage": 77.15, "elapsed_time": "1:31:51", "remaining_time": "0:27:12", "throughput": 5495.36, "total_tokens": 30286384} {"current_steps": 49735, "total_steps": 64460, "loss": 0.1502, "lr": 1.507320960017351e-06, "epoch": 15.431275209432206, "percentage": 77.16, "elapsed_time": "1:31:51", "remaining_time": "0:27:11", "throughput": 5495.29, "total_tokens": 30289104} {"current_steps": 49740, "total_steps": 64460, "loss": 0.1636, "lr": 1.5063523367724237e-06, "epoch": 15.432826559106422, "percentage": 77.16, "elapsed_time": "1:31:52", "remaining_time": "0:27:11", "throughput": 5495.34, "total_tokens": 30292016} {"current_steps": 49745, "total_steps": 64460, "loss": 0.1719, "lr": 1.505383969653243e-06, "epoch": 15.43437790878064, "percentage": 77.17, "elapsed_time": "1:31:52", "remaining_time": "0:27:10", "throughput": 5495.2, "total_tokens": 30294320} {"current_steps": 49750, "total_steps": 64460, "loss": 0.1673, "lr": 1.5044158587307977e-06, "epoch": 15.435929258454856, "percentage": 77.18, "elapsed_time": "1:31:53", "remaining_time": "0:27:10", "throughput": 5495.2, "total_tokens": 30297168} {"current_steps": 49755, "total_steps": 64460, "loss": 0.1207, "lr": 1.5034480040760658e-06, "epoch": 15.437480608129071, "percentage": 77.19, "elapsed_time": "1:31:53", "remaining_time": "0:27:09", "throughput": 5495.22, "total_tokens": 30300624} {"current_steps": 49760, "total_steps": 64460, "loss": 0.1269, "lr": 1.5024804057599984e-06, "epoch": 15.439031957803289, "percentage": 77.2, "elapsed_time": "1:31:54", "remaining_time": "0:27:09", "throughput": 5495.17, "total_tokens": 30303312} {"current_steps": 49765, "total_steps": 64460, "loss": 0.154, "lr": 1.5015130638535363e-06, "epoch": 15.440583307477505, "percentage": 77.2, "elapsed_time": "1:31:55", "remaining_time": "0:27:08", "throughput": 5495.22, "total_tokens": 30306608} {"current_steps": 49770, "total_steps": 64460, "loss": 0.2358, "lr": 1.5005459784275932e-06, "epoch": 15.442134657151723, "percentage": 77.21, "elapsed_time": "1:31:55", "remaining_time": "0:27:07", "throughput": 5495.28, "total_tokens": 30309712} {"current_steps": 49775, "total_steps": 64460, "loss": 0.1567, "lr": 1.4995791495530715e-06, "epoch": 15.443686006825939, "percentage": 77.22, "elapsed_time": "1:31:56", "remaining_time": "0:27:07", "throughput": 5495.23, "total_tokens": 30312080} {"current_steps": 49780, "total_steps": 64460, "loss": 0.1584, "lr": 1.498612577300847e-06, "epoch": 15.445237356500154, "percentage": 77.23, "elapsed_time": "1:31:56", "remaining_time": "0:27:06", "throughput": 5495.26, "total_tokens": 30315056} {"current_steps": 49785, "total_steps": 64460, "loss": 0.2444, "lr": 1.4976462617417854e-06, "epoch": 15.446788706174372, "percentage": 77.23, "elapsed_time": "1:31:57", "remaining_time": "0:27:06", "throughput": 5495.26, "total_tokens": 30317776} {"current_steps": 49790, "total_steps": 64460, "loss": 0.1991, "lr": 1.4966802029467249e-06, "epoch": 15.448340055848588, "percentage": 77.24, "elapsed_time": "1:31:57", "remaining_time": "0:27:05", "throughput": 5495.28, "total_tokens": 30320528} {"current_steps": 49795, "total_steps": 64460, "loss": 0.1374, "lr": 1.4957144009864915e-06, "epoch": 15.449891405522806, "percentage": 77.25, "elapsed_time": "1:31:58", "remaining_time": "0:27:05", "throughput": 5495.36, "total_tokens": 30324528} {"current_steps": 49800, "total_steps": 64460, "loss": 0.1368, "lr": 1.4947488559318908e-06, "epoch": 15.451442755197021, "percentage": 77.26, "elapsed_time": "1:31:58", "remaining_time": "0:27:04", "throughput": 5495.41, "total_tokens": 30327760} {"current_steps": 49805, "total_steps": 64460, "loss": 0.1664, "lr": 1.4937835678537054e-06, "epoch": 15.452994104871237, "percentage": 77.26, "elapsed_time": "1:31:59", "remaining_time": "0:27:04", "throughput": 5495.43, "total_tokens": 30330512} {"current_steps": 49810, "total_steps": 64460, "loss": 0.0893, "lr": 1.4928185368227066e-06, "epoch": 15.454545454545455, "percentage": 77.27, "elapsed_time": "1:31:59", "remaining_time": "0:27:03", "throughput": 5495.53, "total_tokens": 30334800} {"current_steps": 49815, "total_steps": 64460, "loss": 0.2174, "lr": 1.491853762909638e-06, "epoch": 15.456096804219671, "percentage": 77.28, "elapsed_time": "1:32:00", "remaining_time": "0:27:02", "throughput": 5495.51, "total_tokens": 30337424} {"current_steps": 49820, "total_steps": 64460, "loss": 0.2235, "lr": 1.4908892461852331e-06, "epoch": 15.457648153893889, "percentage": 77.29, "elapsed_time": "1:32:00", "remaining_time": "0:27:02", "throughput": 5495.46, "total_tokens": 30339760} {"current_steps": 49825, "total_steps": 64460, "loss": 0.2224, "lr": 1.4899249867201992e-06, "epoch": 15.459199503568104, "percentage": 77.3, "elapsed_time": "1:32:01", "remaining_time": "0:27:01", "throughput": 5495.46, "total_tokens": 30342416} {"current_steps": 49830, "total_steps": 64460, "loss": 0.1851, "lr": 1.4889609845852305e-06, "epoch": 15.46075085324232, "percentage": 77.3, "elapsed_time": "1:32:01", "remaining_time": "0:27:01", "throughput": 5495.45, "total_tokens": 30345456} {"current_steps": 49835, "total_steps": 64460, "loss": 0.1769, "lr": 1.4879972398509973e-06, "epoch": 15.462302202916538, "percentage": 77.31, "elapsed_time": "1:32:02", "remaining_time": "0:27:00", "throughput": 5495.5, "total_tokens": 30348464} {"current_steps": 49840, "total_steps": 64460, "loss": 0.1669, "lr": 1.4870337525881561e-06, "epoch": 15.463853552590754, "percentage": 77.32, "elapsed_time": "1:32:02", "remaining_time": "0:27:00", "throughput": 5495.48, "total_tokens": 30351344} {"current_steps": 49845, "total_steps": 64460, "loss": 0.1242, "lr": 1.486070522867339e-06, "epoch": 15.46540490226497, "percentage": 77.33, "elapsed_time": "1:32:03", "remaining_time": "0:26:59", "throughput": 5495.48, "total_tokens": 30354032} {"current_steps": 49850, "total_steps": 64460, "loss": 0.2347, "lr": 1.4851075507591656e-06, "epoch": 15.466956251939187, "percentage": 77.33, "elapsed_time": "1:32:04", "remaining_time": "0:26:58", "throughput": 5495.61, "total_tokens": 30358064} {"current_steps": 49855, "total_steps": 64460, "loss": 0.1665, "lr": 1.4841448363342292e-06, "epoch": 15.468507601613403, "percentage": 77.34, "elapsed_time": "1:32:04", "remaining_time": "0:26:58", "throughput": 5495.65, "total_tokens": 30361424} {"current_steps": 49860, "total_steps": 64460, "loss": 0.1969, "lr": 1.4831823796631107e-06, "epoch": 15.470058951287621, "percentage": 77.35, "elapsed_time": "1:32:05", "remaining_time": "0:26:57", "throughput": 5495.76, "total_tokens": 30365712} {"current_steps": 49865, "total_steps": 64460, "loss": 0.2134, "lr": 1.4822201808163705e-06, "epoch": 15.471610300961837, "percentage": 77.36, "elapsed_time": "1:32:05", "remaining_time": "0:26:57", "throughput": 5495.73, "total_tokens": 30368208} {"current_steps": 49870, "total_steps": 64460, "loss": 0.2205, "lr": 1.4812582398645463e-06, "epoch": 15.473161650636053, "percentage": 77.37, "elapsed_time": "1:32:06", "remaining_time": "0:26:56", "throughput": 5495.72, "total_tokens": 30370864} {"current_steps": 49875, "total_steps": 64460, "loss": 0.1963, "lr": 1.4802965568781625e-06, "epoch": 15.47471300031027, "percentage": 77.37, "elapsed_time": "1:32:06", "remaining_time": "0:26:56", "throughput": 5495.69, "total_tokens": 30373904} {"current_steps": 49880, "total_steps": 64460, "loss": 0.3049, "lr": 1.4793351319277194e-06, "epoch": 15.476264349984486, "percentage": 77.38, "elapsed_time": "1:32:07", "remaining_time": "0:26:55", "throughput": 5495.72, "total_tokens": 30377392} {"current_steps": 49885, "total_steps": 64460, "loss": 0.1776, "lr": 1.4783739650837036e-06, "epoch": 15.477815699658702, "percentage": 77.39, "elapsed_time": "1:32:07", "remaining_time": "0:26:55", "throughput": 5495.71, "total_tokens": 30379984} {"current_steps": 49890, "total_steps": 64460, "loss": 0.2959, "lr": 1.4774130564165767e-06, "epoch": 15.47936704933292, "percentage": 77.4, "elapsed_time": "1:32:08", "remaining_time": "0:26:54", "throughput": 5495.68, "total_tokens": 30382608} {"current_steps": 49895, "total_steps": 64460, "loss": 0.1185, "lr": 1.4764524059967884e-06, "epoch": 15.480918399007136, "percentage": 77.4, "elapsed_time": "1:32:08", "remaining_time": "0:26:53", "throughput": 5495.67, "total_tokens": 30385456} {"current_steps": 49900, "total_steps": 64460, "loss": 0.2936, "lr": 1.4754920138947614e-06, "epoch": 15.482469748681353, "percentage": 77.41, "elapsed_time": "1:32:09", "remaining_time": "0:26:53", "throughput": 5495.69, "total_tokens": 30388464} {"current_steps": 49905, "total_steps": 64460, "loss": 0.1706, "lr": 1.4745318801809083e-06, "epoch": 15.48402109835557, "percentage": 77.42, "elapsed_time": "1:32:10", "remaining_time": "0:26:52", "throughput": 5495.77, "total_tokens": 30391696} {"current_steps": 49910, "total_steps": 64460, "loss": 0.2018, "lr": 1.4735720049256148e-06, "epoch": 15.485572448029785, "percentage": 77.43, "elapsed_time": "1:32:10", "remaining_time": "0:26:52", "throughput": 5495.79, "total_tokens": 30394416} {"current_steps": 49915, "total_steps": 64460, "loss": 0.1932, "lr": 1.4726123881992521e-06, "epoch": 15.487123797704003, "percentage": 77.44, "elapsed_time": "1:32:10", "remaining_time": "0:26:51", "throughput": 5495.71, "total_tokens": 30396528} {"current_steps": 49920, "total_steps": 64460, "loss": 0.1829, "lr": 1.4716530300721737e-06, "epoch": 15.488675147378219, "percentage": 77.44, "elapsed_time": "1:32:11", "remaining_time": "0:26:51", "throughput": 5495.75, "total_tokens": 30399376} {"current_steps": 49925, "total_steps": 64460, "loss": 0.2085, "lr": 1.4706939306147083e-06, "epoch": 15.490226497052436, "percentage": 77.45, "elapsed_time": "1:32:11", "remaining_time": "0:26:50", "throughput": 5495.71, "total_tokens": 30402000} {"current_steps": 49930, "total_steps": 64460, "loss": 0.1709, "lr": 1.4697350898971729e-06, "epoch": 15.491777846726652, "percentage": 77.46, "elapsed_time": "1:32:12", "remaining_time": "0:26:49", "throughput": 5495.65, "total_tokens": 30404240} {"current_steps": 49935, "total_steps": 64460, "loss": 0.2258, "lr": 1.468776507989858e-06, "epoch": 15.493329196400868, "percentage": 77.47, "elapsed_time": "1:32:13", "remaining_time": "0:26:49", "throughput": 5495.82, "total_tokens": 30410736} {"current_steps": 49940, "total_steps": 64460, "loss": 0.1653, "lr": 1.467818184963043e-06, "epoch": 15.494880546075086, "percentage": 77.47, "elapsed_time": "1:32:13", "remaining_time": "0:26:49", "throughput": 5495.85, "total_tokens": 30414000} {"current_steps": 49945, "total_steps": 64460, "loss": 0.1781, "lr": 1.4668601208869804e-06, "epoch": 15.496431895749302, "percentage": 77.48, "elapsed_time": "1:32:14", "remaining_time": "0:26:48", "throughput": 5495.88, "total_tokens": 30416784} {"current_steps": 49950, "total_steps": 64460, "loss": 0.2062, "lr": 1.4659023158319113e-06, "epoch": 15.49798324542352, "percentage": 77.49, "elapsed_time": "1:32:14", "remaining_time": "0:26:47", "throughput": 5495.91, "total_tokens": 30419664} {"current_steps": 49955, "total_steps": 64460, "loss": 0.1487, "lr": 1.4649447698680513e-06, "epoch": 15.499534595097735, "percentage": 77.5, "elapsed_time": "1:32:15", "remaining_time": "0:26:47", "throughput": 5495.9, "total_tokens": 30422320} {"current_steps": 49960, "total_steps": 64460, "loss": 0.197, "lr": 1.4639874830656003e-06, "epoch": 15.501085944771951, "percentage": 77.51, "elapsed_time": "1:32:15", "remaining_time": "0:26:46", "throughput": 5495.91, "total_tokens": 30425296} {"current_steps": 49965, "total_steps": 64460, "loss": 0.1123, "lr": 1.46303045549474e-06, "epoch": 15.502637294446169, "percentage": 77.51, "elapsed_time": "1:32:16", "remaining_time": "0:26:46", "throughput": 5495.97, "total_tokens": 30428336} {"current_steps": 49970, "total_steps": 64460, "loss": 0.1664, "lr": 1.4620736872256325e-06, "epoch": 15.504188644120385, "percentage": 77.52, "elapsed_time": "1:32:17", "remaining_time": "0:26:45", "throughput": 5496.09, "total_tokens": 30432176} {"current_steps": 49975, "total_steps": 64460, "loss": 0.191, "lr": 1.4611171783284173e-06, "epoch": 15.5057399937946, "percentage": 77.53, "elapsed_time": "1:32:17", "remaining_time": "0:26:45", "throughput": 5496.15, "total_tokens": 30435536} {"current_steps": 49980, "total_steps": 64460, "loss": 0.1808, "lr": 1.4601609288732217e-06, "epoch": 15.507291343468818, "percentage": 77.54, "elapsed_time": "1:32:18", "remaining_time": "0:26:44", "throughput": 5496.18, "total_tokens": 30438512} {"current_steps": 49985, "total_steps": 64460, "loss": 0.1869, "lr": 1.459204938930146e-06, "epoch": 15.508842693143034, "percentage": 77.54, "elapsed_time": "1:32:18", "remaining_time": "0:26:43", "throughput": 5496.2, "total_tokens": 30441264} {"current_steps": 49990, "total_steps": 64460, "loss": 0.1217, "lr": 1.458249208569279e-06, "epoch": 15.510394042817252, "percentage": 77.55, "elapsed_time": "1:32:19", "remaining_time": "0:26:43", "throughput": 5496.17, "total_tokens": 30444048} {"current_steps": 49995, "total_steps": 64460, "loss": 0.1693, "lr": 1.4572937378606844e-06, "epoch": 15.511945392491468, "percentage": 77.56, "elapsed_time": "1:32:19", "remaining_time": "0:26:42", "throughput": 5496.09, "total_tokens": 30446448} {"current_steps": 50000, "total_steps": 64460, "loss": 0.176, "lr": 1.4563385268744124e-06, "epoch": 15.513496742165684, "percentage": 77.57, "elapsed_time": "1:32:20", "remaining_time": "0:26:42", "throughput": 5496.26, "total_tokens": 30450992} {"current_steps": 50005, "total_steps": 64460, "loss": 0.2035, "lr": 1.4553835756804873e-06, "epoch": 15.515048091839901, "percentage": 77.58, "elapsed_time": "1:32:20", "remaining_time": "0:26:41", "throughput": 5496.3, "total_tokens": 30454160} {"current_steps": 50010, "total_steps": 64460, "loss": 0.1592, "lr": 1.4544288843489212e-06, "epoch": 15.516599441514117, "percentage": 77.58, "elapsed_time": "1:32:21", "remaining_time": "0:26:41", "throughput": 5496.29, "total_tokens": 30456912} {"current_steps": 50015, "total_steps": 64460, "loss": 0.1882, "lr": 1.4534744529497058e-06, "epoch": 15.518150791188333, "percentage": 77.59, "elapsed_time": "1:32:21", "remaining_time": "0:26:40", "throughput": 5496.36, "total_tokens": 30460272} {"current_steps": 50020, "total_steps": 64460, "loss": 0.1324, "lr": 1.4525202815528078e-06, "epoch": 15.51970214086255, "percentage": 77.6, "elapsed_time": "1:32:22", "remaining_time": "0:26:40", "throughput": 5496.37, "total_tokens": 30463408} {"current_steps": 50025, "total_steps": 64460, "loss": 0.2035, "lr": 1.4515663702281835e-06, "epoch": 15.521253490536767, "percentage": 77.61, "elapsed_time": "1:32:22", "remaining_time": "0:26:39", "throughput": 5496.32, "total_tokens": 30465872} {"current_steps": 50030, "total_steps": 64460, "loss": 0.2028, "lr": 1.450612719045762e-06, "epoch": 15.522804840210984, "percentage": 77.61, "elapsed_time": "1:32:23", "remaining_time": "0:26:38", "throughput": 5496.38, "total_tokens": 30469200} {"current_steps": 50035, "total_steps": 64460, "loss": 0.1593, "lr": 1.4496593280754612e-06, "epoch": 15.5243561898852, "percentage": 77.62, "elapsed_time": "1:32:24", "remaining_time": "0:26:38", "throughput": 5496.41, "total_tokens": 30472208} {"current_steps": 50040, "total_steps": 64460, "loss": 0.1532, "lr": 1.4487061973871725e-06, "epoch": 15.525907539559416, "percentage": 77.63, "elapsed_time": "1:32:24", "remaining_time": "0:26:37", "throughput": 5496.4, "total_tokens": 30474960} {"current_steps": 50045, "total_steps": 64460, "loss": 0.2322, "lr": 1.4477533270507743e-06, "epoch": 15.527458889233634, "percentage": 77.64, "elapsed_time": "1:32:24", "remaining_time": "0:26:37", "throughput": 5496.33, "total_tokens": 30477136} {"current_steps": 50050, "total_steps": 64460, "loss": 0.1886, "lr": 1.446800717136121e-06, "epoch": 15.52901023890785, "percentage": 77.65, "elapsed_time": "1:32:25", "remaining_time": "0:26:36", "throughput": 5496.43, "total_tokens": 30481008} {"current_steps": 50055, "total_steps": 64460, "loss": 0.2024, "lr": 1.4458483677130525e-06, "epoch": 15.530561588582067, "percentage": 77.65, "elapsed_time": "1:32:26", "remaining_time": "0:26:36", "throughput": 5496.48, "total_tokens": 30484080} {"current_steps": 50060, "total_steps": 64460, "loss": 0.1945, "lr": 1.4448962788513848e-06, "epoch": 15.532112938256283, "percentage": 77.66, "elapsed_time": "1:32:26", "remaining_time": "0:26:35", "throughput": 5496.5, "total_tokens": 30486992} {"current_steps": 50065, "total_steps": 64460, "loss": 0.1378, "lr": 1.4439444506209187e-06, "epoch": 15.533664287930499, "percentage": 77.67, "elapsed_time": "1:32:27", "remaining_time": "0:26:34", "throughput": 5496.49, "total_tokens": 30489584} {"current_steps": 50070, "total_steps": 64460, "loss": 0.2814, "lr": 1.4429928830914358e-06, "epoch": 15.535215637604717, "percentage": 77.68, "elapsed_time": "1:32:27", "remaining_time": "0:26:34", "throughput": 5496.54, "total_tokens": 30492688} {"current_steps": 50075, "total_steps": 64460, "loss": 0.1428, "lr": 1.442041576332694e-06, "epoch": 15.536766987278932, "percentage": 77.68, "elapsed_time": "1:32:28", "remaining_time": "0:26:33", "throughput": 5496.56, "total_tokens": 30495568} {"current_steps": 50080, "total_steps": 64460, "loss": 0.2212, "lr": 1.441090530414439e-06, "epoch": 15.53831833695315, "percentage": 77.69, "elapsed_time": "1:32:28", "remaining_time": "0:26:33", "throughput": 5496.52, "total_tokens": 30498416} {"current_steps": 50085, "total_steps": 64460, "loss": 0.2342, "lr": 1.4401397454063904e-06, "epoch": 15.539869686627366, "percentage": 77.7, "elapsed_time": "1:32:29", "remaining_time": "0:26:32", "throughput": 5496.51, "total_tokens": 30500976} {"current_steps": 50090, "total_steps": 64460, "loss": 0.1551, "lr": 1.439189221378255e-06, "epoch": 15.541421036301582, "percentage": 77.71, "elapsed_time": "1:32:29", "remaining_time": "0:26:32", "throughput": 5496.64, "total_tokens": 30505040} {"current_steps": 50095, "total_steps": 64460, "loss": 0.1375, "lr": 1.4382389583997141e-06, "epoch": 15.5429723859758, "percentage": 77.71, "elapsed_time": "1:32:30", "remaining_time": "0:26:31", "throughput": 5496.72, "total_tokens": 30508976} {"current_steps": 50100, "total_steps": 64460, "loss": 0.2626, "lr": 1.4372889565404368e-06, "epoch": 15.544523735650015, "percentage": 77.72, "elapsed_time": "1:32:30", "remaining_time": "0:26:31", "throughput": 5496.68, "total_tokens": 30511472} {"current_steps": 50105, "total_steps": 64460, "loss": 0.1881, "lr": 1.4363392158700667e-06, "epoch": 15.546075085324231, "percentage": 77.73, "elapsed_time": "1:32:31", "remaining_time": "0:26:30", "throughput": 5496.82, "total_tokens": 30516464} {"current_steps": 50110, "total_steps": 64460, "loss": 0.1365, "lr": 1.435389736458233e-06, "epoch": 15.547626434998449, "percentage": 77.74, "elapsed_time": "1:32:32", "remaining_time": "0:26:29", "throughput": 5496.76, "total_tokens": 30519024} {"current_steps": 50115, "total_steps": 64460, "loss": 0.1964, "lr": 1.4344405183745419e-06, "epoch": 15.549177784672665, "percentage": 77.75, "elapsed_time": "1:32:32", "remaining_time": "0:26:29", "throughput": 5496.77, "total_tokens": 30521968} {"current_steps": 50120, "total_steps": 64460, "loss": 0.207, "lr": 1.4334915616885847e-06, "epoch": 15.550729134346883, "percentage": 77.75, "elapsed_time": "1:32:33", "remaining_time": "0:26:28", "throughput": 5496.74, "total_tokens": 30524368} {"current_steps": 50125, "total_steps": 64460, "loss": 0.2312, "lr": 1.4325428664699287e-06, "epoch": 15.552280484021098, "percentage": 77.76, "elapsed_time": "1:32:33", "remaining_time": "0:26:28", "throughput": 5496.79, "total_tokens": 30527408} {"current_steps": 50130, "total_steps": 64460, "loss": 0.2083, "lr": 1.4315944327881249e-06, "epoch": 15.553831833695314, "percentage": 77.77, "elapsed_time": "1:32:34", "remaining_time": "0:26:27", "throughput": 5496.8, "total_tokens": 30530640} {"current_steps": 50135, "total_steps": 64460, "loss": 0.229, "lr": 1.4306462607127075e-06, "epoch": 15.555383183369532, "percentage": 77.78, "elapsed_time": "1:32:34", "remaining_time": "0:26:27", "throughput": 5496.82, "total_tokens": 30533392} {"current_steps": 50140, "total_steps": 64460, "loss": 0.1773, "lr": 1.4296983503131851e-06, "epoch": 15.556934533043748, "percentage": 77.78, "elapsed_time": "1:32:35", "remaining_time": "0:26:26", "throughput": 5496.76, "total_tokens": 30536112} {"current_steps": 50145, "total_steps": 64460, "loss": 0.2149, "lr": 1.4287507016590534e-06, "epoch": 15.558485882717964, "percentage": 77.79, "elapsed_time": "1:32:35", "remaining_time": "0:26:26", "throughput": 5496.84, "total_tokens": 30539728} {"current_steps": 50150, "total_steps": 64460, "loss": 0.2074, "lr": 1.427803314819784e-06, "epoch": 15.560037232392181, "percentage": 77.8, "elapsed_time": "1:32:36", "remaining_time": "0:26:25", "throughput": 5496.83, "total_tokens": 30542864} {"current_steps": 50155, "total_steps": 64460, "loss": 0.1775, "lr": 1.4268561898648342e-06, "epoch": 15.561588582066397, "percentage": 77.81, "elapsed_time": "1:32:36", "remaining_time": "0:26:24", "throughput": 5496.77, "total_tokens": 30545168} {"current_steps": 50160, "total_steps": 64460, "loss": 0.0977, "lr": 1.4259093268636364e-06, "epoch": 15.563139931740615, "percentage": 77.82, "elapsed_time": "1:32:37", "remaining_time": "0:26:24", "throughput": 5496.63, "total_tokens": 30547152} {"current_steps": 50165, "total_steps": 64460, "loss": 0.1521, "lr": 1.4249627258856103e-06, "epoch": 15.56469128141483, "percentage": 77.82, "elapsed_time": "1:32:38", "remaining_time": "0:26:23", "throughput": 5496.71, "total_tokens": 30550800} {"current_steps": 50170, "total_steps": 64460, "loss": 0.1568, "lr": 1.4240163870001494e-06, "epoch": 15.566242631089047, "percentage": 77.83, "elapsed_time": "1:32:38", "remaining_time": "0:26:23", "throughput": 5496.65, "total_tokens": 30553232} {"current_steps": 50175, "total_steps": 64460, "loss": 0.1828, "lr": 1.4230703102766347e-06, "epoch": 15.567793980763264, "percentage": 77.84, "elapsed_time": "1:32:39", "remaining_time": "0:26:22", "throughput": 5496.6, "total_tokens": 30555664} {"current_steps": 50180, "total_steps": 64460, "loss": 0.2011, "lr": 1.422124495784422e-06, "epoch": 15.56934533043748, "percentage": 77.85, "elapsed_time": "1:32:39", "remaining_time": "0:26:22", "throughput": 5496.7, "total_tokens": 30559216} {"current_steps": 50185, "total_steps": 64460, "loss": 0.2453, "lr": 1.4211789435928525e-06, "epoch": 15.570896680111698, "percentage": 77.85, "elapsed_time": "1:32:40", "remaining_time": "0:26:21", "throughput": 5496.76, "total_tokens": 30562640} {"current_steps": 50190, "total_steps": 64460, "loss": 0.1387, "lr": 1.4202336537712474e-06, "epoch": 15.572448029785914, "percentage": 77.86, "elapsed_time": "1:32:40", "remaining_time": "0:26:20", "throughput": 5496.77, "total_tokens": 30565296} {"current_steps": 50195, "total_steps": 64460, "loss": 0.1828, "lr": 1.4192886263889043e-06, "epoch": 15.57399937946013, "percentage": 77.87, "elapsed_time": "1:32:41", "remaining_time": "0:26:20", "throughput": 5496.71, "total_tokens": 30567664} {"current_steps": 50200, "total_steps": 64460, "loss": 0.1589, "lr": 1.4183438615151091e-06, "epoch": 15.575550729134347, "percentage": 77.88, "elapsed_time": "1:32:41", "remaining_time": "0:26:19", "throughput": 5496.76, "total_tokens": 30570768} {"current_steps": 50205, "total_steps": 64460, "loss": 0.1944, "lr": 1.4173993592191199e-06, "epoch": 15.577102078808563, "percentage": 77.89, "elapsed_time": "1:32:42", "remaining_time": "0:26:19", "throughput": 5496.74, "total_tokens": 30573552} {"current_steps": 50210, "total_steps": 64460, "loss": 0.2262, "lr": 1.4164551195701837e-06, "epoch": 15.578653428482781, "percentage": 77.89, "elapsed_time": "1:32:42", "remaining_time": "0:26:18", "throughput": 5496.88, "total_tokens": 30577904} {"current_steps": 50215, "total_steps": 64460, "loss": 0.1367, "lr": 1.4155111426375213e-06, "epoch": 15.580204778156997, "percentage": 77.9, "elapsed_time": "1:32:43", "remaining_time": "0:26:18", "throughput": 5496.88, "total_tokens": 30580848} {"current_steps": 50220, "total_steps": 64460, "loss": 0.1677, "lr": 1.4145674284903404e-06, "epoch": 15.581756127831213, "percentage": 77.91, "elapsed_time": "1:32:43", "remaining_time": "0:26:17", "throughput": 5496.92, "total_tokens": 30583824} {"current_steps": 50225, "total_steps": 64460, "loss": 0.0874, "lr": 1.4136239771978232e-06, "epoch": 15.58330747750543, "percentage": 77.92, "elapsed_time": "1:32:44", "remaining_time": "0:26:17", "throughput": 5496.98, "total_tokens": 30587056} {"current_steps": 50230, "total_steps": 64460, "loss": 0.1983, "lr": 1.4126807888291394e-06, "epoch": 15.584858827179646, "percentage": 77.92, "elapsed_time": "1:32:44", "remaining_time": "0:26:16", "throughput": 5496.98, "total_tokens": 30590448} {"current_steps": 50235, "total_steps": 64460, "loss": 0.2369, "lr": 1.4117378634534318e-06, "epoch": 15.586410176853862, "percentage": 77.93, "elapsed_time": "1:32:45", "remaining_time": "0:26:15", "throughput": 5496.96, "total_tokens": 30592944} {"current_steps": 50240, "total_steps": 64460, "loss": 0.2224, "lr": 1.4107952011398324e-06, "epoch": 15.58796152652808, "percentage": 77.94, "elapsed_time": "1:32:46", "remaining_time": "0:26:15", "throughput": 5497.06, "total_tokens": 30596816} {"current_steps": 50245, "total_steps": 64460, "loss": 0.1817, "lr": 1.4098528019574454e-06, "epoch": 15.589512876202296, "percentage": 77.95, "elapsed_time": "1:32:46", "remaining_time": "0:26:14", "throughput": 5497.04, "total_tokens": 30599696} {"current_steps": 50250, "total_steps": 64460, "loss": 0.2455, "lr": 1.4089106659753616e-06, "epoch": 15.591064225876513, "percentage": 77.96, "elapsed_time": "1:32:47", "remaining_time": "0:26:14", "throughput": 5497.18, "total_tokens": 30604272} {"current_steps": 50255, "total_steps": 64460, "loss": 0.2709, "lr": 1.407968793262653e-06, "epoch": 15.59261557555073, "percentage": 77.96, "elapsed_time": "1:32:47", "remaining_time": "0:26:13", "throughput": 5497.19, "total_tokens": 30606992} {"current_steps": 50260, "total_steps": 64460, "loss": 0.1546, "lr": 1.407027183888366e-06, "epoch": 15.594166925224945, "percentage": 77.97, "elapsed_time": "1:32:48", "remaining_time": "0:26:13", "throughput": 5497.21, "total_tokens": 30609712} {"current_steps": 50265, "total_steps": 64460, "loss": 0.1712, "lr": 1.4060858379215347e-06, "epoch": 15.595718274899163, "percentage": 77.98, "elapsed_time": "1:32:48", "remaining_time": "0:26:12", "throughput": 5497.3, "total_tokens": 30614032} {"current_steps": 50270, "total_steps": 64460, "loss": 0.3195, "lr": 1.4051447554311687e-06, "epoch": 15.597269624573379, "percentage": 77.99, "elapsed_time": "1:32:49", "remaining_time": "0:26:12", "throughput": 5497.14, "total_tokens": 30616176} {"current_steps": 50275, "total_steps": 64460, "loss": 0.1564, "lr": 1.4042039364862631e-06, "epoch": 15.598820974247595, "percentage": 77.99, "elapsed_time": "1:32:49", "remaining_time": "0:26:11", "throughput": 5497.19, "total_tokens": 30619312} {"current_steps": 50280, "total_steps": 64460, "loss": 0.1344, "lr": 1.4032633811557878e-06, "epoch": 15.600372323921812, "percentage": 78.0, "elapsed_time": "1:32:50", "remaining_time": "0:26:11", "throughput": 5497.15, "total_tokens": 30622128} {"current_steps": 50285, "total_steps": 64460, "loss": 0.2339, "lr": 1.4023230895086997e-06, "epoch": 15.601923673596028, "percentage": 78.01, "elapsed_time": "1:32:51", "remaining_time": "0:26:10", "throughput": 5497.15, "total_tokens": 30625168} {"current_steps": 50290, "total_steps": 64460, "loss": 0.185, "lr": 1.4013830616139313e-06, "epoch": 15.603475023270246, "percentage": 78.02, "elapsed_time": "1:32:51", "remaining_time": "0:26:09", "throughput": 5497.09, "total_tokens": 30627536} {"current_steps": 50295, "total_steps": 64460, "loss": 0.165, "lr": 1.4004432975403992e-06, "epoch": 15.605026372944462, "percentage": 78.03, "elapsed_time": "1:32:52", "remaining_time": "0:26:09", "throughput": 5497.2, "total_tokens": 30631440} {"current_steps": 50300, "total_steps": 64460, "loss": 0.2221, "lr": 1.3995037973569975e-06, "epoch": 15.606577722618677, "percentage": 78.03, "elapsed_time": "1:32:52", "remaining_time": "0:26:08", "throughput": 5497.08, "total_tokens": 30633840} {"current_steps": 50305, "total_steps": 64460, "loss": 0.1535, "lr": 1.3985645611326031e-06, "epoch": 15.608129072292895, "percentage": 78.04, "elapsed_time": "1:32:53", "remaining_time": "0:26:08", "throughput": 5496.95, "total_tokens": 30636208} {"current_steps": 50310, "total_steps": 64460, "loss": 0.1424, "lr": 1.3976255889360763e-06, "epoch": 15.609680421967111, "percentage": 78.05, "elapsed_time": "1:32:53", "remaining_time": "0:26:07", "throughput": 5496.93, "total_tokens": 30639024} {"current_steps": 50315, "total_steps": 64460, "loss": 0.1732, "lr": 1.39668688083625e-06, "epoch": 15.611231771641329, "percentage": 78.06, "elapsed_time": "1:32:54", "remaining_time": "0:26:07", "throughput": 5496.89, "total_tokens": 30642032} {"current_steps": 50320, "total_steps": 64460, "loss": 0.2163, "lr": 1.3957484369019465e-06, "epoch": 15.612783121315545, "percentage": 78.06, "elapsed_time": "1:32:54", "remaining_time": "0:26:06", "throughput": 5496.98, "total_tokens": 30645488} {"current_steps": 50325, "total_steps": 64460, "loss": 0.1072, "lr": 1.3948102572019617e-06, "epoch": 15.61433447098976, "percentage": 78.07, "elapsed_time": "1:32:55", "remaining_time": "0:26:06", "throughput": 5497.12, "total_tokens": 30649328} {"current_steps": 50330, "total_steps": 64460, "loss": 0.1021, "lr": 1.3938723418050786e-06, "epoch": 15.615885820663978, "percentage": 78.08, "elapsed_time": "1:32:56", "remaining_time": "0:26:05", "throughput": 5497.13, "total_tokens": 30652176} {"current_steps": 50335, "total_steps": 64460, "loss": 0.1805, "lr": 1.3929346907800545e-06, "epoch": 15.617437170338194, "percentage": 78.09, "elapsed_time": "1:32:56", "remaining_time": "0:26:04", "throughput": 5497.15, "total_tokens": 30655504} {"current_steps": 50340, "total_steps": 64460, "loss": 0.1233, "lr": 1.391997304195633e-06, "epoch": 15.618988520012412, "percentage": 78.09, "elapsed_time": "1:32:57", "remaining_time": "0:26:04", "throughput": 5497.2, "total_tokens": 30658480} {"current_steps": 50345, "total_steps": 64460, "loss": 0.1124, "lr": 1.3910601821205327e-06, "epoch": 15.620539869686628, "percentage": 78.1, "elapsed_time": "1:32:57", "remaining_time": "0:26:03", "throughput": 5497.25, "total_tokens": 30661648} {"current_steps": 50350, "total_steps": 64460, "loss": 0.1678, "lr": 1.3901233246234585e-06, "epoch": 15.622091219360843, "percentage": 78.11, "elapsed_time": "1:32:58", "remaining_time": "0:26:03", "throughput": 5497.34, "total_tokens": 30665808} {"current_steps": 50355, "total_steps": 64460, "loss": 0.2539, "lr": 1.3891867317730912e-06, "epoch": 15.623642569035061, "percentage": 78.12, "elapsed_time": "1:32:58", "remaining_time": "0:26:02", "throughput": 5497.41, "total_tokens": 30668976} {"current_steps": 50360, "total_steps": 64460, "loss": 0.1466, "lr": 1.3882504036380956e-06, "epoch": 15.625193918709277, "percentage": 78.13, "elapsed_time": "1:32:59", "remaining_time": "0:26:02", "throughput": 5497.48, "total_tokens": 30672240} {"current_steps": 50365, "total_steps": 64460, "loss": 0.1728, "lr": 1.3873143402871136e-06, "epoch": 15.626745268383493, "percentage": 78.13, "elapsed_time": "1:32:59", "remaining_time": "0:26:01", "throughput": 5497.49, "total_tokens": 30675088} {"current_steps": 50370, "total_steps": 64460, "loss": 0.1306, "lr": 1.3863785417887714e-06, "epoch": 15.62829661805771, "percentage": 78.14, "elapsed_time": "1:33:00", "remaining_time": "0:26:00", "throughput": 5497.46, "total_tokens": 30677648} {"current_steps": 50375, "total_steps": 64460, "loss": 0.2821, "lr": 1.3854430082116749e-06, "epoch": 15.629847967731926, "percentage": 78.15, "elapsed_time": "1:33:00", "remaining_time": "0:26:00", "throughput": 5497.48, "total_tokens": 30680400} {"current_steps": 50380, "total_steps": 64460, "loss": 0.159, "lr": 1.3845077396244071e-06, "epoch": 15.631399317406144, "percentage": 78.16, "elapsed_time": "1:33:01", "remaining_time": "0:25:59", "throughput": 5497.43, "total_tokens": 30682896} {"current_steps": 50385, "total_steps": 64460, "loss": 0.1366, "lr": 1.383572736095538e-06, "epoch": 15.63295066708036, "percentage": 78.16, "elapsed_time": "1:33:01", "remaining_time": "0:25:59", "throughput": 5497.52, "total_tokens": 30686608} {"current_steps": 50390, "total_steps": 64460, "loss": 0.2688, "lr": 1.3826379976936099e-06, "epoch": 15.634502016754576, "percentage": 78.17, "elapsed_time": "1:33:02", "remaining_time": "0:25:58", "throughput": 5497.54, "total_tokens": 30689552} {"current_steps": 50395, "total_steps": 64460, "loss": 0.1937, "lr": 1.3817035244871546e-06, "epoch": 15.636053366428794, "percentage": 78.18, "elapsed_time": "1:33:02", "remaining_time": "0:25:58", "throughput": 5497.52, "total_tokens": 30692208} {"current_steps": 50400, "total_steps": 64460, "loss": 0.1929, "lr": 1.3807693165446761e-06, "epoch": 15.63760471610301, "percentage": 78.19, "elapsed_time": "1:33:03", "remaining_time": "0:25:57", "throughput": 5497.65, "total_tokens": 30696560} {"current_steps": 50405, "total_steps": 64460, "loss": 0.1257, "lr": 1.3798353739346665e-06, "epoch": 15.639156065777225, "percentage": 78.2, "elapsed_time": "1:33:04", "remaining_time": "0:25:57", "throughput": 5497.79, "total_tokens": 30700528} {"current_steps": 50410, "total_steps": 64460, "loss": 0.1871, "lr": 1.378901696725592e-06, "epoch": 15.640707415451443, "percentage": 78.2, "elapsed_time": "1:33:04", "remaining_time": "0:25:56", "throughput": 5497.82, "total_tokens": 30703600} {"current_steps": 50415, "total_steps": 64460, "loss": 0.1876, "lr": 1.3779682849859043e-06, "epoch": 15.642258765125659, "percentage": 78.21, "elapsed_time": "1:33:05", "remaining_time": "0:25:55", "throughput": 5497.77, "total_tokens": 30706000} {"current_steps": 50420, "total_steps": 64460, "loss": 0.1636, "lr": 1.3770351387840314e-06, "epoch": 15.643810114799876, "percentage": 78.22, "elapsed_time": "1:33:05", "remaining_time": "0:25:55", "throughput": 5497.79, "total_tokens": 30708816} {"current_steps": 50425, "total_steps": 64460, "loss": 0.1803, "lr": 1.3761022581883848e-06, "epoch": 15.645361464474092, "percentage": 78.23, "elapsed_time": "1:33:06", "remaining_time": "0:25:54", "throughput": 5497.78, "total_tokens": 30711696} {"current_steps": 50430, "total_steps": 64460, "loss": 0.2628, "lr": 1.3751696432673578e-06, "epoch": 15.646912814148308, "percentage": 78.23, "elapsed_time": "1:33:06", "remaining_time": "0:25:54", "throughput": 5497.88, "total_tokens": 30715664} {"current_steps": 50435, "total_steps": 64460, "loss": 0.1098, "lr": 1.3742372940893189e-06, "epoch": 15.648464163822526, "percentage": 78.24, "elapsed_time": "1:33:07", "remaining_time": "0:25:53", "throughput": 5497.97, "total_tokens": 30719184} {"current_steps": 50440, "total_steps": 64460, "loss": 0.2062, "lr": 1.3733052107226236e-06, "epoch": 15.650015513496742, "percentage": 78.25, "elapsed_time": "1:33:07", "remaining_time": "0:25:53", "throughput": 5497.87, "total_tokens": 30721456} {"current_steps": 50445, "total_steps": 64460, "loss": 0.1239, "lr": 1.3723733932356009e-06, "epoch": 15.65156686317096, "percentage": 78.26, "elapsed_time": "1:33:08", "remaining_time": "0:25:52", "throughput": 5497.91, "total_tokens": 30724976} {"current_steps": 50450, "total_steps": 64460, "loss": 0.2767, "lr": 1.3714418416965675e-06, "epoch": 15.653118212845175, "percentage": 78.27, "elapsed_time": "1:33:08", "remaining_time": "0:25:52", "throughput": 5497.95, "total_tokens": 30727856} {"current_steps": 50455, "total_steps": 64460, "loss": 0.1649, "lr": 1.3705105561738141e-06, "epoch": 15.654669562519391, "percentage": 78.27, "elapsed_time": "1:33:09", "remaining_time": "0:25:51", "throughput": 5497.89, "total_tokens": 30730128} {"current_steps": 50460, "total_steps": 64460, "loss": 0.1779, "lr": 1.3695795367356185e-06, "epoch": 15.656220912193609, "percentage": 78.28, "elapsed_time": "1:33:09", "remaining_time": "0:25:50", "throughput": 5497.81, "total_tokens": 30732240} {"current_steps": 50465, "total_steps": 64460, "loss": 0.2252, "lr": 1.3686487834502316e-06, "epoch": 15.657772261867825, "percentage": 78.29, "elapsed_time": "1:33:10", "remaining_time": "0:25:50", "throughput": 5497.87, "total_tokens": 30735664} {"current_steps": 50470, "total_steps": 64460, "loss": 0.2471, "lr": 1.367718296385892e-06, "epoch": 15.659323611542042, "percentage": 78.3, "elapsed_time": "1:33:10", "remaining_time": "0:25:49", "throughput": 5497.92, "total_tokens": 30738736} {"current_steps": 50475, "total_steps": 64460, "loss": 0.2281, "lr": 1.3667880756108126e-06, "epoch": 15.660874961216258, "percentage": 78.3, "elapsed_time": "1:33:11", "remaining_time": "0:25:49", "throughput": 5497.94, "total_tokens": 30741520} {"current_steps": 50480, "total_steps": 64460, "loss": 0.1919, "lr": 1.365858121193192e-06, "epoch": 15.662426310890474, "percentage": 78.31, "elapsed_time": "1:33:12", "remaining_time": "0:25:48", "throughput": 5498.1, "total_tokens": 30746000} {"current_steps": 50485, "total_steps": 64460, "loss": 0.2181, "lr": 1.3649284332012048e-06, "epoch": 15.663977660564692, "percentage": 78.32, "elapsed_time": "1:33:12", "remaining_time": "0:25:48", "throughput": 5498.1, "total_tokens": 30748784} {"current_steps": 50490, "total_steps": 64460, "loss": 0.193, "lr": 1.3639990117030089e-06, "epoch": 15.665529010238908, "percentage": 78.33, "elapsed_time": "1:33:13", "remaining_time": "0:25:47", "throughput": 5498.19, "total_tokens": 30752368} {"current_steps": 50495, "total_steps": 64460, "loss": 0.2073, "lr": 1.3630698567667434e-06, "epoch": 15.667080359913124, "percentage": 78.34, "elapsed_time": "1:33:13", "remaining_time": "0:25:47", "throughput": 5498.26, "total_tokens": 30755632} {"current_steps": 50500, "total_steps": 64460, "loss": 0.1361, "lr": 1.3621409684605242e-06, "epoch": 15.668631709587341, "percentage": 78.34, "elapsed_time": "1:33:14", "remaining_time": "0:25:46", "throughput": 5498.28, "total_tokens": 30758512} {"current_steps": 50505, "total_steps": 64460, "loss": 0.2272, "lr": 1.361212346852452e-06, "epoch": 15.670183059261557, "percentage": 78.35, "elapsed_time": "1:33:14", "remaining_time": "0:25:45", "throughput": 5498.31, "total_tokens": 30761328} {"current_steps": 50510, "total_steps": 64460, "loss": 0.1354, "lr": 1.3602839920106026e-06, "epoch": 15.671734408935775, "percentage": 78.36, "elapsed_time": "1:33:15", "remaining_time": "0:25:45", "throughput": 5498.24, "total_tokens": 30763632} {"current_steps": 50515, "total_steps": 64460, "loss": 0.1669, "lr": 1.3593559040030391e-06, "epoch": 15.67328575860999, "percentage": 78.37, "elapsed_time": "1:33:15", "remaining_time": "0:25:44", "throughput": 5498.34, "total_tokens": 30767952} {"current_steps": 50520, "total_steps": 64460, "loss": 0.1896, "lr": 1.3584280828977975e-06, "epoch": 15.674837108284207, "percentage": 78.37, "elapsed_time": "1:33:16", "remaining_time": "0:25:44", "throughput": 5498.32, "total_tokens": 30770448} {"current_steps": 50525, "total_steps": 64460, "loss": 0.1556, "lr": 1.3575005287629022e-06, "epoch": 15.676388457958424, "percentage": 78.38, "elapsed_time": "1:33:16", "remaining_time": "0:25:43", "throughput": 5498.2, "total_tokens": 30772464} {"current_steps": 50530, "total_steps": 64460, "loss": 0.168, "lr": 1.3565732416663501e-06, "epoch": 15.67793980763264, "percentage": 78.39, "elapsed_time": "1:33:17", "remaining_time": "0:25:43", "throughput": 5498.17, "total_tokens": 30774864} {"current_steps": 50535, "total_steps": 64460, "loss": 0.1659, "lr": 1.3556462216761257e-06, "epoch": 15.679491157306856, "percentage": 78.4, "elapsed_time": "1:33:17", "remaining_time": "0:25:42", "throughput": 5498.17, "total_tokens": 30777456} {"current_steps": 50540, "total_steps": 64460, "loss": 0.1539, "lr": 1.3547194688601855e-06, "epoch": 15.681042506981074, "percentage": 78.41, "elapsed_time": "1:33:18", "remaining_time": "0:25:41", "throughput": 5498.25, "total_tokens": 30781264} {"current_steps": 50545, "total_steps": 64460, "loss": 0.2089, "lr": 1.3537929832864777e-06, "epoch": 15.68259385665529, "percentage": 78.41, "elapsed_time": "1:33:18", "remaining_time": "0:25:41", "throughput": 5498.32, "total_tokens": 30784656} {"current_steps": 50550, "total_steps": 64460, "loss": 0.1981, "lr": 1.3528667650229205e-06, "epoch": 15.684145206329507, "percentage": 78.42, "elapsed_time": "1:33:19", "remaining_time": "0:25:40", "throughput": 5498.26, "total_tokens": 30786992} {"current_steps": 50555, "total_steps": 64460, "loss": 0.2146, "lr": 1.3519408141374196e-06, "epoch": 15.685696556003723, "percentage": 78.43, "elapsed_time": "1:33:19", "remaining_time": "0:25:40", "throughput": 5498.29, "total_tokens": 30790064} {"current_steps": 50560, "total_steps": 64460, "loss": 0.1679, "lr": 1.3510151306978547e-06, "epoch": 15.687247905677939, "percentage": 78.44, "elapsed_time": "1:33:20", "remaining_time": "0:25:39", "throughput": 5498.33, "total_tokens": 30793360} {"current_steps": 50565, "total_steps": 64460, "loss": 0.2024, "lr": 1.3500897147720931e-06, "epoch": 15.688799255352157, "percentage": 78.44, "elapsed_time": "1:33:21", "remaining_time": "0:25:39", "throughput": 5498.41, "total_tokens": 30796944} {"current_steps": 50570, "total_steps": 64460, "loss": 0.2196, "lr": 1.3491645664279752e-06, "epoch": 15.690350605026373, "percentage": 78.45, "elapsed_time": "1:33:21", "remaining_time": "0:25:38", "throughput": 5498.54, "total_tokens": 30801008} {"current_steps": 50575, "total_steps": 64460, "loss": 0.1372, "lr": 1.348239685733327e-06, "epoch": 15.69190195470059, "percentage": 78.46, "elapsed_time": "1:33:22", "remaining_time": "0:25:38", "throughput": 5498.59, "total_tokens": 30804048} {"current_steps": 50580, "total_steps": 64460, "loss": 0.2081, "lr": 1.3473150727559543e-06, "epoch": 15.693453304374806, "percentage": 78.47, "elapsed_time": "1:33:22", "remaining_time": "0:25:37", "throughput": 5498.59, "total_tokens": 30806768} {"current_steps": 50585, "total_steps": 64460, "loss": 0.1586, "lr": 1.3463907275636395e-06, "epoch": 15.695004654049022, "percentage": 78.48, "elapsed_time": "1:33:23", "remaining_time": "0:25:36", "throughput": 5498.64, "total_tokens": 30809776} {"current_steps": 50590, "total_steps": 64460, "loss": 0.2477, "lr": 1.3454666502241514e-06, "epoch": 15.69655600372324, "percentage": 78.48, "elapsed_time": "1:33:23", "remaining_time": "0:25:36", "throughput": 5498.7, "total_tokens": 30813424} {"current_steps": 50595, "total_steps": 64460, "loss": 0.1862, "lr": 1.3445428408052325e-06, "epoch": 15.698107353397456, "percentage": 78.49, "elapsed_time": "1:33:24", "remaining_time": "0:25:35", "throughput": 5498.69, "total_tokens": 30815920} {"current_steps": 50600, "total_steps": 64460, "loss": 0.1778, "lr": 1.3436192993746117e-06, "epoch": 15.699658703071673, "percentage": 78.5, "elapsed_time": "1:33:24", "remaining_time": "0:25:35", "throughput": 5498.79, "total_tokens": 30820016} {"current_steps": 50605, "total_steps": 64460, "loss": 0.2441, "lr": 1.3426960259999927e-06, "epoch": 15.701210052745889, "percentage": 78.51, "elapsed_time": "1:33:25", "remaining_time": "0:25:34", "throughput": 5498.86, "total_tokens": 30824496} {"current_steps": 50610, "total_steps": 64460, "loss": 0.2179, "lr": 1.341773020749066e-06, "epoch": 15.702761402420105, "percentage": 78.51, "elapsed_time": "1:33:26", "remaining_time": "0:25:34", "throughput": 5498.84, "total_tokens": 30827024} {"current_steps": 50615, "total_steps": 64460, "loss": 0.1694, "lr": 1.3408502836894943e-06, "epoch": 15.704312752094323, "percentage": 78.52, "elapsed_time": "1:33:26", "remaining_time": "0:25:33", "throughput": 5498.89, "total_tokens": 30830416} {"current_steps": 50620, "total_steps": 64460, "loss": 0.1914, "lr": 1.33992781488893e-06, "epoch": 15.705864101768539, "percentage": 78.53, "elapsed_time": "1:33:27", "remaining_time": "0:25:33", "throughput": 5498.93, "total_tokens": 30833648} {"current_steps": 50625, "total_steps": 64460, "loss": 0.2425, "lr": 1.3390056144149966e-06, "epoch": 15.707415451442754, "percentage": 78.54, "elapsed_time": "1:33:27", "remaining_time": "0:25:32", "throughput": 5499.0, "total_tokens": 30836880} {"current_steps": 50630, "total_steps": 64460, "loss": 0.1762, "lr": 1.338083682335305e-06, "epoch": 15.708966801116972, "percentage": 78.54, "elapsed_time": "1:33:28", "remaining_time": "0:25:31", "throughput": 5499.05, "total_tokens": 30840112} {"current_steps": 50635, "total_steps": 64460, "loss": 0.1692, "lr": 1.3371620187174438e-06, "epoch": 15.710518150791188, "percentage": 78.55, "elapsed_time": "1:33:28", "remaining_time": "0:25:31", "throughput": 5499.15, "total_tokens": 30843600} {"current_steps": 50640, "total_steps": 64460, "loss": 0.1805, "lr": 1.3362406236289799e-06, "epoch": 15.712069500465406, "percentage": 78.56, "elapsed_time": "1:33:29", "remaining_time": "0:25:30", "throughput": 5499.23, "total_tokens": 30847024} {"current_steps": 50645, "total_steps": 64460, "loss": 0.2717, "lr": 1.3353194971374657e-06, "epoch": 15.713620850139622, "percentage": 78.57, "elapsed_time": "1:33:29", "remaining_time": "0:25:30", "throughput": 5499.24, "total_tokens": 30849872} {"current_steps": 50650, "total_steps": 64460, "loss": 0.1762, "lr": 1.3343986393104263e-06, "epoch": 15.715172199813837, "percentage": 78.58, "elapsed_time": "1:33:30", "remaining_time": "0:25:29", "throughput": 5499.36, "total_tokens": 30853808} {"current_steps": 50655, "total_steps": 64460, "loss": 0.2118, "lr": 1.333478050215376e-06, "epoch": 15.716723549488055, "percentage": 78.58, "elapsed_time": "1:33:30", "remaining_time": "0:25:29", "throughput": 5499.4, "total_tokens": 30856752} {"current_steps": 50660, "total_steps": 64460, "loss": 0.1511, "lr": 1.3325577299198005e-06, "epoch": 15.718274899162271, "percentage": 78.59, "elapsed_time": "1:33:31", "remaining_time": "0:25:28", "throughput": 5499.42, "total_tokens": 30859632} {"current_steps": 50665, "total_steps": 64460, "loss": 0.2114, "lr": 1.3316376784911745e-06, "epoch": 15.719826248836487, "percentage": 78.6, "elapsed_time": "1:33:31", "remaining_time": "0:25:28", "throughput": 5499.47, "total_tokens": 30862896} {"current_steps": 50670, "total_steps": 64460, "loss": 0.1651, "lr": 1.3307178959969453e-06, "epoch": 15.721377598510704, "percentage": 78.61, "elapsed_time": "1:33:32", "remaining_time": "0:25:27", "throughput": 5499.4, "total_tokens": 30865136} {"current_steps": 50675, "total_steps": 64460, "loss": 0.2231, "lr": 1.3297983825045462e-06, "epoch": 15.72292894818492, "percentage": 78.61, "elapsed_time": "1:33:33", "remaining_time": "0:25:26", "throughput": 5499.42, "total_tokens": 30868560} {"current_steps": 50680, "total_steps": 64460, "loss": 0.1252, "lr": 1.328879138081386e-06, "epoch": 15.724480297859138, "percentage": 78.62, "elapsed_time": "1:33:33", "remaining_time": "0:25:26", "throughput": 5499.48, "total_tokens": 30871664} {"current_steps": 50685, "total_steps": 64460, "loss": 0.2016, "lr": 1.327960162794859e-06, "epoch": 15.726031647533354, "percentage": 78.63, "elapsed_time": "1:33:34", "remaining_time": "0:25:25", "throughput": 5499.5, "total_tokens": 30874448} {"current_steps": 50690, "total_steps": 64460, "loss": 0.207, "lr": 1.3270414567123342e-06, "epoch": 15.72758299720757, "percentage": 78.64, "elapsed_time": "1:33:34", "remaining_time": "0:25:25", "throughput": 5499.49, "total_tokens": 30877136} {"current_steps": 50695, "total_steps": 64460, "loss": 0.1857, "lr": 1.3261230199011643e-06, "epoch": 15.729134346881787, "percentage": 78.65, "elapsed_time": "1:33:35", "remaining_time": "0:25:24", "throughput": 5499.51, "total_tokens": 30880272} {"current_steps": 50700, "total_steps": 64460, "loss": 0.1233, "lr": 1.3252048524286843e-06, "epoch": 15.730685696556003, "percentage": 78.65, "elapsed_time": "1:33:35", "remaining_time": "0:25:24", "throughput": 5499.53, "total_tokens": 30883344} {"current_steps": 50705, "total_steps": 64460, "loss": 0.288, "lr": 1.3242869543622034e-06, "epoch": 15.732237046230221, "percentage": 78.66, "elapsed_time": "1:33:36", "remaining_time": "0:25:23", "throughput": 5499.54, "total_tokens": 30886000} {"current_steps": 50710, "total_steps": 64460, "loss": 0.2062, "lr": 1.3233693257690167e-06, "epoch": 15.733788395904437, "percentage": 78.67, "elapsed_time": "1:33:36", "remaining_time": "0:25:22", "throughput": 5499.59, "total_tokens": 30889072} {"current_steps": 50715, "total_steps": 64460, "loss": 0.1545, "lr": 1.322451966716395e-06, "epoch": 15.735339745578653, "percentage": 78.68, "elapsed_time": "1:33:37", "remaining_time": "0:25:22", "throughput": 5499.78, "total_tokens": 30893648} {"current_steps": 50720, "total_steps": 64460, "loss": 0.1998, "lr": 1.321534877271594e-06, "epoch": 15.73689109525287, "percentage": 78.68, "elapsed_time": "1:33:37", "remaining_time": "0:25:21", "throughput": 5499.87, "total_tokens": 30897648} {"current_steps": 50725, "total_steps": 64460, "loss": 0.1759, "lr": 1.320618057501845e-06, "epoch": 15.738442444927086, "percentage": 78.69, "elapsed_time": "1:33:38", "remaining_time": "0:25:21", "throughput": 5499.92, "total_tokens": 30900752} {"current_steps": 50730, "total_steps": 64460, "loss": 0.1835, "lr": 1.3197015074743642e-06, "epoch": 15.739993794601304, "percentage": 78.7, "elapsed_time": "1:33:38", "remaining_time": "0:25:20", "throughput": 5499.88, "total_tokens": 30903408} {"current_steps": 50735, "total_steps": 64460, "loss": 0.1711, "lr": 1.3187852272563427e-06, "epoch": 15.74154514427552, "percentage": 78.71, "elapsed_time": "1:33:39", "remaining_time": "0:25:20", "throughput": 5499.9, "total_tokens": 30906416} {"current_steps": 50740, "total_steps": 64460, "loss": 0.1105, "lr": 1.3178692169149576e-06, "epoch": 15.743096493949736, "percentage": 78.72, "elapsed_time": "1:33:39", "remaining_time": "0:25:19", "throughput": 5499.91, "total_tokens": 30909200} {"current_steps": 50745, "total_steps": 64460, "loss": 0.164, "lr": 1.3169534765173604e-06, "epoch": 15.744647843623953, "percentage": 78.72, "elapsed_time": "1:33:40", "remaining_time": "0:25:19", "throughput": 5499.98, "total_tokens": 30912688} {"current_steps": 50750, "total_steps": 64460, "loss": 0.2118, "lr": 1.316038006130687e-06, "epoch": 15.74619919329817, "percentage": 78.73, "elapsed_time": "1:33:40", "remaining_time": "0:25:18", "throughput": 5500.0, "total_tokens": 30915504} {"current_steps": 50755, "total_steps": 64460, "loss": 0.2091, "lr": 1.3151228058220539e-06, "epoch": 15.747750542972385, "percentage": 78.74, "elapsed_time": "1:33:41", "remaining_time": "0:25:17", "throughput": 5499.96, "total_tokens": 30917872} {"current_steps": 50760, "total_steps": 64460, "loss": 0.1671, "lr": 1.314207875658553e-06, "epoch": 15.749301892646603, "percentage": 78.75, "elapsed_time": "1:33:41", "remaining_time": "0:25:17", "throughput": 5499.96, "total_tokens": 30920624} {"current_steps": 50765, "total_steps": 64460, "loss": 0.1817, "lr": 1.3132932157072626e-06, "epoch": 15.750853242320819, "percentage": 78.75, "elapsed_time": "1:33:42", "remaining_time": "0:25:16", "throughput": 5499.91, "total_tokens": 30922896} {"current_steps": 50770, "total_steps": 64460, "loss": 0.1563, "lr": 1.3123788260352355e-06, "epoch": 15.752404591995036, "percentage": 78.76, "elapsed_time": "1:33:43", "remaining_time": "0:25:16", "throughput": 5500.03, "total_tokens": 30926832} {"current_steps": 50775, "total_steps": 64460, "loss": 0.2303, "lr": 1.3114647067095099e-06, "epoch": 15.753955941669252, "percentage": 78.77, "elapsed_time": "1:33:43", "remaining_time": "0:25:15", "throughput": 5500.06, "total_tokens": 30929744} {"current_steps": 50780, "total_steps": 64460, "loss": 0.1782, "lr": 1.3105508577970982e-06, "epoch": 15.755507291343468, "percentage": 78.78, "elapsed_time": "1:33:44", "remaining_time": "0:25:15", "throughput": 5500.03, "total_tokens": 30932304} {"current_steps": 50785, "total_steps": 64460, "loss": 0.2386, "lr": 1.3096372793649998e-06, "epoch": 15.757058641017686, "percentage": 78.79, "elapsed_time": "1:33:44", "remaining_time": "0:25:14", "throughput": 5500.03, "total_tokens": 30934992} {"current_steps": 50790, "total_steps": 64460, "loss": 0.2551, "lr": 1.308723971480188e-06, "epoch": 15.758609990691902, "percentage": 78.79, "elapsed_time": "1:33:45", "remaining_time": "0:25:13", "throughput": 5500.08, "total_tokens": 30938064} {"current_steps": 50795, "total_steps": 64460, "loss": 0.2172, "lr": 1.3078109342096219e-06, "epoch": 15.760161340366118, "percentage": 78.8, "elapsed_time": "1:33:45", "remaining_time": "0:25:13", "throughput": 5500.02, "total_tokens": 30940272} {"current_steps": 50800, "total_steps": 64460, "loss": 0.1572, "lr": 1.3068981676202347e-06, "epoch": 15.761712690040335, "percentage": 78.81, "elapsed_time": "1:33:45", "remaining_time": "0:25:12", "throughput": 5499.97, "total_tokens": 30942704} {"current_steps": 50805, "total_steps": 64460, "loss": 0.261, "lr": 1.305985671778946e-06, "epoch": 15.763264039714551, "percentage": 78.82, "elapsed_time": "1:33:46", "remaining_time": "0:25:12", "throughput": 5500.02, "total_tokens": 30945776} {"current_steps": 50810, "total_steps": 64460, "loss": 0.2081, "lr": 1.30507344675265e-06, "epoch": 15.764815389388769, "percentage": 78.82, "elapsed_time": "1:33:47", "remaining_time": "0:25:11", "throughput": 5500.14, "total_tokens": 30949584} {"current_steps": 50815, "total_steps": 64460, "loss": 0.1941, "lr": 1.3041614926082247e-06, "epoch": 15.766366739062985, "percentage": 78.83, "elapsed_time": "1:33:47", "remaining_time": "0:25:11", "throughput": 5500.13, "total_tokens": 30952272} {"current_steps": 50820, "total_steps": 64460, "loss": 0.1719, "lr": 1.303249809412529e-06, "epoch": 15.7679180887372, "percentage": 78.84, "elapsed_time": "1:33:48", "remaining_time": "0:25:10", "throughput": 5500.11, "total_tokens": 30954704} {"current_steps": 50825, "total_steps": 64460, "loss": 0.1343, "lr": 1.3023383972323967e-06, "epoch": 15.769469438411418, "percentage": 78.85, "elapsed_time": "1:33:48", "remaining_time": "0:25:09", "throughput": 5500.15, "total_tokens": 30957488} {"current_steps": 50830, "total_steps": 64460, "loss": 0.2147, "lr": 1.301427256134648e-06, "epoch": 15.771020788085634, "percentage": 78.86, "elapsed_time": "1:33:49", "remaining_time": "0:25:09", "throughput": 5500.21, "total_tokens": 30960848} {"current_steps": 50835, "total_steps": 64460, "loss": 0.1696, "lr": 1.3005163861860781e-06, "epoch": 15.772572137759852, "percentage": 78.86, "elapsed_time": "1:33:49", "remaining_time": "0:25:08", "throughput": 5500.25, "total_tokens": 30964176} {"current_steps": 50840, "total_steps": 64460, "loss": 0.2592, "lr": 1.2996057874534662e-06, "epoch": 15.774123487434068, "percentage": 78.87, "elapsed_time": "1:33:50", "remaining_time": "0:25:08", "throughput": 5500.22, "total_tokens": 30966896} {"current_steps": 50845, "total_steps": 64460, "loss": 0.1301, "lr": 1.2986954600035683e-06, "epoch": 15.775674837108284, "percentage": 78.88, "elapsed_time": "1:33:50", "remaining_time": "0:25:07", "throughput": 5500.18, "total_tokens": 30969136} {"current_steps": 50850, "total_steps": 64460, "loss": 0.2179, "lr": 1.2977854039031251e-06, "epoch": 15.777226186782501, "percentage": 78.89, "elapsed_time": "1:33:51", "remaining_time": "0:25:07", "throughput": 5500.25, "total_tokens": 30972656} {"current_steps": 50855, "total_steps": 64460, "loss": 0.1881, "lr": 1.2968756192188509e-06, "epoch": 15.778777536456717, "percentage": 78.89, "elapsed_time": "1:33:51", "remaining_time": "0:25:06", "throughput": 5500.3, "total_tokens": 30975760} {"current_steps": 50860, "total_steps": 64460, "loss": 0.1593, "lr": 1.2959661060174462e-06, "epoch": 15.780328886130935, "percentage": 78.9, "elapsed_time": "1:33:52", "remaining_time": "0:25:06", "throughput": 5500.44, "total_tokens": 30980464} {"current_steps": 50865, "total_steps": 64460, "loss": 0.2581, "lr": 1.2950568643655876e-06, "epoch": 15.78188023580515, "percentage": 78.91, "elapsed_time": "1:33:53", "remaining_time": "0:25:05", "throughput": 5500.53, "total_tokens": 30984528} {"current_steps": 50870, "total_steps": 64460, "loss": 0.1972, "lr": 1.2941478943299334e-06, "epoch": 15.783431585479367, "percentage": 78.92, "elapsed_time": "1:33:53", "remaining_time": "0:25:04", "throughput": 5500.49, "total_tokens": 30986928} {"current_steps": 50875, "total_steps": 64460, "loss": 0.2105, "lr": 1.293239195977124e-06, "epoch": 15.784982935153584, "percentage": 78.92, "elapsed_time": "1:33:53", "remaining_time": "0:25:04", "throughput": 5500.51, "total_tokens": 30989520} {"current_steps": 50880, "total_steps": 64460, "loss": 0.3011, "lr": 1.2923307693737747e-06, "epoch": 15.7865342848278, "percentage": 78.93, "elapsed_time": "1:33:54", "remaining_time": "0:25:03", "throughput": 5500.5, "total_tokens": 30992336} {"current_steps": 50885, "total_steps": 64460, "loss": 0.2027, "lr": 1.2914226145864866e-06, "epoch": 15.788085634502016, "percentage": 78.94, "elapsed_time": "1:33:55", "remaining_time": "0:25:03", "throughput": 5500.59, "total_tokens": 30996016} {"current_steps": 50890, "total_steps": 64460, "loss": 0.2145, "lr": 1.2905147316818363e-06, "epoch": 15.789636984176234, "percentage": 78.95, "elapsed_time": "1:33:55", "remaining_time": "0:25:02", "throughput": 5500.6, "total_tokens": 30998704} {"current_steps": 50895, "total_steps": 64460, "loss": 0.1981, "lr": 1.2896071207263838e-06, "epoch": 15.79118833385045, "percentage": 78.96, "elapsed_time": "1:33:55", "remaining_time": "0:25:02", "throughput": 5500.54, "total_tokens": 31000848} {"current_steps": 50900, "total_steps": 64460, "loss": 0.1881, "lr": 1.2886997817866653e-06, "epoch": 15.792739683524667, "percentage": 78.96, "elapsed_time": "1:33:56", "remaining_time": "0:25:01", "throughput": 5500.66, "total_tokens": 31004752} {"current_steps": 50905, "total_steps": 64460, "loss": 0.1762, "lr": 1.287792714929203e-06, "epoch": 15.794291033198883, "percentage": 78.97, "elapsed_time": "1:33:57", "remaining_time": "0:25:01", "throughput": 5500.69, "total_tokens": 31007568} {"current_steps": 50910, "total_steps": 64460, "loss": 0.1804, "lr": 1.2868859202204925e-06, "epoch": 15.795842382873099, "percentage": 78.98, "elapsed_time": "1:33:57", "remaining_time": "0:25:00", "throughput": 5500.66, "total_tokens": 31010064} {"current_steps": 50915, "total_steps": 64460, "loss": 0.1724, "lr": 1.2859793977270151e-06, "epoch": 15.797393732547317, "percentage": 78.99, "elapsed_time": "1:33:58", "remaining_time": "0:24:59", "throughput": 5500.68, "total_tokens": 31013136} {"current_steps": 50920, "total_steps": 64460, "loss": 0.2458, "lr": 1.2850731475152274e-06, "epoch": 15.798945082221532, "percentage": 78.99, "elapsed_time": "1:33:58", "remaining_time": "0:24:59", "throughput": 5500.71, "total_tokens": 31015952} {"current_steps": 50925, "total_steps": 64460, "loss": 0.2359, "lr": 1.28416716965157e-06, "epoch": 15.800496431895748, "percentage": 79.0, "elapsed_time": "1:33:59", "remaining_time": "0:24:58", "throughput": 5500.68, "total_tokens": 31018384} {"current_steps": 50930, "total_steps": 64460, "loss": 0.2288, "lr": 1.2832614642024604e-06, "epoch": 15.802047781569966, "percentage": 79.01, "elapsed_time": "1:33:59", "remaining_time": "0:24:58", "throughput": 5500.7, "total_tokens": 31021072} {"current_steps": 50935, "total_steps": 64460, "loss": 0.1593, "lr": 1.282356031234298e-06, "epoch": 15.803599131244182, "percentage": 79.02, "elapsed_time": "1:34:00", "remaining_time": "0:24:57", "throughput": 5500.76, "total_tokens": 31024400} {"current_steps": 50940, "total_steps": 64460, "loss": 0.1811, "lr": 1.2814508708134631e-06, "epoch": 15.8051504809184, "percentage": 79.03, "elapsed_time": "1:34:00", "remaining_time": "0:24:57", "throughput": 5500.76, "total_tokens": 31027024} {"current_steps": 50945, "total_steps": 64460, "loss": 0.1508, "lr": 1.2805459830063126e-06, "epoch": 15.806701830592615, "percentage": 79.03, "elapsed_time": "1:34:00", "remaining_time": "0:24:56", "throughput": 5500.81, "total_tokens": 31030064} {"current_steps": 50950, "total_steps": 64460, "loss": 0.209, "lr": 1.279641367879188e-06, "epoch": 15.808253180266831, "percentage": 79.04, "elapsed_time": "1:34:01", "remaining_time": "0:24:55", "throughput": 5500.84, "total_tokens": 31033264} {"current_steps": 50955, "total_steps": 64460, "loss": 0.1451, "lr": 1.2787370254984049e-06, "epoch": 15.809804529941049, "percentage": 79.05, "elapsed_time": "1:34:02", "remaining_time": "0:24:55", "throughput": 5500.79, "total_tokens": 31035568} {"current_steps": 50960, "total_steps": 64460, "loss": 0.1875, "lr": 1.2778329559302654e-06, "epoch": 15.811355879615265, "percentage": 79.06, "elapsed_time": "1:34:02", "remaining_time": "0:24:54", "throughput": 5500.75, "total_tokens": 31038160} {"current_steps": 50965, "total_steps": 64460, "loss": 0.2539, "lr": 1.2769291592410465e-06, "epoch": 15.812907229289483, "percentage": 79.06, "elapsed_time": "1:34:03", "remaining_time": "0:24:54", "throughput": 5500.72, "total_tokens": 31040560} {"current_steps": 50970, "total_steps": 64460, "loss": 0.2228, "lr": 1.2760256354970091e-06, "epoch": 15.814458578963698, "percentage": 79.07, "elapsed_time": "1:34:03", "remaining_time": "0:24:53", "throughput": 5500.78, "total_tokens": 31044048} {"current_steps": 50975, "total_steps": 64460, "loss": 0.2201, "lr": 1.2751223847643896e-06, "epoch": 15.816009928637914, "percentage": 79.08, "elapsed_time": "1:34:04", "remaining_time": "0:24:53", "throughput": 5500.82, "total_tokens": 31046928} {"current_steps": 50980, "total_steps": 64460, "loss": 0.1674, "lr": 1.27421940710941e-06, "epoch": 15.817561278312132, "percentage": 79.09, "elapsed_time": "1:34:04", "remaining_time": "0:24:52", "throughput": 5501.0, "total_tokens": 31051696} {"current_steps": 50985, "total_steps": 64460, "loss": 0.1471, "lr": 1.2733167025982663e-06, "epoch": 15.819112627986348, "percentage": 79.1, "elapsed_time": "1:34:05", "remaining_time": "0:24:51", "throughput": 5501.04, "total_tokens": 31054608} {"current_steps": 50990, "total_steps": 64460, "loss": 0.1858, "lr": 1.2724142712971388e-06, "epoch": 15.820663977660566, "percentage": 79.1, "elapsed_time": "1:34:05", "remaining_time": "0:24:51", "throughput": 5501.12, "total_tokens": 31058320} {"current_steps": 50995, "total_steps": 64460, "loss": 0.1442, "lr": 1.2715121132721881e-06, "epoch": 15.822215327334781, "percentage": 79.11, "elapsed_time": "1:34:06", "remaining_time": "0:24:50", "throughput": 5501.2, "total_tokens": 31062288} {"current_steps": 51000, "total_steps": 64460, "loss": 0.2431, "lr": 1.2706102285895493e-06, "epoch": 15.823766677008997, "percentage": 79.12, "elapsed_time": "1:34:06", "remaining_time": "0:24:50", "throughput": 5501.23, "total_tokens": 31065104} {"current_steps": 51005, "total_steps": 64460, "loss": 0.1843, "lr": 1.269708617315345e-06, "epoch": 15.825318026683215, "percentage": 79.13, "elapsed_time": "1:34:07", "remaining_time": "0:24:49", "throughput": 5501.3, "total_tokens": 31068208} {"current_steps": 51010, "total_steps": 64460, "loss": 0.1991, "lr": 1.2688072795156714e-06, "epoch": 15.82686937635743, "percentage": 79.13, "elapsed_time": "1:34:07", "remaining_time": "0:24:49", "throughput": 5501.3, "total_tokens": 31070864} {"current_steps": 51015, "total_steps": 64460, "loss": 0.135, "lr": 1.267906215256609e-06, "epoch": 15.828420726031647, "percentage": 79.14, "elapsed_time": "1:34:08", "remaining_time": "0:24:48", "throughput": 5501.35, "total_tokens": 31074288} {"current_steps": 51020, "total_steps": 64460, "loss": 0.1585, "lr": 1.2670054246042145e-06, "epoch": 15.829972075705864, "percentage": 79.15, "elapsed_time": "1:34:09", "remaining_time": "0:24:48", "throughput": 5501.58, "total_tokens": 31080528} {"current_steps": 51025, "total_steps": 64460, "loss": 0.2234, "lr": 1.266104907624529e-06, "epoch": 15.83152342538008, "percentage": 79.16, "elapsed_time": "1:34:09", "remaining_time": "0:24:47", "throughput": 5501.56, "total_tokens": 31083056} {"current_steps": 51030, "total_steps": 64460, "loss": 0.1738, "lr": 1.265204664383568e-06, "epoch": 15.833074775054298, "percentage": 79.17, "elapsed_time": "1:34:10", "remaining_time": "0:24:47", "throughput": 5501.56, "total_tokens": 31085776} {"current_steps": 51035, "total_steps": 64460, "loss": 0.1687, "lr": 1.2643046949473337e-06, "epoch": 15.834626124728514, "percentage": 79.17, "elapsed_time": "1:34:10", "remaining_time": "0:24:46", "throughput": 5501.66, "total_tokens": 31089360} {"current_steps": 51040, "total_steps": 64460, "loss": 0.1759, "lr": 1.2634049993818004e-06, "epoch": 15.83617747440273, "percentage": 79.18, "elapsed_time": "1:34:11", "remaining_time": "0:24:45", "throughput": 5501.68, "total_tokens": 31092048} {"current_steps": 51045, "total_steps": 64460, "loss": 0.1654, "lr": 1.2625055777529305e-06, "epoch": 15.837728824076947, "percentage": 79.19, "elapsed_time": "1:34:11", "remaining_time": "0:24:45", "throughput": 5501.65, "total_tokens": 31094544} {"current_steps": 51050, "total_steps": 64460, "loss": 0.1648, "lr": 1.261606430126659e-06, "epoch": 15.839280173751163, "percentage": 79.2, "elapsed_time": "1:34:12", "remaining_time": "0:24:44", "throughput": 5501.67, "total_tokens": 31097200} {"current_steps": 51055, "total_steps": 64460, "loss": 0.1886, "lr": 1.2607075565689047e-06, "epoch": 15.84083152342538, "percentage": 79.2, "elapsed_time": "1:34:12", "remaining_time": "0:24:44", "throughput": 5501.68, "total_tokens": 31100112} {"current_steps": 51060, "total_steps": 64460, "loss": 0.1692, "lr": 1.2598089571455685e-06, "epoch": 15.842382873099597, "percentage": 79.21, "elapsed_time": "1:34:13", "remaining_time": "0:24:43", "throughput": 5501.57, "total_tokens": 31102512} {"current_steps": 51065, "total_steps": 64460, "loss": 0.2104, "lr": 1.2589106319225242e-06, "epoch": 15.843934222773813, "percentage": 79.22, "elapsed_time": "1:34:13", "remaining_time": "0:24:43", "throughput": 5501.59, "total_tokens": 31105552} {"current_steps": 51070, "total_steps": 64460, "loss": 0.139, "lr": 1.2580125809656334e-06, "epoch": 15.84548557244803, "percentage": 79.23, "elapsed_time": "1:34:14", "remaining_time": "0:24:42", "throughput": 5501.72, "total_tokens": 31109680} {"current_steps": 51075, "total_steps": 64460, "loss": 0.1116, "lr": 1.2571148043407306e-06, "epoch": 15.847036922122246, "percentage": 79.24, "elapsed_time": "1:34:15", "remaining_time": "0:24:42", "throughput": 5501.84, "total_tokens": 31113616} {"current_steps": 51080, "total_steps": 64460, "loss": 0.2011, "lr": 1.2562173021136371e-06, "epoch": 15.848588271796462, "percentage": 79.24, "elapsed_time": "1:34:15", "remaining_time": "0:24:41", "throughput": 5501.86, "total_tokens": 31116720} {"current_steps": 51085, "total_steps": 64460, "loss": 0.116, "lr": 1.255320074350146e-06, "epoch": 15.85013962147068, "percentage": 79.25, "elapsed_time": "1:34:16", "remaining_time": "0:24:40", "throughput": 5501.92, "total_tokens": 31120240} {"current_steps": 51090, "total_steps": 64460, "loss": 0.2124, "lr": 1.254423121116039e-06, "epoch": 15.851690971144896, "percentage": 79.26, "elapsed_time": "1:34:16", "remaining_time": "0:24:40", "throughput": 5501.94, "total_tokens": 31123088} {"current_steps": 51095, "total_steps": 64460, "loss": 0.1848, "lr": 1.2535264424770699e-06, "epoch": 15.853242320819113, "percentage": 79.27, "elapsed_time": "1:34:17", "remaining_time": "0:24:39", "throughput": 5502.0, "total_tokens": 31126416} {"current_steps": 51100, "total_steps": 64460, "loss": 0.2202, "lr": 1.2526300384989793e-06, "epoch": 15.85479367049333, "percentage": 79.27, "elapsed_time": "1:34:17", "remaining_time": "0:24:39", "throughput": 5501.97, "total_tokens": 31129008} {"current_steps": 51105, "total_steps": 64460, "loss": 0.1681, "lr": 1.2517339092474807e-06, "epoch": 15.856345020167545, "percentage": 79.28, "elapsed_time": "1:34:18", "remaining_time": "0:24:38", "throughput": 5502.01, "total_tokens": 31132240} {"current_steps": 51110, "total_steps": 64460, "loss": 0.2655, "lr": 1.2508380547882742e-06, "epoch": 15.857896369841763, "percentage": 79.29, "elapsed_time": "1:34:18", "remaining_time": "0:24:38", "throughput": 5501.98, "total_tokens": 31134768} {"current_steps": 51115, "total_steps": 64460, "loss": 0.2142, "lr": 1.2499424751870316e-06, "epoch": 15.859447719515979, "percentage": 79.3, "elapsed_time": "1:34:19", "remaining_time": "0:24:37", "throughput": 5501.98, "total_tokens": 31137488} {"current_steps": 51120, "total_steps": 64460, "loss": 0.1872, "lr": 1.2490471705094164e-06, "epoch": 15.860999069190196, "percentage": 79.3, "elapsed_time": "1:34:19", "remaining_time": "0:24:36", "throughput": 5502.01, "total_tokens": 31140368} {"current_steps": 51125, "total_steps": 64460, "loss": 0.205, "lr": 1.2481521408210595e-06, "epoch": 15.862550418864412, "percentage": 79.31, "elapsed_time": "1:34:20", "remaining_time": "0:24:36", "throughput": 5501.98, "total_tokens": 31142800} {"current_steps": 51130, "total_steps": 64460, "loss": 0.2074, "lr": 1.2472573861875815e-06, "epoch": 15.864101768538628, "percentage": 79.32, "elapsed_time": "1:34:20", "remaining_time": "0:24:35", "throughput": 5502.09, "total_tokens": 31147120} {"current_steps": 51135, "total_steps": 64460, "loss": 0.1819, "lr": 1.2463629066745742e-06, "epoch": 15.865653118212846, "percentage": 79.33, "elapsed_time": "1:34:21", "remaining_time": "0:24:35", "throughput": 5502.19, "total_tokens": 31150800} {"current_steps": 51140, "total_steps": 64460, "loss": 0.1813, "lr": 1.2454687023476153e-06, "epoch": 15.867204467887062, "percentage": 79.34, "elapsed_time": "1:34:22", "remaining_time": "0:24:34", "throughput": 5502.33, "total_tokens": 31155312} {"current_steps": 51145, "total_steps": 64460, "loss": 0.1977, "lr": 1.244574773272263e-06, "epoch": 15.868755817561278, "percentage": 79.34, "elapsed_time": "1:34:22", "remaining_time": "0:24:34", "throughput": 5502.3, "total_tokens": 31157872} {"current_steps": 51150, "total_steps": 64460, "loss": 0.1354, "lr": 1.2436811195140485e-06, "epoch": 15.870307167235495, "percentage": 79.35, "elapsed_time": "1:34:23", "remaining_time": "0:24:33", "throughput": 5502.26, "total_tokens": 31160272} {"current_steps": 51155, "total_steps": 64460, "loss": 0.1407, "lr": 1.2427877411384915e-06, "epoch": 15.871858516909711, "percentage": 79.36, "elapsed_time": "1:34:23", "remaining_time": "0:24:33", "throughput": 5502.24, "total_tokens": 31162800} {"current_steps": 51160, "total_steps": 64460, "loss": 0.1842, "lr": 1.241894638211083e-06, "epoch": 15.873409866583929, "percentage": 79.37, "elapsed_time": "1:34:24", "remaining_time": "0:24:32", "throughput": 5502.29, "total_tokens": 31165936} {"current_steps": 51165, "total_steps": 64460, "loss": 0.1366, "lr": 1.241001810797302e-06, "epoch": 15.874961216258145, "percentage": 79.37, "elapsed_time": "1:34:24", "remaining_time": "0:24:31", "throughput": 5502.22, "total_tokens": 31168176} {"current_steps": 51170, "total_steps": 64460, "loss": 0.2464, "lr": 1.2401092589626001e-06, "epoch": 15.87651256593236, "percentage": 79.38, "elapsed_time": "1:34:25", "remaining_time": "0:24:31", "throughput": 5502.31, "total_tokens": 31171888} {"current_steps": 51175, "total_steps": 64460, "loss": 0.2743, "lr": 1.239216982772415e-06, "epoch": 15.878063915606578, "percentage": 79.39, "elapsed_time": "1:34:25", "remaining_time": "0:24:30", "throughput": 5502.33, "total_tokens": 31174960} {"current_steps": 51180, "total_steps": 64460, "loss": 0.184, "lr": 1.2383249822921572e-06, "epoch": 15.879615265280794, "percentage": 79.4, "elapsed_time": "1:34:26", "remaining_time": "0:24:30", "throughput": 5502.44, "total_tokens": 31178608} {"current_steps": 51185, "total_steps": 64460, "loss": 0.1971, "lr": 1.237433257587225e-06, "epoch": 15.88116661495501, "percentage": 79.41, "elapsed_time": "1:34:26", "remaining_time": "0:24:29", "throughput": 5502.43, "total_tokens": 31181264} {"current_steps": 51190, "total_steps": 64460, "loss": 0.1568, "lr": 1.2365418087229885e-06, "epoch": 15.882717964629228, "percentage": 79.41, "elapsed_time": "1:34:27", "remaining_time": "0:24:29", "throughput": 5502.47, "total_tokens": 31184144} {"current_steps": 51195, "total_steps": 64460, "loss": 0.144, "lr": 1.2356506357648058e-06, "epoch": 15.884269314303443, "percentage": 79.42, "elapsed_time": "1:34:27", "remaining_time": "0:24:28", "throughput": 5502.47, "total_tokens": 31186800} {"current_steps": 51200, "total_steps": 64460, "loss": 0.2103, "lr": 1.2347597387780058e-06, "epoch": 15.885820663977661, "percentage": 79.43, "elapsed_time": "1:34:28", "remaining_time": "0:24:28", "throughput": 5502.46, "total_tokens": 31189872} {"current_steps": 51205, "total_steps": 64460, "loss": 0.1599, "lr": 1.2338691178279045e-06, "epoch": 15.887372013651877, "percentage": 79.44, "elapsed_time": "1:34:28", "remaining_time": "0:24:27", "throughput": 5502.52, "total_tokens": 31192976} {"current_steps": 51210, "total_steps": 64460, "loss": 0.174, "lr": 1.232978772979796e-06, "epoch": 15.888923363326093, "percentage": 79.44, "elapsed_time": "1:34:29", "remaining_time": "0:24:26", "throughput": 5502.48, "total_tokens": 31195280} {"current_steps": 51215, "total_steps": 64460, "loss": 0.1734, "lr": 1.2320887042989498e-06, "epoch": 15.89047471300031, "percentage": 79.45, "elapsed_time": "1:34:29", "remaining_time": "0:24:26", "throughput": 5502.54, "total_tokens": 31198672} {"current_steps": 51220, "total_steps": 64460, "loss": 0.2128, "lr": 1.2311989118506224e-06, "epoch": 15.892026062674526, "percentage": 79.46, "elapsed_time": "1:34:30", "remaining_time": "0:24:25", "throughput": 5502.59, "total_tokens": 31201648} {"current_steps": 51225, "total_steps": 64460, "loss": 0.1746, "lr": 1.2303093957000422e-06, "epoch": 15.893577412348744, "percentage": 79.47, "elapsed_time": "1:34:30", "remaining_time": "0:24:25", "throughput": 5502.61, "total_tokens": 31204528} {"current_steps": 51230, "total_steps": 64460, "loss": 0.2306, "lr": 1.229420155912424e-06, "epoch": 15.89512876202296, "percentage": 79.48, "elapsed_time": "1:34:31", "remaining_time": "0:24:24", "throughput": 5502.69, "total_tokens": 31208144} {"current_steps": 51235, "total_steps": 64460, "loss": 0.2497, "lr": 1.228531192552958e-06, "epoch": 15.896680111697176, "percentage": 79.48, "elapsed_time": "1:34:31", "remaining_time": "0:24:24", "throughput": 5502.74, "total_tokens": 31211120} {"current_steps": 51240, "total_steps": 64460, "loss": 0.168, "lr": 1.227642505686818e-06, "epoch": 15.898231461371394, "percentage": 79.49, "elapsed_time": "1:34:32", "remaining_time": "0:24:23", "throughput": 5502.78, "total_tokens": 31214320} {"current_steps": 51245, "total_steps": 64460, "loss": 0.2098, "lr": 1.2267540953791517e-06, "epoch": 15.89978281104561, "percentage": 79.5, "elapsed_time": "1:34:32", "remaining_time": "0:24:22", "throughput": 5502.82, "total_tokens": 31217200} {"current_steps": 51250, "total_steps": 64460, "loss": 0.1649, "lr": 1.2258659616950942e-06, "epoch": 15.901334160719827, "percentage": 79.51, "elapsed_time": "1:34:33", "remaining_time": "0:24:22", "throughput": 5502.82, "total_tokens": 31219760} {"current_steps": 51255, "total_steps": 64460, "loss": 0.1562, "lr": 1.2249781046997527e-06, "epoch": 15.902885510394043, "percentage": 79.51, "elapsed_time": "1:34:33", "remaining_time": "0:24:21", "throughput": 5502.81, "total_tokens": 31222480} {"current_steps": 51260, "total_steps": 64460, "loss": 0.2028, "lr": 1.2240905244582186e-06, "epoch": 15.904436860068259, "percentage": 79.52, "elapsed_time": "1:34:34", "remaining_time": "0:24:21", "throughput": 5502.84, "total_tokens": 31225392} {"current_steps": 51265, "total_steps": 64460, "loss": 0.1943, "lr": 1.2232032210355643e-06, "epoch": 15.905988209742477, "percentage": 79.53, "elapsed_time": "1:34:34", "remaining_time": "0:24:20", "throughput": 5502.71, "total_tokens": 31227376} {"current_steps": 51270, "total_steps": 64460, "loss": 0.1683, "lr": 1.2223161944968359e-06, "epoch": 15.907539559416692, "percentage": 79.54, "elapsed_time": "1:34:35", "remaining_time": "0:24:20", "throughput": 5502.67, "total_tokens": 31229840} {"current_steps": 51275, "total_steps": 64460, "loss": 0.2251, "lr": 1.2214294449070668e-06, "epoch": 15.909090909090908, "percentage": 79.55, "elapsed_time": "1:34:35", "remaining_time": "0:24:19", "throughput": 5502.7, "total_tokens": 31232944} {"current_steps": 51280, "total_steps": 64460, "loss": 0.2245, "lr": 1.2205429723312628e-06, "epoch": 15.910642258765126, "percentage": 79.55, "elapsed_time": "1:34:36", "remaining_time": "0:24:18", "throughput": 5502.63, "total_tokens": 31235120} {"current_steps": 51285, "total_steps": 64460, "loss": 0.1697, "lr": 1.2196567768344158e-06, "epoch": 15.912193608439342, "percentage": 79.56, "elapsed_time": "1:34:36", "remaining_time": "0:24:18", "throughput": 5502.68, "total_tokens": 31238288} {"current_steps": 51290, "total_steps": 64460, "loss": 0.1466, "lr": 1.2187708584814917e-06, "epoch": 15.91374495811356, "percentage": 79.57, "elapsed_time": "1:34:37", "remaining_time": "0:24:17", "throughput": 5502.72, "total_tokens": 31241232} {"current_steps": 51295, "total_steps": 64460, "loss": 0.156, "lr": 1.2178852173374417e-06, "epoch": 15.915296307787775, "percentage": 79.58, "elapsed_time": "1:34:37", "remaining_time": "0:24:17", "throughput": 5502.74, "total_tokens": 31244208} {"current_steps": 51300, "total_steps": 64460, "loss": 0.2231, "lr": 1.2169998534671907e-06, "epoch": 15.916847657461991, "percentage": 79.58, "elapsed_time": "1:34:38", "remaining_time": "0:24:16", "throughput": 5502.82, "total_tokens": 31247696} {"current_steps": 51305, "total_steps": 64460, "loss": 0.2176, "lr": 1.2161147669356488e-06, "epoch": 15.918399007136209, "percentage": 79.59, "elapsed_time": "1:34:39", "remaining_time": "0:24:16", "throughput": 5502.79, "total_tokens": 31250352} {"current_steps": 51310, "total_steps": 64460, "loss": 0.1789, "lr": 1.2152299578077016e-06, "epoch": 15.919950356810425, "percentage": 79.6, "elapsed_time": "1:34:39", "remaining_time": "0:24:15", "throughput": 5502.8, "total_tokens": 31253040} {"current_steps": 51315, "total_steps": 64460, "loss": 0.2429, "lr": 1.2143454261482178e-06, "epoch": 15.921501706484642, "percentage": 79.61, "elapsed_time": "1:34:39", "remaining_time": "0:24:15", "throughput": 5502.87, "total_tokens": 31256208} {"current_steps": 51320, "total_steps": 64460, "loss": 0.1979, "lr": 1.2134611720220424e-06, "epoch": 15.923053056158858, "percentage": 79.62, "elapsed_time": "1:34:40", "remaining_time": "0:24:14", "throughput": 5502.96, "total_tokens": 31259504} {"current_steps": 51325, "total_steps": 64460, "loss": 0.1983, "lr": 1.212577195494002e-06, "epoch": 15.924604405833074, "percentage": 79.62, "elapsed_time": "1:34:41", "remaining_time": "0:24:13", "throughput": 5503.12, "total_tokens": 31264368} {"current_steps": 51330, "total_steps": 64460, "loss": 0.134, "lr": 1.211693496628904e-06, "epoch": 15.926155755507292, "percentage": 79.63, "elapsed_time": "1:34:41", "remaining_time": "0:24:13", "throughput": 5503.22, "total_tokens": 31267856} {"current_steps": 51335, "total_steps": 64460, "loss": 0.1655, "lr": 1.2108100754915319e-06, "epoch": 15.927707105181508, "percentage": 79.64, "elapsed_time": "1:34:42", "remaining_time": "0:24:12", "throughput": 5503.27, "total_tokens": 31270864} {"current_steps": 51340, "total_steps": 64460, "loss": 0.1608, "lr": 1.2099269321466533e-06, "epoch": 15.929258454855724, "percentage": 79.65, "elapsed_time": "1:34:42", "remaining_time": "0:24:12", "throughput": 5503.27, "total_tokens": 31273328} {"current_steps": 51345, "total_steps": 64460, "loss": 0.175, "lr": 1.2090440666590102e-06, "epoch": 15.930809804529941, "percentage": 79.65, "elapsed_time": "1:34:43", "remaining_time": "0:24:11", "throughput": 5503.34, "total_tokens": 31277008} {"current_steps": 51350, "total_steps": 64460, "loss": 0.1457, "lr": 1.2081614790933304e-06, "epoch": 15.932361154204157, "percentage": 79.66, "elapsed_time": "1:34:43", "remaining_time": "0:24:11", "throughput": 5503.45, "total_tokens": 31281232} {"current_steps": 51355, "total_steps": 64460, "loss": 0.2222, "lr": 1.2072791695143148e-06, "epoch": 15.933912503878375, "percentage": 79.67, "elapsed_time": "1:34:44", "remaining_time": "0:24:10", "throughput": 5503.46, "total_tokens": 31283856} {"current_steps": 51360, "total_steps": 64460, "loss": 0.1999, "lr": 1.2063971379866501e-06, "epoch": 15.93546385355259, "percentage": 79.68, "elapsed_time": "1:34:44", "remaining_time": "0:24:10", "throughput": 5503.47, "total_tokens": 31286800} {"current_steps": 51365, "total_steps": 64460, "loss": 0.2035, "lr": 1.2055153845749967e-06, "epoch": 15.937015203226807, "percentage": 79.69, "elapsed_time": "1:34:45", "remaining_time": "0:24:09", "throughput": 5503.58, "total_tokens": 31290448} {"current_steps": 51370, "total_steps": 64460, "loss": 0.1955, "lr": 1.2046339093440001e-06, "epoch": 15.938566552901024, "percentage": 79.69, "elapsed_time": "1:34:45", "remaining_time": "0:24:08", "throughput": 5503.56, "total_tokens": 31293232} {"current_steps": 51375, "total_steps": 64460, "loss": 0.2066, "lr": 1.203752712358281e-06, "epoch": 15.94011790257524, "percentage": 79.7, "elapsed_time": "1:34:46", "remaining_time": "0:24:08", "throughput": 5503.6, "total_tokens": 31296016} {"current_steps": 51380, "total_steps": 64460, "loss": 0.164, "lr": 1.202871793682442e-06, "epoch": 15.941669252249458, "percentage": 79.71, "elapsed_time": "1:34:46", "remaining_time": "0:24:07", "throughput": 5503.63, "total_tokens": 31298864} {"current_steps": 51385, "total_steps": 64460, "loss": 0.1444, "lr": 1.2019911533810662e-06, "epoch": 15.943220601923674, "percentage": 79.72, "elapsed_time": "1:34:47", "remaining_time": "0:24:07", "throughput": 5503.64, "total_tokens": 31301648} {"current_steps": 51390, "total_steps": 64460, "loss": 0.2723, "lr": 1.2011107915187131e-06, "epoch": 15.94477195159789, "percentage": 79.72, "elapsed_time": "1:34:47", "remaining_time": "0:24:06", "throughput": 5503.71, "total_tokens": 31304720} {"current_steps": 51395, "total_steps": 64460, "loss": 0.1807, "lr": 1.2002307081599264e-06, "epoch": 15.946323301272107, "percentage": 79.73, "elapsed_time": "1:34:48", "remaining_time": "0:24:06", "throughput": 5503.66, "total_tokens": 31307152} {"current_steps": 51400, "total_steps": 64460, "loss": 0.1297, "lr": 1.199350903369223e-06, "epoch": 15.947874650946323, "percentage": 79.74, "elapsed_time": "1:34:48", "remaining_time": "0:24:05", "throughput": 5503.72, "total_tokens": 31310288} {"current_steps": 51405, "total_steps": 64460, "loss": 0.2646, "lr": 1.198471377211106e-06, "epoch": 15.949426000620539, "percentage": 79.75, "elapsed_time": "1:34:49", "remaining_time": "0:24:04", "throughput": 5503.75, "total_tokens": 31313424} {"current_steps": 51410, "total_steps": 64460, "loss": 0.1707, "lr": 1.1975921297500527e-06, "epoch": 15.950977350294757, "percentage": 79.75, "elapsed_time": "1:34:50", "remaining_time": "0:24:04", "throughput": 5503.88, "total_tokens": 31317360} {"current_steps": 51415, "total_steps": 64460, "loss": 0.1644, "lr": 1.1967131610505246e-06, "epoch": 15.952528699968973, "percentage": 79.76, "elapsed_time": "1:34:50", "remaining_time": "0:24:03", "throughput": 5504.06, "total_tokens": 31322288} {"current_steps": 51420, "total_steps": 64460, "loss": 0.2142, "lr": 1.1958344711769582e-06, "epoch": 15.95408004964319, "percentage": 79.77, "elapsed_time": "1:34:51", "remaining_time": "0:24:03", "throughput": 5504.03, "total_tokens": 31324784} {"current_steps": 51425, "total_steps": 64460, "loss": 0.2168, "lr": 1.194956060193775e-06, "epoch": 15.955631399317406, "percentage": 79.78, "elapsed_time": "1:34:51", "remaining_time": "0:24:02", "throughput": 5504.14, "total_tokens": 31329264} {"current_steps": 51430, "total_steps": 64460, "loss": 0.1779, "lr": 1.1940779281653691e-06, "epoch": 15.957182748991622, "percentage": 79.79, "elapsed_time": "1:34:52", "remaining_time": "0:24:02", "throughput": 5504.21, "total_tokens": 31332528} {"current_steps": 51435, "total_steps": 64460, "loss": 0.2604, "lr": 1.1932000751561217e-06, "epoch": 15.95873409866584, "percentage": 79.79, "elapsed_time": "1:34:52", "remaining_time": "0:24:01", "throughput": 5504.26, "total_tokens": 31335536} {"current_steps": 51440, "total_steps": 64460, "loss": 0.1754, "lr": 1.1923225012303864e-06, "epoch": 15.960285448340056, "percentage": 79.8, "elapsed_time": "1:34:53", "remaining_time": "0:24:01", "throughput": 5504.37, "total_tokens": 31339184} {"current_steps": 51445, "total_steps": 64460, "loss": 0.1509, "lr": 1.1914452064525011e-06, "epoch": 15.961836798014273, "percentage": 79.81, "elapsed_time": "1:34:54", "remaining_time": "0:24:00", "throughput": 5504.5, "total_tokens": 31343504} {"current_steps": 51450, "total_steps": 64460, "loss": 0.1545, "lr": 1.1905681908867845e-06, "epoch": 15.96338814768849, "percentage": 79.82, "elapsed_time": "1:34:54", "remaining_time": "0:24:00", "throughput": 5504.63, "total_tokens": 31348016} {"current_steps": 51455, "total_steps": 64460, "loss": 0.1806, "lr": 1.1896914545975279e-06, "epoch": 15.964939497362705, "percentage": 79.82, "elapsed_time": "1:34:55", "remaining_time": "0:23:59", "throughput": 5504.68, "total_tokens": 31351248} {"current_steps": 51460, "total_steps": 64460, "loss": 0.1377, "lr": 1.1888149976490098e-06, "epoch": 15.966490847036923, "percentage": 79.83, "elapsed_time": "1:34:55", "remaining_time": "0:23:58", "throughput": 5504.69, "total_tokens": 31353808} {"current_steps": 51465, "total_steps": 64460, "loss": 0.1729, "lr": 1.1879388201054826e-06, "epoch": 15.968042196711139, "percentage": 79.84, "elapsed_time": "1:34:56", "remaining_time": "0:23:58", "throughput": 5504.75, "total_tokens": 31357136} {"current_steps": 51470, "total_steps": 64460, "loss": 0.1357, "lr": 1.1870629220311825e-06, "epoch": 15.969593546385354, "percentage": 79.85, "elapsed_time": "1:34:56", "remaining_time": "0:23:57", "throughput": 5504.78, "total_tokens": 31360240} {"current_steps": 51475, "total_steps": 64460, "loss": 0.1644, "lr": 1.1861873034903204e-06, "epoch": 15.971144896059572, "percentage": 79.86, "elapsed_time": "1:34:57", "remaining_time": "0:23:57", "throughput": 5504.79, "total_tokens": 31362864} {"current_steps": 51480, "total_steps": 64460, "loss": 0.1693, "lr": 1.1853119645470934e-06, "epoch": 15.972696245733788, "percentage": 79.86, "elapsed_time": "1:34:57", "remaining_time": "0:23:56", "throughput": 5504.72, "total_tokens": 31364880} {"current_steps": 51485, "total_steps": 64460, "loss": 0.1849, "lr": 1.1844369052656702e-06, "epoch": 15.974247595408006, "percentage": 79.87, "elapsed_time": "1:34:58", "remaining_time": "0:23:56", "throughput": 5504.8, "total_tokens": 31368112} {"current_steps": 51490, "total_steps": 64460, "loss": 0.1215, "lr": 1.1835621257102066e-06, "epoch": 15.975798945082222, "percentage": 79.88, "elapsed_time": "1:34:58", "remaining_time": "0:23:55", "throughput": 5504.88, "total_tokens": 31371760} {"current_steps": 51495, "total_steps": 64460, "loss": 0.1563, "lr": 1.1826876259448305e-06, "epoch": 15.977350294756437, "percentage": 79.89, "elapsed_time": "1:34:59", "remaining_time": "0:23:54", "throughput": 5504.92, "total_tokens": 31374800} {"current_steps": 51500, "total_steps": 64460, "loss": 0.1652, "lr": 1.1818134060336562e-06, "epoch": 15.978901644430655, "percentage": 79.89, "elapsed_time": "1:34:59", "remaining_time": "0:23:54", "throughput": 5504.91, "total_tokens": 31377328} {"current_steps": 51505, "total_steps": 64460, "loss": 0.1958, "lr": 1.180939466040774e-06, "epoch": 15.980452994104871, "percentage": 79.9, "elapsed_time": "1:35:00", "remaining_time": "0:23:53", "throughput": 5505.14, "total_tokens": 31382832} {"current_steps": 51510, "total_steps": 64460, "loss": 0.1347, "lr": 1.1800658060302522e-06, "epoch": 15.982004343779089, "percentage": 79.91, "elapsed_time": "1:35:01", "remaining_time": "0:23:53", "throughput": 5505.16, "total_tokens": 31385744} {"current_steps": 51515, "total_steps": 64460, "loss": 0.1424, "lr": 1.179192426066143e-06, "epoch": 15.983555693453305, "percentage": 79.92, "elapsed_time": "1:35:01", "remaining_time": "0:23:52", "throughput": 5505.25, "total_tokens": 31389488} {"current_steps": 51520, "total_steps": 64460, "loss": 0.1993, "lr": 1.1783193262124725e-06, "epoch": 15.98510704312752, "percentage": 79.93, "elapsed_time": "1:35:02", "remaining_time": "0:23:52", "throughput": 5505.25, "total_tokens": 31391920} {"current_steps": 51525, "total_steps": 64460, "loss": 0.151, "lr": 1.1774465065332524e-06, "epoch": 15.986658392801738, "percentage": 79.93, "elapsed_time": "1:35:02", "remaining_time": "0:23:51", "throughput": 5505.32, "total_tokens": 31395728} {"current_steps": 51530, "total_steps": 64460, "loss": 0.1248, "lr": 1.1765739670924676e-06, "epoch": 15.988209742475954, "percentage": 79.94, "elapsed_time": "1:35:03", "remaining_time": "0:23:51", "throughput": 5505.36, "total_tokens": 31398736} {"current_steps": 51535, "total_steps": 64460, "loss": 0.2087, "lr": 1.175701707954089e-06, "epoch": 15.98976109215017, "percentage": 79.95, "elapsed_time": "1:35:03", "remaining_time": "0:23:50", "throughput": 5505.4, "total_tokens": 31401648} {"current_steps": 51540, "total_steps": 64460, "loss": 0.1228, "lr": 1.17482972918206e-06, "epoch": 15.991312441824387, "percentage": 79.96, "elapsed_time": "1:35:04", "remaining_time": "0:23:49", "throughput": 5505.43, "total_tokens": 31404496} {"current_steps": 51545, "total_steps": 64460, "loss": 0.2245, "lr": 1.1739580308403097e-06, "epoch": 15.992863791498603, "percentage": 79.96, "elapsed_time": "1:35:04", "remaining_time": "0:23:49", "throughput": 5505.43, "total_tokens": 31407056} {"current_steps": 51550, "total_steps": 64460, "loss": 0.1846, "lr": 1.173086612992742e-06, "epoch": 15.994415141172821, "percentage": 79.97, "elapsed_time": "1:35:05", "remaining_time": "0:23:48", "throughput": 5505.46, "total_tokens": 31409872} {"current_steps": 51555, "total_steps": 64460, "loss": 0.1597, "lr": 1.1722154757032445e-06, "epoch": 15.995966490847037, "percentage": 79.98, "elapsed_time": "1:35:05", "remaining_time": "0:23:48", "throughput": 5505.55, "total_tokens": 31413456} {"current_steps": 51560, "total_steps": 64460, "loss": 0.1669, "lr": 1.1713446190356786e-06, "epoch": 15.997517840521253, "percentage": 79.99, "elapsed_time": "1:35:06", "remaining_time": "0:23:47", "throughput": 5505.49, "total_tokens": 31415536} {"current_steps": 51565, "total_steps": 64460, "loss": 0.2247, "lr": 1.1704740430538902e-06, "epoch": 15.99906919019547, "percentage": 80.0, "elapsed_time": "1:35:06", "remaining_time": "0:23:47", "throughput": 5505.51, "total_tokens": 31418192} {"current_steps": 51568, "total_steps": 64460, "eval_loss": 0.31593939661979675, "epoch": 