{"current_steps": 5, "total_steps": 61300, "loss": 15.1623, "lr": 3.262642740619902e-08, "epoch": 0.0008156606851549756, "percentage": 0.01, "elapsed_time": "0:00:02", "remaining_time": "8:03:34", "throughput": 3772.17, "total_tokens": 8928} {"current_steps": 10, "total_steps": 61300, "loss": 15.0545, "lr": 7.34094616639478e-08, "epoch": 0.0016313213703099511, "percentage": 0.02, "elapsed_time": "0:00:04", "remaining_time": "8:05:27", "throughput": 4302.7, "total_tokens": 20448} {"current_steps": 15, "total_steps": 61300, "loss": 14.8242, "lr": 1.1419249592169658e-07, "epoch": 0.0024469820554649264, "percentage": 0.02, "elapsed_time": "0:00:06", "remaining_time": "7:55:22", "throughput": 4450.9, "total_tokens": 31072} {"current_steps": 20, "total_steps": 61300, "loss": 14.7497, "lr": 1.5497553017944535e-07, "epoch": 0.0032626427406199023, "percentage": 0.03, "elapsed_time": "0:00:09", "remaining_time": "7:56:58", "throughput": 4553.2, "total_tokens": 42528} {"current_steps": 25, "total_steps": 61300, "loss": 14.8678, "lr": 1.9575856443719413e-07, "epoch": 0.004078303425774877, "percentage": 0.04, "elapsed_time": "0:00:11", "remaining_time": "7:46:36", "throughput": 4602.81, "total_tokens": 52576} {"current_steps": 30, "total_steps": 61300, "loss": 14.9286, "lr": 2.365415986949429e-07, "epoch": 0.004893964110929853, "percentage": 0.05, "elapsed_time": "0:00:13", "remaining_time": "7:42:35", "throughput": 4631.56, "total_tokens": 62944} {"current_steps": 35, "total_steps": 61300, "loss": 14.6226, "lr": 2.773246329526917e-07, "epoch": 0.005709624796084829, "percentage": 0.06, "elapsed_time": "0:00:16", "remaining_time": "7:46:52", "throughput": 4593.05, "total_tokens": 73504} {"current_steps": 40, "total_steps": 61300, "loss": 15.0846, "lr": 3.1810766721044045e-07, "epoch": 0.0065252854812398045, "percentage": 0.07, "elapsed_time": "0:00:18", "remaining_time": "7:47:41", "throughput": 4619.33, "total_tokens": 84640} {"current_steps": 45, "total_steps": 61300, "loss": 14.9394, "lr": 3.5889070146818926e-07, "epoch": 0.00734094616639478, "percentage": 0.07, "elapsed_time": "0:00:20", "remaining_time": "7:51:07", "throughput": 4636.68, "total_tokens": 96288} {"current_steps": 50, "total_steps": 61300, "loss": 14.83, "lr": 3.99673735725938e-07, "epoch": 0.008156606851549755, "percentage": 0.08, "elapsed_time": "0:00:23", "remaining_time": "7:51:22", "throughput": 4650.08, "total_tokens": 107360} {"current_steps": 55, "total_steps": 61300, "loss": 14.8604, "lr": 4.4045676998368683e-07, "epoch": 0.00897226753670473, "percentage": 0.09, "elapsed_time": "0:00:25", "remaining_time": "7:51:32", "throughput": 4661.35, "total_tokens": 118432} {"current_steps": 60, "total_steps": 61300, "loss": 14.7007, "lr": 4.812398042414356e-07, "epoch": 0.009787928221859706, "percentage": 0.1, "elapsed_time": "0:00:27", "remaining_time": "7:47:27", "throughput": 4673.11, "total_tokens": 128416} {"current_steps": 65, "total_steps": 61300, "loss": 14.7743, "lr": 5.220228384991843e-07, "epoch": 0.010603588907014683, "percentage": 0.11, "elapsed_time": "0:00:29", "remaining_time": "7:44:08", "throughput": 4683.02, "total_tokens": 138432} {"current_steps": 70, "total_steps": 61300, "loss": 15.0639, "lr": 5.628058727569332e-07, "epoch": 0.011419249592169658, "percentage": 0.11, "elapsed_time": "0:00:31", "remaining_time": "7:44:58", "throughput": 4687.44, "total_tokens": 149504} {"current_steps": 75, "total_steps": 61300, "loss": 15.0088, "lr": 6.03588907014682e-07, "epoch": 0.012234910277324634, "percentage": 0.12, "elapsed_time": "0:00:34", "remaining_time": "7:44:04", "throughput": 4696.51, "total_tokens": 160192} {"current_steps": 80, "total_steps": 61300, "loss": 14.6747, "lr": 6.443719412724307e-07, "epoch": 0.013050570962479609, "percentage": 0.13, "elapsed_time": "0:00:36", "remaining_time": "7:41:52", "throughput": 4706.28, "total_tokens": 170432} {"current_steps": 85, "total_steps": 61300, "loss": 14.8765, "lr": 6.851549755301795e-07, "epoch": 0.013866231647634585, "percentage": 0.14, "elapsed_time": "0:00:38", "remaining_time": "7:40:19", "throughput": 4711.07, "total_tokens": 180672} {"current_steps": 90, "total_steps": 61300, "loss": 14.6578, "lr": 7.259380097879283e-07, "epoch": 0.01468189233278956, "percentage": 0.15, "elapsed_time": "0:00:40", "remaining_time": "7:41:59", "throughput": 4719.51, "total_tokens": 192352} {"current_steps": 95, "total_steps": 61300, "loss": 14.6515, "lr": 7.66721044045677e-07, "epoch": 0.015497553017944535, "percentage": 0.15, "elapsed_time": "0:00:42", "remaining_time": "7:41:24", "throughput": 4725.0, "total_tokens": 203040} {"current_steps": 100, "total_steps": 61300, "loss": 14.504, "lr": 8.075040783034258e-07, "epoch": 0.01631321370309951, "percentage": 0.16, "elapsed_time": "0:00:45", "remaining_time": "7:42:14", "throughput": 4728.2, "total_tokens": 214272} {"current_steps": 105, "total_steps": 61300, "loss": 14.8303, "lr": 8.482871125611746e-07, "epoch": 0.017128874388254486, "percentage": 0.17, "elapsed_time": "0:00:47", "remaining_time": "7:43:21", "throughput": 4730.68, "total_tokens": 225664} {"current_steps": 110, "total_steps": 61300, "loss": 14.8208, "lr": 8.890701468189233e-07, "epoch": 0.01794453507340946, "percentage": 0.18, "elapsed_time": "0:00:50", "remaining_time": "7:44:32", "throughput": 4734.24, "total_tokens": 237216} {"current_steps": 115, "total_steps": 61300, "loss": 14.9802, "lr": 9.298531810766722e-07, "epoch": 0.018760195758564437, "percentage": 0.19, "elapsed_time": "0:00:52", "remaining_time": "7:41:40", "throughput": 4735.64, "total_tokens": 246560} {"current_steps": 120, "total_steps": 61300, "loss": 14.6534, "lr": 9.70636215334421e-07, "epoch": 0.01957585644371941, "percentage": 0.2, "elapsed_time": "0:00:54", "remaining_time": "7:40:59", "throughput": 4740.54, "total_tokens": 257184} {"current_steps": 125, "total_steps": 61300, "loss": 14.8201, "lr": 1.0114192495921699e-06, "epoch": 0.020391517128874388, "percentage": 0.2, "elapsed_time": "0:00:56", "remaining_time": "7:41:10", "throughput": 4746.9, "total_tokens": 268384} {"current_steps": 130, "total_steps": 61300, "loss": 14.4256, "lr": 1.0522022838499183e-06, "epoch": 0.021207177814029365, "percentage": 0.21, "elapsed_time": "0:00:59", "remaining_time": "7:43:12", "throughput": 4735.12, "total_tokens": 279680} {"current_steps": 135, "total_steps": 61300, "loss": 14.8568, "lr": 1.0929853181076673e-06, "epoch": 0.02202283849918434, "percentage": 0.22, "elapsed_time": "0:01:01", "remaining_time": "7:43:19", "throughput": 4737.53, "total_tokens": 290688} {"current_steps": 140, "total_steps": 61300, "loss": 15.0009, "lr": 1.133768352365416e-06, "epoch": 0.022838499184339316, "percentage": 0.23, "elapsed_time": "0:01:03", "remaining_time": "7:43:04", "throughput": 4739.1, "total_tokens": 301408} {"current_steps": 145, "total_steps": 61300, "loss": 14.4792, "lr": 1.1745513866231649e-06, "epoch": 0.02365415986949429, "percentage": 0.24, "elapsed_time": "0:01:05", "remaining_time": "7:42:26", "throughput": 4742.04, "total_tokens": 311968} {"current_steps": 150, "total_steps": 61300, "loss": 14.6385, "lr": 1.2153344208809136e-06, "epoch": 0.024469820554649267, "percentage": 0.24, "elapsed_time": "0:01:07", "remaining_time": "7:41:12", "throughput": 4744.89, "total_tokens": 322080} {"current_steps": 155, "total_steps": 61300, "loss": 14.6671, "lr": 1.2561174551386625e-06, "epoch": 0.02528548123980424, "percentage": 0.25, "elapsed_time": "0:01:10", "remaining_time": "7:42:22", "throughput": 4746.77, "total_tokens": 333824} {"current_steps": 160, "total_steps": 61300, "loss": 14.4283, "lr": 1.296900489396411e-06, "epoch": 0.026101141924959218, "percentage": 0.26, "elapsed_time": "0:01:12", "remaining_time": "7:42:17", "throughput": 4751.53, "total_tokens": 344896} {"current_steps": 165, "total_steps": 61300, "loss": 14.8793, "lr": 1.33768352365416e-06, "epoch": 0.026916802610114192, "percentage": 0.27, "elapsed_time": "0:01:14", "remaining_time": "7:42:36", "throughput": 4754.72, "total_tokens": 356192} {"current_steps": 170, "total_steps": 61300, "loss": 14.8702, "lr": 1.3784665579119086e-06, "epoch": 0.02773246329526917, "percentage": 0.28, "elapsed_time": "0:01:17", "remaining_time": "7:42:32", "throughput": 4757.0, "total_tokens": 367136} {"current_steps": 175, "total_steps": 61300, "loss": 14.5627, "lr": 1.4192495921696575e-06, "epoch": 0.028548123980424143, "percentage": 0.29, "elapsed_time": "0:01:19", "remaining_time": "7:40:49", "throughput": 4760.43, "total_tokens": 376832} {"current_steps": 180, "total_steps": 61300, "loss": 14.8531, "lr": 1.4600326264274062e-06, "epoch": 0.02936378466557912, "percentage": 0.29, "elapsed_time": "0:01:21", "remaining_time": "7:40:26", "throughput": 4763.31, "total_tokens": 387552} {"current_steps": 185, "total_steps": 61300, "loss": 14.8937, "lr": 1.5008156606851552e-06, "epoch": 0.030179445350734094, "percentage": 0.3, "elapsed_time": "0:01:23", "remaining_time": "7:40:38", "throughput": 4763.47, "total_tokens": 398528} {"current_steps": 190, "total_steps": 61300, "loss": 14.7283, "lr": 1.5415986949429036e-06, "epoch": 0.03099510603588907, "percentage": 0.31, "elapsed_time": "0:01:25", "remaining_time": "7:40:02", "throughput": 4764.53, "total_tokens": 408896} {"current_steps": 195, "total_steps": 61300, "loss": 14.6755, "lr": 1.5823817292006523e-06, "epoch": 0.03181076672104405, "percentage": 0.32, "elapsed_time": "0:01:28", "remaining_time": "7:40:35", "throughput": 4767.04, "total_tokens": 420416} {"current_steps": 200, "total_steps": 61300, "loss": 14.6526, "lr": 1.6231647634584013e-06, "epoch": 0.03262642740619902, "percentage": 0.33, "elapsed_time": "0:01:30", "remaining_time": "7:40:15", "throughput": 4767.03, "total_tokens": 430912} {"current_steps": 205, "total_steps": 61300, "loss": 14.5063, "lr": 1.6639477977161502e-06, "epoch": 0.033442088091353996, "percentage": 0.33, "elapsed_time": "0:01:32", "remaining_time": "7:40:31", "throughput": 4769.21, "total_tokens": 442176} {"current_steps": 210, "total_steps": 61300, "loss": 14.6935, "lr": 1.704730831973899e-06, "epoch": 0.03425774877650897, "percentage": 0.34, "elapsed_time": "0:01:35", "remaining_time": "7:42:02", "throughput": 4769.21, "total_tokens": 454496} {"current_steps": 215, "total_steps": 61300, "loss": 14.3141, "lr": 1.7455138662316478e-06, "epoch": 0.03507340946166395, "percentage": 0.35, "elapsed_time": "0:01:37", "remaining_time": "7:41:25", "throughput": 4770.83, "total_tokens": 464896} {"current_steps": 220, "total_steps": 61300, "loss": 14.9884, "lr": 1.7862969004893963e-06, "epoch": 0.03588907014681892, "percentage": 0.36, "elapsed_time": "0:01:39", "remaining_time": "7:42:41", "throughput": 4770.66, "total_tokens": 477024} {"current_steps": 225, "total_steps": 61300, "loss": 14.4509, "lr": 1.8270799347471452e-06, "epoch": 0.0367047308319739, "percentage": 0.37, "elapsed_time": "0:01:42", "remaining_time": "7:42:35", "throughput": 4770.41, "total_tokens": 487776} {"current_steps": 230, "total_steps": 61300, "loss": 14.3354, "lr": 1.8678629690048941e-06, "epoch": 0.037520391517128875, "percentage": 0.38, "elapsed_time": "0:01:44", "remaining_time": "7:42:21", "throughput": 4771.49, "total_tokens": 498528} {"current_steps": 235, "total_steps": 61300, "loss": 14.6222, "lr": 1.908646003262643e-06, "epoch": 0.03833605220228385, "percentage": 0.38, "elapsed_time": "0:01:46", "remaining_time": "7:42:03", "throughput": 4772.57, "total_tokens": 509184} {"current_steps": 240, "total_steps": 61300, "loss": 14.5586, "lr": 1.9494290375203913e-06, "epoch": 0.03915171288743882, "percentage": 0.39, "elapsed_time": "0:01:48", "remaining_time": "7:42:08", "throughput": 4773.16, "total_tokens": 520224} {"current_steps": 245, "total_steps": 61300, "loss": 14.809, "lr": 1.9902120717781402e-06, "epoch": 0.0399673735725938, "percentage": 0.4, "elapsed_time": "0:01:51", "remaining_time": "7:41:30", "throughput": 4773.94, "total_tokens": 530464} {"current_steps": 250, "total_steps": 61300, "loss": 14.6627, "lr": 2.030995106035889e-06, "epoch": 0.040783034257748776, "percentage": 0.41, "elapsed_time": "0:01:53", "remaining_time": "7:41:50", "throughput": 4775.9, "total_tokens": 541952} {"current_steps": 255, "total_steps": 61300, "loss": 14.4551, "lr": 2.071778140293638e-06, "epoch": 0.041598694942903754, "percentage": 0.42, "elapsed_time": "0:01:55", "remaining_time": "7:40:36", "throughput": 4776.53, "total_tokens": 551424} {"current_steps": 260, "total_steps": 61300, "loss": 14.5698, "lr": 2.1125611745513866e-06, "epoch": 0.04241435562805873, "percentage": 0.42, "elapsed_time": "0:01:57", "remaining_time": "7:39:51", "throughput": 4777.16, "total_tokens": 561440} {"current_steps": 265, "total_steps": 61300, "loss": 14.7042, "lr": 2.1533442088091355e-06, "epoch": 0.0432300163132137, "percentage": 0.43, "elapsed_time": "0:02:00", "remaining_time": "7:40:47", "throughput": 4777.16, "total_tokens": 573440} {"current_steps": 270, "total_steps": 61300, "loss": 14.3967, "lr": 2.1941272430668844e-06, "epoch": 0.04404567699836868, "percentage": 0.44, "elapsed_time": "0:02:02", "remaining_time": "7:40:30", "throughput": 4777.75, "total_tokens": 584032} {"current_steps": 275, "total_steps": 61300, "loss": 14.5015, "lr": 2.2349102773246333e-06, "epoch": 0.044861337683523655, "percentage": 0.45, "elapsed_time": "0:02:04", "remaining_time": "7:40:45", "throughput": 4778.65, "total_tokens": 595328} {"current_steps": 280, "total_steps": 61300, "loss": 14.283, "lr": 2.275693311582382e-06, "epoch": 0.04567699836867863, "percentage": 0.46, "elapsed_time": "0:02:06", "remaining_time": "7:40:21", "throughput": 4779.26, "total_tokens": 605760} {"current_steps": 285, "total_steps": 61300, "loss": 14.5534, "lr": 2.3164763458401307e-06, "epoch": 0.0464926590538336, "percentage": 0.46, "elapsed_time": "0:02:08", "remaining_time": "7:40:03", "throughput": 4780.56, "total_tokens": 616384} {"current_steps": 290, "total_steps": 61300, "loss": 14.3892, "lr": 2.357259380097879e-06, "epoch": 0.04730831973898858, "percentage": 0.47, "elapsed_time": "0:02:11", "remaining_time": "7:39:46", "throughput": 4780.64, "total_tokens": 626880} {"current_steps": 295, "total_steps": 61300, "loss": 14.6321, "lr": 2.398042414355628e-06, "epoch": 0.04812398042414356, "percentage": 0.48, "elapsed_time": "0:02:13", "remaining_time": "7:39:34", "throughput": 4781.27, "total_tokens": 637536} {"current_steps": 300, "total_steps": 61300, "loss": 14.9084, "lr": 2.4388254486133766e-06, "epoch": 0.048939641109298535, "percentage": 0.49, "elapsed_time": "0:02:15", "remaining_time": "7:39:20", "throughput": 4780.7, "total_tokens": 648000} {"current_steps": 305, "total_steps": 61300, "loss": 14.2795, "lr": 2.4796084828711255e-06, "epoch": 0.049755301794453505, "percentage": 0.5, "elapsed_time": "0:02:17", "remaining_time": "7:39:56", "throughput": 4780.31, "total_tokens": 659648} {"current_steps": 310, "total_steps": 61300, "loss": 14.5585, "lr": 2.5203915171288745e-06, "epoch": 0.05057096247960848, "percentage": 0.51, "elapsed_time": "0:02:20", "remaining_time": "7:39:23", "throughput": 4781.78, "total_tokens": 669920} {"current_steps": 315, "total_steps": 61300, "loss": 14.3678, "lr": 2.5611745513866234e-06, "epoch": 0.05138662316476346, "percentage": 0.51, "elapsed_time": "0:02:22", "remaining_time": "7:39:34", "throughput": 4782.88, "total_tokens": 681216} {"current_steps": 320, "total_steps": 61300, "loss": 14.1811, "lr": 2.6019575856443723e-06, "epoch": 0.052202283849918436, "percentage": 0.52, "elapsed_time": "0:02:24", "remaining_time": "7:39:29", "throughput": 4782.33, "total_tokens": 691872} {"current_steps": 325, "total_steps": 61300, "loss": 14.3752, "lr": 2.6427406199021208e-06, "epoch": 0.05301794453507341, "percentage": 0.53, "elapsed_time": "0:02:26", "remaining_time": "7:39:06", "throughput": 4782.69, "total_tokens": 702208} {"current_steps": 330, "total_steps": 61300, "loss": 14.3375, "lr": 2.6835236541598697e-06, "epoch": 0.053833605220228384, "percentage": 0.54, "elapsed_time": "0:02:28", "remaining_time": "7:38:29", "throughput": 4783.82, "total_tokens": 712288} {"current_steps": 335, "total_steps": 61300, "loss": 14.4406, "lr": 2.7243066884176186e-06, "epoch": 0.05464926590538336, "percentage": 0.55, "elapsed_time": "0:02:31", "remaining_time": "7:38:23", "throughput": 4783.71, "total_tokens": 722976} {"current_steps": 340, "total_steps": 61300, "loss": 14.4012, "lr": 2.7650897226753675e-06, "epoch": 0.05546492659053834, "percentage": 0.55, "elapsed_time": "0:02:33", "remaining_time": "7:38:20", "throughput": 4783.81, "total_tokens": 733760} {"current_steps": 345, "total_steps": 61300, "loss": 14.3605, "lr": 2.805872756933116e-06, "epoch": 0.05628058727569331, "percentage": 0.56, "elapsed_time": "0:02:35", "remaining_time": "7:37:32", "throughput": 4785.23, "total_tokens": 743520} {"current_steps": 350, "total_steps": 61300, "loss": 14.2369, "lr": 2.8466557911908645e-06, "epoch": 0.057096247960848286, "percentage": 0.57, "elapsed_time": "0:02:37", "remaining_time": "7:37:19", "throughput": 4785.05, "total_tokens": 753984} {"current_steps": 355, "total_steps": 61300, "loss": 13.9977, "lr": 2.8874388254486134e-06, "epoch": 0.05791190864600326, "percentage": 0.58, "elapsed_time": "0:02:39", "remaining_time": "7:37:30", "throughput": 4786.63, "total_tokens": 765376} {"current_steps": 360, "total_steps": 61300, "loss": 14.5583, "lr": 2.9282218597063623e-06, "epoch": 0.05872756933115824, "percentage": 0.59, "elapsed_time": "0:02:42", "remaining_time": "7:37:15", "throughput": 4787.36, "total_tokens": 775904} {"current_steps": 365, "total_steps": 61300, "loss": 14.3893, "lr": 2.969004893964111e-06, "epoch": 0.05954323001631321, "percentage": 0.6, "elapsed_time": "0:02:44", "remaining_time": "7:37:52", "throughput": 4788.5, "total_tokens": 788000} {"current_steps": 370, "total_steps": 61300, "loss": 14.3673, "lr": 3.0097879282218597e-06, "epoch": 0.06035889070146819, "percentage": 0.6, "elapsed_time": "0:02:46", "remaining_time": "7:37:51", "throughput": 4788.5, "total_tokens": 798816} {"current_steps": 375, "total_steps": 61300, "loss": 14.0826, "lr": 3.0505709624796087e-06, "epoch": 0.061174551386623165, "percentage": 0.61, "elapsed_time": "0:02:49", "remaining_time": "7:37:56", "throughput": 4788.61, "total_tokens": 809856} {"current_steps": 380, "total_steps": 61300, "loss": 13.892, "lr": 3.0913539967373576e-06, "epoch": 0.06199021207177814, "percentage": 0.62, "elapsed_time": "0:02:51", "remaining_time": "7:37:47", "throughput": 4788.61, "total_tokens": 820448} {"current_steps": 385, "total_steps": 61300, "loss": 14.1292, "lr": 3.132137030995106e-06, "epoch": 0.06280587275693311, "percentage": 0.63, "elapsed_time": "0:02:53", "remaining_time": "7:37:25", "throughput": 4788.44, "total_tokens": 830624} {"current_steps": 390, "total_steps": 61300, "loss": 14.1347, "lr": 3.1729200652528554e-06, "epoch": 0.0636215334420881, "percentage": 0.64, "elapsed_time": "0:02:55", "remaining_time": "7:36:49", "throughput": 4787.67, "total_tokens": 840224} {"current_steps": 395, "total_steps": 61300, "loss": 14.342, "lr": 3.213703099510604e-06, "epoch": 0.06443719412724307, "percentage": 0.64, "elapsed_time": "0:02:57", "remaining_time": "7:36:16", "throughput": 4788.34, "total_tokens": 850176} {"current_steps": 400, "total_steps": 61300, "loss": 14.2821, "lr": 3.2544861337683524e-06, "epoch": 0.06525285481239804, "percentage": 0.65, "elapsed_time": "0:02:59", "remaining_time": "7:36:14", "throughput": 4788.97, "total_tokens": 861056} {"current_steps": 405, "total_steps": 61300, "loss": 14.2256, "lr": 3.2952691680261013e-06, "epoch": 0.06606851549755302, "percentage": 0.66, "elapsed_time": "0:03:01", "remaining_time": "7:35:59", "throughput": 4788.71, "total_tokens": 871360} {"current_steps": 410, "total_steps": 61300, "loss": 14.3096, "lr": 3.33605220228385e-06, "epoch": 0.06688417618270799, "percentage": 0.67, "elapsed_time": "0:03:04", "remaining_time": "7:36:14", "throughput": 4788.54, "total_tokens": 882656} {"current_steps": 415, "total_steps": 61300, "loss": 13.9502, "lr": 3.3768352365415987e-06, "epoch": 0.06769983686786298, "percentage": 0.68, "elapsed_time": "0:03:06", "remaining_time": "7:36:26", "throughput": 4788.9, "total_tokens": 893952} {"current_steps": 420, "total_steps": 61300, "loss": 14.1761, "lr": 3.4176182707993476e-06, "epoch": 0.06851549755301795, "percentage": 0.69, "elapsed_time": "0:03:09", "remaining_time": "7:36:39", "throughput": 4790.16, "total_tokens": 905472} {"current_steps": 425, "total_steps": 61300, "loss": 13.8787, "lr": 3.458401305057096e-06, "epoch": 0.06933115823817292, "percentage": 0.69, "elapsed_time": "0:03:11", "remaining_time": "7:36:26", "throughput": 4790.73, "total_tokens": 916000} {"current_steps": 430, "total_steps": 61300, "loss": 14.339, "lr": 3.4991843393148455e-06, "epoch": 0.0701468189233279, "percentage": 0.7, "elapsed_time": "0:03:13", "remaining_time": "7:36:24", "throughput": 4791.58, "total_tokens": 926944} {"current_steps": 435, "total_steps": 61300, "loss": 13.8756, "lr": 3.539967373572594e-06, "epoch": 0.07096247960848287, "percentage": 0.71, "elapsed_time": "0:03:15", "remaining_time": "7:36:46", "throughput": 4791.42, "total_tokens": 938496} {"current_steps": 440, "total_steps": 61300, "loss": 14.0589, "lr": 3.5807504078303425e-06, "epoch": 0.07177814029363784, "percentage": 0.72, "elapsed_time": "0:03:18", "remaining_time": "7:36:45", "throughput": 4792.04, "total_tokens": 949472} {"current_steps": 445, "total_steps": 61300, "loss": 13.8606, "lr": 3.621533442088092e-06, "epoch": 0.07259380097879282, "percentage": 0.73, "elapsed_time": "0:03:20", "remaining_time": "7:36:25", "throughput": 4792.46, "total_tokens": 959712} {"current_steps": 450, "total_steps": 61300, "loss": 13.8254, "lr": 3.6623164763458403e-06, "epoch": 0.0734094616639478, "percentage": 0.73, "elapsed_time": "0:03:22", "remaining_time": "7:36:01", "throughput": 4793.24, "total_tokens": 969888} {"current_steps": 455, "total_steps": 61300, "loss": 14.2285, "lr": 3.7030995106035896e-06, "epoch": 0.07422512234910278, "percentage": 0.74, "elapsed_time": "0:03:24", "remaining_time": "7:36:14", "throughput": 4792.37, "total_tokens": 981024} {"current_steps": 460, "total_steps": 61300, "loss": 13.684, "lr": 3.743882544861338e-06, "epoch": 0.07504078303425775, "percentage": 0.75, "elapsed_time": "0:03:26", "remaining_time": "7:36:05", "throughput": 4792.93, "total_tokens": 991680} {"current_steps": 465, "total_steps": 61300, "loss": 13.7857, "lr": 3.7846655791190866e-06, "epoch": 0.07585644371941272, "percentage": 0.76, "elapsed_time": "0:03:29", "remaining_time": "7:36:15", "throughput": 4793.43, "total_tokens": 1003008} {"current_steps": 470, "total_steps": 61300, "loss": 13.7496, "lr": 3.8254486133768355e-06, "epoch": 0.0766721044045677, "percentage": 0.77, "elapsed_time": "0:03:31", "remaining_time": "7:36:28", "throughput": 4793.29, "total_tokens": 1014336} {"current_steps": 475, "total_steps": 61300, "loss": 13.6239, "lr": 3.866231647634584e-06, "epoch": 0.07748776508972267, "percentage": 0.77, "elapsed_time": "0:03:33", "remaining_time": "7:36:16", "throughput": 4794.19, "total_tokens": 1024960} {"current_steps": 480, "total_steps": 61300, "loss": 13.7562, "lr": 3.9070146818923325e-06, "epoch": 0.07830342577487764, "percentage": 0.78, "elapsed_time": "0:03:35", "remaining_time": "7:35:51", "throughput": 4794.17, "total_tokens": 1034880} {"current_steps": 485, "total_steps": 61300, "loss": 13.8266, "lr": 3.947797716150082e-06, "epoch": 0.07911908646003263, "percentage": 0.79, "elapsed_time": "0:03:38", "remaining_time": "7:35:58", "throughput": 4794.56, "total_tokens": 1046112} {"current_steps": 490, "total_steps": 61300, "loss": 13.9376, "lr": 3.98858075040783e-06, "epoch": 0.0799347471451876, "percentage": 0.8, "elapsed_time": "0:03:40", "remaining_time": "7:35:55", "throughput": 4794.67, "total_tokens": 1056864} {"current_steps": 495, "total_steps": 61300, "loss": 13.6913, "lr": 4.02936378466558e-06, "epoch": 0.08075040783034258, "percentage": 0.81, "elapsed_time": "0:03:42", "remaining_time": "7:35:32", "throughput": 4795.72, "total_tokens": 1067072} {"current_steps": 500, "total_steps": 61300, "loss": 13.6799, "lr": 4.070146818923328e-06, "epoch": 0.08156606851549755, "percentage": 0.82, "elapsed_time": "0:03:45", "remaining_time": "7:36:00", "throughput": 4796.11, "total_tokens": 1079136} {"current_steps": 505, "total_steps": 61300, "loss": 13.5227, "lr": 4.110929853181077e-06, "epoch": 0.08238172920065252, "percentage": 0.82, "elapsed_time": "0:03:47", "remaining_time": "7:35:49", "throughput": 4795.34, "total_tokens": 1089408} {"current_steps": 510, "total_steps": 61300, "loss": 13.4503, "lr": 4.151712887438826e-06, "epoch": 0.08319738988580751, "percentage": 0.83, "elapsed_time": "0:03:49", "remaining_time": "7:35:31", "throughput": 4794.92, "total_tokens": 1099488} {"current_steps": 515, "total_steps": 61300, "loss": 13.9909, "lr": 4.1924959216965745e-06, "epoch": 0.08401305057096248, "percentage": 0.84, "elapsed_time": "0:03:51", "remaining_time": "7:35:32", "throughput": 4795.33, "total_tokens": 1110464} {"current_steps": 520, "total_steps": 61300, "loss": 13.598, "lr": 4.233278955954323e-06, "epoch": 0.08482871125611746, "percentage": 0.85, "elapsed_time": "0:03:53", "remaining_time": "7:35:29", "throughput": 4795.25, "total_tokens": 1121216} {"current_steps": 525, "total_steps": 61300, "loss": 13.7071, "lr": 4.274061990212072e-06, "epoch": 0.08564437194127243, "percentage": 0.86, "elapsed_time": "0:03:56", "remaining_time": "7:35:32", "throughput": 4795.24, "total_tokens": 1132192} {"current_steps": 530, "total_steps": 61300, "loss": 13.7415, "lr": 4.314845024469821e-06, "epoch": 0.0864600326264274, "percentage": 0.86, "elapsed_time": "0:03:58", "remaining_time": "7:35:31", "throughput": 4794.85, "total_tokens": 1142944} {"current_steps": 535, "total_steps": 61300, "loss": 13.3109, "lr": 4.35562805872757e-06, "epoch": 0.08727569331158239, "percentage": 0.87, "elapsed_time": "0:04:00", "remaining_time": "7:35:32", "throughput": 4795.74, "total_tokens": 1154080} {"current_steps": 540, "total_steps": 61300, "loss": 13.4403, "lr": 4.396411092985319e-06, "epoch": 0.08809135399673736, "percentage": 0.88, "elapsed_time": "0:04:02", "remaining_time": "7:35:41", "throughput": 4794.78, "total_tokens": 1165120} {"current_steps": 545, "total_steps": 61300, "loss": 13.3113, "lr": 4.437194127243067e-06, "epoch": 0.08890701468189233, "percentage": 0.89, "elapsed_time": "0:04:05", "remaining_time": "7:35:52", "throughput": 4794.39, "total_tokens": 1176352} {"current_steps": 550, "total_steps": 61300, "loss": 13.5064, "lr": 4.477977161500816e-06, "epoch": 0.08972267536704731, "percentage": 0.9, "elapsed_time": "0:04:07", "remaining_time": "7:36:10", "throughput": 4795.37, "total_tokens": 1188288} {"current_steps": 555, "total_steps": 61300, "loss": 13.4279, "lr": 4.518760195758565e-06, "epoch": 0.09053833605220228, "percentage": 0.91, "elapsed_time": "0:04:10", "remaining_time": "7:36:43", "throughput": 4795.95, "total_tokens": 1200800} {"current_steps": 560, "total_steps": 61300, "loss": 13.6278, "lr": 4.5595432300163135e-06, "epoch": 0.09135399673735727, "percentage": 0.91, "elapsed_time": "0:04:12", "remaining_time": "7:36:38", "throughput": 4795.54, "total_tokens": 1211360} {"current_steps": 565, "total_steps": 61300, "loss": 13.1975, "lr": 4.600326264274062e-06, "epoch": 0.09216965742251224, "percentage": 0.92, "elapsed_time": "0:04:14", "remaining_time": "7:36:10", "throughput": 4796.08, "total_tokens": 1221184} {"current_steps": 570, "total_steps": 61300, "loss": 13.3059, "lr": 4.6411092985318105e-06, "epoch": 0.0929853181076672, "percentage": 0.93, "elapsed_time": "0:04:16", "remaining_time": "7:36:05", "throughput": 4795.92, "total_tokens": 1231808} {"current_steps": 575, "total_steps": 61300, "loss": 13.1034, "lr": 4.68189233278956e-06, "epoch": 0.09380097879282219, "percentage": 0.94, "elapsed_time": "0:04:19", "remaining_time": "7:35:58", "throughput": 4796.53, "total_tokens": 1242560} {"current_steps": 580, "total_steps": 61300, "loss": 13.2515, "lr": 4.722675367047308e-06, "epoch": 0.09461663947797716, "percentage": 0.95, "elapsed_time": "0:04:21", "remaining_time": "7:35:58", "throughput": 4796.39, "total_tokens": 1253440} {"current_steps": 585, "total_steps": 61300, "loss": 13.1274, "lr": 4.763458401305057e-06, "epoch": 0.09543230016313213, "percentage": 0.95, "elapsed_time": "0:04:23", "remaining_time": "7:35:44", "throughput": 4796.14, "total_tokens": 1263616} {"current_steps": 590, "total_steps": 61300, "loss": 13.0282, "lr": 4.804241435562806e-06, "epoch": 0.09624796084828711, "percentage": 0.96, "elapsed_time": "0:04:25", "remaining_time": "7:36:02", "throughput": 4796.53, "total_tokens": 1275488} {"current_steps": 595, "total_steps": 61300, "loss": 12.8156, "lr": 4.845024469820555e-06, "epoch": 0.09706362153344208, "percentage": 0.97, "elapsed_time": "0:04:28", "remaining_time": "7:36:17", "throughput": 4796.85, "total_tokens": 1287200} {"current_steps": 600, "total_steps": 61300, "loss": 13.2093, "lr": 4.885807504078304e-06, "epoch": 0.09787928221859707, "percentage": 0.98, "elapsed_time": "0:04:30", "remaining_time": "7:36:23", "throughput": 4796.62, "total_tokens": 1298336} {"current_steps": 605, "total_steps": 61300, "loss": 13.2613, "lr": 4.9265905383360524e-06, "epoch": 0.09869494290375204, "percentage": 0.99, "elapsed_time": "0:04:32", "remaining_time": "7:36:19", "throughput": 4796.51, "total_tokens": 1309056} {"current_steps": 610, "total_steps": 61300, "loss": 12.6064, "lr": 4.967373572593801e-06, "epoch": 0.09951060358890701, "percentage": 1.0, "elapsed_time": "0:04:35", "remaining_time": "7:36:38", "throughput": 4796.48, "total_tokens": 1320864} {"current_steps": 615, "total_steps": 61300, "loss": 13.0685, "lr": 5.00815660685155e-06, "epoch": 0.100326264274062, "percentage": 1.0, "elapsed_time": "0:04:37", "remaining_time": "7:36:47", "throughput": 4797.25, "total_tokens": 1332448} {"current_steps": 620, "total_steps": 61300, "loss": 12.9159, "lr": 5.048939641109299e-06, "epoch": 0.10114192495921696, "percentage": 1.01, "elapsed_time": "0:04:39", "remaining_time": "7:36:27", "throughput": 4797.04, "total_tokens": 1342368} {"current_steps": 625, "total_steps": 61300, "loss": 12.8462, "lr": 5.089722675367047e-06, "epoch": 0.10195758564437195, "percentage": 1.02, "elapsed_time": "0:04:42", "remaining_time": "7:36:23", "throughput": 4796.76, "total_tokens": 1353024} {"current_steps": 630, "total_steps": 61300, "loss": 12.945, "lr": 5.130505709624797e-06, "epoch": 0.10277324632952692, "percentage": 1.03, "elapsed_time": "0:04:44", "remaining_time": "7:36:23", "throughput": 4796.83, "total_tokens": 1364000} {"current_steps": 635, "total_steps": 61300, "loss": 12.8368, "lr": 5.171288743882545e-06, "epoch": 0.10358890701468189, "percentage": 1.04, "elapsed_time": "0:04:46", "remaining_time": "7:36:20", "throughput": 4796.82, "total_tokens": 1374784} {"current_steps": 640, "total_steps": 61300, "loss": 12.7271, "lr": 5.2120717781402944e-06, "epoch": 0.10440456769983687, "percentage": 1.04, "elapsed_time": "0:04:48", "remaining_time": "7:35:50", "throughput": 4796.78, "total_tokens": 1384192} {"current_steps": 645, "total_steps": 61300, "loss": 12.7658, "lr": 5.252854812398043e-06, "epoch": 0.10522022838499184, "percentage": 1.05, "elapsed_time": "0:04:50", "remaining_time": "7:35:55", "throughput": 4796.9, "total_tokens": 1395392} {"current_steps": 650, "total_steps": 61300, "loss": 12.7647, "lr": 5.293637846655791e-06, "epoch": 0.10603588907014681, "percentage": 1.06, "elapsed_time": "0:04:53", "remaining_time": "7:35:53", "throughput": 4796.85, "total_tokens": 1406208} {"current_steps": 655, "total_steps": 61300, "loss": 12.6271, "lr": 5.334420880913541e-06, "epoch": 0.1068515497553018, "percentage": 1.07, "elapsed_time": "0:04:55", "remaining_time": "7:35:51", "throughput": 4796.73, "total_tokens": 1417024} {"current_steps": 660, "total_steps": 61300, "loss": 13.0394, "lr": 5.375203915171289e-06, "epoch": 0.10766721044045677, "percentage": 1.08, "elapsed_time": "0:04:57", "remaining_time": "7:35:50", "throughput": 4796.5, "total_tokens": 1427808} {"current_steps": 665, "total_steps": 61300, "loss": 12.7137, "lr": 5.415986949429038e-06, "epoch": 0.10848287112561175, "percentage": 1.08, "elapsed_time": "0:04:59", "remaining_time": "7:35:21", "throughput": 4796.93, "total_tokens": 1437344} {"current_steps": 670, "total_steps": 61300, "loss": 12.8953, "lr": 5.456769983686786e-06, "epoch": 0.10929853181076672, "percentage": 1.09, "elapsed_time": "0:05:01", "remaining_time": "7:35:21", "throughput": 4797.21, "total_tokens": 1448352} {"current_steps": 675, "total_steps": 61300, "loss": 12.554, "lr": 5.4975530179445356e-06, "epoch": 0.11011419249592169, "percentage": 1.1, "elapsed_time": "0:05:04", "remaining_time": "7:35:23", "throughput": 4797.51, "total_tokens": 1459520} {"current_steps": 680, "total_steps": 61300, "loss": 12.7628, "lr": 5.538336052202284e-06, "epoch": 0.11092985318107668, "percentage": 1.11, "elapsed_time": "0:05:06", "remaining_time": "7:35:25", "throughput": 4797.19, "total_tokens": 1470432} {"current_steps": 685, "total_steps": 61300, "loss": 12.5045, "lr": 5.5791190864600326e-06, "epoch": 0.11174551386623165, "percentage": 1.12, "elapsed_time": "0:05:08", "remaining_time": "7:35:11", "throughput": 4797.0, "total_tokens": 1480544} {"current_steps": 690, "total_steps": 61300, "loss": 12.0854, "lr": 5.619902120717781e-06, "epoch": 0.11256117455138662, "percentage": 1.13, "elapsed_time": "0:05:10", "remaining_time": "7:34:58", "throughput": 4796.87, "total_tokens": 1490752} {"current_steps": 695, "total_steps": 61300, "loss": 12.9431, "lr": 5.66068515497553e-06, "epoch": 0.1133768352365416, "percentage": 1.13, "elapsed_time": "0:05:13", "remaining_time": "7:35:09", "throughput": 4796.85, "total_tokens": 1502240} {"current_steps": 700, "total_steps": 61300, "loss": 12.2025, "lr": 5.701468189233279e-06, "epoch": 0.11419249592169657, "percentage": 1.14, "elapsed_time": "0:05:15", "remaining_time": "7:34:51", "throughput": 4797.07, "total_tokens": 1512256} {"current_steps": 705, "total_steps": 61300, "loss": 12.3556, "lr": 5.742251223491028e-06, "epoch": 0.11500815660685156, "percentage": 1.15, "elapsed_time": "0:05:17", "remaining_time": "7:34:49", "throughput": 4797.27, "total_tokens": 1523168} {"current_steps": 710, "total_steps": 61300, "loss": 12.3095, "lr": 5.783034257748777e-06, "epoch": 0.11582381729200653, "percentage": 1.16, "elapsed_time": "0:05:19", "remaining_time": "7:35:03", "throughput": 4797.67, "total_tokens": 1534976} {"current_steps": 715, "total_steps": 61300, "loss": 12.1686, "lr": 5.823817292006525e-06, "epoch": 0.1166394779771615, "percentage": 1.17, "elapsed_time": "0:05:22", "remaining_time": "7:35:02", "throughput": 4797.65, "total_tokens": 1545856} {"current_steps": 720, "total_steps": 61300, "loss": 12.2451, "lr": 5.8646003262642745e-06, "epoch": 0.11745513866231648, "percentage": 1.17, "elapsed_time": "0:05:24", "remaining_time": "7:34:42", "throughput": 4797.63, "total_tokens": 1555680} {"current_steps": 725, "total_steps": 61300, "loss": 11.9348, "lr": 5.905383360522023e-06, "epoch": 0.11827079934747145, "percentage": 1.18, "elapsed_time": "0:05:26", "remaining_time": "7:34:54", "throughput": 4797.8, "total_tokens": 1567328} {"current_steps": 730, "total_steps": 61300, "loss": 12.249, "lr": 5.9461663947797715e-06, "epoch": 0.11908646003262642, "percentage": 1.19, "elapsed_time": "0:05:28", "remaining_time": "7:34:33", "throughput": 4798.17, "total_tokens": 1577184} {"current_steps": 735, "total_steps": 61300, "loss": 12.2179, "lr": 5.986949429037521e-06, "epoch": 0.1199021207177814, "percentage": 1.2, "elapsed_time": "0:05:31", "remaining_time": "7:34:39", "throughput": 4798.42, "total_tokens": 1588544} {"current_steps": 740, "total_steps": 61300, "loss": 12.1793, "lr": 6.027732463295269e-06, "epoch": 0.12071778140293637, "percentage": 1.21, "elapsed_time": "0:05:33", "remaining_time": "7:34:41", "throughput": 4798.51, "total_tokens": 1599648} {"current_steps": 745, "total_steps": 61300, "loss": 12.2187, "lr": 6.068515497553019e-06, "epoch": 0.12153344208809136, "percentage": 1.22, "elapsed_time": "0:05:35", "remaining_time": "7:35:03", "throughput": 4799.2, "total_tokens": 1612096} {"current_steps": 750, "total_steps": 61300, "loss": 11.9602, "lr": 6.109298531810767e-06, "epoch": 0.12234910277324633, "percentage": 1.22, "elapsed_time": "0:05:38", "remaining_time": "7:35:09", "throughput": 4799.67, "total_tokens": 1623584} {"current_steps": 755, "total_steps": 61300, "loss": 12.1736, "lr": 6.150081566068516e-06, "epoch": 0.1231647634584013, "percentage": 1.23, "elapsed_time": "0:05:40", "remaining_time": "7:35:10", "throughput": 4799.89, "total_tokens": 1634688} {"current_steps": 760, "total_steps": 61300, "loss": 11.9697, "lr": 6.190864600326265e-06, "epoch": 0.12398042414355628, "percentage": 1.24, "elapsed_time": "0:05:42", "remaining_time": "7:35:10", "throughput": 4799.77, "total_tokens": 1645600} {"current_steps": 765, "total_steps": 61300, "loss": 11.9528, "lr": 6.2316476345840135e-06, "epoch": 0.12479608482871125, "percentage": 1.25, "elapsed_time": "0:05:45", "remaining_time": "7:35:03", "throughput": 4799.37, "total_tokens": 1655968} {"current_steps": 770, "total_steps": 61300, "loss": 12.062, "lr": 6.272430668841763e-06, "epoch": 0.12561174551386622, "percentage": 1.26, "elapsed_time": "0:05:47", "remaining_time": "7:35:00", "throughput": 4799.67, "total_tokens": 1666848} {"current_steps": 775, "total_steps": 61300, "loss": 11.8152, "lr": 6.3132137030995105e-06, "epoch": 0.1264274061990212, "percentage": 1.26, "elapsed_time": "0:05:49", "remaining_time": "7:34:39", "throughput": 4799.56, "total_tokens": 1676512} {"current_steps": 780, "total_steps": 61300, "loss": 11.7803, "lr": 6.35399673735726e-06, "epoch": 0.1272430668841762, "percentage": 1.27, "elapsed_time": "0:05:51", "remaining_time": "7:34:40", "throughput": 4799.42, "total_tokens": 1687488} {"current_steps": 785, "total_steps": 61300, "loss": 12.0575, "lr": 6.394779771615008e-06, "epoch": 0.12805872756933115, "percentage": 1.28, "elapsed_time": "0:05:53", "remaining_time": "7:34:22", "throughput": 4799.45, "total_tokens": 1697312} {"current_steps": 790, "total_steps": 61300, "loss": 11.8554, "lr": 6.435562805872757e-06, "epoch": 0.12887438825448613, "percentage": 1.29, "elapsed_time": "0:05:55", "remaining_time": "7:34:20", "throughput": 4799.23, "total_tokens": 1708096} {"current_steps": 795, "total_steps": 61300, "loss": 11.9737, "lr": 6.476345840130506e-06, "epoch": 0.12969004893964112, "percentage": 1.3, "elapsed_time": "0:05:57", "remaining_time": "7:34:01", "throughput": 4799.2, "total_tokens": 1717824} {"current_steps": 800, "total_steps": 61300, "loss": 11.9278, "lr": 6.517128874388255e-06, "epoch": 0.13050570962479607, "percentage": 1.31, "elapsed_time": "0:06:00", "remaining_time": "7:34:00", "throughput": 4798.98, "total_tokens": 1728608} {"current_steps": 805, "total_steps": 61300, "loss": 11.9317, "lr": 6.557911908646004e-06, "epoch": 0.13132137030995106, "percentage": 1.31, "elapsed_time": "0:06:02", "remaining_time": "7:34:01", "throughput": 4798.5, "total_tokens": 1739456} {"current_steps": 810, "total_steps": 61300, "loss": 11.2222, "lr": 6.598694942903752e-06, "epoch": 0.13213703099510604, "percentage": 1.32, "elapsed_time": "0:06:04", "remaining_time": "7:34:00", "throughput": 4798.42, "total_tokens": 1750304} {"current_steps": 815, "total_steps": 61300, "loss": 11.5998, "lr": 6.639477977161501e-06, "epoch": 0.132952691680261, "percentage": 1.33, "elapsed_time": "0:06:07", "remaining_time": "7:34:18", "throughput": 4798.55, "total_tokens": 1762496} {"current_steps": 820, "total_steps": 61300, "loss": 11.5911, "lr": 6.68026101141925e-06, "epoch": 0.13376835236541598, "percentage": 1.34, "elapsed_time": "0:06:09", "remaining_time": "7:34:06", "throughput": 4798.49, "total_tokens": 1772640} {"current_steps": 825, "total_steps": 61300, "loss": 11.5406, "lr": 6.721044045676998e-06, "epoch": 0.13458401305057097, "percentage": 1.35, "elapsed_time": "0:06:11", "remaining_time": "7:33:46", "throughput": 4798.54, "total_tokens": 1782272} {"current_steps": 830, "total_steps": 61300, "loss": 11.5637, "lr": 6.761827079934747e-06, "epoch": 0.13539967373572595, "percentage": 1.35, "elapsed_time": "0:06:13", "remaining_time": "7:33:43", "throughput": 4798.82, "total_tokens": 1793120} {"current_steps": 835, "total_steps": 61300, "loss": 11.2804, "lr": 6.802610114192497e-06, "epoch": 0.1362153344208809, "percentage": 1.36, "elapsed_time": "0:06:15", "remaining_time": "7:33:33", "throughput": 4798.38, "total_tokens": 1803264} {"current_steps": 840, "total_steps": 61300, "loss": 10.9765, "lr": 6.843393148450244e-06, "epoch": 0.1370309951060359, "percentage": 1.37, "elapsed_time": "0:06:17", "remaining_time": "7:33:17", "throughput": 4798.23, "total_tokens": 1813088} {"current_steps": 845, "total_steps": 61300, "loss": 11.203, "lr": 6.884176182707994e-06, "epoch": 0.13784665579119088, "percentage": 1.38, "elapsed_time": "0:06:20", "remaining_time": "7:33:17", "throughput": 4798.29, "total_tokens": 1824032} {"current_steps": 850, "total_steps": 61300, "loss": 11.7378, "lr": 6.924959216965743e-06, "epoch": 0.13866231647634583, "percentage": 1.39, "elapsed_time": "0:06:22", "remaining_time": "7:33:37", "throughput": 4798.69, "total_tokens": 1836512} {"current_steps": 855, "total_steps": 61300, "loss": 11.4146, "lr": 6.965742251223491e-06, "epoch": 0.13947797716150082, "percentage": 1.39, "elapsed_time": "0:06:25", "remaining_time": "7:33:46", "throughput": 4799.11, "total_tokens": 1848256} {"current_steps": 860, "total_steps": 61300, "loss": 11.3694, "lr": 7.00652528548124e-06, "epoch": 0.1402936378466558, "percentage": 1.4, "elapsed_time": "0:06:27", "remaining_time": "7:33:46", "throughput": 4798.68, "total_tokens": 1859040} {"current_steps": 865, "total_steps": 61300, "loss": 11.2005, "lr": 7.047308319738989e-06, "epoch": 0.14110929853181076, "percentage": 1.41, "elapsed_time": "0:06:29", "remaining_time": "7:33:33", "throughput": 4799.03, "total_tokens": 1869248} {"current_steps": 870, "total_steps": 61300, "loss": 11.4479, "lr": 7.088091353996739e-06, "epoch": 0.14192495921696574, "percentage": 1.42, "elapsed_time": "0:06:31", "remaining_time": "7:33:44", "throughput": 4799.59, "total_tokens": 1881184} {"current_steps": 875, "total_steps": 61300, "loss": 11.0484, "lr": 7.128874388254486e-06, "epoch": 0.14274061990212072, "percentage": 1.43, "elapsed_time": "0:06:34", "remaining_time": "7:34:08", "throughput": 4799.4, "total_tokens": 1893760} {"current_steps": 880, "total_steps": 61300, "loss": 10.8676, "lr": 7.169657422512236e-06, "epoch": 0.14355628058727568, "percentage": 1.44, "elapsed_time": "0:06:36", "remaining_time": "7:34:06", "throughput": 4800.0, "total_tokens": 1904800} {"current_steps": 885, "total_steps": 61300, "loss": 10.733, "lr": 7.210440456769985e-06, "epoch": 0.14437194127243066, "percentage": 1.44, "elapsed_time": "0:06:39", "remaining_time": "7:33:58", "throughput": 4800.17, "total_tokens": 1915296} {"current_steps": 890, "total_steps": 61300, "loss": 11.1754, "lr": 7.251223491027733e-06, "epoch": 0.14518760195758565, "percentage": 1.45, "elapsed_time": "0:06:41", "remaining_time": "7:33:43", "throughput": 4800.04, "total_tokens": 1925152} {"current_steps": 895, "total_steps": 61300, "loss": 10.8569, "lr": 7.292006525285482e-06, "epoch": 0.14600326264274063, "percentage": 1.46, "elapsed_time": "0:06:43", "remaining_time": "7:33:30", "throughput": 4799.98, "total_tokens": 1935200} {"current_steps": 900, "total_steps": 61300, "loss": 10.9873, "lr": 7.3327895595432304e-06, "epoch": 0.1468189233278956, "percentage": 1.47, "elapsed_time": "0:06:45", "remaining_time": "7:33:23", "throughput": 4799.82, "total_tokens": 1945632} {"current_steps": 905, "total_steps": 61300, "loss": 11.1295, "lr": 7.373572593800979e-06, "epoch": 0.14763458401305057, "percentage": 1.48, "elapsed_time": "0:06:47", "remaining_time": "7:33:27", "throughput": 4800.09, "total_tokens": 1956992} {"current_steps": 910, "total_steps": 61300, "loss": 10.823, "lr": 7.414355628058728e-06, "epoch": 0.14845024469820556, "percentage": 1.48, "elapsed_time": "0:06:50", "remaining_time": "7:33:36", "throughput": 4800.55, "total_tokens": 1968800} {"current_steps": 915, "total_steps": 61300, "loss": 10.7993, "lr": 7.455138662316477e-06, "epoch": 0.14926590538336051, "percentage": 1.49, "elapsed_time": "0:06:52", "remaining_time": "7:33:30", "throughput": 4800.79, "total_tokens": 1979424} {"current_steps": 920, "total_steps": 61300, "loss": 10.7022, "lr": 7.495921696574225e-06, "epoch": 0.1500815660685155, "percentage": 1.5, "elapsed_time": "0:06:54", "remaining_time": "7:33:35", "throughput": 4801.32, "total_tokens": 1990976} {"current_steps": 925, "total_steps": 61300, "loss": 10.7687, "lr": 7.536704730831974e-06, "epoch": 0.15089722675367048, "percentage": 1.51, "elapsed_time": "0:06:57", "remaining_time": "7:33:42", "throughput": 4801.19, "total_tokens": 2002432} {"current_steps": 930, "total_steps": 61300, "loss": 10.487, "lr": 7.577487765089723e-06, "epoch": 0.15171288743882544, "percentage": 1.52, "elapsed_time": "0:06:59", "remaining_time": "7:33:43", "throughput": 4801.44, "total_tokens": 2013632} {"current_steps": 935, "total_steps": 61300, "loss": 10.2028, "lr": 7.6182707993474724e-06, "epoch": 0.15252854812398042, "percentage": 1.53, "elapsed_time": "0:07:01", "remaining_time": "7:33:48", "throughput": 4801.43, "total_tokens": 2024960} {"current_steps": 940, "total_steps": 61300, "loss": 10.213, "lr": 7.659053833605221e-06, "epoch": 0.1533442088091354, "percentage": 1.53, "elapsed_time": "0:07:03", "remaining_time": "7:33:43", "throughput": 4801.77, "total_tokens": 2035712} {"current_steps": 945, "total_steps": 61300, "loss": 10.2466, "lr": 7.69983686786297e-06, "epoch": 0.15415986949429036, "percentage": 1.54, "elapsed_time": "0:07:06", "remaining_time": "7:33:43", "throughput": 4801.6, "total_tokens": 2046656} {"current_steps": 950, "total_steps": 61300, "loss": 10.513, "lr": 7.740619902120718e-06, "epoch": 0.15497553017944535, "percentage": 1.55, "elapsed_time": "0:07:08", "remaining_time": "7:33:46", "throughput": 4802.08, "total_tokens": 2058112} {"current_steps": 955, "total_steps": 61300, "loss": 10.5028, "lr": 7.781402936378467e-06, "epoch": 0.15579119086460033, "percentage": 1.56, "elapsed_time": "0:07:10", "remaining_time": "7:33:41", "throughput": 4802.18, "total_tokens": 2068768} {"current_steps": 960, "total_steps": 61300, "loss": 10.5246, "lr": 7.822185970636217e-06, "epoch": 0.1566068515497553, "percentage": 1.57, "elapsed_time": "0:07:13", "remaining_time": "7:33:56", "throughput": 4802.19, "total_tokens": 2080928} {"current_steps": 965, "total_steps": 61300, "loss": 10.4714, "lr": 7.862969004893964e-06, "epoch": 0.15742251223491027, "percentage": 1.57, "elapsed_time": "0:07:15", "remaining_time": "7:33:42", "throughput": 4802.06, "total_tokens": 2090784} {"current_steps": 970, "total_steps": 61300, "loss": 9.7988, "lr": 7.903752039151714e-06, "epoch": 0.15823817292006526, "percentage": 1.58, "elapsed_time": "0:07:17", "remaining_time": "7:33:23", "throughput": 4802.19, "total_tokens": 2100416} {"current_steps": 975, "total_steps": 61300, "loss": 10.2474, "lr": 7.944535073409461e-06, "epoch": 0.15905383360522024, "percentage": 1.59, "elapsed_time": "0:07:19", "remaining_time": "7:33:24", "throughput": 4802.06, "total_tokens": 2111424} {"current_steps": 980, "total_steps": 61300, "loss": 9.8857, "lr": 7.98531810766721e-06, "epoch": 0.1598694942903752, "percentage": 1.6, "elapsed_time": "0:07:21", "remaining_time": "7:33:22", "throughput": 4801.9, "total_tokens": 2122176} {"current_steps": 985, "total_steps": 61300, "loss": 10.2115, "lr": 8.026101141924958e-06, "epoch": 0.16068515497553018, "percentage": 1.61, "elapsed_time": "0:07:24", "remaining_time": "7:33:19", "throughput": 4801.73, "total_tokens": 2132928} {"current_steps": 990, "total_steps": 61300, "loss": 10.0255, "lr": 8.066884176182708e-06, "epoch": 0.16150081566068517, "percentage": 1.62, "elapsed_time": "0:07:26", "remaining_time": "7:33:26", "throughput": 4801.82, "total_tokens": 2144480} {"current_steps": 995, "total_steps": 61300, "loss": 9.9933, "lr": 8.107667210440457e-06, "epoch": 0.16231647634584012, "percentage": 1.62, "elapsed_time": "0:07:28", "remaining_time": "7:33:11", "throughput": 4801.79, "total_tokens": 2154272} {"current_steps": 1000, "total_steps": 61300, "loss": 9.8737, "lr": 8.148450244698205e-06, "epoch": 0.1631321370309951, "percentage": 1.63, "elapsed_time": "0:07:30", "remaining_time": "7:32:52", "throughput": 4802.03, "total_tokens": 2163936} {"current_steps": 1005, "total_steps": 61300, "loss": 10.0246, "lr": 8.189233278955954e-06, "epoch": 0.1639477977161501, "percentage": 1.64, "elapsed_time": "0:07:32", "remaining_time": "7:32:56", "throughput": 4802.42, "total_tokens": 2175392} {"current_steps": 1010, "total_steps": 61300, "loss": 9.9538, "lr": 8.230016313213703e-06, "epoch": 0.16476345840130505, "percentage": 1.65, "elapsed_time": "0:07:35", "remaining_time": "7:32:41", "throughput": 4802.31, "total_tokens": 2185120} {"current_steps": 1015, "total_steps": 61300, "loss": 10.0656, "lr": 8.270799347471453e-06, "epoch": 0.16557911908646003, "percentage": 1.66, "elapsed_time": "0:07:37", "remaining_time": "7:32:48", "throughput": 4802.71, "total_tokens": 2196864} {"current_steps": 1020, "total_steps": 61300, "loss": 9.742, "lr": 8.3115823817292e-06, "epoch": 0.16639477977161501, "percentage": 1.66, "elapsed_time": "0:07:39", "remaining_time": "7:32:45", "throughput": 4802.86, "total_tokens": 2207744} {"current_steps": 1025, "total_steps": 61300, "loss": 10.132, "lr": 8.35236541598695e-06, "epoch": 0.16721044045676997, "percentage": 1.67, "elapsed_time": "0:07:41", "remaining_time": "7:32:40", "throughput": 4803.3, "total_tokens": 2218528} {"current_steps": 1030, "total_steps": 61300, "loss": 9.6707, "lr": 8.393148450244699e-06, "epoch": 0.16802610114192496, "percentage": 1.68, "elapsed_time": "0:07:43", "remaining_time": "7:32:25", "throughput": 4803.41, "total_tokens": 2228320} {"current_steps": 1035, "total_steps": 61300, "loss": 9.5201, "lr": 8.433931484502447e-06, "epoch": 0.16884176182707994, "percentage": 1.69, "elapsed_time": "0:07:46", "remaining_time": "7:32:16", "throughput": 4803.14, "total_tokens": 2238464} {"current_steps": 1040, "total_steps": 61300, "loss": 9.9273, "lr": 8.474714518760196e-06, "epoch": 0.16965742251223492, "percentage": 1.7, "elapsed_time": "0:07:48", "remaining_time": "7:32:16", "throughput": 4803.0, "total_tokens": 2249440} {"current_steps": 1045, "total_steps": 61300, "loss": 9.6332, "lr": 8.515497553017945e-06, "epoch": 0.17047308319738988, "percentage": 1.7, "elapsed_time": "0:07:50", "remaining_time": "7:32:18", "throughput": 4803.04, "total_tokens": 2260576} {"current_steps": 1050, "total_steps": 61300, "loss": 9.2656, "lr": 8.556280587275693e-06, "epoch": 0.17128874388254486, "percentage": 1.71, "elapsed_time": "0:07:53", "remaining_time": "7:32:21", "throughput": 4803.12, "total_tokens": 2271904} {"current_steps": 1055, "total_steps": 61300, "loss": 9.4727, "lr": 8.597063621533442e-06, "epoch": 0.17210440456769985, "percentage": 1.72, "elapsed_time": "0:07:55", "remaining_time": "7:32:05", "throughput": 4803.14, "total_tokens": 2281568} {"current_steps": 1060, "total_steps": 61300, "loss": 9.1893, "lr": 8.637846655791192e-06, "epoch": 0.1729200652528548, "percentage": 1.73, "elapsed_time": "0:07:57", "remaining_time": "7:32:06", "throughput": 4803.15, "total_tokens": 2292704} {"current_steps": 1065, "total_steps": 61300, "loss": 9.2003, "lr": 8.67862969004894e-06, "epoch": 0.1737357259380098, "percentage": 1.74, "elapsed_time": "0:07:59", "remaining_time": "7:32:08", "throughput": 4803.31, "total_tokens": 2303904} {"current_steps": 1070, "total_steps": 61300, "loss": 9.0654, "lr": 8.719412724306688e-06, "epoch": 0.17455138662316477, "percentage": 1.75, "elapsed_time": "0:08:01", "remaining_time": "7:32:03", "throughput": 4803.03, "total_tokens": 2314336} {"current_steps": 1075, "total_steps": 61300, "loss": 9.0153, "lr": 8.760195758564438e-06, "epoch": 0.17536704730831973, "percentage": 1.75, "elapsed_time": "0:08:04", "remaining_time": "7:31:58", "throughput": 4803.17, "total_tokens": 2325024} {"current_steps": 1080, "total_steps": 61300, "loss": 9.0137, "lr": 8.800978792822187e-06, "epoch": 0.1761827079934747, "percentage": 1.76, "elapsed_time": "0:08:06", "remaining_time": "7:32:00", "throughput": 4803.17, "total_tokens": 2336224} {"current_steps": 1085, "total_steps": 61300, "loss": 9.189, "lr": 8.841761827079935e-06, "epoch": 0.1769983686786297, "percentage": 1.77, "elapsed_time": "0:08:08", "remaining_time": "7:31:57", "throughput": 4803.02, "total_tokens": 2346880} {"current_steps": 1090, "total_steps": 61300, "loss": 9.3429, "lr": 8.882544861337684e-06, "epoch": 0.17781402936378465, "percentage": 1.78, "elapsed_time": "0:08:10", "remaining_time": "7:31:53", "throughput": 4803.16, "total_tokens": 2357632} {"current_steps": 1095, "total_steps": 61300, "loss": 9.0216, "lr": 8.923327895595434e-06, "epoch": 0.17862969004893964, "percentage": 1.79, "elapsed_time": "0:08:13", "remaining_time": "7:32:15", "throughput": 4803.35, "total_tokens": 2370592} {"current_steps": 1100, "total_steps": 61300, "loss": 9.0195, "lr": 8.964110929853181e-06, "epoch": 0.17944535073409462, "percentage": 1.79, "elapsed_time": "0:08:15", "remaining_time": "7:32:07", "throughput": 4803.42, "total_tokens": 2381024} {"current_steps": 1105, "total_steps": 61300, "loss": 9.086, "lr": 9.00489396411093e-06, "epoch": 0.1802610114192496, "percentage": 1.8, "elapsed_time": "0:08:18", "remaining_time": "7:32:10", "throughput": 4803.22, "total_tokens": 2392160} {"current_steps": 1110, "total_steps": 61300, "loss": 9.1023, "lr": 9.04567699836868e-06, "epoch": 0.18107667210440456, "percentage": 1.81, "elapsed_time": "0:08:20", "remaining_time": "7:32:13", "throughput": 4803.47, "total_tokens": 2403616} {"current_steps": 1115, "total_steps": 61300, "loss": 9.1412, "lr": 9.086460032626427e-06, "epoch": 0.18189233278955955, "percentage": 1.82, "elapsed_time": "0:08:22", "remaining_time": "7:32:27", "throughput": 4803.73, "total_tokens": 2416032} {"current_steps": 1120, "total_steps": 61300, "loss": 8.5222, "lr": 9.127243066884177e-06, "epoch": 0.18270799347471453, "percentage": 1.83, "elapsed_time": "0:08:25", "remaining_time": "7:32:17", "throughput": 4803.63, "total_tokens": 2426112} {"current_steps": 1125, "total_steps": 61300, "loss": 8.7245, "lr": 9.168026101141926e-06, "epoch": 0.1835236541598695, "percentage": 1.84, "elapsed_time": "0:08:27", "remaining_time": "7:32:19", "throughput": 4803.73, "total_tokens": 2437344} {"current_steps": 1130, "total_steps": 61300, "loss": 8.8685, "lr": 9.208809135399674e-06, "epoch": 0.18433931484502447, "percentage": 1.84, "elapsed_time": "0:08:29", "remaining_time": "7:32:21", "throughput": 4803.87, "total_tokens": 2448672} {"current_steps": 1135, "total_steps": 61300, "loss": 8.7326, "lr": 9.249592169657423e-06, "epoch": 0.18515497553017946, "percentage": 1.85, "elapsed_time": "0:08:31", "remaining_time": "7:32:19", "throughput": 4803.93, "total_tokens": 2459552} {"current_steps": 1140, "total_steps": 61300, "loss": 8.3819, "lr": 9.290375203915172e-06, "epoch": 0.1859706362153344, "percentage": 1.86, "elapsed_time": "0:08:33", "remaining_time": "7:32:03", "throughput": 4804.09, "total_tokens": 2469184} {"current_steps": 1145, "total_steps": 61300, "loss": 8.2813, "lr": 9.33115823817292e-06, "epoch": 0.1867862969004894, "percentage": 1.87, "elapsed_time": "0:08:36", "remaining_time": "7:32:12", "throughput": 4804.28, "total_tokens": 2481120} {"current_steps": 1150, "total_steps": 61300, "loss": 8.2273, "lr": 9.37194127243067e-06, "epoch": 0.18760195758564438, "percentage": 1.88, "elapsed_time": "0:08:38", "remaining_time": "7:31:58", "throughput": 4804.34, "total_tokens": 2490976} {"current_steps": 1155, "total_steps": 61300, "loss": 8.0897, "lr": 9.412724306688419e-06, "epoch": 0.18841761827079934, "percentage": 1.88, "elapsed_time": "0:08:40", "remaining_time": "7:31:48", "throughput": 4804.23, "total_tokens": 2501024} {"current_steps": 1160, "total_steps": 61300, "loss": 8.1322, "lr": 9.453507340946168e-06, "epoch": 0.18923327895595432, "percentage": 1.89, "elapsed_time": "0:08:42", "remaining_time": "7:31:39", "throughput": 4804.42, "total_tokens": 2511264} {"current_steps": 1165, "total_steps": 61300, "loss": 8.2957, "lr": 9.494290375203916e-06, "epoch": 0.1900489396411093, "percentage": 1.9, "elapsed_time": "0:08:44", "remaining_time": "7:31:36", "throughput": 4804.22, "total_tokens": 2521920} {"current_steps": 1170, "total_steps": 61300, "loss": 8.3343, "lr": 9.535073409461665e-06, "epoch": 0.19086460032626426, "percentage": 1.91, "elapsed_time": "0:08:47", "remaining_time": "7:31:37", "throughput": 4804.26, "total_tokens": 2533056} {"current_steps": 1175, "total_steps": 61300, "loss": 7.7762, "lr": 9.575856443719414e-06, "epoch": 0.19168026101141925, "percentage": 1.92, "elapsed_time": "0:08:49", "remaining_time": "7:31:39", "throughput": 4804.35, "total_tokens": 2544320} {"current_steps": 1180, "total_steps": 61300, "loss": 8.1554, "lr": 9.616639477977162e-06, "epoch": 0.19249592169657423, "percentage": 1.92, "elapsed_time": "0:08:51", "remaining_time": "7:31:37", "throughput": 4804.28, "total_tokens": 2555168} {"current_steps": 1185, "total_steps": 61300, "loss": 7.9478, "lr": 9.657422512234911e-06, "epoch": 0.1933115823817292, "percentage": 1.93, "elapsed_time": "0:08:54", "remaining_time": "7:31:37", "throughput": 4804.49, "total_tokens": 2566304} {"current_steps": 1190, "total_steps": 61300, "loss": 8.0267, "lr": 9.69820554649266e-06, "epoch": 0.19412724306688417, "percentage": 1.94, "elapsed_time": "0:08:56", "remaining_time": "7:31:24", "throughput": 4804.19, "total_tokens": 2575936} {"current_steps": 1195, "total_steps": 61300, "loss": 8.1079, "lr": 9.738988580750408e-06, "epoch": 0.19494290375203915, "percentage": 1.95, "elapsed_time": "0:08:58", "remaining_time": "7:31:18", "throughput": 4804.41, "total_tokens": 2586528} {"current_steps": 1200, "total_steps": 61300, "loss": 7.6771, "lr": 9.779771615008158e-06, "epoch": 0.19575856443719414, "percentage": 1.96, "elapsed_time": "0:09:00", "remaining_time": "7:31:01", "throughput": 4804.59, "total_tokens": 2596064} {"current_steps": 1205, "total_steps": 61300, "loss": 7.6469, "lr": 9.820554649265905e-06, "epoch": 0.1965742251223491, "percentage": 1.97, "elapsed_time": "0:09:02", "remaining_time": "7:30:54", "throughput": 4804.74, "total_tokens": 2606464} {"current_steps": 1210, "total_steps": 61300, "loss": 7.8623, "lr": 9.861337683523655e-06, "epoch": 0.19738988580750408, "percentage": 1.97, "elapsed_time": "0:09:04", "remaining_time": "7:30:55", "throughput": 4804.69, "total_tokens": 2617568} {"current_steps": 1215, "total_steps": 61300, "loss": 7.5855, "lr": 9.902120717781402e-06, "epoch": 0.19820554649265906, "percentage": 1.98, "elapsed_time": "0:09:07", "remaining_time": "7:30:59", "throughput": 4804.58, "total_tokens": 2628928} {"current_steps": 1220, "total_steps": 61300, "loss": 7.5476, "lr": 9.942903752039152e-06, "epoch": 0.19902120717781402, "percentage": 1.99, "elapsed_time": "0:09:09", "remaining_time": "7:31:11", "throughput": 4804.89, "total_tokens": 2641344} {"current_steps": 1225, "total_steps": 61300, "loss": 7.0137, "lr": 9.983686786296901e-06, "epoch": 0.199836867862969, "percentage": 2.0, "elapsed_time": "0:09:11", "remaining_time": "7:31:04", "throughput": 4804.74, "total_tokens": 2651584} {"current_steps": 1230, "total_steps": 61300, "loss": 7.2615, "lr": 1.0024469820554649e-05, "epoch": 0.200652528548124, "percentage": 2.01, "elapsed_time": "0:09:14", "remaining_time": "7:31:10", "throughput": 4804.98, "total_tokens": 2663360} {"current_steps": 1235, "total_steps": 61300, "loss": 7.4591, "lr": 1.0065252854812398e-05, "epoch": 0.20146818923327894, "percentage": 2.01, "elapsed_time": "0:09:16", "remaining_time": "7:31:18", "throughput": 4804.8, "total_tokens": 2675168} {"current_steps": 1240, "total_steps": 61300, "loss": 7.1991, "lr": 1.0106035889070147e-05, "epoch": 0.20228384991843393, "percentage": 2.02, "elapsed_time": "0:09:18", "remaining_time": "7:31:14", "throughput": 4805.17, "total_tokens": 2685952} {"current_steps": 1245, "total_steps": 61300, "loss": 7.176, "lr": 1.0146818923327895e-05, "epoch": 0.2030995106035889, "percentage": 2.03, "elapsed_time": "0:09:20", "remaining_time": "7:30:59", "throughput": 4804.96, "total_tokens": 2695488} {"current_steps": 1250, "total_steps": 61300, "loss": 7.0229, "lr": 1.0187601957585644e-05, "epoch": 0.2039151712887439, "percentage": 2.04, "elapsed_time": "0:09:23", "remaining_time": "7:31:03", "throughput": 4805.01, "total_tokens": 2706880} {"current_steps": 1255, "total_steps": 61300, "loss": 7.2102, "lr": 1.0228384991843394e-05, "epoch": 0.20473083197389885, "percentage": 2.05, "elapsed_time": "0:09:25", "remaining_time": "7:30:57", "throughput": 4804.65, "total_tokens": 2717184} {"current_steps": 1260, "total_steps": 61300, "loss": 7.4647, "lr": 1.0269168026101141e-05, "epoch": 0.20554649265905384, "percentage": 2.06, "elapsed_time": "0:09:27", "remaining_time": "7:31:05", "throughput": 4804.96, "total_tokens": 2729184} {"current_steps": 1265, "total_steps": 61300, "loss": 7.2598, "lr": 1.030995106035889e-05, "epoch": 0.20636215334420882, "percentage": 2.06, "elapsed_time": "0:09:30", "remaining_time": "7:31:08", "throughput": 4805.25, "total_tokens": 2740768} {"current_steps": 1270, "total_steps": 61300, "loss": 7.0572, "lr": 1.035073409461664e-05, "epoch": 0.20717781402936378, "percentage": 2.07, "elapsed_time": "0:09:32", "remaining_time": "7:31:04", "throughput": 4805.21, "total_tokens": 2751328} {"current_steps": 1275, "total_steps": 61300, "loss": 7.2696, "lr": 1.0391517128874388e-05, "epoch": 0.20799347471451876, "percentage": 2.08, "elapsed_time": "0:09:34", "remaining_time": "7:31:03", "throughput": 4805.53, "total_tokens": 2762464} {"current_steps": 1280, "total_steps": 61300, "loss": 6.7068, "lr": 1.0432300163132137e-05, "epoch": 0.20880913539967375, "percentage": 2.09, "elapsed_time": "0:09:37", "remaining_time": "7:31:04", "throughput": 4805.71, "total_tokens": 2773824} {"current_steps": 1285, "total_steps": 61300, "loss": 6.9218, "lr": 1.0473083197389886e-05, "epoch": 0.2096247960848287, "percentage": 2.1, "elapsed_time": "0:09:39", "remaining_time": "7:31:01", "throughput": 4805.79, "total_tokens": 2784544} {"current_steps": 1290, "total_steps": 61300, "loss": 6.7008, "lr": 1.0513866231647634e-05, "epoch": 0.21044045676998369, "percentage": 2.1, "elapsed_time": "0:09:41", "remaining_time": "7:31:05", "throughput": 4805.77, "total_tokens": 2796032} {"current_steps": 1295, "total_steps": 61300, "loss": 6.6133, "lr": 1.0554649265905383e-05, "epoch": 0.21125611745513867, "percentage": 2.11, "elapsed_time": "0:09:44", "remaining_time": "7:31:15", "throughput": 4805.61, "total_tokens": 2808096} {"current_steps": 1300, "total_steps": 61300, "loss": 6.7077, "lr": 1.0595432300163133e-05, "epoch": 0.21207177814029363, "percentage": 2.12, "elapsed_time": "0:09:46", "remaining_time": "7:31:05", "throughput": 4805.66, "total_tokens": 2818080} {"current_steps": 1305, "total_steps": 61300, "loss": 6.4535, "lr": 1.0636215334420882e-05, "epoch": 0.2128874388254486, "percentage": 2.13, "elapsed_time": "0:09:48", "remaining_time": "7:31:07", "throughput": 4805.34, "total_tokens": 2829248} {"current_steps": 1310, "total_steps": 61300, "loss": 6.5367, "lr": 1.067699836867863e-05, "epoch": 0.2137030995106036, "percentage": 2.14, "elapsed_time": "0:09:51", "remaining_time": "7:31:06", "throughput": 4805.52, "total_tokens": 2840288} {"current_steps": 1315, "total_steps": 61300, "loss": 6.4221, "lr": 1.0717781402936379e-05, "epoch": 0.21451876019575855, "percentage": 2.15, "elapsed_time": "0:09:52", "remaining_time": "7:30:48", "throughput": 4805.46, "total_tokens": 2849440} {"current_steps": 1320, "total_steps": 61300, "loss": 6.3505, "lr": 1.0758564437194128e-05, "epoch": 0.21533442088091354, "percentage": 2.15, "elapsed_time": "0:09:55", "remaining_time": "7:30:53", "throughput": 4805.51, "total_tokens": 2861056} {"current_steps": 1325, "total_steps": 61300, "loss": 6.2667, "lr": 1.0799347471451876e-05, "epoch": 0.21615008156606852, "percentage": 2.16, "elapsed_time": "0:09:57", "remaining_time": "7:31:00", "throughput": 4805.47, "total_tokens": 2872832} {"current_steps": 1330, "total_steps": 61300, "loss": 6.3322, "lr": 1.0840130505709625e-05, "epoch": 0.2169657422512235, "percentage": 2.17, "elapsed_time": "0:10:00", "remaining_time": "7:30:59", "throughput": 4805.66, "total_tokens": 2883968} {"current_steps": 1335, "total_steps": 61300, "loss": 6.4342, "lr": 1.0880913539967375e-05, "epoch": 0.21778140293637846, "percentage": 2.18, "elapsed_time": "0:10:02", "remaining_time": "7:30:57", "throughput": 4805.72, "total_tokens": 2894880} {"current_steps": 1340, "total_steps": 61300, "loss": 5.9718, "lr": 1.0921696574225122e-05, "epoch": 0.21859706362153344, "percentage": 2.19, "elapsed_time": "0:10:04", "remaining_time": "7:30:50", "throughput": 4805.78, "total_tokens": 2905216} {"current_steps": 1345, "total_steps": 61300, "loss": 6.1041, "lr": 1.0962479608482872e-05, "epoch": 0.21941272430668843, "percentage": 2.19, "elapsed_time": "0:10:06", "remaining_time": "7:30:54", "throughput": 4806.39, "total_tokens": 2917152} {"current_steps": 1350, "total_steps": 61300, "loss": 6.0362, "lr": 1.1003262642740621e-05, "epoch": 0.22022838499184338, "percentage": 2.2, "elapsed_time": "0:10:09", "remaining_time": "7:30:57", "throughput": 4806.32, "total_tokens": 2928448} {"current_steps": 1355, "total_steps": 61300, "loss": 5.8228, "lr": 1.1044045676998369e-05, "epoch": 0.22104404567699837, "percentage": 2.21, "elapsed_time": "0:10:11", "remaining_time": "7:30:45", "throughput": 4806.34, "total_tokens": 2938336} {"current_steps": 1360, "total_steps": 61300, "loss": 6.0142, "lr": 1.1084828711256118e-05, "epoch": 0.22185970636215335, "percentage": 2.22, "elapsed_time": "0:10:13", "remaining_time": "7:30:56", "throughput": 4806.15, "total_tokens": 2950496} {"current_steps": 1365, "total_steps": 61300, "loss": 5.8952, "lr": 1.1125611745513867e-05, "epoch": 0.2226753670473083, "percentage": 2.23, "elapsed_time": "0:10:16", "remaining_time": "7:30:50", "throughput": 4806.42, "total_tokens": 2961024} {"current_steps": 1370, "total_steps": 61300, "loss": 5.602, "lr": 1.1166394779771617e-05, "epoch": 0.2234910277324633, "percentage": 2.23, "elapsed_time": "0:10:18", "remaining_time": "7:30:45", "throughput": 4806.59, "total_tokens": 2971744} {"current_steps": 1375, "total_steps": 61300, "loss": 5.7893, "lr": 1.1207177814029364e-05, "epoch": 0.22430668841761828, "percentage": 2.24, "elapsed_time": "0:10:20", "remaining_time": "7:30:55", "throughput": 4806.94, "total_tokens": 2984192} {"current_steps": 1380, "total_steps": 61300, "loss": 5.4838, "lr": 1.1247960848287114e-05, "epoch": 0.22512234910277323, "percentage": 2.25, "elapsed_time": "0:10:22", "remaining_time": "7:30:50", "throughput": 4807.1, "total_tokens": 2994816} {"current_steps": 1385, "total_steps": 61300, "loss": 5.5621, "lr": 1.1288743882544863e-05, "epoch": 0.22593800978792822, "percentage": 2.26, "elapsed_time": "0:10:25", "remaining_time": "7:30:48", "throughput": 4806.99, "total_tokens": 3005568} {"current_steps": 1390, "total_steps": 61300, "loss": 5.5155, "lr": 1.132952691680261e-05, "epoch": 0.2267536704730832, "percentage": 2.27, "elapsed_time": "0:10:27", "remaining_time": "7:30:38", "throughput": 4807.16, "total_tokens": 3015680} {"current_steps": 1395, "total_steps": 61300, "loss": 5.5867, "lr": 1.137030995106036e-05, "epoch": 0.2275693311582382, "percentage": 2.28, "elapsed_time": "0:10:29", "remaining_time": "7:30:37", "throughput": 4807.26, "total_tokens": 3026752} {"current_steps": 1400, "total_steps": 61300, "loss": 5.4959, "lr": 1.141109298531811e-05, "epoch": 0.22838499184339314, "percentage": 2.28, "elapsed_time": "0:10:31", "remaining_time": "7:30:28", "throughput": 4807.08, "total_tokens": 3036704} {"current_steps": 1405, "total_steps": 61300, "loss": 5.5917, "lr": 1.1451876019575857e-05, "epoch": 0.22920065252854813, "percentage": 2.29, "elapsed_time": "0:10:34", "remaining_time": "7:30:37", "throughput": 4807.22, "total_tokens": 3048960} {"current_steps": 1410, "total_steps": 61300, "loss": 5.3821, "lr": 1.1492659053833606e-05, "epoch": 0.2300163132137031, "percentage": 2.3, "elapsed_time": "0:10:36", "remaining_time": "7:30:32", "throughput": 4807.15, "total_tokens": 3059456} {"current_steps": 1415, "total_steps": 61300, "loss": 5.4058, "lr": 1.1533442088091356e-05, "epoch": 0.23083197389885807, "percentage": 2.31, "elapsed_time": "0:10:38", "remaining_time": "7:30:29", "throughput": 4806.96, "total_tokens": 3070112} {"current_steps": 1420, "total_steps": 61300, "loss": 5.2568, "lr": 1.1574225122349103e-05, "epoch": 0.23164763458401305, "percentage": 2.32, "elapsed_time": "0:10:40", "remaining_time": "7:30:21", "throughput": 4806.83, "total_tokens": 3080224} {"current_steps": 1425, "total_steps": 61300, "loss": 5.4741, "lr": 1.1615008156606853e-05, "epoch": 0.23246329526916804, "percentage": 2.32, "elapsed_time": "0:10:42", "remaining_time": "7:30:13", "throughput": 4806.79, "total_tokens": 3090304} {"current_steps": 1430, "total_steps": 61300, "loss": 5.5096, "lr": 1.1655791190864602e-05, "epoch": 0.233278955954323, "percentage": 2.33, "elapsed_time": "0:10:44", "remaining_time": "7:29:54", "throughput": 4806.69, "total_tokens": 3099232} {"current_steps": 1435, "total_steps": 61300, "loss": 5.2374, "lr": 1.169657422512235e-05, "epoch": 0.23409461663947798, "percentage": 2.34, "elapsed_time": "0:10:46", "remaining_time": "7:29:48", "throughput": 4806.82, "total_tokens": 3109696} {"current_steps": 1440, "total_steps": 61300, "loss": 5.255, "lr": 1.1737357259380099e-05, "epoch": 0.23491027732463296, "percentage": 2.35, "elapsed_time": "0:10:49", "remaining_time": "7:29:42", "throughput": 4807.01, "total_tokens": 3120160} {"current_steps": 1445, "total_steps": 61300, "loss": 5.1006, "lr": 1.1778140293637847e-05, "epoch": 0.23572593800978792, "percentage": 2.36, "elapsed_time": "0:10:51", "remaining_time": "7:29:37", "throughput": 4807.15, "total_tokens": 3130784} {"current_steps": 1450, "total_steps": 61300, "loss": 4.906, "lr": 1.1818923327895596e-05, "epoch": 0.2365415986949429, "percentage": 2.37, "elapsed_time": "0:10:53", "remaining_time": "7:29:35", "throughput": 4807.0, "total_tokens": 3141536} {"current_steps": 1455, "total_steps": 61300, "loss": 4.8066, "lr": 1.1859706362153344e-05, "epoch": 0.23735725938009788, "percentage": 2.37, "elapsed_time": "0:10:55", "remaining_time": "7:29:32", "throughput": 4806.69, "total_tokens": 3152160} {"current_steps": 1460, "total_steps": 61300, "loss": 4.7635, "lr": 1.1900489396411093e-05, "epoch": 0.23817292006525284, "percentage": 2.38, "elapsed_time": "0:10:57", "remaining_time": "7:29:27", "throughput": 4806.53, "total_tokens": 3162560} {"current_steps": 1465, "total_steps": 61300, "loss": 5.1875, "lr": 1.1941272430668842e-05, "epoch": 0.23898858075040783, "percentage": 2.39, "elapsed_time": "0:11:00", "remaining_time": "7:29:43", "throughput": 4806.25, "total_tokens": 3175360} {"current_steps": 1470, "total_steps": 61300, "loss": 4.9941, "lr": 1.198205546492659e-05, "epoch": 0.2398042414355628, "percentage": 2.4, "elapsed_time": "0:11:03", "remaining_time": "7:29:54", "throughput": 4806.62, "total_tokens": 3187936} {"current_steps": 1475, "total_steps": 61300, "loss": 4.6593, "lr": 1.202283849918434e-05, "epoch": 0.2406199021207178, "percentage": 2.41, "elapsed_time": "0:11:05", "remaining_time": "7:29:57", "throughput": 4806.64, "total_tokens": 3199424} {"current_steps": 1480, "total_steps": 61300, "loss": 4.7171, "lr": 1.2063621533442089e-05, "epoch": 0.24143556280587275, "percentage": 2.41, "elapsed_time": "0:11:07", "remaining_time": "7:29:53", "throughput": 4806.86, "total_tokens": 3210272} {"current_steps": 1485, "total_steps": 61300, "loss": 4.6379, "lr": 1.2104404567699836e-05, "epoch": 0.24225122349102773, "percentage": 2.42, "elapsed_time": "0:11:09", "remaining_time": "7:29:39", "throughput": 4806.87, "total_tokens": 3219680} {"current_steps": 1490, "total_steps": 61300, "loss": 4.2692, "lr": 1.2145187601957586e-05, "epoch": 0.24306688417618272, "percentage": 2.43, "elapsed_time": "0:11:11", "remaining_time": "7:29:29", "throughput": 4806.58, "total_tokens": 3229376} {"current_steps": 1495, "total_steps": 61300, "loss": 4.6055, "lr": 1.2185970636215335e-05, "epoch": 0.24388254486133767, "percentage": 2.44, "elapsed_time": "0:11:14", "remaining_time": "7:29:31", "throughput": 4806.73, "total_tokens": 3240896} {"current_steps": 1500, "total_steps": 61300, "loss": 4.6191, "lr": 1.2226753670473083e-05, "epoch": 0.24469820554649266, "percentage": 2.45, "elapsed_time": "0:11:16", "remaining_time": "7:29:29", "throughput": 4806.8, "total_tokens": 3251808} {"current_steps": 1505, "total_steps": 61300, "loss": 4.1895, "lr": 1.2267536704730832e-05, "epoch": 0.24551386623164764, "percentage": 2.46, "elapsed_time": "0:11:18", "remaining_time": "7:29:26", "throughput": 4806.98, "total_tokens": 3262688} {"current_steps": 1510, "total_steps": 61300, "loss": 4.1907, "lr": 1.2308319738988581e-05, "epoch": 0.2463295269168026, "percentage": 2.46, "elapsed_time": "0:11:20", "remaining_time": "7:29:22", "throughput": 4807.11, "total_tokens": 3273344} {"current_steps": 1515, "total_steps": 61300, "loss": 4.3311, "lr": 1.234910277324633e-05, "epoch": 0.24714518760195758, "percentage": 2.47, "elapsed_time": "0:11:23", "remaining_time": "7:29:15", "throughput": 4806.97, "total_tokens": 3283520} {"current_steps": 1520, "total_steps": 61300, "loss": 4.3438, "lr": 1.2389885807504078e-05, "epoch": 0.24796084828711257, "percentage": 2.48, "elapsed_time": "0:11:25", "remaining_time": "7:29:18", "throughput": 4806.77, "total_tokens": 3294816} {"current_steps": 1525, "total_steps": 61300, "loss": 4.3762, "lr": 1.2430668841761828e-05, "epoch": 0.24877650897226752, "percentage": 2.49, "elapsed_time": "0:11:27", "remaining_time": "7:29:11", "throughput": 4806.9, "total_tokens": 3305152} {"current_steps": 1530, "total_steps": 61300, "loss": 3.9197, "lr": 1.2471451876019577e-05, "epoch": 0.2495921696574225, "percentage": 2.5, "elapsed_time": "0:11:29", "remaining_time": "7:29:02", "throughput": 4806.89, "total_tokens": 3315264} {"current_steps": 1535, "total_steps": 61300, "loss": 4.2033, "lr": 1.2512234910277326e-05, "epoch": 0.25040783034257746, "percentage": 2.5, "elapsed_time": "0:11:31", "remaining_time": "7:29:02", "throughput": 4806.72, "total_tokens": 3326208} {"current_steps": 1540, "total_steps": 61300, "loss": 4.1205, "lr": 1.2553017944535072e-05, "epoch": 0.25122349102773245, "percentage": 2.51, "elapsed_time": "0:11:34", "remaining_time": "7:29:04", "throughput": 4806.53, "total_tokens": 3337472} {"current_steps": 1545, "total_steps": 61300, "loss": 3.9564, "lr": 1.2593800978792822e-05, "epoch": 0.25203915171288743, "percentage": 2.52, "elapsed_time": "0:11:36", "remaining_time": "7:29:02", "throughput": 4806.86, "total_tokens": 3348576} {"current_steps": 1550, "total_steps": 61300, "loss": 4.1882, "lr": 1.2634584013050571e-05, "epoch": 0.2528548123980424, "percentage": 2.53, "elapsed_time": "0:11:38", "remaining_time": "7:28:59", "throughput": 4806.79, "total_tokens": 3359200} {"current_steps": 1555, "total_steps": 61300, "loss": 3.9847, "lr": 1.267536704730832e-05, "epoch": 0.2536704730831974, "percentage": 2.54, "elapsed_time": "0:11:41", "remaining_time": "7:28:54", "throughput": 4806.7, "total_tokens": 3369696} {"current_steps": 1560, "total_steps": 61300, "loss": 4.0117, "lr": 1.271615008156607e-05, "epoch": 0.2544861337683524, "percentage": 2.54, "elapsed_time": "0:11:43", "remaining_time": "7:28:56", "throughput": 4806.8, "total_tokens": 3381088} {"current_steps": 1565, "total_steps": 61300, "loss": 3.8674, "lr": 1.2756933115823819e-05, "epoch": 0.2553017944535073, "percentage": 2.55, "elapsed_time": "0:11:45", "remaining_time": "7:29:01", "throughput": 4806.65, "total_tokens": 3392704} {"current_steps": 1570, "total_steps": 61300, "loss": 3.6463, "lr": 1.2797716150081568e-05, "epoch": 0.2561174551386623, "percentage": 2.56, "elapsed_time": "0:11:48", "remaining_time": "7:28:57", "throughput": 4806.37, "total_tokens": 3403136} {"current_steps": 1575, "total_steps": 61300, "loss": 3.6294, "lr": 1.2838499184339314e-05, "epoch": 0.2569331158238173, "percentage": 2.57, "elapsed_time": "0:11:49", "remaining_time": "7:28:40", "throughput": 4806.23, "total_tokens": 3411968} {"current_steps": 1580, "total_steps": 61300, "loss": 3.7282, "lr": 1.2879282218597064e-05, "epoch": 0.25774877650897227, "percentage": 2.58, "elapsed_time": "0:11:51", "remaining_time": "7:28:25", "throughput": 4806.28, "total_tokens": 3421216} {"current_steps": 1585, "total_steps": 61300, "loss": 3.4559, "lr": 1.2920065252854813e-05, "epoch": 0.25856443719412725, "percentage": 2.59, "elapsed_time": "0:11:54", "remaining_time": "7:28:29", "throughput": 4806.55, "total_tokens": 3433120} {"current_steps": 1590, "total_steps": 61300, "loss": 3.6449, "lr": 1.2960848287112562e-05, "epoch": 0.25938009787928223, "percentage": 2.59, "elapsed_time": "0:11:56", "remaining_time": "7:28:35", "throughput": 4806.48, "total_tokens": 3444960} {"current_steps": 1595, "total_steps": 61300, "loss": 3.5001, "lr": 1.3001631321370312e-05, "epoch": 0.2601957585644372, "percentage": 2.6, "elapsed_time": "0:11:59", "remaining_time": "7:28:37", "throughput": 4806.71, "total_tokens": 3456512} {"current_steps": 1600, "total_steps": 61300, "loss": 3.3526, "lr": 1.3042414355628061e-05, "epoch": 0.26101141924959215, "percentage": 2.61, "elapsed_time": "0:12:01", "remaining_time": "7:28:31", "throughput": 4806.75, "total_tokens": 3466880} {"current_steps": 1605, "total_steps": 61300, "loss": 3.3846, "lr": 1.3083197389885807e-05, "epoch": 0.26182707993474713, "percentage": 2.62, "elapsed_time": "0:12:03", "remaining_time": "7:28:36", "throughput": 4806.59, "total_tokens": 3478528} {"current_steps": 1610, "total_steps": 61300, "loss": 3.5957, "lr": 1.3123980424143556e-05, "epoch": 0.2626427406199021, "percentage": 2.63, "elapsed_time": "0:12:06", "remaining_time": "7:28:41", "throughput": 4806.55, "total_tokens": 3490240} {"current_steps": 1615, "total_steps": 61300, "loss": 3.4296, "lr": 1.3164763458401306e-05, "epoch": 0.2634584013050571, "percentage": 2.63, "elapsed_time": "0:12:08", "remaining_time": "7:28:40", "throughput": 4806.4, "total_tokens": 3501152} {"current_steps": 1620, "total_steps": 61300, "loss": 3.3224, "lr": 1.3205546492659055e-05, "epoch": 0.2642740619902121, "percentage": 2.64, "elapsed_time": "0:12:10", "remaining_time": "7:28:33", "throughput": 4806.38, "total_tokens": 3511360} {"current_steps": 1625, "total_steps": 61300, "loss": 3.4298, "lr": 1.3246329526916804e-05, "epoch": 0.26508972267536707, "percentage": 2.65, "elapsed_time": "0:12:12", "remaining_time": "7:28:36", "throughput": 4806.38, "total_tokens": 3522880} {"current_steps": 1630, "total_steps": 61300, "loss": 3.5138, "lr": 1.3287112561174554e-05, "epoch": 0.265905383360522, "percentage": 2.66, "elapsed_time": "0:12:15", "remaining_time": "7:28:42", "throughput": 4806.23, "total_tokens": 3534720} {"current_steps": 1635, "total_steps": 61300, "loss": 3.2033, "lr": 1.3327895595432303e-05, "epoch": 0.266721044045677, "percentage": 2.67, "elapsed_time": "0:12:17", "remaining_time": "7:28:30", "throughput": 4806.07, "total_tokens": 3544128} {"current_steps": 1640, "total_steps": 61300, "loss": 3.1676, "lr": 1.3368678629690049e-05, "epoch": 0.26753670473083196, "percentage": 2.68, "elapsed_time": "0:12:19", "remaining_time": "7:28:31", "throughput": 4806.19, "total_tokens": 3555552} {"current_steps": 1645, "total_steps": 61300, "loss": 2.9786, "lr": 1.3409461663947798e-05, "epoch": 0.26835236541598695, "percentage": 2.68, "elapsed_time": "0:12:21", "remaining_time": "7:28:25", "throughput": 4806.1, "total_tokens": 3565824} {"current_steps": 1650, "total_steps": 61300, "loss": 2.9355, "lr": 1.3450244698205548e-05, "epoch": 0.26916802610114193, "percentage": 2.69, "elapsed_time": "0:12:24", "remaining_time": "7:28:24", "throughput": 4806.27, "total_tokens": 3576864} {"current_steps": 1655, "total_steps": 61300, "loss": 2.8149, "lr": 1.3491027732463297e-05, "epoch": 0.2699836867862969, "percentage": 2.7, "elapsed_time": "0:12:26", "remaining_time": "7:28:22", "throughput": 4806.62, "total_tokens": 3588032} {"current_steps": 1660, "total_steps": 61300, "loss": 2.8823, "lr": 1.3531810766721044e-05, "epoch": 0.2707993474714519, "percentage": 2.71, "elapsed_time": "0:12:28", "remaining_time": "7:28:23", "throughput": 4806.8, "total_tokens": 3599488} {"current_steps": 1665, "total_steps": 61300, "loss": 2.9155, "lr": 1.3572593800978794e-05, "epoch": 0.27161500815660683, "percentage": 2.72, "elapsed_time": "0:12:31", "remaining_time": "7:28:22", "throughput": 4806.71, "total_tokens": 3610368} {"current_steps": 1670, "total_steps": 61300, "loss": 2.7826, "lr": 1.3613376835236541e-05, "epoch": 0.2724306688417618, "percentage": 2.72, "elapsed_time": "0:12:33", "remaining_time": "7:28:12", "throughput": 4806.58, "total_tokens": 3620128} {"current_steps": 1675, "total_steps": 61300, "loss": 2.8634, "lr": 1.365415986949429e-05, "epoch": 0.2732463295269168, "percentage": 2.73, "elapsed_time": "0:12:35", "remaining_time": "7:28:17", "throughput": 4806.48, "total_tokens": 3631872} {"current_steps": 1680, "total_steps": 61300, "loss": 2.8282, "lr": 1.369494290375204e-05, "epoch": 0.2740619902120718, "percentage": 2.74, "elapsed_time": "0:12:37", "remaining_time": "7:28:19", "throughput": 4806.46, "total_tokens": 3643296} {"current_steps": 1685, "total_steps": 61300, "loss": 2.839, "lr": 1.3735725938009788e-05, "epoch": 0.27487765089722677, "percentage": 2.75, "elapsed_time": "0:12:40", "remaining_time": "7:28:20", "throughput": 4806.59, "total_tokens": 3654592} {"current_steps": 1690, "total_steps": 61300, "loss": 2.6891, "lr": 1.3776508972267537e-05, "epoch": 0.27569331158238175, "percentage": 2.76, "elapsed_time": "0:12:42", "remaining_time": "7:28:18", "throughput": 4806.33, "total_tokens": 3665312} {"current_steps": 1695, "total_steps": 61300, "loss": 2.5042, "lr": 1.3817292006525286e-05, "epoch": 0.2765089722675367, "percentage": 2.77, "elapsed_time": "0:12:45", "remaining_time": "7:28:23", "throughput": 4806.23, "total_tokens": 3677024} {"current_steps": 1700, "total_steps": 61300, "loss": 2.5381, "lr": 1.3858075040783036e-05, "epoch": 0.27732463295269166, "percentage": 2.77, "elapsed_time": "0:12:47", "remaining_time": "7:28:19", "throughput": 4806.49, "total_tokens": 3687904} {"current_steps": 1705, "total_steps": 61300, "loss": 2.4646, "lr": 1.3898858075040783e-05, "epoch": 0.27814029363784665, "percentage": 2.78, "elapsed_time": "0:12:49", "remaining_time": "7:28:18", "throughput": 4806.49, "total_tokens": 3698848} {"current_steps": 1710, "total_steps": 61300, "loss": 2.3799, "lr": 1.3939641109298531e-05, "epoch": 0.27895595432300163, "percentage": 2.79, "elapsed_time": "0:12:51", "remaining_time": "7:28:15", "throughput": 4806.77, "total_tokens": 3709856} {"current_steps": 1715, "total_steps": 61300, "loss": 2.6062, "lr": 1.398042414355628e-05, "epoch": 0.2797716150081566, "percentage": 2.8, "elapsed_time": "0:12:54", "remaining_time": "7:28:13", "throughput": 4806.76, "total_tokens": 3720736} {"current_steps": 1720, "total_steps": 61300, "loss": 2.2531, "lr": 1.402120717781403e-05, "epoch": 0.2805872756933116, "percentage": 2.81, "elapsed_time": "0:12:56", "remaining_time": "7:28:09", "throughput": 4806.66, "total_tokens": 3731264} {"current_steps": 1725, "total_steps": 61300, "loss": 2.4895, "lr": 1.4061990212071779e-05, "epoch": 0.2814029363784666, "percentage": 2.81, "elapsed_time": "0:12:58", "remaining_time": "7:28:14", "throughput": 4806.61, "total_tokens": 3743072} {"current_steps": 1730, "total_steps": 61300, "loss": 2.2374, "lr": 1.4102773246329528e-05, "epoch": 0.2822185970636215, "percentage": 2.82, "elapsed_time": "0:13:01", "remaining_time": "7:28:16", "throughput": 4806.75, "total_tokens": 3754656} {"current_steps": 1735, "total_steps": 61300, "loss": 2.1196, "lr": 1.4143556280587274e-05, "epoch": 0.2830342577487765, "percentage": 2.83, "elapsed_time": "0:13:03", "remaining_time": "7:28:12", "throughput": 4806.86, "total_tokens": 3765248} {"current_steps": 1740, "total_steps": 61300, "loss": 2.1945, "lr": 1.4184339314845024e-05, "epoch": 0.2838499184339315, "percentage": 2.84, "elapsed_time": "0:13:05", "remaining_time": "7:27:58", "throughput": 4806.84, "total_tokens": 3774464} {"current_steps": 1745, "total_steps": 61300, "loss": 2.1465, "lr": 1.4225122349102773e-05, "epoch": 0.28466557911908646, "percentage": 2.85, "elapsed_time": "0:13:07", "remaining_time": "7:27:52", "throughput": 4806.65, "total_tokens": 3784608} {"current_steps": 1750, "total_steps": 61300, "loss": 2.2605, "lr": 1.4265905383360522e-05, "epoch": 0.28548123980424145, "percentage": 2.85, "elapsed_time": "0:13:09", "remaining_time": "7:27:57", "throughput": 4806.76, "total_tokens": 3796672} {"current_steps": 1755, "total_steps": 61300, "loss": 2.0151, "lr": 1.4306688417618272e-05, "epoch": 0.28629690048939643, "percentage": 2.86, "elapsed_time": "0:13:12", "remaining_time": "7:27:56", "throughput": 4806.81, "total_tokens": 3807712} {"current_steps": 1760, "total_steps": 61300, "loss": 2.0633, "lr": 1.4347471451876021e-05, "epoch": 0.28711256117455136, "percentage": 2.87, "elapsed_time": "0:13:14", "remaining_time": "7:27:49", "throughput": 4806.9, "total_tokens": 3817984} {"current_steps": 1765, "total_steps": 61300, "loss": 2.0739, "lr": 1.438825448613377e-05, "epoch": 0.28792822185970635, "percentage": 2.88, "elapsed_time": "0:13:16", "remaining_time": "7:27:49", "throughput": 4806.95, "total_tokens": 3829152} {"current_steps": 1770, "total_steps": 61300, "loss": 1.9806, "lr": 1.4429037520391516e-05, "epoch": 0.28874388254486133, "percentage": 2.89, "elapsed_time": "0:13:18", "remaining_time": "7:27:50", "throughput": 4806.81, "total_tokens": 3840352} {"current_steps": 1775, "total_steps": 61300, "loss": 1.9216, "lr": 1.4469820554649266e-05, "epoch": 0.2895595432300163, "percentage": 2.9, "elapsed_time": "0:13:21", "remaining_time": "7:27:49", "throughput": 4806.83, "total_tokens": 3851456} {"current_steps": 1780, "total_steps": 61300, "loss": 2.0241, "lr": 1.4510603588907015e-05, "epoch": 0.2903752039151713, "percentage": 2.9, "elapsed_time": "0:13:23", "remaining_time": "7:27:51", "throughput": 4807.08, "total_tokens": 3863040} {"current_steps": 1785, "total_steps": 61300, "loss": 1.9863, "lr": 1.4551386623164764e-05, "epoch": 0.2911908646003263, "percentage": 2.91, "elapsed_time": "0:13:25", "remaining_time": "7:27:50", "throughput": 4807.19, "total_tokens": 3874176} {"current_steps": 1790, "total_steps": 61300, "loss": 1.8589, "lr": 1.4592169657422514e-05, "epoch": 0.29200652528548127, "percentage": 2.92, "elapsed_time": "0:13:28", "remaining_time": "7:27:45", "throughput": 4807.28, "total_tokens": 3884736} {"current_steps": 1795, "total_steps": 61300, "loss": 1.8345, "lr": 1.4632952691680263e-05, "epoch": 0.2928221859706362, "percentage": 2.93, "elapsed_time": "0:13:30", "remaining_time": "7:27:43", "throughput": 4807.22, "total_tokens": 3895584} {"current_steps": 1800, "total_steps": 61300, "loss": 1.9179, "lr": 1.4673735725938009e-05, "epoch": 0.2936378466557912, "percentage": 2.94, "elapsed_time": "0:13:32", "remaining_time": "7:27:48", "throughput": 4807.41, "total_tokens": 3907584} {"current_steps": 1805, "total_steps": 61300, "loss": 1.8955, "lr": 1.4714518760195758e-05, "epoch": 0.29445350734094616, "percentage": 2.94, "elapsed_time": "0:13:35", "remaining_time": "7:27:52", "throughput": 4807.49, "total_tokens": 3919424} {"current_steps": 1810, "total_steps": 61300, "loss": 1.7843, "lr": 1.4755301794453508e-05, "epoch": 0.29526916802610115, "percentage": 2.95, "elapsed_time": "0:13:37", "remaining_time": "7:27:43", "throughput": 4807.37, "total_tokens": 3929152} {"current_steps": 1815, "total_steps": 61300, "loss": 1.6437, "lr": 1.4796084828711257e-05, "epoch": 0.29608482871125613, "percentage": 2.96, "elapsed_time": "0:13:39", "remaining_time": "7:27:46", "throughput": 4807.49, "total_tokens": 3940928} {"current_steps": 1820, "total_steps": 61300, "loss": 1.6795, "lr": 1.4836867862969006e-05, "epoch": 0.2969004893964111, "percentage": 2.97, "elapsed_time": "0:13:41", "remaining_time": "7:27:28", "throughput": 4807.66, "total_tokens": 3949568} {"current_steps": 1825, "total_steps": 61300, "loss": 1.5602, "lr": 1.4877650897226756e-05, "epoch": 0.29771615008156604, "percentage": 2.98, "elapsed_time": "0:13:43", "remaining_time": "7:27:29", "throughput": 4807.85, "total_tokens": 3961088} {"current_steps": 1830, "total_steps": 61300, "loss": 1.5422, "lr": 1.4918433931484505e-05, "epoch": 0.29853181076672103, "percentage": 2.99, "elapsed_time": "0:13:46", "remaining_time": "7:27:33", "throughput": 4808.07, "total_tokens": 3973088} {"current_steps": 1835, "total_steps": 61300, "loss": 1.4861, "lr": 1.4959216965742251e-05, "epoch": 0.299347471451876, "percentage": 2.99, "elapsed_time": "0:13:48", "remaining_time": "7:27:25", "throughput": 4808.03, "total_tokens": 3982976} {"current_steps": 1840, "total_steps": 61300, "loss": 1.5657, "lr": 1.5e-05, "epoch": 0.300163132137031, "percentage": 3.0, "elapsed_time": "0:13:50", "remaining_time": "7:27:20", "throughput": 4807.93, "total_tokens": 3993440} {"current_steps": 1845, "total_steps": 61300, "loss": 1.5144, "lr": 1.504078303425775e-05, "epoch": 0.300978792822186, "percentage": 3.01, "elapsed_time": "0:13:52", "remaining_time": "7:27:07", "throughput": 4807.97, "total_tokens": 4002720} {"current_steps": 1850, "total_steps": 61300, "loss": 1.579, "lr": 1.5081566068515499e-05, "epoch": 0.30179445350734097, "percentage": 3.02, "elapsed_time": "0:13:54", "remaining_time": "7:27:02", "throughput": 4807.7, "total_tokens": 4012896} {"current_steps": 1855, "total_steps": 61300, "loss": 1.4381, "lr": 1.5122349102773248e-05, "epoch": 0.30261011419249595, "percentage": 3.03, "elapsed_time": "0:13:56", "remaining_time": "7:26:59", "throughput": 4807.86, "total_tokens": 4023680} {"current_steps": 1860, "total_steps": 61300, "loss": 1.4654, "lr": 1.5163132137030998e-05, "epoch": 0.3034257748776509, "percentage": 3.03, "elapsed_time": "0:13:58", "remaining_time": "7:26:50", "throughput": 4807.99, "total_tokens": 4033760} {"current_steps": 1865, "total_steps": 61300, "loss": 1.5872, "lr": 1.5203915171288744e-05, "epoch": 0.30424143556280586, "percentage": 3.04, "elapsed_time": "0:14:01", "remaining_time": "7:26:46", "throughput": 4807.96, "total_tokens": 4044192} {"current_steps": 1870, "total_steps": 61300, "loss": 1.3832, "lr": 1.5244698205546493e-05, "epoch": 0.30505709624796085, "percentage": 3.05, "elapsed_time": "0:14:03", "remaining_time": "7:26:47", "throughput": 4807.92, "total_tokens": 4055520} {"current_steps": 1875, "total_steps": 61300, "loss": 1.4023, "lr": 1.5285481239804242e-05, "epoch": 0.30587275693311583, "percentage": 3.06, "elapsed_time": "0:14:05", "remaining_time": "7:26:50", "throughput": 4808.08, "total_tokens": 4067264} {"current_steps": 1880, "total_steps": 61300, "loss": 1.4064, "lr": 1.532626427406199e-05, "epoch": 0.3066884176182708, "percentage": 3.07, "elapsed_time": "0:14:08", "remaining_time": "7:26:48", "throughput": 4807.91, "total_tokens": 4078016} {"current_steps": 1885, "total_steps": 61300, "loss": 1.4593, "lr": 1.536704730831974e-05, "epoch": 0.3075040783034258, "percentage": 3.08, "elapsed_time": "0:14:10", "remaining_time": "7:26:43", "throughput": 4807.79, "total_tokens": 4088352} {"current_steps": 1890, "total_steps": 61300, "loss": 1.5412, "lr": 1.540783034257749e-05, "epoch": 0.3083197389885807, "percentage": 3.08, "elapsed_time": "0:14:12", "remaining_time": "7:26:49", "throughput": 4807.62, "total_tokens": 4100416} {"current_steps": 1895, "total_steps": 61300, "loss": 1.3185, "lr": 1.5448613376835236e-05, "epoch": 0.3091353996737357, "percentage": 3.09, "elapsed_time": "0:14:14", "remaining_time": "7:26:40", "throughput": 4807.45, "total_tokens": 4110080} {"current_steps": 1900, "total_steps": 61300, "loss": 1.3513, "lr": 1.5489396411092984e-05, "epoch": 0.3099510603588907, "percentage": 3.1, "elapsed_time": "0:14:17", "remaining_time": "7:26:37", "throughput": 4807.42, "total_tokens": 4120736} {"current_steps": 1905, "total_steps": 61300, "loss": 1.4248, "lr": 1.5530179445350735e-05, "epoch": 0.3107667210440457, "percentage": 3.11, "elapsed_time": "0:14:19", "remaining_time": "7:26:42", "throughput": 4807.47, "total_tokens": 4132736} {"current_steps": 1910, "total_steps": 61300, "loss": 1.3641, "lr": 1.5570962479608483e-05, "epoch": 0.31158238172920066, "percentage": 3.12, "elapsed_time": "0:14:21", "remaining_time": "7:26:40", "throughput": 4807.62, "total_tokens": 4143808} {"current_steps": 1915, "total_steps": 61300, "loss": 1.3908, "lr": 1.5611745513866234e-05, "epoch": 0.31239804241435565, "percentage": 3.12, "elapsed_time": "0:14:24", "remaining_time": "7:26:40", "throughput": 4807.58, "total_tokens": 4154976} {"current_steps": 1920, "total_steps": 61300, "loss": 1.2394, "lr": 1.565252854812398e-05, "epoch": 0.3132137030995106, "percentage": 3.13, "elapsed_time": "0:14:26", "remaining_time": "7:26:37", "throughput": 4807.45, "total_tokens": 4165504} {"current_steps": 1925, "total_steps": 61300, "loss": 1.4704, "lr": 1.5693311582381732e-05, "epoch": 0.31402936378466556, "percentage": 3.14, "elapsed_time": "0:14:28", "remaining_time": "7:26:40", "throughput": 4807.45, "total_tokens": 4177184} {"current_steps": 1930, "total_steps": 61300, "loss": 1.2922, "lr": 1.5734094616639477e-05, "epoch": 0.31484502446982054, "percentage": 3.15, "elapsed_time": "0:14:31", "remaining_time": "7:26:43", "throughput": 4807.69, "total_tokens": 4189088} {"current_steps": 1935, "total_steps": 61300, "loss": 1.2471, "lr": 1.5774877650897228e-05, "epoch": 0.31566068515497553, "percentage": 3.16, "elapsed_time": "0:14:33", "remaining_time": "7:26:42", "throughput": 4807.67, "total_tokens": 4200064} {"current_steps": 1940, "total_steps": 61300, "loss": 1.3666, "lr": 1.5815660685154975e-05, "epoch": 0.3164763458401305, "percentage": 3.16, "elapsed_time": "0:14:36", "remaining_time": "7:26:46", "throughput": 4807.71, "total_tokens": 4211936} {"current_steps": 1945, "total_steps": 61300, "loss": 1.2934, "lr": 1.5856443719412726e-05, "epoch": 0.3172920065252855, "percentage": 3.17, "elapsed_time": "0:14:38", "remaining_time": "7:26:38", "throughput": 4807.73, "total_tokens": 4221952} {"current_steps": 1950, "total_steps": 61300, "loss": 1.1727, "lr": 1.5897226753670474e-05, "epoch": 0.3181076672104405, "percentage": 3.18, "elapsed_time": "0:14:40", "remaining_time": "7:26:36", "throughput": 4807.85, "total_tokens": 4233024} {"current_steps": 1955, "total_steps": 61300, "loss": 1.1773, "lr": 1.5938009787928225e-05, "epoch": 0.3189233278955954, "percentage": 3.19, "elapsed_time": "0:14:42", "remaining_time": "7:26:37", "throughput": 4808.05, "total_tokens": 4244480} {"current_steps": 1960, "total_steps": 61300, "loss": 1.1249, "lr": 1.597879282218597e-05, "epoch": 0.3197389885807504, "percentage": 3.2, "elapsed_time": "0:14:45", "remaining_time": "7:26:37", "throughput": 4808.21, "total_tokens": 4255904} {"current_steps": 1965, "total_steps": 61300, "loss": 1.181, "lr": 1.601957585644372e-05, "epoch": 0.3205546492659054, "percentage": 3.21, "elapsed_time": "0:14:47", "remaining_time": "7:26:29", "throughput": 4808.15, "total_tokens": 4265792} {"current_steps": 1970, "total_steps": 61300, "loss": 1.1779, "lr": 1.6060358890701468e-05, "epoch": 0.32137030995106036, "percentage": 3.21, "elapsed_time": "0:14:49", "remaining_time": "7:26:24", "throughput": 4808.16, "total_tokens": 4276160} {"current_steps": 1975, "total_steps": 61300, "loss": 1.0664, "lr": 1.610114192495922e-05, "epoch": 0.32218597063621535, "percentage": 3.22, "elapsed_time": "0:14:51", "remaining_time": "7:26:20", "throughput": 4808.09, "total_tokens": 4286624} {"current_steps": 1980, "total_steps": 61300, "loss": 1.1838, "lr": 1.6141924959216967e-05, "epoch": 0.32300163132137033, "percentage": 3.23, "elapsed_time": "0:14:53", "remaining_time": "7:26:17", "throughput": 4808.25, "total_tokens": 4297600} {"current_steps": 1985, "total_steps": 61300, "loss": 1.1495, "lr": 1.6182707993474718e-05, "epoch": 0.32381729200652526, "percentage": 3.24, "elapsed_time": "0:14:56", "remaining_time": "7:26:14", "throughput": 4808.3, "total_tokens": 4308352} {"current_steps": 1990, "total_steps": 61300, "loss": 1.0547, "lr": 1.6223491027732465e-05, "epoch": 0.32463295269168024, "percentage": 3.25, "elapsed_time": "0:14:58", "remaining_time": "7:26:13", "throughput": 4808.33, "total_tokens": 4319360} {"current_steps": 1995, "total_steps": 61300, "loss": 1.2537, "lr": 1.6264274061990213e-05, "epoch": 0.3254486133768352, "percentage": 3.25, "elapsed_time": "0:15:00", "remaining_time": "7:26:17", "throughput": 4808.59, "total_tokens": 4331552} {"current_steps": 2000, "total_steps": 61300, "loss": 1.4757, "lr": 1.630505709624796e-05, "epoch": 0.3262642740619902, "percentage": 3.26, "elapsed_time": "0:15:03", "remaining_time": "7:26:23", "throughput": 4808.55, "total_tokens": 4343744} {"current_steps": 2005, "total_steps": 61300, "loss": 1.0851, "lr": 1.634584013050571e-05, "epoch": 0.3270799347471452, "percentage": 3.27, "elapsed_time": "0:15:05", "remaining_time": "7:26:19", "throughput": 4808.56, "total_tokens": 4354304} {"current_steps": 2010, "total_steps": 61300, "loss": 1.0976, "lr": 1.638662316476346e-05, "epoch": 0.3278955954323002, "percentage": 3.28, "elapsed_time": "0:15:07", "remaining_time": "7:26:20", "throughput": 4808.58, "total_tokens": 4365696} {"current_steps": 2015, "total_steps": 61300, "loss": 1.1796, "lr": 1.6427406199021207e-05, "epoch": 0.32871125611745516, "percentage": 3.29, "elapsed_time": "0:15:10", "remaining_time": "7:26:20", "throughput": 4808.46, "total_tokens": 4376736} {"current_steps": 2020, "total_steps": 61300, "loss": 1.01, "lr": 1.6468189233278958e-05, "epoch": 0.3295269168026101, "percentage": 3.3, "elapsed_time": "0:15:12", "remaining_time": "7:26:19", "throughput": 4808.75, "total_tokens": 4388064} {"current_steps": 2025, "total_steps": 61300, "loss": 1.1041, "lr": 1.6508972267536706e-05, "epoch": 0.3303425774877651, "percentage": 3.3, "elapsed_time": "0:15:14", "remaining_time": "7:26:17", "throughput": 4808.65, "total_tokens": 4398912} {"current_steps": 2030, "total_steps": 61300, "loss": 0.9952, "lr": 1.6549755301794453e-05, "epoch": 0.33115823817292006, "percentage": 3.31, "elapsed_time": "0:15:17", "remaining_time": "7:26:16", "throughput": 4808.53, "total_tokens": 4409856} {"current_steps": 2035, "total_steps": 61300, "loss": 0.9881, "lr": 1.6590538336052204e-05, "epoch": 0.33197389885807504, "percentage": 3.32, "elapsed_time": "0:15:19", "remaining_time": "7:26:07", "throughput": 4808.45, "total_tokens": 4419552} {"current_steps": 2040, "total_steps": 61300, "loss": 0.9354, "lr": 1.6631321370309952e-05, "epoch": 0.33278955954323003, "percentage": 3.33, "elapsed_time": "0:15:21", "remaining_time": "7:26:03", "throughput": 4808.34, "total_tokens": 4430080} {"current_steps": 2045, "total_steps": 61300, "loss": 1.0081, "lr": 1.66721044045677e-05, "epoch": 0.333605220228385, "percentage": 3.34, "elapsed_time": "0:15:23", "remaining_time": "7:26:05", "throughput": 4808.37, "total_tokens": 4441568} {"current_steps": 2050, "total_steps": 61300, "loss": 0.9705, "lr": 1.671288743882545e-05, "epoch": 0.33442088091353994, "percentage": 3.34, "elapsed_time": "0:15:25", "remaining_time": "7:25:55", "throughput": 4808.42, "total_tokens": 4451200} {"current_steps": 2055, "total_steps": 61300, "loss": 0.99, "lr": 1.6753670473083198e-05, "epoch": 0.3352365415986949, "percentage": 3.35, "elapsed_time": "0:15:27", "remaining_time": "7:25:51", "throughput": 4808.43, "total_tokens": 4461888} {"current_steps": 2060, "total_steps": 61300, "loss": 0.9552, "lr": 1.6794453507340946e-05, "epoch": 0.3360522022838499, "percentage": 3.36, "elapsed_time": "0:15:29", "remaining_time": "7:25:41", "throughput": 4808.39, "total_tokens": 4471392} {"current_steps": 2065, "total_steps": 61300, "loss": 1.1836, "lr": 1.6835236541598694e-05, "epoch": 0.3368678629690049, "percentage": 3.37, "elapsed_time": "0:15:32", "remaining_time": "7:25:41", "throughput": 4808.56, "total_tokens": 4482656} {"current_steps": 2070, "total_steps": 61300, "loss": 1.0381, "lr": 1.6876019575856445e-05, "epoch": 0.3376835236541599, "percentage": 3.38, "elapsed_time": "0:15:34", "remaining_time": "7:25:43", "throughput": 4808.58, "total_tokens": 4494336} {"current_steps": 2075, "total_steps": 61300, "loss": 1.0077, "lr": 1.6916802610114192e-05, "epoch": 0.33849918433931486, "percentage": 3.38, "elapsed_time": "0:15:37", "remaining_time": "7:25:44", "throughput": 4808.57, "total_tokens": 4505760} {"current_steps": 2080, "total_steps": 61300, "loss": 0.8667, "lr": 1.6957585644371943e-05, "epoch": 0.33931484502446985, "percentage": 3.39, "elapsed_time": "0:15:38", "remaining_time": "7:25:33", "throughput": 4808.42, "total_tokens": 4514976} {"current_steps": 2085, "total_steps": 61300, "loss": 0.9765, "lr": 1.699836867862969e-05, "epoch": 0.3401305057096248, "percentage": 3.4, "elapsed_time": "0:15:41", "remaining_time": "7:25:26", "throughput": 4808.4, "total_tokens": 4524928} {"current_steps": 2090, "total_steps": 61300, "loss": 0.9038, "lr": 1.703915171288744e-05, "epoch": 0.34094616639477976, "percentage": 3.41, "elapsed_time": "0:15:43", "remaining_time": "7:25:25", "throughput": 4808.62, "total_tokens": 4536192} {"current_steps": 2095, "total_steps": 61300, "loss": 0.855, "lr": 1.7079934747145186e-05, "epoch": 0.34176182707993474, "percentage": 3.42, "elapsed_time": "0:15:45", "remaining_time": "7:25:29", "throughput": 4808.65, "total_tokens": 4548160} {"current_steps": 2100, "total_steps": 61300, "loss": 0.9793, "lr": 1.7120717781402937e-05, "epoch": 0.3425774877650897, "percentage": 3.43, "elapsed_time": "0:15:47", "remaining_time": "7:25:24", "throughput": 4808.64, "total_tokens": 4558560} {"current_steps": 2105, "total_steps": 61300, "loss": 0.9025, "lr": 1.7161500815660685e-05, "epoch": 0.3433931484502447, "percentage": 3.43, "elapsed_time": "0:15:50", "remaining_time": "7:25:26", "throughput": 4808.76, "total_tokens": 4570272} {"current_steps": 2110, "total_steps": 61300, "loss": 0.9711, "lr": 1.7202283849918436e-05, "epoch": 0.3442088091353997, "percentage": 3.44, "elapsed_time": "0:15:52", "remaining_time": "7:25:21", "throughput": 4808.75, "total_tokens": 4580608} {"current_steps": 2115, "total_steps": 61300, "loss": 0.9896, "lr": 1.7243066884176184e-05, "epoch": 0.3450244698205546, "percentage": 3.45, "elapsed_time": "0:15:54", "remaining_time": "7:25:16", "throughput": 4808.73, "total_tokens": 4591072} {"current_steps": 2120, "total_steps": 61300, "loss": 0.9367, "lr": 1.7283849918433935e-05, "epoch": 0.3458401305057096, "percentage": 3.46, "elapsed_time": "0:15:57", "remaining_time": "7:25:16", "throughput": 4808.84, "total_tokens": 4602368} {"current_steps": 2125, "total_steps": 61300, "loss": 1.0554, "lr": 1.732463295269168e-05, "epoch": 0.3466557911908646, "percentage": 3.47, "elapsed_time": "0:15:59", "remaining_time": "7:25:16", "throughput": 4808.79, "total_tokens": 4613600} {"current_steps": 2130, "total_steps": 61300, "loss": 0.8527, "lr": 1.736541598694943e-05, "epoch": 0.3474714518760196, "percentage": 3.47, "elapsed_time": "0:16:01", "remaining_time": "7:25:10", "throughput": 4808.85, "total_tokens": 4623872} {"current_steps": 2135, "total_steps": 61300, "loss": 1.0087, "lr": 1.7406199021207178e-05, "epoch": 0.34828711256117456, "percentage": 3.48, "elapsed_time": "0:16:03", "remaining_time": "7:25:10", "throughput": 4808.97, "total_tokens": 4635136} {"current_steps": 2140, "total_steps": 61300, "loss": 0.9124, "lr": 1.744698205546493e-05, "epoch": 0.34910277324632955, "percentage": 3.49, "elapsed_time": "0:16:05", "remaining_time": "7:25:03", "throughput": 4808.98, "total_tokens": 4645152} {"current_steps": 2145, "total_steps": 61300, "loss": 0.9076, "lr": 1.7487765089722676e-05, "epoch": 0.34991843393148453, "percentage": 3.5, "elapsed_time": "0:16:07", "remaining_time": "7:24:50", "throughput": 4809.0, "total_tokens": 4654240} {"current_steps": 2150, "total_steps": 61300, "loss": 0.9734, "lr": 1.7528548123980427e-05, "epoch": 0.35073409461663946, "percentage": 3.51, "elapsed_time": "0:16:10", "remaining_time": "7:24:58", "throughput": 4808.34, "total_tokens": 4666240} {"current_steps": 2155, "total_steps": 61300, "loss": 0.8923, "lr": 1.756933115823817e-05, "epoch": 0.35154975530179444, "percentage": 3.52, "elapsed_time": "0:16:12", "remaining_time": "7:25:03", "throughput": 4808.44, "total_tokens": 4678528} {"current_steps": 2160, "total_steps": 61300, "loss": 0.8823, "lr": 1.7610114192495923e-05, "epoch": 0.3523654159869494, "percentage": 3.52, "elapsed_time": "0:16:15", "remaining_time": "7:24:58", "throughput": 4808.44, "total_tokens": 4688768} {"current_steps": 2165, "total_steps": 61300, "loss": 0.781, "lr": 1.765089722675367e-05, "epoch": 0.3531810766721044, "percentage": 3.53, "elapsed_time": "0:16:17", "remaining_time": "7:24:49", "throughput": 4808.39, "total_tokens": 4698496} {"current_steps": 2170, "total_steps": 61300, "loss": 0.8792, "lr": 1.769168026101142e-05, "epoch": 0.3539967373572594, "percentage": 3.54, "elapsed_time": "0:16:19", "remaining_time": "7:24:51", "throughput": 4808.54, "total_tokens": 4710208} {"current_steps": 2175, "total_steps": 61300, "loss": 0.8645, "lr": 1.773246329526917e-05, "epoch": 0.3548123980424144, "percentage": 3.55, "elapsed_time": "0:16:21", "remaining_time": "7:24:46", "throughput": 4808.47, "total_tokens": 4720480} {"current_steps": 2180, "total_steps": 61300, "loss": 1.0087, "lr": 1.777324632952692e-05, "epoch": 0.3556280587275693, "percentage": 3.56, "elapsed_time": "0:16:23", "remaining_time": "7:24:39", "throughput": 4808.45, "total_tokens": 4730560} {"current_steps": 2185, "total_steps": 61300, "loss": 0.8554, "lr": 1.7814029363784668e-05, "epoch": 0.3564437194127243, "percentage": 3.56, "elapsed_time": "0:16:25", "remaining_time": "7:24:34", "throughput": 4808.33, "total_tokens": 4740768} {"current_steps": 2190, "total_steps": 61300, "loss": 0.7838, "lr": 1.7854812398042415e-05, "epoch": 0.3572593800978793, "percentage": 3.57, "elapsed_time": "0:16:28", "remaining_time": "7:24:29", "throughput": 4808.26, "total_tokens": 4751040} {"current_steps": 2195, "total_steps": 61300, "loss": 0.8429, "lr": 1.7895595432300163e-05, "epoch": 0.35807504078303426, "percentage": 3.58, "elapsed_time": "0:16:30", "remaining_time": "7:24:28", "throughput": 4808.11, "total_tokens": 4762016} {"current_steps": 2200, "total_steps": 61300, "loss": 0.7532, "lr": 1.7936378466557914e-05, "epoch": 0.35889070146818924, "percentage": 3.59, "elapsed_time": "0:16:32", "remaining_time": "7:24:20", "throughput": 4808.04, "total_tokens": 4771648} {"current_steps": 2205, "total_steps": 61300, "loss": 0.8124, "lr": 1.797716150081566e-05, "epoch": 0.35970636215334423, "percentage": 3.6, "elapsed_time": "0:16:34", "remaining_time": "7:24:11", "throughput": 4808.08, "total_tokens": 4781440} {"current_steps": 2210, "total_steps": 61300, "loss": 0.8439, "lr": 1.8017944535073413e-05, "epoch": 0.3605220228384992, "percentage": 3.61, "elapsed_time": "0:16:36", "remaining_time": "7:24:15", "throughput": 4808.02, "total_tokens": 4793312} {"current_steps": 2215, "total_steps": 61300, "loss": 0.8655, "lr": 1.805872756933116e-05, "epoch": 0.36133768352365414, "percentage": 3.61, "elapsed_time": "0:16:39", "remaining_time": "7:24:15", "throughput": 4807.84, "total_tokens": 4804288} {"current_steps": 2220, "total_steps": 61300, "loss": 0.8291, "lr": 1.8099510603588908e-05, "epoch": 0.3621533442088091, "percentage": 3.62, "elapsed_time": "0:16:41", "remaining_time": "7:24:12", "throughput": 4807.65, "total_tokens": 4814784} {"current_steps": 2225, "total_steps": 61300, "loss": 0.7969, "lr": 1.8140293637846655e-05, "epoch": 0.3629690048939641, "percentage": 3.63, "elapsed_time": "0:16:43", "remaining_time": "7:24:06", "throughput": 4807.74, "total_tokens": 4825152} {"current_steps": 2230, "total_steps": 61300, "loss": 0.8056, "lr": 1.8181076672104407e-05, "epoch": 0.3637846655791191, "percentage": 3.64, "elapsed_time": "0:16:45", "remaining_time": "7:24:03", "throughput": 4807.66, "total_tokens": 4835776} {"current_steps": 2235, "total_steps": 61300, "loss": 0.8324, "lr": 1.8221859706362154e-05, "epoch": 0.3646003262642741, "percentage": 3.65, "elapsed_time": "0:16:48", "remaining_time": "7:24:03", "throughput": 4807.59, "total_tokens": 4846848} {"current_steps": 2240, "total_steps": 61300, "loss": 0.7596, "lr": 1.8262642740619905e-05, "epoch": 0.36541598694942906, "percentage": 3.65, "elapsed_time": "0:16:50", "remaining_time": "7:24:01", "throughput": 4807.42, "total_tokens": 4857664} {"current_steps": 2245, "total_steps": 61300, "loss": 0.7374, "lr": 1.8303425774877653e-05, "epoch": 0.366231647634584, "percentage": 3.66, "elapsed_time": "0:16:52", "remaining_time": "7:24:01", "throughput": 4807.38, "total_tokens": 4868800} {"current_steps": 2250, "total_steps": 61300, "loss": 0.6446, "lr": 1.83442088091354e-05, "epoch": 0.367047308319739, "percentage": 3.67, "elapsed_time": "0:16:55", "remaining_time": "7:24:00", "throughput": 4807.31, "total_tokens": 4879776} {"current_steps": 2255, "total_steps": 61300, "loss": 0.7024, "lr": 1.8384991843393148e-05, "epoch": 0.36786296900489396, "percentage": 3.68, "elapsed_time": "0:16:57", "remaining_time": "7:23:57", "throughput": 4807.51, "total_tokens": 4890816} {"current_steps": 2260, "total_steps": 61300, "loss": 0.6205, "lr": 1.84257748776509e-05, "epoch": 0.36867862969004894, "percentage": 3.69, "elapsed_time": "0:16:59", "remaining_time": "7:23:41", "throughput": 4807.52, "total_tokens": 4899136} {"current_steps": 2265, "total_steps": 61300, "loss": 0.7551, "lr": 1.8466557911908647e-05, "epoch": 0.3694942903752039, "percentage": 3.69, "elapsed_time": "0:17:01", "remaining_time": "7:23:39", "throughput": 4807.68, "total_tokens": 4910112} {"current_steps": 2270, "total_steps": 61300, "loss": 0.8036, "lr": 1.8507340946166394e-05, "epoch": 0.3703099510603589, "percentage": 3.7, "elapsed_time": "0:17:03", "remaining_time": "7:23:32", "throughput": 4807.63, "total_tokens": 4920032} {"current_steps": 2275, "total_steps": 61300, "loss": 0.8213, "lr": 1.8548123980424145e-05, "epoch": 0.37112561174551384, "percentage": 3.71, "elapsed_time": "0:17:05", "remaining_time": "7:23:30", "throughput": 4807.5, "total_tokens": 4930752} {"current_steps": 2280, "total_steps": 61300, "loss": 0.7448, "lr": 1.8588907014681893e-05, "epoch": 0.3719412724306688, "percentage": 3.72, "elapsed_time": "0:17:07", "remaining_time": "7:23:25", "throughput": 4807.33, "total_tokens": 4940960} {"current_steps": 2285, "total_steps": 61300, "loss": 0.7455, "lr": 1.862969004893964e-05, "epoch": 0.3727569331158238, "percentage": 3.73, "elapsed_time": "0:17:10", "remaining_time": "7:23:24", "throughput": 4807.38, "total_tokens": 4952128} {"current_steps": 2290, "total_steps": 61300, "loss": 0.7165, "lr": 1.867047308319739e-05, "epoch": 0.3735725938009788, "percentage": 3.74, "elapsed_time": "0:17:12", "remaining_time": "7:23:21", "throughput": 4807.37, "total_tokens": 4962848} {"current_steps": 2295, "total_steps": 61300, "loss": 0.8122, "lr": 1.871125611745514e-05, "epoch": 0.3743882544861338, "percentage": 3.74, "elapsed_time": "0:17:14", "remaining_time": "7:23:13", "throughput": 4807.33, "total_tokens": 4972448} {"current_steps": 2300, "total_steps": 61300, "loss": 0.6618, "lr": 1.8752039151712887e-05, "epoch": 0.37520391517128876, "percentage": 3.75, "elapsed_time": "0:17:16", "remaining_time": "7:23:07", "throughput": 4807.16, "total_tokens": 4982432} {"current_steps": 2305, "total_steps": 61300, "loss": 0.6544, "lr": 1.8792822185970638e-05, "epoch": 0.37601957585644374, "percentage": 3.76, "elapsed_time": "0:17:18", "remaining_time": "7:23:01", "throughput": 4807.33, "total_tokens": 4992800} {"current_steps": 2310, "total_steps": 61300, "loss": 0.8387, "lr": 1.8833605220228386e-05, "epoch": 0.3768352365415987, "percentage": 3.77, "elapsed_time": "0:17:20", "remaining_time": "7:23:02", "throughput": 4807.44, "total_tokens": 5004352} {"current_steps": 2315, "total_steps": 61300, "loss": 0.8877, "lr": 1.8874388254486133e-05, "epoch": 0.37765089722675366, "percentage": 3.78, "elapsed_time": "0:17:23", "remaining_time": "7:23:04", "throughput": 4807.41, "total_tokens": 5015968} {"current_steps": 2320, "total_steps": 61300, "loss": 0.7041, "lr": 1.891517128874388e-05, "epoch": 0.37846655791190864, "percentage": 3.78, "elapsed_time": "0:17:25", "remaining_time": "7:23:01", "throughput": 4807.35, "total_tokens": 5026624} {"current_steps": 2325, "total_steps": 61300, "loss": 0.7245, "lr": 1.8955954323001632e-05, "epoch": 0.3792822185970636, "percentage": 3.79, "elapsed_time": "0:17:27", "remaining_time": "7:22:58", "throughput": 4807.38, "total_tokens": 5037312} {"current_steps": 2330, "total_steps": 61300, "loss": 0.7014, "lr": 1.899673735725938e-05, "epoch": 0.3800978792822186, "percentage": 3.8, "elapsed_time": "0:17:30", "remaining_time": "7:22:58", "throughput": 4807.44, "total_tokens": 5048544} {"current_steps": 2335, "total_steps": 61300, "loss": 0.6711, "lr": 1.903752039151713e-05, "epoch": 0.3809135399673736, "percentage": 3.81, "elapsed_time": "0:17:32", "remaining_time": "7:22:56", "throughput": 4807.59, "total_tokens": 5059584} {"current_steps": 2340, "total_steps": 61300, "loss": 1.1529, "lr": 1.907830342577488e-05, "epoch": 0.3817292006525285, "percentage": 3.82, "elapsed_time": "0:17:35", "remaining_time": "7:23:05", "throughput": 4807.65, "total_tokens": 5072736} {"current_steps": 2345, "total_steps": 61300, "loss": 0.6944, "lr": 1.911908646003263e-05, "epoch": 0.3825448613376835, "percentage": 3.83, "elapsed_time": "0:17:37", "remaining_time": "7:23:02", "throughput": 4807.77, "total_tokens": 5083456} {"current_steps": 2350, "total_steps": 61300, "loss": 0.6676, "lr": 1.9159869494290374e-05, "epoch": 0.3833605220228385, "percentage": 3.83, "elapsed_time": "0:17:39", "remaining_time": "7:22:59", "throughput": 4807.82, "total_tokens": 5094240} {"current_steps": 2355, "total_steps": 61300, "loss": 0.5958, "lr": 1.9200652528548125e-05, "epoch": 0.3841761827079935, "percentage": 3.84, "elapsed_time": "0:17:41", "remaining_time": "7:22:50", "throughput": 4807.82, "total_tokens": 5103744} {"current_steps": 2360, "total_steps": 61300, "loss": 0.6951, "lr": 1.9241435562805872e-05, "epoch": 0.38499184339314846, "percentage": 3.85, "elapsed_time": "0:17:43", "remaining_time": "7:22:44", "throughput": 4807.93, "total_tokens": 5114048} {"current_steps": 2365, "total_steps": 61300, "loss": 0.6083, "lr": 1.9282218597063623e-05, "epoch": 0.38580750407830344, "percentage": 3.86, "elapsed_time": "0:17:45", "remaining_time": "7:22:37", "throughput": 4807.75, "total_tokens": 5123744} {"current_steps": 2370, "total_steps": 61300, "loss": 0.6541, "lr": 1.932300163132137e-05, "epoch": 0.3866231647634584, "percentage": 3.87, "elapsed_time": "0:17:47", "remaining_time": "7:22:31", "throughput": 4807.77, "total_tokens": 5133888} {"current_steps": 2375, "total_steps": 61300, "loss": 0.629, "lr": 1.9363784665579122e-05, "epoch": 0.38743882544861336, "percentage": 3.87, "elapsed_time": "0:17:50", "remaining_time": "7:22:30", "throughput": 4807.8, "total_tokens": 5145024} {"current_steps": 2380, "total_steps": 61300, "loss": 0.692, "lr": 1.9404567699836866e-05, "epoch": 0.38825448613376834, "percentage": 3.88, "elapsed_time": "0:17:52", "remaining_time": "7:22:32", "throughput": 4807.76, "total_tokens": 5156544} {"current_steps": 2385, "total_steps": 61300, "loss": 0.659, "lr": 1.9445350734094617e-05, "epoch": 0.3890701468189233, "percentage": 3.89, "elapsed_time": "0:17:54", "remaining_time": "7:22:33", "throughput": 4807.96, "total_tokens": 5168192} {"current_steps": 2390, "total_steps": 61300, "loss": 0.6703, "lr": 1.9486133768352365e-05, "epoch": 0.3898858075040783, "percentage": 3.9, "elapsed_time": "0:17:57", "remaining_time": "7:22:26", "throughput": 4807.94, "total_tokens": 5178240} {"current_steps": 2395, "total_steps": 61300, "loss": 0.6424, "lr": 1.9526916802610116e-05, "epoch": 0.3907014681892333, "percentage": 3.91, "elapsed_time": "0:17:59", "remaining_time": "7:22:24", "throughput": 4808.12, "total_tokens": 5189248} {"current_steps": 2400, "total_steps": 61300, "loss": 0.7052, "lr": 1.9567699836867864e-05, "epoch": 0.3915171288743883, "percentage": 3.92, "elapsed_time": "0:18:01", "remaining_time": "7:22:18", "throughput": 4808.26, "total_tokens": 5199392} {"current_steps": 2405, "total_steps": 61300, "loss": 0.6118, "lr": 1.9608482871125615e-05, "epoch": 0.3923327895595432, "percentage": 3.92, "elapsed_time": "0:18:03", "remaining_time": "7:22:15", "throughput": 4808.37, "total_tokens": 5210240} {"current_steps": 2410, "total_steps": 61300, "loss": 0.6232, "lr": 1.9649265905383362e-05, "epoch": 0.3931484502446982, "percentage": 3.93, "elapsed_time": "0:18:05", "remaining_time": "7:22:08", "throughput": 4808.16, "total_tokens": 5220000} {"current_steps": 2415, "total_steps": 61300, "loss": 0.7748, "lr": 1.969004893964111e-05, "epoch": 0.3939641109298532, "percentage": 3.94, "elapsed_time": "0:18:08", "remaining_time": "7:22:10", "throughput": 4808.11, "total_tokens": 5231520} {"current_steps": 2420, "total_steps": 61300, "loss": 0.622, "lr": 1.9730831973898858e-05, "epoch": 0.39477977161500816, "percentage": 3.95, "elapsed_time": "0:18:10", "remaining_time": "7:22:12", "throughput": 4808.14, "total_tokens": 5243200} {"current_steps": 2425, "total_steps": 61300, "loss": 0.6037, "lr": 1.977161500815661e-05, "epoch": 0.39559543230016314, "percentage": 3.96, "elapsed_time": "0:18:12", "remaining_time": "7:22:08", "throughput": 4807.97, "total_tokens": 5253632} {"current_steps": 2430, "total_steps": 61300, "loss": 0.5346, "lr": 1.9812398042414356e-05, "epoch": 0.3964110929853181, "percentage": 3.96, "elapsed_time": "0:18:15", "remaining_time": "7:22:08", "throughput": 4807.85, "total_tokens": 5264736} {"current_steps": 2435, "total_steps": 61300, "loss": 0.6002, "lr": 1.9853181076672107e-05, "epoch": 0.3972267536704731, "percentage": 3.97, "elapsed_time": "0:18:17", "remaining_time": "7:22:09", "throughput": 4807.82, "total_tokens": 5276192} {"current_steps": 2440, "total_steps": 61300, "loss": 0.78, "lr": 1.9893964110929855e-05, "epoch": 0.39804241435562804, "percentage": 3.98, "elapsed_time": "0:18:19", "remaining_time": "7:22:08", "throughput": 4807.86, "total_tokens": 5287296} {"current_steps": 2445, "total_steps": 61300, "loss": 0.6075, "lr": 1.9934747145187603e-05, "epoch": 0.398858075040783, "percentage": 3.99, "elapsed_time": "0:18:22", "remaining_time": "7:22:07", "throughput": 4807.88, "total_tokens": 5298336} {"current_steps": 2450, "total_steps": 61300, "loss": 0.7009, "lr": 1.997553017944535e-05, "epoch": 0.399673735725938, "percentage": 4.0, "elapsed_time": "0:18:24", "remaining_time": "7:22:05", "throughput": 4807.92, "total_tokens": 5309248} {"current_steps": 2455, "total_steps": 61300, "loss": 0.5647, "lr": 2.00163132137031e-05, "epoch": 0.400489396411093, "percentage": 4.0, "elapsed_time": "0:18:26", "remaining_time": "7:22:04", "throughput": 4807.89, "total_tokens": 5320384} {"current_steps": 2460, "total_steps": 61300, "loss": 0.6288, "lr": 2.005709624796085e-05, "epoch": 0.401305057096248, "percentage": 4.01, "elapsed_time": "0:18:28", "remaining_time": "7:22:04", "throughput": 4808.02, "total_tokens": 5331904} {"current_steps": 2465, "total_steps": 61300, "loss": 0.6346, "lr": 2.00978792822186e-05, "epoch": 0.40212071778140296, "percentage": 4.02, "elapsed_time": "0:18:31", "remaining_time": "7:22:08", "throughput": 4808.03, "total_tokens": 5343904} {"current_steps": 2470, "total_steps": 61300, "loss": 0.56, "lr": 2.0138662316476348e-05, "epoch": 0.4029363784665579, "percentage": 4.03, "elapsed_time": "0:18:33", "remaining_time": "7:22:03", "throughput": 4808.08, "total_tokens": 5354336} {"current_steps": 2475, "total_steps": 61300, "loss": 0.7312, "lr": 2.0179445350734095e-05, "epoch": 0.40375203915171287, "percentage": 4.04, "elapsed_time": "0:18:36", "remaining_time": "7:22:06", "throughput": 4808.14, "total_tokens": 5366144} {"current_steps": 2480, "total_steps": 61300, "loss": 0.5912, "lr": 2.0220228384991843e-05, "epoch": 0.40456769983686786, "percentage": 4.05, "elapsed_time": "0:18:38", "remaining_time": "7:22:05", "throughput": 4808.19, "total_tokens": 5377344} {"current_steps": 2485, "total_steps": 61300, "loss": 0.5708, "lr": 2.0261011419249594e-05, "epoch": 0.40538336052202284, "percentage": 4.05, "elapsed_time": "0:18:40", "remaining_time": "7:21:55", "throughput": 4808.31, "total_tokens": 5386752} {"current_steps": 2490, "total_steps": 61300, "loss": 0.6262, "lr": 2.030179445350734e-05, "epoch": 0.4061990212071778, "percentage": 4.06, "elapsed_time": "0:18:42", "remaining_time": "7:21:47", "throughput": 4808.3, "total_tokens": 5396384} {"current_steps": 2495, "total_steps": 61300, "loss": 0.6724, "lr": 2.034257748776509e-05, "epoch": 0.4070146818923328, "percentage": 4.07, "elapsed_time": "0:18:44", "remaining_time": "7:21:48", "throughput": 4808.49, "total_tokens": 5408256} {"current_steps": 2500, "total_steps": 61300, "loss": 0.5384, "lr": 2.038336052202284e-05, "epoch": 0.4078303425774878, "percentage": 4.08, "elapsed_time": "0:18:46", "remaining_time": "7:21:45", "throughput": 4808.4, "total_tokens": 5418752} {"current_steps": 2505, "total_steps": 61300, "loss": 0.5939, "lr": 2.0424143556280588e-05, "epoch": 0.4086460032626427, "percentage": 4.09, "elapsed_time": "0:18:49", "remaining_time": "7:21:43", "throughput": 4808.44, "total_tokens": 5429792} {"current_steps": 2510, "total_steps": 61300, "loss": 0.62, "lr": 2.0464926590538336e-05, "epoch": 0.4094616639477977, "percentage": 4.09, "elapsed_time": "0:18:51", "remaining_time": "7:21:42", "throughput": 4808.37, "total_tokens": 5440608} {"current_steps": 2515, "total_steps": 61300, "loss": 0.5747, "lr": 2.0505709624796087e-05, "epoch": 0.4102773246329527, "percentage": 4.1, "elapsed_time": "0:18:53", "remaining_time": "7:21:33", "throughput": 4808.31, "total_tokens": 5450016} {"current_steps": 2520, "total_steps": 61300, "loss": 0.5528, "lr": 2.0546492659053834e-05, "epoch": 0.4110929853181077, "percentage": 4.11, "elapsed_time": "0:18:55", "remaining_time": "7:21:32", "throughput": 4808.27, "total_tokens": 5461120} {"current_steps": 2525, "total_steps": 61300, "loss": 0.5975, "lr": 2.0587275693311582e-05, "epoch": 0.41190864600326266, "percentage": 4.12, "elapsed_time": "0:18:57", "remaining_time": "7:21:29", "throughput": 4808.19, "total_tokens": 5471648} {"current_steps": 2530, "total_steps": 61300, "loss": 0.6333, "lr": 2.0628058727569333e-05, "epoch": 0.41272430668841764, "percentage": 4.13, "elapsed_time": "0:19:00", "remaining_time": "7:21:27", "throughput": 4808.26, "total_tokens": 5482656} {"current_steps": 2535, "total_steps": 61300, "loss": 0.4386, "lr": 2.066884176182708e-05, "epoch": 0.41353996737357257, "percentage": 4.14, "elapsed_time": "0:19:02", "remaining_time": "7:21:14", "throughput": 4808.19, "total_tokens": 5491168} {"current_steps": 2540, "total_steps": 61300, "loss": 0.5749, "lr": 2.070962479608483e-05, "epoch": 0.41435562805872755, "percentage": 4.14, "elapsed_time": "0:19:04", "remaining_time": "7:21:11", "throughput": 4808.18, "total_tokens": 5501792} {"current_steps": 2545, "total_steps": 61300, "loss": 0.4401, "lr": 2.0750407830342576e-05, "epoch": 0.41517128874388254, "percentage": 4.15, "elapsed_time": "0:19:06", "remaining_time": "7:21:10", "throughput": 4808.26, "total_tokens": 5513152} {"current_steps": 2550, "total_steps": 61300, "loss": 0.5949, "lr": 2.0791190864600327e-05, "epoch": 0.4159869494290375, "percentage": 4.16, "elapsed_time": "0:19:08", "remaining_time": "7:21:10", "throughput": 4808.33, "total_tokens": 5524480} {"current_steps": 2555, "total_steps": 61300, "loss": 0.5028, "lr": 2.0831973898858075e-05, "epoch": 0.4168026101141925, "percentage": 4.17, "elapsed_time": "0:19:11", "remaining_time": "7:21:06", "throughput": 4808.45, "total_tokens": 5535008} {"current_steps": 2560, "total_steps": 61300, "loss": 0.6725, "lr": 2.0872756933115826e-05, "epoch": 0.4176182707993475, "percentage": 4.18, "elapsed_time": "0:19:13", "remaining_time": "7:21:05", "throughput": 4808.4, "total_tokens": 5546048} {"current_steps": 2565, "total_steps": 61300, "loss": 0.5074, "lr": 2.0913539967373573e-05, "epoch": 0.4184339314845024, "percentage": 4.18, "elapsed_time": "0:19:15", "remaining_time": "7:21:06", "throughput": 4808.49, "total_tokens": 5557760} {"current_steps": 2570, "total_steps": 61300, "loss": 0.4949, "lr": 2.0954323001631324e-05, "epoch": 0.4192495921696574, "percentage": 4.19, "elapsed_time": "0:19:17", "remaining_time": "7:20:59", "throughput": 4808.42, "total_tokens": 5567488} {"current_steps": 2575, "total_steps": 61300, "loss": 0.5866, "lr": 2.099510603588907e-05, "epoch": 0.4200652528548124, "percentage": 4.2, "elapsed_time": "0:19:20", "remaining_time": "7:20:58", "throughput": 4808.4, "total_tokens": 5578592} {"current_steps": 2580, "total_steps": 61300, "loss": 0.6226, "lr": 2.103588907014682e-05, "epoch": 0.42088091353996737, "percentage": 4.21, "elapsed_time": "0:19:22", "remaining_time": "7:20:52", "throughput": 4808.42, "total_tokens": 5588576} {"current_steps": 2585, "total_steps": 61300, "loss": 0.5173, "lr": 2.1076672104404567e-05, "epoch": 0.42169657422512236, "percentage": 4.22, "elapsed_time": "0:19:24", "remaining_time": "7:20:49", "throughput": 4808.43, "total_tokens": 5599264} {"current_steps": 2590, "total_steps": 61300, "loss": 0.4647, "lr": 2.1117455138662318e-05, "epoch": 0.42251223491027734, "percentage": 4.23, "elapsed_time": "0:19:26", "remaining_time": "7:20:44", "throughput": 4808.39, "total_tokens": 5609504} {"current_steps": 2595, "total_steps": 61300, "loss": 0.4552, "lr": 2.1158238172920066e-05, "epoch": 0.4233278955954323, "percentage": 4.23, "elapsed_time": "0:19:28", "remaining_time": "7:20:41", "throughput": 4808.43, "total_tokens": 5620256} {"current_steps": 2600, "total_steps": 61300, "loss": 0.5087, "lr": 2.1199021207177817e-05, "epoch": 0.42414355628058725, "percentage": 4.24, "elapsed_time": "0:19:30", "remaining_time": "7:20:37", "throughput": 4808.39, "total_tokens": 5630592} {"current_steps": 2605, "total_steps": 61300, "loss": 0.5561, "lr": 2.123980424143556e-05, "epoch": 0.42495921696574224, "percentage": 4.25, "elapsed_time": "0:19:33", "remaining_time": "7:20:35", "throughput": 4808.52, "total_tokens": 5641536} {"current_steps": 2610, "total_steps": 61300, "loss": 0.5938, "lr": 2.1280587275693312e-05, "epoch": 0.4257748776508972, "percentage": 4.26, "elapsed_time": "0:19:35", "remaining_time": "7:20:32", "throughput": 4808.62, "total_tokens": 5652416} {"current_steps": 2615, "total_steps": 61300, "loss": 0.4907, "lr": 2.132137030995106e-05, "epoch": 0.4265905383360522, "percentage": 4.27, "elapsed_time": "0:19:37", "remaining_time": "7:20:26", "throughput": 4808.7, "total_tokens": 5662528} {"current_steps": 2620, "total_steps": 61300, "loss": 0.5252, "lr": 2.136215334420881e-05, "epoch": 0.4274061990212072, "percentage": 4.27, "elapsed_time": "0:19:39", "remaining_time": "7:20:19", "throughput": 4808.61, "total_tokens": 5672288} {"current_steps": 2625, "total_steps": 61300, "loss": 0.6227, "lr": 2.140293637846656e-05, "epoch": 0.4282218597063622, "percentage": 4.28, "elapsed_time": "0:19:41", "remaining_time": "7:20:16", "throughput": 4808.68, "total_tokens": 5682976} {"current_steps": 2630, "total_steps": 61300, "loss": 0.5453, "lr": 2.144371941272431e-05, "epoch": 0.4290375203915171, "percentage": 4.29, "elapsed_time": "0:19:44", "remaining_time": "7:20:16", "throughput": 4808.62, "total_tokens": 5694240} {"current_steps": 2635, "total_steps": 61300, "loss": 0.6011, "lr": 2.1484502446982057e-05, "epoch": 0.4298531810766721, "percentage": 4.3, "elapsed_time": "0:19:46", "remaining_time": "7:20:11", "throughput": 4808.46, "total_tokens": 5704192} {"current_steps": 2640, "total_steps": 61300, "loss": 0.5706, "lr": 2.1525285481239805e-05, "epoch": 0.43066884176182707, "percentage": 4.31, "elapsed_time": "0:19:48", "remaining_time": "7:20:12", "throughput": 4808.63, "total_tokens": 5715968} {"current_steps": 2645, "total_steps": 61300, "loss": 0.4859, "lr": 2.1566068515497553e-05, "epoch": 0.43148450244698205, "percentage": 4.31, "elapsed_time": "0:19:50", "remaining_time": "7:20:09", "throughput": 4808.74, "total_tokens": 5726784} {"current_steps": 2650, "total_steps": 61300, "loss": 0.5468, "lr": 2.1606851549755304e-05, "epoch": 0.43230016313213704, "percentage": 4.32, "elapsed_time": "0:19:53", "remaining_time": "7:20:09", "throughput": 4808.66, "total_tokens": 5737952} {"current_steps": 2655, "total_steps": 61300, "loss": 0.537, "lr": 2.164763458401305e-05, "epoch": 0.433115823817292, "percentage": 4.33, "elapsed_time": "0:19:55", "remaining_time": "7:20:05", "throughput": 4808.72, "total_tokens": 5748512} {"current_steps": 2660, "total_steps": 61300, "loss": 0.5144, "lr": 2.1688417618270802e-05, "epoch": 0.433931484502447, "percentage": 4.34, "elapsed_time": "0:19:57", "remaining_time": "7:20:00", "throughput": 4808.78, "total_tokens": 5758944} {"current_steps": 2665, "total_steps": 61300, "loss": 0.4513, "lr": 2.172920065252855e-05, "epoch": 0.43474714518760194, "percentage": 4.35, "elapsed_time": "0:19:59", "remaining_time": "7:19:57", "throughput": 4808.81, "total_tokens": 5769632} {"current_steps": 2670, "total_steps": 61300, "loss": 0.4418, "lr": 2.1769983686786298e-05, "epoch": 0.4355628058727569, "percentage": 4.36, "elapsed_time": "0:20:02", "remaining_time": "7:19:59", "throughput": 4808.71, "total_tokens": 5781248} {"current_steps": 2675, "total_steps": 61300, "loss": 0.5899, "lr": 2.1810766721044045e-05, "epoch": 0.4363784665579119, "percentage": 4.36, "elapsed_time": "0:20:04", "remaining_time": "7:19:57", "throughput": 4808.77, "total_tokens": 5792192} {"current_steps": 2680, "total_steps": 61300, "loss": 0.4946, "lr": 2.1851549755301796e-05, "epoch": 0.4371941272430669, "percentage": 4.37, "elapsed_time": "0:20:06", "remaining_time": "7:19:56", "throughput": 4808.78, "total_tokens": 5803264} {"current_steps": 2685, "total_steps": 61300, "loss": 0.4228, "lr": 2.1892332789559544e-05, "epoch": 0.43800978792822187, "percentage": 4.38, "elapsed_time": "0:20:09", "remaining_time": "7:19:59", "throughput": 4808.73, "total_tokens": 5815072} {"current_steps": 2690, "total_steps": 61300, "loss": 0.5038, "lr": 2.1933115823817295e-05, "epoch": 0.43882544861337686, "percentage": 4.39, "elapsed_time": "0:20:11", "remaining_time": "7:19:53", "throughput": 4808.76, "total_tokens": 5825248} {"current_steps": 2695, "total_steps": 61300, "loss": 0.4987, "lr": 2.1973898858075043e-05, "epoch": 0.4396411092985318, "percentage": 4.4, "elapsed_time": "0:20:13", "remaining_time": "7:19:50", "throughput": 4808.75, "total_tokens": 5835904} {"current_steps": 2700, "total_steps": 61300, "loss": 0.4966, "lr": 2.201468189233279e-05, "epoch": 0.44045676998368677, "percentage": 4.4, "elapsed_time": "0:20:15", "remaining_time": "7:19:39", "throughput": 4808.72, "total_tokens": 5844736} {"current_steps": 2705, "total_steps": 61300, "loss": 0.5891, "lr": 2.2055464926590538e-05, "epoch": 0.44127243066884175, "percentage": 4.41, "elapsed_time": "0:20:17", "remaining_time": "7:19:42", "throughput": 4808.77, "total_tokens": 5856672} {"current_steps": 2710, "total_steps": 61300, "loss": 0.4883, "lr": 2.209624796084829e-05, "epoch": 0.44208809135399674, "percentage": 4.42, "elapsed_time": "0:20:20", "remaining_time": "7:19:37", "throughput": 4808.69, "total_tokens": 5866848} {"current_steps": 2715, "total_steps": 61300, "loss": 0.4431, "lr": 2.2137030995106037e-05, "epoch": 0.4429037520391517, "percentage": 4.43, "elapsed_time": "0:20:22", "remaining_time": "7:19:35", "throughput": 4808.72, "total_tokens": 5877856} {"current_steps": 2720, "total_steps": 61300, "loss": 0.5396, "lr": 2.2177814029363788e-05, "epoch": 0.4437194127243067, "percentage": 4.44, "elapsed_time": "0:20:24", "remaining_time": "7:19:34", "throughput": 4808.7, "total_tokens": 5888896} {"current_steps": 2725, "total_steps": 61300, "loss": 0.4654, "lr": 2.2218597063621535e-05, "epoch": 0.4445350734094617, "percentage": 4.45, "elapsed_time": "0:20:26", "remaining_time": "7:19:33", "throughput": 4808.64, "total_tokens": 5899872} {"current_steps": 2730, "total_steps": 61300, "loss": 0.5572, "lr": 2.2259380097879283e-05, "epoch": 0.4453507340946166, "percentage": 4.45, "elapsed_time": "0:20:29", "remaining_time": "7:19:28", "throughput": 4808.7, "total_tokens": 5910272} {"current_steps": 2735, "total_steps": 61300, "loss": 0.4207, "lr": 2.230016313213703e-05, "epoch": 0.4461663947797716, "percentage": 4.46, "elapsed_time": "0:20:31", "remaining_time": "7:19:27", "throughput": 4808.72, "total_tokens": 5921312} {"current_steps": 2740, "total_steps": 61300, "loss": 0.5744, "lr": 2.234094616639478e-05, "epoch": 0.4469820554649266, "percentage": 4.47, "elapsed_time": "0:20:33", "remaining_time": "7:19:24", "throughput": 4808.71, "total_tokens": 5932032} {"current_steps": 2745, "total_steps": 61300, "loss": 0.3931, "lr": 2.238172920065253e-05, "epoch": 0.44779771615008157, "percentage": 4.48, "elapsed_time": "0:20:35", "remaining_time": "7:19:19", "throughput": 4808.8, "total_tokens": 5942176} {"current_steps": 2750, "total_steps": 61300, "loss": 0.5741, "lr": 2.2422512234910277e-05, "epoch": 0.44861337683523655, "percentage": 4.49, "elapsed_time": "0:20:38", "remaining_time": "7:19:21", "throughput": 4808.95, "total_tokens": 5954336} {"current_steps": 2755, "total_steps": 61300, "loss": 0.4157, "lr": 2.2463295269168028e-05, "epoch": 0.44942903752039154, "percentage": 4.49, "elapsed_time": "0:20:40", "remaining_time": "7:19:20", "throughput": 4808.85, "total_tokens": 5965152} {"current_steps": 2760, "total_steps": 61300, "loss": 0.5184, "lr": 2.2504078303425776e-05, "epoch": 0.45024469820554647, "percentage": 4.5, "elapsed_time": "0:20:42", "remaining_time": "7:19:22", "throughput": 4809.1, "total_tokens": 5977216} {"current_steps": 2765, "total_steps": 61300, "loss": 0.4628, "lr": 2.2544861337683527e-05, "epoch": 0.45106035889070145, "percentage": 4.51, "elapsed_time": "0:20:45", "remaining_time": "7:19:19", "throughput": 4809.11, "total_tokens": 5988000} {"current_steps": 2770, "total_steps": 61300, "loss": 0.5326, "lr": 2.258564437194127e-05, "epoch": 0.45187601957585644, "percentage": 4.52, "elapsed_time": "0:20:47", "remaining_time": "7:19:15", "throughput": 4809.06, "total_tokens": 5998400} {"current_steps": 2775, "total_steps": 61300, "loss": 0.5502, "lr": 2.2626427406199022e-05, "epoch": 0.4526916802610114, "percentage": 4.53, "elapsed_time": "0:20:49", "remaining_time": "7:19:18", "throughput": 4808.94, "total_tokens": 6010176} {"current_steps": 2780, "total_steps": 61300, "loss": 0.54, "lr": 2.266721044045677e-05, "epoch": 0.4535073409461664, "percentage": 4.54, "elapsed_time": "0:20:52", "remaining_time": "7:19:17", "throughput": 4808.98, "total_tokens": 6021312} {"current_steps": 2785, "total_steps": 61300, "loss": 0.5193, "lr": 2.270799347471452e-05, "epoch": 0.4543230016313214, "percentage": 4.54, "elapsed_time": "0:20:54", "remaining_time": "7:19:17", "throughput": 4809.16, "total_tokens": 6033024} {"current_steps": 2790, "total_steps": 61300, "loss": 0.4501, "lr": 2.2748776508972268e-05, "epoch": 0.4551386623164764, "percentage": 4.55, "elapsed_time": "0:20:56", "remaining_time": "7:19:09", "throughput": 4809.04, "total_tokens": 6042432} {"current_steps": 2795, "total_steps": 61300, "loss": 0.4965, "lr": 2.278955954323002e-05, "epoch": 0.4559543230016313, "percentage": 4.56, "elapsed_time": "0:20:58", "remaining_time": "7:19:12", "throughput": 4809.04, "total_tokens": 6054304} {"current_steps": 2800, "total_steps": 61300, "loss": 0.4388, "lr": 2.2830342577487763e-05, "epoch": 0.4567699836867863, "percentage": 4.57, "elapsed_time": "0:21:01", "remaining_time": "7:19:10", "throughput": 4809.02, "total_tokens": 6065312} {"current_steps": 2805, "total_steps": 61300, "loss": 0.4872, "lr": 2.2871125611745514e-05, "epoch": 0.45758564437194127, "percentage": 4.58, "elapsed_time": "0:21:03", "remaining_time": "7:19:04", "throughput": 4808.93, "total_tokens": 6075072} {"current_steps": 2810, "total_steps": 61300, "loss": 0.4353, "lr": 2.2911908646003262e-05, "epoch": 0.45840130505709625, "percentage": 4.58, "elapsed_time": "0:21:05", "remaining_time": "7:18:59", "throughput": 4808.77, "total_tokens": 6084992} {"current_steps": 2815, "total_steps": 61300, "loss": 0.5138, "lr": 2.2952691680261013e-05, "epoch": 0.45921696574225124, "percentage": 4.59, "elapsed_time": "0:21:07", "remaining_time": "7:18:55", "throughput": 4808.78, "total_tokens": 6095424} {"current_steps": 2820, "total_steps": 61300, "loss": 0.4382, "lr": 2.299347471451876e-05, "epoch": 0.4600326264274062, "percentage": 4.6, "elapsed_time": "0:21:10", "remaining_time": "7:18:57", "throughput": 4808.82, "total_tokens": 6107328} {"current_steps": 2825, "total_steps": 61300, "loss": 0.4163, "lr": 2.3034257748776512e-05, "epoch": 0.46084828711256115, "percentage": 4.61, "elapsed_time": "0:21:12", "remaining_time": "7:18:54", "throughput": 4808.82, "total_tokens": 6118048} {"current_steps": 2830, "total_steps": 61300, "loss": 0.3895, "lr": 2.307504078303426e-05, "epoch": 0.46166394779771613, "percentage": 4.62, "elapsed_time": "0:21:14", "remaining_time": "7:18:50", "throughput": 4808.93, "total_tokens": 6128512} {"current_steps": 2835, "total_steps": 61300, "loss": 0.4545, "lr": 2.3115823817292007e-05, "epoch": 0.4624796084828711, "percentage": 4.62, "elapsed_time": "0:21:16", "remaining_time": "7:18:45", "throughput": 4808.9, "total_tokens": 6138720} {"current_steps": 2840, "total_steps": 61300, "loss": 0.4497, "lr": 2.3156606851549755e-05, "epoch": 0.4632952691680261, "percentage": 4.63, "elapsed_time": "0:21:18", "remaining_time": "7:18:42", "throughput": 4809.01, "total_tokens": 6149600} {"current_steps": 2845, "total_steps": 61300, "loss": 0.4883, "lr": 2.3197389885807506e-05, "epoch": 0.4641109298531811, "percentage": 4.64, "elapsed_time": "0:21:21", "remaining_time": "7:18:42", "throughput": 4808.81, "total_tokens": 6160608} {"current_steps": 2850, "total_steps": 61300, "loss": 0.5776, "lr": 2.3238172920065253e-05, "epoch": 0.46492659053833607, "percentage": 4.65, "elapsed_time": "0:21:23", "remaining_time": "7:18:42", "throughput": 4808.74, "total_tokens": 6171968} {"current_steps": 2855, "total_steps": 61300, "loss": 0.495, "lr": 2.3278955954323004e-05, "epoch": 0.46574225122349105, "percentage": 4.66, "elapsed_time": "0:21:25", "remaining_time": "7:18:43", "throughput": 4808.7, "total_tokens": 6183360} {"current_steps": 2860, "total_steps": 61300, "loss": 0.3744, "lr": 2.3319738988580752e-05, "epoch": 0.466557911908646, "percentage": 4.67, "elapsed_time": "0:21:28", "remaining_time": "7:18:39", "throughput": 4808.62, "total_tokens": 6193664} {"current_steps": 2865, "total_steps": 61300, "loss": 0.4558, "lr": 2.33605220228385e-05, "epoch": 0.46737357259380097, "percentage": 4.67, "elapsed_time": "0:21:30", "remaining_time": "7:18:36", "throughput": 4808.57, "total_tokens": 6204320} {"current_steps": 2870, "total_steps": 61300, "loss": 0.4261, "lr": 2.3401305057096247e-05, "epoch": 0.46818923327895595, "percentage": 4.68, "elapsed_time": "0:21:32", "remaining_time": "7:18:31", "throughput": 4808.66, "total_tokens": 6214560} {"current_steps": 2875, "total_steps": 61300, "loss": 0.4387, "lr": 2.3442088091354e-05, "epoch": 0.46900489396411094, "percentage": 4.69, "elapsed_time": "0:21:34", "remaining_time": "7:18:31", "throughput": 4808.74, "total_tokens": 6226176} {"current_steps": 2880, "total_steps": 61300, "loss": 0.5685, "lr": 2.3482871125611746e-05, "epoch": 0.4698205546492659, "percentage": 4.7, "elapsed_time": "0:21:37", "remaining_time": "7:18:29", "throughput": 4808.58, "total_tokens": 6236768} {"current_steps": 2885, "total_steps": 61300, "loss": 0.5078, "lr": 2.3523654159869497e-05, "epoch": 0.4706362153344209, "percentage": 4.71, "elapsed_time": "0:21:39", "remaining_time": "7:18:27", "throughput": 4808.44, "total_tokens": 6247424} {"current_steps": 2890, "total_steps": 61300, "loss": 0.484, "lr": 2.3564437194127245e-05, "epoch": 0.47145187601957583, "percentage": 4.71, "elapsed_time": "0:21:41", "remaining_time": "7:18:21", "throughput": 4808.42, "total_tokens": 6257280} {"current_steps": 2895, "total_steps": 61300, "loss": 0.4264, "lr": 2.3605220228384996e-05, "epoch": 0.4722675367047308, "percentage": 4.72, "elapsed_time": "0:21:43", "remaining_time": "7:18:19", "throughput": 4808.34, "total_tokens": 6268160} {"current_steps": 2900, "total_steps": 61300, "loss": 0.4553, "lr": 2.364600326264274e-05, "epoch": 0.4730831973898858, "percentage": 4.73, "elapsed_time": "0:21:45", "remaining_time": "7:18:17", "throughput": 4808.36, "total_tokens": 6278976} {"current_steps": 2905, "total_steps": 61300, "loss": 0.3656, "lr": 2.368678629690049e-05, "epoch": 0.4738988580750408, "percentage": 4.74, "elapsed_time": "0:21:48", "remaining_time": "7:18:16", "throughput": 4808.39, "total_tokens": 6290144} {"current_steps": 2910, "total_steps": 61300, "loss": 0.5192, "lr": 2.372756933115824e-05, "epoch": 0.47471451876019577, "percentage": 4.75, "elapsed_time": "0:21:50", "remaining_time": "7:18:16", "throughput": 4808.42, "total_tokens": 6301760} {"current_steps": 2915, "total_steps": 61300, "loss": 0.4354, "lr": 2.376835236541599e-05, "epoch": 0.47553017944535075, "percentage": 4.76, "elapsed_time": "0:21:52", "remaining_time": "7:18:14", "throughput": 4808.29, "total_tokens": 6312416} {"current_steps": 2920, "total_steps": 61300, "loss": 0.4558, "lr": 2.3809135399673737e-05, "epoch": 0.4763458401305057, "percentage": 4.76, "elapsed_time": "0:21:55", "remaining_time": "7:18:13", "throughput": 4808.26, "total_tokens": 6323488} {"current_steps": 2925, "total_steps": 61300, "loss": 0.4504, "lr": 2.384991843393149e-05, "epoch": 0.47716150081566067, "percentage": 4.77, "elapsed_time": "0:21:57", "remaining_time": "7:18:11", "throughput": 4808.41, "total_tokens": 6334496} {"current_steps": 2930, "total_steps": 61300, "loss": 0.4708, "lr": 2.3890701468189233e-05, "epoch": 0.47797716150081565, "percentage": 4.78, "elapsed_time": "0:21:59", "remaining_time": "7:18:04", "throughput": 4808.4, "total_tokens": 6344320} {"current_steps": 2935, "total_steps": 61300, "loss": 0.4175, "lr": 2.3931484502446984e-05, "epoch": 0.47879282218597063, "percentage": 4.79, "elapsed_time": "0:22:01", "remaining_time": "7:18:05", "throughput": 4808.5, "total_tokens": 6355904} {"current_steps": 2940, "total_steps": 61300, "loss": 0.5301, "lr": 2.397226753670473e-05, "epoch": 0.4796084828711256, "percentage": 4.8, "elapsed_time": "0:22:03", "remaining_time": "7:18:00", "throughput": 4808.48, "total_tokens": 6366016} {"current_steps": 2945, "total_steps": 61300, "loss": 0.3849, "lr": 2.4013050570962482e-05, "epoch": 0.4804241435562806, "percentage": 4.8, "elapsed_time": "0:22:05", "remaining_time": "7:17:53", "throughput": 4808.38, "total_tokens": 6375712} {"current_steps": 2950, "total_steps": 61300, "loss": 0.4285, "lr": 2.405383360522023e-05, "epoch": 0.4812398042414356, "percentage": 4.81, "elapsed_time": "0:22:08", "remaining_time": "7:17:52", "throughput": 4808.4, "total_tokens": 6386720} {"current_steps": 2955, "total_steps": 61300, "loss": 0.4848, "lr": 2.4094616639477978e-05, "epoch": 0.4820554649265905, "percentage": 4.82, "elapsed_time": "0:22:10", "remaining_time": "7:17:49", "throughput": 4808.43, "total_tokens": 6397536} {"current_steps": 2960, "total_steps": 61300, "loss": 0.4559, "lr": 2.4135399673735725e-05, "epoch": 0.4828711256117455, "percentage": 4.83, "elapsed_time": "0:22:12", "remaining_time": "7:17:47", "throughput": 4808.39, "total_tokens": 6408384} {"current_steps": 2965, "total_steps": 61300, "loss": 0.4687, "lr": 2.4176182707993476e-05, "epoch": 0.4836867862969005, "percentage": 4.84, "elapsed_time": "0:22:15", "remaining_time": "7:17:51", "throughput": 4808.35, "total_tokens": 6420640} {"current_steps": 2970, "total_steps": 61300, "loss": 0.4035, "lr": 2.4216965742251224e-05, "epoch": 0.48450244698205547, "percentage": 4.85, "elapsed_time": "0:22:17", "remaining_time": "7:17:50", "throughput": 4808.27, "total_tokens": 6431680} {"current_steps": 2975, "total_steps": 61300, "loss": 0.4104, "lr": 2.425774877650897e-05, "epoch": 0.48531810766721045, "percentage": 4.85, "elapsed_time": "0:22:19", "remaining_time": "7:17:47", "throughput": 4808.36, "total_tokens": 6442368} {"current_steps": 2980, "total_steps": 61300, "loss": 0.3584, "lr": 2.4298531810766723e-05, "epoch": 0.48613376835236544, "percentage": 4.86, "elapsed_time": "0:22:22", "remaining_time": "7:17:47", "throughput": 4808.35, "total_tokens": 6453856} {"current_steps": 2985, "total_steps": 61300, "loss": 0.4052, "lr": 2.433931484502447e-05, "epoch": 0.48694942903752036, "percentage": 4.87, "elapsed_time": "0:22:24", "remaining_time": "7:17:44", "throughput": 4808.44, "total_tokens": 6464640} {"current_steps": 2990, "total_steps": 61300, "loss": 0.3707, "lr": 2.438009787928222e-05, "epoch": 0.48776508972267535, "percentage": 4.88, "elapsed_time": "0:22:26", "remaining_time": "7:17:42", "throughput": 4808.42, "total_tokens": 6475392} {"current_steps": 2995, "total_steps": 61300, "loss": 0.4952, "lr": 2.442088091353997e-05, "epoch": 0.48858075040783033, "percentage": 4.89, "elapsed_time": "0:22:29", "remaining_time": "7:17:42", "throughput": 4808.49, "total_tokens": 6486880} {"current_steps": 3000, "total_steps": 61300, "loss": 0.4135, "lr": 2.4461663947797717e-05, "epoch": 0.4893964110929853, "percentage": 4.89, "elapsed_time": "0:22:31", "remaining_time": "7:17:38", "throughput": 4808.42, "total_tokens": 6497216} {"current_steps": 3005, "total_steps": 61300, "loss": 0.4063, "lr": 2.4502446982055464e-05, "epoch": 0.4902120717781403, "percentage": 4.9, "elapsed_time": "0:22:33", "remaining_time": "7:17:37", "throughput": 4808.35, "total_tokens": 6508320} {"current_steps": 3010, "total_steps": 61300, "loss": 0.484, "lr": 2.4543230016313215e-05, "epoch": 0.4910277324632953, "percentage": 4.91, "elapsed_time": "0:22:35", "remaining_time": "7:17:37", "throughput": 4808.36, "total_tokens": 6519520} {"current_steps": 3015, "total_steps": 61300, "loss": 0.4078, "lr": 2.4584013050570963e-05, "epoch": 0.49184339314845027, "percentage": 4.92, "elapsed_time": "0:22:38", "remaining_time": "7:17:34", "throughput": 4808.37, "total_tokens": 6530240} {"current_steps": 3020, "total_steps": 61300, "loss": 0.457, "lr": 2.4624796084828714e-05, "epoch": 0.4926590538336052, "percentage": 4.93, "elapsed_time": "0:22:40", "remaining_time": "7:17:28", "throughput": 4808.32, "total_tokens": 6540192} {"current_steps": 3025, "total_steps": 61300, "loss": 0.4381, "lr": 2.466557911908646e-05, "epoch": 0.4934747145187602, "percentage": 4.93, "elapsed_time": "0:22:42", "remaining_time": "7:17:23", "throughput": 4808.14, "total_tokens": 6550016} {"current_steps": 3030, "total_steps": 61300, "loss": 0.4336, "lr": 2.470636215334421e-05, "epoch": 0.49429037520391517, "percentage": 4.94, "elapsed_time": "0:22:44", "remaining_time": "7:17:20", "throughput": 4808.11, "total_tokens": 6560672} {"current_steps": 3035, "total_steps": 61300, "loss": 0.4469, "lr": 2.4747145187601957e-05, "epoch": 0.49510603588907015, "percentage": 4.95, "elapsed_time": "0:22:46", "remaining_time": "7:17:19", "throughput": 4808.1, "total_tokens": 6571808} {"current_steps": 3040, "total_steps": 61300, "loss": 0.3815, "lr": 2.4787928221859708e-05, "epoch": 0.49592169657422513, "percentage": 4.96, "elapsed_time": "0:22:49", "remaining_time": "7:17:16", "throughput": 4808.28, "total_tokens": 6582624} {"current_steps": 3045, "total_steps": 61300, "loss": 0.4905, "lr": 2.4828711256117456e-05, "epoch": 0.4967373572593801, "percentage": 4.97, "elapsed_time": "0:22:51", "remaining_time": "7:17:20", "throughput": 4808.28, "total_tokens": 6595008} {"current_steps": 3050, "total_steps": 61300, "loss": 0.4226, "lr": 2.4869494290375207e-05, "epoch": 0.49755301794453505, "percentage": 4.98, "elapsed_time": "0:22:54", "remaining_time": "7:17:22", "throughput": 4808.29, "total_tokens": 6606976} {"current_steps": 3055, "total_steps": 61300, "loss": 0.4171, "lr": 2.4910277324632954e-05, "epoch": 0.49836867862969003, "percentage": 4.98, "elapsed_time": "0:22:56", "remaining_time": "7:17:19", "throughput": 4808.37, "total_tokens": 6617760} {"current_steps": 3060, "total_steps": 61300, "loss": 0.4177, "lr": 2.4951060358890702e-05, "epoch": 0.499184339314845, "percentage": 4.99, "elapsed_time": "0:22:58", "remaining_time": "7:17:19", "throughput": 4808.27, "total_tokens": 6628896} {"current_steps": 3065, "total_steps": 61300, "loss": 0.4234, "lr": 2.499184339314845e-05, "epoch": 0.5, "percentage": 5.0, "elapsed_time": "0:23:00", "remaining_time": "7:17:15", "throughput": 4808.39, "total_tokens": 6639424} {"current_steps": 3065, "total_steps": 61300, "eval_loss": 0.43225759267807007, "epoch": 0.5, "percentage": 5.0, "elapsed_time": "0:25:12", "remaining_time": "7:59:06", "throughput": 4388.38, "total_tokens": 6639424} {"current_steps": 3070, "total_steps": 61300, "loss": 0.4592, "lr": 2.5032626427406204e-05, "epoch": 0.5008156606851549, "percentage": 5.01, "elapsed_time": "0:25:15", "remaining_time": "7:59:13", "throughput": 4386.26, "total_tokens": 6649280} {"current_steps": 3075, "total_steps": 61300, "loss": 0.4019, "lr": 2.507340946166395e-05, "epoch": 0.50163132137031, "percentage": 5.02, "elapsed_time": "0:25:17", "remaining_time": "7:59:02", "throughput": 4386.78, "total_tokens": 6659008} {"current_steps": 3080, "total_steps": 61300, "loss": 0.5364, "lr": 2.5114192495921696e-05, "epoch": 0.5024469820554649, "percentage": 5.02, "elapsed_time": "0:25:20", "remaining_time": "7:58:54", "throughput": 4387.32, "total_tokens": 6669312} {"current_steps": 3085, "total_steps": 61300, "loss": 0.4217, "lr": 2.5154975530179447e-05, "epoch": 0.5032626427406199, "percentage": 5.03, "elapsed_time": "0:25:22", "remaining_time": "7:58:47", "throughput": 4387.91, "total_tokens": 6679968} {"current_steps": 3090, "total_steps": 61300, "loss": 0.4506, "lr": 2.5195758564437195e-05, "epoch": 0.5040783034257749, "percentage": 5.04, "elapsed_time": "0:25:24", "remaining_time": "7:58:36", "throughput": 4388.43, "total_tokens": 6689728} {"current_steps": 3095, "total_steps": 61300, "loss": 0.3334, "lr": 2.5236541598694946e-05, "epoch": 0.5048939641109299, "percentage": 5.05, "elapsed_time": "0:25:26", "remaining_time": "7:58:30", "throughput": 4389.04, "total_tokens": 6700448} {"current_steps": 3100, "total_steps": 61300, "loss": 0.5625, "lr": 2.5277324632952693e-05, "epoch": 0.5057096247960848, "percentage": 5.06, "elapsed_time": "0:25:28", "remaining_time": "7:58:23", "throughput": 4389.72, "total_tokens": 6711424} {"current_steps": 3105, "total_steps": 61300, "loss": 0.3948, "lr": 2.5318107667210438e-05, "epoch": 0.5065252854812398, "percentage": 5.07, "elapsed_time": "0:25:31", "remaining_time": "7:58:18", "throughput": 4390.45, "total_tokens": 6722752} {"current_steps": 3110, "total_steps": 61300, "loss": 0.3843, "lr": 2.5358890701468192e-05, "epoch": 0.5073409461663948, "percentage": 5.07, "elapsed_time": "0:25:33", "remaining_time": "7:58:13", "throughput": 4391.16, "total_tokens": 6734080} {"current_steps": 3115, "total_steps": 61300, "loss": 0.419, "lr": 2.5399673735725936e-05, "epoch": 0.5081566068515497, "percentage": 5.08, "elapsed_time": "0:25:35", "remaining_time": "7:58:06", "throughput": 4391.68, "total_tokens": 6744672} {"current_steps": 3120, "total_steps": 61300, "loss": 0.4454, "lr": 2.544045676998369e-05, "epoch": 0.5089722675367048, "percentage": 5.09, "elapsed_time": "0:25:37", "remaining_time": "7:57:58", "throughput": 4392.31, "total_tokens": 6755104} {"current_steps": 3125, "total_steps": 61300, "loss": 0.4289, "lr": 2.5481239804241435e-05, "epoch": 0.5097879282218597, "percentage": 5.1, "elapsed_time": "0:25:40", "remaining_time": "7:57:57", "throughput": 4392.98, "total_tokens": 6767168} {"current_steps": 3130, "total_steps": 61300, "loss": 0.4431, "lr": 2.552202283849919e-05, "epoch": 0.5106035889070146, "percentage": 5.11, "elapsed_time": "0:25:42", "remaining_time": "7:57:48", "throughput": 4393.51, "total_tokens": 6777472} {"current_steps": 3135, "total_steps": 61300, "loss": 0.3672, "lr": 2.5562805872756934e-05, "epoch": 0.5114192495921697, "percentage": 5.11, "elapsed_time": "0:25:44", "remaining_time": "7:57:40", "throughput": 4394.15, "total_tokens": 6787776} {"current_steps": 3140, "total_steps": 61300, "loss": 0.411, "lr": 2.560358890701468e-05, "epoch": 0.5122349102773246, "percentage": 5.12, "elapsed_time": "0:25:47", "remaining_time": "7:57:34", "throughput": 4394.88, "total_tokens": 6799008} {"current_steps": 3145, "total_steps": 61300, "loss": 0.4077, "lr": 2.5644371941272432e-05, "epoch": 0.5130505709624796, "percentage": 5.13, "elapsed_time": "0:25:49", "remaining_time": "7:57:26", "throughput": 4395.44, "total_tokens": 6809440} {"current_steps": 3150, "total_steps": 61300, "loss": 0.4222, "lr": 2.568515497553018e-05, "epoch": 0.5138662316476346, "percentage": 5.14, "elapsed_time": "0:25:51", "remaining_time": "7:57:17", "throughput": 4395.95, "total_tokens": 6819456} {"current_steps": 3155, "total_steps": 61300, "loss": 0.4046, "lr": 2.572593800978793e-05, "epoch": 0.5146818923327896, "percentage": 5.15, "elapsed_time": "0:25:53", "remaining_time": "7:57:07", "throughput": 4396.53, "total_tokens": 6829312} {"current_steps": 3160, "total_steps": 61300, "loss": 0.3607, "lr": 2.576672104404568e-05, "epoch": 0.5154975530179445, "percentage": 5.15, "elapsed_time": "0:25:55", "remaining_time": "7:56:59", "throughput": 4396.96, "total_tokens": 6839456} {"current_steps": 3165, "total_steps": 61300, "loss": 0.4414, "lr": 2.580750407830343e-05, "epoch": 0.5163132137030995, "percentage": 5.16, "elapsed_time": "0:25:57", "remaining_time": "7:56:54", "throughput": 4397.62, "total_tokens": 6850752} {"current_steps": 3170, "total_steps": 61300, "loss": 0.3995, "lr": 2.5848287112561177e-05, "epoch": 0.5171288743882545, "percentage": 5.17, "elapsed_time": "0:26:00", "remaining_time": "7:56:49", "throughput": 4398.3, "total_tokens": 6862144} {"current_steps": 3175, "total_steps": 61300, "loss": 0.3684, "lr": 2.588907014681892e-05, "epoch": 0.5179445350734094, "percentage": 5.18, "elapsed_time": "0:26:02", "remaining_time": "7:56:42", "throughput": 4398.85, "total_tokens": 6872704} {"current_steps": 3180, "total_steps": 61300, "loss": 0.4071, "lr": 2.5929853181076673e-05, "epoch": 0.5187601957585645, "percentage": 5.19, "elapsed_time": "0:26:04", "remaining_time": "7:56:35", "throughput": 4399.44, "total_tokens": 6883232} {"current_steps": 3185, "total_steps": 61300, "loss": 0.4107, "lr": 2.597063621533442e-05, "epoch": 0.5195758564437194, "percentage": 5.2, "elapsed_time": "0:26:06", "remaining_time": "7:56:30", "throughput": 4400.03, "total_tokens": 6894368} {"current_steps": 3190, "total_steps": 61300, "loss": 0.4206, "lr": 2.601141924959217e-05, "epoch": 0.5203915171288744, "percentage": 5.2, "elapsed_time": "0:26:09", "remaining_time": "7:56:28", "throughput": 4400.71, "total_tokens": 6906336} {"current_steps": 3195, "total_steps": 61300, "loss": 0.3748, "lr": 2.605220228384992e-05, "epoch": 0.5212071778140294, "percentage": 5.21, "elapsed_time": "0:26:11", "remaining_time": "7:56:22", "throughput": 4401.34, "total_tokens": 6917440} {"current_steps": 3200, "total_steps": 61300, "loss": 0.394, "lr": 2.609298531810767e-05, "epoch": 0.5220228384991843, "percentage": 5.22, "elapsed_time": "0:26:13", "remaining_time": "7:56:17", "throughput": 4402.02, "total_tokens": 6928736} {"current_steps": 3205, "total_steps": 61300, "loss": 0.4389, "lr": 2.6133768352365418e-05, "epoch": 0.5228384991843393, "percentage": 5.23, "elapsed_time": "0:26:16", "remaining_time": "7:56:11", "throughput": 4402.62, "total_tokens": 6939488} {"current_steps": 3210, "total_steps": 61300, "loss": 0.4235, "lr": 2.6174551386623165e-05, "epoch": 0.5236541598694943, "percentage": 5.24, "elapsed_time": "0:26:18", "remaining_time": "7:56:03", "throughput": 4403.19, "total_tokens": 6950016} {"current_steps": 3215, "total_steps": 61300, "loss": 0.3972, "lr": 2.6215334420880916e-05, "epoch": 0.5244698205546493, "percentage": 5.24, "elapsed_time": "0:26:20", "remaining_time": "7:56:01", "throughput": 4403.48, "total_tokens": 6961280} {"current_steps": 3220, "total_steps": 61300, "loss": 0.3972, "lr": 2.6256117455138664e-05, "epoch": 0.5252854812398042, "percentage": 5.25, "elapsed_time": "0:26:22", "remaining_time": "7:55:51", "throughput": 4404.08, "total_tokens": 6971360} {"current_steps": 3225, "total_steps": 61300, "loss": 0.4563, "lr": 2.6296900489396415e-05, "epoch": 0.5261011419249593, "percentage": 5.26, "elapsed_time": "0:26:25", "remaining_time": "7:55:47", "throughput": 4404.63, "total_tokens": 6982528} {"current_steps": 3230, "total_steps": 61300, "loss": 0.4278, "lr": 2.633768352365416e-05, "epoch": 0.5269168026101142, "percentage": 5.27, "elapsed_time": "0:26:27", "remaining_time": "7:55:38", "throughput": 4405.14, "total_tokens": 6992704} {"current_steps": 3235, "total_steps": 61300, "loss": 0.398, "lr": 2.6378466557911907e-05, "epoch": 0.5277324632952691, "percentage": 5.28, "elapsed_time": "0:26:29", "remaining_time": "7:55:31", "throughput": 4405.61, "total_tokens": 7003072} {"current_steps": 3240, "total_steps": 61300, "loss": 0.418, "lr": 2.6419249592169658e-05, "epoch": 0.5285481239804242, "percentage": 5.29, "elapsed_time": "0:26:31", "remaining_time": "7:55:24", "throughput": 4406.16, "total_tokens": 7013728} {"current_steps": 3245, "total_steps": 61300, "loss": 0.3744, "lr": 2.6460032626427406e-05, "epoch": 0.5293637846655791, "percentage": 5.29, "elapsed_time": "0:26:33", "remaining_time": "7:55:17", "throughput": 4406.76, "total_tokens": 7024256} {"current_steps": 3250, "total_steps": 61300, "loss": 0.3456, "lr": 2.6500815660685157e-05, "epoch": 0.5301794453507341, "percentage": 5.3, "elapsed_time": "0:26:36", "remaining_time": "7:55:09", "throughput": 4407.37, "total_tokens": 7034688} {"current_steps": 3255, "total_steps": 61300, "loss": 0.5879, "lr": 2.6541598694942904e-05, "epoch": 0.5309951060358891, "percentage": 5.31, "elapsed_time": "0:26:38", "remaining_time": "7:55:04", "throughput": 4408.01, "total_tokens": 7046080} {"current_steps": 3260, "total_steps": 61300, "loss": 0.4873, "lr": 2.6582381729200655e-05, "epoch": 0.531810766721044, "percentage": 5.32, "elapsed_time": "0:26:40", "remaining_time": "7:54:55", "throughput": 4408.54, "total_tokens": 7056032} {"current_steps": 3265, "total_steps": 61300, "loss": 0.4264, "lr": 2.6623164763458403e-05, "epoch": 0.532626427406199, "percentage": 5.33, "elapsed_time": "0:26:42", "remaining_time": "7:54:49", "throughput": 4409.06, "total_tokens": 7066880} {"current_steps": 3270, "total_steps": 61300, "loss": 0.3788, "lr": 2.666394779771615e-05, "epoch": 0.533442088091354, "percentage": 5.33, "elapsed_time": "0:26:45", "remaining_time": "7:54:43", "throughput": 4409.6, "total_tokens": 7077664} {"current_steps": 3275, "total_steps": 61300, "loss": 0.4282, "lr": 2.67047308319739e-05, "epoch": 0.534257748776509, "percentage": 5.34, "elapsed_time": "0:26:47", "remaining_time": "7:54:39", "throughput": 4410.21, "total_tokens": 7088928} {"current_steps": 3280, "total_steps": 61300, "loss": 0.4151, "lr": 2.6745513866231646e-05, "epoch": 0.5350734094616639, "percentage": 5.35, "elapsed_time": "0:26:49", "remaining_time": "7:54:36", "throughput": 4410.93, "total_tokens": 7100800} {"current_steps": 3285, "total_steps": 61300, "loss": 0.432, "lr": 2.67862969004894e-05, "epoch": 0.535889070146819, "percentage": 5.36, "elapsed_time": "0:26:52", "remaining_time": "7:54:31", "throughput": 4411.61, "total_tokens": 7112160} {"current_steps": 3290, "total_steps": 61300, "loss": 0.3552, "lr": 2.6827079934747145e-05, "epoch": 0.5367047308319739, "percentage": 5.37, "elapsed_time": "0:26:54", "remaining_time": "7:54:24", "throughput": 4412.17, "total_tokens": 7122848} {"current_steps": 3295, "total_steps": 61300, "loss": 0.3828, "lr": 2.68678629690049e-05, "epoch": 0.5375203915171288, "percentage": 5.38, "elapsed_time": "0:26:56", "remaining_time": "7:54:15", "throughput": 4412.67, "total_tokens": 7132800} {"current_steps": 3300, "total_steps": 61300, "loss": 0.397, "lr": 2.6908646003262643e-05, "epoch": 0.5383360522022839, "percentage": 5.38, "elapsed_time": "0:26:58", "remaining_time": "7:54:11", "throughput": 4413.26, "total_tokens": 7144064} {"current_steps": 3305, "total_steps": 61300, "loss": 0.422, "lr": 2.694942903752039e-05, "epoch": 0.5391517128874388, "percentage": 5.39, "elapsed_time": "0:27:01", "remaining_time": "7:54:08", "throughput": 4413.81, "total_tokens": 7155744} {"current_steps": 3310, "total_steps": 61300, "loss": 0.3686, "lr": 2.6990212071778142e-05, "epoch": 0.5399673735725938, "percentage": 5.4, "elapsed_time": "0:27:03", "remaining_time": "7:54:01", "throughput": 4414.33, "total_tokens": 7166336} {"current_steps": 3315, "total_steps": 61300, "loss": 0.3446, "lr": 2.703099510603589e-05, "epoch": 0.5407830342577488, "percentage": 5.41, "elapsed_time": "0:27:05", "remaining_time": "7:53:54", "throughput": 4414.89, "total_tokens": 7176832} {"current_steps": 3320, "total_steps": 61300, "loss": 0.3636, "lr": 2.707177814029364e-05, "epoch": 0.5415986949429038, "percentage": 5.42, "elapsed_time": "0:27:07", "remaining_time": "7:53:48", "throughput": 4415.38, "total_tokens": 7187616} {"current_steps": 3325, "total_steps": 61300, "loss": 0.4492, "lr": 2.7112561174551388e-05, "epoch": 0.5424143556280587, "percentage": 5.42, "elapsed_time": "0:27:10", "remaining_time": "7:53:41", "throughput": 4415.95, "total_tokens": 7198144} {"current_steps": 3330, "total_steps": 61300, "loss": 0.5247, "lr": 2.715334420880914e-05, "epoch": 0.5432300163132137, "percentage": 5.43, "elapsed_time": "0:27:12", "remaining_time": "7:53:35", "throughput": 4416.51, "total_tokens": 7208960} {"current_steps": 3335, "total_steps": 61300, "loss": 0.4305, "lr": 2.7194127243066887e-05, "epoch": 0.5440456769983687, "percentage": 5.44, "elapsed_time": "0:27:14", "remaining_time": "7:53:30", "throughput": 4417.04, "total_tokens": 7220064} {"current_steps": 3340, "total_steps": 61300, "loss": 0.402, "lr": 2.723491027732463e-05, "epoch": 0.5448613376835236, "percentage": 5.45, "elapsed_time": "0:27:16", "remaining_time": "7:53:24", "throughput": 4417.72, "total_tokens": 7231008} {"current_steps": 3345, "total_steps": 61300, "loss": 0.4229, "lr": 2.7275693311582386e-05, "epoch": 0.5456769983686787, "percentage": 5.46, "elapsed_time": "0:27:19", "remaining_time": "7:53:18", "throughput": 4418.41, "total_tokens": 7242144} {"current_steps": 3350, "total_steps": 61300, "loss": 0.416, "lr": 2.731647634584013e-05, "epoch": 0.5464926590538336, "percentage": 5.46, "elapsed_time": "0:27:21", "remaining_time": "7:53:10", "throughput": 4418.89, "total_tokens": 7252448} {"current_steps": 3355, "total_steps": 61300, "loss": 0.4449, "lr": 2.7357259380097884e-05, "epoch": 0.5473083197389886, "percentage": 5.47, "elapsed_time": "0:27:23", "remaining_time": "7:53:00", "throughput": 4419.31, "total_tokens": 7261856} {"current_steps": 3360, "total_steps": 61300, "loss": 0.3911, "lr": 2.739804241435563e-05, "epoch": 0.5481239804241436, "percentage": 5.48, "elapsed_time": "0:27:25", "remaining_time": "7:52:55", "throughput": 4419.67, "total_tokens": 7272800} {"current_steps": 3365, "total_steps": 61300, "loss": 0.3793, "lr": 2.7438825448613376e-05, "epoch": 0.5489396411092985, "percentage": 5.49, "elapsed_time": "0:27:27", "remaining_time": "7:52:50", "throughput": 4420.21, "total_tokens": 7283808} {"current_steps": 3370, "total_steps": 61300, "loss": 0.3808, "lr": 2.7479608482871127e-05, "epoch": 0.5497553017944535, "percentage": 5.5, "elapsed_time": "0:27:30", "remaining_time": "7:52:45", "throughput": 4420.84, "total_tokens": 7294976} {"current_steps": 3375, "total_steps": 61300, "loss": 0.3941, "lr": 2.7520391517128875e-05, "epoch": 0.5505709624796085, "percentage": 5.51, "elapsed_time": "0:27:32", "remaining_time": "7:52:43", "throughput": 4421.33, "total_tokens": 7306560} {"current_steps": 3380, "total_steps": 61300, "loss": 0.3893, "lr": 2.7561174551386626e-05, "epoch": 0.5513866231647635, "percentage": 5.51, "elapsed_time": "0:27:34", "remaining_time": "7:52:37", "throughput": 4421.88, "total_tokens": 7317600} {"current_steps": 3385, "total_steps": 61300, "loss": 0.5208, "lr": 2.7601957585644373e-05, "epoch": 0.5522022838499184, "percentage": 5.52, "elapsed_time": "0:27:37", "remaining_time": "7:52:37", "throughput": 4422.53, "total_tokens": 7330144} {"current_steps": 3390, "total_steps": 61300, "loss": 0.4334, "lr": 2.7642740619902125e-05, "epoch": 0.5530179445350734, "percentage": 5.53, "elapsed_time": "0:27:39", "remaining_time": "7:52:32", "throughput": 4423.08, "total_tokens": 7341248} {"current_steps": 3395, "total_steps": 61300, "loss": 0.4216, "lr": 2.7683523654159872e-05, "epoch": 0.5538336052202284, "percentage": 5.54, "elapsed_time": "0:27:41", "remaining_time": "7:52:24", "throughput": 4423.53, "total_tokens": 7351200} {"current_steps": 3400, "total_steps": 61300, "loss": 0.41, "lr": 2.7724306688417616e-05, "epoch": 0.5546492659053833, "percentage": 5.55, "elapsed_time": "0:27:44", "remaining_time": "7:52:17", "throughput": 4424.03, "total_tokens": 7361792} {"current_steps": 3405, "total_steps": 61300, "loss": 0.4097, "lr": 2.776508972267537e-05, "epoch": 0.5554649265905384, "percentage": 5.55, "elapsed_time": "0:27:46", "remaining_time": "7:52:09", "throughput": 4424.6, "total_tokens": 7372160} {"current_steps": 3410, "total_steps": 61300, "loss": 0.3334, "lr": 2.7805872756933115e-05, "epoch": 0.5562805872756933, "percentage": 5.56, "elapsed_time": "0:27:48", "remaining_time": "7:51:58", "throughput": 4424.98, "total_tokens": 7381408} {"current_steps": 3415, "total_steps": 61300, "loss": 0.4162, "lr": 2.7846655791190866e-05, "epoch": 0.5570962479608483, "percentage": 5.57, "elapsed_time": "0:27:50", "remaining_time": "7:51:54", "throughput": 4425.53, "total_tokens": 7392512} {"current_steps": 3420, "total_steps": 61300, "loss": 0.387, "lr": 2.7887438825448614e-05, "epoch": 0.5579119086460033, "percentage": 5.58, "elapsed_time": "0:27:52", "remaining_time": "7:51:51", "throughput": 4426.14, "total_tokens": 7404192} {"current_steps": 3425, "total_steps": 61300, "loss": 0.4082, "lr": 2.7928221859706365e-05, "epoch": 0.5587275693311582, "percentage": 5.59, "elapsed_time": "0:27:55", "remaining_time": "7:51:45", "throughput": 4426.63, "total_tokens": 7415008} {"current_steps": 3430, "total_steps": 61300, "loss": 0.3768, "lr": 2.7969004893964112e-05, "epoch": 0.5595432300163132, "percentage": 5.6, "elapsed_time": "0:27:57", "remaining_time": "7:51:36", "throughput": 4427.15, "total_tokens": 7425088} {"current_steps": 3435, "total_steps": 61300, "loss": 0.4043, "lr": 2.800978792822186e-05, "epoch": 0.5603588907014682, "percentage": 5.6, "elapsed_time": "0:27:59", "remaining_time": "7:51:33", "throughput": 4427.74, "total_tokens": 7436608} {"current_steps": 3440, "total_steps": 61300, "loss": 0.353, "lr": 2.805057096247961e-05, "epoch": 0.5611745513866232, "percentage": 5.61, "elapsed_time": "0:28:01", "remaining_time": "7:51:25", "throughput": 4428.22, "total_tokens": 7446784} {"current_steps": 3445, "total_steps": 61300, "loss": 0.338, "lr": 2.809135399673736e-05, "epoch": 0.5619902120717781, "percentage": 5.62, "elapsed_time": "0:28:03", "remaining_time": "7:51:15", "throughput": 4428.74, "total_tokens": 7456640} {"current_steps": 3450, "total_steps": 61300, "loss": 0.4296, "lr": 2.813213703099511e-05, "epoch": 0.5628058727569332, "percentage": 5.63, "elapsed_time": "0:28:06", "remaining_time": "7:51:12", "throughput": 4429.3, "total_tokens": 7468096} {"current_steps": 3455, "total_steps": 61300, "loss": 0.4008, "lr": 2.8172920065252857e-05, "epoch": 0.5636215334420881, "percentage": 5.64, "elapsed_time": "0:28:08", "remaining_time": "7:51:10", "throughput": 4429.95, "total_tokens": 7480096} {"current_steps": 3460, "total_steps": 61300, "loss": 0.4405, "lr": 2.8213703099510602e-05, "epoch": 0.564437194127243, "percentage": 5.64, "elapsed_time": "0:28:10", "remaining_time": "7:51:04", "throughput": 4430.54, "total_tokens": 7491136} {"current_steps": 3465, "total_steps": 61300, "loss": 0.3723, "lr": 2.8254486133768353e-05, "epoch": 0.5652528548123981, "percentage": 5.65, "elapsed_time": "0:28:13", "remaining_time": "7:51:00", "throughput": 4431.05, "total_tokens": 7502304} {"current_steps": 3470, "total_steps": 61300, "loss": 0.3839, "lr": 2.82952691680261e-05, "epoch": 0.566068515497553, "percentage": 5.66, "elapsed_time": "0:28:15", "remaining_time": "7:50:53", "throughput": 4431.55, "total_tokens": 7512928} {"current_steps": 3475, "total_steps": 61300, "loss": 0.361, "lr": 2.833605220228385e-05, "epoch": 0.566884176182708, "percentage": 5.67, "elapsed_time": "0:28:17", "remaining_time": "7:50:48", "throughput": 4432.14, "total_tokens": 7523904} {"current_steps": 3480, "total_steps": 61300, "loss": 0.3726, "lr": 2.83768352365416e-05, "epoch": 0.567699836867863, "percentage": 5.68, "elapsed_time": "0:28:19", "remaining_time": "7:50:41", "throughput": 4432.6, "total_tokens": 7534496} {"current_steps": 3485, "total_steps": 61300, "loss": 0.391, "lr": 2.841761827079935e-05, "epoch": 0.5685154975530179, "percentage": 5.69, "elapsed_time": "0:28:21", "remaining_time": "7:50:35", "throughput": 4433.12, "total_tokens": 7545120} {"current_steps": 3490, "total_steps": 61300, "loss": 0.4055, "lr": 2.8458401305057098e-05, "epoch": 0.5693311582381729, "percentage": 5.69, "elapsed_time": "0:28:24", "remaining_time": "7:50:29", "throughput": 4433.56, "total_tokens": 7555712} {"current_steps": 3495, "total_steps": 61300, "loss": 0.4491, "lr": 2.8499184339314845e-05, "epoch": 0.5701468189233279, "percentage": 5.7, "elapsed_time": "0:28:26", "remaining_time": "7:50:26", "throughput": 4434.04, "total_tokens": 7567200} {"current_steps": 3500, "total_steps": 61300, "loss": 0.4328, "lr": 2.8539967373572596e-05, "epoch": 0.5709624796084829, "percentage": 5.71, "elapsed_time": "0:28:28", "remaining_time": "7:50:22", "throughput": 4434.5, "total_tokens": 7578464} {"current_steps": 3505, "total_steps": 61300, "loss": 0.3543, "lr": 2.858075040783034e-05, "epoch": 0.5717781402936378, "percentage": 5.72, "elapsed_time": "0:28:31", "remaining_time": "7:50:13", "throughput": 4434.91, "total_tokens": 7588256} {"current_steps": 3510, "total_steps": 61300, "loss": 0.397, "lr": 2.8621533442088095e-05, "epoch": 0.5725938009787929, "percentage": 5.73, "elapsed_time": "0:28:33", "remaining_time": "7:50:07", "throughput": 4435.42, "total_tokens": 7598848} {"current_steps": 3515, "total_steps": 61300, "loss": 0.3947, "lr": 2.866231647634584e-05, "epoch": 0.5734094616639478, "percentage": 5.73, "elapsed_time": "0:28:35", "remaining_time": "7:50:01", "throughput": 4435.96, "total_tokens": 7609696} {"current_steps": 3520, "total_steps": 61300, "loss": 0.4691, "lr": 2.8703099510603594e-05, "epoch": 0.5742251223491027, "percentage": 5.74, "elapsed_time": "0:28:37", "remaining_time": "7:49:57", "throughput": 4436.44, "total_tokens": 7620864} {"current_steps": 3525, "total_steps": 61300, "loss": 0.3809, "lr": 2.8743882544861338e-05, "epoch": 0.5750407830342578, "percentage": 5.75, "elapsed_time": "0:28:39", "remaining_time": "7:49:49", "throughput": 4437.01, "total_tokens": 7631392} {"current_steps": 3530, "total_steps": 61300, "loss": 0.3909, "lr": 2.8784665579119086e-05, "epoch": 0.5758564437194127, "percentage": 5.76, "elapsed_time": "0:28:42", "remaining_time": "7:49:47", "throughput": 4437.65, "total_tokens": 7643232} {"current_steps": 3535, "total_steps": 61300, "loss": 0.3625, "lr": 2.8825448613376837e-05, "epoch": 0.5766721044045677, "percentage": 5.77, "elapsed_time": "0:28:44", "remaining_time": "7:49:44", "throughput": 4438.21, "total_tokens": 7654944} {"current_steps": 3540, "total_steps": 61300, "loss": 0.4184, "lr": 2.8866231647634584e-05, "epoch": 0.5774877650897227, "percentage": 5.77, "elapsed_time": "0:28:47", "remaining_time": "7:49:38", "throughput": 4438.71, "total_tokens": 7665760} {"current_steps": 3545, "total_steps": 61300, "loss": 0.3647, "lr": 2.8907014681892335e-05, "epoch": 0.5783034257748777, "percentage": 5.78, "elapsed_time": "0:28:49", "remaining_time": "7:49:33", "throughput": 4439.17, "total_tokens": 7676576} {"current_steps": 3550, "total_steps": 61300, "loss": 0.4173, "lr": 2.8947797716150083e-05, "epoch": 0.5791190864600326, "percentage": 5.79, "elapsed_time": "0:28:51", "remaining_time": "7:49:27", "throughput": 4439.53, "total_tokens": 7687104} {"current_steps": 3555, "total_steps": 61300, "loss": 0.3258, "lr": 2.8988580750407834e-05, "epoch": 0.5799347471451876, "percentage": 5.8, "elapsed_time": "0:28:53", "remaining_time": "7:49:22", "throughput": 4440.03, "total_tokens": 7698080} {"current_steps": 3560, "total_steps": 61300, "loss": 0.4355, "lr": 2.9029363784665582e-05, "epoch": 0.5807504078303426, "percentage": 5.81, "elapsed_time": "0:28:56", "remaining_time": "7:49:19", "throughput": 4440.56, "total_tokens": 7709632} {"current_steps": 3565, "total_steps": 61300, "loss": 0.4053, "lr": 2.9070146818923326e-05, "epoch": 0.5815660685154975, "percentage": 5.82, "elapsed_time": "0:28:58", "remaining_time": "7:49:12", "throughput": 4441.0, "total_tokens": 7719936} {"current_steps": 3570, "total_steps": 61300, "loss": 0.3854, "lr": 2.911092985318108e-05, "epoch": 0.5823817292006526, "percentage": 5.82, "elapsed_time": "0:29:00", "remaining_time": "7:49:03", "throughput": 4441.53, "total_tokens": 7730080} {"current_steps": 3575, "total_steps": 61300, "loss": 0.3803, "lr": 2.9151712887438825e-05, "epoch": 0.5831973898858075, "percentage": 5.83, "elapsed_time": "0:29:02", "remaining_time": "7:48:57", "throughput": 4442.0, "total_tokens": 7740576} {"current_steps": 3580, "total_steps": 61300, "loss": 0.3837, "lr": 2.919249592169658e-05, "epoch": 0.5840130505709625, "percentage": 5.84, "elapsed_time": "0:29:04", "remaining_time": "7:48:50", "throughput": 4442.46, "total_tokens": 7751040} {"current_steps": 3585, "total_steps": 61300, "loss": 0.3847, "lr": 2.9233278955954323e-05, "epoch": 0.5848287112561175, "percentage": 5.85, "elapsed_time": "0:29:06", "remaining_time": "7:48:42", "throughput": 4442.81, "total_tokens": 7760768} {"current_steps": 3590, "total_steps": 61300, "loss": 0.3821, "lr": 2.927406199021207e-05, "epoch": 0.5856443719412724, "percentage": 5.86, "elapsed_time": "0:29:09", "remaining_time": "7:48:36", "throughput": 4443.34, "total_tokens": 7771680} {"current_steps": 3595, "total_steps": 61300, "loss": 0.3341, "lr": 2.9314845024469822e-05, "epoch": 0.5864600326264274, "percentage": 5.86, "elapsed_time": "0:29:11", "remaining_time": "7:48:32", "throughput": 4443.89, "total_tokens": 7783072} {"current_steps": 3600, "total_steps": 61300, "loss": 0.3879, "lr": 2.935562805872757e-05, "epoch": 0.5872756933115824, "percentage": 5.87, "elapsed_time": "0:29:13", "remaining_time": "7:48:22", "throughput": 4444.32, "total_tokens": 7792608} {"current_steps": 3605, "total_steps": 61300, "loss": 0.4454, "lr": 2.939641109298532e-05, "epoch": 0.5880913539967374, "percentage": 5.88, "elapsed_time": "0:29:15", "remaining_time": "7:48:18", "throughput": 4444.85, "total_tokens": 7803744} {"current_steps": 3610, "total_steps": 61300, "loss": 0.4091, "lr": 2.943719412724307e-05, "epoch": 0.5889070146818923, "percentage": 5.89, "elapsed_time": "0:29:18", "remaining_time": "7:48:14", "throughput": 4445.27, "total_tokens": 7815008} {"current_steps": 3615, "total_steps": 61300, "loss": 0.3915, "lr": 2.947797716150082e-05, "epoch": 0.5897226753670473, "percentage": 5.9, "elapsed_time": "0:29:20", "remaining_time": "7:48:07", "throughput": 4445.79, "total_tokens": 7825536} {"current_steps": 3620, "total_steps": 61300, "loss": 0.3542, "lr": 2.9518760195758567e-05, "epoch": 0.5905383360522023, "percentage": 5.91, "elapsed_time": "0:29:22", "remaining_time": "7:48:01", "throughput": 4446.31, "total_tokens": 7836160} {"current_steps": 3625, "total_steps": 61300, "loss": 0.4143, "lr": 2.955954323001631e-05, "epoch": 0.5913539967373572, "percentage": 5.91, "elapsed_time": "0:29:25", "remaining_time": "7:48:01", "throughput": 4446.91, "total_tokens": 7848864} {"current_steps": 3630, "total_steps": 61300, "loss": 0.4011, "lr": 2.9600326264274066e-05, "epoch": 0.5921696574225123, "percentage": 5.92, "elapsed_time": "0:29:27", "remaining_time": "7:47:55", "throughput": 4447.44, "total_tokens": 7859488} {"current_steps": 3635, "total_steps": 61300, "loss": 0.3423, "lr": 2.964110929853181e-05, "epoch": 0.5929853181076672, "percentage": 5.93, "elapsed_time": "0:29:29", "remaining_time": "7:47:47", "throughput": 4447.85, "total_tokens": 7869600} {"current_steps": 3640, "total_steps": 61300, "loss": 0.3493, "lr": 2.968189233278956e-05, "epoch": 0.5938009787928222, "percentage": 5.94, "elapsed_time": "0:29:31", "remaining_time": "7:47:40", "throughput": 4448.28, "total_tokens": 7879840} {"current_steps": 3645, "total_steps": 61300, "loss": 0.3988, "lr": 2.972267536704731e-05, "epoch": 0.5946166394779772, "percentage": 5.95, "elapsed_time": "0:29:33", "remaining_time": "7:47:34", "throughput": 4448.65, "total_tokens": 7890272} {"current_steps": 3650, "total_steps": 61300, "loss": 0.3742, "lr": 2.976345840130506e-05, "epoch": 0.5954323001631321, "percentage": 5.95, "elapsed_time": "0:29:35", "remaining_time": "7:47:29", "throughput": 4449.14, "total_tokens": 7901120} {"current_steps": 3655, "total_steps": 61300, "loss": 0.4503, "lr": 2.9804241435562807e-05, "epoch": 0.5962479608482871, "percentage": 5.96, "elapsed_time": "0:29:38", "remaining_time": "7:47:25", "throughput": 4449.67, "total_tokens": 7912608} {"current_steps": 3660, "total_steps": 61300, "loss": 0.4004, "lr": 2.9845024469820555e-05, "epoch": 0.5970636215334421, "percentage": 5.97, "elapsed_time": "0:29:40", "remaining_time": "7:47:21", "throughput": 4450.24, "total_tokens": 7923936} {"current_steps": 3665, "total_steps": 61300, "loss": 0.4092, "lr": 2.9885807504078306e-05, "epoch": 0.5978792822185971, "percentage": 5.98, "elapsed_time": "0:29:42", "remaining_time": "7:47:15", "throughput": 4450.68, "total_tokens": 7934496} {"current_steps": 3670, "total_steps": 61300, "loss": 0.3709, "lr": 2.9926590538336054e-05, "epoch": 0.598694942903752, "percentage": 5.99, "elapsed_time": "0:29:45", "remaining_time": "7:47:11", "throughput": 4451.2, "total_tokens": 7945728} {"current_steps": 3675, "total_steps": 61300, "loss": 0.4144, "lr": 2.9967373572593805e-05, "epoch": 0.5995106035889071, "percentage": 6.0, "elapsed_time": "0:29:47", "remaining_time": "7:47:07", "throughput": 4451.68, "total_tokens": 7956960} {"current_steps": 3680, "total_steps": 61300, "loss": 0.4497, "lr": 3.0008156606851552e-05, "epoch": 0.600326264274062, "percentage": 6.0, "elapsed_time": "0:29:49", "remaining_time": "7:47:06", "throughput": 4452.28, "total_tokens": 7969440} {"current_steps": 3685, "total_steps": 61300, "loss": 0.3792, "lr": 3.0048939641109303e-05, "epoch": 0.6011419249592169, "percentage": 6.01, "elapsed_time": "0:29:51", "remaining_time": "7:46:55", "throughput": 4452.63, "total_tokens": 7978560} {"current_steps": 3690, "total_steps": 61300, "loss": 0.4405, "lr": 3.0089722675367048e-05, "epoch": 0.601957585644372, "percentage": 6.02, "elapsed_time": "0:29:54", "remaining_time": "7:46:53", "throughput": 4453.13, "total_tokens": 7990400} {"current_steps": 3695, "total_steps": 61300, "loss": 0.3674, "lr": 3.0130505709624795e-05, "epoch": 0.6027732463295269, "percentage": 6.03, "elapsed_time": "0:29:56", "remaining_time": "7:46:45", "throughput": 4453.49, "total_tokens": 8000128} {"current_steps": 3700, "total_steps": 61300, "loss": 0.4047, "lr": 3.0171288743882546e-05, "epoch": 0.6035889070146819, "percentage": 6.04, "elapsed_time": "0:29:58", "remaining_time": "7:46:38", "throughput": 4453.93, "total_tokens": 8010592} {"current_steps": 3705, "total_steps": 61300, "loss": 0.3867, "lr": 3.0212071778140294e-05, "epoch": 0.6044045676998369, "percentage": 6.04, "elapsed_time": "0:30:00", "remaining_time": "7:46:36", "throughput": 4454.34, "total_tokens": 8022240} {"current_steps": 3710, "total_steps": 61300, "loss": 0.386, "lr": 3.0252854812398045e-05, "epoch": 0.6052202283849919, "percentage": 6.05, "elapsed_time": "0:30:03", "remaining_time": "7:46:28", "throughput": 4454.73, "total_tokens": 8032096} {"current_steps": 3715, "total_steps": 61300, "loss": 0.3416, "lr": 3.0293637846655793e-05, "epoch": 0.6060358890701468, "percentage": 6.06, "elapsed_time": "0:30:05", "remaining_time": "7:46:21", "throughput": 4455.13, "total_tokens": 8042400} {"current_steps": 3720, "total_steps": 61300, "loss": 0.4344, "lr": 3.033442088091354e-05, "epoch": 0.6068515497553018, "percentage": 6.07, "elapsed_time": "0:30:07", "remaining_time": "7:46:15", "throughput": 4455.48, "total_tokens": 8052672} {"current_steps": 3725, "total_steps": 61300, "loss": 0.4168, "lr": 3.037520391517129e-05, "epoch": 0.6076672104404568, "percentage": 6.08, "elapsed_time": "0:30:09", "remaining_time": "7:46:10", "throughput": 4455.92, "total_tokens": 8063712} {"current_steps": 3730, "total_steps": 61300, "loss": 0.4077, "lr": 3.041598694942904e-05, "epoch": 0.6084828711256117, "percentage": 6.08, "elapsed_time": "0:30:11", "remaining_time": "7:46:02", "throughput": 4456.41, "total_tokens": 8073600} {"current_steps": 3735, "total_steps": 61300, "loss": 0.4063, "lr": 3.045676998368679e-05, "epoch": 0.6092985318107668, "percentage": 6.09, "elapsed_time": "0:30:14", "remaining_time": "7:45:59", "throughput": 4457.04, "total_tokens": 8085664} {"current_steps": 3740, "total_steps": 61300, "loss": 0.3712, "lr": 3.0497553017944534e-05, "epoch": 0.6101141924959217, "percentage": 6.1, "elapsed_time": "0:30:16", "remaining_time": "7:45:56", "throughput": 4457.54, "total_tokens": 8097152} {"current_steps": 3745, "total_steps": 61300, "loss": 0.4331, "lr": 3.0538336052202285e-05, "epoch": 0.6109298531810766, "percentage": 6.11, "elapsed_time": "0:30:18", "remaining_time": "7:45:51", "throughput": 4457.87, "total_tokens": 8107648} {"current_steps": 3750, "total_steps": 61300, "loss": 0.4027, "lr": 3.057911908646003e-05, "epoch": 0.6117455138662317, "percentage": 6.12, "elapsed_time": "0:30:20", "remaining_time": "7:45:45", "throughput": 4458.33, "total_tokens": 8118272} {"current_steps": 3755, "total_steps": 61300, "loss": 0.37, "lr": 3.061990212071778e-05, "epoch": 0.6125611745513866, "percentage": 6.13, "elapsed_time": "0:30:23", "remaining_time": "7:45:39", "throughput": 4458.81, "total_tokens": 8129120} {"current_steps": 3760, "total_steps": 61300, "loss": 0.4016, "lr": 3.0660685154975535e-05, "epoch": 0.6133768352365416, "percentage": 6.13, "elapsed_time": "0:30:25", "remaining_time": "7:45:31", "throughput": 4459.27, "total_tokens": 8139200} {"current_steps": 3765, "total_steps": 61300, "loss": 0.3811, "lr": 3.0701468189233276e-05, "epoch": 0.6141924959216966, "percentage": 6.14, "elapsed_time": "0:30:27", "remaining_time": "7:45:27", "throughput": 4459.72, "total_tokens": 8150272} {"current_steps": 3770, "total_steps": 61300, "loss": 0.4224, "lr": 3.074225122349103e-05, "epoch": 0.6150081566068516, "percentage": 6.15, "elapsed_time": "0:30:30", "remaining_time": "7:45:26", "throughput": 4460.24, "total_tokens": 8162496} {"current_steps": 3775, "total_steps": 61300, "loss": 0.3848, "lr": 3.078303425774878e-05, "epoch": 0.6158238172920065, "percentage": 6.16, "elapsed_time": "0:30:32", "remaining_time": "7:45:21", "throughput": 4460.79, "total_tokens": 8173664} {"current_steps": 3780, "total_steps": 61300, "loss": 0.3832, "lr": 3.082381729200653e-05, "epoch": 0.6166394779771615, "percentage": 6.17, "elapsed_time": "0:30:34", "remaining_time": "7:45:17", "throughput": 4461.19, "total_tokens": 8184512} {"current_steps": 3785, "total_steps": 61300, "loss": 0.4687, "lr": 3.086460032626427e-05, "epoch": 0.6174551386623165, "percentage": 6.17, "elapsed_time": "0:30:36", "remaining_time": "7:45:09", "throughput": 4461.59, "total_tokens": 8194432} {"current_steps": 3790, "total_steps": 61300, "loss": 0.3784, "lr": 3.090538336052202e-05, "epoch": 0.6182707993474714, "percentage": 6.18, "elapsed_time": "0:30:38", "remaining_time": "7:45:03", "throughput": 4462.04, "total_tokens": 8205152} {"current_steps": 3795, "total_steps": 61300, "loss": 0.3409, "lr": 3.0946166394779775e-05, "epoch": 0.6190864600326265, "percentage": 6.19, "elapsed_time": "0:30:41", "remaining_time": "7:44:56", "throughput": 4462.41, "total_tokens": 8215360} {"current_steps": 3800, "total_steps": 61300, "loss": 0.3721, "lr": 3.098694942903752e-05, "epoch": 0.6199021207177814, "percentage": 6.2, "elapsed_time": "0:30:43", "remaining_time": "7:44:48", "throughput": 4462.75, "total_tokens": 8225216} {"current_steps": 3805, "total_steps": 61300, "loss": 0.374, "lr": 3.102773246329527e-05, "epoch": 0.6207177814029364, "percentage": 6.21, "elapsed_time": "0:30:45", "remaining_time": "7:44:41", "throughput": 4463.15, "total_tokens": 8235488} {"current_steps": 3810, "total_steps": 61300, "loss": 0.3487, "lr": 3.106851549755302e-05, "epoch": 0.6215334420880914, "percentage": 6.22, "elapsed_time": "0:30:47", "remaining_time": "7:44:37", "throughput": 4463.47, "total_tokens": 8246208} {"current_steps": 3815, "total_steps": 61300, "loss": 0.3636, "lr": 3.1109298531810766e-05, "epoch": 0.6223491027732463, "percentage": 6.22, "elapsed_time": "0:30:49", "remaining_time": "7:44:34", "throughput": 4463.99, "total_tokens": 8258048} {"current_steps": 3820, "total_steps": 61300, "loss": 0.3756, "lr": 3.115008156606852e-05, "epoch": 0.6231647634584013, "percentage": 6.23, "elapsed_time": "0:30:52", "remaining_time": "7:44:31", "throughput": 4464.43, "total_tokens": 8269472} {"current_steps": 3825, "total_steps": 61300, "loss": 0.4228, "lr": 3.119086460032626e-05, "epoch": 0.6239804241435563, "percentage": 6.24, "elapsed_time": "0:30:54", "remaining_time": "7:44:27", "throughput": 4464.85, "total_tokens": 8280512} {"current_steps": 3830, "total_steps": 61300, "loss": 0.344, "lr": 3.1231647634584016e-05, "epoch": 0.6247960848287113, "percentage": 6.25, "elapsed_time": "0:30:56", "remaining_time": "7:44:22", "throughput": 4465.23, "total_tokens": 8291360} {"current_steps": 3835, "total_steps": 61300, "loss": 0.4159, "lr": 3.127243066884176e-05, "epoch": 0.6256117455138662, "percentage": 