diff --git "a/trainer_log.jsonl" "b/trainer_log.jsonl" new file mode 100644--- /dev/null +++ "b/trainer_log.jsonl" @@ -0,0 +1,1230 @@ +{"current_steps": 5, "total_steps": 122600, "loss": 8.3174, "lr": 3.262642740619902e-07, "epoch": 0.0008156606851549756, "percentage": 0.0, "elapsed_time": "0:00:02", "remaining_time": "16:10:22", "throughput": 4271.81, "total_tokens": 10144} +{"current_steps": 10, "total_steps": 122600, "loss": 7.4675, "lr": 7.34094616639478e-07, "epoch": 0.0016313213703099511, "percentage": 0.01, "elapsed_time": "0:00:04", "remaining_time": "13:52:06", "throughput": 5083.61, "total_tokens": 20704} +{"current_steps": 15, "total_steps": 122600, "loss": 6.5126, "lr": 1.1419249592169658e-06, "epoch": 0.0024469820554649264, "percentage": 0.01, "elapsed_time": "0:00:05", "remaining_time": "13:21:59", "throughput": 5450.95, "total_tokens": 32096} +{"current_steps": 20, "total_steps": 122600, "loss": 5.3189, "lr": 1.5497553017944535e-06, "epoch": 0.0032626427406199023, "percentage": 0.02, "elapsed_time": "0:00:07", "remaining_time": "12:50:57", "throughput": 5600.97, "total_tokens": 42272} +{"current_steps": 25, "total_steps": 122600, "loss": 3.7183, "lr": 1.957585644371941e-06, "epoch": 0.004078303425774877, "percentage": 0.02, "elapsed_time": "0:00:09", "remaining_time": "12:49:46", "throughput": 5710.37, "total_tokens": 53792} +{"current_steps": 30, "total_steps": 122600, "loss": 3.0498, "lr": 2.365415986949429e-06, "epoch": 0.004893964110929853, "percentage": 0.02, "elapsed_time": "0:00:11", "remaining_time": "12:44:59", "throughput": 5773.76, "total_tokens": 64864} +{"current_steps": 35, "total_steps": 122600, "loss": 2.1791, "lr": 2.7732463295269165e-06, "epoch": 0.005709624796084829, "percentage": 0.03, "elapsed_time": "0:00:13", "remaining_time": "12:46:05", "throughput": 5826.58, "total_tokens": 76480} +{"current_steps": 40, "total_steps": 122600, "loss": 1.7123, "lr": 3.1810766721044044e-06, "epoch": 0.0065252854812398045, "percentage": 0.03, "elapsed_time": "0:00:14", "remaining_time": "12:41:51", "throughput": 5872.79, "total_tokens": 87616} +{"current_steps": 45, "total_steps": 122600, "loss": 1.2501, "lr": 3.5889070146818927e-06, "epoch": 0.00734094616639478, "percentage": 0.04, "elapsed_time": "0:00:16", "remaining_time": "12:37:44", "throughput": 5907.88, "total_tokens": 98624} +{"current_steps": 50, "total_steps": 122600, "loss": 0.7328, "lr": 3.99673735725938e-06, "epoch": 0.008156606851549755, "percentage": 0.04, "elapsed_time": "0:00:18", "remaining_time": "12:31:07", "throughput": 5922.36, "total_tokens": 108896} +{"current_steps": 55, "total_steps": 122600, "loss": 0.6449, "lr": 4.404567699836868e-06, "epoch": 0.00897226753670473, "percentage": 0.04, "elapsed_time": "0:00:20", "remaining_time": "12:30:05", "throughput": 5937.73, "total_tokens": 119936} +{"current_steps": 60, "total_steps": 122600, "loss": 0.4664, "lr": 4.812398042414356e-06, "epoch": 0.009787928221859706, "percentage": 0.05, "elapsed_time": "0:00:22", "remaining_time": "12:31:06", "throughput": 5960.19, "total_tokens": 131520} +{"current_steps": 65, "total_steps": 122600, "loss": 0.5114, "lr": 5.2202283849918435e-06, "epoch": 0.010603588907014683, "percentage": 0.05, "elapsed_time": "0:00:23", "remaining_time": "12:31:30", "throughput": 5974.86, "total_tokens": 142912} +{"current_steps": 70, "total_steps": 122600, "loss": 0.4, "lr": 5.628058727569331e-06, "epoch": 0.011419249592169658, "percentage": 0.06, "elapsed_time": "0:00:25", "remaining_time": "12:29:08", "throughput": 5981.67, "total_tokens": 153600} +{"current_steps": 75, "total_steps": 122600, "loss": 0.4806, "lr": 6.035889070146819e-06, "epoch": 0.012234910277324634, "percentage": 0.06, "elapsed_time": "0:00:27", "remaining_time": "12:28:01", "throughput": 5990.55, "total_tokens": 164576} +{"current_steps": 80, "total_steps": 122600, "loss": 0.4291, "lr": 6.443719412724307e-06, "epoch": 0.013050570962479609, "percentage": 0.07, "elapsed_time": "0:00:29", "remaining_time": "12:24:43", "throughput": 5995.0, "total_tokens": 174912} +{"current_steps": 85, "total_steps": 122600, "loss": 0.3929, "lr": 6.851549755301794e-06, "epoch": 0.013866231647634585, "percentage": 0.07, "elapsed_time": "0:00:30", "remaining_time": "12:21:33", "throughput": 6003.16, "total_tokens": 185312} +{"current_steps": 90, "total_steps": 122600, "loss": 0.3971, "lr": 7.2593800978792825e-06, "epoch": 0.01468189233278956, "percentage": 0.07, "elapsed_time": "0:00:32", "remaining_time": "12:21:54", "throughput": 6012.12, "total_tokens": 196608} +{"current_steps": 95, "total_steps": 122600, "loss": 0.5684, "lr": 7.66721044045677e-06, "epoch": 0.015497553017944535, "percentage": 0.08, "elapsed_time": "0:00:34", "remaining_time": "12:26:41", "throughput": 6027.4, "total_tokens": 209408} +{"current_steps": 100, "total_steps": 122600, "loss": 0.476, "lr": 8.075040783034257e-06, "epoch": 0.01631321370309951, "percentage": 0.08, "elapsed_time": "0:00:36", "remaining_time": "12:24:37", "throughput": 6037.36, "total_tokens": 220192} +{"current_steps": 105, "total_steps": 122600, "loss": 0.3937, "lr": 8.482871125611746e-06, "epoch": 0.017128874388254486, "percentage": 0.09, "elapsed_time": "0:00:38", "remaining_time": "12:22:23", "throughput": 6035.96, "total_tokens": 230464} +{"current_steps": 110, "total_steps": 122600, "loss": 0.3869, "lr": 8.890701468189234e-06, "epoch": 0.01794453507340946, "percentage": 0.09, "elapsed_time": "0:00:40", "remaining_time": "12:22:31", "throughput": 6040.28, "total_tokens": 241664} +{"current_steps": 115, "total_steps": 122600, "loss": 0.4125, "lr": 9.298531810766722e-06, "epoch": 0.018760195758564437, "percentage": 0.09, "elapsed_time": "0:00:41", "remaining_time": "12:23:57", "throughput": 6042.69, "total_tokens": 253248} +{"current_steps": 120, "total_steps": 122600, "loss": 0.3685, "lr": 9.706362153344209e-06, "epoch": 0.01957585644371941, "percentage": 0.1, "elapsed_time": "0:00:43", "remaining_time": "12:20:47", "throughput": 6041.01, "total_tokens": 263072} +{"current_steps": 125, "total_steps": 122600, "loss": 0.352, "lr": 1.0114192495921697e-05, "epoch": 0.020391517128874388, "percentage": 0.1, "elapsed_time": "0:00:45", "remaining_time": "12:22:17", "throughput": 6048.62, "total_tokens": 274944} +{"current_steps": 130, "total_steps": 122600, "loss": 0.3605, "lr": 1.0522022838499184e-05, "epoch": 0.021207177814029365, "percentage": 0.11, "elapsed_time": "0:00:47", "remaining_time": "12:20:01", "throughput": 6048.09, "total_tokens": 285056} +{"current_steps": 135, "total_steps": 122600, "loss": 0.3986, "lr": 1.0929853181076672e-05, "epoch": 0.02202283849918434, "percentage": 0.11, "elapsed_time": "0:00:48", "remaining_time": "12:19:52", "throughput": 6050.04, "total_tokens": 296064} +{"current_steps": 140, "total_steps": 122600, "loss": 0.4069, "lr": 1.1337683523654159e-05, "epoch": 0.022838499184339316, "percentage": 0.11, "elapsed_time": "0:00:50", "remaining_time": "12:19:38", "throughput": 6053.73, "total_tokens": 307136} +{"current_steps": 145, "total_steps": 122600, "loss": 0.4322, "lr": 1.1745513866231649e-05, "epoch": 0.02365415986949429, "percentage": 0.12, "elapsed_time": "0:00:52", "remaining_time": "12:17:13", "throughput": 6055.12, "total_tokens": 317152} +{"current_steps": 150, "total_steps": 122600, "loss": 0.4022, "lr": 1.2153344208809135e-05, "epoch": 0.024469820554649267, "percentage": 0.12, "elapsed_time": "0:00:54", "remaining_time": "12:15:45", "throughput": 6056.52, "total_tokens": 327520} +{"current_steps": 155, "total_steps": 122600, "loss": 0.5004, "lr": 1.2561174551386624e-05, "epoch": 0.02528548123980424, "percentage": 0.13, "elapsed_time": "0:00:55", "remaining_time": "12:16:12", "throughput": 6057.56, "total_tokens": 338720} +{"current_steps": 160, "total_steps": 122600, "loss": 0.3486, "lr": 1.296900489396411e-05, "epoch": 0.026101141924959218, "percentage": 0.13, "elapsed_time": "0:00:57", "remaining_time": "12:16:21", "throughput": 6059.11, "total_tokens": 349824} +{"current_steps": 165, "total_steps": 122600, "loss": 0.3352, "lr": 1.3376835236541599e-05, "epoch": 0.026916802610114192, "percentage": 0.13, "elapsed_time": "0:00:59", "remaining_time": "12:16:05", "throughput": 6058.11, "total_tokens": 360576} +{"current_steps": 170, "total_steps": 122600, "loss": 0.3404, "lr": 1.3784665579119085e-05, "epoch": 0.02773246329526917, "percentage": 0.14, "elapsed_time": "0:01:01", "remaining_time": "12:15:55", "throughput": 6056.33, "total_tokens": 371328} +{"current_steps": 175, "total_steps": 122600, "loss": 0.4694, "lr": 1.4192495921696575e-05, "epoch": 0.028548123980424143, "percentage": 0.14, "elapsed_time": "0:01:03", "remaining_time": "12:16:10", "throughput": 6059.99, "total_tokens": 382624} +{"current_steps": 180, "total_steps": 122600, "loss": 0.4874, "lr": 1.4600326264274062e-05, "epoch": 0.02936378466557912, "percentage": 0.15, "elapsed_time": "0:01:05", "remaining_time": "12:18:34", "throughput": 6065.77, "total_tokens": 395232} +{"current_steps": 185, "total_steps": 122600, "loss": 0.7018, "lr": 1.500815660685155e-05, "epoch": 0.030179445350734094, "percentage": 0.15, "elapsed_time": "0:01:07", "remaining_time": "12:19:23", "throughput": 6067.35, "total_tokens": 406784} +{"current_steps": 190, "total_steps": 122600, "loss": 0.416, "lr": 1.5415986949429037e-05, "epoch": 0.03099510603588907, "percentage": 0.15, "elapsed_time": "0:01:08", "remaining_time": "12:18:21", "throughput": 6067.94, "total_tokens": 417248} +{"current_steps": 195, "total_steps": 122600, "loss": 0.4056, "lr": 1.5823817292006523e-05, "epoch": 0.03181076672104405, "percentage": 0.16, "elapsed_time": "0:01:10", "remaining_time": "12:18:12", "throughput": 6068.86, "total_tokens": 428224} +{"current_steps": 200, "total_steps": 122600, "loss": 0.3701, "lr": 1.6231647634584013e-05, "epoch": 0.03262642740619902, "percentage": 0.16, "elapsed_time": "0:01:12", "remaining_time": "12:15:13", "throughput": 6066.91, "total_tokens": 437312} +{"current_steps": 205, "total_steps": 122600, "loss": 0.3989, "lr": 1.66394779771615e-05, "epoch": 0.033442088091353996, "percentage": 0.17, "elapsed_time": "0:01:13", "remaining_time": "12:14:28", "throughput": 6066.61, "total_tokens": 447776} +{"current_steps": 210, "total_steps": 122600, "loss": 0.3959, "lr": 1.704730831973899e-05, "epoch": 0.03425774877650897, "percentage": 0.17, "elapsed_time": "0:01:15", "remaining_time": "12:14:39", "throughput": 6069.32, "total_tokens": 459040} +{"current_steps": 215, "total_steps": 122600, "loss": 0.3368, "lr": 1.7455138662316477e-05, "epoch": 0.03507340946166395, "percentage": 0.18, "elapsed_time": "0:01:17", "remaining_time": "12:15:41", "throughput": 6069.35, "total_tokens": 470656} +{"current_steps": 220, "total_steps": 122600, "loss": 0.3761, "lr": 1.7862969004893963e-05, "epoch": 0.03588907014681892, "percentage": 0.18, "elapsed_time": "0:01:19", "remaining_time": "12:14:41", "throughput": 6068.13, "total_tokens": 480864} +{"current_steps": 225, "total_steps": 122600, "loss": 0.349, "lr": 1.8270799347471453e-05, "epoch": 0.0367047308319739, "percentage": 0.18, "elapsed_time": "0:01:21", "remaining_time": "12:14:27", "throughput": 6068.37, "total_tokens": 491680} +{"current_steps": 230, "total_steps": 122600, "loss": 0.3603, "lr": 1.867862969004894e-05, "epoch": 0.037520391517128875, "percentage": 0.19, "elapsed_time": "0:01:22", "remaining_time": "12:14:03", "throughput": 6069.33, "total_tokens": 502432} +{"current_steps": 235, "total_steps": 122600, "loss": 0.3927, "lr": 1.908646003262643e-05, "epoch": 0.03833605220228385, "percentage": 0.19, "elapsed_time": "0:01:24", "remaining_time": "12:13:13", "throughput": 6069.38, "total_tokens": 512800} +{"current_steps": 240, "total_steps": 122600, "loss": 0.4135, "lr": 1.9494290375203913e-05, "epoch": 0.03915171288743882, "percentage": 0.2, "elapsed_time": "0:01:26", "remaining_time": "12:12:42", "throughput": 6070.21, "total_tokens": 523424} +{"current_steps": 245, "total_steps": 122600, "loss": 0.3361, "lr": 1.9902120717781403e-05, "epoch": 0.0399673735725938, "percentage": 0.2, "elapsed_time": "0:01:27", "remaining_time": "12:11:28", "throughput": 6071.89, "total_tokens": 533600} +{"current_steps": 250, "total_steps": 122600, "loss": 0.411, "lr": 2.0309951060358893e-05, "epoch": 0.040783034257748776, "percentage": 0.2, "elapsed_time": "0:01:29", "remaining_time": "12:11:21", "throughput": 6073.58, "total_tokens": 544576} +{"current_steps": 255, "total_steps": 122600, "loss": 0.41, "lr": 2.071778140293638e-05, "epoch": 0.041598694942903754, "percentage": 0.21, "elapsed_time": "0:01:31", "remaining_time": "12:10:32", "throughput": 6072.54, "total_tokens": 554784} +{"current_steps": 260, "total_steps": 122600, "loss": 0.39, "lr": 2.1125611745513866e-05, "epoch": 0.04241435562805873, "percentage": 0.21, "elapsed_time": "0:01:33", "remaining_time": "12:10:24", "throughput": 6073.08, "total_tokens": 565632} +{"current_steps": 265, "total_steps": 122600, "loss": 0.3545, "lr": 2.1533442088091353e-05, "epoch": 0.0432300163132137, "percentage": 0.22, "elapsed_time": "0:01:34", "remaining_time": "12:09:45", "throughput": 6072.92, "total_tokens": 576000} +{"current_steps": 270, "total_steps": 122600, "loss": 0.3468, "lr": 2.1941272430668843e-05, "epoch": 0.04404567699836868, "percentage": 0.22, "elapsed_time": "0:01:36", "remaining_time": "12:09:46", "throughput": 6071.93, "total_tokens": 586816} +{"current_steps": 275, "total_steps": 122600, "loss": 0.3342, "lr": 2.234910277324633e-05, "epoch": 0.044861337683523655, "percentage": 0.22, "elapsed_time": "0:01:38", "remaining_time": "12:09:26", "throughput": 6073.36, "total_tokens": 597568} +{"current_steps": 280, "total_steps": 122600, "loss": 0.36, "lr": 2.2756933115823816e-05, "epoch": 0.04567699836867863, "percentage": 0.23, "elapsed_time": "0:01:40", "remaining_time": "12:08:51", "throughput": 6074.31, "total_tokens": 608064} +{"current_steps": 285, "total_steps": 122600, "loss": 0.3185, "lr": 2.3164763458401306e-05, "epoch": 0.0464926590538336, "percentage": 0.23, "elapsed_time": "0:01:42", "remaining_time": "12:09:48", "throughput": 6075.71, "total_tokens": 619904} +{"current_steps": 290, "total_steps": 122600, "loss": 0.484, "lr": 2.3572593800978793e-05, "epoch": 0.04730831973898858, "percentage": 0.24, "elapsed_time": "0:01:43", "remaining_time": "12:09:27", "throughput": 6076.33, "total_tokens": 630560} +{"current_steps": 295, "total_steps": 122600, "loss": 0.3715, "lr": 2.3980424143556283e-05, "epoch": 0.04812398042414356, "percentage": 0.24, "elapsed_time": "0:01:45", "remaining_time": "12:09:18", "throughput": 6074.98, "total_tokens": 641184} +{"current_steps": 300, "total_steps": 122600, "loss": 0.4153, "lr": 2.4388254486133766e-05, "epoch": 0.048939641109298535, "percentage": 0.24, "elapsed_time": "0:01:47", "remaining_time": "12:08:32", "throughput": 6075.29, "total_tokens": 651424} +{"current_steps": 305, "total_steps": 122600, "loss": 0.3906, "lr": 2.4796084828711256e-05, "epoch": 0.049755301794453505, "percentage": 0.25, "elapsed_time": "0:01:49", "remaining_time": "12:09:14", "throughput": 6076.47, "total_tokens": 663072} +{"current_steps": 310, "total_steps": 122600, "loss": 0.396, "lr": 2.5203915171288743e-05, "epoch": 0.05057096247960848, "percentage": 0.25, "elapsed_time": "0:01:50", "remaining_time": "12:07:35", "throughput": 6076.2, "total_tokens": 672416} +{"current_steps": 315, "total_steps": 122600, "loss": 0.4705, "lr": 2.5611745513866233e-05, "epoch": 0.05138662316476346, "percentage": 0.26, "elapsed_time": "0:01:52", "remaining_time": "12:07:08", "throughput": 6077.36, "total_tokens": 683008} +{"current_steps": 320, "total_steps": 122600, "loss": 0.4732, "lr": 2.6019575856443723e-05, "epoch": 0.052202283849918436, "percentage": 0.26, "elapsed_time": "0:01:54", "remaining_time": "12:08:02", "throughput": 6079.44, "total_tokens": 694976} +{"current_steps": 325, "total_steps": 122600, "loss": 0.4089, "lr": 2.6427406199021206e-05, "epoch": 0.05301794453507341, "percentage": 0.27, "elapsed_time": "0:01:56", "remaining_time": "12:07:54", "throughput": 6080.2, "total_tokens": 705824} +{"current_steps": 330, "total_steps": 122600, "loss": 0.4339, "lr": 2.6835236541598696e-05, "epoch": 0.053833605220228384, "percentage": 0.27, "elapsed_time": "0:01:57", "remaining_time": "12:08:04", "throughput": 6082.08, "total_tokens": 717088} +{"current_steps": 335, "total_steps": 122600, "loss": 0.4164, "lr": 2.7243066884176183e-05, "epoch": 0.05464926590538336, "percentage": 0.27, "elapsed_time": "0:01:59", "remaining_time": "12:08:41", "throughput": 6083.41, "total_tokens": 728768} +{"current_steps": 340, "total_steps": 122600, "loss": 0.4142, "lr": 2.7650897226753673e-05, "epoch": 0.05546492659053834, "percentage": 0.28, "elapsed_time": "0:02:01", "remaining_time": "12:07:32", "throughput": 6083.67, "total_tokens": 738528} +{"current_steps": 345, "total_steps": 122600, "loss": 0.3912, "lr": 2.805872756933116e-05, "epoch": 0.05628058727569331, "percentage": 0.28, "elapsed_time": "0:02:03", "remaining_time": "12:07:44", "throughput": 6084.16, "total_tokens": 749696} +{"current_steps": 350, "total_steps": 122600, "loss": 0.3433, "lr": 2.8466557911908646e-05, "epoch": 0.057096247960848286, "percentage": 0.29, "elapsed_time": "0:02:04", "remaining_time": "12:07:36", "throughput": 6085.96, "total_tokens": 760672} +{"current_steps": 355, "total_steps": 122600, "loss": 0.3593, "lr": 2.8874388254486136e-05, "epoch": 0.05791190864600326, "percentage": 0.29, "elapsed_time": "0:02:06", "remaining_time": "12:07:39", "throughput": 6086.65, "total_tokens": 771712} +{"current_steps": 360, "total_steps": 122600, "loss": 0.3646, "lr": 2.9282218597063623e-05, "epoch": 0.05872756933115824, "percentage": 0.29, "elapsed_time": "0:02:08", "remaining_time": "12:07:46", "throughput": 6088.04, "total_tokens": 782912} +{"current_steps": 365, "total_steps": 122600, "loss": 0.3592, "lr": 2.969004893964111e-05, "epoch": 0.05954323001631321, "percentage": 0.3, "elapsed_time": "0:02:10", "remaining_time": "12:08:12", "throughput": 6088.58, "total_tokens": 794368} +{"current_steps": 370, "total_steps": 122600, "loss": 0.3586, "lr": 3.0097879282218596e-05, "epoch": 0.06035889070146819, "percentage": 0.3, "elapsed_time": "0:02:12", "remaining_time": "12:07:42", "throughput": 6088.44, "total_tokens": 804704} +{"current_steps": 375, "total_steps": 122600, "loss": 0.3525, "lr": 3.0505709624796086e-05, "epoch": 0.061174551386623165, "percentage": 0.31, "elapsed_time": "0:02:13", "remaining_time": "12:07:54", "throughput": 6088.67, "total_tokens": 815872} +{"current_steps": 380, "total_steps": 122600, "loss": 0.3348, "lr": 3.0913539967373576e-05, "epoch": 0.06199021207177814, "percentage": 0.31, "elapsed_time": "0:02:15", "remaining_time": "12:08:01", "throughput": 6088.69, "total_tokens": 826912} +{"current_steps": 385, "total_steps": 122600, "loss": 0.4138, "lr": 3.132137030995106e-05, "epoch": 0.06280587275693311, "percentage": 0.31, "elapsed_time": "0:02:17", "remaining_time": "12:07:08", "throughput": 6089.0, "total_tokens": 836864} +{"current_steps": 390, "total_steps": 122600, "loss": 0.4467, "lr": 3.172920065252855e-05, "epoch": 0.0636215334420881, "percentage": 0.32, "elapsed_time": "0:02:19", "remaining_time": "12:07:33", "throughput": 6090.43, "total_tokens": 848448} +{"current_steps": 395, "total_steps": 122600, "loss": 0.3861, "lr": 3.213703099510604e-05, "epoch": 0.06443719412724307, "percentage": 0.32, "elapsed_time": "0:02:21", "remaining_time": "12:07:19", "throughput": 6089.7, "total_tokens": 858976} +{"current_steps": 400, "total_steps": 122600, "loss": 0.4364, "lr": 3.254486133768352e-05, "epoch": 0.06525285481239804, "percentage": 0.33, "elapsed_time": "0:02:22", "remaining_time": "12:07:10", "throughput": 6089.31, "total_tokens": 869664} +{"current_steps": 405, "total_steps": 122600, "loss": 0.3747, "lr": 3.295269168026101e-05, "epoch": 0.06606851549755302, "percentage": 0.33, "elapsed_time": "0:02:24", "remaining_time": "12:07:58", "throughput": 6090.41, "total_tokens": 881696} +{"current_steps": 410, "total_steps": 122600, "loss": 0.5381, "lr": 3.33605220228385e-05, "epoch": 0.06688417618270799, "percentage": 0.33, "elapsed_time": "0:02:26", "remaining_time": "12:08:32", "throughput": 6091.34, "total_tokens": 893440} +{"current_steps": 415, "total_steps": 122600, "loss": 0.3439, "lr": 3.3768352365415986e-05, "epoch": 0.06769983686786298, "percentage": 0.34, "elapsed_time": "0:02:28", "remaining_time": "12:08:25", "throughput": 6091.36, "total_tokens": 904224} +{"current_steps": 420, "total_steps": 122600, "loss": 0.4344, "lr": 3.4176182707993476e-05, "epoch": 0.06851549755301795, "percentage": 0.34, "elapsed_time": "0:02:30", "remaining_time": "12:08:51", "throughput": 6091.79, "total_tokens": 915776} +{"current_steps": 425, "total_steps": 122600, "loss": 0.383, "lr": 3.458401305057096e-05, "epoch": 0.06933115823817292, "percentage": 0.35, "elapsed_time": "0:02:32", "remaining_time": "12:08:52", "throughput": 6091.32, "total_tokens": 926656} +{"current_steps": 430, "total_steps": 122600, "loss": 0.4272, "lr": 3.4991843393148456e-05, "epoch": 0.0701468189233279, "percentage": 0.35, "elapsed_time": "0:02:33", "remaining_time": "12:08:57", "throughput": 6091.4, "total_tokens": 937728} +{"current_steps": 435, "total_steps": 122600, "loss": 0.4359, "lr": 3.539967373572594e-05, "epoch": 0.07096247960848287, "percentage": 0.35, "elapsed_time": "0:02:35", "remaining_time": "12:09:02", "throughput": 6091.62, "total_tokens": 948800} +{"current_steps": 440, "total_steps": 122600, "loss": 0.3757, "lr": 3.580750407830342e-05, "epoch": 0.07177814029363784, "percentage": 0.36, "elapsed_time": "0:02:37", "remaining_time": "12:09:06", "throughput": 6090.74, "total_tokens": 959712} +{"current_steps": 445, "total_steps": 122600, "loss": 0.2887, "lr": 3.621533442088092e-05, "epoch": 0.07259380097879282, "percentage": 0.36, "elapsed_time": "0:02:39", "remaining_time": "12:09:12", "throughput": 6089.57, "total_tokens": 970592} +{"current_steps": 450, "total_steps": 122600, "loss": 0.3668, "lr": 3.66231647634584e-05, "epoch": 0.0734094616639478, "percentage": 0.37, "elapsed_time": "0:02:41", "remaining_time": "12:09:24", "throughput": 6088.48, "total_tokens": 981632} +{"current_steps": 455, "total_steps": 122600, "loss": 0.3811, "lr": 3.703099510603589e-05, "epoch": 0.07422512234910278, "percentage": 0.37, "elapsed_time": "0:02:42", "remaining_time": "12:08:42", "throughput": 6088.72, "total_tokens": 991680} +{"current_steps": 460, "total_steps": 122600, "loss": 0.3688, "lr": 3.7438825448613375e-05, "epoch": 0.07504078303425775, "percentage": 0.38, "elapsed_time": "0:02:44", "remaining_time": "12:08:55", "throughput": 6088.6, "total_tokens": 1002880} +{"current_steps": 465, "total_steps": 122600, "loss": 0.3793, "lr": 3.7846655791190865e-05, "epoch": 0.07585644371941272, "percentage": 0.38, "elapsed_time": "0:02:46", "remaining_time": "12:09:39", "throughput": 6089.95, "total_tokens": 1015072} +{"current_steps": 470, "total_steps": 122600, "loss": 0.3835, "lr": 3.8254486133768355e-05, "epoch": 0.0766721044045677, "percentage": 0.38, "elapsed_time": "0:02:48", "remaining_time": "12:09:42", "throughput": 6090.35, "total_tokens": 1026176} +{"current_steps": 475, "total_steps": 122600, "loss": 0.3721, "lr": 3.866231647634584e-05, "epoch": 0.07748776508972267, "percentage": 0.39, "elapsed_time": "0:02:50", "remaining_time": "12:10:03", "throughput": 6090.42, "total_tokens": 1037632} +{"current_steps": 480, "total_steps": 122600, "loss": 0.3572, "lr": 3.907014681892333e-05, "epoch": 0.07830342577487764, "percentage": 0.39, "elapsed_time": "0:02:51", "remaining_time": "12:09:01", "throughput": 6089.93, "total_tokens": 1047040} +{"current_steps": 485, "total_steps": 122600, "loss": 0.332, "lr": 3.947797716150082e-05, "epoch": 0.07911908646003263, "percentage": 0.4, "elapsed_time": "0:02:53", "remaining_time": "12:08:39", "throughput": 6089.32, "total_tokens": 1057344} +{"current_steps": 490, "total_steps": 122600, "loss": 0.3001, "lr": 3.98858075040783e-05, "epoch": 0.0799347471451876, "percentage": 0.4, "elapsed_time": "0:02:55", "remaining_time": "12:08:33", "throughput": 6088.89, "total_tokens": 1068064} +{"current_steps": 495, "total_steps": 122600, "loss": 0.5147, "lr": 4.029363784665579e-05, "epoch": 0.08075040783034258, "percentage": 0.4, "elapsed_time": "0:02:57", "remaining_time": "12:08:19", "throughput": 6088.28, "total_tokens": 1078560} +{"current_steps": 500, "total_steps": 122600, "loss": 0.2397, "lr": 4.070146818923328e-05, "epoch": 0.08156606851549755, "percentage": 0.41, "elapsed_time": "0:02:58", "remaining_time": "12:08:28", "throughput": 6088.87, "total_tokens": 1089824} +{"current_steps": 505, "total_steps": 122600, "loss": 0.6049, "lr": 4.1109298531810765e-05, "epoch": 0.08238172920065252, "percentage": 0.41, "elapsed_time": "0:03:00", "remaining_time": "12:08:37", "throughput": 6089.49, "total_tokens": 1101120} +{"current_steps": 510, "total_steps": 122600, "loss": 0.6272, "lr": 4.1517128874388255e-05, "epoch": 0.08319738988580751, "percentage": 0.42, "elapsed_time": "0:03:02", "remaining_time": "12:08:33", "throughput": 6088.93, "total_tokens": 1111840} +{"current_steps": 515, "total_steps": 122600, "loss": 0.5606, "lr": 4.1924959216965745e-05, "epoch": 0.08401305057096248, "percentage": 0.42, "elapsed_time": "0:03:04", "remaining_time": "12:08:28", "throughput": 6089.14, "total_tokens": 1122720} +{"current_steps": 520, "total_steps": 122600, "loss": 0.1157, "lr": 4.233278955954323e-05, "epoch": 0.08482871125611746, "percentage": 0.42, "elapsed_time": "0:03:05", "remaining_time": "12:07:20", "throughput": 6088.71, "total_tokens": 1131808} +{"current_steps": 525, "total_steps": 122600, "loss": 0.2238, "lr": 4.274061990212072e-05, "epoch": 0.08564437194127243, "percentage": 0.43, "elapsed_time": "0:03:07", "remaining_time": "12:07:19", "throughput": 6088.27, "total_tokens": 1142624} +{"current_steps": 530, "total_steps": 122600, "loss": 0.2579, "lr": 4.314845024469821e-05, "epoch": 0.0864600326264274, "percentage": 0.43, "elapsed_time": "0:03:09", "remaining_time": "12:07:23", "throughput": 6087.63, "total_tokens": 1153536} +{"current_steps": 535, "total_steps": 122600, "loss": 0.1138, "lr": 4.35562805872757e-05, "epoch": 0.08727569331158239, "percentage": 0.44, "elapsed_time": "0:03:11", "remaining_time": "12:07:42", "throughput": 6087.45, "total_tokens": 1164960} +{"current_steps": 540, "total_steps": 122600, "loss": 0.102, "lr": 4.396411092985318e-05, "epoch": 0.08809135399673736, "percentage": 0.44, "elapsed_time": "0:03:13", "remaining_time": "12:07:37", "throughput": 6086.36, "total_tokens": 1175552} +{"current_steps": 545, "total_steps": 122600, "loss": 0.3639, "lr": 4.4371941272430665e-05, "epoch": 0.08890701468189233, "percentage": 0.44, "elapsed_time": "0:03:14", "remaining_time": "12:07:42", "throughput": 6086.46, "total_tokens": 1186624} +{"current_steps": 550, "total_steps": 122600, "loss": 1.4397, "lr": 4.477977161500816e-05, "epoch": 0.08972267536704731, "percentage": 0.45, "elapsed_time": "0:03:16", "remaining_time": "12:08:07", "throughput": 6086.96, "total_tokens": 1198336} +{"current_steps": 555, "total_steps": 122600, "loss": 0.3143, "lr": 4.5187601957585645e-05, "epoch": 0.09053833605220228, "percentage": 0.45, "elapsed_time": "0:03:18", "remaining_time": "12:08:22", "throughput": 6087.24, "total_tokens": 1209760} +{"current_steps": 560, "total_steps": 122600, "loss": 0.3098, "lr": 4.559543230016313e-05, "epoch": 0.09135399673735727, "percentage": 0.46, "elapsed_time": "0:03:20", "remaining_time": "12:07:58", "throughput": 6086.78, "total_tokens": 1219936} +{"current_steps": 565, "total_steps": 122600, "loss": 0.194, "lr": 4.6003262642740625e-05, "epoch": 0.09216965742251224, "percentage": 0.46, "elapsed_time": "0:03:22", "remaining_time": "12:08:16", "throughput": 6087.09, "total_tokens": 1231456} +{"current_steps": 570, "total_steps": 122600, "loss": 0.1057, "lr": 4.641109298531811e-05, "epoch": 0.0929853181076672, "percentage": 0.46, "elapsed_time": "0:03:24", "remaining_time": "12:08:00", "throughput": 6087.09, "total_tokens": 1241952} +{"current_steps": 575, "total_steps": 122600, "loss": 0.3255, "lr": 4.68189233278956e-05, "epoch": 0.09380097879282219, "percentage": 0.47, "elapsed_time": "0:03:25", "remaining_time": "12:08:31", "throughput": 6087.77, "total_tokens": 1253920} +{"current_steps": 580, "total_steps": 122600, "loss": 0.1501, "lr": 4.722675367047308e-05, "epoch": 0.09461663947797716, "percentage": 0.47, "elapsed_time": "0:03:27", "remaining_time": "12:08:56", "throughput": 6087.84, "total_tokens": 1265632} +{"current_steps": 585, "total_steps": 122600, "loss": 0.692, "lr": 4.763458401305057e-05, "epoch": 0.09543230016313213, "percentage": 0.48, "elapsed_time": "0:03:29", "remaining_time": "12:08:50", "throughput": 6087.1, "total_tokens": 1276256} +{"current_steps": 590, "total_steps": 122600, "loss": 0.2242, "lr": 4.804241435562806e-05, "epoch": 0.09624796084828711, "percentage": 0.48, "elapsed_time": "0:03:31", "remaining_time": "12:09:02", "throughput": 6086.46, "total_tokens": 1287424} +{"current_steps": 595, "total_steps": 122600, "loss": 0.0625, "lr": 4.8450244698205544e-05, "epoch": 0.09706362153344208, "percentage": 0.49, "elapsed_time": "0:03:33", "remaining_time": "12:08:54", "throughput": 6087.02, "total_tokens": 1298272} +{"current_steps": 600, "total_steps": 122600, "loss": 0.2317, "lr": 4.885807504078304e-05, "epoch": 0.09787928221859707, "percentage": 0.49, "elapsed_time": "0:03:35", "remaining_time": "12:09:01", "throughput": 6087.9, "total_tokens": 1309632} +{"current_steps": 605, "total_steps": 122600, "loss": 0.4314, "lr": 4.9265905383360524e-05, "epoch": 0.09869494290375204, "percentage": 0.49, "elapsed_time": "0:03:36", "remaining_time": "12:08:28", "throughput": 6086.26, "total_tokens": 1319264} +{"current_steps": 610, "total_steps": 122600, "loss": 0.3954, "lr": 4.967373572593801e-05, "epoch": 0.09951060358890701, "percentage": 0.5, "elapsed_time": "0:03:38", "remaining_time": "12:08:29", "throughput": 6085.8, "total_tokens": 1330144} +{"current_steps": 615, "total_steps": 122600, "loss": 0.2213, "lr": 5.00815660685155e-05, "epoch": 0.100326264274062, "percentage": 0.5, "elapsed_time": "0:03:40", "remaining_time": "12:08:15", "throughput": 6085.62, "total_tokens": 1340640} +{"current_steps": 620, "total_steps": 122600, "loss": 0.4465, "lr": 5.048939641109299e-05, "epoch": 0.10114192495921696, "percentage": 0.51, "elapsed_time": "0:03:42", "remaining_time": "12:08:05", "throughput": 6084.95, "total_tokens": 1351136} +{"current_steps": 625, "total_steps": 122600, "loss": 0.2263, "lr": 5.089722675367047e-05, "epoch": 0.10195758564437195, "percentage": 0.51, "elapsed_time": "0:03:43", "remaining_time": "12:08:33", "throughput": 6085.63, "total_tokens": 1363104} +{"current_steps": 630, "total_steps": 122600, "loss": 0.235, "lr": 5.130505709624796e-05, "epoch": 0.10277324632952692, "percentage": 0.51, "elapsed_time": "0:03:45", "remaining_time": "12:08:28", "throughput": 6085.39, "total_tokens": 1373856} +{"current_steps": 635, "total_steps": 122600, "loss": 0.1787, "lr": 5.171288743882545e-05, "epoch": 0.10358890701468189, "percentage": 0.52, "elapsed_time": "0:03:47", "remaining_time": "12:08:57", "throughput": 6086.52, "total_tokens": 1385984} +{"current_steps": 640, "total_steps": 122600, "loss": 0.1436, "lr": 5.212071778140294e-05, "epoch": 0.10440456769983687, "percentage": 0.52, "elapsed_time": "0:03:49", "remaining_time": "12:09:09", "throughput": 6087.11, "total_tokens": 1397472} +{"current_steps": 645, "total_steps": 122600, "loss": 0.184, "lr": 5.2528548123980424e-05, "epoch": 0.10522022838499184, "percentage": 0.53, "elapsed_time": "0:03:51", "remaining_time": "12:08:49", "throughput": 6086.83, "total_tokens": 1407744} +{"current_steps": 650, "total_steps": 122600, "loss": 0.4137, "lr": 5.293637846655791e-05, "epoch": 0.10603588907014681, "percentage": 0.53, "elapsed_time": "0:03:53", "remaining_time": "12:08:45", "throughput": 6087.21, "total_tokens": 1418688} +{"current_steps": 655, "total_steps": 122600, "loss": 0.2377, "lr": 5.3344208809135404e-05, "epoch": 0.1068515497553018, "percentage": 0.53, "elapsed_time": "0:03:54", "remaining_time": "12:08:32", "throughput": 6086.55, "total_tokens": 1429056} +{"current_steps": 660, "total_steps": 122600, "loss": 0.3604, "lr": 5.375203915171289e-05, "epoch": 0.10766721044045677, "percentage": 0.54, "elapsed_time": "0:03:56", "remaining_time": "12:08:13", "throughput": 6085.89, "total_tokens": 1439264} +{"current_steps": 665, "total_steps": 122600, "loss": 0.4648, "lr": 5.415986949429037e-05, "epoch": 0.10848287112561175, "percentage": 0.54, "elapsed_time": "0:03:58", "remaining_time": "12:08:29", "throughput": 6087.24, "total_tokens": 1451072} +{"current_steps": 670, "total_steps": 122600, "loss": 0.2371, "lr": 5.456769983686787e-05, "epoch": 0.10929853181076672, "percentage": 0.55, "elapsed_time": "0:03:59", "remaining_time": "12:07:49", "throughput": 6086.93, "total_tokens": 1460640} +{"current_steps": 675, "total_steps": 122600, "loss": 0.2627, "lr": 5.497553017944535e-05, "epoch": 0.11011419249592169, "percentage": 0.55, "elapsed_time": "0:04:01", "remaining_time": "12:08:02", "throughput": 6087.73, "total_tokens": 1472224} +{"current_steps": 680, "total_steps": 122600, "loss": 0.4448, "lr": 5.538336052202284e-05, "epoch": 0.11092985318107668, "percentage": 0.55, "elapsed_time": "0:04:03", "remaining_time": "12:08:20", "throughput": 6087.45, "total_tokens": 1483744} +{"current_steps": 685, "total_steps": 122600, "loss": 0.2309, "lr": 5.579119086460033e-05, "epoch": 0.11174551386623165, "percentage": 0.56, "elapsed_time": "0:04:05", "remaining_time": "12:08:43", "throughput": 6087.74, "total_tokens": 1495552} +{"current_steps": 690, "total_steps": 122600, "loss": 0.1059, "lr": 5.6199021207177814e-05, "epoch": 0.11256117455138662, "percentage": 0.56, "elapsed_time": "0:04:07", "remaining_time": "12:08:55", "throughput": 6087.5, "total_tokens": 1506880} +{"current_steps": 695, "total_steps": 122600, "loss": 0.4037, "lr": 5.6606851549755304e-05, "epoch": 0.1133768352365416, "percentage": 0.57, "elapsed_time": "0:04:09", "remaining_time": "12:09:09", "throughput": 6087.41, "total_tokens": 1518336} +{"current_steps": 700, "total_steps": 122600, "loss": 0.169, "lr": 5.701468189233279e-05, "epoch": 0.11419249592169657, "percentage": 0.57, "elapsed_time": "0:04:11", "remaining_time": "12:08:50", "throughput": 6087.57, "total_tokens": 1528704} +{"current_steps": 705, "total_steps": 122600, "loss": 0.2088, "lr": 5.7422512234910284e-05, "epoch": 0.11500815660685156, "percentage": 0.58, "elapsed_time": "0:04:12", "remaining_time": "12:08:49", "throughput": 6087.24, "total_tokens": 1539552} +{"current_steps": 710, "total_steps": 122600, "loss": 0.1942, "lr": 5.783034257748777e-05, "epoch": 0.11582381729200653, "percentage": 0.58, "elapsed_time": "0:04:14", "remaining_time": "12:08:23", "throughput": 6087.47, "total_tokens": 1549696} +{"current_steps": 715, "total_steps": 122600, "loss": 0.1503, "lr": 5.823817292006525e-05, "epoch": 0.1166394779771615, "percentage": 0.58, "elapsed_time": "0:04:16", "remaining_time": "12:07:42", "throughput": 6086.81, "total_tokens": 1559040} +{"current_steps": 720, "total_steps": 122600, "loss": 0.3159, "lr": 5.864600326264275e-05, "epoch": 0.11745513866231648, "percentage": 0.59, "elapsed_time": "0:04:17", "remaining_time": "12:07:42", "throughput": 6087.33, "total_tokens": 1570144} +{"current_steps": 725, "total_steps": 122600, "loss": 0.2283, "lr": 5.905383360522023e-05, "epoch": 0.11827079934747145, "percentage": 0.59, "elapsed_time": "0:04:19", "remaining_time": "12:07:12", "throughput": 6086.38, "total_tokens": 1579776} +{"current_steps": 730, "total_steps": 122600, "loss": 3.0837, "lr": 5.9461663947797714e-05, "epoch": 0.11908646003262642, "percentage": 0.6, "elapsed_time": "0:04:21", "remaining_time": "12:06:30", "throughput": 6086.15, "total_tokens": 1589120} +{"current_steps": 735, "total_steps": 122600, "loss": 2.2193, "lr": 5.9869494290375204e-05, "epoch": 0.1199021207177814, "percentage": 0.6, "elapsed_time": "0:04:22", "remaining_time": "12:06:38", "throughput": 6086.68, "total_tokens": 1600512} +{"current_steps": 740, "total_steps": 122600, "loss": 0.7939, "lr": 6.0277324632952694e-05, "epoch": 0.12071778140293637, "percentage": 0.6, "elapsed_time": "0:04:24", "remaining_time": "12:06:23", "throughput": 6086.61, "total_tokens": 1610880} +{"current_steps": 745, "total_steps": 122600, "loss": 0.2326, "lr": 6.0685154975530184e-05, "epoch": 0.12153344208809136, "percentage": 0.61, "elapsed_time": "0:04:26", "remaining_time": "12:06:00", "throughput": 6086.27, "total_tokens": 1620896} +{"current_steps": 750, "total_steps": 122600, "loss": 0.131, "lr": 6.109298531810767e-05, "epoch": 0.12234910277324633, "percentage": 0.61, "elapsed_time": "0:04:28", "remaining_time": "12:05:45", "throughput": 6086.06, "total_tokens": 1631232} +{"current_steps": 755, "total_steps": 122600, "loss": 0.1412, "lr": 6.150081566068516e-05, "epoch": 0.1231647634584013, "percentage": 0.62, "elapsed_time": "0:04:29", "remaining_time": "12:05:57", "throughput": 6086.32, "total_tokens": 1642688} +{"current_steps": 760, "total_steps": 122600, "loss": 0.4573, "lr": 6.190864600326265e-05, "epoch": 0.12398042414355628, "percentage": 0.62, "elapsed_time": "0:04:31", "remaining_time": "12:05:58", "throughput": 6086.73, "total_tokens": 1653792} +{"current_steps": 765, "total_steps": 122600, "loss": 2.002, "lr": 6.231647634584014e-05, "epoch": 0.12479608482871125, "percentage": 0.62, "elapsed_time": "0:04:33", "remaining_time": "12:05:45", "throughput": 6086.48, "total_tokens": 1664160} +{"current_steps": 770, "total_steps": 122600, "loss": 6.3921, "lr": 6.272430668841763e-05, "epoch": 0.12561174551386622, "percentage": 0.63, "elapsed_time": "0:04:35", "remaining_time": "12:05:45", "throughput": 