16.0, "percentage": 80.0, "elapsed_time": "1:35:41", "remaining_time": "0:23:55", "throughput": 5472.16, "total_tokens": 31419552} {"current_steps": 51570, "total_steps": 64460, "loss": 0.2029, "lr": 1.1696037478217043e-06, "epoch": 16.000620539869686, "percentage": 80.0, "elapsed_time": "1:35:45", "remaining_time": "0:23:56", "throughput": 5468.71, "total_tokens": 31420928} {"current_steps": 51575, "total_steps": 64460, "loss": 0.1478, "lr": 1.1687337334029209e-06, "epoch": 16.002171889543902, "percentage": 80.01, "elapsed_time": "1:35:46", "remaining_time": "0:23:55", "throughput": 5468.65, "total_tokens": 31423456} {"current_steps": 51580, "total_steps": 64460, "loss": 0.1385, "lr": 1.1678639998613256e-06, "epoch": 16.003723239218118, "percentage": 80.02, "elapsed_time": "1:35:46", "remaining_time": "0:23:54", "throughput": 5468.68, "total_tokens": 31426624} {"current_steps": 51585, "total_steps": 64460, "loss": 0.17, "lr": 1.1669945472606763e-06, "epoch": 16.005274588892338, "percentage": 80.03, "elapsed_time": "1:35:47", "remaining_time": "0:23:54", "throughput": 5468.71, "total_tokens": 31429568} {"current_steps": 51590, "total_steps": 64460, "loss": 0.1668, "lr": 1.1661253756647184e-06, "epoch": 16.006825938566553, "percentage": 80.03, "elapsed_time": "1:35:47", "remaining_time": "0:23:53", "throughput": 5468.73, "total_tokens": 31432384} {"current_steps": 51595, "total_steps": 64460, "loss": 0.1581, "lr": 1.1652564851371684e-06, "epoch": 16.00837728824077, "percentage": 80.04, "elapsed_time": "1:35:48", "remaining_time": "0:23:53", "throughput": 5468.72, "total_tokens": 31435040} {"current_steps": 51600, "total_steps": 64460, "loss": 0.1355, "lr": 1.1643878757417298e-06, "epoch": 16.009928637914985, "percentage": 80.05, "elapsed_time": "1:35:48", "remaining_time": "0:23:52", "throughput": 5468.8, "total_tokens": 31438400} {"current_steps": 51605, "total_steps": 64460, "loss": 0.1453, "lr": 1.1635195475420785e-06, "epoch": 16.0114799875892, "percentage": 80.06, "elapsed_time": "1:35:49", "remaining_time": "0:23:52", "throughput": 5468.72, "total_tokens": 31441504} {"current_steps": 51610, "total_steps": 64460, "loss": 0.1772, "lr": 1.1626515006018774e-06, "epoch": 16.01303133726342, "percentage": 80.07, "elapsed_time": "1:35:49", "remaining_time": "0:23:51", "throughput": 5468.75, "total_tokens": 31444448} {"current_steps": 51615, "total_steps": 64460, "loss": 0.2517, "lr": 1.16178373498476e-06, "epoch": 16.014582686937636, "percentage": 80.07, "elapsed_time": "1:35:50", "remaining_time": "0:23:51", "throughput": 5468.8, "total_tokens": 31448448} {"current_steps": 51620, "total_steps": 64460, "loss": 0.168, "lr": 1.1609162507543464e-06, "epoch": 16.016134036611852, "percentage": 80.08, "elapsed_time": "1:35:51", "remaining_time": "0:23:50", "throughput": 5468.71, "total_tokens": 31450848} {"current_steps": 51625, "total_steps": 64460, "loss": 0.1516, "lr": 1.160049047974235e-06, "epoch": 16.017685386286068, "percentage": 80.09, "elapsed_time": "1:35:51", "remaining_time": "0:23:49", "throughput": 5468.64, "total_tokens": 31453024} {"current_steps": 51630, "total_steps": 64460, "loss": 0.1191, "lr": 1.1591821267079984e-06, "epoch": 16.019236735960284, "percentage": 80.1, "elapsed_time": "1:35:52", "remaining_time": "0:23:49", "throughput": 5468.62, "total_tokens": 31455520} {"current_steps": 51635, "total_steps": 64460, "loss": 0.1713, "lr": 1.1583154870191954e-06, "epoch": 16.020788085634504, "percentage": 80.1, "elapsed_time": "1:35:52", "remaining_time": "0:23:48", "throughput": 5468.71, "total_tokens": 31460000} {"current_steps": 51640, "total_steps": 64460, "loss": 0.174, "lr": 1.1574491289713586e-06, "epoch": 16.02233943530872, "percentage": 80.11, "elapsed_time": "1:35:53", "remaining_time": "0:23:48", "throughput": 5468.68, "total_tokens": 31462560} {"current_steps": 51645, "total_steps": 64460, "loss": 0.1315, "lr": 1.1565830526280042e-06, "epoch": 16.023890784982935, "percentage": 80.12, "elapsed_time": "1:35:53", "remaining_time": "0:23:47", "throughput": 5468.73, "total_tokens": 31465792} {"current_steps": 51650, "total_steps": 64460, "loss": 0.1868, "lr": 1.1557172580526233e-06, "epoch": 16.02544213465715, "percentage": 80.13, "elapsed_time": "1:35:54", "remaining_time": "0:23:47", "throughput": 5468.91, "total_tokens": 31470848} {"current_steps": 51655, "total_steps": 64460, "loss": 0.2209, "lr": 1.1548517453086926e-06, "epoch": 16.026993484331367, "percentage": 80.13, "elapsed_time": "1:35:55", "remaining_time": "0:23:46", "throughput": 5468.96, "total_tokens": 31474624} {"current_steps": 51660, "total_steps": 64460, "loss": 0.2117, "lr": 1.15398651445966e-06, "epoch": 16.028544834005586, "percentage": 80.14, "elapsed_time": "1:35:55", "remaining_time": "0:23:46", "throughput": 5469.01, "total_tokens": 31477632} {"current_steps": 51665, "total_steps": 64460, "loss": 0.1277, "lr": 1.153121565568962e-06, "epoch": 16.030096183679802, "percentage": 80.15, "elapsed_time": "1:35:56", "remaining_time": "0:23:45", "throughput": 5469.0, "total_tokens": 31480320} {"current_steps": 51670, "total_steps": 64460, "loss": 0.1754, "lr": 1.1522568987000049e-06, "epoch": 16.03164753335402, "percentage": 80.16, "elapsed_time": "1:35:56", "remaining_time": "0:23:44", "throughput": 5469.12, "total_tokens": 31484160} {"current_steps": 51675, "total_steps": 64460, "loss": 0.1605, "lr": 1.151392513916183e-06, "epoch": 16.033198883028234, "percentage": 80.17, "elapsed_time": "1:35:57", "remaining_time": "0:23:44", "throughput": 5469.15, "total_tokens": 31487072} {"current_steps": 51680, "total_steps": 64460, "loss": 0.1846, "lr": 1.1505284112808624e-06, "epoch": 16.03475023270245, "percentage": 80.17, "elapsed_time": "1:35:57", "remaining_time": "0:23:43", "throughput": 5469.17, "total_tokens": 31489792} {"current_steps": 51685, "total_steps": 64460, "loss": 0.1361, "lr": 1.1496645908573946e-06, "epoch": 16.03630158237667, "percentage": 80.18, "elapsed_time": "1:35:58", "remaining_time": "0:23:43", "throughput": 5469.22, "total_tokens": 31492864} {"current_steps": 51690, "total_steps": 64460, "loss": 0.2158, "lr": 1.1488010527091075e-06, "epoch": 16.037852932050885, "percentage": 80.19, "elapsed_time": "1:35:58", "remaining_time": "0:23:42", "throughput": 5469.22, "total_tokens": 31495456} {"current_steps": 51695, "total_steps": 64460, "loss": 0.1511, "lr": 1.147937796899307e-06, "epoch": 16.0394042817251, "percentage": 80.2, "elapsed_time": "1:35:59", "remaining_time": "0:23:42", "throughput": 5469.34, "total_tokens": 31499328} {"current_steps": 51700, "total_steps": 64460, "loss": 0.1767, "lr": 1.1470748234912821e-06, "epoch": 16.040955631399317, "percentage": 80.2, "elapsed_time": "1:35:59", "remaining_time": "0:23:41", "throughput": 5469.35, "total_tokens": 31502112} {"current_steps": 51705, "total_steps": 64460, "loss": 0.1104, "lr": 1.1462121325482972e-06, "epoch": 16.042506981073533, "percentage": 80.21, "elapsed_time": "1:36:00", "remaining_time": "0:23:40", "throughput": 5469.41, "total_tokens": 31505312} {"current_steps": 51710, "total_steps": 64460, "loss": 0.142, "lr": 1.1453497241336004e-06, "epoch": 16.04405833074775, "percentage": 80.22, "elapsed_time": "1:36:00", "remaining_time": "0:23:40", "throughput": 5469.43, "total_tokens": 31507968} {"current_steps": 51715, "total_steps": 64460, "loss": 0.1631, "lr": 1.1444875983104131e-06, "epoch": 16.04560968042197, "percentage": 80.23, "elapsed_time": "1:36:01", "remaining_time": "0:23:39", "throughput": 5469.48, "total_tokens": 31510880} {"current_steps": 51720, "total_steps": 64460, "loss": 0.2581, "lr": 1.1436257551419427e-06, "epoch": 16.047161030096184, "percentage": 80.24, "elapsed_time": "1:36:01", "remaining_time": "0:23:39", "throughput": 5469.45, "total_tokens": 31513312} {"current_steps": 51725, "total_steps": 64460, "loss": 0.192, "lr": 1.1427641946913693e-06, "epoch": 16.0487123797704, "percentage": 80.24, "elapsed_time": "1:36:02", "remaining_time": "0:23:38", "throughput": 5469.49, "total_tokens": 31516512} {"current_steps": 51730, "total_steps": 64460, "loss": 0.1006, "lr": 1.1419029170218582e-06, "epoch": 16.050263729444616, "percentage": 80.25, "elapsed_time": "1:36:02", "remaining_time": "0:23:38", "throughput": 5469.47, "total_tokens": 31519168} {"current_steps": 51735, "total_steps": 64460, "loss": 0.1281, "lr": 1.1410419221965485e-06, "epoch": 16.051815079118832, "percentage": 80.26, "elapsed_time": "1:36:03", "remaining_time": "0:23:37", "throughput": 5469.58, "total_tokens": 31523104} {"current_steps": 51740, "total_steps": 64460, "loss": 0.2229, "lr": 1.1401812102785643e-06, "epoch": 16.05336642879305, "percentage": 80.27, "elapsed_time": "1:36:04", "remaining_time": "0:23:37", "throughput": 5469.68, "total_tokens": 31527264} {"current_steps": 51745, "total_steps": 64460, "loss": 0.1543, "lr": 1.139320781331003e-06, "epoch": 16.054917778467267, "percentage": 80.27, "elapsed_time": "1:36:04", "remaining_time": "0:23:36", "throughput": 5469.64, "total_tokens": 31529472} {"current_steps": 51750, "total_steps": 64460, "loss": 0.1897, "lr": 1.1384606354169475e-06, "epoch": 16.056469128141483, "percentage": 80.28, "elapsed_time": "1:36:05", "remaining_time": "0:23:35", "throughput": 5469.73, "total_tokens": 31533056} {"current_steps": 51755, "total_steps": 64460, "loss": 0.2158, "lr": 1.137600772599453e-06, "epoch": 16.0580204778157, "percentage": 80.29, "elapsed_time": "1:36:05", "remaining_time": "0:23:35", "throughput": 5469.71, "total_tokens": 31535584} {"current_steps": 51760, "total_steps": 64460, "loss": 0.1769, "lr": 1.1367411929415612e-06, "epoch": 16.059571827489915, "percentage": 80.3, "elapsed_time": "1:36:05", "remaining_time": "0:23:34", "throughput": 5469.66, "total_tokens": 31537856} {"current_steps": 51765, "total_steps": 64460, "loss": 0.203, "lr": 1.1358818965062862e-06, "epoch": 16.061123177164134, "percentage": 80.31, "elapsed_time": "1:36:06", "remaining_time": "0:23:34", "throughput": 5469.75, "total_tokens": 31541152} {"current_steps": 51770, "total_steps": 64460, "loss": 0.2885, "lr": 1.1350228833566263e-06, "epoch": 16.06267452683835, "percentage": 80.31, "elapsed_time": "1:36:07", "remaining_time": "0:23:33", "throughput": 5469.87, "total_tokens": 31545056} {"current_steps": 51775, "total_steps": 64460, "loss": 0.0873, "lr": 1.1341641535555587e-06, "epoch": 16.064225876512566, "percentage": 80.32, "elapsed_time": "1:36:07", "remaining_time": "0:23:33", "throughput": 5469.96, "total_tokens": 31548384} {"current_steps": 51780, "total_steps": 64460, "loss": 0.1356, "lr": 1.1333057071660353e-06, "epoch": 16.065777226186782, "percentage": 80.33, "elapsed_time": "1:36:08", "remaining_time": "0:23:32", "throughput": 5469.95, "total_tokens": 31551008} {"current_steps": 51785, "total_steps": 64460, "loss": 0.1259, "lr": 1.1324475442509935e-06, "epoch": 16.067328575860998, "percentage": 80.34, "elapsed_time": "1:36:08", "remaining_time": "0:23:31", "throughput": 5470.02, "total_tokens": 31554496} {"current_steps": 51790, "total_steps": 64460, "loss": 0.1716, "lr": 1.1315896648733444e-06, "epoch": 16.068879925535217, "percentage": 80.34, "elapsed_time": "1:36:09", "remaining_time": "0:23:31", "throughput": 5470.18, "total_tokens": 31558880} {"current_steps": 51795, "total_steps": 64460, "loss": 0.1671, "lr": 1.1307320690959828e-06, "epoch": 16.070431275209433, "percentage": 80.35, "elapsed_time": "1:36:09", "remaining_time": "0:23:30", "throughput": 5470.21, "total_tokens": 31562912} {"current_steps": 51800, "total_steps": 64460, "loss": 0.1347, "lr": 1.129874756981778e-06, "epoch": 16.07198262488365, "percentage": 80.36, "elapsed_time": "1:36:10", "remaining_time": "0:23:30", "throughput": 5470.27, "total_tokens": 31567296} {"current_steps": 51805, "total_steps": 64460, "loss": 0.1326, "lr": 1.1290177285935844e-06, "epoch": 16.073533974557865, "percentage": 80.37, "elapsed_time": "1:36:11", "remaining_time": "0:23:29", "throughput": 5470.28, "total_tokens": 31570272} {"current_steps": 51810, "total_steps": 64460, "loss": 0.1273, "lr": 1.1281609839942291e-06, "epoch": 16.07508532423208, "percentage": 80.38, "elapsed_time": "1:36:11", "remaining_time": "0:23:29", "throughput": 5470.25, "total_tokens": 31572992} {"current_steps": 51815, "total_steps": 64460, "loss": 0.1601, "lr": 1.127304523246524e-06, "epoch": 16.0766366739063, "percentage": 80.38, "elapsed_time": "1:36:12", "remaining_time": "0:23:28", "throughput": 5470.16, "total_tokens": 31575552} {"current_steps": 51820, "total_steps": 64460, "loss": 0.1334, "lr": 1.1264483464132563e-06, "epoch": 16.078188023580516, "percentage": 80.39, "elapsed_time": "1:36:12", "remaining_time": "0:23:28", "throughput": 5470.19, "total_tokens": 31578464} {"current_steps": 51825, "total_steps": 64460, "loss": 0.1478, "lr": 1.1255924535571939e-06, "epoch": 16.079739373254732, "percentage": 80.4, "elapsed_time": "1:36:13", "remaining_time": "0:23:27", "throughput": 5470.09, "total_tokens": 31580480} {"current_steps": 51830, "total_steps": 64460, "loss": 0.1597, "lr": 1.124736844741086e-06, "epoch": 16.081290722928948, "percentage": 80.41, "elapsed_time": "1:36:13", "remaining_time": "0:23:26", "throughput": 5470.08, "total_tokens": 31583072} {"current_steps": 51835, "total_steps": 64460, "loss": 0.166, "lr": 1.1238815200276565e-06, "epoch": 16.082842072603164, "percentage": 80.41, "elapsed_time": "1:36:14", "remaining_time": "0:23:26", "throughput": 5470.0, "total_tokens": 31585280} {"current_steps": 51840, "total_steps": 64460, "loss": 0.1323, "lr": 1.1230264794796126e-06, "epoch": 16.08439342227738, "percentage": 80.42, "elapsed_time": "1:36:14", "remaining_time": "0:23:25", "throughput": 5469.92, "total_tokens": 31587712} {"current_steps": 51845, "total_steps": 64460, "loss": 0.1435, "lr": 1.1221717231596368e-06, "epoch": 16.0859447719516, "percentage": 80.43, "elapsed_time": "1:36:15", "remaining_time": "0:23:25", "throughput": 5469.83, "total_tokens": 31590080} {"current_steps": 51850, "total_steps": 64460, "loss": 0.1459, "lr": 1.1213172511303954e-06, "epoch": 16.087496121625815, "percentage": 80.44, "elapsed_time": "1:36:15", "remaining_time": "0:23:24", "throughput": 5469.86, "total_tokens": 31592928} {"current_steps": 51855, "total_steps": 64460, "loss": 0.1867, "lr": 1.1204630634545283e-06, "epoch": 16.08904747130003, "percentage": 80.45, "elapsed_time": "1:36:16", "remaining_time": "0:23:24", "throughput": 5469.84, "total_tokens": 31595520} {"current_steps": 51860, "total_steps": 64460, "loss": 0.1029, "lr": 1.1196091601946607e-06, "epoch": 16.090598820974247, "percentage": 80.45, "elapsed_time": "1:36:16", "remaining_time": "0:23:23", "throughput": 5469.95, "total_tokens": 31599872} {"current_steps": 51865, "total_steps": 64460, "loss": 0.2309, "lr": 1.1187555414133916e-06, "epoch": 16.092150170648463, "percentage": 80.46, "elapsed_time": "1:36:17", "remaining_time": "0:23:23", "throughput": 5469.99, "total_tokens": 31602848} {"current_steps": 51870, "total_steps": 64460, "loss": 0.1707, "lr": 1.1179022071733025e-06, "epoch": 16.093701520322682, "percentage": 80.47, "elapsed_time": "1:36:17", "remaining_time": "0:23:22", "throughput": 5469.92, "total_tokens": 31605152} {"current_steps": 51875, "total_steps": 64460, "loss": 0.2129, "lr": 1.117049157536952e-06, "epoch": 16.095252869996898, "percentage": 80.48, "elapsed_time": "1:36:18", "remaining_time": "0:23:21", "throughput": 5469.92, "total_tokens": 31608000} {"current_steps": 51880, "total_steps": 64460, "loss": 0.1485, "lr": 1.11619639256688e-06, "epoch": 16.096804219671114, "percentage": 80.48, "elapsed_time": "1:36:19", "remaining_time": "0:23:21", "throughput": 5469.93, "total_tokens": 31611072} {"current_steps": 51885, "total_steps": 64460, "loss": 0.1565, "lr": 1.1153439123256026e-06, "epoch": 16.09835556934533, "percentage": 80.49, "elapsed_time": "1:36:19", "remaining_time": "0:23:20", "throughput": 5469.93, "total_tokens": 31614016} {"current_steps": 51890, "total_steps": 64460, "loss": 0.1641, "lr": 1.1144917168756175e-06, "epoch": 16.099906919019546, "percentage": 80.5, "elapsed_time": "1:36:20", "remaining_time": "0:23:20", "throughput": 5470.03, "total_tokens": 31617600} {"current_steps": 51895, "total_steps": 64460, "loss": 0.1754, "lr": 1.1136398062794023e-06, "epoch": 16.101458268693765, "percentage": 80.51, "elapsed_time": "1:36:20", "remaining_time": "0:23:19", "throughput": 5470.0, "total_tokens": 31620160} {"current_steps": 51900, "total_steps": 64460, "loss": 0.2013, "lr": 1.1127881805994095e-06, "epoch": 16.10300961836798, "percentage": 80.52, "elapsed_time": "1:36:21", "remaining_time": "0:23:19", "throughput": 5470.05, "total_tokens": 31624672} {"current_steps": 51905, "total_steps": 64460, "loss": 0.2513, "lr": 1.1119368398980756e-06, "epoch": 16.104560968042197, "percentage": 80.52, "elapsed_time": "1:36:21", "remaining_time": "0:23:18", "throughput": 5470.1, "total_tokens": 31627936} {"current_steps": 51910, "total_steps": 64460, "loss": 0.1151, "lr": 1.1110857842378114e-06, "epoch": 16.106112317716413, "percentage": 80.53, "elapsed_time": "1:36:22", "remaining_time": "0:23:17", "throughput": 5470.11, "total_tokens": 31630752} {"current_steps": 51915, "total_steps": 64460, "loss": 0.2391, "lr": 1.1102350136810124e-06, "epoch": 16.10766366739063, "percentage": 80.54, "elapsed_time": "1:36:22", "remaining_time": "0:23:17", "throughput": 5470.14, "total_tokens": 31633664} {"current_steps": 51920, "total_steps": 64460, "loss": 0.1672, "lr": 1.1093845282900473e-06, "epoch": 16.109215017064848, "percentage": 80.55, "elapsed_time": "1:36:23", "remaining_time": "0:23:16", "throughput": 5470.22, "total_tokens": 31637312} {"current_steps": 51925, "total_steps": 64460, "loss": 0.1677, "lr": 1.1085343281272697e-06, "epoch": 16.110766366739064, "percentage": 80.55, "elapsed_time": "1:36:24", "remaining_time": "0:23:16", "throughput": 5470.19, "total_tokens": 31639840} {"current_steps": 51930, "total_steps": 64460, "loss": 0.1623, "lr": 1.1076844132550057e-06, "epoch": 16.11231771641328, "percentage": 80.56, "elapsed_time": "1:36:24", "remaining_time": "0:23:15", "throughput": 5470.19, "total_tokens": 31642656} {"current_steps": 51935, "total_steps": 64460, "loss": 0.1846, "lr": 1.106834783735568e-06, "epoch": 16.113869066087496, "percentage": 80.57, "elapsed_time": "1:36:25", "remaining_time": "0:23:15", "throughput": 5470.24, "total_tokens": 31646752} {"current_steps": 51940, "total_steps": 64460, "loss": 0.056, "lr": 1.1059854396312408e-06, "epoch": 16.11542041576171, "percentage": 80.58, "elapsed_time": "1:36:26", "remaining_time": "0:23:14", "throughput": 5470.4, "total_tokens": 31652000} {"current_steps": 51945, "total_steps": 64460, "loss": 0.186, "lr": 1.1051363810042931e-06, "epoch": 16.11697176543593, "percentage": 80.58, "elapsed_time": "1:36:26", "remaining_time": "0:23:14", "throughput": 5470.41, "total_tokens": 31654720} {"current_steps": 51950, "total_steps": 64460, "loss": 0.2489, "lr": 1.1042876079169722e-06, "epoch": 16.118523115110147, "percentage": 80.59, "elapsed_time": "1:36:27", "remaining_time": "0:23:13", "throughput": 5470.38, "total_tokens": 31657184} {"current_steps": 51955, "total_steps": 64460, "loss": 0.1217, "lr": 1.1034391204315003e-06, "epoch": 16.120074464784363, "percentage": 80.6, "elapsed_time": "1:36:27", "remaining_time": "0:23:12", "throughput": 5470.38, "total_tokens": 31659872} {"current_steps": 51960, "total_steps": 64460, "loss": 0.1491, "lr": 1.1025909186100847e-06, "epoch": 16.12162581445858, "percentage": 80.61, "elapsed_time": "1:36:28", "remaining_time": "0:23:12", "throughput": 5470.39, "total_tokens": 31663040} {"current_steps": 51965, "total_steps": 64460, "loss": 0.0943, "lr": 1.1017430025149057e-06, "epoch": 16.123177164132795, "percentage": 80.62, "elapsed_time": "1:36:28", "remaining_time": "0:23:11", "throughput": 5470.39, "total_tokens": 31665824} {"current_steps": 51970, "total_steps": 64460, "loss": 0.2091, "lr": 1.1008953722081277e-06, "epoch": 16.12472851380701, "percentage": 80.62, "elapsed_time": "1:36:29", "remaining_time": "0:23:11", "throughput": 5470.62, "total_tokens": 31671520} {"current_steps": 51975, "total_steps": 64460, "loss": 0.204, "lr": 1.1000480277518905e-06, "epoch": 16.12627986348123, "percentage": 80.63, "elapsed_time": "1:36:29", "remaining_time": "0:23:10", "throughput": 5470.62, "total_tokens": 31674144} {"current_steps": 51980, "total_steps": 64460, "loss": 0.1869, "lr": 1.0992009692083161e-06, "epoch": 16.127831213155446, "percentage": 80.64, "elapsed_time": "1:36:30", "remaining_time": "0:23:10", "throughput": 5470.62, "total_tokens": 31676992} {"current_steps": 51985, "total_steps": 64460, "loss": 0.1426, "lr": 1.0983541966395016e-06, "epoch": 16.12938256282966, "percentage": 80.65, "elapsed_time": "1:36:30", "remaining_time": "0:23:09", "throughput": 5470.63, "total_tokens": 31679712} {"current_steps": 51990, "total_steps": 64460, "loss": 0.2064, "lr": 1.0975077101075288e-06, "epoch": 16.130933912503878, "percentage": 80.65, "elapsed_time": "1:36:31", "remaining_time": "0:23:09", "throughput": 5470.76, "total_tokens": 31684000} {"current_steps": 51995, "total_steps": 64460, "loss": 0.1119, "lr": 1.0966615096744515e-06, "epoch": 16.132485262178093, "percentage": 80.66, "elapsed_time": "1:36:32", "remaining_time": "0:23:08", "throughput": 5470.82, "total_tokens": 31687168} {"current_steps": 52000, "total_steps": 64460, "loss": 0.1346, "lr": 1.0958155954023092e-06, "epoch": 16.134036611852313, "percentage": 80.67, "elapsed_time": "1:36:32", "remaining_time": "0:23:07", "throughput": 5470.79, "total_tokens": 31689824} {"current_steps": 52005, "total_steps": 64460, "loss": 0.2123, "lr": 1.094969967353115e-06, "epoch": 16.13558796152653, "percentage": 80.68, "elapsed_time": "1:36:33", "remaining_time": "0:23:07", "throughput": 5470.89, "total_tokens": 31693440} {"current_steps": 52010, "total_steps": 64460, "loss": 0.1837, "lr": 1.0941246255888648e-06, "epoch": 16.137139311200745, "percentage": 80.69, "elapsed_time": "1:36:33", "remaining_time": "0:23:06", "throughput": 5470.94, "total_tokens": 31696480} {"current_steps": 52015, "total_steps": 64460, "loss": 0.1983, "lr": 1.0932795701715333e-06, "epoch": 16.13869066087496, "percentage": 80.69, "elapsed_time": "1:36:34", "remaining_time": "0:23:06", "throughput": 5471.03, "total_tokens": 31701056} {"current_steps": 52020, "total_steps": 64460, "loss": 0.1133, "lr": 1.0924348011630704e-06, "epoch": 16.140242010549176, "percentage": 80.7, "elapsed_time": "1:36:34", "remaining_time": "0:23:05", "throughput": 5471.18, "total_tokens": 31705440} {"current_steps": 52025, "total_steps": 64460, "loss": 0.21, "lr": 1.0915903186254107e-06, "epoch": 16.141793360223396, "percentage": 80.71, "elapsed_time": "1:36:35", "remaining_time": "0:23:05", "throughput": 5471.19, "total_tokens": 31708128} {"current_steps": 52030, "total_steps": 64460, "loss": 0.1316, "lr": 1.0907461226204614e-06, "epoch": 16.14334470989761, "percentage": 80.72, "elapsed_time": "1:36:35", "remaining_time": "0:23:04", "throughput": 5471.13, "total_tokens": 31710336} {"current_steps": 52035, "total_steps": 64460, "loss": 0.1965, "lr": 1.089902213210115e-06, "epoch": 16.144896059571828, "percentage": 80.72, "elapsed_time": "1:36:36", "remaining_time": "0:23:04", "throughput": 5471.24, "total_tokens": 31714112} {"current_steps": 52040, "total_steps": 64460, "loss": 0.1518, "lr": 1.0890585904562378e-06, "epoch": 16.146447409246043, "percentage": 80.73, "elapsed_time": "1:36:37", "remaining_time": "0:23:03", "throughput": 5471.28, "total_tokens": 31717344} {"current_steps": 52045, "total_steps": 64460, "loss": 0.2063, "lr": 1.0882152544206798e-06, "epoch": 16.14799875892026, "percentage": 80.74, "elapsed_time": "1:36:37", "remaining_time": "0:23:03", "throughput": 5471.32, "total_tokens": 31720992} {"current_steps": 52050, "total_steps": 64460, "loss": 0.1751, "lr": 1.0873722051652646e-06, "epoch": 16.14955010859448, "percentage": 80.75, "elapsed_time": "1:36:38", "remaining_time": "0:23:02", "throughput": 5471.42, "total_tokens": 31724640} {"current_steps": 52055, "total_steps": 64460, "loss": 0.1484, "lr": 1.0865294427518008e-06, "epoch": 16.151101458268695, "percentage": 80.76, "elapsed_time": "1:36:38", "remaining_time": "0:23:01", "throughput": 5471.44, "total_tokens": 31727648} {"current_steps": 52060, "total_steps": 64460, "loss": 0.1503, "lr": 1.08568696724207e-06, "epoch": 16.15265280794291, "percentage": 80.76, "elapsed_time": "1:36:39", "remaining_time": "0:23:01", "throughput": 5471.42, "total_tokens": 31730656} {"current_steps": 52065, "total_steps": 64460, "loss": 0.1435, "lr": 1.0848447786978378e-06, "epoch": 16.154204157617126, "percentage": 80.77, "elapsed_time": "1:36:39", "remaining_time": "0:23:00", "throughput": 5471.35, "total_tokens": 31732832} {"current_steps": 52070, "total_steps": 64460, "loss": 0.1807, "lr": 1.0840028771808448e-06, "epoch": 16.155755507291342, "percentage": 80.78, "elapsed_time": "1:36:40", "remaining_time": "0:23:00", "throughput": 5471.25, "total_tokens": 31735168} {"current_steps": 52075, "total_steps": 64460, "loss": 0.1598, "lr": 1.0831612627528132e-06, "epoch": 16.157306856965562, "percentage": 80.79, "elapsed_time": "1:36:40", "remaining_time": "0:22:59", "throughput": 5471.26, "total_tokens": 31737888} {"current_steps": 52080, "total_steps": 64460, "loss": 0.163, "lr": 1.0823199354754442e-06, "epoch": 16.158858206639778, "percentage": 80.79, "elapsed_time": "1:36:41", "remaining_time": "0:22:59", "throughput": 5471.23, "total_tokens": 31740384} {"current_steps": 52085, "total_steps": 64460, "loss": 0.1526, "lr": 1.0814788954104156e-06, "epoch": 16.160409556313994, "percentage": 80.8, "elapsed_time": "1:36:41", "remaining_time": "0:22:58", "throughput": 5471.28, "total_tokens": 31743360} {"current_steps": 52090, "total_steps": 64460, "loss": 0.1752, "lr": 1.0806381426193869e-06, "epoch": 16.16196090598821, "percentage": 80.81, "elapsed_time": "1:36:42", "remaining_time": "0:22:57", "throughput": 5471.29, "total_tokens": 31746528} {"current_steps": 52095, "total_steps": 64460, "loss": 0.1326, "lr": 1.0797976771639934e-06, "epoch": 16.163512255662425, "percentage": 80.82, "elapsed_time": "1:36:42", "remaining_time": "0:22:57", "throughput": 5471.37, "total_tokens": 31750112} {"current_steps": 52100, "total_steps": 64460, "loss": 0.1715, "lr": 1.0789574991058538e-06, "epoch": 16.16506360533664, "percentage": 80.83, "elapsed_time": "1:36:43", "remaining_time": "0:22:56", "throughput": 5471.38, "total_tokens": 31753152} {"current_steps": 52105, "total_steps": 64460, "loss": 0.1707, "lr": 1.0781176085065598e-06, "epoch": 16.16661495501086, "percentage": 80.83, "elapsed_time": "1:36:44", "remaining_time": "0:22:56", "throughput": 5471.4, "total_tokens": 31756032} {"current_steps": 52110, "total_steps": 64460, "loss": 0.1443, "lr": 1.0772780054276887e-06, "epoch": 16.168166304685077, "percentage": 80.84, "elapsed_time": "1:36:44", "remaining_time": "0:22:55", "throughput": 5471.45, "total_tokens": 31759136} {"current_steps": 52115, "total_steps": 64460, "loss": 0.1795, "lr": 1.076438689930791e-06, "epoch": 16.169717654359292, "percentage": 80.85, "elapsed_time": "1:36:44", "remaining_time": "0:22:55", "throughput": 5471.44, "total_tokens": 31761728} {"current_steps": 52120, "total_steps": 64460, "loss": 0.1471, "lr": 1.0755996620774001e-06, "epoch": 16.17126900403351, "percentage": 80.86, "elapsed_time": "1:36:45", "remaining_time": "0:22:54", "throughput": 5471.46, "total_tokens": 31764512} {"current_steps": 52125, "total_steps": 64460, "loss": 0.2222, "lr": 1.0747609219290245e-06, "epoch": 16.172820353707724, "percentage": 80.86, "elapsed_time": "1:36:46", "remaining_time": "0:22:53", "throughput": 5471.58, "total_tokens": 31768896} {"current_steps": 52130, "total_steps": 64460, "loss": 0.1588, "lr": 1.073922469547155e-06, "epoch": 16.174371703381944, "percentage": 80.87, "elapsed_time": "1:36:46", "remaining_time": "0:22:53", "throughput": 5471.57, "total_tokens": 31771712} {"current_steps": 52135, "total_steps": 64460, "loss": 0.1353, "lr": 1.0730843049932615e-06, "epoch": 16.17592305305616, "percentage": 80.88, "elapsed_time": "1:36:47", "remaining_time": "0:22:52", "throughput": 5471.65, "total_tokens": 31775328} {"current_steps": 52140, "total_steps": 64460, "loss": 0.2255, "lr": 1.0722464283287891e-06, "epoch": 16.177474402730375, "percentage": 80.89, "elapsed_time": "1:36:47", "remaining_time": "0:22:52", "throughput": 5471.62, "total_tokens": 31777888} {"current_steps": 52145, "total_steps": 64460, "loss": 0.0987, "lr": 1.0714088396151662e-06, "epoch": 16.17902575240459, "percentage": 80.9, "elapsed_time": "1:36:48", "remaining_time": "0:22:51", "throughput": 5471.67, "total_tokens": 31780896} {"current_steps": 52150, "total_steps": 64460, "loss": 0.164, "lr": 1.0705715389137955e-06, "epoch": 16.180577102078807, "percentage": 80.9, "elapsed_time": "1:36:48", "remaining_time": "0:22:51", "throughput": 5471.64, "total_tokens": 31783360} {"current_steps": 52155, "total_steps": 64460, "loss": 0.1791, "lr": 1.0697345262860638e-06, "epoch": 16.182128451753027, "percentage": 80.91, "elapsed_time": "1:36:49", "remaining_time": "0:22:50", "throughput": 5471.57, "total_tokens": 31785952} {"current_steps": 52160, "total_steps": 64460, "loss": 0.1439, "lr": 1.068897801793331e-06, "epoch": 16.183679801427242, "percentage": 80.92, "elapsed_time": "1:36:49", "remaining_time": "0:22:50", "throughput": 5471.45, "total_tokens": 31788096} {"current_steps": 52165, "total_steps": 64460, "loss": 0.126, "lr": 1.0680613654969423e-06, "epoch": 16.18523115110146, "percentage": 80.93, "elapsed_time": "1:36:50", "remaining_time": "0:22:49", "throughput": 5471.49, "total_tokens": 31791360} {"current_steps": 52170, "total_steps": 64460, "loss": 0.1278, "lr": 1.0672252174582148e-06, "epoch": 16.186782500775674, "percentage": 80.93, "elapsed_time": "1:36:50", "remaining_time": "0:22:48", "throughput": 5471.41, "total_tokens": 31793600} {"current_steps": 52175, "total_steps": 64460, "loss": 0.1682, "lr": 1.0663893577384515e-06, "epoch": 16.18833385044989, "percentage": 80.94, "elapsed_time": "1:36:51", "remaining_time": "0:22:48", "throughput": 5471.49, "total_tokens": 31796960} {"current_steps": 52180, "total_steps": 64460, "loss": 0.1087, "lr": 1.0655537863989278e-06, "epoch": 16.18988520012411, "percentage": 80.95, "elapsed_time": "1:36:51", "remaining_time": "0:22:47", "throughput": 5471.52, "total_tokens": 31800128} {"current_steps": 52185, "total_steps": 64460, "loss": 0.1688, "lr": 1.064718503500904e-06, "epoch": 16.191436549798325, "percentage": 80.96, "elapsed_time": "1:36:52", "remaining_time": "0:22:47", "throughput": 5471.56, "total_tokens": 31803296} {"current_steps": 52190, "total_steps": 64460, "loss": 0.2385, "lr": 1.0638835091056132e-06, "epoch": 16.19298789947254, "percentage": 80.96, "elapsed_time": "1:36:52", "remaining_time": "0:22:46", "throughput": 5471.54, "total_tokens": 31806016} {"current_steps": 52195, "total_steps": 64460, "loss": 0.1945, "lr": 1.0630488032742713e-06, "epoch": 16.194539249146757, "percentage": 80.97, "elapsed_time": "1:36:53", "remaining_time": "0:22:46", "throughput": 5471.55, "total_tokens": 31809088} {"current_steps": 52200, "total_steps": 64460, "loss": 0.1737, "lr": 1.0622143860680744e-06, "epoch": 16.196090598820973, "percentage": 80.98, "elapsed_time": "1:36:54", "remaining_time": "0:22:45", "throughput": 5471.54, "total_tokens": 31811968} {"current_steps": 52205, "total_steps": 64460, "loss": 0.2011, "lr": 1.0613802575481919e-06, "epoch": 16.197641948495193, "percentage": 80.99, "elapsed_time": "1:36:54", "remaining_time": "0:22:44", "throughput": 5471.55, "total_tokens": 31814976} {"current_steps": 52210, "total_steps": 64460, "loss": 0.2955, "lr": 1.060546417775778e-06, "epoch": 16.19919329816941, "percentage": 81.0, "elapsed_time": "1:36:55", "remaining_time": "0:22:44", "throughput": 5471.48, "total_tokens": 31817376} {"current_steps": 52215, "total_steps": 64460, "loss": 0.1476, "lr": 1.0597128668119606e-06, "epoch": 16.200744647843624, "percentage": 81.0, "elapsed_time": "1:36:55", "remaining_time": "0:22:43", "throughput": 5471.45, "total_tokens": 31820192} {"current_steps": 52220, "total_steps": 64460, "loss": 0.1685, "lr": 1.0588796047178512e-06, "epoch": 16.20229599751784, "percentage": 81.01, "elapsed_time": "1:36:56", "remaining_time": "0:22:43", "throughput": 5471.51, "total_tokens": 31823296} {"current_steps": 52225, "total_steps": 64460, "loss": 0.1483, "lr": 1.0580466315545357e-06, "epoch": 16.203847347192056, "percentage": 81.02, "elapsed_time": "1:36:56", "remaining_time": "0:22:42", "throughput": 5471.56, "total_tokens": 31826816} {"current_steps": 52230, "total_steps": 64460, "loss": 0.1981, "lr": 1.0572139473830828e-06, "epoch": 16.205398696866272, "percentage": 81.03, "elapsed_time": "1:36:57", "remaining_time": "0:22:42", "throughput": 5471.56, "total_tokens": 31829696} {"current_steps": 52235, "total_steps": 64460, "loss": 0.2008, "lr": 1.0563815522645353e-06, "epoch": 16.20695004654049, "percentage": 81.03, "elapsed_time": "1:36:57", "remaining_time": "0:22:41", "throughput": 5471.63, "total_tokens": 31832992} {"current_steps": 52240, "total_steps": 64460, "loss": 0.2022, "lr": 1.055549446259922e-06, "epoch": 16.208501396214707, "percentage": 81.04, "elapsed_time": "1:36:58", "remaining_time": "0:22:41", "throughput": 5471.71, "total_tokens": 31836992} {"current_steps": 52245, "total_steps": 64460, "loss": 0.1264, "lr": 1.0547176294302414e-06, "epoch": 16.210052745888923, "percentage": 81.05, "elapsed_time": "1:36:59", "remaining_time": "0:22:40", "throughput": 5471.82, "total_tokens": 31840672} {"current_steps": 52250, "total_steps": 64460, "loss": 0.1053, "lr": 1.0538861018364777e-06, "epoch": 16.21160409556314, "percentage": 81.06, "elapsed_time": "1:36:59", "remaining_time": "0:22:39", "throughput": 5471.85, "total_tokens": 31843808} {"current_steps": 52255, "total_steps": 64460, "loss": 0.2079, "lr": 1.0530548635395932e-06, "epoch": 16.213155445237355, "percentage": 81.07, "elapsed_time": "1:37:00", "remaining_time": "0:22:39", "throughput": 5471.83, "total_tokens": 31846304} {"current_steps": 52260, "total_steps": 64460, "loss": 0.1781, "lr": 1.0522239146005248e-06, "epoch": 16.214706794911574, "percentage": 81.07, "elapsed_time": "1:37:00", "remaining_time": "0:22:38", "throughput": 5471.85, "total_tokens": 31849600} {"current_steps": 52265, "total_steps": 64460, "loss": 0.1149, "lr": 1.051393255080193e-06, "epoch": 16.21625814458579, "percentage": 81.08, "elapsed_time": "1:37:01", "remaining_time": "0:22:38", "throughput": 5471.87, "total_tokens": 31852512} {"current_steps": 52270, "total_steps": 64460, "loss": 0.1528, "lr": 1.0505628850394934e-06, "epoch": 16.217809494260006, "percentage": 81.09, "elapsed_time": "1:37:01", "remaining_time": "0:22:37", "throughput": 5471.93, "total_tokens": 31855776} {"current_steps": 52275, "total_steps": 64460, "loss": 0.1155, "lr": 1.0497328045393024e-06, "epoch": 16.219360843934222, "percentage": 81.1, "elapsed_time": "1:37:02", "remaining_time": "0:22:37", "throughput": 5471.95, "total_tokens": 31858688} {"current_steps": 52280, "total_steps": 64460, "loss": 0.1461, "lr": 1.048903013640475e-06, "epoch": 16.220912193608438, "percentage": 81.1, "elapsed_time": "1:37:02", "remaining_time": "0:22:36", "throughput": 5472.0, "total_tokens": 31861792} {"current_steps": 52285, "total_steps": 64460, "loss": 0.1547, "lr": 1.048073512403846e-06, "epoch": 16.222463543282657, "percentage": 81.11, "elapsed_time": "1:37:03", "remaining_time": "0:22:36", "throughput": 5472.06, "total_tokens": 31865440} {"current_steps": 52290, "total_steps": 64460, "loss": 0.1758, "lr": 1.047244300890225e-06, "epoch": 16.224014892956873, "percentage": 81.12, "elapsed_time": "1:37:03", "remaining_time": "0:22:35", "throughput": 5472.04, "total_tokens": 31868096} {"current_steps": 52295, "total_steps": 64460, "loss": 0.212, "lr": 1.0464153791604054e-06, "epoch": 16.22556624263109, "percentage": 81.13, "elapsed_time": "1:37:04", "remaining_time": "0:22:34", "throughput": 5472.03, "total_tokens": 31870880} {"current_steps": 52300, "total_steps": 64460, "loss": 0.1487, "lr": 1.0455867472751551e-06, "epoch": 16.227117592305305, "percentage": 81.14, "elapsed_time": "1:37:04", "remaining_time": "0:22:34", "throughput": 5472.02, "total_tokens": 31873632} {"current_steps": 52305, "total_steps": 64460, "loss": 0.1818, "lr": 1.0447584052952248e-06, "epoch": 16.22866894197952, "percentage": 81.14, "elapsed_time": "1:37:05", "remaining_time": "0:22:33", "throughput": 5471.98, "total_tokens": 31876416} {"current_steps": 52310, "total_steps": 64460, "loss": 0.2761, "lr": 1.0439303532813388e-06, "epoch": 16.23022029165374, "percentage": 81.15, "elapsed_time": "1:37:06", "remaining_time": "0:22:33", "throughput": 5472.06, "total_tokens": 31880736} {"current_steps": 52315, "total_steps": 64460, "loss": 0.1665, "lr": 1.043102591294206e-06, "epoch": 16.231771641327956, "percentage": 81.16, "elapsed_time": "1:37:06", "remaining_time": "0:22:32", "throughput": 5472.05, "total_tokens": 31883680} {"current_steps": 52320, "total_steps": 64460, "loss": 0.2724, "lr": 1.042275119394509e-06, "epoch": 16.233322991002172, "percentage": 81.17, "elapsed_time": "1:37:07", "remaining_time": "0:22:32", "throughput": 5472.06, "total_tokens": 31886752} {"current_steps": 52325, "total_steps": 64460, "loss": 0.1883, "lr": 1.0414479376429137e-06, "epoch": 16.234874340676388, "percentage": 81.17, "elapsed_time": "1:37:07", "remaining_time": "0:22:31", "throughput": 5472.08, "total_tokens": 31889696} {"current_steps": 52330, "total_steps": 64460, "loss": 0.1389, "lr": 1.0406210461000587e-06, "epoch": 16.236425690350604, "percentage": 81.18, "elapsed_time": "1:37:08", "remaining_time": "0:22:30", "throughput": 5472.03, "total_tokens": 31892384} {"current_steps": 52335, "total_steps": 64460, "loss": 0.1421, "lr": 1.039794444826568e-06, "epoch": 16.237977040024823, "percentage": 81.19, "elapsed_time": "1:37:08", "remaining_time": "0:22:30", "throughput": 5472.1, "total_tokens": 31895552} {"current_steps": 52340, "total_steps": 64460, "loss": 0.3123, "lr": 1.0389681338830414e-06, "epoch": 16.23952838969904, "percentage": 81.2, "elapsed_time": "1:37:09", "remaining_time": "0:22:29", "throughput": 5472.15, "total_tokens": 31899072} {"current_steps": 52345, "total_steps": 64460, "loss": 0.1553, "lr": 1.0381421133300545e-06, "epoch": 16.241079739373255, "percentage": 81.21, "elapsed_time": "1:37:09", "remaining_time": "0:22:29", "throughput": 5472.2, "total_tokens": 31902272} {"current_steps": 52350, "total_steps": 64460, "loss": 0.2063, "lr": 1.037316383228168e-06, "epoch": 16.24263108904747, "percentage": 81.21, "elapsed_time": "1:37:10", "remaining_time": "0:22:28", "throughput": 5472.18, "total_tokens": 31904832} {"current_steps": 52355, "total_steps": 64460, "loss": 0.1756, "lr": 1.0364909436379139e-06, "epoch": 16.244182438721687, "percentage": 81.22, "elapsed_time": "1:37:10", "remaining_time": "0:22:28", "throughput": 5472.21, "total_tokens": 31907904} {"current_steps": 52360, "total_steps": 64460, "loss": 0.2404, "lr": 1.0356657946198107e-06, "epoch": 16.245733788395903, "percentage": 81.23, "elapsed_time": "1:37:11", "remaining_time": "0:22:27", "throughput": 5472.21, "total_tokens": 31910624} {"current_steps": 52365, "total_steps": 64460, "loss": 0.1732, "lr": 1.0348409362343476e-06, "epoch": 16.247285138070122, "percentage": 81.24, "elapsed_time": "1:37:11", "remaining_time": "0:22:27", "throughput": 5472.27, "total_tokens": 31913664} {"current_steps": 52370, "total_steps": 64460, "loss": 0.251, "lr": 1.0340163685419997e-06, "epoch": 16.248836487744338, "percentage": 81.24, "elapsed_time": "1:37:12", "remaining_time": "0:22:26", "throughput": 5472.2, "total_tokens": 31915776} {"current_steps": 52375, "total_steps": 64460, "loss": 0.2117, "lr": 1.033192091603215e-06, "epoch": 16.250387837418554, "percentage": 81.25, "elapsed_time": "1:37:12", "remaining_time": "0:22:25", "throughput": 5472.13, "total_tokens": 31918208} {"current_steps": 52380, "total_steps": 64460, "loss": 0.1533, "lr": 1.032368105478425e-06, "epoch": 16.25193918709277, "percentage": 81.26, "elapsed_time": "1:37:13", "remaining_time": "0:22:25", "throughput": 5472.18, "total_tokens": 31921344} {"current_steps": 52385, "total_steps": 64460, "loss": 0.1356, "lr": 1.0315444102280358e-06, "epoch": 16.253490536766986, "percentage": 81.27, "elapsed_time": "1:37:13", "remaining_time": "0:22:24", "throughput": 5472.12, "total_tokens": 31923616} {"current_steps": 52390, "total_steps": 64460, "loss": 0.1997, "lr": 1.0307210059124362e-06, "epoch": 16.255041886441205, "percentage": 81.28, "elapsed_time": "1:37:14", "remaining_time": "0:22:24", "throughput": 5472.05, "total_tokens": 31926144} {"current_steps": 52395, "total_steps": 64460, "loss": 0.2837, "lr": 1.0298978925919888e-06, "epoch": 16.25659323611542, "percentage": 81.28, "elapsed_time": "1:37:14", "remaining_time": "0:22:23", "throughput": 5472.05, "total_tokens": 31928704} {"current_steps": 52400, "total_steps": 64460, "loss": 0.2874, "lr": 1.0290750703270392e-06, "epoch": 16.258144585789637, "percentage": 81.29, "elapsed_time": "1:37:15", "remaining_time": "0:22:23", "throughput": 5472.12, "total_tokens": 31932000} {"current_steps": 52405, "total_steps": 64460, "loss": 0.2021, "lr": 1.0282525391779109e-06, "epoch": 16.259695935463853, "percentage": 81.3, "elapsed_time": "1:37:15", "remaining_time": "0:22:22", "throughput": 5472.2, "total_tokens": 31935360} {"current_steps": 52410, "total_steps": 64460, "loss": 0.1228, "lr": 1.0274302992049024e-06, "epoch": 16.26124728513807, "percentage": 81.31, "elapsed_time": "1:37:16", "remaining_time": "0:22:21", "throughput": 5472.17, "total_tokens": 31938336} {"current_steps": 52415, "total_steps": 64460, "loss": 0.1337, "lr": 1.0266083504682966e-06, "epoch": 16.262798634812288, "percentage": 81.31, "elapsed_time": "1:37:16", "remaining_time": "0:22:21", "throughput": 5472.18, "total_tokens": 31940960} {"current_steps": 52420, "total_steps": 64460, "loss": 0.2678, "lr": 1.0257866930283494e-06, "epoch": 16.264349984486504, "percentage": 81.32, "elapsed_time": "1:37:17", "remaining_time": "0:22:20", "throughput": 5472.14, "total_tokens": 31943264} {"current_steps": 52425, "total_steps": 64460, "loss": 0.1399, "lr": 1.0249653269453003e-06, "epoch": 16.26590133416072, "percentage": 81.33, "elapsed_time": "1:37:17", "remaining_time": "0:22:20", "throughput": 5472.2, "total_tokens": 31946560} {"current_steps": 52430, "total_steps": 64460, "loss": 0.1232, "lr": 1.0241442522793632e-06, "epoch": 16.267452683834936, "percentage": 81.34, "elapsed_time": "1:37:18", "remaining_time": "0:22:19", "throughput": 5472.11, "total_tokens": 31948896} {"current_steps": 52435, "total_steps": 64460, "loss": 0.1847, "lr": 1.0233234690907351e-06, "epoch": 16.26900403350915, "percentage": 81.35, "elapsed_time": "1:37:18", "remaining_time": "0:22:19", "throughput": 5472.07, "total_tokens": 31951168} {"current_steps": 52440, "total_steps": 64460, "loss": 0.0791, "lr": 1.0225029774395862e-06, "epoch": 16.27055538318337, "percentage": 81.35, "elapsed_time": "1:37:19", "remaining_time": "0:22:18", "throughput": 5472.1, "total_tokens": 31954368} {"current_steps": 52445, "total_steps": 64460, "loss": 0.1588, "lr": 1.021682777386071e-06, "epoch": 16.272106732857587, "percentage": 81.36, "elapsed_time": "1:37:20", "remaining_time": "0:22:17", "throughput": 5472.12, "total_tokens": 31957536} {"current_steps": 52450, "total_steps": 64460, "loss": 0.2672, "lr": 1.020862868990317e-06, "epoch": 16.273658082531803, "percentage": 81.37, "elapsed_time": "1:37:20", "remaining_time": "0:22:17", "throughput": 5472.16, "total_tokens": 31960416} {"current_steps": 52455, "total_steps": 64460, "loss": 0.2244, "lr": 1.0200432523124348e-06, "epoch": 16.27520943220602, "percentage": 81.38, "elapsed_time": "1:37:21", "remaining_time": "0:22:16", "throughput": 5472.22, "total_tokens": 31963584} {"current_steps": 52460, "total_steps": 64460, "loss": 0.2331, "lr": 1.0192239274125137e-06, "epoch": 16.276760781880235, "percentage": 81.38, "elapsed_time": "1:37:21", "remaining_time": "0:22:16", "throughput": 5472.29, "total_tokens": 31966848} {"current_steps": 52465, "total_steps": 64460, "loss": 0.1753, "lr": 1.0184048943506164e-06, "epoch": 16.278312131554454, "percentage": 81.39, "elapsed_time": "1:37:22", "remaining_time": "0:22:15", "throughput": 5472.24, "total_tokens": 31969280} {"current_steps": 52470, "total_steps": 64460, "loss": 0.1006, "lr": 1.017586153186791e-06, "epoch": 16.27986348122867, "percentage": 81.4, "elapsed_time": "1:37:22", "remaining_time": "0:22:15", "throughput": 5472.3, "total_tokens": 31972448} {"current_steps": 52475, "total_steps": 64460, "loss": 0.1493, "lr": 1.0167677039810581e-06, "epoch": 16.281414830902886, "percentage": 81.41, "elapsed_time": "1:37:23", "remaining_time": "0:22:14", "throughput": 5472.33, "total_tokens": 31975392} {"current_steps": 52480, "total_steps": 64460, "loss": 0.131, "lr": 1.0159495467934222e-06, "epoch": 16.2829661805771, "percentage": 81.41, "elapsed_time": "1:37:23", "remaining_time": "0:22:13", "throughput": 5472.42, "total_tokens": 31978848} {"current_steps": 52485, "total_steps": 64460, "loss": 0.115, "lr": 1.0151316816838614e-06, "epoch": 16.284517530251318, "percentage": 81.42, "elapsed_time": "1:37:24", "remaining_time": "0:22:13", "throughput": 5472.43, "total_tokens": 31981568} {"current_steps": 52490, "total_steps": 64460, "loss": 0.2381, "lr": 1.0143141087123377e-06, "epoch": 16.286068879925534, "percentage": 81.43, "elapsed_time": "1:37:24", "remaining_time": "0:22:12", "throughput": 5472.46, "total_tokens": 31984672} {"current_steps": 52495, "total_steps": 64460, "loss": 0.1306, "lr": 1.0134968279387858e-06, "epoch": 16.287620229599753, "percentage": 81.44, "elapsed_time": "1:37:25", "remaining_time": "0:22:12", "throughput": 5472.52, "total_tokens": 31988256} {"current_steps": 52500, "total_steps": 64460, "loss": 0.1598, "lr": 1.0126798394231252e-06, "epoch": 16.28917157927397, "percentage": 81.45, "elapsed_time": "1:37:25", "remaining_time": "0:22:11", "throughput": 5472.52, "total_tokens": 31991008} {"current_steps": 52505, "total_steps": 64460, "loss": 0.1359, "lr": 1.011863143225248e-06, "epoch": 16.290722928948185, "percentage": 81.45, "elapsed_time": "1:37:26", "remaining_time": "0:22:11", "throughput": 5472.48, "total_tokens": 31993536} {"current_steps": 52510, "total_steps": 64460, "loss": 0.1795, "lr": 1.0110467394050306e-06, "epoch": 16.2922742786224, "percentage": 81.46, "elapsed_time": "1:37:26", "remaining_time": "0:22:10", "throughput": 5472.56, "total_tokens": 31996832} {"current_steps": 52515, "total_steps": 64460, "loss": 0.2629, "lr": 1.0102306280223217e-06, "epoch": 16.293825628296617, "percentage": 81.47, "elapsed_time": "1:37:27", "remaining_time": "0:22:10", "throughput": 5472.49, "total_tokens": 31999392} {"current_steps": 52520, "total_steps": 64460, "loss": 0.1133, "lr": 1.0094148091369539e-06, "epoch": 16.295376977970836, "percentage": 81.48, "elapsed_time": "1:37:27", "remaining_time": "0:22:09", "throughput": 5472.58, "total_tokens": 32003008} {"current_steps": 52525, "total_steps": 64460, "loss": 0.2207, "lr": 1.008599282808737e-06, "epoch": 16.296928327645052, "percentage": 81.48, "elapsed_time": "1:37:28", "remaining_time": "0:22:08", "throughput": 5472.61, "total_tokens": 32006304} {"current_steps": 52530, "total_steps": 64460, "loss": 0.2176, "lr": 1.0077840490974572e-06, "epoch": 16.298479677319268, "percentage": 81.49, "elapsed_time": "1:37:28", "remaining_time": "0:22:08", "throughput": 5472.59, "total_tokens": 32009056} {"current_steps": 52535, "total_steps": 64460, "loss": 0.222, "lr": 1.006969108062883e-06, "epoch": 16.300031026993484, "percentage": 81.5, "elapsed_time": "1:37:29", "remaining_time": "0:22:07", "throughput": 5472.73, "total_tokens": 32013376} {"current_steps": 52540, "total_steps": 64460, "loss": 0.2263, "lr": 1.006154459764756e-06, "epoch": 16.3015823766677, "percentage": 81.51, "elapsed_time": "1:37:30", "remaining_time": "0:22:07", "throughput": 5472.74, "total_tokens": 32016192} {"current_steps": 52545, "total_steps": 64460, "loss": 0.1572, "lr": 1.0053401042628031e-06, "epoch": 16.30313372634192, "percentage": 81.52, "elapsed_time": "1:37:30", "remaining_time": "0:22:06", "throughput": 5472.74, "total_tokens": 32018912} {"current_steps": 52550, "total_steps": 64460, "loss": 0.0901, "lr": 1.0045260416167224e-06, "epoch": 16.304685076016135, "percentage": 81.52, "elapsed_time": "1:37:31", "remaining_time": "0:22:06", "throughput": 5472.72, "total_tokens": 32021760} {"current_steps": 52555, "total_steps": 64460, "loss": 0.1989, "lr": 1.003712271886198e-06, "epoch": 16.30623642569035, "percentage": 81.53, "elapsed_time": "1:37:31", "remaining_time": "0:22:05", "throughput": 5472.69, "total_tokens": 32024544} {"current_steps": 52560, "total_steps": 64460, "loss": 0.1872, "lr": 1.002898795130886e-06, "epoch": 16.307787775364567, "percentage": 81.54, "elapsed_time": "1:37:32", "remaining_time": "0:22:04", "throughput": 5472.69, "total_tokens": 32027520} {"current_steps": 52565, "total_steps": 64460, "loss": 0.0944, "lr": 1.0020856114104261e-06, "epoch": 16.309339125038782, "percentage": 81.55, "elapsed_time": "1:37:32", "remaining_time": "0:22:04", "throughput": 5472.73, "total_tokens": 32030496} {"current_steps": 52570, "total_steps": 64460, "loss": 0.1906, "lr": 1.0012727207844325e-06, "epoch": 16.310890474713002, "percentage": 81.55, "elapsed_time": "1:37:33", "remaining_time": "0:22:03", "throughput": 5472.7, "total_tokens": 32033056} {"current_steps": 52575, "total_steps": 64460, "loss": 0.1692, "lr": 1.0004601233125e-06, "epoch": 16.312441824387218, "percentage": 81.56, "elapsed_time": "1:37:33", "remaining_time": "0:22:03", "throughput": 5472.74, "total_tokens": 32036064} {"current_steps": 52580, "total_steps": 64460, "loss": 0.1671, "lr": 9.996478190542036e-07, "epoch": 16.313993174061434, "percentage": 81.57, "elapsed_time": "1:37:34", "remaining_time": "0:22:02", "throughput": 5472.71, "total_tokens": 32038560} {"current_steps": 52585, "total_steps": 64460, "loss": 0.1558, "lr": 9.988358080690918e-07, "epoch": 16.31554452373565, "percentage": 81.58, "elapsed_time": "1:37:34", "remaining_time": "0:22:02", "throughput": 5472.8, "total_tokens": 32041856} {"current_steps": 52590, "total_steps": 64460, "loss": 0.1229, "lr": 9.980240904166976e-07, "epoch": 16.317095873409865, "percentage": 81.59, "elapsed_time": "1:37:35", "remaining_time": "0:22:01", "throughput": 5472.8, "total_tokens": 32044544} {"current_steps": 52595, "total_steps": 64460, "loss": 0.1422, "lr": 9.972126661565268e-07, "epoch": 16.318647223084085, "percentage": 81.59, "elapsed_time": "1:37:35", "remaining_time": "0:22:01", "throughput": 5472.78, "total_tokens": 32047136} {"current_steps": 52600, "total_steps": 64460, "loss": 0.1707, "lr": 9.964015353480688e-07, "epoch": 16.3201985727583, "percentage": 81.6, "elapsed_time": "1:37:36", "remaining_time": "0:22:00", "throughput": 5472.75, "total_tokens": 32049664} {"current_steps": 52605, "total_steps": 64460, "loss": 0.1738, "lr": 9.955906980507868e-07, "epoch": 16.321749922432517, "percentage": 81.61, "elapsed_time": "1:37:36", "remaining_time": "0:21:59", "throughput": 5472.8, "total_tokens": 32052768} {"current_steps": 52610, "total_steps": 64460, "loss": 0.0935, "lr": 9.94780154324127e-07, "epoch": 16.323301272106733, "percentage": 81.62, "elapsed_time": "1:37:37", "remaining_time": "0:21:59", "throughput": 5472.91, "total_tokens": 32056672} {"current_steps": 52615, "total_steps": 64460, "loss": 0.1749, "lr": 9.939699042275097e-07, "epoch": 16.32485262178095, "percentage": 81.62, "elapsed_time": "1:37:37", "remaining_time": "0:21:58", "throughput": 5472.89, "total_tokens": 32059104} {"current_steps": 52620, "total_steps": 64460, "loss": 0.1723, "lr": 9.931599478203384e-07, "epoch": 16.326403971455164, "percentage": 81.63, "elapsed_time": "1:37:38", "remaining_time": "0:21:58", "throughput": 5472.87, "total_tokens": 32061792} {"current_steps": 52625, "total_steps": 64460, "loss": 0.185, "lr": 9.923502851619893e-07, "epoch": 16.327955321129384, "percentage": 81.64, "elapsed_time": "1:37:38", "remaining_time": "0:21:57", "throughput": 5472.87, "total_tokens": 32064416} {"current_steps": 52630, "total_steps": 64460, "loss": 0.2163, "lr": 9.915409163118235e-07, "epoch": 16.3295066708036, "percentage": 81.65, "elapsed_time": "1:37:39", "remaining_time": "0:21:57", "throughput": 5472.93, "total_tokens": 32067552} {"current_steps": 52635, "total_steps": 64460, "loss": 0.2461, "lr": 9.907318413291745e-07, "epoch": 16.331058020477816, "percentage": 81.66, "elapsed_time": "1:37:39", "remaining_time": "0:21:56", "throughput": 5472.95, "total_tokens": 32070368} {"current_steps": 52640, "total_steps": 64460, "loss": 0.1075, "lr": 9.899230602733583e-07, "epoch": 16.33260937015203, "percentage": 81.66, "elapsed_time": "1:37:40", "remaining_time": "0:21:55", "throughput": 5473.0, "total_tokens": 32073696} {"current_steps": 52645, "total_steps": 64460, "loss": 0.1317, "lr": 9.891145732036695e-07, "epoch": 16.334160719826247, "percentage": 81.67, "elapsed_time": "1:37:40", "remaining_time": "0:21:55", "throughput": 5473.07, "total_tokens": 32076992} {"current_steps": 52650, "total_steps": 64460, "loss": 0.1082, "lr": 9.883063801793774e-07, "epoch": 16.335712069500467, "percentage": 81.68, "elapsed_time": "1:37:41", "remaining_time": "0:21:54", "throughput": 5473.06, "total_tokens": 32079744} {"current_steps": 52655, "total_steps": 64460, "loss": 0.2592, "lr": 9.874984812597344e-07, "epoch": 16.337263419174683, "percentage": 81.69, "elapsed_time": "1:37:41", "remaining_time": "0:21:54", "throughput": 5473.01, "total_tokens": 32082112} {"current_steps": 52660, "total_steps": 64460, "loss": 0.1545, "lr": 9.866908765039661e-07, "epoch": 16.3388147688489, "percentage": 81.69, "elapsed_time": "1:37:42", "remaining_time": "0:21:53", "throughput": 5472.97, "total_tokens": 32084736} {"current_steps": 52665, "total_steps": 64460, "loss": 0.2054, "lr": 9.858835659712829e-07, "epoch": 16.340366118523114, "percentage": 81.7, "elapsed_time": "1:37:42", "remaining_time": "0:21:53", "throughput": 5472.97, "total_tokens": 32087584} {"current_steps": 52670, "total_steps": 64460, "loss": 0.2701, "lr": 9.850765497208674e-07, "epoch": 16.34191746819733, "percentage": 81.71, "elapsed_time": "1:37:43", "remaining_time": "0:21:52", "throughput": 5473.02, "total_tokens": 32090848} {"current_steps": 52675, "total_steps": 64460, "loss": 0.2037, "lr": 9.842698278118857e-07, "epoch": 16.34346881787155, "percentage": 81.72, "elapsed_time": "1:37:43", "remaining_time": "0:21:51", "throughput": 5473.07, "total_tokens": 32093952} {"current_steps": 52680, "total_steps": 64460, "loss": 0.0449, "lr": 9.834634003034777e-07, "epoch": 16.345020167545766, "percentage": 81.73, "elapsed_time": "1:37:44", "remaining_time": "0:21:51", "throughput": 5473.19, "total_tokens": 32098560} {"current_steps": 52685, "total_steps": 64460, "loss": 0.2202, "lr": 9.826572672547668e-07, "epoch": 16.34657151721998, "percentage": 81.73, "elapsed_time": "1:37:45", "remaining_time": "0:21:50", "throughput": 5473.09, "total_tokens": 32100800} {"current_steps": 52690, "total_steps": 64460, "loss": 0.1908, "lr": 9.818514287248494e-07, "epoch": 16.348122866894197, "percentage": 81.74, "elapsed_time": "1:37:45", "remaining_time": "0:21:50", "throughput": 5473.12, "total_tokens": 32103840} {"current_steps": 52695, "total_steps": 64460, "loss": 0.1977, "lr": 9.810458847728039e-07, "epoch": 16.349674216568413, "percentage": 81.75, "elapsed_time": "1:37:46", "remaining_time": "0:21:49", "throughput": 5473.1, "total_tokens": 32106432} {"current_steps": 52700, "total_steps": 64460, "loss": 0.1357, "lr": 9.802406354576882e-07, "epoch": 16.351225566242633, "percentage": 81.76, "elapsed_time": "1:37:46", "remaining_time": "0:21:49", "throughput": 5473.07, "total_tokens": 32108960} {"current_steps": 52705, "total_steps": 64460, "loss": 0.1378, "lr": 9.794356808385335e-07, "epoch": 16.35277691591685, "percentage": 81.76, "elapsed_time": "1:37:47", "remaining_time": "0:21:48", "throughput": 5473.09, "total_tokens": 32111584} {"current_steps": 52710, "total_steps": 64460, "loss": 0.22, "lr": 9.786310209743555e-07, "epoch": 16.354328265591064, "percentage": 81.77, "elapsed_time": "1:37:47", "remaining_time": "0:21:48", "throughput": 5473.1, "total_tokens": 32114240} {"current_steps": 52715, "total_steps": 64460, "loss": 0.2076, "lr": 9.778266559241422e-07, "epoch": 16.35587961526528, "percentage": 81.78, "elapsed_time": "1:37:48", "remaining_time": "0:21:47", "throughput": 5473.07, "total_tokens": 32117024} {"current_steps": 52720, "total_steps": 64460, "loss": 0.143, "lr": 9.770225857468662e-07, "epoch": 16.357430964939496, "percentage": 81.79, "elapsed_time": "1:37:48", "remaining_time": "0:21:46", "throughput": 5473.06, "total_tokens": 32119616} {"current_steps": 52725, "total_steps": 64460, "loss": 0.2284, "lr": 9.76218810501473e-07, "epoch": 16.358982314613716, "percentage": 81.79, "elapsed_time": "1:37:49", "remaining_time": "0:21:46", "throughput": 5473.08, "total_tokens": 32122464} {"current_steps": 52730, "total_steps": 64460, "loss": 0.2304, "lr": 9.754153302468906e-07, "epoch": 16.36053366428793, "percentage": 81.8, "elapsed_time": "1:37:49", "remaining_time": "0:21:45", "throughput": 5473.04, "total_tokens": 32124992} {"current_steps": 52735, "total_steps": 64460, "loss": 0.2231, "lr": 9.74612145042021e-07, "epoch": 16.362085013962147, "percentage": 81.81, "elapsed_time": "1:37:50", "remaining_time": "0:21:45", "throughput": 5472.93, "total_tokens": 32127136} {"current_steps": 52740, "total_steps": 64460, "loss": 0.1428, "lr": 9.738092549457506e-07, "epoch": 16.363636363636363, "percentage": 81.82, "elapsed_time": "1:37:50", "remaining_time": "0:21:44", "throughput": 5472.83, "total_tokens": 32129408} {"current_steps": 52745, "total_steps": 64460, "loss": 0.1961, "lr": 9.730066600169375e-07, "epoch": 16.36518771331058, "percentage": 81.83, "elapsed_time": "1:37:51", "remaining_time": "0:21:44", "throughput": 5472.78, "total_tokens": 32132096} {"current_steps": 52750, "total_steps": 64460, "loss": 0.1107, "lr": 9.722043603144243e-07, "epoch": 16.366739062984795, "percentage": 81.83, "elapsed_time": "1:37:52", "remaining_time": "0:21:43", "throughput": 5472.92, "total_tokens": 32138432} {"current_steps": 52755, "total_steps": 64460, "loss": 0.1242, "lr": 9.71402355897027e-07, "epoch": 16.368290412659015, "percentage": 81.84, "elapsed_time": "1:37:52", "remaining_time": "0:21:43", "throughput": 5472.96, "total_tokens": 32141632} {"current_steps": 52760, "total_steps": 64460, "loss": 0.1498, "lr": 9.706006468235425e-07, "epoch": 16.36984176233323, "percentage": 81.85, "elapsed_time": "1:37:53", "remaining_time": "0:21:42", "throughput": 5472.97, "total_tokens": 32144320} {"current_steps": 52765, "total_steps": 64460, "loss": 0.1196, "lr": 9.697992331527468e-07, "epoch": 16.371393112007446, "percentage": 81.86, "elapsed_time": "1:37:53", "remaining_time": "0:21:41", "throughput": 5473.0, "total_tokens": 32147264} {"current_steps": 52770, "total_steps": 64460, "loss": 0.1363, "lr": 9.689981149433909e-07, "epoch": 16.372944461681662, "percentage": 81.86, "elapsed_time": "1:37:54", "remaining_time": "0:21:41", "throughput": 5473.01, "total_tokens": 32150368} {"current_steps": 52775, "total_steps": 64460, "loss": 0.1229, "lr": 9.681972922542082e-07, "epoch": 16.374495811355878, "percentage": 81.87, "elapsed_time": "1:37:54", "remaining_time": "0:21:40", "throughput": 5473.03, "total_tokens": 32153216} {"current_steps": 52780, "total_steps": 64460, "loss": 0.15, "lr": 9.67396765143907e-07, "epoch": 16.376047161030097, "percentage": 81.88, "elapsed_time": "1:37:55", "remaining_time": "0:21:40", "throughput": 5473.04, "total_tokens": 32155968} {"current_steps": 52785, "total_steps": 64460, "loss": 0.1461, "lr": 9.665965336711768e-07, "epoch": 16.377598510704313, "percentage": 81.89, "elapsed_time": "1:37:55", "remaining_time": "0:21:39", "throughput": 5473.12, "total_tokens": 32159392} {"current_steps": 52790, "total_steps": 64460, "loss": 0.1655, "lr": 9.657965978946825e-07, "epoch": 16.37914986037853, "percentage": 81.9, "elapsed_time": "1:37:56", "remaining_time": "0:21:39", "throughput": 5473.16, "total_tokens": 32162560} {"current_steps": 52795, "total_steps": 64460, "loss": 0.1518, "lr": 9.649969578730711e-07, "epoch": 16.380701210052745, "percentage": 81.9, "elapsed_time": "1:37:56", "remaining_time": "0:21:38", "throughput": 5473.15, "total_tokens": 32165120} {"current_steps": 52800, "total_steps": 64460, "loss": 0.1365, "lr": 9.641976136649627e-07, "epoch": 16.38225255972696, "percentage": 81.91, "elapsed_time": "1:37:57", "remaining_time": "0:21:37", "throughput": 5473.16, "total_tokens": 32167904} {"current_steps": 52805, "total_steps": 64460, "loss": 0.1283, "lr": 9.63398565328962e-07, "epoch": 16.38380390940118, "percentage": 81.92, "elapsed_time": "1:37:57", "remaining_time": "0:21:37", "throughput": 5473.17, "total_tokens": 32170976} {"current_steps": 52810, "total_steps": 64460, "loss": 0.1552, "lr": 9.625998129236446e-07, "epoch": 16.385355259075396, "percentage": 81.93, "elapsed_time": "1:37:58", "remaining_time": "0:21:36", "throughput": 5473.18, "total_tokens": 32173824} {"current_steps": 52815, "total_steps": 64460, "loss": 0.3604, "lr": 9.618013565075719e-07, "epoch": 16.386906608749612, "percentage": 81.93, "elapsed_time": "1:37:58", "remaining_time": "0:21:36", "throughput": 5473.21, "total_tokens": 32176672} {"current_steps": 52820, "total_steps": 64460, "loss": 0.2003, "lr": 9.6100319613928e-07, "epoch": 16.388457958423828, "percentage": 81.94, "elapsed_time": "1:37:59", "remaining_time": "0:21:35", "throughput": 5473.19, "total_tokens": 32179232} {"current_steps": 52825, "total_steps": 64460, "loss": 0.1939, "lr": 9.602053318772819e-07, "epoch": 16.390009308098044, "percentage": 81.95, "elapsed_time": "1:37:59", "remaining_time": "0:21:35", "throughput": 5473.26, "total_tokens": 32182432} {"current_steps": 52830, "total_steps": 64460, "loss": 0.1852, "lr": 9.59407763780072e-07, "epoch": 16.391560657772263, "percentage": 81.96, "elapsed_time": "1:38:00", "remaining_time": "0:21:34", "throughput": 5473.29, "total_tokens": 32185472} {"current_steps": 52835, "total_steps": 64460, "loss": 0.2482, "lr": 9.586104919061195e-07, "epoch": 16.39311200744648, "percentage": 81.97, "elapsed_time": "1:38:00", "remaining_time": "0:21:33", "throughput": 5473.39, "total_tokens": 32189024} {"current_steps": 52840, "total_steps": 64460, "loss": 0.1967, "lr": 9.578135163138768e-07, "epoch": 16.394663357120695, "percentage": 81.97, "elapsed_time": "1:38:01", "remaining_time": "0:21:33", "throughput": 5473.37, "total_tokens": 32191584} {"current_steps": 52845, "total_steps": 64460, "loss": 0.1458, "lr": 9.57016837061769e-07, "epoch": 16.39621470679491, "percentage": 81.98, "elapsed_time": "1:38:02", "remaining_time": "0:21:32", "throughput": 5473.45, "total_tokens": 32194944} {"current_steps": 52850, "total_steps": 64460, "loss": 0.1375, "lr": 9.562204542082027e-07, "epoch": 16.397766056469127, "percentage": 81.99, "elapsed_time": "1:38:02", "remaining_time": "0:21:32", "throughput": 5473.56, "total_tokens": 32198720} {"current_steps": 52855, "total_steps": 64460, "loss": 0.1773, "lr": 9.554243678115626e-07, "epoch": 16.399317406143346, "percentage": 82.0, "elapsed_time": "1:38:03", "remaining_time": "0:21:31", "throughput": 5473.62, "total_tokens": 32202080} {"current_steps": 52860, "total_steps": 64460, "loss": 0.1731, "lr": 9.546285779302128e-07, "epoch": 16.400868755817562, "percentage": 82.0, "elapsed_time": "1:38:03", "remaining_time": "0:21:31", "throughput": 5473.65, "total_tokens": 32204864} {"current_steps": 52865, "total_steps": 64460, "loss": 0.1825, "lr": 9.53833084622491e-07, "epoch": 16.402420105491778, "percentage": 82.01, "elapsed_time": "1:38:04", "remaining_time": "0:21:30", "throughput": 5473.69, "total_tokens": 32208000} {"current_steps": 52870, "total_steps": 64460, "loss": 0.2248, "lr": 9.530378879467194e-07, "epoch": 16.403971455165994, "percentage": 82.02, "elapsed_time": "1:38:04", "remaining_time": "0:21:30", "throughput": 5473.73, "total_tokens": 32210816} {"current_steps": 52875, "total_steps": 64460, "loss": 0.1823, "lr": 9.522429879611922e-07, "epoch": 16.40552280484021, "percentage": 82.03, "elapsed_time": "1:38:05", "remaining_time": "0:21:29", "throughput": 5473.79, "total_tokens": 32214272} {"current_steps": 52880, "total_steps": 64460, "loss": 0.2179, "lr": 9.514483847241885e-07, "epoch": 16.407074154514426, "percentage": 82.04, "elapsed_time": "1:38:05", "remaining_time": "0:21:28", "throughput": 5473.74, "total_tokens": 32216576} {"current_steps": 52885, "total_steps": 64460, "loss": 0.1465, "lr": 9.506540782939583e-07, "epoch": 16.408625504188645, "percentage": 82.04, "elapsed_time": "1:38:06", "remaining_time": "0:21:28", "throughput": 5473.75, "total_tokens": 32219712} {"current_steps": 52890, "total_steps": 64460, "loss": 0.1768, "lr": 9.498600687287368e-07, "epoch": 16.41017685386286, "percentage": 82.05, "elapsed_time": "1:38:06", "remaining_time": "0:21:27", "throughput": 5473.71, "total_tokens": 32222176} {"current_steps": 52895, "total_steps": 64460, "loss": 0.2077, "lr": 9.490663560867324e-07, "epoch": 16.411728203537077, "percentage": 82.06, "elapsed_time": "1:38:07", "remaining_time": "0:21:27", "throughput": 5473.77, "total_tokens": 32225504} {"current_steps": 52900, "total_steps": 64460, "loss": 0.1938, "lr": 9.482729404261343e-07, "epoch": 16.413279553211293, "percentage": 82.07, "elapsed_time": "1:38:07", "remaining_time": "0:21:26", "throughput": 5473.77, "total_tokens": 32228256} {"current_steps": 52905, "total_steps": 64460, "loss": 0.1795, "lr": 9.474798218051101e-07, "epoch": 16.41483090288551, "percentage": 82.07, "elapsed_time": "1:38:08", "remaining_time": "0:21:26", "throughput": 5473.77, "total_tokens": 32231104} {"current_steps": 52910, "total_steps": 64460, "loss": 0.1976, "lr": 9.466870002818029e-07, "epoch": 16.41638225255973, "percentage": 82.08, "elapsed_time": "1:38:08", "remaining_time": "0:21:25", "throughput": 5473.86, "total_tokens": 32234816} {"current_steps": 52915, "total_steps": 64460, "loss": 0.1504, "lr": 9.458944759143385e-07, "epoch": 16.417933602233944, "percentage": 82.09, "elapsed_time": "1:38:09", "remaining_time": "0:21:24", "throughput": 5473.9, "total_tokens": 32237856} {"current_steps": 52920, "total_steps": 64460, "loss": 0.2303, "lr": 9.451022487608152e-07, "epoch": 16.41948495190816, "percentage": 82.1, "elapsed_time": "1:38:09", "remaining_time": "0:21:24", "throughput": 5473.92, "total_tokens": 32240608} {"current_steps": 52925, "total_steps": 64460, "loss": 0.2162, "lr": 9.443103188793157e-07, "epoch": 16.421036301582376, "percentage": 82.11, "elapsed_time": "1:38:10", "remaining_time": "0:21:23", "throughput": 5473.99, "total_tokens": 32243936} {"current_steps": 52930, "total_steps": 64460, "loss": 0.2187, "lr": 9.43518686327895e-07, "epoch": 16.422587651256592, "percentage": 82.11, "elapsed_time": "1:38:10", "remaining_time": "0:21:23", "throughput": 5474.01, "total_tokens": 32246944} {"current_steps": 52935, "total_steps": 64460, "loss": 0.1248, "lr": 9.427273511645918e-07, "epoch": 16.42413900093081, "percentage": 82.12, "elapsed_time": "1:38:11", "remaining_time": "0:21:22", "throughput": 5474.01, "total_tokens": 32249600} {"current_steps": 52940, "total_steps": 64460, "loss": 0.2328, "lr": 9.41936313447418e-07, "epoch": 16.425690350605027, "percentage": 82.13, "elapsed_time": "1:38:11", "remaining_time": "0:21:22", "throughput": 5473.96, "total_tokens": 32251936} {"current_steps": 52945, "total_steps": 64460, "loss": 0.1556, "lr": 9.411455732343683e-07, "epoch": 16.427241700279243, "percentage": 82.14, "elapsed_time": "1:38:12", "remaining_time": "0:21:21", "throughput": 5474.0, "total_tokens": 32254944} {"current_steps": 52950, "total_steps": 64460, "loss": 0.1347, "lr": 9.403551305834108e-07, "epoch": 16.42879304995346, "percentage": 82.14, "elapsed_time": "1:38:12", "remaining_time": "0:21:20", "throughput": 5474.06, "total_tokens": 32258144} {"current_steps": 52955, "total_steps": 64460, "loss": 0.1443, "lr": 9.395649855524968e-07, "epoch": 16.430344399627675, "percentage": 82.15, "elapsed_time": "1:38:13", "remaining_time": "0:21:20", "throughput": 5474.13, "total_tokens": 32261536} {"current_steps": 52960, "total_steps": 64460, "loss": 0.2496, "lr": 9.387751381995508e-07, "epoch": 16.431895749301894, "percentage": 82.16, "elapsed_time": "1:38:13", "remaining_time": "0:21:19", "throughput": 5474.14, "total_tokens": 32264160} {"current_steps": 52965, "total_steps": 64460, "loss": 0.1593, "lr": 9.37985588582479e-07, "epoch": 16.43344709897611, "percentage": 82.17, "elapsed_time": "1:38:14", "remaining_time": "0:21:19", "throughput": 5474.2, "total_tokens": 32267488} {"current_steps": 52970, "total_steps": 64460, "loss": 0.1598, "lr": 9.371963367591669e-07, "epoch": 16.434998448650326, "percentage": 82.17, "elapsed_time": "1:38:14", "remaining_time": "0:21:18", "throughput": 5474.24, "total_tokens": 32270368} {"current_steps": 52975, "total_steps": 64460, "loss": 0.1452, "lr": 9.364073827874726e-07, "epoch": 16.436549798324542, "percentage": 82.18, "elapsed_time": "1:38:15", "remaining_time": "0:21:18", "throughput": 5474.25, "total_tokens": 32273312} {"current_steps": 52980, "total_steps": 64460, "loss": 0.1784, "lr": 9.356187267252381e-07, "epoch": 16.438101147998758, "percentage": 82.19, "elapsed_time": "1:38:15", "remaining_time": "0:21:17", "throughput": 5474.19, "total_tokens": 32275520} {"current_steps": 52985, "total_steps": 64460, "loss": 0.2121, "lr": 9.348303686302795e-07, "epoch": 16.439652497672977, "percentage": 82.2, "elapsed_time": "1:38:16", "remaining_time": "0:21:17", "throughput": 5474.29, "total_tokens": 32279488} {"current_steps": 52990, "total_steps": 64460, "loss": 0.2639, "lr": 9.34042308560395e-07, "epoch": 16.441203847347193, "percentage": 82.21, "elapsed_time": "1:38:17", "remaining_time": "0:21:16", "throughput": 5474.26, "total_tokens": 32281952} {"current_steps": 52995, "total_steps": 64460, "loss": 0.1257, "lr": 9.332545465733562e-07, "epoch": 16.44275519702141, "percentage": 82.21, "elapsed_time": "1:38:17", "remaining_time": "0:21:15", "throughput": 5474.15, "total_tokens": 32284096} {"current_steps": 53000, "total_steps": 64460, "loss": 0.2363, "lr": 9.324670827269177e-07, "epoch": 16.444306546695625, "percentage": 82.22, "elapsed_time": "1:38:18", "remaining_time": "0:21:15", "throughput": 5474.2, "total_tokens": 32287808} {"current_steps": 53005, "total_steps": 64460, "loss": 0.1879, "lr": 9.316799170788083e-07, "epoch": 16.44585789636984, "percentage": 82.23, "elapsed_time": "1:38:18", "remaining_time": "0:21:14", "throughput": 5474.13, "total_tokens": 32290048} {"current_steps": 53010, "total_steps": 64460, "loss": 0.097, "lr": 9.308930496867374e-07, "epoch": 16.447409246044057, "percentage": 82.24, "elapsed_time": "1:38:19", "remaining_time": "0:21:14", "throughput": 5474.09, "total_tokens": 32292800} {"current_steps": 53015, "total_steps": 64460, "loss": 0.177, "lr": 9.301064806083904e-07, "epoch": 16.448960595718276, "percentage": 82.24, "elapsed_time": "1:38:19", "remaining_time": "0:21:13", "throughput": 5473.98, "total_tokens": 32295008} {"current_steps": 53020, "total_steps": 64460, "loss": 0.1582, "lr": 9.293202099014331e-07, "epoch": 16.450511945392492, "percentage": 82.25, "elapsed_time": "1:38:20", "remaining_time": "0:21:13", "throughput": 5474.0, "total_tokens": 32298144} {"current_steps": 53025, "total_steps": 64460, "loss": 0.1867, "lr": 9.285342376235101e-07, "epoch": 16.452063295066708, "percentage": 82.26, "elapsed_time": "1:38:20", "remaining_time": "0:21:12", "throughput": 5474.03, "total_tokens": 32301184} {"current_steps": 53030, "total_steps": 64460, "loss": 0.1818, "lr": 9.277485638322392e-07, "epoch": 16.453614644740924, "percentage": 82.27, "elapsed_time": "1:38:21", "remaining_time": "0:21:11", "throughput": 5474.07, "total_tokens": 32304096} {"current_steps": 53035, "total_steps": 64460, "loss": 0.2165, "lr": 9.269631885852226e-07, "epoch": 16.45516599441514, "percentage": 82.28, "elapsed_time": "1:38:21", "remaining_time": "0:21:11", "throughput": 5474.06, "total_tokens": 32306560} {"current_steps": 53040, "total_steps": 64460, "loss": 0.0813, "lr": 9.261781119400349e-07, "epoch": 16.45671734408936, "percentage": 82.28, "elapsed_time": "1:38:22", "remaining_time": "0:21:10", "throughput": 5474.1, "total_tokens": 32309408} {"current_steps": 53045, "total_steps": 64460, "loss": 0.1706, "lr": 9.253933339542342e-07, "epoch": 16.458268693763575, "percentage": 82.29, "elapsed_time": "1:38:22", "remaining_time": "0:21:10", "throughput": 5474.1, "total_tokens": 32312032} {"current_steps": 53050, "total_steps": 64460, "loss": 0.1089, "lr": 9.246088546853516e-07, "epoch": 16.45982004343779, "percentage": 82.3, "elapsed_time": "1:38:23", "remaining_time": "0:21:09", "throughput": 5474.15, "total_tokens": 32315200} {"current_steps": 53055, "total_steps": 64460, "loss": 0.2378, "lr": 9.238246741909007e-07, "epoch": 16.461371393112007, "percentage": 82.31, "elapsed_time": "1:38:23", "remaining_time": "0:21:09", "throughput": 5474.15, "total_tokens": 32317856} {"current_steps": 53060, "total_steps": 64460, "loss": 0.2326, "lr": 9.230407925283697e-07, "epoch": 16.462922742786223, "percentage": 82.31, "elapsed_time": "1:38:24", "remaining_time": "0:21:08", "throughput": 5474.15, "total_tokens": 32320640} {"current_steps": 53065, "total_steps": 64460, "loss": 0.1294, "lr": 9.222572097552273e-07, "epoch": 16.464474092460442, "percentage": 82.32, "elapsed_time": "1:38:24", "remaining_time": "0:21:07", "throughput": 5474.19, "total_tokens": 32323584} {"current_steps": 53070, "total_steps": 64460, "loss": 0.1984, "lr": 9.214739259289185e-07, "epoch": 16.466025442134658, "percentage": 82.33, "elapsed_time": "1:38:25", "remaining_time": "0:21:07", "throughput": 5474.25, "total_tokens": 32326816} {"current_steps": 53075, "total_steps": 64460, "loss": 0.2623, "lr": 9.206909411068693e-07, "epoch": 16.467576791808874, "percentage": 82.34, "elapsed_time": "1:38:25", "remaining_time": "0:21:06", "throughput": 5474.27, "total_tokens": 32329568} {"current_steps": 53080, "total_steps": 64460, "loss": 0.1463, "lr": 9.199082553464789e-07, "epoch": 16.46912814148309, "percentage": 82.35, "elapsed_time": "1:38:26", "remaining_time": "0:21:06", "throughput": 5474.38, "total_tokens": 32333024} {"current_steps": 53085, "total_steps": 64460, "loss": 0.1584, "lr": 9.191258687051291e-07, "epoch": 16.470679491157306, "percentage": 82.35, "elapsed_time": "1:38:26", "remaining_time": "0:21:05", "throughput": 5474.41, "total_tokens": 32336032} {"current_steps": 53090, "total_steps": 64460, "loss": 0.2034, "lr": 9.183437812401786e-07, "epoch": 16.472230840831525, "percentage": 82.36, "elapsed_time": "1:38:27", "remaining_time": "0:21:05", "throughput": 5474.38, "total_tokens": 32338528} {"current_steps": 53095, "total_steps": 64460, "loss": 0.1649, "lr": 9.175619930089625e-07, "epoch": 16.47378219050574, "percentage": 82.37, "elapsed_time": "1:38:27", "remaining_time": "0:21:04", "throughput": 5474.37, "total_tokens": 32341024} {"current_steps": 53100, "total_steps": 64460, "loss": 0.135, "lr": 9.167805040687961e-07, "epoch": 16.475333540179957, "percentage": 82.38, "elapsed_time": "1:38:28", "remaining_time": "0:21:03", "throughput": 5474.48, "total_tokens": 32344800} {"current_steps": 53105, "total_steps": 64460, "loss": 0.1771, "lr": 9.159993144769702e-07, "epoch": 16.476884889854173, "percentage": 82.38, "elapsed_time": "1:38:28", "remaining_time": "0:21:03", "throughput": 5474.45, "total_tokens": 32347168} {"current_steps": 53110, "total_steps": 64460, "loss": 0.1636, "lr": 9.15218424290758e-07, "epoch": 16.47843623952839, "percentage": 82.39, "elapsed_time": "1:38:29", "remaining_time": "0:21:02", "throughput": 5474.62, "total_tokens": 32352032} {"current_steps": 53115, "total_steps": 64460, "loss": 0.1928, "lr": 9.144378335674048e-07, "epoch": 16.479987589202608, "percentage": 82.4, "elapsed_time": "1:38:29", "remaining_time": "0:21:02", "throughput": 5474.58, "total_tokens": 32354368} {"current_steps": 53120, "total_steps": 64460, "loss": 0.1641, "lr": 9.136575423641403e-07, "epoch": 16.481538938876824, "percentage": 82.41, "elapsed_time": "1:38:30", "remaining_time": "0:21:01", "throughput": 5474.67, "total_tokens": 32358272} {"current_steps": 53125, "total_steps": 64460, "loss": 0.146, "lr": 9.12877550738166e-07, "epoch": 16.48309028855104, "percentage": 82.42, "elapsed_time": "1:38:31", "remaining_time": "0:21:01", "throughput": 5474.71, "total_tokens": 32361120} {"current_steps": 53130, "total_steps": 64460, "loss": 0.2238, "lr": 9.120978587466673e-07, "epoch": 16.484641638225256, "percentage": 82.42, "elapsed_time": "1:38:31", "remaining_time": "0:21:00", "throughput": 5474.74, "total_tokens": 32363808} {"current_steps": 53135, "total_steps": 64460, "loss": 0.1396, "lr": 9.113184664468017e-07, "epoch": 16.48619298789947, "percentage": 82.43, "elapsed_time": "1:38:31", "remaining_time": "0:21:00", "throughput": 5474.76, "total_tokens": 32366592} {"current_steps": 53140, "total_steps": 64460, "loss": 0.2142, "lr": 9.105393738957119e-07, "epoch": 16.487744337573687, "percentage": 82.44, "elapsed_time": "1:38:32", "remaining_time": "0:20:59", "throughput": 5474.78, "total_tokens": 32369792} {"current_steps": 53145, "total_steps": 64460, "loss": 0.0932, "lr": 9.097605811505106e-07, "epoch": 16.489295687247907, "percentage": 82.45, "elapsed_time": "1:38:33", "remaining_time": "0:20:58", "throughput": 5474.8, "total_tokens": 32372512} {"current_steps": 53150, "total_steps": 64460, "loss": 0.0981, "lr": 9.089820882682949e-07, "epoch": 16.490847036922123, "percentage": 82.45, "elapsed_time": "1:38:33", "remaining_time": "0:20:58", "throughput": 5474.97, "total_tokens": 32377216} {"current_steps": 53155, "total_steps": 64460, "loss": 0.2366, "lr": 9.082038953061378e-07, "epoch": 16.49239838659634, "percentage": 82.46, "elapsed_time": "1:38:34", "remaining_time": "0:20:57", "throughput": 5474.97, "total_tokens": 32380096} {"current_steps": 53160, "total_steps": 64460, "loss": 0.2009, "lr": 9.074260023210879e-07, "epoch": 16.493949736270554, "percentage": 82.47, "elapsed_time": "1:38:34", "remaining_time": "0:20:57", "throughput": 5474.91, "total_tokens": 32382208} {"current_steps": 53165, "total_steps": 64460, "loss": 0.1714, "lr": 9.066484093701772e-07, "epoch": 16.49550108594477, "percentage": 82.48, "elapsed_time": "1:38:35", "remaining_time": "0:20:56", "throughput": 5475.02, "total_tokens": 32385792} {"current_steps": 53170, "total_steps": 64460, "loss": 0.1814, "lr": 9.05871116510409e-07, "epoch": 16.49705243561899, "percentage": 82.49, "elapsed_time": "1:38:35", "remaining_time": "0:20:56", "throughput": 5475.03, "total_tokens": 32388768} {"current_steps": 53175, "total_steps": 64460, "loss": 0.1761, "lr": 9.050941237987709e-07, "epoch": 16.498603785293206, "percentage": 82.49, "elapsed_time": "1:38:36", "remaining_time": "0:20:55", "throughput": 5475.09, "total_tokens": 32392128} {"current_steps": 53180, "total_steps": 64460, "loss": 0.1758, "lr": 9.043174312922237e-07, "epoch": 16.50015513496742, "percentage": 82.5, "elapsed_time": "1:38:36", "remaining_time": "0:20:55", "throughput": 5475.21, "total_tokens": 32395872} {"current_steps": 53185, "total_steps": 64460, "loss": 0.1741, "lr": 9.035410390477095e-07, "epoch": 16.501706484641637, "percentage": 82.51, "elapsed_time": "1:38:37", "remaining_time": "0:20:54", "throughput": 5475.29, "total_tokens": 32399040} {"current_steps": 53190, "total_steps": 64460, "loss": 0.2453, "lr": 9.027649471221456e-07, "epoch": 16.503257834315853, "percentage": 82.52, "elapsed_time": "1:38:37", "remaining_time": "0:20:53", "throughput": 5475.37, "total_tokens": 32402432} {"current_steps": 53195, "total_steps": 64460, "loss": 0.1109, "lr": 9.019891555724308e-07, "epoch": 16.504809183990073, "percentage": 82.52, "elapsed_time": "1:38:38", "remaining_time": "0:20:53", "throughput": 5475.38, "total_tokens": 32405056} {"current_steps": 53200, "total_steps": 64460, "loss": 0.1076, "lr": 9.012136644554376e-07, "epoch": 16.50636053366429, "percentage": 82.53, "elapsed_time": "1:38:38", "remaining_time": "0:20:52", "throughput": 5475.42, "total_tokens": 32408032} {"current_steps": 53205, "total_steps": 64460, "loss": 0.1329, "lr": 9.004384738280192e-07, "epoch": 16.507911883338505, "percentage": 82.54, "elapsed_time": "1:38:39", "remaining_time": "0:20:52", "throughput": 5475.41, "total_tokens": 32410560} {"current_steps": 53210, "total_steps": 64460, "loss": 0.1755, "lr": 8.996635837470086e-07, "epoch": 16.50946323301272, "percentage": 82.55, "elapsed_time": "1:38:40", "remaining_time": "0:20:51", "throughput": 5475.57, "total_tokens": 32415520} {"current_steps": 53215, "total_steps": 64460, "loss": 0.1652, "lr": 8.988889942692109e-07, "epoch": 16.511014582686936, "percentage": 82.56, "elapsed_time": "1:38:40", "remaining_time": "0:20:51", "throughput": 5475.58, "total_tokens": 32418208} {"current_steps": 53220, "total_steps": 64460, "loss": 0.1217, "lr": 8.981147054514155e-07, "epoch": 16.512565932361156, "percentage": 82.56, "elapsed_time": "1:38:41", "remaining_time": "0:20:50", "throughput": 5475.59, "total_tokens": 32421024} {"current_steps": 53225, "total_steps": 64460, "loss": 0.2, "lr": 8.973407173503846e-07, "epoch": 16.51411728203537, "percentage": 82.57, "elapsed_time": "1:38:41", "remaining_time": "0:20:49", "throughput": 5475.6, "total_tokens": 32423680} {"current_steps": 53230, "total_steps": 64460, "loss": 0.1584, "lr": 8.96567030022863e-07, "epoch": 16.515668631709588, "percentage": 82.58, "elapsed_time": "1:38:42", "remaining_time": "0:20:49", "throughput": 5475.53, "total_tokens": 32426112} {"current_steps": 53235, "total_steps": 64460, "loss": 0.1745, "lr": 8.957936435255693e-07, "epoch": 16.517219981383803, "percentage": 82.59, "elapsed_time": "1:38:42", "remaining_time": "0:20:48", "throughput": 5475.59, "total_tokens": 32429952} {"current_steps": 53240, "total_steps": 64460, "loss": 0.1088, "lr": 8.950205579152033e-07, "epoch": 16.51877133105802, "percentage": 82.59, "elapsed_time": "1:38:43", "remaining_time": "0:20:48", "throughput": 5475.65, "total_tokens": 32433088} {"current_steps": 53245, "total_steps": 64460, "loss": 0.1885, "lr": 8.942477732484394e-07, "epoch": 16.52032268073224, "percentage": 82.6, "elapsed_time": "1:38:43", "remaining_time": "0:20:47", "throughput": 5475.72, "total_tokens": 32437088} {"current_steps": 53250, "total_steps": 64460, "loss": 0.1305, "lr": 8.934752895819349e-07, "epoch": 16.521874030406455, "percentage": 82.61, "elapsed_time": "1:38:44", "remaining_time": "0:20:47", "throughput": 5475.7, "total_tokens": 32439616} {"current_steps": 53255, "total_steps": 64460, "loss": 0.1746, "lr": 8.927031069723185e-07, "epoch": 16.52342538008067, "percentage": 82.62, "elapsed_time": "1:38:44", "remaining_time": "0:20:46", "throughput": 5475.72, "total_tokens": 32442560} {"current_steps": 53260, "total_steps": 64460, "loss": 0.1648, "lr": 8.91931225476203e-07, "epoch": 16.524976729754886, "percentage": 82.62, "elapsed_time": "1:38:45", "remaining_time": "0:20:46", "throughput": 5475.73, "total_tokens": 32445184} {"current_steps": 53265, "total_steps": 64460, "loss": 0.1376, "lr": 8.911596451501747e-07, "epoch": 16.526528079429102, "percentage": 82.63, "elapsed_time": "1:38:45", "remaining_time": "0:20:45", "throughput": 5475.86, "total_tokens": 32449184} {"current_steps": 53270, "total_steps": 64460, "loss": 0.1276, "lr": 8.903883660508006e-07, "epoch": 16.528079429103318, "percentage": 82.64, "elapsed_time": "1:38:46", "remaining_time": "0:20:44", "throughput": 5475.89, "total_tokens": 32452320} {"current_steps": 53275, "total_steps": 64460, "loss": 0.133, "lr": 8.896173882346248e-07, "epoch": 16.529630778777538, "percentage": 82.65, "elapsed_time": "1:38:46", "remaining_time": "0:20:44", "throughput": 5475.87, "total_tokens": 32455168} {"current_steps": 53280, "total_steps": 64460, "loss": 0.1599, "lr": 8.888467117581684e-07, "epoch": 16.531182128451753, "percentage": 82.66, "elapsed_time": "1:38:47", "remaining_time": "0:20:43", "throughput": 5475.87, "total_tokens": 32457696} {"current_steps": 53285, "total_steps": 64460, "loss": 0.1783, "lr": 8.880763366779322e-07, "epoch": 16.53273347812597, "percentage": 82.66, "elapsed_time": "1:38:47", "remaining_time": "0:20:43", "throughput": 5475.81, "total_tokens": 32459840} {"current_steps": 53290, "total_steps": 64460, "loss": 0.1657, "lr": 8.873062630503915e-07, "epoch": 16.534284827800185, "percentage": 82.67, "elapsed_time": "1:38:48", "remaining_time": "0:20:42", "throughput": 5475.86, "total_tokens": 32462816} {"current_steps": 53295, "total_steps": 64460, "loss": 0.1464, "lr": 8.865364909320046e-07, "epoch": 16.5358361774744, "percentage": 82.68, "elapsed_time": "1:38:48", "remaining_time": "0:20:42", "throughput": 5475.94, "total_tokens": 32466688} {"current_steps": 53300, "total_steps": 64460, "loss": 0.175, "lr": 8.857670203792023e-07, "epoch": 16.53738752714862, "percentage": 82.69, "elapsed_time": "1:38:49", "remaining_time": "0:20:41", "throughput": 5475.96, "total_tokens": 32469888} {"current_steps": 53305, "total_steps": 64460, "loss": 0.1676, "lr": 8.849978514483986e-07, "epoch": 16.538938876822836, "percentage": 82.69, "elapsed_time": "1:38:50", "remaining_time": "0:20:40", "throughput": 5475.95, "total_tokens": 32472448} {"current_steps": 53310, "total_steps": 64460, "loss": 0.2369, "lr": 8.842289841959801e-07, "epoch": 16.540490226497052, "percentage": 82.7, "elapsed_time": "1:38:50", "remaining_time": "0:20:40", "throughput": 5475.94, "total_tokens": 32475040} {"current_steps": 53315, "total_steps": 64460, "loss": 0.1789, "lr": 8.834604186783164e-07, "epoch": 16.54204157617127, "percentage": 82.71, "elapsed_time": "1:38:51", "remaining_time": "0:20:39", "throughput": 5475.84, "total_tokens": 32477248} {"current_steps": 53320, "total_steps": 64460, "loss": 0.1961, "lr": 8.826921549517498e-07, "epoch": 16.543592925845484, "percentage": 82.72, "elapsed_time": "1:38:51", "remaining_time": "0:20:39", "throughput": 5475.86, "total_tokens": 32480224} {"current_steps": 53325, "total_steps": 64460, "loss": 0.1771, "lr": 8.819241930726041e-07, "epoch": 16.545144275519704, "percentage": 82.73, "elapsed_time": "1:38:52", "remaining_time": "0:20:38", "throughput": 5475.9, "total_tokens": 32483168} {"current_steps": 53330, "total_steps": 64460, "loss": 0.1608, "lr": 8.811565330971822e-07, "epoch": 16.54669562519392, "percentage": 82.73, "elapsed_time": "1:38:52", "remaining_time": "0:20:38", "throughput": 5476.03, "total_tokens": 32488192} {"current_steps": 53335, "total_steps": 64460, "loss": 0.1478, "lr": 8.803891750817589e-07, "epoch": 16.548246974868135, "percentage": 82.74, "elapsed_time": "1:38:53", "remaining_time": "0:20:37", "throughput": 5476.14, "total_tokens": 32491872} {"current_steps": 53340, "total_steps": 64460, "loss": 0.2017, "lr": 8.796221190825943e-07, "epoch": 16.54979832454235, "percentage": 82.75, "elapsed_time": "1:38:53", "remaining_time": "0:20:37", "throughput": 5476.11, "total_tokens": 32494240} {"current_steps": 53345, "total_steps": 64460, "loss": 0.1464, "lr": 8.788553651559195e-07, "epoch": 16.551349674216567, "percentage": 82.76, "elapsed_time": "1:38:54", "remaining_time": "0:20:36", "throughput": 5476.22, "total_tokens": 32498144} {"current_steps": 53350, "total_steps": 64460, "loss": 0.1156, "lr": 8.780889133579496e-07, "epoch": 16.552901023890787, "percentage": 82.76, "elapsed_time": "1:38:54", "remaining_time": "0:20:35", "throughput": 5476.16, "total_tokens": 32500448} {"current_steps": 53355, "total_steps": 64460, "loss": 0.1435, "lr": 8.773227637448717e-07, "epoch": 16.554452373565002, "percentage": 82.77, "elapsed_time": "1:38:55", "remaining_time": "0:20:35", "throughput": 5476.16, "total_tokens": 32503168} {"current_steps": 53360, "total_steps": 64460, "loss": 0.2663, "lr": 8.76556916372856e-07, "epoch": 16.55600372323922, "percentage": 82.78, "elapsed_time": "1:38:55", "remaining_time": "0:20:34", "throughput": 5476.19, "total_tokens": 32506080} {"current_steps": 53365, "total_steps": 64460, "loss": 0.2799, "lr": 8.757913712980465e-07, "epoch": 16.557555072913434, "percentage": 82.79, "elapsed_time": "1:38:56", "remaining_time": "0:20:34", "throughput": 5476.27, "total_tokens": 32509408} {"current_steps": 53370, "total_steps": 64460, "loss": 0.1915, "lr": 8.750261285765682e-07, "epoch": 16.55910642258765, "percentage": 82.8, "elapsed_time": "1:38:56", "remaining_time": "0:20:33", "throughput": 5476.28, "total_tokens": 32512160} {"current_steps": 53375, "total_steps": 64460, "loss": 0.1647, "lr": 8.742611882645207e-07, "epoch": 16.56065777226187, "percentage": 82.8, "elapsed_time": "1:38:57", "remaining_time": "0:20:33", "throughput": 5476.35, "total_tokens": 32515168} {"current_steps": 53380, "total_steps": 64460, "loss": 0.1526, "lr": 8.734965504179854e-07, "epoch": 16.562209121936085, "percentage": 82.81, "elapsed_time": "1:38:57", "remaining_time": "0:20:32", "throughput": 5476.32, "total_tokens": 32518016} {"current_steps": 53385, "total_steps": 64460, "loss": 0.1372, "lr": 8.727322150930167e-07, "epoch": 16.5637604716103, "percentage": 82.82, "elapsed_time": "1:38:58", "remaining_time": "0:20:31", "throughput": 5476.36, "total_tokens": 32521344} {"current_steps": 53390, "total_steps": 64460, "loss": 0.269, "lr": 8.719681823456505e-07, "epoch": 16.565311821284517, "percentage": 82.83, "elapsed_time": "1:38:58", "remaining_time": "0:20:31", "throughput": 5476.35, "total_tokens": 32523968} {"current_steps": 53395, "total_steps": 64460, "loss": 0.15, "lr": 8.712044522319013e-07, "epoch": 16.566863170958733, "percentage": 82.83, "elapsed_time": "1:38:59", "remaining_time": "0:20:30", "throughput": 5476.41, "total_tokens": 32527360} {"current_steps": 53400, "total_steps": 64460, "loss": 0.1831, "lr": 8.704410248077572e-07, "epoch": 16.56841452063295, "percentage": 82.84, "elapsed_time": "1:39:00", "remaining_time": "0:20:30", "throughput": 5476.57, "total_tokens": 32532256} {"current_steps": 53405, "total_steps": 64460, "loss": 0.1622, "lr": 8.696779001291878e-07, "epoch": 16.56996587030717, "percentage": 82.85, "elapsed_time": "1:39:00", "remaining_time": "0:20:29", "throughput": 5476.51, "total_tokens": 32534464} {"current_steps": 53410, "total_steps": 64460, "loss": 