6.26, "elapsed_time": "0:30:58", "remaining_time": "7:44:15", "throughput": 4465.62, "total_tokens": 8301440} {"current_steps": 3840, "total_steps": 61300, "loss": 0.4311, "lr": 3.131321370309952e-05, "epoch": 0.6264274061990212, "percentage": 6.26, "elapsed_time": "0:31:01", "remaining_time": "7:44:13", "throughput": 4466.18, "total_tokens": 8313472} {"current_steps": 3845, "total_steps": 61300, "loss": 0.3625, "lr": 3.135399673735726e-05, "epoch": 0.6272430668841762, "percentage": 6.27, "elapsed_time": "0:31:03", "remaining_time": "7:44:05", "throughput": 4466.58, "total_tokens": 8323488} {"current_steps": 3850, "total_steps": 61300, "loss": 0.3542, "lr": 3.1394779771615006e-05, "epoch": 0.6280587275693311, "percentage": 6.28, "elapsed_time": "0:31:06", "remaining_time": "7:44:06", "throughput": 4467.05, "total_tokens": 8336096} {"current_steps": 3855, "total_steps": 61300, "loss": 0.375, "lr": 3.143556280587276e-05, "epoch": 0.6288743882544862, "percentage": 6.29, "elapsed_time": "0:31:07", "remaining_time": "7:43:55", "throughput": 4467.29, "total_tokens": 8344736} {"current_steps": 3860, "total_steps": 61300, "loss": 0.3436, "lr": 3.147634584013051e-05, "epoch": 0.6296900489396411, "percentage": 6.3, "elapsed_time": "0:31:10", "remaining_time": "7:43:52", "throughput": 4467.85, "total_tokens": 8356416} {"current_steps": 3865, "total_steps": 61300, "loss": 0.3309, "lr": 3.1517128874388256e-05, "epoch": 0.6305057096247961, "percentage": 6.31, "elapsed_time": "0:31:12", "remaining_time": "7:43:48", "throughput": 4468.3, "total_tokens": 8367712} {"current_steps": 3870, "total_steps": 61300, "loss": 0.3523, "lr": 3.1557911908646004e-05, "epoch": 0.6313213703099511, "percentage": 6.31, "elapsed_time": "0:31:14", "remaining_time": "7:43:44", "throughput": 4468.74, "total_tokens": 8378752} {"current_steps": 3875, "total_steps": 61300, "loss": 0.3775, "lr": 3.159869494290376e-05, "epoch": 0.632137030995106, "percentage": 6.32, "elapsed_time": "0:31:17", "remaining_time": "7:43:39", "throughput": 4469.12, "total_tokens": 8389472} {"current_steps": 3880, "total_steps": 61300, "loss": 0.3367, "lr": 3.1639477977161506e-05, "epoch": 0.632952691680261, "percentage": 6.33, "elapsed_time": "0:31:19", "remaining_time": "7:43:33", "throughput": 4469.45, "total_tokens": 8400064} {"current_steps": 3885, "total_steps": 61300, "loss": 0.3706, "lr": 3.1680261011419246e-05, "epoch": 0.633768352365416, "percentage": 6.34, "elapsed_time": "0:31:21", "remaining_time": "7:43:26", "throughput": 4469.88, "total_tokens": 8410176} {"current_steps": 3890, "total_steps": 61300, "loss": 0.3951, "lr": 3.1721044045677e-05, "epoch": 0.634584013050571, "percentage": 6.35, "elapsed_time": "0:31:23", "remaining_time": "7:43:18", "throughput": 4470.31, "total_tokens": 8420256} {"current_steps": 3895, "total_steps": 61300, "loss": 0.4606, "lr": 3.176182707993475e-05, "epoch": 0.6353996737357259, "percentage": 6.35, "elapsed_time": "0:31:26", "remaining_time": "7:43:16", "throughput": 4470.7, "total_tokens": 8431808} {"current_steps": 3900, "total_steps": 61300, "loss": 0.4294, "lr": 3.1802610114192496e-05, "epoch": 0.636215334420881, "percentage": 6.36, "elapsed_time": "0:31:28", "remaining_time": "7:43:15", "throughput": 4471.19, "total_tokens": 8444064} {"current_steps": 3905, "total_steps": 61300, "loss": 0.3663, "lr": 3.1843393148450244e-05, "epoch": 0.6370309951060359, "percentage": 6.37, "elapsed_time": "0:31:30", "remaining_time": "7:43:11", "throughput": 4471.51, "total_tokens": 8454944} {"current_steps": 3910, "total_steps": 61300, "loss": 0.3626, "lr": 3.1884176182708e-05, "epoch": 0.6378466557911908, "percentage": 6.38, "elapsed_time": "0:31:33", "remaining_time": "7:43:07", "throughput": 4471.96, "total_tokens": 8466208} {"current_steps": 3915, "total_steps": 61300, "loss": 0.4001, "lr": 3.1924959216965746e-05, "epoch": 0.6386623164763459, "percentage": 6.39, "elapsed_time": "0:31:35", "remaining_time": "7:43:00", "throughput": 4472.38, "total_tokens": 8476480} {"current_steps": 3920, "total_steps": 61300, "loss": 0.351, "lr": 3.1965742251223494e-05, "epoch": 0.6394779771615008, "percentage": 6.39, "elapsed_time": "0:31:37", "remaining_time": "7:42:54", "throughput": 4472.72, "total_tokens": 8486688} {"current_steps": 3925, "total_steps": 61300, "loss": 0.448, "lr": 3.200652528548124e-05, "epoch": 0.6402936378466558, "percentage": 6.4, "elapsed_time": "0:31:40", "remaining_time": "7:42:54", "throughput": 4473.2, "total_tokens": 8499200} {"current_steps": 3930, "total_steps": 61300, "loss": 0.3758, "lr": 3.204730831973899e-05, "epoch": 0.6411092985318108, "percentage": 6.41, "elapsed_time": "0:31:42", "remaining_time": "7:42:48", "throughput": 4473.66, "total_tokens": 8509728} {"current_steps": 3935, "total_steps": 61300, "loss": 0.3596, "lr": 3.208809135399674e-05, "epoch": 0.6419249592169658, "percentage": 6.42, "elapsed_time": "0:31:44", "remaining_time": "7:42:44", "throughput": 4474.1, "total_tokens": 8520928} {"current_steps": 3940, "total_steps": 61300, "loss": 0.3951, "lr": 3.2128874388254484e-05, "epoch": 0.6427406199021207, "percentage": 6.43, "elapsed_time": "0:31:46", "remaining_time": "7:42:41", "throughput": 4474.56, "total_tokens": 8532448} {"current_steps": 3945, "total_steps": 61300, "loss": 0.3619, "lr": 3.216965742251223e-05, "epoch": 0.6435562805872757, "percentage": 6.44, "elapsed_time": "0:31:49", "remaining_time": "7:42:36", "throughput": 4475.01, "total_tokens": 8543360} {"current_steps": 3950, "total_steps": 61300, "loss": 0.365, "lr": 3.2210440456769986e-05, "epoch": 0.6443719412724307, "percentage": 6.44, "elapsed_time": "0:31:51", "remaining_time": "7:42:30", "throughput": 4475.47, "total_tokens": 8554176} {"current_steps": 3955, "total_steps": 61300, "loss": 0.3852, "lr": 3.2251223491027734e-05, "epoch": 0.6451876019575856, "percentage": 6.45, "elapsed_time": "0:31:53", "remaining_time": "7:42:26", "throughput": 4475.96, "total_tokens": 8565376} {"current_steps": 3960, "total_steps": 61300, "loss": 0.3585, "lr": 3.229200652528548e-05, "epoch": 0.6460032626427407, "percentage": 6.46, "elapsed_time": "0:31:55", "remaining_time": "7:42:22", "throughput": 4476.39, "total_tokens": 8576480} {"current_steps": 3965, "total_steps": 61300, "loss": 0.3927, "lr": 3.233278955954323e-05, "epoch": 0.6468189233278956, "percentage": 6.47, "elapsed_time": "0:31:58", "remaining_time": "7:42:16", "throughput": 4476.8, "total_tokens": 8586944} {"current_steps": 3970, "total_steps": 61300, "loss": 0.3728, "lr": 3.2373572593800984e-05, "epoch": 0.6476345840130505, "percentage": 6.48, "elapsed_time": "0:32:00", "remaining_time": "7:42:08", "throughput": 4477.14, "total_tokens": 8596640} {"current_steps": 3975, "total_steps": 61300, "loss": 0.4371, "lr": 3.241435562805873e-05, "epoch": 0.6484502446982056, "percentage": 6.48, "elapsed_time": "0:32:02", "remaining_time": "7:42:05", "throughput": 4477.63, "total_tokens": 8608256} {"current_steps": 3980, "total_steps": 61300, "loss": 0.3783, "lr": 3.245513866231648e-05, "epoch": 0.6492659053833605, "percentage": 6.49, "elapsed_time": "0:32:04", "remaining_time": "7:41:58", "throughput": 4478.09, "total_tokens": 8618752} {"current_steps": 3985, "total_steps": 61300, "loss": 0.3626, "lr": 3.2495921696574226e-05, "epoch": 0.6500815660685155, "percentage": 6.5, "elapsed_time": "0:32:06", "remaining_time": "7:41:55", "throughput": 4478.41, "total_tokens": 8629824} {"current_steps": 3990, "total_steps": 61300, "loss": 0.3371, "lr": 3.2536704730831974e-05, "epoch": 0.6508972267536705, "percentage": 6.51, "elapsed_time": "0:32:09", "remaining_time": "7:41:50", "throughput": 4478.86, "total_tokens": 8640832} {"current_steps": 3995, "total_steps": 61300, "loss": 0.3824, "lr": 3.257748776508973e-05, "epoch": 0.6517128874388255, "percentage": 6.52, "elapsed_time": "0:32:11", "remaining_time": "7:41:44", "throughput": 4479.24, "total_tokens": 8651104} {"current_steps": 4000, "total_steps": 61300, "loss": 0.3814, "lr": 3.261827079934747e-05, "epoch": 0.6525285481239804, "percentage": 6.53, "elapsed_time": "0:32:13", "remaining_time": "7:41:40", "throughput": 4479.55, "total_tokens": 8662112} {"current_steps": 4005, "total_steps": 61300, "loss": 0.3252, "lr": 3.2659053833605224e-05, "epoch": 0.6533442088091354, "percentage": 6.53, "elapsed_time": "0:32:15", "remaining_time": "7:41:35", "throughput": 4479.91, "total_tokens": 8672960} {"current_steps": 4010, "total_steps": 61300, "loss": 0.4135, "lr": 3.269983686786297e-05, "epoch": 0.6541598694942904, "percentage": 6.54, "elapsed_time": "0:32:18", "remaining_time": "7:41:31", "throughput": 4480.36, "total_tokens": 8683968} {"current_steps": 4015, "total_steps": 61300, "loss": 0.3924, "lr": 3.274061990212072e-05, "epoch": 0.6549755301794453, "percentage": 6.55, "elapsed_time": "0:32:20", "remaining_time": "7:41:27", "throughput": 4480.78, "total_tokens": 8695200} {"current_steps": 4020, "total_steps": 61300, "loss": 0.3559, "lr": 3.278140293637847e-05, "epoch": 0.6557911908646004, "percentage": 6.56, "elapsed_time": "0:32:22", "remaining_time": "7:41:20", "throughput": 4481.14, "total_tokens": 8705408} {"current_steps": 4025, "total_steps": 61300, "loss": 0.3327, "lr": 3.2822185970636214e-05, "epoch": 0.6566068515497553, "percentage": 6.57, "elapsed_time": "0:32:24", "remaining_time": "7:41:15", "throughput": 4481.6, "total_tokens": 8716128} {"current_steps": 4030, "total_steps": 61300, "loss": 0.3754, "lr": 3.286296900489397e-05, "epoch": 0.6574225122349103, "percentage": 6.57, "elapsed_time": "0:32:27", "remaining_time": "7:41:12", "throughput": 4481.99, "total_tokens": 8727744} {"current_steps": 4035, "total_steps": 61300, "loss": 0.3916, "lr": 3.2903752039151716e-05, "epoch": 0.6582381729200653, "percentage": 6.58, "elapsed_time": "0:32:29", "remaining_time": "7:41:12", "throughput": 4482.39, "total_tokens": 8740128} {"current_steps": 4040, "total_steps": 61300, "loss": 0.4297, "lr": 3.2944535073409464e-05, "epoch": 0.6590538336052202, "percentage": 6.59, "elapsed_time": "0:32:32", "remaining_time": "7:41:11", "throughput": 4482.86, "total_tokens": 8752320} {"current_steps": 4045, "total_steps": 61300, "loss": 0.3788, "lr": 3.298531810766721e-05, "epoch": 0.6598694942903752, "percentage": 6.6, "elapsed_time": "0:32:34", "remaining_time": "7:41:06", "throughput": 4483.19, "total_tokens": 8762784} {"current_steps": 4050, "total_steps": 61300, "loss": 0.3414, "lr": 3.302610114192496e-05, "epoch": 0.6606851549755302, "percentage": 6.61, "elapsed_time": "0:32:36", "remaining_time": "7:41:00", "throughput": 4483.52, "total_tokens": 8773312} {"current_steps": 4055, "total_steps": 61300, "loss": 0.402, "lr": 3.3066884176182714e-05, "epoch": 0.6615008156606852, "percentage": 6.62, "elapsed_time": "0:32:38", "remaining_time": "7:40:54", "throughput": 4483.9, "total_tokens": 8783744} {"current_steps": 4060, "total_steps": 61300, "loss": 0.3891, "lr": 3.3107667210440455e-05, "epoch": 0.6623164763458401, "percentage": 6.62, "elapsed_time": "0:32:41", "remaining_time": "7:40:51", "throughput": 4484.32, "total_tokens": 8795104} {"current_steps": 4065, "total_steps": 61300, "loss": 0.3546, "lr": 3.314845024469821e-05, "epoch": 0.6631321370309952, "percentage": 6.63, "elapsed_time": "0:32:43", "remaining_time": "7:40:46", "throughput": 4484.7, "total_tokens": 8805760} {"current_steps": 4070, "total_steps": 61300, "loss": 0.3722, "lr": 3.318923327895596e-05, "epoch": 0.6639477977161501, "percentage": 6.64, "elapsed_time": "0:32:45", "remaining_time": "7:40:44", "throughput": 4485.04, "total_tokens": 8817536} {"current_steps": 4075, "total_steps": 61300, "loss": 0.3806, "lr": 3.3230016313213704e-05, "epoch": 0.664763458401305, "percentage": 6.65, "elapsed_time": "0:32:48", "remaining_time": "7:40:41", "throughput": 4485.53, "total_tokens": 8829184} {"current_steps": 4080, "total_steps": 61300, "loss": 0.4065, "lr": 3.327079934747145e-05, "epoch": 0.6655791190864601, "percentage": 6.66, "elapsed_time": "0:32:50", "remaining_time": "7:40:34", "throughput": 4485.89, "total_tokens": 8839328} {"current_steps": 4085, "total_steps": 61300, "loss": 0.3325, "lr": 3.33115823817292e-05, "epoch": 0.666394779771615, "percentage": 6.66, "elapsed_time": "0:32:52", "remaining_time": "7:40:30", "throughput": 4486.29, "total_tokens": 8850336} {"current_steps": 4090, "total_steps": 61300, "loss": 0.3764, "lr": 3.3352365415986954e-05, "epoch": 0.66721044045677, "percentage": 6.67, "elapsed_time": "0:32:54", "remaining_time": "7:40:21", "throughput": 4486.53, "total_tokens": 8859392} {"current_steps": 4095, "total_steps": 61300, "loss": 0.4067, "lr": 3.33931484502447e-05, "epoch": 0.668026101141925, "percentage": 6.68, "elapsed_time": "0:32:57", "remaining_time": "7:40:18", "throughput": 4486.9, "total_tokens": 8871008} {"current_steps": 4100, "total_steps": 61300, "loss": 0.3589, "lr": 3.343393148450245e-05, "epoch": 0.6688417618270799, "percentage": 6.69, "elapsed_time": "0:32:59", "remaining_time": "7:40:13", "throughput": 4487.27, "total_tokens": 8881760} {"current_steps": 4105, "total_steps": 61300, "loss": 0.4184, "lr": 3.34747145187602e-05, "epoch": 0.6696574225122349, "percentage": 6.7, "elapsed_time": "0:33:01", "remaining_time": "7:40:09", "throughput": 4487.61, "total_tokens": 8892544} {"current_steps": 4110, "total_steps": 61300, "loss": 0.3445, "lr": 3.3515497553017945e-05, "epoch": 0.6704730831973899, "percentage": 6.7, "elapsed_time": "0:33:03", "remaining_time": "7:40:06", "throughput": 4488.02, "total_tokens": 8903936} {"current_steps": 4115, "total_steps": 61300, "loss": 0.3421, "lr": 3.35562805872757e-05, "epoch": 0.6712887438825449, "percentage": 6.71, "elapsed_time": "0:33:05", "remaining_time": "7:39:58", "throughput": 4488.4, "total_tokens": 8913952} {"current_steps": 4120, "total_steps": 61300, "loss": 0.3979, "lr": 3.359706362153344e-05, "epoch": 0.6721044045676998, "percentage": 6.72, "elapsed_time": "0:33:08", "remaining_time": "7:39:54", "throughput": 4488.87, "total_tokens": 8925120} {"current_steps": 4125, "total_steps": 61300, "loss": 0.366, "lr": 3.3637846655791194e-05, "epoch": 0.6729200652528549, "percentage": 6.73, "elapsed_time": "0:33:10", "remaining_time": "7:39:49", "throughput": 4489.21, "total_tokens": 8935872} {"current_steps": 4130, "total_steps": 61300, "loss": 0.3736, "lr": 3.367862969004894e-05, "epoch": 0.6737357259380098, "percentage": 6.74, "elapsed_time": "0:33:12", "remaining_time": "7:39:44", "throughput": 4489.61, "total_tokens": 8946624} {"current_steps": 4135, "total_steps": 61300, "loss": 0.3222, "lr": 3.371941272430669e-05, "epoch": 0.6745513866231647, "percentage": 6.75, "elapsed_time": "0:33:14", "remaining_time": "7:39:39", "throughput": 4490.05, "total_tokens": 8957568} {"current_steps": 4140, "total_steps": 61300, "loss": 0.2687, "lr": 3.376019575856444e-05, "epoch": 0.6753670473083198, "percentage": 6.75, "elapsed_time": "0:33:17", "remaining_time": "7:39:34", "throughput": 4490.39, "total_tokens": 8968160} {"current_steps": 4145, "total_steps": 61300, "loss": 0.3465, "lr": 3.3800978792822185e-05, "epoch": 0.6761827079934747, "percentage": 6.76, "elapsed_time": "0:33:19", "remaining_time": "7:39:28", "throughput": 4490.76, "total_tokens": 8978560} {"current_steps": 4150, "total_steps": 61300, "loss": 0.4102, "lr": 3.384176182707994e-05, "epoch": 0.6769983686786297, "percentage": 6.77, "elapsed_time": "0:33:21", "remaining_time": "7:39:22", "throughput": 4491.11, "total_tokens": 8988896} {"current_steps": 4155, "total_steps": 61300, "loss": 0.3678, "lr": 3.388254486133769e-05, "epoch": 0.6778140293637847, "percentage": 6.78, "elapsed_time": "0:33:23", "remaining_time": "7:39:20", "throughput": 4491.59, "total_tokens": 9000928} {"current_steps": 4160, "total_steps": 61300, "loss": 0.3233, "lr": 3.3923327895595435e-05, "epoch": 0.6786296900489397, "percentage": 6.79, "elapsed_time": "0:33:26", "remaining_time": "7:39:16", "throughput": 4491.88, "total_tokens": 9011712} {"current_steps": 4165, "total_steps": 61300, "loss": 0.2831, "lr": 3.396411092985318e-05, "epoch": 0.6794453507340946, "percentage": 6.79, "elapsed_time": "0:33:28", "remaining_time": "7:39:12", "throughput": 4492.22, "total_tokens": 9022624} {"current_steps": 4170, "total_steps": 61300, "loss": 0.46, "lr": 3.400489396411093e-05, "epoch": 0.6802610114192496, "percentage": 6.8, "elapsed_time": "0:33:30", "remaining_time": "7:39:06", "throughput": 4492.58, "total_tokens": 9033088} {"current_steps": 4175, "total_steps": 61300, "loss": 0.3974, "lr": 3.404567699836868e-05, "epoch": 0.6810766721044046, "percentage": 6.81, "elapsed_time": "0:33:32", "remaining_time": "7:39:01", "throughput": 4492.88, "total_tokens": 9043680} {"current_steps": 4180, "total_steps": 61300, "loss": 0.3999, "lr": 3.4086460032626425e-05, "epoch": 0.6818923327895595, "percentage": 6.82, "elapsed_time": "0:33:35", "remaining_time": "7:38:59", "throughput": 4493.29, "total_tokens": 9055424} {"current_steps": 4185, "total_steps": 61300, "loss": 0.4128, "lr": 3.412724306688418e-05, "epoch": 0.6827079934747146, "percentage": 6.83, "elapsed_time": "0:33:37", "remaining_time": "7:38:57", "throughput": 4493.57, "total_tokens": 9066816} {"current_steps": 4190, "total_steps": 61300, "loss": 0.3597, "lr": 3.416802610114193e-05, "epoch": 0.6835236541598695, "percentage": 6.84, "elapsed_time": "0:33:39", "remaining_time": "7:38:52", "throughput": 4494.01, "total_tokens": 9077792} {"current_steps": 4195, "total_steps": 61300, "loss": 0.3822, "lr": 3.4208809135399675e-05, "epoch": 0.6843393148450244, "percentage": 6.84, "elapsed_time": "0:33:42", "remaining_time": "7:38:46", "throughput": 4494.32, "total_tokens": 9088160} {"current_steps": 4200, "total_steps": 61300, "loss": 0.3747, "lr": 3.424959216965742e-05, "epoch": 0.6851549755301795, "percentage": 6.85, "elapsed_time": "0:33:44", "remaining_time": "7:38:42", "throughput": 4494.69, "total_tokens": 9099264} {"current_steps": 4205, "total_steps": 61300, "loss": 0.4012, "lr": 3.429037520391517e-05, "epoch": 0.6859706362153344, "percentage": 6.86, "elapsed_time": "0:33:46", "remaining_time": "7:38:38", "throughput": 4495.1, "total_tokens": 9110336} {"current_steps": 4210, "total_steps": 61300, "loss": 0.361, "lr": 3.4331158238172925e-05, "epoch": 0.6867862969004894, "percentage": 6.87, "elapsed_time": "0:33:48", "remaining_time": "7:38:33", "throughput": 4495.52, "total_tokens": 9121248} {"current_steps": 4215, "total_steps": 61300, "loss": 0.3909, "lr": 3.4371941272430666e-05, "epoch": 0.6876019575856444, "percentage": 6.88, "elapsed_time": "0:33:51", "remaining_time": "7:38:31", "throughput": 4495.94, "total_tokens": 9132896} {"current_steps": 4220, "total_steps": 61300, "loss": 0.4054, "lr": 3.441272430668842e-05, "epoch": 0.6884176182707994, "percentage": 6.88, "elapsed_time": "0:33:53", "remaining_time": "7:38:27", "throughput": 4496.28, "total_tokens": 9143968} {"current_steps": 4225, "total_steps": 61300, "loss": 0.3578, "lr": 3.445350734094617e-05, "epoch": 0.6892332789559543, "percentage": 6.89, "elapsed_time": "0:33:55", "remaining_time": "7:38:23", "throughput": 4496.63, "total_tokens": 9154848} {"current_steps": 4230, "total_steps": 61300, "loss": 0.3527, "lr": 3.449429037520392e-05, "epoch": 0.6900489396411092, "percentage": 6.9, "elapsed_time": "0:33:58", "remaining_time": "7:38:23", "throughput": 4497.03, "total_tokens": 9167264} {"current_steps": 4235, "total_steps": 61300, "loss": 0.3762, "lr": 3.453507340946166e-05, "epoch": 0.6908646003262643, "percentage": 6.91, "elapsed_time": "0:34:00", "remaining_time": "7:38:17", "throughput": 4497.51, "total_tokens": 9178016} {"current_steps": 4240, "total_steps": 61300, "loss": 0.3826, "lr": 3.457585644371941e-05, "epoch": 0.6916802610114192, "percentage": 6.92, "elapsed_time": "0:34:02", "remaining_time": "7:38:11", "throughput": 4497.8, "total_tokens": 9188224} {"current_steps": 4245, "total_steps": 61300, "loss": 0.3854, "lr": 3.4616639477977165e-05, "epoch": 0.6924959216965743, "percentage": 6.92, "elapsed_time": "0:34:04", "remaining_time": "7:38:04", "throughput": 4498.11, "total_tokens": 9198208} {"current_steps": 4250, "total_steps": 61300, "loss": 0.3632, "lr": 3.465742251223491e-05, "epoch": 0.6933115823817292, "percentage": 6.93, "elapsed_time": "0:34:07", "remaining_time": "7:37:58", "throughput": 4498.34, "total_tokens": 9208128} {"current_steps": 4255, "total_steps": 61300, "loss": 0.3351, "lr": 3.469820554649266e-05, "epoch": 0.6941272430668842, "percentage": 6.94, "elapsed_time": "0:34:09", "remaining_time": "7:37:51", "throughput": 4498.63, "total_tokens": 9218080} {"current_steps": 4260, "total_steps": 61300, "loss": 0.3552, "lr": 3.473898858075041e-05, "epoch": 0.6949429037520392, "percentage": 6.95, "elapsed_time": "0:34:11", "remaining_time": "7:37:45", "throughput": 4498.9, "total_tokens": 9228416} {"current_steps": 4265, "total_steps": 61300, "loss": 0.313, "lr": 3.477977161500816e-05, "epoch": 0.6957585644371941, "percentage": 6.96, "elapsed_time": "0:34:13", "remaining_time": "7:37:41", "throughput": 4499.22, "total_tokens": 9239296} {"current_steps": 4270, "total_steps": 61300, "loss": 0.3529, "lr": 3.482055464926591e-05, "epoch": 0.6965742251223491, "percentage": 6.97, "elapsed_time": "0:34:15", "remaining_time": "7:37:35", "throughput": 4499.56, "total_tokens": 9249472} {"current_steps": 4275, "total_steps": 61300, "loss": 0.3864, "lr": 3.486133768352365e-05, "epoch": 0.697389885807504, "percentage": 6.97, "elapsed_time": "0:34:17", "remaining_time": "7:37:28", "throughput": 4499.91, "total_tokens": 9259616} {"current_steps": 4280, "total_steps": 61300, "loss": 0.3161, "lr": 3.4902120717781405e-05, "epoch": 0.6982055464926591, "percentage": 6.98, "elapsed_time": "0:34:20", "remaining_time": "7:37:26", "throughput": 4500.34, "total_tokens": 9271360} {"current_steps": 4285, "total_steps": 61300, "loss": 0.3903, "lr": 3.494290375203915e-05, "epoch": 0.699021207177814, "percentage": 6.99, "elapsed_time": "0:34:22", "remaining_time": "7:37:20", "throughput": 4500.7, "total_tokens": 9281952} {"current_steps": 4290, "total_steps": 61300, "loss": 0.3895, "lr": 3.498368678629691e-05, "epoch": 0.6998368678629691, "percentage": 7.0, "elapsed_time": "0:34:24", "remaining_time": "7:37:15", "throughput": 4501.0, "total_tokens": 9292480} {"current_steps": 4295, "total_steps": 61300, "loss": 0.3727, "lr": 3.502446982055465e-05, "epoch": 0.700652528548124, "percentage": 7.01, "elapsed_time": "0:34:26", "remaining_time": "7:37:06", "throughput": 4501.31, "total_tokens": 9301696} {"current_steps": 4300, "total_steps": 61300, "loss": 0.3464, "lr": 3.5065252854812396e-05, "epoch": 0.7014681892332789, "percentage": 7.01, "elapsed_time": "0:34:28", "remaining_time": "7:36:59", "throughput": 4501.56, "total_tokens": 9311360} {"current_steps": 4305, "total_steps": 61300, "loss": 0.3969, "lr": 3.510603588907015e-05, "epoch": 0.702283849918434, "percentage": 7.02, "elapsed_time": "0:34:30", "remaining_time": "7:36:52", "throughput": 4501.91, "total_tokens": 9321504} {"current_steps": 4310, "total_steps": 61300, "loss": 0.3846, "lr": 3.51468189233279e-05, "epoch": 0.7030995106035889, "percentage": 7.03, "elapsed_time": "0:34:32", "remaining_time": "7:36:50", "throughput": 4502.28, "total_tokens": 9333024} {"current_steps": 4315, "total_steps": 61300, "loss": 0.355, "lr": 3.5187601957585646e-05, "epoch": 0.7039151712887439, "percentage": 7.04, "elapsed_time": "0:34:35", "remaining_time": "7:36:44", "throughput": 4502.53, "total_tokens": 9343424} {"current_steps": 4320, "total_steps": 61300, "loss": 0.3691, "lr": 3.522838499184339e-05, "epoch": 0.7047308319738989, "percentage": 7.05, "elapsed_time": "0:34:37", "remaining_time": "7:36:39", "throughput": 4502.94, "total_tokens": 9354016} {"current_steps": 4325, "total_steps": 61300, "loss": 0.3796, "lr": 3.526916802610115e-05, "epoch": 0.7055464926590538, "percentage": 7.06, "elapsed_time": "0:34:39", "remaining_time": "7:36:37", "throughput": 4503.26, "total_tokens": 9365600} {"current_steps": 4330, "total_steps": 61300, "loss": 0.3851, "lr": 3.5309951060358895e-05, "epoch": 0.7063621533442088, "percentage": 7.06, "elapsed_time": "0:34:42", "remaining_time": "7:36:34", "throughput": 4503.63, "total_tokens": 9377216} {"current_steps": 4335, "total_steps": 61300, "loss": 0.3622, "lr": 3.5350734094616636e-05, "epoch": 0.7071778140293637, "percentage": 7.07, "elapsed_time": "0:34:44", "remaining_time": "7:36:30", "throughput": 4503.91, "total_tokens": 9388000} {"current_steps": 4340, "total_steps": 61300, "loss": 0.3613, "lr": 3.539151712887439e-05, "epoch": 0.7079934747145188, "percentage": 7.08, "elapsed_time": "0:34:46", "remaining_time": "7:36:28", "throughput": 4504.31, "total_tokens": 9399616} {"current_steps": 4345, "total_steps": 61300, "loss": 0.3701, "lr": 3.543230016313214e-05, "epoch": 0.7088091353996737, "percentage": 7.09, "elapsed_time": "0:34:49", "remaining_time": "7:36:27", "throughput": 4504.72, "total_tokens": 9411872} {"current_steps": 4350, "total_steps": 61300, "loss": 0.4004, "lr": 3.5473083197389886e-05, "epoch": 0.7096247960848288, "percentage": 7.1, "elapsed_time": "0:34:51", "remaining_time": "7:36:23", "throughput": 4505.04, "total_tokens": 9422912} {"current_steps": 4355, "total_steps": 61300, "loss": 0.4031, "lr": 3.5513866231647634e-05, "epoch": 0.7104404567699837, "percentage": 7.1, "elapsed_time": "0:34:53", "remaining_time": "7:36:20", "throughput": 4505.39, "total_tokens": 9434176} {"current_steps": 4360, "total_steps": 61300, "loss": 0.3967, "lr": 3.555464926590539e-05, "epoch": 0.7112561174551386, "percentage": 7.11, "elapsed_time": "0:34:55", "remaining_time": "7:36:12", "throughput": 4505.7, "total_tokens": 9443936} {"current_steps": 4365, "total_steps": 61300, "loss": 0.3683, "lr": 3.5595432300163136e-05, "epoch": 0.7120717781402937, "percentage": 7.12, "elapsed_time": "0:34:58", "remaining_time": "7:36:06", "throughput": 4505.99, "total_tokens": 9453984} {"current_steps": 4370, "total_steps": 61300, "loss": 0.3493, "lr": 3.563621533442088e-05, "epoch": 0.7128874388254486, "percentage": 7.13, "elapsed_time": "0:35:00", "remaining_time": "7:36:03", "throughput": 4506.38, "total_tokens": 9465408} {"current_steps": 4375, "total_steps": 61300, "loss": 0.4026, "lr": 3.567699836867863e-05, "epoch": 0.7137030995106036, "percentage": 7.14, "elapsed_time": "0:35:02", "remaining_time": "7:35:56", "throughput": 4506.73, "total_tokens": 9475392} {"current_steps": 4380, "total_steps": 61300, "loss": 0.3595, "lr": 3.571778140293638e-05, "epoch": 0.7145187601957586, "percentage": 7.15, "elapsed_time": "0:35:04", "remaining_time": "7:35:49", "throughput": 4507.02, "total_tokens": 9485280} {"current_steps": 4385, "total_steps": 61300, "loss": 0.2968, "lr": 3.575856443719413e-05, "epoch": 0.7153344208809136, "percentage": 7.15, "elapsed_time": "0:35:06", "remaining_time": "7:35:45", "throughput": 4507.34, "total_tokens": 9496224} {"current_steps": 4390, "total_steps": 61300, "loss": 0.401, "lr": 3.579934747145188e-05, "epoch": 0.7161500815660685, "percentage": 7.16, "elapsed_time": "0:35:09", "remaining_time": "7:35:42", "throughput": 4507.68, "total_tokens": 9507456} {"current_steps": 4395, "total_steps": 61300, "loss": 0.3428, "lr": 3.584013050570963e-05, "epoch": 0.7169657422512234, "percentage": 7.17, "elapsed_time": "0:35:11", "remaining_time": "7:35:37", "throughput": 4507.92, "total_tokens": 9517952} {"current_steps": 4400, "total_steps": 61300, "loss": 0.4112, "lr": 3.5880913539967376e-05, "epoch": 0.7177814029363785, "percentage": 7.18, "elapsed_time": "0:35:13", "remaining_time": "7:35:32", "throughput": 4508.24, "total_tokens": 9528672} {"current_steps": 4405, "total_steps": 61300, "loss": 0.3732, "lr": 3.5921696574225124e-05, "epoch": 0.7185970636215334, "percentage": 7.19, "elapsed_time": "0:35:15", "remaining_time": "7:35:28", "throughput": 4508.52, "total_tokens": 9539552} {"current_steps": 4410, "total_steps": 61300, "loss": 0.3964, "lr": 3.596247960848287e-05, "epoch": 0.7194127243066885, "percentage": 7.19, "elapsed_time": "0:35:18", "remaining_time": "7:35:23", "throughput": 4508.87, "total_tokens": 9550112} {"current_steps": 4415, "total_steps": 61300, "loss": 0.3497, "lr": 3.600326264274062e-05, "epoch": 0.7202283849918434, "percentage": 7.2, "elapsed_time": "0:35:20", "remaining_time": "7:35:18", "throughput": 4509.17, "total_tokens": 9560544} {"current_steps": 4420, "total_steps": 61300, "loss": 0.3709, "lr": 3.604404567699837e-05, "epoch": 0.7210440456769984, "percentage": 7.21, "elapsed_time": "0:35:22", "remaining_time": "7:35:13", "throughput": 4509.42, "total_tokens": 9571232} {"current_steps": 4425, "total_steps": 61300, "loss": 0.326, "lr": 3.608482871125612e-05, "epoch": 0.7218597063621534, "percentage": 7.22, "elapsed_time": "0:35:24", "remaining_time": "7:35:09", "throughput": 4509.69, "total_tokens": 9581920} {"current_steps": 4430, "total_steps": 61300, "loss": 0.3831, "lr": 3.612561174551387e-05, "epoch": 0.7226753670473083, "percentage": 7.23, "elapsed_time": "0:35:26", "remaining_time": "7:35:04", "throughput": 4509.96, "total_tokens": 9592448} {"current_steps": 4435, "total_steps": 61300, "loss": 0.4558, "lr": 3.6166394779771616e-05, "epoch": 0.7234910277324633, "percentage": 7.23, "elapsed_time": "0:35:29", "remaining_time": "7:35:00", "throughput": 4510.32, "total_tokens": 9603360} {"current_steps": 4440, "total_steps": 61300, "loss": 0.3456, "lr": 3.6207177814029364e-05, "epoch": 0.7243066884176182, "percentage": 7.24, "elapsed_time": "0:35:31", "remaining_time": "7:34:56", "throughput": 4510.63, "total_tokens": 9614336} {"current_steps": 4445, "total_steps": 61300, "loss": 0.3516, "lr": 3.624796084828712e-05, "epoch": 0.7251223491027733, "percentage": 7.25, "elapsed_time": "0:35:33", "remaining_time": "7:34:50", "throughput": 4510.88, "total_tokens": 9624512} {"current_steps": 4450, "total_steps": 61300, "loss": 0.3084, "lr": 3.628874388254486e-05, "epoch": 0.7259380097879282, "percentage": 7.26, "elapsed_time": "0:35:35", "remaining_time": "7:34:45", "throughput": 4511.26, "total_tokens": 9635168} {"current_steps": 4455, "total_steps": 61300, "loss": 0.4192, "lr": 3.6329526916802614e-05, "epoch": 0.7267536704730831, "percentage": 7.27, "elapsed_time": "0:35:37", "remaining_time": "7:34:39", "throughput": 4511.52, "total_tokens": 9645280} {"current_steps": 4460, "total_steps": 61300, "loss": 0.3632, "lr": 3.637030995106036e-05, "epoch": 0.7275693311582382, "percentage": 7.28, "elapsed_time": "0:35:40", "remaining_time": "7:34:34", "throughput": 4511.93, "total_tokens": 9656032} {"current_steps": 4465, "total_steps": 61300, "loss": 0.3485, "lr": 3.641109298531811e-05, "epoch": 0.7283849918433931, "percentage": 7.28, "elapsed_time": "0:35:42", "remaining_time": "7:34:32", "throughput": 4512.43, "total_tokens": 9667968} {"current_steps": 4470, "total_steps": 61300, "loss": 0.4168, "lr": 3.6451876019575856e-05, "epoch": 0.7292006525285482, "percentage": 7.29, "elapsed_time": "0:35:45", "remaining_time": "7:34:31", "throughput": 4512.78, "total_tokens": 9680032} {"current_steps": 4475, "total_steps": 61300, "loss": 0.3543, "lr": 3.6492659053833604e-05, "epoch": 0.7300163132137031, "percentage": 7.3, "elapsed_time": "0:35:47", "remaining_time": "7:34:28", "throughput": 4513.04, "total_tokens": 9691424} {"current_steps": 4480, "total_steps": 61300, "loss": 0.387, "lr": 3.653344208809136e-05, "epoch": 0.7308319738988581, "percentage": 7.31, "elapsed_time": "0:35:49", "remaining_time": "7:34:25", "throughput": 4513.32, "total_tokens": 9702400} {"current_steps": 4485, "total_steps": 61300, "loss": 0.3604, "lr": 3.6574225122349106e-05, "epoch": 0.731647634584013, "percentage": 7.32, "elapsed_time": "0:35:51", "remaining_time": "7:34:20", "throughput": 4513.61, "total_tokens": 9712928} {"current_steps": 4490, "total_steps": 61300, "loss": 0.3354, "lr": 3.6615008156606854e-05, "epoch": 0.732463295269168, "percentage": 7.32, "elapsed_time": "0:35:54", "remaining_time": "7:34:14", "throughput": 4513.97, "total_tokens": 9723360} {"current_steps": 4495, "total_steps": 61300, "loss": 0.3743, "lr": 3.66557911908646e-05, "epoch": 0.733278955954323, "percentage": 7.33, "elapsed_time": "0:35:56", "remaining_time": "7:34:11", "throughput": 4514.26, "total_tokens": 9734496} {"current_steps": 4500, "total_steps": 61300, "loss": 0.3274, "lr": 3.669657422512235e-05, "epoch": 0.734094616639478, "percentage": 7.34, "elapsed_time": "0:35:58", "remaining_time": "7:34:04", "throughput": 4514.48, "total_tokens": 9744288} {"current_steps": 4505, "total_steps": 61300, "loss": 0.3674, "lr": 3.6737357259380104e-05, "epoch": 0.734910277324633, "percentage": 7.35, "elapsed_time": "0:36:00", "remaining_time": "7:34:00", "throughput": 4514.72, "total_tokens": 9755072} {"current_steps": 4510, "total_steps": 61300, "loss": 0.3832, "lr": 3.6778140293637844e-05, "epoch": 0.7357259380097879, "percentage": 7.36, "elapsed_time": "0:36:02", "remaining_time": "7:33:51", "throughput": 4514.95, "total_tokens": 9764192} {"current_steps": 4515, "total_steps": 61300, "loss": 0.3873, "lr": 3.68189233278956e-05, "epoch": 0.736541598694943, "percentage": 7.37, "elapsed_time": "0:36:04", "remaining_time": "7:33:48", "throughput": 4515.33, "total_tokens": 9775392} {"current_steps": 4520, "total_steps": 61300, "loss": 0.3832, "lr": 3.6859706362153346e-05, "epoch": 0.7373572593800979, "percentage": 7.37, "elapsed_time": "0:36:06", "remaining_time": "7:33:40", "throughput": 4515.58, "total_tokens": 9784864} {"current_steps": 4525, "total_steps": 61300, "loss": 0.4442, "lr": 3.6900489396411094e-05, "epoch": 0.7381729200652528, "percentage": 7.38, "elapsed_time": "0:36:09", "remaining_time": "7:33:38", "throughput": 4515.93, "total_tokens": 9796512} {"current_steps": 4530, "total_steps": 61300, "loss": 0.3744, "lr": 3.694127243066884e-05, "epoch": 0.7389885807504079, "percentage": 7.39, "elapsed_time": "0:36:11", "remaining_time": "7:33:37", "throughput": 4516.24, "total_tokens": 9808416} {"current_steps": 4535, "total_steps": 61300, "loss": 0.3196, "lr": 3.698205546492659e-05, "epoch": 0.7398042414355628, "percentage": 7.4, "elapsed_time": "0:36:14", "remaining_time": "7:33:33", "throughput": 4516.58, "total_tokens": 9819552} {"current_steps": 4540, "total_steps": 61300, "loss": 0.3829, "lr": 3.7022838499184344e-05, "epoch": 0.7406199021207178, "percentage": 7.41, "elapsed_time": "0:36:16", "remaining_time": "7:33:30", "throughput": 4517.0, "total_tokens": 9831168} {"current_steps": 4545, "total_steps": 61300, "loss": 0.419, "lr": 3.706362153344209e-05, "epoch": 0.7414355628058727, "percentage": 7.41, "elapsed_time": "0:36:18", "remaining_time": "7:33:24", "throughput": 4517.39, "total_tokens": 9841280} {"current_steps": 4550, "total_steps": 61300, "loss": 0.3861, "lr": 3.710440456769984e-05, "epoch": 0.7422512234910277, "percentage": 7.42, "elapsed_time": "0:36:20", "remaining_time": "7:33:20", "throughput": 4517.62, "total_tokens": 9852224} {"current_steps": 4555, "total_steps": 61300, "loss": 0.3209, "lr": 3.714518760195759e-05, "epoch": 0.7430668841761827, "percentage": 7.43, "elapsed_time": "0:36:23", "remaining_time": "7:33:15", "throughput": 4517.9, "total_tokens": 9862656} {"current_steps": 4560, "total_steps": 61300, "loss": 0.3868, "lr": 3.7185970636215334e-05, "epoch": 0.7438825448613376, "percentage": 7.44, "elapsed_time": "0:36:25", "remaining_time": "7:33:13", "throughput": 4518.25, "total_tokens": 9874304} {"current_steps": 4565, "total_steps": 61300, "loss": 0.3344, "lr": 3.722675367047309e-05, "epoch": 0.7446982055464927, "percentage": 7.45, "elapsed_time": "0:36:27", "remaining_time": "7:33:06", "throughput": 4518.55, "total_tokens": 9884128} {"current_steps": 4570, "total_steps": 61300, "loss": 0.3563, "lr": 3.726753670473083e-05, "epoch": 0.7455138662316476, "percentage": 7.46, "elapsed_time": "0:36:29", "remaining_time": "7:33:00", "throughput": 4518.72, "total_tokens": 9894208} {"current_steps": 4575, "total_steps": 61300, "loss": 0.39, "lr": 3.7308319738988584e-05, "epoch": 0.7463295269168027, "percentage": 7.46, "elapsed_time": "0:36:31", "remaining_time": "7:32:56", "throughput": 4518.99, "total_tokens": 9904864} {"current_steps": 4580, "total_steps": 61300, "loss": 0.3532, "lr": 3.734910277324633e-05, "epoch": 0.7471451876019576, "percentage": 7.47, "elapsed_time": "0:36:34", "remaining_time": "7:32:52", "throughput": 4519.35, "total_tokens": 9915904} {"current_steps": 4585, "total_steps": 61300, "loss": 0.3618, "lr": 3.738988580750408e-05, "epoch": 0.7479608482871125, "percentage": 7.48, "elapsed_time": "0:36:36", "remaining_time": "7:32:46", "throughput": 4519.54, "total_tokens": 9926048} {"current_steps": 4590, "total_steps": 61300, "loss": 0.429, "lr": 3.743066884176183e-05, "epoch": 0.7487765089722676, "percentage": 7.49, "elapsed_time": "0:36:38", "remaining_time": "7:32:42", "throughput": 4519.83, "total_tokens": 9936736} {"current_steps": 4595, "total_steps": 61300, "loss": 0.3586, "lr": 3.7471451876019575e-05, "epoch": 0.7495921696574225, "percentage": 7.5, "elapsed_time": "0:36:41", "remaining_time": "7:32:42", "throughput": 4520.28, "total_tokens": 9949408} {"current_steps": 4600, "total_steps": 61300, "loss": 0.3485, "lr": 3.751223491027733e-05, "epoch": 0.7504078303425775, "percentage": 7.5, "elapsed_time": "0:36:43", "remaining_time": "7:32:38", "throughput": 4520.53, "total_tokens": 9960160} {"current_steps": 4605, "total_steps": 61300, "loss": 0.338, "lr": 3.755301794453508e-05, "epoch": 0.7512234910277324, "percentage": 7.51, "elapsed_time": "0:36:45", "remaining_time": "7:32:32", "throughput": 4520.86, "total_tokens": 9970624} {"current_steps": 4610, "total_steps": 61300, "loss": 0.3618, "lr": 3.7593800978792824e-05, "epoch": 0.7520391517128875, "percentage": 7.52, "elapsed_time": "0:36:47", "remaining_time": "7:32:30", "throughput": 4521.18, "total_tokens": 9982080} {"current_steps": 4615, "total_steps": 61300, "loss": 0.342, "lr": 3.763458401305057e-05, "epoch": 0.7528548123980424, "percentage": 7.53, "elapsed_time": "0:36:49", "remaining_time": "7:32:24", "throughput": 4521.48, "total_tokens": 9992480} {"current_steps": 4620, "total_steps": 61300, "loss": 0.3049, "lr": 3.7675367047308326e-05, "epoch": 0.7536704730831973, "percentage": 7.54, "elapsed_time": "0:36:52", "remaining_time": "7:32:18", "throughput": 4521.79, "total_tokens": 10002496} {"current_steps": 4625, "total_steps": 61300, "loss": 0.4286, "lr": 3.771615008156607e-05, "epoch": 0.7544861337683524, "percentage": 7.54, "elapsed_time": "0:36:54", "remaining_time": "7:32:14", "throughput": 4522.02, "total_tokens": 10013408} {"current_steps": 4630, "total_steps": 61300, "loss": 0.3905, "lr": 3.7756933115823815e-05, "epoch": 0.7553017944535073, "percentage": 7.55, "elapsed_time": "0:36:56", "remaining_time": "7:32:07", "throughput": 4522.25, "total_tokens": 10022880} {"current_steps": 4635, "total_steps": 61300, "loss": 0.3654, "lr": 3.779771615008157e-05, "epoch": 0.7561174551386624, "percentage": 7.56, "elapsed_time": "0:36:58", "remaining_time": "7:32:04", "throughput": 4522.59, "total_tokens": 10034208} {"current_steps": 4640, "total_steps": 61300, "loss": 0.3937, "lr": 3.783849918433932e-05, "epoch": 0.7569331158238173, "percentage": 7.57, "elapsed_time": "0:37:00", "remaining_time": "7:31:59", "throughput": 4522.93, "total_tokens": 10044832} {"current_steps": 4645, "total_steps": 61300, "loss": 0.3682, "lr": 3.7879282218597065e-05, "epoch": 0.7577487765089723, "percentage": 7.58, "elapsed_time": "0:37:03", "remaining_time": "7:31:55", "throughput": 4523.19, "total_tokens": 10055712} {"current_steps": 4650, "total_steps": 61300, "loss": 0.401, "lr": 3.792006525285481e-05, "epoch": 0.7585644371941273, "percentage": 7.59, "elapsed_time": "0:37:05", "remaining_time": "7:31:52", "throughput": 4523.53, "total_tokens": 10066976} {"current_steps": 4655, "total_steps": 61300, "loss": 0.3802, "lr": 3.796084828711256e-05, "epoch": 0.7593800978792822, "percentage": 7.59, "elapsed_time": "0:37:07", "remaining_time": "7:31:50", "throughput": 4523.74, "total_tokens": 10078304} {"current_steps": 4660, "total_steps": 61300, "loss": 0.3717, "lr": 3.8001631321370314e-05, "epoch": 0.7601957585644372, "percentage": 7.6, "elapsed_time": "0:37:10", "remaining_time": "7:31:46", "throughput": 4523.94, "total_tokens": 10089056} {"current_steps": 4665, "total_steps": 61300, "loss": 0.3649, "lr": 3.804241435562806e-05, "epoch": 0.7610114192495921, "percentage": 7.61, "elapsed_time": "0:37:12", "remaining_time": "7:31:41", "throughput": 4524.3, "total_tokens": 10099904} {"current_steps": 4670, "total_steps": 61300, "loss": 0.3584, "lr": 3.808319738988581e-05, "epoch": 0.7618270799347472, "percentage": 7.62, "elapsed_time": "0:37:14", "remaining_time": "7:31:40", "throughput": 4524.58, "total_tokens": 10111552} {"current_steps": 4675, "total_steps": 61300, "loss": 0.3745, "lr": 3.812398042414356e-05, "epoch": 0.7626427406199021, "percentage": 7.63, "elapsed_time": "0:37:16", "remaining_time": "7:31:34", "throughput": 4524.71, "total_tokens": 10121568} {"current_steps": 4680, "total_steps": 61300, "loss": 0.4142, "lr": 3.816476345840131e-05, "epoch": 0.763458401305057, "percentage": 7.63, "elapsed_time": "0:37:19", "remaining_time": "7:31:29", "throughput": 4524.97, "total_tokens": 10132000} {"current_steps": 4685, "total_steps": 61300, "loss": 0.3786, "lr": 3.820554649265905e-05, "epoch": 0.7642740619902121, "percentage": 7.64, "elapsed_time": "0:37:21", "remaining_time": "7:31:23", "throughput": 4525.2, "total_tokens": 10141952} {"current_steps": 4690, "total_steps": 61300, "loss": 0.3705, "lr": 3.82463295269168e-05, "epoch": 0.765089722675367, "percentage": 7.65, "elapsed_time": "0:37:23", "remaining_time": "7:31:17", "throughput": 4525.45, "total_tokens": 10151776} {"current_steps": 4695, "total_steps": 61300, "loss": 0.3421, "lr": 3.8287112561174555e-05, "epoch": 0.765905383360522, "percentage": 7.66, "elapsed_time": "0:37:25", "remaining_time": "7:31:13", "throughput": 4525.76, "total_tokens": 10162688} {"current_steps": 4700, "total_steps": 61300, "loss": 0.3154, "lr": 3.83278955954323e-05, "epoch": 0.766721044045677, "percentage": 7.67, "elapsed_time": "0:37:27", "remaining_time": "7:31:11", "throughput": 4526.12, "total_tokens": 10174624} {"current_steps": 4705, "total_steps": 61300, "loss": 0.3592, "lr": 3.836867862969005e-05, "epoch": 0.767536704730832, "percentage": 7.68, "elapsed_time": "0:37:30", "remaining_time": "7:31:06", "throughput": 4526.38, "total_tokens": 10185248} {"current_steps": 4710, "total_steps": 61300, "loss": 0.3001, "lr": 3.84094616639478e-05, "epoch": 0.768352365415987, "percentage": 7.68, "elapsed_time": "0:37:32", "remaining_time": "7:31:04", "throughput": 4526.67, "total_tokens": 10196768} {"current_steps": 4715, "total_steps": 61300, "loss": 0.3502, "lr": 3.845024469820555e-05, "epoch": 0.7691680261011419, "percentage": 7.69, "elapsed_time": "0:37:34", "remaining_time": "7:30:59", "throughput": 4526.83, "total_tokens": 10206816} {"current_steps": 4720, "total_steps": 61300, "loss": 0.3561, "lr": 3.84910277324633e-05, "epoch": 0.7699836867862969, "percentage": 7.7, "elapsed_time": "0:37:36", "remaining_time": "7:30:54", "throughput": 4527.2, "total_tokens": 10217600} {"current_steps": 4725, "total_steps": 61300, "loss": 0.3836, "lr": 3.853181076672104e-05, "epoch": 0.7707993474714518, "percentage": 7.71, "elapsed_time": "0:37:39", "remaining_time": "7:30:50", "throughput": 4527.51, "total_tokens": 10228544} {"current_steps": 4730, "total_steps": 61300, "loss": 0.3233, "lr": 3.8572593800978795e-05, "epoch": 0.7716150081566069, "percentage": 7.72, "elapsed_time": "0:37:41", "remaining_time": "7:30:45", "throughput": 4527.85, "total_tokens": 10239168} {"current_steps": 4735, "total_steps": 61300, "loss": 0.36, "lr": 3.861337683523654e-05, "epoch": 0.7724306688417618, "percentage": 7.72, "elapsed_time": "0:37:43", "remaining_time": "7:30:43", "throughput": 4528.2, "total_tokens": 10250784} {"current_steps": 4740, "total_steps": 61300, "loss": 0.3735, "lr": 3.86541598694943e-05, "epoch": 0.7732463295269169, "percentage": 7.73, "elapsed_time": "0:37:45", "remaining_time": "7:30:36", "throughput": 4528.42, "total_tokens": 10260480} {"current_steps": 4745, "total_steps": 61300, "loss": 0.3444, "lr": 3.869494290375204e-05, "epoch": 0.7740619902120718, "percentage": 7.74, "elapsed_time": "0:37:48", "remaining_time": "7:30:34", "throughput": 4528.7, "total_tokens": 10272064} {"current_steps": 4750, "total_steps": 61300, "loss": 0.3428, "lr": 3.873572593800979e-05, "epoch": 0.7748776508972267, "percentage": 7.75, "elapsed_time": "0:37:50", "remaining_time": "7:30:26", "throughput": 4528.95, "total_tokens": 10281472} {"current_steps": 4755, "total_steps": 61300, "loss": 0.4206, "lr": 3.877650897226754e-05, "epoch": 0.7756933115823818, "percentage": 7.76, "elapsed_time": "0:37:52", "remaining_time": "7:30:26", "throughput": 4529.25, "total_tokens": 10293536} {"current_steps": 4760, "total_steps": 61300, "loss": 0.3635, "lr": 3.881729200652529e-05, "epoch": 0.7765089722675367, "percentage": 7.77, "elapsed_time": "0:37:54", "remaining_time": "7:30:20", "throughput": 4529.54, "total_tokens": 10303968} {"current_steps": 4765, "total_steps": 61300, "loss": 0.3707, "lr": 3.8858075040783035e-05, "epoch": 0.7773246329526917, "percentage": 7.77, "elapsed_time": "0:37:57", "remaining_time": "7:30:20", "throughput": 4529.8, "total_tokens": 10316064} {"current_steps": 4770, "total_steps": 61300, "loss": 0.3606, "lr": 3.889885807504078e-05, "epoch": 0.7781402936378466, "percentage": 7.78, "elapsed_time": "0:37:59", "remaining_time": "7:30:16", "throughput": 4530.16, "total_tokens": 10327328} {"current_steps": 4775, "total_steps": 61300, "loss": 0.4092, "lr": 3.893964110929854e-05, "epoch": 0.7789559543230016, "percentage": 7.79, "elapsed_time": "0:38:01", "remaining_time": "7:30:10", "throughput": 4530.41, "total_tokens": 10337088} {"current_steps": 4780, "total_steps": 61300, "loss": 0.4059, "lr": 3.8980424143556285e-05, "epoch": 0.7797716150081566, "percentage": 7.8, "elapsed_time": "0:38:03", "remaining_time": "7:30:04", "throughput": 4530.71, "total_tokens": 10347488} {"current_steps": 4785, "total_steps": 61300, "loss": 0.3379, "lr": 3.9021207177814026e-05, "epoch": 0.7805872756933115, "percentage": 7.81, "elapsed_time": "0:38:06", "remaining_time": "7:30:01", "throughput": 4531.09, "total_tokens": 10358656} {"current_steps": 4790, "total_steps": 61300, "loss": 0.3714, "lr": 3.906199021207178e-05, "epoch": 0.7814029363784666, "percentage": 7.81, "elapsed_time": "0:38:08", "remaining_time": "7:30:00", "throughput": 4531.43, "total_tokens": 10370816} {"current_steps": 4795, "total_steps": 61300, "loss": 0.3659, "lr": 3.910277324632953e-05, "epoch": 0.7822185970636215, "percentage": 7.82, "elapsed_time": "0:38:10", "remaining_time": "7:29:57", "throughput": 4531.6, "total_tokens": 10381856} {"current_steps": 4800, "total_steps": 61300, "loss": 0.3262, "lr": 3.914355628058728e-05, "epoch": 0.7830342577487766, "percentage": 7.83, "elapsed_time": "0:38:13", "remaining_time": "7:29:52", "throughput": 4531.85, "total_tokens": 10392320} {"current_steps": 4805, "total_steps": 61300, "loss": 0.3484, "lr": 3.918433931484502e-05, "epoch": 0.7838499184339315, "percentage": 7.84, "elapsed_time": "0:38:15", "remaining_time": "7:29:44", "throughput": 4532.09, "total_tokens": 10401568} {"current_steps": 4810, "total_steps": 61300, "loss": 0.3861, "lr": 3.922512234910278e-05, "epoch": 0.7846655791190864, "percentage": 7.85, "elapsed_time": "0:38:17", "remaining_time": "7:29:42", "throughput": 4532.35, "total_tokens": 10413248} {"current_steps": 4815, "total_steps": 61300, "loss": 0.3308, "lr": 3.9265905383360525e-05, "epoch": 0.7854812398042414, "percentage": 7.85, "elapsed_time": "0:38:19", "remaining_time": "7:29:36", "throughput": 4532.56, "total_tokens": 10423168} {"current_steps": 4820, "total_steps": 61300, "loss": 0.3398, "lr": 3.930668841761827e-05, "epoch": 0.7862969004893964, "percentage": 7.86, "elapsed_time": "0:38:21", "remaining_time": "7:29:32", "throughput": 4532.82, "total_tokens": 10433792} {"current_steps": 4825, "total_steps": 61300, "loss": 0.3476, "lr": 3.934747145187602e-05, "epoch": 0.7871125611745514, "percentage": 7.87, "elapsed_time": "0:38:24", "remaining_time": "7:29:29", "throughput": 4533.15, "total_tokens": 10445120} {"current_steps": 4830, "total_steps": 61300, "loss": 0.3493, "lr": 3.938825448613377e-05, "epoch": 0.7879282218597063, "percentage": 7.88, "elapsed_time": "0:38:26", "remaining_time": "7:29:24", "throughput": 4533.45, "total_tokens": 10455584} {"current_steps": 4835, "total_steps": 61300, "loss": 0.3252, "lr": 3.942903752039152e-05, "epoch": 0.7887438825448614, "percentage": 7.89, "elapsed_time": "0:38:28", "remaining_time": "7:29:21", "throughput": 4533.75, "total_tokens": 10466752} {"current_steps": 4840, "total_steps": 61300, "loss": 0.3817, "lr": 3.946982055464927e-05, "epoch": 0.7895595432300163, "percentage": 7.9, "elapsed_time": "0:38:30", "remaining_time": "7:29:17", "throughput": 4533.9, "total_tokens": 10477376} {"current_steps": 4845, "total_steps": 61300, "loss": 0.2884, "lr": 3.951060358890702e-05, "epoch": 0.7903752039151712, "percentage": 7.9, "elapsed_time": "0:38:32", "remaining_time": "7:29:11", "throughput": 4534.13, "total_tokens": 10487392} {"current_steps": 4850, "total_steps": 61300, "loss": 0.4456, "lr": 3.9551386623164766e-05, "epoch": 0.7911908646003263, "percentage": 7.91, "elapsed_time": "0:38:35", "remaining_time": "7:29:07", "throughput": 4534.36, "total_tokens": 10498208} {"current_steps": 4855, "total_steps": 61300, "loss": 0.3305, "lr": 3.959216965742251e-05, "epoch": 0.7920065252854812, "percentage": 7.92, "elapsed_time": "0:38:37", "remaining_time": "7:28:59", "throughput": 4534.57, "total_tokens": 10507200} {"current_steps": 4860, "total_steps": 61300, "loss": 0.327, "lr": 3.963295269168026e-05, "epoch": 0.7928221859706363, "percentage": 7.93, "elapsed_time": "0:38:39", "remaining_time": "7:28:51", "throughput": 4534.83, "total_tokens": 10516416} {"current_steps": 4865, "total_steps": 61300, "loss": 0.3427, "lr": 3.967373572593801e-05, "epoch": 0.7936378466557912, "percentage": 7.94, "elapsed_time": "0:38:41", "remaining_time": "7:28:48", "throughput": 4535.13, "total_tokens": 10527648} {"current_steps": 4870, "total_steps": 61300, "loss": 0.3424, "lr": 3.971451876019576e-05, "epoch": 0.7944535073409462, "percentage": 7.94, "elapsed_time": "0:38:43", "remaining_time": "7:28:43", "throughput": 4535.35, "total_tokens": 10537952} {"current_steps": 4875, "total_steps": 61300, "loss": 0.3473, "lr": 3.975530179445351e-05, "epoch": 0.7952691680261011, "percentage": 7.95, "elapsed_time": "0:38:45", "remaining_time": "7:28:38", "throughput": 4535.59, "total_tokens": 10548320} {"current_steps": 4880, "total_steps": 61300, "loss": 0.3151, "lr": 3.979608482871126e-05, "epoch": 0.7960848287112561, "percentage": 7.96, "elapsed_time": "0:38:47", "remaining_time": "7:28:30", "throughput": 4535.86, "total_tokens": 10557824} {"current_steps": 4885, "total_steps": 61300, "loss": 0.3966, "lr": 3.9836867862969006e-05, "epoch": 0.7969004893964111, "percentage": 7.97, "elapsed_time": "0:38:49", "remaining_time": "7:28:27", "throughput": 4536.14, "total_tokens": 10568896} {"current_steps": 4890, "total_steps": 61300, "loss": 0.3773, "lr": 3.9877650897226754e-05, "epoch": 0.797716150081566, "percentage": 7.98, "elapsed_time": "0:38:52", "remaining_time": "7:28:24", "throughput": 4536.34, "total_tokens": 10580064} {"current_steps": 4895, "total_steps": 61300, "loss": 0.3294, "lr": 3.991843393148451e-05, "epoch": 0.7985318107667211, "percentage": 7.99, "elapsed_time": "0:38:54", "remaining_time": "7:28:21", "throughput": 4536.48, "total_tokens": 10590976} {"current_steps": 4900, "total_steps": 61300, "loss": 0.4048, "lr": 3.995921696574225e-05, "epoch": 0.799347471451876, "percentage": 7.99, "elapsed_time": "0:38:56", "remaining_time": "7:28:14", "throughput": 4536.73, "total_tokens": 10600448} {"current_steps": 4905, "total_steps": 61300, "loss": 0.3829, "lr": 4e-05, "epoch": 0.8001631321370309, "percentage": 8.0, "elapsed_time": "0:38:58", "remaining_time": "7:28:12", "throughput": 4536.96, "total_tokens": 10611904} {"current_steps": 4910, "total_steps": 61300, "loss": 0.3966, "lr": 4.004078303425775e-05, "epoch": 0.800978792822186, "percentage": 8.01, "elapsed_time": "0:39:01", "remaining_time": "7:28:07", "throughput": 4537.2, "total_tokens": 10622240} {"current_steps": 4915, "total_steps": 61300, "loss": 0.3852, "lr": 4.00815660685155e-05, "epoch": 0.8017944535073409, "percentage": 8.02, "elapsed_time": "0:39:03", "remaining_time": "7:28:02", "throughput": 4537.48, "total_tokens": 10632864} {"current_steps": 4920, "total_steps": 61300, "loss": 0.3753, "lr": 4.0122349102773246e-05, "epoch": 0.802610114192496, "percentage": 8.03, "elapsed_time": "0:39:05", "remaining_time": "7:27:56", "throughput": 4537.68, "total_tokens": 10642464} {"current_steps": 4925, "total_steps": 61300, "loss": 0.3556, "lr": 4.0163132137030994e-05, "epoch": 0.8034257748776509, "percentage": 8.03, "elapsed_time": "0:39:07", "remaining_time": "7:27:51", "throughput": 4537.98, "total_tokens": 10653024} {"current_steps": 4930, "total_steps": 61300, "loss": 0.3656, "lr": 4.020391517128875e-05, "epoch": 0.8042414355628059, "percentage": 8.04, "elapsed_time": "0:39:09", "remaining_time": "7:27:48", "throughput": 4538.29, "total_tokens": 10664384} {"current_steps": 4935, "total_steps": 61300, "loss": 0.3559, "lr": 4.0244698205546496e-05, "epoch": 0.8050570962479608, "percentage": 8.05, "elapsed_time": "0:39:12", "remaining_time": "7:27:45", "throughput": 4538.5, "total_tokens": 10675360} {"current_steps": 4940, "total_steps": 61300, "loss": 0.4164, "lr": 4.0285481239804244e-05, "epoch": 0.8058727569331158, "percentage": 8.06, "elapsed_time": "0:39:14", "remaining_time": "7:27:40", "throughput": 4538.75, "total_tokens": 10685824} {"current_steps": 4945, "total_steps": 61300, "loss": 0.3869, "lr": 4.032626427406199e-05, "epoch": 0.8066884176182708, "percentage": 8.07, "elapsed_time": "0:39:16", "remaining_time": "7:27:38", "throughput": 4539.03, "total_tokens": 10697536} {"current_steps": 4950, "total_steps": 61300, "loss": 0.3783, "lr": 4.036704730831974e-05, "epoch": 0.8075040783034257, "percentage": 8.08, "elapsed_time": "0:39:19", "remaining_time": "7:27:37", "throughput": 4539.46, "total_tokens": 10709888} {"current_steps": 4955, "total_steps": 61300, "loss": 0.394, "lr": 4.040783034257749e-05, "epoch": 0.8083197389885808, "percentage": 8.08, "elapsed_time": "0:39:21", "remaining_time": "7:27:35", "throughput": 4539.71, "total_tokens": 10721216} {"current_steps": 4960, "total_steps": 61300, "loss": 0.3878, "lr": 4.0448613376835234e-05, "epoch": 0.8091353996737357, "percentage": 8.09, "elapsed_time": "0:39:23", "remaining_time": "7:27:26", "throughput": 4539.86, "total_tokens": 10729952} {"current_steps": 4965, "total_steps": 61300, "loss": 0.3804, "lr": 4.048939641109299e-05, "epoch": 0.8099510603588908, "percentage": 8.1, "elapsed_time": "0:39:25", "remaining_time": "7:27:23", "throughput": 4540.16, "total_tokens": 10741216} {"current_steps": 4970, "total_steps": 61300, "loss": 0.3229, "lr": 4.0530179445350736e-05, "epoch": 0.8107667210440457, "percentage": 8.11, "elapsed_time": "0:39:28", "remaining_time": "7:27:20", "throughput": 4540.46, "total_tokens": 10752544} {"current_steps": 4975, "total_steps": 61300, "loss": 0.4153, "lr": 4.057096247960849e-05, "epoch": 0.8115823817292006, "percentage": 8.12, "elapsed_time": "0:39:30", "remaining_time": "7:27:20", "throughput": 4540.81, "total_tokens": 10764960} {"current_steps": 4980, "total_steps": 61300, "loss": 0.3456, "lr": 4.061174551386623e-05, "epoch": 0.8123980424143556, "percentage": 8.12, "elapsed_time": "0:39:32", "remaining_time": "7:27:15", "throughput": 4541.05, "total_tokens": 10775296} {"current_steps": 4985, "total_steps": 61300, "loss": 0.3199, "lr": 4.065252854812398e-05, "epoch": 0.8132137030995106, "percentage": 8.13, "elapsed_time": "0:39:35", "remaining_time": "7:27:10", "throughput": 4541.39, "total_tokens": 10786112} {"current_steps": 4990, "total_steps": 61300, "loss": 0.3919, "lr": 4.0693311582381734e-05, "epoch": 0.8140293637846656, "percentage": 8.14, "elapsed_time": "0:39:37", "remaining_time": "7:27:07", "throughput": 4541.69, "total_tokens": 10797152} {"current_steps": 4995, "total_steps": 61300, "loss": 0.3524, "lr": 4.073409461663948e-05, "epoch": 0.8148450244698205, "percentage": 8.15, "elapsed_time": "0:39:39", "remaining_time": "7:27:04", "throughput": 4541.9, "total_tokens": 10808480} {"current_steps": 5000, "total_steps": 61300, "loss": 0.3606, "lr": 4.077487765089723e-05, "epoch": 0.8156606851549756, "percentage": 8.16, "elapsed_time": "0:39:42", "remaining_time": "7:27:01", "throughput": 4542.15, "total_tokens": 10819424} {"current_steps": 5005, "total_steps": 61300, "loss": 0.3431, "lr": 4.0815660685154977e-05, "epoch": 0.8164763458401305, "percentage": 8.16, "elapsed_time": "0:39:44", "remaining_time": "7:26:57", "throughput": 4542.4, "total_tokens": 10830048} {"current_steps": 5010, "total_steps": 61300, "loss": 0.3757, "lr": 4.0856443719412724e-05, "epoch": 0.8172920065252854, "percentage": 8.17, "elapsed_time": "0:39:46", "remaining_time": "7:26:52", "throughput": 4542.65, "total_tokens": 10840768} {"current_steps": 5015, "total_steps": 61300, "loss": 0.3529, "lr": 4.089722675367048e-05, "epoch": 0.8181076672104405, "percentage": 8.18, "elapsed_time": "0:39:48", "remaining_time": "7:26:44", "throughput": 4542.86, "total_tokens": 10849792} {"current_steps": 5020, "total_steps": 61300, "loss": 0.378, "lr": 4.093800978792822e-05, "epoch": 0.8189233278955954, "percentage": 8.19, "elapsed_time": "0:39:50", "remaining_time": "7:26:43", "throughput": 4543.1, "total_tokens": 10861472} {"current_steps": 5025, "total_steps": 61300, "loss": 0.3184, "lr": 4.0978792822185974e-05, "epoch": 0.8197389885807504, "percentage": 8.2, "elapsed_time": "0:39:52", "remaining_time": "7:26:38", "throughput": 4543.36, "total_tokens": 10871968} {"current_steps": 5030, "total_steps": 61300, "loss": 0.3619, "lr": 4.101957585644372e-05, "epoch": 0.8205546492659054, "percentage": 8.21, "elapsed_time": "0:39:55", "remaining_time": "7:26:34", "throughput": 4543.58, "total_tokens": 10882560} {"current_steps": 5035, "total_steps": 61300, "loss": 0.3691, "lr": 4.106035889070147e-05, "epoch": 0.8213703099510603, "percentage": 8.21, "elapsed_time": "0:39:57", "remaining_time": "7:26:31", "throughput": 4543.89, "total_tokens": 10894048} {"current_steps": 5040, "total_steps": 61300, "loss": 0.3604, "lr": 4.110114192495922e-05, "epoch": 0.8221859706362153, "percentage": 8.22, "elapsed_time": "0:39:59", "remaining_time": "7:26:28", "throughput": 4544.19, "total_tokens": 10905408} {"current_steps": 5045, "total_steps": 61300, "loss": 0.3253, "lr": 4.1141924959216964e-05, "epoch": 0.8230016313213703, "percentage": 8.23, "elapsed_time": "0:40:02", "remaining_time": "7:26:23", "throughput": 4544.39, "total_tokens": 10915648} {"current_steps": 5050, "total_steps": 61300, "loss": 0.3162, "lr": 4.118270799347472e-05, "epoch": 0.8238172920065253, "percentage": 8.24, "elapsed_time": "0:40:04", "remaining_time": "7:26:21", "throughput": 4544.61, "total_tokens": 10926880} {"current_steps": 5055, "total_steps": 61300, "loss": 0.366, "lr": 4.1223491027732467e-05, "epoch": 0.8246329526916802, "percentage": 8.25, "elapsed_time": "0:40:06", "remaining_time": "7:26:18", "throughput": 4544.92, "total_tokens": 10938432} {"current_steps": 5060, "total_steps": 61300, "loss": 0.3767, "lr": 4.1264274061990214e-05, "epoch": 0.8254486133768353, "percentage": 8.25, "elapsed_time": "0:40:08", "remaining_time": "7:26:14", "throughput": 4545.16, "total_tokens": 10948992} {"current_steps": 5065, "total_steps": 61300, "loss": 0.3405, "lr": 4.130505709624796e-05, "epoch": 0.8262642740619902, "percentage": 8.26, "elapsed_time": "0:40:10", "remaining_time": "7:26:06", "throughput": 4545.39, "total_tokens": 10958272} {"current_steps": 5070, "total_steps": 61300, "loss": 0.3935, "lr": 4.1345840130505716e-05, "epoch": 0.8270799347471451, "percentage": 8.27, "elapsed_time": "0:40:13", "remaining_time": "7:26:02", "throughput": 4545.56, "total_tokens": 10968512} {"current_steps": 5075, "total_steps": 61300, "loss": 0.3695, "lr": 4.1386623164763464e-05, "epoch": 0.8278955954323002, "percentage": 8.28, "elapsed_time": "0:40:15", "remaining_time": "7:25:57", "throughput": 4545.86, "total_tokens": 10979072} {"current_steps": 5080, "total_steps": 61300, "loss": 0.3562, "lr": 4.1427406199021205e-05, "epoch": 0.8287112561174551, "percentage": 8.29, "elapsed_time": "0:40:17", "remaining_time": "7:25:50", "throughput": 4546.15, "total_tokens": 10988736} {"current_steps": 5085, "total_steps": 61300, "loss": 0.3492, "lr": 4.146818923327896e-05, "epoch": 0.8295269168026101, "percentage": 8.3, "elapsed_time": "0:40:19", "remaining_time": "7:25:48", "throughput": 4546.49, "total_tokens": 11000512} {"current_steps": 5090, "total_steps": 61300, "loss": 0.4106, "lr": 4.150897226753671e-05, "epoch": 0.8303425774877651, "percentage": 8.3, "elapsed_time": "0:40:21", "remaining_time": "7:25:41", "throughput": 4546.76, "total_tokens": 11010240} {"current_steps": 5095, "total_steps": 61300, "loss": 0.3955, "lr": 4.1549755301794454e-05, "epoch": 0.8311582381729201, "percentage": 8.31, "elapsed_time": "0:40:23", "remaining_time": "7:25:37", "throughput": 4547.0, "total_tokens": 11020672} {"current_steps": 5100, "total_steps": 61300, "loss": 0.4124, "lr": 4.15905383360522e-05, "epoch": 0.831973898858075, "percentage": 8.32, "elapsed_time": "0:40:26", "remaining_time": "7:25:34", "throughput": 4547.15, "total_tokens": 11031808} {"current_steps": 5105, "total_steps": 61300, "loss": 0.3853, "lr": 4.1631321370309957e-05, "epoch": 0.83278955954323, "percentage": 8.33, "elapsed_time": "0:40:28", "remaining_time": "7:25:29", "throughput": 4547.38, "total_tokens": 11042144} {"current_steps": 5110, "total_steps": 61300, "loss": 0.4122, "lr": 4.1672104404567704e-05, "epoch": 0.833605220228385, "percentage": 8.34, "elapsed_time": "0:40:30", "remaining_time": "7:25:27", "throughput": 4547.66, "total_tokens": 11053728} {"current_steps": 5115, "total_steps": 61300, "loss": 0.3894, "lr": 4.171288743882545e-05, "epoch": 0.8344208809135399, "percentage": 8.34, "elapsed_time": "0:40:32", "remaining_time": "7:25:23", "throughput": 4547.81, "total_tokens": 11064032} {"current_steps": 5120, "total_steps": 61300, "loss": 0.3808, "lr": 4.17536704730832e-05, "epoch": 0.835236541598695, "percentage": 8.35, "elapsed_time": "0:40:34", "remaining_time": "7:25:16", "throughput": 4548.03, "total_tokens": 11073792} {"current_steps": 5125, "total_steps": 61300, "loss": 0.3294, "lr": 4.179445350734095e-05, "epoch": 0.8360522022838499, "percentage": 8.36, "elapsed_time": "0:40:37", "remaining_time": "7:25:14", "throughput": 4548.31, "total_tokens": 11085216} {"current_steps": 5130, "total_steps": 61300, "loss": 0.3467, "lr": 4.18352365415987e-05, "epoch": 0.8368678629690048, "percentage": 8.37, "elapsed_time": "0:40:39", "remaining_time": "7:25:11", "throughput": 4548.52, "total_tokens": 11096288} {"current_steps": 5135, "total_steps": 61300, "loss": 0.3822, "lr": 4.187601957585644e-05, "epoch": 0.8376835236541599, "percentage": 8.38, "elapsed_time": "0:40:41", "remaining_time": "7:25:08", "throughput": 4548.83, "total_tokens": 11107584} {"current_steps": 5140, "total_steps": 61300, "loss": 0.4, "lr": 4.191680261011419e-05, "epoch": 0.8384991843393148, "percentage": 8.38, "elapsed_time": "0:40:44", "remaining_time": "7:25:05", "throughput": 4549.11, "total_tokens": 11118752} {"current_steps": 5145, "total_steps": 61300, "loss": 0.3396, "lr": 4.1957585644371944e-05, "epoch": 0.8393148450244698, "percentage": 8.39, "elapsed_time": "0:40:46", "remaining_time": "7:24:57", "throughput": 4549.27, "total_tokens": 11127840} {"current_steps": 5150, "total_steps": 61300, "loss": 0.3443, "lr": 4.199836867862969e-05, "epoch": 0.8401305057096248, "percentage": 8.4, "elapsed_time": "0:40:48", "remaining_time": "7:24:51", "throughput": 4549.53, "total_tokens": 11137952} {"current_steps": 5155, "total_steps": 61300, "loss": 0.4128, "lr": 4.203915171288744e-05, "epoch": 0.8409461663947798, "percentage": 8.41, "elapsed_time": "0:40:50", "remaining_time": "7:24:44", "throughput": 4549.74, "total_tokens": 11147008} {"current_steps": 5160, "total_steps": 61300, "loss": 0.4157, "lr": 4.207993474714519e-05, "epoch": 0.8417618270799347, "percentage": 8.42, "elapsed_time": "0:40:52", "remaining_time": "7:24:42", "throughput": 4550.11, "total_tokens": 11158912} {"current_steps": 5165, "total_steps": 61300, "loss": 0.3585, "lr": 4.212071778140294e-05, "epoch": 0.8425774877650897, "percentage": 8.43, "elapsed_time": "0:40:54", "remaining_time": "7:24:37", "throughput": 4550.36, "total_tokens": 11169440} {"current_steps": 5170, "total_steps": 61300, "loss": 0.3582, "lr": 4.216150081566069e-05, "epoch": 0.8433931484502447, "percentage": 8.43, "elapsed_time": "0:40:56", "remaining_time": "7:24:32", "throughput": 4550.53, "total_tokens": 11179488} {"current_steps": 5175, "total_steps": 61300, "loss": 0.3737, "lr": 4.220228384991843e-05, "epoch": 0.8442088091353996, "percentage": 8.44, "elapsed_time": "0:40:59", "remaining_time": "7:24:29", "throughput": 4550.84, "total_tokens": 11190912} {"current_steps": 5180, "total_steps": 61300, "loss": 0.4057, "lr": 4.2243066884176185e-05, "epoch": 0.8450244698205547, "percentage": 8.45, "elapsed_time": "0:41:01", "remaining_time": "7:24:27", "throughput": 4551.09, "total_tokens": 11202208} {"current_steps": 5185, "total_steps": 61300, "loss": 0.3885, "lr": 4.228384991843393e-05, "epoch": 0.8458401305057096, "percentage": 8.46, "elapsed_time": "0:41:03", "remaining_time": "7:24:22", "throughput": 4551.3, "total_tokens": 11212448} {"current_steps": 5190, "total_steps": 61300, "loss": 0.3409, "lr": 4.232463295269169e-05, "epoch": 0.8466557911908646, "percentage": 8.47, "elapsed_time": "0:41:05", "remaining_time": "7:24:19", "throughput": 4551.57, "total_tokens": 11223648} {"current_steps": 5195, "total_steps": 61300, "loss": 0.3779, "lr": 4.236541598694943e-05, "epoch": 0.8474714518760196, "percentage": 8.47, "elapsed_time": "0:41:08", "remaining_time": "7:24:15", "throughput": 4551.88, "total_tokens": 11234880} {"current_steps": 5200, "total_steps": 61300, "loss": 0.3711, "lr": 4.240619902120718e-05, "epoch": 0.8482871125611745, "percentage": 8.48, "elapsed_time": "0:41:10", "remaining_time": "7:24:11", "throughput": 4552.11, "total_tokens": 11245184} {"current_steps": 5205, "total_steps": 61300, "loss": 0.333, "lr": 4.244698205546493e-05, "epoch": 0.8491027732463295, "percentage": 8.49, "elapsed_time": "0:41:12", "remaining_time": "7:24:07", "throughput": 4552.43, "total_tokens": 11256288} {"current_steps": 5210, "total_steps": 61300, "loss": 0.3715, "lr": 4.248776508972268e-05, "epoch": 0.8499184339314845, "percentage": 8.5, "elapsed_time": "0:41:14", "remaining_time": "7:24:00", "throughput": 4552.6, "total_tokens": 11265728} {"current_steps": 5215, "total_steps": 61300, "loss": 0.3644, "lr": 4.2528548123980425e-05, "epoch": 0.8507340946166395, "percentage": 8.51, "elapsed_time": "0:41:16", "remaining_time": "7:23:55", "throughput": 4552.85, "total_tokens": 11275712} {"current_steps": 5220, "total_steps": 61300, "loss": 0.3854, "lr": 4.256933115823817e-05, "epoch": 0.8515497553017944, "percentage": 8.52, "elapsed_time": "0:41:19", "remaining_time": "7:23:54", "throughput": 4553.11, "total_tokens": 11287776} {"current_steps": 5225, "total_steps": 61300, "loss": 0.3739, "lr": 4.261011419249593e-05, "epoch": 0.8523654159869495, "percentage": 8.52, "elapsed_time": "0:41:21", "remaining_time": "7:23:49", "throughput": 4553.4, "total_tokens": 11298528} {"current_steps": 5230, "total_steps": 61300, "loss": 0.3642, "lr": 4.2650897226753675e-05, "epoch": 0.8531810766721044, "percentage": 8.53, "elapsed_time": "0:41:23", "remaining_time": "7:23:46", "throughput": 4553.64, "total_tokens": 11309536} {"current_steps": 5235, "total_steps": 61300, "loss": 0.3666, "lr": 4.2691680261011416e-05, "epoch": 0.8539967373572593, "percentage": 8.54, "elapsed_time": "0:41:25", "remaining_time": "7:23:40", "throughput": 4553.85, "total_tokens": 11319200} {"current_steps": 5240, "total_steps": 61300, "loss": 0.3759, "lr": 4.273246329526917e-05, "epoch": 0.8548123980424144, "percentage": 8.55, "elapsed_time": "0:41:27", "remaining_time": "7:23:34", "throughput": 4554.05, "total_tokens": 11329120} {"current_steps": 5245, "total_steps": 61300, "loss": 0.3999, "lr": 4.277324632952692e-05, "epoch": 0.8556280587275693, "percentage": 8.56, "elapsed_time": "0:41:29", "remaining_time": "7:23:29", "throughput": 4554.22, "total_tokens": 11339360} {"current_steps": 5250, "total_steps": 61300, "loss": 0.37, "lr": 4.281402936378467e-05, "epoch": 0.8564437194127243, "percentage": 8.56, "elapsed_time": "0:41:32", "remaining_time": "7:23:27", "throughput": 4554.5, "total_tokens": 11350848} {"current_steps": 5255, "total_steps": 61300, "loss": 0.3199, "lr": 4.285481239804241e-05, "epoch": 0.8572593800978793, "percentage": 8.57, "elapsed_time": "0:41:34", "remaining_time": "7:23:21", "throughput": 4554.76, "total_tokens": 11360704} {"current_steps": 5260, "total_steps": 61300, "loss": 0.3883, "lr": 4.289559543230017e-05, "epoch": 0.8580750407830342, "percentage": 8.58, "elapsed_time": "0:41:36", "remaining_time": "7:23:15", "throughput": 4555.02, "total_tokens": 11370816} {"current_steps": 5265, "total_steps": 61300, "loss": 0.3204, "lr": 4.2936378466557915e-05, "epoch": 0.8588907014681892, "percentage": 8.59, "elapsed_time": "0:41:38", "remaining_time": "7:23:13", "throughput": 4555.27, "total_tokens": 11382080} {"current_steps": 5270, "total_steps": 61300, "loss": 0.3721, "lr": 4.297716150081566e-05, "epoch": 0.8597063621533442, "percentage": 8.6, "elapsed_time": "0:41:40", "remaining_time": "7:23:08", "throughput": 4555.54, "total_tokens": 11392736} {"current_steps": 5275, "total_steps": 61300, "loss": 0.3145, "lr": 4.301794453507341e-05, "epoch": 0.8605220228384992, "percentage": 8.61, "elapsed_time": "0:41:42", "remaining_time": "7:23:03", "throughput": 4555.79, "total_tokens": 11402720} {"current_steps": 5280, "total_steps": 61300, "loss": 0.3789, "lr": 4.305872756933116e-05, "epoch": 0.8613376835236541, "percentage": 8.61, "elapsed_time": "0:41:45", "remaining_time": "7:23:00", "throughput": 4556.01, "total_tokens": 11413984} {"current_steps": 5285, "total_steps": 61300, "loss": 0.379, "lr": 4.309951060358891e-05, "epoch": 0.8621533442088092, "percentage": 8.62, "elapsed_time": "0:41:47", "remaining_time": "7:22:56", "throughput": 4556.23, "total_tokens": 11424832} {"current_steps": 5290, "total_steps": 61300, "loss": 0.3303, "lr": 4.314029363784666e-05, "epoch": 0.8629690048939641, "percentage": 8.63, "elapsed_time": "0:41:49", "remaining_time": "7:22:53", "throughput": 4556.51, "total_tokens": 11436128} {"current_steps": 5295, "total_steps": 61300, "loss": 0.3433, "lr": 4.318107667210441e-05, "epoch": 0.863784665579119, "percentage": 8.64, "elapsed_time": "0:41:52", "remaining_time": "7:22:53", "throughput": 4556.84, "total_tokens": 11448448} {"current_steps": 5300, "total_steps": 61300, "loss": 0.3452, "lr": 4.3221859706362155e-05, "epoch": 0.8646003262642741, "percentage": 8.65, "elapsed_time": "0:41:54", "remaining_time": "7:22:46", "throughput": 4557.15, "total_tokens": 11458176} {"current_steps": 5305, "total_steps": 61300, "loss": 0.3632, "lr": 4.32626427406199e-05, "epoch": 0.865415986949429, "percentage": 8.65, "elapsed_time": "0:41:56", "remaining_time": "7:22:42", "throughput": 4557.31, "total_tokens": 11468480} {"current_steps": 5310, "total_steps": 61300, "loss": 0.3661, "lr": 4.330342577487765e-05, "epoch": 0.866231647634584, "percentage": 8.66, "elapsed_time": "0:41:58", "remaining_time": "7:22:37", "throughput": 4557.52, "total_tokens": 11478880} {"current_steps": 5315, "total_steps": 61300, "loss": 0.4301, "lr": 4.33442088091354e-05, "epoch": 0.867047308319739, "percentage": 8.67, "elapsed_time": "0:42:01", "remaining_time": "7:22:35", "throughput": 4557.7, "total_tokens": 11490176} {"current_steps": 5320, "total_steps": 61300, "loss": 0.3801, "lr": 4.338499184339315e-05, "epoch": 0.867862969004894, "percentage": 8.68, "elapsed_time": "0:42:03", "remaining_time": "7:22:31", "throughput": 4557.97, "total_tokens": 11500992} {"current_steps": 5325, "total_steps": 61300, "loss": 0.3712, "lr": 4.34257748776509e-05, "epoch": 0.8686786296900489, "percentage": 8.69, "elapsed_time": "0:42:05", "remaining_time": "7:22:28", "throughput": 4558.26, "total_tokens": 11512288} {"current_steps": 5330, "total_steps": 61300, "loss": 0.3792, "lr": 4.346655791190865e-05, "epoch": 0.8694942903752039, "percentage": 8.69, "elapsed_time": "0:42:07", "remaining_time": "7:22:21", "throughput": 4558.46, "total_tokens": 11521664} {"current_steps": 5335, "total_steps": 61300, "loss": 0.3568, "lr": 4.3507340946166396e-05, "epoch": 0.8703099510603589, "percentage": 8.7, "elapsed_time": "0:42:09", "remaining_time": "7:22:18", "throughput": 4558.7, "total_tokens": 11532608} {"current_steps": 5340, "total_steps": 61300, "loss": 0.3819, "lr": 4.354812398042414e-05, "epoch": 0.8711256117455138, "percentage": 8.71, "elapsed_time": "0:42:11", "remaining_time": "7:22:13", "throughput": 4558.96, "total_tokens": 11543072} {"current_steps": 5345, "total_steps": 61300, "loss": 0.3587, "lr": 4.35889070146819e-05, "epoch": 0.8719412724306689, "percentage": 8.72, "elapsed_time": "0:42:14", "remaining_time": "7:22:10", "throughput": 4559.17, "total_tokens": 11554144} {"current_steps": 5350, "total_steps": 61300, "loss": 0.3814, "lr": 4.3629690048939645e-05, "epoch": 0.8727569331158238, "percentage": 8.73, "elapsed_time": "0:42:16", "remaining_time": "7:22:07", "throughput": 4559.41, "total_tokens": 11565376} {"current_steps": 5355, "total_steps": 61300, "loss": 0.3228, "lr": 4.367047308319739e-05, "epoch": 0.8735725938009788, "percentage": 8.74, "elapsed_time": "0:42:18", "remaining_time": "7:22:04", "throughput": 4559.59, "total_tokens": 11576128} {"current_steps": 5360, "total_steps": 61300, "loss": 0.3603, "lr": 4.371125611745514e-05, "epoch": 0.8743882544861338, "percentage": 8.74, "elapsed_time": "0:42:21", "remaining_time": "7:22:02", "throughput": 4559.87, "total_tokens": 11588000} {"current_steps": 5365, "total_steps": 61300, "loss": 0.3838, "lr": 4.375203915171289e-05, "epoch": 0.8752039151712887, "percentage": 8.75, "elapsed_time": "0:42:23", "remaining_time": "7:22:00", "throughput": 4560.06, "total_tokens": 11599520} {"current_steps": 5370, "total_steps": 61300, "loss": 0.3588, "lr": 4.3792822185970636e-05, "epoch": 0.8760195758564437, "percentage": 8.76, "elapsed_time": "0:42:26", "remaining_time": "7:21:58", "throughput": 4560.26, "total_tokens": 11611168} {"current_steps": 5375, "total_steps": 61300, "loss": 0.3495, "lr": 4.3833605220228384e-05, "epoch": 0.8768352365415987, "percentage": 8.77, "elapsed_time": "0:42:28", "remaining_time": "7:21:54", "throughput": 4560.46, "total_tokens": 11621632} {"current_steps": 5380, "total_steps": 61300, "loss": 0.3574, "lr": 4.387438825448614e-05, "epoch": 0.8776508972267537, "percentage": 8.78, "elapsed_time": "0:42:30", "remaining_time": "7:21:50", "throughput": 4560.73, "total_tokens": 11632160} {"current_steps": 5385, "total_steps": 61300, "loss": 0.3654, "lr": 4.3915171288743886e-05, "epoch": 0.8784665579119086, "percentage": 8.78, "elapsed_time": "0:42:32", "remaining_time": "7:21:43", "throughput": 4560.84, "total_tokens": 11641344} {"current_steps": 5390, "total_steps": 61300, "loss": 0.3195, "lr": 4.395595432300163e-05, "epoch": 0.8792822185970636, "percentage": 8.79, "elapsed_time": "0:42:34", "remaining_time": "7:21:39", "throughput": 4561.12, "total_tokens": 11652128} {"current_steps": 5395, "total_steps": 61300, "loss": 0.2802, "lr": 4.399673735725938e-05, "epoch": 0.8800978792822186, "percentage": 8.8, "elapsed_time": "0:42:36", "remaining_time": "7:21:34", "throughput": 4561.35, "total_tokens": 11662528} {"current_steps": 5400, "total_steps": 61300, "loss": 0.3175, "lr": 4.403752039151713e-05, "epoch": 0.8809135399673735, "percentage": 8.81, "elapsed_time": "0:42:38", "remaining_time": "7:21:29", "throughput": 4561.52, "total_tokens": 11672544} {"current_steps": 5405, "total_steps": 61300, "loss": 0.3741, "lr": 4.407830342577488e-05, "epoch": 0.8817292006525286, "percentage": 8.82, "elapsed_time": "0:42:41", "remaining_time": "7:21:25", "throughput": 4561.82, "total_tokens": 11683552} {"current_steps": 5410, "total_steps": 61300, "loss": 0.3798, "lr": 4.4119086460032624e-05, "epoch": 0.8825448613376835, "percentage": 8.83, "elapsed_time": "0:42:43", "remaining_time": "7:21:20", "throughput": 4562.02, "total_tokens": 11693408} {"current_steps": 5415, "total_steps": 61300, "loss": 0.3322, "lr": 4.415986949429038e-05, "epoch": 0.8833605220228385, "percentage": 8.83, "elapsed_time": "0:42:45", "remaining_time": "7:21:16", "throughput": 4562.23, "total_tokens": 11704160} {"current_steps": 5420, "total_steps": 61300, "loss": 0.389, "lr": 4.4200652528548126e-05, "epoch": 0.8841761827079935, "percentage": 8.84, "elapsed_time": "0:42:47", "remaining_time": "7:21:12", "throughput": 4562.44, "total_tokens": 11714752} {"current_steps": 5425, "total_steps": 61300, "loss": 0.3487, "lr": 4.424143556280588e-05, "epoch": 0.8849918433931484, "percentage": 8.85, "elapsed_time": "0:42:49", "remaining_time": "7:21:08", "throughput": 4562.61, "total_tokens": 11725408} {"current_steps": 5430, "total_steps": 61300, "loss": 0.4798, "lr": 4.428221859706362e-05, "epoch": 0.8858075040783034, "percentage": 8.86, "elapsed_time": "0:42:52", "remaining_time": "7:21:05", "throughput": 4562.85, "total_tokens": 11736640} {"current_steps": 5435, "total_steps": 61300, "loss": 0.2994, "lr": 4.432300163132137e-05, "epoch": 0.8866231647634584, "percentage": 8.87, "elapsed_time": "0:42:54", "remaining_time": "7:21:01", "throughput": 4563.0, "total_tokens": 11747008} {"current_steps": 5440, "total_steps": 61300, "loss": 0.3521, "lr": 4.436378466557912e-05, "epoch": 0.8874388254486134, "percentage": 8.87, "elapsed_time": "0:42:56", "remaining_time": "7:20:58", "throughput": 4563.16, "total_tokens": 11757728} {"current_steps": 5445, "total_steps": 61300, "loss": 0.4041, "lr": 4.440456769983687e-05, "epoch": 0.8882544861337683, "percentage": 8.88, "elapsed_time": "0:42:58", "remaining_time": "7:20:54", "throughput": 4563.4, "total_tokens": 11768704} {"current_steps": 5450, "total_steps": 61300, "loss": 0.3915, "lr": 4.444535073409462e-05, "epoch": 0.8890701468189234, "percentage": 8.89, "elapsed_time": "0:43:01", "remaining_time": "7:20:52", "throughput": 4563.63, "total_tokens": 11780288} {"current_steps": 5455, "total_steps": 61300, "loss": 0.3794, "lr": 4.4486133768352366e-05, "epoch": 0.8898858075040783, "percentage": 8.9, "elapsed_time": "0:43:03", "remaining_time": "7:20:47", "throughput": 4563.82, "total_tokens": 11790080} {"current_steps": 5460, "total_steps": 61300, "loss": 0.3769, "lr": 4.4526916802610114e-05, "epoch": 0.8907014681892332, "percentage": 8.91, "elapsed_time": "0:43:05", "remaining_time": "7:20:45", "throughput": 4564.11, "total_tokens": 11801952} {"current_steps": 5465, "total_steps": 61300, "loss": 0.339, "lr": 4.456769983686787e-05, "epoch": 0.8915171288743883, "percentage": 8.92, "elapsed_time": "0:43:07", "remaining_time": "7:20:39", "throughput": 4564.28, "total_tokens": 11811520} {"current_steps": 5470, "total_steps": 61300, "loss": 0.3195, "lr": 4.460848287112561e-05, "epoch": 0.8923327895595432, "percentage": 8.92, "elapsed_time": "0:43:10", "remaining_time": "7:20:35", "throughput": 4564.45, "total_tokens": 11822240} {"current_steps": 5475, "total_steps": 61300, "loss": 0.3629, "lr": 4.4649265905383364e-05, "epoch": 0.8931484502446982, "percentage": 8.93, "elapsed_time": "0:43:12", "remaining_time": "7:20:33", "throughput": 4564.72, "total_tokens": 11833632} {"current_steps": 5480, "total_steps": 61300, "loss": 0.3585, "lr": 4.469004893964111e-05, "epoch": 0.8939641109298532, "percentage": 8.94, "elapsed_time": "0:43:14", "remaining_time": "7:20:30", "throughput": 4564.92, "total_tokens": 11844640} {"current_steps": 5485, "total_steps": 61300, "loss": 0.3857, "lr": 4.4730831973898866e-05, "epoch": 0.8947797716150081, "percentage": 8.95, "elapsed_time": "0:43:16", "remaining_time": "7:20:26", "throughput": 4565.18, "total_tokens": 11855776} {"current_steps": 5490, "total_steps": 61300, "loss": 0.3322, "lr": 4.4771615008156607e-05, "epoch": 0.8955954323001631, "percentage": 8.96, "elapsed_time": "0:43:19", "remaining_time": "7:20:21", "throughput": 4565.39, "total_tokens": 11865856} {"current_steps": 5495, "total_steps": 61300, "loss": 0.3931, "lr": 4.4812398042414354e-05, "epoch": 0.8964110929853181, "percentage": 8.96, "elapsed_time": "0:43:21", "remaining_time": "7:20:19", "throughput": 4565.71, "total_tokens": 11877504} {"current_steps": 5500, "total_steps": 61300, "loss": 0.2998, "lr": 4.485318107667211e-05, "epoch": 0.8972267536704731, "percentage": 8.97, "elapsed_time": "0:43:23", "remaining_time": "7:20:15", "throughput": 4565.89, "total_tokens": 11888320} {"current_steps": 5505, "total_steps": 61300, "loss": 0.3533, "lr": 4.4893964110929856e-05, "epoch": 0.898042414355628, "percentage": 8.98, "elapsed_time": "0:43:26", "remaining_time": "7:20:12", "throughput": 4566.13, "total_tokens": 11899456} {"current_steps": 5510, "total_steps": 61300, "loss": 0.2963, "lr": 4.4934747145187604e-05, "epoch": 0.8988580750407831, "percentage": 8.99, "elapsed_time": "0:43:28", "remaining_time": "7:20:09", "throughput": 4566.3, "total_tokens": 11910240} {"current_steps": 5515, "total_steps": 61300, "loss": 0.3671, "lr": 4.497553017944535e-05, "epoch": 0.899673735725938, "percentage": 9.0, "elapsed_time": "0:43:30", "remaining_time": "7:20:04", "throughput": 4566.52, "total_tokens": 11920512} {"current_steps": 5520, "total_steps": 61300, "loss": 0.3417, "lr": 4.5016313213703106e-05, "epoch": 0.9004893964110929, "percentage": 9.0, "elapsed_time": "0:43:32", "remaining_time": "7:19:59", "throughput": 4566.7, "total_tokens": 11930592} {"current_steps": 5525, "total_steps": 61300, "loss": 0.4213, "lr": 4.5057096247960854e-05, "epoch": 0.901305057096248, "percentage": 9.01, "elapsed_time": "0:43:34", "remaining_time": "7:19:55", "throughput": 4566.95, "total_tokens": 11941088} {"current_steps": 5530, "total_steps": 61300, "loss": 0.3239, "lr": 4.5097879282218594e-05, "epoch": 0.9021207177814029, "percentage": 9.02, "elapsed_time": "0:43:36", "remaining_time": "7:19:52", "throughput": 4567.2, "total_tokens": 11952320} {"current_steps": 5535, "total_steps": 61300, "loss": 0.3648, "lr": 4.513866231647635e-05, "epoch": 0.9029363784665579, "percentage": 9.03, "elapsed_time": "0:43:39", "remaining_time": "7:19:48", "throughput": 4567.31, "total_tokens": 11962880} {"current_steps": 5540, "total_steps": 61300, "loss": 0.3738, "lr": 4.5179445350734097e-05, "epoch": 0.9037520391517129, "percentage": 9.04, "elapsed_time": "0:43:41", "remaining_time": "7:19:44", "throughput": 4567.55, "total_tokens": 11973472} {"current_steps": 5545, "total_steps": 61300, "loss": 0.3429, "lr": 4.5220228384991844e-05, "epoch": 0.9045676998368679, "percentage": 9.05, "elapsed_time": "0:43:43", "remaining_time": "7:19:40", "throughput": 4567.69, "total_tokens": 11984096} {"current_steps": 5550, "total_steps": 61300, "loss": 0.3921, "lr": 4.526101141924959e-05, "epoch": 0.9053833605220228, "percentage": 9.05, "elapsed_time": "0:43:46", "remaining_time": "7:19:38", "throughput": 4567.9, "total_tokens": 11995488} {"current_steps": 5555, "total_steps": 61300, "loss": 0.2956, "lr": 4.5301794453507346e-05, "epoch": 0.9061990212071778, "percentage": 9.06, "elapsed_time": "0:43:48", "remaining_time": "7:19:36", "throughput": 4568.1, "total_tokens": 12007104} {"current_steps": 5560, "total_steps": 61300, "loss": 0.4067, "lr": 4.5342577487765094e-05, "epoch": 0.9070146818923328, "percentage": 9.07, "elapsed_time": "0:43:50", "remaining_time": "7:19:34", "throughput": 4568.33, "total_tokens": 12018688} {"current_steps": 5565, "total_steps": 61300, "loss": 0.355, "lr": 4.538336052202284e-05, "epoch": 0.9078303425774877, "percentage": 9.08, "elapsed_time": "0:43:52", "remaining_time": "7:19:28", "throughput": 4568.46, "total_tokens": 12028096} {"current_steps": 5570, "total_steps": 61300, "loss": 0.3711, "lr": 4.542414355628059e-05, "epoch": 0.9086460032626428, "percentage": 9.09, "elapsed_time": "0:43:55", "remaining_time": "7:19:25", "throughput": 4568.67, "total_tokens": 12038976} {"current_steps": 5575, "total_steps": 61300, "loss": 0.3363, "lr": 4.546492659053834e-05, "epoch": 0.9094616639477977, "percentage": 9.09, "elapsed_time": "0:43:57", "remaining_time": "7:19:24", "throughput": 4568.86, "total_tokens": 12050816} {"current_steps": 5580, "total_steps": 61300, "loss": 0.3327, "lr": 4.550570962479609e-05, "epoch": 0.9102773246329527, "percentage": 9.1, "elapsed_time": "0:43:59", "remaining_time": "7:19:21", "throughput": 4569.14, "total_tokens": 12062336} {"current_steps": 5585, "total_steps": 61300, "loss": 0.3591, "lr": 4.554649265905383e-05, "epoch": 0.9110929853181077, "percentage": 9.11, "elapsed_time": "0:44:01", "remaining_time": "7:19:15", "throughput": 4569.35, "total_tokens": 12072096} {"current_steps": 5590, "total_steps": 61300, "loss": 0.3301, "lr": 4.558727569331158e-05, "epoch": 0.9119086460032626, "percentage": 9.12, "elapsed_time": "0:44:04", "remaining_time": "7:19:12", "throughput": 4569.58, "total_tokens": 12083136} {"current_steps": 5595, "total_steps": 61300, "loss": 0.3518, "lr": 4.5628058727569334e-05, "epoch": 0.9127243066884176, "percentage": 9.13, "elapsed_time": "0:44:06", "remaining_time": "7:19:09", "throughput": 4569.79, "total_tokens": 12094272} {"current_steps": 5600, "total_steps": 61300, "loss": 0.4061, "lr": 4.566884176182708e-05, "epoch": 0.9135399673735726, "percentage": 9.14, "elapsed_time": "0:44:08", "remaining_time": "7:19:06", "throughput": 4569.97, "total_tokens": 12105280} {"current_steps": 5605, "total_steps": 61300, "loss": 0.3355, "lr": 4.570962479608483e-05, "epoch": 0.9143556280587276, "percentage": 9.14, "elapsed_time": "0:44:11", "remaining_time": "7:19:02", "throughput": 4570.2, "total_tokens": 12115968} {"current_steps": 5610, "total_steps": 61300, "loss": 0.3903, "lr": 4.575040783034258e-05, "epoch": 0.9151712887438825, "percentage": 9.15, "elapsed_time": "0:44:13", "remaining_time": "7:19:00", "throughput": 4570.42, "total_tokens": 12127136} {"current_steps": 5615, "total_steps": 61300, "loss": 0.3196, "lr": 4.579119086460033e-05, "epoch": 0.9159869494290375, "percentage": 9.16, "elapsed_time": "0:44:15", "remaining_time": "7:18:54", "throughput": 4570.54, "total_tokens": 12136704} {"current_steps": 5620, "total_steps": 61300, "loss": 0.3595, "lr": 4.583197389885808e-05, "epoch": 0.9168026101141925, "percentage": 9.17, "elapsed_time": "0:44:17", "remaining_time": "7:18:49", "throughput": 4570.75, "total_tokens": 12146784} {"current_steps": 5625, "total_steps": 61300, "loss": 0.3492, "lr": 4.587275693311583e-05, "epoch": 0.9176182707993474, "percentage": 9.18, "elapsed_time": "0:44:19", "remaining_time": "7:18:45", "throughput": 4570.93, "total_tokens": 12157248} {"current_steps": 5630, "total_steps": 61300, "loss": 0.3909, "lr": 4.5913539967373574e-05, "epoch": 0.9184339314845025, "percentage": 9.18, "elapsed_time": "0:44:21", "remaining_time": "7:18:41", "throughput": 4571.19, "total_tokens": 12168256} {"current_steps": 5635, "total_steps": 61300, "loss": 0.3657, "lr": 4.595432300163132e-05, "epoch": 0.9192495921696574, "percentage": 9.19, "elapsed_time": "0:44:23", "remaining_time": "7:18:35", "throughput": 4571.34, "total_tokens": 12177760} {"current_steps": 5640, "total_steps": 61300, "loss": 0.3529, "lr": 4.5995106035889077e-05, "epoch": 0.9200652528548124, "percentage": 9.2, "elapsed_time": "0:44:26", "remaining_time": "7:18:30", "throughput": 4571.58, "total_tokens": 12188192} {"current_steps": 5645, "total_steps": 61300, "loss": 0.3922, "lr": 4.603588907014682e-05, "epoch": 0.9208809135399674, "percentage": 9.21, "elapsed_time": "0:44:28", "remaining_time": "7:18:27", "throughput": 4571.72, "total_tokens": 12198880} {"current_steps": 5650, "total_steps": 61300, "loss": 0.3915, "lr": 4.607667210440457e-05, "epoch": 0.9216965742251223, "percentage": 9.22, "elapsed_time": "0:44:30", "remaining_time": "7:18:21", "throughput": 4571.96, "total_tokens": 12208800} {"current_steps": 5655, "total_steps": 61300, "loss": 0.3573, "lr": 4.611745513866232e-05, "epoch": 0.9225122349102773, "percentage": 9.23, "elapsed_time": "0:44:32", "remaining_time": "7:18:17", "throughput": 4572.15, "total_tokens": 12219360} {"current_steps": 5660, "total_steps": 61300, "loss": 0.3247, "lr": 4.615823817292007e-05, "epoch": 0.9233278955954323, "percentage": 9.23, "elapsed_time": "0:44:34", "remaining_time": "7:18:12", "throughput": 4572.32, "total_tokens": 12229376} {"current_steps": 5665, "total_steps": 61300, "loss": 0.3703, "lr": 4.6199021207177815e-05, "epoch": 0.9241435562805873, "percentage": 9.24, "elapsed_time": "0:44:37", "remaining_time": "7:18:11", "throughput": 4572.53, "total_tokens": 12241152} {"current_steps": 5670, "total_steps": 61300, "loss": 0.3879, "lr": 4.623980424143556e-05, "epoch": 0.9249592169657422, "percentage": 9.25, "elapsed_time": "0:44:39", "remaining_time": "7:18:08", "throughput": 4572.66, "total_tokens": 12252192} {"current_steps": 5675, "total_steps": 61300, "loss": 0.3329, "lr": 4.628058727569332e-05, "epoch": 0.9257748776508973, "percentage": 9.26, "elapsed_time": "0:44:41", "remaining_time": "7:18:05", "throughput": 4572.84, "total_tokens": 12262848} {"current_steps": 5680, "total_steps": 61300, "loss": 0.3743, "lr": 4.6321370309951064e-05, "epoch": 0.9265905383360522, "percentage": 9.27, "elapsed_time": "0:44:43", "remaining_time": "7:18:02", "throughput": 4572.99, "total_tokens": 12273728} {"current_steps": 5685, "total_steps": 61300, "loss": 0.3508, "lr": 4.636215334420881e-05, "epoch": 0.9274061990212071, "percentage": 9.27, "elapsed_time": "0:44:46", "remaining_time": "7:17:58", "throughput": 4573.21, "total_tokens": 12284512} {"current_steps": 5690, "total_steps": 61300, "loss": 0.3953, "lr": 4.640293637846656e-05, "epoch": 0.9282218597063622, "percentage": 9.28, "elapsed_time": "0:44:48", "remaining_time": "7:17:56", "throughput": 4573.43, "total_tokens": 12295968} {"current_steps": 5695, "total_steps": 61300, "loss": 0.3601, "lr": 4.644371941272431e-05, "epoch": 0.9290375203915171, "percentage": 9.29, "elapsed_time": "0:44:50", "remaining_time": "7:17:53", "throughput": 4573.72, "total_tokens": 12307616} {"current_steps": 5700, "total_steps": 61300, "loss": 0.3605, "lr": 4.648450244698206e-05, "epoch": 0.9298531810766721, "percentage": 9.3, "elapsed_time": "0:44:53", "remaining_time": "7:17:50", "throughput": 4573.88, "total_tokens": 12318400} {"current_steps": 5705, "total_steps": 61300, "loss": 0.3888, "lr": 4.65252854812398e-05, "epoch": 0.9306688417618271, "percentage": 9.31, "elapsed_time": "0:44:55", "remaining_time": "7:17:47", "throughput": 4574.15, "total_tokens": 12329472} {"current_steps": 5710, "total_steps": 61300, "loss": 0.35, "lr": 4.656606851549756e-05, "epoch": 0.9314845024469821, "percentage": 9.31, "elapsed_time": "0:44:57", "remaining_time": "7:17:43", "throughput": 4574.33, "total_tokens": 12340032} {"current_steps": 5715, "total_steps": 61300, "loss": 0.322, "lr": 4.6606851549755305e-05, "epoch": 0.932300163132137, "percentage": 9.32, "elapsed_time": "0:45:00", "remaining_time": "7:17:41", "throughput": 4574.52, "total_tokens": 12351584} {"current_steps": 5720, "total_steps": 61300, "loss": 0.3257, "lr": 4.664763458401305e-05, "epoch": 0.933115823817292, "percentage": 9.33, "elapsed_time": "0:45:02", "remaining_time": "7:17:38", "throughput": 4574.73, "total_tokens": 12362752} {"current_steps": 5725, "total_steps": 61300, "loss": 0.3903, "lr": 4.66884176182708e-05, "epoch": 0.933931484502447, "percentage": 9.34, "elapsed_time": "0:45:04", "remaining_time": "7:17:37", "throughput": 4575.03, "total_tokens": 12374720} {"current_steps": 5730, "total_steps": 61300, "loss": 0.3754, "lr": 4.672920065252855e-05, "epoch": 0.9347471451876019, "percentage": 9.35, "elapsed_time": "0:45:06", "remaining_time": "7:17:32", "throughput": 4575.19, "total_tokens": 12384896} {"current_steps": 5735, "total_steps": 61300, "loss": 0.4029, "lr": 4.67699836867863e-05, "epoch": 0.935562805872757, "percentage": 9.36, "elapsed_time": "0:45:09", "remaining_time": "7:17:28", "throughput": 4575.42, "total_tokens": 12395808} {"current_steps": 5740, "total_steps": 61300, "loss": 0.3062, "lr": 4.681076672104405e-05, "epoch": 0.9363784665579119, "percentage": 9.36, "elapsed_time": "0:45:11", "remaining_time": "7:17:26", "throughput": 4575.62, "total_tokens": 12406880} {"current_steps": 5745, "total_steps": 61300, "loss": 0.309, "lr": 4.68515497553018e-05, "epoch": 0.9371941272430668, "percentage": 9.37, "elapsed_time": "0:45:13", "remaining_time": "7:17:23", "throughput": 4575.79, "total_tokens": 12418240} {"current_steps": 5750, "total_steps": 61300, "loss": 0.3824, "lr": 4.6892332789559545e-05, "epoch": 0.9380097879282219, "percentage": 9.38, "elapsed_time": "0:45:16", "remaining_time": "7:17:20", "throughput": 4575.97, "total_tokens": 12428896} {"current_steps": 5755, "total_steps": 61300, "loss": 0.355, "lr": 4.693311582381729e-05, "epoch": 0.9388254486133768, "percentage": 9.39, "elapsed_time": "0:45:18", "remaining_time": "7:17:17", "throughput": 4576.16, "total_tokens": 12439872} {"current_steps": 5760, "total_steps": 61300, "loss": 0.3365, "lr": 4.697389885807505e-05, "epoch": 0.9396411092985318, "percentage": 9.4, "elapsed_time": "0:45:20", "remaining_time": "7:17:15", "throughput": 4576.44, "total_tokens": 12451840} {"current_steps": 5765, "total_steps": 61300, "loss": 0.3268, "lr": 4.701468189233279e-05, "epoch": 0.9404567699836868, "percentage": 9.4, "elapsed_time": "0:45:23", "remaining_time": "7:17:13", "throughput": 4576.67, "total_tokens": 12463328} {"current_steps": 5770, "total_steps": 61300, "loss": 0.3718, "lr": 4.705546492659054e-05, "epoch": 0.9412724306688418, "percentage": 9.41, "elapsed_time": "0:45:25", "remaining_time": "7:17:09", "throughput": 4576.86, "total_tokens": 12474080} {"current_steps": 5775, "total_steps": 61300, "loss": 0.3352, "lr": 4.709624796084829e-05, "epoch": 0.9420880913539967, "percentage": 9.42, "elapsed_time": "0:45:27", "remaining_time": "7:17:06", "throughput": 4577.07, "total_tokens": 12484960} {"current_steps": 5780, "total_steps": 61300, "loss": 0.3397, "lr": 4.713703099510604e-05, "epoch": 0.9429037520391517, "percentage": 9.43, "elapsed_time": "0:45:29", "remaining_time": "7:17:02", "throughput": 4577.27, "total_tokens": 12495584} {"current_steps": 5785, "total_steps": 61300, "loss": 0.4122, "lr": 4.7177814029363785e-05, "epoch": 0.9437194127243067, "percentage": 9.44, "elapsed_time": "0:45:31", "remaining_time": "7:16:57", "throughput": 4577.49, "total_tokens": 12505568} {"current_steps": 5790, "total_steps": 61300, "loss": 0.3167, "lr": 4.721859706362153e-05, "epoch": 0.9445350734094616, "percentage": 9.45, "elapsed_time": "0:45:34", "remaining_time": "7:16:53", "throughput": 4577.69, "total_tokens": 12516480} {"current_steps": 5795, "total_steps": 61300, "loss": 0.3453, "lr": 4.725938009787929e-05, "epoch": 0.9453507340946167, "percentage": 9.45, "elapsed_time": "0:45:36", "remaining_time": "7:16:49", "throughput": 4577.92, "total_tokens": 12527136} {"current_steps": 5800, "total_steps": 61300, "loss": 0.3491, "lr": 4.7300163132137035e-05, "epoch": 0.9461663947797716, "percentage": 9.46, "elapsed_time": "0:45:38", "remaining_time": "7:16:45", "throughput": 4578.1, "total_tokens": 12537568} {"current_steps": 5805, "total_steps": 61300, "loss": 0.3899, "lr": 4.734094616639478e-05, "epoch": 0.9469820554649266, "percentage": 9.47, "elapsed_time": "0:45:40", "remaining_time": "7:16:42", "throughput": 4578.34, "total_tokens": 12548736} {"current_steps": 5810, "total_steps": 61300, "loss": 0.3854, "lr": 4.738172920065253e-05, "epoch": 0.9477977161500816, "percentage": 9.48, "elapsed_time": "0:45:43", "remaining_time": "7:16:40", "throughput": 4578.52, "total_tokens": 12560192} {"current_steps": 5815, "total_steps": 61300, "loss": 0.3588, "lr": 4.742251223491028e-05, "epoch": 0.9486133768352365, "percentage": 9.49, "elapsed_time": "0:45:45", "remaining_time": "7:16:36", "throughput": 4578.72, "total_tokens": 12570816} {"current_steps": 5820, "total_steps": 61300, "loss": 0.3447, "lr": 4.7463295269168026e-05, "epoch": 0.9494290375203915, "percentage": 9.49, "elapsed_time": "0:45:47", "remaining_time": "7:16:34", "throughput": 4578.93, "total_tokens": 12582272} {"current_steps": 5825, "total_steps": 61300, "loss": 0.3272, "lr": 4.750407830342577e-05, "epoch": 0.9502446982055465, "percentage": 9.5, "elapsed_time": "0:45:50", "remaining_time": "7:16:33", "throughput": 4579.17, "total_tokens": 12594432} {"current_steps": 5830, "total_steps": 61300, "loss": 0.3343, "lr": 4.754486133768353e-05, "epoch": 0.9510603588907015, "percentage": 9.51, "elapsed_time": "0:45:52", "remaining_time": "7:16:31", "throughput": 4579.38, "total_tokens": 12606048} {"current_steps": 5835, "total_steps": 61300, "loss": 0.3547, "lr": 4.7585644371941275e-05, "epoch": 0.9518760195758564, "percentage": 9.52, "elapsed_time": "0:45:55", "remaining_time": "7:16:28", "throughput": 4579.58, "total_tokens": 12617088} {"current_steps": 5840, "total_steps": 61300, "loss": 0.3718, "lr": 4.762642740619902e-05, "epoch": 0.9526916802610114, "percentage": 9.53, "elapsed_time": "0:45:57", "remaining_time": "7:16:24", "throughput": 4579.79, "total_tokens": 12627808} {"current_steps": 5845, "total_steps": 61300, "loss": 0.3572, "lr": 4.766721044045677e-05, "epoch": 0.9535073409461664, "percentage": 9.54, "elapsed_time": "0:45:59", "remaining_time": "7:16:21", "throughput": 4579.97, "total_tokens": 12638720} {"current_steps": 5850, "total_steps": 61300, "loss": 0.3483, "lr": 4.770799347471452e-05, "epoch": 0.9543230016313213, "percentage": 9.54, "elapsed_time": "0:46:01", "remaining_time": "7:16:16", "throughput": 4580.12, "total_tokens": 12648608} {"current_steps": 5855, "total_steps": 61300, "loss": 0.3641, "lr": 4.774877650897227e-05, "epoch": 0.9551386623164764, "percentage": 9.55, "elapsed_time": "0:46:03", "remaining_time": "7:16:11", "throughput": 4580.32, "total_tokens": 12658944} {"current_steps": 5860, "total_steps": 61300, "loss": 0.3045, "lr": 4.7789559543230014e-05, "epoch": 0.9559543230016313, "percentage": 9.56, "elapsed_time": "0:46:06", "remaining_time": "7:16:08", "throughput": 4580.53, "total_tokens": 12669856} {"current_steps": 5865, "total_steps": 61300, "loss": 0.3503, "lr": 4.783034257748777e-05, "epoch": 0.9567699836867863, "percentage": 9.57, "elapsed_time": "0:46:08", "remaining_time": "7:16:03", "throughput": 4580.74, "total_tokens": 12680096} {"current_steps": 5870, "total_steps": 61300, "loss": 0.3984, "lr": 4.7871125611745516e-05, "epoch": 0.9575856443719413, "percentage": 9.58, "elapsed_time": "0:46:10", "remaining_time": "7:16:00", "throughput": 4580.93, "total_tokens": 12691040} {"current_steps": 5875, "total_steps": 61300, "loss": 0.3232, "lr": 4.791190864600327e-05, "epoch": 0.9584013050570962, "percentage": 9.58, "elapsed_time": "0:46:12", "remaining_time": "7:15:57", "throughput": 4581.12, "total_tokens": 12701728} {"current_steps": 5880, "total_steps": 61300, "loss": 0.3665, "lr": 4.795269168026101e-05, "epoch": 0.9592169657422512, "percentage": 9.59, "elapsed_time": "0:46:14", "remaining_time": "7:15:52", "throughput": 4581.32, "total_tokens": 12712224} {"current_steps": 5885, "total_steps": 61300, "loss": 0.3634, "lr": 4.799347471451876e-05, "epoch": 0.9600326264274062, "percentage": 9.6, "elapsed_time": "0:46:17", "remaining_time": "7:15:50", "throughput": 4581.49, "total_tokens": 12723264} {"current_steps": 5890, "total_steps": 61300, "loss": 0.3555, "lr": 4.803425774877651e-05, "epoch": 0.9608482871125612, "percentage": 9.61, "elapsed_time": "0:46:19", "remaining_time": "7:15:47", "throughput": 4581.65, "total_tokens": 12734400} {"current_steps": 5895, "total_steps": 61300, "loss": 0.3538, "lr": 4.807504078303426e-05, "epoch": 0.9616639477977161, "percentage": 9.62, "elapsed_time": "0:46:21", "remaining_time": "7:15:44", "throughput": 4581.84, "total_tokens": 12745504} {"current_steps": 5900, "total_steps": 61300, "loss": 0.3869, "lr": 4.811582381729201e-05, "epoch": 0.9624796084828712, "percentage": 9.62, "elapsed_time": "0:46:23", "remaining_time": "7:15:39", "throughput": 4582.0, "total_tokens": 12755520} {"current_steps": 5905, "total_steps": 61300, "loss": 0.4005, "lr": 4.8156606851549756e-05, "epoch": 0.9632952691680261, "percentage": 9.63, "elapsed_time": "0:46:26", "remaining_time": "7:15:36", "throughput": 4582.2, "total_tokens": 12766336} {"current_steps": 5910, "total_steps": 61300, "loss": 0.3928, "lr": 4.819738988580751e-05, "epoch": 0.964110929853181, "percentage": 9.64, "elapsed_time": "0:46:28", "remaining_time": "7:15:31", "throughput": 4582.37, "total_tokens": 12776704} {"current_steps": 5915, "total_steps": 61300, "loss": 0.3374, "lr": 4.823817292006526e-05, "epoch": 0.9649265905383361, "percentage": 9.65, "elapsed_time": "0:46:30", "remaining_time": "7:15:29", "throughput": 4582.58, "total_tokens": 12787872} {"current_steps": 5920, "total_steps": 61300, "loss": 0.3709, "lr": 4.8278955954323e-05, "epoch": 0.965742251223491, "percentage": 9.66, "elapsed_time": "0:46:32", "remaining_time": "7:15:25", "throughput": 4582.82, "total_tokens": 12798880} {"current_steps": 5925, "total_steps": 61300, "loss": 0.315, "lr": 4.831973898858075e-05, "epoch": 0.966557911908646, "percentage": 9.67, "elapsed_time": "0:46:35", "remaining_time": "7:15:22", "throughput": 4582.99, "total_tokens": 12809696} {"current_steps": 5930, "total_steps": 61300, "loss": 0.3583, "lr": 4.83605220228385e-05, "epoch": 0.967373572593801, "percentage": 9.67, "elapsed_time": "0:46:37", "remaining_time": "7:15:18", "throughput": 4583.25, "total_tokens": 12820192} {"current_steps": 5935, "total_steps": 61300, "loss": 0.3638, "lr": 4.8401305057096255e-05, "epoch": 0.968189233278956, "percentage": 9.68, "elapsed_time": "0:46:39", "remaining_time": "7:15:17", "throughput": 4583.48, "total_tokens": 12832384} {"current_steps": 5940, "total_steps": 61300, "loss": 0.3679, "lr": 4.8442088091353996e-05, "epoch": 0.9690048939641109, "percentage": 9.69, "elapsed_time": "0:46:42", "remaining_time": "7:15:15", "throughput": 4583.62, "total_tokens": 12843936} {"current_steps": 5945, "total_steps": 61300, "loss": 0.3657, "lr": 4.8482871125611744e-05, "epoch": 0.9698205546492659, "percentage": 9.7, "elapsed_time": "0:46:44", "remaining_time": "7:15:12", "throughput": 4583.76, "total_tokens": 12854752} {"current_steps": 5950, "total_steps": 61300, "loss": 0.3786, "lr": 4.85236541598695e-05, "epoch": 0.9706362153344209, "percentage": 9.71, "elapsed_time": "0:46:46", "remaining_time": "7:15:08", "throughput": 4583.88, "total_tokens": 12865248} {"current_steps": 5955, "total_steps": 61300, "loss": 0.3761, "lr": 4.8564437194127246e-05, "epoch": 0.9714518760195758, "percentage": 9.71, "elapsed_time": "0:46:48", "remaining_time": "7:15:05", "throughput": 4584.12, "total_tokens": 12876128} {"current_steps": 5960, "total_steps": 61300, "loss": 0.3497, "lr": 4.8605220228384994e-05, "epoch": 0.9722675367047309, "percentage": 9.72, "elapsed_time": "0:46:51", "remaining_time": "7:15:01", "throughput": 4584.31, "total_tokens": 12887008} {"current_steps": 5965, "total_steps": 61300, "loss": 0.346, "lr": 4.864600326264274e-05, "epoch": 0.9730831973898858, "percentage": 9.73, "elapsed_time": "0:46:53", "remaining_time": "7:15:00", "throughput": 4584.48, "total_tokens": 12898624} {"current_steps": 5970, "total_steps": 61300, "loss": 0.353, "lr": 4.8686786296900496e-05, "epoch": 0.9738988580750407, "percentage": 9.74, "elapsed_time": "0:46:55", "remaining_time": "7:14:57", "throughput": 4584.74, "total_tokens": 12909888} {"current_steps": 5975, "total_steps": 61300, "loss": 0.3766, "lr": 4.872756933115824e-05, "epoch": 0.9747145187601958, "percentage": 9.75, "elapsed_time": "0:46:57", "remaining_time": "7:14:52", "throughput": 4584.88, "total_tokens": 12920032} {"current_steps": 5980, "total_steps": 61300, "loss": 0.3561, "lr": 4.8768352365415984e-05, "epoch": 0.9755301794453507, "percentage": 9.76, "elapsed_time": "0:47:00", "remaining_time": "7:14:50", "throughput": 4585.04, "total_tokens": 12931392} {"current_steps": 5985, "total_steps": 61300, "loss": 0.383, "lr": 4.880913539967374e-05, "epoch": 0.9763458401305057, "percentage": 9.76, "elapsed_time": "0:47:02", "remaining_time": "7:14:45", "throughput": 4585.18, "total_tokens": 12941472} {"current_steps": 5990, "total_steps": 61300, "loss": 0.3673, "lr": 4.8849918433931486e-05, "epoch": 0.9771615008156607, "percentage": 9.77, "elapsed_time": "0:47:04", "remaining_time": "7:14:42", "throughput": 4585.31, "total_tokens": 12952192} {"current_steps": 5995, "total_steps": 61300, "loss": 0.3561, "lr": 4.8890701468189234e-05, "epoch": 0.9779771615008157, "percentage": 9.78, "elapsed_time": "0:47:07", "remaining_time": "7:14:39", "throughput": 4585.46, "total_tokens": 12963200} {"current_steps": 6000, "total_steps": 61300, "loss": 0.3671, "lr": 4.893148450244698e-05, "epoch": 0.9787928221859706, "percentage": 9.79, "elapsed_time": "0:47:09", "remaining_time": "7:14:34", "throughput": 4585.59, "total_tokens": 12972768} {"current_steps": 6005, "total_steps": 61300, "loss": 0.3568, "lr": 4.8972267536704736e-05, "epoch": 0.9796084828711256, "percentage": 9.8, "elapsed_time": "0:47:11", "remaining_time": "7:14:31", "throughput": 4585.81, "total_tokens": 12984064} {"current_steps": 6010, "total_steps": 61300, "loss": 0.3437, "lr": 4.9013050570962484e-05, "epoch": 0.9804241435562806, "percentage": 9.8, "elapsed_time": "0:47:13", "remaining_time": "7:14:27", "throughput": 4585.9, "total_tokens": 12994336} {"current_steps": 6015, "total_steps": 61300, "loss": 0.3083, "lr": 4.905383360522023e-05, "epoch": 0.9812398042414355, "percentage": 9.81, "elapsed_time": "0:47:15", "remaining_time": "7:14:21", "throughput": 4586.11, "total_tokens": 13004096} {"current_steps": 6020, "total_steps": 61300, "loss": 0.3318, "lr": 4.909461663947798e-05, "epoch": 0.9820554649265906, "percentage": 9.82, "elapsed_time": "0:47:17", "remaining_time": "7:14:19", "throughput": 4586.29, "total_tokens": 13015168} {"current_steps": 6025, "total_steps": 61300, "loss": 0.3574, "lr": 4.9135399673735727e-05, "epoch": 0.9828711256117455, "percentage": 9.83, "elapsed_time": "0:47:20", "remaining_time": "7:14:15", "throughput": 4586.5, "total_tokens": 13026080} {"current_steps": 6030, "total_steps": 61300, "loss": 0.3997, "lr": 4.917618270799348e-05, "epoch": 0.9836867862969005, "percentage": 9.84, "elapsed_time": "0:47:22", "remaining_time": "7:14:13", "throughput": 4586.76, "total_tokens": 13037888} {"current_steps": 6035, "total_steps": 61300, "loss": 0.3945, "lr": 4.921696574225123e-05, "epoch": 0.9845024469820555, "percentage": 9.85, "elapsed_time": "0:47:24", "remaining_time": "7:14:11", "throughput": 4586.97, "total_tokens": 13049440} {"current_steps": 6040, "total_steps": 61300, "loss": 0.3393, "lr": 4.9257748776508976e-05, "epoch": 0.9853181076672104, "percentage": 9.85, "elapsed_time": "0:47:27", "remaining_time": "7:14:08", "throughput": 4587.18, "total_tokens": 13060480} {"current_steps": 6045, "total_steps": 61300, "loss": 0.371, "lr": 4.9298531810766724e-05, "epoch": 0.9861337683523654, "percentage": 9.86, "elapsed_time": "0:47:29", "remaining_time": "7:14:06", "throughput": 4587.33, "total_tokens": 13071584} {"current_steps": 6050, "total_steps": 61300, "loss": 0.3594, "lr": 4.933931484502447e-05, "epoch": 0.9869494290375204, "percentage": 9.87, "elapsed_time": "0:47:31", "remaining_time": "7:14:01", "throughput": 4587.45, "total_tokens": 13081376} {"current_steps": 6055, "total_steps": 61300, "loss": 0.3896, "lr": 4.938009787928222e-05, "epoch": 0.9877650897226754, "percentage": 9.88, "elapsed_time": "0:47:33", "remaining_time": "7:13:58", "throughput": 4587.64, "total_tokens": 13092768} {"current_steps": 6060, "total_steps": 61300, "loss": 0.349, "lr": 4.942088091353997e-05, "epoch": 0.9885807504078303, "percentage": 9.89, "elapsed_time": "0:47:36", "remaining_time": "7:13:56", "throughput": 4587.85, "total_tokens": 13104096} {"current_steps": 6065, "total_steps": 61300, "loss": 0.371, "lr": 4.946166394779772e-05, "epoch": 0.9893964110929854, "percentage": 9.89, "elapsed_time": "0:47:38", "remaining_time": "7:13:54", "throughput": 4588.0, "total_tokens": 13115488} {"current_steps": 6070, "total_steps": 61300, "loss": 0.3958, "lr": 4.950244698205547e-05, "epoch": 0.9902120717781403, "percentage": 9.9, "elapsed_time": "0:47:40", "remaining_time": "7:13:51", "throughput": 4588.25, "total_tokens": 13126752} {"current_steps": 6075, "total_steps": 61300, "loss": 0.3423, "lr": 4.9543230016313217e-05, "epoch": 0.9910277324632952, "percentage": 9.91, "elapsed_time": "0:47:43", "remaining_time": "7:13:48", "throughput": 4588.41, "total_tokens": 13137920} {"current_steps": 6080, "total_steps": 61300, "loss": 0.4234, "lr": 4.9584013050570964e-05, "epoch": 0.9918433931484503, "percentage": 9.92, "elapsed_time": "0:47:45", "remaining_time": "7:13:45", "throughput": 4588.53, "total_tokens": 13148416} {"current_steps": 6085, "total_steps": 61300, "loss": 0.3396, "lr": 4.962479608482871e-05, "epoch": 0.9926590538336052, "percentage": 9.93, "elapsed_time": "0:47:47", "remaining_time": "7:13:39", "throughput": 4588.66, "total_tokens": 13157920} {"current_steps": 6090, "total_steps": 61300, "loss": 0.3633, "lr": 4.9665579119086466e-05, "epoch": 0.9934747145187602, "percentage": 9.93, "elapsed_time": "0:47:49", "remaining_time": "7:13:34", "throughput": 4588.8, "total_tokens": 13167968} {"current_steps": 6095, "total_steps": 61300, "loss": 0.3392, "lr": 4.970636215334421e-05, "epoch": 0.9942903752039152, "percentage": 9.94, "elapsed_time": "0:47:52", "remaining_time": "7:13:33", "throughput": 4588.96, "total_tokens": 13179648} {"current_steps": 6100, "total_steps": 61300, "loss": 0.3397, "lr": 4.974714518760196e-05, "epoch": 0.9951060358890701, "percentage": 9.95, "elapsed_time": "0:47:54", "remaining_time": "7:13:30", "throughput": 4589.13, "total_tokens": 13190656} {"current_steps": 6105, "total_steps": 61300, "loss": 0.3718, "lr": 4.978792822185971e-05, "epoch": 0.9959216965742251, "percentage": 9.96, "elapsed_time": "0:47:56", "remaining_time": "7:13:25", "throughput": 4589.37, "total_tokens": 13201120} {"current_steps": 6110, "total_steps": 61300, "loss": 0.3701, "lr": 4.982871125611746e-05, "epoch": 0.9967373572593801, "percentage": 9.97, "elapsed_time": "0:47:58", "remaining_time": "7:13:22", "throughput": 4589.57, "total_tokens": 13211744} {"current_steps": 6115, "total_steps": 61300, "loss": 0.3751, "lr": 4.9869494290375205e-05, "epoch": 0.9975530179445351, "percentage": 9.98, "elapsed_time": "0:48:00", "remaining_time": "7:13:19", "throughput": 4589.75, "total_tokens": 13222752} {"current_steps": 6120, "total_steps": 61300, "loss": 0.3447, "lr": 4.991027732463295e-05, "epoch": 0.99836867862969, "percentage": 9.98, "elapsed_time": "0:48:03", "remaining_time": "7:13:16", "throughput": 4589.89, "total_tokens": 13233696} {"current_steps": 6125, "total_steps": 61300, "loss": 0.3509, "lr": 4.9951060358890707e-05, "epoch": 0.9991843393148451, "percentage": 9.99, "elapsed_time": "0:48:05", "remaining_time": "7:13:14", "throughput": 4590.09, "total_tokens": 13245504} {"current_steps": 6130, "total_steps": 61300, "loss": 0.3074, "lr": 4.9991843393148454e-05, "epoch": 1.0, "percentage": 10.0, "elapsed_time": "0:48:07", "remaining_time": "7:13:10", "throughput": 4590.15, "total_tokens": 13255424} {"current_steps": 6130, "total_steps": 61300, "eval_loss": 0.35445061326026917, "epoch": 1.0, "percentage": 10.0, "elapsed_time": "0:50:19", "remaining_time": "7:32:56", "throughput": 4389.78, "total_tokens": 13255424} {"current_steps": 6135, "total_steps": 61300, "loss": 0.3585, "lr": 4.999999935147941e-05, "epoch": 1.000815660685155, "percentage": 10.01, "elapsed_time": "0:50:22", "remaining_time": "7:33:02", "throughput": 4388.39, "total_tokens": 13265952} {"current_steps": 6140, "total_steps": 61300, "loss": 0.3548, "lr": 4.999999671686456e-05, "epoch": 1.0016313213703099, "percentage": 10.02, "elapsed_time": "0:50:25", "remaining_time": "7:32:57", "throughput": 4388.76, "total_tokens": 13276768} {"current_steps": 6145, "total_steps": 61300, "loss": 0.3469, "lr": 4.999999205562312e-05, "epoch": 1.002446982055465, "percentage": 10.02, "elapsed_time": "0:50:27", "remaining_time": "7:32:53", "throughput": 4389.05, "total_tokens": 13287776} {"current_steps": 6150, "total_steps": 61300, "loss": 0.3332, "lr": 4.999998536775549e-05, "epoch": 1.00326264274062, "percentage": 10.03, "elapsed_time": "0:50:29", "remaining_time": "7:32:50", "throughput": 4389.46, "total_tokens": 13299488} {"current_steps": 6155, "total_steps": 61300, "loss": 0.3719, "lr": 4.9999976653262184e-05, "epoch": 1.004078303425775, "percentage": 10.04, "elapsed_time": "0:50:32", "remaining_time": "7:32:45", "throughput": 4389.79, "total_tokens": 13310208} {"current_steps": 6160, "total_steps": 61300, "loss": 0.3348, "lr": 4.999996591214392e-05, "epoch": 1.0048939641109298, "percentage": 10.05, "elapsed_time": "0:50:34", "remaining_time": "7:32:39", "throughput": 4390.07, "total_tokens": 13319904} {"current_steps": 6165, "total_steps": 61300, "loss": 0.3651, "lr": 4.999995314440158e-05, "epoch": 1.0057096247960848, "percentage": 10.06, "elapsed_time": "0:50:36", "remaining_time": "7:32:34", "throughput": 4390.34, "total_tokens": 13330528} {"current_steps": 6170, "total_steps": 61300, "loss": 0.3133, "lr": 4.999993835003618e-05, "epoch": 1.0065252854812399, "percentage": 10.07, "elapsed_time": "0:50:38", "remaining_time": "7:32:30", "throughput": 4390.67, "total_tokens": 13341760} {"current_steps": 6175, "total_steps": 61300, "loss": 0.3592, "lr": 4.9999921529048945e-05, "epoch": 1.0073409461663947, "percentage": 10.07, "elapsed_time": "0:50:40", "remaining_time": "7:32:25", "throughput": 4391.05, "total_tokens": 13352448} {"current_steps": 6180, "total_steps": 61300, "loss": 0.3558, "lr": 4.9999902681441205e-05, "epoch": 1.0081566068515497, "percentage": 10.08, "elapsed_time": "0:50:43", "remaining_time": "7:32:21", "throughput": 4391.38, "total_tokens": 13363296} {"current_steps": 6185, "total_steps": 61300, "loss": 0.378, "lr": 4.9999881807214515e-05, "epoch": 1.0089722675367048, "percentage": 10.09, "elapsed_time": "0:50:45", "remaining_time": "7:32:17", "throughput": 4391.7, "total_tokens": 13374368} {"current_steps": 6190, "total_steps": 61300, "loss": 0.333, "lr": 4.9999858906370553e-05, "epoch": 1.0097879282218598, "percentage": 10.1, "elapsed_time": "0:50:47", "remaining_time": "7:32:13", "throughput": 4392.03, "total_tokens": 13385184} {"current_steps": 6195, "total_steps": 61300, "loss": 0.329, "lr": 4.9999833978911185e-05, "epoch": 1.0106035889070146, "percentage": 10.11, "elapsed_time": "0:50:49", "remaining_time": "7:32:07", "throughput": 4392.3, "total_tokens": 13395104} {"current_steps": 6200, "total_steps": 61300, "loss": 0.4006, "lr": 4.999980702483842e-05, "epoch": 1.0114192495921697, "percentage": 10.11, "elapsed_time": "0:50:51", "remaining_time": "7:32:02", "throughput": 4392.64, "total_tokens": 13406080} {"current_steps": 6205, "total_steps": 61300, "loss": 0.3647, "lr": 4.999977804415446e-05, "epoch": 1.0122349102773247, "percentage": 10.12, "elapsed_time": "0:50:54", "remaining_time": "7:32:00", "throughput": 4392.97, "total_tokens": 13417952} {"current_steps": 6210, "total_steps": 61300, "loss": 0.3519, "lr": 4.999974703686164e-05, "epoch": 1.0130505709624795, "percentage": 10.13, "elapsed_time": "0:50:56", "remaining_time": "7:31:55", "throughput": 4393.25, "total_tokens": 13428512} {"current_steps": 6215, "total_steps": 61300, "loss": 0.3602, "lr": 4.9999714002962474e-05, "epoch": 1.0138662316476346, "percentage": 10.14, "elapsed_time": "0:50:58", "remaining_time": "7:31:52", "throughput": 4393.57, "total_tokens": 13439648} {"current_steps": 6220, "total_steps": 61300, "loss": 0.3416, "lr": 4.999967894245965e-05, "epoch": 1.0146818923327896, "percentage": 10.15, "elapsed_time": "0:51:01", "remaining_time": "7:31:49", "throughput": 4393.91, "total_tokens": 13451520} {"current_steps": 6225, "total_steps": 61300, "loss": 0.3157, "lr": 4.9999641855355995e-05, "epoch": 1.0154975530179446, "percentage": 10.15, "elapsed_time": "0:51:03", "remaining_time": "7:31:41", "throughput": 4394.22, "total_tokens": 13460480} {"current_steps": 6230, "total_steps": 61300, "loss": 0.3447, "lr": 4.999960274165453e-05, "epoch": 1.0163132137030995, "percentage": 10.16, "elapsed_time": "0:51:05", "remaining_time": "7:31:37", "throughput": 4394.53, "total_tokens": 13471328} {"current_steps": 6235, "total_steps": 61300, "loss": 0.3147, "lr": 4.999956160135842e-05, "epoch": 1.0171288743882545, "percentage": 10.17, "elapsed_time": "0:51:07", "remaining_time": "7:31:32", "throughput": 4394.81, "total_tokens": 13482048} {"current_steps": 6240, "total_steps": 61300, "loss": 0.4209, "lr": 4.999951843447099e-05, "epoch": 1.0179445350734095, "percentage": 10.18, "elapsed_time": "0:51:09", "remaining_time": "7:31:28", "throughput": 4395.07, "total_tokens": 13492512} {"current_steps": 6245, "total_steps": 61300, "loss": 0.3404, "lr": 4.999947324099576e-05, "epoch": 1.0187601957585644, "percentage": 10.19, "elapsed_time": "0:51:12", "remaining_time": "7:31:25", "throughput": 4395.39, "total_tokens": 13504000} {"current_steps": 6250, "total_steps": 61300, "loss": 0.3514, "lr": 4.999942602093638e-05, "epoch": 1.0195758564437194, "percentage": 10.2, "elapsed_time": "0:51:14", "remaining_time": "7:31:20", "throughput": 4395.69, "total_tokens": 13514784} {"current_steps": 6255, "total_steps": 61300, "loss": 0.3252, "lr": 4.999937677429669e-05, "epoch": 1.0203915171288744, "percentage": 10.2, "elapsed_time": "0:51:16", "remaining_time": "7:31:15", "throughput": 4395.98, "total_tokens": 13525376} {"current_steps": 6260, "total_steps": 61300, "loss": 0.3453, "lr": 4.9999325501080666e-05, "epoch": 1.0212071778140293, "percentage": 10.21, "elapsed_time": "0:51:18", "remaining_time": "7:31:11", "throughput": 4396.25, "total_tokens": 13535872} {"current_steps": 6265, "total_steps": 61300, "loss": 0.3837, "lr": 4.999927220129247e-05, "epoch": 1.0220228384991843, "percentage": 10.22, "elapsed_time": "0:51:21", "remaining_time": "7:31:06", "throughput": 4396.52, "total_tokens": 13546464} {"current_steps": 6270, "total_steps": 61300, "loss": 0.3843, "lr": 4.9999216874936426e-05, "epoch": 1.0228384991843393, "percentage": 10.23, "elapsed_time": "0:51:23", "remaining_time": "7:30:59", "throughput": 4396.81, "total_tokens": 13555936} {"current_steps": 6275, "total_steps": 61300, "loss": 0.3643, "lr": 4.9999159522017015e-05, "epoch": 1.0236541598694944, "percentage": 10.24, "elapsed_time": "0:51:25", "remaining_time": "7:30:55", "throughput": 4397.09, "total_tokens": 13566528} {"current_steps": 6280, "total_steps": 61300, "loss": 0.3582, "lr": 4.999910014253889e-05, "epoch": 1.0244698205546492, "percentage": 10.24, "elapsed_time": "0:51:27", "remaining_time": "7:30:50", "throughput": 4397.37, "total_tokens": 13577152} {"current_steps": 6285, "total_steps": 61300, "loss": 0.3663, "lr": 4.999903873650687e-05, "epoch": 1.0252854812398042, "percentage": 10.25, "elapsed_time": "0:51:29", "remaining_time": "7:30:47", "throughput": 4397.72, "total_tokens": 13588704} {"current_steps": 6290, "total_steps": 61300, "loss": 0.3455, "lr": 4.999897530392591e-05, "epoch": 1.0261011419249593, "percentage": 10.26, "elapsed_time": "0:51:32", "remaining_time": "7:30:42", "throughput": 4398.06, "total_tokens": 13599552} {"current_steps": 6295, "total_steps": 61300, "loss": 0.3921, "lr": 4.9998909844801176e-05, "epoch": 1.026916802610114, "percentage": 10.27, "elapsed_time": "0:51:34", "remaining_time": "7:30:40", "throughput": 4398.38, "total_tokens": 13611264} {"current_steps": 6300, "total_steps": 61300, "loss": 0.3704, "lr": 4.999884235913797e-05, "epoch": 1.0277324632952691, "percentage": 10.28, "elapsed_time": "0:51:36", "remaining_time": "7:30:35", "throughput": 4398.68, "total_tokens": 13621760} {"current_steps": 6305, "total_steps": 61300, "loss": 0.3658, "lr": 4.999877284694177e-05, "epoch": 1.0285481239804242, "percentage": 10.29, "elapsed_time": "0:51:39", "remaining_time": "7:30:31", "throughput": 4398.95, "total_tokens": 13632672} {"current_steps": 6310, "total_steps": 61300, "loss": 0.3301, "lr": 4.999870130821818e-05, "epoch": 1.0293637846655792, "percentage": 10.29, "elapsed_time": "0:51:41", "remaining_time": "7:30:27", "throughput": 4399.26, "total_tokens": 13643584} {"current_steps": 6315, "total_steps": 61300, "loss": 0.3474, "lr": 4.9998627742973025e-05, "epoch": 1.030179445350734, "percentage": 10.3, "elapsed_time": "0:51:43", "remaining_time": "7:30:25", "throughput": 4399.57, "total_tokens": 13655488} {"current_steps": 6320, "total_steps": 61300, "loss": 0.3443, "lr": 4.9998552151212276e-05, "epoch": 1.030995106035889, "percentage": 10.31, "elapsed_time": "0:51:46", "remaining_time": "7:30:21", "throughput": 4399.86, "total_tokens": 13666368} {"current_steps": 6325, "total_steps": 61300, "loss": 0.3187, "lr": 4.999847453294204e-05, "epoch": 1.031810766721044, "percentage": 10.32, "elapsed_time": "0:51:48", "remaining_time": "7:30:18", "throughput": 4400.15, "total_tokens": 13678048} {"current_steps": 6330, "total_steps": 61300, "loss": 0.3539, "lr": 4.999839488816861e-05, "epoch": 1.032626427406199, "percentage": 10.33, "elapsed_time": "0:51:50", "remaining_time": "7:30:14", "throughput": 4400.46, "total_tokens": 13689024} {"current_steps": 6335, "total_steps": 61300, "loss": 0.3739, "lr": 4.9998313216898454e-05, "epoch": 1.033442088091354, "percentage": 10.33, "elapsed_time": "0:51:53", "remaining_time": "7:30:10", "throughput": 4400.76, "total_tokens": 13699744} {"current_steps": 6340, "total_steps": 61300, "loss": 0.3333, "lr": 4.99982295191382e-05, "epoch": 1.034257748776509, "percentage": 10.34, "elapsed_time": "0:51:55", "remaining_time": "7:30:04", "throughput": 4401.02, "total_tokens": 13710016} {"current_steps": 6345, "total_steps": 61300, "loss": 0.3382, "lr": 4.99981437948946e-05, "epoch": 1.035073409461664, "percentage": 10.35, "elapsed_time": "0:51:57", "remaining_time": "7:30:01", "throughput": 4401.4, "total_tokens": 13721664} {"current_steps": 6350, "total_steps": 61300, "loss": 0.2961, "lr": 4.999805604417464e-05, "epoch": 1.0358890701468189, "percentage": 10.36, "elapsed_time": "0:52:00", "remaining_time": "7:30:01", "throughput": 4401.74, "total_tokens": 13734752} {"current_steps": 6355, "total_steps": 61300, "loss": 0.3391, "lr": 4.999796626698542e-05, "epoch": 1.036704730831974, "percentage": 10.37, "elapsed_time": "0:52:02", "remaining_time": "7:29:57", "throughput": 4401.97, "total_tokens": 13745504} {"current_steps": 6360, "total_steps": 61300, "loss": 0.3596, "lr": 4.999787446333421e-05, "epoch": 1.037520391517129, "percentage": 10.38, "elapsed_time": "0:52:04", "remaining_time": "7:29:53", "throughput": 4402.21, "total_tokens": 13755968} {"current_steps": 6365, "total_steps": 61300, "loss": 0.3763, "lr": 4.999778063322846e-05, "epoch": 1.0383360522022838, "percentage": 10.38, "elapsed_time": "0:52:07", "remaining_time": "7:29:49", "throughput": 4402.54, "total_tokens": 13767296} {"current_steps": 6370, "total_steps": 61300, "loss": 0.3232, "lr": 4.9997684776675775e-05, "epoch": 1.0391517128874388, "percentage": 10.39, "elapsed_time": "0:52:09", "remaining_time": "7:29:46", "throughput": 4402.82, "total_tokens": 13778656} {"current_steps": 6375, "total_steps": 61300, "loss": 0.3465, "lr": 4.999758689368392e-05, "epoch": 1.0399673735725938, "percentage": 10.4, "elapsed_time": "0:52:11", "remaining_time": "7:29:41", "throughput": 4403.09, "total_tokens": 13789216} {"current_steps": 6380, "total_steps": 61300, "loss": 0.4372, "lr": 4.999748698426084e-05, "epoch": 1.0407830342577489, "percentage": 10.41, "elapsed_time": "0:52:13", "remaining_time": "7:29:36", "throughput": 4403.38, "total_tokens": 13799680} {"current_steps": 6385, "total_steps": 61300, "loss": 0.3681, "lr": 4.9997385048414624e-05, "epoch": 1.0415986949429037, "percentage": 10.42, "elapsed_time": "0:52:16", "remaining_time": "7:29:32", "throughput": 4403.73, "total_tokens": 13810720} {"current_steps": 6390, "total_steps": 61300, "loss": 0.3338, "lr": 4.999728108615355e-05, "epoch": 1.0424143556280587, "percentage": 10.42, "elapsed_time": "0:52:18", "remaining_time": "7:29:29", "throughput": 4404.03, "total_tokens": 13821856} {"current_steps": 6395, "total_steps": 61300, "loss": 0.3319, "lr": 4.9997175097486026e-05, "epoch": 1.0432300163132138, "percentage": 10.43, "elapsed_time": "0:52:20", "remaining_time": "7:29:26", "throughput": 4404.39, "total_tokens": 13833984} {"current_steps": 6400, "total_steps": 61300, "loss": 0.3854, "lr": 4.9997067082420655e-05, "epoch": 1.0440456769983686, "percentage": 10.44, "elapsed_time": "0:52:23", "remaining_time": "7:29:22", "throughput": 4404.73, "total_tokens": 13844928} {"current_steps": 6405, "total_steps": 61300, "loss": 0.398, "lr": 4.9996957040966205e-05, "epoch": 1.0448613376835236, "percentage": 10.45, "elapsed_time": "0:52:25", "remaining_time": "7:29:19", "throughput": 4405.04, "total_tokens": 13856384} {"current_steps": 6410, "total_steps": 61300, "loss": 0.3675, "lr": 4.999684497313157e-05, "epoch": 1.0456769983686787, "percentage": 10.46, "elapsed_time": "0:52:27", "remaining_time": "7:29:15", "throughput": 4405.32, "total_tokens": 13867456} {"current_steps": 6415, "total_steps": 61300, "loss": 0.3474, "lr": 4.9996730878925856e-05, "epoch": 1.0464926590538337, "percentage": 10.46, "elapsed_time": "0:52:29", "remaining_time": "7:29:09", "throughput": 4405.61, "total_tokens": 13877216} {"current_steps": 6420, "total_steps": 61300, "loss": 0.3695, "lr": 4.99966147583583e-05, "epoch": 1.0473083197389885, "percentage": 10.47, "elapsed_time": "0:52:32", "remaining_time": "7:29:05", "throughput": 4405.94, "total_tokens": 13888192} {"current_steps": 6425, "total_steps": 61300, "loss": 0.3433, "lr": 4.9996496611438326e-05, "epoch": 1.0481239804241436, "percentage": 10.48, "elapsed_time": "0:52:34", "remaining_time": "7:29:01", "throughput": 4406.29, "total_tokens": 13899072} {"current_steps": 6430, "total_steps": 61300, "loss": 0.3977, "lr": 4.99963764381755e-05, "epoch": 1.0489396411092986, "percentage": 10.49, "elapsed_time": "0:52:36", "remaining_time": "7:28:56", "throughput": 4406.56, "total_tokens": 13909792} {"current_steps": 6435, "total_steps": 61300, "loss": 0.3726, "lr": 4.999625423857958e-05, "epoch": 1.0497553017944534, "percentage": 10.5, "elapsed_time": "0:52:38", "remaining_time": "7:28:52", "throughput": 4406.83, "total_tokens": 13920800} {"current_steps": 6440, "total_steps": 61300, "loss": 0.3599, "lr": 4.999613001266045e-05, "epoch": 1.0505709624796085, "percentage": 10.51, "elapsed_time": "0:52:41", "remaining_time": "7:28:47", "throughput": 4407.05, "total_tokens": 13930976} {"current_steps": 6445, "total_steps": 61300, "loss": 0.2981, "lr": 4.999600376042819e-05, "epoch": 1.0513866231647635, "percentage": 10.51, "elapsed_time": "0:52:43", "remaining_time": "7:28:44", "throughput": 4407.33, "total_tokens": 13942080} {"current_steps": 6450, "total_steps": 61300, "loss": 0.3384, "lr": 4.999587548189305e-05, "epoch": 1.0522022838499185, "percentage": 10.52, "elapsed_time": "0:52:45", "remaining_time": "7:28:39", "throughput": 4407.65, "total_tokens": 13952736} {"current_steps": 6455, "total_steps": 61300, "loss": 0.3403, "lr": 4.99957451770654e-05, "epoch": 1.0530179445350734, "percentage": 10.53, "elapsed_time": "0:52:47", "remaining_time": "7:28:33", "throughput": 4407.89, "total_tokens": 13962400} {"current_steps": 6460, "total_steps": 61300, "loss": 0.2901, "lr": 4.999561284595583e-05, "epoch": 1.0538336052202284, "percentage": 10.54, "elapsed_time": "0:52:50", "remaining_time": "7:28:30", "throughput": 4408.26, "total_tokens": 13974304} {"current_steps": 6465, "total_steps": 61300, "loss": 0.3679, "lr": 4.9995478488575054e-05, "epoch": 1.0546492659053834, "percentage": 10.55, "elapsed_time": "0:52:52", "remaining_time": "7:28:26", "throughput": 4408.57, "total_tokens": 13985248} {"current_steps": 6470, "total_steps": 61300, "loss": 0.3683, "lr": 4.999534210493396e-05, "epoch": 1.0554649265905383, "percentage": 10.55, "elapsed_time": "0:52:54", "remaining_time": "7:28:22", "throughput": 4408.83, "total_tokens": 13995840} {"current_steps": 6475, "total_steps": 61300, "loss": 0.325, "lr": 4.999520369504362e-05, "epoch": 1.0562805872756933, "percentage": 10.56, "elapsed_time": "0:52:56", "remaining_time": "7:28:18", "throughput": 4409.16, "total_tokens": 14007104} {"current_steps": 6480, "total_steps": 61300, "loss": 0.3986, "lr": 4.9995063258915235e-05, "epoch": 1.0570962479608483, "percentage": 10.57, "elapsed_time": "0:52:59", "remaining_time": "7:28:14", "throughput": 4409.47, "total_tokens": 14018144} {"current_steps": 6485, "total_steps": 61300, "loss": 0.3783, "lr": 4.9994920796560205e-05, "epoch": 1.0579119086460032, "percentage": 10.58, "elapsed_time": "0:53:01", "remaining_time": "7:28:10", "throughput": 4409.72, "total_tokens": 14029024} {"current_steps": 6490, "total_steps": 61300, "loss": 0.338, "lr": 4.999477630799007e-05, "epoch": 1.0587275693311582, "percentage": 10.59, "elapsed_time": "0:53:03", "remaining_time": "7:28:07", "throughput": 4410.05, "total_tokens": 14040480} {"current_steps": 6495, "total_steps": 61300, "loss": 0.2895, "lr": 4.999462979321654e-05, "epoch": 1.0595432300163132, "percentage": 10.6, "elapsed_time": "0:53:05", "remaining_time": "7:28:03", "throughput": 4410.29, "total_tokens": 14050976} {"current_steps": 6500, "total_steps": 61300, "loss": 0.3539, "lr": 4.9994481252251506e-05, "epoch": 1.0603588907014683, "percentage": 10.6, "elapsed_time": "0:53:07", "remaining_time": "7:27:56", "throughput": 4410.51, "total_tokens": 14060352} {"current_steps": 6505, "total_steps": 61300, "loss": 0.3445, "lr": 4.999433068510699e-05, "epoch": 1.061174551386623, "percentage": 10.61, "elapsed_time": "0:53:10", "remaining_time": "7:27:53", "throughput": 4410.79, "total_tokens": 14071680} {"current_steps": 6510, "total_steps": 61300, "loss": 0.3588, "lr": 4.999417809179523e-05, "epoch": 1.0619902120717781, "percentage": 10.62, "elapsed_time": "0:53:12", "remaining_time": "7:27:50", "throughput": 4411.09, "total_tokens": 14083296} {"current_steps": 6515, "total_steps": 61300, "loss": 0.3896, "lr": 4.9994023472328555e-05, "epoch": 1.0628058727569332, "percentage": 10.63, "elapsed_time": "0:53:15", "remaining_time": "7:27:47", "throughput": 4411.43, "total_tokens": 14094752} {"current_steps": 6520, "total_steps": 61300, "loss": 0.3395, "lr": 4.999386682671953e-05, "epoch": 1.0636215334420882, "percentage": 10.64, "elapsed_time": "0:53:17", "remaining_time": "7:27:42", "throughput": 4411.72, "total_tokens": 14105088} {"current_steps": 6525, "total_steps": 61300, "loss": 0.3599, "lr": 4.9993708154980836e-05, "epoch": 1.064437194127243, "percentage": 10.64, "elapsed_time": "0:53:19", "remaining_time": "7:27:36", "throughput": 4411.96, "total_tokens": 14114976} {"current_steps": 6530, "total_steps": 61300, "loss": 0.3769, "lr": 4.999354745712534e-05, "epoch": 1.065252854812398, "percentage": 10.65, "elapsed_time": "0:53:21", "remaining_time": "7:27:33", "throughput": 4412.26, "total_tokens": 14126592} {"current_steps": 6535, "total_steps": 61300, "loss": 0.3288, "lr": 4.999338473316607e-05, "epoch": 1.066068515497553, "percentage": 10.66, "elapsed_time": "0:53:24", "remaining_time": "7:27:30", "throughput": 4412.59, "total_tokens": 14138048} {"current_steps": 6540, "total_steps": 61300, "loss": 0.3537, "lr": 4.9993219983116223e-05, "epoch": 1.066884176182708, "percentage": 10.67, "elapsed_time": "0:53:26", "remaining_time": "7:27:25", "throughput": 4412.8, "total_tokens": 14148128} {"current_steps": 6545, "total_steps": 61300, "loss": 0.3226, "lr": 4.999305320698915e-05, "epoch": 1.067699836867863, "percentage": 10.68, "elapsed_time": "0:53:28", "remaining_time": "7:27:23", "throughput": 4413.14, "total_tokens": 14160096} {"current_steps": 6550, "total_steps": 61300, "loss": 0.332, "lr": 4.999288440479837e-05, "epoch": 1.068515497553018, "percentage": 10.69, "elapsed_time": "0:53:30", "remaining_time": "7:27:18", "throughput": 4413.39, "total_tokens": 14170752} {"current_steps": 6555, "total_steps": 61300, "loss": 0.3532, "lr": 4.999271357655757e-05, "epoch": 1.0693311582381728, "percentage": 10.69, "elapsed_time": "0:53:33", "remaining_time": "7:27:15", "throughput": 4413.68, "total_tokens": 14181952} {"current_steps": 6560, "total_steps": 61300, "loss": 0.3245, "lr": 4.999254072228059e-05, "epoch": 1.0701468189233279, "percentage": 10.7, "elapsed_time": "0:53:35", "remaining_time": "7:27:10", "throughput": 4413.93, "total_tokens": 14192384} {"current_steps": 6565, "total_steps": 61300, "loss": 0.3754, "lr": 4.9992365841981456e-05, "epoch": 1.070962479608483, "percentage": 10.71, "elapsed_time": "0:53:37", "remaining_time": "7:27:08", "throughput": 4414.24, "total_tokens": 14204384} {"current_steps": 6570, "total_steps": 61300, "loss": 0.3125, "lr": 4.9992188935674335e-05, "epoch": 1.071778140293638, "percentage": 10.72, "elapsed_time": "0:53:40", "remaining_time": "7:27:05", "throughput": 4414.55, "total_tokens": 14215776} {"current_steps": 6575, "total_steps": 61300, "loss": 0.3983, "lr": 4.999201000337356e-05, "epoch": 1.0725938009787928, "percentage": 10.73, "elapsed_time": "0:53:42", "remaining_time": "7:27:02", "throughput": 4414.89, "total_tokens": 14227520} {"current_steps": 6580, "total_steps": 61300, "loss": 0.358, "lr": 4.999182904509366e-05, "epoch": 1.0734094616639478, "percentage": 10.73, "elapsed_time": "0:53:44", "remaining_time": "7:26:59", "throughput": 4415.2, "total_tokens": 14238976} {"current_steps": 6585, "total_steps": 61300, "loss": 0.3424, "lr": 4.9991646060849285e-05, "epoch": 1.0742251223491028, "percentage": 10.74, "elapsed_time": "0:53:47", "remaining_time": "7:26:54", "throughput": 4415.51, "total_tokens": 14249344} {"current_steps": 6590, "total_steps": 61300, "loss": 0.3992, "lr": 4.9991461050655264e-05, "epoch": 1.0750407830342577, "percentage": 10.75, "elapsed_time": "0:53:49", "remaining_time": "7:26:49", "throughput": 4415.77, "total_tokens": 14259840} {"current_steps": 6595, "total_steps": 61300, "loss": 0.3435, "lr": 4.999127401452662e-05, "epoch": 1.0758564437194127, "percentage": 10.76, "elapsed_time": "0:53:51", "remaining_time": "7:26:46", "throughput": 4416.1, "total_tokens": 14271456} {"current_steps": 6600, "total_steps": 61300, "loss": 0.3735, "lr": 4.999108495247849e-05, "epoch": 1.0766721044045677, "percentage": 10.77, "elapsed_time": "0:53:54", "remaining_time": "7:26:43", "throughput": 4416.37, "total_tokens": 14282688} {"current_steps": 6605, "total_steps": 61300, "loss": 0.3332, "lr": 4.9990893864526214e-05, "epoch": 1.0774877650897228, "percentage": 10.77, "elapsed_time": "0:53:56", "remaining_time": "7:26:39", "throughput": 4416.73, "total_tokens": 14293920} {"current_steps": 6610, "total_steps": 61300, "loss": 0.3384, "lr": 4.9990700750685276e-05, "epoch": 1.0783034257748776, "percentage": 10.78, "elapsed_time": "0:53:58", "remaining_time": "7:26:34", "throughput": 4416.99, "total_tokens": 14304512} {"current_steps": 6615, "total_steps": 61300, "loss": 0.3647, "lr": 4.999050561097134e-05, "epoch": 1.0791190864600326, "percentage": 10.79, "elapsed_time": "0:54:00", "remaining_time": "7:26:31", "throughput": 4417.28, "total_tokens": 14315616} {"current_steps": 6620, "total_steps": 61300, "loss": 0.3154, "lr": 4.999030844540021e-05, "epoch": 1.0799347471451877, "percentage": 10.8, "elapsed_time": "0:54:03", "remaining_time": "7:26:27", "throughput": 4417.5, "total_tokens": 14326400} {"current_steps": 6625, "total_steps": 61300, "loss": 0.3563, "lr": 4.999010925398788e-05, "epoch": 1.0807504078303425, "percentage": 10.81, "elapsed_time": "0:54:05", "remaining_time": "7:26:21", "throughput": 4417.74, "total_tokens": 14336288} {"current_steps": 6630, "total_steps": 61300, "loss": 0.3682, "lr": 4.99899080367505e-05, "epoch": 1.0815660685154975, "percentage": 10.82, "elapsed_time": "0:54:07", "remaining_time": "7:26:18", "throughput": 4418.1, "total_tokens": 14347616} {"current_steps": 6635, "total_steps": 61300, "loss": 0.2994, "lr": 4.9989704793704374e-05, "epoch": 1.0823817292006526, "percentage": 10.82, "elapsed_time": "0:54:09", "remaining_time": "7:26:12", "throughput": 4418.35, "total_tokens": 14357664} {"current_steps": 6640, "total_steps": 61300, "loss": 0.3599, "lr": 4.998949952486598e-05, "epoch": 1.0831973898858076, "percentage": 10.83, "elapsed_time": "0:54:11", "remaining_time": "7:26:06", "throughput": 4418.54, "total_tokens": 14367232} {"current_steps": 6645, "total_steps": 61300, "loss": 0.3385, "lr": 4.998929223025196e-05, "epoch": 1.0840130505709624, "percentage": 10.84, "elapsed_time": "0:54:13", "remaining_time": "7:26:02", "throughput": 4418.82, "total_tokens": 14378048} {"current_steps": 6650, "total_steps": 61300, "loss": 0.3589, "lr": 4.998908290987913e-05, "epoch": 1.0848287112561175, "percentage": 10.85, "elapsed_time": "0:54:16", "remaining_time": "7:25:59", "throughput": 4419.08, "total_tokens": 14389248} {"current_steps": 6655, "total_steps": 61300, "loss": 0.3457, "lr": 4.998887156376443e-05, "epoch": 1.0856443719412725, "percentage": 10.86, "elapsed_time": "0:54:18", "remaining_time": "7:25:54", "throughput": 4419.31, "total_tokens": 14399616} {"current_steps": 6660, "total_steps": 61300, "loss": 0.3506, "lr": 4.998865819192501e-05, "epoch": 1.0864600326264273, "percentage": 10.86, "elapsed_time": "0:54:20", "remaining_time": "7:25:52", "throughput": 4419.68, "total_tokens": 14412000} {"current_steps": 6665, "total_steps": 61300, "loss": 0.3918, "lr": 4.9988442794378166e-05, "epoch": 1.0872756933115824, "percentage": 10.87, "elapsed_time": "0:54:23", "remaining_time": "7:25:49", "throughput": 4420.02, "total_tokens": 14423392} {"current_steps": 6670, "total_steps": 61300, "loss": 0.3698, "lr": 4.998822537114136e-05, "epoch": 1.0880913539967374, "percentage": 10.88, "elapsed_time": "0:54:25", "remaining_time": "7:25:44", "throughput": 4420.29, "total_tokens": 14433792} {"current_steps": 6675, "total_steps": 61300, "loss": 0.3979, "lr": 4.998800592223222e-05, "epoch": 1.0889070146818924, "percentage": 10.89, "elapsed_time": "0:54:27", "remaining_time": "7:25:41", "throughput": 4420.54, "total_tokens": 14445152} {"current_steps": 6680, "total_steps": 61300, "loss": 0.3411, "lr": 4.9987784447668526e-05, "epoch": 1.0897226753670473, "percentage": 10.9, "elapsed_time": "0:54:30", "remaining_time": "7:25:37", "throughput": 4420.78, "total_tokens": 14455968} {"current_steps": 6685, "total_steps": 61300, "loss": 0.3889, "lr": 4.9987560947468245e-05, "epoch": 1.0905383360522023, "percentage": 10.91, "elapsed_time": "0:54:32", "remaining_time": "7:25:32", "throughput": 4420.99, "total_tokens": 14465824} {"current_steps": 6690, "total_steps": 61300, "loss": 0.3269, "lr": 4.998733542164948e-05, "epoch": 1.0913539967373573, "percentage": 10.91, "elapsed_time": "0:54:34", "remaining_time": "7:25:27", "throughput": 4421.25, "total_tokens": 14476480} {"current_steps": 6695, "total_steps": 61300, "loss": 0.3846, "lr": 4.998710787023053e-05, "epoch": 1.0921696574225122, "percentage": 10.92, "elapsed_time": "0:54:36", "remaining_time": "7:25:21", "throughput": 4421.51, "total_tokens": 14486144} {"current_steps": 6700, "total_steps": 61300, "loss": 0.3621, "lr": 4.998687829322983e-05, "epoch": 1.0929853181076672, "percentage": 10.93, "elapsed_time": "0:54:38", "remaining_time": "7:25:18", "throughput": 4421.81, "total_tokens": 14497664} {"current_steps": 6705, "total_steps": 61300, "loss": 0.3345, "lr": 4.9986646690665996e-05, "epoch": 1.0938009787928222, "percentage": 10.94, "elapsed_time": "0:54:41", "remaining_time": "7:25:16", "throughput": 4422.16, "total_tokens": 14509888} {"current_steps": 6710, "total_steps": 61300, "loss": 0.3637, "lr": 4.998641306255779e-05, "epoch": 1.094616639477977, "percentage": 10.95, "elapsed_time": "0:54:43", "remaining_time": "7:25:14", "throughput": 4422.45, "total_tokens": 14521664} {"current_steps": 6715, "total_steps": 61300, "loss": 0.3273, "lr": 4.998617740892417e-05, "epoch": 1.095432300163132, "percentage": 10.95, "elapsed_time": "0:54:45", "remaining_time": "7:25:10", "throughput": 4422.72, "total_tokens": 14532768} {"current_steps": 6720, "total_steps": 61300, "loss": 0.3611, "lr": 4.998593972978423e-05, "epoch": 1.0962479608482871, "percentage": 10.96, "elapsed_time": "0:54:48", "remaining_time": "7:25:07", "throughput": 4423.01, "total_tokens": 14544160} {"current_steps": 6725, "total_steps": 61300, "loss": 0.378, "lr": 4.9985700025157236e-05, "epoch": 1.0970636215334422, "percentage": 10.97, "elapsed_time": "0:54:50", "remaining_time": "7:25:02", "throughput": 4423.19, "total_tokens": 14554112} {"current_steps": 6730, "total_steps": 61300, "loss": 0.4289, "lr": 4.998545829506263e-05, "epoch": 1.097879282218597, "percentage": 10.98, "elapsed_time": "0:54:52", "remaining_time": "7:24:56", "throughput": 4423.47, "total_tokens": 14564096} {"current_steps": 6735, "total_steps": 61300, "loss": 0.3591, "lr": 4.998521453951999e-05, "epoch": 1.098694942903752, "percentage": 10.99, "elapsed_time": "0:54:54", "remaining_time": "7:24:52", "throughput": 4423.68, "total_tokens": 14574592} {"current_steps": 6740, "total_steps": 61300, "loss": 0.3607, "lr": 4.998496875854908e-05, "epoch": 1.099510603588907, "percentage": 11.0, "elapsed_time": "0:54:57", "remaining_time": "7:24:49", "throughput": 4423.91, "total_tokens": 14585728} {"current_steps": 6745, "total_steps": 61300, "loss": 0.3777, "lr": 4.998472095216984e-05, "epoch": 1.100326264274062, "percentage": 11.0, "elapsed_time": "0:54:58", "remaining_time": "7:24:41", "throughput": 4424.12, "total_tokens": 14594464} {"current_steps": 6750, "total_steps": 61300, "loss": 0.3782, "lr": 4.998447112040235e-05, "epoch": 1.101141924959217, "percentage": 11.01, "elapsed_time": "0:55:00", "remaining_time": "7:24:36", "throughput": 4424.35, "total_tokens": 14604480} {"current_steps": 6755, "total_steps": 61300, "loss": 0.3471, "lr": 4.998421926326685e-05, "epoch": 1.101957585644372, "percentage": 11.02, "elapsed_time": "0:55:03", "remaining_time": "7:24:33", "throughput": 4424.65, "total_tokens": 14616128} {"current_steps": 6760, "total_steps": 61300, "loss": 0.3927, "lr": 4.998396538078378e-05, "epoch": 1.102773246329527, "percentage": 11.03, "elapsed_time": "0:55:05", "remaining_time": "7:24:29", "throughput": 4424.91, "total_tokens": 14627008} {"current_steps": 6765, "total_steps": 61300, "loss": 0.2973, "lr": 4.99837094729737e-05, "epoch": 1.1035889070146818, "percentage": 11.04, "elapsed_time": "0:55:07", "remaining_time": "7:24:24", "throughput": 4425.16, "total_tokens": 14637280} {"current_steps": 6770, "total_steps": 61300, "loss": 0.3617, "lr": 4.998345153985738e-05, "epoch": 1.1044045676998369, "percentage": 11.04, "elapsed_time": "0:55:09", "remaining_time": "7:24:19", "throughput": 4425.36, "total_tokens": 14646976} {"current_steps": 6775, "total_steps": 61300, "loss": 0.4022, "lr": 4.998319158145569e-05, "epoch": 1.105220228384992, "percentage": 11.05, "elapsed_time": "0:55:11", "remaining_time": "7:24:14", "throughput": 4425.57, "total_tokens": 14657152} {"current_steps": 6780, "total_steps": 61300, "loss": 0.3643, "lr": 4.998292959778974e-05, "epoch": 1.1060358890701467, "percentage": 11.06, "elapsed_time": "0:55:14", "remaining_time": "7:24:09", "throughput": 4425.83, "total_tokens": 14667488} {"current_steps": 6785, "total_steps": 61300, "loss": 0.315, "lr": 4.9982665588880753e-05, "epoch": 1.1068515497553018, "percentage": 11.07, "elapsed_time": "0:55:16", "remaining_time": "7:24:04", "throughput": 4426.1, "total_tokens": 14678112} {"current_steps": 6790, "total_steps": 61300, "loss": 0.3513, "lr": 4.9982399554750136e-05, "epoch": 1.1076672104404568, "percentage": 11.08, "elapsed_time": "0:55:18", "remaining_time": "7:24:01", "throughput": 4426.41, "total_tokens": 14689312} {"current_steps": 6795, "total_steps": 61300, "loss": 0.3369, "lr": 4.998213149541945e-05, "epoch": 1.1084828711256118, "percentage": 11.08, "elapsed_time": "0:55:20", "remaining_time": "7:23:56", "throughput": 4426.71, "total_tokens": 14700032} {"current_steps": 6800, "total_steps": 61300, "loss": 0.308, "lr": 4.9981861410910424e-05, "epoch": 1.1092985318107667, "percentage": 11.09, "elapsed_time": "0:55:23", "remaining_time": "7:23:53", "throughput": 4426.98, "total_tokens": 14711008} {"current_steps": 6805, "total_steps": 61300, "loss": 0.3604, "lr": 4.9981589301244956e-05, "epoch": 1.1101141924959217, "percentage": 11.1, "elapsed_time": "0:55:25", "remaining_time": "7:23:46", "throughput": 4427.2, "total_tokens": 14720448} {"current_steps": 6810, "total_steps": 61300, "loss": 0.3971, "lr": 4.99813151664451e-05, "epoch": 1.1109298531810767, "percentage": 11.11, "elapsed_time": "0:55:27", "remaining_time": "7:23:44", "throughput": 4427.42, "total_tokens": 14732128} {"current_steps": 6815, "total_steps": 61300, "loss": 0.3571, "lr": 4.998103900653309e-05, "epoch": 1.1117455138662315, "percentage": 11.12, "elapsed_time": "0:55:29", "remaining_time": "7:23:41", "throughput": 4427.69, "total_tokens": 14743200} {"current_steps": 6820, "total_steps": 61300, "loss": 0.3201, "lr": 4.9980760821531304e-05, "epoch": 1.1125611745513866, "percentage": 11.13, "elapsed_time": "0:55:32", "remaining_time": "7:23:37", "throughput": 4428.01, "total_tokens": 14754464} {"current_steps": 6825, "total_steps": 61300, "loss": 0.357, "lr": 4.998048061146229e-05, "epoch": 1.1133768352365416, "percentage": 11.13, "elapsed_time": "0:55:33", "remaining_time": "7:23:30", "throughput": 4428.27, "total_tokens": 14763840} {"current_steps": 6830, "total_steps": 61300, "loss": 0.381, "lr": 4.9980198376348774e-05, "epoch": 1.1141924959216967, "percentage": 11.14, "elapsed_time": "0:55:36", "remaining_time": "7:23:26", "throughput": 4428.54, "total_tokens": 14774304} {"current_steps": 6835, "total_steps": 61300, "loss": 0.3785, "lr": 4.997991411621362e-05, "epoch": 1.1150081566068515, "percentage": 11.15, "elapsed_time": "0:55:38", "remaining_time": "7:23:19", "throughput": 4428.75, "total_tokens": 14783456} {"current_steps": 6840, "total_steps": 61300, "loss": 0.3403, "lr": 4.9979627831079894e-05, "epoch": 1.1158238172920065, "percentage": 11.16, "elapsed_time": "0:55:40", "remaining_time": "7:23:14", "throughput": 4428.99, "total_tokens": 14793664} {"current_steps": 6845, "total_steps": 61300, "loss": 0.3326, "lr": 4.997933952097078e-05, "epoch": 1.1166394779771616, "percentage": 11.17, "elapsed_time": "0:55:42", "remaining_time": "7:23:10", "throughput": 4429.26, "total_tokens": 14804256} {"current_steps": 6850, "total_steps": 61300, "loss": 0.3474, "lr": 4.997904918590966e-05, "epoch": 1.1174551386623164, "percentage": 11.17, "elapsed_time": "0:55:44", "remaining_time": "7:23:07", "throughput": 4429.51, "total_tokens": 14815744} {"current_steps": 6855, "total_steps": 61300, "loss": 0.3275, "lr": 4.997875682592008e-05, "epoch": 1.1182707993474714, "percentage": 11.18, "elapsed_time": "0:55:46", "remaining_time": "7:23:02", "throughput": 4429.77, "total_tokens": 14826304} {"current_steps": 6860, "total_steps": 61300, "loss": 0.3773, "lr": 4.997846244102573e-05, "epoch": 1.1190864600326265, "percentage": 11.19, "elapsed_time": "0:55:49", "remaining_time": "7:22:59", "throughput": 4430.12, "total_tokens": 14838016} {"current_steps": 6865, "total_steps": 61300, "loss": 0.3534, "lr": 4.997816603125047e-05, "epoch": 1.1199021207177815, "percentage": 11.2, "elapsed_time": "0:55:51", "remaining_time": "7:22:57", "throughput": 4430.34, "total_tokens": 14849344} {"current_steps": 6870, "total_steps": 61300, "loss": 0.3834, "lr": 4.9977867596618333e-05, "epoch": 1.1207177814029363, "percentage": 11.21, "elapsed_time": "0:55:54", "remaining_time": "7:22:53", "throughput": 4430.63, "total_tokens": 14860608} {"current_steps": 6875, "total_steps": 61300, "loss": 0.3844, "lr": 4.997756713715352e-05, "epoch": 1.1215334420880914, "percentage": 11.22, "elapsed_time": "0:55:56", "remaining_time": "7:22:48", "throughput": 4430.89, "total_tokens": 14870976} {"current_steps": 6880, "total_steps": 61300, "loss": 0.3013, "lr": 4.997726465288037e-05, "epoch": 1.1223491027732464, "percentage": 11.22, "elapsed_time": "0:55:58", "remaining_time": "7:22:43", "throughput": 4431.12, "total_tokens": 14880960} {"current_steps": 6885, "total_steps": 61300, "loss": 0.3457, "lr": 4.997696014382341e-05, "epoch": 1.1231647634584012, "percentage": 11.23, "elapsed_time": "0:56:00", "remaining_time": "7:22:40", "throughput": 4431.38, "total_tokens": 14892256} {"current_steps": 6890, "total_steps": 61300, "loss": 0.3682, "lr": 4.997665361000735e-05, "epoch": 1.1239804241435563, "percentage": 11.24, "elapsed_time": "0:56:02", "remaining_time": "7:22:35", "throughput": 4431.61, "total_tokens": 14902304} {"current_steps": 6895, "total_steps": 61300, "loss": 0.364, "lr": 4.9976345051456995e-05, "epoch": 1.1247960848287113, "percentage": 11.25, "elapsed_time": "0:56:05", "remaining_time": "7:22:32", "throughput": 4431.87, "total_tokens": 14913536} {"current_steps": 6900, "total_steps": 61300, "loss": 0.3381, "lr": 4.99760344681974e-05, "epoch": 1.1256117455138663, "percentage": 11.26, "elapsed_time": "0:56:07", "remaining_time": "7:22:28", "throughput": 4432.14, "total_tokens": 14924480} {"current_steps": 6905, "total_steps": 61300, "loss": 0.3971, "lr": 4.997572186025371e-05, "epoch": 1.1264274061990212, "percentage": 11.26, "elapsed_time": "0:56:09", "remaining_time": "7:22:24", "throughput": 4432.41, "total_tokens": 14935264} {"current_steps": 6910, "total_steps": 61300, "loss": 0.3588, "lr": 4.997540722765128e-05, "epoch": 1.1272430668841762, "percentage": 11.27, "elapsed_time": "0:56:12", "remaining_time": "7:22:21", "throughput": 4432.68, "total_tokens": 14947072} {"current_steps": 6915, "total_steps": 61300, "loss": 0.359, "lr": 4.997509057041563e-05, "epoch": 1.1280587275693312, "percentage": 11.28, "elapsed_time": "0:56:14", "remaining_time": "7:22:17", "throughput": 4432.93, "total_tokens": 14957888} {"current_steps": 6920, "total_steps": 61300, "loss": 0.3309, "lr": 4.99747718885724e-05, "epoch": 1.128874388254486, "percentage": 11.29, "elapsed_time": "0:56:16", "remaining_time": "7:22:11", "throughput": 4433.14, "total_tokens": 14967424} {"current_steps": 6925, "total_steps": 61300, "loss": 0.3769, "lr": 4.9974451182147456e-05, "epoch": 1.129690048939641, "percentage": 11.3, "elapsed_time": "0:56:18", "remaining_time": "7:22:06", "throughput": 4433.43, "total_tokens": 14977536} {"current_steps": 6930, "total_steps": 61300, "loss": 0.333, "lr": 4.997412845116677e-05, "epoch": 1.1305057096247961, "percentage": 11.31, "elapsed_time": "0:56:20", "remaining_time": "7:22:00", "throughput": 4433.62, "total_tokens": 14987008} {"current_steps": 6935, "total_steps": 61300, "loss": 0.3491, "lr": 4.997380369565652e-05, "epoch": 1.131321370309951, "percentage": 11.31, "elapsed_time": "0:56:22", "remaining_time": "7:21:57", "throughput": 4433.83, "total_tokens": 14998272} {"current_steps": 6940, "total_steps": 61300, "loss": 0.3825, "lr": 4.9973476915643015e-05, "epoch": 1.132137030995106, "percentage": 11.32, "elapsed_time": "0:56:24", "remaining_time": "7:21:50", "throughput": 4434.04, "total_tokens": 15007392} {"current_steps": 6945, "total_steps": 61300, "loss": 0.3746, "lr": 4.997314811115277e-05, "epoch": 1.132952691680261, "percentage": 11.33, "elapsed_time": "0:56:26", "remaining_time": "7:21:44", "throughput": 4434.28, "total_tokens": 15016608} {"current_steps": 6950, "total_steps": 61300, "loss": 0.3204, "lr": 4.997281728221242e-05, "epoch": 1.133768352365416, "percentage": 11.34, "elapsed_time": "0:56:28", "remaining_time": "7:21:40", "throughput": 4434.6, "total_tokens": 15027712} {"current_steps": 6955, "total_steps": 61300, "loss": 0.3404, "lr": 4.997248442884879e-05, "epoch": 1.1345840130505709, "percentage": 11.35, "elapsed_time": "0:56:30", "remaining_time": "7:21:35", "throughput": 4434.88, "total_tokens": 15038080} {"current_steps": 6960, "total_steps": 61300, "loss": 0.3777, "lr": 4.997214955108887e-05, "epoch": 1.135399673735726, "percentage": 11.35, "elapsed_time": "0:56:33", "remaining_time": "7:21:33", "throughput": 4435.21, "total_tokens": 15050432} {"current_steps": 6965, "total_steps": 61300, "loss": 0.3549, "lr": 4.9971812648959796e-05, "epoch": 1.136215334420881, "percentage": 11.36, "elapsed_time": "0:56:35", "remaining_time": "7:21:29", "throughput": 4435.45, "total_tokens": 15060992} {"current_steps": 6970, "total_steps": 61300, "loss": 0.3132, "lr": 4.997147372248887e-05, "epoch": 1.137030995106036, "percentage": 11.37, "elapsed_time": "0:56:37", "remaining_time": "7:21:24", "throughput": 4435.66, "total_tokens": 15070816} {"current_steps": 6975, "total_steps": 61300, "loss": 0.3344, "lr": 4.99711327717036e-05, "epoch": 1.1378466557911908, "percentage": 11.38, "elapsed_time": "0:56:39", "remaining_time": "7:21:17", "throughput": 4435.86, "total_tokens": 15080128} {"current_steps": 6980, "total_steps": 61300, "loss": 0.3333, "lr": 4.997078979663159e-05, "epoch": 1.1386623164763459, "percentage": 11.39, "elapsed_time": "0:56:41", "remaining_time": "7:21:13", "throughput": 4436.08, "total_tokens": 15090464} {"current_steps": 6985, "total_steps": 61300, "loss": 0.3768, "lr": 4.997044479730067e-05, "epoch": 1.139477977161501, "percentage": 11.39, "elapsed_time": "0:56:44", "remaining_time": "7:21:09", "throughput": 4436.33, "total_tokens": 15101472} {"current_steps": 6990, "total_steps": 61300, "loss": 0.3389, "lr": 4.997009777373879e-05, "epoch": 1.1402936378466557, "percentage": 11.4, "elapsed_time": "0:56:46", "remaining_time": "7:21:04", "throughput": 4436.55, "total_tokens": 15111616} {"current_steps": 6995, "total_steps": 61300, "loss": 0.3616, "lr": 4.9969748725974085e-05, "epoch": 1.1411092985318108, "percentage": 11.41, "elapsed_time": "0:56:48", "remaining_time": "7:21:00", "throughput": 4436.82, "total_tokens": 15122496} {"current_steps": 7000, "total_steps": 61300, "loss": 0.3395, "lr": 4.996939765403486e-05, "epoch": 1.1419249592169658, "percentage": 11.42, "elapsed_time": "0:56:50", "remaining_time": "7:20:58", "throughput": 4437.11, "total_tokens": 15134112} {"current_steps": 7005, "total_steps": 61300, "loss": 0.3662, "lr": 4.996904455794956e-05, "epoch": 1.1427406199021206, "percentage": 11.43, "elapsed_time": "0:56:52", "remaining_time": "7:20:53", "throughput": 4437.34, "total_tokens": 15144352} {"current_steps": 7010, "total_steps": 61300, "loss": 0.3841, "lr": 4.996868943774683e-05, "epoch": 1.1435562805872757, "percentage": 11.44, "elapsed_time": "0:56:55", "remaining_time": "7:20:48", "throughput": 4437.55, "total_tokens": 15154304} {"current_steps": 7015, "total_steps": 61300, "loss": 0.3452, "lr": 4.9968332293455433e-05, "epoch": 1.1443719412724307, "percentage": 11.44, "elapsed_time": "0:56:57", "remaining_time": "7:20:44", "throughput": 4437.8, "total_tokens": 15165024} {"current_steps": 7020, "total_steps": 61300, "loss": 0.3611, "lr": 4.996797312510433e-05, "epoch": 1.1451876019575857, "percentage": 11.45, "elapsed_time": "0:56:59", "remaining_time": "7:20:40", "throughput": 4438.06, "total_tokens": 15176224} {"current_steps": 7025, "total_steps": 61300, "loss": 0.3581, "lr": 4.9967611932722645e-05, "epoch": 1.1460032626427405, "percentage": 11.46, "elapsed_time": "0:57:01", "remaining_time": "7:20:36", "throughput": 4438.27, "total_tokens": 15186464} {"current_steps": 7030, "total_steps": 61300, "loss": 0.3634, "lr": 4.9967248716339656e-05, "epoch": 1.1468189233278956, "percentage": 11.47, "elapsed_time": "0:57:03", "remaining_time": "7:20:32", "throughput": 4438.51, "total_tokens": 15197408} {"current_steps": 7035, "total_steps": 61300, "loss": 0.3132, "lr": 4.9966883475984796e-05, "epoch": 1.1476345840130506, "percentage": 11.48, "elapsed_time": "0:57:06", "remaining_time": "7:20:30", "throughput": 4438.81, "total_tokens": 15209504} {"current_steps": 7040, "total_steps": 61300, "loss": 0.4114, "lr": 4.996651621168768e-05, "epoch": 1.1484502446982057, "percentage": 11.48, "elapsed_time": "0:57:08", "remaining_time": "7:20:26", "throughput": 4439.09, "total_tokens": 15220576} {"current_steps": 7045, "total_steps": 61300, "loss": 0.3627, "lr": 4.9966146923478086e-05, "epoch": 1.1492659053833605, "percentage": 11.49, "elapsed_time": "0:57:10", "remaining_time": "7:20:21", "throughput": 4439.34, "total_tokens": 15230752} {"current_steps": 7050, "total_steps": 61300, "loss": 0.3368, "lr": 4.996577561138594e-05, "epoch": 1.1500815660685155, "percentage": 11.5, "elapsed_time": "0:57:13", "remaining_time": "7:20:17", "throughput": 4439.58, "total_tokens": 15241312} {"current_steps": 7055, "total_steps": 61300, "loss": 0.3352, "lr": 4.996540227544136e-05, "epoch": 1.1508972267536706, "percentage": 11.51, "elapsed_time": "0:57:15", "remaining_time": "7:20:14", "throughput": 4439.82, "total_tokens": 15252512} {"current_steps": 7060, "total_steps": 61300, "loss": 0.3512, "lr": 4.9965026915674584e-05, "epoch": 1.1517128874388254, "percentage": 11.52, "elapsed_time": "0:57:17", "remaining_time": "7:20:08", "throughput": 4440.05, "total_tokens": 15262400} {"current_steps": 7065, "total_steps": 61300, "loss": 0.3684, "lr": 4.9964649532116065e-05, "epoch": 1.1525285481239804, "percentage": 11.53, "elapsed_time": "0:57:19", "remaining_time": "7:20:07", "throughput": 4440.38, "total_tokens": 15274816} {"current_steps": 7070, "total_steps": 61300, "loss": 0.3769, "lr": 4.996427012479638e-05, "epoch": 1.1533442088091355, "percentage": 11.53, "elapsed_time": "0:57:22", "remaining_time": "7:20:02", "throughput": 4440.66, "total_tokens": 15285248} {"current_steps": 7075, "total_steps": 61300, "loss": 0.3197, "lr": 4.9963888693746294e-05, "epoch": 1.1541598694942903, "percentage": 11.54, "elapsed_time": "0:57:24", "remaining_time": "7:19:57", "throughput": 4440.88, "total_tokens": 15295552} {"current_steps": 7080, "total_steps": 61300, "loss": 0.4056, "lr": 4.996350523899672e-05, "epoch": 1.1549755301794453, "percentage": 11.55, "elapsed_time": "0:57:26", "remaining_time": "7:19:52", "throughput": 4441.09, "total_tokens": 15305248} {"current_steps": 7085, "total_steps": 61300, "loss": 0.3952, "lr": 4.9963119760578756e-05, "epoch": 1.1557911908646004, "percentage": 11.56, "elapsed_time": "0:57:28", "remaining_time": "7:19:49", "throughput": 4441.33, "total_tokens": 15316576} {"current_steps": 7090, "total_steps": 61300, "loss": 0.345, "lr": 4.996273225852364e-05, "epoch": 1.1566068515497552, "percentage": 11.57, "elapsed_time": "0:57:31", "remaining_time": "7:19:47", "throughput": 4441.54, "total_tokens": 15328256} {"current_steps": 7095, "total_steps": 61300, "loss": 0.3276, "lr": 4.996234273286278e-05, "epoch": 1.1574225122349102, "percentage": 11.57, "elapsed_time": "0:57:33", "remaining_time": "7:19:42", "throughput": 4441.77, "total_tokens": 15338752} {"current_steps": 7100, "total_steps": 61300, "loss": 0.3488, "lr": 4.996195118362777e-05, "epoch": 1.1582381729200653, "percentage": 11.58, "elapsed_time": "0:57:35", "remaining_time": "7:19:36", "throughput": 4441.97, "total_tokens": 15348224} {"current_steps": 7105, "total_steps": 61300, "loss": 0.3226, "lr": 4.996155761085034e-05, "epoch": 1.1590538336052203, "percentage": 11.59, "elapsed_time": "0:57:37", "remaining_time": "7:19:32", "throughput": 4442.22, "total_tokens": 15359008} {"current_steps": 7110, "total_steps": 61300, "loss": 0.3501, "lr": 4.996116201456239e-05, "epoch": 1.1598694942903751, "percentage": 11.6, "elapsed_time": "0:57:39", "remaining_time": "7:19:28", "throughput": 4442.48, "total_tokens": 15369408} {"current_steps": 7115, "total_steps": 61300, "loss": 0.3144, "lr": 4.9960764394796e-05, "epoch": 1.1606851549755302, "percentage": 11.61, "elapsed_time": "0:57:41", "remaining_time": "7:19:23", "throughput": 4442.65, "total_tokens": 15379392} {"current_steps": 7120, "total_steps": 61300, "loss": 0.3336, "lr": 4.99603647515834e-05, "epoch": 1.1615008156606852, "percentage": 11.62, "elapsed_time": "0:57:43", "remaining_time": "7:19:19", "throughput": 4442.9, "total_tokens": 15389920} {"current_steps": 7125, "total_steps": 61300, "loss": 0.3671, "lr": 4.9959963084956986e-05, "epoch": 1.1623164763458402, "percentage": 11.62, "elapsed_time": "0:57:46", "remaining_time": "7:19:15", "throughput": 4443.16, "total_tokens": 15400896} {"current_steps": 7130, "total_steps": 61300, "loss": 0.3692, "lr": 4.9959559394949315e-05, "epoch": 1.163132137030995, "percentage": 11.63, "elapsed_time": "0:57:48", "remaining_time": "7:19:12", "throughput": 4443.45, "total_tokens": 15412320} {"current_steps": 7135, "total_steps": 61300, "loss": 0.3303, "lr": 4.9959153681593114e-05, "epoch": 1.16394779771615, "percentage": 11.64, "elapsed_time": "0:57:50", "remaining_time": "7:19:09", "throughput": 4443.7, "total_tokens": 15423680} {"current_steps": 7140, "total_steps": 61300, "loss": 0.3422, "lr": 4.9958745944921275e-05, "epoch": 1.1647634584013051, "percentage": 11.65, "elapsed_time": "0:57:53", "remaining_time": "7:19:04", "throughput": 4443.91, "total_tokens": 15433952} {"current_steps": 7145, "total_steps": 61300, "loss": 0.3056, "lr": 4.995833618496685e-05, "epoch": 1.16557911908646, "percentage": 11.66, "elapsed_time": "0:57:55", "remaining_time": "7:19:01", "throughput": 4444.13, "total_tokens": 15444896} {"current_steps": 7150, "total_steps": 61300, "loss": 0.3583, "lr": 4.9957924401763065e-05, "epoch": 1.166394779771615, "percentage": 11.66, "elapsed_time": "0:57:57", "remaining_time": "7:18:57", "throughput": 4444.41, "total_tokens": 15456192} {"current_steps": 7155, "total_steps": 61300, "loss": 0.3212, "lr": 4.9957510595343285e-05, "epoch": 1.16721044045677, "percentage": 11.67, "elapsed_time": "0:57:59", "remaining_time": "7:18:51", "throughput": 4444.57, "total_tokens": 15465312} {"current_steps": 7160, "total_steps": 61300, "loss": 0.3667, "lr": 4.995709476574106e-05, "epoch": 1.1680261011419248, "percentage": 11.68, "elapsed_time": "0:58:01", "remaining_time": "7:18:45", "throughput": 4444.77, "total_tokens": 15474496} {"current_steps": 7165, "total_steps": 61300, "loss": 0.3144, "lr": 4.9956676912990105e-05, "epoch": 1.1688417618270799, "percentage": 11.69, "elapsed_time": "0:58:03", "remaining_time": "7:18:40", "throughput": 4445.02, "total_tokens": 15484992} {"current_steps": 7170, "total_steps": 61300, "loss": 0.3622, "lr": 4.99562570371243e-05, "epoch": 1.169657422512235, "percentage": 11.7, "elapsed_time": "0:58:05", "remaining_time": "7:18:36", "throughput": 4445.24, "total_tokens": 15495232} {"current_steps": 7175, "total_steps": 61300, "loss": 0.3354, "lr": 4.9955835138177667e-05, "epoch": 1.17047308319739, "percentage": 11.7, "elapsed_time": "0:58:08", "remaining_time": "7:18:32", "throughput": 4445.49, "total_tokens": 15506304} {"current_steps": 7180, "total_steps": 61300, "loss": 0.3604, "lr": 4.9955411216184414e-05, "epoch": 1.1712887438825448, "percentage": 11.71, "elapsed_time": "0:58:10", "remaining_time": "7:18:28", "throughput": 4445.74, "total_tokens": 15517248} {"current_steps": 7185, "total_steps": 61300, "loss": 0.3549, "lr": 4.9954985271178903e-05, "epoch": 1.1721044045676998, "percentage": 11.72, "elapsed_time": "0:58:12", "remaining_time": "7:18:23", "throughput": 4445.95, "total_tokens": 15527040} {"current_steps": 7190, "total_steps": 61300, "loss": 0.3285, "lr": 4.995455730319566e-05, "epoch": 1.1729200652528549, "percentage": 11.73, "elapsed_time": "0:58:14", "remaining_time": "7:18:20", "throughput": 4446.19, "total_tokens": 15538368} {"current_steps": 7195, "total_steps": 61300, "loss": 0.4326, "lr": 4.9954127312269386e-05, "epoch": 1.17373572593801, "percentage": 11.74, "elapsed_time": "0:58:16", "remaining_time": "7:18:15", "throughput": 4446.42, "total_tokens": 15548608} {"current_steps": 7200, "total_steps": 61300, "loss": 0.3706, "lr": 4.9953695298434944e-05, "epoch": 1.1745513866231647, "percentage": 11.75, "elapsed_time": "0:58:19", "remaining_time": "7:18:13", "throughput": 4446.65, "total_tokens": 15560032} {"current_steps": 7205, "total_steps": 61300, "loss": 0.3698, "lr": 4.9953261261727334e-05, "epoch": 1.1753670473083198, "percentage": 11.75, "elapsed_time": "0:58:21", "remaining_time": "7:18:10", "throughput": 4446.92, "total_tokens": 15571616} {"current_steps": 7210, "total_steps": 61300, "loss": 0.3818, "lr": 4.9952825202181766e-05, "epoch": 1.1761827079934748, "percentage": 11.76, "elapsed_time": "0:58:24", "remaining_time": "7:18:08", "throughput": 4447.14, "total_tokens": 15583392} {"current_steps": 7215, "total_steps": 61300, "loss": 0.3348, "lr": 4.995238711983358e-05, "epoch": 1.1769983686786296, "percentage": 11.77, "elapsed_time": "0:58:26", "remaining_time": "7:18:03", "throughput": 4447.32, "total_tokens": 15593504} {"current_steps": 7220, "total_steps": 61300, "loss": 0.3815, "lr": 4.995194701471828e-05, "epoch": 1.1778140293637847, "percentage": 11.78, "elapsed_time": "0:58:28", "remaining_time": "7:18:00", "throughput": 4447.57, "total_tokens": 15604928} {"current_steps": 7225, "total_steps": 61300, "loss": 0.3776, "lr": 4.9951504886871545e-05, "epoch": 1.1786296900489397, "percentage": 11.79, "elapsed_time": "0:58:30", "remaining_time": "7:17:56", "throughput": 4447.81, "total_tokens": 15615200} {"current_steps": 7230, "total_steps": 61300, "loss": 0.4193, "lr": 4.995106073632924e-05, "epoch": 1.1794453507340945, "percentage": 11.79, "elapsed_time": "0:58:33", "remaining_time": "7:17:52", "throughput": 4448.08, "total_tokens": 15626176} {"current_steps": 7235, "total_steps": 61300, "loss": 0.3709, "lr": 4.995061456312733e-05, "epoch": 1.1802610114192496, "percentage": 11.8, "elapsed_time": "0:58:35", "remaining_time": "7:17:48", "throughput": 4448.29, "total_tokens": 15636768} {"current_steps": 7240, "total_steps": 61300, "loss": 0.3727, "lr": 4.995016636730202e-05, "epoch": 1.1810766721044046, "percentage": 11.81, "elapsed_time": "0:58:37", "remaining_time": "7:17:46", "throughput": 4448.53, "total_tokens": 15648512} {"current_steps": 7245, "total_steps": 61300, "loss": 0.3533, "lr": 4.994971614888962e-05, "epoch": 1.1818923327895596, "percentage": 11.82, "elapsed_time": "0:58:39", "remaining_time": "7:17:42", "throughput": 4448.79, "total_tokens": 15659328} {"current_steps": 7250, "total_steps": 61300, "loss": 0.3692, "lr": 4.994926390792664e-05, "epoch": 1.1827079934747144, "percentage": 11.83, "elapsed_time": "0:58:42", "remaining_time": "7:17:38", "throughput": 4449.0, "total_tokens": 15669920} {"current_steps": 7255, "total_steps": 61300, "loss": 0.351, "lr": 4.9948809644449734e-05, "epoch": 1.1835236541598695, "percentage": 11.84, "elapsed_time": "0:58:44", "remaining_time": "7:17:34", "throughput": 4449.27, "total_tokens": 15681152} {"current_steps": 7260, "total_steps": 61300, "loss": 0.3995, "lr": 4.994835335849573e-05, "epoch": 1.1843393148450245, "percentage": 11.84, "elapsed_time": "0:58:46", "remaining_time": "7:17:29", "throughput": 4449.45, "total_tokens": 15690912} {"current_steps": 7265, "total_steps": 61300, "loss": 0.3333, "lr": 4.994789505010161e-05, "epoch": 1.1851549755301796, "percentage": 11.85, "elapsed_time": "0:58:48", "remaining_time": "7:17:24", "throughput": 4449.68, "total_tokens": 15701216} {"current_steps": 7270, "total_steps": 61300, "loss": 0.3395, "lr": 4.994743471930454e-05, "epoch": 1.1859706362153344, "percentage": 11.86, "elapsed_time": "0:58:50", "remaining_time": "7:17:20", "throughput": 4449.95, "total_tokens": 15712000} {"current_steps": 7275, "total_steps": 61300, "loss": 0.3349, "lr": 4.994697236614183e-05, "epoch": 1.1867862969004894, "percentage": 11.87, "elapsed_time": "0:58:53", "remaining_time": "7:17:17", "throughput": 4450.14, "total_tokens": 15722848} {"current_steps": 7280, "total_steps": 61300, "loss": 0.3437, "lr": 4.994650799065096e-05, "epoch": 1.1876019575856445, "percentage": 11.88, "elapsed_time": "0:58:55", "remaining_time": "7:17:14", "throughput": 4450.45, "total_tokens": 15734816} {"current_steps": 7285, "total_steps": 61300, "loss": 0.3472, "lr": 4.9946041592869576e-05, "epoch": 1.1884176182707993, "percentage": 11.88, "elapsed_time": "0:58:57", "remaining_time": "7:17:11", "throughput": 4450.73, "total_tokens": 15745664} {"current_steps": 7290, "total_steps": 61300, "loss": 0.3815, "lr": 4.994557317283548e-05, "epoch": 1.1892332789559543, "percentage": 11.89, "elapsed_time": "0:59:00", "remaining_time": "7:17:07", "throughput": 4450.97, "total_tokens": 15756896} {"current_steps": 7295, "total_steps": 61300, "loss": 0.3591, "lr": 4.9945102730586655e-05, "epoch": 1.1900489396411094, "percentage": 11.9, "elapsed_time": "0:59:02", "remaining_time": "7:17:02", "throughput": 4451.21, "total_tokens": 15766656} {"current_steps": 7300, "total_steps": 61300, "loss": 0.3698, "lr": 4.994463026616123e-05, "epoch": 1.1908646003262642, "percentage": 11.91, "elapsed_time": "0:59:04", "remaining_time": "7:16:59", "throughput": 4451.42, "total_tokens": 15777792} {"current_steps": 7305, "total_steps": 61300, "loss": 0.3713, "lr": 4.994415577959751e-05, "epoch": 1.1916802610114192, "percentage": 11.92, "elapsed_time": "0:59:06", "remaining_time": "7:16:54", "throughput": 4451.67, "total_tokens": 15787968} {"current_steps": 7310, "total_steps": 61300, "loss": 0.381, "lr": 4.9943679270933954e-05, "epoch": 1.1924959216965743, "percentage": 11.92, "elapsed_time": "0:59:08", "remaining_time": "7:16:49", "throughput": 4451.82, "total_tokens": 15797920} {"current_steps": 7315, "total_steps": 61300, "loss": 0.3325, "lr": 4.99432007402092e-05, "epoch": 1.1933115823817293, "percentage": 11.93, "elapsed_time": "0:59:11", "remaining_time": "7:16:46", "throughput": 4452.08, "total_tokens": 15809376} {"current_steps": 7320, "total_steps": 61300, "loss": 0.3434, "lr": 4.9942720187462025e-05, "epoch": 1.1941272430668841, "percentage": 11.94, "elapsed_time": "0:59:13", "remaining_time": "7:16:44", "throughput": 4452.35, "total_tokens": 15821408} {"current_steps": 7325, "total_steps": 61300, "loss": 0.3609, "lr": 4.9942237612731395e-05, "epoch": 1.1949429037520392, "percentage": 11.95, "elapsed_time": "0:59:15", "remaining_time": "7:16:38", "throughput": 4452.54, "total_tokens": 15830816} {"current_steps": 7330, "total_steps": 61300, "loss": 0.3543, "lr": 4.994175301605644e-05, "epoch": 1.1957585644371942, "percentage": 11.96, "elapsed_time": "0:59:17", "remaining_time": "7:16:35", "throughput": 4452.79, "total_tokens": 15841792} {"current_steps": 7335, "total_steps": 61300, "loss": 0.325, "lr": 4.9941266397476414e-05, "epoch": 1.196574225122349, "percentage": 11.97, "elapsed_time": "0:59:19", "remaining_time": "7:16:31", "throughput": 4453.06, "total_tokens": 15852768} {"current_steps": 7340, "total_steps": 61300, "loss": 0.3581, "lr": 4.9940777757030796e-05, "epoch": 1.197389885807504, "percentage": 11.97, "elapsed_time": "0:59:22", "remaining_time": "7:16:27", "throughput": 4453.34, "total_tokens": 15863680} {"current_steps": 7345, "total_steps": 61300, "loss": 0.414, "lr": 4.994028709475917e-05, "epoch": 1.198205546492659, "percentage": 11.98, "elapsed_time": "0:59:24", "remaining_time": "7:16:24", "throughput": 4453.58, "total_tokens": 15874976} {"current_steps": 7350, "total_steps": 61300, "loss": 0.3813, "lr": 4.993979441070135e-05, "epoch": 1.1990212071778141, "percentage": 11.99, "elapsed_time": "0:59:26", "remaining_time": "7:16:19", "throughput": 4453.83, "total_tokens": 15885408} {"current_steps": 7355, "total_steps": 61300, "loss": 0.3573, "lr": 4.9939299704897236e-05, "epoch": 1.199836867862969, "percentage": 12.0, "elapsed_time": "0:59:28", "remaining_time": "7:16:14", "throughput": 4454.02, "total_tokens": 15895168} {"current_steps": 7360, "total_steps": 61300, "loss": 0.3106, "lr": 4.993880297738694e-05, "epoch": 1.200652528548124, "percentage": 12.01, "elapsed_time": "0:59:31", "remaining_time": "7:16:11", "throughput": 4454.28, "total_tokens": 15906240} {"current_steps": 7365, "total_steps": 61300, "loss": 0.363, "lr": 4.9938304228210754e-05, "epoch": 1.201468189233279, "percentage": 12.01, "elapsed_time": "0:59:33", "remaining_time": "7:16:07", "throughput": 4454.51, "total_tokens": 15917024} {"current_steps": 7370, "total_steps": 61300, "loss": 0.4035, "lr": 4.9937803457409084e-05, "epoch": 1.2022838499184338, "percentage": 12.02, "elapsed_time": "0:59:35", "remaining_time": "7:16:01", "throughput": 4454.69, "total_tokens": 15926496} {"current_steps": 7375, "total_steps": 61300, "loss": 0.3072, "lr": 4.9937300665022535e-05, "epoch": 1.2030995106035889, "percentage": 12.03, "elapsed_time": "0:59:37", "remaining_time": "7:15:58", "throughput": 4454.9, "total_tokens": 15937600} {"current_steps": 7380, "total_steps": 61300, "loss": 0.3641, "lr": 4.9936795851091854e-05, "epoch": 1.203915171288744, "percentage": 12.04, "elapsed_time": "0:59:39", "remaining_time": "7:15:54", "throughput": 4455.12, "total_tokens": 15948064} {"current_steps": 7385, "total_steps": 61300, "loss": 0.3424, "lr": 4.993628901565799e-05, "epoch": 1.2047308319738987, "percentage": 12.05, "elapsed_time": "0:59:41", "remaining_time": "7:15:50", "throughput": 4455.33, "total_tokens": 15958752} {"current_steps": 7390, "total_steps": 61300, "loss": 0.343, "lr": 4.9935780158762e-05, "epoch": 1.2055464926590538, "percentage": 12.06, "elapsed_time": "0:59:44", "remaining_time": "7:15:47", "throughput": 4455.59, "total_tokens": 15970080} {"current_steps": 7395, "total_steps": 61300, "loss": 0.3714, "lr": 4.993526928044515e-05, "epoch": 1.2063621533442088, "percentage": 12.06, "elapsed_time": "0:59:46", "remaining_time": "7:15:45", "throughput": 4455.82, "total_tokens": 15982080} {"current_steps": 7400, "total_steps": 61300, "loss": 0.3084, "lr": 4.9934756380748846e-05, "epoch": 1.2071778140293639, "percentage": 12.07, "elapsed_time": "0:59:49", "remaining_time": "7:15:41", "throughput": 4456.06, "total_tokens": 15993056} {"current_steps": 7405, "total_steps": 61300, "loss": 0.3976, "lr": 4.993424145971468e-05, "epoch": 1.2079934747145187, "percentage": 12.08, "elapsed_time": "0:59:51", "remaining_time": "7:15:37", "throughput": 4456.25, "total_tokens": 16003584} {"current_steps": 7410, "total_steps": 61300, "loss": 0.3581, "lr": 4.993372451738439e-05, "epoch": 1.2088091353996737, "percentage": 12.09, "elapsed_time": "0:59:53", "remaining_time": "7:15:35", "throughput": 4456.47, "total_tokens": 16014912} {"current_steps": 7415, "total_steps": 61300, "loss": 0.3872, "lr": 4.993320555379987e-05, "epoch": 1.2096247960848288, "percentage": 12.1, "elapsed_time": "0:59:55", "remaining_time": "7:15:32", "throughput": 4456.74, "total_tokens": 16026304} {"current_steps": 7420, "total_steps": 61300, "loss": 0.3742, "lr": 4.9932684569003205e-05, "epoch": 1.2104404567699838, "percentage": 12.1, "elapsed_time": "0:59:58", "remaining_time": "7:15:29", "throughput": 4457.07, "total_tokens": 16038464} {"current_steps": 7425, "total_steps": 61300, "loss": 0.3269, "lr": 4.993216156303662e-05, "epoch": 1.2112561174551386, "percentage": 12.11, "elapsed_time": "1:00:00", "remaining_time": "7:15:27", "throughput": 4457.23, "total_tokens": 16049728} {"current_steps": 7430, "total_steps": 61300, "loss": 0.3363, "lr": 4.9931636535942506e-05, "epoch": 1.2120717781402937, "percentage": 12.12, "elapsed_time": "1:00:02", "remaining_time": "7:15:22", "throughput": 4457.41, "total_tokens": 16060032} {"current_steps": 7435, "total_steps": 61300, "loss": 0.3632, "lr": 4.993110948776344e-05, "epoch": 1.2128874388254487, "percentage": 12.13, "elapsed_time": "1:00:05", "remaining_time": "7:15:21", "throughput": 4457.66, "total_tokens": 16072064} {"current_steps": 7440, "total_steps": 61300, "loss": 0.3253, "lr": 4.993058041854214e-05, "epoch": 1.2137030995106035, "percentage": 12.14, "elapsed_time": "1:00:07", "remaining_time": "7:15:16", "throughput": 4457.82, "total_tokens": 16082112} {"current_steps": 7445, "total_steps": 61300, "loss": 0.3691, "lr": 4.9930049328321495e-05, "epoch": 1.2145187601957586, "percentage": 12.15, "elapsed_time": "1:00:09", "remaining_time": "7:15:13", "throughput": 4458.02, "total_tokens": 16093280} {"current_steps": 7450, "total_steps": 61300, "loss": 0.3235, "lr": 4.9929516217144554e-05, "epoch": 1.2153344208809136, "percentage": 12.15, "elapsed_time": "1:00:12", "remaining_time": "7:15:10", "throughput": 4458.25, "total_tokens": 16104352} {"current_steps": 7455, "total_steps": 61300, "loss": 0.306, "lr": 4.992898108505454e-05, "epoch": 1.2161500815660684, "percentage": 12.16, "elapsed_time": "1:00:14", "remaining_time": "7:15:05", "throughput": 4458.5, "total_tokens": 16114784} {"current_steps": 7460, "total_steps": 61300, "loss": 0.3059, "lr": 4.992844393209483e-05, "epoch": 1.2169657422512234, "percentage": 12.17, "elapsed_time": "1:00:16", "remaining_time": "7:15:02", "throughput": 4458.73, "total_tokens": 16126080} {"current_steps": 7465, "total_steps": 61300, "loss": 0.4136, "lr": 4.992790475830896e-05, "epoch": 1.2177814029363785, "percentage": 12.18, "elapsed_time": "1:00:18", "remaining_time": "7:14:58", "throughput": 4458.91, "total_tokens": 16136480} {"current_steps": 7470, "total_steps": 61300, "loss": 0.3782, "lr": 4.992736356374066e-05, "epoch": 1.2185970636215335, "percentage": 12.19, "elapsed_time": "1:00:21", "remaining_time": "7:14:55", "throughput": 4459.12, "total_tokens": 16147424} {"current_steps": 7475, "total_steps": 61300, "loss": 0.3585, "lr": 4.992682034843379e-05, "epoch": 1.2194127243066883, "percentage": 12.19, "elapsed_time": "1:00:23", "remaining_time": "7:14:49", "throughput": 4459.36, "total_tokens": 16157280} {"current_steps": 7480, "total_steps": 61300, "loss": 0.331, "lr": 4.992627511243238e-05, "epoch": 1.2202283849918434, "percentage": 12.2, "elapsed_time": "1:00:25", "remaining_time": "7:14:45", "throughput": 4459.64, "total_tokens": 16168320} {"current_steps": 7485, "total_steps": 61300, "loss": 0.3312, "lr": 4.992572785578063e-05, "epoch": 1.2210440456769984, "percentage": 12.21, "elapsed_time": "1:00:27", "remaining_time": "7:14:42", "throughput": 4459.83, "total_tokens": 16178976} {"current_steps": 7490, "total_steps": 61300, "loss": 0.3606, "lr": 4.9925178578522914e-05, "epoch": 1.2218597063621535, "percentage": 12.22, "elapsed_time": "1:00:30", "remaining_time": "7:14:39", "throughput": 4460.02, "total_tokens": 16190208} {"current_steps": 7495, "total_steps": 61300, "loss": 0.3629, "lr": 4.992462728070375e-05, "epoch": 1.2226753670473083, "percentage": 12.23, "elapsed_time": "1:00:32", "remaining_time": "7:14:33", "throughput": 4460.2, "total_tokens": 16199488} {"current_steps": 7500, "total_steps": 61300, "loss": 0.3377, "lr": 4.992407396236784e-05, "epoch": 1.2234910277324633, "percentage": 12.23, "elapsed_time": "1:00:34", "remaining_time": "7:14:29", "throughput": 4460.41, "total_tokens": 16210432} {"current_steps": 7505, "total_steps": 61300, "loss": 0.3588, "lr": 4.992351862356003e-05, "epoch": 1.2243066884176184, "percentage": 12.24, "elapsed_time": "1:00:36", "remaining_time": "7:14:27", "throughput": 4460.62, "total_tokens": 16221664} {"current_steps": 7510, "total_steps": 61300, "loss": 0.3566, "lr": 4.992296126432533e-05, "epoch": 1.2251223491027732, "percentage": 12.25, "elapsed_time": "1:00:38", "remaining_time": "7:14:22", "throughput": 4460.84, "total_tokens": 16232064} {"current_steps": 7515, "total_steps": 61300, "loss": 0.3717, "lr": 4.992240188470894e-05, "epoch": 1.2259380097879282, "percentage": 12.26, "elapsed_time": "1:00:41", "remaining_time": "7:14:18", "throughput": 4461.1, "total_tokens": 16242976} {"current_steps": 7520, "total_steps": 61300, "loss": 0.3052, "lr": 4.99218404847562e-05, "epoch": 1.2267536704730833, "percentage": 12.27, "elapsed_time": "1:00:43", "remaining_time": "7:14:14", "throughput": 4461.27, "total_tokens": 16253440} {"current_steps": 7525, "total_steps": 61300, "loss": 0.3579, "lr": 4.9921277064512614e-05, "epoch": 1.227569331158238, "percentage": 12.28, "elapsed_time": "1:00:45", "remaining_time": "7:14:10", "throughput": 4461.46, "total_tokens": 16263680} {"current_steps": 7530, "total_steps": 61300, "loss": 0.332, "lr": 4.992071162402386e-05, "epoch": 1.2283849918433931, "percentage": 12.28, "elapsed_time": "1:00:47", "remaining_time": "7:14:07", "throughput": 4461.7, "total_tokens": 16274944} {"current_steps": 7535, "total_steps": 61300, "loss": 0.4291, "lr": 4.992014416333577e-05, "epoch": 1.2292006525285482, "percentage": 12.29, "elapsed_time": "1:00:49", "remaining_time": "7:14:03", "throughput": 4461.88, "total_tokens": 16285376} {"current_steps": 7540, "total_steps": 61300, "loss": 0.3614, "lr": 4.991957468249436e-05, "epoch": 1.2300163132137032, "percentage": 12.3, "elapsed_time": "1:00:52", "remaining_time": "7:14:00", "throughput": 4462.09, "total_tokens": 16296544} {"current_steps": 7545, "total_steps": 61300, "loss": 0.3826, "lr": 4.991900318154578e-05, "epoch": 1.230831973898858, "percentage": 12.31, "elapsed_time": "1:00:54", "remaining_time": "7:13:55", "throughput": 4462.27, "total_tokens": 16306752} {"current_steps": 7550, "total_steps": 61300, "loss": 0.3526, "lr": 4.991842966053637e-05, "epoch": 1.231647634584013, "percentage": 12.32, "elapsed_time": "1:00:56", "remaining_time": "7:13:52", "throughput": 4462.5, "total_tokens": 16317536} {"current_steps": 7555, "total_steps": 61300, "loss": 0.3917, "lr": 4.991785411951261e-05, "epoch": 1.232463295269168, "percentage": 12.32, "elapsed_time": "1:00:58", "remaining_time": "7:13:48", "throughput": 4462.73, "total_tokens": 16328640} {"current_steps": 7560, "total_steps": 61300, "loss": 0.3809, "lr": 4.9917276558521164e-05, "epoch": 1.233278955954323, "percentage": 12.33, "elapsed_time": "1:01:01", "remaining_time": "7:13:45", "throughput": 4462.96, "total_tokens": 16340032} {"current_steps": 7565, "total_steps": 61300, "loss": 0.3469, "lr": 4.9916696977608855e-05, "epoch": 1.234094616639478, "percentage": 12.34, "elapsed_time": "1:01:03", "remaining_time": "7:13:42", "throughput": 4463.21, "total_tokens": 16351328} {"current_steps": 7570, "total_steps": 61300, "loss": 0.3562, "lr": 4.991611537682266e-05, "epoch": 1.234910277324633, "percentage": 12.35, "elapsed_time": "1:01:05", "remaining_time": "7:13:37", "throughput": 4463.42, "total_tokens": 16360832} {"current_steps": 7575, "total_steps": 61300, "loss": 0.3378, "lr": 4.991553175620973e-05, "epoch": 1.235725938009788, "percentage": 12.36, "elapsed_time": "1:01:07", "remaining_time": "7:13:34", "throughput": 4463.7, "total_tokens": 16372640} {"current_steps": 7580, "total_steps": 61300, "loss": 0.3398, "lr": 4.991494611581738e-05, "epoch": 1.2365415986949428, "percentage": 12.37, "elapsed_time": "1:01:10", "remaining_time": "7:13:30", "throughput": 4463.91, "total_tokens": 16383360} {"current_steps": 7585, "total_steps": 61300, "loss": 0.3918, "lr": 4.9914358455693076e-05, "epoch": 1.2373572593800979, "percentage": 12.37, "elapsed_time": "1:01:12", "remaining_time": "7:13:26", "throughput": 4464.16, "total_tokens": 16393728} {"current_steps": 7590, "total_steps": 61300, "loss": 0.3858, "lr": 4.991376877588446e-05, "epoch": 1.238172920065253, "percentage": 12.38, "elapsed_time": "1:01:14", "remaining_time": "7:13:23", "throughput": 4464.44, "total_tokens": 16405440} {"current_steps": 7595, "total_steps": 61300, "loss": 0.3174, "lr": 4.991317707643934e-05, "epoch": 1.2389885807504077, "percentage": 12.39, "elapsed_time": "1:01:16", "remaining_time": "7:13:20", "throughput": 4464.71, "total_tokens": 16416672} {"current_steps": 7600, "total_steps": 61300, "loss": 0.3509, "lr": 4.991258335740568e-05, "epoch": 1.2398042414355628, "percentage": 12.4, "elapsed_time": "1:01:19", "remaining_time": "7:13:16", "throughput": 4464.88, "total_tokens": 16427136} {"current_steps": 7605, "total_steps": 61300, "loss": 0.3285, "lr": 4.99119876188316e-05, "epoch": 1.2406199021207178, "percentage": 12.41, "elapsed_time": "1:01:21", "remaining_time": "7:13:12", "throughput": 4465.09, "total_tokens": 16437984} {"current_steps": 7610, "total_steps": 61300, "loss": 0.3593, "lr": 4.9911389860765406e-05, "epoch": 1.2414355628058726, "percentage": 12.41, "elapsed_time": "1:01:23", "remaining_time": "7:13:09", "throughput": 4465.28, "total_tokens": 16448640} {"current_steps": 7615, "total_steps": 61300, "loss": 0.3896, "lr": 4.9910790083255555e-05, "epoch": 1.2422512234910277, "percentage": 12.42, "elapsed_time": "1:01:25", "remaining_time": "7:13:02", "throughput": 4465.5, "total_tokens": 16457856} {"current_steps": 7620, "total_steps": 61300, "loss": 0.3606, "lr": 4.991018828635066e-05, "epoch": 1.2430668841761827, "percentage": 12.43, "elapsed_time": "1:01:27", "remaining_time": "7:12:59", "throughput": 4465.68, "total_tokens": 16469056} {"current_steps": 7625, "total_steps": 61300, "loss": 0.3662, "lr": 4.99095844700995e-05, "epoch": 1.2438825448613378, "percentage": 12.44, "elapsed_time": "1:01:30", "remaining_time": "7:12:56", "throughput": 4465.87, "total_tokens": 16479616} {"current_steps": 7630, "total_steps": 61300, "loss": 0.3501, "lr": 4.9908978634551045e-05, "epoch": 1.2446982055464926, "percentage": 12.45, "elapsed_time": "1:01:32", "remaining_time": "7:12:51", "throughput": 4466.05, "total_tokens": 16489952} {"current_steps": 7635, "total_steps": 61300, "loss": 0.3445, "lr": 4.990837077975439e-05, "epoch": 1.2455138662316476, "percentage": 12.46, "elapsed_time": "1:01:34", "remaining_time": "7:12:48", "throughput": 4466.28, "total_tokens": 16501152} {"current_steps": 7640, "total_steps": 61300, "loss": 0.3531, "lr": 4.990776090575881e-05, "epoch": 1.2463295269168027, "percentage": 12.46, "elapsed_time": "1:01:36", "remaining_time": "7:12:45", "throughput": 4466.52, "total_tokens": 16512608} {"current_steps": 7645, "total_steps": 61300, "loss": 0.3449, "lr": 4.990714901261376e-05, "epoch": 1.2471451876019577, "percentage": 12.47, "elapsed_time": "1:01:39", "remaining_time": "7:12:43", "throughput": 4466.73, "total_tokens": 16524064} {"current_steps": 7650, "total_steps": 61300, "loss": 0.3702, "lr": 4.990653510036883e-05, "epoch": 1.2479608482871125, "percentage": 12.48, "elapsed_time": "1:01:41", "remaining_time": "7:12:39", "throughput": 4466.93, "total_tokens": 16534688} {"current_steps": 7655, "total_steps": 61300, "loss": 0.3821, "lr": 4.99059191690738e-05, "epoch": 1.2487765089722676, "percentage": 12.49, "elapsed_time": "1:01:43", "remaining_time": "7:12:35", "throughput": 4467.12, "total_tokens": 16544928} {"current_steps": 7660, "total_steps": 61300, "loss": 0.3713, "lr": 4.9905301218778575e-05, "epoch": 1.2495921696574226, "percentage": 12.5, "elapsed_time": "1:01:45", "remaining_time": "7:12:30", "throughput": 