6086.84, "total_tokens": 1675232} +{"current_steps": 775, "total_steps": 122600, "loss": 4.1665, "lr": 6.31321370309951e-05, "epoch": 0.1264274061990212, "percentage": 0.63, "elapsed_time": "0:04:36", "remaining_time": "12:05:22", "throughput": 6086.81, "total_tokens": 1685280} +{"current_steps": 780, "total_steps": 122600, "loss": 1.2492, "lr": 6.35399673735726e-05, "epoch": 0.1272430668841762, "percentage": 0.64, "elapsed_time": "0:04:38", "remaining_time": "12:04:52", "throughput": 6086.08, "total_tokens": 1694848} +{"current_steps": 785, "total_steps": 122600, "loss": 0.4529, "lr": 6.394779771615008e-05, "epoch": 0.12805872756933115, "percentage": 0.64, "elapsed_time": "0:04:40", "remaining_time": "12:04:46", "throughput": 6086.31, "total_tokens": 1705600} +{"current_steps": 790, "total_steps": 122600, "loss": 0.5815, "lr": 6.435562805872756e-05, "epoch": 0.12887438825448613, "percentage": 0.64, "elapsed_time": "0:04:42", "remaining_time": "12:04:59", "throughput": 6086.63, "total_tokens": 1717152} +{"current_steps": 795, "total_steps": 122600, "loss": 0.5153, "lr": 6.476345840130505e-05, "epoch": 0.12969004893964112, "percentage": 0.65, "elapsed_time": "0:04:43", "remaining_time": "12:05:09", "throughput": 6086.03, "total_tokens": 1728288} +{"current_steps": 800, "total_steps": 122600, "loss": 0.2736, "lr": 6.517128874388255e-05, "epoch": 0.13050570962479607, "percentage": 0.65, "elapsed_time": "0:04:45", "remaining_time": "12:05:24", "throughput": 6086.36, "total_tokens": 1739936} +{"current_steps": 805, "total_steps": 122600, "loss": 0.1994, "lr": 6.557911908646004e-05, "epoch": 0.13132137030995106, "percentage": 0.66, "elapsed_time": "0:04:47", "remaining_time": "12:05:23", "throughput": 6085.68, "total_tokens": 1750656} +{"current_steps": 810, "total_steps": 122600, "loss": 0.3218, "lr": 6.598694942903752e-05, "epoch": 0.13213703099510604, "percentage": 0.66, "elapsed_time": "0:04:49", "remaining_time": "12:04:36", "throughput": 6084.6, "total_tokens": 1759392} +{"current_steps": 815, "total_steps": 122600, "loss": 0.2163, "lr": 6.639477977161501e-05, "epoch": 0.132952691680261, "percentage": 0.66, "elapsed_time": "0:04:51", "remaining_time": "12:04:46", "throughput": 6084.94, "total_tokens": 1770816} +{"current_steps": 820, "total_steps": 122600, "loss": 0.155, "lr": 6.68026101141925e-05, "epoch": 0.13376835236541598, "percentage": 0.67, "elapsed_time": "0:04:52", "remaining_time": "12:04:30", "throughput": 6084.83, "total_tokens": 1781088} +{"current_steps": 825, "total_steps": 122600, "loss": 0.2787, "lr": 6.721044045676998e-05, "epoch": 0.13458401305057097, "percentage": 0.67, "elapsed_time": "0:04:54", "remaining_time": "12:04:07", "throughput": 6084.39, "total_tokens": 1790912} +{"current_steps": 830, "total_steps": 122600, "loss": 0.0285, "lr": 6.761827079934747e-05, "epoch": 0.13539967373572595, "percentage": 0.68, "elapsed_time": "0:04:55", "remaining_time": "12:03:43", "throughput": 6084.03, "total_tokens": 1800736} +{"current_steps": 835, "total_steps": 122600, "loss": 0.2213, "lr": 6.802610114192497e-05, "epoch": 0.1362153344208809, "percentage": 0.68, "elapsed_time": "0:04:57", "remaining_time": "12:03:07", "throughput": 6083.48, "total_tokens": 1810016} +{"current_steps": 840, "total_steps": 122600, "loss": 0.3239, "lr": 6.843393148450245e-05, "epoch": 0.1370309951060359, "percentage": 0.69, "elapsed_time": "0:04:59", "remaining_time": "12:02:49", "throughput": 6083.03, "total_tokens": 1820032} +{"current_steps": 845, "total_steps": 122600, "loss": 0.2064, "lr": 6.884176182707994e-05, "epoch": 0.13784665579119088, "percentage": 0.69, "elapsed_time": "0:05:00", "remaining_time": "12:02:30", "throughput": 6082.89, "total_tokens": 1830080} +{"current_steps": 850, "total_steps": 122600, "loss": 0.3382, "lr": 6.924959216965743e-05, "epoch": 0.13866231647634583, "percentage": 0.69, "elapsed_time": "0:05:02", "remaining_time": "12:02:26", "throughput": 6082.93, "total_tokens": 1840832} +{"current_steps": 855, "total_steps": 122600, "loss": 0.4432, "lr": 6.96574225122349e-05, "epoch": 0.13947797716150082, "percentage": 0.7, "elapsed_time": "0:05:04", "remaining_time": "12:02:33", "throughput": 6082.83, "total_tokens": 1852000} +{"current_steps": 860, "total_steps": 122600, "loss": 0.2847, "lr": 7.006525285481239e-05, "epoch": 0.1402936378466558, "percentage": 0.7, "elapsed_time": "0:05:06", "remaining_time": "12:02:38", "throughput": 6083.31, "total_tokens": 1863264} +{"current_steps": 865, "total_steps": 122600, "loss": 0.2202, "lr": 7.047308319738988e-05, "epoch": 0.14110929853181076, "percentage": 0.71, "elapsed_time": "0:05:08", "remaining_time": "12:02:59", "throughput": 6083.27, "total_tokens": 1875104} +{"current_steps": 870, "total_steps": 122600, "loss": 0.143, "lr": 7.088091353996739e-05, "epoch": 0.14192495921696574, "percentage": 0.71, "elapsed_time": "0:05:09", "remaining_time": "12:02:36", "throughput": 6083.5, "total_tokens": 1885088} +{"current_steps": 875, "total_steps": 122600, "loss": 0.2554, "lr": 7.128874388254486e-05, "epoch": 0.14274061990212072, "percentage": 0.71, "elapsed_time": "0:05:11", "remaining_time": "12:02:22", "throughput": 6083.7, "total_tokens": 1895424} +{"current_steps": 880, "total_steps": 122600, "loss": 0.0546, "lr": 7.169657422512235e-05, "epoch": 0.14355628058727568, "percentage": 0.72, "elapsed_time": "0:05:13", "remaining_time": "12:02:17", "throughput": 6083.5, "total_tokens": 1906048} +{"current_steps": 885, "total_steps": 122600, "loss": 0.017, "lr": 7.210440456769984e-05, "epoch": 0.14437194127243066, "percentage": 0.72, "elapsed_time": "0:05:15", "remaining_time": "12:02:04", "throughput": 6083.24, "total_tokens": 1916320} +{"current_steps": 890, "total_steps": 122600, "loss": 0.1349, "lr": 7.251223491027732e-05, "epoch": 0.14518760195758565, "percentage": 0.73, "elapsed_time": "0:05:16", "remaining_time": "12:01:56", "throughput": 6083.23, "total_tokens": 1926880} +{"current_steps": 895, "total_steps": 122600, "loss": 0.1599, "lr": 7.292006525285481e-05, "epoch": 0.14600326264274063, "percentage": 0.73, "elapsed_time": "0:05:18", "remaining_time": "12:01:57", "throughput": 6083.13, "total_tokens": 1937792} +{"current_steps": 900, "total_steps": 122600, "loss": 0.4864, "lr": 7.332789559543231e-05, "epoch": 0.1468189233278956, "percentage": 0.73, "elapsed_time": "0:05:20", "remaining_time": "12:02:21", "throughput": 6083.97, "total_tokens": 1950048} +{"current_steps": 905, "total_steps": 122600, "loss": 0.5282, "lr": 7.373572593800979e-05, "epoch": 0.14763458401305057, "percentage": 0.74, "elapsed_time": "0:05:22", "remaining_time": "12:02:08", "throughput": 6083.97, "total_tokens": 1960352} +{"current_steps": 910, "total_steps": 122600, "loss": 0.2474, "lr": 7.414355628058728e-05, "epoch": 0.14845024469820556, "percentage": 0.74, "elapsed_time": "0:05:23", "remaining_time": "12:01:59", "throughput": 6083.68, "total_tokens": 1970784} +{"current_steps": 915, "total_steps": 122600, "loss": 0.3021, "lr": 7.455138662316477e-05, "epoch": 0.14926590538336051, "percentage": 0.75, "elapsed_time": "0:05:25", "remaining_time": "12:02:13", "throughput": 6084.27, "total_tokens": 1982528} +{"current_steps": 920, "total_steps": 122600, "loss": 0.23, "lr": 7.495921696574225e-05, "epoch": 0.1500815660685155, "percentage": 0.75, "elapsed_time": "0:05:27", "remaining_time": "12:01:56", "throughput": 6084.39, "total_tokens": 1992704} +{"current_steps": 925, "total_steps": 122600, "loss": 0.2117, "lr": 7.536704730831974e-05, "epoch": 0.15089722675367048, "percentage": 0.75, "elapsed_time": "0:05:29", "remaining_time": "12:01:53", "throughput": 6083.95, "total_tokens": 2003328} +{"current_steps": 930, "total_steps": 122600, "loss": 0.1221, "lr": 7.577487765089723e-05, "epoch": 0.15171288743882544, "percentage": 0.76, "elapsed_time": "0:05:30", "remaining_time": "12:01:39", "throughput": 6084.27, "total_tokens": 2013696} +{"current_steps": 935, "total_steps": 122600, "loss": 0.1289, "lr": 7.618270799347473e-05, "epoch": 0.15252854812398042, "percentage": 0.76, "elapsed_time": "0:05:32", "remaining_time": "12:01:34", "throughput": 6084.04, "total_tokens": 2024288} +{"current_steps": 940, "total_steps": 122600, "loss": 0.1985, "lr": 7.65905383360522e-05, "epoch": 0.1533442088091354, "percentage": 0.77, "elapsed_time": "0:05:34", "remaining_time": "12:01:34", "throughput": 6084.31, "total_tokens": 2035296} +{"current_steps": 945, "total_steps": 122600, "loss": 0.1994, "lr": 7.69983686786297e-05, "epoch": 0.15415986949429036, "percentage": 0.77, "elapsed_time": "0:05:36", "remaining_time": "12:02:01", "throughput": 6084.88, "total_tokens": 2047680} +{"current_steps": 950, "total_steps": 122600, "loss": 0.3784, "lr": 7.740619902120719e-05, "epoch": 0.15497553017944535, "percentage": 0.77, "elapsed_time": "0:05:38", "remaining_time": "12:01:55", "throughput": 6084.57, "total_tokens": 2058208} +{"current_steps": 955, "total_steps": 122600, "loss": 0.1371, "lr": 7.781402936378466e-05, "epoch": 0.15579119086460033, "percentage": 0.78, "elapsed_time": "0:05:40", "remaining_time": "12:02:04", "throughput": 6084.52, "total_tokens": 2069504} +{"current_steps": 960, "total_steps": 122600, "loss": 0.1568, "lr": 7.822185970636215e-05, "epoch": 0.1566068515497553, "percentage": 0.78, "elapsed_time": "0:05:41", "remaining_time": "12:02:03", "throughput": 6084.53, "total_tokens": 2080416} +{"current_steps": 965, "total_steps": 122600, "loss": 0.1437, "lr": 7.862969004893964e-05, "epoch": 0.15742251223491027, "percentage": 0.79, "elapsed_time": "0:05:43", "remaining_time": "12:01:53", "throughput": 6084.64, "total_tokens": 2090880} +{"current_steps": 970, "total_steps": 122600, "loss": 0.2885, "lr": 7.903752039151713e-05, "epoch": 0.15823817292006526, "percentage": 0.79, "elapsed_time": "0:05:45", "remaining_time": "12:01:44", "throughput": 6084.92, "total_tokens": 2101440} +{"current_steps": 975, "total_steps": 122600, "loss": 0.2561, "lr": 7.944535073409462e-05, "epoch": 0.15905383360522024, "percentage": 0.8, "elapsed_time": "0:05:47", "remaining_time": "12:01:26", "throughput": 6084.84, "total_tokens": 2111488} +{"current_steps": 980, "total_steps": 122600, "loss": 0.08, "lr": 7.985318107667211e-05, "epoch": 0.1598694942903752, "percentage": 0.8, "elapsed_time": "0:05:48", "remaining_time": "12:01:43", "throughput": 6085.33, "total_tokens": 2123392} +{"current_steps": 985, "total_steps": 122600, "loss": 0.0638, "lr": 8.026101141924959e-05, "epoch": 0.16068515497553018, "percentage": 0.8, "elapsed_time": "0:05:50", "remaining_time": "12:01:40", "throughput": 6085.0, "total_tokens": 2134016} +{"current_steps": 990, "total_steps": 122600, "loss": 0.2836, "lr": 8.066884176182708e-05, "epoch": 0.16150081566068517, "percentage": 0.81, "elapsed_time": "0:05:52", "remaining_time": "12:01:33", "throughput": 6085.3, "total_tokens": 2144736} +{"current_steps": 995, "total_steps": 122600, "loss": 0.1919, "lr": 8.107667210440457e-05, "epoch": 0.16231647634584012, "percentage": 0.81, "elapsed_time": "0:05:54", "remaining_time": "12:01:29", "throughput": 6085.55, "total_tokens": 2155520} +{"current_steps": 1000, "total_steps": 122600, "loss": 0.276, "lr": 8.148450244698205e-05, "epoch": 0.1631321370309951, "percentage": 0.82, "elapsed_time": "0:05:55", "remaining_time": "12:01:05", "throughput": 6085.69, "total_tokens": 2165312} +{"current_steps": 1005, "total_steps": 122600, "loss": 0.2269, "lr": 8.189233278955955e-05, "epoch": 0.1639477977161501, "percentage": 0.82, "elapsed_time": "0:05:57", "remaining_time": "12:00:46", "throughput": 6085.06, "total_tokens": 2175040} +{"current_steps": 1010, "total_steps": 122600, "loss": 0.2278, "lr": 8.230016313213704e-05, "epoch": 0.16476345840130505, "percentage": 0.82, "elapsed_time": "0:05:59", "remaining_time": "12:00:49", "throughput": 6085.24, "total_tokens": 2186176} +{"current_steps": 1015, "total_steps": 122600, "loss": 0.1486, "lr": 8.270799347471453e-05, "epoch": 0.16557911908646003, "percentage": 0.83, "elapsed_time": "0:06:00", "remaining_time": "12:00:27", "throughput": 6084.89, "total_tokens": 2195808} +{"current_steps": 1020, "total_steps": 122600, "loss": 0.0983, "lr": 8.3115823817292e-05, "epoch": 0.16639477977161501, "percentage": 0.83, "elapsed_time": "0:06:02", "remaining_time": "12:00:34", "throughput": 6085.29, "total_tokens": 2207232} +{"current_steps": 1025, "total_steps": 122600, "loss": 0.1653, "lr": 8.35236541598695e-05, "epoch": 0.16721044045676997, "percentage": 0.84, "elapsed_time": "0:06:04", "remaining_time": "12:00:49", "throughput": 6085.3, "total_tokens": 2218912} +{"current_steps": 1030, "total_steps": 122600, "loss": 0.1919, "lr": 8.393148450244699e-05, "epoch": 0.16802610114192496, "percentage": 0.84, "elapsed_time": "0:06:06", "remaining_time": "12:00:42", "throughput": 6085.39, "total_tokens": 2229536} +{"current_steps": 1035, "total_steps": 122600, "loss": 0.1526, "lr": 8.433931484502446e-05, "epoch": 0.16884176182707994, "percentage": 0.84, "elapsed_time": "0:06:08", "remaining_time": "12:00:44", "throughput": 6085.55, "total_tokens": 2240608} +{"current_steps": 1040, "total_steps": 122600, "loss": 0.3607, "lr": 8.474714518760197e-05, "epoch": 0.16965742251223492, "percentage": 0.85, "elapsed_time": "0:06:09", "remaining_time": "12:00:20", "throughput": 6085.38, "total_tokens": 2250176} +{"current_steps": 1045, "total_steps": 122600, "loss": 0.1367, "lr": 8.515497553017946e-05, "epoch": 0.17047308319738988, "percentage": 0.85, "elapsed_time": "0:06:11", "remaining_time": "12:00:34", "throughput": 6085.99, "total_tokens": 2262080} +{"current_steps": 1050, "total_steps": 122600, "loss": 0.0759, "lr": 8.556280587275693e-05, "epoch": 0.17128874388254486, "percentage": 0.86, "elapsed_time": "0:06:13", "remaining_time": "12:00:18", "throughput": 6085.5, "total_tokens": 2271968} +{"current_steps": 1055, "total_steps": 122600, "loss": 0.1543, "lr": 8.597063621533442e-05, "epoch": 0.17210440456769985, "percentage": 0.86, "elapsed_time": "0:06:15", "remaining_time": "12:00:05", "throughput": 6085.18, "total_tokens": 2282080} +{"current_steps": 1060, "total_steps": 122600, "loss": 0.1822, "lr": 8.637846655791191e-05, "epoch": 0.1729200652528548, "percentage": 0.86, "elapsed_time": "0:06:16", "remaining_time": "11:59:48", "throughput": 6084.37, "total_tokens": 2291744} +{"current_steps": 1065, "total_steps": 122600, "loss": 0.0599, "lr": 8.678629690048939e-05, "epoch": 0.1737357259380098, "percentage": 0.87, "elapsed_time": "0:06:18", "remaining_time": "11:59:40", "throughput": 6084.74, "total_tokens": 2302368} +{"current_steps": 1070, "total_steps": 122600, "loss": 0.1898, "lr": 8.719412724306688e-05, "epoch": 0.17455138662316477, "percentage": 0.87, "elapsed_time": "0:06:20", "remaining_time": "11:59:45", "throughput": 6084.96, "total_tokens": 2313664} +{"current_steps": 1075, "total_steps": 122600, "loss": 0.0623, "lr": 8.760195758564438e-05, "epoch": 0.17536704730831973, "percentage": 0.88, "elapsed_time": "0:06:22", "remaining_time": "11:59:55", "throughput": 6085.18, "total_tokens": 2325184} +{"current_steps": 1080, "total_steps": 122600, "loss": 0.2835, "lr": 8.800978792822187e-05, "epoch": 0.1761827079934747, "percentage": 0.88, "elapsed_time": "0:06:23", "remaining_time": "11:59:59", "throughput": 6085.36, "total_tokens": 2336352} +{"current_steps": 1085, "total_steps": 122600, "loss": 0.0245, "lr": 8.841761827079935e-05, "epoch": 0.1769983686786297, "percentage": 0.88, "elapsed_time": "0:06:25", "remaining_time": "11:59:50", "throughput": 6085.44, "total_tokens": 2346816} +{"current_steps": 1090, "total_steps": 122600, "loss": 0.0903, "lr": 8.882544861337684e-05, "epoch": 0.17781402936378465, "percentage": 0.89, "elapsed_time": "0:06:27", "remaining_time": "11:59:33", "throughput": 6085.1, "total_tokens": 2356672} +{"current_steps": 1095, "total_steps": 122600, "loss": 0.2582, "lr": 8.923327895595433e-05, "epoch": 0.17862969004893964, "percentage": 0.89, "elapsed_time": "0:06:29", "remaining_time": "11:59:27", "throughput": 6084.95, "total_tokens": 2367168} +{"current_steps": 1100, "total_steps": 122600, "loss": 0.2548, "lr": 8.96411092985318e-05, "epoch": 0.17944535073409462, "percentage": 0.9, "elapsed_time": "0:06:30", "remaining_time": "11:59:40", "throughput": 6085.25, "total_tokens": 2378912} +{"current_steps": 1105, "total_steps": 122600, "loss": 0.3341, "lr": 9.00489396411093e-05, "epoch": 0.1802610114192496, "percentage": 0.9, "elapsed_time": "0:06:32", "remaining_time": "11:59:56", "throughput": 6085.49, "total_tokens": 2390848} +{"current_steps": 1110, "total_steps": 122600, "loss": 0.199, "lr": 9.04567699836868e-05, "epoch": 0.18107667210440456, "percentage": 0.91, "elapsed_time": "0:06:34", "remaining_time": "11:59:50", "throughput": 6085.27, "total_tokens": 2401344} +{"current_steps": 1115, "total_steps": 122600, "loss": 0.1403, "lr": 9.086460032626427e-05, "epoch": 0.18189233278955955, "percentage": 0.91, "elapsed_time": "0:06:36", "remaining_time": "11:59:49", "throughput": 6085.32, "total_tokens": 2412224} +{"current_steps": 1120, "total_steps": 122600, "loss": 0.0222, "lr": 9.127243066884176e-05, "epoch": 0.18270799347471453, "percentage": 0.91, "elapsed_time": "0:06:38", "remaining_time": "11:59:46", "throughput": 6085.67, "total_tokens": 2423072} +{"current_steps": 1125, "total_steps": 122600, "loss": 0.1462, "lr": 9.168026101141925e-05, "epoch": 0.1835236541598695, "percentage": 0.92, "elapsed_time": "0:06:40", "remaining_time": "11:59:54", "throughput": 6085.51, "total_tokens": 2434368} +{"current_steps": 1130, "total_steps": 122600, "loss": 0.3705, "lr": 9.208809135399673e-05, "epoch": 0.18433931484502447, "percentage": 0.92, "elapsed_time": "0:06:41", "remaining_time": "11:59:40", "throughput": 6085.5, "total_tokens": 2444544} +{"current_steps": 1135, "total_steps": 122600, "loss": 0.1005, "lr": 9.249592169657422e-05, "epoch": 0.18515497553017946, "percentage": 0.93, "elapsed_time": "0:06:43", "remaining_time": "11:59:19", "throughput": 6084.96, "total_tokens": 2454048} +{"current_steps": 1140, "total_steps": 122600, "loss": 0.2374, "lr": 9.290375203915171e-05, "epoch": 0.1859706362153344, "percentage": 0.93, "elapsed_time": "0:06:45", "remaining_time": "11:59:14", "throughput": 6085.08, "total_tokens": 2464704} +{"current_steps": 1145, "total_steps": 122600, "loss": 0.359, "lr": 9.33115823817292e-05, "epoch": 0.1867862969004894, "percentage": 0.93, "elapsed_time": "0:06:46", "remaining_time": "11:59:17", "throughput": 6084.92, "total_tokens": 2475712} +{"current_steps": 1150, "total_steps": 122600, "loss": 0.3164, "lr": 9.371941272430669e-05, "epoch": 0.18760195758564438, "percentage": 0.94, "elapsed_time": "0:06:48", "remaining_time": "11:59:42", "throughput": 6085.64, "total_tokens": 2488352} +{"current_steps": 1155, "total_steps": 122600, "loss": 0.206, "lr": 9.412724306688418e-05, "epoch": 0.18841761827079934, "percentage": 0.94, "elapsed_time": "0:06:50", "remaining_time": "11:59:41", "throughput": 6085.65, "total_tokens": 2499232} +{"current_steps": 1160, "total_steps": 122600, "loss": 0.0639, "lr": 9.453507340946167e-05, "epoch": 0.18923327895595432, "percentage": 0.95, "elapsed_time": "0:06:52", "remaining_time": "11:59:28", "throughput": 6085.58, "total_tokens": 2509376} +{"current_steps": 1165, "total_steps": 122600, "loss": 0.178, "lr": 9.494290375203915e-05, "epoch": 0.1900489396411093, "percentage": 0.95, "elapsed_time": "0:06:54", "remaining_time": "11:59:30", "throughput": 6085.48, "total_tokens": 2520352} +{"current_steps": 1170, "total_steps": 122600, "loss": 0.1206, "lr": 9.535073409461664e-05, "epoch": 0.19086460032626426, "percentage": 0.95, "elapsed_time": "0:06:55", "remaining_time": "11:59:21", "throughput": 6085.44, "total_tokens": 2530752} +{"current_steps": 1175, "total_steps": 122600, "loss": 0.4729, "lr": 9.575856443719413e-05, "epoch": 0.19168026101141925, "percentage": 0.96, "elapsed_time": "0:06:57", "remaining_time": "11:58:54", "throughput": 6084.97, "total_tokens": 2539872} +{"current_steps": 1180, "total_steps": 122600, "loss": 0.2679, "lr": 9.616639477977162e-05, "epoch": 0.19249592169657423, "percentage": 0.96, "elapsed_time": "0:06:59", "remaining_time": "11:59:02", "throughput": 6085.39, "total_tokens": 2551456} +{"current_steps": 1185, "total_steps": 122600, "loss": 0.119, "lr": 9.657422512234911e-05, "epoch": 0.1933115823817292, "percentage": 0.97, "elapsed_time": "0:07:01", "remaining_time": "11:59:14", "throughput": 6085.58, "total_tokens": 2563136} +{"current_steps": 1190, "total_steps": 122600, "loss": 0.0195, "lr": 9.69820554649266e-05, "epoch": 0.19412724306688417, "percentage": 0.97, "elapsed_time": "0:07:02", "remaining_time": "11:59:13", "throughput": 6085.55, "total_tokens": 2573984} +{"current_steps": 1195, "total_steps": 122600, "loss": 0.2677, "lr": 9.738988580750407e-05, "epoch": 0.19494290375203915, "percentage": 0.97, "elapsed_time": "0:07:04", "remaining_time": "11:59:19", "throughput": 6085.66, "total_tokens": 2585344} +{"current_steps": 1200, "total_steps": 122600, "loss": 0.2518, "lr": 9.779771615008156e-05, "epoch": 0.19575856443719414, "percentage": 0.98, "elapsed_time": "0:07:06", "remaining_time": "11:59:22", "throughput": 6085.71, "total_tokens": 2596448} +{"current_steps": 1205, "total_steps": 122600, "loss": 0.5066, "lr": 9.820554649265905e-05, "epoch": 0.1965742251223491, "percentage": 0.98, "elapsed_time": "0:07:08", "remaining_time": "11:59:13", "throughput": 6085.73, "total_tokens": 2606848} +{"current_steps": 1210, "total_steps": 122600, "loss": 0.1164, "lr": 9.861337683523653e-05, "epoch": 0.19738988580750408, "percentage": 0.99, "elapsed_time": "0:07:10", "remaining_time": "11:59:14", "throughput": 6085.95, "total_tokens": 2617952} +{"current_steps": 1215, "total_steps": 122600, "loss": 0.0511, "lr": 9.902120717781403e-05, "epoch": 0.19820554649265906, "percentage": 0.99, "elapsed_time": "0:07:11", "remaining_time": "11:59:09", "throughput": 6085.66, "total_tokens": 2628448} +{"current_steps": 1220, "total_steps": 122600, "loss": 0.2794, "lr": 9.942903752039152e-05, "epoch": 0.19902120717781402, "percentage": 1.0, "elapsed_time": "0:07:13", "remaining_time": "11:59:15", "throughput": 6085.47, "total_tokens": 2639648} +{"current_steps": 1225, "total_steps": 122600, "loss": 0.0933, "lr": 9.983686786296901e-05, "epoch": 0.199836867862969, "percentage": 1.0, "elapsed_time": "0:07:15", "remaining_time": "11:59:10", "throughput": 6085.09, "total_tokens": 2650112} +{"current_steps": 1230, "total_steps": 122600, "loss": 0.5332, "lr": 0.00010024469820554649, "epoch": 0.200652528548124, "percentage": 1.0, "elapsed_time": "0:07:17", "remaining_time": "11:59:04", "throughput": 6084.98, "total_tokens": 2660576} +{"current_steps": 1235, "total_steps": 122600, "loss": 0.0976, "lr": 0.00010065252854812398, "epoch": 0.20146818923327894, "percentage": 1.01, "elapsed_time": "0:07:18", "remaining_time": "11:58:34", "throughput": 6084.53, "total_tokens": 2669440} +{"current_steps": 1240, "total_steps": 122600, "loss": 0.2455, "lr": 0.00010106035889070147, "epoch": 0.20228384991843393, "percentage": 1.01, "elapsed_time": "0:07:20", "remaining_time": "11:58:35", "throughput": 6084.76, "total_tokens": 2680544} +{"current_steps": 1245, "total_steps": 122600, "loss": 0.2392, "lr": 0.00010146818923327896, "epoch": 0.2030995106035889, "percentage": 1.02, "elapsed_time": "0:07:22", "remaining_time": "11:58:50", "throughput": 6085.25, "total_tokens": 2692608} +{"current_steps": 1250, "total_steps": 122600, "loss": 0.1251, "lr": 0.00010187601957585645, "epoch": 0.2039151712887439, "percentage": 1.02, "elapsed_time": "0:07:24", "remaining_time": "11:58:23", "throughput": 6085.03, "total_tokens": 2701760} +{"current_steps": 1255, "total_steps": 122600, "loss": 0.2331, "lr": 0.00010228384991843394, "epoch": 0.20473083197389885, "percentage": 1.02, "elapsed_time": "0:07:25", "remaining_time": "11:58:19", "throughput": 6084.79, "total_tokens": 2712288} +{"current_steps": 1260, "total_steps": 122600, "loss": 0.1405, "lr": 0.00010269168026101142, "epoch": 0.20554649265905384, "percentage": 1.03, "elapsed_time": "0:07:27", "remaining_time": "11:58:21", "throughput": 6085.05, "total_tokens": 2723488} +{"current_steps": 1265, "total_steps": 122600, "loss": 0.1611, "lr": 0.00010309951060358891, "epoch": 0.20636215334420882, "percentage": 1.03, "elapsed_time": "0:07:29", "remaining_time": "11:58:23", "throughput": 6084.85, "total_tokens": 2734400} +{"current_steps": 1270, "total_steps": 122600, "loss": 0.0854, "lr": 0.0001035073409461664, "epoch": 0.20717781402936378, "percentage": 1.04, "elapsed_time": "0:07:31", "remaining_time": "11:58:36", "throughput": 6084.97, "total_tokens": 2746208} +{"current_steps": 1275, "total_steps": 122600, "loss": 0.1824, "lr": 0.00010391517128874387, "epoch": 0.20799347471451876, "percentage": 1.04, "elapsed_time": "0:07:33", "remaining_time": "11:58:37", "throughput": 6084.93, "total_tokens": 2757216} +{"current_steps": 1280, "total_steps": 122600, "loss": 0.1912, "lr": 0.00010432300163132138, "epoch": 0.20880913539967375, "percentage": 1.04, "elapsed_time": "0:07:34", "remaining_time": "11:58:39", "throughput": 6084.81, "total_tokens": 2768192} +{"current_steps": 1285, "total_steps": 122600, "loss": 0.0904, "lr": 0.00010473083197389887, "epoch": 0.2096247960848287, "percentage": 1.05, "elapsed_time": "0:07:36", "remaining_time": "11:58:28", "throughput": 6084.83, "total_tokens": 2778400} +{"current_steps": 1290, "total_steps": 122600, "loss": 0.3657, "lr": 0.00010513866231647634, "epoch": 0.21044045676998369, "percentage": 1.05, "elapsed_time": "0:07:38", "remaining_time": "11:58:14", "throughput": 6084.75, "total_tokens": 2788416} +{"current_steps": 1295, "total_steps": 122600, "loss": 0.3439, "lr": 0.00010554649265905383, "epoch": 0.21125611745513867, "percentage": 1.06, "elapsed_time": "0:07:40", "remaining_time": "11:58:15", "throughput": 6084.72, "total_tokens": 2799360} +{"current_steps": 1300, "total_steps": 122600, "loss": 0.199, "lr": 0.00010595432300163132, "epoch": 0.21207177814029363, "percentage": 1.06, "elapsed_time": "0:07:41", "remaining_time": "11:58:07", "throughput": 6084.62, "total_tokens": 2809728} +{"current_steps": 1305, "total_steps": 122600, "loss": 0.2865, "lr": 0.00010636215334420881, "epoch": 0.2128874388254486, "percentage": 1.06, "elapsed_time": "0:07:43", "remaining_time": "11:57:55", "throughput": 6084.4, "total_tokens": 2819776} +{"current_steps": 1310, "total_steps": 122600, "loss": 0.1692, "lr": 0.00010676998368678629, "epoch": 0.2137030995106036, "percentage": 1.07, "elapsed_time": "0:07:45", "remaining_time": "11:58:04", "throughput": 6084.59, "total_tokens": 2831360} +{"current_steps": 1315, "total_steps": 122600, "loss": 0.1563, "lr": 0.0001071778140293638, "epoch": 0.21451876019575855, "percentage": 1.07, "elapsed_time": "0:07:47", "remaining_time": "11:58:05", "throughput": 6084.76, "total_tokens": 2842432} +{"current_steps": 1320, "total_steps": 122600, "loss": 0.122, "lr": 0.00010758564437194128, "epoch": 0.21533442088091354, "percentage": 1.08, "elapsed_time": "0:07:48", "remaining_time": "11:57:54", "throughput": 6084.35, "total_tokens": 2852448} +{"current_steps": 1325, "total_steps": 122600, "loss": 0.088, "lr": 0.00010799347471451876, "epoch": 0.21615008156606852, "percentage": 1.08, "elapsed_time": "0:07:50", "remaining_time": "11:57:47", "throughput": 6084.3, "total_tokens": 2862912} +{"current_steps": 1330, "total_steps": 122600, "loss": 0.2082, "lr": 0.00010840130505709625, "epoch": 0.2169657422512235, "percentage": 1.08, "elapsed_time": "0:07:52", "remaining_time": "11:57:48", "throughput": 6084.35, "total_tokens": 2873888} +{"current_steps": 1335, "total_steps": 122600, "loss": 0.1894, "lr": 0.00010880913539967374, "epoch": 0.21778140293637846, "percentage": 1.09, "elapsed_time": "0:07:54", "remaining_time": "11:57:58", "throughput": 6084.66, "total_tokens": 2885664} +{"current_steps": 1340, "total_steps": 122600, "loss": 0.367, "lr": 0.00010921696574225122, "epoch": 0.21859706362153344, "percentage": 1.09, "elapsed_time": "0:07:56", "remaining_time": "11:57:54", "throughput": 6084.63, "total_tokens": 2896288} +{"current_steps": 1345, "total_steps": 122600, "loss": 0.1078, "lr": 0.0001096247960848287, "epoch": 0.21941272430668843, "percentage": 1.1, "elapsed_time": "0:07:57", "remaining_time": "11:57:55", "throughput": 6084.59, "total_tokens": 2907264} +{"current_steps": 1350, "total_steps": 122600, "loss": 0.3341, "lr": 0.00011003262642740621, "epoch": 0.22022838499184338, "percentage": 1.1, "elapsed_time": "0:07:59", "remaining_time": "11:57:58", "throughput": 6084.73, "total_tokens": 2918464} +{"current_steps": 1355, "total_steps": 122600, "loss": 0.4854, "lr": 0.00011044045676998369, "epoch": 0.22104404567699837, "percentage": 1.11, "elapsed_time": "0:08:01", "remaining_time": "11:58:04", "throughput": 6084.71, "total_tokens": 2929792} +{"current_steps": 1360, "total_steps": 122600, "loss": 0.1755, "lr": 0.00011084828711256118, "epoch": 0.22185970636215335, "percentage": 1.11, "elapsed_time": "0:08:03", "remaining_time": "11:57:56", "throughput": 6084.48, "total_tokens": 2940064} +{"current_steps": 1365, "total_steps": 122600, "loss": 0.0783, "lr": 0.00011125611745513867, "epoch": 0.2226753670473083, "percentage": 1.11, "elapsed_time": "0:08:04", "remaining_time": "11:57:49", "throughput": 6084.22, "total_tokens": 2950368} +{"current_steps": 1370, "total_steps": 122600, "loss": 0.3597, "lr": 0.00011166394779771616, "epoch": 0.2234910277324633, "percentage": 1.12, "elapsed_time": "0:08:06", "remaining_time": "11:57:39", "throughput": 6083.89, "total_tokens": 2960448} +{"current_steps": 1375, "total_steps": 122600, "loss": 0.1461, "lr": 0.00011207177814029363, "epoch": 0.22430668841761828, "percentage": 1.12, "elapsed_time": "0:08:08", "remaining_time": "11:57:47", "throughput": 6084.1, "total_tokens": 2972032} +{"current_steps": 1380, "total_steps": 122600, "loss": 0.1338, "lr": 0.00011247960848287112, "epoch": 0.22512234910277323, "percentage": 1.13, "elapsed_time": "0:08:10", "remaining_time": "11:58:00", "throughput": 6084.66, "total_tokens": 2984160} +{"current_steps": 1385, "total_steps": 122600, "loss": 0.0982, "lr": 0.00011288743882544863, "epoch": 0.22593800978792822, "percentage": 1.13, "elapsed_time": "0:08:12", "remaining_time": "11:57:55", "throughput": 6084.68, "total_tokens": 2994752} +{"current_steps": 1390, "total_steps": 122600, "loss": 0.1263, "lr": 0.0001132952691680261, "epoch": 0.2267536704730832, "percentage": 1.13, "elapsed_time": "0:08:13", "remaining_time": "11:57:52", "throughput": 6084.41, "total_tokens": 3005376} +{"current_steps": 1395, "total_steps": 122600, "loss": 0.2681, "lr": 0.00011370309951060359, "epoch": 0.2275693311582382, "percentage": 1.14, "elapsed_time": "0:08:15", "remaining_time": "11:57:56", "throughput": 6084.38, "total_tokens": 3016576} +{"current_steps": 1400, "total_steps": 122600, "loss": 0.3882, "lr": 0.00011411092985318108, "epoch": 0.22838499184339314, "percentage": 1.14, "elapsed_time": "0:08:17", "remaining_time": "11:58:12", "throughput": 6084.6, "total_tokens": 3028704} +{"current_steps": 1405, "total_steps": 122600, "loss": 0.3004, "lr": 0.00011451876019575856, "epoch": 0.22920065252854813, "percentage": 1.15, "elapsed_time": "0:08:19", "remaining_time": "11:58:10", "throughput": 6084.5, "total_tokens": 3039456} +{"current_steps": 1410, "total_steps": 122600, "loss": 0.2714, "lr": 0.00011492659053833605, "epoch": 0.2300163132137031, "percentage": 1.15, "elapsed_time": "0:08:21", "remaining_time": "11:58:17", "throughput": 6084.28, "total_tokens": 3050816} +{"current_steps": 1415, "total_steps": 122600, "loss": 0.1503, "lr": 0.00011533442088091354, "epoch": 0.23083197389885807, "percentage": 1.15, "elapsed_time": "0:08:22", "remaining_time": "11:57:56", "throughput": 6083.91, "total_tokens": 3060064} +{"current_steps": 1420, "total_steps": 122600, "loss": 0.2217, "lr": 0.00011574225122349103, "epoch": 0.23164763458401305, "percentage": 1.16, "elapsed_time": "0:08:24", "remaining_time": "11:58:07", "throughput": 6084.18, "total_tokens": 3071936} +{"current_steps": 1425, "total_steps": 122600, "loss": 0.0531, "lr": 0.00011615008156606852, "epoch": 0.23246329526916804, "percentage": 1.16, "elapsed_time": "0:08:26", "remaining_time": "11:58:05", "throughput": 6084.23, "total_tokens": 3082752} +{"current_steps": 1430, "total_steps": 122600, "loss": 0.0955, "lr": 0.00011655791190864601, "epoch": 0.233278955954323, "percentage": 1.17, "elapsed_time": "0:08:28", "remaining_time": "11:58:14", "throughput": 6084.77, "total_tokens": 3094592} +{"current_steps": 1435, "total_steps": 122600, "loss": 0.2884, "lr": 0.0001169657422512235, "epoch": 0.23409461663947798, "percentage": 1.17, "elapsed_time": "0:08:30", "remaining_time": "11:58:10", "throughput": 6084.77, "total_tokens": 3105312} +{"current_steps": 1440, "total_steps": 122600, "loss": 0.0951, "lr": 0.00011737357259380098, "epoch": 0.23491027732463296, "percentage": 1.17, "elapsed_time": "0:08:32", "remaining_time": "11:58:06", "throughput": 6084.44, "total_tokens": 3115776} +{"current_steps": 1445, "total_steps": 122600, "loss": 0.0828, "lr": 0.00011778140293637847, "epoch": 0.23572593800978792, "percentage": 1.18, "elapsed_time": "0:08:33", "remaining_time": "11:58:14", "throughput": 6084.56, "total_tokens": 3127392} +{"current_steps": 1450, "total_steps": 122600, "loss": 0.1222, "lr": 0.00011818923327895596, "epoch": 0.2365415986949429, "percentage": 1.18, "elapsed_time": "0:08:35", "remaining_time": "11:58:07", "throughput": 6084.55, "total_tokens": 3137760} +{"current_steps": 1455, "total_steps": 122600, "loss": 0.2851, "lr": 0.00011859706362153345, "epoch": 0.23735725938009788, "percentage": 1.19, "elapsed_time": "0:08:37", "remaining_time": "11:58:00", "throughput": 6084.54, "total_tokens": 3148192} +{"current_steps": 1460, "total_steps": 122600, "loss": 0.1418, "lr": 0.00011900489396411094, "epoch": 0.23817292006525284, "percentage": 1.19, "elapsed_time": "0:08:39", "remaining_time": "11:57:58", "throughput": 6084.49, "total_tokens": 3159008} +{"current_steps": 1465, "total_steps": 122600, "loss": 0.0804, "lr": 0.00011941272430668843, "epoch": 0.23898858075040783, "percentage": 1.19, "elapsed_time": "0:08:41", "remaining_time": "11:58:10", "throughput": 6084.46, "total_tokens": 3170784} +{"current_steps": 1470, "total_steps": 122600, "loss": 0.1997, "lr": 0.0001198205546492659, "epoch": 0.2398042414355628, "percentage": 1.2, "elapsed_time": "0:08:42", "remaining_time": "11:58:12", "throughput": 6084.58, "total_tokens": 3182016} +{"current_steps": 1475, "total_steps": 122600, "loss": 0.2176, "lr": 0.00012022838499184339, "epoch": 0.2406199021207178, "percentage": 1.2, "elapsed_time": "0:08:44", "remaining_time": "11:58:06", "throughput": 6084.16, "total_tokens": 3192288} +{"current_steps": 1480, "total_steps": 122600, "loss": 0.1662, "lr": 0.00012063621533442088, "epoch": 0.24143556280587275, "percentage": 1.21, "elapsed_time": "0:08:46", "remaining_time": "11:57:57", "throughput": 6084.17, "total_tokens": 3202560} +{"current_steps": 1485, "total_steps": 122600, "loss": 0.2372, "lr": 0.00012104404567699836, "epoch": 0.24225122349102773, "percentage": 1.21, "elapsed_time": "0:08:48", "remaining_time": "11:58:02", "throughput": 6084.17, "total_tokens": 3213888} +{"current_steps": 1490, "total_steps": 122600, "loss": 0.2751, "lr": 0.00012145187601957586, "epoch": 0.24306688417618272, "percentage": 1.22, "elapsed_time": "0:08:49", "remaining_time": "11:57:53", "throughput": 6083.95, "total_tokens": 3224032} +{"current_steps": 1495, "total_steps": 122600, "loss": 0.0815, "lr": 0.00012185970636215335, "epoch": 0.24388254486133767, "percentage": 1.22, "elapsed_time": "0:08:51", "remaining_time": "11:57:50", "throughput": 6083.89, "total_tokens": 3234720} +{"current_steps": 1500, "total_steps": 122600, "loss": 0.2188, "lr": 0.00012226753670473083, "epoch": 0.24469820554649266, "percentage": 1.22, "elapsed_time": "0:08:53", "remaining_time": "11:57:40", "throughput": 6083.9, "total_tokens": 3244928} +{"current_steps": 1505, "total_steps": 122600, "loss": 0.3815, "lr": 0.00012267536704730833, "epoch": 0.24551386623164764, "percentage": 1.23, "elapsed_time": "0:08:54", "remaining_time": "11:57:22", "throughput": 6083.81, "total_tokens": 3254528} +{"current_steps": 1510, "total_steps": 122600, "loss": 0.0437, "lr": 0.0001230831973898858, "epoch": 0.2463295269168026, "percentage": 1.23, "elapsed_time": "0:08:56", "remaining_time": "11:57:14", "throughput": 6083.66, "total_tokens": 3264768} +{"current_steps": 1515, "total_steps": 122600, "loss": 0.0471, "lr": 0.0001234910277324633, "epoch": 0.24714518760195758, "percentage": 1.24, "elapsed_time": "0:08:58", "remaining_time": "11:57:28", "throughput": 6083.66, "total_tokens": 3276736} +{"current_steps": 1520, "total_steps": 122600, "loss": 0.5108, "lr": 0.0001238988580750408, "epoch": 0.24796084828711257, "percentage": 1.24, "elapsed_time": "0:09:00", "remaining_time": "11:57:22", "throughput": 6083.63, "total_tokens": 3287264} +{"current_steps": 1525, "total_steps": 122600, "loss": 0.3454, "lr": 0.00012430668841761827, "epoch": 0.24877650897226752, "percentage": 1.24, "elapsed_time": "0:09:02", "remaining_time": "11:57:20", "throughput": 6083.69, "total_tokens": 3298048} +{"current_steps": 1530, "total_steps": 122600, "loss": 0.2622, "lr": 0.00012471451876019577, "epoch": 0.2495921696574225, "percentage": 1.25, "elapsed_time": "0:09:03", "remaining_time": "11:57:15", "throughput": 6083.64, "total_tokens": 3308640} +{"current_steps": 1535, "total_steps": 122600, "loss": 0.1249, "lr": 0.00012512234910277325, "epoch": 0.25040783034257746, "percentage": 1.25, "elapsed_time": "0:09:05", "remaining_time": "11:57:07", "throughput": 6083.83, "total_tokens": 3319040} +{"current_steps": 1540, "total_steps": 122600, "loss": 0.0722, "lr": 0.00012553017944535072, "epoch": 0.25122349102773245, "percentage": 