0.1373, "lr": 8.689150782521377e-07, "epoch": 16.571517219981384, "percentage": 82.86, "elapsed_time": "1:39:01", "remaining_time": "0:20:29", "throughput": 5476.51, "total_tokens": 32537120} {"current_steps": 53415, "total_steps": 64460, "loss": 0.2349, "lr": 8.68152559232533e-07, "epoch": 16.5730685696556, "percentage": 82.87, "elapsed_time": "1:39:01", "remaining_time": "0:20:28", "throughput": 5476.64, "total_tokens": 32540992} {"current_steps": 53420, "total_steps": 64460, "loss": 0.1552, "lr": 8.673903431262726e-07, "epoch": 16.574619919329816, "percentage": 82.87, "elapsed_time": "1:39:02", "remaining_time": "0:20:28", "throughput": 5476.61, "total_tokens": 32543360} {"current_steps": 53425, "total_steps": 64460, "loss": 0.1454, "lr": 8.66628429989238e-07, "epoch": 16.576171269004032, "percentage": 82.88, "elapsed_time": "1:39:02", "remaining_time": "0:20:27", "throughput": 5476.5, "total_tokens": 32545280} {"current_steps": 53430, "total_steps": 64460, "loss": 0.1422, "lr": 8.658668198772857e-07, "epoch": 16.57772261867825, "percentage": 82.89, "elapsed_time": "1:39:03", "remaining_time": "0:20:26", "throughput": 5476.53, "total_tokens": 32548128} {"current_steps": 53435, "total_steps": 64460, "loss": 0.2281, "lr": 8.651055128462521e-07, "epoch": 16.579273968352467, "percentage": 82.9, "elapsed_time": "1:39:03", "remaining_time": "0:20:26", "throughput": 5476.52, "total_tokens": 32551072} {"current_steps": 53440, "total_steps": 64460, "loss": 0.1159, "lr": 8.643445089519475e-07, "epoch": 16.580825318026683, "percentage": 82.9, "elapsed_time": "1:39:04", "remaining_time": "0:20:25", "throughput": 5476.49, "total_tokens": 32553504} {"current_steps": 53445, "total_steps": 64460, "loss": 0.1642, "lr": 8.635838082501651e-07, "epoch": 16.5823766677009, "percentage": 82.91, "elapsed_time": "1:39:04", "remaining_time": "0:20:25", "throughput": 5476.52, "total_tokens": 32556544} {"current_steps": 53450, "total_steps": 64460, "loss": 0.16, "lr": 8.628234107966709e-07, "epoch": 16.583928017375115, "percentage": 82.92, "elapsed_time": "1:39:05", "remaining_time": "0:20:24", "throughput": 5476.45, "total_tokens": 32558944} {"current_steps": 53455, "total_steps": 64460, "loss": 0.1556, "lr": 8.620633166472136e-07, "epoch": 16.585479367049334, "percentage": 82.93, "elapsed_time": "1:39:05", "remaining_time": "0:20:24", "throughput": 5476.51, "total_tokens": 32562240} {"current_steps": 53460, "total_steps": 64460, "loss": 0.17, "lr": 8.613035258575148e-07, "epoch": 16.58703071672355, "percentage": 82.94, "elapsed_time": "1:39:06", "remaining_time": "0:20:23", "throughput": 5476.51, "total_tokens": 32564704} {"current_steps": 53465, "total_steps": 64460, "loss": 0.1551, "lr": 8.605440384832775e-07, "epoch": 16.588582066397766, "percentage": 82.94, "elapsed_time": "1:39:06", "remaining_time": "0:20:22", "throughput": 5476.53, "total_tokens": 32567584} {"current_steps": 53470, "total_steps": 64460, "loss": 0.1954, "lr": 8.597848545801801e-07, "epoch": 16.590133416071982, "percentage": 82.95, "elapsed_time": "1:39:07", "remaining_time": "0:20:22", "throughput": 5476.5, "total_tokens": 32570240} {"current_steps": 53475, "total_steps": 64460, "loss": 0.1822, "lr": 8.590259742038798e-07, "epoch": 16.591684765746198, "percentage": 82.96, "elapsed_time": "1:39:07", "remaining_time": "0:20:21", "throughput": 5476.63, "total_tokens": 32574560} {"current_steps": 53480, "total_steps": 64460, "loss": 0.1927, "lr": 8.582673974100136e-07, "epoch": 16.593236115420417, "percentage": 82.97, "elapsed_time": "1:39:08", "remaining_time": "0:20:21", "throughput": 5476.66, "total_tokens": 32577504} {"current_steps": 53485, "total_steps": 64460, "loss": 0.0878, "lr": 8.575091242541911e-07, "epoch": 16.594787465094633, "percentage": 82.97, "elapsed_time": "1:39:08", "remaining_time": "0:20:20", "throughput": 5476.73, "total_tokens": 32580960} {"current_steps": 53490, "total_steps": 64460, "loss": 0.2419, "lr": 8.56751154792006e-07, "epoch": 16.59633881476885, "percentage": 82.98, "elapsed_time": "1:39:09", "remaining_time": "0:20:20", "throughput": 5476.68, "total_tokens": 32583520} {"current_steps": 53495, "total_steps": 64460, "loss": 0.1235, "lr": 8.559934890790228e-07, "epoch": 16.597890164443065, "percentage": 82.99, "elapsed_time": "1:39:10", "remaining_time": "0:20:19", "throughput": 5476.73, "total_tokens": 32586784} {"current_steps": 53500, "total_steps": 64460, "loss": 0.189, "lr": 8.552361271707909e-07, "epoch": 16.59944151411728, "percentage": 83.0, "elapsed_time": "1:39:10", "remaining_time": "0:20:19", "throughput": 5476.79, "total_tokens": 32590336} {"current_steps": 53505, "total_steps": 64460, "loss": 0.1695, "lr": 8.54479069122831e-07, "epoch": 16.6009928637915, "percentage": 83.0, "elapsed_time": "1:39:11", "remaining_time": "0:20:18", "throughput": 5476.84, "total_tokens": 32593408} {"current_steps": 53510, "total_steps": 64460, "loss": 0.0956, "lr": 8.537223149906465e-07, "epoch": 16.602544213465716, "percentage": 83.01, "elapsed_time": "1:39:11", "remaining_time": "0:20:17", "throughput": 5476.82, "total_tokens": 32595872} {"current_steps": 53515, "total_steps": 64460, "loss": 0.1175, "lr": 8.529658648297146e-07, "epoch": 16.604095563139932, "percentage": 83.02, "elapsed_time": "1:39:12", "remaining_time": "0:20:17", "throughput": 5476.86, "total_tokens": 32599040} {"current_steps": 53520, "total_steps": 64460, "loss": 0.1769, "lr": 8.522097186954942e-07, "epoch": 16.605646912814148, "percentage": 83.03, "elapsed_time": "1:39:12", "remaining_time": "0:20:16", "throughput": 5476.84, "total_tokens": 32601504} {"current_steps": 53525, "total_steps": 64460, "loss": 0.2365, "lr": 8.514538766434178e-07, "epoch": 16.607198262488364, "percentage": 83.04, "elapsed_time": "1:39:13", "remaining_time": "0:20:16", "throughput": 5476.86, "total_tokens": 32604480} {"current_steps": 53530, "total_steps": 64460, "loss": 0.1747, "lr": 8.506983387288981e-07, "epoch": 16.608749612162583, "percentage": 83.04, "elapsed_time": "1:39:13", "remaining_time": "0:20:15", "throughput": 5476.95, "total_tokens": 32608096} {"current_steps": 53535, "total_steps": 64460, "loss": 0.1649, "lr": 8.499431050073259e-07, "epoch": 16.6103009618368, "percentage": 83.05, "elapsed_time": "1:39:14", "remaining_time": "0:20:15", "throughput": 5477.02, "total_tokens": 32611168} {"current_steps": 53540, "total_steps": 64460, "loss": 0.2107, "lr": 8.491881755340676e-07, "epoch": 16.611852311511015, "percentage": 83.06, "elapsed_time": "1:39:14", "remaining_time": "0:20:14", "throughput": 5477.01, "total_tokens": 32614688} {"current_steps": 53545, "total_steps": 64460, "loss": 0.1157, "lr": 8.484335503644703e-07, "epoch": 16.61340366118523, "percentage": 83.07, "elapsed_time": "1:39:15", "remaining_time": "0:20:14", "throughput": 5477.14, "total_tokens": 32618912} {"current_steps": 53550, "total_steps": 64460, "loss": 0.1952, "lr": 8.476792295538539e-07, "epoch": 16.614955010859447, "percentage": 83.07, "elapsed_time": "1:39:15", "remaining_time": "0:20:13", "throughput": 5477.04, "total_tokens": 32621152} {"current_steps": 53555, "total_steps": 64460, "loss": 0.2281, "lr": 8.469252131575223e-07, "epoch": 16.616506360533663, "percentage": 83.08, "elapsed_time": "1:39:16", "remaining_time": "0:20:12", "throughput": 5477.02, "total_tokens": 32624544} {"current_steps": 53560, "total_steps": 64460, "loss": 0.1545, "lr": 8.461715012307508e-07, "epoch": 16.618057710207882, "percentage": 83.09, "elapsed_time": "1:39:17", "remaining_time": "0:20:12", "throughput": 5476.98, "total_tokens": 32626848} {"current_steps": 53565, "total_steps": 64460, "loss": 0.1231, "lr": 8.454180938287987e-07, "epoch": 16.619609059882098, "percentage": 83.1, "elapsed_time": "1:39:17", "remaining_time": "0:20:11", "throughput": 5477.03, "total_tokens": 32629952} {"current_steps": 53570, "total_steps": 64460, "loss": 0.1879, "lr": 8.446649910068965e-07, "epoch": 16.621160409556314, "percentage": 83.11, "elapsed_time": "1:39:18", "remaining_time": "0:20:11", "throughput": 5477.01, "total_tokens": 32632576} {"current_steps": 53575, "total_steps": 64460, "loss": 0.1832, "lr": 8.439121928202582e-07, "epoch": 16.62271175923053, "percentage": 83.11, "elapsed_time": "1:39:18", "remaining_time": "0:20:10", "throughput": 5477.01, "total_tokens": 32635488} {"current_steps": 53580, "total_steps": 64460, "loss": 0.1805, "lr": 8.431596993240704e-07, "epoch": 16.624263108904746, "percentage": 83.12, "elapsed_time": "1:39:19", "remaining_time": "0:20:10", "throughput": 5477.1, "total_tokens": 32639328} {"current_steps": 53585, "total_steps": 64460, "loss": 0.1509, "lr": 8.424075105735024e-07, "epoch": 16.625814458578965, "percentage": 83.13, "elapsed_time": "1:39:19", "remaining_time": "0:20:09", "throughput": 5477.03, "total_tokens": 32641472} {"current_steps": 53590, "total_steps": 64460, "loss": 0.2062, "lr": 8.416556266236959e-07, "epoch": 16.62736580825318, "percentage": 83.14, "elapsed_time": "1:39:20", "remaining_time": "0:20:08", "throughput": 5477.07, "total_tokens": 32644416} {"current_steps": 53595, "total_steps": 64460, "loss": 0.1146, "lr": 8.409040475297736e-07, "epoch": 16.628917157927397, "percentage": 83.14, "elapsed_time": "1:39:20", "remaining_time": "0:20:08", "throughput": 5477.02, "total_tokens": 32646656} {"current_steps": 53600, "total_steps": 64460, "loss": 0.1398, "lr": 8.401527733468373e-07, "epoch": 16.630468507601613, "percentage": 83.15, "elapsed_time": "1:39:21", "remaining_time": "0:20:07", "throughput": 5477.04, "total_tokens": 32649696} {"current_steps": 53605, "total_steps": 64460, "loss": 0.2561, "lr": 8.394018041299612e-07, "epoch": 16.63201985727583, "percentage": 83.16, "elapsed_time": "1:39:21", "remaining_time": "0:20:07", "throughput": 5476.99, "total_tokens": 32652064} {"current_steps": 53610, "total_steps": 64460, "loss": 0.1855, "lr": 8.386511399342034e-07, "epoch": 16.633571206950048, "percentage": 83.17, "elapsed_time": "1:39:22", "remaining_time": "0:20:06", "throughput": 5476.95, "total_tokens": 32654752} {"current_steps": 53615, "total_steps": 64460, "loss": 0.1021, "lr": 8.379007808145934e-07, "epoch": 16.635122556624264, "percentage": 83.18, "elapsed_time": "1:39:22", "remaining_time": "0:20:06", "throughput": 5476.91, "total_tokens": 32657280} {"current_steps": 53620, "total_steps": 64460, "loss": 0.1139, "lr": 8.371507268261436e-07, "epoch": 16.63667390629848, "percentage": 83.18, "elapsed_time": "1:39:23", "remaining_time": "0:20:05", "throughput": 5476.89, "total_tokens": 32660128} {"current_steps": 53625, "total_steps": 64460, "loss": 0.1132, "lr": 8.364009780238403e-07, "epoch": 16.638225255972696, "percentage": 83.19, "elapsed_time": "1:39:23", "remaining_time": "0:20:05", "throughput": 5477.03, "total_tokens": 32664512} {"current_steps": 53630, "total_steps": 64460, "loss": 0.1983, "lr": 8.356515344626509e-07, "epoch": 16.63977660564691, "percentage": 83.2, "elapsed_time": "1:39:24", "remaining_time": "0:20:04", "throughput": 5476.94, "total_tokens": 32666528} {"current_steps": 53635, "total_steps": 64460, "loss": 0.1043, "lr": 8.349023961975155e-07, "epoch": 16.64132795532113, "percentage": 83.21, "elapsed_time": "1:39:24", "remaining_time": "0:20:03", "throughput": 5477.0, "total_tokens": 32669696} {"current_steps": 53640, "total_steps": 64460, "loss": 0.1786, "lr": 8.341535632833586e-07, "epoch": 16.642879304995347, "percentage": 83.21, "elapsed_time": "1:39:25", "remaining_time": "0:20:03", "throughput": 5477.06, "total_tokens": 32672896} {"current_steps": 53645, "total_steps": 64460, "loss": 0.1935, "lr": 8.334050357750745e-07, "epoch": 16.644430654669563, "percentage": 83.22, "elapsed_time": "1:39:25", "remaining_time": "0:20:02", "throughput": 5477.07, "total_tokens": 32675744} {"current_steps": 53650, "total_steps": 64460, "loss": 0.1178, "lr": 8.32656813727542e-07, "epoch": 16.64598200434378, "percentage": 83.23, "elapsed_time": "1:39:26", "remaining_time": "0:20:02", "throughput": 5477.13, "total_tokens": 32679264} {"current_steps": 53655, "total_steps": 64460, "loss": 0.1905, "lr": 8.319088971956141e-07, "epoch": 16.647533354017995, "percentage": 83.24, "elapsed_time": "1:39:26", "remaining_time": "0:20:01", "throughput": 5477.1, "total_tokens": 32681696} {"current_steps": 53660, "total_steps": 64460, "loss": 0.1728, "lr": 8.311612862341212e-07, "epoch": 16.64908470369221, "percentage": 83.25, "elapsed_time": "1:39:27", "remaining_time": "0:20:01", "throughput": 5477.14, "total_tokens": 32684864} {"current_steps": 53665, "total_steps": 64460, "loss": 0.1498, "lr": 8.304139808978734e-07, "epoch": 16.65063605336643, "percentage": 83.25, "elapsed_time": "1:39:27", "remaining_time": "0:20:00", "throughput": 5477.15, "total_tokens": 32687552} {"current_steps": 53670, "total_steps": 64460, "loss": 0.1362, "lr": 8.296669812416546e-07, "epoch": 16.652187403040646, "percentage": 83.26, "elapsed_time": "1:39:28", "remaining_time": "0:19:59", "throughput": 5477.19, "total_tokens": 32690560} {"current_steps": 53675, "total_steps": 64460, "loss": 0.1912, "lr": 8.289202873202317e-07, "epoch": 16.65373875271486, "percentage": 83.27, "elapsed_time": "1:39:28", "remaining_time": "0:19:59", "throughput": 5477.24, "total_tokens": 32693568} {"current_steps": 53680, "total_steps": 64460, "loss": 0.1612, "lr": 8.281738991883431e-07, "epoch": 16.655290102389078, "percentage": 83.28, "elapsed_time": "1:39:29", "remaining_time": "0:19:58", "throughput": 5477.12, "total_tokens": 32695424} {"current_steps": 53685, "total_steps": 64460, "loss": 0.1402, "lr": 8.27427816900711e-07, "epoch": 16.656841452063293, "percentage": 83.28, "elapsed_time": "1:39:29", "remaining_time": "0:19:58", "throughput": 5477.15, "total_tokens": 32698272} {"current_steps": 53690, "total_steps": 64460, "loss": 0.1403, "lr": 8.266820405120296e-07, "epoch": 16.658392801737513, "percentage": 83.29, "elapsed_time": "1:39:30", "remaining_time": "0:19:57", "throughput": 5477.13, "total_tokens": 32700768} {"current_steps": 53695, "total_steps": 64460, "loss": 0.1511, "lr": 8.259365700769751e-07, "epoch": 16.65994415141173, "percentage": 83.3, "elapsed_time": "1:39:31", "remaining_time": "0:19:57", "throughput": 5477.21, "total_tokens": 32705664} {"current_steps": 53700, "total_steps": 64460, "loss": 0.1286, "lr": 8.25191405650197e-07, "epoch": 16.661495501085945, "percentage": 83.31, "elapsed_time": "1:39:31", "remaining_time": "0:19:56", "throughput": 5477.22, "total_tokens": 32708352} {"current_steps": 53705, "total_steps": 64460, "loss": 0.167, "lr": 8.244465472863278e-07, "epoch": 16.66304685076016, "percentage": 83.32, "elapsed_time": "1:39:32", "remaining_time": "0:19:55", "throughput": 5477.24, "total_tokens": 32711168} {"current_steps": 53710, "total_steps": 64460, "loss": 0.1379, "lr": 8.237019950399705e-07, "epoch": 16.664598200434376, "percentage": 83.32, "elapsed_time": "1:39:32", "remaining_time": "0:19:55", "throughput": 5477.26, "total_tokens": 32713920} {"current_steps": 53715, "total_steps": 64460, "loss": 0.1515, "lr": 8.229577489657126e-07, "epoch": 16.666149550108596, "percentage": 83.33, "elapsed_time": "1:39:33", "remaining_time": "0:19:54", "throughput": 5477.32, "total_tokens": 32717248} {"current_steps": 53720, "total_steps": 64460, "loss": 0.2621, "lr": 8.222138091181158e-07, "epoch": 16.66770089978281, "percentage": 83.34, "elapsed_time": "1:39:33", "remaining_time": "0:19:54", "throughput": 5477.27, "total_tokens": 32719520} {"current_steps": 53725, "total_steps": 64460, "loss": 0.1731, "lr": 8.214701755517185e-07, "epoch": 16.669252249457028, "percentage": 83.35, "elapsed_time": "1:39:34", "remaining_time": "0:19:53", "throughput": 5477.39, "total_tokens": 32723296} {"current_steps": 53730, "total_steps": 64460, "loss": 0.2155, "lr": 8.20726848321039e-07, "epoch": 16.670803599131244, "percentage": 83.35, "elapsed_time": "1:39:34", "remaining_time": "0:19:53", "throughput": 5477.38, "total_tokens": 32725792} {"current_steps": 53735, "total_steps": 64460, "loss": 0.1219, "lr": 8.19983827480571e-07, "epoch": 16.67235494880546, "percentage": 83.36, "elapsed_time": "1:39:35", "remaining_time": "0:19:52", "throughput": 5477.47, "total_tokens": 32729376} {"current_steps": 53740, "total_steps": 64460, "loss": 0.2135, "lr": 8.192411130847883e-07, "epoch": 16.67390629847968, "percentage": 83.37, "elapsed_time": "1:39:35", "remaining_time": "0:19:52", "throughput": 5477.44, "total_tokens": 32731744} {"current_steps": 53745, "total_steps": 64460, "loss": 0.1733, "lr": 8.184987051881382e-07, "epoch": 16.675457648153895, "percentage": 83.38, "elapsed_time": "1:39:36", "remaining_time": "0:19:51", "throughput": 5477.5, "total_tokens": 32734944} {"current_steps": 53750, "total_steps": 64460, "loss": 0.2824, "lr": 8.177566038450507e-07, "epoch": 16.67700899782811, "percentage": 83.39, "elapsed_time": "1:39:36", "remaining_time": "0:19:50", "throughput": 5477.43, "total_tokens": 32737088} {"current_steps": 53755, "total_steps": 64460, "loss": 0.2229, "lr": 8.170148091099284e-07, "epoch": 16.678560347502327, "percentage": 83.39, "elapsed_time": "1:39:37", "remaining_time": "0:19:50", "throughput": 5477.46, "total_tokens": 32740608} {"current_steps": 53760, "total_steps": 64460, "loss": 0.1529, "lr": 8.162733210371554e-07, "epoch": 16.680111697176542, "percentage": 83.4, "elapsed_time": "1:39:37", "remaining_time": "0:19:49", "throughput": 5477.52, "total_tokens": 32744032} {"current_steps": 53765, "total_steps": 64460, "loss": 0.1612, "lr": 8.155321396810894e-07, "epoch": 16.681663046850762, "percentage": 83.41, "elapsed_time": "1:39:38", "remaining_time": "0:19:49", "throughput": 5477.59, "total_tokens": 32747616} {"current_steps": 53770, "total_steps": 64460, "loss": 0.2794, "lr": 8.147912650960693e-07, "epoch": 16.683214396524978, "percentage": 83.42, "elapsed_time": "1:39:38", "remaining_time": "0:19:48", "throughput": 5477.59, "total_tokens": 32750432} {"current_steps": 53775, "total_steps": 64460, "loss": 0.1428, "lr": 8.140506973364109e-07, "epoch": 16.684765746199194, "percentage": 83.42, "elapsed_time": "1:39:39", "remaining_time": "0:19:48", "throughput": 5477.58, "total_tokens": 32753216} {"current_steps": 53780, "total_steps": 64460, "loss": 0.2009, "lr": 8.133104364564043e-07, "epoch": 16.68631709587341, "percentage": 83.43, "elapsed_time": "1:39:40", "remaining_time": "0:19:47", "throughput": 5477.61, "total_tokens": 32756224} {"current_steps": 53785, "total_steps": 64460, "loss": 0.1667, "lr": 8.12570482510322e-07, "epoch": 16.687868445547625, "percentage": 83.44, "elapsed_time": "1:39:40", "remaining_time": "0:19:46", "throughput": 5477.59, "total_tokens": 32758912} {"current_steps": 53790, "total_steps": 64460, "loss": 0.1641, "lr": 8.118308355524079e-07, "epoch": 16.689419795221845, "percentage": 83.45, "elapsed_time": "1:39:40", "remaining_time": "0:19:46", "throughput": 5477.54, "total_tokens": 32761184} {"current_steps": 53795, "total_steps": 64460, "loss": 0.1876, "lr": 8.11091495636891e-07, "epoch": 16.69097114489606, "percentage": 83.45, "elapsed_time": "1:39:41", "remaining_time": "0:19:45", "throughput": 5477.55, "total_tokens": 32763840} {"current_steps": 53800, "total_steps": 64460, "loss": 0.1274, "lr": 8.103524628179699e-07, "epoch": 16.692522494570277, "percentage": 83.46, "elapsed_time": "1:39:42", "remaining_time": "0:19:45", "throughput": 5477.64, "total_tokens": 32768064} {"current_steps": 53805, "total_steps": 64460, "loss": 0.1244, "lr": 8.096137371498275e-07, "epoch": 16.694073844244492, "percentage": 83.47, "elapsed_time": "1:39:42", "remaining_time": "0:19:44", "throughput": 5477.72, "total_tokens": 32771680} {"current_steps": 53810, "total_steps": 64460, "loss": 0.1703, "lr": 8.088753186866183e-07, "epoch": 16.69562519391871, "percentage": 83.48, "elapsed_time": "1:39:43", "remaining_time": "0:19:44", "throughput": 5477.66, "total_tokens": 32773984} {"current_steps": 53815, "total_steps": 64460, "loss": 0.1179, "lr": 8.0813720748248e-07, "epoch": 16.697176543592924, "percentage": 83.49, "elapsed_time": "1:39:43", "remaining_time": "0:19:43", "throughput": 5477.67, "total_tokens": 32776704} {"current_steps": 53820, "total_steps": 64460, "loss": 0.1811, "lr": 8.073994035915222e-07, "epoch": 16.698727893267144, "percentage": 83.49, "elapsed_time": "1:39:44", "remaining_time": "0:19:43", "throughput": 5477.7, "total_tokens": 32779648} {"current_steps": 53825, "total_steps": 64460, "loss": 0.1227, "lr": 8.066619070678372e-07, "epoch": 16.70027924294136, "percentage": 83.5, "elapsed_time": "1:39:44", "remaining_time": "0:19:42", "throughput": 5477.71, "total_tokens": 32782400} {"current_steps": 53830, "total_steps": 64460, "loss": 0.1087, "lr": 8.059247179654894e-07, "epoch": 16.701830592615575, "percentage": 83.51, "elapsed_time": "1:39:45", "remaining_time": "0:19:41", "throughput": 5477.79, "total_tokens": 32785984} {"current_steps": 53835, "total_steps": 64460, "loss": 0.1188, "lr": 8.051878363385257e-07, "epoch": 16.70338194228979, "percentage": 83.52, "elapsed_time": "1:39:45", "remaining_time": "0:19:41", "throughput": 5477.8, "total_tokens": 32788800} {"current_steps": 53840, "total_steps": 64460, "loss": 0.2443, "lr": 8.044512622409684e-07, "epoch": 16.704933291964007, "percentage": 83.52, "elapsed_time": "1:39:46", "remaining_time": "0:19:40", "throughput": 5477.89, "total_tokens": 32792640} {"current_steps": 53845, "total_steps": 64460, "loss": 0.1673, "lr": 8.037149957268154e-07, "epoch": 16.706484641638227, "percentage": 83.53, "elapsed_time": "1:39:46", "remaining_time": "0:19:40", "throughput": 5477.81, "total_tokens": 32794976} {"current_steps": 53850, "total_steps": 64460, "loss": 0.1799, "lr": 8.029790368500456e-07, "epoch": 16.708035991312443, "percentage": 83.54, "elapsed_time": "1:39:47", "remaining_time": "0:19:39", "throughput": 5477.87, "total_tokens": 32798944} {"current_steps": 53855, "total_steps": 64460, "loss": 0.1448, "lr": 8.022433856646111e-07, "epoch": 16.70958734098666, "percentage": 83.55, "elapsed_time": "1:39:48", "remaining_time": "0:19:39", "throughput": 5477.96, "total_tokens": 32802400} {"current_steps": 53860, "total_steps": 64460, "loss": 0.203, "lr": 8.01508042224447e-07, "epoch": 16.711138690660874, "percentage": 83.56, "elapsed_time": "1:39:48", "remaining_time": "0:19:38", "throughput": 5478.01, "total_tokens": 32805600} {"current_steps": 53865, "total_steps": 64460, "loss": 0.142, "lr": 8.007730065834596e-07, "epoch": 16.71269004033509, "percentage": 83.56, "elapsed_time": "1:39:49", "remaining_time": "0:19:38", "throughput": 5478.09, "total_tokens": 32809184} {"current_steps": 53870, "total_steps": 64460, "loss": 0.2575, "lr": 8.00038278795538e-07, "epoch": 16.71424139000931, "percentage": 83.57, "elapsed_time": "1:39:49", "remaining_time": "0:19:37", "throughput": 5478.1, "total_tokens": 32812320} {"current_steps": 53875, "total_steps": 64460, "loss": 0.1096, "lr": 7.993038589145447e-07, "epoch": 16.715792739683526, "percentage": 83.58, "elapsed_time": "1:39:50", "remaining_time": "0:19:36", "throughput": 5478.07, "total_tokens": 32815232} {"current_steps": 53880, "total_steps": 64460, "loss": 0.1154, "lr": 7.985697469943237e-07, "epoch": 16.71734408935774, "percentage": 83.59, "elapsed_time": "1:39:50", "remaining_time": "0:19:36", "throughput": 5477.98, "total_tokens": 32817440} {"current_steps": 53885, "total_steps": 64460, "loss": 0.1367, "lr": 7.978359430886912e-07, "epoch": 16.718895439031957, "percentage": 83.59, "elapsed_time": "1:39:51", "remaining_time": "0:19:35", "throughput": 5477.94, "total_tokens": 32820160} {"current_steps": 53890, "total_steps": 64460, "loss": 0.1822, "lr": 7.97102447251445e-07, "epoch": 16.720446788706173, "percentage": 83.6, "elapsed_time": "1:39:51", "remaining_time": "0:19:35", "throughput": 5477.97, "total_tokens": 32823104} {"current_steps": 53895, "total_steps": 64460, "loss": 0.0998, "lr": 7.963692595363603e-07, "epoch": 16.721998138380393, "percentage": 83.61, "elapsed_time": "1:39:52", "remaining_time": "0:19:34", "throughput": 5478.0, "total_tokens": 32826080} {"current_steps": 53900, "total_steps": 64460, "loss": 0.1745, "lr": 7.956363799971862e-07, "epoch": 16.72354948805461, "percentage": 83.62, "elapsed_time": "1:39:53", "remaining_time": "0:19:34", "throughput": 5478.09, "total_tokens": 32830400} {"current_steps": 53905, "total_steps": 64460, "loss": 0.236, "lr": 7.949038086876537e-07, "epoch": 16.725100837728824, "percentage": 83.63, "elapsed_time": "1:39:53", "remaining_time": "0:19:33", "throughput": 5478.09, "total_tokens": 32833568} {"current_steps": 53910, "total_steps": 64460, "loss": 0.1206, "lr": 7.941715456614668e-07, "epoch": 16.72665218740304, "percentage": 83.63, "elapsed_time": "1:39:54", "remaining_time": "0:19:33", "throughput": 5478.06, "total_tokens": 32836064} {"current_steps": 53915, "total_steps": 64460, "loss": 0.2091, "lr": 7.934395909723109e-07, "epoch": 16.728203537077256, "percentage": 83.64, "elapsed_time": "1:39:54", "remaining_time": "0:19:32", "throughput": 5478.1, "total_tokens": 32839200} {"current_steps": 53920, "total_steps": 64460, "loss": 0.1211, "lr": 7.927079446738451e-07, "epoch": 16.729754886751472, "percentage": 83.65, "elapsed_time": "1:39:55", "remaining_time": "0:19:31", "throughput": 5478.11, "total_tokens": 32841824} {"current_steps": 53925, "total_steps": 64460, "loss": 0.2791, "lr": 7.919766068197099e-07, "epoch": 16.73130623642569, "percentage": 83.66, "elapsed_time": "1:39:55", "remaining_time": "0:19:31", "throughput": 5478.16, "total_tokens": 32845376} {"current_steps": 53930, "total_steps": 64460, "loss": 0.2243, "lr": 7.912455774635192e-07, "epoch": 16.732857586099907, "percentage": 83.66, "elapsed_time": "1:39:56", "remaining_time": "0:19:30", "throughput": 5478.25, "total_tokens": 32849280} {"current_steps": 53935, "total_steps": 64460, "loss": 0.1624, "lr": 7.905148566588672e-07, "epoch": 16.734408935774123, "percentage": 83.67, "elapsed_time": "1:39:56", "remaining_time": "0:19:30", "throughput": 5478.35, "total_tokens": 32853152} {"current_steps": 53940, "total_steps": 64460, "loss": 0.1874, "lr": 7.897844444593234e-07, "epoch": 16.73596028544834, "percentage": 83.68, "elapsed_time": "1:39:57", "remaining_time": "0:19:29", "throughput": 5478.33, "total_tokens": 32855616} {"current_steps": 53945, "total_steps": 64460, "loss": 0.1983, "lr": 7.89054340918437e-07, "epoch": 16.737511635122555, "percentage": 83.69, "elapsed_time": "1:39:57", "remaining_time": "0:19:29", "throughput": 5478.36, "total_tokens": 32858400} {"current_steps": 53950, "total_steps": 64460, "loss": 0.1541, "lr": 7.883245460897315e-07, "epoch": 16.739062984796774, "percentage": 83.7, "elapsed_time": "1:39:58", "remaining_time": "0:19:28", "throughput": 5478.41, "total_tokens": 32861472} {"current_steps": 53955, "total_steps": 64460, "loss": 0.2065, "lr": 7.875950600267102e-07, "epoch": 16.74061433447099, "percentage": 83.7, "elapsed_time": "1:39:58", "remaining_time": "0:19:27", "throughput": 5478.3, "total_tokens": 32863520} {"current_steps": 53960, "total_steps": 64460, "loss": 0.1547, "lr": 7.868658827828551e-07, "epoch": 16.742165684145206, "percentage": 83.71, "elapsed_time": "1:39:59", "remaining_time": "0:19:27", "throughput": 5478.29, "total_tokens": 32866048} {"current_steps": 53965, "total_steps": 64460, "loss": 0.1674, "lr": 7.861370144116198e-07, "epoch": 16.743717033819422, "percentage": 83.72, "elapsed_time": "1:39:59", "remaining_time": "0:19:26", "throughput": 5478.27, "total_tokens": 32868704} {"current_steps": 53970, "total_steps": 64460, "loss": 0.2002, "lr": 7.854084549664426e-07, "epoch": 16.745268383493638, "percentage": 83.73, "elapsed_time": "1:40:00", "remaining_time": "0:19:26", "throughput": 5478.29, "total_tokens": 32871488} {"current_steps": 53975, "total_steps": 64460, "loss": 0.1927, "lr": 7.846802045007329e-07, "epoch": 16.746819733167857, "percentage": 83.73, "elapsed_time": "1:40:00", "remaining_time": "0:19:25", "throughput": 5478.35, "total_tokens": 32874944} {"current_steps": 53980, "total_steps": 64460, "loss": 0.1515, "lr": 7.839522630678819e-07, "epoch": 16.748371082842073, "percentage": 83.74, "elapsed_time": "1:40:01", "remaining_time": "0:19:25", "throughput": 5478.37, "total_tokens": 32877920} {"current_steps": 53985, "total_steps": 64460, "loss": 0.181, "lr": 7.832246307212543e-07, "epoch": 16.74992243251629, "percentage": 83.75, "elapsed_time": "1:40:01", "remaining_time": "0:19:24", "throughput": 5478.47, "total_tokens": 32881664} {"current_steps": 53990, "total_steps": 64460, "loss": 0.1899, "lr": 7.824973075141967e-07, "epoch": 16.751473782190505, "percentage": 83.76, "elapsed_time": "1:40:02", "remaining_time": "0:19:24", "throughput": 5478.47, "total_tokens": 32884704} {"current_steps": 53995, "total_steps": 64460, "loss": 0.1403, "lr": 7.817702935000282e-07, "epoch": 16.75302513186472, "percentage": 83.77, "elapsed_time": "1:40:03", "remaining_time": "0:19:23", "throughput": 5478.52, "total_tokens": 32887680} {"current_steps": 54000, "total_steps": 64460, "loss": 0.1726, "lr": 7.810435887320494e-07, "epoch": 16.75457648153894, "percentage": 83.77, "elapsed_time": "1:40:03", "remaining_time": "0:19:22", "throughput": 5478.57, "total_tokens": 32890976} {"current_steps": 54005, "total_steps": 64460, "loss": 0.2004, "lr": 7.803171932635329e-07, "epoch": 16.756127831213156, "percentage": 83.78, "elapsed_time": "1:40:04", "remaining_time": "0:19:22", "throughput": 5478.56, "total_tokens": 32893568} {"current_steps": 54010, "total_steps": 64460, "loss": 0.1588, "lr": 7.795911071477374e-07, "epoch": 16.757679180887372, "percentage": 83.79, "elapsed_time": "1:40:04", "remaining_time": "0:19:21", "throughput": 5478.68, "total_tokens": 32898016} {"current_steps": 54015, "total_steps": 64460, "loss": 0.2177, "lr": 7.78865330437889e-07, "epoch": 16.759230530561588, "percentage": 83.8, "elapsed_time": "1:40:05", "remaining_time": "0:19:21", "throughput": 5478.62, "total_tokens": 32900224} {"current_steps": 54020, "total_steps": 64460, "loss": 0.2053, "lr": 7.781398631871995e-07, "epoch": 16.760781880235804, "percentage": 83.8, "elapsed_time": "1:40:05", "remaining_time": "0:19:20", "throughput": 5478.69, "total_tokens": 32903360} {"current_steps": 54025, "total_steps": 64460, "loss": 0.1693, "lr": 7.774147054488513e-07, "epoch": 16.762333229910023, "percentage": 83.81, "elapsed_time": "1:40:06", "remaining_time": "0:19:20", "throughput": 5478.72, "total_tokens": 32906304} {"current_steps": 54030, "total_steps": 64460, "loss": 0.1804, "lr": 7.766898572760084e-07, "epoch": 16.76388457958424, "percentage": 83.82, "elapsed_time": "1:40:06", "remaining_time": "0:19:19", "throughput": 5478.7, "total_tokens": 32908800} {"current_steps": 54035, "total_steps": 64460, "loss": 0.195, "lr": 7.759653187218097e-07, "epoch": 16.765435929258455, "percentage": 83.83, "elapsed_time": "1:40:07", "remaining_time": "0:19:18", "throughput": 5478.72, "total_tokens": 32911680} {"current_steps": 54040, "total_steps": 64460, "loss": 0.1842, "lr": 7.752410898393736e-07, "epoch": 16.76698727893267, "percentage": 83.83, "elapsed_time": "1:40:07", "remaining_time": "0:19:18", "throughput": 5478.73, "total_tokens": 32914304} {"current_steps": 54045, "total_steps": 64460, "loss": 0.1559, "lr": 7.74517170681795e-07, "epoch": 16.768538628606887, "percentage": 83.84, "elapsed_time": "1:40:08", "remaining_time": "0:19:17", "throughput": 5478.76, "total_tokens": 32917888} {"current_steps": 54050, "total_steps": 64460, "loss": 0.2424, "lr": 7.737935613021436e-07, "epoch": 16.770089978281106, "percentage": 83.85, "elapsed_time": "1:40:08", "remaining_time": "0:19:17", "throughput": 5478.78, "total_tokens": 32920704} {"current_steps": 54055, "total_steps": 64460, "loss": 0.1144, "lr": 7.730702617534713e-07, "epoch": 16.771641327955322, "percentage": 83.86, "elapsed_time": "1:40:09", "remaining_time": "0:19:16", "throughput": 5478.82, "total_tokens": 32923872} {"current_steps": 54060, "total_steps": 64460, "loss": 0.1503, "lr": 7.72347272088802e-07, "epoch": 16.773192677629538, "percentage": 83.87, "elapsed_time": "1:40:09", "remaining_time": "0:19:16", "throughput": 5478.97, "total_tokens": 32928192} {"current_steps": 54065, "total_steps": 64460, "loss": 0.1656, "lr": 7.71624592361142e-07, "epoch": 16.774744027303754, "percentage": 83.87, "elapsed_time": "1:40:10", "remaining_time": "0:19:15", "throughput": 5478.99, "total_tokens": 32931136} {"current_steps": 54070, "total_steps": 64460, "loss": 0.1927, "lr": 7.709022226234697e-07, "epoch": 16.77629537697797, "percentage": 83.88, "elapsed_time": "1:40:10", "remaining_time": "0:19:15", "throughput": 5478.97, "total_tokens": 32933760} {"current_steps": 54075, "total_steps": 64460, "loss": 0.231, "lr": 7.701801629287454e-07, "epoch": 16.777846726652186, "percentage": 83.89, "elapsed_time": "1:40:11", "remaining_time": "0:19:14", "throughput": 5479.02, "total_tokens": 32937088} {"current_steps": 54080, "total_steps": 64460, "loss": 0.2403, "lr": 7.694584133299021e-07, "epoch": 16.779398076326405, "percentage": 83.9, "elapsed_time": "1:40:12", "remaining_time": "0:19:13", "throughput": 5479.07, "total_tokens": 32940800} {"current_steps": 54085, "total_steps": 64460, "loss": 0.1778, "lr": 7.687369738798561e-07, "epoch": 16.78094942600062, "percentage": 83.9, "elapsed_time": "1:40:12", "remaining_time": "0:19:13", "throughput": 5479.06, "total_tokens": 32943424} {"current_steps": 54090, "total_steps": 64460, "loss": 0.1173, "lr": 7.68015844631494e-07, "epoch": 16.782500775674837, "percentage": 83.91, "elapsed_time": "1:40:13", "remaining_time": "0:19:12", "throughput": 5479.12, "total_tokens": 32946816} {"current_steps": 54095, "total_steps": 64460, "loss": 0.1161, "lr": 7.67295025637686e-07, "epoch": 16.784052125349053, "percentage": 83.92, "elapsed_time": "1:40:13", "remaining_time": "0:19:12", "throughput": 5479.21, "total_tokens": 32950336} {"current_steps": 54100, "total_steps": 64460, "loss": 0.2048, "lr": 7.665745169512739e-07, "epoch": 16.78560347502327, "percentage": 83.93, "elapsed_time": "1:40:14", "remaining_time": "0:19:11", "throughput": 5479.24, "total_tokens": 32953408} {"current_steps": 54105, "total_steps": 64460, "loss": 0.1355, "lr": 7.658543186250817e-07, "epoch": 16.787154824697488, "percentage": 83.94, "elapsed_time": "1:40:14", "remaining_time": "0:19:11", "throughput": 5479.25, "total_tokens": 32956160} {"current_steps": 54110, "total_steps": 64460, "loss": 0.0943, "lr": 7.65134430711908e-07, "epoch": 16.788706174371704, "percentage": 83.94, "elapsed_time": "1:40:15", "remaining_time": "0:19:10", "throughput": 5479.3, "total_tokens": 32959136} {"current_steps": 54115, "total_steps": 64460, "loss": 0.277, "lr": 7.644148532645284e-07, "epoch": 16.79025752404592, "percentage": 83.95, "elapsed_time": "1:40:15", "remaining_time": "0:19:10", "throughput": 5479.44, "total_tokens": 32963616} {"current_steps": 54120, "total_steps": 64460, "loss": 0.1519, "lr": 7.636955863356977e-07, "epoch": 16.791808873720136, "percentage": 83.96, "elapsed_time": "1:40:16", "remaining_time": "0:19:09", "throughput": 5479.47, "total_tokens": 32966496} {"current_steps": 54125, "total_steps": 64460, "loss": 0.1307, "lr": 7.629766299781449e-07, "epoch": 16.79336022339435, "percentage": 83.97, "elapsed_time": "1:40:16", "remaining_time": "0:19:08", "throughput": 5479.54, "total_tokens": 32969952} {"current_steps": 54130, "total_steps": 64460, "loss": 0.1749, "lr": 7.622579842445799e-07, "epoch": 16.79491157306857, "percentage": 83.97, "elapsed_time": "1:40:17", "remaining_time": "0:19:08", "throughput": 5479.56, "total_tokens": 32973216} {"current_steps": 54135, "total_steps": 64460, "loss": 0.2373, "lr": 7.615396491876859e-07, "epoch": 16.796462922742787, "percentage": 83.98, "elapsed_time": "1:40:18", "remaining_time": "0:19:07", "throughput": 5479.6, "total_tokens": 32976384} {"current_steps": 54140, "total_steps": 64460, "loss": 0.1734, "lr": 7.608216248601274e-07, "epoch": 16.798014272417003, "percentage": 83.99, "elapsed_time": "1:40:18", "remaining_time": "0:19:07", "throughput": 5479.65, "total_tokens": 32979744} {"current_steps": 54145, "total_steps": 64460, "loss": 0.1209, "lr": 7.601039113145425e-07, "epoch": 16.79956562209122, "percentage": 84.0, "elapsed_time": "1:40:19", "remaining_time": "0:19:06", "throughput": 5479.85, "total_tokens": 32985504} {"current_steps": 54150, "total_steps": 64460, "loss": 0.1517, "lr": 7.593865086035501e-07, "epoch": 16.801116971765435, "percentage": 84.01, "elapsed_time": "1:40:19", "remaining_time": "0:19:06", "throughput": 5479.89, "total_tokens": 32988736} {"current_steps": 54155, "total_steps": 64460, "loss": 0.1527, "lr": 7.586694167797415e-07, "epoch": 16.802668321439654, "percentage": 84.01, "elapsed_time": "1:40:20", "remaining_time": "0:19:05", "throughput": 5479.85, "total_tokens": 32991136} {"current_steps": 54160, "total_steps": 64460, "loss": 0.1057, "lr": 7.57952635895689e-07, "epoch": 16.80421967111387, "percentage": 84.02, "elapsed_time": "1:40:20", "remaining_time": "0:19:05", "throughput": 5479.89, "total_tokens": 32993984} {"current_steps": 54165, "total_steps": 64460, "loss": 0.1293, "lr": 7.572361660039434e-07, "epoch": 16.805771020788086, "percentage": 84.03, "elapsed_time": "1:40:21", "remaining_time": "0:19:04", "throughput": 5480.03, "total_tokens": 32998912} {"current_steps": 54170, "total_steps": 64460, "loss": 0.1462, "lr": 7.565200071570278e-07, "epoch": 16.807322370462302, "percentage": 84.04, "elapsed_time": "1:40:22", "remaining_time": "0:19:03", "throughput": 5480.09, "total_tokens": 33002304} {"current_steps": 54175, "total_steps": 64460, "loss": 0.1431, "lr": 7.558041594074466e-07, "epoch": 16.808873720136518, "percentage": 84.04, "elapsed_time": "1:40:22", "remaining_time": "0:19:03", "throughput": 5480.18, "total_tokens": 33006304} {"current_steps": 54180, "total_steps": 64460, "loss": 0.201, "lr": 7.550886228076787e-07, "epoch": 16.810425069810734, "percentage": 84.05, "elapsed_time": "1:40:23", "remaining_time": "0:19:02", "throughput": 5480.14, "total_tokens": 33008864} {"current_steps": 54185, "total_steps": 64460, "loss": 0.1821, "lr": 7.543733974101825e-07, "epoch": 16.811976419484953, "percentage": 84.06, "elapsed_time": "1:40:23", "remaining_time": "0:19:02", "throughput": 5480.1, "total_tokens": 33011232} {"current_steps": 54190, "total_steps": 64460, "loss": 0.1306, "lr": 7.53658483267391e-07, "epoch": 16.81352776915917, "percentage": 84.07, "elapsed_time": "1:40:24", "remaining_time": "0:19:01", "throughput": 5480.27, "total_tokens": 33016288} {"current_steps": 54195, "total_steps": 64460, "loss": 0.1941, "lr": 7.529438804317185e-07, "epoch": 16.815079118833385, "percentage": 84.08, "elapsed_time": "1:40:25", "remaining_time": "0:19:01", "throughput": 5480.23, "total_tokens": 33018720} {"current_steps": 54200, "total_steps": 64460, "loss": 0.2147, "lr": 7.522295889555508e-07, "epoch": 16.8166304685076, "percentage": 84.08, "elapsed_time": "1:40:25", "remaining_time": "0:19:00", "throughput": 5480.17, "total_tokens": 33020960} {"current_steps": 54205, "total_steps": 64460, "loss": 0.1716, "lr": 7.515156088912567e-07, "epoch": 16.818181818181817, "percentage": 84.09, "elapsed_time": "1:40:26", "remaining_time": "0:19:00", "throughput": 5480.19, "total_tokens": 33023872} {"current_steps": 54210, "total_steps": 64460, "loss": 0.2481, "lr": 7.508019402911765e-07, "epoch": 16.819733167856036, "percentage": 84.1, "elapsed_time": "1:40:26", "remaining_time": "0:18:59", "throughput": 5480.18, "total_tokens": 33026592} {"current_steps": 54215, "total_steps": 64460, "loss": 0.1502, "lr": 7.500885832076332e-07, "epoch": 16.821284517530252, "percentage": 84.11, "elapsed_time": "1:40:27", "remaining_time": "0:18:58", "throughput": 5480.19, "total_tokens": 33029408} {"current_steps": 54220, "total_steps": 64460, "loss": 0.1179, "lr": 7.493755376929224e-07, "epoch": 16.822835867204468, "percentage": 84.11, "elapsed_time": "1:40:27", "remaining_time": "0:18:58", "throughput": 5480.24, "total_tokens": 33032608} {"current_steps": 54225, "total_steps": 64460, "loss": 0.1918, "lr": 7.486628037993199e-07, "epoch": 16.824387216878684, "percentage": 84.12, "elapsed_time": "1:40:28", "remaining_time": "0:18:57", "throughput": 5480.25, "total_tokens": 33035392} {"current_steps": 54230, "total_steps": 64460, "loss": 0.151, "lr": 7.479503815790779e-07, "epoch": 16.8259385665529, "percentage": 84.13, "elapsed_time": "1:40:28", "remaining_time": "0:18:57", "throughput": 5480.19, "total_tokens": 33037824} {"current_steps": 54235, "total_steps": 64460, "loss": 0.2081, "lr": 7.472382710844239e-07, "epoch": 16.82748991622712, "percentage": 84.14, "elapsed_time": "1:40:29", "remaining_time": "0:18:56", "throughput": 5480.11, "total_tokens": 33040000} {"current_steps": 54240, "total_steps": 64460, "loss": 0.1358, "lr": 7.465264723675658e-07, "epoch": 16.829041265901335, "percentage": 84.15, "elapsed_time": "1:40:29", "remaining_time": "0:18:56", "throughput": 5480.09, "total_tokens": 33042880} {"current_steps": 54245, "total_steps": 64460, "loss": 0.1378, "lr": 7.458149854806846e-07, "epoch": 16.83059261557555, "percentage": 84.15, "elapsed_time": "1:40:30", "remaining_time": "0:18:55", "throughput": 5480.18, "total_tokens": 33047008} {"current_steps": 54250, "total_steps": 64460, "loss": 0.1352, "lr": 7.451038104759434e-07, "epoch": 16.832143965249767, "percentage": 84.16, "elapsed_time": "1:40:30", "remaining_time": "0:18:55", "throughput": 5480.2, "total_tokens": 33049888} {"current_steps": 54255, "total_steps": 64460, "loss": 0.2769, "lr": 7.443929474054773e-07, "epoch": 16.833695314923983, "percentage": 84.17, "elapsed_time": "1:40:31", "remaining_time": "0:18:54", "throughput": 5480.2, "total_tokens": 33052736} {"current_steps": 54260, "total_steps": 64460, "loss": 0.1277, "lr": 7.436823963214035e-07, "epoch": 16.835246664598202, "percentage": 84.18, "elapsed_time": "1:40:31", "remaining_time": "0:18:53", "throughput": 5480.28, "total_tokens": 33056416} {"current_steps": 54265, "total_steps": 64460, "loss": 0.1276, "lr": 7.429721572758108e-07, "epoch": 16.836798014272418, "percentage": 84.18, "elapsed_time": "1:40:32", "remaining_time": "0:18:53", "throughput": 5480.32, "total_tokens": 33059872} {"current_steps": 54270, "total_steps": 64460, "loss": 0.2235, "lr": 7.42262230320771e-07, "epoch": 16.838349363946634, "percentage": 84.19, "elapsed_time": "1:40:32", "remaining_time": "0:18:52", "throughput": 5480.39, "total_tokens": 33063072} {"current_steps": 54275, "total_steps": 64460, "loss": 0.204, "lr": 7.415526155083281e-07, "epoch": 16.83990071362085, "percentage": 84.2, "elapsed_time": "1:40:33", "remaining_time": "0:18:52", "throughput": 5480.44, "total_tokens": 33066304} {"current_steps": 54280, "total_steps": 64460, "loss": 0.2688, "lr": 7.408433128905057e-07, "epoch": 16.841452063295065, "percentage": 84.21, "elapsed_time": "1:40:34", "remaining_time": "0:18:51", "throughput": 5480.45, "total_tokens": 33069120} {"current_steps": 54285, "total_steps": 64460, "loss": 0.0982, "lr": 7.401343225193053e-07, "epoch": 16.843003412969285, "percentage": 84.22, "elapsed_time": "1:40:34", "remaining_time": "0:18:51", "throughput": 5480.42, "total_tokens": 33071680} {"current_steps": 54290, "total_steps": 64460, "loss": 0.1746, "lr": 7.394256444467024e-07, "epoch": 16.8445547626435, "percentage": 84.22, "elapsed_time": "1:40:35", "remaining_time": "0:18:50", "throughput": 5480.39, "total_tokens": 33074432} {"current_steps": 54295, "total_steps": 64460, "loss": 0.1935, "lr": 7.387172787246539e-07, "epoch": 16.846106112317717, "percentage": 84.23, "elapsed_time": "1:40:35", "remaining_time": "0:18:49", "throughput": 5480.35, "total_tokens": 33076768} {"current_steps": 54300, "total_steps": 64460, "loss": 0.2101, "lr": 7.380092254050891e-07, "epoch": 16.847657461991933, "percentage": 84.24, "elapsed_time": "1:40:35", "remaining_time": "0:18:49", "throughput": 5480.32, "total_tokens": 33079200} {"current_steps": 54305, "total_steps": 64460, "loss": 0.1416, "lr": 7.373014845399185e-07, "epoch": 16.84920881166615, "percentage": 84.25, "elapsed_time": "1:40:36", "remaining_time": "0:18:48", "throughput": 5480.41, "total_tokens": 33082624} {"current_steps": 54310, "total_steps": 64460, "loss": 0.1927, "lr": 7.365940561810253e-07, "epoch": 16.850760161340368, "percentage": 84.25, "elapsed_time": "1:40:37", "remaining_time": "0:18:48", "throughput": 5480.43, "total_tokens": 33086304} {"current_steps": 54315, "total_steps": 64460, "loss": 0.1818, "lr": 7.358869403802759e-07, "epoch": 16.852311511014584, "percentage": 84.26, "elapsed_time": "1:40:37", "remaining_time": "0:18:47", "throughput": 5480.51, "total_tokens": 33090080} {"current_steps": 54320, "total_steps": 64460, "loss": 0.2153, "lr": 7.351801371895068e-07, "epoch": 16.8538628606888, "percentage": 84.27, "elapsed_time": "1:40:38", "remaining_time": "0:18:47", "throughput": 5480.47, "total_tokens": 33092448} {"current_steps": 54325, "total_steps": 64460, "loss": 0.1739, "lr": 7.344736466605385e-07, "epoch": 16.855414210363016, "percentage": 84.28, "elapsed_time": "1:40:38", "remaining_time": "0:18:46", "throughput": 5480.45, "total_tokens": 33095104} {"current_steps": 54330, "total_steps": 64460, "loss": 0.186, "lr": 7.337674688451612e-07, "epoch": 16.85696556003723, "percentage": 84.28, "elapsed_time": "1:40:39", "remaining_time": "0:18:46", "throughput": 5480.59, "total_tokens": 33099104} {"current_steps": 54335, "total_steps": 64460, "loss": 0.115, "lr": 7.330616037951499e-07, "epoch": 16.858516909711447, "percentage": 84.29, "elapsed_time": "1:40:39", "remaining_time": "0:18:45", "throughput": 5480.62, "total_tokens": 33102080} {"current_steps": 54340, "total_steps": 64460, "loss": 0.2173, "lr": 7.323560515622502e-07, "epoch": 16.860068259385667, "percentage": 84.3, "elapsed_time": "1:40:40", "remaining_time": "0:18:44", "throughput": 5480.61, "total_tokens": 33104736} {"current_steps": 54345, "total_steps": 64460, "loss": 0.2343, "lr": 7.31650812198188e-07, "epoch": 16.861619609059883, "percentage": 84.31, "elapsed_time": "1:40:40", "remaining_time": "0:18:44", "throughput": 5480.61, "total_tokens": 33107776} {"current_steps": 54350, "total_steps": 64460, "loss": 0.1504, "lr": 7.309458857546675e-07, "epoch": 16.8631709587341, "percentage": 84.32, "elapsed_time": "1:40:41", "remaining_time": "0:18:43", "throughput": 5480.66, "total_tokens": 33110880} {"current_steps": 54355, "total_steps": 64460, "loss": 0.1706, "lr": 7.302412722833651e-07, "epoch": 16.864722308408314, "percentage": 84.32, "elapsed_time": "1:40:41", "remaining_time": "0:18:43", "throughput": 5480.69, "total_tokens": 33113984} {"current_steps": 54360, "total_steps": 64460, "loss": 0.1227, "lr": 7.295369718359408e-07, "epoch": 16.86627365808253, "percentage": 84.33, "elapsed_time": "1:40:42", "remaining_time": "0:18:42", "throughput": 5480.72, "total_tokens": 33117376} {"current_steps": 54365, "total_steps": 64460, "loss": 0.155, "lr": 7.288329844640246e-07, "epoch": 16.86782500775675, "percentage": 84.34, "elapsed_time": "1:40:43", "remaining_time": "0:18:42", "throughput": 5480.78, "total_tokens": 33121568} {"current_steps": 54370, "total_steps": 64460, "loss": 0.2135, "lr": 7.281293102192299e-07, "epoch": 16.869376357430966, "percentage": 84.35, "elapsed_time": "1:40:43", "remaining_time": "0:18:41", "throughput": 5480.78, "total_tokens": 33124224} {"current_steps": 54375, "total_steps": 64460, "loss": 0.142, "lr": 7.274259491531427e-07, "epoch": 16.87092770710518, "percentage": 84.35, "elapsed_time": "1:40:44", "remaining_time": "0:18:41", "throughput": 5480.81, "total_tokens": 33127072} {"current_steps": 54380, "total_steps": 64460, "loss": 0.104, "lr": 7.267229013173294e-07, "epoch": 16.872479056779397, "percentage": 84.36, "elapsed_time": "1:40:44", "remaining_time": "0:18:40", "throughput": 5480.81, "total_tokens": 33130304} {"current_steps": 54385, "total_steps": 64460, "loss": 0.2408, "lr": 7.260201667633287e-07, "epoch": 16.874030406453613, "percentage": 84.37, "elapsed_time": "1:40:45", "remaining_time": "0:18:39", "throughput": 5480.83, "total_tokens": 33133760} {"current_steps": 54390, "total_steps": 64460, "loss": 0.2718, "lr": 7.253177455426629e-07, "epoch": 16.875581756127833, "percentage": 84.38, "elapsed_time": "1:40:45", "remaining_time": "0:18:39", "throughput": 5480.8, "total_tokens": 33136416} {"current_steps": 54395, "total_steps": 64460, "loss": 0.2005, "lr": 7.246156377068253e-07, "epoch": 16.87713310580205, "percentage": 84.39, "elapsed_time": "1:40:46", "remaining_time": "0:18:38", "throughput": 5480.84, "total_tokens": 33139456} {"current_steps": 54400, "total_steps": 64460, "loss": 0.1473, "lr": 7.239138433072889e-07, "epoch": 16.878684455476265, "percentage": 84.39, "elapsed_time": "1:40:47", "remaining_time": "0:18:38", "throughput": 5480.91, "total_tokens": 33143104} {"current_steps": 54405, "total_steps": 64460, "loss": 0.1976, "lr": 7.232123623955062e-07, "epoch": 16.88023580515048, "percentage": 84.4, "elapsed_time": "1:40:47", "remaining_time": "0:18:37", "throughput": 5480.94, "total_tokens": 33146272} {"current_steps": 54410, "total_steps": 64460, "loss": 0.1535, "lr": 7.225111950229002e-07, "epoch": 16.881787154824696, "percentage": 84.41, "elapsed_time": "1:40:48", "remaining_time": "0:18:37", "throughput": 5480.91, "total_tokens": 33148832} {"current_steps": 54415, "total_steps": 64460, "loss": 0.2388, "lr": 7.218103412408783e-07, "epoch": 16.883338504498916, "percentage": 84.42, "elapsed_time": "1:40:48", "remaining_time": "0:18:36", "throughput": 5480.87, "total_tokens": 33151392} {"current_steps": 54420, "total_steps": 64460, "loss": 0.2591, "lr": 7.211098011008183e-07, "epoch": 16.88488985417313, "percentage": 84.42, "elapsed_time": "1:40:49", "remaining_time": "0:18:36", "throughput": 5480.86, "total_tokens": 33154176} {"current_steps": 54425, "total_steps": 64460, "loss": 0.1913, "lr": 7.204095746540807e-07, "epoch": 16.886441203847347, "percentage": 84.43, "elapsed_time": "1:40:49", "remaining_time": "0:18:35", "throughput": 5480.9, "total_tokens": 33157472} {"current_steps": 54430, "total_steps": 64460, "loss": 0.1032, "lr": 7.197096619519983e-07, "epoch": 16.887992553521563, "percentage": 84.44, "elapsed_time": "1:40:50", "remaining_time": "0:18:34", "throughput": 5480.84, "total_tokens": 33159872} {"current_steps": 54435, "total_steps": 64460, "loss": 0.1315, "lr": 7.190100630458846e-07, "epoch": 16.88954390319578, "percentage": 84.45, "elapsed_time": "1:40:50", "remaining_time": "0:18:34", "throughput": 5480.8, "total_tokens": 33162208} {"current_steps": 54440, "total_steps": 64460, "loss": 0.1707, "lr": 7.183107779870268e-07, "epoch": 16.891095252869995, "percentage": 84.46, "elapsed_time": "1:40:51", "remaining_time": "0:18:33", "throughput": 5480.76, "total_tokens": 33164832} {"current_steps": 54445, "total_steps": 64460, "loss": 0.1672, "lr": 7.17611806826693e-07, "epoch": 16.892646602544215, "percentage": 84.46, "elapsed_time": "1:40:51", "remaining_time": "0:18:33", "throughput": 5480.67, "total_tokens": 33166976} {"current_steps": 54450, "total_steps": 64460, "loss": 0.1521, "lr": 7.169131496161235e-07, "epoch": 16.89419795221843, "percentage": 84.47, "elapsed_time": "1:40:52", "remaining_time": "0:18:32", "throughput": 5480.8, "total_tokens": 33171456} {"current_steps": 54455, "total_steps": 64460, "loss": 0.1172, "lr": 7.16214806406541e-07, "epoch": 16.895749301892646, "percentage": 84.48, "elapsed_time": "1:40:52", "remaining_time": "0:18:32", "throughput": 5480.86, "total_tokens": 33174784} {"current_steps": 54460, "total_steps": 64460, "loss": 0.1651, "lr": 7.155167772491394e-07, "epoch": 16.897300651566862, "percentage": 84.49, "elapsed_time": "1:40:53", "remaining_time": "0:18:31", "throughput": 5480.78, "total_tokens": 33177120} {"current_steps": 54465, "total_steps": 64460, "loss": 0.1822, "lr": 7.14819062195094e-07, "epoch": 16.898852001241078, "percentage": 84.49, "elapsed_time": "1:40:53", "remaining_time": "0:18:30", "throughput": 5480.73, "total_tokens": 33179456} {"current_steps": 54470, "total_steps": 64460, "loss": 0.1463, "lr": 7.141216612955565e-07, "epoch": 16.900403350915298, "percentage": 84.5, "elapsed_time": "1:40:54", "remaining_time": "0:18:30", "throughput": 5480.7, "total_tokens": 33182176} {"current_steps": 54475, "total_steps": 64460, "loss": 0.2703, "lr": 7.134245746016527e-07, "epoch": 16.901954700589513, "percentage": 84.51, "elapsed_time": "1:40:54", "remaining_time": "0:18:29", "throughput": 5480.71, "total_tokens": 33185120} {"current_steps": 54480, "total_steps": 64460, "loss": 0.2329, "lr": 7.12727802164489e-07, "epoch": 16.90350605026373, "percentage": 84.52, "elapsed_time": "1:40:55", "remaining_time": "0:18:29", "throughput": 5480.78, "total_tokens": 33188704} {"current_steps": 54485, "total_steps": 64460, "loss": 0.1703, "lr": 7.120313440351456e-07, "epoch": 16.905057399937945, "percentage": 84.53, "elapsed_time": "1:40:55", "remaining_time": "0:18:28", "throughput": 5480.83, "total_tokens": 33191680} {"current_steps": 54490, "total_steps": 64460, "loss": 0.1569, "lr": 7.113352002646828e-07, "epoch": 16.90660874961216, "percentage": 84.53, "elapsed_time": "1:40:56", "remaining_time": "0:18:28", "throughput": 5480.82, "total_tokens": 33194240} {"current_steps": 54495, "total_steps": 64460, "loss": 0.1534, "lr": 7.106393709041337e-07, "epoch": 16.90816009928638, "percentage": 84.54, "elapsed_time": "1:40:56", "remaining_time": "0:18:27", "throughput": 5480.67, "total_tokens": 33196320} {"current_steps": 54500, "total_steps": 64460, "loss": 0.1913, "lr": 7.099438560045141e-07, "epoch": 16.909711448960596, "percentage": 84.55, "elapsed_time": "1:40:57", "remaining_time": "0:18:27", "throughput": 5480.65, "total_tokens": 33198912} {"current_steps": 54505, "total_steps": 64460, "loss": 0.1471, "lr": 7.092486556168099e-07, "epoch": 16.911262798634812, "percentage": 84.56, "elapsed_time": "1:40:57", "remaining_time": "0:18:26", "throughput": 5480.64, "total_tokens": 33201472} {"current_steps": 54510, "total_steps": 64460, "loss": 0.2052, "lr": 7.085537697919908e-07, "epoch": 16.912814148309028, "percentage": 84.56, "elapsed_time": "1:40:58", "remaining_time": "0:18:25", "throughput": 5480.63, "total_tokens": 33203968} {"current_steps": 54515, "total_steps": 64460, "loss": 0.1272, "lr": 7.078591985809979e-07, "epoch": 16.914365497983244, "percentage": 84.57, "elapsed_time": "1:40:58", "remaining_time": "0:18:25", "throughput": 5480.66, "total_tokens": 33206880} {"current_steps": 54520, "total_steps": 64460, "loss": 0.1347, "lr": 7.07164942034752e-07, "epoch": 16.915916847657464, "percentage": 84.58, "elapsed_time": "1:40:59", "remaining_time": "0:18:24", "throughput": 5480.73, "total_tokens": 33210528} {"current_steps": 54525, "total_steps": 64460, "loss": 0.2169, "lr": 7.064710002041514e-07, "epoch": 16.91746819733168, "percentage": 84.59, "elapsed_time": "1:40:59", "remaining_time": "0:18:24", "throughput": 5480.66, "total_tokens": 33212768} {"current_steps": 54530, "total_steps": 64460, "loss": 0.1617, "lr": 7.057773731400691e-07, "epoch": 16.919019547005895, "percentage": 84.6, "elapsed_time": "1:41:00", "remaining_time": "0:18:23", "throughput": 5480.63, "total_tokens": 33215328} {"current_steps": 54535, "total_steps": 64460, "loss": 0.2148, "lr": 7.050840608933568e-07, "epoch": 16.92057089668011, "percentage": 84.6, "elapsed_time": "1:41:00", "remaining_time": "0:18:23", "throughput": 5480.63, "total_tokens": 33217952} {"current_steps": 54540, "total_steps": 64460, "loss": 0.1031, "lr": 7.043910635148422e-07, "epoch": 16.922122246354327, "percentage": 84.61, "elapsed_time": "1:41:01", "remaining_time": "0:18:22", "throughput": 5480.62, "total_tokens": 33220896} {"current_steps": 54545, "total_steps": 64460, "loss": 0.1518, "lr": 7.036983810553305e-07, "epoch": 16.923673596028546, "percentage": 84.62, "elapsed_time": "1:41:02", "remaining_time": "0:18:21", "throughput": 5480.64, "total_tokens": 33224288} {"current_steps": 54550, "total_steps": 64460, "loss": 0.1477, "lr": 7.030060135656025e-07, "epoch": 16.925224945702762, "percentage": 84.63, "elapsed_time": "1:41:02", "remaining_time": "0:18:21", "throughput": 5480.66, "total_tokens": 33226976} {"current_steps": 54555, "total_steps": 64460, "loss": 0.2312, "lr": 7.023139610964186e-07, "epoch": 16.92677629537698, "percentage": 84.63, "elapsed_time": "1:41:03", "remaining_time": "0:18:20", "throughput": 5480.67, "total_tokens": 33229696} {"current_steps": 54560, "total_steps": 64460, "loss": 0.1532, "lr": 7.016222236985126e-07, "epoch": 16.928327645051194, "percentage": 84.64, "elapsed_time": "1:41:03", "remaining_time": "0:18:20", "throughput": 5480.77, "total_tokens": 33234048} {"current_steps": 54565, "total_steps": 64460, "loss": 0.1455, "lr": 7.009308014225991e-07, "epoch": 16.92987899472541, "percentage": 84.65, "elapsed_time": "1:41:04", "remaining_time": "0:18:19", "throughput": 5480.84, "total_tokens": 33237600} {"current_steps": 54570, "total_steps": 64460, "loss": 0.1817, "lr": 7.002396943193657e-07, "epoch": 16.93143034439963, "percentage": 84.66, "elapsed_time": "1:41:04", "remaining_time": "0:18:19", "throughput": 5480.88, "total_tokens": 33240832} {"current_steps": 54575, "total_steps": 64460, "loss": 0.2007, "lr": 6.995489024394803e-07, "epoch": 16.932981694073845, "percentage": 84.66, "elapsed_time": "1:41:05", "remaining_time": "0:18:18", "throughput": 5480.99, "total_tokens": 33244960} {"current_steps": 54580, "total_steps": 64460, "loss": 0.1726, "lr": 6.98858425833584e-07, "epoch": 16.93453304374806, "percentage": 84.67, "elapsed_time": "1:41:06", "remaining_time": "0:18:18", "throughput": 5481.04, "total_tokens": 33248288} {"current_steps": 54585, "total_steps": 64460, "loss": 0.1336, "lr": 6.981682645522985e-07, "epoch": 16.936084393422277, "percentage": 84.68, "elapsed_time": "1:41:06", "remaining_time": "0:18:17", "throughput": 5481.06, "total_tokens": 33251328} {"current_steps": 54590, "total_steps": 64460, "loss": 0.0969, "lr": 6.974784186462202e-07, "epoch": 16.937635743096493, "percentage": 84.69, "elapsed_time": "1:41:07", "remaining_time": "0:18:16", "throughput": 5481.15, "total_tokens": 33255520} {"current_steps": 54595, "total_steps": 64460, "loss": 0.2892, "lr": 6.967888881659251e-07, "epoch": 16.93918709277071, "percentage": 84.7, "elapsed_time": "1:41:07", "remaining_time": "0:18:16", "throughput": 5481.05, "total_tokens": 33257696} {"current_steps": 54600, "total_steps": 64460, "loss": 0.1912, "lr": 6.960996731619607e-07, "epoch": 16.94073844244493, "percentage": 84.7, "elapsed_time": "1:41:08", "remaining_time": "0:18:15", "throughput": 5481.11, "total_tokens": 33261120} {"current_steps": 54605, "total_steps": 64460, "loss": 0.2031, "lr": 6.954107736848558e-07, "epoch": 16.942289792119144, "percentage": 84.71, "elapsed_time": "1:41:08", "remaining_time": "0:18:15", "throughput": 5481.18, "total_tokens": 33264704} {"current_steps": 54610, "total_steps": 64460, "loss": 0.247, "lr": 6.947221897851164e-07, "epoch": 16.94384114179336, "percentage": 84.72, "elapsed_time": "1:41:09", "remaining_time": "0:18:14", "throughput": 5481.13, "total_tokens": 33267200} {"current_steps": 54615, "total_steps": 64460, "loss": 0.1099, "lr": 6.940339215132213e-07, "epoch": 16.945392491467576, "percentage": 84.73, "elapsed_time": "1:41:10", "remaining_time": "0:18:14", "throughput": 5481.25, "total_tokens": 33271264} {"current_steps": 54620, "total_steps": 64460, "loss": 0.2303, "lr": 6.933459689196315e-07, "epoch": 16.946943841141792, "percentage": 84.73, "elapsed_time": "1:41:10", "remaining_time": "0:18:13", "throughput": 5481.21, "total_tokens": 33273792} {"current_steps": 54625, "total_steps": 64460, "loss": 0.1665, "lr": 6.926583320547792e-07, "epoch": 16.94849519081601, "percentage": 84.74, "elapsed_time": "1:41:11", "remaining_time": "0:18:13", "throughput": 5481.23, "total_tokens": 33276704} {"current_steps": 54630, "total_steps": 64460, "loss": 0.2376, "lr": 6.919710109690792e-07, "epoch": 16.950046540490227, "percentage": 84.75, "elapsed_time": "1:41:11", "remaining_time": "0:18:12", "throughput": 5481.2, "total_tokens": 33279264} {"current_steps": 54635, "total_steps": 64460, "loss": 0.1172, "lr": 6.912840057129172e-07, "epoch": 16.951597890164443, "percentage": 84.76, "elapsed_time": "1:41:12", "remaining_time": "0:18:11", "throughput": 5481.25, "total_tokens": 33282656} {"current_steps": 54640, "total_steps": 64460, "loss": 0.1225, "lr": 6.905973163366619e-07, "epoch": 16.95314923983866, "percentage": 84.77, "elapsed_time": "1:41:12", "remaining_time": "0:18:11", "throughput": 5481.25, "total_tokens": 33285824} {"current_steps": 54645, "total_steps": 64460, "loss": 0.2942, "lr": 6.899109428906531e-07, "epoch": 16.954700589512875, "percentage": 84.77, "elapsed_time": "1:41:13", "remaining_time": "0:18:10", "throughput": 5481.37, "total_tokens": 33290336} {"current_steps": 54650, "total_steps": 64460, "loss": 0.1782, "lr": 6.892248854252121e-07, "epoch": 16.956251939187094, "percentage": 84.78, "elapsed_time": "1:41:13", "remaining_time": "0:18:10", "throughput": 5481.4, "total_tokens": 33293440} {"current_steps": 54655, "total_steps": 64460, "loss": 0.143, "lr": 6.88539143990633e-07, "epoch": 16.95780328886131, "percentage": 84.79, "elapsed_time": "1:41:14", "remaining_time": "0:18:09", "throughput": 5481.5, "total_tokens": 33297312} {"current_steps": 54660, "total_steps": 64460, "loss": 0.2001, "lr": 6.878537186371914e-07, "epoch": 16.959354638535526, "percentage": 84.8, "elapsed_time": "1:41:15", "remaining_time": "0:18:09", "throughput": 5481.58, "total_tokens": 33301152} {"current_steps": 54665, "total_steps": 64460, "loss": 0.1827, "lr": 6.871686094151348e-07, "epoch": 16.960905988209742, "percentage": 84.8, "elapsed_time": "1:41:15", "remaining_time": "0:18:08", "throughput": 5481.5, "total_tokens": 33303328} {"current_steps": 54670, "total_steps": 64460, "loss": 0.1021, "lr": 6.864838163746906e-07, "epoch": 16.962457337883958, "percentage": 84.81, "elapsed_time": "1:41:16", "remaining_time": "0:18:08", "throughput": 5481.59, "total_tokens": 33306752} {"current_steps": 54675, "total_steps": 64460, "loss": 0.2622, "lr": 6.857993395660633e-07, "epoch": 16.964008687558177, "percentage": 84.82, "elapsed_time": "1:41:16", "remaining_time": "0:18:07", "throughput": 5481.71, "total_tokens": 33311520} {"current_steps": 54680, "total_steps": 64460, "loss": 0.1404, "lr": 6.851151790394311e-07, "epoch": 16.965560037232393, "percentage": 84.83, "elapsed_time": "1:41:17", "remaining_time": "0:18:06", "throughput": 5481.81, "total_tokens": 33315168} {"current_steps": 54685, "total_steps": 64460, "loss": 0.2888, "lr": 6.844313348449533e-07, "epoch": 16.96711138690661, "percentage": 84.84, "elapsed_time": "1:41:17", "remaining_time": "0:18:06", "throughput": 5481.81, "total_tokens": 33317984} {"current_steps": 54690, "total_steps": 64460, "loss": 0.0997, "lr": 6.837478070327613e-07, "epoch": 16.968662736580825, "percentage": 84.84, "elapsed_time": "1:41:18", "remaining_time": "0:18:05", "throughput": 5481.81, "total_tokens": 33320672} {"current_steps": 54695, "total_steps": 64460, "loss": 0.2364, "lr": 6.83064595652968e-07, "epoch": 16.97021408625504, "percentage": 84.85, "elapsed_time": "1:41:18", "remaining_time": "0:18:05", "throughput": 5481.87, "total_tokens": 33324032} {"current_steps": 54700, "total_steps": 64460, "loss": 0.162, "lr": 6.823817007556594e-07, "epoch": 16.971765435929257, "percentage": 84.86, "elapsed_time": "1:41:19", "remaining_time": "0:18:04", "throughput": 5481.95, "total_tokens": 33327200} {"current_steps": 54705, "total_steps": 64460, "loss": 0.1707, "lr": 6.816991223909014e-07, "epoch": 16.973316785603476, "percentage": 84.87, "elapsed_time": "1:41:19", "remaining_time": "0:18:04", "throughput": 5481.94, "total_tokens": 33329920} {"current_steps": 54710, "total_steps": 64460, "loss": 0.1535, "lr": 6.81016860608733e-07, "epoch": 16.974868135277692, "percentage": 84.87, "elapsed_time": "1:41:20", "remaining_time": "0:18:03", "throughput": 5481.98, "total_tokens": 33333408} {"current_steps": 54715, "total_steps": 64460, "loss": 0.1699, "lr": 6.803349154591743e-07, "epoch": 16.976419484951908, "percentage": 84.88, "elapsed_time": "1:41:21", "remaining_time": "0:18:03", "throughput": 5482.06, "total_tokens": 33337152} {"current_steps": 54720, "total_steps": 64460, "loss": 0.1543, "lr": 6.796532869922173e-07, "epoch": 16.977970834626124, "percentage": 84.89, "elapsed_time": "1:41:21", "remaining_time": "0:18:02", "throughput": 5482.03, "total_tokens": 33339872} {"current_steps": 54725, "total_steps": 64460, "loss": 0.1551, "lr": 6.789719752578355e-07, "epoch": 16.97952218430034, "percentage": 84.9, "elapsed_time": "1:41:22", "remaining_time": "0:18:01", "throughput": 5482.11, "total_tokens": 33343936} {"current_steps": 54730, "total_steps": 64460, "loss": 0.1602, "lr": 6.782909803059772e-07, "epoch": 16.98107353397456, "percentage": 84.91, "elapsed_time": "1:41:22", "remaining_time": "0:18:01", "throughput": 5482.08, "total_tokens": 33346880} {"current_steps": 54735, "total_steps": 64460, "loss": 0.138, "lr": 6.776103021865654e-07, "epoch": 16.982624883648775, "percentage": 84.91, "elapsed_time": "1:41:23", "remaining_time": "0:18:00", "throughput": 5482.1, "total_tokens": 33349728} {"current_steps": 54740, "total_steps": 64460, "loss": 0.2957, "lr": 6.76929940949505e-07, "epoch": 16.98417623332299, "percentage": 84.92, "elapsed_time": "1:41:23", "remaining_time": "0:18:00", "throughput": 5482.13, "total_tokens": 33352640} {"current_steps": 54745, "total_steps": 64460, "loss": 0.2194, "lr": 6.762498966446712e-07, "epoch": 16.985727582997207, "percentage": 84.93, "elapsed_time": "1:41:24", "remaining_time": "0:17:59", "throughput": 5482.16, "total_tokens": 33355520} {"current_steps": 54750, "total_steps": 64460, "loss": 0.1779, "lr": 6.755701693219219e-07, "epoch": 16.987278932671423, "percentage": 84.94, "elapsed_time": "1:41:24", "remaining_time": "0:17:59", "throughput": 5482.2, "total_tokens": 33358528} {"current_steps": 54755, "total_steps": 64460, "loss": 0.179, "lr": 6.748907590310871e-07, "epoch": 16.988830282345642, "percentage": 84.94, "elapsed_time": "1:41:25", "remaining_time": "0:17:58", "throughput": 5482.29, "total_tokens": 33362144} {"current_steps": 54760, "total_steps": 64460, "loss": 0.1682, "lr": 6.742116658219777e-07, "epoch": 16.990381632019858, "percentage": 84.95, "elapsed_time": "1:41:25", "remaining_time": "0:17:58", "throughput": 5482.26, "total_tokens": 33364544} {"current_steps": 54765, "total_steps": 64460, "loss": 0.2815, "lr": 6.735328897443772e-07, "epoch": 16.991932981694074, "percentage": 84.96, "elapsed_time": "1:41:26", "remaining_time": "0:17:57", "throughput": 5482.28, "total_tokens": 33367424} {"current_steps": 54770, "total_steps": 64460, "loss": 0.2382, "lr": 6.7285443084805e-07, "epoch": 16.99348433136829, "percentage": 84.97, "elapsed_time": "1:41:26", "remaining_time": "0:17:56", "throughput": 5482.25, "total_tokens": 33369856} {"current_steps": 54775, "total_steps": 64460, "loss": 0.1609, "lr": 6.721762891827327e-07, "epoch": 16.995035681042506, "percentage": 84.98, "elapsed_time": "1:41:27", "remaining_time": "0:17:56", "throughput": 5482.3, "total_tokens": 33373760} {"current_steps": 54780, "total_steps": 64460, "loss": 0.1426, "lr": 6.714984647981443e-07, "epoch": 16.996587030716725, "percentage": 84.98, "elapsed_time": "1:41:28", "remaining_time": "0:17:55", "throughput": 5482.34, "total_tokens": 33377024} {"current_steps": 54785, "total_steps": 64460, "loss": 0.1365, "lr": 6.708209577439739e-07, "epoch": 16.99813838039094, "percentage": 84.99, "elapsed_time": "1:41:28", "remaining_time": "0:17:55", "throughput": 5482.3, "total_tokens": 33379296} {"current_steps": 54790, "total_steps": 64460, "loss": 0.1068, "lr": 6.701437680698925e-07, "epoch": 16.999689730065157, "percentage": 85.0, "elapsed_time": "1:41:29", "remaining_time": "0:17:54", "throughput": 5482.36, "total_tokens": 33382432} {"current_steps": 54795, "total_steps": 64460, "loss": 0.1778, "lr": 6.694668958255473e-07, "epoch": 17.001241079739373, "percentage": 85.01, "elapsed_time": "1:41:29", "remaining_time": "0:17:54", "throughput": 5482.1, "total_tokens": 33385872} {"current_steps": 54800, "total_steps": 64460, "loss": 0.1436, "lr": 6.687903410605584e-07, "epoch": 17.00279242941359, "percentage": 85.01, "elapsed_time": "1:41:30", "remaining_time": "0:17:53", "throughput": 5482.03, "total_tokens": 33388336} {"current_steps": 54805, "total_steps": 64460, "loss": 0.1373, "lr": 6.681141038245282e-07, "epoch": 17.004343779087808, "percentage": 85.02, "elapsed_time": "1:41:30", "remaining_time": "0:17:53", "throughput": 5481.99, "total_tokens": 33390608} {"current_steps": 54810, "total_steps": 64460, "loss": 0.142, "lr": 6.674381841670302e-07, "epoch": 17.005895128762024, "percentage": 85.03, "elapsed_time": "1:41:31", "remaining_time": "0:17:52", "throughput": 5481.94, "total_tokens": 33393264} {"current_steps": 54815, "total_steps": 64460, "loss": 0.1086, "lr": 6.667625821376195e-07, "epoch": 17.00744647843624, "percentage": 85.04, "elapsed_time": "1:41:32", "remaining_time": "0:17:51", "throughput": 5482.02, "total_tokens": 33396752} {"current_steps": 54820, "total_steps": 64460, "loss": 0.1625, "lr": 6.660872977858235e-07, "epoch": 17.008997828110456, "percentage": 85.04, "elapsed_time": "1:41:32", "remaining_time": "0:17:51", "throughput": 5481.99, "total_tokens": 33399184} {"current_steps": 54825, "total_steps": 64460, "loss": 0.155, "lr": 6.65412331161151e-07, "epoch": 17.01054917778467, "percentage": 85.05, "elapsed_time": "1:41:33", "remaining_time": "0:17:50", "throughput": 5482.01, "total_tokens": 33402160} {"current_steps": 54830, "total_steps": 64460, "loss": 0.1597, "lr": 6.64737682313083e-07, "epoch": 17.01210052745889, "percentage": 85.06, "elapsed_time": "1:41:33", "remaining_time": "0:17:50", "throughput": 5481.95, "total_tokens": 33404336} {"current_steps": 54835, "total_steps": 64460, "loss": 0.1476, "lr": 6.640633512910805e-07, "epoch": 17.013651877133107, "percentage": 85.07, "elapsed_time": "1:41:34", "remaining_time": "0:17:49", "throughput": 5481.98, "total_tokens": 33407664} {"current_steps": 54840, "total_steps": 64460, "loss": 0.1179, "lr": 6.633893381445788e-07, "epoch": 17.015203226807323, "percentage": 85.08, "elapsed_time": "1:41:34", "remaining_time": "0:17:49", "throughput": 5481.92, "total_tokens": 33409936} {"current_steps": 54845, "total_steps": 64460, "loss": 0.1333, "lr": 6.627156429229919e-07, "epoch": 17.01675457648154, "percentage": 85.08, "elapsed_time": "1:41:35", "remaining_time": "0:17:48", "throughput": 5481.98, "total_tokens": 33413200} {"current_steps": 54850, "total_steps": 64460, "loss": 0.2189, "lr": 6.620422656757109e-07, "epoch": 17.018305926155755, "percentage": 85.09, "elapsed_time": "1:41:35", "remaining_time": "0:17:47", "throughput": 5481.97, "total_tokens": 33415728} {"current_steps": 54855, "total_steps": 64460, "loss": 0.1963, "lr": 6.613692064520993e-07, "epoch": 17.01985727582997, "percentage": 85.1, "elapsed_time": "1:41:36", "remaining_time": "0:17:47", "throughput": 5481.95, "total_tokens": 33418352} {"current_steps": 54860, "total_steps": 64460, "loss": 0.1901, "lr": 6.60696465301503e-07, "epoch": 17.02140862550419, "percentage": 85.11, "elapsed_time": "1:41:36", "remaining_time": "0:17:46", "throughput": 5481.93, "total_tokens": 33421200} {"current_steps": 54865, "total_steps": 64460, "loss": 0.2418, "lr": 6.600240422732401e-07, "epoch": 17.022959975178406, "percentage": 85.11, "elapsed_time": "1:41:37", "remaining_time": "0:17:46", "throughput": 5481.95, "total_tokens": 33424336} {"current_steps": 54870, "total_steps": 64460, "loss": 0.2717, "lr": 6.59351937416609e-07, "epoch": 17.02451132485262, "percentage": 85.12, "elapsed_time": "1:41:37", "remaining_time": "0:17:45", "throughput": 5481.82, "total_tokens": 33426416} {"current_steps": 54875, "total_steps": 64460, "loss": 0.1453, "lr": 6.586801507808804e-07, "epoch": 17.026062674526838, "percentage": 85.13, "elapsed_time": "1:41:38", "remaining_time": "0:17:45", "throughput": 5481.83, "total_tokens": 33429168} {"current_steps": 54880, "total_steps": 64460, "loss": 0.2087, "lr": 6.580086824153071e-07, "epoch": 17.027614024201053, "percentage": 85.14, "elapsed_time": "1:41:38", "remaining_time": "0:17:44", "throughput": 5481.86, "total_tokens": 33432048} {"current_steps": 54885, "total_steps": 64460, "loss": 0.1908, "lr": 6.573375323691128e-07, "epoch": 17.029165373875273, "percentage": 85.15, "elapsed_time": "1:41:39", "remaining_time": "0:17:44", "throughput": 5481.85, "total_tokens": 33434672} {"current_steps": 54890, "total_steps": 64460, "loss": 0.1689, "lr": 6.566667006915034e-07, "epoch": 17.03071672354949, "percentage": 85.15, "elapsed_time": "1:41:39", "remaining_time": "0:17:43", "throughput": 5481.83, "total_tokens": 33437264} {"current_steps": 54895, "total_steps": 64460, "loss": 0.1737, "lr": 6.559961874316568e-07, "epoch": 17.032268073223705, "percentage": 85.16, "elapsed_time": "1:41:40", "remaining_time": "0:17:42", "throughput": 5481.81, "total_tokens": 33439760} {"current_steps": 54900, "total_steps": 64460, "loss": 0.1281, "lr": 6.553259926387312e-07, "epoch": 17.03381942289792, "percentage": 85.17, "elapsed_time": "1:41:40", "remaining_time": "0:17:42", "throughput": 5481.73, "total_tokens": 33442032} {"current_steps": 54905, "total_steps": 64460, "loss": 0.2134, "lr": 6.546561163618581e-07, "epoch": 17.035370772572136, "percentage": 85.18, "elapsed_time": "1:41:41", "remaining_time": "0:17:41", "throughput": 5481.67, "total_tokens": 33444464} {"current_steps": 54910, "total_steps": 64460, "loss": 0.1659, "lr": 6.539865586501481e-07, "epoch": 17.036922122246356, "percentage": 85.18, "elapsed_time": "1:41:41", "remaining_time": "0:17:41", "throughput": 5481.73, "total_tokens": 33447568} {"current_steps": 54915, "total_steps": 64460, "loss": 0.1615, "lr": 6.533173195526888e-07, "epoch": 17.03847347192057, "percentage": 85.19, "elapsed_time": "1:41:42", "remaining_time": "0:17:40", "throughput": 5481.82, "total_tokens": 33450992} {"current_steps": 54920, "total_steps": 64460, "loss": 0.1397, "lr": 6.526483991185411e-07, "epoch": 17.040024821594788, "percentage": 85.2, "elapsed_time": "1:41:42", "remaining_time": "0:17:40", "throughput": 5481.7, "total_tokens": 33452944} {"current_steps": 54925, "total_steps": 64460, "loss": 0.1014, "lr": 6.519797973967478e-07, "epoch": 17.041576171269003, "percentage": 85.21, "elapsed_time": "1:41:43", "remaining_time": "0:17:39", "throughput": 5481.75, "total_tokens": 33456592} {"current_steps": 54930, "total_steps": 64460, "loss": 0.1547, "lr": 6.513115144363224e-07, "epoch": 17.04312752094322, "percentage": 85.22, "elapsed_time": "1:41:43", "remaining_time": "0:17:38", "throughput": 5481.73, "total_tokens": 33458992} {"current_steps": 54935, "total_steps": 64460, "loss": 0.2117, "lr": 6.506435502862602e-07, "epoch": 17.04467887061744, "percentage": 85.22, "elapsed_time": "1:41:44", "remaining_time": "0:17:38", "throughput": 5481.77, "total_tokens": 33462480} {"current_steps": 54940, "total_steps": 64460, "loss": 0.1728, "lr": 6.499759049955284e-07, "epoch": 17.046230220291655, "percentage": 85.23, "elapsed_time": "1:41:44", "remaining_time": "0:17:37", "throughput": 5481.73, "total_tokens": 33464944} {"current_steps": 54945, "total_steps": 64460, "loss": 0.1433, "lr": 6.49308578613076e-07, "epoch": 17.04778156996587, "percentage": 85.24, "elapsed_time": "1:41:45", "remaining_time": "0:17:37", "throughput": 5481.75, "total_tokens": 33467792} {"current_steps": 54950, "total_steps": 64460, "loss": 0.165, "lr": 6.486415711878236e-07, "epoch": 17.049332919640086, "percentage": 85.25, "elapsed_time": "1:41:45", "remaining_time": "0:17:36", "throughput": 5481.69, "total_tokens": 33469936} {"current_steps": 54955, "total_steps": 64460, "loss": 0.1866, "lr": 6.479748827686732e-07, "epoch": 17.050884269314302, "percentage": 85.25, "elapsed_time": "1:41:46", "remaining_time": "0:17:36", "throughput": 5481.65, "total_tokens": 33472400} {"current_steps": 54960, "total_steps": 64460, "loss": 0.1758, "lr": 6.473085134044981e-07, "epoch": 17.052435618988522, "percentage": 85.26, "elapsed_time": "1:41:46", "remaining_time": "0:17:35", "throughput": 5481.72, "total_tokens": 33475792} {"current_steps": 54965, "total_steps": 64460, "loss": 0.1316, "lr": 6.466424631441531e-07, "epoch": 17.053986968662738, "percentage": 85.27, "elapsed_time": "1:41:47", "remaining_time": "0:17:35", "throughput": 5481.74, "total_tokens": 33478576} {"current_steps": 54970, "total_steps": 64460, "loss": 0.1451, "lr": 6.459767320364673e-07, "epoch": 17.055538318336954, "percentage": 85.28, "elapsed_time": "1:41:47", "remaining_time": "0:17:34", "throughput": 5481.73, "total_tokens": 33481296} {"current_steps": 54975, "total_steps": 64460, "loss": 0.0646, "lr": 6.453113201302458e-07, "epoch": 17.05708966801117, "percentage": 85.29, "elapsed_time": "1:41:48", "remaining_time": "0:17:33", "throughput": 5481.79, "total_tokens": 33484464} {"current_steps": 54980, "total_steps": 64460, "loss": 0.181, "lr": 6.446462274742731e-07, "epoch": 17.058641017685385, "percentage": 85.29, "elapsed_time": "1:41:48", "remaining_time": "0:17:33", "throughput": 5481.75, "total_tokens": 33486800} {"current_steps": 54985, "total_steps": 64460, "loss": 0.1478, "lr": 6.439814541173057e-07, "epoch": 17.0601923673596, "percentage": 85.3, "elapsed_time": "1:41:49", "remaining_time": "0:17:32", "throughput": 5481.74, "total_tokens": 33489328} {"current_steps": 54990, "total_steps": 64460, "loss": 0.1736, "lr": 6.433170001080818e-07, "epoch": 17.06174371703382, "percentage": 85.31, "elapsed_time": "1:41:49", "remaining_time": "0:17:32", "throughput": 5481.75, "total_tokens": 33492336} {"current_steps": 54995, "total_steps": 64460, "loss": 0.1125, "lr": 6.426528654953112e-07, "epoch": 17.063295066708037, "percentage": 85.32, "elapsed_time": "1:41:50", "remaining_time": "0:17:31", "throughput": 5481.76, "total_tokens": 33495120} {"current_steps": 55000, "total_steps": 64460, "loss": 0.1942, "lr": 6.419890503276854e-07, "epoch": 17.064846416382252, "percentage": 85.32, "elapsed_time": "1:41:50", "remaining_time": "0:17:31", "throughput": 5481.79, "total_tokens": 33498320} {"current_steps": 55005, "total_steps": 64460, "loss": 0.1677, "lr": 6.413255546538683e-07, "epoch": 17.06639776605647, "percentage": 85.33, "elapsed_time": "1:41:51", "remaining_time": "0:17:30", "throughput": 5481.84, "total_tokens": 33501328} {"current_steps": 55010, "total_steps": 64460, "loss": 0.1453, "lr": 6.40662378522503e-07, "epoch": 17.067949115730684, "percentage": 85.34, "elapsed_time": "1:41:51", "remaining_time": "0:17:29", "throughput": 5481.88, "total_tokens": 33504944} {"current_steps": 55015, "total_steps": 64460, "loss": 0.1632, "lr": 6.39999521982207e-07, "epoch": 17.069500465404904, "percentage": 85.35, "elapsed_time": "1:41:52", "remaining_time": "0:17:29", "throughput": 5481.95, "total_tokens": 33508240} {"current_steps": 55020, "total_steps": 64460, "loss": 0.1112, "lr": 6.393369850815767e-07, "epoch": 17.07105181507912, "percentage": 85.36, "elapsed_time": "1:41:53", "remaining_time": "0:17:28", "throughput": 5482.02, "total_tokens": 33511760} {"current_steps": 55025, "total_steps": 64460, "loss": 0.1763, "lr": 6.386747678691829e-07, "epoch": 17.072603164753335, "percentage": 85.36, "elapsed_time": "1:41:53", "remaining_time": "0:17:28", "throughput": 5482.06, "total_tokens": 33514704} {"current_steps": 55030, "total_steps": 64460, "loss": 0.1165, "lr": 6.380128703935739e-07, "epoch": 17.07415451442755, "percentage": 85.37, "elapsed_time": "1:41:54", "remaining_time": "0:17:27", "throughput": 5482.04, "total_tokens": 33517488} {"current_steps": 55035, "total_steps": 64460, "loss": 0.1339, "lr": 6.373512927032766e-07, "epoch": 17.075705864101767, "percentage": 85.38, "elapsed_time": "1:41:54", "remaining_time": "0:17:27", "throughput": 5481.98, "total_tokens": 33519664} {"current_steps": 55040, "total_steps": 64460, "loss": 0.1475, "lr": 6.366900348467897e-07, "epoch": 17.077257213775987, "percentage": 85.39, "elapsed_time": "1:41:55", "remaining_time": "0:17:26", "throughput": 5482.04, "total_tokens": 33523408} {"current_steps": 55045, "total_steps": 64460, "loss": 0.1385, "lr": 6.360290968725936e-07, "epoch": 17.078808563450202, "percentage": 85.39, "elapsed_time": "1:41:55", "remaining_time": "0:17:26", "throughput": 5482.04, "total_tokens": 33526224} {"current_steps": 55050, "total_steps": 64460, "loss": 0.125, "lr": 6.353684788291408e-07, "epoch": 17.08035991312442, "percentage": 85.4, "elapsed_time": "1:41:56", "remaining_time": "0:17:25", "throughput": 5482.09, "total_tokens": 33529296} {"current_steps": 55055, "total_steps": 64460, "loss": 0.1149, "lr": 6.347081807648648e-07, "epoch": 17.081911262798634, "percentage": 85.41, "elapsed_time": "1:41:56", "remaining_time": "0:17:24", "throughput": 5482.09, "total_tokens": 33531920} {"current_steps": 55060, "total_steps": 64460, "loss": 0.1665, "lr": 6.340482027281708e-07, "epoch": 17.08346261247285, "percentage": 85.42, "elapsed_time": "1:41:57", "remaining_time": "0:17:24", "throughput": 5482.23, "total_tokens": 33536816} {"current_steps": 55065, "total_steps": 64460, "loss": 0.1349, "lr": 6.333885447674448e-07, "epoch": 17.08501396214707, "percentage": 85.43, "elapsed_time": "1:41:58", "remaining_time": "0:17:23", "throughput": 5482.36, "total_tokens": 33541488} {"current_steps": 55070, "total_steps": 64460, "loss": 0.2041, "lr": 6.327292069310465e-07, "epoch": 17.086565311821285, "percentage": 85.43, "elapsed_time": "1:41:58", "remaining_time": "0:17:23", "throughput": 5482.41, "total_tokens": 33544368} {"current_steps": 55075, "total_steps": 64460, "loss": 0.1615, "lr": 6.320701892673142e-07, "epoch": 17.0881166614955, "percentage": 85.44, "elapsed_time": "1:41:59", "remaining_time": "0:17:22", "throughput": 5482.39, "total_tokens": 33546928} {"current_steps": 55080, "total_steps": 64460, "loss": 0.1009, "lr": 6.314114918245601e-07, "epoch": 17.089668011169717, "percentage": 85.45, "elapsed_time": "1:41:59", "remaining_time": "0:17:22", "throughput": 5482.51, "total_tokens": 33551728} {"current_steps": 55085, "total_steps": 64460, "loss": 0.1729, "lr": 6.307531146510754e-07, "epoch": 17.091219360843933, "percentage": 85.46, "elapsed_time": "1:42:00", "remaining_time": "0:17:21", "throughput": 5482.58, "total_tokens": 33554960} {"current_steps": 55090, "total_steps": 64460, "loss": 0.2017, "lr": 6.300950577951281e-07, "epoch": 17.092770710518153, "percentage": 85.46, "elapsed_time": "1:42:00", "remaining_time": "0:17:21", "throughput": 5482.62, "total_tokens": 33558384} {"current_steps": 55095, "total_steps": 64460, "loss": 0.2432, "lr": 6.294373213049593e-07, "epoch": 17.09432206019237, "percentage": 85.47, "elapsed_time": "1:42:01", "remaining_time": "0:17:20", "throughput": 5482.66, "total_tokens": 33561488} {"current_steps": 55100, "total_steps": 64460, "loss": 0.1959, "lr": 6.287799052287913e-07, "epoch": 17.095873409866584, "percentage": 85.48, "elapsed_time": "1:42:01", "remaining_time": "0:17:19", "throughput": 5482.61, "total_tokens": 33563920} {"current_steps": 55105, "total_steps": 64460, "loss": 0.2115, "lr": 6.281228096148178e-07, "epoch": 17.0974247595408, "percentage": 85.49, "elapsed_time": "1:42:02", "remaining_time": "0:17:19", "throughput": 5482.64, "total_tokens": 33567024} {"current_steps": 55110, "total_steps": 64460, "loss": 0.0793, "lr": 6.274660345112149e-07, "epoch": 17.098976109215016, "percentage": 85.49, "elapsed_time": "1:42:02", "remaining_time": "0:17:18", "throughput": 5482.67, "total_tokens": 33570000} {"current_steps": 55115, "total_steps": 64460, "loss": 0.1787, "lr": 6.26809579966129e-07, "epoch": 17.100527458889232, "percentage": 85.5, "elapsed_time": "1:42:03", "remaining_time": "0:17:18", "throughput": 5482.75, "total_tokens": 33573296} {"current_steps": 55120, "total_steps": 64460, "loss": 0.2024, "lr": 6.261534460276881e-07, "epoch": 17.10207880856345, "percentage": 85.51, "elapsed_time": "1:42:03", "remaining_time": "0:17:17", "throughput": 5482.76, "total_tokens": 33576144} {"current_steps": 55125, "total_steps": 64460, "loss": 0.1405, "lr": 6.254976327439921e-07, "epoch": 17.103630158237667, "percentage": 85.52, "elapsed_time": "1:42:04", "remaining_time": "0:17:17", "throughput": 5482.87, "total_tokens": 33580560} {"current_steps": 55130, "total_steps": 64460, "loss": 0.1096, "lr": 6.248421401631233e-07, "epoch": 17.105181507911883, "percentage": 85.53, "elapsed_time": "1:42:05", "remaining_time": "0:17:16", "throughput": 5482.82, "total_tokens": 33582736} {"current_steps": 55135, "total_steps": 64460, "loss": 0.1525, "lr": 6.241869683331337e-07, "epoch": 17.1067328575861, "percentage": 85.53, "elapsed_time": "1:42:05", "remaining_time": "0:17:16", "throughput": 5482.83, "total_tokens": 33585584} {"current_steps": 55140, "total_steps": 64460, "loss": 0.1431, "lr": 6.235321173020581e-07, "epoch": 17.108284207260315, "percentage": 85.54, "elapsed_time": "1:42:06", "remaining_time": "0:17:15", "throughput": 5482.77, "total_tokens": 33587728} {"current_steps": 55145, "total_steps": 64460, "loss": 0.1147, "lr": 6.228775871179021e-07, "epoch": 17.109835556934534, "percentage": 85.55, "elapsed_time": "1:42:06", "remaining_time": "0:17:14", "throughput": 5482.73, "total_tokens": 33590032} {"current_steps": 55150, "total_steps": 64460, "loss": 0.2117, "lr": 6.222233778286518e-07, "epoch": 17.11138690660875, "percentage": 85.56, "elapsed_time": "1:42:07", "remaining_time": "0:17:14", "throughput": 5482.8, "total_tokens": 33593264} {"current_steps": 55155, "total_steps": 64460, "loss": 0.0872, "lr": 6.215694894822699e-07, "epoch": 17.112938256282966, "percentage": 85.56, "elapsed_time": "1:42:07", "remaining_time": "0:17:13", "throughput": 5482.87, "total_tokens": 33597072} {"current_steps": 55160, "total_steps": 64460, "loss": 0.062, "lr": 6.209159221266919e-07, "epoch": 17.114489605957182, "percentage": 85.57, "elapsed_time": "1:42:08", "remaining_time": "0:17:13", "throughput": 5482.9, "total_tokens": 33600144} {"current_steps": 55165, "total_steps": 64460, "loss": 0.095, "lr": 6.202626758098324e-07, "epoch": 17.116040955631398, "percentage": 85.58, "elapsed_time": "1:42:08", "remaining_time": "0:17:12", "throughput": 5482.9, "total_tokens": 33602992} {"current_steps": 55170, "total_steps": 64460, "loss": 0.1542, "lr": 6.19609750579584e-07, "epoch": 17.117592305305617, "percentage": 85.59, "elapsed_time": "1:42:09", "remaining_time": "0:17:12", "throughput": 5482.96, "total_tokens": 33606480} {"current_steps": 55175, "total_steps": 64460, "loss": 0.1979, "lr": 6.189571464838112e-07, "epoch": 17.119143654979833, "percentage": 85.6, "elapsed_time": "1:42:09", "remaining_time": "0:17:11", "throughput": 5483.01, "total_tokens": 33609680} {"current_steps": 55180, "total_steps": 64460, "loss": 0.1097, "lr": 6.183048635703592e-07, "epoch": 17.12069500465405, "percentage": 85.6, "elapsed_time": "1:42:10", "remaining_time": "0:17:10", "throughput": 5482.98, "total_tokens": 33612304} {"current_steps": 55185, "total_steps": 64460, "loss": 0.1898, "lr": 6.176529018870487e-07, "epoch": 17.122246354328265, "percentage": 85.61, "elapsed_time": "1:42:10", "remaining_time": "0:17:10", "throughput": 5482.95, "total_tokens": 33614832} {"current_steps": 55190, "total_steps": 64460, "loss": 0.1043, "lr": 6.17001261481674e-07, "epoch": 17.12379770400248, "percentage": 85.62, "elapsed_time": "1:42:11", "remaining_time": "0:17:09", "throughput": 5482.93, "total_tokens": 33617520} {"current_steps": 55195, "total_steps": 64460, "loss": 0.1981, "lr": 6.163499424020103e-07, "epoch": 17.1253490536767, "percentage": 85.63, "elapsed_time": "1:42:11", "remaining_time": "0:17:09", "throughput": 5483.0, "total_tokens": 33620848} {"current_steps": 55200, "total_steps": 64460, "loss": 0.2363, "lr": 6.15698944695805e-07, "epoch": 17.126900403350916, "percentage": 85.63, "elapsed_time": "1:42:12", "remaining_time": "0:17:08", "throughput": 5482.98, "total_tokens": 33623536} {"current_steps": 55205, "total_steps": 64460, "loss": 0.1298, "lr": 6.150482684107861e-07, "epoch": 17.128451753025132, "percentage": 85.64, "elapsed_time": "1:42:12", "remaining_time": "0:17:08", "throughput": 5483.04, "total_tokens": 33626544} {"current_steps": 55210, "total_steps": 64460, "loss": 0.18, "lr": 6.143979135946537e-07, "epoch": 17.130003102699348, "percentage": 85.65, "elapsed_time": "1:42:13", "remaining_time": "0:17:07", "throughput": 5483.07, "total_tokens": 33629584} {"current_steps": 55215, "total_steps": 64460, "loss": 0.2434, "lr": 6.137478802950886e-07, "epoch": 17.131554452373564, "percentage": 85.66, "elapsed_time": "1:42:13", "remaining_time": "0:17:07", "throughput": 5483.01, "total_tokens": 33632016} {"current_steps": 55220, "total_steps": 64460, "loss": 0.1872, "lr": 6.130981685597436e-07, "epoch": 17.133105802047783, "percentage": 85.67, "elapsed_time": "1:42:14", "remaining_time": "0:17:06", "throughput": 5483.14, "total_tokens": 33635920} {"current_steps": 55225, "total_steps": 64460, "loss": 0.1546, "lr": 6.124487784362526e-07, "epoch": 17.134657151722, "percentage": 85.67, "elapsed_time": "1:42:15", "remaining_time": "0:17:05", "throughput": 5483.21, "total_tokens": 33639696} {"current_steps": 55230, "total_steps": 64460, "loss": 0.1252, "lr": 6.117997099722217e-07, "epoch": 17.136208501396215, "percentage": 85.68, "elapsed_time": "1:42:15", "remaining_time": "0:17:05", "throughput": 5483.25, "total_tokens": 33642640} {"current_steps": 55235, "total_steps": 64460, "loss": 0.1683, "lr": 6.111509632152362e-07, "epoch": 17.13775985107043, "percentage": 85.69, "elapsed_time": "1:42:16", "remaining_time": "0:17:04", "throughput": 5483.3, "total_tokens": 33645808} {"current_steps": 55240, "total_steps": 64460, "loss": 0.1052, "lr": 6.105025382128577e-07, "epoch": 17.139311200744647, "percentage": 85.7, "elapsed_time": "1:42:16", "remaining_time": "0:17:04", "throughput": 5483.3, "total_tokens": 33648592} {"current_steps": 55245, "total_steps": 64460, "loss": 0.1345, "lr": 6.098544350126212e-07, "epoch": 17.140862550418863, "percentage": 85.7, "elapsed_time": "1:42:17", "remaining_time": "0:17:03", "throughput": 5483.29, "total_tokens": 33651440} {"current_steps": 55250, "total_steps": 64460, "loss": 0.1367, "lr": 6.092066536620433e-07, "epoch": 17.142413900093082, "percentage": 85.71, "elapsed_time": "1:42:17", "remaining_time": "0:17:03", "throughput": 5483.28, "total_tokens": 33654160} {"current_steps": 55255, "total_steps": 64460, "loss": 0.1255, "lr": 6.085591942086111e-07, "epoch": 17.143965249767298, "percentage": 85.72, "elapsed_time": "1:42:18", "remaining_time": "0:17:02", "throughput": 