4467.27, "total_tokens": 16555200} {"current_steps": 7665, "total_steps": 61300, "loss": 0.3276, "lr": 4.990468124953328e-05, "epoch": 1.2504078303425774, "percentage": 12.5, "elapsed_time": "1:01:48", "remaining_time": "7:12:27", "throughput": 4467.45, "total_tokens": 16566304} {"current_steps": 7670, "total_steps": 61300, "loss": 0.3585, "lr": 4.990405926138815e-05, "epoch": 1.2512234910277324, "percentage": 12.51, "elapsed_time": "1:01:50", "remaining_time": "7:12:26", "throughput": 4467.72, "total_tokens": 16578560} {"current_steps": 7675, "total_steps": 61300, "loss": 0.3296, "lr": 4.9903435254393616e-05, "epoch": 1.2520391517128875, "percentage": 12.52, "elapsed_time": "1:01:52", "remaining_time": "7:12:21", "throughput": 4467.86, "total_tokens": 16588704} {"current_steps": 7680, "total_steps": 61300, "loss": 0.3347, "lr": 4.990280922860026e-05, "epoch": 1.2528548123980423, "percentage": 12.53, "elapsed_time": "1:01:55", "remaining_time": "7:12:18", "throughput": 4468.07, "total_tokens": 16599776} {"current_steps": 7685, "total_steps": 61300, "loss": 0.3145, "lr": 4.990218118405883e-05, "epoch": 1.2536704730831973, "percentage": 12.54, "elapsed_time": "1:01:57", "remaining_time": "7:12:13", "throughput": 4468.27, "total_tokens": 16609824} {"current_steps": 7690, "total_steps": 61300, "loss": 0.3212, "lr": 4.990155112082024e-05, "epoch": 1.2544861337683524, "percentage": 12.54, "elapsed_time": "1:01:59", "remaining_time": "7:12:11", "throughput": 4468.48, "total_tokens": 16621280} {"current_steps": 7695, "total_steps": 61300, "loss": 0.3844, "lr": 4.9900919038935564e-05, "epoch": 1.2553017944535072, "percentage": 12.55, "elapsed_time": "1:02:01", "remaining_time": "7:12:07", "throughput": 4468.66, "total_tokens": 16631776} {"current_steps": 7700, "total_steps": 61300, "loss": 0.3262, "lr": 4.9900284938456056e-05, "epoch": 1.2561174551386622, "percentage": 12.56, "elapsed_time": "1:02:04", "remaining_time": "7:12:04", "throughput": 4468.92, "total_tokens": 16643584} {"current_steps": 7705, "total_steps": 61300, "loss": 0.3709, "lr": 4.98996488194331e-05, "epoch": 1.2569331158238173, "percentage": 12.57, "elapsed_time": "1:02:06", "remaining_time": "7:12:01", "throughput": 4469.15, "total_tokens": 16654432} {"current_steps": 7710, "total_steps": 61300, "loss": 0.3089, "lr": 4.989901068191828e-05, "epoch": 1.2577487765089723, "percentage": 12.58, "elapsed_time": "1:02:08", "remaining_time": "7:11:55", "throughput": 4469.33, "total_tokens": 16664064} {"current_steps": 7715, "total_steps": 61300, "loss": 0.3583, "lr": 4.9898370525963314e-05, "epoch": 1.2585644371941274, "percentage": 12.59, "elapsed_time": "1:02:10", "remaining_time": "7:11:51", "throughput": 4469.52, "total_tokens": 16674432} {"current_steps": 7720, "total_steps": 61300, "loss": 0.305, "lr": 4.9897728351620085e-05, "epoch": 1.2593800978792822, "percentage": 12.59, "elapsed_time": "1:02:13", "remaining_time": "7:11:49", "throughput": 4469.72, "total_tokens": 16685920} {"current_steps": 7725, "total_steps": 61300, "loss": 0.3444, "lr": 4.989708415894069e-05, "epoch": 1.2601957585644372, "percentage": 12.6, "elapsed_time": "1:02:15", "remaining_time": "7:11:45", "throughput": 4469.89, "total_tokens": 16696320} {"current_steps": 7730, "total_steps": 61300, "loss": 0.3696, "lr": 4.9896437947977306e-05, "epoch": 1.2610114192495923, "percentage": 12.61, "elapsed_time": "1:02:17", "remaining_time": "7:11:41", "throughput": 4470.08, "total_tokens": 16707040} {"current_steps": 7735, "total_steps": 61300, "loss": 0.3158, "lr": 4.989578971878235e-05, "epoch": 1.261827079934747, "percentage": 12.62, "elapsed_time": "1:02:19", "remaining_time": "7:11:38", "throughput": 4470.35, "total_tokens": 16718208} {"current_steps": 7740, "total_steps": 61300, "loss": 0.3596, "lr": 4.9895139471408356e-05, "epoch": 1.2626427406199021, "percentage": 12.63, "elapsed_time": "1:02:21", "remaining_time": "7:11:33", "throughput": 4470.58, "total_tokens": 16728480} {"current_steps": 7745, "total_steps": 61300, "loss": 0.3394, "lr": 4.9894487205908044e-05, "epoch": 1.2634584013050572, "percentage": 12.63, "elapsed_time": "1:02:24", "remaining_time": "7:11:31", "throughput": 4470.79, "total_tokens": 16740384} {"current_steps": 7750, "total_steps": 61300, "loss": 0.3507, "lr": 4.9893832922334285e-05, "epoch": 1.264274061990212, "percentage": 12.64, "elapsed_time": "1:02:26", "remaining_time": "7:11:26", "throughput": 4470.97, "total_tokens": 16749888} {"current_steps": 7755, "total_steps": 61300, "loss": 0.3174, "lr": 4.989317662074011e-05, "epoch": 1.265089722675367, "percentage": 12.65, "elapsed_time": "1:02:28", "remaining_time": "7:11:22", "throughput": 4471.2, "total_tokens": 16761024} {"current_steps": 7760, "total_steps": 61300, "loss": 0.3666, "lr": 4.989251830117874e-05, "epoch": 1.265905383360522, "percentage": 12.66, "elapsed_time": "1:02:30", "remaining_time": "7:11:18", "throughput": 4471.38, "total_tokens": 16771296} {"current_steps": 7765, "total_steps": 61300, "loss": 0.3618, "lr": 4.9891857963703535e-05, "epoch": 1.2667210440456769, "percentage": 12.67, "elapsed_time": "1:02:33", "remaining_time": "7:11:14", "throughput": 4471.61, "total_tokens": 16781984} {"current_steps": 7770, "total_steps": 61300, "loss": 0.3602, "lr": 4.989119560836802e-05, "epoch": 1.267536704730832, "percentage": 12.68, "elapsed_time": "1:02:35", "remaining_time": "7:11:11", "throughput": 4471.87, "total_tokens": 16793056} {"current_steps": 7775, "total_steps": 61300, "loss": 0.3573, "lr": 4.989053123522589e-05, "epoch": 1.268352365415987, "percentage": 12.68, "elapsed_time": "1:02:37", "remaining_time": "7:11:09", "throughput": 4472.15, "total_tokens": 16805568} {"current_steps": 7780, "total_steps": 61300, "loss": 0.3405, "lr": 4.988986484433101e-05, "epoch": 1.269168026101142, "percentage": 12.69, "elapsed_time": "1:02:39", "remaining_time": "7:11:05", "throughput": 4472.36, "total_tokens": 16815808} {"current_steps": 7785, "total_steps": 61300, "loss": 0.3604, "lr": 4.988919643573739e-05, "epoch": 1.269983686786297, "percentage": 12.7, "elapsed_time": "1:02:42", "remaining_time": "7:11:01", "throughput": 4472.52, "total_tokens": 16826272} {"current_steps": 7790, "total_steps": 61300, "loss": 0.3343, "lr": 4.9888526009499223e-05, "epoch": 1.2707993474714518, "percentage": 12.71, "elapsed_time": "1:02:44", "remaining_time": "7:10:57", "throughput": 4472.71, "total_tokens": 16836576} {"current_steps": 7795, "total_steps": 61300, "loss": 0.3677, "lr": 4.9887853565670854e-05, "epoch": 1.2716150081566069, "percentage": 12.72, "elapsed_time": "1:02:46", "remaining_time": "7:10:52", "throughput": 4472.89, "total_tokens": 16846720} {"current_steps": 7800, "total_steps": 61300, "loss": 0.3919, "lr": 4.9887179104306796e-05, "epoch": 1.272430668841762, "percentage": 12.72, "elapsed_time": "1:02:48", "remaining_time": "7:10:48", "throughput": 4473.1, "total_tokens": 16856960} {"current_steps": 7805, "total_steps": 61300, "loss": 0.3682, "lr": 4.988650262546173e-05, "epoch": 1.2732463295269167, "percentage": 12.73, "elapsed_time": "1:02:50", "remaining_time": "7:10:45", "throughput": 4473.32, "total_tokens": 16868512} {"current_steps": 7810, "total_steps": 61300, "loss": 0.3367, "lr": 4.9885824129190476e-05, "epoch": 1.2740619902120718, "percentage": 12.74, "elapsed_time": "1:02:53", "remaining_time": "7:10:42", "throughput": 4473.52, "total_tokens": 16879744} {"current_steps": 7815, "total_steps": 61300, "loss": 0.3439, "lr": 4.988514361554806e-05, "epoch": 1.2748776508972268, "percentage": 12.75, "elapsed_time": "1:02:55", "remaining_time": "7:10:37", "throughput": 4473.68, "total_tokens": 16889440} {"current_steps": 7820, "total_steps": 61300, "loss": 0.3396, "lr": 4.988446108458963e-05, "epoch": 1.2756933115823816, "percentage": 12.76, "elapsed_time": "1:02:57", "remaining_time": "7:10:34", "throughput": 4473.92, "total_tokens": 16900768} {"current_steps": 7825, "total_steps": 61300, "loss": 0.3684, "lr": 4.988377653637052e-05, "epoch": 1.2765089722675367, "percentage": 12.77, "elapsed_time": "1:02:59", "remaining_time": "7:10:29", "throughput": 4474.04, "total_tokens": 16910240} {"current_steps": 7830, "total_steps": 61300, "loss": 0.3286, "lr": 4.988308997094623e-05, "epoch": 1.2773246329526917, "percentage": 12.77, "elapsed_time": "1:03:01", "remaining_time": "7:10:26", "throughput": 4474.25, "total_tokens": 16921600} {"current_steps": 7835, "total_steps": 61300, "loss": 0.3662, "lr": 4.988240138837241e-05, "epoch": 1.2781402936378465, "percentage": 12.78, "elapsed_time": "1:03:04", "remaining_time": "7:10:24", "throughput": 4474.52, "total_tokens": 16933344} {"current_steps": 7840, "total_steps": 61300, "loss": 0.3414, "lr": 4.988171078870488e-05, "epoch": 1.2789559543230016, "percentage": 12.79, "elapsed_time": "1:03:06", "remaining_time": "7:10:21", "throughput": 4474.73, "total_tokens": 16944416} {"current_steps": 7845, "total_steps": 61300, "loss": 0.3041, "lr": 4.988101817199963e-05, "epoch": 1.2797716150081566, "percentage": 12.8, "elapsed_time": "1:03:08", "remaining_time": "7:10:17", "throughput": 4474.89, "total_tokens": 16954816} {"current_steps": 7850, "total_steps": 61300, "loss": 0.3519, "lr": 4.988032353831279e-05, "epoch": 1.2805872756933117, "percentage": 12.81, "elapsed_time": "1:03:10", "remaining_time": "7:10:12", "throughput": 4475.1, "total_tokens": 16964992} {"current_steps": 7855, "total_steps": 61300, "loss": 0.3135, "lr": 4.9879626887700694e-05, "epoch": 1.2814029363784667, "percentage": 12.81, "elapsed_time": "1:03:13", "remaining_time": "7:10:07", "throughput": 4475.31, "total_tokens": 16975200} {"current_steps": 7860, "total_steps": 61300, "loss": 0.3364, "lr": 4.98789282202198e-05, "epoch": 1.2822185970636215, "percentage": 12.82, "elapsed_time": "1:03:15", "remaining_time": "7:10:04", "throughput": 4475.49, "total_tokens": 16985984} {"current_steps": 7865, "total_steps": 61300, "loss": 0.3641, "lr": 4.9878227535926745e-05, "epoch": 1.2830342577487766, "percentage": 12.83, "elapsed_time": "1:03:17", "remaining_time": "7:10:01", "throughput": 4475.73, "total_tokens": 16997504} {"current_steps": 7870, "total_steps": 61300, "loss": 0.4103, "lr": 4.987752483487834e-05, "epoch": 1.2838499184339316, "percentage": 12.84, "elapsed_time": "1:03:19", "remaining_time": "7:09:56", "throughput": 4475.88, "total_tokens": 17007296} {"current_steps": 7875, "total_steps": 61300, "loss": 0.329, "lr": 4.987682011713155e-05, "epoch": 1.2846655791190864, "percentage": 12.85, "elapsed_time": "1:03:21", "remaining_time": "7:09:52", "throughput": 4476.1, "total_tokens": 17017792} {"current_steps": 7880, "total_steps": 61300, "loss": 0.3747, "lr": 4.9876113382743496e-05, "epoch": 1.2854812398042414, "percentage": 12.85, "elapsed_time": "1:03:24", "remaining_time": "7:09:50", "throughput": 4476.3, "total_tokens": 17029472} {"current_steps": 7885, "total_steps": 61300, "loss": 0.3545, "lr": 4.987540463177147e-05, "epoch": 1.2862969004893965, "percentage": 12.86, "elapsed_time": "1:03:26", "remaining_time": "7:09:46", "throughput": 4476.5, "total_tokens": 17039808} {"current_steps": 7890, "total_steps": 61300, "loss": 0.3531, "lr": 4.987469386427292e-05, "epoch": 1.2871125611745513, "percentage": 12.87, "elapsed_time": "1:03:28", "remaining_time": "7:09:42", "throughput": 4476.68, "total_tokens": 17050720} {"current_steps": 7895, "total_steps": 61300, "loss": 0.3548, "lr": 4.987398108030548e-05, "epoch": 1.2879282218597063, "percentage": 12.88, "elapsed_time": "1:03:31", "remaining_time": "7:09:39", "throughput": 4476.88, "total_tokens": 17061792} {"current_steps": 7900, "total_steps": 61300, "loss": 0.3161, "lr": 4.987326627992692e-05, "epoch": 1.2887438825448614, "percentage": 12.89, "elapsed_time": "1:03:33", "remaining_time": "7:09:35", "throughput": 4477.1, "total_tokens": 17072512} {"current_steps": 7905, "total_steps": 61300, "loss": 0.3771, "lr": 4.98725494631952e-05, "epoch": 1.2895595432300162, "percentage": 12.9, "elapsed_time": "1:03:35", "remaining_time": "7:09:33", "throughput": 4477.28, "total_tokens": 17084288} {"current_steps": 7910, "total_steps": 61300, "loss": 0.3421, "lr": 4.9871830630168404e-05, "epoch": 1.2903752039151712, "percentage": 12.9, "elapsed_time": "1:03:38", "remaining_time": "7:09:31", "throughput": 4477.5, "total_tokens": 17095648} {"current_steps": 7915, "total_steps": 61300, "loss": 0.3476, "lr": 4.987110978090482e-05, "epoch": 1.2911908646003263, "percentage": 12.91, "elapsed_time": "1:03:40", "remaining_time": "7:09:28", "throughput": 4477.74, "total_tokens": 17106976} {"current_steps": 7920, "total_steps": 61300, "loss": 0.3608, "lr": 4.9870386915462894e-05, "epoch": 1.2920065252854813, "percentage": 12.92, "elapsed_time": "1:03:42", "remaining_time": "7:09:22", "throughput": 4477.95, "total_tokens": 17116640} {"current_steps": 7925, "total_steps": 61300, "loss": 0.3427, "lr": 4.986966203390121e-05, "epoch": 1.2928221859706361, "percentage": 12.93, "elapsed_time": "1:03:44", "remaining_time": "7:09:19", "throughput": 4478.1, "total_tokens": 17127584} {"current_steps": 7930, "total_steps": 61300, "loss": 0.3304, "lr": 4.986893513627853e-05, "epoch": 1.2936378466557912, "percentage": 12.94, "elapsed_time": "1:03:46", "remaining_time": "7:09:15", "throughput": 4478.23, "total_tokens": 17137760} {"current_steps": 7935, "total_steps": 61300, "loss": 0.3453, "lr": 4.9868206222653785e-05, "epoch": 1.2944535073409462, "percentage": 12.94, "elapsed_time": "1:03:49", "remaining_time": "7:09:12", "throughput": 4478.44, "total_tokens": 17149056} {"current_steps": 7940, "total_steps": 61300, "loss": 0.3491, "lr": 4.9867475293086066e-05, "epoch": 1.2952691680261013, "percentage": 12.95, "elapsed_time": "1:03:51", "remaining_time": "7:09:09", "throughput": 4478.63, "total_tokens": 17160096} {"current_steps": 7945, "total_steps": 61300, "loss": 0.3877, "lr": 4.9866742347634624e-05, "epoch": 1.296084828711256, "percentage": 12.96, "elapsed_time": "1:03:53", "remaining_time": "7:09:05", "throughput": 4478.85, "total_tokens": 17170592} {"current_steps": 7950, "total_steps": 61300, "loss": 0.3994, "lr": 4.986600738635887e-05, "epoch": 1.2969004893964111, "percentage": 12.97, "elapsed_time": "1:03:56", "remaining_time": "7:09:02", "throughput": 4479.06, "total_tokens": 17181760} {"current_steps": 7955, "total_steps": 61300, "loss": 0.3291, "lr": 4.986527040931839e-05, "epoch": 1.2977161500815662, "percentage": 12.98, "elapsed_time": "1:03:58", "remaining_time": "7:08:58", "throughput": 4479.29, "total_tokens": 17192416} {"current_steps": 7960, "total_steps": 61300, "loss": 0.3634, "lr": 4.9864531416572926e-05, "epoch": 1.298531810766721, "percentage": 12.99, "elapsed_time": "1:04:00", "remaining_time": "7:08:56", "throughput": 4479.49, "total_tokens": 17204256} {"current_steps": 7965, "total_steps": 61300, "loss": 0.3248, "lr": 4.986379040818239e-05, "epoch": 1.299347471451876, "percentage": 12.99, "elapsed_time": "1:04:03", "remaining_time": "7:08:53", "throughput": 4479.68, "total_tokens": 17215520} {"current_steps": 7970, "total_steps": 61300, "loss": 0.3529, "lr": 4.9863047384206835e-05, "epoch": 1.300163132137031, "percentage": 13.0, "elapsed_time": "1:04:05", "remaining_time": "7:08:50", "throughput": 4479.88, "total_tokens": 17226560} {"current_steps": 7975, "total_steps": 61300, "loss": 0.348, "lr": 4.986230234470651e-05, "epoch": 1.3009787928221859, "percentage": 13.01, "elapsed_time": "1:04:07", "remaining_time": "7:08:46", "throughput": 4480.06, "total_tokens": 17236864} {"current_steps": 7980, "total_steps": 61300, "loss": 0.3635, "lr": 4.986155528974181e-05, "epoch": 1.301794453507341, "percentage": 13.02, "elapsed_time": "1:04:09", "remaining_time": "7:08:42", "throughput": 4480.27, "total_tokens": 17247424} {"current_steps": 7985, "total_steps": 61300, "loss": 0.3507, "lr": 4.986080621937329e-05, "epoch": 1.302610114192496, "percentage": 13.03, "elapsed_time": "1:04:11", "remaining_time": "7:08:38", "throughput": 4480.44, "total_tokens": 17258208} {"current_steps": 7990, "total_steps": 61300, "loss": 0.3327, "lr": 4.9860055133661675e-05, "epoch": 1.3034257748776508, "percentage": 13.03, "elapsed_time": "1:04:14", "remaining_time": "7:08:35", "throughput": 4480.65, "total_tokens": 17269280} {"current_steps": 7995, "total_steps": 61300, "loss": 0.3261, "lr": 4.985930203266785e-05, "epoch": 1.3042414355628058, "percentage": 13.04, "elapsed_time": "1:04:16", "remaining_time": "7:08:30", "throughput": 4480.84, "total_tokens": 17278816} {"current_steps": 8000, "total_steps": 61300, "loss": 0.3533, "lr": 4.985854691645287e-05, "epoch": 1.3050570962479608, "percentage": 13.05, "elapsed_time": "1:04:18", "remaining_time": "7:08:27", "throughput": 4481.01, "total_tokens": 17289824} {"current_steps": 8005, "total_steps": 61300, "loss": 0.3472, "lr": 4.985778978507795e-05, "epoch": 1.3058727569331159, "percentage": 13.06, "elapsed_time": "1:04:20", "remaining_time": "7:08:23", "throughput": 4481.18, "total_tokens": 17300448} {"current_steps": 8010, "total_steps": 61300, "loss": 0.3681, "lr": 4.9857030638604454e-05, "epoch": 1.306688417618271, "percentage": 13.07, "elapsed_time": "1:04:22", "remaining_time": "7:08:19", "throughput": 4481.35, "total_tokens": 17310592} {"current_steps": 8015, "total_steps": 61300, "loss": 0.3201, "lr": 4.985626947709393e-05, "epoch": 1.3075040783034257, "percentage": 13.08, "elapsed_time": "1:04:25", "remaining_time": "7:08:15", "throughput": 4481.56, "total_tokens": 17321632} {"current_steps": 8020, "total_steps": 61300, "loss": 0.3562, "lr": 4.985550630060809e-05, "epoch": 1.3083197389885808, "percentage": 13.08, "elapsed_time": "1:04:27", "remaining_time": "7:08:12", "throughput": 4481.79, "total_tokens": 17332960} {"current_steps": 8025, "total_steps": 61300, "loss": 0.3761, "lr": 4.985474110920879e-05, "epoch": 1.3091353996737358, "percentage": 13.09, "elapsed_time": "1:04:29", "remaining_time": "7:08:09", "throughput": 4482.0, "total_tokens": 17343808} {"current_steps": 8030, "total_steps": 61300, "loss": 0.3201, "lr": 4.985397390295807e-05, "epoch": 1.3099510603588906, "percentage": 13.1, "elapsed_time": "1:04:31", "remaining_time": "7:08:04", "throughput": 4482.16, "total_tokens": 17353696} {"current_steps": 8035, "total_steps": 61300, "loss": 0.3485, "lr": 4.985320468191811e-05, "epoch": 1.3107667210440457, "percentage": 13.11, "elapsed_time": "1:04:33", "remaining_time": "7:08:00", "throughput": 4482.34, "total_tokens": 17364000} {"current_steps": 8040, "total_steps": 61300, "loss": 0.325, "lr": 4.985243344615128e-05, "epoch": 1.3115823817292007, "percentage": 13.12, "elapsed_time": "1:04:35", "remaining_time": "7:07:53", "throughput": 4482.46, "total_tokens": 17371936} {"current_steps": 8045, "total_steps": 61300, "loss": 0.3404, "lr": 4.9851660195720095e-05, "epoch": 1.3123980424143555, "percentage": 13.12, "elapsed_time": "1:04:37", "remaining_time": "7:07:48", "throughput": 4482.68, "total_tokens": 17382304} {"current_steps": 8050, "total_steps": 61300, "loss": 0.3408, "lr": 4.985088493068724e-05, "epoch": 1.3132137030995106, "percentage": 13.13, "elapsed_time": "1:04:39", "remaining_time": "7:07:43", "throughput": 4482.87, "total_tokens": 17392000} {"current_steps": 8055, "total_steps": 61300, "loss": 0.3776, "lr": 4.985010765111555e-05, "epoch": 1.3140293637846656, "percentage": 13.14, "elapsed_time": "1:04:41", "remaining_time": "7:07:39", "throughput": 4483.08, "total_tokens": 17402528} {"current_steps": 8060, "total_steps": 61300, "loss": 0.368, "lr": 4.984932835706805e-05, "epoch": 1.3148450244698204, "percentage": 13.15, "elapsed_time": "1:04:43", "remaining_time": "7:07:34", "throughput": 4483.26, "total_tokens": 17412480} {"current_steps": 8065, "total_steps": 61300, "loss": 0.3091, "lr": 4.984854704860791e-05, "epoch": 1.3156606851549755, "percentage": 13.16, "elapsed_time": "1:04:46", "remaining_time": "7:07:31", "throughput": 4483.47, "total_tokens": 17423520} {"current_steps": 8070, "total_steps": 61300, "loss": 0.3513, "lr": 4.984776372579847e-05, "epoch": 1.3164763458401305, "percentage": 13.16, "elapsed_time": "1:04:48", "remaining_time": "7:07:27", "throughput": 4483.68, "total_tokens": 17434176} {"current_steps": 8075, "total_steps": 61300, "loss": 0.2866, "lr": 4.984697838870322e-05, "epoch": 1.3172920065252856, "percentage": 13.17, "elapsed_time": "1:04:50", "remaining_time": "7:07:24", "throughput": 4483.9, "total_tokens": 17445504} {"current_steps": 8080, "total_steps": 61300, "loss": 0.3818, "lr": 4.984619103738584e-05, "epoch": 1.3181076672104406, "percentage": 13.18, "elapsed_time": "1:04:52", "remaining_time": "7:07:21", "throughput": 4484.1, "total_tokens": 17456544} {"current_steps": 8085, "total_steps": 61300, "loss": 0.3628, "lr": 4.984540167191014e-05, "epoch": 1.3189233278955954, "percentage": 13.19, "elapsed_time": "1:04:55", "remaining_time": "7:07:16", "throughput": 4484.27, "total_tokens": 17466432} {"current_steps": 8090, "total_steps": 61300, "loss": 0.3582, "lr": 4.984461029234011e-05, "epoch": 1.3197389885807504, "percentage": 13.2, "elapsed_time": "1:04:57", "remaining_time": "7:07:13", "throughput": 4484.49, "total_tokens": 17477472} {"current_steps": 8095, "total_steps": 61300, "loss": 0.3452, "lr": 4.9843816898739913e-05, "epoch": 1.3205546492659055, "percentage": 13.21, "elapsed_time": "1:04:59", "remaining_time": "7:07:09", "throughput": 4484.62, "total_tokens": 17487360} {"current_steps": 8100, "total_steps": 61300, "loss": 0.4061, "lr": 4.984302149117387e-05, "epoch": 1.3213703099510603, "percentage": 13.21, "elapsed_time": "1:05:01", "remaining_time": "7:07:05", "throughput": 4484.76, "total_tokens": 17497568} {"current_steps": 8105, "total_steps": 61300, "loss": 0.3686, "lr": 4.984222406970644e-05, "epoch": 1.3221859706362153, "percentage": 13.22, "elapsed_time": "1:05:03", "remaining_time": "7:07:02", "throughput": 4484.93, "total_tokens": 17508768} {"current_steps": 8110, "total_steps": 61300, "loss": 0.3734, "lr": 4.984142463440229e-05, "epoch": 1.3230016313213704, "percentage": 13.23, "elapsed_time": "1:05:05", "remaining_time": "7:06:57", "throughput": 4485.09, "total_tokens": 17518368} {"current_steps": 8115, "total_steps": 61300, "loss": 0.3634, "lr": 4.984062318532621e-05, "epoch": 1.3238172920065252, "percentage": 13.24, "elapsed_time": "1:05:08", "remaining_time": "7:06:52", "throughput": 4485.26, "total_tokens": 17528416} {"current_steps": 8120, "total_steps": 61300, "loss": 0.3552, "lr": 4.983981972254317e-05, "epoch": 1.3246329526916802, "percentage": 13.25, "elapsed_time": "1:05:09", "remaining_time": "7:06:47", "throughput": 4485.42, "total_tokens": 17537600} {"current_steps": 8125, "total_steps": 61300, "loss": 0.3742, "lr": 4.983901424611832e-05, "epoch": 1.3254486133768353, "percentage": 13.25, "elapsed_time": "1:05:12", "remaining_time": "7:06:43", "throughput": 4485.63, "total_tokens": 17548736} {"current_steps": 8130, "total_steps": 61300, "loss": 0.3373, "lr": 4.9838206756116926e-05, "epoch": 1.32626427406199, "percentage": 13.26, "elapsed_time": "1:05:14", "remaining_time": "7:06:38", "throughput": 4485.8, "total_tokens": 17558336} {"current_steps": 8135, "total_steps": 61300, "loss": 0.3446, "lr": 4.983739725260448e-05, "epoch": 1.3270799347471451, "percentage": 13.27, "elapsed_time": "1:05:16", "remaining_time": "7:06:36", "throughput": 4486.05, "total_tokens": 17570272} {"current_steps": 8140, "total_steps": 61300, "loss": 0.38, "lr": 4.983658573564658e-05, "epoch": 1.3278955954323002, "percentage": 13.28, "elapsed_time": "1:05:18", "remaining_time": "7:06:32", "throughput": 4486.25, "total_tokens": 17580960} {"current_steps": 8145, "total_steps": 61300, "loss": 0.3463, "lr": 4.983577220530902e-05, "epoch": 1.3287112561174552, "percentage": 13.29, "elapsed_time": "1:05:20", "remaining_time": "7:06:27", "throughput": 4486.41, "total_tokens": 17590528} {"current_steps": 8150, "total_steps": 61300, "loss": 0.3828, "lr": 4.983495666165775e-05, "epoch": 1.32952691680261, "percentage": 13.3, "elapsed_time": "1:05:22", "remaining_time": "7:06:23", "throughput": 4486.57, "total_tokens": 17600672} {"current_steps": 8155, "total_steps": 61300, "loss": 0.3148, "lr": 4.983413910475889e-05, "epoch": 1.330342577487765, "percentage": 13.3, "elapsed_time": "1:05:25", "remaining_time": "7:06:20", "throughput": 4486.73, "total_tokens": 17611648} {"current_steps": 8160, "total_steps": 61300, "loss": 0.342, "lr": 4.98333195346787e-05, "epoch": 1.3311582381729201, "percentage": 13.31, "elapsed_time": "1:05:27", "remaining_time": "7:06:17", "throughput": 4486.93, "total_tokens": 17622656} {"current_steps": 8165, "total_steps": 61300, "loss": 0.3239, "lr": 4.983249795148363e-05, "epoch": 1.3319738988580752, "percentage": 13.32, "elapsed_time": "1:05:29", "remaining_time": "7:06:12", "throughput": 4487.11, "total_tokens": 17632864} {"current_steps": 8170, "total_steps": 61300, "loss": 0.3831, "lr": 4.983167435524027e-05, "epoch": 1.33278955954323, "percentage": 13.33, "elapsed_time": "1:05:31", "remaining_time": "7:06:09", "throughput": 4487.31, "total_tokens": 17643968} {"current_steps": 8175, "total_steps": 61300, "loss": 0.3659, "lr": 4.98308487460154e-05, "epoch": 1.333605220228385, "percentage": 13.34, "elapsed_time": "1:05:34", "remaining_time": "7:06:05", "throughput": 4487.5, "total_tokens": 17654272} {"current_steps": 8180, "total_steps": 61300, "loss": 0.3374, "lr": 4.983002112387594e-05, "epoch": 1.33442088091354, "percentage": 13.34, "elapsed_time": "1:05:36", "remaining_time": "7:06:02", "throughput": 4487.73, "total_tokens": 17665728} {"current_steps": 8185, "total_steps": 61300, "loss": 0.3826, "lr": 4.982919148888897e-05, "epoch": 1.3352365415986949, "percentage": 13.35, "elapsed_time": "1:05:38", "remaining_time": "7:06:01", "throughput": 4487.91, "total_tokens": 17677856} {"current_steps": 8190, "total_steps": 61300, "loss": 0.3115, "lr": 4.982835984112177e-05, "epoch": 1.33605220228385, "percentage": 13.36, "elapsed_time": "1:05:41", "remaining_time": "7:05:57", "throughput": 4488.12, "total_tokens": 17688672} {"current_steps": 8195, "total_steps": 61300, "loss": 0.3373, "lr": 4.982752618064174e-05, "epoch": 1.336867862969005, "percentage": 13.37, "elapsed_time": "1:05:43", "remaining_time": "7:05:54", "throughput": 4488.33, "total_tokens": 17699456} {"current_steps": 8200, "total_steps": 61300, "loss": 0.3386, "lr": 4.982669050751646e-05, "epoch": 1.3376835236541598, "percentage": 13.38, "elapsed_time": "1:05:45", "remaining_time": "7:05:51", "throughput": 4488.55, "total_tokens": 17710976} {"current_steps": 8205, "total_steps": 61300, "loss": 0.3343, "lr": 4.982585282181368e-05, "epoch": 1.3384991843393148, "percentage": 13.38, "elapsed_time": "1:05:47", "remaining_time": "7:05:47", "throughput": 4488.73, "total_tokens": 17721152} {"current_steps": 8210, "total_steps": 61300, "loss": 0.3274, "lr": 4.9825013123601305e-05, "epoch": 1.3393148450244698, "percentage": 13.39, "elapsed_time": "1:05:50", "remaining_time": "7:05:42", "throughput": 4488.88, "total_tokens": 17731200} {"current_steps": 8215, "total_steps": 61300, "loss": 0.3433, "lr": 4.9824171412947404e-05, "epoch": 1.3401305057096247, "percentage": 13.4, "elapsed_time": "1:05:52", "remaining_time": "7:05:39", "throughput": 4489.07, "total_tokens": 17741760} {"current_steps": 8220, "total_steps": 61300, "loss": 0.3723, "lr": 4.982332768992021e-05, "epoch": 1.3409461663947797, "percentage": 13.41, "elapsed_time": "1:05:54", "remaining_time": "7:05:37", "throughput": 4489.3, "total_tokens": 17754368} {"current_steps": 8225, "total_steps": 61300, "loss": 0.407, "lr": 4.982248195458812e-05, "epoch": 1.3417618270799347, "percentage": 13.42, "elapsed_time": "1:05:56", "remaining_time": "7:05:33", "throughput": 4489.47, "total_tokens": 17764096} {"current_steps": 8230, "total_steps": 61300, "loss": 0.3115, "lr": 4.98216342070197e-05, "epoch": 1.3425774877650898, "percentage": 13.43, "elapsed_time": "1:05:59", "remaining_time": "7:05:29", "throughput": 4489.64, "total_tokens": 17774784} {"current_steps": 8235, "total_steps": 61300, "loss": 0.3208, "lr": 4.982078444728367e-05, "epoch": 1.3433931484502448, "percentage": 13.43, "elapsed_time": "1:06:01", "remaining_time": "7:05:26", "throughput": 4489.84, "total_tokens": 17786112} {"current_steps": 8240, "total_steps": 61300, "loss": 0.4067, "lr": 4.981993267544891e-05, "epoch": 1.3442088091353996, "percentage": 13.44, "elapsed_time": "1:06:03", "remaining_time": "7:05:23", "throughput": 4490.03, "total_tokens": 17797120} {"current_steps": 8245, "total_steps": 61300, "loss": 0.3956, "lr": 4.9819078891584467e-05, "epoch": 1.3450244698205547, "percentage": 13.45, "elapsed_time": "1:06:05", "remaining_time": "7:05:20", "throughput": 4490.23, "total_tokens": 17808032} {"current_steps": 8250, "total_steps": 61300, "loss": 0.3825, "lr": 4.981822309575956e-05, "epoch": 1.3458401305057097, "percentage": 13.46, "elapsed_time": "1:06:08", "remaining_time": "7:05:15", "throughput": 4490.39, "total_tokens": 17818144} {"current_steps": 8255, "total_steps": 61300, "loss": 0.3715, "lr": 4.981736528804357e-05, "epoch": 1.3466557911908645, "percentage": 13.47, "elapsed_time": "1:06:10", "remaining_time": "7:05:11", "throughput": 4490.51, "total_tokens": 17828032} {"current_steps": 8260, "total_steps": 61300, "loss": 0.331, "lr": 4.9816505468506026e-05, "epoch": 1.3474714518760196, "percentage": 13.47, "elapsed_time": "1:06:12", "remaining_time": "7:05:08", "throughput": 4490.71, "total_tokens": 17839232} {"current_steps": 8265, "total_steps": 61300, "loss": 0.374, "lr": 4.981564363721663e-05, "epoch": 1.3482871125611746, "percentage": 13.48, "elapsed_time": "1:06:14", "remaining_time": "7:05:03", "throughput": 4490.87, "total_tokens": 17849088} {"current_steps": 8270, "total_steps": 61300, "loss": 0.3538, "lr": 4.981477979424524e-05, "epoch": 1.3491027732463294, "percentage": 13.49, "elapsed_time": "1:06:16", "remaining_time": "7:05:01", "throughput": 4491.09, "total_tokens": 17860512} {"current_steps": 8275, "total_steps": 61300, "loss": 0.3733, "lr": 4.98139139396619e-05, "epoch": 1.3499184339314845, "percentage": 13.5, "elapsed_time": "1:06:19", "remaining_time": "7:04:58", "throughput": 4491.27, "total_tokens": 17872000} {"current_steps": 8280, "total_steps": 61300, "loss": 0.3581, "lr": 4.981304607353678e-05, "epoch": 1.3507340946166395, "percentage": 13.51, "elapsed_time": "1:06:21", "remaining_time": "7:04:56", "throughput": 4491.48, "total_tokens": 17883712} {"current_steps": 8285, "total_steps": 61300, "loss": 0.3086, "lr": 4.981217619594026e-05, "epoch": 1.3515497553017943, "percentage": 13.52, "elapsed_time": "1:06:23", "remaining_time": "7:04:52", "throughput": 4491.62, "total_tokens": 17894240} {"current_steps": 8290, "total_steps": 61300, "loss": 0.3865, "lr": 4.981130430694283e-05, "epoch": 1.3523654159869494, "percentage": 13.52, "elapsed_time": "1:06:25", "remaining_time": "7:04:47", "throughput": 4491.79, "total_tokens": 17903904} {"current_steps": 8295, "total_steps": 61300, "loss": 0.361, "lr": 4.9810430406615194e-05, "epoch": 1.3531810766721044, "percentage": 13.53, "elapsed_time": "1:06:28", "remaining_time": "7:04:43", "throughput": 4491.92, "total_tokens": 17914208} {"current_steps": 8300, "total_steps": 61300, "loss": 0.3661, "lr": 4.980955449502818e-05, "epoch": 1.3539967373572595, "percentage": 13.54, "elapsed_time": "1:06:30", "remaining_time": "7:04:40", "throughput": 4492.07, "total_tokens": 17924640} {"current_steps": 8305, "total_steps": 61300, "loss": 0.3344, "lr": 4.980867657225279e-05, "epoch": 1.3548123980424145, "percentage": 13.55, "elapsed_time": "1:06:32", "remaining_time": "7:04:36", "throughput": 4492.26, "total_tokens": 17935520} {"current_steps": 8310, "total_steps": 61300, "loss": 0.3122, "lr": 4.980779663836019e-05, "epoch": 1.3556280587275693, "percentage": 13.56, "elapsed_time": "1:06:34", "remaining_time": "7:04:34", "throughput": 4492.44, "total_tokens": 17946848} {"current_steps": 8315, "total_steps": 61300, "loss": 0.3538, "lr": 4.980691469342174e-05, "epoch": 1.3564437194127243, "percentage": 13.56, "elapsed_time": "1:06:37", "remaining_time": "7:04:30", "throughput": 4492.61, "total_tokens": 17957568} {"current_steps": 8320, "total_steps": 61300, "loss": 0.3583, "lr": 4.98060307375089e-05, "epoch": 1.3572593800978794, "percentage": 13.57, "elapsed_time": "1:06:39", "remaining_time": "7:04:26", "throughput": 4492.81, "total_tokens": 17967776} {"current_steps": 8325, "total_steps": 61300, "loss": 0.3816, "lr": 4.980514477069336e-05, "epoch": 1.3580750407830342, "percentage": 13.58, "elapsed_time": "1:06:41", "remaining_time": "7:04:23", "throughput": 4492.97, "total_tokens": 17978688} {"current_steps": 8330, "total_steps": 61300, "loss": 0.3706, "lr": 4.980425679304691e-05, "epoch": 1.3588907014681892, "percentage": 13.59, "elapsed_time": "1:06:43", "remaining_time": "7:04:21", "throughput": 4493.15, "total_tokens": 17990432} {"current_steps": 8335, "total_steps": 61300, "loss": 0.3375, "lr": 4.9803366804641556e-05, "epoch": 1.3597063621533443, "percentage": 13.6, "elapsed_time": "1:06:46", "remaining_time": "7:04:18", "throughput": 4493.38, "total_tokens": 18001888} {"current_steps": 8340, "total_steps": 61300, "loss": 0.3975, "lr": 4.980247480554944e-05, "epoch": 1.360522022838499, "percentage": 13.61, "elapsed_time": "1:06:48", "remaining_time": "7:04:16", "throughput": 4493.52, "total_tokens": 18013536} {"current_steps": 8345, "total_steps": 61300, "loss": 0.3544, "lr": 4.980158079584286e-05, "epoch": 1.3613376835236541, "percentage": 13.61, "elapsed_time": "1:06:51", "remaining_time": "7:04:13", "throughput": 4493.7, "total_tokens": 18024864} {"current_steps": 8350, "total_steps": 61300, "loss": 0.3466, "lr": 4.9800684775594306e-05, "epoch": 1.3621533442088092, "percentage": 13.62, "elapsed_time": "1:06:53", "remaining_time": "7:04:10", "throughput": 4493.92, "total_tokens": 18036192} {"current_steps": 8355, "total_steps": 61300, "loss": 0.3593, "lr": 4.979978674487641e-05, "epoch": 1.362969004893964, "percentage": 13.63, "elapsed_time": "1:06:55", "remaining_time": "7:04:04", "throughput": 4494.03, "total_tokens": 18044864} {"current_steps": 8360, "total_steps": 61300, "loss": 0.3457, "lr": 4.979888670376196e-05, "epoch": 1.363784665579119, "percentage": 13.64, "elapsed_time": "1:06:57", "remaining_time": "7:04:02", "throughput": 4494.2, "total_tokens": 18056192} {"current_steps": 8365, "total_steps": 61300, "loss": 0.3373, "lr": 4.979798465232393e-05, "epoch": 1.364600326264274, "percentage": 13.65, "elapsed_time": "1:06:59", "remaining_time": "7:03:58", "throughput": 4494.34, "total_tokens": 18066592} {"current_steps": 8370, "total_steps": 61300, "loss": 0.3654, "lr": 4.9797080590635434e-05, "epoch": 1.3654159869494291, "percentage": 13.65, "elapsed_time": "1:07:02", "remaining_time": "7:03:54", "throughput": 4494.51, "total_tokens": 18077408} {"current_steps": 8375, "total_steps": 61300, "loss": 0.3581, "lr": 4.979617451876978e-05, "epoch": 1.366231647634584, "percentage": 13.66, "elapsed_time": "1:07:04", "remaining_time": "7:03:51", "throughput": 4494.7, "total_tokens": 18088544} {"current_steps": 8380, "total_steps": 61300, "loss": 0.3986, "lr": 4.979526643680039e-05, "epoch": 1.367047308319739, "percentage": 13.67, "elapsed_time": "1:07:06", "remaining_time": "7:03:49", "throughput": 4494.87, "total_tokens": 18100192} {"current_steps": 8385, "total_steps": 61300, "loss": 0.3356, "lr": 4.9794356344800894e-05, "epoch": 1.367862969004894, "percentage": 13.68, "elapsed_time": "1:07:08", "remaining_time": "7:03:45", "throughput": 4495.07, "total_tokens": 18110432} {"current_steps": 8390, "total_steps": 61300, "loss": 0.3318, "lr": 4.9793444242845075e-05, "epoch": 1.368678629690049, "percentage": 13.69, "elapsed_time": "1:07:11", "remaining_time": "7:03:41", "throughput": 4495.26, "total_tokens": 18120928} {"current_steps": 8395, "total_steps": 61300, "loss": 0.3351, "lr": 4.979253013100686e-05, "epoch": 1.3694942903752039, "percentage": 13.69, "elapsed_time": "1:07:13", "remaining_time": "7:03:37", "throughput": 4495.4, "total_tokens": 18131104} {"current_steps": 8400, "total_steps": 61300, "loss": 0.3387, "lr": 4.979161400936036e-05, "epoch": 1.370309951060359, "percentage": 13.7, "elapsed_time": "1:07:15", "remaining_time": "7:03:34", "throughput": 4495.63, "total_tokens": 18142720} {"current_steps": 8405, "total_steps": 61300, "loss": 0.3473, "lr": 4.979069587797984e-05, "epoch": 1.371125611745514, "percentage": 13.71, "elapsed_time": "1:07:17", "remaining_time": "7:03:31", "throughput": 4495.81, "total_tokens": 18153664} {"current_steps": 8410, "total_steps": 61300, "loss": 0.3984, "lr": 4.978977573693972e-05, "epoch": 1.3719412724306688, "percentage": 13.72, "elapsed_time": "1:07:20", "remaining_time": "7:03:28", "throughput": 4495.96, "total_tokens": 18164512} {"current_steps": 8415, "total_steps": 61300, "loss": 0.3815, "lr": 4.97888535863146e-05, "epoch": 1.3727569331158238, "percentage": 13.73, "elapsed_time": "1:07:22", "remaining_time": "7:03:24", "throughput": 4496.09, "total_tokens": 18174368} {"current_steps": 8420, "total_steps": 61300, "loss": 0.3164, "lr": 4.9787929426179224e-05, "epoch": 1.3735725938009788, "percentage": 13.74, "elapsed_time": "1:07:24", "remaining_time": "7:03:20", "throughput": 4496.29, "total_tokens": 18185216} {"current_steps": 8425, "total_steps": 61300, "loss": 0.3678, "lr": 4.978700325660852e-05, "epoch": 1.3743882544861337, "percentage": 13.74, "elapsed_time": "1:07:26", "remaining_time": "7:03:17", "throughput": 4496.47, "total_tokens": 18196256} {"current_steps": 8430, "total_steps": 61300, "loss": 0.3527, "lr": 4.978607507767757e-05, "epoch": 1.3752039151712887, "percentage": 13.75, "elapsed_time": "1:07:29", "remaining_time": "7:03:14", "throughput": 4496.65, "total_tokens": 18207264} {"current_steps": 8435, "total_steps": 61300, "loss": 0.3435, "lr": 4.9785144889461606e-05, "epoch": 1.3760195758564437, "percentage": 13.76, "elapsed_time": "1:07:31", "remaining_time": "7:03:10", "throughput": 4496.8, "total_tokens": 18217760} {"current_steps": 8440, "total_steps": 61300, "loss": 0.3548, "lr": 4.978421269203604e-05, "epoch": 1.3768352365415986, "percentage": 13.77, "elapsed_time": "1:07:33", "remaining_time": "7:03:07", "throughput": 4496.94, "total_tokens": 18228608} {"current_steps": 8445, "total_steps": 61300, "loss": 0.3924, "lr": 4.9783278485476434e-05, "epoch": 1.3776508972267536, "percentage": 13.78, "elapsed_time": "1:07:35", "remaining_time": "7:03:03", "throughput": 4497.15, "total_tokens": 18239200} {"current_steps": 8450, "total_steps": 61300, "loss": 0.3947, "lr": 4.978234226985853e-05, "epoch": 1.3784665579119086, "percentage": 13.78, "elapsed_time": "1:07:38", "remaining_time": "7:03:01", "throughput": 4497.32, "total_tokens": 18251200} {"current_steps": 8455, "total_steps": 61300, "loss": 0.3599, "lr": 4.978140404525822e-05, "epoch": 1.3792822185970637, "percentage": 13.79, "elapsed_time": "1:07:40", "remaining_time": "7:02:58", "throughput": 4497.52, "total_tokens": 18261856} {"current_steps": 8460, "total_steps": 61300, "loss": 0.3402, "lr": 4.978046381175155e-05, "epoch": 1.3800978792822187, "percentage": 13.8, "elapsed_time": "1:07:42", "remaining_time": "7:02:55", "throughput": 4497.66, "total_tokens": 18273152} {"current_steps": 8465, "total_steps": 61300, "loss": 0.4031, "lr": 4.977952156941476e-05, "epoch": 1.3809135399673735, "percentage": 13.81, "elapsed_time": "1:07:45", "remaining_time": "7:02:53", "throughput": 4497.86, "total_tokens": 18284896} {"current_steps": 8470, "total_steps": 61300, "loss": 0.3166, "lr": 4.977857731832421e-05, "epoch": 1.3817292006525286, "percentage": 13.82, "elapsed_time": "1:07:47", "remaining_time": "7:02:48", "throughput": 4498.06, "total_tokens": 18294912} {"current_steps": 8475, "total_steps": 61300, "loss": 0.3579, "lr": 4.977763105855646e-05, "epoch": 1.3825448613376836, "percentage": 13.83, "elapsed_time": "1:07:49", "remaining_time": "7:02:44", "throughput": 4498.21, "total_tokens": 18304672} {"current_steps": 8480, "total_steps": 61300, "loss": 0.3375, "lr": 4.9776682790188225e-05, "epoch": 1.3833605220228384, "percentage": 13.83, "elapsed_time": "1:07:51", "remaining_time": "7:02:41", "throughput": 4498.42, "total_tokens": 18316256} {"current_steps": 8485, "total_steps": 61300, "loss": 0.3449, "lr": 4.977573251329636e-05, "epoch": 1.3841761827079935, "percentage": 13.84, "elapsed_time": "1:07:54", "remaining_time": "7:02:39", "throughput": 4498.58, "total_tokens": 18327904} {"current_steps": 8490, "total_steps": 61300, "loss": 0.3326, "lr": 4.97747802279579e-05, "epoch": 1.3849918433931485, "percentage": 13.85, "elapsed_time": "1:07:56", "remaining_time": "7:02:36", "throughput": 4498.74, "total_tokens": 18338752} {"current_steps": 8495, "total_steps": 61300, "loss": 0.3795, "lr": 4.9773825934250056e-05, "epoch": 1.3858075040783033, "percentage": 13.86, "elapsed_time": "1:07:58", "remaining_time": "7:02:34", "throughput": 4498.94, "total_tokens": 18350464} {"current_steps": 8500, "total_steps": 61300, "loss": 0.3069, "lr": 4.977286963225018e-05, "epoch": 1.3866231647634584, "percentage": 13.87, "elapsed_time": "1:08:00", "remaining_time": "7:02:30", "throughput": 4499.11, "total_tokens": 18360832} {"current_steps": 8505, "total_steps": 61300, "loss": 0.3547, "lr": 4.9771911322035794e-05, "epoch": 1.3874388254486134, "percentage": 13.87, "elapsed_time": "1:08:03", "remaining_time": "7:02:25", "throughput": 4499.27, "total_tokens": 18370976} {"current_steps": 8510, "total_steps": 61300, "loss": 0.3496, "lr": 4.977095100368459e-05, "epoch": 1.3882544861337682, "percentage": 13.88, "elapsed_time": "1:08:05", "remaining_time": "7:02:22", "throughput": 4499.49, "total_tokens": 18381920} {"current_steps": 8515, "total_steps": 61300, "loss": 0.3789, "lr": 4.9769988677274405e-05, "epoch": 1.3890701468189233, "percentage": 13.89, "elapsed_time": "1:08:07", "remaining_time": "7:02:19", "throughput": 4499.67, "total_tokens": 18393152} {"current_steps": 8520, "total_steps": 61300, "loss": 0.379, "lr": 4.976902434288326e-05, "epoch": 1.3898858075040783, "percentage": 13.9, "elapsed_time": "1:08:09", "remaining_time": "7:02:15", "throughput": 4499.77, "total_tokens": 18403168} {"current_steps": 8525, "total_steps": 61300, "loss": 0.3443, "lr": 4.9768058000589325e-05, "epoch": 1.3907014681892333, "percentage": 13.91, "elapsed_time": "1:08:12", "remaining_time": "7:02:12", "throughput": 4499.93, "total_tokens": 18413792} {"current_steps": 8530, "total_steps": 61300, "loss": 0.3697, "lr": 4.976708965047093e-05, "epoch": 1.3915171288743884, "percentage": 13.92, "elapsed_time": "1:08:14", "remaining_time": "7:02:09", "throughput": 4500.1, "total_tokens": 18424864} {"current_steps": 8535, "total_steps": 61300, "loss": 0.3318, "lr": 4.976611929260659e-05, "epoch": 1.3923327895595432, "percentage": 13.92, "elapsed_time": "1:08:16", "remaining_time": "7:02:03", "throughput": 4500.24, "total_tokens": 18434144} {"current_steps": 8540, "total_steps": 61300, "loss": 0.3433, "lr": 4.976514692707496e-05, "epoch": 1.3931484502446982, "percentage": 13.93, "elapsed_time": "1:08:18", "remaining_time": "7:02:00", "throughput": 4500.38, "total_tokens": 18444576} {"current_steps": 8545, "total_steps": 61300, "loss": 0.3411, "lr": 4.9764172553954855e-05, "epoch": 1.3939641109298533, "percentage": 13.94, "elapsed_time": "1:08:20", "remaining_time": "7:01:57", "throughput": 4500.57, "total_tokens": 18455808} {"current_steps": 8550, "total_steps": 61300, "loss": 0.3437, "lr": 4.976319617332527e-05, "epoch": 1.394779771615008, "percentage": 13.95, "elapsed_time": "1:08:23", "remaining_time": "7:01:54", "throughput": 4500.76, "total_tokens": 18466848} {"current_steps": 8555, "total_steps": 61300, "loss": 0.3321, "lr": 4.9762217785265356e-05, "epoch": 1.3955954323001631, "percentage": 13.96, "elapsed_time": "1:08:25", "remaining_time": "7:01:52", "throughput": 4500.97, "total_tokens": 18479040} {"current_steps": 8560, "total_steps": 61300, "loss": 0.3903, "lr": 4.976123738985443e-05, "epoch": 1.3964110929853182, "percentage": 13.96, "elapsed_time": "1:08:27", "remaining_time": "7:01:49", "throughput": 4501.11, "total_tokens": 18490080} {"current_steps": 8565, "total_steps": 61300, "loss": 0.382, "lr": 4.976025498717196e-05, "epoch": 1.397226753670473, "percentage": 13.97, "elapsed_time": "1:08:30", "remaining_time": "7:01:47", "throughput": 4501.28, "total_tokens": 18501632} {"current_steps": 8570, "total_steps": 61300, "loss": 0.3287, "lr": 4.9759270577297603e-05, "epoch": 1.398042414355628, "percentage": 13.98, "elapsed_time": "1:08:32", "remaining_time": "7:01:44", "throughput": 4501.47, "total_tokens": 18513056} {"current_steps": 8575, "total_steps": 61300, "loss": 0.3537, "lr": 4.975828416031113e-05, "epoch": 1.398858075040783, "percentage": 13.99, "elapsed_time": "1:08:34", "remaining_time": "7:01:40", "throughput": 4501.66, "total_tokens": 18523616} {"current_steps": 8580, "total_steps": 61300, "loss": 0.3975, "lr": 4.975729573629252e-05, "epoch": 1.399673735725938, "percentage": 14.0, "elapsed_time": "1:08:37", "remaining_time": "7:01:37", "throughput": 4501.85, "total_tokens": 18534688} {"current_steps": 8585, "total_steps": 61300, "loss": 0.3625, "lr": 4.9756305305321906e-05, "epoch": 1.400489396411093, "percentage": 14.0, "elapsed_time": "1:08:39", "remaining_time": "7:01:33", "throughput": 4502.03, "total_tokens": 18545120} {"current_steps": 8590, "total_steps": 61300, "loss": 0.4013, "lr": 4.975531286747958e-05, "epoch": 1.401305057096248, "percentage": 14.01, "elapsed_time": "1:08:41", "remaining_time": "7:01:30", "throughput": 4502.23, "total_tokens": 18556224} {"current_steps": 8595, "total_steps": 61300, "loss": 0.362, "lr": 4.975431842284597e-05, "epoch": 1.402120717781403, "percentage": 14.02, "elapsed_time": "1:08:43", "remaining_time": "7:01:26", "throughput": 4502.35, "total_tokens": 18566272} {"current_steps": 8600, "total_steps": 61300, "loss": 0.3436, "lr": 4.975332197150171e-05, "epoch": 1.4029363784665578, "percentage": 14.03, "elapsed_time": "1:08:45", "remaining_time": "7:01:23", "throughput": 4502.51, "total_tokens": 18577216} {"current_steps": 8605, "total_steps": 61300, "loss": 0.3672, "lr": 4.975232351352758e-05, "epoch": 1.4037520391517129, "percentage": 14.04, "elapsed_time": "1:08:47", "remaining_time": "7:01:18", "throughput": 4502.69, "total_tokens": 18587072} {"current_steps": 8610, "total_steps": 61300, "loss": 0.3592, "lr": 4.975132304900451e-05, "epoch": 1.404567699836868, "percentage": 14.05, "elapsed_time": "1:08:50", "remaining_time": "7:01:15", "throughput": 4502.87, "total_tokens": 18598112} {"current_steps": 8615, "total_steps": 61300, "loss": 0.3584, "lr": 4.975032057801361e-05, "epoch": 1.405383360522023, "percentage": 14.05, "elapsed_time": "1:08:52", "remaining_time": "7:01:11", "throughput": 4503.07, "total_tokens": 18608384} {"current_steps": 8620, "total_steps": 61300, "loss": 0.3822, "lr": 4.974931610063613e-05, "epoch": 1.4061990212071778, "percentage": 14.06, "elapsed_time": "1:08:54", "remaining_time": "7:01:07", "throughput": 4503.26, "total_tokens": 18618944} {"current_steps": 8625, "total_steps": 61300, "loss": 0.3659, "lr": 4.974830961695353e-05, "epoch": 1.4070146818923328, "percentage": 14.07, "elapsed_time": "1:08:56", "remaining_time": "7:01:03", "throughput": 4503.42, "total_tokens": 18629248} {"current_steps": 8630, "total_steps": 61300, "loss": 0.324, "lr": 4.9747301127047366e-05, "epoch": 1.4078303425774878, "percentage": 14.08, "elapsed_time": "1:08:59", "remaining_time": "7:01:01", "throughput": 4503.61, "total_tokens": 18641248} {"current_steps": 8635, "total_steps": 61300, "loss": 0.3586, "lr": 4.974629063099942e-05, "epoch": 1.4086460032626427, "percentage": 14.09, "elapsed_time": "1:09:01", "remaining_time": "7:00:58", "throughput": 4503.74, "total_tokens": 18651520} {"current_steps": 8640, "total_steps": 61300, "loss": 0.3452, "lr": 4.974527812889158e-05, "epoch": 1.4094616639477977, "percentage": 14.09, "elapsed_time": "1:09:03", "remaining_time": "7:00:54", "throughput": 4503.9, "total_tokens": 18662304} {"current_steps": 8645, "total_steps": 61300, "loss": 0.3498, "lr": 4.974426362080594e-05, "epoch": 1.4102773246329527, "percentage": 14.1, "elapsed_time": "1:09:05", "remaining_time": "7:00:50", "throughput": 4504.07, "total_tokens": 18672416} {"current_steps": 8650, "total_steps": 61300, "loss": 0.3298, "lr": 4.974324710682474e-05, "epoch": 1.4110929853181076, "percentage": 14.11, "elapsed_time": "1:09:07", "remaining_time": "7:00:47", "throughput": 4504.21, "total_tokens": 18683136} {"current_steps": 8655, "total_steps": 61300, "loss": 0.3564, "lr": 4.974222858703039e-05, "epoch": 1.4119086460032626, "percentage": 14.12, "elapsed_time": "1:09:10", "remaining_time": "7:00:43", "throughput": 4504.41, "total_tokens": 18693472} {"current_steps": 8660, "total_steps": 61300, "loss": 0.3435, "lr": 4.9741208061505454e-05, "epoch": 1.4127243066884176, "percentage": 14.13, "elapsed_time": "1:09:12", "remaining_time": "7:00:39", "throughput": 4504.58, "total_tokens": 18704128} {"current_steps": 8665, "total_steps": 61300, "loss": 0.3319, "lr": 4.974018553033264e-05, "epoch": 1.4135399673735725, "percentage": 14.14, "elapsed_time": "1:09:14", "remaining_time": "7:00:36", "throughput": 4504.77, "total_tokens": 18715456} {"current_steps": 8670, "total_steps": 61300, "loss": 0.3198, "lr": 4.973916099359487e-05, "epoch": 1.4143556280587275, "percentage": 14.14, "elapsed_time": "1:09:16", "remaining_time": "7:00:33", "throughput": 4504.97, "total_tokens": 18726240} {"current_steps": 8675, "total_steps": 61300, "loss": 0.3825, "lr": 4.973813445137518e-05, "epoch": 1.4151712887438825, "percentage": 14.15, "elapsed_time": "1:09:19", "remaining_time": "7:00:29", "throughput": 4505.14, "total_tokens": 18736992} {"current_steps": 8680, "total_steps": 61300, "loss": 0.3037, "lr": 4.9737105903756794e-05, "epoch": 1.4159869494290376, "percentage": 14.16, "elapsed_time": "1:09:21", "remaining_time": "7:00:28", "throughput": 4505.35, "total_tokens": 18749216} {"current_steps": 8685, "total_steps": 61300, "loss": 0.3677, "lr": 4.973607535082309e-05, "epoch": 1.4168026101141926, "percentage": 14.17, "elapsed_time": "1:09:23", "remaining_time": "7:00:25", "throughput": 4505.53, "total_tokens": 18760352} {"current_steps": 8690, "total_steps": 61300, "loss": 0.3613, "lr": 4.97350427926576e-05, "epoch": 1.4176182707993474, "percentage": 14.18, "elapsed_time": "1:09:25", "remaining_time": "7:00:20", "throughput": 4505.65, "total_tokens": 18769792} {"current_steps": 8695, "total_steps": 61300, "loss": 0.3286, "lr": 4.973400822934404e-05, "epoch": 1.4184339314845025, "percentage": 14.18, "elapsed_time": "1:09:28", "remaining_time": "7:00:18", "throughput": 4505.88, "total_tokens": 18781696} {"current_steps": 8700, "total_steps": 61300, "loss": 0.3047, "lr": 4.973297166096628e-05, "epoch": 1.4192495921696575, "percentage": 14.19, "elapsed_time": "1:09:30", "remaining_time": "7:00:12", "throughput": 4506.03, "total_tokens": 18790912} {"current_steps": 8705, "total_steps": 61300, "loss": 0.3329, "lr": 4.9731933087608334e-05, "epoch": 1.4200652528548123, "percentage": 14.2, "elapsed_time": "1:09:32", "remaining_time": "7:00:08", "throughput": 4506.14, "total_tokens": 18800672} {"current_steps": 8710, "total_steps": 61300, "loss": 0.3714, "lr": 4.973089250935441e-05, "epoch": 1.4208809135399674, "percentage": 14.21, "elapsed_time": "1:09:34", "remaining_time": "7:00:05", "throughput": 4506.38, "total_tokens": 18812032} {"current_steps": 8715, "total_steps": 61300, "loss": 0.4078, "lr": 4.972984992628885e-05, "epoch": 1.4216965742251224, "percentage": 14.22, "elapsed_time": "1:09:36", "remaining_time": "7:00:02", "throughput": 4506.61, "total_tokens": 18823328} {"current_steps": 8720, "total_steps": 61300, "loss": 0.3604, "lr": 4.972880533849619e-05, "epoch": 1.4225122349102772, "percentage": 14.23, "elapsed_time": "1:09:39", "remaining_time": "6:59:59", "throughput": 4506.75, "total_tokens": 18834048} {"current_steps": 8725, "total_steps": 61300, "loss": 0.3218, "lr": 4.9727758746061084e-05, "epoch": 1.4233278955954323, "percentage": 14.23, "elapsed_time": "1:09:41", "remaining_time": "6:59:56", "throughput": 4506.91, "total_tokens": 18845216} {"current_steps": 8730, "total_steps": 61300, "loss": 0.3858, "lr": 4.972671014906839e-05, "epoch": 1.4241435562805873, "percentage": 14.24, "elapsed_time": "1:09:43", "remaining_time": "6:59:51", "throughput": 4507.08, "total_tokens": 18854848} {"current_steps": 8735, "total_steps": 61300, "loss": 0.298, "lr": 4.972565954760311e-05, "epoch": 1.4249592169657421, "percentage": 14.25, "elapsed_time": "1:09:45", "remaining_time": "6:59:48", "throughput": 4507.26, "total_tokens": 18866368} {"current_steps": 8740, "total_steps": 61300, "loss": 0.3889, "lr": 4.9724606941750406e-05, "epoch": 1.4257748776508972, "percentage": 14.26, "elapsed_time": "1:09:48", "remaining_time": "6:59:46", "throughput": 4507.5, "total_tokens": 18878464} {"current_steps": 8745, "total_steps": 61300, "loss": 0.3521, "lr": 4.972355233159562e-05, "epoch": 1.4265905383360522, "percentage": 14.27, "elapsed_time": "1:09:50", "remaining_time": "6:59:44", "throughput": 4507.7, "total_tokens": 18889856} {"current_steps": 8750, "total_steps": 61300, "loss": 0.3695, "lr": 4.972249571722423e-05, "epoch": 1.4274061990212072, "percentage": 14.27, "elapsed_time": "1:09:52", "remaining_time": "6:59:40", "throughput": 4507.87, "total_tokens": 18900352} {"current_steps": 8755, "total_steps": 61300, "loss": 0.32, "lr": 4.97214370987219e-05, "epoch": 1.4282218597063623, "percentage": 14.28, "elapsed_time": "1:09:55", "remaining_time": "6:59:37", "throughput": 4508.07, "total_tokens": 18911936} {"current_steps": 8760, "total_steps": 61300, "loss": 0.3362, "lr": 4.972037647617444e-05, "epoch": 1.429037520391517, "percentage": 14.29, "elapsed_time": "1:09:57", "remaining_time": "6:59:34", "throughput": 4508.18, "total_tokens": 18922048} {"current_steps": 8765, "total_steps": 61300, "loss": 0.3419, "lr": 4.9719313849667835e-05, "epoch": 1.4298531810766721, "percentage": 14.3, "elapsed_time": "1:09:59", "remaining_time": "6:59:30", "throughput": 4508.32, "total_tokens": 18932288} {"current_steps": 8770, "total_steps": 61300, "loss": 0.3327, "lr": 4.9718249219288226e-05, "epoch": 1.4306688417618272, "percentage": 14.31, "elapsed_time": "1:10:01", "remaining_time": "6:59:26", "throughput": 4508.5, "total_tokens": 18943008} {"current_steps": 8775, "total_steps": 61300, "loss": 0.3889, "lr": 4.971718258512191e-05, "epoch": 1.431484502446982, "percentage": 14.31, "elapsed_time": "1:10:03", "remaining_time": "6:59:22", "throughput": 4508.66, "total_tokens": 18953376} {"current_steps": 8780, "total_steps": 61300, "loss": 0.3498, "lr": 4.971611394725537e-05, "epoch": 1.432300163132137, "percentage": 14.32, "elapsed_time": "1:10:06", "remaining_time": "6:59:21", "throughput": 4508.88, "total_tokens": 18965600} {"current_steps": 8785, "total_steps": 61300, "loss": 0.3755, "lr": 4.971504330577521e-05, "epoch": 1.433115823817292, "percentage": 14.33, "elapsed_time": "1:10:08", "remaining_time": "6:59:17", "throughput": 4509.04, "total_tokens": 18975936} {"current_steps": 8790, "total_steps": 61300, "loss": 0.3349, "lr": 4.971397066076825e-05, "epoch": 1.433931484502447, "percentage": 14.34, "elapsed_time": "1:10:10", "remaining_time": "6:59:12", "throughput": 4509.2, "total_tokens": 18986048} {"current_steps": 8795, "total_steps": 61300, "loss": 0.3387, "lr": 4.971289601232143e-05, "epoch": 1.434747145187602, "percentage": 14.35, "elapsed_time": "1:10:12", "remaining_time": "6:59:09", "throughput": 4509.37, "total_tokens": 18997056} {"current_steps": 8800, "total_steps": 61300, "loss": 0.3004, "lr": 4.971181936052186e-05, "epoch": 1.435562805872757, "percentage": 14.36, "elapsed_time": "1:10:14", "remaining_time": "6:59:06", "throughput": 4509.56, "total_tokens": 19007744} {"current_steps": 8805, "total_steps": 61300, "loss": 0.3157, "lr": 4.971074070545684e-05, "epoch": 1.4363784665579118, "percentage": 14.36, "elapsed_time": "1:10:17", "remaining_time": "6:59:03", "throughput": 4509.71, "total_tokens": 19018784} {"current_steps": 8810, "total_steps": 61300, "loss": 0.3215, "lr": 4.970966004721378e-05, "epoch": 1.4371941272430668, "percentage": 14.37, "elapsed_time": "1:10:19", "remaining_time": "6:59:00", "throughput": 4509.89, "total_tokens": 19030176} {"current_steps": 8815, "total_steps": 61300, "loss": 0.3737, "lr": 4.970857738588031e-05, "epoch": 1.4380097879282219, "percentage": 14.38, "elapsed_time": "1:10:21", "remaining_time": "6:58:57", "throughput": 4510.05, "total_tokens": 19041088} {"current_steps": 8820, "total_steps": 61300, "loss": 0.4292, "lr": 4.9707492721544185e-05, "epoch": 1.438825448613377, "percentage": 14.39, "elapsed_time": "1:10:24", "remaining_time": "6:58:54", "throughput": 4510.22, "total_tokens": 19052352} {"current_steps": 8825, "total_steps": 61300, "loss": 0.3797, "lr": 4.970640605429334e-05, "epoch": 1.4396411092985317, "percentage": 14.4, "elapsed_time": "1:10:26", "remaining_time": "6:58:50", "throughput": 4510.4, "total_tokens": 19062688} {"current_steps": 8830, "total_steps": 61300, "loss": 0.3138, "lr": 4.970531738421585e-05, "epoch": 1.4404567699836868, "percentage": 14.4, "elapsed_time": "1:10:28", "remaining_time": "6:58:47", "throughput": 4510.55, "total_tokens": 19073504} {"current_steps": 8835, "total_steps": 61300, "loss": 0.3189, "lr": 4.970422671139999e-05, "epoch": 1.4412724306688418, "percentage": 14.41, "elapsed_time": "1:10:31", "remaining_time": "6:58:46", "throughput": 4510.74, "total_tokens": 19085792} {"current_steps": 8840, "total_steps": 61300, "loss": 0.3443, "lr": 4.970313403593416e-05, "epoch": 1.4420880913539968, "percentage": 14.42, "elapsed_time": "1:10:33", "remaining_time": "6:58:42", "throughput": 4510.9, "total_tokens": 19096512} {"current_steps": 8845, "total_steps": 61300, "loss": 0.3464, "lr": 4.970203935790695e-05, "epoch": 1.4429037520391517, "percentage": 14.43, "elapsed_time": "1:10:35", "remaining_time": "6:58:38", "throughput": 4511.04, "total_tokens": 19106336} {"current_steps": 8850, "total_steps": 61300, "loss": 0.3352, "lr": 4.970094267740708e-05, "epoch": 1.4437194127243067, "percentage": 14.44, "elapsed_time": "1:10:37", "remaining_time": "6:58:34", "throughput": 4511.18, "total_tokens": 19116800} {"current_steps": 8855, "total_steps": 61300, "loss": 0.4176, "lr": 4.969984399452347e-05, "epoch": 1.4445350734094617, "percentage": 14.45, "elapsed_time": "1:10:39", "remaining_time": "6:58:31", "throughput": 4511.31, "total_tokens": 19127488} {"current_steps": 8860, "total_steps": 61300, "loss": 0.3176, "lr": 4.9698743309345184e-05, "epoch": 1.4453507340946166, "percentage": 14.45, "elapsed_time": "1:10:41", "remaining_time": "6:58:24", "throughput": 4511.44, "total_tokens": 19135264} {"current_steps": 8865, "total_steps": 61300, "loss": 0.3423, "lr": 4.969764062196145e-05, "epoch": 1.4461663947797716, "percentage": 14.46, "elapsed_time": "1:10:43", "remaining_time": "6:58:21", "throughput": 4511.63, "total_tokens": 19146656} {"current_steps": 8870, "total_steps": 61300, "loss": 0.3697, "lr": 4.969653593246164e-05, "epoch": 1.4469820554649266, "percentage": 14.47, "elapsed_time": "1:10:46", "remaining_time": "6:58:20", "throughput": 4511.82, "total_tokens": 19158880} {"current_steps": 8875, "total_steps": 61300, "loss": 0.3734, "lr": 4.9695429240935335e-05, "epoch": 1.4477977161500815, "percentage": 14.48, "elapsed_time": "1:10:48", "remaining_time": "6:58:17", "throughput": 4511.97, "total_tokens": 19170240} {"current_steps": 8880, "total_steps": 61300, "loss": 0.3422, "lr": 4.9694320547472215e-05, "epoch": 1.4486133768352365, "percentage": 14.49, "elapsed_time": "1:10:50", "remaining_time": "6:58:14", "throughput": 4512.11, "total_tokens": 19180960} {"current_steps": 8885, "total_steps": 61300, "loss": 0.3224, "lr": 4.9693209852162184e-05, "epoch": 1.4494290375203915, "percentage": 14.49, "elapsed_time": "1:10:53", "remaining_time": "6:58:11", "throughput": 4512.28, "total_tokens": 19192576} {"current_steps": 8890, "total_steps": 61300, "loss": 0.3364, "lr": 4.969209715509526e-05, "epoch": 1.4502446982055464, "percentage": 14.5, "elapsed_time": "1:10:55", "remaining_time": "6:58:07", "throughput": 4512.43, "total_tokens": 19202752} {"current_steps": 8895, "total_steps": 61300, "loss": 0.3693, "lr": 4.969098245636167e-05, "epoch": 1.4510603588907014, "percentage": 14.51, "elapsed_time": "1:10:57", "remaining_time": "6:58:05", "throughput": 4512.62, "total_tokens": 19214048} {"current_steps": 8900, "total_steps": 61300, "loss": 0.3503, "lr": 4.968986575605175e-05, "epoch": 1.4518760195758564, "percentage": 14.52, "elapsed_time": "1:11:00", "remaining_time": "6:58:02", "throughput": 4512.78, "total_tokens": 19225056} {"current_steps": 8905, "total_steps": 61300, "loss": 0.3595, "lr": 4.968874705425604e-05, "epoch": 1.4526916802610115, "percentage": 14.53, "elapsed_time": "1:11:02", "remaining_time": "6:57:59", "throughput": 4512.94, "total_tokens": 19236480} {"current_steps": 8910, "total_steps": 61300, "loss": 0.3604, "lr": 4.968762635106522e-05, "epoch": 1.4535073409461665, "percentage": 14.54, "elapsed_time": "1:11:04", "remaining_time": "6:57:57", "throughput": 4513.12, "total_tokens": 19248192} {"current_steps": 8915, "total_steps": 61300, "loss": 0.3389, "lr": 4.9686503646570146e-05, "epoch": 1.4543230016313213, "percentage": 14.54, "elapsed_time": "1:11:07", "remaining_time": "6:57:53", "throughput": 4513.24, "total_tokens": 19258368} {"current_steps": 8920, "total_steps": 61300, "loss": 0.3566, "lr": 4.9685378940861826e-05, "epoch": 1.4551386623164764, "percentage": 14.55, "elapsed_time": "1:11:09", "remaining_time": "6:57:50", "throughput": 4513.35, "total_tokens": 19269088} {"current_steps": 8925, "total_steps": 61300, "loss": 0.3444, "lr": 4.9684252234031446e-05, "epoch": 1.4559543230016314, "percentage": 14.56, "elapsed_time": "1:11:11", "remaining_time": "6:57:47", "throughput": 4513.5, "total_tokens": 19280384} {"current_steps": 8930, "total_steps": 61300, "loss": 0.3662, "lr": 4.968312352617033e-05, "epoch": 1.4567699836867862, "percentage": 14.57, "elapsed_time": "1:11:14", "remaining_time": "6:57:45", "throughput": 4513.68, "total_tokens": 19292192} {"current_steps": 8935, "total_steps": 61300, "loss": 0.4052, "lr": 4.968199281736997e-05, "epoch": 1.4575856443719413, "percentage": 14.58, "elapsed_time": "1:11:16", "remaining_time": "6:57:43", "throughput": 4513.88, "total_tokens": 19303904} {"current_steps": 8940, "total_steps": 61300, "loss": 0.3646, "lr": 4.968086010772205e-05, "epoch": 1.4584013050570963, "percentage": 14.58, "elapsed_time": "1:11:18", "remaining_time": "6:57:41", "throughput": 4514.08, "total_tokens": 19315712} {"current_steps": 8945, "total_steps": 61300, "loss": 0.3444, "lr": 4.9679725397318375e-05, "epoch": 1.4592169657422511, "percentage": 14.59, "elapsed_time": "1:11:21", "remaining_time": "6:57:38", "throughput": 4514.24, "total_tokens": 19326848} {"current_steps": 8950, "total_steps": 61300, "loss": 0.3173, "lr": 4.967858868625094e-05, "epoch": 1.4600326264274062, "percentage": 14.6, "elapsed_time": "1:11:23", "remaining_time": "6:57:36", "throughput": 4514.43, "total_tokens": 19338496} {"current_steps": 8955, "total_steps": 61300, "loss": 0.414, "lr": 4.967744997461188e-05, "epoch": 1.4608482871125612, "percentage": 14.61, "elapsed_time": "1:11:25", "remaining_time": "6:57:32", "throughput": 4514.62, "total_tokens": 19348992} {"current_steps": 8960, "total_steps": 61300, "loss": 0.3773, "lr": 4.9676309262493513e-05, "epoch": 1.461663947797716, "percentage": 14.62, "elapsed_time": "1:11:28", "remaining_time": "6:57:29", "throughput": 4514.74, "total_tokens": 19359680} {"current_steps": 8965, "total_steps": 61300, "loss": 0.3757, "lr": 4.9675166549988314e-05, "epoch": 1.462479608482871, "percentage": 14.62, "elapsed_time": "1:11:30", "remaining_time": "6:57:26", "throughput": 4514.92, "total_tokens": 19370848} {"current_steps": 8970, "total_steps": 61300, "loss": 0.3723, "lr": 4.9674021837188917e-05, "epoch": 1.463295269168026, "percentage": 14.63, "elapsed_time": "1:11:32", "remaining_time": "6:57:23", "throughput": 4515.09, "total_tokens": 19381888} {"current_steps": 8975, "total_steps": 61300, "loss": 0.3565, "lr": 4.967287512418811e-05, "epoch": 1.4641109298531811, "percentage": 14.64, "elapsed_time": "1:11:34", "remaining_time": "6:57:19", "throughput": 4515.27, "total_tokens": 19392768} {"current_steps": 8980, "total_steps": 61300, "loss": 0.3432, "lr": 4.9671726411078864e-05, "epoch": 1.4649265905383362, "percentage": 14.65, "elapsed_time": "1:11:37", "remaining_time": "6:57:16", "throughput": 4515.45, "total_tokens": 19403488} {"current_steps": 8985, "total_steps": 61300, "loss": 0.3464, "lr": 4.967057569795428e-05, "epoch": 1.465742251223491, "percentage": 14.66, "elapsed_time": "1:11:39", "remaining_time": "6:57:13", "throughput": 4515.6, "total_tokens": 19414656} {"current_steps": 8990, "total_steps": 61300, "loss": 0.3621, "lr": 4.966942298490767e-05, "epoch": 1.466557911908646, "percentage": 14.67, "elapsed_time": "1:11:41", "remaining_time": "6:57:09", "throughput": 4515.72, "total_tokens": 19424960} {"current_steps": 8995, "total_steps": 61300, "loss": 0.3279, "lr": 4.966826827203245e-05, "epoch": 1.467373572593801, "percentage": 14.67, "elapsed_time": "1:11:44", "remaining_time": "6:57:07", "throughput": 4515.91, "total_tokens": 19436512} {"current_steps": 9000, "total_steps": 61300, "loss": 0.3046, "lr": 4.966711155942223e-05, "epoch": 1.468189233278956, "percentage": 14.68, "elapsed_time": "1:11:46", "remaining_time": "6:57:04", "throughput": 4516.07, "total_tokens": 19447808} {"current_steps": 9005, "total_steps": 61300, "loss": 0.2931, "lr": 4.966595284717081e-05, "epoch": 1.469004893964111, "percentage": 14.69, "elapsed_time": "1:11:48", "remaining_time": "6:57:00", "throughput": 4516.22, "total_tokens": 19457984} {"current_steps": 9010, "total_steps": 61300, "loss": 0.3164, "lr": 4.966479213537207e-05, "epoch": 1.469820554649266, "percentage": 14.7, "elapsed_time": "1:11:50", "remaining_time": "6:56:56", "throughput": 4516.38, "total_tokens": 19467680} {"current_steps": 9015, "total_steps": 61300, "loss": 0.4149, "lr": 4.966362942412015e-05, "epoch": 1.4706362153344208, "percentage": 14.71, "elapsed_time": "1:11:52", "remaining_time": "6:56:49", "throughput": 4516.49, "total_tokens": 19475968} {"current_steps": 9020, "total_steps": 61300, "loss": 0.3343, "lr": 4.9662464713509285e-05, "epoch": 1.4714518760195758, "percentage": 14.71, "elapsed_time": "1:11:54", "remaining_time": "6:56:47", "throughput": 4516.62, "total_tokens": 19487328} {"current_steps": 9025, "total_steps": 61300, "loss": 0.3005, "lr": 4.966129800363389e-05, "epoch": 1.4722675367047309, "percentage": 14.72, "elapsed_time": "1:11:56", "remaining_time": "6:56:43", "throughput": 4516.74, "total_tokens": 19497280} {"current_steps": 9030, "total_steps": 61300, "loss": 0.3571, "lr": 4.9660129294588554e-05, "epoch": 1.4730831973898857, "percentage": 14.73, "elapsed_time": "1:11:58", "remaining_time": "6:56:39", "throughput": 4516.88, "total_tokens": 19507264} {"current_steps": 9035, "total_steps": 61300, "loss": 0.3587, "lr": 4.965895858646801e-05, "epoch": 1.4738988580750407, "percentage": 14.74, "elapsed_time": "1:12:00", "remaining_time": "6:56:35", "throughput": 4517.05, "total_tokens": 19518080} {"current_steps": 9040, "total_steps": 61300, "loss": 0.3075, "lr": 4.9657785879367166e-05, "epoch": 1.4747145187601958, "percentage": 14.75, "elapsed_time": "1:12:03", "remaining_time": "6:56:31", "throughput": 4517.17, "total_tokens": 19528288} {"current_steps": 9045, "total_steps": 61300, "loss": 0.361, "lr": 4.965661117338108e-05, "epoch": 1.4755301794453508, "percentage": 14.76, "elapsed_time": "1:12:05", "remaining_time": "6:56:28", "throughput": 4517.33, "total_tokens": 19539072} {"current_steps": 9050, "total_steps": 61300, "loss": 0.3714, "lr": 4.9655434468605e-05, "epoch": 1.4763458401305056, "percentage": 14.76, "elapsed_time": "1:12:07", "remaining_time": "6:56:25", "throughput": 4517.52, "total_tokens": 19550496} {"current_steps": 9055, "total_steps": 61300, "loss": 0.346, "lr": 4.9654255765134294e-05, "epoch": 1.4771615008156607, "percentage": 14.77, "elapsed_time": "1:12:10", "remaining_time": "6:56:24", "throughput": 4517.77, "total_tokens": 19562752} {"current_steps": 9060, "total_steps": 61300, "loss": 0.3368, "lr": 4.965307506306452e-05, "epoch": 1.4779771615008157, "percentage": 14.78, "elapsed_time": "1:12:12", "remaining_time": "6:56:19", "throughput": 4517.91, "total_tokens": 19572512} {"current_steps": 9065, "total_steps": 61300, "loss": 0.3461, "lr": 4.965189236249139e-05, "epoch": 1.4787928221859707, "percentage": 14.79, "elapsed_time": "1:12:14", "remaining_time": "6:56:15", "throughput": 4518.07, "total_tokens": 19582752} {"current_steps": 9070, "total_steps": 61300, "loss": 0.348, "lr": 4.9650707663510785e-05, "epoch": 1.4796084828711256, "percentage": 14.8, "elapsed_time": "1:12:16", "remaining_time": "6:56:11", "throughput": 4518.22, "total_tokens": 19593184} {"current_steps": 9075, "total_steps": 61300, "loss": 0.3221, "lr": 4.9649520966218744e-05, "epoch": 1.4804241435562806, "percentage": 14.8, "elapsed_time": "1:12:18", "remaining_time": "6:56:09", "throughput": 4518.41, "total_tokens": 19604768} {"current_steps": 9080, "total_steps": 61300, "loss": 0.3597, "lr": 4.9648332270711463e-05, "epoch": 1.4812398042414356, "percentage": 14.81, "elapsed_time": "1:12:21", "remaining_time": "6:56:07", "throughput": 4518.61, "total_tokens": 19616576} {"current_steps": 9085, "total_steps": 61300, "loss": 0.3341, "lr": 4.96471415770853e-05, "epoch": 1.4820554649265905, "percentage": 14.82, "elapsed_time": "1:12:23", "remaining_time": "6:56:05", "throughput": 4518.75, "total_tokens": 19628384} {"current_steps": 9090, "total_steps": 61300, "loss": 0.3555, "lr": 4.964594888543678e-05, "epoch": 1.4828711256117455, "percentage": 14.83, "elapsed_time": "1:12:25", "remaining_time": "6:56:01", "throughput": 4518.96, "total_tokens": 19639136} {"current_steps": 9095, "total_steps": 61300, "loss": 0.3181, "lr": 4.9644754195862597e-05, "epoch": 1.4836867862969005, "percentage": 14.84, "elapsed_time": "1:12:28", "remaining_time": "6:55:58", "throughput": 4519.08, "total_tokens": 19649856} {"current_steps": 9100, "total_steps": 61300, "loss": 0.3287, "lr": 4.964355750845959e-05, "epoch": 1.4845024469820554, "percentage": 14.85, "elapsed_time": "1:12:30", "remaining_time": "6:55:55", "throughput": 4519.26, "total_tokens": 19661120} {"current_steps": 9105, "total_steps": 61300, "loss": 0.3084, "lr": 4.9642358823324776e-05, "epoch": 1.4853181076672104, "percentage": 14.85, "elapsed_time": "1:12:32", "remaining_time": "6:55:51", "throughput": 4519.44, "total_tokens": 19671648} {"current_steps": 9110, "total_steps": 61300, "loss": 0.3142, "lr": 4.964115814055531e-05, "epoch": 1.4861337683523654, "percentage": 14.86, "elapsed_time": "1:12:35", "remaining_time": "6:55:50", "throughput": 4519.6, "total_tokens": 19683584} {"current_steps": 9115, "total_steps": 61300, "loss": 0.3811, "lr": 4.963995546024854e-05, "epoch": 1.4869494290375203, "percentage": 14.87, "elapsed_time": "1:12:37", "remaining_time": "6:55:46", "throughput": 4519.75, "total_tokens": 19694080} {"current_steps": 9120, "total_steps": 61300, "loss": 0.3436, "lr": 4.963875078250197e-05, "epoch": 1.4877650897226753, "percentage": 14.88, "elapsed_time": "1:12:39", "remaining_time": "6:55:44", "throughput": 4519.94, "total_tokens": 19705824} {"current_steps": 9125, "total_steps": 61300, "loss": 0.3226, "lr": 4.963754410741324e-05, "epoch": 1.4885807504078303, "percentage": 14.89, "elapsed_time": "1:12:42", "remaining_time": "6:55:41", "throughput": 4520.13, "total_tokens": 19717056} {"current_steps": 9130, "total_steps": 61300, "loss": 0.3312, "lr": 4.9636335435080174e-05, "epoch": 1.4893964110929854, "percentage": 14.89, "elapsed_time": "1:12:44", "remaining_time": "6:55:38", "throughput": 4520.28, "total_tokens": 19728512} {"current_steps": 9135, "total_steps": 61300, "loss": 0.3622, "lr": 4.963512476560075e-05, "epoch": 1.4902120717781404, "percentage": 14.9, "elapsed_time": "1:12:46", "remaining_time": "6:55:37", "throughput": 4520.47, "total_tokens": 19740768} {"current_steps": 9140, "total_steps": 61300, "loss": 0.3484, "lr": 4.963391209907312e-05, "epoch": 1.4910277324632952, "percentage": 14.91, "elapsed_time": "1:12:49", "remaining_time": "6:55:35", "throughput": 4520.66, "total_tokens": 19752576} {"current_steps": 9145, "total_steps": 61300, "loss": 0.356, "lr": 4.9632697435595585e-05, "epoch": 1.4918433931484503, "percentage": 14.92, "elapsed_time": "1:12:51", "remaining_time": "6:55:32", "throughput": 4520.86, "total_tokens": 19764064} {"current_steps": 9150, "total_steps": 61300, "loss": 0.3841, "lr": 4.96314807752666e-05, "epoch": 1.4926590538336053, "percentage": 14.93, "elapsed_time": "1:12:54", "remaining_time": "6:55:31", "throughput": 4521.03, "total_tokens": 19776608} {"current_steps": 9155, "total_steps": 61300, "loss": 0.3472, "lr": 4.963026211818482e-05, "epoch": 1.4934747145187601, "percentage": 14.93, "elapsed_time": "1:12:56", "remaining_time": "6:55:28", "throughput": 4521.16, "total_tokens": 19787488} {"current_steps": 9160, "total_steps": 61300, "loss": 0.3373, "lr": 4.962904146444901e-05, "epoch": 1.4942903752039152, "percentage": 14.94, "elapsed_time": "1:12:58", "remaining_time": "6:55:24", "throughput": 4521.35, "total_tokens": 19798240} {"current_steps": 9165, "total_steps": 61300, "loss": 0.3992, "lr": 4.962781881415814e-05, "epoch": 1.4951060358890702, "percentage": 14.95, "elapsed_time": "1:13:00", "remaining_time": "6:55:20", "throughput": 4521.5, "total_tokens": 19808384} {"current_steps": 9170, "total_steps": 61300, "loss": 0.3438, "lr": 4.962659416741131e-05, "epoch": 1.495921696574225, "percentage": 14.96, "elapsed_time": "1:13:02", "remaining_time": "6:55:15", "throughput": 4521.62, "total_tokens": 19817696} {"current_steps": 9175, "total_steps": 61300, "loss": 0.3681, "lr": 4.962536752430781e-05, "epoch": 1.49673735725938, "percentage": 14.97, "elapsed_time": "1:13:05", "remaining_time": "6:55:12", "throughput": 4521.81, "total_tokens": 19828384} {"current_steps": 9180, "total_steps": 61300, "loss": 0.3583, "lr": 4.962413888494706e-05, "epoch": 1.497553017944535, "percentage": 14.98, "elapsed_time": "1:13:07", "remaining_time": "6:55:10", "throughput": 4521.98, "total_tokens": 19840704} {"current_steps": 9185, "total_steps": 61300, "loss": 0.2512, "lr": 4.9622908249428676e-05, "epoch": 1.49836867862969, "percentage": 14.98, "elapsed_time": "1:13:09", "remaining_time": "6:55:07", "throughput": 4522.13, "total_tokens": 19851648} {"current_steps": 9190, "total_steps": 61300, "loss": 0.3545, "lr": 4.962167561785241e-05, "epoch": 1.499184339314845, "percentage": 14.99, "elapsed_time": "1:13:11", "remaining_time": "6:55:03", "throughput": 4522.25, "total_tokens": 19861568} {"current_steps": 9195, "total_steps": 61300, "loss": 0.3571, "lr": 4.962044099031819e-05, "epoch": 1.5, "percentage": 15.0, "elapsed_time": "1:13:13", "remaining_time": "6:54:58", "throughput": 4522.44, "total_tokens": 19871232} {"current_steps": 9195, "total_steps": 61300, "eval_loss": 0.360756516456604, "epoch": 1.5, "percentage": 15.0, "elapsed_time": "1:15:26", "remaining_time": "7:07:27", "throughput": 4390.38, "total_tokens": 19871232} {"current_steps": 9200, "total_steps": 61300, "loss": 0.51, "lr": 4.9619204366926106e-05, "epoch": 1.5008156606851548, "percentage": 15.01, "elapsed_time": "1:15:29", "remaining_time": "7:07:29", "throughput": 4389.73, "total_tokens": 19882400} {"current_steps": 9205, "total_steps": 61300, "loss": 0.378, "lr": 4.96179657477764e-05, "epoch": 1.50163132137031, "percentage": 15.02, "elapsed_time": "1:15:31", "remaining_time": "7:07:26", "throughput": 4389.99, "total_tokens": 19893824} {"current_steps": 9210, "total_steps": 61300, "loss": 0.3935, "lr": 4.961672513296948e-05, "epoch": 1.502446982055465, "percentage": 15.02, "elapsed_time": "1:15:34", "remaining_time": "7:07:23", "throughput": 4390.2, "total_tokens": 19905280} {"current_steps": 9215, "total_steps": 61300, "loss": 0.3418, "lr": 4.9615482522605915e-05, "epoch": 1.50326264274062, "percentage": 15.03, "elapsed_time": "1:15:36", "remaining_time": "7:07:19", "throughput": 4390.42, "total_tokens": 19916032} {"current_steps": 9220, "total_steps": 61300, "loss": 0.3447, "lr": 4.9614237916786434e-05, "epoch": 1.504078303425775, "percentage": 15.04, "elapsed_time": "1:15:38", "remaining_time": "7:07:16", "throughput": 4390.61, "total_tokens": 19927232} {"current_steps": 9225, "total_steps": 61300, "loss": 0.3481, "lr": 4.961299131561194e-05, "epoch": 1.5048939641109298, "percentage": 15.05, "elapsed_time": "1:15:40", "remaining_time": "7:07:11", "throughput": 4390.82, "total_tokens": 19936992} {"current_steps": 9230, "total_steps": 61300, "loss": 0.3763, "lr": 4.961174271918349e-05, "epoch": 1.5057096247960848, "percentage": 15.06, "elapsed_time": "1:15:42", "remaining_time": "7:07:08", "throughput": 4391.03, "total_tokens": 19948256} {"current_steps": 9235, "total_steps": 61300, "loss": 0.3335, "lr": 4.961049212760229e-05, "epoch": 1.5065252854812399, "percentage": 15.07, "elapsed_time": "1:15:45", "remaining_time": "7:07:06", "throughput": 4391.3, "total_tokens": 19960416} {"current_steps": 9240, "total_steps": 61300, "loss": 0.3391, "lr": 4.960923954096972e-05, "epoch": 1.5073409461663947, "percentage": 15.07, "elapsed_time": "1:15:47", "remaining_time": "7:07:01", "throughput": 4391.5, "total_tokens": 19970656} {"current_steps": 9245, "total_steps": 61300, "loss": 0.3439, "lr": 4.960798495938734e-05, "epoch": 1.5081566068515497, "percentage": 15.08, "elapsed_time": "1:15:49", "remaining_time": "7:06:59", "throughput": 4391.71, "total_tokens": 19982176} {"current_steps": 9250, "total_steps": 61300, "loss": 0.3252, "lr": 4.960672838295683e-05, "epoch": 1.5089722675367048, "percentage": 15.09, "elapsed_time": "1:15:51", "remaining_time": "7:06:54", "throughput": 4391.91, "total_tokens": 19991968} {"current_steps": 9255, "total_steps": 61300, "loss": 0.3302, "lr": 4.960546981178007e-05, "epoch": 1.5097879282218596, "percentage": 15.1, "elapsed_time": "1:15:54", "remaining_time": "7:06:51", "throughput": 4392.15, "total_tokens": 20003968} {"current_steps": 9260, "total_steps": 61300, "loss": 0.3891, "lr": 4.9604209245959076e-05, "epoch": 1.5106035889070146, "percentage": 15.11, "elapsed_time": "1:15:56", "remaining_time": "7:06:48", "throughput": 4392.35, "total_tokens": 20014784} {"current_steps": 9265, "total_steps": 61300, "loss": 0.3829, "lr": 4.960294668559604e-05, "epoch": 1.5114192495921697, "percentage": 15.11, "elapsed_time": "1:15:58", "remaining_time": "7:06:43", "throughput": 4392.51, "total_tokens": 20024192} {"current_steps": 9270, "total_steps": 61300, "loss": 0.3572, "lr": 4.960168213079331e-05, "epoch": 1.5122349102773245, "percentage": 15.12, "elapsed_time": "1:16:00", "remaining_time": "7:06:38", "throughput": 4392.72, "total_tokens": 20034368} {"current_steps": 9275, "total_steps": 61300, "loss": 0.3761, "lr": 4.9600415581653406e-05, "epoch": 1.5130505709624797, "percentage": 15.13, "elapsed_time": "1:16:03", "remaining_time": "7:06:34", "throughput": 4392.94, "total_tokens": 20045216} {"current_steps": 9280, "total_steps": 61300, "loss": 0.3374, "lr": 4.9599147038278984e-05, "epoch": 1.5138662316476346, "percentage": 15.14, "elapsed_time": "1:16:05", "remaining_time": "7:06:32", "throughput": 4393.18, "total_tokens": 20056928} {"current_steps": 9285, "total_steps": 61300, "loss": 0.3543, "lr": 4.95978765007729e-05, "epoch": 1.5146818923327896, "percentage": 15.15, "elapsed_time": "1:16:07", "remaining_time": "7:06:28", "throughput": 4393.39, "total_tokens": 20067520} {"current_steps": 9290, "total_steps": 61300, "loss": 0.3351, "lr": 4.959660396923813e-05, "epoch": 1.5154975530179446, "percentage": 15.15, "elapsed_time": "1:16:09", "remaining_time": "7:06:23", "throughput": 4393.62, "total_tokens": 20077568} {"current_steps": 9295, "total_steps": 61300, "loss": 0.3645, "lr": 4.9595329443777836e-05, "epoch": 1.5163132137030995, "percentage": 15.16, "elapsed_time": "1:16:11", "remaining_time": "7:06:19", "throughput": 4393.79, "total_tokens": 20087584} {"current_steps": 9300, "total_steps": 61300, "loss": 0.2825, "lr": 4.959405292449535e-05, "epoch": 1.5171288743882545, "percentage": 15.17, "elapsed_time": "1:16:14", "remaining_time": "7:06:15", "throughput": 4394.03, "total_tokens": 20098880} {"current_steps": 9305, "total_steps": 61300, "loss": 0.3566, "lr": 4.959277441149415e-05, "epoch": 1.5179445350734095, "percentage": 15.18, "elapsed_time": "1:16:16", "remaining_time": "7:06:12", "throughput": 4394.23, "total_tokens": 20109568} {"current_steps": 9310, "total_steps": 61300, "loss": 0.3268, "lr": 4.959149390487786e-05, "epoch": 1.5187601957585644, "percentage": 15.19, "elapsed_time": "1:16:18", "remaining_time": "7:06:09", "throughput": 4394.44, "total_tokens": 20121184} {"current_steps": 9315, "total_steps": 61300, "loss": 0.3531, "lr": 4.959021140475031e-05, "epoch": 1.5195758564437194, "percentage": 15.2, "elapsed_time": "1:16:21", "remaining_time": "7:06:06", "throughput": 4394.67, "total_tokens": 20132608} {"current_steps": 9320, "total_steps": 61300, "loss": 0.3117, "lr": 4.958892691121545e-05, "epoch": 1.5203915171288744, "percentage": 15.2, "elapsed_time": "1:16:23", "remaining_time": "7:06:02", "throughput": 4394.88, "total_tokens": 20143200} {"current_steps": 9325, "total_steps": 61300, "loss": 0.2973, "lr": 4.958764042437741e-05, "epoch": 1.5212071778140293, "percentage": 15.21, "elapsed_time": "1:16:25", "remaining_time": "7:05:57", "throughput": 4395.07, "total_tokens": 20153344} {"current_steps": 9330, "total_steps": 61300, "loss": 0.3501, "lr": 4.958635194434048e-05, "epoch": 1.5220228384991843, "percentage": 15.22, "elapsed_time": "1:16:27", "remaining_time": "7:05:54", "throughput": 4395.25, "total_tokens": 20164288} {"current_steps": 9335, "total_steps": 61300, "loss": 0.3247, "lr": 4.958506147120912e-05, "epoch": 1.5228384991843393, "percentage": 15.23, "elapsed_time": "1:16:29", "remaining_time": "7:05:50", "throughput": 4395.49, "total_tokens": 20174880} {"current_steps": 9340, "total_steps": 61300, "loss": 0.3683, "lr": 4.958376900508792e-05, "epoch": 1.5236541598694942, "percentage": 15.24, "elapsed_time": "1:16:31", "remaining_time": "7:05:46", "throughput": 4395.69, "total_tokens": 20184960} {"current_steps": 9345, "total_steps": 61300, "loss": 0.3429, "lr": 4.958247454608167e-05, "epoch": 1.5244698205546494, "percentage": 15.24, "elapsed_time": "1:16:33", "remaining_time": "7:05:40", "throughput": 4395.88, "total_tokens": 20194464} {"current_steps": 9350, "total_steps": 61300, "loss": 0.335, "lr": 4.958117809429531e-05, "epoch": 1.5252854812398042, "percentage": 15.25, "elapsed_time": "1:16:36", "remaining_time": "7:05:36", "throughput": 4396.02, "total_tokens": 20204352} {"current_steps": 9355, "total_steps": 61300, "loss": 0.3685, "lr": 4.9579879649833925e-05, "epoch": 1.5261011419249593, "percentage": 15.26, "elapsed_time": "1:16:38", "remaining_time": "7:05:32", "throughput": 4396.18, "total_tokens": 20214816} {"current_steps": 9360, "total_steps": 61300, "loss": 0.3596, "lr": 4.957857921280279e-05, "epoch": 1.5269168026101143, "percentage": 15.27, "elapsed_time": "1:16:40", "remaining_time": "7:05:29", "throughput": 4396.37, "total_tokens": 20225664} {"current_steps": 9365, "total_steps": 61300, "loss": 0.3585, "lr": 4.9577276783307296e-05, "epoch": 1.5277324632952691, "percentage": 15.28, "elapsed_time": "1:16:42", "remaining_time": "7:05:25", "throughput": 4396.57, "total_tokens": 20236672} {"current_steps": 9370, "total_steps": 61300, "loss": 0.3715, "lr": 4.9575972361453046e-05, "epoch": 1.5285481239804242, "percentage": 15.29, "elapsed_time": "1:16:44", "remaining_time": "7:05:21", "throughput": 4396.77, "total_tokens": 20246784} {"current_steps": 9375, "total_steps": 61300, "loss": 0.3397, "lr": 4.957466594734579e-05, "epoch": 1.5293637846655792, "percentage": 15.29, "elapsed_time": "1:16:47", "remaining_time": "7:05:17", "throughput": 4396.94, "total_tokens": 20257088} {"current_steps": 9380, "total_steps": 61300, "loss": 0.3427, "lr": 4.9573357541091414e-05, "epoch": 1.530179445350734, "percentage": 15.3, "elapsed_time": "1:16:49", "remaining_time": "7:05:13", "throughput": 4397.11, "total_tokens": 20267520} {"current_steps": 9385, "total_steps": 61300, "loss": 0.3327, "lr": 4.957204714279599e-05, "epoch": 1.530995106035889, "percentage": 15.31, "elapsed_time": "1:16:51", "remaining_time": "7:05:08", "throughput": 4397.3, "total_tokens": 20277568} {"current_steps": 9390, "total_steps": 61300, "loss": 0.3396, "lr": 4.957073475256575e-05, "epoch": 1.531810766721044, "percentage": 15.32, "elapsed_time": "1:16:53", "remaining_time": "7:05:05", "throughput": 4397.55, "total_tokens": 20288768} {"current_steps": 9395, "total_steps": 61300, "loss": 0.3551, "lr": 4.9569420370507087e-05, "epoch": 1.532626427406199, "percentage": 15.33, "elapsed_time": "1:16:55", "remaining_time": "7:05:01", "throughput": 4397.8, "total_tokens": 20299968} {"current_steps": 9400, "total_steps": 61300, "loss": 0.3445, "lr": 4.956810399672653e-05, "epoch": 1.533442088091354, "percentage": 15.33, "elapsed_time": "1:16:58", "remaining_time": "7:04:58", "throughput": 4397.99, "total_tokens": 20310592} {"current_steps": 9405, "total_steps": 61300, "loss": 0.3644, "lr": 4.956678563133082e-05, "epoch": 1.534257748776509, "percentage": 15.34, "elapsed_time": "1:17:00", "remaining_time": "7:04:54", "throughput": 4398.21, "total_tokens": 20321088} {"current_steps": 9410, "total_steps": 61300, "loss": 0.3412, "lr": 4.956546527442681e-05, "epoch": 1.5350734094616638, "percentage": 15.35, "elapsed_time": "1:17:02", "remaining_time": "7:04:49", "throughput": 4398.4, "total_tokens": 20331136} {"current_steps": 9415, "total_steps": 61300, "loss": 0.343, "lr": 4.956414292612154e-05, "epoch": 1.535889070146819, "percentage": 15.36, "elapsed_time": "1:17:04", "remaining_time": "7:04:46", "throughput": 4398.66, "total_tokens": 20343136} {"current_steps": 9420, "total_steps": 61300, "loss": 0.3655, "lr": 4.9562818586522206e-05, "epoch": 1.536704730831974, "percentage": 15.37, "elapsed_time": "1:17:07", "remaining_time": "7:04:44", "throughput": 4398.88, "total_tokens": 20354656} {"current_steps": 9425, "total_steps": 61300, "loss": 0.4035, "lr": 4.9561492255736175e-05, "epoch": 1.5375203915171287, "percentage": 15.38, "elapsed_time": "1:17:09", "remaining_time": "7:04:41", "throughput": 4399.09, "total_tokens": 20365856} {"current_steps": 9430, "total_steps": 61300, "loss": 0.3428, "lr": 4.9560163933870954e-05, "epoch": 1.538336052202284, "percentage": 15.38, "elapsed_time": "1:17:11", "remaining_time": "7:04:36", "throughput": 4399.27, "total_tokens": 20376064} {"current_steps": 9435, "total_steps": 61300, "loss": 0.3663, "lr": 4.9558833621034224e-05, "epoch": 1.5391517128874388, "percentage": 15.39, "elapsed_time": "1:17:13", "remaining_time": "7:04:33", "throughput": 4399.48, "total_tokens": 20387104} {"current_steps": 9440, "total_steps": 61300, "loss": 0.3206, "lr": 4.955750131733383e-05, "epoch": 1.5399673735725938, "percentage": 15.4, "elapsed_time": "1:17:16", "remaining_time": "7:04:30", "throughput": 4399.67, "total_tokens": 20398112} {"current_steps": 9445, "total_steps": 61300, "loss": 0.3317, "lr": 4.955616702287778e-05, "epoch": 1.5407830342577489, "percentage": 15.41, "elapsed_time": "1:17:18", "remaining_time": "7:04:26", "throughput": 4399.87, "total_tokens": 20409152} {"current_steps": 9450, "total_steps": 61300, "loss": 0.4093, "lr": 4.9554830737774226e-05, "epoch": 1.5415986949429037, "percentage": 15.42, "elapsed_time": "1:17:20", "remaining_time": "7:04:23", "throughput": 4400.12, "total_tokens": 20420704} {"current_steps": 9455, "total_steps": 61300, "loss": 0.3129, "lr": 4.955349246213151e-05, "epoch": 1.5424143556280587, "percentage": 15.42, "elapsed_time": "1:17:23", "remaining_time": "7:04:20", "throughput": 4400.32, "total_tokens": 20431456} {"current_steps": 9460, "total_steps": 61300, "loss": 0.3345, "lr": 4.9552152196058114e-05, "epoch": 1.5432300163132138, "percentage": 15.43, "elapsed_time": "1:17:25", "remaining_time": "7:04:17", "throughput": 4400.54, "total_tokens": 20442880} {"current_steps": 9465, "total_steps": 61300, "loss": 0.3693, "lr": 4.955080993966268e-05, "epoch": 1.5440456769983686, "percentage": 15.44, "elapsed_time": "1:17:27", "remaining_time": "7:04:14", "throughput": 4400.8, "total_tokens": 20454624} {"current_steps": 9470, "total_steps": 61300, "loss": 0.3281, "lr": 4.954946569305402e-05, "epoch": 1.5448613376835236, "percentage": 15.45, "elapsed_time": "1:17:30", "remaining_time": "7:04:11", "throughput": 4401.02, "total_tokens": 20465824} {"current_steps": 9475, "total_steps": 61300, "loss": 0.3423, "lr": 4.9548119456341114e-05, "epoch": 1.5456769983686787, "percentage": 15.46, "elapsed_time": "1:17:32", "remaining_time": "7:04:08", "throughput": 4401.22, "total_tokens": 20477088} {"current_steps": 9480, "total_steps": 61300, "loss": 0.3319, "lr": 4.954677122963309e-05, "epoch": 1.5464926590538335, "percentage": 15.46, "elapsed_time": "1:17:34", "remaining_time": "7:04:03", "throughput": 4401.39, "total_tokens": 20487296} {"current_steps": 9485, "total_steps": 61300, "loss": 0.3785, "lr": 4.954542101303924e-05, "epoch": 1.5473083197389887, "percentage": 15.47, "elapsed_time": "1:17:36", "remaining_time": "7:04:00", "throughput": 4401.59, "total_tokens": 20498080} {"current_steps": 9490, "total_steps": 61300, "loss": 0.3823, "lr": 4.954406880666902e-05, "epoch": 1.5481239804241436, "percentage": 15.48, "elapsed_time": "1:17:39", "remaining_time": "7:03:57", "throughput": 4401.85, "total_tokens": 20509824} {"current_steps": 9495, "total_steps": 61300, "loss": 0.3279, "lr": 4.954271461063204e-05, "epoch": 1.5489396411092984, "percentage": 15.49, "elapsed_time": "1:17:41", "remaining_time": "7:03:54", "throughput": 4402.07, "total_tokens": 20520928} {"current_steps": 9500, "total_steps": 61300, "loss": 0.3779, "lr": 4.9541358425038095e-05, "epoch": 1.5497553017944536, "percentage": 15.5, "elapsed_time": "1:17:43", "remaining_time": "7:03:51", "throughput": 4402.29, "total_tokens": 20532288} {"current_steps": 9505, "total_steps": 61300, "loss": 0.3254, "lr": 4.954000024999711e-05, "epoch": 1.5505709624796085, "percentage": 15.51, "elapsed_time": "1:17:46", "remaining_time": "7:03:47", "throughput": 4402.51, "total_tokens": 20543456} {"current_steps": 9510, "total_steps": 61300, "loss": 0.3697, "lr": 4.9538640085619184e-05, "epoch": 1.5513866231647635, "percentage": 15.51, "elapsed_time": "1:17:48", "remaining_time": "7:03:44", "throughput": 4402.72, "total_tokens": 20554592} {"current_steps": 9515, "total_steps": 61300, "loss": 0.3582, "lr": 4.953727793201459e-05, "epoch": 1.5522022838499185, "percentage": 15.52, "elapsed_time": "1:17:50", "remaining_time": "7:03:41", "throughput": 4402.93, "total_tokens": 20565504} {"current_steps": 9520, "total_steps": 61300, "loss": 0.3792, "lr": 4.953591378929375e-05, "epoch": 1.5530179445350734, "percentage": 15.53, "elapsed_time": "1:17:53", "remaining_time": "7:03:38", "throughput": 4403.12, "total_tokens": 20576896} {"current_steps": 9525, "total_steps": 61300, "loss": 0.3268, "lr": 4.953454765756724e-05, "epoch": 1.5538336052202284, "percentage": 15.54, "elapsed_time": "1:17:55", "remaining_time": "7:03:33", "throughput": 4403.26, "total_tokens": 20586720} {"current_steps": 9530, "total_steps": 61300, "loss": 0.3279, "lr": 4.953317953694582e-05, "epoch": 1.5546492659053834, "percentage": 15.55, "elapsed_time": "1:17:57", "remaining_time": "7:03:29", "throughput": 4403.46, "total_tokens": 20597376} {"current_steps": 9535, "total_steps": 61300, "loss": 0.3583, "lr": 4.953180942754037e-05, "epoch": 1.5554649265905383, "percentage": 15.55, "elapsed_time": "1:17:59", "remaining_time": "7:03:26", "throughput": 4403.68, "total_tokens": 20608608} {"current_steps": 9540, "total_steps": 61300, "loss": 0.3338, "lr": 4.9530437329461987e-05, "epoch": 1.5562805872756933, "percentage": 15.56, "elapsed_time": "1:18:02", "remaining_time": "7:03:24", "throughput": 4403.86, "total_tokens": 20620128} {"current_steps": 9545, "total_steps": 61300, "loss": 0.3332, "lr": 4.952906324282188e-05, "epoch": 1.5570962479608483, "percentage": 15.57, "elapsed_time": "1:18:04", "remaining_time": "7:03:20", "throughput": 4404.07, "total_tokens": 20631200} {"current_steps": 9550, "total_steps": 61300, "loss": 0.3768, "lr": 4.952768716773145e-05, "epoch": 1.5579119086460032, "percentage": 15.58, "elapsed_time": "1:18:06", "remaining_time": "7:03:15", "throughput": 4404.25, "total_tokens": 20640352} {"current_steps": 9555, "total_steps": 61300, "loss": 0.4179, "lr": 4.9526309104302246e-05, "epoch": 1.5587275693311582, "percentage": 15.59, "elapsed_time": "1:18:09", "remaining_time": "7:03:13", "throughput": 4404.47, "total_tokens": 20652832} {"current_steps": 9560, "total_steps": 61300, "loss": 0.3471, "lr": 4.952492905264599e-05, "epoch": 1.5595432300163132, "percentage": 15.6, "elapsed_time": "1:18:11", "remaining_time": "7:03:09", "throughput": 4404.66, "total_tokens": 20663488} {"current_steps": 9565, "total_steps": 61300, "loss": 0.3685, "lr": 4.9523547012874524e-05, "epoch": 1.560358890701468, "percentage": 15.6, "elapsed_time": "1:18:13", "remaining_time": "7:03:06", "throughput": 4404.86, "total_tokens": 20674464} {"current_steps": 9570, "total_steps": 61300, "loss": 0.3343, "lr": 4.952216298509993e-05, "epoch": 1.5611745513866233, "percentage": 15.61, "elapsed_time": "1:18:15", "remaining_time": "7:03:03", "throughput": 4405.08, "total_tokens": 20685760} {"current_steps": 9575, "total_steps": 61300, "loss": 0.3237, "lr": 4.952077696943437e-05, "epoch": 1.5619902120717781, "percentage": 15.62, "elapsed_time": "1:18:18", "remaining_time": "7:03:00", "throughput": 4405.3, "total_tokens": 20697280} {"current_steps": 9580, "total_steps": 61300, "loss": 0.354, "lr": 4.951938896599021e-05, "epoch": 1.5628058727569332, "percentage": 15.63, "elapsed_time": "1:18:20", "remaining_time": "7:02:56", "throughput": 4405.52, "total_tokens": 20708000} {"current_steps": 9585, "total_steps": 61300, "loss": 0.3549, "lr": 4.951799897487997e-05, "epoch": 1.5636215334420882, "percentage": 15.64, "elapsed_time": "1:18:22", "remaining_time": "7:02:53", "throughput": 4405.73, "total_tokens": 20719424} {"current_steps": 9590, "total_steps": 61300, "loss": 0.369, "lr": 4.951660699621633e-05, "epoch": 1.564437194127243, "percentage": 15.64, "elapsed_time": "1:18:24", "remaining_time": "7:02:47", "throughput": 4405.9, "total_tokens": 20728096} {"current_steps": 9595, "total_steps": 61300, "loss": 0.3559, "lr": 4.9515213030112135e-05, "epoch": 1.565252854812398, "percentage": 15.65, "elapsed_time": "1:18:26", "remaining_time": "7:02:43", "throughput": 4406.11, "total_tokens": 20738816} {"current_steps": 9600, "total_steps": 61300, "loss": 0.3499, "lr": 4.951381707668038e-05, "epoch": 1.566068515497553, "percentage": 15.66, "elapsed_time": "1:18:29", "remaining_time": "7:02:40", "throughput": 4406.28, "total_tokens": 20749408} {"current_steps": 9605, "total_steps": 61300, "loss": 0.3692, "lr": 4.951241913603423e-05, "epoch": 1.566884176182708, "percentage": 15.67, "elapsed_time": "1:18:31", "remaining_time": "7:02:35", "throughput": 4406.47, "total_tokens": 20759200} {"current_steps": 9610, "total_steps": 61300, "loss": 0.3967, "lr": 4.9511019208287014e-05, "epoch": 1.567699836867863, "percentage": 15.68, "elapsed_time": "1:18:33", "remaining_time": "7:02:32", "throughput": 4406.7, "total_tokens": 20770560} {"current_steps": 9615, "total_steps": 61300, "loss": 0.3761, "lr": 4.9509617293552215e-05, "epoch": 1.568515497553018, "percentage": 15.69, "elapsed_time": "1:18:35", "remaining_time": "7:02:28", "throughput": 4406.88, "total_tokens": 20781056} {"current_steps": 9620, "total_steps": 61300, "loss": 0.372, "lr": 4.9508213391943467e-05, "epoch": 1.5693311582381728, "percentage": 15.69, "elapsed_time": "1:18:37", "remaining_time": "7:02:24", "throughput": 4407.05, "total_tokens": 20791648} {"current_steps": 9625, "total_steps": 61300, "loss": 0.402, "lr": 4.950680750357459e-05, "epoch": 1.5701468189233279, "percentage": 15.7, "elapsed_time": "1:18:40", "remaining_time": "7:02:23", "throughput": 4407.27, "total_tokens": 20804128} {"current_steps": 9630, "total_steps": 61300, "loss": 0.3526, "lr": 4.950539962855956e-05, "epoch": 1.570962479608483, "percentage": 15.71, "elapsed_time": "1:18:42", "remaining_time": "7:02:19", "throughput": 4407.46, "total_tokens": 20814752} {"current_steps": 9635, "total_steps": 61300, "loss": 0.3697, "lr": 4.9503989767012493e-05, "epoch": 1.5717781402936377, "percentage": 15.72, "elapsed_time": "1:18:45", "remaining_time": "7:02:16", "throughput": 4407.69, "total_tokens": 20826720} {"current_steps": 9640, "total_steps": 61300, "loss": 0.3308, "lr": 4.950257791904768e-05, "epoch": 1.572593800978793, "percentage": 15.73, "elapsed_time": "1:18:47", "remaining_time": "7:02:13", "throughput": 4407.92, "total_tokens": 20837536} {"current_steps": 9645, "total_steps": 61300, "loss": 0.3604, "lr": 4.950116408477958e-05, "epoch": 1.5734094616639478, "percentage": 15.73, "elapsed_time": "1:18:49", "remaining_time": "7:02:08", "throughput": 4408.13, "total_tokens": 20847744} {"current_steps": 9650, "total_steps": 61300, "loss": 0.3378, "lr": 4.94997482643228e-05, "epoch": 1.5742251223491026, "percentage": 15.74, "elapsed_time": "1:18:51", "remaining_time": "7:02:05", "throughput": 4408.35, "total_tokens": 20859136} {"current_steps": 9655, "total_steps": 61300, "loss": 0.3304, "lr": 4.949833045779212e-05, "epoch": 1.5750407830342579, "percentage": 15.75, "elapsed_time": "1:18:53", "remaining_time": "7:02:01", "throughput": 4408.48, "total_tokens": 20868832} {"current_steps": 9660, "total_steps": 61300, "loss": 0.3408, "lr": 4.9496910665302467e-05, "epoch": 1.5758564437194127, "percentage": 15.76, "elapsed_time": "1:18:55", "remaining_time": "7:01:56", "throughput": 4408.61, "total_tokens": 20878080} {"current_steps": 9665, "total_steps": 61300, "loss": 0.3433, "lr": 4.949548888696893e-05, "epoch": 1.5766721044045677, "percentage": 15.77, "elapsed_time": "1:18:58", "remaining_time": "7:01:53", "throughput": 4408.81, "total_tokens": 20889600} {"current_steps": 9670, "total_steps": 61300, "loss": 0.3612, "lr": 4.9494065122906787e-05, "epoch": 1.5774877650897228, "percentage": 15.77, "elapsed_time": "1:19:00", "remaining_time": "7:01:48", "throughput": 4408.99, "total_tokens": 20899392} {"current_steps": 9675, "total_steps": 61300, "loss": 0.352, "lr": 4.9492639373231436e-05, "epoch": 1.5783034257748776, "percentage": 15.78, "elapsed_time": "1:19:02", "remaining_time": "7:01:44", "throughput": 4409.17, "total_tokens": 20909888} {"current_steps": 9680, "total_steps": 61300, "loss": 0.3358, "lr": 4.949121163805847e-05, "epoch": 1.5791190864600326, "percentage": 15.79, "elapsed_time": "1:19:04", "remaining_time": "7:01:40", "throughput": 4409.35, "total_tokens": 20920032} {"current_steps": 9685, "total_steps": 61300, "loss": 0.3561, "lr": 4.948978191750362e-05, "epoch": 1.5799347471451877, "percentage": 15.8, "elapsed_time": "1:19:06", "remaining_time": "7:01:37", "throughput": 4409.56, "total_tokens": 20931136} {"current_steps": 9690, "total_steps": 61300, "loss": 0.3561, "lr": 4.948835021168278e-05, "epoch": 1.5807504078303425, "percentage": 15.81, "elapsed_time": "1:19:08", "remaining_time": "7:01:33", "throughput": 4409.79, "total_tokens": 20941792} {"current_steps": 9695, "total_steps": 61300, "loss": 0.3524, "lr": 4.9486916520712026e-05, "epoch": 1.5815660685154975, "percentage": 15.82, "elapsed_time": "1:19:11", "remaining_time": "7:01:30", "throughput": 4409.94, "total_tokens": 20952672} {"current_steps": 9700, "total_steps": 61300, "loss": 0.3819, "lr": 4.948548084470757e-05, "epoch": 1.5823817292006526, "percentage": 15.82, "elapsed_time": "1:19:13", "remaining_time": "7:01:27", "throughput": 4410.18, "total_tokens": 20964480} {"current_steps": 9705, "total_steps": 61300, "loss": 0.3355, "lr": 4.94840431837858e-05, "epoch": 1.5831973898858074, "percentage": 15.83, "elapsed_time": "1:19:15", "remaining_time": "7:01:24", "throughput": 4410.35, "total_tokens": 20975392} {"current_steps": 9710, "total_steps": 61300, "loss": 0.3676, "lr": 4.948260353806326e-05, "epoch": 1.5840130505709626, "percentage": 15.84, "elapsed_time": "1:19:18", "remaining_time": "7:01:19", "throughput": 4410.48, "total_tokens": 20985344} {"current_steps": 9715, "total_steps": 61300, "loss": 0.3883, "lr": 4.948116190765665e-05, "epoch": 1.5848287112561175, "percentage": 15.85, "elapsed_time": "1:19:20", "remaining_time": "7:01:15", "throughput": 4410.65, "total_tokens": 20995456} {"current_steps": 9720, "total_steps": 61300, "loss": 0.3328, "lr": 4.9479718292682846e-05, "epoch": 1.5856443719412723, "percentage": 15.86, "elapsed_time": "1:19:22", "remaining_time": "7:01:12", "throughput": 4410.85, "total_tokens": 21006816} {"current_steps": 9725, "total_steps": 61300, "loss": 0.3729, "lr": 4.9478272693258866e-05, "epoch": 1.5864600326264275, "percentage": 15.86, "elapsed_time": "1:19:24", "remaining_time": "7:01:09", "throughput": 4411.0, "total_tokens": 21017344} {"current_steps": 9730, "total_steps": 61300, "loss": 0.3459, "lr": 4.94768251095019e-05, "epoch": 1.5872756933115824, "percentage": 15.87, "elapsed_time": "1:19:26", "remaining_time": "7:01:04", "throughput": 4411.15, "total_tokens": 21027040} {"current_steps": 9735, "total_steps": 61300, "loss": 0.3637, "lr": 4.9475375541529294e-05, "epoch": 1.5880913539967374, "percentage": 15.88, "elapsed_time": "1:19:28", "remaining_time": "7:01:00", "throughput": 4411.34, "total_tokens": 21037472} {"current_steps": 9740, "total_steps": 61300, "loss": 0.3578, "lr": 4.947392398945856e-05, "epoch": 1.5889070146818924, "percentage": 15.89, "elapsed_time": "1:19:31", "remaining_time": "7:00:57", "throughput": 4411.55, "total_tokens": 21048800} {"current_steps": 9745, "total_steps": 61300, "loss": 0.3383, "lr": 4.9472470453407374e-05, "epoch": 1.5897226753670473, "percentage": 15.9, "elapsed_time": "1:19:33", "remaining_time": "7:00:55", "throughput": 4411.73, "total_tokens": 21060672} {"current_steps": 9750, "total_steps": 61300, "loss": 0.3644, "lr": 4.947101493349355e-05, "epoch": 1.5905383360522023, "percentage": 15.91, "elapsed_time": "1:19:35", "remaining_time": "7:00:51", "throughput": 4411.91, "total_tokens": 21070880} {"current_steps": 9755, "total_steps": 61300, "loss": 0.3542, "lr": 4.94695574298351e-05, "epoch": 1.5913539967373573, "percentage": 15.91, "elapsed_time": "1:19:38", "remaining_time": "7:00:47", "throughput": 4412.12, "total_tokens": 21081792} {"current_steps": 9760, "total_steps": 61300, "loss": 0.37, "lr": 4.946809794255016e-05, "epoch": 1.5921696574225122, "percentage": 15.92, "elapsed_time": "1:19:40", "remaining_time": "7:00:44", "throughput": 4412.33, "total_tokens": 21093280} {"current_steps": 9765, "total_steps": 61300, "loss": 0.3342, "lr": 4.946663647175706e-05, "epoch": 1.5929853181076672, "percentage": 15.93, "elapsed_time": "1:19:42", "remaining_time": "7:00:40", "throughput": 4412.54, "total_tokens": 21103264} {"current_steps": 9770, "total_steps": 61300, "loss": 0.4044, "lr": 4.946517301757426e-05, "epoch": 1.5938009787928222, "percentage": 15.94, "elapsed_time": "1:19:44", "remaining_time": "7:00:36", "throughput": 4412.71, "total_tokens": 21113632} {"current_steps": 9775, "total_steps": 61300, "loss": 0.3739, "lr": 4.94637075801204e-05, "epoch": 1.594616639477977, "percentage": 15.95, "elapsed_time": "1:19:47", "remaining_time": "7:00:32", "throughput": 4412.88, "total_tokens": 21124448} {"current_steps": 9780, "total_steps": 61300, "loss": 0.3762, "lr": 4.946224015951427e-05, "epoch": 1.595432300163132, "percentage": 15.95, "elapsed_time": "1:19:49", "remaining_time": "7:00:29", "throughput": 4413.07, "total_tokens": 21135776} {"current_steps": 9785, "total_steps": 61300, "loss": 0.3578, "lr": 4.946077075587484e-05, "epoch": 1.5962479608482871, "percentage": 15.96, "elapsed_time": "1:19:51", "remaining_time": "7:00:26", "throughput": 4413.29, "total_tokens": 21147072} {"current_steps": 9790, "total_steps": 61300, "loss": 0.3187, "lr": 4.945929936932122e-05, "epoch": 1.597063621533442, "percentage": 15.97, "elapsed_time": "1:19:54", "remaining_time": "7:00:24", "throughput": 4413.53, "total_tokens": 21158848} {"current_steps": 9795, "total_steps": 61300, "loss": 0.3463, "lr": 4.945782599997269e-05, "epoch": 1.5978792822185972, "percentage": 15.98, "elapsed_time": "1:19:56", "remaining_time": "7:00:19", "throughput": 4413.72, "total_tokens": 21168448} {"current_steps": 9800, "total_steps": 61300, "loss": 0.3291, "lr": 4.945635064794869e-05, "epoch": 1.598694942903752, "percentage": 15.99, "elapsed_time": "1:19:58", "remaining_time": "7:00:16", "throughput": 4413.92, "total_tokens": 21179744} {"current_steps": 9805, "total_steps": 61300, "loss": 0.3171, "lr": 4.94548733133688e-05, "epoch": 1.599510603588907, "percentage": 16.0, "elapsed_time": "1:20:00", "remaining_time": "7:00:14", "throughput": 4414.12, "total_tokens": 21191904} {"current_steps": 9810, "total_steps": 61300, "loss": 0.3568, "lr": 4.945339399635281e-05, "epoch": 1.600326264274062, "percentage": 16.0, "elapsed_time": "1:20:03", "remaining_time": "7:00:10", "throughput": 4414.28, "total_tokens": 21202848} {"current_steps": 9815, "total_steps": 61300, "loss": 0.3648, "lr": 4.945191269702062e-05, "epoch": 1.601141924959217, "percentage": 16.01, "elapsed_time": "1:20:05", "remaining_time": "7:00:07", "throughput": 4414.51, "total_tokens": 21214304} {"current_steps": 9820, "total_steps": 61300, "loss": 0.294, "lr": 4.945042941549233e-05, "epoch": 1.601957585644372, "percentage": 16.02, "elapsed_time": "1:20:07", "remaining_time": "7:00:03", "throughput": 4414.66, "total_tokens": 21224448} {"current_steps": 9825, "total_steps": 61300, "loss": 0.3779, "lr": 4.944894415188815e-05, "epoch": 1.602773246329527, "percentage": 16.03, "elapsed_time": "1:20:10", "remaining_time": "7:00:00", "throughput": 4414.84, "total_tokens": 21235392} {"current_steps": 9830, "total_steps": 61300, "loss": 0.3673, "lr": 4.944745690632852e-05, "epoch": 1.6035889070146818, "percentage": 16.04, "elapsed_time": "1:20:12", "remaining_time": "6:59:57", "throughput": 4415.03, "total_tokens": 21246656} {"current_steps": 9835, "total_steps": 61300, "loss": 0.3589, "lr": 4.944596767893399e-05, "epoch": 1.6044045676998369, "percentage": 16.04, "elapsed_time": "1:20:14", "remaining_time": "6:59:53", "throughput": 4415.2, "total_tokens": 21257376} {"current_steps": 9840, "total_steps": 61300, "loss": 0.3343, "lr": 4.944447646982529e-05, "epoch": 1.605220228384992, "percentage": 16.05, "elapsed_time": "1:20:16", "remaining_time": "6:59:49", "throughput": 4415.38, "total_tokens": 21267456} {"current_steps": 9845, "total_steps": 61300, "loss": 0.3256, "lr": 4.9442983279123276e-05, "epoch": 1.6060358890701467, "percentage": 16.06, "elapsed_time": "1:20:19", "remaining_time": "6:59:47", "throughput": 4415.58, "total_tokens": 21279104} {"current_steps": 9850, "total_steps": 61300, "loss": 0.3584, "lr": 4.944148810694903e-05, "epoch": 1.6068515497553018, "percentage": 16.07, "elapsed_time": "1:20:21", "remaining_time": "6:59:44", "throughput": 4415.81, "total_tokens": 21291328} {"current_steps": 9855, "total_steps": 61300, "loss": 0.3207, "lr": 4.9439990953423735e-05, "epoch": 1.6076672104404568, "percentage": 16.08, "elapsed_time": "1:20:23", "remaining_time": "6:59:41", "throughput": 4415.95, "total_tokens": 21302016} {"current_steps": 9860, "total_steps": 61300, "loss": 0.3413, "lr": 4.943849181866876e-05, "epoch": 1.6084828711256116, "percentage": 16.08, "elapsed_time": "1:20:26", "remaining_time": "6:59:37", "throughput": 4416.12, "total_tokens": 21312448} {"current_steps": 9865, "total_steps": 61300, "loss": 0.3549, "lr": 4.943699070280565e-05, "epoch": 1.6092985318107669, "percentage": 16.09, "elapsed_time": "1:20:28", "remaining_time": "6:59:34", "throughput": 4416.27, "total_tokens": 21323136} {"current_steps": 9870, "total_steps": 61300, "loss": 0.3152, "lr": 4.9435487605956084e-05, "epoch": 1.6101141924959217, "percentage": 16.1, "elapsed_time": "1:20:30", "remaining_time": "6:59:31", "throughput": 4416.47, "total_tokens": 21334368} {"current_steps": 9875, "total_steps": 61300, "loss": 0.2891, "lr": 4.94339825282419e-05, "epoch": 1.6109298531810765, "percentage": 16.11, "elapsed_time": "1:20:32", "remaining_time": "6:59:27", "throughput": 4416.64, "total_tokens": 21344992} {"current_steps": 9880, "total_steps": 61300, "loss": 0.2537, "lr": 4.943247546978512e-05, "epoch": 1.6117455138662318, "percentage": 16.12, "elapsed_time": "1:20:34", "remaining_time": "6:59:22", "throughput": 4416.8, "total_tokens": 21354688} {"current_steps": 9885, "total_steps": 61300, "loss": 0.4282, "lr": 4.943096643070791e-05, "epoch": 1.6125611745513866, "percentage": 16.13, "elapsed_time": "1:20:37", "remaining_time": "6:59:19", "throughput": 4416.98, "total_tokens": 21365696} {"current_steps": 9890, "total_steps": 61300, "loss": 0.3451, "lr": 4.9429455411132596e-05, "epoch": 1.6133768352365416, "percentage": 16.13, "elapsed_time": "1:20:39", "remaining_time": "6:59:17", "throughput": 4417.21, "total_tokens": 21378240} {"current_steps": 9895, "total_steps": 61300, "loss": 0.4272, "lr": 4.942794241118167e-05, "epoch": 1.6141924959216967, "percentage": 16.14, "elapsed_time": "1:20:42", "remaining_time": "6:59:14", "throughput": 4417.38, "total_tokens": 21388992} {"current_steps": 9900, "total_steps": 61300, "loss": 0.3291, "lr": 4.9426427430977796e-05, "epoch": 1.6150081566068515, "percentage": 16.15, "elapsed_time": "1:20:44", "remaining_time": "6:59:11", "throughput": 4417.54, "total_tokens": 21399808} {"current_steps": 9905, "total_steps": 61300, "loss": 0.3446, "lr": 4.942491047064377e-05, "epoch": 1.6158238172920065, "percentage": 16.16, "elapsed_time": "1:20:46", "remaining_time": "6:59:06", "throughput": 4417.72, "total_tokens": 21409696} {"current_steps": 9910, "total_steps": 61300, "loss": 0.3356, "lr": 4.942339153030257e-05, "epoch": 1.6166394779771616, "percentage": 16.17, "elapsed_time": "1:20:48", "remaining_time": "6:59:02", "throughput": 4417.92, "total_tokens": 21420416} {"current_steps": 9915, "total_steps": 61300, "loss": 0.3379, "lr": 4.942187061007732e-05, "epoch": 1.6174551386623164, "percentage": 16.17, "elapsed_time": "1:20:50", "remaining_time": "6:58:59", "throughput": 4418.12, "total_tokens": 21431648} {"current_steps": 9920, "total_steps": 61300, "loss": 0.3613, "lr": 4.942034771009134e-05, "epoch": 1.6182707993474714, "percentage": 16.18, "elapsed_time": "1:20:52", "remaining_time": "6:58:55", "throughput": 4418.28, "total_tokens": 21441856} {"current_steps": 9925, "total_steps": 61300, "loss": 0.3615, "lr": 4.941882283046806e-05, "epoch": 1.6190864600326265, "percentage": 16.19, "elapsed_time": "1:20:55", "remaining_time": "6:58:52", "throughput": 4418.51, "total_tokens": 21452736} {"current_steps": 9930, "total_steps": 61300, "loss": 0.367, "lr": 4.94172959713311e-05, "epoch": 1.6199021207177813, "percentage": 16.2, "elapsed_time": "1:20:57", "remaining_time": "6:58:48", "throughput": 4418.66, "total_tokens": 21463552} {"current_steps": 9935, "total_steps": 61300, "loss": 0.3515, "lr": 4.941576713280424e-05, "epoch": 1.6207177814029365, "percentage": 16.21, "elapsed_time": "1:20:59", "remaining_time": "6:58:45", "throughput": 4418.89, "total_tokens": 21475136} {"current_steps": 9940, "total_steps": 61300, "loss": 0.3414, "lr": 4.941423631501141e-05, "epoch": 1.6215334420880914, "percentage": 16.22, "elapsed_time": "1:21:02", "remaining_time": "6:58:42", "throughput": 4419.04, "total_tokens": 21485536} {"current_steps": 9945, "total_steps": 61300, "loss": 0.3357, "lr": 4.941270351807671e-05, "epoch": 1.6223491027732462, "percentage": 16.22, "elapsed_time": "1:21:04", "remaining_time": "6:58:38", "throughput": 4419.23, "total_tokens": 21496320} {"current_steps": 9950, "total_steps": 61300, "loss": 0.3384, "lr": 4.941116874212439e-05, "epoch": 1.6231647634584014, "percentage": 16.23, "elapsed_time": "1:21:06", "remaining_time": "6:58:34", "throughput": 4419.4, "total_tokens": 21506688} {"current_steps": 9955, "total_steps": 61300, "loss": 0.3595, "lr": 4.940963198727887e-05, "epoch": 1.6239804241435563, "percentage": 16.24, "elapsed_time": "1:21:08", "remaining_time": "6:58:30", "throughput": 4419.59, "total_tokens": 21517184} {"current_steps": 9960, "total_steps": 61300, "loss": 0.3243, "lr": 4.940809325366473e-05, "epoch": 1.6247960848287113, "percentage": 16.25, "elapsed_time": "1:21:10", "remaining_time": "6:58:26", "throughput": 4419.73, "total_tokens": 21527104} {"current_steps": 9965, "total_steps": 61300, "loss": 0.339, "lr": 4.9406552541406707e-05, "epoch": 1.6256117455138663, "percentage": 16.26, "elapsed_time": "1:21:12", "remaining_time": "6:58:22", "throughput": 4419.88, "total_tokens": 21537024} {"current_steps": 9970, "total_steps": 61300, "loss": 0.3836, "lr": 4.94050098506297e-05, "epoch": 1.6264274061990212, "percentage": 16.26, "elapsed_time": "1:21:14", "remaining_time": "6:58:18", "throughput": 4420.07, "total_tokens": 21547648} {"current_steps": 9975, "total_steps": 61300, "loss": 0.3415, "lr": 4.940346518145876e-05, "epoch": 1.6272430668841762, "percentage": 16.27, "elapsed_time": "1:21:17", "remaining_time": "6:58:15", "throughput": 4420.26, "total_tokens": 21558944} {"current_steps": 9980, "total_steps": 61300, "loss": 0.3408, "lr": 4.940191853401911e-05, "epoch": 1.6280587275693312, "percentage": 16.28, "elapsed_time": "1:21:19", "remaining_time": "6:58:11", "throughput": 4420.48, "total_tokens": 21569408} {"current_steps": 9985, "total_steps": 61300, "loss": 0.2964, "lr": 4.940036990843613e-05, "epoch": 1.628874388254486, "percentage": 16.29, "elapsed_time": "1:21:21", "remaining_time": "6:58:08", "throughput": 4420.66, "total_tokens": 21580384} {"current_steps": 9990, "total_steps": 61300, "loss": 0.3732, "lr": 4.9398819304835364e-05, "epoch": 1.629690048939641, "percentage": 16.3, "elapsed_time": "1:21:23", "remaining_time": "6:58:04", "throughput": 4420.85, "total_tokens": 21591328} {"current_steps": 9995, "total_steps": 61300, "loss": 0.3953, "lr": 4.93972667233425e-05, "epoch": 1.6305057096247961, "percentage": 16.31, "elapsed_time": "1:21:26", "remaining_time": "6:58:02", "throughput": 4421.06, "total_tokens": 21603456} {"current_steps": 10000, "total_steps": 61300, "loss": 0.3662, "lr": 4.9395712164083406e-05, "epoch": 1.631321370309951, "percentage": 16.31, "elapsed_time": "1:21:28", "remaining_time": "6:57:58", "throughput": 4421.22, "total_tokens": 21613248} {"current_steps": 10005, "total_steps": 61300, "loss": 0.3364, "lr": 4.93941556271841e-05, "epoch": 1.632137030995106, "percentage": 16.32, "elapsed_time": "1:21:30", "remaining_time": "6:57:54", "throughput": 4421.43, "total_tokens": 21624256} {"current_steps": 10010, "total_steps": 61300, "loss": 0.3509, "lr": 4.9392597112770765e-05, "epoch": 1.632952691680261, "percentage": 16.33, "elapsed_time": "1:21:33", "remaining_time": "6:57:52", "throughput": 4421.64, "total_tokens": 21636032} {"current_steps": 10015, "total_steps": 61300, "loss": 0.3571, "lr": 4.939103662096974e-05, "epoch": 1.6337683523654158, "percentage": 16.34, "elapsed_time": "1:21:35", "remaining_time": "6:57:49", "throughput": 4421.84, "total_tokens": 21647264} {"current_steps": 10020, "total_steps": 61300, "loss": 0.353, "lr": 4.938947415190754e-05, "epoch": 1.634584013050571, "percentage": 16.35, "elapsed_time": "1:21:37", "remaining_time": "6:57:46", "throughput": 4422.02, "total_tokens": 21658496} {"current_steps": 10025, "total_steps": 61300, "loss": 0.3534, "lr": 4.93879097057108e-05, "epoch": 1.635399673735726, "percentage": 16.35, "elapsed_time": "1:21:40", "remaining_time": "6:57:42", "throughput": 4422.2, "total_tokens": 21669248} {"current_steps": 10030, "total_steps": 61300, "loss": 0.3531, "lr": 4.938634328250636e-05, "epoch": 1.636215334420881, "percentage": 16.36, "elapsed_time": "1:21:42", "remaining_time": "6:57:39", "throughput": 4422.37, "total_tokens": 21679840} {"current_steps": 10035, "total_steps": 61300, "loss": 0.3499, "lr": 4.93847748824212e-05, "epoch": 1.637030995106036, "percentage": 16.37, "elapsed_time": "1:21:44", "remaining_time": "6:57:36", "throughput": 4422.55, "total_tokens": 21691904} {"current_steps": 10040, "total_steps": 61300, "loss": 0.3555, "lr": 4.938320450558246e-05, "epoch": 1.6378466557911908, "percentage": 16.38, "elapsed_time": "1:21:46", "remaining_time": "6:57:32", "throughput": 4422.7, "total_tokens": 21701408} {"current_steps": 10045, "total_steps": 61300, "loss": 0.3207, "lr": 4.938163215211745e-05, "epoch": 1.6386623164763459, "percentage": 16.39, "elapsed_time": "1:21:49", "remaining_time": "6:57:28", "throughput": 4422.86, "total_tokens": 21712256} {"current_steps": 10050, "total_steps": 61300, "loss": 0.3621, "lr": 4.938005782215362e-05, "epoch": 1.639477977161501, "percentage": 16.39, "elapsed_time": "1:21:51", "remaining_time": "6:57:24", "throughput": 4423.0, "total_tokens": 21722304} {"current_steps": 10055, "total_steps": 61300, "loss": 0.3661, "lr": 4.93784815158186e-05, "epoch": 1.6402936378466557, "percentage": 16.4, "elapsed_time": "1:21:53", "remaining_time": "6:57:21", "throughput": 4423.18, "total_tokens": 21733152} {"current_steps": 10060, "total_steps": 61300, "loss": 0.333, "lr": 4.937690323324017e-05, "epoch": 1.6411092985318108, "percentage": 16.41, "elapsed_time": "1:21:55", "remaining_time": "6:57:18", "throughput": 4423.37, "total_tokens": 21744160} {"current_steps": 10065, "total_steps": 61300, "loss": 0.3369, "lr": 4.9375322974546285e-05, "epoch": 1.6419249592169658, "percentage": 16.42, "elapsed_time": "1:21:57", "remaining_time": "6:57:14", "throughput": 4423.54, "total_tokens": 21754432} {"current_steps": 10070, "total_steps": 61300, "loss": 0.3508, "lr": 4.937374073986504e-05, "epoch": 1.6427406199021206, "percentage": 16.43, "elapsed_time": "1:22:00", "remaining_time": "6:57:10", "throughput": 4423.71, "total_tokens": 21764928} {"current_steps": 10075, "total_steps": 61300, "loss": 0.3838, "lr": 4.937215652932469e-05, "epoch": 1.6435562805872757, "percentage": 16.44, "elapsed_time": "1:22:02", "remaining_time": "6:57:05", "throughput": 4423.89, "total_tokens": 21775008} {"current_steps": 10080, "total_steps": 61300, "loss": 0.365, "lr": 4.937057034305368e-05, "epoch": 1.6443719412724307, "percentage": 16.44, "elapsed_time": "1:22:04", "remaining_time": "6:57:02", "throughput": 4424.07, "total_tokens": 21785792} {"current_steps": 10085, "total_steps": 61300, "loss": 0.3562, "lr": 4.9368982181180576e-05, "epoch": 1.6451876019575855, "percentage": 16.45, "elapsed_time": "1:22:06", "remaining_time": "6:56:59", "throughput": 4424.26, "total_tokens": 21796704} {"current_steps": 10090, "total_steps": 61300, "loss": 0.3516, "lr": 4.936739204383413e-05, "epoch": 1.6460032626427408, "percentage": 16.46, "elapsed_time": "1:22:08", "remaining_time": "6:56:56", "throughput": 4424.43, "total_tokens": 21807840} {"current_steps": 10095, "total_steps": 61300, "loss": 0.3477, "lr": 4.936579993114324e-05, "epoch": 1.6468189233278956, "percentage": 16.47, "elapsed_time": "1:22:11", "remaining_time": "6:56:52", "throughput": 4424.6, "total_tokens": 21818528} {"current_steps": 10100, "total_steps": 61300, "loss": 0.3698, "lr": 4.936420584323699e-05, "epoch": 1.6476345840130504, "percentage": 16.48, "elapsed_time": "1:22:13", "remaining_time": "6:56:49", "throughput": 4424.78, "total_tokens": 21829472} {"current_steps": 10105, "total_steps": 61300, "loss": 0.322, "lr": 4.936260978024458e-05, "epoch": 1.6484502446982057, "percentage": 16.48, "elapsed_time": "1:22:15", "remaining_time": "6:56:46", "throughput": 4425.0, "total_tokens": 21841024} {"current_steps": 10110, "total_steps": 61300, "loss": 0.3584, "lr": 4.936101174229541e-05, "epoch": 1.6492659053833605, "percentage": 16.49, "elapsed_time": "1:22:18", "remaining_time": "6:56:43", "throughput": 4425.18, "total_tokens": 21852096} {"current_steps": 10115, "total_steps": 61300, "loss": 0.329, "lr": 4.935941172951902e-05, "epoch": 1.6500815660685155, "percentage": 16.5, "elapsed_time": "1:22:20", "remaining_time": "6:56:40", "throughput": 4425.41, "total_tokens": 21863904} {"current_steps": 10120, "total_steps": 61300, "loss": 0.3883, "lr": 4.9357809742045126e-05, "epoch": 1.6508972267536706, "percentage": 16.51, "elapsed_time": "1:22:22", "remaining_time": "6:56:36", "throughput": 4425.54, "total_tokens": 21874048} {"current_steps": 10125, "total_steps": 61300, "loss": 0.3746, "lr": 4.935620578000358e-05, "epoch": 1.6517128874388254, "percentage": 16.52, "elapsed_time": "1:22:25", "remaining_time": "6:56:33", "throughput": 4425.77, "total_tokens": 21885632} {"current_steps": 10130, "total_steps": 61300, "loss": 0.3286, "lr": 4.935459984352441e-05, "epoch": 1.6525285481239804, "percentage": 16.53, "elapsed_time": "1:22:27", "remaining_time": "6:56:30", "throughput": 4425.94, "total_tokens": 21896864} {"current_steps": 10135, "total_steps": 61300, "loss": 0.3968, "lr": 4.93529919327378e-05, "epoch": 1.6533442088091355, "percentage": 16.53, "elapsed_time": "1:22:29", "remaining_time": "6:56:27", "throughput": 4426.12, "total_tokens": 21907712} {"current_steps": 10140, "total_steps": 61300, "loss": 0.3841, "lr": 4.9351382047774095e-05, "epoch": 1.6541598694942903, "percentage": 16.54, "elapsed_time": "1:22:31", "remaining_time": "6:56:24", "throughput": 4426.3, "total_tokens": 21918464} {"current_steps": 10145, "total_steps": 61300, "loss": 0.3666, "lr": 4.934977018876381e-05, "epoch": 1.6549755301794453, "percentage": 16.55, "elapsed_time": "1:22:34", "remaining_time": "6:56:20", "throughput": 4426.49, "total_tokens": 21929664} {"current_steps": 10150, "total_steps": 61300, "loss": 0.3522, "lr": 4.93481563558376e-05, "epoch": 1.6557911908646004, "percentage": 16.56, "elapsed_time": "1:22:36", "remaining_time": "6:56:17", "throughput": 4426.67, "total_tokens": 21940288} {"current_steps": 10155, "total_steps": 61300, "loss": 0.3485, "lr": 4.9346540549126305e-05, "epoch": 1.6566068515497552, "percentage": 16.57, "elapsed_time": "1:22:38", "remaining_time": "6:56:13", "throughput": 4426.83, "total_tokens": 21950464} {"current_steps": 10160, "total_steps": 61300, "loss": 0.3317, "lr": 4.934492276876089e-05, "epoch": 1.6574225122349104, "percentage": 16.57, "elapsed_time": "1:22:40", "remaining_time": "6:56:10", "throughput": 4427.04, "total_tokens": 21961696} {"current_steps": 10165, "total_steps": 61300, "loss": 0.3571, "lr": 4.934330301487251e-05, "epoch": 1.6582381729200653, "percentage": 16.58, "elapsed_time": "1:22:42", "remaining_time": "6:56:06", "throughput": 4427.21, "total_tokens": 21972192} {"current_steps": 10170, "total_steps": 61300, "loss": 0.365, "lr": 4.934168128759248e-05, "epoch": 1.65905383360522, "percentage": 16.59, "elapsed_time": "1:22:45", "remaining_time": "6:56:01", "throughput": 4427.4, "total_tokens": 21982112} {"current_steps": 10175, "total_steps": 61300, "loss": 0.3737, "lr": 4.9340057587052245e-05, "epoch": 1.6598694942903753, "percentage": 16.6, "elapsed_time": "1:22:47", "remaining_time": "6:55:58", "throughput": 4427.6, "total_tokens": 21993568} {"current_steps": 10180, "total_steps": 61300, "loss": 0.3286, "lr": 4.9338431913383444e-05, "epoch": 1.6606851549755302, "percentage": 16.61, "elapsed_time": "1:22:49", "remaining_time": "6:55:54", "throughput": 4427.78, "total_tokens": 22003296} {"current_steps": 10185, "total_steps": 61300, "loss": 0.3653, "lr": 4.9336804266717864e-05, "epoch": 1.6615008156606852, "percentage": 16.62, "elapsed_time": "1:22:51", "remaining_time": "6:55:49", "throughput": 4427.98, "total_tokens": 22013344} {"current_steps": 10190, "total_steps": 61300, "loss": 0.2985, "lr": 4.933517464718744e-05, "epoch": 1.6623164763458402, "percentage": 16.62, "elapsed_time": "1:22:53", "remaining_time": "6:55:44", "throughput": 4428.11, "total_tokens": 22022112} {"current_steps": 10195, "total_steps": 61300, "loss": 0.3624, "lr": 4.933354305492429e-05, "epoch": 1.663132137030995, "percentage": 16.63, "elapsed_time": "1:22:55", "remaining_time": "6:55:40", "throughput": 4428.27, "total_tokens": 22032704} {"current_steps": 10200, "total_steps": 61300, "loss": 0.3417, "lr": 4.933190949006068e-05, "epoch": 1.66394779771615, "percentage": 16.64, "elapsed_time": "1:22:57", "remaining_time": "6:55:38", "throughput": 4428.45, "total_tokens": 22044320} {"current_steps": 10205, "total_steps": 61300, "loss": 0.348, "lr": 4.933027395272901e-05, "epoch": 1.6647634584013051, "percentage": 16.65, "elapsed_time": "1:23:00", "remaining_time": "6:55:34", "throughput": 4428.6, "total_tokens": 22055008} {"current_steps": 10210, "total_steps": 61300, "loss": 0.3727, "lr": 4.9328636443061894e-05, "epoch": 1.66557911908646, "percentage": 16.66, "elapsed_time": "1:23:02", "remaining_time": "6:55:31", "throughput": 4428.79, "total_tokens": 22065920} {"current_steps": 10215, "total_steps": 61300, "loss": 0.337, "lr": 4.932699696119207e-05, "epoch": 1.666394779771615, "percentage": 16.66, "elapsed_time": "1:23:04", "remaining_time": "6:55:28", "throughput": 4428.97, "total_tokens": 22077024} {"current_steps": 10220, "total_steps": 61300, "loss": 0.3527, "lr": 4.932535550725243e-05, "epoch": 1.66721044045677, "percentage": 16.67, "elapsed_time": "1:23:07", "remaining_time": "6:55:25", "throughput": 4429.15, "total_tokens": 22088320} {"current_steps": 10225, "total_steps": 61300, "loss": 0.3235, "lr": 4.932371208137605e-05, "epoch": 1.6680261011419248, "percentage": 16.68, "elapsed_time": "1:23:09", "remaining_time": "6:55:21", "throughput": 4429.32, "total_tokens": 22098528} {"current_steps": 10230, "total_steps": 61300, "loss": 0.3626, "lr": 4.932206668369615e-05, "epoch": 1.6688417618270799, "percentage": 16.69, "elapsed_time": "1:23:11", "remaining_time": "6:55:18", "throughput": 4429.51, "total_tokens": 22109792} {"current_steps": 10235, "total_steps": 61300, "loss": 0.3708, "lr": 4.932041931434611e-05, "epoch": 1.669657422512235, "percentage": 16.7, "elapsed_time": "1:23:13", "remaining_time": "6:55:14", "throughput": 4429.67, "total_tokens": 22120064} {"current_steps": 10240, "total_steps": 61300, "loss": 0.343, "lr": 4.931876997345949e-05, "epoch": 1.6704730831973897, "percentage": 16.7, "elapsed_time": "1:23:15", "remaining_time": "6:55:11", "throughput": 4429.85, "total_tokens": 22131200} {"current_steps": 10245, "total_steps": 61300, "loss": 0.3121, "lr": 4.931711866116998e-05, "epoch": 1.671288743882545, "percentage": 16.71, "elapsed_time": "1:23:18", "remaining_time": "6:55:08", "throughput": 4430.0, "total_tokens": 22142880} {"current_steps": 10250, "total_steps": 61300, "loss": 0.334, "lr": 4.9315465377611445e-05, "epoch": 1.6721044045676998, "percentage": 16.72, "elapsed_time": "1:23:20", "remaining_time": "6:55:03", "throughput": 4430.14, "total_tokens": 22151744} {"current_steps": 10255, "total_steps": 61300, "loss": 0.3421, "lr": 4.9313810122917914e-05, "epoch": 1.6729200652528549, "percentage": 16.73, "elapsed_time": "1:23:22", "remaining_time": "6:55:00", "throughput": 4430.3, "total_tokens": 22162432} {"current_steps": 10260, "total_steps": 61300, "loss": 0.387, "lr": 4.931215289722357e-05, "epoch": 1.67373572593801, "percentage": 16.74, "elapsed_time": "1:23:24", "remaining_time": "6:54:58", "throughput": 4430.48, "total_tokens": 22174432} {"current_steps": 10265, "total_steps": 61300, "loss": 0.3987, "lr": 4.931049370066275e-05, "epoch": 1.6745513866231647, "percentage": 16.75, "elapsed_time": "1:23:27", "remaining_time": "6:54:54", "throughput": 4430.63, "total_tokens": 22185184} {"current_steps": 10270, "total_steps": 61300, "loss": 0.3345, "lr": 4.930883253336996e-05, "epoch": 1.6753670473083198, "percentage": 16.75, "elapsed_time": "1:23:29", "remaining_time": "6:54:51", "throughput": 4430.81, "total_tokens": 22196480} {"current_steps": 10275, "total_steps": 61300, "loss": 0.344, "lr": 4.930716939547986e-05, "epoch": 1.6761827079934748, "percentage": 16.76, "elapsed_time": "1:23:31", "remaining_time": "6:54:48", "throughput": 4430.97, "total_tokens": 22207392} {"current_steps": 10280, "total_steps": 61300, "loss": 0.3561, "lr": 4.930550428712728e-05, "epoch": 1.6769983686786296, "percentage": 16.77, "elapsed_time": "1:23:34", "remaining_time": "6:54:45", "throughput": 4431.13, "total_tokens": 22218880} {"current_steps": 10285, "total_steps": 61300, "loss": 0.3425, "lr": 4.93038372084472e-05, "epoch": 1.6778140293637847, "percentage": 16.78, "elapsed_time": "1:23:36", "remaining_time": "6:54:42", "throughput": 4431.29, "total_tokens": 22229184} {"current_steps": 10290, "total_steps": 61300, "loss": 0.358, "lr": 4.9302168159574756e-05, "epoch": 1.6786296900489397, "percentage": 16.79, "elapsed_time": "1:23:38", "remaining_time": "6:54:38", "throughput": 4431.47, "total_tokens": 22240096} {"current_steps": 10295, "total_steps": 61300, "loss": 0.3556, "lr": 4.930049714064525e-05, "epoch": 1.6794453507340945, "percentage": 16.79, "elapsed_time": "1:23:41", "remaining_time": "6:54:36", "throughput": 4431.66, "total_tokens": 22251616} {"current_steps": 10300, "total_steps": 61300, "loss": 0.3397, "lr": 4.9298824151794154e-05, "epoch": 1.6802610114192496, "percentage": 16.8, "elapsed_time": "1:23:43", "remaining_time": "6:54:32", "throughput": 4431.82, "total_tokens": 22262464} {"current_steps": 10305, "total_steps": 61300, "loss": 0.3701, "lr": 4.9297149193157075e-05, "epoch": 1.6810766721044046, "percentage": 16.81, "elapsed_time": "1:23:45", "remaining_time": "6:54:28", "throughput": 4431.97, "total_tokens": 22272640} {"current_steps": 10310, "total_steps": 61300, "loss": 0.3577, "lr": 4.9295472264869804e-05, "epoch": 1.6818923327895594, "percentage": 16.82, "elapsed_time": "1:23:47", "remaining_time": "6:54:25", "throughput": 4432.15, "total_tokens": 22283264} {"current_steps": 10315, "total_steps": 61300, "loss": 0.3227, "lr": 4.929379336706827e-05, "epoch": 1.6827079934747147, "percentage": 16.83, "elapsed_time": "1:23:49", "remaining_time": "6:54:22", "throughput": 4432.27, "total_tokens": 22294112} {"current_steps": 10320, "total_steps": 61300, "loss": 0.3714, "lr": 4.9292112499888584e-05, "epoch": 1.6835236541598695, "percentage": 16.84, "elapsed_time": "1:23:52", "remaining_time": "6:54:18", "throughput": 4432.44, "total_tokens": 22305184} {"current_steps": 10325, "total_steps": 61300, "loss": 0.408, "lr": 4.929042966346701e-05, "epoch": 1.6843393148450243, "percentage": 16.84, "elapsed_time": "1:23:54", "remaining_time": "6:54:15", "throughput": 4432.59, "total_tokens": 22315840} {"current_steps": 10330, "total_steps": 61300, "loss": 0.3674, "lr": 4.928874485793995e-05, "epoch": 1.6851549755301796, "percentage": 16.85, "elapsed_time": "1:23:56", "remaining_time": "6:54:11", "throughput": 4432.78, "total_tokens": 22325728} {"current_steps": 10335, "total_steps": 61300, "loss": 0.3616, "lr": 4.928705808344399e-05, "epoch": 1.6859706362153344, "percentage": 16.86, "elapsed_time": "1:23:58", "remaining_time": "6:54:06", "throughput": 4432.98, "total_tokens": 22335904} {"current_steps": 10340, "total_steps": 61300, "loss": 0.3613, "lr": 4.928536934011587e-05, "epoch": 1.6867862969004894, "percentage": 16.87, "elapsed_time": "1:24:00", "remaining_time": "6:54:01", "throughput": 4433.13, "total_tokens": 22345184} {"current_steps": 10345, "total_steps": 61300, "loss": 0.324, "lr": 4.92836786280925e-05, "epoch": 1.6876019575856445, "percentage": 16.88, "elapsed_time": "1:24:02", "remaining_time": "6:53:59", "throughput": 4433.33, "total_tokens": 22356736} {"current_steps": 10350, "total_steps": 61300, "loss": 0.3814, "lr": 4.9281985947510915e-05, "epoch": 1.6884176182707993, "percentage": 16.88, "elapsed_time": "1:24:05", "remaining_time": "6:53:56", "throughput": 4433.55, "total_tokens": 22368704} {"current_steps": 10355, "total_steps": 61300, "loss": 0.3487, "lr": 4.9280291298508355e-05, "epoch": 1.6892332789559543, "percentage": 16.89, "elapsed_time": "1:24:07", "remaining_time": "6:53:53", "throughput": 4433.72, "total_tokens": 22379904} {"current_steps": 10360, "total_steps": 61300, "loss": 0.3392, "lr": 4.927859468122217e-05, "epoch": 1.6900489396411094, "percentage": 16.9, "elapsed_time": "1:24:10", "remaining_time": "6:53:51", "throughput": 4433.9, "total_tokens": 22391776} {"current_steps": 10365, "total_steps": 61300, "loss": 0.3426, "lr": 4.9276896095789924e-05, "epoch": 1.6908646003262642, "percentage": 16.91, "elapsed_time": "1:24:12", "remaining_time": "6:53:47", "throughput": 4434.07, "total_tokens": 22401792} {"current_steps": 10370, "total_steps": 61300, "loss": 0.3556, "lr": 4.927519554234929e-05, "epoch": 1.6916802610114192, "percentage": 16.92, "elapsed_time": "1:24:14", "remaining_time": "6:53:43", "throughput": 4434.18, "total_tokens": 22411968} {"current_steps": 10375, "total_steps": 61300, "loss": 0.3537, "lr": 4.9273493021038146e-05, "epoch": 1.6924959216965743, "percentage": 16.92, "elapsed_time": "1:24:16", "remaining_time": "6:53:41", "throughput": 4434.36, "total_tokens": 22424000} {"current_steps": 10380, "total_steps": 61300, "loss": 0.3505, "lr": 4.927178853199449e-05, "epoch": 1.693311582381729, "percentage": 16.93, "elapsed_time": "1:24:18", "remaining_time": "6:53:37", "throughput": 4434.5, "total_tokens": 22434048} {"current_steps": 10385, "total_steps": 61300, "loss": 0.3118, "lr": 4.927008207535651e-05, "epoch": 1.6941272430668843, "percentage": 16.94, "elapsed_time": "1:24:21", "remaining_time": "6:53:35", "throughput": 4434.72, "total_tokens": 22446176} {"current_steps": 10390, "total_steps": 61300, "loss": 0.374, "lr": 4.9268373651262515e-05, "epoch": 1.6949429037520392, "percentage": 16.95, "elapsed_time": "1:24:23", "remaining_time": "6:53:32", "throughput": 4434.91, "total_tokens": 22457600} {"current_steps": 10395, "total_steps": 61300, "loss": 0.3619, "lr": 4.9266663259851025e-05, "epoch": 1.695758564437194, "percentage": 16.96, "elapsed_time": "1:24:26", "remaining_time": "6:53:29", "throughput": 4435.03, "total_tokens": 22468768} {"current_steps": 10400, "total_steps": 61300, "loss": 0.3539, "lr": 4.926495090126068e-05, "epoch": 1.6965742251223492, "percentage": 16.97, "elapsed_time": "1:24:28", "remaining_time": "6:53:26", "throughput": 4435.25, "total_tokens": 22480448} {"current_steps": 10405, "total_steps": 61300, "loss": 0.3556, "lr": 4.92632365756303e-05, "epoch": 1.697389885807504, "percentage": 16.97, "elapsed_time": "1:24:30", "remaining_time": "6:53:22", "throughput": 4435.43, "total_tokens": 22490880} {"current_steps": 10410, "total_steps": 61300, "loss": 0.3325, "lr": 4.926152028309885e-05, "epoch": 1.698205546492659, "percentage": 16.98, "elapsed_time": "1:24:32", "remaining_time": "6:53:18", "throughput": 4435.58, "total_tokens": 22500704} {"current_steps": 10415, "total_steps": 61300, "loss": 0.3296, "lr": 4.9259802023805466e-05, "epoch": 1.6990212071778141, "percentage": 16.99, "elapsed_time": "1:24:34", "remaining_time": "6:53:14", "throughput": 4435.73, "total_tokens": 22511040} {"current_steps": 10420, "total_steps": 61300, "loss": 0.389, "lr": 4.9258081797889434e-05, "epoch": 1.699836867862969, "percentage": 17.0, "elapsed_time": "1:24:37", "remaining_time": "6:53:11", "throughput": 4435.87, "total_tokens": 22521664} {"current_steps": 10425, "total_steps": 61300, "loss": 0.3592, "lr": 4.925635960549021e-05, "epoch": 1.700652528548124, "percentage": 17.01, "elapsed_time": "1:24:39", "remaining_time": "6:53:07", "throughput": 4436.06, "total_tokens": 22532192} {"current_steps": 10430, "total_steps": 61300, "loss": 0.2994, "lr": 4.92546354467474e-05, "epoch": 1.701468189233279, "percentage": 17.01, "elapsed_time": "1:24:41", "remaining_time": "6:53:05", "throughput": 4436.23, "total_tokens": 22543712} {"current_steps": 10435, "total_steps": 61300, "loss": 0.3665, "lr": 4.9252909321800775e-05, "epoch": 1.7022838499184338, "percentage": 17.02, "elapsed_time": "1:24:44", "remaining_time": "6:53:02", "throughput": 4436.44, "total_tokens": 22555232} {"current_steps": 10440, "total_steps": 61300, "loss": 0.3426, "lr": 4.925118123079026e-05, "epoch": 1.7030995106035889, "percentage": 17.03, "elapsed_time": "1:24:46", "remaining_time": "6:52:59", "throughput": 4436.65, "total_tokens": 22566720} {"current_steps": 10445, "total_steps": 61300, "loss": 0.3647, "lr": 4.924945117385594e-05, "epoch": 1.703915171288744, "percentage": 17.04, "elapsed_time": "1:24:48", "remaining_time": "6:52:55", "throughput": 4436.82, "total_tokens": 22577376} {"current_steps": 10450, "total_steps": 61300, "loss": 0.3586, "lr": 4.9247719151138086e-05, "epoch": 1.7047308319738987, "percentage": 17.05, "elapsed_time": "1:24:51", "remaining_time": "6:52:53", "throughput": 4437.0, "total_tokens": 22589568} {"current_steps": 10455, "total_steps": 61300, "loss": 0.3085, "lr": 4.924598516277707e-05, "epoch": 1.7055464926590538, "percentage": 17.06, "elapsed_time": "1:24:53", "remaining_time": "6:52:50", "throughput": 4437.15, "total_tokens": 22600672} {"current_steps": 10460, "total_steps": 61300, "loss": 0.3812, "lr": 4.924424920891347e-05, "epoch": 1.7063621533442088, "percentage": 17.06, "elapsed_time": "1:24:55", "remaining_time": "6:52:47", "throughput": 4437.33, "total_tokens": 22611200} {"current_steps": 10465, "total_steps": 61300, "loss": 0.3818, "lr": 4.9242511289688024e-05, "epoch": 1.7071778140293636, "percentage": 17.07, "elapsed_time": "1:24:57", "remaining_time": "6:52:42", "throughput": 4437.45, "total_tokens": 22620608} {"current_steps": 10470, "total_steps": 61300, "loss": 0.4086, "lr": 4.924077140524161e-05, "epoch": 1.707993474714519, "percentage": 17.08, "elapsed_time": "1:24:59", "remaining_time": "6:52:38", "throughput": 4437.63, "total_tokens": 22631168} {"current_steps": 10475, "total_steps": 61300, "loss": 0.3505, "lr": 4.9239029555715264e-05, "epoch": 1.7088091353996737, "percentage": 17.09, "elapsed_time": "1:25:01", "remaining_time": "6:52:33", "throughput": 4437.79, "total_tokens": 22640640} {"current_steps": 10480, "total_steps": 61300, "loss": 0.3103, "lr": 4.92372857412502e-05, "epoch": 1.7096247960848288, "percentage": 17.1, "elapsed_time": "1:25:03", "remaining_time": "6:52:30", "throughput": 4437.94, "total_tokens": 22650976} {"current_steps": 10485, "total_steps": 61300, "loss": 0.3919, "lr": 4.9235539961987766e-05, "epoch": 1.7104404567699838, "percentage": 17.1, "elapsed_time": "1:25:06", "remaining_time": "6:52:26", "throughput": 4438.09, "total_tokens": 22661472} {"current_steps": 10490, "total_steps": 61300, "loss": 0.3434, "lr": 4.9233792218069494e-05, "epoch": 1.7112561174551386, "percentage": 17.11, "elapsed_time": "1:25:08", "remaining_time": "6:52:23", "throughput": 4438.28, "total_tokens": 22673024} {"current_steps": 10495, "total_steps": 61300, "loss": 0.3621, "lr": 4.923204250963707e-05, "epoch": 1.7120717781402937, "percentage": 17.12, "elapsed_time": "1:25:10", "remaining_time": "6:52:21", "throughput": 4438.46, "total_tokens": 22684416} {"current_steps": 10500, "total_steps": 61300, "loss": 0.3628, "lr": 4.923029083683233e-05, "epoch": 1.7128874388254487, "percentage": 17.13, "elapsed_time": "1:25:13", "remaining_time": "6:52:17", "throughput": 4438.62, "total_tokens": 22695136} {"current_steps": 10505, "total_steps": 61300, "loss": 0.3515, "lr": 4.9228537199797263e-05, "epoch": 1.7137030995106035, "percentage": 17.14, "elapsed_time": "1:25:15", "remaining_time": "6:52:14", "throughput": 4438.74, "total_tokens": 22705408} {"current_steps": 10510, "total_steps": 61300, "loss": 0.3294, "lr": 4.9226781598674047e-05, "epoch": 1.7145187601957586, "percentage": 17.15, "elapsed_time": "1:25:17", "remaining_time": "6:52:10", "throughput": 4438.93, "total_tokens": 22716000} {"current_steps": 10515, "total_steps": 61300, "loss": 0.3112, "lr": 4.922502403360498e-05, "epoch": 1.7153344208809136, "percentage": 17.15, "elapsed_time": "1:25:19", "remaining_time": "6:52:08", "throughput": 4439.1, "total_tokens": 22727936} {"current_steps": 10520, "total_steps": 61300, "loss": 0.3702, "lr": 4.922326450473255e-05, "epoch": 1.7161500815660684, "percentage": 17.16, "elapsed_time": "1:25:21", "remaining_time": "6:52:03", "throughput": 4439.24, "total_tokens": 22737632} {"current_steps": 10525, "total_steps": 61300, "loss": 0.3398, "lr": 4.9221503012199386e-05, "epoch": 1.7169657422512234, "percentage": 17.17, "elapsed_time": "1:25:24", "remaining_time": "6:52:00", "throughput": 4439.42, "total_tokens": 22748288} {"current_steps": 10530, "total_steps": 61300, "loss": 0.3373, "lr": 4.92197395561483e-05, "epoch": 1.7177814029363785, "percentage": 17.18, "elapsed_time": "1:25:26", "remaining_time": "6:51:57", "throughput": 4439.6, "total_tokens": 22760288} {"current_steps": 10535, "total_steps": 61300, "loss": 0.3325, "lr": 4.9217974136722235e-05, "epoch": 1.7185970636215333, "percentage": 17.19, "elapsed_time": "1:25:29", "remaining_time": "6:51:55", "throughput": 4439.83, "total_tokens": 22772032} {"current_steps": 10540, "total_steps": 61300, "loss": 0.3889, "lr": 4.92162067540643e-05, "epoch": 1.7194127243066886, "percentage": 17.19, "elapsed_time": "1:25:31", "remaining_time": "6:51:52", "throughput": 4440.02, "total_tokens": 22783392} {"current_steps": 10545, "total_steps": 61300, "loss": 0.3732, "lr": 4.921443740831778e-05, "epoch": 1.7202283849918434, "percentage": 17.2, "elapsed_time": "1:25:33", "remaining_time": "6:51:50", "throughput": 4440.23, "total_tokens": 22795808} {"current_steps": 10550, "total_steps": 61300, "loss": 0.4012, "lr": 4.9212666099626095e-05, "epoch": 1.7210440456769984, "percentage": 17.21, "elapsed_time": "1:25:36", "remaining_time": "6:51:47", "throughput": 4440.36, "total_tokens": 22806400} {"current_steps": 10555, "total_steps": 61300, "loss": 0.3237, "lr": 4.9210892828132835e-05, "epoch": 1.7218597063621535, "percentage": 17.22, "elapsed_time": "1:25:38", "remaining_time": "6:51:43", "throughput": 4440.48, "total_tokens": 22816256} {"current_steps": 10560, "total_steps": 61300, "loss": 0.3331, "lr": 4.920911759398177e-05, "epoch": 1.7226753670473083, "percentage": 17.23, "elapsed_time": "1:25:40", "remaining_time": "6:51:39", "throughput": 4440.63, "total_tokens": 22827200} {"current_steps": 10565, "total_steps": 61300, "loss": 0.3368, "lr": 4.920734039731679e-05, "epoch": 1.7234910277324633, "percentage": 17.23, "elapsed_time": "1:25:42", "remaining_time": "6:51:35", "throughput": 4440.77, "total_tokens": 22837248} {"current_steps": 10570, "total_steps": 61300, "loss": 0.372, "lr": 4.9205561238281985e-05, "epoch": 1.7243066884176184, "percentage": 17.24, "elapsed_time": "1:25:44", "remaining_time": "6:51:30", "throughput": 4440.87, "total_tokens": 22846048} {"current_steps": 10575, "total_steps": 61300, "loss": 0.3533, "lr": 4.920378011702155e-05, "epoch": 1.7251223491027732, "percentage": 17.25, "elapsed_time": "1:25:46", "remaining_time": "6:51:26", "throughput": 4441.06, "total_tokens": 22856672} {"current_steps": 10580, "total_steps": 61300, "loss": 0.3656, "lr": 4.92019970336799e-05, "epoch": 1.7259380097879282, "percentage": 17.26, "elapsed_time": "1:25:49", "remaining_time": "6:51:24", "throughput": 4441.25, "total_tokens": 22868224} {"current_steps": 10585, "total_steps": 61300, "loss": 0.3688, "lr": 4.920021198840157e-05, "epoch": 1.7267536704730833, "percentage": 17.27, "elapsed_time": "1:25:51", "remaining_time": "6:51:21", "throughput": 4441.44, "total_tokens": 22879584} {"current_steps": 10590, "total_steps": 61300, "loss": 0.322, "lr": 4.919842498133126e-05, "epoch": 1.727569331158238, "percentage": 17.28, "elapsed_time": "1:25:53", "remaining_time": "6:51:17", "throughput": 4441.58, "total_tokens": 22889696} {"current_steps": 10595, "total_steps": 61300, "loss": 0.3669, "lr": 4.919663601261384e-05, "epoch": 1.7283849918433931, "percentage": 17.28, "elapsed_time": "1:25:55", "remaining_time": "6:51:13", "throughput": 4441.77, "total_tokens": 22900224} {"current_steps": 10600, "total_steps": 61300, "loss": 0.3275, "lr": 4.919484508239434e-05, "epoch": 1.7292006525285482, "percentage": 17.29, "elapsed_time": "1:25:57", "remaining_time": "6:51:10", "throughput": 4441.95, "total_tokens": 22911136} {"current_steps": 10605, "total_steps": 61300, "loss": 0.3551, "lr": 4.9193052190817926e-05, "epoch": 1.730016313213703, "percentage": 17.3, "elapsed_time": "1:26:00", "remaining_time": "6:51:07", "throughput": 4442.18, "total_tokens": 22922400} {"current_steps": 10610, "total_steps": 61300, "loss": 0.3291, "lr": 4.919125733802995e-05, "epoch": 1.7308319738988582, "percentage": 17.31, "elapsed_time": "1:26:02", "remaining_time": "6:51:04", "throughput": 4442.37, "total_tokens": 22933664} {"current_steps": 10615, "total_steps": 61300, "loss": 0.3648, "lr": 4.9189460524175915e-05, "epoch": 1.731647634584013, "percentage": 17.32, "elapsed_time": "1:26:04", "remaining_time": "6:50:59", "throughput": 4442.45, "total_tokens": 22943104} {"current_steps": 10620, "total_steps": 61300, "loss": 0.3795, "lr": 4.918766174940146e-05, "epoch": 1.7324632952691679, "percentage": 17.32, "elapsed_time": "1:26:06", "remaining_time": "6:50:55", "throughput": 4442.58, "total_tokens": 22953344} {"current_steps": 10625, "total_steps": 61300, "loss": 0.358, "lr": 4.918586101385243e-05, "epoch": 1.7332789559543231, "percentage": 17.33, "elapsed_time": "1:26:09", "remaining_time": "6:50:53", "throughput": 4442.78, "total_tokens": 22964928} {"current_steps": 10630, "total_steps": 61300, "loss": 0.3425, "lr": 4.918405831767478e-05, "epoch": 1.734094616639478, "percentage": 17.34, "elapsed_time": "1:26:11", "remaining_time": "6:50:51", "throughput": 4442.95, "total_tokens": 22977152} {"current_steps": 10635, "total_steps": 61300, "loss": 0.3102, "lr": 4.9182253661014656e-05, "epoch": 1.734910277324633, "percentage": 17.35, "elapsed_time": "1:26:13", "remaining_time": "6:50:48", "throughput": 4443.12, "total_tokens": 22988448} {"current_steps": 10640, "total_steps": 61300, "loss": 0.3379, "lr": 4.9180447044018354e-05, "epoch": 1.735725938009788, "percentage": 17.36, "elapsed_time": "1:26:16", "remaining_time": "6:50:44", "throughput": 4443.26, "total_tokens": 22998592} {"current_steps": 10645, "total_steps": 61300, "loss": 0.3537, "lr": 4.917863846683232e-05, "epoch": 1.7365415986949428, "percentage": 17.37, "elapsed_time": "1:26:18", "remaining_time": "6:50:41", "throughput": 4443.44, "total_tokens": 23009344} {"current_steps": 10650, "total_steps": 61300, "loss": 0.3291, "lr": 4.9176827929603176e-05, "epoch": 1.7373572593800979, "percentage": 17.37, "elapsed_time": "1:26:20", "remaining_time": "6:50:37", "throughput": 4443.56, "total_tokens": 23019584} {"current_steps": 10655, "total_steps": 61300, "loss": 0.3941, "lr": 4.9175015432477686e-05, "epoch": 1.738172920065253, "percentage": 17.38, "elapsed_time": "1:26:22", "remaining_time": "6:50:34", "throughput": 4443.7, "total_tokens": 23030336} {"current_steps": 10660, "total_steps": 61300, "loss": 0.3456, "lr": 4.9173200975602776e-05, "epoch": 1.7389885807504077, "percentage": 17.39, "elapsed_time": "1:26:25", "remaining_time": "6:50:31", "throughput": 4443.9, "total_tokens": 23041760} {"current_steps": 10665, "total_steps": 61300, "loss": 0.353, "lr": 4.917138455912555e-05, "epoch": 1.7398042414355628, "percentage": 17.4, "elapsed_time": "1:26:27", "remaining_time": "6:50:27", "throughput": 4444.06, "total_tokens": 23051840} {"current_steps": 10670, "total_steps": 61300, "loss": 0.3175, "lr": 4.916956618319324e-05, "epoch": 1.7406199021207178, "percentage": 17.41, "elapsed_time": "1:26:29", "remaining_time": "6:50:23", "throughput": 4444.19, "total_tokens": 23061632} {"current_steps": 10675, "total_steps": 61300, "loss": 0.3496, "lr": 4.916774584795327e-05, "epoch": 1.7414355628058726, "percentage": 17.41, "elapsed_time": "1:26:31", "remaining_time": "6:50:18", "throughput": 4444.31, "total_tokens": 23071520} {"current_steps": 10680, "total_steps": 61300, "loss": 0.3495, "lr": 4.916592355355318e-05, "epoch": 1.7422512234910277, "percentage": 17.42, "elapsed_time": "1:26:33", "remaining_time": "6:50:15", "throughput": 4444.47, "total_tokens": 23082304} {"current_steps": 10685, "total_steps": 61300, "loss": 0.3382, "lr": 4.916409930014073e-05, "epoch": 1.7430668841761827, "percentage": 17.43, "elapsed_time": "1:26:35", "remaining_time": "6:50:11", "throughput": 4444.57, "total_tokens": 23092416} {"current_steps": 10690, "total_steps": 61300, "loss": 0.3518, "lr": 4.916227308786377e-05, "epoch": 1.7438825448613375, "percentage": 17.44, "elapsed_time": "1:26:37", "remaining_time": "6:50:08", "throughput": 4444.69, "total_tokens": 23102720} {"current_steps": 10695, "total_steps": 61300, "loss": 0.3751, "lr": 4.916044491687036e-05, "epoch": 1.7446982055464928, "percentage": 17.45, "elapsed_time": "1:26:40", "remaining_time": "6:50:05", "throughput": 4444.85, "total_tokens": 23114016} {"current_steps": 10700, "total_steps": 61300, "loss": 0.3316, "lr": 4.915861478730869e-05, "epoch": 1.7455138662316476, "percentage": 17.46, "elapsed_time": "1:26:42", "remaining_time": "6:50:03", "throughput": 4445.04, "total_tokens": 23125888} {"current_steps": 10705, "total_steps": 61300, "loss": 0.3094, "lr": 4.915678269932713e-05, "epoch": 1.7463295269168027, "percentage": 17.46, "elapsed_time": "1:26:44", "remaining_time": "6:50:00", "throughput": 4445.22, "total_tokens": 23137248} {"current_steps": 10710, "total_steps": 61300, "loss": 0.3741, "lr": 4.91549486530742e-05, "epoch": 1.7471451876019577, "percentage": 17.47, "elapsed_time": "1:26:47", "remaining_time": "6:49:56", "throughput": 4445.38, "total_tokens": 23148064} {"current_steps": 10715, "total_steps": 61300, "loss": 0.3598, "lr": 4.9153112648698565e-05, "epoch": 1.7479608482871125, "percentage": 17.48, "elapsed_time": "1:26:49", "remaining_time": "6:49:53", "throughput": 4445.51, "total_tokens": 23158208} {"current_steps": 10720, "total_steps": 61300, "loss": 0.3143, "lr": 4.915127468634906e-05, "epoch": 1.7487765089722676, "percentage": 17.49, "elapsed_time": "1:26:51", "remaining_time": "6:49:50", "throughput": 4445.67, "total_tokens": 23170144} {"current_steps": 10725, "total_steps": 61300, "loss": 0.3294, "lr": 4.9149434766174695e-05, "epoch": 1.7495921696574226, "percentage": 17.5, "elapsed_time": "1:26:54", "remaining_time": "6:49:47", "throughput": 4445.81, "total_tokens": 23180768} {"current_steps": 10730, "total_steps": 61300, "loss": 0.3304, "lr": 4.914759288832462e-05, "epoch": 1.7504078303425774, "percentage": 17.5, "elapsed_time": "1:26:56", "remaining_time": "6:49:44", "throughput": 4445.98, "total_tokens": 23191840} {"current_steps": 10735, "total_steps": 61300, "loss": 0.3415, "lr": 4.914574905294813e-05, "epoch": 1.7512234910277324, "percentage": 17.51, "elapsed_time": "1:26:58", "remaining_time": "6:49:40", "throughput": 4446.14, "total_tokens": 23201760} {"current_steps": 10740, "total_steps": 61300, "loss": 0.3172, "lr": 4.9143903260194715e-05, "epoch": 1.7520391517128875, "percentage": 17.52, "elapsed_time": "1:27:00", "remaining_time": "6:49:37", "throughput": 4446.26, "total_tokens": 23213024} {"current_steps": 10745, "total_steps": 61300, "loss": 0.3183, "lr": 4.914205551021399e-05, "epoch": 1.7528548123980423, "percentage": 17.53, "elapsed_time": "1:27:03", "remaining_time": "6:49:34", "throughput": 4446.44, "total_tokens": 23224512} {"current_steps": 10750, "total_steps": 61300, "loss": 0.3238, "lr": 4.914020580315576e-05, "epoch": 1.7536704730831973, "percentage": 17.54, "elapsed_time": "1:27:05", "remaining_time": "6:49:31", "throughput": 4446.58, "total_tokens": 23235040} {"current_steps": 10755, "total_steps": 61300, "loss": 0.3534, "lr": 4.913835413916996e-05, "epoch": 1.7544861337683524, "percentage": 17.54, "elapsed_time": "1:27:07", "remaining_time": "6:49:27", "throughput": 4446.71, "total_tokens": 23245056} {"current_steps": 10760, "total_steps": 61300, "loss": 0.3746, "lr": 4.9136500518406694e-05, "epoch": 1.7553017944535072, "percentage": 17.55, "elapsed_time": "1:27:10", "remaining_time": "6:49:26", "throughput": 4446.9, "total_tokens": 23257824} {"current_steps": 10765, "total_steps": 61300, "loss": 0.3229, "lr": 4.913464494101622e-05, "epoch": 1.7561174551386625, "percentage": 17.56, "elapsed_time": "1:27:12", "remaining_time": "6:49:23", "throughput": 4447.06, "total_tokens": 23269376} {"current_steps": 10770, "total_steps": 61300, "loss": 0.3844, "lr": 4.913278740714898e-05, "epoch": 1.7569331158238173, "percentage": 17.57, "elapsed_time": "1:27:15", "remaining_time": "6:49:22", "throughput": 4447.28, "total_tokens": 23282560} {"current_steps": 10775, "total_steps": 61300, "loss": 0.3593, "lr": 4.913092791695554e-05, "epoch": 1.7577487765089723, "percentage": 17.58, "elapsed_time": "1:27:17", "remaining_time": "6:49:18", "throughput": 4447.4, "total_tokens": 23292896} {"current_steps": 10780, "total_steps": 61300, "loss": 0.3143, "lr": 4.912906647058664e-05, "epoch": 1.7585644371941274, "percentage": 17.59, "elapsed_time": "1:27:19", "remaining_time": "6:49:14", "throughput": 4447.55, "total_tokens": 23303168} {"current_steps": 10785, "total_steps": 61300, "loss": 0.314, "lr": 4.912720306819319e-05, "epoch": 1.7593800978792822, "percentage": 17.59, "elapsed_time": "1:27:21", "remaining_time": "6:49:12", "throughput": 4447.7, "total_tokens": 23314784} {"current_steps": 10790, "total_steps": 61300, "loss": 0.4098, "lr": 4.9125337709926235e-05, "epoch": 1.7601957585644372, "percentage": 17.6, "elapsed_time": "1:27:24", "remaining_time": "6:49:09", "throughput": 4447.85, "total_tokens": 23325696} {"current_steps": 10795, "total_steps": 61300, "loss": 0.4061, "lr": 4.9123470395937e-05, "epoch": 1.7610114192495923, "percentage": 17.61, "elapsed_time": "1:27:26", "remaining_time": "6:49:06", "throughput": 4447.99, "total_tokens": 23337120} {"current_steps": 10800, "total_steps": 61300, "loss": 0.3243, "lr": 4.9121601126376845e-05, "epoch": 1.761827079934747, "percentage": 17.62, "elapsed_time": "1:27:28", "remaining_time": "6:49:03", "throughput": 4448.15, "total_tokens": 23347584} {"current_steps": 10805, "total_steps": 61300, "loss": 0.3394, "lr": 4.9119729901397313e-05, "epoch": 1.7626427406199021, "percentage": 17.63, "elapsed_time": "1:27:30", "remaining_time": "6:48:58", "throughput": 4448.31, "total_tokens": 23357504} {"current_steps": 10810, "total_steps": 61300, "loss": 0.3923, "lr": 4.9117856721150095e-05, "epoch": 1.7634584013050572, "percentage": 17.63, "elapsed_time": "1:27:32", "remaining_time": "6:48:54", "throughput": 4448.45, "total_tokens": 23367456} {"current_steps": 10815, "total_steps": 61300, "loss": 0.3391, "lr": 4.911598158578704e-05, "epoch": 1.764274061990212, "percentage": 17.64, "elapsed_time": "1:27:35", "remaining_time": "6:48:51", "throughput": 4448.6, "total_tokens": 23377984} {"current_steps": 10820, "total_steps": 61300, "loss": 0.3289, "lr": 4.9114104495460154e-05, "epoch": 1.765089722675367, "percentage": 17.65, "elapsed_time": "1:27:37", "remaining_time": "6:48:49", "throughput": 4448.74, "total_tokens": 23390272} {"current_steps": 10825, "total_steps": 61300, "loss": 0.3385, "lr": 4.9112225450321606e-05, "epoch": 1.765905383360522, "percentage": 17.66, "elapsed_time": "1:27:39", "remaining_time": "6:48:45", "throughput": 4448.84, "total_tokens": 23400416} {"current_steps": 10830, "total_steps": 61300, "loss": 0.3716, "lr": 4.911034445052371e-05, "epoch": 1.7667210440456769, "percentage": 17.67, "elapsed_time": "1:27:42", "remaining_time": "6:48:44", "throughput": 4449.01, "total_tokens": 23412704} {"current_steps": 10835, "total_steps": 61300, "loss": 0.3325, "lr": 4.910846149621896e-05, "epoch": 1.7675367047308321, "percentage": 17.68, "elapsed_time": "1:27:44", "remaining_time": "6:48:39", "throughput": 4449.13, "total_tokens": 23421952} {"current_steps": 10840, "total_steps": 61300, "loss": 0.3722, "lr": 4.9106576587560006e-05, "epoch": 1.768352365415987, "percentage": 17.68, "elapsed_time": "1:27:46", "remaining_time": "6:48:34", "throughput": 4449.24, "total_tokens": 23431136} {"current_steps": 10845, "total_steps": 61300, "loss": 0.3268, "lr": 4.9104689724699625e-05, "epoch": 1.7691680261011418, "percentage": 17.69, "elapsed_time": "1:27:48", "remaining_time": "6:48:32", "throughput": 4449.37, "total_tokens": 23442880} {"current_steps": 10850, "total_steps": 61300, "loss": 0.357, "lr": 4.91028009077908e-05, "epoch": 1.769983686786297, "percentage": 17.7, "elapsed_time": "1:27:50", "remaining_time": "6:48:28", "throughput": 4449.55, "total_tokens": 23453120} {"current_steps": 10855, "total_steps": 61300, "loss": 0.3623, "lr": 4.910091013698663e-05, "epoch": 1.7707993474714518, "percentage": 17.71, "elapsed_time": "1:27:53", "remaining_time": "6:48:25", "throughput": 4449.7, "total_tokens": 23464192} {"current_steps": 10860, "total_steps": 61300, "loss": 0.3214, "lr": 4.90990174124404e-05, "epoch": 1.7716150081566069, "percentage": 17.72, "elapsed_time": "1:27:55", "remaining_time": "6:48:22", "throughput": 4449.87, "total_tokens": 23475264} {"current_steps": 10865, "total_steps": 61300, "loss": 0.3607, "lr": 4.909712273430554e-05, "epoch": 1.772430668841762, "percentage": 17.72, "elapsed_time": "1:27:57", "remaining_time": "6:48:18", "throughput": 4450.04, "total_tokens": 23485440} {"current_steps": 10870, "total_steps": 61300, "loss": 0.2929, "lr": 4.9095226102735645e-05, "epoch": 1.7732463295269167, "percentage": 17.73, "elapsed_time": "1:27:59", "remaining_time": "6:48:15", "throughput": 4450.22, "total_tokens": 23496768} {"current_steps": 10875, "total_steps": 61300, "loss": 0.3561, "lr": 4.909332751788447e-05, "epoch": 1.7740619902120718, "percentage": 17.74, "elapsed_time": "1:28:02", "remaining_time": "6:48:12", "throughput": 4450.36, "total_tokens": 23507328} {"current_steps": 10880, "total_steps": 61300, "loss": 0.3377, "lr": 4.909142697990591e-05, "epoch": 1.7748776508972268, "percentage": 17.75, "elapsed_time": "1:28:04", "remaining_time": "6:48:09", "throughput": 4450.46, "total_tokens": 23518976} {"current_steps": 10885, "total_steps": 61300, "loss": 0.3642, "lr": 4.908952448895404e-05, "epoch": 1.7756933115823816, "percentage": 17.76, "elapsed_time": "1:28:07", "remaining_time": "6:48:07", "throughput": 4450.66, "total_tokens": 23530720} {"current_steps": 10890, "total_steps": 61300, "loss": 0.3805, "lr": 4.908762004518309e-05, "epoch": 1.7765089722675367, "percentage": 17.77, "elapsed_time": "1:28:09", "remaining_time": "6:48:03", "throughput": 4450.8, "total_tokens": 23541312} {"current_steps": 10895, "total_steps": 61300, "loss": 0.3276, "lr": 4.908571364874743e-05, "epoch": 1.7773246329526917, "percentage": 17.77, "elapsed_time": "1:28:11", "remaining_time": "6:48:00", "throughput": 4450.97, "total_tokens": 23552064} {"current_steps": 10900, "total_steps": 61300, "loss": 0.345, "lr": 4.9083805299801626e-05, "epoch": 1.7781402936378465, "percentage": 17.78, "elapsed_time": "1:28:13", "remaining_time": "6:47:57", "throughput": 4451.16, "total_tokens": 23563104} {"current_steps": 10905, "total_steps": 61300, "loss": 0.3531, "lr": 4.908189499850036e-05, "epoch": 1.7789559543230016, "percentage": 17.79, "elapsed_time": "1:28:15", "remaining_time": "6:47:53", "throughput": 4451.31, "total_tokens": 23572992} {"current_steps": 10910, "total_steps": 61300, "loss": 0.3574, "lr": 4.907998274499849e-05, "epoch": 1.7797716150081566, "percentage": 17.8, "elapsed_time": "1:28:17", "remaining_time": "6:47:49", "throughput": 4451.45, "total_tokens": 23583328} {"current_steps": 10915, "total_steps": 61300, "loss": 0.3868, "lr": 4.9078068539451045e-05, "epoch": 1.7805872756933114, "percentage": 17.81, "elapsed_time": "1:28:20", "remaining_time": "6:47:45", "throughput": 4451.59, "total_tokens": 23593888} {"current_steps": 10920, "total_steps": 61300, "loss": 0.3229, "lr": 4.907615238201319e-05, "epoch": 1.7814029363784667, "percentage": 17.81, "elapsed_time": "1:28:22", "remaining_time": "6:47:42", "throughput": 4451.76, "total_tokens": 23604544} {"current_steps": 10925, "total_steps": 61300, "loss": 0.3284, "lr": 4.907423427284026e-05, "epoch": 1.7822185970636215, "percentage": 17.82, "elapsed_time": "1:28:24", "remaining_time": "6:47:39", "throughput": 4451.93, "total_tokens": 23615584} {"current_steps": 10930, "total_steps": 61300, "loss": 0.3455, "lr": 4.907231421208775e-05, "epoch": 1.7830342577487766, "percentage": 17.83, "elapsed_time": "1:28:26", "remaining_time": "6:47:35", "throughput": 4452.05, "total_tokens": 23625568} {"current_steps": 10935, "total_steps": 61300, "loss": 0.358, "lr": 4.907039219991131e-05, "epoch": 1.7838499184339316, "percentage": 17.84, "elapsed_time": "1:28:28", "remaining_time": "6:47:31", "throughput": 4452.21, "total_tokens": 23636320} {"current_steps": 10940, "total_steps": 61300, "loss": 0.3575, "lr": 4.906846823646675e-05, "epoch": 1.7846655791190864, "percentage": 17.85, "elapsed_time": "1:28:31", "remaining_time": "6:47:28", "throughput": 4452.35, "total_tokens": 23646912} {"current_steps": 10945, "total_steps": 61300, "loss": 0.3234, "lr": 4.906654232191002e-05, "epoch": 1.7854812398042414, "percentage": 17.85, "elapsed_time": "1:28:33", "remaining_time": "6:47:24", "throughput": 4452.49, "total_tokens": 23657120} {"current_steps": 10950, "total_steps": 61300, "loss": 0.3896, "lr": 4.906461445639726e-05, "epoch": 1.7862969004893965, "percentage": 17.86, "elapsed_time": "1:28:35", "remaining_time": "6:47:21", "throughput": 4452.63, "total_tokens": 23667712} {"current_steps": 10955, "total_steps": 61300, "loss": 0.3702, "lr": 4.906268464008476e-05, "epoch": 1.7871125611745513, "percentage": 17.87, "elapsed_time": "1:28:37", "remaining_time": "6:47:18", "throughput": 4452.77, "total_tokens": 23678720} {"current_steps": 10960, "total_steps": 61300, "loss": 0.3442, "lr": 4.9060752873128946e-05, "epoch": 1.7879282218597063, "percentage": 17.88, "elapsed_time": "1:28:39", "remaining_time": "6:47:13", "throughput": 4452.9, "total_tokens": 23688160} {"current_steps": 10965, "total_steps": 61300, "loss": 0.361, "lr": 4.905881915568642e-05, "epoch": 1.7887438825448614, "percentage": 17.89, "elapsed_time": "1:28:42", "remaining_time": "6:47:11", "throughput": 4453.05, "total_tokens": 23699680} {"current_steps": 10970, "total_steps": 61300, "loss": 0.3801, "lr": 4.905688348791394e-05, "epoch": 1.7895595432300162, "percentage": 17.9, "elapsed_time": "1:28:44", "remaining_time": "6:47:08", "throughput": 4453.2, "total_tokens": 23710880} {"current_steps": 10975, "total_steps": 61300, "loss": 0.3279, "lr": 4.905494586996842e-05, "epoch": 1.7903752039151712, "percentage": 17.9, "elapsed_time": "1:28:46", "remaining_time": "6:47:05", "throughput": 4453.35, "total_tokens": 23722304} {"current_steps": 10980, "total_steps": 61300, "loss": 0.381, "lr": 4.905300630200693e-05, "epoch": 1.7911908646003263, "percentage": 17.91, "elapsed_time": "1:28:49", "remaining_time": "6:47:03", "throughput": 4453.48, "total_tokens": 23734048} {"current_steps": 10985, "total_steps": 61300, "loss": 0.3276, "lr": 4.9051064784186704e-05, "epoch": 1.792006525285481, "percentage": 17.92, "elapsed_time": "1:28:51", "remaining_time": "6:47:00", "throughput": 4453.68, "total_tokens": 23745600} {"current_steps": 10990, "total_steps": 61300, "loss": 0.3316, "lr": 4.9049121316665146e-05, "epoch": 1.7928221859706364, "percentage": 17.93, "elapsed_time": "1:28:53", "remaining_time": "6:46:57", "throughput": 4453.85, "total_tokens": 23756800} {"current_steps": 10995, "total_steps": 61300, "loss": 0.3569, "lr": 4.904717589959978e-05, "epoch": 1.7936378466557912, "percentage": 17.94, "elapsed_time": "1:28:56", "remaining_time": "6:46:54", "throughput": 4453.99, "total_tokens": 23766880} {"current_steps": 11000, "total_steps": 61300, "loss": 0.3393, "lr": 4.904522853314833e-05, "epoch": 1.7944535073409462, "percentage": 17.94, "elapsed_time": "1:28:58", "remaining_time": "6:46:50", "throughput": 4454.13, "total_tokens": 23777472} {"current_steps": 11005, "total_steps": 61300, "loss": 0.3473, "lr": 4.904327921746864e-05, "epoch": 1.7952691680261013, "percentage": 17.95, "elapsed_time": "1:29:00", "remaining_time": "6:46:45", "throughput": 4454.22, "total_tokens": 23786336} {"current_steps": 11010, "total_steps": 61300, "loss": 0.3707, "lr": 4.904132795271875e-05, "epoch": 1.796084828711256, "percentage": 17.96, "elapsed_time": "1:29:02", "remaining_time": "6:46:42", "throughput": 4454.32, "total_tokens": 23797184} {"current_steps": 11015, "total_steps": 61300, "loss": 0.3698, "lr": 4.9039374739056825e-05, "epoch": 1.7969004893964111, "percentage": 17.97, "elapsed_time": "1:29:04", "remaining_time": "6:46:39", "throughput": 4454.51, "total_tokens": 23808288} {"current_steps": 11020, "total_steps": 61300, "loss": 0.3706, "lr": 4.903741957664121e-05, "epoch": 1.7977161500815662, "percentage": 17.98, "elapsed_time": "1:29:06", "remaining_time": "6:46:35", "throughput": 4454.65, "total_tokens": 23818176} {"current_steps": 11025, "total_steps": 61300, "loss": 0.3466, "lr": 4.903546246563041e-05, "epoch": 1.798531810766721, "percentage": 17.99, "elapsed_time": "1:29:09", "remaining_time": "6:46:32", "throughput": 4454.82, "total_tokens": 23829344} {"current_steps": 11030, "total_steps": 61300, "loss": 0.369, "lr": 4.9033503406183055e-05, "epoch": 1.799347471451876, "percentage": 17.99, "elapsed_time": "1:29:11", "remaining_time": "6:46:28", "throughput": 4454.99, "total_tokens": 23839936} {"current_steps": 11035, "total_steps": 61300, "loss": 0.3434, "lr": 4.9031542398457974e-05, "epoch": 1.800163132137031, "percentage": 18.0, "elapsed_time": "1:29:13", "remaining_time": "6:46:27", "throughput": 4455.15, "total_tokens": 23852736} {"current_steps": 11040, "total_steps": 61300, "loss": 0.3731, "lr": 4.902957944261413e-05, "epoch": 1.8009787928221859, "percentage": 18.01, "elapsed_time": "1:29:16", "remaining_time": "6:46:25", "throughput": 4455.36, "total_tokens": 23864736} {"current_steps": 11045, "total_steps": 61300, "loss": 0.3227, "lr": 4.902761453881065e-05, "epoch": 1.801794453507341, "percentage": 18.02, "elapsed_time": "1:29:18", "remaining_time": "6:46:21", "throughput": 4455.48, "total_tokens": 23874432} {"current_steps": 11050, "total_steps": 61300, "loss": 0.3696, "lr": 4.9025647687206824e-05, "epoch": 1.802610114192496, "percentage": 18.03, "elapsed_time": "1:29:20", "remaining_time": "6:46:17", "throughput": 4455.61, "total_tokens": 23885056} {"current_steps": 11055, "total_steps": 61300, "loss": 0.3473, "lr": 4.90236788879621e-05, "epoch": 1.8034257748776508, "percentage": 18.03, "elapsed_time": "1:29:22", "remaining_time": "6:46:14", "throughput": 4455.76, "total_tokens": 23896096} {"current_steps": 11060, "total_steps": 61300, "loss": 0.3499, "lr": 4.9021708141236056e-05, "epoch": 1.804241435562806, "percentage": 18.04, "elapsed_time": "1:29:25", "remaining_time": "6:46:11", "throughput": 4455.9, "total_tokens": 23907200} {"current_steps": 11065, "total_steps": 61300, "loss": 0.339, "lr": 4.901973544718847e-05, "epoch": 1.8050570962479608, "percentage": 18.05, "elapsed_time": "1:29:27", "remaining_time": "6:46:07", "throughput": 4456.02, "total_tokens": 23916576} {"current_steps": 11070, "total_steps": 61300, "loss": 0.3328, "lr": 4.901776080597926e-05, "epoch": 1.8058727569331157, "percentage": 18.06, "elapsed_time": "1:29:29", "remaining_time": "6:46:03", "throughput": 4456.15, "total_tokens": 23926784} {"current_steps": 11075, "total_steps": 61300, "loss": 0.3743, "lr": 4.9015784217768487e-05, "epoch": 1.806688417618271, "percentage": 18.07, "elapsed_time": "1:29:31", "remaining_time": "6:46:00", "throughput": 4456.28, "total_tokens": 23937632} {"current_steps": 11080, "total_steps": 61300, "loss": 0.3573, "lr": 4.901380568271639e-05, "epoch": 1.8075040783034257, "percentage": 18.08, "elapsed_time": "1:29:34", "remaining_time": "6:45:57", "throughput": 4456.43, "total_tokens": 23949024} {"current_steps": 11085, "total_steps": 61300, "loss": 0.33, "lr": 4.901182520098336e-05, "epoch": 1.8083197389885808, "percentage": 18.08, "elapsed_time": "1:29:36", "remaining_time": "6:45:54", "throughput": 4456.58, "total_tokens": 23960192} {"current_steps": 11090, "total_steps": 61300, "loss": 0.347, "lr": 4.9009842772729944e-05, "epoch": 1.8091353996737358, "percentage": 18.09, "elapsed_time": "1:29:38", "remaining_time": "6:45:51", "throughput": 4456.69, "total_tokens": 23970304} {"current_steps": 11095, "total_steps": 61300, "loss": 0.3797, "lr": 4.9007858398116856e-05, "epoch": 1.8099510603588906, "percentage": 18.1, "elapsed_time": "1:29:40", "remaining_time": "6:45:47", "throughput": 4456.84, "total_tokens": 23980544} {"current_steps": 11100, "total_steps": 61300, "loss": 0.3329, "lr": 4.9005872077304944e-05, "epoch": 1.8107667210440457, "percentage": 18.11, "elapsed_time": "1:29:42", "remaining_time": "6:45:44", "throughput": 4457.01, "total_tokens": 23991680} {"current_steps": 11105, "total_steps": 61300, "loss": 0.3184, "lr": 4.900388381045524e-05, "epoch": 1.8115823817292007, "percentage": 18.12, "elapsed_time": "1:29:44", "remaining_time": "6:45:39", "throughput": 4457.13, "total_tokens": 24000672} {"current_steps": 11110, "total_steps": 61300, "loss": 0.3755, "lr": 4.9001893597728915e-05, "epoch": 1.8123980424143555, "percentage": 18.12, "elapsed_time": "1:29:46", "remaining_time": "6:45:35", "throughput": 4457.26, "total_tokens": 24010496} {"current_steps": 11115, "total_steps": 61300, "loss": 0.3066, "lr": 4.899990143928731e-05, "epoch": 1.8132137030995106, "percentage": 18.13, "elapsed_time": "1:29:49", "remaining_time": "6:45:31", "throughput": 4457.41, "total_tokens": 24021056} {"current_steps": 11120, "total_steps": 61300, "loss": 0.3521, "lr": 4.899790733529193e-05, "epoch": 1.8140293637846656, "percentage": 18.14, "elapsed_time": "1:29:51", "remaining_time": "6:45:27", "throughput": 4457.54, "total_tokens": 24031136} {"current_steps": 11125, "total_steps": 61300, "loss": 0.3562, "lr": 4.8995911285904404e-05, "epoch": 1.8148450244698204, "percentage": 18.15, "elapsed_time": "1:29:53", "remaining_time": "6:45:23", "throughput": 4457.67, "total_tokens": 24040864} {"current_steps": 11130, "total_steps": 61300, "loss": 0.4033, "lr": 4.899391329128656e-05, "epoch": 1.8156606851549757, "percentage": 18.16, "elapsed_time": "1:29:55", "remaining_time": "6:45:19", "throughput": 4457.82, "total_tokens": 24051168} {"current_steps": 11135, "total_steps": 61300, "loss": 0.361, "lr": 4.899191335160037e-05, "epoch": 1.8164763458401305, "percentage": 18.16, "elapsed_time": "1:29:57", "remaining_time": "6:45:15", "throughput": 4457.92, "total_tokens": 24060448} {"current_steps": 11140, "total_steps": 61300, "loss": 0.3654, "lr": 4.898991146700794e-05, "epoch": 1.8172920065252853, "percentage": 18.17, "elapsed_time": "1:29:59", "remaining_time": "6:45:11", "throughput": 4458.05, "total_tokens": 24070208} {"current_steps": 11145, "total_steps": 61300, "loss": 0.3233, "lr": 4.898790763767157e-05, "epoch": 1.8181076672104406, "percentage": 18.18, "elapsed_time": "1:30:01", "remaining_time": "6:45:07", "throughput": 4458.16, "total_tokens": 24080000} {"current_steps": 11150, "total_steps": 61300, "loss": 0.3261, "lr": 4.8985901863753694e-05, "epoch": 1.8189233278955954, "percentage": 18.19, "elapsed_time": "1:30:03", "remaining_time": "6:45:02", "throughput": 4458.24, "total_tokens": 24089120} {"current_steps": 11155, "total_steps": 61300, "loss": 0.3063, "lr": 4.8983894145416896e-05, "epoch": 1.8197389885807504, "percentage": 18.2, "elapsed_time": "1:30:05", "remaining_time": "6:44:59", "throughput": 4458.38, "total_tokens": 24099968} {"current_steps": 11160, "total_steps": 61300, "loss": 0.3577, "lr": 4.898188448282396e-05, "epoch": 1.8205546492659055, "percentage": 18.21, "elapsed_time": "1:30:07", "remaining_time": "6:44:56", "throughput": 4458.51, "total_tokens": 24110560} {"current_steps": 11165, "total_steps": 61300, "loss": 0.3345, "lr": 4.897987287613778e-05, "epoch": 1.8213703099510603, "percentage": 18.21, "elapsed_time": "1:30:10", "remaining_time": "6:44:53", "throughput": 4458.69, "total_tokens": 24121984} {"current_steps": 11170, "total_steps": 61300, "loss": 0.3435, "lr": 4.897785932552143e-05, "epoch": 1.8221859706362153, "percentage": 18.22, "elapsed_time": "1:30:12", "remaining_time": "6:44:49", "throughput": 4458.85, "total_tokens": 24132544} {"current_steps": 11175, "total_steps": 61300, "loss": 0.3353, "lr": 4.897584383113814e-05, "epoch": 1.8230016313213704, "percentage": 18.23, "elapsed_time": "1:30:14", "remaining_time": "6:44:47", "throughput": 4459.0, "total_tokens": 24143808} {"current_steps": 11180, "total_steps": 61300, "loss": 0.374, "lr": 4.89738263931513e-05, "epoch": 1.8238172920065252, "percentage": 18.24, "elapsed_time": "1:30:16", "remaining_time": "6:44:43", "throughput": 4459.16, "total_tokens": 24154496} {"current_steps": 11185, "total_steps": 61300, "loss": 0.3701, "lr": 4.8971807011724444e-05, "epoch": 1.8246329526916802, "percentage": 18.25, "elapsed_time": "1:30:19", "remaining_time": "6:44:40", "throughput": 4459.31, "total_tokens": 24165472} {"current_steps": 11190, "total_steps": 61300, "loss": 0.3188, "lr": 4.8969785687021294e-05, "epoch": 1.8254486133768353, "percentage": 18.25, "elapsed_time": "1:30:21", "remaining_time": "6:44:38", "throughput": 4459.49, "total_tokens": 24177088} {"current_steps": 11195, "total_steps": 61300, "loss": 0.3221, "lr": 4.8967762419205684e-05, "epoch": 1.82626427406199, "percentage": 18.26, "elapsed_time": "1:30:23", "remaining_time": "6:44:35", "throughput": 4459.68, "total_tokens": 24188768} {"current_steps": 11200, "total_steps": 61300, "loss": 0.3825, "lr": 4.896573720844164e-05, "epoch": 1.8270799347471451, "percentage": 18.27, "elapsed_time": "1:30:26", "remaining_time": "6:44:32", "throughput": 4459.8, "total_tokens": 24199712} {"current_steps": 11205, "total_steps": 61300, "loss": 0.3732, "lr": 4.896371005489334e-05, "epoch": 1.8278955954323002, "percentage": 18.28, "elapsed_time": "1:30:28", "remaining_time": "6:44:29", "throughput": 4459.96, "total_tokens": 24210912} {"current_steps": 11210, "total_steps": 61300, "loss": 0.3418, "lr": 4.896168095872511e-05, "epoch": 1.828711256117455, "percentage": 18.29, "elapsed_time": "1:30:30", "remaining_time": "6:44:26", "throughput": 4460.09, "total_tokens": 24221824} {"current_steps": 11215, "total_steps": 61300, "loss": 0.3456, "lr": 4.895964992010145e-05, "epoch": 1.8295269168026103, "percentage": 18.3, "elapsed_time": "1:30:32", "remaining_time": "6:44:22", "throughput": 4460.21, "total_tokens": 24231168} {"current_steps": 11220, "total_steps": 61300, "loss": 0.3586, "lr": 4.895761693918699e-05, "epoch": 1.830342577487765, "percentage": 18.3, "elapsed_time": "1:30:34", "remaining_time": "6:44:18", "throughput": 4460.36, "total_tokens": 24241408} {"current_steps": 11225, "total_steps": 61300, "loss": 0.345, "lr": 4.895558201614654e-05, "epoch": 1.8311582381729201, "percentage": 18.31, "elapsed_time": "1:30:36", "remaining_time": "6:44:14", "throughput": 4460.47, "total_tokens": 24251520} {"current_steps": 11230, "total_steps": 61300, "loss": 0.3549, "lr": 4.895354515114506e-05, "epoch": 1.8319738988580752, "percentage": 18.32, "elapsed_time": "1:30:39", "remaining_time": "6:44:10", "throughput": 4460.64, "total_tokens": 24262144} {"current_steps": 11235, "total_steps": 61300, "loss": 0.3795, "lr": 4.895150634434769e-05, "epoch": 1.83278955954323, "percentage": 18.33, "elapsed_time": "1:30:41", "remaining_time": "6:44:08", "throughput": 4460.77, "total_tokens": 24273440} {"current_steps": 11240, "total_steps": 61300, "loss": 0.3451, "lr": 4.894946559591966e-05, "epoch": 1.833605220228385, "percentage": 18.34, "elapsed_time": "1:30:43", "remaining_time": "6:44:05", "throughput": 4460.93, "total_tokens": 24284832} {"current_steps": 11245, "total_steps": 61300, "loss": 0.3313, "lr": 4.8947422906026446e-05, "epoch": 1.83442088091354, "percentage": 18.34, "elapsed_time": "1:30:46", "remaining_time": "6:44:02", "throughput": 4461.07, "total_tokens": 24295488} {"current_steps": 11250, "total_steps": 61300, "loss": 0.3337, "lr": 4.894537827483362e-05, "epoch": 1.8352365415986949, "percentage": 18.35, "elapsed_time": "1:30:48", "remaining_time": "6:43:59", "throughput": 4461.19, "total_tokens": 24306624} {"current_steps": 11255, "total_steps": 61300, "loss": 0.3759, "lr": 4.8943331702506935e-05, "epoch": 1.83605220228385, "percentage": 18.36, "elapsed_time": "1:30:50", "remaining_time": "6:43:57", "throughput": 4461.36, "total_tokens": 24318176} {"current_steps": 11260, "total_steps": 61300, "loss": 0.356, "lr": 4.894128318921229e-05, "epoch": 1.836867862969005, "percentage": 18.37, "elapsed_time": "1:30:53", "remaining_time": "6:43:53", "throughput": 4461.48, "total_tokens": 24329024} {"current_steps": 11265, "total_steps": 61300, "loss": 0.3494, "lr": 4.893923273511576e-05, "epoch": 1.8376835236541598, "percentage": 18.38, "elapsed_time": "1:30:55", "remaining_time": "6:43:50", "throughput": 4461.64, "total_tokens": 24339680} {"current_steps": 11270, "total_steps": 61300, "loss": 0.3626, "lr": 4.893718034038355e-05, "epoch": 1.8384991843393148, "percentage": 18.38, "elapsed_time": "1:30:57", "remaining_time": "6:43:47", "throughput": 4461.78, "total_tokens": 24350368} {"current_steps": 11275, "total_steps": 61300, "loss": 0.3657, "lr": 4.8935126005182056e-05, "epoch": 1.8393148450244698, "percentage": 18.39, "elapsed_time": "1:30:59", "remaining_time": "6:43:44", "throughput": 4461.96, "total_tokens": 24361536} {"current_steps": 11280, "total_steps": 61300, "loss": 0.3549, "lr": 4.8933069729677795e-05, "epoch": 1.8401305057096247, "percentage": 18.4, "elapsed_time": "1:31:02", "remaining_time": "6:43:41", "throughput": 4462.15, "total_tokens": 24372768} {"current_steps": 11285, "total_steps": 61300, "loss": 0.3456, "lr": 4.893101151403747e-05, "epoch": 1.84094616639478, "percentage": 18.41, "elapsed_time": "1:31:04", "remaining_time": "6:43:37", "throughput": 4462.27, "total_tokens": 24382592} {"current_steps": 11290, "total_steps": 61300, "loss": 0.3414, "lr": 4.892895135842792e-05, "epoch": 1.8417618270799347, "percentage": 18.42, "elapsed_time": "1:31:06", "remaining_time": "6:43:33", "throughput": 4462.43, "total_tokens": 24393248} {"current_steps": 11295, "total_steps": 61300, "loss": 0.3537, "lr": 4.892688926301616e-05, "epoch": 1.8425774877650896, "percentage": 18.43, "elapsed_time": "1:31:08", "remaining_time": "6:43:29", "throughput": 4462.55, "total_tokens": 24403232} {"current_steps": 11300, "total_steps": 61300, "loss": 0.3442, "lr": 4.892482522796936e-05, "epoch": 1.8433931484502448, "percentage": 18.43, "elapsed_time": "1:31:10", "remaining_time": "6:43:26", "throughput": 4462.7, "total_tokens": 24413792} {"current_steps": 11305, "total_steps": 61300, "loss": 0.3614, "lr": 4.892275925345483e-05, "epoch": 1.8442088091353996, "percentage": 18.44, "elapsed_time": "1:31:12", "remaining_time": "6:43:22", "throughput": 4462.81, "total_tokens": 24423328} {"current_steps": 11310, "total_steps": 61300, "loss": 0.3347, "lr": 4.8920691339640055e-05, "epoch": 1.8450244698205547, "percentage": 18.45, "elapsed_time": "1:31:14", "remaining_time": "6:43:18", "throughput": 4462.99, "total_tokens": 24434464} {"current_steps": 11315, "total_steps": 61300, "loss": 0.3404, "lr": 4.8918621486692663e-05, "epoch": 1.8458401305057097, "percentage": 18.46, "elapsed_time": "1:31:16", "remaining_time": "6:43:14", "throughput": 4463.11, "total_tokens": 24444224} {"current_steps": 11320, "total_steps": 61300, "loss": 0.3502, "lr": 4.8916549694780455e-05, "epoch": 1.8466557911908645, "percentage": 18.47, "elapsed_time": "1:31:19", "remaining_time": "6:43:11", "throughput": 4463.24, "total_tokens": 24454912} {"current_steps": 11325, "total_steps": 61300, "loss": 0.3405, "lr": 4.891447596407137e-05, "epoch": 1.8474714518760196, "percentage": 18.47, "elapsed_time": "1:31:21", "remaining_time": "6:43:08", "throughput": 4463.41, "total_tokens": 24466304} {"current_steps": 11330, "total_steps": 61300, "loss": 0.3244, "lr": 4.8912400294733526e-05, "epoch": 1.8482871125611746, "percentage": 18.48, "elapsed_time": "1:31:23", "remaining_time": "6:43:05", "throughput": 4463.54, "total_tokens": 24476960} {"current_steps": 11335, "total_steps": 61300, "loss": 0.333, "lr": 4.891032268693519e-05, "epoch": 1.8491027732463294, "percentage": 18.49, "elapsed_time": "1:31:25", "remaining_time": "6:43:01", "throughput": 4463.64, "total_tokens": 24486784} {"current_steps": 11340, "total_steps": 61300, "loss": 0.3716, "lr": 4.8908243140844765e-05, "epoch": 1.8499184339314845, "percentage": 18.5, "elapsed_time": "1:31:27", "remaining_time": "6:42:58", "throughput": 4463.77, "total_tokens": 24497120} {"current_steps": 11345, "total_steps": 61300, "loss": 0.3656, "lr": 4.890616165663085e-05, "epoch": 1.8507340946166395, "percentage": 18.51, "elapsed_time": "1:31:30", "remaining_time": "6:42:54", "throughput": 4463.92, "total_tokens": 24507200} {"current_steps": 11350, "total_steps": 61300, "loss": 0.3557, "lr": 4.890407823446218e-05, "epoch": 1.8515497553017943, "percentage": 18.52, "elapsed_time": "1:31:32", "remaining_time": "6:42:50", "throughput": 4464.06, "total_tokens": 24517920} {"current_steps": 11355, "total_steps": 61300, "loss": 0.3187, "lr": 4.890199287450763e-05, "epoch": 1.8523654159869496, "percentage": 18.52, "elapsed_time": "1:31:34", "remaining_time": "6:42:47", "throughput": 4464.19, "total_tokens": 24528640} {"current_steps": 11360, "total_steps": 61300, "loss": 0.3559, "lr": 4.889990557693626e-05, "epoch": 1.8531810766721044, "percentage": 18.53, "elapsed_time": "1:31:36", "remaining_time": "6:42:45", "throughput": 4464.35, "total_tokens": 24540352} {"current_steps": 11365, "total_steps": 61300, "loss": 0.3076, "lr": 4.889781634191728e-05, "epoch": 1.8539967373572592, "percentage": 18.54, "elapsed_time": "1:31:39", "remaining_time": "6:42:42", "throughput": 4464.52, "total_tokens": 24551584} {"current_steps": 11370, "total_steps": 61300, "loss": 0.3481, "lr": 4.889572516962006e-05, "epoch": 1.8548123980424145, "percentage": 18.55, "elapsed_time": "1:31:41", "remaining_time": "6:42:39", "throughput": 4464.66, "total_tokens": 24562400} {"current_steps": 11375, "total_steps": 61300, "loss": 0.3565, "lr": 4.889363206021409e-05, "epoch": 1.8556280587275693, "percentage": 18.56, "elapsed_time": "1:31:43", "remaining_time": "6:42:35", "throughput": 4464.77, "total_tokens": 24572736} {"current_steps": 11380, "total_steps": 61300, "loss": 0.352, "lr": 4.889153701386908e-05, "epoch": 1.8564437194127243, "percentage": 18.56, "elapsed_time": "1:31:46", "remaining_time": "6:42:33", "throughput": 4464.95, "total_tokens": 24584416} {"current_steps": 11385, "total_steps": 61300, "loss": 0.3531, "lr": 4.888944003075486e-05, "epoch": 1.8572593800978794, "percentage": 18.57, "elapsed_time": "1:31:47", "remaining_time": "6:42:28", "throughput": 4465.05, "total_tokens": 24593472} {"current_steps": 11390, "total_steps": 61300, "loss": 0.3398, "lr": 4.888734111104142e-05, "epoch": 1.8580750407830342, "percentage": 18.58, "elapsed_time": "1:31:50", "remaining_time": "6:42:25", "throughput": 4465.2, "total_tokens": 24604544} {"current_steps": 11395, "total_steps": 61300, "loss": 0.3678, "lr": 4.88852402548989e-05, "epoch": 1.8588907014681892, "percentage": 18.59, "elapsed_time": "1:31:52", "remaining_time": "6:42:22", "throughput": 4465.31, "total_tokens": 24614784} {"current_steps": 11400, "total_steps": 61300, "loss": 0.3735, "lr": 4.8883137462497615e-05, "epoch": 1.8597063621533443, "percentage": 18.6, "elapsed_time": "1:31:54", "remaining_time": "6:42:18", "throughput": 4465.45, "total_tokens": 24625504} {"current_steps": 11405, "total_steps": 61300, "loss": 0.3362, "lr": 4.8881032734008024e-05, "epoch": 1.860522022838499, "percentage": 18.61, "elapsed_time": "1:31:56", "remaining_time": "6:42:15", "throughput": 4465.57, "total_tokens": 24636192} {"current_steps": 11410, "total_steps": 61300, "loss": 0.3783, "lr": 4.887892606960075e-05, "epoch": 1.8613376835236541, "percentage": 18.61, "elapsed_time": "1:31:59", "remaining_time": "6:42:12", "throughput": 4465.74, "total_tokens": 24647200} {"current_steps": 11415, "total_steps": 61300, "loss": 0.3407, "lr": 4.887681746944657e-05, "epoch": 1.8621533442088092, "percentage": 18.62, "elapsed_time": "1:32:01", "remaining_time": "6:42:08", "throughput": 4465.85, "total_tokens": 24656640} {"current_steps": 11420, "total_steps": 61300, "loss": 0.356, "lr": 4.8874706933716406e-05, "epoch": 1.862969004893964, "percentage": 18.63, "elapsed_time": "1:32:03", "remaining_time": "6:42:03", "throughput": 4465.94, "total_tokens": 24665664} {"current_steps": 11425, "total_steps": 61300, "loss": 0.3597, "lr": 4.887259446258137e-05, "epoch": 1.863784665579119, "percentage": 18.64, "elapsed_time": "1:32:05", "remaining_time": "6:42:00", "throughput": 4466.1, "total_tokens": 24676896} {"current_steps": 11430, "total_steps": 61300, "loss": 0.3777, "lr": 4.887048005621269e-05, "epoch": 1.864600326264274, "percentage": 18.65, "elapsed_time": "1:32:07", "remaining_time": "6:41:58", "throughput": 4466.28, "total_tokens": 24688960} {"current_steps": 11435, "total_steps": 61300, "loss": 0.3615, "lr": 4.886836371478178e-05, "epoch": 1.865415986949429, "percentage": 18.65, "elapsed_time": "1:32:10", "remaining_time": "6:41:54", "throughput": 4466.39, "total_tokens": 24699200} {"current_steps": 11440, "total_steps": 61300, "loss": 0.3333, "lr": 4.8866245438460215e-05, "epoch": 1.8662316476345842, "percentage": 18.66, "elapsed_time": "1:32:12", "remaining_time": "6:41:51", "throughput": 4466.54, "total_tokens": 24709600} {"current_steps": 11445, "total_steps": 61300, "loss": 0.3812, "lr": 4.886412522741968e-05, "epoch": 1.867047308319739, "percentage": 18.67, "elapsed_time": "1:32:14", "remaining_time": "6:41:47", "throughput": 4466.67, "total_tokens": 24719968} {"current_steps": 11450, "total_steps": 61300, "loss": 0.3672, "lr": 4.886200308183207e-05, "epoch": 1.867862969004894, "percentage": 18.68, "elapsed_time": "1:32:16", "remaining_time": "6:41:45", "throughput": 4466.84, "total_tokens": 24731520} {"current_steps": 11455, "total_steps": 61300, "loss": 0.3162, "lr": 4.885987900186943e-05, "epoch": 1.868678629690049, "percentage": 18.69, "elapsed_time": "1:32:19", "remaining_time": "6:41:42", "throughput": 4467.01, "total_tokens": 24742880} {"current_steps": 11460, "total_steps": 61300, "loss": 0.3391, "lr": 4.8857752987703924e-05, "epoch": 1.8694942903752039, "percentage": 18.69, "elapsed_time": "1:32:21", "remaining_time": "6:41:39", "throughput": 4467.14, "total_tokens": 24753600} {"current_steps": 11465, "total_steps": 61300, "loss": 0.3594, "lr": 4.8855625039507916e-05, "epoch": 1.870309951060359, "percentage": 18.7, "elapsed_time": "1:32:23", "remaining_time": "6:41:36", "throughput": 4467.27, "total_tokens": 24764608} {"current_steps": 11470, "total_steps": 61300, "loss": 0.3305, "lr": 4.8853495157453886e-05, "epoch": 1.871125611745514, "percentage": 