1.26, "elapsed_time": "0:09:07", "remaining_time": "11:57:16", "throughput": 6083.91, "total_tokens": 3330720} +{"current_steps": 1545, "total_steps": 122600, "loss": 0.3257, "lr": 0.00012593800978792823, "epoch": 0.25203915171288743, "percentage": 1.26, "elapsed_time": "0:09:09", "remaining_time": "11:57:01", "throughput": 6083.58, "total_tokens": 3340352} +{"current_steps": 1550, "total_steps": 122600, "loss": 0.2996, "lr": 0.0001263458401305057, "epoch": 0.2528548123980424, "percentage": 1.26, "elapsed_time": "0:09:10", "remaining_time": "11:56:49", "throughput": 6083.43, "total_tokens": 3350272} +{"current_steps": 1555, "total_steps": 122600, "loss": 0.2076, "lr": 0.0001267536704730832, "epoch": 0.2536704730831974, "percentage": 1.27, "elapsed_time": "0:09:12", "remaining_time": "11:56:52", "throughput": 6083.43, "total_tokens": 3361440} +{"current_steps": 1560, "total_steps": 122600, "loss": 0.2664, "lr": 0.00012716150081566068, "epoch": 0.2544861337683524, "percentage": 1.27, "elapsed_time": "0:09:14", "remaining_time": "11:57:04", "throughput": 6083.87, "total_tokens": 3373600} +{"current_steps": 1565, "total_steps": 122600, "loss": 0.2678, "lr": 0.00012756933115823819, "epoch": 0.2553017944535073, "percentage": 1.28, "elapsed_time": "0:09:16", "remaining_time": "11:56:59", "throughput": 6083.9, "total_tokens": 3384160} +{"current_steps": 1570, "total_steps": 122600, "loss": 0.6454, "lr": 0.00012797716150081566, "epoch": 0.2561174551386623, "percentage": 1.28, "elapsed_time": "0:09:17", "remaining_time": "11:56:44", "throughput": 6083.72, "total_tokens": 3393792} +{"current_steps": 1575, "total_steps": 122600, "loss": 0.4939, "lr": 0.00012838499184339314, "epoch": 0.2569331158238173, "percentage": 1.28, "elapsed_time": "0:09:19", "remaining_time": "11:56:43", "throughput": 6083.55, "total_tokens": 3404576} +{"current_steps": 1580, "total_steps": 122600, "loss": 0.2159, "lr": 0.00012879282218597064, "epoch": 0.25774877650897227, "percentage": 1.29, "elapsed_time": "0:09:21", "remaining_time": "11:56:33", "throughput": 6083.71, "total_tokens": 3414816} +{"current_steps": 1585, "total_steps": 122600, "loss": 0.1312, "lr": 0.00012920065252854812, "epoch": 0.25856443719412725, "percentage": 1.29, "elapsed_time": "0:09:23", "remaining_time": "11:56:26", "throughput": 6083.69, "total_tokens": 3425248} +{"current_steps": 1590, "total_steps": 122600, "loss": 0.069, "lr": 0.00012960848287112562, "epoch": 0.25938009787928223, "percentage": 1.3, "elapsed_time": "0:09:24", "remaining_time": "11:56:21", "throughput": 6083.59, "total_tokens": 3435680} +{"current_steps": 1595, "total_steps": 122600, "loss": 0.0704, "lr": 0.0001300163132137031, "epoch": 0.2601957585644372, "percentage": 1.3, "elapsed_time": "0:09:26", "remaining_time": "11:56:29", "throughput": 6083.85, "total_tokens": 3447488} +{"current_steps": 1600, "total_steps": 122600, "loss": 0.1689, "lr": 0.0001304241435562806, "epoch": 0.26101141924959215, "percentage": 1.31, "elapsed_time": "0:09:28", "remaining_time": "11:56:30", "throughput": 6083.61, "total_tokens": 3458336} +{"current_steps": 1605, "total_steps": 122600, "loss": 0.2302, "lr": 0.00013083197389885805, "epoch": 0.26182707993474713, "percentage": 1.31, "elapsed_time": "0:09:30", "remaining_time": "11:56:13", "throughput": 6083.25, "total_tokens": 3467680} +{"current_steps": 1610, "total_steps": 122600, "loss": 0.3058, "lr": 0.00013123980424143555, "epoch": 0.2626427406199021, "percentage": 1.31, "elapsed_time": "0:09:31", "remaining_time": "11:56:11", "throughput": 6083.11, "total_tokens": 3478400} +{"current_steps": 1615, "total_steps": 122600, "loss": 0.0356, "lr": 0.00013164763458401306, "epoch": 0.2634584013050571, "percentage": 1.32, "elapsed_time": "0:09:33", "remaining_time": "11:56:09", "throughput": 6083.25, "total_tokens": 3489280} +{"current_steps": 1620, "total_steps": 122600, "loss": 0.3348, "lr": 0.00013205546492659053, "epoch": 0.2642740619902121, "percentage": 1.32, "elapsed_time": "0:09:35", "remaining_time": "11:56:14", "throughput": 6083.48, "total_tokens": 3500800} +{"current_steps": 1625, "total_steps": 122600, "loss": 0.1261, "lr": 0.00013246329526916804, "epoch": 0.26508972267536707, "percentage": 1.33, "elapsed_time": "0:09:37", "remaining_time": "11:56:03", "throughput": 6083.22, "total_tokens": 3510656} +{"current_steps": 1630, "total_steps": 122600, "loss": 0.1386, "lr": 0.00013287112561174552, "epoch": 0.265905383360522, "percentage": 1.33, "elapsed_time": "0:09:38", "remaining_time": "11:56:02", "throughput": 6083.55, "total_tokens": 3521696} +{"current_steps": 1635, "total_steps": 122600, "loss": 0.0952, "lr": 0.00013327895595432302, "epoch": 0.266721044045677, "percentage": 1.33, "elapsed_time": "0:09:40", "remaining_time": "11:56:18", "throughput": 6084.07, "total_tokens": 3534304} +{"current_steps": 1640, "total_steps": 122600, "loss": 0.2073, "lr": 0.00013368678629690047, "epoch": 0.26753670473083196, "percentage": 1.34, "elapsed_time": "0:09:42", "remaining_time": "11:56:10", "throughput": 6083.78, "total_tokens": 3544416} +{"current_steps": 1645, "total_steps": 122600, "loss": 0.1812, "lr": 0.00013409461663947797, "epoch": 0.26835236541598695, "percentage": 1.34, "elapsed_time": "0:09:44", "remaining_time": "11:55:51", "throughput": 6083.68, "total_tokens": 3553760} +{"current_steps": 1650, "total_steps": 122600, "loss": 0.1423, "lr": 0.00013450244698205548, "epoch": 0.26916802610114193, "percentage": 1.35, "elapsed_time": "0:09:45", "remaining_time": "11:55:43", "throughput": 6083.3, "total_tokens": 3563776} +{"current_steps": 1655, "total_steps": 122600, "loss": 0.1907, "lr": 0.00013491027732463295, "epoch": 0.2699836867862969, "percentage": 1.35, "elapsed_time": "0:09:47", "remaining_time": "11:55:47", "throughput": 6083.51, "total_tokens": 3575200} +{"current_steps": 1660, "total_steps": 122600, "loss": 0.1143, "lr": 0.00013531810766721046, "epoch": 0.2707993474714519, "percentage": 1.35, "elapsed_time": "0:09:49", "remaining_time": "11:55:59", "throughput": 6083.83, "total_tokens": 3587328} +{"current_steps": 1665, "total_steps": 122600, "loss": 0.15, "lr": 0.00013572593800978793, "epoch": 0.27161500815660683, "percentage": 1.36, "elapsed_time": "0:09:51", "remaining_time": "11:55:46", "throughput": 6083.62, "total_tokens": 3597056} +{"current_steps": 1670, "total_steps": 122600, "loss": 0.0857, "lr": 0.0001361337683523654, "epoch": 0.2724306688417618, "percentage": 1.36, "elapsed_time": "0:09:53", "remaining_time": "11:55:45", "throughput": 6083.83, "total_tokens": 3608064} +{"current_steps": 1675, "total_steps": 122600, "loss": 0.2567, "lr": 0.00013654159869494288, "epoch": 0.2732463295269168, "percentage": 1.37, "elapsed_time": "0:09:54", "remaining_time": "11:55:36", "throughput": 6083.65, "total_tokens": 3618208} +{"current_steps": 1680, "total_steps": 122600, "loss": 0.4063, "lr": 0.0001369494290375204, "epoch": 0.2740619902120718, "percentage": 1.37, "elapsed_time": "0:09:56", "remaining_time": "11:55:42", "throughput": 6083.61, "total_tokens": 3629600} +{"current_steps": 1685, "total_steps": 122600, "loss": 0.1756, "lr": 0.0001373572593800979, "epoch": 0.27487765089722677, "percentage": 1.37, "elapsed_time": "0:09:58", "remaining_time": "11:55:36", "throughput": 6083.74, "total_tokens": 3640160} +{"current_steps": 1690, "total_steps": 122600, "loss": 0.1398, "lr": 0.00013776508972267537, "epoch": 0.27569331158238175, "percentage": 1.38, "elapsed_time": "0:09:59", "remaining_time": "11:55:24", "throughput": 6083.64, "total_tokens": 3649984} +{"current_steps": 1695, "total_steps": 122600, "loss": 0.041, "lr": 0.00013817292006525287, "epoch": 0.2765089722675367, "percentage": 1.38, "elapsed_time": "0:10:01", "remaining_time": "11:55:20", "throughput": 6083.54, "total_tokens": 3660544} +{"current_steps": 1700, "total_steps": 122600, "loss": 0.2259, "lr": 0.00013858075040783035, "epoch": 0.27732463295269166, "percentage": 1.39, "elapsed_time": "0:10:03", "remaining_time": "11:55:12", "throughput": 6083.26, "total_tokens": 3670688} +{"current_steps": 1705, "total_steps": 122600, "loss": 0.1137, "lr": 0.00013898858075040782, "epoch": 0.27814029363784665, "percentage": 1.39, "elapsed_time": "0:10:05", "remaining_time": "11:55:05", "throughput": 6083.04, "total_tokens": 3680896} +{"current_steps": 1710, "total_steps": 122600, "loss": 0.1308, "lr": 0.00013939641109298533, "epoch": 0.27895595432300163, "percentage": 1.39, "elapsed_time": "0:10:06", "remaining_time": "11:55:04", "throughput": 6082.89, "total_tokens": 3691648} +{"current_steps": 1715, "total_steps": 122600, "loss": 0.2624, "lr": 0.0001398042414355628, "epoch": 0.2797716150081566, "percentage": 1.4, "elapsed_time": "0:10:08", "remaining_time": "11:54:58", "throughput": 6082.68, "total_tokens": 3701920} +{"current_steps": 1720, "total_steps": 122600, "loss": 0.3476, "lr": 0.0001402120717781403, "epoch": 0.2805872756933116, "percentage": 1.4, "elapsed_time": "0:10:10", "remaining_time": "11:54:45", "throughput": 6082.46, "total_tokens": 3711648} +{"current_steps": 1725, "total_steps": 122600, "loss": 0.1822, "lr": 0.00014061990212071778, "epoch": 0.2814029363784666, "percentage": 1.41, "elapsed_time": "0:10:11", "remaining_time": "11:54:33", "throughput": 6082.08, "total_tokens": 3721312} +{"current_steps": 1730, "total_steps": 122600, "loss": 0.1454, "lr": 0.0001410277324632953, "epoch": 0.2822185970636215, "percentage": 1.41, "elapsed_time": "0:10:13", "remaining_time": "11:54:32", "throughput": 6082.15, "total_tokens": 3732192} +{"current_steps": 1735, "total_steps": 122600, "loss": 0.2084, "lr": 0.00014143556280587274, "epoch": 0.2830342577487765, "percentage": 1.42, "elapsed_time": "0:10:15", "remaining_time": "11:54:25", "throughput": 6081.92, "total_tokens": 3742368} +{"current_steps": 1740, "total_steps": 122600, "loss": 0.2289, "lr": 0.00014184339314845024, "epoch": 0.2838499184339315, "percentage": 1.42, "elapsed_time": "0:10:17", "remaining_time": "11:54:28", "throughput": 6081.8, "total_tokens": 3753536} +{"current_steps": 1745, "total_steps": 122600, "loss": 0.0779, "lr": 0.00014225122349102774, "epoch": 0.28466557911908646, "percentage": 1.42, "elapsed_time": "0:10:19", "remaining_time": "11:54:34", "throughput": 6081.75, "total_tokens": 3764960} +{"current_steps": 1750, "total_steps": 122600, "loss": 0.0627, "lr": 0.00014265905383360522, "epoch": 0.28548123980424145, "percentage": 1.43, "elapsed_time": "0:10:20", "remaining_time": "11:54:37", "throughput": 6081.9, "total_tokens": 3776224} +{"current_steps": 1755, "total_steps": 122600, "loss": 0.3102, "lr": 0.00014306688417618272, "epoch": 0.28629690048939643, "percentage": 1.43, "elapsed_time": "0:10:22", "remaining_time": "11:54:26", "throughput": 6081.94, "total_tokens": 3786208} +{"current_steps": 1760, "total_steps": 122600, "loss": 0.1619, "lr": 0.0001434747145187602, "epoch": 0.28711256117455136, "percentage": 1.44, "elapsed_time": "0:10:24", "remaining_time": "11:54:22", "throughput": 6081.77, "total_tokens": 3796768} +{"current_steps": 1765, "total_steps": 122600, "loss": 0.1974, "lr": 0.0001438825448613377, "epoch": 0.28792822185970635, "percentage": 1.44, "elapsed_time": "0:10:26", "remaining_time": "11:54:32", "throughput": 6082.29, "total_tokens": 3808928} +{"current_steps": 1770, "total_steps": 122600, "loss": 0.2318, "lr": 0.00014429037520391515, "epoch": 0.28874388254486133, "percentage": 1.44, "elapsed_time": "0:10:28", "remaining_time": "11:54:39", "throughput": 6082.33, "total_tokens": 3820480} +{"current_steps": 1775, "total_steps": 122600, "loss": 0.1204, "lr": 0.00014469820554649266, "epoch": 0.2895595432300163, "percentage": 1.45, "elapsed_time": "0:10:30", "remaining_time": "11:54:49", "throughput": 6082.4, "total_tokens": 3832352} +{"current_steps": 1780, "total_steps": 122600, "loss": 0.1203, "lr": 0.00014510603588907016, "epoch": 0.2903752039151713, "percentage": 1.45, "elapsed_time": "0:10:31", "remaining_time": "11:54:41", "throughput": 6082.28, "total_tokens": 3842560} +{"current_steps": 1785, "total_steps": 122600, "loss": 0.3127, "lr": 0.00014551386623164764, "epoch": 0.2911908646003263, "percentage": 1.46, "elapsed_time": "0:10:33", "remaining_time": "11:54:44", "throughput": 6082.36, "total_tokens": 3853824} +{"current_steps": 1790, "total_steps": 122600, "loss": 0.1092, "lr": 0.00014592169657422514, "epoch": 0.29200652528548127, "percentage": 1.46, "elapsed_time": "0:10:35", "remaining_time": "11:54:49", "throughput": 6082.47, "total_tokens": 3865280} +{"current_steps": 1795, "total_steps": 122600, "loss": 0.1014, "lr": 0.00014632952691680262, "epoch": 0.2928221859706362, "percentage": 1.46, "elapsed_time": "0:10:37", "remaining_time": "11:54:35", "throughput": 6082.4, "total_tokens": 3874944} +{"current_steps": 1800, "total_steps": 122600, "loss": 0.125, "lr": 0.0001467373572593801, "epoch": 0.2936378466557912, "percentage": 1.47, "elapsed_time": "0:10:38", "remaining_time": "11:54:34", "throughput": 6082.46, "total_tokens": 3885824} +{"current_steps": 1805, "total_steps": 122600, "loss": 0.2931, "lr": 0.00014714518760195757, "epoch": 0.29445350734094616, "percentage": 1.47, "elapsed_time": "0:10:40", "remaining_time": "11:54:31", "throughput": 6082.37, "total_tokens": 3896480} +{"current_steps": 1810, "total_steps": 122600, "loss": 0.2474, "lr": 0.00014755301794453507, "epoch": 0.29526916802610115, "percentage": 1.48, "elapsed_time": "0:10:42", "remaining_time": "11:54:40", "throughput": 6082.45, "total_tokens": 3908256} +{"current_steps": 1815, "total_steps": 122600, "loss": 0.0975, "lr": 0.00014796084828711258, "epoch": 0.29608482871125613, "percentage": 1.48, "elapsed_time": "0:10:44", "remaining_time": "11:54:42", "throughput": 6082.69, "total_tokens": 3919584} +{"current_steps": 1820, "total_steps": 122600, "loss": 0.1539, "lr": 0.00014836867862969005, "epoch": 0.2969004893964111, "percentage": 1.48, "elapsed_time": "0:10:46", "remaining_time": "11:54:38", "throughput": 6082.39, "total_tokens": 3930016} +{"current_steps": 1825, "total_steps": 122600, "loss": 0.0723, "lr": 0.00014877650897226756, "epoch": 0.29771615008156604, "percentage": 1.49, "elapsed_time": "0:10:47", "remaining_time": "11:54:37", "throughput": 6082.37, "total_tokens": 3940800} +{"current_steps": 1830, "total_steps": 122600, "loss": 0.0975, "lr": 0.00014918433931484503, "epoch": 0.29853181076672103, "percentage": 1.49, "elapsed_time": "0:10:49", "remaining_time": "11:54:41", "throughput": 6082.47, "total_tokens": 3952192} +{"current_steps": 1835, "total_steps": 122600, "loss": 0.0374, "lr": 0.0001495921696574225, "epoch": 0.299347471451876, "percentage": 1.5, "elapsed_time": "0:10:51", "remaining_time": "11:54:48", "throughput": 6082.56, "total_tokens": 3963936} +{"current_steps": 1840, "total_steps": 122600, "loss": 0.145, "lr": 0.00015, "epoch": 0.300163132137031, "percentage": 1.5, "elapsed_time": "0:10:53", "remaining_time": "11:54:37", "throughput": 6082.59, "total_tokens": 3973824} +{"current_steps": 1845, "total_steps": 122600, "loss": 0.0033, "lr": 0.0001504078303425775, "epoch": 0.300978792822186, "percentage": 1.5, "elapsed_time": "0:10:55", "remaining_time": "11:54:34", "throughput": 6082.64, "total_tokens": 3984576} +{"current_steps": 1850, "total_steps": 122600, "loss": 0.0119, "lr": 0.000150815660685155, "epoch": 0.30179445350734097, "percentage": 1.51, "elapsed_time": "0:10:57", "remaining_time": "11:54:46", "throughput": 6083.14, "total_tokens": 3997024} +{"current_steps": 1855, "total_steps": 122600, "loss": 0.1895, "lr": 0.00015122349102773247, "epoch": 0.30261011419249595, "percentage": 1.51, "elapsed_time": "0:10:58", "remaining_time": "11:54:45", "throughput": 6083.12, "total_tokens": 4007808} +{"current_steps": 1860, "total_steps": 122600, "loss": 0.188, "lr": 0.00015163132137030997, "epoch": 0.3034257748776509, "percentage": 1.52, "elapsed_time": "0:11:00", "remaining_time": "11:54:45", "throughput": 6083.32, "total_tokens": 4018944} +{"current_steps": 1865, "total_steps": 122600, "loss": 0.6462, "lr": 0.00015203915171288742, "epoch": 0.30424143556280586, "percentage": 1.52, "elapsed_time": "0:11:02", "remaining_time": "11:54:43", "throughput": 6083.4, "total_tokens": 4029824} +{"current_steps": 1870, "total_steps": 122600, "loss": 0.3281, "lr": 0.00015244698205546493, "epoch": 0.30505709624796085, "percentage": 1.53, "elapsed_time": "0:11:04", "remaining_time": "11:54:44", "throughput": 6083.28, "total_tokens": 4040800} +{"current_steps": 1875, "total_steps": 122600, "loss": 0.2342, "lr": 0.0001528548123980424, "epoch": 0.30587275693311583, "percentage": 1.53, "elapsed_time": "0:11:05", "remaining_time": "11:54:36", "throughput": 6083.15, "total_tokens": 4050912} +{"current_steps": 1880, "total_steps": 122600, "loss": 0.1647, "lr": 0.0001532626427406199, "epoch": 0.3066884176182708, "percentage": 1.53, "elapsed_time": "0:11:07", "remaining_time": "11:54:33", "throughput": 6083.31, "total_tokens": 4061696} +{"current_steps": 1885, "total_steps": 122600, "loss": 0.2302, "lr": 0.0001536704730831974, "epoch": 0.3075040783034258, "percentage": 1.54, "elapsed_time": "0:11:09", "remaining_time": "11:54:18", "throughput": 6083.33, "total_tokens": 4071264} +{"current_steps": 1890, "total_steps": 122600, "loss": 0.1746, "lr": 0.0001540783034257749, "epoch": 0.3083197389885807, "percentage": 1.54, "elapsed_time": "0:11:10", "remaining_time": "11:54:08", "throughput": 6083.2, "total_tokens": 4081152} +{"current_steps": 1895, "total_steps": 122600, "loss": 0.1498, "lr": 0.00015448613376835236, "epoch": 0.3091353996737357, "percentage": 1.55, "elapsed_time": "0:11:12", "remaining_time": "11:54:04", "throughput": 6082.98, "total_tokens": 4091584} +{"current_steps": 1900, "total_steps": 122600, "loss": 0.0782, "lr": 0.00015489396411092984, "epoch": 0.3099510603588907, "percentage": 1.55, "elapsed_time": "0:11:14", "remaining_time": "11:54:02", "throughput": 6083.29, "total_tokens": 4102560} +{"current_steps": 1905, "total_steps": 122600, "loss": 0.1151, "lr": 0.00015530179445350734, "epoch": 0.3107667210440457, "percentage": 1.55, "elapsed_time": "0:11:16", "remaining_time": "11:54:06", "throughput": 6083.3, "total_tokens": 4113920} +{"current_steps": 1910, "total_steps": 122600, "loss": 0.1237, "lr": 0.00015570962479608482, "epoch": 0.31158238172920066, "percentage": 1.56, "elapsed_time": "0:11:18", "remaining_time": "11:54:11", "throughput": 6083.43, "total_tokens": 4125472} +{"current_steps": 1915, "total_steps": 122600, "loss": 0.2935, "lr": 0.00015611745513866232, "epoch": 0.31239804241435565, "percentage": 1.56, "elapsed_time": "0:11:19", "remaining_time": "11:54:05", "throughput": 6083.62, "total_tokens": 4136032} +{"current_steps": 1920, "total_steps": 122600, "loss": 0.0692, "lr": 0.00015652528548123983, "epoch": 0.3132137030995106, "percentage": 1.57, "elapsed_time": "0:11:21", "remaining_time": "11:53:53", "throughput": 6083.53, "total_tokens": 4145792} +{"current_steps": 1925, "total_steps": 122600, "loss": 0.2522, "lr": 0.0001569331158238173, "epoch": 0.31402936378466556, "percentage": 1.57, "elapsed_time": "0:11:23", "remaining_time": "11:53:54", "throughput": 6083.51, "total_tokens": 4156832} +{"current_steps": 1930, "total_steps": 122600, "loss": 0.1961, "lr": 0.00015734094616639478, "epoch": 0.31484502446982054, "percentage": 1.57, "elapsed_time": "0:11:25", "remaining_time": "11:53:50", "throughput": 6083.5, "total_tokens": 4167424} +{"current_steps": 1935, "total_steps": 122600, "loss": 0.0822, "lr": 0.00015774877650897226, "epoch": 0.31566068515497553, "percentage": 1.58, "elapsed_time": "0:11:26", "remaining_time": "11:53:40", "throughput": 6083.24, "total_tokens": 4177248} +{"current_steps": 1940, "total_steps": 122600, "loss": 0.1321, "lr": 0.00015815660685154976, "epoch": 0.3164763458401305, "percentage": 1.58, "elapsed_time": "0:11:28", "remaining_time": "11:53:39", "throughput": 6083.18, "total_tokens": 4188064} +{"current_steps": 1945, "total_steps": 122600, "loss": 0.0615, "lr": 0.00015856443719412724, "epoch": 0.3172920065252855, "percentage": 1.59, "elapsed_time": "0:11:30", "remaining_time": "11:53:31", "throughput": 6083.04, "total_tokens": 4198144} +{"current_steps": 1950, "total_steps": 122600, "loss": 0.1123, "lr": 0.00015897226753670474, "epoch": 0.3181076672104405, "percentage": 1.59, "elapsed_time": "0:11:32", "remaining_time": "11:53:39", "throughput": 6083.19, "total_tokens": 4209952} +{"current_steps": 1955, "total_steps": 122600, "loss": 0.025, "lr": 0.00015938009787928224, "epoch": 0.3189233278955954, "percentage": 1.59, "elapsed_time": "0:11:33", "remaining_time": "11:53:25", "throughput": 6082.93, "total_tokens": 4219360} +{"current_steps": 1960, "total_steps": 122600, "loss": 0.2129, "lr": 0.0001597879282218597, "epoch": 0.3197389885807504, "percentage": 1.6, "elapsed_time": "0:11:35", "remaining_time": "11:53:23", "throughput": 6082.85, "total_tokens": 4230080} +{"current_steps": 1965, "total_steps": 122600, "loss": 0.1465, "lr": 0.0001601957585644372, "epoch": 0.3205546492659054, "percentage": 1.6, "elapsed_time": "0:11:37", "remaining_time": "11:53:20", "throughput": 6082.8, "total_tokens": 4240768} +{"current_steps": 1970, "total_steps": 122600, "loss": 0.3903, "lr": 0.00016060358890701467, "epoch": 0.32137030995106036, "percentage": 1.61, "elapsed_time": "0:11:39", "remaining_time": "11:53:24", "throughput": 6082.98, "total_tokens": 4252224} +{"current_steps": 1975, "total_steps": 122600, "loss": 0.1853, "lr": 0.00016101141924959218, "epoch": 0.32218597063621535, "percentage": 1.61, "elapsed_time": "0:11:40", "remaining_time": "11:53:32", "throughput": 6083.25, "total_tokens": 4264160} +{"current_steps": 1980, "total_steps": 122600, "loss": 0.2022, "lr": 0.00016141924959216965, "epoch": 0.32300163132137033, "percentage": 1.62, "elapsed_time": "0:11:42", "remaining_time": "11:53:26", "throughput": 6082.95, "total_tokens": 4274368} +{"current_steps": 1985, "total_steps": 122600, "loss": 0.1015, "lr": 0.00016182707993474716, "epoch": 0.32381729200652526, "percentage": 1.62, "elapsed_time": "0:11:44", "remaining_time": "11:53:14", "throughput": 6082.63, "total_tokens": 4283936} +{"current_steps": 1990, "total_steps": 122600, "loss": 0.1015, "lr": 0.00016223491027732466, "epoch": 0.32463295269168024, "percentage": 1.62, "elapsed_time": "0:11:46", "remaining_time": "11:53:10", "throughput": 6082.44, "total_tokens": 4294368} +{"current_steps": 1995, "total_steps": 122600, "loss": 0.0639, "lr": 0.0001626427406199021, "epoch": 0.3254486133768352, "percentage": 1.63, "elapsed_time": "0:11:47", "remaining_time": "11:52:53", "throughput": 6082.09, "total_tokens": 4303328} +{"current_steps": 2000, "total_steps": 122600, "loss": 0.1864, "lr": 0.0001630505709624796, "epoch": 0.3262642740619902, "percentage": 1.63, "elapsed_time": "0:11:49", "remaining_time": "11:52:58", "throughput": 6082.48, "total_tokens": 4315072} +{"current_steps": 2005, "total_steps": 122600, "loss": 0.0466, "lr": 0.0001634584013050571, "epoch": 0.3270799347471452, "percentage": 1.64, "elapsed_time": "0:11:51", "remaining_time": "11:53:04", "throughput": 6082.68, "total_tokens": 4326816} +{"current_steps": 2010, "total_steps": 122600, "loss": 0.0934, "lr": 0.0001638662316476346, "epoch": 0.3278955954323002, "percentage": 1.64, "elapsed_time": "0:11:52", "remaining_time": "11:52:56", "throughput": 6082.62, "total_tokens": 4336896} +{"current_steps": 2015, "total_steps": 122600, "loss": 0.0852, "lr": 0.00016427406199021207, "epoch": 0.32871125611745516, "percentage": 1.64, "elapsed_time": "0:11:54", "remaining_time": "11:52:51", "throughput": 6082.5, "total_tokens": 4347328} +{"current_steps": 2020, "total_steps": 122600, "loss": 0.1983, "lr": 0.00016468189233278957, "epoch": 0.3295269168026101, "percentage": 1.65, "elapsed_time": "0:11:56", "remaining_time": "11:52:51", "throughput": 6082.43, "total_tokens": 4358208} +{"current_steps": 2025, "total_steps": 122600, "loss": 0.1892, "lr": 0.00016508972267536705, "epoch": 0.3303425774877651, "percentage": 1.65, "elapsed_time": "0:11:58", "remaining_time": "11:52:46", "throughput": 6082.44, "total_tokens": 4368672} +{"current_steps": 2030, "total_steps": 122600, "loss": 0.1723, "lr": 0.00016549755301794453, "epoch": 0.33115823817292006, "percentage": 1.66, "elapsed_time": "0:12:00", "remaining_time": "11:52:48", "throughput": 6082.43, "total_tokens": 4379808} +{"current_steps": 2035, "total_steps": 122600, "loss": 0.1136, "lr": 0.00016590538336052203, "epoch": 0.33197389885807504, "percentage": 1.66, "elapsed_time": "0:12:01", "remaining_time": "11:52:40", "throughput": 6082.08, "total_tokens": 4389728} +{"current_steps": 2040, "total_steps": 122600, "loss": 0.0093, "lr": 0.0001663132137030995, "epoch": 0.33278955954323003, "percentage": 1.66, "elapsed_time": "0:12:03", "remaining_time": "11:52:41", "throughput": 6081.96, "total_tokens": 4400704} +{"current_steps": 2045, "total_steps": 122600, "loss": 0.2122, "lr": 0.000166721044045677, "epoch": 0.333605220228385, "percentage": 1.67, "elapsed_time": "0:12:05", "remaining_time": "11:52:41", "throughput": 6081.87, "total_tokens": 4411648} +{"current_steps": 2050, "total_steps": 122600, "loss": 0.1275, "lr": 0.00016712887438825449, "epoch": 0.33442088091353994, "percentage": 1.67, "elapsed_time": "0:12:07", "remaining_time": "11:52:47", "throughput": 6082.01, "total_tokens": 4423328} +{"current_steps": 2055, "total_steps": 122600, "loss": 0.3971, "lr": 0.000167536704730832, "epoch": 0.3352365415986949, "percentage": 1.68, "elapsed_time": "0:12:09", "remaining_time": "11:52:49", "throughput": 6081.77, "total_tokens": 4434336} +{"current_steps": 2060, "total_steps": 122600, "loss": 0.1908, "lr": 0.00016794453507340947, "epoch": 0.3360522022838499, "percentage": 1.68, "elapsed_time": "0:12:10", "remaining_time": "11:52:44", "throughput": 6081.66, "total_tokens": 4444672} +{"current_steps": 2065, "total_steps": 122600, "loss": 0.0652, "lr": 0.00016835236541598694, "epoch": 0.3368678629690049, "percentage": 1.68, "elapsed_time": "0:12:12", "remaining_time": "11:52:46", "throughput": 6081.72, "total_tokens": 4455872} +{"current_steps": 2070, "total_steps": 122600, "loss": 0.129, "lr": 0.00016876019575856445, "epoch": 0.3376835236541599, "percentage": 1.69, "elapsed_time": "0:12:14", "remaining_time": "11:52:53", "throughput": 6081.75, "total_tokens": 4467616} +{"current_steps": 2075, "total_steps": 122600, "loss": 0.143, "lr": 0.00016916802610114192, "epoch": 0.33849918433931486, "percentage": 1.69, "elapsed_time": "0:12:16", "remaining_time": "11:52:54", "throughput": 6081.66, "total_tokens": 4478656} +{"current_steps": 2080, "total_steps": 122600, "loss": 0.0389, "lr": 0.00016957585644371943, "epoch": 0.33931484502446985, "percentage": 1.7, "elapsed_time": "0:12:18", "remaining_time": "11:52:48", "throughput": 6081.41, "total_tokens": 4488800} +{"current_steps": 2085, "total_steps": 122600, "loss": 0.0959, "lr": 0.0001699836867862969, "epoch": 0.3401305057096248, "percentage": 1.7, "elapsed_time": "0:12:19", "remaining_time": "11:52:37", "throughput": 6081.19, "total_tokens": 4498496} +{"current_steps": 2090, "total_steps": 122600, "loss": 0.2579, "lr": 0.00017039151712887438, "epoch": 0.34094616639477976, "percentage": 1.7, "elapsed_time": "0:12:21", "remaining_time": "11:52:34", "throughput": 6081.16, "total_tokens": 4509152} +{"current_steps": 2095, "total_steps": 122600, "loss": 0.0914, "lr": 0.00017079934747145188, "epoch": 0.34176182707993474, "percentage": 1.71, "elapsed_time": "0:12:23", "remaining_time": "11:52:42", "throughput": 6081.35, "total_tokens": 4521120} +{"current_steps": 2100, "total_steps": 122600, "loss": 0.1256, "lr": 0.00017120717781402936, "epoch": 0.3425774877650897, "percentage": 1.71, "elapsed_time": "0:12:25", "remaining_time": "11:52:39", "throughput": 6081.31, "total_tokens": 4531744} +{"current_steps": 2105, "total_steps": 122600, "loss": 0.2788, "lr": 0.00017161500815660686, "epoch": 0.3433931484502447, "percentage": 1.72, "elapsed_time": "0:12:26", "remaining_time": "11:52:22", "throughput": 6081.1, "total_tokens": 4540704} +{"current_steps": 2110, "total_steps": 122600, "loss": 0.1521, "lr": 0.00017202283849918434, "epoch": 0.3442088091353997, "percentage": 1.72, "elapsed_time": "0:12:28", "remaining_time": "11:52:20", "throughput": 6081.18, "total_tokens": 4551552} +{"current_steps": 2115, "total_steps": 122600, "loss": 0.2539, "lr": 0.00017243066884176184, "epoch": 0.3450244698205546, "percentage": 1.73, "elapsed_time": "0:12:30", "remaining_time": "11:52:24", "throughput": 6081.15, "total_tokens": 4562976} +{"current_steps": 2120, "total_steps": 122600, "loss": 0.1712, "lr": 0.00017283849918433932, "epoch": 0.3458401305057096, "percentage": 1.73, "elapsed_time": "0:12:32", "remaining_time": "11:52:23", "throughput": 6081.36, "total_tokens": 4573920} +{"current_steps": 2125, "total_steps": 122600, "loss": 0.2538, "lr": 0.0001732463295269168, "epoch": 0.3466557911908646, "percentage": 1.73, "elapsed_time": "0:12:33", "remaining_time": "11:52:25", "throughput": 6081.3, "total_tokens": 4585088} +{"current_steps": 2130, "total_steps": 122600, "loss": 0.1483, "lr": 0.0001736541598694943, "epoch": 0.3474714518760196, "percentage": 1.74, "elapsed_time": "0:12:35", "remaining_time": "11:52:13", "throughput": 6081.2, "total_tokens": 4594752} +{"current_steps": 2135, "total_steps": 122600, "loss": 0.1508, "lr": 0.00017406199021207178, "epoch": 0.34828711256117456, "percentage": 1.74, "elapsed_time": "0:12:37", "remaining_time": "11:52:03", "throughput": 6081.0, "total_tokens": 4604512} +{"current_steps": 2140, "total_steps": 122600, "loss": 0.0691, "lr": 0.00017446982055464928, "epoch": 0.34910277324632955, "percentage": 1.75, "elapsed_time": "0:12:39", "remaining_time": "11:52:04", "throughput": 6081.04, "total_tokens": 4615616} +{"current_steps": 2145, "total_steps": 122600, "loss": 0.2726, "lr": 0.00017487765089722676, "epoch": 0.34991843393148453, "percentage": 1.75, "elapsed_time": "0:12:40", "remaining_time": "11:52:00", "throughput": 6080.82, "total_tokens": 4625984} +{"current_steps": 2150, "total_steps": 122600, "loss": 0.1277, "lr": 0.00017528548123980426, "epoch": 0.35073409461663946, "percentage": 1.75, "elapsed_time": "0:12:42", "remaining_time": "11:52:02", "throughput": 6080.62, "total_tokens": 4636992} +{"current_steps": 2155, "total_steps": 122600, "loss": 0.0274, "lr": 0.0001756933115823817, "epoch": 0.35154975530179444, "percentage": 1.76, "elapsed_time": "0:12:44", "remaining_time": "11:51:57", "throughput": 6080.58, "total_tokens": 4647424} +{"current_steps": 2160, "total_steps": 122600, "loss": 0.1646, "lr": 0.0001761011419249592, "epoch": 0.3523654159869494, "percentage": 1.76, "elapsed_time": "0:12:46", "remaining_time": "11:52:03", "throughput": 6080.96, "total_tokens": 4659360} +{"current_steps": 2165, "total_steps": 122600, "loss": 0.1761, "lr": 0.00017650897226753672, "epoch": 0.3531810766721044, "percentage": 1.77, "elapsed_time": "0:12:47", "remaining_time": "11:51:54", "throughput": 6080.87, "total_tokens": 4669248} +{"current_steps": 2170, "total_steps": 122600, "loss": 0.0855, "lr": 0.0001769168026101142, "epoch": 0.3539967373572594, "percentage": 1.77, "elapsed_time": "0:12:49", "remaining_time": "11:51:47", "throughput": 6080.74, "total_tokens": 4679360} +{"current_steps": 2175, "total_steps": 122600, "loss": 0.3686, "lr": 0.0001773246329526917, "epoch": 0.3548123980424144, "percentage": 1.77, "elapsed_time": "0:12:51", "remaining_time": "11:51:52", "throughput": 6080.98, "total_tokens": 4691104} +{"current_steps": 2180, "total_steps": 122600, "loss": 0.1182, "lr": 0.00017773246329526917, "epoch": 0.3556280587275693, "percentage": 1.78, "elapsed_time": "0:12:52", "remaining_time": "11:51:38", "throughput": 6080.82, "total_tokens": 4700416} +{"current_steps": 2185, "total_steps": 122600, "loss": 0.3337, "lr": 0.00017814029363784668, "epoch": 0.3564437194127243, "percentage": 1.78, "elapsed_time": "0:12:54", "remaining_time": "11:51:37", "throughput": 6080.67, "total_tokens": 4711072} +{"current_steps": 2190, "total_steps": 122600, "loss": 0.2498, "lr": 0.00017854812398042412, "epoch": 0.3572593800978793, "percentage": 1.79, "elapsed_time": "0:12:56", "remaining_time": "11:51:39", "throughput": 6080.83, "total_tokens": 4722496} +{"current_steps": 2195, "total_steps": 122600, "loss": 0.1047, "lr": 0.00017895595432300163, "epoch": 0.35807504078303426, "percentage": 1.79, "elapsed_time": "0:12:58", "remaining_time": "11:51:17", "throughput": 6080.63, "total_tokens": 4730784} +{"current_steps": 2200, "total_steps": 122600, "loss": 0.1373, "lr": 0.00017936378466557913, "epoch": 0.35889070146818924, "percentage": 1.79, "elapsed_time": "0:12:59", "remaining_time": "11:51:09", "throughput": 6080.58, "total_tokens": 4740896} +{"current_steps": 2205, "total_steps": 122600, "loss": 0.1279, "lr": 0.0001797716150081566, "epoch": 0.35970636215334423, "percentage": 1.8, "elapsed_time": "0:13:01", "remaining_time": "11:51:14", "throughput": 6080.68, "total_tokens": 4752448} +{"current_steps": 2210, "total_steps": 122600, "loss": 0.1135, "lr": 0.0001801794453507341, "epoch": 0.3605220228384992, "percentage": 1.8, "elapsed_time": "0:13:03", "remaining_time": "11:51:18", "throughput": 6080.7, "total_tokens": 4763904} +{"current_steps": 2215, "total_steps": 122600, "loss": 0.092, "lr": 0.0001805872756933116, "epoch": 0.36133768352365414, "percentage": 1.81, "elapsed_time": "0:13:05", "remaining_time": "11:51:09", "throughput": 6080.79, "total_tokens": 4773952} +{"current_steps": 2220, "total_steps": 122600, "loss": 0.1956, "lr": 0.00018099510603588906, "epoch": 0.3621533442088091, "percentage": 1.81, "elapsed_time": "0:13:06", "remaining_time": "11:51:07", "throughput": 6080.81, "total_tokens": 4784672} +{"current_steps": 2225, "total_steps": 122600, "loss": 0.1935, "lr": 0.00018140293637846654, "epoch": 0.3629690048939641, "percentage": 1.81, "elapsed_time": "0:13:08", "remaining_time": "11:51:12", "throughput": 6081.07, "total_tokens": 4796480} +{"current_steps": 2230, "total_steps": 122600, "loss": 0.2541, "lr": 0.00018181076672104404, "epoch": 0.3637846655791191, "percentage": 1.82, "elapsed_time": "0:13:10", "remaining_time": "11:51:11", "throughput": 6081.06, "total_tokens": 4807328} +{"current_steps": 2235, "total_steps": 122600, "loss": 0.1581, "lr": 0.00018221859706362155, "epoch": 0.3646003262642741, "percentage": 1.82, "elapsed_time": "0:13:12", "remaining_time": "11:51:15", "throughput": 6081.24, "total_tokens": 4818848} +{"current_steps": 2240, "total_steps": 122600, "loss": 0.1676, "lr": 0.00018262642740619902, "epoch": 0.36541598694942906, "percentage": 1.83, "elapsed_time": "0:13:14", "remaining_time": "11:51:09", "throughput": 6080.98, "total_tokens": 4829024} +{"current_steps": 2245, "total_steps": 122600, "loss": 0.1468, "lr": 0.00018303425774877653, "epoch": 0.366231647634584, "percentage": 1.83, "elapsed_time": "0:13:15", "remaining_time": "11:51:08", "throughput": 6081.1, "total_tokens": 4839936} +{"current_steps": 2250, "total_steps": 122600, "loss": 0.2178, "lr": 0.00018344208809135398, "epoch": 0.367047308319739, "percentage": 1.84, "elapsed_time": "0:13:17", "remaining_time": "11:51:12", "throughput": 6081.1, "total_tokens": 4851424} +{"current_steps": 2255, "total_steps": 122600, "loss": 0.1108, "lr": 0.00018384991843393148, "epoch": 0.36786296900489396, "percentage": 1.84, "elapsed_time": "0:13:19", "remaining_time": "11:51:07", "throughput": 6081.14, "total_tokens": 4861888} +{"current_steps": 2260, "total_steps": 122600, "loss": 0.0889, "lr": 0.00018425774877650896, "epoch": 0.36867862969004894, "percentage": 1.84, "elapsed_time": "0:13:21", "remaining_time": "11:50:53", "throughput": 6080.97, "total_tokens": 4871136} +{"current_steps": 2265, "total_steps": 122600, "loss": 0.0765, "lr": 0.00018466557911908646, "epoch": 0.3694942903752039, "percentage": 1.85, "elapsed_time": "0:13:22", "remaining_time": "11:50:59", "throughput": 6081.18, "total_tokens": 4882976} +{"current_steps": 2270, "total_steps": 122600, "loss": 0.0865, "lr": 0.00018507340946166396, "epoch": 0.3703099510603589, "percentage": 1.85, "elapsed_time": "0:13:24", "remaining_time": "11:50:56", "throughput": 6081.19, "total_tokens": 4893536} +{"current_steps": 2275, "total_steps": 122600, "loss": 0.2369, "lr": 0.00018548123980424144, "epoch": 0.37112561174551384, "percentage": 1.86, "elapsed_time": "0:13:26", "remaining_time": "11:50:54", "throughput": 6081.2, "total_tokens": 4904384} +{"current_steps": 2280, "total_steps": 122600, "loss": 0.2179, "lr": 0.00018588907014681894, "epoch": 0.3719412724306688, "percentage": 1.86, "elapsed_time": "0:13:28", "remaining_time": "11:50:50", "throughput": 6081.35, "total_tokens": 4915008} +{"current_steps": 2285, "total_steps": 122600, "loss": 0.081, "lr": 0.0001862969004893964, "epoch": 0.3727569331158238, "percentage": 1.86, "elapsed_time": "0:13:29", "remaining_time": "11:50:48", "throughput": 6081.25, "total_tokens": 4925632} +{"current_steps": 2290, "total_steps": 122600, "loss": 0.0769, "lr": 0.0001867047308319739, "epoch": 0.3735725938009788, "percentage": 1.87, "elapsed_time": "0:13:31", "remaining_time": "11:50:45", "throughput": 6081.25, "total_tokens": 4936224} +{"current_steps": 2295, "total_steps": 122600, "loss": 0.1736, "lr": 0.0001871125611745514, "epoch": 0.3743882544861338, "percentage": 1.87, "elapsed_time": "0:13:33", "remaining_time": "11:50:43", "throughput": 6081.35, "total_tokens": 4947072} +{"current_steps": 2300, "total_steps": 122600, "loss": 0.1318, "lr": 0.00018752039151712888, "epoch": 0.37520391517128876, "percentage": 1.88, "elapsed_time": "0:13:35", "remaining_time": "11:50:34", "throughput": 6081.29, "total_tokens": 4957024} +{"current_steps": 2305, "total_steps": 122600, "loss": 0.0439, "lr": 0.00018792822185970638, "epoch": 0.37601957585644374, "percentage": 1.88, "elapsed_time": "0:13:36", "remaining_time": "11:50:22", "throughput": 6081.18, "total_tokens": 4966528} +{"current_steps": 2310, "total_steps": 122600, "loss": 