5483.27, "total_tokens": 33656976} {"current_steps": 55260, "total_steps": 64460, "loss": 0.1887, "lr": 6.079120566997937e-07, "epoch": 17.145516599441514, "percentage": 85.73, "elapsed_time": "1:42:18", "remaining_time": "0:17:02", "throughput": 5483.36, "total_tokens": 33661136} {"current_steps": 55265, "total_steps": 64460, "loss": 0.1785, "lr": 6.072652411830315e-07, "epoch": 17.14706794911573, "percentage": 85.74, "elapsed_time": "1:42:19", "remaining_time": "0:17:01", "throughput": 5483.36, "total_tokens": 33663920} {"current_steps": 55270, "total_steps": 64460, "loss": 0.1422, "lr": 6.066187477057456e-07, "epoch": 17.148619298789946, "percentage": 85.74, "elapsed_time": "1:42:19", "remaining_time": "0:17:00", "throughput": 5483.36, "total_tokens": 33666768} {"current_steps": 55275, "total_steps": 64460, "loss": 0.1194, "lr": 6.059725763153301e-07, "epoch": 17.150170648464165, "percentage": 85.75, "elapsed_time": "1:42:20", "remaining_time": "0:17:00", "throughput": 5483.38, "total_tokens": 33669552} {"current_steps": 55280, "total_steps": 64460, "loss": 0.0976, "lr": 6.053267270591589e-07, "epoch": 17.15172199813838, "percentage": 85.76, "elapsed_time": "1:42:20", "remaining_time": "0:16:59", "throughput": 5483.41, "total_tokens": 33672624} {"current_steps": 55285, "total_steps": 64460, "loss": 0.2904, "lr": 6.046811999845786e-07, "epoch": 17.153273347812597, "percentage": 85.77, "elapsed_time": "1:42:21", "remaining_time": "0:16:59", "throughput": 5483.52, "total_tokens": 33676496} {"current_steps": 55290, "total_steps": 64460, "loss": 0.2183, "lr": 6.040359951389157e-07, "epoch": 17.154824697486813, "percentage": 85.77, "elapsed_time": "1:42:21", "remaining_time": "0:16:58", "throughput": 5483.56, "total_tokens": 33679440} {"current_steps": 55295, "total_steps": 64460, "loss": 0.1233, "lr": 6.033911125694691e-07, "epoch": 17.15637604716103, "percentage": 85.78, "elapsed_time": "1:42:22", "remaining_time": "0:16:58", "throughput": 5483.62, "total_tokens": 33683024} {"current_steps": 55300, "total_steps": 64460, "loss": 0.2418, "lr": 6.027465523235171e-07, "epoch": 17.157927396835248, "percentage": 85.79, "elapsed_time": "1:42:22", "remaining_time": "0:16:57", "throughput": 5483.64, "total_tokens": 33685936} {"current_steps": 55305, "total_steps": 64460, "loss": 0.1918, "lr": 6.021023144483156e-07, "epoch": 17.159478746509464, "percentage": 85.8, "elapsed_time": "1:42:23", "remaining_time": "0:16:56", "throughput": 5483.6, "total_tokens": 33688528} {"current_steps": 55310, "total_steps": 64460, "loss": 0.2225, "lr": 6.014583989910927e-07, "epoch": 17.16103009618368, "percentage": 85.81, "elapsed_time": "1:42:24", "remaining_time": "0:16:56", "throughput": 5483.72, "total_tokens": 33692912} {"current_steps": 55315, "total_steps": 64460, "loss": 0.1192, "lr": 6.008148059990559e-07, "epoch": 17.162581445857896, "percentage": 85.81, "elapsed_time": "1:42:24", "remaining_time": "0:16:55", "throughput": 5483.66, "total_tokens": 33695344} {"current_steps": 55320, "total_steps": 64460, "loss": 0.1901, "lr": 6.001715355193876e-07, "epoch": 17.16413279553211, "percentage": 85.82, "elapsed_time": "1:42:25", "remaining_time": "0:16:55", "throughput": 5483.63, "total_tokens": 33697776} {"current_steps": 55325, "total_steps": 64460, "loss": 0.1634, "lr": 5.995285875992485e-07, "epoch": 17.16568414520633, "percentage": 85.83, "elapsed_time": "1:42:25", "remaining_time": "0:16:54", "throughput": 5483.61, "total_tokens": 33700496} {"current_steps": 55330, "total_steps": 64460, "loss": 0.1281, "lr": 5.988859622857718e-07, "epoch": 17.167235494880547, "percentage": 85.84, "elapsed_time": "1:42:26", "remaining_time": "0:16:54", "throughput": 5483.6, "total_tokens": 33703056} {"current_steps": 55335, "total_steps": 64460, "loss": 0.1456, "lr": 5.982436596260721e-07, "epoch": 17.168786844554763, "percentage": 85.84, "elapsed_time": "1:42:26", "remaining_time": "0:16:53", "throughput": 5483.58, "total_tokens": 33705520} {"current_steps": 55340, "total_steps": 64460, "loss": 0.1492, "lr": 5.976016796672363e-07, "epoch": 17.17033819422898, "percentage": 85.85, "elapsed_time": "1:42:27", "remaining_time": "0:16:53", "throughput": 5483.64, "total_tokens": 33708784} {"current_steps": 55345, "total_steps": 64460, "loss": 0.146, "lr": 5.969600224563304e-07, "epoch": 17.171889543903195, "percentage": 85.86, "elapsed_time": "1:42:27", "remaining_time": "0:16:52", "throughput": 5483.65, "total_tokens": 33711504} {"current_steps": 55350, "total_steps": 64460, "loss": 0.1568, "lr": 5.963186880403931e-07, "epoch": 17.173440893577414, "percentage": 85.87, "elapsed_time": "1:42:28", "remaining_time": "0:16:51", "throughput": 5483.64, "total_tokens": 33714224} {"current_steps": 55355, "total_steps": 64460, "loss": 0.1225, "lr": 5.95677676466444e-07, "epoch": 17.17499224325163, "percentage": 85.87, "elapsed_time": "1:42:28", "remaining_time": "0:16:51", "throughput": 5483.76, "total_tokens": 33717968} {"current_steps": 55360, "total_steps": 64460, "loss": 0.141, "lr": 5.950369877814771e-07, "epoch": 17.176543592925846, "percentage": 85.88, "elapsed_time": "1:42:29", "remaining_time": "0:16:50", "throughput": 5483.71, "total_tokens": 33720432} {"current_steps": 55365, "total_steps": 64460, "loss": 0.1946, "lr": 5.943966220324604e-07, "epoch": 17.17809494260006, "percentage": 85.89, "elapsed_time": "1:42:29", "remaining_time": "0:16:50", "throughput": 5483.57, "total_tokens": 33722448} {"current_steps": 55370, "total_steps": 64460, "loss": 0.1402, "lr": 5.937565792663425e-07, "epoch": 17.179646292274278, "percentage": 85.9, "elapsed_time": "1:42:30", "remaining_time": "0:16:49", "throughput": 5483.59, "total_tokens": 33725424} {"current_steps": 55375, "total_steps": 64460, "loss": 0.2542, "lr": 5.931168595300435e-07, "epoch": 17.181197641948494, "percentage": 85.91, "elapsed_time": "1:42:30", "remaining_time": "0:16:49", "throughput": 5483.65, "total_tokens": 33728688} {"current_steps": 55380, "total_steps": 64460, "loss": 0.1408, "lr": 5.92477462870466e-07, "epoch": 17.182748991622713, "percentage": 85.91, "elapsed_time": "1:42:31", "remaining_time": "0:16:48", "throughput": 5483.71, "total_tokens": 33731888} {"current_steps": 55385, "total_steps": 64460, "loss": 0.1516, "lr": 5.918383893344815e-07, "epoch": 17.18430034129693, "percentage": 85.92, "elapsed_time": "1:42:31", "remaining_time": "0:16:48", "throughput": 5483.77, "total_tokens": 33735376} {"current_steps": 55390, "total_steps": 64460, "loss": 0.1123, "lr": 5.91199638968945e-07, "epoch": 17.185851690971145, "percentage": 85.93, "elapsed_time": "1:42:32", "remaining_time": "0:16:47", "throughput": 5483.85, "total_tokens": 33739536} {"current_steps": 55395, "total_steps": 64460, "loss": 0.1083, "lr": 5.905612118206822e-07, "epoch": 17.18740304064536, "percentage": 85.94, "elapsed_time": "1:42:33", "remaining_time": "0:16:46", "throughput": 5483.9, "total_tokens": 33742608} {"current_steps": 55400, "total_steps": 64460, "loss": 0.1751, "lr": 5.899231079364986e-07, "epoch": 17.188954390319577, "percentage": 85.94, "elapsed_time": "1:42:33", "remaining_time": "0:16:46", "throughput": 5483.91, "total_tokens": 33745360} {"current_steps": 55405, "total_steps": 64460, "loss": 0.1438, "lr": 5.892853273631733e-07, "epoch": 17.190505739993796, "percentage": 85.95, "elapsed_time": "1:42:34", "remaining_time": "0:16:45", "throughput": 5483.94, "total_tokens": 33748336} {"current_steps": 55410, "total_steps": 64460, "loss": 0.1588, "lr": 5.886478701474658e-07, "epoch": 17.192057089668012, "percentage": 85.96, "elapsed_time": "1:42:34", "remaining_time": "0:16:45", "throughput": 5484.0, "total_tokens": 33752592} {"current_steps": 55415, "total_steps": 64460, "loss": 0.1146, "lr": 5.88010736336106e-07, "epoch": 17.193608439342228, "percentage": 85.97, "elapsed_time": "1:42:35", "remaining_time": "0:16:44", "throughput": 5484.03, "total_tokens": 33755792} {"current_steps": 55420, "total_steps": 64460, "loss": 0.084, "lr": 5.873739259758049e-07, "epoch": 17.195159789016444, "percentage": 85.98, "elapsed_time": "1:42:35", "remaining_time": "0:16:44", "throughput": 5484.15, "total_tokens": 33759600} {"current_steps": 55425, "total_steps": 64460, "loss": 0.1374, "lr": 5.867374391132497e-07, "epoch": 17.19671113869066, "percentage": 85.98, "elapsed_time": "1:42:36", "remaining_time": "0:16:43", "throughput": 5484.17, "total_tokens": 33762768} {"current_steps": 55430, "total_steps": 64460, "loss": 0.1093, "lr": 5.861012757951001e-07, "epoch": 17.19826248836488, "percentage": 85.99, "elapsed_time": "1:42:36", "remaining_time": "0:16:43", "throughput": 5484.19, "total_tokens": 33765680} {"current_steps": 55435, "total_steps": 64460, "loss": 0.1412, "lr": 5.854654360679962e-07, "epoch": 17.199813838039095, "percentage": 86.0, "elapsed_time": "1:42:37", "remaining_time": "0:16:42", "throughput": 5484.17, "total_tokens": 33768464} {"current_steps": 55440, "total_steps": 64460, "loss": 0.0965, "lr": 5.848299199785512e-07, "epoch": 17.20136518771331, "percentage": 86.01, "elapsed_time": "1:42:37", "remaining_time": "0:16:41", "throughput": 5484.19, "total_tokens": 33771344} {"current_steps": 55445, "total_steps": 64460, "loss": 0.181, "lr": 5.841947275733567e-07, "epoch": 17.202916537387527, "percentage": 86.01, "elapsed_time": "1:42:38", "remaining_time": "0:16:41", "throughput": 5484.2, "total_tokens": 33774352} {"current_steps": 55450, "total_steps": 64460, "loss": 0.1464, "lr": 5.835598588989793e-07, "epoch": 17.204467887061742, "percentage": 86.02, "elapsed_time": "1:42:38", "remaining_time": "0:16:40", "throughput": 5484.19, "total_tokens": 33776944} {"current_steps": 55455, "total_steps": 64460, "loss": 0.1331, "lr": 5.829253140019636e-07, "epoch": 17.206019236735962, "percentage": 86.03, "elapsed_time": "1:42:39", "remaining_time": "0:16:40", "throughput": 5484.25, "total_tokens": 33780752} {"current_steps": 55460, "total_steps": 64460, "loss": 0.0994, "lr": 5.822910929288272e-07, "epoch": 17.207570586410178, "percentage": 86.04, "elapsed_time": "1:42:40", "remaining_time": "0:16:39", "throughput": 5484.24, "total_tokens": 33784336} {"current_steps": 55465, "total_steps": 64460, "loss": 0.1521, "lr": 5.816571957260681e-07, "epoch": 17.209121936084394, "percentage": 86.05, "elapsed_time": "1:42:40", "remaining_time": "0:16:39", "throughput": 5484.12, "total_tokens": 33786384} {"current_steps": 55470, "total_steps": 64460, "loss": 0.0956, "lr": 5.810236224401566e-07, "epoch": 17.21067328575861, "percentage": 86.05, "elapsed_time": "1:42:41", "remaining_time": "0:16:38", "throughput": 5484.13, "total_tokens": 33789424} {"current_steps": 55475, "total_steps": 64460, "loss": 0.0731, "lr": 5.803903731175426e-07, "epoch": 17.212224635432825, "percentage": 86.06, "elapsed_time": "1:42:41", "remaining_time": "0:16:37", "throughput": 5484.16, "total_tokens": 33792368} {"current_steps": 55480, "total_steps": 64460, "loss": 0.2346, "lr": 5.797574478046502e-07, "epoch": 17.213775985107045, "percentage": 86.07, "elapsed_time": "1:42:42", "remaining_time": "0:16:37", "throughput": 5484.14, "total_tokens": 33794864} {"current_steps": 55485, "total_steps": 64460, "loss": 0.2528, "lr": 5.791248465478805e-07, "epoch": 17.21532733478126, "percentage": 86.08, "elapsed_time": "1:42:42", "remaining_time": "0:16:36", "throughput": 5484.19, "total_tokens": 33798000} {"current_steps": 55490, "total_steps": 64460, "loss": 0.131, "lr": 5.784925693936111e-07, "epoch": 17.216878684455477, "percentage": 86.08, "elapsed_time": "1:42:43", "remaining_time": "0:16:36", "throughput": 5484.17, "total_tokens": 33800528} {"current_steps": 55495, "total_steps": 64460, "loss": 0.1344, "lr": 5.778606163881934e-07, "epoch": 17.218430034129693, "percentage": 86.09, "elapsed_time": "1:42:43", "remaining_time": "0:16:35", "throughput": 5484.14, "total_tokens": 33802864} {"current_steps": 55500, "total_steps": 64460, "loss": 0.2585, "lr": 5.772289875779602e-07, "epoch": 17.21998138380391, "percentage": 86.1, "elapsed_time": "1:42:44", "remaining_time": "0:16:35", "throughput": 5484.1, "total_tokens": 33805360} {"current_steps": 55505, "total_steps": 64460, "loss": 0.0903, "lr": 5.76597683009214e-07, "epoch": 17.221532733478124, "percentage": 86.11, "elapsed_time": "1:42:44", "remaining_time": "0:16:34", "throughput": 5484.15, "total_tokens": 33808496} {"current_steps": 55510, "total_steps": 64460, "loss": 0.2393, "lr": 5.759667027282401e-07, "epoch": 17.223084083152344, "percentage": 86.12, "elapsed_time": "1:42:45", "remaining_time": "0:16:34", "throughput": 5484.13, "total_tokens": 33811280} {"current_steps": 55515, "total_steps": 64460, "loss": 0.1281, "lr": 5.753360467812941e-07, "epoch": 17.22463543282656, "percentage": 86.12, "elapsed_time": "1:42:45", "remaining_time": "0:16:33", "throughput": 5484.21, "total_tokens": 33814800} {"current_steps": 55520, "total_steps": 64460, "loss": 0.1515, "lr": 5.747057152146129e-07, "epoch": 17.226186782500776, "percentage": 86.13, "elapsed_time": "1:42:46", "remaining_time": "0:16:32", "throughput": 5484.18, "total_tokens": 33817488} {"current_steps": 55525, "total_steps": 64460, "loss": 0.1936, "lr": 5.740757080744048e-07, "epoch": 17.22773813217499, "percentage": 86.14, "elapsed_time": "1:42:46", "remaining_time": "0:16:32", "throughput": 5484.27, "total_tokens": 33820784} {"current_steps": 55530, "total_steps": 64460, "loss": 0.1287, "lr": 5.734460254068591e-07, "epoch": 17.229289481849207, "percentage": 86.15, "elapsed_time": "1:42:47", "remaining_time": "0:16:31", "throughput": 5484.37, "total_tokens": 33824752} {"current_steps": 55535, "total_steps": 64460, "loss": 0.1669, "lr": 5.72816667258137e-07, "epoch": 17.230840831523427, "percentage": 86.15, "elapsed_time": "1:42:48", "remaining_time": "0:16:31", "throughput": 5484.41, "total_tokens": 33827952} {"current_steps": 55540, "total_steps": 64460, "loss": 0.1696, "lr": 5.721876336743793e-07, "epoch": 17.232392181197643, "percentage": 86.16, "elapsed_time": "1:42:48", "remaining_time": "0:16:30", "throughput": 5484.38, "total_tokens": 33830512} {"current_steps": 55545, "total_steps": 64460, "loss": 0.2249, "lr": 5.715589247017017e-07, "epoch": 17.23394353087186, "percentage": 86.17, "elapsed_time": "1:42:49", "remaining_time": "0:16:30", "throughput": 5484.39, "total_tokens": 33833232} {"current_steps": 55550, "total_steps": 64460, "loss": 0.1594, "lr": 5.709305403861948e-07, "epoch": 17.235494880546074, "percentage": 86.18, "elapsed_time": "1:42:49", "remaining_time": "0:16:29", "throughput": 5484.33, "total_tokens": 33835504} {"current_steps": 55555, "total_steps": 64460, "loss": 0.1506, "lr": 5.703024807739277e-07, "epoch": 17.23704623022029, "percentage": 86.19, "elapsed_time": "1:42:50", "remaining_time": "0:16:29", "throughput": 5484.45, "total_tokens": 33839696} {"current_steps": 55560, "total_steps": 64460, "loss": 0.0883, "lr": 5.696747459109436e-07, "epoch": 17.23859757989451, "percentage": 86.19, "elapsed_time": "1:42:50", "remaining_time": "0:16:28", "throughput": 5484.49, "total_tokens": 33842672} {"current_steps": 55565, "total_steps": 64460, "loss": 0.1291, "lr": 5.690473358432647e-07, "epoch": 17.240148929568726, "percentage": 86.2, "elapsed_time": "1:42:51", "remaining_time": "0:16:27", "throughput": 5484.46, "total_tokens": 33845104} {"current_steps": 55570, "total_steps": 64460, "loss": 0.1591, "lr": 5.684202506168856e-07, "epoch": 17.24170027924294, "percentage": 86.21, "elapsed_time": "1:42:51", "remaining_time": "0:16:27", "throughput": 5484.49, "total_tokens": 33847920} {"current_steps": 55575, "total_steps": 64460, "loss": 0.1914, "lr": 5.677934902777804e-07, "epoch": 17.243251628917157, "percentage": 86.22, "elapsed_time": "1:42:52", "remaining_time": "0:16:26", "throughput": 5484.48, "total_tokens": 33850352} {"current_steps": 55580, "total_steps": 64460, "loss": 0.1578, "lr": 5.671670548718971e-07, "epoch": 17.244802978591373, "percentage": 86.22, "elapsed_time": "1:42:52", "remaining_time": "0:16:26", "throughput": 5484.48, "total_tokens": 33852880} {"current_steps": 55585, "total_steps": 64460, "loss": 0.1425, "lr": 5.66540944445162e-07, "epoch": 17.246354328265593, "percentage": 86.23, "elapsed_time": "1:42:53", "remaining_time": "0:16:25", "throughput": 5484.53, "total_tokens": 33856176} {"current_steps": 55590, "total_steps": 64460, "loss": 0.1195, "lr": 5.659151590434742e-07, "epoch": 17.24790567793981, "percentage": 86.24, "elapsed_time": "1:42:53", "remaining_time": "0:16:25", "throughput": 5484.6, "total_tokens": 33859632} {"current_steps": 55595, "total_steps": 64460, "loss": 0.1128, "lr": 5.652896987127132e-07, "epoch": 17.249457027614024, "percentage": 86.25, "elapsed_time": "1:42:54", "remaining_time": "0:16:24", "throughput": 5484.65, "total_tokens": 33862576} {"current_steps": 55600, "total_steps": 64460, "loss": 0.1205, "lr": 5.64664563498733e-07, "epoch": 17.25100837728824, "percentage": 86.26, "elapsed_time": "1:42:54", "remaining_time": "0:16:23", "throughput": 5484.7, "total_tokens": 33865456} {"current_steps": 55605, "total_steps": 64460, "loss": 0.1428, "lr": 5.640397534473613e-07, "epoch": 17.252559726962456, "percentage": 86.26, "elapsed_time": "1:42:55", "remaining_time": "0:16:23", "throughput": 5484.74, "total_tokens": 33868464} {"current_steps": 55610, "total_steps": 64460, "loss": 0.3165, "lr": 5.63415268604407e-07, "epoch": 17.254111076636676, "percentage": 86.27, "elapsed_time": "1:42:55", "remaining_time": "0:16:22", "throughput": 5484.76, "total_tokens": 33871216} {"current_steps": 55615, "total_steps": 64460, "loss": 0.181, "lr": 5.62791109015649e-07, "epoch": 17.25566242631089, "percentage": 86.28, "elapsed_time": "1:42:56", "remaining_time": "0:16:22", "throughput": 5484.79, "total_tokens": 33874064} {"current_steps": 55620, "total_steps": 64460, "loss": 0.1233, "lr": 5.62167274726848e-07, "epoch": 17.257213775985107, "percentage": 86.29, "elapsed_time": "1:42:56", "remaining_time": "0:16:21", "throughput": 5484.7, "total_tokens": 33876048} {"current_steps": 55625, "total_steps": 64460, "loss": 0.2077, "lr": 5.615437657837369e-07, "epoch": 17.258765125659323, "percentage": 86.29, "elapsed_time": "1:42:57", "remaining_time": "0:16:21", "throughput": 5484.77, "total_tokens": 33879408} {"current_steps": 55630, "total_steps": 64460, "loss": 0.1673, "lr": 5.609205822320274e-07, "epoch": 17.26031647533354, "percentage": 86.3, "elapsed_time": "1:42:57", "remaining_time": "0:16:20", "throughput": 5484.75, "total_tokens": 33882192} {"current_steps": 55635, "total_steps": 64460, "loss": 0.1653, "lr": 5.602977241174051e-07, "epoch": 17.261867825007755, "percentage": 86.31, "elapsed_time": "1:42:58", "remaining_time": "0:16:19", "throughput": 5484.74, "total_tokens": 33884752} {"current_steps": 55640, "total_steps": 64460, "loss": 0.1707, "lr": 5.596751914855348e-07, "epoch": 17.263419174681975, "percentage": 86.32, "elapsed_time": "1:42:58", "remaining_time": "0:16:19", "throughput": 5484.79, "total_tokens": 33887856} {"current_steps": 55645, "total_steps": 64460, "loss": 0.1309, "lr": 5.59052984382053e-07, "epoch": 17.26497052435619, "percentage": 86.32, "elapsed_time": "1:42:59", "remaining_time": "0:16:18", "throughput": 5484.89, "total_tokens": 33891728} {"current_steps": 55650, "total_steps": 64460, "loss": 0.2458, "lr": 5.584311028525774e-07, "epoch": 17.266521874030406, "percentage": 86.33, "elapsed_time": "1:42:59", "remaining_time": "0:16:18", "throughput": 5485.02, "total_tokens": 33896432} {"current_steps": 55655, "total_steps": 64460, "loss": 0.1705, "lr": 5.578095469426969e-07, "epoch": 17.268073223704622, "percentage": 86.34, "elapsed_time": "1:43:00", "remaining_time": "0:16:17", "throughput": 5484.97, "total_tokens": 33898736} {"current_steps": 55660, "total_steps": 64460, "loss": 0.1641, "lr": 5.571883166979797e-07, "epoch": 17.269624573378838, "percentage": 86.35, "elapsed_time": "1:43:00", "remaining_time": "0:16:17", "throughput": 5484.92, "total_tokens": 33901296} {"current_steps": 55665, "total_steps": 64460, "loss": 0.2227, "lr": 5.565674121639713e-07, "epoch": 17.271175923053057, "percentage": 86.36, "elapsed_time": "1:43:01", "remaining_time": "0:16:16", "throughput": 5484.87, "total_tokens": 33903728} {"current_steps": 55670, "total_steps": 64460, "loss": 0.1788, "lr": 5.559468333861884e-07, "epoch": 17.272727272727273, "percentage": 86.36, "elapsed_time": "1:43:01", "remaining_time": "0:16:16", "throughput": 5484.89, "total_tokens": 33907408} {"current_steps": 55675, "total_steps": 64460, "loss": 0.0848, "lr": 5.553265804101288e-07, "epoch": 17.27427862240149, "percentage": 86.37, "elapsed_time": "1:43:02", "remaining_time": "0:16:15", "throughput": 5484.89, "total_tokens": 33910160} {"current_steps": 55680, "total_steps": 64460, "loss": 0.1438, "lr": 5.547066532812629e-07, "epoch": 17.275829972075705, "percentage": 86.38, "elapsed_time": "1:43:02", "remaining_time": "0:16:14", "throughput": 5484.93, "total_tokens": 33913072} {"current_steps": 55685, "total_steps": 64460, "loss": 0.2533, "lr": 5.540870520450403e-07, "epoch": 17.27738132174992, "percentage": 86.39, "elapsed_time": "1:43:03", "remaining_time": "0:16:14", "throughput": 5484.9, "total_tokens": 33915984} {"current_steps": 55690, "total_steps": 64460, "loss": 0.1163, "lr": 5.534677767468832e-07, "epoch": 17.27893267142414, "percentage": 86.39, "elapsed_time": "1:43:04", "remaining_time": "0:16:13", "throughput": 5484.92, "total_tokens": 33918864} {"current_steps": 55695, "total_steps": 64460, "loss": 0.109, "lr": 5.528488274321941e-07, "epoch": 17.280484021098356, "percentage": 86.4, "elapsed_time": "1:43:04", "remaining_time": "0:16:13", "throughput": 5484.93, "total_tokens": 33921616} {"current_steps": 55700, "total_steps": 64460, "loss": 0.2613, "lr": 5.522302041463473e-07, "epoch": 17.282035370772572, "percentage": 86.41, "elapsed_time": "1:43:05", "remaining_time": "0:16:12", "throughput": 5484.92, "total_tokens": 33924240} {"current_steps": 55705, "total_steps": 64460, "loss": 0.2057, "lr": 5.516119069346964e-07, "epoch": 17.283586720446788, "percentage": 86.42, "elapsed_time": "1:43:05", "remaining_time": "0:16:12", "throughput": 5484.97, "total_tokens": 33927216} {"current_steps": 55710, "total_steps": 64460, "loss": 0.2304, "lr": 5.509939358425692e-07, "epoch": 17.285138070121004, "percentage": 86.43, "elapsed_time": "1:43:05", "remaining_time": "0:16:11", "throughput": 5484.94, "total_tokens": 33929680} {"current_steps": 55715, "total_steps": 64460, "loss": 0.2241, "lr": 5.503762909152705e-07, "epoch": 17.286689419795223, "percentage": 86.43, "elapsed_time": "1:43:06", "remaining_time": "0:16:11", "throughput": 5485.0, "total_tokens": 33933008} {"current_steps": 55720, "total_steps": 64460, "loss": 0.1833, "lr": 5.497589721980817e-07, "epoch": 17.28824076946944, "percentage": 86.44, "elapsed_time": "1:43:07", "remaining_time": "0:16:10", "throughput": 5484.99, "total_tokens": 33935696} {"current_steps": 55725, "total_steps": 64460, "loss": 0.1202, "lr": 5.49141979736258e-07, "epoch": 17.289792119143655, "percentage": 86.45, "elapsed_time": "1:43:07", "remaining_time": "0:16:09", "throughput": 5485.04, "total_tokens": 33938928} {"current_steps": 55730, "total_steps": 64460, "loss": 0.1519, "lr": 5.485253135750346e-07, "epoch": 17.29134346881787, "percentage": 86.46, "elapsed_time": "1:43:08", "remaining_time": "0:16:09", "throughput": 5485.03, "total_tokens": 33941584} {"current_steps": 55735, "total_steps": 64460, "loss": 0.1648, "lr": 5.479089737596177e-07, "epoch": 17.292894818492087, "percentage": 86.46, "elapsed_time": "1:43:08", "remaining_time": "0:16:08", "throughput": 5485.07, "total_tokens": 33944720} {"current_steps": 55740, "total_steps": 64460, "loss": 0.1876, "lr": 5.472929603351939e-07, "epoch": 17.294446168166306, "percentage": 86.47, "elapsed_time": "1:43:09", "remaining_time": "0:16:08", "throughput": 5485.13, "total_tokens": 33948240} {"current_steps": 55745, "total_steps": 64460, "loss": 0.1701, "lr": 5.466772733469239e-07, "epoch": 17.295997517840522, "percentage": 86.48, "elapsed_time": "1:43:09", "remaining_time": "0:16:07", "throughput": 5485.18, "total_tokens": 33951536} {"current_steps": 55750, "total_steps": 64460, "loss": 0.1709, "lr": 5.460619128399464e-07, "epoch": 17.297548867514738, "percentage": 86.49, "elapsed_time": "1:43:10", "remaining_time": "0:16:07", "throughput": 5485.13, "total_tokens": 33953776} {"current_steps": 55755, "total_steps": 64460, "loss": 0.1846, "lr": 5.45446878859372e-07, "epoch": 17.299100217188954, "percentage": 86.5, "elapsed_time": "1:43:10", "remaining_time": "0:16:06", "throughput": 5485.1, "total_tokens": 33956464} {"current_steps": 55760, "total_steps": 64460, "loss": 0.181, "lr": 5.448321714502919e-07, "epoch": 17.30065156686317, "percentage": 86.5, "elapsed_time": "1:43:11", "remaining_time": "0:16:05", "throughput": 5485.13, "total_tokens": 33959888} {"current_steps": 55765, "total_steps": 64460, "loss": 0.1512, "lr": 5.442177906577701e-07, "epoch": 17.302202916537386, "percentage": 86.51, "elapsed_time": "1:43:11", "remaining_time": "0:16:05", "throughput": 5485.15, "total_tokens": 33962576} {"current_steps": 55770, "total_steps": 64460, "loss": 0.1476, "lr": 5.436037365268493e-07, "epoch": 17.303754266211605, "percentage": 86.52, "elapsed_time": "1:43:12", "remaining_time": "0:16:04", "throughput": 5485.13, "total_tokens": 33965168} {"current_steps": 55775, "total_steps": 64460, "loss": 0.3088, "lr": 5.429900091025453e-07, "epoch": 17.30530561588582, "percentage": 86.53, "elapsed_time": "1:43:12", "remaining_time": "0:16:04", "throughput": 5485.15, "total_tokens": 33967824} {"current_steps": 55780, "total_steps": 64460, "loss": 0.1429, "lr": 5.423766084298532e-07, "epoch": 17.306856965560037, "percentage": 86.53, "elapsed_time": "1:43:13", "remaining_time": "0:16:03", "throughput": 5485.09, "total_tokens": 33970128} {"current_steps": 55785, "total_steps": 64460, "loss": 0.1353, "lr": 5.417635345537414e-07, "epoch": 17.308408315234253, "percentage": 86.54, "elapsed_time": "1:43:13", "remaining_time": "0:16:03", "throughput": 5485.19, "total_tokens": 33973776} {"current_steps": 55790, "total_steps": 64460, "loss": 0.0789, "lr": 5.411507875191569e-07, "epoch": 17.30995966490847, "percentage": 86.55, "elapsed_time": "1:43:14", "remaining_time": "0:16:02", "throughput": 5485.22, "total_tokens": 33976816} {"current_steps": 55795, "total_steps": 64460, "loss": 0.1512, "lr": 5.405383673710191e-07, "epoch": 17.31151101458269, "percentage": 86.56, "elapsed_time": "1:43:14", "remaining_time": "0:16:02", "throughput": 5485.28, "total_tokens": 33980144} {"current_steps": 55800, "total_steps": 64460, "loss": 0.1279, "lr": 5.399262741542266e-07, "epoch": 17.313062364256904, "percentage": 86.57, "elapsed_time": "1:43:15", "remaining_time": "0:16:01", "throughput": 5485.29, "total_tokens": 33982800} {"current_steps": 55805, "total_steps": 64460, "loss": 0.1364, "lr": 5.393145079136552e-07, "epoch": 17.31461371393112, "percentage": 86.57, "elapsed_time": "1:43:15", "remaining_time": "0:16:00", "throughput": 5485.32, "total_tokens": 33985872} {"current_steps": 55810, "total_steps": 64460, "loss": 0.1437, "lr": 5.387030686941514e-07, "epoch": 17.316165063605336, "percentage": 86.58, "elapsed_time": "1:43:16", "remaining_time": "0:16:00", "throughput": 5485.42, "total_tokens": 33990224} {"current_steps": 55815, "total_steps": 64460, "loss": 0.1069, "lr": 5.380919565405429e-07, "epoch": 17.317716413279552, "percentage": 86.59, "elapsed_time": "1:43:16", "remaining_time": "0:15:59", "throughput": 5485.46, "total_tokens": 33992944} {"current_steps": 55820, "total_steps": 64460, "loss": 0.1743, "lr": 5.374811714976302e-07, "epoch": 17.31926776295377, "percentage": 86.6, "elapsed_time": "1:43:17", "remaining_time": "0:15:59", "throughput": 5485.46, "total_tokens": 33995472} {"current_steps": 55825, "total_steps": 64460, "loss": 0.1865, "lr": 5.368707136101931e-07, "epoch": 17.320819112627987, "percentage": 86.6, "elapsed_time": "1:43:17", "remaining_time": "0:15:58", "throughput": 5485.47, "total_tokens": 33998096} {"current_steps": 55830, "total_steps": 64460, "loss": 0.1395, "lr": 5.362605829229828e-07, "epoch": 17.322370462302203, "percentage": 86.61, "elapsed_time": "1:43:18", "remaining_time": "0:15:58", "throughput": 5485.51, "total_tokens": 34000976} {"current_steps": 55835, "total_steps": 64460, "loss": 0.1253, "lr": 5.356507794807314e-07, "epoch": 17.32392181197642, "percentage": 86.62, "elapsed_time": "1:43:18", "remaining_time": "0:15:57", "throughput": 5485.51, "total_tokens": 34003728} {"current_steps": 55840, "total_steps": 64460, "loss": 0.0894, "lr": 5.350413033281426e-07, "epoch": 17.325473161650635, "percentage": 86.63, "elapsed_time": "1:43:19", "remaining_time": "0:15:56", "throughput": 5485.51, "total_tokens": 34006288} {"current_steps": 55845, "total_steps": 64460, "loss": 0.0923, "lr": 5.344321545099002e-07, "epoch": 17.327024511324854, "percentage": 86.64, "elapsed_time": "1:43:19", "remaining_time": "0:15:56", "throughput": 5485.55, "total_tokens": 34009040} {"current_steps": 55850, "total_steps": 64460, "loss": 0.1288, "lr": 5.338233330706599e-07, "epoch": 17.32857586099907, "percentage": 86.64, "elapsed_time": "1:43:20", "remaining_time": "0:15:55", "throughput": 5485.6, "total_tokens": 34012016} {"current_steps": 55855, "total_steps": 64460, "loss": 0.1167, "lr": 5.332148390550585e-07, "epoch": 17.330127210673286, "percentage": 86.65, "elapsed_time": "1:43:20", "remaining_time": "0:15:55", "throughput": 5485.73, "total_tokens": 34016048} {"current_steps": 55860, "total_steps": 64460, "loss": 0.1604, "lr": 5.326066725077023e-07, "epoch": 17.331678560347502, "percentage": 86.66, "elapsed_time": "1:43:21", "remaining_time": "0:15:54", "throughput": 5485.75, "total_tokens": 34019120} {"current_steps": 55865, "total_steps": 64460, "loss": 0.1446, "lr": 5.31998833473179e-07, "epoch": 17.333229910021718, "percentage": 86.67, "elapsed_time": "1:43:21", "remaining_time": "0:15:54", "throughput": 5485.76, "total_tokens": 34021648} {"current_steps": 55870, "total_steps": 64460, "loss": 0.3281, "lr": 5.313913219960515e-07, "epoch": 17.334781259695937, "percentage": 86.67, "elapsed_time": "1:43:22", "remaining_time": "0:15:53", "throughput": 5485.81, "total_tokens": 34024528} {"current_steps": 55875, "total_steps": 64460, "loss": 0.1381, "lr": 5.307841381208551e-07, "epoch": 17.336332609370153, "percentage": 86.68, "elapsed_time": "1:43:22", "remaining_time": "0:15:53", "throughput": 5485.81, "total_tokens": 34027056} {"current_steps": 55880, "total_steps": 64460, "loss": 0.0767, "lr": 5.301772818921058e-07, "epoch": 17.33788395904437, "percentage": 86.69, "elapsed_time": "1:43:23", "remaining_time": "0:15:52", "throughput": 5485.91, "total_tokens": 34030672} {"current_steps": 55885, "total_steps": 64460, "loss": 0.1504, "lr": 5.295707533542915e-07, "epoch": 17.339435308718585, "percentage": 86.7, "elapsed_time": "1:43:23", "remaining_time": "0:15:51", "throughput": 5485.95, "total_tokens": 34033744} {"current_steps": 55890, "total_steps": 64460, "loss": 0.0493, "lr": 5.2896455255188e-07, "epoch": 17.3409866583928, "percentage": 86.7, "elapsed_time": "1:43:24", "remaining_time": "0:15:51", "throughput": 5486.02, "total_tokens": 34037328} {"current_steps": 55895, "total_steps": 64460, "loss": 0.2479, "lr": 5.283586795293105e-07, "epoch": 17.342538008067017, "percentage": 86.71, "elapsed_time": "1:43:24", "remaining_time": "0:15:50", "throughput": 5486.05, "total_tokens": 34040144} {"current_steps": 55900, "total_steps": 64460, "loss": 0.1933, "lr": 5.277531343310033e-07, "epoch": 17.344089357741236, "percentage": 86.72, "elapsed_time": "1:43:25", "remaining_time": "0:15:50", "throughput": 5486.09, "total_tokens": 34042864} {"current_steps": 55905, "total_steps": 64460, "loss": 0.1834, "lr": 5.271479170013494e-07, "epoch": 17.345640707415452, "percentage": 86.73, "elapsed_time": "1:43:25", "remaining_time": "0:15:49", "throughput": 5486.05, "total_tokens": 34045136} {"current_steps": 55910, "total_steps": 64460, "loss": 0.1561, "lr": 5.265430275847206e-07, "epoch": 17.347192057089668, "percentage": 86.74, "elapsed_time": "1:43:26", "remaining_time": "0:15:49", "throughput": 5486.05, "total_tokens": 34047664} {"current_steps": 55915, "total_steps": 64460, "loss": 0.0929, "lr": 5.259384661254602e-07, "epoch": 17.348743406763884, "percentage": 86.74, "elapsed_time": "1:43:26", "remaining_time": "0:15:48", "throughput": 5486.05, "total_tokens": 34050160} {"current_steps": 55920, "total_steps": 64460, "loss": 0.134, "lr": 5.253342326678918e-07, "epoch": 17.3502947564381, "percentage": 86.75, "elapsed_time": "1:43:27", "remaining_time": "0:15:47", "throughput": 5486.06, "total_tokens": 34052816} {"current_steps": 55925, "total_steps": 64460, "loss": 0.1734, "lr": 5.247303272563125e-07, "epoch": 17.35184610611232, "percentage": 86.76, "elapsed_time": "1:43:27", "remaining_time": "0:15:47", "throughput": 5486.2, "total_tokens": 34057136} {"current_steps": 55930, "total_steps": 64460, "loss": 0.1296, "lr": 5.241267499349945e-07, "epoch": 17.353397455786535, "percentage": 86.77, "elapsed_time": "1:43:28", "remaining_time": "0:15:46", "throughput": 5486.28, "total_tokens": 34060400} {"current_steps": 55935, "total_steps": 64460, "loss": 0.1058, "lr": 5.235235007481892e-07, "epoch": 17.35494880546075, "percentage": 86.77, "elapsed_time": "1:43:28", "remaining_time": "0:15:46", "throughput": 5486.27, "total_tokens": 34062864} {"current_steps": 55940, "total_steps": 64460, "loss": 0.1562, "lr": 5.229205797401193e-07, "epoch": 17.356500155134967, "percentage": 86.78, "elapsed_time": "1:43:29", "remaining_time": "0:15:45", "throughput": 5486.2, "total_tokens": 34064976} {"current_steps": 55945, "total_steps": 64460, "loss": 0.1887, "lr": 5.223179869549888e-07, "epoch": 17.358051504809183, "percentage": 86.79, "elapsed_time": "1:43:29", "remaining_time": "0:15:45", "throughput": 5486.22, "total_tokens": 34067952} {"current_steps": 55950, "total_steps": 64460, "loss": 0.1334, "lr": 5.217157224369728e-07, "epoch": 17.359602854483402, "percentage": 86.8, "elapsed_time": "1:43:30", "remaining_time": "0:15:44", "throughput": 5486.26, "total_tokens": 34071248} {"current_steps": 55955, "total_steps": 64460, "loss": 0.2136, "lr": 5.211137862302257e-07, "epoch": 17.361154204157618, "percentage": 86.81, "elapsed_time": "1:43:30", "remaining_time": "0:15:44", "throughput": 5486.34, "total_tokens": 34074832} {"current_steps": 55960, "total_steps": 64460, "loss": 0.0935, "lr": 5.205121783788752e-07, "epoch": 17.362705553831834, "percentage": 86.81, "elapsed_time": "1:43:31", "remaining_time": "0:15:43", "throughput": 5486.42, "total_tokens": 34078320} {"current_steps": 55965, "total_steps": 64460, "loss": 0.1495, "lr": 5.199108989270279e-07, "epoch": 17.36425690350605, "percentage": 86.82, "elapsed_time": "1:43:31", "remaining_time": "0:15:42", "throughput": 5486.46, "total_tokens": 34081168} {"current_steps": 55970, "total_steps": 64460, "loss": 0.1915, "lr": 5.19309947918763e-07, "epoch": 17.365808253180266, "percentage": 86.83, "elapsed_time": "1:43:32", "remaining_time": "0:15:42", "throughput": 5486.53, "total_tokens": 34084336} {"current_steps": 55975, "total_steps": 64460, "loss": 0.2419, "lr": 5.187093253981395e-07, "epoch": 17.367359602854485, "percentage": 86.84, "elapsed_time": "1:43:32", "remaining_time": "0:15:41", "throughput": 5486.53, "total_tokens": 34087216} {"current_steps": 55980, "total_steps": 64460, "loss": 0.142, "lr": 5.181090314091874e-07, "epoch": 17.3689109525287, "percentage": 86.84, "elapsed_time": "1:43:33", "remaining_time": "0:15:41", "throughput": 5486.56, "total_tokens": 34089968} {"current_steps": 55985, "total_steps": 64460, "loss": 0.1553, "lr": 5.175090659959176e-07, "epoch": 17.370462302202917, "percentage": 86.85, "elapsed_time": "1:43:33", "remaining_time": "0:15:40", "throughput": 5486.64, "total_tokens": 34093232} {"current_steps": 55990, "total_steps": 64460, "loss": 0.1804, "lr": 5.169094292023141e-07, "epoch": 17.372013651877133, "percentage": 86.86, "elapsed_time": "1:43:34", "remaining_time": "0:15:40", "throughput": 5486.58, "total_tokens": 34095280} {"current_steps": 55995, "total_steps": 64460, "loss": 0.1263, "lr": 5.163101210723365e-07, "epoch": 17.37356500155135, "percentage": 86.87, "elapsed_time": "1:43:34", "remaining_time": "0:15:39", "throughput": 5486.67, "total_tokens": 34099056} {"current_steps": 56000, "total_steps": 64460, "loss": 0.0873, "lr": 5.157111416499227e-07, "epoch": 17.375116351225568, "percentage": 86.88, "elapsed_time": "1:43:35", "remaining_time": "0:15:38", "throughput": 5486.76, "total_tokens": 34102704} {"current_steps": 56005, "total_steps": 64460, "loss": 0.0965, "lr": 5.151124909789835e-07, "epoch": 17.376667700899784, "percentage": 86.88, "elapsed_time": "1:43:35", "remaining_time": "0:15:38", "throughput": 5486.77, "total_tokens": 34105712} {"current_steps": 56010, "total_steps": 64460, "loss": 0.1692, "lr": 5.145141691034084e-07, "epoch": 17.378219050574, "percentage": 86.89, "elapsed_time": "1:43:36", "remaining_time": "0:15:37", "throughput": 5486.88, "total_tokens": 34109648} {"current_steps": 56015, "total_steps": 64460, "loss": 0.231, "lr": 5.139161760670597e-07, "epoch": 17.379770400248216, "percentage": 86.9, "elapsed_time": "1:43:37", "remaining_time": "0:15:37", "throughput": 5486.92, "total_tokens": 34112880} {"current_steps": 56020, "total_steps": 64460, "loss": 0.1078, "lr": 5.133185119137796e-07, "epoch": 17.38132174992243, "percentage": 86.91, "elapsed_time": "1:43:37", "remaining_time": "0:15:36", "throughput": 5487.06, "total_tokens": 34117424} {"current_steps": 56025, "total_steps": 64460, "loss": 0.1304, "lr": 5.127211766873819e-07, "epoch": 17.382873099596647, "percentage": 86.91, "elapsed_time": "1:43:38", "remaining_time": "0:15:36", "throughput": 5487.11, "total_tokens": 34120432} {"current_steps": 56030, "total_steps": 64460, "loss": 0.2007, "lr": 5.121241704316604e-07, "epoch": 17.384424449270867, "percentage": 86.92, "elapsed_time": "1:43:38", "remaining_time": "0:15:35", "throughput": 5487.22, "total_tokens": 34124112} {"current_steps": 56035, "total_steps": 64460, "loss": 0.2495, "lr": 5.115274931903807e-07, "epoch": 17.385975798945083, "percentage": 86.93, "elapsed_time": "1:43:39", "remaining_time": "0:15:35", "throughput": 5487.32, "total_tokens": 34127536} {"current_steps": 56040, "total_steps": 64460, "loss": 0.1102, "lr": 5.109311450072868e-07, "epoch": 17.3875271486193, "percentage": 86.94, "elapsed_time": "1:43:39", "remaining_time": "0:15:34", "throughput": 5487.38, "total_tokens": 34130704} {"current_steps": 56045, "total_steps": 64460, "loss": 0.2594, "lr": 5.103351259260997e-07, "epoch": 17.389078498293514, "percentage": 86.95, "elapsed_time": "1:43:40", "remaining_time": "0:15:33", "throughput": 5487.36, "total_tokens": 34133168} {"current_steps": 56050, "total_steps": 64460, "loss": 0.1712, "lr": 5.097394359905128e-07, "epoch": 17.39062984796773, "percentage": 86.95, "elapsed_time": "1:43:40", "remaining_time": "0:15:33", "throughput": 5487.44, "total_tokens": 34137328} {"current_steps": 56055, "total_steps": 64460, "loss": 0.192, "lr": 5.091440752441984e-07, "epoch": 17.39218119764195, "percentage": 86.96, "elapsed_time": "1:43:41", "remaining_time": "0:15:32", "throughput": 5487.52, "total_tokens": 34140592} {"current_steps": 56060, "total_steps": 64460, "loss": 0.1056, "lr": 5.085490437308021e-07, "epoch": 17.393732547316166, "percentage": 86.97, "elapsed_time": "1:43:41", "remaining_time": "0:15:32", "throughput": 5487.54, "total_tokens": 34143440} {"current_steps": 56065, "total_steps": 64460, "loss": 0.1637, "lr": 5.079543414939487e-07, "epoch": 17.39528389699038, "percentage": 86.98, "elapsed_time": "1:43:42", "remaining_time": "0:15:31", "throughput": 5487.51, "total_tokens": 34145904} {"current_steps": 56070, "total_steps": 64460, "loss": 0.1258, "lr": 5.073599685772346e-07, "epoch": 17.396835246664597, "percentage": 86.98, "elapsed_time": "1:43:43", "remaining_time": "0:15:31", "throughput": 5487.58, "total_tokens": 34149712} {"current_steps": 56075, "total_steps": 64460, "loss": 0.2704, "lr": 5.067659250242368e-07, "epoch": 17.398386596338813, "percentage": 86.99, "elapsed_time": "1:43:43", "remaining_time": "0:15:30", "throughput": 5487.57, "total_tokens": 34152240} {"current_steps": 56080, "total_steps": 64460, "loss": 0.1974, "lr": 5.061722108785033e-07, "epoch": 17.399937946013033, "percentage": 87.0, "elapsed_time": "1:43:44", "remaining_time": "0:15:30", "throughput": 5487.64, "total_tokens": 34155984} {"current_steps": 56085, "total_steps": 64460, "loss": 0.1619, "lr": 5.055788261835631e-07, "epoch": 17.40148929568725, "percentage": 87.01, "elapsed_time": "1:43:44", "remaining_time": "0:15:29", "throughput": 5487.64, "total_tokens": 34158576} {"current_steps": 56090, "total_steps": 64460, "loss": 0.138, "lr": 5.049857709829159e-07, "epoch": 17.403040645361465, "percentage": 87.02, "elapsed_time": "1:43:45", "remaining_time": "0:15:28", "throughput": 5487.7, "total_tokens": 34161840} {"current_steps": 56095, "total_steps": 64460, "loss": 0.1321, "lr": 5.043930453200413e-07, "epoch": 17.40459199503568, "percentage": 87.02, "elapsed_time": "1:43:45", "remaining_time": "0:15:28", "throughput": 5487.67, "total_tokens": 34164144} {"current_steps": 56100, "total_steps": 64460, "loss": 0.184, "lr": 5.038006492383913e-07, "epoch": 17.406143344709896, "percentage": 87.03, "elapsed_time": "1:43:46", "remaining_time": "0:15:27", "throughput": 5487.68, "total_tokens": 34166896} {"current_steps": 56105, "total_steps": 64460, "loss": 0.3044, "lr": 5.03208582781397e-07, "epoch": 17.407694694384116, "percentage": 87.04, "elapsed_time": "1:43:46", "remaining_time": "0:15:27", "throughput": 5487.69, "total_tokens": 34169968} {"current_steps": 56110, "total_steps": 64460, "loss": 0.2576, "lr": 5.02616845992464e-07, "epoch": 17.40924604405833, "percentage": 87.05, "elapsed_time": "1:43:47", "remaining_time": "0:15:26", "throughput": 5487.79, "total_tokens": 34173552} {"current_steps": 56115, "total_steps": 64460, "loss": 0.1809, "lr": 5.020254389149726e-07, "epoch": 17.410797393732548, "percentage": 87.05, "elapsed_time": "1:43:47", "remaining_time": "0:15:26", "throughput": 5487.85, "total_tokens": 34176688} {"current_steps": 56120, "total_steps": 64460, "loss": 0.1961, "lr": 5.014343615922818e-07, "epoch": 17.412348743406763, "percentage": 87.06, "elapsed_time": "1:43:48", "remaining_time": "0:15:25", "throughput": 5487.9, "total_tokens": 34180016} {"current_steps": 56125, "total_steps": 64460, "loss": 0.0803, "lr": 5.008436140677219e-07, "epoch": 17.41390009308098, "percentage": 87.07, "elapsed_time": "1:43:48", "remaining_time": "0:15:25", "throughput": 5487.96, "total_tokens": 34183152} {"current_steps": 56130, "total_steps": 64460, "loss": 0.1199, "lr": 5.002531963846041e-07, "epoch": 17.4154514427552, "percentage": 87.08, "elapsed_time": "1:43:49", "remaining_time": "0:15:24", "throughput": 5488.02, "total_tokens": 34186416} {"current_steps": 56135, "total_steps": 64460, "loss": 0.1393, "lr": 4.996631085862108e-07, "epoch": 17.417002792429415, "percentage": 87.09, "elapsed_time": "1:43:49", "remaining_time": "0:15:23", "throughput": 5488.07, "total_tokens": 34189680} {"current_steps": 56140, "total_steps": 64460, "loss": 0.274, "lr": 4.990733507158052e-07, "epoch": 17.41855414210363, "percentage": 87.09, "elapsed_time": "1:43:50", "remaining_time": "0:15:23", "throughput": 5488.06, "total_tokens": 34192176} {"current_steps": 56145, "total_steps": 64460, "loss": 0.268, "lr": 4.984839228166205e-07, "epoch": 17.420105491777846, "percentage": 87.1, "elapsed_time": "1:43:50", "remaining_time": "0:15:22", "throughput": 5488.1, "total_tokens": 34195088} {"current_steps": 56150, "total_steps": 64460, "loss": 0.1601, "lr": 4.97894824931871e-07, "epoch": 17.421656841452062, "percentage": 87.11, "elapsed_time": "1:43:51", "remaining_time": "0:15:22", "throughput": 5488.13, "total_tokens": 34197872} {"current_steps": 56155, "total_steps": 64460, "loss": 0.1661, "lr": 4.973060571047433e-07, "epoch": 17.423208191126278, "percentage": 87.12, "elapsed_time": "1:43:51", "remaining_time": "0:15:21", "throughput": 5488.22, "total_tokens": 34201200} {"current_steps": 56160, "total_steps": 64460, "loss": 0.0772, "lr": 4.967176193784013e-07, "epoch": 17.424759540800498, "percentage": 87.12, "elapsed_time": "1:43:52", "remaining_time": "0:15:21", "throughput": 5488.25, "total_tokens": 34204304} {"current_steps": 56165, "total_steps": 64460, "loss": 0.1634, "lr": 4.961295117959852e-07, "epoch": 17.426310890474713, "percentage": 87.13, "elapsed_time": "1:43:52", "remaining_time": "0:15:20", "throughput": 5488.22, "total_tokens": 34206544} {"current_steps": 56170, "total_steps": 64460, "loss": 0.0893, "lr": 4.955417344006091e-07, "epoch": 17.42786224014893, "percentage": 87.14, "elapsed_time": "1:43:53", "remaining_time": "0:15:19", "throughput": 5488.29, "total_tokens": 34210096} {"current_steps": 56175, "total_steps": 64460, "loss": 0.2208, "lr": 4.949542872353658e-07, "epoch": 17.429413589823145, "percentage": 87.15, "elapsed_time": "1:43:53", "remaining_time": "0:15:19", "throughput": 5488.31, "total_tokens": 34213040} {"current_steps": 56180, "total_steps": 64460, "loss": 0.0627, "lr": 4.943671703433195e-07, "epoch": 17.43096493949736, "percentage": 87.15, "elapsed_time": "1:43:54", "remaining_time": "0:15:18", "throughput": 5488.31, "total_tokens": 34215952} {"current_steps": 56185, "total_steps": 64460, "loss": 0.1657, "lr": 4.937803837675153e-07, "epoch": 17.43251628917158, "percentage": 87.16, "elapsed_time": "1:43:54", "remaining_time": "0:15:18", "throughput": 5488.33, "total_tokens": 34218960} {"current_steps": 56190, "total_steps": 64460, "loss": 0.1151, "lr": 4.9319392755097e-07, "epoch": 17.434067638845796, "percentage": 87.17, "elapsed_time": "1:43:55", "remaining_time": "0:15:17", "throughput": 5488.41, "total_tokens": 34222352} {"current_steps": 56195, "total_steps": 64460, "loss": 0.1917, "lr": 4.926078017366793e-07, "epoch": 17.435618988520012, "percentage": 87.18, "elapsed_time": "1:43:55", "remaining_time": "0:15:17", "throughput": 5488.47, "total_tokens": 34225360} {"current_steps": 56200, "total_steps": 64460, "loss": 0.094, "lr": 4.920220063676106e-07, "epoch": 17.43717033819423, "percentage": 87.19, "elapsed_time": "1:43:56", "remaining_time": "0:15:16", "throughput": 5488.5, "total_tokens": 34228304} {"current_steps": 56205, "total_steps": 64460, "loss": 0.1507, "lr": 4.914365414867128e-07, "epoch": 17.438721687868444, "percentage": 87.19, "elapsed_time": "1:43:56", "remaining_time": "0:15:16", "throughput": 5488.52, "total_tokens": 34231120} {"current_steps": 56210, "total_steps": 64460, "loss": 0.1834, "lr": 4.908514071369052e-07, "epoch": 17.440273037542664, "percentage": 87.2, "elapsed_time": "1:43:57", "remaining_time": "0:15:15", "throughput": 5488.54, "total_tokens": 34233904} {"current_steps": 56215, "total_steps": 64460, "loss": 0.1162, "lr": 4.902666033610864e-07, "epoch": 17.44182438721688, "percentage": 87.21, "elapsed_time": "1:43:57", "remaining_time": "0:15:14", "throughput": 5488.62, "total_tokens": 34237456} {"current_steps": 56220, "total_steps": 64460, "loss": 0.2167, "lr": 4.896821302021276e-07, "epoch": 17.443375736891095, "percentage": 87.22, "elapsed_time": "1:43:58", "remaining_time": "0:15:14", "throughput": 5488.67, "total_tokens": 34240624} {"current_steps": 56225, "total_steps": 64460, "loss": 0.1657, "lr": 4.890979877028795e-07, "epoch": 17.44492708656531, "percentage": 87.22, "elapsed_time": "1:43:58", "remaining_time": "0:15:13", "throughput": 5488.69, "total_tokens": 34243280} {"current_steps": 56230, "total_steps": 64460, "loss": 0.2358, "lr": 4.885141759061663e-07, "epoch": 17.446478436239527, "percentage": 87.23, "elapsed_time": "1:43:59", "remaining_time": "0:15:13", "throughput": 5488.78, "total_tokens": 34246672} {"current_steps": 56235, "total_steps": 64460, "loss": 0.1289, "lr": 4.879306948547874e-07, "epoch": 17.448029785913747, "percentage": 87.24, "elapsed_time": "1:43:59", "remaining_time": "0:15:12", "throughput": 5488.79, "total_tokens": 34249680} {"current_steps": 56240, "total_steps": 64460, "loss": 0.1844, "lr": 4.873475445915199e-07, "epoch": 17.449581135587962, "percentage": 87.25, "elapsed_time": "1:44:00", "remaining_time": "0:15:12", "throughput": 5488.83, "total_tokens": 34252464} {"current_steps": 56245, "total_steps": 64460, "loss": 0.2291, "lr": 4.867647251591146e-07, "epoch": 17.45113248526218, "percentage": 87.26, "elapsed_time": "1:44:00", "remaining_time": "0:15:11", "throughput": 5488.9, "total_tokens": 34255696} {"current_steps": 56250, "total_steps": 64460, "loss": 0.1622, "lr": 4.861822366003011e-07, "epoch": 17.452683834936394, "percentage": 87.26, "elapsed_time": "1:44:01", "remaining_time": "0:15:10", "throughput": 5488.99, "total_tokens": 34259600} {"current_steps": 56255, "total_steps": 64460, "loss": 0.1128, "lr": 4.856000789577797e-07, "epoch": 17.45423518461061, "percentage": 87.27, "elapsed_time": "1:44:02", "remaining_time": "0:15:10", "throughput": 5489.07, "total_tokens": 34264368} {"current_steps": 56260, "total_steps": 64460, "loss": 0.0928, "lr": 4.850182522742319e-07, "epoch": 17.45578653428483, "percentage": 87.28, "elapsed_time": "1:44:02", "remaining_time": "0:15:09", "throughput": 5489.14, "total_tokens": 34267472} {"current_steps": 56265, "total_steps": 64460, "loss": 0.1641, "lr": 4.844367565923109e-07, "epoch": 17.457337883959045, "percentage": 87.29, "elapsed_time": "1:44:03", "remaining_time": "0:15:09", "throughput": 5489.19, "total_tokens": 34270800} {"current_steps": 56270, "total_steps": 64460, "loss": 0.1554, "lr": 4.838555919546484e-07, "epoch": 17.45888923363326, "percentage": 87.29, "elapsed_time": "1:44:03", "remaining_time": "0:15:08", "throughput": 5489.24, "total_tokens": 34274000} {"current_steps": 56275, "total_steps": 64460, "loss": 0.1235, "lr": 4.8327475840385e-07, "epoch": 17.460440583307477, "percentage": 87.3, "elapsed_time": "1:44:04", "remaining_time": "0:15:08", "throughput": 5489.26, "total_tokens": 34276816} {"current_steps": 56280, "total_steps": 64460, "loss": 0.1646, "lr": 4.826942559824982e-07, "epoch": 17.461991932981693, "percentage": 87.31, "elapsed_time": "1:44:04", "remaining_time": "0:15:07", "throughput": 5489.26, "total_tokens": 34279504} {"current_steps": 56285, "total_steps": 64460, "loss": 0.1958, "lr": 4.821140847331495e-07, "epoch": 17.46354328265591, "percentage": 87.32, "elapsed_time": "1:44:05", "remaining_time": "0:15:07", "throughput": 5489.23, "total_tokens": 34282160} {"current_steps": 56290, "total_steps": 64460, "loss": 0.1007, "lr": 4.815342446983379e-07, "epoch": 17.46509463233013, "percentage": 87.33, "elapsed_time": "1:44:05", "remaining_time": "0:15:06", "throughput": 5489.25, "total_tokens": 34284976} {"current_steps": 56295, "total_steps": 64460, "loss": 0.1007, "lr": 4.809547359205741e-07, "epoch": 17.466645982004344, "percentage": 87.33, "elapsed_time": "1:44:06", "remaining_time": "0:15:05", "throughput": 5489.29, "total_tokens": 34287792} {"current_steps": 56300, "total_steps": 64460, "loss": 0.2354, "lr": 4.803755584423409e-07, "epoch": 17.46819733167856, "percentage": 87.34, "elapsed_time": "1:44:06", "remaining_time": "0:15:05", "throughput": 5489.32, "total_tokens": 34290832} {"current_steps": 56305, "total_steps": 64460, "loss": 0.1622, "lr": 4.797967123061003e-07, "epoch": 17.469748681352776, "percentage": 87.35, "elapsed_time": "1:44:07", "remaining_time": "0:15:04", "throughput": 5489.36, "total_tokens": 34293680} {"current_steps": 56310, "total_steps": 64460, "loss": 0.1375, "lr": 4.79218197554287e-07, "epoch": 17.471300031026992, "percentage": 87.36, "elapsed_time": "1:44:07", "remaining_time": "0:15:04", "throughput": 5489.34, "total_tokens": 34296016} {"current_steps": 56315, "total_steps": 64460, "loss": 0.1555, "lr": 4.78640014229314e-07, "epoch": 17.47285138070121, "percentage": 87.36, "elapsed_time": "1:44:08", "remaining_time": "0:15:03", "throughput": 5489.38, "total_tokens": 34298928} {"current_steps": 56320, "total_steps": 64460, "loss": 0.2212, "lr": 4.780621623735687e-07, "epoch": 17.474402730375427, "percentage": 87.37, "elapsed_time": "1:44:08", "remaining_time": "0:15:03", "throughput": 5489.32, "total_tokens": 34301072} {"current_steps": 56325, "total_steps": 64460, "loss": 0.1955, "lr": 4.774846420294155e-07, "epoch": 17.475954080049643, "percentage": 87.38, "elapsed_time": "1:44:09", "remaining_time": "0:15:02", "throughput": 5489.35, "total_tokens": 34303920} {"current_steps": 56330, "total_steps": 64460, "loss": 0.1466, "lr": 4.769074532391921e-07, "epoch": 17.47750542972386, "percentage": 87.39, "elapsed_time": "1:44:09", "remaining_time": "0:15:02", "throughput": 5489.36, "total_tokens": 34306576} {"current_steps": 56335, "total_steps": 64460, "loss": 0.1509, "lr": 4.7633059604521416e-07, "epoch": 17.479056779398075, "percentage": 87.4, "elapsed_time": "1:44:10", "remaining_time": "0:15:01", "throughput": 5489.32, "total_tokens": 34308976} {"current_steps": 56340, "total_steps": 64460, "loss": 0.1326, "lr": 4.757540704897712e-07, "epoch": 17.480608129072294, "percentage": 87.4, "elapsed_time": "1:44:10", "remaining_time": "0:15:00", "throughput": 5489.36, "total_tokens": 34311920} {"current_steps": 56345, "total_steps": 64460, "loss": 0.235, "lr": 4.75177876615131e-07, "epoch": 17.48215947874651, "percentage": 87.41, "elapsed_time": "1:44:11", "remaining_time": "0:15:00", "throughput": 5489.44, "total_tokens": 34315472} {"current_steps": 56350, "total_steps": 64460, "loss": 0.3208, "lr": 4.7460201446353325e-07, "epoch": 17.483710828420726, "percentage": 87.42, "elapsed_time": "1:44:11", "remaining_time": "0:14:59", "throughput": 5489.57, "total_tokens": 34319728} {"current_steps": 56355, "total_steps": 64460, "loss": 0.1542, "lr": 4.7402648407719744e-07, "epoch": 17.485262178094942, "percentage": 87.43, "elapsed_time": "1:44:12", "remaining_time": "0:14:59", "throughput": 5489.54, "total_tokens": 34322160} {"current_steps": 56360, "total_steps": 64460, "loss": 0.207, "lr": 4.734512854983153e-07, "epoch": 17.486813527769158, "percentage": 87.43, "elapsed_time": "1:44:12", "remaining_time": "0:14:58", "throughput": 5489.56, "total_tokens": 34325040} {"current_steps": 56365, "total_steps": 64460, "loss": 0.1756, "lr": 4.7287641876905654e-07, "epoch": 17.488364877443377, "percentage": 87.44, "elapsed_time": "1:44:13", "remaining_time": "0:14:58", "throughput": 5489.69, "total_tokens": 34329648} {"current_steps": 56370, "total_steps": 64460, "loss": 0.2544, "lr": 4.7230188393156516e-07, "epoch": 17.489916227117593, "percentage": 87.45, "elapsed_time": "1:44:14", "remaining_time": "0:14:57", "throughput": 5489.81, "total_tokens": 34333616} {"current_steps": 56375, "total_steps": 64460, "loss": 0.0942, "lr": 4.717276810279614e-07, "epoch": 17.49146757679181, "percentage": 87.46, "elapsed_time": "1:44:14", "remaining_time": "0:14:56", "throughput": 5489.9, "total_tokens": 34337008} {"current_steps": 56380, "total_steps": 64460, "loss": 0.0877, "lr": 4.711538101003427e-07, "epoch": 17.493018926466025, "percentage": 87.47, "elapsed_time": "1:44:15", "remaining_time": "0:14:56", "throughput": 5489.93, "total_tokens": 34340080} {"current_steps": 56385, "total_steps": 64460, "loss": 0.1379, "lr": 4.7058027119077755e-07, "epoch": 17.49457027614024, "percentage": 87.47, "elapsed_time": "1:44:15", "remaining_time": "0:14:55", "throughput": 5490.01, "total_tokens": 34343280} {"current_steps": 56390, "total_steps": 64460, "loss": 0.0799, "lr": 4.7000706434131627e-07, "epoch": 17.49612162581446, "percentage": 87.48, "elapsed_time": "1:44:16", "remaining_time": "0:14:55", "throughput": 5490.09, "total_tokens": 34346960} {"current_steps": 56395, "total_steps": 64460, "loss": 0.2702, "lr": 4.694341895939797e-07, "epoch": 17.497672975488676, "percentage": 87.49, "elapsed_time": "1:44:16", "remaining_time": "0:14:54", "throughput": 5490.11, "total_tokens": 34350032} {"current_steps": 56400, "total_steps": 64460, "loss": 0.0957, "lr": 4.688616469907675e-07, "epoch": 17.499224325162892, "percentage": 87.5, "elapsed_time": "1:44:17", "remaining_time": "0:14:54", "throughput": 5490.11, "total_tokens": 34352720} {"current_steps": 56405, "total_steps": 64460, "loss": 0.1618, "lr": 4.682894365736523e-07, "epoch": 17.500775674837108, "percentage": 87.5, "elapsed_time": "1:44:17", "remaining_time": "0:14:53", "throughput": 5490.27, "total_tokens": 34357552} {"current_steps": 56410, "total_steps": 64460, "loss": 0.2191, "lr": 4.677175583845861e-07, "epoch": 17.502327024511324, "percentage": 87.51, "elapsed_time": "1:44:18", "remaining_time": "0:14:53", "throughput": 5490.26, "total_tokens": 34360016} {"current_steps": 56415, "total_steps": 64460, "loss": 0.1436, "lr": 4.6714601246549197e-07, "epoch": 17.50387837418554, "percentage": 87.52, "elapsed_time": "1:44:18", "remaining_time": "0:14:52", "throughput": 5490.2, "total_tokens": 34362288} {"current_steps": 56420, "total_steps": 64460, "loss": 0.1153, "lr": 4.6657479885827304e-07, "epoch": 17.50542972385976, "percentage": 87.53, "elapsed_time": "1:44:19", "remaining_time": "0:14:51", "throughput": 5490.29, "total_tokens": 34365776} {"current_steps": 56425, "total_steps": 64460, "loss": 0.1599, "lr": 4.660039176048042e-07, "epoch": 17.506981073533975, "percentage": 87.53, "elapsed_time": "1:44:19", "remaining_time": "0:14:51", "throughput": 5490.29, "total_tokens": 34368592} {"current_steps": 56430, "total_steps": 64460, "loss": 0.0806, "lr": 4.654333687469392e-07, "epoch": 17.50853242320819, "percentage": 87.54, "elapsed_time": "1:44:20", "remaining_time": "0:14:50", "throughput": 5490.28, "total_tokens": 34371056} {"current_steps": 56435, "total_steps": 64460, "loss": 0.1618, "lr": 4.6486315232650626e-07, "epoch": 17.510083772882407, "percentage": 87.55, "elapsed_time": "1:44:20", "remaining_time": "0:14:50", "throughput": 5490.32, "total_tokens": 34374864} {"current_steps": 56440, "total_steps": 64460, "loss": 0.1937, "lr": 4.6429326838530685e-07, "epoch": 17.511635122556623, "percentage": 87.56, "elapsed_time": "1:44:21", "remaining_time": "0:14:49", "throughput": 5490.38, "total_tokens": 34378448} {"current_steps": 56445, "total_steps": 64460, "loss": 0.1049, "lr": 4.637237169651232e-07, "epoch": 17.513186472230842, "percentage": 87.57, "elapsed_time": "1:44:22", "remaining_time": "0:14:49", "throughput": 5490.48, "total_tokens": 34382544} {"current_steps": 56450, "total_steps": 64460, "loss": 0.3705, "lr": 4.631544981077074e-07, "epoch": 17.514737821905058, "percentage": 87.57, "elapsed_time": "1:44:22", "remaining_time": "0:14:48", "throughput": 5490.53, "total_tokens": 34385840} {"current_steps": 56455, "total_steps": 64460, "loss": 0.1624, "lr": 4.625856118547922e-07, "epoch": 17.516289171579274, "percentage": 87.58, "elapsed_time": "1:44:23", "remaining_time": "0:14:48", "throughput": 5490.62, "total_tokens": 34389584} {"current_steps": 56460, "total_steps": 64460, "loss": 0.2311, "lr": 4.6201705824808205e-07, "epoch": 17.51784052125349, "percentage": 87.59, "elapsed_time": "1:44:23", "remaining_time": "0:14:47", "throughput": 5490.6, "total_tokens": 34392464} {"current_steps": 56465, "total_steps": 64460, "loss": 0.2143, "lr": 4.614488373292597e-07, "epoch": 17.519391870927706, "percentage": 87.6, "elapsed_time": "1:44:24", "remaining_time": "0:14:46", "throughput": 5490.59, "total_tokens": 34395216} {"current_steps": 56470, "total_steps": 64460, "loss": 0.162, "lr": 4.608809491399818e-07, "epoch": 17.520943220601925, "percentage": 87.6, "elapsed_time": "1:44:24", "remaining_time": "0:14:46", "throughput": 5490.6, "total_tokens": 34398032} {"current_steps": 56475, "total_steps": 64460, "loss": 0.2052, "lr": 4.6031339372188176e-07, "epoch": 17.52249457027614, "percentage": 87.61, "elapsed_time": "1:44:25", "remaining_time": "0:14:45", "throughput": 5490.55, "total_tokens": 34400528} {"current_steps": 56480, "total_steps": 64460, "loss": 0.1688, "lr": 4.597461711165674e-07, "epoch": 17.524045919950357, "percentage": 87.62, "elapsed_time": "1:44:26", "remaining_time": "0:14:45", "throughput": 5490.74, "total_tokens": 34406544} {"current_steps": 56485, "total_steps": 64460, "loss": 0.1792, "lr": 4.591792813656243e-07, "epoch": 17.525597269624573, "percentage": 87.63, "elapsed_time": "1:44:26", "remaining_time": "0:14:44", "throughput": 5490.76, "total_tokens": 34409424} {"current_steps": 56490, "total_steps": 64460, "loss": 0.0973, "lr": 4.5861272451060976e-07, "epoch": 17.52714861929879, "percentage": 87.64, "elapsed_time": "1:44:27", "remaining_time": "0:14:44", "throughput": 5490.82, "total_tokens": 34412688} {"current_steps": 56495, "total_steps": 64460, "loss": 0.1471, "lr": 4.580465005930612e-07, "epoch": 17.528699968973008, "percentage": 87.64, "elapsed_time": "1:44:27", "remaining_time": "0:14:43", "throughput": 5490.85, "total_tokens": 34415696} {"current_steps": 56500, "total_steps": 64460, "loss": 0.1042, "lr": 4.5748060965448984e-07, "epoch": 17.530251318647224, "percentage": 87.65, "elapsed_time": "1:44:28", "remaining_time": "0:14:43", "throughput": 5490.91, "total_tokens": 34418928} {"current_steps": 56505, "total_steps": 64460, "loss": 0.0856, "lr": 4.569150517363802e-07, "epoch": 17.53180266832144, "percentage": 87.66, "elapsed_time": "1:44:28", "remaining_time": "0:14:42", "throughput": 5490.98, "total_tokens": 34422736} {"current_steps": 56510, "total_steps": 64460, "loss": 0.1477, "lr": 4.563498268801958e-07, "epoch": 17.533354017995656, "percentage": 87.67, "elapsed_time": "1:44:29", "remaining_time": "0:14:42", "throughput": 5490.92, "total_tokens": 34424912} {"current_steps": 56515, "total_steps": 64460, "loss": 0.1598, "lr": 4.5578493512737356e-07, "epoch": 17.53490536766987, "percentage": 87.67, "elapsed_time": "1:44:29", "remaining_time": "0:14:41", "throughput": 5490.98, "total_tokens": 34428048} {"current_steps": 56520, "total_steps": 64460, "loss": 0.152, "lr": 4.5522037651932803e-07, "epoch": 17.53645671734409, "percentage": 87.68, "elapsed_time": "1:44:30", "remaining_time": "0:14:40", "throughput": 5490.96, "total_tokens": 34430672} {"current_steps": 56525, "total_steps": 64460, "loss": 0.1629, "lr": 4.546561510974462e-07, "epoch": 17.538008067018307, "percentage": 87.69, "elapsed_time": "1:44:30", "remaining_time": "0:14:40", "throughput": 5491.02, "total_tokens": 34434064} {"current_steps": 56530, "total_steps": 64460, "loss": 0.0709, "lr": 4.540922589030944e-07, "epoch": 17.539559416692523, "percentage": 87.7, "elapsed_time": "1:44:31", "remaining_time": "0:14:39", "throughput": 5491.09, "total_tokens": 34437680} {"current_steps": 56535, "total_steps": 64460, "loss": 0.2078, "lr": 4.535286999776106e-07, "epoch": 17.54111076636674, "percentage": 87.71, "elapsed_time": "1:44:32", "remaining_time": "0:14:39", "throughput": 5491.15, "total_tokens": 34440880} {"current_steps": 56540, "total_steps": 64460, "loss": 0.244, "lr": 4.529654743623124e-07, "epoch": 17.542662116040955, "percentage": 87.71, "elapsed_time": "1:44:32", "remaining_time": "0:14:38", "throughput": 5491.18, "total_tokens": 34444080} {"current_steps": 56545, "total_steps": 64460, "loss": 0.1688, "lr": 4.5240258209848896e-07, "epoch": 17.54421346571517, "percentage": 87.72, "elapsed_time": "1:44:33", "remaining_time": "0:14:38", "throughput": 5491.22, "total_tokens": 34446992} {"current_steps": 56550, "total_steps": 64460, "loss": 0.0881, "lr": 4.5184002322740784e-07, "epoch": 17.54576481538939, "percentage": 87.73, "elapsed_time": "1:44:33", "remaining_time": "0:14:37", "throughput": 5491.25, "total_tokens": 34450000} {"current_steps": 56555, "total_steps": 64460, "loss": 0.1595, "lr": 4.5127779779031213e-07, "epoch": 17.547316165063606, "percentage": 87.74, "elapsed_time": "1:44:34", "remaining_time": "0:14:36", "throughput": 5491.26, "total_tokens": 34452720} {"current_steps": 56560, "total_steps": 64460, "loss": 0.1569, "lr": 4.5071590582841773e-07, "epoch": 17.54886751473782, "percentage": 87.74, "elapsed_time": "1:44:34", "remaining_time": "0:14:36", "throughput": 5491.33, "total_tokens": 34456464} {"current_steps": 56565, "total_steps": 64460, "loss": 0.1691, "lr": 4.501543473829201e-07, "epoch": 17.550418864412038, "percentage": 87.75, "elapsed_time": "1:44:35", "remaining_time": "0:14:35", "throughput": 5491.36, "total_tokens": 34459472} {"current_steps": 56570, "total_steps": 64460, "loss": 0.1861, "lr": 4.495931224949862e-07, "epoch": 17.551970214086253, "percentage": 87.76, "elapsed_time": "1:44:35", "remaining_time": "0:14:35", "throughput": 5491.23, "total_tokens": 34461648} {"current_steps": 56575, "total_steps": 64460, "loss": 0.2149, "lr": 4.4903223120576213e-07, "epoch": 17.553521563760473, "percentage": 87.77, "elapsed_time": "1:44:36", "remaining_time": "0:14:34", "throughput": 5491.18, "total_tokens": 34463984} {"current_steps": 56580, "total_steps": 64460, "loss": 0.2735, "lr": 4.484716735563666e-07, "epoch": 17.55507291343469, "percentage": 87.78, "elapsed_time": "1:44:36", "remaining_time": "0:14:34", "throughput": 5491.21, "total_tokens": 34466864} {"current_steps": 56585, "total_steps": 64460, "loss": 0.1657, "lr": 4.4791144958789556e-07, "epoch": 17.556624263108905, "percentage": 87.78, "elapsed_time": "1:44:37", "remaining_time": "0:14:33", "throughput": 5491.26, "total_tokens": 34471280} {"current_steps": 56590, "total_steps": 64460, "loss": 0.2238, "lr": 4.473515593414196e-07, "epoch": 17.55817561278312, "percentage": 87.79, "elapsed_time": "1:44:38", "remaining_time": "0:14:33", "throughput": 5491.3, "total_tokens": 34474608} {"current_steps": 56595, "total_steps": 64460, "loss": 0.1953, "lr": 4.4679200285798694e-07, "epoch": 17.559726962457336, "percentage": 87.8, "elapsed_time": "1:44:38", "remaining_time": "0:14:32", "throughput": 5491.29, "total_tokens": 34477424} {"current_steps": 56600, "total_steps": 64460, "loss": 0.2447, "lr": 4.4623278017861703e-07, "epoch": 17.561278312131556, "percentage": 87.81, "elapsed_time": "1:44:39", "remaining_time": "0:14:31", "throughput": 5491.28, "total_tokens": 34480144} {"current_steps": 56605, "total_steps": 64460, "loss": 0.1602, "lr": 4.456738913443104e-07, "epoch": 17.56282966180577, "percentage": 87.81, "elapsed_time": "1:44:39", "remaining_time": "0:14:31", "throughput": 5491.28, "total_tokens": 34482864} {"current_steps": 56610, "total_steps": 64460, "loss": 0.0993, "lr": 4.4511533639603753e-07, "epoch": 17.564381011479988, "percentage": 87.82, "elapsed_time": "1:44:40", "remaining_time": "0:14:30", "throughput": 5491.34, "total_tokens": 34486096} {"current_steps": 56615, "total_steps": 64460, "loss": 0.1328, "lr": 4.4455711537474857e-07, "epoch": 17.565932361154204, "percentage": 87.83, "elapsed_time": "1:44:40", "remaining_time": "0:14:30", "throughput": 5491.42, "total_tokens": 34489648} {"current_steps": 56620, "total_steps": 64460, "loss": 0.2465, "lr": 4.4399922832136844e-07, "epoch": 17.56748371082842, "percentage": 87.84, "elapsed_time": "1:44:41", "remaining_time": "0:14:29", "throughput": 5491.44, "total_tokens": 34492720} {"current_steps": 56625, "total_steps": 64460, "loss": 0.1352, "lr": 4.434416752767956e-07, "epoch": 17.56903506050264, "percentage": 87.85, "elapsed_time": "1:44:41", "remaining_time": "0:14:29", "throughput": 5491.53, "total_tokens": 34496336} {"current_steps": 56630, "total_steps": 64460, "loss": 0.0711, "lr": 4.4288445628190566e-07, "epoch": 17.570586410176855, "percentage": 87.85, "elapsed_time": "1:44:42", "remaining_time": "0:14:28", "throughput": 5491.73, "total_tokens": 34501808} {"current_steps": 56635, "total_steps": 64460, "loss": 0.0993, "lr": 4.423275713775493e-07, "epoch": 17.57213775985107, "percentage": 87.86, "elapsed_time": "1:44:43", "remaining_time": "0:14:28", "throughput": 5491.76, "total_tokens": 34504912} {"current_steps": 56640, "total_steps": 64460, "loss": 0.1481, "lr": 4.4177102060455337e-07, "epoch": 17.573689109525287, "percentage": 87.87, "elapsed_time": "1:44:43", "remaining_time": "0:14:27", "throughput": 5491.76, "total_tokens": 34507856} {"current_steps": 56645, "total_steps": 64460, "loss": 0.1373, "lr": 4.412148040037184e-07, "epoch": 17.575240459199502, "percentage": 87.88, "elapsed_time": "1:44:44", "remaining_time": "0:14:26", "throughput": 5491.87, "total_tokens": 34511856} {"current_steps": 56650, "total_steps": 64460, "loss": 0.1229, "lr": 4.40658921615823e-07, "epoch": 17.576791808873722, "percentage": 87.88, "elapsed_time": "1:44:44", "remaining_time": "0:14:26", "throughput": 5491.87, "total_tokens": 34514576} {"current_steps": 56655, "total_steps": 64460, "loss": 0.1375, "lr": 4.4010337348161847e-07, "epoch": 17.578343158547938, "percentage": 87.89, "elapsed_time": "1:44:45", "remaining_time": "0:14:25", "throughput": 5491.83, "total_tokens": 34516944} {"current_steps": 56660, "total_steps": 64460, "loss": 0.2111, "lr": 4.3954815964183496e-07, "epoch": 17.579894508222154, "percentage": 87.9, "elapsed_time": "1:44:45", "remaining_time": "0:14:25", "throughput": 5491.87, "total_tokens": 34520336} {"current_steps": 56665, "total_steps": 64460, "loss": 0.1082, "lr": 4.3899328013717437e-07, "epoch": 17.58144585789637, "percentage": 87.91, "elapsed_time": "1:44:46", "remaining_time": "0:14:24", "throughput": 5491.86, "total_tokens": 34522960} {"current_steps": 56670, "total_steps": 64460, "loss": 0.1489, "lr": 4.3843873500831693e-07, "epoch": 17.582997207570585, "percentage": 87.91, "elapsed_time": "1:44:46", "remaining_time": "0:14:24", "throughput": 5491.79, "total_tokens": 34525296} {"current_steps": 56675, "total_steps": 64460, "loss": 0.2239, "lr": 4.378845242959179e-07, "epoch": 17.5845485572448, "percentage": 87.92, "elapsed_time": "1:44:47", "remaining_time": "0:14:23", "throughput": 5491.79, "total_tokens": 34528112} {"current_steps": 56680, "total_steps": 64460, "loss": 0.1404, "lr": 4.373306480406059e-07, "epoch": 17.58609990691902, "percentage": 87.93, "elapsed_time": "1:44:47", "remaining_time": "0:14:23", "throughput": 5491.77, "total_tokens": 34530768} {"current_steps": 56685, "total_steps": 64460, "loss": 0.1285, "lr": 4.3677710628298784e-07, "epoch": 17.587651256593237, "percentage": 87.94, "elapsed_time": "1:44:48", "remaining_time": "0:14:22", "throughput": 5491.87, "total_tokens": 34534288} {"current_steps": 56690, "total_steps": 64460, "loss": 0.1555, "lr": 4.3622389906364413e-07, "epoch": 17.589202606267452, "percentage": 87.95, "elapsed_time": "1:44:48", "remaining_time": "0:14:21", "throughput": 5491.81, "total_tokens": 34536368} {"current_steps": 56695, "total_steps": 64460, "loss": 0.2074, "lr": 4.3567102642313287e-07, "epoch": 17.59075395594167, "percentage": 87.95, "elapsed_time": "1:44:49", "remaining_time": "0:14:21", "throughput": 5491.83, "total_tokens": 34539088} {"current_steps": 56700, "total_steps": 64460, "loss": 0.1796, "lr": 4.351184884019838e-07, "epoch": 17.592305305615884, "percentage": 87.96, "elapsed_time": "1:44:49", "remaining_time": "0:14:20", "throughput": 5491.84, "total_tokens": 34541680} {"current_steps": 56705, "total_steps": 64460, "loss": 0.1531, "lr": 4.3456628504070674e-07, "epoch": 17.593856655290104, "percentage": 87.97, "elapsed_time": "1:44:50", "remaining_time": "0:14:20", "throughput": 5491.86, "total_tokens": 34544784} {"current_steps": 56710, "total_steps": 64460, "loss": 0.2031, "lr": 4.3401441637978325e-07, "epoch": 17.59540800496432, "percentage": 87.98, "elapsed_time": "1:44:50", "remaining_time": "0:14:19", "throughput": 5491.95, "total_tokens": 34548176} {"current_steps": 56715, "total_steps": 64460, "loss": 0.2607, "lr": 4.334628824596732e-07, "epoch": 17.596959354638535, "percentage": 87.98, "elapsed_time": "1:44:51", "remaining_time": "0:14:19", "throughput": 5491.94, "total_tokens": 34550704} {"current_steps": 56720, "total_steps": 64460, "loss": 0.1718, "lr": 4.329116833208086e-07, "epoch": 17.59851070431275, "percentage": 87.99, "elapsed_time": "1:44:51", "remaining_time": "0:14:18", "throughput": 5491.94, "total_tokens": 34553392} {"current_steps": 56725, "total_steps": 64460, "loss": 0.1093, "lr": 4.3236081900360105e-07, "epoch": 17.600062053986967, "percentage": 88.0, "elapsed_time": "1:44:52", "remaining_time": "0:14:18", "throughput": 5492.03, "total_tokens": 34556976} {"current_steps": 56730, "total_steps": 64460, "loss": 0.2604, "lr": 4.3181028954843386e-07, "epoch": 17.601613403661187, "percentage": 88.01, "elapsed_time": "1:44:52", "remaining_time": "0:14:17", "throughput": 5492.0, "total_tokens": 34559344} {"current_steps": 56735, "total_steps": 64460, "loss": 0.1707, "lr": 4.3126009499566747e-07, "epoch": 17.603164753335403, "percentage": 88.02, "elapsed_time": "1:44:53", "remaining_time": "0:14:16", "throughput": 5492.08, "total_tokens": 34562960} {"current_steps": 56740, "total_steps": 64460, "loss": 0.1008, "lr": 4.3071023538563904e-07, "epoch": 17.60471610300962, "percentage": 88.02, "elapsed_time": "1:44:53", "remaining_time": "0:14:16", "throughput": 5492.02, "total_tokens": 34565136} {"current_steps": 56745, "total_steps": 64460, "loss": 0.1541, "lr": 4.3016071075865805e-07, "epoch": 17.606267452683834, "percentage": 88.03, "elapsed_time": "1:44:54", "remaining_time": "0:14:15", "throughput": 5492.03, "total_tokens": 34567920} {"current_steps": 56750, "total_steps": 64460, "loss": 0.186, "lr": 4.296115211550128e-07, "epoch": 17.60781880235805, "percentage": 88.04, "elapsed_time": "1:44:54", "remaining_time": "0:14:15", "throughput": 5492.07, "total_tokens": 34570928} {"current_steps": 56755, "total_steps": 64460, "loss": 0.1887, "lr": 4.2906266661496385e-07, "epoch": 17.60937015203227, "percentage": 88.05, "elapsed_time": "1:44:55", "remaining_time": "0:14:14", "throughput": 5492.11, "total_tokens": 34573776} {"current_steps": 56760, "total_steps": 64460, "loss": 0.1236, "lr": 4.285141471787502e-07, "epoch": 17.610921501706486, "percentage": 88.05, "elapsed_time": "1:44:55", "remaining_time": "0:14:14", "throughput": 5492.19, "total_tokens": 34577744} {"current_steps": 56765, "total_steps": 64460, "loss": 0.1171, "lr": 4.279659628865829e-07, "epoch": 17.6124728513807, "percentage": 88.06, "elapsed_time": "1:44:56", "remaining_time": "0:14:13", "throughput": 5492.19, "total_tokens": 34580176} {"current_steps": 56770, "total_steps": 64460, "loss": 0.1816, "lr": 4.274181137786526e-07, "epoch": 17.614024201054917, "percentage": 88.07, "elapsed_time": "1:44:56", "remaining_time": "0:14:12", "throughput": 5492.25, "total_tokens": 34583920} {"current_steps": 56775, "total_steps": 64460, "loss": 0.1688, "lr": 4.2687059989512114e-07, "epoch": 17.615575550729133, "percentage": 88.08, "elapsed_time": "1:44:57", "remaining_time": "0:14:12", "throughput": 5492.23, "total_tokens": 34586512} {"current_steps": 56780, "total_steps": 64460, "loss": 0.1258, "lr": 4.263234212761297e-07, "epoch": 17.617126900403353, "percentage": 88.09, "elapsed_time": "1:44:57", "remaining_time": "0:14:11", "throughput": 5492.25, "total_tokens": 34589104} {"current_steps": 56785, "total_steps": 64460, "loss": 0.2312, "lr": 4.2577657796179116e-07, "epoch": 17.61867825007757, "percentage": 88.09, "elapsed_time": "1:44:58", "remaining_time": "0:14:11", "throughput": 5492.33, "total_tokens": 34592432} {"current_steps": 56790, "total_steps": 64460, "loss": 0.1504, "lr": 4.2523006999219575e-07, "epoch": 17.620229599751784, "percentage": 88.1, "elapsed_time": "1:44:58", "remaining_time": "0:14:10", "throughput": 5492.37, "total_tokens": 34595600} {"current_steps": 56795, "total_steps": 64460, "loss": 0.2211, "lr": 4.246838974074108e-07, "epoch": 17.621780949426, "percentage": 88.11, "elapsed_time": "1:44:59", "remaining_time": "0:14:10", "throughput": 5492.36, "total_tokens": 34598448} {"current_steps": 56800, "total_steps": 64460, "loss": 0.1748, "lr": 4.241380602474754e-07, "epoch": 17.623332299100216, "percentage": 88.12, "elapsed_time": "1:44:59", "remaining_time": "0:14:09", "throughput": 5492.29, "total_tokens": 34600560} {"current_steps": 56805, "total_steps": 64460, "loss": 0.1186, "lr": 4.23592558552407e-07, "epoch": 17.624883648774436, "percentage": 88.12, "elapsed_time": "1:45:00", "remaining_time": "0:14:09", "throughput": 5492.27, "total_tokens": 34603280} {"current_steps": 56810, "total_steps": 64460, "loss": 0.2526, "lr": 4.230473923621964e-07, "epoch": 17.62643499844865, "percentage": 88.13, "elapsed_time": "1:45:00", "remaining_time": "0:14:08", "throughput": 5492.24, "total_tokens": 34605712} {"current_steps": 56815, "total_steps": 64460, "loss": 0.1971, "lr": 4.225025617168116e-07, "epoch": 17.627986348122867, "percentage": 88.14, "elapsed_time": "1:45:01", "remaining_time": "0:14:07", "throughput": 5492.23, "total_tokens": 34608528} {"current_steps": 56820, "total_steps": 64460, "loss": 0.1606, "lr": 4.2195806665619396e-07, "epoch": 17.629537697797083, "percentage": 88.15, "elapsed_time": "1:45:01", "remaining_time": "0:14:07", "throughput": 5492.23, "total_tokens": 34611280} {"current_steps": 56825, "total_steps": 64460, "loss": 0.128, "lr": 4.2141390722026276e-07, "epoch": 17.6310890474713, "percentage": 88.16, "elapsed_time": "1:45:02", "remaining_time": "0:14:06", "throughput": 5492.25, "total_tokens": 34613936} {"current_steps": 56830, "total_steps": 64460, "loss": 0.1066, "lr": 4.2087008344891043e-07, "epoch": 17.632640397145515, "percentage": 88.16, "elapsed_time": "1:45:02", "remaining_time": "0:14:06", "throughput": 5492.32, "total_tokens": 34617136} {"current_steps": 56835, "total_steps": 64460, "loss": 0.1065, "lr": 4.203265953820063e-07, "epoch": 17.634191746819734, "percentage": 88.17, "elapsed_time": "1:45:03", "remaining_time": "0:14:05", "throughput": 5492.37, "total_tokens": 34620944} {"current_steps": 56840, "total_steps": 64460, "loss": 0.188, "lr": 4.197834430593939e-07, "epoch": 17.63574309649395, "percentage": 88.18, "elapsed_time": "1:45:03", "remaining_time": "0:14:05", "throughput": 5492.32, "total_tokens": 34623184} {"current_steps": 56845, "total_steps": 64460, "loss": 0.2131, "lr": 4.1924062652089316e-07, "epoch": 17.637294446168166, "percentage": 88.19, "elapsed_time": "1:45:04", "remaining_time": "0:14:04", "throughput": 5492.26, "total_tokens": 34625360} {"current_steps": 56850, "total_steps": 64460, "loss": 0.1433, "lr": 4.186981458062983e-07, "epoch": 17.638845795842382, "percentage": 88.19, "elapsed_time": "1:45:04", "remaining_time": "0:14:03", "throughput": 5492.31, "total_tokens": 34628464} {"current_steps": 56855, "total_steps": 64460, "loss": 0.1799, "lr": 4.1815600095538035e-07, "epoch": 17.640397145516598, "percentage": 88.2, "elapsed_time": "1:45:05", "remaining_time": "0:14:03", "throughput": 5492.34, "total_tokens": 34632336} {"current_steps": 56860, "total_steps": 64460, "loss": 0.1571, "lr": 4.1761419200788525e-07, "epoch": 17.641948495190817, "percentage": 88.21, "elapsed_time": "1:45:06", "remaining_time": "0:14:02", "throughput": 5492.4, "total_tokens": 34635504} {"current_steps": 56865, "total_steps": 64460, "loss": 0.1602, "lr": 4.1707271900353285e-07, "epoch": 17.643499844865033, "percentage": 88.22, "elapsed_time": "1:45:06", "remaining_time": "0:14:02", "throughput": 5492.44, "total_tokens": 34638800} {"current_steps": 56870, "total_steps": 64460, "loss": 0.2039, "lr": 4.1653158198202036e-07, "epoch": 17.64505119453925, "percentage": 88.23, "elapsed_time": "1:45:07", "remaining_time": "0:14:01", "throughput": 5492.42, "total_tokens": 34641200} {"current_steps": 56875, "total_steps": 64460, "loss": 0.1772, "lr": 4.159907809830188e-07, "epoch": 17.646602544213465, "percentage": 88.23, "elapsed_time": "1:45:07", "remaining_time": "0:14:01", "throughput": 5492.4, "total_tokens": 34643920} {"current_steps": 56880, "total_steps": 64460, "loss": 0.1337, "lr": 4.15450316046177e-07, "epoch": 17.64815389388768, "percentage": 88.24, "elapsed_time": "1:45:08", "remaining_time": "0:14:00", "throughput": 5492.43, "total_tokens": 34646896} {"current_steps": 56885, "total_steps": 64460, "loss": 0.1314, "lr": 4.1491018721111496e-07, "epoch": 17.6497052435619, "percentage": 88.25, "elapsed_time": "1:45:08", "remaining_time": "0:14:00", "throughput": 5492.52, "total_tokens": 34650416} {"current_steps": 56890, "total_steps": 64460, "loss": 0.1108, "lr": 4.1437039451743265e-07, "epoch": 17.651256593236116, "percentage": 88.26, "elapsed_time": "1:45:09", "remaining_time": "0:13:59", "throughput": 5492.61, "total_tokens": 34654064} {"current_steps": 56895, "total_steps": 64460, "loss": 0.3572, "lr": 4.138309380047006e-07, "epoch": 17.652807942910332, "percentage": 88.26, "elapsed_time": "1:45:09", "remaining_time": "0:13:58", "throughput": 5492.6, "total_tokens": 34656432} {"current_steps": 56900, "total_steps": 64460, "loss": 0.2364, "lr": 4.1329181771247117e-07, "epoch": 17.654359292584548, "percentage": 88.27, "elapsed_time": "1:45:10", "remaining_time": "0:13:58", "throughput": 5492.61, "total_tokens": 34659376} {"current_steps": 56905, "total_steps": 64460, "loss": 0.1336, "lr": 4.127530336802654e-07, "epoch": 17.655910642258764, "percentage": 88.28, "elapsed_time": "1:45:10", "remaining_time": "0:13:57", "throughput": 5492.68, "total_tokens": 34662704} {"current_steps": 56910, "total_steps": 64460, "loss": 0.1805, "lr": 4.1221458594758404e-07, "epoch": 17.657461991932983, "percentage": 88.29, "elapsed_time": "1:45:11", "remaining_time": "0:13:57", "throughput": 5492.76, "total_tokens": 34666416} {"current_steps": 56915, "total_steps": 64460, "loss": 0.136, "lr": 4.1167647455390037e-07, "epoch": 17.6590133416072, "percentage": 88.3, "elapsed_time": "1:45:11", "remaining_time": "0:13:56", "throughput": 5492.79, "total_tokens": 34669264} {"current_steps": 56920, "total_steps": 64460, "loss": 0.1697, "lr": 4.111386995386657e-07, "epoch": 17.660564691281415, "percentage": 88.3, "elapsed_time": "1:45:12", "remaining_time": "0:13:56", "throughput": 5492.73, "total_tokens": 34671920} {"current_steps": 56925, "total_steps": 64460, "loss": 0.1662, "lr": 4.10601260941304e-07, "epoch": 17.66211604095563, "percentage": 88.31, "elapsed_time": "1:45:12", "remaining_time": "0:13:55", "throughput": 5492.84, "total_tokens": 34676208} {"current_steps": 56930, "total_steps": 64460, "loss": 0.115, "lr": 4.100641588012172e-07, "epoch": 17.663667390629847, "percentage": 88.32, "elapsed_time": "1:45:13", "remaining_time": "0:13:55", "throughput": 5492.83, "total_tokens": 34678800} {"current_steps": 56935, "total_steps": 64460, "loss": 0.1162, "lr": 4.095273931577792e-07, "epoch": 17.665218740304063, "percentage": 88.33, "elapsed_time": "1:45:14", "remaining_time": "0:13:54", "throughput": 5492.91, "total_tokens": 34682256} {"current_steps": 56940, "total_steps": 64460, "loss": 0.1649, "lr": 4.089909640503431e-07, "epoch": 17.666770089978282, "percentage": 88.33, "elapsed_time": "1:45:14", "remaining_time": "0:13:53", "throughput": 5493.06, "total_tokens": 34687248} {"current_steps": 56945, "total_steps": 64460, "loss": 0.1468, "lr": 4.084548715182357e-07, "epoch": 17.668321439652498, "percentage": 88.34, "elapsed_time": "1:45:15", "remaining_time": "0:13:53", "throughput": 5493.13, "total_tokens": 34690512} {"current_steps": 56950, "total_steps": 64460, "loss": 0.1182, "lr": 4.0791911560075783e-07, "epoch": 17.669872789326714, "percentage": 88.35, "elapsed_time": "1:45:15", "remaining_time": "0:13:52", "throughput": 5493.16, "total_tokens": 34693232} {"current_steps": 56955, "total_steps": 64460, "loss": 0.1485, "lr": 4.0738369633718746e-07, "epoch": 17.67142413900093, "percentage": 88.36, "elapsed_time": "1:45:16", "remaining_time": "0:13:52", "throughput": 5493.21, "total_tokens": 34696496} {"current_steps": 56960, "total_steps": 64460, "loss": 0.1853, "lr": 4.0684861376677596e-07, "epoch": 17.672975488675146, "percentage": 88.36, "elapsed_time": "1:45:16", "remaining_time": "0:13:51", "throughput": 5493.18, "total_tokens": 34698736} {"current_steps": 56965, "total_steps": 64460, "loss": 0.1741, "lr": 4.0631386792875314e-07, "epoch": 17.674526838349365, "percentage": 88.37, "elapsed_time": "1:45:17", "remaining_time": "0:13:51", "throughput": 5493.24, "total_tokens": 34702160} {"current_steps": 56970, "total_steps": 64460, "loss": 0.1006, "lr": 4.0577945886232096e-07, "epoch": 17.67607818802358, "percentage": 88.38, "elapsed_time": "1:45:17", "remaining_time": "0:13:50", "throughput": 5493.31, "total_tokens": 34705360} {"current_steps": 56975, "total_steps": 64460, "loss": 0.2207, "lr": 4.05245386606658e-07, "epoch": 17.677629537697797, "percentage": 88.39, "elapsed_time": "1:45:18", "remaining_time": "0:13:50", "throughput": 5493.4, "total_tokens": 34709328} {"current_steps": 56980, "total_steps": 64460, "loss": 0.1841, "lr": 4.0471165120091805e-07, "epoch": 17.679180887372013, "percentage": 88.4, "elapsed_time": "1:45:18", "remaining_time": "0:13:49", "throughput": 5493.38, "total_tokens": 34711696} {"current_steps": 56985, "total_steps": 64460, "loss": 0.1286, "lr": 4.0417825268423085e-07, "epoch": 17.68073223704623, "percentage": 88.4, "elapsed_time": "1:45:19", "remaining_time": "0:13:48", "throughput": 5493.5, "total_tokens": 34716400} {"current_steps": 56990, "total_steps": 64460, "loss": 0.1779, "lr": 4.0364519109570013e-07, "epoch": 17.682283586720448, "percentage": 88.41, "elapsed_time": "1:45:20", "remaining_time": "0:13:48", "throughput": 5493.56, "total_tokens": 34719728} {"current_steps": 56995, "total_steps": 64460, "loss": 0.1062, "lr": 4.0311246647440517e-07, "epoch": 17.683834936394664, "percentage": 88.42, "elapsed_time": "1:45:20", "remaining_time": "0:13:47", "throughput": 5493.67, "total_tokens": 34723536} {"current_steps": 57000, "total_steps": 64460, "loss": 0.2343, "lr": 4.025800788594031e-07, "epoch": 17.68538628606888, "percentage": 88.43, "elapsed_time": "1:45:21", "remaining_time": "0:13:47", "throughput": 5493.7, "total_tokens": 34726416} {"current_steps": 57005, "total_steps": 64460, "loss": 0.1526, "lr": 4.0204802828972156e-07, "epoch": 17.686937635743096, "percentage": 88.43, "elapsed_time": "1:45:21", "remaining_time": "0:13:46", "throughput": 5493.83, "total_tokens": 34730672} {"current_steps": 57010, "total_steps": 64460, "loss": 0.1554, "lr": 4.0151631480436883e-07, "epoch": 17.68848898541731, "percentage": 88.44, "elapsed_time": "1:45:22", "remaining_time": "0:13:46", "throughput": 5493.86, "total_tokens": 34733648} {"current_steps": 57015, "total_steps": 64460, "loss": 0.2387, "lr": 4.009849384423231e-07, "epoch": 17.69004033509153, "percentage": 88.45, "elapsed_time": "1:45:22", "remaining_time": "0:13:45", "throughput": 5493.9, "total_tokens": 34736880} {"current_steps": 57020, "total_steps": 64460, "loss": 0.1803, "lr": 4.004538992425427e-07, "epoch": 17.691591684765747, "percentage": 88.46, "elapsed_time": "1:45:23", "remaining_time": "0:13:45", "throughput": 5493.86, "total_tokens": 34739376} {"current_steps": 57025, "total_steps": 64460, "loss": 0.1331, "lr": 3.9992319724395767e-07, "epoch": 17.693143034439963, "percentage": 88.47, "elapsed_time": "1:45:23", "remaining_time": "0:13:44", "throughput": 5493.89, "total_tokens": 34742320} {"current_steps": 57030, "total_steps": 64460, "loss": 0.1487, "lr": 3.9939283248547623e-07, "epoch": 17.69469438411418, "percentage": 88.47, "elapsed_time": "1:45:24", "remaining_time": "0:13:43", "throughput": 5493.91, "total_tokens": 34745008} {"current_steps": 57035, "total_steps": 64460, "loss": 0.1223, "lr": 3.9886280500597896e-07, "epoch": 17.696245733788395, "percentage": 88.48, "elapsed_time": "1:45:25", "remaining_time": "0:13:43", "throughput": 5494.04, "total_tokens": 34751248} {"current_steps": 57040, "total_steps": 64460, "loss": 0.1505, "lr": 3.9833311484432367e-07, "epoch": 17.697797083462614, "percentage": 88.49, "elapsed_time": "1:45:25", "remaining_time": "0:13:42", "throughput": 5494.08, "total_tokens": 34754704} {"current_steps": 57045, "total_steps": 64460, "loss": 0.172, "lr": 3.978037620393427e-07, "epoch": 17.69934843313683, "percentage": 88.5, "elapsed_time": "1:45:26", "remaining_time": "0:13:42", "throughput": 5494.12, "total_tokens": 34757488} {"current_steps": 57050, "total_steps": 64460, "loss": 0.1575, "lr": 3.972747466298449e-07, "epoch": 17.700899782811046, "percentage": 88.5, "elapsed_time": "1:45:26", "remaining_time": "0:13:41", "throughput": 5494.06, "total_tokens": 34759632} {"current_steps": 57055, "total_steps": 64460, "loss": 0.2505, "lr": 3.967460686546115e-07, "epoch": 17.702451132485262, "percentage": 88.51, "elapsed_time": "1:45:27", "remaining_time": "0:13:41", "throughput": 5494.09, "total_tokens": 34762736} {"current_steps": 57060, "total_steps": 64460, "loss": 0.2105, "lr": 3.9621772815240214e-07, "epoch": 17.704002482159478, "percentage": 88.52, "elapsed_time": "1:45:27", "remaining_time": "0:13:40", "throughput": 5494.12, "total_tokens": 34765680} {"current_steps": 57065, "total_steps": 64460, "loss": 0.1613, "lr": 3.9568972516195124e-07, "epoch": 17.705553831833697, "percentage": 88.53, "elapsed_time": "1:45:28", "remaining_time": "0:13:40", "throughput": 5494.06, "total_tokens": 34768144} {"current_steps": 57070, "total_steps": 64460, "loss": 0.1591, "lr": 3.9516205972196573e-07, "epoch": 17.707105181507913, "percentage": 88.54, "elapsed_time": "1:45:28", "remaining_time": "0:13:39", "throughput": 5494.07, "total_tokens": 34770768} {"current_steps": 57075, "total_steps": 64460, "loss": 0.1454, "lr": 3.9463473187113134e-07, "epoch": 17.70865653118213, "percentage": 88.54, "elapsed_time": "1:45:29", "remaining_time": "0:13:38", "throughput": 5494.06, "total_tokens": 34773200} {"current_steps": 57080, "total_steps": 64460, "loss": 0.1531, "lr": 3.941077416481065e-07, "epoch": 17.710207880856345, "percentage": 88.55, "elapsed_time": "1:45:29", "remaining_time": "0:13:38", "throughput": 5494.2, "total_tokens": 34777648} {"current_steps": 57085, "total_steps": 64460, "loss": 0.2546, "lr": 3.935810890915265e-07, "epoch": 17.71175923053056, "percentage": 88.56, "elapsed_time": "1:45:30", "remaining_time": "0:13:37", "throughput": 5494.22, "total_tokens": 34780752} {"current_steps": 57090, "total_steps": 64460, "loss": 0.2105, "lr": 3.9305477423999985e-07, "epoch": 17.713310580204777, "percentage": 88.57, "elapsed_time": "1:45:31", "remaining_time": "0:13:37", "throughput": 5494.32, "total_tokens": 34784656} {"current_steps": 57095, "total_steps": 64460, "loss": 0.1973, "lr": 3.9252879713211343e-07, "epoch": 17.714861929878996, "percentage": 88.57, "elapsed_time": "1:45:31", "remaining_time": "0:13:36", "throughput": 5494.4, "total_tokens": 34787984} {"current_steps": 57100, "total_steps": 64460, "loss": 0.0652, "lr": 3.920031578064265e-07, "epoch": 17.716413279553212, "percentage": 88.58, "elapsed_time": "1:45:32", "remaining_time": "0:13:36", "throughput": 