18.71, "elapsed_time": "1:32:25", "remaining_time": "6:41:33", "throughput": 4467.42, "total_tokens": 24775872} {"current_steps": 11475, "total_steps": 61300, "loss": 0.3133, "lr": 4.885136334171452e-05, "epoch": 1.8719412724306688, "percentage": 18.72, "elapsed_time": "1:32:28", "remaining_time": "6:41:29", "throughput": 4467.54, "total_tokens": 24786208} {"current_steps": 11480, "total_steps": 61300, "loss": 0.3198, "lr": 4.8849229592462615e-05, "epoch": 1.8727569331158238, "percentage": 18.73, "elapsed_time": "1:32:29", "remaining_time": "6:41:25", "throughput": 4467.63, "total_tokens": 24795296} {"current_steps": 11485, "total_steps": 61300, "loss": 0.3381, "lr": 4.884709390987115e-05, "epoch": 1.8735725938009788, "percentage": 18.74, "elapsed_time": "1:32:32", "remaining_time": "6:41:21", "throughput": 4467.76, "total_tokens": 24805632} {"current_steps": 11490, "total_steps": 61300, "loss": 0.316, "lr": 4.8844956294113255e-05, "epoch": 1.8743882544861337, "percentage": 18.74, "elapsed_time": "1:32:34", "remaining_time": "6:41:17", "throughput": 4467.89, "total_tokens": 24815552} {"current_steps": 11495, "total_steps": 61300, "loss": 0.3833, "lr": 4.884281674536221e-05, "epoch": 1.8752039151712887, "percentage": 18.75, "elapsed_time": "1:32:36", "remaining_time": "6:41:15", "throughput": 4468.04, "total_tokens": 24827264} {"current_steps": 11500, "total_steps": 61300, "loss": 0.3578, "lr": 4.884067526379147e-05, "epoch": 1.8760195758564437, "percentage": 18.76, "elapsed_time": "1:32:39", "remaining_time": "6:41:13", "throughput": 4468.21, "total_tokens": 24839168} {"current_steps": 11505, "total_steps": 61300, "loss": 0.3556, "lr": 4.8838531849574624e-05, "epoch": 1.8768352365415986, "percentage": 18.77, "elapsed_time": "1:32:41", "remaining_time": "6:41:10", "throughput": 4468.34, "total_tokens": 24850336} {"current_steps": 11510, "total_steps": 61300, "loss": 0.3584, "lr": 4.8836386502885426e-05, "epoch": 1.8776508972267538, "percentage": 18.78, "elapsed_time": "1:32:43", "remaining_time": "6:41:08", "throughput": 4468.48, "total_tokens": 24861984} {"current_steps": 11515, "total_steps": 61300, "loss": 0.332, "lr": 4.88342392238978e-05, "epoch": 1.8784665579119086, "percentage": 18.78, "elapsed_time": "1:32:45", "remaining_time": "6:41:04", "throughput": 4468.63, "total_tokens": 24872160} {"current_steps": 11520, "total_steps": 61300, "loss": 0.3774, "lr": 4.88320900127858e-05, "epoch": 1.8792822185970635, "percentage": 18.79, "elapsed_time": "1:32:48", "remaining_time": "6:41:00", "throughput": 4468.73, "total_tokens": 24882272} {"current_steps": 11525, "total_steps": 61300, "loss": 0.3505, "lr": 4.882993886972367e-05, "epoch": 1.8800978792822187, "percentage": 18.8, "elapsed_time": "1:32:50", "remaining_time": "6:40:56", "throughput": 4468.86, "total_tokens": 24892448} {"current_steps": 11530, "total_steps": 61300, "loss": 0.3571, "lr": 4.882778579488578e-05, "epoch": 1.8809135399673735, "percentage": 18.81, "elapsed_time": "1:32:52", "remaining_time": "6:40:52", "throughput": 4468.97, "total_tokens": 24902016} {"current_steps": 11535, "total_steps": 61300, "loss": 0.3489, "lr": 4.882563078844668e-05, "epoch": 1.8817292006525286, "percentage": 18.82, "elapsed_time": "1:32:54", "remaining_time": "6:40:50", "throughput": 4469.13, "total_tokens": 24913344} {"current_steps": 11540, "total_steps": 61300, "loss": 0.3271, "lr": 4.882347385058105e-05, "epoch": 1.8825448613376836, "percentage": 18.83, "elapsed_time": "1:32:56", "remaining_time": "6:40:46", "throughput": 4469.26, "total_tokens": 24923840} {"current_steps": 11545, "total_steps": 61300, "loss": 0.3522, "lr": 4.882131498146375e-05, "epoch": 1.8833605220228384, "percentage": 18.83, "elapsed_time": "1:32:58", "remaining_time": "6:40:42", "throughput": 4469.41, "total_tokens": 24933568} {"current_steps": 11550, "total_steps": 61300, "loss": 0.3455, "lr": 4.881915418126979e-05, "epoch": 1.8841761827079935, "percentage": 18.84, "elapsed_time": "1:33:00", "remaining_time": "6:40:38", "throughput": 4469.5, "total_tokens": 24943520} {"current_steps": 11555, "total_steps": 61300, "loss": 0.3037, "lr": 4.8816991450174334e-05, "epoch": 1.8849918433931485, "percentage": 18.85, "elapsed_time": "1:33:03", "remaining_time": "6:40:35", "throughput": 4469.66, "total_tokens": 24954976} {"current_steps": 11560, "total_steps": 61300, "loss": 0.3866, "lr": 4.881482678835271e-05, "epoch": 1.8858075040783033, "percentage": 18.86, "elapsed_time": "1:33:05", "remaining_time": "6:40:31", "throughput": 4469.79, "total_tokens": 24964384} {"current_steps": 11565, "total_steps": 61300, "loss": 0.3512, "lr": 4.881266019598039e-05, "epoch": 1.8866231647634584, "percentage": 18.87, "elapsed_time": "1:33:07", "remaining_time": "6:40:28", "throughput": 4469.94, "total_tokens": 24975584} {"current_steps": 11570, "total_steps": 61300, "loss": 0.3681, "lr": 4.8810491673233006e-05, "epoch": 1.8874388254486134, "percentage": 18.87, "elapsed_time": "1:33:09", "remaining_time": "6:40:26", "throughput": 4470.09, "total_tokens": 24987520} {"current_steps": 11575, "total_steps": 61300, "loss": 0.3092, "lr": 4.880832122028635e-05, "epoch": 1.8882544861337682, "percentage": 18.88, "elapsed_time": "1:33:12", "remaining_time": "6:40:24", "throughput": 4470.23, "total_tokens": 24999424} {"current_steps": 11580, "total_steps": 61300, "loss": 0.3789, "lr": 4.880614883731638e-05, "epoch": 1.8890701468189235, "percentage": 18.89, "elapsed_time": "1:33:14", "remaining_time": "6:40:21", "throughput": 4470.41, "total_tokens": 25010624} {"current_steps": 11585, "total_steps": 61300, "loss": 0.337, "lr": 4.88039745244992e-05, "epoch": 1.8898858075040783, "percentage": 18.9, "elapsed_time": "1:33:17", "remaining_time": "6:40:18", "throughput": 4470.54, "total_tokens": 25021696} {"current_steps": 11590, "total_steps": 61300, "loss": 0.3484, "lr": 4.880179828201106e-05, "epoch": 1.8907014681892331, "percentage": 18.91, "elapsed_time": "1:33:19", "remaining_time": "6:40:15", "throughput": 4470.69, "total_tokens": 25032640} {"current_steps": 11595, "total_steps": 61300, "loss": 0.3243, "lr": 4.8799620110028375e-05, "epoch": 1.8915171288743884, "percentage": 18.92, "elapsed_time": "1:33:21", "remaining_time": "6:40:12", "throughput": 4470.87, "total_tokens": 25043744} {"current_steps": 11600, "total_steps": 61300, "loss": 0.3645, "lr": 4.879744000872774e-05, "epoch": 1.8923327895595432, "percentage": 18.92, "elapsed_time": "1:33:23", "remaining_time": "6:40:09", "throughput": 4471.01, "total_tokens": 25055136} {"current_steps": 11605, "total_steps": 61300, "loss": 0.3487, "lr": 4.879525797828585e-05, "epoch": 1.8931484502446982, "percentage": 18.93, "elapsed_time": "1:33:26", "remaining_time": "6:40:07", "throughput": 4471.16, "total_tokens": 25066528} {"current_steps": 11610, "total_steps": 61300, "loss": 0.3304, "lr": 4.879307401887963e-05, "epoch": 1.8939641109298533, "percentage": 18.94, "elapsed_time": "1:33:28", "remaining_time": "6:40:04", "throughput": 4471.27, "total_tokens": 25077280} {"current_steps": 11615, "total_steps": 61300, "loss": 0.3649, "lr": 4.87908881306861e-05, "epoch": 1.894779771615008, "percentage": 18.95, "elapsed_time": "1:33:30", "remaining_time": "6:40:01", "throughput": 4471.42, "total_tokens": 25088544} {"current_steps": 11620, "total_steps": 61300, "loss": 0.3432, "lr": 4.878870031388246e-05, "epoch": 1.8955954323001631, "percentage": 18.96, "elapsed_time": "1:33:32", "remaining_time": "6:39:56", "throughput": 4471.49, "total_tokens": 25097344} {"current_steps": 11625, "total_steps": 61300, "loss": 0.3403, "lr": 4.8786510568646074e-05, "epoch": 1.8964110929853182, "percentage": 18.96, "elapsed_time": "1:33:35", "remaining_time": "6:39:54", "throughput": 4471.61, "total_tokens": 25108736} {"current_steps": 11630, "total_steps": 61300, "loss": 0.3829, "lr": 4.878431889515445e-05, "epoch": 1.897226753670473, "percentage": 18.97, "elapsed_time": "1:33:37", "remaining_time": "6:39:51", "throughput": 4471.75, "total_tokens": 25119648} {"current_steps": 11635, "total_steps": 61300, "loss": 0.3448, "lr": 4.8782125293585255e-05, "epoch": 1.898042414355628, "percentage": 18.98, "elapsed_time": "1:33:39", "remaining_time": "6:39:47", "throughput": 4471.86, "total_tokens": 25130048} {"current_steps": 11640, "total_steps": 61300, "loss": 0.3285, "lr": 4.877992976411632e-05, "epoch": 1.898858075040783, "percentage": 18.99, "elapsed_time": "1:33:41", "remaining_time": "6:39:43", "throughput": 4471.98, "total_tokens": 25140032} {"current_steps": 11645, "total_steps": 61300, "loss": 0.3275, "lr": 4.8777732306925614e-05, "epoch": 1.899673735725938, "percentage": 19.0, "elapsed_time": "1:33:44", "remaining_time": "6:39:41", "throughput": 4472.07, "total_tokens": 25151136} {"current_steps": 11650, "total_steps": 61300, "loss": 0.3391, "lr": 4.877553292219128e-05, "epoch": 1.900489396411093, "percentage": 19.0, "elapsed_time": "1:33:46", "remaining_time": "6:39:37", "throughput": 4472.2, "total_tokens": 25161408} {"current_steps": 11655, "total_steps": 61300, "loss": 0.3332, "lr": 4.877333161009161e-05, "epoch": 1.901305057096248, "percentage": 19.01, "elapsed_time": "1:33:48", "remaining_time": "6:39:34", "throughput": 4472.37, "total_tokens": 25172224} {"current_steps": 11660, "total_steps": 61300, "loss": 0.4109, "lr": 4.8771128370805066e-05, "epoch": 1.9021207177814028, "percentage": 19.02, "elapsed_time": "1:33:50", "remaining_time": "6:39:31", "throughput": 4472.52, "total_tokens": 25183424} {"current_steps": 11665, "total_steps": 61300, "loss": 0.3765, "lr": 4.876892320451023e-05, "epoch": 1.902936378466558, "percentage": 19.03, "elapsed_time": "1:33:53", "remaining_time": "6:39:28", "throughput": 4472.67, "total_tokens": 25194944} {"current_steps": 11670, "total_steps": 61300, "loss": 0.3766, "lr": 4.876671611138588e-05, "epoch": 1.9037520391517129, "percentage": 19.04, "elapsed_time": "1:33:55", "remaining_time": "6:39:25", "throughput": 4472.81, "total_tokens": 25205728} {"current_steps": 11675, "total_steps": 61300, "loss": 0.3522, "lr": 4.876450709161093e-05, "epoch": 1.904567699836868, "percentage": 19.05, "elapsed_time": "1:33:57", "remaining_time": "6:39:22", "throughput": 4472.96, "total_tokens": 25216576} {"current_steps": 11680, "total_steps": 61300, "loss": 0.3414, "lr": 4.876229614536446e-05, "epoch": 1.905383360522023, "percentage": 19.05, "elapsed_time": "1:33:59", "remaining_time": "6:39:19", "throughput": 4473.1, "total_tokens": 25227616} {"current_steps": 11685, "total_steps": 61300, "loss": 0.4052, "lr": 4.8760083272825695e-05, "epoch": 1.9061990212071778, "percentage": 19.06, "elapsed_time": "1:34:01", "remaining_time": "6:39:16", "throughput": 4473.21, "total_tokens": 25237856} {"current_steps": 11690, "total_steps": 61300, "loss": 0.3563, "lr": 4.875786847417402e-05, "epoch": 1.9070146818923328, "percentage": 19.07, "elapsed_time": "1:34:04", "remaining_time": "6:39:12", "throughput": 4473.35, "total_tokens": 25248256} {"current_steps": 11695, "total_steps": 61300, "loss": 0.3735, "lr": 4.875565174958898e-05, "epoch": 1.9078303425774878, "percentage": 19.08, "elapsed_time": "1:34:06", "remaining_time": "6:39:09", "throughput": 4473.44, "total_tokens": 25258944} {"current_steps": 11700, "total_steps": 61300, "loss": 0.337, "lr": 4.8753433099250276e-05, "epoch": 1.9086460032626427, "percentage": 19.09, "elapsed_time": "1:34:08", "remaining_time": "6:39:05", "throughput": 4473.56, "total_tokens": 25269120} {"current_steps": 11705, "total_steps": 61300, "loss": 0.3185, "lr": 4.875121252333776e-05, "epoch": 1.9094616639477977, "percentage": 19.09, "elapsed_time": "1:34:10", "remaining_time": "6:39:03", "throughput": 4473.7, "total_tokens": 25280160} {"current_steps": 11710, "total_steps": 61300, "loss": 0.3481, "lr": 4.874899002203145e-05, "epoch": 1.9102773246329527, "percentage": 19.1, "elapsed_time": "1:34:12", "remaining_time": "6:38:59", "throughput": 4473.84, "total_tokens": 25290112} {"current_steps": 11715, "total_steps": 61300, "loss": 0.3628, "lr": 4.8746765595511504e-05, "epoch": 1.9110929853181076, "percentage": 19.11, "elapsed_time": "1:34:15", "remaining_time": "6:38:56", "throughput": 4473.98, "total_tokens": 25301664} {"current_steps": 11720, "total_steps": 61300, "loss": 0.3329, "lr": 4.874453924395824e-05, "epoch": 1.9119086460032626, "percentage": 19.12, "elapsed_time": "1:34:17", "remaining_time": "6:38:52", "throughput": 4474.11, "total_tokens": 25311264} {"current_steps": 11725, "total_steps": 61300, "loss": 0.3174, "lr": 4.874231096755216e-05, "epoch": 1.9127243066884176, "percentage": 19.13, "elapsed_time": "1:34:19", "remaining_time": "6:38:49", "throughput": 4474.23, "total_tokens": 25321984} {"current_steps": 11730, "total_steps": 61300, "loss": 0.3662, "lr": 4.8740080766473876e-05, "epoch": 1.9135399673735725, "percentage": 19.14, "elapsed_time": "1:34:21", "remaining_time": "6:38:47", "throughput": 4474.35, "total_tokens": 25333664} {"current_steps": 11735, "total_steps": 61300, "loss": 0.3875, "lr": 4.873784864090419e-05, "epoch": 1.9143556280587277, "percentage": 19.14, "elapsed_time": "1:34:23", "remaining_time": "6:38:42", "throughput": 4474.45, "total_tokens": 25342944} {"current_steps": 11740, "total_steps": 61300, "loss": 0.3761, "lr": 4.873561459102406e-05, "epoch": 1.9151712887438825, "percentage": 19.15, "elapsed_time": "1:34:26", "remaining_time": "6:38:39", "throughput": 4474.56, "total_tokens": 25353568} {"current_steps": 11745, "total_steps": 61300, "loss": 0.3483, "lr": 4.873337861701456e-05, "epoch": 1.9159869494290374, "percentage": 19.16, "elapsed_time": "1:34:28", "remaining_time": "6:38:36", "throughput": 4474.71, "total_tokens": 25364736} {"current_steps": 11750, "total_steps": 61300, "loss": 0.3479, "lr": 4.8731140719056977e-05, "epoch": 1.9168026101141926, "percentage": 19.17, "elapsed_time": "1:34:30", "remaining_time": "6:38:32", "throughput": 4474.82, "total_tokens": 25374528} {"current_steps": 11755, "total_steps": 61300, "loss": 0.3293, "lr": 4.872890089733272e-05, "epoch": 1.9176182707993474, "percentage": 19.18, "elapsed_time": "1:34:32", "remaining_time": "6:38:29", "throughput": 4474.96, "total_tokens": 25385440} {"current_steps": 11760, "total_steps": 61300, "loss": 0.3293, "lr": 4.8726659152023356e-05, "epoch": 1.9184339314845025, "percentage": 19.18, "elapsed_time": "1:34:35", "remaining_time": "6:38:27", "throughput": 4475.14, "total_tokens": 25397344} {"current_steps": 11765, "total_steps": 61300, "loss": 0.3326, "lr": 4.87244154833106e-05, "epoch": 1.9192495921696575, "percentage": 19.19, "elapsed_time": "1:34:37", "remaining_time": "6:38:24", "throughput": 4475.29, "total_tokens": 25408448} {"current_steps": 11770, "total_steps": 61300, "loss": 0.3384, "lr": 4.872216989137637e-05, "epoch": 1.9200652528548123, "percentage": 19.2, "elapsed_time": "1:34:39", "remaining_time": "6:38:20", "throughput": 4475.41, "total_tokens": 25418336} {"current_steps": 11775, "total_steps": 61300, "loss": 0.3512, "lr": 4.871992237640267e-05, "epoch": 1.9208809135399674, "percentage": 19.21, "elapsed_time": "1:34:41", "remaining_time": "6:38:17", "throughput": 4475.54, "total_tokens": 25429824} {"current_steps": 11780, "total_steps": 61300, "loss": 0.3541, "lr": 4.871767293857171e-05, "epoch": 1.9216965742251224, "percentage": 19.22, "elapsed_time": "1:34:43", "remaining_time": "6:38:13", "throughput": 4475.67, "total_tokens": 25439584} {"current_steps": 11785, "total_steps": 61300, "loss": 0.3299, "lr": 4.871542157806584e-05, "epoch": 1.9225122349102772, "percentage": 19.23, "elapsed_time": "1:34:46", "remaining_time": "6:38:11", "throughput": 4475.87, "total_tokens": 25451744} {"current_steps": 11790, "total_steps": 61300, "loss": 0.3854, "lr": 4.871316829506757e-05, "epoch": 1.9233278955954323, "percentage": 19.23, "elapsed_time": "1:34:48", "remaining_time": "6:38:08", "throughput": 4475.97, "total_tokens": 25461856} {"current_steps": 11795, "total_steps": 61300, "loss": 0.365, "lr": 4.871091308975955e-05, "epoch": 1.9241435562805873, "percentage": 19.24, "elapsed_time": "1:34:50", "remaining_time": "6:38:05", "throughput": 4476.14, "total_tokens": 25473120} {"current_steps": 11800, "total_steps": 61300, "loss": 0.3299, "lr": 4.8708655962324615e-05, "epoch": 1.9249592169657421, "percentage": 19.25, "elapsed_time": "1:34:53", "remaining_time": "6:38:03", "throughput": 4476.29, "total_tokens": 25485632} {"current_steps": 11805, "total_steps": 61300, "loss": 0.3491, "lr": 4.870639691294573e-05, "epoch": 1.9257748776508974, "percentage": 19.26, "elapsed_time": "1:34:55", "remaining_time": "6:38:00", "throughput": 4476.39, "total_tokens": 25496160} {"current_steps": 11810, "total_steps": 61300, "loss": 0.3707, "lr": 4.8704135941806016e-05, "epoch": 1.9265905383360522, "percentage": 19.27, "elapsed_time": "1:34:58", "remaining_time": "6:37:57", "throughput": 4476.54, "total_tokens": 25507712} {"current_steps": 11815, "total_steps": 61300, "loss": 0.3713, "lr": 4.870187304908878e-05, "epoch": 1.927406199021207, "percentage": 19.27, "elapsed_time": "1:35:00", "remaining_time": "6:37:55", "throughput": 4476.7, "total_tokens": 25519328} {"current_steps": 11820, "total_steps": 61300, "loss": 0.3174, "lr": 4.869960823497745e-05, "epoch": 1.9282218597063623, "percentage": 19.28, "elapsed_time": "1:35:02", "remaining_time": "6:37:51", "throughput": 4476.82, "total_tokens": 25528992} {"current_steps": 11825, "total_steps": 61300, "loss": 0.3408, "lr": 4.8697341499655626e-05, "epoch": 1.929037520391517, "percentage": 19.29, "elapsed_time": "1:35:04", "remaining_time": "6:37:48", "throughput": 4476.97, "total_tokens": 25540032} {"current_steps": 11830, "total_steps": 61300, "loss": 0.3152, "lr": 4.8695072843307064e-05, "epoch": 1.9298531810766721, "percentage": 19.3, "elapsed_time": "1:35:07", "remaining_time": "6:37:45", "throughput": 4477.13, "total_tokens": 25551392} {"current_steps": 11835, "total_steps": 61300, "loss": 0.3439, "lr": 4.869280226611567e-05, "epoch": 1.9306688417618272, "percentage": 19.31, "elapsed_time": "1:35:09", "remaining_time": "6:37:42", "throughput": 4477.27, "total_tokens": 25561856} {"current_steps": 11840, "total_steps": 61300, "loss": 0.2733, "lr": 4.86905297682655e-05, "epoch": 1.931484502446982, "percentage": 19.31, "elapsed_time": "1:35:11", "remaining_time": "6:37:38", "throughput": 4477.36, "total_tokens": 25571712} {"current_steps": 11845, "total_steps": 61300, "loss": 0.3751, "lr": 4.868825534994078e-05, "epoch": 1.932300163132137, "percentage": 19.32, "elapsed_time": "1:35:13", "remaining_time": "6:37:34", "throughput": 4477.45, "total_tokens": 25581088} {"current_steps": 11850, "total_steps": 61300, "loss": 0.2706, "lr": 4.86859790113259e-05, "epoch": 1.933115823817292, "percentage": 19.33, "elapsed_time": "1:35:15", "remaining_time": "6:37:32", "throughput": 4477.61, "total_tokens": 25593376} {"current_steps": 11855, "total_steps": 61300, "loss": 0.3761, "lr": 4.868370075260538e-05, "epoch": 1.933931484502447, "percentage": 19.34, "elapsed_time": "1:35:17", "remaining_time": "6:37:28", "throughput": 4477.73, "total_tokens": 25603488} {"current_steps": 11860, "total_steps": 61300, "loss": 0.4224, "lr": 4.86814205739639e-05, "epoch": 1.934747145187602, "percentage": 19.35, "elapsed_time": "1:35:19", "remaining_time": "6:37:24", "throughput": 4477.86, "total_tokens": 25613216} {"current_steps": 11865, "total_steps": 61300, "loss": 0.3349, "lr": 4.86791384755863e-05, "epoch": 1.935562805872757, "percentage": 19.36, "elapsed_time": "1:35:22", "remaining_time": "6:37:21", "throughput": 4477.98, "total_tokens": 25624096} {"current_steps": 11870, "total_steps": 61300, "loss": 0.3445, "lr": 4.86768544576576e-05, "epoch": 1.9363784665579118, "percentage": 19.36, "elapsed_time": "1:35:24", "remaining_time": "6:37:17", "throughput": 4478.1, "total_tokens": 25633760} {"current_steps": 11875, "total_steps": 61300, "loss": 0.3676, "lr": 4.867456852036295e-05, "epoch": 1.9371941272430668, "percentage": 19.37, "elapsed_time": "1:35:26", "remaining_time": "6:37:14", "throughput": 4478.23, "total_tokens": 25645216} {"current_steps": 11880, "total_steps": 61300, "loss": 0.3586, "lr": 4.867228066388765e-05, "epoch": 1.9380097879282219, "percentage": 19.38, "elapsed_time": "1:35:28", "remaining_time": "6:37:11", "throughput": 4478.39, "total_tokens": 25656288} {"current_steps": 11885, "total_steps": 61300, "loss": 0.3222, "lr": 4.866999088841716e-05, "epoch": 1.9388254486133767, "percentage": 19.39, "elapsed_time": "1:35:31", "remaining_time": "6:37:09", "throughput": 4478.51, "total_tokens": 25667488} {"current_steps": 11890, "total_steps": 61300, "loss": 0.3807, "lr": 4.866769919413711e-05, "epoch": 1.939641109298532, "percentage": 19.4, "elapsed_time": "1:35:33", "remaining_time": "6:37:06", "throughput": 4478.64, "total_tokens": 25678848} {"current_steps": 11895, "total_steps": 61300, "loss": 0.3611, "lr": 4.866540558123328e-05, "epoch": 1.9404567699836868, "percentage": 19.4, "elapsed_time": "1:35:35", "remaining_time": "6:37:03", "throughput": 4478.75, "total_tokens": 25689280} {"current_steps": 11900, "total_steps": 61300, "loss": 0.3129, "lr": 4.8663110049891595e-05, "epoch": 1.9412724306688418, "percentage": 19.41, "elapsed_time": "1:35:37", "remaining_time": "6:36:59", "throughput": 4478.89, "total_tokens": 25699552} {"current_steps": 11905, "total_steps": 61300, "loss": 0.3149, "lr": 4.866081260029813e-05, "epoch": 1.9420880913539968, "percentage": 19.42, "elapsed_time": "1:35:40", "remaining_time": "6:36:56", "throughput": 4479.01, "total_tokens": 25709920} {"current_steps": 11910, "total_steps": 61300, "loss": 0.3598, "lr": 4.8658513232639155e-05, "epoch": 1.9429037520391517, "percentage": 19.43, "elapsed_time": "1:35:42", "remaining_time": "6:36:54", "throughput": 4479.19, "total_tokens": 25722592} {"current_steps": 11915, "total_steps": 61300, "loss": 0.3615, "lr": 4.8656211947101054e-05, "epoch": 1.9437194127243067, "percentage": 19.44, "elapsed_time": "1:35:45", "remaining_time": "6:36:51", "throughput": 4479.31, "total_tokens": 25733696} {"current_steps": 11920, "total_steps": 61300, "loss": 0.391, "lr": 4.865390874387038e-05, "epoch": 1.9445350734094617, "percentage": 19.45, "elapsed_time": "1:35:47", "remaining_time": "6:36:48", "throughput": 4479.41, "total_tokens": 25743712} {"current_steps": 11925, "total_steps": 61300, "loss": 0.3185, "lr": 4.865160362313384e-05, "epoch": 1.9453507340946166, "percentage": 19.45, "elapsed_time": "1:35:49", "remaining_time": "6:36:44", "throughput": 4479.52, "total_tokens": 25753952} {"current_steps": 11930, "total_steps": 61300, "loss": 0.3422, "lr": 4.8649296585078316e-05, "epoch": 1.9461663947797716, "percentage": 19.46, "elapsed_time": "1:35:51", "remaining_time": "6:36:41", "throughput": 4479.66, "total_tokens": 25764896} {"current_steps": 11935, "total_steps": 61300, "loss": 0.3834, "lr": 4.864698762989081e-05, "epoch": 1.9469820554649266, "percentage": 19.47, "elapsed_time": "1:35:53", "remaining_time": "6:36:37", "throughput": 4479.77, "total_tokens": 25774944} {"current_steps": 11940, "total_steps": 61300, "loss": 0.3229, "lr": 4.86446767577585e-05, "epoch": 1.9477977161500815, "percentage": 19.48, "elapsed_time": "1:35:55", "remaining_time": "6:36:34", "throughput": 4479.87, "total_tokens": 25785472} {"current_steps": 11945, "total_steps": 61300, "loss": 0.3307, "lr": 4.864236396886872e-05, "epoch": 1.9486133768352365, "percentage": 19.49, "elapsed_time": "1:35:58", "remaining_time": "6:36:31", "throughput": 4480.02, "total_tokens": 25796448} {"current_steps": 11950, "total_steps": 61300, "loss": 0.3597, "lr": 4.864004926340896e-05, "epoch": 1.9494290375203915, "percentage": 19.49, "elapsed_time": "1:36:00", "remaining_time": "6:36:28", "throughput": 4480.14, "total_tokens": 25807168} {"current_steps": 11955, "total_steps": 61300, "loss": 0.3437, "lr": 4.8637732641566855e-05, "epoch": 1.9502446982055464, "percentage": 19.5, "elapsed_time": "1:36:02", "remaining_time": "6:36:25", "throughput": 4480.27, "total_tokens": 25817792} {"current_steps": 11960, "total_steps": 61300, "loss": 0.3553, "lr": 4.8635414103530205e-05, "epoch": 1.9510603588907016, "percentage": 19.51, "elapsed_time": "1:36:04", "remaining_time": "6:36:21", "throughput": 4480.39, "total_tokens": 25827392} {"current_steps": 11965, "total_steps": 61300, "loss": 0.3556, "lr": 4.863309364948697e-05, "epoch": 1.9518760195758564, "percentage": 19.52, "elapsed_time": "1:36:06", "remaining_time": "6:36:18", "throughput": 4480.54, "total_tokens": 25838720} {"current_steps": 11970, "total_steps": 61300, "loss": 0.3419, "lr": 4.863077127962524e-05, "epoch": 1.9526916802610113, "percentage": 19.53, "elapsed_time": "1:36:09", "remaining_time": "6:36:16", "throughput": 4480.7, "total_tokens": 25850496} {"current_steps": 11975, "total_steps": 61300, "loss": 0.3526, "lr": 4.8628446994133306e-05, "epoch": 1.9535073409461665, "percentage": 19.54, "elapsed_time": "1:36:11", "remaining_time": "6:36:13", "throughput": 4480.84, "total_tokens": 25862240} {"current_steps": 11980, "total_steps": 61300, "loss": 0.3398, "lr": 4.8626120793199545e-05, "epoch": 1.9543230016313213, "percentage": 19.54, "elapsed_time": "1:36:14", "remaining_time": "6:36:11", "throughput": 4480.93, "total_tokens": 25873280} {"current_steps": 11985, "total_steps": 61300, "loss": 0.3601, "lr": 4.862379267701257e-05, "epoch": 1.9551386623164764, "percentage": 19.55, "elapsed_time": "1:36:16", "remaining_time": "6:36:07", "throughput": 4481.05, "total_tokens": 25883872} {"current_steps": 11990, "total_steps": 61300, "loss": 0.3449, "lr": 4.86214626457611e-05, "epoch": 1.9559543230016314, "percentage": 19.56, "elapsed_time": "1:36:18", "remaining_time": "6:36:05", "throughput": 4481.19, "total_tokens": 25895424} {"current_steps": 11995, "total_steps": 61300, "loss": 0.3415, "lr": 4.8619130699633994e-05, "epoch": 1.9567699836867862, "percentage": 19.57, "elapsed_time": "1:36:21", "remaining_time": "6:36:03", "throughput": 4481.3, "total_tokens": 25906944} {"current_steps": 12000, "total_steps": 61300, "loss": 0.3366, "lr": 4.861679683882033e-05, "epoch": 1.9575856443719413, "percentage": 19.58, "elapsed_time": "1:36:23", "remaining_time": "6:36:00", "throughput": 4481.47, "total_tokens": 25918720} {"current_steps": 12005, "total_steps": 61300, "loss": 0.3251, "lr": 4.861446106350928e-05, "epoch": 1.9584013050570963, "percentage": 19.58, "elapsed_time": "1:36:25", "remaining_time": "6:35:57", "throughput": 4481.58, "total_tokens": 25929248} {"current_steps": 12010, "total_steps": 61300, "loss": 0.3988, "lr": 4.861212337389019e-05, "epoch": 1.9592169657422511, "percentage": 19.59, "elapsed_time": "1:36:27", "remaining_time": "6:35:53", "throughput": 4481.68, "total_tokens": 25939040} {"current_steps": 12015, "total_steps": 61300, "loss": 0.3622, "lr": 4.8609783770152575e-05, "epoch": 1.9600326264274062, "percentage": 19.6, "elapsed_time": "1:36:29", "remaining_time": "6:35:49", "throughput": 4481.8, "total_tokens": 25949024} {"current_steps": 12020, "total_steps": 61300, "loss": 0.375, "lr": 4.8607442252486095e-05, "epoch": 1.9608482871125612, "percentage": 19.61, "elapsed_time": "1:36:31", "remaining_time": "6:35:46", "throughput": 4481.93, "total_tokens": 25959264} {"current_steps": 12025, "total_steps": 61300, "loss": 0.361, "lr": 4.8605098821080564e-05, "epoch": 1.961663947797716, "percentage": 19.62, "elapsed_time": "1:36:34", "remaining_time": "6:35:43", "throughput": 4482.1, "total_tokens": 25970432} {"current_steps": 12030, "total_steps": 61300, "loss": 0.3546, "lr": 4.8602753476125954e-05, "epoch": 1.9624796084828713, "percentage": 19.62, "elapsed_time": "1:36:36", "remaining_time": "6:35:40", "throughput": 4482.22, "total_tokens": 25981856} {"current_steps": 12035, "total_steps": 61300, "loss": 0.3223, "lr": 4.860040621781238e-05, "epoch": 1.963295269168026, "percentage": 19.63, "elapsed_time": "1:36:39", "remaining_time": "6:35:38", "throughput": 4482.36, "total_tokens": 25993696} {"current_steps": 12040, "total_steps": 61300, "loss": 0.3802, "lr": 4.8598057046330135e-05, "epoch": 1.964110929853181, "percentage": 19.64, "elapsed_time": "1:36:41", "remaining_time": "6:35:35", "throughput": 4482.51, "total_tokens": 26004736} {"current_steps": 12045, "total_steps": 61300, "loss": 0.3943, "lr": 4.8595705961869656e-05, "epoch": 1.9649265905383362, "percentage": 19.65, "elapsed_time": "1:36:43", "remaining_time": "6:35:33", "throughput": 4482.64, "total_tokens": 26016480} {"current_steps": 12050, "total_steps": 61300, "loss": 0.3734, "lr": 4.859335296462152e-05, "epoch": 1.965742251223491, "percentage": 19.66, "elapsed_time": "1:36:46", "remaining_time": "6:35:29", "throughput": 4482.78, "total_tokens": 26027072} {"current_steps": 12055, "total_steps": 61300, "loss": 0.3787, "lr": 4.859099805477648e-05, "epoch": 1.966557911908646, "percentage": 19.67, "elapsed_time": "1:36:47", "remaining_time": "6:35:25", "throughput": 4482.88, "total_tokens": 26036096} {"current_steps": 12060, "total_steps": 61300, "loss": 0.3363, "lr": 4.858864123252544e-05, "epoch": 1.967373572593801, "percentage": 19.67, "elapsed_time": "1:36:50", "remaining_time": "6:35:22", "throughput": 4483.0, "total_tokens": 26047264} {"current_steps": 12065, "total_steps": 61300, "loss": 0.3333, "lr": 4.8586282498059456e-05, "epoch": 1.968189233278956, "percentage": 19.68, "elapsed_time": "1:36:52", "remaining_time": "6:35:19", "throughput": 4483.12, "total_tokens": 26058176} {"current_steps": 12070, "total_steps": 61300, "loss": 0.3238, "lr": 4.8583921851569735e-05, "epoch": 1.969004893964111, "percentage": 19.69, "elapsed_time": "1:36:54", "remaining_time": "6:35:17", "throughput": 4483.27, "total_tokens": 26069664} {"current_steps": 12075, "total_steps": 61300, "loss": 0.3571, "lr": 4.8581559293247655e-05, "epoch": 1.969820554649266, "percentage": 19.7, "elapsed_time": "1:36:57", "remaining_time": "6:35:14", "throughput": 4483.39, "total_tokens": 26080640} {"current_steps": 12080, "total_steps": 61300, "loss": 0.3796, "lr": 4.857919482328471e-05, "epoch": 1.9706362153344208, "percentage": 19.71, "elapsed_time": "1:36:59", "remaining_time": "6:35:11", "throughput": 4483.53, "total_tokens": 26091360} {"current_steps": 12085, "total_steps": 61300, "loss": 0.3416, "lr": 4.857682844187261e-05, "epoch": 1.9714518760195758, "percentage": 19.71, "elapsed_time": "1:37:01", "remaining_time": "6:35:07", "throughput": 4483.66, "total_tokens": 26102080} {"current_steps": 12090, "total_steps": 61300, "loss": 0.3158, "lr": 4.857446014920316e-05, "epoch": 1.9722675367047309, "percentage": 19.72, "elapsed_time": "1:37:03", "remaining_time": "6:35:04", "throughput": 4483.8, "total_tokens": 26112192} {"current_steps": 12095, "total_steps": 61300, "loss": 0.3499, "lr": 4.857208994546836e-05, "epoch": 1.9730831973898857, "percentage": 19.73, "elapsed_time": "1:37:05", "remaining_time": "6:35:00", "throughput": 4483.93, "total_tokens": 26122496} {"current_steps": 12100, "total_steps": 61300, "loss": 0.368, "lr": 4.856971783086034e-05, "epoch": 1.9738988580750407, "percentage": 19.74, "elapsed_time": "1:37:08", "remaining_time": "6:34:58", "throughput": 4484.05, "total_tokens": 26134048} {"current_steps": 12105, "total_steps": 61300, "loss": 0.3986, "lr": 4.85673438055714e-05, "epoch": 1.9747145187601958, "percentage": 19.75, "elapsed_time": "1:37:10", "remaining_time": "6:34:54", "throughput": 4484.16, "total_tokens": 26144192} {"current_steps": 12110, "total_steps": 61300, "loss": 0.3594, "lr": 4.856496786979399e-05, "epoch": 1.9755301794453506, "percentage": 19.76, "elapsed_time": "1:37:12", "remaining_time": "6:34:51", "throughput": 4484.3, "total_tokens": 26155328} {"current_steps": 12115, "total_steps": 61300, "loss": 0.3549, "lr": 4.8562590023720725e-05, "epoch": 1.9763458401305058, "percentage": 19.76, "elapsed_time": "1:37:14", "remaining_time": "6:34:48", "throughput": 4484.44, "total_tokens": 26166272} {"current_steps": 12120, "total_steps": 61300, "loss": 0.3557, "lr": 4.8560210267544345e-05, "epoch": 1.9771615008156607, "percentage": 19.77, "elapsed_time": "1:37:16", "remaining_time": "6:34:44", "throughput": 4484.55, "total_tokens": 26175520} {"current_steps": 12125, "total_steps": 61300, "loss": 0.3518, "lr": 4.855782860145779e-05, "epoch": 1.9779771615008157, "percentage": 19.78, "elapsed_time": "1:37:19", "remaining_time": "6:34:41", "throughput": 4484.67, "total_tokens": 26187008} {"current_steps": 12130, "total_steps": 61300, "loss": 0.3447, "lr": 4.8555445025654116e-05, "epoch": 1.9787928221859707, "percentage": 19.79, "elapsed_time": "1:37:21", "remaining_time": "6:34:39", "throughput": 4484.78, "total_tokens": 26198016} {"current_steps": 12135, "total_steps": 61300, "loss": 0.3443, "lr": 4.855305954032655e-05, "epoch": 1.9796084828711256, "percentage": 19.8, "elapsed_time": "1:37:23", "remaining_time": "6:34:36", "throughput": 4484.91, "total_tokens": 26209440} {"current_steps": 12140, "total_steps": 61300, "loss": 0.3058, "lr": 4.855067214566846e-05, "epoch": 1.9804241435562806, "percentage": 19.8, "elapsed_time": "1:37:26", "remaining_time": "6:34:34", "throughput": 4485.02, "total_tokens": 26220736} {"current_steps": 12145, "total_steps": 61300, "loss": 0.3961, "lr": 4.85482828418734e-05, "epoch": 1.9812398042414356, "percentage": 19.81, "elapsed_time": "1:37:28", "remaining_time": "6:34:30", "throughput": 4485.17, "total_tokens": 26231456} {"current_steps": 12150, "total_steps": 61300, "loss": 0.3714, "lr": 4.854589162913505e-05, "epoch": 1.9820554649265905, "percentage": 19.82, "elapsed_time": "1:37:30", "remaining_time": "6:34:27", "throughput": 4485.3, "total_tokens": 26241568} {"current_steps": 12155, "total_steps": 61300, "loss": 0.3371, "lr": 4.854349850764725e-05, "epoch": 1.9828711256117455, "percentage": 19.83, "elapsed_time": "1:37:32", "remaining_time": "6:34:24", "throughput": 4485.43, "total_tokens": 26252480} {"current_steps": 12160, "total_steps": 61300, "loss": 0.3968, "lr": 4.8541103477604e-05, "epoch": 1.9836867862969005, "percentage": 19.84, "elapsed_time": "1:37:35", "remaining_time": "6:34:21", "throughput": 4485.56, "total_tokens": 26263264} {"current_steps": 12165, "total_steps": 61300, "loss": 0.3404, "lr": 4.853870653919946e-05, "epoch": 1.9845024469820554, "percentage": 19.85, "elapsed_time": "1:37:37", "remaining_time": "6:34:18", "throughput": 4485.72, "total_tokens": 26274496} {"current_steps": 12170, "total_steps": 61300, "loss": 0.3354, "lr": 4.853630769262794e-05, "epoch": 1.9853181076672104, "percentage": 19.85, "elapsed_time": "1:37:39", "remaining_time": "6:34:14", "throughput": 4485.85, "total_tokens": 26285152} {"current_steps": 12175, "total_steps": 61300, "loss": 0.3325, "lr": 4.853390693808388e-05, "epoch": 1.9861337683523654, "percentage": 19.86, "elapsed_time": "1:37:41", "remaining_time": "6:34:12", "throughput": 4485.96, "total_tokens": 26296064} {"current_steps": 12180, "total_steps": 61300, "loss": 0.3551, "lr": 4.853150427576193e-05, "epoch": 1.9869494290375203, "percentage": 19.87, "elapsed_time": "1:37:43", "remaining_time": "6:34:08", "throughput": 4486.08, "total_tokens": 26305984} {"current_steps": 12185, "total_steps": 61300, "loss": 0.3525, "lr": 4.852909970585684e-05, "epoch": 1.9877650897226755, "percentage": 19.88, "elapsed_time": "1:37:46", "remaining_time": "6:34:05", "throughput": 4486.17, "total_tokens": 26316896} {"current_steps": 12190, "total_steps": 61300, "loss": 0.3628, "lr": 4.852669322856354e-05, "epoch": 1.9885807504078303, "percentage": 19.89, "elapsed_time": "1:37:48", "remaining_time": "6:34:01", "throughput": 4486.29, "total_tokens": 26326976} {"current_steps": 12195, "total_steps": 61300, "loss": 0.3608, "lr": 4.8524284844077116e-05, "epoch": 1.9893964110929854, "percentage": 19.89, "elapsed_time": "1:37:50", "remaining_time": "6:33:58", "throughput": 4486.39, "total_tokens": 26337504} {"current_steps": 12200, "total_steps": 61300, "loss": 0.3449, "lr": 4.8521874552592805e-05, "epoch": 1.9902120717781404, "percentage": 19.9, "elapsed_time": "1:37:52", "remaining_time": "6:33:55", "throughput": 4486.52, "total_tokens": 26348608} {"current_steps": 12205, "total_steps": 61300, "loss": 0.3087, "lr": 4.851946235430599e-05, "epoch": 1.9910277324632952, "percentage": 19.91, "elapsed_time": "1:37:54", "remaining_time": "6:33:51", "throughput": 4486.61, "total_tokens": 26358240} {"current_steps": 12210, "total_steps": 61300, "loss": 0.3331, "lr": 4.851704824941222e-05, "epoch": 1.9918433931484503, "percentage": 19.92, "elapsed_time": "1:37:57", "remaining_time": "6:33:49", "throughput": 4486.74, "total_tokens": 26369568} {"current_steps": 12215, "total_steps": 61300, "loss": 0.3525, "lr": 4.8514632238107194e-05, "epoch": 1.9926590538336053, "percentage": 19.93, "elapsed_time": "1:37:59", "remaining_time": "6:33:45", "throughput": 4486.84, "total_tokens": 26379936} {"current_steps": 12220, "total_steps": 61300, "loss": 0.3522, "lr": 4.851221432058677e-05, "epoch": 1.9934747145187601, "percentage": 19.93, "elapsed_time": "1:38:01", "remaining_time": "6:33:42", "throughput": 4486.96, "total_tokens": 26390624} {"current_steps": 12225, "total_steps": 61300, "loss": 0.3441, "lr": 4.850979449704695e-05, "epoch": 1.9942903752039152, "percentage": 19.94, "elapsed_time": "1:38:03", "remaining_time": "6:33:38", "throughput": 4487.06, "total_tokens": 26399616} {"current_steps": 12230, "total_steps": 61300, "loss": 0.3042, "lr": 4.85073727676839e-05, "epoch": 1.9951060358890702, "percentage": 19.95, "elapsed_time": "1:38:05", "remaining_time": "6:33:35", "throughput": 4487.17, "total_tokens": 26410208} {"current_steps": 12235, "total_steps": 61300, "loss": 0.3562, "lr": 4.8504949132693936e-05, "epoch": 1.995921696574225, "percentage": 19.96, "elapsed_time": "1:38:07", "remaining_time": "6:33:31", "throughput": 4487.31, "total_tokens": 26420160} {"current_steps": 12240, "total_steps": 61300, "loss": 0.3412, "lr": 4.850252359227353e-05, "epoch": 1.99673735725938, "percentage": 19.97, "elapsed_time": "1:38:09", "remaining_time": "6:33:27", "throughput": 4487.41, "total_tokens": 26430432} {"current_steps": 12245, "total_steps": 61300, "loss": 0.3382, "lr": 4.8500096146619325e-05, "epoch": 1.997553017944535, "percentage": 19.98, "elapsed_time": "1:38:11", "remaining_time": "6:33:23", "throughput": 4487.49, "total_tokens": 26440128} {"current_steps": 12250, "total_steps": 61300, "loss": 0.3759, "lr": 4.849766679592808e-05, "epoch": 1.99836867862969, "percentage": 19.98, "elapsed_time": "1:38:14", "remaining_time": "6:33:20", "throughput": 4487.62, "total_tokens": 26450496} {"current_steps": 12255, "total_steps": 61300, "loss": 0.3258, "lr": 4.849523554039673e-05, "epoch": 1.9991843393148452, "percentage": 19.99, "elapsed_time": "1:38:16", "remaining_time": "6:33:17", "throughput": 4487.77, "total_tokens": 26461824} {"current_steps": 12260, "total_steps": 61300, "loss": 0.4006, "lr": 4.8492802380222393e-05, "epoch": 2.0, "percentage": 20.0, "elapsed_time": "1:38:18", "remaining_time": "6:33:13", "throughput": 4487.79, "total_tokens": 26471216} {"current_steps": 12260, "total_steps": 61300, "eval_loss": 0.3466723561286926, "epoch": 2.0, "percentage": 20.0, "elapsed_time": "1:40:30", "remaining_time": "6:42:01", "throughput": 4389.63, "total_tokens": 26471216} {"current_steps": 12265, "total_steps": 61300, "loss": 0.3675, "lr": 4.849036731560228e-05, "epoch": 2.000815660685155, "percentage": 20.01, "elapsed_time": "1:40:33", "remaining_time": "6:42:03", "throughput": 4388.9, "total_tokens": 26481904} {"current_steps": 12270, "total_steps": 61300, "loss": 0.3155, "lr": 4.84879303467338e-05, "epoch": 2.00163132137031, "percentage": 20.02, "elapsed_time": "1:40:35", "remaining_time": "6:41:58", "throughput": 4389.01, "total_tokens": 26491344} {"current_steps": 12275, "total_steps": 61300, "loss": 0.3608, "lr": 4.8485491473814514e-05, "epoch": 2.002446982055465, "percentage": 20.02, "elapsed_time": "1:40:38", "remaining_time": "6:41:55", "throughput": 4389.14, "total_tokens": 26502160} {"current_steps": 12280, "total_steps": 61300, "loss": 0.3724, "lr": 4.8483050697042135e-05, "epoch": 2.0032626427406197, "percentage": 20.03, "elapsed_time": "1:40:40", "remaining_time": "6:41:52", "throughput": 4389.28, "total_tokens": 26512816} {"current_steps": 12285, "total_steps": 61300, "loss": 0.364, "lr": 4.8480608016614504e-05, "epoch": 2.004078303425775, "percentage": 20.04, "elapsed_time": "1:40:42", "remaining_time": "6:41:47", "throughput": 4389.45, "total_tokens": 26522640} {"current_steps": 12290, "total_steps": 61300, "loss": 0.3487, "lr": 4.847816343272965e-05, "epoch": 2.00489396411093, "percentage": 20.05, "elapsed_time": "1:40:44", "remaining_time": "6:41:44", "throughput": 4389.59, "total_tokens": 26533072} {"current_steps": 12295, "total_steps": 61300, "loss": 0.3388, "lr": 4.847571694558574e-05, "epoch": 2.0057096247960846, "percentage": 20.06, "elapsed_time": "1:40:46", "remaining_time": "6:41:40", "throughput": 4389.73, "total_tokens": 26543408} {"current_steps": 12300, "total_steps": 61300, "loss": 0.3579, "lr": 4.84732685553811e-05, "epoch": 2.00652528548124, "percentage": 20.07, "elapsed_time": "1:40:48", "remaining_time": "6:41:37", "throughput": 4389.88, "total_tokens": 26554320} {"current_steps": 12305, "total_steps": 61300, "loss": 0.3561, "lr": 4.847081826231421e-05, "epoch": 2.0073409461663947, "percentage": 20.07, "elapsed_time": "1:40:51", "remaining_time": "6:41:34", "throughput": 4390.07, "total_tokens": 26565008} {"current_steps": 12310, "total_steps": 61300, "loss": 0.3526, "lr": 4.846836606658371e-05, "epoch": 2.00815660685155, "percentage": 20.08, "elapsed_time": "1:40:53", "remaining_time": "6:41:31", "throughput": 4390.23, "total_tokens": 26576912} {"current_steps": 12315, "total_steps": 61300, "loss": 0.3568, "lr": 4.8465911968388364e-05, "epoch": 2.0089722675367048, "percentage": 20.09, "elapsed_time": "1:40:55", "remaining_time": "6:41:27", "throughput": 4390.34, "total_tokens": 26586800} {"current_steps": 12320, "total_steps": 61300, "loss": 0.3554, "lr": 4.846345596792713e-05, "epoch": 2.0097879282218596, "percentage": 20.1, "elapsed_time": "1:40:58", "remaining_time": "6:41:24", "throughput": 4390.5, "total_tokens": 26598160} {"current_steps": 12325, "total_steps": 61300, "loss": 0.3185, "lr": 4.846099806539911e-05, "epoch": 2.010603588907015, "percentage": 20.11, "elapsed_time": "1:41:00", "remaining_time": "6:41:21", "throughput": 4390.66, "total_tokens": 26609136} {"current_steps": 12330, "total_steps": 61300, "loss": 0.3264, "lr": 4.845853826100355e-05, "epoch": 2.0114192495921697, "percentage": 20.11, "elapsed_time": "1:41:02", "remaining_time": "6:41:19", "throughput": 4390.83, "total_tokens": 26620752} {"current_steps": 12335, "total_steps": 61300, "loss": 0.3452, "lr": 4.845607655493984e-05, "epoch": 2.0122349102773245, "percentage": 20.12, "elapsed_time": "1:41:04", "remaining_time": "6:41:14", "throughput": 4390.98, "total_tokens": 26630256} {"current_steps": 12340, "total_steps": 61300, "loss": 0.3413, "lr": 4.8453612947407564e-05, "epoch": 2.0130505709624797, "percentage": 20.13, "elapsed_time": "1:41:07", "remaining_time": "6:41:11", "throughput": 4391.13, "total_tokens": 26641136} {"current_steps": 12345, "total_steps": 61300, "loss": 0.331, "lr": 4.8451147438606416e-05, "epoch": 2.0138662316476346, "percentage": 20.14, "elapsed_time": "1:41:09", "remaining_time": "6:41:08", "throughput": 4391.28, "total_tokens": 26651824} {"current_steps": 12350, "total_steps": 61300, "loss": 0.3351, "lr": 4.844868002873626e-05, "epoch": 2.0146818923327894, "percentage": 20.15, "elapsed_time": "1:41:11", "remaining_time": "6:41:04", "throughput": 4391.42, "total_tokens": 26662064} {"current_steps": 12355, "total_steps": 61300, "loss": 0.4232, "lr": 4.844621071799712e-05, "epoch": 2.0154975530179446, "percentage": 20.15, "elapsed_time": "1:41:13", "remaining_time": "6:41:01", "throughput": 4391.58, "total_tokens": 26673104} {"current_steps": 12360, "total_steps": 61300, "loss": 0.3579, "lr": 4.844373950658918e-05, "epoch": 2.0163132137030995, "percentage": 20.16, "elapsed_time": "1:41:15", "remaining_time": "6:40:56", "throughput": 4391.73, "total_tokens": 26682736} {"current_steps": 12365, "total_steps": 61300, "loss": 0.3472, "lr": 4.844126639471277e-05, "epoch": 2.0171288743882543, "percentage": 20.17, "elapsed_time": "1:41:18", "remaining_time": "6:40:54", "throughput": 4391.89, "total_tokens": 26694224} {"current_steps": 12370, "total_steps": 61300, "loss": 0.3595, "lr": 4.843879138256836e-05, "epoch": 2.0179445350734095, "percentage": 20.18, "elapsed_time": "1:41:20", "remaining_time": "6:40:50", "throughput": 4392.04, "total_tokens": 26704880} {"current_steps": 12375, "total_steps": 61300, "loss": 0.3509, "lr": 4.843631447035659e-05, "epoch": 2.0187601957585644, "percentage": 20.19, "elapsed_time": "1:41:22", "remaining_time": "6:40:45", "throughput": 4392.18, "total_tokens": 26713648} {"current_steps": 12380, "total_steps": 61300, "loss": 0.3669, "lr": 4.843383565827826e-05, "epoch": 2.0195758564437196, "percentage": 20.2, "elapsed_time": "1:41:24", "remaining_time": "6:40:42", "throughput": 4392.35, "total_tokens": 26724560} {"current_steps": 12385, "total_steps": 61300, "loss": 0.3667, "lr": 4.843135494653431e-05, "epoch": 2.0203915171288744, "percentage": 20.2, "elapsed_time": "1:41:26", "remaining_time": "6:40:39", "throughput": 4392.49, "total_tokens": 26735344} {"current_steps": 12390, "total_steps": 61300, "loss": 0.343, "lr": 4.842887233532584e-05, "epoch": 2.0212071778140293, "percentage": 20.21, "elapsed_time": "1:41:28", "remaining_time": "6:40:36", "throughput": 4392.64, "total_tokens": 26746288} {"current_steps": 12395, "total_steps": 61300, "loss": 0.3592, "lr": 4.842638782485409e-05, "epoch": 2.0220228384991845, "percentage": 20.22, "elapsed_time": "1:41:31", "remaining_time": "6:40:33", "throughput": 4392.79, "total_tokens": 26757936} {"current_steps": 12400, "total_steps": 61300, "loss": 0.3395, "lr": 4.8423901415320486e-05, "epoch": 2.0228384991843393, "percentage": 20.23, "elapsed_time": "1:41:33", "remaining_time": "6:40:31", "throughput": 4392.98, "total_tokens": 26770256} {"current_steps": 12405, "total_steps": 61300, "loss": 0.3642, "lr": 4.8421413106926586e-05, "epoch": 2.023654159869494, "percentage": 20.24, "elapsed_time": "1:41:35", "remaining_time": "6:40:27", "throughput": 4393.12, "total_tokens": 26780240} {"current_steps": 12410, "total_steps": 61300, "loss": 0.3652, "lr": 4.841892289987409e-05, "epoch": 2.0244698205546494, "percentage": 20.24, "elapsed_time": "1:41:38", "remaining_time": "6:40:24", "throughput": 4393.3, "total_tokens": 26791824} {"current_steps": 12415, "total_steps": 61300, "loss": 0.3625, "lr": 4.841643079436489e-05, "epoch": 2.0252854812398042, "percentage": 20.25, "elapsed_time": "1:41:40", "remaining_time": "6:40:21", "throughput": 4393.45, "total_tokens": 26802576} {"current_steps": 12420, "total_steps": 61300, "loss": 0.3492, "lr": 4.841393679060099e-05, "epoch": 2.026101141924959, "percentage": 20.26, "elapsed_time": "1:41:42", "remaining_time": "6:40:18", "throughput": 4393.64, "total_tokens": 26814256} {"current_steps": 12425, "total_steps": 61300, "loss": 0.3583, "lr": 4.841144088878457e-05, "epoch": 2.0269168026101143, "percentage": 20.27, "elapsed_time": "1:41:45", "remaining_time": "6:40:15", "throughput": 4393.78, "total_tokens": 26824528} {"current_steps": 12430, "total_steps": 61300, "loss": 0.335, "lr": 4.8408943089117964e-05, "epoch": 2.027732463295269, "percentage": 20.28, "elapsed_time": "1:41:47", "remaining_time": "6:40:12", "throughput": 4393.97, "total_tokens": 26836816} {"current_steps": 12435, "total_steps": 61300, "loss": 0.3541, "lr": 4.840644339180366e-05, "epoch": 2.028548123980424, "percentage": 20.29, "elapsed_time": "1:41:49", "remaining_time": "6:40:08", "throughput": 4394.12, "total_tokens": 26846800} {"current_steps": 12440, "total_steps": 61300, "loss": 0.3694, "lr": 4.8403941797044286e-05, "epoch": 2.029363784665579, "percentage": 20.29, "elapsed_time": "1:41:52", "remaining_time": "6:40:06", "throughput": 4394.31, "total_tokens": 26858288} {"current_steps": 12445, "total_steps": 61300, "loss": 0.3484, "lr": 4.840143830504264e-05, "epoch": 2.030179445350734, "percentage": 20.3, "elapsed_time": "1:41:54", "remaining_time": "6:40:02", "throughput": 4394.43, "total_tokens": 26868624} {"current_steps": 12450, "total_steps": 61300, "loss": 0.3295, "lr": 4.839893291600167e-05, "epoch": 2.0309951060358893, "percentage": 20.31, "elapsed_time": "1:41:56", "remaining_time": "6:39:59", "throughput": 4394.58, "total_tokens": 26879536} {"current_steps": 12455, "total_steps": 61300, "loss": 0.4093, "lr": 4.839642563012447e-05, "epoch": 2.031810766721044, "percentage": 20.32, "elapsed_time": "1:41:58", "remaining_time": "6:39:56", "throughput": 4394.73, "total_tokens": 26890320} {"current_steps": 12460, "total_steps": 61300, "loss": 0.3018, "lr": 4.83939164476143e-05, "epoch": 2.032626427406199, "percentage": 20.33, "elapsed_time": "1:42:00", "remaining_time": "6:39:52", "throughput": 4394.85, "total_tokens": 26900784} {"current_steps": 12465, "total_steps": 61300, "loss": 0.3564, "lr": 4.839140536867456e-05, "epoch": 2.033442088091354, "percentage": 20.33, "elapsed_time": "1:42:03", "remaining_time": "6:39:50", "throughput": 4395.03, "total_tokens": 26912944} {"current_steps": 12470, "total_steps": 61300, "loss": 0.3684, "lr": 4.838889239350881e-05, "epoch": 2.034257748776509, "percentage": 20.34, "elapsed_time": "1:42:05", "remaining_time": "6:39:47", "throughput": 4395.2, "total_tokens": 26923792} {"current_steps": 12475, "total_steps": 61300, "loss": 0.3601, "lr": 4.838637752232078e-05, "epoch": 2.035073409461664, "percentage": 20.35, "elapsed_time": "1:42:08", "remaining_time": "6:39:44", "throughput": 4395.34, "total_tokens": 26934736} {"current_steps": 12480, "total_steps": 61300, "loss": 0.3395, "lr": 4.838386075531432e-05, "epoch": 2.035889070146819, "percentage": 20.36, "elapsed_time": "1:42:10", "remaining_time": "6:39:41", "throughput": 4395.49, "total_tokens": 26945840} {"current_steps": 12485, "total_steps": 61300, "loss": 0.339, "lr": 4.8381342092693464e-05, "epoch": 2.036704730831974, "percentage": 20.37, "elapsed_time": "1:42:12", "remaining_time": "6:39:37", "throughput": 4395.64, "total_tokens": 26956304} {"current_steps": 12490, "total_steps": 61300, "loss": 0.3558, "lr": 4.837882153466237e-05, "epoch": 2.0375203915171287, "percentage": 20.38, "elapsed_time": "1:42:14", "remaining_time": "6:39:34", "throughput": 4395.82, "total_tokens": 26967632} {"current_steps": 12495, "total_steps": 61300, "loss": 0.3607, "lr": 4.837629908142539e-05, "epoch": 2.038336052202284, "percentage": 20.38, "elapsed_time": "1:42:17", "remaining_time": "6:39:30", "throughput": 4395.98, "total_tokens": 26978160} {"current_steps": 12500, "total_steps": 61300, "loss": 0.3523, "lr": 4.837377473318699e-05, "epoch": 2.039151712887439, "percentage": 20.39, "elapsed_time": "1:42:18", "remaining_time": "6:39:26", "throughput": 4396.09, "total_tokens": 26987568} {"current_steps": 12505, "total_steps": 61300, "loss": 0.3503, "lr": 4.837124849015182e-05, "epoch": 2.0399673735725936, "percentage": 20.4, "elapsed_time": "1:42:21", "remaining_time": "6:39:24", "throughput": 4396.28, "total_tokens": 26999760} {"current_steps": 12510, "total_steps": 61300, "loss": 0.3622, "lr": 4.8368720352524655e-05, "epoch": 2.040783034257749, "percentage": 20.41, "elapsed_time": "1:42:23", "remaining_time": "6:39:22", "throughput": 4396.45, "total_tokens": 27011696} {"current_steps": 12515, "total_steps": 61300, "loss": 0.3449, "lr": 4.8366190320510454e-05, "epoch": 2.0415986949429037, "percentage": 20.42, "elapsed_time": "1:42:26", "remaining_time": "6:39:18", "throughput": 4396.6, "total_tokens": 27022608} {"current_steps": 12520, "total_steps": 61300, "loss": 0.3477, "lr": 4.83636583943143e-05, "epoch": 2.0424143556280585, "percentage": 20.42, "elapsed_time": "1:42:28", "remaining_time": "6:39:15", "throughput": 4396.76, "total_tokens": 27033680} {"current_steps": 12525, "total_steps": 61300, "loss": 0.3371, "lr": 4.8361124574141455e-05, "epoch": 2.0432300163132138, "percentage": 20.43, "elapsed_time": "1:42:30", "remaining_time": "6:39:13", "throughput": 4396.91, "total_tokens": 27045136} {"current_steps": 12530, "total_steps": 61300, "loss": 0.3718, "lr": 4.835858886019732e-05, "epoch": 2.0440456769983686, "percentage": 20.44, "elapsed_time": "1:42:33", "remaining_time": "6:39:09", "throughput": 4397.05, "total_tokens": 27055760} {"current_steps": 12535, "total_steps": 61300, "loss": 0.3481, "lr": 4.835605125268745e-05, "epoch": 2.044861337683524, "percentage": 20.45, "elapsed_time": "1:42:35", "remaining_time": "6:39:06", "throughput": 4397.22, "total_tokens": 27066352} {"current_steps": 12540, "total_steps": 61300, "loss": 0.3484, "lr": 4.835351175181755e-05, "epoch": 2.0456769983686787, "percentage": 20.46, "elapsed_time": "1:42:37", "remaining_time": "6:39:03", "throughput": 4397.36, "total_tokens": 27077872} {"current_steps": 12545, "total_steps": 61300, "loss": 0.3581, "lr": 4.83509703577935e-05, "epoch": 2.0464926590538335, "percentage": 20.46, "elapsed_time": "1:42:40", "remaining_time": "6:39:00", "throughput": 4397.53, "total_tokens": 27088912} {"current_steps": 12550, "total_steps": 61300, "loss": 0.3612, "lr": 4.834842707082131e-05, "epoch": 2.0473083197389887, "percentage": 20.47, "elapsed_time": "1:42:42", "remaining_time": "6:38:56", "throughput": 4397.7, "total_tokens": 27099216} {"current_steps": 12555, "total_steps": 61300, "loss": 0.331, "lr": 4.834588189110716e-05, "epoch": 2.0481239804241436, "percentage": 20.48, "elapsed_time": "1:42:44", "remaining_time": "6:38:52", "throughput": 4397.86, "total_tokens": 27109712} {"current_steps": 12560, "total_steps": 61300, "loss": 0.3263, "lr": 4.834333481885735e-05, "epoch": 2.0489396411092984, "percentage": 20.49, "elapsed_time": "1:42:46", "remaining_time": "6:38:49", "throughput": 4398.0, "total_tokens": 27120304} {"current_steps": 12565, "total_steps": 61300, "loss": 0.3483, "lr": 4.8340785854278395e-05, "epoch": 2.0497553017944536, "percentage": 20.5, "elapsed_time": "1:42:48", "remaining_time": "6:38:46", "throughput": 4398.15, "total_tokens": 27130992} {"current_steps": 12570, "total_steps": 61300, "loss": 0.3593, "lr": 4.83382349975769e-05, "epoch": 2.0505709624796085, "percentage": 20.51, "elapsed_time": "1:42:50", "remaining_time": "6:38:42", "throughput": 4398.32, "total_tokens": 27141136} {"current_steps": 12575, "total_steps": 61300, "loss": 0.3422, "lr": 4.833568224895967e-05, "epoch": 2.0513866231647633, "percentage": 20.51, "elapsed_time": "1:42:53", "remaining_time": "6:38:39", "throughput": 4398.47, "total_tokens": 27152208} {"current_steps": 12580, "total_steps": 61300, "loss": 0.3244, "lr": 4.833312760863362e-05, "epoch": 2.0522022838499185, "percentage": 20.52, "elapsed_time": "1:42:55", "remaining_time": "6:38:36", "throughput": 4398.65, "total_tokens": 27164016} {"current_steps": 12585, "total_steps": 61300, "loss": 0.357, "lr": 4.833057107680586e-05, "epoch": 2.0530179445350734, "percentage": 20.53, "elapsed_time": "1:42:57", "remaining_time": "6:38:33", "throughput": 4398.79, "total_tokens": 27174800} {"current_steps": 12590, "total_steps": 61300, "loss": 0.3415, "lr": 4.832801265368363e-05, "epoch": 2.053833605220228, "percentage": 20.54, "elapsed_time": "1:42:59", "remaining_time": "6:38:29", "throughput": 4398.91, "total_tokens": 27184784} {"current_steps": 12595, "total_steps": 61300, "loss": 0.3346, "lr": 4.832545233947433e-05, "epoch": 2.0546492659053834, "percentage": 20.55, "elapsed_time": "1:43:02", "remaining_time": "6:38:26", "throughput": 4399.06, "total_tokens": 27195600} {"current_steps": 12600, "total_steps": 61300, "loss": 0.3557, "lr": 4.832289013438551e-05, "epoch": 2.0554649265905383, "percentage": 20.55, "elapsed_time": "1:43:04", "remaining_time": "6:38:22", "throughput": 4399.24, "total_tokens": 27206416} {"current_steps": 12605, "total_steps": 61300, "loss": 0.3381, "lr": 4.8320326038624875e-05, "epoch": 2.0562805872756935, "percentage": 20.56, "elapsed_time": "1:43:06", "remaining_time": "6:38:19", "throughput": 4399.38, "total_tokens": 27217360} {"current_steps": 12610, "total_steps": 61300, "loss": 0.3232, "lr": 4.831776005240029e-05, "epoch": 2.0570962479608483, "percentage": 20.57, "elapsed_time": "1:43:08", "remaining_time": "6:38:16", "throughput": 4399.49, "total_tokens": 27228304} {"current_steps": 12615, "total_steps": 61300, "loss": 0.3531, "lr": 4.831519217591976e-05, "epoch": 2.057911908646003, "percentage": 20.58, "elapsed_time": "1:43:11", "remaining_time": "6:38:14", "throughput": 4399.65, "total_tokens": 27240208} {"current_steps": 12620, "total_steps": 61300, "loss": 0.3393, "lr": 4.831262240939144e-05, "epoch": 2.0587275693311584, "percentage": 20.59, "elapsed_time": "1:43:13", "remaining_time": "6:38:10", "throughput": 4399.76, "total_tokens": 27250256} {"current_steps": 12625, "total_steps": 61300, "loss": 0.3839, "lr": 4.8310050753023674e-05, "epoch": 2.0595432300163132, "percentage": 20.6, "elapsed_time": "1:43:15", "remaining_time": "6:38:06", "throughput": 4399.89, "total_tokens": 27260080} {"current_steps": 12630, "total_steps": 61300, "loss": 0.3363, "lr": 4.8307477207024923e-05, "epoch": 2.060358890701468, "percentage": 20.6, "elapsed_time": "1:43:18", "remaining_time": "6:38:04", "throughput": 4400.08, "total_tokens": 27272112} {"current_steps": 12635, "total_steps": 61300, "loss": 0.3449, "lr": 4.83049017716038e-05, "epoch": 2.0611745513866233, "percentage": 20.61, "elapsed_time": "1:43:20", "remaining_time": "6:38:00", "throughput": 4400.24, "total_tokens": 27282672} {"current_steps": 12640, "total_steps": 61300, "loss": 0.3462, "lr": 4.8302324446969094e-05, "epoch": 2.061990212071778, "percentage": 20.62, "elapsed_time": "1:43:22", "remaining_time": "6:37:58", "throughput": 4400.41, "total_tokens": 27294704} {"current_steps": 12645, "total_steps": 61300, "loss": 0.333, "lr": 4.829974523332973e-05, "epoch": 2.062805872756933, "percentage": 20.63, "elapsed_time": "1:43:25", "remaining_time": "6:37:56", "throughput": 4400.58, "total_tokens": 27306320} {"current_steps": 12650, "total_steps": 61300, "loss": 0.3112, "lr": 4.8297164130894804e-05, "epoch": 2.063621533442088, "percentage": 20.64, "elapsed_time": "1:43:27", "remaining_time": "6:37:52", "throughput": 4400.69, "total_tokens": 27316720} {"current_steps": 12655, "total_steps": 61300, "loss": 0.3453, "lr": 4.8294581139873544e-05, "epoch": 2.064437194127243, "percentage": 20.64, "elapsed_time": "1:43:29", "remaining_time": "6:37:49", "throughput": 4400.83, "total_tokens": 27327408} {"current_steps": 12660, "total_steps": 61300, "loss": 0.3373, "lr": 4.829199626047534e-05, "epoch": 2.065252854812398, "percentage": 20.65, "elapsed_time": "1:43:31", "remaining_time": "6:37:46", "throughput": 4401.01, "total_tokens": 27338672} {"current_steps": 12665, "total_steps": 61300, "loss": 0.3912, "lr": 4.8289409492909726e-05, "epoch": 2.066068515497553, "percentage": 20.66, "elapsed_time": "1:43:34", "remaining_time": "6:37:43", "throughput": 4401.17, "total_tokens": 27350352} {"current_steps": 12670, "total_steps": 61300, "loss": 0.3202, "lr": 4.8286820837386416e-05, "epoch": 2.066884176182708, "percentage": 20.67, "elapsed_time": "1:43:36", "remaining_time": "6:37:39", "throughput": 4401.31, "total_tokens": 27360432} {"current_steps": 12675, "total_steps": 61300, "loss": 0.3699, "lr": 4.828423029411526e-05, "epoch": 2.067699836867863, "percentage": 20.68, "elapsed_time": "1:43:38", "remaining_time": "6:37:35", "throughput": 4401.41, "total_tokens": 27369840} {"current_steps": 12680, "total_steps": 61300, "loss": 0.3524, "lr": 4.828163786330624e-05, "epoch": 2.068515497553018, "percentage": 20.69, "elapsed_time": "1:43:40", "remaining_time": "6:37:31", "throughput": 4401.54, "total_tokens": 27380016} {"current_steps": 12685, "total_steps": 61300, "loss": 0.3568, "lr": 4.8279043545169535e-05, "epoch": 2.069331158238173, "percentage": 20.69, "elapsed_time": "1:43:42", "remaining_time": "6:37:29", "throughput": 4401.7, "total_tokens": 27391504} {"current_steps": 12690, "total_steps": 61300, "loss": 0.3179, "lr": 4.8276447339915446e-05, "epoch": 2.070146818923328, "percentage": 20.7, "elapsed_time": "1:43:45", "remaining_time": "6:37:25", "throughput": 4401.84, "total_tokens": 27402064} {"current_steps": 12695, "total_steps": 61300, "loss": 0.345, "lr": 4.827384924775442e-05, "epoch": 2.070962479608483, "percentage": 20.71, "elapsed_time": "1:43:47", "remaining_time": "6:37:23", "throughput": 4401.99, "total_tokens": 27413808} {"current_steps": 12700, "total_steps": 61300, "loss": 0.3434, "lr": 4.8271249268897094e-05, "epoch": 2.0717781402936377, "percentage": 20.72, "elapsed_time": "1:43:50", "remaining_time": "6:37:20", "throughput": 4402.17, "total_tokens": 27425520} {"current_steps": 12705, "total_steps": 61300, "loss": 0.3703, "lr": 4.826864740355422e-05, "epoch": 2.072593800978793, "percentage": 20.73, "elapsed_time": "1:43:52", "remaining_time": "6:37:17", "throughput": 4402.31, "total_tokens": 27436624} {"current_steps": 12710, "total_steps": 61300, "loss": 0.3538, "lr": 4.826604365193673e-05, "epoch": 2.073409461663948, "percentage": 20.73, "elapsed_time": "1:43:54", "remaining_time": "6:37:15", "throughput": 4402.49, "total_tokens": 27448176} {"current_steps": 12715, "total_steps": 61300, "loss": 0.3409, "lr": 4.8263438014255687e-05, "epoch": 2.0742251223491026, "percentage": 20.74, "elapsed_time": "1:43:57", "remaining_time": "6:37:12", "throughput": 4402.67, "total_tokens": 27459568} {"current_steps": 12720, "total_steps": 61300, "loss": 0.3105, "lr": 4.8260830490722317e-05, "epoch": 2.075040783034258, "percentage": 20.75, "elapsed_time": "1:43:59", "remaining_time": "6:37:09", "throughput": 4402.82, "total_tokens": 27470800} {"current_steps": 12725, "total_steps": 61300, "loss": 0.3208, "lr": 4.8258221081548004e-05, "epoch": 2.0758564437194127, "percentage": 20.76, "elapsed_time": "1:44:01", "remaining_time": "6:37:05", "throughput": 4402.96, "total_tokens": 27481168} {"current_steps": 12730, "total_steps": 61300, "loss": 0.3582, "lr": 4.825560978694429e-05, "epoch": 2.0766721044045675, "percentage": 20.77, "elapsed_time": "1:44:03", "remaining_time": "6:37:02", "throughput": 4403.12, "total_tokens": 27492528} {"current_steps": 12735, "total_steps": 61300, "loss": 0.3096, "lr": 4.8252996607122835e-05, "epoch": 2.0774877650897228, "percentage": 20.77, "elapsed_time": "1:44:06", "remaining_time": "6:36:59", "throughput": 4403.28, "total_tokens": 27503152} {"current_steps": 12740, "total_steps": 61300, "loss": 0.3626, "lr": 4.82503815422955e-05, "epoch": 2.0783034257748776, "percentage": 20.78, "elapsed_time": "1:44:08", "remaining_time": "6:36:56", "throughput": 4403.43, "total_tokens": 27513904} {"current_steps": 12745, "total_steps": 61300, "loss": 0.3341, "lr": 4.824776459267426e-05, "epoch": 2.0791190864600324, "percentage": 20.79, "elapsed_time": "1:44:10", "remaining_time": "6:36:53", "throughput": 4403.6, "total_tokens": 27525648} {"current_steps": 12750, "total_steps": 61300, "loss": 0.3574, "lr": 4.824514575847127e-05, "epoch": 2.0799347471451877, "percentage": 20.8, "elapsed_time": "1:44:13", "remaining_time": "6:36:51", "throughput": 4403.74, "total_tokens": 27537264} {"current_steps": 12755, "total_steps": 61300, "loss": 0.3403, "lr": 4.824252503989881e-05, "epoch": 2.0807504078303425, "percentage": 20.81, "elapsed_time": "1:44:15", "remaining_time": "6:36:47", "throughput": 4403.89, "total_tokens": 27548144} {"current_steps": 12760, "total_steps": 61300, "loss": 0.3398, "lr": 4.823990243716935e-05, "epoch": 2.0815660685154977, "percentage": 20.82, "elapsed_time": "1:44:17", "remaining_time": "6:36:45", "throughput": 4404.05, "total_tokens": 27559568} {"current_steps": 12765, "total_steps": 61300, "loss": 0.3722, "lr": 4.823727795049548e-05, "epoch": 2.0823817292006526, "percentage": 20.82, "elapsed_time": "1:44:20", "remaining_time": "6:36:41", "throughput": 4404.22, "total_tokens": 27570544} {"current_steps": 12770, "total_steps": 61300, "loss": 0.3726, "lr": 4.8234651580089945e-05, "epoch": 2.0831973898858074, "percentage": 20.83, "elapsed_time": "1:44:22", "remaining_time": "6:36:38", "throughput": 4404.38, "total_tokens": 27581616} {"current_steps": 12775, "total_steps": 61300, "loss": 0.3619, "lr": 4.823202332616567e-05, "epoch": 2.0840130505709626, "percentage": 20.84, "elapsed_time": "1:44:24", "remaining_time": "6:36:35", "throughput": 4404.53, "total_tokens": 27592112} {"current_steps": 12780, "total_steps": 61300, "loss": 0.3585, "lr": 4.8229393188935703e-05, "epoch": 2.0848287112561175, "percentage": 20.85, "elapsed_time": "1:44:26", "remaining_time": "6:36:32", "throughput": 4404.69, "total_tokens": 27603056} {"current_steps": 12785, "total_steps": 61300, "loss": 0.3377, "lr": 4.8226761168613255e-05, "epoch": 2.0856443719412723, "percentage": 20.86, "elapsed_time": "1:44:28", "remaining_time": "6:36:28", "throughput": 4404.81, "total_tokens": 27613616} {"current_steps": 12790, "total_steps": 61300, "loss": 0.3366, "lr": 4.82241272654117e-05, "epoch": 2.0864600326264275, "percentage": 20.86, "elapsed_time": "1:44:31", "remaining_time": "6:36:25", "throughput": 4404.94, "total_tokens": 27624784} {"current_steps": 12795, "total_steps": 61300, "loss": 0.3137, "lr": 4.822149147954455e-05, "epoch": 2.0872756933115824, "percentage": 20.87, "elapsed_time": "1:44:33", "remaining_time": "6:36:23", "throughput": 4405.07, "total_tokens": 27636048} {"current_steps": 12800, "total_steps": 61300, "loss": 0.3504, "lr": 4.8218853811225475e-05, "epoch": 2.088091353996737, "percentage": 20.88, "elapsed_time": "1:44:35", "remaining_time": "6:36:18", "throughput": 4405.21, "total_tokens": 27645328} {"current_steps": 12805, "total_steps": 61300, "loss": 0.3372, "lr": 4.8216214260668304e-05, "epoch": 2.0889070146818924, "percentage": 20.89, "elapsed_time": "1:44:37", "remaining_time": "6:36:14", "throughput": 4405.33, "total_tokens": 27655024} {"current_steps": 12810, "total_steps": 61300, "loss": 0.4207, "lr": 4.8213572828087e-05, "epoch": 2.0897226753670473, "percentage": 20.9, "elapsed_time": "1:44:39", "remaining_time": "6:36:11", "throughput": 4405.46, "total_tokens": 27666224} {"current_steps": 12815, "total_steps": 61300, "loss": 0.3351, "lr": 4.82109295136957e-05, "epoch": 2.090538336052202, "percentage": 20.91, "elapsed_time": "1:44:42", "remaining_time": "6:36:09", "throughput": 4405.62, "total_tokens": 27677904} {"current_steps": 12820, "total_steps": 61300, "loss": 0.3625, "lr": 4.820828431770868e-05, "epoch": 2.0913539967373573, "percentage": 20.91, "elapsed_time": "1:44:44", "remaining_time": "6:36:04", "throughput": 4405.75, "total_tokens": 27687088} {"current_steps": 12825, "total_steps": 61300, "loss": 0.344, "lr": 4.820563724034039e-05, "epoch": 2.092169657422512, "percentage": 20.92, "elapsed_time": "1:44:46", "remaining_time": "6:36:00", "throughput": 4405.85, "total_tokens": 27697008} {"current_steps": 12830, "total_steps": 61300, "loss": 0.3428, "lr": 4.820298828180538e-05, "epoch": 2.0929853181076674, "percentage": 20.93, "elapsed_time": "1:44:48", "remaining_time": "6:35:58", "throughput": 4405.99, "total_tokens": 27708208} {"current_steps": 12835, "total_steps": 61300, "loss": 0.3362, "lr": 4.8200337442318424e-05, "epoch": 2.0938009787928222, "percentage": 20.94, "elapsed_time": "1:44:50", "remaining_time": "6:35:54", "throughput": 4406.13, "total_tokens": 27718704} {"current_steps": 12840, "total_steps": 61300, "loss": 0.373, "lr": 4.819768472209439e-05, "epoch": 2.094616639477977, "percentage": 20.95, "elapsed_time": "1:44:53", "remaining_time": "6:35:50", "throughput": 4406.25, "total_tokens": 27728816} {"current_steps": 12845, "total_steps": 61300, "loss": 0.3602, "lr": 4.8195030121348336e-05, "epoch": 2.0954323001631323, "percentage": 20.95, "elapsed_time": "1:44:55", "remaining_time": "6:35:47", "throughput": 4406.38, "total_tokens": 27738992} {"current_steps": 12850, "total_steps": 61300, "loss": 0.3618, "lr": 4.819237364029544e-05, "epoch": 2.096247960848287, "percentage": 20.96, "elapsed_time": "1:44:57", "remaining_time": "6:35:44", "throughput": 4406.51, "total_tokens": 27750384} {"current_steps": 12855, "total_steps": 61300, "loss": 0.3301, "lr": 4.818971527915107e-05, "epoch": 2.097063621533442, "percentage": 20.97, "elapsed_time": "1:44:59", "remaining_time": "6:35:41", "throughput": 4406.65, "total_tokens": 27760784} {"current_steps": 12860, "total_steps": 61300, "loss": 0.35, "lr": 4.818705503813071e-05, "epoch": 2.097879282218597, "percentage": 20.98, "elapsed_time": "1:45:02", "remaining_time": "6:35:38", "throughput": 4406.8, "total_tokens": 27771952} {"current_steps": 12865, "total_steps": 61300, "loss": 0.3703, "lr": 4.818439291745002e-05, "epoch": 2.098694942903752, "percentage": 20.99, "elapsed_time": "1:45:04", "remaining_time": "6:35:34", "throughput": 4406.92, "total_tokens": 27781744} {"current_steps": 12870, "total_steps": 61300, "loss": 0.3507, "lr": 4.81817289173248e-05, "epoch": 2.099510603588907, "percentage": 21.0, "elapsed_time": "1:45:06", "remaining_time": "6:35:31", "throughput": 4407.07, "total_tokens": 27792944} {"current_steps": 12875, "total_steps": 61300, "loss": 0.3422, "lr": 4.8179063037971016e-05, "epoch": 2.100326264274062, "percentage": 21.0, "elapsed_time": "1:45:08", "remaining_time": "6:35:28", "throughput": 4407.23, "total_tokens": 27804048} {"current_steps": 12880, "total_steps": 61300, "loss": 0.3355, "lr": 4.817639527960477e-05, "epoch": 2.101141924959217, "percentage": 21.01, "elapsed_time": "1:45:11", "remaining_time": "6:35:25", "throughput": 4407.37, "total_tokens": 27814960} {"current_steps": 12885, "total_steps": 61300, "loss": 0.372, "lr": 4.817372564244233e-05, "epoch": 2.1019575856443717, "percentage": 21.02, "elapsed_time": "1:45:13", "remaining_time": "6:35:22", "throughput": 4407.56, "total_tokens": 27827280} {"current_steps": 12890, "total_steps": 61300, "loss": 0.326, "lr": 4.817105412670011e-05, "epoch": 2.102773246329527, "percentage": 21.03, "elapsed_time": "1:45:15", "remaining_time": "6:35:19", "throughput": 4407.68, "total_tokens": 27837520} {"current_steps": 12895, "total_steps": 61300, "loss": 0.3224, "lr": 4.8168380732594666e-05, "epoch": 2.103588907014682, "percentage": 21.04, "elapsed_time": "1:45:18", "remaining_time": "6:35:16", "throughput": 4407.82, "total_tokens": 27848912} {"current_steps": 12900, "total_steps": 61300, "loss": 0.3325, "lr": 4.816570546034273e-05, "epoch": 2.104404567699837, "percentage": 21.04, "elapsed_time": "1:45:20", "remaining_time": "6:35:13", "throughput": 4407.96, "total_tokens": 27859504} {"current_steps": 12905, "total_steps": 61300, "loss": 0.3918, "lr": 4.816302831016116e-05, "epoch": 2.105220228384992, "percentage": 21.05, "elapsed_time": "1:45:22", "remaining_time": "6:35:10", "throughput": 4408.11, "total_tokens": 27870736} {"current_steps": 12910, "total_steps": 61300, "loss": 0.3269, "lr": 4.8160349282266995e-05, "epoch": 2.1060358890701467, "percentage": 21.06, "elapsed_time": "1:45:24", "remaining_time": "6:35:06", "throughput": 4408.25, "total_tokens": 27880720} {"current_steps": 12915, "total_steps": 61300, "loss": 0.3345, "lr": 4.81576683768774e-05, "epoch": 2.106851549755302, "percentage": 21.07, "elapsed_time": "1:45:27", "remaining_time": "6:35:03", "throughput": 4408.39, "total_tokens": 27892048} {"current_steps": 12920, "total_steps": 61300, "loss": 0.3893, "lr": 4.81549855942097e-05, "epoch": 2.107667210440457, "percentage": 21.08, "elapsed_time": "1:45:29", "remaining_time": "6:35:01", "throughput": 4408.57, "total_tokens": 27903760} {"current_steps": 12925, "total_steps": 61300, "loss": 0.3552, "lr": 4.8152300934481384e-05, "epoch": 2.1084828711256116, "percentage": 21.08, "elapsed_time": "1:45:31", "remaining_time": "6:34:57", "throughput": 4408.7, "total_tokens": 27914192} {"current_steps": 12930, "total_steps": 61300, "loss": 0.3554, "lr": 4.8149614397910094e-05, "epoch": 2.109298531810767, "percentage": 21.09, "elapsed_time": "1:45:34", "remaining_time": "6:34:55", "throughput": 4408.87, "total_tokens": 27925936} {"current_steps": 12935, "total_steps": 61300, "loss": 0.3443, "lr": 4.8146925984713585e-05, "epoch": 2.1101141924959217, "percentage": 21.1, "elapsed_time": "1:45:36", "remaining_time": "6:34:52", "throughput": 4409.01, "total_tokens": 27937392} {"current_steps": 12940, "total_steps": 61300, "loss": 0.3158, "lr": 4.814423569510981e-05, "epoch": 2.1109298531810765, "percentage": 21.11, "elapsed_time": "1:45:38", "remaining_time": "6:34:49", "throughput": 4409.14, "total_tokens": 27948304} {"current_steps": 12945, "total_steps": 61300, "loss": 0.3393, "lr": 4.814154352931687e-05, "epoch": 2.1117455138662318, "percentage": 21.12, "elapsed_time": "1:45:41", "remaining_time": "6:34:46", "throughput": 4409.27, "total_tokens": 27959344} {"current_steps": 12950, "total_steps": 61300, "loss": 0.3569, "lr": 4.813884948755298e-05, "epoch": 2.1125611745513866, "percentage": 21.13, "elapsed_time": "1:45:43", "remaining_time": "6:34:43", "throughput": 4409.41, "total_tokens": 27970032} {"current_steps": 12955, "total_steps": 61300, "loss": 0.3535, "lr": 4.8136153570036544e-05, "epoch": 2.1133768352365414, "percentage": 21.13, "elapsed_time": "1:45:45", "remaining_time": "6:34:39", "throughput": 4409.57, "total_tokens": 27979984} {"current_steps": 12960, "total_steps": 61300, "loss": 0.3514, "lr": 4.8133455776986114e-05, "epoch": 2.1141924959216967, "percentage": 21.14, "elapsed_time": "1:45:47", "remaining_time": "6:34:34", "throughput": 4409.67, "total_tokens": 27989200} {"current_steps": 12965, "total_steps": 61300, "loss": 0.3146, "lr": 4.813075610862038e-05, "epoch": 2.1150081566068515, "percentage": 21.15, "elapsed_time": "1:45:49", "remaining_time": "6:34:31", "throughput": 4409.83, "total_tokens": 28000432} {"current_steps": 12970, "total_steps": 61300, "loss": 0.3666, "lr": 4.8128054565158196e-05, "epoch": 2.1158238172920063, "percentage": 21.16, "elapsed_time": "1:45:51", "remaining_time": "6:34:27", "throughput": 4409.99, "total_tokens": 28010064} {"current_steps": 12975, "total_steps": 61300, "loss": 0.3693, "lr": 4.8125351146818556e-05, "epoch": 2.1166394779771616, "percentage": 21.17, "elapsed_time": "1:45:53", "remaining_time": "6:34:24", "throughput": 4410.16, "total_tokens": 28021776} {"current_steps": 12980, "total_steps": 61300, "loss": 0.3502, "lr": 4.8122645853820604e-05, "epoch": 2.1174551386623164, "percentage": 21.17, "elapsed_time": "1:45:56", "remaining_time": "6:34:21", "throughput": 4410.3, "total_tokens": 28032656} {"current_steps": 12985, "total_steps": 61300, "loss": 0.3226, "lr": 4.811993868638367e-05, "epoch": 2.1182707993474716, "percentage": 21.18, "elapsed_time": "1:45:58", "remaining_time": "6:34:18", "throughput": 4410.44, "total_tokens": 28043728} {"current_steps": 12990, "total_steps": 61300, "loss": 0.3295, "lr": 4.811722964472719e-05, "epoch": 2.1190864600326265, "percentage": 21.19, "elapsed_time": "1:46:00", "remaining_time": "6:34:15", "throughput": 4410.63, "total_tokens": 28055120} {"current_steps": 12995, "total_steps": 61300, "loss": 0.3464, "lr": 4.811451872907078e-05, "epoch": 2.1199021207177813, "percentage": 21.2, "elapsed_time": "1:46:03", "remaining_time": "6:34:12", "throughput": 4410.79, "total_tokens": 28065936} {"current_steps": 13000, "total_steps": 61300, "loss": 0.3414, "lr": 4.8111805939634204e-05, "epoch": 2.1207177814029365, "percentage": 21.21, "elapsed_time": "1:46:05", "remaining_time": "6:34:09", "throughput": 4410.93, "total_tokens": 28077040} {"current_steps": 13005, "total_steps": 61300, "loss": 0.3221, "lr": 4.810909127663736e-05, "epoch": 2.1215334420880914, "percentage": 21.22, "elapsed_time": "1:46:07", "remaining_time": "6:34:06", "throughput": 4411.11, "total_tokens": 28088624} {"current_steps": 13010, "total_steps": 61300, "loss": 0.3649, "lr": 4.810637474030033e-05, "epoch": 2.122349102773246, "percentage": 21.22, "elapsed_time": "1:46:09", "remaining_time": "6:34:02", "throughput": 4411.21, "total_tokens": 28097520} {"current_steps": 13015, "total_steps": 61300, "loss": 0.3607, "lr": 4.810365633084333e-05, "epoch": 2.1231647634584014, "percentage": 21.23, "elapsed_time": "1:46:11", "remaining_time": "6:33:58", "throughput": 4411.34, "total_tokens": 28107504} {"current_steps": 13020, "total_steps": 61300, "loss": 0.3356, "lr": 4.810093604848671e-05, "epoch": 2.1239804241435563, "percentage": 21.24, "elapsed_time": "1:46:13", "remaining_time": "6:33:55", "throughput": 4411.47, "total_tokens": 28118352} {"current_steps": 13025, "total_steps": 61300, "loss": 0.33, "lr": 4.8098213893451005e-05, "epoch": 2.124796084828711, "percentage": 21.25, "elapsed_time": "1:46:16", "remaining_time": "6:33:52", "throughput": 4411.61, "total_tokens": 28129936} {"current_steps": 13030, "total_steps": 61300, "loss": 0.3618, "lr": 4.809548986595688e-05, "epoch": 2.1256117455138663, "percentage": 21.26, "elapsed_time": "1:46:18", "remaining_time": "6:33:49", "throughput": 4411.74, "total_tokens": 28140496} {"current_steps": 13035, "total_steps": 61300, "loss": 0.3274, "lr": 4.809276396622516e-05, "epoch": 2.126427406199021, "percentage": 21.26, "elapsed_time": "1:46:20", "remaining_time": "6:33:46", "throughput": 4411.9, "total_tokens": 28151440} {"current_steps": 13040, "total_steps": 61300, "loss": 0.3575, "lr": 4.809003619447683e-05, "epoch": 2.1272430668841764, "percentage": 21.27, "elapsed_time": "1:46:22", "remaining_time": "6:33:42", "throughput": 4411.99, "total_tokens": 28161200} {"current_steps": 13045, "total_steps": 61300, "loss": 0.3624, "lr": 4.8087306550932996e-05, "epoch": 2.1280587275693312, "percentage": 21.28, "elapsed_time": "1:46:25", "remaining_time": "6:33:38", "throughput": 4412.14, "total_tokens": 28171568} {"current_steps": 13050, "total_steps": 61300, "loss": 0.3397, "lr": 4.808457503581496e-05, "epoch": 2.128874388254486, "percentage": 21.29, "elapsed_time": "1:46:27", "remaining_time": "6:33:36", "throughput": 4412.32, "total_tokens": 28183344} {"current_steps": 13055, "total_steps": 61300, "loss": 0.3473, "lr": 4.808184164934414e-05, "epoch": 2.1296900489396413, "percentage": 21.3, "elapsed_time": "1:46:29", "remaining_time": "6:33:32", "throughput": 4412.45, "total_tokens": 28193552} {"current_steps": 13060, "total_steps": 61300, "loss": 0.3502, "lr": 4.8079106391742115e-05, "epoch": 2.130505709624796, "percentage": 21.31, "elapsed_time": "1:46:31", "remaining_time": "6:33:29", "throughput": 4412.56, "total_tokens": 28203600} {"current_steps": 13065, "total_steps": 61300, "loss": 0.3459, "lr": 4.807636926323063e-05, "epoch": 2.131321370309951, "percentage": 21.31, "elapsed_time": "1:46:33", "remaining_time": "6:33:25", "throughput": 4412.71, "total_tokens": 28213584} {"current_steps": 13070, "total_steps": 61300, "loss": 0.3575, "lr": 4.8073630264031556e-05, "epoch": 2.132137030995106, "percentage": 21.32, "elapsed_time": "1:46:35", "remaining_time": "6:33:21", "throughput": 4412.84, "total_tokens": 28224016} {"current_steps": 13075, "total_steps": 61300, "loss": 0.3266, "lr": 4.807088939436695e-05, "epoch": 2.132952691680261, "percentage": 21.33, "elapsed_time": "1:46:38", "remaining_time": "6:33:19", "throughput": 4412.98, "total_tokens": 28235760} {"current_steps": 13080, "total_steps": 61300, "loss": 0.362, "lr": 4.806814665445898e-05, "epoch": 2.133768352365416, "percentage": 21.34, "elapsed_time": "1:46:40", "remaining_time": "6:33:14", "throughput": 4413.1, "total_tokens": 28244656} {"current_steps": 13085, "total_steps": 61300, "loss": 0.3539, "lr": 4.8065402044529994e-05, "epoch": 2.134584013050571, "percentage": 21.35, "elapsed_time": "1:46:42", "remaining_time": "6:33:10", "throughput": 4413.21, "total_tokens": 28254096} {"current_steps": 13090, "total_steps": 61300, "loss": 0.3664, "lr": 4.806265556480249e-05, "epoch": 2.135399673735726, "percentage": 21.35, "elapsed_time": "1:46:44", "remaining_time": "6:33:07", "throughput": 4413.35, "total_tokens": 28264880} {"current_steps": 13095, "total_steps": 61300, "loss": 0.3551, "lr": 4.80599072154991e-05, "epoch": 2.1362153344208807, "percentage": 21.36, "elapsed_time": "1:46:46", "remaining_time": "6:33:03", "throughput": 4413.48, "total_tokens": 28274448} {"current_steps": 13100, "total_steps": 61300, "loss": 0.3227, "lr": 4.805715699684264e-05, "epoch": 2.137030995106036, "percentage": 21.37, "elapsed_time": "1:46:48", "remaining_time": "6:33:00", "throughput": 4413.64, "total_tokens": 28285776} {"current_steps": 13105, "total_steps": 61300, "loss": 0.3445, "lr": 4.8054404909056036e-05, "epoch": 2.137846655791191, "percentage": 21.38, "elapsed_time": "1:46:50", "remaining_time": "6:32:56", "throughput": 4413.77, "total_tokens": 28296016} {"current_steps": 13110, "total_steps": 61300, "loss": 0.3317, "lr": 4.805165095236239e-05, "epoch": 2.1386623164763456, "percentage": 21.39, "elapsed_time": "1:46:53", "remaining_time": "6:32:54", "throughput": 4413.95, "total_tokens": 28307952} {"current_steps": 13115, "total_steps": 61300, "loss": 0.3383, "lr": 4.804889512698496e-05, "epoch": 2.139477977161501, "percentage": 21.39, "elapsed_time": "1:46:55", "remaining_time": "6:32:51", "throughput": 4414.1, "total_tokens": 28318960} {"current_steps": 13120, "total_steps": 61300, "loss": 0.3615, "lr": 4.804613743314714e-05, "epoch": 2.1402936378466557, "percentage": 21.4, "elapsed_time": "1:46:57", "remaining_time": "6:32:47", "throughput": 4414.24, "total_tokens": 28329136} {"current_steps": 13125, "total_steps": 61300, "loss": 0.3372, "lr": 4.804337787107248e-05, "epoch": 2.141109298531811, "percentage": 21.41, "elapsed_time": "1:46:59", "remaining_time": "6:32:44", "throughput": 4414.37, "total_tokens": 28339696} {"current_steps": 13130, "total_steps": 61300, "loss": 0.3523, "lr": 4.80406164409847e-05, "epoch": 2.141924959216966, "percentage": 21.42, "elapsed_time": "1:47:02", "remaining_time": "6:32:41", "throughput": 4414.51, "total_tokens": 28351440} {"current_steps": 13135, "total_steps": 61300, "loss": 0.3727, "lr": 4.8037853143107634e-05, "epoch": 2.1427406199021206, "percentage": 21.43, "elapsed_time": "1:47:04", "remaining_time": "6:32:37", "throughput": 4414.64, "total_tokens": 28361232} {"current_steps": 13140, "total_steps": 61300, "loss": 0.326, "lr": 4.8035087977665304e-05, "epoch": 2.143556280587276, "percentage": 21.44, "elapsed_time": "1:47:06", "remaining_time": "6:32:33", "throughput": 4414.74, "total_tokens": 28370864} {"current_steps": 13145, "total_steps": 61300, "loss": 0.348, "lr": 4.803232094488186e-05, "epoch": 2.1443719412724307, "percentage": 21.44, "elapsed_time": "1:47:08", "remaining_time": "6:32:30", "throughput": 4414.87, "total_tokens": 28381456} {"current_steps": 13150, "total_steps": 61300, "loss": 0.3124, "lr": 4.802955204498162e-05, "epoch": 2.1451876019575855, "percentage": 21.45, "elapsed_time": "1:47:10", "remaining_time": "6:32:26", "throughput": 4414.99, "total_tokens": 28391600} {"current_steps": 13155, "total_steps": 61300, "loss": 0.3926, "lr": 4.802678127818904e-05, "epoch": 2.1460032626427408, "percentage": 21.46, "elapsed_time": "1:47:13", "remaining_time": "6:32:23", "throughput": 4415.13, "total_tokens": 28402640} {"current_steps": 13160, "total_steps": 61300, "loss": 0.3185, "lr": 4.802400864472873e-05, "epoch": 2.1468189233278956, "percentage": 21.47, "elapsed_time": "1:47:15", "remaining_time": "6:32:19", "throughput": 4415.23, "total_tokens": 28412272} {"current_steps": 13165, "total_steps": 61300, "loss": 0.3448, "lr": 4.8021234144825456e-05, "epoch": 2.1476345840130504, "percentage": 21.48, "elapsed_time": "1:47:17", "remaining_time": "6:32:16", "throughput": 4415.39, "total_tokens": 28423312} {"current_steps": 13170, "total_steps": 61300, "loss": 0.3502, "lr": 4.801845777870414e-05, "epoch": 2.1484502446982057, "percentage": 21.48, "elapsed_time": "1:47:19", "remaining_time": "6:32:13", "throughput": 4415.51, "total_tokens": 28433424} {"current_steps": 13175, "total_steps": 61300, "loss": 0.3597, "lr": 4.801567954658984e-05, "epoch": 2.1492659053833605, "percentage": 21.49, "elapsed_time": "1:47:21", "remaining_time": "6:32:09", "throughput": 4415.66, "total_tokens": 28443984} {"current_steps": 13180, "total_steps": 61300, "loss": 0.3806, "lr": 4.801289944870777e-05, "epoch": 2.1500815660685153, "percentage": 21.5, "elapsed_time": "1:47:23", "remaining_time": "6:32:06", "throughput": 4415.77, "total_tokens": 28454832} {"current_steps": 13185, "total_steps": 61300, "loss": 0.3438, "lr": 4.8010117485283305e-05, "epoch": 2.1508972267536706, "percentage": 21.51, "elapsed_time": "1:47:26", "remaining_time": "6:32:04", "throughput": 4415.94, "total_tokens": 28467280} {"current_steps": 13190, "total_steps": 61300, "loss": 0.3366, "lr": 4.800733365654197e-05, "epoch": 2.1517128874388254, "percentage": 21.52, "elapsed_time": "1:47:28", "remaining_time": "6:32:01", "throughput": 4416.06, "total_tokens": 28478128} {"current_steps": 13195, "total_steps": 61300, "loss": 0.3615, "lr": 4.8004547962709424e-05, "epoch": 2.15252854812398, "percentage": 21.53, "elapsed_time": "1:47:31", "remaining_time": "6:31:58", "throughput": 4416.22, "total_tokens": 28489200} {"current_steps": 13200, "total_steps": 61300, "loss": 0.381, "lr": 4.80017604040115e-05, "epoch": 2.1533442088091355, "percentage": 21.53, "elapsed_time": "1:47:33", "remaining_time": "6:31:55", "throughput": 4416.35, "total_tokens": 28500240} {"current_steps": 13205, "total_steps": 61300, "loss": 0.3592, "lr": 4.799897098067417e-05, "epoch": 2.1541598694942903, "percentage": 21.54, "elapsed_time": "1:47:35", "remaining_time": "6:31:53", "throughput": 4416.49, "total_tokens": 28511824} {"current_steps": 13210, "total_steps": 61300, "loss": 0.3435, "lr": 4.799617969292355e-05, "epoch": 2.1549755301794455, "percentage": 21.55, "elapsed_time": "1:47:37", "remaining_time": "6:31:48", "throughput": 4416.62, "total_tokens": 28521456} {"current_steps": 13215, "total_steps": 61300, "loss": 0.332, "lr": 4.799338654098593e-05, "epoch": 2.1557911908646004, "percentage": 21.56, "elapsed_time": "1:47:39", "remaining_time": "6:31:45", "throughput": 4416.76, "total_tokens": 28531888} {"current_steps": 13220, "total_steps": 61300, "loss": 0.3376, "lr": 4.799059152508773e-05, "epoch": 2.156606851549755, "percentage": 21.57, "elapsed_time": "1:47:41", "remaining_time": "6:31:41", "throughput": 4416.87, "total_tokens": 28541616} {"current_steps": 13225, "total_steps": 61300, "loss": 0.3351, "lr": 4.798779464545552e-05, "epoch": 2.1574225122349104, "percentage": 21.57, "elapsed_time": "1:47:44", "remaining_time": "6:31:39", "throughput": 4417.04, "total_tokens": 28553776} {"current_steps": 13230, "total_steps": 61300, "loss": 0.349, "lr": 4.7984995902316045e-05, "epoch": 2.1582381729200653, "percentage": 21.58, "elapsed_time": "1:47:46", "remaining_time": "6:31:36", "throughput": 4417.23, "total_tokens": 28565680} {"current_steps": 13235, "total_steps": 61300, "loss": 0.3281, "lr": 4.798219529589618e-05, "epoch": 2.15905383360522, "percentage": 21.59, "elapsed_time": "1:47:49", "remaining_time": "6:31:33", "throughput": 4417.33, "total_tokens": 28576560} {"current_steps": 13240, "total_steps": 61300, "loss": 0.315, "lr": 4.797939282642294e-05, "epoch": 2.1598694942903753, "percentage": 21.6, "elapsed_time": "1:47:51", "remaining_time": "6:31:29", "throughput": 4417.46, "total_tokens": 28586352} {"current_steps": 13245, "total_steps": 61300, "loss": 0.3558, "lr": 4.797658849412353e-05, "epoch": 2.16068515497553, "percentage": 21.61, "elapsed_time": "1:47:53", "remaining_time": "6:31:27", "throughput": 4417.61, "total_tokens": 28598416} {"current_steps": 13250, "total_steps": 61300, "loss": 0.2991, "lr": 4.797378229922528e-05, "epoch": 2.161500815660685, "percentage": 21.62, "elapsed_time": "1:47:55", "remaining_time": "6:31:24", "throughput": 4417.76, "total_tokens": 28609424} {"current_steps": 13255, "total_steps": 61300, "loss": 0.3502, "lr": 4.797097424195566e-05, "epoch": 2.1623164763458402, "percentage": 21.62, "elapsed_time": "1:47:58", "remaining_time": "6:31:20", "throughput": 4417.88, "total_tokens": 28619184} {"current_steps": 13260, "total_steps": 61300, "loss": 0.3449, "lr": 4.796816432254232e-05, "epoch": 2.163132137030995, "percentage": 21.63, "elapsed_time": "1:48:00", "remaining_time": "6:31:17", "throughput": 4418.0, "total_tokens": 28629232} {"current_steps": 13265, "total_steps": 61300, "loss": 0.3644, "lr": 4.796535254121304e-05, "epoch": 2.1639477977161503, "percentage": 21.64, "elapsed_time": "1:48:02", "remaining_time": "6:31:13", "throughput": 4418.15, "total_tokens": 28639408} {"current_steps": 13270, "total_steps": 61300, "loss": 0.3687, "lr": 4.7962538898195754e-05, "epoch": 2.164763458401305, "percentage": 21.65, "elapsed_time": "1:48:04", "remaining_time": "6:31:10", "throughput": 4418.3, "total_tokens": 28650736} {"current_steps": 13275, "total_steps": 61300, "loss": 0.3412, "lr": 4.7959723393718556e-05, "epoch": 2.16557911908646, "percentage": 21.66, "elapsed_time": "1:48:06", "remaining_time": "6:31:06", "throughput": 4418.43, "total_tokens": 28660784} {"current_steps": 13280, "total_steps": 61300, "loss": 0.3639, "lr": 4.7956906028009683e-05, "epoch": 2.166394779771615, "percentage": 21.66, "elapsed_time": "1:48:08", "remaining_time": "6:31:03", "throughput": 4418.58, "total_tokens": 28671248} {"current_steps": 13285, "total_steps": 61300, "loss": 0.34, "lr": 4.795408680129753e-05, "epoch": 2.16721044045677, "percentage": 21.67, "elapsed_time": "1:48:11", "remaining_time": "6:31:00", "throughput": 4418.72, "total_tokens": 28682000} {"current_steps": 13290, "total_steps": 61300, "loss": 0.3287, "lr": 4.795126571381062e-05, "epoch": 2.168026101141925, "percentage": 21.68, "elapsed_time": "1:48:13", "remaining_time": "6:30:56", "throughput": 4418.86, "total_tokens": 28692912} {"current_steps": 13295, "total_steps": 61300, "loss": 0.2834, "lr": 4.794844276577767e-05, "epoch": 2.16884176182708, "percentage": 21.69, "elapsed_time": "1:48:15", "remaining_time": "6:30:53", "throughput": 4418.97, "total_tokens": 28703504} {"current_steps": 13300, "total_steps": 61300, "loss": 0.3764, "lr": 4.794561795742751e-05, "epoch": 2.169657422512235, "percentage": 21.7, "elapsed_time": "1:48:17", "remaining_time": "6:30:50", "throughput": 4419.1, "total_tokens": 28714416} {"current_steps": 13305, "total_steps": 61300, "loss": 0.2727, "lr": 4.794279128898913e-05, "epoch": 2.1704730831973897, "percentage": 21.7, "elapsed_time": "1:48:20", "remaining_time": "6:30:47", "throughput": 4419.21, "total_tokens": 28725200} {"current_steps": 13310, "total_steps": 61300, "loss": 0.3849, "lr": 4.7939962760691675e-05, "epoch": 2.171288743882545, "percentage": 21.71, "elapsed_time": "1:48:22", "remaining_time": "6:30:44", "throughput": 4419.39, "total_tokens": 28736176} {"current_steps": 13315, "total_steps": 61300, "loss": 0.3949, "lr": 4.793713237276445e-05, "epoch": 2.1721044045677, "percentage": 21.72, "elapsed_time": "1:48:24", "remaining_time": "6:30:41", "throughput": 4419.56, "total_tokens": 28746928} {"current_steps": 13320, "total_steps": 61300, "loss": 0.3121, "lr": 4.7934300125436885e-05, "epoch": 2.1729200652528546, "percentage": 21.73, "elapsed_time": "1:48:26", "remaining_time": "6:30:37", "throughput": 4419.68, "total_tokens": 28757584} {"current_steps": 13325, "total_steps": 61300, "loss": 0.3197, "lr": 4.7931466018938586e-05, "epoch": 2.17373572593801, "percentage": 21.74, "elapsed_time": "1:48:28", "remaining_time": "6:30:33", "throughput": 4419.77, "total_tokens": 28766224} {"current_steps": 13330, "total_steps": 61300, "loss": 0.37, "lr": 4.79286300534993e-05, "epoch": 2.1745513866231647, "percentage": 21.75, "elapsed_time": "1:48:30", "remaining_time": "6:30:29", "throughput": 4419.89, "total_tokens": 28775984} {"current_steps": 13335, "total_steps": 61300, "loss": 0.301, "lr": 4.792579222934892e-05, "epoch": 2.1753670473083195, "percentage": 21.75, "elapsed_time": "1:48:32", "remaining_time": "6:30:26", "throughput": 4420.02, "total_tokens": 28787056} {"current_steps": 13340, "total_steps": 61300, "loss": 0.3086, "lr": 4.79229525467175e-05, "epoch": 2.176182707993475, "percentage": 21.76, "elapsed_time": "1:48:35", "remaining_time": "6:30:23", "throughput": 4420.15, "total_tokens": 28797648} {"current_steps": 13345, "total_steps": 61300, "loss": 0.3752, "lr": 4.792011100583524e-05, "epoch": 2.1769983686786296, "percentage": 21.77, "elapsed_time": "1:48:37", "remaining_time": "6:30:20", "throughput": 4420.26, "total_tokens": 28808656} {"current_steps": 13350, "total_steps": 61300, "loss": 0.3339, "lr": 4.791726760693248e-05, "epoch": 2.177814029363785, "percentage": 21.78, "elapsed_time": "1:48:39", "remaining_time": "6:30:16", "throughput": 4420.38, "total_tokens": 28818448} {"current_steps": 13355, "total_steps": 61300, "loss": 0.3481, "lr": 4.791442235023974e-05, "epoch": 2.1786296900489397, "percentage": 21.79, "elapsed_time": "1:48:41", "remaining_time": "6:30:12", "throughput": 4420.52, "total_tokens": 28828752} {"current_steps": 13360, "total_steps": 61300, "loss": 0.2878, "lr": 4.7911575235987644e-05, "epoch": 2.1794453507340945, "percentage": 21.79, "elapsed_time": "1:48:43", "remaining_time": "6:30:09", "throughput": 4420.65, "total_tokens": 28838896} {"current_steps": 13365, "total_steps": 61300, "loss": 0.3343, "lr": 4.790872626440701e-05, "epoch": 2.1802610114192498, "percentage": 21.8, "elapsed_time": "1:48:45", "remaining_time": "6:30:05", "throughput": 4420.75, "total_tokens": 28848880} {"current_steps": 13370, "total_steps": 61300, "loss": 0.3471, "lr": 4.790587543572879e-05, "epoch": 2.1810766721044046, "percentage": 21.81, "elapsed_time": "1:48:48", "remaining_time": "6:30:02", "throughput": 4420.92, "total_tokens": 28860592} {"current_steps": 13375, "total_steps": 61300, "loss": 0.319, "lr": 4.790302275018408e-05, "epoch": 2.1818923327895594, "percentage": 21.82, "elapsed_time": "1:48:50", "remaining_time": "6:30:00", "throughput": 4421.09, "total_tokens": 28872432} {"current_steps": 13380, "total_steps": 61300, "loss": 0.3338, "lr": 4.790016820800414e-05, "epoch": 2.1827079934747147, "percentage": 21.83, "elapsed_time": "1:48:52", "remaining_time": "6:29:57", "throughput": 4421.24, "total_tokens": 28883856} {"current_steps": 13385, "total_steps": 61300, "loss": 0.3556, "lr": 4.789731180942037e-05, "epoch": 2.1835236541598695, "percentage": 21.84, "elapsed_time": "1:48:55", "remaining_time": "6:29:54", "throughput": 4421.36, "total_tokens": 28894384} {"current_steps": 13390, "total_steps": 61300, "loss": 0.3228, "lr": 4.7894453554664325e-05, "epoch": 2.1843393148450243, "percentage": 21.84, "elapsed_time": "1:48:56", "remaining_time": "6:29:49", "throughput": 4421.45, "total_tokens": 28902288} {"current_steps": 13395, "total_steps": 61300, "loss": 0.3271, "lr": 4.7891593443967706e-05, "epoch": 2.1851549755301796, "percentage": 21.85, "elapsed_time": "1:48:59", "remaining_time": "6:29:46", "throughput": 4421.6, "total_tokens": 28913296} {"current_steps": 13400, "total_steps": 61300, "loss": 0.3421, "lr": 4.788873147756238e-05, "epoch": 2.1859706362153344, "percentage": 21.86, "elapsed_time": "1:49:01", "remaining_time": "6:29:42", "throughput": 4421.71, "total_tokens": 28923888} {"current_steps": 13405, "total_steps": 61300, "loss": 0.3842, "lr": 4.788586765568034e-05, "epoch": 2.186786296900489, "percentage": 21.87, "elapsed_time": "1:49:03", "remaining_time": "6:29:39", "throughput": 4421.84, "total_tokens": 28934640} {"current_steps": 13410, "total_steps": 61300, "loss": 0.4018, "lr": 4.788300197855374e-05, "epoch": 2.1876019575856445, "percentage": 21.88, "elapsed_time": "1:49:05", "remaining_time": "6:29:36", "throughput": 4421.97, "total_tokens": 28945648} {"current_steps": 13415, "total_steps": 61300, "loss": 0.3153, "lr": 4.788013444641491e-05, "epoch": 2.1884176182707993, "percentage": 21.88, "elapsed_time": "1:49:08", "remaining_time": "6:29:34", "throughput": 4422.1, "total_tokens": 28957392} {"current_steps": 13420, "total_steps": 61300, "loss": 0.3604, "lr": 4.7877265059496266e-05, "epoch": 2.189233278955954, "percentage": 21.89, "elapsed_time": "1:49:10", "remaining_time": "6:29:30", "throughput": 4422.23, "total_tokens": 28967056} {"current_steps": 13425, "total_steps": 61300, "loss": 0.3578, "lr": 4.7874393818030456e-05, "epoch": 2.1900489396411094, "percentage": 21.9, "elapsed_time": "1:49:12", "remaining_time": "6:29:27", "throughput": 4422.35, "total_tokens": 28977808} {"current_steps": 13430, "total_steps": 61300, "loss": 0.3486, "lr": 4.7871520722250214e-05, "epoch": 2.190864600326264, "percentage": 21.91, "elapsed_time": "1:49:14", "remaining_time": "6:29:23", "throughput": 4422.45, "total_tokens": 28987440} {"current_steps": 13435, "total_steps": 61300, "loss": 0.3587, "lr": 4.786864577238845e-05, "epoch": 2.1916802610114194, "percentage": 21.92, "elapsed_time": "1:49:16", "remaining_time": "6:29:19", "throughput": 4422.57, "total_tokens": 28997392} {"current_steps": 13440, "total_steps": 61300, "loss": 0.3146, "lr": 4.7865768968678226e-05, "epoch": 2.1924959216965743, "percentage": 21.92, "elapsed_time": "1:49:18", "remaining_time": "6:29:16", "throughput": 4422.69, "total_tokens": 29007824} {"current_steps": 13445, "total_steps": 61300, "loss": 0.3402, "lr": 4.786289031135275e-05, "epoch": 2.193311582381729, "percentage": 21.93, "elapsed_time": "1:49:21", "remaining_time": "6:29:13", "throughput": 4422.85, "total_tokens": 29019024} {"current_steps": 13450, "total_steps": 61300, "loss": 0.34, "lr": 4.786000980064538e-05, "epoch": 2.1941272430668843, "percentage": 21.94, "elapsed_time": "1:49:23", "remaining_time": "6:29:11", "throughput": 4423.04, "total_tokens": 29031600} {"current_steps": 13455, "total_steps": 61300, "loss": 0.3161, "lr": 4.785712743678963e-05, "epoch": 2.194942903752039, "percentage": 21.95, "elapsed_time": "1:49:26", "remaining_time": "6:29:08", "throughput": 4423.17, "total_tokens": 29043056} {"current_steps": 13460, "total_steps": 61300, "loss": 0.3383, "lr": 4.785424322001915e-05, "epoch": 2.195758564437194, "percentage": 21.96, "elapsed_time": "1:49:28", "remaining_time": "6:29:05", "throughput": 4423.3, "total_tokens": 29053648} {"current_steps": 13465, "total_steps": 61300, "loss": 0.3603, "lr": 4.785135715056775e-05, "epoch": 2.1965742251223492, "percentage": 21.97, "elapsed_time": "1:49:30", "remaining_time": "6:29:01", "throughput": 4423.43, "total_tokens": 29064112} {"current_steps": 13470, "total_steps": 61300, "loss": 0.3666, "lr": 4.78484692286694e-05, "epoch": 2.197389885807504, "percentage": 21.97, "elapsed_time": "1:49:32", "remaining_time": "6:28:59", "throughput": 4423.55, "total_tokens": 29075216} {"current_steps": 13475, "total_steps": 61300, "loss": 0.3338, "lr": 4.7845579454558196e-05, "epoch": 2.198205546492659, "percentage": 21.98, "elapsed_time": "1:49:34", "remaining_time": "6:28:54", "throughput": 4423.63, "total_tokens": 29084368} {"current_steps": 13480, "total_steps": 61300, "loss": 0.3269, "lr": 4.784268782846841e-05, "epoch": 2.199021207177814, "percentage": 21.99, "elapsed_time": "1:49:37", "remaining_time": "6:28:52", "throughput": 4423.78, "total_tokens": 29096016} {"current_steps": 13485, "total_steps": 61300, "loss": 0.3636, "lr": 4.783979435063445e-05, "epoch": 2.199836867862969, "percentage": 22.0, "elapsed_time": "1:49:39", "remaining_time": "6:28:49", "throughput": 4423.88, "total_tokens": 29106768} {"current_steps": 13490, "total_steps": 61300, "loss": 0.3817, "lr": 4.783689902129086e-05, "epoch": 2.200652528548124, "percentage": 22.01, "elapsed_time": "1:49:41", "remaining_time": "6:28:45", "throughput": 4423.99, "total_tokens": 29116560} {"current_steps": 13495, "total_steps": 61300, "loss": 0.3792, "lr": 4.783400184067237e-05, "epoch": 2.201468189233279, "percentage": 22.01, "elapsed_time": "1:49:43", "remaining_time": "6:28:42", "throughput": 4424.13, "total_tokens": 29127376} {"current_steps": 13500, "total_steps": 61300, "loss": 0.387, "lr": 4.783110280901383e-05, "epoch": 2.202283849918434, "percentage": 22.02, "elapsed_time": "1:49:46", "remaining_time": "6:28:39", "throughput": 4424.3, "total_tokens": 29139088} {"current_steps": 13505, "total_steps": 61300, "loss": 0.3284, "lr": 4.7828201926550245e-05, "epoch": 2.203099510603589, "percentage": 22.03, "elapsed_time": "1:49:48", "remaining_time": "6:28:36", "throughput": 4424.46, "total_tokens": 29149488} {"current_steps": 13510, "total_steps": 61300, "loss": 0.3572, "lr": 4.7825299193516794e-05, "epoch": 2.203915171288744, "percentage": 22.04, "elapsed_time": "1:49:50", "remaining_time": "6:28:32", "throughput": 4424.58, "total_tokens": 29159728} {"current_steps": 13515, "total_steps": 61300, "loss": 0.3488, "lr": 4.782239461014877e-05, "epoch": 2.2047308319738987, "percentage": 22.05, "elapsed_time": "1:49:52", "remaining_time": "6:28:29", "throughput": 4424.72, "total_tokens": 29170928} {"current_steps": 13520, "total_steps": 61300, "loss": 0.3167, "lr": 4.781948817668164e-05, "epoch": 2.205546492659054, "percentage": 22.06, "elapsed_time": "1:49:54", "remaining_time": "6:28:26", "throughput": 4424.83, "total_tokens": 29180912} {"current_steps": 13525, "total_steps": 61300, "loss": 0.3737, "lr": 4.7816579893351014e-05, "epoch": 2.206362153344209, "percentage": 22.06, "elapsed_time": "1:49:56", "remaining_time": "6:28:22", "throughput": 4424.93, "total_tokens": 29191216} {"current_steps": 13530, "total_steps": 61300, "loss": 0.3492, "lr": 4.781366976039265e-05, "epoch": 2.2071778140293636, "percentage": 22.07, "elapsed_time": "1:49:59", "remaining_time": "6:28:19", "throughput": 4425.05, "total_tokens": 29201424} {"current_steps": 13535, "total_steps": 61300, "loss": 0.327, "lr": 4.781075777804246e-05, "epoch": 2.207993474714519, "percentage": 22.08, "elapsed_time": "1:50:01", "remaining_time": "6:28:15", "throughput": 4425.17, "total_tokens": 29211152} {"current_steps": 13540, "total_steps": 61300, "loss": 0.3392, "lr": 4.7807843946536514e-05, "epoch": 2.2088091353996737, "percentage": 22.09, "elapsed_time": "1:50:03", "remaining_time": "6:28:12", "throughput": 4425.3, "total_tokens": 29221744} {"current_steps": 13545, "total_steps": 61300, "loss": 0.338, "lr": 4.7804928266110996e-05, "epoch": 2.2096247960848285, "percentage": 22.1, "elapsed_time": "1:50:05", "remaining_time": "6:28:08", "throughput": 4425.4, "total_tokens": 29231568} {"current_steps": 13550, "total_steps": 61300, "loss": 0.3501, "lr": 4.780201073700229e-05, "epoch": 2.210440456769984, "percentage": 22.1, "elapsed_time": "1:50:07", "remaining_time": "6:28:05", "throughput": 4425.52, "total_tokens": 29242128} {"current_steps": 13555, "total_steps": 61300, "loss": 0.3766, "lr": 4.7799091359446905e-05, "epoch": 2.2112561174551386, "percentage": 22.11, "elapsed_time": "1:50:09", "remaining_time": "6:28:00", "throughput": 4425.64, "total_tokens": 29250992} {"current_steps": 13560, "total_steps": 61300, "loss": 0.3648, "lr": 4.779617013368148e-05, "epoch": 2.2120717781402934, "percentage": 22.12, "elapsed_time": "1:50:11", "remaining_time": "6:27:56", "throughput": 4425.77, "total_tokens": 29261072} {"current_steps": 13565, "total_steps": 61300, "loss": 0.3376, "lr": 4.7793247059942845e-05, "epoch": 2.2128874388254487, "percentage": 22.13, "elapsed_time": "1:50:13", "remaining_time": "6:27:53", "throughput": 4425.9, "total_tokens": 29271760} {"current_steps": 13570, "total_steps": 61300, "loss": 0.3432, "lr": 4.779032213846795e-05, "epoch": 2.2137030995106035, "percentage": 22.14, "elapsed_time": "1:50:15", "remaining_time": "6:27:50", "throughput": 4426.03, "total_tokens": 29282480} {"current_steps": 13575, "total_steps": 61300, "loss": 0.3553, "lr": 4.77873953694939e-05, "epoch": 2.2145187601957588, "percentage": 22.15, "elapsed_time": "1:50:18", "remaining_time": "6:27:47", "throughput": 4426.14, "total_tokens": 29292912} {"current_steps": 13580, "total_steps": 61300, "loss": 0.3391, "lr": 4.778446675325796e-05, "epoch": 2.2153344208809136, "percentage": 22.15, "elapsed_time": "1:50:20", "remaining_time": "6:27:43", "throughput": 4426.22, "total_tokens": 29302800} {"current_steps": 13585, "total_steps": 61300, "loss": 0.3323, "lr": 4.778153628999754e-05, "epoch": 2.2161500815660684, "percentage": 22.16, "elapsed_time": "1:50:22", "remaining_time": "6:27:40", "throughput": 4426.36, "total_tokens": 29313424} {"current_steps": 13590, "total_steps": 61300, "loss": 0.3306, "lr": 4.7778603979950196e-05, "epoch": 2.2169657422512237, "percentage": 22.17, "elapsed_time": "1:50:24", "remaining_time": "6:27:36", "throughput": 4426.48, "total_tokens": 29323856} {"current_steps": 13595, "total_steps": 61300, "loss": 0.3695, "lr": 4.777566982335364e-05, "epoch": 2.2177814029363785, "percentage": 22.18, "elapsed_time": "1:50:26", "remaining_time": "6:27:33", "throughput": 4426.61, "total_tokens": 29334832} {"current_steps": 13600, "total_steps": 61300, "loss": 0.3247, "lr": 4.777273382044572e-05, "epoch": 2.2185970636215333, "percentage": 22.19, "elapsed_time": "1:50:29", "remaining_time": "6:27:31", "throughput": 4426.72, "total_tokens": 29345936} {"current_steps": 13605, "total_steps": 61300, "loss": 0.3393, "lr": 4.7769795971464456e-05, "epoch": 2.2194127243066886, "percentage": 22.19, "elapsed_time": "1:50:31", "remaining_time": "6:27:27", "throughput": 4426.84, "total_tokens": 29356560} {"current_steps": 13610, "total_steps": 61300, "loss": 0.3567, "lr": 4.7766856276647986e-05, "epoch": 2.2202283849918434, "percentage": 22.2, "elapsed_time": "1:50:33", "remaining_time": "6:27:24", "throughput": 4426.97, "total_tokens": 29367024} {"current_steps": 13615, "total_steps": 61300, "loss": 0.3181, "lr": 4.776391473623464e-05, "epoch": 2.221044045676998, "percentage": 22.21, "elapsed_time": "1:50:35", "remaining_time": "6:27:20", "throughput": 4427.07, "total_tokens": 29376944} {"current_steps": 13620, "total_steps": 61300, "loss": 0.3625, "lr": 4.7760971350462856e-05, "epoch": 2.2218597063621535, "percentage": 22.22, "elapsed_time": "1:50:38", "remaining_time": "6:27:19", "throughput": 4427.23, "total_tokens": 29389552} {"current_steps": 13625, "total_steps": 61300, "loss": 0.356, "lr": 4.775802611957125e-05, "epoch": 2.2226753670473083, "percentage": 22.23, "elapsed_time": "1:50:40", "remaining_time": "6:27:15", "throughput": 4427.35, "total_tokens": 29399600} {"current_steps": 13630, "total_steps": 61300, "loss": 0.3363, "lr": 4.7755079043798565e-05, "epoch": 2.223491027732463, "percentage": 22.23, "elapsed_time": "1:50:42", "remaining_time": "6:27:12", "throughput": 4427.47, "total_tokens": 29410896} {"current_steps": 13635, "total_steps": 61300, "loss": 0.3987, "lr": 4.775213012338373e-05, "epoch": 2.2243066884176184, "percentage": 22.24, "elapsed_time": "1:50:45", "remaining_time": "6:27:09", "throughput": 4427.56, "total_tokens": 29421136} {"current_steps": 13640, "total_steps": 61300, "loss": 0.347, "lr": 4.774917935856577e-05, "epoch": 2.225122349102773, "percentage": 22.25, "elapsed_time": "1:50:47", "remaining_time": "6:27:06", "throughput": 4427.69, "total_tokens": 29431536} {"current_steps": 13645, "total_steps": 61300, "loss": 0.3598, "lr": 4.774622674958391e-05, "epoch": 2.225938009787928, "percentage": 22.26, "elapsed_time": "1:50:49", "remaining_time": "6:27:02", "throughput": 4427.83, "total_tokens": 29442416} {"current_steps": 13650, "total_steps": 61300, "loss": 0.3504, "lr": 4.7743272296677495e-05, "epoch": 2.2267536704730833, "percentage": 22.27, "elapsed_time": "1:50:51", "remaining_time": "6:26:59", "throughput": 4427.96, "total_tokens": 29453232} {"current_steps": 13655, "total_steps": 61300, "loss": 0.3609, "lr": 4.774031600008603e-05, "epoch": 2.227569331158238, "percentage": 22.28, "elapsed_time": "1:50:54", "remaining_time": "6:26:57", "throughput": 4428.13, "total_tokens": 29464976} {"current_steps": 13660, "total_steps": 61300, "loss": 0.366, "lr": 4.7737357860049164e-05, "epoch": 2.2283849918433933, "percentage": 22.28, "elapsed_time": "1:50:56", "remaining_time": "6:26:54", "throughput": 4428.25, "total_tokens": 29475536} {"current_steps": 13665, "total_steps": 61300, "loss": 0.3719, "lr": 4.7734397876806704e-05, "epoch": 2.229200652528548, "percentage": 22.29, "elapsed_time": "1:50:58", "remaining_time": "6:26:50", "throughput": 4428.4, "total_tokens": 29486256} {"current_steps": 13670, "total_steps": 61300, "loss": 0.3717, "lr": 4.77314360505986e-05, "epoch": 2.230016313213703, "percentage": 22.3, "elapsed_time": "1:51:00", "remaining_time": "6:26:48", "throughput": 4428.55, "total_tokens": 29498512} {"current_steps": 13675, "total_steps": 61300, "loss": 0.3569, "lr": 4.772847238166495e-05, "epoch": 2.2308319738988582, "percentage": 22.31, "elapsed_time": "1:51:03", "remaining_time": "6:26:45", "throughput": 4428.67, "total_tokens": 29509360} {"current_steps": 13680, "total_steps": 61300, "loss": 0.3239, "lr": 4.7725506870246006e-05, "epoch": 2.231647634584013, "percentage": 22.32, "elapsed_time": "1:51:05", "remaining_time": "6:26:42", "throughput": 4428.81, "total_tokens": 29520400} {"current_steps": 13685, "total_steps": 61300, "loss": 0.3184, "lr": 4.772253951658217e-05, "epoch": 2.232463295269168, "percentage": 22.32, "elapsed_time": "1:51:07", "remaining_time": "6:26:40", "throughput": 4428.95, "total_tokens": 29532016} {"current_steps": 13690, "total_steps": 61300, "loss": 0.3307, "lr": 4.771957032091398e-05, "epoch": 2.233278955954323, "percentage": 22.33, "elapsed_time": "1:51:10", "remaining_time": "6:26:37", "throughput": 4429.12, "total_tokens": 29543728} {"current_steps": 13695, "total_steps": 61300, "loss": 0.3554, "lr": 4.771659928348214e-05, "epoch": 2.234094616639478, "percentage": 22.34, "elapsed_time": "1:51:12", "remaining_time": "6:26:34", "throughput": 4429.26, "total_tokens": 29554352} {"current_steps": 13700, "total_steps": 61300, "loss": 0.3484, "lr": 4.7713626404527514e-05, "epoch": 2.2349102773246328, "percentage": 22.35, "elapsed_time": "1:51:14", "remaining_time": "6:26:31", "throughput": 4429.38, "total_tokens": 29565168} {"current_steps": 13705, "total_steps": 61300, "loss": 0.3579, "lr": 4.7710651684291074e-05, "epoch": 2.235725938009788, "percentage": 22.36, "elapsed_time": "1:51:16", "remaining_time": "6:26:27", "throughput": 4429.53, "total_tokens": 29575792} {"current_steps": 13710, "total_steps": 61300, "loss": 0.4082, "lr": 4.770767512301398e-05, "epoch": 2.236541598694943, "percentage": 22.37, "elapsed_time": "1:51:19", "remaining_time": "6:26:24", "throughput": 4429.67, "total_tokens": 29586384} {"current_steps": 13715, "total_steps": 61300, "loss": 0.3252, "lr": 4.770469672093752e-05, "epoch": 2.237357259380098, "percentage": 22.37, "elapsed_time": "1:51:21", "remaining_time": "6:26:21", "throughput": 4429.8, "total_tokens": 29597232} {"current_steps": 13720, "total_steps": 61300, "loss": 0.326, "lr": 4.7701716478303135e-05, "epoch": 2.238172920065253, "percentage": 22.38, "elapsed_time": "1:51:23", "remaining_time": "6:26:17", "throughput": 4429.91, "total_tokens": 29606896} {"current_steps": 13725, "total_steps": 61300, "loss": 0.3281, "lr": 4.769873439535244e-05, "epoch": 2.2389885807504077, "percentage": 22.39, "elapsed_time": "1:51:25", "remaining_time": "6:26:14", "throughput": 4430.03, "total_tokens": 29617648} {"current_steps": 13730, "total_steps": 61300, "loss": 0.3276, "lr": 4.769575047232715e-05, "epoch": 2.239804241435563, "percentage": 22.4, "elapsed_time": "1:51:27", "remaining_time": "6:26:10", "throughput": 4430.17, "total_tokens": 29627664} {"current_steps": 13735, "total_steps": 61300, "loss": 0.3201, "lr": 4.769276470946917e-05, "epoch": 2.240619902120718, "percentage": 22.41, "elapsed_time": "1:51:30", "remaining_time": "6:26:08", "throughput": 4430.3, "total_tokens": 29639088} {"current_steps": 13740, "total_steps": 61300, "loss": 0.3241, "lr": 4.768977710702055e-05, "epoch": 2.2414355628058726, "percentage": 22.41, "elapsed_time": "1:51:32", "remaining_time": "6:26:04", "throughput": 4430.42, "total_tokens": 29649648} {"current_steps": 13745, "total_steps": 61300, "loss": 0.3536, "lr": 4.768678766522347e-05, "epoch": 2.242251223491028, "percentage": 22.42, "elapsed_time": "1:51:34", "remaining_time": "6:26:02", "throughput": 4430.56, "total_tokens": 29661360} {"current_steps": 13750, "total_steps": 61300, "loss": 0.3172, "lr": 4.768379638432026e-05, "epoch": 2.2430668841761827, "percentage": 22.43, "elapsed_time": "1:51:37", "remaining_time": "6:25:59", "throughput": 4430.69, "total_tokens": 29672336} {"current_steps": 13755, "total_steps": 61300, "loss": 0.398, "lr": 4.768080326455343e-05, "epoch": 2.2438825448613375, "percentage": 22.44, "elapsed_time": "1:51:39", "remaining_time": "6:25:56", "throughput": 4430.82, "total_tokens": 29683472} {"current_steps": 13760, "total_steps": 61300, "loss": 0.2924, "lr": 4.7677808306165596e-05, "epoch": 2.244698205546493, "percentage": 22.45, "elapsed_time": "1:51:41", "remaining_time": "6:25:54", "throughput": 4430.97, "total_tokens": 29695472} {"current_steps": 13765, "total_steps": 61300, "loss": 0.4201, "lr": 4.767481150939956e-05, "epoch": 2.2455138662316476, "percentage": 22.46, "elapsed_time": "1:51:43", "remaining_time": "6:25:50", "throughput": 4431.06, "total_tokens": 29705520} {"current_steps": 13770, "total_steps": 61300, "loss": 0.3733, "lr": 4.767181287449825e-05, "epoch": 2.2463295269168024, "percentage": 22.46, "elapsed_time": "1:51:46", "remaining_time": "6:25:47", "throughput": 4431.17, "total_tokens": 29715824} {"current_steps": 13775, "total_steps": 61300, "loss": 0.358, "lr": 4.766881240170475e-05, "epoch": 2.2471451876019577, "percentage": 22.47, "elapsed_time": "1:51:48", "remaining_time": "6:25:44", "throughput": 4431.27, "total_tokens": 29726864} {"current_steps": 13780, "total_steps": 61300, "loss": 0.4121, "lr": 4.7665810091262305e-05, "epoch": 2.2479608482871125, "percentage": 22.48, "elapsed_time": "1:51:50", "remaining_time": "6:25:41", "throughput": 4431.41, "total_tokens": 29738128} {"current_steps": 13785, "total_steps": 61300, "loss": 0.3376, "lr": 4.766280594341428e-05, "epoch": 2.2487765089722673, "percentage": 22.49, "elapsed_time": "1:51:52", "remaining_time": "6:25:37", "throughput": 4431.51, "total_tokens": 29747152} {"current_steps": 13790, "total_steps": 61300, "loss": 0.3359, "lr": 4.7659799958404225e-05, "epoch": 2.2495921696574226, "percentage": 22.5, "elapsed_time": "1:51:54", "remaining_time": "6:25:33", "throughput": 4431.64, "total_tokens": 29756912} {"current_steps": 13795, "total_steps": 61300, "loss": 0.3471, "lr": 4.7656792136475804e-05, "epoch": 2.2504078303425774, "percentage": 22.5, "elapsed_time": "1:51:56", "remaining_time": "6:25:29", "throughput": 4431.75, "total_tokens": 29766768} {"current_steps": 13800, "total_steps": 61300, "loss": 0.3667, "lr": 4.765378247787285e-05, "epoch": 2.2512234910277327, "percentage": 22.51, "elapsed_time": "1:51:59", "remaining_time": "6:25:27", "throughput": 4431.89, "total_tokens": 29778032} {"current_steps": 13805, "total_steps": 61300, "loss": 0.3643, "lr": 4.765077098283935e-05, "epoch": 2.2520391517128875, "percentage": 22.52, "elapsed_time": "1:52:00", "remaining_time": "6:25:22", "throughput": 4432.03, "total_tokens": 29787408} {"current_steps": 13810, "total_steps": 61300, "loss": 0.3724, "lr": 4.764775765161943e-05, "epoch": 2.2528548123980423, "percentage": 22.53, "elapsed_time": "1:52:02", "remaining_time": "6:25:19", "throughput": 4432.13, "total_tokens": 29797232} {"current_steps": 13815, "total_steps": 61300, "loss": 0.3754, "lr": 4.764474248445735e-05, "epoch": 2.2536704730831976, "percentage": 22.54, "elapsed_time": "1:52:05", "remaining_time": "6:25:16", "throughput": 4432.27, "total_tokens": 29808016} {"current_steps": 13820, "total_steps": 61300, "loss": 0.3419, "lr": 4.764172548159755e-05, "epoch": 2.2544861337683524, "percentage": 22.54, "elapsed_time": "1:52:07", "remaining_time": "6:25:12", "throughput": 4432.38, "total_tokens": 29818640} {"current_steps": 13825, "total_steps": 61300, "loss": 0.3672, "lr": 4.7638706643284605e-05, "epoch": 2.255301794453507, "percentage": 22.55, "elapsed_time": "1:52:09", "remaining_time": "6:25:09", "throughput": 4432.52, "total_tokens": 29829776} {"current_steps": 13830, "total_steps": 61300, "loss": 0.3606, "lr": 4.7635685969763225e-05, "epoch": 2.2561174551386625, "percentage": 22.56, "elapsed_time": "1:52:11", "remaining_time": "6:25:06", "throughput": 4432.63, "total_tokens": 29840304} {"current_steps": 13835, "total_steps": 61300, "loss": 0.3392, "lr": 4.763266346127829e-05, "epoch": 2.2569331158238173, "percentage": 22.57, "elapsed_time": "1:52:14", "remaining_time": "6:25:04", "throughput": 4432.79, "total_tokens": 29852048} {"current_steps": 13840, "total_steps": 61300, "loss": 0.3283, "lr": 4.7629639118074816e-05, "epoch": 2.257748776508972, "percentage": 22.58, "elapsed_time": "1:52:16", "remaining_time": "6:25:00", "throughput": 4432.9, "total_tokens": 29861264} {"current_steps": 13845, "total_steps": 61300, "loss": 0.3146, "lr": 4.7626612940397976e-05, "epoch": 2.2585644371941274, "percentage": 22.59, "elapsed_time": "1:52:18", "remaining_time": "6:24:56", "throughput": 4433.03, "total_tokens": 29871984} {"current_steps": 13850, "total_steps": 61300, "loss": 0.3562, "lr": 4.762358492849308e-05, "epoch": 2.259380097879282, "percentage": 22.59, "elapsed_time": "1:52:20", "remaining_time": "6:24:53", "throughput": 4433.17, "total_tokens": 29882256} {"current_steps": 13855, "total_steps": 61300, "loss": 0.3541, "lr": 4.762055508260561e-05, "epoch": 2.2601957585644374, "percentage": 22.6, "elapsed_time": "1:52:22", "remaining_time": "6:24:49", "throughput": 4433.28, "total_tokens": 29891696} {"current_steps": 13860, "total_steps": 61300, "loss": 0.354, "lr": 4.7617523402981155e-05, "epoch": 2.2610114192495923, "percentage": 22.61, "elapsed_time": "1:52:25", "remaining_time": "6:24:46", "throughput": 4433.46, "total_tokens": 29903856} {"current_steps": 13865, "total_steps": 61300, "loss": 0.3283, "lr": 4.7614489889865506e-05, "epoch": 2.261827079934747, "percentage": 22.62, "elapsed_time": "1:52:27", "remaining_time": "6:24:43", "throughput": 4433.56, "total_tokens": 29913520} {"current_steps": 13870, "total_steps": 61300, "loss": 0.339, "lr": 4.761145454350455e-05, "epoch": 2.262642740619902, "percentage": 22.63, "elapsed_time": "1:52:29", "remaining_time": "6:24:39", "throughput": 4433.69, "total_tokens": 29924016} {"current_steps": 13875, "total_steps": 61300, "loss": 0.3383, "lr": 4.760841736414437e-05, "epoch": 2.263458401305057, "percentage": 22.63, "elapsed_time": "1:52:31", "remaining_time": "6:24:36", "throughput": 4433.82, "total_tokens": 29935120} {"current_steps": 13880, "total_steps": 61300, "loss": 0.374, "lr": 4.760537835203116e-05, "epoch": 2.264274061990212, "percentage": 22.64, "elapsed_time": "1:52:33", "remaining_time": "6:24:34", "throughput": 4433.96, "total_tokens": 29946288} {"current_steps": 13885, "total_steps": 61300, "loss": 0.3267, "lr": 4.760233750741128e-05, "epoch": 2.2650897226753672, "percentage": 22.65, "elapsed_time": "1:52:36", "remaining_time": "6:24:30", "throughput": 4434.08, "total_tokens": 29957008} {"current_steps": 13890, "total_steps": 61300, "loss": 0.3558, "lr": 4.7599294830531235e-05, "epoch": 2.265905383360522, "percentage": 22.66, "elapsed_time": "1:52:38", "remaining_time": "6:24:27", "throughput": 4434.19, "total_tokens": 29966896} {"current_steps": 13895, "total_steps": 61300, "loss": 0.3531, "lr": 4.759625032163769e-05, "epoch": 2.266721044045677, "percentage": 22.67, "elapsed_time": "1:52:40", "remaining_time": "6:24:23", "throughput": 4434.29, "total_tokens": 29976528} {"current_steps": 13900, "total_steps": 61300, "loss": 0.356, "lr": 4.7593203980977444e-05, "epoch": 2.267536704730832, "percentage": 22.68, "elapsed_time": "1:52:42", "remaining_time": "6:24:20", "throughput": 4434.43, "total_tokens": 29987120} {"current_steps": 13905, "total_steps": 61300, "loss": 0.3306, "lr": 4.759015580879744e-05, "epoch": 2.268352365415987, "percentage": 22.68, "elapsed_time": "1:52:44", "remaining_time": "6:24:16", "throughput": 4434.53, "total_tokens": 29997680} {"current_steps": 13910, "total_steps": 61300, "loss": 0.3472, "lr": 4.758710580534479e-05, "epoch": 2.2691680261011418, "percentage": 22.69, "elapsed_time": "1:52:46", "remaining_time": "6:24:14", "throughput": 4434.65, "total_tokens": 30008784} {"current_steps": 13915, "total_steps": 61300, "loss": 0.3191, "lr": 4.758405397086674e-05, "epoch": 2.269983686786297, "percentage": 22.7, "elapsed_time": "1:52:48", "remaining_time": "6:24:10", "throughput": 4434.77, "total_tokens": 30018416} {"current_steps": 13920, "total_steps": 61300, "loss": 0.351, "lr": 4.758100030561068e-05, "epoch": 2.270799347471452, "percentage": 22.71, "elapsed_time": "1:52:51", "remaining_time": "6:24:08", "throughput": 4434.87, "total_tokens": 30030352} {"current_steps": 13925, "total_steps": 61300, "loss": 0.3636, "lr": 4.757794480982416e-05, "epoch": 2.2716150081566067, "percentage": 22.72, "elapsed_time": "1:52:53", "remaining_time": "6:24:05", "throughput": 4435.02, "total_tokens": 30041392} {"current_steps": 13930, "total_steps": 61300, "loss": 0.3407, "lr": 4.757488748375487e-05, "epoch": 2.272430668841762, "percentage": 22.72, "elapsed_time": "1:52:55", "remaining_time": "6:24:02", "throughput": 4435.13, "total_tokens": 30052240} {"current_steps": 13935, "total_steps": 61300, "loss": 0.3407, "lr": 4.757182832765067e-05, "epoch": 2.2732463295269167, "percentage": 22.73, "elapsed_time": "1:52:58", "remaining_time": "6:23:58", "throughput": 4435.24, "total_tokens": 30062192} {"current_steps": 13940, "total_steps": 61300, "loss": 0.361, "lr": 4.7568767341759526e-05, "epoch": 2.274061990212072, "percentage": 22.74, "elapsed_time": "1:53:00", "remaining_time": "6:23:56", "throughput": 4435.37, "total_tokens": 30073808} {"current_steps": 13945, "total_steps": 61300, "loss": 0.3504, "lr": 4.756570452632959e-05, "epoch": 2.274877650897227, "percentage": 22.75, "elapsed_time": "1:53:02", "remaining_time": "6:23:52", "throughput": 4435.48, "total_tokens": 30084016} {"current_steps": 13950, "total_steps": 61300, "loss": 0.3294, "lr": 4.756263988160915e-05, "epoch": 2.2756933115823816, "percentage": 22.76, "elapsed_time": "1:53:04", "remaining_time": "6:23:50", "throughput": 4435.61, "total_tokens": 30095600} {"current_steps": 13955, "total_steps": 61300, "loss": 0.3218, "lr": 4.755957340784664e-05, "epoch": 2.2765089722675365, "percentage": 22.77, "elapsed_time": "1:53:07", "remaining_time": "6:23:47", "throughput": 4435.74, "total_tokens": 30106800} {"current_steps": 13960, "total_steps": 61300, "loss": 0.3262, "lr": 4.755650510529064e-05, "epoch": 2.2773246329526917, "percentage": 22.77, "elapsed_time": "1:53:09", "remaining_time": "6:23:44", "throughput": 4435.91, "total_tokens": 30118288} {"current_steps": 13965, "total_steps": 61300, "loss": 0.3605, "lr": 4.755343497418989e-05, "epoch": 2.2781402936378465, "percentage": 22.78, "elapsed_time": "1:53:11", "remaining_time": "6:23:41", "throughput": 4436.04, "total_tokens": 30129552} {"current_steps": 13970, "total_steps": 61300, "loss": 0.3684, "lr": 4.7550363014793264e-05, "epoch": 2.278955954323002, "percentage": 22.79, "elapsed_time": "1:53:14", "remaining_time": "6:23:38", "throughput": 4436.18, "total_tokens": 30140720} {"current_steps": 13975, "total_steps": 61300, "loss": 0.333, "lr": 4.754728922734979e-05, "epoch": 2.2797716150081566, "percentage": 22.8, "elapsed_time": "1:53:16", "remaining_time": "6:23:35", "throughput": 4436.28, "total_tokens": 30150640} {"current_steps": 13980, "total_steps": 61300, "loss": 0.3265, "lr": 4.754421361210865e-05, "epoch": 2.2805872756933114, "percentage": 22.81, "elapsed_time": "1:53:18", "remaining_time": "6:23:31", "throughput": 4436.38, "total_tokens": 30160976} {"current_steps": 13985, "total_steps": 61300, "loss": 0.3564, "lr": 4.7541136169319165e-05, "epoch": 2.2814029363784667, "percentage": 22.81, "elapsed_time": "1:53:20", "remaining_time": "6:23:28", "throughput": 4436.49, "total_tokens": 30170576} {"current_steps": 13990, "total_steps": 61300, "loss": 0.3649, "lr": 4.7538056899230815e-05, "epoch": 2.2822185970636215, "percentage": 22.82, "elapsed_time": "1:53:22", "remaining_time": "6:23:25", "throughput": 4436.61, "total_tokens": 30181904} {"current_steps": 13995, "total_steps": 61300, "loss": 0.3411, "lr": 4.753497580209321e-05, "epoch": 2.2830342577487763, "percentage": 22.83, "elapsed_time": "1:53:25", "remaining_time": "6:23:22", "throughput": 4436.73, "total_tokens": 30193392} {"current_steps": 14000, "total_steps": 61300, "loss": 0.3421, "lr": 4.7531892878156125e-05, "epoch": 2.2838499184339316, "percentage": 22.84, "elapsed_time": "1:53:27", "remaining_time": "6:23:20", "throughput": 4436.84, "total_tokens": 30204528} {"current_steps": 14005, "total_steps": 61300, "loss": 0.4019, "lr": 4.752880812766948e-05, "epoch": 2.2846655791190864, "percentage": 22.85, "elapsed_time": "1:53:30", "remaining_time": "6:23:17", "throughput": 4436.94, "total_tokens": 30215760} {"current_steps": 14010, "total_steps": 61300, "loss": 0.3599, "lr": 4.752572155088334e-05, "epoch": 2.2854812398042412, "percentage": 22.85, "elapsed_time": "1:53:32", "remaining_time": "6:23:14", "throughput": 4437.07, "total_tokens": 30226096} {"current_steps": 14015, "total_steps": 61300, "loss": 0.35, "lr": 4.752263314804791e-05, "epoch": 2.2862969004893965, "percentage": 22.86, "elapsed_time": "1:53:34", "remaining_time": "6:23:11", "throughput": 4437.17, "total_tokens": 30236784} {"current_steps": 14020, "total_steps": 61300, "loss": 0.3457, "lr": 4.7519542919413566e-05, "epoch": 2.2871125611745513, "percentage": 22.87, "elapsed_time": "1:53:36", "remaining_time": "6:23:08", "throughput": 4437.3, "total_tokens": 30248432} {"current_steps": 14025, "total_steps": 61300, "loss": 0.3325, "lr": 4.751645086523081e-05, "epoch": 2.2879282218597066, "percentage": 22.88, "elapsed_time": "1:53:38", "remaining_time": "6:23:05", "throughput": 4437.42, "total_tokens": 30258448} {"current_steps": 14030, "total_steps": 61300, "loss": 0.3301, "lr": 4.75133569857503e-05, "epoch": 2.2887438825448614, "percentage": 22.89, "elapsed_time": "1:53:41", "remaining_time": "6:23:02", "throughput": 4437.56, "total_tokens": 30269424} {"current_steps": 14035, "total_steps": 61300, "loss": 0.3615, "lr": 4.751026128122283e-05, "epoch": 2.289559543230016, "percentage": 22.9, "elapsed_time": "1:53:43", "remaining_time": "6:22:58", "throughput": 4437.69, "total_tokens": 30280144} {"current_steps": 14040, "total_steps": 61300, "loss": 0.3661, "lr": 4.7507163751899374e-05, "epoch": 2.2903752039151715, "percentage": 22.9, "elapsed_time": "1:53:45", "remaining_time": "6:22:55", "throughput": 4437.8, "total_tokens": 30290064} {"current_steps": 14045, "total_steps": 61300, "loss": 0.3476, "lr": 4.750406439803102e-05, "epoch": 2.2911908646003263, "percentage": 22.91, "elapsed_time": "1:53:47", "remaining_time": "6:22:51", "throughput": 4437.89, "total_tokens": 30299984} {"current_steps": 14050, "total_steps": 61300, "loss": 0.3393, "lr": 4.750096321986902e-05, "epoch": 2.292006525285481, "percentage": 22.92, "elapsed_time": "1:53:49", "remaining_time": "6:22:48", "throughput": 4438.0, "total_tokens": 30311248} {"current_steps": 14055, "total_steps": 61300, "loss": 0.3882, "lr": 4.749786021766478e-05, "epoch": 2.2928221859706364, "percentage": 22.93, "elapsed_time": "1:53:52", "remaining_time": "6:22:45", "throughput": 4438.14, "total_tokens": 30322160} {"current_steps": 14060, "total_steps": 61300, "loss": 0.3096, "lr": 4.749475539166983e-05, "epoch": 2.293637846655791, "percentage": 22.94, "elapsed_time": "1:53:54", "remaining_time": "6:22:43", "throughput": 4438.29, "total_tokens": 30333616} {"current_steps": 14065, "total_steps": 61300, "loss": 0.3931, "lr": 4.749164874213588e-05, "epoch": 2.294453507340946, "percentage": 22.94, "elapsed_time": "1:53:56", "remaining_time": "6:22:39", "throughput": 4438.41, "total_tokens": 30344112} {"current_steps": 14070, "total_steps": 61300, "loss": 0.3298, "lr": 4.7488540269314756e-05, "epoch": 2.2952691680261013, "percentage": 22.95, "elapsed_time": "1:53:58", "remaining_time": "6:22:36", "throughput": 4438.52, "total_tokens": 30354192} {"current_steps": 14075, "total_steps": 61300, "loss": 0.355, "lr": 4.748542997345845e-05, "epoch": 2.296084828711256, "percentage": 22.96, "elapsed_time": "1:54:01", "remaining_time": "6:22:33", "throughput": 4438.67, "total_tokens": 30365168} {"current_steps": 14080, "total_steps": 61300, "loss": 0.3438, "lr": 4.74823178548191e-05, "epoch": 2.2969004893964113, "percentage": 22.97, "elapsed_time": "1:54:03", "remaining_time": "6:22:30", "throughput": 4438.79, "total_tokens": 30376464} {"current_steps": 14085, "total_steps": 61300, "loss": 0.3347, "lr": 4.7479203913649e-05, "epoch": 2.297716150081566, "percentage": 22.98, "elapsed_time": "1:54:05", "remaining_time": "6:22:27", "throughput": 4438.9, "total_tokens": 30387472} {"current_steps": 14090, "total_steps": 61300, "loss": 0.3459, "lr": 4.747608815020056e-05, "epoch": 2.298531810766721, "percentage": 22.99, "elapsed_time": "1:54:07", "remaining_time": "6:22:24", "throughput": 4439.01, "total_tokens": 30398224} {"current_steps": 14095, "total_steps": 61300, "loss": 0.3797, "lr": 4.747297056472638e-05, "epoch": 2.299347471451876, "percentage": 22.99, "elapsed_time": "1:54:10", "remaining_time": "6:22:22", "throughput": 4439.15, "total_tokens": 30409872} {"current_steps": 14100, "total_steps": 61300, "loss": 0.3461, "lr": 4.7469851157479177e-05, "epoch": 2.300163132137031, "percentage": 23.0, "elapsed_time": "1:54:12", "remaining_time": "6:22:18", "throughput": 4439.26, "total_tokens": 30420144} {"current_steps": 14105, "total_steps": 61300, "loss": 0.3398, "lr": 4.746672992871183e-05, "epoch": 2.300978792822186, "percentage": 23.01, "elapsed_time": "1:54:14", "remaining_time": "6:22:15", "throughput": 4439.4, "total_tokens": 30430704} {"current_steps": 14110, "total_steps": 61300, "loss": 0.353, "lr": 4.746360687867736e-05, "epoch": 2.301794453507341, "percentage": 23.02, "elapsed_time": "1:54:16", "remaining_time": "6:22:12", "throughput": 4439.5, "total_tokens": 30441328} {"current_steps": 14115, "total_steps": 61300, "loss": 0.3147, "lr": 4.746048200762893e-05, "epoch": 2.302610114192496, "percentage": 23.03, "elapsed_time": "1:54:19", "remaining_time": "6:22:09", "throughput": 4439.65, "total_tokens": 30452208} {"current_steps": 14120, "total_steps": 61300, "loss": 0.3551, "lr": 4.7457355315819874e-05, "epoch": 2.3034257748776508, "percentage": 23.03, "elapsed_time": "1:54:21", "remaining_time": "6:22:06", "throughput": 4439.78, "total_tokens": 30462960} {"current_steps": 14125, "total_steps": 61300, "loss": 0.3528, "lr": 4.745422680350364e-05, "epoch": 2.304241435562806, "percentage": 23.04, "elapsed_time": "1:54:23", "remaining_time": "6:22:02", "throughput": 4439.9, "total_tokens": 30473168} {"current_steps": 14130, "total_steps": 61300, "loss": 0.3418, "lr": 4.745109647093385e-05, "epoch": 2.305057096247961, "percentage": 23.05, "elapsed_time": "1:54:25", "remaining_time": "6:21:59", "throughput": 4440.03, "total_tokens": 30483824} {"current_steps": 14135, "total_steps": 61300, "loss": 0.338, "lr": 4.744796431836428e-05, "epoch": 2.3058727569331157, "percentage": 23.06, "elapsed_time": "1:54:28", "remaining_time": "6:21:57", "throughput": 4440.18, "total_tokens": 30495632} {"current_steps": 14140, "total_steps": 61300, "loss": 0.3509, "lr": 4.7444830346048804e-05, "epoch": 2.306688417618271, "percentage": 23.07, "elapsed_time": "1:54:30", "remaining_time": "6:21:53", "throughput": 4440.31, "total_tokens": 30505808} {"current_steps": 14145, "total_steps": 61300, "loss": 0.342, "lr": 4.744169455424151e-05, "epoch": 2.3075040783034257, "percentage": 23.08, "elapsed_time": "1:54:32", "remaining_time": "6:21:50", "throughput": 4440.44, "total_tokens": 30516368} {"current_steps": 14150, "total_steps": 61300, "loss": 0.3351, "lr": 4.7438556943196574e-05, "epoch": 2.3083197389885806, "percentage": 23.08, "elapsed_time": "1:54:34", "remaining_time": "6:21:47", "throughput": 4440.57, "total_tokens": 30527856} {"current_steps": 14155, "total_steps": 61300, "loss": 0.3689, "lr": 4.743541751316837e-05, "epoch": 2.309135399673736, "percentage": 23.09, "elapsed_time": "1:54:36", "remaining_time": "6:21:44", "throughput": 4440.67, "total_tokens": 30537936} {"current_steps": 14160, "total_steps": 61300, "loss": 0.3301, "lr": 4.743227626441139e-05, "epoch": 2.3099510603588906, "percentage": 23.1, "elapsed_time": "1:54:39", "remaining_time": "6:21:40", "throughput": 4440.79, "total_tokens": 30548304} {"current_steps": 14165, "total_steps": 61300, "loss": 0.3367, "lr": 4.7429133197180264e-05, "epoch": 2.310766721044046, "percentage": 23.11, "elapsed_time": "1:54:41", "remaining_time": "6:21:38", "throughput": 4440.92, "total_tokens": 30559728} {"current_steps": 14170, "total_steps": 61300, "loss": 0.3457, "lr": 4.7425988311729805e-05, "epoch": 2.3115823817292007, "percentage": 23.12, "elapsed_time": "1:54:43", "remaining_time": "6:21:34", "throughput": 4441.0, "total_tokens": 30569840} {"current_steps": 14175, "total_steps": 61300, "loss": 0.3599, "lr": 4.742284160831494e-05, "epoch": 2.3123980424143555, "percentage": 23.12, "elapsed_time": "1:54:45", "remaining_time": "6:21:31", "throughput": 4441.11, "total_tokens": 30580400} {"current_steps": 14180, "total_steps": 61300, "loss": 0.317, "lr": 4.741969308719076e-05, "epoch": 2.3132137030995104, "percentage": 23.13, "elapsed_time": "1:54:48", "remaining_time": "6:21:31", "throughput": 4441.27, "total_tokens": 30594544} {"current_steps": 14185, "total_steps": 61300, "loss": 0.3654, "lr": 4.741654274861251e-05, "epoch": 2.3140293637846656, "percentage": 23.14, "elapsed_time": "1:54:50", "remaining_time": "6:21:27", "throughput": 4441.4, "total_tokens": 30604912} {"current_steps": 14190, "total_steps": 61300, "loss": 0.3325, "lr": 4.741339059283556e-05, "epoch": 2.3148450244698204, "percentage": 23.15, "elapsed_time": "1:54:53", "remaining_time": "6:21:24", "throughput": 4441.55, "total_tokens": 30616400} {"current_steps": 14195, "total_steps": 61300, "loss": 0.3448, "lr": 4.7410236620115444e-05, "epoch": 2.3156606851549757, "percentage": 23.16, "elapsed_time": "1:54:55", "remaining_time": "6:21:22", "throughput": 4441.68, "total_tokens": 30627824} {"current_steps": 14200, "total_steps": 61300, "loss": 0.3761, "lr": 4.740708083070784e-05, "epoch": 2.3164763458401305, "percentage": 23.16, "elapsed_time": "1:54:57", "remaining_time": "6:21:19", "throughput": 4441.8, "total_tokens": 30638320} {"current_steps": 14205, "total_steps": 61300, "loss": 0.3338, "lr": 4.740392322486858e-05, "epoch": 2.3172920065252853, "percentage": 23.17, "elapsed_time": "1:55:00", "remaining_time": "6:21:16", "throughput": 4441.94, "total_tokens": 30649744} {"current_steps": 14210, "total_steps": 61300, "loss": 0.3333, "lr": 4.740076380285361e-05, "epoch": 2.3181076672104406, "percentage": 23.18, "elapsed_time": "1:55:02", "remaining_time": "6:21:13", "throughput": 4442.05, "total_tokens": 30661136} {"current_steps": 14215, "total_steps": 61300, "loss": 0.3412, "lr": 4.739760256491908e-05, "epoch": 2.3189233278955954, "percentage": 23.19, "elapsed_time": "1:55:04", "remaining_time": "6:21:11", "throughput": 4442.19, "total_tokens": 30672368} {"current_steps": 14220, "total_steps": 61300, "loss": 0.3323, "lr": 4.7394439511321225e-05, "epoch": 2.3197389885807502, "percentage": 23.2, "elapsed_time": "1:55:07", "remaining_time": "6:21:09", "throughput": 4442.34, "total_tokens": 30684784} {"current_steps": 14225, "total_steps": 61300, "loss": 0.3445, "lr": 4.7391274642316485e-05, "epoch": 2.3205546492659055, "percentage": 23.21, "elapsed_time": "1:55:09", "remaining_time": "6:21:06", "throughput": 4442.46, "total_tokens": 30696432} {"current_steps": 14230, "total_steps": 61300, "loss": 0.3605, "lr": 4.7388107958161414e-05, "epoch": 2.3213703099510603, "percentage": 23.21, "elapsed_time": "1:55:11", "remaining_time": "6:21:02", "throughput": 4442.57, "total_tokens": 30706256} {"current_steps": 14235, "total_steps": 61300, "loss": 0.3409, "lr": 4.738493945911271e-05, "epoch": 2.322185970636215, "percentage": 23.22, "elapsed_time": "1:55:14", "remaining_time": "6:20:59", "throughput": 4442.67, "total_tokens": 30716976} {"current_steps": 14240, "total_steps": 61300, "loss": 0.3758, "lr": 4.738176914542723e-05, "epoch": 2.3230016313213704, "percentage": 23.23, "elapsed_time": "1:55:16", "remaining_time": "6:20:56", "throughput": 4442.77, "total_tokens": 30726768} {"current_steps": 14245, "total_steps": 61300, "loss": 0.3458, "lr": 4.737859701736199e-05, "epoch": 2.323817292006525, "percentage": 23.24, "elapsed_time": "1:55:18", "remaining_time": "6:20:52", "throughput": 4442.9, "total_tokens": 30737072} {"current_steps": 14250, "total_steps": 61300, "loss": 0.3373, "lr": 4.737542307517413e-05, "epoch": 2.3246329526916805, "percentage": 23.25, "elapsed_time": "1:55:20", "remaining_time": "6:20:50", "throughput": 4443.02, "total_tokens": 30748400} {"current_steps": 14255, "total_steps": 61300, "loss": 0.3381, "lr": 4.737224731912093e-05, "epoch": 2.3254486133768353, "percentage": 23.25, "elapsed_time": "1:55:23", "remaining_time": "6:20:47", "throughput": 4443.17, "total_tokens": 30760240} {"current_steps": 14260, "total_steps": 61300, "loss": 0.3573, "lr": 4.736906974945986e-05, "epoch": 2.32626427406199, "percentage": 23.26, "elapsed_time": "1:55:25", "remaining_time": "6:20:44", "throughput": 4443.31, "total_tokens": 30770928} {"current_steps": 14265, "total_steps": 61300, "loss": 0.382, "lr": 4.736589036644848e-05, "epoch": 2.3270799347471454, "percentage": 23.27, "elapsed_time": "1:55:27", "remaining_time": "6:20:40", "throughput": 4443.4, "total_tokens": 30780240} {"current_steps": 14270, "total_steps": 61300, "loss": 0.3183, "lr": 4.736270917034456e-05, "epoch": 2.3278955954323, "percentage": 23.28, "elapsed_time": "1:55:29", "remaining_time": "6:20:38", "throughput": 4443.51, "total_tokens": 30792144} {"current_steps": 14275, "total_steps": 61300, "loss": 0.3376, "lr": 4.735952616140597e-05, "epoch": 2.328711256117455, "percentage": 23.29, "elapsed_time": "1:55:31", "remaining_time": "6:20:34", "throughput": 4443.63, "total_tokens": 30802416} {"current_steps": 14280, "total_steps": 61300, "loss": 0.3363, "lr": 4.735634133989072e-05, "epoch": 2.3295269168026103, "percentage": 23.3, "elapsed_time": "1:55:34", "remaining_time": "6:20:32", "throughput": 4443.75, "total_tokens": 30813872} {"current_steps": 14285, "total_steps": 61300, "loss": 0.3203, "lr": 4.735315470605702e-05, "epoch": 2.330342577487765, "percentage": 23.3, "elapsed_time": "1:55:36", "remaining_time": "6:20:29", "throughput": 4443.89, "total_tokens": 30825584} {"current_steps": 14290, "total_steps": 61300, "loss": 0.3676, "lr": 4.734996626016317e-05, "epoch": 2.33115823817292, "percentage": 23.31, "elapsed_time": "1:55:38", "remaining_time": "6:20:27", "throughput": 4443.99, "total_tokens": 30836688} {"current_steps": 14295, "total_steps": 61300, "loss": 0.3385, "lr": 4.7346776002467664e-05, "epoch": 2.331973898858075, "percentage": 23.32, "elapsed_time": "1:55:41", "remaining_time": "6:20:25", "throughput": 4444.13, "total_tokens": 30848816} {"current_steps": 14300, "total_steps": 61300, "loss": 0.3561, "lr": 4.73435839332291e-05, "epoch": 2.33278955954323, "percentage": 23.33, "elapsed_time": "1:55:43", "remaining_time": "6:20:21", "throughput": 4444.23, "total_tokens": 30858608} {"current_steps": 14305, "total_steps": 61300, "loss": 0.3675, "lr": 4.734039005270625e-05, "epoch": 2.3336052202283852, "percentage": 23.34, "elapsed_time": "1:55:45", "remaining_time": "6:20:17", "throughput": 4444.33, "total_tokens": 30868560} {"current_steps": 14310, "total_steps": 61300, "loss": 0.3215, "lr": 4.733719436115804e-05, "epoch": 2.33442088091354, "percentage": 23.34, "elapsed_time": "1:55:47", "remaining_time": "6:20:13", "throughput": 4444.43, "total_tokens": 30878192} {"current_steps": 14315, "total_steps": 61300, "loss": 0.3393, "lr": 4.733399685884351e-05, "epoch": 2.335236541598695, "percentage": 23.35, "elapsed_time": "1:55:49", "remaining_time": "6:20:10", "throughput": 4444.51, "total_tokens": 30888432} {"current_steps": 14320, "total_steps": 61300, "loss": 0.3142, "lr": 4.7330797546021876e-05, "epoch": 2.3360522022838497, "percentage": 23.36, "elapsed_time": "1:55:51", "remaining_time": "6:20:07", "throughput": 4444.62, "total_tokens": 30898864} {"current_steps": 14325, "total_steps": 61300, "loss": 0.4109, "lr": 4.732759642295248e-05, "epoch": 2.336867862969005, "percentage": 23.37, "elapsed_time": "1:55:54", "remaining_time": "6:20:04", "throughput": 4444.72, "total_tokens": 30909424} {"current_steps": 14330, "total_steps": 61300, "loss": 0.3352, "lr": 4.732439348989484e-05, "epoch": 2.3376835236541598, "percentage": 23.38, "elapsed_time": "1:55:56", "remaining_time": "6:20:01", "throughput": 4444.81, "total_tokens": 30919600} {"current_steps": 14335, "total_steps": 61300, "loss": 0.3186, "lr": 4.732118874710858e-05, "epoch": 2.338499184339315, "percentage": 23.38, "elapsed_time": "1:55:58", "remaining_time": "6:19:58", "throughput": 4444.91, "total_tokens": 30930416} {"current_steps": 14340, "total_steps": 61300, "loss": 0.375, "lr": 4.731798219485351e-05, "epoch": 2.33931484502447, "percentage": 23.39, "elapsed_time": "1:56:00", "remaining_time": "6:19:54", "throughput": 4445.03, "total_tokens": 30940560} {"current_steps": 14345, "total_steps": 61300, "loss": 0.3129, "lr": 4.7314773833389567e-05, "epoch": 2.3401305057096247, "percentage": 23.4, "elapsed_time": "1:56:02", "remaining_time": "6:19:51", "throughput": 4445.15, "total_tokens": 30951440} {"current_steps": 14350, "total_steps": 61300, "loss": 0.3813, "lr": 4.731156366297682e-05, "epoch": 2.34094616639478, "percentage": 23.41, "elapsed_time": "1:56:05", "remaining_time": "6:19:48", "throughput": 4445.25, "total_tokens": 30961936} {"current_steps": 14355, "total_steps": 61300, "loss": 0.3416, "lr": 4.730835168387553e-05, "epoch": 2.3417618270799347, "percentage": 23.42, "elapsed_time": "1:56:07", "remaining_time": "6:19:45", "throughput": 4445.35, "total_tokens": 30972112} {"current_steps": 14360, "total_steps": 61300, "loss": 0.3187, "lr": 4.730513789634605e-05, "epoch": 2.3425774877650896, "percentage": 23.43, "elapsed_time": "1:56:09", "remaining_time": "6:19:42", "throughput": 4445.5, "total_tokens": 30984272} {"current_steps": 14365, "total_steps": 61300, "loss": 0.3471, "lr": 4.7301922300648926e-05, "epoch": 2.343393148450245, "percentage": 23.43, "elapsed_time": "1:56:12", "remaining_time": "6:19:40", "throughput": 4445.61, "total_tokens": 30996368} {"current_steps": 14370, "total_steps": 61300, "loss": 0.3496, "lr": 4.729870489704481e-05, "epoch": 2.3442088091353996, "percentage": 23.44, "elapsed_time": "1:56:14", "remaining_time": "6:19:37", "throughput": 4445.75, "total_tokens": 31007216} {"current_steps": 14375, "total_steps": 61300, "loss": 0.3698, "lr": 4.729548568579454e-05, "epoch": 2.3450244698205545, "percentage": 23.45, "elapsed_time": "1:56:16", "remaining_time": "6:19:35", "throughput": 4445.86, "total_tokens": 31018416} {"current_steps": 14380, "total_steps": 61300, "loss": 0.3503, "lr": 4.729226466715907e-05, "epoch": 2.3458401305057097, "percentage": 23.46, "elapsed_time": "1:56:19", "remaining_time": "6:19:32", "throughput": 4446.0, "total_tokens": 31030416} {"current_steps": 14385, "total_steps": 61300, "loss": 0.3587, "lr": 4.728904184139952e-05, "epoch": 2.3466557911908645, "percentage": 23.47, "elapsed_time": "1:56:21", "remaining_time": "6:19:29", "throughput": 4446.1, "total_tokens": 31040752} {"current_steps": 14390, "total_steps": 61300, "loss": 0.3491, "lr": 4.728581720877715e-05, "epoch": 2.34747145187602, "percentage": 23.47, "elapsed_time": "1:56:23", "remaining_time": "6:19:26", "throughput": 4446.2, "total_tokens": 31052048} {"current_steps": 14395, "total_steps": 61300, "loss": 0.3478, "lr": 4.7282590769553346e-05, "epoch": 2.3482871125611746, "percentage": 23.48, "elapsed_time": "1:56:26", "remaining_time": "6:19:23", "throughput": 4446.31, "total_tokens": 31062320} {"current_steps": 14400, "total_steps": 61300, "loss": 0.3443, "lr": 4.727936252398969e-05, "epoch": 2.3491027732463294, "percentage": 23.49, "elapsed_time": "1:56:28", "remaining_time": "6:19:19", "throughput": 4446.43, "total_tokens": 31071856} {"current_steps": 14405, "total_steps": 61300, "loss": 0.3613, "lr": 4.727613247234785e-05, "epoch": 2.3499184339314847, "percentage": 23.5, "elapsed_time": "1:56:30", "remaining_time": "6:19:16", "throughput": 4446.55, "total_tokens": 31082096} {"current_steps": 14410, "total_steps": 61300, "loss": 0.3407, "lr": 4.727290061488969e-05, "epoch": 2.3507340946166395, "percentage": 23.51, "elapsed_time": "1:56:32", "remaining_time": "6:19:12", "throughput": 4446.64, "total_tokens": 31092400} {"current_steps": 14415, "total_steps": 61300, "loss": 0.3306, "lr": 4.726966695187719e-05, "epoch": 2.3515497553017943, "percentage": 23.52, "elapsed_time": "1:56:34", "remaining_time": "6:19:09", "throughput": 4446.75, "total_tokens": 31102768} {"current_steps": 14420, "total_steps": 61300, "loss": 0.3389, "lr": 4.7266431483572495e-05, "epoch": 2.3523654159869496, "percentage": 23.52, "elapsed_time": "1:56:36", "remaining_time": "6:19:06", "throughput": 4446.88, "total_tokens": 31113936} {"current_steps": 14425, "total_steps": 61300, "loss": 0.3164, "lr": 4.726319421023789e-05, "epoch": 2.3531810766721044, "percentage": 23.53, "elapsed_time": "1:56:38", "remaining_time": "6:19:03", "throughput": 4446.99, "total_tokens": 31123920} {"current_steps": 14430, "total_steps": 61300, "loss": 0.3531, "lr": 4.725995513213579e-05, "epoch": 2.3539967373572592, "percentage": 23.54, "elapsed_time": "1:56:41", "remaining_time": "6:19:00", "throughput": 4447.11, "total_tokens": 31135472} {"current_steps": 14435, "total_steps": 61300, "loss": 0.4023, "lr": 4.725671424952879e-05, "epoch": 2.3548123980424145, "percentage": 23.55, "elapsed_time": "1:56:43", "remaining_time": "6:18:57", "throughput": 4447.24, "total_tokens": 31145552} {"current_steps": 14440, "total_steps": 61300, "loss": 0.3066, "lr": 4.7253471562679594e-05, "epoch": 2.3556280587275693, "percentage": 23.56, "elapsed_time": "1:56:45", "remaining_time": "6:18:55", "throughput": 4447.38, "total_tokens": 31157680} {"current_steps": 14445, "total_steps": 61300, "loss": 0.3565, "lr": 4.725022707185109e-05, "epoch": 2.356443719412724, "percentage": 23.56, "elapsed_time": "1:56:48", "remaining_time": "6:18:52", "throughput": 4447.51, "total_tokens": 31168720} {"current_steps": 14450, "total_steps": 61300, "loss": 0.3132, "lr": 4.724698077730628e-05, "epoch": 2.3572593800978794, "percentage": 23.57, "elapsed_time": "1:56:50", "remaining_time": "6:18:48", "throughput": 4447.62, "total_tokens": 31178832} {"current_steps": 14455, "total_steps": 61300, "loss": 0.37, "lr": 4.7243732679308325e-05, "epoch": 2.358075040783034, "percentage": 23.58, "elapsed_time": "1:56:52", "remaining_time": "6:18:46", "throughput": 4447.74, "total_tokens": 31190288} {"current_steps": 14460, "total_steps": 61300, "loss": 0.3604, "lr": 4.724048277812054e-05, "epoch": 2.358890701468189, "percentage": 23.59, "elapsed_time": "1:56:55", "remaining_time": "6:18:43", "throughput": 4447.89, "total_tokens": 31202128} {"current_steps": 14465, "total_steps": 61300, "loss": 0.2985, "lr": 4.7237231074006374e-05, "epoch": 2.3597063621533443, "percentage": 23.6, "elapsed_time": "1:56:57", "remaining_time": "6:18:40", "throughput": 4448.02, "total_tokens": 31213232} {"current_steps": 14470, "total_steps": 61300, "loss": 0.3249, "lr": 4.723397756722942e-05, "epoch": 2.360522022838499, "percentage": 23.61, "elapsed_time": "1:56:59", "remaining_time": "6:18:37", "throughput": 4448.14, "total_tokens": 31224272} {"current_steps": 14475, "total_steps": 61300, "loss": 0.3556, "lr": 4.7230722258053434e-05, "epoch": 2.3613376835236544, "percentage": 23.61, "elapsed_time": "1:57:01", "remaining_time": "6:18:34", "throughput": 4448.25, "total_tokens": 31234064} {"current_steps": 14480, "total_steps": 61300, "loss": 0.3387, "lr": 4.7227465146742304e-05, "epoch": 2.362153344208809, "percentage": 23.62, "elapsed_time": "1:57:04", "remaining_time": "6:18:31", "throughput": 4448.39, "total_tokens": 31245776} {"current_steps": 14485, "total_steps": 61300, "loss": 0.351, "lr": 4.722420623356007e-05, "epoch": 2.362969004893964, "percentage": 23.63, "elapsed_time": "1:57:06", "remaining_time": "6:18:29", "throughput": 4448.53, "total_tokens": 31257392} {"current_steps": 14490, "total_steps": 61300, "loss": 0.3706, "lr": 4.722094551877091e-05, "epoch": 2.3637846655791193, "percentage": 23.64, "elapsed_time": "1:57:08", "remaining_time": "6:18:25", "throughput": 4448.64, "total_tokens": 31267408} {"current_steps": 14495, "total_steps": 61300, "loss": 0.3552, "lr": 4.7217683002639165e-05, "epoch": 2.364600326264274, "percentage": 23.65, "elapsed_time": "1:57:10", "remaining_time": "6:18:23", "throughput": 4448.79, "total_tokens": 31278960} {"current_steps": 14500, "total_steps": 61300, "loss": 0.3504, "lr": 4.7214418685429295e-05, "epoch": 2.365415986949429, "percentage": 23.65, "elapsed_time": "1:57:12", "remaining_time": "6:18:19", "throughput": 4448.93, "total_tokens": 31289264} {"current_steps": 14505, "total_steps": 61300, "loss": 0.3481, "lr": 4.721115256740594e-05, "epoch": 2.366231647634584, "percentage": 23.66, "elapsed_time": "1:57:15", "remaining_time": "6:18:15", "throughput": 4449.05, "total_tokens": 31299152} {"current_steps": 14510, "total_steps": 61300, "loss": 0.3543, "lr": 4.720788464883385e-05, "epoch": 2.367047308319739, "percentage": 23.67, "elapsed_time": "1:57:17", "remaining_time": "6:18:12", "throughput": 4449.16, "total_tokens": 31308944} {"current_steps": 14515, "total_steps": 61300, "loss": 0.3078, "lr": 4.720461492997796e-05, "epoch": 2.367862969004894, "percentage": 23.68, "elapsed_time": "1:57:19", "remaining_time": "6:18:09", "throughput": 4449.28, "total_tokens": 31319824} {"current_steps": 14520, "total_steps": 61300, "loss": 0.3247, "lr": 4.720134341110332e-05, "epoch": 2.368678629690049, "percentage": 23.69, "elapsed_time": "1:57:21", "remaining_time": "6:18:07", "throughput": 4449.43, "total_tokens": 31332016} {"current_steps": 14525, "total_steps": 61300, "loss": 0.3478, "lr": 4.719807009247513e-05, "epoch": 2.369494290375204, "percentage": 23.69, "elapsed_time": "1:57:24", "remaining_time": "6:18:03", "throughput": 4449.53, "total_tokens": 31342512} {"current_steps": 14530, "total_steps": 61300, "loss": 0.3463, "lr": 4.7194794974358744e-05, "epoch": 2.370309951060359, "percentage": 23.7, "elapsed_time": "1:57:26", "remaining_time": "6:18:00", "throughput": 4449.65, "total_tokens": 31352528} {"current_steps": 14535, "total_steps": 61300, "loss": 0.3399, "lr": 4.719151805701966e-05, "epoch": 2.371125611745514, "percentage": 23.71, "elapsed_time": "1:57:27", "remaining_time": "6:17:56", "throughput": 4449.75, "total_tokens": 31361520} {"current_steps": 14540, "total_steps": 61300, "loss": 0.3742, "lr": 4.7188239340723526e-05, "epoch": 2.3719412724306688, "percentage": 23.72, "elapsed_time": "1:57:30", "remaining_time": "6:17:53", "throughput": 4449.86, "total_tokens": 31372304} {"current_steps": 14545, "total_steps": 61300, "loss": 0.3171, "lr": 4.7184958825736135e-05, "epoch": 2.3727569331158236, "percentage": 23.73, "elapsed_time": "1:57:32", "remaining_time": "6:17:49", "throughput": 4449.97, "total_tokens": 31382960} {"current_steps": 14550, "total_steps": 61300, "loss": 0.3771, "lr": 4.718167651232341e-05, "epoch": 2.373572593800979, "percentage": 23.74, "elapsed_time": "1:57:34", "remaining_time": "6:17:47", "throughput": 4450.09, "total_tokens": 31394128} {"current_steps": 14555, "total_steps": 61300, "loss": 0.3648, "lr": 4.7178392400751433e-05, "epoch": 2.3743882544861337, "percentage": 23.74, "elapsed_time": "1:57:37", "remaining_time": "6:17:44", "throughput": 4450.19, "total_tokens": 31405072} {"current_steps": 14560, "total_steps": 61300, "loss": 0.3417, "lr": 4.7175106491286446e-05, "epoch": 2.375203915171289, "percentage": 23.75, "elapsed_time": "1:57:39", "remaining_time": "6:17:40", "throughput": 4450.31, "total_tokens": 31415280} {"current_steps": 14565, "total_steps": 61300, "loss": 0.3482, "lr": 4.717181878419481e-05, "epoch": 2.3760195758564437, "percentage": 23.76, "elapsed_time": "1:57:41", "remaining_time": "6:17:38", "throughput": 4450.42, "total_tokens": 31426384} {"current_steps": 14570, "total_steps": 61300, "loss": 0.3233, "lr": 4.7168529279743046e-05, "epoch": 2.3768352365415986, "percentage": 23.77, "elapsed_time": "1:57:43", "remaining_time": "6:17:34", "throughput": 4450.51, "total_tokens": 31436304} {"current_steps": 14575, "total_steps": 61300, "loss": 0.3476, "lr": 4.716523797819781e-05, "epoch": 2.377650897226754, "percentage": 23.78, "elapsed_time": "1:57:45", "remaining_time": "6:17:32", "throughput": 4450.67, "total_tokens": 31448240} {"current_steps": 14580, "total_steps": 61300, "loss": 0.3336, "lr": 4.716194487982592e-05, "epoch": 2.3784665579119086, "percentage": 23.78, "elapsed_time": "1:57:48", "remaining_time": "6:17:29", "throughput": 4450.78, "total_tokens": 31458928} {"current_steps": 14585, "total_steps": 61300, "loss": 0.3476, "lr": 4.715864998489433e-05, "epoch": 2.3792822185970635, "percentage": 23.79, "elapsed_time": "1:57:50", "remaining_time": "6:17:26", "throughput": 4450.9, "total_tokens": 31470480} {"current_steps": 14590, "total_steps": 61300, "loss": 0.3657, "lr": 4.715535329367014e-05, "epoch": 2.3800978792822187, "percentage": 23.8, "elapsed_time": "1:57:52", "remaining_time": "6:17:24", "throughput": 4451.02, "total_tokens": 31481968} {"current_steps": 14595, "total_steps": 61300, "loss": 0.3784, "lr": 4.71520548064206e-05, "epoch": 2.3809135399673735, "percentage": 23.81, "elapsed_time": "1:57:55", "remaining_time": "6:17:21", "throughput": 4451.13, "total_tokens": 31493360} {"current_steps": 14600, "total_steps": 61300, "loss": 0.3298, "lr": 4.71487545234131e-05, "epoch": 2.3817292006525284, "percentage": 23.82, "elapsed_time": "1:57:57", "remaining_time": "6:17:19", "throughput": 4451.27, "total_tokens": 31505552} {"current_steps": 14605, "total_steps": 61300, "loss": 0.3543, "lr": 4.7145452444915175e-05, "epoch": 2.3825448613376836, "percentage": 23.83, "elapsed_time": "1:58:00", "remaining_time": "6:17:16", "throughput": 4451.39, "total_tokens": 31516336} {"current_steps": 14610, "total_steps": 61300, "loss": 0.3389, "lr": 4.71421485711945e-05, "epoch": 2.3833605220228384, "percentage": 23.83, "elapsed_time": "1:58:02", "remaining_time": "6:17:13", "throughput": 4451.51, "total_tokens": 31527152} {"current_steps": 14615, "total_steps": 61300, "loss": 0.369, "lr": 4.713884290251892e-05, "epoch": 2.3841761827079937, "percentage": 23.84, "elapsed_time": "1:58:04", "remaining_time": "6:17:09", "throughput": 4451.6, "total_tokens": 31536400} {"current_steps": 14620, "total_steps": 61300, "loss": 0.3656, "lr": 4.713553543915641e-05, "epoch": 2.3849918433931485, "percentage": 23.85, "elapsed_time": "1:58:06", "remaining_time": "6:17:06", "throughput": 4451.7, "total_tokens": 31547056} {"current_steps": 14625, "total_steps": 61300, "loss": 0.3441, "lr": 4.713222618137508e-05, "epoch": 2.3858075040783033, "percentage": 23.86, "elapsed_time": "1:58:08", "remaining_time": "6:17:03", "throughput": 4451.79, "total_tokens": 31557840} {"current_steps": 14630, "total_steps": 61300, "loss": 0.3322, "lr": 4.71289151294432e-05, "epoch": 2.3866231647634586, "percentage": 23.87, "elapsed_time": "1:58:11", "remaining_time": "6:17:01", "throughput": 4451.92, "total_tokens": 31569424} {"current_steps": 14635, "total_steps": 61300, "loss": 0.3292, "lr": 4.7125602283629166e-05, "epoch": 2.3874388254486134, "percentage": 23.87, "elapsed_time": "1:58:13", "remaining_time": "6:16:57", "throughput": 4452.03, "total_tokens": 31579504} {"current_steps": 14640, "total_steps": 61300, "loss": 0.3327, "lr": 4.7122287644201556e-05, "epoch": 2.3882544861337682, "percentage": 23.88, "elapsed_time": "1:58:15", "remaining_time": "6:16:55", "throughput": 4452.16, "total_tokens": 31591120} {"current_steps": 14645, "total_steps": 61300, "loss": 0.3399, "lr": 4.711897121142906e-05, "epoch": 2.3890701468189235, "percentage": 23.89, "elapsed_time": "1:58:17", "remaining_time": "6:16:52", "throughput": 4452.26, "total_tokens": 31601968} {"current_steps": 14650, "total_steps": 61300, "loss": 0.3157, "lr": 4.711565298558053e-05, "epoch": 2.3898858075040783, "percentage": 23.9, "elapsed_time": "1:58:20", "remaining_time": "6:16:49", "throughput": 4452.37, "total_tokens": 31612944} {"current_steps": 14655, "total_steps": 61300, "loss": 0.3461, "lr": 4.711233296692495e-05, "epoch": 2.390701468189233, "percentage": 23.91, "elapsed_time": "1:58:22", "remaining_time": "6:16:46", "throughput": 4452.47, "total_tokens": 31623472} {"current_steps": 14660, "total_steps": 61300, "loss": 0.3685, "lr": 4.7109011155731475e-05, "epoch": 2.3915171288743884, "percentage": 23.92, "elapsed_time": "1:58:24", "remaining_time": "6:16:43", "throughput": 4452.62, "total_tokens": 31635248} {"current_steps": 14665, "total_steps": 61300, "loss": 0.3533, "lr": 4.710568755226936e-05, "epoch": 2.392332789559543, "percentage": 23.92, "elapsed_time": "1:58:27", "remaining_time": "6:16:40", "throughput": 4452.72, "total_tokens": 31646320} {"current_steps": 14670, "total_steps": 61300, "loss": 0.3586, "lr": 4.710236215680806e-05, "epoch": 2.393148450244698, "percentage": 23.93, "elapsed_time": "1:58:29", "remaining_time": "6:16:38", "throughput": 4452.89, "total_tokens": 31658608} {"current_steps": 14675, "total_steps": 61300, "loss": 0.3136, "lr": 4.709903496961713e-05, "epoch": 2.3939641109298533, "percentage": 23.94, "elapsed_time": "1:58:31", "remaining_time": "6:16:35", "throughput": 4453.01, "total_tokens": 31669680} {"current_steps": 14680, "total_steps": 61300, "loss": 0.3544, "lr": 4.7095705990966306e-05, "epoch": 2.394779771615008, "percentage": 23.95, "elapsed_time": "1:58:34", "remaining_time": "6:16:32", "throughput": 4453.12, "total_tokens": 31679696} {"current_steps": 14685, "total_steps": 61300, "loss": 0.3093, "lr": 4.709237522112543e-05, "epoch": 2.395595432300163, "percentage": 23.96, "elapsed_time": "1:58:36", "remaining_time": "6:16:30", "throughput": 4453.25, "total_tokens": 31691472} {"current_steps": 14690, "total_steps": 61300, "loss": 0.3282, "lr": 4.708904266036453e-05, "epoch": 2.396411092985318, "percentage": 23.96, "elapsed_time": "1:58:38", "remaining_time": "6:16:26", "throughput": 4453.37, "total_tokens": 31701968} {"current_steps": 14695, "total_steps": 61300, "loss": 0.3309, "lr": 4.7085708308953754e-05, "epoch": 2.397226753670473, "percentage": 23.97, "elapsed_time": "1:58:40", "remaining_time": "6:16:24", "throughput": 4453.48, "total_tokens": 31713104} {"current_steps": 14700, "total_steps": 61300, "loss": 0.3051, "lr": 4.7082372167163394e-05, "epoch": 2.3980424143556283, "percentage": 23.98, "elapsed_time": "1:58:43", "remaining_time": "6:16:21", "throughput": 4453.6, "total_tokens": 31724560} {"current_steps": 14705, "total_steps": 61300, "loss": 0.355, "lr": 4.707903423526391e-05, "epoch": 2.398858075040783, "percentage": 23.99, "elapsed_time": "1:58:45", "remaining_time": "6:16:17", "throughput": 4453.68, "total_tokens": 31733776} {"current_steps": 14710, "total_steps": 61300, "loss": 0.2896, "lr": 4.707569451352588e-05, "epoch": 2.399673735725938, "percentage": 24.0, "elapsed_time": "1:58:47", "remaining_time": "6:16:15", "throughput": 4453.8, "total_tokens": 31745680} {"current_steps": 14715, "total_steps": 61300, "loss": 0.3418, "lr": 4.707235300222004e-05, "epoch": 2.400489396411093, "percentage": 24.0, "elapsed_time": "1:58:49", "remaining_time": "6:16:12", "throughput": 4453.9, "total_tokens": 31756240} {"current_steps": 14720, "total_steps": 61300, "loss": 0.3673, "lr": 4.706900970161727e-05, "epoch": 2.401305057096248, "percentage": 24.01, "elapsed_time": "1:58:52", "remaining_time": "6:16:09", "throughput": 4454.01, "total_tokens": 31767056} {"current_steps": 14725, "total_steps": 61300, "loss": 0.3348, "lr": 4.7065664611988596e-05, "epoch": 2.402120717781403, "percentage": 24.02, "elapsed_time": "1:58:54", "remaining_time": "6:16:06", "throughput": 4454.12, "total_tokens": 31777968} {"current_steps": 14730, "total_steps": 61300, "loss": 0.3243, "lr": 4.7062317733605185e-05, "epoch": 2.402936378466558, "percentage": 24.03, "elapsed_time": "1:58:56", "remaining_time": "6:16:03", "throughput": 4454.22, "total_tokens": 31788976} {"current_steps": 14735, "total_steps": 61300, "loss": 0.3483, "lr": 4.705896906673837e-05, "epoch": 2.403752039151713, "percentage": 24.04, "elapsed_time": "1:58:58", "remaining_time": "6:16:00", "throughput": 4454.33, "total_tokens": 31799280} {"current_steps": 14740, "total_steps": 61300, "loss": 0.3259, "lr": 4.705561861165959e-05, "epoch": 2.4045676998368677, "percentage": 24.05, "elapsed_time": "1:59:01", "remaining_time": "6:15:57", "throughput": 4454.44, "total_tokens": 31810288} {"current_steps": 14745, "total_steps": 61300, "loss": 0.3062, "lr": 4.705226636864045e-05, "epoch": 2.405383360522023, "percentage": 24.05, "elapsed_time": "1:59:03", "remaining_time": "6:15:54", "throughput": 4454.56, "total_tokens": 31820880} {"current_steps": 14750, "total_steps": 61300, "loss": 0.3577, "lr": 4.704891233795271e-05, "epoch": 2.4061990212071778, "percentage": 24.06, "elapsed_time": "1:59:05", "remaining_time": "6:15:50", "throughput": 4454.66, "total_tokens": 31830704} {"current_steps": 14755, "total_steps": 61300, "loss": 0.3428, "lr": 4.704555651986826e-05, "epoch": 2.407014681892333, "percentage": 24.07, "elapsed_time": "1:59:07", "remaining_time": "6:15:48", "throughput": 4454.8, "total_tokens": 31842608} {"current_steps": 14760, "total_steps": 61300, "loss": 0.3059, "lr": 4.704219891465914e-05, "epoch": 2.407830342577488, "percentage": 24.08, "elapsed_time": "1:59:10", "remaining_time": "6:15:45", "throughput": 4454.91, "total_tokens": 31853456} {"current_steps": 14765, "total_steps": 61300, "loss": 0.3506, "lr": 4.703883952259754e-05, "epoch": 2.4086460032626427, "percentage": 24.09, "elapsed_time": "1:59:12", "remaining_time": "6:15:42", "throughput": 4455.02, "total_tokens": 31864240} {"current_steps": 14770, "total_steps": 61300, "loss": 0.3828, "lr": 4.7035478343955774e-05, "epoch": 2.4094616639477975, "percentage": 24.09, "elapsed_time": "1:59:14", "remaining_time": "6:15:39", "throughput": 4455.11, "total_tokens": 31874896} {"current_steps": 14775, "total_steps": 61300, "loss": 0.3468, "lr": 4.7032115379006337e-05, "epoch": 2.4102773246329527, "percentage": 24.1, "elapsed_time": "1:59:17", "remaining_time": "6:15:37", "throughput": 4455.25, "total_tokens": 31887120} {"current_steps": 14780, "total_steps": 61300, "loss": 0.4226, "lr": 4.7028750628021834e-05, "epoch": 2.4110929853181076, "percentage": 24.11, "elapsed_time": "1:59:19", "remaining_time": "6:15:35", "throughput": 4455.39, "total_tokens": 31899216} {"current_steps": 14785, "total_steps": 61300, "loss": 0.3471, "lr": 4.702538409127503e-05, "epoch": 2.411908646003263, "percentage": 24.12, "elapsed_time": "1:59:22", "remaining_time": "6:15:32", "throughput": 4455.52, "total_tokens": 31911248} {"current_steps": 14790, "total_steps": 61300, "loss": 0.3193, "lr": 4.7022015769038844e-05, "epoch": 2.4127243066884176, "percentage": 24.13, "elapsed_time": "1:59:24", "remaining_time": "6:15:29", "throughput": 4455.65, "total_tokens": 31921264} {"current_steps": 14795, "total_steps": 61300, "loss": 0.3363, "lr": 4.701864566158631e-05, "epoch": 2.4135399673735725, "percentage": 24.14, "elapsed_time": "1:59:26", "remaining_time": "6:15:26", "throughput": 4455.75, "total_tokens": 31932208} {"current_steps": 14800, "total_steps": 61300, "loss": 0.3348, "lr": 4.701527376919064e-05, "epoch": 2.4143556280587277, "percentage": 24.14, "elapsed_time": "1:59:28", "remaining_time": "6:15:23", "throughput": 4455.9, "total_tokens": 31943792} {"current_steps": 14805, "total_steps": 61300, "loss": 0.3291, "lr": 4.701190009212518e-05, "epoch": 2.4151712887438825, "percentage": 24.15, "elapsed_time": "1:59:31", "remaining_time": "6:15:20", "throughput": 4455.99, "total_tokens": 31954128} {"current_steps": 14810, "total_steps": 61300, "loss": 0.3164, "lr": 4.700852463066341e-05, "epoch": 2.4159869494290374, "percentage": 24.16, "elapsed_time": "1:59:33", "remaining_time": "6:15:17", "throughput": 4456.08, "total_tokens": 31964176} {"current_steps": 14815, "total_steps": 61300, "loss": 0.3539, "lr": 4.7005147385078956e-05, "epoch": 2.4168026101141926, "percentage": 24.17, "elapsed_time": "1:59:35", "remaining_time": "6:15:14", "throughput": 4456.21, "total_tokens": 31975312} {"current_steps": 14820, "total_steps": 61300, "loss": 0.3526, "lr": 4.700176835564561e-05, "epoch": 2.4176182707993474, "percentage": 24.18, "elapsed_time": "1:59:37", "remaining_time": "6:15:11", "throughput": 4456.32, "total_tokens": 31985520} {"current_steps": 14825, "total_steps": 61300, "loss": 0.2972, "lr": 4.699838754263728e-05, "epoch": 2.4184339314845023, "percentage": 24.18, "elapsed_time": "1:59:39", "remaining_time": "6:15:08", "throughput": 4456.41, "total_tokens": 31996656} {"current_steps": 14830, "total_steps": 61300, "loss": 0.3421, "lr": 4.6995004946328035e-05, "epoch": 2.4192495921696575, "percentage": 24.19, "elapsed_time": "1:59:41", "remaining_time": "6:15:04", "throughput": 4456.51, "total_tokens": 32005680} {"current_steps": 14835, "total_steps": 61300, "loss": 0.3431, "lr": 4.699162056699209e-05, "epoch": 2.4200652528548123, "percentage": 24.2, "elapsed_time": "1:59:44", "remaining_time": "6:15:01", "throughput": 4456.62, "total_tokens": 32017232} {"current_steps": 14840, "total_steps": 61300, "loss": 0.3282, "lr": 4.698823440490381e-05, "epoch": 2.4208809135399676, "percentage": 24.21, "elapsed_time": "1:59:46", "remaining_time": "6:14:58", "throughput": 4456.74, "total_tokens": 32028112} {"current_steps": 14845, "total_steps": 61300, "loss": 0.3771, "lr": 4.6984846460337664e-05, "epoch": 2.4216965742251224, "percentage": 24.22, "elapsed_time": "1:59:48", "remaining_time": "6:14:55", "throughput": 4456.85, "total_tokens": 32038608} {"current_steps": 14850, "total_steps": 61300, "loss": 0.3414, "lr": 4.698145673356832e-05, "epoch": 2.4225122349102772, "percentage": 24.23, "elapsed_time": "1:59:50", "remaining_time": "6:14:52", "throughput": 4456.96, "total_tokens": 32048880} {"current_steps": 14855, "total_steps": 61300, "loss": 0.3657, "lr": 4.697806522487056e-05, "epoch": 2.4233278955954325, "percentage": 24.23, "elapsed_time": "1:59:52", "remaining_time": "6:14:48", "throughput": 4457.03, "total_tokens": 32058864} {"current_steps": 14860, "total_steps": 61300, "loss": 0.3383, "lr": 4.697467193451932e-05, "epoch": 2.4241435562805873, "percentage": 24.24, "elapsed_time": "1:59:54", "remaining_time": "6:14:45", "throughput": 4457.14, "total_tokens": 32068816} {"current_steps": 14865, "total_steps": 61300, "loss": 0.3772, "lr": 4.6971276862789674e-05, "epoch": 2.424959216965742, "percentage": 24.25, "elapsed_time": "1:59:57", "remaining_time": "6:14:43", "throughput": 4457.26, "total_tokens": 32080848} {"current_steps": 14870, "total_steps": 61300, "loss": 0.297, "lr": 4.6967880009956845e-05, "epoch": 2.4257748776508974, "percentage": 24.26, "elapsed_time": "1:59:59", "remaining_time": "6:14:40", "throughput": 4457.38, "total_tokens": 32091824} {"current_steps": 14875, "total_steps": 61300, "loss": 0.3178, "lr": 4.69644813762962e-05, "epoch": 2.426590538336052, "percentage": 24.27, "elapsed_time": "2:00:01", "remaining_time": "6:14:37", "throughput": 4457.47, "total_tokens": 32102448} {"current_steps": 14880, "total_steps": 61300, "loss": 0.4019, "lr": 4.696108096208324e-05, "epoch": 2.427406199021207, "percentage": 24.27, "elapsed_time": "2:00:04", "remaining_time": "6:14:34", "throughput": 4457.58, "total_tokens": 32114000} {"current_steps": 14885, "total_steps": 61300, "loss": 0.3023, "lr": 4.695767876759363e-05, "epoch": 2.4282218597063623, "percentage": 24.28, "elapsed_time": "2:00:06", "remaining_time": "6:14:32", "throughput": 4457.75, "total_tokens": 32126192} {"current_steps": 14890, "total_steps": 61300, "loss": 0.3769, "lr": 4.695427479310317e-05, "epoch": 2.429037520391517, "percentage": 24.29, "elapsed_time": "2:00:09", "remaining_time": "6:14:29", "throughput": 4457.86, "total_tokens": 32136880} {"current_steps": 14895, "total_steps": 61300, "loss": 0.3291, "lr": 4.6950869038887804e-05, "epoch": 2.429853181076672, "percentage": 24.3, "elapsed_time": "2:00:11", "remaining_time": "6:14:26", "throughput": 4457.95, "total_tokens": 32147408} {"current_steps": 14900, "total_steps": 61300, "loss": 0.3361, "lr": 4.6947461505223614e-05, "epoch": 2.430668841761827, "percentage": 24.31, "elapsed_time": "2:00:13", "remaining_time": "6:14:23", "throughput": 4458.06, "total_tokens": 32158416} {"current_steps": 14905, "total_steps": 61300, "loss": 0.3627, "lr": 4.6944052192386836e-05, "epoch": 2.431484502446982, "percentage": 24.31, "elapsed_time": "2:00:15", "remaining_time": "6:14:20", "throughput": 4458.17, "total_tokens": 32169264} {"current_steps": 14910, "total_steps": 61300, "loss": 0.3321, "lr": 4.6940641100653834e-05, "epoch": 2.432300163132137, "percentage": 24.32, "elapsed_time": "2:00:18", "remaining_time": "6:14:18", "throughput": 4458.29, "total_tokens": 32181872} {"current_steps": 14915, "total_steps": 61300, "loss": 0.3441, "lr": 4.693722823030114e-05, "epoch": 2.433115823817292, "percentage": 24.33, "elapsed_time": "2:00:20", "remaining_time": "6:14:16", "throughput": 4458.38, "total_tokens": 32192816} {"current_steps": 14920, "total_steps": 61300, "loss": 0.3401, "lr": 4.693381358160543e-05, "epoch": 2.433931484502447, "percentage": 24.34, "elapsed_time": "2:00:23", "remaining_time": "6:14:13", "throughput": 4458.5, "total_tokens": 32203952} {"current_steps": 14925, "total_steps": 61300, "loss": 0.3658, "lr": 4.693039715484349e-05, "epoch": 2.434747145187602, "percentage": 24.35, "elapsed_time": "2:00:25", "remaining_time": "6:14:10", "throughput": 4458.63, "total_tokens": 32215088} {"current_steps": 14930, "total_steps": 61300, "loss": 0.3561, "lr": 4.692697895029229e-05, "epoch": 2.435562805872757, "percentage": 24.36, "elapsed_time": "2:00:27", "remaining_time": "6:14:07", "throughput": 4458.72, "total_tokens": 32226256} {"current_steps": 14935, "total_steps": 61300, "loss": 0.331, "lr": 4.6923558968228906e-05, "epoch": 2.436378466557912, "percentage": 24.36, "elapsed_time": "2:00:30", "remaining_time": "6:14:05", "throughput": 4458.85, "total_tokens": 32238096} {"current_steps": 14940, "total_steps": 61300, "loss": 0.3252, "lr": 4.692013720893061e-05, "epoch": 2.437194127243067, "percentage": 24.37, "elapsed_time": "2:00:32", "remaining_time": "6:14:01", "throughput": 4458.95, "total_tokens": 32247440} {"current_steps": 14945, "total_steps": 61300, "loss": 0.3459, "lr": 4.691671367267476e-05, "epoch": 2.438009787928222, "percentage": 24.38, "elapsed_time": "2:00:34", "remaining_time": "6:13:58", "throughput": 4459.06, "total_tokens": 32257488} {"current_steps": 14950, "total_steps": 61300, "loss": 0.3089, "lr": 4.6913288359738895e-05, "epoch": 2.4388254486133767, "percentage": 24.39, "elapsed_time": "2:00:36", "remaining_time": "6:13:55", "throughput": 4459.18, "total_tokens": 32268816} {"current_steps": 14955, "total_steps": 61300, "loss": 0.3269, "lr": 4.690986127040069e-05, "epoch": 2.439641109298532, "percentage": 24.4, "elapsed_time": "2:00:38", "remaining_time": "6:13:52", "throughput": 4459.3, "total_tokens": 32280048} {"current_steps": 14960, "total_steps": 61300, "loss": 0.3201, "lr": 4.690643240493797e-05, "epoch": 2.4404567699836868, "percentage": 24.4, "elapsed_time": "2:00:40", "remaining_time": "6:13:49", "throughput": 4459.4, "total_tokens": 32289680} {"current_steps": 14965, "total_steps": 61300, "loss": 0.3646, "lr": 4.690300176362867e-05, "epoch": 2.4412724306688416, "percentage": 24.41, "elapsed_time": "2:00:43", "remaining_time": "6:13:46", "throughput": 4459.51, "total_tokens": 32300656} {"current_steps": 14970, "total_steps": 61300, "loss": 0.2778, "lr": 4.6899569346750924e-05, "epoch": 2.442088091353997, "percentage": 24.42, "elapsed_time": "2:00:45", "remaining_time": "6:13:43", "throughput": 4459.63, "total_tokens": 32311888} {"current_steps": 14975, "total_steps": 61300, "loss": 0.2945, "lr": 4.689613515458297e-05, "epoch": 2.4429037520391517, "percentage": 24.43, "elapsed_time": "2:00:47", "remaining_time": "6:13:40", "throughput": 4459.74, "total_tokens": 32323248} {"current_steps": 14980, "total_steps": 61300, "loss": 0.3424, "lr": 4.68926991874032e-05, "epoch": 2.443719412724307, "percentage": 24.44, "elapsed_time": "2:00:49", "remaining_time": "6:13:37", "throughput": 4459.85, "total_tokens": 32333808} {"current_steps": 14985, "total_steps": 61300, "loss": 0.3543, "lr": 4.688926144549015e-05, "epoch": 2.4445350734094617, "percentage": 24.45, "elapsed_time": "2:00:52", "remaining_time": "6:13:35", "throughput": 4459.98, "total_tokens": 32345648} {"current_steps": 14990, "total_steps": 61300, "loss": 0.2501, "lr": 4.6885821929122497e-05, "epoch": 2.4453507340946166, "percentage": 24.45, "elapsed_time": "2:00:54", "remaining_time": "6:13:32", "throughput": 4460.07, "total_tokens": 32356272} {"current_steps": 14995, "total_steps": 61300, "loss": 0.3426, "lr": 4.688238063857908e-05, "epoch": 2.4461663947797714, "percentage": 24.46, "elapsed_time": "2:00:56", "remaining_time": "6:13:29", "throughput": 4460.18, "total_tokens": 32366800} {"current_steps": 15000, "total_steps": 61300, "loss": 0.3472, "lr": 4.687893757413885e-05, "epoch": 2.4469820554649266, "percentage": 24.47, "elapsed_time": "2:00:58", "remaining_time": "6:13:26", "throughput": 4460.28, "total_tokens": 32377072} {"current_steps": 15005, "total_steps": 61300, "loss": 0.3187, "lr": 4.6875492736080935e-05, "epoch": 2.4477977161500815, "percentage": 24.48, "elapsed_time": "2:01:00", "remaining_time": "6:13:22", "throughput": 4460.36, "total_tokens": 32386640} {"current_steps": 15010, "total_steps": 61300, "loss": 0.2971, "lr": 4.687204612468458e-05, "epoch": 2.4486133768352367, "percentage": 24.49, "elapsed_time": "2:01:03", "remaining_time": "6:13:18", "throughput": 4460.47, "total_tokens": 32396496} {"current_steps": 15015, "total_steps": 61300, "loss": 0.4213, "lr": 4.6868597740229186e-05, "epoch": 2.4494290375203915, "percentage": 24.49, "elapsed_time": "2:01:05", "remaining_time": "6:13:16", "throughput": 4460.59, "total_tokens": 32407824} {"current_steps": 15020, "total_steps": 61300, "loss": 0.3496, "lr": 4.68651475829943e-05, "epoch": 2.4502446982055464, "percentage": 24.5, "elapsed_time": "2:01:07", "remaining_time": "6:13:12", "throughput": 4460.69, "total_tokens": 32417968} {"current_steps": 15025, "total_steps": 61300, "loss": 0.3621, "lr": 4.686169565325961e-05, "epoch": 2.4510603588907016, "percentage": 24.51, "elapsed_time": "2:01:09", "remaining_time": "6:13:09", "throughput": 4460.77, "total_tokens": 32428240} {"current_steps": 15030, "total_steps": 61300, "loss": 0.2787, "lr": 4.685824195130495e-05, "epoch": 2.4518760195758564, "percentage": 24.52, "elapsed_time": "2:01:11", "remaining_time": "6:13:06", "throughput": 4460.87, "total_tokens": 32438704} {"current_steps": 15035, "total_steps": 61300, "loss": 0.3239, "lr": 4.6854786477410286e-05, "epoch": 2.4526916802610113, "percentage": 24.53, "elapsed_time": "2:01:14", "remaining_time": "6:13:03", "throughput": 4460.95, "total_tokens": 32449776} {"current_steps": 15040, "total_steps": 61300, "loss": 0.3466, "lr": 4.6851329231855736e-05, "epoch": 2.4535073409461665, "percentage": 24.54, "elapsed_time": "2:01:16", "remaining_time": "6:13:00", "throughput": 4461.06, "total_tokens": 32460240} {"current_steps": 15045, "total_steps": 61300, "loss": 0.3558, "lr": 4.6847870214921566e-05, "epoch": 2.4543230016313213, "percentage": 24.54, "elapsed_time": "2:01:18", "remaining_time": "6:12:56", "throughput": 4461.16, "total_tokens": 32469808} {"current_steps": 15050, "total_steps": 61300, "loss": 0.3224, "lr": 4.6844409426888186e-05, "epoch": 2.455138662316476, "percentage": 24.55, "elapsed_time": "2:01:20", "remaining_time": "6:12:54", "throughput": 4461.26, "total_tokens": 32481232} {"current_steps": 15055, "total_steps": 61300, "loss": 0.3417, "lr": 4.684094686803614e-05, "epoch": 2.4559543230016314, "percentage": 24.56, "elapsed_time": "2:01:23", "remaining_time": "6:12:51", "throughput": 4461.38, "total_tokens": 32492272} {"current_steps": 15060, "total_steps": 61300, "loss": 0.3878, "lr": 4.683748253864612e-05, "epoch": 2.4567699836867862, "percentage": 24.57, "elapsed_time": "2:01:25", "remaining_time": "6:12:48", "throughput": 4461.52, "total_tokens": 32503312} {"current_steps": 15065, "total_steps": 61300, "loss": 0.3345, "lr": 4.6834016438998965e-05, "epoch": 2.4575856443719415, "percentage": 24.58, "elapsed_time": "2:01:27", "remaining_time": "6:12:45", "throughput": 4461.63, "total_tokens": 32513424} {"current_steps": 15070, "total_steps": 61300, "loss": 0.3168, "lr": 4.6830548569375645e-05, "epoch": 2.4584013050570963, "percentage": 24.58, "elapsed_time": "2:01:29", "remaining_time": "6:12:42", "throughput": 4461.76, "total_tokens": 32525264} {"current_steps": 15075, "total_steps": 61300, "loss": 0.3508, "lr": 4.68270789300573e-05, "epoch": 2.459216965742251, "percentage": 24.59, "elapsed_time": "2:01:32", "remaining_time": "6:12:40", "throughput": 4461.89, "total_tokens": 32536592} {"current_steps": 15080, "total_steps": 61300, "loss": 0.3078, "lr": 4.682360752132518e-05, "epoch": 2.4600326264274064, "percentage": 24.6, "elapsed_time": "2:01:34", "remaining_time": "6:12:37", "throughput": 4462.0, "total_tokens": 32547344} {"current_steps": 15085, "total_steps": 61300, "loss": 0.3557, "lr": 4.682013434346071e-05, "epoch": 2.460848287112561, "percentage": 24.61, "elapsed_time": "2:01:36", "remaining_time": "6:12:34", "throughput": 4462.1, "total_tokens": 32558800} {"current_steps": 15090, "total_steps": 61300, "loss": 0.3099, "lr": 4.6816659396745424e-05, "epoch": 2.461663947797716, "percentage": 24.62, "elapsed_time": "2:01:38", "remaining_time": "6:12:31", "throughput": 4462.2, "total_tokens": 32569392} {"current_steps": 15095, "total_steps": 61300, "loss": 0.3836, "lr": 4.6813182681461044e-05, "epoch": 2.4624796084828713, "percentage": 24.62, "elapsed_time": "2:01:41", "remaining_time": "6:12:28", "throughput": 4462.3, "total_tokens": 32579632} {"current_steps": 15100, "total_steps": 61300, "loss": 0.3422, "lr": 4.680970419788939e-05, "epoch": 2.463295269168026, "percentage": 24.63, "elapsed_time": "2:01:43", "remaining_time": "6:12:25", "throughput": 4462.4, "total_tokens": 32590128} {"current_steps": 15105, "total_steps": 61300, "loss": 0.346, "lr": 4.6806223946312455e-05, "epoch": 2.464110929853181, "percentage": 24.64, "elapsed_time": "2:01:45", "remaining_time": "6:12:21", "throughput": 4462.53, "total_tokens": 32600656} {"current_steps": 15110, "total_steps": 61300, "loss": 0.3784, "lr": 4.6802741927012363e-05, "epoch": 2.464926590538336, "percentage": 24.65, "elapsed_time": "2:01:47", "remaining_time": "6:12:18", "throughput": 4462.62, "total_tokens": 32610928} {"current_steps": 15115, "total_steps": 61300, "loss": 0.3644, "lr": 4.679925814027138e-05, "epoch": 2.465742251223491, "percentage": 24.66, "elapsed_time": "2:01:49", "remaining_time": "6:12:15", "throughput": 4462.72, "total_tokens": 32621488} {"current_steps": 15120, "total_steps": 61300, "loss": 0.346, "lr": 4.6795772586371934e-05, "epoch": 2.466557911908646, "percentage": 24.67, "elapsed_time": "2:01:52", "remaining_time": "6:12:13", "throughput": 4462.85, "total_tokens": 32633712} {"current_steps": 15125, "total_steps": 61300, "loss": 0.3537, "lr": 4.679228526559656e-05, "epoch": 2.467373572593801, "percentage": 24.67, "elapsed_time": "2:01:54", "remaining_time": "6:12:10", "throughput": 4462.93, "total_tokens": 32644560} {"current_steps": 15130, "total_steps": 61300, "loss": 0.3616, "lr": 4.678879617822798e-05, "epoch": 2.468189233278956, "percentage": 24.68, "elapsed_time": "2:01:56", "remaining_time": "6:12:08", "throughput": 4463.04, "total_tokens": 32655888} {"current_steps": 15135, "total_steps": 61300, "loss": 0.3337, "lr": 4.6785305324549016e-05, "epoch": 2.4690048939641107, "percentage": 24.69, "elapsed_time": "2:01:59", "remaining_time": "6:12:05", "throughput": 4463.13, "total_tokens": 32666832} {"current_steps": 15140, "total_steps": 61300, "loss": 0.3662, "lr": 4.678181270484267e-05, "epoch": 2.469820554649266, "percentage": 24.7, "elapsed_time": "2:02:01", "remaining_time": "6:12:02", "throughput": 4463.25, "total_tokens": 32677616} {"current_steps": 15145, "total_steps": 61300, "loss": 0.3753, "lr": 4.677831831939207e-05, "epoch": 2.470636215334421, "percentage": 24.71, "elapsed_time": "2:02:03", "remaining_time": "6:11:58", "throughput": 4463.35, "total_tokens": 32687696} {"current_steps": 15150, "total_steps": 61300, "loss": 0.3665, "lr": 4.6774822168480476e-05, "epoch": 2.471451876019576, "percentage": 24.71, "elapsed_time": "2:02:05", "remaining_time": "6:11:55", "throughput": 4463.47, "total_tokens": 32698096} {"current_steps": 15155, "total_steps": 61300, "loss": 0.3469, "lr": 4.677132425239132e-05, "epoch": 2.472267536704731, "percentage": 24.72, "elapsed_time": "2:02:07", "remaining_time": "6:11:51", "throughput": 4463.58, "total_tokens": 32707920} {"current_steps": 15160, "total_steps": 61300, "loss": 0.3578, "lr": 4.676782457140815e-05, "epoch": 2.4730831973898857, "percentage": 24.73, "elapsed_time": "2:02:10", "remaining_time": "6:11:49", "throughput": 4463.71, "total_tokens": 32719472} {"current_steps": 15165, "total_steps": 61300, "loss": 0.3634, "lr": 4.676432312581467e-05, "epoch": 2.473898858075041, "percentage": 24.74, "elapsed_time": "2:02:12", "remaining_time": "6:11:46", "throughput": 4463.82, "total_tokens": 32730064} {"current_steps": 15170, "total_steps": 61300, "loss": 0.3167, "lr": 4.676081991589473e-05, "epoch": 2.4747145187601958, "percentage": 24.75, "elapsed_time": "2:02:14", "remaining_time": "6:11:43", "throughput": 4463.92, "total_tokens": 32740944} {"current_steps": 15175, "total_steps": 61300, "loss": 0.3708, "lr": 4.6757314941932315e-05, "epoch": 2.4755301794453506, "percentage": 24.76, "elapsed_time": "2:02:16", "remaining_time": "6:11:40", "throughput": 4464.01, "total_tokens": 32751856} {"current_steps": 15180, "total_steps": 61300, "loss": 0.3677, "lr": 4.6753808204211554e-05, "epoch": 2.476345840130506, "percentage": 24.76, "elapsed_time": "2:02:19", "remaining_time": "6:11:37", "throughput": 4464.12, "total_tokens": 32762928} {"current_steps": 15185, "total_steps": 61300, "loss": 0.3346, "lr": 4.675029970301672e-05, "epoch": 2.4771615008156607, "percentage": 24.77, "elapsed_time": "2:02:21", "remaining_time": "6:11:34", "throughput": 4464.24, "total_tokens": 32773840} {"current_steps": 15190, "total_steps": 61300, "loss": 0.3706, "lr": 4.674678943863223e-05, "epoch": 2.4779771615008155, "percentage": 24.78, "elapsed_time": "2:02:23", "remaining_time": "6:11:33", "throughput": 4464.34, "total_tokens": 32786064} {"current_steps": 15195, "total_steps": 61300, "loss": 0.3397, "lr": 4.674327741134266e-05, "epoch": 2.4787928221859707, "percentage": 24.79, "elapsed_time": "2:02:26", "remaining_time": "6:11:30", "throughput": 4464.44, "total_tokens": 32796816} {"current_steps": 15200, "total_steps": 61300, "loss": 0.3339, "lr": 4.673976362143269e-05, "epoch": 2.4796084828711256, "percentage": 24.8, "elapsed_time": "2:02:28", "remaining_time": "6:11:26", "throughput": 4464.53, "total_tokens": 32807088} {"current_steps": 15205, "total_steps": 61300, "loss": 0.3648, "lr": 4.673624806918717e-05, "epoch": 2.480424143556281, "percentage": 24.8, "elapsed_time": "2:02:30", "remaining_time": "6:11:23", "throughput": 4464.61, "total_tokens": 32817424} {"current_steps": 15210, "total_steps": 61300, "loss": 0.3786, "lr": 4.673273075489109e-05, "epoch": 2.4812398042414356, "percentage": 24.81, "elapsed_time": "2:02:32", "remaining_time": "6:11:20", "throughput": 4464.7, "total_tokens": 32827984} {"current_steps": 15215, "total_steps": 61300, "loss": 0.3909, "lr": 4.6729211678829595e-05, "epoch": 2.4820554649265905, "percentage": 24.82, "elapsed_time": "2:02:35", "remaining_time": "6:11:18", "throughput": 4464.84, "total_tokens": 32839664} {"current_steps": 15220, "total_steps": 61300, "loss": 0.3341, "lr": 4.672569084128794e-05, "epoch": 2.4828711256117453, "percentage": 24.83, "elapsed_time": "2:02:37", "remaining_time": "6:11:15", "throughput": 4464.94, "total_tokens": 32851280} {"current_steps": 15225, "total_steps": 61300, "loss": 0.3289, "lr": 4.6722168242551554e-05, "epoch": 2.4836867862969005, "percentage": 24.84, "elapsed_time": "2:02:39", "remaining_time": "6:11:12", "throughput": 4465.06, "total_tokens": 32862224} {"current_steps": 15230, "total_steps": 61300, "loss": 0.3431, "lr": 4.671864388290599e-05, "epoch": 2.4845024469820554, "percentage": 24.85, "elapsed_time": "2:02:41", "remaining_time": "6:11:09", "throughput": 4465.2, "total_tokens": 32872816} {"current_steps": 15235, "total_steps": 61300, "loss": 0.3512, "lr": 4.671511776263696e-05, "epoch": 2.4853181076672106, "percentage": 24.85, "elapsed_time": "2:02:44", "remaining_time": "6:11:06", "throughput": 4465.32, "total_tokens": 32882896} {"current_steps": 15240, "total_steps": 61300, "loss": 0.3493, "lr": 4.67115898820303e-05, "epoch": 2.4861337683523654, "percentage": 24.86, "elapsed_time": "2:02:46", "remaining_time": "6:11:03", "throughput": 4465.41, "total_tokens": 32894256} {"current_steps": 15245, "total_steps": 61300, "loss": 0.3473, "lr": 4.6708060241372e-05, "epoch": 2.4869494290375203, "percentage": 24.87, "elapsed_time": "2:02:48", "remaining_time": "6:11:01", "throughput": 4465.51, "total_tokens": 32905392} {"current_steps": 15250, "total_steps": 61300, "loss": 0.3103, "lr": 4.670452884094819e-05, "epoch": 2.4877650897226755, "percentage": 24.88, "elapsed_time": "2:02:51", "remaining_time": "6:10:58", "throughput": 4465.62, "total_tokens": 32916592} {"current_steps": 15255, "total_steps": 61300, "loss": 0.3933, "lr": 4.6700995681045144e-05, "epoch": 2.4885807504078303, "percentage": 24.89, "elapsed_time": "2:02:53", "remaining_time": "6:10:55", "throughput": 4465.71, "total_tokens": 32927216} {"current_steps": 15260, "total_steps": 61300, "loss": 0.343, "lr": 4.669746076194928e-05, "epoch": 2.489396411092985, "percentage": 24.89, "elapsed_time": "2:02:55", "remaining_time": "6:10:52", "throughput": 4465.82, "total_tokens": 32937648} {"current_steps": 15265, "total_steps": 61300, "loss": 0.3071, "lr": 4.669392408394716e-05, "epoch": 2.4902120717781404, "percentage": 24.9, "elapsed_time": "2:02:57", "remaining_time": "6:10:49", "throughput": 4465.91, "total_tokens": 32948496} {"current_steps": 15270, "total_steps": 61300, "loss": 0.37, "lr": 4.669038564732548e-05, "epoch": 2.4910277324632952, "percentage": 24.91, "elapsed_time": "2:02:59", "remaining_time": "6:10:46", "throughput": 4466.01, "total_tokens": 