0.1136, "lr": 0.00018833605220228386, "epoch": 0.3768352365415987, "percentage": 1.88, "elapsed_time": "0:13:38", "remaining_time": "11:50:18", "throughput": 6081.08, "total_tokens": 4976928} +{"current_steps": 2315, "total_steps": 122600, "loss": 0.2085, "lr": 0.00018874388254486133, "epoch": 0.37765089722675366, "percentage": 1.89, "elapsed_time": "0:13:40", "remaining_time": "11:50:14", "throughput": 6080.96, "total_tokens": 4987296} +{"current_steps": 2320, "total_steps": 122600, "loss": 0.0911, "lr": 0.0001891517128874388, "epoch": 0.37846655791190864, "percentage": 1.89, "elapsed_time": "0:13:41", "remaining_time": "11:50:14", "throughput": 6080.93, "total_tokens": 4998336} +{"current_steps": 2325, "total_steps": 122600, "loss": 0.1669, "lr": 0.00018955954323001631, "epoch": 0.3792822185970636, "percentage": 1.9, "elapsed_time": "0:13:43", "remaining_time": "11:50:06", "throughput": 6080.89, "total_tokens": 5008256} +{"current_steps": 2330, "total_steps": 122600, "loss": 0.195, "lr": 0.00018996737357259382, "epoch": 0.3800978792822186, "percentage": 1.9, "elapsed_time": "0:13:45", "remaining_time": "11:50:01", "throughput": 6080.87, "total_tokens": 5018688} +{"current_steps": 2335, "total_steps": 122600, "loss": 0.1354, "lr": 0.0001903752039151713, "epoch": 0.3809135399673736, "percentage": 1.9, "elapsed_time": "0:13:47", "remaining_time": "11:50:03", "throughput": 6080.94, "total_tokens": 5029984} +{"current_steps": 2340, "total_steps": 122600, "loss": 0.0567, "lr": 0.0001907830342577488, "epoch": 0.3817292006525285, "percentage": 1.91, "elapsed_time": "0:13:48", "remaining_time": "11:49:57", "throughput": 6080.91, "total_tokens": 5040160} +{"current_steps": 2345, "total_steps": 122600, "loss": 0.1691, "lr": 0.00019119086460032627, "epoch": 0.3825448613376835, "percentage": 1.91, "elapsed_time": "0:13:50", "remaining_time": "11:50:08", "throughput": 6081.09, "total_tokens": 5052640} +{"current_steps": 2350, "total_steps": 122600, "loss": 0.1856, "lr": 0.00019159869494290375, "epoch": 0.3833605220228385, "percentage": 1.92, "elapsed_time": "0:13:52", "remaining_time": "11:50:07", "throughput": 6081.23, "total_tokens": 5063616} +{"current_steps": 2355, "total_steps": 122600, "loss": 0.1788, "lr": 0.00019200652528548123, "epoch": 0.3841761827079935, "percentage": 1.92, "elapsed_time": "0:13:54", "remaining_time": "11:50:14", "throughput": 6081.37, "total_tokens": 5075584} +{"current_steps": 2360, "total_steps": 122600, "loss": 0.2466, "lr": 0.00019241435562805873, "epoch": 0.38499184339314846, "percentage": 1.92, "elapsed_time": "0:13:56", "remaining_time": "11:50:12", "throughput": 6081.34, "total_tokens": 5086272} +{"current_steps": 2365, "total_steps": 122600, "loss": 0.2486, "lr": 0.00019282218597063623, "epoch": 0.38580750407830344, "percentage": 1.93, "elapsed_time": "0:13:58", "remaining_time": "11:50:21", "throughput": 6081.62, "total_tokens": 5098560} +{"current_steps": 2370, "total_steps": 122600, "loss": 0.1211, "lr": 0.0001932300163132137, "epoch": 0.3866231647634584, "percentage": 1.93, "elapsed_time": "0:14:00", "remaining_time": "11:50:23", "throughput": 6081.58, "total_tokens": 5109792} +{"current_steps": 2375, "total_steps": 122600, "loss": 0.2811, "lr": 0.00019363784665579121, "epoch": 0.38743882544861336, "percentage": 1.94, "elapsed_time": "0:14:01", "remaining_time": "11:50:12", "throughput": 6081.43, "total_tokens": 5119328} +{"current_steps": 2380, "total_steps": 122600, "loss": 0.1733, "lr": 0.00019404567699836866, "epoch": 0.38825448613376834, "percentage": 1.94, "elapsed_time": "0:14:03", "remaining_time": "11:50:07", "throughput": 6081.56, "total_tokens": 5129824} +{"current_steps": 2385, "total_steps": 122600, "loss": 0.2479, "lr": 0.00019445350734094617, "epoch": 0.3890701468189233, "percentage": 1.95, "elapsed_time": "0:14:05", "remaining_time": "11:50:06", "throughput": 6081.66, "total_tokens": 5140800} +{"current_steps": 2390, "total_steps": 122600, "loss": 0.1671, "lr": 0.00019486133768352364, "epoch": 0.3898858075040783, "percentage": 1.95, "elapsed_time": "0:14:07", "remaining_time": "11:50:08", "throughput": 6081.73, "total_tokens": 5152064} +{"current_steps": 2395, "total_steps": 122600, "loss": 0.1038, "lr": 0.00019526916802610115, "epoch": 0.3907014681892333, "percentage": 1.95, "elapsed_time": "0:14:09", "remaining_time": "11:50:16", "throughput": 6082.09, "total_tokens": 5164288} +{"current_steps": 2400, "total_steps": 122600, "loss": 0.0697, "lr": 0.00019567699836867865, "epoch": 0.3915171288743883, "percentage": 1.96, "elapsed_time": "0:14:10", "remaining_time": "11:50:11", "throughput": 6082.13, "total_tokens": 5174784} +{"current_steps": 2405, "total_steps": 122600, "loss": 0.1027, "lr": 0.00019608482871125613, "epoch": 0.3923327895595432, "percentage": 1.96, "elapsed_time": "0:14:12", "remaining_time": "11:50:10", "throughput": 6082.31, "total_tokens": 5185792} +{"current_steps": 2410, "total_steps": 122600, "loss": 0.2045, "lr": 0.00019649265905383363, "epoch": 0.3931484502446982, "percentage": 1.97, "elapsed_time": "0:14:14", "remaining_time": "11:50:11", "throughput": 6082.23, "total_tokens": 5196832} +{"current_steps": 2415, "total_steps": 122600, "loss": 0.3627, "lr": 0.00019690048939641108, "epoch": 0.3939641109298532, "percentage": 1.97, "elapsed_time": "0:14:16", "remaining_time": "11:50:13", "throughput": 6082.48, "total_tokens": 5208288} +{"current_steps": 2420, "total_steps": 122600, "loss": 0.0812, "lr": 0.00019730831973898858, "epoch": 0.39477977161500816, "percentage": 1.97, "elapsed_time": "0:14:18", "remaining_time": "11:50:11", "throughput": 6082.4, "total_tokens": 5219008} +{"current_steps": 2425, "total_steps": 122600, "loss": 0.1785, "lr": 0.00019771615008156606, "epoch": 0.39559543230016314, "percentage": 1.98, "elapsed_time": "0:14:19", "remaining_time": "11:50:13", "throughput": 6082.62, "total_tokens": 5230400} +{"current_steps": 2430, "total_steps": 122600, "loss": 0.1409, "lr": 0.00019812398042414356, "epoch": 0.3964110929853181, "percentage": 1.98, "elapsed_time": "0:14:21", "remaining_time": "11:50:16", "throughput": 6082.81, "total_tokens": 5241920} +{"current_steps": 2435, "total_steps": 122600, "loss": 0.1043, "lr": 0.00019853181076672107, "epoch": 0.3972267536704731, "percentage": 1.99, "elapsed_time": "0:14:23", "remaining_time": "11:50:13", "throughput": 6083.06, "total_tokens": 5252768} +{"current_steps": 2440, "total_steps": 122600, "loss": 0.0898, "lr": 0.00019893964110929854, "epoch": 0.39804241435562804, "percentage": 1.99, "elapsed_time": "0:14:25", "remaining_time": "11:50:13", "throughput": 6083.15, "total_tokens": 5263840} +{"current_steps": 2445, "total_steps": 122600, "loss": 0.2313, "lr": 0.00019934747145187602, "epoch": 0.398858075040783, "percentage": 1.99, "elapsed_time": "0:14:27", "remaining_time": "11:50:11", "throughput": 6083.12, "total_tokens": 5274656} +{"current_steps": 2450, "total_steps": 122600, "loss": 0.0766, "lr": 0.0001997553017944535, "epoch": 0.399673735725938, "percentage": 2.0, "elapsed_time": "0:14:28", "remaining_time": "11:50:09", "throughput": 6083.33, "total_tokens": 5285504} +{"current_steps": 2455, "total_steps": 122600, "loss": 0.2409, "lr": 0.000200163132137031, "epoch": 0.400489396411093, "percentage": 2.0, "elapsed_time": "0:14:30", "remaining_time": "11:50:12", "throughput": 6083.44, "total_tokens": 5297024} +{"current_steps": 2460, "total_steps": 122600, "loss": 0.2762, "lr": 0.00020057096247960848, "epoch": 0.401305057096248, "percentage": 2.01, "elapsed_time": "0:14:32", "remaining_time": "11:50:12", "throughput": 6083.51, "total_tokens": 5308064} +{"current_steps": 2465, "total_steps": 122600, "loss": 0.1081, "lr": 0.00020097879282218598, "epoch": 0.40212071778140296, "percentage": 2.01, "elapsed_time": "0:14:34", "remaining_time": "11:50:10", "throughput": 6083.51, "total_tokens": 5318880} +{"current_steps": 2470, "total_steps": 122600, "loss": 0.1588, "lr": 0.00020138662316476348, "epoch": 0.4029363784665579, "percentage": 2.01, "elapsed_time": "0:14:36", "remaining_time": "11:50:06", "throughput": 6083.53, "total_tokens": 5329440} +{"current_steps": 2475, "total_steps": 122600, "loss": 0.0775, "lr": 0.00020179445350734096, "epoch": 0.40375203915171287, "percentage": 2.02, "elapsed_time": "0:14:37", "remaining_time": "11:50:04", "throughput": 6083.41, "total_tokens": 5340000} +{"current_steps": 2480, "total_steps": 122600, "loss": 0.1216, "lr": 0.00020220228384991844, "epoch": 0.40456769983686786, "percentage": 2.02, "elapsed_time": "0:14:39", "remaining_time": "11:50:03", "throughput": 6083.37, "total_tokens": 5350944} +{"current_steps": 2485, "total_steps": 122600, "loss": 0.257, "lr": 0.0002026101141924959, "epoch": 0.40538336052202284, "percentage": 2.03, "elapsed_time": "0:14:41", "remaining_time": "11:50:04", "throughput": 6083.29, "total_tokens": 5362016} +{"current_steps": 2490, "total_steps": 122600, "loss": 0.1702, "lr": 0.00020301794453507342, "epoch": 0.4061990212071778, "percentage": 2.03, "elapsed_time": "0:14:43", "remaining_time": "11:50:05", "throughput": 6083.24, "total_tokens": 5373024} +{"current_steps": 2495, "total_steps": 122600, "loss": 0.1976, "lr": 0.0002034257748776509, "epoch": 0.4070146818923328, "percentage": 2.04, "elapsed_time": "0:14:45", "remaining_time": "11:50:04", "throughput": 6083.13, "total_tokens": 5383840} +{"current_steps": 2500, "total_steps": 122600, "loss": 0.0945, "lr": 0.0002038336052202284, "epoch": 0.4078303425774878, "percentage": 2.04, "elapsed_time": "0:14:46", "remaining_time": "11:50:02", "throughput": 6083.21, "total_tokens": 5394688} +{"current_steps": 2505, "total_steps": 122600, "loss": 0.0589, "lr": 0.0002042414355628059, "epoch": 0.4086460032626427, "percentage": 2.04, "elapsed_time": "0:14:48", "remaining_time": "11:50:02", "throughput": 6083.31, "total_tokens": 5405760} +{"current_steps": 2510, "total_steps": 122600, "loss": 0.1422, "lr": 0.00020464926590538335, "epoch": 0.4094616639477977, "percentage": 2.05, "elapsed_time": "0:14:50", "remaining_time": "11:50:01", "throughput": 6083.46, "total_tokens": 5416736} +{"current_steps": 2515, "total_steps": 122600, "loss": 0.1631, "lr": 0.00020505709624796085, "epoch": 0.4102773246329527, "percentage": 2.05, "elapsed_time": "0:14:52", "remaining_time": "11:50:04", "throughput": 6083.47, "total_tokens": 5428160} +{"current_steps": 2520, "total_steps": 122600, "loss": 0.0302, "lr": 0.00020546492659053833, "epoch": 0.4110929853181077, "percentage": 2.06, "elapsed_time": "0:14:54", "remaining_time": "11:50:06", "throughput": 6083.57, "total_tokens": 5439616} +{"current_steps": 2525, "total_steps": 122600, "loss": 0.1358, "lr": 0.00020587275693311583, "epoch": 0.41190864600326266, "percentage": 2.06, "elapsed_time": "0:14:55", "remaining_time": "11:50:03", "throughput": 6083.39, "total_tokens": 5450048} +{"current_steps": 2530, "total_steps": 122600, "loss": 0.1655, "lr": 0.0002062805872756933, "epoch": 0.41272430668841764, "percentage": 2.06, "elapsed_time": "0:14:57", "remaining_time": "11:49:59", "throughput": 6083.42, "total_tokens": 5460512} +{"current_steps": 2535, "total_steps": 122600, "loss": 0.1076, "lr": 0.0002066884176182708, "epoch": 0.41353996737357257, "percentage": 2.07, "elapsed_time": "0:14:59", "remaining_time": "11:49:51", "throughput": 6083.33, "total_tokens": 5470496} +{"current_steps": 2540, "total_steps": 122600, "loss": 0.4035, "lr": 0.00020709624796084832, "epoch": 0.41435562805872755, "percentage": 2.07, "elapsed_time": "0:15:01", "remaining_time": "11:49:54", "throughput": 6083.58, "total_tokens": 5482112} +{"current_steps": 2545, "total_steps": 122600, "loss": 0.0887, "lr": 0.00020750407830342577, "epoch": 0.41517128874388254, "percentage": 2.08, "elapsed_time": "0:15:03", "remaining_time": "11:49:59", "throughput": 6083.8, "total_tokens": 5493984} +{"current_steps": 2550, "total_steps": 122600, "loss": 0.0843, "lr": 0.00020791190864600327, "epoch": 0.4159869494290375, "percentage": 2.08, "elapsed_time": "0:15:04", "remaining_time": "11:50:01", "throughput": 6083.97, "total_tokens": 5505440} +{"current_steps": 2555, "total_steps": 122600, "loss": 0.1324, "lr": 0.00020831973898858075, "epoch": 0.4168026101141925, "percentage": 2.08, "elapsed_time": "0:15:06", "remaining_time": "11:50:03", "throughput": 6084.09, "total_tokens": 5516800} +{"current_steps": 2560, "total_steps": 122600, "loss": 0.0315, "lr": 0.00020872756933115825, "epoch": 0.4176182707993475, "percentage": 2.09, "elapsed_time": "0:15:08", "remaining_time": "11:49:59", "throughput": 6084.08, "total_tokens": 5527360} +{"current_steps": 2565, "total_steps": 122600, "loss": 0.1176, "lr": 0.00020913539967373573, "epoch": 0.4184339314845024, "percentage": 2.09, "elapsed_time": "0:15:10", "remaining_time": "11:49:55", "throughput": 6084.12, "total_tokens": 5537792} +{"current_steps": 2570, "total_steps": 122600, "loss": 0.269, "lr": 0.00020954323001631323, "epoch": 0.4192495921696574, "percentage": 2.1, "elapsed_time": "0:15:12", "remaining_time": "11:49:55", "throughput": 6084.16, "total_tokens": 5548864} +{"current_steps": 2575, "total_steps": 122600, "loss": 0.0807, "lr": 0.0002099510603588907, "epoch": 0.4200652528548124, "percentage": 2.1, "elapsed_time": "0:15:13", "remaining_time": "11:49:49", "throughput": 6084.12, "total_tokens": 5559072} +{"current_steps": 2580, "total_steps": 122600, "loss": 0.2578, "lr": 0.00021035889070146818, "epoch": 0.42088091353996737, "percentage": 2.1, "elapsed_time": "0:15:15", "remaining_time": "11:49:40", "throughput": 6084.01, "total_tokens": 5568864} +{"current_steps": 2585, "total_steps": 122600, "loss": 0.1429, "lr": 0.00021076672104404569, "epoch": 0.42169657422512236, "percentage": 2.11, "elapsed_time": "0:15:17", "remaining_time": "11:49:38", "throughput": 6084.12, "total_tokens": 5579744} +{"current_steps": 2590, "total_steps": 122600, "loss": 0.2167, "lr": 0.00021117455138662316, "epoch": 0.42251223491027734, "percentage": 2.11, "elapsed_time": "0:15:18", "remaining_time": "11:49:31", "throughput": 6084.05, "total_tokens": 5589824} +{"current_steps": 2595, "total_steps": 122600, "loss": 0.143, "lr": 0.00021158238172920067, "epoch": 0.4233278955954323, "percentage": 2.12, "elapsed_time": "0:15:20", "remaining_time": "11:49:32", "throughput": 6084.21, "total_tokens": 5601056} +{"current_steps": 2600, "total_steps": 122600, "loss": 0.2179, "lr": 0.00021199021207177814, "epoch": 0.42414355628058725, "percentage": 2.12, "elapsed_time": "0:15:22", "remaining_time": "11:49:29", "throughput": 6084.21, "total_tokens": 5611744} +{"current_steps": 2605, "total_steps": 122600, "loss": 0.2343, "lr": 0.00021239804241435562, "epoch": 0.42495921696574224, "percentage": 2.12, "elapsed_time": "0:15:23", "remaining_time": "11:49:22", "throughput": 6084.03, "total_tokens": 5621600} +{"current_steps": 2610, "total_steps": 122600, "loss": 0.143, "lr": 0.00021280587275693312, "epoch": 0.4257748776508972, "percentage": 2.13, "elapsed_time": "0:15:25", "remaining_time": "11:49:25", "throughput": 6084.1, "total_tokens": 5633088} +{"current_steps": 2615, "total_steps": 122600, "loss": 0.1942, "lr": 0.0002132137030995106, "epoch": 0.4265905383360522, "percentage": 2.13, "elapsed_time": "0:15:27", "remaining_time": "11:49:26", "throughput": 6084.2, "total_tokens": 5644352} +{"current_steps": 2620, "total_steps": 122600, "loss": 0.1614, "lr": 0.0002136215334420881, "epoch": 0.4274061990212072, "percentage": 2.14, "elapsed_time": "0:15:29", "remaining_time": "11:49:14", "throughput": 6083.93, "total_tokens": 5653600} +{"current_steps": 2625, "total_steps": 122600, "loss": 0.1703, "lr": 0.00021402936378466558, "epoch": 0.4282218597063622, "percentage": 2.14, "elapsed_time": "0:15:31", "remaining_time": "11:49:18", "throughput": 6083.96, "total_tokens": 5665152} +{"current_steps": 2630, "total_steps": 122600, "loss": 0.1177, "lr": 0.00021443719412724308, "epoch": 0.4290375203915171, "percentage": 2.15, "elapsed_time": "0:15:33", "remaining_time": "11:49:20", "throughput": 6084.18, "total_tokens": 5676640} +{"current_steps": 2635, "total_steps": 122600, "loss": 0.0626, "lr": 0.00021484502446982056, "epoch": 0.4298531810766721, "percentage": 2.15, "elapsed_time": "0:15:34", "remaining_time": "11:49:18", "throughput": 6084.13, "total_tokens": 5687360} +{"current_steps": 2640, "total_steps": 122600, "loss": 0.1724, "lr": 0.00021525285481239804, "epoch": 0.43066884176182707, "percentage": 2.15, "elapsed_time": "0:15:36", "remaining_time": "11:49:16", "throughput": 6084.06, "total_tokens": 5698112} +{"current_steps": 2645, "total_steps": 122600, "loss": 0.2369, "lr": 0.00021566068515497554, "epoch": 0.43148450244698205, "percentage": 2.16, "elapsed_time": "0:15:38", "remaining_time": "11:49:12", "throughput": 6084.04, "total_tokens": 5708480} +{"current_steps": 2650, "total_steps": 122600, "loss": 0.1843, "lr": 0.00021606851549755302, "epoch": 0.43230016313213704, "percentage": 2.16, "elapsed_time": "0:15:39", "remaining_time": "11:49:01", "throughput": 6084.05, "total_tokens": 5718144} +{"current_steps": 2655, "total_steps": 122600, "loss": 0.2882, "lr": 0.00021647634584013052, "epoch": 0.433115823817292, "percentage": 2.17, "elapsed_time": "0:15:41", "remaining_time": "11:48:59", "throughput": 6083.98, "total_tokens": 5728832} +{"current_steps": 2660, "total_steps": 122600, "loss": 0.1196, "lr": 0.000216884176182708, "epoch": 0.433931484502447, "percentage": 2.17, "elapsed_time": "0:15:43", "remaining_time": "11:48:57", "throughput": 6084.09, "total_tokens": 5739584} +{"current_steps": 2665, "total_steps": 122600, "loss": 0.145, "lr": 0.0002172920065252855, "epoch": 0.43474714518760194, "percentage": 2.17, "elapsed_time": "0:15:45", "remaining_time": "11:48:50", "throughput": 6083.96, "total_tokens": 5749632} +{"current_steps": 2670, "total_steps": 122600, "loss": 0.0556, "lr": 0.00021769983686786295, "epoch": 0.4355628058727569, "percentage": 2.18, "elapsed_time": "0:15:46", "remaining_time": "11:48:49", "throughput": 6083.94, "total_tokens": 5760480} +{"current_steps": 2675, "total_steps": 122600, "loss": 0.1921, "lr": 0.00021810766721044045, "epoch": 0.4363784665579119, "percentage": 2.18, "elapsed_time": "0:15:48", "remaining_time": "11:48:42", "throughput": 6083.94, "total_tokens": 5770560} +{"current_steps": 2680, "total_steps": 122600, "loss": 0.1473, "lr": 0.00021851549755301796, "epoch": 0.4371941272430669, "percentage": 2.19, "elapsed_time": "0:15:50", "remaining_time": "11:48:35", "throughput": 6083.72, "total_tokens": 5780416} +{"current_steps": 2685, "total_steps": 122600, "loss": 0.2966, "lr": 0.00021892332789559543, "epoch": 0.43800978792822187, "percentage": 2.19, "elapsed_time": "0:15:51", "remaining_time": "11:48:32", "throughput": 6083.84, "total_tokens": 5791136} +{"current_steps": 2690, "total_steps": 122600, "loss": 0.1756, "lr": 0.00021933115823817294, "epoch": 0.43882544861337686, "percentage": 2.19, "elapsed_time": "0:15:53", "remaining_time": "11:48:29", "throughput": 6083.73, "total_tokens": 5801600} +{"current_steps": 2695, "total_steps": 122600, "loss": 0.19, "lr": 0.0002197389885807504, "epoch": 0.4396411092985318, "percentage": 2.2, "elapsed_time": "0:15:55", "remaining_time": "11:48:35", "throughput": 6083.86, "total_tokens": 5813632} +{"current_steps": 2700, "total_steps": 122600, "loss": 0.0424, "lr": 0.00022014681892332792, "epoch": 0.44045676998368677, "percentage": 2.2, "elapsed_time": "0:15:57", "remaining_time": "11:48:28", "throughput": 6083.78, "total_tokens": 5823680} +{"current_steps": 2705, "total_steps": 122600, "loss": 0.1069, "lr": 0.00022055464926590536, "epoch": 0.44127243066884175, "percentage": 2.21, "elapsed_time": "0:15:58", "remaining_time": "11:48:23", "throughput": 6083.6, "total_tokens": 5833760} +{"current_steps": 2710, "total_steps": 122600, "loss": 0.184, "lr": 0.00022096247960848287, "epoch": 0.44208809135399674, "percentage": 2.21, "elapsed_time": "0:16:00", "remaining_time": "11:48:19", "throughput": 6083.65, "total_tokens": 5844352} +{"current_steps": 2715, "total_steps": 122600, "loss": 0.1101, "lr": 0.00022137030995106037, "epoch": 0.4429037520391517, "percentage": 2.21, "elapsed_time": "0:16:02", "remaining_time": "11:48:14", "throughput": 6083.57, "total_tokens": 5854624} +{"current_steps": 2720, "total_steps": 122600, "loss": 0.1279, "lr": 0.00022177814029363785, "epoch": 0.4437194127243067, "percentage": 2.22, "elapsed_time": "0:16:04", "remaining_time": "11:48:11", "throughput": 6083.64, "total_tokens": 5865280} +{"current_steps": 2725, "total_steps": 122600, "loss": 0.128, "lr": 0.00022218597063621535, "epoch": 0.4445350734094617, "percentage": 2.22, "elapsed_time": "0:16:05", "remaining_time": "11:48:06", "throughput": 6083.61, "total_tokens": 5875552} +{"current_steps": 2730, "total_steps": 122600, "loss": 0.2118, "lr": 0.00022259380097879283, "epoch": 0.4453507340946166, "percentage": 2.23, "elapsed_time": "0:16:07", "remaining_time": "11:48:07", "throughput": 6083.51, "total_tokens": 5886592} +{"current_steps": 2735, "total_steps": 122600, "loss": 0.1433, "lr": 0.0002230016313213703, "epoch": 0.4461663947797716, "percentage": 2.23, "elapsed_time": "0:16:09", "remaining_time": "11:48:02", "throughput": 6083.45, "total_tokens": 5896864} +{"current_steps": 2740, "total_steps": 122600, "loss": 0.1857, "lr": 0.00022340946166394778, "epoch": 0.4469820554649266, "percentage": 2.23, "elapsed_time": "0:16:11", "remaining_time": "11:47:58", "throughput": 6083.48, "total_tokens": 5907360} +{"current_steps": 2745, "total_steps": 122600, "loss": 0.1385, "lr": 0.00022381729200652529, "epoch": 0.44779771615008157, "percentage": 2.24, "elapsed_time": "0:16:12", "remaining_time": "11:47:50", "throughput": 6083.46, "total_tokens": 5917344} +{"current_steps": 2750, "total_steps": 122600, "loss": 0.2181, "lr": 0.0002242251223491028, "epoch": 0.44861337683523655, "percentage": 2.24, "elapsed_time": "0:16:14", "remaining_time": "11:47:57", "throughput": 6083.75, "total_tokens": 5929536} +{"current_steps": 2755, "total_steps": 122600, "loss": 0.155, "lr": 0.00022463295269168027, "epoch": 0.44942903752039154, "percentage": 2.25, "elapsed_time": "0:16:16", "remaining_time": "11:48:00", "throughput": 6083.69, "total_tokens": 5940992} +{"current_steps": 2760, "total_steps": 122600, "loss": 0.1618, "lr": 0.00022504078303425777, "epoch": 0.45024469820554647, "percentage": 2.25, "elapsed_time": "0:16:18", "remaining_time": "11:47:57", "throughput": 6083.57, "total_tokens": 5951520} +{"current_steps": 2765, "total_steps": 122600, "loss": 0.1302, "lr": 0.00022544861337683525, "epoch": 0.45106035889070145, "percentage": 2.26, "elapsed_time": "0:16:20", "remaining_time": "11:47:53", "throughput": 6083.55, "total_tokens": 5961952} +{"current_steps": 2770, "total_steps": 122600, "loss": 0.2578, "lr": 0.00022585644371941272, "epoch": 0.45187601957585644, "percentage": 2.26, "elapsed_time": "0:16:21", "remaining_time": "11:47:47", "throughput": 6083.46, "total_tokens": 5972000} +{"current_steps": 2775, "total_steps": 122600, "loss": 0.1126, "lr": 0.0002262642740619902, "epoch": 0.4526916802610114, "percentage": 2.26, "elapsed_time": "0:16:23", "remaining_time": "11:47:39", "throughput": 6083.47, "total_tokens": 5981984} +{"current_steps": 2780, "total_steps": 122600, "loss": 0.0887, "lr": 0.0002266721044045677, "epoch": 0.4535073409461664, "percentage": 2.27, "elapsed_time": "0:16:25", "remaining_time": "11:47:38", "throughput": 6083.5, "total_tokens": 5992800} +{"current_steps": 2785, "total_steps": 122600, "loss": 0.0777, "lr": 0.0002270799347471452, "epoch": 0.4543230016313214, "percentage": 2.27, "elapsed_time": "0:16:26", "remaining_time": "11:47:37", "throughput": 6083.54, "total_tokens": 6003808} +{"current_steps": 2790, "total_steps": 122600, "loss": 0.1955, "lr": 0.00022748776508972268, "epoch": 0.4551386623164764, "percentage": 2.28, "elapsed_time": "0:16:28", "remaining_time": "11:47:33", "throughput": 6083.6, "total_tokens": 6014336} +{"current_steps": 2795, "total_steps": 122600, "loss": 0.2142, "lr": 0.00022789559543230019, "epoch": 0.4559543230016313, "percentage": 2.28, "elapsed_time": "0:16:30", "remaining_time": "11:47:36", "throughput": 6083.71, "total_tokens": 6025792} +{"current_steps": 2800, "total_steps": 122600, "loss": 0.1424, "lr": 0.00022830342577487763, "epoch": 0.4567699836867863, "percentage": 2.28, "elapsed_time": "0:16:32", "remaining_time": "11:47:31", "throughput": 6083.51, "total_tokens": 6035968} +{"current_steps": 2805, "total_steps": 122600, "loss": 0.1321, "lr": 0.00022871125611745514, "epoch": 0.45758564437194127, "percentage": 2.29, "elapsed_time": "0:16:33", "remaining_time": "11:47:30", "throughput": 6083.65, "total_tokens": 6047040} +{"current_steps": 2810, "total_steps": 122600, "loss": 0.0808, "lr": 0.00022911908646003261, "epoch": 0.45840130505709625, "percentage": 2.29, "elapsed_time": "0:16:35", "remaining_time": "11:47:28", "throughput": 6083.66, "total_tokens": 6057728} +{"current_steps": 2815, "total_steps": 122600, "loss": 0.1649, "lr": 0.00022952691680261012, "epoch": 0.45921696574225124, "percentage": 2.3, "elapsed_time": "0:16:37", "remaining_time": "11:47:36", "throughput": 6083.95, "total_tokens": 6070208} +{"current_steps": 2820, "total_steps": 122600, "loss": 0.1928, "lr": 0.00022993474714518762, "epoch": 0.4600326264274062, "percentage": 2.3, "elapsed_time": "0:16:39", "remaining_time": "11:47:41", "throughput": 6084.04, "total_tokens": 6082144} +{"current_steps": 2825, "total_steps": 122600, "loss": 0.1365, "lr": 0.0002303425774877651, "epoch": 0.46084828711256115, "percentage": 2.3, "elapsed_time": "0:16:41", "remaining_time": "11:47:46", "throughput": 6084.31, "total_tokens": 6094112} +{"current_steps": 2830, "total_steps": 122600, "loss": 0.1038, "lr": 0.0002307504078303426, "epoch": 0.46166394779771613, "percentage": 2.31, "elapsed_time": "0:16:43", "remaining_time": "11:47:43", "throughput": 6084.19, "total_tokens": 6104608} +{"current_steps": 2835, "total_steps": 122600, "loss": 0.0966, "lr": 0.00023115823817292005, "epoch": 0.4624796084828711, "percentage": 2.31, "elapsed_time": "0:16:45", "remaining_time": "11:47:39", "throughput": 6084.0, "total_tokens": 6114816} +{"current_steps": 2840, "total_steps": 122600, "loss": 0.1219, "lr": 0.00023156606851549755, "epoch": 0.4632952691680261, "percentage": 2.32, "elapsed_time": "0:16:46", "remaining_time": "11:47:39", "throughput": 6084.03, "total_tokens": 6125952} +{"current_steps": 2845, "total_steps": 122600, "loss": 0.2323, "lr": 0.00023197389885807503, "epoch": 0.4641109298531811, "percentage": 2.32, "elapsed_time": "0:16:48", "remaining_time": "11:47:39", "throughput": 6084.04, "total_tokens": 6137056} +{"current_steps": 2850, "total_steps": 122600, "loss": 0.0779, "lr": 0.00023238172920065253, "epoch": 0.46492659053833607, "percentage": 2.32, "elapsed_time": "0:16:50", "remaining_time": "11:47:37", "throughput": 6084.07, "total_tokens": 6147840} +{"current_steps": 2855, "total_steps": 122600, "loss": 0.222, "lr": 0.00023278955954323004, "epoch": 0.46574225122349105, "percentage": 2.33, "elapsed_time": "0:16:52", "remaining_time": "11:47:43", "throughput": 6084.21, "total_tokens": 6159808} +{"current_steps": 2860, "total_steps": 122600, "loss": 0.1266, "lr": 0.00023319738988580751, "epoch": 0.466557911908646, "percentage": 2.33, "elapsed_time": "0:16:54", "remaining_time": "11:47:46", "throughput": 6084.36, "total_tokens": 6171520} +{"current_steps": 2865, "total_steps": 122600, "loss": 0.1842, "lr": 0.000233605220228385, "epoch": 0.46737357259380097, "percentage": 2.34, "elapsed_time": "0:16:56", "remaining_time": "11:47:45", "throughput": 6084.59, "total_tokens": 6182656} +{"current_steps": 2870, "total_steps": 122600, "loss": 0.2398, "lr": 0.00023401305057096247, "epoch": 0.46818923327895595, "percentage": 2.34, "elapsed_time": "0:16:57", "remaining_time": "11:47:46", "throughput": 6084.49, "total_tokens": 6193696} +{"current_steps": 2875, "total_steps": 122600, "loss": 0.1797, "lr": 0.00023442088091353997, "epoch": 0.46900489396411094, "percentage": 2.35, "elapsed_time": "0:16:59", "remaining_time": "11:47:42", "throughput": 6084.5, "total_tokens": 6204192} +{"current_steps": 2880, "total_steps": 122600, "loss": 0.1488, "lr": 0.00023482871125611747, "epoch": 0.4698205546492659, "percentage": 2.35, "elapsed_time": "0:17:01", "remaining_time": "11:47:42", "throughput": 6084.39, "total_tokens": 6215136} +{"current_steps": 2885, "total_steps": 122600, "loss": 0.0896, "lr": 0.00023523654159869495, "epoch": 0.4706362153344209, "percentage": 2.35, "elapsed_time": "0:17:03", "remaining_time": "11:47:40", "throughput": 6084.44, "total_tokens": 6225952} +{"current_steps": 2890, "total_steps": 122600, "loss": 0.2225, "lr": 0.00023564437194127245, "epoch": 0.47145187601957583, "percentage": 2.36, "elapsed_time": "0:17:05", "remaining_time": "11:47:41", "throughput": 6084.48, "total_tokens": 6237152} +{"current_steps": 2895, "total_steps": 122600, "loss": 0.1513, "lr": 0.00023605220228384993, "epoch": 0.4722675367047308, "percentage": 2.36, "elapsed_time": "0:17:06", "remaining_time": "11:47:42", "throughput": 6084.55, "total_tokens": 6248416} +{"current_steps": 2900, "total_steps": 122600, "loss": 0.1621, "lr": 0.0002364600326264274, "epoch": 0.4730831973898858, "percentage": 2.37, "elapsed_time": "0:17:08", "remaining_time": "11:47:44", "throughput": 6084.59, "total_tokens": 6259840} +{"current_steps": 2905, "total_steps": 122600, "loss": 0.1043, "lr": 0.00023686786296900488, "epoch": 0.4738988580750408, "percentage": 2.37, "elapsed_time": "0:17:10", "remaining_time": "11:47:45", "throughput": 6084.71, "total_tokens": 6271104} +{"current_steps": 2910, "total_steps": 122600, "loss": 0.1725, "lr": 0.0002372756933115824, "epoch": 0.47471451876019577, "percentage": 2.37, "elapsed_time": "0:17:12", "remaining_time": "11:47:42", "throughput": 6084.62, "total_tokens": 6281696} +{"current_steps": 2915, "total_steps": 122600, "loss": 0.1408, "lr": 0.0002376835236541599, "epoch": 0.47553017944535075, "percentage": 2.38, "elapsed_time": "0:17:14", "remaining_time": "11:47:47", "throughput": 6084.89, "total_tokens": 6293760} +{"current_steps": 2920, "total_steps": 122600, "loss": 0.091, "lr": 0.00023809135399673737, "epoch": 0.4763458401305057, "percentage": 2.38, "elapsed_time": "0:17:16", "remaining_time": "11:47:49", "throughput": 6085.12, "total_tokens": 6305376} +{"current_steps": 2925, "total_steps": 122600, "loss": 0.1022, "lr": 0.00023849918433931487, "epoch": 0.47716150081566067, "percentage": 2.39, "elapsed_time": "0:17:17", "remaining_time": "11:47:47", "throughput": 6085.03, "total_tokens": 6316032} +{"current_steps": 2930, "total_steps": 122600, "loss": 0.2899, "lr": 0.00023890701468189232, "epoch": 0.47797716150081565, "percentage": 2.39, "elapsed_time": "0:17:19", "remaining_time": "11:47:49", "throughput": 6085.17, "total_tokens": 6327552} +{"current_steps": 2935, "total_steps": 122600, "loss": 0.1099, "lr": 0.00023931484502446982, "epoch": 0.47879282218597063, "percentage": 2.39, "elapsed_time": "0:17:21", "remaining_time": "11:47:42", "throughput": 6085.03, "total_tokens": 6337344} +{"current_steps": 2940, "total_steps": 122600, "loss": 0.1346, "lr": 0.0002397226753670473, "epoch": 0.4796084828711256, "percentage": 2.4, "elapsed_time": "0:17:23", "remaining_time": "11:47:45", "throughput": 6085.21, "total_tokens": 6349120} +{"current_steps": 2945, "total_steps": 122600, "loss": 0.1392, "lr": 0.0002401305057096248, "epoch": 0.4804241435562806, "percentage": 2.4, "elapsed_time": "0:17:25", "remaining_time": "11:47:42", "throughput": 6085.17, "total_tokens": 6359584} +{"current_steps": 2950, "total_steps": 122600, "loss": 0.1193, "lr": 0.0002405383360522023, "epoch": 0.4812398042414356, "percentage": 2.41, "elapsed_time": "0:17:26", "remaining_time": "11:47:39", "throughput": 6085.1, "total_tokens": 6370112} +{"current_steps": 2955, "total_steps": 122600, "loss": 0.0465, "lr": 0.00024094616639477978, "epoch": 0.4820554649265905, "percentage": 2.41, "elapsed_time": "0:17:28", "remaining_time": "11:47:39", "throughput": 6085.07, "total_tokens": 6381248} +{"current_steps": 2960, "total_steps": 122600, "loss": 0.1825, "lr": 0.00024135399673735726, "epoch": 0.4828711256117455, "percentage": 2.41, "elapsed_time": "0:17:30", "remaining_time": "11:47:38", "throughput": 6085.11, "total_tokens": 6392224} +{"current_steps": 2965, "total_steps": 122600, "loss": 0.2347, "lr": 0.00024176182707993474, "epoch": 0.4836867862969005, "percentage": 2.42, "elapsed_time": "0:17:32", "remaining_time": "11:47:30", "throughput": 6084.97, "total_tokens": 6401888} +{"current_steps": 2970, "total_steps": 122600, "loss": 0.1298, "lr": 0.00024216965742251224, "epoch": 0.48450244698205547, "percentage": 2.42, "elapsed_time": "0:17:33", "remaining_time": "11:47:26", "throughput": 6084.91, "total_tokens": 6412352} +{"current_steps": 2975, "total_steps": 122600, "loss": 0.115, "lr": 0.00024257748776508972, "epoch": 0.48531810766721045, "percentage": 2.43, "elapsed_time": "0:17:35", "remaining_time": "11:47:24", "throughput": 6084.78, "total_tokens": 6422880} +{"current_steps": 2980, "total_steps": 122600, "loss": 0.1675, "lr": 0.00024298531810766722, "epoch": 0.48613376835236544, "percentage": 2.43, "elapsed_time": "0:17:37", "remaining_time": "11:47:22", "throughput": 6084.76, "total_tokens": 6433696} +{"current_steps": 2985, "total_steps": 122600, "loss": 0.2255, "lr": 0.00024339314845024472, "epoch": 0.48694942903752036, "percentage": 2.43, "elapsed_time": "0:17:39", "remaining_time": "11:47:21", "throughput": 6084.81, "total_tokens": 6444576} +{"current_steps": 2990, "total_steps": 122600, "loss": 0.0739, "lr": 0.0002438009787928222, "epoch": 0.48776508972267535, "percentage": 2.44, "elapsed_time": "0:17:40", "remaining_time": "11:47:20", "throughput": 6084.93, "total_tokens": 6455616} +{"current_steps": 2995, "total_steps": 122600, "loss": 0.1702, "lr": 0.0002442088091353997, "epoch": 0.48858075040783033, "percentage": 2.44, "elapsed_time": "0:17:42", "remaining_time": "11:47:14", "throughput": 6084.71, "total_tokens": 6465632} +{"current_steps": 3000, "total_steps": 122600, "loss": 0.1988, "lr": 0.00024461663947797715, "epoch": 0.4893964110929853, "percentage": 2.45, "elapsed_time": "0:17:44", "remaining_time": "11:47:13", "throughput": 6084.58, "total_tokens": 6476320} +{"current_steps": 3005, "total_steps": 122600, "loss": 0.1749, "lr": 0.00024502446982055463, "epoch": 0.4902120717781403, "percentage": 2.45, "elapsed_time": "0:17:46", "remaining_time": "11:47:09", "throughput": 6084.43, "total_tokens": 6486560} +{"current_steps": 3010, "total_steps": 122600, "loss": 0.06, "lr": 0.00024543230016313216, "epoch": 0.4910277324632953, "percentage": 2.46, "elapsed_time": "0:17:47", "remaining_time": "11:47:02", "throughput": 6084.22, "total_tokens": 6496448} +{"current_steps": 3015, "total_steps": 122600, "loss": 0.1295, "lr": 0.00024584013050570964, "epoch": 0.49184339314845027, "percentage": 2.46, "elapsed_time": "0:17:49", "remaining_time": "11:46:57", "throughput": 6084.19, "total_tokens": 6506624} +{"current_steps": 3020, "total_steps": 122600, "loss": 0.1661, "lr": 0.0002462479608482871, "epoch": 0.4926590538336052, "percentage": 2.46, "elapsed_time": "0:17:51", "remaining_time": "11:46:53", "throughput": 6084.1, "total_tokens": 6516960} +{"current_steps": 3025, "total_steps": 122600, "loss": 0.1348, "lr": 0.0002466557911908646, "epoch": 0.4934747145187602, "percentage": 2.47, "elapsed_time": "0:17:53", "remaining_time": "11:46:57", "throughput": 6084.28, "total_tokens": 6528896} +{"current_steps": 3030, "total_steps": 122600, "loss": 0.0731, "lr": 0.00024706362153344207, "epoch": 0.49429037520391517, "percentage": 2.47, "elapsed_time": "0:17:54", "remaining_time": "11:47:00", "throughput": 6084.46, "total_tokens": 6540576} +{"current_steps": 3035, "total_steps": 122600, "loss": 0.0626, "lr": 0.0002474714518760196, "epoch": 0.49510603588907015, "percentage": 2.48, "elapsed_time": "0:17:56", "remaining_time": "11:46:57", "throughput": 6084.58, "total_tokens": 6551424} +{"current_steps": 3040, "total_steps": 122600, "loss": 0.0862, "lr": 0.0002478792822185971, "epoch": 0.49592169657422513, "percentage": 2.48, "elapsed_time": "0:17:58", "remaining_time": "11:46:55", "throughput": 6084.62, "total_tokens": 6562176} +{"current_steps": 3045, "total_steps": 122600, "loss": 0.0904, "lr": 0.00024828711256117455, "epoch": 0.4967373572593801, "percentage": 2.48, "elapsed_time": "0:18:00", "remaining_time": "11:46:50", "throughput": 6084.52, "total_tokens": 6572384} +{"current_steps": 3050, "total_steps": 122600, "loss": 0.2203, "lr": 0.000248694942903752, "epoch": 0.49755301794453505, "percentage": 2.49, "elapsed_time": "0:18:01", "remaining_time": "11:46:50", "throughput": 6084.56, "total_tokens": 6583424} +{"current_steps": 3055, "total_steps": 122600, "loss": 0.0513, "lr": 0.00024910277324632956, "epoch": 0.49836867862969003, "percentage": 2.49, "elapsed_time": "0:18:03", "remaining_time": "11:46:47", "throughput": 6084.61, "total_tokens": 6594144} +{"current_steps": 3060, "total_steps": 122600, "loss": 0.1248, "lr": 0.00024951060358890703, "epoch": 0.499184339314845, "percentage": 2.5, "elapsed_time": "0:18:05", "remaining_time": "11:46:51", "throughput": 6084.65, "total_tokens": 6605760} +{"current_steps": 3065, "total_steps": 122600, "loss": 0.1945, "lr": 0.0002499184339314845, "epoch": 0.5, "percentage": 2.5, "elapsed_time": "0:18:07", "remaining_time": "11:46:49", "throughput": 6084.81, "total_tokens": 6616832} +{"current_steps": 3070, "total_steps": 122600, "loss": 0.159, "lr": 0.00025032626427406204, "epoch": 0.5008156606851549, "percentage": 2.5, "elapsed_time": "0:18:09", "remaining_time": "11:46:52", "throughput": 6084.85, "total_tokens": 6628384} +{"current_steps": 3075, "total_steps": 122600, "loss": 0.0486, "lr": 0.00025073409461663946, "epoch": 0.50163132137031, "percentage": 2.51, "elapsed_time": "0:18:11", "remaining_time": "11:46:52", "throughput": 