5494.39, "total_tokens": 34790800} {"current_steps": 57105, "total_steps": 64460, "loss": 0.1457, "lr": 3.914778563014754e-07, "epoch": 17.717964629227428, "percentage": 88.59, "elapsed_time": "1:45:32", "remaining_time": "0:13:35", "throughput": 5494.4, "total_tokens": 34793488} {"current_steps": 57110, "total_steps": 64460, "loss": 0.0943, "lr": 3.9095289265576984e-07, "epoch": 17.719515978901644, "percentage": 88.6, "elapsed_time": "1:45:33", "remaining_time": "0:13:35", "throughput": 5494.51, "total_tokens": 34797296} {"current_steps": 57115, "total_steps": 64460, "loss": 0.119, "lr": 3.9042826690779633e-07, "epoch": 17.72106732857586, "percentage": 88.61, "elapsed_time": "1:45:33", "remaining_time": "0:13:34", "throughput": 5494.44, "total_tokens": 34799344} {"current_steps": 57120, "total_steps": 64460, "loss": 0.1133, "lr": 3.8990397909601743e-07, "epoch": 17.72261867825008, "percentage": 88.61, "elapsed_time": "1:45:34", "remaining_time": "0:13:33", "throughput": 5494.51, "total_tokens": 34802896} {"current_steps": 57125, "total_steps": 64460, "loss": 0.2125, "lr": 3.893800292588673e-07, "epoch": 17.724170027924295, "percentage": 88.62, "elapsed_time": "1:45:34", "remaining_time": "0:13:33", "throughput": 5494.57, "total_tokens": 34805904} {"current_steps": 57130, "total_steps": 64460, "loss": 0.1484, "lr": 3.8885641743476034e-07, "epoch": 17.72572137759851, "percentage": 88.63, "elapsed_time": "1:45:35", "remaining_time": "0:13:32", "throughput": 5494.51, "total_tokens": 34808432} {"current_steps": 57135, "total_steps": 64460, "loss": 0.1004, "lr": 3.8833314366208077e-07, "epoch": 17.727272727272727, "percentage": 88.64, "elapsed_time": "1:45:35", "remaining_time": "0:13:32", "throughput": 5494.69, "total_tokens": 34813840} {"current_steps": 57140, "total_steps": 64460, "loss": 0.1467, "lr": 3.878102079791934e-07, "epoch": 17.728824076946943, "percentage": 88.64, "elapsed_time": "1:45:36", "remaining_time": "0:13:31", "throughput": 5494.74, "total_tokens": 34816912} {"current_steps": 57145, "total_steps": 64460, "loss": 0.2331, "lr": 3.872876104244333e-07, "epoch": 17.730375426621162, "percentage": 88.65, "elapsed_time": "1:45:36", "remaining_time": "0:13:31", "throughput": 5494.77, "total_tokens": 34819856} {"current_steps": 57150, "total_steps": 64460, "loss": 0.1456, "lr": 3.8676535103611466e-07, "epoch": 17.731926776295378, "percentage": 88.66, "elapsed_time": "1:45:37", "remaining_time": "0:13:30", "throughput": 5494.76, "total_tokens": 34822256} {"current_steps": 57155, "total_steps": 64460, "loss": 0.1027, "lr": 3.862434298525236e-07, "epoch": 17.733478125969594, "percentage": 88.67, "elapsed_time": "1:45:37", "remaining_time": "0:13:30", "throughput": 5494.8, "total_tokens": 34825040} {"current_steps": 57160, "total_steps": 64460, "loss": 0.1458, "lr": 3.857218469119256e-07, "epoch": 17.73502947564381, "percentage": 88.68, "elapsed_time": "1:45:38", "remaining_time": "0:13:29", "throughput": 5494.85, "total_tokens": 34827984} {"current_steps": 57165, "total_steps": 64460, "loss": 0.1075, "lr": 3.8520060225255616e-07, "epoch": 17.736580825318025, "percentage": 88.68, "elapsed_time": "1:45:38", "remaining_time": "0:13:28", "throughput": 5494.87, "total_tokens": 34831408} {"current_steps": 57170, "total_steps": 64460, "loss": 0.18, "lr": 3.8467969591263145e-07, "epoch": 17.738132174992245, "percentage": 88.69, "elapsed_time": "1:45:39", "remaining_time": "0:13:28", "throughput": 5494.93, "total_tokens": 34834480} {"current_steps": 57175, "total_steps": 64460, "loss": 0.1837, "lr": 3.841591279303369e-07, "epoch": 17.73968352466646, "percentage": 88.7, "elapsed_time": "1:45:39", "remaining_time": "0:13:27", "throughput": 5494.85, "total_tokens": 34836720} {"current_steps": 57180, "total_steps": 64460, "loss": 0.1982, "lr": 3.836388983438383e-07, "epoch": 17.741234874340677, "percentage": 88.71, "elapsed_time": "1:45:40", "remaining_time": "0:13:27", "throughput": 5494.81, "total_tokens": 34838992} {"current_steps": 57185, "total_steps": 64460, "loss": 0.1902, "lr": 3.831190071912755e-07, "epoch": 17.742786224014893, "percentage": 88.71, "elapsed_time": "1:45:40", "remaining_time": "0:13:26", "throughput": 5494.76, "total_tokens": 34841424} {"current_steps": 57190, "total_steps": 64460, "loss": 0.1038, "lr": 3.825994545107603e-07, "epoch": 17.74433757368911, "percentage": 88.72, "elapsed_time": "1:45:41", "remaining_time": "0:13:26", "throughput": 5494.75, "total_tokens": 34843824} {"current_steps": 57195, "total_steps": 64460, "loss": 0.1043, "lr": 3.820802403403845e-07, "epoch": 17.745888923363324, "percentage": 88.73, "elapsed_time": "1:45:41", "remaining_time": "0:13:25", "throughput": 5494.83, "total_tokens": 34847312} {"current_steps": 57200, "total_steps": 64460, "loss": 0.1671, "lr": 3.8156136471821036e-07, "epoch": 17.747440273037544, "percentage": 88.74, "elapsed_time": "1:45:42", "remaining_time": "0:13:24", "throughput": 5494.8, "total_tokens": 34849776} {"current_steps": 57205, "total_steps": 64460, "loss": 0.1247, "lr": 3.8104282768227976e-07, "epoch": 17.74899162271176, "percentage": 88.74, "elapsed_time": "1:45:42", "remaining_time": "0:13:24", "throughput": 5494.78, "total_tokens": 34852272} {"current_steps": 57210, "total_steps": 64460, "loss": 0.1909, "lr": 3.805246292706055e-07, "epoch": 17.750542972385976, "percentage": 88.75, "elapsed_time": "1:45:43", "remaining_time": "0:13:23", "throughput": 5494.71, "total_tokens": 34854640} {"current_steps": 57215, "total_steps": 64460, "loss": 0.1822, "lr": 3.8000676952117954e-07, "epoch": 17.75209432206019, "percentage": 88.76, "elapsed_time": "1:45:43", "remaining_time": "0:13:23", "throughput": 5494.74, "total_tokens": 34857392} {"current_steps": 57220, "total_steps": 64460, "loss": 0.1417, "lr": 3.794892484719653e-07, "epoch": 17.753645671734407, "percentage": 88.77, "elapsed_time": "1:45:44", "remaining_time": "0:13:22", "throughput": 5494.75, "total_tokens": 34860112} {"current_steps": 57225, "total_steps": 64460, "loss": 0.1783, "lr": 3.7897206616090533e-07, "epoch": 17.755197021408627, "percentage": 88.78, "elapsed_time": "1:45:44", "remaining_time": "0:13:22", "throughput": 5494.82, "total_tokens": 34863344} {"current_steps": 57230, "total_steps": 64460, "loss": 0.1179, "lr": 3.7845522262591303e-07, "epoch": 17.756748371082843, "percentage": 88.78, "elapsed_time": "1:45:45", "remaining_time": "0:13:21", "throughput": 5494.82, "total_tokens": 34865936} {"current_steps": 57235, "total_steps": 64460, "loss": 0.0856, "lr": 3.77938717904881e-07, "epoch": 17.75829972075706, "percentage": 88.79, "elapsed_time": "1:45:45", "remaining_time": "0:13:21", "throughput": 5494.83, "total_tokens": 34868720} {"current_steps": 57240, "total_steps": 64460, "loss": 0.1127, "lr": 3.7742255203567337e-07, "epoch": 17.759851070431274, "percentage": 88.8, "elapsed_time": "1:45:46", "remaining_time": "0:13:20", "throughput": 5494.83, "total_tokens": 34871280} {"current_steps": 57245, "total_steps": 64460, "loss": 0.141, "lr": 3.769067250561326e-07, "epoch": 17.76140242010549, "percentage": 88.81, "elapsed_time": "1:45:46", "remaining_time": "0:13:19", "throughput": 5494.93, "total_tokens": 34874992} {"current_steps": 57250, "total_steps": 64460, "loss": 0.1376, "lr": 3.763912370040751e-07, "epoch": 17.76295376977971, "percentage": 88.81, "elapsed_time": "1:45:47", "remaining_time": "0:13:19", "throughput": 5494.93, "total_tokens": 34877488} {"current_steps": 57255, "total_steps": 64460, "loss": 0.1449, "lr": 3.7587608791729067e-07, "epoch": 17.764505119453926, "percentage": 88.82, "elapsed_time": "1:45:47", "remaining_time": "0:13:18", "throughput": 5495.02, "total_tokens": 34881488} {"current_steps": 57260, "total_steps": 64460, "loss": 0.1893, "lr": 3.7536127783354746e-07, "epoch": 17.76605646912814, "percentage": 88.83, "elapsed_time": "1:45:48", "remaining_time": "0:13:18", "throughput": 5495.09, "total_tokens": 34884720} {"current_steps": 57265, "total_steps": 64460, "loss": 0.1186, "lr": 3.7484680679058636e-07, "epoch": 17.767607818802357, "percentage": 88.84, "elapsed_time": "1:45:48", "remaining_time": "0:13:17", "throughput": 5495.14, "total_tokens": 34887664} {"current_steps": 57270, "total_steps": 64460, "loss": 0.1775, "lr": 3.7433267482612447e-07, "epoch": 17.769159168476573, "percentage": 88.85, "elapsed_time": "1:45:49", "remaining_time": "0:13:17", "throughput": 5495.19, "total_tokens": 34890672} {"current_steps": 57275, "total_steps": 64460, "loss": 0.1692, "lr": 3.7381888197785323e-07, "epoch": 17.770710518150793, "percentage": 88.85, "elapsed_time": "1:45:49", "remaining_time": "0:13:16", "throughput": 5495.19, "total_tokens": 34893904} {"current_steps": 57280, "total_steps": 64460, "loss": 0.109, "lr": 3.7330542828344087e-07, "epoch": 17.77226186782501, "percentage": 88.86, "elapsed_time": "1:45:50", "remaining_time": "0:13:16", "throughput": 5495.24, "total_tokens": 34896944} {"current_steps": 57285, "total_steps": 64460, "loss": 0.0742, "lr": 3.727923137805278e-07, "epoch": 17.773813217499224, "percentage": 88.87, "elapsed_time": "1:45:50", "remaining_time": "0:13:15", "throughput": 5495.27, "total_tokens": 34900080} {"current_steps": 57290, "total_steps": 64460, "loss": 0.1448, "lr": 3.722795385067335e-07, "epoch": 17.77536456717344, "percentage": 88.88, "elapsed_time": "1:45:51", "remaining_time": "0:13:14", "throughput": 5495.35, "total_tokens": 34903536} {"current_steps": 57295, "total_steps": 64460, "loss": 0.1606, "lr": 3.717671024996489e-07, "epoch": 17.776915916847656, "percentage": 88.88, "elapsed_time": "1:45:51", "remaining_time": "0:13:14", "throughput": 5495.36, "total_tokens": 34906160} {"current_steps": 57300, "total_steps": 64460, "loss": 0.0905, "lr": 3.712550057968417e-07, "epoch": 17.778467266521876, "percentage": 88.89, "elapsed_time": "1:45:52", "remaining_time": "0:13:13", "throughput": 5495.43, "total_tokens": 34909360} {"current_steps": 57305, "total_steps": 64460, "loss": 0.1892, "lr": 3.707432484358564e-07, "epoch": 17.78001861619609, "percentage": 88.9, "elapsed_time": "1:45:53", "remaining_time": "0:13:13", "throughput": 5495.56, "total_tokens": 34913648} {"current_steps": 57310, "total_steps": 64460, "loss": 0.1049, "lr": 3.7023183045420794e-07, "epoch": 17.781569965870307, "percentage": 88.91, "elapsed_time": "1:45:53", "remaining_time": "0:13:12", "throughput": 5495.66, "total_tokens": 34917488} {"current_steps": 57315, "total_steps": 64460, "loss": 0.1968, "lr": 3.697207518893925e-07, "epoch": 17.783121315544523, "percentage": 88.92, "elapsed_time": "1:45:54", "remaining_time": "0:13:12", "throughput": 5495.71, "total_tokens": 34920784} {"current_steps": 57320, "total_steps": 64460, "loss": 0.2588, "lr": 3.692100127788756e-07, "epoch": 17.78467266521874, "percentage": 88.92, "elapsed_time": "1:45:54", "remaining_time": "0:13:11", "throughput": 5495.7, "total_tokens": 34923376} {"current_steps": 57325, "total_steps": 64460, "loss": 0.1413, "lr": 3.686996131601028e-07, "epoch": 17.78622401489296, "percentage": 88.93, "elapsed_time": "1:45:55", "remaining_time": "0:13:11", "throughput": 5495.76, "total_tokens": 34926672} {"current_steps": 57330, "total_steps": 64460, "loss": 0.1874, "lr": 3.6818955307048985e-07, "epoch": 17.787775364567175, "percentage": 88.94, "elapsed_time": "1:45:55", "remaining_time": "0:13:10", "throughput": 5495.74, "total_tokens": 34929072} {"current_steps": 57335, "total_steps": 64460, "loss": 0.191, "lr": 3.6767983254743236e-07, "epoch": 17.78932671424139, "percentage": 88.95, "elapsed_time": "1:45:56", "remaining_time": "0:13:09", "throughput": 5495.81, "total_tokens": 34932368} {"current_steps": 57340, "total_steps": 64460, "loss": 0.2308, "lr": 3.6717045162829703e-07, "epoch": 17.790878063915606, "percentage": 88.95, "elapsed_time": "1:45:56", "remaining_time": "0:13:09", "throughput": 5495.84, "total_tokens": 34935216} {"current_steps": 57345, "total_steps": 64460, "loss": 0.1609, "lr": 3.6666141035042956e-07, "epoch": 17.792429413589822, "percentage": 88.96, "elapsed_time": "1:45:57", "remaining_time": "0:13:08", "throughput": 5495.89, "total_tokens": 34939088} {"current_steps": 57350, "total_steps": 64460, "loss": 0.1653, "lr": 3.661527087511468e-07, "epoch": 17.793980763264038, "percentage": 88.97, "elapsed_time": "1:45:57", "remaining_time": "0:13:08", "throughput": 5495.88, "total_tokens": 34941680} {"current_steps": 57355, "total_steps": 64460, "loss": 0.2104, "lr": 3.656443468677445e-07, "epoch": 17.795532112938258, "percentage": 88.98, "elapsed_time": "1:45:58", "remaining_time": "0:13:07", "throughput": 5495.8, "total_tokens": 34943664} {"current_steps": 57360, "total_steps": 64460, "loss": 0.1316, "lr": 3.651363247374895e-07, "epoch": 17.797083462612473, "percentage": 88.99, "elapsed_time": "1:45:58", "remaining_time": "0:13:07", "throughput": 5495.85, "total_tokens": 34947152} {"current_steps": 57365, "total_steps": 64460, "loss": 0.2692, "lr": 3.6462864239762697e-07, "epoch": 17.79863481228669, "percentage": 88.99, "elapsed_time": "1:45:59", "remaining_time": "0:13:06", "throughput": 5495.83, "total_tokens": 34949744} {"current_steps": 57370, "total_steps": 64460, "loss": 0.0949, "lr": 3.641212998853766e-07, "epoch": 17.800186161960905, "percentage": 89.0, "elapsed_time": "1:45:59", "remaining_time": "0:13:05", "throughput": 5495.91, "total_tokens": 34953168} {"current_steps": 57375, "total_steps": 64460, "loss": 0.1032, "lr": 3.636142972379314e-07, "epoch": 17.80173751163512, "percentage": 89.01, "elapsed_time": "1:46:00", "remaining_time": "0:13:05", "throughput": 5495.91, "total_tokens": 34955856} {"current_steps": 57380, "total_steps": 64460, "loss": 0.1227, "lr": 3.631076344924617e-07, "epoch": 17.80328886130934, "percentage": 89.02, "elapsed_time": "1:46:00", "remaining_time": "0:13:04", "throughput": 5496.01, "total_tokens": 34959600} {"current_steps": 57385, "total_steps": 64460, "loss": 0.1481, "lr": 3.62601311686111e-07, "epoch": 17.804840210983556, "percentage": 89.02, "elapsed_time": "1:46:01", "remaining_time": "0:13:04", "throughput": 5496.09, "total_tokens": 34963376} {"current_steps": 57390, "total_steps": 64460, "loss": 0.1356, "lr": 3.6209532885599973e-07, "epoch": 17.806391560657772, "percentage": 89.03, "elapsed_time": "1:46:02", "remaining_time": "0:13:03", "throughput": 5496.13, "total_tokens": 34966416} {"current_steps": 57395, "total_steps": 64460, "loss": 0.2017, "lr": 3.6158968603922093e-07, "epoch": 17.807942910331988, "percentage": 89.04, "elapsed_time": "1:46:02", "remaining_time": "0:13:03", "throughput": 5496.18, "total_tokens": 34969520} {"current_steps": 57400, "total_steps": 64460, "loss": 0.108, "lr": 3.610843832728461e-07, "epoch": 17.809494260006204, "percentage": 89.05, "elapsed_time": "1:46:02", "remaining_time": "0:13:02", "throughput": 5496.19, "total_tokens": 34972208} {"current_steps": 57405, "total_steps": 64460, "loss": 0.196, "lr": 3.6057942059391836e-07, "epoch": 17.811045609680423, "percentage": 89.06, "elapsed_time": "1:46:03", "remaining_time": "0:13:02", "throughput": 5496.21, "total_tokens": 34974928} {"current_steps": 57410, "total_steps": 64460, "loss": 0.1499, "lr": 3.6007479803945867e-07, "epoch": 17.81259695935464, "percentage": 89.06, "elapsed_time": "1:46:04", "remaining_time": "0:13:01", "throughput": 5496.25, "total_tokens": 34978320} {"current_steps": 57415, "total_steps": 64460, "loss": 0.1887, "lr": 3.5957051564646015e-07, "epoch": 17.814148309028855, "percentage": 89.07, "elapsed_time": "1:46:04", "remaining_time": "0:13:00", "throughput": 5496.23, "total_tokens": 34980656} {"current_steps": 57420, "total_steps": 64460, "loss": 0.215, "lr": 3.590665734518944e-07, "epoch": 17.81569965870307, "percentage": 89.08, "elapsed_time": "1:46:04", "remaining_time": "0:13:00", "throughput": 5496.25, "total_tokens": 34983312} {"current_steps": 57425, "total_steps": 64460, "loss": 0.1609, "lr": 3.585629714927058e-07, "epoch": 17.817251008377287, "percentage": 89.09, "elapsed_time": "1:46:05", "remaining_time": "0:12:59", "throughput": 5496.32, "total_tokens": 34986896} {"current_steps": 57430, "total_steps": 64460, "loss": 0.1772, "lr": 3.580597098058136e-07, "epoch": 17.818802358051506, "percentage": 89.09, "elapsed_time": "1:46:06", "remaining_time": "0:12:59", "throughput": 5496.42, "total_tokens": 34990640} {"current_steps": 57435, "total_steps": 64460, "loss": 0.1751, "lr": 3.5755678842811446e-07, "epoch": 17.820353707725722, "percentage": 89.1, "elapsed_time": "1:46:06", "remaining_time": "0:12:58", "throughput": 5496.44, "total_tokens": 34993520} {"current_steps": 57440, "total_steps": 64460, "loss": 0.2269, "lr": 3.570542073964767e-07, "epoch": 17.82190505739994, "percentage": 89.11, "elapsed_time": "1:46:07", "remaining_time": "0:12:58", "throughput": 5496.38, "total_tokens": 34996048} {"current_steps": 57445, "total_steps": 64460, "loss": 0.2555, "lr": 3.5655196674774685e-07, "epoch": 17.823456407074154, "percentage": 89.12, "elapsed_time": "1:46:07", "remaining_time": "0:12:57", "throughput": 5496.35, "total_tokens": 34998544} {"current_steps": 57450, "total_steps": 64460, "loss": 0.3269, "lr": 3.560500665187439e-07, "epoch": 17.82500775674837, "percentage": 89.13, "elapsed_time": "1:46:08", "remaining_time": "0:12:57", "throughput": 5496.38, "total_tokens": 35001904} {"current_steps": 57455, "total_steps": 64460, "loss": 0.1838, "lr": 3.555485067462644e-07, "epoch": 17.826559106422586, "percentage": 89.13, "elapsed_time": "1:46:08", "remaining_time": "0:12:56", "throughput": 5496.35, "total_tokens": 35004688} {"current_steps": 57460, "total_steps": 64460, "loss": 0.261, "lr": 3.550472874670774e-07, "epoch": 17.828110456096805, "percentage": 89.14, "elapsed_time": "1:46:09", "remaining_time": "0:12:55", "throughput": 5496.27, "total_tokens": 35006864} {"current_steps": 57465, "total_steps": 64460, "loss": 0.1923, "lr": 3.54546408717929e-07, "epoch": 17.82966180577102, "percentage": 89.15, "elapsed_time": "1:46:09", "remaining_time": "0:12:55", "throughput": 5496.27, "total_tokens": 35009840} {"current_steps": 57470, "total_steps": 64460, "loss": 0.191, "lr": 3.540458705355376e-07, "epoch": 17.831213155445237, "percentage": 89.16, "elapsed_time": "1:46:10", "remaining_time": "0:12:54", "throughput": 5496.19, "total_tokens": 35012048} {"current_steps": 57475, "total_steps": 64460, "loss": 0.1695, "lr": 3.5354567295660223e-07, "epoch": 17.832764505119453, "percentage": 89.16, "elapsed_time": "1:46:10", "remaining_time": "0:12:54", "throughput": 5496.29, "total_tokens": 35016240} {"current_steps": 57480, "total_steps": 64460, "loss": 0.229, "lr": 3.530458160177902e-07, "epoch": 17.83431585479367, "percentage": 89.17, "elapsed_time": "1:46:11", "remaining_time": "0:12:53", "throughput": 5496.27, "total_tokens": 35019280} {"current_steps": 57485, "total_steps": 64460, "loss": 0.1612, "lr": 3.5254629975574883e-07, "epoch": 17.83586720446789, "percentage": 89.18, "elapsed_time": "1:46:12", "remaining_time": "0:12:53", "throughput": 5496.29, "total_tokens": 35022896} {"current_steps": 57490, "total_steps": 64460, "loss": 0.1495, "lr": 3.520471242070972e-07, "epoch": 17.837418554142104, "percentage": 89.19, "elapsed_time": "1:46:12", "remaining_time": "0:12:52", "throughput": 5496.36, "total_tokens": 35026224} {"current_steps": 57495, "total_steps": 64460, "loss": 0.2264, "lr": 3.515482894084321e-07, "epoch": 17.83896990381632, "percentage": 89.19, "elapsed_time": "1:46:13", "remaining_time": "0:12:52", "throughput": 5496.4, "total_tokens": 35029296} {"current_steps": 57500, "total_steps": 64460, "loss": 0.1555, "lr": 3.510497953963221e-07, "epoch": 17.840521253490536, "percentage": 89.2, "elapsed_time": "1:46:13", "remaining_time": "0:12:51", "throughput": 5496.43, "total_tokens": 35032208} {"current_steps": 57505, "total_steps": 64460, "loss": 0.0876, "lr": 3.5055164220731407e-07, "epoch": 17.842072603164752, "percentage": 89.21, "elapsed_time": "1:46:14", "remaining_time": "0:12:50", "throughput": 5496.45, "total_tokens": 35035312} {"current_steps": 57510, "total_steps": 64460, "loss": 0.1679, "lr": 3.5005382987792933e-07, "epoch": 17.84362395283897, "percentage": 89.22, "elapsed_time": "1:46:14", "remaining_time": "0:12:50", "throughput": 5496.5, "total_tokens": 35038768} {"current_steps": 57515, "total_steps": 64460, "loss": 0.1609, "lr": 3.495563584446615e-07, "epoch": 17.845175302513187, "percentage": 89.23, "elapsed_time": "1:46:15", "remaining_time": "0:12:49", "throughput": 5496.56, "total_tokens": 35042256} {"current_steps": 57520, "total_steps": 64460, "loss": 0.1462, "lr": 3.4905922794398305e-07, "epoch": 17.846726652187403, "percentage": 89.23, "elapsed_time": "1:46:15", "remaining_time": "0:12:49", "throughput": 5496.63, "total_tokens": 35046032} {"current_steps": 57525, "total_steps": 64460, "loss": 0.09, "lr": 3.485624384123382e-07, "epoch": 17.84827800186162, "percentage": 89.24, "elapsed_time": "1:46:16", "remaining_time": "0:12:48", "throughput": 5496.6, "total_tokens": 35048432} {"current_steps": 57530, "total_steps": 64460, "loss": 0.2124, "lr": 3.480659898861477e-07, "epoch": 17.849829351535835, "percentage": 89.25, "elapsed_time": "1:46:16", "remaining_time": "0:12:48", "throughput": 5496.58, "total_tokens": 35051088} {"current_steps": 57535, "total_steps": 64460, "loss": 0.1933, "lr": 3.47569882401807e-07, "epoch": 17.851380701210054, "percentage": 89.26, "elapsed_time": "1:46:17", "remaining_time": "0:12:47", "throughput": 5496.53, "total_tokens": 35053360} {"current_steps": 57540, "total_steps": 64460, "loss": 0.2239, "lr": 3.4707411599568807e-07, "epoch": 17.85293205088427, "percentage": 89.26, "elapsed_time": "1:46:17", "remaining_time": "0:12:47", "throughput": 5496.52, "total_tokens": 35055952} {"current_steps": 57545, "total_steps": 64460, "loss": 0.2296, "lr": 3.465786907041341e-07, "epoch": 17.854483400558486, "percentage": 89.27, "elapsed_time": "1:46:18", "remaining_time": "0:12:46", "throughput": 5496.5, "total_tokens": 35058448} {"current_steps": 57550, "total_steps": 64460, "loss": 0.1142, "lr": 3.4608360656346764e-07, "epoch": 17.856034750232702, "percentage": 89.28, "elapsed_time": "1:46:18", "remaining_time": "0:12:45", "throughput": 5496.45, "total_tokens": 35060944} {"current_steps": 57555, "total_steps": 64460, "loss": 0.161, "lr": 3.45588863609983e-07, "epoch": 17.857586099906918, "percentage": 89.29, "elapsed_time": "1:46:19", "remaining_time": "0:12:45", "throughput": 5496.52, "total_tokens": 35064272} {"current_steps": 57560, "total_steps": 64460, "loss": 0.1857, "lr": 3.450944618799512e-07, "epoch": 17.859137449581137, "percentage": 89.3, "elapsed_time": "1:46:19", "remaining_time": "0:12:44", "throughput": 5496.52, "total_tokens": 35067440} {"current_steps": 57565, "total_steps": 64460, "loss": 0.0879, "lr": 3.446004014096177e-07, "epoch": 17.860688799255353, "percentage": 89.3, "elapsed_time": "1:46:20", "remaining_time": "0:12:44", "throughput": 5496.6, "total_tokens": 35070928} {"current_steps": 57570, "total_steps": 64460, "loss": 0.2091, "lr": 3.4410668223520237e-07, "epoch": 17.86224014892957, "percentage": 89.31, "elapsed_time": "1:46:20", "remaining_time": "0:12:43", "throughput": 5496.62, "total_tokens": 35073680} {"current_steps": 57575, "total_steps": 64460, "loss": 0.1394, "lr": 3.4361330439290244e-07, "epoch": 17.863791498603785, "percentage": 89.32, "elapsed_time": "1:46:21", "remaining_time": "0:12:43", "throughput": 5496.66, "total_tokens": 35076784} {"current_steps": 57580, "total_steps": 64460, "loss": 0.1079, "lr": 3.431202679188861e-07, "epoch": 17.865342848278, "percentage": 89.33, "elapsed_time": "1:46:21", "remaining_time": "0:12:42", "throughput": 5496.68, "total_tokens": 35079696} {"current_steps": 57585, "total_steps": 64460, "loss": 0.2731, "lr": 3.426275728493006e-07, "epoch": 17.86689419795222, "percentage": 89.33, "elapsed_time": "1:46:22", "remaining_time": "0:12:41", "throughput": 5496.67, "total_tokens": 35082320} {"current_steps": 57590, "total_steps": 64460, "loss": 0.1788, "lr": 3.421352192202648e-07, "epoch": 17.868445547626436, "percentage": 89.34, "elapsed_time": "1:46:22", "remaining_time": "0:12:41", "throughput": 5496.72, "total_tokens": 35085360} {"current_steps": 57595, "total_steps": 64460, "loss": 0.2317, "lr": 3.41643207067876e-07, "epoch": 17.869996897300652, "percentage": 89.35, "elapsed_time": "1:46:23", "remaining_time": "0:12:40", "throughput": 5496.76, "total_tokens": 35088816} {"current_steps": 57600, "total_steps": 64460, "loss": 0.1322, "lr": 3.4115153642820196e-07, "epoch": 17.871548246974868, "percentage": 89.36, "elapsed_time": "1:46:24", "remaining_time": "0:12:40", "throughput": 5496.73, "total_tokens": 35091216} {"current_steps": 57605, "total_steps": 64460, "loss": 0.192, "lr": 3.406602073372906e-07, "epoch": 17.873099596649084, "percentage": 89.37, "elapsed_time": "1:46:24", "remaining_time": "0:12:39", "throughput": 5496.93, "total_tokens": 35097296} {"current_steps": 57610, "total_steps": 64460, "loss": 0.2794, "lr": 3.401692198311596e-07, "epoch": 17.8746509463233, "percentage": 89.37, "elapsed_time": "1:46:25", "remaining_time": "0:12:39", "throughput": 5497.09, "total_tokens": 35102064} {"current_steps": 57615, "total_steps": 64460, "loss": 0.1658, "lr": 3.396785739458064e-07, "epoch": 17.87620229599752, "percentage": 89.38, "elapsed_time": "1:46:26", "remaining_time": "0:12:38", "throughput": 5497.11, "total_tokens": 35104912} {"current_steps": 57620, "total_steps": 64460, "loss": 0.1068, "lr": 3.3918826971719945e-07, "epoch": 17.877753645671735, "percentage": 89.39, "elapsed_time": "1:46:26", "remaining_time": "0:12:38", "throughput": 5497.13, "total_tokens": 35107664} {"current_steps": 57625, "total_steps": 64460, "loss": 0.1946, "lr": 3.3869830718128494e-07, "epoch": 17.87930499534595, "percentage": 89.4, "elapsed_time": "1:46:27", "remaining_time": "0:12:37", "throughput": 5497.11, "total_tokens": 35110160} {"current_steps": 57630, "total_steps": 64460, "loss": 0.2568, "lr": 3.3820868637398305e-07, "epoch": 17.880856345020167, "percentage": 89.4, "elapsed_time": "1:46:27", "remaining_time": "0:12:37", "throughput": 5497.17, "total_tokens": 35113808} {"current_steps": 57635, "total_steps": 64460, "loss": 0.1368, "lr": 3.3771940733118734e-07, "epoch": 17.882407694694383, "percentage": 89.41, "elapsed_time": "1:46:28", "remaining_time": "0:12:36", "throughput": 5497.12, "total_tokens": 35116240} {"current_steps": 57640, "total_steps": 64460, "loss": 0.0626, "lr": 3.3723047008876966e-07, "epoch": 17.883959044368602, "percentage": 89.42, "elapsed_time": "1:46:28", "remaining_time": "0:12:35", "throughput": 5497.14, "total_tokens": 35119536} {"current_steps": 57645, "total_steps": 64460, "loss": 0.1252, "lr": 3.3674187468257346e-07, "epoch": 17.885510394042818, "percentage": 89.43, "elapsed_time": "1:46:29", "remaining_time": "0:12:35", "throughput": 5497.21, "total_tokens": 35122928} {"current_steps": 57650, "total_steps": 64460, "loss": 0.1893, "lr": 3.362536211484196e-07, "epoch": 17.887061743717034, "percentage": 89.44, "elapsed_time": "1:46:29", "remaining_time": "0:12:34", "throughput": 5497.2, "total_tokens": 35125456} {"current_steps": 57655, "total_steps": 64460, "loss": 0.1379, "lr": 3.357657095221012e-07, "epoch": 17.88861309339125, "percentage": 89.44, "elapsed_time": "1:46:30", "remaining_time": "0:12:34", "throughput": 5497.16, "total_tokens": 35127856} {"current_steps": 57660, "total_steps": 64460, "loss": 0.1811, "lr": 3.3527813983939064e-07, "epoch": 17.890164443065466, "percentage": 89.45, "elapsed_time": "1:46:30", "remaining_time": "0:12:33", "throughput": 5497.14, "total_tokens": 35130640} {"current_steps": 57665, "total_steps": 64460, "loss": 0.1576, "lr": 3.3479091213602986e-07, "epoch": 17.891715792739685, "percentage": 89.46, "elapsed_time": "1:46:31", "remaining_time": "0:12:33", "throughput": 5497.12, "total_tokens": 35133040} {"current_steps": 57670, "total_steps": 64460, "loss": 0.162, "lr": 3.343040264477404e-07, "epoch": 17.8932671424139, "percentage": 89.47, "elapsed_time": "1:46:31", "remaining_time": "0:12:32", "throughput": 5497.16, "total_tokens": 35136080} {"current_steps": 57675, "total_steps": 64460, "loss": 0.1911, "lr": 3.3381748281021473e-07, "epoch": 17.894818492088117, "percentage": 89.47, "elapsed_time": "1:46:32", "remaining_time": "0:12:31", "throughput": 5497.15, "total_tokens": 35138800} {"current_steps": 57680, "total_steps": 64460, "loss": 0.1329, "lr": 3.333312812591244e-07, "epoch": 17.896369841762333, "percentage": 89.48, "elapsed_time": "1:46:32", "remaining_time": "0:12:31", "throughput": 5497.19, "total_tokens": 35142064} {"current_steps": 57685, "total_steps": 64460, "loss": 0.1304, "lr": 3.328454218301125e-07, "epoch": 17.89792119143655, "percentage": 89.49, "elapsed_time": "1:46:33", "remaining_time": "0:12:30", "throughput": 5497.12, "total_tokens": 35144272} {"current_steps": 57690, "total_steps": 64460, "loss": 0.1092, "lr": 3.323599045587983e-07, "epoch": 17.899472541110768, "percentage": 89.5, "elapsed_time": "1:46:33", "remaining_time": "0:12:30", "throughput": 5497.15, "total_tokens": 35147184} {"current_steps": 57695, "total_steps": 64460, "loss": 0.1938, "lr": 3.318747294807767e-07, "epoch": 17.901023890784984, "percentage": 89.51, "elapsed_time": "1:46:34", "remaining_time": "0:12:29", "throughput": 5497.07, "total_tokens": 35149232} {"current_steps": 57700, "total_steps": 64460, "loss": 0.1397, "lr": 3.313898966316159e-07, "epoch": 17.9025752404592, "percentage": 89.51, "elapsed_time": "1:46:34", "remaining_time": "0:12:29", "throughput": 5497.07, "total_tokens": 35151952} {"current_steps": 57705, "total_steps": 64460, "loss": 0.1531, "lr": 3.3090540604686083e-07, "epoch": 17.904126590133416, "percentage": 89.52, "elapsed_time": "1:46:35", "remaining_time": "0:12:28", "throughput": 5497.04, "total_tokens": 35154448} {"current_steps": 57710, "total_steps": 64460, "loss": 0.1785, "lr": 3.3042125776202914e-07, "epoch": 17.90567793980763, "percentage": 89.53, "elapsed_time": "1:46:35", "remaining_time": "0:12:28", "throughput": 5497.01, "total_tokens": 35157136} {"current_steps": 57715, "total_steps": 64460, "loss": 0.2078, "lr": 3.2993745181261585e-07, "epoch": 17.907229289481847, "percentage": 89.54, "elapsed_time": "1:46:36", "remaining_time": "0:12:27", "throughput": 5496.98, "total_tokens": 35159568} {"current_steps": 57720, "total_steps": 64460, "loss": 0.1202, "lr": 3.294539882340886e-07, "epoch": 17.908780639156067, "percentage": 89.54, "elapsed_time": "1:46:36", "remaining_time": "0:12:26", "throughput": 5496.96, "total_tokens": 35162096} {"current_steps": 57725, "total_steps": 64460, "loss": 0.112, "lr": 3.289708670618924e-07, "epoch": 17.910331988830283, "percentage": 89.55, "elapsed_time": "1:46:37", "remaining_time": "0:12:26", "throughput": 5496.98, "total_tokens": 35164816} {"current_steps": 57730, "total_steps": 64460, "loss": 0.1477, "lr": 3.28488088331444e-07, "epoch": 17.9118833385045, "percentage": 89.56, "elapsed_time": "1:46:37", "remaining_time": "0:12:25", "throughput": 5497.07, "total_tokens": 35168816} {"current_steps": 57735, "total_steps": 64460, "loss": 0.1724, "lr": 3.2800565207813883e-07, "epoch": 17.913434688178715, "percentage": 89.57, "elapsed_time": "1:46:38", "remaining_time": "0:12:25", "throughput": 5497.12, "total_tokens": 35171888} {"current_steps": 57740, "total_steps": 64460, "loss": 0.1968, "lr": 3.2752355833734315e-07, "epoch": 17.91498603785293, "percentage": 89.57, "elapsed_time": "1:46:38", "remaining_time": "0:12:24", "throughput": 5497.05, "total_tokens": 35174320} {"current_steps": 57745, "total_steps": 64460, "loss": 0.1017, "lr": 3.2704180714440095e-07, "epoch": 17.91653738752715, "percentage": 89.58, "elapsed_time": "1:46:39", "remaining_time": "0:12:24", "throughput": 5497.15, "total_tokens": 35178416} {"current_steps": 57750, "total_steps": 64460, "loss": 0.1017, "lr": 3.2656039853463104e-07, "epoch": 17.918088737201366, "percentage": 89.59, "elapsed_time": "1:46:39", "remaining_time": "0:12:23", "throughput": 5497.16, "total_tokens": 35181008} {"current_steps": 57755, "total_steps": 64460, "loss": 0.2008, "lr": 3.260793325433248e-07, "epoch": 17.91964008687558, "percentage": 89.6, "elapsed_time": "1:46:40", "remaining_time": "0:12:23", "throughput": 5497.1, "total_tokens": 35183248} {"current_steps": 57760, "total_steps": 64460, "loss": 0.3103, "lr": 3.255986092057523e-07, "epoch": 17.921191436549798, "percentage": 89.61, "elapsed_time": "1:46:40", "remaining_time": "0:12:22", "throughput": 5497.19, "total_tokens": 35187248} {"current_steps": 57765, "total_steps": 64460, "loss": 0.1086, "lr": 3.2511822855715357e-07, "epoch": 17.922742786224013, "percentage": 89.61, "elapsed_time": "1:46:41", "remaining_time": "0:12:21", "throughput": 5497.19, "total_tokens": 35189872} {"current_steps": 57770, "total_steps": 64460, "loss": 0.1371, "lr": 3.2463819063274894e-07, "epoch": 17.924294135898233, "percentage": 89.62, "elapsed_time": "1:46:41", "remaining_time": "0:12:21", "throughput": 5497.14, "total_tokens": 35192080} {"current_steps": 57775, "total_steps": 64460, "loss": 0.124, "lr": 3.2415849546772795e-07, "epoch": 17.92584548557245, "percentage": 89.63, "elapsed_time": "1:46:42", "remaining_time": "0:12:20", "throughput": 5497.23, "total_tokens": 35196304} {"current_steps": 57780, "total_steps": 64460, "loss": 0.147, "lr": 3.236791430972608e-07, "epoch": 17.927396835246665, "percentage": 89.64, "elapsed_time": "1:46:43", "remaining_time": "0:12:20", "throughput": 5497.31, "total_tokens": 35200976} {"current_steps": 57785, "total_steps": 64460, "loss": 0.1175, "lr": 3.232001335564877e-07, "epoch": 17.92894818492088, "percentage": 89.64, "elapsed_time": "1:46:43", "remaining_time": "0:12:19", "throughput": 5497.36, "total_tokens": 35204784} {"current_steps": 57790, "total_steps": 64460, "loss": 0.1285, "lr": 3.227214668805273e-07, "epoch": 17.930499534595096, "percentage": 89.65, "elapsed_time": "1:46:44", "remaining_time": "0:12:19", "throughput": 5497.4, "total_tokens": 35208208} {"current_steps": 57795, "total_steps": 64460, "loss": 0.1665, "lr": 3.2224314310446926e-07, "epoch": 17.932050884269316, "percentage": 89.66, "elapsed_time": "1:46:44", "remaining_time": "0:12:18", "throughput": 5497.37, "total_tokens": 35210512} {"current_steps": 57800, "total_steps": 64460, "loss": 0.1451, "lr": 3.217651622633827e-07, "epoch": 17.93360223394353, "percentage": 89.67, "elapsed_time": "1:46:45", "remaining_time": "0:12:18", "throughput": 5497.47, "total_tokens": 35214768} {"current_steps": 57805, "total_steps": 64460, "loss": 0.1117, "lr": 3.21287524392308e-07, "epoch": 17.935153583617748, "percentage": 89.68, "elapsed_time": "1:46:46", "remaining_time": "0:12:17", "throughput": 5497.43, "total_tokens": 35217200} {"current_steps": 57810, "total_steps": 64460, "loss": 0.2006, "lr": 3.2081022952626163e-07, "epoch": 17.936704933291963, "percentage": 89.68, "elapsed_time": "1:46:46", "remaining_time": "0:12:16", "throughput": 5497.37, "total_tokens": 35219408} {"current_steps": 57815, "total_steps": 64460, "loss": 0.1558, "lr": 3.2033327770023604e-07, "epoch": 17.93825628296618, "percentage": 89.69, "elapsed_time": "1:46:47", "remaining_time": "0:12:16", "throughput": 5497.41, "total_tokens": 35222992} {"current_steps": 57820, "total_steps": 64460, "loss": 0.1789, "lr": 3.1985666894919665e-07, "epoch": 17.9398076326404, "percentage": 89.7, "elapsed_time": "1:46:47", "remaining_time": "0:12:15", "throughput": 5497.5, "total_tokens": 35226992} {"current_steps": 57825, "total_steps": 64460, "loss": 0.1266, "lr": 3.193804033080844e-07, "epoch": 17.941358982314615, "percentage": 89.71, "elapsed_time": "1:46:48", "remaining_time": "0:12:15", "throughput": 5497.52, "total_tokens": 35229712} {"current_steps": 57830, "total_steps": 64460, "loss": 0.1446, "lr": 3.1890448081181525e-07, "epoch": 17.94291033198883, "percentage": 89.71, "elapsed_time": "1:46:48", "remaining_time": "0:12:14", "throughput": 5497.6, "total_tokens": 35233104} {"current_steps": 57835, "total_steps": 64460, "loss": 0.1898, "lr": 3.184289014952807e-07, "epoch": 17.944461681663046, "percentage": 89.72, "elapsed_time": "1:46:49", "remaining_time": "0:12:14", "throughput": 5497.68, "total_tokens": 35236560} {"current_steps": 57840, "total_steps": 64460, "loss": 0.1358, "lr": 3.179536653933452e-07, "epoch": 17.946013031337262, "percentage": 89.73, "elapsed_time": "1:46:49", "remaining_time": "0:12:13", "throughput": 5497.72, "total_tokens": 35239888} {"current_steps": 57845, "total_steps": 64460, "loss": 0.1931, "lr": 3.174787725408501e-07, "epoch": 17.94756438101148, "percentage": 89.74, "elapsed_time": "1:46:50", "remaining_time": "0:12:13", "throughput": 5497.69, "total_tokens": 35242736} {"current_steps": 57850, "total_steps": 64460, "loss": 0.1079, "lr": 3.1700422297261004e-07, "epoch": 17.949115730685698, "percentage": 89.75, "elapsed_time": "1:46:50", "remaining_time": "0:12:12", "throughput": 5497.76, "total_tokens": 35246000} {"current_steps": 57855, "total_steps": 64460, "loss": 0.1405, "lr": 3.165300167234159e-07, "epoch": 17.950667080359914, "percentage": 89.75, "elapsed_time": "1:46:51", "remaining_time": "0:12:11", "throughput": 5497.71, "total_tokens": 35248336} {"current_steps": 57860, "total_steps": 64460, "loss": 0.195, "lr": 3.1605615382803157e-07, "epoch": 17.95221843003413, "percentage": 89.76, "elapsed_time": "1:46:51", "remaining_time": "0:12:11", "throughput": 5497.65, "total_tokens": 35250480} {"current_steps": 57865, "total_steps": 64460, "loss": 0.193, "lr": 3.1558263432119706e-07, "epoch": 17.953769779708345, "percentage": 89.77, "elapsed_time": "1:46:52", "remaining_time": "0:12:10", "throughput": 5497.63, "total_tokens": 35253200} {"current_steps": 57870, "total_steps": 64460, "loss": 0.1325, "lr": 3.1510945823762796e-07, "epoch": 17.95532112938256, "percentage": 89.78, "elapsed_time": "1:46:52", "remaining_time": "0:12:10", "throughput": 5497.67, "total_tokens": 35256112} {"current_steps": 57875, "total_steps": 64460, "loss": 0.1994, "lr": 3.146366256120126e-07, "epoch": 17.95687247905678, "percentage": 89.78, "elapsed_time": "1:46:53", "remaining_time": "0:12:09", "throughput": 5497.73, "total_tokens": 35259600} {"current_steps": 57880, "total_steps": 64460, "loss": 0.1736, "lr": 3.14164136479016e-07, "epoch": 17.958423828730997, "percentage": 89.79, "elapsed_time": "1:46:54", "remaining_time": "0:12:09", "throughput": 5497.83, "total_tokens": 35263920} {"current_steps": 57885, "total_steps": 64460, "loss": 0.133, "lr": 3.1369199087327664e-07, "epoch": 17.959975178405212, "percentage": 89.8, "elapsed_time": "1:46:54", "remaining_time": "0:12:08", "throughput": 5497.88, "total_tokens": 35266992} {"current_steps": 57890, "total_steps": 64460, "loss": 0.16, "lr": 3.132201888294084e-07, "epoch": 17.96152652807943, "percentage": 89.81, "elapsed_time": "1:46:55", "remaining_time": "0:12:08", "throughput": 5497.83, "total_tokens": 35269712} {"current_steps": 57895, "total_steps": 64460, "loss": 0.0952, "lr": 3.1274873038199983e-07, "epoch": 17.963077877753644, "percentage": 89.82, "elapsed_time": "1:46:55", "remaining_time": "0:12:07", "throughput": 5497.96, "total_tokens": 35274064} {"current_steps": 57900, "total_steps": 64460, "loss": 0.1682, "lr": 3.1227761556561543e-07, "epoch": 17.964629227427864, "percentage": 89.82, "elapsed_time": "1:46:56", "remaining_time": "0:12:06", "throughput": 5497.91, "total_tokens": 35276464} {"current_steps": 57905, "total_steps": 64460, "loss": 0.1906, "lr": 3.11806844414792e-07, "epoch": 17.96618057710208, "percentage": 89.83, "elapsed_time": "1:46:56", "remaining_time": "0:12:06", "throughput": 5497.99, "total_tokens": 35279888} {"current_steps": 57910, "total_steps": 64460, "loss": 0.2032, "lr": 3.1133641696404425e-07, "epoch": 17.967731926776295, "percentage": 89.84, "elapsed_time": "1:46:57", "remaining_time": "0:12:05", "throughput": 5497.95, "total_tokens": 35282352} {"current_steps": 57915, "total_steps": 64460, "loss": 0.1695, "lr": 3.108663332478584e-07, "epoch": 17.96928327645051, "percentage": 89.85, "elapsed_time": "1:46:57", "remaining_time": "0:12:05", "throughput": 5498.0, "total_tokens": 35286032} {"current_steps": 57920, "total_steps": 64460, "loss": 0.1765, "lr": 3.103965933006986e-07, "epoch": 17.970834626124727, "percentage": 89.85, "elapsed_time": "1:46:58", "remaining_time": "0:12:04", "throughput": 5497.99, "total_tokens": 35288656} {"current_steps": 57925, "total_steps": 64460, "loss": 0.1404, "lr": 3.099271971570006e-07, "epoch": 17.972385975798947, "percentage": 89.86, "elapsed_time": "1:46:58", "remaining_time": "0:12:04", "throughput": 5497.97, "total_tokens": 35291120} {"current_steps": 57930, "total_steps": 64460, "loss": 0.0806, "lr": 3.0945814485117855e-07, "epoch": 17.973937325473162, "percentage": 89.87, "elapsed_time": "1:46:59", "remaining_time": "0:12:03", "throughput": 5498.02, "total_tokens": 35294832} {"current_steps": 57935, "total_steps": 64460, "loss": 0.1742, "lr": 3.0898943641761936e-07, "epoch": 17.97548867514738, "percentage": 89.88, "elapsed_time": "1:47:00", "remaining_time": "0:12:03", "throughput": 5498.09, "total_tokens": 35298704} {"current_steps": 57940, "total_steps": 64460, "loss": 0.0902, "lr": 3.0852107189068334e-07, "epoch": 17.977040024821594, "percentage": 89.89, "elapsed_time": "1:47:00", "remaining_time": "0:12:02", "throughput": 5498.06, "total_tokens": 35301104} {"current_steps": 57945, "total_steps": 64460, "loss": 0.1164, "lr": 3.080530513047092e-07, "epoch": 17.97859137449581, "percentage": 89.89, "elapsed_time": "1:47:01", "remaining_time": "0:12:01", "throughput": 5498.11, "total_tokens": 35304080} {"current_steps": 57950, "total_steps": 64460, "loss": 0.2091, "lr": 3.075853746940061e-07, "epoch": 17.98014272417003, "percentage": 89.9, "elapsed_time": "1:47:01", "remaining_time": "0:12:01", "throughput": 5498.17, "total_tokens": 35307216} {"current_steps": 57955, "total_steps": 64460, "loss": 0.2563, "lr": 3.0711804209286266e-07, "epoch": 17.981694073844245, "percentage": 89.91, "elapsed_time": "1:47:02", "remaining_time": "0:12:00", "throughput": 5498.15, "total_tokens": 35311088} {"current_steps": 57960, "total_steps": 64460, "loss": 0.1451, "lr": 3.0665105353553824e-07, "epoch": 17.98324542351846, "percentage": 89.92, "elapsed_time": "1:47:03", "remaining_time": "0:12:00", "throughput": 5498.28, "total_tokens": 35316432} {"current_steps": 57965, "total_steps": 64460, "loss": 0.2422, "lr": 3.0618440905626936e-07, "epoch": 17.984796773192677, "percentage": 89.92, "elapsed_time": "1:47:03", "remaining_time": "0:11:59", "throughput": 5498.25, "total_tokens": 35318992} {"current_steps": 57970, "total_steps": 64460, "loss": 0.2846, "lr": 3.057181086892663e-07, "epoch": 17.986348122866893, "percentage": 89.93, "elapsed_time": "1:47:04", "remaining_time": "0:11:59", "throughput": 5498.27, "total_tokens": 35322000} {"current_steps": 57975, "total_steps": 64460, "loss": 0.1639, "lr": 3.0525215246871466e-07, "epoch": 17.98789947254111, "percentage": 89.94, "elapsed_time": "1:47:04", "remaining_time": "0:11:58", "throughput": 5498.24, "total_tokens": 35324432} {"current_steps": 57980, "total_steps": 64460, "loss": 0.1952, "lr": 3.047865404287742e-07, "epoch": 17.98945082221533, "percentage": 89.95, "elapsed_time": "1:47:05", "remaining_time": "0:11:58", "throughput": 5498.26, "total_tokens": 35327344} {"current_steps": 57985, "total_steps": 64460, "loss": 0.0997, "lr": 3.0432127260357934e-07, "epoch": 17.991002171889544, "percentage": 89.96, "elapsed_time": "1:47:05", "remaining_time": "0:11:57", "throughput": 5498.25, "total_tokens": 35330416} {"current_steps": 57990, "total_steps": 64460, "loss": 0.1955, "lr": 3.038563490272417e-07, "epoch": 17.99255352156376, "percentage": 89.96, "elapsed_time": "1:47:06", "remaining_time": "0:11:56", "throughput": 5498.25, "total_tokens": 35333264} {"current_steps": 57995, "total_steps": 64460, "loss": 0.1643, "lr": 3.0339176973384285e-07, "epoch": 17.994104871237976, "percentage": 89.97, "elapsed_time": "1:47:06", "remaining_time": "0:11:56", "throughput": 5498.23, "total_tokens": 35335792} {"current_steps": 58000, "total_steps": 64460, "loss": 0.2029, "lr": 3.0292753475744505e-07, "epoch": 17.995656220912192, "percentage": 89.98, "elapsed_time": "1:47:07", "remaining_time": "0:11:55", "throughput": 5498.27, "total_tokens": 35338928} {"current_steps": 58005, "total_steps": 64460, "loss": 0.3168, "lr": 3.024636441320794e-07, "epoch": 17.99720757058641, "percentage": 89.99, "elapsed_time": "1:47:07", "remaining_time": "0:11:55", "throughput": 5498.27, "total_tokens": 35341936} {"current_steps": 58010, "total_steps": 64460, "loss": 0.1999, "lr": 3.0200009789175646e-07, "epoch": 17.998758920260627, "percentage": 89.99, "elapsed_time": "1:47:08", "remaining_time": "0:11:54", "throughput": 5498.19, "total_tokens": 35344304} {"current_steps": 58014, "total_steps": 64460, "eval_loss": 0.38111791014671326, "epoch": 18.0, "percentage": 90.0, "elapsed_time": "1:47:43", "remaining_time": "0:11:58", "throughput": 5468.82, "total_tokens": 35346160} {"current_steps": 58015, "total_steps": 64460, "loss": 0.2293, "lr": 3.015368960704584e-07, "epoch": 18.000310269934843, "percentage": 90.0, "elapsed_time": "1:47:47", "remaining_time": "0:11:58", "throughput": 5465.59, "total_tokens": 35346608} {"current_steps": 58020, "total_steps": 64460, "loss": 0.0788, "lr": 3.010740387021449e-07, "epoch": 18.00186161960906, "percentage": 90.01, "elapsed_time": "1:47:47", "remaining_time": "0:11:57", "throughput": 5465.63, "total_tokens": 35350064} {"current_steps": 58025, "total_steps": 64460, "loss": 0.1163, "lr": 3.0061152582074704e-07, "epoch": 18.003412969283275, "percentage": 90.02, "elapsed_time": "1:47:48", "remaining_time": "0:11:57", "throughput": 5465.77, "total_tokens": 35356464} {"current_steps": 58030, "total_steps": 64460, "loss": 0.1638, "lr": 3.0014935746017383e-07, "epoch": 18.004964318957494, "percentage": 90.02, "elapsed_time": "1:47:49", "remaining_time": "0:11:56", "throughput": 5465.81, "total_tokens": 35359504} {"current_steps": 58035, "total_steps": 64460, "loss": 0.1531, "lr": 2.99687533654307e-07, "epoch": 18.00651566863171, "percentage": 90.03, "elapsed_time": "1:47:49", "remaining_time": "0:11:56", "throughput": 5465.9, "total_tokens": 35363952} {"current_steps": 58040, "total_steps": 64460, "loss": 0.2054, "lr": 2.9922605443700457e-07, "epoch": 18.008067018305926, "percentage": 90.04, "elapsed_time": "1:47:50", "remaining_time": "0:11:55", "throughput": 5465.83, "total_tokens": 35366224} {"current_steps": 58045, "total_steps": 64460, "loss": 0.1819, "lr": 2.987649198420972e-07, "epoch": 18.009618367980142, "percentage": 90.05, "elapsed_time": "1:47:51", "remaining_time": "0:11:55", "throughput": 5465.82, "total_tokens": 35369616} {"current_steps": 58050, "total_steps": 64460, "loss": 0.1047, "lr": 2.9830412990339173e-07, "epoch": 18.011169717654358, "percentage": 90.06, "elapsed_time": "1:47:51", "remaining_time": "0:11:54", "throughput": 5465.85, "total_tokens": 35372688} {"current_steps": 58055, "total_steps": 64460, "loss": 0.1621, "lr": 2.978436846546706e-07, "epoch": 18.012721067328577, "percentage": 90.06, "elapsed_time": "1:47:52", "remaining_time": "0:11:54", "throughput": 5465.85, "total_tokens": 35375312} {"current_steps": 58060, "total_steps": 64460, "loss": 0.1444, "lr": 2.973835841296896e-07, "epoch": 18.014272417002793, "percentage": 90.07, "elapsed_time": "1:47:52", "remaining_time": "0:11:53", "throughput": 5465.85, "total_tokens": 35378064} {"current_steps": 58065, "total_steps": 64460, "loss": 0.154, "lr": 2.969238283621784e-07, "epoch": 18.01582376667701, "percentage": 90.08, "elapsed_time": "1:47:53", "remaining_time": "0:11:52", "throughput": 5465.89, "total_tokens": 35381264} {"current_steps": 58070, "total_steps": 64460, "loss": 0.1205, "lr": 2.964644173858433e-07, "epoch": 18.017375116351225, "percentage": 90.09, "elapsed_time": "1:47:53", "remaining_time": "0:11:52", "throughput": 5465.88, "total_tokens": 35383888} {"current_steps": 58075, "total_steps": 64460, "loss": 0.1713, "lr": 2.960053512343658e-07, "epoch": 18.01892646602544, "percentage": 90.09, "elapsed_time": "1:47:54", "remaining_time": "0:11:51", "throughput": 5465.9, "total_tokens": 35386768} {"current_steps": 58080, "total_steps": 64460, "loss": 0.2023, "lr": 2.9554662994139837e-07, "epoch": 18.02047781569966, "percentage": 90.1, "elapsed_time": "1:47:54", "remaining_time": "0:11:51", "throughput": 5466.0, "total_tokens": 35391120} {"current_steps": 58085, "total_steps": 64460, "loss": 0.2364, "lr": 2.9508825354057303e-07, "epoch": 18.022029165373876, "percentage": 90.11, "elapsed_time": "1:47:55", "remaining_time": "0:11:50", "throughput": 5465.98, "total_tokens": 35393680} {"current_steps": 58090, "total_steps": 64460, "loss": 0.1638, "lr": 2.946302220654923e-07, "epoch": 18.023580515048092, "percentage": 90.12, "elapsed_time": "1:47:55", "remaining_time": "0:11:50", "throughput": 5466.0, "total_tokens": 35396880} {"current_steps": 58095, "total_steps": 64460, "loss": 0.1499, "lr": 2.941725355497371e-07, "epoch": 18.025131864722308, "percentage": 90.13, "elapsed_time": "1:47:56", "remaining_time": "0:11:49", "throughput": 5466.06, "total_tokens": 35400080} {"current_steps": 58100, "total_steps": 64460, "loss": 0.1693, "lr": 2.937151940268601e-07, "epoch": 18.026683214396524, "percentage": 90.13, "elapsed_time": "1:47:56", "remaining_time": "0:11:48", "throughput": 5466.1, "total_tokens": 35403152} {"current_steps": 58105, "total_steps": 64460, "loss": 0.1713, "lr": 2.9325819753039e-07, "epoch": 18.028234564070743, "percentage": 90.14, "elapsed_time": "1:47:57", "remaining_time": "0:11:48", "throughput": 5466.13, "total_tokens": 35406032} {"current_steps": 58110, "total_steps": 64460, "loss": 0.1072, "lr": 2.9280154609382994e-07, "epoch": 18.02978591374496, "percentage": 90.15, "elapsed_time": "1:47:57", "remaining_time": "0:11:47", "throughput": 5466.16, "total_tokens": 35408848} {"current_steps": 58115, "total_steps": 64460, "loss": 0.1447, "lr": 2.9234523975065874e-07, "epoch": 18.031337263419175, "percentage": 90.16, "elapsed_time": "1:47:58", "remaining_time": "0:11:47", "throughput": 5466.15, "total_tokens": 35411344} {"current_steps": 58120, "total_steps": 64460, "loss": 0.1829, "lr": 2.91889278534328e-07, "epoch": 18.03288861309339, "percentage": 90.16, "elapsed_time": "1:47:59", "remaining_time": "0:11:46", "throughput": 5466.31, "total_tokens": 35416592} {"current_steps": 58125, "total_steps": 64460, "loss": 0.1811, "lr": 2.91433662478266e-07, "epoch": 18.034439962767607, "percentage": 90.17, "elapsed_time": "1:47:59", "remaining_time": "0:11:46", "throughput": 5466.39, "total_tokens": 35420144} {"current_steps": 58130, "total_steps": 64460, "loss": 0.1298, "lr": 2.9097839161587317e-07, "epoch": 18.035991312441823, "percentage": 90.18, "elapsed_time": "1:48:00", "remaining_time": "0:11:45", "throughput": 5466.45, "total_tokens": 35423152} {"current_steps": 58135, "total_steps": 64460, "loss": 0.0943, "lr": 2.9052346598052783e-07, "epoch": 18.037542662116042, "percentage": 90.19, "elapsed_time": "1:48:00", "remaining_time": "0:11:45", "throughput": 5466.45, "total_tokens": 35425968} {"current_steps": 58140, "total_steps": 64460, "loss": 0.1061, "lr": 2.900688856055817e-07, "epoch": 18.039094011790258, "percentage": 90.2, "elapsed_time": "1:48:01", "remaining_time": "0:11:44", "throughput": 5466.5, "total_tokens": 35428912} {"current_steps": 58145, "total_steps": 64460, "loss": 0.1449, "lr": 2.8961465052435965e-07, "epoch": 18.040645361464474, "percentage": 90.2, "elapsed_time": "1:48:01", "remaining_time": "0:11:43", "throughput": 5466.55, "total_tokens": 35432080} {"current_steps": 58150, "total_steps": 64460, "loss": 0.1504, "lr": 2.891607607701635e-07, "epoch": 18.04219671113869, "percentage": 90.21, "elapsed_time": "1:48:02", "remaining_time": "0:11:43", "throughput": 5466.59, "total_tokens": 35435312} {"current_steps": 58155, "total_steps": 64460, "loss": 0.09, "lr": 2.8870721637626777e-07, "epoch": 18.043748060812906, "percentage": 90.22, "elapsed_time": "1:48:02", "remaining_time": "0:11:42", "throughput": 5466.59, "total_tokens": 35437808} {"current_steps": 58160, "total_steps": 64460, "loss": 0.1228, "lr": 2.882540173759235e-07, "epoch": 18.045299410487125, "percentage": 90.23, "elapsed_time": "1:48:03", "remaining_time": "0:11:42", "throughput": 5466.64, "total_tokens": 35440880} {"current_steps": 58165, "total_steps": 64460, "loss": 0.1806, "lr": 2.8780116380235424e-07, "epoch": 18.04685076016134, "percentage": 90.23, "elapsed_time": "1:48:03", "remaining_time": "0:11:41", "throughput": 5466.67, "total_tokens": 35443888} {"current_steps": 58170, "total_steps": 64460, "loss": 0.2042, "lr": 2.873486556887617e-07, "epoch": 18.048402109835557, "percentage": 90.24, "elapsed_time": "1:48:04", "remaining_time": "0:11:41", "throughput": 5466.67, "total_tokens": 35446480} {"current_steps": 58175, "total_steps": 64460, "loss": 0.1347, "lr": 2.8689649306831823e-07, "epoch": 18.049953459509773, "percentage": 90.25, "elapsed_time": "1:48:04", "remaining_time": "0:11:40", "throughput": 5466.75, "total_tokens": 35449936} {"current_steps": 58180, "total_steps": 64460, "loss": 0.1603, "lr": 2.8644467597417347e-07, "epoch": 18.05150480918399, "percentage": 90.26, "elapsed_time": "1:48:05", "remaining_time": "0:11:40", "throughput": 5466.71, "total_tokens": 35452080} {"current_steps": 58185, "total_steps": 64460, "loss": 0.2761, "lr": 2.8599320443945034e-07, "epoch": 18.053056158858208, "percentage": 90.27, "elapsed_time": "1:48:05", "remaining_time": "0:11:39", "throughput": 5466.74, "total_tokens": 35454768} {"current_steps": 58190, "total_steps": 64460, "loss": 0.0918, "lr": 2.855420784972479e-07, "epoch": 18.054607508532424, "percentage": 90.27, "elapsed_time": "1:48:06", "remaining_time": "0:11:38", "throughput": 5466.73, "total_tokens": 35457264} {"current_steps": 58195, "total_steps": 64460, "loss": 0.177, "lr": 2.8509129818063863e-07, "epoch": 18.05615885820664, "percentage": 90.28, "elapsed_time": "1:48:06", "remaining_time": "0:11:38", "throughput": 5466.81, "total_tokens": 35460976} {"current_steps": 58200, "total_steps": 64460, "loss": 0.1753, "lr": 2.8464086352266993e-07, "epoch": 18.057710207880856, "percentage": 90.29, "elapsed_time": "1:48:07", "remaining_time": "0:11:37", "throughput": 5466.81, "total_tokens": 35463568} {"current_steps": 58205, "total_steps": 64460, "loss": 0.2157, "lr": 2.8419077455636433e-07, "epoch": 18.05926155755507, "percentage": 90.3, "elapsed_time": "1:48:07", "remaining_time": "0:11:37", "throughput": 5466.93, "total_tokens": 35467568} {"current_steps": 58210, "total_steps": 64460, "loss": 0.1881, "lr": 2.837410313147182e-07, "epoch": 18.06081290722929, "percentage": 90.3, "elapsed_time": "1:48:08", "remaining_time": "0:11:36", "throughput": 5467.03, "total_tokens": 35471600} {"current_steps": 58215, "total_steps": 64460, "loss": 0.1225, "lr": 2.83291633830704e-07, "epoch": 18.062364256903507, "percentage": 90.31, "elapsed_time": "1:48:08", "remaining_time": "0:11:36", "throughput": 5467.05, "total_tokens": 35474128} {"current_steps": 58220, "total_steps": 64460, "loss": 0.1252, "lr": 2.8284258213726657e-07, "epoch": 18.063915606577723, "percentage": 90.32, "elapsed_time": "1:48:09", "remaining_time": "0:11:35", "throughput": 5467.17, "total_tokens": 35478288} {"current_steps": 58225, "total_steps": 64460, "loss": 0.192, "lr": 2.8239387626732784e-07, "epoch": 18.06546695625194, "percentage": 90.33, "elapsed_time": "1:48:09", "remaining_time": "0:11:34", "throughput": 5467.14, "total_tokens": 35480528} {"current_steps": 58230, "total_steps": 64460, "loss": 0.1269, "lr": 2.8194551625378266e-07, "epoch": 18.067018305926155, "percentage": 90.34, "elapsed_time": "1:48:10", "remaining_time": "0:11:34", "throughput": 5467.24, "total_tokens": 35484464} {"current_steps": 58235, "total_steps": 64460, "loss": 0.2021, "lr": 2.8149750212950135e-07, "epoch": 18.068569655600374, "percentage": 90.34, "elapsed_time": "1:48:10", "remaining_time": "0:11:33", "throughput": 5467.29, "total_tokens": 35487632} {"current_steps": 58240, "total_steps": 64460, "loss": 0.0794, "lr": 2.810498339273282e-07, "epoch": 18.07012100527459, "percentage": 90.35, "elapsed_time": "1:48:11", "remaining_time": "0:11:33", "throughput": 5467.26, "total_tokens": 35489904} {"current_steps": 58245, "total_steps": 64460, "loss": 0.1128, "lr": 2.8060251168008314e-07, "epoch": 18.071672354948806, "percentage": 90.36, "elapsed_time": "1:48:11", "remaining_time": "0:11:32", "throughput": 5467.27, "total_tokens": 35492528} {"current_steps": 58250, "total_steps": 64460, "loss": 0.1557, "lr": 2.8015553542055984e-07, "epoch": 18.07322370462302, "percentage": 90.37, "elapsed_time": "1:48:12", "remaining_time": "0:11:32", "throughput": 5467.24, "total_tokens": 35494768} {"current_steps": 58255, "total_steps": 64460, "loss": 0.1626, "lr": 2.797089051815266e-07, "epoch": 18.074775054297238, "percentage": 90.37, "elapsed_time": "1:48:12", "remaining_time": "0:11:31", "throughput": 5467.34, "total_tokens": 35498672} {"current_steps": 58260, "total_steps": 64460, "loss": 0.1513, "lr": 2.792626209957283e-07, "epoch": 18.076326403971454, "percentage": 90.38, "elapsed_time": "1:48:13", "remaining_time": "0:11:31", "throughput": 5467.38, "total_tokens": 35501680} {"current_steps": 58265, "total_steps": 64460, "loss": 0.2442, "lr": 2.7881668289588106e-07, "epoch": 18.077877753645673, "percentage": 90.39, "elapsed_time": "1:48:13", "remaining_time": "0:11:30", "throughput": 5467.37, "total_tokens": 35504144} {"current_steps": 58270, "total_steps": 64460, "loss": 0.1429, "lr": 2.783710909146792e-07, "epoch": 18.07942910331989, "percentage": 90.4, "elapsed_time": "1:48:14", "remaining_time": "0:11:29", "throughput": 5467.39, "total_tokens": 35507248} {"current_steps": 58275, "total_steps": 64460, "loss": 0.0966, "lr": 2.779258450847877e-07, "epoch": 18.080980452994105, "percentage": 90.4, "elapsed_time": "1:48:14", "remaining_time": "0:11:29", "throughput": 5467.37, "total_tokens": 35509616} {"current_steps": 58280, "total_steps": 64460, "loss": 0.1088, "lr": 2.7748094543884995e-07, "epoch": 18.08253180266832, "percentage": 90.41, "elapsed_time": "1:48:15", "remaining_time": "0:11:28", "throughput": 5467.35, "total_tokens": 35512208} {"current_steps": 58285, "total_steps": 64460, "loss": 0.1243, "lr": 2.770363920094815e-07, "epoch": 18.084083152342536, "percentage": 90.42, "elapsed_time": "1:48:15", "remaining_time": "0:11:28", "throughput": 5467.45, "total_tokens": 35515728} {"current_steps": 58290, "total_steps": 64460, "loss": 0.1209, "lr": 2.7659218482927464e-07, "epoch": 18.085634502016756, "percentage": 90.43, "elapsed_time": "1:48:16", "remaining_time": "0:11:27", "throughput": 5467.48, "total_tokens": 35518640} {"current_steps": 58295, "total_steps": 64460, "loss": 0.0892, "lr": 2.761483239307933e-07, "epoch": 18.087185851690972, "percentage": 90.44, "elapsed_time": "1:48:17", "remaining_time": "0:11:27", "throughput": 5467.63, "total_tokens": 35523504} {"current_steps": 58300, "total_steps": 64460, "loss": 0.1628, "lr": 2.757048093465792e-07, "epoch": 18.088737201365188, "percentage": 90.44, "elapsed_time": "1:48:17", "remaining_time": "0:11:26", "throughput": 5467.66, "total_tokens": 35526192} {"current_steps": 58305, "total_steps": 64460, "loss": 0.126, "lr": 2.7526164110914577e-07, "epoch": 18.090288551039404, "percentage": 90.45, "elapsed_time": "1:48:17", "remaining_time": "0:11:25", "throughput": 5467.7, "total_tokens": 35529104} {"current_steps": 58310, "total_steps": 64460, "loss": 0.1781, "lr": 2.748188192509843e-07, "epoch": 18.09183990071362, "percentage": 90.46, "elapsed_time": "1:48:18", "remaining_time": "0:11:25", "throughput": 5467.73, "total_tokens": 35532400} {"current_steps": 58315, "total_steps": 64460, "loss": 0.1552, "lr": 2.743763438045566e-07, "epoch": 18.09339125038784, "percentage": 90.47, "elapsed_time": "1:48:19", "remaining_time": "0:11:24", "throughput": 5467.72, "total_tokens": 35535056} {"current_steps": 58320, "total_steps": 64460, "loss": 0.1553, "lr": 2.739342148023033e-07, "epoch": 18.094942600062055, "percentage": 90.47, "elapsed_time": "1:48:19", "remaining_time": "0:11:24", "throughput": 5467.7, "total_tokens": 35537424} {"current_steps": 58325, "total_steps": 64460, "loss": 0.1525, "lr": 2.7349243227663744e-07, "epoch": 18.09649394973627, "percentage": 90.48, "elapsed_time": "1:48:20", "remaining_time": "0:11:23", "throughput": 5467.78, "total_tokens": 35540752} {"current_steps": 58330, "total_steps": 64460, "loss": 0.2009, "lr": 2.7305099625994593e-07, "epoch": 18.098045299410487, "percentage": 90.49, "elapsed_time": "1:48:20", "remaining_time": "0:11:23", "throughput": 5467.82, "total_tokens": 35543696} {"current_steps": 58335, "total_steps": 64460, "loss": 0.1339, "lr": 2.726099067845928e-07, "epoch": 18.099596649084702, "percentage": 90.5, "elapsed_time": "1:48:21", "remaining_time": "0:11:22", "throughput": 5467.82, "total_tokens": 35546480} {"current_steps": 58340, "total_steps": 64460, "loss": 0.1586, "lr": 2.721691638829133e-07, "epoch": 18.101147998758922, "percentage": 90.51, "elapsed_time": "1:48:21", "remaining_time": "0:11:22", "throughput": 5467.82, "total_tokens": 35549104} {"current_steps": 58345, "total_steps": 64460, "loss": 0.1743, "lr": 2.7172876758722045e-07, "epoch": 18.102699348433138, "percentage": 90.51, "elapsed_time": "1:48:22", "remaining_time": "0:11:21", "throughput": 5467.9, "total_tokens": 35552784} {"current_steps": 58350, "total_steps": 64460, "loss": 0.1704, "lr": 2.712887179297996e-07, "epoch": 18.104250698107354, "percentage": 90.52, "elapsed_time": "1:48:22", "remaining_time": "0:11:20", "throughput": 5467.95, "total_tokens": 35555568} {"current_steps": 58355, "total_steps": 64460, "loss": 0.1218, "lr": 2.708490149429127e-07, "epoch": 18.10580204778157, "percentage": 90.53, "elapsed_time": "1:48:23", "remaining_time": "0:11:20", "throughput": 5467.95, "total_tokens": 35558256} {"current_steps": 58360, "total_steps": 64460, "loss": 0.2137, "lr": 2.704096586587934e-07, "epoch": 18.107353397455785, "percentage": 90.54, "elapsed_time": "1:48:23", "remaining_time": "0:11:19", "throughput": 5468.04, "total_tokens": 35562544} {"current_steps": 58365, "total_steps": 64460, "loss": 0.2082, "lr": 2.699706491096543e-07, "epoch": 18.108904747130005, "percentage": 90.54, "elapsed_time": "1:48:24", "remaining_time": "0:11:19", "throughput": 5468.11, "total_tokens": 35565712} {"current_steps": 58370, "total_steps": 64460, "loss": 0.0848, "lr": 2.695319863276774e-07, "epoch": 18.11045609680422, "percentage": 90.55, "elapsed_time": "1:48:24", "remaining_time": "0:11:18", "throughput": 5468.16, "total_tokens": 35568656} {"current_steps": 58375, "total_steps": 64460, "loss": 0.0899, "lr": 2.690936703450231e-07, "epoch": 18.112007446478437, "percentage": 90.56, "elapsed_time": "1:48:25", "remaining_time": "0:11:18", "throughput": 5468.21, "total_tokens": 35571536} {"current_steps": 58380, "total_steps": 64460, "loss": 0.113, "lr": 2.6865570119382564e-07, "epoch": 18.113558796152653, "percentage": 90.57, "elapsed_time": "1:48:25", "remaining_time": "0:11:17", "throughput": 5468.29, "total_tokens": 35575184} {"current_steps": 58385, "total_steps": 64460, "loss": 0.2196, "lr": 2.6821807890619223e-07, "epoch": 18.11511014582687, "percentage": 90.58, "elapsed_time": "1:48:26", "remaining_time": "0:11:16", "throughput": 5468.27, "total_tokens": 35577872} {"current_steps": 58390, "total_steps": 64460, "loss": 0.2601, "lr": 2.677808035142071e-07, "epoch": 18.116661495501084, "percentage": 90.58, "elapsed_time": "1:48:26", "remaining_time": "0:11:16", "throughput": 5468.26, "total_tokens": 35580368} {"current_steps": 58395, "total_steps": 64460, "loss": 0.1056, "lr": 2.6734387504992633e-07, "epoch": 18.118212845175304, "percentage": 90.59, "elapsed_time": "1:48:27", "remaining_time": "0:11:15", "throughput": 5468.24, "total_tokens": 35582928} {"current_steps": 58400, "total_steps": 64460, "loss": 0.1897, "lr": 2.6690729354538315e-07, "epoch": 18.11976419484952, "percentage": 90.6, "elapsed_time": "1:48:27", "remaining_time": "0:11:15", "throughput": 5468.3, "total_tokens": 35586608} {"current_steps": 58405, "total_steps": 64460, "loss": 0.1855, "lr": 2.664710590325825e-07, "epoch": 18.121315544523735, "percentage": 90.61, "elapsed_time": "1:48:28", "remaining_time": "0:11:14", "throughput": 5468.26, "total_tokens": 35589040} {"current_steps": 58410, "total_steps": 64460, "loss": 0.1725, "lr": 2.6603517154350777e-07, "epoch": 18.12286689419795, "percentage": 90.61, "elapsed_time": "1:48:28", "remaining_time": "0:11:14", "throughput": 5468.3, "total_tokens": 35592208} {"current_steps": 58415, "total_steps": 64460, "loss": 0.0816, "lr": 2.655996311101122e-07, "epoch": 18.124418243872167, "percentage": 90.62, "elapsed_time": "1:48:29", "remaining_time": "0:11:13", "throughput": 5468.34, "total_tokens": 35595664} {"current_steps": 58420, "total_steps": 64460, "loss": 0.1723, "lr": 2.651644377643287e-07, "epoch": 18.125969593546387, "percentage": 90.63, "elapsed_time": "1:48:29", "remaining_time": "0:11:13", "throughput": 5468.39, "total_tokens": 35599024} {"current_steps": 58425, "total_steps": 64460, "loss": 0.127, "lr": 2.647295915380599e-07, "epoch": 18.127520943220603, "percentage": 90.64, "elapsed_time": "1:48:30", "remaining_time": "0:11:12", "throughput": 5468.36, "total_tokens": 35601808} {"current_steps": 58430, "total_steps": 64460, "loss": 0.139, "lr": 2.642950924631865e-07, "epoch": 18.12907229289482, "percentage": 90.65, "elapsed_time": "1:48:31", "remaining_time": "0:11:11", "throughput": 5468.44, "total_tokens": 35606000} {"current_steps": 58435, "total_steps": 64460, "loss": 0.1542, "lr": 2.638609405715614e-07, "epoch": 18.130623642569034, "percentage": 90.65, "elapsed_time": "1:48:31", "remaining_time": "0:11:11", "throughput": 5468.44, "total_tokens": 35608784} {"current_steps": 58440, "total_steps": 64460, "loss": 0.0764, "lr": 2.6342713589501356e-07, "epoch": 18.13217499224325, "percentage": 90.66, "elapsed_time": "1:48:32", "remaining_time": "0:11:10", "throughput": 5468.38, "total_tokens": 35611184} {"current_steps": 58445, "total_steps": 64460, "loss": 0.1487, "lr": 2.6299367846534693e-07, "epoch": 18.13372634191747, "percentage": 90.67, "elapsed_time": "1:48:32", "remaining_time": "0:11:10", "throughput": 5468.37, "total_tokens": 35613616} {"current_steps": 58450, "total_steps": 64460, "loss": 0.1964, "lr": 2.625605683143373e-07, "epoch": 18.135277691591686, "percentage": 90.68, "elapsed_time": "1:48:33", "remaining_time": "0:11:09", "throughput": 5468.34, "total_tokens": 35616112} {"current_steps": 58455, "total_steps": 64460, "loss": 0.1312, "lr": 2.621278054737386e-07, "epoch": 18.1368290412659, "percentage": 90.68, "elapsed_time": "1:48:33", "remaining_time": "0:11:09", "throughput": 5468.35, "total_tokens": 35618832} {"current_steps": 58460, "total_steps": 64460, "loss": 0.1103, "lr": 2.6169538997527556e-07, "epoch": 18.138380390940117, "percentage": 90.69, "elapsed_time": "1:48:34", "remaining_time": "0:11:08", "throughput": 5468.38, "total_tokens": 35622096} {"current_steps": 58465, "total_steps": 64460, "loss": 0.1927, "lr": 2.612633218506516e-07, "epoch": 18.139931740614333, "percentage": 90.7, "elapsed_time": "1:48:34", "remaining_time": "0:11:08", "throughput": 5468.52, "total_tokens": 35626992} {"current_steps": 58470, "total_steps": 64460, "loss": 0.162, "lr": 2.6083160113153985e-07, "epoch": 18.141483090288553, "percentage": 90.71, "elapsed_time": "1:48:35", "remaining_time": "0:11:07", "throughput": 5468.5, "total_tokens": 35629648} {"current_steps": 58475, "total_steps": 64460, "loss": 0.1824, "lr": 2.6040022784959316e-07, "epoch": 18.14303443996277, "percentage": 90.72, "elapsed_time": "1:48:35", "remaining_time": "0:11:06", "throughput": 5468.48, "total_tokens": 35632240} {"current_steps": 58480, "total_steps": 64460, "loss": 0.1412, "lr": 2.599692020364336e-07, "epoch": 18.144585789636984, "percentage": 90.72, "elapsed_time": "1:48:36", "remaining_time": "0:11:06", "throughput": 5468.54, "total_tokens": 35635664} {"current_steps": 58485, "total_steps": 64460, "loss": 0.173, "lr": 2.5953852372366307e-07, "epoch": 18.1461371393112, "percentage": 90.73, "elapsed_time": "1:48:37", "remaining_time": "0:11:05", "throughput": 5468.53, "total_tokens": 35638448} {"current_steps": 58490, "total_steps": 64460, "loss": 0.1804, "lr": 2.591081929428535e-07, "epoch": 18.147688488985416, "percentage": 90.74, "elapsed_time": "1:48:37", "remaining_time": "0:11:05", "throughput": 5468.56, "total_tokens": 35641872} {"current_steps": 58495, "total_steps": 64460, "loss": 0.1192, "lr": 2.5867820972555413e-07, "epoch": 18.149239838659636, "percentage": 90.75, "elapsed_time": "1:48:38", "remaining_time": "0:11:04", "throughput": 5468.52, "total_tokens": 35644432} {"current_steps": 58500, "total_steps": 64460, "loss": 0.179, "lr": 2.582485741032881e-07, "epoch": 18.15079118833385, "percentage": 90.75, "elapsed_time": "1:48:38", "remaining_time": "0:11:04", "throughput": 5468.5, "total_tokens": 35647120} {"current_steps": 58505, "total_steps": 64460, "loss": 0.1689, "lr": 2.578192861075518e-07, "epoch": 18.152342538008067, "percentage": 90.76, "elapsed_time": "1:48:39", "remaining_time": "0:11:03", "throughput": 5468.48, "total_tokens": 35649648} {"current_steps": 58510, "total_steps": 64460, "loss": 0.1128, "lr": 2.5739034576981794e-07, "epoch": 18.153893887682283, "percentage": 90.77, "elapsed_time": "1:48:39", "remaining_time": "0:11:02", "throughput": 5468.5, "total_tokens": 35652752} {"current_steps": 58515, "total_steps": 64460, "loss": 0.2178, "lr": 2.569617531215324e-07, "epoch": 18.1554452373565, "percentage": 90.78, "elapsed_time": "1:48:40", "remaining_time": "0:11:02", "throughput": 5468.49, "total_tokens": 35655824} {"current_steps": 58520, "total_steps": 64460, "loss": 0.1406, "lr": 2.565335081941167e-07, "epoch": 18.156996587030715, "percentage": 90.78, "elapsed_time": "1:48:40", "remaining_time": "0:11:01", "throughput": 5468.49, "total_tokens": 35658704} {"current_steps": 58525, "total_steps": 64460, "loss": 0.141, "lr": 2.561056110189653e-07, "epoch": 18.158547936704935, "percentage": 90.79, "elapsed_time": "1:48:41", "remaining_time": "0:11:01", "throughput": 5468.59, "total_tokens": 35662448} {"current_steps": 58530, "total_steps": 64460, "loss": 0.0891, "lr": 2.556780616274496e-07, "epoch": 18.16009928637915, "percentage": 90.8, "elapsed_time": "1:48:41", "remaining_time": "0:11:00", "throughput": 5468.59, "total_tokens": 35665296} {"current_steps": 58535, "total_steps": 64460, "loss": 0.1302, "lr": 2.5525086005091235e-07, "epoch": 18.161650636053366, "percentage": 90.81, "elapsed_time": "1:48:42", "remaining_time": "0:11:00", "throughput": 5468.6, "total_tokens": 35668240} {"current_steps": 58540, "total_steps": 64460, "loss": 0.1375, "lr": 2.5482400632067415e-07, "epoch": 18.163201985727582, "percentage": 90.82, "elapsed_time": "1:48:42", "remaining_time": "0:10:59", "throughput": 5468.62, "total_tokens": 35671152} {"current_steps": 58545, "total_steps": 64460, "loss": 0.1924, "lr": 2.5439750046802656e-07, "epoch": 18.164753335401798, "percentage": 90.82, "elapsed_time": "1:48:43", "remaining_time": "0:10:59", "throughput": 5468.59, "total_tokens": 35673744} {"current_steps": 58550, "total_steps": 64460, "loss": 0.1079, "lr": 2.5397134252423906e-07, "epoch": 18.166304685076017, "percentage": 90.83, "elapsed_time": "1:48:44", "remaining_time": "0:10:58", "throughput": 5468.65, "total_tokens": 35677552} {"current_steps": 58555, "total_steps": 64460, "loss": 0.1305, "lr": 2.5354553252055324e-07, "epoch": 18.167856034750233, "percentage": 90.84, "elapsed_time": "1:48:44", "remaining_time": "0:10:57", "throughput": 5468.61, "total_tokens": 35680336} {"current_steps": 58560, "total_steps": 64460, "loss": 0.1449, "lr": 2.5312007048818646e-07, "epoch": 18.16940738442445, "percentage": 90.85, "elapsed_time": "1:48:45", "remaining_time": "0:10:57", "throughput": 5468.57, "total_tokens": 35682640} {"current_steps": 58565, "total_steps": 64460, "loss": 0.1455, "lr": 2.526949564583303e-07, "epoch": 18.170958734098665, "percentage": 90.85, "elapsed_time": "1:48:45", "remaining_time": "0:10:56", "throughput": 5468.59, "total_tokens": 35685520} {"current_steps": 58570, "total_steps": 64460, "loss": 0.1765, "lr": 2.5227019046214993e-07, "epoch": 18.17251008377288, "percentage": 90.86, "elapsed_time": "1:48:46", "remaining_time": "0:10:56", "throughput": 5468.65, "total_tokens": 35688560} {"current_steps": 58575, "total_steps": 64460, "loss": 0.1195, "lr": 2.5184577253078656e-07, "epoch": 18.1740614334471, "percentage": 90.87, "elapsed_time": "1:48:46", "remaining_time": "0:10:55", "throughput": 5468.6, "total_tokens": 35691312} {"current_steps": 58580, "total_steps": 64460, "loss": 0.2438, "lr": 2.5142170269535417e-07, "epoch": 18.175612783121316, "percentage": 90.88, "elapsed_time": "1:48:47", "remaining_time": "0:10:55", "throughput": 5468.59, "total_tokens": 35693840} {"current_steps": 58585, "total_steps": 64460, "loss": 0.1927, "lr": 2.509979809869428e-07, "epoch": 18.177164132795532, "percentage": 90.89, "elapsed_time": "1:48:47", "remaining_time": "0:10:54", "throughput": 5468.58, "total_tokens": 35696656} {"current_steps": 58590, "total_steps": 64460, "loss": 0.1725, "lr": 2.5057460743661556e-07, "epoch": 18.178715482469748, "percentage": 90.89, "elapsed_time": "1:48:48", "remaining_time": "0:10:54", "throughput": 5468.65, "total_tokens": 35699952} {"current_steps": 58595, "total_steps": 64460, "loss": 0.1701, "lr": 2.501515820754119e-07, "epoch": 18.180266832143964, "percentage": 90.9, "elapsed_time": "1:48:48", "remaining_time": "0:10:53", "throughput": 5468.67, "total_tokens": 35702736} {"current_steps": 58600, "total_steps": 64460, "loss": 0.1843, "lr": 2.497289049343438e-07, "epoch": 18.181818181818183, "percentage": 90.91, "elapsed_time": "1:48:49", "remaining_time": "0:10:52", "throughput": 5468.73, "total_tokens": 35706064} {"current_steps": 58605, "total_steps": 64460, "loss": 0.1159, "lr": 2.493065760443986e-07, "epoch": 18.1833695314924, "percentage": 90.92, "elapsed_time": "1:48:49", "remaining_time": "0:10:52", "throughput": 5468.75, "total_tokens": 35709008} {"current_steps": 58610, "total_steps": 64460, "loss": 0.0753, "lr": 2.4888459543653763e-07, "epoch": 18.184920881166615, "percentage": 90.92, "elapsed_time": "1:48:50", "remaining_time": "0:10:51", "throughput": 5468.75, "total_tokens": 35711920} {"current_steps": 58615, "total_steps": 64460, "loss": 0.1268, "lr": 2.484629631416968e-07, "epoch": 18.18647223084083, "percentage": 90.93, "elapsed_time": "1:48:50", "remaining_time": "0:10:51", "throughput": 5468.89, "total_tokens": 35716272} {"current_steps": 58620, "total_steps": 64460, "loss": 0.1526, "lr": 2.480416791907886e-07, "epoch": 18.188023580515047, "percentage": 90.94, "elapsed_time": "1:48:51", "remaining_time": "0:10:50", "throughput": 5468.86, "total_tokens": 35718800} {"current_steps": 58625, "total_steps": 64460, "loss": 0.1338, "lr": 2.4762074361469656e-07, "epoch": 18.189574930189266, "percentage": 90.95, "elapsed_time": "1:48:51", "remaining_time": "0:10:50", "throughput": 5468.81, "total_tokens": 35721872} {"current_steps": 58630, "total_steps": 64460, "loss": 0.1288, "lr": 2.4720015644428e-07, "epoch": 18.191126279863482, "percentage": 90.96, "elapsed_time": "1:48:52", "remaining_time": "0:10:49", "throughput": 5468.82, "total_tokens": 35724752} {"current_steps": 58635, "total_steps": 64460, "loss": 0.1629, "lr": 2.4677991771037467e-07, "epoch": 18.192677629537698, "percentage": 90.96, "elapsed_time": "1:48:52", "remaining_time": "0:10:49", "throughput": 5468.72, "total_tokens": 35727120} {"current_steps": 58640, "total_steps": 64460, "loss": 0.1651, "lr": 2.4636002744378664e-07, "epoch": 18.194228979211914, "percentage": 90.97, "elapsed_time": "1:48:53", "remaining_time": "0:10:48", "throughput": 5468.68, "total_tokens": 35730032} {"current_steps": 58645, "total_steps": 64460, "loss": 0.165, "lr": 2.459404856753006e-07, "epoch": 18.19578032888613, "percentage": 90.98, "elapsed_time": "1:48:54", "remaining_time": "0:10:47", "throughput": 5468.75, "total_tokens": 35733936} {"current_steps": 58650, "total_steps": 64460, "loss": 0.2145, "lr": 2.455212924356742e-07, "epoch": 18.197331678560346, "percentage": 90.99, "elapsed_time": "1:48:54", "remaining_time": "0:10:47", "throughput": 5468.75, "total_tokens": 35736624} {"current_steps": 58655, "total_steps": 64460, "loss": 0.0991, "lr": 2.4510244775563743e-07, "epoch": 18.198883028234565, "percentage": 90.99, "elapsed_time": "1:48:55", "remaining_time": "0:10:46", "throughput": 5468.77, "total_tokens": 35739536} {"current_steps": 58660, "total_steps": 64460, "loss": 0.1223, "lr": 2.4468395166589885e-07, "epoch": 18.20043437790878, "percentage": 91.0, "elapsed_time": "1:48:55", "remaining_time": "0:10:46", "throughput": 5468.8, "total_tokens": 35742736} {"current_steps": 58665, "total_steps": 64460, "loss": 0.1303, "lr": 2.4426580419713684e-07, "epoch": 18.201985727582997, "percentage": 91.01, "elapsed_time": "1:48:56", "remaining_time": "0:10:45", "throughput": 5468.93, "total_tokens": 35748048} {"current_steps": 58670, "total_steps": 64460, "loss": 0.2679, "lr": 2.4384800538000854e-07, "epoch": 18.203537077257213, "percentage": 91.02, "elapsed_time": "1:48:57", "remaining_time": "0:10:45", "throughput": 5468.95, "total_tokens": 35750960} {"current_steps": 58675, "total_steps": 64460, "loss": 0.2138, "lr": 2.4343055524514214e-07, "epoch": 18.20508842693143, "percentage": 91.03, "elapsed_time": "1:48:57", "remaining_time": "0:10:44", "throughput": 5468.99, "total_tokens": 35753872} {"current_steps": 58680, "total_steps": 64460, "loss": 0.1583, "lr": 2.430134538231427e-07, "epoch": 18.20663977660565, "percentage": 91.03, "elapsed_time": "1:48:58", "remaining_time": "0:10:44", "throughput": 5469.02, "total_tokens": 35756944} {"current_steps": 58685, "total_steps": 64460, "loss": 0.2204, "lr": 2.425967011445879e-07, "epoch": 18.208191126279864, "percentage": 91.04, "elapsed_time": "1:48:58", "remaining_time": "0:10:43", "throughput": 5468.95, "total_tokens": 35759184} {"current_steps": 58690, "total_steps": 64460, "loss": 0.1027, "lr": 2.4218029724003165e-07, "epoch": 18.20974247595408, "percentage": 91.05, "elapsed_time": "1:48:59", "remaining_time": "0:10:42", "throughput": 5468.95, "total_tokens": 35761936} {"current_steps": 58695, "total_steps": 64460, "loss": 0.1108, "lr": 2.417642421399996e-07, "epoch": 18.211293825628296, "percentage": 91.06, "elapsed_time": "1:48:59", "remaining_time": "0:10:42", "throughput": 5468.96, "total_tokens": 35765072} {"current_steps": 58700, "total_steps": 64460, "loss": 0.1289, "lr": 2.413485358749945e-07, "epoch": 18.212845175302512, "percentage": 91.06, "elapsed_time": "1:49:00", "remaining_time": "0:10:41", "throughput": 5468.94, "total_tokens": 35767664} {"current_steps": 58705, "total_steps": 64460, "loss": 0.1901, "lr": 2.409331784754937e-07, "epoch": 18.21439652497673, "percentage": 91.07, "elapsed_time": "1:49:00", "remaining_time": "0:10:41", "throughput": 5468.99, "total_tokens": 35771440} {"current_steps": 58710, "total_steps": 64460, "loss": 0.1745, "lr": 2.4051816997194555e-07, "epoch": 18.215947874650947, "percentage": 91.08, "elapsed_time": "1:49:01", "remaining_time": "0:10:40", "throughput": 5468.94, "total_tokens": 35773808} {"current_steps": 58715, "total_steps": 64460, "loss": 0.1278, "lr": 2.401035103947774e-07, "epoch": 18.217499224325163, "percentage": 91.09, "elapsed_time": "1:49:02", "remaining_time": "0:10:40", "throughput": 5468.98, "total_tokens": 35778064} {"current_steps": 58720, "total_steps": 64460, "loss": 0.1823, "lr": 2.3968919977438664e-07, "epoch": 18.21905057399938, "percentage": 91.1, "elapsed_time": "1:49:02", "remaining_time": "0:10:39", "throughput": 5468.91, "total_tokens": 35780336} {"current_steps": 58725, "total_steps": 64460, "loss": 0.2182, "lr": 2.392752381411484e-07, "epoch": 18.220601923673595, "percentage": 91.1, "elapsed_time": "1:49:03", "remaining_time": "0:10:38", "throughput": 5468.87, "total_tokens": 35782928} {"current_steps": 58730, "total_steps": 64460, "loss": 0.1958, "lr": 2.388616255254106e-07, "epoch": 18.222153273347814, "percentage": 91.11, "elapsed_time": "1:49:03", "remaining_time": "0:10:38", "throughput": 5468.89, "total_tokens": 35786384} {"current_steps": 58735, "total_steps": 64460, "loss": 0.1342, "lr": 2.384483619574962e-07, "epoch": 18.22370462302203, "percentage": 91.12, "elapsed_time": "1:49:04", "remaining_time": "0:10:37", "throughput": 5468.92, "total_tokens": 35789328} {"current_steps": 58740, "total_steps": 64460, "loss": 0.18, "lr": 2.3803544746770158e-07, "epoch": 18.225255972696246, "percentage": 91.13, "elapsed_time": "1:49:04", "remaining_time": "0:10:37", "throughput": 5468.91, "total_tokens": 35791888} {"current_steps": 58745, "total_steps": 64460, "loss": 0.1926, "lr": 2.3762288208629914e-07, "epoch": 18.226807322370462, "percentage": 91.13, "elapsed_time": "1:49:05", "remaining_time": "0:10:36", "throughput": 5468.94, "total_tokens": 35794960} {"current_steps": 58750, "total_steps": 64460, "loss": 0.0734, "lr": 2.3721066584353414e-07, "epoch": 18.228358672044678, "percentage": 91.14, "elapsed_time": "1:49:05", "remaining_time": "0:10:36", "throughput": 5468.98, "total_tokens": 35798160} {"current_steps": 58755, "total_steps": 64460, "loss": 0.31, "lr": 2.367987987696274e-07, "epoch": 18.229910021718897, "percentage": 91.15, "elapsed_time": "1:49:06", "remaining_time": "0:10:35", "throughput": 5468.95, "total_tokens": 35800560} {"current_steps": 58760, "total_steps": 64460, "loss": 0.1618, "lr": 2.3638728089477315e-07, "epoch": 18.231461371393113, "percentage": 91.16, "elapsed_time": "1:49:06", "remaining_time": "0:10:35", "throughput": 5468.94, "total_tokens": 35803504} {"current_steps": 58765, "total_steps": 64460, "loss": 0.1291, "lr": 2.359761122491411e-07, "epoch": 18.23301272106733, "percentage": 91.17, "elapsed_time": "1:49:07", "remaining_time": "0:10:34", "throughput": 5469.06, "total_tokens": 35808560} {"current_steps": 58770, "total_steps": 64460, "loss": 0.0863, "lr": 2.3556529286287488e-07, "epoch": 18.234564070741545, "percentage": 91.17, "elapsed_time": "1:49:07", "remaining_time": "0:10:33", "throughput": 5469.04, "total_tokens": 35811088} {"current_steps": 58775, "total_steps": 64460, "loss": 0.2353, "lr": 2.3515482276609104e-07, "epoch": 18.23611542041576, "percentage": 91.18, "elapsed_time": "1:49:08", "remaining_time": "0:10:33", "throughput": 5469.14, "total_tokens": 35815120} {"current_steps": 58780, "total_steps": 64460, "loss": 0.1729, "lr": 2.3474470198888378e-07, "epoch": 18.237666770089977, "percentage": 91.19, "elapsed_time": "1:49:09", "remaining_time": "0:10:32", "throughput": 5469.18, "total_tokens": 35817936} {"current_steps": 58785, "total_steps": 64460, "loss": 0.2007, "lr": 2.3433493056131851e-07, "epoch": 18.239218119764196, "percentage": 91.2, "elapsed_time": "1:49:09", "remaining_time": "0:10:32", "throughput": 5469.1, "total_tokens": 35820240} {"current_steps": 58790, "total_steps": 64460, "loss": 0.1045, "lr": 2.3392550851343732e-07, "epoch": 18.240769469438412, "percentage": 91.2, "elapsed_time": "1:49:10", "remaining_time": "0:10:31", "throughput": 5469.08, "total_tokens": 35823280} {"current_steps": 58795, "total_steps": 64460, "loss": 0.1465, "lr": 2.3351643587525397e-07, "epoch": 18.242320819112628, "percentage": 91.21, "elapsed_time": "1:49:10", "remaining_time": "0:10:31", "throughput": 5469.05, "total_tokens": 35825776} {"current_steps": 58800, "total_steps": 64460, "loss": 0.1789, "lr": 2.3310771267676057e-07, "epoch": 18.243872168786844, "percentage": 91.22, "elapsed_time": "1:49:11", "remaining_time": "0:10:30", "throughput": 5469.06, "total_tokens": 35828784} {"current_steps": 58805, "total_steps": 64460, "loss": 0.1424, "lr": 2.3269933894791986e-07, "epoch": 18.24542351846106, "percentage": 91.23, "elapsed_time": "1:49:11", "remaining_time": "0:10:30", "throughput": 5469.01, "total_tokens": 35831184} {"current_steps": 58810, "total_steps": 64460, "loss": 0.1276, "lr": 2.3229131471867117e-07, "epoch": 18.24697486813528, "percentage": 91.23, "elapsed_time": "1:49:12", "remaining_time": "0:10:29", "throughput": 5469.1, "total_tokens": 35835280} {"current_steps": 58815, "total_steps": 64460, "loss": 0.1755, "lr": 2.3188364001892672e-07, "epoch": 18.248526217809495, "percentage": 91.24, "elapsed_time": "1:49:12", "remaining_time": "0:10:28", "throughput": 5469.04, "total_tokens": 35837520} {"current_steps": 58820, "total_steps": 64460, "loss": 0.2715, "lr": 2.3147631487857426e-07, "epoch": 18.25007756748371, "percentage": 91.25, "elapsed_time": "1:49:13", "remaining_time": "0:10:28", "throughput": 5469.07, "total_tokens": 35840528} {"current_steps": 58825, "total_steps": 64460, "loss": 0.1508, "lr": 2.3106933932747654e-07, "epoch": 18.251628917157927, "percentage": 91.26, "elapsed_time": "1:49:13", "remaining_time": "0:10:27", "throughput": 5469.04, "total_tokens": 35842896} {"current_steps": 58830, "total_steps": 64460, "loss": 0.1071, "lr": 2.3066271339546809e-07, "epoch": 18.253180266832143, "percentage": 91.27, "elapsed_time": "1:49:14", "remaining_time": "0:10:27", "throughput": 5469.07, "total_tokens": 35845904} {"current_steps": 58835, "total_steps": 64460, "loss": 0.1006, "lr": 2.3025643711236055e-07, "epoch": 18.254731616506362, "percentage": 91.27, "elapsed_time": "1:49:14", "remaining_time": "0:10:26", "throughput": 5469.08, "total_tokens": 35848912} {"current_steps": 58840, "total_steps": 64460, "loss": 0.1435, "lr": 2.2985051050793795e-07, "epoch": 18.256282966180578, "percentage": 91.28, "elapsed_time": "1:49:15", "remaining_time": "0:10:26", "throughput": 5469.08, "total_tokens": 35851632} {"current_steps": 58845, "total_steps": 64460, "loss": 0.1928, "lr": 2.2944493361196084e-07, "epoch": 18.257834315854794, "percentage": 91.29, "elapsed_time": "1:49:16", "remaining_time": "0:10:25", "throughput": 5469.15, "total_tokens": 35856080} {"current_steps": 58850, "total_steps": 64460, "loss": 0.128, "lr": 2.2903970645416108e-07, "epoch": 18.25938566552901, "percentage": 91.3, "elapsed_time": "1:49:16", "remaining_time": "0:10:25", "throughput": 5469.26, "total_tokens": 35860464} {"current_steps": 58855, "total_steps": 64460, "loss": 0.0789, "lr": 2.2863482906424816e-07, "epoch": 18.260937015203226, "percentage": 91.3, "elapsed_time": "1:49:17", "remaining_time": "0:10:24", "throughput": 5469.26, "total_tokens": 35863344} {"current_steps": 58860, "total_steps": 64460, "loss": 0.1647, "lr": 2.2823030147190284e-07, "epoch": 18.262488364877445, "percentage": 91.31, "elapsed_time": "1:49:17", "remaining_time": "0:10:23", "throughput": 5469.29, "total_tokens": 35866416} {"current_steps": 58865, "total_steps": 64460, "loss": 0.1751, "lr": 2.2782612370678358e-07, "epoch": 18.26403971455166, "percentage": 91.32, "elapsed_time": "1:49:18", "remaining_time": "0:10:23", "throughput": 5469.38, "total_tokens": 35869904} {"current_steps": 58870, "total_steps": 64460, "loss": 0.2174, "lr": 2.274222957985195e-07, "epoch": 18.265591064225877, "percentage": 91.33, "elapsed_time": "1:49:18", "remaining_time": "0:10:22", "throughput": 5469.35, "total_tokens": 35872272} {"current_steps": 58875, "total_steps": 64460, "loss": 0.2069, "lr": 2.270188177767174e-07, "epoch": 18.267142413900093, "percentage": 91.34, "elapsed_time": "1:49:19", "remaining_time": "0:10:22", "throughput": 5469.37, "total_tokens": 35875248} {"current_steps": 58880, "total_steps": 64460, "loss": 0.1213, "lr": 2.2661568967095648e-07, "epoch": 18.26869376357431, "percentage": 91.34, "elapsed_time": "1:49:19", "remaining_time": "0:10:21", "throughput": 5469.41, "total_tokens": 35878224} {"current_steps": 58885, "total_steps": 64460, "loss": 0.1326, "lr": 2.2621291151079029e-07, "epoch": 18.270245113248528, "percentage": 91.35, "elapsed_time": "1:49:20", "remaining_time": "0:10:21", "throughput": 5469.41, "total_tokens": 35881008} {"current_steps": 58890, "total_steps": 64460, "loss": 0.1451, "lr": 2.258104833257485e-07, "epoch": 18.271796462922744, "percentage": 91.36, "elapsed_time": "1:49:20", "remaining_time": "0:10:20", "throughput": 5469.43, "total_tokens": 35883984} {"current_steps": 58895, "total_steps": 64460, "loss": 0.149, "lr": 2.2540840514533258e-07, "epoch": 18.27334781259696, "percentage": 91.37, "elapsed_time": "1:49:21", "remaining_time": "0:10:19", "throughput": 5469.43, "total_tokens": 35886704} {"current_steps": 58900, "total_steps": 64460, "loss": 0.1259, "lr": 2.250066769990211e-07, "epoch": 18.274899162271176, "percentage": 91.37, "elapsed_time": "1:49:21", "remaining_time": "0:10:19", "throughput": 5469.46, "total_tokens": 35889552} {"current_steps": 58905, "total_steps": 64460, "loss": 0.1628, "lr": 2.2460529891626393e-07, "epoch": 18.27645051194539, "percentage": 91.38, "elapsed_time": "1:49:22", "remaining_time": "0:10:18", "throughput": 5469.59, "total_tokens": 35894288} {"current_steps": 58910, "total_steps": 64460, "loss": 0.137, "lr": 2.2420427092648743e-07, "epoch": 18.278001861619607, "percentage": 91.39, "elapsed_time": "1:49:22", "remaining_time": "0:10:18", "throughput": 5469.51, "total_tokens": 35896336} {"current_steps": 58915, "total_steps": 64460, "loss": 0.2066, "lr": 2.2380359305909205e-07, "epoch": 18.279553211293827, "percentage": 91.4, "elapsed_time": "1:49:23", "remaining_time": "0:10:17", "throughput": 5469.54, "total_tokens": 35899248} {"current_steps": 58920, "total_steps": 64460, "loss": 0.2089, "lr": 2.2340326534345202e-07, "epoch": 18.281104560968043, "percentage": 91.41, "elapsed_time": "1:49:23", "remaining_time": "0:10:17", "throughput": 5469.53, "total_tokens": 35901808} {"current_steps": 58925, "total_steps": 64460, "loss": 0.1939, "lr": 2.2300328780891555e-07, "epoch": 18.28265591064226, "percentage": 91.41, "elapsed_time": "1:49:24", "remaining_time": "0:10:16", "throughput": 5469.6, "total_tokens": 35905264} {"current_steps": 58930, "total_steps": 64460, "loss": 0.2087, "lr": 2.226036604848064e-07, "epoch": 18.284207260316474, "percentage": 91.42, "elapsed_time": "1:49:25", "remaining_time": "0:10:16", "throughput": 5469.7, "total_tokens": 35908880} {"current_steps": 58935, "total_steps": 64460, "loss": 0.1383, "lr": 2.2220438340042173e-07, "epoch": 18.28575860999069, "percentage": 91.43, "elapsed_time": "1:49:25", "remaining_time": "0:10:15", "throughput": 5469.76, "total_tokens": 35912592} {"current_steps": 58940, "total_steps": 64460, "loss": 0.1901, "lr": 2.2180545658503306e-07, "epoch": 18.28730995966491, "percentage": 