32958832} {"current_steps": 15275, "total_steps": 61300, "loss": 0.3465, "lr": 4.668684545237107e-05, "epoch": 2.49184339314845, "percentage": 24.92, "elapsed_time": "2:03:02", "remaining_time": "6:10:43", "throughput": 4466.13, "total_tokens": 32969456} {"current_steps": 15280, "total_steps": 61300, "loss": 0.324, "lr": 4.668330349937093e-05, "epoch": 2.4926590538336053, "percentage": 24.93, "elapsed_time": "2:03:04", "remaining_time": "6:10:40", "throughput": 4466.23, "total_tokens": 32980496} {"current_steps": 15285, "total_steps": 61300, "loss": 0.3406, "lr": 4.6679759788612205e-05, "epoch": 2.49347471451876, "percentage": 24.93, "elapsed_time": "2:03:06", "remaining_time": "6:10:37", "throughput": 4466.34, "total_tokens": 32991888} {"current_steps": 15290, "total_steps": 61300, "loss": 0.3088, "lr": 4.667621432038214e-05, "epoch": 2.4942903752039154, "percentage": 24.94, "elapsed_time": "2:03:09", "remaining_time": "6:10:34", "throughput": 4466.44, "total_tokens": 33002672} {"current_steps": 15295, "total_steps": 61300, "loss": 0.3516, "lr": 4.6672667094968156e-05, "epoch": 2.49510603588907, "percentage": 24.95, "elapsed_time": "2:03:11", "remaining_time": "6:10:31", "throughput": 4466.52, "total_tokens": 33012720} {"current_steps": 15300, "total_steps": 61300, "loss": 0.3776, "lr": 4.6669118112657814e-05, "epoch": 2.495921696574225, "percentage": 24.96, "elapsed_time": "2:03:13", "remaining_time": "6:10:28", "throughput": 4466.63, "total_tokens": 33023760} {"current_steps": 15305, "total_steps": 61300, "loss": 0.4078, "lr": 4.666556737373881e-05, "epoch": 2.4967373572593803, "percentage": 24.97, "elapsed_time": "2:03:15", "remaining_time": "6:10:25", "throughput": 4466.73, "total_tokens": 33034192} {"current_steps": 15310, "total_steps": 61300, "loss": 0.3404, "lr": 4.666201487849898e-05, "epoch": 2.497553017944535, "percentage": 24.98, "elapsed_time": "2:03:17", "remaining_time": "6:10:22", "throughput": 4466.8, "total_tokens": 33044080} {"current_steps": 15315, "total_steps": 61300, "loss": 0.3448, "lr": 4.665846062722632e-05, "epoch": 2.49836867862969, "percentage": 24.98, "elapsed_time": "2:03:19", "remaining_time": "6:10:19", "throughput": 4466.93, "total_tokens": 33055184} {"current_steps": 15320, "total_steps": 61300, "loss": 0.3542, "lr": 4.665490462020895e-05, "epoch": 2.499184339314845, "percentage": 24.99, "elapsed_time": "2:03:22", "remaining_time": "6:10:16", "throughput": 4467.05, "total_tokens": 33065712} {"current_steps": 15325, "total_steps": 61300, "loss": 0.3218, "lr": 4.665134685773513e-05, "epoch": 2.5, "percentage": 25.0, "elapsed_time": "2:03:24", "remaining_time": "6:10:12", "throughput": 4467.14, "total_tokens": 33075856} {"current_steps": 15325, "total_steps": 61300, "eval_loss": 0.343363881111145, "epoch": 2.5, "percentage": 25.0, "elapsed_time": "2:05:36", "remaining_time": "6:16:48", "throughput": 4388.95, "total_tokens": 33075856} {"current_steps": 15330, "total_steps": 61300, "loss": 0.3134, "lr": 4.664778734009327e-05, "epoch": 2.500815660685155, "percentage": 25.01, "elapsed_time": "2:05:39", "remaining_time": "6:16:48", "throughput": 4388.55, "total_tokens": 33087312} {"current_steps": 15335, "total_steps": 61300, "loss": 0.3363, "lr": 4.664422606757194e-05, "epoch": 2.50163132137031, "percentage": 25.02, "elapsed_time": "2:05:41", "remaining_time": "6:16:45", "throughput": 4388.69, "total_tokens": 33098960} {"current_steps": 15340, "total_steps": 61300, "loss": 0.3535, "lr": 4.664066304045982e-05, "epoch": 2.502446982055465, "percentage": 25.02, "elapsed_time": "2:05:44", "remaining_time": "6:16:42", "throughput": 4388.82, "total_tokens": 33109712} {"current_steps": 15345, "total_steps": 61300, "loss": 0.3084, "lr": 4.6637098259045744e-05, "epoch": 2.50326264274062, "percentage": 25.03, "elapsed_time": "2:05:46", "remaining_time": "6:16:40", "throughput": 4388.95, "total_tokens": 33121008} {"current_steps": 15350, "total_steps": 61300, "loss": 0.3523, "lr": 4.66335317236187e-05, "epoch": 2.504078303425775, "percentage": 25.04, "elapsed_time": "2:05:48", "remaining_time": "6:16:37", "throughput": 4389.12, "total_tokens": 33133360} {"current_steps": 15355, "total_steps": 61300, "loss": 0.3499, "lr": 4.662996343446781e-05, "epoch": 2.50489396411093, "percentage": 25.05, "elapsed_time": "2:05:51", "remaining_time": "6:16:34", "throughput": 4389.27, "total_tokens": 33144688} {"current_steps": 15360, "total_steps": 61300, "loss": 0.3414, "lr": 4.6626393391882326e-05, "epoch": 2.5057096247960846, "percentage": 25.06, "elapsed_time": "2:05:53", "remaining_time": "6:16:31", "throughput": 4389.4, "total_tokens": 33155024} {"current_steps": 15365, "total_steps": 61300, "loss": 0.3475, "lr": 4.6622821596151676e-05, "epoch": 2.50652528548124, "percentage": 25.07, "elapsed_time": "2:05:55", "remaining_time": "6:16:28", "throughput": 4389.55, "total_tokens": 33166576} {"current_steps": 15370, "total_steps": 61300, "loss": 0.3266, "lr": 4.6619248047565386e-05, "epoch": 2.5073409461663947, "percentage": 25.07, "elapsed_time": "2:05:57", "remaining_time": "6:16:25", "throughput": 4389.68, "total_tokens": 33176720} {"current_steps": 15375, "total_steps": 61300, "loss": 0.3207, "lr": 4.6615672746413156e-05, "epoch": 2.50815660685155, "percentage": 25.08, "elapsed_time": "2:06:00", "remaining_time": "6:16:22", "throughput": 4389.83, "total_tokens": 33187824} {"current_steps": 15380, "total_steps": 61300, "loss": 0.3189, "lr": 4.661209569298482e-05, "epoch": 2.5089722675367048, "percentage": 25.09, "elapsed_time": "2:06:02", "remaining_time": "6:16:19", "throughput": 4389.93, "total_tokens": 33198800} {"current_steps": 15385, "total_steps": 61300, "loss": 0.3461, "lr": 4.660851688757034e-05, "epoch": 2.5097879282218596, "percentage": 25.1, "elapsed_time": "2:06:04", "remaining_time": "6:16:15", "throughput": 4390.07, "total_tokens": 33209232} {"current_steps": 15390, "total_steps": 61300, "loss": 0.3243, "lr": 4.6604936330459845e-05, "epoch": 2.5106035889070144, "percentage": 25.11, "elapsed_time": "2:06:06", "remaining_time": "6:16:12", "throughput": 4390.19, "total_tokens": 33219760} {"current_steps": 15395, "total_steps": 61300, "loss": 0.3352, "lr": 4.660135402194359e-05, "epoch": 2.5114192495921697, "percentage": 25.11, "elapsed_time": "2:06:08", "remaining_time": "6:16:08", "throughput": 4390.3, "total_tokens": 33229040} {"current_steps": 15400, "total_steps": 61300, "loss": 0.3496, "lr": 4.6597769962311975e-05, "epoch": 2.5122349102773245, "percentage": 25.12, "elapsed_time": "2:06:10", "remaining_time": "6:16:04", "throughput": 4390.41, "total_tokens": 33238960} {"current_steps": 15405, "total_steps": 61300, "loss": 0.3034, "lr": 4.6594184151855536e-05, "epoch": 2.5130505709624797, "percentage": 25.13, "elapsed_time": "2:06:12", "remaining_time": "6:16:00", "throughput": 4390.51, "total_tokens": 33247920} {"current_steps": 15410, "total_steps": 61300, "loss": 0.336, "lr": 4.6590596590864966e-05, "epoch": 2.5138662316476346, "percentage": 25.14, "elapsed_time": "2:06:15", "remaining_time": "6:15:57", "throughput": 4390.67, "total_tokens": 33259504} {"current_steps": 15415, "total_steps": 61300, "loss": 0.3192, "lr": 4.658700727963109e-05, "epoch": 2.5146818923327894, "percentage": 25.15, "elapsed_time": "2:06:17", "remaining_time": "6:15:54", "throughput": 4390.81, "total_tokens": 33269872} {"current_steps": 15420, "total_steps": 61300, "loss": 0.3578, "lr": 4.6583416218444866e-05, "epoch": 2.5154975530179446, "percentage": 25.15, "elapsed_time": "2:06:19", "remaining_time": "6:15:52", "throughput": 4390.97, "total_tokens": 33282192} {"current_steps": 15425, "total_steps": 61300, "loss": 0.3073, "lr": 4.657982340759741e-05, "epoch": 2.5163132137030995, "percentage": 25.16, "elapsed_time": "2:06:22", "remaining_time": "6:15:49", "throughput": 4391.11, "total_tokens": 33293648} {"current_steps": 15430, "total_steps": 61300, "loss": 0.3423, "lr": 4.657622884737998e-05, "epoch": 2.5171288743882547, "percentage": 25.17, "elapsed_time": "2:06:24", "remaining_time": "6:15:46", "throughput": 4391.26, "total_tokens": 33304752} {"current_steps": 15435, "total_steps": 61300, "loss": 0.3614, "lr": 4.657263253808396e-05, "epoch": 2.5179445350734095, "percentage": 25.18, "elapsed_time": "2:06:26", "remaining_time": "6:15:43", "throughput": 4391.4, "total_tokens": 33315216} {"current_steps": 15440, "total_steps": 61300, "loss": 0.3451, "lr": 4.6569034480000887e-05, "epoch": 2.5187601957585644, "percentage": 25.19, "elapsed_time": "2:06:28", "remaining_time": "6:15:39", "throughput": 4391.53, "total_tokens": 33325392} {"current_steps": 15445, "total_steps": 61300, "loss": 0.3154, "lr": 4.656543467342244e-05, "epoch": 2.519575856443719, "percentage": 25.2, "elapsed_time": "2:06:30", "remaining_time": "6:15:36", "throughput": 4391.67, "total_tokens": 33336656} {"current_steps": 15450, "total_steps": 61300, "loss": 0.3367, "lr": 4.656183311864043e-05, "epoch": 2.5203915171288744, "percentage": 25.2, "elapsed_time": "2:06:33", "remaining_time": "6:15:34", "throughput": 4391.78, "total_tokens": 33347856} {"current_steps": 15455, "total_steps": 61300, "loss": 0.3352, "lr": 4.655822981594683e-05, "epoch": 2.5212071778140293, "percentage": 25.21, "elapsed_time": "2:06:35", "remaining_time": "6:15:30", "throughput": 4391.91, "total_tokens": 33358640} {"current_steps": 15460, "total_steps": 61300, "loss": 0.3541, "lr": 4.6554624765633734e-05, "epoch": 2.5220228384991845, "percentage": 25.22, "elapsed_time": "2:06:37", "remaining_time": "6:15:27", "throughput": 4392.02, "total_tokens": 33369200} {"current_steps": 15465, "total_steps": 61300, "loss": 0.3927, "lr": 4.655101796799338e-05, "epoch": 2.5228384991843393, "percentage": 25.23, "elapsed_time": "2:06:39", "remaining_time": "6:15:23", "throughput": 4392.1, "total_tokens": 33378320} {"current_steps": 15470, "total_steps": 61300, "loss": 0.3221, "lr": 4.654740942331818e-05, "epoch": 2.523654159869494, "percentage": 25.24, "elapsed_time": "2:06:41", "remaining_time": "6:15:20", "throughput": 4392.23, "total_tokens": 33388976} {"current_steps": 15475, "total_steps": 61300, "loss": 0.361, "lr": 4.6543799131900625e-05, "epoch": 2.5244698205546494, "percentage": 25.24, "elapsed_time": "2:06:44", "remaining_time": "6:15:17", "throughput": 4392.36, "total_tokens": 33399664} {"current_steps": 15480, "total_steps": 61300, "loss": 0.3488, "lr": 4.6540187094033407e-05, "epoch": 2.5252854812398042, "percentage": 25.25, "elapsed_time": "2:06:46", "remaining_time": "6:15:13", "throughput": 4392.46, "total_tokens": 33409616} {"current_steps": 15485, "total_steps": 61300, "loss": 0.3542, "lr": 4.6536573310009326e-05, "epoch": 2.5261011419249595, "percentage": 25.26, "elapsed_time": "2:06:48", "remaining_time": "6:15:10", "throughput": 4392.58, "total_tokens": 33420624} {"current_steps": 15490, "total_steps": 61300, "loss": 0.3655, "lr": 4.653295778012134e-05, "epoch": 2.5269168026101143, "percentage": 25.27, "elapsed_time": "2:06:50", "remaining_time": "6:15:07", "throughput": 4392.7, "total_tokens": 33430960} {"current_steps": 15495, "total_steps": 61300, "loss": 0.3256, "lr": 4.652934050466254e-05, "epoch": 2.527732463295269, "percentage": 25.28, "elapsed_time": "2:06:53", "remaining_time": "6:15:05", "throughput": 4392.87, "total_tokens": 33443344} {"current_steps": 15500, "total_steps": 61300, "loss": 0.3621, "lr": 4.652572148392616e-05, "epoch": 2.528548123980424, "percentage": 25.29, "elapsed_time": "2:06:55", "remaining_time": "6:15:01", "throughput": 4393.0, "total_tokens": 33454032} {"current_steps": 15505, "total_steps": 61300, "loss": 0.4057, "lr": 4.652210071820557e-05, "epoch": 2.529363784665579, "percentage": 25.29, "elapsed_time": "2:06:57", "remaining_time": "6:14:59", "throughput": 4393.14, "total_tokens": 33465360} {"current_steps": 15510, "total_steps": 61300, "loss": 0.3423, "lr": 4.6518478207794304e-05, "epoch": 2.530179445350734, "percentage": 25.3, "elapsed_time": "2:06:59", "remaining_time": "6:14:56", "throughput": 4393.26, "total_tokens": 33476336} {"current_steps": 15515, "total_steps": 61300, "loss": 0.3296, "lr": 4.6514853952986e-05, "epoch": 2.5309951060358893, "percentage": 25.31, "elapsed_time": "2:07:02", "remaining_time": "6:14:52", "throughput": 4393.38, "total_tokens": 33486736} {"current_steps": 15520, "total_steps": 61300, "loss": 0.3185, "lr": 4.6511227954074476e-05, "epoch": 2.531810766721044, "percentage": 25.32, "elapsed_time": "2:07:04", "remaining_time": "6:14:49", "throughput": 4393.49, "total_tokens": 33497680} {"current_steps": 15525, "total_steps": 61300, "loss": 0.3275, "lr": 4.650760021135366e-05, "epoch": 2.532626427406199, "percentage": 25.33, "elapsed_time": "2:07:06", "remaining_time": "6:14:47", "throughput": 4393.61, "total_tokens": 33509456} {"current_steps": 15530, "total_steps": 61300, "loss": 0.3576, "lr": 4.650397072511765e-05, "epoch": 2.5334420880913537, "percentage": 25.33, "elapsed_time": "2:07:09", "remaining_time": "6:14:44", "throughput": 4393.77, "total_tokens": 33521040} {"current_steps": 15535, "total_steps": 61300, "loss": 0.3444, "lr": 4.650033949566066e-05, "epoch": 2.534257748776509, "percentage": 25.34, "elapsed_time": "2:07:11", "remaining_time": "6:14:41", "throughput": 4393.89, "total_tokens": 33531472} {"current_steps": 15540, "total_steps": 61300, "loss": 0.3369, "lr": 4.6496706523277054e-05, "epoch": 2.535073409461664, "percentage": 25.35, "elapsed_time": "2:07:13", "remaining_time": "6:14:37", "throughput": 4394.01, "total_tokens": 33541552} {"current_steps": 15545, "total_steps": 61300, "loss": 0.3408, "lr": 4.649307180826136e-05, "epoch": 2.535889070146819, "percentage": 25.36, "elapsed_time": "2:07:15", "remaining_time": "6:14:34", "throughput": 4394.17, "total_tokens": 33551920} {"current_steps": 15550, "total_steps": 61300, "loss": 0.3242, "lr": 4.64894353509082e-05, "epoch": 2.536704730831974, "percentage": 25.37, "elapsed_time": "2:07:17", "remaining_time": "6:14:31", "throughput": 4394.27, "total_tokens": 33562960} {"current_steps": 15555, "total_steps": 61300, "loss": 0.3669, "lr": 4.648579715151237e-05, "epoch": 2.5375203915171287, "percentage": 25.38, "elapsed_time": "2:07:19", "remaining_time": "6:14:27", "throughput": 4394.39, "total_tokens": 33572848} {"current_steps": 15560, "total_steps": 61300, "loss": 0.3443, "lr": 4.648215721036881e-05, "epoch": 2.538336052202284, "percentage": 25.38, "elapsed_time": "2:07:21", "remaining_time": "6:14:24", "throughput": 4394.47, "total_tokens": 33582224} {"current_steps": 15565, "total_steps": 61300, "loss": 0.3349, "lr": 4.647851552777258e-05, "epoch": 2.539151712887439, "percentage": 25.39, "elapsed_time": "2:07:24", "remaining_time": "6:14:21", "throughput": 4394.6, "total_tokens": 33593680} {"current_steps": 15570, "total_steps": 61300, "loss": 0.3233, "lr": 4.6474872104018907e-05, "epoch": 2.539967373572594, "percentage": 25.4, "elapsed_time": "2:07:26", "remaining_time": "6:14:18", "throughput": 4394.75, "total_tokens": 33605616} {"current_steps": 15575, "total_steps": 61300, "loss": 0.3125, "lr": 4.6471226939403145e-05, "epoch": 2.540783034257749, "percentage": 25.41, "elapsed_time": "2:07:29", "remaining_time": "6:14:16", "throughput": 4394.87, "total_tokens": 33616752} {"current_steps": 15580, "total_steps": 61300, "loss": 0.3723, "lr": 4.646758003422077e-05, "epoch": 2.5415986949429037, "percentage": 25.42, "elapsed_time": "2:07:31", "remaining_time": "6:14:13", "throughput": 4395.01, "total_tokens": 33628048} {"current_steps": 15585, "total_steps": 61300, "loss": 0.3324, "lr": 4.646393138876745e-05, "epoch": 2.5424143556280585, "percentage": 25.42, "elapsed_time": "2:07:33", "remaining_time": "6:14:10", "throughput": 4395.15, "total_tokens": 33639280} {"current_steps": 15590, "total_steps": 61300, "loss": 0.3461, "lr": 4.6460281003338924e-05, "epoch": 2.5432300163132138, "percentage": 25.43, "elapsed_time": "2:07:35", "remaining_time": "6:14:07", "throughput": 4395.27, "total_tokens": 33649808} {"current_steps": 15595, "total_steps": 61300, "loss": 0.3725, "lr": 4.6456628878231144e-05, "epoch": 2.5440456769983686, "percentage": 25.44, "elapsed_time": "2:07:37", "remaining_time": "6:14:03", "throughput": 4395.37, "total_tokens": 33658992} {"current_steps": 15600, "total_steps": 61300, "loss": 0.3409, "lr": 4.645297501374015e-05, "epoch": 2.544861337683524, "percentage": 25.45, "elapsed_time": "2:07:40", "remaining_time": "6:14:00", "throughput": 4395.48, "total_tokens": 33669904} {"current_steps": 15605, "total_steps": 61300, "loss": 0.3754, "lr": 4.644931941016216e-05, "epoch": 2.5456769983686787, "percentage": 25.46, "elapsed_time": "2:07:42", "remaining_time": "6:13:56", "throughput": 4395.61, "total_tokens": 33680080} {"current_steps": 15610, "total_steps": 61300, "loss": 0.3459, "lr": 4.644566206779349e-05, "epoch": 2.5464926590538335, "percentage": 25.46, "elapsed_time": "2:07:44", "remaining_time": "6:13:54", "throughput": 4395.77, "total_tokens": 33692208} {"current_steps": 15615, "total_steps": 61300, "loss": 0.3384, "lr": 4.6442002986930656e-05, "epoch": 2.5473083197389887, "percentage": 25.47, "elapsed_time": "2:07:46", "remaining_time": "6:13:51", "throughput": 4395.87, "total_tokens": 33703088} {"current_steps": 15620, "total_steps": 61300, "loss": 0.3445, "lr": 4.6438342167870255e-05, "epoch": 2.5481239804241436, "percentage": 25.48, "elapsed_time": "2:07:48", "remaining_time": "6:13:47", "throughput": 4396.01, "total_tokens": 33712944} {"current_steps": 15625, "total_steps": 61300, "loss": 0.3798, "lr": 4.643467961090906e-05, "epoch": 2.5489396411092984, "percentage": 25.49, "elapsed_time": "2:07:51", "remaining_time": "6:13:44", "throughput": 4396.14, "total_tokens": 33723408} {"current_steps": 15630, "total_steps": 61300, "loss": 0.3529, "lr": 4.643101531634399e-05, "epoch": 2.5497553017944536, "percentage": 25.5, "elapsed_time": "2:07:53", "remaining_time": "6:13:40", "throughput": 4396.25, "total_tokens": 33733488} {"current_steps": 15635, "total_steps": 61300, "loss": 0.3481, "lr": 4.642734928447207e-05, "epoch": 2.5505709624796085, "percentage": 25.51, "elapsed_time": "2:07:55", "remaining_time": "6:13:36", "throughput": 4396.32, "total_tokens": 33742640} {"current_steps": 15640, "total_steps": 61300, "loss": 0.3981, "lr": 4.642368151559049e-05, "epoch": 2.5513866231647633, "percentage": 25.51, "elapsed_time": "2:07:57", "remaining_time": "6:13:34", "throughput": 4396.41, "total_tokens": 33753584} {"current_steps": 15645, "total_steps": 61300, "loss": 0.3546, "lr": 4.642001200999659e-05, "epoch": 2.5522022838499185, "percentage": 25.52, "elapsed_time": "2:07:59", "remaining_time": "6:13:31", "throughput": 4396.52, "total_tokens": 33764656} {"current_steps": 15650, "total_steps": 61300, "loss": 0.3421, "lr": 4.6416340767987833e-05, "epoch": 2.5530179445350734, "percentage": 25.53, "elapsed_time": "2:08:02", "remaining_time": "6:13:28", "throughput": 4396.66, "total_tokens": 33775632} {"current_steps": 15655, "total_steps": 61300, "loss": 0.3597, "lr": 4.641266778986182e-05, "epoch": 2.5538336052202286, "percentage": 25.54, "elapsed_time": "2:08:04", "remaining_time": "6:13:25", "throughput": 4396.81, "total_tokens": 33787536} {"current_steps": 15660, "total_steps": 61300, "loss": 0.3335, "lr": 4.640899307591632e-05, "epoch": 2.5546492659053834, "percentage": 25.55, "elapsed_time": "2:08:06", "remaining_time": "6:13:22", "throughput": 4396.95, "total_tokens": 33798736} {"current_steps": 15665, "total_steps": 61300, "loss": 0.3693, "lr": 4.64053166264492e-05, "epoch": 2.5554649265905383, "percentage": 25.55, "elapsed_time": "2:08:09", "remaining_time": "6:13:20", "throughput": 4397.09, "total_tokens": 33810256} {"current_steps": 15670, "total_steps": 61300, "loss": 0.3817, "lr": 4.640163844175852e-05, "epoch": 2.556280587275693, "percentage": 25.56, "elapsed_time": "2:08:11", "remaining_time": "6:13:16", "throughput": 4397.17, "total_tokens": 33820272} {"current_steps": 15675, "total_steps": 61300, "loss": 0.3348, "lr": 4.6397958522142426e-05, "epoch": 2.5570962479608483, "percentage": 25.57, "elapsed_time": "2:08:13", "remaining_time": "6:13:13", "throughput": 4397.29, "total_tokens": 33830448} {"current_steps": 15680, "total_steps": 61300, "loss": 0.36, "lr": 4.639427686789924e-05, "epoch": 2.557911908646003, "percentage": 25.58, "elapsed_time": "2:08:15", "remaining_time": "6:13:10", "throughput": 4397.43, "total_tokens": 33841808} {"current_steps": 15685, "total_steps": 61300, "loss": 0.3659, "lr": 4.6390593479327424e-05, "epoch": 2.5587275693311584, "percentage": 25.59, "elapsed_time": "2:08:17", "remaining_time": "6:13:06", "throughput": 4397.54, "total_tokens": 33851088} {"current_steps": 15690, "total_steps": 61300, "loss": 0.3223, "lr": 4.6386908356725564e-05, "epoch": 2.5595432300163132, "percentage": 25.6, "elapsed_time": "2:08:20", "remaining_time": "6:13:04", "throughput": 4397.69, "total_tokens": 33863600} {"current_steps": 15695, "total_steps": 61300, "loss": 0.3364, "lr": 4.63832215003924e-05, "epoch": 2.560358890701468, "percentage": 25.6, "elapsed_time": "2:08:22", "remaining_time": "6:13:00", "throughput": 4397.83, "total_tokens": 33873712} {"current_steps": 15700, "total_steps": 61300, "loss": 0.3497, "lr": 4.63795329106268e-05, "epoch": 2.5611745513866233, "percentage": 25.61, "elapsed_time": "2:08:24", "remaining_time": "6:12:57", "throughput": 4397.97, "total_tokens": 33884496} {"current_steps": 15705, "total_steps": 61300, "loss": 0.3423, "lr": 4.637584258772779e-05, "epoch": 2.561990212071778, "percentage": 25.62, "elapsed_time": "2:08:26", "remaining_time": "6:12:55", "throughput": 4398.11, "total_tokens": 33896176} {"current_steps": 15710, "total_steps": 61300, "loss": 0.3277, "lr": 4.637215053199451e-05, "epoch": 2.5628058727569334, "percentage": 25.63, "elapsed_time": "2:08:29", "remaining_time": "6:12:52", "throughput": 4398.23, "total_tokens": 33907760} {"current_steps": 15715, "total_steps": 61300, "loss": 0.3161, "lr": 4.6368456743726276e-05, "epoch": 2.563621533442088, "percentage": 25.64, "elapsed_time": "2:08:31", "remaining_time": "6:12:49", "throughput": 4398.36, "total_tokens": 33918864} {"current_steps": 15720, "total_steps": 61300, "loss": 0.3309, "lr": 4.636476122322251e-05, "epoch": 2.564437194127243, "percentage": 25.64, "elapsed_time": "2:08:33", "remaining_time": "6:12:46", "throughput": 4398.46, "total_tokens": 33929072} {"current_steps": 15725, "total_steps": 61300, "loss": 0.3866, "lr": 4.636106397078279e-05, "epoch": 2.565252854812398, "percentage": 25.65, "elapsed_time": "2:08:36", "remaining_time": "6:12:43", "throughput": 4398.55, "total_tokens": 33939440} {"current_steps": 15730, "total_steps": 61300, "loss": 0.3707, "lr": 4.635736498670685e-05, "epoch": 2.566068515497553, "percentage": 25.66, "elapsed_time": "2:08:38", "remaining_time": "6:12:39", "throughput": 4398.66, "total_tokens": 33949168} {"current_steps": 15735, "total_steps": 61300, "loss": 0.3301, "lr": 4.635366427129454e-05, "epoch": 2.566884176182708, "percentage": 25.67, "elapsed_time": "2:08:40", "remaining_time": "6:12:35", "throughput": 4398.75, "total_tokens": 33958800} {"current_steps": 15740, "total_steps": 61300, "loss": 0.3359, "lr": 4.634996182484584e-05, "epoch": 2.567699836867863, "percentage": 25.68, "elapsed_time": "2:08:42", "remaining_time": "6:12:31", "throughput": 4398.85, "total_tokens": 33968144} {"current_steps": 15745, "total_steps": 61300, "loss": 0.3616, "lr": 4.634625764766093e-05, "epoch": 2.568515497553018, "percentage": 25.69, "elapsed_time": "2:08:44", "remaining_time": "6:12:28", "throughput": 4398.98, "total_tokens": 33979344} {"current_steps": 15750, "total_steps": 61300, "loss": 0.3295, "lr": 4.6342551740040053e-05, "epoch": 2.569331158238173, "percentage": 25.69, "elapsed_time": "2:08:46", "remaining_time": "6:12:25", "throughput": 4399.1, "total_tokens": 33990160} {"current_steps": 15755, "total_steps": 61300, "loss": 0.3559, "lr": 4.633884410228364e-05, "epoch": 2.5701468189233276, "percentage": 25.7, "elapsed_time": "2:08:48", "remaining_time": "6:12:22", "throughput": 4399.23, "total_tokens": 34000336} {"current_steps": 15760, "total_steps": 61300, "loss": 0.3497, "lr": 4.633513473469225e-05, "epoch": 2.570962479608483, "percentage": 25.71, "elapsed_time": "2:08:51", "remaining_time": "6:12:19", "throughput": 4399.37, "total_tokens": 34011696} {"current_steps": 15765, "total_steps": 61300, "loss": 0.3624, "lr": 4.633142363756658e-05, "epoch": 2.5717781402936377, "percentage": 25.72, "elapsed_time": "2:08:53", "remaining_time": "6:12:16", "throughput": 4399.47, "total_tokens": 34022256} {"current_steps": 15770, "total_steps": 61300, "loss": 0.4043, "lr": 4.6327710811207486e-05, "epoch": 2.572593800978793, "percentage": 25.73, "elapsed_time": "2:08:55", "remaining_time": "6:12:13", "throughput": 4399.58, "total_tokens": 34032848} {"current_steps": 15775, "total_steps": 61300, "loss": 0.3125, "lr": 4.6323996255915936e-05, "epoch": 2.573409461663948, "percentage": 25.73, "elapsed_time": "2:08:57", "remaining_time": "6:12:10", "throughput": 4399.73, "total_tokens": 34043888} {"current_steps": 15780, "total_steps": 61300, "loss": 0.3708, "lr": 4.6320279971993055e-05, "epoch": 2.5742251223491026, "percentage": 25.74, "elapsed_time": "2:09:00", "remaining_time": "6:12:07", "throughput": 4399.86, "total_tokens": 34055760} {"current_steps": 15785, "total_steps": 61300, "loss": 0.3231, "lr": 4.631656195974009e-05, "epoch": 2.575040783034258, "percentage": 25.75, "elapsed_time": "2:09:02", "remaining_time": "6:12:05", "throughput": 4400.01, "total_tokens": 34067536} {"current_steps": 15790, "total_steps": 61300, "loss": 0.3337, "lr": 4.631284221945846e-05, "epoch": 2.5758564437194127, "percentage": 25.76, "elapsed_time": "2:09:04", "remaining_time": "6:12:02", "throughput": 4400.14, "total_tokens": 34078896} {"current_steps": 15795, "total_steps": 61300, "loss": 0.3338, "lr": 4.6309120751449706e-05, "epoch": 2.576672104404568, "percentage": 25.77, "elapsed_time": "2:09:07", "remaining_time": "6:11:59", "throughput": 4400.27, "total_tokens": 34089648} {"current_steps": 15800, "total_steps": 61300, "loss": 0.342, "lr": 4.63053975560155e-05, "epoch": 2.5774877650897228, "percentage": 25.77, "elapsed_time": "2:09:09", "remaining_time": "6:11:56", "throughput": 4400.42, "total_tokens": 34101392} {"current_steps": 15805, "total_steps": 61300, "loss": 0.3543, "lr": 4.630167263345766e-05, "epoch": 2.5783034257748776, "percentage": 25.78, "elapsed_time": "2:09:11", "remaining_time": "6:11:53", "throughput": 4400.51, "total_tokens": 34111184} {"current_steps": 15810, "total_steps": 61300, "loss": 0.3469, "lr": 4.629794598407815e-05, "epoch": 2.5791190864600324, "percentage": 25.79, "elapsed_time": "2:09:13", "remaining_time": "6:11:50", "throughput": 4400.63, "total_tokens": 34121872} {"current_steps": 15815, "total_steps": 61300, "loss": 0.3466, "lr": 4.629421760817908e-05, "epoch": 2.5799347471451877, "percentage": 25.8, "elapsed_time": "2:09:16", "remaining_time": "6:11:47", "throughput": 4400.76, "total_tokens": 34132912} {"current_steps": 15820, "total_steps": 61300, "loss": 0.2961, "lr": 4.6290487506062685e-05, "epoch": 2.5807504078303425, "percentage": 25.81, "elapsed_time": "2:09:18", "remaining_time": "6:11:44", "throughput": 4400.88, "total_tokens": 34143632} {"current_steps": 15825, "total_steps": 61300, "loss": 0.3823, "lr": 4.6286755678031344e-05, "epoch": 2.5815660685154977, "percentage": 25.82, "elapsed_time": "2:09:20", "remaining_time": "6:11:41", "throughput": 4401.0, "total_tokens": 34154928} {"current_steps": 15830, "total_steps": 61300, "loss": 0.4053, "lr": 4.628302212438758e-05, "epoch": 2.5823817292006526, "percentage": 25.82, "elapsed_time": "2:09:22", "remaining_time": "6:11:37", "throughput": 4401.11, "total_tokens": 34165168} {"current_steps": 15835, "total_steps": 61300, "loss": 0.3252, "lr": 4.627928684543406e-05, "epoch": 2.5831973898858074, "percentage": 25.83, "elapsed_time": "2:09:25", "remaining_time": "6:11:35", "throughput": 4401.22, "total_tokens": 34176304} {"current_steps": 15840, "total_steps": 61300, "loss": 0.3238, "lr": 4.627554984147357e-05, "epoch": 2.5840130505709626, "percentage": 25.84, "elapsed_time": "2:09:27", "remaining_time": "6:11:32", "throughput": 4401.34, "total_tokens": 34186928} {"current_steps": 15845, "total_steps": 61300, "loss": 0.3123, "lr": 4.627181111280906e-05, "epoch": 2.5848287112561175, "percentage": 25.85, "elapsed_time": "2:09:29", "remaining_time": "6:11:28", "throughput": 4401.47, "total_tokens": 34197712} {"current_steps": 15850, "total_steps": 61300, "loss": 0.3213, "lr": 4.6268070659743605e-05, "epoch": 2.5856443719412723, "percentage": 25.86, "elapsed_time": "2:09:31", "remaining_time": "6:11:25", "throughput": 4401.57, "total_tokens": 34208144} {"current_steps": 15855, "total_steps": 61300, "loss": 0.3512, "lr": 4.626432848258044e-05, "epoch": 2.5864600326264275, "percentage": 25.86, "elapsed_time": "2:09:34", "remaining_time": "6:11:22", "throughput": 4401.7, "total_tokens": 34219504} {"current_steps": 15860, "total_steps": 61300, "loss": 0.3512, "lr": 4.62605845816229e-05, "epoch": 2.5872756933115824, "percentage": 25.87, "elapsed_time": "2:09:36", "remaining_time": "6:11:19", "throughput": 4401.81, "total_tokens": 34230032} {"current_steps": 15865, "total_steps": 61300, "loss": 0.3162, "lr": 4.625683895717451e-05, "epoch": 2.588091353996737, "percentage": 25.88, "elapsed_time": "2:09:38", "remaining_time": "6:11:16", "throughput": 4401.92, "total_tokens": 34240400} {"current_steps": 15870, "total_steps": 61300, "loss": 0.3107, "lr": 4.62530916095389e-05, "epoch": 2.5889070146818924, "percentage": 25.89, "elapsed_time": "2:09:40", "remaining_time": "6:11:13", "throughput": 4402.07, "total_tokens": 34252048} {"current_steps": 15875, "total_steps": 61300, "loss": 0.3083, "lr": 4.6249342539019844e-05, "epoch": 2.5897226753670473, "percentage": 25.9, "elapsed_time": "2:09:43", "remaining_time": "6:11:10", "throughput": 4402.19, "total_tokens": 34262832} {"current_steps": 15880, "total_steps": 61300, "loss": 0.2991, "lr": 4.6245591745921254e-05, "epoch": 2.5905383360522025, "percentage": 25.91, "elapsed_time": "2:09:45", "remaining_time": "6:11:08", "throughput": 4402.34, "total_tokens": 34274512} {"current_steps": 15885, "total_steps": 61300, "loss": 0.3199, "lr": 4.624183923054721e-05, "epoch": 2.5913539967373573, "percentage": 25.91, "elapsed_time": "2:09:47", "remaining_time": "6:11:04", "throughput": 4402.45, "total_tokens": 34284240} {"current_steps": 15890, "total_steps": 61300, "loss": 0.3208, "lr": 4.623808499320189e-05, "epoch": 2.592169657422512, "percentage": 25.92, "elapsed_time": "2:09:49", "remaining_time": "6:11:00", "throughput": 4402.54, "total_tokens": 34293744} {"current_steps": 15895, "total_steps": 61300, "loss": 0.3883, "lr": 4.623432903418965e-05, "epoch": 2.592985318107667, "percentage": 25.93, "elapsed_time": "2:09:51", "remaining_time": "6:10:57", "throughput": 4402.65, "total_tokens": 34304144} {"current_steps": 15900, "total_steps": 61300, "loss": 0.3158, "lr": 4.6230571353814944e-05, "epoch": 2.5938009787928222, "percentage": 25.94, "elapsed_time": "2:09:53", "remaining_time": "6:10:54", "throughput": 4402.78, "total_tokens": 34314992} {"current_steps": 15905, "total_steps": 61300, "loss": 0.3769, "lr": 4.622681195238241e-05, "epoch": 2.594616639477977, "percentage": 25.95, "elapsed_time": "2:09:56", "remaining_time": "6:10:51", "throughput": 4402.93, "total_tokens": 34326768} {"current_steps": 15910, "total_steps": 61300, "loss": 0.3428, "lr": 4.622305083019679e-05, "epoch": 2.5954323001631323, "percentage": 25.95, "elapsed_time": "2:09:58", "remaining_time": "6:10:47", "throughput": 4403.02, "total_tokens": 34336080} {"current_steps": 15915, "total_steps": 61300, "loss": 0.3477, "lr": 4.621928798756299e-05, "epoch": 2.596247960848287, "percentage": 25.96, "elapsed_time": "2:10:00", "remaining_time": "6:10:45", "throughput": 4403.17, "total_tokens": 34347568} {"current_steps": 15920, "total_steps": 61300, "loss": 0.3482, "lr": 4.621552342478604e-05, "epoch": 2.597063621533442, "percentage": 25.97, "elapsed_time": "2:10:02", "remaining_time": "6:10:42", "throughput": 4403.3, "total_tokens": 34358864} {"current_steps": 15925, "total_steps": 61300, "loss": 0.3415, "lr": 4.6211757142171105e-05, "epoch": 2.597879282218597, "percentage": 25.98, "elapsed_time": "2:10:05", "remaining_time": "6:10:40", "throughput": 4403.42, "total_tokens": 34371024} {"current_steps": 15930, "total_steps": 61300, "loss": 0.3346, "lr": 4.620798914002352e-05, "epoch": 2.598694942903752, "percentage": 25.99, "elapsed_time": "2:10:07", "remaining_time": "6:10:37", "throughput": 4403.51, "total_tokens": 34381520} {"current_steps": 15935, "total_steps": 61300, "loss": 0.3231, "lr": 4.6204219418648724e-05, "epoch": 2.5995106035889073, "percentage": 26.0, "elapsed_time": "2:10:10", "remaining_time": "6:10:34", "throughput": 4403.65, "total_tokens": 34392880} {"current_steps": 15940, "total_steps": 61300, "loss": 0.3574, "lr": 4.6200447978352315e-05, "epoch": 2.600326264274062, "percentage": 26.0, "elapsed_time": "2:10:12", "remaining_time": "6:10:31", "throughput": 4403.78, "total_tokens": 34404816} {"current_steps": 15945, "total_steps": 61300, "loss": 0.3463, "lr": 4.6196674819440015e-05, "epoch": 2.601141924959217, "percentage": 26.01, "elapsed_time": "2:10:14", "remaining_time": "6:10:28", "throughput": 4403.88, "total_tokens": 34414896} {"current_steps": 15950, "total_steps": 61300, "loss": 0.3484, "lr": 4.619289994221771e-05, "epoch": 2.6019575856443717, "percentage": 26.02, "elapsed_time": "2:10:17", "remaining_time": "6:10:25", "throughput": 4404.01, "total_tokens": 34426480} {"current_steps": 15955, "total_steps": 61300, "loss": 0.3177, "lr": 4.61891233469914e-05, "epoch": 2.602773246329527, "percentage": 26.03, "elapsed_time": "2:10:19", "remaining_time": "6:10:22", "throughput": 4404.16, "total_tokens": 34437328} {"current_steps": 15960, "total_steps": 61300, "loss": 0.3441, "lr": 4.618534503406724e-05, "epoch": 2.603588907014682, "percentage": 26.04, "elapsed_time": "2:10:21", "remaining_time": "6:10:20", "throughput": 4404.29, "total_tokens": 34449584} {"current_steps": 15965, "total_steps": 61300, "loss": 0.3815, "lr": 4.6181565003751525e-05, "epoch": 2.604404567699837, "percentage": 26.04, "elapsed_time": "2:10:24", "remaining_time": "6:10:17", "throughput": 4404.41, "total_tokens": 34460592} {"current_steps": 15970, "total_steps": 61300, "loss": 0.338, "lr": 4.617778325635067e-05, "epoch": 2.605220228384992, "percentage": 26.05, "elapsed_time": "2:10:26", "remaining_time": "6:10:15", "throughput": 4404.55, "total_tokens": 34472944} {"current_steps": 15975, "total_steps": 61300, "loss": 0.3609, "lr": 4.617399979217125e-05, "epoch": 2.6060358890701467, "percentage": 26.06, "elapsed_time": "2:10:28", "remaining_time": "6:10:12", "throughput": 4404.67, "total_tokens": 34483536} {"current_steps": 15980, "total_steps": 61300, "loss": 0.354, "lr": 4.617021461151997e-05, "epoch": 2.6068515497553015, "percentage": 26.07, "elapsed_time": "2:10:31", "remaining_time": "6:10:09", "throughput": 4404.8, "total_tokens": 34495248} {"current_steps": 15985, "total_steps": 61300, "loss": 0.3416, "lr": 4.616642771470367e-05, "epoch": 2.607667210440457, "percentage": 26.08, "elapsed_time": "2:10:33", "remaining_time": "6:10:07", "throughput": 4404.92, "total_tokens": 34506832} {"current_steps": 15990, "total_steps": 61300, "loss": 0.3803, "lr": 4.616263910202936e-05, "epoch": 2.6084828711256116, "percentage": 26.08, "elapsed_time": "2:10:35", "remaining_time": "6:10:04", "throughput": 4405.03, "total_tokens": 34517168} {"current_steps": 15995, "total_steps": 61300, "loss": 0.3404, "lr": 4.615884877380413e-05, "epoch": 2.609298531810767, "percentage": 26.09, "elapsed_time": "2:10:38", "remaining_time": "6:10:01", "throughput": 4405.15, "total_tokens": 34528272} {"current_steps": 16000, "total_steps": 61300, "loss": 0.3376, "lr": 4.6155056730335274e-05, "epoch": 2.6101141924959217, "percentage": 26.1, "elapsed_time": "2:10:40", "remaining_time": "6:09:57", "throughput": 4405.25, "total_tokens": 34537904} {"current_steps": 16005, "total_steps": 61300, "loss": 0.3441, "lr": 4.615126297193017e-05, "epoch": 2.6109298531810765, "percentage": 26.11, "elapsed_time": "2:10:42", "remaining_time": "6:09:54", "throughput": 4405.35, "total_tokens": 34548368} {"current_steps": 16010, "total_steps": 61300, "loss": 0.3544, "lr": 4.614746749889637e-05, "epoch": 2.6117455138662318, "percentage": 26.12, "elapsed_time": "2:10:44", "remaining_time": "6:09:51", "throughput": 4405.48, "total_tokens": 34559024} {"current_steps": 16015, "total_steps": 61300, "loss": 0.3826, "lr": 4.614367031154155e-05, "epoch": 2.6125611745513866, "percentage": 26.13, "elapsed_time": "2:10:46", "remaining_time": "6:09:48", "throughput": 4405.61, "total_tokens": 34570224} {"current_steps": 16020, "total_steps": 61300, "loss": 0.346, "lr": 4.613987141017354e-05, "epoch": 2.613376835236542, "percentage": 26.13, "elapsed_time": "2:10:49", "remaining_time": "6:09:45", "throughput": 4405.74, "total_tokens": 34581968} {"current_steps": 16025, "total_steps": 61300, "loss": 0.342, "lr": 4.6136070795100285e-05, "epoch": 2.6141924959216967, "percentage": 26.14, "elapsed_time": "2:10:51", "remaining_time": "6:09:43", "throughput": 4405.88, "total_tokens": 34593392} {"current_steps": 16030, "total_steps": 61300, "loss": 0.3397, "lr": 4.613226846662989e-05, "epoch": 2.6150081566068515, "percentage": 26.15, "elapsed_time": "2:10:53", "remaining_time": "6:09:39", "throughput": 4406.02, "total_tokens": 34604176} {"current_steps": 16035, "total_steps": 61300, "loss": 0.3639, "lr": 4.6128464425070595e-05, "epoch": 2.6158238172920063, "percentage": 26.16, "elapsed_time": "2:10:56", "remaining_time": "6:09:36", "throughput": 4406.15, "total_tokens": 34615024} {"current_steps": 16040, "total_steps": 61300, "loss": 0.3261, "lr": 4.612465867073076e-05, "epoch": 2.6166394779771616, "percentage": 26.17, "elapsed_time": "2:10:58", "remaining_time": "6:09:33", "throughput": 4406.27, "total_tokens": 34626160} {"current_steps": 16045, "total_steps": 61300, "loss": 0.3306, "lr": 4.612085120391891e-05, "epoch": 2.6174551386623164, "percentage": 26.17, "elapsed_time": "2:11:00", "remaining_time": "6:09:30", "throughput": 4406.36, "total_tokens": 34635632} {"current_steps": 16050, "total_steps": 61300, "loss": 0.3777, "lr": 4.61170420249437e-05, "epoch": 2.6182707993474716, "percentage": 26.18, "elapsed_time": "2:11:02", "remaining_time": "6:09:27", "throughput": 4406.49, "total_tokens": 34646288} {"current_steps": 16055, "total_steps": 61300, "loss": 0.3425, "lr": 4.611323113411391e-05, "epoch": 2.6190864600326265, "percentage": 26.19, "elapsed_time": "2:11:04", "remaining_time": "6:09:24", "throughput": 4406.61, "total_tokens": 34657232} {"current_steps": 16060, "total_steps": 61300, "loss": 0.3219, "lr": 4.610941853173848e-05, "epoch": 2.6199021207177813, "percentage": 26.2, "elapsed_time": "2:11:06", "remaining_time": "6:09:20", "throughput": 4406.72, "total_tokens": 34667408} {"current_steps": 16065, "total_steps": 61300, "loss": 0.33, "lr": 4.610560421812647e-05, "epoch": 2.6207177814029365, "percentage": 26.21, "elapsed_time": "2:11:09", "remaining_time": "6:09:17", "throughput": 4406.8, "total_tokens": 34677616} {"current_steps": 16070, "total_steps": 61300, "loss": 0.3352, "lr": 4.6101788193587103e-05, "epoch": 2.6215334420880914, "percentage": 26.22, "elapsed_time": "2:11:11", "remaining_time": "6:09:14", "throughput": 4406.93, "total_tokens": 34688688} {"current_steps": 16075, "total_steps": 61300, "loss": 0.3073, "lr": 4.609797045842972e-05, "epoch": 2.622349102773246, "percentage": 26.22, "elapsed_time": "2:11:13", "remaining_time": "6:09:11", "throughput": 4407.05, "total_tokens": 34700272} {"current_steps": 16080, "total_steps": 61300, "loss": 0.4089, "lr": 4.609415101296379e-05, "epoch": 2.6231647634584014, "percentage": 26.23, "elapsed_time": "2:11:16", "remaining_time": "6:09:08", "throughput": 4407.16, "total_tokens": 34710832} {"current_steps": 16085, "total_steps": 61300, "loss": 0.3292, "lr": 4.609032985749895e-05, "epoch": 2.6239804241435563, "percentage": 26.24, "elapsed_time": "2:11:18", "remaining_time": "6:09:06", "throughput": 4407.28, "total_tokens": 34722224} {"current_steps": 16090, "total_steps": 61300, "loss": 0.3477, "lr": 4.6086506992344956e-05, "epoch": 2.624796084828711, "percentage": 26.25, "elapsed_time": "2:11:20", "remaining_time": "6:09:03", "throughput": 4407.36, "total_tokens": 34733136} {"current_steps": 16095, "total_steps": 61300, "loss": 0.3865, "lr": 4.608268241781172e-05, "epoch": 2.6256117455138663, "percentage": 26.26, "elapsed_time": "2:11:22", "remaining_time": "6:09:00", "throughput": 4407.45, "total_tokens": 34743408} {"current_steps": 16100, "total_steps": 61300, "loss": 0.3553, "lr": 4.6078856134209284e-05, "epoch": 2.626427406199021, "percentage": 26.26, "elapsed_time": "2:11:25", "remaining_time": "6:08:57", "throughput": 4407.58, "total_tokens": 34755184} {"current_steps": 16105, "total_steps": 61300, "loss": 0.3436, "lr": 4.6075028141847795e-05, "epoch": 2.6272430668841764, "percentage": 26.27, "elapsed_time": "2:11:27", "remaining_time": "6:08:53", "throughput": 4407.71, "total_tokens": 34765040} {"current_steps": 16110, "total_steps": 61300, "loss": 0.3703, "lr": 4.607119844103761e-05, "epoch": 2.6280587275693312, "percentage": 26.28, "elapsed_time": "2:11:29", "remaining_time": "6:08:50", "throughput": 4407.81, "total_tokens": 34775312} {"current_steps": 16115, "total_steps": 61300, "loss": 0.3352, "lr": 4.606736703208916e-05, "epoch": 2.628874388254486, "percentage": 26.29, "elapsed_time": "2:11:31", "remaining_time": "6:08:46", "throughput": 4407.9, "total_tokens": 34784400} {"current_steps": 16120, "total_steps": 61300, "loss": 0.3298, "lr": 4.606353391531304e-05, "epoch": 2.629690048939641, "percentage": 26.3, "elapsed_time": "2:11:33", "remaining_time": "6:08:44", "throughput": 4408.05, "total_tokens": 34796080} {"current_steps": 16125, "total_steps": 61300, "loss": 0.3589, "lr": 4.605969909101998e-05, "epoch": 2.630505709624796, "percentage": 26.31, "elapsed_time": "2:11:36", "remaining_time": "6:08:41", "throughput": 4408.16, "total_tokens": 34807280} {"current_steps": 16130, "total_steps": 61300, "loss": 0.3644, "lr": 4.605586255952087e-05, "epoch": 2.631321370309951, "percentage": 26.31, "elapsed_time": "2:11:38", "remaining_time": "6:08:38", "throughput": 4408.29, "total_tokens": 34818896} {"current_steps": 16135, "total_steps": 61300, "loss": 0.3528, "lr": 4.6052024321126695e-05, "epoch": 2.632137030995106, "percentage": 26.32, "elapsed_time": "2:11:40", "remaining_time": "6:08:36", "throughput": 4408.42, "total_tokens": 34830288} {"current_steps": 16140, "total_steps": 61300, "loss": 0.3465, "lr": 4.6048184376148616e-05, "epoch": 2.632952691680261, "percentage": 26.33, "elapsed_time": "2:11:43", "remaining_time": "6:08:32", "throughput": 4408.53, "total_tokens": 34840688} {"current_steps": 16145, "total_steps": 61300, "loss": 0.3541, "lr": 4.6044342724897915e-05, "epoch": 2.633768352365416, "percentage": 26.34, "elapsed_time": "2:11:45", "remaining_time": "6:08:30", "throughput": 4408.64, "total_tokens": 34852848} {"current_steps": 16150, "total_steps": 61300, "loss": 0.3407, "lr": 4.604049936768601e-05, "epoch": 2.634584013050571, "percentage": 26.35, "elapsed_time": "2:11:47", "remaining_time": "6:08:27", "throughput": 4408.73, "total_tokens": 34863728} {"current_steps": 16155, "total_steps": 61300, "loss": 0.3555, "lr": 4.6036654304824464e-05, "epoch": 2.635399673735726, "percentage": 26.35, "elapsed_time": "2:11:50", "remaining_time": "6:08:24", "throughput": 4408.84, "total_tokens": 34874672} {"current_steps": 16160, "total_steps": 61300, "loss": 0.36, "lr": 4.603280753662499e-05, "epoch": 2.636215334420881, "percentage": 26.36, "elapsed_time": "2:11:52", "remaining_time": "6:08:22", "throughput": 4408.97, "total_tokens": 34885904} {"current_steps": 16165, "total_steps": 61300, "loss": 0.3504, "lr": 4.602895906339941e-05, "epoch": 2.637030995106036, "percentage": 26.37, "elapsed_time": "2:11:54", "remaining_time": "6:08:18", "throughput": 4409.07, "total_tokens": 34896144} {"current_steps": 16170, "total_steps": 61300, "loss": 0.3299, "lr": 4.6025108885459725e-05, "epoch": 2.637846655791191, "percentage": 26.38, "elapsed_time": "2:11:56", "remaining_time": "6:08:15", "throughput": 4409.18, "total_tokens": 34906928} {"current_steps": 16175, "total_steps": 61300, "loss": 0.326, "lr": 4.602125700311801e-05, "epoch": 2.6386623164763456, "percentage": 26.39, "elapsed_time": "2:11:59", "remaining_time": "6:08:12", "throughput": 4409.29, "total_tokens": 34917392} {"current_steps": 16180, "total_steps": 61300, "loss": 0.3642, "lr": 4.6017403416686555e-05, "epoch": 2.639477977161501, "percentage": 26.39, "elapsed_time": "2:12:01", "remaining_time": "6:08:09", "throughput": 4409.41, "total_tokens": 34928240} {"current_steps": 16185, "total_steps": 61300, "loss": 0.4015, "lr": 4.601354812647774e-05, "epoch": 2.6402936378466557, "percentage": 26.4, "elapsed_time": "2:12:03", "remaining_time": "6:08:07", "throughput": 4409.52, "total_tokens": 34939824} {"current_steps": 16190, "total_steps": 61300, "loss": 0.3441, "lr": 4.600969113280409e-05, "epoch": 2.641109298531811, "percentage": 26.41, "elapsed_time": "2:12:05", "remaining_time": "6:08:04", "throughput": 4409.64, "total_tokens": 34950704} {"current_steps": 16195, "total_steps": 61300, "loss": 0.3257, "lr": 4.6005832435978266e-05, "epoch": 2.641924959216966, "percentage": 26.42, "elapsed_time": "2:12:08", "remaining_time": "6:08:01", "throughput": 4409.78, "total_tokens": 34962224} {"current_steps": 16200, "total_steps": 61300, "loss": 0.3549, "lr": 4.600197203631309e-05, "epoch": 2.6427406199021206, "percentage": 26.43, "elapsed_time": "2:12:10", "remaining_time": "6:07:58", "throughput": 4409.92, "total_tokens": 34973936} {"current_steps": 16205, "total_steps": 61300, "loss": 0.3389, "lr": 4.5998109934121494e-05, "epoch": 2.6435562805872754, "percentage": 26.44, "elapsed_time": "2:12:13", "remaining_time": "6:07:56", "throughput": 4410.05, "total_tokens": 34985296} {"current_steps": 16210, "total_steps": 61300, "loss": 0.3526, "lr": 4.599424612971657e-05, "epoch": 2.6443719412724307, "percentage": 26.44, "elapsed_time": "2:12:15", "remaining_time": "6:07:53", "throughput": 4410.15, "total_tokens": 34996528} {"current_steps": 16215, "total_steps": 61300, "loss": 0.351, "lr": 4.599038062341153e-05, "epoch": 2.6451876019575855, "percentage": 26.45, "elapsed_time": "2:12:17", "remaining_time": "6:07:50", "throughput": 4410.25, "total_tokens": 35007056} {"current_steps": 16220, "total_steps": 61300, "loss": 0.3395, "lr": 4.598651341551973e-05, "epoch": 2.6460032626427408, "percentage": 26.46, "elapsed_time": "2:12:19", "remaining_time": "6:07:47", "throughput": 4410.38, "total_tokens": 35017744} {"current_steps": 16225, "total_steps": 61300, "loss": 0.337, "lr": 4.5982644506354666e-05, "epoch": 2.6468189233278956, "percentage": 26.47, "elapsed_time": "2:12:22", "remaining_time": "6:07:44", "throughput": 4410.52, "total_tokens": 35029104} {"current_steps": 16230, "total_steps": 61300, "loss": 0.3408, "lr": 4.5978773896229977e-05, "epoch": 2.6476345840130504, "percentage": 26.48, "elapsed_time": "2:12:24", "remaining_time": "6:07:41", "throughput": 4410.63, "total_tokens": 35039632} {"current_steps": 16235, "total_steps": 61300, "loss": 0.3615, "lr": 4.597490158545943e-05, "epoch": 2.6484502446982057, "percentage": 26.48, "elapsed_time": "2:12:26", "remaining_time": "6:07:38", "throughput": 4410.74, "total_tokens": 35050704} {"current_steps": 16240, "total_steps": 61300, "loss": 0.3621, "lr": 4.5971027574356926e-05, "epoch": 2.6492659053833605, "percentage": 26.49, "elapsed_time": "2:12:28", "remaining_time": "6:07:34", "throughput": 4410.82, "total_tokens": 35060688} {"current_steps": 16245, "total_steps": 61300, "loss": 0.3581, "lr": 4.5967151863236534e-05, "epoch": 2.6500815660685157, "percentage": 26.5, "elapsed_time": "2:12:31", "remaining_time": "6:07:32", "throughput": 4410.96, "total_tokens": 35071920} {"current_steps": 16250, "total_steps": 61300, "loss": 0.3208, "lr": 4.5963274452412416e-05, "epoch": 2.6508972267536706, "percentage": 26.51, "elapsed_time": "2:12:33", "remaining_time": "6:07:29", "throughput": 4411.1, "total_tokens": 35083056} {"current_steps": 16255, "total_steps": 61300, "loss": 0.3884, "lr": 4.595939534219891e-05, "epoch": 2.6517128874388254, "percentage": 26.52, "elapsed_time": "2:12:35", "remaining_time": "6:07:26", "throughput": 4411.22, "total_tokens": 35094320} {"current_steps": 16260, "total_steps": 61300, "loss": 0.3469, "lr": 4.595551453291047e-05, "epoch": 2.65252854812398, "percentage": 26.53, "elapsed_time": "2:12:37", "remaining_time": "6:07:23", "throughput": 4411.32, "total_tokens": 35104560} {"current_steps": 16265, "total_steps": 61300, "loss": 0.3654, "lr": 4.5951632024861694e-05, "epoch": 2.6533442088091355, "percentage": 26.53, "elapsed_time": "2:12:40", "remaining_time": "6:07:20", "throughput": 4411.44, "total_tokens": 35115376} {"current_steps": 16270, "total_steps": 61300, "loss": 0.3639, "lr": 4.594774781836732e-05, "epoch": 2.6541598694942903, "percentage": 26.54, "elapsed_time": "2:12:42", "remaining_time": "6:07:17", "throughput": 4411.55, "total_tokens": 35126192} {"current_steps": 16275, "total_steps": 61300, "loss": 0.3427, "lr": 4.594386191374221e-05, "epoch": 2.6549755301794455, "percentage": 26.55, "elapsed_time": "2:12:44", "remaining_time": "6:07:14", "throughput": 4411.69, "total_tokens": 35137936} {"current_steps": 16280, "total_steps": 61300, "loss": 0.3553, "lr": 4.5939974311301406e-05, "epoch": 2.6557911908646004, "percentage": 26.56, "elapsed_time": "2:12:46", "remaining_time": "6:07:11", "throughput": 4411.8, "total_tokens": 35148560} {"current_steps": 16285, "total_steps": 61300, "loss": 0.3156, "lr": 4.593608501136002e-05, "epoch": 2.656606851549755, "percentage": 26.57, "elapsed_time": "2:12:49", "remaining_time": "6:07:08", "throughput": 4411.9, "total_tokens": 35159632} {"current_steps": 16290, "total_steps": 61300, "loss": 0.3752, "lr": 4.5932194014233356e-05, "epoch": 2.6574225122349104, "percentage": 26.57, "elapsed_time": "2:12:51", "remaining_time": "6:07:05", "throughput": 4411.99, "total_tokens": 35170000} {"current_steps": 16295, "total_steps": 61300, "loss": 0.3635, "lr": 4.592830132023684e-05, "epoch": 2.6582381729200653, "percentage": 26.58, "elapsed_time": "2:12:53", "remaining_time": "6:07:02", "throughput": 4412.15, "total_tokens": 35181360} {"current_steps": 16300, "total_steps": 61300, "loss": 0.337, "lr": 4.592440692968602e-05, "epoch": 2.65905383360522, "percentage": 26.59, "elapsed_time": "2:12:55", "remaining_time": "6:06:59", "throughput": 4412.24, "total_tokens": 35191600} {"current_steps": 16305, "total_steps": 61300, "loss": 0.3785, "lr": 4.5920510842896624e-05, "epoch": 2.6598694942903753, "percentage": 26.6, "elapsed_time": "2:12:57", "remaining_time": "6:06:55", "throughput": 4412.34, "total_tokens": 35201136} {"current_steps": 16310, "total_steps": 61300, "loss": 0.3534, "lr": 4.591661306018446e-05, "epoch": 2.66068515497553, "percentage": 26.61, "elapsed_time": "2:13:00", "remaining_time": "6:06:52", "throughput": 4412.46, "total_tokens": 35211600} {"current_steps": 16315, "total_steps": 61300, "loss": 0.3703, "lr": 4.591271358186551e-05, "epoch": 2.661500815660685, "percentage": 26.62, "elapsed_time": "2:13:02", "remaining_time": "6:06:49", "throughput": 4412.57, "total_tokens": 35222416} {"current_steps": 16320, "total_steps": 61300, "loss": 0.3356, "lr": 4.5908812408255884e-05, "epoch": 2.6623164763458402, "percentage": 26.62, "elapsed_time": "2:13:04", "remaining_time": "6:06:46", "throughput": 4412.7, "total_tokens": 35233904} {"current_steps": 16325, "total_steps": 61300, "loss": 0.3448, "lr": 4.5904909539671836e-05, "epoch": 2.663132137030995, "percentage": 26.63, "elapsed_time": "2:13:06", "remaining_time": "6:06:43", "throughput": 4412.82, "total_tokens": 35243984} {"current_steps": 16330, "total_steps": 61300, "loss": 0.3381, "lr": 4.590100497642975e-05, "epoch": 2.6639477977161503, "percentage": 26.64, "elapsed_time": "2:13:09", "remaining_time": "6:06:40", "throughput": 4412.91, "total_tokens": 35255216} {"current_steps": 16335, "total_steps": 61300, "loss": 0.3968, "lr": 4.589709871884615e-05, "epoch": 2.664763458401305, "percentage": 26.65, "elapsed_time": "2:13:11", "remaining_time": "6:06:37", "throughput": 4413.0, "total_tokens": 35265136} {"current_steps": 16340, "total_steps": 61300, "loss": 0.3283, "lr": 4.58931907672377e-05, "epoch": 2.66557911908646, "percentage": 26.66, "elapsed_time": "2:13:13", "remaining_time": "6:06:34", "throughput": 4413.1, "total_tokens": 35275600} {"current_steps": 16345, "total_steps": 61300, "loss": 0.3432, "lr": 4.588928112192119e-05, "epoch": 2.6663947797716148, "percentage": 26.66, "elapsed_time": "2:13:15", "remaining_time": "6:06:31", "throughput": 4413.24, "total_tokens": 35286928} {"current_steps": 16350, "total_steps": 61300, "loss": 0.3533, "lr": 4.588536978321357e-05, "epoch": 2.66721044045677, "percentage": 26.67, "elapsed_time": "2:13:18", "remaining_time": "6:06:28", "throughput": 4413.36, "total_tokens": 35299024} {"current_steps": 16355, "total_steps": 61300, "loss": 0.3889, "lr": 4.588145675143189e-05, "epoch": 2.668026101141925, "percentage": 26.68, "elapsed_time": "2:13:20", "remaining_time": "6:06:26", "throughput": 4413.49, "total_tokens": 35310320} {"current_steps": 16360, "total_steps": 61300, "loss": 0.3746, "lr": 4.5877542026893395e-05, "epoch": 2.66884176182708, "percentage": 26.69, "elapsed_time": "2:13:22", "remaining_time": "6:06:23", "throughput": 4413.61, "total_tokens": 35321104} {"current_steps": 16365, "total_steps": 61300, "loss": 0.3453, "lr": 4.5873625609915393e-05, "epoch": 2.669657422512235, "percentage": 26.7, "elapsed_time": "2:13:25", "remaining_time": "6:06:20", "throughput": 4413.73, "total_tokens": 35332688} {"current_steps": 16370, "total_steps": 61300, "loss": 0.356, "lr": 4.58697075008154e-05, "epoch": 2.6704730831973897, "percentage": 26.7, "elapsed_time": "2:13:27", "remaining_time": "6:06:17", "throughput": 4413.83, "total_tokens": 35342416} {"current_steps": 16375, "total_steps": 61300, "loss": 0.3282, "lr": 4.586578769991102e-05, "epoch": 2.671288743882545, "percentage": 26.71, "elapsed_time": "2:13:29", "remaining_time": "6:06:14", "throughput": 4413.94, "total_tokens": 35353616} {"current_steps": 16380, "total_steps": 61300, "loss": 0.3312, "lr": 4.586186620752001e-05, "epoch": 2.6721044045677, "percentage": 26.72, "elapsed_time": "2:13:31", "remaining_time": "6:06:11", "throughput": 4414.05, "total_tokens": 35364304} {"current_steps": 16385, "total_steps": 61300, "loss": 0.3461, "lr": 4.585794302396028e-05, "epoch": 2.672920065252855, "percentage": 26.73, "elapsed_time": "2:13:34", "remaining_time": "6:06:08", "throughput": 4414.14, "total_tokens": 35374992} {"current_steps": 16390, "total_steps": 61300, "loss": 0.357, "lr": 4.585401814954986e-05, "epoch": 2.67373572593801, "percentage": 26.74, "elapsed_time": "2:13:36", "remaining_time": "6:06:05", "throughput": 4414.26, "total_tokens": 35386544} {"current_steps": 16395, "total_steps": 61300, "loss": 0.329, "lr": 4.5850091584606906e-05, "epoch": 2.6745513866231647, "percentage": 26.75, "elapsed_time": "2:13:38", "remaining_time": "6:06:02", "throughput": 4414.38, "total_tokens": 35397616} {"current_steps": 16400, "total_steps": 61300, "loss": 0.3397, "lr": 4.5846163329449745e-05, "epoch": 2.6753670473083195, "percentage": 26.75, "elapsed_time": "2:13:40", "remaining_time": "6:05:59", "throughput": 4414.49, "total_tokens": 35407408} {"current_steps": 16405, "total_steps": 61300, "loss": 0.3367, "lr": 4.584223338439681e-05, "epoch": 2.676182707993475, "percentage": 26.76, "elapsed_time": "2:13:43", "remaining_time": "6:05:56", "throughput": 4414.61, "total_tokens": 35418512} {"current_steps": 16410, "total_steps": 61300, "loss": 0.3675, "lr": 4.583830174976669e-05, "epoch": 2.6769983686786296, "percentage": 26.77, "elapsed_time": "2:13:45", "remaining_time": "6:05:53", "throughput": 4414.72, "total_tokens": 35429712} {"current_steps": 16415, "total_steps": 61300, "loss": 0.3682, "lr": 4.5834368425878085e-05, "epoch": 2.677814029363785, "percentage": 26.78, "elapsed_time": "2:13:47", "remaining_time": "6:05:50", "throughput": 4414.85, "total_tokens": 35440560} {"current_steps": 16420, "total_steps": 61300, "loss": 0.3488, "lr": 4.583043341304987e-05, "epoch": 2.6786296900489397, "percentage": 26.79, "elapsed_time": "2:13:49", "remaining_time": "6:05:47", "throughput": 4414.99, "total_tokens": 35451504} {"current_steps": 16425, "total_steps": 61300, "loss": 0.3048, "lr": 4.582649671160103e-05, "epoch": 2.6794453507340945, "percentage": 26.79, "elapsed_time": "2:13:52", "remaining_time": "6:05:44", "throughput": 4415.11, "total_tokens": 35462640} {"current_steps": 16430, "total_steps": 61300, "loss": 0.3639, "lr": 4.5822558321850696e-05, "epoch": 2.6802610114192493, "percentage": 26.8, "elapsed_time": "2:13:54", "remaining_time": "6:05:42", "throughput": 4415.22, "total_tokens": 35474160} {"current_steps": 16435, "total_steps": 61300, "loss": 0.3057, "lr": 4.5818618244118126e-05, "epoch": 2.6810766721044046, "percentage": 26.81, "elapsed_time": "2:13:56", "remaining_time": "6:05:39", "throughput": 4415.35, "total_tokens": 35485200} {"current_steps": 16440, "total_steps": 61300, "loss": 0.3567, "lr": 4.581467647872273e-05, "epoch": 2.6818923327895594, "percentage": 26.82, "elapsed_time": "2:13:59", "remaining_time": "6:05:36", "throughput": 4415.45, "total_tokens": 35496176} {"current_steps": 16445, "total_steps": 61300, "loss": 0.3671, "lr": 4.5810733025984045e-05, "epoch": 2.6827079934747147, "percentage": 26.83, "elapsed_time": "2:14:01", "remaining_time": "6:05:33", "throughput": 4415.58, "total_tokens": 35506960} {"current_steps": 16450, "total_steps": 61300, "loss": 0.3327, "lr": 4.580678788622176e-05, "epoch": 2.6835236541598695, "percentage": 26.84, "elapsed_time": "2:14:03", "remaining_time": "6:05:30", "throughput": 4415.69, "total_tokens": 35517744} {"current_steps": 16455, "total_steps": 61300, "loss": 0.3706, "lr": 4.580284105975566e-05, "epoch": 2.6843393148450243, "percentage": 26.84, "elapsed_time": "2:14:06", "remaining_time": "6:05:27", "throughput": 4415.81, "total_tokens": 35529680} {"current_steps": 16460, "total_steps": 61300, "loss": 0.3225, "lr": 4.5798892546905726e-05, "epoch": 2.6851549755301796, "percentage": 26.85, "elapsed_time": "2:14:08", "remaining_time": "6:05:24", "throughput": 4415.92, "total_tokens": 35540496} {"current_steps": 16465, "total_steps": 61300, "loss": 0.329, "lr": 4.579494234799202e-05, "epoch": 2.6859706362153344, "percentage": 26.86, "elapsed_time": "2:14:10", "remaining_time": "6:05:22", "throughput": 4416.07, "total_tokens": 35552176} {"current_steps": 16470, "total_steps": 61300, "loss": 0.3328, "lr": 4.579099046333477e-05, "epoch": 2.6867862969004896, "percentage": 26.87, "elapsed_time": "2:14:13", "remaining_time": "6:05:19", "throughput": 4416.17, "total_tokens": 35563440} {"current_steps": 16475, "total_steps": 61300, "loss": 0.3119, "lr": 4.5787036893254355e-05, "epoch": 2.6876019575856445, "percentage": 26.88, "elapsed_time": "2:14:15", "remaining_time": "6:05:16", "throughput": 4416.28, "total_tokens": 35574256} {"current_steps": 16480, "total_steps": 61300, "loss": 0.3327, "lr": 4.578308163807125e-05, "epoch": 2.6884176182707993, "percentage": 26.88, "elapsed_time": "2:14:17", "remaining_time": "6:05:13", "throughput": 4416.38, "total_tokens": 35584368} {"current_steps": 16485, "total_steps": 61300, "loss": 0.2984, "lr": 4.577912469810609e-05, "epoch": 2.689233278955954, "percentage": 26.89, "elapsed_time": "2:14:19", "remaining_time": "6:05:10", "throughput": 4416.48, "total_tokens": 35594896} {"current_steps": 16490, "total_steps": 61300, "loss": 0.3583, "lr": 4.577516607367965e-05, "epoch": 2.6900489396411094, "percentage": 26.9, "elapsed_time": "2:14:21", "remaining_time": "6:05:07", "throughput": 4416.59, "total_tokens": 35605488} {"current_steps": 16495, "total_steps": 61300, "loss": 0.3977, "lr": 4.577120576511285e-05, "epoch": 2.690864600326264, "percentage": 26.91, "elapsed_time": "2:14:24", "remaining_time": "6:05:04", "throughput": 4416.74, "total_tokens": 35617616} {"current_steps": 16500, "total_steps": 61300, "loss": 0.3633, "lr": 4.5767243772726706e-05, "epoch": 2.6916802610114194, "percentage": 26.92, "elapsed_time": "2:14:26", "remaining_time": "6:05:01", "throughput": 4416.86, "total_tokens": 35628304} {"current_steps": 16505, "total_steps": 61300, "loss": 0.367, "lr": 4.576328009684241e-05, "epoch": 2.6924959216965743, "percentage": 26.92, "elapsed_time": "2:14:28", "remaining_time": "6:04:59", "throughput": 4417.0, "total_tokens": 35640016} {"current_steps": 16510, "total_steps": 61300, "loss": 0.3329, "lr": 4.5759314737781275e-05, "epoch": 2.693311582381729, "percentage": 26.93, "elapsed_time": "2:14:31", "remaining_time": "6:04:56", "throughput": 4417.12, "total_tokens": 35651632} {"current_steps": 16515, "total_steps": 61300, "loss": 0.3242, "lr": 4.575534769586477e-05, "epoch": 2.6941272430668843, "percentage": 26.94, "elapsed_time": "2:14:33", "remaining_time": "6:04:52", "throughput": 4417.22, "total_tokens": 35661200} {"current_steps": 16520, "total_steps": 61300, "loss": 0.3654, "lr": 4.575137897141446e-05, "epoch": 2.694942903752039, "percentage": 26.95, "elapsed_time": "2:14:35", "remaining_time": "6:04:49", "throughput": 4417.3, "total_tokens": 35671472} {"current_steps": 16525, "total_steps": 61300, "loss": 0.3384, "lr": 4.574740856475207e-05, "epoch": 2.695758564437194, "percentage": 26.96, "elapsed_time": "2:14:37", "remaining_time": "6:04:46", "throughput": 4417.43, "total_tokens": 35682480} {"current_steps": 16530, "total_steps": 61300, "loss": 0.3584, "lr": 4.574343647619949e-05, "epoch": 2.6965742251223492, "percentage": 26.97, "elapsed_time": "2:14:39", "remaining_time": "6:04:43", "throughput": 4417.53, "total_tokens": 35693168} {"current_steps": 16535, "total_steps": 61300, "loss": 0.3508, "lr": 4.573946270607868e-05, "epoch": 2.697389885807504, "percentage": 26.97, "elapsed_time": "2:14:42", "remaining_time": "6:04:41", "throughput": 4417.65, "total_tokens": 35704624} {"current_steps": 16540, "total_steps": 61300, "loss": 0.3389, "lr": 4.573548725471181e-05, "epoch": 2.698205546492659, "percentage": 26.98, "elapsed_time": "2:14:44", "remaining_time": "6:04:37", "throughput": 4417.75, "total_tokens": 35714768} {"current_steps": 16545, "total_steps": 61300, "loss": 0.3462, "lr": 4.573151012242112e-05, "epoch": 2.699021207177814, "percentage": 26.99, "elapsed_time": "2:14:46", "remaining_time": "6:04:33", "throughput": 4417.84, "total_tokens": 35724240} {"current_steps": 16550, "total_steps": 61300, "loss": 0.3424, "lr": 4.5727531309529024e-05, "epoch": 2.699836867862969, "percentage": 27.0, "elapsed_time": "2:14:48", "remaining_time": "6:04:31", "throughput": 4417.97, "total_tokens": 35735472} {"current_steps": 16555, "total_steps": 61300, "loss": 0.3364, "lr": 4.5723550816358076e-05, "epoch": 2.700652528548124, "percentage": 27.01, "elapsed_time": "2:14:51", "remaining_time": "6:04:28", "throughput": 4418.09, "total_tokens": 35747376} {"current_steps": 16560, "total_steps": 61300, "loss": 0.3531, "lr": 4.571956864323095e-05, "epoch": 2.701468189233279, "percentage": 27.01, "elapsed_time": "2:14:53", "remaining_time": "6:04:26", "throughput": 4418.22, "total_tokens": 35758960} {"current_steps": 16565, "total_steps": 61300, "loss": 0.3523, "lr": 4.571558479047046e-05, "epoch": 2.702283849918434, "percentage": 27.02, "elapsed_time": "2:14:55", "remaining_time": "6:04:23", "throughput": 4418.32, "total_tokens": 35770512} {"current_steps": 16570, "total_steps": 61300, "loss": 0.3394, "lr": 4.571159925839956e-05, "epoch": 2.7030995106035887, "percentage": 27.03, "elapsed_time": "2:14:58", "remaining_time": "6:04:20", "throughput": 4418.42, "total_tokens": 35781424} {"current_steps": 16575, "total_steps": 61300, "loss": 0.3609, "lr": 4.570761204734133e-05, "epoch": 2.703915171288744, "percentage": 27.04, "elapsed_time": "2:15:00", "remaining_time": "6:04:18", "throughput": 4418.55, "total_tokens": 35793200} {"current_steps": 16580, "total_steps": 61300, "loss": 0.317, "lr": 4.5703623157619e-05, "epoch": 2.7047308319738987, "percentage": 27.05, "elapsed_time": "2:15:03", "remaining_time": "6:04:15", "throughput": 4418.68, "total_tokens": 35804880} {"current_steps": 16585, "total_steps": 61300, "loss": 0.3441, "lr": 4.5699632589555924e-05, "epoch": 2.705546492659054, "percentage": 27.06, "elapsed_time": "2:15:05", "remaining_time": "6:04:12", "throughput": 4418.79, "total_tokens": 35815376} {"current_steps": 16590, "total_steps": 61300, "loss": 0.3709, "lr": 4.569564034347561e-05, "epoch": 2.706362153344209, "percentage": 27.06, "elapsed_time": "2:15:07", "remaining_time": "6:04:09", "throughput": 4418.88, "total_tokens": 35825008} {"current_steps": 16595, "total_steps": 61300, "loss": 0.345, "lr": 4.5691646419701675e-05, "epoch": 2.7071778140293636, "percentage": 27.07, "elapsed_time": "2:15:09", "remaining_time": "6:04:05", "throughput": 4418.99, "total_tokens": 35834384} {"current_steps": 16600, "total_steps": 61300, "loss": 0.3569, "lr": 4.5687650818557884e-05, "epoch": 2.707993474714519, "percentage": 27.08, "elapsed_time": "2:15:11", "remaining_time": "6:04:01", "throughput": 4419.1, "total_tokens": 35844752} {"current_steps": 16605, "total_steps": 61300, "loss": 0.3176, "lr": 4.568365354036816e-05, "epoch": 2.7088091353996737, "percentage": 27.09, "elapsed_time": "2:15:13", "remaining_time": "6:03:59", "throughput": 4419.21, "total_tokens": 35855664} {"current_steps": 16610, "total_steps": 61300, "loss": 0.3244, "lr": 4.567965458545653e-05, "epoch": 2.709624796084829, "percentage": 27.1, "elapsed_time": "2:15:16", "remaining_time": "6:03:56", "throughput": 4419.32, "total_tokens": 35867472} {"current_steps": 16615, "total_steps": 61300, "loss": 0.3536, "lr": 4.5675653954147174e-05, "epoch": 2.710440456769984, "percentage": 27.1, "elapsed_time": "2:15:18", "remaining_time": "6:03:53", "throughput": 4419.44, "total_tokens": 35878544} {"current_steps": 16620, "total_steps": 61300, "loss": 0.3696, "lr": 4.56716516467644e-05, "epoch": 2.7112561174551386, "percentage": 27.11, "elapsed_time": "2:15:20", "remaining_time": "6:03:51", "throughput": 4419.57, "total_tokens": 35890704} {"current_steps": 16625, "total_steps": 61300, "loss": 0.3684, "lr": 4.5667647663632653e-05, "epoch": 2.7120717781402934, "percentage": 27.12, "elapsed_time": "2:15:23", "remaining_time": "6:03:48", "throughput": 4419.68, "total_tokens": 35901424} {"current_steps": 16630, "total_steps": 61300, "loss": 0.326, "lr": 4.566364200507652e-05, "epoch": 2.7128874388254487, "percentage": 27.13, "elapsed_time": "2:15:25", "remaining_time": "6:03:45", "throughput": 4419.8, "total_tokens": 35912688} {"current_steps": 16635, "total_steps": 61300, "loss": 0.3557, "lr": 4.565963467142073e-05, "epoch": 2.7137030995106035, "percentage": 27.14, "elapsed_time": "2:15:27", "remaining_time": "6:03:43", "throughput": 4419.93, "total_tokens": 35924272} {"current_steps": 16640, "total_steps": 61300, "loss": 0.367, "lr": 4.565562566299012e-05, "epoch": 2.7145187601957588, "percentage": 27.15, "elapsed_time": "2:15:30", "remaining_time": "6:03:40", "throughput": 4420.07, "total_tokens": 35935984} {"current_steps": 16645, "total_steps": 61300, "loss": 0.3466, "lr": 4.5651614980109684e-05, "epoch": 2.7153344208809136, "percentage": 27.15, "elapsed_time": "2:15:32", "remaining_time": "6:03:37", "throughput": 4420.18, "total_tokens": 35945840} {"current_steps": 16650, "total_steps": 61300, "loss": 0.3168, "lr": 4.564760262310456e-05, "epoch": 2.7161500815660684, "percentage": 27.16, "elapsed_time": "2:15:34", "remaining_time": "6:03:33", "throughput": 4420.28, "total_tokens": 35956336} {"current_steps": 16655, "total_steps": 61300, "loss": 0.3697, "lr": 4.5643588592300004e-05, "epoch": 2.7169657422512232, "percentage": 27.17, "elapsed_time": "2:15:36", "remaining_time": "6:03:31", "throughput": 4420.39, "total_tokens": 35967664} {"current_steps": 16660, "total_steps": 61300, "loss": 0.3406, "lr": 4.56395728880214e-05, "epoch": 2.7177814029363785, "percentage": 27.18, "elapsed_time": "2:15:38", "remaining_time": "6:03:28", "throughput": 4420.51, "total_tokens": 35978480} {"current_steps": 16665, "total_steps": 61300, "loss": 0.3278, "lr": 4.5635555510594304e-05, "epoch": 2.7185970636215333, "percentage": 27.19, "elapsed_time": "2:15:41", "remaining_time": "6:03:25", "throughput": 4420.6, "total_tokens": 35989040} {"current_steps": 16670, "total_steps": 61300, "loss": 0.3411, "lr": 4.563153646034437e-05, "epoch": 2.7194127243066886, "percentage": 27.19, "elapsed_time": "2:15:43", "remaining_time": "6:03:22", "throughput": 4420.71, "total_tokens": 35999792} {"current_steps": 16675, "total_steps": 61300, "loss": 0.359, "lr": 4.5627515737597406e-05, "epoch": 2.7202283849918434, "percentage": 27.2, "elapsed_time": "2:15:45", "remaining_time": "6:03:18", "throughput": 4420.8, "total_tokens": 36009392} {"current_steps": 16680, "total_steps": 61300, "loss": 0.341, "lr": 4.562349334267936e-05, "epoch": 2.721044045676998, "percentage": 27.21, "elapsed_time": "2:15:47", "remaining_time": "6:03:15", "throughput": 4420.9, "total_tokens": 36019952} {"current_steps": 16685, "total_steps": 61300, "loss": 0.3051, "lr": 4.5619469275916294e-05, "epoch": 2.7218597063621535, "percentage": 27.22, "elapsed_time": "2:15:49", "remaining_time": "6:03:12", "throughput": 4421.04, "total_tokens": 36031152} {"current_steps": 16690, "total_steps": 61300, "loss": 0.3592, "lr": 4.5615443537634425e-05, "epoch": 2.7226753670473083, "percentage": 27.23, "elapsed_time": "2:15:52", "remaining_time": "6:03:09", "throughput": 4421.15, "total_tokens": 36041808} {"current_steps": 16695, "total_steps": 61300, "loss": 0.3546, "lr": 4.561141612816011e-05, "epoch": 2.7234910277324635, "percentage": 27.23, "elapsed_time": "2:15:54", "remaining_time": "6:03:05", "throughput": 4421.25, "total_tokens": 36051248} {"current_steps": 16700, "total_steps": 61300, "loss": 0.3624, "lr": 4.560738704781982e-05, "epoch": 2.7243066884176184, "percentage": 27.24, "elapsed_time": "2:15:56", "remaining_time": "6:03:03", "throughput": 4421.38, "total_tokens": 36063024} {"current_steps": 16705, "total_steps": 61300, "loss": 0.3409, "lr": 4.560335629694018e-05, "epoch": 2.725122349102773, "percentage": 27.25, "elapsed_time": "2:15:58", "remaining_time": "6:03:00", "throughput": 4421.51, "total_tokens": 36074800} {"current_steps": 16710, "total_steps": 61300, "loss": 0.3762, "lr": 4.559932387584792e-05, "epoch": 2.725938009787928, "percentage": 27.26, "elapsed_time": "2:16:01", "remaining_time": "6:02:57", "throughput": 4421.61, "total_tokens": 36084784} {"current_steps": 16715, "total_steps": 61300, "loss": 0.3517, "lr": 4.559528978486997e-05, "epoch": 2.7267536704730833, "percentage": 27.27, "elapsed_time": "2:16:03", "remaining_time": "6:02:54", "throughput": 4421.7, "total_tokens": 36095248} {"current_steps": 16720, "total_steps": 61300, "loss": 0.3624, "lr": 4.5591254024333304e-05, "epoch": 2.727569331158238, "percentage": 27.28, "elapsed_time": "2:16:05", "remaining_time": "6:02:51", "throughput": 4421.81, "total_tokens": 36106288} {"current_steps": 16725, "total_steps": 61300, "loss": 0.3225, "lr": 4.558721659456513e-05, "epoch": 2.7283849918433933, "percentage": 27.28, "elapsed_time": "2:16:07", "remaining_time": "6:02:48", "throughput": 4421.92, "total_tokens": 36116976} {"current_steps": 16730, "total_steps": 61300, "loss": 0.3519, "lr": 4.558317749589271e-05, "epoch": 2.729200652528548, "percentage": 27.29, "elapsed_time": "2:16:09", "remaining_time": "6:02:45", "throughput": 4422.04, "total_tokens": 36127504} {"current_steps": 16735, "total_steps": 61300, "loss": 0.3535, "lr": 4.557913672864349e-05, "epoch": 2.730016313213703, "percentage": 27.3, "elapsed_time": "2:16:12", "remaining_time": "6:02:41", "throughput": 4422.13, "total_tokens": 36137744} {"current_steps": 16740, "total_steps": 61300, "loss": 0.3614, "lr": 4.5575094293145025e-05, "epoch": 2.7308319738988582, "percentage": 27.31, "elapsed_time": "2:16:14", "remaining_time": "6:02:39", "throughput": 4422.24, "total_tokens": 36149328} {"current_steps": 16745, "total_steps": 61300, "loss": 0.3344, "lr": 4.557105018972502e-05, "epoch": 2.731647634584013, "percentage": 27.32, "elapsed_time": "2:16:16", "remaining_time": "6:02:36", "throughput": 4422.37, "total_tokens": 36160688} {"current_steps": 16750, "total_steps": 61300, "loss": 0.3353, "lr": 4.5567004418711314e-05, "epoch": 2.732463295269168, "percentage": 27.32, "elapsed_time": "2:16:18", "remaining_time": "6:02:33", "throughput": 4422.45, "total_tokens": 36171056} {"current_steps": 16755, "total_steps": 61300, "loss": 0.3494, "lr": 4.556295698043187e-05, "epoch": 2.733278955954323, "percentage": 27.33, "elapsed_time": "2:16:21", "remaining_time": "6:02:30", "throughput": 4422.54, "total_tokens": 36181552} {"current_steps": 16760, "total_steps": 61300, "loss": 0.3515, "lr": 4.55589078752148e-05, "epoch": 2.734094616639478, "percentage": 27.34, "elapsed_time": "2:16:23", "remaining_time": "6:02:27", "throughput": 4422.62, "total_tokens": 36191472} {"current_steps": 16765, "total_steps": 61300, "loss": 0.3724, "lr": 4.5554857103388336e-05, "epoch": 2.7349102773246328, "percentage": 27.35, "elapsed_time": "2:16:25", "remaining_time": "6:02:25", "throughput": 4422.74, "total_tokens": 36204272} {"current_steps": 16770, "total_steps": 61300, "loss": 0.3691, "lr": 4.555080466528087e-05, "epoch": 2.735725938009788, "percentage": 27.36, "elapsed_time": "2:16:28", "remaining_time": "6:02:22", "throughput": 4422.86, "total_tokens": 36216144} {"current_steps": 16775, "total_steps": 61300, "loss": 0.3208, "lr": 4.5546750561220896e-05, "epoch": 2.736541598694943, "percentage": 27.37, "elapsed_time": "2:16:30", "remaining_time": "6:02:19", "throughput": 4422.95, "total_tokens": 36226672} {"current_steps": 16780, "total_steps": 61300, "loss": 0.3778, "lr": 4.554269479153708e-05, "epoch": 2.737357259380098, "percentage": 27.37, "elapsed_time": "2:16:33", "remaining_time": "6:02:17", "throughput": 4423.07, "total_tokens": 36238448} {"current_steps": 16785, "total_steps": 61300, "loss": 0.3138, "lr": 4.553863735655818e-05, "epoch": 2.738172920065253, "percentage": 27.38, "elapsed_time": "2:16:35", "remaining_time": "6:02:14", "throughput": 4423.17, "total_tokens": 36248400} {"current_steps": 16790, "total_steps": 61300, "loss": 0.3558, "lr": 4.553457825661313e-05, "epoch": 2.7389885807504077, "percentage": 27.39, "elapsed_time": "2:16:37", "remaining_time": "6:02:11", "throughput": 4423.28, "total_tokens": 36259824} {"current_steps": 16795, "total_steps": 61300, "loss": 0.3467, "lr": 4.553051749203097e-05, "epoch": 2.7398042414355626, "percentage": 27.4, "elapsed_time": "2:16:39", "remaining_time": "6:02:07", "throughput": 4423.38, "total_tokens": 36269168} {"current_steps": 16800, "total_steps": 61300, "loss": 0.3253, "lr": 4.5526455063140894e-05, "epoch": 2.740619902120718, "percentage": 27.41, "elapsed_time": "2:16:41", "remaining_time": "6:02:03", "throughput": 4423.48, "total_tokens": 36278288} {"current_steps": 16805, "total_steps": 61300, "loss": 0.3679, "lr": 4.552239097027222e-05, "epoch": 2.7414355628058726, "percentage": 27.41, "elapsed_time": "2:16:43", "remaining_time": "6:02:00", "throughput": 4423.58, "total_tokens": 36289200} {"current_steps": 16810, "total_steps": 61300, "loss": 0.3415, "lr": 4.551832521375441e-05, "epoch": 2.742251223491028, "percentage": 27.42, "elapsed_time": "2:16:45", "remaining_time": "6:01:57", "throughput": 4423.68, "total_tokens": 36300112} {"current_steps": 16815, "total_steps": 61300, "loss": 0.3312, "lr": 4.551425779391705e-05, "epoch": 2.7430668841761827, "percentage": 27.43, "elapsed_time": "2:16:47", "remaining_time": "6:01:54", "throughput": 4423.78, "total_tokens": 36309872} {"current_steps": 16820, "total_steps": 61300, "loss": 0.3333, "lr": 4.551018871108985e-05, "epoch": 2.7438825448613375, "percentage": 27.44, "elapsed_time": "2:16:49", "remaining_time": "6:01:51", "throughput": 4423.88, "total_tokens": 36320080} {"current_steps": 16825, "total_steps": 61300, "loss": 0.3409, "lr": 4.55061179656027e-05, "epoch": 2.744698205546493, "percentage": 27.45, "elapsed_time": "2:16:52", "remaining_time": "6:01:47", "throughput": 4423.98, "total_tokens": 36330448} {"current_steps": 16830, "total_steps": 61300, "loss": 0.3767, "lr": 4.550204555778558e-05, "epoch": 2.7455138662316476, "percentage": 27.46, "elapsed_time": "2:16:54", "remaining_time": "6:01:44", "throughput": 4424.08, "total_tokens": 36341008} {"current_steps": 16835, "total_steps": 61300, "loss": 0.3388, "lr": 4.549797148796861e-05, "epoch": 2.746329526916803, "percentage": 27.46, "elapsed_time": "2:16:56", "remaining_time": "6:01:41", "throughput": 4424.18, "total_tokens": 36351728} {"current_steps": 16840, "total_steps": 61300, "loss": 0.3469, "lr": 4.549389575648208e-05, "epoch": 2.7471451876019577, "percentage": 27.47, "elapsed_time": "2:16:58", "remaining_time": "6:01:38", "throughput": 4424.32, "total_tokens": 36362832} {"current_steps": 16845, "total_steps": 61300, "loss": 0.3725, "lr": 4.548981836365636e-05, "epoch": 2.7479608482871125, "percentage": 27.48, "elapsed_time": "2:17:01", "remaining_time": "6:01:36", "throughput": 4424.41, "total_tokens": 36373520} {"current_steps": 16850, "total_steps": 61300, "loss": 0.3784, "lr": 4.5485739309822e-05, "epoch": 2.7487765089722673, "percentage": 27.49, "elapsed_time": "2:17:03", "remaining_time": "6:01:33", "throughput": 4424.52, "total_tokens": 36384912} {"current_steps": 16855, "total_steps": 61300, "loss": 0.3178, "lr": 4.548165859530968e-05, "epoch": 2.7495921696574226, "percentage": 27.5, "elapsed_time": "2:17:05", "remaining_time": "6:01:30", "throughput": 4424.63, "total_tokens": 36395760} {"current_steps": 16860, "total_steps": 61300, "loss": 0.3243, "lr": 4.547757622045018e-05, "epoch": 2.7504078303425774, "percentage": 27.5, "elapsed_time": "2:17:08", "remaining_time": "6:01:27", "throughput": 4424.74, "total_tokens": 36406768} {"current_steps": 16865, "total_steps": 61300, "loss": 0.3672, "lr": 4.5473492185574465e-05, "epoch": 2.7512234910277327, "percentage": 27.51, "elapsed_time": "2:17:09", "remaining_time": "6:01:23", "throughput": 4424.79, "total_tokens": 36415728} {"current_steps": 16870, "total_steps": 61300, "loss": 0.375, "lr": 4.546940649101358e-05, "epoch": 2.7520391517128875, "percentage": 27.52, "elapsed_time": "2:17:12", "remaining_time": "6:01:21", "throughput": 4424.94, "total_tokens": 36427728} {"current_steps": 16875, "total_steps": 61300, "loss": 0.36, "lr": 4.546531913709874e-05, "epoch": 2.7528548123980423, "percentage": 27.53, "elapsed_time": "2:17:14", "remaining_time": "6:01:18", "throughput": 4425.05, "total_tokens": 36438640} {"current_steps": 16880, "total_steps": 61300, "loss": 0.3328, "lr": 4.5461230124161294e-05, "epoch": 2.753670473083197, "percentage": 27.54, "elapsed_time": "2:17:16", "remaining_time": "6:01:15", "throughput": 4425.14, "total_tokens": 36448976} {"current_steps": 16885, "total_steps": 61300, "loss": 0.3453, "lr": 4.545713945253272e-05, "epoch": 2.7544861337683524, "percentage": 27.54, "elapsed_time": "2:17:18", "remaining_time": "6:01:11", "throughput": 4425.24, "total_tokens": 36458736} {"current_steps": 16890, "total_steps": 61300, "loss": 0.3286, "lr": 4.545304712254462e-05, "epoch": 2.755301794453507, "percentage": 27.55, "elapsed_time": "2:17:20", "remaining_time": "6:01:08", "throughput": 4425.33, "total_tokens": 36468144} {"current_steps": 16895, "total_steps": 61300, "loss": 0.3115, "lr": 4.544895313452875e-05, "epoch": 2.7561174551386625, "percentage": 27.56, "elapsed_time": "2:17:22", "remaining_time": "6:01:04", "throughput": 4425.43, "total_tokens": 36478512} {"current_steps": 16900, "total_steps": 61300, "loss": 0.2807, "lr": 4.544485748881697e-05, "epoch": 2.7569331158238173, "percentage": 27.57, "elapsed_time": "2:17:25", "remaining_time": "6:01:02", "throughput": 4425.54, "total_tokens": 36490384} {"current_steps": 16905, "total_steps": 61300, "loss": 0.3748, "lr": 4.544076018574131e-05, "epoch": 2.757748776508972, "percentage": 27.58, "elapsed_time": "2:17:27", "remaining_time": "6:00:59", "throughput": 4425.64, "total_tokens": 36500944} {"current_steps": 16910, "total_steps": 61300, "loss": 0.3196, "lr": 4.5436661225633915e-05, "epoch": 2.7585644371941274, "percentage": 27.59, "elapsed_time": "2:17:29", "remaining_time": "6:00:56", "throughput": 4425.72, "total_tokens": 36511056} {"current_steps": 16915, "total_steps": 61300, "loss": 0.3871, "lr": 4.543256060882707e-05, "epoch": 2.759380097879282, "percentage": 27.59, "elapsed_time": "2:17:32", "remaining_time": "6:00:53", "throughput": 4425.84, "total_tokens": 36522448} {"current_steps": 16920, "total_steps": 61300, "loss": 0.3461, "lr": 4.542845833565318e-05, "epoch": 2.7601957585644374, "percentage": 27.6, "elapsed_time": "2:17:34", "remaining_time": "6:00:50", "throughput": 4425.95, "total_tokens": 36533456} {"current_steps": 16925, "total_steps": 61300, "loss": 0.3266, "lr": 4.5424354406444815e-05, "epoch": 2.7610114192495923, "percentage": 27.61, "elapsed_time": "2:17:36", "remaining_time": "6:00:47", "throughput": 4426.07, "total_tokens": 36544656} {"current_steps": 16930, "total_steps": 61300, "loss": 0.3647, "lr": 4.542024882153464e-05, "epoch": 2.761827079934747, "percentage": 27.62, "elapsed_time": "2:17:39", "remaining_time": "6:00:45", "throughput": 4426.2, "total_tokens": 36556144} {"current_steps": 16935, "total_steps": 61300, "loss": 0.358, "lr": 4.541614158125549e-05, "epoch": 2.762642740619902, "percentage": 27.63, "elapsed_time": "2:17:41", "remaining_time": "6:00:41", "throughput": 4426.3, "total_tokens": 36566064} {"current_steps": 16940, "total_steps": 61300, "loss": 0.3491, "lr": 4.541203268594031e-05, "epoch": 2.763458401305057, "percentage": 27.63, "elapsed_time": "2:17:43", "remaining_time": "6:00:38", "throughput": 4426.39, "total_tokens": 36576528} {"current_steps": 16945, "total_steps": 61300, "loss": 0.3227, "lr": 4.5407922135922194e-05, "epoch": 2.764274061990212, "percentage": 27.64, "elapsed_time": "2:17:45", "remaining_time": "6:00:36", "throughput": 4426.5, "total_tokens": 36587856} {"current_steps": 16950, "total_steps": 61300, "loss": 0.352, "lr": 4.5403809931534355e-05, "epoch": 2.7650897226753672, "percentage": 27.65, "elapsed_time": "2:17:47", "remaining_time": "6:00:32", "throughput": 4426.59, "total_tokens": 36597936} {"current_steps": 16955, "total_steps": 61300, "loss": 0.349, "lr": 4.5399696073110166e-05, "epoch": 2.765905383360522, "percentage": 27.66, "elapsed_time": "2:17:49", "remaining_time": "6:00:29", "throughput": 4426.69, "total_tokens": 36608688} {"current_steps": 16960, "total_steps": 61300, "loss": 0.3842, "lr": 4.53955805609831e-05, "epoch": 2.766721044045677, "percentage": 27.67, "elapsed_time": "2:17:52", "remaining_time": "6:00:26", "throughput": 4426.81, "total_tokens": 36619824} {"current_steps": 16965, "total_steps": 61300, "loss": 0.3417, "lr": 4.5391463395486784e-05, "epoch": 2.767536704730832, "percentage": 27.68, "elapsed_time": "2:17:54", "remaining_time": "6:00:24", "throughput": 4426.92, "total_tokens": 36630960} {"current_steps": 16970, "total_steps": 61300, "loss": 0.3481, "lr": 4.538734457695498e-05, "epoch": 2.768352365415987, "percentage": 27.68, "elapsed_time": "2:17:56", "remaining_time": "6:00:20", "throughput": 4427.02, "total_tokens": 36640976} {"current_steps": 16975, "total_steps": 61300, "loss": 0.3348, "lr": 4.5383224105721586e-05, "epoch": 2.7691680261011418, "percentage": 27.69, "elapsed_time": "2:17:58", "remaining_time": "6:00:17", "throughput": 4427.13, "total_tokens": 36651792} {"current_steps": 16980, "total_steps": 61300, "loss": 0.3267, "lr": 4.537910198212061e-05, "epoch": 2.769983686786297, "percentage": 27.7, "elapsed_time": "2:18:01", "remaining_time": "6:00:15", "throughput": 4427.24, "total_tokens": 36662896} {"current_steps": 16985, "total_steps": 61300, "loss": 0.3215, "lr": 4.537497820648624e-05, "epoch": 2.770799347471452, "percentage": 27.71, "elapsed_time": "2:18:03", "remaining_time": "6:00:11", "throughput": 4427.32, "total_tokens": 36673040} {"current_steps": 16990, "total_steps": 61300, "loss": 0.3429, "lr": 4.537085277915275e-05, "epoch": 2.7716150081566067, "percentage": 27.72, "elapsed_time": "2:18:05", "remaining_time": "6:00:09", "throughput": 4427.43, "total_tokens": 36684464} {"current_steps": 16995, "total_steps": 61300, "loss": 0.3037, "lr": 4.536672570045457e-05, "epoch": 2.772430668841762, "percentage": 27.72, "elapsed_time": "2:18:08", "remaining_time": "6:00:06", "throughput": 4427.54, "total_tokens": 36696368} {"current_steps": 17000, "total_steps": 61300, "loss": 0.3762, "lr": 4.536259697072627e-05, "epoch": 2.7732463295269167, "percentage": 27.73, "elapsed_time": "2:18:10", "remaining_time": "6:00:04", "throughput": 4427.63, "total_tokens": 36707600} {"current_steps": 17005, "total_steps": 61300, "loss": 0.3735, "lr": 4.535846659030254e-05, "epoch": 2.774061990212072, "percentage": 27.74, "elapsed_time": "2:18:12", "remaining_time": "6:00:01", "throughput": 4427.74, "total_tokens": 36718992} {"current_steps": 17010, "total_steps": 61300, "loss": 0.306, "lr": 4.5354334559518205e-05, "epoch": 2.774877650897227, "percentage": 27.75, "elapsed_time": "2:18:15", "remaining_time": "5:59:58", "throughput": 4427.85, "total_tokens": 36729840} {"current_steps": 17015, "total_steps": 61300, "loss": 0.3179, "lr": 4.535020087870824e-05, "epoch": 2.7756933115823816, "percentage": 27.76, "elapsed_time": "2:18:16", "remaining_time": "5:59:54", "throughput": 4427.95, "total_tokens": 36738672} {"current_steps": 17020, "total_steps": 61300, "loss": 0.3613, "lr": 4.5346065548207727e-05, "epoch": 2.7765089722675365, "percentage": 27.77, "elapsed_time": "2:18:19", "remaining_time": "5:59:51", "throughput": 4428.06, "total_tokens": 36749104} {"current_steps": 17025, "total_steps": 61300, "loss": 0.3294, "lr": 4.5341928568351915e-05, "epoch": 2.7773246329526917, "percentage": 27.77, "elapsed_time": "2:18:21", "remaining_time": "5:59:48", "throughput": 4428.17, "total_tokens": 36760560} {"current_steps": 17030, "total_steps": 61300, "loss": 0.3559, "lr": 4.533778993947615e-05, "epoch": 2.7781402936378465, "percentage": 27.78, "elapsed_time": "2:18:23", "remaining_time": "5:59:46", "throughput": 4428.28, "total_tokens": 36771728} {"current_steps": 17035, "total_steps": 61300, "loss": 0.3117, "lr": 4.533364966191595e-05, "epoch": 2.778955954323002, "percentage": 27.79, "elapsed_time": "2:18:26", "remaining_time": "5:59:43", "throughput": 4428.38, "total_tokens": 36783472} {"current_steps": 17040, "total_steps": 61300, "loss": 0.3373, "lr": 4.532950773600694e-05, "epoch": 2.7797716150081566, "percentage": 27.8, "elapsed_time": "2:18:28", "remaining_time": "5:59:40", "throughput": 4428.5, "total_tokens": 36794672} {"current_steps": 17045, "total_steps": 61300, "loss": 0.3372, "lr": 4.532536416208487e-05, "epoch": 2.7805872756933114, "percentage": 27.81, "elapsed_time": "2:18:30", "remaining_time": "5:59:38", "throughput": 4428.61, "total_tokens": 36805840} {"current_steps": 17050, "total_steps": 61300, "loss": 0.3209, "lr": 4.532121894048566e-05, "epoch": 2.7814029363784667, "percentage": 27.81, "elapsed_time": "2:18:33", "remaining_time": "5:59:35", "throughput": 4428.7, "total_tokens": 36816368} {"current_steps": 17055, "total_steps": 61300, "loss": 0.304, "lr": 4.531707207154532e-05, "epoch": 2.7822185970636215, "percentage": 27.82, "elapsed_time": "2:18:35", "remaining_time": "5:59:32", "throughput": 4428.83, "total_tokens": 36827920} {"current_steps": 17060, "total_steps": 61300, "loss": 0.3977, "lr": 4.531292355560004e-05, "epoch": 2.7830342577487768, "percentage": 27.83, "elapsed_time": "2:18:37", "remaining_time": "5:59:29", "throughput": 4428.96, "total_tokens": 36839312} {"current_steps": 17065, "total_steps": 61300, "loss": 0.3674, "lr": 4.5308773392986115e-05, "epoch": 2.7838499184339316, "percentage": 27.84, "elapsed_time": "2:18:39", "remaining_time": "5:59:26", "throughput": 4429.05, "total_tokens": 36849264} {"current_steps": 17070, "total_steps": 61300, "loss": 0.3608, "lr": 4.530462158403996e-05, "epoch": 2.7846655791190864, "percentage": 27.85, "elapsed_time": "2:18:42", "remaining_time": "5:59:23", "throughput": 4429.15, "total_tokens": 36859664} {"current_steps": 17075, "total_steps": 61300, "loss": 0.3639, "lr": 4.5300468129098165e-05, "epoch": 2.7854812398042412, "percentage": 27.85, "elapsed_time": "2:18:44", "remaining_time": "5:59:19", "throughput": 4429.25, "total_tokens": 36869776} {"current_steps": 17080, "total_steps": 61300, "loss": 0.3271, "lr": 4.529631302849742e-05, "epoch": 2.7862969004893965, "percentage": 27.86, "elapsed_time": "2:18:46", "remaining_time": "5:59:17", "throughput": 4429.36, "total_tokens": 36880912} {"current_steps": 17085, "total_steps": 61300, "loss": 0.3157, "lr": 4.529215628257455e-05, "epoch": 2.7871125611745513, "percentage": 27.87, "elapsed_time": "2:18:48", "remaining_time": "5:59:13", "throughput": 4429.45, "total_tokens": 36891056} {"current_steps": 17090, "total_steps": 61300, "loss": 0.3489, "lr": 4.528799789166654e-05, "epoch": 2.7879282218597066, "percentage": 27.88, "elapsed_time": "2:18:50", "remaining_time": "5:59:10", "throughput": 4429.57, "total_tokens": 36901456} {"current_steps": 17095, "total_steps": 61300, "loss": 0.3371, "lr": 4.5283837856110474e-05, "epoch": 2.7887438825448614, "percentage": 27.89, "elapsed_time": "2:18:52", "remaining_time": "5:59:07", "throughput": 4429.68, "total_tokens": 36912336} {"current_steps": 17100, "total_steps": 61300, "loss": 0.3662, "lr": 4.5279676176243596e-05, "epoch": 2.789559543230016, "percentage": 27.9, "elapsed_time": "2:18:54", "remaining_time": "5:59:03", "throughput": 4429.77, "total_tokens": 36921456} {"current_steps": 17105, "total_steps": 61300, "loss": 0.3749, "lr": 4.527551285240327e-05, "epoch": 2.790375203915171, "percentage": 27.9, "elapsed_time": "2:18:57", "remaining_time": "5:59:00", "throughput": 4429.88, "total_tokens": 36932272} {"current_steps": 17110, "total_steps": 61300, "loss": 0.3312, "lr": 4.527134788492698e-05, "epoch": 2.7911908646003263, "percentage": 27.91, "elapsed_time": "2:18:59", "remaining_time": "5:58:57", "throughput": 4429.98, "total_tokens": 36942640} {"current_steps": 17115, "total_steps": 61300, "loss": 0.407, "lr": 4.526718127415239e-05, "epoch": 2.792006525285481, "percentage": 27.92, "elapsed_time": "2:19:01", "remaining_time": "5:58:55", "throughput": 4430.11, "total_tokens": 36954192} {"current_steps": 17120, "total_steps": 61300, "loss": 0.3887, "lr": 4.5263013020417254e-05, "epoch": 2.7928221859706364, "percentage": 27.93, "elapsed_time": "2:19:03", "remaining_time": "5:58:52", "throughput": 4430.2, "total_tokens": 36964880} {"current_steps": 17125, "total_steps": 61300, "loss": 0.3428, "lr": 4.5258843124059466e-05, "epoch": 2.793637846655791, "percentage": 27.94, "elapsed_time": "2:19:06", "remaining_time": "5:58:49", "throughput": 4430.29, "total_tokens": 36976112} {"current_steps": 17130, "total_steps": 61300, "loss": 0.3485, "lr": 4.5254671585417056e-05, "epoch": 2.794453507340946, "percentage": 27.94, "elapsed_time": "2:19:08", "remaining_time": "5:58:45", "throughput": 4430.37, "total_tokens": 36985232} {"current_steps": 17135, "total_steps": 61300, "loss": 0.38, "lr": 4.52504984048282e-05, "epoch": 2.7952691680261013, "percentage": 27.95, "elapsed_time": "2:19:10", "remaining_time": "5:58:42", "throughput": 4430.43, "total_tokens": 36995376} {"current_steps": 17140, "total_steps": 61300, "loss": 0.3605, "lr": 4.5246323582631196e-05, "epoch": 2.796084828711256, "percentage": 27.96, "elapsed_time": "2:19:12", "remaining_time": "5:58:40", "throughput": 4430.52, "total_tokens": 37006576} {"current_steps": 17145, "total_steps": 61300, "loss": 0.3461, "lr": 4.524214711916447e-05, "epoch": 2.7969004893964113, "percentage": 27.97, "elapsed_time": "2:19:14", "remaining_time": "5:58:37", "throughput": 4430.61, "total_tokens": 37017264} {"current_steps": 17150, "total_steps": 61300, "loss": 0.3407, "lr": 4.523796901476659e-05, "epoch": 2.797716150081566, "percentage": 27.98, "elapsed_time": "2:19:16", "remaining_time": "5:58:33", "throughput": 4430.73, "total_tokens": 37027472} {"current_steps": 17155, "total_steps": 61300, "loss": 0.3573, "lr": 4.5233789269776264e-05, "epoch": 2.798531810766721, "percentage": 27.99, "elapsed_time": "2:19:19", "remaining_time": "5:58:30", "throughput": 4430.85, "total_tokens": 37038768} {"current_steps": 17160, "total_steps": 61300, "loss": 0.3379, "lr": 4.5229607884532306e-05, "epoch": 2.799347471451876, "percentage": 27.99, "elapsed_time": "2:19:21", "remaining_time": "5:58:28", "throughput": 4430.94, "total_tokens": 37049424} {"current_steps": 17165, "total_steps": 61300, "loss": 0.3727, "lr": 4.522542485937369e-05, "epoch": 2.800163132137031, "percentage": 28.0, "elapsed_time": "2:19:23", "remaining_time": "5:58:25", "throughput": 4431.04, "total_tokens": 37060912} {"current_steps": 17170, "total_steps": 61300, "loss": 0.3699, "lr": 4.5221240194639514e-05, "epoch": 2.800978792822186, "percentage": 28.01, "elapsed_time": "2:19:25", "remaining_time": "5:58:21", "throughput": 4431.12, "total_tokens": 37070032} {"current_steps": 17175, "total_steps": 61300, "loss": 0.3402, "lr": 4.5217053890669004e-05, "epoch": 2.801794453507341, "percentage": 28.02, "elapsed_time": "2:19:27", "remaining_time": "5:58:18", "throughput": 4431.21, "total_tokens": 37079792} {"current_steps": 17180, "total_steps": 61300, "loss": 0.3645, "lr": 4.521286594780152e-05, "epoch": 2.802610114192496, "percentage": 28.03, "elapsed_time": "2:19:30", "remaining_time": "5:58:15", "throughput": 4431.31, "total_tokens": 37091344} {"current_steps": 17185, "total_steps": 61300, "loss": 0.3556, "lr": 4.5208676366376574e-05, "epoch": 2.8034257748776508, "percentage": 28.03, "elapsed_time": "2:19:32", "remaining_time": "5:58:13", "throughput": 4431.43, "total_tokens": 37102800} {"current_steps": 17190, "total_steps": 61300, "loss": 0.3459, "lr": 4.520448514673378e-05, "epoch": 2.804241435562806, "percentage": 28.04, "elapsed_time": "2:19:35", "remaining_time": "5:58:10", "throughput": 4431.56, "total_tokens": 37114512} {"current_steps": 17195, "total_steps": 61300, "loss": 0.3331, "lr": 4.52002922892129e-05, "epoch": 2.805057096247961, "percentage": 28.05, "elapsed_time": "2:19:37", "remaining_time": "5:58:07", "throughput": 4431.65, "total_tokens": 37125232} {"current_steps": 17200, "total_steps": 61300, "loss": 0.3329, "lr": 4.519609779415384e-05, "epoch": 2.8058727569331157, "percentage": 28.06, "elapsed_time": "2:19:39", "remaining_time": "5:58:05", "throughput": 4431.76, "total_tokens": 37136656} {"current_steps": 17205, "total_steps": 61300, "loss": 0.3763, "lr": 4.519190166189661e-05, "epoch": 2.806688417618271, "percentage": 28.07, "elapsed_time": "2:19:42", "remaining_time": "5:58:02", "throughput": 4431.88, "total_tokens": 37148112} {"current_steps": 17210, "total_steps": 61300, "loss": 0.3277, "lr": 4.518770389278138e-05, "epoch": 2.8075040783034257, "percentage": 28.08, "elapsed_time": "2:19:44", "remaining_time": "5:58:00", "throughput": 4432.0, "total_tokens": 37160208} {"current_steps": 17215, "total_steps": 61300, "loss": 0.3183, "lr": 4.5183504487148444e-05, "epoch": 2.8083197389885806, "percentage": 28.08, "elapsed_time": "2:19:46", "remaining_time": "5:57:56", "throughput": 4432.11, "total_tokens": 37170288} {"current_steps": 17220, "total_steps": 61300, "loss": 0.3497, "lr": 4.517930344533822e-05, "epoch": 2.809135399673736, "percentage": 28.09, "elapsed_time": "2:19:48", "remaining_time": "5:57:52", "throughput": 4432.19, "total_tokens": 37179408} {"current_steps": 17225, "total_steps": 61300, "loss": 0.3399, "lr": 4.517510076769128e-05, "epoch": 2.8099510603588906, "percentage": 28.1, "elapsed_time": "2:19:50", "remaining_time": "5:57:50", "throughput": 4432.31, "total_tokens": 37191472} {"current_steps": 17230, "total_steps": 61300, "loss": 0.3739, "lr": 4.517089645454829e-05, "epoch": 2.810766721044046, "percentage": 28.11, "elapsed_time": "2:19:52", "remaining_time": "5:57:46", "throughput": 4432.39, "total_tokens": 37200528} {"current_steps": 17235, "total_steps": 61300, "loss": 0.3316, "lr": 4.51666905062501e-05, "epoch": 2.8115823817292007, "percentage": 28.12, "elapsed_time": "2:19:55", "remaining_time": "5:57:43", "throughput": 4432.48, "total_tokens": 37210960} {"current_steps": 17240, "total_steps": 61300, "loss": 0.3331, "lr": 4.516248292313765e-05, "epoch": 2.8123980424143555, "percentage": 28.12, "elapsed_time": "2:19:57", "remaining_time": "5:57:41", "throughput": 4432.59, "total_tokens": 37222192} {"current_steps": 17245, "total_steps": 61300, "loss": 0.3363, "lr": 4.515827370555202e-05, "epoch": 2.8132137030995104, "percentage": 28.13, "elapsed_time": "2:19:59", "remaining_time": "5:57:38", "throughput": 4432.7, "total_tokens": 37234064} {"current_steps": 17250, "total_steps": 61300, "loss": 0.359, "lr": 4.515406285383446e-05, "epoch": 2.8140293637846656, "percentage": 28.14, "elapsed_time": "2:20:02", "remaining_time": "5:57:36", "throughput": 4432.81, "total_tokens": 37245968} {"current_steps": 17255, "total_steps": 61300, "loss": 0.3676, "lr": 4.514985036832628e-05, "epoch": 2.8148450244698204, "percentage": 28.15, "elapsed_time": "2:20:04", "remaining_time": "5:57:33", "throughput": 4432.92, "total_tokens": 37256432} {"current_steps": 17260, "total_steps": 61300, "loss": 0.3468, "lr": 4.514563624936901e-05, "epoch": 2.8156606851549757, "percentage": 28.16, "elapsed_time": "2:20:06", "remaining_time": "5:57:30", "throughput": 4433.02, "total_tokens": 37267312} {"current_steps": 17265, "total_steps": 61300, "loss": 0.3667, "lr": 4.514142049730424e-05, "epoch": 2.8164763458401305, "percentage": 28.16, "elapsed_time": "2:20:09", "remaining_time": "5:57:27", "throughput": 4433.12, "total_tokens": 37278256} {"current_steps": 17270, "total_steps": 61300, "loss": 0.3601, "lr": 4.513720311247374e-05, "epoch": 2.8172920065252853, "percentage": 28.17, "elapsed_time": "2:20:11", "remaining_time": "5:57:24", "throughput": 4433.25, "total_tokens": 37289968} {"current_steps": 17275, "total_steps": 61300, "loss": 0.3417, "lr": 4.5132984095219364e-05, "epoch": 2.8181076672104406, "percentage": 28.18, "elapsed_time": "2:20:13", "remaining_time": "5:57:22", "throughput": 4433.38, "total_tokens": 37301072} {"current_steps": 17280, "total_steps": 61300, "loss": 0.3431, "lr": 4.512876344588315e-05, "epoch": 2.8189233278955954, "percentage": 28.19, "elapsed_time": "2:20:15", "remaining_time": "5:57:19", "throughput": 4433.47, "total_tokens": 37311664} {"current_steps": 17285, "total_steps": 61300, "loss": 0.3772, "lr": 4.512454116480724e-05, "epoch": 2.8197389885807507, "percentage": 28.2, "elapsed_time": "2:20:18", "remaining_time": "5:57:16", "throughput": 4433.58, "total_tokens": 37323120} {"current_steps": 17290, "total_steps": 61300, "loss": 0.3369, "lr": 4.512031725233391e-05, "epoch": 2.8205546492659055, "percentage": 28.21, "elapsed_time": "2:20:20", "remaining_time": "5:57:13", "throughput": 4433.7, "total_tokens": 37334672} {"current_steps": 17295, "total_steps": 61300, "loss": 0.3205, "lr": 4.5116091708805575e-05, "epoch": 2.8213703099510603, "percentage": 28.21, "elapsed_time": "2:20:23", "remaining_time": "5:57:11", "throughput": 4433.82, "total_tokens": 37346384} {"current_steps": 17300, "total_steps": 61300, "loss": 0.3431, "lr": 4.5111864534564776e-05, "epoch": 2.822185970636215, "percentage": 28.22, "elapsed_time": "2:20:25", "remaining_time": "5:57:09", "throughput": 4433.93, "total_tokens": 37358256} {"current_steps": 17305, "total_steps": 61300, "loss": 0.3349, "lr": 4.510763572995419e-05, "epoch": 2.8230016313213704, "percentage": 28.23, "elapsed_time": "2:20:27", "remaining_time": "5:57:06", "throughput": 4434.04, "total_tokens": 37369968} {"current_steps": 17310, "total_steps": 61300, "loss": 0.3519, "lr": 4.5103405295316634e-05, "epoch": 2.823817292006525, "percentage": 28.24, "elapsed_time": "2:20:30", "remaining_time": "5:57:03", "throughput": 4434.12, "total_tokens": 37380432} {"current_steps": 17315, "total_steps": 61300, "loss": 0.3453, "lr": 4.509917323099504e-05, "epoch": 2.8246329526916805, "percentage": 28.25, "elapsed_time": "2:20:32", "remaining_time": "5:57:00", "throughput": 4434.23, "total_tokens": 37390480} {"current_steps": 17320, "total_steps": 61300, "loss": 0.3711, "lr": 4.5094939537332475e-05, "epoch": 2.8254486133768353, "percentage": 28.25, "elapsed_time": "2:20:34", "remaining_time": "5:56:57", "throughput": 4434.35, "total_tokens": 37402608} {"current_steps": 17325, "total_steps": 61300, "loss": 0.325, "lr": 4.5090704214672155e-05, "epoch": 2.82626427406199, "percentage": 28.26, "elapsed_time": "2:20:37", "remaining_time": "5:56:55", "throughput": 4434.45, "total_tokens": 37413936} {"current_steps": 17330, "total_steps": 61300, "loss": 0.3795, "lr": 4.508646726335741e-05, "epoch": 2.827079934747145, "percentage": 28.27, "elapsed_time": "2:20:39", "remaining_time": "5:56:53", "throughput": 4434.58, "total_tokens": 37426480} {"current_steps": 17335, "total_steps": 61300, "loss": 0.3354, "lr": 4.508222868373171e-05, "epoch": 2.8278955954323, "percentage": 28.28, "elapsed_time": "2:20:42", "remaining_time": "5:56:50", "throughput": 4434.71, "total_tokens": 37438224} {"current_steps": 17340, "total_steps": 61300, "loss": 0.3335, "lr": 4.507798847613866e-05, "epoch": 2.828711256117455, "percentage": 28.29, "elapsed_time": "2:20:44", "remaining_time": "5:56:47", "throughput": 4434.79, "total_tokens": 37448176} {"current_steps": 17345, "total_steps": 61300, "loss": 0.3262, "lr": 4.507374664092199e-05, "epoch": 2.8295269168026103, "percentage": 28.3, "elapsed_time": "2:20:46", "remaining_time": "5:56:44", "throughput": 4434.89, "total_tokens": 37458672} {"current_steps": 17350, "total_steps": 61300, "loss": 0.3504, "lr": 4.506950317842556e-05, "epoch": 2.830342577487765, "percentage": 28.3, "elapsed_time": "2:20:48", "remaining_time": "5:56:41", "throughput": 4435.0, "total_tokens": 37469840} {"current_steps": 17355, "total_steps": 61300, "loss": 0.3374, "lr": 4.506525808899337e-05, "epoch": 2.83115823817292, "percentage": 28.31, "elapsed_time": "2:20:50", "remaining_time": "5:56:38", "throughput": 4435.08, "total_tokens": 37479376} {"current_steps": 17360, "total_steps": 61300, "loss": 0.2937, "lr": 4.506101137296955e-05, "epoch": 2.831973898858075, "percentage": 28.32, "elapsed_time": "2:20:52", "remaining_time": "5:56:34", "throughput": 4435.18, "total_tokens": 37489392} {"current_steps": 17365, "total_steps": 61300, "loss": 0.3812, "lr": 4.505676303069837e-05, "epoch": 2.83278955954323, "percentage": 28.33, "elapsed_time": "2:20:54", "remaining_time": "5:56:31", "throughput": 4435.27, "total_tokens": 37499504} {"current_steps": 17370, "total_steps": 61300, "loss": 0.3054, "lr": 4.5052513062524196e-05, "epoch": 2.8336052202283852, "percentage": 28.34, "elapsed_time": "2:20:57", "remaining_time": "5:56:28", "throughput": 4435.36, "total_tokens": 37510512} {"current_steps": 17375, "total_steps": 61300, "loss": 0.31, "lr": 4.504826146879158e-05, "epoch": 2.83442088091354, "percentage": 28.34, "elapsed_time": "2:20:59", "remaining_time": "5:56:25", "throughput": 4435.46, "total_tokens": 37521424} {"current_steps": 17380, "total_steps": 61300, "loss": 0.3805, "lr": 4.504400824984516e-05, "epoch": 2.835236541598695, "percentage": 28.35, "elapsed_time": "2:21:01", "remaining_time": "5:56:23", "throughput": 4435.56, "total_tokens": 37532976} {"current_steps": 17385, "total_steps": 61300, "loss": 0.3321, "lr": 4.503975340602973e-05, "epoch": 2.8360522022838497, "percentage": 28.36, "elapsed_time": "2:21:03", "remaining_time": "5:56:20", "throughput": 4435.68, "total_tokens": 37543504} {"current_steps": 17390, "total_steps": 61300, "loss": 0.3222, "lr": 4.50354969376902e-05, "epoch": 2.836867862969005, "percentage": 28.37, "elapsed_time": "2:21:06", "remaining_time": "5:56:17", "throughput": 4435.77, "total_tokens": 37554000} {"current_steps": 17395, "total_steps": 61300, "loss": 0.3631, "lr": 4.5031238845171644e-05, "epoch": 2.8376835236541598, "percentage": 28.38, "elapsed_time": "2:21:08", "remaining_time": "5:56:14", "throughput": 4435.88, "total_tokens": 37565360} {"current_steps": 17400, "total_steps": 61300, "loss": 0.3461, "lr": 4.502697912881923e-05, "epoch": 2.838499184339315, "percentage": 28.38, "elapsed_time": "2:21:10", "remaining_time": "5:56:11", "throughput": 4435.99, "total_tokens": 37576368} {"current_steps": 17405, "total_steps": 61300, "loss": 0.3566, "lr": 4.502271778897825e-05, "epoch": 2.83931484502447, "percentage": 28.39, "elapsed_time": "2:21:13", "remaining_time": "5:56:09", "throughput": 4436.1, "total_tokens": 37587664} {"current_steps": 17410, "total_steps": 61300, "loss": 0.3331, "lr": 4.50184548259942e-05, "epoch": 2.8401305057096247, "percentage": 28.4, "elapsed_time": "2:21:15", "remaining_time": "5:56:06", "throughput": 4436.2, "total_tokens": 37598256} {"current_steps": 17415, "total_steps": 61300, "loss": 0.3654, "lr": 4.501419024021261e-05, "epoch": 2.84094616639478, "percentage": 28.41, "elapsed_time": "2:21:17", "remaining_time": "5:56:03", "throughput": 4436.3, "total_tokens": 37608976} {"current_steps": 17420, "total_steps": 61300, "loss": 0.3331, "lr": 4.500992403197921e-05, "epoch": 2.8417618270799347, "percentage": 28.42, "elapsed_time": "2:21:19", "remaining_time": "5:55:59", "throughput": 4436.37, "total_tokens": 37618352} {"current_steps": 17425, "total_steps": 61300, "loss": 0.3391, "lr": 4.500565620163985e-05, "epoch": 2.8425774877650896, "percentage": 28.43, "elapsed_time": "2:21:21", "remaining_time": "5:55:56", "throughput": 4436.48, "total_tokens": 37628816} {"current_steps": 17430, "total_steps": 61300, "loss": 0.3609, "lr": 4.500138674954047e-05, "epoch": 2.843393148450245, "percentage": 28.43, "elapsed_time": "2:21:23", "remaining_time": "5:55:53", "throughput": 4436.57, "total_tokens": 37639824} {"current_steps": 17435, "total_steps": 61300, "loss": 0.3918, "lr": 4.499711567602721e-05, "epoch": 2.8442088091353996, "percentage": 28.44, "elapsed_time": "2:21:26", "remaining_time": "5:55:51", "throughput": 4436.7, "total_tokens": 37651504} {"current_steps": 17440, "total_steps": 61300, "loss": 0.3552, "lr": 4.499284298144629e-05, "epoch": 2.8450244698205545, "percentage": 28.45, "elapsed_time": "2:21:28", "remaining_time": "5:55:48", "throughput": 4436.81, "total_tokens": 37662992} {"current_steps": 17445, "total_steps": 61300, "loss": 0.3309, "lr": 4.498856866614407e-05, "epoch": 2.8458401305057097, "percentage": 28.46, "elapsed_time": "2:21:31", "remaining_time": "5:55:45", "throughput": 4436.92, "total_tokens": 37673904} {"current_steps": 17450, "total_steps": 61300, "loss": 0.3374, "lr": 4.498429273046705e-05, "epoch": 2.8466557911908645, "percentage": 28.47, "elapsed_time": "2:21:33", "remaining_time": "5:55:42", "throughput": 4437.0, "total_tokens": 37684368} {"current_steps": 17455, "total_steps": 61300, "loss": 0.35, "lr": 4.498001517476187e-05, "epoch": 2.84747145187602, "percentage": 28.47, "elapsed_time": "2:21:35", "remaining_time": "5:55:39", "throughput": 4437.12, "total_tokens": 37694480} {"current_steps": 17460, "total_steps": 61300, "loss": 0.3657, "lr": 4.497573599937528e-05, "epoch": 2.8482871125611746, "percentage": 28.48, "elapsed_time": "2:21:37", "remaining_time": "5:55:36", "throughput": 4437.21, "total_tokens": 37705040} {"current_steps": 17465, "total_steps": 61300, "loss": 0.3415, "lr": 4.497145520465417e-05, "epoch": 2.8491027732463294, "percentage": 28.49, "elapsed_time": "2:21:39", "remaining_time": "5:55:33", "throughput": 4437.33, "total_tokens": 37716304} {"current_steps": 17470, "total_steps": 61300, "loss": 0.3395, "lr": 4.4967172790945565e-05, "epoch": 2.8499184339314843, "percentage": 28.5, "elapsed_time": "2:21:41", "remaining_time": "5:55:29", "throughput": 4437.45, "total_tokens": 37726352} {"current_steps": 17475, "total_steps": 61300, "loss": 0.3382, "lr": 4.496288875859663e-05, "epoch": 2.8507340946166395, "percentage": 28.51, "elapsed_time": "2:21:43", "remaining_time": "5:55:26", "throughput": 4437.55, "total_tokens": 37736048} {"current_steps": 17480, "total_steps": 61300, "loss": 0.3499, "lr": 4.4958603107954635e-05, "epoch": 2.8515497553017943, "percentage": 28.52, "elapsed_time": "2:21:46", "remaining_time": "5:55:23", "throughput": 4437.65, "total_tokens": 37746704} {"current_steps": 17485, "total_steps": 61300, "loss": 0.339, "lr": 4.4954315839367006e-05, "epoch": 2.8523654159869496, "percentage": 28.52, "elapsed_time": "2:21:48", "remaining_time": "5:55:20", "throughput": 4437.77, "total_tokens": 37758000} {"current_steps": 17490, "total_steps": 61300, "loss": 0.3388, "lr": 4.495002695318129e-05, "epoch": 2.8531810766721044, "percentage": 28.53, "elapsed_time": "2:21:50", "remaining_time": "5:55:17", "throughput": 4437.86, "total_tokens": 37768240} {"current_steps": 17495, "total_steps": 61300, "loss": 0.358, "lr": 4.494573644974516e-05, "epoch": 2.8539967373572592, "percentage": 28.54, "elapsed_time": "2:21:52", "remaining_time": "5:55:14", "throughput": 4437.95, "total_tokens": 37778576} {"current_steps": 17500, "total_steps": 61300, "loss": 0.3231, "lr": 4.494144432940643e-05, "epoch": 2.8548123980424145, "percentage": 28.55, "elapsed_time": "2:21:54", "remaining_time": "5:55:11", "throughput": 4438.03, "total_tokens": 37788880} {"current_steps": 17505, "total_steps": 61300, "loss": 0.3445, "lr": 4.493715059251304e-05, "epoch": 2.8556280587275693, "percentage": 28.56, "elapsed_time": "2:21:57", "remaining_time": "5:55:08", "throughput": 4438.12, "total_tokens": 37799856} {"current_steps": 17510, "total_steps": 61300, "loss": 0.3651, "lr": 4.4932855239413065e-05, "epoch": 2.8564437194127246, "percentage": 28.56, "elapsed_time": "2:21:59", "remaining_time": "5:55:05", "throughput": 4438.21, "total_tokens": 37809808} {"current_steps": 17515, "total_steps": 61300, "loss": 0.3538, "lr": 4.49285582704547e-05, "epoch": 2.8572593800978794, "percentage": 28.57, "elapsed_time": "2:22:01", "remaining_time": "5:55:01", "throughput": 4438.31, "total_tokens": 37819856} {"current_steps": 17520, "total_steps": 61300, "loss": 0.3858, "lr": 4.492425968598629e-05, "epoch": 2.858075040783034, "percentage": 28.58, "elapsed_time": "2:22:03", "remaining_time": "5:54:59", "throughput": 4438.41, "total_tokens": 37831792} {"current_steps": 17525, "total_steps": 61300, "loss": 0.2995, "lr": 4.49199594863563e-05, "epoch": 2.858890701468189, "percentage": 28.59, "elapsed_time": "2:22:06", "remaining_time": "5:54:57", "throughput": 4438.52, "total_tokens": 37843280} {"current_steps": 17530, "total_steps": 61300, "loss": 0.3683, "lr": 4.4915657671913314e-05, "epoch": 2.8597063621533443, "percentage": 28.6, "elapsed_time": "2:22:08", "remaining_time": "5:54:54", "throughput": 4438.61, "total_tokens": 37854928} {"current_steps": 17535, "total_steps": 61300, "loss": 0.3254, "lr": 4.491135424300607e-05, "epoch": 2.860522022838499, "percentage": 28.61, "elapsed_time": "2:22:10", "remaining_time": "5:54:51", "throughput": 4438.69, "total_tokens": 37865424} {"current_steps": 17540, "total_steps": 61300, "loss": 0.3252, "lr": 4.490704919998342e-05, "epoch": 2.8613376835236544, "percentage": 28.61, "elapsed_time": "2:22:13", "remaining_time": "5:54:48", "throughput": 4438.79, "total_tokens": 37876624} {"current_steps": 17545, "total_steps": 61300, "loss": 0.3242, "lr": 4.4902742543194356e-05, "epoch": 2.862153344208809, "percentage": 28.62, "elapsed_time": "2:22:15", "remaining_time": "5:54:45", "throughput": 4438.87, "total_tokens": 37886896} {"current_steps": 17550, "total_steps": 61300, "loss": 0.3523, "lr": 4.4898434272988e-05, "epoch": 2.862969004893964, "percentage": 28.63, "elapsed_time": "2:22:17", "remaining_time": "5:54:42", "throughput": 4438.96, "total_tokens": 37897424} {"current_steps": 17555, "total_steps": 61300, "loss": 0.3309, "lr": 4.489412438971359e-05, "epoch": 2.863784665579119, "percentage": 28.64, "elapsed_time": "2:22:19", "remaining_time": "5:54:39", "throughput": 4439.07, "total_tokens": 37908080} {"current_steps": 17560, "total_steps": 61300, "loss": 0.3523, "lr": 4.488981289372052e-05, "epoch": 2.864600326264274, "percentage": 28.65, "elapsed_time": "2:22:21", "remaining_time": "5:54:36", "throughput": 4439.18, "total_tokens": 37918768} {"current_steps": 17565, "total_steps": 61300, "loss": 0.3036, "lr": 4.488549978535829e-05, "epoch": 2.865415986949429, "percentage": 28.65, "elapsed_time": "2:22:24", "remaining_time": "5:54:33", "throughput": 4439.26, "total_tokens": 37929488} {"current_steps": 17570, "total_steps": 61300, "loss": 0.3441, "lr": 4.4881185064976553e-05, "epoch": 2.866231647634584, "percentage": 28.66, "elapsed_time": "2:22:26", "remaining_time": "5:54:31", "throughput": 4439.38, "total_tokens": 37940560} {"current_steps": 17575, "total_steps": 61300, "loss": 0.3891, "lr": 4.487686873292508e-05, "epoch": 2.867047308319739, "percentage": 28.67, "elapsed_time": "2:22:28", "remaining_time": "5:54:28", "throughput": 4439.47, "total_tokens": 37951248} {"current_steps": 17580, "total_steps": 61300, "loss": 0.3312, "lr": 4.487255078955378e-05, "epoch": 2.867862969004894, "percentage": 28.68, "elapsed_time": "2:22:30", "remaining_time": "5:54:25", "throughput": 4439.56, "total_tokens": 37961936} {"current_steps": 17585, "total_steps": 61300, "loss": 0.4048, "lr": 4.486823123521267e-05, "epoch": 2.868678629690049, "percentage": 28.69, "elapsed_time": "2:22:33", "remaining_time": "5:54:22", "throughput": 4439.68, "total_tokens": 37972560} {"current_steps": 17590, "total_steps": 61300, "loss": 0.3041, "lr": 4.4863910070251927e-05, "epoch": 2.869494290375204, "percentage": 28.69, "elapsed_time": "2:22:35", "remaining_time": "5:54:19", "throughput": 4439.79, "total_tokens": 37984016} {"current_steps": 17595, "total_steps": 61300, "loss": 0.3584, "lr": 4.485958729502185e-05, "epoch": 2.870309951060359, "percentage": 28.7, "elapsed_time": "2:22:37", "remaining_time": "5:54:16", "throughput": 4439.91, "total_tokens": 37994896} {"current_steps": 17600, "total_steps": 61300, "loss": 0.3239, "lr": 4.485526290987286e-05, "epoch": 2.871125611745514, "percentage": 28.71, "elapsed_time": "2:22:40", "remaining_time": "5:54:14", "throughput": 4440.01, "total_tokens": 38006832} {"current_steps": 17605, "total_steps": 61300, "loss": 0.344, "lr": 4.485093691515551e-05, "epoch": 2.8719412724306688, "percentage": 28.72, "elapsed_time": "2:22:42", "remaining_time": "5:54:11", "throughput": 4440.12, "total_tokens": 38018832} {"current_steps": 17610, "total_steps": 61300, "loss": 0.3585, "lr": 4.4846609311220494e-05, "epoch": 2.8727569331158236, "percentage": 28.73, "elapsed_time": "2:22:44", "remaining_time": "5:54:08", "throughput": 4440.23, "total_tokens": 38029520} {"current_steps": 17615, "total_steps": 61300, "loss": 0.3268, "lr": 4.484228009841863e-05, "epoch": 2.873572593800979, "percentage": 28.74, "elapsed_time": "2:22:46", "remaining_time": "5:54:05", "throughput": 4440.32, "total_tokens": 38039568} {"current_steps": 17620, "total_steps": 61300, "loss": 0.3297, "lr": 4.483794927710085e-05, "epoch": 2.8743882544861337, "percentage": 28.74, "elapsed_time": "2:22:49", "remaining_time": "5:54:03", "throughput": 4440.44, "total_tokens": 38051344} {"current_steps": 17625, "total_steps": 61300, "loss": 0.3406, "lr": 4.483361684761826e-05, "epoch": 2.875203915171289, "percentage": 28.75, "elapsed_time": "2:22:51", "remaining_time": "5:54:00", "throughput": 4440.54, "total_tokens": 38062448} {"current_steps": 17630, "total_steps": 61300, "loss": 0.347, "lr": 4.482928281032205e-05, "epoch": 2.8760195758564437, "percentage": 28.76, "elapsed_time": "2:22:53", "remaining_time": "5:53:57", "throughput": 4440.62, "total_tokens": 38073520} {"current_steps": 17635, "total_steps": 61300, "loss": 0.3378, "lr": 4.482494716556356e-05, "epoch": 2.8768352365415986, "percentage": 28.77, "elapsed_time": "2:22:56", "remaining_time": "5:53:54", "throughput": 4440.72, "total_tokens": 38084400} {"current_steps": 17640, "total_steps": 61300, "loss": 0.3569, "lr": 4.482060991369426e-05, "epoch": 2.877650897226754, "percentage": 28.78, "elapsed_time": "2:22:58", "remaining_time": "5:53:51", "throughput": 4440.82, "total_tokens": 38094288} {"current_steps": 17645, "total_steps": 61300, "loss": 0.3332, "lr": 4.481627105506575e-05, "epoch": 2.8784665579119086, "percentage": 28.78, "elapsed_time": "2:23:00", "remaining_time": "5:53:48", "throughput": 4440.94, "total_tokens": 38104752} {"current_steps": 17650, "total_steps": 61300, "loss": 0.3254, "lr": 4.481193059002976e-05, "epoch": 2.8792822185970635, "percentage": 28.79, "elapsed_time": "2:23:02", "remaining_time": "5:53:44", "throughput": 4441.0, "total_tokens": 38113456} {"current_steps": 17655, "total_steps": 61300, "loss": 0.3527, "lr": 4.480758851893816e-05, "epoch": 2.8800978792822187, "percentage": 28.8, "elapsed_time": "2:23:04", "remaining_time": "5:53:41", "throughput": 4441.12, "total_tokens": 38123888} {"current_steps": 17660, "total_steps": 61300, "loss": 0.3577, "lr": 4.480324484214293e-05, "epoch": 2.8809135399673735, "percentage": 28.81, "elapsed_time": "2:23:06", "remaining_time": "5:53:38", "throughput": 4441.21, "total_tokens": 38134448} {"current_steps": 17665, "total_steps": 61300, "loss": 0.354, "lr": 4.479889955999619e-05, "epoch": 2.8817292006525284, "percentage": 28.82, "elapsed_time": "2:23:08", "remaining_time": "5:53:35", "throughput": 4441.3, "total_tokens": 38145104} {"current_steps": 17670, "total_steps": 61300, "loss": 0.3549, "lr": 4.4794552672850185e-05, "epoch": 2.8825448613376836, "percentage": 28.83, "elapsed_time": "2:23:10", "remaining_time": "5:53:32", "throughput": 4441.4, "total_tokens": 38155984} {"current_steps": 17675, "total_steps": 61300, "loss": 0.3502, "lr": 4.479020418105732e-05, "epoch": 2.8833605220228384, "percentage": 28.83, "elapsed_time": "2:23:13", "remaining_time": "5:53:29", "throughput": 4441.51, "total_tokens": 38167408} {"current_steps": 17680, "total_steps": 61300, "loss": 0.3389, "lr": 4.478585408497008e-05, "epoch": 2.8841761827079937, "percentage": 28.84, "elapsed_time": "2:23:15", "remaining_time": "5:53:26", "throughput": 4441.6, "total_tokens": 38178096} {"current_steps": 17685, "total_steps": 61300, "loss": 0.3703, "lr": 4.478150238494112e-05, "epoch": 2.8849918433931485, "percentage": 28.85, "elapsed_time": "2:23:17", "remaining_time": "5:53:23", "throughput": 4441.69, "total_tokens": 38188304} {"current_steps": 17690, "total_steps": 61300, "loss": 0.325, "lr": 4.47771490813232e-05, "epoch": 2.8858075040783033, "percentage": 28.86, "elapsed_time": "2:23:19", "remaining_time": "5:53:20", "throughput": 4441.78, "total_tokens": 38198512} {"current_steps": 17695, "total_steps": 61300, "loss": 0.3285, "lr": 4.4772794174469234e-05, "epoch": 2.886623164763458, "percentage": 28.87, "elapsed_time": "2:23:22", "remaining_time": "5:53:17", "throughput": 4441.88, "total_tokens": 38209840} {"current_steps": 17700, "total_steps": 61300, "loss": 0.3773, "lr": 4.4768437664732244e-05, "epoch": 2.8874388254486134, "percentage": 28.87, "elapsed_time": "2:23:24", "remaining_time": "5:53:14", "throughput": 4441.96, "total_tokens": 38219760} {"current_steps": 17705, "total_steps": 61300, "loss": 0.3757, "lr": 4.4764079552465385e-05, "epoch": 2.8882544861337682, "percentage": 28.88, "elapsed_time": "2:23:26", "remaining_time": "5:53:12", "throughput": 4442.08, "total_tokens": 38231376} {"current_steps": 17710, "total_steps": 61300, "loss": 0.3462, "lr": 4.475971983802196e-05, "epoch": 2.8890701468189235, "percentage": 28.89, "elapsed_time": "2:23:28", "remaining_time": "5:53:09", "throughput": 4442.18, "total_tokens": 38242096} {"current_steps": 17715, "total_steps": 61300, "loss": 0.3891, "lr": 4.475535852175539e-05, "epoch": 2.8898858075040783, "percentage": 28.9, "elapsed_time": "2:23:31", "remaining_time": "5:53:06", "throughput": 4442.28, "total_tokens": 38252624} {"current_steps": 17720, "total_steps": 61300, "loss": 0.3168, "lr": 4.475099560401922e-05, "epoch": 2.890701468189233, "percentage": 28.91, "elapsed_time": "2:23:33", "remaining_time": "5:53:02", "throughput": 4442.38, "total_tokens": 38262864} {"current_steps": 17725, "total_steps": 61300, "loss": 0.3299, "lr": 4.474663108516713e-05, "epoch": 2.8915171288743884, "percentage": 28.92, "elapsed_time": "2:23:35", "remaining_time": "5:53:00", "throughput": 4442.49, "total_tokens": 38274640} {"current_steps": 17730, "total_steps": 61300, "loss": 0.3518, "lr": 4.474226496555293e-05, "epoch": 2.892332789559543, "percentage": 28.92, "elapsed_time": "2:23:38", "remaining_time": "5:52:58", "throughput": 4442.61, "total_tokens": 38286512} {"current_steps": 17735, "total_steps": 61300, "loss": 0.3245, "lr": 4.473789724553056e-05, "epoch": 2.8931484502446985, "percentage": 28.93, "elapsed_time": "2:23:40", "remaining_time": "5:52:55", "throughput": 4442.68, "total_tokens": 38297456} {"current_steps": 17740, "total_steps": 61300, "loss": 0.3208, "lr": 4.473352792545409e-05, "epoch": 2.8939641109298533, "percentage": 28.94, "elapsed_time": "2:23:42", "remaining_time": "5:52:52", "throughput": 4442.78, "total_tokens": 38308304} {"current_steps": 17745, "total_steps": 61300, "loss": 0.3496, "lr": 4.4729157005677724e-05, "epoch": 2.894779771615008, "percentage": 28.95, "elapsed_time": "2:23:44", "remaining_time": "5:52:49", "throughput": 4442.86, "total_tokens": 38318640} {"current_steps": 17750, "total_steps": 61300, "loss": 0.3401, "lr": 4.472478448655578e-05, "epoch": 2.895595432300163, "percentage": 28.96, "elapsed_time": "2:23:47", "remaining_time": "5:52:47", "throughput": 4442.96, "total_tokens": 38330320} {"current_steps": 17755, "total_steps": 61300, "loss": 0.3691, "lr": 4.4720410368442724e-05, "epoch": 2.896411092985318, "percentage": 28.96, "elapsed_time": "2:23:49", "remaining_time": "5:52:43", "throughput": 4443.06, "total_tokens": 38340432} {"current_steps": 17760, "total_steps": 61300, "loss": 0.2986, "lr": 4.471603465169314e-05, "epoch": 2.897226753670473, "percentage": 28.97, "elapsed_time": "2:23:51", "remaining_time": "5:52:41", "throughput": 4443.16, "total_tokens": 38351760} {"current_steps": 17765, "total_steps": 61300, "loss": 0.3044, "lr": 4.471165733666176e-05, "epoch": 2.8980424143556283, "percentage": 28.98, "elapsed_time": "2:23:53", "remaining_time": "5:52:37", "throughput": 4443.23, "total_tokens": 38361136} {"current_steps": 17770, "total_steps": 61300, "loss": 0.3555, "lr": 4.4707278423703415e-05, "epoch": 2.898858075040783, "percentage": 28.99, "elapsed_time": "2:23:55", "remaining_time": "5:52:34", "throughput": 4443.3, "total_tokens": 38371408} {"current_steps": 17775, "total_steps": 61300, "loss": 0.3661, "lr": 4.470289791317308e-05, "epoch": 2.899673735725938, "percentage": 29.0, "elapsed_time": "2:23:58", "remaining_time": "5:52:32", "throughput": 4443.41, "total_tokens": 38383056} {"current_steps": 17780, "total_steps": 61300, "loss": 0.3532, "lr": 4.4698515805425876e-05, "epoch": 2.9004893964110927, "percentage": 29.0, "elapsed_time": "2:24:00", "remaining_time": "5:52:29", "throughput": 4443.51, "total_tokens": 38393840} {"current_steps": 17785, "total_steps": 61300, "loss": 0.3979, "lr": 4.469413210081703e-05, "epoch": 2.901305057096248, "percentage": 29.01, "elapsed_time": "2:24:02", "remaining_time": "5:52:26", "throughput": 4443.62, "total_tokens": 38406096} {"current_steps": 17790, "total_steps": 61300, "loss": 0.3458, "lr": 4.468974679970191e-05, "epoch": 2.902120717781403, "percentage": 29.02, "elapsed_time": "2:24:05", "remaining_time": "5:52:24", "throughput": 4443.72, "total_tokens": 38416912} {"current_steps": 17795, "total_steps": 61300, "loss": 0.3347, "lr": 4.468535990243601e-05, "epoch": 2.902936378466558, "percentage": 29.03, "elapsed_time": "2:24:07", "remaining_time": "5:52:21", "throughput": 4443.83, "total_tokens": 38428016} {"current_steps": 17800, "total_steps": 61300, "loss": 0.3373, "lr": 4.468097140937495e-05, "epoch": 2.903752039151713, "percentage": 29.04, "elapsed_time": "2:24:09", "remaining_time": "5:52:18", "throughput": 4443.89, "total_tokens": 38438480} {"current_steps": 17805, "total_steps": 61300, "loss": 0.3554, "lr": 4.467658132087449e-05, "epoch": 2.9045676998368677, "percentage": 29.05, "elapsed_time": "2:24:11", "remaining_time": "5:52:14", "throughput": 4443.98, "total_tokens": 38448112} {"current_steps": 17810, "total_steps": 61300, "loss": 0.3511, "lr": 4.4672189637290505e-05, "epoch": 2.905383360522023, "percentage": 29.05, "elapsed_time": "2:24:13", "remaining_time": "5:52:11", "throughput": 4444.07, "total_tokens": 38457872} {"current_steps": 17815, "total_steps": 61300, "loss": 0.3467, "lr": 4.466779635897902e-05, "epoch": 2.9061990212071778, "percentage": 29.06, "elapsed_time": "2:24:16", "remaining_time": "5:52:08", "throughput": 4444.18, "total_tokens": 38469040} {"current_steps": 17820, "total_steps": 61300, "loss": 0.3591, "lr": 4.466340148629617e-05, "epoch": 2.907014681892333, "percentage": 29.07, "elapsed_time": "2:24:18", "remaining_time": "5:52:05", "throughput": 4444.27, "total_tokens": 38479344} {"current_steps": 17825, "total_steps": 61300, "loss": 0.3621, "lr": 4.465900501959822e-05, "epoch": 2.907830342577488, "percentage": 29.08, "elapsed_time": "2:24:20", "remaining_time": "5:52:02", "throughput": 4444.37, "total_tokens": 38489552} {"current_steps": 17830, "total_steps": 61300, "loss": 0.3698, "lr": 4.465460695924157e-05, "epoch": 2.9086460032626427, "percentage": 29.09, "elapsed_time": "2:24:22", "remaining_time": "5:51:59", "throughput": 4444.49, "total_tokens": 38500752} {"current_steps": 17835, "total_steps": 61300, "loss": 0.3133, "lr": 4.4650207305582756e-05, "epoch": 2.9094616639477975, "percentage": 29.09, "elapsed_time": "2:24:24", "remaining_time": "5:51:57", "throughput": 4444.62, "total_tokens": 38512432} {"current_steps": 17840, "total_steps": 61300, "loss": 0.3379, "lr": 4.464580605897844e-05, "epoch": 2.9102773246329527, "percentage": 29.1, "elapsed_time": "2:24:26", "remaining_time": "5:51:53", "throughput": 4444.71, "total_tokens": 38522256} {"current_steps": 17845, "total_steps": 61300, "loss": 0.3417, "lr": 4.4641403219785396e-05, "epoch": 2.9110929853181076, "percentage": 29.11, "elapsed_time": "2:24:29", "remaining_time": "5:51:50", "throughput": 4444.81, "total_tokens": 38532784} {"current_steps": 17850, "total_steps": 61300, "loss": 0.3031, "lr": 4.463699878836055e-05, "epoch": 2.911908646003263, "percentage": 29.12, "elapsed_time": "2:24:31", "remaining_time": "5:51:47", "throughput": 4444.89, "total_tokens": 38542640} {"current_steps": 17855, "total_steps": 61300, "loss": 0.3348, "lr": 4.463259276506095e-05, "epoch": 2.9127243066884176, "percentage": 29.13, "elapsed_time": "2:24:33", "remaining_time": "5:51:44", "throughput": 4444.99, "total_tokens": 38553008} {"current_steps": 17860, "total_steps": 61300, "loss": 0.3267, "lr": 4.462818515024376e-05, "epoch": 2.9135399673735725, "percentage": 29.14, "elapsed_time": "2:24:35", "remaining_time": "5:51:41", "throughput": 4445.11, "total_tokens": 38565200} {"current_steps": 17865, "total_steps": 61300, "loss": 0.3481, "lr": 4.462377594426629e-05, "epoch": 2.9143556280587277, "percentage": 29.14, "elapsed_time": "2:24:37", "remaining_time": "5:51:38", "throughput": 4445.2, "total_tokens": 38574736} {"current_steps": 17870, "total_steps": 61300, "loss": 0.3865, "lr": 4.461936514748597e-05, "epoch": 2.9151712887438825, "percentage": 29.15, "elapsed_time": "2:24:39", "remaining_time": "5:51:34", "throughput": 4445.29, "total_tokens": 38584496} {"current_steps": 17875, "total_steps": 61300, "loss": 0.3081, "lr": 4.4614952760260366e-05, "epoch": 2.9159869494290374, "percentage": 29.16, "elapsed_time": "2:24:41", "remaining_time": "5:51:31", "throughput": 4445.37, "total_tokens": 38594448} {"current_steps": 17880, "total_steps": 61300, "loss": 0.3542, "lr": 4.4610538782947166e-05, "epoch": 2.9168026101141926, "percentage": 29.17, "elapsed_time": "2:24:44", "remaining_time": "5:51:28", "throughput": 4445.46, "total_tokens": 38604976} {"current_steps": 17885, "total_steps": 61300, "loss": 0.2996, "lr": 4.460612321590419e-05, "epoch": 2.9176182707993474, "percentage": 29.18, "elapsed_time": "2:24:46", "remaining_time": "5:51:25", "throughput": 4445.55, "total_tokens": 38615792} {"current_steps": 17890, "total_steps": 61300, "loss": 0.3859, "lr": 4.460170605948939e-05, "epoch": 2.9184339314845023, "percentage": 29.18, "elapsed_time": "2:24:48", "remaining_time": "5:51:22", "throughput": 4445.64, "total_tokens": 38626320} {"current_steps": 17895, "total_steps": 61300, "loss": 0.3424, "lr": 4.459728731406083e-05, "epoch": 2.9192495921696575, "percentage": 29.19, "elapsed_time": "2:24:50", "remaining_time": "5:51:19", "throughput": 4445.74, "total_tokens": 38637008} {"current_steps": 17900, "total_steps": 61300, "loss": 0.3835, "lr": 4.4592866979976725e-05, "epoch": 2.9200652528548123, "percentage": 29.2, "elapsed_time": "2:24:52", "remaining_time": "5:51:16", "throughput": 4445.82, "total_tokens": 38647056} {"current_steps": 17905, "total_steps": 61300, "loss": 0.359, "lr": 4.458844505759542e-05, "epoch": 2.9208809135399676, "percentage": 29.21, "elapsed_time": "2:24:55", "remaining_time": "5:51:14", "throughput": 4445.93, "total_tokens": 38658512} {"current_steps": 17910, "total_steps": 61300, "loss": 0.3678, "lr": 4.4584021547275356e-05, "epoch": 2.9216965742251224, "percentage": 29.22, "elapsed_time": "2:24:57", "remaining_time": "5:51:11", "throughput": 4446.03, "total_tokens": 38669328} {"current_steps": 17915, "total_steps": 61300, "loss": 0.3586, "lr": 4.457959644937514e-05, "epoch": 2.9225122349102772, "percentage": 29.23, "elapsed_time": "2:24:59", "remaining_time": "5:51:08", "throughput": 4446.14, "total_tokens": 38680048} {"current_steps": 17920, "total_steps": 61300, "loss": 0.3353, "lr": 4.457516976425349e-05, "epoch": 2.923327895595432, "percentage": 29.23, "elapsed_time": "2:25:02", "remaining_time": "5:51:05", "throughput": 4446.25, "total_tokens": 38691952} {"current_steps": 17925, "total_steps": 61300, "loss": 0.3475, "lr": 4.457074149226926e-05, "epoch": 2.9241435562805873, "percentage": 29.24, "elapsed_time": "2:25:04", "remaining_time": "5:51:02", "throughput": 4446.31, "total_tokens": 38701872} {"current_steps": 17930, "total_steps": 61300, "loss": 0.3388, "lr": 4.456631163378142e-05, "epoch": 2.924959216965742, "percentage": 29.25, "elapsed_time": "2:25:06", "remaining_time": "5:50:59", "throughput": 4446.41, "total_tokens": 38713104} {"current_steps": 17935, "total_steps": 61300, "loss": 0.3186, "lr": 4.456188018914908e-05, "epoch": 2.9257748776508974, "percentage": 29.26, "elapsed_time": "2:25:08", "remaining_time": "5:50:57", "throughput": 4446.5, "total_tokens": 38723952} {"current_steps": 17940, "total_steps": 61300, "loss": 0.3665, "lr": 4.455744715873148e-05, "epoch": 2.926590538336052, "percentage": 29.27, "elapsed_time": "2:25:11", "remaining_time": "5:50:54", "throughput": 4446.61, "total_tokens": 38735216} {"current_steps": 17945, "total_steps": 61300, "loss": 0.3264, "lr": 4.455301254288797e-05, "epoch": 2.927406199021207, "percentage": 29.27, "elapsed_time": "2:25:13", "remaining_time": "5:50:51", "throughput": 4446.71, "total_tokens": 38746032} {"current_steps": 17950, "total_steps": 61300, "loss": 0.3288, "lr": 4.454857634197806e-05, "epoch": 2.9282218597063623, "percentage": 29.28, "elapsed_time": "2:25:15", "remaining_time": "5:50:48", "throughput": 4446.8, "total_tokens": 38756464} {"current_steps": 17955, "total_steps": 61300, "loss": 0.3607, "lr": 4.4544138556361364e-05, "epoch": 2.929037520391517, "percentage": 29.29, "elapsed_time": "2:25:17", "remaining_time": "5:50:45", "throughput": 4446.9, "total_tokens": 38767952} {"current_steps": 17960, "total_steps": 61300, "loss": 0.3525, "lr": 4.453969918639763e-05, "epoch": 2.9298531810766724, "percentage": 29.3, "elapsed_time": "2:25:20", "remaining_time": "5:50:43", "throughput": 4446.98, "total_tokens": 38779312} {"current_steps": 17965, "total_steps": 61300, "loss": 0.3783, "lr": 4.453525823244673e-05, "epoch": 2.930668841761827, "percentage": 29.31, "elapsed_time": "2:25:22", "remaining_time": "5:50:40", "throughput": 4447.06, "total_tokens": 38790576} {"current_steps": 17970, "total_steps": 61300, "loss": 0.3478, "lr": 4.453081569486869e-05, "epoch": 2.931484502446982, "percentage": 29.31, "elapsed_time": "2:25:25", "remaining_time": "5:50:38", "throughput": 4447.15, "total_tokens": 38802032} {"current_steps": 17975, "total_steps": 61300, "loss": 0.3484, "lr": 4.452637157402362e-05, "epoch": 2.932300163132137, "percentage": 29.32, "elapsed_time": "2:25:27", "remaining_time": "5:50:35", "throughput": 4447.26, "total_tokens": 38812080} {"current_steps": 17980, "total_steps": 61300, "loss": 0.3458, "lr": 4.45219258702718e-05, "epoch": 2.933115823817292, "percentage": 29.33, "elapsed_time": "2:25:29", "remaining_time": "5:50:32", "throughput": 4447.37, "total_tokens": 38823664} {"current_steps": 17985, "total_steps": 61300, "loss": 0.3315, "lr": 4.451747858397361e-05, "epoch": 2.933931484502447, "percentage": 29.34, "elapsed_time": "2:25:31", "remaining_time": "5:50:29", "throughput": 4447.45, "total_tokens": 38833840} {"current_steps": 17990, "total_steps": 61300, "loss": 0.3389, "lr": 4.451302971548958e-05, "epoch": 2.934747145187602, "percentage": 29.35, "elapsed_time": "2:25:33", "remaining_time": "5:50:26", "throughput": 4447.54, "total_tokens": 38844400} {"current_steps": 17995, "total_steps": 61300, "loss": 0.3301, "lr": 4.450857926518035e-05, "epoch": 2.935562805872757, "percentage": 29.36, "elapsed_time": "2:25:36", "remaining_time": "5:50:23", "throughput": 4447.64, "total_tokens": 38855248} {"current_steps": 18000, "total_steps": 61300, "loss": 0.317, "lr": 4.45041272334067e-05, "epoch": 2.936378466557912, "percentage": 29.36, "elapsed_time": "2:25:38", "remaining_time": "5:50:21", "throughput": 4447.74, "total_tokens": 38867472} {"current_steps": 18005, "total_steps": 61300, "loss": 0.348, "lr": 4.449967362052954e-05, "epoch": 2.9371941272430666, "percentage": 29.37, "elapsed_time": "2:25:41", "remaining_time": "5:50:18", "throughput": 4447.85, "total_tokens": 38878864} {"current_steps": 18010, "total_steps": 61300, "loss": 0.3513, "lr": 4.449521842690989e-05, "epoch": 2.938009787928222, "percentage": 29.38, "elapsed_time": "2:25:43", "remaining_time": "5:50:16", "throughput": 4447.93, "total_tokens": 38890032} {"current_steps": 18015, "total_steps": 61300, "loss": 0.2843, "lr": 4.449076165290892e-05, "epoch": 2.9388254486133767, "percentage": 29.39, "elapsed_time": "2:25:45", "remaining_time": "5:50:13", "throughput": 4448.01, "total_tokens": 38900624} {"current_steps": 18020, "total_steps": 61300, "loss": 0.3541, "lr": 4.448630329888791e-05, "epoch": 2.939641109298532, "percentage": 29.4, "elapsed_time": "2:25:47", "remaining_time": "5:50:10", "throughput": 4448.11, "total_tokens": 38911984} {"current_steps": 18025, "total_steps": 61300, "loss": 0.3261, "lr": 4.448184336520829e-05, "epoch": 2.9404567699836868, "percentage": 29.4, "elapsed_time": "2:25:50", "remaining_time": "5:50:07", "throughput": 4448.2, "total_tokens": 38922896} {"current_steps": 18030, "total_steps": 61300, "loss": 0.2999, "lr": 4.447738185223158e-05, "epoch": 2.9412724306688416, "percentage": 29.41, "elapsed_time": "2:25:52", "remaining_time": "5:50:05", "throughput": 4448.27, "total_tokens": 38933872} {"current_steps": 18035, "total_steps": 61300, "loss": 0.3271, "lr": 4.447291876031949e-05, "epoch": 2.942088091353997, "percentage": 29.42, "elapsed_time": "2:25:54", "remaining_time": "5:50:01", "throughput": 4448.35, "total_tokens": 38943088} {"current_steps": 18040, "total_steps": 61300, "loss": 0.3328, "lr": 4.446845408983379e-05, "epoch": 2.9429037520391517, "percentage": 29.43, "elapsed_time": "2:25:56", "remaining_time": "5:49:58", "throughput": 4448.44, "total_tokens": 38954064} {"current_steps": 18045, "total_steps": 61300, "loss": 0.3417, "lr": 4.446398784113642e-05, "epoch": 2.943719412724307, "percentage": 29.44, "elapsed_time": "2:25:59", "remaining_time": "5:49:56", "throughput": 4448.55, "total_tokens": 38965904} {"current_steps": 18050, "total_steps": 61300, "loss": 0.3539, "lr": 4.445952001458944e-05, "epoch": 2.9445350734094617, "percentage": 29.45, "elapsed_time": "2:26:01", "remaining_time": "5:49:53", "throughput": 4448.63, "total_tokens": 38976080} {"current_steps": 18055, "total_steps": 61300, "loss": 0.304, "lr": 4.445505061055503e-05, "epoch": 2.9453507340946166, "percentage": 29.45, "elapsed_time": "2:26:03", "remaining_time": "5:49:50", "throughput": 4448.73, "total_tokens": 38987344} {"current_steps": 18060, "total_steps": 61300, "loss": 0.3525, "lr": 4.44505796293955e-05, "epoch": 2.9461663947797714, "percentage": 29.46, "elapsed_time": "2:26:06", "remaining_time": "5:49:48", "throughput": 4448.84, "total_tokens": 38999472} {"current_steps": 18065, "total_steps": 61300, "loss": 0.3395, "lr": 4.44461070714733e-05, "epoch": 2.9469820554649266, "percentage": 29.47, "elapsed_time": "2:26:08", "remaining_time": "5:49:45", "throughput": 4448.95, "total_tokens": 39010352} {"current_steps": 18070, "total_steps": 61300, "loss": 0.363, "lr": 4.4441632937150984e-05, "epoch": 2.9477977161500815, "percentage": 29.48, "elapsed_time": "2:26:10", "remaining_time": "5:49:42", "throughput": 4449.04, "total_tokens": 39020816} {"current_steps": 18075, "total_steps": 61300, "loss": 0.3562, "lr": 4.443715722679126e-05, "epoch": 2.9486133768352367, "percentage": 29.49, "elapsed_time": "2:26:12", "remaining_time": "5:49:39", "throughput": 4449.13, "total_tokens": 39032112} {"current_steps": 18080, "total_steps": 61300, "loss": 0.3333, "lr": 4.443267994075695e-05, "epoch": 2.9494290375203915, "percentage": 29.49, "elapsed_time": "2:26:15", "remaining_time": "5:49:37", "throughput": 4449.21, "total_tokens": 39043536} {"current_steps": 18085, "total_steps": 61300, "loss": 0.3512, "lr": 4.4428201079411004e-05, "epoch": 2.9502446982055464, "percentage": 29.5, "elapsed_time": "2:26:17", "remaining_time": "5:49:34", "throughput": 4449.3, "total_tokens": 39053232} {"current_steps": 18090, "total_steps": 61300, "loss": 0.3339, "lr": 4.4423720643116495e-05, "epoch": 2.9510603588907016, "percentage": 29.51, "elapsed_time": "2:26:19", "remaining_time": "5:49:31", "throughput": 4449.39, "total_tokens": 39064368} {"current_steps": 18095, "total_steps": 61300, "loss": 0.3446, "lr": 4.441923863223664e-05, "epoch": 2.9518760195758564, "percentage": 29.52, "elapsed_time": "2:26:21", "remaining_time": "5:49:27", "throughput": 4449.45, "total_tokens": 39072560} {"current_steps": 18100, "total_steps": 61300, "loss": 0.3554, "lr": 4.441475504713477e-05, "epoch": 2.9526916802610113, "percentage": 29.53, "elapsed_time": "2:26:23", "remaining_time": "5:49:24", "throughput": 4449.56, "total_tokens": 39084080} {"current_steps": 18105, "total_steps": 61300, "loss": 0.3242, "lr": 4.4410269888174346e-05, "epoch": 2.9535073409461665, "percentage": 29.54, "elapsed_time": "2:26:26", "remaining_time": "5:49:21", "throughput": 4449.65, "total_tokens": 39095056} {"current_steps": 18110, "total_steps": 61300, "loss": 0.3393, "lr": 4.440578315571896e-05, "epoch": 2.9543230016313213, "percentage": 29.54, "elapsed_time": "2:26:28", "remaining_time": "5:49:19", "throughput": 4449.74, "total_tokens": 39106000} {"current_steps": 18115, "total_steps": 61300, "loss": 0.3358, "lr": 4.4401294850132324e-05, "epoch": 2.955138662316476, "percentage": 29.55, "elapsed_time": "2:26:30", "remaining_time": "5:49:15", "throughput": 4449.81, "total_tokens": 39115760} {"current_steps": 18120, "total_steps": 61300, "loss": 0.3543, "lr": 4.439680497177829e-05, "epoch": 2.9559543230016314, "percentage": 29.56, "elapsed_time": "2:26:32", "remaining_time": "5:49:12", "throughput": 4449.91, "total_tokens": 39126160} {"current_steps": 18125, "total_steps": 61300, "loss": 0.3781, "lr": 4.439231352102082e-05, "epoch": 2.9567699836867862, "percentage": 29.57, "elapsed_time": "2:26:34", "remaining_time": "5:49:09", "throughput": 4450.02, "total_tokens": 39137264} {"current_steps": 18130, "total_steps": 61300, "loss": 0.3494, "lr": 4.438782049822403e-05, "epoch": 2.9575856443719415, "percentage": 29.58, "elapsed_time": "2:26:37", "remaining_time": "5:49:07", "throughput": 4450.09, "total_tokens": 39147824} {"current_steps": 18135, "total_steps": 61300, "loss": 0.337, "lr": 4.4383325903752124e-05, "epoch": 2.9584013050570963, "percentage": 29.58, "elapsed_time": "2:26:39", "remaining_time": "5:49:04", "throughput": 4450.2, "total_tokens": 39158768} {"current_steps": 18140, "total_steps": 61300, "loss": 0.3348, "lr": 4.437882973796948e-05, "epoch": 2.959216965742251, "percentage": 29.59, "elapsed_time": "2:26:41", "remaining_time": "5:49:00", "throughput": 4450.29, "total_tokens": 39168752} {"current_steps": 18145, "total_steps": 61300, "loss": 0.2957, "lr": 4.437433200124057e-05, "epoch": 2.960032626427406, "percentage": 29.6, "elapsed_time": "2:26:43", "remaining_time": "5:48:58", "throughput": 4450.41, "total_tokens": 39180528} {"current_steps": 18150, "total_steps": 61300, "loss": 0.3453, "lr": 4.4369832693930005e-05, "epoch": 2.960848287112561, "percentage": 29.61, "elapsed_time": "2:26:46", "remaining_time": "5:48:56", "throughput": 4450.51, "total_tokens": 39192336} {"current_steps": 18155, "total_steps": 61300, "loss": 0.3651, "lr": 4.436533181640252e-05, "epoch": 2.961663947797716, "percentage": 29.62, "elapsed_time": "2:26:48", "remaining_time": "5:48:53", "throughput": 4450.59, "total_tokens": 39203056} {"current_steps": 18160, "total_steps": 61300, "loss": 0.3791, "lr": 4.436082936902297e-05, "epoch": 2.9624796084828713, "percentage": 29.62, "elapsed_time": "2:26:50", "remaining_time": "5:48:50", "throughput": 4450.66, "total_tokens": 39213104} {"current_steps": 18165, "total_steps": 61300, "loss": 0.3423, "lr": 4.435632535215637e-05, "epoch": 2.963295269168026, "percentage": 29.63, "elapsed_time": "2:26:52", "remaining_time": "5:48:47", "throughput": 4450.75, "total_tokens": 39223792} {"current_steps": 18170, "total_steps": 61300, "loss": 0.3207, "lr": 4.435181976616781e-05, "epoch": 2.964110929853181, "percentage": 29.64, "elapsed_time": "2:26:55", "remaining_time": "5:48:44", "throughput": 4450.87, "total_tokens": 39235248} {"current_steps": 18175, "total_steps": 61300, "loss": 0.3409, "lr": 4.4347312611422555e-05, "epoch": 2.964926590538336, "percentage": 29.65, "elapsed_time": "2:26:57", "remaining_time": "5:48:41", "throughput": 4450.94, "total_tokens": 39245424} {"current_steps": 18180, "total_steps": 61300, "loss": 0.3463, "lr": 4.434280388828598e-05, "epoch": 2.965742251223491, "percentage": 29.66, "elapsed_time": "2:26:59", "remaining_time": "5:48:38", "throughput": 4451.01, "total_tokens": 39255344} {"current_steps": 18185, "total_steps": 61300, "loss": 0.3196, "lr": 4.433829359712356e-05, "epoch": 2.9665579119086463, "percentage": 29.67, "elapsed_time": "2:27:01", "remaining_time": "5:48:35", "throughput": 4451.1, "total_tokens": 39266192} {"current_steps": 18190, "total_steps": 61300, "loss": 0.3715, "lr": 4.4333781738300954e-05, "epoch": 2.967373572593801, "percentage": 29.67, "elapsed_time": "2:27:03", "remaining_time": "5:48:32", "throughput": 4451.2, "total_tokens": 39277040} {"current_steps": 18195, "total_steps": 61300, "loss": 0.3376, "lr": 4.43292683121839e-05, "epoch": 2.968189233278956, "percentage": 29.68, "elapsed_time": "2:27:05", "remaining_time": "5:48:28", "throughput": 4451.27, "total_tokens": 39286160} {"current_steps": 18200, "total_steps": 61300, "loss": 0.3361, "lr": 4.432475331913828e-05, "epoch": 2.9690048939641107, "percentage": 29.69, "elapsed_time": "2:27:08", "remaining_time": "5:48:25", "throughput": 4451.34, "total_tokens": 39296496} {"current_steps": 18205, "total_steps": 61300, "loss": 0.3159, "lr": 4.4320236759530095e-05, "epoch": 2.969820554649266, "percentage": 29.7, "elapsed_time": "2:27:10", "remaining_time": "5:48:22", "throughput": 4451.42, "total_tokens": 39306672} {"current_steps": 18210, "total_steps": 61300, "loss": 0.3403, "lr": 4.43157186337255e-05, "epoch": 2.970636215334421, "percentage": 29.71, "elapsed_time": "2:27:12", "remaining_time": "5:48:19", "throughput": 4451.53, "total_tokens": 39316816} {"current_steps": 18215, "total_steps": 61300, "loss": 0.3468, "lr": 4.431119894209074e-05, "epoch": 2.971451876019576, "percentage": 29.71, "elapsed_time": "2:27:14", "remaining_time": "5:48:16", "throughput": 4451.64, "total_tokens": 39327984} {"current_steps": 18220, "total_steps": 61300, "loss": 0.373, "lr": 4.430667768499221e-05, "epoch": 2.972267536704731, "percentage": 29.72, "elapsed_time": "2:27:16", "remaining_time": "5:48:13", "throughput": 4451.74, "total_tokens": 39338832} {"current_steps": 18225, "total_steps": 61300, "loss": 0.3237, "lr": 4.4302154862796425e-05, "epoch": 2.9730831973898857, "percentage": 29.73, "elapsed_time": "2:27:18", "remaining_time": "5:48:10", "throughput": 4451.84, "total_tokens": 39349104} {"current_steps": 18230, "total_steps": 61300, "loss": 0.3616, "lr": 4.4297630475870025e-05, "epoch": 2.9738988580750405, "percentage": 29.74, "elapsed_time": "2:27:20", "remaining_time": "5:48:07", "throughput": 4451.9, "total_tokens": 39358640} {"current_steps": 18235, "total_steps": 61300, "loss": 0.3937, "lr": 4.429310452457979e-05, "epoch": 2.9747145187601958, "percentage": 29.75, "elapsed_time": "2:27:22", "remaining_time": "5:48:04", "throughput": 4451.99, "total_tokens": 39368688} {"current_steps": 18240, "total_steps": 61300, "loss": 0.3435, "lr": 4.428857700929261e-05, "epoch": 2.9755301794453506, "percentage": 29.76, "elapsed_time": "2:27:24", "remaining_time": "5:48:00", "throughput": 4452.06, "total_tokens": 39378224} {"current_steps": 18245, "total_steps": 61300, "loss": 0.3156, "lr": 4.428404793037551e-05, "epoch": 2.976345840130506, "percentage": 29.76, "elapsed_time": "2:27:27", "remaining_time": "5:47:57", "throughput": 4452.16, "total_tokens": 39388368} {"current_steps": 18250, "total_steps": 61300, "loss": 0.3255, "lr": 4.427951728819564e-05, "epoch": 2.9771615008156607, "percentage": 29.77, "elapsed_time": "2:27:29", "remaining_time": "5:47:54", "throughput": 4452.25, "total_tokens": 39399120} {"current_steps": 18255, "total_steps": 61300, "loss": 0.3582, "lr": 4.427498508312026e-05, "epoch": 2.9779771615008155, "percentage": 29.78, "elapsed_time": "2:27:31", "remaining_time": "5:47:51", "throughput": 4452.32, "total_tokens": 39408560} {"current_steps": 18260, "total_steps": 61300, "loss": 0.3322, "lr": 4.4270451315516807e-05, "epoch": 2.9787928221859707, "percentage": 29.79, "elapsed_time": "2:27:33", "remaining_time": "5:47:48", "throughput": 4452.41, "total_tokens": 39419664} {"current_steps": 18265, "total_steps": 61300, "loss": 0.3072, "lr": 4.426591598575278e-05, "epoch": 2.9796084828711256, "percentage": 29.8, "elapsed_time": "2:27:35", "remaining_time": "5:47:45", "throughput": 4452.49, "total_tokens": 39430480} {"current_steps": 18270, "total_steps": 61300, "loss": 0.4119, "lr": 4.4261379094195856e-05, "epoch": 2.980424143556281, "percentage": 29.8, "elapsed_time": "2:27:38", "remaining_time": "5:47:42", "throughput": 4452.57, "total_tokens": 39441008} {"current_steps": 18275, "total_steps": 61300, "loss": 0.3166, "lr": 4.425684064121381e-05, "epoch": 2.9812398042414356, "percentage": 29.81, "elapsed_time": "2:27:40", "remaining_time": "5:47:39", "throughput": 4452.67, "total_tokens": 39451984} {"current_steps": 18280, "total_steps": 61300, "loss": 0.3455, "lr": 4.425230062717455e-05, "epoch": 2.9820554649265905, "percentage": 29.82, "elapsed_time": "2:27:42", "remaining_time": "5:47:36", "throughput": 4452.75, "total_tokens": 39461904} {"current_steps": 18285, "total_steps": 61300, "loss": 0.3436, "lr": 4.424775905244612e-05, "epoch": 2.9828711256117453, "percentage": 29.83, "elapsed_time": "2:27:44", "remaining_time": "5:47:33", "throughput": 4452.86, "total_tokens": 39472656} {"current_steps": 18290, "total_steps": 61300, "loss": 0.3527, "lr": 4.424321591739668e-05, "epoch": 2.9836867862969005, "percentage": 29.84, "elapsed_time": "2:27:46", "remaining_time": "5:47:30", "throughput": 4452.95, "total_tokens": 39483376} {"current_steps": 18295, "total_steps": 61300, "loss": 0.3201, "lr": 4.423867122239451e-05, "epoch": 2.9845024469820554, "percentage": 29.85, "elapsed_time": "2:27:49", "remaining_time": "5:47:28", "throughput": 4453.04, "total_tokens": 39496144} {"current_steps": 18300, "total_steps": 61300, "loss": 0.3599, "lr": 4.4234124967808044e-05, "epoch": 2.9853181076672106, "percentage": 29.85, "elapsed_time": "2:27:51", "remaining_time": "5:47:25", "throughput": 4453.14, "total_tokens": 39506128} {"current_steps": 18305, "total_steps": 61300, "loss": 0.3939, "lr": 4.4229577154005814e-05, "epoch": 2.9861337683523654, "percentage": 29.86, "elapsed_time": "2:27:53", "remaining_time": "5:47:21", "throughput": 4453.24, "total_tokens": 39515440} {"current_steps": 18310, "total_steps": 61300, "loss": 0.3437, "lr": 4.4225027781356484e-05, "epoch": 2.9869494290375203, "percentage": 29.87, "elapsed_time": "2:27:55", "remaining_time": "5:47:19", "throughput": 4453.34, "total_tokens": 39526512} {"current_steps": 18315, "total_steps": 61300, "loss": 0.3524, "lr": 4.4220476850228866e-05, "epoch": 2.9877650897226755, "percentage": 29.88, "elapsed_time": "2:27:57", "remaining_time": "5:47:16", "throughput": 4453.42, "total_tokens": 39537136} {"current_steps": 18320, "total_steps": 61300, "loss": 0.3557, "lr": 4.421592436099186e-05, "epoch": 2.9885807504078303, "percentage": 29.89, "elapsed_time": "2:27:59", "remaining_time": "5:47:12", "throughput": 4453.5, "total_tokens": 39545808} {"current_steps": 18325, "total_steps": 61300, "loss": 0.386, "lr": 4.4211370314014534e-05, "epoch": 2.9893964110929856, "percentage": 29.89, "elapsed_time": "2:28:02", "remaining_time": "5:47:10", "throughput": 4453.62, "total_tokens": 39558000} {"current_steps": 18330, "total_steps": 61300, "loss": 0.3537, "lr": 4.4206814709666046e-05, "epoch": 2.9902120717781404, "percentage": 29.9, "elapsed_time": "2:28:04", "remaining_time": "5:47:08", "throughput": 4453.7, "total_tokens": 39570000} {"current_steps": 18335, "total_steps": 61300, "loss": 0.345, "lr": 4.4202257548315704e-05, "epoch": 2.9910277324632952, "percentage": 29.91, "elapsed_time": "2:28:06", "remaining_time": "5:47:05", "throughput": 4453.78, "total_tokens": 39580560} {"current_steps": 18340, "total_steps": 61300, "loss": 0.3508, "lr": 4.4197698830332934e-05, "epoch": 2.99184339314845, "percentage": 29.92, "elapsed_time": "2:28:09", "remaining_time": "5:47:02", "throughput": 4453.86, "total_tokens": 39591408} {"current_steps": 18345, "total_steps": 61300, "loss": 0.3608, "lr": 4.419313855608729e-05, "epoch": 2.9926590538336053, "percentage": 29.93, "elapsed_time": "2:28:11", "remaining_time": "5:46:59", "throughput": 4453.93, "total_tokens": 39601872} {"current_steps": 18350, "total_steps": 61300, "loss": 0.3604, "lr": 4.418857672594845e-05, "epoch": 2.99347471451876, "percentage": 29.93, "elapsed_time": "2:28:13", "remaining_time": "5:46:56", "throughput": 4454.03, "total_tokens": 39613008} {"current_steps": 18355, "total_steps": 61300, "loss": 0.3443, "lr": 4.4184013340286215e-05, "epoch": 2.9942903752039154, "percentage": 29.94, "elapsed_time": "2:28:16", "remaining_time": "5:46:54", "throughput": 4454.12, "total_tokens": 39624272} {"current_steps": 18360, "total_steps": 61300, "loss": 0.3403, "lr": 4.417944839947053e-05, "epoch": 2.99510603588907, "percentage": 29.95, "elapsed_time": "2:28:18", "remaining_time": "5:46:51", "throughput": 4454.22, "total_tokens": 39635216} {"current_steps": 18365, "total_steps": 61300, "loss": 0.3584, "lr": 4.417488190387144e-05, "epoch": 2.995921696574225, "percentage": 29.96, "elapsed_time": "2:28:20", "remaining_time": "5:46:48", "throughput": 4454.33, "total_tokens": 39645808} {"current_steps": 18370, "total_steps": 61300, "loss": 0.3342, "lr": 4.417031385385911e-05, "epoch": 2.99673735725938, "percentage": 29.97, "elapsed_time": "2:28:22", "remaining_time": "5:46:45", "throughput": 4454.42, "total_tokens": 39656560} {"current_steps": 18375, "total_steps": 61300, "loss": 0.3643, "lr": 4.416574424980389e-05, "epoch": 2.997553017944535, "percentage": 29.98, "elapsed_time": "2:28:24", "remaining_time": "5:46:42", "throughput": 4454.49, "total_tokens": 39666704} {"current_steps": 18380, "total_steps": 61300, "loss": 0.3557, "lr": 4.4161173092076194e-05, "epoch": 2.99836867862969, "percentage": 29.98, "elapsed_time": "2:28:27", "remaining_time": "5:46:39", "throughput": 4454.57, "total_tokens": 39677008} {"current_steps": 18385, "total_steps": 61300, "loss": 0.3283, "lr": 4.415660038104658e-05, "epoch": 2.999184339314845, "percentage": 29.99, "elapsed_time": "2:28:28", "remaining_time": "5:46:35", "throughput": 4454.65, "total_tokens": 39686416} {"current_steps": 18390, "total_steps": 61300, "loss": 0.3285, "lr": 4.4152026117085735e-05, "epoch": 3.0, "percentage": 30.0, "elapsed_time": "2:28:30", "remaining_time": "5:46:31", "throughput": 4454.67, "total_tokens": 39694112} {"current_steps": 18390, "total_steps": 61300, "eval_loss": 0.34291771054267883, "epoch": 3.0, "percentage": 30.0, "elapsed_time": "2:30:42", "remaining_time": "5:51:39", "throughput": 4389.56, "total_tokens": 39694112} {"current_steps": 18395, "total_steps": 61300, "loss": 0.3484, "lr": 4.4147450300564485e-05, "epoch": 3.000815660685155, "percentage": 30.01, "elapsed_time": "2:30:46", "remaining_time": "5:51:39", "throughput": 4388.96, "total_tokens": 39703936} {"current_steps": 18400, "total_steps": 61300, "loss": 0.3366, "lr": 4.414287293185376e-05, "epoch": 3.00163132137031, "percentage": 30.02, "elapsed_time": "2:30:48", "remaining_time": "5:51:37", "throughput": 4389.08, "total_tokens": 39715968} {"current_steps": 18405, "total_steps": 61300, "loss": 0.3355, "lr": 4.413829401132462e-05, "epoch": 3.002446982055465, "percentage": 30.02, "elapsed_time": "2:30:51", "remaining_time": "5:51:34", "throughput": 4389.19, "total_tokens": 39726912} {"current_steps": 18410, "total_steps": 61300, "loss": 0.3505, "lr": 4.4133713539348266e-05, "epoch": 3.0032626427406197, "percentage": 30.03, "elapsed_time": "2:30:53", "remaining_time": "5:51:31", "throughput": 4389.27, "total_tokens": 39737504} {"current_steps": 18415, "total_steps": 61300, "loss": 0.3358, "lr": 4.4129131516296006e-05, "epoch": 3.004078303425775, "percentage": 30.04, "elapsed_time": "2:30:55", "remaining_time": "5:51:29", "throughput": 4389.41, "total_tokens": 39749792} {"current_steps": 18420, "total_steps": 61300, "loss": 0.3543, "lr": 4.412454794253928e-05, "epoch": 3.00489396411093, "percentage": 30.05, "elapsed_time": "2:30:58", "remaining_time": "5:51:26", "throughput": 4389.51, "total_tokens": 39760928} {"current_steps": 18425, "total_steps": 61300, "loss": 0.3421, "lr": 4.4119962818449665e-05, "epoch": 3.0057096247960846, "percentage": 30.06, "elapsed_time": "2:31:00", "remaining_time": "5:51:23", "throughput": 4389.62, "total_tokens": 39772096} {"current_steps": 18430, "total_steps": 61300, "loss": 0.3463, "lr": 4.411537614439886e-05, "epoch": 3.00652528548124, "percentage": 30.07, "elapsed_time": "2:31:02", "remaining_time": "5:51:20", "throughput": 4389.74, "total_tokens": 39782528} {"current_steps": 18435, "total_steps": 61300, "loss": 0.3164, "lr": 4.4110787920758663e-05, "epoch": 3.0073409461663947, "percentage": 30.07, "elapsed_time": "2:31:05", "remaining_time": "5:51:17", "throughput": 4389.88, "total_tokens": 39794336} {"current_steps": 18440, "total_steps": 61300, "loss": 0.3265, "lr": 4.4106198147901035e-05, "epoch": 3.00815660685155, "percentage": 30.08, "elapsed_time": "2:31:07", "remaining_time": "5:51:15", "throughput": 4390.0, "total_tokens": 39805376} {"current_steps": 18445, "total_steps": 61300, "loss": 0.3068, "lr": 4.410160682619803e-05, "epoch": 3.0089722675367048, "percentage": 30.09, "elapsed_time": "2:31:09", "remaining_time": "5:51:12", "throughput": 4390.1, "total_tokens": 39816768} {"current_steps": 18450, "total_steps": 61300, "loss": 0.307, "lr": 4.409701395602187e-05, "epoch": 3.0097879282218596, "percentage": 30.1, "elapsed_time": "2:31:11", "remaining_time": "5:51:09", "throughput": 4390.2, "total_tokens": 39827520} {"current_steps": 18455, "total_steps": 61300, "loss": 0.337, "lr": 4.4092419537744854e-05, "epoch": 3.010603588907015, "percentage": 30.11, "elapsed_time": "2:31:14", "remaining_time": "5:51:06", "throughput": 4390.32, "total_tokens": 39839072} {"current_steps": 18460, "total_steps": 61300, "loss": 0.3412, "lr": 4.408782357173944e-05, "epoch": 3.0114192495921697, "percentage": 30.11, "elapsed_time": "2:31:16", "remaining_time": "5:51:04", "throughput": 4390.42, "total_tokens": 39850432} {"current_steps": 18465, "total_steps": 61300, "loss": 0.3579, "lr": 4.408322605837819e-05, "epoch": 3.0122349102773245, "percentage": 30.12, "elapsed_time": "2:31:18", "remaining_time": "5:51:01", "throughput": 4390.54, "total_tokens": 39861600} {"current_steps": 18470, "total_steps": 61300, "loss": 0.3174, "lr": 4.407862699803381e-05, "epoch": 3.0130505709624797, "percentage": 30.13, "elapsed_time": "2:31:21", "remaining_time": "5:50:58", "throughput": 4390.65, "total_tokens": 39872288} {"current_steps": 18475, "total_steps": 61300, "loss": 0.3425, "lr": 4.4074026391079126e-05, "epoch": 3.0138662316476346, "percentage": 30.14, "elapsed_time": "2:31:23", "remaining_time": "5:50:54", "throughput": 4390.75, "total_tokens": 39881984} {"current_steps": 18480, "total_steps": 61300, "loss": 0.3663, "lr": 4.406942423788708e-05, "epoch": 3.0146818923327894, "percentage": 30.15, "elapsed_time": "2:31:25", "remaining_time": "5:50:52", "throughput": 4390.85, "total_tokens": 39893184} {"current_steps": 18485, "total_steps": 61300, "loss": 0.3489, "lr": 4.406482053883075e-05, "epoch": 3.0154975530179446, "percentage": 30.15, "elapsed_time": "2:31:27", "remaining_time": "5:50:48", "throughput": 4390.95, "total_tokens": 39903200} {"current_steps": 18490, "total_steps": 61300, "loss": 0.3312, "lr": 4.406021529428334e-05, "epoch": 3.0163132137030995, "percentage": 30.16, "elapsed_time": "2:31:29", "remaining_time": "5:50:45", "throughput": 4391.04, "total_tokens": 39913728} {"current_steps": 18495, "total_steps": 61300, "loss": 0.3211, "lr": 4.405560850461815e-05, "epoch": 3.0171288743882543, "percentage": 30.17, "elapsed_time": "2:31:32", "remaining_time": "5:50:42", "throughput": 4391.13, "total_tokens": 39924576} {"current_steps": 18500, "total_steps": 61300, "loss": 0.3449, "lr": 4.405100017020866e-05, "epoch": 3.0179445350734095, "percentage": 30.18, "elapsed_time": "2:31:34", "remaining_time": "5:50:40", "throughput": 4391.23, "total_tokens": 39935808} {"current_steps": 18505, "total_steps": 61300, "loss": 0.3135, "lr": 4.4046390291428426e-05, "epoch": 3.0187601957585644, "percentage": 30.19, "elapsed_time": "2:31:36", "remaining_time": "5:50:37", "throughput": 4391.32, "total_tokens": 39946592} {"current_steps": 18510, "total_steps": 61300, "loss": 0.3252, "lr": 4.4041778868651155e-05, "epoch": 3.0195758564437196, "percentage": 30.2, "elapsed_time": "2:31:39", "remaining_time": "5:50:34", "throughput": 4391.43, "total_tokens": 39958592} {"current_steps": 18515, "total_steps": 61300, "loss": 0.3563, "lr": 4.4037165902250676e-05, "epoch": 3.0203915171288744, "percentage": 30.2, "elapsed_time": "2:31:41", "remaining_time": "5:50:31", "throughput": 4391.56, "total_tokens": 39969760} {"current_steps": 18520, "total_steps": 61300, "loss": 0.3292, "lr": 4.403255139260093e-05, "epoch": 3.0212071778140293, "percentage": 30.21, "elapsed_time": "2:31:43", "remaining_time": "5:50:28", "throughput": 4391.65, "total_tokens": 39980064} {"current_steps": 18525, "total_steps": 61300, "loss": 0.3445, "lr": 4.4027935340076005e-05, "epoch": 3.0220228384991845, "percentage": 30.22, "elapsed_time": "2:31:46", "remaining_time": "5:50:26", "throughput": 4391.77, "total_tokens": 39991840} {"current_steps": 18530, "total_steps": 61300, "loss": 0.3338, "lr": 4.402331774505009e-05, "epoch": 3.0228384991843393, "percentage": 30.23, "elapsed_time": "2:31:48", "remaining_time": "5:50:23", "throughput": 4391.89, "total_tokens": 40002912} {"current_steps": 18535, "total_steps": 61300, "loss": 0.3374, "lr": 4.4018698607897515e-05, "epoch": 3.023654159869494, "percentage": 30.24, "elapsed_time": "2:31:50", "remaining_time": "5:50:20", "throughput": 4392.04, "total_tokens": 40014624} {"current_steps": 18540, "total_steps": 61300, "loss": 0.3866, "lr": 4.4014077928992736e-05, "epoch": 3.0244698205546494, "percentage": 30.24, "elapsed_time": "2:31:52", "remaining_time": "5:50:17", "throughput": 4392.14, "total_tokens": 40025408} {"current_steps": 18545, "total_steps": 61300, "loss": 0.362, "lr": 4.4009455708710315e-05, "epoch": 3.0252854812398042, "percentage": 30.25, "elapsed_time": "2:31:55", "remaining_time": "5:50:14", "throughput": 4392.25, "total_tokens": 40036352} {"current_steps": 18550, "total_steps": 61300, "loss": 0.3595, "lr": 4.4004831947424967e-05, "epoch": 3.026101141924959, "percentage": 30.26, "elapsed_time": "2:31:57", "remaining_time": "5:50:11", "throughput": 4392.35, "total_tokens": 40045888} {"current_steps": 18555, "total_steps": 61300, "loss": 0.3173, "lr": 4.400020664551151e-05, "epoch": 3.0269168026101143, "percentage": 30.27, "elapsed_time": "2:31:59", "remaining_time": "5:50:08", "throughput": 4392.46, "total_tokens": 40056928} {"current_steps": 18560, "total_steps": 61300, "loss": 0.2951, "lr": 4.39955798033449e-05, "epoch": 3.027732463295269, "percentage": 30.28, "elapsed_time": "2:32:01", "remaining_time": "5:50:05", "throughput": 4392.55, "total_tokens": 40067456} {"current_steps": 18565, "total_steps": 61300, "loss": 0.3742, "lr": 4.399095142130021e-05, "epoch": 3.028548123980424, "percentage": 30.29, "elapsed_time": "2:32:03", "remaining_time": "5:50:02", "throughput": 4392.65, "total_tokens": 40077760} {"current_steps": 18570, "total_steps": 61300, "loss": 0.3079, "lr": 4.398632149975263e-05, "epoch": 3.029363784665579, "percentage": 30.29, "elapsed_time": "2:32:06", "remaining_time": "5:49:59", "throughput": 4392.76, "total_tokens": 40089376} {"current_steps": 18575, "total_steps": 61300, "loss": 0.3083, "lr": 4.39816900390775e-05, "epoch": 3.030179445350734, "percentage": 30.3, "elapsed_time": "2:32:08", "remaining_time": "5:49:56", "throughput": 4392.86, "total_tokens": 40100544} {"current_steps": 18580, "total_steps": 61300, "loss": 0.3038, "lr": 4.397705703965026e-05, "epoch": 3.0309951060358893, "percentage": 30.31, "elapsed_time": "2:32:10", "remaining_time": "5:49:54", "throughput": 4392.96, "total_tokens": 40111616} {"current_steps": 18585, "total_steps": 61300, "loss": 0.3691, "lr": 4.397242250184649e-05, "epoch": 3.031810766721044, "percentage": 30.32, "elapsed_time": "2:32:13", "remaining_time": "5:49:51", "throughput": 4393.1, "total_tokens": 40123712} {"current_steps": 18590, "total_steps": 61300, "loss": 0.3267, "lr": 4.396778642604188e-05, "epoch": 3.032626427406199, "percentage": 30.33, "elapsed_time": "2:32:15", "remaining_time": "5:49:49", "throughput": 4393.19, "total_tokens": 40134976} {"current_steps": 18595, "total_steps": 61300, "loss": 0.3402, "lr": 4.396314881261227e-05, "epoch": 3.033442088091354, "percentage": 30.33, "elapsed_time": "2:32:17", "remaining_time": "5:49:45", "throughput": 4393.29, "total_tokens": 40144992} {"current_steps": 18600, "total_steps": 61300, "loss": 0.317, "lr": 4.39585096619336e-05, "epoch": 3.034257748776509, "percentage": 30.34, "elapsed_time": "2:32:20", "remaining_time": "5:49:43", "throughput": 4393.41, "total_tokens": 40156928} {"current_steps": 18605, "total_steps": 61300, "loss": 0.3522, "lr": 4.395386897438194e-05, "epoch": 3.035073409461664, "percentage": 30.35, "elapsed_time": "2:32:22", "remaining_time": "5:49:40", "throughput": 4393.5, "total_tokens": 40167264} {"current_steps": 18610, "total_steps": 61300, "loss": 0.3477, "lr": 4.3949226750333484e-05, "epoch": 3.035889070146819, "percentage": 30.36, "elapsed_time": "2:32:24", "remaining_time": "5:49:37", "throughput": 4393.61, "total_tokens": 40178944} {"current_steps": 18615, "total_steps": 61300, "loss": 0.3672, "lr": 4.3944582990164565e-05, "epoch": 3.036704730831974, "percentage": 30.37, "elapsed_time": "2:32:27", "remaining_time": "5:49:34", "throughput": 4393.72, "total_tokens": 40190240} {"current_steps": 18620, "total_steps": 61300, "loss": 0.3533, "lr": 4.393993769425162e-05, "epoch": 3.0375203915171287, "percentage": 30.38, "elapsed_time": "2:32:29", "remaining_time": "5:49:32", "throughput": 4393.83, "total_tokens": 40201696} {"current_steps": 18625, "total_steps": 61300, "loss": 0.3159, "lr": 4.393529086297123e-05, "epoch": 3.038336052202284, "percentage": 30.38, "elapsed_time": "2:32:31", "remaining_time": "5:49:28", "throughput": 4393.91, "total_tokens": 40211424} {"current_steps": 18630, "total_steps": 61300, "loss": 0.3151, "lr": 4.3930642496700084e-05, "epoch": 3.039151712887439, "percentage": 30.39, "elapsed_time": "2:32:33", "remaining_time": "5:49:25", "throughput": 4394.0, "total_tokens": 40221888} {"current_steps": 18635, "total_steps": 61300, "loss": 0.3487, "lr": 4.392599259581501e-05, "epoch": 3.0399673735725936, "percentage": 30.4, "elapsed_time": "2:32:36", "remaining_time": "5:49:23", "throughput": 4394.13, "total_tokens": 40233120} {"current_steps": 18640, "total_steps": 61300, "loss": 0.3401, "lr": 4.392134116069294e-05, "epoch": 3.040783034257749, "percentage": 30.41, "elapsed_time": "2:32:38", "remaining_time": "5:49:19", "throughput": 4394.22, "total_tokens": 40243104} {"current_steps": 18645, "total_steps": 61300, "loss": 0.3561, "lr": 4.391668819171095e-05, "epoch": 3.0415986949429037, "percentage": 30.42, "elapsed_time": "2:32:40", "remaining_time": "5:49:16", "throughput": 4394.33, "total_tokens": 40253344} {"current_steps": 18650, "total_steps": 61300, "loss": 0.3465, "lr": 4.391203368924623e-05, "epoch": 3.0424143556280585, "percentage": 30.42, "elapsed_time": "2:32:42", "remaining_time": "5:49:14", "throughput": 4394.44, "total_tokens": 40265280} {"current_steps": 18655, "total_steps": 61300, "loss": 0.3211, "lr": 4.3907377653676104e-05, "epoch": 3.0432300163132138, "percentage": 30.43, "elapsed_time": "2:32:45", "remaining_time": "5:49:11", "throughput": 4394.56, "total_tokens": 40276224} {"current_steps": 18660, "total_steps": 61300, "loss": 0.3479, "lr": 4.390272008537802e-05, "epoch": 3.0440456769983686, "percentage": 30.44, "elapsed_time": "2:32:47", "remaining_time": "5:49:08", "throughput": 4394.66, "total_tokens": 40287168} {"current_steps": 18665, "total_steps": 61300, "loss": 0.3281, "lr": 4.3898060984729526e-05, "epoch": 3.044861337683524, "percentage": 30.45, "elapsed_time": "2:32:49", "remaining_time": "5:49:04", "throughput": 4394.75, "total_tokens": 40297184} {"current_steps": 18670, "total_steps": 61300, "loss": 0.3231, "lr": 4.389340035210832e-05, "epoch": 3.0456769983686787, "percentage": 30.46, "elapsed_time": "2:32:51", "remaining_time": "5:49:02", "throughput": 4394.83, "total_tokens": 40308128} {"current_steps": 18675, "total_steps": 61300, "loss": 0.339, "lr": 4.388873818789222e-05, "epoch": 3.0464926590538335, "percentage": 30.46, "elapsed_time": "2:32:54", "remaining_time": "5:48:59", "throughput": 4394.93, "total_tokens": 40320352} {"current_steps": 18680, "total_steps": 61300, "loss": 0.3098, "lr": 4.388407449245916e-05, "epoch": 3.0473083197389887, "percentage": 30.47, "elapsed_time": "2:32:56", "remaining_time": "5:48:57", "throughput": 4395.03, "total_tokens": 40331424} {"current_steps": 18685, "total_steps": 61300, "loss": 0.3204, "lr": 4.38794092661872e-05, "epoch": 3.0481239804241436, "percentage": 30.48, "elapsed_time": "2:32:59", "remaining_time": "5:48:54", "throughput": 4395.16, "total_tokens": 40343264} {"current_steps": 18690, "total_steps": 61300, "loss": 0.3526, "lr": 4.3874742509454536e-05, "epoch": 3.0489396411092984, "percentage": 30.49, "elapsed_time": "2:33:01", "remaining_time": "5:48:52", "throughput": 4395.29, "total_tokens": 40356608} {"current_steps": 18695, "total_steps": 61300, "loss": 0.3008, "lr": 4.387007422263948e-05, "epoch": 3.0497553017944536, "percentage": 30.5, "elapsed_time": "2:33:04", "remaining_time": "5:48:49", "throughput": 4395.4, "total_tokens": 40367456} {"current_steps": 18700, "total_steps": 61300, "loss": 0.3872, "lr": 4.3865404406120456e-05, "epoch": 3.0505709624796085, "percentage": 30.51, "elapsed_time": "2:33:06", "remaining_time": "5:48:46", "throughput": 4395.5, "total_tokens": 40377728} {"current_steps": 18705, "total_steps": 61300, "loss": 0.3809, "lr": 4.3860733060276025e-05, "epoch": 3.0513866231647633, "percentage": 30.51, "elapsed_time": "2:33:08", "remaining_time": "5:48:44", "throughput": 4395.62, "total_tokens": 40389184} {"current_steps": 18710, "total_steps": 61300, "loss": 0.3789, "lr": 4.385606018548488e-05, "epoch": 3.0522022838499185, "percentage": 30.52, "elapsed_time": "2:33:10", "remaining_time": "5:48:41", "throughput": 4395.74, "total_tokens": 40400512} {"current_steps": 18715, "total_steps": 61300, "loss": 0.3652, "lr": 4.385138578212582e-05, "epoch": 3.0530179445350734, "percentage": 30.53, "elapsed_time": "2:33:12", "remaining_time": "5:48:38", "throughput": 4395.85, "total_tokens": 40411008} {"current_steps": 18720, "total_steps": 61300, "loss": 0.3415, "lr": 4.384670985057778e-05, "epoch": 3.053833605220228, "percentage": 30.54, "elapsed_time": "2:33:15", "remaining_time": "5:48:35", "throughput": 4395.95, "total_tokens": 40422528} {"current_steps": 18725, "total_steps": 61300, "loss": 0.332, "lr": 4.3842032391219804e-05, "epoch": 3.0546492659053834, "percentage": 30.55, "elapsed_time": "2:33:17", "remaining_time": "5:48:32", "throughput": 4396.04, "total_tokens": 40432384} {"current_steps": 18730, "total_steps": 61300, "loss": 0.3337, "lr": 4.3837353404431086e-05, "epoch": 3.0554649265905383, "percentage": 30.55, "elapsed_time": "2:33:19", "remaining_time": "5:48:29", "throughput": 4396.15, "total_tokens": 40443424} {"current_steps": 18735, "total_steps": 61300, "loss": 0.3769, "lr": 4.383267289059092e-05, "epoch": 3.0562805872756935, "percentage": 30.56, "elapsed_time": "2:33:21", "remaining_time": "5:48:26", "throughput": 4396.24, "total_tokens": 40453760} {"current_steps": 18740, "total_steps": 61300, "loss": 0.3465, "lr": 4.382799085007873e-05, "epoch": 3.0570962479608483, "percentage": 30.57, "elapsed_time": "2:33:24", "remaining_time": "5:48:23", "throughput": 4396.34, "total_tokens": 40464832} {"current_steps": 18745, "total_steps": 61300, "loss": 0.3502, "lr": 4.382330728327407e-05, "epoch": 3.057911908646003, "percentage": 30.58, "elapsed_time": "2:33:26", "remaining_time": "5:48:20", "throughput": 4396.44, "total_tokens": 40475136} {"current_steps": 18750, "total_steps": 61300, "loss": 0.3934, "lr": 4.3818622190556624e-05, "epoch": 3.0587275693311584, "percentage": 30.59, "elapsed_time": "2:33:28", "remaining_time": "5:48:17", "throughput": 4396.53, "total_tokens": 40485856} {"current_steps": 18755, "total_steps": 61300, "loss": 0.3325, "lr": 4.381393557230617e-05, "epoch": 3.0595432300163132, "percentage": 30.6, "elapsed_time": "2:33:30", "remaining_time": "5:48:14", "throughput": 4396.65, "total_tokens": 40497120} {"current_steps": 18760, "total_steps": 61300, "loss": 0.3008, "lr": 4.380924742890264e-05, "epoch": 3.060358890701468, "percentage": 30.6, "elapsed_time": "2:33:33", "remaining_time": "5:48:12", "throughput": 4396.76, "total_tokens": 40508928} {"current_steps": 18765, "total_steps": 61300, "loss": 0.2979, "lr": 4.380455776072607e-05, "epoch": 3.0611745513866233, "percentage": 30.61, "elapsed_time": "2:33:35", "remaining_time": "5:48:09", "throughput": 4396.86, "total_tokens": 40519904} {"current_steps": 18770, "total_steps": 61300, "loss": 0.3403, "lr": 4.3799866568156634e-05, "epoch": 3.061990212071778, "percentage": 30.62, "elapsed_time": "2:33:37", "remaining_time": "5:48:05", "throughput": 4396.95, "total_tokens": 40529568} {"current_steps": 18775, "total_steps": 61300, "loss": 0.3009, "lr": 4.379517385157463e-05, "epoch": 3.062805872756933, "percentage": 30.63, "elapsed_time": "2:33:39", "remaining_time": "5:48:03", "throughput": 4397.04, "total_tokens": 40540512} {"current_steps": 18780, "total_steps": 61300, "loss": 0.3298, "lr": 4.3790479611360466e-05, "epoch": 3.063621533442088, "percentage": 30.64, "elapsed_time": "2:33:42", "remaining_time": "5:47:59", "throughput": 4397.14, "total_tokens": 40550592} {"current_steps": 18785, "total_steps": 61300, "loss": 0.3623, "lr": 4.378578384789469e-05, "epoch": 3.064437194127243, "percentage": 30.64, "elapsed_time": "2:33:44", "remaining_time": "5:47:56", "throughput": 4397.25, "total_tokens": 40561824} {"current_steps": 18790, "total_steps": 61300, "loss": 0.3649, "lr": 4.378108656155795e-05, "epoch": 3.065252854812398, "percentage": 30.65, "elapsed_time": "2:33:46", "remaining_time": "5:47:53", "throughput": 4397.35, "total_tokens": 40572416} {"current_steps": 18795, "total_steps": 61300, "loss": 0.398, "lr": 4.377638775273104e-05, "epoch": 3.066068515497553, "percentage": 30.66, "elapsed_time": "2:33:48", "remaining_time": "5:47:51", "throughput": 4397.46, "total_tokens": 40583712} {"current_steps": 18800, "total_steps": 61300, "loss": 0.3906, "lr": 4.3771687421794866e-05, "epoch": 3.066884176182708, "percentage": 30.67, "elapsed_time": "2:33:51", "remaining_time": "5:47:48", "throughput": 4397.57, "total_tokens": 40594560} {"current_steps": 18805, "total_steps": 61300, "loss": 0.3343, "lr": 4.3766985569130465e-05, "epoch": 3.067699836867863, "percentage": 30.68, "elapsed_time": "2:33:53", "remaining_time": "5:47:45", "throughput": 4397.66, "total_tokens": 40605536} {"current_steps": 18810, "total_steps": 61300, "loss": 0.3262, "lr": 4.376228219511899e-05, "epoch": 3.068515497553018, "percentage": 30.69, "elapsed_time": "2:33:55", "remaining_time": "5:47:42", "throughput": 4397.74, "total_tokens": 40615328} {"current_steps": 18815, "total_steps": 61300, "loss": 0.336, "lr": 4.375757730014172e-05, "epoch": 3.069331158238173, "percentage": 30.69, "elapsed_time": "2:33:57", "remaining_time": "5:47:38", "throughput": 4397.85, "total_tokens": 40625504} {"current_steps": 18820, "total_steps": 61300, "loss": 0.3443, "lr": 4.3752870884580065e-05, "epoch": 3.070146818923328, "percentage": 30.7, "elapsed_time": "2:33:59", "remaining_time": "5:47:36", "throughput": 4397.95, "total_tokens": 40636896} {"current_steps": 18825, "total_steps": 61300, "loss": 0.3569, "lr": 4.374816294881554e-05, "epoch": 3.070962479608483, "percentage": 30.71, "elapsed_time": "2:34:02", "remaining_time": "5:47:33", "throughput": 4398.03, "total_tokens": 40647456} {"current_steps": 18830, "total_steps": 61300, "loss": 0.3447, "lr": 4.37434534932298e-05, "epoch": 3.0717781402936377, "percentage": 30.72, "elapsed_time": "2:34:04", "remaining_time": "5:47:29", "throughput": 4398.11, "total_tokens": 40656832} {"current_steps": 18835, "total_steps": 61300, "loss": 0.3527, "lr": 4.373874251820462e-05, "epoch": 3.072593800978793, "percentage": 30.73, "elapsed_time": "2:34:06", "remaining_time": "5:47:26", "throughput": 4398.2, "total_tokens": 40666752} {"current_steps": 18840, "total_steps": 61300, "loss": 0.3509, "lr": 4.3734030024121886e-05, "epoch": 3.073409461663948, "percentage": 30.73, "elapsed_time": "2:34:08", "remaining_time": "5:47:23", "throughput": 4398.31, "total_tokens": 40678368} {"current_steps": 18845, "total_steps": 61300, "loss": 0.3543, "lr": 4.372931601136363e-05, "epoch": 3.0742251223491026, "percentage": 30.74, "elapsed_time": "2:34:10", "remaining_time": "5:47:21", "throughput": 4398.42, "total_tokens": 40689632} {"current_steps": 18850, "total_steps": 61300, "loss": 0.3432, "lr": 4.372460048031198e-05, "epoch": 3.075040783034258, "percentage": 30.75, "elapsed_time": "2:34:13", "remaining_time": "5:47:18", "throughput": 4398.51, "total_tokens": 40700576} {"current_steps": 18855, "total_steps": 61300, "loss": 0.3402, "lr": 4.3719883431349206e-05, "epoch": 3.0758564437194127, "percentage": 30.76, "elapsed_time": "2:34:15", "remaining_time": "5:47:15", "throughput": 4398.6, "total_tokens": 40711488} {"current_steps": 18860, "total_steps": 61300, "loss": 0.3247, "lr": 4.3715164864857705e-05, "epoch": 3.0766721044045675, "percentage": 30.77, "elapsed_time": "2:34:17", "remaining_time": "5:47:11", "throughput": 4398.68, "total_tokens": 40720832} {"current_steps": 18865, "total_steps": 61300, "loss": 0.3405, "lr": 4.371044478121998e-05, "epoch": 3.0774877650897228, "percentage": 30.77, "elapsed_time": "2:34:19", "remaining_time": "5:47:08", "throughput": 4398.78, "total_tokens": 40731200} {"current_steps": 18870, "total_steps": 61300, "loss": 0.3399, "lr": 4.370572318081866e-05, "epoch": 3.0783034257748776, "percentage": 30.78, "elapsed_time": "2:34:21", "remaining_time": "5:47:05", "throughput": 4398.88, "total_tokens": 40742432} {"current_steps": 18875, "total_steps": 61300, "loss": 0.3032, "lr": 4.3701000064036504e-05, "epoch": 3.0791190864600324, "percentage": 30.79, "elapsed_time": "2:34:24", "remaining_time": "5:47:03", "throughput": 4398.98, "total_tokens": 40753856} {"current_steps": 18880, "total_steps": 61300, "loss": 0.2949, "lr": 4.3696275431256405e-05, "epoch": 3.0799347471451877, "percentage": 30.8, "elapsed_time": "2:34:26", "remaining_time": "5:46:59", "throughput": 4399.07, "total_tokens": 40762976} {"current_steps": 18885, "total_steps": 61300, "loss": 0.2859, "lr": 4.369154928286134e-05, "epoch": 3.0807504078303425, "percentage": 30.81, "elapsed_time": "2:34:28", "remaining_time": "5:46:56", "throughput": 4399.18, "total_tokens": 40773504} {"current_steps": 18890, "total_steps": 61300, "loss": 0.3613, "lr": 4.368682161923447e-05, "epoch": 3.0815660685154977, "percentage": 30.82, "elapsed_time": "2:34:30", "remaining_time": "5:46:53", "throughput": 4399.28, "total_tokens": 40784576} {"current_steps": 18895, "total_steps": 61300, "loss": 0.3472, "lr": 4.368209244075901e-05, "epoch": 3.0823817292006526, "percentage": 30.82, "elapsed_time": "2:34:32", "remaining_time": "5:46:50", "throughput": 4399.37, "total_tokens": 40794240} {"current_steps": 18900, "total_steps": 61300, "loss": 0.3916, "lr": 4.3677361747818355e-05, "epoch": 3.0831973898858074, "percentage": 30.83, "elapsed_time": "2:34:35", "remaining_time": "5:46:47", "throughput": 4399.48, "total_tokens": 40805600} {"current_steps": 18905, "total_steps": 61300, "loss": 0.3758, "lr": 4.3672629540795976e-05, "epoch": 3.0840130505709626, "percentage": 30.84, "elapsed_time": "2:34:37", "remaining_time": "5:46:44", "throughput": 4399.56, "total_tokens": 40816352} {"current_steps": 18910, "total_steps": 61300, "loss": 0.3079, "lr": 4.366789582007551e-05, "epoch": 3.0848287112561175, "percentage": 30.85, "elapsed_time": "2:34:39", "remaining_time": "5:46:41", "throughput": 4399.62, "total_tokens": 40826720} {"current_steps": 18915, "total_steps": 61300, "loss": 0.3681, "lr": 4.366316058604069e-05, "epoch": 3.0856443719412723, "percentage": 30.86, "elapsed_time": "2:34:41", "remaining_time": "5:46:38", "throughput": 4399.71, "total_tokens": 40837216} {"current_steps": 18920, "total_steps": 61300, "loss": 0.3544, "lr": 4.3658423839075376e-05, "epoch": 3.0864600326264275, "percentage": 30.86, "elapsed_time": "2:34:44", "remaining_time": "5:46:35", "throughput": 4399.8, "total_tokens": 40847904} {"current_steps": 18925, "total_steps": 61300, "loss": 0.3371, "lr": 4.3653685579563555e-05, "epoch": 3.0872756933115824, "percentage": 30.87, "elapsed_time": "2:34:46", "remaining_time": "5:46:32", "throughput": 4399.9, "total_tokens": 40858304} {"current_steps": 18930, "total_steps": 61300, "loss": 0.3463, "lr": 4.364894580788932e-05, "epoch": 3.088091353996737, "percentage": 30.88, "elapsed_time": "2:34:48", "remaining_time": "5:46:29", "throughput": 4399.99, "total_tokens": 40869088} {"current_steps": 18935, "total_steps": 61300, "loss": 0.3373, "lr": 4.364420452443693e-05, "epoch": 3.0889070146818924, "percentage": 30.89, "elapsed_time": "2:34:50", "remaining_time": "5:46:26", "throughput": 4400.08, "total_tokens": 40878976} {"current_steps": 18940, "total_steps": 61300, "loss": 0.3383, "lr": 4.363946172959071e-05, "epoch": 3.0897226753670473, "percentage": 30.9, "elapsed_time": "2:34:52", "remaining_time": "5:46:23", "throughput": 4400.19, "total_tokens": 40890144} {"current_steps": 18945, "total_steps": 61300, "loss": 0.3387, "lr": 4.363471742373516e-05, "epoch": 3.090538336052202, "percentage": 30.91, "elapsed_time": "2:34:54", "remaining_time": "5:46:20", "throughput": 4400.28, "total_tokens": 40900448} {"current_steps": 18950, "total_steps": 61300, "loss": 0.3313, "lr": 4.3629971607254855e-05, "epoch": 3.0913539967373573, "percentage": 30.91, "elapsed_time": "2:34:57", "remaining_time": "5:46:17", "throughput": 4400.37, "total_tokens": 40910880} {"current_steps": 18955, "total_steps": 61300, "loss": 0.3484, "lr": 4.362522428053453e-05, "epoch": 3.092169657422512, "percentage": 30.92, "elapsed_time": "2:34:59", "remaining_time": "5:46:15", "throughput": 4400.48, "total_tokens": 40922752} {"current_steps": 18960, "total_steps": 61300, "loss": 0.3347, "lr": 4.3620475443959016e-05, "epoch": 3.0929853181076674, "percentage": 30.93, "elapsed_time": "2:35:01", "remaining_time": "5:46:11", "throughput": 4400.59, "total_tokens": 40932640} {"current_steps": 18965, "total_steps": 61300, "loss": 0.3115, "lr": 4.361572509791328e-05, "epoch": 3.0938009787928222, "percentage": 30.94, "elapsed_time": "2:35:03", "remaining_time": "5:46:08", "throughput": 4400.69, "total_tokens": 40943264} {"current_steps": 18970, "total_steps": 61300, "loss": 0.3184, "lr": 4.361097324278242e-05, "epoch": 3.094616639477977, "percentage": 30.95, "elapsed_time": "2:35:05", "remaining_time": "5:46:05", "throughput": 4400.79, "total_tokens": 40953664} {"current_steps": 18975, "total_steps": 61300, "loss": 0.3749, "lr": 4.3606219878951623e-05, "epoch": 3.0954323001631323, "percentage": 30.95, "elapsed_time": "2:35:08", "remaining_time": "5:46:02", "throughput": 4400.89, "total_tokens": 40964544} {"current_steps": 18980, "total_steps": 61300, "loss": 0.3624, "lr": 4.360146500680625e-05, "epoch": 3.096247960848287, "percentage": 30.96, "elapsed_time": "2:35:10", "remaining_time": "5:45:59", "throughput": 4401.0, "total_tokens": 40975520} {"current_steps": 18985, "total_steps": 61300, "loss": 0.3475, "lr": 4.3596708626731744e-05, "epoch": 3.097063621533442, "percentage": 30.97, "elapsed_time": "2:35:12", "remaining_time": "5:45:56", "throughput": 4401.09, "total_tokens": 40985728} {"current_steps": 18990, "total_steps": 61300, "loss": 0.3633, "lr": 4.359195073911367e-05, "epoch": 3.097879282218597, "percentage": 30.98, "elapsed_time": "2:35:14", "remaining_time": "5:45:53", "throughput": 4401.18, "total_tokens": 40996064} {"current_steps": 18995, "total_steps": 61300, "loss": 0.4175, "lr": 4.3587191344337735e-05, "epoch": 3.098694942903752, "percentage": 30.99, "elapsed_time": "2:35:17", "remaining_time": "5:45:50", "throughput": 4401.29, "total_tokens": 41007456} {"current_steps": 19000, "total_steps": 61300, "loss": 0.3457, "lr": 4.358243044278976e-05, "epoch": 3.099510603588907, "percentage": 31.0, "elapsed_time": "2:35:19", "remaining_time": "5:45:47", "throughput": 4401.39, "total_tokens": 41017792} {"current_steps": 19005, "total_steps": 61300, "loss": 0.3318, "lr": 4.3577668034855684e-05, "epoch": 3.100326264274062, "percentage": 31.0, "elapsed_time": "2:35:21", "remaining_time": "5:45:44", "throughput": 4401.48, "total_tokens": 41028512} {"current_steps": 19010, "total_steps": 61300, "loss": 0.3396, "lr": 4.357290412092158e-05, "epoch": 3.101141924959217, "percentage": 31.01, "elapsed_time": "2:35:23", "remaining_time": "5:45:41", "throughput": 4401.57, "total_tokens": 41039520} {"current_steps": 19015, "total_steps": 61300, "loss": 0.3393, "lr": 4.356813870137363e-05, "epoch": 3.1019575856443717, "percentage": 31.02, "elapsed_time": "2:35:26", "remaining_time": "5:45:39", "throughput": 4401.67, "total_tokens": 41050336} {"current_steps": 19020, "total_steps": 61300, "loss": 0.3606, "lr": 4.356337177659814e-05, "epoch": 3.102773246329527, "percentage": 31.03, "elapsed_time": "2:35:28", "remaining_time": "5:45:36", "throughput": 4401.78, "total_tokens": 41061088} {"current_steps": 19025, "total_steps": 61300, "loss": 0.3271, "lr": 4.355860334698154e-05, "epoch": 3.103588907014682, "percentage": 31.04, "elapsed_time": "2:35:30", "remaining_time": "5:45:33", "throughput": 4401.88, "total_tokens": 41071680} {"current_steps": 19030, "total_steps": 61300, "loss": 0.3184, "lr": 4.3553833412910395e-05, "epoch": 3.104404567699837, "percentage": 31.04, "elapsed_time": "2:35:32", "remaining_time": "5:45:30", "throughput": 4402.0, "total_tokens": 41083744} {"current_steps": 19035, "total_steps": 61300, "loss": 0.3412, "lr": 4.354906197477137e-05, "epoch": 3.105220228384992, "percentage": 31.05, "elapsed_time": "2:35:35", "remaining_time": "5:45:27", "throughput": 4402.1, "total_tokens": 41094688} {"current_steps": 19040, "total_steps": 61300, "loss": 0.3391, "lr": 4.354428903295126e-05, "epoch": 3.1060358890701467, "percentage": 31.06, "elapsed_time": "2:35:37", "remaining_time": "5:45:25", "throughput": 4402.23, "total_tokens": 41106656} {"current_steps": 19045, "total_steps": 61300, "loss": 0.2992, "lr": 4.353951458783699e-05, "epoch": 3.106851549755302, "percentage": 31.07, "elapsed_time": "2:35:39", "remaining_time": "5:45:22", "throughput": 4402.31, "total_tokens": 41117280} {"current_steps": 19050, "total_steps": 61300, "loss": 0.3606, "lr": 4.3534738639815606e-05, "epoch": 3.107667210440457, "percentage": 31.08, "elapsed_time": "2:35:42", "remaining_time": "5:45:19", "throughput": 4402.4, "total_tokens": 41128064} {"current_steps": 19055, "total_steps": 61300, "loss": 0.3564, "lr": 4.352996118927426e-05, "epoch": 3.1084828711256116, "percentage": 31.08, "elapsed_time": "2:35:44", "remaining_time": "5:45:16", "throughput": 4402.48, "total_tokens": 41137440} {"current_steps": 19060, "total_steps": 61300, "loss": 0.3481, "lr": 4.3525182236600235e-05, "epoch": 3.109298531810767, "percentage": 31.09, "elapsed_time": "2:35:46", "remaining_time": "5:45:12", "throughput": 4402.55, "total_tokens": 41147648} {"current_steps": 19065, "total_steps": 61300, "loss": 0.3781, "lr": 4.3520401782180954e-05, "epoch": 3.1101141924959217, "percentage": 31.1, "elapsed_time": "2:35:48", "remaining_time": "5:45:10", "throughput": 4402.64, "total_tokens": 41158688} {"current_steps": 19070, "total_steps": 61300, "loss": 0.3256, "lr": 4.351561982640392e-05, "epoch": 3.1109298531810765, "percentage": 