6084.95, "total_tokens": 6639456} +{"current_steps": 3080, "total_steps": 122600, "loss": 0.0311, "lr": 0.00025114192495921694, "epoch": 0.5024469820554649, "percentage": 2.51, "elapsed_time": "0:18:13", "remaining_time": "11:46:57", "throughput": 6085.08, "total_tokens": 6651520} +{"current_steps": 3085, "total_steps": 122600, "loss": 0.1245, "lr": 0.00025154975530179447, "epoch": 0.5032626427406199, "percentage": 2.52, "elapsed_time": "0:18:14", "remaining_time": "11:46:51", "throughput": 6085.04, "total_tokens": 6661664} +{"current_steps": 3090, "total_steps": 122600, "loss": 0.2796, "lr": 0.00025195758564437195, "epoch": 0.5040783034257749, "percentage": 2.52, "elapsed_time": "0:18:16", "remaining_time": "11:46:53", "throughput": 6085.07, "total_tokens": 6673024} +{"current_steps": 3095, "total_steps": 122600, "loss": 0.1932, "lr": 0.0002523654159869495, "epoch": 0.5048939641109299, "percentage": 2.52, "elapsed_time": "0:18:18", "remaining_time": "11:46:58", "throughput": 6085.36, "total_tokens": 6685216} +{"current_steps": 3100, "total_steps": 122600, "loss": 0.1647, "lr": 0.0002527732463295269, "epoch": 0.5057096247960848, "percentage": 2.53, "elapsed_time": "0:18:20", "remaining_time": "11:46:56", "throughput": 6085.44, "total_tokens": 6696096} +{"current_steps": 3105, "total_steps": 122600, "loss": 0.2937, "lr": 0.0002531810766721044, "epoch": 0.5065252854812398, "percentage": 2.53, "elapsed_time": "0:18:22", "remaining_time": "11:46:53", "throughput": 6085.4, "total_tokens": 6706656} +{"current_steps": 3110, "total_steps": 122600, "loss": 0.1488, "lr": 0.0002535889070146819, "epoch": 0.5073409461663948, "percentage": 2.54, "elapsed_time": "0:18:23", "remaining_time": "11:46:47", "throughput": 6085.37, "total_tokens": 6716704} +{"current_steps": 3115, "total_steps": 122600, "loss": 0.1496, "lr": 0.0002539967373572594, "epoch": 0.5081566068515497, "percentage": 2.54, "elapsed_time": "0:18:25", "remaining_time": "11:46:49", "throughput": 6085.53, "total_tokens": 6728352} +{"current_steps": 3120, "total_steps": 122600, "loss": 0.1336, "lr": 0.00025440456769983686, "epoch": 0.5089722675367048, "percentage": 2.54, "elapsed_time": "0:18:27", "remaining_time": "11:46:48", "throughput": 6085.65, "total_tokens": 6739296} +{"current_steps": 3125, "total_steps": 122600, "loss": 0.1314, "lr": 0.00025481239804241434, "epoch": 0.5097879282218597, "percentage": 2.55, "elapsed_time": "0:18:29", "remaining_time": "11:46:46", "throughput": 6085.76, "total_tokens": 6750176} +{"current_steps": 3130, "total_steps": 122600, "loss": 0.1824, "lr": 0.00025522022838499187, "epoch": 0.5106035889070146, "percentage": 2.55, "elapsed_time": "0:18:30", "remaining_time": "11:46:40", "throughput": 6085.65, "total_tokens": 6760288} +{"current_steps": 3135, "total_steps": 122600, "loss": 0.1319, "lr": 0.00025562805872756934, "epoch": 0.5114192495921697, "percentage": 2.56, "elapsed_time": "0:18:32", "remaining_time": "11:46:31", "throughput": 6085.52, "total_tokens": 6769792} +{"current_steps": 3140, "total_steps": 122600, "loss": 0.169, "lr": 0.0002560358890701468, "epoch": 0.5122349102773246, "percentage": 2.56, "elapsed_time": "0:18:34", "remaining_time": "11:46:24", "throughput": 6085.46, "total_tokens": 6779712} +{"current_steps": 3145, "total_steps": 122600, "loss": 0.1126, "lr": 0.0002564437194127243, "epoch": 0.5130505709624796, "percentage": 2.57, "elapsed_time": "0:18:35", "remaining_time": "11:46:27", "throughput": 6085.46, "total_tokens": 6791232} +{"current_steps": 3150, "total_steps": 122600, "loss": 0.0951, "lr": 0.00025685154975530177, "epoch": 0.5138662316476346, "percentage": 2.57, "elapsed_time": "0:18:37", "remaining_time": "11:46:23", "throughput": 6085.54, "total_tokens": 6801696} +{"current_steps": 3155, "total_steps": 122600, "loss": 0.0867, "lr": 0.0002572593800978793, "epoch": 0.5146818923327896, "percentage": 2.57, "elapsed_time": "0:18:39", "remaining_time": "11:46:21", "throughput": 6085.62, "total_tokens": 6812672} +{"current_steps": 3160, "total_steps": 122600, "loss": 0.2778, "lr": 0.0002576672104404568, "epoch": 0.5154975530179445, "percentage": 2.58, "elapsed_time": "0:18:41", "remaining_time": "11:46:17", "throughput": 6085.63, "total_tokens": 6822976} +{"current_steps": 3165, "total_steps": 122600, "loss": 0.179, "lr": 0.0002580750407830343, "epoch": 0.5163132137030995, "percentage": 2.58, "elapsed_time": "0:18:42", "remaining_time": "11:46:15", "throughput": 6085.68, "total_tokens": 6833888} +{"current_steps": 3170, "total_steps": 122600, "loss": 0.3424, "lr": 0.00025848287112561173, "epoch": 0.5171288743882545, "percentage": 2.59, "elapsed_time": "0:18:44", "remaining_time": "11:46:18", "throughput": 6085.92, "total_tokens": 6845632} +{"current_steps": 3175, "total_steps": 122600, "loss": 0.1384, "lr": 0.0002588907014681892, "epoch": 0.5179445350734094, "percentage": 2.59, "elapsed_time": "0:18:46", "remaining_time": "11:46:14", "throughput": 6085.94, "total_tokens": 6856128} +{"current_steps": 3180, "total_steps": 122600, "loss": 0.0676, "lr": 0.00025929853181076674, "epoch": 0.5187601957585645, "percentage": 2.59, "elapsed_time": "0:18:48", "remaining_time": "11:46:17", "throughput": 6085.99, "total_tokens": 6867840} +{"current_steps": 3185, "total_steps": 122600, "loss": 0.1326, "lr": 0.0002597063621533442, "epoch": 0.5195758564437194, "percentage": 2.6, "elapsed_time": "0:18:50", "remaining_time": "11:46:12", "throughput": 6086.01, "total_tokens": 6878112} +{"current_steps": 3190, "total_steps": 122600, "loss": 0.1368, "lr": 0.00026011419249592175, "epoch": 0.5203915171288744, "percentage": 2.6, "elapsed_time": "0:18:51", "remaining_time": "11:46:13", "throughput": 6086.0, "total_tokens": 6889312} +{"current_steps": 3195, "total_steps": 122600, "loss": 0.2752, "lr": 0.00026052202283849917, "epoch": 0.5212071778140294, "percentage": 2.61, "elapsed_time": "0:18:53", "remaining_time": "11:46:11", "throughput": 6085.89, "total_tokens": 6899968} +{"current_steps": 3200, "total_steps": 122600, "loss": 0.106, "lr": 0.0002609298531810767, "epoch": 0.5220228384991843, "percentage": 2.61, "elapsed_time": "0:18:55", "remaining_time": "11:46:03", "throughput": 6085.78, "total_tokens": 6909568} +{"current_steps": 3205, "total_steps": 122600, "loss": 0.0982, "lr": 0.0002613376835236542, "epoch": 0.5228384991843393, "percentage": 2.61, "elapsed_time": "0:18:57", "remaining_time": "11:46:04", "throughput": 6085.79, "total_tokens": 6920928} +{"current_steps": 3210, "total_steps": 122600, "loss": 0.059, "lr": 0.00026174551386623165, "epoch": 0.5236541598694943, "percentage": 2.62, "elapsed_time": "0:18:58", "remaining_time": "11:45:54", "throughput": 6085.64, "total_tokens": 6930144} +{"current_steps": 3215, "total_steps": 122600, "loss": 0.1161, "lr": 0.00026215334420880913, "epoch": 0.5244698205546493, "percentage": 2.62, "elapsed_time": "0:19:00", "remaining_time": "11:45:50", "throughput": 6085.44, "total_tokens": 6940320} +{"current_steps": 3220, "total_steps": 122600, "loss": 0.2524, "lr": 0.0002625611745513866, "epoch": 0.5252854812398042, "percentage": 2.63, "elapsed_time": "0:19:02", "remaining_time": "11:45:45", "throughput": 6085.41, "total_tokens": 6950656} +{"current_steps": 3225, "total_steps": 122600, "loss": 0.3218, "lr": 0.00026296900489396414, "epoch": 0.5261011419249593, "percentage": 2.63, "elapsed_time": "0:19:03", "remaining_time": "11:45:43", "throughput": 6085.3, "total_tokens": 6961216} +{"current_steps": 3230, "total_steps": 122600, "loss": 0.1797, "lr": 0.0002633768352365416, "epoch": 0.5269168026101142, "percentage": 2.63, "elapsed_time": "0:19:05", "remaining_time": "11:45:40", "throughput": 6085.25, "total_tokens": 6971808} +{"current_steps": 3235, "total_steps": 122600, "loss": 0.1472, "lr": 0.0002637846655791191, "epoch": 0.5277324632952691, "percentage": 2.64, "elapsed_time": "0:19:07", "remaining_time": "11:45:46", "throughput": 6085.42, "total_tokens": 6984000} +{"current_steps": 3240, "total_steps": 122600, "loss": 0.1489, "lr": 0.00026419249592169657, "epoch": 0.5285481239804242, "percentage": 2.64, "elapsed_time": "0:19:09", "remaining_time": "11:45:40", "throughput": 6085.39, "total_tokens": 6994112} +{"current_steps": 3245, "total_steps": 122600, "loss": 0.1576, "lr": 0.00026460032626427404, "epoch": 0.5293637846655791, "percentage": 2.65, "elapsed_time": "0:19:11", "remaining_time": "11:45:40", "throughput": 6085.46, "total_tokens": 7005184} +{"current_steps": 3250, "total_steps": 122600, "loss": 0.1407, "lr": 0.00026500815660685157, "epoch": 0.5301794453507341, "percentage": 2.65, "elapsed_time": "0:19:12", "remaining_time": "11:45:38", "throughput": 6085.4, "total_tokens": 7015968} +{"current_steps": 3255, "total_steps": 122600, "loss": 0.1001, "lr": 0.00026541598694942905, "epoch": 0.5309951060358891, "percentage": 2.65, "elapsed_time": "0:19:14", "remaining_time": "11:45:41", "throughput": 6085.48, "total_tokens": 7027584} +{"current_steps": 3260, "total_steps": 122600, "loss": 0.1434, "lr": 0.0002658238172920066, "epoch": 0.531810766721044, "percentage": 2.66, "elapsed_time": "0:19:16", "remaining_time": "11:45:44", "throughput": 6085.64, "total_tokens": 7039424} +{"current_steps": 3265, "total_steps": 122600, "loss": 0.2385, "lr": 0.000266231647634584, "epoch": 0.532626427406199, "percentage": 2.66, "elapsed_time": "0:19:18", "remaining_time": "11:45:41", "throughput": 6085.56, "total_tokens": 7049824} +{"current_steps": 3270, "total_steps": 122600, "loss": 0.2721, "lr": 0.0002666394779771615, "epoch": 0.533442088091354, "percentage": 2.67, "elapsed_time": "0:19:20", "remaining_time": "11:45:44", "throughput": 6085.57, "total_tokens": 7061472} +{"current_steps": 3275, "total_steps": 122600, "loss": 0.1761, "lr": 0.000267047308319739, "epoch": 0.534257748776509, "percentage": 2.67, "elapsed_time": "0:19:22", "remaining_time": "11:45:46", "throughput": 6085.74, "total_tokens": 7073152} +{"current_steps": 3280, "total_steps": 122600, "loss": 0.192, "lr": 0.0002674551386623165, "epoch": 0.5350734094616639, "percentage": 2.68, "elapsed_time": "0:19:24", "remaining_time": "11:45:48", "throughput": 6085.83, "total_tokens": 7084640} +{"current_steps": 3285, "total_steps": 122600, "loss": 0.0733, "lr": 0.00026786296900489396, "epoch": 0.535889070146819, "percentage": 2.68, "elapsed_time": "0:19:25", "remaining_time": "11:45:34", "throughput": 6085.6, "total_tokens": 7093088} +{"current_steps": 3290, "total_steps": 122600, "loss": 0.0965, "lr": 0.00026827079934747144, "epoch": 0.5367047308319739, "percentage": 2.68, "elapsed_time": "0:19:27", "remaining_time": "11:45:27", "throughput": 6085.65, "total_tokens": 7103072} +{"current_steps": 3295, "total_steps": 122600, "loss": 0.0664, "lr": 0.00026867862969004897, "epoch": 0.5375203915171288, "percentage": 2.69, "elapsed_time": "0:19:28", "remaining_time": "11:45:24", "throughput": 6085.75, "total_tokens": 7113792} +{"current_steps": 3300, "total_steps": 122600, "loss": 0.109, "lr": 0.00026908646003262645, "epoch": 0.5383360522022839, "percentage": 2.69, "elapsed_time": "0:19:30", "remaining_time": "11:45:23", "throughput": 6085.74, "total_tokens": 7124800} +{"current_steps": 3305, "total_steps": 122600, "loss": 0.0801, "lr": 0.0002694942903752039, "epoch": 0.5391517128874388, "percentage": 2.7, "elapsed_time": "0:19:32", "remaining_time": "11:45:31", "throughput": 6085.87, "total_tokens": 7137280} +{"current_steps": 3310, "total_steps": 122600, "loss": 0.0672, "lr": 0.0002699021207177814, "epoch": 0.5399673735725938, "percentage": 2.7, "elapsed_time": "0:19:34", "remaining_time": "11:45:24", "throughput": 6085.89, "total_tokens": 7147264} +{"current_steps": 3315, "total_steps": 122600, "loss": 0.1905, "lr": 0.0002703099510603589, "epoch": 0.5407830342577488, "percentage": 2.7, "elapsed_time": "0:19:36", "remaining_time": "11:45:18", "throughput": 6085.89, "total_tokens": 7157408} +{"current_steps": 3320, "total_steps": 122600, "loss": 0.0451, "lr": 0.0002707177814029364, "epoch": 0.5415986949429038, "percentage": 2.71, "elapsed_time": "0:19:37", "remaining_time": "11:45:17", "throughput": 6085.79, "total_tokens": 7168224} +{"current_steps": 3325, "total_steps": 122600, "loss": 0.1935, "lr": 0.0002711256117455139, "epoch": 0.5424143556280587, "percentage": 2.71, "elapsed_time": "0:19:39", "remaining_time": "11:45:19", "throughput": 6085.81, "total_tokens": 7179680} +{"current_steps": 3330, "total_steps": 122600, "loss": 0.0687, "lr": 0.0002715334420880914, "epoch": 0.5432300163132137, "percentage": 2.72, "elapsed_time": "0:19:41", "remaining_time": "11:45:20", "throughput": 6085.89, "total_tokens": 7190944} +{"current_steps": 3335, "total_steps": 122600, "loss": 0.2025, "lr": 0.00027194127243066883, "epoch": 0.5440456769983687, "percentage": 2.72, "elapsed_time": "0:19:43", "remaining_time": "11:45:15", "throughput": 6085.71, "total_tokens": 7200928} +{"current_steps": 3340, "total_steps": 122600, "loss": 0.0574, "lr": 0.0002723491027732463, "epoch": 0.5448613376835236, "percentage": 2.72, "elapsed_time": "0:19:44", "remaining_time": "11:45:06", "throughput": 6085.51, "total_tokens": 7210400} +{"current_steps": 3345, "total_steps": 122600, "loss": 0.0494, "lr": 0.00027275693311582384, "epoch": 0.5456769983686787, "percentage": 2.73, "elapsed_time": "0:19:46", "remaining_time": "11:45:07", "throughput": 6085.54, "total_tokens": 7221696} +{"current_steps": 3350, "total_steps": 122600, "loss": 0.3457, "lr": 0.0002731647634584013, "epoch": 0.5464926590538336, "percentage": 2.73, "elapsed_time": "0:19:48", "remaining_time": "11:45:05", "throughput": 6085.5, "total_tokens": 7232288} +{"current_steps": 3355, "total_steps": 122600, "loss": 0.0976, "lr": 0.0002735725938009788, "epoch": 0.5473083197389886, "percentage": 2.74, "elapsed_time": "0:19:50", "remaining_time": "11:45:06", "throughput": 6085.64, "total_tokens": 7243808} +{"current_steps": 3360, "total_steps": 122600, "loss": 0.1636, "lr": 0.00027398042414355627, "epoch": 0.5481239804241436, "percentage": 2.74, "elapsed_time": "0:19:52", "remaining_time": "11:45:06", "throughput": 6085.7, "total_tokens": 7254880} +{"current_steps": 3365, "total_steps": 122600, "loss": 0.0648, "lr": 0.00027438825448613375, "epoch": 0.5489396411092985, "percentage": 2.74, "elapsed_time": "0:19:53", "remaining_time": "11:45:03", "throughput": 6085.74, "total_tokens": 7265664} +{"current_steps": 3370, "total_steps": 122600, "loss": 0.2246, "lr": 0.0002747960848287113, "epoch": 0.5497553017944535, "percentage": 2.75, "elapsed_time": "0:19:55", "remaining_time": "11:44:56", "throughput": 6085.62, "total_tokens": 7275424} +{"current_steps": 3375, "total_steps": 122600, "loss": 0.1724, "lr": 0.00027520391517128875, "epoch": 0.5505709624796085, "percentage": 2.75, "elapsed_time": "0:19:57", "remaining_time": "11:44:56", "throughput": 6085.64, "total_tokens": 7286496} +{"current_steps": 3380, "total_steps": 122600, "loss": 0.2398, "lr": 0.00027561174551386623, "epoch": 0.5513866231647635, "percentage": 2.76, "elapsed_time": "0:19:59", "remaining_time": "11:44:53", "throughput": 6085.74, "total_tokens": 7297152} +{"current_steps": 3385, "total_steps": 122600, "loss": 0.1214, "lr": 0.0002760195758564437, "epoch": 0.5522022838499184, "percentage": 2.76, "elapsed_time": "0:20:00", "remaining_time": "11:44:46", "throughput": 6085.55, "total_tokens": 7306816} +{"current_steps": 3390, "total_steps": 122600, "loss": 0.0529, "lr": 0.00027642740619902124, "epoch": 0.5530179445350734, "percentage": 2.77, "elapsed_time": "0:20:02", "remaining_time": "11:44:46", "throughput": 6085.58, "total_tokens": 7317888} +{"current_steps": 3395, "total_steps": 122600, "loss": 0.151, "lr": 0.0002768352365415987, "epoch": 0.5538336052202284, "percentage": 2.77, "elapsed_time": "0:20:04", "remaining_time": "11:44:45", "throughput": 6085.68, "total_tokens": 7329056} +{"current_steps": 3400, "total_steps": 122600, "loss": 0.0376, "lr": 0.0002772430668841762, "epoch": 0.5546492659053833, "percentage": 2.77, "elapsed_time": "0:20:06", "remaining_time": "11:44:45", "throughput": 6085.72, "total_tokens": 7340192} +{"current_steps": 3405, "total_steps": 122600, "loss": 0.0647, "lr": 0.00027765089722675367, "epoch": 0.5554649265905384, "percentage": 2.78, "elapsed_time": "0:20:07", "remaining_time": "11:44:46", "throughput": 6085.8, "total_tokens": 7351584} +{"current_steps": 3410, "total_steps": 122600, "loss": 0.2417, "lr": 0.00027805872756933114, "epoch": 0.5562805872756933, "percentage": 2.78, "elapsed_time": "0:20:09", "remaining_time": "11:44:41", "throughput": 6085.73, "total_tokens": 7361632} +{"current_steps": 3415, "total_steps": 122600, "loss": 0.0949, "lr": 0.0002784665579119087, "epoch": 0.5570962479608483, "percentage": 2.79, "elapsed_time": "0:20:11", "remaining_time": "11:44:36", "throughput": 6085.53, "total_tokens": 7371616} +{"current_steps": 3420, "total_steps": 122600, "loss": 0.1879, "lr": 0.00027887438825448615, "epoch": 0.5579119086460033, "percentage": 2.79, "elapsed_time": "0:20:13", "remaining_time": "11:44:39", "throughput": 6085.62, "total_tokens": 7383488} +{"current_steps": 3425, "total_steps": 122600, "loss": 0.1062, "lr": 0.00027928221859706363, "epoch": 0.5587275693311582, "percentage": 2.79, "elapsed_time": "0:20:15", "remaining_time": "11:44:40", "throughput": 6085.64, "total_tokens": 7394720} +{"current_steps": 3430, "total_steps": 122600, "loss": 0.0697, "lr": 0.0002796900489396411, "epoch": 0.5595432300163132, "percentage": 2.8, "elapsed_time": "0:20:16", "remaining_time": "11:44:38", "throughput": 6085.55, "total_tokens": 7405312} +{"current_steps": 3435, "total_steps": 122600, "loss": 0.0896, "lr": 0.0002800978792822186, "epoch": 0.5603588907014682, "percentage": 2.8, "elapsed_time": "0:20:18", "remaining_time": "11:44:30", "throughput": 6085.45, "total_tokens": 7415040} +{"current_steps": 3440, "total_steps": 122600, "loss": 0.0852, "lr": 0.0002805057096247961, "epoch": 0.5611745513866232, "percentage": 2.81, "elapsed_time": "0:20:20", "remaining_time": "11:44:30", "throughput": 6085.57, "total_tokens": 7426144} +{"current_steps": 3445, "total_steps": 122600, "loss": 0.1836, "lr": 0.0002809135399673736, "epoch": 0.5619902120717781, "percentage": 2.81, "elapsed_time": "0:20:22", "remaining_time": "11:44:28", "throughput": 6085.57, "total_tokens": 7437024} +{"current_steps": 3450, "total_steps": 122600, "loss": 0.0583, "lr": 0.00028132137030995106, "epoch": 0.5628058727569332, "percentage": 2.81, "elapsed_time": "0:20:23", "remaining_time": "11:44:25", "throughput": 6085.62, "total_tokens": 7447552} +{"current_steps": 3455, "total_steps": 122600, "loss": 0.2494, "lr": 0.00028172920065252854, "epoch": 0.5636215334420881, "percentage": 2.82, "elapsed_time": "0:20:25", "remaining_time": "11:44:26", "throughput": 6085.77, "total_tokens": 7459040} +{"current_steps": 3460, "total_steps": 122600, "loss": 0.3266, "lr": 0.000282137030995106, "epoch": 0.564437194127243, "percentage": 2.82, "elapsed_time": "0:20:27", "remaining_time": "11:44:22", "throughput": 6085.62, "total_tokens": 7469248} +{"current_steps": 3465, "total_steps": 122600, "loss": 0.1012, "lr": 0.00028254486133768355, "epoch": 0.5652528548123981, "percentage": 2.83, "elapsed_time": "0:20:29", "remaining_time": "11:44:23", "throughput": 6085.81, "total_tokens": 7480832} +{"current_steps": 3470, "total_steps": 122600, "loss": 0.1335, "lr": 0.000282952691680261, "epoch": 0.566068515497553, "percentage": 2.83, "elapsed_time": "0:20:30", "remaining_time": "11:44:13", "throughput": 6085.71, "total_tokens": 7490016} +{"current_steps": 3475, "total_steps": 122600, "loss": 0.0739, "lr": 0.0002833605220228385, "epoch": 0.566884176182708, "percentage": 2.83, "elapsed_time": "0:20:32", "remaining_time": "11:44:14", "throughput": 6085.65, "total_tokens": 7501184} +{"current_steps": 3480, "total_steps": 122600, "loss": 0.1605, "lr": 0.000283768352365416, "epoch": 0.567699836867863, "percentage": 2.84, "elapsed_time": "0:20:34", "remaining_time": "11:44:11", "throughput": 6085.52, "total_tokens": 7511648} +{"current_steps": 3485, "total_steps": 122600, "loss": 0.0847, "lr": 0.0002841761827079935, "epoch": 0.5685154975530179, "percentage": 2.84, "elapsed_time": "0:20:36", "remaining_time": "11:44:12", "throughput": 6085.65, "total_tokens": 7523104} +{"current_steps": 3490, "total_steps": 122600, "loss": 0.2082, "lr": 0.000284584013050571, "epoch": 0.5693311582381729, "percentage": 2.85, "elapsed_time": "0:20:38", "remaining_time": "11:44:13", "throughput": 6085.7, "total_tokens": 7534496} +{"current_steps": 3495, "total_steps": 122600, "loss": 0.2414, "lr": 0.0002849918433931484, "epoch": 0.5701468189233279, "percentage": 2.85, "elapsed_time": "0:20:39", "remaining_time": "11:44:13", "throughput": 6085.73, "total_tokens": 7545568} +{"current_steps": 3500, "total_steps": 122600, "loss": 0.0974, "lr": 0.00028539967373572594, "epoch": 0.5709624796084829, "percentage": 2.85, "elapsed_time": "0:20:41", "remaining_time": "11:44:08", "throughput": 6085.71, "total_tokens": 7555808} +{"current_steps": 3505, "total_steps": 122600, "loss": 0.1989, "lr": 0.0002858075040783034, "epoch": 0.5717781402936378, "percentage": 2.86, "elapsed_time": "0:20:43", "remaining_time": "11:44:11", "throughput": 6085.68, "total_tokens": 7567296} +{"current_steps": 3510, "total_steps": 122600, "loss": 0.1782, "lr": 0.00028621533442088094, "epoch": 0.5725938009787929, "percentage": 2.86, "elapsed_time": "0:20:45", "remaining_time": "11:44:08", "throughput": 6085.59, "total_tokens": 7577824} +{"current_steps": 3515, "total_steps": 122600, "loss": 0.1201, "lr": 0.0002866231647634584, "epoch": 0.5734094616639478, "percentage": 2.87, "elapsed_time": "0:20:46", "remaining_time": "11:44:06", "throughput": 6085.52, "total_tokens": 7588448} +{"current_steps": 3520, "total_steps": 122600, "loss": 0.1526, "lr": 0.0002870309951060359, "epoch": 0.5742251223491027, "percentage": 2.87, "elapsed_time": "0:20:48", "remaining_time": "11:44:05", "throughput": 6085.44, "total_tokens": 7599264} +{"current_steps": 3525, "total_steps": 122600, "loss": 0.2732, "lr": 0.0002874388254486134, "epoch": 0.5750407830342578, "percentage": 2.88, "elapsed_time": "0:20:50", "remaining_time": "11:44:08", "throughput": 6085.6, "total_tokens": 7611264} +{"current_steps": 3530, "total_steps": 122600, "loss": 0.1366, "lr": 0.00028784665579119085, "epoch": 0.5758564437194127, "percentage": 2.88, "elapsed_time": "0:20:52", "remaining_time": "11:44:02", "throughput": 6085.61, "total_tokens": 7621312} +{"current_steps": 3535, "total_steps": 122600, "loss": 0.2843, "lr": 0.0002882544861337684, "epoch": 0.5766721044045677, "percentage": 2.88, "elapsed_time": "0:20:54", "remaining_time": "11:44:04", "throughput": 6085.63, "total_tokens": 7632736} +{"current_steps": 3540, "total_steps": 122600, "loss": 0.2393, "lr": 0.00028866231647634586, "epoch": 0.5774877650897227, "percentage": 2.89, "elapsed_time": "0:20:55", "remaining_time": "11:44:01", "throughput": 6085.61, "total_tokens": 7643296} +{"current_steps": 3545, "total_steps": 122600, "loss": 0.1396, "lr": 0.00028907014681892333, "epoch": 0.5783034257748777, "percentage": 2.89, "elapsed_time": "0:20:57", "remaining_time": "11:43:58", "throughput": 6085.58, "total_tokens": 7653888} +{"current_steps": 3550, "total_steps": 122600, "loss": 0.089, "lr": 0.0002894779771615008, "epoch": 0.5791190864600326, "percentage": 2.9, "elapsed_time": "0:20:59", "remaining_time": "11:43:55", "throughput": 6085.59, "total_tokens": 7664448} +{"current_steps": 3555, "total_steps": 122600, "loss": 0.0754, "lr": 0.00028988580750407834, "epoch": 0.5799347471451876, "percentage": 2.9, "elapsed_time": "0:21:01", "remaining_time": "11:43:48", "throughput": 6085.47, "total_tokens": 7674176} +{"current_steps": 3560, "total_steps": 122600, "loss": 0.1165, "lr": 0.0002902936378466558, "epoch": 0.5807504078303426, "percentage": 2.9, "elapsed_time": "0:21:02", "remaining_time": "11:43:48", "throughput": 6085.49, "total_tokens": 7685184} +{"current_steps": 3565, "total_steps": 122600, "loss": 0.2567, "lr": 0.00029070146818923324, "epoch": 0.5815660685154975, "percentage": 2.91, "elapsed_time": "0:21:04", "remaining_time": "11:43:46", "throughput": 6085.5, "total_tokens": 7696064} +{"current_steps": 3570, "total_steps": 122600, "loss": 0.2791, "lr": 0.00029110929853181077, "epoch": 0.5823817292006526, "percentage": 2.91, "elapsed_time": "0:21:06", "remaining_time": "11:43:47", "throughput": 6085.5, "total_tokens": 7707328} +{"current_steps": 3575, "total_steps": 122600, "loss": 0.0736, "lr": 0.00029151712887438825, "epoch": 0.5831973898858075, "percentage": 2.92, "elapsed_time": "0:21:08", "remaining_time": "11:43:47", "throughput": 6085.48, "total_tokens": 7718368} +{"current_steps": 3580, "total_steps": 122600, "loss": 0.1135, "lr": 0.0002919249592169658, "epoch": 0.5840130505709625, "percentage": 2.92, "elapsed_time": "0:21:10", "remaining_time": "11:43:49", "throughput": 6085.42, "total_tokens": 7729888} +{"current_steps": 3585, "total_steps": 122600, "loss": 0.2485, "lr": 0.00029233278955954325, "epoch": 0.5848287112561175, "percentage": 2.92, "elapsed_time": "0:21:11", "remaining_time": "11:43:41", "throughput": 6085.34, "total_tokens": 7739424} +{"current_steps": 3590, "total_steps": 122600, "loss": 0.1966, "lr": 0.0002927406199021207, "epoch": 0.5856443719412724, "percentage": 2.93, "elapsed_time": "0:21:13", "remaining_time": "11:43:33", "throughput": 6085.25, "total_tokens": 7748832} +{"current_steps": 3595, "total_steps": 122600, "loss": 0.0973, "lr": 0.0002931484502446982, "epoch": 0.5864600326264274, "percentage": 2.93, "elapsed_time": "0:21:15", "remaining_time": "11:43:34", "throughput": 6085.15, "total_tokens": 7760128} +{"current_steps": 3600, "total_steps": 122600, "loss": 0.1069, "lr": 0.0002935562805872757, "epoch": 0.5872756933115824, "percentage": 2.94, "elapsed_time": "0:21:16", "remaining_time": "11:43:31", "throughput": 6085.15, "total_tokens": 7770688} +{"current_steps": 3605, "total_steps": 122600, "loss": 0.1512, "lr": 0.0002939641109298532, "epoch": 0.5880913539967374, "percentage": 2.94, "elapsed_time": "0:21:18", "remaining_time": "11:43:34", "throughput": 6085.12, "total_tokens": 7782304} +{"current_steps": 3610, "total_steps": 122600, "loss": 0.1987, "lr": 0.0002943719412724307, "epoch": 0.5889070146818923, "percentage": 2.94, "elapsed_time": "0:21:20", "remaining_time": "11:43:32", "throughput": 6085.18, "total_tokens": 7793184} +{"current_steps": 3615, "total_steps": 122600, "loss": 0.1869, "lr": 0.00029477977161500817, "epoch": 0.5897226753670473, "percentage": 2.95, "elapsed_time": "0:21:22", "remaining_time": "11:43:29", "throughput": 6085.15, "total_tokens": 7803648} +{"current_steps": 3620, "total_steps": 122600, "loss": 0.1128, "lr": 0.00029518760195758564, "epoch": 0.5905383360522023, "percentage": 2.95, "elapsed_time": "0:21:24", "remaining_time": "11:43:26", "throughput": 6085.14, "total_tokens": 7814272} +{"current_steps": 3625, "total_steps": 122600, "loss": 0.1743, "lr": 0.0002955954323001631, "epoch": 0.5913539967373572, "percentage": 2.96, "elapsed_time": "0:21:25", "remaining_time": "11:43:24", "throughput": 6085.23, "total_tokens": 7825120} +{"current_steps": 3630, "total_steps": 122600, "loss": 0.135, "lr": 0.00029600326264274065, "epoch": 0.5921696574225123, "percentage": 2.96, "elapsed_time": "0:21:27", "remaining_time": "11:43:29", "throughput": 6085.49, "total_tokens": 7837440} +{"current_steps": 3635, "total_steps": 122600, "loss": 0.0608, "lr": 0.00029641109298531807, "epoch": 0.5929853181076672, "percentage": 2.96, "elapsed_time": "0:21:29", "remaining_time": "11:43:26", "throughput": 6085.49, "total_tokens": 7848064} +{"current_steps": 3640, "total_steps": 122600, "loss": 0.1347, "lr": 0.0002968189233278956, "epoch": 0.5938009787928222, "percentage": 2.97, "elapsed_time": "0:21:31", "remaining_time": "11:43:25", "throughput": 6085.44, "total_tokens": 7858816} +{"current_steps": 3645, "total_steps": 122600, "loss": 0.2535, "lr": 0.0002972267536704731, "epoch": 0.5946166394779772, "percentage": 2.97, "elapsed_time": "0:21:33", "remaining_time": "11:43:23", "throughput": 6085.34, "total_tokens": 7869504} +{"current_steps": 3650, "total_steps": 122600, "loss": 0.0354, "lr": 0.0002976345840130506, "epoch": 0.5954323001631321, "percentage": 2.98, "elapsed_time": "0:21:34", "remaining_time": "11:43:20", "throughput": 6085.11, "total_tokens": 7879712} +{"current_steps": 3655, "total_steps": 122600, "loss": 0.0763, "lr": 0.0002980424143556281, "epoch": 0.5962479608482871, "percentage": 2.98, "elapsed_time": "0:21:36", "remaining_time": "11:43:18", "throughput": 6085.01, "total_tokens": 7890368} +{"current_steps": 3660, "total_steps": 122600, "loss": 0.0591, "lr": 0.0002984502446982055, "epoch": 0.5970636215334421, "percentage": 2.99, "elapsed_time": "0:21:38", "remaining_time": "11:43:14", "throughput": 6084.99, "total_tokens": 7900704} +{"current_steps": 3665, "total_steps": 122600, "loss": 0.2029, "lr": 0.00029885807504078304, "epoch": 0.5978792822185971, "percentage": 2.99, "elapsed_time": "0:21:40", "remaining_time": "11:43:13", "throughput": 6084.99, "total_tokens": 7911776} +{"current_steps": 3670, "total_steps": 122600, "loss": 0.2295, "lr": 0.0002992659053833605, "epoch": 0.598694942903752, "percentage": 2.99, "elapsed_time": "0:21:41", "remaining_time": "11:43:08", "throughput": 6085.0, "total_tokens": 7921984} +{"current_steps": 3675, "total_steps": 122600, "loss": 0.2408, "lr": 0.00029967373572593805, "epoch": 0.5995106035889071, "percentage": 3.0, "elapsed_time": "0:21:43", "remaining_time": "11:43:13", "throughput": 6085.13, "total_tokens": 7934080} +{"current_steps": 3680, "total_steps": 122600, "loss": 0.1547, "lr": 0.0003000815660685155, "epoch": 0.600326264274062, "percentage": 3.0, "elapsed_time": "0:21:45", "remaining_time": "11:43:10", "throughput": 6085.12, "total_tokens": 7944736} +{"current_steps": 3685, "total_steps": 122600, "loss": 0.1293, "lr": 0.000300489396411093, "epoch": 0.6011419249592169, "percentage": 3.01, "elapsed_time": "0:21:47", "remaining_time": "11:43:13", "throughput": 6085.1, "total_tokens": 7956256} +{"current_steps": 3690, "total_steps": 122600, "loss": 0.1261, "lr": 0.0003008972267536705, "epoch": 0.601957585644372, "percentage": 3.01, "elapsed_time": "0:21:49", "remaining_time": "11:43:15", "throughput": 6085.11, "total_tokens": 7967808} +{"current_steps": 3695, "total_steps": 122600, "loss": 0.0563, "lr": 0.00030130505709624795, "epoch": 0.6027732463295269, "percentage": 3.01, "elapsed_time": "0:21:51", "remaining_time": "11:43:18", "throughput": 6085.23, "total_tokens": 7979648} +{"current_steps": 3700, "total_steps": 122600, "loss": 0.0928, "lr": 0.0003017128874388255, "epoch": 0.6035889070146819, "percentage": 3.02, "elapsed_time": "0:21:53", "remaining_time": "11:43:18", "throughput": 6085.31, "total_tokens": 7990944} +{"current_steps": 3705, "total_steps": 122600, "loss": 0.1239, "lr": 0.0003021207177814029, "epoch": 0.6044045676998369, "percentage": 3.02, "elapsed_time": "0:21:54", "remaining_time": "11:43:16", "throughput": 6085.26, "total_tokens": 8001568} +{"current_steps": 3710, "total_steps": 122600, "loss": 0.2942, "lr": 0.00030252854812398044, "epoch": 0.6052202283849919, "percentage": 3.03, "elapsed_time": "0:21:56", "remaining_time": "11:43:17", "throughput": 6085.5, "total_tokens": 8013376} +{"current_steps": 3715, "total_steps": 122600, "loss": 0.2152, "lr": 0.0003029363784665579, "epoch": 0.6060358890701468, "percentage": 3.03, "elapsed_time": "0:21:58", "remaining_time": "11:43:17", "throughput": 6085.54, "total_tokens": 8024512} +{"current_steps": 3720, "total_steps": 122600, "loss": 0.1756, "lr": 0.0003033442088091354, "epoch": 0.6068515497553018, "percentage": 3.03, "elapsed_time": "0:22:00", "remaining_time": "11:43:16", "throughput": 6085.62, "total_tokens": 8035520} +{"current_steps": 3725, "total_steps": 122600, "loss": 0.1294, "lr": 0.0003037520391517129, "epoch": 0.6076672104404568, "percentage": 3.04, "elapsed_time": "0:22:02", "remaining_time": "11:43:17", "throughput": 6085.68, "total_tokens": 8046912} +{"current_steps": 3730, "total_steps": 122600, "loss": 0.1097, "lr": 0.00030415986949429034, "epoch": 0.6084828711256117, "percentage": 3.04, "elapsed_time": "0:22:04", "remaining_time": "11:43:14", "throughput": 6085.66, "total_tokens": 8057472} +{"current_steps": 3735, "total_steps": 122600, "loss": 0.3589, "lr": 0.00030456769983686787, "epoch": 0.6092985318107668, "percentage": 3.05, "elapsed_time": "0:22:05", "remaining_time": "11:43:14", "throughput": 6085.67, "total_tokens": 8068576} +{"current_steps": 3740, "total_steps": 122600, "loss": 0.1123, "lr": 0.00030497553017944535, "epoch": 0.6101141924959217, "percentage": 3.05, "elapsed_time": "0:22:07", "remaining_time": "11:43:16", "throughput": 6085.76, "total_tokens": 8080320} +{"current_steps": 3745, "total_steps": 122600, "loss": 0.2047, "lr": 0.0003053833605220229, "epoch": 0.6109298531810766, "percentage": 3.05, "elapsed_time": "0:22:09", "remaining_time": "11:43:09", "throughput": 6085.76, "total_tokens": 8090144} +{"current_steps": 3750, "total_steps": 122600, "loss": 0.0666, "lr": 0.00030579119086460036, "epoch": 0.6117455138662317, "percentage": 3.06, "elapsed_time": "0:22:11", "remaining_time": "11:43:10", "throughput": 6085.86, "total_tokens": 8101472} +{"current_steps": 3755, "total_steps": 122600, "loss": 0.1242, "lr": 0.0003061990212071778, "epoch": 0.6125611745513866, "percentage": 3.06, "elapsed_time": "0:22:13", "remaining_time": "11:43:10", "throughput": 6085.86, "total_tokens": 8112736} +{"current_steps": 3760, "total_steps": 122600, "loss": 0.1184, "lr": 0.0003066068515497553, "epoch": 0.6133768352365416, "percentage": 3.07, "elapsed_time": "0:22:14", "remaining_time": "11:43:07", "throughput": 6085.81, "total_tokens": 8123296} +{"current_steps": 3765, "total_steps": 122600, "loss": 0.1969, "lr": 0.0003070146818923328, "epoch": 0.6141924959216966, "percentage": 3.07, "elapsed_time": "0:22:16", "remaining_time": "11:43:02", "throughput": 6085.67, "total_tokens": 8133248} +{"current_steps": 3770, "total_steps": 122600, "loss": 0.1198, "lr": 0.0003074225122349103, "epoch": 0.6150081566068516, "percentage": 3.08, "elapsed_time": "0:22:18", "remaining_time": "11:43:03", "throughput": 6085.62, "total_tokens": 8144448} +{"current_steps": 3775, "total_steps": 122600, "loss": 0.1982, "lr": 0.00030783034257748774, "epoch": 0.6158238172920065, "percentage": 3.08, "elapsed_time": "0:22:20", "remaining_time": "11:42:59", "throughput": 6085.55, "total_tokens": 8154656} +{"current_steps": 3780, "total_steps": 122600, "loss": 0.0528, "lr": 0.00030823817292006527, "epoch": 0.6166394779771615, "percentage": 3.08, "elapsed_time": "0:22:21", "remaining_time": "11:42:59", "throughput": 6085.54, "total_tokens": 8165888} +{"current_steps": 3785, "total_steps": 122600, "loss": 0.0759, "lr": 0.00030864600326264275, "epoch": 0.6174551386623165, "percentage": 3.09, "elapsed_time": "0:22:23", "remaining_time": "11:42:52", "throughput": 6085.54, "total_tokens": 8175744} +{"current_steps": 3790, "total_steps": 122600, "loss": 0.1605, "lr": 0.0003090538336052202, "epoch": 0.6182707993474714, "percentage": 3.09, "elapsed_time": "0:22:25", "remaining_time": "11:42:53", "throughput": 6085.46, "total_tokens": 8186880} +{"current_steps": 3795, "total_steps": 122600, "loss": 0.1947, "lr": 0.00030946166394779775, "epoch": 0.6190864600326265, "percentage": 3.1, "elapsed_time": "0:22:26", "remaining_time": "11:42:45", "throughput": 6085.26, "total_tokens": 8196192} +{"current_steps": 3800, "total_steps": 122600, "loss": 0.1919, "lr": 0.0003098694942903752, "epoch": 0.6199021207177814, "percentage": 3.1, "elapsed_time": "0:22:28", "remaining_time": "11:42:37", "throughput": 6085.11, "total_tokens": 8205632} +{"current_steps": 3805, "total_steps": 122600, "loss": 0.1056, "lr": 0.0003102773246329527, "epoch": 0.6207177814029364, "percentage": 3.1, "elapsed_time": "0:22:30", "remaining_time": "11:42:33", "throughput": 6085.11, "total_tokens": 8216032} +{"current_steps": 3810, "total_steps": 122600, "loss": 0.1347, "lr": 0.0003106851549755302, "epoch": 0.6215334420880914, "percentage": 3.11, "elapsed_time": "0:22:32", "remaining_time": "11:42:37", "throughput": 6085.28, "total_tokens": 8228192} +{"current_steps": 3815, "total_steps": 122600, "loss": 0.143, "lr": 0.00031109298531810766, "epoch": 0.6223491027732463, "percentage": 3.11, "elapsed_time": "0:22:33", "remaining_time": "11:42:36", "throughput": 6085.27, "total_tokens": 8239136} +{"current_steps": 3820, "total_steps": 122600, "loss": 0.0687, "lr": 0.0003115008156606852, "epoch": 0.6231647634584013, "percentage": 3.12, "elapsed_time": "0:22:35", "remaining_time": "11:42:31", "throughput": 6085.22, "total_tokens": 8249184} +{"current_steps": 3825, "total_steps": 122600, "loss": 0.1604, "lr": 0.0003119086460032626, "epoch": 0.6239804241435563, "percentage": 3.12, "elapsed_time": "0:22:37", "remaining_time": "11:42:30", "throughput": 6085.33, "total_tokens": 8260288} +{"current_steps": 3830, "total_steps": 122600, "loss": 0.2936, "lr": 0.00031231647634584014, "epoch": 0.6247960848287113, "percentage": 3.12, "elapsed_time": "0:22:39", "remaining_time": "11:42:29", "throughput": 6085.39, "total_tokens": 8271232} +{"current_steps": 3835, "total_steps": 122600, "loss": 0.1355, "lr": 0.0003127243066884176, "epoch": 0.6256117455138662, "percentage": 3.13, "elapsed_time": "0:22:40", "remaining_time": "11:42:24", "throughput": 6085.3, "total_tokens": 8281248} +{"current_steps": 3840, "total_steps": 122600, "loss": 0.1825, "lr": 0.00031313213703099515, "epoch": 0.6264274061990212, "percentage": 3.13, "elapsed_time": "0:22:42", "remaining_time": "11:42:25", "throughput": 6085.45, "total_tokens": 8292864} +{"current_steps": 3845, "total_steps": 122600, "loss": 0.1879, "lr": 0.0003135399673735726, "epoch": 0.6272430668841762, "percentage": 3.14, "elapsed_time": "0:22:44", "remaining_time": "11:42:23", "throughput": 