91.44, "elapsed_time": "1:49:26", "remaining_time": "0:10:14", "throughput": 5469.71, "total_tokens": 35914960} {"current_steps": 58945, "total_steps": 64460, "loss": 0.2826, "lr": 2.2140688006788702e-07, "epoch": 18.288861309339126, "percentage": 91.44, "elapsed_time": "1:49:26", "remaining_time": "0:10:14", "throughput": 5469.76, "total_tokens": 35918192} {"current_steps": 58950, "total_steps": 64460, "loss": 0.1484, "lr": 2.2100865387820358e-07, "epoch": 18.29041265901334, "percentage": 91.45, "elapsed_time": "1:49:27", "remaining_time": "0:10:13", "throughput": 5469.66, "total_tokens": 35920592} {"current_steps": 58955, "total_steps": 64460, "loss": 0.1221, "lr": 2.2061077804517772e-07, "epoch": 18.291964008687557, "percentage": 91.46, "elapsed_time": "1:49:27", "remaining_time": "0:10:13", "throughput": 5469.67, "total_tokens": 35923376} {"current_steps": 58960, "total_steps": 64460, "loss": 0.1675, "lr": 2.2021325259797776e-07, "epoch": 18.293515358361773, "percentage": 91.47, "elapsed_time": "1:49:28", "remaining_time": "0:10:12", "throughput": 5469.62, "total_tokens": 35925936} {"current_steps": 58965, "total_steps": 64460, "loss": 0.255, "lr": 2.1981607756574874e-07, "epoch": 18.295066708035993, "percentage": 91.48, "elapsed_time": "1:49:28", "remaining_time": "0:10:12", "throughput": 5469.69, "total_tokens": 35929712} {"current_steps": 58970, "total_steps": 64460, "loss": 0.1339, "lr": 2.194192529776057e-07, "epoch": 18.29661805771021, "percentage": 91.48, "elapsed_time": "1:49:29", "remaining_time": "0:10:11", "throughput": 5469.66, "total_tokens": 35932208} {"current_steps": 58975, "total_steps": 64460, "loss": 0.1331, "lr": 2.190227788626431e-07, "epoch": 18.298169407384425, "percentage": 91.49, "elapsed_time": "1:49:29", "remaining_time": "0:10:11", "throughput": 5469.63, "total_tokens": 35934832} {"current_steps": 58980, "total_steps": 64460, "loss": 0.2266, "lr": 2.18626655249925e-07, "epoch": 18.29972075705864, "percentage": 91.5, "elapsed_time": "1:49:30", "remaining_time": "0:10:10", "throughput": 5469.66, "total_tokens": 35937808} {"current_steps": 58985, "total_steps": 64460, "loss": 0.2512, "lr": 2.1823088216849363e-07, "epoch": 18.301272106732856, "percentage": 91.51, "elapsed_time": "1:49:30", "remaining_time": "0:10:09", "throughput": 5469.67, "total_tokens": 35940656} {"current_steps": 58990, "total_steps": 64460, "loss": 0.1856, "lr": 2.1783545964736308e-07, "epoch": 18.302823456407076, "percentage": 91.51, "elapsed_time": "1:49:31", "remaining_time": "0:10:09", "throughput": 5469.78, "total_tokens": 35945040} {"current_steps": 58995, "total_steps": 64460, "loss": 0.166, "lr": 2.174403877155229e-07, "epoch": 18.30437480608129, "percentage": 91.52, "elapsed_time": "1:49:32", "remaining_time": "0:10:08", "throughput": 5469.68, "total_tokens": 35947312} {"current_steps": 59000, "total_steps": 64460, "loss": 0.1766, "lr": 2.1704566640193548e-07, "epoch": 18.305926155755508, "percentage": 91.53, "elapsed_time": "1:49:32", "remaining_time": "0:10:08", "throughput": 5469.71, "total_tokens": 35950672} {"current_steps": 59005, "total_steps": 64460, "loss": 0.0995, "lr": 2.166512957355399e-07, "epoch": 18.307477505429723, "percentage": 91.54, "elapsed_time": "1:49:33", "remaining_time": "0:10:07", "throughput": 5469.78, "total_tokens": 35954160} {"current_steps": 59010, "total_steps": 64460, "loss": 0.13, "lr": 2.16257275745248e-07, "epoch": 18.30902885510394, "percentage": 91.55, "elapsed_time": "1:49:33", "remaining_time": "0:10:07", "throughput": 5469.84, "total_tokens": 35957296} {"current_steps": 59015, "total_steps": 64460, "loss": 0.1335, "lr": 2.158636064599451e-07, "epoch": 18.31058020477816, "percentage": 91.55, "elapsed_time": "1:49:34", "remaining_time": "0:10:06", "throughput": 5469.88, "total_tokens": 35960624} {"current_steps": 59020, "total_steps": 64460, "loss": 0.1824, "lr": 2.1547028790849301e-07, "epoch": 18.312131554452375, "percentage": 91.56, "elapsed_time": "1:49:34", "remaining_time": "0:10:06", "throughput": 5469.94, "total_tokens": 35964336} {"current_steps": 59025, "total_steps": 64460, "loss": 0.172, "lr": 2.1507732011972592e-07, "epoch": 18.31368290412659, "percentage": 91.57, "elapsed_time": "1:49:35", "remaining_time": "0:10:05", "throughput": 5469.96, "total_tokens": 35967600} {"current_steps": 59030, "total_steps": 64460, "loss": 0.1572, "lr": 2.146847031224536e-07, "epoch": 18.315234253800806, "percentage": 91.58, "elapsed_time": "1:49:36", "remaining_time": "0:10:04", "throughput": 5469.99, "total_tokens": 35970768} {"current_steps": 59035, "total_steps": 64460, "loss": 0.1067, "lr": 2.1429243694545854e-07, "epoch": 18.316785603475022, "percentage": 91.58, "elapsed_time": "1:49:36", "remaining_time": "0:10:04", "throughput": 5469.94, "total_tokens": 35972944} {"current_steps": 59040, "total_steps": 64460, "loss": 0.2268, "lr": 2.1390052161749942e-07, "epoch": 18.318336953149238, "percentage": 91.59, "elapsed_time": "1:49:37", "remaining_time": "0:10:03", "throughput": 5469.9, "total_tokens": 35975696} {"current_steps": 59045, "total_steps": 64460, "loss": 0.167, "lr": 2.1350895716730768e-07, "epoch": 18.319888302823458, "percentage": 91.6, "elapsed_time": "1:49:37", "remaining_time": "0:10:03", "throughput": 5469.98, "total_tokens": 35979856} {"current_steps": 59050, "total_steps": 64460, "loss": 0.1164, "lr": 2.1311774362359038e-07, "epoch": 18.321439652497673, "percentage": 91.61, "elapsed_time": "1:49:38", "remaining_time": "0:10:02", "throughput": 5470.06, "total_tokens": 35983504} {"current_steps": 59055, "total_steps": 64460, "loss": 0.1812, "lr": 2.1272688101502736e-07, "epoch": 18.32299100217189, "percentage": 91.61, "elapsed_time": "1:49:38", "remaining_time": "0:10:02", "throughput": 5470.02, "total_tokens": 35985904} {"current_steps": 59060, "total_steps": 64460, "loss": 0.1643, "lr": 2.1233636937027346e-07, "epoch": 18.324542351846105, "percentage": 91.62, "elapsed_time": "1:49:39", "remaining_time": "0:10:01", "throughput": 5470.0, "total_tokens": 35988528} {"current_steps": 59065, "total_steps": 64460, "loss": 0.1549, "lr": 2.1194620871795857e-07, "epoch": 18.32609370152032, "percentage": 91.63, "elapsed_time": "1:49:39", "remaining_time": "0:10:00", "throughput": 5469.95, "total_tokens": 35990960} {"current_steps": 59070, "total_steps": 64460, "loss": 0.1847, "lr": 2.1155639908668536e-07, "epoch": 18.32764505119454, "percentage": 91.64, "elapsed_time": "1:49:40", "remaining_time": "0:10:00", "throughput": 5469.94, "total_tokens": 35993392} {"current_steps": 59075, "total_steps": 64460, "loss": 0.2174, "lr": 2.1116694050503206e-07, "epoch": 18.329196400868756, "percentage": 91.65, "elapsed_time": "1:49:40", "remaining_time": "0:09:59", "throughput": 5469.93, "total_tokens": 35996016} {"current_steps": 59080, "total_steps": 64460, "loss": 0.1496, "lr": 2.1077783300154974e-07, "epoch": 18.330747750542972, "percentage": 91.65, "elapsed_time": "1:49:41", "remaining_time": "0:09:59", "throughput": 5469.93, "total_tokens": 35998768} {"current_steps": 59085, "total_steps": 64460, "loss": 0.2041, "lr": 2.1038907660476615e-07, "epoch": 18.33229910021719, "percentage": 91.66, "elapsed_time": "1:49:41", "remaining_time": "0:09:58", "throughput": 5469.85, "total_tokens": 36000816} {"current_steps": 59090, "total_steps": 64460, "loss": 0.1377, "lr": 2.1000067134317958e-07, "epoch": 18.333850449891404, "percentage": 91.67, "elapsed_time": "1:49:42", "remaining_time": "0:09:58", "throughput": 5469.79, "total_tokens": 36003280} {"current_steps": 59095, "total_steps": 64460, "loss": 0.1519, "lr": 2.0961261724526673e-07, "epoch": 18.335401799565624, "percentage": 91.68, "elapsed_time": "1:49:42", "remaining_time": "0:09:57", "throughput": 5469.88, "total_tokens": 36007376} {"current_steps": 59100, "total_steps": 64460, "loss": 0.1803, "lr": 2.0922491433947535e-07, "epoch": 18.33695314923984, "percentage": 91.68, "elapsed_time": "1:49:43", "remaining_time": "0:09:57", "throughput": 5470.0, "total_tokens": 36011728} {"current_steps": 59105, "total_steps": 64460, "loss": 0.0961, "lr": 2.0883756265422938e-07, "epoch": 18.338504498914055, "percentage": 91.69, "elapsed_time": "1:49:43", "remaining_time": "0:09:56", "throughput": 5470.02, "total_tokens": 36014640} {"current_steps": 59110, "total_steps": 64460, "loss": 0.0893, "lr": 2.0845056221792502e-07, "epoch": 18.34005584858827, "percentage": 91.7, "elapsed_time": "1:49:44", "remaining_time": "0:09:55", "throughput": 5470.0, "total_tokens": 36017392} {"current_steps": 59115, "total_steps": 64460, "loss": 0.1208, "lr": 2.0806391305893568e-07, "epoch": 18.341607198262487, "percentage": 91.71, "elapsed_time": "1:49:45", "remaining_time": "0:09:55", "throughput": 5470.1, "total_tokens": 36022384} {"current_steps": 59120, "total_steps": 64460, "loss": 0.1674, "lr": 2.0767761520560591e-07, "epoch": 18.343158547936707, "percentage": 91.72, "elapsed_time": "1:49:45", "remaining_time": "0:09:54", "throughput": 5470.17, "total_tokens": 36026064} {"current_steps": 59125, "total_steps": 64460, "loss": 0.2053, "lr": 2.0729166868625695e-07, "epoch": 18.344709897610922, "percentage": 91.72, "elapsed_time": "1:49:46", "remaining_time": "0:09:54", "throughput": 5470.2, "total_tokens": 36028944} {"current_steps": 59130, "total_steps": 64460, "loss": 0.081, "lr": 2.069060735291828e-07, "epoch": 18.34626124728514, "percentage": 91.73, "elapsed_time": "1:49:46", "remaining_time": "0:09:53", "throughput": 5470.28, "total_tokens": 36032272} {"current_steps": 59135, "total_steps": 64460, "loss": 0.1492, "lr": 2.0652082976265196e-07, "epoch": 18.347812596959354, "percentage": 91.74, "elapsed_time": "1:49:47", "remaining_time": "0:09:53", "throughput": 5470.27, "total_tokens": 36035632} {"current_steps": 59140, "total_steps": 64460, "loss": 0.1214, "lr": 2.06135937414908e-07, "epoch": 18.34936394663357, "percentage": 91.75, "elapsed_time": "1:49:48", "remaining_time": "0:09:52", "throughput": 5470.22, "total_tokens": 36038320} {"current_steps": 59145, "total_steps": 64460, "loss": 0.2607, "lr": 2.057513965141672e-07, "epoch": 18.35091529630779, "percentage": 91.75, "elapsed_time": "1:49:48", "remaining_time": "0:09:52", "throughput": 5470.31, "total_tokens": 36042160} {"current_steps": 59150, "total_steps": 64460, "loss": 0.1748, "lr": 2.05367207088622e-07, "epoch": 18.352466645982005, "percentage": 91.76, "elapsed_time": "1:49:49", "remaining_time": "0:09:51", "throughput": 5470.4, "total_tokens": 36045872} {"current_steps": 59155, "total_steps": 64460, "loss": 0.1482, "lr": 2.0498336916643712e-07, "epoch": 18.35401799565622, "percentage": 91.77, "elapsed_time": "1:49:49", "remaining_time": "0:09:50", "throughput": 5470.42, "total_tokens": 36049648} {"current_steps": 59160, "total_steps": 64460, "loss": 0.1588, "lr": 2.0459988277575337e-07, "epoch": 18.355569345330437, "percentage": 91.78, "elapsed_time": "1:49:50", "remaining_time": "0:09:50", "throughput": 5470.46, "total_tokens": 36052720} {"current_steps": 59165, "total_steps": 64460, "loss": 0.0846, "lr": 2.0421674794468326e-07, "epoch": 18.357120695004653, "percentage": 91.79, "elapsed_time": "1:49:50", "remaining_time": "0:09:49", "throughput": 5470.54, "total_tokens": 36055984} {"current_steps": 59170, "total_steps": 64460, "loss": 0.0826, "lr": 2.0383396470131654e-07, "epoch": 18.35867204467887, "percentage": 91.79, "elapsed_time": "1:49:51", "remaining_time": "0:09:49", "throughput": 5470.53, "total_tokens": 36058800} {"current_steps": 59175, "total_steps": 64460, "loss": 0.1192, "lr": 2.0345153307371523e-07, "epoch": 18.36022339435309, "percentage": 91.8, "elapsed_time": "1:49:51", "remaining_time": "0:09:48", "throughput": 5470.56, "total_tokens": 36061872} {"current_steps": 59180, "total_steps": 64460, "loss": 0.1509, "lr": 2.0306945308991578e-07, "epoch": 18.361774744027304, "percentage": 91.81, "elapsed_time": "1:49:52", "remaining_time": "0:09:48", "throughput": 5470.65, "total_tokens": 36065872} {"current_steps": 59185, "total_steps": 64460, "loss": 0.1555, "lr": 2.0268772477793075e-07, "epoch": 18.36332609370152, "percentage": 91.82, "elapsed_time": "1:49:53", "remaining_time": "0:09:47", "throughput": 5470.75, "total_tokens": 36070096} {"current_steps": 59190, "total_steps": 64460, "loss": 0.1425, "lr": 2.023063481657428e-07, "epoch": 18.364877443375736, "percentage": 91.82, "elapsed_time": "1:49:53", "remaining_time": "0:09:47", "throughput": 5470.73, "total_tokens": 36072592} {"current_steps": 59195, "total_steps": 64460, "loss": 0.0936, "lr": 2.0192532328131397e-07, "epoch": 18.366428793049952, "percentage": 91.83, "elapsed_time": "1:49:54", "remaining_time": "0:09:46", "throughput": 5470.79, "total_tokens": 36076048} {"current_steps": 59200, "total_steps": 64460, "loss": 0.1497, "lr": 2.0154465015257586e-07, "epoch": 18.36798014272417, "percentage": 91.84, "elapsed_time": "1:49:54", "remaining_time": "0:09:45", "throughput": 5470.8, "total_tokens": 36078736} {"current_steps": 59205, "total_steps": 64460, "loss": 0.1302, "lr": 2.0116432880743663e-07, "epoch": 18.369531492398387, "percentage": 91.85, "elapsed_time": "1:49:55", "remaining_time": "0:09:45", "throughput": 5470.78, "total_tokens": 36081808} {"current_steps": 59210, "total_steps": 64460, "loss": 0.2373, "lr": 2.007843592737796e-07, "epoch": 18.371082842072603, "percentage": 91.86, "elapsed_time": "1:49:55", "remaining_time": "0:09:44", "throughput": 5470.81, "total_tokens": 36084816} {"current_steps": 59215, "total_steps": 64460, "loss": 0.176, "lr": 2.004047415794602e-07, "epoch": 18.37263419174682, "percentage": 91.86, "elapsed_time": "1:49:56", "remaining_time": "0:09:44", "throughput": 5470.82, "total_tokens": 36087568} {"current_steps": 59220, "total_steps": 64460, "loss": 0.0967, "lr": 2.0002547575230845e-07, "epoch": 18.374185541421035, "percentage": 91.87, "elapsed_time": "1:49:56", "remaining_time": "0:09:43", "throughput": 5470.85, "total_tokens": 36090416} {"current_steps": 59225, "total_steps": 64460, "loss": 0.0808, "lr": 1.9964656182013042e-07, "epoch": 18.375736891095254, "percentage": 91.88, "elapsed_time": "1:49:57", "remaining_time": "0:09:43", "throughput": 5470.87, "total_tokens": 36093136} {"current_steps": 59230, "total_steps": 64460, "loss": 0.0827, "lr": 1.9926799981070334e-07, "epoch": 18.37728824076947, "percentage": 91.89, "elapsed_time": "1:49:57", "remaining_time": "0:09:42", "throughput": 5470.85, "total_tokens": 36095632} {"current_steps": 59235, "total_steps": 64460, "loss": 0.2373, "lr": 1.9888978975178164e-07, "epoch": 18.378839590443686, "percentage": 91.89, "elapsed_time": "1:49:58", "remaining_time": "0:09:42", "throughput": 5470.88, "total_tokens": 36098672} {"current_steps": 59240, "total_steps": 64460, "loss": 0.2279, "lr": 1.985119316710915e-07, "epoch": 18.380390940117902, "percentage": 91.9, "elapsed_time": "1:49:58", "remaining_time": "0:09:41", "throughput": 5470.9, "total_tokens": 36101456} {"current_steps": 59245, "total_steps": 64460, "loss": 0.1252, "lr": 1.9813442559633523e-07, "epoch": 18.381942289792118, "percentage": 91.91, "elapsed_time": "1:49:59", "remaining_time": "0:09:40", "throughput": 5470.94, "total_tokens": 36104496} {"current_steps": 59250, "total_steps": 64460, "loss": 0.0806, "lr": 1.9775727155518787e-07, "epoch": 18.383493639466337, "percentage": 91.92, "elapsed_time": "1:50:00", "remaining_time": "0:09:40", "throughput": 5471.05, "total_tokens": 36109328} {"current_steps": 59255, "total_steps": 64460, "loss": 0.1013, "lr": 1.973804695753001e-07, "epoch": 18.385044989140553, "percentage": 91.93, "elapsed_time": "1:50:00", "remaining_time": "0:09:39", "throughput": 5471.09, "total_tokens": 36112272} {"current_steps": 59260, "total_steps": 64460, "loss": 0.1973, "lr": 1.9700401968429483e-07, "epoch": 18.38659633881477, "percentage": 91.93, "elapsed_time": "1:50:01", "remaining_time": "0:09:39", "throughput": 5471.11, "total_tokens": 36115216} {"current_steps": 59265, "total_steps": 64460, "loss": 0.1692, "lr": 1.9662792190977166e-07, "epoch": 18.388147688488985, "percentage": 91.94, "elapsed_time": "1:50:01", "remaining_time": "0:09:38", "throughput": 5471.13, "total_tokens": 36118032} {"current_steps": 59270, "total_steps": 64460, "loss": 0.2166, "lr": 1.9625217627930126e-07, "epoch": 18.3896990381632, "percentage": 91.95, "elapsed_time": "1:50:02", "remaining_time": "0:09:38", "throughput": 5471.1, "total_tokens": 36120368} {"current_steps": 59275, "total_steps": 64460, "loss": 0.1585, "lr": 1.9587678282043164e-07, "epoch": 18.39125038783742, "percentage": 91.96, "elapsed_time": "1:50:02", "remaining_time": "0:09:37", "throughput": 5471.15, "total_tokens": 36123504} {"current_steps": 59280, "total_steps": 64460, "loss": 0.1347, "lr": 1.9550174156068302e-07, "epoch": 18.392801737511636, "percentage": 91.96, "elapsed_time": "1:50:03", "remaining_time": "0:09:36", "throughput": 5471.18, "total_tokens": 36126576} {"current_steps": 59285, "total_steps": 64460, "loss": 0.2491, "lr": 1.951270525275506e-07, "epoch": 18.394353087185852, "percentage": 91.97, "elapsed_time": "1:50:03", "remaining_time": "0:09:36", "throughput": 5471.11, "total_tokens": 36128720} {"current_steps": 59290, "total_steps": 64460, "loss": 0.1851, "lr": 1.9475271574850409e-07, "epoch": 18.395904436860068, "percentage": 91.98, "elapsed_time": "1:50:04", "remaining_time": "0:09:35", "throughput": 5471.19, "total_tokens": 36132912} {"current_steps": 59295, "total_steps": 64460, "loss": 0.1177, "lr": 1.943787312509854e-07, "epoch": 18.397455786534284, "percentage": 91.99, "elapsed_time": "1:50:04", "remaining_time": "0:09:35", "throughput": 5471.22, "total_tokens": 36136016} {"current_steps": 59300, "total_steps": 64460, "loss": 0.122, "lr": 1.9400509906241316e-07, "epoch": 18.3990071362085, "percentage": 92.0, "elapsed_time": "1:50:05", "remaining_time": "0:09:34", "throughput": 5471.25, "total_tokens": 36139120} {"current_steps": 59305, "total_steps": 64460, "loss": 0.1437, "lr": 1.9363181921017826e-07, "epoch": 18.40055848588272, "percentage": 92.0, "elapsed_time": "1:50:05", "remaining_time": "0:09:34", "throughput": 5471.34, "total_tokens": 36142800} {"current_steps": 59310, "total_steps": 64460, "loss": 0.189, "lr": 1.9325889172164714e-07, "epoch": 18.402109835556935, "percentage": 92.01, "elapsed_time": "1:50:06", "remaining_time": "0:09:33", "throughput": 5471.34, "total_tokens": 36145392} {"current_steps": 59315, "total_steps": 64460, "loss": 0.1215, "lr": 1.9288631662415958e-07, "epoch": 18.40366118523115, "percentage": 92.02, "elapsed_time": "1:50:06", "remaining_time": "0:09:33", "throughput": 5471.35, "total_tokens": 36148208} {"current_steps": 59320, "total_steps": 64460, "loss": 0.1574, "lr": 1.9251409394502983e-07, "epoch": 18.405212534905367, "percentage": 92.03, "elapsed_time": "1:50:07", "remaining_time": "0:09:32", "throughput": 5471.33, "total_tokens": 36150704} {"current_steps": 59325, "total_steps": 64460, "loss": 0.3086, "lr": 1.9214222371154613e-07, "epoch": 18.406763884579583, "percentage": 92.03, "elapsed_time": "1:50:07", "remaining_time": "0:09:31", "throughput": 5471.36, "total_tokens": 36153776} {"current_steps": 59330, "total_steps": 64460, "loss": 0.1191, "lr": 1.9177070595097047e-07, "epoch": 18.408315234253802, "percentage": 92.04, "elapsed_time": "1:50:08", "remaining_time": "0:09:31", "throughput": 5471.37, "total_tokens": 36156528} {"current_steps": 59335, "total_steps": 64460, "loss": 0.0965, "lr": 1.9139954069054113e-07, "epoch": 18.409866583928018, "percentage": 92.05, "elapsed_time": "1:50:08", "remaining_time": "0:09:30", "throughput": 5471.37, "total_tokens": 36159280} {"current_steps": 59340, "total_steps": 64460, "loss": 0.0891, "lr": 1.9102872795746685e-07, "epoch": 18.411417933602234, "percentage": 92.06, "elapsed_time": "1:50:09", "remaining_time": "0:09:30", "throughput": 5471.44, "total_tokens": 36162928} {"current_steps": 59345, "total_steps": 64460, "loss": 0.1257, "lr": 1.9065826777893425e-07, "epoch": 18.41296928327645, "percentage": 92.06, "elapsed_time": "1:50:09", "remaining_time": "0:09:29", "throughput": 5471.42, "total_tokens": 36165360} {"current_steps": 59350, "total_steps": 64460, "loss": 0.2173, "lr": 1.9028816018210106e-07, "epoch": 18.414520632950666, "percentage": 92.07, "elapsed_time": "1:50:10", "remaining_time": "0:09:29", "throughput": 5471.41, "total_tokens": 36168112} {"current_steps": 59355, "total_steps": 64460, "loss": 0.1214, "lr": 1.8991840519410166e-07, "epoch": 18.416071982624885, "percentage": 92.08, "elapsed_time": "1:50:10", "remaining_time": "0:09:28", "throughput": 5471.48, "total_tokens": 36171408} {"current_steps": 59360, "total_steps": 64460, "loss": 0.124, "lr": 1.8954900284204269e-07, "epoch": 18.4176233322991, "percentage": 92.09, "elapsed_time": "1:50:11", "remaining_time": "0:09:28", "throughput": 5471.52, "total_tokens": 36174608} {"current_steps": 59365, "total_steps": 64460, "loss": 0.1874, "lr": 1.891799531530064e-07, "epoch": 18.419174681973317, "percentage": 92.1, "elapsed_time": "1:50:11", "remaining_time": "0:09:27", "throughput": 5471.56, "total_tokens": 36177776} {"current_steps": 59370, "total_steps": 64460, "loss": 0.1883, "lr": 1.8881125615404783e-07, "epoch": 18.420726031647533, "percentage": 92.1, "elapsed_time": "1:50:12", "remaining_time": "0:09:26", "throughput": 5471.56, "total_tokens": 36180592} {"current_steps": 59375, "total_steps": 64460, "loss": 0.1578, "lr": 1.884429118721981e-07, "epoch": 18.42227738132175, "percentage": 92.11, "elapsed_time": "1:50:13", "remaining_time": "0:09:26", "throughput": 5471.64, "total_tokens": 36184976} {"current_steps": 59380, "total_steps": 64460, "loss": 0.1859, "lr": 1.8807492033445895e-07, "epoch": 18.423828730995968, "percentage": 92.12, "elapsed_time": "1:50:13", "remaining_time": "0:09:25", "throughput": 5471.63, "total_tokens": 36187504} {"current_steps": 59385, "total_steps": 64460, "loss": 0.1187, "lr": 1.8770728156781104e-07, "epoch": 18.425380080670184, "percentage": 92.13, "elapsed_time": "1:50:14", "remaining_time": "0:09:25", "throughput": 5471.63, "total_tokens": 36190384} {"current_steps": 59390, "total_steps": 64460, "loss": 0.1919, "lr": 1.8733999559920446e-07, "epoch": 18.4269314303444, "percentage": 92.13, "elapsed_time": "1:50:14", "remaining_time": "0:09:24", "throughput": 5471.64, "total_tokens": 36193104} {"current_steps": 59395, "total_steps": 64460, "loss": 0.1217, "lr": 1.8697306245556712e-07, "epoch": 18.428482780018616, "percentage": 92.14, "elapsed_time": "1:50:15", "remaining_time": "0:09:24", "throughput": 5471.63, "total_tokens": 36195632} {"current_steps": 59400, "total_steps": 64460, "loss": 0.1522, "lr": 1.8660648216379918e-07, "epoch": 18.43003412969283, "percentage": 92.15, "elapsed_time": "1:50:15", "remaining_time": "0:09:23", "throughput": 5471.57, "total_tokens": 36197936} {"current_steps": 59405, "total_steps": 64460, "loss": 0.1918, "lr": 1.8624025475077522e-07, "epoch": 18.43158547936705, "percentage": 92.16, "elapsed_time": "1:50:16", "remaining_time": "0:09:22", "throughput": 5471.52, "total_tokens": 36200176} {"current_steps": 59410, "total_steps": 64460, "loss": 0.1801, "lr": 1.8587438024334382e-07, "epoch": 18.433136829041267, "percentage": 92.17, "elapsed_time": "1:50:16", "remaining_time": "0:09:22", "throughput": 5471.56, "total_tokens": 36203344} {"current_steps": 59415, "total_steps": 64460, "loss": 0.1889, "lr": 1.855088586683279e-07, "epoch": 18.434688178715483, "percentage": 92.17, "elapsed_time": "1:50:17", "remaining_time": "0:09:21", "throughput": 5471.74, "total_tokens": 36209104} {"current_steps": 59420, "total_steps": 64460, "loss": 0.1474, "lr": 1.8514369005252554e-07, "epoch": 18.4362395283897, "percentage": 92.18, "elapsed_time": "1:50:18", "remaining_time": "0:09:21", "throughput": 5471.87, "total_tokens": 36213424} {"current_steps": 59425, "total_steps": 64460, "loss": 0.1145, "lr": 1.8477887442270638e-07, "epoch": 18.437790878063915, "percentage": 92.19, "elapsed_time": "1:50:18", "remaining_time": "0:09:20", "throughput": 5471.87, "total_tokens": 36216048} {"current_steps": 59430, "total_steps": 64460, "loss": 0.1223, "lr": 1.844144118056168e-07, "epoch": 18.43934222773813, "percentage": 92.2, "elapsed_time": "1:50:19", "remaining_time": "0:09:20", "throughput": 5471.92, "total_tokens": 36219344} {"current_steps": 59435, "total_steps": 64460, "loss": 0.1944, "lr": 1.8405030222797605e-07, "epoch": 18.44089357741235, "percentage": 92.2, "elapsed_time": "1:50:19", "remaining_time": "0:09:19", "throughput": 5471.85, "total_tokens": 36221456} {"current_steps": 59440, "total_steps": 64460, "loss": 0.1487, "lr": 1.8368654571647715e-07, "epoch": 18.442444927086566, "percentage": 92.21, "elapsed_time": "1:50:20", "remaining_time": "0:09:19", "throughput": 5471.84, "total_tokens": 36223952} {"current_steps": 59445, "total_steps": 64460, "loss": 0.0943, "lr": 1.8332314229778824e-07, "epoch": 18.44399627676078, "percentage": 92.22, "elapsed_time": "1:50:20", "remaining_time": "0:09:18", "throughput": 5471.85, "total_tokens": 36227312} {"current_steps": 59450, "total_steps": 64460, "loss": 0.0869, "lr": 1.8296009199855081e-07, "epoch": 18.445547626434998, "percentage": 92.23, "elapsed_time": "1:50:21", "remaining_time": "0:09:17", "throughput": 5471.85, "total_tokens": 36229872} {"current_steps": 59455, "total_steps": 64460, "loss": 0.1233, "lr": 1.8259739484538132e-07, "epoch": 18.447098976109213, "percentage": 92.24, "elapsed_time": "1:50:21", "remaining_time": "0:09:17", "throughput": 5471.87, "total_tokens": 36232624} {"current_steps": 59460, "total_steps": 64460, "loss": 0.0956, "lr": 1.8223505086486904e-07, "epoch": 18.448650325783433, "percentage": 92.24, "elapsed_time": "1:50:22", "remaining_time": "0:09:16", "throughput": 5471.87, "total_tokens": 36235152} {"current_steps": 59465, "total_steps": 64460, "loss": 0.2271, "lr": 1.8187306008357887e-07, "epoch": 18.45020167545765, "percentage": 92.25, "elapsed_time": "1:50:22", "remaining_time": "0:09:16", "throughput": 5471.87, "total_tokens": 36238160} {"current_steps": 59470, "total_steps": 64460, "loss": 0.1382, "lr": 1.8151142252804787e-07, "epoch": 18.451753025131865, "percentage": 92.26, "elapsed_time": "1:50:23", "remaining_time": "0:09:15", "throughput": 5471.91, "total_tokens": 36241232} {"current_steps": 59475, "total_steps": 64460, "loss": 0.1329, "lr": 1.811501382247899e-07, "epoch": 18.45330437480608, "percentage": 92.27, "elapsed_time": "1:50:23", "remaining_time": "0:09:15", "throughput": 5471.9, "total_tokens": 36243728} {"current_steps": 59480, "total_steps": 64460, "loss": 0.1826, "lr": 1.807892072002898e-07, "epoch": 18.454855724480296, "percentage": 92.27, "elapsed_time": "1:50:24", "remaining_time": "0:09:14", "throughput": 5471.92, "total_tokens": 36246832} {"current_steps": 59485, "total_steps": 64460, "loss": 0.1778, "lr": 1.8042862948100924e-07, "epoch": 18.456407074154516, "percentage": 92.28, "elapsed_time": "1:50:24", "remaining_time": "0:09:14", "throughput": 5472.04, "total_tokens": 36250896} {"current_steps": 59490, "total_steps": 64460, "loss": 0.2128, "lr": 1.8006840509338208e-07, "epoch": 18.45795842382873, "percentage": 92.29, "elapsed_time": "1:50:25", "remaining_time": "0:09:13", "throughput": 5472.04, "total_tokens": 36253424} {"current_steps": 59495, "total_steps": 64460, "loss": 0.1118, "lr": 1.7970853406381773e-07, "epoch": 18.459509773502948, "percentage": 92.3, "elapsed_time": "1:50:25", "remaining_time": "0:09:12", "throughput": 5472.02, "total_tokens": 36255888} {"current_steps": 59500, "total_steps": 64460, "loss": 0.0655, "lr": 1.7934901641869784e-07, "epoch": 18.461061123177164, "percentage": 92.31, "elapsed_time": "1:50:26", "remaining_time": "0:09:12", "throughput": 5472.17, "total_tokens": 36260528} {"current_steps": 59505, "total_steps": 64460, "loss": 0.2752, "lr": 1.7898985218438082e-07, "epoch": 18.46261247285138, "percentage": 92.31, "elapsed_time": "1:50:26", "remaining_time": "0:09:11", "throughput": 5472.2, "total_tokens": 36263632} {"current_steps": 59510, "total_steps": 64460, "loss": 0.2131, "lr": 1.7863104138719668e-07, "epoch": 18.4641638225256, "percentage": 92.32, "elapsed_time": "1:50:27", "remaining_time": "0:09:11", "throughput": 5472.32, "total_tokens": 36268336} {"current_steps": 59515, "total_steps": 64460, "loss": 0.1678, "lr": 1.782725840534505e-07, "epoch": 18.465715172199815, "percentage": 92.33, "elapsed_time": "1:50:28", "remaining_time": "0:09:10", "throughput": 5472.35, "total_tokens": 36271312} {"current_steps": 59520, "total_steps": 64460, "loss": 0.1798, "lr": 1.7791448020942237e-07, "epoch": 18.46726652187403, "percentage": 92.34, "elapsed_time": "1:50:28", "remaining_time": "0:09:10", "throughput": 5472.34, "total_tokens": 36273968} {"current_steps": 59525, "total_steps": 64460, "loss": 0.1027, "lr": 1.7755672988136407e-07, "epoch": 18.468817871548247, "percentage": 92.34, "elapsed_time": "1:50:29", "remaining_time": "0:09:09", "throughput": 5472.35, "total_tokens": 36276976} {"current_steps": 59530, "total_steps": 64460, "loss": 0.1569, "lr": 1.7719933309550462e-07, "epoch": 18.470369221222462, "percentage": 92.35, "elapsed_time": "1:50:29", "remaining_time": "0:09:09", "throughput": 5472.36, "total_tokens": 36279728} {"current_steps": 59535, "total_steps": 64460, "loss": 0.0718, "lr": 1.768422898780442e-07, "epoch": 18.471920570896682, "percentage": 92.36, "elapsed_time": "1:50:30", "remaining_time": "0:09:08", "throughput": 5472.46, "total_tokens": 36283984} {"current_steps": 59540, "total_steps": 64460, "loss": 0.1653, "lr": 1.7648560025515847e-07, "epoch": 18.473471920570898, "percentage": 92.37, "elapsed_time": "1:50:30", "remaining_time": "0:09:07", "throughput": 5472.5, "total_tokens": 36287184} {"current_steps": 59545, "total_steps": 64460, "loss": 0.188, "lr": 1.7612926425299715e-07, "epoch": 18.475023270245114, "percentage": 92.38, "elapsed_time": "1:50:31", "remaining_time": "0:09:07", "throughput": 5472.57, "total_tokens": 36290576} {"current_steps": 59550, "total_steps": 64460, "loss": 0.1208, "lr": 1.7577328189768484e-07, "epoch": 18.47657461991933, "percentage": 92.38, "elapsed_time": "1:50:32", "remaining_time": "0:09:06", "throughput": 5472.68, "total_tokens": 36294832} {"current_steps": 59555, "total_steps": 64460, "loss": 0.1228, "lr": 1.7541765321531734e-07, "epoch": 18.478125969593545, "percentage": 92.39, "elapsed_time": "1:50:32", "remaining_time": "0:09:06", "throughput": 5472.71, "total_tokens": 36297680} {"current_steps": 59560, "total_steps": 64460, "loss": 0.183, "lr": 1.750623782319677e-07, "epoch": 18.47967731926776, "percentage": 92.4, "elapsed_time": "1:50:32", "remaining_time": "0:09:05", "throughput": 5472.69, "total_tokens": 36300208} {"current_steps": 59565, "total_steps": 64460, "loss": 0.1787, "lr": 1.747074569736812e-07, "epoch": 18.48122866894198, "percentage": 92.41, "elapsed_time": "1:50:33", "remaining_time": "0:09:05", "throughput": 5472.68, "total_tokens": 36302896} {"current_steps": 59570, "total_steps": 64460, "loss": 0.1152, "lr": 1.7435288946647867e-07, "epoch": 18.482780018616197, "percentage": 92.41, "elapsed_time": "1:50:33", "remaining_time": "0:09:04", "throughput": 5472.69, "total_tokens": 36305744} {"current_steps": 59575, "total_steps": 64460, "loss": 0.1013, "lr": 1.7399867573635375e-07, "epoch": 18.484331368290412, "percentage": 92.42, "elapsed_time": "1:50:34", "remaining_time": "0:09:04", "throughput": 5472.61, "total_tokens": 36307760} {"current_steps": 59580, "total_steps": 64460, "loss": 0.1745, "lr": 1.736448158092735e-07, "epoch": 18.48588271796463, "percentage": 92.43, "elapsed_time": "1:50:35", "remaining_time": "0:09:03", "throughput": 5472.63, "total_tokens": 36310992} {"current_steps": 59585, "total_steps": 64460, "loss": 0.1572, "lr": 1.7329130971118156e-07, "epoch": 18.487434067638844, "percentage": 92.44, "elapsed_time": "1:50:35", "remaining_time": "0:09:02", "throughput": 5472.58, "total_tokens": 36313296} {"current_steps": 59590, "total_steps": 64460, "loss": 0.1339, "lr": 1.729381574679928e-07, "epoch": 18.488985417313064, "percentage": 92.44, "elapsed_time": "1:50:36", "remaining_time": "0:09:02", "throughput": 5472.55, "total_tokens": 36315920} {"current_steps": 59595, "total_steps": 64460, "loss": 0.1732, "lr": 1.725853591055987e-07, "epoch": 18.49053676698728, "percentage": 92.45, "elapsed_time": "1:50:36", "remaining_time": "0:09:01", "throughput": 5472.54, "total_tokens": 36318736} {"current_steps": 59600, "total_steps": 64460, "loss": 0.18, "lr": 1.7223291464986248e-07, "epoch": 18.492088116661495, "percentage": 92.46, "elapsed_time": "1:50:37", "remaining_time": "0:09:01", "throughput": 5472.52, "total_tokens": 36321360} {"current_steps": 59605, "total_steps": 64460, "loss": 0.1038, "lr": 1.7188082412662343e-07, "epoch": 18.49363946633571, "percentage": 92.47, "elapsed_time": "1:50:37", "remaining_time": "0:09:00", "throughput": 5472.54, "total_tokens": 36324112} {"current_steps": 59610, "total_steps": 64460, "loss": 0.1342, "lr": 1.715290875616926e-07, "epoch": 18.495190816009927, "percentage": 92.48, "elapsed_time": "1:50:38", "remaining_time": "0:09:00", "throughput": 5472.54, "total_tokens": 36326800} {"current_steps": 59615, "total_steps": 64460, "loss": 0.1574, "lr": 1.711777049808583e-07, "epoch": 18.496742165684147, "percentage": 92.48, "elapsed_time": "1:50:38", "remaining_time": "0:08:59", "throughput": 5472.6, "total_tokens": 36330000} {"current_steps": 59620, "total_steps": 64460, "loss": 0.1667, "lr": 1.7082667640987926e-07, "epoch": 18.498293515358363, "percentage": 92.49, "elapsed_time": "1:50:39", "remaining_time": "0:08:58", "throughput": 5472.66, "total_tokens": 36333168} {"current_steps": 59625, "total_steps": 64460, "loss": 0.1679, "lr": 1.7047600187449108e-07, "epoch": 18.49984486503258, "percentage": 92.5, "elapsed_time": "1:50:39", "remaining_time": "0:08:58", "throughput": 5472.76, "total_tokens": 36336720} {"current_steps": 59630, "total_steps": 64460, "loss": 0.2193, "lr": 1.701256814004021e-07, "epoch": 18.501396214706794, "percentage": 92.51, "elapsed_time": "1:50:40", "remaining_time": "0:08:57", "throughput": 5472.76, "total_tokens": 36339280} {"current_steps": 59635, "total_steps": 64460, "loss": 0.2256, "lr": 1.697757150132945e-07, "epoch": 18.50294756438101, "percentage": 92.51, "elapsed_time": "1:50:40", "remaining_time": "0:08:57", "throughput": 5472.83, "total_tokens": 36342544} {"current_steps": 59640, "total_steps": 64460, "loss": 0.1618, "lr": 1.694261027388261e-07, "epoch": 18.50449891405523, "percentage": 92.52, "elapsed_time": "1:50:41", "remaining_time": "0:08:56", "throughput": 5472.87, "total_tokens": 36345936} {"current_steps": 59645, "total_steps": 64460, "loss": 0.1503, "lr": 1.6907684460262642e-07, "epoch": 18.506050263729446, "percentage": 92.53, "elapsed_time": "1:50:41", "remaining_time": "0:08:56", "throughput": 5472.8, "total_tokens": 36348144} {"current_steps": 59650, "total_steps": 64460, "loss": 0.3058, "lr": 1.6872794063030106e-07, "epoch": 18.50760161340366, "percentage": 92.54, "elapsed_time": "1:50:42", "remaining_time": "0:08:55", "throughput": 5472.86, "total_tokens": 36351408} {"current_steps": 59655, "total_steps": 64460, "loss": 0.1393, "lr": 1.683793908474285e-07, "epoch": 18.509152963077877, "percentage": 92.55, "elapsed_time": "1:50:42", "remaining_time": "0:08:55", "throughput": 5472.88, "total_tokens": 36355088} {"current_steps": 59660, "total_steps": 64460, "loss": 0.1501, "lr": 1.6803119527956158e-07, "epoch": 18.510704312752093, "percentage": 92.55, "elapsed_time": "1:50:43", "remaining_time": "0:08:54", "throughput": 5472.88, "total_tokens": 36358128} {"current_steps": 59665, "total_steps": 64460, "loss": 0.2615, "lr": 1.6768335395222657e-07, "epoch": 18.512255662426313, "percentage": 92.56, "elapsed_time": "1:50:43", "remaining_time": "0:08:53", "throughput": 5472.85, "total_tokens": 36360624} {"current_steps": 59670, "total_steps": 64460, "loss": 0.1028, "lr": 1.6733586689092585e-07, "epoch": 18.51380701210053, "percentage": 92.57, "elapsed_time": "1:50:44", "remaining_time": "0:08:53", "throughput": 5472.83, "total_tokens": 36363184} {"current_steps": 59675, "total_steps": 64460, "loss": 0.1187, "lr": 1.6698873412113236e-07, "epoch": 18.515358361774744, "percentage": 92.58, "elapsed_time": "1:50:44", "remaining_time": "0:08:52", "throughput": 5472.79, "total_tokens": 36365872} {"current_steps": 59680, "total_steps": 64460, "loss": 0.1081, "lr": 1.6664195566829689e-07, "epoch": 18.51690971144896, "percentage": 92.58, "elapsed_time": "1:50:45", "remaining_time": "0:08:52", "throughput": 5472.84, "total_tokens": 36369168} {"current_steps": 59685, "total_steps": 64460, "loss": 0.1211, "lr": 1.6629553155784072e-07, "epoch": 18.518461061123176, "percentage": 92.59, "elapsed_time": "1:50:45", "remaining_time": "0:08:51", "throughput": 5472.9, "total_tokens": 36372272} {"current_steps": 59690, "total_steps": 64460, "loss": 0.1003, "lr": 1.659494618151619e-07, "epoch": 18.520012410797392, "percentage": 92.6, "elapsed_time": "1:50:46", "remaining_time": "0:08:51", "throughput": 5472.91, "total_tokens": 36375344} {"current_steps": 59695, "total_steps": 64460, "loss": 0.116, "lr": 1.656037464656318e-07, "epoch": 18.52156376047161, "percentage": 92.61, "elapsed_time": "1:50:46", "remaining_time": "0:08:50", "throughput": 5472.96, "total_tokens": 36378736} {"current_steps": 59700, "total_steps": 64460, "loss": 0.1195, "lr": 1.652583855345946e-07, "epoch": 18.523115110145827, "percentage": 92.62, "elapsed_time": "1:50:47", "remaining_time": "0:08:50", "throughput": 5472.94, "total_tokens": 36381232} {"current_steps": 59705, "total_steps": 64460, "loss": 0.1573, "lr": 1.6491337904737004e-07, "epoch": 18.524666459820043, "percentage": 92.62, "elapsed_time": "1:50:47", "remaining_time": "0:08:49", "throughput": 5472.9, "total_tokens": 36383536} {"current_steps": 59710, "total_steps": 64460, "loss": 0.1556, "lr": 1.645687270292501e-07, "epoch": 18.52621780949426, "percentage": 92.63, "elapsed_time": "1:50:48", "remaining_time": "0:08:48", "throughput": 5472.88, "total_tokens": 36386032} {"current_steps": 59715, "total_steps": 64460, "loss": 0.0701, "lr": 1.6422442950550344e-07, "epoch": 18.527769159168475, "percentage": 92.64, "elapsed_time": "1:50:48", "remaining_time": "0:08:48", "throughput": 5472.91, "total_tokens": 36388880} {"current_steps": 59720, "total_steps": 64460, "loss": 0.1308, "lr": 1.6388048650136933e-07, "epoch": 18.529320508842694, "percentage": 92.65, "elapsed_time": "1:50:49", "remaining_time": "0:08:47", "throughput": 5472.93, "total_tokens": 36391856} {"current_steps": 59725, "total_steps": 64460, "loss": 0.179, "lr": 1.635368980420643e-07, "epoch": 18.53087185851691, "percentage": 92.65, "elapsed_time": "1:50:49", "remaining_time": "0:08:47", "throughput": 5472.97, "total_tokens": 36394928} {"current_steps": 59730, "total_steps": 64460, "loss": 0.1821, "lr": 1.631936641527765e-07, "epoch": 18.532423208191126, "percentage": 92.66, "elapsed_time": "1:50:50", "remaining_time": "0:08:46", "throughput": 5473.01, "total_tokens": 36397904} {"current_steps": 59735, "total_steps": 64460, "loss": 0.1771, "lr": 1.6285078485867022e-07, "epoch": 18.533974557865342, "percentage": 92.67, "elapsed_time": "1:50:51", "remaining_time": "0:08:46", "throughput": 5472.97, "total_tokens": 36400784} {"current_steps": 59740, "total_steps": 64460, "loss": 0.1084, "lr": 1.6250826018488096e-07, "epoch": 18.535525907539558, "percentage": 92.68, "elapsed_time": "1:50:51", "remaining_time": "0:08:45", "throughput": 5472.96, "total_tokens": 36403600} {"current_steps": 59745, "total_steps": 64460, "loss": 0.0758, "lr": 1.6216609015652195e-07, "epoch": 18.537077257213777, "percentage": 92.69, "elapsed_time": "1:50:52", "remaining_time": "0:08:44", "throughput": 5472.96, "total_tokens": 36406288} {"current_steps": 59750, "total_steps": 64460, "loss": 0.1071, "lr": 1.618242747986759e-07, "epoch": 18.538628606887993, "percentage": 92.69, "elapsed_time": "1:50:52", "remaining_time": "0:08:44", "throughput": 5472.96, "total_tokens": 36408912} {"current_steps": 59755, "total_steps": 64460, "loss": 0.1825, "lr": 1.6148281413640278e-07, "epoch": 18.54017995656221, "percentage": 92.7, "elapsed_time": "1:50:53", "remaining_time": "0:08:43", "throughput": 5472.9, "total_tokens": 36411280} {"current_steps": 59760, "total_steps": 64460, "loss": 0.0945, "lr": 1.6114170819473695e-07, "epoch": 18.541731306236425, "percentage": 92.71, "elapsed_time": "1:50:53", "remaining_time": "0:08:43", "throughput": 5472.98, "total_tokens": 36415152} {"current_steps": 59765, "total_steps": 64460, "loss": 0.3391, "lr": 1.6080095699868404e-07, "epoch": 18.54328265591064, "percentage": 92.72, "elapsed_time": "1:50:54", "remaining_time": "0:08:42", "throughput": 5472.94, "total_tokens": 36417712} {"current_steps": 59770, "total_steps": 64460, "loss": 0.2037, "lr": 1.6046056057322623e-07, "epoch": 18.54483400558486, "percentage": 92.72, "elapsed_time": "1:50:54", "remaining_time": "0:08:42", "throughput": 5472.94, "total_tokens": 36420688} {"current_steps": 59775, "total_steps": 64460, "loss": 0.1527, "lr": 1.601205189433175e-07, "epoch": 18.546385355259076, "percentage": 92.73, "elapsed_time": "1:50:55", "remaining_time": "0:08:41", "throughput": 5473.01, "total_tokens": 36424336} {"current_steps": 59780, "total_steps": 64460, "loss": 0.1607, "lr": 1.5978083213388784e-07, "epoch": 18.547936704933292, "percentage": 92.74, "elapsed_time": "1:50:55", "remaining_time": "0:08:41", "throughput": 5472.99, "total_tokens": 36426800} {"current_steps": 59785, "total_steps": 64460, "loss": 0.2318, "lr": 1.5944150016983907e-07, "epoch": 18.549488054607508, "percentage": 92.75, "elapsed_time": "1:50:56", "remaining_time": "0:08:40", "throughput": 5473.04, "total_tokens": 36430448} {"current_steps": 59790, "total_steps": 64460, "loss": 0.2383, "lr": 1.5910252307605012e-07, "epoch": 18.551039404281724, "percentage": 92.76, "elapsed_time": "1:50:56", "remaining_time": "0:08:39", "throughput": 5473.07, "total_tokens": 36433200} {"current_steps": 59795, "total_steps": 64460, "loss": 0.1599, "lr": 1.5876390087737058e-07, "epoch": 18.552590753955943, "percentage": 92.76, "elapsed_time": "1:50:57", "remaining_time": "0:08:39", "throughput": 5473.07, "total_tokens": 36436048} {"current_steps": 59800, "total_steps": 64460, "loss": 0.1529, "lr": 1.5842563359862617e-07, "epoch": 18.55414210363016, "percentage": 92.77, "elapsed_time": "1:50:57", "remaining_time": "0:08:38", "throughput": 5473.07, "total_tokens": 36438928} {"current_steps": 59805, "total_steps": 64460, "loss": 0.1383, "lr": 1.5808772126461537e-07, "epoch": 18.555693453304375, "percentage": 92.78, "elapsed_time": "1:50:58", "remaining_time": "0:08:38", "throughput": 5473.05, "total_tokens": 36441520} {"current_steps": 59810, "total_steps": 64460, "loss": 0.1869, "lr": 1.5775016390011166e-07, "epoch": 18.55724480297859, "percentage": 92.79, "elapsed_time": "1:50:58", "remaining_time": "0:08:37", "throughput": 5473.0, "total_tokens": 36443728} {"current_steps": 59815, "total_steps": 64460, "loss": 0.2423, "lr": 1.5741296152986196e-07, "epoch": 18.558796152652807, "percentage": 92.79, "elapsed_time": "1:50:59", "remaining_time": "0:08:37", "throughput": 5472.96, "total_tokens": 36446032} {"current_steps": 59820, "total_steps": 64460, "loss": 0.0895, "lr": 1.5707611417858704e-07, "epoch": 18.560347502327023, "percentage": 92.8, "elapsed_time": "1:50:59", "remaining_time": "0:08:36", "throughput": 5473.0, "total_tokens": 36449072} {"current_steps": 59825, "total_steps": 64460, "loss": 0.1126, "lr": 1.5673962187098102e-07, "epoch": 18.561898852001242, "percentage": 92.81, "elapsed_time": "1:51:00", "remaining_time": "0:08:36", "throughput": 5473.02, "total_tokens": 36451952} {"current_steps": 59830, "total_steps": 64460, "loss": 0.1152, "lr": 1.5640348463171416e-07, "epoch": 18.563450201675458, "percentage": 92.82, "elapsed_time": "1:51:00", "remaining_time": "0:08:35", "throughput": 5473.04, "total_tokens": 36454704} {"current_steps": 59835, "total_steps": 64460, "loss": 0.2047, "lr": 1.560677024854279e-07, "epoch": 18.565001551349674, "percentage": 92.83, "elapsed_time": "1:51:01", "remaining_time": "0:08:34", "throughput": 5473.05, "total_tokens": 36457456} {"current_steps": 59840, "total_steps": 64460, "loss": 0.1251, "lr": 1.557322754567403e-07, "epoch": 18.56655290102389, "percentage": 92.83, "elapsed_time": "1:51:01", "remaining_time": "0:08:34", "throughput": 5473.12, "total_tokens": 36460848} {"current_steps": 59845, "total_steps": 64460, "loss": 0.2089, "lr": 1.5539720357024168e-07, "epoch": 18.568104250698106, "percentage": 92.84, "elapsed_time": "1:51:02", "remaining_time": "0:08:33", "throughput": 5473.07, "total_tokens": 36463088} {"current_steps": 59850, "total_steps": 64460, "loss": 0.1341, "lr": 1.5506248685049628e-07, "epoch": 18.569655600372325, "percentage": 92.85, "elapsed_time": "1:51:02", "remaining_time": "0:08:33", "throughput": 5473.12, "total_tokens": 36466192} {"current_steps": 59855, "total_steps": 64460, "loss": 0.129, "lr": 1.5472812532204395e-07, "epoch": 18.57120695004654, "percentage": 92.86, "elapsed_time": "1:51:03", "remaining_time": "0:08:32", "throughput": 5473.13, "total_tokens": 36468880} {"current_steps": 59860, "total_steps": 64460, "loss": 0.2279, "lr": 1.5439411900939617e-07, "epoch": 18.572758299720757, "percentage": 92.86, "elapsed_time": "1:51:03", "remaining_time": "0:08:32", "throughput": 5473.19, "total_tokens": 36472368} {"current_steps": 59865, "total_steps": 64460, "loss": 0.0772, "lr": 1.5406046793704054e-07, "epoch": 18.574309649394973, "percentage": 92.87, "elapsed_time": "1:51:04", "remaining_time": "0:08:31", "throughput": 5473.18, "total_tokens": 36474896} {"current_steps": 59870, "total_steps": 64460, "loss": 0.132, "lr": 1.5372717212943645e-07, "epoch": 18.57586099906919, "percentage": 92.88, "elapsed_time": "1:51:04", "remaining_time": "0:08:30", "throughput": 5473.2, "total_tokens": 36477808} {"current_steps": 59875, "total_steps": 64460, "loss": 0.096, "lr": 1.5339423161101986e-07, "epoch": 18.577412348743408, "percentage": 92.89, "elapsed_time": "1:51:05", "remaining_time": "0:08:30", "throughput": 5473.26, "total_tokens": 36481296} {"current_steps": 59880, "total_steps": 64460, "loss": 0.1275, "lr": 1.5306164640619736e-07, "epoch": 18.578963698417624, "percentage": 92.89, "elapsed_time": "1:51:05", "remaining_time": "0:08:29", "throughput": 5473.23, "total_tokens": 36483600} {"current_steps": 59885, "total_steps": 64460, "loss": 0.1474, "lr": 1.5272941653935336e-07, "epoch": 18.58051504809184, "percentage": 92.9, "elapsed_time": "1:51:06", "remaining_time": "0:08:29", "throughput": 5473.34, "total_tokens": 36487472} {"current_steps": 59890, "total_steps": 64460, "loss": 0.1397, "lr": 1.5239754203484335e-07, "epoch": 18.582066397766056, "percentage": 92.91, "elapsed_time": "1:51:06", "remaining_time": "0:08:28", "throughput": 5473.32, "total_tokens": 36490064} {"current_steps": 59895, "total_steps": 64460, "loss": 0.1225, "lr": 1.5206602291699735e-07, "epoch": 18.58361774744027, "percentage": 92.92, "elapsed_time": "1:51:07", "remaining_time": "0:08:28", "throughput": 5473.37, "total_tokens": 36493040} {"current_steps": 59900, "total_steps": 64460, "loss": 0.131, "lr": 1.5173485921012033e-07, "epoch": 18.58516909711449, "percentage": 92.93, "elapsed_time": "1:51:08", "remaining_time": "0:08:27", "throughput": 5473.46, "total_tokens": 36497008} {"current_steps": 59905, "total_steps": 64460, "loss": 0.1106, "lr": 1.5140405093848952e-07, "epoch": 18.586720446788707, "percentage": 92.93, "elapsed_time": "1:51:08", "remaining_time": "0:08:27", "throughput": 5473.47, "total_tokens": 36499760} {"current_steps": 59910, "total_steps": 64460, "loss": 0.1205, "lr": 1.510735981263589e-07, "epoch": 18.588271796462923, "percentage": 92.94, "elapsed_time": "1:51:08", "remaining_time": "0:08:26", "throughput": 5473.52, "total_tokens": 36502832} {"current_steps": 59915, "total_steps": 64460, "loss": 0.1276, "lr": 1.5074350079795242e-07, "epoch": 18.58982314613714, "percentage": 92.95, "elapsed_time": "1:51:09", "remaining_time": "0:08:25", "throughput": 5473.48, "total_tokens": 36505360} {"current_steps": 59920, "total_steps": 64460, "loss": 0.1381, "lr": 1.504137589774718e-07, "epoch": 18.591374495811355, "percentage": 92.96, "elapsed_time": "1:51:10", "remaining_time": "0:08:25", "throughput": 5473.48, "total_tokens": 36508112} {"current_steps": 59925, "total_steps": 64460, "loss": 0.1059, "lr": 1.5008437268908992e-07, "epoch": 18.592925845485574, "percentage": 92.96, "elapsed_time": "1:51:10", "remaining_time": "0:08:24", "throughput": 5473.47, "total_tokens": 36510768} {"current_steps": 59930, "total_steps": 64460, "loss": 0.1141, "lr": 1.497553419569553e-07, "epoch": 18.59447719515979, "percentage": 92.97, "elapsed_time": "1:51:11", "remaining_time": "0:08:24", "throughput": 5473.42, "total_tokens": 36513360} {"current_steps": 59935, "total_steps": 64460, "loss": 0.1198, "lr": 1.4942666680518913e-07, "epoch": 18.596028544834006, "percentage": 92.98, "elapsed_time": "1:51:11", "remaining_time": "0:08:23", "throughput": 5473.28, "total_tokens": 36515664} {"current_steps": 59940, "total_steps": 64460, "loss": 0.099, "lr": 1.490983472578883e-07, "epoch": 18.597579894508222, "percentage": 92.99, "elapsed_time": "1:51:12", "remaining_time": "0:08:23", "throughput": 5473.23, "total_tokens": 36518032} {"current_steps": 59945, "total_steps": 64460, "loss": 0.1063, "lr": 1.4877038333912186e-07, "epoch": 18.599131244182438, "percentage": 93.0, "elapsed_time": "1:51:12", "remaining_time": "0:08:22", "throughput": 5473.25, "total_tokens": 36520976} {"current_steps": 59950, "total_steps": 64460, "loss": 0.2101, "lr": 1.4844277507293335e-07, "epoch": 18.600682593856654, "percentage": 93.0, "elapsed_time": "1:51:13", "remaining_time": "0:08:22", "throughput": 5473.19, "total_tokens": 36523280} {"current_steps": 59955, "total_steps": 64460, "loss": 0.092, "lr": 1.4811552248334028e-07, "epoch": 18.602233943530873, "percentage": 93.01, "elapsed_time": "1:51:13", "remaining_time": "0:08:21", "throughput": 5473.22, "total_tokens": 36526032} {"current_steps": 59960, "total_steps": 64460, "loss": 0.2402, "lr": 1.4778862559433395e-07, "epoch": 18.60378529320509, "percentage": 93.02, "elapsed_time": "1:51:14", "remaining_time": "0:08:20", "throughput": 5473.23, "total_tokens": 36529040} {"current_steps": 59965, "total_steps": 64460, "loss": 0.1303, "lr": 1.4746208442988075e-07, "epoch": 18.605336642879305, "percentage": 93.03, "elapsed_time": "1:51:14", "remaining_time": "0:08:20", "throughput": 5473.23, "total_tokens": 36531920} {"current_steps": 59970, "total_steps": 64460, "loss": 0.2096, "lr": 1.4713589901391932e-07, "epoch": 18.60688799255352, "percentage": 93.03, "elapsed_time": "1:51:15", "remaining_time": "0:08:19", "throughput": 5473.26, "total_tokens": 36535728} {"current_steps": 59975, "total_steps": 64460, "loss": 0.2301, "lr": 1.468100693703628e-07, "epoch": 18.608439342227737, "percentage": 93.04, "elapsed_time": "1:51:15", "remaining_time": "0:08:19", "throughput": 5473.22, "total_tokens": 36538000} {"current_steps": 59980, "total_steps": 64460, "loss": 0.2598, "lr": 1.464845955230987e-07, "epoch": 18.609990691901956, "percentage": 93.05, "elapsed_time": "1:51:16", "remaining_time": "0:08:18", "throughput": 5473.21, "total_tokens": 36540688} {"current_steps": 59985, "total_steps": 64460, "loss": 0.1722, "lr": 1.4615947749598847e-07, "epoch": 18.611542041576172, "percentage": 93.06, "elapsed_time": "1:51:16", "remaining_time": "0:08:18", "throughput": 5473.28, "total_tokens": 36544080} {"current_steps": 59990, "total_steps": 64460, "loss": 0.0907, "lr": 1.4583471531286587e-07, "epoch": 18.613093391250388, "percentage": 93.07, "elapsed_time": "1:51:17", "remaining_time": "0:08:17", "throughput": 5473.34, "total_tokens": 36547152} {"current_steps": 59995, "total_steps": 64460, "loss": 0.1575, "lr": 1.455103089975407e-07, "epoch": 18.614644740924604, "percentage": 93.07, "elapsed_time": "1:51:17", "remaining_time": "0:08:16", "throughput": 5473.32, "total_tokens": 36549680} {"current_steps": 60000, "total_steps": 64460, "loss": 0.1138, "lr": 1.4518625857379565e-07, "epoch": 18.61619609059882, "percentage": 93.08, "elapsed_time": "1:51:18", "remaining_time": "0:08:16", "throughput": 5473.23, "total_tokens": 36551888} {"current_steps": 60005, "total_steps": 64460, "loss": 0.136, "lr": 1.448625640653878e-07, "epoch": 18.61774744027304, "percentage": 93.09, "elapsed_time": "1:51:18", "remaining_time": "0:08:15", "throughput": 5473.25, "total_tokens": 36554704} {"current_steps": 60010, "total_steps": 64460, "loss": 0.1339, "lr": 1.4453922549604705e-07, "epoch": 18.619298789947255, "percentage": 93.1, "elapsed_time": "1:51:19", "remaining_time": "0:08:15", "throughput": 5473.31, "total_tokens": 36557904} {"current_steps": 60015, "total_steps": 64460, "loss": 0.2331, "lr": 1.4421624288947777e-07, "epoch": 18.62085013962147, "percentage": 93.1, "elapsed_time": "1:51:19", "remaining_time": "0:08:14", "throughput": 5473.28, "total_tokens": 36560336} {"current_steps": 60020, "total_steps": 64460, "loss": 0.12, "lr": 1.4389361626935993e-07, "epoch": 18.622401489295687, "percentage": 93.11, "elapsed_time": "1:51:20", "remaining_time": "0:08:14", "throughput": 5473.32, "total_tokens": 36563216} {"current_steps": 60025, "total_steps": 64460, "loss": 0.086, "lr": 1.435713456593446e-07, "epoch": 18.623952838969903, "percentage": 93.12, "elapsed_time": "1:51:20", "remaining_time": "0:08:13", "throughput": 5473.33, "total_tokens": 36566064} {"current_steps": 60030, "total_steps": 64460, "loss": 0.144, "lr": 1.4324943108305845e-07, "epoch": 18.625504188644122, "percentage": 93.13, "elapsed_time": "1:51:21", "remaining_time": "0:08:13", "throughput": 5473.36, "total_tokens": 36569296} {"current_steps": 60035, "total_steps": 64460, "loss": 0.0668, "lr": 1.4292787256410145e-07, "epoch": 18.627055538318338, "percentage": 93.14, "elapsed_time": "1:51:21", "remaining_time": "0:08:12", "throughput": 5473.31, "total_tokens": 36571600} {"current_steps": 60040, "total_steps": 64460, "loss": 0.1602, "lr": 1.426066701260481e-07, "epoch": 18.628606887992554, "percentage": 93.14, "elapsed_time": "1:51:22", "remaining_time": "0:08:11", "throughput": 5473.33, "total_tokens": 36575024} {"current_steps": 60045, "total_steps": 64460, "loss": 0.0831, "lr": 1.4228582379244514e-07, "epoch": 18.63015823766677, "percentage": 93.15, "elapsed_time": "1:51:22", "remaining_time": "0:08:11", "throughput": 5473.27, "total_tokens": 36577456} {"current_steps": 60050, "total_steps": 64460, "loss": 0.1818, "lr": 1.4196533358681596e-07, "epoch": 18.631709587340985, "percentage": 93.16, "elapsed_time": "1:51:23", "remaining_time": "0:08:10", "throughput": 5473.32, "total_tokens": 36580656} {"current_steps": 60055, "total_steps": 64460, "loss": 0.1314, "lr": 1.416451995326551e-07, "epoch": 18.633260937015205, "percentage": 93.17, "elapsed_time": "1:51:23", "remaining_time": "0:08:10", "throughput": 5473.34, "total_tokens": 36583504} {"current_steps": 60060, "total_steps": 64460, "loss": 0.1415, "lr": 1.413254216534332e-07, "epoch": 18.63481228668942, "percentage": 93.17, "elapsed_time": "1:51:24", "remaining_time": "0:08:09", "throughput": 5473.35, "total_tokens": 36586288} {"current_steps": 60065, "total_steps": 64460, "loss": 0.175, "lr": 1.4100599997259267e-07, "epoch": 18.636363636363637, "percentage": 93.18, "elapsed_time": "1:51:24", "remaining_time": "0:08:09", "throughput": 5473.35, "total_tokens": 36589008} {"current_steps": 60070, "total_steps": 64460, "loss": 0.1707, "lr": 1.4068693451355197e-07, "epoch": 18.637914986037853, "percentage": 93.19, "elapsed_time": "1:51:25", "remaining_time": "0:08:08", "throughput": 5473.3, "total_tokens": 36591344} {"current_steps": 60075, "total_steps": 64460, "loss": 0.1923, "lr": 1.403682252997013e-07, "epoch": 18.63946633571207, "percentage": 93.2, "elapsed_time": "1:51:25", "remaining_time": "0:08:08", "throughput": 5473.32, "total_tokens": 36594064} {"current_steps": 60080, "total_steps": 64460, "loss": 0.1268, "lr": 1.4004987235440637e-07, "epoch": 18.641017685386288, "percentage": 93.21, "elapsed_time": "1:51:26", "remaining_time": "0:08:07", "throughput": 5473.36, "total_tokens": 36597360} {"current_steps": 60085, "total_steps": 64460, "loss": 0.1713, "lr": 1.3973187570100687e-07, "epoch": 18.642569035060504, "percentage": 93.21, "elapsed_time": "1:51:26", "remaining_time": "0:08:06", "throughput": 5473.41, "total_tokens": 36600432} {"current_steps": 60090, "total_steps": 64460, "loss": 0.1452, "lr": 1.394142353628142e-07, "epoch": 18.64412038473472, "percentage": 93.22, "elapsed_time": "1:51:27", "remaining_time": "0:08:06", "throughput": 5473.38, "total_tokens": 36603152} {"current_steps": 60095, "total_steps": 64460, "loss": 0.1715, "lr": 1.3909695136311686e-07, "epoch": 18.645671734408936, "percentage": 93.23, "elapsed_time": "1:51:28", "remaining_time": "0:08:05", "throughput": 5473.49, "total_tokens": 36607024} {"current_steps": 60100, "total_steps": 64460, "loss": 0.2069, "lr": 1.3878002372517408e-07, "epoch": 18.64722308408315, "percentage": 93.24, "elapsed_time": "1:51:28", "remaining_time": "0:08:05", "throughput": 5473.47, "total_tokens": 36609712} {"current_steps": 60105, "total_steps": 64460, "loss": 0.2857, "lr": 1.3846345247222115e-07, "epoch": 18.648774433757367, "percentage": 93.24, "elapsed_time": "1:51:29", "remaining_time": "0:08:04", "throughput": 5473.55, "total_tokens": 36613552} {"current_steps": 60110, "total_steps": 64460, "loss": 0.1659, "lr": 1.381472376274662e-07, "epoch": 18.650325783431587, "percentage": 93.25, "elapsed_time": "1:51:29", "remaining_time": "0:08:04", "throughput": 5473.59, "total_tokens": 36616656} {"current_steps": 60115, "total_steps": 64460, "loss": 0.3452, "lr": 1.378313792140923e-07, "epoch": 18.651877133105803, "percentage": 93.26, "elapsed_time": "1:51:30", "remaining_time": "0:08:03", "throughput": 5473.59, "total_tokens": 36619280} {"current_steps": 60120, "total_steps": 64460, "loss": 0.2006, "lr": 1.3751587725525428e-07, "epoch": 18.65342848278002, "percentage": 93.27, "elapsed_time": "1:51:30", "remaining_time": "0:08:02", "throughput": 5473.53, "total_tokens": 36621584} {"current_steps": 60125, "total_steps": 64460, "loss": 0.1388, "lr": 1.3720073177408365e-07, "epoch": 18.654979832454234, "percentage": 93.27, "elapsed_time": "1:51:31", "remaining_time": "0:08:02", "throughput": 5473.49, "total_tokens": 36623888} {"current_steps": 60130, "total_steps": 64460, "loss": 0.1195, "lr": 1.368859427936825e-07, "epoch": 18.65653118212845, "percentage": 93.28, "elapsed_time": "1:51:31", "remaining_time": "0:08:01", "throughput": 5473.62, "total_tokens": 36628208} {"current_steps": 60135, "total_steps": 64460, "loss": 0.0763, "lr": 1.365715103371301e-07, "epoch": 18.65808253180267, "percentage": 93.29, "elapsed_time": "1:51:32", "remaining_time": "0:08:01", "throughput": 5473.69, "total_tokens": 36631632} {"current_steps": 60140, "total_steps": 64460, "loss": 0.1487, "lr": 1.3625743442747809e-07, "epoch": 18.659633881476886, "percentage": 93.3, "elapsed_time": "1:51:32", "remaining_time": "0:08:00", "throughput": 5473.62, "total_tokens": 36633744} {"current_steps": 60145, "total_steps": 64460, "loss": 0.174, "lr": 1.3594371508775072e-07, "epoch": 18.6611852311511, "percentage": 93.31, "elapsed_time": "1:51:33", "remaining_time": "0:08:00", "throughput": 5473.64, "total_tokens": 36636656} {"current_steps": 60150, "total_steps": 64460, "loss": 0.2223, "lr": 1.3563035234094856e-07, "epoch": 18.662736580825317, "percentage": 93.31, "elapsed_time": "1:51:33", "remaining_time": "0:07:59", "throughput": 5473.67, "total_tokens": 36640016} {"current_steps": 60155, "total_steps": 64460, "loss": 0.1152, "lr": 1.3531734621004432e-07, "epoch": 18.664287930499533, "percentage": 93.32, "elapsed_time": "1:51:34", "remaining_time": "0:07:59", "throughput": 5473.64, "total_tokens": 36642960} {"current_steps": 60160, "total_steps": 64460, "loss": 0.1706, "lr": 1.3500469671798522e-07, "epoch": 18.665839280173753, "percentage": 93.33, "elapsed_time": "1:51:34", "remaining_time": "0:07:58", "throughput": 5473.73, "total_tokens": 36646480} {"current_steps": 60165, "total_steps": 64460, "loss": 0.1927, "lr": 1.3469240388769122e-07, "epoch": 18.66739062984797, "percentage": 93.34, "elapsed_time": "1:51:35", "remaining_time": "0:07:57", "throughput": 5473.72, "total_tokens": 36649200} {"current_steps": 60170, "total_steps": 64460, "loss": 0.1631, "lr": 1.3438046774205903e-07, "epoch": 18.668941979522184, "percentage": 93.34, "elapsed_time": "1:51:36", "remaining_time": "0:07:57", "throughput": 5473.64, "total_tokens": 36651568} {"current_steps": 60175, "total_steps": 64460, "loss": 0.1126, "lr": 1.340688883039548e-07, "epoch": 18.6704933291964, "percentage": 93.35, "elapsed_time": "1:51:36", "remaining_time": "0:07:56", "throughput": 5473.6, "total_tokens": 36654064} {"current_steps": 60180, "total_steps": 64460, "loss": 0.1593, "lr": 1.337576655962236e-07, "epoch": 18.672044678870616, "percentage": 93.36, "elapsed_time": "1:51:36", "remaining_time": "0:07:56", "throughput": 5473.57, "total_tokens": 36656464} {"current_steps": 60185, "total_steps": 64460, "loss": 0.173, "lr": 1.334467996416794e-07, "epoch": 18.673596028544836, "percentage": 93.37, "elapsed_time": "1:51:37", "remaining_time": "0:07:55", "throughput": 5473.61, "total_tokens": 36659664} {"current_steps": 60190, "total_steps": 64460, "loss": 0.3027, "lr": 1.331362904631145e-07, "epoch": 18.67514737821905, "percentage": 93.38, "elapsed_time": "1:51:38", "remaining_time": "0:07:55", "throughput": 5473.55, "total_tokens": 36661936} {"current_steps": 60195, "total_steps": 64460, "loss": 0.1319, "lr": 1.328261380832907e-07, "epoch": 18.676698727893267, "percentage": 93.38, "elapsed_time": "1:51:38", "remaining_time": "0:07:54", "throughput": 5473.53, "total_tokens": 36664848} {"current_steps": 60200, "total_steps": 64460, "loss": 0.1983, "lr": 1.3251634252494704e-07, "epoch": 18.678250077567483, "percentage": 93.39, "elapsed_time": "1:51:39", "remaining_time": "0:07:54", "throughput": 5473.58, "total_tokens": 36667760} {"current_steps": 60205, "total_steps": 64460, "loss": 0.1565, "lr": 1.3220690381079593e-07, "epoch": 18.6798014272417, "percentage": 93.4, "elapsed_time": "1:51:39", "remaining_time": "0:07:53", "throughput": 5473.59, "total_tokens": 36670416} {"current_steps": 60210, "total_steps": 64460, "loss": 0.1461, "lr": 1.3189782196352086e-07, "epoch": 18.681352776915915, "percentage": 93.41, "elapsed_time": "1:51:40", "remaining_time": "0:07:52", "throughput": 5473.63, "total_tokens": 36673424} {"current_steps": 60215, "total_steps": 64460, "loss": 0.1171, "lr": 1.315890970057837e-07, "epoch": 18.682904126590135, "percentage": 93.41, "elapsed_time": "1:51:40", "remaining_time": "0:07:52", "throughput": 5473.64, "total_tokens": 36676304} {"current_steps": 60220, "total_steps": 64460, "loss": 0.1183, "lr": 1.3128072896021525e-07, "epoch": 18.68445547626435, "percentage": 93.42, "elapsed_time": "1:51:40", "remaining_time": "0:07:51", "throughput": 5473.58, "total_tokens": 36678448} {"current_steps": 60225, "total_steps": 64460, "loss": 0.1424, "lr": 1.3097271784942467e-07, "epoch": 18.686006825938566, "percentage": 93.43, "elapsed_time": "1:51:41", "remaining_time": "0:07:51", "throughput": 5473.55, "total_tokens": 36680784} {"current_steps": 60230, "total_steps": 64460, "loss": 0.1359, "lr": 1.3066506369599107e-07, "epoch": 18.687558175612782, "percentage": 93.44, "elapsed_time": "1:51:42", "remaining_time": "0:07:50", "throughput": 5473.73, "total_tokens": 36686672} {"current_steps": 60235, "total_steps": 64460, "loss": 0.137, "lr": 1.3035776652247034e-07, "epoch": 18.689109525286998, "percentage": 93.45, "elapsed_time": "1:51:42", "remaining_time": "0:07:50", "throughput": 5473.73, "total_tokens": 36689456} {"current_steps": 60240, "total_steps": 64460, "loss": 0.2537, "lr": 1.3005082635138999e-07, "epoch": 18.690660874961218, "percentage": 93.45, "elapsed_time": "1:51:43", "remaining_time": "0:07:49", "throughput": 5473.63, "total_tokens": 36691696} {"current_steps": 60245, "total_steps": 64460, "loss": 0.1297, "lr": 1.2974424320525314e-07, "epoch": 18.692212224635433, "percentage": 93.46, "elapsed_time": "1:51:43", "remaining_time": "0:07:49", "throughput": 5473.57, "total_tokens": 36694192} {"current_steps": 60250, "total_steps": 64460, "loss": 0.1832, "lr": 1.2943801710653515e-07, "epoch": 18.69376357430965, "percentage": 93.47, "elapsed_time": "1:51:44", "remaining_time": "0:07:48", "throughput": 5473.6, "total_tokens": 36697264} {"current_steps": 60255, "total_steps": 64460, "loss": 0.2774, "lr": 1.2913214807768693e-07, "epoch": 18.695314923983865, "percentage": 93.48, "elapsed_time": "1:51:44", "remaining_time": "0:07:47", "throughput": 5473.61, "total_tokens": 36699952} {"current_steps": 60260, "total_steps": 64460, "loss": 0.1611, "lr": 1.2882663614113278e-07, "epoch": 18.69686627365808, "percentage": 93.48, "elapsed_time": "1:51:45", "remaining_time": "0:07:47", "throughput": 5473.67, "total_tokens": 36703280} {"current_steps": 60265, "total_steps": 64460, "loss": 0.1622, "lr": 1.2852148131926868e-07, "epoch": 18.6984176233323, "percentage": 93.49, "elapsed_time": "1:51:45", "remaining_time": "0:07:46", "throughput": 5473.69, "total_tokens": 36706448} {"current_steps": 60270, "total_steps": 64460, "loss": 0.1234, "lr": 1.2821668363446725e-07, "epoch": 18.699968973006516, "percentage": 93.5, "elapsed_time": "1:51:46", "remaining_time": "0:07:46", "throughput": 5473.76, "total_tokens": 36710096} {"current_steps": 60275, "total_steps": 64460, "loss": 0.0928, "lr": 1.279122431090729e-07, "epoch": 18.701520322680732, "percentage": 93.51, "elapsed_time": "1:51:47", "remaining_time": "0:07:45", "throughput": 5473.72, "total_tokens": 36712528} {"current_steps": 60280, "total_steps": 64460, "loss": 0.2128, "lr": 1.2760815976540608e-07, "epoch": 18.703071672354948, "percentage": 93.52, "elapsed_time": "1:51:47", "remaining_time": "0:07:45", "throughput": 5473.72, "total_tokens": 36715248} {"current_steps": 60285, "total_steps": 64460, "loss": 0.1435, "lr": 1.273044336257584e-07, "epoch": 18.704623022029164, "percentage": 93.52, "elapsed_time": "1:51:48", "remaining_time": "0:07:44", "throughput": 5473.67, "total_tokens": 36717456} {"current_steps": 60290, "total_steps": 64460, "loss": 0.3027, "lr": 1.270010647123976e-07, "epoch": 18.706174371703383, "percentage": 93.53, "elapsed_time": "1:51:48", "remaining_time": "0:07:43", "throughput": 5473.58, "total_tokens": 36719632} {"current_steps": 60295, "total_steps": 64460, "loss": 0.1472, "lr": 1.2669805304756312e-07, "epoch": 18.7077257213776, "percentage": 93.54, "elapsed_time": "1:51:49", "remaining_time": "0:07:43", "throughput": 5473.67, "total_tokens": 36723632} {"current_steps": 60300, "total_steps": 64460, "loss": 0.1211, "lr": 1.2639539865346996e-07, "epoch": 18.709277071051815, "percentage": 93.55, "elapsed_time": "1:51:49", "remaining_time": "0:07:42", "throughput": 5473.79, "total_tokens": 36728080} {"current_steps": 60305, "total_steps": 64460, "loss": 0.1797, "lr": 1.2609310155230647e-07, "epoch": 18.71082842072603, "percentage": 93.55, "elapsed_time": "1:51:50", "remaining_time": "0:07:42", "throughput": 5473.76, "total_tokens": 36730576} {"current_steps": 60310, "total_steps": 64460, "loss": 0.0966, "lr": 1.2579116176623441e-07, "epoch": 18.712379770400247, "percentage": 93.56, "elapsed_time": "1:51:50", "remaining_time": "0:07:41", "throughput": 5473.79, "total_tokens": 36733584} {"current_steps": 60315, "total_steps": 64460, "loss": 0.1624, "lr": 1.254895793173888e-07, "epoch": 18.713931120074466, "percentage": 93.57, "elapsed_time": "1:51:51", "remaining_time": "0:07:41", "throughput": 5473.88, "total_tokens": 36737296} {"current_steps": 60320, "total_steps": 64460, "loss": 0.1199, "lr": 1.2518835422788033e-07, "epoch": 18.715482469748682, "percentage": 93.58, "elapsed_time": "1:51:51", "remaining_time": "0:07:40", "throughput": 5473.88, "total_tokens": 36739984} {"current_steps": 60325, "total_steps": 64460, "loss": 0.2065, "lr": 1.2488748651979187e-07, "epoch": 18.7170338194229, "percentage": 93.59, "elapsed_time": "1:51:52", "remaining_time": "0:07:40", "throughput": 5474.02, "total_tokens": 36745136} {"current_steps": 60330, "total_steps": 64460, "loss": 0.1707, "lr": 1.2458697621518024e-07, "epoch": 18.718585169097114, "percentage": 93.59, "elapsed_time": "1:51:53", "remaining_time": "0:07:39", "throughput": 5474.05, "total_tokens": 36748048} {"current_steps": 60335, "total_steps": 64460, "loss": 0.1551, "lr": 1.2428682333607777e-07, "epoch": 18.72013651877133, "percentage": 93.6, "elapsed_time": "1:51:53", "remaining_time": "0:07:39", "throughput": 5474.12, "total_tokens": 36751472} {"current_steps": 60340, "total_steps": 64460, "loss": 0.0941, "lr": 1.2398702790448746e-07, "epoch": 18.72168786844555, "percentage": 93.61, "elapsed_time": "1:51:54", "remaining_time": "0:07:38", "throughput": 5474.13, "total_tokens": 36754224} {"current_steps": 60345, "total_steps": 64460, "loss": 0.1188, "lr": 1.2368758994238893e-07, "epoch": 18.723239218119765, "percentage": 93.62, "elapsed_time": "1:51:54", "remaining_time": "0:07:37", "throughput": 5474.22, "total_tokens": 36758096} {"current_steps": 60350, "total_steps": 64460, "loss": 0.1915, "lr": 1.2338850947173352e-07, "epoch": 18.72479056779398, "percentage": 93.62, "elapsed_time": "1:51:55", "remaining_time": "0:07:37", "throughput": 5474.3, "total_tokens": 36761712} {"current_steps": 60355, "total_steps": 64460, "loss": 0.2227, "lr": 1.2308978651444926e-07, "epoch": 18.726341917468197, "percentage": 93.63, "elapsed_time": "1:51:55", "remaining_time": "0:07:36", "throughput": 5474.36, "total_tokens": 36765232} {"current_steps": 60360, "total_steps": 64460, "loss": 0.1145, "lr": 1.2279142109243358e-07, "epoch": 18.727893267142413, "percentage": 93.64, "elapsed_time": "1:51:56", "remaining_time": "0:07:36", "throughput": 5474.38, "total_tokens": 36768080} {"current_steps": 60365, "total_steps": 64460, "loss": 0.1811, "lr": 1.2249341322756236e-07, "epoch": 18.72944461681663, "percentage": 93.65, "elapsed_time": "1:51:56", "remaining_time": "0:07:35", "throughput": 5474.39, "total_tokens": 36770896} {"current_steps": 60370, "total_steps": 64460, "loss": 0.0766, "lr": 1.22195762941682e-07, "epoch": 18.73099596649085, "percentage": 93.65, "elapsed_time": "1:51:57", "remaining_time": "0:07:35", "throughput": 5474.41, "total_tokens": 36773616} {"current_steps": 60375, "total_steps": 64460, "loss": 0.1701, "lr": 1.218984702566145e-07, "epoch": 18.732547316165064, "percentage": 93.66, "elapsed_time": "1:51:57", "remaining_time": "0:07:34", "throughput": 5474.43, "total_tokens": 36776528} {"current_steps": 60380, "total_steps": 64460, "loss": 0.1402, "lr": 1.2160153519415407e-07, "epoch": 18.73409866583928, "percentage": 93.67, "elapsed_time": "1:51:58", "remaining_time": "0:07:33", "throughput": 5474.46, "total_tokens": 36779632} {"current_steps": 60385, "total_steps": 64460, "loss": 0.226, "lr": 1.2130495777607e-07, "epoch": 18.735650015513496, "percentage": 93.68, "elapsed_time": "1:51:58", "remaining_time": "0:07:33", "throughput": 5474.44, "total_tokens": 36782352} {"current_steps": 60390, "total_steps": 64460, "loss": 0.2566, "lr": 1.2100873802410483e-07, "epoch": 18.737201365187712, "percentage": 93.69, "elapsed_time": "1:51:59", "remaining_time": "0:07:32", "throughput": 5474.56, "total_tokens": 36786288} {"current_steps": 60395, "total_steps": 64460, "loss": 0.1507, "lr": 1.207128759599757e-07, "epoch": 18.73875271486193, "percentage": 93.69, "elapsed_time": "1:51:59", "remaining_time": "0:07:32", "throughput": 5474.59, "total_tokens": 36789264} {"current_steps": 60400, "total_steps": 64460, "loss": 0.1116, "lr": 1.2041737160537136e-07, "epoch": 18.740304064536147, "percentage": 93.7, "elapsed_time": "1:52:00", "remaining_time": "0:07:31", "throughput": 5474.51, "total_tokens": 36791408} {"current_steps": 60405, "total_steps": 64460, "loss": 0.1535, "lr": 1.2012222498195724e-07, "epoch": 18.741855414210363, "percentage": 93.71, "elapsed_time": "1:52:01", "remaining_time": "0:07:31", "throughput": 5474.55, "total_tokens": 36795088} {"current_steps": 60410, "total_steps": 64460, "loss": 0.2241, "lr": 1.1982743611136993e-07, "epoch": 18.74340676388458, "percentage": 93.72, "elapsed_time": "1:52:01", "remaining_time": "0:07:30", "throughput": 5474.6, "total_tokens": 36798224} {"current_steps": 60415, "total_steps": 64460, "loss": 0.1363, "lr": 1.1953300501522159e-07, "epoch": 18.744958113558795, "percentage": 93.72, "elapsed_time": "1:52:02", "remaining_time": "0:07:30", "throughput": 5474.68, "total_tokens": 36801840} {"current_steps": 60420, "total_steps": 64460, "loss": 0.174, "lr": 1.192389317150977e-07, "epoch": 18.746509463233014, "percentage": 93.73, "elapsed_time": "1:52:02", "remaining_time": "0:07:29", "throughput": 5474.76, "total_tokens": 36805840} {"current_steps": 60425, "total_steps": 64460, "loss": 0.1163, "lr": 1.1894521623255661e-07, "epoch": 18.74806081290723, "percentage": 93.74, "elapsed_time": "1:52:03", "remaining_time": "0:07:28", "throughput": 5474.69, "total_tokens": 36808144} {"current_steps": 60430, "total_steps": 64460, "loss": 0.1874, "lr": 1.1865185858913163e-07, "epoch": 18.749612162581446, "percentage": 93.75, "elapsed_time": "1:52:03", "remaining_time": "0:07:28", "throughput": 5474.75, "total_tokens": 36811504} {"current_steps": 60435, "total_steps": 64460, "loss": 0.2466, "lr": 1.1835885880632891e-07, "epoch": 18.751163512255662, "percentage": 93.76, "elapsed_time": "1:52:04", "remaining_time": "0:07:27", "throughput": 5474.71, "total_tokens": 36814000} {"current_steps": 60440, "total_steps": 64460, "loss": 0.1295, "lr": 1.1806621690563014e-07, "epoch": 18.752714861929878, "percentage": 93.76, "elapsed_time": "1:52:04", "remaining_time": "0:07:27", "throughput": 5474.59, "total_tokens": 36816400} {"current_steps": 60445, "total_steps": 64460, "loss": 0.1426, "lr": 1.1777393290848704e-07, "epoch": 18.754266211604097, "percentage": 93.77, "elapsed_time": "1:52:05", "remaining_time": "0:07:26", "throughput": 5474.67, "total_tokens": 36820400} {"current_steps": 60450, "total_steps": 64460, "loss": 0.243, "lr": 1.1748200683632971e-07, "epoch": 18.755817561278313, "percentage": 93.78, "elapsed_time": "1:52:06", "remaining_time": "0:07:26", "throughput": 5474.68, "total_tokens": 36823216} {"current_steps": 60455, "total_steps": 64460, "loss": 0.0912, "lr": 1.171904387105588e-07, "epoch": 18.75736891095253, "percentage": 93.79, "elapsed_time": "1:52:06", "remaining_time": "0:07:25", "throughput": 5474.63, "total_tokens": 36825424} {"current_steps": 60460, "total_steps": 64460, "loss": 0.2029, "lr": 1.1689922855254998e-07, "epoch": 18.758920260626745, "percentage": 93.79, "elapsed_time": "1:52:07", "remaining_time": "0:07:25", "throughput": 5474.59, "total_tokens": 36827792} {"current_steps": 60465, "total_steps": 64460, "loss": 0.1359, "lr": 1.1660837638365175e-07, "epoch": 18.76047161030096, "percentage": 93.8, "elapsed_time": "1:52:07", "remaining_time": "0:07:24", "throughput": 5474.63, "total_tokens": 36830768} {"current_steps": 60470, "total_steps": 64460, "loss": 0.1661, "lr": 1.1631788222518758e-07, "epoch": 18.762022959975177, "percentage": 93.81, "elapsed_time": "1:52:08", "remaining_time": "0:07:23", "throughput": 5474.52, "total_tokens": 36833008} {"current_steps": 60475, "total_steps": 64460, "loss": 0.1408, "lr": 1.160277460984549e-07, "epoch": 18.763574309649396, "percentage": 93.82, "elapsed_time": "1:52:08", "remaining_time": "0:07:23", "throughput": 5474.53, "total_tokens": 36835984} {"current_steps": 60480, "total_steps": 64460, "loss": 0.0848, "lr": 1.1573796802472282e-07, "epoch": 18.765125659323612, "percentage": 93.83, "elapsed_time": "1:52:09", "remaining_time": "0:07:22", "throughput": 5474.47, "total_tokens": 36838064} {"current_steps": 60485, "total_steps": 64460, "loss": 0.156, "lr": 1.1544854802523598e-07, "epoch": 18.766677008997828, "percentage": 93.83, "elapsed_time": "1:52:09", "remaining_time": "0:07:22", "throughput": 5474.45, "total_tokens": 36840528} {"current_steps": 60490, "total_steps": 64460, "loss": 0.1792, "lr": 1.1515948612121187e-07, "epoch": 18.768228358672044, "percentage": 93.84, "elapsed_time": "1:52:10", "remaining_time": "0:07:21", "throughput": 5474.46, "total_tokens": 36843248} {"current_steps": 60495, "total_steps": 64460, "loss": 0.1227, "lr": 1.1487078233384352e-07, "epoch": 18.76977970834626, "percentage": 93.85, "elapsed_time": "1:52:10", "remaining_time": "0:07:21", "throughput": 5474.46, "total_tokens": 36845936} {"current_steps": 60500, "total_steps": 64460, "loss": 0.1824, "lr": 1.1458243668429458e-07, "epoch": 18.77133105802048, "percentage": 93.86, "elapsed_time": "1:52:10", "remaining_time": "0:07:20", "throughput": 5474.43, "total_tokens": 36848368} {"current_steps": 60505, "total_steps": 64460, "loss": 0.1798, "lr": 1.1429444919370592e-07, "epoch": 18.772882407694695, "percentage": 93.86, "elapsed_time": "1:52:11", "remaining_time": "0:07:20", "throughput": 5474.55, "total_tokens": 36853136} {"current_steps": 60510, "total_steps": 64460, "loss": 0.1918, "lr": 1.140068198831884e-07, "epoch": 18.77443375736891, "percentage": 93.87, "elapsed_time": "1:52:12", "remaining_time": "0:07:19", "throughput": 5474.6, "total_tokens": 36856432} {"current_steps": 60515, "total_steps": 64460, "loss": 0.1241, "lr": 1.1371954877383074e-07, "epoch": 18.775985107043127, "percentage": 93.88, "elapsed_time": "1:52:12", "remaining_time": "0:07:18", "throughput": 5474.68, "total_tokens": 36860048} {"current_steps": 60520, "total_steps": 64460, "loss": 0.1401, "lr": 1.1343263588669162e-07, "epoch": 18.777536456717343, "percentage": 93.89, "elapsed_time": "1:52:13", "remaining_time": "0:07:18", "throughput": 5474.65, "total_tokens": 36862512} {"current_steps": 60525, "total_steps": 64460, "loss": 0.2314, "lr": 1.1314608124280646e-07, "epoch": 18.779087806391562, "percentage": 93.9, "elapsed_time": "1:52:13", "remaining_time": "0:07:17", "throughput": 5474.63, "total_tokens": 36865136} {"current_steps": 60530, "total_steps": 64460, "loss": 0.1731, "lr": 1.1285988486318234e-07, "epoch": 18.780639156065778, "percentage": 93.9, "elapsed_time": "1:52:14", "remaining_time": "0:07:17", "throughput": 5474.68, "total_tokens": 36868720} {"current_steps": 60535, "total_steps": 64460, "loss": 0.1485, "lr": 1.1257404676880135e-07, "epoch": 18.782190505739994, "percentage": 93.91, "elapsed_time": "1:52:15", "remaining_time": "0:07:16", "throughput": 5474.8, "total_tokens": 36873168} {"current_steps": 60540, "total_steps": 64460, "loss": 0.1413, "lr": 1.122885669806184e-07, "epoch": 18.78374185541421, "percentage": 93.92, "elapsed_time": "1:52:15", "remaining_time": "0:07:16", "throughput": 5474.82, "total_tokens": 36875920} {"current_steps": 60545, "total_steps": 64460, "loss": 0.1523, "lr": 1.1200344551956232e-07, "epoch": 18.785293205088426, "percentage": 93.93, "elapsed_time": "1:52:16", "remaining_time": "0:07:15", "throughput": 5474.87, "total_tokens": 36879312} {"current_steps": 60550, "total_steps": 64460, "loss": 0.1259, "lr": 1.1171868240653638e-07, "epoch": 18.786844554762645, "percentage": 93.93, "elapsed_time": "1:52:16", "remaining_time": "0:07:15", "throughput": 5474.88, "total_tokens": 36882032} {"current_steps": 60555, "total_steps": 64460, "loss": 0.1463, "lr": 1.1143427766241665e-07, "epoch": 18.78839590443686, "percentage": 93.94, "elapsed_time": "1:52:17", "remaining_time": "0:07:14", "throughput": 5474.9, "total_tokens": 36884976} {"current_steps": 60560, "total_steps": 64460, "loss": 0.1434, "lr": 1.1115023130805424e-07, "epoch": 18.789947254111077, "percentage": 93.95, "elapsed_time": "1:52:17", "remaining_time": "0:07:13", "throughput": 5474.9, "total_tokens": 36888016} {"current_steps": 60565, "total_steps": 64460, "loss": 0.2402, "lr": 1.108665433642725e-07, "epoch": 18.791498603785293, "percentage": 93.96, "elapsed_time": "1:52:18", "remaining_time": "0:07:13", "throughput": 5475.0, "total_tokens": 36892112} {"current_steps": 60570, "total_steps": 64460, "loss": 0.1824, "lr": 1.1058321385186921e-07, "epoch": 18.79304995345951, "percentage": 93.97, "elapsed_time": "1:52:18", "remaining_time": "0:07:12", "throughput": 5474.97, "total_tokens": 36894736} {"current_steps": 60575, "total_steps": 64460, "loss": 0.1224, "lr": 1.10300242791615e-07, "epoch": 18.794601303133728, "percentage": 93.97, "elapsed_time": "1:52:19", "remaining_time": "0:07:12", "throughput": 5474.97, "total_tokens": 36897424} {"current_steps": 60580, "total_steps": 64460, "loss": 0.0773, "lr": 1.1001763020425605e-07, "epoch": 18.796152652807944, "percentage": 93.98, "elapsed_time": "1:52:19", "remaining_time": "0:07:11", "throughput": 5474.99, "total_tokens": 36900336} {"current_steps": 60585, "total_steps": 64460, "loss": 0.2187, "lr": 1.0973537611051077e-07, "epoch": 18.79770400248216, "percentage": 93.99, "elapsed_time": "1:52:20", "remaining_time": "0:07:11", "throughput": 5475.0, "total_tokens": 36903184} {"current_steps": 60590, "total_steps": 64460, "loss": 0.2484, "lr": 1.0945348053107207e-07, "epoch": 18.799255352156376, "percentage": 94.0, "elapsed_time": "1:52:20", "remaining_time": "0:07:10", "throughput": 5475.07, "total_tokens": 36906576} {"current_steps": 60595, "total_steps": 64460, "loss": 0.2479, "lr": 1.0917194348660564e-07, "epoch": 18.80080670183059, "percentage": 94.0, "elapsed_time": "1:52:21", "remaining_time": "0:07:09", "throughput": 5475.09, "total_tokens": 36909264} {"current_steps": 60600, "total_steps": 64460, "loss": 0.1913, "lr": 1.088907649977522e-07, "epoch": 18.80235805150481, "percentage": 94.01, "elapsed_time": "1:52:21", "remaining_time": "0:07:09", "throughput": 5475.11, "total_tokens": 36912400} {"current_steps": 60605, "total_steps": 64460, "loss": 0.1838, "lr": 1.0860994508512524e-07, "epoch": 18.803909401179027, "percentage": 94.02, "elapsed_time": "1:52:22", "remaining_time": "0:07:08", "throughput": 5475.17, "total_tokens": 36915952} {"current_steps": 60610, "total_steps": 64460, "loss": 0.061, "lr": 1.0832948376931108e-07, "epoch": 18.805460750853243, "percentage": 94.03, "elapsed_time": "1:52:22", "remaining_time": "0:07:08", "throughput": 5475.25, "total_tokens": 36919248} {"current_steps": 60615, "total_steps": 64460, "loss": 0.1351, "lr": 1.0804938107087271e-07, "epoch": 18.80701210052746, "percentage": 94.04, "elapsed_time": "1:52:23", "remaining_time": "0:07:07", "throughput": 5475.36, "total_tokens": 36922960} {"current_steps": 60620, "total_steps": 64460, "loss": 0.1663, "lr": 1.0776963701034371e-07, "epoch": 18.808563450201675, "percentage": 94.04, "elapsed_time": "1:52:23", "remaining_time": "0:07:07", "throughput": 5475.4, "total_tokens": 36926032} {"current_steps": 60625, "total_steps": 64460, "loss": 0.1245, "lr": 1.0749025160823323e-07, "epoch": 18.81011479987589, "percentage": 94.05, "elapsed_time": "1:52:24", "remaining_time": "0:07:06", "throughput": 5475.44, "total_tokens": 36928976} {"current_steps": 60630, "total_steps": 64460, "loss": 0.2707, "lr": 1.0721122488502322e-07, "epoch": 18.81166614955011, "percentage": 94.06, "elapsed_time": "1:52:24", "remaining_time": "0:07:06", "throughput": 5475.5, "total_tokens": 36932144} {"current_steps": 60635, "total_steps": 64460, "loss": 0.1852, "lr": 1.0693255686116954e-07, "epoch": 18.813217499224326, "percentage": 94.07, "elapsed_time": "1:52:25", "remaining_time": "0:07:05", "throughput": 5475.51, "total_tokens": 36935152} {"current_steps": 60640, "total_steps": 64460, "loss": 0.1189, "lr": 1.0665424755710197e-07, "epoch": 18.81476884889854, "percentage": 94.07, "elapsed_time": "1:52:26", "remaining_time": "0:07:04", "throughput": 5475.55, "total_tokens": 36938288} {"current_steps": 60645, "total_steps": 64460, "loss": 0.1539, "lr": 1.0637629699322416e-07, "epoch": 18.816320198572758, "percentage": 94.08, "elapsed_time": "1:52:26", "remaining_time": "0:07:04", "throughput": 5475.55, "total_tokens": 36940944} {"current_steps": 60650, "total_steps": 64460, "loss": 0.1271, "lr": 1.0609870518991317e-07, "epoch": 18.817871548246973, "percentage": 94.09, "elapsed_time": "1:52:27", "remaining_time": "0:07:03", "throughput": 5475.63, "total_tokens": 36944720} {"current_steps": 60655, "total_steps": 64460, "loss": 0.1534, "lr": 1.0582147216751881e-07, "epoch": 18.819422897921193, "percentage": 94.1, "elapsed_time": "1:52:27", "remaining_time": "0:07:03", "throughput": 5475.62, "total_tokens": 36947408} {"current_steps": 60660, "total_steps": 64460, "loss": 0.1135, "lr": 1.0554459794636707e-07, "epoch": 18.82097424759541, "percentage": 94.1, "elapsed_time": "1:52:28", "remaining_time": "0:07:02", "throughput": 5475.65, "total_tokens": 36950320} {"current_steps": 60665, "total_steps": 64460, "loss": 0.1635, "lr": 1.0526808254675447e-07, "epoch": 18.822525597269625, "percentage": 94.11, "elapsed_time": "1:52:28", "remaining_time": "0:07:02", "throughput": 5475.62, "total_tokens": 36952720} {"current_steps": 60670, "total_steps": 64460, "loss": 0.1237, "lr": 1.049919259889548e-07, "epoch": 18.82407694694384, "percentage": 94.12, "elapsed_time": "1:52:29", "remaining_time": "0:07:01", "throughput": 5475.7, "total_tokens": 36956240} {"current_steps": 60675, "total_steps": 64460, "loss": 0.1182, "lr": 1.0471612829321187e-07, "epoch": 18.825628296618056, "percentage": 94.13, "elapsed_time": "1:52:29", "remaining_time": "0:07:01", "throughput": 5475.67, "total_tokens": 36958640} {"current_steps": 60680, "total_steps": 64460, "loss": 0.1822, "lr": 1.0444068947974562e-07, "epoch": 18.827179646292276, "percentage": 94.14, "elapsed_time": "1:52:30", "remaining_time": "0:07:00", "throughput": 5475.56, "total_tokens": 36960656} {"current_steps": 60685, "total_steps": 64460, "loss": 0.1961, "lr": 1.0416560956874877e-07, "epoch": 18.82873099596649, "percentage": 94.14, "elapsed_time": "1:52:30", "remaining_time": "0:06:59", "throughput": 5475.57, "total_tokens": 36963696} {"current_steps": 60690, "total_steps": 64460, "loss": 0.1709, "lr": 1.0389088858038854e-07, "epoch": 18.830282345640708, "percentage": 94.15, "elapsed_time": "1:52:31", "remaining_time": "0:06:59", "throughput": 5475.56, "total_tokens": 36966160} {"current_steps": 60695, "total_steps": 64460, "loss": 0.2167, "lr": 1.0361652653480437e-07, "epoch": 18.831833695314923, "percentage": 94.16, "elapsed_time": "1:52:31", "remaining_time": "0:06:58", "throughput": 5475.54, "total_tokens": 36968816} {"current_steps": 60700, "total_steps": 64460, "loss": 0.0754, "lr": 1.0334252345211126e-07, "epoch": 18.83338504498914, "percentage": 94.17, "elapsed_time": "1:52:32", "remaining_time": "0:06:58", "throughput": 5475.57, "total_tokens": 36971888} {"current_steps": 60705, "total_steps": 64460, "loss": 0.2475, "lr": 1.030688793523954e-07, "epoch": 18.83493639466336, "percentage": 94.17, "elapsed_time": "1:52:32", "remaining_time": "0:06:57", "throughput": 5475.63, "total_tokens": 36975120} {"current_steps": 60710, "total_steps": 64460, "loss": 0.1141, "lr": 1.0279559425571906e-07, "epoch": 18.836487744337575, "percentage": 94.18, "elapsed_time": "1:52:33", "remaining_time": "0:06:57", "throughput": 5475.69, "total_tokens": 36978224} {"current_steps": 60715, "total_steps": 64460, "loss": 0.126, "lr": 1.0252266818211786e-07, "epoch": 18.83803909401179, "percentage": 94.19, "elapsed_time": "1:52:33", "remaining_time": "0:06:56", "throughput": 5475.67, "total_tokens": 36981264} {"current_steps": 60720, "total_steps": 64460, "loss": 0.0743, "lr": 1.0225010115159972e-07, "epoch": 18.839590443686006, "percentage": 94.2, "elapsed_time": "1:52:34", "remaining_time": "0:06:56", "throughput": 5475.67, "total_tokens": 36984080} {"current_steps": 60725, "total_steps": 64460, "loss": 0.0548, "lr": 1.0197789318414753e-07, "epoch": 18.841141793360222, "percentage": 94.21, "elapsed_time": "1:52:34", "remaining_time": "0:06:55", "throughput": 5475.69, "total_tokens": 36986768} {"current_steps": 60730, "total_steps": 64460, "loss": 0.1571, "lr": 1.0170604429971643e-07, "epoch": 18.842693143034438, "percentage": 94.21, "elapsed_time": "1:52:35", "remaining_time": "0:06:54", "throughput": 5475.67, "total_tokens": 36989264} {"current_steps": 60735, "total_steps": 64460, "loss": 0.1993, "lr": 1.0143455451823714e-07, "epoch": 18.844244492708658, "percentage": 94.22, "elapsed_time": "1:52:35", "remaining_time": "0:06:54", "throughput": 5475.73, "total_tokens": 36992560} {"current_steps": 60740, "total_steps": 64460, "loss": 0.1877, "lr": 1.0116342385961209e-07, "epoch": 18.845795842382874, "percentage": 94.23, "elapsed_time": "1:52:36", "remaining_time": "0:06:53", "throughput": 5475.73, "total_tokens": 36995280} {"current_steps": 60745, "total_steps": 64460, "loss": 0.1492, "lr": 1.0089265234371981e-07, "epoch": 18.84734719205709, "percentage": 94.24, "elapsed_time": "1:52:36", "remaining_time": "0:06:53", "throughput": 5475.71, "total_tokens": 36997968} {"current_steps": 60750, "total_steps": 64460, "loss": 0.1386, "lr": 1.0062223999040943e-07, "epoch": 18.848898541731305, "percentage": 94.24, "elapsed_time": "1:52:37", "remaining_time": "0:06:52", "throughput": 5475.76, "total_tokens": 37000976} {"current_steps": 60755, "total_steps": 64460, "loss": 0.2061, "lr": 1.0035218681950676e-07, "epoch": 18.85044989140552, "percentage": 94.25, "elapsed_time": "1:52:37", "remaining_time": "0:06:52", "throughput": 5475.69, "total_tokens": 37003088} {"current_steps": 60760, "total_steps": 64460, "loss": 0.1093, "lr": 1.0008249285080929e-07, "epoch": 18.85200124107974, "percentage": 94.26, "elapsed_time": "1:52:38", "remaining_time": "0:06:51", "throughput": 5475.65, "total_tokens": 37005328} {"current_steps": 60765, "total_steps": 64460, "loss": 0.1721, "lr": 9.981315810408842e-08, "epoch": 18.853552590753957, "percentage": 94.27, "elapsed_time": "1:52:38", "remaining_time": "0:06:50", "throughput": 5475.65, "total_tokens": 37008400} {"current_steps": 60770, "total_steps": 64460, "loss": 0.1522, "lr": 9.954418259909004e-08, "epoch": 18.855103940428172, "percentage": 94.28, "elapsed_time": "1:52:39", "remaining_time": "0:06:50", "throughput": 5475.71, "total_tokens": 37011504} {"current_steps": 60775, "total_steps": 64460, "loss": 0.087, "lr": 9.927556635553337e-08, "epoch": 18.85665529010239, "percentage": 94.28, "elapsed_time": "1:52:39", "remaining_time": "0:06:49", "throughput": 5475.75, "total_tokens": 37014672} {"current_steps": 60780, "total_steps": 64460, "loss": 0.0993, "lr": 9.900730939311099e-08, "epoch": 18.858206639776604, "percentage": 94.29, "elapsed_time": "1:52:40", "remaining_time": "0:06:49", "throughput": 