31.11, "elapsed_time": "2:35:50", "remaining_time": "5:45:06", "throughput": 4402.72, "total_tokens": 41168160} {"current_steps": 19075, "total_steps": 61300, "loss": 0.3424, "lr": 4.35108363696568e-05, "epoch": 3.1117455138662318, "percentage": 31.12, "elapsed_time": "2:35:53", "remaining_time": "5:45:04", "throughput": 4402.83, "total_tokens": 41179936} {"current_steps": 19080, "total_steps": 61300, "loss": 0.3537, "lr": 4.3506051412327364e-05, "epoch": 3.1125611745513866, "percentage": 31.13, "elapsed_time": "2:35:55", "remaining_time": "5:45:01", "throughput": 4402.93, "total_tokens": 41190528} {"current_steps": 19085, "total_steps": 61300, "loss": 0.3032, "lr": 4.3501264954803495e-05, "epoch": 3.1133768352365414, "percentage": 31.13, "elapsed_time": "2:35:57", "remaining_time": "5:44:57", "throughput": 4403.03, "total_tokens": 41200128} {"current_steps": 19090, "total_steps": 61300, "loss": 0.3402, "lr": 4.3496476997473216e-05, "epoch": 3.1141924959216967, "percentage": 31.14, "elapsed_time": "2:35:59", "remaining_time": "5:44:54", "throughput": 4403.12, "total_tokens": 41211040} {"current_steps": 19095, "total_steps": 61300, "loss": 0.371, "lr": 4.349168754072467e-05, "epoch": 3.1150081566068515, "percentage": 31.15, "elapsed_time": "2:36:02", "remaining_time": "5:44:52", "throughput": 4403.23, "total_tokens": 41223392} {"current_steps": 19100, "total_steps": 61300, "loss": 0.3366, "lr": 4.3486896584946094e-05, "epoch": 3.1158238172920063, "percentage": 31.16, "elapsed_time": "2:36:04", "remaining_time": "5:44:49", "throughput": 4403.32, "total_tokens": 41233344} {"current_steps": 19105, "total_steps": 61300, "loss": 0.3415, "lr": 4.348210413052589e-05, "epoch": 3.1166394779771616, "percentage": 31.17, "elapsed_time": "2:36:06", "remaining_time": "5:44:46", "throughput": 4403.42, "total_tokens": 41244512} {"current_steps": 19110, "total_steps": 61300, "loss": 0.3514, "lr": 4.3477310177852537e-05, "epoch": 3.1174551386623164, "percentage": 31.17, "elapsed_time": "2:36:08", "remaining_time": "5:44:43", "throughput": 4403.52, "total_tokens": 41255360} {"current_steps": 19115, "total_steps": 61300, "loss": 0.3508, "lr": 4.347251472731467e-05, "epoch": 3.1182707993474716, "percentage": 31.18, "elapsed_time": "2:36:10", "remaining_time": "5:44:40", "throughput": 4403.6, "total_tokens": 41265856} {"current_steps": 19120, "total_steps": 61300, "loss": 0.3268, "lr": 4.3467717779301046e-05, "epoch": 3.1190864600326265, "percentage": 31.19, "elapsed_time": "2:36:13", "remaining_time": "5:44:38", "throughput": 4403.7, "total_tokens": 41277216} {"current_steps": 19125, "total_steps": 61300, "loss": 0.3809, "lr": 4.3462919334200494e-05, "epoch": 3.1199021207177813, "percentage": 31.2, "elapsed_time": "2:36:15", "remaining_time": "5:44:35", "throughput": 4403.79, "total_tokens": 41288256} {"current_steps": 19130, "total_steps": 61300, "loss": 0.3018, "lr": 4.345811939240203e-05, "epoch": 3.1207177814029365, "percentage": 31.21, "elapsed_time": "2:36:17", "remaining_time": "5:44:32", "throughput": 4403.89, "total_tokens": 41298784} {"current_steps": 19135, "total_steps": 61300, "loss": 0.3357, "lr": 4.3453317954294755e-05, "epoch": 3.1215334420880914, "percentage": 31.22, "elapsed_time": "2:36:20", "remaining_time": "5:44:29", "throughput": 4404.01, "total_tokens": 41309792} {"current_steps": 19140, "total_steps": 61300, "loss": 0.3339, "lr": 4.3448515020267896e-05, "epoch": 3.122349102773246, "percentage": 31.22, "elapsed_time": "2:36:22", "remaining_time": "5:44:26", "throughput": 4404.09, "total_tokens": 41320320} {"current_steps": 19145, "total_steps": 61300, "loss": 0.338, "lr": 4.3443710590710795e-05, "epoch": 3.1231647634584014, "percentage": 31.23, "elapsed_time": "2:36:24", "remaining_time": "5:44:23", "throughput": 4404.2, "total_tokens": 41331008} {"current_steps": 19150, "total_steps": 61300, "loss": 0.3583, "lr": 4.343890466601294e-05, "epoch": 3.1239804241435563, "percentage": 31.24, "elapsed_time": "2:36:26", "remaining_time": "5:44:20", "throughput": 4404.3, "total_tokens": 41341888} {"current_steps": 19155, "total_steps": 61300, "loss": 0.3163, "lr": 4.343409724656391e-05, "epoch": 3.124796084828711, "percentage": 31.25, "elapsed_time": "2:36:28", "remaining_time": "5:44:17", "throughput": 4404.37, "total_tokens": 41351840} {"current_steps": 19160, "total_steps": 61300, "loss": 0.3192, "lr": 4.342928833275341e-05, "epoch": 3.1256117455138663, "percentage": 31.26, "elapsed_time": "2:36:31", "remaining_time": "5:44:14", "throughput": 4404.46, "total_tokens": 41362592} {"current_steps": 19165, "total_steps": 61300, "loss": 0.3488, "lr": 4.342447792497131e-05, "epoch": 3.126427406199021, "percentage": 31.26, "elapsed_time": "2:36:33", "remaining_time": "5:44:11", "throughput": 4404.54, "total_tokens": 41372704} {"current_steps": 19170, "total_steps": 61300, "loss": 0.3338, "lr": 4.341966602360754e-05, "epoch": 3.1272430668841764, "percentage": 31.27, "elapsed_time": "2:36:35", "remaining_time": "5:44:08", "throughput": 4404.64, "total_tokens": 41383584} {"current_steps": 19175, "total_steps": 61300, "loss": 0.358, "lr": 4.3414852629052175e-05, "epoch": 3.1280587275693312, "percentage": 31.28, "elapsed_time": "2:36:37", "remaining_time": "5:44:05", "throughput": 4404.74, "total_tokens": 41394976} {"current_steps": 19180, "total_steps": 61300, "loss": 0.3346, "lr": 4.341003774169542e-05, "epoch": 3.128874388254486, "percentage": 31.29, "elapsed_time": "2:36:40", "remaining_time": "5:44:02", "throughput": 4404.86, "total_tokens": 41406016} {"current_steps": 19185, "total_steps": 61300, "loss": 0.3607, "lr": 4.34052213619276e-05, "epoch": 3.1296900489396413, "percentage": 31.3, "elapsed_time": "2:36:42", "remaining_time": "5:44:00", "throughput": 4404.98, "total_tokens": 41417376} {"current_steps": 19190, "total_steps": 61300, "loss": 0.3121, "lr": 4.340040349013915e-05, "epoch": 3.130505709624796, "percentage": 31.31, "elapsed_time": "2:36:44", "remaining_time": "5:43:57", "throughput": 4405.06, "total_tokens": 41428416} {"current_steps": 19195, "total_steps": 61300, "loss": 0.3422, "lr": 4.3395584126720626e-05, "epoch": 3.131321370309951, "percentage": 31.31, "elapsed_time": "2:36:47", "remaining_time": "5:43:54", "throughput": 4405.17, "total_tokens": 41439552} {"current_steps": 19200, "total_steps": 61300, "loss": 0.3293, "lr": 4.339076327206272e-05, "epoch": 3.132137030995106, "percentage": 31.32, "elapsed_time": "2:36:48", "remaining_time": "5:43:51", "throughput": 4405.26, "total_tokens": 41448928} {"current_steps": 19205, "total_steps": 61300, "loss": 0.3476, "lr": 4.338594092655622e-05, "epoch": 3.132952691680261, "percentage": 31.33, "elapsed_time": "2:36:51", "remaining_time": "5:43:48", "throughput": 4405.37, "total_tokens": 41460096} {"current_steps": 19210, "total_steps": 61300, "loss": 0.3143, "lr": 4.338111709059206e-05, "epoch": 3.133768352365416, "percentage": 31.34, "elapsed_time": "2:36:53", "remaining_time": "5:43:44", "throughput": 4405.45, "total_tokens": 41469696} {"current_steps": 19215, "total_steps": 61300, "loss": 0.3266, "lr": 4.337629176456129e-05, "epoch": 3.134584013050571, "percentage": 31.35, "elapsed_time": "2:36:55", "remaining_time": "5:43:41", "throughput": 4405.56, "total_tokens": 41480224} {"current_steps": 19220, "total_steps": 61300, "loss": 0.3592, "lr": 4.337146494885507e-05, "epoch": 3.135399673735726, "percentage": 31.35, "elapsed_time": "2:36:57", "remaining_time": "5:43:38", "throughput": 4405.66, "total_tokens": 41490176} {"current_steps": 19225, "total_steps": 61300, "loss": 0.3874, "lr": 4.336663664386468e-05, "epoch": 3.1362153344208807, "percentage": 31.36, "elapsed_time": "2:36:59", "remaining_time": "5:43:35", "throughput": 4405.75, "total_tokens": 41500928} {"current_steps": 19230, "total_steps": 61300, "loss": 0.3547, "lr": 4.3361806849981535e-05, "epoch": 3.137030995106036, "percentage": 31.37, "elapsed_time": "2:37:02", "remaining_time": "5:43:33", "throughput": 4405.85, "total_tokens": 41512608} {"current_steps": 19235, "total_steps": 61300, "loss": 0.3116, "lr": 4.335697556759716e-05, "epoch": 3.137846655791191, "percentage": 31.38, "elapsed_time": "2:37:04", "remaining_time": "5:43:29", "throughput": 4405.95, "total_tokens": 41522880} {"current_steps": 19240, "total_steps": 61300, "loss": 0.353, "lr": 4.3352142797103204e-05, "epoch": 3.1386623164763456, "percentage": 31.39, "elapsed_time": "2:37:06", "remaining_time": "5:43:27", "throughput": 4406.04, "total_tokens": 41533632} {"current_steps": 19245, "total_steps": 61300, "loss": 0.376, "lr": 4.334730853889143e-05, "epoch": 3.139477977161501, "percentage": 31.39, "elapsed_time": "2:37:09", "remaining_time": "5:43:24", "throughput": 4406.14, "total_tokens": 41546112} {"current_steps": 19250, "total_steps": 61300, "loss": 0.3472, "lr": 4.3342472793353736e-05, "epoch": 3.1402936378466557, "percentage": 31.4, "elapsed_time": "2:37:11", "remaining_time": "5:43:22", "throughput": 4406.25, "total_tokens": 41557376} {"current_steps": 19255, "total_steps": 61300, "loss": 0.3388, "lr": 4.333763556088213e-05, "epoch": 3.141109298531811, "percentage": 31.41, "elapsed_time": "2:37:13", "remaining_time": "5:43:19", "throughput": 4406.35, "total_tokens": 41568160} {"current_steps": 19260, "total_steps": 61300, "loss": 0.3313, "lr": 4.333279684186874e-05, "epoch": 3.141924959216966, "percentage": 31.42, "elapsed_time": "2:37:15", "remaining_time": "5:43:15", "throughput": 4406.42, "total_tokens": 41577696} {"current_steps": 19265, "total_steps": 61300, "loss": 0.2982, "lr": 4.332795663670581e-05, "epoch": 3.1427406199021206, "percentage": 31.43, "elapsed_time": "2:37:18", "remaining_time": "5:43:13", "throughput": 4406.51, "total_tokens": 41589088} {"current_steps": 19270, "total_steps": 61300, "loss": 0.3527, "lr": 4.332311494578573e-05, "epoch": 3.143556280587276, "percentage": 31.44, "elapsed_time": "2:37:20", "remaining_time": "5:43:10", "throughput": 4406.62, "total_tokens": 41599904} {"current_steps": 19275, "total_steps": 61300, "loss": 0.3583, "lr": 4.331827176950098e-05, "epoch": 3.1443719412724307, "percentage": 31.44, "elapsed_time": "2:37:22", "remaining_time": "5:43:07", "throughput": 4406.7, "total_tokens": 41610784} {"current_steps": 19280, "total_steps": 61300, "loss": 0.3165, "lr": 4.3313427108244175e-05, "epoch": 3.1451876019575855, "percentage": 31.45, "elapsed_time": "2:37:24", "remaining_time": "5:43:04", "throughput": 4406.79, "total_tokens": 41620768} {"current_steps": 19285, "total_steps": 61300, "loss": 0.3438, "lr": 4.330858096240804e-05, "epoch": 3.1460032626427408, "percentage": 31.46, "elapsed_time": "2:37:27", "remaining_time": "5:43:01", "throughput": 4406.88, "total_tokens": 41632384} {"current_steps": 19290, "total_steps": 61300, "loss": 0.3328, "lr": 4.3303733332385446e-05, "epoch": 3.1468189233278956, "percentage": 31.47, "elapsed_time": "2:37:29", "remaining_time": "5:42:59", "throughput": 4406.98, "total_tokens": 41643680} {"current_steps": 19295, "total_steps": 61300, "loss": 0.3453, "lr": 4.329888421856936e-05, "epoch": 3.1476345840130504, "percentage": 31.48, "elapsed_time": "2:37:31", "remaining_time": "5:42:56", "throughput": 4407.08, "total_tokens": 41655424} {"current_steps": 19300, "total_steps": 61300, "loss": 0.3042, "lr": 4.3294033621352856e-05, "epoch": 3.1484502446982057, "percentage": 31.48, "elapsed_time": "2:37:34", "remaining_time": "5:42:53", "throughput": 4407.18, "total_tokens": 41666144} {"current_steps": 19305, "total_steps": 61300, "loss": 0.3571, "lr": 4.3289181541129174e-05, "epoch": 3.1492659053833605, "percentage": 31.49, "elapsed_time": "2:37:36", "remaining_time": "5:42:51", "throughput": 4407.28, "total_tokens": 41677312} {"current_steps": 19310, "total_steps": 61300, "loss": 0.3311, "lr": 4.328432797829164e-05, "epoch": 3.1500815660685153, "percentage": 31.5, "elapsed_time": "2:37:39", "remaining_time": "5:42:48", "throughput": 4407.36, "total_tokens": 41689344} {"current_steps": 19315, "total_steps": 61300, "loss": 0.3468, "lr": 4.3279472933233696e-05, "epoch": 3.1508972267536706, "percentage": 31.51, "elapsed_time": "2:37:41", "remaining_time": "5:42:45", "throughput": 4407.45, "total_tokens": 41700032} {"current_steps": 19320, "total_steps": 61300, "loss": 0.327, "lr": 4.327461640634893e-05, "epoch": 3.1517128874388254, "percentage": 31.52, "elapsed_time": "2:37:43", "remaining_time": "5:42:43", "throughput": 4407.56, "total_tokens": 41711040} {"current_steps": 19325, "total_steps": 61300, "loss": 0.3568, "lr": 4.3269758398031037e-05, "epoch": 3.15252854812398, "percentage": 31.53, "elapsed_time": "2:37:45", "remaining_time": "5:42:39", "throughput": 4407.65, "total_tokens": 41721184} {"current_steps": 19330, "total_steps": 61300, "loss": 0.3369, "lr": 4.3264898908673826e-05, "epoch": 3.1533442088091355, "percentage": 31.53, "elapsed_time": "2:37:47", "remaining_time": "5:42:36", "throughput": 4407.74, "total_tokens": 41731616} {"current_steps": 19335, "total_steps": 61300, "loss": 0.3364, "lr": 4.3260037938671237e-05, "epoch": 3.1541598694942903, "percentage": 31.54, "elapsed_time": "2:37:49", "remaining_time": "5:42:33", "throughput": 4407.83, "total_tokens": 41741568} {"current_steps": 19340, "total_steps": 61300, "loss": 0.3389, "lr": 4.325517548841732e-05, "epoch": 3.1549755301794455, "percentage": 31.55, "elapsed_time": "2:37:52", "remaining_time": "5:42:30", "throughput": 4407.92, "total_tokens": 41752512} {"current_steps": 19345, "total_steps": 61300, "loss": 0.3603, "lr": 4.3250311558306255e-05, "epoch": 3.1557911908646004, "percentage": 31.56, "elapsed_time": "2:37:54", "remaining_time": "5:42:27", "throughput": 4408.01, "total_tokens": 41763040} {"current_steps": 19350, "total_steps": 61300, "loss": 0.3001, "lr": 4.324544614873233e-05, "epoch": 3.156606851549755, "percentage": 31.57, "elapsed_time": "2:37:56", "remaining_time": "5:42:24", "throughput": 4408.1, "total_tokens": 41773472} {"current_steps": 19355, "total_steps": 61300, "loss": 0.3299, "lr": 4.324057926008997e-05, "epoch": 3.1574225122349104, "percentage": 31.57, "elapsed_time": "2:37:58", "remaining_time": "5:42:21", "throughput": 4408.19, "total_tokens": 41784096} {"current_steps": 19360, "total_steps": 61300, "loss": 0.2944, "lr": 4.323571089277369e-05, "epoch": 3.1582381729200653, "percentage": 31.58, "elapsed_time": "2:38:01", "remaining_time": "5:42:19", "throughput": 4408.3, "total_tokens": 41795616} {"current_steps": 19365, "total_steps": 61300, "loss": 0.3257, "lr": 4.3230841047178175e-05, "epoch": 3.15905383360522, "percentage": 31.59, "elapsed_time": "2:38:03", "remaining_time": "5:42:16", "throughput": 4408.4, "total_tokens": 41806784} {"current_steps": 19370, "total_steps": 61300, "loss": 0.3692, "lr": 4.3225969723698165e-05, "epoch": 3.1598694942903753, "percentage": 31.6, "elapsed_time": "2:38:05", "remaining_time": "5:42:13", "throughput": 4408.49, "total_tokens": 41817920} {"current_steps": 19375, "total_steps": 61300, "loss": 0.3132, "lr": 4.322109692272858e-05, "epoch": 3.16068515497553, "percentage": 31.61, "elapsed_time": "2:38:07", "remaining_time": "5:42:10", "throughput": 4408.56, "total_tokens": 41827520} {"current_steps": 19380, "total_steps": 61300, "loss": 0.3774, "lr": 4.321622264466443e-05, "epoch": 3.161500815660685, "percentage": 31.62, "elapsed_time": "2:38:10", "remaining_time": "5:42:07", "throughput": 4408.65, "total_tokens": 41838496} {"current_steps": 19385, "total_steps": 61300, "loss": 0.3808, "lr": 4.321134688990084e-05, "epoch": 3.1623164763458402, "percentage": 31.62, "elapsed_time": "2:38:12", "remaining_time": "5:42:04", "throughput": 4408.74, "total_tokens": 41848800} {"current_steps": 19390, "total_steps": 61300, "loss": 0.3325, "lr": 4.320646965883307e-05, "epoch": 3.163132137030995, "percentage": 31.63, "elapsed_time": "2:38:14", "remaining_time": "5:42:01", "throughput": 4408.82, "total_tokens": 41859616} {"current_steps": 19395, "total_steps": 61300, "loss": 0.3763, "lr": 4.320159095185648e-05, "epoch": 3.1639477977161503, "percentage": 31.64, "elapsed_time": "2:38:16", "remaining_time": "5:41:58", "throughput": 4408.91, "total_tokens": 41870432} {"current_steps": 19400, "total_steps": 61300, "loss": 0.3835, "lr": 4.3196710769366585e-05, "epoch": 3.164763458401305, "percentage": 31.65, "elapsed_time": "2:38:19", "remaining_time": "5:41:55", "throughput": 4408.98, "total_tokens": 41880960} {"current_steps": 19405, "total_steps": 61300, "loss": 0.3348, "lr": 4.3191829111758985e-05, "epoch": 3.16557911908646, "percentage": 31.66, "elapsed_time": "2:38:21", "remaining_time": "5:41:52", "throughput": 4409.09, "total_tokens": 41891456} {"current_steps": 19410, "total_steps": 61300, "loss": 0.3474, "lr": 4.318694597942941e-05, "epoch": 3.166394779771615, "percentage": 31.66, "elapsed_time": "2:38:23", "remaining_time": "5:41:50", "throughput": 4409.18, "total_tokens": 41903040} {"current_steps": 19415, "total_steps": 61300, "loss": 0.3441, "lr": 4.318206137277372e-05, "epoch": 3.16721044045677, "percentage": 31.67, "elapsed_time": "2:38:25", "remaining_time": "5:41:47", "throughput": 4409.28, "total_tokens": 41914272} {"current_steps": 19420, "total_steps": 61300, "loss": 0.3764, "lr": 4.317717529218788e-05, "epoch": 3.168026101141925, "percentage": 31.68, "elapsed_time": "2:38:28", "remaining_time": "5:41:44", "throughput": 4409.37, "total_tokens": 41925184} {"current_steps": 19425, "total_steps": 61300, "loss": 0.3303, "lr": 4.317228773806797e-05, "epoch": 3.16884176182708, "percentage": 31.69, "elapsed_time": "2:38:30", "remaining_time": "5:41:42", "throughput": 4409.47, "total_tokens": 41936288} {"current_steps": 19430, "total_steps": 61300, "loss": 0.4243, "lr": 4.316739871081021e-05, "epoch": 3.169657422512235, "percentage": 31.7, "elapsed_time": "2:38:32", "remaining_time": "5:41:38", "throughput": 4409.57, "total_tokens": 41945984} {"current_steps": 19435, "total_steps": 61300, "loss": 0.3386, "lr": 4.3162508210810936e-05, "epoch": 3.1704730831973897, "percentage": 31.7, "elapsed_time": "2:38:34", "remaining_time": "5:41:35", "throughput": 4409.65, "total_tokens": 41956256} {"current_steps": 19440, "total_steps": 61300, "loss": 0.3635, "lr": 4.31576162384666e-05, "epoch": 3.171288743882545, "percentage": 31.71, "elapsed_time": "2:38:36", "remaining_time": "5:41:32", "throughput": 4409.75, "total_tokens": 41967040} {"current_steps": 19445, "total_steps": 61300, "loss": 0.3128, "lr": 4.315272279417375e-05, "epoch": 3.1721044045677, "percentage": 31.72, "elapsed_time": "2:38:39", "remaining_time": "5:41:29", "throughput": 4409.83, "total_tokens": 41977664} {"current_steps": 19450, "total_steps": 61300, "loss": 0.3382, "lr": 4.314782787832908e-05, "epoch": 3.1729200652528546, "percentage": 31.73, "elapsed_time": "2:38:41", "remaining_time": "5:41:26", "throughput": 4409.92, "total_tokens": 41988384} {"current_steps": 19455, "total_steps": 61300, "loss": 0.3608, "lr": 4.314293149132941e-05, "epoch": 3.17373572593801, "percentage": 31.74, "elapsed_time": "2:38:43", "remaining_time": "5:41:24", "throughput": 4410.02, "total_tokens": 42000576} {"current_steps": 19460, "total_steps": 61300, "loss": 0.3674, "lr": 4.313803363357166e-05, "epoch": 3.1745513866231647, "percentage": 31.75, "elapsed_time": "2:38:45", "remaining_time": "5:41:21", "throughput": 4410.09, "total_tokens": 42010176} {"current_steps": 19465, "total_steps": 61300, "loss": 0.3449, "lr": 4.313313430545286e-05, "epoch": 3.1753670473083195, "percentage": 31.75, "elapsed_time": "2:38:48", "remaining_time": "5:41:18", "throughput": 4410.21, "total_tokens": 42021248} {"current_steps": 19470, "total_steps": 61300, "loss": 0.3413, "lr": 4.3128233507370196e-05, "epoch": 3.176182707993475, "percentage": 31.76, "elapsed_time": "2:38:50", "remaining_time": "5:41:15", "throughput": 4410.29, "total_tokens": 42031712} {"current_steps": 19475, "total_steps": 61300, "loss": 0.3248, "lr": 4.312333123972094e-05, "epoch": 3.1769983686786296, "percentage": 31.77, "elapsed_time": "2:38:52", "remaining_time": "5:41:12", "throughput": 4410.4, "total_tokens": 42042848} {"current_steps": 19480, "total_steps": 61300, "loss": 0.3714, "lr": 4.31184275029025e-05, "epoch": 3.177814029363785, "percentage": 31.78, "elapsed_time": "2:38:54", "remaining_time": "5:41:09", "throughput": 4410.48, "total_tokens": 42053856} {"current_steps": 19485, "total_steps": 61300, "loss": 0.3495, "lr": 4.311352229731239e-05, "epoch": 3.1786296900489397, "percentage": 31.79, "elapsed_time": "2:38:57", "remaining_time": "5:41:06", "throughput": 4410.6, "total_tokens": 42064864} {"current_steps": 19490, "total_steps": 61300, "loss": 0.3517, "lr": 4.310861562334826e-05, "epoch": 3.1794453507340945, "percentage": 31.79, "elapsed_time": "2:38:59", "remaining_time": "5:41:04", "throughput": 4410.7, "total_tokens": 42076864} {"current_steps": 19495, "total_steps": 61300, "loss": 0.3383, "lr": 4.310370748140786e-05, "epoch": 3.1802610114192498, "percentage": 31.8, "elapsed_time": "2:39:01", "remaining_time": "5:41:01", "throughput": 4410.8, "total_tokens": 42086592} {"current_steps": 19500, "total_steps": 61300, "loss": 0.3554, "lr": 4.3098797871889075e-05, "epoch": 3.1810766721044046, "percentage": 31.81, "elapsed_time": "2:39:03", "remaining_time": "5:40:58", "throughput": 4410.87, "total_tokens": 42096736} {"current_steps": 19505, "total_steps": 61300, "loss": 0.3496, "lr": 4.30938867951899e-05, "epoch": 3.1818923327895594, "percentage": 31.82, "elapsed_time": "2:39:05", "remaining_time": "5:40:54", "throughput": 4410.95, "total_tokens": 42106592} {"current_steps": 19510, "total_steps": 61300, "loss": 0.3357, "lr": 4.308897425170846e-05, "epoch": 3.1827079934747147, "percentage": 31.83, "elapsed_time": "2:39:08", "remaining_time": "5:40:51", "throughput": 4411.07, "total_tokens": 42117024} {"current_steps": 19515, "total_steps": 61300, "loss": 0.3776, "lr": 4.3084060241842984e-05, "epoch": 3.1835236541598695, "percentage": 31.84, "elapsed_time": "2:39:10", "remaining_time": "5:40:48", "throughput": 4411.18, "total_tokens": 42127776} {"current_steps": 19520, "total_steps": 61300, "loss": 0.3468, "lr": 4.307914476599182e-05, "epoch": 3.1843393148450243, "percentage": 31.84, "elapsed_time": "2:39:12", "remaining_time": "5:40:45", "throughput": 4411.3, "total_tokens": 42138976} {"current_steps": 19525, "total_steps": 61300, "loss": 0.3264, "lr": 4.307422782455346e-05, "epoch": 3.1851549755301796, "percentage": 31.85, "elapsed_time": "2:39:14", "remaining_time": "5:40:43", "throughput": 4411.39, "total_tokens": 42150752} {"current_steps": 19530, "total_steps": 61300, "loss": 0.3743, "lr": 4.306930941792648e-05, "epoch": 3.1859706362153344, "percentage": 31.86, "elapsed_time": "2:39:17", "remaining_time": "5:40:40", "throughput": 4411.5, "total_tokens": 42161696} {"current_steps": 19535, "total_steps": 61300, "loss": 0.3456, "lr": 4.3064389546509585e-05, "epoch": 3.186786296900489, "percentage": 31.87, "elapsed_time": "2:39:19", "remaining_time": "5:40:38", "throughput": 4411.6, "total_tokens": 42173312} {"current_steps": 19540, "total_steps": 61300, "loss": 0.3346, "lr": 4.305946821070163e-05, "epoch": 3.1876019575856445, "percentage": 31.88, "elapsed_time": "2:39:22", "remaining_time": "5:40:35", "throughput": 4411.7, "total_tokens": 42185344} {"current_steps": 19545, "total_steps": 61300, "loss": 0.3148, "lr": 4.3054545410901547e-05, "epoch": 3.1884176182707993, "percentage": 31.88, "elapsed_time": "2:39:24", "remaining_time": "5:40:33", "throughput": 4411.79, "total_tokens": 42196480} {"current_steps": 19550, "total_steps": 61300, "loss": 0.3071, "lr": 4.30496211475084e-05, "epoch": 3.189233278955954, "percentage": 31.89, "elapsed_time": "2:39:26", "remaining_time": "5:40:29", "throughput": 4411.88, "total_tokens": 42206624} {"current_steps": 19555, "total_steps": 61300, "loss": 0.3496, "lr": 4.3044695420921386e-05, "epoch": 3.1900489396411094, "percentage": 31.9, "elapsed_time": "2:39:29", "remaining_time": "5:40:27", "throughput": 4411.97, "total_tokens": 42218688} {"current_steps": 19560, "total_steps": 61300, "loss": 0.3587, "lr": 4.30397682315398e-05, "epoch": 3.190864600326264, "percentage": 31.91, "elapsed_time": "2:39:31", "remaining_time": "5:40:24", "throughput": 4412.06, "total_tokens": 42228896} {"current_steps": 19565, "total_steps": 61300, "loss": 0.331, "lr": 4.303483957976306e-05, "epoch": 3.1916802610114194, "percentage": 31.92, "elapsed_time": "2:39:33", "remaining_time": "5:40:21", "throughput": 4412.15, "total_tokens": 42239424} {"current_steps": 19570, "total_steps": 61300, "loss": 0.3322, "lr": 4.302990946599073e-05, "epoch": 3.1924959216965743, "percentage": 31.92, "elapsed_time": "2:39:35", "remaining_time": "5:40:18", "throughput": 4412.25, "total_tokens": 42250272} {"current_steps": 19575, "total_steps": 61300, "loss": 0.3373, "lr": 4.302497789062245e-05, "epoch": 3.193311582381729, "percentage": 31.93, "elapsed_time": "2:39:37", "remaining_time": "5:40:15", "throughput": 4412.34, "total_tokens": 42261024} {"current_steps": 19580, "total_steps": 61300, "loss": 0.3207, "lr": 4.3020044854058e-05, "epoch": 3.1941272430668843, "percentage": 31.94, "elapsed_time": "2:39:40", "remaining_time": "5:40:12", "throughput": 4412.42, "total_tokens": 42271680} {"current_steps": 19585, "total_steps": 61300, "loss": 0.3651, "lr": 4.3015110356697285e-05, "epoch": 3.194942903752039, "percentage": 31.95, "elapsed_time": "2:39:42", "remaining_time": "5:40:09", "throughput": 4412.52, "total_tokens": 42281792} {"current_steps": 19590, "total_steps": 61300, "loss": 0.3527, "lr": 4.301017439894032e-05, "epoch": 3.195758564437194, "percentage": 31.96, "elapsed_time": "2:39:44", "remaining_time": "5:40:06", "throughput": 4412.61, "total_tokens": 42292128} {"current_steps": 19595, "total_steps": 61300, "loss": 0.3098, "lr": 4.300523698118722e-05, "epoch": 3.1965742251223492, "percentage": 31.97, "elapsed_time": "2:39:46", "remaining_time": "5:40:03", "throughput": 4412.72, "total_tokens": 42303232} {"current_steps": 19600, "total_steps": 61300, "loss": 0.3053, "lr": 4.3000298103838274e-05, "epoch": 3.197389885807504, "percentage": 31.97, "elapsed_time": "2:39:48", "remaining_time": "5:40:00", "throughput": 4412.81, "total_tokens": 42313056} {"current_steps": 19605, "total_steps": 61300, "loss": 0.3288, "lr": 4.299535776729382e-05, "epoch": 3.198205546492659, "percentage": 31.98, "elapsed_time": "2:39:51", "remaining_time": "5:39:57", "throughput": 4412.91, "total_tokens": 42324320} {"current_steps": 19610, "total_steps": 61300, "loss": 0.3193, "lr": 4.2990415971954364e-05, "epoch": 3.199021207177814, "percentage": 31.99, "elapsed_time": "2:39:52", "remaining_time": "5:39:53", "throughput": 4412.98, "total_tokens": 42332800} {"current_steps": 19615, "total_steps": 61300, "loss": 0.3319, "lr": 4.29854727182205e-05, "epoch": 3.199836867862969, "percentage": 32.0, "elapsed_time": "2:39:55", "remaining_time": "5:39:51", "throughput": 4413.08, "total_tokens": 42344448} {"current_steps": 19620, "total_steps": 61300, "loss": 0.3903, "lr": 4.298052800649296e-05, "epoch": 3.200652528548124, "percentage": 32.01, "elapsed_time": "2:39:57", "remaining_time": "5:39:48", "throughput": 4413.17, "total_tokens": 42355520} {"current_steps": 19625, "total_steps": 61300, "loss": 0.3376, "lr": 4.297558183717259e-05, "epoch": 3.201468189233279, "percentage": 32.01, "elapsed_time": "2:39:59", "remaining_time": "5:39:45", "throughput": 4413.27, "total_tokens": 42366656} {"current_steps": 19630, "total_steps": 61300, "loss": 0.3864, "lr": 4.297063421066035e-05, "epoch": 3.202283849918434, "percentage": 32.02, "elapsed_time": "2:40:02", "remaining_time": "5:39:43", "throughput": 4413.36, "total_tokens": 42377824} {"current_steps": 19635, "total_steps": 61300, "loss": 0.335, "lr": 4.296568512735732e-05, "epoch": 3.203099510603589, "percentage": 32.03, "elapsed_time": "2:40:04", "remaining_time": "5:39:40", "throughput": 4413.45, "total_tokens": 42388064} {"current_steps": 19640, "total_steps": 61300, "loss": 0.3315, "lr": 4.29607345876647e-05, "epoch": 3.203915171288744, "percentage": 32.04, "elapsed_time": "2:40:06", "remaining_time": "5:39:37", "throughput": 4413.55, "total_tokens": 42399648} {"current_steps": 19645, "total_steps": 61300, "loss": 0.3445, "lr": 4.2955782591983795e-05, "epoch": 3.2047308319738987, "percentage": 32.05, "elapsed_time": "2:40:08", "remaining_time": "5:39:34", "throughput": 4413.62, "total_tokens": 42409024} {"current_steps": 19650, "total_steps": 61300, "loss": 0.3599, "lr": 4.295082914071604e-05, "epoch": 3.205546492659054, "percentage": 32.06, "elapsed_time": "2:40:10", "remaining_time": "5:39:31", "throughput": 4413.71, "total_tokens": 42419552} {"current_steps": 19655, "total_steps": 61300, "loss": 0.3729, "lr": 4.294587423426301e-05, "epoch": 3.206362153344209, "percentage": 32.06, "elapsed_time": "2:40:12", "remaining_time": "5:39:27", "throughput": 4413.78, "total_tokens": 42428992} {"current_steps": 19660, "total_steps": 61300, "loss": 0.3549, "lr": 4.294091787302634e-05, "epoch": 3.2071778140293636, "percentage": 32.07, "elapsed_time": "2:40:15", "remaining_time": "5:39:25", "throughput": 4413.88, "total_tokens": 42440736} {"current_steps": 19665, "total_steps": 61300, "loss": 0.3374, "lr": 4.2935960057407855e-05, "epoch": 3.207993474714519, "percentage": 32.08, "elapsed_time": "2:40:17", "remaining_time": "5:39:22", "throughput": 4413.95, "total_tokens": 42451168} {"current_steps": 19670, "total_steps": 61300, "loss": 0.3684, "lr": 4.2931000787809426e-05, "epoch": 3.2088091353996737, "percentage": 32.09, "elapsed_time": "2:40:19", "remaining_time": "5:39:19", "throughput": 4414.06, "total_tokens": 42462528} {"current_steps": 19675, "total_steps": 61300, "loss": 0.3566, "lr": 4.29260400646331e-05, "epoch": 3.2096247960848285, "percentage": 32.1, "elapsed_time": "2:40:21", "remaining_time": "5:39:16", "throughput": 4414.13, "total_tokens": 42471648} {"current_steps": 19680, "total_steps": 61300, "loss": 0.3335, "lr": 4.2921077888281014e-05, "epoch": 3.210440456769984, "percentage": 32.1, "elapsed_time": "2:40:24", "remaining_time": "5:39:13", "throughput": 4414.23, "total_tokens": 42482944} {"current_steps": 19685, "total_steps": 61300, "loss": 0.3591, "lr": 4.2916114259155414e-05, "epoch": 3.2112561174551386, "percentage": 32.11, "elapsed_time": "2:40:26", "remaining_time": "5:39:10", "throughput": 4414.31, "total_tokens": 42493152} {"current_steps": 19690, "total_steps": 61300, "loss": 0.368, "lr": 4.291114917765869e-05, "epoch": 3.2120717781402934, "percentage": 32.12, "elapsed_time": "2:40:28", "remaining_time": "5:39:07", "throughput": 4414.41, "total_tokens": 42504544} {"current_steps": 19695, "total_steps": 61300, "loss": 0.3549, "lr": 4.290618264419334e-05, "epoch": 3.2128874388254487, "percentage": 32.13, "elapsed_time": "2:40:30", "remaining_time": "5:39:04", "throughput": 4414.51, "total_tokens": 42514496} {"current_steps": 19700, "total_steps": 61300, "loss": 0.3432, "lr": 4.290121465916196e-05, "epoch": 3.2137030995106035, "percentage": 32.14, "elapsed_time": "2:40:32", "remaining_time": "5:39:01", "throughput": 4414.6, "total_tokens": 42524704} {"current_steps": 19705, "total_steps": 61300, "loss": 0.3172, "lr": 4.2896245222967296e-05, "epoch": 3.2145187601957588, "percentage": 32.15, "elapsed_time": "2:40:34", "remaining_time": "5:38:58", "throughput": 4414.68, "total_tokens": 42534688} {"current_steps": 19710, "total_steps": 61300, "loss": 0.3447, "lr": 4.2891274336012186e-05, "epoch": 3.2153344208809136, "percentage": 32.15, "elapsed_time": "2:40:37", "remaining_time": "5:38:55", "throughput": 4414.79, "total_tokens": 42546016} {"current_steps": 19715, "total_steps": 61300, "loss": 0.3341, "lr": 4.288630199869961e-05, "epoch": 3.2161500815660684, "percentage": 32.16, "elapsed_time": "2:40:39", "remaining_time": "5:38:52", "throughput": 4414.88, "total_tokens": 42556672} {"current_steps": 19720, "total_steps": 61300, "loss": 0.3542, "lr": 4.2881328211432626e-05, "epoch": 3.2169657422512237, "percentage": 32.17, "elapsed_time": "2:40:41", "remaining_time": "5:38:49", "throughput": 4414.98, "total_tokens": 42567168} {"current_steps": 19725, "total_steps": 61300, "loss": 0.3461, "lr": 4.2876352974614456e-05, "epoch": 3.2177814029363785, "percentage": 32.18, "elapsed_time": "2:40:43", "remaining_time": "5:38:46", "throughput": 4415.07, "total_tokens": 42577760} {"current_steps": 19730, "total_steps": 61300, "loss": 0.3389, "lr": 4.28713762886484e-05, "epoch": 3.2185970636215333, "percentage": 32.19, "elapsed_time": "2:40:46", "remaining_time": "5:38:43", "throughput": 4415.16, "total_tokens": 42588672} {"current_steps": 19735, "total_steps": 61300, "loss": 0.3442, "lr": 4.286639815393791e-05, "epoch": 3.2194127243066886, "percentage": 32.19, "elapsed_time": "2:40:48", "remaining_time": "5:38:41", "throughput": 4415.26, "total_tokens": 42600480} {"current_steps": 19740, "total_steps": 61300, "loss": 0.3235, "lr": 4.286141857088654e-05, "epoch": 3.2202283849918434, "percentage": 32.2, "elapsed_time": "2:40:51", "remaining_time": "5:38:39", "throughput": 4415.37, "total_tokens": 42612992} {"current_steps": 19745, "total_steps": 61300, "loss": 0.343, "lr": 4.285643753989794e-05, "epoch": 3.221044045676998, "percentage": 32.21, "elapsed_time": "2:40:53", "remaining_time": "5:38:36", "throughput": 4415.49, "total_tokens": 42624576} {"current_steps": 19750, "total_steps": 61300, "loss": 0.3631, "lr": 4.2851455061375924e-05, "epoch": 3.2218597063621535, "percentage": 32.22, "elapsed_time": "2:40:55", "remaining_time": "5:38:33", "throughput": 4415.59, "total_tokens": 42636128} {"current_steps": 19755, "total_steps": 61300, "loss": 0.3273, "lr": 4.2846471135724376e-05, "epoch": 3.2226753670473083, "percentage": 32.23, "elapsed_time": "2:40:57", "remaining_time": "5:38:30", "throughput": 4415.66, "total_tokens": 42646304} {"current_steps": 19760, "total_steps": 61300, "loss": 0.3488, "lr": 4.2841485763347324e-05, "epoch": 3.223491027732463, "percentage": 32.23, "elapsed_time": "2:41:00", "remaining_time": "5:38:27", "throughput": 4415.75, "total_tokens": 42656576} {"current_steps": 19765, "total_steps": 61300, "loss": 0.3553, "lr": 4.2836498944648904e-05, "epoch": 3.2243066884176184, "percentage": 32.24, "elapsed_time": "2:41:02", "remaining_time": "5:38:24", "throughput": 4415.82, "total_tokens": 42666624} {"current_steps": 19770, "total_steps": 61300, "loss": 0.3537, "lr": 4.2831510680033394e-05, "epoch": 3.225122349102773, "percentage": 32.25, "elapsed_time": "2:41:04", "remaining_time": "5:38:21", "throughput": 4415.92, "total_tokens": 42676096} {"current_steps": 19775, "total_steps": 61300, "loss": 0.3293, "lr": 4.2826520969905134e-05, "epoch": 3.225938009787928, "percentage": 32.26, "elapsed_time": "2:41:06", "remaining_time": "5:38:18", "throughput": 4416.01, "total_tokens": 42686752} {"current_steps": 19780, "total_steps": 61300, "loss": 0.3354, "lr": 4.282152981466865e-05, "epoch": 3.2267536704730833, "percentage": 32.27, "elapsed_time": "2:41:08", "remaining_time": "5:38:15", "throughput": 4416.11, "total_tokens": 42697792} {"current_steps": 19785, "total_steps": 61300, "loss": 0.3508, "lr": 4.2816537214728524e-05, "epoch": 3.227569331158238, "percentage": 32.28, "elapsed_time": "2:41:10", "remaining_time": "5:38:12", "throughput": 4416.2, "total_tokens": 42708384} {"current_steps": 19790, "total_steps": 61300, "loss": 0.3628, "lr": 4.281154317048949e-05, "epoch": 3.2283849918433933, "percentage": 32.28, "elapsed_time": "2:41:13", "remaining_time": "5:38:09", "throughput": 4416.3, "total_tokens": 42719136} {"current_steps": 19795, "total_steps": 61300, "loss": 0.3566, "lr": 4.28065476823564e-05, "epoch": 3.229200652528548, "percentage": 32.29, "elapsed_time": "2:41:15", "remaining_time": "5:38:06", "throughput": 4416.36, "total_tokens": 42728896} {"current_steps": 19800, "total_steps": 61300, "loss": 0.3616, "lr": 4.2801550750734195e-05, "epoch": 3.230016313213703, "percentage": 32.3, "elapsed_time": "2:41:17", "remaining_time": "5:38:03", "throughput": 4416.46, "total_tokens": 42740512} {"current_steps": 19805, "total_steps": 61300, "loss": 0.3408, "lr": 4.279655237602796e-05, "epoch": 3.2308319738988582, "percentage": 32.31, "elapsed_time": "2:41:19", "remaining_time": "5:38:00", "throughput": 4416.55, "total_tokens": 42750240} {"current_steps": 19810, "total_steps": 61300, "loss": 0.3308, "lr": 4.279155255864291e-05, "epoch": 3.231647634584013, "percentage": 32.32, "elapsed_time": "2:41:21", "remaining_time": "5:37:57", "throughput": 4416.63, "total_tokens": 42760672} {"current_steps": 19815, "total_steps": 61300, "loss": 0.3584, "lr": 4.2786551298984315e-05, "epoch": 3.232463295269168, "percentage": 32.32, "elapsed_time": "2:41:23", "remaining_time": "5:37:54", "throughput": 4416.74, "total_tokens": 42771680} {"current_steps": 19820, "total_steps": 61300, "loss": 0.3394, "lr": 4.278154859745763e-05, "epoch": 3.233278955954323, "percentage": 32.33, "elapsed_time": "2:41:26", "remaining_time": "5:37:51", "throughput": 4416.81, "total_tokens": 42782048} {"current_steps": 19825, "total_steps": 61300, "loss": 0.3501, "lr": 4.27765444544684e-05, "epoch": 3.234094616639478, "percentage": 32.34, "elapsed_time": "2:41:28", "remaining_time": "5:37:48", "throughput": 4416.87, "total_tokens": 42792864} {"current_steps": 19830, "total_steps": 61300, "loss": 0.3297, "lr": 4.277153887042227e-05, "epoch": 3.2349102773246328, "percentage": 32.35, "elapsed_time": "2:41:30", "remaining_time": "5:37:46", "throughput": 4416.96, "total_tokens": 42803904} {"current_steps": 19835, "total_steps": 61300, "loss": 0.3473, "lr": 4.2766531845725036e-05, "epoch": 3.235725938009788, "percentage": 32.36, "elapsed_time": "2:41:33", "remaining_time": "5:37:43", "throughput": 4417.06, "total_tokens": 42814720} {"current_steps": 19840, "total_steps": 61300, "loss": 0.343, "lr": 4.276152338078258e-05, "epoch": 3.236541598694943, "percentage": 32.37, "elapsed_time": "2:41:35", "remaining_time": "5:37:40", "throughput": 4417.17, "total_tokens": 42825856} {"current_steps": 19845, "total_steps": 61300, "loss": 0.3464, "lr": 4.275651347600092e-05, "epoch": 3.237357259380098, "percentage": 32.37, "elapsed_time": "2:41:37", "remaining_time": "5:37:37", "throughput": 4417.26, "total_tokens": 42837408} {"current_steps": 19850, "total_steps": 61300, "loss": 0.3874, "lr": 4.275150213178618e-05, "epoch": 3.238172920065253, "percentage": 32.38, "elapsed_time": "2:41:40", "remaining_time": "5:37:35", "throughput": 4417.36, "total_tokens": 42848960} {"current_steps": 19855, "total_steps": 61300, "loss": 0.3398, "lr": 4.27464893485446e-05, "epoch": 3.2389885807504077, "percentage": 32.39, "elapsed_time": "2:41:42", "remaining_time": "5:37:32", "throughput": 4417.45, "total_tokens": 42859168} {"current_steps": 19860, "total_steps": 61300, "loss": 0.345, "lr": 4.274147512668256e-05, "epoch": 3.239804241435563, "percentage": 32.4, "elapsed_time": "2:41:44", "remaining_time": "5:37:28", "throughput": 4417.52, "total_tokens": 42867872} {"current_steps": 19865, "total_steps": 61300, "loss": 0.3666, "lr": 4.273645946660652e-05, "epoch": 3.240619902120718, "percentage": 32.41, "elapsed_time": "2:41:46", "remaining_time": "5:37:25", "throughput": 4417.63, "total_tokens": 42879264} {"current_steps": 19870, "total_steps": 61300, "loss": 0.3386, "lr": 4.273144236872308e-05, "epoch": 3.2414355628058726, "percentage": 32.41, "elapsed_time": "2:41:48", "remaining_time": "5:37:23", "throughput": 4417.74, "total_tokens": 42890816} {"current_steps": 19875, "total_steps": 61300, "loss": 0.3625, "lr": 4.2726423833438964e-05, "epoch": 3.242251223491028, "percentage": 32.42, "elapsed_time": "2:41:51", "remaining_time": "5:37:20", "throughput": 4417.84, "total_tokens": 42902400} {"current_steps": 19880, "total_steps": 61300, "loss": 0.3552, "lr": 4.272140386116098e-05, "epoch": 3.2430668841761827, "percentage": 32.43, "elapsed_time": "2:41:53", "remaining_time": "5:37:17", "throughput": 4417.93, "total_tokens": 42913152} {"current_steps": 19885, "total_steps": 61300, "loss": 0.3411, "lr": 4.2716382452296086e-05, "epoch": 3.2438825448613375, "percentage": 32.44, "elapsed_time": "2:41:55", "remaining_time": "5:37:15", "throughput": 4418.04, "total_tokens": 42924672} {"current_steps": 19890, "total_steps": 61300, "loss": 0.3254, "lr": 4.271135960725133e-05, "epoch": 3.244698205546493, "percentage": 32.45, "elapsed_time": "2:41:57", "remaining_time": "5:37:12", "throughput": 4418.13, "total_tokens": 42934880} {"current_steps": 19895, "total_steps": 61300, "loss": 0.334, "lr": 4.270633532643391e-05, "epoch": 3.2455138662316476, "percentage": 32.46, "elapsed_time": "2:42:00", "remaining_time": "5:37:09", "throughput": 4418.22, "total_tokens": 42946176} {"current_steps": 19900, "total_steps": 61300, "loss": 0.319, "lr": 4.27013096102511e-05, "epoch": 3.2463295269168024, "percentage": 32.46, "elapsed_time": "2:42:02", "remaining_time": "5:37:07", "throughput": 4418.33, "total_tokens": 42958016} {"current_steps": 19905, "total_steps": 61300, "loss": 0.3131, "lr": 4.269628245911031e-05, "epoch": 3.2471451876019577, "percentage": 32.47, "elapsed_time": "2:42:04", "remaining_time": "5:37:04", "throughput": 4418.42, "total_tokens": 42968320} {"current_steps": 19910, "total_steps": 61300, "loss": 0.3728, "lr": 4.269125387341909e-05, "epoch": 3.2479608482871125, "percentage": 32.48, "elapsed_time": "2:42:07", "remaining_time": "5:37:01", "throughput": 4418.53, "total_tokens": 42980096} {"current_steps": 19915, "total_steps": 61300, "loss": 0.3263, "lr": 4.268622385358506e-05, "epoch": 3.2487765089722673, "percentage": 32.49, "elapsed_time": "2:42:09", "remaining_time": "5:36:58", "throughput": 4418.61, "total_tokens": 42990304} {"current_steps": 19920, "total_steps": 61300, "loss": 0.3001, "lr": 4.268119240001598e-05, "epoch": 3.2495921696574226, "percentage": 32.5, "elapsed_time": "2:42:11", "remaining_time": "5:36:55", "throughput": 4418.69, "total_tokens": 43001280} {"current_steps": 19925, "total_steps": 61300, "loss": 0.3535, "lr": 4.267615951311974e-05, "epoch": 3.2504078303425774, "percentage": 32.5, "elapsed_time": "2:42:13", "remaining_time": "5:36:52", "throughput": 4418.77, "total_tokens": 43011584} {"current_steps": 19930, "total_steps": 61300, "loss": 0.3394, "lr": 4.267112519330432e-05, "epoch": 3.2512234910277327, "percentage": 32.51, "elapsed_time": "2:42:16", "remaining_time": "5:36:49", "throughput": 4418.86, "total_tokens": 43022432} {"current_steps": 19935, "total_steps": 61300, "loss": 0.3443, "lr": 4.266608944097782e-05, "epoch": 3.2520391517128875, "percentage": 32.52, "elapsed_time": "2:42:18", "remaining_time": "5:36:47", "throughput": 4418.95, "total_tokens": 43033792} {"current_steps": 19940, "total_steps": 61300, "loss": 0.3847, "lr": 4.266105225654848e-05, "epoch": 3.2528548123980423, "percentage": 32.53, "elapsed_time": "2:42:20", "remaining_time": "5:36:44", "throughput": 4419.04, "total_tokens": 43045504} {"current_steps": 19945, "total_steps": 61300, "loss": 0.2992, "lr": 4.265601364042463e-05, "epoch": 3.2536704730831976, "percentage": 32.54, "elapsed_time": "2:42:23", "remaining_time": "5:36:42", "throughput": 4419.12, "total_tokens": 43056544} {"current_steps": 19950, "total_steps": 61300, "loss": 0.3517, "lr": 4.2650973593014734e-05, "epoch": 3.2544861337683524, "percentage": 32.54, "elapsed_time": "2:42:25", "remaining_time": "5:36:38", "throughput": 4419.19, "total_tokens": 43065184} {"current_steps": 19955, "total_steps": 61300, "loss": 0.3687, "lr": 4.264593211472735e-05, "epoch": 3.255301794453507, "percentage": 32.55, "elapsed_time": "2:42:27", "remaining_time": "5:36:35", "throughput": 4419.24, "total_tokens": 43074784} {"current_steps": 19960, "total_steps": 61300, "loss": 0.3453, "lr": 4.264088920597118e-05, "epoch": 3.2561174551386625, "percentage": 32.56, "elapsed_time": "2:42:29", "remaining_time": "5:36:31", "throughput": 4419.33, "total_tokens": 43084864} {"current_steps": 19965, "total_steps": 61300, "loss": 0.3122, "lr": 4.263584486715503e-05, "epoch": 3.2569331158238173, "percentage": 32.57, "elapsed_time": "2:42:31", "remaining_time": "5:36:29", "throughput": 4419.44, "total_tokens": 43096576} {"current_steps": 19970, "total_steps": 61300, "loss": 0.3601, "lr": 4.2630799098687804e-05, "epoch": 3.257748776508972, "percentage": 32.58, "elapsed_time": "2:42:33", "remaining_time": "5:36:26", "throughput": 4419.53, "total_tokens": 43106816} {"current_steps": 19975, "total_steps": 61300, "loss": 0.3058, "lr": 4.262575190097854e-05, "epoch": 3.2585644371941274, "percentage": 32.59, "elapsed_time": "2:42:36", "remaining_time": "5:36:23", "throughput": 4419.63, "total_tokens": 43118304} {"current_steps": 19980, "total_steps": 61300, "loss": 0.3272, "lr": 4.262070327443639e-05, "epoch": 3.259380097879282, "percentage": 32.59, "elapsed_time": "2:42:38", "remaining_time": "5:36:20", "throughput": 4419.71, "total_tokens": 43128384} {"current_steps": 19985, "total_steps": 61300, "loss": 0.3483, "lr": 4.261565321947064e-05, "epoch": 3.2601957585644374, "percentage": 32.6, "elapsed_time": "2:42:40", "remaining_time": "5:36:17", "throughput": 4419.81, "total_tokens": 43139136} {"current_steps": 19990, "total_steps": 61300, "loss": 0.3674, "lr": 4.261060173649065e-05, "epoch": 3.2610114192495923, "percentage": 32.61, "elapsed_time": "2:42:42", "remaining_time": "5:36:14", "throughput": 4419.9, "total_tokens": 43150048} {"current_steps": 19995, "total_steps": 61300, "loss": 0.3724, "lr": 4.260554882590594e-05, "epoch": 3.261827079934747, "percentage": 32.62, "elapsed_time": "2:42:44", "remaining_time": "5:36:11", "throughput": 4419.96, "total_tokens": 43159456} {"current_steps": 20000, "total_steps": 61300, "loss": 0.3546, "lr": 4.2600494488126104e-05, "epoch": 3.262642740619902, "percentage": 32.63, "elapsed_time": "2:42:47", "remaining_time": "5:36:08", "throughput": 4420.04, "total_tokens": 43170816} {"current_steps": 20005, "total_steps": 61300, "loss": 0.3584, "lr": 4.259543872356088e-05, "epoch": 3.263458401305057, "percentage": 32.63, "elapsed_time": "2:42:49", "remaining_time": "5:36:06", "throughput": 4420.14, "total_tokens": 43182336} {"current_steps": 20010, "total_steps": 61300, "loss": 0.3392, "lr": 4.259038153262012e-05, "epoch": 3.264274061990212, "percentage": 32.64, "elapsed_time": "2:42:51", "remaining_time": "5:36:03", "throughput": 4420.22, "total_tokens": 43192384} {"current_steps": 20015, "total_steps": 61300, "loss": 0.3528, "lr": 4.2585322915713774e-05, "epoch": 3.2650897226753672, "percentage": 32.65, "elapsed_time": "2:42:53", "remaining_time": "5:36:00", "throughput": 4420.32, "total_tokens": 43203744} {"current_steps": 20020, "total_steps": 61300, "loss": 0.3434, "lr": 4.258026287325192e-05, "epoch": 3.265905383360522, "percentage": 32.66, "elapsed_time": "2:42:55", "remaining_time": "5:35:57", "throughput": 4420.4, "total_tokens": 43213376} {"current_steps": 20025, "total_steps": 61300, "loss": 0.35, "lr": 4.2575201405644764e-05, "epoch": 3.266721044045677, "percentage": 32.67, "elapsed_time": "2:42:58", "remaining_time": "5:35:54", "throughput": 4420.49, "total_tokens": 43223744} {"current_steps": 20030, "total_steps": 61300, "loss": 0.3574, "lr": 4.257013851330261e-05, "epoch": 3.267536704730832, "percentage": 32.68, "elapsed_time": "2:43:00", "remaining_time": "5:35:51", "throughput": 4420.58, "total_tokens": 43234752} {"current_steps": 20035, "total_steps": 61300, "loss": 0.3693, "lr": 4.256507419663587e-05, "epoch": 3.268352365415987, "percentage": 32.68, "elapsed_time": "2:43:02", "remaining_time": "5:35:48", "throughput": 4420.65, "total_tokens": 43245280} {"current_steps": 20040, "total_steps": 61300, "loss": 0.36, "lr": 4.25600084560551e-05, "epoch": 3.2691680261011418, "percentage": 32.69, "elapsed_time": "2:43:04", "remaining_time": "5:35:45", "throughput": 4420.76, "total_tokens": 43256672} {"current_steps": 20045, "total_steps": 61300, "loss": 0.3478, "lr": 4.255494129197094e-05, "epoch": 3.269983686786297, "percentage": 32.7, "elapsed_time": "2:43:07", "remaining_time": "5:35:43", "throughput": 4420.86, "total_tokens": 43268288} {"current_steps": 20050, "total_steps": 61300, "loss": 0.3579, "lr": 4.254987270479417e-05, "epoch": 3.270799347471452, "percentage": 32.71, "elapsed_time": "2:43:09", "remaining_time": "5:35:40", "throughput": 4420.92, "total_tokens": 43278080} {"current_steps": 20055, "total_steps": 61300, "loss": 0.3298, "lr": 4.254480269493567e-05, "epoch": 3.2716150081566067, "percentage": 32.72, "elapsed_time": "2:43:11", "remaining_time": "5:35:36", "throughput": 4421.0, "total_tokens": 43287392} {"current_steps": 20060, "total_steps": 61300, "loss": 0.328, "lr": 4.253973126280644e-05, "epoch": 3.272430668841762, "percentage": 32.72, "elapsed_time": "2:43:13", "remaining_time": "5:35:33", "throughput": 4421.08, "total_tokens": 43297824} {"current_steps": 20065, "total_steps": 61300, "loss": 0.3325, "lr": 4.2534658408817595e-05, "epoch": 3.2732463295269167, "percentage": 32.73, "elapsed_time": "2:43:15", "remaining_time": "5:35:31", "throughput": 4421.18, "total_tokens": 43308864} {"current_steps": 20070, "total_steps": 61300, "loss": 0.3386, "lr": 4.252958413338038e-05, "epoch": 3.274061990212072, "percentage": 32.74, "elapsed_time": "2:43:17", "remaining_time": "5:35:27", "throughput": 4421.27, "total_tokens": 43318912} {"current_steps": 20075, "total_steps": 61300, "loss": 0.3471, "lr": 4.2524508436906124e-05, "epoch": 3.274877650897227, "percentage": 32.75, "elapsed_time": "2:43:19", "remaining_time": "5:35:24", "throughput": 4421.35, "total_tokens": 43328896} {"current_steps": 20080, "total_steps": 61300, "loss": 0.3441, "lr": 4.251943131980629e-05, "epoch": 3.2756933115823816, "percentage": 32.76, "elapsed_time": "2:43:22", "remaining_time": "5:35:22", "throughput": 4421.43, "total_tokens": 43340512} {"current_steps": 20085, "total_steps": 61300, "loss": 0.3629, "lr": 4.2514352782492475e-05, "epoch": 3.2765089722675365, "percentage": 32.77, "elapsed_time": "2:43:24", "remaining_time": "5:35:19", "throughput": 4421.51, "total_tokens": 43351840} {"current_steps": 20090, "total_steps": 61300, "loss": 0.3448, "lr": 4.250927282537635e-05, "epoch": 3.2773246329526917, "percentage": 32.77, "elapsed_time": "2:43:27", "remaining_time": "5:35:17", "throughput": 4421.6, "total_tokens": 43363328} {"current_steps": 20095, "total_steps": 61300, "loss": 0.3274, "lr": 4.2504191448869716e-05, "epoch": 3.2781402936378465, "percentage": 32.78, "elapsed_time": "2:43:29", "remaining_time": "5:35:14", "throughput": 4421.69, "total_tokens": 43374688} {"current_steps": 20100, "total_steps": 61300, "loss": 0.3201, "lr": 4.249910865338452e-05, "epoch": 3.278955954323002, "percentage": 32.79, "elapsed_time": "2:43:31", "remaining_time": "5:35:11", "throughput": 4421.77, "total_tokens": 43384832} {"current_steps": 20105, "total_steps": 61300, "loss": 0.362, "lr": 4.249402443933279e-05, "epoch": 3.2797716150081566, "percentage": 32.8, "elapsed_time": "2:43:34", "remaining_time": "5:35:08", "throughput": 4421.87, "total_tokens": 43396352} {"current_steps": 20110, "total_steps": 61300, "loss": 0.3801, "lr": 4.248893880712667e-05, "epoch": 3.2805872756933114, "percentage": 32.81, "elapsed_time": "2:43:36", "remaining_time": "5:35:05", "throughput": 4421.96, "total_tokens": 43407104} {"current_steps": 20115, "total_steps": 61300, "loss": 0.3184, "lr": 4.248385175717843e-05, "epoch": 3.2814029363784667, "percentage": 32.81, "elapsed_time": "2:43:38", "remaining_time": "5:35:03", "throughput": 4422.06, "total_tokens": 43418816} {"current_steps": 20120, "total_steps": 61300, "loss": 0.3454, "lr": 4.247876328990046e-05, "epoch": 3.2822185970636215, "percentage": 32.82, "elapsed_time": "2:43:40", "remaining_time": "5:35:00", "throughput": 4422.14, "total_tokens": 43429088} {"current_steps": 20125, "total_steps": 61300, "loss": 0.3278, "lr": 4.247367340570525e-05, "epoch": 3.2830342577487763, "percentage": 32.83, "elapsed_time": "2:43:43", "remaining_time": "5:34:57", "throughput": 4422.23, "total_tokens": 43439744} {"current_steps": 20130, "total_steps": 61300, "loss": 0.3607, "lr": 4.2468582105005413e-05, "epoch": 3.2838499184339316, "percentage": 32.84, "elapsed_time": "2:43:45", "remaining_time": "5:34:55", "throughput": 4422.33, "total_tokens": 43451264} {"current_steps": 20135, "total_steps": 61300, "loss": 0.3745, "lr": 4.246348938821367e-05, "epoch": 3.2846655791190864, "percentage": 32.85, "elapsed_time": "2:43:47", "remaining_time": "5:34:52", "throughput": 4422.4, "total_tokens": 43461696} {"current_steps": 20140, "total_steps": 61300, "loss": 0.2993, "lr": 4.2458395255742875e-05, "epoch": 3.2854812398042412, "percentage": 32.85, "elapsed_time": "2:43:49", "remaining_time": "5:34:48", "throughput": 4422.49, "total_tokens": 43471904} {"current_steps": 20145, "total_steps": 61300, "loss": 0.3343, "lr": 4.245329970800597e-05, "epoch": 3.2862969004893965, "percentage": 32.86, "elapsed_time": "2:43:51", "remaining_time": "5:34:46", "throughput": 4422.57, "total_tokens": 43482400} {"current_steps": 20150, "total_steps": 61300, "loss": 0.3263, "lr": 4.244820274541604e-05, "epoch": 3.2871125611745513, "percentage": 32.87, "elapsed_time": "2:43:54", "remaining_time": "5:34:42", "throughput": 4422.63, "total_tokens": 43492160} {"current_steps": 20155, "total_steps": 61300, "loss": 0.3528, "lr": 4.244310436838627e-05, "epoch": 3.2879282218597066, "percentage": 32.88, "elapsed_time": "2:43:56", "remaining_time": "5:34:39", "throughput": 4422.71, "total_tokens": 43502688} {"current_steps": 20160, "total_steps": 61300, "loss": 0.3416, "lr": 4.2438004577329946e-05, "epoch": 3.2887438825448614, "percentage": 32.89, "elapsed_time": "2:43:58", "remaining_time": "5:34:36", "throughput": 4422.79, "total_tokens": 43513184} {"current_steps": 20165, "total_steps": 61300, "loss": 0.3772, "lr": 4.243290337266049e-05, "epoch": 3.289559543230016, "percentage": 32.9, "elapsed_time": "2:44:00", "remaining_time": "5:34:33", "throughput": 4422.88, "total_tokens": 43522592} {"current_steps": 20170, "total_steps": 61300, "loss": 0.3366, "lr": 4.242780075479143e-05, "epoch": 3.2903752039151715, "percentage": 32.9, "elapsed_time": "2:44:02", "remaining_time": "5:34:30", "throughput": 4422.96, "total_tokens": 43533312} {"current_steps": 20175, "total_steps": 61300, "loss": 0.3434, "lr": 4.242269672413643e-05, "epoch": 3.2911908646003263, "percentage": 32.91, "elapsed_time": "2:44:04", "remaining_time": "5:34:27", "throughput": 4423.07, "total_tokens": 43543808} {"current_steps": 20180, "total_steps": 61300, "loss": 0.34, "lr": 4.241759128110922e-05, "epoch": 3.292006525285481, "percentage": 32.92, "elapsed_time": "2:44:06", "remaining_time": "5:34:24", "throughput": 4423.17, "total_tokens": 43554528} {"current_steps": 20185, "total_steps": 61300, "loss": 0.3539, "lr": 4.241248442612368e-05, "epoch": 3.2928221859706364, "percentage": 32.93, "elapsed_time": "2:44:09", "remaining_time": "5:34:21", "throughput": 4423.26, "total_tokens": 43564960} {"current_steps": 20190, "total_steps": 61300, "loss": 0.3559, "lr": 4.240737615959381e-05, "epoch": 3.293637846655791, "percentage": 32.94, "elapsed_time": "2:44:11", "remaining_time": "5:34:19", "throughput": 4423.36, "total_tokens": 43576576} {"current_steps": 20195, "total_steps": 61300, "loss": 0.331, "lr": 4.2402266481933706e-05, "epoch": 3.294453507340946, "percentage": 32.94, "elapsed_time": "2:44:14", "remaining_time": "5:34:16", "throughput": 4423.44, "total_tokens": 43588576} {"current_steps": 20200, "total_steps": 61300, "loss": 0.3485, "lr": 4.2397155393557574e-05, "epoch": 3.2952691680261013, "percentage": 32.95, "elapsed_time": "2:44:16", "remaining_time": "5:34:13", "throughput": 4423.5, "total_tokens": 43598912} {"current_steps": 20205, "total_steps": 61300, "loss": 0.3218, "lr": 4.239204289487976e-05, "epoch": 3.296084828711256, "percentage": 32.96, "elapsed_time": "2:44:18", "remaining_time": "5:34:11", "throughput": 4423.59, "total_tokens": 43609568} {"current_steps": 20210, "total_steps": 61300, "loss": 0.3394, "lr": 4.23869289863147e-05, "epoch": 3.2969004893964113, "percentage": 32.97, "elapsed_time": "2:44:20", "remaining_time": "5:34:08", "throughput": 4423.67, "total_tokens": 43619904} {"current_steps": 20215, "total_steps": 61300, "loss": 0.3539, "lr": 4.238181366827696e-05, "epoch": 3.297716150081566, "percentage": 32.98, "elapsed_time": "2:44:22", "remaining_time": "5:34:05", "throughput": 4423.75, "total_tokens": 43630976} {"current_steps": 20220, "total_steps": 61300, "loss": 0.3154, "lr": 4.237669694118121e-05, "epoch": 3.298531810766721, "percentage": 32.99, "elapsed_time": "2:44:24", "remaining_time": "5:34:01", "throughput": 4423.82, "total_tokens": 43640384} {"current_steps": 20225, "total_steps": 61300, "loss": 0.3838, "lr": 4.237157880544223e-05, "epoch": 3.299347471451876, "percentage": 32.99, "elapsed_time": "2:44:27", "remaining_time": "5:33:59", "throughput": 4423.9, "total_tokens": 43650912} {"current_steps": 20230, "total_steps": 61300, "loss": 0.3425, "lr": 4.2366459261474933e-05, "epoch": 3.300163132137031, "percentage": 33.0, "elapsed_time": "2:44:29", "remaining_time": "5:33:56", "throughput": 4423.98, "total_tokens": 43662368} {"current_steps": 20235, "total_steps": 61300, "loss": 0.3634, "lr": 4.2361338309694335e-05, "epoch": 3.300978792822186, "percentage": 33.01, "elapsed_time": "2:44:31", "remaining_time": "5:33:54", "throughput": 4424.08, "total_tokens": 43674048} {"current_steps": 20240, "total_steps": 61300, "loss": 0.3605, "lr": 4.235621595051556e-05, "epoch": 3.301794453507341, "percentage": 33.02, "elapsed_time": "2:44:34", "remaining_time": "5:33:51", "throughput": 4424.17, "total_tokens": 43685120} {"current_steps": 20245, "total_steps": 61300, "loss": 0.3463, "lr": 4.2351092184353855e-05, "epoch": 3.302610114192496, "percentage": 33.03, "elapsed_time": "2:44:36", "remaining_time": "5:33:48", "throughput": 4424.27, "total_tokens": 43696288} {"current_steps": 20250, "total_steps": 61300, "loss": 0.3038, "lr": 4.234596701162458e-05, "epoch": 3.3034257748776508, "percentage": 33.03, "elapsed_time": "2:44:38", "remaining_time": "5:33:46", "throughput": 4424.36, "total_tokens": 43708000} {"current_steps": 20255, "total_steps": 61300, "loss": 0.3472, "lr": 4.2340840432743206e-05, "epoch": 3.304241435562806, "percentage": 33.04, "elapsed_time": "2:44:41", "remaining_time": "5:33:43", "throughput": 4424.48, "total_tokens": 43720416} {"current_steps": 20260, "total_steps": 61300, "loss": 0.3306, "lr": 4.2335712448125316e-05, "epoch": 3.305057096247961, "percentage": 33.05, "elapsed_time": "2:44:43", "remaining_time": "5:33:40", "throughput": 4424.56, "total_tokens": 43730080} {"current_steps": 20265, "total_steps": 61300, "loss": 0.3608, "lr": 4.233058305818662e-05, "epoch": 3.3058727569331157, "percentage": 33.06, "elapsed_time": "2:44:45", "remaining_time": "5:33:37", "throughput": 4424.63, "total_tokens": 43740896} {"current_steps": 20270, "total_steps": 61300, "loss": 0.3504, "lr": 4.232545226334293e-05, "epoch": 3.306688417618271, "percentage": 33.07, "elapsed_time": "2:44:48", "remaining_time": "5:33:35", "throughput": 4424.73, "total_tokens": 43752128} {"current_steps": 20275, "total_steps": 61300, "loss": 0.3709, "lr": 4.232032006401017e-05, "epoch": 3.3075040783034257, "percentage": 33.08, "elapsed_time": "2:44:50", "remaining_time": "5:33:32", "throughput": 4424.82, "total_tokens": 43763008} {"current_steps": 20280, "total_steps": 61300, "loss": 0.3644, "lr": 4.231518646060438e-05, "epoch": 3.3083197389885806, "percentage": 33.08, "elapsed_time": "2:44:52", "remaining_time": "5:33:29", "throughput": 4424.91, "total_tokens": 43774144} {"current_steps": 20285, "total_steps": 61300, "loss": 0.3509, "lr": 4.231005145354172e-05, "epoch": 3.309135399673736, "percentage": 33.09, "elapsed_time": "2:44:55", "remaining_time": "5:33:27", "throughput": 4424.98, "total_tokens": 43785280} {"current_steps": 20290, "total_steps": 61300, "loss": 0.3688, "lr": 4.230491504323846e-05, "epoch": 3.3099510603588906, "percentage": 33.1, "elapsed_time": "2:44:57", "remaining_time": "5:33:24", "throughput": 4425.07, "total_tokens": 43796288} {"current_steps": 20295, "total_steps": 61300, "loss": 0.3162, "lr": 4.229977723011097e-05, "epoch": 3.310766721044046, "percentage": 33.11, "elapsed_time": "2:44:59", "remaining_time": "5:33:21", "throughput": 4425.18, "total_tokens": 43807392} {"current_steps": 20300, "total_steps": 61300, "loss": 0.3314, "lr": 4.2294638014575774e-05, "epoch": 3.3115823817292007, "percentage": 33.12, "elapsed_time": "2:45:02", "remaining_time": "5:33:19", "throughput": 4425.27, "total_tokens": 43819328} {"current_steps": 20305, "total_steps": 61300, "loss": 0.3429, "lr": 4.228949739704946e-05, "epoch": 3.3123980424143555, "percentage": 33.12, "elapsed_time": "2:45:04", "remaining_time": "5:33:16", "throughput": 4425.35, "total_tokens": 43829632} {"current_steps": 20310, "total_steps": 61300, "loss": 0.3584, "lr": 4.228435537794877e-05, "epoch": 3.3132137030995104, "percentage": 33.13, "elapsed_time": "2:45:06", "remaining_time": "5:33:13", "throughput": 4425.43, "total_tokens": 43839520} {"current_steps": 20315, "total_steps": 61300, "loss": 0.3482, "lr": 4.227921195769053e-05, "epoch": 3.3140293637846656, "percentage": 33.14, "elapsed_time": "2:45:08", "remaining_time": "5:33:10", "throughput": 4425.51, "total_tokens": 43850048} {"current_steps": 20320, "total_steps": 61300, "loss": 0.3723, "lr": 4.227406713669169e-05, "epoch": 3.3148450244698204, "percentage": 33.15, "elapsed_time": "2:45:10", "remaining_time": "5:33:07", "throughput": 4425.59, "total_tokens": 43860480} {"current_steps": 20325, "total_steps": 61300, "loss": 0.3474, "lr": 4.226892091536933e-05, "epoch": 3.3156606851549757, "percentage": 33.16, "elapsed_time": "2:45:12", "remaining_time": "5:33:04", "throughput": 4425.71, "total_tokens": 43871456} {"current_steps": 20330, "total_steps": 61300, "loss": 0.3364, "lr": 4.226377329414061e-05, "epoch": 3.3164763458401305, "percentage": 33.16, "elapsed_time": "2:45:15", "remaining_time": "5:33:01", "throughput": 4425.81, "total_tokens": 43882208} {"current_steps": 20335, "total_steps": 61300, "loss": 0.3418, "lr": 4.225862427342283e-05, "epoch": 3.3172920065252853, "percentage": 33.17, "elapsed_time": "2:45:17", "remaining_time": "5:32:58", "throughput": 4425.91, "total_tokens": 43893568} {"current_steps": 20340, "total_steps": 61300, "loss": 0.349, "lr": 4.2253473853633405e-05, "epoch": 3.3181076672104406, "percentage": 33.18, "elapsed_time": "2:45:19", "remaining_time": "5:32:55", "throughput": 4426.01, "total_tokens": 43904736} {"current_steps": 20345, "total_steps": 61300, "loss": 0.3342, "lr": 4.2248322035189835e-05, "epoch": 3.3189233278955954, "percentage": 33.19, "elapsed_time": "2:45:21", "remaining_time": "5:32:53", "throughput": 4426.09, "total_tokens": 43915232} {"current_steps": 20350, "total_steps": 61300, "loss": 0.3402, "lr": 4.224316881850977e-05, "epoch": 3.3197389885807502, "percentage": 33.2, "elapsed_time": "2:45:24", "remaining_time": "5:32:50", "throughput": 4426.18, "total_tokens": 43925664} {"current_steps": 20355, "total_steps": 61300, "loss": 0.338, "lr": 4.223801420401095e-05, "epoch": 3.3205546492659055, "percentage": 33.21, "elapsed_time": "2:45:26", "remaining_time": "5:32:47", "throughput": 4426.26, "total_tokens": 43936736} {"current_steps": 20360, "total_steps": 61300, "loss": 0.3658, "lr": 4.223285819211124e-05, "epoch": 3.3213703099510603, "percentage": 33.21, "elapsed_time": "2:45:28", "remaining_time": "5:32:44", "throughput": 4426.36, "total_tokens": 43948320} {"current_steps": 20365, "total_steps": 61300, "loss": 0.3344, "lr": 4.2227700783228594e-05, "epoch": 3.322185970636215, "percentage": 33.22, "elapsed_time": "2:45:30", "remaining_time": "5:32:41", "throughput": 4426.43, "total_tokens": 43958304} {"current_steps": 20370, "total_steps": 61300, "loss": 0.307, "lr": 4.222254197778112e-05, "epoch": 3.3230016313213704, "percentage": 33.23, "elapsed_time": "2:45:33", "remaining_time": "5:32:38", "throughput": 4426.52, "total_tokens": 43969120} {"current_steps": 20375, "total_steps": 61300, "loss": 0.3648, "lr": 4.2217381776187005e-05, "epoch": 3.323817292006525, "percentage": 33.24, "elapsed_time": "2:45:35", "remaining_time": "5:32:36", "throughput": 4426.61, "total_tokens": 43980768} {"current_steps": 20380, "total_steps": 61300, "loss": 0.3299, "lr": 4.2212220178864556e-05, "epoch": 3.3246329526916805, "percentage": 33.25, "elapsed_time": "2:45:37", "remaining_time": "5:32:33", "throughput": 4426.67, "total_tokens": 43991360} {"current_steps": 20385, "total_steps": 61300, "loss": 0.3497, "lr": 4.2207057186232215e-05, "epoch": 3.3254486133768353, "percentage": 33.25, "elapsed_time": "2:45:40", "remaining_time": "5:32:30", "throughput": 4426.77, "total_tokens": 44002464} {"current_steps": 20390, "total_steps": 61300, "loss": 0.3498, "lr": 4.220189279870851e-05, "epoch": 3.32626427406199, "percentage": 33.26, "elapsed_time": "2:45:41", "remaining_time": "5:32:27", "throughput": 4426.84, "total_tokens": 44011264} {"current_steps": 20395, "total_steps": 61300, "loss": 0.3374, "lr": 4.219672701671209e-05, "epoch": 3.3270799347471454, "percentage": 33.27, "elapsed_time": "2:45:44", "remaining_time": "5:32:24", "throughput": 4426.92, "total_tokens": 44021632} {"current_steps": 20400, "total_steps": 61300, "loss": 0.3072, "lr": 4.219155984066171e-05, "epoch": 3.3278955954323, "percentage": 33.28, "elapsed_time": "2:45:46", "remaining_time": "5:32:21", "throughput": 4427.0, "total_tokens": 44031872} {"current_steps": 20405, "total_steps": 61300, "loss": 0.3683, "lr": 4.218639127097628e-05, "epoch": 3.328711256117455, "percentage": 33.29, "elapsed_time": "2:45:48", "remaining_time": "5:32:19", "throughput": 4427.07, "total_tokens": 44044064} {"current_steps": 20410, "total_steps": 61300, "loss": 0.336, "lr": 4.218122130807476e-05, "epoch": 3.3295269168026103, "percentage": 33.3, "elapsed_time": "2:45:51", "remaining_time": "5:32:16", "throughput": 4427.17, "total_tokens": 44055488} {"current_steps": 20415, "total_steps": 61300, "loss": 0.337, "lr": 4.2176049952376265e-05, "epoch": 3.330342577487765, "percentage": 33.3, "elapsed_time": "2:45:53", "remaining_time": "5:32:13", "throughput": 4427.25, "total_tokens": 44066496} {"current_steps": 20420, "total_steps": 61300, "loss": 0.3634, "lr": 4.217087720430002e-05, "epoch": 3.33115823817292, "percentage": 33.31, "elapsed_time": "2:45:55", "remaining_time": "5:32:11", "throughput": 4427.34, "total_tokens": 44077664} {"current_steps": 20425, "total_steps": 61300, "loss": 0.305, "lr": 4.2165703064265335e-05, "epoch": 3.331973898858075, "percentage": 33.32, "elapsed_time": "2:45:58", "remaining_time": "5:32:08", "throughput": 4427.43, "total_tokens": 44089344} {"current_steps": 20430, "total_steps": 61300, "loss": 0.3249, "lr": 4.216052753269166e-05, "epoch": 3.33278955954323, "percentage": 33.33, "elapsed_time": "2:46:00", "remaining_time": "5:32:05", "throughput": 4427.51, "total_tokens": 44100288} {"current_steps": 20435, "total_steps": 61300, "loss": 0.3377, "lr": 4.215535060999856e-05, "epoch": 3.3336052202283852, "percentage": 33.34, "elapsed_time": "2:46:02", "remaining_time": "5:32:03", "throughput": 4427.6, "total_tokens": 44111040} {"current_steps": 20440, "total_steps": 61300, "loss": 0.3604, "lr": 4.215017229660569e-05, "epoch": 3.33442088091354, "percentage": 33.34, "elapsed_time": "2:46:05", "remaining_time": "5:32:00", "throughput": 4427.69, "total_tokens": 44122144} {"current_steps": 20445, "total_steps": 61300, "loss": 0.2868, "lr": 4.214499259293283e-05, "epoch": 3.335236541598695, "percentage": 33.35, "elapsed_time": "2:46:07", "remaining_time": "5:31:57", "throughput": 4427.78, "total_tokens": 44133344} {"current_steps": 20450, "total_steps": 61300, "loss": 0.3194, "lr": 4.213981149939988e-05, "epoch": 3.3360522022838497, "percentage": 33.36, "elapsed_time": "2:46:09", "remaining_time": "5:31:54", "throughput": 4427.86, "total_tokens": 44143520} {"current_steps": 20455, "total_steps": 61300, "loss": 0.3401, "lr": 4.213462901642685e-05, "epoch": 3.336867862969005, "percentage": 33.37, "elapsed_time": "2:46:11", "remaining_time": "5:31:51", "throughput": 4427.95, "total_tokens": 44154496} {"current_steps": 20460, "total_steps": 61300, "loss": 0.3019, "lr": 4.212944514443384e-05, "epoch": 3.3376835236541598, "percentage": 33.38, "elapsed_time": "2:46:14", "remaining_time": "5:31:49", "throughput": 4428.04, "total_tokens": 44165504} {"current_steps": 20465, "total_steps": 61300, "loss": 0.3925, "lr": 4.21242598838411e-05, "epoch": 3.338499184339315, "percentage": 33.38, "elapsed_time": "2:46:16", "remaining_time": "5:31:46", "throughput": 4428.14, "total_tokens": 44177472} {"current_steps": 20470, "total_steps": 61300, "loss": 0.3341, "lr": 4.211907323506897e-05, "epoch": 3.33931484502447, "percentage": 33.39, "elapsed_time": "2:46:18", "remaining_time": "5:31:43", "throughput": 4428.21, "total_tokens": 44187712} {"current_steps": 20475, "total_steps": 61300, "loss": 0.3011, "lr": 4.21138851985379e-05, "epoch": 3.3401305057096247, "percentage": 33.4, "elapsed_time": "2:46:21", "remaining_time": "5:31:41", "throughput": 4428.28, "total_tokens": 44198816} {"current_steps": 20480, "total_steps": 61300, "loss": 0.3309, "lr": 4.210869577466846e-05, "epoch": 3.34094616639478, "percentage": 33.41, "elapsed_time": "2:46:23", "remaining_time": "5:31:38", "throughput": 4428.36, "total_tokens": 44209600} {"current_steps": 20485, "total_steps": 61300, "loss": 0.3149, "lr": 4.210350496388133e-05, "epoch": 3.3417618270799347, "percentage": 33.42, "elapsed_time": "2:46:25", "remaining_time": "5:31:35", "throughput": 4428.44, "total_tokens": 44220768} {"current_steps": 20490, "total_steps": 61300, "loss": 0.3385, "lr": 4.2098312766597305e-05, "epoch": 3.3425774877650896, "percentage": 33.43, "elapsed_time": "2:46:27", "remaining_time": "5:31:33", "throughput": 4428.52, "total_tokens": 44231936} {"current_steps": 20495, "total_steps": 61300, "loss": 0.3938, "lr": 4.209311918323729e-05, "epoch": 3.343393148450245, "percentage": 33.43, "elapsed_time": "2:46:30", "remaining_time": "5:31:30", "throughput": 4428.62, "total_tokens": 44242912} {"current_steps": 20500, "total_steps": 61300, "loss": 0.3678, "lr": 4.208792421422231e-05, "epoch": 3.3442088091353996, "percentage": 33.44, "elapsed_time": "2:46:32", "remaining_time": "5:31:27", "throughput": 4428.71, "total_tokens": 44254144} {"current_steps": 20505, "total_steps": 61300, "loss": 0.338, "lr": 4.208272785997348e-05, "epoch": 3.3450244698205545, "percentage": 33.45, "elapsed_time": "2:46:34", "remaining_time": "5:31:24", "throughput": 4428.81, "total_tokens": 44264832} {"current_steps": 20510, "total_steps": 61300, "loss": 0.3401, "lr": 4.207753012091207e-05, "epoch": 3.3458401305057097, "percentage": 33.46, "elapsed_time": "2:46:37", "remaining_time": "5:31:22", "throughput": 4428.92, "total_tokens": 44276800} {"current_steps": 20515, "total_steps": 61300, "loss": 0.3784, "lr": 4.20723309974594e-05, "epoch": 3.3466557911908645, "percentage": 33.47, "elapsed_time": "2:46:39", "remaining_time": "5:31:19", "throughput": 4429.01, "total_tokens": 44287584} {"current_steps": 20520, "total_steps": 61300, "loss": 0.3069, "lr": 4.2067130490036964e-05, "epoch": 3.34747145187602, "percentage": 33.47, "elapsed_time": "2:46:41", "remaining_time": "5:31:16", "throughput": 4429.09, "total_tokens": 44298688} {"current_steps": 20525, "total_steps": 61300, "loss": 0.309, "lr": 4.206192859906633e-05, "epoch": 3.3482871125611746, "percentage": 33.48, "elapsed_time": "2:46:43", "remaining_time": "5:31:13", "throughput": 4429.18, "total_tokens": 44309184} {"current_steps": 20530, "total_steps": 61300, "loss": 0.3287, "lr": 4.205672532496919e-05, "epoch": 3.3491027732463294, "percentage": 33.49, "elapsed_time": "2:46:46", "remaining_time": "5:31:10", "throughput": 4429.27, "total_tokens": 44319872} {"current_steps": 20535, "total_steps": 61300, "loss": 0.3262, "lr": 4.205152066816736e-05, "epoch": 3.3499184339314847, "percentage": 33.5, "elapsed_time": "2:46:48", "remaining_time": "5:31:08", "throughput": 4429.34, "total_tokens": 44330432} {"current_steps": 20540, "total_steps": 61300, "loss": 0.3527, "lr": 4.204631462908274e-05, "epoch": 3.3507340946166395, "percentage": 33.51, "elapsed_time": "2:46:50", "remaining_time": "5:31:05", "throughput": 4429.44, "total_tokens": 44341920} {"current_steps": 20545, "total_steps": 61300, "loss": 0.3526, "lr": 4.2041107208137366e-05, "epoch": 3.3515497553017943, "percentage": 33.52, "elapsed_time": "2:46:52", "remaining_time": "5:31:02", "throughput": 4429.52, "total_tokens": 44352096} {"current_steps": 20550, "total_steps": 61300, "loss": 0.3484, "lr": 4.203589840575337e-05, "epoch": 3.3523654159869496, "percentage": 33.52, "elapsed_time": "2:46:55", "remaining_time": "5:30:59", "throughput": 4429.61, "total_tokens": 44363456} {"current_steps": 20555, "total_steps": 61300, "loss": 0.3507, "lr": 4.203068822235302e-05, "epoch": 3.3531810766721044, "percentage": 33.53, "elapsed_time": "2:46:57", "remaining_time": "5:30:57", "throughput": 4429.7, "total_tokens": 44375168} {"current_steps": 20560, "total_steps": 61300, "loss": 0.344, "lr": 4.2025476658358656e-05, "epoch": 3.3539967373572592, "percentage": 33.54, "elapsed_time": "2:46:59", "remaining_time": "5:30:54", "throughput": 4429.79, "total_tokens": 44385824} {"current_steps": 20565, "total_steps": 61300, "loss": 0.371, "lr": 4.202026371419278e-05, "epoch": 3.3548123980424145, "percentage": 33.55, "elapsed_time": "2:47:02", "remaining_time": "5:30:51", "throughput": 4429.87, "total_tokens": 44396736} {"current_steps": 20570, "total_steps": 61300, "loss": 0.3264, "lr": 4.201504939027796e-05, "epoch": 3.3556280587275693, "percentage": 33.56, "elapsed_time": "2:47:04", "remaining_time": "5:30:48", "throughput": 4429.96, "total_tokens": 44407648} {"current_steps": 20575, "total_steps": 61300, "loss": 0.3021, "lr": 4.20098336870369e-05, "epoch": 3.356443719412724, "percentage": 33.56, "elapsed_time": "2:47:06", "remaining_time": "5:30:46", "throughput": 4430.04, "total_tokens": 44418336} {"current_steps": 20580, "total_steps": 61300, "loss": 0.3239, "lr": 4.200461660489242e-05, "epoch": 3.3572593800978794, "percentage": 33.57, "elapsed_time": "2:47:08", "remaining_time": "5:30:43", "throughput": 4430.12, "total_tokens": 44428960} {"current_steps": 20585, "total_steps": 61300, "loss": 0.3045, "lr": 4.199939814426744e-05, "epoch": 3.358075040783034, "percentage": 33.58, "elapsed_time": "2:47:11", "remaining_time": "5:30:40", "throughput": 4430.21, "total_tokens": 44440608} {"current_steps": 20590, "total_steps": 61300, "loss": 0.3385, "lr": 4.1994178305584996e-05, "epoch": 3.358890701468189, "percentage": 33.59, "elapsed_time": "2:47:13", "remaining_time": "5:30:37", "throughput": 4430.28, "total_tokens": 44451040} {"current_steps": 20595, "total_steps": 61300, "loss": 0.3825, "lr": 4.198895708926822e-05, "epoch": 3.3597063621533443, "percentage": 33.6, "elapsed_time": "2:47:15", "remaining_time": "5:30:35", "throughput": 4430.38, "total_tokens": 44461792} {"current_steps": 20600, "total_steps": 61300, "loss": 0.3572, "lr": 4.198373449574039e-05, "epoch": 3.360522022838499, "percentage": 33.61, "elapsed_time": "2:47:17", "remaining_time": "5:30:32", "throughput": 4430.44, "total_tokens": 44472000} {"current_steps": 20605, "total_steps": 61300, "loss": 0.3528, "lr": 4.197851052542486e-05, "epoch": 3.3613376835236544, "percentage": 33.61, "elapsed_time": "2:47:20", "remaining_time": "5:30:29", "throughput": 4430.52, "total_tokens": 44482752} {"current_steps": 20610, "total_steps": 61300, "loss": 0.3598, "lr": 4.197328517874513e-05, "epoch": 3.362153344208809, "percentage": 33.62, "elapsed_time": "2:47:22", "remaining_time": "5:30:26", "throughput": 4430.63, "total_tokens": 44494624} {"current_steps": 20615, "total_steps": 61300, "loss": 0.3424, "lr": 4.1968058456124756e-05, "epoch": 3.362969004893964, "percentage": 33.63, "elapsed_time": "2:47:24", "remaining_time": "5:30:23", "throughput": 4430.71, "total_tokens": 44504256} {"current_steps": 20620, "total_steps": 61300, "loss": 0.3375, "lr": 4.196283035798749e-05, "epoch": 3.3637846655791193, "percentage": 33.64, "elapsed_time": "2:47:26", "remaining_time": "5:30:20", "throughput": 4430.8, "total_tokens": 44515680} {"current_steps": 20625, "total_steps": 61300, "loss": 0.3417, "lr": 4.1957600884757124e-05, "epoch": 3.364600326264274, "percentage": 33.65, "elapsed_time": "2:47:29", "remaining_time": "5:30:18", "throughput": 4430.9, "total_tokens": 44527360} {"current_steps": 20630, "total_steps": 61300, "loss": 0.3663, "lr": 4.195237003685759e-05, "epoch": 3.365415986949429, "percentage": 33.65, "elapsed_time": "2:47:31", "remaining_time": "5:30:15", "throughput": 4430.98, "total_tokens": 44537600} {"current_steps": 20635, "total_steps": 61300, "loss": 0.3349, "lr": 4.194713781471292e-05, "epoch": 3.366231647634584, "percentage": 33.66, "elapsed_time": "2:47:33", "remaining_time": "5:30:12", "throughput": 4431.08, "total_tokens": 44548704} {"current_steps": 20640, "total_steps": 61300, "loss": 0.3211, "lr": 4.194190421874727e-05, "epoch": 3.367047308319739, "percentage": 33.67, "elapsed_time": "2:47:35", "remaining_time": "5:30:09", "throughput": 4431.17, "total_tokens": 44559584} {"current_steps": 20645, "total_steps": 61300, "loss": 0.3293, "lr": 4.193666924938491e-05, "epoch": 3.367862969004894, "percentage": 33.68, "elapsed_time": "2:47:37", "remaining_time": "5:30:06", "throughput": 4431.22, "total_tokens": 44568576} {"current_steps": 20650, "total_steps": 61300, "loss": 0.3293, "lr": 4.1931432907050196e-05, "epoch": 3.368678629690049, "percentage": 33.69, "elapsed_time": "2:47:40", "remaining_time": "5:30:03", "throughput": 4431.32, "total_tokens": 44579968} {"current_steps": 20655, "total_steps": 61300, "loss": 0.3371, "lr": 4.192619519216763e-05, "epoch": 3.369494290375204, "percentage": 33.69, "elapsed_time": "2:47:42", "remaining_time": "5:30:01", "throughput": 4431.4, "total_tokens": 44591552} {"current_steps": 20660, "total_steps": 61300, "loss": 0.3533, "lr": 4.192095610516179e-05, "epoch": 3.370309951060359, "percentage": 33.7, "elapsed_time": "2:47:44", "remaining_time": "5:29:58", "throughput": 4431.48, "total_tokens": 44602016} {"current_steps": 20665, "total_steps": 61300, "loss": 0.3039, "lr": 4.1915715646457385e-05, "epoch": 3.371125611745514, "percentage": 33.71, "elapsed_time": "2:47:46", "remaining_time": "5:29:55", "throughput": 4431.57, "total_tokens": 44611936} {"current_steps": 20670, "total_steps": 61300, "loss": 0.3513, "lr": 4.191047381647925e-05, "epoch": 3.3719412724306688, "percentage": 33.72, "elapsed_time": "2:47:49", "remaining_time": "5:29:52", "throughput": 4431.65, "total_tokens": 44623232} {"current_steps": 20675, "total_steps": 61300, "loss": 0.3358, "lr": 4.190523061565231e-05, "epoch": 3.3727569331158236, "percentage": 33.73, "elapsed_time": "2:47:51", "remaining_time": "5:29:49", "throughput": 4431.75, "total_tokens": 44634592} {"current_steps": 20680, "total_steps": 61300, "loss": 0.3399, "lr": 4.189998604440159e-05, "epoch": 3.373572593800979, "percentage": 33.74, "elapsed_time": "2:47:53", "remaining_time": "5:29:47", "throughput": 4431.84, "total_tokens": 44645568} {"current_steps": 20685, "total_steps": 61300, "loss": 0.3078, "lr": 4.189474010315226e-05, "epoch": 3.3743882544861337, "percentage": 33.74, "elapsed_time": "2:47:56", "remaining_time": "5:29:44", "throughput": 4431.93, "total_tokens": 44656992} {"current_steps": 20690, "total_steps": 61300, "loss": 0.3269, "lr": 4.188949279232958e-05, "epoch": 3.375203915171289, "percentage": 33.75, "elapsed_time": "2:47:58", "remaining_time": "5:29:42", "throughput": 4432.03, "total_tokens": 44669248} {"current_steps": 20695, "total_steps": 61300, "loss": 0.3475, "lr": 4.188424411235891e-05, "epoch": 3.3760195758564437, "percentage": 33.76, "elapsed_time": "2:48:01", "remaining_time": "5:29:39", "throughput": 4432.13, "total_tokens": 44680864} {"current_steps": 20700, "total_steps": 61300, "loss": 0.3613, "lr": 4.1878994063665734e-05, "epoch": 3.3768352365415986, "percentage": 33.77, "elapsed_time": "2:48:03", "remaining_time": "5:29:36", "throughput": 4432.21, "total_tokens": 44691456} {"current_steps": 20705, "total_steps": 61300, "loss": 0.3451, "lr": 4.187374264667566e-05, "epoch": 3.377650897226754, "percentage": 33.78, "elapsed_time": "2:48:05", "remaining_time": "5:29:34", "throughput": 4432.3, "total_tokens": 44702336} {"current_steps": 20710, "total_steps": 61300, "loss": 0.3413, "lr": 4.1868489861814394e-05, "epoch": 3.3784665579119086, "percentage": 33.78, "elapsed_time": "2:48:07", "remaining_time": "5:29:31", "throughput": 4432.39, "total_tokens": 44713728} {"current_steps": 20715, "total_steps": 61300, "loss": 0.3501, "lr": 4.1863235709507755e-05, "epoch": 3.3792822185970635, "percentage": 33.79, "elapsed_time": "2:48:10", "remaining_time": "5:29:28", "throughput": 4432.48, "total_tokens": 44723968} {"current_steps": 20720, "total_steps": 61300, "loss": 0.3492, "lr": 4.1857980190181655e-05, "epoch": 3.3800978792822187, "percentage": 33.8, "elapsed_time": "2:48:12", "remaining_time": "5:29:25", "throughput": 4432.54, "total_tokens": 44734304} {"current_steps": 20725, "total_steps": 61300, "loss": 0.3375, "lr": 4.1852723304262145e-05, "epoch": 3.3809135399673735, "percentage": 33.81, "elapsed_time": "2:48:14", "remaining_time": "5:29:23", "throughput": 4432.62, "total_tokens": 44745568} {"current_steps": 20730, "total_steps": 61300, "loss": 0.3593, "lr": 4.1847465052175386e-05, "epoch": 3.3817292006525284, "percentage": 33.82, "elapsed_time": "2:48:17", "remaining_time": "5:29:20", "throughput": 4432.71, "total_tokens": 44757216} {"current_steps": 20735, "total_steps": 61300, "loss": 0.3236, "lr": 4.184220543434762e-05, "epoch": 3.3825448613376836, "percentage": 33.83, "elapsed_time": "2:48:19", "remaining_time": "5:29:17", "throughput": 4432.78, "total_tokens": 44767808} {"current_steps": 20740, "total_steps": 61300, "loss": 0.3495, "lr": 4.1836944451205215e-05, "epoch": 3.3833605220228384, "percentage": 33.83, "elapsed_time": "2:48:21", "remaining_time": "5:29:14", "throughput": 4432.88, "total_tokens": 44778208} {"current_steps": 20745, "total_steps": 61300, "loss": 0.3229, "lr": 4.1831682103174676e-05, "epoch": 3.3841761827079937, "percentage": 33.84, "elapsed_time": "2:48:23", "remaining_time": "5:29:11", "throughput": 4432.95, "total_tokens": 44788032} {"current_steps": 20750, "total_steps": 61300, "loss": 0.3304, "lr": 4.182641839068259e-05, "epoch": 3.3849918433931485, "percentage": 33.85, "elapsed_time": "2:48:25", "remaining_time": "5:29:08", "throughput": 4433.02, "total_tokens": 44797440} {"current_steps": 20755, "total_steps": 61300, "loss": 0.3185, "lr": 4.182115331415564e-05, "epoch": 3.3858075040783033, "percentage": 33.86, "elapsed_time": "2:48:27", "remaining_time": "5:29:05", "throughput": 4433.1, "total_tokens": 44809248} {"current_steps": 20760, "total_steps": 61300, "loss": 0.3201, "lr": 4.1815886874020646e-05, "epoch": 3.3866231647634586, "percentage": 33.87, "elapsed_time": "2:48:30", "remaining_time": "5:29:03", "throughput": 4433.19, "total_tokens": 44820768} {"current_steps": 20765, "total_steps": 61300, "loss": 0.3536, "lr": 4.181061907070455e-05, "epoch": 3.3874388254486134, "percentage": 33.87, "elapsed_time": "2:48:32", "remaining_time": "5:29:00", "throughput": 4433.28, "total_tokens": 44832128} {"current_steps": 20770, "total_steps": 61300, "loss": 0.3229, "lr": 4.180534990463437e-05, "epoch": 3.3882544861337682, "percentage": 33.88, "elapsed_time": "2:48:34", "remaining_time": "5:28:57", "throughput": 4433.35, "total_tokens": 44840992} {"current_steps": 20775, "total_steps": 61300, "loss": 0.3447, "lr": 4.1800079376237265e-05, "epoch": 3.3890701468189235, "percentage": 33.89, "elapsed_time": "2:48:36", "remaining_time": "5:28:53", "throughput": 4433.44, "total_tokens": 44851232} {"current_steps": 20780, "total_steps": 61300, "loss": 0.2992, "lr": 4.179480748594048e-05, "epoch": 3.3898858075040783, "percentage": 33.9, "elapsed_time": "2:48:38", "remaining_time": "5:28:50", "throughput": 4433.53, "total_tokens": 44860672} {"current_steps": 20785, "total_steps": 61300, "loss": 0.3708, "lr": 4.178953423417138e-05, "epoch": 3.390701468189233, "percentage": 33.91, "elapsed_time": "2:48:40", "remaining_time": "5:28:47", "throughput": 4433.63, "total_tokens": 44870688} {"current_steps": 20790, "total_steps": 61300, "loss": 0.3948, "lr": 4.1784259621357444e-05, "epoch": 3.3915171288743884, "percentage": 33.92, "elapsed_time": "2:48:42", "remaining_time": "5:28:44", "throughput": 4433.71, "total_tokens": 44881760} {"current_steps": 20795, "total_steps": 61300, "loss": 0.3372, "lr": 4.1778983647926274e-05, "epoch": 3.392332789559543, "percentage": 33.92, "elapsed_time": "2:48:45", "remaining_time": "5:28:42", "throughput": 4433.8, "total_tokens": 44892896} {"current_steps": 20800, "total_steps": 61300, "loss": 0.3802, "lr": 4.177370631430554e-05, "epoch": 3.393148450244698, "percentage": 33.93, "elapsed_time": "2:48:47", "remaining_time": "5:28:39", "throughput": 4433.86, "total_tokens": 44903296} {"current_steps": 20805, "total_steps": 61300, "loss": 0.3469, "lr": 4.176842762092307e-05, "epoch": 3.3939641109298533, "percentage": 33.94, "elapsed_time": "2:48:49", "remaining_time": "5:28:36", "throughput": 4433.93, "total_tokens": 44913664} {"current_steps": 20810, "total_steps": 61300, "loss": 0.3801, "lr": 4.176314756820677e-05, "epoch": 3.394779771615008, "percentage": 33.95, "elapsed_time": "2:48:51", "remaining_time": "5:28:33", "throughput": 4434.02, "total_tokens": 44924864} {"current_steps": 20815, "total_steps": 61300, "loss": 0.3488, "lr": 4.175786615658468e-05, "epoch": 3.395595432300163, "percentage": 33.96, "elapsed_time": "2:48:54", "remaining_time": "5:28:30", "throughput": 4434.08, "total_tokens": 44935008} {"current_steps": 20820, "total_steps": 61300, "loss": 0.3832, "lr": 4.175258338648493e-05, "epoch": 3.396411092985318, "percentage": 33.96, "elapsed_time": "2:48:56", "remaining_time": "5:28:27", "throughput": 4434.15, "total_tokens": 44945280} {"current_steps": 20825, "total_steps": 61300, "loss": 0.3634, "lr": 4.174729925833576e-05, "epoch": 3.397226753670473, "percentage": 33.97, "elapsed_time": "2:48:58", "remaining_time": "5:28:24", "throughput": 4434.24, "total_tokens": 44956064} {"current_steps": 20830, "total_steps": 61300, "loss": 0.3563, "lr": 4.174201377256555e-05, "epoch": 3.3980424143556283, "percentage": 33.98, "elapsed_time": "2:49:00", "remaining_time": "5:28:22", "throughput": 4434.33, "total_tokens": 44967424} {"current_steps": 20835, "total_steps": 61300, "loss": 0.3668, "lr": 4.173672692960274e-05, "epoch": 3.398858075040783, "percentage": 33.99, "elapsed_time": "2:49:02", "remaining_time": "5:28:19", "throughput": 4434.42, "total_tokens": 44977952} {"current_steps": 20840, "total_steps": 61300, "loss": 0.3355, "lr": 4.173143872987594e-05, "epoch": 3.399673735725938, "percentage": 34.0, "elapsed_time": "2:49:05", "remaining_time": "5:28:16", "throughput": 4434.47, "total_tokens": 44988384} {"current_steps": 20845, "total_steps": 61300, "loss": 0.3266, "lr": 4.172614917381381e-05, "epoch": 3.400489396411093, "percentage": 34.0, "elapsed_time": "2:49:07", "remaining_time": "5:28:13", "throughput": 4434.54, "total_tokens": 44998816} {"current_steps": 20850, "total_steps": 61300, "loss": 0.3655, "lr": 4.1720858261845166e-05, "epoch": 3.401305057096248, "percentage": 34.01, "elapsed_time": "2:49:09", "remaining_time": "5:28:10", "throughput": 4434.63, "total_tokens": 45010112} {"current_steps": 20855, "total_steps": 61300, "loss": 0.3648, "lr": 4.171556599439891e-05, "epoch": 3.402120717781403, "percentage": 34.02, "elapsed_time": "2:49:11", "remaining_time": "5:28:08", "throughput": 4434.72, "total_tokens": 45021184} {"current_steps": 20860, "total_steps": 61300, "loss": 0.3296, "lr": 4.1710272371904055e-05, "epoch": 3.402936378466558, "percentage": 34.03, "elapsed_time": "2:49:13", "remaining_time": "5:28:04", "throughput": 4434.8, "total_tokens": 45030976} {"current_steps": 20865, "total_steps": 61300, "loss": 0.3637, "lr": 4.170497739478974e-05, "epoch": 3.403752039151713, "percentage": 34.04, "elapsed_time": "2:49:16", "remaining_time": "5:28:02", "throughput": 4434.88, "total_tokens": 45042400} {"current_steps": 20870, "total_steps": 61300, "loss": 0.353, "lr": 4.16996810634852e-05, "epoch": 3.4045676998368677, "percentage": 34.05, "elapsed_time": "2:49:18", "remaining_time": "5:27:59", "throughput": 4434.94, "total_tokens": 45052352} {"current_steps": 20875, "total_steps": 61300, "loss": 0.35, "lr": 4.1694383378419774e-05, "epoch": 3.405383360522023, "percentage": 34.05, "elapsed_time": "2:49:20", "remaining_time": "5:27:56", "throughput": 4435.04, "total_tokens": 45063520} {"current_steps": 20880, "total_steps": 61300, "loss": 0.3538, "lr": 4.168908434002292e-05, "epoch": 3.4061990212071778, "percentage": 34.06, "elapsed_time": "2:49:22", "remaining_time": "5:27:53", "throughput": 4435.13, "total_tokens": 45074144} {"current_steps": 20885, "total_steps": 61300, "loss": 0.33, "lr": 4.168378394872422e-05, "epoch": 3.407014681892333, "percentage": 34.07, "elapsed_time": "2:49:25", "remaining_time": "5:27:50", "throughput": 4435.2, "total_tokens": 45084704} {"current_steps": 20890, "total_steps": 61300, "loss": 0.3265, "lr": 4.167848220495334e-05, "epoch": 3.407830342577488, "percentage": 34.08, "elapsed_time": "2:49:27", "remaining_time": "5:27:48", "throughput": 4435.3, "total_tokens": 45095744} {"current_steps": 20895, "total_steps": 61300, "loss": 0.3699, "lr": 4.167317910914006e-05, "epoch": 3.4086460032626427, "percentage": 34.09, "elapsed_time": "2:49:29", "remaining_time": "5:27:45", "throughput": 4435.37, "total_tokens": 45105952} {"current_steps": 20900, "total_steps": 61300, "loss": 0.3414, "lr": 4.166787466171429e-05, "epoch": 3.4094616639477975, "percentage": 34.09, "elapsed_time": "2:49:32", "remaining_time": "5:27:42", "throughput": 4435.47, "total_tokens": 45118080} {"current_steps": 20905, "total_steps": 61300, "loss": 0.3388, "lr": 4.166256886310602e-05, "epoch": 3.4102773246329527, "percentage": 34.1, "elapsed_time": "2:49:34", "remaining_time": "5:27:40", "throughput": 4435.56, "total_tokens": 45129024} {"current_steps": 20910, "total_steps": 61300, "loss": 0.3518, "lr": 4.165726171374538e-05, "epoch": 3.4110929853181076, "percentage": 34.11, "elapsed_time": "2:49:36", "remaining_time": "5:27:37", "throughput": 4435.63, "total_tokens": 45139200} {"current_steps": 20915, "total_steps": 61300, "loss": 0.3367, "lr": 4.165195321406259e-05, "epoch": 3.411908646003263, "percentage": 34.12, "elapsed_time": "2:49:38", "remaining_time": "5:27:34", "throughput": 4435.73, "total_tokens": 45150752} {"current_steps": 20920, "total_steps": 61300, "loss": 0.3257, "lr": 4.164664336448797e-05, "epoch": 3.4127243066884176, "percentage": 34.13, "elapsed_time": "2:49:41", "remaining_time": "5:27:31", "throughput": 4435.83, "total_tokens": 45162016} {"current_steps": 20925, "total_steps": 61300, "loss": 0.325, "lr": 4.164133216545199e-05, "epoch": 3.4135399673735725, "percentage": 34.14, "elapsed_time": "2:49:43", "remaining_time": "5:27:28", "throughput": 4435.9, "total_tokens": 45171904} {"current_steps": 20930, "total_steps": 61300, "loss": 0.3509, "lr": 4.163601961738517e-05, "epoch": 3.4143556280587277, "percentage": 34.14, "elapsed_time": "2:49:45", "remaining_time": "5:27:26", "throughput": 4435.99, "total_tokens": 45183712} {"current_steps": 20935, "total_steps": 61300, "loss": 0.3898, "lr": 4.16307057207182e-05, "epoch": 3.4151712887438825, "percentage": 34.15, "elapsed_time": "2:49:47", "remaining_time": "5:27:23", "throughput": 4436.08, "total_tokens": 45194656} {"current_steps": 20940, "total_steps": 61300, "loss": 0.3393, "lr": 4.162539047588183e-05, "epoch": 3.4159869494290374, "percentage": 34.16, "elapsed_time": "2:49:50", "remaining_time": "5:27:20", "throughput": 4436.15, "total_tokens": 45204800} {"current_steps": 20945, "total_steps": 61300, "loss": 0.335, "lr": 4.162007388330696e-05, "epoch": 3.4168026101141926, "percentage": 34.17, "elapsed_time": "2:49:52", "remaining_time": "5:27:17", "throughput": 4436.22, "total_tokens": 45215776} {"current_steps": 20950, "total_steps": 61300, "loss": 0.3218, "lr": 4.1614755943424575e-05, "epoch": 3.4176182707993474, "percentage": 34.18, "elapsed_time": "2:49:54", "remaining_time": "5:27:14", "throughput": 4436.29, "total_tokens": 45225952} {"current_steps": 20955, "total_steps": 61300, "loss": 0.3307, "lr": 4.160943665666577e-05, "epoch": 3.4184339314845023, "percentage": 34.18, "elapsed_time": "2:49:56", "remaining_time": "5:27:12", "throughput": 4436.38, "total_tokens": 45237312} {"current_steps": 20960, "total_steps": 61300, "loss": 0.3455, "lr": 4.160411602346175e-05, "epoch": 3.4192495921696575, "percentage": 34.19, "elapsed_time": "2:49:58", "remaining_time": "5:27:08", "throughput": 4436.46, "total_tokens": 45246912} {"current_steps": 20965, "total_steps": 61300, "loss": 0.3815, "lr": 4.159879404424384e-05, "epoch": 3.4200652528548123, "percentage": 34.2, "elapsed_time": "2:50:01", "remaining_time": "5:27:06", "throughput": 4436.53, "total_tokens": 45257440} {"current_steps": 20970, "total_steps": 61300, "loss": 0.3282, "lr": 4.159347071944346e-05, "epoch": 3.4208809135399676, "percentage": 34.21, "elapsed_time": "2:50:03", "remaining_time": "5:27:03", "throughput": 4436.61, "total_tokens": 45268416} {"current_steps": 20975, "total_steps": 61300, "loss": 0.3593, "lr": 4.158814604949215e-05, "epoch": 3.4216965742251224, "percentage": 34.22, "elapsed_time": "2:50:05", "remaining_time": "5:27:00", "throughput": 4436.69, "total_tokens": 45278848} {"current_steps": 20980, "total_steps": 61300, "loss": 0.3327, "lr": 4.158282003482156e-05, "epoch": 3.4225122349102772, "percentage": 34.23, "elapsed_time": "2:50:08", "remaining_time": "5:26:58", "throughput": 4436.79, "total_tokens": 45291072} {"current_steps": 20985, "total_steps": 61300, "loss": 0.3162, "lr": 4.157749267586343e-05, "epoch": 3.4233278955954325, "percentage": 34.23, "elapsed_time": "2:50:10", "remaining_time": "5:26:55", "throughput": 4436.87, "total_tokens": 45302336} {"current_steps": 20990, "total_steps": 61300, "loss": 0.3349, "lr": 4.1572163973049624e-05, "epoch": 3.4241435562805873, "percentage": 34.24, "elapsed_time": "2:50:12", "remaining_time": "5:26:52", "throughput": 4436.95, "total_tokens": 45312864} {"current_steps": 20995, "total_steps": 61300, "loss": 0.3515, "lr": 4.1566833926812135e-05, "epoch": 3.424959216965742, "percentage": 34.25, "elapsed_time": "2:50:14", "remaining_time": "5:26:49", "throughput": 4437.04, "total_tokens": 45323744} {"current_steps": 21000, "total_steps": 61300, "loss": 0.3732, "lr": 4.1561502537583016e-05, "epoch": 3.4257748776508974, "percentage": 34.26, "elapsed_time": "2:50:16", "remaining_time": "5:26:46", "throughput": 4437.12, "total_tokens": 45333760} {"current_steps": 21005, "total_steps": 61300, "loss": 0.3266, "lr": 4.155616980579447e-05, "epoch": 3.426590538336052, "percentage": 34.27, "elapsed_time": "2:50:19", "remaining_time": "5:26:44", "throughput": 4437.21, "total_tokens": 45344896} {"current_steps": 21010, "total_steps": 61300, "loss": 0.3447, "lr": 4.155083573187881e-05, "epoch": 3.427406199021207, "percentage": 34.27, "elapsed_time": "2:50:21", "remaining_time": "5:26:40", "throughput": 4437.29, "total_tokens": 45354336} {"current_steps": 21015, "total_steps": 61300, "loss": 0.342, "lr": 4.154550031626842e-05, "epoch": 3.4282218597063623, "percentage": 34.28, "elapsed_time": "2:50:23", "remaining_time": "5:26:38", "throughput": 4437.37, "total_tokens": 45365376} {"current_steps": 21020, "total_steps": 61300, "loss": 0.3632, "lr": 4.1540163559395816e-05, "epoch": 3.429037520391517, "percentage": 34.29, "elapsed_time": "2:50:25", "remaining_time": "5:26:35", "throughput": 4437.47, "total_tokens": 45376416} {"current_steps": 21025, "total_steps": 61300, "loss": 0.3696, "lr": 4.153482546169364e-05, "epoch": 3.429853181076672, "percentage": 34.3, "elapsed_time": "2:50:27", "remaining_time": "5:26:32", "throughput": 4437.54, "total_tokens": 45386272} {"current_steps": 21030, "total_steps": 61300, "loss": 0.3113, "lr": 4.15294860235946e-05, "epoch": 3.430668841761827, "percentage": 34.31, "elapsed_time": "2:50:29", "remaining_time": "5:26:28", "throughput": 4437.6, "total_tokens": 45395936} {"current_steps": 21035, "total_steps": 61300, "loss": 0.341, "lr": 4.152414524553156e-05, "epoch": 3.431484502446982, "percentage": 34.31, "elapsed_time": "2:50:32", "remaining_time": "5:26:26", "throughput": 4437.68, "total_tokens": 45407680} {"current_steps": 21040, "total_steps": 61300, "loss": 0.3416, "lr": 4.1518803127937464e-05, "epoch": 3.432300163132137, "percentage": 34.32, "elapsed_time": "2:50:34", "remaining_time": "5:26:23", "throughput": 4437.73, "total_tokens": 45417088} {"current_steps": 21045, "total_steps": 61300, "loss": 0.3098, "lr": 4.1513459671245384e-05, "epoch": 3.433115823817292, "percentage": 34.33, "elapsed_time": "2:50:36", "remaining_time": "5:26:21", "throughput": 4437.84, "total_tokens": 45429536} {"current_steps": 21050, "total_steps": 61300, "loss": 0.3238, "lr": 4.150811487588846e-05, "epoch": 3.433931484502447, "percentage": 34.34, "elapsed_time": "2:50:39", "remaining_time": "5:26:18", "throughput": 4437.92, "total_tokens": 45440320} {"current_steps": 21055, "total_steps": 61300, "loss": 0.3504, "lr": 4.150276874229999e-05, "epoch": 3.434747145187602, "percentage": 34.35, "elapsed_time": "2:50:41", "remaining_time": "5:26:15", "throughput": 4438.01, "total_tokens": 45451008} {"current_steps": 21060, "total_steps": 61300, "loss": 0.3233, "lr": 4.149742127091335e-05, "epoch": 3.435562805872757, "percentage": 34.36, "elapsed_time": "2:50:43", "remaining_time": "5:26:12", "throughput": 4438.11, "total_tokens": 45462432} {"current_steps": 21065, "total_steps": 61300, "loss": 0.3473, "lr": 4.149207246216203e-05, "epoch": 3.436378466557912, "percentage": 34.36, "elapsed_time": "2:50:45", "remaining_time": "5:26:09", "throughput": 4438.19, "total_tokens": 45472544} {"current_steps": 21070, "total_steps": 61300, "loss": 0.3486, "lr": 4.1486722316479635e-05, "epoch": 3.437194127243067, "percentage": 34.37, "elapsed_time": "2:50:47", "remaining_time": "5:26:06", "throughput": 4438.27, "total_tokens": 45483168} {"current_steps": 21075, "total_steps": 61300, "loss": 0.3735, "lr": 4.1481370834299884e-05, "epoch": 3.438009787928222, "percentage": 34.38, "elapsed_time": "2:50:49", "remaining_time": "5:26:03", "throughput": 4438.34, "total_tokens": 45492832} {"current_steps": 21080, "total_steps": 61300, "loss": 0.3725, "lr": 4.1476018016056583e-05, "epoch": 3.4388254486133767, "percentage": 34.39, "elapsed_time": "2:50:52", "remaining_time": "5:26:01", "throughput": 4438.43, "total_tokens": 45504064} {"current_steps": 21085, "total_steps": 61300, "loss": 0.3242, "lr": 4.1470663862183664e-05, "epoch": 3.439641109298532, "percentage": 34.4, "elapsed_time": "2:50:54", "remaining_time": "5:25:58", "throughput": 4438.5, "total_tokens": 45514336} {"current_steps": 21090, "total_steps": 61300, "loss": 0.3233, "lr": 4.146530837311516e-05, "epoch": 3.4404567699836868, "percentage": 34.4, "elapsed_time": "2:50:56", "remaining_time": "5:25:54", "throughput": 4438.59, "total_tokens": 45524480} {"current_steps": 21095, "total_steps": 61300, "loss": 0.3403, "lr": 4.145995154928521e-05, "epoch": 3.4412724306688416, "percentage": 34.41, "elapsed_time": "2:50:58", "remaining_time": "5:25:52", "throughput": 4438.66, "total_tokens": 45535264} {"current_steps": 21100, "total_steps": 61300, "loss": 0.3496, "lr": 4.1454593391128084e-05, "epoch": 3.442088091353997, "percentage": 34.42, "elapsed_time": "2:51:01", "remaining_time": "5:25:49", "throughput": 4438.76, "total_tokens": 45546560} {"current_steps": 21105, "total_steps": 61300, "loss": 0.3681, "lr": 4.144923389907812e-05, "epoch": 3.4429037520391517, "percentage": 34.43, "elapsed_time": "2:51:03", "remaining_time": "5:25:47", "throughput": 4438.85, "total_tokens": 45558016} {"current_steps": 21110, "total_steps": 61300, "loss": 0.3313, "lr": 4.1443873073569796e-05, "epoch": 3.443719412724307, "percentage": 34.44, "elapsed_time": "2:51:05", "remaining_time": "5:25:44", "throughput": 4438.91, "total_tokens": 45568512} {"current_steps": 21115, "total_steps": 61300, "loss": 0.3539, "lr": 4.143851091503768e-05, "epoch": 3.4445350734094617, "percentage": 34.45, "elapsed_time": "2:51:08", "remaining_time": "5:25:41", "throughput": 4439.0, "total_tokens": 45579968} {"current_steps": 21120, "total_steps": 61300, "loss": 0.3302, "lr": 4.1433147423916466e-05, "epoch": 3.4453507340946166, "percentage": 34.45, "elapsed_time": "2:51:10", "remaining_time": "5:25:39", "throughput": 4439.1, "total_tokens": 45592064} {"current_steps": 21125, "total_steps": 61300, "loss": 0.3235, "lr": 4.1427782600640943e-05, "epoch": 3.4461663947797714, "percentage": 34.46, "elapsed_time": "2:51:12", "remaining_time": "5:25:36", "throughput": 4439.19, "total_tokens": 45603040} {"current_steps": 21130, "total_steps": 61300, "loss": 0.348, "lr": 4.1422416445646e-05, "epoch": 3.4469820554649266, "percentage": 34.47, "elapsed_time": "2:51:15", "remaining_time": "5:25:33", "throughput": 4439.26, "total_tokens": 45613536} {"current_steps": 21135, "total_steps": 61300, "loss": 0.32, "lr": 4.141704895936666e-05, "epoch": 3.4477977161500815, "percentage": 34.48, "elapsed_time": "2:51:17", "remaining_time": "5:25:31", "throughput": 4439.34, "total_tokens": 45625120} {"current_steps": 21140, "total_steps": 61300, "loss": 0.3669, "lr": 4.141168014223803e-05, "epoch": 3.4486133768352367, "percentage": 34.49, "elapsed_time": "2:51:19", "remaining_time": "5:25:28", "throughput": 4439.43, "total_tokens": 45635744} {"current_steps": 21145, "total_steps": 61300, "loss": 0.3374, "lr": 4.1406309994695335e-05, "epoch": 3.4494290375203915, "percentage": 34.49, "elapsed_time": "2:51:21", "remaining_time": "5:25:25", "throughput": 4439.5, "total_tokens": 45646432} {"current_steps": 21150, "total_steps": 61300, "loss": 0.3398, "lr": 4.1400938517173905e-05, "epoch": 3.4502446982055464, "percentage": 34.5, "elapsed_time": "2:51:24", "remaining_time": "5:25:22", "throughput": 4439.57, "total_tokens": 45656576} {"current_steps": 21155, "total_steps": 61300, "loss": 0.3455, "lr": 4.139556571010919e-05, "epoch": 3.4510603588907016, "percentage": 34.51, "elapsed_time": "2:51:26", "remaining_time": "5:25:20", "throughput": 4439.66, "total_tokens": 45667904} {"current_steps": 21160, "total_steps": 61300, "loss": 0.3264, "lr": 4.139019157393672e-05, "epoch": 3.4518760195758564, "percentage": 34.52, "elapsed_time": "2:51:28", "remaining_time": "5:25:17", "throughput": 4439.74, "total_tokens": 45678528} {"current_steps": 21165, "total_steps": 61300, "loss": 0.3359, "lr": 4.138481610909216e-05, "epoch": 3.4526916802610113, "percentage": 34.53, "elapsed_time": "2:51:30", "remaining_time": "5:25:14", "throughput": 4439.82, "total_tokens": 45689312} {"current_steps": 21170, "total_steps": 61300, "loss": 0.3807, "lr": 4.137943931601127e-05, "epoch": 3.4535073409461665, "percentage": 34.54, "elapsed_time": "2:51:33", "remaining_time": "5:25:11", "throughput": 4439.9, "total_tokens": 45700160} {"current_steps": 21175, "total_steps": 61300, "loss": 0.3355, "lr": 4.1374061195129924e-05, "epoch": 3.4543230016313213, "percentage": 34.54, "elapsed_time": "2:51:35", "remaining_time": "5:25:08", "throughput": 4439.97, "total_tokens": 45710432} {"current_steps": 21180, "total_steps": 61300, "loss": 0.3468, "lr": 4.13686817468841e-05, "epoch": 3.455138662316476, "percentage": 34.55, "elapsed_time": "2:51:37", "remaining_time": "5:25:05", "throughput": 4440.05, "total_tokens": 45721248} {"current_steps": 21185, "total_steps": 61300, "loss": 0.3409, "lr": 4.1363300971709866e-05, "epoch": 3.4559543230016314, "percentage": 34.56, "elapsed_time": "2:51:39", "remaining_time": "5:25:03", "throughput": 4440.15, "total_tokens": 45732768} {"current_steps": 21190, "total_steps": 61300, "loss": 0.3367, "lr": 4.135791887004344e-05, "epoch": 3.4567699836867862, "percentage": 34.57, "elapsed_time": "2:51:42", "remaining_time": "5:25:00", "throughput": 4440.22, "total_tokens": 45743200} {"current_steps": 21195, "total_steps": 61300, "loss": 0.3347, "lr": 4.13525354423211e-05, "epoch": 3.4575856443719415, "percentage": 34.58, "elapsed_time": "2:51:44", "remaining_time": "5:24:57", "throughput": 4440.31, "total_tokens": 45753376} {"current_steps": 21200, "total_steps": 61300, "loss": 0.3336, "lr": 4.1347150688979275e-05, "epoch": 3.4584013050570963, "percentage": 34.58, "elapsed_time": "2:51:46", "remaining_time": "5:24:54", "throughput": 4440.38, "total_tokens": 45764064} {"current_steps": 21205, "total_steps": 61300, "loss": 0.376, "lr": 4.134176461045447e-05, "epoch": 3.459216965742251, "percentage": 34.59, "elapsed_time": "2:51:48", "remaining_time": "5:24:51", "throughput": 4440.47, "total_tokens": 45774944} {"current_steps": 21210, "total_steps": 61300, "loss": 0.3491, "lr": 4.133637720718331e-05, "epoch": 3.4600326264274064, "percentage": 34.6, "elapsed_time": "2:51:50", "remaining_time": "5:24:48", "throughput": 4440.56, "total_tokens": 45785856} {"current_steps": 21215, "total_steps": 61300, "loss": 0.3344, "lr": 4.133098847960252e-05, "epoch": 3.460848287112561, "percentage": 34.61, "elapsed_time": "2:51:53", "remaining_time": "5:24:46", "throughput": 4440.64, "total_tokens": 45796352} {"current_steps": 21220, "total_steps": 61300, "loss": 0.3553, "lr": 4.1325598428148935e-05, "epoch": 3.461663947797716, "percentage": 34.62, "elapsed_time": "2:51:55", "remaining_time": "5:24:43", "throughput": 4440.73, "total_tokens": 45808160} {"current_steps": 21225, "total_steps": 61300, "loss": 0.3757, "lr": 4.132020705325952e-05, "epoch": 3.4624796084828713, "percentage": 34.62, "elapsed_time": "2:51:57", "remaining_time": "5:24:41", "throughput": 4440.81, "total_tokens": 45819744} {"current_steps": 21230, "total_steps": 61300, "loss": 0.3465, "lr": 4.13148143553713e-05, "epoch": 3.463295269168026, "percentage": 34.63, "elapsed_time": "2:51:59", "remaining_time": "5:24:38", "throughput": 4440.9, "total_tokens": 45830048} {"current_steps": 21235, "total_steps": 61300, "loss": 0.3574, "lr": 4.130942033492146e-05, "epoch": 3.464110929853181, "percentage": 34.64, "elapsed_time": "2:52:02", "remaining_time": "5:24:35", "throughput": 4440.99, "total_tokens": 45841216} {"current_steps": 21240, "total_steps": 61300, "loss": 0.3454, "lr": 4.1304024992347245e-05, "epoch": 3.464926590538336, "percentage": 34.65, "elapsed_time": "2:52:04", "remaining_time": "5:24:32", "throughput": 4441.05, "total_tokens": 45850720} {"current_steps": 21245, "total_steps": 61300, "loss": 0.3413, "lr": 4.129862832808604e-05, "epoch": 3.465742251223491, "percentage": 34.66, "elapsed_time": "2:52:06", "remaining_time": "5:24:29", "throughput": 4441.13, "total_tokens": 45862272} {"current_steps": 21250, "total_steps": 61300, "loss": 0.3117, "lr": 4.129323034257533e-05, "epoch": 3.466557911908646, "percentage": 34.67, "elapsed_time": "2:52:08", "remaining_time": "5:24:26", "throughput": 4441.22, "total_tokens": 45872576} {"current_steps": 21255, "total_steps": 61300, "loss": 0.3536, "lr": 4.128783103625269e-05, "epoch": 3.467373572593801, "percentage": 34.67, "elapsed_time": "2:52:10", "remaining_time": "5:24:23", "throughput": 4441.28, "total_tokens": 45882816} {"current_steps": 21260, "total_steps": 61300, "loss": 0.3259, "lr": 4.128243040955583e-05, "epoch": 3.468189233278956, "percentage": 34.68, "elapsed_time": "2:52:13", "remaining_time": "5:24:21", "throughput": 4441.37, "total_tokens": 45893856} {"current_steps": 21265, "total_steps": 61300, "loss": 0.3833, "lr": 4.1277028462922535e-05, "epoch": 3.4690048939641107, "percentage": 34.69, "elapsed_time": "2:52:15", "remaining_time": "5:24:18", "throughput": 4441.44, "total_tokens": 45904128} {"current_steps": 21270, "total_steps": 61300, "loss": 0.3256, "lr": 4.127162519679073e-05, "epoch": 3.469820554649266, "percentage": 34.7, "elapsed_time": "2:52:17", "remaining_time": "5:24:15", "throughput": 4441.53, "total_tokens": 45914624} {"current_steps": 21275, "total_steps": 61300, "loss": 0.3404, "lr": 4.126622061159843e-05, "epoch": 3.470636215334421, "percentage": 34.71, "elapsed_time": "2:52:20", "remaining_time": "5:24:12", "throughput": 4441.62, "total_tokens": 45926432} {"current_steps": 21280, "total_steps": 61300, "loss": 0.3519, "lr": 4.126081470778375e-05, "epoch": 3.471451876019576, "percentage": 34.71, "elapsed_time": "2:52:22", "remaining_time": "5:24:09", "throughput": 4441.7, "total_tokens": 45936608} {"current_steps": 21285, "total_steps": 61300, "loss": 0.3553, "lr": 4.125540748578491e-05, "epoch": 3.472267536704731, "percentage": 34.72, "elapsed_time": "2:52:24", "remaining_time": "5:24:07", "throughput": 4441.81, "total_tokens": 45948768} {"current_steps": 21290, "total_steps": 61300, "loss": 0.3016, "lr": 4.124999894604028e-05, "epoch": 3.4730831973898857, "percentage": 34.73, "elapsed_time": "2:52:26", "remaining_time": "5:24:04", "throughput": 4441.86, "total_tokens": 45958080} {"current_steps": 21295, "total_steps": 61300, "loss": 0.3546, "lr": 4.124458908898827e-05, "epoch": 3.473898858075041, "percentage": 34.74, "elapsed_time": "2:52:28", "remaining_time": "5:24:01", "throughput": 4441.94, "total_tokens": 45968768} {"current_steps": 21300, "total_steps": 61300, "loss": 0.3415, "lr": 4.1239177915067454e-05, "epoch": 3.4747145187601958, "percentage": 34.75, "elapsed_time": "2:52:30", "remaining_time": "5:23:58", "throughput": 4442.03, "total_tokens": 45979360} {"current_steps": 21305, "total_steps": 61300, "loss": 0.3571, "lr": 4.123376542471648e-05, "epoch": 3.4755301794453506, "percentage": 34.76, "elapsed_time": "2:52:33", "remaining_time": "5:23:55", "throughput": 4442.11, "total_tokens": 45990880} {"current_steps": 21310, "total_steps": 61300, "loss": 0.3141, "lr": 4.122835161837409e-05, "epoch": 3.476345840130506, "percentage": 34.76, "elapsed_time": "2:52:35", "remaining_time": "5:23:53", "throughput": 4442.17, "total_tokens": 46001344} {"current_steps": 21315, "total_steps": 61300, "loss": 0.3191, "lr": 4.12229364964792e-05, "epoch": 3.4771615008156607, "percentage": 34.77, "elapsed_time": "2:52:38", "remaining_time": "5:23:50", "throughput": 4442.26, "total_tokens": 46013152} {"current_steps": 21320, "total_steps": 61300, "loss": 0.3357, "lr": 4.121752005947076e-05, "epoch": 3.4779771615008155, "percentage": 34.78, "elapsed_time": "2:52:40", "remaining_time": "5:23:47", "throughput": 4442.33, "total_tokens": 46023424} {"current_steps": 21325, "total_steps": 61300, "loss": 0.3514, "lr": 4.121210230778785e-05, "epoch": 3.4787928221859707, "percentage": 34.79, "elapsed_time": "2:52:42", "remaining_time": "5:23:44", "throughput": 4442.39, "total_tokens": 46033568} {"current_steps": 21330, "total_steps": 61300, "loss": 0.3339, "lr": 4.120668324186967e-05, "epoch": 3.4796084828711256, "percentage": 34.8, "elapsed_time": "2:52:44", "remaining_time": "5:23:42", "throughput": 4442.47, "total_tokens": 46045088} {"current_steps": 21335, "total_steps": 61300, "loss": 0.3199, "lr": 4.120126286215552e-05, "epoch": 3.480424143556281, "percentage": 34.8, "elapsed_time": "2:52:47", "remaining_time": "5:23:39", "throughput": 4442.58, "total_tokens": 46056640} {"current_steps": 21340, "total_steps": 61300, "loss": 0.3056, "lr": 4.119584116908478e-05, "epoch": 3.4812398042414356, "percentage": 34.81, "elapsed_time": "2:52:49", "remaining_time": "5:23:36", "throughput": 4442.66, "total_tokens": 46067008} {"current_steps": 21345, "total_steps": 61300, "loss": 0.4, "lr": 4.1190418163097e-05, "epoch": 3.4820554649265905, "percentage": 34.82, "elapsed_time": "2:52:51", "remaining_time": "5:23:34", "throughput": 4442.75, "total_tokens": 46078048} {"current_steps": 21350, "total_steps": 61300, "loss": 0.3605, "lr": 4.118499384463176e-05, "epoch": 3.4828711256117453, "percentage": 34.83, "elapsed_time": "2:52:53", "remaining_time": "5:23:31", "throughput": 4442.83, "total_tokens": 46089568} {"current_steps": 21355, "total_steps": 61300, "loss": 0.3555, "lr": 4.1179568214128805e-05, "epoch": 3.4836867862969005, "percentage": 34.84, "elapsed_time": "2:52:56", "remaining_time": "5:23:29", "throughput": 4442.92, "total_tokens": 46101024} {"current_steps": 21360, "total_steps": 61300, "loss": 0.3713, "lr": 4.117414127202795e-05, "epoch": 3.4845024469820554, "percentage": 34.85, "elapsed_time": "2:52:58", "remaining_time": "5:23:26", "throughput": 4442.99, "total_tokens": 46112064} {"current_steps": 21365, "total_steps": 61300, "loss": 0.3733, "lr": 4.116871301876914e-05, "epoch": 3.4853181076672106, "percentage": 34.85, "elapsed_time": "2:53:00", "remaining_time": "5:23:23", "throughput": 4443.07, "total_tokens": 46122080} {"current_steps": 21370, "total_steps": 61300, "loss": 0.3479, "lr": 4.116328345479241e-05, "epoch": 3.4861337683523654, "percentage": 34.86, "elapsed_time": "2:53:02", "remaining_time": "5:23:20", "throughput": 4443.16, "total_tokens": 46132992} {"current_steps": 21375, "total_steps": 61300, "loss": 0.3853, "lr": 4.115785258053792e-05, "epoch": 3.4869494290375203, "percentage": 34.87, "elapsed_time": "2:53:05", "remaining_time": "5:23:18", "throughput": 4443.26, "total_tokens": 46144576} {"current_steps": 21380, "total_steps": 61300, "loss": 0.3497, "lr": 4.1152420396445915e-05, "epoch": 3.4877650897226755, "percentage": 34.88, "elapsed_time": "2:53:07", "remaining_time": "5:23:15", "throughput": 4443.33, "total_tokens": 46155296} {"current_steps": 21385, "total_steps": 61300, "loss": 0.3685, "lr": 4.1146986902956745e-05, "epoch": 3.4885807504078303, "percentage": 34.89, "elapsed_time": "2:53:09", "remaining_time": "5:23:12", "throughput": 4443.42, "total_tokens": 46166528} {"current_steps": 21390, "total_steps": 61300, "loss": 0.369, "lr": 4.1141552100510896e-05, "epoch": 3.489396411092985, "percentage": 34.89, "elapsed_time": "2:53:11", "remaining_time": "5:23:09", "throughput": 4443.49, "total_tokens": 46176672} {"current_steps": 21395, "total_steps": 61300, "loss": 0.3218, "lr": 4.1136115989548926e-05, "epoch": 3.4902120717781404, "percentage": 34.9, "elapsed_time": "2:53:14", "remaining_time": "5:23:06", "throughput": 4443.56, "total_tokens": 46186880} {"current_steps": 21400, "total_steps": 61300, "loss": 0.3644, "lr": 4.113067857051153e-05, "epoch": 3.4910277324632952, "percentage": 34.91, "elapsed_time": "2:53:16", "remaining_time": "5:23:03", "throughput": 4443.63, "total_tokens": 46196320} {"current_steps": 21405, "total_steps": 61300, "loss": 0.3639, "lr": 4.112523984383948e-05, "epoch": 3.49184339314845, "percentage": 34.92, "elapsed_time": "2:53:18", "remaining_time": "5:23:00", "throughput": 4443.72, "total_tokens": 46207040} {"current_steps": 21410, "total_steps": 61300, "loss": 0.325, "lr": 4.111979980997366e-05, "epoch": 3.4926590538336053, "percentage": 34.93, "elapsed_time": "2:53:20", "remaining_time": "5:22:57", "throughput": 4443.79, "total_tokens": 46217248} {"current_steps": 21415, "total_steps": 61300, "loss": 0.3092, "lr": 4.1114358469355084e-05, "epoch": 3.49347471451876, "percentage": 34.93, "elapsed_time": "2:53:22", "remaining_time": "5:22:54", "throughput": 4443.86, "total_tokens": 46226688} {"current_steps": 21420, "total_steps": 61300, "loss": 0.3407, "lr": 4.110891582242485e-05, "epoch": 3.4942903752039154, "percentage": 34.94, "elapsed_time": "2:53:24", "remaining_time": "5:22:51", "throughput": 4443.95, "total_tokens": 46236768} {"current_steps": 21425, "total_steps": 61300, "loss": 0.3645, "lr": 4.1103471869624154e-05, "epoch": 3.49510603588907, "percentage": 34.95, "elapsed_time": "2:53:26", "remaining_time": "5:22:48", "throughput": 4444.03, "total_tokens": 46247872} {"current_steps": 21430, "total_steps": 61300, "loss": 0.3199, "lr": 4.109802661139433e-05, "epoch": 3.495921696574225, "percentage": 34.96, "elapsed_time": "2:53:29", "remaining_time": "5:22:45", "throughput": 4444.1, "total_tokens": 46258688} {"current_steps": 21435, "total_steps": 61300, "loss": 0.3109, "lr": 4.109258004817679e-05, "epoch": 3.4967373572593803, "percentage": 34.97, "elapsed_time": "2:53:31", "remaining_time": "5:22:42", "throughput": 4444.17, "total_tokens": 46269504} {"current_steps": 21440, "total_steps": 61300, "loss": 0.3641, "lr": 4.1087132180413047e-05, "epoch": 3.497553017944535, "percentage": 34.98, "elapsed_time": "2:53:33", "remaining_time": "5:22:40", "throughput": 4444.25, "total_tokens": 46280928} {"current_steps": 21445, "total_steps": 61300, "loss": 0.3625, "lr": 4.108168300854475e-05, "epoch": 3.49836867862969, "percentage": 34.98, "elapsed_time": "2:53:35", "remaining_time": "5:22:37", "throughput": 4444.34, "total_tokens": 46291648} {"current_steps": 21450, "total_steps": 61300, "loss": 0.3291, "lr": 4.1076232533013635e-05, "epoch": 3.499184339314845, "percentage": 34.99, "elapsed_time": "2:53:38", "remaining_time": "5:22:34", "throughput": 4444.41, "total_tokens": 46302592} {"current_steps": 21455, "total_steps": 61300, "loss": 0.3234, "lr": 4.1070780754261533e-05, "epoch": 3.5, "percentage": 35.0, "elapsed_time": "2:53:40", "remaining_time": "5:22:32", "throughput": 4444.47, "total_tokens": 46313216} {"current_steps": 21455, "total_steps": 61300, "eval_loss": 0.3399241268634796, "epoch": 3.5, "percentage": 35.0, "elapsed_time": "2:55:52", "remaining_time": "5:26:37", "throughput": 4388.9, "total_tokens": 46313216} {"current_steps": 21460, "total_steps": 61300, "loss": 0.3259, "lr": 4.10653276727304e-05, "epoch": 3.500815660685155, "percentage": 35.01, "elapsed_time": "2:55:55", "remaining_time": "5:26:35", "throughput": 4388.55, "total_tokens": 46322656} {"current_steps": 21465, "total_steps": 61300, "loss": 0.3861, "lr": 4.105987328886229e-05, "epoch": 3.50163132137031, "percentage": 35.02, "elapsed_time": "2:55:57", "remaining_time": "5:26:32", "throughput": 4388.64, "total_tokens": 46332576} {"current_steps": 21470, "total_steps": 61300, "loss": 0.3447, "lr": 4.1054417603099376e-05, "epoch": 3.502446982055465, "percentage": 35.02, "elapsed_time": "2:55:59", "remaining_time": "5:26:29", "throughput": 4388.75, "total_tokens": 46343584} {"current_steps": 21475, "total_steps": 61300, "loss": 0.3209, "lr": 4.104896061588391e-05, "epoch": 3.50326264274062, "percentage": 35.03, "elapsed_time": "2:56:01", "remaining_time": "5:26:26", "throughput": 4388.84, "total_tokens": 46354240} {"current_steps": 21480, "total_steps": 61300, "loss": 0.3341, "lr": 4.1043502327658256e-05, "epoch": 3.504078303425775, "percentage": 35.04, "elapsed_time": "2:56:04", "remaining_time": "5:26:23", "throughput": 4388.93, "total_tokens": 46364736} {"current_steps": 21485, "total_steps": 61300, "loss": 0.3274, "lr": 4.1038042738864906e-05, "epoch": 3.50489396411093, "percentage": 35.05, "elapsed_time": "2:56:06", "remaining_time": "5:26:20", "throughput": 4389.03, "total_tokens": 46374976} {"current_steps": 21490, "total_steps": 61300, "loss": 0.3716, "lr": 4.103258184994644e-05, "epoch": 3.5057096247960846, "percentage": 35.06, "elapsed_time": "2:56:08", "remaining_time": "5:26:17", "throughput": 4389.12, "total_tokens": 46386080} {"current_steps": 21495, "total_steps": 61300, "loss": 0.3413, "lr": 4.102711966134553e-05, "epoch": 3.50652528548124, "percentage": 35.07, "elapsed_time": "2:56:10", "remaining_time": "5:26:15", "throughput": 4389.21, "total_tokens": 46397152} {"current_steps": 21500, "total_steps": 61300, "loss": 0.3241, "lr": 4.102165617350498e-05, "epoch": 3.5073409461663947, "percentage": 35.07, "elapsed_time": "2:56:13", "remaining_time": "5:26:12", "throughput": 4389.31, "total_tokens": 46408480} {"current_steps": 21505, "total_steps": 61300, "loss": 0.3181, "lr": 4.101619138686769e-05, "epoch": 3.50815660685155, "percentage": 35.08, "elapsed_time": "2:56:15", "remaining_time": "5:26:09", "throughput": 4389.4, "total_tokens": 46419712} {"current_steps": 21510, "total_steps": 61300, "loss": 0.3149, "lr": 4.101072530187666e-05, "epoch": 3.5089722675367048, "percentage": 35.09, "elapsed_time": "2:56:17", "remaining_time": "5:26:07", "throughput": 4389.49, "total_tokens": 46431072} {"current_steps": 21515, "total_steps": 61300, "loss": 0.3966, "lr": 4.100525791897501e-05, "epoch": 3.5097879282218596, "percentage": 35.1, "elapsed_time": "2:56:19", "remaining_time": "5:26:04", "throughput": 4389.58, "total_tokens": 46441280} {"current_steps": 21520, "total_steps": 61300, "loss": 0.3248, "lr": 4.0999789238605925e-05, "epoch": 3.5106035889070144, "percentage": 35.11, "elapsed_time": "2:56:22", "remaining_time": "5:26:01", "throughput": 4389.67, "total_tokens": 46451808} {"current_steps": 21525, "total_steps": 61300, "loss": 0.3187, "lr": 4.099431926121276e-05, "epoch": 3.5114192495921697, "percentage": 35.11, "elapsed_time": "2:56:24", "remaining_time": "5:25:58", "throughput": 4389.78, "total_tokens": 46463136} {"current_steps": 21530, "total_steps": 61300, "loss": 0.3198, "lr": 4.098884798723891e-05, "epoch": 3.5122349102773245, "percentage": 35.12, "elapsed_time": "2:56:26", "remaining_time": "5:25:55", "throughput": 4389.87, "total_tokens": 46473280} {"current_steps": 21535, "total_steps": 61300, "loss": 0.3222, "lr": 4.098337541712791e-05, "epoch": 3.5130505709624797, "percentage": 35.13, "elapsed_time": "2:56:28", "remaining_time": "5:25:52", "throughput": 4389.95, "total_tokens": 46484032} {"current_steps": 21540, "total_steps": 61300, "loss": 0.362, "lr": 4.0977901551323414e-05, "epoch": 3.5138662316476346, "percentage": 35.14, "elapsed_time": "2:56:31", "remaining_time": "5:25:49", "throughput": 4390.06, "total_tokens": 46495488} {"current_steps": 21545, "total_steps": 61300, "loss": 0.3578, "lr": 4.097242639026914e-05, "epoch": 3.5146818923327894, "percentage": 35.15, "elapsed_time": "2:56:33", "remaining_time": "5:25:47", "throughput": 4390.16, "total_tokens": 46506944} {"current_steps": 21550, "total_steps": 61300, "loss": 0.418, "lr": 4.0966949934408946e-05, "epoch": 3.5154975530179446, "percentage": 35.15, "elapsed_time": "2:56:35", "remaining_time": "5:25:44", "throughput": 4390.24, "total_tokens": 46517216} {"current_steps": 21555, "total_steps": 61300, "loss": 0.356, "lr": 4.0961472184186766e-05, "epoch": 3.5163132137030995, "percentage": 35.16, "elapsed_time": "2:56:37", "remaining_time": "5:25:41", "throughput": 4390.36, "total_tokens": 46528864} {"current_steps": 21560, "total_steps": 61300, "loss": 0.3467, "lr": 4.0955993140046665e-05, "epoch": 3.5171288743882547, "percentage": 35.17, "elapsed_time": "2:56:40", "remaining_time": "5:25:38", "throughput": 4390.43, "total_tokens": 46539072} {"current_steps": 21565, "total_steps": 61300, "loss": 0.3092, "lr": 4.095051280243281e-05, "epoch": 3.5179445350734095, "percentage": 35.18, "elapsed_time": "2:56:42", "remaining_time": "5:25:35", "throughput": 4390.52, "total_tokens": 46550016} {"current_steps": 21570, "total_steps": 61300, "loss": 0.3639, "lr": 4.0945031171789435e-05, "epoch": 3.5187601957585644, "percentage": 35.19, "elapsed_time": "2:56:44", "remaining_time": "5:25:32", "throughput": 4390.61, "total_tokens": 46559968} {"current_steps": 21575, "total_steps": 61300, "loss": 0.3354, "lr": 4.0939548248560946e-05, "epoch": 3.519575856443719, "percentage": 35.2, "elapsed_time": "2:56:46", "remaining_time": "5:25:29", "throughput": 4390.71, "total_tokens": 46571456} {"current_steps": 21580, "total_steps": 61300, "loss": 0.353, "lr": 4.093406403319179e-05, "epoch": 3.5203915171288744, "percentage": 35.2, "elapsed_time": "2:56:49", "remaining_time": "5:25:27", "throughput": 4390.81, "total_tokens": 46583104} {"current_steps": 21585, "total_steps": 61300, "loss": 0.3338, "lr": 4.0928578526126566e-05, "epoch": 3.5212071778140293, "percentage": 35.21, "elapsed_time": "2:56:51", "remaining_time": "5:25:23", "throughput": 4390.88, "total_tokens": 46592384} {"current_steps": 21590, "total_steps": 61300, "loss": 0.3435, "lr": 4.092309172780994e-05, "epoch": 3.5220228384991845, "percentage": 35.22, "elapsed_time": "2:56:53", "remaining_time": "5:25:21", "throughput": 4390.96, "total_tokens": 46603488} {"current_steps": 21595, "total_steps": 61300, "loss": 0.3504, "lr": 4.09176036386867e-05, "epoch": 3.5228384991843393, "percentage": 35.23, "elapsed_time": "2:56:55", "remaining_time": "5:25:18", "throughput": 4391.04, "total_tokens": 46614528} {"current_steps": 21600, "total_steps": 61300, "loss": 0.3458, "lr": 4.091211425920175e-05, "epoch": 3.523654159869494, "percentage": 35.24, "elapsed_time": "2:56:58", "remaining_time": "5:25:15", "throughput": 4391.16, "total_tokens": 46625920} {"current_steps": 21605, "total_steps": 61300, "loss": 0.3522, "lr": 4.090662358980009e-05, "epoch": 3.5244698205546494, "percentage": 35.24, "elapsed_time": "2:57:00", "remaining_time": "5:25:12", "throughput": 4391.25, "total_tokens": 46636288} {"current_steps": 21610, "total_steps": 61300, "loss": 0.3485, "lr": 4.0901131630926794e-05, "epoch": 3.5252854812398042, "percentage": 35.25, "elapsed_time": "2:57:02", "remaining_time": "5:25:09", "throughput": 4391.31, "total_tokens": 46645536} {"current_steps": 21615, "total_steps": 61300, "loss": 0.3664, "lr": 4.089563838302709e-05, "epoch": 3.5261011419249595, "percentage": 35.26, "elapsed_time": "2:57:04", "remaining_time": "5:25:06", "throughput": 4391.37, "total_tokens": 46656224} {"current_steps": 21620, "total_steps": 61300, "loss": 0.3423, "lr": 4.089014384654629e-05, "epoch": 3.5269168026101143, "percentage": 35.27, "elapsed_time": "2:57:06", "remaining_time": "5:25:03", "throughput": 4391.44, "total_tokens": 46665920} {"current_steps": 21625, "total_steps": 61300, "loss": 0.3522, "lr": 4.088464802192981e-05, "epoch": 3.527732463295269, "percentage": 35.28, "elapsed_time": "2:57:08", "remaining_time": "5:25:00", "throughput": 4391.52, "total_tokens": 46676864} {"current_steps": 21630, "total_steps": 61300, "loss": 0.3299, "lr": 4.0879150909623156e-05, "epoch": 3.528548123980424, "percentage": 35.29, "elapsed_time": "2:57:11", "remaining_time": "5:24:57", "throughput": 4391.63, "total_tokens": 46688192} {"current_steps": 21635, "total_steps": 61300, "loss": 0.3465, "lr": 4.0873652510071955e-05, "epoch": 3.529363784665579, "percentage": 35.29, "elapsed_time": "2:57:13", "remaining_time": "5:24:54", "throughput": 4391.71, "total_tokens": 46698848} {"current_steps": 21640, "total_steps": 61300, "loss": 0.33, "lr": 4.086815282372195e-05, "epoch": 3.530179445350734, "percentage": 35.3, "elapsed_time": "2:57:15", "remaining_time": "5:24:52", "throughput": 4391.82, "total_tokens": 46709920} {"current_steps": 21645, "total_steps": 61300, "loss": 0.3202, "lr": 4.086265185101895e-05, "epoch": 3.5309951060358893, "percentage": 35.31, "elapsed_time": "2:57:18", "remaining_time": "5:24:49", "throughput": 4391.91, "total_tokens": 46721152} {"current_steps": 21650, "total_steps": 61300, "loss": 0.4049, "lr": 4.0857149592408914e-05, "epoch": 3.531810766721044, "percentage": 35.32, "elapsed_time": "2:57:20", "remaining_time": "5:24:46", "throughput": 4392.0, "total_tokens": 46732320} {"current_steps": 21655, "total_steps": 61300, "loss": 0.3505, "lr": 4.085164604833788e-05, "epoch": 3.532626427406199, "percentage": 35.33, "elapsed_time": "2:57:22", "remaining_time": "5:24:44", "throughput": 4392.11, "total_tokens": 46744032} {"current_steps": 21660, "total_steps": 61300, "loss": 0.3419, "lr": 4.084614121925198e-05, "epoch": 3.5334420880913537, "percentage": 35.33, "elapsed_time": "2:57:25", "remaining_time": "5:24:41", "throughput": 4392.22, "total_tokens": 46755584} {"current_steps": 21665, "total_steps": 61300, "loss": 0.3395, "lr": 4.084063510559746e-05, "epoch": 3.534257748776509, "percentage": 35.34, "elapsed_time": "2:57:27", "remaining_time": "5:24:38", "throughput": 4392.3, "total_tokens": 46766368} {"current_steps": 21670, "total_steps": 61300, "loss": 0.3557, "lr": 4.0835127707820696e-05, "epoch": 3.535073409461664, "percentage": 35.35, "elapsed_time": "2:57:29", "remaining_time": "5:24:36", "throughput": 4392.39, "total_tokens": 46777920} {"current_steps": 21675, "total_steps": 61300, "loss": 0.3231, "lr": 4.0829619026368134e-05, "epoch": 3.535889070146819, "percentage": 35.36, "elapsed_time": "2:57:32", "remaining_time": "5:24:33", "throughput": 4392.51, "total_tokens": 46789312} {"current_steps": 21680, "total_steps": 61300, "loss": 0.3226, "lr": 4.0824109061686325e-05, "epoch": 3.536704730831974, "percentage": 35.37, "elapsed_time": "2:57:34", "remaining_time": "5:24:30", "throughput": 4392.6, "total_tokens": 46800736} {"current_steps": 21685, "total_steps": 61300, "loss": 0.3403, "lr": 4.081859781422195e-05, "epoch": 3.5375203915171287, "percentage": 35.38, "elapsed_time": "2:57:36", "remaining_time": "5:24:28", "throughput": 4392.69, "total_tokens": 46812096} {"current_steps": 21690, "total_steps": 61300, "loss": 0.3125, "lr": 4.0813085284421774e-05, "epoch": 3.538336052202284, "percentage": 35.38, "elapsed_time": "2:57:39", "remaining_time": "5:24:25", "throughput": 4392.77, "total_tokens": 46822624} {"current_steps": 21695, "total_steps": 61300, "loss": 0.3567, "lr": 4.080757147273267e-05, "epoch": 3.539151712887439, "percentage": 35.39, "elapsed_time": "2:57:41", "remaining_time": "5:24:22", "throughput": 4392.87, "total_tokens": 46833760} {"current_steps": 21700, "total_steps": 61300, "loss": 0.382, "lr": 4.080205637960162e-05, "epoch": 3.539967373572594, "percentage": 35.4, "elapsed_time": "2:57:43", "remaining_time": "5:24:20", "throughput": 4392.97, "total_tokens": 46845312} {"current_steps": 21705, "total_steps": 61300, "loss": 0.373, "lr": 4.07965400054757e-05, "epoch": 3.540783034257749, "percentage": 35.41, "elapsed_time": "2:57:45", "remaining_time": "5:24:17", "throughput": 4393.06, "total_tokens": 46855904} {"current_steps": 21710, "total_steps": 61300, "loss": 0.3367, "lr": 4.0791022350802086e-05, "epoch": 3.5415986949429037, "percentage": 35.42, "elapsed_time": "2:57:47", "remaining_time": "5:24:13", "throughput": 4393.14, "total_tokens": 46865760} {"current_steps": 21715, "total_steps": 61300, "loss": 0.3664, "lr": 4.078550341602809e-05, "epoch": 3.5424143556280585, "percentage": 35.42, "elapsed_time": "2:57:50", "remaining_time": "5:24:11", "throughput": 4393.24, "total_tokens": 46877888} {"current_steps": 21720, "total_steps": 61300, "loss": 0.3523, "lr": 4.077998320160109e-05, "epoch": 3.5432300163132138, "percentage": 35.43, "elapsed_time": "2:57:52", "remaining_time": "5:24:08", "throughput": 4393.34, "total_tokens": 46889312} {"current_steps": 21725, "total_steps": 61300, "loss": 0.338, "lr": 4.077446170796858e-05, "epoch": 3.5440456769983686, "percentage": 35.44, "elapsed_time": "2:57:54", "remaining_time": "5:24:05", "throughput": 4393.42, "total_tokens": 46899392} {"current_steps": 21730, "total_steps": 61300, "loss": 0.314, "lr": 4.076893893557816e-05, "epoch": 3.544861337683524, "percentage": 35.45, "elapsed_time": "2:57:57", "remaining_time": "5:24:03", "throughput": 4393.52, "total_tokens": 46910784} {"current_steps": 21735, "total_steps": 61300, "loss": 0.3414, "lr": 4.076341488487755e-05, "epoch": 3.5456769983686787, "percentage": 35.46, "elapsed_time": "2:57:59", "remaining_time": "5:24:00", "throughput": 4393.61, "total_tokens": 46921920} {"current_steps": 21740, "total_steps": 61300, "loss": 0.3549, "lr": 4.0757889556314545e-05, "epoch": 3.5464926590538335, "percentage": 35.46, "elapsed_time": "2:58:01", "remaining_time": "5:23:57", "throughput": 4393.68, "total_tokens": 46931776} {"current_steps": 21745, "total_steps": 61300, "loss": 0.3409, "lr": 4.0752362950337054e-05, "epoch": 3.5473083197389887, "percentage": 35.47, "elapsed_time": "2:58:03", "remaining_time": "5:23:54", "throughput": 4393.78, "total_tokens": 46942848} {"current_steps": 21750, "total_steps": 61300, "loss": 0.3412, "lr": 4.0746835067393096e-05, "epoch": 3.5481239804241436, "percentage": 35.48, "elapsed_time": "2:58:06", "remaining_time": "5:23:51", "throughput": 4393.86, "total_tokens": 46953408} {"current_steps": 21755, "total_steps": 61300, "loss": 0.3412, "lr": 4.074130590793079e-05, "epoch": 3.5489396411092984, "percentage": 35.49, "elapsed_time": "2:58:08", "remaining_time": "5:23:48", "throughput": 4393.96, "total_tokens": 46964416} {"current_steps": 21760, "total_steps": 61300, "loss": 0.3287, "lr": 4.073577547239836e-05, "epoch": 3.5497553017944536, "percentage": 35.5, "elapsed_time": "2:58:10", "remaining_time": "5:23:45", "throughput": 4394.04, "total_tokens": 46974304} {"current_steps": 21765, "total_steps": 61300, "loss": 0.3593, "lr": 4.073024376124412e-05, "epoch": 3.5505709624796085, "percentage": 35.51, "elapsed_time": "2:58:12", "remaining_time": "5:23:42", "throughput": 4394.11, "total_tokens": 46984256} {"current_steps": 21770, "total_steps": 61300, "loss": 0.3307, "lr": 4.072471077491651e-05, "epoch": 3.5513866231647633, "percentage": 35.51, "elapsed_time": "2:58:14", "remaining_time": "5:23:39", "throughput": 4394.22, "total_tokens": 46995424} {"current_steps": 21775, "total_steps": 61300, "loss": 0.3083, "lr": 4.071917651386406e-05, "epoch": 3.5522022838499185, "percentage": 35.52, "elapsed_time": "2:58:17", "remaining_time": "5:23:37", "throughput": 4394.3, "total_tokens": 47006880} {"current_steps": 21780, "total_steps": 61300, "loss": 0.3451, "lr": 4.071364097853541e-05, "epoch": 3.5530179445350734, "percentage": 35.53, "elapsed_time": "2:58:19", "remaining_time": "5:23:33", "throughput": 4394.39, "total_tokens": 47016864} {"current_steps": 21785, "total_steps": 61300, "loss": 0.3414, "lr": 4.070810416937927e-05, "epoch": 3.5538336052202286, "percentage": 35.54, "elapsed_time": "2:58:21", "remaining_time": "5:23:31", "throughput": 4394.49, "total_tokens": 47029248} {"current_steps": 21790, "total_steps": 61300, "loss": 0.3504, "lr": 4.070256608684452e-05, "epoch": 3.5546492659053834, "percentage": 35.55, "elapsed_time": "2:58:24", "remaining_time": "5:23:29", "throughput": 4394.58, "total_tokens": 47040480} {"current_steps": 21795, "total_steps": 61300, "loss": 0.3364, "lr": 4.069702673138009e-05, "epoch": 3.5554649265905383, "percentage": 35.55, "elapsed_time": "2:58:26", "remaining_time": "5:23:26", "throughput": 4394.68, "total_tokens": 47051872} {"current_steps": 21800, "total_steps": 61300, "loss": 0.3243, "lr": 4.0691486103435025e-05, "epoch": 3.556280587275693, "percentage": 35.56, "elapsed_time": "2:58:28", "remaining_time": "5:23:23", "throughput": 4394.77, "total_tokens": 47063008} {"current_steps": 21805, "total_steps": 61300, "loss": 0.3357, "lr": 4.0685944203458476e-05, "epoch": 3.5570962479608483, "percentage": 35.57, "elapsed_time": "2:58:31", "remaining_time": "5:23:20", "throughput": 4394.87, "total_tokens": 47073792} {"current_steps": 21810, "total_steps": 61300, "loss": 0.3927, "lr": 4.06804010318997e-05, "epoch": 3.557911908646003, "percentage": 35.58, "elapsed_time": "2:58:33", "remaining_time": "5:23:18", "throughput": 4394.94, "total_tokens": 47084832} {"current_steps": 21815, "total_steps": 61300, "loss": 0.377, "lr": 4.0674856589208063e-05, "epoch": 3.5587275693311584, "percentage": 35.59, "elapsed_time": "2:58:35", "remaining_time": "5:23:15", "throughput": 4395.02, "total_tokens": 47096032} {"current_steps": 21820, "total_steps": 61300, "loss": 0.3573, "lr": 4.066931087583301e-05, "epoch": 3.5595432300163132, "percentage": 35.6, "elapsed_time": "2:58:38", "remaining_time": "5:23:12", "throughput": 4395.1, "total_tokens": 47106720} {"current_steps": 21825, "total_steps": 61300, "loss": 0.3267, "lr": 4.0663763892224114e-05, "epoch": 3.560358890701468, "percentage": 35.6, "elapsed_time": "2:58:40", "remaining_time": "5:23:10", "throughput": 4395.2, "total_tokens": 47118592} {"current_steps": 21830, "total_steps": 61300, "loss": 0.3448, "lr": 4.065821563883104e-05, "epoch": 3.5611745513866233, "percentage": 35.61, "elapsed_time": "2:58:42", "remaining_time": "5:23:07", "throughput": 4395.3, "total_tokens": 47129792} {"current_steps": 21835, "total_steps": 61300, "loss": 0.3449, "lr": 4.0652666116103556e-05, "epoch": 3.561990212071778, "percentage": 35.62, "elapsed_time": "2:58:44", "remaining_time": "5:23:04", "throughput": 4395.39, "total_tokens": 47140224} {"current_steps": 21840, "total_steps": 61300, "loss": 0.354, "lr": 4.064711532449153e-05, "epoch": 3.5628058727569334, "percentage": 35.63, "elapsed_time": "2:58:47", "remaining_time": "5:23:01", "throughput": 4395.49, "total_tokens": 47151904} {"current_steps": 21845, "total_steps": 61300, "loss": 0.3607, "lr": 4.0641563264444946e-05, "epoch": 3.563621533442088, "percentage": 35.64, "elapsed_time": "2:58:49", "remaining_time": "5:22:58", "throughput": 4395.56, "total_tokens": 47161920} {"current_steps": 21850, "total_steps": 61300, "loss": 0.3525, "lr": 4.063600993641389e-05, "epoch": 3.564437194127243, "percentage": 35.64, "elapsed_time": "2:58:51", "remaining_time": "5:22:55", "throughput": 4395.65, "total_tokens": 47172128} {"current_steps": 21855, "total_steps": 61300, "loss": 0.3242, "lr": 4.0630455340848525e-05, "epoch": 3.565252854812398, "percentage": 35.65, "elapsed_time": "2:58:53", "remaining_time": "5:22:52", "throughput": 4395.74, "total_tokens": 47182784} {"current_steps": 21860, "total_steps": 61300, "loss": 0.3772, "lr": 4.062489947819914e-05, "epoch": 3.566068515497553, "percentage": 35.66, "elapsed_time": "2:58:56", "remaining_time": "5:22:50", "throughput": 4395.83, "total_tokens": 47194336} {"current_steps": 21865, "total_steps": 61300, "loss": 0.3626, "lr": 4.061934234891612e-05, "epoch": 3.566884176182708, "percentage": 35.67, "elapsed_time": "2:58:58", "remaining_time": "5:22:47", "throughput": 4395.91, "total_tokens": 47204832} {"current_steps": 21870, "total_steps": 61300, "loss": 0.3248, "lr": 4.0613783953449966e-05, "epoch": 3.567699836867863, "percentage": 35.68, "elapsed_time": "2:59:00", "remaining_time": "5:22:44", "throughput": 4395.99, "total_tokens": 47215648} {"current_steps": 21875, "total_steps": 61300, "loss": 0.3302, "lr": 4.0608224292251264e-05, "epoch": 3.568515497553018, "percentage": 35.69, "elapsed_time": "2:59:02", "remaining_time": "5:22:41", "throughput": 4396.06, "total_tokens": 47226080} {"current_steps": 21880, "total_steps": 61300, "loss": 0.3407, "lr": 4.0602663365770696e-05, "epoch": 3.569331158238173, "percentage": 35.69, "elapsed_time": "2:59:05", "remaining_time": "5:22:39", "throughput": 4396.18, "total_tokens": 47238112} {"current_steps": 21885, "total_steps": 61300, "loss": 0.3739, "lr": 4.0597101174459074e-05, "epoch": 3.5701468189233276, "percentage": 35.7, "elapsed_time": "2:59:07", "remaining_time": "5:22:36", "throughput": 4396.27, "total_tokens": 47249216} {"current_steps": 21890, "total_steps": 61300, "loss": 0.3399, "lr": 4.0591537718767284e-05, "epoch": 3.570962479608483, "percentage": 35.71, "elapsed_time": "2:59:09", "remaining_time": "5:22:33", "throughput": 4396.34, "total_tokens": 47259296} {"current_steps": 21895, "total_steps": 61300, "loss": 0.3431, "lr": 4.058597299914634e-05, "epoch": 3.5717781402936377, "percentage": 35.72, "elapsed_time": "2:59:11", "remaining_time": "5:22:30", "throughput": 4396.44, "total_tokens": 47270336} {"current_steps": 21900, "total_steps": 61300, "loss": 0.3429, "lr": 4.0580407016047345e-05, "epoch": 3.572593800978793, "percentage": 35.73, "elapsed_time": "2:59:14", "remaining_time": "5:22:27", "throughput": 4396.55, "total_tokens": 47280736} {"current_steps": 21905, "total_steps": 61300, "loss": 0.3952, "lr": 4.0574839769921504e-05, "epoch": 3.573409461663948, "percentage": 35.73, "elapsed_time": "2:59:16", "remaining_time": "5:22:24", "throughput": 4396.63, "total_tokens": 47291328} {"current_steps": 21910, "total_steps": 61300, "loss": 0.337, "lr": 4.056927126122012e-05, "epoch": 3.5742251223491026, "percentage": 35.74, "elapsed_time": "2:59:18", "remaining_time": "5:22:21", "throughput": 4396.71, "total_tokens": 47302368} {"current_steps": 21915, "total_steps": 61300, "loss": 0.3188, "lr": 4.056370149039461e-05, "epoch": 3.575040783034258, "percentage": 35.75, "elapsed_time": "2:59:20", "remaining_time": "5:22:18", "throughput": 4396.79, "total_tokens": 47312768} {"current_steps": 21920, "total_steps": 61300, "loss": 0.3274, "lr": 4.05581304578965e-05, "epoch": 3.5758564437194127, "percentage": 35.76, "elapsed_time": "2:59:22", "remaining_time": "5:22:16", "throughput": 4396.88, "total_tokens": 47323520} {"current_steps": 21925, "total_steps": 61300, "loss": 0.3578, "lr": 4.055255816417738e-05, "epoch": 3.576672104404568, "percentage": 35.77, "elapsed_time": "2:59:25", "remaining_time": "5:22:13", "throughput": 4396.96, "total_tokens": 47334688} {"current_steps": 21930, "total_steps": 61300, "loss": 0.3557, "lr": 4.054698460968899e-05, "epoch": 3.5774877650897228, "percentage": 35.77, "elapsed_time": "2:59:27", "remaining_time": "5:22:10", "throughput": 4397.05, "total_tokens": 47345184} {"current_steps": 21935, "total_steps": 61300, "loss": 0.3715, "lr": 4.054140979488314e-05, "epoch": 3.5783034257748776, "percentage": 35.78, "elapsed_time": "2:59:29", "remaining_time": "5:22:07", "throughput": 4397.14, "total_tokens": 47356608} {"current_steps": 21940, "total_steps": 61300, "loss": 0.3313, "lr": 4.0535833720211755e-05, "epoch": 3.5791190864600324, "percentage": 35.79, "elapsed_time": "2:59:32", "remaining_time": "5:22:04", "throughput": 4397.24, "total_tokens": 47367520} {"current_steps": 21945, "total_steps": 61300, "loss": 0.3447, "lr": 4.053025638612686e-05, "epoch": 3.5799347471451877, "percentage": 35.8, "elapsed_time": "2:59:33", "remaining_time": "5:22:01", "throughput": 4397.29, "total_tokens": 47376288} {"current_steps": 21950, "total_steps": 61300, "loss": 0.3676, "lr": 4.052467779308058e-05, "epoch": 3.5807504078303425, "percentage": 35.81, "elapsed_time": "2:59:36", "remaining_time": "5:21:58", "throughput": 4397.38, "total_tokens": 47386592} {"current_steps": 21955, "total_steps": 61300, "loss": 0.328, "lr": 4.051909794152515e-05, "epoch": 3.5815660685154977, "percentage": 35.82, "elapsed_time": "2:59:38", "remaining_time": "5:21:55", "throughput": 4397.47, "total_tokens": 47397792} {"current_steps": 21960, "total_steps": 61300, "loss": 0.3488, "lr": 4.05135168319129e-05, "epoch": 3.5823817292006526, "percentage": 35.82, "elapsed_time": "2:59:40", "remaining_time": "5:21:53", "throughput": 4397.56, "total_tokens": 47409280} {"current_steps": 21965, "total_steps": 61300, "loss": 0.349, "lr": 4.050793446469626e-05, "epoch": 3.5831973898858074, "percentage": 35.83, "elapsed_time": "2:59:43", "remaining_time": "5:21:50", "throughput": 4397.63, "total_tokens": 47419680} {"current_steps": 21970, "total_steps": 61300, "loss": 0.3495, "lr": 4.0502350840327764e-05, "epoch": 3.5840130505709626, "percentage": 35.84, "elapsed_time": "2:59:45", "remaining_time": "5:21:47", "throughput": 4397.73, "total_tokens": 47431296} {"current_steps": 21975, "total_steps": 61300, "loss": 0.3512, "lr": 4.0496765959260055e-05, "epoch": 3.5848287112561175, "percentage": 35.85, "elapsed_time": "2:59:47", "remaining_time": "5:21:44", "throughput": 4397.81, "total_tokens": 47441824} {"current_steps": 21980, "total_steps": 61300, "loss": 0.3065, "lr": 4.049117982194586e-05, "epoch": 3.5856443719412723, "percentage": 35.86, "elapsed_time": "2:59:49", "remaining_time": "5:21:41", "throughput": 4397.87, "total_tokens": 47452192} {"current_steps": 21985, "total_steps": 61300, "loss": 0.3204, "lr": 4.048559242883804e-05, "epoch": 3.5864600326264275, "percentage": 35.86, "elapsed_time": "2:59:51", "remaining_time": "5:21:38", "throughput": 4397.93, "total_tokens": 47461696} {"current_steps": 21990, "total_steps": 61300, "loss": 0.332, "lr": 4.0480003780389507e-05, "epoch": 3.5872756933115824, "percentage": 35.87, "elapsed_time": "2:59:54", "remaining_time": "5:21:35", "throughput": 4398.02, "total_tokens": 47472960} {"current_steps": 21995, "total_steps": 61300, "loss": 0.3637, "lr": 4.0474413877053335e-05, "epoch": 3.588091353996737, "percentage": 35.88, "elapsed_time": "2:59:56", "remaining_time": "5:21:33", "throughput": 4398.1, "total_tokens": 47483712} {"current_steps": 22000, "total_steps": 61300, "loss": 0.3804, "lr": 4.0468822719282654e-05, "epoch": 3.5889070146818924, "percentage": 35.89, "elapsed_time": "2:59:58", "remaining_time": "5:21:30", "throughput": 4398.16, "total_tokens": 47493728} {"current_steps": 22005, "total_steps": 61300, "loss": 0.3696, "lr": 4.046323030753071e-05, "epoch": 3.5897226753670473, "percentage": 35.9, "elapsed_time": "3:00:00", "remaining_time": "5:21:27", "throughput": 4398.24, "total_tokens": 47504928} {"current_steps": 22010, "total_steps": 61300, "loss": 0.3454, "lr": 4.045763664225087e-05, "epoch": 3.5905383360522025, "percentage": 35.91, "elapsed_time": "3:00:02", "remaining_time": "5:21:24", "throughput": 4398.34, "total_tokens": 47514880} {"current_steps": 22015, "total_steps": 61300, "loss": 0.3408, "lr": 4.045204172389656e-05, "epoch": 3.5913539967373573, "percentage": 35.91, "elapsed_time": "3:00:05", "remaining_time": "5:21:21", "throughput": 4398.44, "total_tokens": 47526688} {"current_steps": 22020, "total_steps": 61300, "loss": 0.3742, "lr": 4.044644555292135e-05, "epoch": 3.592169657422512, "percentage": 35.92, "elapsed_time": "3:00:07", "remaining_time": "5:21:18", "throughput": 4398.51, "total_tokens": 47536768} {"current_steps": 22025, "total_steps": 61300, "loss": 0.3304, "lr": 4.04408481297789e-05, "epoch": 3.592985318107667, "percentage": 35.93, "elapsed_time": "3:00:09", "remaining_time": "5:21:16", "throughput": 4398.61, "total_tokens": 47548768} {"current_steps": 22030, "total_steps": 61300, "loss": 0.3395, "lr": 4.043524945492294e-05, "epoch": 3.5938009787928222, "percentage": 35.94, "elapsed_time": "3:00:12", "remaining_time": "5:21:13", "throughput": 4398.7, "total_tokens": 47559968} {"current_steps": 22035, "total_steps": 61300, "loss": 0.3372, "lr": 4.042964952880734e-05, "epoch": 3.594616639477977, "percentage": 35.95, "elapsed_time": "3:00:14", "remaining_time": "5:21:10", "throughput": 4398.78, "total_tokens": 47571040} {"current_steps": 22040, "total_steps": 61300, "loss": 0.3515, "lr": 4.042404835188607e-05, "epoch": 3.5954323001631323, "percentage": 35.95, "elapsed_time": "3:00:16", "remaining_time": "5:21:08", "throughput": 4398.9, "total_tokens": 47582816} {"current_steps": 22045, "total_steps": 61300, "loss": 0.355, "lr": 4.041844592461318e-05, "epoch": 3.596247960848287, "percentage": 35.96, "elapsed_time": "3:00:19", "remaining_time": "5:21:05", "throughput": 4398.98, "total_tokens": 47594112} {"current_steps": 22050, "total_steps": 61300, "loss": 0.3501, "lr": 4.0412842247442815e-05, "epoch": 3.597063621533442, "percentage": 35.97, "elapsed_time": "3:00:21", "remaining_time": "5:21:02", "throughput": 4399.07, "total_tokens": 47604320} {"current_steps": 22055, "total_steps": 61300, "loss": 0.3201, "lr": 4.040723732082927e-05, "epoch": 3.597879282218597, "percentage": 35.98, "elapsed_time": "3:00:23", "remaining_time": "5:20:59", "throughput": 4399.14, "total_tokens": 47613472} {"current_steps": 22060, "total_steps": 61300, "loss": 0.3697, "lr": 4.040163114522689e-05, "epoch": 3.598694942903752, "percentage": 35.99, "elapsed_time": "3:00:25", "remaining_time": "5:20:56", "throughput": 4399.23, "total_tokens": 47624096} {"current_steps": 22065, "total_steps": 61300, "loss": 0.3263, "lr": 4.039602372109014e-05, "epoch": 3.5995106035889073, "percentage": 36.0, "elapsed_time": "3:00:27", "remaining_time": "5:20:53", "throughput": 4399.32, "total_tokens": 47635456} {"current_steps": 22070, "total_steps": 61300, "loss": 0.2821, "lr": 4.0390415048873584e-05, "epoch": 3.600326264274062, "percentage": 36.0, "elapsed_time": "3:00:29", "remaining_time": "5:20:50", "throughput": 4399.39, "total_tokens": 47644448} {"current_steps": 22075, "total_steps": 61300, "loss": 0.3558, "lr": 4.03848051290319e-05, "epoch": 3.601141924959217, "percentage": 36.01, "elapsed_time": "3:00:31", "remaining_time": "5:20:47", "throughput": 4399.46, "total_tokens": 47654144} {"current_steps": 22080, "total_steps": 61300, "loss": 0.3358, "lr": 4.037919396201985e-05, "epoch": 3.6019575856443717, "percentage": 36.02, "elapsed_time": "3:00:34", "remaining_time": "5:20:44", "throughput": 4399.54, "total_tokens": 47664672} {"current_steps": 22085, "total_steps": 61300, "loss": 0.3318, "lr": 4.0373581548292305e-05, "epoch": 3.602773246329527, "percentage": 36.03, "elapsed_time": "3:00:36", "remaining_time": "5:20:41", "throughput": 4399.62, "total_tokens": 47676512} {"current_steps": 22090, "total_steps": 61300, "loss": 0.3134, "lr": 4.036796788830423e-05, "epoch": 3.603588907014682, "percentage": 36.04, "elapsed_time": "3:00:38", "remaining_time": "5:20:38", "throughput": 4399.7, "total_tokens": 47687168} {"current_steps": 22095, "total_steps": 61300, "loss": 0.3215, "lr": 4.036235298251071e-05, "epoch": 3.604404567699837, "percentage": 36.04, "elapsed_time": "3:00:41", "remaining_time": "5:20:36", "throughput": 4399.79, "total_tokens": 47698208} {"current_steps": 22100, "total_steps": 61300, "loss": 0.397, "lr": 4.03567368313669e-05, "epoch": 3.605220228384992, "percentage": 36.05, "elapsed_time": "3:00:43", "remaining_time": "5:20:33", "throughput": 4399.88, "total_tokens": 47708448} {"current_steps": 22105, "total_steps": 61300, "loss": 0.3812, "lr": 4.035111943532808e-05, "epoch": 3.6060358890701467, "percentage": 36.06, "elapsed_time": "3:00:45", "remaining_time": "5:20:29", "throughput": 4399.96, "total_tokens": 47718624} {"current_steps": 22110, "total_steps": 61300, "loss": 0.399, "lr": 4.034550079484964e-05, "epoch": 3.6068515497553015, "percentage": 36.07, "elapsed_time": "3:00:47", "remaining_time": "5:20:27", "throughput": 4400.04, "total_tokens": 47729184} {"current_steps": 22115, "total_steps": 61300, "loss": 0.3512, "lr": 4.033988091038704e-05, "epoch": 3.607667210440457, "percentage": 36.08, "elapsed_time": "3:00:49", "remaining_time": "5:20:24", "throughput": 4400.15, "total_tokens": 47740992} {"current_steps": 22120, "total_steps": 61300, "loss": 0.3322, "lr": 4.0334259782395855e-05, "epoch": 3.6084828711256116, "percentage": 36.08, "elapsed_time": "3:00:52", "remaining_time": "5:20:21", "throughput": 4400.23, "total_tokens": 47751520} {"current_steps": 22125, "total_steps": 61300, "loss": 0.3419, "lr": 4.032863741133177e-05, "epoch": 3.609298531810767, "percentage": 36.09, "elapsed_time": "3:00:54", "remaining_time": "5:20:18", "throughput": 4400.3, "total_tokens": 47761920} {"current_steps": 22130, "total_steps": 61300, "loss": 0.3333, "lr": 4.0323013797650556e-05, "epoch": 3.6101141924959217, "percentage": 36.1, "elapsed_time": "3:00:56", "remaining_time": "5:20:16", "throughput": 4400.38, "total_tokens": 47773376} {"current_steps": 22135, "total_steps": 61300, "loss": 0.3416, "lr": 4.0317388941808096e-05, "epoch": 3.6109298531810765, "percentage": 36.11, "elapsed_time": "3:00:58", "remaining_time": "5:20:13", "throughput": 4400.46, "total_tokens": 47784064} {"current_steps": 22140, "total_steps": 61300, "loss": 0.3398, "lr": 4.0311762844260377e-05, "epoch": 3.6117455138662318, "percentage": 36.12, "elapsed_time": "3:01:01", "remaining_time": "5:20:10", "throughput": 4400.55, "total_tokens": 47794592} {"current_steps": 22145, "total_steps": 61300, "loss": 0.3713, "lr": 4.030613550546347e-05, "epoch": 3.6125611745513866, "percentage": 36.13, "elapsed_time": "3:01:03", "remaining_time": "5:20:07", "throughput": 4400.64, "total_tokens": 47805504} {"current_steps": 22150, "total_steps": 61300, "loss": 0.334, "lr": 4.030050692587355e-05, "epoch": 3.613376835236542, "percentage": 36.13, "elapsed_time": "3:01:05", "remaining_time": "5:20:04", "throughput": 4400.71, "total_tokens": 47816128} {"current_steps": 22155, "total_steps": 61300, "loss": 0.3432, "lr": 4.02948771059469e-05, "epoch": 3.6141924959216967, "percentage": 36.14, "elapsed_time": "3:01:07", "remaining_time": "5:20:01", "throughput": 4400.82, "total_tokens": 47827264} {"current_steps": 22160, "total_steps": 61300, "loss": 0.3411, "lr": 4.028924604613991e-05, "epoch": 3.6150081566068515, "percentage": 36.15, "elapsed_time": "3:01:10", "remaining_time": "5:19:59", "throughput": 4400.9, "total_tokens": 47838208} {"current_steps": 22165, "total_steps": 61300, "loss": 0.3462, "lr": 4.028361374690906e-05, "epoch": 3.6158238172920063, "percentage": 36.16, "elapsed_time": "3:01:12", "remaining_time": "5:19:56", "throughput": 4400.99, "total_tokens": 47848192} {"current_steps": 22170, "total_steps": 61300, "loss": 0.3358, "lr": 4.027798020871093e-05, "epoch": 3.6166394779771616, "percentage": 36.17, "elapsed_time": "3:01:14", "remaining_time": "5:19:53", "throughput": 4401.06, "total_tokens": 47858688} {"current_steps": 22175, "total_steps": 61300, "loss": 0.3461, "lr": 4.027234543200221e-05, "epoch": 3.6174551386623164, "percentage": 36.17, "elapsed_time": "3:01:16", "remaining_time": "5:19:50", "throughput": 4401.14, "total_tokens": 47870048} {"current_steps": 22180, "total_steps": 61300, "loss": 0.3451, "lr": 4.026670941723968e-05, "epoch": 3.6182707993474716, "percentage": 36.18, "elapsed_time": "3:01:19", "remaining_time": "5:19:48", "throughput": 4401.22, "total_tokens": 47881984} {"current_steps": 22185, "total_steps": 61300, "loss": 0.323, "lr": 4.026107216488022e-05, "epoch": 3.6190864600326265, "percentage": 36.19, "elapsed_time": "3:01:21", "remaining_time": "5:19:45", "throughput": 4401.31, "total_tokens": 47893376} {"current_steps": 22190, "total_steps": 61300, "loss": 0.3488, "lr": 4.0255433675380803e-05, "epoch": 3.6199021207177813, "percentage": 36.2, "elapsed_time": "3:01:23", "remaining_time": "5:19:42", "throughput": 4401.38, "total_tokens": 47903680} {"current_steps": 22195, "total_steps": 61300, "loss": 0.3367, "lr": 4.024979394919855e-05, "epoch": 3.6207177814029365, "percentage": 36.21, "elapsed_time": "3:01:25", "remaining_time": "5:19:39", "throughput": 4401.47, "total_tokens": 47914144} {"current_steps": 22200, "total_steps": 61300, "loss": 0.3238, "lr": 4.0244152986790604e-05, "epoch": 3.6215334420880914, "percentage": 36.22, "elapsed_time": "3:01:28", "remaining_time": "5:19:36", "throughput": 4401.55, "total_tokens": 47924224} {"current_steps": 22205, "total_steps": 61300, "loss": 0.3298, "lr": 4.0238510788614276e-05, "epoch": 3.622349102773246, "percentage": 36.22, "elapsed_time": "3:01:30", "remaining_time": "5:19:33", "throughput": 4401.64, "total_tokens": 47935264} {"current_steps": 22210, "total_steps": 61300, "loss": 0.3485, "lr": 4.0232867355126934e-05, "epoch": 3.6231647634584014, "percentage": 36.23, "elapsed_time": "3:01:32", "remaining_time": "5:19:31", "throughput": 4401.73, "total_tokens": 47946432} {"current_steps": 22215, "total_steps": 61300, "loss": 0.3404, "lr": 4.0227222686786084e-05, "epoch": 3.6239804241435563, "percentage": 36.24, "elapsed_time": "3:01:34", "remaining_time": "5:19:28", "throughput": 4401.81, "total_tokens": 47956608} {"current_steps": 22220, "total_steps": 61300, "loss": 0.3232, "lr": 4.02215767840493e-05, "epoch": 3.624796084828711, "percentage": 36.25, "elapsed_time": "3:01:36", "remaining_time": "5:19:25", "throughput": 4401.9, "total_tokens": 47967552} {"current_steps": 22225, "total_steps": 61300, "loss": 0.3471, "lr": 4.021592964737427e-05, "epoch": 3.6256117455138663, "percentage": 36.26, "elapsed_time": "3:01:39", "remaining_time": "5:19:22", "throughput": 4402.0, "total_tokens": 47977888} {"current_steps": 22230, "total_steps": 61300, "loss": 0.3274, "lr": 4.021028127721878e-05, "epoch": 3.626427406199021, "percentage": 36.26, "elapsed_time": "3:01:41", "remaining_time": "5:19:19", "throughput": 4402.1, "total_tokens": 47988576} {"current_steps": 22235, "total_steps": 61300, "loss": 0.359, "lr": 4.020463167404071e-05, "epoch": 3.6272430668841764, "percentage": 36.27, "elapsed_time": "3:01:43", "remaining_time": "5:19:16", "throughput": 4402.19, "total_tokens": 47999776} {"current_steps": 22240, "total_steps": 61300, "loss": 0.3496, "lr": 4.019898083829804e-05, "epoch": 3.6280587275693312, "percentage": 36.28, "elapsed_time": "3:01:45", "remaining_time": "5:19:14", "throughput": 4402.26, "total_tokens": 48010688} {"current_steps": 22245, "total_steps": 61300, "loss": 0.3541, "lr": 4.019332877044888e-05, "epoch": 3.628874388254486, "percentage": 36.29, "elapsed_time": "3:01:48", "remaining_time": "5:19:11", "throughput": 4402.32, "total_tokens": 48021152} {"current_steps": 22250, "total_steps": 61300, "loss": 0.3517, "lr": 4.018767547095139e-05, "epoch": 3.629690048939641, "percentage": 36.3, "elapsed_time": "3:01:50", "remaining_time": "5:19:07", "throughput": 4402.39, "total_tokens": 48030176} {"current_steps": 22255, "total_steps": 61300, "loss": 0.3562, "lr": 4.018202094026386e-05, "epoch": 3.630505709624796, "percentage": 36.31, "elapsed_time": "3:01:51", "remaining_time": "5:19:04", "throughput": 4402.47, "total_tokens": 48039232} {"current_steps": 22260, "total_steps": 61300, "loss": 0.3486, "lr": 4.01763651788447e-05, "epoch": 3.631321370309951, "percentage": 36.31, "elapsed_time": "3:01:54", "remaining_time": "5:19:01", "throughput": 4402.56, "total_tokens": 48049984} {"current_steps": 22265, "total_steps": 61300, "loss": 0.3358, "lr": 4.017070818715235e-05, "epoch": 3.632137030995106, "percentage": 36.32, "elapsed_time": "3:01:56", "remaining_time": "5:18:58", "throughput": 4402.66, "total_tokens": 48061088} {"current_steps": 22270, "total_steps": 61300, "loss": 0.3255, "lr": 4.016504996564544e-05, "epoch": 3.632952691680261, "percentage": 36.33, "elapsed_time": "3:01:58", "remaining_time": "5:18:56", "throughput": 4402.75, "total_tokens": 48072704} {"current_steps": 22275, "total_steps": 61300, "loss": 0.3262, "lr": 4.015939051478262e-05, "epoch": 3.633768352365416, "percentage": 36.34, "elapsed_time": "3:02:00", "remaining_time": "5:18:53", "throughput": 4402.83, "total_tokens": 48082848} {"current_steps": 22280, "total_steps": 61300, "loss": 0.3553, "lr": 4.0153729835022685e-05, "epoch": 3.634584013050571, "percentage": 36.35, "elapsed_time": "3:02:03", "remaining_time": "5:18:50", "throughput": 4402.94, "total_tokens": 48094464} {"current_steps": 22285, "total_steps": 61300, "loss": 0.358, "lr": 4.014806792682453e-05, "epoch": 3.635399673735726, "percentage": 36.35, "elapsed_time": "3:02:05", "remaining_time": "5:18:47", "throughput": 4403.02, "total_tokens": 48105088} {"current_steps": 22290, "total_steps": 61300, "loss": 0.3469, "lr": 4.0142404790647124e-05, "epoch": 3.636215334420881, "percentage": 36.36, "elapsed_time": "3:02:07", "remaining_time": "5:18:44", "throughput": 4403.09, "total_tokens": 48114432} {"current_steps": 22295, "total_steps": 61300, "loss": 0.3751, "lr": 4.0136740426949546e-05, "epoch": 3.637030995106036, "percentage": 36.37, "elapsed_time": "3:02:09", "remaining_time": "5:18:41", "throughput": 4403.16, "total_tokens": 48124288} {"current_steps": 22300, "total_steps": 61300, "loss": 0.3623, "lr": 4.0131074836191e-05, "epoch": 3.637846655791191, "percentage": 36.38, "elapsed_time": "3:02:11", "remaining_time": "5:18:37", "throughput": 4403.24, "total_tokens": 48134144} {"current_steps": 22305, "total_steps": 61300, "loss": 0.3301, "lr": 4.0125408018830744e-05, "epoch": 3.6386623164763456, "percentage": 36.39, "elapsed_time": "3:02:13", "remaining_time": "5:18:34", "throughput": 4403.3, "total_tokens": 48144416} {"current_steps": 22310, "total_steps": 61300, "loss": 0.3863, "lr": 4.011973997532818e-05, "epoch": 3.639477977161501, "percentage": 36.39, "elapsed_time": "3:02:16", "remaining_time": "5:18:32", "throughput": 4403.39, "total_tokens": 48155584} {"current_steps": 22315, "total_steps": 61300, "loss": 0.3524, "lr": 4.011407070614276e-05, "epoch": 3.6402936378466557, "percentage": 36.4, "elapsed_time": "3:02:18", "remaining_time": "5:18:29", "throughput": 4403.48, "total_tokens": 48167232} {"current_steps": 22320, "total_steps": 61300, "loss": 0.3487, "lr": 4.010840021173409e-05, "epoch": 3.641109298531811, "percentage": 36.41, "elapsed_time": "3:02:20", "remaining_time": "5:18:27", "throughput": 4403.58, "total_tokens": 48178208} {"current_steps": 22325, "total_steps": 61300, "loss": 0.3404, "lr": 4.010272849256184e-05, "epoch": 3.641924959216966, "percentage": 36.42, "elapsed_time": "3:02:22", "remaining_time": "5:18:24", "throughput": 4403.66, "total_tokens": 48188896} {"current_steps": 22330, "total_steps": 61300, "loss": 0.3534, "lr": 4.0097055549085784e-05, "epoch": 3.6427406199021206, "percentage": 36.43, "elapsed_time": "3:02:25", "remaining_time": "5:18:21", "throughput": 4403.74, "total_tokens": 48200000} {"current_steps": 22335, "total_steps": 61300, "loss": 0.3723, "lr": 4.009138138176581e-05, "epoch": 3.6435562805872754, "percentage": 36.44, "elapsed_time": "3:02:27", "remaining_time": "5:18:18", "throughput": 4403.81, "total_tokens": 48211200} {"current_steps": 22340, "total_steps": 61300, "loss": 0.3811, "lr": 4.008570599106188e-05, "epoch": 3.6443719412724307, "percentage": 36.44, "elapsed_time": "3:02:29", "remaining_time": "5:18:15", "throughput": 4403.87, "total_tokens": 48221504} {"current_steps": 22345, "total_steps": 61300, "loss": 0.3675, "lr": 4.008002937743409e-05, "epoch": 3.6451876019575855, "percentage": 36.45, "elapsed_time": "3:02:31", "remaining_time": "5:18:12", "throughput": 4403.95, "total_tokens": 48230976} {"current_steps": 22350, "total_steps": 61300, "loss": 0.3451, "lr": 4.0074351541342595e-05, "epoch": 3.6460032626427408, "percentage": 36.46, "elapsed_time": "3:02:34", "remaining_time": "5:18:10", "throughput": 4404.03, "total_tokens": 48242368} {"current_steps": 22355, "total_steps": 61300, "loss": 0.3426, "lr": 4.006867248324767e-05, "epoch": 3.6468189233278956, "percentage": 36.47, "elapsed_time": "3:02:36", "remaining_time": "5:18:07", "throughput": 4404.11, "total_tokens": 48253696} {"current_steps": 22360, "total_steps": 61300, "loss": 0.3594, "lr": 4.006299220360971e-05, "epoch": 3.6476345840130504, "percentage": 36.48, "elapsed_time": "3:02:38", "remaining_time": "5:18:04", "throughput": 4404.19, "total_tokens": 48264768} {"current_steps": 22365, "total_steps": 61300, "loss": 0.3492, "lr": 4.0057310702889164e-05, "epoch": 3.6484502446982057, "percentage": 36.48, "elapsed_time": "3:02:41", "remaining_time": "5:18:02", "throughput": 4404.27, "total_tokens": 48275520} {"current_steps": 22370, "total_steps": 61300, "loss": 0.3428, "lr": 4.005162798154661e-05, "epoch": 3.6492659053833605, "percentage": 36.49, "elapsed_time": "3:02:43", "remaining_time": "5:17:58", "throughput": 4404.34, "total_tokens": 48284960} {"current_steps": 22375, "total_steps": 61300, "loss": 0.3297, "lr": 4.004594404004273e-05, "epoch": 3.6500815660685157, "percentage": 36.5, "elapsed_time": "3:02:45", "remaining_time": "5:17:55", "throughput": 4404.43, "total_tokens": 48295840} {"current_steps": 22380, "total_steps": 61300, "loss": 0.322, "lr": 4.0040258878838284e-05, "epoch": 3.6508972267536706, "percentage": 36.51, "elapsed_time": "3:02:47", "remaining_time": "5:17:53", "throughput": 4404.52, "total_tokens": 48306880} {"current_steps": 22385, "total_steps": 61300, "loss": 0.3422, "lr": 4.003457249839413e-05, "epoch": 3.6517128874388254, "percentage": 36.52, "elapsed_time": "3:02:49", "remaining_time": "5:17:50", "throughput": 4404.62, "total_tokens": 48318336} {"current_steps": 22390, "total_steps": 61300, "loss": 0.3588, "lr": 4.002888489917126e-05, "epoch": 3.65252854812398, "percentage": 36.53, "elapsed_time": "3:02:52", "remaining_time": "5:17:47", "throughput": 4404.71, "total_tokens": 48329152} {"current_steps": 22395, "total_steps": 61300, "loss": 0.334, "lr": 4.002319608163071e-05, "epoch": 3.6533442088091355, "percentage": 36.53, "elapsed_time": "3:02:54", "remaining_time": "5:17:44", "throughput": 4404.78, "total_tokens": 48339136} {"current_steps": 22400, "total_steps": 61300, "loss": 0.3385, "lr": 4.0017506046233664e-05, "epoch": 3.6541598694942903, "percentage": 36.54, "elapsed_time": "3:02:56", "remaining_time": "5:17:41", "throughput": 4404.86, "total_tokens": 48350208} {"current_steps": 22405, "total_steps": 61300, "loss": 0.343, "lr": 4.001181479344138e-05, "epoch": 3.6549755301794455, "percentage": 36.55, "elapsed_time": "3:02:59", "remaining_time": "5:17:39", "throughput": 4404.95, "total_tokens": 48362016} {"current_steps": 22410, "total_steps": 61300, "loss": 0.3307, "lr": 4.000612232371522e-05, "epoch": 3.6557911908646004, "percentage": 36.56, "elapsed_time": "3:03:00", "remaining_time": "5:17:36", "throughput": 4405.02, "total_tokens": 48371424} {"current_steps": 22415, "total_steps": 61300, "loss": 0.3601, "lr": 4.000042863751664e-05, "epoch": 3.656606851549755, "percentage": 36.57, "elapsed_time": "3:03:03", "remaining_time": "5:17:33", "throughput": 4405.12, "total_tokens": 48383328} {"current_steps": 22420, "total_steps": 61300, "loss": 0.3161, "lr": 3.999473373530721e-05, "epoch": 3.6574225122349104, "percentage": 36.57, "elapsed_time": "3:03:05", "remaining_time": "5:17:31", "throughput": 4405.19, "total_tokens": 48394304} {"current_steps": 22425, "total_steps": 61300, "loss": 0.3445, "lr": 3.9989037617548575e-05, "epoch": 3.6582381729200653, "percentage": 36.58, "elapsed_time": "3:03:08", "remaining_time": "5:17:28", "throughput": 4405.28, "total_tokens": 48405376} {"current_steps": 22430, "total_steps": 61300, "loss": 0.3857, "lr": 3.9983340284702495e-05, "epoch": 3.65905383360522, "percentage": 36.59, "elapsed_time": "3:03:10", "remaining_time": "5:17:25", "throughput": 4405.35, "total_tokens": 48416352} {"current_steps": 22435, "total_steps": 61300, "loss": 0.3148, "lr": 3.9977641737230833e-05, "epoch": 3.6598694942903753, "percentage": 36.6, "elapsed_time": "3:03:12", "remaining_time": "5:17:22", "throughput": 4405.44, "total_tokens": 48427488} {"current_steps": 22440, "total_steps": 61300, "loss": 0.335, "lr": 3.9971941975595535e-05, "epoch": 3.66068515497553, "percentage": 36.61, "elapsed_time": "3:03:15", "remaining_time": "5:17:20", "throughput": 4405.55, "total_tokens": 48439520} {"current_steps": 22445, "total_steps": 61300, "loss": 0.3589, "lr": 3.996624100025865e-05, "epoch": 3.661500815660685, "percentage": 36.62, "elapsed_time": "3:03:17", "remaining_time": "5:17:17", "throughput": 4405.63, "total_tokens": 48449984} {"current_steps": 22450, "total_steps": 61300, "loss": 0.3179, "lr": 3.9960538811682334e-05, "epoch": 3.6623164763458402, "percentage": 36.62, "elapsed_time": "3:03:19", "remaining_time": "5:17:14", "throughput": 4405.71, "total_tokens": 48460672} {"current_steps": 22455, "total_steps": 61300, "loss": 0.3109, "lr": 3.9954835410328836e-05, "epoch": 3.663132137030995, "percentage": 36.63, "elapsed_time": "3:03:21", "remaining_time": "5:17:11", "throughput": 4405.79, "total_tokens": 48471328} {"current_steps": 22460, "total_steps": 61300, "loss": 0.3532, "lr": 3.9949130796660496e-05, "epoch": 3.6639477977161503, "percentage": 36.64, "elapsed_time": "3:03:23", "remaining_time": "5:17:09", "throughput": 4405.85, "total_tokens": 48481664} {"current_steps": 22465, "total_steps": 61300, "loss": 0.3622, "lr": 3.994342497113977e-05, "epoch": 3.664763458401305, "percentage": 36.65, "elapsed_time": "3:03:26", "remaining_time": "5:17:06", "throughput": 4405.93, "total_tokens": 48492896} {"current_steps": 22470, "total_steps": 61300, "loss": 0.3234, "lr": 3.993771793422918e-05, "epoch": 3.66557911908646, "percentage": 36.66, "elapsed_time": "3:03:28", "remaining_time": "5:17:03", "throughput": 4406.03, "total_tokens": 48503648} {"current_steps": 22475, "total_steps": 61300, "loss": 0.3156, "lr": 3.993200968639139e-05, "epoch": 3.6663947797716148, "percentage": 36.66, "elapsed_time": "3:03:30", "remaining_time": "5:17:00", "throughput": 4406.09, "total_tokens": 48514368} {"current_steps": 22480, "total_steps": 61300, "loss": 0.3387, "lr": 3.9926300228089124e-05, "epoch": 3.66721044045677, "percentage": 36.67, "elapsed_time": "3:03:33", "remaining_time": "5:16:58", "throughput": 4406.18, "total_tokens": 48525504} {"current_steps": 22485, "total_steps": 61300, "loss": 0.3465, "lr": 3.992058955978523e-05, "epoch": 3.668026101141925, "percentage": 36.68, "elapsed_time": "3:03:35", "remaining_time": "5:16:54", "throughput": 4406.24, "total_tokens": 48534880} {"current_steps": 22490, "total_steps": 61300, "loss": 0.353, "lr": 3.9914877681942645e-05, "epoch": 3.66884176182708, "percentage": 36.69, "elapsed_time": "3:03:37", "remaining_time": "5:16:52", "throughput": 4406.33, "total_tokens": 48546656} {"current_steps": 22495, "total_steps": 61300, "loss": 0.3199, "lr": 3.99091645950244e-05, "epoch": 3.669657422512235, "percentage": 36.7, "elapsed_time": "3:03:39", "remaining_time": "5:16:49", "throughput": 4406.41, "total_tokens": 48557952} {"current_steps": 22500, "total_steps": 61300, "loss": 0.3378, "lr": 3.990345029949361e-05, "epoch": 3.6704730831973897, "percentage": 36.7, "elapsed_time": "3:03:42", "remaining_time": "5:16:47", "throughput": 4406.49, "total_tokens": 48568832} {"current_steps": 22505, "total_steps": 61300, "loss": 0.3719, "lr": 3.9897734795813524e-05, "epoch": 3.671288743882545, "percentage": 36.71, "elapsed_time": "3:03:44", "remaining_time": "5:16:43", "throughput": 4406.57, "total_tokens": 48578784} {"current_steps": 22510, "total_steps": 61300, "loss": 0.3559, "lr": 3.989201808444747e-05, "epoch": 3.6721044045677, "percentage": 36.72, "elapsed_time": "3:03:46", "remaining_time": "5:16:41", "throughput": 4406.66, "total_tokens": 48590016} {"current_steps": 22515, "total_steps": 61300, "loss": 0.3809, "lr": 3.988630016585887e-05, "epoch": 3.672920065252855, "percentage": 36.73, "elapsed_time": "3:03:48", "remaining_time": "5:16:38", "throughput": 4406.73, "total_tokens": 48600608} {"current_steps": 22520, "total_steps": 61300, "loss": 0.3234, "lr": 3.988058104051124e-05, "epoch": 3.67373572593801, "percentage": 36.74, "elapsed_time": "3:03:50", "remaining_time": "5:16:35", "throughput": 4406.82, "total_tokens": 48610912} {"current_steps": 22525, "total_steps": 61300, "loss": 0.349, "lr": 3.987486070886821e-05, "epoch": 3.6745513866231647, "percentage": 36.75, "elapsed_time": "3:03:53", "remaining_time": "5:16:32", "throughput": 4406.9, "total_tokens": 48622272} {"current_steps": 22530, "total_steps": 61300, "loss": 0.3259, "lr": 3.98691391713935e-05, "epoch": 3.6753670473083195, "percentage": 36.75, "elapsed_time": "3:03:55", "remaining_time": "5:16:30", "throughput": 4406.99, "total_tokens": 48633376} {"current_steps": 22535, "total_steps": 61300, "loss": 0.2901, "lr": 3.986341642855092e-05, "epoch": 3.676182707993475, "percentage": 36.76, "elapsed_time": "3:03:57", "remaining_time": "5:16:27", "throughput": 4407.08, "total_tokens": 48644608} {"current_steps": 22540, "total_steps": 61300, "loss": 0.3535, "lr": 3.985769248080439e-05, "epoch": 3.6769983686786296, "percentage": 36.77, "elapsed_time": "3:04:00", "remaining_time": "5:16:24", "throughput": 4407.19, "total_tokens": 48656448} {"current_steps": 22545, "total_steps": 61300, "loss": 0.3165, "lr": 3.9851967328617925e-05, "epoch": 3.677814029363785, "percentage": 36.78, "elapsed_time": "3:04:02", "remaining_time": "5:16:22", "throughput": 4407.28, "total_tokens": 48667936} {"current_steps": 22550, "total_steps": 61300, "loss": 0.3938, "lr": 3.984624097245562e-05, "epoch": 3.6786296900489397, "percentage": 36.79, "elapsed_time": "3:04:04", "remaining_time": "5:16:19", "throughput": 4407.36, "total_tokens": 48678240} {"current_steps": 22555, "total_steps": 61300, "loss": 0.3604, "lr": 3.98405134127817e-05, "epoch": 3.6794453507340945, "percentage": 36.79, "elapsed_time": "3:04:06", "remaining_time": "5:16:15", "throughput": 4407.42, "total_tokens": 48687296} {"current_steps": 22560, "total_steps": 61300, "loss": 0.3546, "lr": 3.983478465006045e-05, "epoch": 3.6802610114192493, "percentage": 36.8, "elapsed_time": "3:04:09", "remaining_time": "5:16:13", "throughput": 4407.51, "total_tokens": 48698720} {"current_steps": 22565, "total_steps": 61300, "loss": 0.3137, "lr": 3.9829054684756304e-05, "epoch": 3.6810766721044046, "percentage": 36.81, "elapsed_time": "3:04:11", "remaining_time": "5:16:10", "throughput": 4407.58, "total_tokens": 48709696} {"current_steps": 22570, "total_steps": 61300, "loss": 0.3446, "lr": 3.982332351733373e-05, "epoch": 3.6818923327895594, "percentage": 36.82, "elapsed_time": "3:04:13", "remaining_time": "5:16:07", "throughput": 4407.64, "total_tokens": 48720032} {"current_steps": 22575, "total_steps": 61300, "loss": 0.3554, "lr": 3.981759114825735e-05, "epoch": 3.6827079934747147, "percentage": 36.83, "elapsed_time": "3:04:15", "remaining_time": "5:16:04", "throughput": 4407.7, "total_tokens": 48729664} {"current_steps": 22580, "total_steps": 61300, "loss": 0.3231, "lr": 3.981185757799184e-05, "epoch": 3.6835236541598695, "percentage": 36.84, "elapsed_time": "3:04:18", "remaining_time": "5:16:02", "throughput": 4407.81, "total_tokens": 48742336} {"current_steps": 22585, "total_steps": 61300, "loss": 0.3141, "lr": 3.9806122807002e-05, "epoch": 3.6843393148450243, "percentage": 36.84, "elapsed_time": "3:04:20", "remaining_time": "5:15:59", "throughput": 4407.91, "total_tokens": 48754048} {"current_steps": 22590, "total_steps": 61300, "loss": 0.3466, "lr": 3.9800386835752726e-05, "epoch": 3.6851549755301796, "percentage": 36.85, "elapsed_time": "3:04:22", "remaining_time": "5:15:57", "throughput": 4408.0, "total_tokens": 48765344} {"current_steps": 22595, "total_steps": 61300, "loss": 0.3305, "lr": 3.979464966470899e-05, "epoch": 3.6859706362153344, "percentage": 36.86, "elapsed_time": "3:04:25", "remaining_time": "5:15:54", "throughput": 4408.09, "total_tokens": 48777152} {"current_steps": 22600, "total_steps": 61300, "loss": 0.3582, "lr": 3.978891129433588e-05, "epoch": 3.6867862969004896, "percentage": 36.87, "elapsed_time": "3:04:27", "remaining_time": "5:15:51", "throughput": 4408.17, "total_tokens": 48786880} {"current_steps": 22605, "total_steps": 61300, "loss": 0.3464, "lr": 3.97831717250986e-05, "epoch": 3.6876019575856445, "percentage": 36.88, "elapsed_time": "3:04:29", "remaining_time": "5:15:48", "throughput": 4408.24, "total_tokens": 48796256} {"current_steps": 22610, "total_steps": 61300, "loss": 0.3806, "lr": 3.97774309574624e-05, "epoch": 3.6884176182707993, "percentage": 36.88, "elapsed_time": "3:04:31", "remaining_time": "5:15:45", "throughput": 4408.34, "total_tokens": 48808096} {"current_steps": 22615, "total_steps": 61300, "loss": 0.3652, "lr": 3.977168899189267e-05, "epoch": 3.689233278955954, "percentage": 36.89, "elapsed_time": "3:04:33", "remaining_time": "5:15:43", "throughput": 4408.43, "total_tokens": 48818848} {"current_steps": 22620, "total_steps": 61300, "loss": 0.3372, "lr": 3.9765945828854876e-05, "epoch": 3.6900489396411094, "percentage": 36.9, "elapsed_time": "3:04:36", "remaining_time": "5:15:40", "throughput": 4408.53, "total_tokens": 48831296} {"current_steps": 22625, "total_steps": 61300, "loss": 0.3477, "lr": 3.97602014688146e-05, "epoch": 3.690864600326264, "percentage": 36.91, "elapsed_time": "3:04:38", "remaining_time": "5:15:37", "throughput": 4408.62, "total_tokens": 48841536} {"current_steps": 22630, "total_steps": 61300, "loss": 0.3694, "lr": 3.9754455912237486e-05, "epoch": 3.6916802610114194, "percentage": 36.92, "elapsed_time": "3:04:41", "remaining_time": "5:15:35", "throughput": 4408.72, "total_tokens": 48853152} {"current_steps": 22635, "total_steps": 61300, "loss": 0.3684, "lr": 3.974870915958932e-05, "epoch": 3.6924959216965743, "percentage": 36.92, "elapsed_time": "3:04:42", "remaining_time": "5:15:31", "throughput": 4408.81, "total_tokens": 48862688} {"current_steps": 22640, "total_steps": 61300, "loss": 0.3388, "lr": 3.974296121133596e-05, "epoch": 3.693311582381729, "percentage": 36.93, "elapsed_time": "3:04:45", "remaining_time": "5:15:29", "throughput": 4408.9, "total_tokens": 48874688} {"current_steps": 22645, "total_steps": 61300, "loss": 0.3609, "lr": 3.9737212067943354e-05, "epoch": 3.6941272430668843, "percentage": 36.94, "elapsed_time": "3:04:47", "remaining_time": "5:15:26", "throughput": 4408.99, "total_tokens": 48885856} {"current_steps": 22650, "total_steps": 61300, "loss": 0.3396, "lr": 3.973146172987756e-05, "epoch": 3.694942903752039, "percentage": 36.95, "elapsed_time": "3:04:49", "remaining_time": "5:15:23", "throughput": 4409.07, "total_tokens": 48896096} {"current_steps": 22655, "total_steps": 61300, "loss": 0.3286, "lr": 3.9725710197604735e-05, "epoch": 3.695758564437194, "percentage": 36.96, "elapsed_time": "3:04:52", "remaining_time": "5:15:21", "throughput": 4409.16, "total_tokens": 48907328} {"current_steps": 22660, "total_steps": 61300, "loss": 0.362, "lr": 3.971995747159113e-05, "epoch": 3.6965742251223492, "percentage": 36.97, "elapsed_time": "3:04:54", "remaining_time": "5:15:18", "throughput": 4409.24, "total_tokens": 48918304} {"current_steps": 22665, "total_steps": 61300, "loss": 0.3383, "lr": 3.971420355230308e-05, "epoch": 3.697389885807504, "percentage": 36.97, "elapsed_time": "3:04:56", "remaining_time": "5:15:15", "throughput": 4409.34, "total_tokens": 48929440} {"current_steps": 22670, "total_steps": 61300, "loss": 0.3384, "lr": 3.9708448440207026e-05, "epoch": 3.698205546492659, "percentage": 36.98, "elapsed_time": "3:04:59", "remaining_time": "5:15:12", "throughput": 4409.42, "total_tokens": 48940256} {"current_steps": 22675, "total_steps": 61300, "loss": 0.3312, "lr": 3.970269213576951e-05, "epoch": 3.699021207177814, "percentage": 36.99, "elapsed_time": "3:05:01", "remaining_time": "5:15:09", "throughput": 4409.5, "total_tokens": 48949856} {"current_steps": 22680, "total_steps": 61300, "loss": 0.3653, "lr": 3.969693463945717e-05, "epoch": 3.699836867862969, "percentage": 37.0, "elapsed_time": "3:05:03", "remaining_time": "5:15:06", "throughput": 4409.58, "total_tokens": 48960768} {"current_steps": 22685, "total_steps": 61300, "loss": 0.356, "lr": 3.9691175951736745e-05, "epoch": 3.700652528548124, "percentage": 37.01, "elapsed_time": "3:05:05", "remaining_time": "5:15:04", "throughput": 4409.64, "total_tokens": 48971264} {"current_steps": 22690, "total_steps": 61300, "loss": 0.3527, "lr": 3.9685416073075045e-05, "epoch": 3.701468189233279, "percentage": 37.01, "elapsed_time": "3:05:07", "remaining_time": "5:15:01", "throughput": 4409.72, "total_tokens": 48981632} {"current_steps": 22695, "total_steps": 61300, "loss": 0.3334, "lr": 3.967965500393901e-05, "epoch": 3.702283849918434, "percentage": 37.02, "elapsed_time": "3:05:09", "remaining_time": "5:14:58", "throughput": 4409.82, "total_tokens": 48993024} {"current_steps": 22700, "total_steps": 61300, "loss": 0.357, "lr": 3.9673892744795655e-05, "epoch": 3.7030995106035887, "percentage": 37.03, "elapsed_time": "3:05:12", "remaining_time": "5:14:55", "throughput": 4409.9, "total_tokens": 49004064} {"current_steps": 22705, "total_steps": 61300, "loss": 0.3469, "lr": 3.96681292961121e-05, "epoch": 3.703915171288744, "percentage": 37.04, "elapsed_time": "3:05:14", "remaining_time": "5:14:53", "throughput": 4409.98, "total_tokens": 49016032} {"current_steps": 22710, "total_steps": 61300, "loss": 0.3488, "lr": 3.9662364658355555e-05, "epoch": 3.7047308319738987, "percentage": 37.05, "elapsed_time": "3:05:16", "remaining_time": "5:14:50", "throughput": 4410.04, "total_tokens": 49026336} {"current_steps": 22715, "total_steps": 61300, "loss": 0.3335, "lr": 3.965659883199334e-05, "epoch": 3.705546492659054, "percentage": 37.06, "elapsed_time": "3:05:19", "remaining_time": "5:14:47", "throughput": 4410.12, "total_tokens": 49037312} {"current_steps": 22720, "total_steps": 61300, "loss": 0.3185, "lr": 3.9650831817492864e-05, "epoch": 3.706362153344209, "percentage": 37.06, "elapsed_time": "3:05:21", "remaining_time": "5:14:45", "throughput": 4410.17, "total_tokens": 49048480} {"current_steps": 22725, "total_steps": 61300, "loss": 0.3756, "lr": 3.964506361532161e-05, "epoch": 3.7071778140293636, "percentage": 37.07, "elapsed_time": "3:05:24", "remaining_time": "5:14:42", "throughput": 4410.26, "total_tokens": 49059840} {"current_steps": 22730, "total_steps": 61300, "loss": 0.3742, "lr": 3.96392942259472e-05, "epoch": 3.707993474714519, "percentage": 37.08, "elapsed_time": "3:05:26", "remaining_time": "5:14:39", "throughput": 4410.33, "total_tokens": 49070720} {"current_steps": 22735, "total_steps": 61300, "loss": 0.3112, "lr": 3.963352364983731e-05, "epoch": 3.7088091353996737, "percentage": 37.09, "elapsed_time": "3:05:28", "remaining_time": "5:14:37", "throughput": 4410.4, "total_tokens": 49081408} {"current_steps": 22740, "total_steps": 61300, "loss": 0.325, "lr": 3.962775188745975e-05, "epoch": 3.709624796084829, "percentage": 37.1, "elapsed_time": "3:05:30", "remaining_time": "5:14:34", "throughput": 4410.5, "total_tokens": 49092416} {"current_steps": 22745, "total_steps": 61300, "loss": 0.343, "lr": 3.9621978939282405e-05, "epoch": 3.710440456769984, "percentage": 37.1, "elapsed_time": "3:05:32", "remaining_time": "5:14:31", "throughput": 4410.57, "total_tokens": 49102464} {"current_steps": 22750, "total_steps": 61300, "loss": 0.3597, "lr": 3.961620480577325e-05, "epoch": 3.7112561174551386, "percentage": 37.11, "elapsed_time": "3:05:35", "remaining_time": "5:14:28", "throughput": 4410.64, "total_tokens": 49113920} {"current_steps": 22755, "total_steps": 61300, "loss": 0.333, "lr": 3.961042948740038e-05, "epoch": 3.7120717781402934, "percentage": 37.12, "elapsed_time": "3:05:37", "remaining_time": "5:14:25", "throughput": 4410.71, "total_tokens": 49124096} {"current_steps": 22760, "total_steps": 61300, "loss": 0.3474, "lr": 3.960465298463195e-05, "epoch": 3.7128874388254487, "percentage": 37.13, "elapsed_time": "3:05:39", "remaining_time": "5:14:22", "throughput": 4410.8, "total_tokens": 49134048} {"current_steps": 22765, "total_steps": 61300, "loss": 0.3345, "lr": 3.959887529793625e-05, "epoch": 3.7137030995106035, "percentage": 37.14, "elapsed_time": "3:05:41", "remaining_time": "5:14:19", "throughput": 4410.88, "total_tokens": 49144800} {"current_steps": 22770, "total_steps": 61300, "loss": 0.3316, "lr": 3.9593096427781665e-05, "epoch": 3.7145187601957588, "percentage": 37.15, "elapsed_time": "3:05:44", "remaining_time": "5:14:17", "throughput": 4410.96, "total_tokens": 49156128} {"current_steps": 22775, "total_steps": 61300, "loss": 0.3597, "lr": 3.958731637463662e-05, "epoch": 3.7153344208809136, "percentage": 37.15, "elapsed_time": "3:05:46", "remaining_time": "5:14:14", "throughput": 4411.04, "total_tokens": 49167168} {"current_steps": 22780, "total_steps": 61300, "loss": 0.3598, "lr": 3.958153513896969e-05, "epoch": 3.7161500815660684, "percentage": 37.16, "elapsed_time": "3:05:48", "remaining_time": "5:14:11", "throughput": 4411.12, "total_tokens": 49177248} {"current_steps": 22785, "total_steps": 61300, "loss": 0.3097, "lr": 3.957575272124954e-05, "epoch": 3.7169657422512232, "percentage": 37.17, "elapsed_time": "3:05:50", "remaining_time": "5:14:09", "throughput": 4411.23, "total_tokens": 49189568} {"current_steps": 22790, "total_steps": 61300, "loss": 0.339, "lr": 3.9569969121944925e-05, "epoch": 3.7177814029363785, "percentage": 37.18, "elapsed_time": "3:05:52", "remaining_time": "5:14:05", "throughput": 4411.3, "total_tokens": 49198912} {"current_steps": 22795, "total_steps": 61300, "loss": 0.3597, "lr": 3.956418434152467e-05, "epoch": 3.7185970636215333, "percentage": 37.19, "elapsed_time": "3:05:55", "remaining_time": "5:14:03", "throughput": 4411.38, "total_tokens": 49210112} {"current_steps": 22800, "total_steps": 61300, "loss": 0.3294, "lr": 3.955839838045775e-05, "epoch": 3.7194127243066886, "percentage": 37.19, "elapsed_time": "3:05:57", "remaining_time": "5:14:00", "throughput": 4411.47, "total_tokens": 49221344} {"current_steps": 22805, "total_steps": 61300, "loss": 0.3795, "lr": 3.9552611239213185e-05, "epoch": 3.7202283849918434, "percentage": 37.2, "elapsed_time": "3:05:59", "remaining_time": "5:13:57", "throughput": 4411.55, "total_tokens": 49232064} {"current_steps": 22810, "total_steps": 61300, "loss": 0.339, "lr": 3.954682291826011e-05, "epoch": 3.721044045676998, "percentage": 37.21, "elapsed_time": "3:06:01", "remaining_time": "5:13:54", "throughput": 4411.62, "total_tokens": 49242144} {"current_steps": 22815, "total_steps": 61300, "loss": 0.3135, "lr": 3.9541033418067765e-05, "epoch": 3.7218597063621535, "percentage": 37.22, "elapsed_time": "3:06:04", "remaining_time": "5:13:52", "throughput": 4411.72, "total_tokens": 49253248} {"current_steps": 22820, "total_steps": 61300, "loss": 0.3329, "lr": 3.953524273910546e-05, "epoch": 3.7226753670473083, "percentage": 37.23, "elapsed_time": "3:06:06", "remaining_time": "5:13:49", "throughput": 4411.79, "total_tokens": 49264384} {"current_steps": 22825, "total_steps": 61300, "loss": 0.3111, "lr": 3.952945088184264e-05, "epoch": 3.7234910277324635, "percentage": 37.23, "elapsed_time": "3:06:08", "remaining_time": "5:13:47", "throughput": 4411.9, "total_tokens": 49276416} {"current_steps": 22830, "total_steps": 61300, "loss": 0.2944, "lr": 3.952365784674881e-05, "epoch": 3.7243066884176184, "percentage": 37.24, "elapsed_time": "3:06:11", "remaining_time": "5:13:44", "throughput": 4412.0, "total_tokens": 49288800} {"current_steps": 22835, "total_steps": 61300, "loss": 0.3663, "lr": 3.951786363429357e-05, "epoch": 3.725122349102773, "percentage": 37.25, "elapsed_time": "3:06:13", "remaining_time": "5:13:41", "throughput": 4412.09, "total_tokens": 49299328} {"current_steps": 22840, "total_steps": 61300, "loss": 0.3563, "lr": 3.951206824494665e-05, "epoch": 3.725938009787928, "percentage": 37.26, "elapsed_time": "3:06:16", "remaining_time": "5:13:39", "throughput": 4412.18, "total_tokens": 49311360} {"current_steps": 22845, "total_steps": 61300, "loss": 0.3181, "lr": 3.950627167917784e-05, "epoch": 3.7267536704730833, "percentage": 37.27, "elapsed_time": "3:06:18", "remaining_time": "5:13:36", "throughput": 4412.24, "total_tokens": 49321632} {"current_steps": 22850, "total_steps": 61300, "loss": 0.2989, "lr": 3.950047393745705e-05, "epoch": 3.727569331158238, "percentage": 37.28, "elapsed_time": "3:06:20", "remaining_time": "5:13:33", "throughput": 4412.32, "total_tokens": 49332256} {"current_steps": 22855, "total_steps": 61300, "loss": 0.32, "lr": 3.949467502025426e-05, "epoch": 3.7283849918433933, "percentage": 37.28, "elapsed_time": "3:06:22", "remaining_time": "5:13:30", "throughput": 4412.42, "total_tokens": 49343360} {"current_steps": 22860, "total_steps": 61300, "loss": 0.3482, "lr": 3.948887492803957e-05, "epoch": 3.729200652528548, "percentage": 37.29, "elapsed_time": "3:06:25", "remaining_time": "5:13:28", "throughput": 4412.5, "total_tokens": 49354112} {"current_steps": 22865, "total_steps": 61300, "loss": 0.3871, "lr": 3.948307366128316e-05, "epoch": 3.730016313213703, "percentage": 37.3, "elapsed_time": "3:06:27", "remaining_time": "5:13:25", "throughput": 4412.58, "total_tokens": 49365120} {"current_steps": 22870, "total_steps": 61300, "loss": 0.361, "lr": 3.9477271220455323e-05, "epoch": 3.7308319738988582, "percentage": 37.31, "elapsed_time": "3:06:29", "remaining_time": "5:13:23", "throughput": 4412.67, "total_tokens": 49377600} {"current_steps": 22875, "total_steps": 61300, "loss": 0.3079, "lr": 