6085.41, "total_tokens": 8303488} +{"current_steps": 3850, "total_steps": 122600, "loss": 0.217, "lr": 0.00031394779771615005, "epoch": 0.6280587275693311, "percentage": 3.14, "elapsed_time": "0:22:46", "remaining_time": "11:42:25", "throughput": 6085.38, "total_tokens": 8315008} +{"current_steps": 3855, "total_steps": 122600, "loss": 0.1261, "lr": 0.0003143556280587276, "epoch": 0.6288743882544862, "percentage": 3.14, "elapsed_time": "0:22:48", "remaining_time": "11:42:22", "throughput": 6085.42, "total_tokens": 8325696} +{"current_steps": 3860, "total_steps": 122600, "loss": 0.1513, "lr": 0.00031476345840130506, "epoch": 0.6296900489396411, "percentage": 3.15, "elapsed_time": "0:22:49", "remaining_time": "11:42:22", "throughput": 6085.53, "total_tokens": 8336960} +{"current_steps": 3865, "total_steps": 122600, "loss": 0.1153, "lr": 0.0003151712887438826, "epoch": 0.6305057096247961, "percentage": 3.15, "elapsed_time": "0:22:51", "remaining_time": "11:42:23", "throughput": 6085.66, "total_tokens": 8348544} +{"current_steps": 3870, "total_steps": 122600, "loss": 0.1825, "lr": 0.00031557911908646, "epoch": 0.6313213703099511, "percentage": 3.16, "elapsed_time": "0:22:53", "remaining_time": "11:42:21", "throughput": 6085.58, "total_tokens": 8359072} +{"current_steps": 3875, "total_steps": 122600, "loss": 0.1694, "lr": 0.00031598694942903754, "epoch": 0.632137030995106, "percentage": 3.16, "elapsed_time": "0:22:55", "remaining_time": "11:42:16", "throughput": 6085.5, "total_tokens": 8369184} +{"current_steps": 3880, "total_steps": 122600, "loss": 0.0905, "lr": 0.000316394779771615, "epoch": 0.632952691680261, "percentage": 3.16, "elapsed_time": "0:22:57", "remaining_time": "11:42:16", "throughput": 6085.54, "total_tokens": 8380352} +{"current_steps": 3885, "total_steps": 122600, "loss": 0.0495, "lr": 0.0003168026101141925, "epoch": 0.633768352365416, "percentage": 3.17, "elapsed_time": "0:22:58", "remaining_time": "11:42:12", "throughput": 6085.56, "total_tokens": 8390880} +{"current_steps": 3890, "total_steps": 122600, "loss": 0.1514, "lr": 0.00031721044045677, "epoch": 0.634584013050571, "percentage": 3.17, "elapsed_time": "0:23:00", "remaining_time": "11:42:12", "throughput": 6085.74, "total_tokens": 8402176} +{"current_steps": 3895, "total_steps": 122600, "loss": 0.0868, "lr": 0.00031761827079934744, "epoch": 0.6353996737357259, "percentage": 3.18, "elapsed_time": "0:23:02", "remaining_time": "11:42:12", "throughput": 6085.73, "total_tokens": 8413280} +{"current_steps": 3900, "total_steps": 122600, "loss": 0.046, "lr": 0.000318026101141925, "epoch": 0.636215334420881, "percentage": 3.18, "elapsed_time": "0:23:04", "remaining_time": "11:42:14", "throughput": 6085.77, "total_tokens": 8424960} +{"current_steps": 3905, "total_steps": 122600, "loss": 0.0594, "lr": 0.00031843393148450245, "epoch": 0.6370309951060359, "percentage": 3.19, "elapsed_time": "0:23:06", "remaining_time": "11:42:14", "throughput": 6085.78, "total_tokens": 8436160} +{"current_steps": 3910, "total_steps": 122600, "loss": 0.1185, "lr": 0.00031884176182708, "epoch": 0.6378466557911908, "percentage": 3.19, "elapsed_time": "0:23:07", "remaining_time": "11:42:08", "throughput": 6085.62, "total_tokens": 8445856} +{"current_steps": 3915, "total_steps": 122600, "loss": 0.5507, "lr": 0.00031924959216965746, "epoch": 0.6386623164763459, "percentage": 3.19, "elapsed_time": "0:23:09", "remaining_time": "11:42:00", "throughput": 6085.49, "total_tokens": 8455264} +{"current_steps": 3920, "total_steps": 122600, "loss": 0.1775, "lr": 0.0003196574225122349, "epoch": 0.6394779771615008, "percentage": 3.2, "elapsed_time": "0:23:11", "remaining_time": "11:41:59", "throughput": 6085.37, "total_tokens": 8465984} +{"current_steps": 3925, "total_steps": 122600, "loss": 0.2106, "lr": 0.0003200652528548124, "epoch": 0.6402936378466558, "percentage": 3.2, "elapsed_time": "0:23:13", "remaining_time": "11:41:59", "throughput": 6085.43, "total_tokens": 8477344} +{"current_steps": 3930, "total_steps": 122600, "loss": 0.1166, "lr": 0.0003204730831973899, "epoch": 0.6411092985318108, "percentage": 3.21, "elapsed_time": "0:23:14", "remaining_time": "11:41:59", "throughput": 6085.48, "total_tokens": 8488544} +{"current_steps": 3935, "total_steps": 122600, "loss": 0.1048, "lr": 0.0003208809135399674, "epoch": 0.6419249592169658, "percentage": 3.21, "elapsed_time": "0:23:16", "remaining_time": "11:41:57", "throughput": 6085.57, "total_tokens": 8499296} +{"current_steps": 3940, "total_steps": 122600, "loss": 0.1382, "lr": 0.00032128874388254484, "epoch": 0.6427406199021207, "percentage": 3.21, "elapsed_time": "0:23:18", "remaining_time": "11:41:59", "throughput": 6085.6, "total_tokens": 8510912} +{"current_steps": 3945, "total_steps": 122600, "loss": 0.1376, "lr": 0.0003216965742251223, "epoch": 0.6435562805872757, "percentage": 3.22, "elapsed_time": "0:23:20", "remaining_time": "11:41:58", "throughput": 6085.63, "total_tokens": 8521920} +{"current_steps": 3950, "total_steps": 122600, "loss": 0.1312, "lr": 0.00032210440456769985, "epoch": 0.6443719412724307, "percentage": 3.22, "elapsed_time": "0:23:22", "remaining_time": "11:41:55", "throughput": 6085.59, "total_tokens": 8532448} +{"current_steps": 3955, "total_steps": 122600, "loss": 0.1139, "lr": 0.0003225122349102773, "epoch": 0.6451876019575856, "percentage": 3.23, "elapsed_time": "0:23:23", "remaining_time": "11:41:56", "throughput": 6085.63, "total_tokens": 8543936} +{"current_steps": 3960, "total_steps": 122600, "loss": 0.0836, "lr": 0.00032292006525285486, "epoch": 0.6460032626427407, "percentage": 3.23, "elapsed_time": "0:23:25", "remaining_time": "11:42:00", "throughput": 6085.8, "total_tokens": 8556160} +{"current_steps": 3965, "total_steps": 122600, "loss": 0.0522, "lr": 0.0003233278955954323, "epoch": 0.6468189233278956, "percentage": 3.23, "elapsed_time": "0:23:27", "remaining_time": "11:41:58", "throughput": 6085.81, "total_tokens": 8566816} +{"current_steps": 3970, "total_steps": 122600, "loss": 0.2619, "lr": 0.0003237357259380098, "epoch": 0.6476345840130505, "percentage": 3.24, "elapsed_time": "0:23:29", "remaining_time": "11:41:53", "throughput": 6085.82, "total_tokens": 8576992} +{"current_steps": 3975, "total_steps": 122600, "loss": 0.2148, "lr": 0.0003241435562805873, "epoch": 0.6484502446982056, "percentage": 3.24, "elapsed_time": "0:23:31", "remaining_time": "11:41:53", "throughput": 6085.85, "total_tokens": 8588224} +{"current_steps": 3980, "total_steps": 122600, "loss": 0.0982, "lr": 0.00032455138662316476, "epoch": 0.6492659053833605, "percentage": 3.25, "elapsed_time": "0:23:32", "remaining_time": "11:41:51", "throughput": 6085.81, "total_tokens": 8598976} +{"current_steps": 3985, "total_steps": 122600, "loss": 0.0892, "lr": 0.0003249592169657423, "epoch": 0.6500815660685155, "percentage": 3.25, "elapsed_time": "0:23:34", "remaining_time": "11:41:47", "throughput": 6085.76, "total_tokens": 8609216} +{"current_steps": 3990, "total_steps": 122600, "loss": 0.1666, "lr": 0.0003253670473083197, "epoch": 0.6508972267536705, "percentage": 3.25, "elapsed_time": "0:23:36", "remaining_time": "11:41:45", "throughput": 6085.78, "total_tokens": 8620032} +{"current_steps": 3995, "total_steps": 122600, "loss": 0.2013, "lr": 0.00032577487765089724, "epoch": 0.6517128874388255, "percentage": 3.26, "elapsed_time": "0:23:38", "remaining_time": "11:41:45", "throughput": 6085.94, "total_tokens": 8631456} +{"current_steps": 4000, "total_steps": 122600, "loss": 0.0616, "lr": 0.0003261827079934747, "epoch": 0.6525285481239804, "percentage": 3.26, "elapsed_time": "0:23:39", "remaining_time": "11:41:41", "throughput": 6085.96, "total_tokens": 8641696} +{"current_steps": 4005, "total_steps": 122600, "loss": 0.1575, "lr": 0.00032659053833605225, "epoch": 0.6533442088091354, "percentage": 3.27, "elapsed_time": "0:23:41", "remaining_time": "11:41:40", "throughput": 6085.91, "total_tokens": 8652576} +{"current_steps": 4010, "total_steps": 122600, "loss": 0.2312, "lr": 0.0003269983686786297, "epoch": 0.6541598694942904, "percentage": 3.27, "elapsed_time": "0:23:43", "remaining_time": "11:41:34", "throughput": 6085.84, "total_tokens": 8662464} +{"current_steps": 4015, "total_steps": 122600, "loss": 0.0936, "lr": 0.00032740619902120715, "epoch": 0.6549755301794453, "percentage": 3.27, "elapsed_time": "0:23:45", "remaining_time": "11:41:32", "throughput": 6085.83, "total_tokens": 8673312} +{"current_steps": 4020, "total_steps": 122600, "loss": 0.1401, "lr": 0.0003278140293637847, "epoch": 0.6557911908646004, "percentage": 3.28, "elapsed_time": "0:23:46", "remaining_time": "11:41:29", "throughput": 6085.86, "total_tokens": 8683904} +{"current_steps": 4025, "total_steps": 122600, "loss": 0.0753, "lr": 0.00032822185970636216, "epoch": 0.6566068515497553, "percentage": 3.28, "elapsed_time": "0:23:48", "remaining_time": "11:41:28", "throughput": 6085.92, "total_tokens": 8694944} +{"current_steps": 4030, "total_steps": 122600, "loss": 0.0465, "lr": 0.0003286296900489397, "epoch": 0.6574225122349103, "percentage": 3.29, "elapsed_time": "0:23:50", "remaining_time": "11:41:30", "throughput": 6085.96, "total_tokens": 8706400} +{"current_steps": 4035, "total_steps": 122600, "loss": 0.1025, "lr": 0.0003290375203915171, "epoch": 0.6582381729200653, "percentage": 3.29, "elapsed_time": "0:23:52", "remaining_time": "11:41:29", "throughput": 6086.01, "total_tokens": 8717504} +{"current_steps": 4040, "total_steps": 122600, "loss": 0.0554, "lr": 0.00032944535073409464, "epoch": 0.6590538336052202, "percentage": 3.3, "elapsed_time": "0:23:54", "remaining_time": "11:41:29", "throughput": 6086.08, "total_tokens": 8728736} +{"current_steps": 4045, "total_steps": 122600, "loss": 0.3712, "lr": 0.0003298531810766721, "epoch": 0.6598694942903752, "percentage": 3.3, "elapsed_time": "0:23:56", "remaining_time": "11:41:28", "throughput": 6086.2, "total_tokens": 8740032} +{"current_steps": 4050, "total_steps": 122600, "loss": 0.1152, "lr": 0.0003302610114192496, "epoch": 0.6606851549755302, "percentage": 3.3, "elapsed_time": "0:23:57", "remaining_time": "11:41:21", "throughput": 6086.01, "total_tokens": 8749280} +{"current_steps": 4055, "total_steps": 122600, "loss": 0.0288, "lr": 0.0003306688417618271, "epoch": 0.6615008156606852, "percentage": 3.31, "elapsed_time": "0:23:59", "remaining_time": "11:41:19", "throughput": 6086.09, "total_tokens": 8760320} +{"current_steps": 4060, "total_steps": 122600, "loss": 0.1337, "lr": 0.00033107667210440455, "epoch": 0.6623164763458401, "percentage": 3.31, "elapsed_time": "0:24:01", "remaining_time": "11:41:18", "throughput": 6086.06, "total_tokens": 8771104} +{"current_steps": 4065, "total_steps": 122600, "loss": 0.0709, "lr": 0.0003314845024469821, "epoch": 0.6631321370309952, "percentage": 3.32, "elapsed_time": "0:24:02", "remaining_time": "11:41:15", "throughput": 6086.06, "total_tokens": 8781664} +{"current_steps": 4070, "total_steps": 122600, "loss": 0.0715, "lr": 0.00033189233278955955, "epoch": 0.6639477977161501, "percentage": 3.32, "elapsed_time": "0:24:04", "remaining_time": "11:41:12", "throughput": 6085.99, "total_tokens": 8792128} +{"current_steps": 4075, "total_steps": 122600, "loss": 0.2244, "lr": 0.00033230016313213703, "epoch": 0.664763458401305, "percentage": 3.32, "elapsed_time": "0:24:06", "remaining_time": "11:41:12", "throughput": 6086.15, "total_tokens": 8803616} +{"current_steps": 4080, "total_steps": 122600, "loss": 0.0932, "lr": 0.0003327079934747145, "epoch": 0.6655791190864601, "percentage": 3.33, "elapsed_time": "0:24:08", "remaining_time": "11:41:07", "throughput": 6086.1, "total_tokens": 8813696} +{"current_steps": 4085, "total_steps": 122600, "loss": 0.1977, "lr": 0.000333115823817292, "epoch": 0.666394779771615, "percentage": 3.33, "elapsed_time": "0:24:09", "remaining_time": "11:41:06", "throughput": 6086.13, "total_tokens": 8824672} +{"current_steps": 4090, "total_steps": 122600, "loss": 0.0225, "lr": 0.0003335236541598695, "epoch": 0.66721044045677, "percentage": 3.34, "elapsed_time": "0:24:11", "remaining_time": "11:41:07", "throughput": 6086.25, "total_tokens": 8836256} +{"current_steps": 4095, "total_steps": 122600, "loss": 0.1962, "lr": 0.000333931484502447, "epoch": 0.668026101141925, "percentage": 3.34, "elapsed_time": "0:24:13", "remaining_time": "11:41:06", "throughput": 6086.3, "total_tokens": 8847168} +{"current_steps": 4100, "total_steps": 122600, "loss": 0.1747, "lr": 0.0003343393148450245, "epoch": 0.6688417618270799, "percentage": 3.34, "elapsed_time": "0:24:14", "remaining_time": "11:40:51", "throughput": 6086.13, "total_tokens": 8855008} +{"current_steps": 4105, "total_steps": 122600, "loss": 0.1966, "lr": 0.00033474714518760194, "epoch": 0.6696574225122349, "percentage": 3.35, "elapsed_time": "0:24:16", "remaining_time": "11:40:49", "throughput": 6086.17, "total_tokens": 8865728} +{"current_steps": 4110, "total_steps": 122600, "loss": 0.1633, "lr": 0.0003351549755301794, "epoch": 0.6704730831973899, "percentage": 3.35, "elapsed_time": "0:24:18", "remaining_time": "11:40:50", "throughput": 6086.35, "total_tokens": 8877440} +{"current_steps": 4115, "total_steps": 122600, "loss": 0.2213, "lr": 0.00033556280587275695, "epoch": 0.6712887438825449, "percentage": 3.36, "elapsed_time": "0:24:20", "remaining_time": "11:40:52", "throughput": 6086.45, "total_tokens": 8889248} +{"current_steps": 4120, "total_steps": 122600, "loss": 0.0987, "lr": 0.0003359706362153344, "epoch": 0.6721044045676998, "percentage": 3.36, "elapsed_time": "0:24:22", "remaining_time": "11:40:53", "throughput": 6086.49, "total_tokens": 8900640} +{"current_steps": 4125, "total_steps": 122600, "loss": 0.1707, "lr": 0.00033637846655791196, "epoch": 0.6729200652528549, "percentage": 3.36, "elapsed_time": "0:24:24", "remaining_time": "11:40:50", "throughput": 6086.51, "total_tokens": 8911232} +{"current_steps": 4130, "total_steps": 122600, "loss": 0.1078, "lr": 0.0003367862969004894, "epoch": 0.6737357259380098, "percentage": 3.37, "elapsed_time": "0:24:25", "remaining_time": "11:40:48", "throughput": 6086.53, "total_tokens": 8921952} +{"current_steps": 4135, "total_steps": 122600, "loss": 0.1293, "lr": 0.0003371941272430669, "epoch": 0.6745513866231647, "percentage": 3.37, "elapsed_time": "0:24:27", "remaining_time": "11:40:51", "throughput": 6086.63, "total_tokens": 8933856} +{"current_steps": 4140, "total_steps": 122600, "loss": 0.061, "lr": 0.0003376019575856444, "epoch": 0.6753670473083198, "percentage": 3.38, "elapsed_time": "0:24:29", "remaining_time": "11:40:50", "throughput": 6086.61, "total_tokens": 8944800} +{"current_steps": 4145, "total_steps": 122600, "loss": 0.0411, "lr": 0.00033800978792822186, "epoch": 0.6761827079934747, "percentage": 3.38, "elapsed_time": "0:24:31", "remaining_time": "11:40:51", "throughput": 6086.59, "total_tokens": 8956352} +{"current_steps": 4150, "total_steps": 122600, "loss": 0.0789, "lr": 0.00033841761827079934, "epoch": 0.6769983686786297, "percentage": 3.38, "elapsed_time": "0:24:33", "remaining_time": "11:40:50", "throughput": 6086.73, "total_tokens": 8967520} +{"current_steps": 4155, "total_steps": 122600, "loss": 0.1638, "lr": 0.0003388254486133768, "epoch": 0.6778140293637847, "percentage": 3.39, "elapsed_time": "0:24:34", "remaining_time": "11:40:46", "throughput": 6086.77, "total_tokens": 8977888} +{"current_steps": 4160, "total_steps": 122600, "loss": 0.0441, "lr": 0.00033923327895595435, "epoch": 0.6786296900489397, "percentage": 3.39, "elapsed_time": "0:24:36", "remaining_time": "11:40:47", "throughput": 6086.89, "total_tokens": 8989440} +{"current_steps": 4165, "total_steps": 122600, "loss": 0.0742, "lr": 0.0003396411092985318, "epoch": 0.6794453507340946, "percentage": 3.4, "elapsed_time": "0:24:38", "remaining_time": "11:40:48", "throughput": 6087.02, "total_tokens": 9000896} +{"current_steps": 4170, "total_steps": 122600, "loss": 0.1311, "lr": 0.0003400489396411093, "epoch": 0.6802610114192496, "percentage": 3.4, "elapsed_time": "0:24:40", "remaining_time": "11:40:46", "throughput": 6087.12, "total_tokens": 9011808} +{"current_steps": 4175, "total_steps": 122600, "loss": 0.1348, "lr": 0.0003404567699836868, "epoch": 0.6810766721044046, "percentage": 3.41, "elapsed_time": "0:24:42", "remaining_time": "11:40:50", "throughput": 6087.28, "total_tokens": 9024096} +{"current_steps": 4180, "total_steps": 122600, "loss": 0.2088, "lr": 0.00034086460032626425, "epoch": 0.6818923327895595, "percentage": 3.41, "elapsed_time": "0:24:44", "remaining_time": "11:40:50", "throughput": 6087.43, "total_tokens": 9035648} +{"current_steps": 4185, "total_steps": 122600, "loss": 0.0742, "lr": 0.0003412724306688418, "epoch": 0.6827079934747146, "percentage": 3.41, "elapsed_time": "0:24:46", "remaining_time": "11:40:46", "throughput": 6087.41, "total_tokens": 9045920} +{"current_steps": 4190, "total_steps": 122600, "loss": 0.0632, "lr": 0.00034168026101141926, "epoch": 0.6835236541598695, "percentage": 3.42, "elapsed_time": "0:24:47", "remaining_time": "11:40:46", "throughput": 6087.48, "total_tokens": 9057088} +{"current_steps": 4195, "total_steps": 122600, "loss": 0.1719, "lr": 0.0003420880913539968, "epoch": 0.6843393148450244, "percentage": 3.42, "elapsed_time": "0:24:49", "remaining_time": "11:40:37", "throughput": 6087.28, "total_tokens": 9066208} +{"current_steps": 4200, "total_steps": 122600, "loss": 0.1812, "lr": 0.0003424959216965742, "epoch": 0.6851549755301795, "percentage": 3.43, "elapsed_time": "0:24:51", "remaining_time": "11:40:36", "throughput": 6087.24, "total_tokens": 9077120} +{"current_steps": 4205, "total_steps": 122600, "loss": 0.2524, "lr": 0.0003429037520391517, "epoch": 0.6859706362153344, "percentage": 3.43, "elapsed_time": "0:24:52", "remaining_time": "11:40:29", "throughput": 6087.17, "total_tokens": 9086592} +{"current_steps": 4210, "total_steps": 122600, "loss": 0.1456, "lr": 0.0003433115823817292, "epoch": 0.6867862969004894, "percentage": 3.43, "elapsed_time": "0:24:54", "remaining_time": "11:40:25", "throughput": 6087.11, "total_tokens": 9096864} +{"current_steps": 4215, "total_steps": 122600, "loss": 0.1622, "lr": 0.0003437194127243067, "epoch": 0.6876019575856444, "percentage": 3.44, "elapsed_time": "0:24:56", "remaining_time": "11:40:22", "throughput": 6087.15, "total_tokens": 9107424} +{"current_steps": 4220, "total_steps": 122600, "loss": 0.0809, "lr": 0.00034412724306688417, "epoch": 0.6884176182707994, "percentage": 3.44, "elapsed_time": "0:24:57", "remaining_time": "11:40:18", "throughput": 6087.03, "total_tokens": 9117696} +{"current_steps": 4225, "total_steps": 122600, "loss": 0.0914, "lr": 0.00034453507340946165, "epoch": 0.6892332789559543, "percentage": 3.45, "elapsed_time": "0:24:59", "remaining_time": "11:40:16", "throughput": 6086.9, "total_tokens": 9128096} +{"current_steps": 4230, "total_steps": 122600, "loss": 0.1346, "lr": 0.0003449429037520392, "epoch": 0.6900489396411092, "percentage": 3.45, "elapsed_time": "0:25:01", "remaining_time": "11:40:15", "throughput": 6086.89, "total_tokens": 9139104} +{"current_steps": 4235, "total_steps": 122600, "loss": 0.1032, "lr": 0.00034535073409461666, "epoch": 0.6908646003262643, "percentage": 3.45, "elapsed_time": "0:25:03", "remaining_time": "11:40:11", "throughput": 6086.85, "total_tokens": 9149408} +{"current_steps": 4240, "total_steps": 122600, "loss": 0.064, "lr": 0.00034575856443719413, "epoch": 0.6916802610114192, "percentage": 3.46, "elapsed_time": "0:25:04", "remaining_time": "11:40:12", "throughput": 6086.85, "total_tokens": 9160672} +{"current_steps": 4245, "total_steps": 122600, "loss": 0.2815, "lr": 0.0003461663947797716, "epoch": 0.6924959216965743, "percentage": 3.46, "elapsed_time": "0:25:06", "remaining_time": "11:40:08", "throughput": 6086.82, "total_tokens": 9171104} +{"current_steps": 4250, "total_steps": 122600, "loss": 0.0785, "lr": 0.0003465742251223491, "epoch": 0.6933115823817292, "percentage": 3.47, "elapsed_time": "0:25:08", "remaining_time": "11:40:05", "throughput": 6086.67, "total_tokens": 9181440} +{"current_steps": 4255, "total_steps": 122600, "loss": 0.0703, "lr": 0.0003469820554649266, "epoch": 0.6941272430668842, "percentage": 3.47, "elapsed_time": "0:25:10", "remaining_time": "11:40:01", "throughput": 6086.61, "total_tokens": 9191488} +{"current_steps": 4260, "total_steps": 122600, "loss": 0.2139, "lr": 0.0003473898858075041, "epoch": 0.6949429037520392, "percentage": 3.47, "elapsed_time": "0:25:12", "remaining_time": "11:40:04", "throughput": 6086.65, "total_tokens": 9203392} +{"current_steps": 4265, "total_steps": 122600, "loss": 0.2403, "lr": 0.0003477977161500816, "epoch": 0.6957585644371941, "percentage": 3.48, "elapsed_time": "0:25:13", "remaining_time": "11:40:03", "throughput": 6086.66, "total_tokens": 9214368} +{"current_steps": 4270, "total_steps": 122600, "loss": 0.062, "lr": 0.00034820554649265905, "epoch": 0.6965742251223491, "percentage": 3.48, "elapsed_time": "0:25:15", "remaining_time": "11:40:01", "throughput": 6086.74, "total_tokens": 9225248} +{"current_steps": 4275, "total_steps": 122600, "loss": 0.1181, "lr": 0.0003486133768352365, "epoch": 0.697389885807504, "percentage": 3.49, "elapsed_time": "0:25:17", "remaining_time": "11:40:01", "throughput": 6086.8, "total_tokens": 9236640} +{"current_steps": 4280, "total_steps": 122600, "loss": 0.0849, "lr": 0.00034902120717781405, "epoch": 0.6982055464926591, "percentage": 3.49, "elapsed_time": "0:25:19", "remaining_time": "11:40:02", "throughput": 6086.84, "total_tokens": 9248000} +{"current_steps": 4285, "total_steps": 122600, "loss": 0.267, "lr": 0.00034942903752039153, "epoch": 0.699021207177814, "percentage": 3.5, "elapsed_time": "0:25:21", "remaining_time": "11:40:00", "throughput": 6086.8, "total_tokens": 9258752} +{"current_steps": 4290, "total_steps": 122600, "loss": 0.1027, "lr": 0.000349836867862969, "epoch": 0.6998368678629691, "percentage": 3.5, "elapsed_time": "0:25:22", "remaining_time": "11:39:56", "throughput": 6086.92, "total_tokens": 9269376} +{"current_steps": 4295, "total_steps": 122600, "loss": 0.2004, "lr": 0.0003502446982055465, "epoch": 0.700652528548124, "percentage": 3.5, "elapsed_time": "0:25:24", "remaining_time": "11:39:59", "throughput": 6086.99, "total_tokens": 9281312} +{"current_steps": 4300, "total_steps": 122600, "loss": 0.0653, "lr": 0.00035065252854812396, "epoch": 0.7014681892332789, "percentage": 3.51, "elapsed_time": "0:25:26", "remaining_time": "11:39:57", "throughput": 6086.91, "total_tokens": 9291936} +{"current_steps": 4305, "total_steps": 122600, "loss": 0.1115, "lr": 0.0003510603588907015, "epoch": 0.702283849918434, "percentage": 3.51, "elapsed_time": "0:25:28", "remaining_time": "11:39:55", "throughput": 6086.89, "total_tokens": 9302528} +{"current_steps": 4310, "total_steps": 122600, "loss": 0.0653, "lr": 0.00035146818923327897, "epoch": 0.7030995106035889, "percentage": 3.52, "elapsed_time": "0:25:30", "remaining_time": "11:39:53", "throughput": 6086.95, "total_tokens": 9313536} +{"current_steps": 4315, "total_steps": 122600, "loss": 0.1076, "lr": 0.00035187601957585644, "epoch": 0.7039151712887439, "percentage": 3.52, "elapsed_time": "0:25:31", "remaining_time": "11:39:51", "throughput": 6087.02, "total_tokens": 9324384} +{"current_steps": 4320, "total_steps": 122600, "loss": 0.2702, "lr": 0.0003522838499184339, "epoch": 0.7047308319738989, "percentage": 3.52, "elapsed_time": "0:25:33", "remaining_time": "11:39:49", "throughput": 6086.97, "total_tokens": 9335104} +{"current_steps": 4325, "total_steps": 122600, "loss": 0.2341, "lr": 0.00035269168026101145, "epoch": 0.7055464926590538, "percentage": 3.53, "elapsed_time": "0:25:35", "remaining_time": "11:39:47", "throughput": 6086.97, "total_tokens": 9345824} +{"current_steps": 4330, "total_steps": 122600, "loss": 0.0657, "lr": 0.0003530995106035889, "epoch": 0.7063621533442088, "percentage": 3.53, "elapsed_time": "0:25:37", "remaining_time": "11:39:47", "throughput": 6087.03, "total_tokens": 9357088} +{"current_steps": 4335, "total_steps": 122600, "loss": 0.2489, "lr": 0.0003535073409461664, "epoch": 0.7071778140293637, "percentage": 3.54, "elapsed_time": "0:25:38", "remaining_time": "11:39:41", "throughput": 6086.92, "total_tokens": 9366784} +{"current_steps": 4340, "total_steps": 122600, "loss": 0.1474, "lr": 0.0003539151712887439, "epoch": 0.7079934747145188, "percentage": 3.54, "elapsed_time": "0:25:40", "remaining_time": "11:39:37", "throughput": 6086.94, "total_tokens": 9377024} +{"current_steps": 4345, "total_steps": 122600, "loss": 0.1546, "lr": 0.00035432300163132136, "epoch": 0.7088091353996737, "percentage": 3.54, "elapsed_time": "0:25:42", "remaining_time": "11:39:40", "throughput": 6087.14, "total_tokens": 9389152} +{"current_steps": 4350, "total_steps": 122600, "loss": 0.1935, "lr": 0.0003547308319738989, "epoch": 0.7096247960848288, "percentage": 3.55, "elapsed_time": "0:25:44", "remaining_time": "11:39:36", "throughput": 6087.13, "total_tokens": 9399616} +{"current_steps": 4355, "total_steps": 122600, "loss": 0.0919, "lr": 0.00035513866231647636, "epoch": 0.7104404567699837, "percentage": 3.55, "elapsed_time": "0:25:45", "remaining_time": "11:39:34", "throughput": 6087.08, "total_tokens": 9410176} +{"current_steps": 4360, "total_steps": 122600, "loss": 0.1165, "lr": 0.0003555464926590539, "epoch": 0.7112561174551386, "percentage": 3.56, "elapsed_time": "0:25:47", "remaining_time": "11:39:35", "throughput": 6087.09, "total_tokens": 9421760} +{"current_steps": 4365, "total_steps": 122600, "loss": 0.0539, "lr": 0.0003559543230016313, "epoch": 0.7120717781402937, "percentage": 3.56, "elapsed_time": "0:25:49", "remaining_time": "11:39:35", "throughput": 6087.17, "total_tokens": 9432960} +{"current_steps": 4370, "total_steps": 122600, "loss": 0.3573, "lr": 0.0003563621533442088, "epoch": 0.7128874388254486, "percentage": 3.56, "elapsed_time": "0:25:51", "remaining_time": "11:39:34", "throughput": 6087.09, "total_tokens": 9443936} +{"current_steps": 4375, "total_steps": 122600, "loss": 0.0536, "lr": 0.0003567699836867863, "epoch": 0.7137030995106036, "percentage": 3.57, "elapsed_time": "0:25:53", "remaining_time": "11:39:26", "throughput": 6086.99, "total_tokens": 9453120} +{"current_steps": 4380, "total_steps": 122600, "loss": 0.1671, "lr": 0.0003571778140293638, "epoch": 0.7145187601957586, "percentage": 3.57, "elapsed_time": "0:25:54", "remaining_time": "11:39:26", "throughput": 6087.13, "total_tokens": 9464480} +{"current_steps": 4385, "total_steps": 122600, "loss": 0.1845, "lr": 0.0003575856443719413, "epoch": 0.7153344208809136, "percentage": 3.58, "elapsed_time": "0:25:56", "remaining_time": "11:39:25", "throughput": 6087.06, "total_tokens": 9475360} +{"current_steps": 4390, "total_steps": 122600, "loss": 0.2689, "lr": 0.00035799347471451875, "epoch": 0.7161500815660685, "percentage": 3.58, "elapsed_time": "0:25:58", "remaining_time": "11:39:19", "throughput": 6086.94, "total_tokens": 9484992} +{"current_steps": 4395, "total_steps": 122600, "loss": 0.0575, "lr": 0.0003584013050570963, "epoch": 0.7169657422512234, "percentage": 3.58, "elapsed_time": "0:25:59", "remaining_time": "11:39:15", "throughput": 6086.91, "total_tokens": 9495296} +{"current_steps": 4400, "total_steps": 122600, "loss": 0.0646, "lr": 0.00035880913539967376, "epoch": 0.7177814029363785, "percentage": 3.59, "elapsed_time": "0:26:01", "remaining_time": "11:39:15", "throughput": 6087.01, "total_tokens": 9506592} +{"current_steps": 4405, "total_steps": 122600, "loss": 0.1364, "lr": 0.00035921696574225124, "epoch": 0.7185970636215334, "percentage": 3.59, "elapsed_time": "0:26:03", "remaining_time": "11:39:11", "throughput": 6087.04, "total_tokens": 9517056} +{"current_steps": 4410, "total_steps": 122600, "loss": 0.0476, "lr": 0.0003596247960848287, "epoch": 0.7194127243066885, "percentage": 3.6, "elapsed_time": "0:26:05", "remaining_time": "11:39:09", "throughput": 6087.04, "total_tokens": 9527808} +{"current_steps": 4415, "total_steps": 122600, "loss": 0.0485, "lr": 0.0003600326264274062, "epoch": 0.7202283849918434, "percentage": 3.6, "elapsed_time": "0:26:07", "remaining_time": "11:39:08", "throughput": 6086.96, "total_tokens": 9538624} +{"current_steps": 4420, "total_steps": 122600, "loss": 0.1898, "lr": 0.0003604404567699837, "epoch": 0.7210440456769984, "percentage": 3.61, "elapsed_time": "0:26:08", "remaining_time": "11:38:59", "throughput": 6086.88, "total_tokens": 9547744} +{"current_steps": 4425, "total_steps": 122600, "loss": 0.0678, "lr": 0.0003608482871125612, "epoch": 0.7218597063621534, "percentage": 3.61, "elapsed_time": "0:26:10", "remaining_time": "11:39:00", "throughput": 6086.93, "total_tokens": 9559072} +{"current_steps": 4430, "total_steps": 122600, "loss": 0.1456, "lr": 0.0003612561174551386, "epoch": 0.7226753670473083, "percentage": 3.61, "elapsed_time": "0:26:12", "remaining_time": "11:39:00", "throughput": 6087.02, "total_tokens": 9570528} +{"current_steps": 4435, "total_steps": 122600, "loss": 0.1853, "lr": 0.00036166394779771615, "epoch": 0.7234910277324633, "percentage": 3.62, "elapsed_time": "0:26:13", "remaining_time": "11:38:56", "throughput": 6087.0, "total_tokens": 9580800} +{"current_steps": 4440, "total_steps": 122600, "loss": 0.1803, "lr": 0.0003620717781402936, "epoch": 0.7243066884176182, "percentage": 3.62, "elapsed_time": "0:26:15", "remaining_time": "11:38:56", "throughput": 6087.02, "total_tokens": 9592064} +{"current_steps": 4445, "total_steps": 122600, "loss": 0.1577, "lr": 0.00036247960848287116, "epoch": 0.7251223491027733, "percentage": 3.63, "elapsed_time": "0:26:17", "remaining_time": "11:38:58", "throughput": 6087.12, "total_tokens": 9603744} +{"current_steps": 4450, "total_steps": 122600, "loss": 0.247, "lr": 0.00036288743882544863, "epoch": 0.7259380097879282, "percentage": 3.63, "elapsed_time": "0:26:19", "remaining_time": "11:38:58", "throughput": 6087.15, "total_tokens": 9615008} +{"current_steps": 4455, "total_steps": 122600, "loss": 0.198, "lr": 0.0003632952691680261, "epoch": 0.7267536704730831, "percentage": 3.63, "elapsed_time": "0:26:21", "remaining_time": "11:38:54", "throughput": 6087.17, "total_tokens": 9625376} +{"current_steps": 4460, "total_steps": 122600, "loss": 0.1478, "lr": 0.0003637030995106036, "epoch": 0.7275693311582382, "percentage": 3.64, "elapsed_time": "0:26:23", "remaining_time": "11:38:52", "throughput": 6087.1, "total_tokens": 9636128} +{"current_steps": 4465, "total_steps": 122600, "loss": 0.2096, "lr": 0.00036411092985318106, "epoch": 0.7283849918433931, "percentage": 3.64, "elapsed_time": "0:26:24", "remaining_time": "11:38:53", "throughput": 6087.24, "total_tokens": 9647808} +{"current_steps": 4470, "total_steps": 122600, "loss": 0.1935, "lr": 0.0003645187601957586, "epoch": 0.7292006525285482, "percentage": 3.65, "elapsed_time": "0:26:26", "remaining_time": "11:38:52", "throughput": 6087.14, "total_tokens": 9658496} +{"current_steps": 4475, "total_steps": 122600, "loss": 0.1422, "lr": 0.00036492659053833607, "epoch": 0.7300163132137031, "percentage": 3.65, "elapsed_time": "0:26:28", "remaining_time": "11:38:49", "throughput": 6087.14, "total_tokens": 9669120} +{"current_steps": 4480, "total_steps": 122600, "loss": 0.1005, "lr": 0.00036533442088091354, "epoch": 0.7308319738988581, "percentage": 3.65, "elapsed_time": "0:26:30", "remaining_time": "11:38:50", "throughput": 6087.15, "total_tokens": 9680448} +{"current_steps": 4485, "total_steps": 122600, "loss": 0.0592, "lr": 0.000365742251223491, "epoch": 0.731647634584013, "percentage": 3.66, "elapsed_time": "0:26:31", "remaining_time": "11:38:45", "throughput": 6087.13, "total_tokens": 9690592} +{"current_steps": 4490, "total_steps": 122600, "loss": 0.1675, "lr": 0.00036615008156606855, "epoch": 0.732463295269168, "percentage": 3.66, "elapsed_time": "0:26:33", "remaining_time": "11:38:45", "throughput": 6087.2, "total_tokens": 9701824} +{"current_steps": 4495, "total_steps": 122600, "loss": 0.2252, "lr": 0.00036655791190864603, "epoch": 0.733278955954323, "percentage": 3.67, "elapsed_time": "0:26:35", "remaining_time": "11:38:42", "throughput": 6087.18, "total_tokens": 9712384} +{"current_steps": 4500, "total_steps": 122600, "loss": 0.2337, "lr": 0.0003669657422512235, "epoch": 0.734094616639478, "percentage": 3.67, "elapsed_time": "0:26:37", "remaining_time": "11:38:40", "throughput": 6087.19, "total_tokens": 9723200} +{"current_steps": 4505, "total_steps": 122600, "loss": 0.138, "lr": 0.000367373572593801, "epoch": 0.734910277324633, "percentage": 3.67, "elapsed_time": "0:26:39", "remaining_time": "11:38:37", "throughput": 6087.13, "total_tokens": 9733536} +{"current_steps": 4510, "total_steps": 122600, "loss": 0.2098, "lr": 0.00036778140293637846, "epoch": 0.7357259380097879, "percentage": 3.68, "elapsed_time": "0:26:40", "remaining_time": "11:38:37", "throughput": 6087.14, "total_tokens": 9744832} +{"current_steps": 4515, "total_steps": 122600, "loss": 0.1022, "lr": 0.000368189233278956, "epoch": 0.736541598694943, "percentage": 3.68, "elapsed_time": "0:26:42", "remaining_time": "11:38:35", "throughput": 6087.09, "total_tokens": 9755520} +{"current_steps": 4520, "total_steps": 122600, "loss": 0.1647, "lr": 0.00036859706362153346, "epoch": 0.7373572593800979, "percentage": 3.69, "elapsed_time": "0:26:44", "remaining_time": "11:38:33", "throughput": 6087.03, "total_tokens": 9766208} +{"current_steps": 4525, "total_steps": 122600, "loss": 0.1981, "lr": 0.0003690048939641109, "epoch": 0.7381729200652528, "percentage": 3.69, "elapsed_time": "0:26:46", "remaining_time": "11:38:36", "throughput": 6087.16, "total_tokens": 9778272} +{"current_steps": 4530, "total_steps": 122600, "loss": 0.1662, "lr": 0.0003694127243066884, "epoch": 0.7389885807504079, "percentage": 3.69, "elapsed_time": "0:26:48", "remaining_time": "11:38:37", "throughput": 6087.17, "total_tokens": 9789760} +{"current_steps": 4535, "total_steps": 122600, "loss": 0.1121, "lr": 0.0003698205546492659, "epoch": 0.7398042414355628, "percentage": 3.7, "elapsed_time": "0:26:50", "remaining_time": "11:38:36", "throughput": 6087.2, "total_tokens": 9800800} +{"current_steps": 4540, "total_steps": 122600, "loss": 0.1574, "lr": 0.0003702283849918434, "epoch": 0.7406199021207178, "percentage": 3.7, "elapsed_time": "0:26:52", "remaining_time": "11:38:39", "throughput": 6087.22, "total_tokens": 9812672} +{"current_steps": 4545, "total_steps": 122600, "loss": 0.2866, "lr": 0.0003706362153344209, "epoch": 0.7414355628058727, "percentage": 3.71, "elapsed_time": "0:26:53", "remaining_time": "11:38:36", "throughput": 6087.2, "total_tokens": 9823232} +{"current_steps": 4550, "total_steps": 122600, "loss": 0.1755, "lr": 0.0003710440456769984, "epoch": 0.7422512234910277, "percentage": 3.71, "elapsed_time": "0:26:55", "remaining_time": "11:38:38", "throughput": 6087.21, "total_tokens": 9834848} +{"current_steps": 4555, "total_steps": 122600, "loss": 0.1221, "lr": 0.00037145187601957585, "epoch": 0.7430668841761827, "percentage": 3.72, "elapsed_time": "0:26:57", "remaining_time": "11:38:38", "throughput": 6087.29, "total_tokens": 9846304} +{"current_steps": 4560, "total_steps": 122600, "loss": 0.0962, "lr": 0.00037185970636215333, "epoch": 0.7438825448613376, "percentage": 3.72, "elapsed_time": "0:26:59", "remaining_time": "11:38:38", "throughput": 6087.35, "total_tokens": 9857472} +{"current_steps": 4565, "total_steps": 122600, "loss": 0.0883, "lr": 0.00037226753670473086, "epoch": 0.7446982055464927, "percentage": 3.72, "elapsed_time": "0:27:01", "remaining_time": "11:38:41", "throughput": 6087.39, "total_tokens": 9869632} +{"current_steps": 4570, "total_steps": 122600, "loss": 0.0608, "lr": 0.00037267536704730834, "epoch": 0.7455138662316476, "percentage": 3.73, "elapsed_time": "0:27:03", "remaining_time": "11:38:43", "throughput": 6087.47, "total_tokens": 9881344} +{"current_steps": 4575, "total_steps": 122600, "loss": 0.1219, "lr": 0.0003730831973898858, "epoch": 0.7463295269168027, "percentage": 3.73, "elapsed_time": "0:27:05", "remaining_time": "11:38:43", "throughput": 6087.47, "total_tokens": 9892640} +{"current_steps": 4580, "total_steps": 122600, "loss": 0.0878, "lr": 0.0003734910277324633, "epoch": 0.7471451876019576, "percentage": 3.74, "elapsed_time": "0:27:06", "remaining_time": "11:38:41", "throughput": 6087.48, "total_tokens": 9903296} +{"current_steps": 4585, "total_steps": 122600, "loss": 0.0736, "lr": 0.0003738988580750408, "epoch": 0.7479608482871125, "percentage": 3.74, "elapsed_time": "0:27:08", "remaining_time": "11:38:38", "throughput": 6087.48, "total_tokens": 9913952} +{"current_steps": 4590, "total_steps": 122600, "loss": 0.0757, "lr": 0.0003743066884176183, "epoch": 0.7487765089722676, "percentage": 3.74, "elapsed_time": "0:27:10", "remaining_time": "11:38:37", "throughput": 6087.49, "total_tokens": 9924928} +{"current_steps": 4595, "total_steps": 122600, "loss": 0.0751, "lr": 0.0003747145187601957, "epoch": 0.7495921696574225, "percentage": 3.75, "elapsed_time": "0:27:12", "remaining_time": "11:38:39", "throughput": 6087.46, "total_tokens": 9936576} +{"current_steps": 4600, "total_steps": 122600, "loss": 0.2172, "lr": 0.00037512234910277325, "epoch": 0.7504078303425775, "percentage": 3.75, "elapsed_time": "0:27:14", "remaining_time": "11:38:40", "throughput": 6087.55, "total_tokens": 9948288} +{"current_steps": 4605, "total_steps": 122600, "loss": 0.1958, "lr": 0.00037553017944535073, "epoch": 0.7512234910277324, "percentage": 3.76, "elapsed_time": "0:27:15", "remaining_time": "11:38:39", "throughput": 6087.48, "total_tokens": 9958976} +{"current_steps": 4610, "total_steps": 122600, "loss": 0.2062, "lr": 0.00037593800978792826, "epoch": 0.7520391517128875, "percentage": 3.76, "elapsed_time": "0:27:17", "remaining_time": "11:38:37", "throughput": 6087.47, "total_tokens": 9969856} +{"current_steps": 4615, "total_steps": 122600, "loss": 0.1369, "lr": 0.00037634584013050573, "epoch": 0.7528548123980424, "percentage": 3.76, "elapsed_time": "0:27:19", "remaining_time": "11:38:40", "throughput": 6087.64, "total_tokens": 