5475.87, "total_tokens": 37019312} {"current_steps": 60785, "total_steps": 64460, "loss": 0.1721, "lr": 9.873941173148882e-08, "epoch": 18.859757989450824, "percentage": 94.3, "elapsed_time": "1:52:40", "remaining_time": "0:06:48", "throughput": 5475.93, "total_tokens": 37022544} {"current_steps": 60790, "total_steps": 64460, "loss": 0.1272, "lr": 9.847187339030783e-08, "epoch": 18.86130933912504, "percentage": 94.31, "elapsed_time": "1:52:41", "remaining_time": "0:06:48", "throughput": 5476.04, "total_tokens": 37026544} {"current_steps": 60795, "total_steps": 64460, "loss": 0.0956, "lr": 9.820469438918124e-08, "epoch": 18.862860688799255, "percentage": 94.31, "elapsed_time": "1:52:42", "remaining_time": "0:06:47", "throughput": 5476.02, "total_tokens": 37029136} {"current_steps": 60800, "total_steps": 64460, "loss": 0.1184, "lr": 9.793787474769667e-08, "epoch": 18.86441203847347, "percentage": 94.32, "elapsed_time": "1:52:42", "remaining_time": "0:06:47", "throughput": 5476.02, "total_tokens": 37031888} {"current_steps": 60805, "total_steps": 64460, "loss": 0.0774, "lr": 9.767141448541462e-08, "epoch": 18.865963388147687, "percentage": 94.33, "elapsed_time": "1:52:43", "remaining_time": "0:06:46", "throughput": 5476.14, "total_tokens": 37036208} {"current_steps": 60810, "total_steps": 64460, "loss": 0.187, "lr": 9.740531362187056e-08, "epoch": 18.867514737821907, "percentage": 94.34, "elapsed_time": "1:52:43", "remaining_time": "0:06:45", "throughput": 5476.15, "total_tokens": 37039152} {"current_steps": 60815, "total_steps": 64460, "loss": 0.1065, "lr": 9.713957217657166e-08, "epoch": 18.869066087496122, "percentage": 94.35, "elapsed_time": "1:52:44", "remaining_time": "0:06:45", "throughput": 5476.04, "total_tokens": 37041488} {"current_steps": 60820, "total_steps": 64460, "loss": 0.1781, "lr": 9.687419016900123e-08, "epoch": 18.87061743717034, "percentage": 94.35, "elapsed_time": "1:52:44", "remaining_time": "0:06:44", "throughput": 5476.0, "total_tokens": 37043984} {"current_steps": 60825, "total_steps": 64460, "loss": 0.1235, "lr": 9.660916761861427e-08, "epoch": 18.872168786844554, "percentage": 94.36, "elapsed_time": "1:52:45", "remaining_time": "0:06:44", "throughput": 5475.99, "total_tokens": 37046992} {"current_steps": 60830, "total_steps": 64460, "loss": 0.1509, "lr": 9.634450454483968e-08, "epoch": 18.87372013651877, "percentage": 94.37, "elapsed_time": "1:52:45", "remaining_time": "0:06:43", "throughput": 5475.92, "total_tokens": 37049264} {"current_steps": 60835, "total_steps": 64460, "loss": 0.2113, "lr": 9.608020096708193e-08, "epoch": 18.87527148619299, "percentage": 94.38, "elapsed_time": "1:52:46", "remaining_time": "0:06:43", "throughput": 5475.97, "total_tokens": 37052592} {"current_steps": 60840, "total_steps": 64460, "loss": 0.1051, "lr": 9.581625690471553e-08, "epoch": 18.876822835867205, "percentage": 94.38, "elapsed_time": "1:52:46", "remaining_time": "0:06:42", "throughput": 5476.01, "total_tokens": 37055856} {"current_steps": 60845, "total_steps": 64460, "loss": 0.2524, "lr": 9.555267237709221e-08, "epoch": 18.87837418554142, "percentage": 94.39, "elapsed_time": "1:52:47", "remaining_time": "0:06:42", "throughput": 5476.07, "total_tokens": 37059696} {"current_steps": 60850, "total_steps": 64460, "loss": 0.0992, "lr": 9.528944740353541e-08, "epoch": 18.879925535215637, "percentage": 94.4, "elapsed_time": "1:52:48", "remaining_time": "0:06:41", "throughput": 5476.03, "total_tokens": 37062352} {"current_steps": 60855, "total_steps": 64460, "loss": 0.0792, "lr": 9.502658200334247e-08, "epoch": 18.881476884889853, "percentage": 94.41, "elapsed_time": "1:52:48", "remaining_time": "0:06:40", "throughput": 5476.09, "total_tokens": 37066032} {"current_steps": 60860, "total_steps": 64460, "loss": 0.1771, "lr": 9.47640761957841e-08, "epoch": 18.883028234564073, "percentage": 94.42, "elapsed_time": "1:52:49", "remaining_time": "0:06:40", "throughput": 5476.14, "total_tokens": 37069232} {"current_steps": 60865, "total_steps": 64460, "loss": 0.1461, "lr": 9.450193000010655e-08, "epoch": 18.88457958423829, "percentage": 94.42, "elapsed_time": "1:52:49", "remaining_time": "0:06:39", "throughput": 5476.24, "total_tokens": 37073648} {"current_steps": 60870, "total_steps": 64460, "loss": 0.1624, "lr": 9.424014343552668e-08, "epoch": 18.886130933912504, "percentage": 94.43, "elapsed_time": "1:52:50", "remaining_time": "0:06:39", "throughput": 5476.31, "total_tokens": 37077296} {"current_steps": 60875, "total_steps": 64460, "loss": 0.1699, "lr": 9.397871652123803e-08, "epoch": 18.88768228358672, "percentage": 94.44, "elapsed_time": "1:52:50", "remaining_time": "0:06:38", "throughput": 5476.27, "total_tokens": 37079728} {"current_steps": 60880, "total_steps": 64460, "loss": 0.179, "lr": 9.371764927640414e-08, "epoch": 18.889233633260936, "percentage": 94.45, "elapsed_time": "1:52:51", "remaining_time": "0:06:38", "throughput": 5476.23, "total_tokens": 37082128} {"current_steps": 60885, "total_steps": 64460, "loss": 0.0697, "lr": 9.345694172016639e-08, "epoch": 18.890784982935152, "percentage": 94.45, "elapsed_time": "1:52:51", "remaining_time": "0:06:37", "throughput": 5476.19, "total_tokens": 37084432} {"current_steps": 60890, "total_steps": 64460, "loss": 0.1633, "lr": 9.319659387163726e-08, "epoch": 18.89233633260937, "percentage": 94.46, "elapsed_time": "1:52:52", "remaining_time": "0:06:37", "throughput": 5476.25, "total_tokens": 37087632} {"current_steps": 60895, "total_steps": 64460, "loss": 0.1991, "lr": 9.29366057499026e-08, "epoch": 18.893887682283587, "percentage": 94.47, "elapsed_time": "1:52:53", "remaining_time": "0:06:36", "throughput": 5476.27, "total_tokens": 37090800} {"current_steps": 60900, "total_steps": 64460, "loss": 0.1011, "lr": 9.267697737402325e-08, "epoch": 18.895439031957803, "percentage": 94.48, "elapsed_time": "1:52:53", "remaining_time": "0:06:35", "throughput": 5476.32, "total_tokens": 37094032} {"current_steps": 60905, "total_steps": 64460, "loss": 0.212, "lr": 9.241770876303236e-08, "epoch": 18.89699038163202, "percentage": 94.48, "elapsed_time": "1:52:53", "remaining_time": "0:06:35", "throughput": 5476.28, "total_tokens": 37096272} {"current_steps": 60910, "total_steps": 64460, "loss": 0.1874, "lr": 9.215879993593857e-08, "epoch": 18.898541731306235, "percentage": 94.49, "elapsed_time": "1:52:54", "remaining_time": "0:06:34", "throughput": 5476.33, "total_tokens": 37099440} {"current_steps": 60915, "total_steps": 64460, "loss": 0.1539, "lr": 9.190025091172172e-08, "epoch": 18.900093080980454, "percentage": 94.5, "elapsed_time": "1:52:55", "remaining_time": "0:06:34", "throughput": 5476.38, "total_tokens": 37103376} {"current_steps": 60920, "total_steps": 64460, "loss": 0.1072, "lr": 9.164206170933775e-08, "epoch": 18.90164443065467, "percentage": 94.51, "elapsed_time": "1:52:55", "remaining_time": "0:06:33", "throughput": 5476.44, "total_tokens": 37106672} {"current_steps": 60925, "total_steps": 64460, "loss": 0.1657, "lr": 9.138423234771376e-08, "epoch": 18.903195780328886, "percentage": 94.52, "elapsed_time": "1:52:56", "remaining_time": "0:06:33", "throughput": 5476.48, "total_tokens": 37110224} {"current_steps": 60930, "total_steps": 64460, "loss": 0.1786, "lr": 9.11267628457524e-08, "epoch": 18.904747130003102, "percentage": 94.52, "elapsed_time": "1:52:56", "remaining_time": "0:06:32", "throughput": 5476.52, "total_tokens": 37113072} {"current_steps": 60935, "total_steps": 64460, "loss": 0.191, "lr": 9.08696532223291e-08, "epoch": 18.906298479677318, "percentage": 94.53, "elapsed_time": "1:52:57", "remaining_time": "0:06:32", "throughput": 5476.56, "total_tokens": 37116176} {"current_steps": 60940, "total_steps": 64460, "loss": 0.1317, "lr": 9.061290349629271e-08, "epoch": 18.907849829351537, "percentage": 94.54, "elapsed_time": "1:52:57", "remaining_time": "0:06:31", "throughput": 5476.54, "total_tokens": 37118704} {"current_steps": 60945, "total_steps": 64460, "loss": 0.202, "lr": 9.035651368646647e-08, "epoch": 18.909401179025753, "percentage": 94.55, "elapsed_time": "1:52:58", "remaining_time": "0:06:30", "throughput": 5476.61, "total_tokens": 37122192} {"current_steps": 60950, "total_steps": 64460, "loss": 0.2401, "lr": 9.010048381164705e-08, "epoch": 18.91095252869997, "percentage": 94.55, "elapsed_time": "1:52:58", "remaining_time": "0:06:30", "throughput": 5476.59, "total_tokens": 37124656} {"current_steps": 60955, "total_steps": 64460, "loss": 0.1478, "lr": 8.98448138906033e-08, "epoch": 18.912503878374185, "percentage": 94.56, "elapsed_time": "1:52:59", "remaining_time": "0:06:29", "throughput": 5476.73, "total_tokens": 37129456} {"current_steps": 60960, "total_steps": 64460, "loss": 0.142, "lr": 8.958950394208077e-08, "epoch": 18.9140552280484, "percentage": 94.57, "elapsed_time": "1:52:59", "remaining_time": "0:06:29", "throughput": 5476.76, "total_tokens": 37132400} {"current_steps": 60965, "total_steps": 64460, "loss": 0.1572, "lr": 8.933455398479451e-08, "epoch": 18.91560657772262, "percentage": 94.58, "elapsed_time": "1:53:00", "remaining_time": "0:06:28", "throughput": 5476.82, "total_tokens": 37135760} {"current_steps": 60970, "total_steps": 64460, "loss": 0.1479, "lr": 8.90799640374368e-08, "epoch": 18.917157927396836, "percentage": 94.59, "elapsed_time": "1:53:01", "remaining_time": "0:06:28", "throughput": 5476.9, "total_tokens": 37139408} {"current_steps": 60975, "total_steps": 64460, "loss": 0.0931, "lr": 8.882573411867213e-08, "epoch": 18.918709277071052, "percentage": 94.59, "elapsed_time": "1:53:01", "remaining_time": "0:06:27", "throughput": 5476.97, "total_tokens": 37142608} {"current_steps": 60980, "total_steps": 64460, "loss": 0.0901, "lr": 8.857186424713726e-08, "epoch": 18.920260626745268, "percentage": 94.6, "elapsed_time": "1:53:02", "remaining_time": "0:06:27", "throughput": 5477.05, "total_tokens": 37146064} {"current_steps": 60985, "total_steps": 64460, "loss": 0.1078, "lr": 8.831835444144566e-08, "epoch": 18.921811976419484, "percentage": 94.61, "elapsed_time": "1:53:02", "remaining_time": "0:06:26", "throughput": 5477.07, "total_tokens": 37148816} {"current_steps": 60990, "total_steps": 64460, "loss": 0.1506, "lr": 8.806520472018132e-08, "epoch": 18.9233633260937, "percentage": 94.62, "elapsed_time": "1:53:03", "remaining_time": "0:06:25", "throughput": 5477.15, "total_tokens": 37152528} {"current_steps": 60995, "total_steps": 64460, "loss": 0.1322, "lr": 8.781241510190331e-08, "epoch": 18.92491467576792, "percentage": 94.62, "elapsed_time": "1:53:03", "remaining_time": "0:06:25", "throughput": 5477.13, "total_tokens": 37154832} {"current_steps": 61000, "total_steps": 64460, "loss": 0.1615, "lr": 8.755998560514455e-08, "epoch": 18.926466025442135, "percentage": 94.63, "elapsed_time": "1:53:04", "remaining_time": "0:06:24", "throughput": 5477.11, "total_tokens": 37157200} {"current_steps": 61005, "total_steps": 64460, "loss": 0.2146, "lr": 8.730791624841084e-08, "epoch": 18.92801737511635, "percentage": 94.64, "elapsed_time": "1:53:04", "remaining_time": "0:06:24", "throughput": 5477.15, "total_tokens": 37160432} {"current_steps": 61010, "total_steps": 64460, "loss": 0.1715, "lr": 8.705620705018181e-08, "epoch": 18.929568724790567, "percentage": 94.65, "elapsed_time": "1:53:05", "remaining_time": "0:06:23", "throughput": 5477.1, "total_tokens": 37162704} {"current_steps": 61015, "total_steps": 64460, "loss": 0.1742, "lr": 8.680485802891048e-08, "epoch": 18.931120074464783, "percentage": 94.66, "elapsed_time": "1:53:05", "remaining_time": "0:06:23", "throughput": 5477.15, "total_tokens": 37166352} {"current_steps": 61020, "total_steps": 64460, "loss": 0.1645, "lr": 8.655386920302433e-08, "epoch": 18.932671424139002, "percentage": 94.66, "elapsed_time": "1:53:06", "remaining_time": "0:06:22", "throughput": 5477.2, "total_tokens": 37169328} {"current_steps": 61025, "total_steps": 64460, "loss": 0.1389, "lr": 8.630324059092365e-08, "epoch": 18.934222773813218, "percentage": 94.67, "elapsed_time": "1:53:06", "remaining_time": "0:06:22", "throughput": 5477.29, "total_tokens": 37172816} {"current_steps": 61030, "total_steps": 64460, "loss": 0.1526, "lr": 8.605297221098152e-08, "epoch": 18.935774123487434, "percentage": 94.68, "elapsed_time": "1:53:07", "remaining_time": "0:06:21", "throughput": 5477.33, "total_tokens": 37175856} {"current_steps": 61035, "total_steps": 64460, "loss": 0.0808, "lr": 8.58030640815466e-08, "epoch": 18.93732547316165, "percentage": 94.69, "elapsed_time": "1:53:07", "remaining_time": "0:06:20", "throughput": 5477.32, "total_tokens": 37178224} {"current_steps": 61040, "total_steps": 64460, "loss": 0.1999, "lr": 8.555351622094033e-08, "epoch": 18.938876822835866, "percentage": 94.69, "elapsed_time": "1:53:08", "remaining_time": "0:06:20", "throughput": 5477.36, "total_tokens": 37181040} {"current_steps": 61045, "total_steps": 64460, "loss": 0.1227, "lr": 8.530432864745697e-08, "epoch": 18.940428172510085, "percentage": 94.7, "elapsed_time": "1:53:08", "remaining_time": "0:06:19", "throughput": 5477.31, "total_tokens": 37183120} {"current_steps": 61050, "total_steps": 64460, "loss": 0.1287, "lr": 8.505550137936525e-08, "epoch": 18.9419795221843, "percentage": 94.71, "elapsed_time": "1:53:09", "remaining_time": "0:06:19", "throughput": 5477.39, "total_tokens": 37186864} {"current_steps": 61055, "total_steps": 64460, "loss": 0.2109, "lr": 8.480703443490612e-08, "epoch": 18.943530871858517, "percentage": 94.72, "elapsed_time": "1:53:09", "remaining_time": "0:06:18", "throughput": 5477.46, "total_tokens": 37190480} {"current_steps": 61060, "total_steps": 64460, "loss": 0.1199, "lr": 8.455892783229669e-08, "epoch": 18.945082221532733, "percentage": 94.73, "elapsed_time": "1:53:10", "remaining_time": "0:06:18", "throughput": 5477.48, "total_tokens": 37193488} {"current_steps": 61065, "total_steps": 64460, "loss": 0.1973, "lr": 8.431118158972517e-08, "epoch": 18.94663357120695, "percentage": 94.73, "elapsed_time": "1:53:10", "remaining_time": "0:06:17", "throughput": 5477.56, "total_tokens": 37196816} {"current_steps": 61070, "total_steps": 64460, "loss": 0.083, "lr": 8.406379572535484e-08, "epoch": 18.948184920881168, "percentage": 94.74, "elapsed_time": "1:53:11", "remaining_time": "0:06:16", "throughput": 5477.66, "total_tokens": 37200528} {"current_steps": 61075, "total_steps": 64460, "loss": 0.173, "lr": 8.381677025732116e-08, "epoch": 18.949736270555384, "percentage": 94.75, "elapsed_time": "1:53:11", "remaining_time": "0:06:16", "throughput": 5477.67, "total_tokens": 37203376} {"current_steps": 61080, "total_steps": 64460, "loss": 0.1984, "lr": 8.357010520373465e-08, "epoch": 18.9512876202296, "percentage": 94.76, "elapsed_time": "1:53:12", "remaining_time": "0:06:15", "throughput": 5477.71, "total_tokens": 37206448} {"current_steps": 61085, "total_steps": 64460, "loss": 0.2674, "lr": 8.332380058267864e-08, "epoch": 18.952838969903816, "percentage": 94.76, "elapsed_time": "1:53:12", "remaining_time": "0:06:15", "throughput": 5477.74, "total_tokens": 37209328} {"current_steps": 61090, "total_steps": 64460, "loss": 0.1512, "lr": 8.307785641220978e-08, "epoch": 18.95439031957803, "percentage": 94.77, "elapsed_time": "1:53:13", "remaining_time": "0:06:14", "throughput": 5477.82, "total_tokens": 37213200} {"current_steps": 61095, "total_steps": 64460, "loss": 0.1101, "lr": 8.283227271035976e-08, "epoch": 18.95594166925225, "percentage": 94.78, "elapsed_time": "1:53:14", "remaining_time": "0:06:14", "throughput": 5477.89, "total_tokens": 37217072} {"current_steps": 61100, "total_steps": 64460, "loss": 0.1359, "lr": 8.258704949513196e-08, "epoch": 18.957493018926467, "percentage": 94.79, "elapsed_time": "1:53:14", "remaining_time": "0:06:13", "throughput": 5477.97, "total_tokens": 37220528} {"current_steps": 61105, "total_steps": 64460, "loss": 0.1964, "lr": 8.234218678450479e-08, "epoch": 18.959044368600683, "percentage": 94.8, "elapsed_time": "1:53:15", "remaining_time": "0:06:13", "throughput": 5478.05, "total_tokens": 37224400} {"current_steps": 61110, "total_steps": 64460, "loss": 0.1403, "lr": 8.20976845964283e-08, "epoch": 18.9605957182749, "percentage": 94.8, "elapsed_time": "1:53:15", "remaining_time": "0:06:12", "throughput": 5478.12, "total_tokens": 37227888} {"current_steps": 61115, "total_steps": 64460, "loss": 0.2007, "lr": 8.185354294882875e-08, "epoch": 18.962147067949115, "percentage": 94.81, "elapsed_time": "1:53:16", "remaining_time": "0:06:11", "throughput": 5478.21, "total_tokens": 37231792} {"current_steps": 61120, "total_steps": 64460, "loss": 0.1895, "lr": 8.160976185960401e-08, "epoch": 18.963698417623334, "percentage": 94.82, "elapsed_time": "1:53:16", "remaining_time": "0:06:11", "throughput": 5478.19, "total_tokens": 37234256} {"current_steps": 61125, "total_steps": 64460, "loss": 0.1504, "lr": 8.136634134662591e-08, "epoch": 18.96524976729755, "percentage": 94.83, "elapsed_time": "1:53:17", "remaining_time": "0:06:10", "throughput": 5478.24, "total_tokens": 37237328} {"current_steps": 61130, "total_steps": 64460, "loss": 0.2731, "lr": 8.112328142774017e-08, "epoch": 18.966801116971766, "percentage": 94.83, "elapsed_time": "1:53:17", "remaining_time": "0:06:10", "throughput": 5478.21, "total_tokens": 37239728} {"current_steps": 61135, "total_steps": 64460, "loss": 0.1568, "lr": 8.0880582120767e-08, "epoch": 18.96835246664598, "percentage": 94.84, "elapsed_time": "1:53:18", "remaining_time": "0:06:09", "throughput": 5478.27, "total_tokens": 37243440} {"current_steps": 61140, "total_steps": 64460, "loss": 0.1478, "lr": 8.063824344349714e-08, "epoch": 18.969903816320198, "percentage": 94.85, "elapsed_time": "1:53:18", "remaining_time": "0:06:09", "throughput": 5478.28, "total_tokens": 37246192} {"current_steps": 61145, "total_steps": 64460, "loss": 0.1594, "lr": 8.03962654136986e-08, "epoch": 18.971455165994414, "percentage": 94.86, "elapsed_time": "1:53:19", "remaining_time": "0:06:08", "throughput": 5478.27, "total_tokens": 37248784} {"current_steps": 61150, "total_steps": 64460, "loss": 0.1243, "lr": 8.015464804911055e-08, "epoch": 18.973006515668633, "percentage": 94.87, "elapsed_time": "1:53:19", "remaining_time": "0:06:08", "throughput": 5478.36, "total_tokens": 37252400} {"current_steps": 61155, "total_steps": 64460, "loss": 0.1184, "lr": 7.991339136744658e-08, "epoch": 18.97455786534285, "percentage": 94.87, "elapsed_time": "1:53:20", "remaining_time": "0:06:07", "throughput": 5478.33, "total_tokens": 37254704} {"current_steps": 61160, "total_steps": 64460, "loss": 0.2188, "lr": 7.967249538639365e-08, "epoch": 18.976109215017065, "percentage": 94.88, "elapsed_time": "1:53:20", "remaining_time": "0:06:06", "throughput": 5478.32, "total_tokens": 37257552} {"current_steps": 61165, "total_steps": 64460, "loss": 0.07, "lr": 7.943196012361153e-08, "epoch": 18.97766056469128, "percentage": 94.89, "elapsed_time": "1:53:21", "remaining_time": "0:06:06", "throughput": 5478.33, "total_tokens": 37260272} {"current_steps": 61170, "total_steps": 64460, "loss": 0.0988, "lr": 7.919178559673557e-08, "epoch": 18.979211914365496, "percentage": 94.9, "elapsed_time": "1:53:21", "remaining_time": "0:06:05", "throughput": 5478.39, "total_tokens": 37263728} {"current_steps": 61175, "total_steps": 64460, "loss": 0.1459, "lr": 7.895197182337278e-08, "epoch": 18.980763264039716, "percentage": 94.9, "elapsed_time": "1:53:22", "remaining_time": "0:06:05", "throughput": 5478.41, "total_tokens": 37266704} {"current_steps": 61180, "total_steps": 64460, "loss": 0.0919, "lr": 7.871251882110464e-08, "epoch": 18.982314613713932, "percentage": 94.91, "elapsed_time": "1:53:22", "remaining_time": "0:06:04", "throughput": 5478.4, "total_tokens": 37269328} {"current_steps": 61185, "total_steps": 64460, "loss": 0.1562, "lr": 7.847342660748491e-08, "epoch": 18.983865963388148, "percentage": 94.92, "elapsed_time": "1:53:23", "remaining_time": "0:06:04", "throughput": 5478.47, "total_tokens": 37272752} {"current_steps": 61190, "total_steps": 64460, "loss": 0.1647, "lr": 7.82346952000429e-08, "epoch": 18.985417313062364, "percentage": 94.93, "elapsed_time": "1:53:24", "remaining_time": "0:06:03", "throughput": 5478.55, "total_tokens": 37277136} {"current_steps": 61195, "total_steps": 64460, "loss": 0.1376, "lr": 7.799632461628015e-08, "epoch": 18.98696866273658, "percentage": 94.93, "elapsed_time": "1:53:24", "remaining_time": "0:06:03", "throughput": 5478.62, "total_tokens": 37280528} {"current_steps": 61200, "total_steps": 64460, "loss": 0.0979, "lr": 7.775831487367269e-08, "epoch": 18.9885200124108, "percentage": 94.94, "elapsed_time": "1:53:25", "remaining_time": "0:06:02", "throughput": 5478.7, "total_tokens": 37283984} {"current_steps": 61205, "total_steps": 64460, "loss": 0.1686, "lr": 7.752066598966767e-08, "epoch": 18.990071362085015, "percentage": 94.95, "elapsed_time": "1:53:25", "remaining_time": "0:06:01", "throughput": 5478.69, "total_tokens": 37286416} {"current_steps": 61210, "total_steps": 64460, "loss": 0.1612, "lr": 7.72833779816895e-08, "epoch": 18.99162271175923, "percentage": 94.96, "elapsed_time": "1:53:26", "remaining_time": "0:06:01", "throughput": 5478.72, "total_tokens": 37289424} {"current_steps": 61215, "total_steps": 64460, "loss": 0.1091, "lr": 7.704645086713314e-08, "epoch": 18.993174061433447, "percentage": 94.97, "elapsed_time": "1:53:26", "remaining_time": "0:06:00", "throughput": 5478.85, "total_tokens": 37294000} {"current_steps": 61220, "total_steps": 64460, "loss": 0.1508, "lr": 7.680988466336858e-08, "epoch": 18.994725411107662, "percentage": 94.97, "elapsed_time": "1:53:27", "remaining_time": "0:06:00", "throughput": 5478.87, "total_tokens": 37297168} {"current_steps": 61225, "total_steps": 64460, "loss": 0.1329, "lr": 7.657367938773863e-08, "epoch": 18.996276760781882, "percentage": 94.98, "elapsed_time": "1:53:27", "remaining_time": "0:05:59", "throughput": 5478.86, "total_tokens": 37299984} {"current_steps": 61230, "total_steps": 64460, "loss": 0.1615, "lr": 7.633783505755998e-08, "epoch": 18.997828110456098, "percentage": 94.99, "elapsed_time": "1:53:28", "remaining_time": "0:05:59", "throughput": 5478.92, "total_tokens": 37303184} {"current_steps": 61235, "total_steps": 64460, "loss": 0.1478, "lr": 7.610235169012325e-08, "epoch": 18.999379460130314, "percentage": 95.0, "elapsed_time": "1:53:28", "remaining_time": "0:05:58", "throughput": 5478.96, "total_tokens": 37306032} {"current_steps": 61240, "total_steps": 64460, "loss": 0.1122, "lr": 7.58672293026913e-08, "epoch": 19.00093080980453, "percentage": 95.0, "elapsed_time": "1:53:29", "remaining_time": "0:05:58", "throughput": 5478.68, "total_tokens": 37308032} {"current_steps": 61245, "total_steps": 64460, "loss": 0.1014, "lr": 7.563246791250256e-08, "epoch": 19.002482159478745, "percentage": 95.01, "elapsed_time": "1:53:30", "remaining_time": "0:05:57", "throughput": 5478.71, "total_tokens": 37311200} {"current_steps": 61250, "total_steps": 64460, "loss": 0.1323, "lr": 7.53980675367666e-08, "epoch": 19.004033509152965, "percentage": 95.02, "elapsed_time": "1:53:30", "remaining_time": "0:05:56", "throughput": 5478.65, "total_tokens": 37313472} {"current_steps": 61255, "total_steps": 64460, "loss": 0.1059, "lr": 7.516402819266854e-08, "epoch": 19.00558485882718, "percentage": 95.03, "elapsed_time": "1:53:31", "remaining_time": "0:05:56", "throughput": 5478.72, "total_tokens": 37316736} {"current_steps": 61260, "total_steps": 64460, "loss": 0.1698, "lr": 7.493034989736581e-08, "epoch": 19.007136208501397, "percentage": 95.04, "elapsed_time": "1:53:31", "remaining_time": "0:05:55", "throughput": 5478.74, "total_tokens": 37319616} {"current_steps": 61265, "total_steps": 64460, "loss": 0.1658, "lr": 7.469703266799078e-08, "epoch": 19.008687558175613, "percentage": 95.04, "elapsed_time": "1:53:32", "remaining_time": "0:05:55", "throughput": 5478.78, "total_tokens": 37322784} {"current_steps": 61270, "total_steps": 64460, "loss": 0.1341, "lr": 7.446407652164644e-08, "epoch": 19.01023890784983, "percentage": 95.05, "elapsed_time": "1:53:32", "remaining_time": "0:05:54", "throughput": 5478.87, "total_tokens": 37327200} {"current_steps": 61275, "total_steps": 64460, "loss": 0.1225, "lr": 7.423148147541248e-08, "epoch": 19.011790257524044, "percentage": 95.06, "elapsed_time": "1:53:33", "remaining_time": "0:05:54", "throughput": 5478.94, "total_tokens": 37330304} {"current_steps": 61280, "total_steps": 64460, "loss": 0.1544, "lr": 7.399924754634136e-08, "epoch": 19.013341607198264, "percentage": 95.07, "elapsed_time": "1:53:33", "remaining_time": "0:05:53", "throughput": 5478.95, "total_tokens": 37332992} {"current_steps": 61285, "total_steps": 64460, "loss": 0.1097, "lr": 7.376737475145778e-08, "epoch": 19.01489295687248, "percentage": 95.07, "elapsed_time": "1:53:34", "remaining_time": "0:05:53", "throughput": 5478.96, "total_tokens": 37335648} {"current_steps": 61290, "total_steps": 64460, "loss": 0.1247, "lr": 7.353586310776096e-08, "epoch": 19.016444306546695, "percentage": 95.08, "elapsed_time": "1:53:34", "remaining_time": "0:05:52", "throughput": 5478.94, "total_tokens": 37338176} {"current_steps": 61295, "total_steps": 64460, "loss": 0.0591, "lr": 7.330471263222339e-08, "epoch": 19.01799565622091, "percentage": 95.09, "elapsed_time": "1:53:35", "remaining_time": "0:05:51", "throughput": 5478.95, "total_tokens": 37341152} {"current_steps": 61300, "total_steps": 64460, "loss": 0.1206, "lr": 7.307392334179097e-08, "epoch": 19.019547005895127, "percentage": 95.1, "elapsed_time": "1:53:35", "remaining_time": "0:05:51", "throughput": 5478.88, "total_tokens": 37343488} {"current_steps": 61305, "total_steps": 64460, "loss": 0.189, "lr": 7.284349525338352e-08, "epoch": 19.021098355569347, "percentage": 95.11, "elapsed_time": "1:53:36", "remaining_time": "0:05:50", "throughput": 5478.79, "total_tokens": 37345696} {"current_steps": 61310, "total_steps": 64460, "loss": 0.1628, "lr": 7.261342838389474e-08, "epoch": 19.022649705243563, "percentage": 95.11, "elapsed_time": "1:53:36", "remaining_time": "0:05:50", "throughput": 5478.72, "total_tokens": 37347872} {"current_steps": 61315, "total_steps": 64460, "loss": 0.1941, "lr": 7.238372275019001e-08, "epoch": 19.02420105491778, "percentage": 95.12, "elapsed_time": "1:53:37", "remaining_time": "0:05:49", "throughput": 5478.66, "total_tokens": 37350016} {"current_steps": 61320, "total_steps": 64460, "loss": 0.3715, "lr": 7.215437836911032e-08, "epoch": 19.025752404591994, "percentage": 95.13, "elapsed_time": "1:53:37", "remaining_time": "0:05:49", "throughput": 5478.65, "total_tokens": 37352608} {"current_steps": 61325, "total_steps": 64460, "loss": 0.0663, "lr": 7.192539525746945e-08, "epoch": 19.02730375426621, "percentage": 95.14, "elapsed_time": "1:53:38", "remaining_time": "0:05:48", "throughput": 5478.67, "total_tokens": 37355712} {"current_steps": 61330, "total_steps": 64460, "loss": 0.1531, "lr": 7.16967734320534e-08, "epoch": 19.02885510394043, "percentage": 95.14, "elapsed_time": "1:53:38", "remaining_time": "0:05:48", "throughput": 5478.62, "total_tokens": 37358144} {"current_steps": 61335, "total_steps": 64460, "loss": 0.1338, "lr": 7.146851290962431e-08, "epoch": 19.030406453614646, "percentage": 95.15, "elapsed_time": "1:53:39", "remaining_time": "0:05:47", "throughput": 5478.72, "total_tokens": 37362048} {"current_steps": 61340, "total_steps": 64460, "loss": 0.1728, "lr": 7.124061370691548e-08, "epoch": 19.03195780328886, "percentage": 95.16, "elapsed_time": "1:53:40", "remaining_time": "0:05:46", "throughput": 5478.78, "total_tokens": 37365312} {"current_steps": 61345, "total_steps": 64460, "loss": 0.229, "lr": 7.101307584063521e-08, "epoch": 19.033509152963077, "percentage": 95.17, "elapsed_time": "1:53:40", "remaining_time": "0:05:46", "throughput": 5478.82, "total_tokens": 37369152} {"current_steps": 61350, "total_steps": 64460, "loss": 0.1311, "lr": 7.07858993274646e-08, "epoch": 19.035060502637293, "percentage": 95.18, "elapsed_time": "1:53:41", "remaining_time": "0:05:45", "throughput": 5478.86, "total_tokens": 37372096} {"current_steps": 61355, "total_steps": 64460, "loss": 0.1746, "lr": 7.05590841840581e-08, "epoch": 19.036611852311513, "percentage": 95.18, "elapsed_time": "1:53:41", "remaining_time": "0:05:45", "throughput": 5478.81, "total_tokens": 37374400} {"current_steps": 61360, "total_steps": 64460, "loss": 0.2248, "lr": 7.033263042704353e-08, "epoch": 19.03816320198573, "percentage": 95.19, "elapsed_time": "1:53:42", "remaining_time": "0:05:44", "throughput": 5478.84, "total_tokens": 37377280} {"current_steps": 61365, "total_steps": 64460, "loss": 0.144, "lr": 7.01065380730237e-08, "epoch": 19.039714551659944, "percentage": 95.2, "elapsed_time": "1:53:42", "remaining_time": "0:05:44", "throughput": 5478.83, "total_tokens": 37380192} {"current_steps": 61370, "total_steps": 64460, "loss": 0.107, "lr": 6.98808071385726e-08, "epoch": 19.04126590133416, "percentage": 95.21, "elapsed_time": "1:53:43", "remaining_time": "0:05:43", "throughput": 5478.83, "total_tokens": 37382848} {"current_steps": 61375, "total_steps": 64460, "loss": 0.1121, "lr": 6.96554376402403e-08, "epoch": 19.042817251008376, "percentage": 95.21, "elapsed_time": "1:53:43", "remaining_time": "0:05:42", "throughput": 5478.82, "total_tokens": 37385760} {"current_steps": 61380, "total_steps": 64460, "loss": 0.1427, "lr": 6.943042959454804e-08, "epoch": 19.044368600682596, "percentage": 95.22, "elapsed_time": "1:53:44", "remaining_time": "0:05:42", "throughput": 5478.84, "total_tokens": 37388448} {"current_steps": 61385, "total_steps": 64460, "loss": 0.1053, "lr": 6.920578301799263e-08, "epoch": 19.04591995035681, "percentage": 95.23, "elapsed_time": "1:53:44", "remaining_time": "0:05:41", "throughput": 5478.93, "total_tokens": 37391904} {"current_steps": 61390, "total_steps": 64460, "loss": 0.1204, "lr": 6.8981497927042e-08, "epoch": 19.047471300031027, "percentage": 95.24, "elapsed_time": "1:53:45", "remaining_time": "0:05:41", "throughput": 5478.92, "total_tokens": 37394688} {"current_steps": 61395, "total_steps": 64460, "loss": 0.168, "lr": 6.875757433813967e-08, "epoch": 19.049022649705243, "percentage": 95.25, "elapsed_time": "1:53:45", "remaining_time": "0:05:40", "throughput": 5478.94, "total_tokens": 37397760} {"current_steps": 61400, "total_steps": 64460, "loss": 0.2482, "lr": 6.853401226770196e-08, "epoch": 19.05057399937946, "percentage": 95.25, "elapsed_time": "1:53:46", "remaining_time": "0:05:40", "throughput": 5478.9, "total_tokens": 37400160} {"current_steps": 61405, "total_steps": 64460, "loss": 0.1597, "lr": 6.831081173211851e-08, "epoch": 19.052125349053675, "percentage": 95.26, "elapsed_time": "1:53:46", "remaining_time": "0:05:39", "throughput": 5478.9, "total_tokens": 37402784} {"current_steps": 61410, "total_steps": 64460, "loss": 0.1487, "lr": 6.808797274775236e-08, "epoch": 19.053676698727894, "percentage": 95.27, "elapsed_time": "1:53:47", "remaining_time": "0:05:39", "throughput": 5478.98, "total_tokens": 37406208} {"current_steps": 61415, "total_steps": 64460, "loss": 0.1741, "lr": 6.786549533094045e-08, "epoch": 19.05522804840211, "percentage": 95.28, "elapsed_time": "1:53:47", "remaining_time": "0:05:38", "throughput": 5479.03, "total_tokens": 37409664} {"current_steps": 61420, "total_steps": 64460, "loss": 0.1061, "lr": 6.764337949799304e-08, "epoch": 19.056779398076326, "percentage": 95.28, "elapsed_time": "1:53:48", "remaining_time": "0:05:37", "throughput": 5479.09, "total_tokens": 37412704} {"current_steps": 61425, "total_steps": 64460, "loss": 0.1592, "lr": 6.742162526519324e-08, "epoch": 19.058330747750542, "percentage": 95.29, "elapsed_time": "1:53:48", "remaining_time": "0:05:37", "throughput": 5479.08, "total_tokens": 37415104} {"current_steps": 61430, "total_steps": 64460, "loss": 0.1609, "lr": 6.720023264879971e-08, "epoch": 19.059882097424758, "percentage": 95.3, "elapsed_time": "1:53:49", "remaining_time": "0:05:36", "throughput": 5479.18, "total_tokens": 37419008} {"current_steps": 61435, "total_steps": 64460, "loss": 0.2639, "lr": 6.697920166504112e-08, "epoch": 19.061433447098977, "percentage": 95.31, "elapsed_time": "1:53:49", "remaining_time": "0:05:36", "throughput": 5479.08, "total_tokens": 37421088} {"current_steps": 61440, "total_steps": 64460, "loss": 0.1651, "lr": 6.675853233012342e-08, "epoch": 19.062984796773193, "percentage": 95.31, "elapsed_time": "1:53:50", "remaining_time": "0:05:35", "throughput": 5479.18, "total_tokens": 37424864} {"current_steps": 61445, "total_steps": 64460, "loss": 0.1454, "lr": 6.653822466022364e-08, "epoch": 19.06453614644741, "percentage": 95.32, "elapsed_time": "1:53:50", "remaining_time": "0:05:35", "throughput": 5479.16, "total_tokens": 37427232} {"current_steps": 61450, "total_steps": 64460, "loss": 0.1514, "lr": 6.631827867149277e-08, "epoch": 19.066087496121625, "percentage": 95.33, "elapsed_time": "1:53:51", "remaining_time": "0:05:34", "throughput": 5479.13, "total_tokens": 37429536} {"current_steps": 61455, "total_steps": 64460, "loss": 0.0701, "lr": 6.609869438005567e-08, "epoch": 19.06763884579584, "percentage": 95.34, "elapsed_time": "1:53:51", "remaining_time": "0:05:34", "throughput": 5479.08, "total_tokens": 37431744} {"current_steps": 61460, "total_steps": 64460, "loss": 0.1991, "lr": 6.587947180201004e-08, "epoch": 19.06919019547006, "percentage": 95.35, "elapsed_time": "1:53:52", "remaining_time": "0:05:33", "throughput": 5479.12, "total_tokens": 37434656} {"current_steps": 61465, "total_steps": 64460, "loss": 0.1143, "lr": 6.566061095342857e-08, "epoch": 19.070741545144276, "percentage": 95.35, "elapsed_time": "1:53:52", "remaining_time": "0:05:32", "throughput": 5479.14, "total_tokens": 37437664} {"current_steps": 61470, "total_steps": 64460, "loss": 0.1604, "lr": 6.544211185035454e-08, "epoch": 19.072292894818492, "percentage": 95.36, "elapsed_time": "1:53:53", "remaining_time": "0:05:32", "throughput": 5479.22, "total_tokens": 37441600} {"current_steps": 61475, "total_steps": 64460, "loss": 0.1131, "lr": 6.522397450880901e-08, "epoch": 19.073844244492708, "percentage": 95.37, "elapsed_time": "1:53:53", "remaining_time": "0:05:31", "throughput": 5479.18, "total_tokens": 37443872} {"current_steps": 61480, "total_steps": 64460, "loss": 0.1381, "lr": 6.500619894478145e-08, "epoch": 19.075395594166924, "percentage": 95.38, "elapsed_time": "1:53:54", "remaining_time": "0:05:31", "throughput": 5479.2, "total_tokens": 37446880} {"current_steps": 61485, "total_steps": 64460, "loss": 0.076, "lr": 6.478878517423959e-08, "epoch": 19.076946943841143, "percentage": 95.38, "elapsed_time": "1:53:54", "remaining_time": "0:05:30", "throughput": 5479.14, "total_tokens": 37449216} {"current_steps": 61490, "total_steps": 64460, "loss": 0.1945, "lr": 6.457173321312072e-08, "epoch": 19.07849829351536, "percentage": 95.39, "elapsed_time": "1:53:55", "remaining_time": "0:05:30", "throughput": 5479.14, "total_tokens": 37452096} {"current_steps": 61495, "total_steps": 64460, "loss": 0.1411, "lr": 6.435504307733819e-08, "epoch": 19.080049643189575, "percentage": 95.4, "elapsed_time": "1:53:55", "remaining_time": "0:05:29", "throughput": 5479.21, "total_tokens": 37455616} {"current_steps": 61500, "total_steps": 64460, "loss": 0.2795, "lr": 6.413871478277766e-08, "epoch": 19.08160099286379, "percentage": 95.41, "elapsed_time": "1:53:56", "remaining_time": "0:05:29", "throughput": 5479.22, "total_tokens": 37458624} {"current_steps": 61505, "total_steps": 64460, "loss": 0.1672, "lr": 6.392274834529865e-08, "epoch": 19.083152342538007, "percentage": 95.42, "elapsed_time": "1:53:57", "remaining_time": "0:05:28", "throughput": 5479.24, "total_tokens": 37461568} {"current_steps": 61510, "total_steps": 64460, "loss": 0.0909, "lr": 6.370714378073406e-08, "epoch": 19.084703692212226, "percentage": 95.42, "elapsed_time": "1:53:57", "remaining_time": "0:05:27", "throughput": 5479.24, "total_tokens": 37464832} {"current_steps": 61515, "total_steps": 64460, "loss": 0.1376, "lr": 6.349190110489068e-08, "epoch": 19.086255041886442, "percentage": 95.43, "elapsed_time": "1:53:58", "remaining_time": "0:05:27", "throughput": 5479.22, "total_tokens": 37467680} {"current_steps": 61520, "total_steps": 64460, "loss": 0.1961, "lr": 6.327702033354754e-08, "epoch": 19.087806391560658, "percentage": 95.44, "elapsed_time": "1:53:58", "remaining_time": "0:05:26", "throughput": 5479.31, "total_tokens": 37471744} {"current_steps": 61525, "total_steps": 64460, "loss": 0.1559, "lr": 6.306250148245873e-08, "epoch": 19.089357741234874, "percentage": 95.45, "elapsed_time": "1:53:59", "remaining_time": "0:05:26", "throughput": 5479.27, "total_tokens": 37474272} {"current_steps": 61530, "total_steps": 64460, "loss": 0.2283, "lr": 6.284834456735001e-08, "epoch": 19.09090909090909, "percentage": 95.45, "elapsed_time": "1:53:59", "remaining_time": "0:05:25", "throughput": 5479.34, "total_tokens": 37478240} {"current_steps": 61535, "total_steps": 64460, "loss": 0.1241, "lr": 6.263454960392324e-08, "epoch": 19.092460440583306, "percentage": 95.46, "elapsed_time": "1:54:00", "remaining_time": "0:05:25", "throughput": 5479.45, "total_tokens": 37482528} {"current_steps": 61540, "total_steps": 64460, "loss": 0.1297, "lr": 6.242111660785034e-08, "epoch": 19.094011790257525, "percentage": 95.47, "elapsed_time": "1:54:01", "remaining_time": "0:05:24", "throughput": 5479.42, "total_tokens": 37484864} {"current_steps": 61545, "total_steps": 64460, "loss": 0.1782, "lr": 6.220804559477934e-08, "epoch": 19.09556313993174, "percentage": 95.48, "elapsed_time": "1:54:01", "remaining_time": "0:05:24", "throughput": 5479.38, "total_tokens": 37487648} {"current_steps": 61550, "total_steps": 64460, "loss": 0.1663, "lr": 6.199533658033108e-08, "epoch": 19.097114489605957, "percentage": 95.49, "elapsed_time": "1:54:02", "remaining_time": "0:05:23", "throughput": 5479.44, "total_tokens": 37491168} {"current_steps": 61555, "total_steps": 64460, "loss": 0.1544, "lr": 6.17829895800992e-08, "epoch": 19.098665839280173, "percentage": 95.49, "elapsed_time": "1:54:02", "remaining_time": "0:05:22", "throughput": 5479.49, "total_tokens": 37495072} {"current_steps": 61560, "total_steps": 64460, "loss": 0.1778, "lr": 6.157100460965182e-08, "epoch": 19.10021718895439, "percentage": 95.5, "elapsed_time": "1:54:03", "remaining_time": "0:05:22", "throughput": 5479.53, "total_tokens": 37498496} {"current_steps": 61565, "total_steps": 64460, "loss": 0.1376, "lr": 6.13593816845287e-08, "epoch": 19.10176853862861, "percentage": 95.51, "elapsed_time": "1:54:03", "remaining_time": "0:05:21", "throughput": 5479.6, "total_tokens": 37501792} {"current_steps": 61570, "total_steps": 64460, "loss": 0.1635, "lr": 6.114812082024635e-08, "epoch": 19.103319888302824, "percentage": 95.52, "elapsed_time": "1:54:04", "remaining_time": "0:05:21", "throughput": 5479.62, "total_tokens": 37504800} {"current_steps": 61575, "total_steps": 64460, "loss": 0.1642, "lr": 6.093722203229069e-08, "epoch": 19.10487123797704, "percentage": 95.52, "elapsed_time": "1:54:04", "remaining_time": "0:05:20", "throughput": 5479.57, "total_tokens": 37507360} {"current_steps": 61580, "total_steps": 64460, "loss": 0.1778, "lr": 6.07266853361238e-08, "epoch": 19.106422587651256, "percentage": 95.53, "elapsed_time": "1:54:05", "remaining_time": "0:05:20", "throughput": 5479.55, "total_tokens": 37509920} {"current_steps": 61585, "total_steps": 64460, "loss": 0.1447, "lr": 6.051651074718112e-08, "epoch": 19.107973937325472, "percentage": 95.54, "elapsed_time": "1:54:05", "remaining_time": "0:05:19", "throughput": 5479.55, "total_tokens": 37512608} {"current_steps": 61590, "total_steps": 64460, "loss": 0.1357, "lr": 6.030669828087033e-08, "epoch": 19.10952528699969, "percentage": 95.55, "elapsed_time": "1:54:06", "remaining_time": "0:05:19", "throughput": 5479.59, "total_tokens": 37515552} {"current_steps": 61595, "total_steps": 64460, "loss": 0.1365, "lr": 6.0097247952573e-08, "epoch": 19.111076636673907, "percentage": 95.56, "elapsed_time": "1:54:06", "remaining_time": "0:05:18", "throughput": 5479.59, "total_tokens": 37518112} {"current_steps": 61600, "total_steps": 64460, "loss": 0.1269, "lr": 5.988815977764461e-08, "epoch": 19.112627986348123, "percentage": 95.56, "elapsed_time": "1:54:07", "remaining_time": "0:05:17", "throughput": 5479.62, "total_tokens": 37521440} {"current_steps": 61605, "total_steps": 64460, "loss": 0.1251, "lr": 5.967943377141405e-08, "epoch": 19.11417933602234, "percentage": 95.57, "elapsed_time": "1:54:07", "remaining_time": "0:05:17", "throughput": 5479.64, "total_tokens": 37524224} {"current_steps": 61610, "total_steps": 64460, "loss": 0.2131, "lr": 5.9471069949182946e-08, "epoch": 19.115730685696555, "percentage": 95.58, "elapsed_time": "1:54:08", "remaining_time": "0:05:16", "throughput": 5479.62, "total_tokens": 37526592} {"current_steps": 61615, "total_steps": 64460, "loss": 0.0945, "lr": 5.926306832622686e-08, "epoch": 19.117282035370774, "percentage": 95.59, "elapsed_time": "1:54:08", "remaining_time": "0:05:16", "throughput": 5479.63, "total_tokens": 37529536} {"current_steps": 61620, "total_steps": 64460, "loss": 0.1344, "lr": 5.905542891779526e-08, "epoch": 19.11883338504499, "percentage": 95.59, "elapsed_time": "1:54:09", "remaining_time": "0:05:15", "throughput": 5479.78, "total_tokens": 37534272} {"current_steps": 61625, "total_steps": 64460, "loss": 0.1451, "lr": 5.8848151739110405e-08, "epoch": 19.120384734719206, "percentage": 95.6, "elapsed_time": "1:54:10", "remaining_time": "0:05:15", "throughput": 5479.74, "total_tokens": 37536512} {"current_steps": 61630, "total_steps": 64460, "loss": 0.1229, "lr": 5.8641236805367375e-08, "epoch": 19.121936084393422, "percentage": 95.61, "elapsed_time": "1:54:10", "remaining_time": "0:05:14", "throughput": 5479.75, "total_tokens": 37539424} {"current_steps": 61635, "total_steps": 64460, "loss": 0.1481, "lr": 5.843468413173681e-08, "epoch": 19.123487434067638, "percentage": 95.62, "elapsed_time": "1:54:11", "remaining_time": "0:05:14", "throughput": 5479.83, "total_tokens": 37543040} {"current_steps": 61640, "total_steps": 64460, "loss": 0.0936, "lr": 5.822849373336048e-08, "epoch": 19.125038783741857, "percentage": 95.63, "elapsed_time": "1:54:11", "remaining_time": "0:05:13", "throughput": 5479.82, "total_tokens": 37545952} {"current_steps": 61645, "total_steps": 64460, "loss": 0.1079, "lr": 5.802266562535519e-08, "epoch": 19.126590133416073, "percentage": 95.63, "elapsed_time": "1:54:12", "remaining_time": "0:05:12", "throughput": 5479.75, "total_tokens": 37548224} {"current_steps": 61650, "total_steps": 64460, "loss": 0.1762, "lr": 5.781719982280998e-08, "epoch": 19.12814148309029, "percentage": 95.64, "elapsed_time": "1:54:12", "remaining_time": "0:05:12", "throughput": 5479.88, "total_tokens": 37552640} {"current_steps": 61655, "total_steps": 64460, "loss": 0.1571, "lr": 5.761209634078835e-08, "epoch": 19.129692832764505, "percentage": 95.65, "elapsed_time": "1:54:13", "remaining_time": "0:05:11", "throughput": 5479.85, "total_tokens": 37555200} {"current_steps": 61660, "total_steps": 64460, "loss": 0.2221, "lr": 5.7407355194326606e-08, "epoch": 19.13124418243872, "percentage": 95.66, "elapsed_time": "1:54:13", "remaining_time": "0:05:11", "throughput": 5479.83, "total_tokens": 37557792} {"current_steps": 61665, "total_steps": 64460, "loss": 0.0638, "lr": 5.720297639843442e-08, "epoch": 19.132795532112937, "percentage": 95.66, "elapsed_time": "1:54:14", "remaining_time": "0:05:10", "throughput": 5479.81, "total_tokens": 37560544} {"current_steps": 61670, "total_steps": 64460, "loss": 0.1394, "lr": 5.69989599680959e-08, "epoch": 19.134346881787156, "percentage": 95.67, "elapsed_time": "1:54:14", "remaining_time": "0:05:10", "throughput": 5479.84, "total_tokens": 37563680} {"current_steps": 61675, "total_steps": 64460, "loss": 0.1873, "lr": 5.679530591826743e-08, "epoch": 19.135898231461372, "percentage": 95.68, "elapsed_time": "1:54:15", "remaining_time": "0:05:09", "throughput": 5479.88, "total_tokens": 37566880} {"current_steps": 61680, "total_steps": 64460, "loss": 0.0911, "lr": 5.659201426387983e-08, "epoch": 19.137449581135588, "percentage": 95.69, "elapsed_time": "1:54:15", "remaining_time": "0:05:09", "throughput": 5479.85, "total_tokens": 37569504} {"current_steps": 61685, "total_steps": 64460, "loss": 0.1973, "lr": 5.6389085019835646e-08, "epoch": 19.139000930809804, "percentage": 95.7, "elapsed_time": "1:54:16", "remaining_time": "0:05:08", "throughput": 5479.93, "total_tokens": 37573376} {"current_steps": 61690, "total_steps": 64460, "loss": 0.2196, "lr": 5.618651820101295e-08, "epoch": 19.14055228048402, "percentage": 95.7, "elapsed_time": "1:54:17", "remaining_time": "0:05:07", "throughput": 5479.94, "total_tokens": 37576224} {"current_steps": 61695, "total_steps": 64460, "loss": 0.1566, "lr": 5.598431382226155e-08, "epoch": 19.14210363015824, "percentage": 95.71, "elapsed_time": "1:54:17", "remaining_time": "0:05:07", "throughput": 5480.04, "total_tokens": 37580960} {"current_steps": 61700, "total_steps": 64460, "loss": 0.1333, "lr": 5.578247189840624e-08, "epoch": 19.143654979832455, "percentage": 95.72, "elapsed_time": "1:54:18", "remaining_time": "0:05:06", "throughput": 5480.1, "total_tokens": 37584768} {"current_steps": 61705, "total_steps": 64460, "loss": 0.1115, "lr": 5.558099244424409e-08, "epoch": 19.14520632950667, "percentage": 95.73, "elapsed_time": "1:54:18", "remaining_time": "0:05:06", "throughput": 5480.1, "total_tokens": 37587360} {"current_steps": 61710, "total_steps": 64460, "loss": 0.1118, "lr": 5.537987547454604e-08, "epoch": 19.146757679180887, "percentage": 95.73, "elapsed_time": "1:54:19", "remaining_time": "0:05:05", "throughput": 5480.12, "total_tokens": 37590368} {"current_steps": 61715, "total_steps": 64460, "loss": 0.1267, "lr": 5.517912100405587e-08, "epoch": 19.148309028855103, "percentage": 95.74, "elapsed_time": "1:54:19", "remaining_time": "0:05:05", "throughput": 5480.07, "total_tokens": 37592608} {"current_steps": 61720, "total_steps": 64460, "loss": 0.1398, "lr": 5.497872904749124e-08, "epoch": 19.149860378529322, "percentage": 95.75, "elapsed_time": "1:54:20", "remaining_time": "0:05:04", "throughput": 5480.13, "total_tokens": 37595840} {"current_steps": 61725, "total_steps": 64460, "loss": 0.1537, "lr": 5.477869961954429e-08, "epoch": 19.151411728203538, "percentage": 95.76, "elapsed_time": "1:54:20", "remaining_time": "0:05:04", "throughput": 5480.15, "total_tokens": 37599200} {"current_steps": 61730, "total_steps": 64460, "loss": 0.1108, "lr": 5.45790327348783e-08, "epoch": 19.152963077877754, "percentage": 95.76, "elapsed_time": "1:54:21", "remaining_time": "0:05:03", "throughput": 5480.11, "total_tokens": 37601696} {"current_steps": 61735, "total_steps": 64460, "loss": 0.1392, "lr": 5.4379728408132106e-08, "epoch": 19.15451442755197, "percentage": 95.77, "elapsed_time": "1:54:22", "remaining_time": "0:05:02", "throughput": 5480.15, "total_tokens": 37604832} {"current_steps": 61740, "total_steps": 64460, "loss": 0.2222, "lr": 5.4180786653916237e-08, "epoch": 19.156065777226186, "percentage": 95.78, "elapsed_time": "1:54:22", "remaining_time": "0:05:02", "throughput": 5480.21, "total_tokens": 37608128} {"current_steps": 61745, "total_steps": 64460, "loss": 0.1796, "lr": 5.398220748681682e-08, "epoch": 19.157617126900405, "percentage": 95.79, "elapsed_time": "1:54:22", "remaining_time": "0:05:01", "throughput": 5480.21, "total_tokens": 37610656} {"current_steps": 61750, "total_steps": 64460, "loss": 0.2033, "lr": 5.3783990921390526e-08, "epoch": 19.15916847657462, "percentage": 95.8, "elapsed_time": "1:54:23", "remaining_time": "0:05:01", "throughput": 5480.19, "total_tokens": 37613248} {"current_steps": 61755, "total_steps": 64460, "loss": 0.245, "lr": 5.3586136972169636e-08, "epoch": 19.160719826248837, "percentage": 95.8, "elapsed_time": "1:54:23", "remaining_time": "0:05:00", "throughput": 5480.14, "total_tokens": 37615552} {"current_steps": 61760, "total_steps": 64460, "loss": 0.1538, "lr": 5.33886456536592e-08, "epoch": 19.162271175923053, "percentage": 95.81, "elapsed_time": "1:54:24", "remaining_time": "0:05:00", "throughput": 5480.11, "total_tokens": 37618304} {"current_steps": 61765, "total_steps": 64460, "loss": 0.0934, "lr": 5.31915169803382e-08, "epoch": 19.16382252559727, "percentage": 95.82, "elapsed_time": "1:54:25", "remaining_time": "0:04:59", "throughput": 5480.19, "total_tokens": 37622432} {"current_steps": 61770, "total_steps": 64460, "loss": 0.1995, "lr": 5.299475096665785e-08, "epoch": 19.165373875271488, "percentage": 95.83, "elapsed_time": "1:54:25", "remaining_time": "0:04:58", "throughput": 5480.16, "total_tokens": 37624800} {"current_steps": 61775, "total_steps": 64460, "loss": 0.1605, "lr": 5.279834762704328e-08, "epoch": 19.166925224945704, "percentage": 95.83, "elapsed_time": "1:54:26", "remaining_time": "0:04:58", "throughput": 5480.11, "total_tokens": 37627072} {"current_steps": 61780, "total_steps": 64460, "loss": 0.1363, "lr": 5.260230697589353e-08, "epoch": 19.16847657461992, "percentage": 95.84, "elapsed_time": "1:54:26", "remaining_time": "0:04:57", "throughput": 5480.16, "total_tokens": 37630784} {"current_steps": 61785, "total_steps": 64460, "loss": 0.1188, "lr": 5.2406629027580423e-08, "epoch": 19.170027924294136, "percentage": 95.85, "elapsed_time": "1:54:27", "remaining_time": "0:04:57", "throughput": 5480.19, "total_tokens": 37633728} {"current_steps": 61790, "total_steps": 64460, "loss": 0.0775, "lr": 5.221131379645028e-08, "epoch": 19.17157927396835, "percentage": 95.86, "elapsed_time": "1:54:27", "remaining_time": "0:04:56", "throughput": 5480.28, "total_tokens": 37637824} {"current_steps": 61795, "total_steps": 64460, "loss": 0.1195, "lr": 5.201636129682053e-08, "epoch": 19.173130623642567, "percentage": 95.87, "elapsed_time": "1:54:28", "remaining_time": "0:04:56", "throughput": 5480.24, "total_tokens": 37640448} {"current_steps": 61800, "total_steps": 64460, "loss": 0.2551, "lr": 5.182177154298529e-08, "epoch": 19.174681973316787, "percentage": 95.87, "elapsed_time": "1:54:29", "remaining_time": "0:04:55", "throughput": 5480.32, "total_tokens": 37644640} {"current_steps": 61805, "total_steps": 64460, "loss": 0.113, "lr": 5.162754454920871e-08, "epoch": 19.176233322991003, "percentage": 95.88, "elapsed_time": "1:54:29", "remaining_time": "0:04:55", "throughput": 5480.25, "total_tokens": 37647168} {"current_steps": 61810, "total_steps": 64460, "loss": 0.1135, "lr": 5.143368032973106e-08, "epoch": 19.17778467266522, "percentage": 95.89, "elapsed_time": "1:54:30", "remaining_time": "0:04:54", "throughput": 5480.26, "total_tokens": 37650432} {"current_steps": 61815, "total_steps": 64460, "loss": 0.1031, "lr": 5.124017889876431e-08, "epoch": 19.179336022339434, "percentage": 95.9, "elapsed_time": "1:54:30", "remaining_time": "0:04:53", "throughput": 5480.26, "total_tokens": 37653888} {"current_steps": 61820, "total_steps": 64460, "loss": 0.1715, "lr": 5.104704027049434e-08, "epoch": 19.18088737201365, "percentage": 95.9, "elapsed_time": "1:54:31", "remaining_time": "0:04:53", "throughput": 5480.2, "total_tokens": 37656352} {"current_steps": 61825, "total_steps": 64460, "loss": 0.1492, "lr": 5.0854264459080923e-08, "epoch": 19.18243872168787, "percentage": 95.91, "elapsed_time": "1:54:31", "remaining_time": "0:04:52", "throughput": 5480.18, "total_tokens": 37659040} {"current_steps": 61830, "total_steps": 64460, "loss": 0.1625, "lr": 5.0661851478656654e-08, "epoch": 19.183990071362086, "percentage": 95.92, "elapsed_time": "1:54:32", "remaining_time": "0:04:52", "throughput": 5480.24, "total_tokens": 37662336} {"current_steps": 61835, "total_steps": 64460, "loss": 0.1106, "lr": 5.046980134332746e-08, "epoch": 19.1855414210363, "percentage": 95.93, "elapsed_time": "1:54:32", "remaining_time": "0:04:51", "throughput": 5480.24, "total_tokens": 37665344} {"current_steps": 61840, "total_steps": 64460, "loss": 0.0613, "lr": 5.027811406717264e-08, "epoch": 19.187092770710517, "percentage": 95.94, "elapsed_time": "1:54:33", "remaining_time": "0:04:51", "throughput": 5480.31, "total_tokens": 37668800} {"current_steps": 61845, "total_steps": 64460, "loss": 0.1797, "lr": 5.008678966424652e-08, "epoch": 19.188644120384733, "percentage": 95.94, "elapsed_time": "1:54:34", "remaining_time": "0:04:50", "throughput": 5480.33, "total_tokens": 37671840} {"current_steps": 61850, "total_steps": 64460, "loss": 0.2057, "lr": 4.9895828148573414e-08, "epoch": 19.190195470058953, "percentage": 95.95, "elapsed_time": "1:54:34", "remaining_time": "0:04:50", "throughput": 5480.32, "total_tokens": 37674656} {"current_steps": 61855, "total_steps": 64460, "loss": 0.0753, "lr": 4.970522953415491e-08, "epoch": 19.19174681973317, "percentage": 95.96, "elapsed_time": "1:54:35", "remaining_time": "0:04:49", "throughput": 5480.31, "total_tokens": 37677408} {"current_steps": 61860, "total_steps": 64460, "loss": 0.0402, "lr": 4.9514993834962613e-08, "epoch": 19.193298169407385, "percentage": 95.97, "elapsed_time": "1:54:35", "remaining_time": "0:04:48", "throughput": 5480.21, "total_tokens": 37679680} {"current_steps": 61865, "total_steps": 64460, "loss": 0.1904, "lr": 4.932512106494425e-08, "epoch": 19.1948495190816, "percentage": 95.97, "elapsed_time": "1:54:36", "remaining_time": "0:04:48", "throughput": 5480.15, "total_tokens": 37682144} {"current_steps": 61870, "total_steps": 64460, "loss": 0.3076, "lr": 4.9135611238019245e-08, "epoch": 19.196400868755816, "percentage": 95.98, "elapsed_time": "1:54:36", "remaining_time": "0:04:47", "throughput": 5480.13, "total_tokens": 37684576} {"current_steps": 61875, "total_steps": 64460, "loss": 0.1572, "lr": 4.894646436808092e-08, "epoch": 19.197952218430036, "percentage": 95.99, "elapsed_time": "1:54:37", "remaining_time": "0:04:47", "throughput": 5480.18, "total_tokens": 37687552} {"current_steps": 61880, "total_steps": 64460, "loss": 0.1094, "lr": 4.8757680468995985e-08, "epoch": 19.19950356810425, "percentage": 96.0, "elapsed_time": "1:54:37", "remaining_time": "0:04:46", "throughput": 5480.21, "total_tokens": 37690464} {"current_steps": 61885, "total_steps": 64460, "loss": 0.148, "lr": 4.8569259554604453e-08, "epoch": 19.201054917778468, "percentage": 96.01, "elapsed_time": "1:54:38", "remaining_time": "0:04:46", "throughput": 5480.24, "total_tokens": 37694176} {"current_steps": 61890, "total_steps": 64460, "loss": 0.1613, "lr": 4.8381201638719735e-08, "epoch": 19.202606267452683, "percentage": 96.01, "elapsed_time": "1:54:38", "remaining_time": "0:04:45", "throughput": 5480.26, "total_tokens": 37697184} {"current_steps": 61895, "total_steps": 64460, "loss": 0.1508, "lr": 4.819350673512968e-08, "epoch": 19.2041576171269, "percentage": 96.02, "elapsed_time": "1:54:39", "remaining_time": "0:04:45", "throughput": 5480.32, "total_tokens": 37700768} {"current_steps": 61900, "total_steps": 64460, "loss": 0.2029, "lr": 4.800617485759274e-08, "epoch": 19.20570896680112, "percentage": 96.03, "elapsed_time": "1:54:39", "remaining_time": "0:04:44", "throughput": 5480.33, "total_tokens": 37703520} {"current_steps": 61905, "total_steps": 64460, "loss": 0.1575, "lr": 4.781920601984402e-08, "epoch": 19.207260316475335, "percentage": 96.04, "elapsed_time": "1:54:40", "remaining_time": "0:04:43", "throughput": 5480.35, "total_tokens": 37706496} {"current_steps": 61910, "total_steps": 64460, "loss": 0.1719, "lr": 4.7632600235590354e-08, "epoch": 19.20881166614955, "percentage": 96.04, "elapsed_time": "1:54:40", "remaining_time": "0:04:43", "throughput": 5480.31, "total_tokens": 37709248} {"current_steps": 61915, "total_steps": 64460, "loss": 0.1065, "lr": 4.744635751851134e-08, "epoch": 19.210363015823766, "percentage": 96.05, "elapsed_time": "1:54:41", "remaining_time": "0:04:42", "throughput": 5480.32, "total_tokens": 37712384} {"current_steps": 61920, "total_steps": 64460, "loss": 0.1241, "lr": 4.726047788226162e-08, "epoch": 19.211914365497982, "percentage": 96.06, "elapsed_time": "1:54:41", "remaining_time": "0:04:42", "throughput": 5480.42, "total_tokens": 37716000} {"current_steps": 61925, "total_steps": 64460, "loss": 0.1846, "lr": 4.707496134046807e-08, "epoch": 19.213465715172198, "percentage": 96.07, "elapsed_time": "1:54:42", "remaining_time": "0:04:41", "throughput": 5480.49, "total_tokens": 37719872} {"current_steps": 61930, "total_steps": 64460, "loss": 0.1732, "lr": 4.688980790673148e-08, "epoch": 19.215017064846418, "percentage": 96.08, "elapsed_time": "1:54:43", "remaining_time": "0:04:41", "throughput": 5480.48, "total_tokens": 37722720} {"current_steps": 61935, "total_steps": 64460, "loss": 0.2022, "lr": 4.670501759462542e-08, "epoch": 19.216568414520633, "percentage": 96.08, "elapsed_time": "1:54:43", "remaining_time": "0:04:40", "throughput": 5480.55, "total_tokens": 37726240} {"current_steps": 61940, "total_steps": 64460, "loss": 0.1233, "lr": 4.652059041769741e-08, "epoch": 19.21811976419485, "percentage": 96.09, "elapsed_time": "1:54:44", "remaining_time": "0:04:40", "throughput": 5480.56, "total_tokens": 37728960} {"current_steps": 61945, "total_steps": 64460, "loss": 0.1664, "lr": 4.633652638946773e-08, "epoch": 19.219671113869065, "percentage": 96.1, "elapsed_time": "1:54:44", "remaining_time": "0:04:39", "throughput": 5480.56, "total_tokens": 37731552} {"current_steps": 61950, "total_steps": 64460, "loss": 0.156, "lr": 4.615282552343115e-08, "epoch": 19.22122246354328, "percentage": 96.11, "elapsed_time": "1:54:45", "remaining_time": "0:04:38", "throughput": 5480.52, "total_tokens": 37733920} {"current_steps": 61955, "total_steps": 64460, "loss": 0.1831, "lr": 4.596948783305466e-08, "epoch": 19.2227738132175, "percentage": 96.11, "elapsed_time": "1:54:45", "remaining_time": "0:04:38", "throughput": 5480.61, "total_tokens": 37737664} {"current_steps": 61960, "total_steps": 64460, "loss": 0.1467, "lr": 4.578651333177919e-08, "epoch": 19.224325162891716, "percentage": 96.12, "elapsed_time": "1:54:46", "remaining_time": "0:04:37", "throughput": 5480.65, "total_tokens": 37740832} {"current_steps": 61965, "total_steps": 64460, "loss": 0.1717, "lr": 4.560390203301901e-08, "epoch": 19.225876512565932, "percentage": 96.13, "elapsed_time": "1:54:46", "remaining_time": "0:04:37", "throughput": 5480.72, "total_tokens": 37744864} {"current_steps": 61970, "total_steps": 64460, "loss": 0.1946, "lr": 4.5421653950161736e-08, "epoch": 19.227427862240148, "percentage": 96.14, "elapsed_time": "1:54:47", "remaining_time": "0:04:36", "throughput": 5480.72, "total_tokens": 37747552} {"current_steps": 61975, "total_steps": 64460, "loss": 0.1669, "lr": 4.52397690965678e-08, "epoch": 19.228979211914364, "percentage": 96.14, "elapsed_time": "1:54:47", "remaining_time": "0:04:36", "throughput": 5480.75, "total_tokens": 37750656} {"current_steps": 61980, "total_steps": 64460, "loss": 0.1399, "lr": 4.505824748557208e-08, "epoch": 19.230530561588584, "percentage": 96.15, "elapsed_time": "1:54:48", "remaining_time": "0:04:35", "throughput": 5480.76, "total_tokens": 37753472} {"current_steps": 61985, "total_steps": 64460, "loss": 0.1837, "lr": 4.487708913048283e-08, "epoch": 19.2320819112628, "percentage": 96.16, "elapsed_time": "1:54:48", "remaining_time": "0:04:35", "throughput": 5480.8, "total_tokens": 37757216} {"current_steps": 61990, "total_steps": 64460, "loss": 0.1569, "lr": 4.469629404457942e-08, "epoch": 19.233633260937015, "percentage": 96.17, "elapsed_time": "1:54:49", "remaining_time": "0:04:34", "throughput": 5480.92, "total_tokens": 37761920} {"current_steps": 61995, "total_steps": 64460, "loss": 0.2018, "lr": 4.451586224111792e-08, "epoch": 19.23518461061123, "percentage": 96.18, "elapsed_time": "1:54:50", "remaining_time": "0:04:33", "throughput": 5481.0, "total_tokens": 37765536} {"current_steps": 62000, "total_steps": 64460, "loss": 0.1989, "lr": 4.433579373332497e-08, "epoch": 19.236735960285447, "percentage": 96.18, "elapsed_time": "1:54:50", "remaining_time": "0:04:33", "throughput": 5480.96, "total_tokens": 37767968} {"current_steps": 62005, "total_steps": 64460, "loss": 0.2251, "lr": 4.4156088534402784e-08, "epoch": 19.238287309959667, "percentage": 96.19, "elapsed_time": "1:54:51", "remaining_time": "0:04:32", "throughput": 5481.0, "total_tokens": 37771296} {"current_steps": 62010, "total_steps": 64460, "loss": 0.2497, "lr": 4.397674665752471e-08, "epoch": 19.239838659633882, "percentage": 96.2, "elapsed_time": "1:54:51", "remaining_time": "0:04:32", "throughput": 5480.99, "total_tokens": 37774112} {"current_steps": 62015, "total_steps": 64460, "loss": 0.1479, "lr": 4.379776811583913e-08, "epoch": 19.2413900093081, "percentage": 96.21, "elapsed_time": "1:54:52", "remaining_time": "0:04:31", "throughput": 5481.0, "total_tokens": 37777120} {"current_steps": 62020, "total_steps": 64460, "loss": 0.0929, "lr": 4.3619152922467766e-08, "epoch": 19.242941358982314, "percentage": 96.21, "elapsed_time": "1:54:52", "remaining_time": "0:04:31", "throughput": 5481.0, "total_tokens": 37779744} {"current_steps": 62025, "total_steps": 64460, "loss": 0.0846, "lr": 4.344090109050403e-08, "epoch": 19.24449270865653, "percentage": 96.22, "elapsed_time": "1:54:53", "remaining_time": "0:04:30", "throughput": 5480.96, "total_tokens": 37782272} {"current_steps": 62030, "total_steps": 64460, "loss": 0.1171, "lr": 4.3263012633017466e-08, "epoch": 19.24604405833075, "percentage": 96.23, "elapsed_time": "1:54:53", "remaining_time": "0:04:30", "throughput": 5481.01, "total_tokens": 37785632} {"current_steps": 62035, "total_steps": 64460, "loss": 0.0943, "lr": 4.308548756304876e-08, "epoch": 19.247595408004965, "percentage": 96.24, "elapsed_time": "1:54:54", "remaining_time": "0:04:29", "throughput": 5481.04, "total_tokens": 37788800} {"current_steps": 62040, "total_steps": 64460, "loss": 0.1894, "lr": 4.2908325893611935e-08, "epoch": 19.24914675767918, "percentage": 96.25, "elapsed_time": "1:54:54", "remaining_time": "0:04:28", "throughput": 5481.03, "total_tokens": 37791552} {"current_steps": 62045, "total_steps": 64460, "loss": 0.089, "lr": 4.273152763769606e-08, "epoch": 19.250698107353397, "percentage": 96.25, "elapsed_time": "1:54:55", "remaining_time": "0:04:28", "throughput": 5481.03, "total_tokens": 37794496} {"current_steps": 62050, "total_steps": 64460, "loss": 0.1837, "lr": 4.255509280826187e-08, "epoch": 19.252249457027613, "percentage": 96.26, "elapsed_time": "1:54:56", "remaining_time": "0:04:27", "throughput": 5481.1, "total_tokens": 37798080} {"current_steps": 62055, "total_steps": 64460, "loss": 0.1083, "lr": 4.237902141824401e-08, "epoch": 19.25380080670183, "percentage": 96.27, "elapsed_time": "1:54:56", "remaining_time": "0:04:27", "throughput": 5481.09, "total_tokens": 37800736} {"current_steps": 62060, "total_steps": 64460, "loss": 0.1667, "lr": 4.220331348055107e-08, "epoch": 19.25535215637605, "percentage": 96.28, "elapsed_time": "1:54:57", "remaining_time": "0:04:26", "throughput": 5481.07, "total_tokens": 37803456} {"current_steps": 62065, "total_steps": 64460, "loss": 0.1181, "lr": 4.2027969008064387e-08, "epoch": 19.256903506050264, "percentage": 96.28, "elapsed_time": "1:54:57", "remaining_time": "0:04:26", "throughput": 5481.11, "total_tokens": 37806560} {"current_steps": 62070, "total_steps": 64460, "loss": 0.1806, "lr": 4.185298801363869e-08, "epoch": 19.25845485572448, "percentage": 96.29, "elapsed_time": "1:54:58", "remaining_time": "0:04:25", "throughput": 5481.19, "total_tokens": 37810112} {"current_steps": 62075, "total_steps": 64460, "loss": 0.1234, "lr": 4.167837051010204e-08, "epoch": 19.260006205398696, "percentage": 96.3, "elapsed_time": "1:54:58", "remaining_time": "0:04:25", "throughput": 5481.23, "total_tokens": 37813248} {"current_steps": 62080, "total_steps": 64460, "loss": 0.1752, "lr": 4.150411651025643e-08, "epoch": 19.261557555072912, "percentage": 96.31, "elapsed_time": "1:54:59", "remaining_time": "0:04:24", "throughput": 5481.28, "total_tokens": 37816864} {"current_steps": 62085, "total_steps": 64460, "loss": 0.2126, "lr": 4.133022602687664e-08, "epoch": 19.26310890474713, "percentage": 96.32, "elapsed_time": "1:54:59", "remaining_time": "0:04:23", "throughput": 5481.42, "total_tokens": 37821600} {"current_steps": 62090, "total_steps": 64460, "loss": 0.1655, "lr": 4.115669907271025e-08, "epoch": 19.264660254421347, "percentage": 96.32, "elapsed_time": "1:55:00", "remaining_time": "0:04:23", "throughput": 5481.31, "total_tokens": 37824224} {"current_steps": 62095, "total_steps": 64460, "loss": 0.1316, "lr": 4.09835356604793e-08, "epoch": 19.266211604095563, "percentage": 96.33, "elapsed_time": "1:55:01", "remaining_time": "0:04:22", "throughput": 5481.37, "total_tokens": 37828448} {"current_steps": 62100, "total_steps": 64460, "loss": 0.0771, "lr": 4.0810735802879196e-08, "epoch": 19.26776295376978, "percentage": 96.34, "elapsed_time": "1:55:01", "remaining_time": "0:04:22", "throughput": 5481.37, "total_tokens": 37831264} {"current_steps": 62105, "total_steps": 64460, "loss": 0.1648, "lr": 4.063829951257758e-08, "epoch": 19.269314303443995, "percentage": 96.35, "elapsed_time": "1:55:02", "remaining_time": "0:04:21", "throughput": 5481.3, "total_tokens": 37833376} {"current_steps": 62110, "total_steps": 64460, "loss": 0.0897, "lr": 4.0466226802216016e-08, "epoch": 19.270865653118214, "percentage": 96.35, "elapsed_time": "1:55:03", "remaining_time": "0:04:21", "throughput": 5481.44, "total_tokens": 37838784} {"current_steps": 62115, "total_steps": 64460, "loss": 0.1579, "lr": 4.029451768440995e-08, "epoch": 19.27241700279243, "percentage": 96.36, "elapsed_time": "1:55:03", "remaining_time": "0:04:20", "throughput": 5481.38, "total_tokens": 37840928} {"current_steps": 62120, "total_steps": 64460, "loss": 0.2596, "lr": 4.0123172171747104e-08, "epoch": 19.273968352466646, "percentage": 96.37, "elapsed_time": "1:55:04", "remaining_time": "0:04:20", "throughput": 5481.4, "total_tokens": 37844032} {"current_steps": 62125, "total_steps": 64460, "loss": 0.1228, "lr": 3.995219027678965e-08, "epoch": 19.275519702140862, "percentage": 96.38, "elapsed_time": "1:55:04", "remaining_time": "0:04:19", "throughput": 5481.44, "total_tokens": 37847392} {"current_steps": 62130, "total_steps": 64460, "loss": 0.1181, "lr": 3.9781572012072556e-08, "epoch": 19.277071051815078, "percentage": 96.39, "elapsed_time": "1:55:05", "remaining_time": "0:04:18", "throughput": 5481.42, "total_tokens": 37849952} {"current_steps": 62135, "total_steps": 64460, "loss": 0.0697, "lr": 3.9611317390104156e-08, "epoch": 19.278622401489297, "percentage": 96.39, "elapsed_time": "1:55:05", "remaining_time": "0:04:18", "throughput": 5481.5, "total_tokens": 37853440} {"current_steps": 62140, "total_steps": 64460, "loss": 0.147, "lr": 3.944142642336557e-08, "epoch": 19.280173751163513, "percentage": 96.4, "elapsed_time": "1:55:06", "remaining_time": "0:04:17", "throughput": 5481.53, "total_tokens": 37856512} {"current_steps": 62145, "total_steps": 64460, "loss": 0.3209, "lr": 3.9271899124312395e-08, "epoch": 19.28172510083773, "percentage": 96.41, "elapsed_time": "1:55:06", "remaining_time": "0:04:17", "throughput": 5481.59, "total_tokens": 37860512} {"current_steps": 62150, "total_steps": 64460, "loss": 0.2613, "lr": 3.910273550537247e-08, "epoch": 19.283276450511945, "percentage": 96.42, "elapsed_time": "1:55:07", "remaining_time": "0:04:16", "throughput": 5481.6, "total_tokens": 37863552} {"current_steps": 62155, "total_steps": 64460, "loss": 0.171, "lr": 3.8933935578948646e-08, "epoch": 19.28482780018616, "percentage": 96.42, "elapsed_time": "1:55:07", "remaining_time": "0:04:16", "throughput": 5481.57, "total_tokens": 37866144} {"current_steps": 62160, "total_steps": 64460, "loss": 0.0826, "lr": 3.876549935741436e-08, "epoch": 19.28637914986038, "percentage": 96.43, "elapsed_time": "1:55:08", "remaining_time": "0:04:15", "throughput": 5481.61, "total_tokens": 37869280} {"current_steps": 62165, "total_steps": 64460, "loss": 0.1037, "lr": 3.859742685311918e-08, "epoch": 19.287930499534596, "percentage": 96.44, "elapsed_time": "1:55:08", "remaining_time": "0:04:15", "throughput": 5481.61, "total_tokens": 37871968} {"current_steps": 62170, "total_steps": 64460, "loss": 0.1911, "lr": 3.842971807838436e-08, "epoch": 19.289481849208812, "percentage": 96.45, "elapsed_time": "1:55:09", "remaining_time": "0:04:14", "throughput": 5481.66, "total_tokens": 37875200} {"current_steps": 62175, "total_steps": 64460, "loss": 0.1288, "lr": 3.826237304550451e-08, "epoch": 19.291033198883028, "percentage": 96.46, "elapsed_time": "1:55:09", "remaining_time": "0:04:13", "throughput": 5481.74, "total_tokens": 37878592} {"current_steps": 62180, "total_steps": 64460, "loss": 0.1758, "lr": 3.809539176674926e-08, "epoch": 19.292584548557244, "percentage": 96.46, "elapsed_time": "1:55:10", "remaining_time": "0:04:13", "throughput": 5481.69, "total_tokens": 37881088} {"current_steps": 62185, "total_steps": 64460, "loss": 0.1524, "lr": 3.792877425435937e-08, "epoch": 19.29413589823146, "percentage": 96.47, "elapsed_time": "1:55:11", "remaining_time": "0:04:12", "throughput": 5481.64, "total_tokens": 37883616} {"current_steps": 62190, "total_steps": 64460, "loss": 0.0974, "lr": 3.776252052055007e-08, "epoch": 19.29568724790568, "percentage": 96.48, "elapsed_time": "1:55:11", "remaining_time": "0:04:12", "throughput": 5481.55, "total_tokens": 37885856} {"current_steps": 62195, "total_steps": 64460, "loss": 0.182, "lr": 3.7596630577509396e-08, "epoch": 19.297238597579895, "percentage": 96.49, "elapsed_time": "1:55:12", "remaining_time": "0:04:11", "throughput": 5481.52, "total_tokens": 37888256} {"current_steps": 62200, "total_steps": 64460, "loss": 0.1816, "lr": 3.743110443739928e-08, "epoch": 19.29878994725411, "percentage": 96.49, "elapsed_time": "1:55:12", "remaining_time": "0:04:11", "throughput": 5481.52, "total_tokens": 37891072} {"current_steps": 62205, "total_steps": 64460, "loss": 0.1055, "lr": 3.7265942112355015e-08, "epoch": 19.300341296928327, "percentage": 96.5, "elapsed_time": "1:55:13", "remaining_time": "0:04:10", "throughput": 5481.61, "total_tokens": 37894848} {"current_steps": 62210, "total_steps": 64460, "loss": 0.0451, "lr": 3.710114361448469e-08, "epoch": 19.301892646602543, "percentage": 96.51, "elapsed_time": "1:55:13", "remaining_time": "0:04:10", "throughput": 5481.75, "total_tokens": 37899648} {"current_steps": 62215, "total_steps": 64460, "loss": 0.175, "lr": 3.6936708955870316e-08, "epoch": 19.303443996276762, "percentage": 96.52, "elapsed_time": "1:55:14", "remaining_time": "0:04:09", "throughput": 5481.73, "total_tokens": 37902336} {"current_steps": 62220, "total_steps": 64460, "loss": 0.1749, "lr": 3.677263814856613e-08, "epoch": 19.304995345950978, "percentage": 96.52, "elapsed_time": "1:55:14", "remaining_time": "0:04:08", "throughput": 5481.75, "total_tokens": 37905056} {"current_steps": 62225, "total_steps": 64460, "loss": 0.189, "lr": 3.6608931204601406e-08, "epoch": 19.306546695625194, "percentage": 96.53, "elapsed_time": "1:55:15", "remaining_time": "0:04:08", "throughput": 5481.76, "total_tokens": 37907648} {"current_steps": 62230, "total_steps": 64460, "loss": 0.1092, "lr": 3.644558813597709e-08, "epoch": 19.30809804529941, "percentage": 96.54, "elapsed_time": "1:55:15", "remaining_time": "0:04:07", "throughput": 5481.73, "total_tokens": 37910048} {"current_steps": 62235, "total_steps": 64460, "loss": 0.0767, "lr": 3.6282608954668616e-08, "epoch": 19.309649394973626, "percentage": 96.55, "elapsed_time": "1:55:16", "remaining_time": "0:04:07", "throughput": 5481.75, "total_tokens": 37912896} {"current_steps": 62240, "total_steps": 64460, "loss": 0.1395, "lr": 3.61199936726242e-08, "epoch": 19.311200744647845, "percentage": 96.56, "elapsed_time": "1:55:16", "remaining_time": "0:04:06", "throughput": 5481.84, "total_tokens": 37916928} {"current_steps": 62245, "total_steps": 64460, "loss": 0.1353, "lr": 3.595774230176541e-08, "epoch": 19.31275209432206, "percentage": 96.56, "elapsed_time": "1:55:17", "remaining_time": "0:04:06", "throughput": 5481.84, "total_tokens": 37919840} {"current_steps": 62250, "total_steps": 64460, "loss": 0.1593, "lr": 3.579585485398662e-08, "epoch": 19.314303443996277, "percentage": 96.57, "elapsed_time": "1:55:17", "remaining_time": "0:04:05", "throughput": 5481.83, "total_tokens": 37922592} {"current_steps": 62255, "total_steps": 64460, "loss": 0.1754, "lr": 3.563433134115723e-08, "epoch": 19.315854793670493, "percentage": 96.58, "elapsed_time": "1:55:18", "remaining_time": "0:04:05", "throughput": 5481.82, "total_tokens": 37925056} {"current_steps": 62260, "total_steps": 64460, "loss": 0.1455, "lr": 3.547317177511777e-08, "epoch": 19.31740614334471, "percentage": 96.59, "elapsed_time": "1:55:18", "remaining_time": "0:04:04", "throughput": 5481.89, "total_tokens": 37928544} {"current_steps": 62265, "total_steps": 64460, "loss": 0.2873, "lr": 3.5312376167684346e-08, "epoch": 19.318957493018928, "percentage": 96.59, "elapsed_time": "1:55:19", "remaining_time": "0:04:03", "throughput": 5481.91, "total_tokens": 37931744} {"current_steps": 62270, "total_steps": 64460, "loss": 0.1283, "lr": 3.5151944530643634e-08, "epoch": 19.320508842693144, "percentage": 96.6, "elapsed_time": "1:55:19", "remaining_time": "0:04:03", "throughput": 5481.88, "total_tokens": 37934208} {"current_steps": 62275, "total_steps": 64460, "loss": 0.1793, "lr": 3.499187687575845e-08, "epoch": 19.32206019236736, "percentage": 96.61, "elapsed_time": "1:55:20", "remaining_time": "0:04:02", "throughput": 5481.79, "total_tokens": 37936544} {"current_steps": 62280, "total_steps": 64460, "loss": 0.1315, "lr": 3.483217321476273e-08, "epoch": 19.323611542041576, "percentage": 96.62, "elapsed_time": "1:55:20", "remaining_time": "0:04:02", "throughput": 5481.72, "total_tokens": 37938592} {"current_steps": 62285, "total_steps": 64460, "loss": 0.0848, "lr": 3.467283355936546e-08, "epoch": 19.32516289171579, "percentage": 96.63, "elapsed_time": "1:55:21", "remaining_time": "0:04:01", "throughput": 5481.73, "total_tokens": 37941248} {"current_steps": 62290, "total_steps": 64460, "loss": 0.1304, "lr": 3.451385792124784e-08, "epoch": 19.32671424139001, "percentage": 96.63, "elapsed_time": "1:55:21", "remaining_time": "0:04:01", "throughput": 5481.83, "total_tokens": 37945152} {"current_steps": 62295, "total_steps": 64460, "loss": 0.1747, "lr": 3.435524631206444e-08, "epoch": 19.328265591064227, "percentage": 96.64, "elapsed_time": "1:55:22", "remaining_time": "0:04:00", "throughput": 5481.87, "total_tokens": 37948768} {"current_steps": 62300, "total_steps": 64460, "loss": 0.2111, "lr": 3.4196998743443734e-08, "epoch": 19.329816940738443, "percentage": 96.65, "elapsed_time": "1:55:23", "remaining_time": "0:04:00", "throughput": 5481.9, "total_tokens": 37951904} {"current_steps": 62305, "total_steps": 64460, "loss": 0.1549, "lr": 3.403911522698644e-08, "epoch": 19.33136829041266, "percentage": 96.66, "elapsed_time": "1:55:23", "remaining_time": "0:03:59", "throughput": 5481.85, "total_tokens": 37954080} {"current_steps": 62310, "total_steps": 64460, "loss": 0.1675, "lr": 3.38815957742683e-08, "epoch": 19.332919640086875, "percentage": 96.66, "elapsed_time": "1:55:24", "remaining_time": "0:03:58", "throughput": 5481.87, "total_tokens": 37957312} {"current_steps": 62315, "total_steps": 64460, "loss": 0.1501, "lr": 3.3724440396836755e-08, "epoch": 19.33447098976109, "percentage": 96.67, "elapsed_time": "1:55:24", "remaining_time": "0:03:58", "throughput": 5481.93, "total_tokens": 37960960} {"current_steps": 62320, "total_steps": 64460, "loss": 0.1442, "lr": 3.356764910621313e-08, "epoch": 19.33602233943531, "percentage": 96.68, "elapsed_time": "1:55:25", "remaining_time": "0:03:57", "throughput": 5481.92, "total_tokens": 37963712} {"current_steps": 62325, "total_steps": 64460, "loss": 0.2911, "lr": 3.341122191389157e-08, "epoch": 19.337573689109526, "percentage": 96.69, "elapsed_time": "1:55:25", "remaining_time": "0:03:57", "throughput": 5481.95, "total_tokens": 37966688} {"current_steps": 62330, "total_steps": 64460, "loss": 0.1655, "lr": 3.325515883134178e-08, "epoch": 19.33912503878374, "percentage": 96.7, "elapsed_time": "1:55:26", "remaining_time": "0:03:56", "throughput": 5481.94, "total_tokens": 37969440} {"current_steps": 62335, "total_steps": 64460, "loss": 0.1155, "lr": 3.309945987000296e-08, "epoch": 19.340676388457958, "percentage": 96.7, "elapsed_time": "1:55:26", "remaining_time": "0:03:56", "throughput": 5481.94, "total_tokens": 37972320} {"current_steps": 62340, "total_steps": 64460, "loss": 0.1239, "lr": 3.2944125041291517e-08, "epoch": 19.342227738132173, "percentage": 96.71, "elapsed_time": "1:55:27", "remaining_time": "0:03:55", "throughput": 5481.98, "total_tokens": 37975200} {"current_steps": 62345, "total_steps": 64460, "loss": 0.1718, "lr": 3.278915435659335e-08, "epoch": 19.343779087806393, "percentage": 96.72, "elapsed_time": "1:55:27", "remaining_time": "0:03:55", "throughput": 5481.99, "total_tokens": 37978336} {"current_steps": 62350, "total_steps": 64460, "loss": 0.2239, "lr": 3.26345478272716e-08, "epoch": 19.34533043748061, "percentage": 96.73, "elapsed_time": "1:55:28", "remaining_time": "0:03:54", "throughput": 5482.03, "total_tokens": 37981440} {"current_steps": 62355, "total_steps": 64460, "loss": 0.1048, "lr": 3.248030546465941e-08, "epoch": 19.346881787154825, "percentage": 96.73, "elapsed_time": "1:55:28", "remaining_time": "0:03:53", "throughput": 5482.04, "total_tokens": 37984288} {"current_steps": 62360, "total_steps": 64460, "loss": 0.2377, "lr": 3.232642728006552e-08, "epoch": 19.34843313682904, "percentage": 96.74, "elapsed_time": "1:55:29", "remaining_time": "0:03:53", "throughput": 5482.12, "total_tokens": 37987840} {"current_steps": 62365, "total_steps": 64460, "loss": 0.1544, "lr": 3.217291328477035e-08, "epoch": 19.349984486503256, "percentage": 96.75, "elapsed_time": "1:55:29", "remaining_time": "0:03:52", "throughput": 5482.13, "total_tokens": 37990592} {"current_steps": 62370, "total_steps": 64460, "loss": 0.1582, "lr": 3.201976349002822e-08, "epoch": 19.351535836177476, "percentage": 96.76, "elapsed_time": "1:55:30", "remaining_time": "0:03:52", "throughput": 5482.21, "total_tokens": 37994528} {"current_steps": 62375, "total_steps": 64460, "loss": 0.1762, "lr": 3.186697790706794e-08, "epoch": 19.35308718585169, "percentage": 96.77, "elapsed_time": "1:55:31", "remaining_time": "0:03:51", "throughput": 5482.1, "total_tokens": 37996768} {"current_steps": 62380, "total_steps": 64460, "loss": 0.1277, "lr": 3.171455654708888e-08, "epoch": 19.354638535525908, "percentage": 96.77, "elapsed_time": "1:55:31", "remaining_time": "0:03:51", "throughput": 5482.14, "total_tokens": 38000032} {"current_steps": 62385, "total_steps": 64460, "loss": 0.1441, "lr": 3.156249942126655e-08, "epoch": 19.356189885200124, "percentage": 96.78, "elapsed_time": "1:55:32", "remaining_time": "0:03:50", "throughput": 5482.14, "total_tokens": 38003040} {"current_steps": 62390, "total_steps": 64460, "loss": 0.0883, "lr": 3.1410806540747574e-08, "epoch": 19.35774123487434, "percentage": 96.79, "elapsed_time": "1:55:32", "remaining_time": "0:03:50", "throughput": 5482.17, "total_tokens": 38005952} {"current_steps": 62395, "total_steps": 64460, "loss": 0.1139, "lr": 3.125947791665418e-08, "epoch": 19.35929258454856, "percentage": 96.8, "elapsed_time": "1:55:33", "remaining_time": "0:03:49", "throughput": 5482.13, "total_tokens": 38008864} {"current_steps": 62400, "total_steps": 64460, "loss": 0.102, "lr": 3.110851356007916e-08, "epoch": 19.360843934222775, "percentage": 96.8, "elapsed_time": "1:55:33", "remaining_time": "0:03:48", "throughput": 5482.12, "total_tokens": 38011328} {"current_steps": 62405, "total_steps": 64460, "loss": 0.1175, "lr": 3.0957913482090874e-08, "epoch": 19.36239528389699, "percentage": 96.81, "elapsed_time": "1:55:34", "remaining_time": "0:03:48", "throughput": 5482.14, "total_tokens": 38014272} {"current_steps": 62410, "total_steps": 64460, "loss": 0.1373, "lr": 3.080767769372939e-08, "epoch": 19.363946633571206, "percentage": 96.82, "elapsed_time": "1:55:34", "remaining_time": "0:03:47", "throughput": 5482.23, "total_tokens": 38018624} {"current_steps": 62415, "total_steps": 64460, "loss": 0.1352, "lr": 3.065780620600922e-08, "epoch": 19.365497983245422, "percentage": 96.83, "elapsed_time": "1:55:35", "remaining_time": "0:03:47", "throughput": 5482.23, "total_tokens": 38021120} {"current_steps": 62420, "total_steps": 64460, "loss": 0.3008, "lr": 3.050829902991825e-08, "epoch": 19.367049332919642, "percentage": 96.84, "elapsed_time": "1:55:35", "remaining_time": "0:03:46", "throughput": 5482.21, "total_tokens": 38023904} {"current_steps": 62425, "total_steps": 64460, "loss": 0.1684, "lr": 3.035915617641605e-08, "epoch": 19.368600682593858, "percentage": 96.84, "elapsed_time": "1:55:36", "remaining_time": "0:03:46", "throughput": 5482.25, "total_tokens": 38026912} {"current_steps": 62430, "total_steps": 64460, "loss": 0.1385, "lr": 3.0210377656437195e-08, "epoch": 19.370152032268074, "percentage": 96.85, "elapsed_time": "1:55:36", "remaining_time": "0:03:45", "throughput": 5482.28, "total_tokens": 38029920} {"current_steps": 62435, "total_steps": 64460, "loss": 0.2843, "lr": 3.006196348088852e-08, "epoch": 19.37170338194229, "percentage": 96.86, "elapsed_time": "1:55:37", "remaining_time": "0:03:45", "throughput": 5482.26, "total_tokens": 38032416} {"current_steps": 62440, "total_steps": 64460, "loss": 0.2047, "lr": 2.991391366065133e-08, "epoch": 19.373254731616505, "percentage": 96.87, "elapsed_time": "1:55:37", "remaining_time": "0:03:44", "throughput": 5482.27, "total_tokens": 38035296} {"current_steps": 62445, "total_steps": 64460, "loss": 0.1075, "lr": 2.9766228206578597e-08, "epoch": 19.37480608129072, "percentage": 96.87, "elapsed_time": "1:55:38", "remaining_time": "0:03:43", "throughput": 5482.37, "total_tokens": 38039360} {"current_steps": 62450, "total_steps": 64460, "loss": 0.2286, "lr": 2.9618907129497777e-08, "epoch": 19.37635743096494, "percentage": 96.88, "elapsed_time": "1:55:39", "remaining_time": "0:03:43", "throughput": 5482.51, "total_tokens": 38044288} {"current_steps": 62455, "total_steps": 64460, "loss": 0.1222, "lr": 2.9471950440208563e-08, "epoch": 19.377908780639157, "percentage": 96.89, "elapsed_time": "1:55:39", "remaining_time": "0:03:42", "throughput": 5482.61, "total_tokens": 38047904} {"current_steps": 62460, "total_steps": 64460, "loss": 0.1331, "lr": 2.932535814948623e-08, "epoch": 19.379460130313372, "percentage": 96.9, "elapsed_time": "1:55:40", "remaining_time": "0:03:42", "throughput": 5482.62, "total_tokens": 38050432} {"current_steps": 62465, "total_steps": 64460, "loss": 0.0978, "lr": 2.9179130268076062e-08, "epoch": 19.38101147998759, "percentage": 96.91, "elapsed_time": "1:55:40", "remaining_time": "0:03:41", "throughput": 5482.62, "total_tokens": 38053216} {"current_steps": 62470, "total_steps": 64460, "loss": 0.1624, "lr": 2.9033266806698934e-08, "epoch": 19.382562829661804, "percentage": 96.91, "elapsed_time": "1:55:41", "remaining_time": "0:03:41", "throughput": 5482.58, "total_tokens": 38055520} {"current_steps": 62475, "total_steps": 64460, "loss": 0.1581, "lr": 2.888776777604907e-08, "epoch": 19.384114179336024, "percentage": 96.92, "elapsed_time": "1:55:41", "remaining_time": "0:03:40", "throughput": 5482.62, "total_tokens": 38058368} {"current_steps": 62480, "total_steps": 64460, "loss": 0.1658, "lr": 2.8742633186791825e-08, "epoch": 19.38566552901024, "percentage": 96.93, "elapsed_time": "1:55:42", "remaining_time": "0:03:39", "throughput": 5482.67, "total_tokens": 38061312} {"current_steps": 62485, "total_steps": 64460, "loss": 0.1684, "lr": 2.8597863049568687e-08, "epoch": 19.387216878684455, "percentage": 96.94, "elapsed_time": "1:55:42", "remaining_time": "0:03:39", "throughput": 5482.79, "total_tokens": 38065184} {"current_steps": 62490, "total_steps": 64460, "loss": 0.1256, "lr": 2.8453457374992276e-08, "epoch": 19.38876822835867, "percentage": 96.94, "elapsed_time": "1:55:43", "remaining_time": "0:03:38", "throughput": 5482.82, "total_tokens": 38068032} {"current_steps": 62495, "total_steps": 64460, "loss": 0.1805, "lr": 2.830941617364913e-08, "epoch": 19.390319578032887, "percentage": 96.95, "elapsed_time": "1:55:43", "remaining_time": "0:03:38", "throughput": 5482.93, "total_tokens": 38071808} {"current_steps": 62500, "total_steps": 64460, "loss": 0.0947, "lr": 2.8165739456099682e-08, "epoch": 19.391870927707107, "percentage": 96.96, "elapsed_time": "1:55:44", "remaining_time": "0:03:37", "throughput": 5482.95, "total_tokens": 38074496} {"current_steps": 62505, "total_steps": 64460, "loss": 0.1257, "lr": 2.8022427232876626e-08, "epoch": 19.393422277381323, "percentage": 96.97, "elapsed_time": "1:55:44", "remaining_time": "0:03:37", "throughput": 5482.95, "total_tokens": 38077088} {"current_steps": 62510, "total_steps": 64460, "loss": 0.1677, "lr": 2.7879479514486553e-08, "epoch": 19.39497362705554, "percentage": 96.97, "elapsed_time": "1:55:45", "remaining_time": "0:03:36", "throughput": 5482.99, "total_tokens": 38080096} {"current_steps": 62515, "total_steps": 64460, "loss": 0.1244, "lr": 2.7736896311409412e-08, "epoch": 19.396524976729754, "percentage": 96.98, "elapsed_time": "1:55:45", "remaining_time": "0:03:36", "throughput": 5483.02, "total_tokens": 38082816} {"current_steps": 62520, "total_steps": 64460, "loss": 0.0617, "lr": 2.759467763409851e-08, "epoch": 19.39807632640397, "percentage": 96.99, "elapsed_time": "1:55:46", "remaining_time": "0:03:35", "throughput": 5483.1, "total_tokens": 38086304} {"current_steps": 62525, "total_steps": 64460, "loss": 0.1459, "lr": 2.7452823492979397e-08, "epoch": 19.39962767607819, "percentage": 97.0, "elapsed_time": "1:55:46", "remaining_time": "0:03:34", "throughput": 5483.1, "total_tokens": 38089120} {"current_steps": 62530, "total_steps": 64460, "loss": 0.1, "lr": 2.731133389845264e-08, "epoch": 19.401179025752405, "percentage": 97.01, "elapsed_time": "1:55:47", "remaining_time": "0:03:34", "throughput": 5483.19, "total_tokens": 38093056} {"current_steps": 62535, "total_steps": 64460, "loss": 0.1736, "lr": 2.7170208860889948e-08, "epoch": 19.40273037542662, "percentage": 97.01, "elapsed_time": "1:55:47", "remaining_time": "0:03:33", "throughput": 5483.22, "total_tokens": 38095968} {"current_steps": 62540, "total_steps": 64460, "loss": 0.2257, "lr": 2.702944839063859e-08, "epoch": 19.404281725100837, "percentage": 97.02, "elapsed_time": "1:55:48", "remaining_time": "0:03:33", "throughput": 5483.25, "total_tokens": 38098944} {"current_steps": 62545, "total_steps": 64460, "loss": 0.2152, "lr": 2.688905249801699e-08, "epoch": 19.405833074775053, "percentage": 97.03, "elapsed_time": "1:55:48", "remaining_time": "0:03:32", "throughput": 5483.3, "total_tokens": 38102656} {"current_steps": 62550, "total_steps": 64460, "loss": 0.1261, "lr": 2.6749021193318568e-08, "epoch": 19.407384424449273, "percentage": 97.04, "elapsed_time": "1:55:49", "remaining_time": "0:03:32", "throughput": 5483.26, "total_tokens": 38104896} {"current_steps": 62555, "total_steps": 64460, "loss": 0.1094, "lr": 2.660935448680846e-08, "epoch": 19.40893577412349, "percentage": 97.04, "elapsed_time": "1:55:49", "remaining_time": "0:03:31", "throughput": 5483.2, "total_tokens": 38107296} {"current_steps": 62560, "total_steps": 64460, "loss": 0.1262, "lr": 2.6470052388727353e-08, "epoch": 19.410487123797704, "percentage": 97.05, "elapsed_time": "1:55:50", "remaining_time": "0:03:31", "throughput": 5483.32, "total_tokens": 38112032} {"current_steps": 62565, "total_steps": 64460, "loss": 0.1818, "lr": 2.633111490928597e-08, "epoch": 19.41203847347192, "percentage": 97.06, "elapsed_time": "1:55:51", "remaining_time": "0:03:30", "throughput": 5483.41, "total_tokens": 38116352} {"current_steps": 62570, "total_steps": 64460, "loss": 0.1494, "lr": 2.619254205867172e-08, "epoch": 19.413589823146136, "percentage": 97.07, "elapsed_time": "1:55:51", "remaining_time": "0:03:29", "throughput": 5483.36, "total_tokens": 38119200} {"current_steps": 62575, "total_steps": 64460, "loss": 0.1077, "lr": 2.6054333847042036e-08, "epoch": 19.415141172820352, "percentage": 97.08, "elapsed_time": "1:55:52", "remaining_time": "0:03:29", "throughput": 5483.42, "total_tokens": 38122528} {"current_steps": 62580, "total_steps": 64460, "loss": 0.1258, "lr": 2.591649028453047e-08, "epoch": 19.41669252249457, "percentage": 97.08, "elapsed_time": "1:55:52", "remaining_time": "0:03:28", "throughput": 5483.43, "total_tokens": 38125280} {"current_steps": 62585, "total_steps": 64460, "loss": 0.2485, "lr": 2.5779011381241727e-08, "epoch": 19.418243872168787, "percentage": 97.09, "elapsed_time": "1:55:53", "remaining_time": "0:03:28", "throughput": 5483.43, "total_tokens": 38128096} {"current_steps": 62590, "total_steps": 64460, "loss": 0.1636, "lr": 2.5641897147255512e-08, "epoch": 19.419795221843003, "percentage": 97.1, "elapsed_time": "1:55:53", "remaining_time": "0:03:27", "throughput": 5483.43, "total_tokens": 38131424} {"current_steps": 62595, "total_steps": 64460, "loss": 0.1947, "lr": 2.5505147592623236e-08, "epoch": 19.42134657151722, "percentage": 97.11, "elapsed_time": "1:55:54", "remaining_time": "0:03:27", "throughput": 5483.4, "total_tokens": 38133952} {"current_steps": 62600, "total_steps": 64460, "loss": 0.0841, "lr": 2.536876272737021e-08, "epoch": 19.422897921191435, "percentage": 97.11, "elapsed_time": "1:55:54", "remaining_time": "0:03:26", "throughput": 5483.44, "total_tokens": 38137024} {"current_steps": 62605, "total_steps": 64460, "loss": 0.072, "lr": 2.523274256149566e-08, "epoch": 19.424449270865654, "percentage": 97.12, "elapsed_time": "1:55:55", "remaining_time": "0:03:26", "throughput": 5483.51, "total_tokens": 38140352} {"current_steps": 62610, "total_steps": 64460, "loss": 0.1149, "lr": 2.509708710497105e-08, "epoch": 19.42600062053987, "percentage": 97.13, "elapsed_time": "1:55:55", "remaining_time": "0:03:25", "throughput": 5483.46, "total_tokens": 38142592} {"current_steps": 62615, "total_steps": 64460, "loss": 0.1063, "lr": 2.4961796367741763e-08, "epoch": 19.427551970214086, "percentage": 97.14, "elapsed_time": "1:55:56", "remaining_time": "0:03:24", "throughput": 5483.44, "total_tokens": 38145024} {"current_steps": 62620, "total_steps": 64460, "loss": 0.1664, "lr": 2.4826870359725975e-08, "epoch": 19.429103319888302, "percentage": 97.15, "elapsed_time": "1:55:56", "remaining_time": "0:03:24", "throughput": 5483.4, "total_tokens": 38147392} {"current_steps": 62625, "total_steps": 64460, "loss": 0.0956, "lr": 2.469230909081577e-08, "epoch": 19.430654669562518, "percentage": 97.15, "elapsed_time": "1:55:57", "remaining_time": "0:03:23", "throughput": 5483.33, "total_tokens": 