3.947146760602642e-05, "epoch": 3.731647634584013, "percentage": 37.32, "elapsed_time": "3:06:32", "remaining_time": "5:13:20", "throughput": 4412.75, "total_tokens": 49387648} {"current_steps": 22880, "total_steps": 61300, "loss": 0.3122, "lr": 3.946566281846692e-05, "epoch": 3.732463295269168, "percentage": 37.32, "elapsed_time": "3:06:34", "remaining_time": "5:13:17", "throughput": 4412.83, "total_tokens": 49398368} {"current_steps": 22885, "total_steps": 61300, "loss": 0.3418, "lr": 3.9459856858247404e-05, "epoch": 3.733278955954323, "percentage": 37.33, "elapsed_time": "3:06:36", "remaining_time": "5:13:14", "throughput": 4412.89, "total_tokens": 49408416} {"current_steps": 22890, "total_steps": 61300, "loss": 0.3492, "lr": 3.945404972583851e-05, "epoch": 3.734094616639478, "percentage": 37.34, "elapsed_time": "3:06:38", "remaining_time": "5:13:11", "throughput": 4412.97, "total_tokens": 49417888} {"current_steps": 22895, "total_steps": 61300, "loss": 0.3926, "lr": 3.9448241421711004e-05, "epoch": 3.7349102773246328, "percentage": 37.35, "elapsed_time": "3:06:40", "remaining_time": "5:13:07", "throughput": 4413.03, "total_tokens": 49427296} {"current_steps": 22900, "total_steps": 61300, "loss": 0.336, "lr": 3.9442431946335755e-05, "epoch": 3.735725938009788, "percentage": 37.36, "elapsed_time": "3:06:42", "remaining_time": "5:13:05", "throughput": 4413.11, "total_tokens": 49437984} {"current_steps": 22905, "total_steps": 61300, "loss": 0.3571, "lr": 3.943662130018368e-05, "epoch": 3.736541598694943, "percentage": 37.37, "elapsed_time": "3:06:44", "remaining_time": "5:13:02", "throughput": 4413.18, "total_tokens": 49448288} {"current_steps": 22910, "total_steps": 61300, "loss": 0.3454, "lr": 3.943080948372583e-05, "epoch": 3.737357259380098, "percentage": 37.37, "elapsed_time": "3:06:46", "remaining_time": "5:12:59", "throughput": 4413.26, "total_tokens": 49458624} {"current_steps": 22915, "total_steps": 61300, "loss": 0.3584, "lr": 3.942499649743335e-05, "epoch": 3.738172920065253, "percentage": 37.38, "elapsed_time": "3:06:48", "remaining_time": "5:12:55", "throughput": 4413.33, "total_tokens": 49468032} {"current_steps": 22920, "total_steps": 61300, "loss": 0.3388, "lr": 3.941918234177746e-05, "epoch": 3.7389885807504077, "percentage": 37.39, "elapsed_time": "3:06:51", "remaining_time": "5:12:53", "throughput": 4413.43, "total_tokens": 49479744} {"current_steps": 22925, "total_steps": 61300, "loss": 0.3169, "lr": 3.941336701722949e-05, "epoch": 3.7398042414355626, "percentage": 37.4, "elapsed_time": "3:06:53", "remaining_time": "5:12:50", "throughput": 4413.51, "total_tokens": 49490688} {"current_steps": 22930, "total_steps": 61300, "loss": 0.3564, "lr": 3.940755052426085e-05, "epoch": 3.740619902120718, "percentage": 37.41, "elapsed_time": "3:06:55", "remaining_time": "5:12:47", "throughput": 4413.58, "total_tokens": 49499936} {"current_steps": 22935, "total_steps": 61300, "loss": 0.3473, "lr": 3.940173286334307e-05, "epoch": 3.7414355628058726, "percentage": 37.41, "elapsed_time": "3:06:57", "remaining_time": "5:12:44", "throughput": 4413.66, "total_tokens": 49510080} {"current_steps": 22940, "total_steps": 61300, "loss": 0.3129, "lr": 3.9395914034947744e-05, "epoch": 3.742251223491028, "percentage": 37.42, "elapsed_time": "3:06:59", "remaining_time": "5:12:41", "throughput": 4413.75, "total_tokens": 49521056} {"current_steps": 22945, "total_steps": 61300, "loss": 0.3628, "lr": 3.939009403954659e-05, "epoch": 3.7430668841761827, "percentage": 37.43, "elapsed_time": "3:07:01", "remaining_time": "5:12:38", "throughput": 4413.82, "total_tokens": 49531712} {"current_steps": 22950, "total_steps": 61300, "loss": 0.3404, "lr": 3.9384272877611384e-05, "epoch": 3.7438825448613375, "percentage": 37.44, "elapsed_time": "3:07:04", "remaining_time": "5:12:35", "throughput": 4413.92, "total_tokens": 49542912} {"current_steps": 22955, "total_steps": 61300, "loss": 0.3466, "lr": 3.9378450549614044e-05, "epoch": 3.744698205546493, "percentage": 37.45, "elapsed_time": "3:07:06", "remaining_time": "5:12:33", "throughput": 4414.02, "total_tokens": 49553888} {"current_steps": 22960, "total_steps": 61300, "loss": 0.3545, "lr": 3.9372627056026544e-05, "epoch": 3.7455138662316476, "percentage": 37.46, "elapsed_time": "3:07:08", "remaining_time": "5:12:30", "throughput": 4414.11, "total_tokens": 49565376} {"current_steps": 22965, "total_steps": 61300, "loss": 0.3481, "lr": 3.9366802397320966e-05, "epoch": 3.746329526916803, "percentage": 37.46, "elapsed_time": "3:07:11", "remaining_time": "5:12:28", "throughput": 4414.2, "total_tokens": 49577184} {"current_steps": 22970, "total_steps": 61300, "loss": 0.3276, "lr": 3.9360976573969494e-05, "epoch": 3.7471451876019577, "percentage": 37.47, "elapsed_time": "3:07:13", "remaining_time": "5:12:25", "throughput": 4414.3, "total_tokens": 49588608} {"current_steps": 22975, "total_steps": 61300, "loss": 0.3634, "lr": 3.935514958644439e-05, "epoch": 3.7479608482871125, "percentage": 37.48, "elapsed_time": "3:07:15", "remaining_time": "5:12:22", "throughput": 4414.39, "total_tokens": 49599840} {"current_steps": 22980, "total_steps": 61300, "loss": 0.3304, "lr": 3.934932143521803e-05, "epoch": 3.7487765089722673, "percentage": 37.49, "elapsed_time": "3:07:18", "remaining_time": "5:12:20", "throughput": 4414.46, "total_tokens": 49611040} {"current_steps": 22985, "total_steps": 61300, "loss": 0.3571, "lr": 3.934349212076286e-05, "epoch": 3.7495921696574226, "percentage": 37.5, "elapsed_time": "3:07:20", "remaining_time": "5:12:17", "throughput": 4414.51, "total_tokens": 49621472} {"current_steps": 22990, "total_steps": 61300, "loss": 0.3192, "lr": 3.933766164355145e-05, "epoch": 3.7504078303425774, "percentage": 37.5, "elapsed_time": "3:07:22", "remaining_time": "5:12:14", "throughput": 4414.59, "total_tokens": 49632832} {"current_steps": 22995, "total_steps": 61300, "loss": 0.3342, "lr": 3.9331830004056424e-05, "epoch": 3.7512234910277327, "percentage": 37.51, "elapsed_time": "3:07:25", "remaining_time": "5:12:11", "throughput": 4414.68, "total_tokens": 49643136} {"current_steps": 23000, "total_steps": 61300, "loss": 0.3481, "lr": 3.932599720275055e-05, "epoch": 3.7520391517128875, "percentage": 37.52, "elapsed_time": "3:07:27", "remaining_time": "5:12:09", "throughput": 4414.74, "total_tokens": 49653920} {"current_steps": 23005, "total_steps": 61300, "loss": 0.3007, "lr": 3.9320163240106656e-05, "epoch": 3.7528548123980423, "percentage": 37.53, "elapsed_time": "3:07:29", "remaining_time": "5:12:06", "throughput": 4414.82, "total_tokens": 49664992} {"current_steps": 23010, "total_steps": 61300, "loss": 0.3487, "lr": 3.931432811659766e-05, "epoch": 3.753670473083197, "percentage": 37.54, "elapsed_time": "3:07:31", "remaining_time": "5:12:03", "throughput": 4414.91, "total_tokens": 49676000} {"current_steps": 23015, "total_steps": 61300, "loss": 0.3797, "lr": 3.9308491832696596e-05, "epoch": 3.7544861337683524, "percentage": 37.54, "elapsed_time": "3:07:34", "remaining_time": "5:12:01", "throughput": 4414.98, "total_tokens": 49687712} {"current_steps": 23020, "total_steps": 61300, "loss": 0.3256, "lr": 3.930265438887659e-05, "epoch": 3.755301794453507, "percentage": 37.55, "elapsed_time": "3:07:36", "remaining_time": "5:11:58", "throughput": 4415.06, "total_tokens": 49698944} {"current_steps": 23025, "total_steps": 61300, "loss": 0.4296, "lr": 3.929681578561084e-05, "epoch": 3.7561174551386625, "percentage": 37.56, "elapsed_time": "3:07:38", "remaining_time": "5:11:56", "throughput": 4415.15, "total_tokens": 49710048} {"current_steps": 23030, "total_steps": 61300, "loss": 0.3259, "lr": 3.929097602337267e-05, "epoch": 3.7569331158238173, "percentage": 37.57, "elapsed_time": "3:07:41", "remaining_time": "5:11:53", "throughput": 4415.23, "total_tokens": 49720672} {"current_steps": 23035, "total_steps": 61300, "loss": 0.343, "lr": 3.9285135102635474e-05, "epoch": 3.757748776508972, "percentage": 37.58, "elapsed_time": "3:07:43", "remaining_time": "5:11:50", "throughput": 4415.34, "total_tokens": 49731776} {"current_steps": 23040, "total_steps": 61300, "loss": 0.3272, "lr": 3.9279293023872745e-05, "epoch": 3.7585644371941274, "percentage": 37.59, "elapsed_time": "3:07:45", "remaining_time": "5:11:47", "throughput": 4415.41, "total_tokens": 49742336} {"current_steps": 23045, "total_steps": 61300, "loss": 0.3599, "lr": 3.927344978755806e-05, "epoch": 3.759380097879282, "percentage": 37.59, "elapsed_time": "3:07:47", "remaining_time": "5:11:44", "throughput": 4415.49, "total_tokens": 49753408} {"current_steps": 23050, "total_steps": 61300, "loss": 0.3509, "lr": 3.926760539416512e-05, "epoch": 3.7601957585644374, "percentage": 37.6, "elapsed_time": "3:07:50", "remaining_time": "5:11:42", "throughput": 4415.57, "total_tokens": 49764192} {"current_steps": 23055, "total_steps": 61300, "loss": 0.3715, "lr": 3.926175984416769e-05, "epoch": 3.7610114192495923, "percentage": 37.61, "elapsed_time": "3:07:52", "remaining_time": "5:11:39", "throughput": 4415.66, "total_tokens": 49775840} {"current_steps": 23060, "total_steps": 61300, "loss": 0.3148, "lr": 3.9255913138039645e-05, "epoch": 3.761827079934747, "percentage": 37.62, "elapsed_time": "3:07:54", "remaining_time": "5:11:36", "throughput": 4415.71, "total_tokens": 49785408} {"current_steps": 23065, "total_steps": 61300, "loss": 0.3205, "lr": 3.925006527625494e-05, "epoch": 3.762642740619902, "percentage": 37.63, "elapsed_time": "3:07:56", "remaining_time": "5:11:33", "throughput": 4415.8, "total_tokens": 49796192} {"current_steps": 23070, "total_steps": 61300, "loss": 0.3633, "lr": 3.924421625928765e-05, "epoch": 3.763458401305057, "percentage": 37.63, "elapsed_time": "3:07:59", "remaining_time": "5:11:30", "throughput": 4415.89, "total_tokens": 49807296} {"current_steps": 23075, "total_steps": 61300, "loss": 0.3021, "lr": 3.923836608761192e-05, "epoch": 3.764274061990212, "percentage": 37.64, "elapsed_time": "3:08:01", "remaining_time": "5:11:28", "throughput": 4415.95, "total_tokens": 49818368} {"current_steps": 23080, "total_steps": 61300, "loss": 0.338, "lr": 3.923251476170198e-05, "epoch": 3.7650897226753672, "percentage": 37.65, "elapsed_time": "3:08:03", "remaining_time": "5:11:26", "throughput": 4416.04, "total_tokens": 49830368} {"current_steps": 23085, "total_steps": 61300, "loss": 0.3285, "lr": 3.922666228203218e-05, "epoch": 3.765905383360522, "percentage": 37.66, "elapsed_time": "3:08:06", "remaining_time": "5:11:23", "throughput": 4416.12, "total_tokens": 49840960} {"current_steps": 23090, "total_steps": 61300, "loss": 0.4067, "lr": 3.9220808649076954e-05, "epoch": 3.766721044045677, "percentage": 37.67, "elapsed_time": "3:08:08", "remaining_time": "5:11:20", "throughput": 4416.21, "total_tokens": 49851776} {"current_steps": 23095, "total_steps": 61300, "loss": 0.3744, "lr": 3.921495386331082e-05, "epoch": 3.767536704730832, "percentage": 37.68, "elapsed_time": "3:08:10", "remaining_time": "5:11:17", "throughput": 4416.29, "total_tokens": 49862336} {"current_steps": 23100, "total_steps": 61300, "loss": 0.3481, "lr": 3.9209097925208405e-05, "epoch": 3.768352365415987, "percentage": 37.68, "elapsed_time": "3:08:12", "remaining_time": "5:11:14", "throughput": 4416.39, "total_tokens": 49874208} {"current_steps": 23105, "total_steps": 61300, "loss": 0.3405, "lr": 3.920324083524441e-05, "epoch": 3.7691680261011418, "percentage": 37.69, "elapsed_time": "3:08:15", "remaining_time": "5:11:12", "throughput": 4416.47, "total_tokens": 49885440} {"current_steps": 23110, "total_steps": 61300, "loss": 0.3152, "lr": 3.919738259389365e-05, "epoch": 3.769983686786297, "percentage": 37.7, "elapsed_time": "3:08:17", "remaining_time": "5:11:09", "throughput": 4416.56, "total_tokens": 49896832} {"current_steps": 23115, "total_steps": 61300, "loss": 0.3119, "lr": 3.919152320163101e-05, "epoch": 3.770799347471452, "percentage": 37.71, "elapsed_time": "3:08:19", "remaining_time": "5:11:06", "throughput": 4416.63, "total_tokens": 49907008} {"current_steps": 23120, "total_steps": 61300, "loss": 0.3457, "lr": 3.91856626589315e-05, "epoch": 3.7716150081566067, "percentage": 37.72, "elapsed_time": "3:08:21", "remaining_time": "5:11:03", "throughput": 4416.71, "total_tokens": 49917600} {"current_steps": 23125, "total_steps": 61300, "loss": 0.3393, "lr": 3.91798009662702e-05, "epoch": 3.772430668841762, "percentage": 37.72, "elapsed_time": "3:08:24", "remaining_time": "5:11:01", "throughput": 4416.8, "total_tokens": 49929280} {"current_steps": 23130, "total_steps": 61300, "loss": 0.3388, "lr": 3.917393812412229e-05, "epoch": 3.7732463295269167, "percentage": 37.73, "elapsed_time": "3:08:26", "remaining_time": "5:10:58", "throughput": 4416.9, "total_tokens": 49940384} {"current_steps": 23135, "total_steps": 61300, "loss": 0.3317, "lr": 3.916807413296303e-05, "epoch": 3.774061990212072, "percentage": 37.74, "elapsed_time": "3:08:28", "remaining_time": "5:10:55", "throughput": 4416.97, "total_tokens": 49949696} {"current_steps": 23140, "total_steps": 61300, "loss": 0.3671, "lr": 3.916220899326779e-05, "epoch": 3.774877650897227, "percentage": 37.75, "elapsed_time": "3:08:30", "remaining_time": "5:10:52", "throughput": 4417.04, "total_tokens": 49959680} {"current_steps": 23145, "total_steps": 61300, "loss": 0.3691, "lr": 3.915634270551204e-05, "epoch": 3.7756933115823816, "percentage": 37.76, "elapsed_time": "3:08:32", "remaining_time": "5:10:49", "throughput": 4417.11, "total_tokens": 49970592} {"current_steps": 23150, "total_steps": 61300, "loss": 0.363, "lr": 3.915047527017132e-05, "epoch": 3.7765089722675365, "percentage": 37.77, "elapsed_time": "3:08:35", "remaining_time": "5:10:46", "throughput": 4417.2, "total_tokens": 49981440} {"current_steps": 23155, "total_steps": 61300, "loss": 0.3522, "lr": 3.914460668772127e-05, "epoch": 3.7773246329526917, "percentage": 37.77, "elapsed_time": "3:08:37", "remaining_time": "5:10:44", "throughput": 4417.28, "total_tokens": 49993024} {"current_steps": 23160, "total_steps": 61300, "loss": 0.3552, "lr": 3.913873695863763e-05, "epoch": 3.7781402936378465, "percentage": 37.78, "elapsed_time": "3:08:40", "remaining_time": "5:10:41", "throughput": 4417.37, "total_tokens": 50004704} {"current_steps": 23165, "total_steps": 61300, "loss": 0.3398, "lr": 3.913286608339625e-05, "epoch": 3.778955954323002, "percentage": 37.79, "elapsed_time": "3:08:42", "remaining_time": "5:10:39", "throughput": 4417.44, "total_tokens": 50015424} {"current_steps": 23170, "total_steps": 61300, "loss": 0.3325, "lr": 3.9126994062473013e-05, "epoch": 3.7797716150081566, "percentage": 37.8, "elapsed_time": "3:08:44", "remaining_time": "5:10:36", "throughput": 4417.54, "total_tokens": 50026368} {"current_steps": 23175, "total_steps": 61300, "loss": 0.3349, "lr": 3.912112089634397e-05, "epoch": 3.7805872756933114, "percentage": 37.81, "elapsed_time": "3:08:46", "remaining_time": "5:10:33", "throughput": 4417.62, "total_tokens": 50036512} {"current_steps": 23180, "total_steps": 61300, "loss": 0.3432, "lr": 3.911524658548522e-05, "epoch": 3.7814029363784667, "percentage": 37.81, "elapsed_time": "3:08:48", "remaining_time": "5:10:30", "throughput": 4417.7, "total_tokens": 50047776} {"current_steps": 23185, "total_steps": 61300, "loss": 0.3769, "lr": 3.9109371130372956e-05, "epoch": 3.7822185970636215, "percentage": 37.82, "elapsed_time": "3:08:51", "remaining_time": "5:10:27", "throughput": 4417.77, "total_tokens": 50058048} {"current_steps": 23190, "total_steps": 61300, "loss": 0.3666, "lr": 3.910349453148348e-05, "epoch": 3.7830342577487768, "percentage": 37.83, "elapsed_time": "3:08:53", "remaining_time": "5:10:24", "throughput": 4417.86, "total_tokens": 50068992} {"current_steps": 23195, "total_steps": 61300, "loss": 0.326, "lr": 3.909761678929318e-05, "epoch": 3.7838499184339316, "percentage": 37.84, "elapsed_time": "3:08:55", "remaining_time": "5:10:22", "throughput": 4417.94, "total_tokens": 50079776} {"current_steps": 23200, "total_steps": 61300, "loss": 0.3407, "lr": 3.909173790427852e-05, "epoch": 3.7846655791190864, "percentage": 37.85, "elapsed_time": "3:08:57", "remaining_time": "5:10:19", "throughput": 4418.0, "total_tokens": 50090592} {"current_steps": 23205, "total_steps": 61300, "loss": 0.3498, "lr": 3.90858578769161e-05, "epoch": 3.7854812398042412, "percentage": 37.85, "elapsed_time": "3:09:00", "remaining_time": "5:10:16", "throughput": 4418.1, "total_tokens": 50102240} {"current_steps": 23210, "total_steps": 61300, "loss": 0.3327, "lr": 3.907997670768256e-05, "epoch": 3.7862969004893965, "percentage": 37.86, "elapsed_time": "3:09:02", "remaining_time": "5:10:14", "throughput": 4418.18, "total_tokens": 50113472} {"current_steps": 23215, "total_steps": 61300, "loss": 0.3396, "lr": 3.907409439705467e-05, "epoch": 3.7871125611745513, "percentage": 37.87, "elapsed_time": "3:09:04", "remaining_time": "5:10:11", "throughput": 4418.25, "total_tokens": 50124224} {"current_steps": 23220, "total_steps": 61300, "loss": 0.3496, "lr": 3.9068210945509276e-05, "epoch": 3.7879282218597066, "percentage": 37.88, "elapsed_time": "3:09:07", "remaining_time": "5:10:08", "throughput": 4418.32, "total_tokens": 50135264} {"current_steps": 23225, "total_steps": 61300, "loss": 0.3572, "lr": 3.906232635352333e-05, "epoch": 3.7887438825448614, "percentage": 37.89, "elapsed_time": "3:09:09", "remaining_time": "5:10:06", "throughput": 4418.4, "total_tokens": 50145824} {"current_steps": 23230, "total_steps": 61300, "loss": 0.3806, "lr": 3.9056440621573855e-05, "epoch": 3.789559543230016, "percentage": 37.9, "elapsed_time": "3:09:11", "remaining_time": "5:10:03", "throughput": 4418.47, "total_tokens": 50156864} {"current_steps": 23235, "total_steps": 61300, "loss": 0.3315, "lr": 3.9050553750137975e-05, "epoch": 3.790375203915171, "percentage": 37.9, "elapsed_time": "3:09:13", "remaining_time": "5:10:00", "throughput": 4418.54, "total_tokens": 50167872} {"current_steps": 23240, "total_steps": 61300, "loss": 0.3572, "lr": 3.904466573969292e-05, "epoch": 3.7911908646003263, "percentage": 37.91, "elapsed_time": "3:09:16", "remaining_time": "5:09:58", "throughput": 4418.61, "total_tokens": 50178880} {"current_steps": 23245, "total_steps": 61300, "loss": 0.338, "lr": 3.9038776590716e-05, "epoch": 3.792006525285481, "percentage": 37.92, "elapsed_time": "3:09:18", "remaining_time": "5:09:55", "throughput": 4418.7, "total_tokens": 50189280} {"current_steps": 23250, "total_steps": 61300, "loss": 0.3781, "lr": 3.903288630368461e-05, "epoch": 3.7928221859706364, "percentage": 37.93, "elapsed_time": "3:09:20", "remaining_time": "5:09:52", "throughput": 4418.79, "total_tokens": 50200736} {"current_steps": 23255, "total_steps": 61300, "loss": 0.3431, "lr": 3.902699487907626e-05, "epoch": 3.793637846655791, "percentage": 37.94, "elapsed_time": "3:09:22", "remaining_time": "5:09:49", "throughput": 4418.87, "total_tokens": 50210208} {"current_steps": 23260, "total_steps": 61300, "loss": 0.3267, "lr": 3.902110231736853e-05, "epoch": 3.794453507340946, "percentage": 37.94, "elapsed_time": "3:09:24", "remaining_time": "5:09:46", "throughput": 4418.94, "total_tokens": 50220960} {"current_steps": 23265, "total_steps": 61300, "loss": 0.3332, "lr": 3.901520861903911e-05, "epoch": 3.7952691680261013, "percentage": 37.95, "elapsed_time": "3:09:27", "remaining_time": "5:09:43", "throughput": 4419.01, "total_tokens": 50232384} {"current_steps": 23270, "total_steps": 61300, "loss": 0.3178, "lr": 3.900931378456576e-05, "epoch": 3.796084828711256, "percentage": 37.96, "elapsed_time": "3:09:29", "remaining_time": "5:09:41", "throughput": 4419.1, "total_tokens": 50243328} {"current_steps": 23275, "total_steps": 61300, "loss": 0.3467, "lr": 3.9003417814426346e-05, "epoch": 3.7969004893964113, "percentage": 37.97, "elapsed_time": "3:09:31", "remaining_time": "5:09:38", "throughput": 4419.18, "total_tokens": 50254080} {"current_steps": 23280, "total_steps": 61300, "loss": 0.3132, "lr": 3.8997520709098845e-05, "epoch": 3.797716150081566, "percentage": 37.98, "elapsed_time": "3:09:33", "remaining_time": "5:09:35", "throughput": 4419.25, "total_tokens": 50264384} {"current_steps": 23285, "total_steps": 61300, "loss": 0.3273, "lr": 3.899162246906129e-05, "epoch": 3.798531810766721, "percentage": 37.99, "elapsed_time": "3:09:36", "remaining_time": "5:09:32", "throughput": 4419.33, "total_tokens": 50275232} {"current_steps": 23290, "total_steps": 61300, "loss": 0.3694, "lr": 3.8985723094791814e-05, "epoch": 3.799347471451876, "percentage": 37.99, "elapsed_time": "3:09:38", "remaining_time": "5:09:29", "throughput": 4419.41, "total_tokens": 50286048} {"current_steps": 23295, "total_steps": 61300, "loss": 0.3861, "lr": 3.897982258676867e-05, "epoch": 3.800163132137031, "percentage": 38.0, "elapsed_time": "3:09:40", "remaining_time": "5:09:26", "throughput": 4419.49, "total_tokens": 50296192} {"current_steps": 23300, "total_steps": 61300, "loss": 0.3361, "lr": 3.8973920945470174e-05, "epoch": 3.800978792822186, "percentage": 38.01, "elapsed_time": "3:09:42", "remaining_time": "5:09:23", "throughput": 4419.56, "total_tokens": 50305888} {"current_steps": 23305, "total_steps": 61300, "loss": 0.3623, "lr": 3.896801817137474e-05, "epoch": 3.801794453507341, "percentage": 38.02, "elapsed_time": "3:09:44", "remaining_time": "5:09:21", "throughput": 4419.64, "total_tokens": 50316640} {"current_steps": 23310, "total_steps": 61300, "loss": 0.3179, "lr": 3.8962114264960894e-05, "epoch": 3.802610114192496, "percentage": 38.03, "elapsed_time": "3:09:47", "remaining_time": "5:09:18", "throughput": 4419.73, "total_tokens": 50328832} {"current_steps": 23315, "total_steps": 61300, "loss": 0.3838, "lr": 3.8956209226707206e-05, "epoch": 3.8034257748776508, "percentage": 38.03, "elapsed_time": "3:09:49", "remaining_time": "5:09:15", "throughput": 4419.81, "total_tokens": 50339136} {"current_steps": 23320, "total_steps": 61300, "loss": 0.3499, "lr": 3.8950303057092386e-05, "epoch": 3.804241435562806, "percentage": 38.04, "elapsed_time": "3:09:51", "remaining_time": "5:09:13", "throughput": 4419.88, "total_tokens": 50350336} {"current_steps": 23325, "total_steps": 61300, "loss": 0.3534, "lr": 3.8944395756595225e-05, "epoch": 3.805057096247961, "percentage": 38.05, "elapsed_time": "3:09:54", "remaining_time": "5:09:10", "throughput": 4419.97, "total_tokens": 50361376} {"current_steps": 23330, "total_steps": 61300, "loss": 0.3369, "lr": 3.893848732569458e-05, "epoch": 3.8058727569331157, "percentage": 38.06, "elapsed_time": "3:09:56", "remaining_time": "5:09:07", "throughput": 4420.04, "total_tokens": 50372064} {"current_steps": 23335, "total_steps": 61300, "loss": 0.3313, "lr": 3.893257776486944e-05, "epoch": 3.806688417618271, "percentage": 38.07, "elapsed_time": "3:09:58", "remaining_time": "5:09:04", "throughput": 4420.14, "total_tokens": 50382304} {"current_steps": 23340, "total_steps": 61300, "loss": 0.3588, "lr": 3.8926667074598846e-05, "epoch": 3.8075040783034257, "percentage": 38.08, "elapsed_time": "3:10:00", "remaining_time": "5:09:01", "throughput": 4420.21, "total_tokens": 50392416} {"current_steps": 23345, "total_steps": 61300, "loss": 0.3662, "lr": 3.892075525536196e-05, "epoch": 3.8083197389885806, "percentage": 38.08, "elapsed_time": "3:10:02", "remaining_time": "5:08:58", "throughput": 4420.28, "total_tokens": 50402816} {"current_steps": 23350, "total_steps": 61300, "loss": 0.3471, "lr": 3.891484230763802e-05, "epoch": 3.809135399673736, "percentage": 38.09, "elapsed_time": "3:10:04", "remaining_time": "5:08:55", "throughput": 4420.34, "total_tokens": 50412224} {"current_steps": 23355, "total_steps": 61300, "loss": 0.3814, "lr": 3.890892823190636e-05, "epoch": 3.8099510603588906, "percentage": 38.1, "elapsed_time": "3:10:06", "remaining_time": "5:08:52", "throughput": 4420.42, "total_tokens": 50423680} {"current_steps": 23360, "total_steps": 61300, "loss": 0.3577, "lr": 3.890301302864641e-05, "epoch": 3.810766721044046, "percentage": 38.11, "elapsed_time": "3:10:09", "remaining_time": "5:08:50", "throughput": 4420.5, "total_tokens": 50435072} {"current_steps": 23365, "total_steps": 61300, "loss": 0.3555, "lr": 3.889709669833767e-05, "epoch": 3.8115823817292007, "percentage": 38.12, "elapsed_time": "3:10:11", "remaining_time": "5:08:47", "throughput": 4420.59, "total_tokens": 50446336} {"current_steps": 23370, "total_steps": 61300, "loss": 0.3643, "lr": 3.8891179241459766e-05, "epoch": 3.8123980424143555, "percentage": 38.12, "elapsed_time": "3:10:13", "remaining_time": "5:08:44", "throughput": 4420.66, "total_tokens": 50456928} {"current_steps": 23375, "total_steps": 61300, "loss": 0.3249, "lr": 3.888526065849238e-05, "epoch": 3.8132137030995104, "percentage": 38.13, "elapsed_time": "3:10:16", "remaining_time": "5:08:42", "throughput": 4420.74, "total_tokens": 50467488} {"current_steps": 23380, "total_steps": 61300, "loss": 0.3519, "lr": 3.887934094991531e-05, "epoch": 3.8140293637846656, "percentage": 38.14, "elapsed_time": "3:10:18", "remaining_time": "5:08:39", "throughput": 4420.84, "total_tokens": 50479168} {"current_steps": 23385, "total_steps": 61300, "loss": 0.3529, "lr": 3.887342011620845e-05, "epoch": 3.8148450244698204, "percentage": 38.15, "elapsed_time": "3:10:20", "remaining_time": "5:08:36", "throughput": 4420.93, "total_tokens": 50490048} {"current_steps": 23390, "total_steps": 61300, "loss": 0.3462, "lr": 3.886749815785176e-05, "epoch": 3.8156606851549757, "percentage": 38.16, "elapsed_time": "3:10:22", "remaining_time": "5:08:33", "throughput": 4421.0, "total_tokens": 50500192} {"current_steps": 23395, "total_steps": 61300, "loss": 0.3329, "lr": 3.8861575075325304e-05, "epoch": 3.8164763458401305, "percentage": 38.16, "elapsed_time": "3:10:25", "remaining_time": "5:08:31", "throughput": 4421.07, "total_tokens": 50510944} {"current_steps": 23400, "total_steps": 61300, "loss": 0.3489, "lr": 3.8855650869109246e-05, "epoch": 3.8172920065252853, "percentage": 38.17, "elapsed_time": "3:10:27", "remaining_time": "5:08:28", "throughput": 4421.15, "total_tokens": 50521344} {"current_steps": 23405, "total_steps": 61300, "loss": 0.3217, "lr": 3.884972553968382e-05, "epoch": 3.8181076672104406, "percentage": 38.18, "elapsed_time": "3:10:29", "remaining_time": "5:08:25", "throughput": 4421.24, "total_tokens": 50532064} {"current_steps": 23410, "total_steps": 61300, "loss": 0.3409, "lr": 3.884379908752936e-05, "epoch": 3.8189233278955954, "percentage": 38.19, "elapsed_time": "3:10:31", "remaining_time": "5:08:22", "throughput": 4421.32, "total_tokens": 50542816} {"current_steps": 23415, "total_steps": 61300, "loss": 0.3428, "lr": 3.883787151312632e-05, "epoch": 3.8197389885807507, "percentage": 38.2, "elapsed_time": "3:10:33", "remaining_time": "5:08:19", "throughput": 4421.39, "total_tokens": 50553088} {"current_steps": 23420, "total_steps": 61300, "loss": 0.3124, "lr": 3.88319428169552e-05, "epoch": 3.8205546492659055, "percentage": 38.21, "elapsed_time": "3:10:35", "remaining_time": "5:08:16", "throughput": 4421.45, "total_tokens": 50561792} {"current_steps": 23425, "total_steps": 61300, "loss": 0.3582, "lr": 3.882601299949661e-05, "epoch": 3.8213703099510603, "percentage": 38.21, "elapsed_time": "3:10:37", "remaining_time": "5:08:13", "throughput": 4421.55, "total_tokens": 50573280} {"current_steps": 23430, "total_steps": 61300, "loss": 0.3031, "lr": 3.882008206123125e-05, "epoch": 3.822185970636215, "percentage": 38.22, "elapsed_time": "3:10:40", "remaining_time": "5:08:10", "throughput": 4421.62, "total_tokens": 50584384} {"current_steps": 23435, "total_steps": 61300, "loss": 0.3564, "lr": 3.881415000263991e-05, "epoch": 3.8230016313213704, "percentage": 38.23, "elapsed_time": "3:10:42", "remaining_time": "5:08:08", "throughput": 4421.7, "total_tokens": 50595904} {"current_steps": 23440, "total_steps": 61300, "loss": 0.3131, "lr": 3.8808216824203494e-05, "epoch": 3.823817292006525, "percentage": 38.24, "elapsed_time": "3:10:45", "remaining_time": "5:08:06", "throughput": 4421.8, "total_tokens": 50608224} {"current_steps": 23445, "total_steps": 61300, "loss": 0.3702, "lr": 3.880228252640295e-05, "epoch": 3.8246329526916805, "percentage": 38.25, "elapsed_time": "3:10:47", "remaining_time": "5:08:03", "throughput": 4421.87, "total_tokens": 50618912} {"current_steps": 23450, "total_steps": 61300, "loss": 0.381, "lr": 3.879634710971935e-05, "epoch": 3.8254486133768353, "percentage": 38.25, "elapsed_time": "3:10:49", "remaining_time": "5:08:00", "throughput": 4421.96, "total_tokens": 50629728} {"current_steps": 23455, "total_steps": 61300, "loss": 0.3907, "lr": 3.8790410574633854e-05, "epoch": 3.82626427406199, "percentage": 38.26, "elapsed_time": "3:10:51", "remaining_time": "5:07:57", "throughput": 4422.03, "total_tokens": 50640096} {"current_steps": 23460, "total_steps": 61300, "loss": 0.3484, "lr": 3.8784472921627715e-05, "epoch": 3.827079934747145, "percentage": 38.27, "elapsed_time": "3:10:53", "remaining_time": "5:07:54", "throughput": 4422.11, "total_tokens": 50650176} {"current_steps": 23465, "total_steps": 61300, "loss": 0.3383, "lr": 3.877853415118224e-05, "epoch": 3.8278955954323, "percentage": 38.28, "elapsed_time": "3:10:56", "remaining_time": "5:07:51", "throughput": 4422.19, "total_tokens": 50661504} {"current_steps": 23470, "total_steps": 61300, "loss": 0.3462, "lr": 3.877259426377889e-05, "epoch": 3.828711256117455, "percentage": 38.29, "elapsed_time": "3:10:58", "remaining_time": "5:07:49", "throughput": 4422.28, "total_tokens": 50672384} {"current_steps": 23475, "total_steps": 61300, "loss": 0.3408, "lr": 3.8766653259899165e-05, "epoch": 3.8295269168026103, "percentage": 38.3, "elapsed_time": "3:11:00", "remaining_time": "5:07:46", "throughput": 4422.37, "total_tokens": 50683168} {"current_steps": 23480, "total_steps": 61300, "loss": 0.341, "lr": 3.8760711140024677e-05, "epoch": 3.830342577487765, "percentage": 38.3, "elapsed_time": "3:11:02", "remaining_time": "5:07:43", "throughput": 4422.43, "total_tokens": 50692512} {"current_steps": 23485, "total_steps": 61300, "loss": 0.3321, "lr": 3.875476790463712e-05, "epoch": 3.83115823817292, "percentage": 38.31, "elapsed_time": "3:11:04", "remaining_time": "5:07:40", "throughput": 4422.49, "total_tokens": 50703168} {"current_steps": 23490, "total_steps": 61300, "loss": 0.3351, "lr": 3.8748823554218286e-05, "epoch": 3.831973898858075, "percentage": 38.32, "elapsed_time": "3:11:07", "remaining_time": "5:07:37", "throughput": 4422.59, "total_tokens": 50714112} {"current_steps": 23495, "total_steps": 61300, "loss": 0.3408, "lr": 3.8742878089250043e-05, "epoch": 3.83278955954323, "percentage": 38.33, "elapsed_time": "3:11:09", "remaining_time": "5:07:34", "throughput": 4422.65, "total_tokens": 50724576} {"current_steps": 23500, "total_steps": 61300, "loss": 0.3431, "lr": 3.8736931510214385e-05, "epoch": 3.8336052202283852, "percentage": 38.34, "elapsed_time": "3:11:11", "remaining_time": "5:07:32", "throughput": 4422.73, "total_tokens": 50735392} {"current_steps": 23505, "total_steps": 61300, "loss": 0.3192, "lr": 3.873098381759336e-05, "epoch": 3.83442088091354, "percentage": 38.34, "elapsed_time": "3:11:14", "remaining_time": "5:07:29", "throughput": 4422.82, "total_tokens": 50747488} {"current_steps": 23510, "total_steps": 61300, "loss": 0.3586, "lr": 3.872503501186911e-05, "epoch": 3.835236541598695, "percentage": 38.35, "elapsed_time": "3:11:16", "remaining_time": "5:07:26", "throughput": 4422.89, "total_tokens": 50757120} {"current_steps": 23515, "total_steps": 61300, "loss": 0.3416, "lr": 3.871908509352388e-05, "epoch": 3.8360522022838497, "percentage": 38.36, "elapsed_time": "3:11:18", "remaining_time": "5:07:23", "throughput": 4422.95, "total_tokens": 50767136} {"current_steps": 23520, "total_steps": 61300, "loss": 0.3367, "lr": 3.871313406304001e-05, "epoch": 3.836867862969005, "percentage": 38.37, "elapsed_time": "3:11:20", "remaining_time": "5:07:20", "throughput": 4423.03, "total_tokens": 50777728} {"current_steps": 23525, "total_steps": 61300, "loss": 0.334, "lr": 3.87071819208999e-05, "epoch": 3.8376835236541598, "percentage": 38.38, "elapsed_time": "3:11:22", "remaining_time": "5:07:17", "throughput": 4423.1, "total_tokens": 50787488} {"current_steps": 23530, "total_steps": 61300, "loss": 0.3234, "lr": 3.870122866758609e-05, "epoch": 3.838499184339315, "percentage": 38.38, "elapsed_time": "3:11:24", "remaining_time": "5:07:14", "throughput": 4423.18, "total_tokens": 50797760} {"current_steps": 23535, "total_steps": 61300, "loss": 0.3633, "lr": 3.869527430358116e-05, "epoch": 3.83931484502447, "percentage": 38.39, "elapsed_time": "3:11:26", "remaining_time": "5:07:11", "throughput": 4423.26, "total_tokens": 50808832} {"current_steps": 23540, "total_steps": 61300, "loss": 0.3382, "lr": 3.8689318829367796e-05, "epoch": 3.8401305057096247, "percentage": 38.4, "elapsed_time": "3:11:28", "remaining_time": "5:07:09", "throughput": 4423.33, "total_tokens": 50819296} {"current_steps": 23545, "total_steps": 61300, "loss": 0.3355, "lr": 3.86833622454288e-05, "epoch": 3.84094616639478, "percentage": 38.41, "elapsed_time": "3:11:31", "remaining_time": "5:07:06", "throughput": 4423.42, "total_tokens": 50831424} {"current_steps": 23550, "total_steps": 61300, "loss": 0.3362, "lr": 3.8677404552247024e-05, "epoch": 3.8417618270799347, "percentage": 38.42, "elapsed_time": "3:11:33", "remaining_time": "5:07:03", "throughput": 4423.49, "total_tokens": 50841152} {"current_steps": 23555, "total_steps": 61300, "loss": 0.3796, "lr": 3.8671445750305444e-05, "epoch": 3.8425774877650896, "percentage": 38.43, "elapsed_time": "3:11:35", "remaining_time": "5:07:00", "throughput": 4423.56, "total_tokens": 50850752} {"current_steps": 23560, "total_steps": 61300, "loss": 0.3611, "lr": 3.8665485840087104e-05, "epoch": 3.843393148450245, "percentage": 38.43, "elapsed_time": "3:11:37", "remaining_time": "5:06:57", "throughput": 4423.63, "total_tokens": 50860896} {"current_steps": 23565, "total_steps": 61300, "loss": 0.3321, "lr": 3.865952482207513e-05, "epoch": 3.8442088091353996, "percentage": 38.44, "elapsed_time": "3:11:39", "remaining_time": "5:06:54", "throughput": 4423.71, "total_tokens": 50871072} {"current_steps": 23570, "total_steps": 61300, "loss": 0.3471, "lr": 3.865356269675278e-05, "epoch": 3.8450244698205545, "percentage": 38.45, "elapsed_time": "3:11:41", "remaining_time": "5:06:51", "throughput": 4423.77, "total_tokens": 50880960} {"current_steps": 23575, "total_steps": 61300, "loss": 0.3619, "lr": 3.8647599464603355e-05, "epoch": 3.8458401305057097, "percentage": 38.46, "elapsed_time": "3:11:43", "remaining_time": "5:06:48", "throughput": 4423.82, "total_tokens": 50890080} {"current_steps": 23580, "total_steps": 61300, "loss": 0.3353, "lr": 3.864163512611028e-05, "epoch": 3.8466557911908645, "percentage": 38.47, "elapsed_time": "3:11:45", "remaining_time": "5:06:45", "throughput": 4423.9, "total_tokens": 50901216} {"current_steps": 23585, "total_steps": 61300, "loss": 0.3152, "lr": 3.863566968175703e-05, "epoch": 3.84747145187602, "percentage": 38.47, "elapsed_time": "3:11:48", "remaining_time": "5:06:42", "throughput": 4423.98, "total_tokens": 50912416} {"current_steps": 23590, "total_steps": 61300, "loss": 0.3357, "lr": 3.862970313202722e-05, "epoch": 3.8482871125611746, "percentage": 38.48, "elapsed_time": "3:11:50", "remaining_time": "5:06:40", "throughput": 4424.04, "total_tokens": 50922752} {"current_steps": 23595, "total_steps": 61300, "loss": 0.3262, "lr": 3.86237354774045e-05, "epoch": 3.8491027732463294, "percentage": 38.49, "elapsed_time": "3:11:53", "remaining_time": "5:06:37", "throughput": 4424.14, "total_tokens": 50935168} {"current_steps": 23600, "total_steps": 61300, "loss": 0.3653, "lr": 3.861776671837267e-05, "epoch": 3.8499184339314843, "percentage": 38.5, "elapsed_time": "3:11:55", "remaining_time": "5:06:35", "throughput": 4424.22, "total_tokens": 50946304} {"current_steps": 23605, "total_steps": 61300, "loss": 0.3598, "lr": 3.861179685541557e-05, "epoch": 3.8507340946166395, "percentage": 38.51, "elapsed_time": "3:11:57", "remaining_time": "5:06:32", "throughput": 4424.29, "total_tokens": 50955872} {"current_steps": 23610, "total_steps": 61300, "loss": 0.3204, "lr": 3.8605825889017156e-05, "epoch": 3.8515497553017943, "percentage": 38.52, "elapsed_time": "3:11:59", "remaining_time": "5:06:29", "throughput": 4424.39, "total_tokens": 50967488} {"current_steps": 23615, "total_steps": 61300, "loss": 0.3667, "lr": 3.859985381966146e-05, "epoch": 3.8523654159869496, "percentage": 38.52, "elapsed_time": "3:12:01", "remaining_time": "5:06:26", "throughput": 4424.44, "total_tokens": 50977664} {"current_steps": 23620, "total_steps": 61300, "loss": 0.3404, "lr": 3.8593880647832606e-05, "epoch": 3.8531810766721044, "percentage": 38.53, "elapsed_time": "3:12:04", "remaining_time": "5:06:24", "throughput": 4424.55, "total_tokens": 50989920} {"current_steps": 23625, "total_steps": 61300, "loss": 0.3714, "lr": 3.858790637401482e-05, "epoch": 3.8539967373572592, "percentage": 38.54, "elapsed_time": "3:12:06", "remaining_time": "5:06:21", "throughput": 4424.61, "total_tokens": 50999136} {"current_steps": 23630, "total_steps": 61300, "loss": 0.3491, "lr": 3.858193099869239e-05, "epoch": 3.8548123980424145, "percentage": 38.55, "elapsed_time": "3:12:08", "remaining_time": "5:06:18", "throughput": 4424.68, "total_tokens": 51010336} {"current_steps": 23635, "total_steps": 61300, "loss": 0.3408, "lr": 3.857595452234971e-05, "epoch": 3.8556280587275693, "percentage": 38.56, "elapsed_time": "3:12:10", "remaining_time": "5:06:15", "throughput": 4424.76, "total_tokens": 51021792} {"current_steps": 23640, "total_steps": 61300, "loss": 0.3394, "lr": 3.856997694547129e-05, "epoch": 3.8564437194127246, "percentage": 38.56, "elapsed_time": "3:12:13", "remaining_time": "5:06:13", "throughput": 4424.84, "total_tokens": 51032416} {"current_steps": 23645, "total_steps": 61300, "loss": 0.338, "lr": 3.856399826854168e-05, "epoch": 3.8572593800978794, "percentage": 38.57, "elapsed_time": "3:12:15", "remaining_time": "5:06:10", "throughput": 4424.9, "total_tokens": 51042304} {"current_steps": 23650, "total_steps": 61300, "loss": 0.3428, "lr": 3.855801849204555e-05, "epoch": 3.858075040783034, "percentage": 38.58, "elapsed_time": "3:12:17", "remaining_time": "5:06:07", "throughput": 4424.97, "total_tokens": 51053664} {"current_steps": 23655, "total_steps": 61300, "loss": 0.345, "lr": 3.855203761646764e-05, "epoch": 3.858890701468189, "percentage": 38.59, "elapsed_time": "3:12:19", "remaining_time": "5:06:04", "throughput": 4425.06, "total_tokens": 51064608} {"current_steps": 23660, "total_steps": 61300, "loss": 0.308, "lr": 3.85460556422928e-05, "epoch": 3.8597063621533443, "percentage": 38.6, "elapsed_time": "3:12:21", "remaining_time": "5:06:01", "throughput": 4425.13, "total_tokens": 51074208} {"current_steps": 23665, "total_steps": 61300, "loss": 0.3272, "lr": 3.854007257000596e-05, "epoch": 3.860522022838499, "percentage": 38.61, "elapsed_time": "3:12:24", "remaining_time": "5:05:59", "throughput": 4425.22, "total_tokens": 51085600} {"current_steps": 23670, "total_steps": 61300, "loss": 0.3606, "lr": 3.853408840009214e-05, "epoch": 3.8613376835236544, "percentage": 38.61, "elapsed_time": "3:12:26", "remaining_time": "5:05:56", "throughput": 4425.31, "total_tokens": 51097344} {"current_steps": 23675, "total_steps": 61300, "loss": 0.3568, "lr": 3.8528103133036434e-05, "epoch": 3.862153344208809, "percentage": 38.62, "elapsed_time": "3:12:29", "remaining_time": "5:05:54", "throughput": 4425.4, "total_tokens": 51109184} {"current_steps": 23680, "total_steps": 61300, "loss": 0.3478, "lr": 3.8522116769324056e-05, "epoch": 3.862969004893964, "percentage": 38.63, "elapsed_time": "3:12:31", "remaining_time": "5:05:51", "throughput": 4425.48, "total_tokens": 51120800} {"current_steps": 23685, "total_steps": 61300, "loss": 0.3355, "lr": 3.851612930944027e-05, "epoch": 3.863784665579119, "percentage": 38.64, "elapsed_time": "3:12:33", "remaining_time": "5:05:48", "throughput": 4425.56, "total_tokens": 51131008} {"current_steps": 23690, "total_steps": 61300, "loss": 0.3392, "lr": 3.851014075387048e-05, "epoch": 3.864600326264274, "percentage": 38.65, "elapsed_time": "3:12:35", "remaining_time": "5:05:45", "throughput": 4425.64, "total_tokens": 51141600} {"current_steps": 23695, "total_steps": 61300, "loss": 0.3683, "lr": 3.850415110310012e-05, "epoch": 3.865415986949429, "percentage": 38.65, "elapsed_time": "3:12:37", "remaining_time": "5:05:42", "throughput": 4425.73, "total_tokens": 51152128} {"current_steps": 23700, "total_steps": 61300, "loss": 0.3391, "lr": 3.8498160357614756e-05, "epoch": 3.866231647634584, "percentage": 38.66, "elapsed_time": "3:12:40", "remaining_time": "5:05:40", "throughput": 4425.82, "total_tokens": 51163840} {"current_steps": 23705, "total_steps": 61300, "loss": 0.3249, "lr": 3.8492168517900016e-05, "epoch": 3.867047308319739, "percentage": 38.67, "elapsed_time": "3:12:42", "remaining_time": "5:05:37", "throughput": 4425.89, "total_tokens": 51173984} {"current_steps": 23710, "total_steps": 61300, "loss": 0.3441, "lr": 3.8486175584441643e-05, "epoch": 3.867862969004894, "percentage": 38.68, "elapsed_time": "3:12:44", "remaining_time": "5:05:34", "throughput": 4425.96, "total_tokens": 51185120} {"current_steps": 23715, "total_steps": 61300, "loss": 0.3333, "lr": 3.8480181557725455e-05, "epoch": 3.868678629690049, "percentage": 38.69, "elapsed_time": "3:12:46", "remaining_time": "5:05:32", "throughput": 4426.04, "total_tokens": 51195968} {"current_steps": 23720, "total_steps": 61300, "loss": 0.3792, "lr": 3.847418643823735e-05, "epoch": 3.869494290375204, "percentage": 38.69, "elapsed_time": "3:12:49", "remaining_time": "5:05:29", "throughput": 4426.11, "total_tokens": 51206368} {"current_steps": 23725, "total_steps": 61300, "loss": 0.3774, "lr": 3.8468190226463316e-05, "epoch": 3.870309951060359, "percentage": 38.7, "elapsed_time": "3:12:51", "remaining_time": "5:05:26", "throughput": 4426.18, "total_tokens": 51216928} {"current_steps": 23730, "total_steps": 61300, "loss": 0.3693, "lr": 3.846219292288945e-05, "epoch": 3.871125611745514, "percentage": 38.71, "elapsed_time": "3:12:53", "remaining_time": "5:05:23", "throughput": 4426.26, "total_tokens": 51227936} {"current_steps": 23735, "total_steps": 61300, "loss": 0.3023, "lr": 3.845619452800192e-05, "epoch": 3.8719412724306688, "percentage": 38.72, "elapsed_time": "3:12:55", "remaining_time": "5:05:20", "throughput": 4426.35, "total_tokens": 51238880} {"current_steps": 23740, "total_steps": 61300, "loss": 0.3296, "lr": 3.845019504228699e-05, "epoch": 3.8727569331158236, "percentage": 38.73, "elapsed_time": "3:12:58", "remaining_time": "5:05:18", "throughput": 4426.42, "total_tokens": 51250560} {"current_steps": 23745, "total_steps": 61300, "loss": 0.3417, "lr": 3.8444194466230994e-05, "epoch": 3.873572593800979, "percentage": 38.74, "elapsed_time": "3:13:00", "remaining_time": "5:05:15", "throughput": 4426.49, "total_tokens": 51261440} {"current_steps": 23750, "total_steps": 61300, "loss": 0.3423, "lr": 3.843819280032038e-05, "epoch": 3.8743882544861337, "percentage": 38.74, "elapsed_time": "3:13:02", "remaining_time": "5:05:13", "throughput": 4426.57, "total_tokens": 51272640} {"current_steps": 23755, "total_steps": 61300, "loss": 0.3527, "lr": 3.843219004504168e-05, "epoch": 3.875203915171289, "percentage": 38.75, "elapsed_time": "3:13:05", "remaining_time": "5:05:10", "throughput": 4426.64, "total_tokens": 51284064} {"current_steps": 23760, "total_steps": 61300, "loss": 0.3343, "lr": 3.84261862008815e-05, "epoch": 3.8760195758564437, "percentage": 38.76, "elapsed_time": "3:13:07", "remaining_time": "5:05:07", "throughput": 4426.71, "total_tokens": 51294368} {"current_steps": 23765, "total_steps": 61300, "loss": 0.3739, "lr": 3.8420181268326536e-05, "epoch": 3.8768352365415986, "percentage": 38.77, "elapsed_time": "3:13:09", "remaining_time": "5:05:04", "throughput": 4426.77, "total_tokens": 51304704} {"current_steps": 23770, "total_steps": 61300, "loss": 0.3455, "lr": 3.841417524786359e-05, "epoch": 3.877650897226754, "percentage": 38.78, "elapsed_time": "3:13:11", "remaining_time": "5:05:02", "throughput": 4426.86, "total_tokens": 51316128} {"current_steps": 23775, "total_steps": 61300, "loss": 0.3364, "lr": 3.840816813997954e-05, "epoch": 3.8784665579119086, "percentage": 38.78, "elapsed_time": "3:13:14", "remaining_time": "5:04:59", "throughput": 4426.95, "total_tokens": 51327712} {"current_steps": 23780, "total_steps": 61300, "loss": 0.36, "lr": 3.8402159945161346e-05, "epoch": 3.8792822185970635, "percentage": 38.79, "elapsed_time": "3:13:16", "remaining_time": "5:04:57", "throughput": 4427.02, "total_tokens": 51338624} {"current_steps": 23785, "total_steps": 61300, "loss": 0.346, "lr": 3.839615066389607e-05, "epoch": 3.8800978792822187, "percentage": 38.8, "elapsed_time": "3:13:18", "remaining_time": "5:04:54", "throughput": 4427.09, "total_tokens": 51348928} {"current_steps": 23790, "total_steps": 61300, "loss": 0.3585, "lr": 3.839014029667084e-05, "epoch": 3.8809135399673735, "percentage": 38.81, "elapsed_time": "3:13:21", "remaining_time": "5:04:51", "throughput": 4427.15, "total_tokens": 51359744} {"current_steps": 23795, "total_steps": 61300, "loss": 0.3173, "lr": 3.83841288439729e-05, "epoch": 3.8817292006525284, "percentage": 38.82, "elapsed_time": "3:13:23", "remaining_time": "5:04:49", "throughput": 4427.25, "total_tokens": 51371616} {"current_steps": 23800, "total_steps": 61300, "loss": 0.3559, "lr": 3.837811630628957e-05, "epoch": 3.8825448613376836, "percentage": 38.83, "elapsed_time": "3:13:25", "remaining_time": "5:04:46", "throughput": 4427.33, "total_tokens": 51382752} {"current_steps": 23805, "total_steps": 61300, "loss": 0.3525, "lr": 3.837210268410824e-05, "epoch": 3.8833605220228384, "percentage": 38.83, "elapsed_time": "3:13:28", "remaining_time": "5:04:43", "throughput": 4427.41, "total_tokens": 51393440} {"current_steps": 23810, "total_steps": 61300, "loss": 0.3344, "lr": 3.836608797791642e-05, "epoch": 3.8841761827079937, "percentage": 38.84, "elapsed_time": "3:13:29", "remaining_time": "5:04:40", "throughput": 4427.45, "total_tokens": 51401792} {"current_steps": 23815, "total_steps": 61300, "loss": 0.3436, "lr": 3.8360072188201704e-05, "epoch": 3.8849918433931485, "percentage": 38.85, "elapsed_time": "3:13:32", "remaining_time": "5:04:37", "throughput": 4427.56, "total_tokens": 51413216} {"current_steps": 23820, "total_steps": 61300, "loss": 0.3344, "lr": 3.835405531545173e-05, "epoch": 3.8858075040783033, "percentage": 38.86, "elapsed_time": "3:13:34", "remaining_time": "5:04:34", "throughput": 4427.62, "total_tokens": 51423840} {"current_steps": 23825, "total_steps": 61300, "loss": 0.3478, "lr": 3.834803736015428e-05, "epoch": 3.886623164763458, "percentage": 38.87, "elapsed_time": "3:13:36", "remaining_time": "5:04:31", "throughput": 4427.7, "total_tokens": 51434464} {"current_steps": 23830, "total_steps": 61300, "loss": 0.3954, "lr": 3.8342018322797205e-05, "epoch": 3.8874388254486134, "percentage": 38.87, "elapsed_time": "3:13:38", "remaining_time": "5:04:29", "throughput": 4427.79, "total_tokens": 51446112} {"current_steps": 23835, "total_steps": 61300, "loss": 0.369, "lr": 3.833599820386842e-05, "epoch": 3.8882544861337682, "percentage": 38.88, "elapsed_time": "3:13:41", "remaining_time": "5:04:26", "throughput": 4427.86, "total_tokens": 51456704} {"current_steps": 23840, "total_steps": 61300, "loss": 0.3289, "lr": 3.8329977003855956e-05, "epoch": 3.8890701468189235, "percentage": 38.89, "elapsed_time": "3:13:43", "remaining_time": "5:04:23", "throughput": 4427.93, "total_tokens": 51467424} {"current_steps": 23845, "total_steps": 61300, "loss": 0.3432, "lr": 3.832395472324791e-05, "epoch": 3.8898858075040783, "percentage": 38.9, "elapsed_time": "3:13:45", "remaining_time": "5:04:21", "throughput": 4427.98, "total_tokens": 51477792} {"current_steps": 23850, "total_steps": 61300, "loss": 0.321, "lr": 3.83179313625325e-05, "epoch": 3.890701468189233, "percentage": 38.91, "elapsed_time": "3:13:47", "remaining_time": "5:04:17", "throughput": 4428.03, "total_tokens": 51486368} {"current_steps": 23855, "total_steps": 61300, "loss": 0.344, "lr": 3.8311906922198005e-05, "epoch": 3.8915171288743884, "percentage": 38.92, "elapsed_time": "3:13:49", "remaining_time": "5:04:14", "throughput": 4428.1, "total_tokens": 51496224} {"current_steps": 23860, "total_steps": 61300, "loss": 0.3467, "lr": 3.830588140273278e-05, "epoch": 3.892332789559543, "percentage": 38.92, "elapsed_time": "3:13:51", "remaining_time": "5:04:12", "throughput": 4428.19, "total_tokens": 51507872} {"current_steps": 23865, "total_steps": 61300, "loss": 0.3399, "lr": 3.829985480462529e-05, "epoch": 3.8931484502446985, "percentage": 38.93, "elapsed_time": "3:13:53", "remaining_time": "5:04:09", "throughput": 4428.27, "total_tokens": 51518112} {"current_steps": 23870, "total_steps": 61300, "loss": 0.3498, "lr": 3.82938271283641e-05, "epoch": 3.8939641109298533, "percentage": 38.94, "elapsed_time": "3:13:56", "remaining_time": "5:04:06", "throughput": 4428.35, "total_tokens": 51529120} {"current_steps": 23875, "total_steps": 61300, "loss": 0.3569, "lr": 3.828779837443783e-05, "epoch": 3.894779771615008, "percentage": 38.95, "elapsed_time": "3:13:58", "remaining_time": "5:04:03", "throughput": 4428.44, "total_tokens": 51540768} {"current_steps": 23880, "total_steps": 61300, "loss": 0.364, "lr": 3.8281768543335195e-05, "epoch": 3.895595432300163, "percentage": 38.96, "elapsed_time": "3:14:00", "remaining_time": "5:04:00", "throughput": 4428.5, "total_tokens": 51550304} {"current_steps": 23885, "total_steps": 61300, "loss": 0.3795, "lr": 3.827573763554502e-05, "epoch": 3.896411092985318, "percentage": 38.96, "elapsed_time": "3:14:02", "remaining_time": "5:03:58", "throughput": 4428.59, "total_tokens": 51561088} {"current_steps": 23890, "total_steps": 61300, "loss": 0.342, "lr": 3.826970565155618e-05, "epoch": 3.897226753670473, "percentage": 38.97, "elapsed_time": "3:14:04", "remaining_time": "5:03:55", "throughput": 4428.65, "total_tokens": 51571264} {"current_steps": 23895, "total_steps": 61300, "loss": 0.3327, "lr": 3.8263672591857666e-05, "epoch": 3.8980424143556283, "percentage": 38.98, "elapsed_time": "3:14:07", "remaining_time": "5:03:52", "throughput": 4428.74, "total_tokens": 51582912} {"current_steps": 23900, "total_steps": 61300, "loss": 0.3489, "lr": 3.825763845693857e-05, "epoch": 3.898858075040783, "percentage": 38.99, "elapsed_time": "3:14:09", "remaining_time": "5:03:49", "throughput": 4428.82, "total_tokens": 51594144} {"current_steps": 23905, "total_steps": 61300, "loss": 0.3379, "lr": 3.825160324728802e-05, "epoch": 3.899673735725938, "percentage": 39.0, "elapsed_time": "3:14:11", "remaining_time": "5:03:47", "throughput": 4428.9, "total_tokens": 51604928} {"current_steps": 23910, "total_steps": 61300, "loss": 0.3684, "lr": 3.824556696339528e-05, "epoch": 3.9004893964110927, "percentage": 39.0, "elapsed_time": "3:14:13", "remaining_time": "5:03:43", "throughput": 4428.96, "total_tokens": 51614176} {"current_steps": 23915, "total_steps": 61300, "loss": 0.3635, "lr": 3.823952960574967e-05, "epoch": 3.901305057096248, "percentage": 39.01, "elapsed_time": "3:14:16", "remaining_time": "5:03:41", "throughput": 4429.03, "total_tokens": 51624992} {"current_steps": 23920, "total_steps": 61300, "loss": 0.3639, "lr": 3.823349117484062e-05, "epoch": 3.902120717781403, "percentage": 39.02, "elapsed_time": "3:14:18", "remaining_time": "5:03:38", "throughput": 4429.11, "total_tokens": 51635744} {"current_steps": 23925, "total_steps": 61300, "loss": 0.3411, "lr": 3.822745167115762e-05, "epoch": 3.902936378466558, "percentage": 39.03, "elapsed_time": "3:14:20", "remaining_time": "5:03:35", "throughput": 4429.15, "total_tokens": 51645472} {"current_steps": 23930, "total_steps": 61300, "loss": 0.3485, "lr": 3.822141109519027e-05, "epoch": 3.903752039151713, "percentage": 39.04, "elapsed_time": "3:14:22", "remaining_time": "5:03:32", "throughput": 4429.23, "total_tokens": 51656128} {"current_steps": 23935, "total_steps": 61300, "loss": 0.3294, "lr": 3.821536944742827e-05, "epoch": 3.9045676998368677, "percentage": 39.05, "elapsed_time": "3:14:24", "remaining_time": "5:03:29", "throughput": 4429.3, "total_tokens": 51666368} {"current_steps": 23940, "total_steps": 61300, "loss": 0.3608, "lr": 3.820932672836135e-05, "epoch": 3.905383360522023, "percentage": 39.05, "elapsed_time": "3:14:27", "remaining_time": "5:03:27", "throughput": 4429.36, "total_tokens": 51677792} {"current_steps": 23945, "total_steps": 61300, "loss": 0.3628, "lr": 3.820328293847939e-05, "epoch": 3.9061990212071778, "percentage": 39.06, "elapsed_time": "3:14:29", "remaining_time": "5:03:24", "throughput": 4429.44, "total_tokens": 51689280} {"current_steps": 23950, "total_steps": 61300, "loss": 0.3409, "lr": 3.819723807827232e-05, "epoch": 3.907014681892333, "percentage": 39.07, "elapsed_time": "3:14:31", "remaining_time": "5:03:21", "throughput": 4429.51, "total_tokens": 51699712} {"current_steps": 23955, "total_steps": 61300, "loss": 0.3392, "lr": 3.8191192148230176e-05, "epoch": 3.907830342577488, "percentage": 39.08, "elapsed_time": "3:14:33", "remaining_time": "5:03:19", "throughput": 4429.58, "total_tokens": 51710624} {"current_steps": 23960, "total_steps": 61300, "loss": 0.3597, "lr": 3.818514514884306e-05, "epoch": 3.9086460032626427, "percentage": 39.09, "elapsed_time": "3:14:36", "remaining_time": "5:03:16", "throughput": 4429.65, "total_tokens": 51721952} {"current_steps": 23965, "total_steps": 61300, "loss": 0.3681, "lr": 3.8179097080601175e-05, "epoch": 3.9094616639477975, "percentage": 39.09, "elapsed_time": "3:14:38", "remaining_time": "5:03:13", "throughput": 4429.71, "total_tokens": 51731584} {"current_steps": 23970, "total_steps": 61300, "loss": 0.3707, "lr": 3.817304794399481e-05, "epoch": 3.9102773246329527, "percentage": 39.1, "elapsed_time": "3:14:40", "remaining_time": "5:03:11", "throughput": 4429.8, "total_tokens": 51743232} {"current_steps": 23975, "total_steps": 61300, "loss": 0.3402, "lr": 3.816699773951434e-05, "epoch": 3.9110929853181076, "percentage": 39.11, "elapsed_time": "3:14:43", "remaining_time": "5:03:08", "throughput": 4429.9, "total_tokens": 51755712} {"current_steps": 23980, "total_steps": 61300, "loss": 0.3251, "lr": 3.8160946467650226e-05, "epoch": 3.911908646003263, "percentage": 39.12, "elapsed_time": "3:14:45", "remaining_time": "5:03:06", "throughput": 4429.97, "total_tokens": 51767776} {"current_steps": 23985, "total_steps": 61300, "loss": 0.3519, "lr": 3.815489412889302e-05, "epoch": 3.9127243066884176, "percentage": 39.13, "elapsed_time": "3:14:47", "remaining_time": "5:03:03", "throughput": 4430.04, "total_tokens": 51778176} {"current_steps": 23990, "total_steps": 61300, "loss": 0.3824, "lr": 3.8148840723733335e-05, "epoch": 3.9135399673735725, "percentage": 39.14, "elapsed_time": "3:14:50", "remaining_time": "5:03:01", "throughput": 4430.1, "total_tokens": 51789024} {"current_steps": 23995, "total_steps": 61300, "loss": 0.3554, "lr": 3.814278625266191e-05, "epoch": 3.9143556280587277, "percentage": 39.14, "elapsed_time": "3:14:52", "remaining_time": "5:02:57", "throughput": 4430.17, "total_tokens": 51798752} {"current_steps": 24000, "total_steps": 61300, "loss": 0.3589, "lr": 3.8136730716169554e-05, "epoch": 3.9151712887438825, "percentage": 39.15, "elapsed_time": "3:14:54", "remaining_time": "5:02:55", "throughput": 4430.27, "total_tokens": 51809856} {"current_steps": 24005, "total_steps": 61300, "loss": 0.3289, "lr": 3.8130674114747146e-05, "epoch": 3.9159869494290374, "percentage": 39.16, "elapsed_time": "3:14:56", "remaining_time": "5:02:52", "throughput": 4430.33, "total_tokens": 51819584} {"current_steps": 24010, "total_steps": 61300, "loss": 0.3438, "lr": 3.812461644888566e-05, "epoch": 3.9168026101141926, "percentage": 39.17, "elapsed_time": "3:14:58", "remaining_time": "5:02:49", "throughput": 4430.42, "total_tokens": 51831168} {"current_steps": 24015, "total_steps": 61300, "loss": 0.3363, "lr": 3.8118557719076186e-05, "epoch": 3.9176182707993474, "percentage": 39.18, "elapsed_time": "3:15:00", "remaining_time": "5:02:46", "throughput": 4430.47, "total_tokens": 51839776} {"current_steps": 24020, "total_steps": 61300, "loss": 0.351, "lr": 3.811249792580985e-05, "epoch": 3.9184339314845023, "percentage": 39.18, "elapsed_time": "3:15:02", "remaining_time": "5:02:43", "throughput": 4430.54, "total_tokens": 51850368} {"current_steps": 24025, "total_steps": 61300, "loss": 0.32, "lr": 3.810643706957791e-05, "epoch": 3.9192495921696575, "percentage": 39.19, "elapsed_time": "3:15:05", "remaining_time": "5:02:40", "throughput": 4430.61, "total_tokens": 51861248} {"current_steps": 24030, "total_steps": 61300, "loss": 0.3316, "lr": 3.810037515087167e-05, "epoch": 3.9200652528548123, "percentage": 39.2, "elapsed_time": "3:15:07", "remaining_time": "5:02:38", "throughput": 4430.68, "total_tokens": 51872928} {"current_steps": 24035, "total_steps": 61300, "loss": 0.3466, "lr": 3.809431217018255e-05, "epoch": 3.9208809135399676, "percentage": 39.21, "elapsed_time": "3:15:09", "remaining_time": "5:02:35", "throughput": 4430.75, "total_tokens": 51883680} {"current_steps": 24040, "total_steps": 61300, "loss": 0.3046, "lr": 3.8088248128002044e-05, "epoch": 3.9216965742251224, "percentage": 39.22, "elapsed_time": "3:15:12", "remaining_time": "5:02:33", "throughput": 4430.83, "total_tokens": 51895808} {"current_steps": 24045, "total_steps": 61300, "loss": 0.2959, "lr": 3.808218302482175e-05, "epoch": 3.9225122349102772, "percentage": 39.23, "elapsed_time": "3:15:14", "remaining_time": "5:02:30", "throughput": 4430.9, "total_tokens": 51905760} {"current_steps": 24050, "total_steps": 61300, "loss": 0.3396, "lr": 3.8076116861133305e-05, "epoch": 3.923327895595432, "percentage": 39.23, "elapsed_time": "3:15:16", "remaining_time": "5:02:27", "throughput": 4430.97, "total_tokens": 51916288} {"current_steps": 24055, "total_steps": 61300, "loss": 0.3606, "lr": 3.8070049637428485e-05, "epoch": 3.9241435562805873, "percentage": 39.24, "elapsed_time": "3:15:18", "remaining_time": "5:02:24", "throughput": 4431.03, "total_tokens": 51927040} {"current_steps": 24060, "total_steps": 61300, "loss": 0.304, "lr": 3.806398135419913e-05, "epoch": 3.924959216965742, "percentage": 39.25, "elapsed_time": "3:15:21", "remaining_time": "5:02:22", "throughput": 4431.09, "total_tokens": 51937760} {"current_steps": 24065, "total_steps": 61300, "loss": 0.3405, "lr": 3.805791201193716e-05, "epoch": 3.9257748776508974, "percentage": 39.26, "elapsed_time": "3:15:23", "remaining_time": "5:02:19", "throughput": 4431.15, "total_tokens": 51948384} {"current_steps": 24070, "total_steps": 61300, "loss": 0.3405, "lr": 3.8051841611134576e-05, "epoch": 3.926590538336052, "percentage": 39.27, "elapsed_time": "3:15:25", "remaining_time": "5:02:16", "throughput": 4431.22, "total_tokens": 51958496} {"current_steps": 24075, "total_steps": 61300, "loss": 0.3766, "lr": 3.804577015228349e-05, "epoch": 3.927406199021207, "percentage": 39.27, "elapsed_time": "3:15:27", "remaining_time": "5:02:13", "throughput": 4431.29, "total_tokens": 51969216} {"current_steps": 24080, "total_steps": 61300, "loss": 0.2957, "lr": 3.803969763587609e-05, "epoch": 3.9282218597063623, "percentage": 39.28, "elapsed_time": "3:15:30", "remaining_time": "5:02:11", "throughput": 4431.37, "total_tokens": 51980768} {"current_steps": 24085, "total_steps": 61300, "loss": 0.3113, "lr": 3.803362406240463e-05, "epoch": 3.929037520391517, "percentage": 39.29, "elapsed_time": "3:15:32", "remaining_time": "5:02:08", "throughput": 4431.43, "total_tokens": 51990976} {"current_steps": 24090, "total_steps": 61300, "loss": 0.3134, "lr": 3.802754943236148e-05, "epoch": 3.9298531810766724, "percentage": 39.3, "elapsed_time": "3:15:34", "remaining_time": "5:02:05", "throughput": 4431.5, "total_tokens": 52002240} {"current_steps": 24095, "total_steps": 61300, "loss": 0.3223, "lr": 3.8021473746239064e-05, "epoch": 3.930668841761827, "percentage": 39.31, "elapsed_time": "3:15:37", "remaining_time": "5:02:03", "throughput": 4431.58, "total_tokens": 52013760} {"current_steps": 24100, "total_steps": 61300, "loss": 0.3947, "lr": 3.801539700452992e-05, "epoch": 3.931484502446982, "percentage": 39.31, "elapsed_time": "3:15:39", "remaining_time": "5:02:00", "throughput": 4431.65, "total_tokens": 52024960} {"current_steps": 24105, "total_steps": 61300, "loss": 0.3268, "lr": 3.800931920772666e-05, "epoch": 3.932300163132137, "percentage": 39.32, "elapsed_time": "3:15:41", "remaining_time": "5:01:57", "throughput": 4431.73, "total_tokens": 52035872} {"current_steps": 24110, "total_steps": 61300, "loss": 0.3314, "lr": 3.8003240356321965e-05, "epoch": 3.933115823817292, "percentage": 39.33, "elapsed_time": "3:15:44", "remaining_time": "5:01:55", "throughput": 4431.8, "total_tokens": 52047136} {"current_steps": 24115, "total_steps": 61300, "loss": 0.3628, "lr": 3.7997160450808634e-05, "epoch": 3.933931484502447, "percentage": 39.34, "elapsed_time": "3:15:46", "remaining_time": "5:01:52", "throughput": 4431.88, "total_tokens": 52059040} {"current_steps": 24120, "total_steps": 61300, "loss": 0.3326, "lr": 3.7991079491679524e-05, "epoch": 3.934747145187602, "percentage": 39.35, "elapsed_time": "3:15:48", "remaining_time": "5:01:50", "throughput": 4431.96, "total_tokens": 52070176} {"current_steps": 24125, "total_steps": 61300, "loss": 0.3338, "lr": 3.79849974794276e-05, "epoch": 3.935562805872757, "percentage": 39.36, "elapsed_time": "3:15:50", "remaining_time": "5:01:47", "throughput": 4432.03, "total_tokens": 52080576} {"current_steps": 24130, "total_steps": 61300, "loss": 0.3345, "lr": 3.7978914414545895e-05, "epoch": 3.936378466557912, "percentage": 39.36, "elapsed_time": "3:15:53", "remaining_time": "5:01:44", "throughput": 4432.11, "total_tokens": 52091744} {"current_steps": 24135, "total_steps": 61300, "loss": 0.3517, "lr": 3.797283029752753e-05, "epoch": 3.9371941272430666, "percentage": 39.37, "elapsed_time": "3:15:55", "remaining_time": "5:01:42", "throughput": 4432.18, "total_tokens": 52102432} {"current_steps": 24140, "total_steps": 61300, "loss": 0.3369, "lr": 3.796674512886573e-05, "epoch": 3.938009787928222, "percentage": 39.38, "elapsed_time": "3:15:57", "remaining_time": "5:01:38", "throughput": 4432.25, "total_tokens": 52111968} {"current_steps": 24145, "total_steps": 61300, "loss": 0.3434, "lr": 3.7960658909053766e-05, "epoch": 3.9388254486133767, "percentage": 39.39, "elapsed_time": "3:15:59", "remaining_time": "5:01:36", "throughput": 4432.34, "total_tokens": 52123872} {"current_steps": 24150, "total_steps": 61300, "loss": 0.3313, "lr": 3.7954571638585035e-05, "epoch": 3.939641109298532, "percentage": 39.4, "elapsed_time": "3:16:02", "remaining_time": "5:01:33", "throughput": 4432.41, "total_tokens": 52134400} {"current_steps": 24155, "total_steps": 61300, "loss": 0.3228, "lr": 3.7948483317952985e-05, "epoch": 3.9404567699836868, "percentage": 39.4, "elapsed_time": "3:16:04", "remaining_time": "5:01:30", "throughput": 4432.47, "total_tokens": 52144448} {"current_steps": 24160, "total_steps": 61300, "loss": 0.348, "lr": 3.794239394765119e-05, "epoch": 3.9412724306688416, "percentage": 39.41, "elapsed_time": "3:16:06", "remaining_time": "5:01:28", "throughput": 4432.55, "total_tokens": 52155840} {"current_steps": 24165, "total_steps": 61300, "loss": 0.3453, "lr": 3.793630352817327e-05, "epoch": 3.942088091353997, "percentage": 39.42, "elapsed_time": "3:16:09", "remaining_time": "5:01:25", "throughput": 4432.63, "total_tokens": 52167968} {"current_steps": 24170, "total_steps": 61300, "loss": 0.3739, "lr": 3.7930212060012946e-05, "epoch": 3.9429037520391517, "percentage": 39.43, "elapsed_time": "3:16:11", "remaining_time": "5:01:22", "throughput": 4432.69, "total_tokens": 52177792} {"current_steps": 24175, "total_steps": 61300, "loss": 0.313, "lr": 3.792411954366402e-05, "epoch": 3.943719412724307, "percentage": 39.44, "elapsed_time": "3:16:13", "remaining_time": "5:01:20", "throughput": 4432.76, "total_tokens": 52188992} {"current_steps": 24180, "total_steps": 61300, "loss": 0.3668, "lr": 3.791802597962039e-05, "epoch": 3.9445350734094617, "percentage": 39.45, "elapsed_time": "3:16:15", "remaining_time": "5:01:17", "throughput": 4432.82, "total_tokens": 52200192} {"current_steps": 24185, "total_steps": 61300, "loss": 0.3482, "lr": 3.791193136837603e-05, "epoch": 3.9453507340946166, "percentage": 39.45, "elapsed_time": "3:16:18", "remaining_time": "5:01:14", "throughput": 4432.89, "total_tokens": 52210944} {"current_steps": 24190, "total_steps": 61300, "loss": 0.385, "lr": 3.7905835710425e-05, "epoch": 3.9461663947797714, "percentage": 39.46, "elapsed_time": "3:16:20", "remaining_time": "5:01:12", "throughput": 4432.96, "total_tokens": 52220960} {"current_steps": 24195, "total_steps": 61300, "loss": 0.3347, "lr": 3.789973900626145e-05, "epoch": 3.9469820554649266, "percentage": 39.47, "elapsed_time": "3:16:22", "remaining_time": "5:01:09", "throughput": 4433.02, "total_tokens": 52231232} {"current_steps": 24200, "total_steps": 61300, "loss": 0.3407, "lr": 3.78936412563796e-05, "epoch": 3.9477977161500815, "percentage": 39.48, "elapsed_time": "3:16:24", "remaining_time": "5:01:05", "throughput": 4433.07, "total_tokens": 52240032} {"current_steps": 24205, "total_steps": 61300, "loss": 0.325, "lr": 3.788754246127375e-05, "epoch": 3.9486133768352367, "percentage": 39.49, "elapsed_time": "3:16:26", "remaining_time": "5:01:03", "throughput": 4433.15, "total_tokens": 52251968} {"current_steps": 24210, "total_steps": 61300, "loss": 0.3415, "lr": 3.7881442621438333e-05, "epoch": 3.9494290375203915, "percentage": 39.49, "elapsed_time": "3:16:28", "remaining_time": "5:01:00", "throughput": 4433.24, "total_tokens": 52263072} {"current_steps": 24215, "total_steps": 61300, "loss": 0.3499, "lr": 3.787534173736782e-05, "epoch": 3.9502446982055464, "percentage": 39.5, "elapsed_time": "3:16:31", "remaining_time": "5:00:58", "throughput": 4433.32, "total_tokens": 52274336} {"current_steps": 24220, "total_steps": 61300, "loss": 0.3516, "lr": 3.786923980955678e-05, "epoch": 3.9510603588907016, "percentage": 39.51, "elapsed_time": "3:16:33", "remaining_time": "5:00:55", "throughput": 4433.38, "total_tokens": 52284992} {"current_steps": 24225, "total_steps": 61300, "loss": 0.3221, "lr": 3.7863136838499855e-05, "epoch": 3.9518760195758564, "percentage": 39.52, "elapsed_time": "3:16:35", "remaining_time": "5:00:52", "throughput": 4433.45, "total_tokens": 52296032} {"current_steps": 24230, "total_steps": 61300, "loss": 0.3491, "lr": 3.785703282469179e-05, "epoch": 3.9526916802610113, "percentage": 39.53, "elapsed_time": "3:16:37", "remaining_time": "5:00:49", "throughput": 4433.52, "total_tokens": 52306432} {"current_steps": 24235, "total_steps": 61300, "loss": 0.3269, "lr": 3.785092776862741e-05, "epoch": 3.9535073409461665, "percentage": 39.54, "elapsed_time": "3:16:40", "remaining_time": "5:00:47", "throughput": 4433.59, "total_tokens": 52316640} {"current_steps": 24240, "total_steps": 61300, "loss": 0.357, "lr": 3.784482167080162e-05, "epoch": 3.9543230016313213, "percentage": 39.54, "elapsed_time": "3:16:42", "remaining_time": "5:00:44", "throughput": 4433.65, "total_tokens": 52327104} {"current_steps": 24245, "total_steps": 61300, "loss": 0.3438, "lr": 3.783871453170941e-05, "epoch": 3.955138662316476, "percentage": 39.55, "elapsed_time": "3:16:44", "remaining_time": "5:00:41", "throughput": 4433.74, "total_tokens": 52338080} {"current_steps": 24250, "total_steps": 61300, "loss": 0.3778, "lr": 3.783260635184586e-05, "epoch": 3.9559543230016314, "percentage": 39.56, "elapsed_time": "3:16:46", "remaining_time": "5:00:38", "throughput": 4433.8, "total_tokens": 52348576} {"current_steps": 24255, "total_steps": 61300, "loss": 0.3089, "lr": 3.782649713170613e-05, "epoch": 3.9567699836867862, "percentage": 39.57, "elapsed_time": "3:16:48", "remaining_time": "5:00:35", "throughput": 4433.88, "total_tokens": 52358848} {"current_steps": 24260, "total_steps": 61300, "loss": 0.3519, "lr": 3.7820386871785455e-05, "epoch": 3.9575856443719415, "percentage": 39.58, "elapsed_time": "3:16:50", "remaining_time": "5:00:32", "throughput": 4433.94, "total_tokens": 52369248} {"current_steps": 24265, "total_steps": 61300, "loss": 0.3264, "lr": 3.7814275572579175e-05, "epoch": 3.9584013050570963, "percentage": 39.58, "elapsed_time": "3:16:53", "remaining_time": "5:00:30", "throughput": 4434.02, "total_tokens": 52380640} {"current_steps": 24270, "total_steps": 61300, "loss": 0.3623, "lr": 3.780816323458269e-05, "epoch": 3.959216965742251, "percentage": 39.59, "elapsed_time": "3:16:55", "remaining_time": "5:00:27", "throughput": 4434.09, "total_tokens": 52391136} {"current_steps": 24275, "total_steps": 61300, "loss": 0.3769, "lr": 3.7802049858291515e-05, "epoch": 3.960032626427406, "percentage": 39.6, "elapsed_time": "3:16:57", "remaining_time": "5:00:24", "throughput": 4434.15, "total_tokens": 52401824} {"current_steps": 24280, "total_steps": 61300, "loss": 0.3537, "lr": 3.779593544420122e-05, "epoch": 3.960848287112561, "percentage": 39.61, "elapsed_time": "3:16:59", "remaining_time": "5:00:22", "throughput": 4434.23, "total_tokens": 52412576} {"current_steps": 24285, "total_steps": 61300, "loss": 0.3421, "lr": 3.7789819992807474e-05, "epoch": 3.961663947797716, "percentage": 39.62, "elapsed_time": "3:17:02", "remaining_time": "5:00:19", "throughput": 4434.29, "total_tokens": 52422720} {"current_steps": 24290, "total_steps": 61300, "loss": 0.3607, "lr": 3.778370350460601e-05, "epoch": 3.9624796084828713, "percentage": 39.62, "elapsed_time": "3:17:04", "remaining_time": "5:00:16", "throughput": 4434.36, "total_tokens": 52432800} {"current_steps": 24295, "total_steps": 61300, "loss": 0.3404, "lr": 3.777758598009269e-05, "epoch": 3.963295269168026, "percentage": 39.63, "elapsed_time": "3:17:06", "remaining_time": "5:00:13", "throughput": 4434.43, "total_tokens": 52443680} {"current_steps": 24300, "total_steps": 61300, "loss": 0.3121, "lr": 3.777146741976342e-05, "epoch": 3.964110929853181, "percentage": 39.64, "elapsed_time": "3:17:08", "remaining_time": "5:00:10", "throughput": 4434.51, "total_tokens": 52454976} {"current_steps": 24305, "total_steps": 61300, "loss": 0.333, "lr": 3.776534782411419e-05, "epoch": 3.964926590538336, "percentage": 39.65, "elapsed_time": "3:17:10", "remaining_time": "5:00:08", "throughput": 4434.59, "total_tokens": 52465376} {"current_steps": 24310, "total_steps": 61300, "loss": 0.3476, "lr": 3.77592271936411e-05, "epoch": 3.965742251223491, "percentage": 39.66, "elapsed_time": "3:17:13", "remaining_time": "5:00:05", "throughput": 4434.67, "total_tokens": 52477408} {"current_steps": 24315, "total_steps": 61300, "loss": 0.3506, "lr": 3.775310552884031e-05, "epoch": 3.9665579119086463, "percentage": 39.67, "elapsed_time": "3:17:15", "remaining_time": "5:00:03", "throughput": 4434.76, "total_tokens": 52489472} {"current_steps": 24320, "total_steps": 61300, "loss": 0.363, "lr": 3.7746982830208075e-05, "epoch": 3.967373572593801, "percentage": 39.67, "elapsed_time": "3:17:18", "remaining_time": "5:00:00", "throughput": 4434.82, "total_tokens": 52499648} {"current_steps": 24325, "total_steps": 61300, "loss": 0.3082, "lr": 3.774085909824074e-05, "epoch": 3.968189233278956, "percentage": 39.68, "elapsed_time": "3:17:19", "remaining_time": "4:59:56", "throughput": 4434.89, "total_tokens": 52508096} {"current_steps": 24330, "total_steps": 61300, "loss": 0.35, "lr": 3.7734734333434726e-05, "epoch": 3.9690048939641107, "percentage": 39.69, "elapsed_time": "3:17:22", "remaining_time": "4:59:54", "throughput": 4434.96, "total_tokens": 52520224} {"current_steps": 24335, "total_steps": 61300, "loss": 0.3501, "lr": 3.772860853628652e-05, "epoch": 3.969820554649266, "percentage": 39.7, "elapsed_time": "3:17:24", "remaining_time": "4:59:52", "throughput": 4435.04, "total_tokens": 52531520} {"current_steps": 24340, "total_steps": 61300, "loss": 0.3343, "lr": 3.772248170729272e-05, "epoch": 3.970636215334421, "percentage": 39.71, "elapsed_time": "3:17:27", "remaining_time": "4:59:49", "throughput": 4435.12, "total_tokens": 52543040} {"current_steps": 24345, "total_steps": 61300, "loss": 0.3674, "lr": 3.771635384695001e-05, "epoch": 3.971451876019576, "percentage": 39.71, "elapsed_time": "3:17:29", "remaining_time": "4:59:46", "throughput": 4435.18, "total_tokens": 52553760} {"current_steps": 24350, "total_steps": 61300, "loss": 0.3889, "lr": 3.771022495575513e-05, "epoch": 3.972267536704731, "percentage": 39.72, "elapsed_time": "3:17:31", "remaining_time": "4:59:44", "throughput": 4435.24, "total_tokens": 52564416} {"current_steps": 24355, "total_steps": 61300, "loss": 0.3296, "lr": 3.770409503420492e-05, "epoch": 3.9730831973898857, "percentage": 39.73, "elapsed_time": "3:17:33", "remaining_time": "4:59:41", "throughput": 4435.32, "total_tokens": 52574880} {"current_steps": 24360, "total_steps": 61300, "loss": 0.3818, "lr": 3.769796408279631e-05, "epoch": 3.9738988580750405, "percentage": 39.74, "elapsed_time": "3:17:36", "remaining_time": "4:59:38", "throughput": 4435.39, "total_tokens": 52586464} {"current_steps": 24365, "total_steps": 61300, "loss": 0.3475, "lr": 3.76918321020263e-05, "epoch": 3.9747145187601958, "percentage": 39.75, "elapsed_time": "3:17:38", "remaining_time": "4:59:35", "throughput": 4435.45, "total_tokens": 52596608} {"current_steps": 24370, "total_steps": 61300, "loss": 0.3648, "lr": 3.768569909239199e-05, "epoch": 3.9755301794453506, "percentage": 39.76, "elapsed_time": "3:17:40", "remaining_time": "4:59:33", "throughput": 4435.52, "total_tokens": 52607680} {"current_steps": 24375, "total_steps": 61300, "loss": 0.3839, "lr": 3.767956505439054e-05, "epoch": 3.976345840130506, "percentage": 39.76, "elapsed_time": "3:17:43", "remaining_time": "4:59:30", "throughput": 4435.6, "total_tokens": 52619648} {"current_steps": 24380, "total_steps": 61300, "loss": 0.34, "lr": 3.767342998851921e-05, "epoch": 3.9771615008156607, "percentage": 39.77, "elapsed_time": "3:17:45", "remaining_time": "4:59:28", "throughput": 4435.66, "total_tokens": 52630528} {"current_steps": 24385, "total_steps": 61300, "loss": 0.3297, "lr": 3.766729389527535e-05, "epoch": 3.9779771615008155, "percentage": 39.78, "elapsed_time": "3:17:47", "remaining_time": "4:59:25", "throughput": 4435.72, "total_tokens": 52640608} {"current_steps": 24390, "total_steps": 61300, "loss": 0.3411, "lr": 3.766115677515637e-05, "epoch": 3.9787928221859707, "percentage": 39.79, "elapsed_time": "3:17:49", "remaining_time": "4:59:22", "throughput": 4435.78, "total_tokens": 52651872} {"current_steps": 24395, "total_steps": 61300, "loss": 0.3194, "lr": 3.765501862865976e-05, "epoch": 3.9796084828711256, "percentage": 39.8, "elapsed_time": "3:17:52", "remaining_time": "4:59:20", "throughput": 4435.88, "total_tokens": 52663904} {"current_steps": 24400, "total_steps": 61300, "loss": 0.3246, "lr": 3.764887945628315e-05, "epoch": 3.980424143556281, "percentage": 39.8, "elapsed_time": "3:17:54", "remaining_time": "4:59:17", "throughput": 4435.94, "total_tokens": 52674848} {"current_steps": 24405, "total_steps": 61300, "loss": 0.3696, "lr": 3.76427392585242e-05, "epoch": 3.9812398042414356, "percentage": 39.81, "elapsed_time": "3:17:56", "remaining_time": "4:59:15", "throughput": 4436.03, "total_tokens": 52686656} {"current_steps": 24410, "total_steps": 61300, "loss": 0.354, "lr": 3.7636598035880633e-05, "epoch": 3.9820554649265905, "percentage": 39.82, "elapsed_time": "3:17:59", "remaining_time": "4:59:12", "throughput": 4436.1, "total_tokens": 52696544} {"current_steps": 24415, "total_steps": 61300, "loss": 0.3198, "lr": 3.763045578885033e-05, "epoch": 3.9828711256117453, "percentage": 39.83, "elapsed_time": "3:18:01", "remaining_time": "4:59:09", "throughput": 4436.17, "total_tokens": 52706912} {"current_steps": 24420, "total_steps": 61300, "loss": 0.3233, "lr": 3.762431251793118e-05, "epoch": 3.9836867862969005, "percentage": 39.84, "elapsed_time": "3:18:03", "remaining_time": "4:59:06", "throughput": 4436.25, "total_tokens": 52718016} {"current_steps": 24425, "total_steps": 61300, "loss": 0.3503, "lr": 3.7618168223621215e-05, "epoch": 3.9845024469820554, "percentage": 39.85, "elapsed_time": "3:18:05", "remaining_time": "4:59:03", "throughput": 4436.32, "total_tokens": 52728288} {"current_steps": 24430, "total_steps": 61300, "loss": 0.3266, "lr": 3.761202290641851e-05, "epoch": 3.9853181076672106, "percentage": 39.85, "elapsed_time": "3:18:07", "remaining_time": "4:59:01", "throughput": 4436.38, "total_tokens": 52739104} {"current_steps": 24435, "total_steps": 61300, "loss": 0.3649, "lr": 3.760587656682122e-05, "epoch": 3.9861337683523654, "percentage": 39.86, "elapsed_time": "3:18:10", "remaining_time": "4:58:58", "throughput": 4436.46, "total_tokens": 52749536} {"current_steps": 24440, "total_steps": 61300, "loss": 0.3598, "lr": 3.759972920532762e-05, "epoch": 3.9869494290375203, "percentage": 39.87, "elapsed_time": "3:18:12", "remaining_time": "4:58:55", "throughput": 4436.52, "total_tokens": 52760416} {"current_steps": 24445, "total_steps": 61300, "loss": 0.3434, "lr": 3.759358082243604e-05, "epoch": 3.9877650897226755, "percentage": 39.88, "elapsed_time": "3:18:14", "remaining_time": "4:58:53", "throughput": 4436.59, "total_tokens": 52772160} {"current_steps": 24450, "total_steps": 61300, "loss": 0.3508, "lr": 3.7587431418644906e-05, "epoch": 3.9885807504078303, "percentage": 39.89, "elapsed_time": "3:18:16", "remaining_time": "4:58:50", "throughput": 4436.65, "total_tokens": 52781984} {"current_steps": 24455, "total_steps": 61300, "loss": 0.3316, "lr": 3.758128099445271e-05, "epoch": 3.9893964110929856, "percentage": 39.89, "elapsed_time": "3:18:18", "remaining_time": "4:58:47", "throughput": 4436.73, "total_tokens": 52791776} {"current_steps": 24460, "total_steps": 61300, "loss": 0.3356, "lr": 3.757512955035804e-05, "epoch": 3.9902120717781404, "percentage": 39.9, "elapsed_time": "3:18:21", "remaining_time": "4:58:44", "throughput": 4436.8, "total_tokens": 52802528} {"current_steps": 24465, "total_steps": 61300, "loss": 0.3545, "lr": 3.7568977086859566e-05, "epoch": 3.9910277324632952, "percentage": 39.91, "elapsed_time": "3:18:23", "remaining_time": "4:58:41", "throughput": 4436.88, "total_tokens": 52812640} {"current_steps": 24470, "total_steps": 61300, "loss": 0.3343, "lr": 3.7562823604456035e-05, "epoch": 3.99184339314845, "percentage": 39.92, "elapsed_time": "3:18:25", "remaining_time": "4:58:38", "throughput": 4436.97, "total_tokens": 52823744} {"current_steps": 24475, "total_steps": 61300, "loss": 0.3522, "lr": 3.7556669103646266e-05, "epoch": 3.9926590538336053, "percentage": 39.93, "elapsed_time": "3:18:27", "remaining_time": "4:58:35", "throughput": 4437.05, "total_tokens": 52834016} {"current_steps": 24480, "total_steps": 61300, "loss": 0.343, "lr": 3.75505135849292e-05, "epoch": 3.99347471451876, "percentage": 39.93, "elapsed_time": "3:18:29", "remaining_time": "4:58:33", "throughput": 4437.12, "total_tokens": 52845248} {"current_steps": 24485, "total_steps": 61300, "loss": 0.3525, "lr": 3.7544357048803824e-05, "epoch": 3.9942903752039154, "percentage": 39.94, "elapsed_time": "3:18:31", "remaining_time": "4:58:30", "throughput": 4437.18, "total_tokens": 52855104} {"current_steps": 24490, "total_steps": 61300, "loss": 0.3643, "lr": 3.7538199495769214e-05, "epoch": 3.99510603588907, "percentage": 39.95, "elapsed_time": "3:18:34", "remaining_time": "4:58:27", "throughput": 4437.24, "total_tokens": 52866048} {"current_steps": 24495, "total_steps": 61300, "loss": 0.3119, "lr": 3.753204092632454e-05, "epoch": 3.995921696574225, "percentage": 39.96, "elapsed_time": "3:18:36", "remaining_time": "4:58:25", "throughput": 4437.3, "total_tokens": 52876768} {"current_steps": 24500, "total_steps": 61300, "loss": 0.3235, "lr": 3.752588134096903e-05, "epoch": 3.99673735725938, "percentage": 39.97, "elapsed_time": "3:18:38", "remaining_time": "4:58:22", "throughput": 4437.38, "total_tokens": 52887872} {"current_steps": 24505, "total_steps": 61300, "loss": 0.3611, "lr": 3.751972074020202e-05, "epoch": 3.997553017944535, "percentage": 39.98, "elapsed_time": "3:18:40", "remaining_time": "4:58:19", "throughput": 4437.44, "total_tokens": 52898624} {"current_steps": 24510, "total_steps": 61300, "loss": 0.3278, "lr": 3.751355912452294e-05, "epoch": 3.99836867862969, "percentage": 39.98, "elapsed_time": "3:18:43", "remaining_time": "4:58:16", "throughput": 4437.5, "total_tokens": 52908768} {"current_steps": 24515, "total_steps": 61300, "loss": 0.3167, "lr": 3.7507396494431246e-05, "epoch": 3.999184339314845, "percentage": 39.99, "elapsed_time": "3:18:45", "remaining_time": "4:58:14", "throughput": 4437.58, "total_tokens": 52920064} {"current_steps": 24520, "total_steps": 61300, "loss": 0.3171, "lr": 3.750123285042654e-05, "epoch": 4.0, "percentage": 40.0, "elapsed_time": "3:18:47", "remaining_time": "4:58:11", "throughput": 4437.61, "total_tokens": 52929744} {"current_steps": 24520, "total_steps": 61300, "eval_loss": 0.3391866981983185, "epoch": 4.0, "percentage": 40.0, "elapsed_time": "3:20:59", "remaining_time": "5:01:29", "throughput": 4388.89, "total_tokens": 52929744} {"current_steps": 24525, "total_steps": 61300, "loss": 0.3444, "lr": 3.749506819300846e-05, "epoch": 4.000815660685155, "percentage": 40.01, "elapsed_time": "3:21:03", "remaining_time": "5:01:29", "throughput": 4388.54, "total_tokens": 52941840} {"current_steps": 24530, "total_steps": 61300, "loss": 0.3546, "lr": 3.748890252267676e-05, "epoch": 4.00163132137031, "percentage": 40.02, "elapsed_time": "3:21:05", "remaining_time": "5:01:26", "throughput": 4388.61, "total_tokens": 52952560} {"current_steps": 24535, "total_steps": 61300, "loss": 0.3723, "lr": 3.748273583993126e-05, "epoch": 4.002446982055465, "percentage": 40.02, "elapsed_time": "3:21:07", "remaining_time": "5:01:23", "throughput": 4388.66, "total_tokens": 52961968} {"current_steps": 24540, "total_steps": 61300, "loss": 0.3444, "lr": 3.747656814527185e-05, "epoch": 4.00326264274062, "percentage": 40.03, "elapsed_time": "3:21:09", "remaining_time": "5:01:20", "throughput": 4388.74, "total_tokens": 52971408} {"current_steps": 24545, "total_steps": 61300, "loss": 0.3463, "lr": 3.747039943919852e-05, "epoch": 4.004078303425775, "percentage": 40.04, "elapsed_time": "3:21:12", "remaining_time": "5:01:17", "throughput": 4388.81, "total_tokens": 52982832} {"current_steps": 24550, "total_steps": 61300, "loss": 0.3286, "lr": 3.746422972221134e-05, "epoch": 4.00489396411093, "percentage": 40.05, "elapsed_time": "3:21:14", "remaining_time": "5:01:14", "throughput": 4388.89, "total_tokens": 52993648} {"current_steps": 24555, "total_steps": 61300, "loss": 0.3745, "lr": 3.745805899481045e-05, "epoch": 4.005709624796085, "percentage": 40.06, "elapsed_time": "3:21:16", "remaining_time": "5:01:12", "throughput": 4388.97, "total_tokens": 53004272} {"current_steps": 24560, "total_steps": 61300, "loss": 0.3706, "lr": 3.745188725749609e-05, "epoch": 4.006525285481239, "percentage": 40.07, "elapsed_time": "3:21:18", "remaining_time": "5:01:08", "throughput": 4389.03, "total_tokens": 53013872} {"current_steps": 24565, "total_steps": 61300, "loss": 0.3294, "lr": 3.744571451076856e-05, "epoch": 4.007340946166395, "percentage": 40.07, "elapsed_time": "3:21:21", "remaining_time": "5:01:06", "throughput": 4389.1, "total_tokens": 53024912} {"current_steps": 24570, "total_steps": 61300, "loss": 0.3484, "lr": 3.7439540755128276e-05, "epoch": 4.00815660685155, "percentage": 40.08, "elapsed_time": "3:21:23", "remaining_time": "5:01:03", "throughput": 4389.2, "total_tokens": 53037360} {"current_steps": 24575, "total_steps": 61300, "loss": 0.3484, "lr": 3.7433365991075695e-05, "epoch": 4.008972267536705, "percentage": 40.09, "elapsed_time": "3:21:25", "remaining_time": "5:01:01", "throughput": 4389.28, "total_tokens": 53048688} {"current_steps": 24580, "total_steps": 61300, "loss": 0.352, "lr": 3.742719021911138e-05, "epoch": 4.00978792822186, "percentage": 40.1, "elapsed_time": "3:21:28", "remaining_time": "5:00:58", "throughput": 4389.36, "total_tokens": 53059568} {"current_steps": 24585, "total_steps": 61300, "loss": 0.2993, "lr": 3.742101343973598e-05, "epoch": 4.010603588907014, "percentage": 40.11, "elapsed_time": "3:21:30", "remaining_time": "5:00:56", "throughput": 4389.45, "total_tokens": 53071312} {"current_steps": 24590, "total_steps": 61300, "loss": 0.361, "lr": 3.741483565345019e-05, "epoch": 4.011419249592169, "percentage": 40.11, "elapsed_time": "3:21:32", "remaining_time": "5:00:53", "throughput": 4389.55, "total_tokens": 53082544} {"current_steps": 24595, "total_steps": 61300, "loss": 0.3294, "lr": 3.740865686075484e-05, "epoch": 4.012234910277325, "percentage": 40.12, "elapsed_time": "3:21:35", "remaining_time": "5:00:50", "throughput": 4389.61, "total_tokens": 53093168} {"current_steps": 24600, "total_steps": 61300, "loss": 0.3306, "lr": 3.7402477062150795e-05, "epoch": 4.01305057096248, "percentage": 40.13, "elapsed_time": "3:21:37", "remaining_time": "5:00:48", "throughput": 4389.69, "total_tokens": 53104688} {"current_steps": 24605, "total_steps": 61300, "loss": 0.3312, "lr": 3.739629625813904e-05, "epoch": 4.013866231647635, "percentage": 40.14, "elapsed_time": "3:21:40", "remaining_time": "5:00:45", "throughput": 4389.78, "total_tokens": 53116528} {"current_steps": 24610, "total_steps": 61300, "loss": 0.3462, "lr": 3.739011444922061e-05, "epoch": 4.014681892332789, "percentage": 40.15, "elapsed_time": "3:21:42", "remaining_time": "5:00:43", "throughput": 4389.86, "total_tokens": 53128016} {"current_steps": 24615, "total_steps": 61300, "loss": 0.3027, "lr": 3.7383931635896634e-05, "epoch": 4.015497553017944, "percentage": 40.15, "elapsed_time": "3:21:44", "remaining_time": "5:00:40", "throughput": 4389.94, "total_tokens": 53139120} {"current_steps": 24620, "total_steps": 61300, "loss": 0.3282, "lr": 3.737774781866833e-05, "epoch": 4.0163132137031, "percentage": 40.16, "elapsed_time": "3:21:46", "remaining_time": "5:00:37", "throughput": 4390.02, "total_tokens": 53149392} {"current_steps": 24625, "total_steps": 61300, "loss": 0.3537, "lr": 3.737156299803698e-05, "epoch": 4.017128874388255, "percentage": 40.17, "elapsed_time": "3:21:49", "remaining_time": "5:00:34", "throughput": 4390.1, "total_tokens": 53160304} {"current_steps": 24630, "total_steps": 61300, "loss": 0.3012, "lr": 3.7365377174503956e-05, "epoch": 4.0179445350734095, "percentage": 40.18, "elapsed_time": "3:21:51", "remaining_time": "5:00:31", "throughput": 4390.18, "total_tokens": 53171248} {"current_steps": 24635, "total_steps": 61300, "loss": 0.3325, "lr": 3.7359190348570726e-05, "epoch": 4.018760195758564, "percentage": 40.19, "elapsed_time": "3:21:53", "remaining_time": "5:00:29", "throughput": 4390.27, "total_tokens": 53183312} {"current_steps": 24640, "total_steps": 61300, "loss": 0.3472, "lr": 3.735300252073881e-05, "epoch": 4.019575856443719, "percentage": 40.2, "elapsed_time": "3:21:56", "remaining_time": "5:00:26", "throughput": 4390.35, "total_tokens": 53194192} {"current_steps": 24645, "total_steps": 61300, "loss": 0.3302, "lr": 3.734681369150983e-05, "epoch": 4.020391517128874, "percentage": 40.2, "elapsed_time": "3:21:58", "remaining_time": "5:00:24", "throughput": 4390.43, "total_tokens": 53205296} {"current_steps": 24650, "total_steps": 61300, "loss": 0.3036, "lr": 3.7340623861385496e-05, "epoch": 4.02120717781403, "percentage": 40.21, "elapsed_time": "3:22:00", "remaining_time": "5:00:21", "throughput": 4390.51, "total_tokens": 53215632} {"current_steps": 24655, "total_steps": 61300, "loss": 0.3787, "lr": 3.7334433030867564e-05, "epoch": 4.0220228384991845, "percentage": 40.22, "elapsed_time": "3:22:02", "remaining_time": "5:00:18", "throughput": 4390.6, "total_tokens": 53226704} {"current_steps": 24660, "total_steps": 61300, "loss": 0.3093, "lr": 3.732824120045791e-05, "epoch": 4.022838499184339, "percentage": 40.23, "elapsed_time": "3:22:05", "remaining_time": "5:00:15", "throughput": 4390.68, "total_tokens": 53237328} {"current_steps": 24665, "total_steps": 61300, "loss": 0.2993, "lr": 3.732204837065847e-05, "epoch": 4.023654159869494, "percentage": 40.24, "elapsed_time": "3:22:07", "remaining_time": "5:00:12", "throughput": 4390.77, "total_tokens": 53248912} {"current_steps": 24670, "total_steps": 61300, "loss": 0.3347, "lr": 3.731585454197127e-05, "epoch": 4.024469820554649, "percentage": 40.24, "elapsed_time": "3:22:09", "remaining_time": "5:00:10", "throughput": 4390.85, "total_tokens": 53260528} {"current_steps": 24675, "total_steps": 61300, "loss": 0.3493, "lr": 3.7309659714898404e-05, "epoch": 4.025285481239805, "percentage": 40.25, "elapsed_time": "3:22:12", "remaining_time": "5:00:07", "throughput": 4390.94, "total_tokens": 53272016} {"current_steps": 24680, "total_steps": 61300, "loss": 0.3283, "lr": 3.730346388994207e-05, "epoch": 4.0261011419249595, "percentage": 40.26, "elapsed_time": "3:22:14", "remaining_time": "5:00:05", "throughput": 4391.02, "total_tokens": 53282640} {"current_steps": 24685, "total_steps": 61300, "loss": 0.3204, "lr": 3.729726706760452e-05, "epoch": 4.026916802610114, "percentage": 40.27, "elapsed_time": "3:22:16", "remaining_time": "5:00:02", "throughput": 4391.12, "total_tokens": 53293904} {"current_steps": 24690, "total_steps": 61300, "loss": 0.3287, "lr": 3.729106924838812e-05, "epoch": 4.027732463295269, "percentage": 40.28, "elapsed_time": "3:22:19", "remaining_time": "4:59:59", "throughput": 4391.22, "total_tokens": 53305904} {"current_steps": 24695, "total_steps": 61300, "loss": 0.3091, "lr": 3.728487043279527e-05, "epoch": 4.028548123980424, "percentage": 40.29, "elapsed_time": "3:22:21", "remaining_time": "4:59:57", "throughput": 4391.29, "total_tokens": 53316528} {"current_steps": 24700, "total_steps": 61300, "loss": 0.333, "lr": 3.727867062132849e-05, "epoch": 4.029363784665579, "percentage": 40.29, "elapsed_time": "3:22:23", "remaining_time": "4:59:54", "throughput": 4391.37, "total_tokens": 53328464} {"current_steps": 24705, "total_steps": 61300, "loss": 0.3674, "lr": 3.7272469814490376e-05, "epoch": 4.0301794453507345, "percentage": 40.3, "elapsed_time": "3:22:26", "remaining_time": "4:59:51", "throughput": 4391.46, "total_tokens": 53339440} {"current_steps": 24710, "total_steps": 61300, "loss": 0.3256, "lr": 3.726626801278358e-05, "epoch": 4.030995106035889, "percentage": 40.31, "elapsed_time": "3:22:28", "remaining_time": "4:59:49", "throughput": 4391.53, "total_tokens": 53350000} {"current_steps": 24715, "total_steps": 61300, "loss": 0.2895, "lr": 3.726006521671086e-05, "epoch": 4.031810766721044, "percentage": 40.32, "elapsed_time": "3:22:30", "remaining_time": "4:59:46", "throughput": 4391.61, "total_tokens": 53360528} {"current_steps": 24720, "total_steps": 61300, "loss": 0.3386, "lr": 3.7253861426775056e-05, "epoch": 4.032626427406199, "percentage": 40.33, "elapsed_time": "3:22:32", "remaining_time": "4:59:43", "throughput": 4391.7, "total_tokens": 53371600} {"current_steps": 24725, "total_steps": 61300, "loss": 0.3285, "lr": 3.7247656643479064e-05, "epoch": 4.033442088091354, "percentage": 40.33, "elapsed_time": "3:22:35", "remaining_time": "4:59:40", "throughput": 4391.77, "total_tokens": 53382032} {"current_steps": 24730, "total_steps": 61300, "loss": 0.3367, "lr": 3.724145086732588e-05, "epoch": 4.034257748776509, "percentage": 40.34, "elapsed_time": "3:22:37", "remaining_time": "4:59:37", "throughput": 4391.86, "total_tokens": 53392816} {"current_steps": 24735, "total_steps": 61300, "loss": 0.3334, "lr": 3.7235244098818576e-05, "epoch": 4.035073409461664, "percentage": 40.35, "elapsed_time": "3:22:39", "remaining_time": "4:59:35", "throughput": 4391.94, "total_tokens": 53404624} {"current_steps": 24740, "total_steps": 61300, "loss": 0.3318, "lr": 3.722903633846031e-05, "epoch": 4.035889070146819, "percentage": 40.36, "elapsed_time": "3:22:42", "remaining_time": "4:59:32", "throughput": 4392.03, "total_tokens": 53416048} {"current_steps": 24745, "total_steps": 61300, "loss": 0.364, "lr": 3.72228275867543e-05, "epoch": 4.036704730831974, "percentage": 40.37, "elapsed_time": "3:22:44", "remaining_time": "4:59:29", "throughput": 4392.1, "total_tokens": 53426704} {"current_steps": 24750, "total_steps": 61300, "loss": 0.3163, "lr": 3.721661784420387e-05, "epoch": 4.037520391517129, "percentage": 40.38, "elapsed_time": "3:22:46", "remaining_time": "4:59:27", "throughput": 4392.19, "total_tokens": 53439248} {"current_steps": 24755, "total_steps": 61300, "loss": 0.3199, "lr": 3.721040711131242e-05, "epoch": 4.0383360522022835, "percentage": 40.38, "elapsed_time": "3:22:48", "remaining_time": "4:59:24", "throughput": 4392.25, "total_tokens": 53448400} {"current_steps": 24760, "total_steps": 61300, "loss": 0.3377, "lr": 3.72041953885834e-05, "epoch": 4.039151712887439, "percentage": 40.39, "elapsed_time": "3:22:51", "remaining_time": "4:59:21", "throughput": 4392.34, "total_tokens": 53460336} {"current_steps": 24765, "total_steps": 61300, "loss": 0.3248, "lr": 3.719798267652038e-05, "epoch": 4.039967373572594, "percentage": 40.4, "elapsed_time": "3:22:53", "remaining_time": "4:59:19", "throughput": 4392.41, "total_tokens": 53471568} {"current_steps": 24770, "total_steps": 61300, "loss": 0.3404, "lr": 3.719176897562701e-05, "epoch": 4.040783034257749, "percentage": 40.41, "elapsed_time": "3:22:56", "remaining_time": "4:59:16", "throughput": 4392.5, "total_tokens": 53483568} {"current_steps": 24775, "total_steps": 61300, "loss": 0.3746, "lr": 3.718555428640697e-05, "epoch": 4.041598694942904, "percentage": 40.42, "elapsed_time": "3:22:57", "remaining_time": "4:59:13", "throughput": 4392.59, "total_tokens": 53492848} {"current_steps": 24780, "total_steps": 61300, "loss": 0.3633, "lr": 3.717933860936407e-05, "epoch": 4.0424143556280585, "percentage": 40.42, "elapsed_time": "3:23:00", "remaining_time": "4:59:10", "throughput": 4392.65, "total_tokens": 53502992} {"current_steps": 24785, "total_steps": 61300, "loss": 0.3071, "lr": 3.7173121945002197e-05, "epoch": 4.043230016313213, "percentage": 40.43, "elapsed_time": "3:23:02", "remaining_time": "4:59:07", "throughput": 4392.73, "total_tokens": 53513264} {"current_steps": 24790, "total_steps": 61300, "loss": 0.3535, "lr": 3.716690429382529e-05, "epoch": 4.044045676998369, "percentage": 40.44, "elapsed_time": "3:23:04", "remaining_time": "4:59:04", "throughput": 4392.81, "total_tokens": 53523984} {"current_steps": 24795, "total_steps": 61300, "loss": 0.3232, "lr": 3.716068565633738e-05, "epoch": 4.044861337683524, "percentage": 40.45, "elapsed_time": "3:23:06", "remaining_time": "4:59:02", "throughput": 4392.88, "total_tokens": 53534672} {"current_steps": 24800, "total_steps": 61300, "loss": 0.3378, "lr": 3.715446603304259e-05, "epoch": 4.045676998368679, "percentage": 40.46, "elapsed_time": "3:23:09", "remaining_time": "4:58:59", "throughput": 4392.98, "total_tokens": 53546224} {"current_steps": 24805, "total_steps": 61300, "loss": 0.3346, "lr": 3.7148245424445114e-05, "epoch": 4.0464926590538335, "percentage": 40.46, "elapsed_time": "3:23:11", "remaining_time": "4:58:56", "throughput": 4393.04, "total_tokens": 53555952} {"current_steps": 24810, "total_steps": 61300, "loss": 0.2952, "lr": 3.7142023831049226e-05, "epoch": 4.047308319738988, "percentage": 40.47, "elapsed_time": "3:23:13", "remaining_time": "4:58:53", "throughput": 4393.13, "total_tokens": 53567024} {"current_steps": 24815, "total_steps": 61300, "loss": 0.3176, "lr": 3.713580125335928e-05, "epoch": 4.048123980424143, "percentage": 40.48, "elapsed_time": "3:23:15", "remaining_time": "4:58:51", "throughput": 4393.21, "total_tokens": 53578032} {"current_steps": 24820, "total_steps": 61300, "loss": 0.3498, "lr": 3.7129577691879694e-05, "epoch": 4.048939641109299, "percentage": 40.49, "elapsed_time": "3:23:18", "remaining_time": "4:58:48", "throughput": 4393.31, "total_tokens": 53589968} {"current_steps": 24825, "total_steps": 61300, "loss": 0.3445, "lr": 3.712335314711501e-05, "epoch": 4.049755301794454, "percentage": 40.5, "elapsed_time": "3:23:20", "remaining_time": "4:58:45", "throughput": 4393.36, "total_tokens": 53599472} {"current_steps": 24830, "total_steps": 61300, "loss": 0.3964, "lr": 3.7117127619569796e-05, "epoch": 4.0505709624796085, "percentage": 40.51, "elapsed_time": "3:23:22", "remaining_time": "4:58:42", "throughput": 4393.45, "total_tokens": 53611376} {"current_steps": 24835, "total_steps": 61300, "loss": 0.3053, "lr": 3.7110901109748745e-05, "epoch": 4.051386623164763, "percentage": 40.51, "elapsed_time": "3:23:25", "remaining_time": "4:58:40", "throughput": 4393.55, "total_tokens": 53623760} {"current_steps": 24840, "total_steps": 61300, "loss": 0.3537, "lr": 3.710467361815659e-05, "epoch": 4.052202283849918, "percentage": 40.52, "elapsed_time": "3:23:27", "remaining_time": "4:58:37", "throughput": 4393.63, "total_tokens": 53634416} {"current_steps": 24845, "total_steps": 61300, "loss": 0.3658, "lr": 3.709844514529818e-05, "epoch": 4.053017944535074, "percentage": 40.53, "elapsed_time": "3:23:29", "remaining_time": "4:58:34", "throughput": 4393.71, "total_tokens": 53644528} {"current_steps": 24850, "total_steps": 61300, "loss": 0.3383, "lr": 3.709221569167842e-05, "epoch": 4.053833605220229, "percentage": 40.54, "elapsed_time": "3:23:31", "remaining_time": "4:58:31", "throughput": 4393.78, "total_tokens": 53654480} {"current_steps": 24855, "total_steps": 61300, "loss": 0.3246, "lr": 3.70859852578023e-05, "epoch": 4.054649265905383, "percentage": 40.55, "elapsed_time": "3:23:33", "remaining_time": "4:58:28", "throughput": 4393.85, "total_tokens": 53665136} {"current_steps": 24860, "total_steps": 61300, "loss": 0.3411, "lr": 3.70797538441749e-05, "epoch": 4.055464926590538, "percentage": 40.55, "elapsed_time": "3:23:36", "remaining_time": "4:58:26", "throughput": 4393.94, "total_tokens": 53677104} {"current_steps": 24865, "total_steps": 61300, "loss": 0.3447, "lr": 3.707352145130135e-05, "epoch": 4.056280587275693, "percentage": 40.56, "elapsed_time": "3:23:38", "remaining_time": "4:58:23", "throughput": 4394.0, "total_tokens": 53688016} {"current_steps": 24870, "total_steps": 61300, "loss": 0.3504, "lr": 3.706728807968689e-05, "epoch": 4.057096247960848, "percentage": 40.57, "elapsed_time": "3:23:40", "remaining_time": "4:58:21", "throughput": 4394.08, "total_tokens": 53698544} {"current_steps": 24875, "total_steps": 61300, "loss": 0.3184, "lr": 3.706105372983683e-05, "epoch": 4.057911908646004, "percentage": 40.58, "elapsed_time": "3:23:43", "remaining_time": "4:58:18", "throughput": 4394.17, "total_tokens": 53710000} {"current_steps": 24880, "total_steps": 61300, "loss": 0.3064, "lr": 3.705481840225656e-05, "epoch": 4.058727569331158, "percentage": 40.59, "elapsed_time": "3:23:45", "remaining_time": "4:58:15", "throughput": 4394.24, "total_tokens": 53720656} {"current_steps": 24885, "total_steps": 61300, "loss": 0.3577, "lr": 3.704858209745155e-05, "epoch": 4.059543230016313, "percentage": 40.6, "elapsed_time": "3:23:47", "remaining_time": "4:58:12", "throughput": 4394.32, "total_tokens": 53731280} {"current_steps": 24890, "total_steps": 61300, "loss": 0.3443, "lr": 3.704234481592733e-05, "epoch": 4.060358890701468, "percentage": 40.6, "elapsed_time": "3:23:49", "remaining_time": "4:58:09", "throughput": 4394.4, "total_tokens": 53741712} {"current_steps": 24895, "total_steps": 61300, "loss": 0.3724, "lr": 3.703610655818955e-05, "epoch": 4.061174551386623, "percentage": 40.61, "elapsed_time": "3:23:51", "remaining_time": "4:58:07", "throughput": 4394.49, "total_tokens": 53753360} {"current_steps": 24900, "total_steps": 61300, "loss": 0.3093, "lr": 3.702986732474389e-05, "epoch": 4.061990212071779, "percentage": 40.62, "elapsed_time": "3:23:54", "remaining_time": "4:58:04", "throughput": 4394.57, "total_tokens": 53764112} {"current_steps": 24905, "total_steps": 61300, "loss": 0.3321, "lr": 3.702362711609615e-05, "epoch": 4.062805872756933, "percentage": 40.63, "elapsed_time": "3:23:56", "remaining_time": "4:58:01", "throughput": 4394.62, "total_tokens": 53774320} {"current_steps": 24910, "total_steps": 61300, "loss": 0.3189, "lr": 3.701738593275219e-05, "epoch": 4.063621533442088, "percentage": 40.64, "elapsed_time": "3:23:58", "remaining_time": "4:57:58", "throughput": 4394.7, "total_tokens": 53784848} {"current_steps": 24915, "total_steps": 61300, "loss": 0.332, "lr": 3.701114377521795e-05, "epoch": 4.064437194127243, "percentage": 40.64, "elapsed_time": "3:24:00", "remaining_time": "4:57:56", "throughput": 4394.77, "total_tokens": 53795632} {"current_steps": 24920, "total_steps": 61300, "loss": 0.3471, "lr": 3.700490064399945e-05, "epoch": 4.065252854812398, "percentage": 40.65, "elapsed_time": "3:24:03", "remaining_time": "4:57:53", "throughput": 4394.84, "total_tokens": 53806480} {"current_steps": 24925, "total_steps": 61300, "loss": 0.3188, "lr": 3.6998656539602795e-05, "epoch": 4.066068515497553, "percentage": 40.66, "elapsed_time": "3:24:05", "remaining_time": "4:57:50", "throughput": 4394.91, "total_tokens": 53816816} {"current_steps": 24930, "total_steps": 61300, "loss": 0.3483, "lr": 3.699241146253416e-05, "epoch": 4.066884176182708, "percentage": 40.67, "elapsed_time": "3:24:07", "remaining_time": "4:57:47", "throughput": 4395.01, "total_tokens": 53828720} {"current_steps": 24935, "total_steps": 61300, "loss": 0.3534, "lr": 3.69861654132998e-05, "epoch": 4.067699836867863, "percentage": 40.68, "elapsed_time": "3:24:10", "remaining_time": "4:57:45", "throughput": 4395.1, "total_tokens": 53840816} {"current_steps": 24940, "total_steps": 61300, "loss": 0.325, "lr": 3.6979918392406055e-05, "epoch": 4.068515497553018, "percentage": 40.69, "elapsed_time": "3:24:12", "remaining_time": "4:57:42", "throughput": 4395.18, "total_tokens": 53851120} {"current_steps": 24945, "total_steps": 61300, "loss": 0.3355, "lr": 3.697367040035934e-05, "epoch": 4.069331158238173, "percentage": 40.69, "elapsed_time": "3:24:14", "remaining_time": "4:57:39", "throughput": 4395.26, "total_tokens": 53862288} {"current_steps": 24950, "total_steps": 61300, "loss": 0.3325, "lr": 3.696742143766615e-05, "epoch": 4.070146818923328, "percentage": 40.7, "elapsed_time": "3:24:16", "remaining_time": "4:57:37", "throughput": 4395.35, "total_tokens": 53873584} {"current_steps": 24955, "total_steps": 61300, "loss": 0.375, "lr": 3.696117150483306e-05, "epoch": 4.0709624796084825, "percentage": 40.71, "elapsed_time": "3:24:19", "remaining_time": "4:57:34", "throughput": 4395.42, "total_tokens": 53885328} {"current_steps": 24960, "total_steps": 61300, "loss": 0.3357, "lr": 3.695492060236671e-05, "epoch": 4.071778140293638, "percentage": 40.72, "elapsed_time": "3:24:21", "remaining_time": "4:57:31", "throughput": 4395.49, "total_tokens": 53895376} {"current_steps": 24965, "total_steps": 61300, "loss": 0.3461, "lr": 3.694866873077384e-05, "epoch": 4.072593800978793, "percentage": 40.73, "elapsed_time": "3:24:23", "remaining_time": "4:57:29", "throughput": 4395.56, "total_tokens": 53906640} {"current_steps": 24970, "total_steps": 61300, "loss": 0.3369, "lr": 3.6942415890561254e-05, "epoch": 4.073409461663948, "percentage": 40.73, "elapsed_time": "3:24:26", "remaining_time": "4:57:26", "throughput": 4395.64, "total_tokens": 53917264} {"current_steps": 24975, "total_steps": 61300, "loss": 0.3605, "lr": 3.6936162082235844e-05, "epoch": 4.074225122349103, "percentage": 40.74, "elapsed_time": "3:24:28", "remaining_time": "4:57:23", "throughput": 4395.7, "total_tokens": 53927984} {"current_steps": 24980, "total_steps": 61300, "loss": 0.3402, "lr": 3.692990730630457e-05, "epoch": 4.075040783034257, "percentage": 40.75, "elapsed_time": "3:24:30", "remaining_time": "4:57:20", "throughput": 4395.79, "total_tokens": 53938672} {"current_steps": 24985, "total_steps": 61300, "loss": 0.3323, "lr": 3.692365156327448e-05, "epoch": 4.075856443719413, "percentage": 40.76, "elapsed_time": "3:24:33", "remaining_time": "4:57:18", "throughput": 4395.87, "total_tokens": 53951120} {"current_steps": 24990, "total_steps": 61300, "loss": 0.3581, "lr": 3.691739485365269e-05, "epoch": 4.076672104404568, "percentage": 40.77, "elapsed_time": "3:24:35", "remaining_time": "4:57:15", "throughput": 4395.96, "total_tokens": 53962192} {"current_steps": 24995, "total_steps": 61300, "loss": 0.339, "lr": 3.691113717794641e-05, "epoch": 4.077487765089723, "percentage": 40.77, "elapsed_time": "3:24:37", "remaining_time": "4:57:13", "throughput": 4396.03, "total_tokens": 53973488} {"current_steps": 25000, "total_steps": 61300, "loss": 0.3555, "lr": 3.6904878536662904e-05, "epoch": 4.078303425774878, "percentage": 40.78, "elapsed_time": "3:24:40", "remaining_time": "4:57:10", "throughput": 4396.11, "total_tokens": 53984272} {"current_steps": 25005, "total_steps": 61300, "loss": 0.3239, "lr": 3.6898618930309556e-05, "epoch": 4.079119086460032, "percentage": 40.79, "elapsed_time": "3:24:42", "remaining_time": "4:57:07", "throughput": 4396.19, "total_tokens": 53994704} {"current_steps": 25010, "total_steps": 61300, "loss": 0.346, "lr": 3.6892358359393767e-05, "epoch": 4.079934747145187, "percentage": 40.8, "elapsed_time": "3:24:44", "remaining_time": "4:57:04", "throughput": 4396.26, "total_tokens": 54005552} {"current_steps": 25015, "total_steps": 61300, "loss": 0.3264, "lr": 3.688609682442308e-05, "epoch": 4.080750407830343, "percentage": 40.81, "elapsed_time": "3:24:46", "remaining_time": "4:57:02", "throughput": 4396.34, "total_tokens": 54016560} {"current_steps": 25020, "total_steps": 61300, "loss": 0.359, "lr": 3.687983432590507e-05, "epoch": 4.081566068515498, "percentage": 40.82, "elapsed_time": "3:24:48", "remaining_time": "4:56:59", "throughput": 4396.4, "total_tokens": 54026736} {"current_steps": 25025, "total_steps": 61300, "loss": 0.3174, "lr": 3.6873570864347415e-05, "epoch": 4.082381729200653, "percentage": 40.82, "elapsed_time": "3:24:50", "remaining_time": "4:56:56", "throughput": 4396.47, "total_tokens": 54036592} {"current_steps": 25030, "total_steps": 61300, "loss": 0.3387, "lr": 3.686730644025786e-05, "epoch": 4.083197389885807, "percentage": 40.83, "elapsed_time": "3:24:53", "remaining_time": "4:56:53", "throughput": 4396.54, "total_tokens": 54046864} {"current_steps": 25035, "total_steps": 61300, "loss": 0.3069, "lr": 3.686104105414423e-05, "epoch": 4.084013050570962, "percentage": 40.84, "elapsed_time": "3:24:55", "remaining_time": "4:56:50", "throughput": 4396.63, "total_tokens": 54058448} {"current_steps": 25040, "total_steps": 61300, "loss": 0.3387, "lr": 3.6854774706514424e-05, "epoch": 4.084828711256117, "percentage": 40.85, "elapsed_time": "3:24:57", "remaining_time": "4:56:47", "throughput": 4396.71, "total_tokens": 54068848} {"current_steps": 25045, "total_steps": 61300, "loss": 0.3396, "lr": 3.684850739787644e-05, "epoch": 4.085644371941273, "percentage": 40.86, "elapsed_time": "3:24:59", "remaining_time": "4:56:45", "throughput": 4396.8, "total_tokens": 54079504} {"current_steps": 25050, "total_steps": 61300, "loss": 0.3512, "lr": 3.684223912873832e-05, "epoch": 4.0864600326264275, "percentage": 40.86, "elapsed_time": "3:25:01", "remaining_time": "4:56:42", "throughput": 4396.86, "total_tokens": 54089424} {"current_steps": 25055, "total_steps": 61300, "loss": 0.3226, "lr": 3.683596989960821e-05, "epoch": 4.087275693311582, "percentage": 40.87, "elapsed_time": "3:25:04", "remaining_time": "4:56:39", "throughput": 4396.95, "total_tokens": 54100848} {"current_steps": 25060, "total_steps": 61300, "loss": 0.362, "lr": 3.682969971099433e-05, "epoch": 4.088091353996737, "percentage": 40.88, "elapsed_time": "3:25:06", "remaining_time": "4:56:36", "throughput": 4397.02, "total_tokens": 54111376} {"current_steps": 25065, "total_steps": 61300, "loss": 0.3333, "lr": 3.682342856340496e-05, "epoch": 4.088907014681892, "percentage": 40.89, "elapsed_time": "3:25:08", "remaining_time": "4:56:34", "throughput": 4397.12, "total_tokens": 54123408} {"current_steps": 25070, "total_steps": 61300, "loss": 0.3257, "lr": 3.681715645734848e-05, "epoch": 4.089722675367048, "percentage": 40.9, "elapsed_time": "3:25:10", "remaining_time": "4:56:31", "throughput": 4397.19, "total_tokens": 54133296} {"current_steps": 25075, "total_steps": 61300, "loss": 0.3157, "lr": 3.681088339333334e-05, "epoch": 4.0905383360522025, "percentage": 40.91, "elapsed_time": "3:25:13", "remaining_time": "4:56:28", "throughput": 4397.28, "total_tokens": 54144240} {"current_steps": 25080, "total_steps": 61300, "loss": 0.3345, "lr": 3.680460937186807e-05, "epoch": 4.091353996737357, "percentage": 40.91, "elapsed_time": "3:25:15", "remaining_time": "4:56:26", "throughput": 4397.37, "total_tokens": 54157008} {"current_steps": 25085, "total_steps": 61300, "loss": 0.3416, "lr": 3.679833439346126e-05, "epoch": 4.092169657422512, "percentage": 40.92, "elapsed_time": "3:25:17", "remaining_time": "4:56:23", "throughput": 4397.45, "total_tokens": 54167792} {"current_steps": 25090, "total_steps": 61300, "loss": 0.3259, "lr": 3.6792058458621607e-05, "epoch": 4.092985318107667, "percentage": 40.93, "elapsed_time": "3:25:20", "remaining_time": "4:56:20", "throughput": 4397.53, "total_tokens": 54178672} {"current_steps": 25095, "total_steps": 61300, "loss": 0.3445, "lr": 3.678578156785786e-05, "epoch": 4.093800978792822, "percentage": 40.94, "elapsed_time": "3:25:22", "remaining_time": "4:56:18", "throughput": 4397.62, "total_tokens": 54190288} {"current_steps": 25100, "total_steps": 61300, "loss": 0.3315, "lr": 3.677950372167885e-05, "epoch": 4.0946166394779775, "percentage": 40.95, "elapsed_time": "3:25:24", "remaining_time": "4:56:15", "throughput": 4397.66, "total_tokens": 54199728} {"current_steps": 25105, "total_steps": 61300, "loss": 0.3637, "lr": 3.677322492059352e-05, "epoch": 4.095432300163132, "percentage": 40.95, "elapsed_time": "3:25:26", "remaining_time": "4:56:12", "throughput": 4397.75, "total_tokens": 54209840} {"current_steps": 25110, "total_steps": 61300, "loss": 0.3261, "lr": 3.676694516511083e-05, "epoch": 4.096247960848287, "percentage": 40.96, "elapsed_time": "3:25:28", "remaining_time": "4:56:09", "throughput": 4397.81, "total_tokens": 54219856} {"current_steps": 25115, "total_steps": 61300, "loss": 0.3745, "lr": 3.676066445573986e-05, "epoch": 4.097063621533442, "percentage": 40.97, "elapsed_time": "3:25:30", "remaining_time": "4:56:06", "throughput": 4397.88, "total_tokens": 54230096} {"current_steps": 25120, "total_steps": 61300, "loss": 0.3379, "lr": 3.675438279298975e-05, "epoch": 4.097879282218597, "percentage": 40.98, "elapsed_time": "3:25:33", "remaining_time": "4:56:03", "throughput": 4397.95, "total_tokens": 54241840} {"current_steps": 25125, "total_steps": 61300, "loss": 0.3718, "lr": 3.674810017736974e-05, "epoch": 4.0986949429037525, "percentage": 40.99, "elapsed_time": "3:25:35", "remaining_time": "4:56:00", "throughput": 4398.03, "total_tokens": 54251920} {"current_steps": 25130, "total_steps": 61300, "loss": 0.3725, "lr": 3.674181660938911e-05, "epoch": 4.099510603588907, "percentage": 41.0, "elapsed_time": "3:25:37", "remaining_time": "4:55:58", "throughput": 4398.12, "total_tokens": 54263344} {"current_steps": 25135, "total_steps": 61300, "loss": 0.3835, "lr": 3.6735532089557256e-05, "epoch": 4.100326264274062, "percentage": 41.0, "elapsed_time": "3:25:40", "remaining_time": "4:55:55", "throughput": 4398.2, "total_tokens": 54274384} {"current_steps": 25140, "total_steps": 61300, "loss": 0.3517, "lr": 3.672924661838362e-05, "epoch": 4.101141924959217, "percentage": 41.01, "elapsed_time": "3:25:42", "remaining_time": "4:55:52", "throughput": 4398.28, "total_tokens": 54285296} {"current_steps": 25145, "total_steps": 61300, "loss": 0.3243, "lr": 3.672296019637774e-05, "epoch": 4.101957585644372, "percentage": 41.02, "elapsed_time": "3:25:44", "remaining_time": "4:55:49", "throughput": 4398.36, "total_tokens": 54295504} {"current_steps": 25150, "total_steps": 61300, "loss": 0.3023, "lr": 3.6716672824049234e-05, "epoch": 4.102773246329527, "percentage": 41.03, "elapsed_time": "3:25:46", "remaining_time": "4:55:47", "throughput": 4398.42, "total_tokens": 54306704} {"current_steps": 25155, "total_steps": 61300, "loss": 0.3501, "lr": 3.671038450190777e-05, "epoch": 4.103588907014682, "percentage": 41.04, "elapsed_time": "3:25:48", "remaining_time": "4:55:44", "throughput": 4398.5, "total_tokens": 54316720} {"current_steps": 25160, "total_steps": 61300, "loss": 0.307, "lr": 3.670409523046312e-05, "epoch": 4.104404567699837, "percentage": 41.04, "elapsed_time": "3:25:51", "remaining_time": "4:55:41", "throughput": 4398.58, "total_tokens": 54327408} {"current_steps": 25165, "total_steps": 61300, "loss": 0.3215, "lr": 3.669780501022513e-05, "epoch": 4.105220228384992, "percentage": 41.05, "elapsed_time": "3:25:53", "remaining_time": "4:55:38", "throughput": 4398.66, "total_tokens": 54337104} {"current_steps": 25170, "total_steps": 61300, "loss": 0.3018, "lr": 3.669151384170371e-05, "epoch": 4.106035889070147, "percentage": 41.06, "elapsed_time": "3:25:55", "remaining_time": "4:55:35", "throughput": 4398.73, "total_tokens": 54347408} {"current_steps": 25175, "total_steps": 61300, "loss": 0.3554, "lr": 3.668522172540886e-05, "epoch": 4.1068515497553015, "percentage": 41.07, "elapsed_time": "3:25:57", "remaining_time": "4:55:32", "throughput": 4398.79, "total_tokens": 54357264} {"current_steps": 25180, "total_steps": 61300, "loss": 0.325, "lr": 3.667892866185064e-05, "epoch": 4.107667210440456, "percentage": 41.08, "elapsed_time": "3:25:59", "remaining_time": "4:55:29", "throughput": 4398.88, "total_tokens": 54368816} {"current_steps": 25185, "total_steps": 61300, "loss": 0.3183, "lr": 3.6672634651539205e-05, "epoch": 4.108482871125612, "percentage": 41.08, "elapsed_time": "3:26:02", "remaining_time": "4:55:27", "throughput": 4398.97, "total_tokens": 54380848} {"current_steps": 25190, "total_steps": 61300, "loss": 0.2876, "lr": 3.6666339694984785e-05, "epoch": 4.109298531810767, "percentage": 41.09, "elapsed_time": "3:26:04", "remaining_time": "4:55:24", "throughput": 4399.05, "total_tokens": 54391760} {"current_steps": 25195, "total_steps": 61300, "loss": 0.317, "lr": 3.666004379269766e-05, "epoch": 4.110114192495922, "percentage": 41.1, "elapsed_time": "3:26:06", "remaining_time": "4:55:21", "throughput": 4399.12, "total_tokens": 54402384} {"current_steps": 25200, "total_steps": 61300, "loss": 0.3423, "lr": 3.665374694518824e-05, "epoch": 4.1109298531810765, "percentage": 41.11, "elapsed_time": "3:26:08", "remaining_time": "4:55:19", "throughput": 4399.2, "total_tokens": 54413680} {"current_steps": 25205, "total_steps": 61300, "loss": 0.3584, "lr": 3.664744915296695e-05, "epoch": 4.111745513866231, "percentage": 41.12, "elapsed_time": "3:26:10", "remaining_time": "4:55:15", "throughput": 4399.26, "total_tokens": 54422640} {"current_steps": 25210, "total_steps": 61300, "loss": 0.3875, "lr": 3.664115041654434e-05, "epoch": 4.112561174551387, "percentage": 41.13, "elapsed_time": "3:26:13", "remaining_time": "4:55:13", "throughput": 4399.35, "total_tokens": 54434576} {"current_steps": 25215, "total_steps": 61300, "loss": 0.38, "lr": 3.663485073643102e-05, "epoch": 4.113376835236542, "percentage": 41.13, "elapsed_time": "3:26:15", "remaining_time": "4:55:10", "throughput": 4399.4, "total_tokens": 54444272} {"current_steps": 25220, "total_steps": 61300, "loss": 0.3484, "lr": 3.6628550113137635e-05, "epoch": 4.114192495921697, "percentage": 41.14, "elapsed_time": "3:26:17", "remaining_time": "4:55:07", "throughput": 4399.5, "total_tokens": 54456016} {"current_steps": 25225, "total_steps": 61300, "loss": 0.3519, "lr": 3.6622248547175e-05, "epoch": 4.1150081566068515, "percentage": 41.15, "elapsed_time": "3:26:19", "remaining_time": "4:55:04", "throughput": 4399.58, "total_tokens": 54466448} {"current_steps": 25230, "total_steps": 61300, "loss": 0.3725, "lr": 3.661594603905392e-05, "epoch": 4.115823817292006, "percentage": 41.16, "elapsed_time": "3:26:22", "remaining_time": "4:55:01", "throughput": 4399.64, "total_tokens": 54476592} {"current_steps": 25235, "total_steps": 61300, "loss": 0.325, "lr": 3.660964258928532e-05, "epoch": 4.116639477977161, "percentage": 41.17, "elapsed_time": "3:26:24", "remaining_time": "4:54:59", "throughput": 4399.71, "total_tokens": 54488048} {"current_steps": 25240, "total_steps": 61300, "loss": 0.3244, "lr": 3.660333819838018e-05, "epoch": 4.117455138662317, "percentage": 41.17, "elapsed_time": "3:26:26", "remaining_time": "4:54:56", "throughput": 4399.79, "total_tokens": 54499120} {"current_steps": 25245, "total_steps": 61300, "loss": 0.3281, "lr": 3.659703286684957e-05, "epoch": 4.118270799347472, "percentage": 41.18, "elapsed_time": "3:26:29", "remaining_time": "4:54:54", "throughput": 4399.86, "total_tokens": 54510576} {"current_steps": 25250, "total_steps": 61300, "loss": 0.3355, "lr": 3.659072659520463e-05, "epoch": 4.1190864600326265, "percentage": 41.19, "elapsed_time": "3:26:31", "remaining_time": "4:54:51", "throughput": 4399.96, "total_tokens": 54522160} {"current_steps": 25255, "total_steps": 61300, "loss": 0.3147, "lr": 3.658441938395659e-05, "epoch": 4.119902120717781, "percentage": 41.2, "elapsed_time": "3:26:33", "remaining_time": "4:54:49", "throughput": 4400.05, "total_tokens": 54533872} {"current_steps": 25260, "total_steps": 61300, "loss": 0.3006, "lr": 3.6578111233616726e-05, "epoch": 4.120717781402936, "percentage": 41.21, "elapsed_time": "3:26:36", "remaining_time": "4:54:46", "throughput": 4400.13, "total_tokens": 54545200} {"current_steps": 25265, "total_steps": 61300, "loss": 0.3621, "lr": 3.657180214469643e-05, "epoch": 4.121533442088092, "percentage": 41.22, "elapsed_time": "3:26:38", "remaining_time": "4:54:43", "throughput": 4400.2, "total_tokens": 54554960} {"current_steps": 25270, "total_steps": 61300, "loss": 0.3302, "lr": 3.656549211770713e-05, "epoch": 4.122349102773247, "percentage": 41.22, "elapsed_time": "3:26:40", "remaining_time": "4:54:40", "throughput": 4400.27, "total_tokens": 54565456} {"current_steps": 25275, "total_steps": 61300, "loss": 0.3533, "lr": 3.655918115316036e-05, "epoch": 4.123164763458401, "percentage": 41.23, "elapsed_time": "3:26:42", "remaining_time": "4:54:37", "throughput": 4400.34, "total_tokens": 54575536} {"current_steps": 25280, "total_steps": 61300, "loss": 0.3659, "lr": 3.655286925156772e-05, "epoch": 4.123980424143556, "percentage": 41.24, "elapsed_time": "3:26:44", "remaining_time": "4:54:34", "throughput": 4400.41, "total_tokens": 54585296} {"current_steps": 25285, "total_steps": 61300, "loss": 0.3339, "lr": 3.654655641344087e-05, "epoch": 4.124796084828711, "percentage": 41.25, "elapsed_time": "3:26:46", "remaining_time": "4:54:31", "throughput": 4400.48, "total_tokens": 54595600} {"current_steps": 25290, "total_steps": 61300, "loss": 0.3363, "lr": 3.654024263929157e-05, "epoch": 4.125611745513866, "percentage": 41.26, "elapsed_time": "3:26:48", "remaining_time": "4:54:28", "throughput": 4400.55, "total_tokens": 54606160} {"current_steps": 25295, "total_steps": 61300, "loss": 0.3342, "lr": 3.653392792963165e-05, "epoch": 4.126427406199022, "percentage": 41.26, "elapsed_time": "3:26:51", "remaining_time": "4:54:26", "throughput": 4400.63, "total_tokens": 54617232} {"current_steps": 25300, "total_steps": 61300, "loss": 0.3147, "lr": 3.652761228497301e-05, "epoch": 4.127243066884176, "percentage": 41.27, "elapsed_time": "3:26:53", "remaining_time": "4:54:23", "throughput": 4400.7, "total_tokens": 54628688} {"current_steps": 25305, "total_steps": 61300, "loss": 0.3567, "lr": 3.652129570582763e-05, "epoch": 4.128058727569331, "percentage": 41.28, "elapsed_time": "3:26:55", "remaining_time": "4:54:21", "throughput": 4400.79, "total_tokens": 54640016} {"current_steps": 25310, "total_steps": 61300, "loss": 0.3812, "lr": 3.651497819270756e-05, "epoch": 4.128874388254486, "percentage": 41.29, "elapsed_time": "3:26:57", "remaining_time": "4:54:17", "throughput": 4400.85, "total_tokens": 54648848} {"current_steps": 25315, "total_steps": 61300, "loss": 0.3455, "lr": 3.650865974612493e-05, "epoch": 4.129690048939641, "percentage": 41.3, "elapsed_time": "3:26:59", "remaining_time": "4:54:14", "throughput": 4400.93, "total_tokens": 54659376} {"current_steps": 25320, "total_steps": 61300, "loss": 0.3514, "lr": 3.650234036659195e-05, "epoch": 4.130505709624796, "percentage": 41.31, "elapsed_time": "3:27:02", "remaining_time": "4:54:12", "throughput": 4401.01, "total_tokens": 54670928} {"current_steps": 25325, "total_steps": 61300, "loss": 0.3251, "lr": 3.649602005462089e-05, "epoch": 4.131321370309951, "percentage": 41.31, "elapsed_time": "3:27:04", "remaining_time": "4:54:09", "throughput": 4401.08, "total_tokens": 54681584} {"current_steps": 25330, "total_steps": 61300, "loss": 0.3511, "lr": 3.648969881072412e-05, "epoch": 4.132137030995106, "percentage": 41.32, "elapsed_time": "3:27:06", "remaining_time": "4:54:06", "throughput": 4401.15, "total_tokens": 54692432} {"current_steps": 25335, "total_steps": 61300, "loss": 0.3575, "lr": 3.648337663541407e-05, "epoch": 4.132952691680261, "percentage": 41.33, "elapsed_time": "3:27:09", "remaining_time": "4:54:03", "throughput": 4401.23, "total_tokens": 54703152} {"current_steps": 25340, "total_steps": 61300, "loss": 0.3446, "lr": 3.647705352920324e-05, "epoch": 4.133768352365416, "percentage": 41.34, "elapsed_time": "3:27:11", "remaining_time": "4:54:01", "throughput": 4401.31, "total_tokens": 54714032} {"current_steps": 25345, "total_steps": 61300, "loss": 0.3257, "lr": 3.647072949260422e-05, "epoch": 4.134584013050571, "percentage": 41.35, "elapsed_time": "3:27:13", "remaining_time": "4:53:58", "throughput": 4401.37, "total_tokens": 54724272} {"current_steps": 25350, "total_steps": 61300, "loss": 0.3297, "lr": 3.646440452612965e-05, "epoch": 4.135399673735726, "percentage": 41.35, "elapsed_time": "3:27:15", "remaining_time": "4:53:55", "throughput": 4401.43, "total_tokens": 54734864} {"current_steps": 25355, "total_steps": 61300, "loss": 0.3535, "lr": 3.645807863029229e-05, "epoch": 4.136215334420881, "percentage": 41.36, "elapsed_time": "3:27:17", "remaining_time": "4:53:52", "throughput": 4401.5, "total_tokens": 54744464} {"current_steps": 25360, "total_steps": 61300, "loss": 0.3743, "lr": 3.645175180560495e-05, "epoch": 4.137030995106036, "percentage": 41.37, "elapsed_time": "3:27:19", "remaining_time": "4:53:49", "throughput": 4401.58, "total_tokens": 54754672} {"current_steps": 25365, "total_steps": 61300, "loss": 0.335, "lr": 3.644542405258049e-05, "epoch": 4.137846655791191, "percentage": 41.38, "elapsed_time": "3:27:22", "remaining_time": "4:53:46", "throughput": 4401.68, "total_tokens": 54766256} {"current_steps": 25370, "total_steps": 61300, "loss": 0.3602, "lr": 3.643909537173188e-05, "epoch": 4.138662316476346, "percentage": 41.39, "elapsed_time": "3:27:24", "remaining_time": "4:53:44", "throughput": 4401.75, "total_tokens": 54777296} {"current_steps": 25375, "total_steps": 61300, "loss": 0.3064, "lr": 3.643276576357216e-05, "epoch": 4.1394779771615005, "percentage": 41.39, "elapsed_time": "3:27:26", "remaining_time": "4:53:41", "throughput": 4401.82, "total_tokens": 54787728} {"current_steps": 25380, "total_steps": 61300, "loss": 0.3697, "lr": 3.642643522861444e-05, "epoch": 4.140293637846656, "percentage": 41.4, "elapsed_time": "3:27:28", "remaining_time": "4:53:38", "throughput": 4401.91, "total_tokens": 54798864} {"current_steps": 25385, "total_steps": 61300, "loss": 0.3519, "lr": 3.642010376737191e-05, "epoch": 4.141109298531811, "percentage": 41.41, "elapsed_time": "3:27:31", "remaining_time": "4:53:36", "throughput": 4401.99, "total_tokens": 54809872} {"current_steps": 25390, "total_steps": 61300, "loss": 0.3378, "lr": 3.641377138035782e-05, "epoch": 4.141924959216966, "percentage": 41.42, "elapsed_time": "3:27:33", "remaining_time": "4:53:32", "throughput": 4402.05, "total_tokens": 54819248} {"current_steps": 25395, "total_steps": 61300, "loss": 0.3475, "lr": 3.640743806808551e-05, "epoch": 4.142740619902121, "percentage": 41.43, "elapsed_time": "3:27:35", "remaining_time": "4:53:30", "throughput": 4402.14, "total_tokens": 54830448} {"current_steps": 25400, "total_steps": 61300, "loss": 0.3212, "lr": 3.640110383106838e-05, "epoch": 4.143556280587275, "percentage": 41.44, "elapsed_time": "3:27:37", "remaining_time": "4:53:27", "throughput": 4402.22, "total_tokens": 54841776} {"current_steps": 25405, "total_steps": 61300, "loss": 0.3637, "lr": 3.639476866981993e-05, "epoch": 4.14437194127243, "percentage": 41.44, "elapsed_time": "3:27:39", "remaining_time": "4:53:24", "throughput": 4402.28, "total_tokens": 54851888} {"current_steps": 25410, "total_steps": 61300, "loss": 0.3404, "lr": 3.638843258485372e-05, "epoch": 4.145187601957586, "percentage": 41.45, "elapsed_time": "3:27:41", "remaining_time": "4:53:21", "throughput": 4402.36, "total_tokens": 54861968} {"current_steps": 25415, "total_steps": 61300, "loss": 0.3359, "lr": 3.638209557668337e-05, "epoch": 4.146003262642741, "percentage": 41.46, "elapsed_time": "3:27:44", "remaining_time": "4:53:19", "throughput": 4402.44, "total_tokens": 54873104} {"current_steps": 25420, "total_steps": 61300, "loss": 0.3328, "lr": 3.637575764582261e-05, "epoch": 4.146818923327896, "percentage": 41.47, "elapsed_time": "3:27:46", "remaining_time": "4:53:16", "throughput": 4402.52, "total_tokens": 54883600} {"current_steps": 25425, "total_steps": 61300, "loss": 0.3421, "lr": 3.636941879278522e-05, "epoch": 4.14763458401305, "percentage": 41.48, "elapsed_time": "3:27:48", "remaining_time": "4:53:13", "throughput": 4402.6, "total_tokens": 54895184} {"current_steps": 25430, "total_steps": 61300, "loss": 0.3326, "lr": 3.636307901808504e-05, "epoch": 4.148450244698205, "percentage": 41.48, "elapsed_time": "3:27:51", "remaining_time": "4:53:11", "throughput": 4402.69, "total_tokens": 54906640} {"current_steps": 25435, "total_steps": 61300, "loss": 0.3788, "lr": 3.635673832223603e-05, "epoch": 4.149265905383361, "percentage": 41.49, "elapsed_time": "3:27:53", "remaining_time": "4:53:08", "throughput": 4402.77, "total_tokens": 54918192} {"current_steps": 25440, "total_steps": 61300, "loss": 0.3345, "lr": 3.635039670575218e-05, "epoch": 4.150081566068516, "percentage": 41.5, "elapsed_time": "3:27:55", "remaining_time": "4:53:05", "throughput": 4402.83, "total_tokens": 54927536} {"current_steps": 25445, "total_steps": 61300, "loss": 0.3153, "lr": 3.6344054169147584e-05, "epoch": 4.150897226753671, "percentage": 41.51, "elapsed_time": "3:27:57", "remaining_time": "4:53:02", "throughput": 4402.9, "total_tokens": 54938224} {"current_steps": 25450, "total_steps": 61300, "loss": 0.3297, "lr": 3.63377107129364e-05, "epoch": 4.151712887438825, "percentage": 41.52, "elapsed_time": "3:28:00", "remaining_time": "4:52:59", "throughput": 4402.96, "total_tokens": 54949104} {"current_steps": 25455, "total_steps": 61300, "loss": 0.3404, "lr": 3.633136633763286e-05, "epoch": 4.15252854812398, "percentage": 41.53, "elapsed_time": "3:28:02", "remaining_time": "4:52:57", "throughput": 4403.04, "total_tokens": 54960848} {"current_steps": 25460, "total_steps": 61300, "loss": 0.2765, "lr": 3.632502104375127e-05, "epoch": 4.153344208809135, "percentage": 41.53, "elapsed_time": "3:28:04", "remaining_time": "4:52:54", "throughput": 4403.12, "total_tokens": 54971600} {"current_steps": 25465, "total_steps": 61300, "loss": 0.3229, "lr": 3.6318674831806e-05, "epoch": 4.154159869494291, "percentage": 41.54, "elapsed_time": "3:28:06", "remaining_time": "4:52:51", "throughput": 4403.2, "total_tokens": 54981936} {"current_steps": 25470, "total_steps": 61300, "loss": 0.3482, "lr": 3.6312327702311536e-05, "epoch": 4.1549755301794455, "percentage": 41.55, "elapsed_time": "3:28:09", "remaining_time": "4:52:49", "throughput": 4403.28, "total_tokens": 54993552} {"current_steps": 25475, "total_steps": 61300, "loss": 0.366, "lr": 3.630597965578238e-05, "epoch": 4.1557911908646, "percentage": 41.56, "elapsed_time": "3:28:11", "remaining_time": "4:52:46", "throughput": 4403.36, "total_tokens": 55005200} {"current_steps": 25480, "total_steps": 61300, "loss": 0.3388, "lr": 3.629963069273315e-05, "epoch": 4.156606851549755, "percentage": 41.57, "elapsed_time": "3:28:13", "remaining_time": "4:52:44", "throughput": 4403.44, "total_tokens": 55016464} {"current_steps": 25485, "total_steps": 61300, "loss": 0.3085, "lr": 3.6293280813678523e-05, "epoch": 4.15742251223491, "percentage": 41.57, "elapsed_time": "3:28:16", "remaining_time": "4:52:41", "throughput": 4403.5, "total_tokens": 55026576} {"current_steps": 25490, "total_steps": 61300, "loss": 0.2892, "lr": 3.628693001913325e-05, "epoch": 4.158238172920065, "percentage": 41.58, "elapsed_time": "3:28:18", "remaining_time": "4:52:38", "throughput": 4403.58, "total_tokens": 55037904} {"current_steps": 25495, "total_steps": 61300, "loss": 0.3748, "lr": 3.6280578309612165e-05, "epoch": 4.1590538336052205, "percentage": 41.59, "elapsed_time": "3:28:20", "remaining_time": "4:52:35", "throughput": 4403.64, "total_tokens": 55047408} {"current_steps": 25500, "total_steps": 61300, "loss": 0.3533, "lr": 3.6274225685630156e-05, "epoch": 4.159869494290375, "percentage": 41.6, "elapsed_time": "3:28:22", "remaining_time": "4:52:32", "throughput": 4403.71, "total_tokens": 55058064} {"current_steps": 25505, "total_steps": 61300, "loss": 0.332, "lr": 3.626787214770221e-05, "epoch": 4.16068515497553, "percentage": 41.61, "elapsed_time": "3:28:24", "remaining_time": "4:52:30", "throughput": 4403.78, "total_tokens": 55069008} {"current_steps": 25510, "total_steps": 61300, "loss": 0.342, "lr": 3.626151769634338e-05, "epoch": 4.161500815660685, "percentage": 41.62, "elapsed_time": "3:28:27", "remaining_time": "4:52:27", "throughput": 4403.85, "total_tokens": 55079792} {"current_steps": 25515, "total_steps": 61300, "loss": 0.3587, "lr": 3.6255162332068785e-05, "epoch": 4.16231647634584, "percentage": 41.62, "elapsed_time": "3:28:29", "remaining_time": "4:52:24", "throughput": 4403.93, "total_tokens": 55090864} {"current_steps": 25520, "total_steps": 61300, "loss": 0.3668, "lr": 3.624880605539362e-05, "epoch": 4.1631321370309955, "percentage": 41.63, "elapsed_time": "3:28:31", "remaining_time": "4:52:21", "throughput": 4404.02, "total_tokens": 55101904} {"current_steps": 25525, "total_steps": 61300, "loss": 0.3348, "lr": 3.6242448866833164e-05, "epoch": 4.16394779771615, "percentage": 41.64, "elapsed_time": "3:28:33", "remaining_time": "4:52:19", "throughput": 4404.09, "total_tokens": 55112656} {"current_steps": 25530, "total_steps": 61300, "loss": 0.3463, "lr": 3.623609076690275e-05, "epoch": 4.164763458401305, "percentage": 41.65, "elapsed_time": "3:28:36", "remaining_time": "4:52:16", "throughput": 4404.16, "total_tokens": 55123024} {"current_steps": 25535, "total_steps": 61300, "loss": 0.321, "lr": 3.622973175611781e-05, "epoch": 4.16557911908646, "percentage": 41.66, "elapsed_time": "3:28:38", "remaining_time": "4:52:13", "throughput": 4404.22, "total_tokens": 55133136} {"current_steps": 25540, "total_steps": 61300, "loss": 0.3575, "lr": 3.622337183499384e-05, "epoch": 4.166394779771615, "percentage": 41.66, "elapsed_time": "3:28:40", "remaining_time": "4:52:10", "throughput": 4404.28, "total_tokens": 55142864} {"current_steps": 25545, "total_steps": 61300, "loss": 0.3143, "lr": 3.6217011004046404e-05, "epoch": 4.16721044045677, "percentage": 41.67, "elapsed_time": "3:28:42", "remaining_time": "4:52:07", "throughput": 4404.34, "total_tokens": 55152848} {"current_steps": 25550, "total_steps": 61300, "loss": 0.3235, "lr": 3.621064926379114e-05, "epoch": 4.168026101141925, "percentage": 41.68, "elapsed_time": "3:28:44", "remaining_time": "4:52:04", "throughput": 4404.4, "total_tokens": 55162032} {"current_steps": 25555, "total_steps": 61300, "loss": 0.3472, "lr": 3.620428661474377e-05, "epoch": 4.16884176182708, "percentage": 41.69, "elapsed_time": "3:28:46", "remaining_time": "4:52:01", "throughput": 4404.49, "total_tokens": 55173616} {"current_steps": 25560, "total_steps": 61300, "loss": 0.3366, "lr": 3.619792305742006e-05, "epoch": 4.169657422512235, "percentage": 41.7, "elapsed_time": "3:28:49", "remaining_time": "4:51:59", "throughput": 4404.58, "total_tokens": 55185328} {"current_steps": 25565, "total_steps": 61300, "loss": 0.3658, "lr": 3.619155859233589e-05, "epoch": 4.17047308319739, "percentage": 41.7, "elapsed_time": "3:28:51", "remaining_time": "4:51:56", "throughput": 4404.68, "total_tokens": 55197072} {"current_steps": 25570, "total_steps": 61300, "loss": 0.3508, "lr": 3.6185193220007214e-05, "epoch": 4.171288743882545, "percentage": 41.71, "elapsed_time": "3:28:53", "remaining_time": "4:51:53", "throughput": 4404.74, "total_tokens": 55205936} {"current_steps": 25575, "total_steps": 61300, "loss": 0.3203, "lr": 3.617882694095001e-05, "epoch": 4.1721044045677, "percentage": 41.72, "elapsed_time": "3:28:55", "remaining_time": "4:51:50", "throughput": 4404.82, "total_tokens": 55216560} {"current_steps": 25580, "total_steps": 61300, "loss": 0.3305, "lr": 3.617245975568038e-05, "epoch": 4.172920065252855, "percentage": 41.73, "elapsed_time": "3:28:57", "remaining_time": "4:51:47", "throughput": 4404.88, "total_tokens": 55227504} {"current_steps": 25585, "total_steps": 61300, "loss": 0.3686, "lr": 3.616609166471447e-05, "epoch": 4.17373572593801, "percentage": 41.74, "elapsed_time": "3:28:59", "remaining_time": "4:51:44", "throughput": 4404.96, "total_tokens": 55238032} {"current_steps": 25590, "total_steps": 61300, "loss": 0.3087, "lr": 3.615972266856851e-05, "epoch": 4.174551386623165, "percentage": 41.75, "elapsed_time": "3:29:02", "remaining_time": "4:51:42", "throughput": 4405.02, "total_tokens": 55248080} {"current_steps": 25595, "total_steps": 61300, "loss": 0.341, "lr": 3.6153352767758816e-05, "epoch": 4.1753670473083195, "percentage": 41.75, "elapsed_time": "3:29:04", "remaining_time": "4:51:39", "throughput": 4405.1, "total_tokens": 55259760} {"current_steps": 25600, "total_steps": 61300, "loss": 0.3941, "lr": 3.6146981962801744e-05, "epoch": 4.176182707993474, "percentage": 41.76, "elapsed_time": "3:29:06", "remaining_time": "4:51:36", "throughput": 4405.17, "total_tokens": 55270128} {"current_steps": 25605, "total_steps": 61300, "loss": 0.2932, "lr": 3.6140610254213756e-05, "epoch": 4.17699836867863, "percentage": 41.77, "elapsed_time": "3:29:08", "remaining_time": "4:51:33", "throughput": 4405.25, "total_tokens": 55280592} {"current_steps": 25610, "total_steps": 61300, "loss": 0.3192, "lr": 3.613423764251138e-05, "epoch": 4.177814029363785, "percentage": 41.78, "elapsed_time": "3:29:11", "remaining_time": "4:51:31", "throughput": 4405.32, "total_tokens": 55291344} {"current_steps": 25615, "total_steps": 61300, "loss": 0.379, "lr": 3.61278641282112e-05, "epoch": 4.17862969004894, "percentage": 41.79, "elapsed_time": "3:29:13", "remaining_time": "4:51:28", "throughput": 4405.39, "total_tokens": 55301360} {"current_steps": 25620, "total_steps": 61300, "loss": 0.2682, "lr": 3.612148971182989e-05, "epoch": 4.1794453507340945, "percentage": 41.79, "elapsed_time": "3:29:15", "remaining_time": "4:51:25", "throughput": 4405.47, "total_tokens": 55311696} {"current_steps": 25625, "total_steps": 61300, "loss": 0.3633, "lr": 3.6115114393884206e-05, "epoch": 4.180261011419249, "percentage": 41.8, "elapsed_time": "3:29:17", "remaining_time": "4:51:22", "throughput": 4405.55, "total_tokens": 55322704} {"current_steps": 25630, "total_steps": 61300, "loss": 0.3479, "lr": 3.6108738174890944e-05, "epoch": 4.181076672104404, "percentage": 41.81, "elapsed_time": "3:29:19", "remaining_time": "4:51:20", "throughput": 4405.65, "total_tokens": 55334704} {"current_steps": 25635, "total_steps": 61300, "loss": 0.3291, "lr": 3.6102361055367e-05, "epoch": 4.18189233278956, "percentage": 41.82, "elapsed_time": "3:29:22", "remaining_time": "4:51:17", "throughput": 4405.72, "total_tokens": 55344912} {"current_steps": 25640, "total_steps": 61300, "loss": 0.3225, "lr": 3.609598303582934e-05, "epoch": 4.182707993474715, "percentage": 41.83, "elapsed_time": "3:29:24", "remaining_time": "4:51:14", "throughput": 4405.78, "total_tokens": 55354832} {"current_steps": 25645, "total_steps": 61300, "loss": 0.42, "lr": 3.608960411679499e-05, "epoch": 4.1835236541598695, "percentage": 41.84, "elapsed_time": "3:29:26", "remaining_time": "4:51:11", "throughput": 4405.87, "total_tokens": 55365776} {"current_steps": 25650, "total_steps": 61300, "loss": 0.3523, "lr": 3.608322429878107e-05, "epoch": 4.184339314845024, "percentage": 41.84, "elapsed_time": "3:29:28", "remaining_time": "4:51:08", "throughput": 4405.94, "total_tokens": 55376208} {"current_steps": 25655, "total_steps": 61300, "loss": 0.3316, "lr": 3.6076843582304744e-05, "epoch": 4.185154975530179, "percentage": 41.85, "elapsed_time": "3:29:30", "remaining_time": "4:51:05", "throughput": 4406.02, "total_tokens": 55386512} {"current_steps": 25660, "total_steps": 61300, "loss": 0.3246, "lr": 3.607046196788328e-05, "epoch": 4.185970636215335, "percentage": 41.86, "elapsed_time": "3:29:32", "remaining_time": "4:51:02", "throughput": 4406.08, "total_tokens": 55397168} {"current_steps": 25665, "total_steps": 61300, "loss": 0.3133, "lr": 3.6064079456033996e-05, "epoch": 4.18678629690049, "percentage": 41.87, "elapsed_time": "3:29:35", "remaining_time": "4:51:00", "throughput": 4406.17, "total_tokens": 55408912} {"current_steps": 25670, "total_steps": 61300, "loss": 0.3366, "lr": 3.6057696047274285e-05, "epoch": 4.1876019575856445, "percentage": 41.88, "elapsed_time": "3:29:37", "remaining_time": "4:50:57", "throughput": 4406.24, "total_tokens": 55418672} {"current_steps": 25675, "total_steps": 61300, "loss": 0.3514, "lr": 3.605131174212164e-05, "epoch": 4.188417618270799, "percentage": 41.88, "elapsed_time": "3:29:39", "remaining_time": "4:50:54", "throughput": 4406.32, "total_tokens": 55430768} {"current_steps": 25680, "total_steps": 61300, "loss": 0.3903, "lr": 3.604492654109357e-05, "epoch": 4.189233278955954, "percentage": 41.89, "elapsed_time": "3:29:41", "remaining_time": "4:50:52", "throughput": 4406.4, "total_tokens": 55441232} {"current_steps": 25685, "total_steps": 61300, "loss": 0.3222, "lr": 3.6038540444707734e-05, "epoch": 4.190048939641109, "percentage": 41.9, "elapsed_time": "3:29:44", "remaining_time": "4:50:49", "throughput": 4406.47, "total_tokens": 55453040} {"current_steps": 25690, "total_steps": 61300, "loss": 0.3377, "lr": 3.603215345348179e-05, "epoch": 4.190864600326265, "percentage": 41.91, "elapsed_time": "3:29:46", "remaining_time": "4:50:46", "throughput": 4406.53, "total_tokens": 55462768} {"current_steps": 25695, "total_steps": 61300, "loss": 0.3364, "lr": 3.602576556793352e-05, "epoch": 4.191680261011419, "percentage": 41.92, "elapsed_time": "3:29:48", "remaining_time": "4:50:44", "throughput": 4406.61, "total_tokens": 55474416} {"current_steps": 25700, "total_steps": 61300, "loss": 0.3395, "lr": 3.601937678858074e-05, "epoch": 4.192495921696574, "percentage": 41.92, "elapsed_time": "3:29:50", "remaining_time": "4:50:41", "throughput": 4406.67, "total_tokens": 55484272} {"current_steps": 25705, "total_steps": 61300, "loss": 0.3014, "lr": 3.601298711594137e-05, "epoch": 4.193311582381729, "percentage": 41.93, "elapsed_time": "3:29:53", "remaining_time": "4:50:38", "throughput": 4406.75, "total_tokens": 55496336} {"current_steps": 25710, "total_steps": 61300, "loss": 0.3153, "lr": 3.6006596550533385e-05, "epoch": 4.194127243066884, "percentage": 41.94, "elapsed_time": "3:29:56", "remaining_time": "4:50:36", "throughput": 4406.85, "total_tokens": 55508656} {"current_steps": 25715, "total_steps": 61300, "loss": 0.3888, "lr": 3.600020509287483e-05, "epoch": 4.19494290375204, "percentage": 41.95, "elapsed_time": "3:29:58", "remaining_time": "4:50:33", "throughput": 4406.91, "total_tokens": 55519664} {"current_steps": 25720, "total_steps": 61300, "loss": 0.3367, "lr": 3.599381274348385e-05, "epoch": 4.195758564437194, "percentage": 41.96, "elapsed_time": "3:30:00", "remaining_time": "4:50:30", "throughput": 4406.97, "total_tokens": 55529744} {"current_steps": 25725, "total_steps": 61300, "loss": 0.3153, "lr": 3.598741950287861e-05, "epoch": 4.196574225122349, "percentage": 41.97, "elapsed_time": "3:30:02", "remaining_time": "4:50:28", "throughput": 4407.04, "total_tokens": 55540400} {"current_steps": 25730, "total_steps": 61300, "loss": 0.2829, "lr": 3.5981025371577404e-05, "epoch": 4.197389885807504, "percentage": 41.97, "elapsed_time": "3:30:04", "remaining_time": "4:50:25", "throughput": 4407.11, "total_tokens": 55551312} {"current_steps": 25735, "total_steps": 61300, "loss": 0.3535, "lr": 3.5974630350098566e-05, "epoch": 4.198205546492659, "percentage": 41.98, "elapsed_time": "3:30:07", "remaining_time": "4:50:22", "throughput": 4407.19, "total_tokens": 55562448} {"current_steps": 25740, "total_steps": 61300, "loss": 0.2833, "lr": 3.5968234438960505e-05, "epoch": 4.199021207177814, "percentage": 41.99, "elapsed_time": "3:30:09", "remaining_time": "4:50:19", "throughput": 4407.26, "total_tokens": 55572848} {"current_steps": 25745, "total_steps": 61300, "loss": 0.3381, "lr": 3.5961837638681714e-05, "epoch": 4.199836867862969, "percentage": 42.0, "elapsed_time": "3:30:11", "remaining_time": "4:50:16", "throughput": 4407.34, "total_tokens": 55582800} {"current_steps": 25750, "total_steps": 61300, "loss": 0.3163, "lr": 3.595543994978073e-05, "epoch": 4.200652528548124, "percentage": 42.01, "elapsed_time": "3:30:13", "remaining_time": "4:50:14", "throughput": 4407.42, "total_tokens": 55594096} {"current_steps": 25755, "total_steps": 61300, "loss": 0.3849, "lr": 3.594904137277621e-05, "epoch": 4.201468189233279, "percentage": 42.01, "elapsed_time": "3:30:16", "remaining_time": "4:50:11", "throughput": 4407.48, "total_tokens": 55605456} {"current_steps": 25760, "total_steps": 61300, "loss": 0.3249, "lr": 3.594264190818683e-05, "epoch": 4.202283849918434, "percentage": 42.02, "elapsed_time": "3:30:18", "remaining_time": "4:50:09", "throughput": 4407.56, "total_tokens": 55617072} {"current_steps": 25765, "total_steps": 61300, "loss": 0.3515, "lr": 3.593624155653138e-05, "epoch": 4.203099510603589, "percentage": 42.03, "elapsed_time": "3:30:20", "remaining_time": "4:50:06", "throughput": 4407.64, "total_tokens": 55628176} {"current_steps": 25770, "total_steps": 61300, "loss": 0.3626, "lr": 3.592984031832871e-05, "epoch": 4.2039151712887435, "percentage": 42.04, "elapsed_time": "3:30:22", "remaining_time": "4:50:03", "throughput": 4407.69, "total_tokens": 55637744} {"current_steps": 25775, "total_steps": 61300, "loss": 0.3194, "lr": 3.5923438194097715e-05, "epoch": 4.204730831973899, "percentage": 42.05, "elapsed_time": "3:30:25", "remaining_time": "4:50:01", "throughput": 4407.77, "total_tokens": 55649104} {"current_steps": 25780, "total_steps": 61300, "loss": 0.3484, "lr": 3.591703518435739e-05, "epoch": 4.205546492659054, "percentage": 42.06, "elapsed_time": "3:30:27", "remaining_time": "4:49:58", "throughput": 4407.85, "total_tokens": 55660272} {"current_steps": 25785, "total_steps": 61300, "loss": 0.3651, "lr": 3.591063128962681e-05, "epoch": 4.206362153344209, "percentage": 42.06, "elapsed_time": "3:30:29", "remaining_time": "4:49:55", "throughput": 4407.92, "total_tokens": 55670864} {"current_steps": 25790, "total_steps": 61300, "loss": 0.3241, "lr": 3.5904226510425095e-05, "epoch": 4.207177814029364, "percentage": 42.07, "elapsed_time": "3:30:31", "remaining_time": "4:49:52", "throughput": 4408.0, "total_tokens": 55681456} {"current_steps": 25795, "total_steps": 61300, "loss": 0.3719, "lr": 3.5897820847271446e-05, "epoch": 4.2079934747145185, "percentage": 42.08, "elapsed_time": "3:30:34", "remaining_time": "4:49:50", "throughput": 4408.08, "total_tokens": 55692464} {"current_steps": 25800, "total_steps": 61300, "loss": 0.3169, "lr": 3.5891414300685155e-05, "epoch": 4.208809135399674, "percentage": 42.09, "elapsed_time": "3:30:36", "remaining_time": "4:49:47", "throughput": 4408.15, "total_tokens": 55702704} {"current_steps": 25805, "total_steps": 61300, "loss": 0.3371, "lr": 3.588500687118555e-05, "epoch": 4.209624796084829, "percentage": 42.1, "elapsed_time": "3:30:38", "remaining_time": "4:49:44", "throughput": 4408.23, "total_tokens": 55713040} {"current_steps": 25810, "total_steps": 61300, "loss": 0.3397, "lr": 3.587859855929207e-05, "epoch": 4.210440456769984, "percentage": 42.1, "elapsed_time": "3:30:40", "remaining_time": "4:49:41", "throughput": 4408.31, "total_tokens": 55723920} {"current_steps": 25815, "total_steps": 61300, "loss": 0.3752, "lr": 3.5872189365524175e-05, "epoch": 4.211256117455139, "percentage": 42.11, "elapsed_time": "3:30:43", "remaining_time": "4:49:38", "throughput": 4408.4, "total_tokens": 55735440} {"current_steps": 25820, "total_steps": 61300, "loss": 0.3318, "lr": 3.586577929040146e-05, "epoch": 4.212071778140293, "percentage": 42.12, "elapsed_time": "3:30:45", "remaining_time": "4:49:36", "throughput": 4408.46, "total_tokens": 55745680} {"current_steps": 25825, "total_steps": 61300, "loss": 0.3442, "lr": 3.5859368334443536e-05, "epoch": 4.212887438825448, "percentage": 42.13, "elapsed_time": "3:30:47", "remaining_time": "4:49:33", "throughput": 4408.55, "total_tokens": 55757680} {"current_steps": 25830, "total_steps": 61300, "loss": 0.3111, "lr": 3.585295649817011e-05, "epoch": 4.213703099510604, "percentage": 42.14, "elapsed_time": "3:30:49", "remaining_time": "4:49:30", "throughput": 4408.62, "total_tokens": 55767536} {"current_steps": 25835, "total_steps": 61300, "loss": 0.3797, "lr": 3.5846543782100974e-05, "epoch": 4.214518760195759, "percentage": 42.15, "elapsed_time": "3:30:51", "remaining_time": "4:49:27", "throughput": 4408.7, "total_tokens": 55778032} {"current_steps": 25840, "total_steps": 61300, "loss": 0.3686, "lr": 3.584013018675596e-05, "epoch": 4.215334420880914, "percentage": 42.15, "elapsed_time": "3:30:54", "remaining_time": "4:49:25", "throughput": 4408.78, "total_tokens": 55790000} {"current_steps": 25845, "total_steps": 61300, "loss": 0.3456, "lr": 3.583371571265498e-05, "epoch": 4.216150081566068, "percentage": 42.16, "elapsed_time": "3:30:56", "remaining_time": "4:49:22", "throughput": 4408.84, "total_tokens": 55800688} {"current_steps": 25850, "total_steps": 61300, "loss": 0.3257, "lr": 3.582730036031805e-05, "epoch": 4.216965742251223, "percentage": 42.17, "elapsed_time": "3:30:58", "remaining_time": "4:49:20", "throughput": 4408.93, "total_tokens": 55812208} {"current_steps": 25855, "total_steps": 61300, "loss": 0.3358, "lr": 3.582088413026521e-05, "epoch": 4.217781402936378, "percentage": 42.18, "elapsed_time": "3:31:01", "remaining_time": "4:49:17", "throughput": 4408.99, "total_tokens": 55823120} {"current_steps": 25860, "total_steps": 61300, "loss": 0.3142, "lr": 3.581446702301659e-05, "epoch": 4.218597063621534, "percentage": 42.19, "elapsed_time": "3:31:03", "remaining_time": "4:49:14", "throughput": 4409.07, "total_tokens": 55834416} {"current_steps": 25865, "total_steps": 61300, "loss": 0.3537, "lr": 3.5808049039092414e-05, "epoch": 4.219412724306689, "percentage": 42.19, "elapsed_time": "3:31:06", "remaining_time": "4:49:12", "throughput": 4409.15, "total_tokens": 55846480} {"current_steps": 25870, "total_steps": 61300, "loss": 0.3469, "lr": 3.580163017901295e-05, "epoch": 4.220228384991843, "percentage": 42.2, "elapsed_time": "3:31:08", "remaining_time": "4:49:09", "throughput": 4409.22, "total_tokens": 55857200} {"current_steps": 25875, "total_steps": 61300, "loss": 0.3356, "lr": 3.579521044329852e-05, "epoch": 4.221044045676998, "percentage": 42.21, "elapsed_time": "3:31:10", "remaining_time": "4:49:07", "throughput": 4409.3, "total_tokens": 55868976} {"current_steps": 25880, "total_steps": 61300, "loss": 0.3377, "lr": 3.578878983246956e-05, "epoch": 4.221859706362153, "percentage": 42.22, "elapsed_time": "3:31:13", "remaining_time": "4:49:04", "throughput": 4409.38, "total_tokens": 55881360} {"current_steps": 25885, "total_steps": 61300, "loss": 0.3688, "lr": 3.578236834704656e-05, "epoch": 4.222675367047309, "percentage": 42.23, "elapsed_time": "3:31:15", "remaining_time": "4:49:02", "throughput": 4409.45, "total_tokens": 55892208} {"current_steps": 25890, "total_steps": 61300, "loss": 0.3366, "lr": 3.577594598755006e-05, "epoch": 4.2234910277324635, "percentage": 42.23, "elapsed_time": "3:31:17", "remaining_time": "4:48:59", "throughput": 4409.51, "total_tokens": 55901936} {"current_steps": 25895, "total_steps": 61300, "loss": 0.3098, "lr": 3.5769522754500714e-05, "epoch": 4.224306688417618, "percentage": 42.24, "elapsed_time": "3:31:19", "remaining_time": "4:48:56", "throughput": 4409.58, "total_tokens": 55912784} {"current_steps": 25900, "total_steps": 61300, "loss": 0.364, "lr": 3.5763098648419216e-05, "epoch": 4.225122349102773, "percentage": 42.25, "elapsed_time": "3:31:22", "remaining_time": "4:48:54", "throughput": 4409.65, "total_tokens": 55924432} {"current_steps": 25905, "total_steps": 61300, "loss": 0.3253, "lr": 3.575667366982631e-05, "epoch": 4.225938009787928, "percentage": 42.26, "elapsed_time": "3:31:24", "remaining_time": "4:48:51", "throughput": 4409.72, "total_tokens": 55935216} {"current_steps": 25910, "total_steps": 61300, "loss": 0.3143, "lr": 3.575024781924288e-05, "epoch": 4.226753670473083, "percentage": 42.27, "elapsed_time": "3:31:26", "remaining_time": "4:48:48", "throughput": 4409.78, "total_tokens": 55945680} {"current_steps": 25915, "total_steps": 61300, "loss": 0.3855, "lr": 3.574382109718979e-05, "epoch": 4.2275693311582385, "percentage": 42.28, "elapsed_time": "3:31:28", "remaining_time": "4:48:45", "throughput": 4409.86, "total_tokens": 55956496} {"current_steps": 25920, "total_steps": 61300, "loss": 0.3469, "lr": 3.573739350418806e-05, "epoch": 4.228384991843393, "percentage": 42.28, "elapsed_time": "3:31:31", "remaining_time": "4:48:43", "throughput": 4409.92, "total_tokens": 55967280} {"current_steps": 25925, "total_steps": 61300, "loss": 0.3901, "lr": 3.573096504075874e-05, "epoch": 4.229200652528548, "percentage": 42.29, "elapsed_time": "3:31:33", "remaining_time": "4:48:40", "throughput": 4410.0, "total_tokens": 55978160} {"current_steps": 25930, "total_steps": 61300, "loss": 0.3382, "lr": 3.572453570742294e-05, "epoch": 4.230016313213703, "percentage": 42.3, "elapsed_time": "3:31:35", "remaining_time": "4:48:37", "throughput": 4410.08, "total_tokens": 55989808} {"current_steps": 25935, "total_steps": 61300, "loss": 0.3206, "lr": 3.571810550470186e-05, "epoch": 4.230831973898858, "percentage": 42.31, "elapsed_time": "3:31:38", "remaining_time": "4:48:35", "throughput": 4410.16, "total_tokens": 56000944} {"current_steps": 25940, "total_steps": 61300, "loss": 0.3467, "lr": 3.571167443311676e-05, "epoch": 4.231647634584013, "percentage": 42.32, "elapsed_time": "3:31:40", "remaining_time": "4:48:32", "throughput": 4410.22, "total_tokens": 56011408} {"current_steps": 25945, "total_steps": 61300, "loss": 0.3416, "lr": 3.5705242493188986e-05, "epoch": 4.232463295269168, "percentage": 42.32, "elapsed_time": "3:31:42", "remaining_time": "4:48:29", "throughput": 4410.29, "total_tokens": 56020944} {"current_steps": 25950, "total_steps": 61300, "loss": 0.3418, "lr": 3.569880968543994e-05, "epoch": 4.233278955954323, "percentage": 42.33, "elapsed_time": "3:31:44", "remaining_time": "4:48:26", "throughput": 4410.36, "total_tokens": 56031792} {"current_steps": 25955, "total_steps": 61300, "loss": 0.3142, "lr": 3.569237601039109e-05, "epoch": 4.234094616639478, "percentage": 42.34, "elapsed_time": "3:31:46", "remaining_time": "4:48:23", "throughput": 4410.43, "total_tokens": 56041936} {"current_steps": 25960, "total_steps": 61300, "loss": 0.3234, "lr": 3.5685941468563985e-05, "epoch": 4.234910277324633, "percentage": 42.35, "elapsed_time": "3:31:48", "remaining_time": "4:48:20", "throughput": 4410.5, "total_tokens": 56052272} {"current_steps": 25965, "total_steps": 61300, "loss": 0.3401, "lr": 3.567950606048025e-05, "epoch": 4.235725938009788, "percentage": 42.36, "elapsed_time": "3:31:50", "remaining_time": "4:48:17", "throughput": 4410.57, "total_tokens": 56061808} {"current_steps": 25970, "total_steps": 61300, "loss": 0.3325, "lr": 3.5673069786661566e-05, "epoch": 4.236541598694943, "percentage": 42.37, "elapsed_time": "3:31:52", "remaining_time": "4:48:14", "throughput": 4410.63, "total_tokens": 56071536} {"current_steps": 25975, "total_steps": 61300, "loss": 0.3034, "lr": 3.566663264762969e-05, "epoch": 4.237357259380098, "percentage": 42.37, "elapsed_time": "3:31:55", "remaining_time": "4:48:12", "throughput": 4410.72, "total_tokens": 56083568} {"current_steps": 25980, "total_steps": 61300, "loss": 0.3699, "lr": 3.5660194643906455e-05, "epoch": 4.238172920065253, "percentage": 42.38, "elapsed_time": "3:31:57", "remaining_time": "4:48:09", "throughput": 4410.79, "total_tokens": 56094000} {"current_steps": 25985, "total_steps": 61300, "loss": 0.3348, "lr": 3.5653755776013745e-05, "epoch": 4.238988580750408, "percentage": 42.39, "elapsed_time": "3:31:59", "remaining_time": "4:48:06", "throughput": 4410.86, "total_tokens": 56103952} {"current_steps": 25990, "total_steps": 61300, "loss": 0.3518, "lr": 3.5647316044473537e-05, "epoch": 4.239804241435563, "percentage": 42.4, "elapsed_time": "3:32:01", "remaining_time": "4:48:03", "throughput": 4410.92, "total_tokens": 56114224} {"current_steps": 25995, "total_steps": 61300, "loss": 0.3263, "lr": 3.564087544980786e-05, "epoch": 4.240619902120717, "percentage": 42.41, "elapsed_time": "3:32:03", "remaining_time": "4:48:00", "throughput": 4410.99, "total_tokens": 56124464} {"current_steps": 26000, "total_steps": 61300, "loss": 0.321, "lr": 3.563443399253883e-05, "epoch": 4.241435562805873, "percentage": 42.41, "elapsed_time": "3:32:06", "remaining_time": "4:47:58", "throughput": 4411.06, "total_tokens": 56135280} {"current_steps": 26005, "total_steps": 61300, "loss": 0.314, "lr": 3.5627991673188624e-05, "epoch": 4.242251223491028, "percentage": 42.42, "elapsed_time": "3:32:08", "remaining_time": "4:47:55", "throughput": 4411.12, "total_tokens": 56144976} {"current_steps": 26010, "total_steps": 61300, "loss": 0.3391, "lr": 3.562154849227949e-05, "epoch": 4.243066884176183, "percentage": 42.43, "elapsed_time": "3:32:10", "remaining_time": "4:47:52", "throughput": 4411.21, "total_tokens": 56156688} {"current_steps": 26015, "total_steps": 61300, "loss": 0.3513, "lr": 3.561510445033375e-05, "epoch": 4.2438825448613375, "percentage": 42.44, "elapsed_time": "3:32:12", "remaining_time": "4:47:49", "throughput": 4411.27, "total_tokens": 56167856} {"current_steps": 26020, "total_steps": 61300, "loss": 0.3355, "lr": 3.560865954787377e-05, "epoch": 4.244698205546492, "percentage": 42.45, "elapsed_time": "3:32:15", "remaining_time": "4:47:47", "throughput": 4411.35, "total_tokens": 56178928} {"current_steps": 26025, "total_steps": 61300, "loss": 0.3408, "lr": 3.5602213785422025e-05, "epoch": 4.245513866231648, "percentage": 42.46, "elapsed_time": "3:32:17", "remaining_time": "4:47:44", "throughput": 4411.43, "total_tokens": 56189584} {"current_steps": 26030, "total_steps": 61300, "loss": 0.3218, "lr": 3.5595767163501034e-05, "epoch": 4.246329526916803, "percentage": 42.46, "elapsed_time": "3:32:19", "remaining_time": "4:47:41", "throughput": 4411.5, "total_tokens": 56200080} {"current_steps": 26035, "total_steps": 61300, "loss": 0.3397, "lr": 3.5589319682633393e-05, "epoch": 4.247145187601958, "percentage": 42.47, "elapsed_time": "3:32:21", "remaining_time": "4:47:38", "throughput": 4411.56, "total_tokens": 56210288} {"current_steps": 26040, "total_steps": 61300, "loss": 0.3224, "lr": 3.558287134334177e-05, "epoch": 4.2479608482871125, "percentage": 42.48, "elapsed_time": "3:32:23", "remaining_time": "4:47:36", "throughput": 4411.63, "total_tokens": 56220976} {"current_steps": 26045, "total_steps": 61300, "loss": 0.3072, "lr": 3.55764221461489e-05, "epoch": 4.248776508972267, "percentage": 42.49, "elapsed_time": "3:32:26", "remaining_time": "4:47:33", "throughput": 4411.71, "total_tokens": 56232176} {"current_steps": 26050, "total_steps": 61300, "loss": 0.3221, "lr": 3.556997209157759e-05, "epoch": 4.249592169657422, "percentage": 42.5, "elapsed_time": "3:32:28", "remaining_time": "4:47:31", "throughput": 4411.79, "total_tokens": 56244400} {"current_steps": 26055, "total_steps": 61300, "loss": 0.3162, "lr": 3.5563521180150704e-05, "epoch": 4.250407830342578, "percentage": 42.5, "elapsed_time": "3:32:31", "remaining_time": "4:47:28", "throughput": 4411.87, "total_tokens": 56255952} {"current_steps": 26060, "total_steps": 61300, "loss": 0.3673, "lr": 3.55570694123912e-05, "epoch": 4.251223491027733, "percentage": 42.51, "elapsed_time": "3:32:33", "remaining_time": "4:47:26", "throughput": 4411.96, "total_tokens": 56267760} {"current_steps": 26065, "total_steps": 61300, "loss": 0.3287, "lr": 3.5550616788822074e-05, "epoch": 4.2520391517128875, "percentage": 42.52, "elapsed_time": "3:32:35", "remaining_time": "4:47:23", "throughput": 4412.04, "total_tokens": 56278800} {"current_steps": 26070, "total_steps": 61300, "loss": 0.3653, "lr": 3.5544163309966425e-05, "epoch": 4.252854812398042, "percentage": 42.53, "elapsed_time": "3:32:38", "remaining_time": "4:47:20", "throughput": 4412.1, "total_tokens": 56289552} {"current_steps": 26075, "total_steps": 61300, "loss": 0.3524, "lr": 3.5537708976347386e-05, "epoch": 4.253670473083197, "percentage": 42.54, "elapsed_time": "3:32:40", "remaining_time": "4:47:18", "throughput": 4412.17, "total_tokens": 56301808} {"current_steps": 26080, "total_steps": 61300, "loss": 0.3404, "lr": 3.55312537884882e-05, "epoch": 4.254486133768353, "percentage": 42.54, "elapsed_time": "3:32:42", "remaining_time": "4:47:15", "throughput": 4412.23, "total_tokens": 56311536} {"current_steps": 26085, "total_steps": 61300, "loss": 0.3434, "lr": 3.552479774691215e-05, "epoch": 4.255301794453508, "percentage": 42.55, "elapsed_time": "3:32:45", "remaining_time": "4:47:12", "throughput": 4412.31, "total_tokens": 56323344} {"current_steps": 26090, "total_steps": 61300, "loss": 0.3429, "lr": 3.5518340852142587e-05, "epoch": 4.2561174551386625, "percentage": 42.56, "elapsed_time": "3:32:47", "remaining_time": "4:47:10", "throughput": 4412.39, "total_tokens": 56333904} {"current_steps": 26095, "total_steps": 61300, "loss": 0.3408, "lr": 3.5511883104702943e-05, "epoch": 4.256933115823817, "percentage": 42.57, "elapsed_time": "3:32:49", "remaining_time": "4:47:07", "throughput": 4412.44, "total_tokens": 56343312} {"current_steps": 26100, "total_steps": 61300, "loss": 0.319, "lr": 3.5505424505116714e-05, "epoch": 4.257748776508972, "percentage": 42.58, "elapsed_time": "3:32:51", "remaining_time": "4:47:04", "throughput": 4412.5, "total_tokens": 56354960} {"current_steps": 26105, "total_steps": 61300, "loss": 0.3739, "lr": 3.549896505390748e-05, "epoch": 4.258564437194127, "percentage": 42.59, "elapsed_time": "3:32:53", "remaining_time": "4:47:01", "throughput": 4412.58, "total_tokens": 56366032} {"current_steps": 26110, "total_steps": 61300, "loss": 0.342, "lr": 3.549250475159887e-05, "epoch": 4.259380097879283, "percentage": 42.59, "elapsed_time": "3:32:56", "remaining_time": "4:46:59", "throughput": 4412.65, "total_tokens": 56376496} {"current_steps": 26115, "total_steps": 61300, "loss": 0.3077, "lr": 3.5486043598714576e-05, "epoch": 4.260195758564437, "percentage": 42.6, "elapsed_time": "3:32:58", "remaining_time": "4:46:56", "throughput": 4412.71, "total_tokens": 56387408} {"current_steps": 26120, "total_steps": 61300, "loss": 0.3098, "lr": 3.547958159577839e-05, "epoch": 4.261011419249592, "percentage": 42.61, "elapsed_time": "3:33:00", "remaining_time": "4:46:53", "throughput": 4412.77, "total_tokens": 56397328} {"current_steps": 26125, "total_steps": 61300, "loss": 0.3508, "lr": 3.547311874331414e-05, "epoch": 4.261827079934747, "percentage": 42.62, "elapsed_time": "3:33:02", "remaining_time": "4:46:50", "throughput": 4412.85, "total_tokens": 56406640} {"current_steps": 26130, "total_steps": 61300, "loss": 0.359, "lr": 3.546665504184575e-05, "epoch": 4.262642740619902, "percentage": 42.63, "elapsed_time": "3:33:04", "remaining_time": "4:46:47", "throughput": 4412.9, "total_tokens": 56416400} {"current_steps": 26135, "total_steps": 61300, "loss": 0.3218, "lr": 3.5460190491897195e-05, "epoch": 4.263458401305057, "percentage": 42.63, "elapsed_time": "3:33:06", "remaining_time": "4:46:44", "throughput": 4412.99, "total_tokens": 56426320} {"current_steps": 26140, "total_steps": 61300, "loss": 0.3119, "lr": 3.5453725093992526e-05, "epoch": 4.264274061990212, "percentage": 42.64, "elapsed_time": "3:33:08", "remaining_time": "4:46:41", "throughput": 4413.05, "total_tokens": 56436400} {"current_steps": 26145, "total_steps": 61300, "loss": 0.4004, "lr": 3.544725884865585e-05, "epoch": 4.265089722675367, "percentage": 42.65, "elapsed_time": "3:33:10", "remaining_time": "4:46:38", "throughput": 4413.1, "total_tokens": 56445712} {"current_steps": 26150, "total_steps": 61300, "loss": 0.3341, "lr": 3.544079175641137e-05, "epoch": 4.265905383360522, "percentage": 42.66, "elapsed_time": "3:33:12", "remaining_time": "4:46:35", "throughput": 4413.18, "total_tokens": 56456720} {"current_steps": 26155, "total_steps": 61300, "loss": 0.3782, "lr": 3.543432381778333e-05, "epoch": 4.266721044045677, "percentage": 42.67, "elapsed_time": "3:33:15", "remaining_time": "4:46:33", "throughput": 4413.24, "total_tokens": 56468464} {"current_steps": 26160, "total_steps": 61300, "loss": 0.3776, "lr": 3.5427855033296056e-05, "epoch": 4.267536704730832, "percentage": 42.68, "elapsed_time": "3:33:17", "remaining_time": "4:46:30", "throughput": 4413.3, "total_tokens": 56478096} {"current_steps": 26165, "total_steps": 61300, "loss": 0.3548, "lr": 3.542138540347395e-05, "epoch": 4.268352365415987, "percentage": 42.68, "elapsed_time": "3:33:19", "remaining_time": "4:46:27", "throughput": 4413.38, "total_tokens": 56489776} {"current_steps": 26170, "total_steps": 61300, "loss": 0.3223, "lr": 3.5414914928841467e-05, "epoch": 4.269168026101142, "percentage": 42.69, "elapsed_time": "3:33:22", "remaining_time": "4:46:25", "throughput": 4413.46, "total_tokens": 56501232} {"current_steps": 26175, "total_steps": 61300, "loss": 0.3794, "lr": 3.540844360992313e-05, "epoch": 4.269983686786297, "percentage": 42.7, "elapsed_time": "3:33:24", "remaining_time": "4:46:22", "throughput": 4413.53, "total_tokens": 56511664} {"current_steps": 26180, "total_steps": 61300, "loss": 0.341, "lr": 3.5401971447243545e-05, "epoch": 4.270799347471452, "percentage": 42.71, "elapsed_time": "3:33:26", "remaining_time": "4:46:19", "throughput": 4413.59, "total_tokens": 56522032} {"current_steps": 26185, "total_steps": 61300, "loss": 0.3, "lr": 3.539549844132737e-05, "epoch": 4.271615008156607, "percentage": 42.72, "elapsed_time": "3:33:28", "remaining_time": "4:46:16", "throughput": 4413.66, "total_tokens": 56533008} {"current_steps": 26190, "total_steps": 61300, "loss": 0.3405, "lr": 3.538902459269935e-05, "epoch": 4.2724306688417615, "percentage": 42.72, "elapsed_time": "3:33:30", "remaining_time": "4:46:14", "throughput": 4413.73, "total_tokens": 56544176} {"current_steps": 26195, "total_steps": 61300, "loss": 0.3453, "lr": 3.538254990188429e-05, "epoch": 4.273246329526917, "percentage": 42.73, "elapsed_time": "3:33:33", "remaining_time": "4:46:11", "throughput": 4413.81, "total_tokens": 56555376} {"current_steps": 26200, "total_steps": 61300, "loss": 0.349, "lr": 3.5376074369407044e-05, "epoch": 4.274061990212072, "percentage": 42.74, "elapsed_time": "3:33:35", "remaining_time": "4:46:08", "throughput": 4413.88, "total_tokens": 56566256} {"current_steps": 26205, "total_steps": 61300, "loss": 0.3669, "lr": 3.536959799579256e-05, "epoch": 4.274877650897227, "percentage": 42.75, "elapsed_time": "3:33:37", "remaining_time": "4:46:06", "throughput": 4413.96, "total_tokens": 56576976} {"current_steps": 26210, "total_steps": 61300, "loss": 0.3503, "lr": 3.5363120781565854e-05, "epoch": 4.275693311582382, "percentage": 42.76, "elapsed_time": "3:33:39", "remaining_time": "4:46:03", "throughput": 4414.04, "total_tokens": 56587504} {"current_steps": 26215, "total_steps": 61300, "loss": 0.3604, "lr": 3.535664272725199e-05, "epoch": 4.2765089722675365, "percentage": 42.77, "elapsed_time": "3:33:42", "remaining_time": "4:46:00", "throughput": 4414.1, "total_tokens": 56598800} {"current_steps": 26220, "total_steps": 61300, "loss": 0.3217, "lr": 3.5350163833376124e-05, "epoch": 4.277324632952691, "percentage": 42.77, "elapsed_time": "3:33:44", "remaining_time": "4:45:58", "throughput": 4414.16, "total_tokens": 56609584} {"current_steps": 26225, "total_steps": 61300, "loss": 0.3302, "lr": 3.534368410046346e-05, "epoch": 4.278140293637847, "percentage": 42.78, "elapsed_time": "3:33:46", "remaining_time": "4:45:55", "throughput": 4414.23, "total_tokens": 56619984} {"current_steps": 26230, "total_steps": 61300, "loss": 0.3394, "lr": 3.5337203529039275e-05, "epoch": 4.278955954323002, "percentage": 42.79, "elapsed_time": "3:33:48", "remaining_time": "4:45:52", "throughput": 4414.29, "total_tokens": 56630128} {"current_steps": 26235, "total_steps": 61300, "loss": 0.3278, "lr": 3.533072211962892e-05, "epoch": 4.279771615008157, "percentage": 42.8, "elapsed_time": "3:33:51", "remaining_time": "4:45:49", "throughput": 4414.36, "total_tokens": 56641264} {"current_steps": 26240, "total_steps": 61300, "loss": 0.3395, "lr": 3.532423987275782e-05, "epoch": 4.280587275693311, "percentage": 42.81, "elapsed_time": "3:33:53", "remaining_time": "4:45:47", "throughput": 4414.44, "total_tokens": 56652688} {"current_steps": 26245, "total_steps": 61300, "loss": 0.348, "lr": 3.531775678895145e-05, "epoch": 4.281402936378466, "percentage": 42.81, "elapsed_time": "3:33:55", "remaining_time": "4:45:44", "throughput": 4414.5, "total_tokens": 56663600} {"current_steps": 26250, "total_steps": 61300, "loss": 0.3242, "lr": 3.531127286873536e-05, "epoch": 4.282218597063622, "percentage": 42.82, "elapsed_time": "3:33:58", "remaining_time": "4:45:41", "throughput": 4414.57, "total_tokens": 56674544} {"current_steps": 26255, "total_steps": 61300, "loss": 0.3381, "lr": 3.530478811263518e-05, "epoch": 4.283034257748777, "percentage": 42.83, "elapsed_time": "3:34:00", "remaining_time": "4:45:39", "throughput": 4414.64, "total_tokens": 56685680} {"current_steps": 26260, "total_steps": 61300, "loss": 0.3573, "lr": 3.529830252117657e-05, "epoch": 4.283849918433932, "percentage": 42.84, "elapsed_time": "3:34:02", "remaining_time": "4:45:36", "throughput": 4414.73, "total_tokens": 56696752} {"current_steps": 26265, "total_steps": 61300, "loss": 0.3393, "lr": 3.529181609488532e-05, "epoch": 4.284665579119086, "percentage": 42.85, "elapsed_time": "3:34:04", "remaining_time": "4:45:33", "throughput": 4414.81, "total_tokens": 56707600} {"current_steps": 26270, "total_steps": 61300, "loss": 0.3706, "lr": 3.528532883428724e-05, "epoch": 4.285481239804241, "percentage": 42.85, "elapsed_time": "3:34:07", "remaining_time": "4:45:31", "throughput": 4414.88, "total_tokens": 56718608} {"current_steps": 26275, "total_steps": 61300, "loss": 0.369, "lr": 3.527884073990822e-05, "epoch": 4.286296900489396, "percentage": 42.86, "elapsed_time": "3:34:09", "remaining_time": "4:45:28", "throughput": 4414.95, "total_tokens": 56729840} {"current_steps": 26280, "total_steps": 61300, "loss": 0.3261, "lr": 3.52723518122742e-05, "epoch": 4.287112561174552, "percentage": 42.87, "elapsed_time": "3:34:11", "remaining_time": "4:45:25", "throughput": 4415.01, "total_tokens": 56739984} {"current_steps": 26285, "total_steps": 61300, "loss": 0.3714, "lr": 3.526586205191123e-05, "epoch": 4.287928221859707, "percentage": 42.88, "elapsed_time": "3:34:13", "remaining_time": "4:45:23", "throughput": 4415.08, "total_tokens": 56751248} {"current_steps": 26290, "total_steps": 61300, "loss": 0.3629, "lr": 3.525937145934539e-05, "epoch": 4.288743882544861, "percentage": 42.89, "elapsed_time": "3:34:16", "remaining_time": "4:45:20", "throughput": 4415.15, "total_tokens": 56762480} {"current_steps": 26295, "total_steps": 61300, "loss": 0.3366, "lr": 3.525288003510285e-05, "epoch": 4.289559543230016, "percentage": 42.9, "elapsed_time": "3:34:18", "remaining_time": "4:45:17", "throughput": 4415.21, "total_tokens": 56772016} {"current_steps": 26300, "total_steps": 61300, "loss": 0.357, "lr": 3.524638777970982e-05, "epoch": 4.290375203915171, "percentage": 42.9, "elapsed_time": "3:34:20", "remaining_time": "4:45:14", "throughput": 4415.27, "total_tokens": 56781168} {"current_steps": 26305, "total_steps": 61300, "loss": 0.3384, "lr": 3.523989469369262e-05, "epoch": 4.291190864600326, "percentage": 42.91, "elapsed_time": "3:34:22", "remaining_time": "4:45:11", "throughput": 4415.35, "total_tokens": 56792720} {"current_steps": 26310, "total_steps": 61300, "loss": 0.3431, "lr": 3.523340077757759e-05, "epoch": 4.2920065252854815, "percentage": 42.92, "elapsed_time": "3:34:24", "remaining_time": "4:45:09", "throughput": 4415.42, "total_tokens": 56803856} {"current_steps": 26315, "total_steps": 61300, "loss": 0.3483, "lr": 3.522690603189117e-05, "epoch": 4.292822185970636, "percentage": 42.93, "elapsed_time": "3:34:27", "remaining_time": "4:45:06", "throughput": 4415.49, "total_tokens": 56814480} {"current_steps": 26320, "total_steps": 61300, "loss": 0.3368, "lr": 3.522041045715986e-05, "epoch": 4.293637846655791, "percentage": 42.94, "elapsed_time": "3:34:29", "remaining_time": "4:45:03", "throughput": 4415.55, "total_tokens": 56824816} {"current_steps": 26325, "total_steps": 61300, "loss": 0.3452, "lr": 3.521391405391022e-05, "epoch": 4.294453507340946, "percentage": 42.94, "elapsed_time": "3:34:31", "remaining_time": "4:45:00", "throughput": 4415.61, "total_tokens": 56834928} {"current_steps": 26330, "total_steps": 61300, "loss": 0.3577, "lr": 3.520741682266888e-05, "epoch": 4.295269168026101, "percentage": 42.95, "elapsed_time": "3:34:33", "remaining_time": "4:44:58", "throughput": 4415.67, "total_tokens": 56845680} {"current_steps": 26335, "total_steps": 61300, "loss": 0.3536, "lr": 3.520091876396255e-05, "epoch": 4.2960848287112565, "percentage": 42.96, "elapsed_time": "3:34:35", "remaining_time": "4:44:55", "throughput": 4415.75, "total_tokens": 56856464} {"current_steps": 26340, "total_steps": 61300, "loss": 0.3199, "lr": 3.5194419878317975e-05, "epoch": 4.296900489396411, "percentage": 42.97, "elapsed_time": "3:34:38", "remaining_time": "4:44:52", "throughput": 4415.81, "total_tokens": 56867920} {"current_steps": 26345, "total_steps": 61300, "loss": 0.3436, "lr": 3.518792016626201e-05, "epoch": 4.297716150081566, "percentage": 42.98, "elapsed_time": "3:34:40", "remaining_time": "4:44:50", "throughput": 4415.87, "total_tokens": 56878672} {"current_steps": 26350, "total_steps": 61300, "loss": 0.3402, "lr": 3.518141962832153e-05, "epoch": 4.298531810766721, "percentage": 42.99, "elapsed_time": "3:34:42", "remaining_time": "4:44:47", "throughput": 4415.94, "total_tokens": 56889616} {"current_steps": 26355, "total_steps": 61300, "loss": 0.3387, "lr": 3.517491826502352e-05, "epoch": 4.299347471451876, "percentage": 42.99, "elapsed_time": "3:34:44", "remaining_time": "4:44:44", "throughput": 4415.99, "total_tokens": 56899184} {"current_steps": 26360, "total_steps": 61300, "loss": 0.3307, "lr": 3.516841607689501e-05, "epoch": 4.300163132137031, "percentage": 43.0, "elapsed_time": "3:34:47", "remaining_time": "4:44:41", "throughput": 4416.05, "total_tokens": 56910480} {"current_steps": 26365, "total_steps": 61300, "loss": 0.3612, "lr": 3.516191306446309e-05, "epoch": 4.300978792822186, "percentage": 43.01, "elapsed_time": "3:34:49", "remaining_time": "4:44:39", "throughput": 4416.13, "total_tokens": 56921040} {"current_steps": 26370, "total_steps": 61300, "loss": 0.361, "lr": 3.5155409228254946e-05, "epoch": 4.301794453507341, "percentage": 43.02, "elapsed_time": "3:34:51", "remaining_time": "4:44:36", "throughput": 4416.21, "total_tokens": 56931920} {"current_steps": 26375, "total_steps": 61300, "loss": 0.3715, "lr": 3.5148904568797805e-05, "epoch": 4.302610114192496, "percentage": 43.03, "elapsed_time": "3:34:53", "remaining_time": "4:44:33", "throughput": 4416.29, "total_tokens": 56942960} {"current_steps": 26380, "total_steps": 61300, "loss": 0.3504, "lr": 3.514239908661896e-05, "epoch": 4.303425774877651, "percentage": 43.03, "elapsed_time": "3:34:56", "remaining_time": "4:44:31", "throughput": 4416.37, "total_tokens": 56955728} {"current_steps": 26385, "total_steps": 61300, "loss": 0.3329, "lr": 3.513589278224577e-05, "epoch": 4.304241435562806, "percentage": 43.04, "elapsed_time": "3:34:58", "remaining_time": "4:44:28", "throughput": 4416.44, "total_tokens": 56966224} {"current_steps": 26390, "total_steps": 61300, "loss": 0.3452, "lr": 3.5129385656205696e-05, "epoch": 4.30505709624796, "percentage": 43.05, "elapsed_time": "3:35:00", "remaining_time": "4:44:25", "throughput": 4416.48, "total_tokens": 56975440} {"current_steps": 26395, "total_steps": 61300, "loss": 0.3426, "lr": 3.512287770902623e-05, "epoch": 4.305872756933116, "percentage": 43.06, "elapsed_time": "3:35:02", "remaining_time": "4:44:22", "throughput": 4416.55, "total_tokens": 56986416} {"current_steps": 26400, "total_steps": 61300, "loss": 0.3556, "lr": 3.5116368941234924e-05, "epoch": 4.306688417618271, "percentage": 43.07, "elapsed_time": "3:35:05", "remaining_time": "4:44:20", "throughput": 4416.62, "total_tokens": 56997392} {"current_steps": 26405, "total_steps": 61300, "loss": 0.3143, "lr": 3.510985935335943e-05, "epoch": 4.307504078303426, "percentage": 43.08, "elapsed_time": "3:35:07", "remaining_time": "4:44:17", "throughput": 4416.69, "total_tokens": 57008144} {"current_steps": 26410, "total_steps": 61300, "loss": 0.3461, "lr": 3.510334894592743e-05, "epoch": 4.308319738988581, "percentage": 43.08, "elapsed_time": "3:35:09", "remaining_time": "4:44:14", "throughput": 4416.77, "total_tokens": 57019472} {"current_steps": 26415, "total_steps": 61300, "loss": 0.2975, "lr": 3.509683771946671e-05, "epoch": 4.309135399673735, "percentage": 43.09, "elapsed_time": "3:35:11", "remaining_time": "4:44:11", "throughput": 4416.82, "total_tokens": 57029136} {"current_steps": 26420, "total_steps": 61300, "loss": 0.3459, "lr": 3.509032567450508e-05, "epoch": 4.309951060358891, "percentage": 43.1, "elapsed_time": "3:35:13", "remaining_time": "4:44:09", "throughput": 4416.88, "total_tokens": 57039504} {"current_steps": 26425, "total_steps": 61300, "loss": 0.3656, "lr": 3.508381281157046e-05, "epoch": 4.310766721044046, "percentage": 43.11, "elapsed_time": "3:35:16", "remaining_time": "4:44:06", "throughput": 4416.96, "total_tokens": 57050064} {"current_steps": 26430, "total_steps": 61300, "loss": 0.3355, "lr": 3.507729913119081e-05, "epoch": 4.311582381729201, "percentage": 43.12, "elapsed_time": "3:35:18", "remaining_time": "4:44:03", "throughput": 4417.02, "total_tokens": 57061232} {"current_steps": 26435, "total_steps": 61300, "loss": 0.3272, "lr": 3.507078463389417e-05, "epoch": 4.3123980424143555, "percentage": 43.12, "elapsed_time": "3:35:20", "remaining_time": "4:44:01", "throughput": 4417.1, "total_tokens": 57072016} {"current_steps": 26440, "total_steps": 61300, "loss": 0.3392, "lr": 3.506426932020861e-05, "epoch": 4.31321370309951, "percentage": 43.13, "elapsed_time": "3:35:22", "remaining_time": "4:43:58", "throughput": 4417.16, "total_tokens": 57082576} {"current_steps": 26445, "total_steps": 61300, "loss": 0.3838, "lr": 3.505775319066233e-05, "epoch": 4.314029363784665, "percentage": 43.14, "elapsed_time": "3:35:25", "remaining_time": "4:43:55", "throughput": 4417.22, "total_tokens": 57093712} {"current_steps": 26450, "total_steps": 61300, "loss": 0.3424, "lr": 3.5051236245783536e-05, "epoch": 4.314845024469821, "percentage": 43.15, "elapsed_time": "3:35:27", "remaining_time": "4:43:53", "throughput": 4417.28, "total_tokens": 57104432} {"current_steps": 26455, "total_steps": 61300, "loss": 0.3356, "lr": 3.5044718486100536e-05, "epoch": 4.315660685154976, "percentage": 43.16, "elapsed_time": "3:35:29", "remaining_time": "4:43:50", "throughput": 4417.35, "total_tokens": 57114576} {"current_steps": 26460, "total_steps": 61300, "loss": 0.3641, "lr": 3.503819991214168e-05, "epoch": 4.3164763458401305, "percentage": 43.16, "elapsed_time": "3:35:31", "remaining_time": "4:43:47", "throughput": 4417.44, "total_tokens": 57125744} {"current_steps": 26465, "total_steps": 61300, "loss": 0.311, "lr": 3.503168052443542e-05, "epoch": 4.317292006525285, "percentage": 43.17, "elapsed_time": "3:35:34", "remaining_time": "4:43:44", "throughput": 4417.51, "total_tokens": 57136784} {"current_steps": 26470, "total_steps": 61300, "loss": 0.3628, "lr": 3.502516032351022e-05, "epoch": 4.31810766721044, "percentage": 43.18, "elapsed_time": "3:35:36", "remaining_time": "4:43:42", "throughput": 4417.58, "total_tokens": 57147888} {"current_steps": 26475, "total_steps": 61300, "loss": 0.3534, "lr": 3.501863930989467e-05, "epoch": 4.318923327895595, "percentage": 43.19, "elapsed_time": "3:35:38", "remaining_time": "4:43:39", "throughput": 4417.65, "total_tokens": 57158704} {"current_steps": 26480, "total_steps": 61300, "loss": 0.3291, "lr": 3.501211748411738e-05, "epoch": 4.319738988580751, "percentage": 43.2, "elapsed_time": "3:35:41", "remaining_time": "4:43:36", "throughput": 4417.73, "total_tokens": 57170096} {"current_steps": 26485, "total_steps": 61300, "loss": 0.3559, "lr": 3.500559484670705e-05, "epoch": 4.3205546492659055, "percentage": 43.21, "elapsed_time": "3:35:43", "remaining_time": "4:43:34", "throughput": 4417.8, "total_tokens": 57181008} {"current_steps": 26490, "total_steps": 61300, "loss": 0.3463, "lr": 3.499907139819242e-05, "epoch": 4.32137030995106, "percentage": 43.21, "elapsed_time": "3:35:45", "remaining_time": "4:43:31", "throughput": 4417.86, "total_tokens": 57192752} {"current_steps": 26495, "total_steps": 61300, "loss": 0.3385, "lr": 3.499254713910234e-05, "epoch": 4.322185970636215, "percentage": 43.22, "elapsed_time": "3:35:48", "remaining_time": "4:43:29", "throughput": 4417.94, "total_tokens": 57204976} {"current_steps": 26500, "total_steps": 61300, "loss": 0.341, "lr": 3.498602206996569e-05, "epoch": 4.32300163132137, "percentage": 43.23, "elapsed_time": "3:35:50", "remaining_time": "4:43:27", "throughput": 4418.02, "total_tokens": 57216592} {"current_steps": 26505, "total_steps": 61300, "loss": 0.359, "lr": 3.497949619131141e-05, "epoch": 4.323817292006526, "percentage": 43.24, "elapsed_time": "3:35:53", "remaining_time": "4:43:24", "throughput": 4418.09, "total_tokens": 57227568} {"current_steps": 26510, "total_steps": 61300, "loss": 0.3447, "lr": 3.497296950366854e-05, "epoch": 4.3246329526916805, "percentage": 43.25, "elapsed_time": "3:35:55", "remaining_time": "4:43:21", "throughput": 4418.14, "total_tokens": 57238096} {"current_steps": 26515, "total_steps": 61300, "loss": 0.3508, "lr": 3.4966442007566165e-05, "epoch": 4.325448613376835, "percentage": 43.25, "elapsed_time": "3:35:57", "remaining_time": "4:43:19", "throughput": 4418.22, "total_tokens": 57250416} {"current_steps": 26520, "total_steps": 61300, "loss": 0.3507, "lr": 3.495991370353342e-05, "epoch": 4.32626427406199, "percentage": 43.26, "elapsed_time": "3:36:00", "remaining_time": "4:43:16", "throughput": 4418.28, "total_tokens": 57261008} {"current_steps": 26525, "total_steps": 61300, "loss": 0.3297, "lr": 3.4953384592099536e-05, "epoch": 4.327079934747145, "percentage": 43.27, "elapsed_time": "3:36:02", "remaining_time": "4:43:13", "throughput": 4418.35, "total_tokens": 57271344} {"current_steps": 26530, "total_steps": 61300, "loss": 0.3245, "lr": 3.494685467379381e-05, "epoch": 4.327895595432301, "percentage": 43.28, "elapsed_time": "3:36:04", "remaining_time": "4:43:10", "throughput": 4418.41, "total_tokens": 57280752} {"current_steps": 26535, "total_steps": 61300, "loss": 0.3681, "lr": 3.494032394914555e-05, "epoch": 4.328711256117455, "percentage": 43.29, "elapsed_time": "3:36:06", "remaining_time": "4:43:07", "throughput": 4418.47, "total_tokens": 57290736} {"current_steps": 26540, "total_steps": 61300, "loss": 0.295, "lr": 3.493379241868421e-05, "epoch": 4.32952691680261, "percentage": 43.3, "elapsed_time": "3:36:08", "remaining_time": "4:43:05", "throughput": 4418.55, "total_tokens": 57301680} {"current_steps": 26545, "total_steps": 61300, "loss": 0.3639, "lr": 3.492726008293925e-05, "epoch": 4.330342577487765, "percentage": 43.3, "elapsed_time": "3:36:10", "remaining_time": "4:43:02", "throughput": 4418.61, "total_tokens": 57313200} {"current_steps": 26550, "total_steps": 61300, "loss": 0.3467, "lr": 3.4920726942440215e-05, "epoch": 4.33115823817292, "percentage": 43.31, "elapsed_time": "3:36:13", "remaining_time": "4:42:59", "throughput": 4418.67, "total_tokens": 57323856} {"current_steps": 26555, "total_steps": 61300, "loss": 0.33, "lr": 3.4914192997716724e-05, "epoch": 4.331973898858075, "percentage": 43.32, "elapsed_time": "3:36:15", "remaining_time": "4:42:57", "throughput": 4418.72, "total_tokens": 57334768} {"current_steps": 26560, "total_steps": 61300, "loss": 0.3292, "lr": 3.4907658249298435e-05, "epoch": 4.33278955954323, "percentage": 43.33, "elapsed_time": "3:36:17", "remaining_time": "4:42:54", "throughput": 4418.77, "total_tokens": 57344720} {"current_steps": 26565, "total_steps": 61300, "loss": 0.3625, "lr": 3.4901122697715096e-05, "epoch": 4.333605220228385, "percentage": 43.34, "elapsed_time": "3:36:20", "remaining_time": "4:42:52", "throughput": 4418.85, "total_tokens": 57356784} {"current_steps": 26570, "total_steps": 61300, "loss": 0.3415, "lr": 3.4894586343496524e-05, "epoch": 4.33442088091354, "percentage": 43.34, "elapsed_time": "3:36:22", "remaining_time": "4:42:49", "throughput": 4418.9, "total_tokens": 57367184} {"current_steps": 26575, "total_steps": 61300, "loss": 0.3315, "lr": 3.4888049187172566e-05, "epoch": 4.335236541598695, "percentage": 43.35, "elapsed_time": "3:36:24", "remaining_time": "4:42:46", "throughput": 4418.97, "total_tokens": 57377840} {"current_steps": 26580, "total_steps": 61300, "loss": 0.3514, "lr": 3.4881511229273175e-05, "epoch": 4.33605220228385, "percentage": 43.36, "elapsed_time": "3:36:26", "remaining_time": "4:42:43", "throughput": 4419.03, "total_tokens": 57389232} {"current_steps": 26585, "total_steps": 61300, "loss": 0.341, "lr": 3.487497247032835e-05, "epoch": 4.3368678629690045, "percentage": 43.37, "elapsed_time": "3:36:29", "remaining_time": "4:42:41", "throughput": 4419.11, "total_tokens": 57400176} {"current_steps": 26590, "total_steps": 61300, "loss": 0.3557, "lr": 3.4868432910868156e-05, "epoch": 4.33768352365416, "percentage": 43.38, "elapsed_time": "3:36:31", "remaining_time": "4:42:38", "throughput": 4419.17, "total_tokens": 57410768} {"current_steps": 26595, "total_steps": 61300, "loss": 0.3507, "lr": 3.48618925514227e-05, "epoch": 4.338499184339315, "percentage": 43.38, "elapsed_time": "3:36:33", "remaining_time": "4:42:35", "throughput": 4419.24, "total_tokens": 57421680} {"current_steps": 26600, "total_steps": 61300, "loss": 0.3508, "lr": 3.4855351392522214e-05, "epoch": 4.33931484502447, "percentage": 43.39, "elapsed_time": "3:36:35", "remaining_time": "4:42:32", "throughput": 4419.32, "total_tokens": 57431600} {"current_steps": 26605, "total_steps": 61300, "loss": 0.3446, "lr": 3.4848809434696924e-05, "epoch": 4.340130505709625, "percentage": 43.4, "elapsed_time": "3:36:37", "remaining_time": "4:42:30", "throughput": 4419.39, "total_tokens": 57442640} {"current_steps": 26610, "total_steps": 61300, "loss": 0.3601, "lr": 3.484226667847718e-05, "epoch": 4.3409461663947795, "percentage": 43.41, "elapsed_time": "3:36:39", "remaining_time": "4:42:27", "throughput": 4419.47, "total_tokens": 57453072} {"current_steps": 26615, "total_steps": 61300, "loss": 0.3307, "lr": 3.4835723124393347e-05, "epoch": 4.341761827079935, "percentage": 43.42, "elapsed_time": "3:36:42", "remaining_time": "4:42:24", "throughput": 4419.53, "total_tokens": 57463792} {"current_steps": 26620, "total_steps": 61300, "loss": 0.3041, "lr": 3.48291787729759e-05, "epoch": 4.34257748776509, "percentage": 43.43, "elapsed_time": "3:36:44", "remaining_time": "4:42:21", "throughput": 4419.59, "total_tokens": 57474448} {"current_steps": 26625, "total_steps": 61300, "loss": 0.3157, "lr": 3.482263362475535e-05, "epoch": 4.343393148450245, "percentage": 43.43, "elapsed_time": "3:36:46", "remaining_time": "4:42:19", "throughput": 4419.68, "total_tokens": 57485904} {"current_steps": 26630, "total_steps": 61300, "loss": 0.3194, "lr": 3.4816087680262275e-05, "epoch": 4.3442088091354, "percentage": 43.44, "elapsed_time": "3:36:49", "remaining_time": "4:42:16", "throughput": 4419.75, "total_tokens": 57497008} {"current_steps": 26635, "total_steps": 61300, "loss": 0.3483, "lr": 3.480954094002733e-05, "epoch": 4.3450244698205545, "percentage": 43.45, "elapsed_time": "3:36:51", "remaining_time": "4:42:14", "throughput": 4419.81, "total_tokens": 57507920} {"current_steps": 26640, "total_steps": 61300, "loss": 0.3777, "lr": 3.480299340458123e-05, "epoch": 4.345840130505709, "percentage": 43.46, "elapsed_time": "3:36:53", "remaining_time": "4:42:11", "throughput": 4419.88, "total_tokens": 57518832} {"current_steps": 26645, "total_steps": 61300, "loss": 0.3379, "lr": 3.479644507445473e-05, "epoch": 4.346655791190865, "percentage": 43.47, "elapsed_time": "3:36:55", "remaining_time": "4:42:08", "throughput": 4419.95, "total_tokens": 57529808} {"current_steps": 26650, "total_steps": 61300, "loss": 0.3068, "lr": 3.4789895950178694e-05, "epoch": 4.34747145187602, "percentage": 43.47, "elapsed_time": "3:36:58", "remaining_time": "4:42:06", "throughput": 4420.01, "total_tokens": 57540944} {"current_steps": 26655, "total_steps": 61300, "loss": 0.3803, "lr": 3.478334603228401e-05, "epoch": 4.348287112561175, "percentage": 43.48, "elapsed_time": "3:37:00", "remaining_time": "4:42:03", "throughput": 4420.08, "total_tokens": 57552176} {"current_steps": 26660, "total_steps": 61300, "loss": 0.3667, "lr": 3.477679532130167e-05, "epoch": 4.349102773246329, "percentage": 43.49, "elapsed_time": "3:37:02", "remaining_time": "4:42:00", "throughput": 4420.15, "total_tokens": 57563184} {"current_steps": 26665, "total_steps": 61300, "loss": 0.3264, "lr": 3.4770243817762686e-05, "epoch": 4.349918433931484, "percentage": 43.5, "elapsed_time": "3:37:05", "remaining_time": "4:41:58", "throughput": 4420.23, "total_tokens": 57574320} {"current_steps": 26670, "total_steps": 61300, "loss": 0.3404, "lr": 3.476369152219817e-05, "epoch": 4.350734094616639, "percentage": 43.51, "elapsed_time": "3:37:07", "remaining_time": "4:41:55", "throughput": 4420.29, "total_tokens": 57584944} {"current_steps": 26675, "total_steps": 61300, "loss": 0.3294, "lr": 3.4757138435139274e-05, "epoch": 4.351549755301795, "percentage": 43.52, "elapsed_time": "3:37:09", "remaining_time": "4:41:52", "throughput": 4420.35, "total_tokens": 57595600} {"current_steps": 26680, "total_steps": 61300, "loss": 0.3428, "lr": 3.4750584557117234e-05, "epoch": 4.35236541598695, "percentage": 43.52, "elapsed_time": "3:37:12", "remaining_time": "4:41:50", "throughput": 