9982176} +{"current_steps": 4620, "total_steps": 122600, "loss": 0.1607, "lr": 0.0003767536704730832, "epoch": 0.7536704730831973, "percentage": 3.77, "elapsed_time": "0:27:21", "remaining_time": "11:38:43", "throughput": 6087.75, "total_tokens": 9994176} +{"current_steps": 4625, "total_steps": 122600, "loss": 0.127, "lr": 0.0003771615008156607, "epoch": 0.7544861337683524, "percentage": 3.77, "elapsed_time": "0:27:23", "remaining_time": "11:38:43", "throughput": 6087.76, "total_tokens": 10005504} +{"current_steps": 4630, "total_steps": 122600, "loss": 0.1428, "lr": 0.00037756933115823816, "epoch": 0.7553017944535073, "percentage": 3.78, "elapsed_time": "0:27:25", "remaining_time": "11:38:43", "throughput": 6087.81, "total_tokens": 10016800} +{"current_steps": 4635, "total_steps": 122600, "loss": 0.2997, "lr": 0.0003779771615008157, "epoch": 0.7561174551386624, "percentage": 3.78, "elapsed_time": "0:27:27", "remaining_time": "11:38:37", "throughput": 6087.84, "total_tokens": 10026720} +{"current_steps": 4640, "total_steps": 122600, "loss": 0.1112, "lr": 0.00037838499184339317, "epoch": 0.7569331158238173, "percentage": 3.78, "elapsed_time": "0:27:28", "remaining_time": "11:38:36", "throughput": 6087.93, "total_tokens": 10037664} +{"current_steps": 4645, "total_steps": 122600, "loss": 0.1725, "lr": 0.00037879282218597065, "epoch": 0.7577487765089723, "percentage": 3.79, "elapsed_time": "0:27:30", "remaining_time": "11:38:36", "throughput": 6087.99, "total_tokens": 10049216} +{"current_steps": 4650, "total_steps": 122600, "loss": 0.0869, "lr": 0.0003792006525285481, "epoch": 0.7585644371941273, "percentage": 3.79, "elapsed_time": "0:27:32", "remaining_time": "11:38:38", "throughput": 6088.09, "total_tokens": 10060960} +{"current_steps": 4655, "total_steps": 122600, "loss": 0.1028, "lr": 0.0003796084828711256, "epoch": 0.7593800978792822, "percentage": 3.8, "elapsed_time": "0:27:34", "remaining_time": "11:38:37", "throughput": 6088.12, "total_tokens": 10072096} +{"current_steps": 4660, "total_steps": 122600, "loss": 0.0883, "lr": 0.00038001631321370313, "epoch": 0.7601957585644372, "percentage": 3.8, "elapsed_time": "0:27:36", "remaining_time": "11:38:38", "throughput": 6088.24, "total_tokens": 10083712} +{"current_steps": 4665, "total_steps": 122600, "loss": 0.1009, "lr": 0.00038042414355628055, "epoch": 0.7610114192495921, "percentage": 3.81, "elapsed_time": "0:27:38", "remaining_time": "11:38:37", "throughput": 6088.22, "total_tokens": 10094656} +{"current_steps": 4670, "total_steps": 122600, "loss": 0.0981, "lr": 0.0003808319738988581, "epoch": 0.7618270799347472, "percentage": 3.81, "elapsed_time": "0:27:39", "remaining_time": "11:38:36", "throughput": 6088.16, "total_tokens": 10105568} +{"current_steps": 4675, "total_steps": 122600, "loss": 0.0465, "lr": 0.00038123980424143556, "epoch": 0.7626427406199021, "percentage": 3.81, "elapsed_time": "0:27:41", "remaining_time": "11:38:35", "throughput": 6088.21, "total_tokens": 10116800} +{"current_steps": 4680, "total_steps": 122600, "loss": 0.151, "lr": 0.0003816476345840131, "epoch": 0.763458401305057, "percentage": 3.82, "elapsed_time": "0:27:43", "remaining_time": "11:38:32", "throughput": 6088.23, "total_tokens": 10127360} +{"current_steps": 4685, "total_steps": 122600, "loss": 0.0895, "lr": 0.00038205546492659057, "epoch": 0.7642740619902121, "percentage": 3.82, "elapsed_time": "0:27:45", "remaining_time": "11:38:27", "throughput": 6088.19, "total_tokens": 10137312} +{"current_steps": 4690, "total_steps": 122600, "loss": 0.2656, "lr": 0.000382463295269168, "epoch": 0.765089722675367, "percentage": 3.83, "elapsed_time": "0:27:46", "remaining_time": "11:38:29", "throughput": 6088.19, "total_tokens": 10148960} +{"current_steps": 4695, "total_steps": 122600, "loss": 0.0484, "lr": 0.0003828711256117455, "epoch": 0.765905383360522, "percentage": 3.83, "elapsed_time": "0:27:48", "remaining_time": "11:38:20", "throughput": 6088.01, "total_tokens": 10157856} +{"current_steps": 4700, "total_steps": 122600, "loss": 0.0808, "lr": 0.000383278955954323, "epoch": 0.766721044045677, "percentage": 3.83, "elapsed_time": "0:27:50", "remaining_time": "11:38:19", "throughput": 6088.02, "total_tokens": 10168672} +{"current_steps": 4705, "total_steps": 122600, "loss": 0.0645, "lr": 0.00038368678629690053, "epoch": 0.767536704730832, "percentage": 3.84, "elapsed_time": "0:27:51", "remaining_time": "11:38:13", "throughput": 6087.84, "total_tokens": 10178272} +{"current_steps": 4710, "total_steps": 122600, "loss": 0.0414, "lr": 0.000384094616639478, "epoch": 0.768352365415987, "percentage": 3.84, "elapsed_time": "0:27:53", "remaining_time": "11:38:11", "throughput": 6087.82, "total_tokens": 10188896} +{"current_steps": 4715, "total_steps": 122600, "loss": 0.1535, "lr": 0.0003845024469820555, "epoch": 0.7691680261011419, "percentage": 3.85, "elapsed_time": "0:27:55", "remaining_time": "11:38:07", "throughput": 6087.88, "total_tokens": 10199488} +{"current_steps": 4720, "total_steps": 122600, "loss": 0.1137, "lr": 0.00038491027732463296, "epoch": 0.7699836867862969, "percentage": 3.85, "elapsed_time": "0:27:57", "remaining_time": "11:38:07", "throughput": 6087.96, "total_tokens": 10210720} +{"current_steps": 4725, "total_steps": 122600, "loss": 0.0798, "lr": 0.00038531810766721043, "epoch": 0.7707993474714518, "percentage": 3.85, "elapsed_time": "0:27:58", "remaining_time": "11:38:04", "throughput": 6088.01, "total_tokens": 10221472} +{"current_steps": 4730, "total_steps": 122600, "loss": 0.1995, "lr": 0.00038572593800978796, "epoch": 0.7716150081566069, "percentage": 3.86, "elapsed_time": "0:28:00", "remaining_time": "11:38:03", "throughput": 6088.02, "total_tokens": 10232288} +{"current_steps": 4735, "total_steps": 122600, "loss": 0.1711, "lr": 0.0003861337683523654, "epoch": 0.7724306688417618, "percentage": 3.86, "elapsed_time": "0:28:02", "remaining_time": "11:38:03", "throughput": 6088.06, "total_tokens": 10243616} +{"current_steps": 4740, "total_steps": 122600, "loss": 0.1026, "lr": 0.0003865415986949429, "epoch": 0.7732463295269169, "percentage": 3.87, "elapsed_time": "0:28:04", "remaining_time": "11:38:01", "throughput": 6088.07, "total_tokens": 10254464} +{"current_steps": 4745, "total_steps": 122600, "loss": 0.065, "lr": 0.0003869494290375204, "epoch": 0.7740619902120718, "percentage": 3.87, "elapsed_time": "0:28:06", "remaining_time": "11:38:00", "throughput": 6088.06, "total_tokens": 10265472} +{"current_steps": 4750, "total_steps": 122600, "loss": 0.1856, "lr": 0.0003873572593800979, "epoch": 0.7748776508972267, "percentage": 3.87, "elapsed_time": "0:28:08", "remaining_time": "11:38:01", "throughput": 6088.14, "total_tokens": 10277184} +{"current_steps": 4755, "total_steps": 122600, "loss": 0.1439, "lr": 0.0003877650897226754, "epoch": 0.7756933115823818, "percentage": 3.88, "elapsed_time": "0:28:09", "remaining_time": "11:37:56", "throughput": 6088.1, "total_tokens": 10287104} +{"current_steps": 4760, "total_steps": 122600, "loss": 0.1302, "lr": 0.0003881729200652528, "epoch": 0.7765089722675367, "percentage": 3.88, "elapsed_time": "0:28:11", "remaining_time": "11:37:55", "throughput": 6088.1, "total_tokens": 10297952} +{"current_steps": 4765, "total_steps": 122600, "loss": 0.0866, "lr": 0.00038858075040783035, "epoch": 0.7773246329526917, "percentage": 3.89, "elapsed_time": "0:28:13", "remaining_time": "11:37:55", "throughput": 6088.11, "total_tokens": 10309440} +{"current_steps": 4770, "total_steps": 122600, "loss": 0.2505, "lr": 0.00038898858075040783, "epoch": 0.7781402936378466, "percentage": 3.89, "elapsed_time": "0:28:15", "remaining_time": "11:37:51", "throughput": 6088.1, "total_tokens": 10319680} +{"current_steps": 4775, "total_steps": 122600, "loss": 0.1576, "lr": 0.00038939641109298536, "epoch": 0.7789559543230016, "percentage": 3.89, "elapsed_time": "0:28:16", "remaining_time": "11:37:53", "throughput": 6088.16, "total_tokens": 10331424} +{"current_steps": 4780, "total_steps": 122600, "loss": 0.2242, "lr": 0.00038980424143556284, "epoch": 0.7797716150081566, "percentage": 3.9, "elapsed_time": "0:28:18", "remaining_time": "11:37:49", "throughput": 6088.07, "total_tokens": 10341600} +{"current_steps": 4785, "total_steps": 122600, "loss": 0.2602, "lr": 0.00039021207177814026, "epoch": 0.7805872756933115, "percentage": 3.9, "elapsed_time": "0:28:20", "remaining_time": "11:37:52", "throughput": 6088.11, "total_tokens": 10353504} +{"current_steps": 4790, "total_steps": 122600, "loss": 0.0848, "lr": 0.0003906199021207178, "epoch": 0.7814029363784666, "percentage": 3.91, "elapsed_time": "0:28:22", "remaining_time": "11:37:53", "throughput": 6088.28, "total_tokens": 10365536} +{"current_steps": 4795, "total_steps": 122600, "loss": 0.1797, "lr": 0.00039102773246329527, "epoch": 0.7822185970636215, "percentage": 3.91, "elapsed_time": "0:28:24", "remaining_time": "11:37:48", "throughput": 6088.23, "total_tokens": 10375456} +{"current_steps": 4800, "total_steps": 122600, "loss": 0.1878, "lr": 0.0003914355628058728, "epoch": 0.7830342577487766, "percentage": 3.92, "elapsed_time": "0:28:25", "remaining_time": "11:37:47", "throughput": 6088.24, "total_tokens": 10386336} +{"current_steps": 4805, "total_steps": 122600, "loss": 0.1707, "lr": 0.0003918433931484502, "epoch": 0.7838499184339315, "percentage": 3.92, "elapsed_time": "0:28:27", "remaining_time": "11:37:46", "throughput": 6088.23, "total_tokens": 10397504} +{"current_steps": 4810, "total_steps": 122600, "loss": 0.0681, "lr": 0.00039225122349102775, "epoch": 0.7846655791190864, "percentage": 3.92, "elapsed_time": "0:28:29", "remaining_time": "11:37:42", "throughput": 6088.19, "total_tokens": 10407520} +{"current_steps": 4815, "total_steps": 122600, "loss": 0.1559, "lr": 0.0003926590538336052, "epoch": 0.7854812398042414, "percentage": 3.93, "elapsed_time": "0:28:31", "remaining_time": "11:37:40", "throughput": 6088.22, "total_tokens": 10418368} +{"current_steps": 4820, "total_steps": 122600, "loss": 0.1942, "lr": 0.0003930668841761827, "epoch": 0.7862969004893964, "percentage": 3.93, "elapsed_time": "0:28:32", "remaining_time": "11:37:36", "throughput": 6088.29, "total_tokens": 10428864} +{"current_steps": 4825, "total_steps": 122600, "loss": 0.1266, "lr": 0.00039347471451876023, "epoch": 0.7871125611745514, "percentage": 3.94, "elapsed_time": "0:28:34", "remaining_time": "11:37:37", "throughput": 6088.26, "total_tokens": 10440224} +{"current_steps": 4830, "total_steps": 122600, "loss": 0.1644, "lr": 0.00039388254486133766, "epoch": 0.7879282218597063, "percentage": 3.94, "elapsed_time": "0:28:36", "remaining_time": "11:37:35", "throughput": 6088.21, "total_tokens": 10450912} +{"current_steps": 4835, "total_steps": 122600, "loss": 0.1277, "lr": 0.0003942903752039152, "epoch": 0.7887438825448614, "percentage": 3.94, "elapsed_time": "0:28:38", "remaining_time": "11:37:29", "throughput": 6088.06, "total_tokens": 10460352} +{"current_steps": 4840, "total_steps": 122600, "loss": 0.242, "lr": 0.00039469820554649266, "epoch": 0.7895595432300163, "percentage": 3.95, "elapsed_time": "0:28:40", "remaining_time": "11:37:30", "throughput": 6088.08, "total_tokens": 10471968} +{"current_steps": 4845, "total_steps": 122600, "loss": 0.1504, "lr": 0.0003951060358890702, "epoch": 0.7903752039151712, "percentage": 3.95, "elapsed_time": "0:28:41", "remaining_time": "11:37:23", "throughput": 6087.97, "total_tokens": 10481312} +{"current_steps": 4850, "total_steps": 122600, "loss": 0.1634, "lr": 0.00039551386623164767, "epoch": 0.7911908646003263, "percentage": 3.96, "elapsed_time": "0:28:43", "remaining_time": "11:37:18", "throughput": 6087.93, "total_tokens": 10491136} +{"current_steps": 4855, "total_steps": 122600, "loss": 0.1022, "lr": 0.0003959216965742251, "epoch": 0.7920065252854812, "percentage": 3.96, "elapsed_time": "0:28:44", "remaining_time": "11:37:14", "throughput": 6087.82, "total_tokens": 10501344} +{"current_steps": 4860, "total_steps": 122600, "loss": 0.0808, "lr": 0.0003963295269168026, "epoch": 0.7928221859706363, "percentage": 3.96, "elapsed_time": "0:28:46", "remaining_time": "11:37:12", "throughput": 6087.83, "total_tokens": 10511968} +{"current_steps": 4865, "total_steps": 122600, "loss": 0.139, "lr": 0.0003967373572593801, "epoch": 0.7936378466557912, "percentage": 3.97, "elapsed_time": "0:28:48", "remaining_time": "11:37:11", "throughput": 6087.9, "total_tokens": 10523296} +{"current_steps": 4870, "total_steps": 122600, "loss": 0.068, "lr": 0.00039714518760195763, "epoch": 0.7944535073409462, "percentage": 3.97, "elapsed_time": "0:28:50", "remaining_time": "11:37:06", "throughput": 6087.84, "total_tokens": 10532992} +{"current_steps": 4875, "total_steps": 122600, "loss": 0.1123, "lr": 0.00039755301794453505, "epoch": 0.7952691680261011, "percentage": 3.98, "elapsed_time": "0:28:52", "remaining_time": "11:37:07", "throughput": 6087.88, "total_tokens": 10544768} +{"current_steps": 4880, "total_steps": 122600, "loss": 0.049, "lr": 0.00039796084828711253, "epoch": 0.7960848287112561, "percentage": 3.98, "elapsed_time": "0:28:53", "remaining_time": "11:37:05", "throughput": 6087.95, "total_tokens": 10555680} +{"current_steps": 4885, "total_steps": 122600, "loss": 0.0519, "lr": 0.00039836867862969006, "epoch": 0.7969004893964111, "percentage": 3.98, "elapsed_time": "0:28:55", "remaining_time": "11:37:03", "throughput": 6087.99, "total_tokens": 10566304} +{"current_steps": 4890, "total_steps": 122600, "loss": 0.0219, "lr": 0.00039877650897226754, "epoch": 0.797716150081566, "percentage": 3.99, "elapsed_time": "0:28:57", "remaining_time": "11:36:57", "throughput": 6087.93, "total_tokens": 10576128} +{"current_steps": 4895, "total_steps": 122600, "loss": 0.032, "lr": 0.00039918433931484507, "epoch": 0.7985318107667211, "percentage": 3.99, "elapsed_time": "0:28:59", "remaining_time": "11:36:56", "throughput": 6087.97, "total_tokens": 10587072} +{"current_steps": 4900, "total_steps": 122600, "loss": 0.087, "lr": 0.0003995921696574225, "epoch": 0.799347471451876, "percentage": 4.0, "elapsed_time": "0:29:00", "remaining_time": "11:36:53", "throughput": 6087.96, "total_tokens": 10597696} +{"current_steps": 4905, "total_steps": 122600, "loss": 0.1629, "lr": 0.0004, "epoch": 0.8001631321370309, "percentage": 4.0, "elapsed_time": "0:29:02", "remaining_time": "11:36:53", "throughput": 6088.05, "total_tokens": 10608928} +{"current_steps": 4910, "total_steps": 122600, "loss": 0.04, "lr": 0.0004004078303425775, "epoch": 0.800978792822186, "percentage": 4.0, "elapsed_time": "0:29:04", "remaining_time": "11:36:52", "throughput": 6087.98, "total_tokens": 10619872} +{"current_steps": 4915, "total_steps": 122600, "loss": 0.1131, "lr": 0.00040081566068515497, "epoch": 0.8017944535073409, "percentage": 4.01, "elapsed_time": "0:29:06", "remaining_time": "11:36:52", "throughput": 6088.02, "total_tokens": 10631360} +{"current_steps": 4920, "total_steps": 122600, "loss": 0.0874, "lr": 0.0004012234910277325, "epoch": 0.802610114192496, "percentage": 4.01, "elapsed_time": "0:29:08", "remaining_time": "11:36:53", "throughput": 6088.05, "total_tokens": 10642880} +{"current_steps": 4925, "total_steps": 122600, "loss": 0.0408, "lr": 0.0004016313213703099, "epoch": 0.8034257748776509, "percentage": 4.02, "elapsed_time": "0:29:09", "remaining_time": "11:36:45", "throughput": 6088.02, "total_tokens": 10651968} +{"current_steps": 4930, "total_steps": 122600, "loss": 0.246, "lr": 0.00040203915171288746, "epoch": 0.8042414355628059, "percentage": 4.02, "elapsed_time": "0:29:11", "remaining_time": "11:36:41", "throughput": 6087.98, "total_tokens": 10662240} +{"current_steps": 4935, "total_steps": 122600, "loss": 0.0533, "lr": 0.00040244698205546493, "epoch": 0.8050570962479608, "percentage": 4.03, "elapsed_time": "0:29:13", "remaining_time": "11:36:38", "throughput": 6088.07, "total_tokens": 10672864} +{"current_steps": 4940, "total_steps": 122600, "loss": 0.1148, "lr": 0.00040285481239804246, "epoch": 0.8058727569331158, "percentage": 4.03, "elapsed_time": "0:29:14", "remaining_time": "11:36:37", "throughput": 6088.12, "total_tokens": 10683936} +{"current_steps": 4945, "total_steps": 122600, "loss": 0.2105, "lr": 0.0004032626427406199, "epoch": 0.8066884176182708, "percentage": 4.03, "elapsed_time": "0:29:16", "remaining_time": "11:36:37", "throughput": 6088.07, "total_tokens": 10695104} +{"current_steps": 4950, "total_steps": 122600, "loss": 0.1674, "lr": 0.00040367047308319736, "epoch": 0.8075040783034257, "percentage": 4.04, "elapsed_time": "0:29:18", "remaining_time": "11:36:37", "throughput": 6088.14, "total_tokens": 10706528} +{"current_steps": 4955, "total_steps": 122600, "loss": 0.1362, "lr": 0.0004040783034257749, "epoch": 0.8083197389885808, "percentage": 4.04, "elapsed_time": "0:29:20", "remaining_time": "11:36:36", "throughput": 6088.24, "total_tokens": 10717728} +{"current_steps": 4960, "total_steps": 122600, "loss": 0.1047, "lr": 0.00040448613376835237, "epoch": 0.8091353996737357, "percentage": 4.05, "elapsed_time": "0:29:21", "remaining_time": "11:36:30", "throughput": 6088.11, "total_tokens": 10727104} +{"current_steps": 4965, "total_steps": 122600, "loss": 0.1412, "lr": 0.0004048939641109299, "epoch": 0.8099510603588908, "percentage": 4.05, "elapsed_time": "0:29:23", "remaining_time": "11:36:28", "throughput": 6088.1, "total_tokens": 10737952} +{"current_steps": 4970, "total_steps": 122600, "loss": 0.2602, "lr": 0.0004053017944535073, "epoch": 0.8107667210440457, "percentage": 4.05, "elapsed_time": "0:29:25", "remaining_time": "11:36:22", "throughput": 6088.13, "total_tokens": 10747744} +{"current_steps": 4975, "total_steps": 122600, "loss": 0.1059, "lr": 0.00040570962479608485, "epoch": 0.8115823817292006, "percentage": 4.06, "elapsed_time": "0:29:27", "remaining_time": "11:36:18", "throughput": 6088.08, "total_tokens": 10757920} +{"current_steps": 4980, "total_steps": 122600, "loss": 0.0414, "lr": 0.00040611745513866233, "epoch": 0.8123980424143556, "percentage": 4.06, "elapsed_time": "0:29:28", "remaining_time": "11:36:16", "throughput": 6088.16, "total_tokens": 10768896} +{"current_steps": 4985, "total_steps": 122600, "loss": 0.0599, "lr": 0.0004065252854812398, "epoch": 0.8132137030995106, "percentage": 4.07, "elapsed_time": "0:29:30", "remaining_time": "11:36:13", "throughput": 6088.12, "total_tokens": 10779136} +{"current_steps": 4990, "total_steps": 122600, "loss": 0.1839, "lr": 0.00040693311582381734, "epoch": 0.8140293637846656, "percentage": 4.07, "elapsed_time": "0:29:32", "remaining_time": "11:36:08", "throughput": 6088.11, "total_tokens": 10789280} +{"current_steps": 4995, "total_steps": 122600, "loss": 0.1297, "lr": 0.00040734094616639476, "epoch": 0.8148450244698205, "percentage": 4.07, "elapsed_time": "0:29:33", "remaining_time": "11:36:07", "throughput": 6088.16, "total_tokens": 10800192} +{"current_steps": 5000, "total_steps": 122600, "loss": 0.0795, "lr": 0.0004077487765089723, "epoch": 0.8156606851549756, "percentage": 4.08, "elapsed_time": "0:29:35", "remaining_time": "11:36:06", "throughput": 6088.19, "total_tokens": 10811296} +{"current_steps": 5005, "total_steps": 122600, "loss": 0.0298, "lr": 0.00040815660685154977, "epoch": 0.8164763458401305, "percentage": 4.08, "elapsed_time": "0:29:37", "remaining_time": "11:36:04", "throughput": 6088.31, "total_tokens": 10822272} +{"current_steps": 5010, "total_steps": 122600, "loss": 0.0643, "lr": 0.00040856443719412724, "epoch": 0.8172920065252854, "percentage": 4.09, "elapsed_time": "0:29:39", "remaining_time": "11:36:02", "throughput": 6088.25, "total_tokens": 10832832} +{"current_steps": 5015, "total_steps": 122600, "loss": 0.2636, "lr": 0.00040897226753670477, "epoch": 0.8181076672104405, "percentage": 4.09, "elapsed_time": "0:29:41", "remaining_time": "11:35:58", "throughput": 6088.11, "total_tokens": 10843008} +{"current_steps": 5020, "total_steps": 122600, "loss": 0.0742, "lr": 0.0004093800978792822, "epoch": 0.8189233278955954, "percentage": 4.09, "elapsed_time": "0:29:43", "remaining_time": "11:36:04", "throughput": 6088.32, "total_tokens": 10856000} +{"current_steps": 5025, "total_steps": 122600, "loss": 0.0642, "lr": 0.0004097879282218597, "epoch": 0.8197389885807504, "percentage": 4.1, "elapsed_time": "0:29:44", "remaining_time": "11:36:00", "throughput": 6088.22, "total_tokens": 10866144} +{"current_steps": 5030, "total_steps": 122600, "loss": 0.3499, "lr": 0.0004101957585644372, "epoch": 0.8205546492659054, "percentage": 4.1, "elapsed_time": "0:29:46", "remaining_time": "11:36:00", "throughput": 6088.2, "total_tokens": 10877312} +{"current_steps": 5035, "total_steps": 122600, "loss": 0.1298, "lr": 0.00041060358890701473, "epoch": 0.8213703099510603, "percentage": 4.11, "elapsed_time": "0:29:48", "remaining_time": "11:35:54", "throughput": 6088.12, "total_tokens": 10887040} +{"current_steps": 5040, "total_steps": 122600, "loss": 0.0691, "lr": 0.00041101141924959215, "epoch": 0.8221859706362153, "percentage": 4.11, "elapsed_time": "0:29:49", "remaining_time": "11:35:51", "throughput": 6088.04, "total_tokens": 10897440} +{"current_steps": 5045, "total_steps": 122600, "loss": 0.0708, "lr": 0.00041141924959216963, "epoch": 0.8230016313213703, "percentage": 4.12, "elapsed_time": "0:29:51", "remaining_time": "11:35:54", "throughput": 6088.15, "total_tokens": 10909504} +{"current_steps": 5050, "total_steps": 122600, "loss": 0.3704, "lr": 0.00041182707993474716, "epoch": 0.8238172920065253, "percentage": 4.12, "elapsed_time": "0:29:53", "remaining_time": "11:35:57", "throughput": 6088.26, "total_tokens": 10921728} +{"current_steps": 5055, "total_steps": 122600, "loss": 0.0518, "lr": 0.00041223491027732464, "epoch": 0.8246329526916802, "percentage": 4.12, "elapsed_time": "0:29:55", "remaining_time": "11:35:52", "throughput": 6088.3, "total_tokens": 10931776} +{"current_steps": 5060, "total_steps": 122600, "loss": 0.0695, "lr": 0.00041264274061990217, "epoch": 0.8254486133768353, "percentage": 4.13, "elapsed_time": "0:29:57", "remaining_time": "11:35:51", "throughput": 6088.27, "total_tokens": 10942784} +{"current_steps": 5065, "total_steps": 122600, "loss": 0.0299, "lr": 0.0004130505709624796, "epoch": 0.8262642740619902, "percentage": 4.13, "elapsed_time": "0:29:59", "remaining_time": "11:35:51", "throughput": 6088.4, "total_tokens": 10954272} +{"current_steps": 5070, "total_steps": 122600, "loss": 0.1194, "lr": 0.0004134584013050571, "epoch": 0.8270799347471451, "percentage": 4.14, "elapsed_time": "0:30:00", "remaining_time": "11:35:48", "throughput": 6088.45, "total_tokens": 10964864} +{"current_steps": 5075, "total_steps": 122600, "loss": 0.1849, "lr": 0.0004138662316476346, "epoch": 0.8278955954323002, "percentage": 4.14, "elapsed_time": "0:30:02", "remaining_time": "11:35:44", "throughput": 6088.43, "total_tokens": 10975104} +{"current_steps": 5080, "total_steps": 122600, "loss": 0.0728, "lr": 0.0004142740619902121, "epoch": 0.8287112561174551, "percentage": 4.14, "elapsed_time": "0:30:04", "remaining_time": "11:35:40", "throughput": 6088.33, "total_tokens": 10985152} +{"current_steps": 5085, "total_steps": 122600, "loss": 0.0663, "lr": 0.0004146818923327896, "epoch": 0.8295269168026101, "percentage": 4.15, "elapsed_time": "0:30:06", "remaining_time": "11:35:40", "throughput": 6088.41, "total_tokens": 10996640} +{"current_steps": 5090, "total_steps": 122600, "loss": 0.1359, "lr": 0.00041508972267536703, "epoch": 0.8303425774877651, "percentage": 4.15, "elapsed_time": "0:30:07", "remaining_time": "11:35:38", "throughput": 6088.45, "total_tokens": 11007328} +{"current_steps": 5095, "total_steps": 122600, "loss": 0.1779, "lr": 0.00041549755301794456, "epoch": 0.8311582381729201, "percentage": 4.16, "elapsed_time": "0:30:09", "remaining_time": "11:35:34", "throughput": 6088.46, "total_tokens": 11017760} +{"current_steps": 5100, "total_steps": 122600, "loss": 0.0765, "lr": 0.00041590538336052203, "epoch": 0.831973898858075, "percentage": 4.16, "elapsed_time": "0:30:11", "remaining_time": "11:35:33", "throughput": 6088.45, "total_tokens": 11028768} +{"current_steps": 5105, "total_steps": 122600, "loss": 0.269, "lr": 0.00041631321370309957, "epoch": 0.83278955954323, "percentage": 4.16, "elapsed_time": "0:30:13", "remaining_time": "11:35:30", "throughput": 6088.49, "total_tokens": 11039360} +{"current_steps": 5110, "total_steps": 122600, "loss": 0.0634, "lr": 0.000416721044045677, "epoch": 0.833605220228385, "percentage": 4.17, "elapsed_time": "0:30:14", "remaining_time": "11:35:29", "throughput": 6088.53, "total_tokens": 11050272} +{"current_steps": 5115, "total_steps": 122600, "loss": 0.3043, "lr": 0.00041712887438825446, "epoch": 0.8344208809135399, "percentage": 4.17, "elapsed_time": "0:30:16", "remaining_time": "11:35:26", "throughput": 6088.55, "total_tokens": 11060736} +{"current_steps": 5120, "total_steps": 122600, "loss": 0.1503, "lr": 0.000417536704730832, "epoch": 0.835236541598695, "percentage": 4.18, "elapsed_time": "0:30:18", "remaining_time": "11:35:21", "throughput": 6088.44, "total_tokens": 11070688} +{"current_steps": 5125, "total_steps": 122600, "loss": 0.2831, "lr": 0.00041794453507340947, "epoch": 0.8360522022838499, "percentage": 4.18, "elapsed_time": "0:30:19", "remaining_time": "11:35:17", "throughput": 6088.38, "total_tokens": 11080800} +{"current_steps": 5130, "total_steps": 122600, "loss": 0.0262, "lr": 0.000418352365415987, "epoch": 0.8368678629690048, "percentage": 4.18, "elapsed_time": "0:30:21", "remaining_time": "11:35:15", "throughput": 6088.42, "total_tokens": 11091680} +{"current_steps": 5135, "total_steps": 122600, "loss": 0.1475, "lr": 0.0004187601957585644, "epoch": 0.8376835236541599, "percentage": 4.19, "elapsed_time": "0:30:23", "remaining_time": "11:35:14", "throughput": 6088.46, "total_tokens": 11102656} +{"current_steps": 5140, "total_steps": 122600, "loss": 0.0642, "lr": 0.0004191680261011419, "epoch": 0.8384991843393148, "percentage": 4.19, "elapsed_time": "0:30:25", "remaining_time": "11:35:11", "throughput": 6088.41, "total_tokens": 11112960} +{"current_steps": 5145, "total_steps": 122600, "loss": 0.098, "lr": 0.00041957585644371943, "epoch": 0.8393148450244698, "percentage": 4.2, "elapsed_time": "0:30:27", "remaining_time": "11:35:11", "throughput": 6088.46, "total_tokens": 11124512} +{"current_steps": 5150, "total_steps": 122600, "loss": 0.2984, "lr": 0.0004199836867862969, "epoch": 0.8401305057096248, "percentage": 4.2, "elapsed_time": "0:30:28", "remaining_time": "11:35:08", "throughput": 6088.54, "total_tokens": 11134976} +{"current_steps": 5155, "total_steps": 122600, "loss": 0.1555, "lr": 0.00042039151712887444, "epoch": 0.8409461663947798, "percentage": 4.2, "elapsed_time": "0:30:30", "remaining_time": "11:35:07", "throughput": 6088.58, "total_tokens": 11146144} +{"current_steps": 5160, "total_steps": 122600, "loss": 0.0533, "lr": 0.00042079934747145186, "epoch": 0.8417618270799347, "percentage": 4.21, "elapsed_time": "0:30:32", "remaining_time": "11:35:06", "throughput": 6088.57, "total_tokens": 11157152} +{"current_steps": 5165, "total_steps": 122600, "loss": 0.0976, "lr": 0.0004212071778140294, "epoch": 0.8425774877650897, "percentage": 4.21, "elapsed_time": "0:30:34", "remaining_time": "11:34:59", "throughput": 6088.44, "total_tokens": 11166400} +{"current_steps": 5170, "total_steps": 122600, "loss": 0.0887, "lr": 0.00042161500815660687, "epoch": 0.8433931484502447, "percentage": 4.22, "elapsed_time": "0:30:35", "remaining_time": "11:35:00", "throughput": 6088.5, "total_tokens": 11178016} +{"current_steps": 5175, "total_steps": 122600, "loss": 0.1065, "lr": 0.00042202283849918434, "epoch": 0.8442088091353996, "percentage": 4.22, "elapsed_time": "0:30:37", "remaining_time": "11:34:59", "throughput": 6088.55, "total_tokens": 11188992} +{"current_steps": 5180, "total_steps": 122600, "loss": 0.0694, "lr": 0.0004224306688417618, "epoch": 0.8450244698205547, "percentage": 4.23, "elapsed_time": "0:30:39", "remaining_time": "11:34:58", "throughput": 6088.55, "total_tokens": 11200160} +{"current_steps": 5185, "total_steps": 122600, "loss": 0.2449, "lr": 0.0004228384991843393, "epoch": 0.8458401305057096, "percentage": 4.23, "elapsed_time": "0:30:41", "remaining_time": "11:34:59", "throughput": 6088.62, "total_tokens": 11211776} +{"current_steps": 5190, "total_steps": 122600, "loss": 0.2644, "lr": 0.00042324632952691683, "epoch": 0.8466557911908646, "percentage": 4.23, "elapsed_time": "0:30:43", "remaining_time": "11:35:00", "throughput": 6088.6, "total_tokens": 11223328} +{"current_steps": 5195, "total_steps": 122600, "loss": 0.1336, "lr": 0.0004236541598694943, "epoch": 0.8474714518760196, "percentage": 4.24, "elapsed_time": "0:30:45", "remaining_time": "11:35:00", "throughput": 6088.59, "total_tokens": 11234528} +{"current_steps": 5200, "total_steps": 122600, "loss": 0.1566, "lr": 0.00042406199021207183, "epoch": 0.8482871125611745, "percentage": 4.24, "elapsed_time": "0:30:47", "remaining_time": "11:35:00", "throughput": 6088.68, "total_tokens": 11245920} +{"current_steps": 5205, "total_steps": 122600, "loss": 0.1481, "lr": 0.00042446982055464926, "epoch": 0.8491027732463295, "percentage": 4.25, "elapsed_time": "0:30:48", "remaining_time": "11:35:02", "throughput": 6088.79, "total_tokens": 11258080} +{"current_steps": 5210, "total_steps": 122600, "loss": 0.1028, "lr": 0.00042487765089722673, "epoch": 0.8499184339314845, "percentage": 4.25, "elapsed_time": "0:30:50", "remaining_time": "11:35:05", "throughput": 6088.85, "total_tokens": 11270176} +{"current_steps": 5215, "total_steps": 122600, "loss": 0.0622, "lr": 0.00042528548123980426, "epoch": 0.8507340946166395, "percentage": 4.25, "elapsed_time": "0:30:52", "remaining_time": "11:35:06", "throughput": 6088.88, "total_tokens": 11282016} +{"current_steps": 5220, "total_steps": 122600, "loss": 0.0544, "lr": 0.00042569331158238174, "epoch": 0.8515497553017944, "percentage": 4.26, "elapsed_time": "0:30:54", "remaining_time": "11:35:03", "throughput": 6088.89, "total_tokens": 11292320} +{"current_steps": 5225, "total_steps": 122600, "loss": 0.1094, "lr": 0.00042610114192495927, "epoch": 0.8523654159869495, "percentage": 4.26, "elapsed_time": "0:30:56", "remaining_time": "11:35:00", "throughput": 6088.92, "total_tokens": 11303040} +{"current_steps": 5230, "total_steps": 122600, "loss": 0.1155, "lr": 0.0004265089722675367, "epoch": 0.8531810766721044, "percentage": 4.27, "elapsed_time": "0:30:57", "remaining_time": "11:34:55", "throughput": 6088.81, "total_tokens": 11312672} +{"current_steps": 5235, "total_steps": 122600, "loss": 0.0373, "lr": 0.00042691680261011417, "epoch": 0.8539967373572593, "percentage": 4.27, "elapsed_time": "0:30:59", "remaining_time": "11:34:54", "throughput": 6088.75, "total_tokens": 11323488} +{"current_steps": 5240, "total_steps": 122600, "loss": 0.0487, "lr": 0.0004273246329526917, "epoch": 0.8548123980424144, "percentage": 4.27, "elapsed_time": "0:31:01", "remaining_time": "11:34:51", "throughput": 6088.78, "total_tokens": 11334176} +{"current_steps": 5245, "total_steps": 122600, "loss": 0.1613, "lr": 0.0004277324632952692, "epoch": 0.8556280587275693, "percentage": 4.28, "elapsed_time": "0:31:03", "remaining_time": "11:34:51", "throughput": 6088.84, "total_tokens": 11345632} +{"current_steps": 5250, "total_steps": 122600, "loss": 0.0364, "lr": 0.00042814029363784665, "epoch": 0.8564437194127243, "percentage": 4.28, "elapsed_time": "0:31:04", "remaining_time": "11:34:46", "throughput": 6088.84, "total_tokens": 11355552} +{"current_steps": 5255, "total_steps": 122600, "loss": 0.1908, "lr": 0.00042854812398042413, "epoch": 0.8572593800978793, "percentage": 4.29, "elapsed_time": "0:31:06", "remaining_time": "11:34:47", "throughput": 6088.85, "total_tokens": 11367072} +{"current_steps": 5260, "total_steps": 122600, "loss": 0.2137, "lr": 0.00042895595432300166, "epoch": 0.8580750407830342, "percentage": 4.29, "elapsed_time": "0:31:08", "remaining_time": "11:34:42", "throughput": 6088.88, "total_tokens": 11377120} +{"current_steps": 5265, "total_steps": 122600, "loss": 0.0982, "lr": 0.00042936378466557914, "epoch": 0.8588907014681892, "percentage": 4.29, "elapsed_time": "0:31:10", "remaining_time": "11:34:41", "throughput": 6089.0, "total_tokens": 11388416} +{"current_steps": 5270, "total_steps": 122600, "loss": 0.1723, "lr": 0.0004297716150081566, "epoch": 0.8597063621533442, "percentage": 4.3, "elapsed_time": "0:31:12", "remaining_time": "11:34:37", "throughput": 6088.93, "total_tokens": 11398528} +{"current_steps": 5275, "total_steps": 122600, "loss": 0.0976, "lr": 0.0004301794453507341, "epoch": 0.8605220228384992, "percentage": 4.3, "elapsed_time": "0:31:13", "remaining_time": "11:34:33", "throughput": 6088.9, "total_tokens": 11408576} +{"current_steps": 5280, "total_steps": 122600, "loss": 0.0709, "lr": 0.00043058727569331157, "epoch": 0.8613376835236541, "percentage": 4.31, "elapsed_time": "0:31:15", "remaining_time": "11:34:33", "throughput": 6088.92, "total_tokens": 11420000} +{"current_steps": 5285, "total_steps": 122600, "loss": 0.1581, "lr": 0.0004309951060358891, "epoch": 0.8621533442088092, "percentage": 4.31, "elapsed_time": "0:31:17", "remaining_time": "11:34:31", "throughput": 6088.92, "total_tokens": 11430528} +{"current_steps": 5290, "total_steps": 122600, "loss": 0.0703, "lr": 0.0004314029363784666, "epoch": 0.8629690048939641, "percentage": 4.31, "elapsed_time": "0:31:18", "remaining_time": "11:34:27", "throughput": 6088.94, "total_tokens": 11440992} +{"current_steps": 5295, "total_steps": 122600, "loss": 0.1036, "lr": 0.0004318107667210441, "epoch": 0.863784665579119, "percentage": 4.32, "elapsed_time": "0:31:20", "remaining_time": "11:34:26", "throughput": 6088.89, "total_tokens": 11451712} +{"current_steps": 5300, "total_steps": 122600, "loss": 0.1564, "lr": 0.0004322185970636215, "epoch": 0.8646003262642741, "percentage": 4.32, "elapsed_time": "0:31:22", "remaining_time": "11:34:27", "throughput": 6089.0, "total_tokens": 11463584} +{"current_steps": 5305, "total_steps": 122600, "loss": 0.0607, "lr": 0.000432626427406199, "epoch": 0.865415986949429, "percentage": 4.33, "elapsed_time": "0:31:24", "remaining_time": "11:34:26", "throughput": 6089.02, "total_tokens": 11474560} +{"current_steps": 5310, "total_steps": 122600, "loss": 0.0883, "lr": 0.00043303425774877653, "epoch": 0.866231647634584, "percentage": 4.33, "elapsed_time": "0:31:26", "remaining_time": "11:34:26", "throughput": 6089.05, "total_tokens": 11486080} +{"current_steps": 5315, "total_steps": 122600, "loss": 0.1829, "lr": 0.000433442088091354, "epoch": 0.867047308319739, "percentage": 4.34, "elapsed_time": "0:31:28", "remaining_time": "11:34:29", "throughput": 6089.14, "total_tokens": 11498464} +{"current_steps": 5320, "total_steps": 122600, "loss": 0.2018, "lr": 0.0004338499184339315, "epoch": 0.867862969004894, "percentage": 4.34, "elapsed_time": "0:31:30", "remaining_time": "11:34:28", "throughput": 6089.14, "total_tokens": 11509376} +{"current_steps": 5325, "total_steps": 122600, "loss": 0.202, "lr": 0.00043425774877650896, "epoch": 0.8686786296900489, "percentage": 4.34, "elapsed_time": "0:31:31", "remaining_time": "11:34:27", "throughput": 6089.16, "total_tokens": 11520480} +{"current_steps": 5330, "total_steps": 122600, "loss": 0.0892, "lr": 0.0004346655791190865, "epoch": 0.8694942903752039, "percentage": 4.35, "elapsed_time": "0:31:33", "remaining_time": "11:34:25", "throughput": 6089.14, "total_tokens": 11531136} +{"current_steps": 5335, "total_steps": 122600, "loss": 0.0623, "lr": 0.00043507340946166397, "epoch": 0.8703099510603589, "percentage": 4.35, "elapsed_time": "0:31:35", "remaining_time": "11:34:21", "throughput": 6089.19, "total_tokens": 11541408} +{"current_steps": 5340, "total_steps": 122600, "loss": 0.2217, "lr": 0.00043548123980424145, "epoch": 0.8711256117455138, "percentage": 4.36, "elapsed_time": "0:31:37", "remaining_time": "11:34:20", "throughput": 6089.13, "total_tokens": 11552320} +{"current_steps": 5345, "total_steps": 122600, "loss": 0.2593, "lr": 0.0004358890701468189, "epoch": 0.8719412724306689, "percentage": 4.36, "elapsed_time": "0:31:38", "remaining_time": "11:34:18", "throughput": 6089.12, "total_tokens": 11563232} +{"current_steps": 5350, "total_steps": 122600, "loss": 0.0955, "lr": 0.0004362969004893964, "epoch": 0.8727569331158238, "percentage": 4.36, "elapsed_time": "0:31:40", "remaining_time": "11:34:16", "throughput": 6089.15, "total_tokens": 11573856} +{"current_steps": 5355, "total_steps": 122600, "loss": 0.1101, "lr": 0.00043670473083197393, "epoch": 0.8735725938009788, "percentage": 4.37, "elapsed_time": "0:31:42", "remaining_time": "11:34:15", "throughput": 6089.19, "total_tokens": 11584960} +{"current_steps": 5360, "total_steps": 122600, "loss": 0.1191, "lr": 0.0004371125611745514, "epoch": 0.8743882544861338, "percentage": 4.37, "elapsed_time": "0:31:44", "remaining_time": "11:34:11", "throughput": 6089.22, "total_tokens": 11595168} +{"current_steps": 5365, "total_steps": 122600, "loss": 0.1045, "lr": 0.0004375203915171289, "epoch": 0.8752039151712887, "percentage": 4.38, "elapsed_time": "0:31:45", "remaining_time": "11:34:07", "throughput": 6089.26, "total_tokens": 11605472} +{"current_steps": 5370, "total_steps": 122600, "loss": 0.035, "lr": 0.00043792822185970636, "epoch": 0.8760195758564437, "percentage": 4.38, "elapsed_time": "0:31:47", "remaining_time": "11:34:05", "throughput": 6089.27, "total_tokens": 11616224} +{"current_steps": 5375, "total_steps": 122600, "loss": 0.077, "lr": 0.00043833605220228384, "epoch": 0.8768352365415987, "percentage": 4.38, "elapsed_time": "0:31:49", "remaining_time": "11:34:02", "throughput": 6089.21, "total_tokens": 11626816} +{"current_steps": 5380, "total_steps": 122600, "loss": 0.0706, "lr": 0.00043874388254486137, "epoch": 0.8776508972267537, "percentage": 4.39, "elapsed_time": "0:31:51", "remaining_time": "11:34:00", "throughput": 6089.13, "total_tokens": 11637152} +{"current_steps": 5385, "total_steps": 122600, "loss": 0.1373, "lr": 0.00043915171288743884, "epoch": 