38149600} {"current_steps": 62630, "total_steps": 64460, "loss": 0.1224, "lr": 2.4558112570874924e-08, "epoch": 19.432206019236737, "percentage": 97.16, "elapsed_time": "1:55:57", "remaining_time": "0:03:23", "throughput": 5483.28, "total_tokens": 38151968} {"current_steps": 62635, "total_steps": 64460, "loss": 0.1642, "lr": 2.442428080974335e-08, "epoch": 19.433757368910953, "percentage": 97.17, "elapsed_time": "1:55:58", "remaining_time": "0:03:22", "throughput": 5483.34, "total_tokens": 38155136} {"current_steps": 62640, "total_steps": 64460, "loss": 0.1491, "lr": 2.4290813817230975e-08, "epoch": 19.43530871858517, "percentage": 97.18, "elapsed_time": "1:55:58", "remaining_time": "0:03:22", "throughput": 5483.43, "total_tokens": 38158592} {"current_steps": 62645, "total_steps": 64460, "loss": 0.2379, "lr": 2.4157711603123855e-08, "epoch": 19.436860068259385, "percentage": 97.18, "elapsed_time": "1:55:59", "remaining_time": "0:03:21", "throughput": 5483.35, "total_tokens": 38160704} {"current_steps": 62650, "total_steps": 64460, "loss": 0.2128, "lr": 2.402497417717864e-08, "epoch": 19.4384114179336, "percentage": 97.19, "elapsed_time": "1:55:59", "remaining_time": "0:03:21", "throughput": 5483.44, "total_tokens": 38164640} {"current_steps": 62655, "total_steps": 64460, "loss": 0.0631, "lr": 2.3892601549126982e-08, "epoch": 19.43996276760782, "percentage": 97.2, "elapsed_time": "1:56:00", "remaining_time": "0:03:20", "throughput": 5483.5, "total_tokens": 38167648} {"current_steps": 62660, "total_steps": 64460, "loss": 0.162, "lr": 2.3760593728674452e-08, "epoch": 19.441514117282036, "percentage": 97.21, "elapsed_time": "1:56:00", "remaining_time": "0:03:19", "throughput": 5483.4, "total_tokens": 38169568} {"current_steps": 62665, "total_steps": 64460, "loss": 0.1868, "lr": 2.3628950725497202e-08, "epoch": 19.443065466956252, "percentage": 97.22, "elapsed_time": "1:56:01", "remaining_time": "0:03:19", "throughput": 5483.47, "total_tokens": 38173664} {"current_steps": 62670, "total_steps": 64460, "loss": 0.1576, "lr": 2.3497672549246952e-08, "epoch": 19.444616816630468, "percentage": 97.22, "elapsed_time": "1:56:02", "remaining_time": "0:03:18", "throughput": 5483.45, "total_tokens": 38176192} {"current_steps": 62675, "total_steps": 64460, "loss": 0.1486, "lr": 2.3366759209548228e-08, "epoch": 19.446168166304684, "percentage": 97.23, "elapsed_time": "1:56:02", "remaining_time": "0:03:18", "throughput": 5483.61, "total_tokens": 38181760} {"current_steps": 62680, "total_steps": 64460, "loss": 0.1462, "lr": 2.32362107159978e-08, "epoch": 19.447719515978903, "percentage": 97.24, "elapsed_time": "1:56:03", "remaining_time": "0:03:17", "throughput": 5483.63, "total_tokens": 38184576} {"current_steps": 62685, "total_steps": 64460, "loss": 0.1577, "lr": 2.3106027078166894e-08, "epoch": 19.44927086565312, "percentage": 97.25, "elapsed_time": "1:56:03", "remaining_time": "0:03:17", "throughput": 5483.7, "total_tokens": 38188128} {"current_steps": 62690, "total_steps": 64460, "loss": 0.3123, "lr": 2.29762083056001e-08, "epoch": 19.450822215327335, "percentage": 97.25, "elapsed_time": "1:56:04", "remaining_time": "0:03:16", "throughput": 5483.69, "total_tokens": 38190752} {"current_steps": 62695, "total_steps": 64460, "loss": 0.1177, "lr": 2.284675440781314e-08, "epoch": 19.45237356500155, "percentage": 97.26, "elapsed_time": "1:56:04", "remaining_time": "0:03:16", "throughput": 5483.68, "total_tokens": 38193568} {"current_steps": 62700, "total_steps": 64460, "loss": 0.1677, "lr": 2.271766539429787e-08, "epoch": 19.453924914675767, "percentage": 97.27, "elapsed_time": "1:56:05", "remaining_time": "0:03:15", "throughput": 5483.71, "total_tokens": 38196832} {"current_steps": 62705, "total_steps": 64460, "loss": 0.1197, "lr": 2.2588941274517273e-08, "epoch": 19.455476264349983, "percentage": 97.28, "elapsed_time": "1:56:06", "remaining_time": "0:03:14", "throughput": 5483.81, "total_tokens": 38200480} {"current_steps": 62710, "total_steps": 64460, "loss": 0.2041, "lr": 2.2460582057909354e-08, "epoch": 19.457027614024202, "percentage": 97.29, "elapsed_time": "1:56:06", "remaining_time": "0:03:14", "throughput": 5483.85, "total_tokens": 38203776} {"current_steps": 62715, "total_steps": 64460, "loss": 0.1964, "lr": 2.2332587753882695e-08, "epoch": 19.458578963698418, "percentage": 97.29, "elapsed_time": "1:56:07", "remaining_time": "0:03:13", "throughput": 5483.9, "total_tokens": 38207104} {"current_steps": 62720, "total_steps": 64460, "loss": 0.1047, "lr": 2.220495837182257e-08, "epoch": 19.460130313372634, "percentage": 97.3, "elapsed_time": "1:56:07", "remaining_time": "0:03:13", "throughput": 5483.89, "total_tokens": 38209664} {"current_steps": 62725, "total_steps": 64460, "loss": 0.189, "lr": 2.2077693921084276e-08, "epoch": 19.46168166304685, "percentage": 97.31, "elapsed_time": "1:56:08", "remaining_time": "0:03:12", "throughput": 5483.93, "total_tokens": 38212576} {"current_steps": 62730, "total_steps": 64460, "loss": 0.1566, "lr": 2.1950794410999232e-08, "epoch": 19.463233012721066, "percentage": 97.32, "elapsed_time": "1:56:08", "remaining_time": "0:03:12", "throughput": 5483.94, "total_tokens": 38215648} {"current_steps": 62735, "total_steps": 64460, "loss": 0.1084, "lr": 2.182425985086889e-08, "epoch": 19.464784362395285, "percentage": 97.32, "elapsed_time": "1:56:09", "remaining_time": "0:03:11", "throughput": 5483.97, "total_tokens": 38219456} {"current_steps": 62740, "total_steps": 64460, "loss": 0.1602, "lr": 2.1698090249971383e-08, "epoch": 19.4663357120695, "percentage": 97.33, "elapsed_time": "1:56:09", "remaining_time": "0:03:11", "throughput": 5484.01, "total_tokens": 38222720} {"current_steps": 62745, "total_steps": 64460, "loss": 0.1344, "lr": 2.157228561755542e-08, "epoch": 19.467887061743717, "percentage": 97.34, "elapsed_time": "1:56:10", "remaining_time": "0:03:10", "throughput": 5484.02, "total_tokens": 38225664} {"current_steps": 62750, "total_steps": 64460, "loss": 0.1451, "lr": 2.144684596284474e-08, "epoch": 19.469438411417933, "percentage": 97.35, "elapsed_time": "1:56:10", "remaining_time": "0:03:09", "throughput": 5484.04, "total_tokens": 38228608} {"current_steps": 62755, "total_steps": 64460, "loss": 0.1797, "lr": 2.1321771295034764e-08, "epoch": 19.47098976109215, "percentage": 97.35, "elapsed_time": "1:56:11", "remaining_time": "0:03:09", "throughput": 5484.15, "total_tokens": 38232576} {"current_steps": 62760, "total_steps": 64460, "loss": 0.1976, "lr": 2.119706162329538e-08, "epoch": 19.472541110766368, "percentage": 97.36, "elapsed_time": "1:56:11", "remaining_time": "0:03:08", "throughput": 5484.22, "total_tokens": 38235872} {"current_steps": 62765, "total_steps": 64460, "loss": 0.1776, "lr": 2.1072716956769267e-08, "epoch": 19.474092460440584, "percentage": 97.37, "elapsed_time": "1:56:12", "remaining_time": "0:03:08", "throughput": 5484.27, "total_tokens": 38239008} {"current_steps": 62770, "total_steps": 64460, "loss": 0.1409, "lr": 2.0948737304572474e-08, "epoch": 19.4756438101148, "percentage": 97.38, "elapsed_time": "1:56:12", "remaining_time": "0:03:07", "throughput": 5484.3, "total_tokens": 38241984} {"current_steps": 62775, "total_steps": 64460, "loss": 0.1229, "lr": 2.082512267579384e-08, "epoch": 19.477195159789016, "percentage": 97.39, "elapsed_time": "1:56:13", "remaining_time": "0:03:07", "throughput": 5484.29, "total_tokens": 38244864} {"current_steps": 62780, "total_steps": 64460, "loss": 0.1509, "lr": 2.0701873079496115e-08, "epoch": 19.47874650946323, "percentage": 97.39, "elapsed_time": "1:56:14", "remaining_time": "0:03:06", "throughput": 5484.24, "total_tokens": 38247136} {"current_steps": 62785, "total_steps": 64460, "loss": 0.243, "lr": 2.057898852471485e-08, "epoch": 19.48029785913745, "percentage": 97.4, "elapsed_time": "1:56:14", "remaining_time": "0:03:06", "throughput": 5484.4, "total_tokens": 38253440} {"current_steps": 62790, "total_steps": 64460, "loss": 0.1351, "lr": 2.0456469020458392e-08, "epoch": 19.481849208811667, "percentage": 97.41, "elapsed_time": "1:56:15", "remaining_time": "0:03:05", "throughput": 5484.35, "total_tokens": 38256032} {"current_steps": 62795, "total_steps": 64460, "loss": 0.1632, "lr": 2.0334314575710112e-08, "epoch": 19.483400558485883, "percentage": 97.42, "elapsed_time": "1:56:16", "remaining_time": "0:03:04", "throughput": 5484.46, "total_tokens": 38260512} {"current_steps": 62800, "total_steps": 64460, "loss": 0.2695, "lr": 2.021252519942396e-08, "epoch": 19.4849519081601, "percentage": 97.42, "elapsed_time": "1:56:16", "remaining_time": "0:03:04", "throughput": 5484.49, "total_tokens": 38263648} {"current_steps": 62805, "total_steps": 64460, "loss": 0.1182, "lr": 2.009110090052946e-08, "epoch": 19.486503257834315, "percentage": 97.43, "elapsed_time": "1:56:17", "remaining_time": "0:03:03", "throughput": 5484.52, "total_tokens": 38266656} {"current_steps": 62810, "total_steps": 64460, "loss": 0.1274, "lr": 1.9970041687928375e-08, "epoch": 19.488054607508534, "percentage": 97.44, "elapsed_time": "1:56:17", "remaining_time": "0:03:03", "throughput": 5484.56, "total_tokens": 38270816} {"current_steps": 62815, "total_steps": 64460, "loss": 0.2113, "lr": 1.9849347570495837e-08, "epoch": 19.48960595718275, "percentage": 97.45, "elapsed_time": "1:56:18", "remaining_time": "0:03:02", "throughput": 5484.52, "total_tokens": 38273216} {"current_steps": 62820, "total_steps": 64460, "loss": 0.2305, "lr": 1.9729018557079206e-08, "epoch": 19.491157306856966, "percentage": 97.46, "elapsed_time": "1:56:18", "remaining_time": "0:03:02", "throughput": 5484.42, "total_tokens": 38275552} {"current_steps": 62825, "total_steps": 64460, "loss": 0.1291, "lr": 1.9609054656501427e-08, "epoch": 19.492708656531182, "percentage": 97.46, "elapsed_time": "1:56:19", "remaining_time": "0:03:01", "throughput": 5484.49, "total_tokens": 38278912} {"current_steps": 62830, "total_steps": 64460, "loss": 0.1971, "lr": 1.9489455877556017e-08, "epoch": 19.494260006205398, "percentage": 97.47, "elapsed_time": "1:56:20", "remaining_time": "0:03:01", "throughput": 5484.6, "total_tokens": 38282912} {"current_steps": 62835, "total_steps": 64460, "loss": 0.1362, "lr": 1.937022222901208e-08, "epoch": 19.495811355879614, "percentage": 97.48, "elapsed_time": "1:56:20", "remaining_time": "0:03:00", "throughput": 5484.59, "total_tokens": 38285856} {"current_steps": 62840, "total_steps": 64460, "loss": 0.1014, "lr": 1.92513537196104e-08, "epoch": 19.497362705553833, "percentage": 97.49, "elapsed_time": "1:56:21", "remaining_time": "0:02:59", "throughput": 5484.62, "total_tokens": 38288864} {"current_steps": 62845, "total_steps": 64460, "loss": 0.1487, "lr": 1.913285035806456e-08, "epoch": 19.49891405522805, "percentage": 97.49, "elapsed_time": "1:56:21", "remaining_time": "0:02:59", "throughput": 5484.67, "total_tokens": 38291872} {"current_steps": 62850, "total_steps": 64460, "loss": 0.1394, "lr": 1.901471215306372e-08, "epoch": 19.500465404902265, "percentage": 97.5, "elapsed_time": "1:56:22", "remaining_time": "0:02:58", "throughput": 5484.61, "total_tokens": 38294240} {"current_steps": 62855, "total_steps": 64460, "loss": 0.0846, "lr": 1.8896939113268175e-08, "epoch": 19.50201675457648, "percentage": 97.51, "elapsed_time": "1:56:22", "remaining_time": "0:02:58", "throughput": 5484.64, "total_tokens": 38297152} {"current_steps": 62860, "total_steps": 64460, "loss": 0.1209, "lr": 1.8779531247311577e-08, "epoch": 19.503568104250697, "percentage": 97.52, "elapsed_time": "1:56:23", "remaining_time": "0:02:57", "throughput": 5484.63, "total_tokens": 38300160} {"current_steps": 62865, "total_steps": 64460, "loss": 0.1908, "lr": 1.8662488563802595e-08, "epoch": 19.505119453924916, "percentage": 97.53, "elapsed_time": "1:56:23", "remaining_time": "0:02:57", "throughput": 5484.61, "total_tokens": 38302528} {"current_steps": 62870, "total_steps": 64460, "loss": 0.1712, "lr": 1.8545811071320474e-08, "epoch": 19.506670803599132, "percentage": 97.53, "elapsed_time": "1:56:24", "remaining_time": "0:02:56", "throughput": 5484.77, "total_tokens": 38307328} {"current_steps": 62875, "total_steps": 64460, "loss": 0.246, "lr": 1.842949877842004e-08, "epoch": 19.508222153273348, "percentage": 97.54, "elapsed_time": "1:56:24", "remaining_time": "0:02:56", "throughput": 5484.79, "total_tokens": 38310560} {"current_steps": 62880, "total_steps": 64460, "loss": 0.1489, "lr": 1.8313551693627806e-08, "epoch": 19.509773502947564, "percentage": 97.55, "elapsed_time": "1:56:25", "remaining_time": "0:02:55", "throughput": 5484.85, "total_tokens": 38314144} {"current_steps": 62885, "total_steps": 64460, "loss": 0.1572, "lr": 1.8197969825444194e-08, "epoch": 19.51132485262178, "percentage": 97.56, "elapsed_time": "1:56:26", "remaining_time": "0:02:54", "throughput": 5484.96, "total_tokens": 38318048} {"current_steps": 62890, "total_steps": 64460, "loss": 0.1424, "lr": 1.8082753182342428e-08, "epoch": 19.512876202296, "percentage": 97.56, "elapsed_time": "1:56:26", "remaining_time": "0:02:54", "throughput": 5484.91, "total_tokens": 38320224} {"current_steps": 62895, "total_steps": 64460, "loss": 0.2435, "lr": 1.796790177277019e-08, "epoch": 19.514427551970215, "percentage": 97.57, "elapsed_time": "1:56:27", "remaining_time": "0:02:53", "throughput": 5484.87, "total_tokens": 38322880} {"current_steps": 62900, "total_steps": 64460, "loss": 0.1437, "lr": 1.7853415605146305e-08, "epoch": 19.51597890164443, "percentage": 97.58, "elapsed_time": "1:56:27", "remaining_time": "0:02:53", "throughput": 5484.99, "total_tokens": 38326976} {"current_steps": 62905, "total_steps": 64460, "loss": 0.1809, "lr": 1.773929468786517e-08, "epoch": 19.517530251318647, "percentage": 97.59, "elapsed_time": "1:56:28", "remaining_time": "0:02:52", "throughput": 5484.98, "total_tokens": 38329632} {"current_steps": 62910, "total_steps": 64460, "loss": 0.0829, "lr": 1.762553902929176e-08, "epoch": 19.519081600992862, "percentage": 97.6, "elapsed_time": "1:56:28", "remaining_time": "0:02:52", "throughput": 5484.98, "total_tokens": 38332320} {"current_steps": 62915, "total_steps": 64460, "loss": 0.1717, "lr": 1.7512148637766624e-08, "epoch": 19.520632950667082, "percentage": 97.6, "elapsed_time": "1:56:29", "remaining_time": "0:02:51", "throughput": 5484.98, "total_tokens": 38335072} {"current_steps": 62920, "total_steps": 64460, "loss": 0.1576, "lr": 1.7399123521602557e-08, "epoch": 19.522184300341298, "percentage": 97.61, "elapsed_time": "1:56:29", "remaining_time": "0:02:51", "throughput": 5484.97, "total_tokens": 38337792} {"current_steps": 62925, "total_steps": 64460, "loss": 0.1763, "lr": 1.728646368908571e-08, "epoch": 19.523735650015514, "percentage": 97.62, "elapsed_time": "1:56:30", "remaining_time": "0:02:50", "throughput": 5485.06, "total_tokens": 38342048} {"current_steps": 62930, "total_steps": 64460, "loss": 0.2474, "lr": 1.7174169148475584e-08, "epoch": 19.52528699968973, "percentage": 97.63, "elapsed_time": "1:56:30", "remaining_time": "0:02:49", "throughput": 5485.22, "total_tokens": 38346912} {"current_steps": 62935, "total_steps": 64460, "loss": 0.1848, "lr": 1.706223990800393e-08, "epoch": 19.526838349363945, "percentage": 97.63, "elapsed_time": "1:56:31", "remaining_time": "0:02:49", "throughput": 5485.29, "total_tokens": 38350464} {"current_steps": 62940, "total_steps": 64460, "loss": 0.1066, "lr": 1.695067597587696e-08, "epoch": 19.528389699038165, "percentage": 97.64, "elapsed_time": "1:56:32", "remaining_time": "0:02:48", "throughput": 5485.29, "total_tokens": 38353248} {"current_steps": 62945, "total_steps": 64460, "loss": 0.1725, "lr": 1.683947736027314e-08, "epoch": 19.52994104871238, "percentage": 97.65, "elapsed_time": "1:56:32", "remaining_time": "0:02:48", "throughput": 5485.29, "total_tokens": 38355776} {"current_steps": 62950, "total_steps": 64460, "loss": 0.1027, "lr": 1.6728644069345935e-08, "epoch": 19.531492398386597, "percentage": 97.66, "elapsed_time": "1:56:33", "remaining_time": "0:02:47", "throughput": 5485.35, "total_tokens": 38359232} {"current_steps": 62955, "total_steps": 64460, "loss": 0.0943, "lr": 1.6618176111218854e-08, "epoch": 19.533043748060813, "percentage": 97.67, "elapsed_time": "1:56:33", "remaining_time": "0:02:47", "throughput": 5485.4, "total_tokens": 38362304} {"current_steps": 62960, "total_steps": 64460, "loss": 0.1622, "lr": 1.6508073493992637e-08, "epoch": 19.53459509773503, "percentage": 97.67, "elapsed_time": "1:56:34", "remaining_time": "0:02:46", "throughput": 5485.39, "total_tokens": 38364800} {"current_steps": 62965, "total_steps": 64460, "loss": 0.1162, "lr": 1.6398336225736944e-08, "epoch": 19.536146447409244, "percentage": 97.68, "elapsed_time": "1:56:34", "remaining_time": "0:02:46", "throughput": 5485.52, "total_tokens": 38371232} {"current_steps": 62970, "total_steps": 64460, "loss": 0.1234, "lr": 1.6288964314498668e-08, "epoch": 19.537697797083464, "percentage": 97.69, "elapsed_time": "1:56:35", "remaining_time": "0:02:45", "throughput": 5485.53, "total_tokens": 38374208} {"current_steps": 62975, "total_steps": 64460, "loss": 0.1764, "lr": 1.617995776829473e-08, "epoch": 19.53924914675768, "percentage": 97.7, "elapsed_time": "1:56:36", "remaining_time": "0:02:44", "throughput": 5485.51, "total_tokens": 38376800} {"current_steps": 62980, "total_steps": 64460, "loss": 0.1168, "lr": 1.6071316595117626e-08, "epoch": 19.540800496431896, "percentage": 97.7, "elapsed_time": "1:56:36", "remaining_time": "0:02:44", "throughput": 5485.46, "total_tokens": 38379232} {"current_steps": 62985, "total_steps": 64460, "loss": 0.2174, "lr": 1.596304080293154e-08, "epoch": 19.54235184610611, "percentage": 97.71, "elapsed_time": "1:56:36", "remaining_time": "0:02:43", "throughput": 5485.4, "total_tokens": 38381280} {"current_steps": 62990, "total_steps": 64460, "loss": 0.1877, "lr": 1.5855130399674012e-08, "epoch": 19.543903195780327, "percentage": 97.72, "elapsed_time": "1:56:37", "remaining_time": "0:02:43", "throughput": 5485.41, "total_tokens": 38384096} {"current_steps": 62995, "total_steps": 64460, "loss": 0.1235, "lr": 1.5747585393256493e-08, "epoch": 19.545454545454547, "percentage": 97.73, "elapsed_time": "1:56:38", "remaining_time": "0:02:42", "throughput": 5485.47, "total_tokens": 38387648} {"current_steps": 63000, "total_steps": 64460, "loss": 0.1025, "lr": 1.5640405791563784e-08, "epoch": 19.547005895128763, "percentage": 97.74, "elapsed_time": "1:56:38", "remaining_time": "0:02:42", "throughput": 5485.46, "total_tokens": 38390272} {"current_steps": 63005, "total_steps": 64460, "loss": 0.1459, "lr": 1.5533591602452935e-08, "epoch": 19.54855724480298, "percentage": 97.74, "elapsed_time": "1:56:39", "remaining_time": "0:02:41", "throughput": 5485.51, "total_tokens": 38393504} {"current_steps": 63010, "total_steps": 64460, "loss": 0.0977, "lr": 1.5427142833754348e-08, "epoch": 19.550108594477194, "percentage": 97.75, "elapsed_time": "1:56:39", "remaining_time": "0:02:41", "throughput": 5485.53, "total_tokens": 38396480} {"current_steps": 63015, "total_steps": 64460, "loss": 0.1238, "lr": 1.5321059493272894e-08, "epoch": 19.55165994415141, "percentage": 97.76, "elapsed_time": "1:56:40", "remaining_time": "0:02:40", "throughput": 5485.57, "total_tokens": 38399424} {"current_steps": 63020, "total_steps": 64460, "loss": 0.171, "lr": 1.521534158878457e-08, "epoch": 19.55321129382563, "percentage": 97.77, "elapsed_time": "1:56:40", "remaining_time": "0:02:39", "throughput": 5485.65, "total_tokens": 38404480} {"current_steps": 63025, "total_steps": 64460, "loss": 0.1387, "lr": 1.510998912804096e-08, "epoch": 19.554762643499846, "percentage": 97.77, "elapsed_time": "1:56:41", "remaining_time": "0:02:39", "throughput": 5485.66, "total_tokens": 38407424} {"current_steps": 63030, "total_steps": 64460, "loss": 0.1523, "lr": 1.5005002118764768e-08, "epoch": 19.55631399317406, "percentage": 97.78, "elapsed_time": "1:56:41", "remaining_time": "0:02:38", "throughput": 5485.63, "total_tokens": 38409824} {"current_steps": 63035, "total_steps": 64460, "loss": 0.121, "lr": 1.4900380568653172e-08, "epoch": 19.557865342848277, "percentage": 97.79, "elapsed_time": "1:56:42", "remaining_time": "0:02:38", "throughput": 5485.6, "total_tokens": 38412480} {"current_steps": 63040, "total_steps": 64460, "loss": 0.113, "lr": 1.479612448537615e-08, "epoch": 19.559416692522493, "percentage": 97.8, "elapsed_time": "1:56:42", "remaining_time": "0:02:37", "throughput": 5485.65, "total_tokens": 38415680} {"current_steps": 63045, "total_steps": 64460, "loss": 0.1065, "lr": 1.4692233876576479e-08, "epoch": 19.560968042196713, "percentage": 97.8, "elapsed_time": "1:56:43", "remaining_time": "0:02:37", "throughput": 5485.64, "total_tokens": 38418496} {"current_steps": 63050, "total_steps": 64460, "loss": 0.1137, "lr": 1.4588708749871395e-08, "epoch": 19.56251939187093, "percentage": 97.81, "elapsed_time": "1:56:44", "remaining_time": "0:02:36", "throughput": 5485.73, "total_tokens": 38422720} {"current_steps": 63055, "total_steps": 64460, "loss": 0.1456, "lr": 1.4485549112849829e-08, "epoch": 19.564070741545144, "percentage": 97.82, "elapsed_time": "1:56:44", "remaining_time": "0:02:36", "throughput": 5485.71, "total_tokens": 38425120} {"current_steps": 63060, "total_steps": 64460, "loss": 0.1914, "lr": 1.4382754973075175e-08, "epoch": 19.56562209121936, "percentage": 97.83, "elapsed_time": "1:56:45", "remaining_time": "0:02:35", "throughput": 5485.7, "total_tokens": 38427904} {"current_steps": 63065, "total_steps": 64460, "loss": 0.1121, "lr": 1.4280326338082518e-08, "epoch": 19.567173440893576, "percentage": 97.84, "elapsed_time": "1:56:45", "remaining_time": "0:02:34", "throughput": 5485.68, "total_tokens": 38430592} {"current_steps": 63070, "total_steps": 64460, "loss": 0.1756, "lr": 1.417826321538196e-08, "epoch": 19.568724790567796, "percentage": 97.84, "elapsed_time": "1:56:46", "remaining_time": "0:02:34", "throughput": 5485.74, "total_tokens": 38433824} {"current_steps": 63075, "total_steps": 64460, "loss": 0.1209, "lr": 1.4076565612455851e-08, "epoch": 19.57027614024201, "percentage": 97.85, "elapsed_time": "1:56:46", "remaining_time": "0:02:33", "throughput": 5485.79, "total_tokens": 38437248} {"current_steps": 63080, "total_steps": 64460, "loss": 0.1775, "lr": 1.3975233536759337e-08, "epoch": 19.571827489916227, "percentage": 97.86, "elapsed_time": "1:56:47", "remaining_time": "0:02:33", "throughput": 5485.79, "total_tokens": 38439936} {"current_steps": 63085, "total_steps": 64460, "loss": 0.1834, "lr": 1.387426699572203e-08, "epoch": 19.573378839590443, "percentage": 97.87, "elapsed_time": "1:56:47", "remaining_time": "0:02:32", "throughput": 5485.7, "total_tokens": 38442176} {"current_steps": 63090, "total_steps": 64460, "loss": 0.2135, "lr": 1.3773665996745234e-08, "epoch": 19.57493018926466, "percentage": 97.87, "elapsed_time": "1:56:48", "remaining_time": "0:02:32", "throughput": 5485.76, "total_tokens": 38445440} {"current_steps": 63095, "total_steps": 64460, "loss": 0.1937, "lr": 1.3673430547204714e-08, "epoch": 19.576481538938875, "percentage": 97.88, "elapsed_time": "1:56:48", "remaining_time": "0:02:31", "throughput": 5485.77, "total_tokens": 38448672} {"current_steps": 63100, "total_steps": 64460, "loss": 0.139, "lr": 1.3573560654447927e-08, "epoch": 19.578032888613095, "percentage": 97.89, "elapsed_time": "1:56:49", "remaining_time": "0:02:31", "throughput": 5485.71, "total_tokens": 38450816} {"current_steps": 63105, "total_steps": 64460, "loss": 0.1496, "lr": 1.3474056325797902e-08, "epoch": 19.57958423828731, "percentage": 97.9, "elapsed_time": "1:56:49", "remaining_time": "0:02:30", "throughput": 5485.73, "total_tokens": 38453536} {"current_steps": 63110, "total_steps": 64460, "loss": 0.1362, "lr": 1.3374917568548806e-08, "epoch": 19.581135587961526, "percentage": 97.91, "elapsed_time": "1:56:50", "remaining_time": "0:02:29", "throughput": 5485.69, "total_tokens": 38455744} {"current_steps": 63115, "total_steps": 64460, "loss": 0.1175, "lr": 1.3276144389968715e-08, "epoch": 19.582686937635742, "percentage": 97.91, "elapsed_time": "1:56:50", "remaining_time": "0:02:29", "throughput": 5485.71, "total_tokens": 38458496} {"current_steps": 63120, "total_steps": 64460, "loss": 0.1441, "lr": 1.3177736797299056e-08, "epoch": 19.584238287309958, "percentage": 97.92, "elapsed_time": "1:56:51", "remaining_time": "0:02:28", "throughput": 5485.69, "total_tokens": 38461216} {"current_steps": 63125, "total_steps": 64460, "loss": 0.138, "lr": 1.3079694797754061e-08, "epoch": 19.585789636984178, "percentage": 97.93, "elapsed_time": "1:56:51", "remaining_time": "0:02:28", "throughput": 5485.78, "total_tokens": 38465184} {"current_steps": 63130, "total_steps": 64460, "loss": 0.0843, "lr": 1.2982018398520757e-08, "epoch": 19.587340986658393, "percentage": 97.94, "elapsed_time": "1:56:52", "remaining_time": "0:02:27", "throughput": 5485.72, "total_tokens": 38467680} {"current_steps": 63135, "total_steps": 64460, "loss": 0.1263, "lr": 1.2884707606761193e-08, "epoch": 19.58889233633261, "percentage": 97.94, "elapsed_time": "1:56:52", "remaining_time": "0:02:27", "throughput": 5485.68, "total_tokens": 38469952} {"current_steps": 63140, "total_steps": 64460, "loss": 0.072, "lr": 1.2787762429608552e-08, "epoch": 19.590443686006825, "percentage": 97.95, "elapsed_time": "1:56:53", "remaining_time": "0:02:26", "throughput": 5485.71, "total_tokens": 38473184} {"current_steps": 63145, "total_steps": 64460, "loss": 0.1475, "lr": 1.2691182874171037e-08, "epoch": 19.59199503568104, "percentage": 97.96, "elapsed_time": "1:56:53", "remaining_time": "0:02:26", "throughput": 5485.71, "total_tokens": 38475936} {"current_steps": 63150, "total_steps": 64460, "loss": 0.1605, "lr": 1.259496894752743e-08, "epoch": 19.59354638535526, "percentage": 97.97, "elapsed_time": "1:56:54", "remaining_time": "0:02:25", "throughput": 5485.72, "total_tokens": 38478784} {"current_steps": 63155, "total_steps": 64460, "loss": 0.091, "lr": 1.2499120656733198e-08, "epoch": 19.595097735029476, "percentage": 97.98, "elapsed_time": "1:56:54", "remaining_time": "0:02:24", "throughput": 5485.76, "total_tokens": 38481824} {"current_steps": 63160, "total_steps": 64460, "loss": 0.0901, "lr": 1.2403638008813835e-08, "epoch": 19.596649084703692, "percentage": 97.98, "elapsed_time": "1:56:55", "remaining_time": "0:02:24", "throughput": 5485.84, "total_tokens": 38485440} {"current_steps": 63165, "total_steps": 64460, "loss": 0.1232, "lr": 1.2308521010769848e-08, "epoch": 19.598200434377908, "percentage": 97.99, "elapsed_time": "1:56:55", "remaining_time": "0:02:23", "throughput": 5485.83, "total_tokens": 38488128} {"current_steps": 63170, "total_steps": 64460, "loss": 0.1476, "lr": 1.2213769669573993e-08, "epoch": 19.599751784052124, "percentage": 98.0, "elapsed_time": "1:56:56", "remaining_time": "0:02:23", "throughput": 5485.79, "total_tokens": 38490528} {"current_steps": 63175, "total_steps": 64460, "loss": 0.1398, "lr": 1.2119383992173494e-08, "epoch": 19.601303133726343, "percentage": 98.01, "elapsed_time": "1:56:57", "remaining_time": "0:02:22", "throughput": 5485.89, "total_tokens": 38494624} {"current_steps": 63180, "total_steps": 64460, "loss": 0.1625, "lr": 1.2025363985487259e-08, "epoch": 19.60285448340056, "percentage": 98.01, "elapsed_time": "1:56:57", "remaining_time": "0:02:22", "throughput": 5485.92, "total_tokens": 38497728} {"current_steps": 63185, "total_steps": 64460, "loss": 0.1034, "lr": 1.1931709656408663e-08, "epoch": 19.604405833074775, "percentage": 98.02, "elapsed_time": "1:56:58", "remaining_time": "0:02:21", "throughput": 5485.97, "total_tokens": 38501280} {"current_steps": 63190, "total_steps": 64460, "loss": 0.2434, "lr": 1.1838421011803325e-08, "epoch": 19.60595718274899, "percentage": 98.03, "elapsed_time": "1:56:58", "remaining_time": "0:02:21", "throughput": 5485.92, "total_tokens": 38503616} {"current_steps": 63195, "total_steps": 64460, "loss": 0.2459, "lr": 1.1745498058509663e-08, "epoch": 19.607508532423207, "percentage": 98.04, "elapsed_time": "1:56:59", "remaining_time": "0:02:20", "throughput": 5485.89, "total_tokens": 38506400} {"current_steps": 63200, "total_steps": 64460, "loss": 0.2512, "lr": 1.1652940803341672e-08, "epoch": 19.609059882097426, "percentage": 98.05, "elapsed_time": "1:56:59", "remaining_time": "0:02:19", "throughput": 5485.89, "total_tokens": 38509184} {"current_steps": 63205, "total_steps": 64460, "loss": 0.1615, "lr": 1.1560749253083369e-08, "epoch": 19.610611231771642, "percentage": 98.05, "elapsed_time": "1:57:00", "remaining_time": "0:02:19", "throughput": 5486.0, "total_tokens": 38513312} {"current_steps": 63210, "total_steps": 64460, "loss": 0.1009, "lr": 1.1468923414494349e-08, "epoch": 19.612162581445858, "percentage": 98.06, "elapsed_time": "1:57:00", "remaining_time": "0:02:18", "throughput": 5486.06, "total_tokens": 38517184} {"current_steps": 63215, "total_steps": 64460, "loss": 0.1187, "lr": 1.1377463294305891e-08, "epoch": 19.613713931120074, "percentage": 98.07, "elapsed_time": "1:57:01", "remaining_time": "0:02:18", "throughput": 5486.25, "total_tokens": 38523168} {"current_steps": 63220, "total_steps": 64460, "loss": 0.1436, "lr": 1.1286368899224298e-08, "epoch": 19.61526528079429, "percentage": 98.08, "elapsed_time": "1:57:02", "remaining_time": "0:02:17", "throughput": 5486.27, "total_tokens": 38525984} {"current_steps": 63225, "total_steps": 64460, "loss": 0.1193, "lr": 1.1195640235926453e-08, "epoch": 19.616816630468506, "percentage": 98.08, "elapsed_time": "1:57:02", "remaining_time": "0:02:17", "throughput": 5486.25, "total_tokens": 38528672} {"current_steps": 63230, "total_steps": 64460, "loss": 0.1045, "lr": 1.1105277311064811e-08, "epoch": 19.618367980142725, "percentage": 98.09, "elapsed_time": "1:57:03", "remaining_time": "0:02:16", "throughput": 5486.29, "total_tokens": 38532000} {"current_steps": 63235, "total_steps": 64460, "loss": 0.1711, "lr": 1.1015280131263518e-08, "epoch": 19.61991932981694, "percentage": 98.1, "elapsed_time": "1:57:03", "remaining_time": "0:02:16", "throughput": 5486.33, "total_tokens": 38535040} {"current_steps": 63240, "total_steps": 64460, "loss": 0.1283, "lr": 1.0925648703120628e-08, "epoch": 19.621470679491157, "percentage": 98.11, "elapsed_time": "1:57:04", "remaining_time": "0:02:15", "throughput": 5486.36, "total_tokens": 38538336} {"current_steps": 63245, "total_steps": 64460, "loss": 0.1468, "lr": 1.0836383033206998e-08, "epoch": 19.623022029165373, "percentage": 98.12, "elapsed_time": "1:57:04", "remaining_time": "0:02:14", "throughput": 5486.28, "total_tokens": 38540416} {"current_steps": 63250, "total_steps": 64460, "loss": 0.0701, "lr": 1.0747483128066837e-08, "epoch": 19.62457337883959, "percentage": 98.12, "elapsed_time": "1:57:05", "remaining_time": "0:02:14", "throughput": 5486.31, "total_tokens": 38543552} {"current_steps": 63255, "total_steps": 64460, "loss": 0.2638, "lr": 1.0658948994218266e-08, "epoch": 19.62612472851381, "percentage": 98.13, "elapsed_time": "1:57:05", "remaining_time": "0:02:13", "throughput": 5486.26, "total_tokens": 38545888} {"current_steps": 63260, "total_steps": 64460, "loss": 0.158, "lr": 1.057078063815109e-08, "epoch": 19.627676078188024, "percentage": 98.14, "elapsed_time": "1:57:06", "remaining_time": "0:02:13", "throughput": 5486.26, "total_tokens": 38548768} {"current_steps": 63265, "total_steps": 64460, "loss": 0.0921, "lr": 1.0482978066329585e-08, "epoch": 19.62922742786224, "percentage": 98.15, "elapsed_time": "1:57:07", "remaining_time": "0:02:12", "throughput": 5486.36, "total_tokens": 38552832} {"current_steps": 63270, "total_steps": 64460, "loss": 0.1782, "lr": 1.039554128519027e-08, "epoch": 19.630778777536456, "percentage": 98.15, "elapsed_time": "1:57:07", "remaining_time": "0:02:12", "throughput": 5486.29, "total_tokens": 38555328} {"current_steps": 63275, "total_steps": 64460, "loss": 0.1226, "lr": 1.0308470301143569e-08, "epoch": 19.632330127210672, "percentage": 98.16, "elapsed_time": "1:57:08", "remaining_time": "0:02:11", "throughput": 5486.34, "total_tokens": 38558880} {"current_steps": 63280, "total_steps": 64460, "loss": 0.2945, "lr": 1.0221765120573269e-08, "epoch": 19.63388147688489, "percentage": 98.17, "elapsed_time": "1:57:08", "remaining_time": "0:02:11", "throughput": 5486.27, "total_tokens": 38561248} {"current_steps": 63285, "total_steps": 64460, "loss": 0.2384, "lr": 1.0135425749834837e-08, "epoch": 19.635432826559107, "percentage": 98.18, "elapsed_time": "1:57:09", "remaining_time": "0:02:10", "throughput": 5486.26, "total_tokens": 38563872} {"current_steps": 63290, "total_steps": 64460, "loss": 0.2721, "lr": 1.004945219525877e-08, "epoch": 19.636984176233323, "percentage": 98.18, "elapsed_time": "1:57:09", "remaining_time": "0:02:09", "throughput": 5486.29, "total_tokens": 38567040} {"current_steps": 63295, "total_steps": 64460, "loss": 0.1695, "lr": 9.963844463147798e-09, "epoch": 19.63853552590754, "percentage": 98.19, "elapsed_time": "1:57:10", "remaining_time": "0:02:09", "throughput": 5486.27, "total_tokens": 38569536} {"current_steps": 63300, "total_steps": 64460, "loss": 0.1142, "lr": 9.878602559777462e-09, "epoch": 19.640086875581755, "percentage": 98.2, "elapsed_time": "1:57:10", "remaining_time": "0:02:08", "throughput": 5486.39, "total_tokens": 38573760} {"current_steps": 63305, "total_steps": 64460, "loss": 0.1606, "lr": 9.793726491397759e-09, "epoch": 19.641638225255974, "percentage": 98.21, "elapsed_time": "1:57:11", "remaining_time": "0:02:08", "throughput": 5486.41, "total_tokens": 38576672} {"current_steps": 63310, "total_steps": 64460, "loss": 0.1643, "lr": 9.709216264230936e-09, "epoch": 19.64318957493019, "percentage": 98.22, "elapsed_time": "1:57:11", "remaining_time": "0:02:07", "throughput": 5486.46, "total_tokens": 38580000} {"current_steps": 63315, "total_steps": 64460, "loss": 0.1069, "lr": 9.625071884472036e-09, "epoch": 19.644740924604406, "percentage": 98.22, "elapsed_time": "1:57:12", "remaining_time": "0:02:07", "throughput": 5486.48, "total_tokens": 38582816} {"current_steps": 63320, "total_steps": 64460, "loss": 0.0866, "lr": 9.54129335829057e-09, "epoch": 19.646292274278622, "percentage": 98.23, "elapsed_time": "1:57:12", "remaining_time": "0:02:06", "throughput": 5486.42, "total_tokens": 38584992} {"current_steps": 63325, "total_steps": 64460, "loss": 0.2215, "lr": 9.457880691827736e-09, "epoch": 19.647843623952838, "percentage": 98.24, "elapsed_time": "1:57:13", "remaining_time": "0:02:06", "throughput": 5486.37, "total_tokens": 38587488} {"current_steps": 63330, "total_steps": 64460, "loss": 0.2123, "lr": 9.374833891199752e-09, "epoch": 19.649394973627057, "percentage": 98.25, "elapsed_time": "1:57:13", "remaining_time": "0:02:05", "throughput": 5486.41, "total_tokens": 38590752} {"current_steps": 63335, "total_steps": 64460, "loss": 0.0715, "lr": 9.292152962493972e-09, "epoch": 19.650946323301273, "percentage": 98.25, "elapsed_time": "1:57:14", "remaining_time": "0:02:04", "throughput": 5486.46, "total_tokens": 38593952} {"current_steps": 63340, "total_steps": 64460, "loss": 0.2848, "lr": 9.209837911772212e-09, "epoch": 19.65249767297549, "percentage": 98.26, "elapsed_time": "1:57:14", "remaining_time": "0:02:04", "throughput": 5486.49, "total_tokens": 38596992} {"current_steps": 63345, "total_steps": 64460, "loss": 0.1409, "lr": 9.127888745069091e-09, "epoch": 19.654049022649705, "percentage": 98.27, "elapsed_time": "1:57:15", "remaining_time": "0:02:03", "throughput": 5486.46, "total_tokens": 38599456} {"current_steps": 63350, "total_steps": 64460, "loss": 0.2118, "lr": 9.04630546839258e-09, "epoch": 19.65560037232392, "percentage": 98.28, "elapsed_time": "1:57:15", "remaining_time": "0:02:03", "throughput": 5486.5, "total_tokens": 38602528} {"current_steps": 63355, "total_steps": 64460, "loss": 0.1549, "lr": 8.96508808772345e-09, "epoch": 19.65715172199814, "percentage": 98.29, "elapsed_time": "1:57:16", "remaining_time": "0:02:02", "throughput": 5486.52, "total_tokens": 38605280} {"current_steps": 63360, "total_steps": 64460, "loss": 0.1306, "lr": 8.884236609016384e-09, "epoch": 19.658703071672356, "percentage": 98.29, "elapsed_time": "1:57:16", "remaining_time": "0:02:02", "throughput": 5486.5, "total_tokens": 38607872} {"current_steps": 63365, "total_steps": 64460, "loss": 0.0746, "lr": 8.803751038198305e-09, "epoch": 19.660254421346572, "percentage": 98.3, "elapsed_time": "1:57:17", "remaining_time": "0:02:01", "throughput": 5486.58, "total_tokens": 38611840} {"current_steps": 63370, "total_steps": 64460, "loss": 0.1032, "lr": 8.723631381169496e-09, "epoch": 19.661805771020788, "percentage": 98.31, "elapsed_time": "1:57:17", "remaining_time": "0:02:01", "throughput": 5486.52, "total_tokens": 38614080} {"current_steps": 63375, "total_steps": 64460, "loss": 0.1451, "lr": 8.6438776438047e-09, "epoch": 19.663357120695004, "percentage": 98.32, "elapsed_time": "1:57:18", "remaining_time": "0:02:00", "throughput": 5486.41, "total_tokens": 38616224} {"current_steps": 63380, "total_steps": 64460, "loss": 0.1458, "lr": 8.564489831949241e-09, "epoch": 19.66490847036922, "percentage": 98.32, "elapsed_time": "1:57:19", "remaining_time": "0:01:59", "throughput": 5486.35, "total_tokens": 38618816} {"current_steps": 63385, "total_steps": 64460, "loss": 0.1612, "lr": 8.48546795142513e-09, "epoch": 19.66645982004344, "percentage": 98.33, "elapsed_time": "1:57:19", "remaining_time": "0:01:59", "throughput": 5486.42, "total_tokens": 38622240} {"current_steps": 63390, "total_steps": 64460, "loss": 0.1026, "lr": 8.406812008023846e-09, "epoch": 19.668011169717655, "percentage": 98.34, "elapsed_time": "1:57:20", "remaining_time": "0:01:58", "throughput": 5486.56, "total_tokens": 38626912} {"current_steps": 63395, "total_steps": 64460, "loss": 0.1129, "lr": 8.328522007512996e-09, "epoch": 19.66956251939187, "percentage": 98.35, "elapsed_time": "1:57:20", "remaining_time": "0:01:58", "throughput": 5486.62, "total_tokens": 38630272} {"current_steps": 63400, "total_steps": 64460, "loss": 0.1948, "lr": 8.250597955631878e-09, "epoch": 19.671113869066087, "percentage": 98.36, "elapsed_time": "1:57:21", "remaining_time": "0:01:57", "throughput": 5486.64, "total_tokens": 38633408} {"current_steps": 63405, "total_steps": 64460, "loss": 0.1633, "lr": 8.173039858092591e-09, "epoch": 19.672665218740303, "percentage": 98.36, "elapsed_time": "1:57:21", "remaining_time": "0:01:57", "throughput": 5486.69, "total_tokens": 38636640} {"current_steps": 63410, "total_steps": 64460, "loss": 0.1127, "lr": 8.095847720581696e-09, "epoch": 19.674216568414522, "percentage": 98.37, "elapsed_time": "1:57:22", "remaining_time": "0:01:56", "throughput": 5486.74, "total_tokens": 38640096} {"current_steps": 63415, "total_steps": 64460, "loss": 0.1598, "lr": 8.019021548758554e-09, "epoch": 19.675767918088738, "percentage": 98.38, "elapsed_time": "1:57:22", "remaining_time": "0:01:56", "throughput": 5486.73, "total_tokens": 38642720} {"current_steps": 63420, "total_steps": 64460, "loss": 0.1737, "lr": 7.942561348254219e-09, "epoch": 19.677319267762954, "percentage": 98.39, "elapsed_time": "1:57:23", "remaining_time": "0:01:55", "throughput": 5486.71, "total_tokens": 38645280} {"current_steps": 63425, "total_steps": 64460, "loss": 0.1477, "lr": 7.866467124675315e-09, "epoch": 19.67887061743717, "percentage": 98.39, "elapsed_time": "1:57:23", "remaining_time": "0:01:54", "throughput": 5486.71, "total_tokens": 38648064} {"current_steps": 63430, "total_steps": 64460, "loss": 0.1294, "lr": 7.790738883600712e-09, "epoch": 19.680421967111386, "percentage": 98.4, "elapsed_time": "1:57:24", "remaining_time": "0:01:54", "throughput": 5486.68, "total_tokens": 38650528} {"current_steps": 63435, "total_steps": 64460, "loss": 0.2157, "lr": 7.715376630580972e-09, "epoch": 19.681973316785605, "percentage": 98.41, "elapsed_time": "1:57:24", "remaining_time": "0:01:53", "throughput": 5486.74, "total_tokens": 38653728} {"current_steps": 63440, "total_steps": 64460, "loss": 0.131, "lr": 7.640380371141675e-09, "epoch": 19.68352466645982, "percentage": 98.42, "elapsed_time": "1:57:25", "remaining_time": "0:01:53", "throughput": 5486.81, "total_tokens": 38657248} {"current_steps": 63445, "total_steps": 64460, "loss": 0.2278, "lr": 7.565750110780646e-09, "epoch": 19.685076016134037, "percentage": 98.43, "elapsed_time": "1:57:26", "remaining_time": "0:01:52", "throughput": 5486.82, "total_tokens": 38660256} {"current_steps": 63450, "total_steps": 64460, "loss": 0.1699, "lr": 7.491485854969616e-09, "epoch": 19.686627365808253, "percentage": 98.43, "elapsed_time": "1:57:26", "remaining_time": "0:01:52", "throughput": 5486.79, "total_tokens": 38662656} {"current_steps": 63455, "total_steps": 64460, "loss": 0.1152, "lr": 7.417587609152566e-09, "epoch": 19.68817871548247, "percentage": 98.44, "elapsed_time": "1:57:26", "remaining_time": "0:01:51", "throughput": 5486.75, "total_tokens": 38664928} {"current_steps": 63460, "total_steps": 64460, "loss": 0.1101, "lr": 7.344055378747938e-09, "epoch": 19.689730065156688, "percentage": 98.45, "elapsed_time": "1:57:27", "remaining_time": "0:01:51", "throughput": 5486.8, "total_tokens": 38668256} {"current_steps": 63465, "total_steps": 64460, "loss": 0.1698, "lr": 7.2708891691453125e-09, "epoch": 19.691281414830904, "percentage": 98.46, "elapsed_time": "1:57:27", "remaining_time": "0:01:50", "throughput": 5486.79, "total_tokens": 38670784} {"current_steps": 63470, "total_steps": 64460, "loss": 0.0891, "lr": 7.198088985709839e-09, "epoch": 19.69283276450512, "percentage": 98.46, "elapsed_time": "1:57:28", "remaining_time": "0:01:49", "throughput": 5486.8, "total_tokens": 38673728} {"current_steps": 63475, "total_steps": 64460, "loss": 0.1528, "lr": 7.1256548337778066e-09, "epoch": 19.694384114179336, "percentage": 98.47, "elapsed_time": "1:57:29", "remaining_time": "0:01:49", "throughput": 5486.85, "total_tokens": 38677088} {"current_steps": 63480, "total_steps": 64460, "loss": 0.1977, "lr": 7.053586718659966e-09, "epoch": 19.69593546385355, "percentage": 98.48, "elapsed_time": "1:57:29", "remaining_time": "0:01:48", "throughput": 5486.84, "total_tokens": 38679776} {"current_steps": 63485, "total_steps": 64460, "loss": 0.1104, "lr": 6.9818846456393145e-09, "epoch": 19.697486813527767, "percentage": 98.49, "elapsed_time": "1:57:30", "remaining_time": "0:01:48", "throughput": 5486.94, "total_tokens": 38684064} {"current_steps": 63490, "total_steps": 64460, "loss": 0.1785, "lr": 6.910548619972201e-09, "epoch": 19.699038163201987, "percentage": 98.5, "elapsed_time": "1:57:30", "remaining_time": "0:01:47", "throughput": 5486.98, "total_tokens": 38687648} {"current_steps": 63495, "total_steps": 64460, "loss": 0.1222, "lr": 6.8395786468899995e-09, "epoch": 19.700589512876203, "percentage": 98.5, "elapsed_time": "1:57:31", "remaining_time": "0:01:47", "throughput": 5487.07, "total_tokens": 38691072} {"current_steps": 63500, "total_steps": 64460, "loss": 0.138, "lr": 6.7689747315935476e-09, "epoch": 19.70214086255042, "percentage": 98.51, "elapsed_time": "1:57:31", "remaining_time": "0:01:46", "throughput": 5487.05, "total_tokens": 38693792} {"current_steps": 63505, "total_steps": 64460, "loss": 0.1047, "lr": 6.69873687926037e-09, "epoch": 19.703692212224635, "percentage": 98.52, "elapsed_time": "1:57:32", "remaining_time": "0:01:46", "throughput": 5487.1, "total_tokens": 38697536} {"current_steps": 63510, "total_steps": 64460, "loss": 0.1596, "lr": 6.628865095039683e-09, "epoch": 19.70524356189885, "percentage": 98.53, "elapsed_time": "1:57:32", "remaining_time": "0:01:45", "throughput": 5487.1, "total_tokens": 38700224} {"current_steps": 63515, "total_steps": 64460, "loss": 0.162, "lr": 6.5593593840529436e-09, "epoch": 19.70679491157307, "percentage": 98.53, "elapsed_time": "1:57:33", "remaining_time": "0:01:44", "throughput": 5487.2, "total_tokens": 38704288} {"current_steps": 63520, "total_steps": 64460, "loss": 0.2062, "lr": 6.490219751396631e-09, "epoch": 19.708346261247286, "percentage": 98.54, "elapsed_time": "1:57:34", "remaining_time": "0:01:44", "throughput": 5487.32, "total_tokens": 38708736} {"current_steps": 63525, "total_steps": 64460, "loss": 0.1409, "lr": 6.4214462021389145e-09, "epoch": 19.7098976109215, "percentage": 98.55, "elapsed_time": "1:57:34", "remaining_time": "0:01:43", "throughput": 5487.42, "total_tokens": 38713632} {"current_steps": 63530, "total_steps": 64460, "loss": 0.2419, "lr": 6.353038741322426e-09, "epoch": 19.711448960595717, "percentage": 98.56, "elapsed_time": "1:57:35", "remaining_time": "0:01:43", "throughput": 5487.44, "total_tokens": 38716352} {"current_steps": 63535, "total_steps": 64460, "loss": 0.1496, "lr": 6.284997373961488e-09, "epoch": 19.713000310269933, "percentage": 98.57, "elapsed_time": "1:57:36", "remaining_time": "0:01:42", "throughput": 5487.45, "total_tokens": 38719904} {"current_steps": 63540, "total_steps": 64460, "loss": 0.0787, "lr": 6.217322105044887e-09, "epoch": 19.714551659944153, "percentage": 98.57, "elapsed_time": "1:57:36", "remaining_time": "0:01:42", "throughput": 5487.39, "total_tokens": 38722272} {"current_steps": 63545, "total_steps": 64460, "loss": 0.2217, "lr": 6.150012939533656e-09, "epoch": 19.71610300961837, "percentage": 98.58, "elapsed_time": "1:57:37", "remaining_time": "0:01:41", "throughput": 5487.44, "total_tokens": 38725376} {"current_steps": 63550, "total_steps": 64460, "loss": 0.2058, "lr": 6.083069882362736e-09, "epoch": 19.717654359292585, "percentage": 98.59, "elapsed_time": "1:57:37", "remaining_time": "0:01:41", "throughput": 5487.48, "total_tokens": 38729664} {"current_steps": 63555, "total_steps": 64460, "loss": 0.1639, "lr": 6.016492938439311e-09, "epoch": 19.7192057089668, "percentage": 98.6, "elapsed_time": "1:57:38", "remaining_time": "0:01:40", "throughput": 5487.51, "total_tokens": 38732672} {"current_steps": 63560, "total_steps": 64460, "loss": 0.1558, "lr": 5.950282112645034e-09, "epoch": 19.720757058641016, "percentage": 98.6, "elapsed_time": "1:57:38", "remaining_time": "0:01:39", "throughput": 5487.5, "total_tokens": 38735424} {"current_steps": 63565, "total_steps": 64460, "loss": 0.11, "lr": 5.884437409833243e-09, "epoch": 19.722308408315236, "percentage": 98.61, "elapsed_time": "1:57:39", "remaining_time": "0:01:39", "throughput": 5487.52, "total_tokens": 38738304} {"current_steps": 63570, "total_steps": 64460, "loss": 0.1518, "lr": 5.81895883483119e-09, "epoch": 19.72385975798945, "percentage": 98.62, "elapsed_time": "1:57:39", "remaining_time": "0:01:38", "throughput": 5487.56, "total_tokens": 38741600} {"current_steps": 63575, "total_steps": 64460, "loss": 0.1598, "lr": 5.753846392439477e-09, "epoch": 19.725411107663668, "percentage": 98.63, "elapsed_time": "1:57:40", "remaining_time": "0:01:38", "throughput": 5487.57, "total_tokens": 38744416} {"current_steps": 63580, "total_steps": 64460, "loss": 0.1683, "lr": 5.689100087431509e-09, "epoch": 19.726962457337883, "percentage": 98.63, "elapsed_time": "1:57:40", "remaining_time": "0:01:37", "throughput": 5487.61, "total_tokens": 38747808} {"current_steps": 63585, "total_steps": 64460, "loss": 0.0847, "lr": 5.624719924554045e-09, "epoch": 19.7285138070121, "percentage": 98.64, "elapsed_time": "1:57:41", "remaining_time": "0:01:37", "throughput": 5487.72, "total_tokens": 38752704} {"current_steps": 63590, "total_steps": 64460, "loss": 0.2074, "lr": 5.560705908527197e-09, "epoch": 19.73006515668632, "percentage": 98.65, "elapsed_time": "1:57:42", "remaining_time": "0:01:36", "throughput": 5487.81, "total_tokens": 38756448} {"current_steps": 63595, "total_steps": 64460, "loss": 0.1444, "lr": 5.497058044043324e-09, "epoch": 19.731616506360535, "percentage": 98.66, "elapsed_time": "1:57:42", "remaining_time": "0:01:36", "throughput": 5487.75, "total_tokens": 38758912} {"current_steps": 63600, "total_steps": 64460, "loss": 0.0815, "lr": 5.4337763357686925e-09, "epoch": 19.73316785603475, "percentage": 98.67, "elapsed_time": "1:57:43", "remaining_time": "0:01:35", "throughput": 5487.8, "total_tokens": 38762336} {"current_steps": 63605, "total_steps": 64460, "loss": 0.1754, "lr": 5.370860788342924e-09, "epoch": 19.734719205708966, "percentage": 98.67, "elapsed_time": "1:57:43", "remaining_time": "0:01:34", "throughput": 5487.79, "total_tokens": 38764960} {"current_steps": 63610, "total_steps": 64460, "loss": 0.1095, "lr": 5.308311406378441e-09, "epoch": 19.736270555383182, "percentage": 98.68, "elapsed_time": "1:57:44", "remaining_time": "0:01:34", "throughput": 5487.88, "total_tokens": 38768480} {"current_steps": 63615, "total_steps": 64460, "loss": 0.1385, "lr": 5.246128194460465e-09, "epoch": 19.7378219050574, "percentage": 98.69, "elapsed_time": "1:57:44", "remaining_time": "0:01:33", "throughput": 5487.93, "total_tokens": 38771456} {"current_steps": 63620, "total_steps": 64460, "loss": 0.2026, "lr": 5.184311157148125e-09, "epoch": 19.739373254731618, "percentage": 98.7, "elapsed_time": "1:57:45", "remaining_time": "0:01:33", "throughput": 5487.94, "total_tokens": 38774560} {"current_steps": 63625, "total_steps": 64460, "loss": 0.1506, "lr": 5.122860298973353e-09, "epoch": 19.740924604405834, "percentage": 98.7, "elapsed_time": "1:57:46", "remaining_time": "0:01:32", "throughput": 5487.98, "total_tokens": 38778400} {"current_steps": 63630, "total_steps": 64460, "loss": 0.2147, "lr": 5.061775624440879e-09, "epoch": 19.74247595408005, "percentage": 98.71, "elapsed_time": "1:57:46", "remaining_time": "0:01:32", "throughput": 5487.98, "total_tokens": 38781248} {"current_steps": 63635, "total_steps": 64460, "loss": 0.0987, "lr": 5.001057138029341e-09, "epoch": 19.744027303754265, "percentage": 98.72, "elapsed_time": "1:57:47", "remaining_time": "0:01:31", "throughput": 5487.98, "total_tokens": 38783936} {"current_steps": 63640, "total_steps": 64460, "loss": 0.0992, "lr": 4.940704844190181e-09, "epoch": 19.74557865342848, "percentage": 98.73, "elapsed_time": "1:57:47", "remaining_time": "0:01:31", "throughput": 5488.04, "total_tokens": 38787264} {"current_steps": 63645, "total_steps": 64460, "loss": 0.1808, "lr": 4.880718747347635e-09, "epoch": 19.7471300031027, "percentage": 98.74, "elapsed_time": "1:57:48", "remaining_time": "0:01:30", "throughput": 5488.05, "total_tokens": 38790240} {"current_steps": 63650, "total_steps": 64460, "loss": 0.151, "lr": 4.8210988518992975e-09, "epoch": 19.748681352776916, "percentage": 98.74, "elapsed_time": "1:57:48", "remaining_time": "0:01:29", "throughput": 5488.11, "total_tokens": 38794080} {"current_steps": 63655, "total_steps": 64460, "loss": 0.0752, "lr": 4.761845162216117e-09, "epoch": 19.750232702451132, "percentage": 98.75, "elapsed_time": "1:57:49", "remaining_time": "0:01:29", "throughput": 5488.12, "total_tokens": 38797056} {"current_steps": 63660, "total_steps": 64460, "loss": 0.0967, "lr": 4.7029576826423954e-09, "epoch": 19.75178405212535, "percentage": 98.76, "elapsed_time": "1:57:49", "remaining_time": "0:01:28", "throughput": 5488.18, "total_tokens": 38800672} {"current_steps": 63665, "total_steps": 64460, "loss": 0.1559, "lr": 4.64443641749468e-09, "epoch": 19.753335401799564, "percentage": 98.77, "elapsed_time": "1:57:50", "remaining_time": "0:01:28", "throughput": 5488.16, "total_tokens": 38803168} {"current_steps": 63670, "total_steps": 64460, "loss": 0.1438, "lr": 4.586281371063983e-09, "epoch": 19.754886751473784, "percentage": 98.77, "elapsed_time": "1:57:50", "remaining_time": "0:01:27", "throughput": 5488.24, "total_tokens": 38807104} {"current_steps": 63675, "total_steps": 64460, "loss": 0.1238, "lr": 4.528492547613006e-09, "epoch": 19.756438101148, "percentage": 98.78, "elapsed_time": "1:57:51", "remaining_time": "0:01:27", "throughput": 5488.33, "total_tokens": 38811520} {"current_steps": 63680, "total_steps": 64460, "loss": 0.1192, "lr": 4.471069951378915e-09, "epoch": 19.757989450822215, "percentage": 98.79, "elapsed_time": "1:57:52", "remaining_time": "0:01:26", "throughput": 5488.31, "total_tokens": 38814048} {"current_steps": 63685, "total_steps": 64460, "loss": 0.0872, "lr": 4.414013586571675e-09, "epoch": 19.75954080049643, "percentage": 98.8, "elapsed_time": "1:57:52", "remaining_time": "0:01:26", "throughput": 5488.35, "total_tokens": 38816992} {"current_steps": 63690, "total_steps": 64460, "loss": 0.0772, "lr": 4.3573234573734965e-09, "epoch": 19.761092150170647, "percentage": 98.81, "elapsed_time": "1:57:53", "remaining_time": "0:01:25", "throughput": 5488.45, "total_tokens": 38821024} {"current_steps": 63695, "total_steps": 64460, "loss": 0.0951, "lr": 4.3009995679405e-09, "epoch": 19.762643499844867, "percentage": 98.81, "elapsed_time": "1:57:53", "remaining_time": "0:01:24", "throughput": 5488.48, "total_tokens": 38823904} {"current_steps": 63700, "total_steps": 64460, "loss": 0.1224, "lr": 4.245041922402715e-09, "epoch": 19.764194849519082, "percentage": 98.82, "elapsed_time": "1:57:54", "remaining_time": "0:01:24", "throughput": 5488.54, "total_tokens": 38827584} {"current_steps": 63705, "total_steps": 64460, "loss": 0.1296, "lr": 4.18945052486186e-09, "epoch": 19.7657461991933, "percentage": 98.83, "elapsed_time": "1:57:54", "remaining_time": "0:01:23", "throughput": 5488.56, "total_tokens": 38830720} {"current_steps": 63710, "total_steps": 64460, "loss": 0.164, "lr": 4.1342253793935635e-09, "epoch": 19.767297548867514, "percentage": 98.84, "elapsed_time": "1:57:55", "remaining_time": "0:01:23", "throughput": 5488.6, "total_tokens": 38833824} {"current_steps": 63715, "total_steps": 64460, "loss": 0.0811, "lr": 4.0793664900457e-09, "epoch": 19.76884889854173, "percentage": 98.84, "elapsed_time": "1:57:55", "remaining_time": "0:01:22", "throughput": 5488.64, "total_tokens": 38836800} {"current_steps": 63720, "total_steps": 64460, "loss": 0.1439, "lr": 4.024873860841716e-09, "epoch": 19.77040024821595, "percentage": 98.85, "elapsed_time": "1:57:56", "remaining_time": "0:01:22", "throughput": 5488.6, "total_tokens": 38839104} {"current_steps": 63725, "total_steps": 64460, "loss": 0.1737, "lr": 3.970747495775085e-09, "epoch": 19.771951597890165, "percentage": 98.86, "elapsed_time": "1:57:56", "remaining_time": "0:01:21", "throughput": 5488.63, "total_tokens": 38842112} {"current_steps": 63730, "total_steps": 64460, "loss": 0.107, "lr": 3.916987398814853e-09, "epoch": 19.77350294756438, "percentage": 98.87, "elapsed_time": "1:57:57", "remaining_time": "0:01:21", "throughput": 5488.62, "total_tokens": 38844768} {"current_steps": 63735, "total_steps": 64460, "loss": 0.1959, "lr": 3.863593573901758e-09, "epoch": 19.775054297238597, "percentage": 98.88, "elapsed_time": "1:57:57", "remaining_time": "0:01:20", "throughput": 5488.66, "total_tokens": 38847776} {"current_steps": 63740, "total_steps": 64460, "loss": 0.0744, "lr": 3.8105660249504465e-09, "epoch": 19.776605646912813, "percentage": 98.88, "elapsed_time": "1:57:58", "remaining_time": "0:01:19", "throughput": 5488.7, "total_tokens": 38850656} {"current_steps": 63745, "total_steps": 64460, "loss": 0.1179, "lr": 3.757904755848363e-09, "epoch": 19.77815699658703, "percentage": 98.89, "elapsed_time": "1:57:58", "remaining_time": "0:01:19", "throughput": 5488.67, "total_tokens": 38852992} {"current_steps": 63750, "total_steps": 64460, "loss": 0.102, "lr": 3.705609770456309e-09, "epoch": 19.77970834626125, "percentage": 98.9, "elapsed_time": "1:57:59", "remaining_time": "0:01:18", "throughput": 5488.81, "total_tokens": 38857760} {"current_steps": 63755, "total_steps": 64460, "loss": 0.1154, "lr": 3.6536810726078843e-09, "epoch": 19.781259695935464, "percentage": 98.91, "elapsed_time": "1:57:59", "remaining_time": "0:01:18", "throughput": 5488.82, "total_tokens": 38860416} {"current_steps": 63760, "total_steps": 64460, "loss": 0.1016, "lr": 3.602118666110599e-09, "epoch": 19.78281104560968, "percentage": 98.91, "elapsed_time": "1:58:00", "remaining_time": "0:01:17", "throughput": 5488.91, "total_tokens": 38864416} {"current_steps": 63765, "total_steps": 64460, "loss": 0.0773, "lr": 3.550922554743652e-09, "epoch": 19.784362395283896, "percentage": 98.92, "elapsed_time": "1:58:01", "remaining_time": "0:01:17", "throughput": 5488.95, "total_tokens": 38867488} {"current_steps": 63770, "total_steps": 64460, "loss": 0.1105, "lr": 3.500092742261263e-09, "epoch": 19.785913744958112, "percentage": 98.93, "elapsed_time": "1:58:01", "remaining_time": "0:01:16", "throughput": 5488.96, "total_tokens": 38870048} {"current_steps": 63775, "total_steps": 64460, "loss": 0.1336, "lr": 3.44962923238934e-09, "epoch": 19.78746509463233, "percentage": 98.94, "elapsed_time": "1:58:02", "remaining_time": "0:01:16", "throughput": 5489.03, "total_tokens": 38873504} {"current_steps": 63780, "total_steps": 64460, "loss": 0.0758, "lr": 3.3995320288277013e-09, "epoch": 19.789016444306547, "percentage": 98.95, "elapsed_time": "1:58:02", "remaining_time": "0:01:15", "throughput": 5488.98, "total_tokens": 38875584} {"current_steps": 63785, "total_steps": 64460, "loss": 0.1134, "lr": 3.3498011352489643e-09, "epoch": 19.790567793980763, "percentage": 98.95, "elapsed_time": "1:58:02", "remaining_time": "0:01:14", "throughput": 5489.01, "total_tokens": 38878592} {"current_steps": 63790, "total_steps": 64460, "loss": 0.1005, "lr": 3.3004365552991026e-09, "epoch": 19.79211914365498, "percentage": 98.96, "elapsed_time": "1:58:03", "remaining_time": "0:01:14", "throughput": 5489.05, "total_tokens": 38881632} {"current_steps": 63795, "total_steps": 64460, "loss": 0.2271, "lr": 3.251438292596887e-09, "epoch": 19.793670493329195, "percentage": 98.97, "elapsed_time": "1:58:03", "remaining_time": "0:01:13", "throughput": 5489.05, "total_tokens": 38884288} {"current_steps": 63800, "total_steps": 64460, "loss": 0.1706, "lr": 3.2028063507344443e-09, "epoch": 19.795221843003414, "percentage": 98.98, "elapsed_time": "1:58:04", "remaining_time": "0:01:13", "throughput": 5489.15, "total_tokens": 38888192} {"current_steps": 63805, "total_steps": 64460, "loss": 0.1301, "lr": 3.154540733277256e-09, "epoch": 19.79677319267763, "percentage": 98.98, "elapsed_time": "1:58:05", "remaining_time": "0:01:12", "throughput": 5489.15, "total_tokens": 38890752} {"current_steps": 63810, "total_steps": 64460, "loss": 0.1036, "lr": 3.106641443763603e-09, "epoch": 19.798324542351846, "percentage": 98.99, "elapsed_time": "1:58:05", "remaining_time": "0:01:12", "throughput": 5489.15, "total_tokens": 38893376} {"current_steps": 63815, "total_steps": 64460, "loss": 0.1402, "lr": 3.059108485705675e-09, "epoch": 19.799875892026062, "percentage": 99.0, "elapsed_time": "1:58:05", "remaining_time": "0:01:11", "throughput": 5489.16, "total_tokens": 38896000} {"current_steps": 63820, "total_steps": 64460, "loss": 0.135, "lr": 3.011941862587353e-09, "epoch": 19.801427241700278, "percentage": 99.01, "elapsed_time": "1:58:06", "remaining_time": "0:01:11", "throughput": 5489.24, "total_tokens": 38899360} {"current_steps": 63825, "total_steps": 64460, "loss": 0.1932, "lr": 2.965141577866981e-09, "epoch": 19.802978591374497, "percentage": 99.01, "elapsed_time": "1:58:06", "remaining_time": "0:01:10", "throughput": 5489.24, "total_tokens": 38902080} {"current_steps": 63830, "total_steps": 64460, "loss": 0.1163, "lr": 2.9187076349757037e-09, "epoch": 19.804529941048713, "percentage": 99.02, "elapsed_time": "1:58:07", "remaining_time": "0:01:09", "throughput": 5489.28, "total_tokens": 38904992} {"current_steps": 63835, "total_steps": 64460, "loss": 0.1456, "lr": 2.8726400373169093e-09, "epoch": 19.80608129072293, "percentage": 99.03, "elapsed_time": "1:58:07", "remaining_time": "0:01:09", "throughput": 5489.24, "total_tokens": 38907328} {"current_steps": 63840, "total_steps": 64460, "loss": 0.1641, "lr": 2.826938788269007e-09, "epoch": 19.807632640397145, "percentage": 99.04, "elapsed_time": "1:58:08", "remaining_time": "0:01:08", "throughput": 5489.26, "total_tokens": 38910528} {"current_steps": 63845, "total_steps": 64460, "loss": 0.0999, "lr": 2.781603891181539e-09, "epoch": 19.80918399007136, "percentage": 99.05, "elapsed_time": "1:58:08", "remaining_time": "0:01:08", "throughput": 5489.27, "total_tokens": 38913344} {"current_steps": 63850, "total_steps": 64460, "loss": 0.1513, "lr": 2.7366353493785135e-09, "epoch": 19.81073533974558, "percentage": 99.05, "elapsed_time": "1:58:09", "remaining_time": "0:01:07", "throughput": 5489.25, "total_tokens": 38915872} {"current_steps": 63855, "total_steps": 64460, "loss": 0.0992, "lr": 2.692033166156738e-09, "epoch": 19.812286689419796, "percentage": 99.06, "elapsed_time": "1:58:10", "remaining_time": "0:01:07", "throughput": 5489.29, "total_tokens": 38919136} {"current_steps": 63860, "total_steps": 64460, "loss": 0.1687, "lr": 2.6477973447858185e-09, "epoch": 19.813838039094012, "percentage": 99.07, "elapsed_time": "1:58:10", "remaining_time": "0:01:06", "throughput": 5489.26, "total_tokens": 38921568} {"current_steps": 63865, "total_steps": 64460, "loss": 0.2274, "lr": 2.603927888508717e-09, "epoch": 19.815389388768228, "percentage": 99.08, "elapsed_time": "1:58:10", "remaining_time": "0:01:06", "throughput": 5489.24, "total_tokens": 38924032} {"current_steps": 63870, "total_steps": 64460, "loss": 0.1099, "lr": 2.56042480054175e-09, "epoch": 19.816940738442444, "percentage": 99.08, "elapsed_time": "1:58:11", "remaining_time": "0:01:05", "throughput": 5489.29, "total_tokens": 38927072} {"current_steps": 63875, "total_steps": 64460, "loss": 0.2458, "lr": 2.5172880840745873e-09, "epoch": 19.818492088116663, "percentage": 99.09, "elapsed_time": "1:58:12", "remaining_time": "0:01:04", "throughput": 5489.32, "total_tokens": 38930752} {"current_steps": 63880, "total_steps": 64460, "loss": 0.1575, "lr": 2.4745177422685897e-09, "epoch": 19.82004343779088, "percentage": 99.1, "elapsed_time": "1:58:12", "remaining_time": "0:01:04", "throughput": 5489.36, "total_tokens": 38933792} {"current_steps": 63885, "total_steps": 64460, "loss": 0.1264, "lr": 2.432113778260137e-09, "epoch": 19.821594787465095, "percentage": 99.11, "elapsed_time": "1:58:13", "remaining_time": "0:01:03", "throughput": 5489.38, "total_tokens": 38937056} {"current_steps": 63890, "total_steps": 64460, "loss": 0.193, "lr": 2.3900761951584086e-09, "epoch": 19.82314613713931, "percentage": 99.12, "elapsed_time": "1:58:13", "remaining_time": "0:01:03", "throughput": 5489.35, "total_tokens": 38939680} {"current_steps": 63895, "total_steps": 64460, "loss": 0.2734, "lr": 2.3484049960442732e-09, "epoch": 19.824697486813527, "percentage": 99.12, "elapsed_time": "1:58:14", "remaining_time": "0:01:02", "throughput": 5489.32, "total_tokens": 38942272} {"current_steps": 63900, "total_steps": 64460, "loss": 0.124, "lr": 2.3071001839730655e-09, "epoch": 19.826248836487743, "percentage": 99.13, "elapsed_time": "1:58:14", "remaining_time": "0:01:02", "throughput": 5489.27, "total_tokens": 38944800} {"current_steps": 63905, "total_steps": 64460, "loss": 0.1242, "lr": 2.2661617619729183e-09, "epoch": 19.827800186161962, "percentage": 99.14, "elapsed_time": "1:58:15", "remaining_time": "0:01:01", "throughput": 5489.31, "total_tokens": 38948064} {"current_steps": 63910, "total_steps": 64460, "loss": 0.1071, "lr": 2.225589733044764e-09, "epoch": 19.829351535836178, "percentage": 99.15, "elapsed_time": "1:58:15", "remaining_time": "0:01:01", "throughput": 5489.36, "total_tokens": 38951008} {"current_steps": 63915, "total_steps": 64460, "loss": 0.1705, "lr": 2.1853841001640008e-09, "epoch": 19.830902885510394, "percentage": 99.15, "elapsed_time": "1:58:16", "remaining_time": "0:01:00", "throughput": 5489.4, "total_tokens": 38954176} {"current_steps": 63920, "total_steps": 64460, "loss": 0.1447, "lr": 2.1455448662771603e-09, "epoch": 19.83245423518461, "percentage": 99.16, "elapsed_time": "1:58:16", "remaining_time": "0:00:59", "throughput": 5489.37, "total_tokens": 38956672} {"current_steps": 63925, "total_steps": 64460, "loss": 0.1379, "lr": 2.106072034305795e-09, "epoch": 19.834005584858826, "percentage": 99.17, "elapsed_time": "1:58:17", "remaining_time": "0:00:59", "throughput": 5489.43, "total_tokens": 38960000} {"current_steps": 63930, "total_steps": 64460, "loss": 0.0897, "lr": 2.0669656071425902e-09, "epoch": 19.835556934533045, "percentage": 99.18, "elapsed_time": "1:58:17", "remaining_time": "0:00:58", "throughput": 5489.42, "total_tokens": 38962656} {"current_steps": 63935, "total_steps": 64460, "loss": 0.1116, "lr": 2.0282255876558075e-09, "epoch": 19.83710828420726, "percentage": 99.19, "elapsed_time": "1:58:18", "remaining_time": "0:00:58", "throughput": 5489.47, "total_tokens": 38965888} {"current_steps": 63940, "total_steps": 64460, "loss": 0.1415, "lr": 1.9898519786848426e-09, "epoch": 19.838659633881477, "percentage": 99.19, "elapsed_time": "1:58:18", "remaining_time": "0:00:57", "throughput": 5489.51, "total_tokens": 38968896} {"current_steps": 63945, "total_steps": 64460, "loss": 0.1008, "lr": 1.9518447830429997e-09, "epoch": 19.840210983555693, "percentage": 99.2, "elapsed_time": "1:58:19", "remaining_time": "0:00:57", "throughput": 5489.49, "total_tokens": 38971840} {"current_steps": 63950, "total_steps": 64460, "loss": 0.1468, "lr": 1.9142040035163844e-09, "epoch": 19.84176233322991, "percentage": 99.21, "elapsed_time": "1:58:19", "remaining_time": "0:00:56", "throughput": 5489.48, "total_tokens": 38974400} {"current_steps": 63955, "total_steps": 64460, "loss": 0.1958, "lr": 1.876929642865011e-09, "epoch": 19.843313682904128, "percentage": 99.22, "elapsed_time": "1:58:20", "remaining_time": "0:00:56", "throughput": 5489.48, "total_tokens": 38976896} {"current_steps": 63960, "total_steps": 64460, "loss": 0.0684, "lr": 1.8400217038211376e-09, "epoch": 19.844865032578344, "percentage": 99.22, "elapsed_time": "1:58:20", "remaining_time": "0:00:55", "throughput": 5489.51, "total_tokens": 38979936} {"current_steps": 63965, "total_steps": 64460, "loss": 0.1303, "lr": 1.8034801890909338e-09, "epoch": 19.84641638225256, "percentage": 99.23, "elapsed_time": "1:58:21", "remaining_time": "0:00:54", "throughput": 5489.49, "total_tokens": 38982272} {"current_steps": 63970, "total_steps": 64460, "loss": 0.1747, "lr": 1.767305101353367e-09, "epoch": 19.847967731926776, "percentage": 99.24, "elapsed_time": "1:58:21", "remaining_time": "0:00:54", "throughput": 5489.56, "total_tokens": 38985824} {"current_steps": 63975, "total_steps": 64460, "loss": 0.1624, "lr": 1.7314964432596503e-09, "epoch": 19.84951908160099, "percentage": 99.25, "elapsed_time": "1:58:22", "remaining_time": "0:00:53", "throughput": 5489.59, "total_tokens": 38988864} {"current_steps": 63980, "total_steps": 64460, "loss": 0.1964, "lr": 1.696054217436016e-09, "epoch": 19.85107043127521, "percentage": 99.26, "elapsed_time": "1:58:22", "remaining_time": "0:00:53", "throughput": 5489.63, "total_tokens": 38991776} {"current_steps": 63985, "total_steps": 64460, "loss": 0.1749, "lr": 1.6609784264803862e-09, "epoch": 19.852621780949427, "percentage": 99.26, "elapsed_time": "1:58:23", "remaining_time": "0:00:52", "throughput": 5489.68, "total_tokens": 38995104} {"current_steps": 63990, "total_steps": 64460, "loss": 0.1881, "lr": 1.6262690729640373e-09, "epoch": 19.854173130623643, "percentage": 99.27, "elapsed_time": "1:58:23", "remaining_time": "0:00:52", "throughput": 5489.68, "total_tokens": 38997760} {"current_steps": 63995, "total_steps": 64460, "loss": 0.116, "lr": 1.5919261594321556e-09, "epoch": 19.85572448029786, "percentage": 99.28, "elapsed_time": "1:58:24", "remaining_time": "0:00:51", "throughput": 5489.75, "total_tokens": 39001152} {"current_steps": 64000, "total_steps": 64460, "loss": 0.1132, "lr": 1.5579496884016166e-09, "epoch": 19.857275829972075, "percentage": 99.29, "elapsed_time": "1:58:24", "remaining_time": "0:00:51", "throughput": 5489.75, "total_tokens": 39003872} {"current_steps": 64005, "total_steps": 64460, "loss": 0.1524, "lr": 1.524339662364316e-09, "epoch": 19.85882717964629, "percentage": 99.29, "elapsed_time": "1:58:25", "remaining_time": "0:00:50", "throughput": 5489.83, "total_tokens": 39007392} {"current_steps": 64010, "total_steps": 64460, "loss": 0.1797, "lr": 1.4910960837832833e-09, "epoch": 19.86037852932051, "percentage": 99.3, "elapsed_time": "1:58:26", "remaining_time": "0:00:49", "throughput": 5489.9, "total_tokens": 39011264} {"current_steps": 64015, "total_steps": 64460, "loss": 0.1622, "lr": 1.4582189550960135e-09, "epoch": 19.861929878994726, "percentage": 99.31, "elapsed_time": "1:58:26", "remaining_time": "0:00:49", "throughput": 5489.93, "total_tokens": 39014432} {"current_steps": 64020, "total_steps": 64460, "loss": 0.1761, "lr": 1.4257082787133557e-09, "epoch": 19.86348122866894, "percentage": 99.32, "elapsed_time": "1:58:27", "remaining_time": "0:00:48", "throughput": 5489.9, "total_tokens": 39016832} {"current_steps": 64025, "total_steps": 64460, "loss": 0.1067, "lr": 1.3935640570178489e-09, "epoch": 19.865032578343158, "percentage": 99.33, "elapsed_time": "1:58:27", "remaining_time": "0:00:48", "throughput": 5489.93, "total_tokens": 39019680} {"current_steps": 64030, "total_steps": 64460, "loss": 0.1824, "lr": 1.361786292366496e-09, "epoch": 19.866583928017373, "percentage": 99.33, "elapsed_time": "1:58:27", "remaining_time": "0:00:47", "throughput": 5489.93, "total_tokens": 39022304} {"current_steps": 64035, "total_steps": 64460, "loss": 0.1369, "lr": 1.3303749870891003e-09, "epoch": 19.868135277691593, "percentage": 99.34, "elapsed_time": "1:58:28", "remaining_time": "0:00:47", "throughput": 5489.97, "total_tokens": 39025568} {"current_steps": 64040, "total_steps": 64460, "loss": 0.1097, "lr": 1.2993301434882644e-09, "epoch": 19.86968662736581, "percentage": 99.35, "elapsed_time": "1:58:29", "remaining_time": "0:00:46", "throughput": 5490.0, "total_tokens": 39028512} {"current_steps": 64045, "total_steps": 64460, "loss": 0.1078, "lr": 1.2686517638399454e-09, "epoch": 19.871237977040025, "percentage": 99.36, "elapsed_time": "1:58:29", "remaining_time": "0:00:46", "throughput": 5490.04, "total_tokens": 39031520} {"current_steps": 64050, "total_steps": 64460, "loss": 0.2328, "lr": 1.2383398503934551e-09, "epoch": 19.87278932671424, "percentage": 99.36, "elapsed_time": "1:58:30", "remaining_time": "0:00:45", "throughput": 5490.08, "total_tokens": 39034592} {"current_steps": 64055, "total_steps": 64460, "loss": 0.2218, "lr": 1.2083944053709052e-09, "epoch": 19.874340676388456, "percentage": 99.37, "elapsed_time": "1:58:30", "remaining_time": "0:00:44", "throughput": 5490.07, "total_tokens": 39037024} {"current_steps": 64060, "total_steps": 64460, "loss": 0.1268, "lr": 1.1788154309672061e-09, "epoch": 19.875892026062676, "percentage": 99.38, "elapsed_time": "1:58:30", "remaining_time": "0:00:44", "throughput": 5490.08, "total_tokens": 39039616} {"current_steps": 64065, "total_steps": 64460, "loss": 0.2547, "lr": 1.149602929351179e-09, "epoch": 19.877443375736892, "percentage": 99.39, "elapsed_time": "1:58:31", "remaining_time": "0:00:43", "throughput": 5490.13, "total_tokens": 39042752} {"current_steps": 64070, "total_steps": 64460, "loss": 0.0781, "lr": 1.120756902664999e-09, "epoch": 19.878994725411108, "percentage": 99.39, "elapsed_time": "1:58:31", "remaining_time": "0:00:43", "throughput": 5490.12, "total_tokens": 39045536} {"current_steps": 64075, "total_steps": 64460, "loss": 0.177, "lr": 1.0922773530225306e-09, "epoch": 19.880546075085324, "percentage": 99.4, "elapsed_time": "1:58:32", "remaining_time": "0:00:42", "throughput": 5490.15, "total_tokens": 39048640} {"current_steps": 64080, "total_steps": 64460, "loss": 0.1425, "lr": 1.0641642825126585e-09, "epoch": 19.88209742475954, "percentage": 99.41, "elapsed_time": "1:58:32", "remaining_time": "0:00:42", "throughput": 5490.14, "total_tokens": 39051008} {"current_steps": 64085, "total_steps": 64460, "loss": 0.171, "lr": 1.0364176931948466e-09, "epoch": 19.88364877443376, "percentage": 99.42, "elapsed_time": "1:58:33", "remaining_time": "0:00:41", "throughput": 5490.1, "total_tokens": 39053280} {"current_steps": 64090, "total_steps": 64460, "loss": 0.1161, "lr": 1.0090375871052439e-09, "epoch": 19.885200124107975, "percentage": 99.43, "elapsed_time": "1:58:33", "remaining_time": "0:00:41", "throughput": 5490.09, "total_tokens": 39055840} {"current_steps": 64095, "total_steps": 64460, "loss": 0.1324, "lr": 9.82023966249468e-10, "epoch": 19.88675147378219, "percentage": 99.43, "elapsed_time": "1:58:34", "remaining_time": "0:00:40", "throughput": 5490.11, "total_tokens": 39058560} {"current_steps": 64100, "total_steps": 64460, "loss": 0.1753, "lr": 9.55376832608712e-10, "epoch": 19.888302823456407, "percentage": 99.44, "elapsed_time": "1:58:34", "remaining_time": "0:00:39", "throughput": 5490.05, "total_tokens": 39060736} {"current_steps": 64105, "total_steps": 64460, "loss": 0.1009, "lr": 9.290961881358584e-10, "epoch": 19.889854173130622, "percentage": 99.45, "elapsed_time": "1:58:35", "remaining_time": "0:00:39", "throughput": 5490.08, "total_tokens": 39063744} {"current_steps": 64110, "total_steps": 64460, "loss": 0.1269, "lr": 9.031820347588094e-10, "epoch": 19.891405522804842, "percentage": 99.46, "elapsed_time": "1:58:35", "remaining_time": "0:00:38", "throughput": 5490.12, "total_tokens": 39066656} {"current_steps": 64115, "total_steps": 64460, "loss": 0.1091, "lr": 8.776343743766014e-10, "epoch": 19.892956872479058, "percentage": 99.46, "elapsed_time": "1:58:36", "remaining_time": "0:00:38", "throughput": 5490.15, "total_tokens": 39069568} {"current_steps": 64120, "total_steps": 64460, "loss": 0.2651, "lr": 8.524532088621806e-10, "epoch": 19.894508222153274, "percentage": 99.47, "elapsed_time": "1:58:36", "remaining_time": "0:00:37", "throughput": 5490.18, "total_tokens": 39072800} {"current_steps": 64125, "total_steps": 64460, "loss": 0.1437, "lr": 8.27638540061293e-10, "epoch": 19.89605957182749, "percentage": 99.48, "elapsed_time": "1:58:37", "remaining_time": "0:00:37", "throughput": 5490.11, "total_tokens": 39074912} {"current_steps": 64130, "total_steps": 64460, "loss": 0.1186, "lr": 8.03190369794149e-10, "epoch": 19.897610921501705, "percentage": 99.49, "elapsed_time": "1:58:37", "remaining_time": "0:00:36", "throughput": 5490.15, "total_tokens": 39078080} {"current_steps": 64135, "total_steps": 64460, "loss": 0.1061, "lr": 7.791086998520936e-10, "epoch": 19.899162271175925, "percentage": 99.5, "elapsed_time": "1:58:38", "remaining_time": "0:00:36", "throughput": 5490.2, "total_tokens": 39081088} {"current_steps": 64140, "total_steps": 64460, "loss": 0.1399, "lr": 7.553935320009365e-10, "epoch": 19.90071362085014, "percentage": 99.5, "elapsed_time": "1:58:38", "remaining_time": "0:00:35", "throughput": 5490.28, "total_tokens": 39085056} {"current_steps": 64145, "total_steps": 64460, "loss": 0.1802, "lr": 7.32044867979842e-10, "epoch": 19.902264970524357, "percentage": 99.51, "elapsed_time": "1:58:39", "remaining_time": "0:00:34", "throughput": 5490.25, "total_tokens": 39087680} {"current_steps": 64150, "total_steps": 64460, "loss": 0.149, "lr": 7.090627094996638e-10, "epoch": 19.903816320198572, "percentage": 99.52, "elapsed_time": "1:58:39", "remaining_time": "0:00:34", "throughput": 5490.23, "total_tokens": 39090080} {"current_steps": 64155, "total_steps": 64460, "loss": 0.1536, "lr": 6.864470582457206e-10, "epoch": 19.90536766987279, "percentage": 99.53, "elapsed_time": "1:58:40", "remaining_time": "0:00:33", "throughput": 5490.27, "total_tokens": 39093856} {"current_steps": 64160, "total_steps": 64460, "loss": 0.1433, "lr": 6.641979158761302e-10, "epoch": 19.906919019547004, "percentage": 99.53, "elapsed_time": "1:58:41", "remaining_time": "0:00:33", "throughput": 5490.34, "total_tokens": 39097440} {"current_steps": 64165, "total_steps": 64460, "loss": 0.1999, "lr": 6.423152840218105e-10, "epoch": 19.908470369221224, "percentage": 99.54, "elapsed_time": "1:58:41", "remaining_time": "0:00:32", "throughput": 5490.38, "total_tokens": 39100544} {"current_steps": 64170, "total_steps": 64460, "loss": 0.1966, "lr": 6.207991642864785e-10, "epoch": 19.91002171889544, "percentage": 99.55, "elapsed_time": "1:58:42", "remaining_time": "0:00:32", "throughput": 5490.46, "total_tokens": 39104608} {"current_steps": 64175, "total_steps": 64460, "loss": 0.3279, "lr": 5.996495582488715e-10, "epoch": 19.911573068569655, "percentage": 99.56, "elapsed_time": "1:58:42", "remaining_time": "0:00:31", "throughput": 5490.5, "total_tokens": 39107584} {"current_steps": 64180, "total_steps": 64460, "loss": 0.1623, "lr": 5.788664674583056e-10, "epoch": 19.91312441824387, "percentage": 99.57, "elapsed_time": "1:58:43", "remaining_time": "0:00:31", "throughput": 5490.51, "total_tokens": 39110784} {"current_steps": 64185, "total_steps": 64460, "loss": 0.1851, "lr": 5.584498934385618e-10, "epoch": 19.914675767918087, "percentage": 99.57, "elapsed_time": "1:58:43", "remaining_time": "0:00:30", "throughput": 5490.58, "total_tokens": 39114336} {"current_steps": 64190, "total_steps": 64460, "loss": 0.1923, "lr": 5.383998376873312e-10, "epoch": 19.916227117592307, "percentage": 99.58, "elapsed_time": "1:58:44", "remaining_time": "0:00:29", "throughput": 5490.62, "total_tokens": 39117216} {"current_steps": 64195, "total_steps": 64460, "loss": 0.2639, "lr": 5.187163016734387e-10, "epoch": 19.917778467266523, "percentage": 99.59, "elapsed_time": "1:58:45", "remaining_time": "0:00:29", "throughput": 5490.62, "total_tokens": 39121056} {"current_steps": 64200, "total_steps": 64460, "loss": 0.0769, "lr": 4.993992868401743e-10, "epoch": 19.91932981694074, "percentage": 99.6, "elapsed_time": "1:58:45", "remaining_time": "0:00:28", "throughput": 5490.59, "total_tokens": 39123456} {"current_steps": 64205, "total_steps": 64460, "loss": 0.2085, "lr": 4.804487946041824e-10, "epoch": 19.920881166614954, "percentage": 99.6, "elapsed_time": "1:58:46", "remaining_time": "0:00:28", "throughput": 5490.62, "total_tokens": 39126560} {"current_steps": 64210, "total_steps": 64460, "loss": 0.1569, "lr": 4.6186482635435236e-10, "epoch": 19.92243251628917, "percentage": 99.61, "elapsed_time": "1:58:46", "remaining_time": "0:00:27", "throughput": 5490.55, "total_tokens": 39128736} {"current_steps": 64215, "total_steps": 64460, "loss": 0.1312, "lr": 4.436473834534827e-10, "epoch": 19.92398386596339, "percentage": 99.62, "elapsed_time": "1:58:47", "remaining_time": "0:00:27", "throughput": 5490.51, "total_tokens": 39131200} {"current_steps": 64220, "total_steps": 64460, "loss": 0.1379, "lr": 4.257964672366166e-10, "epoch": 19.925535215637606, "percentage": 99.63, "elapsed_time": "1:58:47", "remaining_time": "0:00:26", "throughput": 5490.52, "total_tokens": 39133920} {"current_steps": 64225, "total_steps": 64460, "loss": 0.1063, "lr": 4.0831207901270707e-10, "epoch": 19.92708656531182, "percentage": 99.64, "elapsed_time": "1:58:48", "remaining_time": "0:00:26", "throughput": 5490.52, "total_tokens": 39136640} {"current_steps": 64230, "total_steps": 64460, "loss": 0.1721, "lr": 3.911942200635066e-10, "epoch": 19.928637914986037, "percentage": 99.64, "elapsed_time": "1:58:48", "remaining_time": "0:00:25", "throughput": 5490.52, "total_tokens": 39139424} {"current_steps": 64235, "total_steps": 64460, "loss": 0.1407, "lr": 3.744428916441223e-10, "epoch": 19.930189264660253, "percentage": 99.65, "elapsed_time": "1:58:49", "remaining_time": "0:00:24", "throughput": 5490.5, "total_tokens": 39141984} {"current_steps": 64240, "total_steps": 64460, "loss": 0.2043, "lr": 3.580580949824608e-10, "epoch": 19.931740614334473, "percentage": 99.66, "elapsed_time": "1:58:49", "remaining_time": "0:00:24", "throughput": 5490.6, "total_tokens": 39145760} {"current_steps": 64245, "total_steps": 64460, "loss": 0.1391, "lr": 3.4203983127978345e-10, "epoch": 19.93329196400869, "percentage": 99.67, "elapsed_time": "1:58:50", "remaining_time": "0:00:23", "throughput": 5490.52, "total_tokens": 39148096} {"current_steps": 64250, "total_steps": 64460, "loss": 0.0983, "lr": 3.2638810171070625e-10, "epoch": 19.934843313682904, "percentage": 99.67, "elapsed_time": "1:58:50", "remaining_time": "0:00:23", "throughput": 5490.52, "total_tokens": 39150752} {"current_steps": 64255, "total_steps": 64460, "loss": 0.1324, "lr": 3.111029074215344e-10, "epoch": 19.93639466335712, "percentage": 99.68, "elapsed_time": "1:58:51", "remaining_time": "0:00:22", "throughput": 5490.52, "total_tokens": 39153600} {"current_steps": 64260, "total_steps": 64460, "loss": 0.1658, "lr": 2.9618424953470337e-10, "epoch": 19.937946013031336, "percentage": 99.69, "elapsed_time": "1:58:51", "remaining_time": "0:00:22", "throughput": 5490.58, "total_tokens": 39156960} {"current_steps": 64265, "total_steps": 64460, "loss": 0.1496, "lr": 2.8163212914211756e-10, "epoch": 19.939497362705552, "percentage": 99.7, "elapsed_time": "1:58:52", "remaining_time": "0:00:21", "throughput": 5490.59, "total_tokens": 39159712} {"current_steps": 64270, "total_steps": 64460, "loss": 0.0969, "lr": 2.674465473118115e-10, "epoch": 19.94104871237977, "percentage": 99.71, "elapsed_time": "1:58:52", "remaining_time": "0:00:21", "throughput": 5490.7, "total_tokens": 39163648} {"current_steps": 64275, "total_steps": 64460, "loss": 0.2048, "lr": 2.53627505082954e-10, "epoch": 19.942600062053987, "percentage": 99.71, "elapsed_time": "1:58:53", "remaining_time": "0:00:20", "throughput": 5490.68, "total_tokens": 39166144} {"current_steps": 64280, "total_steps": 64460, "loss": 0.1967, "lr": 2.4017500346973367e-10, "epoch": 19.944151411728203, "percentage": 99.72, "elapsed_time": "1:58:53", "remaining_time": "0:00:19", "throughput": 5490.68, "total_tokens": 39168736} {"current_steps": 64285, "total_steps": 64460, "loss": 0.1533, "lr": 2.270890434569184e-10, "epoch": 19.94570276140242, "percentage": 99.73, "elapsed_time": "1:58:54", "remaining_time": "0:00:19", "throughput": 5490.67, "total_tokens": 39171232} {"current_steps": 64290, "total_steps": 64460, "loss": 0.0741, "lr": 2.1436962600540623e-10, "epoch": 19.947254111076635, "percentage": 99.74, "elapsed_time": "1:58:54", "remaining_time": "0:00:18", "throughput": 5490.74, "total_tokens": 39174688} {"current_steps": 64295, "total_steps": 64460, "loss": 0.1304, "lr": 2.0201675204667426e-10, "epoch": 19.948805460750854, "percentage": 99.74, "elapsed_time": "1:58:55", "remaining_time": "0:00:18", "throughput": 5490.7, "total_tokens": 39177056} {"current_steps": 64300, "total_steps": 64460, "loss": 0.0994, "lr": 1.9003042248610937e-10, "epoch": 19.95035681042507, "percentage": 99.75, "elapsed_time": "1:58:55", "remaining_time": "0:00:17", "throughput": 5490.7, "total_tokens": 39179712} {"current_steps": 64305, "total_steps": 64460, "loss": 0.1884, "lr": 1.784106382035633e-10, "epoch": 19.951908160099286, "percentage": 99.76, "elapsed_time": "1:58:56", "remaining_time": "0:00:17", "throughput": 5490.73, "total_tokens": 39182560} {"current_steps": 64310, "total_steps": 64460, "loss": 0.2314, "lr": 1.67157400050022e-10, "epoch": 19.953459509773502, "percentage": 99.77, "elapsed_time": "1:58:56", "remaining_time": "0:00:16", "throughput": 5490.66, "total_tokens": 39184736} {"current_steps": 64315, "total_steps": 64460, "loss": 0.2638, "lr": 1.562707088503812e-10, "epoch": 19.955010859447718, "percentage": 99.78, "elapsed_time": "1:58:57", "remaining_time": "0:00:16", "throughput": 5490.64, "total_tokens": 39187168} {"current_steps": 64320, "total_steps": 64460, "loss": 0.0827, "lr": 1.4575056540344636e-10, "epoch": 19.956562209121937, "percentage": 99.78, "elapsed_time": "1:58:57", "remaining_time": "0:00:15", "throughput": 5490.67, "total_tokens": 39190016} {"current_steps": 64325, "total_steps": 64460, "loss": 0.1542, "lr": 1.3559697048026732e-10, "epoch": 19.958113558796153, "percentage": 99.79, "elapsed_time": "1:58:58", "remaining_time": "0:00:14", "throughput": 5490.66, "total_tokens": 39192608} {"current_steps": 64330, "total_steps": 64460, "loss": 0.1941, "lr": 1.2580992482469358e-10, "epoch": 19.95966490847037, "percentage": 99.8, "elapsed_time": "1:58:58", "remaining_time": "0:00:14", "throughput": 5490.74, "total_tokens": 39196160} {"current_steps": 64335, "total_steps": 64460, "loss": 0.0864, "lr": 1.1638942915503937e-10, "epoch": 19.961216258144585, "percentage": 99.81, "elapsed_time": "1:58:59", "remaining_time": "0:00:13", "throughput": 5490.7, "total_tokens": 39198336} {"current_steps": 64340, "total_steps": 64460, "loss": 0.1453, "lr": 1.0733548416130834e-10, "epoch": 19.9627676078188, "percentage": 99.81, "elapsed_time": "1:58:59", "remaining_time": "0:00:13", "throughput": 5490.76, "total_tokens": 39202240} {"current_steps": 64345, "total_steps": 64460, "loss": 0.1896, "lr": 9.864809050741386e-11, "epoch": 19.96431895749302, "percentage": 99.82, "elapsed_time": "1:59:00", "remaining_time": "0:00:12", "throughput": 5490.7, "total_tokens": 39204800} {"current_steps": 64350, "total_steps": 64460, "loss": 0.1536, "lr": 9.032724883006883e-11, "epoch": 19.965870307167236, "percentage": 99.83, "elapsed_time": "1:59:00", "remaining_time": "0:00:12", "throughput": 5490.68, "total_tokens": 39207840} {"current_steps": 64355, "total_steps": 64460, "loss": 0.1677, "lr": 8.23729597398959e-11, "epoch": 19.967421656841452, "percentage": 99.84, "elapsed_time": "1:59:01", "remaining_time": "0:00:11", "throughput": 5490.65, "total_tokens": 39210272} {"current_steps": 64360, "total_steps": 64460, "loss": 0.1139, "lr": 7.478522381976217e-11, "epoch": 19.968973006515668, "percentage": 99.84, "elapsed_time": "1:59:01", "remaining_time": "0:00:11", "throughput": 5490.63, "total_tokens": 39212704} {"current_steps": 64365, "total_steps": 64460, "loss": 0.1149, "lr": 6.756404162588936e-11, "epoch": 19.970524356189884, "percentage": 99.85, "elapsed_time": "1:59:02", "remaining_time": "0:00:10", "throughput": 5490.77, "total_tokens": 39218272} {"current_steps": 64370, "total_steps": 64460, "loss": 0.1223, "lr": 6.070941368729877e-11, "epoch": 19.972075705864103, "percentage": 99.86, "elapsed_time": "1:59:03", "remaining_time": "0:00:09", "throughput": 5490.77, "total_tokens": 39221088} {"current_steps": 64375, "total_steps": 64460, "loss": 0.1978, "lr": 5.4221340506921404e-11, "epoch": 19.97362705553832, "percentage": 99.87, "elapsed_time": "1:59:03", "remaining_time": "0:00:09", "throughput": 5490.82, "total_tokens": 39224512} {"current_steps": 64380, "total_steps": 64460, "loss": 0.168, "lr": 4.809982256048784e-11, "epoch": 19.975178405212535, "percentage": 99.88, "elapsed_time": "1:59:04", "remaining_time": "0:00:08", "throughput": 5490.83, "total_tokens": 39227808} {"current_steps": 64385, "total_steps": 64460, "loss": 0.1477, "lr": 4.234486029652818e-11, "epoch": 19.97672975488675, "percentage": 99.88, "elapsed_time": "1:59:04", "remaining_time": "0:00:08", "throughput": 5490.79, "total_tokens": 39230592} {"current_steps": 64390, "total_steps": 64460, "loss": 0.114, "lr": 3.6956454136927164e-11, "epoch": 19.978281104560967, "percentage": 99.89, "elapsed_time": "1:59:05", "remaining_time": "0:00:07", "throughput": 5490.85, "total_tokens": 39233920} {"current_steps": 64395, "total_steps": 64460, "loss": 0.1451, "lr": 3.1934604476924206e-11, "epoch": 19.979832454235186, "percentage": 99.9, "elapsed_time": "1:59:05", "remaining_time": "0:00:07", "throughput": 5490.87, "total_tokens": 39236864} {"current_steps": 64400, "total_steps": 64460, "loss": 0.2533, "lr": 2.727931168455822e-11, "epoch": 19.981383803909402, "percentage": 99.91, "elapsed_time": "1:59:06", "remaining_time": "0:00:06", "throughput": 5490.84, "total_tokens": 39239264} {"current_steps": 64405, "total_steps": 64460, "loss": 0.1113, "lr": 2.2990576101222795e-11, "epoch": 19.982935153583618, "percentage": 99.91, "elapsed_time": "1:59:06", "remaining_time": "0:00:06", "throughput": 5490.92, "total_tokens": 39242848} {"current_steps": 64410, "total_steps": 64460, "loss": 0.1975, "lr": 1.9068398041111046e-11, "epoch": 19.984486503257834, "percentage": 99.92, "elapsed_time": "1:59:07", "remaining_time": "0:00:05", "throughput": 5490.92, "total_tokens": 39245792} {"current_steps": 64415, "total_steps": 64460, "loss": 0.1313, "lr": 1.5512777792325852e-11, "epoch": 19.98603785293205, "percentage": 99.93, "elapsed_time": "1:59:07", "remaining_time": "0:00:04", "throughput": 5490.94, "total_tokens": 39248672} {"current_steps": 64420, "total_steps": 64460, "loss": 0.114, "lr": 1.2323715614659394e-11, "epoch": 19.987589202606266, "percentage": 99.94, "elapsed_time": "1:59:08", "remaining_time": "0:00:04", "throughput": 5490.89, "total_tokens": 39251104} {"current_steps": 64425, "total_steps": 64460, "loss": 0.1476, "lr": 9.501211742368732e-12, "epoch": 19.989140552280485, "percentage": 99.95, "elapsed_time": "1:59:08", "remaining_time": "0:00:03", "throughput": 5490.86, "total_tokens": 39253696} {"current_steps": 64430, "total_steps": 64460, "loss": 0.2119, "lr": 7.0452663825104626e-12, "epoch": 19.9906919019547, "percentage": 99.95, "elapsed_time": "1:59:09", "remaining_time": "0:00:03", "throughput": 5490.84, "total_tokens": 39256416} {"current_steps": 64435, "total_steps": 64460, "loss": 0.1702, "lr": 4.955879715495826e-12, "epoch": 19.992243251628917, "percentage": 99.96, "elapsed_time": "1:59:09", "remaining_time": "0:00:02", "throughput": 5490.84, "total_tokens": 39259296} {"current_steps": 64440, "total_steps": 64460, "loss": 0.1929, "lr": 3.2330518934253764e-12, "epoch": 19.993794601303133, "percentage": 99.97, "elapsed_time": "1:59:10", "remaining_time": "0:00:02", "throughput": 5490.87, "total_tokens": 39262560} {"current_steps": 64445, "total_steps": 64460, "loss": 0.1209, "lr": 1.87678304341965e-12, "epoch": 19.99534595097735, "percentage": 99.98, "elapsed_time": "1:59:11", "remaining_time": "0:00:01", "throughput": 5490.91, "total_tokens": 39265536} {"current_steps": 64450, "total_steps": 64460, "loss": 0.0997, "lr": 8.870732648436076e-13, "epoch": 19.99689730065157, "percentage": 99.98, "elapsed_time": "1:59:11", "remaining_time": "0:00:01", "throughput": 5490.95, "total_tokens": 39268608} {"current_steps": 64455, "total_steps": 64460, "loss": 0.3129, "lr": 2.6392262986174587e-13, "epoch": 19.998448650325784, "percentage": 99.99, "elapsed_time": "1:59:12", "remaining_time": "0:00:00", "throughput": 5490.96, "total_tokens": 39271680} {"current_steps": 64460, "total_steps": 64460, "loss": 0.1512, "lr": 7.331183993208869e-15, "epoch": 20.0, "percentage": 100.0, "elapsed_time": "1:59:12", "remaining_time": "0:00:00", "throughput": 5490.88, "total_tokens": 39274528} {"current_steps": 64460, "total_steps": 64460, "eval_loss": 0.40142932534217834, "epoch": 20.0, "percentage": 100.0, "elapsed_time": "1:59:47", "remaining_time": "0:00:00", "throughput": 5464.6, "total_tokens": 39274528} {"current_steps": 64460, "total_steps": 64460, "epoch": 20.0, "percentage": 100.0, "elapsed_time": "1:59:50", "remaining_time": "0:00:00", "throughput": 5461.89, "total_tokens": 39274528}