0.8784665579119086, "percentage": 4.39, "elapsed_time": "0:31:52", "remaining_time": "11:33:58", "throughput": 6089.18, "total_tokens": 11648160} +{"current_steps": 5390, "total_steps": 122600, "loss": 0.2045, "lr": 0.0004395595432300163, "epoch": 0.8792822185970636, "percentage": 4.4, "elapsed_time": "0:31:54", "remaining_time": "11:34:00", "throughput": 6089.32, "total_tokens": 11660320} +{"current_steps": 5395, "total_steps": 122600, "loss": 0.1744, "lr": 0.0004399673735725938, "epoch": 0.8800978792822186, "percentage": 4.4, "elapsed_time": "0:31:56", "remaining_time": "11:33:57", "throughput": 6089.33, "total_tokens": 11670816} +{"current_steps": 5400, "total_steps": 122600, "loss": 0.0314, "lr": 0.00044037520391517127, "epoch": 0.8809135399673735, "percentage": 4.4, "elapsed_time": "0:31:58", "remaining_time": "11:33:58", "throughput": 6089.4, "total_tokens": 11682560} +{"current_steps": 5405, "total_steps": 122600, "loss": 0.3882, "lr": 0.0004407830342577488, "epoch": 0.8817292006525286, "percentage": 4.41, "elapsed_time": "0:32:00", "remaining_time": "11:34:00", "throughput": 6089.48, "total_tokens": 11694400} +{"current_steps": 5410, "total_steps": 122600, "loss": 0.0998, "lr": 0.0004411908646003263, "epoch": 0.8825448613376835, "percentage": 4.41, "elapsed_time": "0:32:02", "remaining_time": "11:34:00", "throughput": 6089.44, "total_tokens": 11705728} +{"current_steps": 5415, "total_steps": 122600, "loss": 0.1255, "lr": 0.00044159869494290376, "epoch": 0.8833605220228385, "percentage": 4.42, "elapsed_time": "0:32:04", "remaining_time": "11:33:58", "throughput": 6089.49, "total_tokens": 11716736} +{"current_steps": 5420, "total_steps": 122600, "loss": 0.0871, "lr": 0.00044200652528548123, "epoch": 0.8841761827079935, "percentage": 4.42, "elapsed_time": "0:32:05", "remaining_time": "11:33:53", "throughput": 6089.39, "total_tokens": 11726208} +{"current_steps": 5425, "total_steps": 122600, "loss": 0.0952, "lr": 0.00044241435562805876, "epoch": 0.8849918433931484, "percentage": 4.42, "elapsed_time": "0:32:07", "remaining_time": "11:33:53", "throughput": 6089.45, "total_tokens": 11737664} +{"current_steps": 5430, "total_steps": 122600, "loss": 0.1987, "lr": 0.00044282218597063624, "epoch": 0.8858075040783034, "percentage": 4.43, "elapsed_time": "0:32:09", "remaining_time": "11:33:53", "throughput": 6089.52, "total_tokens": 11749312} +{"current_steps": 5435, "total_steps": 122600, "loss": 0.2475, "lr": 0.0004432300163132137, "epoch": 0.8866231647634584, "percentage": 4.43, "elapsed_time": "0:32:11", "remaining_time": "11:33:51", "throughput": 6089.58, "total_tokens": 11760192} +{"current_steps": 5440, "total_steps": 122600, "loss": 0.164, "lr": 0.0004436378466557912, "epoch": 0.8874388254486134, "percentage": 4.44, "elapsed_time": "0:32:12", "remaining_time": "11:33:48", "throughput": 6089.49, "total_tokens": 11770464} +{"current_steps": 5445, "total_steps": 122600, "loss": 0.1861, "lr": 0.00044404567699836867, "epoch": 0.8882544861337683, "percentage": 4.44, "elapsed_time": "0:32:14", "remaining_time": "11:33:46", "throughput": 6089.55, "total_tokens": 11781344} +{"current_steps": 5450, "total_steps": 122600, "loss": 0.116, "lr": 0.0004444535073409462, "epoch": 0.8890701468189234, "percentage": 4.45, "elapsed_time": "0:32:16", "remaining_time": "11:33:44", "throughput": 6089.54, "total_tokens": 11791968} +{"current_steps": 5455, "total_steps": 122600, "loss": 0.1099, "lr": 0.0004448613376835237, "epoch": 0.8898858075040783, "percentage": 4.45, "elapsed_time": "0:32:18", "remaining_time": "11:33:42", "throughput": 6089.52, "total_tokens": 11802624} +{"current_steps": 5460, "total_steps": 122600, "loss": 0.2742, "lr": 0.0004452691680261011, "epoch": 0.8907014681892332, "percentage": 4.45, "elapsed_time": "0:32:19", "remaining_time": "11:33:39", "throughput": 6089.58, "total_tokens": 11813248} +{"current_steps": 5465, "total_steps": 122600, "loss": 0.1914, "lr": 0.00044567699836867863, "epoch": 0.8915171288743883, "percentage": 4.46, "elapsed_time": "0:32:21", "remaining_time": "11:33:34", "throughput": 6089.56, "total_tokens": 11823040} +{"current_steps": 5470, "total_steps": 122600, "loss": 0.1478, "lr": 0.0004460848287112561, "epoch": 0.8923327895595432, "percentage": 4.46, "elapsed_time": "0:32:23", "remaining_time": "11:33:34", "throughput": 6089.57, "total_tokens": 11834528} +{"current_steps": 5475, "total_steps": 122600, "loss": 0.1098, "lr": 0.00044649265905383364, "epoch": 0.8931484502446982, "percentage": 4.47, "elapsed_time": "0:32:25", "remaining_time": "11:33:30", "throughput": 6089.61, "total_tokens": 11844896} +{"current_steps": 5480, "total_steps": 122600, "loss": 0.0678, "lr": 0.0004469004893964111, "epoch": 0.8939641109298532, "percentage": 4.47, "elapsed_time": "0:32:26", "remaining_time": "11:33:27", "throughput": 6089.62, "total_tokens": 11855392} +{"current_steps": 5485, "total_steps": 122600, "loss": 0.2677, "lr": 0.0004473083197389886, "epoch": 0.8947797716150081, "percentage": 4.47, "elapsed_time": "0:32:28", "remaining_time": "11:33:21", "throughput": 6089.48, "total_tokens": 11864608} +{"current_steps": 5490, "total_steps": 122600, "loss": 0.2639, "lr": 0.00044771615008156607, "epoch": 0.8955954323001631, "percentage": 4.48, "elapsed_time": "0:32:30", "remaining_time": "11:33:20", "throughput": 6089.52, "total_tokens": 11875776} +{"current_steps": 5495, "total_steps": 122600, "loss": 0.0903, "lr": 0.00044812398042414354, "epoch": 0.8964110929853181, "percentage": 4.48, "elapsed_time": "0:32:31", "remaining_time": "11:33:15", "throughput": 6089.51, "total_tokens": 11885472} +{"current_steps": 5500, "total_steps": 122600, "loss": 0.178, "lr": 0.00044853181076672107, "epoch": 0.8972267536704731, "percentage": 4.49, "elapsed_time": "0:32:33", "remaining_time": "11:33:15", "throughput": 6089.58, "total_tokens": 11897056} +{"current_steps": 5505, "total_steps": 122600, "loss": 0.1818, "lr": 0.00044893964110929855, "epoch": 0.898042414355628, "percentage": 4.49, "elapsed_time": "0:32:35", "remaining_time": "11:33:10", "throughput": 6089.6, "total_tokens": 11907104} +{"current_steps": 5510, "total_steps": 122600, "loss": 0.1849, "lr": 0.000449347471451876, "epoch": 0.8988580750407831, "percentage": 4.49, "elapsed_time": "0:32:36", "remaining_time": "11:33:05", "throughput": 6089.58, "total_tokens": 11916960} +{"current_steps": 5515, "total_steps": 122600, "loss": 0.0843, "lr": 0.0004497553017944535, "epoch": 0.899673735725938, "percentage": 4.5, "elapsed_time": "0:32:38", "remaining_time": "11:33:02", "throughput": 6089.5, "total_tokens": 11927232} +{"current_steps": 5520, "total_steps": 122600, "loss": 0.2114, "lr": 0.00045016313213703103, "epoch": 0.9004893964110929, "percentage": 4.5, "elapsed_time": "0:32:40", "remaining_time": "11:33:01", "throughput": 6089.53, "total_tokens": 11938272} +{"current_steps": 5525, "total_steps": 122600, "loss": 0.2142, "lr": 0.0004505709624796085, "epoch": 0.901305057096248, "percentage": 4.51, "elapsed_time": "0:32:42", "remaining_time": "11:33:01", "throughput": 6089.55, "total_tokens": 11949632} +{"current_steps": 5530, "total_steps": 122600, "loss": 0.1789, "lr": 0.00045097879282218593, "epoch": 0.9021207177814029, "percentage": 4.51, "elapsed_time": "0:32:43", "remaining_time": "11:32:55", "throughput": 6089.5, "total_tokens": 11959232} +{"current_steps": 5535, "total_steps": 122600, "loss": 0.1218, "lr": 0.00045138662316476346, "epoch": 0.9029363784665579, "percentage": 4.51, "elapsed_time": "0:32:45", "remaining_time": "11:32:55", "throughput": 6089.46, "total_tokens": 11970304} +{"current_steps": 5540, "total_steps": 122600, "loss": 0.1069, "lr": 0.00045179445350734094, "epoch": 0.9037520391517129, "percentage": 4.52, "elapsed_time": "0:32:47", "remaining_time": "11:32:53", "throughput": 6089.4, "total_tokens": 11980864} +{"current_steps": 5545, "total_steps": 122600, "loss": 0.1869, "lr": 0.00045220228384991847, "epoch": 0.9045676998368679, "percentage": 4.52, "elapsed_time": "0:32:49", "remaining_time": "11:32:47", "throughput": 6089.38, "total_tokens": 11990592} +{"current_steps": 5550, "total_steps": 122600, "loss": 0.0485, "lr": 0.00045261011419249595, "epoch": 0.9053833605220228, "percentage": 4.53, "elapsed_time": "0:32:51", "remaining_time": "11:32:49", "throughput": 6089.48, "total_tokens": 12002720} +{"current_steps": 5555, "total_steps": 122600, "loss": 0.126, "lr": 0.0004530179445350734, "epoch": 0.9061990212071778, "percentage": 4.53, "elapsed_time": "0:32:52", "remaining_time": "11:32:46", "throughput": 6089.41, "total_tokens": 12012896} +{"current_steps": 5560, "total_steps": 122600, "loss": 0.1054, "lr": 0.0004534257748776509, "epoch": 0.9070146818923328, "percentage": 4.54, "elapsed_time": "0:32:54", "remaining_time": "11:32:48", "throughput": 6089.59, "total_tokens": 12025120} +{"current_steps": 5565, "total_steps": 122600, "loss": 0.3257, "lr": 0.0004538336052202284, "epoch": 0.9078303425774877, "percentage": 4.54, "elapsed_time": "0:32:56", "remaining_time": "11:32:48", "throughput": 6089.56, "total_tokens": 12036384} +{"current_steps": 5570, "total_steps": 122600, "loss": 0.2105, "lr": 0.0004542414355628059, "epoch": 0.9086460032626428, "percentage": 4.54, "elapsed_time": "0:32:58", "remaining_time": "11:32:46", "throughput": 6089.59, "total_tokens": 12047296} +{"current_steps": 5575, "total_steps": 122600, "loss": 0.1081, "lr": 0.0004546492659053834, "epoch": 0.9094616639477977, "percentage": 4.55, "elapsed_time": "0:33:00", "remaining_time": "11:32:43", "throughput": 6089.57, "total_tokens": 12057664} +{"current_steps": 5580, "total_steps": 122600, "loss": 0.1315, "lr": 0.00045505709624796086, "epoch": 0.9102773246329527, "percentage": 4.55, "elapsed_time": "0:33:01", "remaining_time": "11:32:44", "throughput": 6089.63, "total_tokens": 12069344} +{"current_steps": 5585, "total_steps": 122600, "loss": 0.0992, "lr": 0.00045546492659053833, "epoch": 0.9110929853181077, "percentage": 4.56, "elapsed_time": "0:33:03", "remaining_time": "11:32:42", "throughput": 6089.64, "total_tokens": 12080224} +{"current_steps": 5590, "total_steps": 122600, "loss": 0.0847, "lr": 0.0004558727569331158, "epoch": 0.9119086460032626, "percentage": 4.56, "elapsed_time": "0:33:05", "remaining_time": "11:32:37", "throughput": 6089.56, "total_tokens": 12089824} +{"current_steps": 5595, "total_steps": 122600, "loss": 0.0778, "lr": 0.00045628058727569334, "epoch": 0.9127243066884176, "percentage": 4.56, "elapsed_time": "0:33:07", "remaining_time": "11:32:36", "throughput": 6089.61, "total_tokens": 12101152} +{"current_steps": 5600, "total_steps": 122600, "loss": 0.1407, "lr": 0.00045668841761827076, "epoch": 0.9135399673735726, "percentage": 4.57, "elapsed_time": "0:33:08", "remaining_time": "11:32:34", "throughput": 6089.65, "total_tokens": 12111936} +{"current_steps": 5605, "total_steps": 122600, "loss": 0.1784, "lr": 0.0004570962479608483, "epoch": 0.9143556280587276, "percentage": 4.57, "elapsed_time": "0:33:10", "remaining_time": "11:32:31", "throughput": 6089.69, "total_tokens": 12122528} +{"current_steps": 5610, "total_steps": 122600, "loss": 0.2051, "lr": 0.00045750407830342577, "epoch": 0.9151712887438825, "percentage": 4.58, "elapsed_time": "0:33:12", "remaining_time": "11:32:26", "throughput": 6089.57, "total_tokens": 12132128} +{"current_steps": 5615, "total_steps": 122600, "loss": 0.2114, "lr": 0.0004579119086460033, "epoch": 0.9159869494290375, "percentage": 4.58, "elapsed_time": "0:33:14", "remaining_time": "11:32:26", "throughput": 6089.6, "total_tokens": 12143552} +{"current_steps": 5620, "total_steps": 122600, "loss": 0.1329, "lr": 0.0004583197389885808, "epoch": 0.9168026101141925, "percentage": 4.58, "elapsed_time": "0:33:15", "remaining_time": "11:32:21", "throughput": 6089.5, "total_tokens": 12152992} +{"current_steps": 5625, "total_steps": 122600, "loss": 0.1475, "lr": 0.0004587275693311582, "epoch": 0.9176182707993474, "percentage": 4.59, "elapsed_time": "0:33:17", "remaining_time": "11:32:17", "throughput": 6089.54, "total_tokens": 12163488} +{"current_steps": 5630, "total_steps": 122600, "loss": 0.0997, "lr": 0.00045913539967373573, "epoch": 0.9184339314845025, "percentage": 4.59, "elapsed_time": "0:33:19", "remaining_time": "11:32:18", "throughput": 6089.57, "total_tokens": 12174976} +{"current_steps": 5635, "total_steps": 122600, "loss": 0.0692, "lr": 0.0004595432300163132, "epoch": 0.9192495921696574, "percentage": 4.6, "elapsed_time": "0:33:21", "remaining_time": "11:32:16", "throughput": 6089.59, "total_tokens": 12185984} +{"current_steps": 5640, "total_steps": 122600, "loss": 0.2212, "lr": 0.00045995106035889074, "epoch": 0.9200652528548124, "percentage": 4.6, "elapsed_time": "0:33:22", "remaining_time": "11:32:15", "throughput": 6089.49, "total_tokens": 12196768} +{"current_steps": 5645, "total_steps": 122600, "loss": 0.0561, "lr": 0.0004603588907014682, "epoch": 0.9208809135399674, "percentage": 4.6, "elapsed_time": "0:33:24", "remaining_time": "11:32:18", "throughput": 6089.62, "total_tokens": 12209120} +{"current_steps": 5650, "total_steps": 122600, "loss": 0.0937, "lr": 0.0004607667210440457, "epoch": 0.9216965742251223, "percentage": 4.61, "elapsed_time": "0:33:26", "remaining_time": "11:32:19", "throughput": 6089.66, "total_tokens": 12220768} +{"current_steps": 5655, "total_steps": 122600, "loss": 0.047, "lr": 0.00046117455138662317, "epoch": 0.9225122349102773, "percentage": 4.61, "elapsed_time": "0:33:28", "remaining_time": "11:32:15", "throughput": 6089.57, "total_tokens": 12230720} +{"current_steps": 5660, "total_steps": 122600, "loss": 0.1112, "lr": 0.00046158238172920064, "epoch": 0.9233278955954323, "percentage": 4.62, "elapsed_time": "0:33:30", "remaining_time": "11:32:17", "throughput": 6089.65, "total_tokens": 12242880} +{"current_steps": 5665, "total_steps": 122600, "loss": 0.0375, "lr": 0.0004619902120717782, "epoch": 0.9241435562805873, "percentage": 4.62, "elapsed_time": "0:33:32", "remaining_time": "11:32:15", "throughput": 6089.62, "total_tokens": 12253760} +{"current_steps": 5670, "total_steps": 122600, "loss": 0.1231, "lr": 0.0004623980424143556, "epoch": 0.9249592169657422, "percentage": 4.62, "elapsed_time": "0:33:33", "remaining_time": "11:32:11", "throughput": 6089.53, "total_tokens": 12263712} +{"current_steps": 5675, "total_steps": 122600, "loss": 0.145, "lr": 0.00046280587275693313, "epoch": 0.9257748776508973, "percentage": 4.63, "elapsed_time": "0:33:35", "remaining_time": "11:32:10", "throughput": 6089.54, "total_tokens": 12274560} +{"current_steps": 5680, "total_steps": 122600, "loss": 0.159, "lr": 0.0004632137030995106, "epoch": 0.9265905383360522, "percentage": 4.63, "elapsed_time": "0:33:37", "remaining_time": "11:32:07", "throughput": 6089.49, "total_tokens": 12285024} +{"current_steps": 5685, "total_steps": 122600, "loss": 0.1451, "lr": 0.00046362153344208813, "epoch": 0.9274061990212071, "percentage": 4.64, "elapsed_time": "0:33:39", "remaining_time": "11:32:05", "throughput": 6089.49, "total_tokens": 12295712} +{"current_steps": 5690, "total_steps": 122600, "loss": 0.1199, "lr": 0.0004640293637846656, "epoch": 0.9282218597063622, "percentage": 4.64, "elapsed_time": "0:33:40", "remaining_time": "11:31:58", "throughput": 6089.43, "total_tokens": 12305024} +{"current_steps": 5695, "total_steps": 122600, "loss": 0.1054, "lr": 0.00046443719412724303, "epoch": 0.9290375203915171, "percentage": 4.65, "elapsed_time": "0:33:42", "remaining_time": "11:31:56", "throughput": 6089.31, "total_tokens": 12315360} +{"current_steps": 5700, "total_steps": 122600, "loss": 0.0757, "lr": 0.00046484502446982056, "epoch": 0.9298531810766721, "percentage": 4.65, "elapsed_time": "0:33:44", "remaining_time": "11:31:55", "throughput": 6089.25, "total_tokens": 12326464} +{"current_steps": 5705, "total_steps": 122600, "loss": 0.0945, "lr": 0.00046525285481239804, "epoch": 0.9306688417618271, "percentage": 4.65, "elapsed_time": "0:33:46", "remaining_time": "11:31:55", "throughput": 6089.22, "total_tokens": 12337600} +{"current_steps": 5710, "total_steps": 122600, "loss": 0.2785, "lr": 0.00046566068515497557, "epoch": 0.9314845024469821, "percentage": 4.66, "elapsed_time": "0:33:47", "remaining_time": "11:31:51", "throughput": 6089.23, "total_tokens": 12347904} +{"current_steps": 5715, "total_steps": 122600, "loss": 0.1508, "lr": 0.00046606851549755305, "epoch": 0.932300163132137, "percentage": 4.66, "elapsed_time": "0:33:49", "remaining_time": "11:31:53", "throughput": 6089.28, "total_tokens": 12359712} +{"current_steps": 5720, "total_steps": 122600, "loss": 0.1295, "lr": 0.00046647634584013047, "epoch": 0.933115823817292, "percentage": 4.67, "elapsed_time": "0:33:51", "remaining_time": "11:31:49", "throughput": 6089.23, "total_tokens": 12369952} +{"current_steps": 5725, "total_steps": 122600, "loss": 0.1429, "lr": 0.000466884176182708, "epoch": 0.933931484502447, "percentage": 4.67, "elapsed_time": "0:33:53", "remaining_time": "11:31:46", "throughput": 6089.19, "total_tokens": 12380384} +{"current_steps": 5730, "total_steps": 122600, "loss": 0.1297, "lr": 0.0004672920065252855, "epoch": 0.9347471451876019, "percentage": 4.67, "elapsed_time": "0:33:55", "remaining_time": "11:31:46", "throughput": 6089.32, "total_tokens": 12391904} +{"current_steps": 5735, "total_steps": 122600, "loss": 0.0857, "lr": 0.000467699836867863, "epoch": 0.935562805872757, "percentage": 4.68, "elapsed_time": "0:33:56", "remaining_time": "11:31:45", "throughput": 6089.31, "total_tokens": 12402944} +{"current_steps": 5740, "total_steps": 122600, "loss": 0.2689, "lr": 0.0004681076672104405, "epoch": 0.9363784665579119, "percentage": 4.68, "elapsed_time": "0:33:58", "remaining_time": "11:31:46", "throughput": 6089.29, "total_tokens": 12414432} +{"current_steps": 5745, "total_steps": 122600, "loss": 0.2165, "lr": 0.00046851549755301796, "epoch": 0.9371941272430668, "percentage": 4.69, "elapsed_time": "0:34:00", "remaining_time": "11:31:43", "throughput": 6089.32, "total_tokens": 12425024} +{"current_steps": 5750, "total_steps": 122600, "loss": 0.2883, "lr": 0.00046892332789559544, "epoch": 0.9380097879282219, "percentage": 4.69, "elapsed_time": "0:34:02", "remaining_time": "11:31:40", "throughput": 6089.26, "total_tokens": 12435232} +{"current_steps": 5755, "total_steps": 122600, "loss": 0.1216, "lr": 0.0004693311582381729, "epoch": 0.9388254486133768, "percentage": 4.69, "elapsed_time": "0:34:03", "remaining_time": "11:31:38", "throughput": 6089.21, "total_tokens": 12445984} +{"current_steps": 5760, "total_steps": 122600, "loss": 0.1076, "lr": 0.00046973898858075044, "epoch": 0.9396411092985318, "percentage": 4.7, "elapsed_time": "0:34:05", "remaining_time": "11:31:35", "throughput": 6089.14, "total_tokens": 12456416} +{"current_steps": 5765, "total_steps": 122600, "loss": 0.2011, "lr": 0.00047014681892332787, "epoch": 0.9404567699836868, "percentage": 4.7, "elapsed_time": "0:34:07", "remaining_time": "11:31:32", "throughput": 6089.05, "total_tokens": 12466656} +{"current_steps": 5770, "total_steps": 122600, "loss": 0.0862, "lr": 0.0004705546492659054, "epoch": 0.9412724306688418, "percentage": 4.71, "elapsed_time": "0:34:09", "remaining_time": "11:31:31", "throughput": 6089.05, "total_tokens": 12477696} +{"current_steps": 5775, "total_steps": 122600, "loss": 0.2129, "lr": 0.0004709624796084829, "epoch": 0.9420880913539967, "percentage": 4.71, "elapsed_time": "0:34:11", "remaining_time": "11:31:31", "throughput": 6089.04, "total_tokens": 12488896} +{"current_steps": 5780, "total_steps": 122600, "loss": 0.1227, "lr": 0.0004713703099510604, "epoch": 0.9429037520391517, "percentage": 4.71, "elapsed_time": "0:34:12", "remaining_time": "11:31:27", "throughput": 6088.99, "total_tokens": 12499040} +{"current_steps": 5785, "total_steps": 122600, "loss": 0.1309, "lr": 0.0004717781402936379, "epoch": 0.9437194127243067, "percentage": 4.72, "elapsed_time": "0:34:14", "remaining_time": "11:31:25", "throughput": 6089.02, "total_tokens": 12509760} +{"current_steps": 5790, "total_steps": 122600, "loss": 0.1011, "lr": 0.0004721859706362153, "epoch": 0.9445350734094616, "percentage": 4.72, "elapsed_time": "0:34:16", "remaining_time": "11:31:26", "throughput": 6089.11, "total_tokens": 12521440} +{"current_steps": 5795, "total_steps": 122600, "loss": 0.2528, "lr": 0.00047259380097879283, "epoch": 0.9453507340946167, "percentage": 4.73, "elapsed_time": "0:34:18", "remaining_time": "11:31:23", "throughput": 6089.07, "total_tokens": 12531840} +{"current_steps": 5800, "total_steps": 122600, "loss": 0.2248, "lr": 0.0004730016313213703, "epoch": 0.9461663947797716, "percentage": 4.73, "elapsed_time": "0:34:19", "remaining_time": "11:31:23", "throughput": 6089.06, "total_tokens": 12543136} +{"current_steps": 5805, "total_steps": 122600, "loss": 0.2949, "lr": 0.00047340946166394784, "epoch": 0.9469820554649266, "percentage": 4.73, "elapsed_time": "0:34:21", "remaining_time": "11:31:22", "throughput": 6089.07, "total_tokens": 12554240} +{"current_steps": 5810, "total_steps": 122600, "loss": 0.1823, "lr": 0.0004738172920065253, "epoch": 0.9477977161500816, "percentage": 4.74, "elapsed_time": "0:34:23", "remaining_time": "11:31:19", "throughput": 6089.06, "total_tokens": 12564640} +{"current_steps": 5815, "total_steps": 122600, "loss": 0.2085, "lr": 0.00047422512234910274, "epoch": 0.9486133768352365, "percentage": 4.74, "elapsed_time": "0:34:25", "remaining_time": "11:31:15", "throughput": 6089.04, "total_tokens": 12574976} +{"current_steps": 5820, "total_steps": 122600, "loss": 0.1755, "lr": 0.00047463295269168027, "epoch": 0.9494290375203915, "percentage": 4.75, "elapsed_time": "0:34:26", "remaining_time": "11:31:13", "throughput": 6089.05, "total_tokens": 12585632} +{"current_steps": 5825, "total_steps": 122600, "loss": 0.2283, "lr": 0.00047504078303425775, "epoch": 0.9502446982055465, "percentage": 4.75, "elapsed_time": "0:34:28", "remaining_time": "11:31:10", "throughput": 6089.05, "total_tokens": 12596096} +{"current_steps": 5830, "total_steps": 122600, "loss": 0.0988, "lr": 0.0004754486133768353, "epoch": 0.9510603588907015, "percentage": 4.76, "elapsed_time": "0:34:30", "remaining_time": "11:31:11", "throughput": 6089.1, "total_tokens": 12607712} +{"current_steps": 5835, "total_steps": 122600, "loss": 0.0766, "lr": 0.0004758564437194127, "epoch": 0.9518760195758564, "percentage": 4.76, "elapsed_time": "0:34:32", "remaining_time": "11:31:08", "throughput": 6089.14, "total_tokens": 12618272} +{"current_steps": 5840, "total_steps": 122600, "loss": 0.0792, "lr": 0.00047626427406199023, "epoch": 0.9526916802610114, "percentage": 4.76, "elapsed_time": "0:34:34", "remaining_time": "11:31:08", "throughput": 6089.18, "total_tokens": 12629856} +{"current_steps": 5845, "total_steps": 122600, "loss": 0.1799, "lr": 0.0004766721044045677, "epoch": 0.9535073409461664, "percentage": 4.77, "elapsed_time": "0:34:35", "remaining_time": "11:31:03", "throughput": 6089.11, "total_tokens": 12639456} +{"current_steps": 5850, "total_steps": 122600, "loss": 0.1551, "lr": 0.0004770799347471452, "epoch": 0.9543230016313213, "percentage": 4.77, "elapsed_time": "0:34:37", "remaining_time": "11:30:57", "throughput": 6089.08, "total_tokens": 12649088} +{"current_steps": 5855, "total_steps": 122600, "loss": 0.0948, "lr": 0.0004774877650897227, "epoch": 0.9551386623164764, "percentage": 4.78, "elapsed_time": "0:34:39", "remaining_time": "11:30:55", "throughput": 6089.06, "total_tokens": 12659680} +{"current_steps": 5860, "total_steps": 122600, "loss": 0.1348, "lr": 0.00047789559543230014, "epoch": 0.9559543230016313, "percentage": 4.78, "elapsed_time": "0:34:40", "remaining_time": "11:30:55", "throughput": 6089.07, "total_tokens": 12670848} +{"current_steps": 5865, "total_steps": 122600, "loss": 0.0595, "lr": 0.00047830342577487767, "epoch": 0.9567699836867863, "percentage": 4.78, "elapsed_time": "0:34:42", "remaining_time": "11:30:52", "throughput": 6089.07, "total_tokens": 12681568} +{"current_steps": 5870, "total_steps": 122600, "loss": 0.2106, "lr": 0.00047871125611745514, "epoch": 0.9575856443719413, "percentage": 4.79, "elapsed_time": "0:34:44", "remaining_time": "11:30:49", "throughput": 6088.98, "total_tokens": 12691616} +{"current_steps": 5875, "total_steps": 122600, "loss": 0.1245, "lr": 0.0004791190864600327, "epoch": 0.9584013050570962, "percentage": 4.79, "elapsed_time": "0:34:46", "remaining_time": "11:30:45", "throughput": 6088.95, "total_tokens": 12701728} +{"current_steps": 5880, "total_steps": 122600, "loss": 0.1439, "lr": 0.00047952691680261015, "epoch": 0.9592169657422512, "percentage": 4.8, "elapsed_time": "0:34:47", "remaining_time": "11:30:42", "throughput": 6089.02, "total_tokens": 12712480} +{"current_steps": 5885, "total_steps": 122600, "loss": 0.2585, "lr": 0.00047993474714518757, "epoch": 0.9600326264274062, "percentage": 4.8, "elapsed_time": "0:34:49", "remaining_time": "11:30:44", "throughput": 6089.09, "total_tokens": 12724544} +{"current_steps": 5890, "total_steps": 122600, "loss": 0.0721, "lr": 0.0004803425774877651, "epoch": 0.9608482871125612, "percentage": 4.8, "elapsed_time": "0:34:51", "remaining_time": "11:30:44", "throughput": 6089.03, "total_tokens": 12735552} +{"current_steps": 5895, "total_steps": 122600, "loss": 0.2742, "lr": 0.0004807504078303426, "epoch": 0.9616639477977161, "percentage": 4.81, "elapsed_time": "0:34:53", "remaining_time": "11:30:44", "throughput": 6089.09, "total_tokens": 12747072} +{"current_steps": 5900, "total_steps": 122600, "loss": 0.2193, "lr": 0.0004811582381729201, "epoch": 0.9624796084828712, "percentage": 4.81, "elapsed_time": "0:34:55", "remaining_time": "11:30:41", "throughput": 6089.09, "total_tokens": 12757504} +{"current_steps": 5905, "total_steps": 122600, "loss": 0.1594, "lr": 0.00048156606851549753, "epoch": 0.9632952691680261, "percentage": 4.82, "elapsed_time": "0:34:56", "remaining_time": "11:30:40", "throughput": 6089.01, "total_tokens": 12768544} +{"current_steps": 5910, "total_steps": 122600, "loss": 0.069, "lr": 0.00048197389885807506, "epoch": 0.964110929853181, "percentage": 4.82, "elapsed_time": "0:34:58", "remaining_time": "11:30:36", "throughput": 6088.95, "total_tokens": 12778464} +{"current_steps": 5915, "total_steps": 122600, "loss": 0.1426, "lr": 0.00048238172920065254, "epoch": 0.9649265905383361, "percentage": 4.82, "elapsed_time": "0:35:00", "remaining_time": "11:30:32", "throughput": 6088.89, "total_tokens": 12788352} +{"current_steps": 5920, "total_steps": 122600, "loss": 0.1739, "lr": 0.00048278955954323, "epoch": 0.965742251223491, "percentage": 4.83, "elapsed_time": "0:35:01", "remaining_time": "11:30:25", "throughput": 6088.77, "total_tokens": 12797344} +{"current_steps": 5925, "total_steps": 122600, "loss": 0.1457, "lr": 0.00048319738988580755, "epoch": 0.966557911908646, "percentage": 4.83, "elapsed_time": "0:35:03", "remaining_time": "11:30:20", "throughput": 6088.73, "total_tokens": 12807264} +{"current_steps": 5930, "total_steps": 122600, "loss": 0.1057, "lr": 0.00048360522022838497, "epoch": 0.967373572593801, "percentage": 4.84, "elapsed_time": "0:35:05", "remaining_time": "11:30:17", "throughput": 6088.7, "total_tokens": 12817408} +{"current_steps": 5935, "total_steps": 122600, "loss": 0.1548, "lr": 0.0004840130505709625, "epoch": 0.968189233278956, "percentage": 4.84, "elapsed_time": "0:35:06", "remaining_time": "11:30:13", "throughput": 6088.64, "total_tokens": 12827616} +{"current_steps": 5940, "total_steps": 122600, "loss": 0.181, "lr": 0.00048442088091354, "epoch": 0.9690048939641109, "percentage": 4.85, "elapsed_time": "0:35:08", "remaining_time": "11:30:09", "throughput": 6088.6, "total_tokens": 12837696} +{"current_steps": 5945, "total_steps": 122600, "loss": 0.0716, "lr": 0.00048482871125611745, "epoch": 0.9698205546492659, "percentage": 4.85, "elapsed_time": "0:35:10", "remaining_time": "11:30:09", "throughput": 6088.67, "total_tokens": 12848928} +{"current_steps": 5950, "total_steps": 122600, "loss": 0.2212, "lr": 0.000485236541598695, "epoch": 0.9706362153344209, "percentage": 4.85, "elapsed_time": "0:35:12", "remaining_time": "11:30:05", "throughput": 6088.66, "total_tokens": 12859264} +{"current_steps": 5955, "total_steps": 122600, "loss": 0.1212, "lr": 0.0004856443719412724, "epoch": 0.9714518760195758, "percentage": 4.86, "elapsed_time": "0:35:13", "remaining_time": "11:30:04", "throughput": 6088.67, "total_tokens": 12870336} +{"current_steps": 5960, "total_steps": 122600, "loss": 0.308, "lr": 0.00048605220228384994, "epoch": 0.9722675367047309, "percentage": 4.86, "elapsed_time": "0:35:15", "remaining_time": "11:30:03", "throughput": 6088.62, "total_tokens": 12881280} +{"current_steps": 5965, "total_steps": 122600, "loss": 0.1112, "lr": 0.0004864600326264274, "epoch": 0.9730831973898858, "percentage": 4.87, "elapsed_time": "0:35:17", "remaining_time": "11:30:03", "throughput": 6088.58, "total_tokens": 12892544} +{"current_steps": 5970, "total_steps": 122600, "loss": 0.1458, "lr": 0.00048686786296900494, "epoch": 0.9738988580750407, "percentage": 4.87, "elapsed_time": "0:35:19", "remaining_time": "11:30:02", "throughput": 6088.61, "total_tokens": 12903680} +{"current_steps": 5975, "total_steps": 122600, "loss": 0.1987, "lr": 0.00048727569331158237, "epoch": 0.9747145187601958, "percentage": 4.87, "elapsed_time": "0:35:21", "remaining_time": "11:30:01", "throughput": 6088.57, "total_tokens": 12914400} +{"current_steps": 5980, "total_steps": 122600, "loss": 0.1782, "lr": 0.00048768352365415984, "epoch": 0.9755301794453507, "percentage": 4.88, "elapsed_time": "0:35:22", "remaining_time": "11:30:01", "throughput": 6088.57, "total_tokens": 12925920} +{"current_steps": 5985, "total_steps": 122600, "loss": 0.1816, "lr": 0.00048809135399673737, "epoch": 0.9763458401305057, "percentage": 4.88, "elapsed_time": "0:35:24", "remaining_time": "11:29:59", "throughput": 6088.52, "total_tokens": 12936640} +{"current_steps": 5990, "total_steps": 122600, "loss": 0.177, "lr": 0.0004884991843393148, "epoch": 0.9771615008156607, "percentage": 4.89, "elapsed_time": "0:35:26", "remaining_time": "11:29:59", "throughput": 6088.59, "total_tokens": 12948160} +{"current_steps": 5995, "total_steps": 122600, "loss": 0.1374, "lr": 0.0004889070146818923, "epoch": 0.9779771615008157, "percentage": 4.89, "elapsed_time": "0:35:28", "remaining_time": "11:29:58", "throughput": 6088.66, "total_tokens": 12959296} +{"current_steps": 6000, "total_steps": 122600, "loss": 0.1107, "lr": 0.0004893148450244698, "epoch": 0.9787928221859706, "percentage": 4.89, "elapsed_time": "0:35:30", "remaining_time": "11:29:58", "throughput": 6088.73, "total_tokens": 12970624} +{"current_steps": 6005, "total_steps": 122600, "loss": 0.2367, "lr": 0.0004897226753670474, "epoch": 0.9796084828711256, "percentage": 4.9, "elapsed_time": "0:35:32", "remaining_time": "11:29:57", "throughput": 6088.72, "total_tokens": 12981664} +{"current_steps": 6010, "total_steps": 122600, "loss": 0.2274, "lr": 0.0004901305057096248, "epoch": 0.9804241435562806, "percentage": 4.9, "elapsed_time": "0:35:33", "remaining_time": "11:29:52", "throughput": 6088.65, "total_tokens": 12991328} +{"current_steps": 6015, "total_steps": 122600, "loss": 0.046, "lr": 0.0004905383360522022, "epoch": 0.9812398042414355, "percentage": 4.91, "elapsed_time": "0:35:35", "remaining_time": "11:29:49", "throughput": 6088.49, "total_tokens": 13001632} +{"current_steps": 6020, "total_steps": 122600, "loss": 0.1611, "lr": 0.0004909461663947798, "epoch": 0.9820554649265906, "percentage": 4.91, "elapsed_time": "0:35:37", "remaining_time": "11:29:47", "throughput": 6088.44, "total_tokens": 13012256} +{"current_steps": 6025, "total_steps": 122600, "loss": 0.1385, "lr": 0.0004913539967373573, "epoch": 0.9828711256117455, "percentage": 4.91, "elapsed_time": "0:35:39", "remaining_time": "11:29:50", "throughput": 6088.53, "total_tokens": 13024480} +{"current_steps": 6030, "total_steps": 122600, "loss": 0.0512, "lr": 0.0004917618270799348, "epoch": 0.9836867862969005, "percentage": 4.92, "elapsed_time": "0:35:40", "remaining_time": "11:29:45", "throughput": 6088.53, "total_tokens": 13034432} +{"current_steps": 6035, "total_steps": 122600, "loss": 0.163, "lr": 0.0004921696574225122, "epoch": 0.9845024469820555, "percentage": 4.92, "elapsed_time": "0:35:42", "remaining_time": "11:29:45", "throughput": 6088.54, "total_tokens": 13045824} +{"current_steps": 6040, "total_steps": 122600, "loss": 0.1086, "lr": 0.0004925774877650897, "epoch": 0.9853181076672104, "percentage": 4.93, "elapsed_time": "0:35:44", "remaining_time": "11:29:46", "throughput": 6088.57, "total_tokens": 13057536} +{"current_steps": 6045, "total_steps": 122600, "loss": 0.1038, "lr": 0.0004929853181076672, "epoch": 0.9861337683523654, "percentage": 4.93, "elapsed_time": "0:35:46", "remaining_time": "11:29:46", "throughput": 6088.61, "total_tokens": 13069120} +{"current_steps": 6050, "total_steps": 122600, "loss": 0.0449, "lr": 0.0004933931484502447, "epoch": 0.9869494290375204, "percentage": 4.93, "elapsed_time": "0:35:48", "remaining_time": "11:29:46", "throughput": 6088.52, "total_tokens": 13080192} +{"current_steps": 6055, "total_steps": 122600, "loss": 0.1282, "lr": 0.0004938009787928223, "epoch": 0.9877650897226754, "percentage": 4.94, "elapsed_time": "0:35:50", "remaining_time": "11:29:45", "throughput": 6088.46, "total_tokens": 13091040} +{"current_steps": 6060, "total_steps": 122600, "loss": 0.0451, "lr": 0.0004942088091353996, "epoch": 0.9885807504078303, "percentage": 4.94, "elapsed_time": "0:35:52", "remaining_time": "11:29:47", "throughput": 6088.47, "total_tokens": 13102976} +{"current_steps": 6065, "total_steps": 122600, "loss": 0.3, "lr": 0.0004946166394779772, "epoch": 0.9893964110929854, "percentage": 4.95, "elapsed_time": "0:35:53", "remaining_time": "11:29:47", "throughput": 6088.58, "total_tokens": 13114688} +{"current_steps": 6070, "total_steps": 122600, "loss": 0.0628, "lr": 0.0004950244698205547, "epoch": 0.9902120717781403, "percentage": 4.95, "elapsed_time": "0:35:55", "remaining_time": "11:29:47", "throughput": 6088.72, "total_tokens": 13126432} +{"current_steps": 6075, "total_steps": 122600, "loss": 0.1958, "lr": 0.0004954323001631322, "epoch": 0.9910277324632952, "percentage": 4.96, "elapsed_time": "0:35:57", "remaining_time": "11:29:46", "throughput": 6088.72, "total_tokens": 13137344} +{"current_steps": 6080, "total_steps": 122600, "loss": 0.1382, "lr": 0.0004958401305057096, "epoch": 0.9918433931484503, "percentage": 4.96, "elapsed_time": "0:35:59", "remaining_time": "11:29:45", "throughput": 6088.81, "total_tokens": 13148608} +{"current_steps": 6085, "total_steps": 122600, "loss": 0.1019, "lr": 0.0004962479608482871, "epoch": 0.9926590538336052, "percentage": 4.96, "elapsed_time": "0:36:01", "remaining_time": "11:29:44", "throughput": 6088.85, "total_tokens": 13159840} +{"current_steps": 6090, "total_steps": 122600, "loss": 0.1872, "lr": 0.0004966557911908646, "epoch": 0.9934747145187602, "percentage": 4.97, "elapsed_time": "0:36:02", "remaining_time": "11:29:40", "throughput": 6088.8, "total_tokens": 13169856} +{"current_steps": 6095, "total_steps": 122600, "loss": 0.1258, "lr": 0.0004970636215334421, "epoch": 0.9942903752039152, "percentage": 4.97, "elapsed_time": "0:36:04", "remaining_time": "11:29:41", "throughput": 6088.84, "total_tokens": 13181728} +{"current_steps": 6100, "total_steps": 122600, "loss": 0.1266, "lr": 0.0004974714518760197, "epoch": 0.9951060358890701, "percentage": 4.98, "elapsed_time": "0:36:06", "remaining_time": "11:29:42", "throughput": 6088.96, "total_tokens": 13193760} +{"current_steps": 6105, "total_steps": 122600, "loss": 0.0894, "lr": 0.000497879282218597, "epoch": 0.9959216965742251, "percentage": 4.98, "elapsed_time": "0:36:08", "remaining_time": "11:29:42", "throughput": 6089.04, "total_tokens": 13205280} +{"current_steps": 6110, "total_steps": 122600, "loss": 0.2232, "lr": 0.0004982871125611745, "epoch": 0.9967373572593801, "percentage": 4.98, "elapsed_time": "0:36:10", "remaining_time": "11:29:39", "throughput": 6088.98, "total_tokens": 13215584} +{"current_steps": 6115, "total_steps": 122600, "loss": 0.1846, "lr": 0.0004986949429037521, "epoch": 0.9975530179445351, "percentage": 4.99, "elapsed_time": "0:36:12", "remaining_time": "11:29:38", "throughput": 6088.97, "total_tokens": 13226496} +{"current_steps": 6120, "total_steps": 122600, "loss": 0.1192, "lr": 0.0004991027732463296, "epoch": 0.99836867862969, "percentage": 4.99, "elapsed_time": "0:36:13", "remaining_time": "11:29:35", "throughput": 6088.96, "total_tokens": 13236992} +{"current_steps": 6125, "total_steps": 122600, "loss": 0.2165, "lr": 0.000499510603588907, "epoch": 0.9991843393148451, "percentage": 5.0, "elapsed_time": "0:36:15", "remaining_time": "11:29:32", "throughput": 6088.96, "total_tokens": 13247424} +{"current_steps": 6130, "total_steps": 122600, "loss": 0.1799, "lr": 0.0004999184339314845, "epoch": 1.0, "percentage": 5.0, "elapsed_time": "0:36:17", "remaining_time": "11:29:28", "throughput": 6088.65, "total_tokens": 13256608} +{"current_steps": 6130, "total_steps": 122600, "eval_loss": 0.1398823857307434, "epoch": 1.0, "percentage": 5.0, "elapsed_time": "0:38:00", "remaining_time": "12:02:12", "throughput": 5812.61, "total_tokens": 13256608} +{"current_steps": 6135, "total_steps": 122600, "loss": 0.1257, "lr": 0.000500326264274062, "epoch": 1.000815660685155, "percentage": 5.0, "elapsed_time": "0:38:04", "remaining_time": "12:02:51", "throughput": 5807.66, "total_tokens": 13268544} +{"current_steps": 6140, "total_steps": 122600, "loss": 0.1004, "lr": 0.0005007340946166395, "epoch": 1.0016313213703099, "percentage": 5.01, "elapsed_time": "0:38:06", "remaining_time": "12:02:48", "throughput": 5807.88, "total_tokens": 13279712} +{"current_steps": 6145, "total_steps": 122600, "loss": 0.1524, "lr": 0.0005011419249592169, "epoch": 1.002446982055465, "percentage": 5.01, "elapsed_time": "0:38:08", "remaining_time": "12:02:42", "throughput": 5808.05, "total_tokens": 13289344}