4420.44, "total_tokens": 57607472} {"current_steps": 26685, "total_steps": 61300, "loss": 0.3647, "lr": 3.4744029888663326e-05, "epoch": 4.353181076672104, "percentage": 43.53, "elapsed_time": "3:37:14", "remaining_time": "4:41:47", "throughput": 4420.51, "total_tokens": 57618800} {"current_steps": 26690, "total_steps": 61300, "loss": 0.3345, "lr": 3.473747443030892e-05, "epoch": 4.353996737357259, "percentage": 43.54, "elapsed_time": "3:37:16", "remaining_time": "4:41:44", "throughput": 4420.58, "total_tokens": 57629040} {"current_steps": 26695, "total_steps": 61300, "loss": 0.3653, "lr": 3.473091818258543e-05, "epoch": 4.354812398042414, "percentage": 43.55, "elapsed_time": "3:37:18", "remaining_time": "4:41:42", "throughput": 4420.66, "total_tokens": 57639728} {"current_steps": 26700, "total_steps": 61300, "loss": 0.3356, "lr": 3.472436114602433e-05, "epoch": 4.35562805872757, "percentage": 43.56, "elapsed_time": "3:37:21", "remaining_time": "4:41:39", "throughput": 4420.71, "total_tokens": 57650512} {"current_steps": 26705, "total_steps": 61300, "loss": 0.3244, "lr": 3.471780332115719e-05, "epoch": 4.356443719412725, "percentage": 43.56, "elapsed_time": "3:37:23", "remaining_time": "4:41:37", "throughput": 4420.78, "total_tokens": 57662096} {"current_steps": 26710, "total_steps": 61300, "loss": 0.3374, "lr": 3.47112447085156e-05, "epoch": 4.357259380097879, "percentage": 43.57, "elapsed_time": "3:37:25", "remaining_time": "4:41:34", "throughput": 4420.85, "total_tokens": 57672080} {"current_steps": 26715, "total_steps": 61300, "loss": 0.3772, "lr": 3.470468530863123e-05, "epoch": 4.358075040783034, "percentage": 43.58, "elapsed_time": "3:37:27", "remaining_time": "4:41:31", "throughput": 4420.91, "total_tokens": 57682704} {"current_steps": 26720, "total_steps": 61300, "loss": 0.3435, "lr": 3.469812512203584e-05, "epoch": 4.358890701468189, "percentage": 43.59, "elapsed_time": "3:37:29", "remaining_time": "4:41:28", "throughput": 4420.98, "total_tokens": 57693520} {"current_steps": 26725, "total_steps": 61300, "loss": 0.338, "lr": 3.469156414926121e-05, "epoch": 4.359706362153344, "percentage": 43.6, "elapsed_time": "3:37:31", "remaining_time": "4:41:25", "throughput": 4421.04, "total_tokens": 57703312} {"current_steps": 26730, "total_steps": 61300, "loss": 0.3406, "lr": 3.4685002390839226e-05, "epoch": 4.3605220228384995, "percentage": 43.61, "elapsed_time": "3:37:34", "remaining_time": "4:41:23", "throughput": 4421.11, "total_tokens": 57714672} {"current_steps": 26735, "total_steps": 61300, "loss": 0.343, "lr": 3.467843984730179e-05, "epoch": 4.361337683523654, "percentage": 43.61, "elapsed_time": "3:37:36", "remaining_time": "4:41:20", "throughput": 4421.18, "total_tokens": 57724464} {"current_steps": 26740, "total_steps": 61300, "loss": 0.3348, "lr": 3.467187651918093e-05, "epoch": 4.362153344208809, "percentage": 43.62, "elapsed_time": "3:37:38", "remaining_time": "4:41:17", "throughput": 4421.25, "total_tokens": 57735856} {"current_steps": 26745, "total_steps": 61300, "loss": 0.3559, "lr": 3.466531240700868e-05, "epoch": 4.362969004893964, "percentage": 43.63, "elapsed_time": "3:37:41", "remaining_time": "4:41:15", "throughput": 4421.32, "total_tokens": 57747440} {"current_steps": 26750, "total_steps": 61300, "loss": 0.3383, "lr": 3.465874751131716e-05, "epoch": 4.363784665579119, "percentage": 43.64, "elapsed_time": "3:37:43", "remaining_time": "4:41:12", "throughput": 4421.36, "total_tokens": 57757168} {"current_steps": 26755, "total_steps": 61300, "loss": 0.3319, "lr": 3.4652181832638566e-05, "epoch": 4.364600326264274, "percentage": 43.65, "elapsed_time": "3:37:45", "remaining_time": "4:41:09", "throughput": 4421.42, "total_tokens": 57768112} {"current_steps": 26760, "total_steps": 61300, "loss": 0.3267, "lr": 3.464561537150513e-05, "epoch": 4.365415986949429, "percentage": 43.65, "elapsed_time": "3:37:47", "remaining_time": "4:41:06", "throughput": 4421.49, "total_tokens": 57778480} {"current_steps": 26765, "total_steps": 61300, "loss": 0.3504, "lr": 3.4639048128449175e-05, "epoch": 4.366231647634584, "percentage": 43.66, "elapsed_time": "3:37:49", "remaining_time": "4:41:04", "throughput": 4421.56, "total_tokens": 57789328} {"current_steps": 26770, "total_steps": 61300, "loss": 0.3153, "lr": 3.463248010400307e-05, "epoch": 4.367047308319739, "percentage": 43.67, "elapsed_time": "3:37:52", "remaining_time": "4:41:01", "throughput": 4421.62, "total_tokens": 57800112} {"current_steps": 26775, "total_steps": 61300, "loss": 0.3474, "lr": 3.462591129869925e-05, "epoch": 4.367862969004894, "percentage": 43.68, "elapsed_time": "3:37:54", "remaining_time": "4:40:58", "throughput": 4421.67, "total_tokens": 57810064} {"current_steps": 26780, "total_steps": 61300, "loss": 0.321, "lr": 3.461934171307022e-05, "epoch": 4.368678629690049, "percentage": 43.69, "elapsed_time": "3:37:56", "remaining_time": "4:40:56", "throughput": 4421.75, "total_tokens": 57821680} {"current_steps": 26785, "total_steps": 61300, "loss": 0.3585, "lr": 3.461277134764855e-05, "epoch": 4.369494290375204, "percentage": 43.69, "elapsed_time": "3:37:58", "remaining_time": "4:40:53", "throughput": 4421.81, "total_tokens": 57832496} {"current_steps": 26790, "total_steps": 61300, "loss": 0.3461, "lr": 3.460620020296684e-05, "epoch": 4.370309951060359, "percentage": 43.7, "elapsed_time": "3:38:01", "remaining_time": "4:40:50", "throughput": 4421.88, "total_tokens": 57842768} {"current_steps": 26795, "total_steps": 61300, "loss": 0.3122, "lr": 3.459962827955782e-05, "epoch": 4.371125611745514, "percentage": 43.71, "elapsed_time": "3:38:03", "remaining_time": "4:40:47", "throughput": 4421.94, "total_tokens": 57853008} {"current_steps": 26800, "total_steps": 61300, "loss": 0.3952, "lr": 3.459305557795422e-05, "epoch": 4.371941272430669, "percentage": 43.72, "elapsed_time": "3:38:05", "remaining_time": "4:40:44", "throughput": 4421.99, "total_tokens": 57863312} {"current_steps": 26805, "total_steps": 61300, "loss": 0.32, "lr": 3.458648209868886e-05, "epoch": 4.372756933115824, "percentage": 43.73, "elapsed_time": "3:38:07", "remaining_time": "4:40:42", "throughput": 4422.05, "total_tokens": 57873552} {"current_steps": 26810, "total_steps": 61300, "loss": 0.3576, "lr": 3.4579907842294614e-05, "epoch": 4.373572593800978, "percentage": 43.74, "elapsed_time": "3:38:09", "remaining_time": "4:40:39", "throughput": 4422.11, "total_tokens": 57884336} {"current_steps": 26815, "total_steps": 61300, "loss": 0.3422, "lr": 3.457333280930444e-05, "epoch": 4.374388254486134, "percentage": 43.74, "elapsed_time": "3:38:11", "remaining_time": "4:40:36", "throughput": 4422.17, "total_tokens": 57894512} {"current_steps": 26820, "total_steps": 61300, "loss": 0.3242, "lr": 3.456675700025132e-05, "epoch": 4.375203915171289, "percentage": 43.75, "elapsed_time": "3:38:14", "remaining_time": "4:40:34", "throughput": 4422.25, "total_tokens": 57906576} {"current_steps": 26825, "total_steps": 61300, "loss": 0.3418, "lr": 3.4560180415668354e-05, "epoch": 4.376019575856444, "percentage": 43.76, "elapsed_time": "3:38:16", "remaining_time": "4:40:31", "throughput": 4422.3, "total_tokens": 57916816} {"current_steps": 26830, "total_steps": 61300, "loss": 0.34, "lr": 3.455360305608865e-05, "epoch": 4.376835236541599, "percentage": 43.77, "elapsed_time": "3:38:18", "remaining_time": "4:40:28", "throughput": 4422.37, "total_tokens": 57927088} {"current_steps": 26835, "total_steps": 61300, "loss": 0.3593, "lr": 3.4547024922045405e-05, "epoch": 4.377650897226753, "percentage": 43.78, "elapsed_time": "3:38:21", "remaining_time": "4:40:26", "throughput": 4422.45, "total_tokens": 57939120} {"current_steps": 26840, "total_steps": 61300, "loss": 0.3596, "lr": 3.454044601407187e-05, "epoch": 4.378466557911908, "percentage": 43.78, "elapsed_time": "3:38:23", "remaining_time": "4:40:23", "throughput": 4422.5, "total_tokens": 57949264} {"current_steps": 26845, "total_steps": 61300, "loss": 0.3141, "lr": 3.453386633270138e-05, "epoch": 4.379282218597064, "percentage": 43.79, "elapsed_time": "3:38:25", "remaining_time": "4:40:21", "throughput": 4422.57, "total_tokens": 57961328} {"current_steps": 26850, "total_steps": 61300, "loss": 0.3515, "lr": 3.4527285878467305e-05, "epoch": 4.380097879282219, "percentage": 43.8, "elapsed_time": "3:38:28", "remaining_time": "4:40:18", "throughput": 4422.65, "total_tokens": 57972816} {"current_steps": 26855, "total_steps": 61300, "loss": 0.3263, "lr": 3.45207046519031e-05, "epoch": 4.3809135399673735, "percentage": 43.81, "elapsed_time": "3:38:30", "remaining_time": "4:40:15", "throughput": 4422.71, "total_tokens": 57983440} {"current_steps": 26860, "total_steps": 61300, "loss": 0.3146, "lr": 3.451412265354227e-05, "epoch": 4.381729200652528, "percentage": 43.82, "elapsed_time": "3:38:32", "remaining_time": "4:40:13", "throughput": 4422.78, "total_tokens": 57994384} {"current_steps": 26865, "total_steps": 61300, "loss": 0.3407, "lr": 3.450753988391839e-05, "epoch": 4.382544861337683, "percentage": 43.83, "elapsed_time": "3:38:35", "remaining_time": "4:40:10", "throughput": 4422.87, "total_tokens": 58006192} {"current_steps": 26870, "total_steps": 61300, "loss": 0.344, "lr": 3.450095634356508e-05, "epoch": 4.383360522022839, "percentage": 43.83, "elapsed_time": "3:38:37", "remaining_time": "4:40:07", "throughput": 4422.93, "total_tokens": 58016784} {"current_steps": 26875, "total_steps": 61300, "loss": 0.3301, "lr": 3.449437203301604e-05, "epoch": 4.384176182707994, "percentage": 43.84, "elapsed_time": "3:38:39", "remaining_time": "4:40:05", "throughput": 4422.98, "total_tokens": 58026736} {"current_steps": 26880, "total_steps": 61300, "loss": 0.3574, "lr": 3.4487786952805035e-05, "epoch": 4.3849918433931485, "percentage": 43.85, "elapsed_time": "3:38:41", "remaining_time": "4:40:02", "throughput": 4423.05, "total_tokens": 58037200} {"current_steps": 26885, "total_steps": 61300, "loss": 0.3651, "lr": 3.4481201103465875e-05, "epoch": 4.385807504078303, "percentage": 43.86, "elapsed_time": "3:38:44", "remaining_time": "4:39:59", "throughput": 4423.13, "total_tokens": 58049200} {"current_steps": 26890, "total_steps": 61300, "loss": 0.3398, "lr": 3.447461448553245e-05, "epoch": 4.386623164763458, "percentage": 43.87, "elapsed_time": "3:38:46", "remaining_time": "4:39:57", "throughput": 4423.2, "total_tokens": 58060144} {"current_steps": 26895, "total_steps": 61300, "loss": 0.3486, "lr": 3.4468027099538694e-05, "epoch": 4.387438825448613, "percentage": 43.87, "elapsed_time": "3:38:48", "remaining_time": "4:39:54", "throughput": 4423.27, "total_tokens": 58071600} {"current_steps": 26900, "total_steps": 61300, "loss": 0.3651, "lr": 3.446143894601862e-05, "epoch": 4.388254486133769, "percentage": 43.88, "elapsed_time": "3:38:50", "remaining_time": "4:39:51", "throughput": 4423.34, "total_tokens": 58081616} {"current_steps": 26905, "total_steps": 61300, "loss": 0.3448, "lr": 3.44548500255063e-05, "epoch": 4.3890701468189235, "percentage": 43.89, "elapsed_time": "3:38:53", "remaining_time": "4:39:49", "throughput": 4423.4, "total_tokens": 58092976} {"current_steps": 26910, "total_steps": 61300, "loss": 0.3183, "lr": 3.444826033853587e-05, "epoch": 4.389885807504078, "percentage": 43.9, "elapsed_time": "3:38:55", "remaining_time": "4:39:46", "throughput": 4423.46, "total_tokens": 58103536} {"current_steps": 26915, "total_steps": 61300, "loss": 0.3408, "lr": 3.4441669885641517e-05, "epoch": 4.390701468189233, "percentage": 43.91, "elapsed_time": "3:38:57", "remaining_time": "4:39:44", "throughput": 4423.55, "total_tokens": 58115504} {"current_steps": 26920, "total_steps": 61300, "loss": 0.3629, "lr": 3.443507866735749e-05, "epoch": 4.391517128874388, "percentage": 43.92, "elapsed_time": "3:38:59", "remaining_time": "4:39:41", "throughput": 4423.6, "total_tokens": 58125648} {"current_steps": 26925, "total_steps": 61300, "loss": 0.297, "lr": 3.4428486684218116e-05, "epoch": 4.392332789559543, "percentage": 43.92, "elapsed_time": "3:39:02", "remaining_time": "4:39:38", "throughput": 4423.67, "total_tokens": 58136816} {"current_steps": 26930, "total_steps": 61300, "loss": 0.3488, "lr": 3.442189393675777e-05, "epoch": 4.3931484502446985, "percentage": 43.93, "elapsed_time": "3:39:04", "remaining_time": "4:39:35", "throughput": 4423.73, "total_tokens": 58146832} {"current_steps": 26935, "total_steps": 61300, "loss": 0.3668, "lr": 3.44153004255109e-05, "epoch": 4.393964110929853, "percentage": 43.94, "elapsed_time": "3:39:06", "remaining_time": "4:39:32", "throughput": 4423.78, "total_tokens": 58156912} {"current_steps": 26940, "total_steps": 61300, "loss": 0.3238, "lr": 3.4408706151012e-05, "epoch": 4.394779771615008, "percentage": 43.95, "elapsed_time": "3:39:08", "remaining_time": "4:39:30", "throughput": 4423.85, "total_tokens": 58167856} {"current_steps": 26945, "total_steps": 61300, "loss": 0.3608, "lr": 3.440211111379564e-05, "epoch": 4.395595432300163, "percentage": 43.96, "elapsed_time": "3:39:11", "remaining_time": "4:39:27", "throughput": 4423.91, "total_tokens": 58178928} {"current_steps": 26950, "total_steps": 61300, "loss": 0.3508, "lr": 3.4395515314396445e-05, "epoch": 4.396411092985318, "percentage": 43.96, "elapsed_time": "3:39:12", "remaining_time": "4:39:24", "throughput": 4423.97, "total_tokens": 58187888} {"current_steps": 26955, "total_steps": 61300, "loss": 0.3272, "lr": 3.4388918753349106e-05, "epoch": 4.397226753670473, "percentage": 43.97, "elapsed_time": "3:39:14", "remaining_time": "4:39:21", "throughput": 4424.03, "total_tokens": 58198160} {"current_steps": 26960, "total_steps": 61300, "loss": 0.37, "lr": 3.438232143118838e-05, "epoch": 4.398042414355628, "percentage": 43.98, "elapsed_time": "3:39:17", "remaining_time": "4:39:19", "throughput": 4424.11, "total_tokens": 58209808} {"current_steps": 26965, "total_steps": 61300, "loss": 0.3578, "lr": 3.437572334844907e-05, "epoch": 4.398858075040783, "percentage": 43.99, "elapsed_time": "3:39:19", "remaining_time": "4:39:16", "throughput": 4424.19, "total_tokens": 58221104} {"current_steps": 26970, "total_steps": 61300, "loss": 0.3241, "lr": 3.436912450566606e-05, "epoch": 4.399673735725938, "percentage": 44.0, "elapsed_time": "3:39:21", "remaining_time": "4:39:13", "throughput": 4424.24, "total_tokens": 58230832} {"current_steps": 26975, "total_steps": 61300, "loss": 0.2744, "lr": 3.436252490337428e-05, "epoch": 4.400489396411093, "percentage": 44.0, "elapsed_time": "3:39:23", "remaining_time": "4:39:10", "throughput": 4424.31, "total_tokens": 58241328} {"current_steps": 26980, "total_steps": 61300, "loss": 0.2818, "lr": 3.4355924542108716e-05, "epoch": 4.401305057096248, "percentage": 44.01, "elapsed_time": "3:39:26", "remaining_time": "4:39:08", "throughput": 4424.39, "total_tokens": 58252720} {"current_steps": 26985, "total_steps": 61300, "loss": 0.3479, "lr": 3.4349323422404444e-05, "epoch": 4.402120717781403, "percentage": 44.02, "elapsed_time": "3:39:28", "remaining_time": "4:39:05", "throughput": 4424.44, "total_tokens": 58263216} {"current_steps": 26990, "total_steps": 61300, "loss": 0.3239, "lr": 3.434272154479657e-05, "epoch": 4.402936378466558, "percentage": 44.03, "elapsed_time": "3:39:30", "remaining_time": "4:39:02", "throughput": 4424.5, "total_tokens": 58274320} {"current_steps": 26995, "total_steps": 61300, "loss": 0.365, "lr": 3.4336118909820295e-05, "epoch": 4.403752039151713, "percentage": 44.04, "elapsed_time": "3:39:33", "remaining_time": "4:39:00", "throughput": 4424.56, "total_tokens": 58285392} {"current_steps": 27000, "total_steps": 61300, "loss": 0.3489, "lr": 3.432951551801084e-05, "epoch": 4.404567699836868, "percentage": 44.05, "elapsed_time": "3:39:35", "remaining_time": "4:38:57", "throughput": 4424.61, "total_tokens": 58295728} {"current_steps": 27005, "total_steps": 61300, "loss": 0.3463, "lr": 3.432291136990352e-05, "epoch": 4.4053833605220225, "percentage": 44.05, "elapsed_time": "3:39:37", "remaining_time": "4:38:54", "throughput": 4424.68, "total_tokens": 58306704} {"current_steps": 27010, "total_steps": 61300, "loss": 0.3743, "lr": 3.4316306466033704e-05, "epoch": 4.406199021207178, "percentage": 44.06, "elapsed_time": "3:39:39", "remaining_time": "4:38:52", "throughput": 4424.76, "total_tokens": 58318288} {"current_steps": 27015, "total_steps": 61300, "loss": 0.3446, "lr": 3.430970080693681e-05, "epoch": 4.407014681892333, "percentage": 44.07, "elapsed_time": "3:39:42", "remaining_time": "4:38:50", "throughput": 4424.83, "total_tokens": 58330416} {"current_steps": 27020, "total_steps": 61300, "loss": 0.3065, "lr": 3.430309439314834e-05, "epoch": 4.407830342577488, "percentage": 44.08, "elapsed_time": "3:39:44", "remaining_time": "4:38:47", "throughput": 4424.89, "total_tokens": 58341456} {"current_steps": 27025, "total_steps": 61300, "loss": 0.3329, "lr": 3.4296487225203825e-05, "epoch": 4.408646003262643, "percentage": 44.09, "elapsed_time": "3:39:46", "remaining_time": "4:38:44", "throughput": 4424.94, "total_tokens": 58351568} {"current_steps": 27030, "total_steps": 61300, "loss": 0.3115, "lr": 3.42898793036389e-05, "epoch": 4.4094616639477975, "percentage": 44.09, "elapsed_time": "3:39:49", "remaining_time": "4:38:41", "throughput": 4424.99, "total_tokens": 58361968} {"current_steps": 27035, "total_steps": 61300, "loss": 0.3179, "lr": 3.428327062898921e-05, "epoch": 4.410277324632952, "percentage": 44.1, "elapsed_time": "3:39:51", "remaining_time": "4:38:39", "throughput": 4425.07, "total_tokens": 58373200} {"current_steps": 27040, "total_steps": 61300, "loss": 0.3233, "lr": 3.4276661201790506e-05, "epoch": 4.411092985318108, "percentage": 44.11, "elapsed_time": "3:39:53", "remaining_time": "4:38:36", "throughput": 4425.13, "total_tokens": 58383632} {"current_steps": 27045, "total_steps": 61300, "loss": 0.2868, "lr": 3.427005102257857e-05, "epoch": 4.411908646003263, "percentage": 44.12, "elapsed_time": "3:39:55", "remaining_time": "4:38:33", "throughput": 4425.19, "total_tokens": 58394768} {"current_steps": 27050, "total_steps": 61300, "loss": 0.3023, "lr": 3.426344009188927e-05, "epoch": 4.412724306688418, "percentage": 44.13, "elapsed_time": "3:39:57", "remaining_time": "4:38:30", "throughput": 4425.24, "total_tokens": 58403856} {"current_steps": 27055, "total_steps": 61300, "loss": 0.375, "lr": 3.425682841025851e-05, "epoch": 4.4135399673735725, "percentage": 44.14, "elapsed_time": "3:40:00", "remaining_time": "4:38:28", "throughput": 4425.31, "total_tokens": 58415152} {"current_steps": 27060, "total_steps": 61300, "loss": 0.3294, "lr": 3.4250215978222264e-05, "epoch": 4.414355628058727, "percentage": 44.14, "elapsed_time": "3:40:02", "remaining_time": "4:38:25", "throughput": 4425.37, "total_tokens": 58425584} {"current_steps": 27065, "total_steps": 61300, "loss": 0.4102, "lr": 3.424360279631659e-05, "epoch": 4.415171288743883, "percentage": 44.15, "elapsed_time": "3:40:04", "remaining_time": "4:38:22", "throughput": 4425.44, "total_tokens": 58435088} {"current_steps": 27070, "total_steps": 61300, "loss": 0.3515, "lr": 3.423698886507756e-05, "epoch": 4.415986949429038, "percentage": 44.16, "elapsed_time": "3:40:06", "remaining_time": "4:38:20", "throughput": 4425.52, "total_tokens": 58447088} {"current_steps": 27075, "total_steps": 61300, "loss": 0.3038, "lr": 3.4230374185041346e-05, "epoch": 4.416802610114193, "percentage": 44.17, "elapsed_time": "3:40:09", "remaining_time": "4:38:17", "throughput": 4425.59, "total_tokens": 58458928} {"current_steps": 27080, "total_steps": 61300, "loss": 0.3353, "lr": 3.4223758756744176e-05, "epoch": 4.417618270799347, "percentage": 44.18, "elapsed_time": "3:40:11", "remaining_time": "4:38:15", "throughput": 4425.66, "total_tokens": 58470224} {"current_steps": 27085, "total_steps": 61300, "loss": 0.3481, "lr": 3.421714258072231e-05, "epoch": 4.418433931484502, "percentage": 44.18, "elapsed_time": "3:40:13", "remaining_time": "4:38:12", "throughput": 4425.73, "total_tokens": 58480816} {"current_steps": 27090, "total_steps": 61300, "loss": 0.324, "lr": 3.421052565751209e-05, "epoch": 4.419249592169657, "percentage": 44.19, "elapsed_time": "3:40:16", "remaining_time": "4:38:09", "throughput": 4425.82, "total_tokens": 58492528} {"current_steps": 27095, "total_steps": 61300, "loss": 0.3333, "lr": 3.420390798764995e-05, "epoch": 4.420065252854813, "percentage": 44.2, "elapsed_time": "3:40:18", "remaining_time": "4:38:06", "throughput": 4425.89, "total_tokens": 58502640} {"current_steps": 27100, "total_steps": 61300, "loss": 0.3455, "lr": 3.4197289571672316e-05, "epoch": 4.420880913539968, "percentage": 44.21, "elapsed_time": "3:40:20", "remaining_time": "4:38:04", "throughput": 4425.96, "total_tokens": 58514064} {"current_steps": 27105, "total_steps": 61300, "loss": 0.3691, "lr": 3.4190670410115724e-05, "epoch": 4.421696574225122, "percentage": 44.22, "elapsed_time": "3:40:23", "remaining_time": "4:38:02", "throughput": 4426.03, "total_tokens": 58526032} {"current_steps": 27110, "total_steps": 61300, "loss": 0.3052, "lr": 3.418405050351674e-05, "epoch": 4.422512234910277, "percentage": 44.23, "elapsed_time": "3:40:25", "remaining_time": "4:37:59", "throughput": 4426.1, "total_tokens": 58537904} {"current_steps": 27115, "total_steps": 61300, "loss": 0.3476, "lr": 3.417742985241205e-05, "epoch": 4.423327895595432, "percentage": 44.23, "elapsed_time": "3:40:27", "remaining_time": "4:37:56", "throughput": 4426.14, "total_tokens": 58548208} {"current_steps": 27120, "total_steps": 61300, "loss": 0.3085, "lr": 3.417080845733831e-05, "epoch": 4.424143556280587, "percentage": 44.24, "elapsed_time": "3:40:30", "remaining_time": "4:37:54", "throughput": 4426.21, "total_tokens": 58559568} {"current_steps": 27125, "total_steps": 61300, "loss": 0.3236, "lr": 3.416418631883231e-05, "epoch": 4.424959216965743, "percentage": 44.25, "elapsed_time": "3:40:32", "remaining_time": "4:37:51", "throughput": 4426.28, "total_tokens": 58570576} {"current_steps": 27130, "total_steps": 61300, "loss": 0.3611, "lr": 3.415756343743088e-05, "epoch": 4.425774877650897, "percentage": 44.26, "elapsed_time": "3:40:34", "remaining_time": "4:37:49", "throughput": 4426.34, "total_tokens": 58581680} {"current_steps": 27135, "total_steps": 61300, "loss": 0.3212, "lr": 3.4150939813670886e-05, "epoch": 4.426590538336052, "percentage": 44.27, "elapsed_time": "3:40:37", "remaining_time": "4:37:46", "throughput": 4426.4, "total_tokens": 58593040} {"current_steps": 27140, "total_steps": 61300, "loss": 0.3629, "lr": 3.414431544808928e-05, "epoch": 4.427406199021207, "percentage": 44.27, "elapsed_time": "3:40:39", "remaining_time": "4:37:43", "throughput": 4426.47, "total_tokens": 58603728} {"current_steps": 27145, "total_steps": 61300, "loss": 0.3022, "lr": 3.413769034122306e-05, "epoch": 4.428221859706362, "percentage": 44.28, "elapsed_time": "3:40:41", "remaining_time": "4:37:41", "throughput": 4426.53, "total_tokens": 58614640} {"current_steps": 27150, "total_steps": 61300, "loss": 0.3628, "lr": 3.41310644936093e-05, "epoch": 4.4290375203915175, "percentage": 44.29, "elapsed_time": "3:40:43", "remaining_time": "4:37:38", "throughput": 4426.58, "total_tokens": 58623536} {"current_steps": 27155, "total_steps": 61300, "loss": 0.3362, "lr": 3.412443790578512e-05, "epoch": 4.429853181076672, "percentage": 44.3, "elapsed_time": "3:40:45", "remaining_time": "4:37:35", "throughput": 4426.63, "total_tokens": 58633648} {"current_steps": 27160, "total_steps": 61300, "loss": 0.3284, "lr": 3.4117810578287704e-05, "epoch": 4.430668841761827, "percentage": 44.31, "elapsed_time": "3:40:47", "remaining_time": "4:37:32", "throughput": 4426.71, "total_tokens": 58644624} {"current_steps": 27165, "total_steps": 61300, "loss": 0.3458, "lr": 3.411118251165431e-05, "epoch": 4.431484502446982, "percentage": 44.31, "elapsed_time": "3:40:50", "remaining_time": "4:37:29", "throughput": 4426.77, "total_tokens": 58655344} {"current_steps": 27170, "total_steps": 61300, "loss": 0.3019, "lr": 3.410455370642221e-05, "epoch": 4.432300163132137, "percentage": 44.32, "elapsed_time": "3:40:52", "remaining_time": "4:37:27", "throughput": 4426.83, "total_tokens": 58666448} {"current_steps": 27175, "total_steps": 61300, "loss": 0.3993, "lr": 3.409792416312881e-05, "epoch": 4.433115823817292, "percentage": 44.33, "elapsed_time": "3:40:54", "remaining_time": "4:37:24", "throughput": 4426.91, "total_tokens": 58678672} {"current_steps": 27180, "total_steps": 61300, "loss": 0.3675, "lr": 3.409129388231151e-05, "epoch": 4.433931484502447, "percentage": 44.34, "elapsed_time": "3:40:57", "remaining_time": "4:37:22", "throughput": 4426.99, "total_tokens": 58690672} {"current_steps": 27185, "total_steps": 61300, "loss": 0.3474, "lr": 3.40846628645078e-05, "epoch": 4.434747145187602, "percentage": 44.35, "elapsed_time": "3:40:59", "remaining_time": "4:37:20", "throughput": 4427.07, "total_tokens": 58702320} {"current_steps": 27190, "total_steps": 61300, "loss": 0.3396, "lr": 3.407803111025522e-05, "epoch": 4.435562805872757, "percentage": 44.36, "elapsed_time": "3:41:02", "remaining_time": "4:37:17", "throughput": 4427.14, "total_tokens": 58714192} {"current_steps": 27195, "total_steps": 61300, "loss": 0.3291, "lr": 3.407139862009138e-05, "epoch": 4.436378466557912, "percentage": 44.36, "elapsed_time": "3:41:04", "remaining_time": "4:37:15", "throughput": 4427.22, "total_tokens": 58725488} {"current_steps": 27200, "total_steps": 61300, "loss": 0.3459, "lr": 3.406476539455394e-05, "epoch": 4.437194127243067, "percentage": 44.37, "elapsed_time": "3:41:06", "remaining_time": "4:37:12", "throughput": 4427.29, "total_tokens": 58736208} {"current_steps": 27205, "total_steps": 61300, "loss": 0.3434, "lr": 3.405813143418062e-05, "epoch": 4.438009787928221, "percentage": 44.38, "elapsed_time": "3:41:09", "remaining_time": "4:37:09", "throughput": 4427.36, "total_tokens": 58746608} {"current_steps": 27210, "total_steps": 61300, "loss": 0.343, "lr": 3.4051496739509216e-05, "epoch": 4.438825448613377, "percentage": 44.39, "elapsed_time": "3:41:11", "remaining_time": "4:37:06", "throughput": 4427.42, "total_tokens": 58756880} {"current_steps": 27215, "total_steps": 61300, "loss": 0.335, "lr": 3.404486131107754e-05, "epoch": 4.439641109298532, "percentage": 44.4, "elapsed_time": "3:41:13", "remaining_time": "4:37:04", "throughput": 4427.49, "total_tokens": 58768080} {"current_steps": 27220, "total_steps": 61300, "loss": 0.3321, "lr": 3.403822514942353e-05, "epoch": 4.440456769983687, "percentage": 44.4, "elapsed_time": "3:41:15", "remaining_time": "4:37:01", "throughput": 4427.55, "total_tokens": 58778896} {"current_steps": 27225, "total_steps": 61300, "loss": 0.3595, "lr": 3.4031588255085126e-05, "epoch": 4.441272430668842, "percentage": 44.41, "elapsed_time": "3:41:18", "remaining_time": "4:36:58", "throughput": 4427.61, "total_tokens": 58790032} {"current_steps": 27230, "total_steps": 61300, "loss": 0.3408, "lr": 3.4024950628600345e-05, "epoch": 4.442088091353996, "percentage": 44.42, "elapsed_time": "3:41:20", "remaining_time": "4:36:56", "throughput": 4427.67, "total_tokens": 58800880} {"current_steps": 27235, "total_steps": 61300, "loss": 0.3458, "lr": 3.401831227050728e-05, "epoch": 4.442903752039152, "percentage": 44.43, "elapsed_time": "3:41:22", "remaining_time": "4:36:53", "throughput": 4427.74, "total_tokens": 58811760} {"current_steps": 27240, "total_steps": 61300, "loss": 0.3459, "lr": 3.401167318134406e-05, "epoch": 4.443719412724307, "percentage": 44.44, "elapsed_time": "3:41:24", "remaining_time": "4:36:50", "throughput": 4427.81, "total_tokens": 58821808} {"current_steps": 27245, "total_steps": 61300, "loss": 0.3358, "lr": 3.400503336164888e-05, "epoch": 4.444535073409462, "percentage": 44.45, "elapsed_time": "3:41:26", "remaining_time": "4:36:47", "throughput": 4427.87, "total_tokens": 58832080} {"current_steps": 27250, "total_steps": 61300, "loss": 0.3368, "lr": 3.3998392811960024e-05, "epoch": 4.445350734094617, "percentage": 44.45, "elapsed_time": "3:41:28", "remaining_time": "4:36:45", "throughput": 4427.95, "total_tokens": 58842480} {"current_steps": 27255, "total_steps": 61300, "loss": 0.331, "lr": 3.399175153281578e-05, "epoch": 4.446166394779771, "percentage": 44.46, "elapsed_time": "3:41:31", "remaining_time": "4:36:42", "throughput": 4428.0, "total_tokens": 58852752} {"current_steps": 27260, "total_steps": 61300, "loss": 0.3579, "lr": 3.3985109524754535e-05, "epoch": 4.446982055464926, "percentage": 44.47, "elapsed_time": "3:41:33", "remaining_time": "4:36:39", "throughput": 4428.06, "total_tokens": 58863312} {"current_steps": 27265, "total_steps": 61300, "loss": 0.3713, "lr": 3.397846678831472e-05, "epoch": 4.447797716150082, "percentage": 44.48, "elapsed_time": "3:41:35", "remaining_time": "4:36:36", "throughput": 4428.11, "total_tokens": 58873104} {"current_steps": 27270, "total_steps": 61300, "loss": 0.3331, "lr": 3.397182332403482e-05, "epoch": 4.448613376835237, "percentage": 44.49, "elapsed_time": "3:41:37", "remaining_time": "4:36:34", "throughput": 4428.19, "total_tokens": 58884624} {"current_steps": 27275, "total_steps": 61300, "loss": 0.363, "lr": 3.3965179132453416e-05, "epoch": 4.4494290375203915, "percentage": 44.49, "elapsed_time": "3:41:39", "remaining_time": "4:36:31", "throughput": 4428.25, "total_tokens": 58894864} {"current_steps": 27280, "total_steps": 61300, "loss": 0.3189, "lr": 3.3958534214109095e-05, "epoch": 4.450244698205546, "percentage": 44.5, "elapsed_time": "3:41:42", "remaining_time": "4:36:28", "throughput": 4428.32, "total_tokens": 58906512} {"current_steps": 27285, "total_steps": 61300, "loss": 0.3256, "lr": 3.395188856954054e-05, "epoch": 4.451060358890701, "percentage": 44.51, "elapsed_time": "3:41:44", "remaining_time": "4:36:26", "throughput": 4428.4, "total_tokens": 58917904} {"current_steps": 27290, "total_steps": 61300, "loss": 0.3194, "lr": 3.394524219928647e-05, "epoch": 4.451876019575856, "percentage": 44.52, "elapsed_time": "3:41:46", "remaining_time": "4:36:23", "throughput": 4428.46, "total_tokens": 58928304} {"current_steps": 27295, "total_steps": 61300, "loss": 0.3608, "lr": 3.3938595103885684e-05, "epoch": 4.452691680261012, "percentage": 44.53, "elapsed_time": "3:41:48", "remaining_time": "4:36:20", "throughput": 4428.53, "total_tokens": 58939056} {"current_steps": 27300, "total_steps": 61300, "loss": 0.3464, "lr": 3.393194728387702e-05, "epoch": 4.4535073409461665, "percentage": 44.54, "elapsed_time": "3:41:51", "remaining_time": "4:36:18", "throughput": 4428.61, "total_tokens": 58950384} {"current_steps": 27305, "total_steps": 61300, "loss": 0.3415, "lr": 3.39252987397994e-05, "epoch": 4.454323001631321, "percentage": 44.54, "elapsed_time": "3:41:53", "remaining_time": "4:36:15", "throughput": 4428.67, "total_tokens": 58959952} {"current_steps": 27310, "total_steps": 61300, "loss": 0.3466, "lr": 3.391864947219177e-05, "epoch": 4.455138662316476, "percentage": 44.55, "elapsed_time": "3:41:55", "remaining_time": "4:36:12", "throughput": 4428.75, "total_tokens": 58970288} {"current_steps": 27315, "total_steps": 61300, "loss": 0.3546, "lr": 3.391199948159315e-05, "epoch": 4.455954323001631, "percentage": 44.56, "elapsed_time": "3:41:57", "remaining_time": "4:36:09", "throughput": 4428.82, "total_tokens": 58981936} {"current_steps": 27320, "total_steps": 61300, "loss": 0.3237, "lr": 3.390534876854265e-05, "epoch": 4.456769983686787, "percentage": 44.57, "elapsed_time": "3:41:59", "remaining_time": "4:36:06", "throughput": 4428.89, "total_tokens": 58992432} {"current_steps": 27325, "total_steps": 61300, "loss": 0.3246, "lr": 3.389869733357939e-05, "epoch": 4.4575856443719415, "percentage": 44.58, "elapsed_time": "3:42:02", "remaining_time": "4:36:04", "throughput": 4428.96, "total_tokens": 59002832} {"current_steps": 27330, "total_steps": 61300, "loss": 0.3355, "lr": 3.389204517724256e-05, "epoch": 4.458401305057096, "percentage": 44.58, "elapsed_time": "3:42:04", "remaining_time": "4:36:01", "throughput": 4429.03, "total_tokens": 59013936} {"current_steps": 27335, "total_steps": 61300, "loss": 0.3179, "lr": 3.388539230007145e-05, "epoch": 4.459216965742251, "percentage": 44.59, "elapsed_time": "3:42:06", "remaining_time": "4:35:58", "throughput": 4429.09, "total_tokens": 59023440} {"current_steps": 27340, "total_steps": 61300, "loss": 0.2714, "lr": 3.387873870260534e-05, "epoch": 4.460032626427406, "percentage": 44.6, "elapsed_time": "3:42:08", "remaining_time": "4:35:55", "throughput": 4429.17, "total_tokens": 59034224} {"current_steps": 27345, "total_steps": 61300, "loss": 0.3562, "lr": 3.3872084385383626e-05, "epoch": 4.460848287112561, "percentage": 44.61, "elapsed_time": "3:42:10", "remaining_time": "4:35:52", "throughput": 4429.22, "total_tokens": 59044016} {"current_steps": 27350, "total_steps": 61300, "loss": 0.3689, "lr": 3.3865429348945735e-05, "epoch": 4.4616639477977165, "percentage": 44.62, "elapsed_time": "3:42:12", "remaining_time": "4:35:49", "throughput": 4429.27, "total_tokens": 59053648} {"current_steps": 27355, "total_steps": 61300, "loss": 0.3671, "lr": 3.385877359383116e-05, "epoch": 4.462479608482871, "percentage": 44.62, "elapsed_time": "3:42:14", "remaining_time": "4:35:47", "throughput": 4429.34, "total_tokens": 59064080} {"current_steps": 27360, "total_steps": 61300, "loss": 0.3336, "lr": 3.385211712057945e-05, "epoch": 4.463295269168026, "percentage": 44.63, "elapsed_time": "3:42:16", "remaining_time": "4:35:44", "throughput": 4429.41, "total_tokens": 59074672} {"current_steps": 27365, "total_steps": 61300, "loss": 0.33, "lr": 3.384545992973021e-05, "epoch": 4.464110929853181, "percentage": 44.64, "elapsed_time": "3:42:19", "remaining_time": "4:35:41", "throughput": 4429.46, "total_tokens": 59084784} {"current_steps": 27370, "total_steps": 61300, "loss": 0.3104, "lr": 3.383880202182311e-05, "epoch": 4.464926590538336, "percentage": 44.65, "elapsed_time": "3:42:21", "remaining_time": "4:35:38", "throughput": 4429.54, "total_tokens": 59095504} {"current_steps": 27375, "total_steps": 61300, "loss": 0.3371, "lr": 3.3832143397397855e-05, "epoch": 4.465742251223491, "percentage": 44.66, "elapsed_time": "3:42:23", "remaining_time": "4:35:35", "throughput": 4429.6, "total_tokens": 59105616} {"current_steps": 27380, "total_steps": 61300, "loss": 0.3482, "lr": 3.382548405699426e-05, "epoch": 4.466557911908646, "percentage": 44.67, "elapsed_time": "3:42:25", "remaining_time": "4:35:32", "throughput": 4429.63, "total_tokens": 59114576} {"current_steps": 27385, "total_steps": 61300, "loss": 0.3269, "lr": 3.3818824001152135e-05, "epoch": 4.467373572593801, "percentage": 44.67, "elapsed_time": "3:42:27", "remaining_time": "4:35:30", "throughput": 4429.71, "total_tokens": 59124976} {"current_steps": 27390, "total_steps": 61300, "loss": 0.391, "lr": 3.38121632304114e-05, "epoch": 4.468189233278956, "percentage": 44.68, "elapsed_time": "3:42:29", "remaining_time": "4:35:27", "throughput": 4429.78, "total_tokens": 59136336} {"current_steps": 27395, "total_steps": 61300, "loss": 0.3253, "lr": 3.3805501745312e-05, "epoch": 4.469004893964111, "percentage": 44.69, "elapsed_time": "3:42:31", "remaining_time": "4:35:24", "throughput": 4429.85, "total_tokens": 59146960} {"current_steps": 27400, "total_steps": 61300, "loss": 0.3361, "lr": 3.379883954639394e-05, "epoch": 4.4698205546492655, "percentage": 44.7, "elapsed_time": "3:42:34", "remaining_time": "4:35:22", "throughput": 4429.91, "total_tokens": 59158096} {"current_steps": 27405, "total_steps": 61300, "loss": 0.3326, "lr": 3.379217663419731e-05, "epoch": 4.470636215334421, "percentage": 44.71, "elapsed_time": "3:42:36", "remaining_time": "4:35:19", "throughput": 4429.97, "total_tokens": 59168912} {"current_steps": 27410, "total_steps": 61300, "loss": 0.3218, "lr": 3.378551300926222e-05, "epoch": 4.471451876019576, "percentage": 44.71, "elapsed_time": "3:42:38", "remaining_time": "4:35:16", "throughput": 4430.04, "total_tokens": 59179728} {"current_steps": 27415, "total_steps": 61300, "loss": 0.3371, "lr": 3.3778848672128884e-05, "epoch": 4.472267536704731, "percentage": 44.72, "elapsed_time": "3:42:41", "remaining_time": "4:35:14", "throughput": 4430.11, "total_tokens": 59191312} {"current_steps": 27420, "total_steps": 61300, "loss": 0.3781, "lr": 3.3772183623337524e-05, "epoch": 4.473083197389886, "percentage": 44.73, "elapsed_time": "3:42:43", "remaining_time": "4:35:11", "throughput": 4430.18, "total_tokens": 59202352} {"current_steps": 27425, "total_steps": 61300, "loss": 0.3329, "lr": 3.3765517863428456e-05, "epoch": 4.4738988580750405, "percentage": 44.74, "elapsed_time": "3:42:45", "remaining_time": "4:35:08", "throughput": 4430.24, "total_tokens": 59212560} {"current_steps": 27430, "total_steps": 61300, "loss": 0.3462, "lr": 3.375885139294202e-05, "epoch": 4.474714518760196, "percentage": 44.75, "elapsed_time": "3:42:47", "remaining_time": "4:35:05", "throughput": 4430.29, "total_tokens": 59221968} {"current_steps": 27435, "total_steps": 61300, "loss": 0.3614, "lr": 3.375218421241866e-05, "epoch": 4.475530179445351, "percentage": 44.76, "elapsed_time": "3:42:49", "remaining_time": "4:35:03", "throughput": 4430.36, "total_tokens": 59232848} {"current_steps": 27440, "total_steps": 61300, "loss": 0.3713, "lr": 3.3745516322398834e-05, "epoch": 4.476345840130506, "percentage": 44.76, "elapsed_time": "3:42:52", "remaining_time": "4:35:00", "throughput": 4430.42, "total_tokens": 59243984} {"current_steps": 27445, "total_steps": 61300, "loss": 0.355, "lr": 3.373884772342308e-05, "epoch": 4.477161500815661, "percentage": 44.77, "elapsed_time": "3:42:54", "remaining_time": "4:34:57", "throughput": 4430.49, "total_tokens": 59253840} {"current_steps": 27450, "total_steps": 61300, "loss": 0.3481, "lr": 3.3732178416032e-05, "epoch": 4.4779771615008155, "percentage": 44.78, "elapsed_time": "3:42:56", "remaining_time": "4:34:55", "throughput": 4430.54, "total_tokens": 59264400} {"current_steps": 27455, "total_steps": 61300, "loss": 0.3523, "lr": 3.372550840076622e-05, "epoch": 4.47879282218597, "percentage": 44.79, "elapsed_time": "3:42:58", "remaining_time": "4:34:52", "throughput": 4430.61, "total_tokens": 59275728} {"current_steps": 27460, "total_steps": 61300, "loss": 0.322, "lr": 3.371883767816646e-05, "epoch": 4.479608482871126, "percentage": 44.8, "elapsed_time": "3:43:01", "remaining_time": "4:34:49", "throughput": 4430.67, "total_tokens": 59286896} {"current_steps": 27465, "total_steps": 61300, "loss": 0.2997, "lr": 3.371216624877348e-05, "epoch": 4.480424143556281, "percentage": 44.8, "elapsed_time": "3:43:03", "remaining_time": "4:34:47", "throughput": 4430.74, "total_tokens": 59297808} {"current_steps": 27470, "total_steps": 61300, "loss": 0.3366, "lr": 3.370549411312809e-05, "epoch": 4.481239804241436, "percentage": 44.81, "elapsed_time": "3:43:05", "remaining_time": "4:34:44", "throughput": 4430.81, "total_tokens": 59308752} {"current_steps": 27475, "total_steps": 61300, "loss": 0.3142, "lr": 3.3698821271771186e-05, "epoch": 4.4820554649265905, "percentage": 44.82, "elapsed_time": "3:43:07", "remaining_time": "4:34:41", "throughput": 4430.86, "total_tokens": 59318320} {"current_steps": 27480, "total_steps": 61300, "loss": 0.3383, "lr": 3.369214772524369e-05, "epoch": 4.482871125611745, "percentage": 44.83, "elapsed_time": "3:43:09", "remaining_time": "4:34:38", "throughput": 4430.92, "total_tokens": 59328464} {"current_steps": 27485, "total_steps": 61300, "loss": 0.3312, "lr": 3.3685473474086584e-05, "epoch": 4.4836867862969, "percentage": 44.84, "elapsed_time": "3:43:11", "remaining_time": "4:34:35", "throughput": 4430.98, "total_tokens": 59338000} {"current_steps": 27490, "total_steps": 61300, "loss": 0.3672, "lr": 3.3678798518840946e-05, "epoch": 4.484502446982056, "percentage": 44.85, "elapsed_time": "3:43:13", "remaining_time": "4:34:32", "throughput": 4431.03, "total_tokens": 59347792} {"current_steps": 27495, "total_steps": 61300, "loss": 0.3375, "lr": 3.367212286004786e-05, "epoch": 4.485318107667211, "percentage": 44.85, "elapsed_time": "3:43:15", "remaining_time": "4:34:29", "throughput": 4431.09, "total_tokens": 59357648} {"current_steps": 27500, "total_steps": 61300, "loss": 0.3446, "lr": 3.366544649824849e-05, "epoch": 4.486133768352365, "percentage": 44.86, "elapsed_time": "3:43:17", "remaining_time": "4:34:27", "throughput": 4431.16, "total_tokens": 59367760} {"current_steps": 27505, "total_steps": 61300, "loss": 0.3617, "lr": 3.365876943398406e-05, "epoch": 4.48694942903752, "percentage": 44.87, "elapsed_time": "3:43:20", "remaining_time": "4:34:24", "throughput": 4431.21, "total_tokens": 59378416} {"current_steps": 27510, "total_steps": 61300, "loss": 0.319, "lr": 3.365209166779585e-05, "epoch": 4.487765089722675, "percentage": 44.88, "elapsed_time": "3:43:22", "remaining_time": "4:34:21", "throughput": 4431.27, "total_tokens": 59388944} {"current_steps": 27515, "total_steps": 61300, "loss": 0.3641, "lr": 3.3645413200225175e-05, "epoch": 4.488580750407831, "percentage": 44.89, "elapsed_time": "3:43:24", "remaining_time": "4:34:18", "throughput": 4431.32, "total_tokens": 59397776} {"current_steps": 27520, "total_steps": 61300, "loss": 0.293, "lr": 3.363873403181346e-05, "epoch": 4.489396411092986, "percentage": 44.89, "elapsed_time": "3:43:26", "remaining_time": "4:34:15", "throughput": 4431.37, "total_tokens": 59408464} {"current_steps": 27525, "total_steps": 61300, "loss": 0.3336, "lr": 3.363205416310212e-05, "epoch": 4.49021207177814, "percentage": 44.9, "elapsed_time": "3:43:28", "remaining_time": "4:34:13", "throughput": 4431.43, "total_tokens": 59419888} {"current_steps": 27530, "total_steps": 61300, "loss": 0.3457, "lr": 3.362537359463267e-05, "epoch": 4.491027732463295, "percentage": 44.91, "elapsed_time": "3:43:30", "remaining_time": "4:34:10", "throughput": 4431.49, "total_tokens": 59429712} {"current_steps": 27535, "total_steps": 61300, "loss": 0.3546, "lr": 3.361869232694666e-05, "epoch": 4.49184339314845, "percentage": 44.92, "elapsed_time": "3:43:33", "remaining_time": "4:34:07", "throughput": 4431.55, "total_tokens": 59440688} {"current_steps": 27540, "total_steps": 61300, "loss": 0.3325, "lr": 3.3612010360585744e-05, "epoch": 4.492659053833605, "percentage": 44.93, "elapsed_time": "3:43:35", "remaining_time": "4:34:05", "throughput": 4431.61, "total_tokens": 59451120} {"current_steps": 27545, "total_steps": 61300, "loss": 0.3169, "lr": 3.360532769609156e-05, "epoch": 4.493474714518761, "percentage": 44.93, "elapsed_time": "3:43:37", "remaining_time": "4:34:02", "throughput": 4431.68, "total_tokens": 59461776} {"current_steps": 27550, "total_steps": 61300, "loss": 0.3275, "lr": 3.359864433400585e-05, "epoch": 4.494290375203915, "percentage": 44.94, "elapsed_time": "3:43:39", "remaining_time": "4:33:59", "throughput": 4431.74, "total_tokens": 59472464} {"current_steps": 27555, "total_steps": 61300, "loss": 0.372, "lr": 3.3591960274870394e-05, "epoch": 4.49510603588907, "percentage": 44.95, "elapsed_time": "3:43:41", "remaining_time": "4:33:56", "throughput": 4431.8, "total_tokens": 59482704} {"current_steps": 27560, "total_steps": 61300, "loss": 0.3241, "lr": 3.3585275519227046e-05, "epoch": 4.495921696574225, "percentage": 44.96, "elapsed_time": "3:43:43", "remaining_time": "4:33:54", "throughput": 4431.85, "total_tokens": 59492976} {"current_steps": 27565, "total_steps": 61300, "loss": 0.3544, "lr": 3.357859006761771e-05, "epoch": 4.49673735725938, "percentage": 44.97, "elapsed_time": "3:43:46", "remaining_time": "4:33:51", "throughput": 4431.9, "total_tokens": 59503344} {"current_steps": 27570, "total_steps": 61300, "loss": 0.3318, "lr": 3.357190392058433e-05, "epoch": 4.497553017944535, "percentage": 44.98, "elapsed_time": "3:43:48", "remaining_time": "4:33:48", "throughput": 4431.98, "total_tokens": 59514896} {"current_steps": 27575, "total_steps": 61300, "loss": 0.3108, "lr": 3.356521707866893e-05, "epoch": 4.49836867862969, "percentage": 44.98, "elapsed_time": "3:43:51", "remaining_time": "4:33:46", "throughput": 4432.05, "total_tokens": 59527408} {"current_steps": 27580, "total_steps": 61300, "loss": 0.3541, "lr": 3.3558529542413574e-05, "epoch": 4.499184339314845, "percentage": 44.99, "elapsed_time": "3:43:53", "remaining_time": "4:33:43", "throughput": 4432.1, "total_tokens": 59537520} {"current_steps": 27585, "total_steps": 61300, "loss": 0.3376, "lr": 3.3551841312360386e-05, "epoch": 4.5, "percentage": 45.0, "elapsed_time": "3:43:55", "remaining_time": "4:33:41", "throughput": 4432.17, "total_tokens": 59549072} {"current_steps": 27585, "total_steps": 61300, "eval_loss": 0.34551090002059937, "epoch": 4.5, "percentage": 45.0, "elapsed_time": "3:46:07", "remaining_time": "4:36:22", "throughput": 4389.1, "total_tokens": 59549072} {"current_steps": 27590, "total_steps": 61300, "loss": 0.3262, "lr": 3.354515238905155e-05, "epoch": 4.500815660685155, "percentage": 45.01, "elapsed_time": "3:46:10", "remaining_time": "4:36:20", "throughput": 4388.84, "total_tokens": 59559824} {"current_steps": 27595, "total_steps": 61300, "loss": 0.3577, "lr": 3.35384627730293e-05, "epoch": 4.50163132137031, "percentage": 45.02, "elapsed_time": "3:46:12", "remaining_time": "4:36:18", "throughput": 4388.9, "total_tokens": 59569776} {"current_steps": 27600, "total_steps": 61300, "loss": 0.3414, "lr": 3.353177246483594e-05, "epoch": 4.502446982055465, "percentage": 45.02, "elapsed_time": "3:46:14", "remaining_time": "4:36:15", "throughput": 4388.95, "total_tokens": 59579184} {"current_steps": 27605, "total_steps": 61300, "loss": 0.3421, "lr": 3.352508146501381e-05, "epoch": 4.50326264274062, "percentage": 45.03, "elapsed_time": "3:46:17", "remaining_time": "4:36:12", "throughput": 4389.02, "total_tokens": 59590416} {"current_steps": 27610, "total_steps": 61300, "loss": 0.3154, "lr": 3.3518389774105326e-05, "epoch": 4.504078303425775, "percentage": 45.04, "elapsed_time": "3:46:19", "remaining_time": "4:36:09", "throughput": 4389.09, "total_tokens": 59601136} {"current_steps": 27615, "total_steps": 61300, "loss": 0.3147, "lr": 3.351169739265294e-05, "epoch": 4.50489396411093, "percentage": 45.05, "elapsed_time": "3:46:21", "remaining_time": "4:36:07", "throughput": 4389.18, "total_tokens": 59612816} {"current_steps": 27620, "total_steps": 61300, "loss": 0.3184, "lr": 3.350500432119917e-05, "epoch": 4.505709624796085, "percentage": 45.06, "elapsed_time": "3:46:24", "remaining_time": "4:36:04", "throughput": 4389.24, "total_tokens": 59624080} {"current_steps": 27625, "total_steps": 61300, "loss": 0.3418, "lr": 3.3498310560286604e-05, "epoch": 4.506525285481239, "percentage": 45.07, "elapsed_time": "3:46:26", "remaining_time": "4:36:01", "throughput": 4389.31, "total_tokens": 59634608} {"current_steps": 27630, "total_steps": 61300, "loss": 0.3455, "lr": 3.349161611045786e-05, "epoch": 4.507340946166395, "percentage": 45.07, "elapsed_time": "3:46:28", "remaining_time": "4:35:59", "throughput": 4389.37, "total_tokens": 59645200} {"current_steps": 27635, "total_steps": 61300, "loss": 0.327, "lr": 3.348492097225563e-05, "epoch": 4.50815660685155, "percentage": 45.08, "elapsed_time": "3:46:30", "remaining_time": "4:35:55", "throughput": 4389.44, "total_tokens": 59654736} {"current_steps": 27640, "total_steps": 61300, "loss": 0.3394, "lr": 3.347822514622265e-05, "epoch": 4.508972267536705, "percentage": 45.09, "elapsed_time": "3:46:32", "remaining_time": "4:35:53", "throughput": 4389.5, "total_tokens": 59664624} {"current_steps": 27645, "total_steps": 61300, "loss": 0.3311, "lr": 3.347152863290173e-05, "epoch": 4.50978792822186, "percentage": 45.1, "elapsed_time": "3:46:34", "remaining_time": "4:35:50", "throughput": 4389.55, "total_tokens": 59674480} {"current_steps": 27650, "total_steps": 61300, "loss": 0.3331, "lr": 3.346483143283571e-05, "epoch": 4.510603588907014, "percentage": 45.11, "elapsed_time": "3:46:36", "remaining_time": "4:35:47", "throughput": 4389.62, "total_tokens": 59685392} {"current_steps": 27655, "total_steps": 61300, "loss": 0.356, "lr": 3.3458133546567506e-05, "epoch": 4.511419249592169, "percentage": 45.11, "elapsed_time": "3:46:39", "remaining_time": "4:35:44", "throughput": 4389.68, "total_tokens": 59695280} {"current_steps": 27660, "total_steps": 61300, "loss": 0.3431, "lr": 3.345143497464007e-05, "epoch": 4.512234910277325, "percentage": 45.12, "elapsed_time": "3:46:41", "remaining_time": "4:35:41", "throughput": 4389.75, "total_tokens": 59705872} {"current_steps": 27665, "total_steps": 61300, "loss": 0.3195, "lr": 3.344473571759645e-05, "epoch": 4.51305057096248, "percentage": 45.13, "elapsed_time": "3:46:43", "remaining_time": "4:35:39", "throughput": 4389.83, "total_tokens": 59717936} {"current_steps": 27670, "total_steps": 61300, "loss": 0.3294, "lr": 3.343803577597969e-05, "epoch": 4.513866231647635, "percentage": 45.14, "elapsed_time": "3:46:45", "remaining_time": "4:35:36", "throughput": 4389.89, "total_tokens": 59728144} {"current_steps": 27675, "total_steps": 61300, "loss": 0.3382, "lr": 3.343133515033295e-05, "epoch": 4.514681892332789, "percentage": 45.15, "elapsed_time": "3:46:48", "remaining_time": "4:35:33", "throughput": 4389.97, "total_tokens": 59739888} {"current_steps": 27680, "total_steps": 61300, "loss": 0.3391, "lr": 3.342463384119939e-05, "epoch": 4.515497553017944, "percentage": 45.15, "elapsed_time": "3:46:50", "remaining_time": "4:35:31", "throughput": 4390.05, "total_tokens": 59750320} {"current_steps": 27685, "total_steps": 61300, "loss": 0.327, "lr": 3.3417931849122275e-05, "epoch": 4.5163132137031, "percentage": 45.16, "elapsed_time": "3:46:52", "remaining_time": "4:35:28", "throughput": 4390.12, "total_tokens": 59761520} {"current_steps": 27690, "total_steps": 61300, "loss": 0.3472, "lr": 3.341122917464489e-05, "epoch": 4.517128874388255, "percentage": 45.17, "elapsed_time": "3:46:54", "remaining_time": "4:35:25", "throughput": 4390.19, "total_tokens": 59771632} {"current_steps": 27695, "total_steps": 61300, "loss": 0.3823, "lr": 3.340452581831057e-05, "epoch": 4.5179445350734095, "percentage": 45.18, "elapsed_time": "3:46:56", "remaining_time": "4:35:22", "throughput": 4390.26, "total_tokens": 59781744} {"current_steps": 27700, "total_steps": 61300, "loss": 0.3164, "lr": 3.3397821780662764e-05, "epoch": 4.518760195758564, "percentage": 45.19, "elapsed_time": "3:46:59", "remaining_time": "4:35:19", "throughput": 4390.32, "total_tokens": 59791760} {"current_steps": 27705, "total_steps": 61300, "loss": 0.3391, "lr": 3.3391117062244913e-05, "epoch": 4.519575856443719, "percentage": 45.2, "elapsed_time": "3:47:01", "remaining_time": "4:35:16", "throughput": 4390.37, "total_tokens": 59801872} {"current_steps": 27710, "total_steps": 61300, "loss": 0.373, "lr": 3.338441166360054e-05, "epoch": 4.520391517128875, "percentage": 45.2, "elapsed_time": "3:47:03", "remaining_time": "4:35:13", "throughput": 4390.44, "total_tokens": 59811152} {"current_steps": 27715, "total_steps": 61300, "loss": 0.3447, "lr": 3.33777055852732e-05, "epoch": 4.52120717781403, "percentage": 45.21, "elapsed_time": "3:47:05", "remaining_time": "4:35:11", "throughput": 4390.48, "total_tokens": 59821264} {"current_steps": 27720, "total_steps": 61300, "loss": 0.3359, "lr": 3.3370998827806543e-05, "epoch": 4.5220228384991845, "percentage": 45.22, "elapsed_time": "3:47:07", "remaining_time": "4:35:08", "throughput": 4390.55, "total_tokens": 59832336} {"current_steps": 27725, "total_steps": 61300, "loss": 0.2931, "lr": 3.336429139174425e-05, "epoch": 4.522838499184339, "percentage": 45.23, "elapsed_time": "3:47:09", "remaining_time": "4:35:05", "throughput": 4390.61, "total_tokens": 59842288} {"current_steps": 27730, "total_steps": 61300, "loss": 0.3429, "lr": 3.335758327763006e-05, "epoch": 4.523654159869494, "percentage": 45.24, "elapsed_time": "3:47:11", "remaining_time": "4:35:02", "throughput": 4390.67, "total_tokens": 59852912} {"current_steps": 27735, "total_steps": 61300, "loss": 0.3308, "lr": 3.335087448600776e-05, "epoch": 4.524469820554649, "percentage": 45.24, "elapsed_time": "3:47:13", "remaining_time": "4:34:59", "throughput": 4390.74, "total_tokens": 59863280} {"current_steps": 27740, "total_steps": 61300, "loss": 0.3473, "lr": 3.33441650174212e-05, "epoch": 4.525285481239804, "percentage": 45.25, "elapsed_time": "3:47:16", "remaining_time": "4:34:57", "throughput": 4390.81, "total_tokens": 59874288} {"current_steps": 27745, "total_steps": 61300, "loss": 0.3473, "lr": 3.3337454872414294e-05, "epoch": 4.5261011419249595, "percentage": 45.26, "elapsed_time": "3:47:18", "remaining_time": "4:34:54", "throughput": 4390.89, "total_tokens": 59886000} {"current_steps": 27750, "total_steps": 61300, "loss": 0.3538, "lr": 3.333074405153098e-05, "epoch": 4.526916802610114, "percentage": 45.27, "elapsed_time": "3:47:20", "remaining_time": "4:34:51", "throughput": 4390.95, "total_tokens": 59896432} {"current_steps": 27755, "total_steps": 61300, "loss": 0.3628, "lr": 3.332403255531529e-05, "epoch": 4.527732463295269, "percentage": 45.28, "elapsed_time": "3:47:23", "remaining_time": "4:34:49", "throughput": 4391.02, "total_tokens": 59906704} {"current_steps": 27760, "total_steps": 61300, "loss": 0.3403, "lr": 3.331732038431129e-05, "epoch": 4.528548123980424, "percentage": 45.29, "elapsed_time": "3:47:25", "remaining_time": "4:34:46", "throughput": 4391.08, "total_tokens": 59917392} {"current_steps": 27765, "total_steps": 61300, "loss": 0.338, "lr": 3.3310607539063096e-05, "epoch": 4.529363784665579, "percentage": 45.29, "elapsed_time": "3:47:27", "remaining_time": "4:34:43", "throughput": 4391.14, "total_tokens": 59927984} {"current_steps": 27770, "total_steps": 61300, "loss": 0.3359, "lr": 3.3303894020114886e-05, "epoch": 4.5301794453507345, "percentage": 45.3, "elapsed_time": "3:47:29", "remaining_time": "4:34:40", "throughput": 4391.19, "total_tokens": 59938160} {"current_steps": 27775, "total_steps": 61300, "loss": 0.3501, "lr": 3.329717982801089e-05, "epoch": 4.530995106035889, "percentage": 45.31, "elapsed_time": "3:47:32", "remaining_time": "4:34:38", "throughput": 4391.28, "total_tokens": 59950000} {"current_steps": 27780, "total_steps": 61300, "loss": 0.3485, "lr": 3.32904649632954e-05, "epoch": 4.531810766721044, "percentage": 45.32, "elapsed_time": "3:47:34", "remaining_time": "4:34:35", "throughput": 4391.36, "total_tokens": 59960720} {"current_steps": 27785, "total_steps": 61300, "loss": 0.3167, "lr": 3.328374942651275e-05, "epoch": 4.532626427406199, "percentage": 45.33, "elapsed_time": "3:47:36", "remaining_time": "4:34:32", "throughput": 4391.42, "total_tokens": 59970864} {"current_steps": 27790, "total_steps": 61300, "loss": 0.3749, "lr": 3.3277033218207346e-05, "epoch": 4.533442088091354, "percentage": 45.33, "elapsed_time": "3:47:38", "remaining_time": "4:34:30", "throughput": 4391.49, "total_tokens": 59982256} {"current_steps": 27795, "total_steps": 61300, "loss": 0.3656, "lr": 3.327031633892363e-05, "epoch": 4.5342577487765094, "percentage": 45.34, "elapsed_time": "3:47:41", "remaining_time": "4:34:27", "throughput": 4391.57, "total_tokens": 59993584} {"current_steps": 27800, "total_steps": 61300, "loss": 0.3153, "lr": 3.32635987892061e-05, "epoch": 4.535073409461664, "percentage": 45.35, "elapsed_time": "3:47:43", "remaining_time": "4:34:24", "throughput": 4391.64, "total_tokens": 60004720} {"current_steps": 27805, "total_steps": 61300, "loss": 0.342, "lr": 3.3256880569599335e-05, "epoch": 4.535889070146819, "percentage": 45.36, "elapsed_time": "3:47:45", "remaining_time": "4:34:22", "throughput": 4391.69, "total_tokens": 60015120} {"current_steps": 27810, "total_steps": 61300, "loss": 0.3397, "lr": 3.325016168064794e-05, "epoch": 4.536704730831974, "percentage": 45.37, "elapsed_time": "3:47:47", "remaining_time": "4:34:19", "throughput": 4391.76, "total_tokens": 60024752} {"current_steps": 27815, "total_steps": 61300, "loss": 0.324, "lr": 3.324344212289657e-05, "epoch": 4.537520391517129, "percentage": 45.38, "elapsed_time": "3:47:50", "remaining_time": "4:34:16", "throughput": 4391.84, "total_tokens": 60037072} {"current_steps": 27820, "total_steps": 61300, "loss": 0.3186, "lr": 3.3236721896889954e-05, "epoch": 4.5383360522022835, "percentage": 45.38, "elapsed_time": "3:47:52", "remaining_time": "4:34:14", "throughput": 4391.92, "total_tokens": 60048144} {"current_steps": 27825, "total_steps": 61300, "loss": 0.3698, "lr": 3.323000100317287e-05, "epoch": 4.539151712887438, "percentage": 45.39, "elapsed_time": "3:47:54", "remaining_time": "4:34:11", "throughput": 4391.98, "total_tokens": 60058544} {"current_steps": 27830, "total_steps": 61300, "loss": 0.3924, "lr": 3.3223279442290146e-05, "epoch": 4.539967373572594, "percentage": 45.4, "elapsed_time": "3:47:56", "remaining_time": "4:34:08", "throughput": 4392.04, "total_tokens": 60068688} {"current_steps": 27835, "total_steps": 61300, "loss": 0.3007, "lr": 3.321655721478667e-05, "epoch": 4.540783034257749, "percentage": 45.41, "elapsed_time": "3:47:58", "remaining_time": "4:34:05", "throughput": 4392.12, "total_tokens": 60079664} {"current_steps": 27840, "total_steps": 61300, "loss": 0.354, "lr": 3.320983432120737e-05, "epoch": 4.541598694942904, "percentage": 45.42, "elapsed_time": "3:48:00", "remaining_time": "4:34:02", "throughput": 4392.18, "total_tokens": 60089296} {"current_steps": 27845, "total_steps": 61300, "loss": 0.3578, "lr": 3.320311076209724e-05, "epoch": 4.5424143556280585, "percentage": 45.42, "elapsed_time": "3:48:03", "remaining_time": "4:33:59", "throughput": 4392.24, "total_tokens": 60099568} {"current_steps": 27850, "total_steps": 61300, "loss": 0.3615, "lr": 3.3196386538001346e-05, "epoch": 4.543230016313213, "percentage": 45.43, "elapsed_time": "3:48:05", "remaining_time": "4:33:57", "throughput": 4392.31, "total_tokens": 60110160} {"current_steps": 27855, "total_steps": 61300, "loss": 0.3741, "lr": 3.3189661649464754e-05, "epoch": 4.544045676998369, "percentage": 45.44, "elapsed_time": "3:48:07", "remaining_time": "4:33:54", "throughput": 4392.38, "total_tokens": 60120880} {"current_steps": 27860, "total_steps": 61300, "loss": 0.3332, "lr": 3.318293609703264e-05, "epoch": 4.544861337683524, "percentage": 45.45, "elapsed_time": "3:48:09", "remaining_time": "4:33:51", "throughput": 4392.45, "total_tokens": 60132336} {"current_steps": 27865, "total_steps": 61300, "loss": 0.3329, "lr": 3.3176209881250206e-05, "epoch": 4.545676998368679, "percentage": 45.46, "elapsed_time": "3:48:12", "remaining_time": "4:33:49", "throughput": 4392.51, "total_tokens": 60142608} {"current_steps": 27870, "total_steps": 61300, "loss": 0.3469, "lr": 3.3169483002662714e-05, "epoch": 4.5464926590538335, "percentage": 45.46, "elapsed_time": "3:48:14", "remaining_time": "4:33:46", "throughput": 4392.58, "total_tokens": 60153744} {"current_steps": 27875, "total_steps": 61300, "loss": 0.3254, "lr": 3.316275546181548e-05, "epoch": 4.547308319738988, "percentage": 45.47, "elapsed_time": "3:48:17", "remaining_time": "4:33:44", "throughput": 4392.65, "total_tokens": 60166288} {"current_steps": 27880, "total_steps": 61300, "loss": 0.364, "lr": 3.315602725925387e-05, "epoch": 4.548123980424144, "percentage": 45.48, "elapsed_time": "3:48:19", "remaining_time": "4:33:41", "throughput": 4392.71, "total_tokens": 60176208} {"current_steps": 27885, "total_steps": 61300, "loss": 0.3265, "lr": 3.314929839552331e-05, "epoch": 4.548939641109299, "percentage": 45.49, "elapsed_time": "3:48:21", "remaining_time": "4:33:38", "throughput": 4392.77, "total_tokens": 60187088} {"current_steps": 27890, "total_steps": 61300, "loss": 0.3521, "lr": 3.314256887116927e-05, "epoch": 4.549755301794454, "percentage": 45.5, "elapsed_time": "3:48:23", "remaining_time": "4:33:35", "throughput": 4392.83, "total_tokens": 60197488} {"current_steps": 27895, "total_steps": 61300, "loss": 0.3765, "lr": 3.313583868673728e-05, "epoch": 4.5505709624796085, "percentage": 45.51, "elapsed_time": "3:48:25", "remaining_time": "4:33:33", "throughput": 4392.9, "total_tokens": 60208816} {"current_steps": 27900, "total_steps": 61300, "loss": 0.3507, "lr": 3.312910784277293e-05, "epoch": 4.551386623164763, "percentage": 45.51, "elapsed_time": "3:48:28", "remaining_time": "4:33:30", "throughput": 4392.97, "total_tokens": 60219728} {"current_steps": 27905, "total_steps": 61300, "loss": 0.3269, "lr": 3.312237633982185e-05, "epoch": 4.552202283849918, "percentage": 45.52, "elapsed_time": "3:48:30", "remaining_time": "4:33:27", "throughput": 4393.05, "total_tokens": 60230288} {"current_steps": 27910, "total_steps": 61300, "loss": 0.3665, "lr": 3.3115644178429725e-05, "epoch": 4.553017944535073, "percentage": 45.53, "elapsed_time": "3:48:32", "remaining_time": "4:33:25", "throughput": 4393.13, "total_tokens": 60242384} {"current_steps": 27915, "total_steps": 61300, "loss": 0.3365, "lr": 3.310891135914231e-05, "epoch": 4.553833605220229, "percentage": 45.54, "elapsed_time": "3:48:35", "remaining_time": "4:33:22", "throughput": 4393.2, "total_tokens": 60253360} {"current_steps": 27920, "total_steps": 61300, "loss": 0.3254, "lr": 3.31021778825054e-05, "epoch": 4.554649265905383, "percentage": 45.55, "elapsed_time": "3:48:37", "remaining_time": "4:33:19", "throughput": 4393.27, "total_tokens": 60263440} {"current_steps": 27925, "total_steps": 61300, "loss": 0.3404, "lr": 3.309544374906484e-05, "epoch": 4.555464926590538, "percentage": 45.55, "elapsed_time": "3:48:39", "remaining_time": "4:33:16", "throughput": 4393.33, "total_tokens": 60273392} {"current_steps": 27930, "total_steps": 61300, "loss": 0.3477, "lr": 3.308870895936652e-05, "epoch": 4.556280587275693, "percentage": 45.56, "elapsed_time": "3:48:41", "remaining_time": "4:33:14", "throughput": 4393.41, "total_tokens": 60285424} {"current_steps": 27935, "total_steps": 61300, "loss": 0.334, "lr": 3.308197351395643e-05, "epoch": 4.557096247960848, "percentage": 45.57, "elapsed_time": "3:48:43", "remaining_time": "4:33:11", "throughput": 4393.47, "total_tokens": 60295248} {"current_steps": 27940, "total_steps": 61300, "loss": 0.3637, "lr": 3.3075237413380545e-05, "epoch": 4.557911908646004, "percentage": 45.58, "elapsed_time": "3:48:46", "remaining_time": "4:33:08", "throughput": 4393.53, "total_tokens": 60306320} {"current_steps": 27945, "total_steps": 61300, "loss": 0.3481, "lr": 3.306850065818494e-05, "epoch": 4.558727569331158, "percentage": 45.59, "elapsed_time": "3:48:48", "remaining_time": "4:33:05", "throughput": 4393.59, "total_tokens": 60315600} {"current_steps": 27950, "total_steps": 61300, "loss": 0.3936, "lr": 3.3061763248915744e-05, "epoch": 4.559543230016313, "percentage": 45.6, "elapsed_time": "3:48:50", "remaining_time": "4:33:03", "throughput": 4393.66, "total_tokens": 60326608} {"current_steps": 27955, "total_steps": 61300, "loss": 0.3641, "lr": 3.305502518611911e-05, "epoch": 4.560358890701468, "percentage": 45.6, "elapsed_time": "3:48:52", "remaining_time": "4:33:00", "throughput": 4393.72, "total_tokens": 60336944} {"current_steps": 27960, "total_steps": 61300, "loss": 0.3102, "lr": 3.304828647034126e-05, "epoch": 4.561174551386623, "percentage": 45.61, "elapsed_time": "3:48:54", "remaining_time": "4:32:57", "throughput": 4393.8, "total_tokens": 60348656} {"current_steps": 27965, "total_steps": 61300, "loss": 0.3377, "lr": 3.304154710212847e-05, "epoch": 4.561990212071779, "percentage": 45.62, "elapsed_time": "3:48:57", "remaining_time": "4:32:55", "throughput": 4393.87, "total_tokens": 60359568} {"current_steps": 27970, "total_steps": 61300, "loss": 0.3353, "lr": 3.303480708202708e-05, "epoch": 4.562805872756933, "percentage": 45.63, "elapsed_time": "3:48:59", "remaining_time": "4:32:52", "throughput": 4393.92, "total_tokens": 60370192} {"current_steps": 27975, "total_steps": 61300, "loss": 0.3504, "lr": 3.3028066410583456e-05, "epoch": 4.563621533442088, "percentage": 45.64, "elapsed_time": "3:49:01", "remaining_time": "4:32:49", "throughput": 4393.99, "total_tokens": 60381136} {"current_steps": 27980, "total_steps": 61300, "loss": 0.3518, "lr": 3.3021325088344036e-05, "epoch": 4.564437194127243, "percentage": 45.64, "elapsed_time": "3:49:04", "remaining_time": "4:32:47", "throughput": 4394.07, "total_tokens": 60392304} {"current_steps": 27985, "total_steps": 61300, "loss": 0.3147, "lr": 3.3014583115855304e-05, "epoch": 4.565252854812398, "percentage": 45.65, "elapsed_time": "3:49:06", "remaining_time": "4:32:44", "throughput": 4394.13, "total_tokens": 60402544} {"current_steps": 27990, "total_steps": 61300, "loss": 0.3384, "lr": 3.3007840493663794e-05, "epoch": 4.566068515497553, "percentage": 45.66, "elapsed_time": "3:49:08", "remaining_time": "4:32:41", "throughput": 4394.21, "total_tokens": 60413488} {"current_steps": 27995, "total_steps": 61300, "loss": 0.3629, "lr": 3.30010972223161e-05, "epoch": 4.566884176182708, "percentage": 45.67, "elapsed_time": "3:49:10", "remaining_time": "4:32:38", "throughput": 4394.27, "total_tokens": 60423696} {"current_steps": 28000, "total_steps": 61300, "loss": 0.3748, "lr": 3.2994353302358875e-05, "epoch": 4.567699836867863, "percentage": 45.68, "elapsed_time": "3:49:12", "remaining_time": "4:32:36", "throughput": 4394.34, "total_tokens": 60434576} {"current_steps": 28005, "total_steps": 61300, "loss": 0.3395, "lr": 3.298760873433881e-05, "epoch": 4.568515497553018, "percentage": 45.69, "elapsed_time": "3:49:14", "remaining_time": "4:32:32", "throughput": 4394.41, "total_tokens": 60443856} {"current_steps": 28010, "total_steps": 61300, "loss": 0.323, "lr": 3.298086351880265e-05, "epoch": 4.569331158238173, "percentage": 45.69, "elapsed_time": "3:49:17", "remaining_time": "4:32:30", "throughput": 4394.48, "total_tokens": 60454864} {"current_steps": 28015, "total_steps": 61300, "loss": 0.3461, "lr": 3.2974117656297194e-05, "epoch": 4.570146818923328, "percentage": 45.7, "elapsed_time": "3:49:19", "remaining_time": "4:32:27", "throughput": 4394.54, "total_tokens": 60465456} {"current_steps": 28020, "total_steps": 61300, "loss": 0.3315, "lr": 3.2967371147369306e-05, "epoch": 4.5709624796084825, "percentage": 45.71, "elapsed_time": "3:49:21", "remaining_time": "4:32:24", "throughput": 4394.62, "total_tokens": 60476816} {"current_steps": 28025, "total_steps": 61300, "loss": 0.332, "lr": 3.296062399256587e-05, "epoch": 4.571778140293638, "percentage": 45.72, "elapsed_time": "3:49:24", "remaining_time": "4:32:22", "throughput": 4394.69, "total_tokens": 60488784} {"current_steps": 28030, "total_steps": 61300, "loss": 0.3467, "lr": 3.295387619243389e-05, "epoch": 4.572593800978793, "percentage": 45.73, "elapsed_time": "3:49:26", "remaining_time": "4:32:20", "throughput": 4394.77, "total_tokens": 60500656} {"current_steps": 28035, "total_steps": 61300, "loss": 0.3745, "lr": 3.294712774752033e-05, "epoch": 4.573409461663948, "percentage": 45.73, "elapsed_time": "3:49:28", "remaining_time": "4:32:17", "throughput": 4394.85, "total_tokens": 60511664} {"current_steps": 28040, "total_steps": 61300, "loss": 0.3736, "lr": 3.2940378658372276e-05, "epoch": 4.574225122349103, "percentage": 45.74, "elapsed_time": "3:49:30", "remaining_time": "4:32:14", "throughput": 4394.92, "total_tokens": 60522000} {"current_steps": 28045, "total_steps": 61300, "loss": 0.3252, "lr": 3.293362892553684e-05, "epoch": 4.575040783034257, "percentage": 45.75, "elapsed_time": "3:49:33", "remaining_time": "4:32:11", "throughput": 4395.0, "total_tokens": 60532688} {"current_steps": 28050, "total_steps": 61300, "loss": 0.3424, "lr": 3.292687854956119e-05, "epoch": 4.575856443719413, "percentage": 45.76, "elapsed_time": "3:49:35", "remaining_time": "4:32:08", "throughput": 4395.05, "total_tokens": 60543152} {"current_steps": 28055, "total_steps": 61300, "loss": 0.3388, "lr": 3.292012753099254e-05, "epoch": 4.576672104404568, "percentage": 45.77, "elapsed_time": "3:49:37", "remaining_time": "4:32:05", "throughput": 4395.12, "total_tokens": 60552272} {"current_steps": 28060, "total_steps": 61300, "loss": 0.3328, "lr": 3.2913375870378165e-05, "epoch": 4.577487765089723, "percentage": 45.77, "elapsed_time": "3:49:39", "remaining_time": "4:32:03", "throughput": 4395.19, "total_tokens": 60563888} {"current_steps": 28065, "total_steps": 61300, "loss": 0.3479, "lr": 3.2906623568265396e-05, "epoch": 4.578303425774878, "percentage": 45.78, "elapsed_time": "3:49:41", "remaining_time": "4:32:00", "throughput": 4395.25, "total_tokens": 60574576} {"current_steps": 28070, "total_steps": 61300, "loss": 0.33, "lr": 3.289987062520159e-05, "epoch": 4.579119086460032, "percentage": 45.79, "elapsed_time": "3:49:43", "remaining_time": "4:31:57", "throughput": 4395.31, "total_tokens": 60584848} {"current_steps": 28075, "total_steps": 61300, "loss": 0.3381, "lr": 3.28931170417342e-05, "epoch": 4.579934747145187, "percentage": 45.8, "elapsed_time": "3:49:46", "remaining_time": "4:31:55", "throughput": 4395.37, "total_tokens": 60595312} {"current_steps": 28080, "total_steps": 61300, "loss": 0.3384, "lr": 3.288636281841069e-05, "epoch": 4.580750407830343, "percentage": 45.81, "elapsed_time": "3:49:48", "remaining_time": "4:31:52", "throughput": 4395.43, "total_tokens": 60604848} {"current_steps": 28085, "total_steps": 61300, "loss": 0.3368, "lr": 3.287960795577859e-05, "epoch": 4.581566068515498, "percentage": 45.82, "elapsed_time": "3:49:50", "remaining_time": "4:31:49", "throughput": 4395.49, "total_tokens": 60614640} {"current_steps": 28090, "total_steps": 61300, "loss": 0.3675, "lr": 3.2872852454385495e-05, "epoch": 4.582381729200653, "percentage": 45.82, "elapsed_time": "3:49:52", "remaining_time": "4:31:46", "throughput": 4395.55, "total_tokens": 60624912} {"current_steps": 28095, "total_steps": 61300, "loss": 0.3338, "lr": 3.2866096314779035e-05, "epoch": 4.583197389885807, "percentage": 45.83, "elapsed_time": "3:49:55", "remaining_time": "4:31:44", "throughput": 4395.64, "total_tokens": 60637968} {"current_steps": 28100, "total_steps": 61300, "loss": 0.3316, "lr": 3.285933953750689e-05, "epoch": 4.584013050570962, "percentage": 45.84, "elapsed_time": "3:49:57", "remaining_time": "4:31:41", "throughput": 4395.7, "total_tokens": 60648816} {"current_steps": 28105, "total_steps": 61300, "loss": 0.3643, "lr": 3.28525821231168e-05, "epoch": 4.584828711256117, "percentage": 45.85, "elapsed_time": "3:49:59", "remaining_time": "4:31:38", "throughput": 4395.78, "total_tokens": 60659888} {"current_steps": 28110, "total_steps": 61300, "loss": 0.3094, "lr": 3.284582407215657e-05, "epoch": 4.585644371941273, "percentage": 45.86, "elapsed_time": "3:50:01", "remaining_time": "4:31:36", "throughput": 4395.85, "total_tokens": 60671472} {"current_steps": 28115, "total_steps": 61300, "loss": 0.346, "lr": 3.283906538517403e-05, "epoch": 4.5864600326264275, "percentage": 45.86, "elapsed_time": "3:50:04", "remaining_time": "4:31:33", "throughput": 4395.93, "total_tokens": 60683696} {"current_steps": 28120, "total_steps": 61300, "loss": 0.3424, "lr": 3.283230606271707e-05, "epoch": 4.587275693311582, "percentage": 45.87, "elapsed_time": "3:50:06", "remaining_time": "4:31:31", "throughput": 4396.0, "total_tokens": 60694832} {"current_steps": 28125, "total_steps": 61300, "loss": 0.3436, "lr": 3.2825546105333634e-05, "epoch": 4.588091353996737, "percentage": 45.88, "elapsed_time": "3:50:09", "remaining_time": "4:31:28", "throughput": 4396.07, "total_tokens": 60706192} {"current_steps": 28130, "total_steps": 61300, "loss": 0.3185, "lr": 3.281878551357174e-05, "epoch": 4.588907014681892, "percentage": 45.89, "elapsed_time": "3:50:11", "remaining_time": "4:31:25", "throughput": 4396.15, "total_tokens": 60716880} {"current_steps": 28135, "total_steps": 61300, "loss": 0.3335, "lr": 3.281202428797941e-05, "epoch": 4.589722675367048, "percentage": 45.9, "elapsed_time": "3:50:13", "remaining_time": "4:31:23", "throughput": 4396.2, "total_tokens": 60727792} {"current_steps": 28140, "total_steps": 61300, "loss": 0.345, "lr": 3.2805262429104755e-05, "epoch": 4.5905383360522025, "percentage": 45.91, "elapsed_time": "3:50:15", "remaining_time": "4:31:20", "throughput": 4396.27, "total_tokens": 60738800} {"current_steps": 28145, "total_steps": 61300, "loss": 0.3427, "lr": 3.279849993749593e-05, "epoch": 4.591353996737357, "percentage": 45.91, "elapsed_time": "3:50:17", "remaining_time": "4:31:17", "throughput": 4396.33, "total_tokens": 60748336} {"current_steps": 28150, "total_steps": 61300, "loss": 0.3339, "lr": 3.279173681370112e-05, "epoch": 4.592169657422512, "percentage": 45.92, "elapsed_time": "3:50:20", "remaining_time": "4:31:15", "throughput": 4396.41, "total_tokens": 60759728} {"current_steps": 28155, "total_steps": 61300, "loss": 0.3519, "lr": 3.27849730582686e-05, "epoch": 4.592985318107667, "percentage": 45.93, "elapsed_time": "3:50:22", "remaining_time": "4:31:12", "throughput": 4396.48, "total_tokens": 60771184} {"current_steps": 28160, "total_steps": 61300, "loss": 0.3352, "lr": 3.2778208671746654e-05, "epoch": 4.593800978792823, "percentage": 45.94, "elapsed_time": "3:50:25", "remaining_time": "4:31:10", "throughput": 4396.56, "total_tokens": 60782864} {"current_steps": 28165, "total_steps": 61300, "loss": 0.3352, "lr": 3.277144365468365e-05, "epoch": 4.5946166394779775, "percentage": 45.95, "elapsed_time": "3:50:27", "remaining_time": "4:31:07", "throughput": 4396.64, "total_tokens": 60794800} {"current_steps": 28170, "total_steps": 61300, "loss": 0.3516, "lr": 3.2764678007627994e-05, "epoch": 4.595432300163132, "percentage": 45.95, "elapsed_time": "3:50:29", "remaining_time": "4:31:05", "throughput": 4396.71, "total_tokens": 60806224} {"current_steps": 28175, "total_steps": 61300, "loss": 0.3129, "lr": 3.275791173112814e-05, "epoch": 4.596247960848287, "percentage": 45.96, "elapsed_time": "3:50:32", "remaining_time": "4:31:02", "throughput": 4396.79, "total_tokens": 60817232} {"current_steps": 28180, "total_steps": 61300, "loss": 0.3547, "lr": 3.2751144825732595e-05, "epoch": 4.597063621533442, "percentage": 45.97, "elapsed_time": "3:50:34", "remaining_time": "4:30:59", "throughput": 4396.87, "total_tokens": 60828400} {"current_steps": 28185, "total_steps": 61300, "loss": 0.3695, "lr": 3.274437729198992e-05, "epoch": 4.597879282218597, "percentage": 45.98, "elapsed_time": "3:50:36", "remaining_time": "4:30:57", "throughput": 4396.94, "total_tokens": 60840080} {"current_steps": 28190, "total_steps": 61300, "loss": 0.3257, "lr": 3.273760913044873e-05, "epoch": 4.598694942903752, "percentage": 45.99, "elapsed_time": "3:50:39", "remaining_time": "4:30:54", "throughput": 4397.0, "total_tokens": 60851088} {"current_steps": 28195, "total_steps": 61300, "loss": 0.3589, "lr": 3.273084034165769e-05, "epoch": 4.599510603588907, "percentage": 46.0, "elapsed_time": "3:50:41", "remaining_time": "4:30:51", "throughput": 4397.07, "total_tokens": 60862096} {"current_steps": 28200, "total_steps": 61300, "loss": 0.3275, "lr": 3.2724070926165495e-05, "epoch": 4.600326264274062, "percentage": 46.0, "elapsed_time": "3:50:43", "remaining_time": "4:30:49", "throughput": 4397.14, "total_tokens": 60872848} {"current_steps": 28205, "total_steps": 61300, "loss": 0.3465, "lr": 3.271730088452093e-05, "epoch": 4.601141924959217, "percentage": 46.01, "elapsed_time": "3:50:46", "remaining_time": "4:30:46", "throughput": 4397.21, "total_tokens": 60883760} {"current_steps": 28210, "total_steps": 61300, "loss": 0.3145, "lr": 3.2710530217272794e-05, "epoch": 4.601957585644372, "percentage": 46.02, "elapsed_time": "3:50:48", "remaining_time": "4:30:43", "throughput": 4397.26, "total_tokens": 60893456} {"current_steps": 28215, "total_steps": 61300, "loss": 0.3517, "lr": 3.270375892496995e-05, "epoch": 4.602773246329527, "percentage": 46.03, "elapsed_time": "3:50:50", "remaining_time": "4:30:41", "throughput": 4397.32, "total_tokens": 60905136} {"current_steps": 28220, "total_steps": 61300, "loss": 0.3318, "lr": 3.2696987008161325e-05, "epoch": 4.603588907014682, "percentage": 46.04, "elapsed_time": "3:50:52", "remaining_time": "4:30:38", "throughput": 4397.39, "total_tokens": 60915088} {"current_steps": 28225, "total_steps": 61300, "loss": 0.3637, "lr": 3.269021446739588e-05, "epoch": 4.604404567699837, "percentage": 46.04, "elapsed_time": "3:50:54", "remaining_time": "4:30:35", "throughput": 4397.46, "total_tokens": 60926704} {"current_steps": 28230, "total_steps": 61300, "loss": 0.3212, "lr": 3.268344130322262e-05, "epoch": 4.605220228384992, "percentage": 46.05, "elapsed_time": "3:50:57", "remaining_time": "4:30:33", "throughput": 4397.53, "total_tokens": 60937808} {"current_steps": 28235, "total_steps": 61300, "loss": 0.3364, "lr": 3.2676667516190634e-05, "epoch": 4.606035889070147, "percentage": 46.06, "elapsed_time": "3:50:59", "remaining_time": "4:30:30", "throughput": 4397.6, "total_tokens": 60948112} {"current_steps": 28240, "total_steps": 61300, "loss": 0.3395, "lr": 3.266989310684902e-05, "epoch": 4.6068515497553015, "percentage": 46.07, "elapsed_time": "3:51:01", "remaining_time": "4:30:27", "throughput": 4397.67, "total_tokens": 60959312} {"current_steps": 28245, "total_steps": 61300, "loss": 0.339, "lr": 3.266311807574697e-05, "epoch": 4.607667210440457, "percentage": 46.08, "elapsed_time": "3:51:03", "remaining_time": "4:30:24", "throughput": 4397.74, "total_tokens": 60970256} {"current_steps": 28250, "total_steps": 61300, "loss": 0.3386, "lr": 3.265634242343367e-05, "epoch": 4.608482871125612, "percentage": 46.08, "elapsed_time": "3:51:06", "remaining_time": "4:30:22", "throughput": 4397.8, "total_tokens": 60980752} {"current_steps": 28255, "total_steps": 61300, "loss": 0.3295, "lr": 3.264956615045841e-05, "epoch": 4.609298531810767, "percentage": 46.09, "elapsed_time": "3:51:08", "remaining_time": "4:30:19", "throughput": 4397.87, "total_tokens": 60991344} {"current_steps": 28260, "total_steps": 61300, "loss": 0.3286, "lr": 3.26427892573705e-05, "epoch": 4.610114192495922, "percentage": 46.1, "elapsed_time": "3:51:10", "remaining_time": "4:30:16", "throughput": 4397.93, "total_tokens": 61001264} {"current_steps": 28265, "total_steps": 61300, "loss": 0.3173, "lr": 3.263601174471932e-05, "epoch": 4.6109298531810765, "percentage": 46.11, "elapsed_time": "3:51:12", "remaining_time": "4:30:13", "throughput": 4398.0, "total_tokens": 61011408} {"current_steps": 28270, "total_steps": 61300, "loss": 0.3489, "lr": 3.262923361305429e-05, "epoch": 4.611745513866231, "percentage": 46.12, "elapsed_time": "3:51:14", "remaining_time": "4:30:10", "throughput": 4398.07, "total_tokens": 61020944} {"current_steps": 28275, "total_steps": 61300, "loss": 0.329, "lr": 3.262245486292486e-05, "epoch": 4.612561174551386, "percentage": 46.13, "elapsed_time": "3:51:16", "remaining_time": "4:30:07", "throughput": 4398.13, "total_tokens": 61031248} {"current_steps": 28280, "total_steps": 61300, "loss": 0.3297, "lr": 3.261567549488056e-05, "epoch": 4.613376835236542, "percentage": 46.13, "elapsed_time": "3:51:18", "remaining_time": "4:30:05", "throughput": 4398.19, "total_tokens": 61042320} {"current_steps": 28285, "total_steps": 61300, "loss": 0.327, "lr": 3.260889550947098e-05, "epoch": 4.614192495921697, "percentage": 46.14, "elapsed_time": "3:51:21", "remaining_time": "4:30:02", "throughput": 4398.27, "total_tokens": 61053520} {"current_steps": 28290, "total_steps": 61300, "loss": 0.3396, "lr": 3.260211490724571e-05, "epoch": 4.6150081566068515, "percentage": 46.15, "elapsed_time": "3:51:23", "remaining_time": "4:29:59", "throughput": 4398.33, "total_tokens": 61062960} {"current_steps": 28295, "total_steps": 61300, "loss": 0.3519, "lr": 3.259533368875444e-05, "epoch": 4.615823817292006, "percentage": 46.16, "elapsed_time": "3:51:25", "remaining_time": "4:29:56", "throughput": 4398.41, "total_tokens": 61073392} {"current_steps": 28300, "total_steps": 61300, "loss": 0.3214, "lr": 3.2588551854546876e-05, "epoch": 4.616639477977161, "percentage": 46.17, "elapsed_time": "3:51:27", "remaining_time": "4:29:53", "throughput": 4398.47, "total_tokens": 61083984} {"current_steps": 28305, "total_steps": 61300, "loss": 0.3356, "lr": 3.2581769405172805e-05, "epoch": 4.617455138662317, "percentage": 46.17, "elapsed_time": "3:51:29", "remaining_time": "4:29:51", "throughput": 4398.55, "total_tokens": 61095280} {"current_steps": 28310, "total_steps": 61300, "loss": 0.3537, "lr": 3.2574986341182026e-05, "epoch": 4.618270799347472, "percentage": 46.18, "elapsed_time": "3:51:32", "remaining_time": "4:29:48", "throughput": 4398.62, "total_tokens": 61107024} {"current_steps": 28315, "total_steps": 61300, "loss": 0.393, "lr": 3.256820266312442e-05, "epoch": 4.6190864600326265, "percentage": 46.19, "elapsed_time": "3:51:34", "remaining_time": "4:29:46", "throughput": 4398.68, "total_tokens": 61117552} {"current_steps": 28320, "total_steps": 61300, "loss": 0.3184, "lr": 3.256141837154991e-05, "epoch": 4.619902120717781, "percentage": 46.2, "elapsed_time": "3:51:36", "remaining_time": "4:29:43", "throughput": 4398.75, "total_tokens": 61129040} {"current_steps": 28325, "total_steps": 61300, "loss": 0.3827, "lr": 3.255463346700846e-05, "epoch": 4.620717781402936, "percentage": 46.21, "elapsed_time": "3:51:39", "remaining_time": "4:29:40", "throughput": 4398.81, "total_tokens": 61139664} {"current_steps": 28330, "total_steps": 61300, "loss": 0.348, "lr": 3.254784795005008e-05, "epoch": 4.621533442088092, "percentage": 46.22, "elapsed_time": "3:51:41", "remaining_time": "4:29:38", "throughput": 4398.89, "total_tokens": 61151728} {"current_steps": 28335, "total_steps": 61300, "loss": 0.3514, "lr": 3.254106182122486e-05, "epoch": 4.622349102773247, "percentage": 46.22, "elapsed_time": "3:51:43", "remaining_time": "4:29:35", "throughput": 4398.96, "total_tokens": 61162448} {"current_steps": 28340, "total_steps": 61300, "loss": 0.3743, "lr": 3.2534275081082896e-05, "epoch": 4.623164763458401, "percentage": 46.23, "elapsed_time": "3:51:46", "remaining_time": "4:29:33", "throughput": 4399.03, "total_tokens": 61173136} {"current_steps": 28345, "total_steps": 61300, "loss": 0.3464, "lr": 3.252748773017437e-05, "epoch": 4.623980424143556, "percentage": 46.24, "elapsed_time": "3:51:48", "remaining_time": "4:29:30", "throughput": 4399.09, "total_tokens": 61183120} {"current_steps": 28350, "total_steps": 61300, "loss": 0.364, "lr": 3.2520699769049496e-05, "epoch": 4.624796084828711, "percentage": 46.25, "elapsed_time": "3:51:50", "remaining_time": "4:29:27", "throughput": 4399.15, "total_tokens": 61194000} {"current_steps": 28355, "total_steps": 61300, "loss": 0.3304, "lr": 3.251391119825854e-05, "epoch": 4.625611745513866, "percentage": 46.26, "elapsed_time": "3:51:52", "remaining_time": "4:29:24", "throughput": 4399.22, "total_tokens": 61204688} {"current_steps": 28360, "total_steps": 61300, "loss": 0.3421, "lr": 3.2507122018351815e-05, "epoch": 4.626427406199021, "percentage": 46.26, "elapsed_time": "3:51:54", "remaining_time": "4:29:22", "throughput": 4399.28, "total_tokens": 61215376} {"current_steps": 28365, "total_steps": 61300, "loss": 0.3075, "lr": 3.250033222987969e-05, "epoch": 4.627243066884176, "percentage": 46.27, "elapsed_time": "3:51:57", "remaining_time": "4:29:19", "throughput": 4399.35, "total_tokens": 61226256} {"current_steps": 28370, "total_steps": 61300, "loss": 0.3431, "lr": 3.2493541833392575e-05, "epoch": 4.628058727569331, "percentage": 46.28, "elapsed_time": "3:51:59", "remaining_time": "4:29:16", "throughput": 4399.42, "total_tokens": 61238192} {"current_steps": 28375, "total_steps": 61300, "loss": 0.3675, "lr": 3.2486750829440946e-05, "epoch": 4.628874388254486, "percentage": 46.29, "elapsed_time": "3:52:01", "remaining_time": "4:29:14", "throughput": 4399.49, "total_tokens": 61248944} {"current_steps": 28380, "total_steps": 61300, "loss": 0.3297, "lr": 3.2479959218575295e-05, "epoch": 4.629690048939641, "percentage": 46.3, "elapsed_time": "3:52:04", "remaining_time": "4:29:11", "throughput": 4399.57, "total_tokens": 61260752} {"current_steps": 28385, "total_steps": 61300, "loss": 0.4027, "lr": 3.24731670013462e-05, "epoch": 4.630505709624796, "percentage": 46.31, "elapsed_time": "3:52:06", "remaining_time": "4:29:09", "throughput": 4399.64, "total_tokens": 61271984} {"current_steps": 28390, "total_steps": 61300, "loss": 0.3401, "lr": 3.246637417830427e-05, "epoch": 4.631321370309951, "percentage": 46.31, "elapsed_time": "3:52:08", "remaining_time": "4:29:06", "throughput": 4399.71, "total_tokens": 61283248} {"current_steps": 28395, "total_steps": 61300, "loss": 0.3808, "lr": 3.245958075000017e-05, "epoch": 4.632137030995106, "percentage": 46.32, "elapsed_time": "3:52:11", "remaining_time": "4:29:03", "throughput": 4399.79, "total_tokens": 61294512} {"current_steps": 28400, "total_steps": 61300, "loss": 0.3856, "lr": 3.24527867169846e-05, "epoch": 4.632952691680261, "percentage": 46.33, "elapsed_time": "3:52:13", "remaining_time": "4:29:01", "throughput": 4399.85, "total_tokens": 61304944} {"current_steps": 28405, "total_steps": 61300, "loss": 0.3431, "lr": 3.244599207980833e-05, "epoch": 4.633768352365416, "percentage": 46.34, "elapsed_time": "3:52:15", "remaining_time": "4:28:58", "throughput": 4399.91, "total_tokens": 61315408} {"current_steps": 28410, "total_steps": 61300, "loss": 0.3279, "lr": 3.243919683902216e-05, "epoch": 4.634584013050571, "percentage": 46.35, "elapsed_time": "3:52:17", "remaining_time": "4:28:55", "throughput": 4399.97, "total_tokens": 61326000} {"current_steps": 28415, "total_steps": 61300, "loss": 0.3355, "lr": 3.2432400995176934e-05, "epoch": 4.635399673735726, "percentage": 46.35, "elapsed_time": "3:52:19", "remaining_time": "4:28:52", "throughput": 4400.03, "total_tokens": 61335984} {"current_steps": 28420, "total_steps": 61300, "loss": 0.3606, "lr": 3.242560454882359e-05, "epoch": 4.636215334420881, "percentage": 46.36, "elapsed_time": "3:52:22", "remaining_time": "4:28:50", "throughput": 4400.11, "total_tokens": 61347344} {"current_steps": 28425, "total_steps": 61300, "loss": 0.3305, "lr": 3.241880750051306e-05, "epoch": 4.637030995106036, "percentage": 46.37, "elapsed_time": "3:52:24", "remaining_time": "4:28:47", "throughput": 4400.18, "total_tokens": 61358352} {"current_steps": 28430, "total_steps": 61300, "loss": 0.3471, "lr": 3.241200985079634e-05, "epoch": 4.637846655791191, "percentage": 46.38, "elapsed_time": "3:52:26", "remaining_time": "4:28:44", "throughput": 4400.25, "total_tokens": 61369168} {"current_steps": 28435, "total_steps": 61300, "loss": 0.3292, "lr": 3.2405211600224503e-05, "epoch": 4.638662316476346, "percentage": 46.39, "elapsed_time": "3:52:29", "remaining_time": "4:28:42", "throughput": 4400.31, "total_tokens": 61379984} {"current_steps": 28440, "total_steps": 61300, "loss": 0.3253, "lr": 3.239841274934863e-05, "epoch": 4.6394779771615005, "percentage": 46.39, "elapsed_time": "3:52:31", "remaining_time": "4:28:39", "throughput": 4400.38, "total_tokens": 61391760} {"current_steps": 28445, "total_steps": 61300, "loss": 0.3493, "lr": 3.239161329871989e-05, "epoch": 4.640293637846656, "percentage": 46.4, "elapsed_time": "3:52:33", "remaining_time": "4:28:36", "throughput": 4400.44, "total_tokens": 61401680} {"current_steps": 28450, "total_steps": 61300, "loss": 0.3286, "lr": 3.2384813248889475e-05, "epoch": 4.641109298531811, "percentage": 46.41, "elapsed_time": "3:52:35", "remaining_time": "4:28:33", "throughput": 4400.51, "total_tokens": 61411696} {"current_steps": 28455, "total_steps": 61300, "loss": 0.3472, "lr": 3.2378012600408625e-05, "epoch": 4.641924959216966, "percentage": 46.42, "elapsed_time": "3:52:37", "remaining_time": "4:28:31", "throughput": 4400.57, "total_tokens": 61421968} {"current_steps": 28460, "total_steps": 61300, "loss": 0.3336, "lr": 3.2371211353828636e-05, "epoch": 4.642740619902121, "percentage": 46.43, "elapsed_time": "3:52:39", "remaining_time": "4:28:27", "throughput": 4400.62, "total_tokens": 61430960} {"current_steps": 28465, "total_steps": 61300, "loss": 0.319, "lr": 3.236440950970085e-05, "epoch": 4.643556280587275, "percentage": 46.44, "elapsed_time": "3:52:41", "remaining_time": "4:28:25", "throughput": 4400.69, "total_tokens": 61442032} {"current_steps": 28470, "total_steps": 61300, "loss": 0.3413, "lr": 3.2357607068576664e-05, "epoch": 4.64437194127243, "percentage": 46.44, "elapsed_time": "3:52:44", "remaining_time": "4:28:22", "throughput": 4400.75, "total_tokens": 61453136} {"current_steps": 28475, "total_steps": 61300, "loss": 0.3136, "lr": 3.2350804031007524e-05, "epoch": 4.645187601957586, "percentage": 46.45, "elapsed_time": "3:52:46", "remaining_time": "4:28:20", "throughput": 4400.81, "total_tokens": 61464048} {"current_steps": 28480, "total_steps": 61300, "loss": 0.3274, "lr": 3.234400039754491e-05, "epoch": 4.646003262642741, "percentage": 46.46, "elapsed_time": "3:52:48", "remaining_time": "4:28:17", "throughput": 4400.88, "total_tokens": 61475344} {"current_steps": 28485, "total_steps": 61300, "loss": 0.377, "lr": 3.2337196168740356e-05, "epoch": 4.646818923327896, "percentage": 46.47, "elapsed_time": "3:52:50", "remaining_time": "4:28:14", "throughput": 4400.93, "total_tokens": 61485168} {"current_steps": 28490, "total_steps": 61300, "loss": 0.3205, "lr": 3.233039134514545e-05, "epoch": 4.64763458401305, "percentage": 46.48, "elapsed_time": "3:52:53", "remaining_time": "4:28:12", "throughput": 4401.0, "total_tokens": 61496304} {"current_steps": 28495, "total_steps": 61300, "loss": 0.3518, "lr": 3.2323585927311825e-05, "epoch": 4.648450244698205, "percentage": 46.48, "elapsed_time": "3:52:55", "remaining_time": "4:28:09", "throughput": 4401.07, "total_tokens": 61507088} {"current_steps": 28500, "total_steps": 61300, "loss": 0.3236, "lr": 3.231677991579118e-05, "epoch": 4.649265905383361, "percentage": 46.49, "elapsed_time": "3:52:57", "remaining_time": "4:28:06", "throughput": 4401.14, "total_tokens": 61518032} {"current_steps": 28505, "total_steps": 61300, "loss": 0.3299, "lr": 3.230997331113521e-05, "epoch": 4.650081566068516, "percentage": 46.5, "elapsed_time": "3:53:00", "remaining_time": "4:28:04", "throughput": 4401.21, "total_tokens": 61529424} {"current_steps": 28510, "total_steps": 61300, "loss": 0.3161, "lr": 3.230316611389573e-05, "epoch": 4.650897226753671, "percentage": 46.51, "elapsed_time": "3:53:02", "remaining_time": "4:28:01", "throughput": 4401.27, "total_tokens": 61540976} {"current_steps": 28515, "total_steps": 61300, "loss": 0.3347, "lr": 3.229635832462454e-05, "epoch": 4.651712887438825, "percentage": 46.52, "elapsed_time": "3:53:04", "remaining_time": "4:27:59", "throughput": 4401.33, "total_tokens": 61552368} {"current_steps": 28520, "total_steps": 61300, "loss": 0.3322, "lr": 3.228954994387352e-05, "epoch": 4.65252854812398, "percentage": 46.53, "elapsed_time": "3:53:07", "remaining_time": "4:27:56", "throughput": 4401.4, "total_tokens": 61563184} {"current_steps": 28525, "total_steps": 61300, "loss": 0.3363, "lr": 3.2282740972194606e-05, "epoch": 4.653344208809135, "percentage": 46.53, "elapsed_time": "3:53:09", "remaining_time": "4:27:53", "throughput": 4401.45, "total_tokens": 61572720} {"current_steps": 28530, "total_steps": 61300, "loss": 0.3404, "lr": 3.2275931410139755e-05, "epoch": 4.654159869494291, "percentage": 46.54, "elapsed_time": "3:53:11", "remaining_time": "4:27:50", "throughput": 4401.53, "total_tokens": 61584176} {"current_steps": 28535, "total_steps": 61300, "loss": 0.3425, "lr": 3.226912125826098e-05, "epoch": 4.6549755301794455, "percentage": 46.55, "elapsed_time": "3:53:13", "remaining_time": "4:27:48", "throughput": 4401.59, "total_tokens": 61595152} {"current_steps": 28540, "total_steps": 61300, "loss": 0.336, "lr": 3.226231051711035e-05, "epoch": 4.6557911908646, "percentage": 46.56, "elapsed_time": "3:53:16", "remaining_time": "4:27:45", "throughput": 4401.66, "total_tokens": 61606032} {"current_steps": 28545, "total_steps": 61300, "loss": 0.2923, "lr": 3.225549918723999e-05, "epoch": 4.656606851549755, "percentage": 46.57, "elapsed_time": "3:53:18", "remaining_time": "4:27:43", "throughput": 4401.73, "total_tokens": 61617680} {"current_steps": 28550, "total_steps": 61300, "loss": 0.3218, "lr": 3.224868726920205e-05, "epoch": 4.65742251223491, "percentage": 46.57, "elapsed_time": "3:53:20", "remaining_time": "4:27:40", "throughput": 4401.79, "total_tokens": 61628080} {"current_steps": 28555, "total_steps": 61300, "loss": 0.3999, "lr": 3.224187476354873e-05, "epoch": 4.658238172920065, "percentage": 46.58, "elapsed_time": "3:53:23", "remaining_time": "4:27:37", "throughput": 4401.86, "total_tokens": 61639440} {"current_steps": 28560, "total_steps": 61300, "loss": 0.3412, "lr": 3.223506167083231e-05, "epoch": 4.6590538336052205, "percentage": 46.59, "elapsed_time": "3:53:25", "remaining_time": "4:27:35", "throughput": 4401.94, "total_tokens": 61650544} {"current_steps": 28565, "total_steps": 61300, "loss": 0.3788, "lr": 3.222824799160508e-05, "epoch": 4.659869494290375, "percentage": 46.6, "elapsed_time": "3:53:27", "remaining_time": "4:27:32", "throughput": 4402.0, "total_tokens": 61661232} {"current_steps": 28570, "total_steps": 61300, "loss": 0.3576, "lr": 3.222143372641938e-05, "epoch": 4.66068515497553, "percentage": 46.61, "elapsed_time": "3:53:29", "remaining_time": "4:27:29", "throughput": 4402.07, "total_tokens": 61671984} {"current_steps": 28575, "total_steps": 61300, "loss": 0.3381, "lr": 3.2214618875827626e-05, "epoch": 4.661500815660685, "percentage": 46.62, "elapsed_time": "3:53:31", "remaining_time": "4:27:26", "throughput": 4402.12, "total_tokens": 61682160} {"current_steps": 28580, "total_steps": 61300, "loss": 0.3455, "lr": 3.220780344038227e-05, "epoch": 4.66231647634584, "percentage": 46.62, "elapsed_time": "3:53:33", "remaining_time": "4:27:23", "throughput": 4402.2, "total_tokens": 61692112} {"current_steps": 28585, "total_steps": 61300, "loss": 0.3425, "lr": 3.220098742063578e-05, "epoch": 4.6631321370309955, "percentage": 46.63, "elapsed_time": "3:53:36", "remaining_time": "4:27:21", "throughput": 4402.27, "total_tokens": 61703312} {"current_steps": 28590, "total_steps": 61300, "loss": 0.3224, "lr": 3.219417081714072e-05, "epoch": 4.66394779771615, "percentage": 46.64, "elapsed_time": "3:53:38", "remaining_time": "4:27:18", "throughput": 4402.33, "total_tokens": 61713616} {"current_steps": 28595, "total_steps": 61300, "loss": 0.3683, "lr": 3.218735363044967e-05, "epoch": 4.664763458401305, "percentage": 46.65, "elapsed_time": "3:53:40", "remaining_time": "4:27:15", "throughput": 4402.39, "total_tokens": 61724080} {"current_steps": 28600, "total_steps": 61300, "loss": 0.3333, "lr": 3.218053586111526e-05, "epoch": 4.66557911908646, "percentage": 46.66, "elapsed_time": "3:53:42", "remaining_time": "4:27:13", "throughput": 4402.45, "total_tokens": 61735216} {"current_steps": 28605, "total_steps": 61300, "loss": 0.3072, "lr": 3.217371750969019e-05, "epoch": 4.666394779771615, "percentage": 46.66, "elapsed_time": "3:53:45", "remaining_time": "4:27:10", "throughput": 4402.52, "total_tokens": 61746736} {"current_steps": 28610, "total_steps": 61300, "loss": 0.3513, "lr": 3.2166898576727176e-05, "epoch": 4.6672104404567705, "percentage": 46.67, "elapsed_time": "3:53:47", "remaining_time": "4:27:08", "throughput": 4402.59, "total_tokens": 61758032} {"current_steps": 28615, "total_steps": 61300, "loss": 0.3386, "lr": 3.2160079062779005e-05, "epoch": 4.668026101141925, "percentage": 46.68, "elapsed_time": "3:53:49", "remaining_time": "4:27:05", "throughput": 4402.66, "total_tokens": 61768624} {"current_steps": 28620, "total_steps": 61300, "loss": 0.351, "lr": 3.215325896839848e-05, "epoch": 4.66884176182708, "percentage": 46.69, "elapsed_time": "3:53:52", "remaining_time": "4:27:02", "throughput": 4402.73, "total_tokens": 61779408} {"current_steps": 28625, "total_steps": 61300, "loss": 0.3512, "lr": 3.2146438294138505e-05, "epoch": 4.669657422512235, "percentage": 46.7, "elapsed_time": "3:53:54", "remaining_time": "4:26:59", "throughput": 4402.81, "total_tokens": 61790320} {"current_steps": 28630, "total_steps": 61300, "loss": 0.3649, "lr": 3.2139617040551966e-05, "epoch": 4.67047308319739, "percentage": 46.7, "elapsed_time": "3:53:56", "remaining_time": "4:26:57", "throughput": 4402.88, "total_tokens": 61801968} {"current_steps": 28635, "total_steps": 61300, "loss": 0.3244, "lr": 3.2132795208191853e-05, "epoch": 4.671288743882545, "percentage": 46.71, "elapsed_time": "3:53:58", "remaining_time": "4:26:54", "throughput": 4402.95, "total_tokens": 61812944} {"current_steps": 28640, "total_steps": 61300, "loss": 0.3595, "lr": 3.212597279761116e-05, "epoch": 4.672104404567699, "percentage": 46.72, "elapsed_time": "3:54:01", "remaining_time": "4:26:52", "throughput": 4403.04, "total_tokens": 61824912} {"current_steps": 28645, "total_steps": 61300, "loss": 0.3548, "lr": 3.211914980936296e-05, "epoch": 4.672920065252855, "percentage": 46.73, "elapsed_time": "3:54:03", "remaining_time": "4:26:49", "throughput": 4403.11, "total_tokens": 61835120} {"current_steps": 28650, "total_steps": 61300, "loss": 0.3422, "lr": 3.2112326244000355e-05, "epoch": 4.67373572593801, "percentage": 46.74, "elapsed_time": "3:54:05", "remaining_time": "4:26:46", "throughput": 4403.17, "total_tokens": 61845680} {"current_steps": 28655, "total_steps": 61300, "loss": 0.3272, "lr": 3.2105502102076494e-05, "epoch": 4.674551386623165, "percentage": 46.75, "elapsed_time": "3:54:07", "remaining_time": "4:26:43", "throughput": 4403.24, "total_tokens": 61856368} {"current_steps": 28660, "total_steps": 61300, "loss": 0.3252, "lr": 3.209867738414459e-05, "epoch": 4.6753670473083195, "percentage": 46.75, "elapsed_time": "3:54:10", "remaining_time": "4:26:41", "throughput": 4403.29, "total_tokens": 61866448} {"current_steps": 28665, "total_steps": 61300, "loss": 0.3132, "lr": 3.2091852090757865e-05, "epoch": 4.676182707993474, "percentage": 46.76, "elapsed_time": "3:54:12", "remaining_time": "4:26:38", "throughput": 4403.35, "total_tokens": 61877040} {"current_steps": 28670, "total_steps": 61300, "loss": 0.3614, "lr": 3.208502622246964e-05, "epoch": 4.67699836867863, "percentage": 46.77, "elapsed_time": "3:54:14", "remaining_time": "4:26:35", "throughput": 4403.42, "total_tokens": 61887472} {"current_steps": 28675, "total_steps": 61300, "loss": 0.3227, "lr": 3.207819977983323e-05, "epoch": 4.677814029363785, "percentage": 46.78, "elapsed_time": "3:54:16", "remaining_time": "4:26:33", "throughput": 4403.49, "total_tokens": 61898864} {"current_steps": 28680, "total_steps": 61300, "loss": 0.3379, "lr": 3.207137276340203e-05, "epoch": 4.67862969004894, "percentage": 46.79, "elapsed_time": "3:54:19", "remaining_time": "4:26:30", "throughput": 4403.56, "total_tokens": 61910160} {"current_steps": 28685, "total_steps": 61300, "loss": 0.3678, "lr": 3.206454517372949e-05, "epoch": 4.6794453507340945, "percentage": 46.79, "elapsed_time": "3:54:21", "remaining_time": "4:26:27", "throughput": 4403.63, "total_tokens": 61920176} {"current_steps": 28690, "total_steps": 61300, "loss": 0.3569, "lr": 3.205771701136906e-05, "epoch": 4.680261011419249, "percentage": 46.8, "elapsed_time": "3:54:23", "remaining_time": "4:26:24", "throughput": 4403.69, "total_tokens": 61930992} {"current_steps": 28695, "total_steps": 61300, "loss": 0.3388, "lr": 3.205088827687428e-05, "epoch": 4.681076672104405, "percentage": 46.81, "elapsed_time": "3:54:25", "remaining_time": "4:26:22", "throughput": 4403.75, "total_tokens": 61941744} {"current_steps": 28700, "total_steps": 61300, "loss": 0.3555, "lr": 3.204405897079872e-05, "epoch": 4.68189233278956, "percentage": 46.82, "elapsed_time": "3:54:27", "remaining_time": "4:26:19", "throughput": 4403.8, "total_tokens": 61951760} {"current_steps": 28705, "total_steps": 61300, "loss": 0.3928, "lr": 3.2037229093696e-05, "epoch": 4.682707993474715, "percentage": 46.83, "elapsed_time": "3:54:29", "remaining_time": "4:26:16", "throughput": 4403.86, "total_tokens": 61961040} {"current_steps": 28710, "total_steps": 61300, "loss": 0.3655, "lr": 3.203039864611978e-05, "epoch": 4.6835236541598695, "percentage": 46.84, "elapsed_time": "3:54:31", "remaining_time": "4:26:13", "throughput": 4403.92, "total_tokens": 61971856} {"current_steps": 28715, "total_steps": 61300, "loss": 0.307, "lr": 3.202356762862377e-05, "epoch": 4.684339314845024, "percentage": 46.84, "elapsed_time": "3:54:34", "remaining_time": "4:26:11", "throughput": 4403.99, "total_tokens": 61983760} {"current_steps": 28720, "total_steps": 61300, "loss": 0.3308, "lr": 3.201673604176174e-05, "epoch": 4.685154975530179, "percentage": 46.85, "elapsed_time": "3:54:36", "remaining_time": "4:26:08", "throughput": 4404.06, "total_tokens": 61994480} {"current_steps": 28725, "total_steps": 61300, "loss": 0.3079, "lr": 3.2009903886087476e-05, "epoch": 4.685970636215334, "percentage": 46.86, "elapsed_time": "3:54:38", "remaining_time": "4:26:05", "throughput": 4404.12, "total_tokens": 62005360} {"current_steps": 28730, "total_steps": 61300, "loss": 0.3531, "lr": 3.200307116215485e-05, "epoch": 4.68678629690049, "percentage": 46.87, "elapsed_time": "3:54:41", "remaining_time": "4:26:03", "throughput": 4404.18, "total_tokens": 62016976} {"current_steps": 28735, "total_steps": 61300, "loss": 0.3242, "lr": 3.1996237870517734e-05, "epoch": 4.6876019575856445, "percentage": 46.88, "elapsed_time": "3:54:43", "remaining_time": "4:26:00", "throughput": 4404.25, "total_tokens": 62028176} {"current_steps": 28740, "total_steps": 61300, "loss": 0.354, "lr": 3.198940401173007e-05, "epoch": 4.688417618270799, "percentage": 46.88, "elapsed_time": "3:54:45", "remaining_time": "4:25:58", "throughput": 4404.31, "total_tokens": 62038672} {"current_steps": 28745, "total_steps": 61300, "loss": 0.3271, "lr": 3.198256958634586e-05, "epoch": 4.689233278955954, "percentage": 46.89, "elapsed_time": "3:54:48", "remaining_time": "4:25:55", "throughput": 4404.37, "total_tokens": 62049424} {"current_steps": 28750, "total_steps": 61300, "loss": 0.3188, "lr": 3.197573459491913e-05, "epoch": 4.690048939641109, "percentage": 46.9, "elapsed_time": "3:54:50", "remaining_time": "4:25:52", "throughput": 4404.44, "total_tokens": 62060112} {"current_steps": 28755, "total_steps": 61300, "loss": 0.3472, "lr": 3.1968899038003965e-05, "epoch": 4.690864600326265, "percentage": 46.91, "elapsed_time": "3:54:52", "remaining_time": "4:25:50", "throughput": 4404.52, "total_tokens": 62071728} {"current_steps": 28760, "total_steps": 61300, "loss": 0.3163, "lr": 3.196206291615447e-05, "epoch": 4.691680261011419, "percentage": 46.92, "elapsed_time": "3:54:54", "remaining_time": "4:25:47", "throughput": 4404.58, "total_tokens": 62081680} {"current_steps": 28765, "total_steps": 61300, "loss": 0.3513, "lr": 3.195522622992484e-05, "epoch": 4.692495921696574, "percentage": 46.92, "elapsed_time": "3:54:56", "remaining_time": "4:25:44", "throughput": 4404.64, "total_tokens": 62091984} {"current_steps": 28770, "total_steps": 61300, "loss": 0.3176, "lr": 3.1948388979869277e-05, "epoch": 4.693311582381729, "percentage": 46.93, "elapsed_time": "3:54:59", "remaining_time": "4:25:41", "throughput": 4404.71, "total_tokens": 62102864} {"current_steps": 28775, "total_steps": 61300, "loss": 0.3553, "lr": 3.194155116654205e-05, "epoch": 4.694127243066884, "percentage": 46.94, "elapsed_time": "3:55:01", "remaining_time": "4:25:39", "throughput": 4404.77, "total_tokens": 62114256} {"current_steps": 28780, "total_steps": 61300, "loss": 0.3247, "lr": 3.193471279049746e-05, "epoch": 4.69494290375204, "percentage": 46.95, "elapsed_time": "3:55:03", "remaining_time": "4:25:36", "throughput": 4404.84, "total_tokens": 62124816} {"current_steps": 28785, "total_steps": 61300, "loss": 0.3589, "lr": 3.192787385228987e-05, "epoch": 4.695758564437194, "percentage": 46.96, "elapsed_time": "3:55:06", "remaining_time": "4:25:34", "throughput": 4404.9, "total_tokens": 62136368} {"current_steps": 28790, "total_steps": 61300, "loss": 0.3406, "lr": 3.192103435247368e-05, "epoch": 4.696574225122349, "percentage": 46.97, "elapsed_time": "3:55:08", "remaining_time": "4:25:31", "throughput": 4404.97, "total_tokens": 62147024} {"current_steps": 28795, "total_steps": 61300, "loss": 0.3417, "lr": 3.1914194291603313e-05, "epoch": 4.697389885807504, "percentage": 46.97, "elapsed_time": "3:55:10", "remaining_time": "4:25:28", "throughput": 4405.04, "total_tokens": 62156848} {"current_steps": 28800, "total_steps": 61300, "loss": 0.3674, "lr": 3.190735367023328e-05, "epoch": 4.698205546492659, "percentage": 46.98, "elapsed_time": "3:55:12", "remaining_time": "4:25:25", "throughput": 4405.11, "total_tokens": 62168496} {"current_steps": 28805, "total_steps": 61300, "loss": 0.3466, "lr": 3.1900512488918114e-05, "epoch": 4.699021207177814, "percentage": 46.99, "elapsed_time": "3:55:14", "remaining_time": "4:25:23", "throughput": 4405.17, "total_tokens": 62178800} {"current_steps": 28810, "total_steps": 61300, "loss": 0.3542, "lr": 3.189367074821239e-05, "epoch": 4.699836867862969, "percentage": 47.0, "elapsed_time": "3:55:17", "remaining_time": "4:25:20", "throughput": 4405.24, "total_tokens": 62190768} {"current_steps": 28815, "total_steps": 61300, "loss": 0.334, "lr": 3.1886828448670734e-05, "epoch": 4.700652528548124, "percentage": 47.01, "elapsed_time": "3:55:19", "remaining_time": "4:25:18", "throughput": 4405.31, "total_tokens": 62201648} {"current_steps": 28820, "total_steps": 61300, "loss": 0.3033, "lr": 3.1879985590847824e-05, "epoch": 4.701468189233279, "percentage": 47.01, "elapsed_time": "3:55:22", "remaining_time": "4:25:15", "throughput": 4405.37, "total_tokens": 62212816} {"current_steps": 28825, "total_steps": 61300, "loss": 0.3391, "lr": 3.187314217529838e-05, "epoch": 4.702283849918434, "percentage": 47.02, "elapsed_time": "3:55:24", "remaining_time": "4:25:12", "throughput": 4405.43, "total_tokens": 62222992} {"current_steps": 28830, "total_steps": 61300, "loss": 0.3247, "lr": 3.1866298202577157e-05, "epoch": 4.703099510603589, "percentage": 47.03, "elapsed_time": "3:55:26", "remaining_time": "4:25:10", "throughput": 4405.5, "total_tokens": 62234192} {"current_steps": 28835, "total_steps": 61300, "loss": 0.3311, "lr": 3.185945367323895e-05, "epoch": 4.7039151712887435, "percentage": 47.04, "elapsed_time": "3:55:28", "remaining_time": "4:25:07", "throughput": 4405.57, "total_tokens": 62244848} {"current_steps": 28840, "total_steps": 61300, "loss": 0.319, "lr": 3.185260858783864e-05, "epoch": 4.704730831973899, "percentage": 47.05, "elapsed_time": "3:55:30", "remaining_time": "4:25:04", "throughput": 4405.63, "total_tokens": 62255376} {"current_steps": 28845, "total_steps": 61300, "loss": 0.3283, "lr": 3.1845762946931093e-05, "epoch": 4.705546492659054, "percentage": 47.06, "elapsed_time": "3:55:33", "remaining_time": "4:25:01", "throughput": 4405.69, "total_tokens": 62266192} {"current_steps": 28850, "total_steps": 61300, "loss": 0.3422, "lr": 3.183891675107128e-05, "epoch": 4.706362153344209, "percentage": 47.06, "elapsed_time": "3:55:35", "remaining_time": "4:24:59", "throughput": 4405.77, "total_tokens": 62277232} {"current_steps": 28855, "total_steps": 61300, "loss": 0.3616, "lr": 3.183207000081416e-05, "epoch": 4.707177814029364, "percentage": 47.07, "elapsed_time": "3:55:37", "remaining_time": "4:24:56", "throughput": 4405.83, "total_tokens": 62288368} {"current_steps": 28860, "total_steps": 61300, "loss": 0.3757, "lr": 3.1825222696714796e-05, "epoch": 4.7079934747145185, "percentage": 47.08, "elapsed_time": "3:55:39", "remaining_time": "4:24:53", "throughput": 4405.89, "total_tokens": 62299024} {"current_steps": 28865, "total_steps": 61300, "loss": 0.3592, "lr": 3.1818374839328236e-05, "epoch": 4.708809135399674, "percentage": 47.09, "elapsed_time": "3:55:42", "remaining_time": "4:24:51", "throughput": 4405.94, "total_tokens": 62309136} {"current_steps": 28870, "total_steps": 61300, "loss": 0.3413, "lr": 3.181152642920962e-05, "epoch": 4.709624796084829, "percentage": 47.1, "elapsed_time": "3:55:44", "remaining_time": "4:24:48", "throughput": 4406.02, "total_tokens": 62320656} {"current_steps": 28875, "total_steps": 61300, "loss": 0.3058, "lr": 3.180467746691411e-05, "epoch": 4.710440456769984, "percentage": 47.1, "elapsed_time": "3:55:46", "remaining_time": "4:24:45", "throughput": 4406.07, "total_tokens": 62330896} {"current_steps": 28880, "total_steps": 61300, "loss": 0.3399, "lr": 3.1797827952996914e-05, "epoch": 4.711256117455139, "percentage": 47.11, "elapsed_time": "3:55:48", "remaining_time": "4:24:43", "throughput": 4406.13, "total_tokens": 62342032} {"current_steps": 28885, "total_steps": 61300, "loss": 0.3466, "lr": 3.1790977888013294e-05, "epoch": 4.712071778140293, "percentage": 47.12, "elapsed_time": "3:55:51", "remaining_time": "4:24:40", "throughput": 4406.18, "total_tokens": 62351984} {"current_steps": 28890, "total_steps": 61300, "loss": 0.3418, "lr": 3.178412727251856e-05, "epoch": 4.712887438825448, "percentage": 47.13, "elapsed_time": "3:55:53", "remaining_time": "4:24:37", "throughput": 4406.24, "total_tokens": 62362256} {"current_steps": 28895, "total_steps": 61300, "loss": 0.3411, "lr": 3.177727610706804e-05, "epoch": 4.713703099510604, "percentage": 47.14, "elapsed_time": "3:55:55", "remaining_time": "4:24:34", "throughput": 4406.31, "total_tokens": 62373040} {"current_steps": 28900, "total_steps": 61300, "loss": 0.3549, "lr": 3.177042439221713e-05, "epoch": 4.714518760195759, "percentage": 47.15, "elapsed_time": "3:55:57", "remaining_time": "4:24:32", "throughput": 4406.39, "total_tokens": 62384304} {"current_steps": 28905, "total_steps": 61300, "loss": 0.3463, "lr": 3.176357212852127e-05, "epoch": 4.715334420880914, "percentage": 47.15, "elapsed_time": "3:55:59", "remaining_time": "4:24:29", "throughput": 4406.44, "total_tokens": 62394864} {"current_steps": 28910, "total_steps": 61300, "loss": 0.3433, "lr": 3.175671931653593e-05, "epoch": 4.716150081566068, "percentage": 47.16, "elapsed_time": "3:56:02", "remaining_time": "4:24:26", "throughput": 4406.5, "total_tokens": 62405040} {"current_steps": 28915, "total_steps": 61300, "loss": 0.339, "lr": 3.174986595681664e-05, "epoch": 4.716965742251223, "percentage": 47.17, "elapsed_time": "3:56:04", "remaining_time": "4:24:24", "throughput": 4406.59, "total_tokens": 62417040} {"current_steps": 28920, "total_steps": 61300, "loss": 0.3312, "lr": 3.174301204991896e-05, "epoch": 4.717781402936378, "percentage": 47.18, "elapsed_time": "3:56:06", "remaining_time": "4:24:21", "throughput": 4406.64, "total_tokens": 62427088} {"current_steps": 28925, "total_steps": 61300, "loss": 0.3454, "lr": 3.173615759639852e-05, "epoch": 4.718597063621534, "percentage": 47.19, "elapsed_time": "3:56:08", "remaining_time": "4:24:18", "throughput": 4406.7, "total_tokens": 62436816} {"current_steps": 28930, "total_steps": 61300, "loss": 0.3565, "lr": 3.1729302596810965e-05, "epoch": 4.719412724306689, "percentage": 47.19, "elapsed_time": "3:56:10", "remaining_time": "4:24:15", "throughput": 4406.77, "total_tokens": 62447248} {"current_steps": 28935, "total_steps": 61300, "loss": 0.3718, "lr": 3.172244705171199e-05, "epoch": 4.720228384991843, "percentage": 47.2, "elapsed_time": "3:56:12", "remaining_time": "4:24:12", "throughput": 4406.82, "total_tokens": 62456368} {"current_steps": 28940, "total_steps": 61300, "loss": 0.3349, "lr": 3.171559096165736e-05, "epoch": 4.721044045676998, "percentage": 47.21, "elapsed_time": "3:56:14", "remaining_time": "4:24:10", "throughput": 4406.88, "total_tokens": 62467088} {"current_steps": 28945, "total_steps": 61300, "loss": 0.3512, "lr": 3.170873432720285e-05, "epoch": 4.721859706362153, "percentage": 47.22, "elapsed_time": "3:56:16", "remaining_time": "4:24:07", "throughput": 4406.93, "total_tokens": 62476752} {"current_steps": 28950, "total_steps": 61300, "loss": 0.3491, "lr": 3.170187714890429e-05, "epoch": 4.722675367047309, "percentage": 47.23, "elapsed_time": "3:56:19", "remaining_time": "4:24:04", "throughput": 4406.98, "total_tokens": 62487152} {"current_steps": 28955, "total_steps": 61300, "loss": 0.3305, "lr": 3.1695019427317564e-05, "epoch": 4.7234910277324635, "percentage": 47.23, "elapsed_time": "3:56:21", "remaining_time": "4:24:01", "throughput": 4407.05, "total_tokens": 62498544} {"current_steps": 28960, "total_steps": 61300, "loss": 0.3377, "lr": 3.1688161162998595e-05, "epoch": 4.724306688417618, "percentage": 47.24, "elapsed_time": "3:56:23", "remaining_time": "4:23:59", "throughput": 4407.12, "total_tokens": 62509488} {"current_steps": 28965, "total_steps": 61300, "loss": 0.361, "lr": 3.1681302356503337e-05, "epoch": 4.725122349102773, "percentage": 47.25, "elapsed_time": "3:56:25", "remaining_time": "4:23:56", "throughput": 4407.2, "total_tokens": 62520464} {"current_steps": 28970, "total_steps": 61300, "loss": 0.3591, "lr": 3.167444300838782e-05, "epoch": 4.725938009787928, "percentage": 47.26, "elapsed_time": "3:56:28", "remaining_time": "4:23:53", "throughput": 4407.28, "total_tokens": 62531536} {"current_steps": 28975, "total_steps": 61300, "loss": 0.3252, "lr": 3.1667583119208085e-05, "epoch": 4.726753670473083, "percentage": 47.27, "elapsed_time": "3:56:30", "remaining_time": "4:23:51", "throughput": 4407.35, "total_tokens": 62542320} {"current_steps": 28980, "total_steps": 61300, "loss": 0.3544, "lr": 3.1660722689520225e-05, "epoch": 4.7275693311582385, "percentage": 47.28, "elapsed_time": "3:56:32", "remaining_time": "4:23:48", "throughput": 4407.4, "total_tokens": 62551760} {"current_steps": 28985, "total_steps": 61300, "loss": 0.3585, "lr": 3.16538617198804e-05, "epoch": 4.728384991843393, "percentage": 47.28, "elapsed_time": "3:56:34", "remaining_time": "4:23:45", "throughput": 4407.46, "total_tokens": 62562512} {"current_steps": 28990, "total_steps": 61300, "loss": 0.3234, "lr": 3.164700021084478e-05, "epoch": 4.729200652528548, "percentage": 47.29, "elapsed_time": "3:56:37", "remaining_time": "4:23:42", "throughput": 4407.52, "total_tokens": 62573648} {"current_steps": 28995, "total_steps": 61300, "loss": 0.332, "lr": 3.164013816296959e-05, "epoch": 4.730016313213703, "percentage": 47.3, "elapsed_time": "3:56:39", "remaining_time": "4:23:40", "throughput": 4407.6, "total_tokens": 62584592} {"current_steps": 29000, "total_steps": 61300, "loss": 0.3511, "lr": 3.163327557681111e-05, "epoch": 4.730831973898858, "percentage": 47.31, "elapsed_time": "3:56:41", "remaining_time": "4:23:37", "throughput": 4407.68, "total_tokens": 62596496} {"current_steps": 29005, "total_steps": 61300, "loss": 0.342, "lr": 3.162641245292566e-05, "epoch": 4.731647634584013, "percentage": 47.32, "elapsed_time": "3:56:43", "remaining_time": "4:23:35", "throughput": 4407.73, "total_tokens": 62607312} {"current_steps": 29010, "total_steps": 61300, "loss": 0.3109, "lr": 3.161954879186959e-05, "epoch": 4.732463295269168, "percentage": 47.32, "elapsed_time": "3:56:46", "remaining_time": "4:23:32", "throughput": 4407.79, "total_tokens": 62617680} {"current_steps": 29015, "total_steps": 61300, "loss": 0.3899, "lr": 3.161268459419931e-05, "epoch": 4.733278955954323, "percentage": 47.33, "elapsed_time": "3:56:48", "remaining_time": "4:23:29", "throughput": 4407.85, "total_tokens": 62627664} {"current_steps": 29020, "total_steps": 61300, "loss": 0.3477, "lr": 3.160581986047127e-05, "epoch": 4.734094616639478, "percentage": 47.34, "elapsed_time": "3:56:50", "remaining_time": "4:23:26", "throughput": 4407.91, "total_tokens": 62638352} {"current_steps": 29025, "total_steps": 61300, "loss": 0.3234, "lr": 3.1598954591241934e-05, "epoch": 4.734910277324633, "percentage": 47.35, "elapsed_time": "3:56:52", "remaining_time": "4:23:24", "throughput": 4407.96, "total_tokens": 62649520} {"current_steps": 29030, "total_steps": 61300, "loss": 0.3693, "lr": 3.159208878706787e-05, "epoch": 4.735725938009788, "percentage": 47.36, "elapsed_time": "3:56:55", "remaining_time": "4:23:21", "throughput": 4408.02, "total_tokens": 62660080} {"current_steps": 29035, "total_steps": 61300, "loss": 0.3329, "lr": 3.1585222448505644e-05, "epoch": 4.736541598694943, "percentage": 47.37, "elapsed_time": "3:56:57", "remaining_time": "4:23:18", "throughput": 4408.08, "total_tokens": 62669808} {"current_steps": 29040, "total_steps": 61300, "loss": 0.3749, "lr": 3.1578355576111864e-05, "epoch": 4.737357259380098, "percentage": 47.37, "elapsed_time": "3:56:59", "remaining_time": "4:23:16", "throughput": 4408.14, "total_tokens": 62681136} {"current_steps": 29045, "total_steps": 61300, "loss": 0.3351, "lr": 3.157148817044321e-05, "epoch": 4.738172920065253, "percentage": 47.38, "elapsed_time": "3:57:01", "remaining_time": "4:23:13", "throughput": 4408.21, "total_tokens": 62692144} {"current_steps": 29050, "total_steps": 61300, "loss": 0.3187, "lr": 3.156462023205638e-05, "epoch": 4.738988580750408, "percentage": 47.39, "elapsed_time": "3:57:03", "remaining_time": "4:23:10", "throughput": 4408.24, "total_tokens": 62701360} {"current_steps": 29055, "total_steps": 61300, "loss": 0.3373, "lr": 3.155775176150812e-05, "epoch": 4.739804241435563, "percentage": 47.4, "elapsed_time": "3:57:06", "remaining_time": "4:23:08", "throughput": 4408.33, "total_tokens": 62713488} {"current_steps": 29060, "total_steps": 61300, "loss": 0.3407, "lr": 3.1550882759355246e-05, "epoch": 4.740619902120718, "percentage": 47.41, "elapsed_time": "3:57:08", "remaining_time": "4:23:05", "throughput": 4408.41, "total_tokens": 62725264} {"current_steps": 29065, "total_steps": 61300, "loss": 0.3204, "lr": 3.154401322615456e-05, "epoch": 4.741435562805873, "percentage": 47.41, "elapsed_time": "3:57:10", "remaining_time": "4:23:02", "throughput": 4408.46, "total_tokens": 62735312} {"current_steps": 29070, "total_steps": 61300, "loss": 0.3414, "lr": 3.153714316246297e-05, "epoch": 4.742251223491028, "percentage": 47.42, "elapsed_time": "3:57:12", "remaining_time": "4:22:59", "throughput": 4408.53, "total_tokens": 62745744} {"current_steps": 29075, "total_steps": 61300, "loss": 0.3155, "lr": 3.153027256883737e-05, "epoch": 4.743066884176183, "percentage": 47.43, "elapsed_time": "3:57:14", "remaining_time": "4:22:56", "throughput": 4408.58, "total_tokens": 62754960} {"current_steps": 29080, "total_steps": 61300, "loss": 0.2995, "lr": 3.152340144583475e-05, "epoch": 4.7438825448613375, "percentage": 47.44, "elapsed_time": "3:57:16", "remaining_time": "4:22:54", "throughput": 4408.64, "total_tokens": 62765712} {"current_steps": 29085, "total_steps": 61300, "loss": 0.3661, "lr": 3.151652979401211e-05, "epoch": 4.744698205546492, "percentage": 47.45, "elapsed_time": "3:57:19", "remaining_time": "4:22:51", "throughput": 4408.71, "total_tokens": 62776784} {"current_steps": 29090, "total_steps": 61300, "loss": 0.3705, "lr": 3.15096576139265e-05, "epoch": 4.745513866231647, "percentage": 47.46, "elapsed_time": "3:57:21", "remaining_time": "4:22:49", "throughput": 4408.79, "total_tokens": 62787984} {"current_steps": 29095, "total_steps": 61300, "loss": 0.3697, "lr": 3.150278490613501e-05, "epoch": 4.746329526916803, "percentage": 47.46, "elapsed_time": "3:57:23", "remaining_time": "4:22:46", "throughput": 4408.83, "total_tokens": 62797680} {"current_steps": 29100, "total_steps": 61300, "loss": 0.3561, "lr": 3.149591167119479e-05, "epoch": 4.747145187601958, "percentage": 47.47, "elapsed_time": "3:57:25", "remaining_time": "4:22:43", "throughput": 4408.88, "total_tokens": 62808112} {"current_steps": 29105, "total_steps": 61300, "loss": 0.3494, "lr": 3.148903790966301e-05, "epoch": 4.7479608482871125, "percentage": 47.48, "elapsed_time": "3:57:28", "remaining_time": "4:22:40", "throughput": 4408.95, "total_tokens": 62818928} {"current_steps": 29110, "total_steps": 61300, "loss": 0.3481, "lr": 3.148216362209688e-05, "epoch": 4.748776508972267, "percentage": 47.49, "elapsed_time": "3:57:30", "remaining_time": "4:22:38", "throughput": 4409.01, "total_tokens": 62829872} {"current_steps": 29115, "total_steps": 61300, "loss": 0.3389, "lr": 3.1475288809053684e-05, "epoch": 4.749592169657422, "percentage": 47.5, "elapsed_time": "3:57:32", "remaining_time": "4:22:35", "throughput": 4409.08, "total_tokens": 62840144} {"current_steps": 29120, "total_steps": 61300, "loss": 0.3274, "lr": 3.146841347109072e-05, "epoch": 4.750407830342578, "percentage": 47.5, "elapsed_time": "3:57:34", "remaining_time": "4:22:32", "throughput": 4409.15, "total_tokens": 62851856} {"current_steps": 29125, "total_steps": 61300, "loss": 0.3162, "lr": 3.146153760876534e-05, "epoch": 4.751223491027733, "percentage": 47.51, "elapsed_time": "3:57:37", "remaining_time": "4:22:30", "throughput": 4409.21, "total_tokens": 62863056} {"current_steps": 29130, "total_steps": 61300, "loss": 0.3375, "lr": 3.145466122263494e-05, "epoch": 4.7520391517128875, "percentage": 47.52, "elapsed_time": "3:57:39", "remaining_time": "4:22:27", "throughput": 4409.26, "total_tokens": 62872592} {"current_steps": 29135, "total_steps": 61300, "loss": 0.3642, "lr": 3.144778431325694e-05, "epoch": 4.752854812398042, "percentage": 47.53, "elapsed_time": "3:57:41", "remaining_time": "4:22:24", "throughput": 4409.32, "total_tokens": 62883600} {"current_steps": 29140, "total_steps": 61300, "loss": 0.3679, "lr": 3.1440906881188835e-05, "epoch": 4.753670473083197, "percentage": 47.54, "elapsed_time": "3:57:43", "remaining_time": "4:22:21", "throughput": 4409.39, "total_tokens": 62894160} {"current_steps": 29145, "total_steps": 61300, "loss": 0.3237, "lr": 3.143402892698814e-05, "epoch": 4.754486133768353, "percentage": 47.54, "elapsed_time": "3:57:46", "remaining_time": "4:22:19", "throughput": 4409.46, "total_tokens": 62905648} {"current_steps": 29150, "total_steps": 61300, "loss": 0.3409, "lr": 3.142715045121241e-05, "epoch": 4.755301794453508, "percentage": 47.55, "elapsed_time": "3:57:48", "remaining_time": "4:22:17", "throughput": 4409.53, "total_tokens": 62918256} {"current_steps": 29155, "total_steps": 61300, "loss": 0.3416, "lr": 3.142027145441926e-05, "epoch": 4.7561174551386625, "percentage": 47.56, "elapsed_time": "3:57:50", "remaining_time": "4:22:14", "throughput": 4409.6, "total_tokens": 62929200} {"current_steps": 29160, "total_steps": 61300, "loss": 0.3397, "lr": 3.141339193716633e-05, "epoch": 4.756933115823817, "percentage": 47.57, "elapsed_time": "3:57:53", "remaining_time": "4:22:11", "throughput": 4409.66, "total_tokens": 62940016} {"current_steps": 29165, "total_steps": 61300, "loss": 0.3412, "lr": 3.1406511900011295e-05, "epoch": 4.757748776508972, "percentage": 47.58, "elapsed_time": "3:57:55", "remaining_time": "4:22:08", "throughput": 4409.73, "total_tokens": 62949744} {"current_steps": 29170, "total_steps": 61300, "loss": 0.3435, "lr": 3.139963134351191e-05, "epoch": 4.758564437194127, "percentage": 47.59, "elapsed_time": "3:57:57", "remaining_time": "4:22:06", "throughput": 4409.78, "total_tokens": 62960848} {"current_steps": 29175, "total_steps": 61300, "loss": 0.3491, "lr": 3.139275026822594e-05, "epoch": 4.759380097879282, "percentage": 47.59, "elapsed_time": "3:57:59", "remaining_time": "4:22:03", "throughput": 4409.84, "total_tokens": 62971984} {"current_steps": 29180, "total_steps": 61300, "loss": 0.3569, "lr": 3.138586867471118e-05, "epoch": 4.760195758564437, "percentage": 47.6, "elapsed_time": "3:58:02", "remaining_time": "4:22:00", "throughput": 4409.89, "total_tokens": 62982224} {"current_steps": 29185, "total_steps": 61300, "loss": 0.3486, "lr": 3.137898656352551e-05, "epoch": 4.761011419249592, "percentage": 47.61, "elapsed_time": "3:58:04", "remaining_time": "4:21:58", "throughput": 4409.95, "total_tokens": 62992464} {"current_steps": 29190, "total_steps": 61300, "loss": 0.3429, "lr": 3.137210393522683e-05, "epoch": 4.761827079934747, "percentage": 47.62, "elapsed_time": "3:58:06", "remaining_time": "4:21:55", "throughput": 4410.01, "total_tokens": 63002960} {"current_steps": 29195, "total_steps": 61300, "loss": 0.3445, "lr": 3.136522079037307e-05, "epoch": 4.762642740619902, "percentage": 47.63, "elapsed_time": "3:58:08", "remaining_time": "4:21:52", "throughput": 4410.08, "total_tokens": 63013520} {"current_steps": 29200, "total_steps": 61300, "loss": 0.3268, "lr": 3.135833712952222e-05, "epoch": 4.763458401305057, "percentage": 47.63, "elapsed_time": "3:58:10", "remaining_time": "4:21:49", "throughput": 4410.13, "total_tokens": 63023760} {"current_steps": 29205, "total_steps": 61300, "loss": 0.3381, "lr": 3.135145295323229e-05, "epoch": 4.764274061990212, "percentage": 47.64, "elapsed_time": "3:58:13", "remaining_time": "4:21:47", "throughput": 4410.19, "total_tokens": 63035248} {"current_steps": 29210, "total_steps": 61300, "loss": 0.3805, "lr": 3.1344568262061366e-05, "epoch": 4.765089722675367, "percentage": 47.65, "elapsed_time": "3:58:15", "remaining_time": "4:21:44", "throughput": 4410.25, "total_tokens": 63045904} {"current_steps": 29215, "total_steps": 61300, "loss": 0.3512, "lr": 3.133768305656755e-05, "epoch": 4.765905383360522, "percentage": 47.66, "elapsed_time": "3:58:17", "remaining_time": "4:21:42", "throughput": 4410.31, "total_tokens": 63056336} {"current_steps": 29220, "total_steps": 61300, "loss": 0.3433, "lr": 3.1330797337308984e-05, "epoch": 4.766721044045677, "percentage": 47.67, "elapsed_time": "3:58:19", "remaining_time": "4:21:39", "throughput": 4410.37, "total_tokens": 63067376} {"current_steps": 29225, "total_steps": 61300, "loss": 0.3322, "lr": 3.1323911104843865e-05, "epoch": 4.767536704730832, "percentage": 47.68, "elapsed_time": "3:58:21", "remaining_time": "4:21:36", "throughput": 4410.41, "total_tokens": 63077456} {"current_steps": 29230, "total_steps": 61300, "loss": 0.3439, "lr": 3.131702435973042e-05, "epoch": 4.768352365415987, "percentage": 47.68, "elapsed_time": "3:58:23", "remaining_time": "4:21:33", "throughput": 4410.46, "total_tokens": 63087024} {"current_steps": 29235, "total_steps": 61300, "loss": 0.3347, "lr": 3.1310137102526926e-05, "epoch": 4.769168026101142, "percentage": 47.69, "elapsed_time": "3:58:26", "remaining_time": "4:21:31", "throughput": 4410.53, "total_tokens": 63098608} {"current_steps": 29240, "total_steps": 61300, "loss": 0.3405, "lr": 3.13032493337917e-05, "epoch": 4.769983686786297, "percentage": 47.7, "elapsed_time": "3:58:28", "remaining_time": "4:21:28", "throughput": 4410.58, "total_tokens": 63108144} {"current_steps": 29245, "total_steps": 61300, "loss": 0.338, "lr": 3.129636105408311e-05, "epoch": 4.770799347471452, "percentage": 47.71, "elapsed_time": "3:58:30", "remaining_time": "4:21:25", "throughput": 4410.65, "total_tokens": 63118736} {"current_steps": 29250, "total_steps": 61300, "loss": 0.3637, "lr": 3.128947226395954e-05, "epoch": 4.771615008156607, "percentage": 47.72, "elapsed_time": "3:58:32", "remaining_time": "4:21:22", "throughput": 4410.7, "total_tokens": 63128656} {"current_steps": 29255, "total_steps": 61300, "loss": 0.3408, "lr": 3.1282582963979434e-05, "epoch": 4.7724306688417615, "percentage": 47.72, "elapsed_time": "3:58:34", "remaining_time": "4:21:20", "throughput": 4410.76, "total_tokens": 63139632} {"current_steps": 29260, "total_steps": 61300, "loss": 0.3376, "lr": 3.127569315470128e-05, "epoch": 4.773246329526917, "percentage": 47.73, "elapsed_time": "3:58:37", "remaining_time": "4:21:17", "throughput": 4410.83, "total_tokens": 63150128} {"current_steps": 29265, "total_steps": 61300, "loss": 0.3792, "lr": 3.12688028366836e-05, "epoch": 4.774061990212072, "percentage": 47.74, "elapsed_time": "3:58:39", "remaining_time": "4:21:14", "throughput": 4410.87, "total_tokens": 63160112} {"current_steps": 29270, "total_steps": 61300, "loss": 0.389, "lr": 3.126191201048494e-05, "epoch": 4.774877650897227, "percentage": 47.75, "elapsed_time": "3:58:41", "remaining_time": "4:21:12", "throughput": 4410.95, "total_tokens": 63172592} {"current_steps": 29275, "total_steps": 61300, "loss": 0.3227, "lr": 3.125502067666393e-05, "epoch": 4.775693311582382, "percentage": 47.76, "elapsed_time": "3:58:44", "remaining_time": "4:21:09", "throughput": 4411.02, "total_tokens": 63184304} {"current_steps": 29280, "total_steps": 61300, "loss": 0.3316, "lr": 3.1248128835779206e-05, "epoch": 4.7765089722675365, "percentage": 47.77, "elapsed_time": "3:58:46", "remaining_time": "4:21:07", "throughput": 4411.09, "total_tokens": 63195184} {"current_steps": 29285, "total_steps": 61300, "loss": 0.339, "lr": 3.124123648838946e-05, "epoch": 4.777324632952691, "percentage": 47.77, "elapsed_time": "3:58:48", "remaining_time": "4:21:04", "throughput": 4411.15, "total_tokens": 63206064} {"current_steps": 29290, "total_steps": 61300, "loss": 0.3294, "lr": 3.123434363505341e-05, "epoch": 4.778140293637847, "percentage": 47.78, "elapsed_time": "3:58:50", "remaining_time": "4:21:01", "throughput": 4411.2, "total_tokens": 63215536} {"current_steps": 29295, "total_steps": 61300, "loss": 0.3337, "lr": 3.122745027632983e-05, "epoch": 4.778955954323002, "percentage": 47.79, "elapsed_time": "3:58:52", "remaining_time": "4:20:58", "throughput": 4411.26, "total_tokens": 63226480} {"current_steps": 29300, "total_steps": 61300, "loss": 0.3319, "lr": 3.1220556412777536e-05, "epoch": 4.779771615008157, "percentage": 47.8, "elapsed_time": "3:58:55", "remaining_time": "4:20:56", "throughput": 4411.32, "total_tokens": 63237200} {"current_steps": 29305, "total_steps": 61300, "loss": 0.3069, "lr": 3.121366204495538e-05, "epoch": 4.780587275693311, "percentage": 47.81, "elapsed_time": "3:58:57", "remaining_time": "4:20:53", "throughput": 4411.39, "total_tokens": 63247632} {"current_steps": 29310, "total_steps": 61300, "loss": 0.3316, "lr": 3.120676717342225e-05, "epoch": 4.781402936378466, "percentage": 47.81, "elapsed_time": "3:58:59", "remaining_time": "4:20:50", "throughput": 4411.45, "total_tokens": 63258864} {"current_steps": 29315, "total_steps": 61300, "loss": 0.3461, "lr": 3.119987179873707e-05, "epoch": 4.782218597063622, "percentage": 47.82, "elapsed_time": "3:59:02", "remaining_time": "4:20:48", "throughput": 4411.52, "total_tokens": 63270928} {"current_steps": 29320, "total_steps": 61300, "loss": 0.341, "lr": 3.119297592145884e-05, "epoch": 4.783034257748777, "percentage": 47.83, "elapsed_time": "3:59:04", "remaining_time": "4:20:45", "throughput": 4411.58, "total_tokens": 63281200} {"current_steps": 29325, "total_steps": 61300, "loss": 0.3608, "lr": 3.1186079542146554e-05, "epoch": 4.783849918433932, "percentage": 47.84, "elapsed_time": "3:59:06", "remaining_time": "4:20:42", "throughput": 4411.62, "total_tokens": 63291184} {"current_steps": 29330, "total_steps": 61300, "loss": 0.3343, "lr": 3.117918266135927e-05, "epoch": 4.784665579119086, "percentage": 47.85, "elapsed_time": "3:59:08", "remaining_time": "4:20:40", "throughput": 4411.69, "total_tokens": 63302544} {"current_steps": 29335, "total_steps": 61300, "loss": 0.3606, "lr": 3.1172285279656085e-05, "epoch": 4.785481239804241, "percentage": 47.85, "elapsed_time": "3:59:10", "remaining_time": "4:20:37", "throughput": 4411.76, "total_tokens": 63312464} {"current_steps": 29340, "total_steps": 61300, "loss": 0.353, "lr": 3.1165387397596136e-05, "epoch": 4.786296900489396, "percentage": 47.86, "elapsed_time": "3:59:13", "remaining_time": "4:20:34", "throughput": 4411.84, "total_tokens": 63323856} {"current_steps": 29345, "total_steps": 61300, "loss": 0.3648, "lr": 3.1158489015738604e-05, "epoch": 4.787112561174552, "percentage": 47.87, "elapsed_time": "3:59:15", "remaining_time": "4:20:32", "throughput": 4411.91, "total_tokens": 63335664} {"current_steps": 29350, "total_steps": 61300, "loss": 0.3167, "lr": 3.1151590134642705e-05, "epoch": 4.787928221859707, "percentage": 47.88, "elapsed_time": "3:59:18", "remaining_time": "4:20:29", "throughput": 4411.99, "total_tokens": 63347632} {"current_steps": 29355, "total_steps": 61300, "loss": 0.3137, "lr": 3.114469075486769e-05, "epoch": 4.788743882544861, "percentage": 47.89, "elapsed_time": "3:59:20", "remaining_time": "4:20:27", "throughput": 4412.07, "total_tokens": 63359152} {"current_steps": 29360, "total_steps": 61300, "loss": 0.3063, "lr": 3.113779087697287e-05, "epoch": 4.789559543230016, "percentage": 47.9, "elapsed_time": "3:59:22", "remaining_time": "4:20:24", "throughput": 4412.13, "total_tokens": 63370224} {"current_steps": 29365, "total_steps": 61300, "loss": 0.3745, "lr": 3.1130890501517586e-05, "epoch": 4.790375203915171, "percentage": 47.9, "elapsed_time": "3:59:24", "remaining_time": "4:20:22", "throughput": 4412.19, "total_tokens": 63380784} {"current_steps": 29370, "total_steps": 61300, "loss": 0.3388, "lr": 3.11239896290612e-05, "epoch": 4.791190864600326, "percentage": 47.91, "elapsed_time": "3:59:27", "remaining_time": "4:20:19", "throughput": 4412.26, "total_tokens": 63392656} {"current_steps": 29375, "total_steps": 61300, "loss": 0.3368, "lr": 3.111708826016315e-05, "epoch": 4.7920065252854815, "percentage": 47.92, "elapsed_time": "3:59:29", "remaining_time": "4:20:17", "throughput": 4412.33, "total_tokens": 63403440} {"current_steps": 29380, "total_steps": 61300, "loss": 0.351, "lr": 3.1110186395382885e-05, "epoch": 4.792822185970636, "percentage": 47.93, "elapsed_time": "3:59:31", "remaining_time": "4:20:14", "throughput": 4412.38, "total_tokens": 63413968} {"current_steps": 29385, "total_steps": 61300, "loss": 0.3551, "lr": 3.1103284035279905e-05, "epoch": 4.793637846655791, "percentage": 47.94, "elapsed_time": "3:59:34", "remaining_time": "4:20:11", "throughput": 4412.45, "total_tokens": 63424752} {"current_steps": 29390, "total_steps": 61300, "loss": 0.3283, "lr": 3.109638118041376e-05, "epoch": 4.794453507340946, "percentage": 47.94, "elapsed_time": "3:59:36", "remaining_time": "4:20:09", "throughput": 4412.51, "total_tokens": 63435792} {"current_steps": 29395, "total_steps": 61300, "loss": 0.3296, "lr": 3.108947783134402e-05, "epoch": 4.795269168026101, "percentage": 47.95, "elapsed_time": "3:59:38", "remaining_time": "4:20:06", "throughput": 4412.59, "total_tokens": 63448016} {"current_steps": 29400, "total_steps": 61300, "loss": 0.3425, "lr": 3.10825739886303e-05, "epoch": 4.7960848287112565, "percentage": 47.96, "elapsed_time": "3:59:40", "remaining_time": "4:20:03", "throughput": 4412.64, "total_tokens": 63456880} {"current_steps": 29405, "total_steps": 61300, "loss": 0.3079, "lr": 3.107566965283228e-05, "epoch": 4.796900489396411, "percentage": 47.97, "elapsed_time": "3:59:42", "remaining_time": "4:20:00", "throughput": 4412.71, "total_tokens": 63467504} {"current_steps": 29410, "total_steps": 61300, "loss": 0.333, "lr": 3.106876482450964e-05, "epoch": 4.797716150081566, "percentage": 47.98, "elapsed_time": "3:59:45", "remaining_time": "4:19:58", "throughput": 4412.78, "total_tokens": 63478288} {"current_steps": 29415, "total_steps": 61300, "loss": 0.3852, "lr": 3.106185950422215e-05, "epoch": 4.798531810766721, "percentage": 47.99, "elapsed_time": "3:59:47", "remaining_time": "4:19:55", "throughput": 4412.82, "total_tokens": 63487888} {"current_steps": 29420, "total_steps": 61300, "loss": 0.246, "lr": 3.105495369252956e-05, "epoch": 4.799347471451876, "percentage": 47.99, "elapsed_time": "3:59:49", "remaining_time": "4:19:52", "throughput": 4412.88, "total_tokens": 63498576} {"current_steps": 29425, "total_steps": 61300, "loss": 0.3342, "lr": 3.104804738999169e-05, "epoch": 4.800163132137031, "percentage": 48.0, "elapsed_time": "3:59:51", "remaining_time": "4:19:50", "throughput": 4412.95, "total_tokens": 63509872} {"current_steps": 29430, "total_steps": 61300, "loss": 0.3378, "lr": 3.1041140597168425e-05, "epoch": 4.800978792822186, "percentage": 48.01, "elapsed_time": "3:59:54", "remaining_time": "4:19:47", "throughput": 4413.0, "total_tokens": 63521328} {"current_steps": 29435, "total_steps": 61300, "loss": 0.3545, "lr": 3.1034233314619647e-05, "epoch": 4.801794453507341, "percentage": 48.02, "elapsed_time": "3:59:56", "remaining_time": "4:19:44", "throughput": 4413.06, "total_tokens": 63531248} {"current_steps": 29440, "total_steps": 61300, "loss": 0.3744, "lr": 3.102732554290531e-05, "epoch": 4.802610114192496, "percentage": 48.03, "elapsed_time": "3:59:58", "remaining_time": "4:19:41", "throughput": 4413.12, "total_tokens": 63541648} {"current_steps": 29445, "total_steps": 61300, "loss": 0.3583, "lr": 3.102041728258537e-05, "epoch": 4.803425774877651, "percentage": 48.03, "elapsed_time": "4:00:00", "remaining_time": "4:19:39", "throughput": 4413.16, "total_tokens": 63551408} {"current_steps": 29450, "total_steps": 61300, "loss": 0.2817, "lr": 3.101350853421986e-05, "epoch": 4.804241435562806, "percentage": 48.04, "elapsed_time": "4:00:02", "remaining_time": "4:19:36", "throughput": 4413.22, "total_tokens": 63562160} {"current_steps": 29455, "total_steps": 61300, "loss": 0.3269, "lr": 3.1006599298368826e-05, "epoch": 4.80505709624796, "percentage": 48.05, "elapsed_time": "4:00:05", "remaining_time": "4:19:33", "throughput": 4413.29, "total_tokens": 63573648} {"current_steps": 29460, "total_steps": 61300, "loss": 0.3319, "lr": 3.099968957559239e-05, "epoch": 4.805872756933116, "percentage": 48.06, "elapsed_time": "4:00:07", "remaining_time": "4:19:31", "throughput": 4413.35, "total_tokens": 63584048} {"current_steps": 29465, "total_steps": 61300, "loss": 0.314, "lr": 3.0992779366450666e-05, "epoch": 4.806688417618271, "percentage": 48.07, "elapsed_time": "4:00:09", "remaining_time": "4:19:28", "throughput": 4413.42, "total_tokens": 63595344} {"current_steps": 29470, "total_steps": 61300, "loss": 0.2692, "lr": 3.098586867150385e-05, "epoch": 4.807504078303426, "percentage": 48.08, "elapsed_time": "4:00:11", "remaining_time": "4:19:26", "throughput": 4413.49, "total_tokens": 63606800} {"current_steps": 29475, "total_steps": 61300, "loss": 0.2967, "lr": 3.097895749131214e-05, "epoch": 4.808319738988581, "percentage": 48.08, "elapsed_time": "4:00:14", "remaining_time": "4:19:23", "throughput": 4413.56, "total_tokens": 63617456} {"current_steps": 29480, "total_steps": 61300, "loss": 0.3232, "lr": 3.09720458264358e-05, "epoch": 4.809135399673735, "percentage": 48.09, "elapsed_time": "4:00:16", "remaining_time": "4:19:20", "throughput": 4413.63, "total_tokens": 63628336} {"current_steps": 29485, "total_steps": 61300, "loss": 0.3289, "lr": 3.096513367743513e-05, "epoch": 4.809951060358891, "percentage": 48.1, "elapsed_time": "4:00:18", "remaining_time": "4:19:18", "throughput": 4413.71, "total_tokens": 63640720} {"current_steps": 29490, "total_steps": 61300, "loss": 0.352, "lr": 3.095822104487045e-05, "epoch": 4.810766721044046, "percentage": 48.11, "elapsed_time": "4:00:21", "remaining_time": "4:19:15", "throughput": 4413.76, "total_tokens": 63650960} {"current_steps": 29495, "total_steps": 61300, "loss": 0.3378, "lr": 3.0951307929302136e-05, "epoch": 4.811582381729201, "percentage": 48.12, "elapsed_time": "4:00:23", "remaining_time": "4:19:12", "throughput": 4413.83, "total_tokens": 63662192} {"current_steps": 29500, "total_steps": 61300, "loss": 0.3391, "lr": 3.094439433129061e-05, "epoch": 4.8123980424143555, "percentage": 48.12, "elapsed_time": "4:00:25", "remaining_time": "4:19:10", "throughput": 4413.89, "total_tokens": 63673232} {"current_steps": 29505, "total_steps": 61300, "loss": 0.391, "lr": 3.093748025139632e-05, "epoch": 4.81321370309951, "percentage": 48.13, "elapsed_time": "4:00:27", "remaining_time": "4:19:07", "throughput": 4413.96, "total_tokens": 63683728} {"current_steps": 29510, "total_steps": 61300, "loss": 0.4014, "lr": 3.093056569017975e-05, "epoch": 4.814029363784666, "percentage": 48.14, "elapsed_time": "4:00:30", "remaining_time": "4:19:04", "throughput": 4414.03, "total_tokens": 63694768} {"current_steps": 29515, "total_steps": 61300, "loss": 0.3432, "lr": 3.0923650648201436e-05, "epoch": 4.814845024469821, "percentage": 48.15, "elapsed_time": "4:00:32", "remaining_time": "4:19:02", "throughput": 4414.09, "total_tokens": 63705488} {"current_steps": 29520, "total_steps": 61300, "loss": 0.3253, "lr": 3.0916735126021945e-05, "epoch": 4.815660685154976, "percentage": 48.16, "elapsed_time": "4:00:34", "remaining_time": "4:18:59", "throughput": 4414.14, "total_tokens": 63715600} {"current_steps": 29525, "total_steps": 61300, "loss": 0.3576, "lr": 3.090981912420188e-05, "epoch": 4.8164763458401305, "percentage": 48.16, "elapsed_time": "4:00:36", "remaining_time": "4:18:56", "throughput": 4414.19, "total_tokens": 63726000} {"current_steps": 29530, "total_steps": 61300, "loss": 0.3603, "lr": 3.09029026433019e-05, "epoch": 4.817292006525285, "percentage": 48.17, "elapsed_time": "4:00:38", "remaining_time": "4:18:54", "throughput": 4414.24, "total_tokens": 63736400} {"current_steps": 29535, "total_steps": 61300, "loss": 0.3409, "lr": 3.0895985683882675e-05, "epoch": 4.81810766721044, "percentage": 48.18, "elapsed_time": "4:00:41", "remaining_time": "4:18:51", "throughput": 4414.29, "total_tokens": 63747600} {"current_steps": 29540, "total_steps": 61300, "loss": 0.3423, "lr": 3.088906824650493e-05, "epoch": 4.818923327895595, "percentage": 48.19, "elapsed_time": "4:00:43", "remaining_time": "4:18:48", "throughput": 4414.36, "total_tokens": 63758416} {"current_steps": 29545, "total_steps": 61300, "loss": 0.3465, "lr": 3.088215033172944e-05, "epoch": 4.819738988580751, "percentage": 48.2, "elapsed_time": "4:00:45", "remaining_time": "4:18:46", "throughput": 4414.43, "total_tokens": 63768976} {"current_steps": 29550, "total_steps": 61300, "loss": 0.3426, "lr": 3.087523194011699e-05, "epoch": 4.8205546492659055, "percentage": 48.21, "elapsed_time": "4:00:47", "remaining_time": "4:18:43", "throughput": 4414.47, "total_tokens": 63778896} {"current_steps": 29555, "total_steps": 61300, "loss": 0.344, "lr": 3.086831307222844e-05, "epoch": 4.82137030995106, "percentage": 48.21, "elapsed_time": "4:00:50", "remaining_time": "4:18:40", "throughput": 4414.54, "total_tokens": 63790384} {"current_steps": 29560, "total_steps": 61300, "loss": 0.3028, "lr": 3.086139372862464e-05, "epoch": 4.822185970636215, "percentage": 48.22, "elapsed_time": "4:00:52", "remaining_time": "4:18:38", "throughput": 4414.59, "total_tokens": 63800688} {"current_steps": 29565, "total_steps": 61300, "loss": 0.3492, "lr": 3.085447390986653e-05, "epoch": 4.82300163132137, "percentage": 48.23, "elapsed_time": "4:00:54", "remaining_time": "4:18:35", "throughput": 4414.66, "total_tokens": 63811856} {"current_steps": 29570, "total_steps": 61300, "loss": 0.3515, "lr": 3.084755361651507e-05, "epoch": 4.823817292006526, "percentage": 48.24, "elapsed_time": "4:00:56", "remaining_time": "4:18:32", "throughput": 4414.71, "total_tokens": 63822576} {"current_steps": 29575, "total_steps": 61300, "loss": 0.3657, "lr": 3.0840632849131236e-05, "epoch": 4.8246329526916805, "percentage": 48.25, "elapsed_time": "4:00:59", "remaining_time": "4:18:30", "throughput": 4414.76, "total_tokens": 63833168} {"current_steps": 29580, "total_steps": 61300, "loss": 0.3616, "lr": 3.083371160827606e-05, "epoch": 4.825448613376835, "percentage": 48.25, "elapsed_time": "4:01:01", "remaining_time": "4:18:27", "throughput": 4414.82, "total_tokens": 63843312} {"current_steps": 29585, "total_steps": 61300, "loss": 0.3534, "lr": 3.082678989451063e-05, "epoch": 4.82626427406199, "percentage": 48.26, "elapsed_time": "4:01:03", "remaining_time": "4:18:24", "throughput": 4414.88, "total_tokens": 63853904} {"current_steps": 29590, "total_steps": 61300, "loss": 0.3825, "lr": 3.081986770839605e-05, "epoch": 4.827079934747145, "percentage": 48.27, "elapsed_time": "4:01:05", "remaining_time": "4:18:22", "throughput": 4414.94, "total_tokens": 63865072} {"current_steps": 29595, "total_steps": 61300, "loss": 0.3119, "lr": 3.0812945050493464e-05, "epoch": 4.827895595432301, "percentage": 48.28, "elapsed_time": "4:01:07", "remaining_time": "4:18:19", "throughput": 4415.01, "total_tokens": 63875760} {"current_steps": 29600, "total_steps": 61300, "loss": 0.3058, "lr": 3.080602192136405e-05, "epoch": 4.828711256117455, "percentage": 48.29, "elapsed_time": "4:01:10", "remaining_time": "4:18:16", "throughput": 4415.07, "total_tokens": 63887216} {"current_steps": 29605, "total_steps": 61300, "loss": 0.3683, "lr": 3.079909832156905e-05, "epoch": 4.82952691680261, "percentage": 48.3, "elapsed_time": "4:01:12", "remaining_time": "4:18:14", "throughput": 4415.12, "total_tokens": 63897104} {"current_steps": 29610, "total_steps": 61300, "loss": 0.3722, "lr": 3.0792174251669706e-05, "epoch": 4.830342577487765, "percentage": 48.3, "elapsed_time": "4:01:14", "remaining_time": "4:18:11", "throughput": 4415.16, "total_tokens": 63907984} {"current_steps": 29615, "total_steps": 61300, "loss": 0.3609, "lr": 3.078524971222733e-05, "epoch": 4.83115823817292, "percentage": 48.31, "elapsed_time": "4:01:16", "remaining_time": "4:18:08", "throughput": 4415.23, "total_tokens": 63918640} {"current_steps": 29620, "total_steps": 61300, "loss": 0.3585, "lr": 3.0778324703803256e-05, "epoch": 4.831973898858075, "percentage": 48.32, "elapsed_time": "4:01:19", "remaining_time": "4:18:05", "throughput": 4415.3, "total_tokens": 63929136} {"current_steps": 29625, "total_steps": 61300, "loss": 0.3853, "lr": 3.0771399226958865e-05, "epoch": 4.8327895595432295, "percentage": 48.33, "elapsed_time": "4:01:21", "remaining_time": "4:18:03", "throughput": 4415.36, "total_tokens": 63940464} {"current_steps": 29630, "total_steps": 61300, "loss": 0.3718, "lr": 3.076447328225557e-05, "epoch": 4.833605220228385, "percentage": 48.34, "elapsed_time": "4:01:23", "remaining_time": "4:18:00", "throughput": 4415.42, "total_tokens": 63950512} {"current_steps": 29635, "total_steps": 61300, "loss": 0.3426, "lr": 3.075754687025482e-05, "epoch": 4.83442088091354, "percentage": 48.34, "elapsed_time": "4:01:25", "remaining_time": "4:17:58", "throughput": 4415.48, "total_tokens": 63961840} {"current_steps": 29640, "total_steps": 61300, "loss": 0.3289, "lr": 3.0750619991518115e-05, "epoch": 4.835236541598695, "percentage": 48.35, "elapsed_time": "4:01:27", "remaining_time": "4:17:55", "throughput": 4415.53, "total_tokens": 63971440} {"current_steps": 29645, "total_steps": 61300, "loss": 0.3586, "lr": 3.074369264660697e-05, "epoch": 4.83605220228385, "percentage": 48.36, "elapsed_time": "4:01:30", "remaining_time": "4:17:52", "throughput": 4415.6, "total_tokens": 63982608} {"current_steps": 29650, "total_steps": 61300, "loss": 0.3354, "lr": 3.0736764836082954e-05, "epoch": 4.8368678629690045, "percentage": 48.37, "elapsed_time": "4:01:32", "remaining_time": "4:17:50", "throughput": 4415.68, "total_tokens": 63994000} {"current_steps": 29655, "total_steps": 61300, "loss": 0.3333, "lr": 3.072983656050767e-05, "epoch": 4.83768352365416, "percentage": 48.38, "elapsed_time": "4:01:34", "remaining_time": "4:17:47", "throughput": 4415.74, "total_tokens": 64005008} {"current_steps": 29660, "total_steps": 61300, "loss": 0.3361, "lr": 3.072290782044276e-05, "epoch": 4.838499184339315, "percentage": 48.38, "elapsed_time": "4:01:36", "remaining_time": "4:17:44", "throughput": 4415.8, "total_tokens": 64014448} {"current_steps": 29665, "total_steps": 61300, "loss": 0.3235, "lr": 3.0715978616449906e-05, "epoch": 4.83931484502447, "percentage": 48.39, "elapsed_time": "4:01:39", "remaining_time": "4:17:42", "throughput": 4415.87, "total_tokens": 64026672} {"current_steps": 29670, "total_steps": 61300, "loss": 0.3459, "lr": 3.070904894909083e-05, "epoch": 4.840130505709625, "percentage": 48.4, "elapsed_time": "4:01:41", "remaining_time": "4:17:39", "throughput": 4415.92, "total_tokens": 64036752} {"current_steps": 29675, "total_steps": 61300, "loss": 0.3343, "lr": 3.070211881892727e-05, "epoch": 4.8409461663947795, "percentage": 48.41, "elapsed_time": "4:01:43", "remaining_time": "4:17:36", "throughput": 4416.0, "total_tokens": 64047760} {"current_steps": 29680, "total_steps": 61300, "loss": 0.3411, "lr": 3.069518822652103e-05, "epoch": 4.841761827079935, "percentage": 48.42, "elapsed_time": "4:01:46", "remaining_time": "4:17:34", "throughput": 4416.08, "total_tokens": 64059664} {"current_steps": 29685, "total_steps": 61300, "loss": 0.3486, "lr": 3.0688257172433944e-05, "epoch": 4.84257748776509, "percentage": 48.43, "elapsed_time": "4:01:48", "remaining_time": "4:17:31", "throughput": 4416.15, "total_tokens": 64071408} {"current_steps": 29690, "total_steps": 61300, "loss": 0.3485, "lr": 3.068132565722786e-05, "epoch": 4.843393148450245, "percentage": 48.43, "elapsed_time": "4:01:50", "remaining_time": "4:17:29", "throughput": 4416.21, "total_tokens": 64082448} {"current_steps": 29695, "total_steps": 61300, "loss": 0.3552, "lr": 3.06743936814647e-05, "epoch": 4.8442088091354, "percentage": 48.44, "elapsed_time": "4:01:53", "remaining_time": "4:17:26", "throughput": 4416.27, "total_tokens": 64094320} {"current_steps": 29700, "total_steps": 61300, "loss": 0.3503, "lr": 3.0667461245706386e-05, "epoch": 4.8450244698205545, "percentage": 48.45, "elapsed_time": "4:01:55", "remaining_time": "4:17:24", "throughput": 4416.35, "total_tokens": 64105392} {"current_steps": 29705, "total_steps": 61300, "loss": 0.3492, "lr": 3.066052835051491e-05, "epoch": 4.845840130505709, "percentage": 48.46, "elapsed_time": "4:01:57", "remaining_time": "4:17:21", "throughput": 4416.42, "total_tokens": 64117008} {"current_steps": 29710, "total_steps": 61300, "loss": 0.3588, "lr": 3.065359499645228e-05, "epoch": 4.846655791190865, "percentage": 48.47, "elapsed_time": "4:02:00", "remaining_time": "4:17:18", "throughput": 4416.49, "total_tokens": 64128016} {"current_steps": 29715, "total_steps": 61300, "loss": 0.3663, "lr": 3.064666118408057e-05, "epoch": 4.84747145187602, "percentage": 48.47, "elapsed_time": "4:02:02", "remaining_time": "4:17:16", "throughput": 4416.54, "total_tokens": 64138448} {"current_steps": 29720, "total_steps": 61300, "loss": 0.3606, "lr": 3.0639726913961833e-05, "epoch": 4.848287112561175, "percentage": 48.48, "elapsed_time": "4:02:04", "remaining_time": "4:17:13", "throughput": 4416.59, "total_tokens": 64148848} {"current_steps": 29725, "total_steps": 61300, "loss": 0.3283, "lr": 3.0632792186658225e-05, "epoch": 4.849102773246329, "percentage": 48.49, "elapsed_time": "4:02:06", "remaining_time": "4:17:10", "throughput": 4416.65, "total_tokens": 64159280} {"current_steps": 29730, "total_steps": 61300, "loss": 0.3219, "lr": 3.062585700273191e-05, "epoch": 4.849918433931484, "percentage": 48.5, "elapsed_time": "4:02:08", "remaining_time": "4:17:08", "throughput": 4416.72, "total_tokens": 64170384} {"current_steps": 29735, "total_steps": 61300, "loss": 0.3384, "lr": 3.0618921362745075e-05, "epoch": 4.850734094616639, "percentage": 48.51, "elapsed_time": "4:02:10", "remaining_time": "4:17:05", "throughput": 4416.77, "total_tokens": 64180112} {"current_steps": 29740, "total_steps": 61300, "loss": 0.3315, "lr": 3.061198526725996e-05, "epoch": 4.851549755301795, "percentage": 48.52, "elapsed_time": "4:02:13", "remaining_time": "4:17:02", "throughput": 4416.83, "total_tokens": 64190032} {"current_steps": 29745, "total_steps": 61300, "loss": 0.3655, "lr": 3.060504871683885e-05, "epoch": 4.85236541598695, "percentage": 48.52, "elapsed_time": "4:02:15", "remaining_time": "4:16:59", "throughput": 4416.9, "total_tokens": 64201936} {"current_steps": 29750, "total_steps": 61300, "loss": 0.3496, "lr": 3.059811171204404e-05, "epoch": 4.853181076672104, "percentage": 48.53, "elapsed_time": "4:02:17", "remaining_time": "4:16:57", "throughput": 4416.96, "total_tokens": 64212784} {"current_steps": 29755, "total_steps": 61300, "loss": 0.3285, "lr": 3.0591174253437904e-05, "epoch": 4.853996737357259, "percentage": 48.54, "elapsed_time": "4:02:20", "remaining_time": "4:16:54", "throughput": 4417.03, "total_tokens": 64224208} {"current_steps": 29760, "total_steps": 61300, "loss": 0.3631, "lr": 3.05842363415828e-05, "epoch": 4.854812398042414, "percentage": 48.55, "elapsed_time": "4:02:22", "remaining_time": "4:16:52", "throughput": 4417.1, "total_tokens": 64235792} {"current_steps": 29765, "total_steps": 61300, "loss": 0.3416, "lr": 3.057729797704118e-05, "epoch": 4.85562805872757, "percentage": 48.56, "elapsed_time": "4:02:24", "remaining_time": "4:16:49", "throughput": 4417.16, "total_tokens": 64246512} {"current_steps": 29770, "total_steps": 61300, "loss": 0.3375, "lr": 3.057035916037548e-05, "epoch": 4.856443719412725, "percentage": 48.56, "elapsed_time": "4:02:26", "remaining_time": "4:16:46", "throughput": 4417.21, "total_tokens": 64256624} {"current_steps": 29775, "total_steps": 61300, "loss": 0.3169, "lr": 3.05634198921482e-05, "epoch": 4.857259380097879, "percentage": 48.57, "elapsed_time": "4:02:28", "remaining_time": "4:16:44", "throughput": 4417.25, "total_tokens": 64266544} {"current_steps": 29780, "total_steps": 61300, "loss": 0.3553, "lr": 3.055648017292188e-05, "epoch": 4.858075040783034, "percentage": 48.58, "elapsed_time": "4:02:31", "remaining_time": "4:16:41", "throughput": 4417.32, "total_tokens": 64277904} {"current_steps": 29785, "total_steps": 61300, "loss": 0.3523, "lr": 3.0549540003259084e-05, "epoch": 4.858890701468189, "percentage": 48.59, "elapsed_time": "4:02:33", "remaining_time": "4:16:38", "throughput": 4417.37, "total_tokens": 64288464} {"current_steps": 29790, "total_steps": 61300, "loss": 0.327, "lr": 3.054259938372242e-05, "epoch": 4.859706362153344, "percentage": 48.6, "elapsed_time": "4:02:35", "remaining_time": "4:16:36", "throughput": 4417.44, "total_tokens": 64299408} {"current_steps": 29795, "total_steps": 61300, "loss": 0.332, "lr": 3.0535658314874515e-05, "epoch": 4.8605220228384995, "percentage": 48.61, "elapsed_time": "4:02:38", "remaining_time": "4:16:33", "throughput": 4417.51, "total_tokens": 64310224} {"current_steps": 29800, "total_steps": 61300, "loss": 0.3534, "lr": 3.0528716797278064e-05, "epoch": 4.861337683523654, "percentage": 48.61, "elapsed_time": "4:02:40", "remaining_time": "4:16:30", "throughput": 4417.57, "total_tokens": 64321520} {"current_steps": 29805, "total_steps": 61300, "loss": 0.344, "lr": 3.052177483149578e-05, "epoch": 4.862153344208809, "percentage": 48.62, "elapsed_time": "4:02:42", "remaining_time": "4:16:28", "throughput": 4417.64, "total_tokens": 64332880} {"current_steps": 29810, "total_steps": 61300, "loss": 0.3428, "lr": 3.0514832418090406e-05, "epoch": 4.862969004893964, "percentage": 48.63, "elapsed_time": "4:02:44", "remaining_time": "4:16:25", "throughput": 4417.69, "total_tokens": 64342576} {"current_steps": 29815, "total_steps": 61300, "loss": 0.3561, "lr": 3.050788955762474e-05, "epoch": 4.863784665579119, "percentage": 48.64, "elapsed_time": "4:02:47", "remaining_time": "4:16:23", "throughput": 4417.75, "total_tokens": 64353936} {"current_steps": 29820, "total_steps": 61300, "loss": 0.3551, "lr": 3.05009462506616e-05, "epoch": 4.864600326264274, "percentage": 48.65, "elapsed_time": "4:02:49", "remaining_time": "4:16:20", "throughput": 4417.81, "total_tokens": 64364592} {"current_steps": 29825, "total_steps": 61300, "loss": 0.3464, "lr": 3.049400249776384e-05, "epoch": 4.865415986949429, "percentage": 48.65, "elapsed_time": "4:02:51", "remaining_time": "4:16:17", "throughput": 4417.87, "total_tokens": 64375696} {"current_steps": 29830, "total_steps": 61300, "loss": 0.332, "lr": 3.0487058299494363e-05, "epoch": 4.866231647634584, "percentage": 48.66, "elapsed_time": "4:02:54", "remaining_time": "4:16:15", "throughput": 4417.94, "total_tokens": 64387440} {"current_steps": 29835, "total_steps": 61300, "loss": 0.3306, "lr": 3.0480113656416103e-05, "epoch": 4.867047308319739, "percentage": 48.67, "elapsed_time": "4:02:56", "remaining_time": "4:16:12", "throughput": 4418.02, "total_tokens": 64399088} {"current_steps": 29840, "total_steps": 61300, "loss": 0.3261, "lr": 3.047316856909202e-05, "epoch": 4.867862969004894, "percentage": 48.68, "elapsed_time": "4:02:58", "remaining_time": "4:16:10", "throughput": 4418.07, "total_tokens": 64409712} {"current_steps": 29845, "total_steps": 61300, "loss": 0.3574, "lr": 3.0466223038085128e-05, "epoch": 4.868678629690049, "percentage": 48.69, "elapsed_time": "4:03:01", "remaining_time": "4:16:07", "throughput": 4418.15, "total_tokens": 64421200} {"current_steps": 29850, "total_steps": 61300, "loss": 0.3638, "lr": 3.0459277063958457e-05, "epoch": 4.869494290375204, "percentage": 48.69, "elapsed_time": "4:03:03", "remaining_time": "4:16:04", "throughput": 4418.21, "total_tokens": 64431344} {"current_steps": 29855, "total_steps": 61300, "loss": 0.341, "lr": 3.0452330647275086e-05, "epoch": 4.870309951060359, "percentage": 48.7, "elapsed_time": "4:03:05", "remaining_time": "4:16:02", "throughput": 4418.29, "total_tokens": 64442928} {"current_steps": 29860, "total_steps": 61300, "loss": 0.31, "lr": 3.044538378859813e-05, "epoch": 4.871125611745514, "percentage": 48.71, "elapsed_time": "4:03:07", "remaining_time": "4:15:59", "throughput": 4418.36, "total_tokens": 64453968} {"current_steps": 29865, "total_steps": 61300, "loss": 0.3208, "lr": 3.0438436488490736e-05, "epoch": 4.871941272430669, "percentage": 48.72, "elapsed_time": "4:03:10", "remaining_time": "4:15:57", "throughput": 4418.41, "total_tokens": 64465008} {"current_steps": 29870, "total_steps": 61300, "loss": 0.3404, "lr": 3.0431488747516085e-05, "epoch": 4.872756933115824, "percentage": 48.73, "elapsed_time": "4:03:12", "remaining_time": "4:15:54", "throughput": 4418.46, "total_tokens": 64474832} {"current_steps": 29875, "total_steps": 61300, "loss": 0.3502, "lr": 3.0424540566237398e-05, "epoch": 4.873572593800979, "percentage": 48.74, "elapsed_time": "4:03:14", "remaining_time": "4:15:51", "throughput": 4418.51, "total_tokens": 64485776} {"current_steps": 29880, "total_steps": 61300, "loss": 0.3411, "lr": 3.041759194521792e-05, "epoch": 4.874388254486134, "percentage": 48.74, "elapsed_time": "4:03:16", "remaining_time": "4:15:49", "throughput": 4418.59, "total_tokens": 64497392} {"current_steps": 29885, "total_steps": 61300, "loss": 0.3487, "lr": 3.0410642885020957e-05, "epoch": 4.875203915171289, "percentage": 48.75, "elapsed_time": "4:03:19", "remaining_time": "4:15:46", "throughput": 4418.65, "total_tokens": 64508176} {"current_steps": 29890, "total_steps": 61300, "loss": 0.3667, "lr": 3.040369338620983e-05, "epoch": 4.876019575856444, "percentage": 48.76, "elapsed_time": "4:03:21", "remaining_time": "4:15:43", "throughput": 4418.7, "total_tokens": 64517808} {"current_steps": 29895, "total_steps": 61300, "loss": 0.3591, "lr": 3.0396743449347893e-05, "epoch": 4.876835236541599, "percentage": 48.77, "elapsed_time": "4:03:23", "remaining_time": "4:15:40", "throughput": 4418.75, "total_tokens": 64527696} {"current_steps": 29900, "total_steps": 61300, "loss": 0.3423, "lr": 3.0389793074998553e-05, "epoch": 4.877650897226753, "percentage": 48.78, "elapsed_time": "4:03:25", "remaining_time": "4:15:38", "throughput": 4418.79, "total_tokens": 64538448} {"current_steps": 29905, "total_steps": 61300, "loss": 0.3314, "lr": 3.038284226372524e-05, "epoch": 4.878466557911908, "percentage": 48.78, "elapsed_time": "4:03:27", "remaining_time": "4:15:35", "throughput": 4418.85, "total_tokens": 64548784} {"current_steps": 29910, "total_steps": 61300, "loss": 0.34, "lr": 3.0375891016091424e-05, "epoch": 4.879282218597064, "percentage": 48.79, "elapsed_time": "4:03:29", "remaining_time": "4:15:32", "throughput": 4418.89, "total_tokens": 64559152} {"current_steps": 29915, "total_steps": 61300, "loss": 0.3454, "lr": 3.0368939332660603e-05, "epoch": 4.880097879282219, "percentage": 48.8, "elapsed_time": "4:03:32", "remaining_time": "4:15:30", "throughput": 4418.95, "total_tokens": 64570096} {"current_steps": 29920, "total_steps": 61300, "loss": 0.3117, "lr": 3.036198721399631e-05, "epoch": 4.8809135399673735, "percentage": 48.81, "elapsed_time": "4:03:34", "remaining_time": "4:15:27", "throughput": 4419.0, "total_tokens": 64581744} {"current_steps": 29925, "total_steps": 61300, "loss": 0.3231, "lr": 3.035503466066214e-05, "epoch": 4.881729200652528, "percentage": 48.82, "elapsed_time": "4:03:36", "remaining_time": "4:15:24", "throughput": 4419.06, "total_tokens": 64591856} {"current_steps": 29930, "total_steps": 61300, "loss": 0.3571, "lr": 3.0348081673221678e-05, "epoch": 4.882544861337683, "percentage": 48.83, "elapsed_time": "4:03:38", "remaining_time": "4:15:22", "throughput": 4419.11, "total_tokens": 64602192} {"current_steps": 29935, "total_steps": 61300, "loss": 0.3756, "lr": 3.034112825223858e-05, "epoch": 4.883360522022839, "percentage": 48.83, "elapsed_time": "4:03:41", "remaining_time": "4:15:19", "throughput": 4419.16, "total_tokens": 64612976} {"current_steps": 29940, "total_steps": 61300, "loss": 0.3457, "lr": 3.0334174398276532e-05, "epoch": 4.884176182707994, "percentage": 48.84, "elapsed_time": "4:03:43", "remaining_time": "4:15:16", "throughput": 4419.22, "total_tokens": 64623984} {"current_steps": 29945, "total_steps": 61300, "loss": 0.3392, "lr": 3.032722011189924e-05, "epoch": 4.8849918433931485, "percentage": 48.85, "elapsed_time": "4:03:45", "remaining_time": "4:15:14", "throughput": 4419.28, "total_tokens": 64634992} {"current_steps": 29950, "total_steps": 61300, "loss": 0.3456, "lr": 3.032026539367046e-05, "epoch": 4.885807504078303, "percentage": 48.86, "elapsed_time": "4:03:47", "remaining_time": "4:15:11", "throughput": 4419.35, "total_tokens": 64645840} {"current_steps": 29955, "total_steps": 61300, "loss": 0.3325, "lr": 3.0313310244153968e-05, "epoch": 4.886623164763458, "percentage": 48.87, "elapsed_time": "4:03:49", "remaining_time": "4:15:08", "throughput": 4419.41, "total_tokens": 64656016} {"current_steps": 29960, "total_steps": 61300, "loss": 0.3352, "lr": 3.0306354663913588e-05, "epoch": 4.887438825448614, "percentage": 48.87, "elapsed_time": "4:03:52", "remaining_time": "4:15:06", "throughput": 4419.49, "total_tokens": 64667760} {"current_steps": 29965, "total_steps": 61300, "loss": 0.3362, "lr": 3.029939865351317e-05, "epoch": 4.888254486133769, "percentage": 48.88, "elapsed_time": "4:03:54", "remaining_time": "4:15:03", "throughput": 4419.55, "total_tokens": 64677872} {"current_steps": 29970, "total_steps": 61300, "loss": 0.2787, "lr": 3.0292442213516613e-05, "epoch": 4.8890701468189235, "percentage": 48.89, "elapsed_time": "4:03:56", "remaining_time": "4:15:00", "throughput": 4419.61, "total_tokens": 64688784} {"current_steps": 29975, "total_steps": 61300, "loss": 0.3535, "lr": 3.0285485344487834e-05, "epoch": 4.889885807504078, "percentage": 48.9, "elapsed_time": "4:03:58", "remaining_time": "4:14:58", "throughput": 4419.67, "total_tokens": 64698576} {"current_steps": 29980, "total_steps": 61300, "loss": 0.3453, "lr": 3.02785280469908e-05, "epoch": 4.890701468189233, "percentage": 48.91, "elapsed_time": "4:04:01", "remaining_time": "4:14:55", "throughput": 4419.72, "total_tokens": 64709520} {"current_steps": 29985, "total_steps": 61300, "loss": 0.3617, "lr": 3.0271570321589494e-05, "epoch": 4.891517128874388, "percentage": 48.92, "elapsed_time": "4:04:03", "remaining_time": "4:14:52", "throughput": 4419.79, "total_tokens": 64720592} {"current_steps": 29990, "total_steps": 61300, "loss": 0.3451, "lr": 3.026461216884795e-05, "epoch": 4.892332789559543, "percentage": 48.92, "elapsed_time": "4:04:05", "remaining_time": "4:14:50", "throughput": 4419.85, "total_tokens": 64731568} {"current_steps": 29995, "total_steps": 61300, "loss": 0.3424, "lr": 3.025765358933024e-05, "epoch": 4.8931484502446985, "percentage": 48.93, "elapsed_time": "4:04:07", "remaining_time": "4:14:47", "throughput": 4419.91, "total_tokens": 64742256} {"current_steps": 30000, "total_steps": 61300, "loss": 0.328, "lr": 3.0250694583600448e-05, "epoch": 4.893964110929853, "percentage": 48.94, "elapsed_time": "4:04:09", "remaining_time": "4:14:44", "throughput": 4419.96, "total_tokens": 64752208} {"current_steps": 30005, "total_steps": 61300, "loss": 0.3457, "lr": 3.024373515222271e-05, "epoch": 4.894779771615008, "percentage": 48.95, "elapsed_time": "4:04:11", "remaining_time": "4:14:41", "throughput": 4420.01, "total_tokens": 64761168} {"current_steps": 30010, "total_steps": 61300, "loss": 0.3414, "lr": 3.0236775295761194e-05, "epoch": 4.895595432300163, "percentage": 48.96, "elapsed_time": "4:04:14", "remaining_time": "4:14:39", "throughput": 4420.08, "total_tokens": 64773040} {"current_steps": 30015, "total_steps": 61300, "loss": 0.3298, "lr": 3.02298150147801e-05, "epoch": 4.896411092985318, "percentage": 48.96, "elapsed_time": "4:04:16", "remaining_time": "4:14:37", "throughput": 4420.16, "total_tokens": 64785584} {"current_steps": 30020, "total_steps": 61300, "loss": 0.3499, "lr": 3.022285430984367e-05, "epoch": 4.897226753670473, "percentage": 48.97, "elapsed_time": "4:04:19", "remaining_time": "4:14:34", "throughput": 4420.22, "total_tokens": 64797648} {"current_steps": 30025, "total_steps": 61300, "loss": 0.3498, "lr": 3.0215893181516163e-05, "epoch": 4.898042414355628, "percentage": 48.98, "elapsed_time": "4:04:21", "remaining_time": "4:14:32", "throughput": 4420.28, "total_tokens": 64808912} {"current_steps": 30030, "total_steps": 61300, "loss": 0.3452, "lr": 3.02089316303619e-05, "epoch": 4.898858075040783, "percentage": 48.99, "elapsed_time": "4:04:24", "remaining_time": "4:14:29", "throughput": 4420.35, "total_tokens": 64820336} {"current_steps": 30035, "total_steps": 61300, "loss": 0.3096, "lr": 3.0201969656945196e-05, "epoch": 4.899673735725938, "percentage": 49.0, "elapsed_time": "4:04:26", "remaining_time": "4:14:27", "throughput": 4420.42, "total_tokens": 64831600} {"current_steps": 30040, "total_steps": 61300, "loss": 0.3049, "lr": 3.0195007261830438e-05, "epoch": 4.900489396411093, "percentage": 49.0, "elapsed_time": "4:04:28", "remaining_time": "4:14:24", "throughput": 4420.47, "total_tokens": 64842000} {"current_steps": 30045, "total_steps": 61300, "loss": 0.3379, "lr": 3.018804444558204e-05, "epoch": 4.901305057096248, "percentage": 49.01, "elapsed_time": "4:04:30", "remaining_time": "4:14:21", "throughput": 4420.54, "total_tokens": 64853456} {"current_steps": 30050, "total_steps": 61300, "loss": 0.3377, "lr": 3.018108120876443e-05, "epoch": 4.902120717781403, "percentage": 49.02, "elapsed_time": "4:04:33", "remaining_time": "4:14:19", "throughput": 4420.59, "total_tokens": 64863952} {"current_steps": 30055, "total_steps": 61300, "loss": 0.3142, "lr": 3.0174117551942087e-05, "epoch": 4.902936378466558, "percentage": 49.03, "elapsed_time": "4:04:35", "remaining_time": "4:14:16", "throughput": 4420.63, "total_tokens": 64874128} {"current_steps": 30060, "total_steps": 61300, "loss": 0.3029, "lr": 3.0167153475679527e-05, "epoch": 4.903752039151713, "percentage": 49.04, "elapsed_time": "4:04:37", "remaining_time": "4:14:13", "throughput": 4420.68, "total_tokens": 64883856} {"current_steps": 30065, "total_steps": 61300, "loss": 0.3771, "lr": 3.0160188980541288e-05, "epoch": 4.904567699836868, "percentage": 49.05, "elapsed_time": "4:04:39", "remaining_time": "4:14:10", "throughput": 4420.74, "total_tokens": 64894736} {"current_steps": 30070, "total_steps": 61300, "loss": 0.3219, "lr": 3.0153224067091952e-05, "epoch": 4.9053833605220225, "percentage": 49.05, "elapsed_time": "4:04:41", "remaining_time": "4:14:08", "throughput": 4420.8, "total_tokens": 64905808} {"current_steps": 30075, "total_steps": 61300, "loss": 0.3485, "lr": 3.0146258735896117e-05, "epoch": 4.906199021207177, "percentage": 49.06, "elapsed_time": "4:04:44", "remaining_time": "4:14:05", "throughput": 4420.85, "total_tokens": 64917104} {"current_steps": 30080, "total_steps": 61300, "loss": 0.3746, "lr": 3.0139292987518443e-05, "epoch": 4.907014681892333, "percentage": 49.07, "elapsed_time": "4:04:46", "remaining_time": "4:14:02", "throughput": 4420.91, "total_tokens": 64926800} {"current_steps": 30085, "total_steps": 61300, "loss": 0.3068, "lr": 3.0132326822523606e-05, "epoch": 4.907830342577488, "percentage": 49.08, "elapsed_time": "4:04:48", "remaining_time": "4:14:00", "throughput": 4420.97, "total_tokens": 64937904} {"current_steps": 30090, "total_steps": 61300, "loss": 0.3675, "lr": 3.01253602414763e-05, "epoch": 4.908646003262643, "percentage": 49.09, "elapsed_time": "4:04:50", "remaining_time": "4:13:57", "throughput": 4421.04, "total_tokens": 64948592} {"current_steps": 30095, "total_steps": 61300, "loss": 0.3609, "lr": 3.0118393244941302e-05, "epoch": 4.9094616639477975, "percentage": 49.09, "elapsed_time": "4:04:52", "remaining_time": "4:13:54", "throughput": 4421.11, "total_tokens": 64959152} {"current_steps": 30100, "total_steps": 61300, "loss": 0.3297, "lr": 3.011142583348337e-05, "epoch": 4.910277324632952, "percentage": 49.1, "elapsed_time": "4:04:55", "remaining_time": "4:13:52", "throughput": 4421.16, "total_tokens": 64970736} {"current_steps": 30105, "total_steps": 61300, "loss": 0.3584, "lr": 3.010445800766733e-05, "epoch": 4.911092985318108, "percentage": 49.11, "elapsed_time": "4:04:57", "remaining_time": "4:13:49", "throughput": 4421.22, "total_tokens": 64982032} {"current_steps": 30110, "total_steps": 61300, "loss": 0.3445, "lr": 3.0097489768058022e-05, "epoch": 4.911908646003263, "percentage": 49.12, "elapsed_time": "4:05:00", "remaining_time": "4:13:47", "throughput": 4421.29, "total_tokens": 64994448} {"current_steps": 30115, "total_steps": 61300, "loss": 0.3331, "lr": 3.0090521115220327e-05, "epoch": 4.912724306688418, "percentage": 49.13, "elapsed_time": "4:05:02", "remaining_time": "4:13:45", "throughput": 4421.36, "total_tokens": 65005744} {"current_steps": 30120, "total_steps": 61300, "loss": 0.3163, "lr": 3.0083552049719167e-05, "epoch": 4.9135399673735725, "percentage": 49.14, "elapsed_time": "4:05:04", "remaining_time": "4:13:42", "throughput": 4421.43, "total_tokens": 65016848} {"current_steps": 30125, "total_steps": 61300, "loss": 0.313, "lr": 3.0076582572119473e-05, "epoch": 4.914355628058727, "percentage": 49.14, "elapsed_time": "4:05:07", "remaining_time": "4:13:39", "throughput": 4421.5, "total_tokens": 65027600} {"current_steps": 30130, "total_steps": 61300, "loss": 0.3768, "lr": 3.0069612682986247e-05, "epoch": 4.915171288743883, "percentage": 49.15, "elapsed_time": "4:05:09", "remaining_time": "4:13:37", "throughput": 4421.57, "total_tokens": 65039120} {"current_steps": 30135, "total_steps": 61300, "loss": 0.376, "lr": 3.0062642382884494e-05, "epoch": 4.915986949429038, "percentage": 49.16, "elapsed_time": "4:05:11", "remaining_time": "4:13:34", "throughput": 4421.63, "total_tokens": 65050512} {"current_steps": 30140, "total_steps": 61300, "loss": 0.3565, "lr": 3.005567167237926e-05, "epoch": 4.916802610114193, "percentage": 49.17, "elapsed_time": "4:05:13", "remaining_time": "4:13:31", "throughput": 4421.69, "total_tokens": 65059888} {"current_steps": 30145, "total_steps": 61300, "loss": 0.3666, "lr": 3.004870055203562e-05, "epoch": 4.917618270799347, "percentage": 49.18, "elapsed_time": "4:05:16", "remaining_time": "4:13:29", "throughput": 4421.75, "total_tokens": 65071120} {"current_steps": 30150, "total_steps": 61300, "loss": 0.3635, "lr": 3.0041729022418702e-05, "epoch": 4.918433931484502, "percentage": 49.18, "elapsed_time": "4:05:18", "remaining_time": "4:13:26", "throughput": 4421.81, "total_tokens": 65081744} {"current_steps": 30155, "total_steps": 61300, "loss": 0.3352, "lr": 3.003475708409365e-05, "epoch": 4.919249592169657, "percentage": 49.19, "elapsed_time": "4:05:20", "remaining_time": "4:13:23", "throughput": 4421.88, "total_tokens": 65093040} {"current_steps": 30160, "total_steps": 61300, "loss": 0.3127, "lr": 3.0027784737625646e-05, "epoch": 4.920065252854813, "percentage": 49.2, "elapsed_time": "4:05:22", "remaining_time": "4:13:21", "throughput": 4421.95, "total_tokens": 65103056} {"current_steps": 30165, "total_steps": 61300, "loss": 0.3266, "lr": 3.00208119835799e-05, "epoch": 4.920880913539968, "percentage": 49.21, "elapsed_time": "4:05:25", "remaining_time": "4:13:18", "throughput": 4421.99, "total_tokens": 65113904} {"current_steps": 30170, "total_steps": 61300, "loss": 0.3645, "lr": 3.0013838822521655e-05, "epoch": 4.921696574225122, "percentage": 49.22, "elapsed_time": "4:05:27", "remaining_time": "4:13:15", "throughput": 4422.05, "total_tokens": 65124016} {"current_steps": 30175, "total_steps": 61300, "loss": 0.3612, "lr": 3.0006865255016192e-05, "epoch": 4.922512234910277, "percentage": 49.23, "elapsed_time": "4:05:29", "remaining_time": "4:13:13", "throughput": 4422.13, "total_tokens": 65135120} {"current_steps": 30180, "total_steps": 61300, "loss": 0.3606, "lr": 2.9999891281628832e-05, "epoch": 4.923327895595432, "percentage": 49.23, "elapsed_time": "4:05:31", "remaining_time": "4:13:10", "throughput": 4422.18, "total_tokens": 65144784} {"current_steps": 30185, "total_steps": 61300, "loss": 0.3372, "lr": 2.9992916902924917e-05, "epoch": 4.924143556280587, "percentage": 49.24, "elapsed_time": "4:05:33", "remaining_time": "4:13:07", "throughput": 4422.23, "total_tokens": 65154928} {"current_steps": 30190, "total_steps": 61300, "loss": 0.3381, "lr": 2.998594211946982e-05, "epoch": 4.924959216965743, "percentage": 49.25, "elapsed_time": "4:05:35", "remaining_time": "4:13:04", "throughput": 4422.28, "total_tokens": 65165808} {"current_steps": 30195, "total_steps": 61300, "loss": 0.3672, "lr": 2.9978966931828957e-05, "epoch": 4.925774877650897, "percentage": 49.26, "elapsed_time": "4:05:37", "remaining_time": "4:13:02", "throughput": 4422.33, "total_tokens": 65175952} {"current_steps": 30200, "total_steps": 61300, "loss": 0.3528, "lr": 2.9971991340567773e-05, "epoch": 4.926590538336052, "percentage": 49.27, "elapsed_time": "4:05:39", "remaining_time": "4:12:59", "throughput": 4422.39, "total_tokens": 65185904} {"current_steps": 30205, "total_steps": 61300, "loss": 0.3412, "lr": 2.9965015346251747e-05, "epoch": 4.927406199021207, "percentage": 49.27, "elapsed_time": "4:05:42", "remaining_time": "4:12:56", "throughput": 4422.45, "total_tokens": 65196848} {"current_steps": 30210, "total_steps": 61300, "loss": 0.3277, "lr": 2.995803894944637e-05, "epoch": 4.928221859706362, "percentage": 49.28, "elapsed_time": "4:05:44", "remaining_time": "4:12:53", "throughput": 4422.51, "total_tokens": 65207440} {"current_steps": 30215, "total_steps": 61300, "loss": 0.3623, "lr": 2.9951062150717212e-05, "epoch": 4.9290375203915175, "percentage": 49.29, "elapsed_time": "4:05:46", "remaining_time": "4:12:51", "throughput": 4422.57, "total_tokens": 65217904} {"current_steps": 30220, "total_steps": 61300, "loss": 0.3553, "lr": 2.994408495062983e-05, "epoch": 4.929853181076672, "percentage": 49.3, "elapsed_time": "4:05:48", "remaining_time": "4:12:48", "throughput": 4422.62, "total_tokens": 65228464} {"current_steps": 30225, "total_steps": 61300, "loss": 0.3562, "lr": 2.9937107349749842e-05, "epoch": 4.930668841761827, "percentage": 49.31, "elapsed_time": "4:05:50", "remaining_time": "4:12:45", "throughput": 4422.69, "total_tokens": 65239024} {"current_steps": 30230, "total_steps": 61300, "loss": 0.2869, "lr": 2.9930129348642877e-05, "epoch": 4.931484502446982, "percentage": 49.31, "elapsed_time": "4:05:53", "remaining_time": "4:12:43", "throughput": 4422.75, "total_tokens": 65249872} {"current_steps": 30235, "total_steps": 61300, "loss": 0.3533, "lr": 2.9923150947874613e-05, "epoch": 4.932300163132137, "percentage": 49.32, "elapsed_time": "4:05:55", "remaining_time": "4:12:40", "throughput": 4422.81, "total_tokens": 65260560} {"current_steps": 30240, "total_steps": 61300, "loss": 0.3006, "lr": 2.991617214801075e-05, "epoch": 4.933115823817292, "percentage": 49.33, "elapsed_time": "4:05:57", "remaining_time": "4:12:37", "throughput": 4422.88, "total_tokens": 65272016} {"current_steps": 30245, "total_steps": 61300, "loss": 0.3588, "lr": 2.9909192949617036e-05, "epoch": 4.933931484502447, "percentage": 49.34, "elapsed_time": "4:05:59", "remaining_time": "4:12:35", "throughput": 4422.92, "total_tokens": 65281136} {"current_steps": 30250, "total_steps": 61300, "loss": 0.3261, "lr": 2.9902213353259223e-05, "epoch": 4.934747145187602, "percentage": 49.35, "elapsed_time": "4:06:01", "remaining_time": "4:12:32", "throughput": 4422.97, "total_tokens": 65290640} {"current_steps": 30255, "total_steps": 61300, "loss": 0.3362, "lr": 2.989523335950313e-05, "epoch": 4.935562805872757, "percentage": 49.36, "elapsed_time": "4:06:04", "remaining_time": "4:12:29", "throughput": 4423.04, "total_tokens": 65302032} {"current_steps": 30260, "total_steps": 61300, "loss": 0.3357, "lr": 2.9888252968914576e-05, "epoch": 4.936378466557912, "percentage": 49.36, "elapsed_time": "4:06:06", "remaining_time": "4:12:27", "throughput": 4423.1, "total_tokens": 65313168} {"current_steps": 30265, "total_steps": 61300, "loss": 0.3307, "lr": 2.988127218205944e-05, "epoch": 4.937194127243067, "percentage": 49.37, "elapsed_time": "4:06:08", "remaining_time": "4:12:24", "throughput": 4423.17, "total_tokens": 65324528} {"current_steps": 30270, "total_steps": 61300, "loss": 0.3101, "lr": 2.9874290999503606e-05, "epoch": 4.938009787928221, "percentage": 49.38, "elapsed_time": "4:06:10", "remaining_time": "4:12:21", "throughput": 4423.25, "total_tokens": 65335568} {"current_steps": 30275, "total_steps": 61300, "loss": 0.3738, "lr": 2.9867309421813018e-05, "epoch": 4.938825448613377, "percentage": 49.39, "elapsed_time": "4:06:13", "remaining_time": "4:12:19", "throughput": 4423.3, "total_tokens": 65346032} {"current_steps": 30280, "total_steps": 61300, "loss": 0.3538, "lr": 2.9860327449553626e-05, "epoch": 4.939641109298532, "percentage": 49.4, "elapsed_time": "4:06:15", "remaining_time": "4:12:16", "throughput": 4423.37, "total_tokens": 65357712} {"current_steps": 30285, "total_steps": 61300, "loss": 0.3578, "lr": 2.9853345083291434e-05, "epoch": 4.940456769983687, "percentage": 49.4, "elapsed_time": "4:06:18", "remaining_time": "4:12:14", "throughput": 4423.43, "total_tokens": 65369552} {"current_steps": 30290, "total_steps": 61300, "loss": 0.3533, "lr": 2.9846362323592463e-05, "epoch": 4.941272430668842, "percentage": 49.41, "elapsed_time": "4:06:20", "remaining_time": "4:12:11", "throughput": 4423.5, "total_tokens": 65380912} {"current_steps": 30295, "total_steps": 61300, "loss": 0.3568, "lr": 2.9839379171022776e-05, "epoch": 4.942088091353996, "percentage": 49.42, "elapsed_time": "4:06:22", "remaining_time": "4:12:09", "throughput": 4423.56, "total_tokens": 65392080} {"current_steps": 30300, "total_steps": 61300, "loss": 0.3338, "lr": 2.983239562614845e-05, "epoch": 4.942903752039152, "percentage": 49.43, "elapsed_time": "4:06:24", "remaining_time": "4:12:06", "throughput": 4423.62, "total_tokens": 65402256} {"current_steps": 30305, "total_steps": 61300, "loss": 0.3273, "lr": 2.982541168953562e-05, "epoch": 4.943719412724307, "percentage": 49.44, "elapsed_time": "4:06:27", "remaining_time": "4:12:03", "throughput": 4423.68, "total_tokens": 65413456} {"current_steps": 30310, "total_steps": 61300, "loss": 0.3379, "lr": 2.9818427361750434e-05, "epoch": 4.944535073409462, "percentage": 49.45, "elapsed_time": "4:06:29", "remaining_time": "4:12:01", "throughput": 4423.75, "total_tokens": 65424912} {"current_steps": 30315, "total_steps": 61300, "loss": 0.3659, "lr": 2.9811442643359076e-05, "epoch": 4.945350734094617, "percentage": 49.45, "elapsed_time": "4:06:31", "remaining_time": "4:11:58", "throughput": 4423.8, "total_tokens": 65434896} {"current_steps": 30320, "total_steps": 61300, "loss": 0.3711, "lr": 2.9804457534927772e-05, "epoch": 4.946166394779771, "percentage": 49.46, "elapsed_time": "4:06:33", "remaining_time": "4:11:55", "throughput": 4423.85, "total_tokens": 65445424} {"current_steps": 30325, "total_steps": 61300, "loss": 0.3246, "lr": 2.9797472037022757e-05, "epoch": 4.946982055464927, "percentage": 49.47, "elapsed_time": "4:06:35", "remaining_time": "4:11:52", "throughput": 4423.9, "total_tokens": 65454672} {"current_steps": 30330, "total_steps": 61300, "loss": 0.3679, "lr": 2.9790486150210316e-05, "epoch": 4.947797716150082, "percentage": 49.48, "elapsed_time": "4:06:37", "remaining_time": "4:11:50", "throughput": 4423.97, "total_tokens": 65465776} {"current_steps": 30335, "total_steps": 61300, "loss": 0.3502, "lr": 2.9783499875056766e-05, "epoch": 4.948613376835237, "percentage": 49.49, "elapsed_time": "4:06:40", "remaining_time": "4:11:47", "throughput": 4424.04, "total_tokens": 65477168} {"current_steps": 30340, "total_steps": 61300, "loss": 0.348, "lr": 2.9776513212128442e-05, "epoch": 4.9494290375203915, "percentage": 49.49, "elapsed_time": "4:06:42", "remaining_time": "4:11:44", "throughput": 4424.1, "total_tokens": 65487248} {"current_steps": 30345, "total_steps": 61300, "loss": 0.2951, "lr": 2.976952616199172e-05, "epoch": 4.950244698205546, "percentage": 49.5, "elapsed_time": "4:06:44", "remaining_time": "4:11:42", "throughput": 4424.15, "total_tokens": 65497360} {"current_steps": 30350, "total_steps": 61300, "loss": 0.321, "lr": 2.9762538725213007e-05, "epoch": 4.951060358890701, "percentage": 49.51, "elapsed_time": "4:06:46", "remaining_time": "4:11:39", "throughput": 4424.21, "total_tokens": 65507728} {"current_steps": 30355, "total_steps": 61300, "loss": 0.3581, "lr": 2.9755550902358737e-05, "epoch": 4.951876019575856, "percentage": 49.52, "elapsed_time": "4:06:48", "remaining_time": "4:11:36", "throughput": 4424.26, "total_tokens": 65517104} {"current_steps": 30360, "total_steps": 61300, "loss": 0.3492, "lr": 2.9748562693995386e-05, "epoch": 4.952691680261012, "percentage": 49.53, "elapsed_time": "4:06:51", "remaining_time": "4:11:34", "throughput": 4424.33, "total_tokens": 65529168} {"current_steps": 30365, "total_steps": 61300, "loss": 0.3211, "lr": 2.974157410068944e-05, "epoch": 4.9535073409461665, "percentage": 49.54, "elapsed_time": "4:06:53", "remaining_time": "4:11:31", "throughput": 4424.39, "total_tokens": 65538960} {"current_steps": 30370, "total_steps": 61300, "loss": 0.3269, "lr": 2.9734585123007446e-05, "epoch": 4.954323001631321, "percentage": 49.54, "elapsed_time": "4:06:55", "remaining_time": "4:11:28", "throughput": 4424.44, "total_tokens": 65549392} {"current_steps": 30375, "total_steps": 61300, "loss": 0.3637, "lr": 2.9727595761515958e-05, "epoch": 4.955138662316476, "percentage": 49.55, "elapsed_time": "4:06:57", "remaining_time": "4:11:25", "throughput": 4424.49, "total_tokens": 65559824} {"current_steps": 30380, "total_steps": 61300, "loss": 0.3589, "lr": 2.9720606016781577e-05, "epoch": 4.955954323001631, "percentage": 49.56, "elapsed_time": "4:06:59", "remaining_time": "4:11:23", "throughput": 4424.56, "total_tokens": 65570896} {"current_steps": 30385, "total_steps": 61300, "loss": 0.3792, "lr": 2.9713615889370917e-05, "epoch": 4.956769983686787, "percentage": 49.57, "elapsed_time": "4:07:02", "remaining_time": "4:11:20", "throughput": 4424.61, "total_tokens": 65582384} {"current_steps": 30390, "total_steps": 61300, "loss": 0.3606, "lr": 2.9706625379850627e-05, "epoch": 4.9575856443719415, "percentage": 49.58, "elapsed_time": "4:07:04", "remaining_time": "4:11:18", "throughput": 4424.67, "total_tokens": 65593264} {"current_steps": 30395, "total_steps": 61300, "loss": 0.338, "lr": 2.9699634488787415e-05, "epoch": 4.958401305057096, "percentage": 49.58, "elapsed_time": "4:07:06", "remaining_time": "4:11:15", "throughput": 4424.72, "total_tokens": 65604016} {"current_steps": 30400, "total_steps": 61300, "loss": 0.3248, "lr": 2.9692643216747978e-05, "epoch": 4.959216965742251, "percentage": 49.59, "elapsed_time": "4:07:08", "remaining_time": "4:11:12", "throughput": 4424.77, "total_tokens": 65613616} {"current_steps": 30405, "total_steps": 61300, "loss": 0.3501, "lr": 2.9685651564299077e-05, "epoch": 4.960032626427406, "percentage": 49.6, "elapsed_time": "4:07:11", "remaining_time": "4:11:10", "throughput": 4424.84, "total_tokens": 65624816} {"current_steps": 30410, "total_steps": 61300, "loss": 0.3399, "lr": 2.9678659532007475e-05, "epoch": 4.960848287112562, "percentage": 49.61, "elapsed_time": "4:07:13", "remaining_time": "4:11:07", "throughput": 4424.9, "total_tokens": 65635792} {"current_steps": 30415, "total_steps": 61300, "loss": 0.3458, "lr": 2.967166712044e-05, "epoch": 4.9616639477977165, "percentage": 49.62, "elapsed_time": "4:07:15", "remaining_time": "4:11:04", "throughput": 4424.95, "total_tokens": 65646512} {"current_steps": 30420, "total_steps": 61300, "loss": 0.3269, "lr": 2.9664674330163485e-05, "epoch": 4.962479608482871, "percentage": 49.62, "elapsed_time": "4:07:17", "remaining_time": "4:11:02", "throughput": 4425.01, "total_tokens": 65656976} {"current_steps": 30425, "total_steps": 61300, "loss": 0.3213, "lr": 2.96576811617448e-05, "epoch": 4.963295269168026, "percentage": 49.63, "elapsed_time": "4:07:19", "remaining_time": "4:10:59", "throughput": 4425.07, "total_tokens": 65667792} {"current_steps": 30430, "total_steps": 61300, "loss": 0.3454, "lr": 2.9650687615750843e-05, "epoch": 4.964110929853181, "percentage": 49.64, "elapsed_time": "4:07:22", "remaining_time": "4:10:56", "throughput": 4425.13, "total_tokens": 65679088} {"current_steps": 30435, "total_steps": 61300, "loss": 0.328, "lr": 2.964369369274856e-05, "epoch": 4.964926590538336, "percentage": 49.65, "elapsed_time": "4:07:24", "remaining_time": "4:10:54", "throughput": 4425.19, "total_tokens": 65689840} {"current_steps": 30440, "total_steps": 61300, "loss": 0.3221, "lr": 2.963669939330489e-05, "epoch": 4.9657422512234906, "percentage": 49.66, "elapsed_time": "4:07:26", "remaining_time": "4:10:51", "throughput": 4425.25, "total_tokens": 65700528} {"current_steps": 30445, "total_steps": 61300, "loss": 0.3232, "lr": 2.962970471798685e-05, "epoch": 4.966557911908646, "percentage": 49.67, "elapsed_time": "4:07:28", "remaining_time": "4:10:48", "throughput": 4425.31, "total_tokens": 65710128} {"current_steps": 30450, "total_steps": 61300, "loss": 0.2729, "lr": 2.9622709667361455e-05, "epoch": 4.967373572593801, "percentage": 49.67, "elapsed_time": "4:07:31", "remaining_time": "4:10:46", "throughput": 4425.39, "total_tokens": 65722064} {"current_steps": 30455, "total_steps": 61300, "loss": 0.3116, "lr": 2.9615714241995758e-05, "epoch": 4.968189233278956, "percentage": 49.68, "elapsed_time": "4:07:33", "remaining_time": "4:10:43", "throughput": 4425.45, "total_tokens": 65732336} {"current_steps": 30460, "total_steps": 61300, "loss": 0.3547, "lr": 2.9608718442456844e-05, "epoch": 4.969004893964111, "percentage": 49.69, "elapsed_time": "4:07:35", "remaining_time": "4:10:40", "throughput": 4425.52, "total_tokens": 65743504} {"current_steps": 30465, "total_steps": 61300, "loss": 0.3722, "lr": 2.9601722269311827e-05, "epoch": 4.9698205546492655, "percentage": 49.7, "elapsed_time": "4:07:37", "remaining_time": "4:10:38", "throughput": 4425.58, "total_tokens": 65754608} {"current_steps": 30470, "total_steps": 61300, "loss": 0.3688, "lr": 2.9594725723127855e-05, "epoch": 4.970636215334421, "percentage": 49.71, "elapsed_time": "4:07:40", "remaining_time": "4:10:35", "throughput": 4425.64, "total_tokens": 65765584} {"current_steps": 30475, "total_steps": 61300, "loss": 0.3678, "lr": 2.9587728804472104e-05, "epoch": 4.971451876019576, "percentage": 49.71, "elapsed_time": "4:07:42", "remaining_time": "4:10:33", "throughput": 4425.71, "total_tokens": 65776816} {"current_steps": 30480, "total_steps": 61300, "loss": 0.2984, "lr": 2.9580731513911773e-05, "epoch": 4.972267536704731, "percentage": 49.72, "elapsed_time": "4:07:44", "remaining_time": "4:10:30", "throughput": 4425.77, "total_tokens": 65788336} {"current_steps": 30485, "total_steps": 61300, "loss": 0.2971, "lr": 2.9573733852014112e-05, "epoch": 4.973083197389886, "percentage": 49.73, "elapsed_time": "4:07:47", "remaining_time": "4:10:27", "throughput": 4425.82, "total_tokens": 65798704} {"current_steps": 30490, "total_steps": 61300, "loss": 0.3672, "lr": 2.9566735819346376e-05, "epoch": 4.9738988580750405, "percentage": 49.74, "elapsed_time": "4:07:49", "remaining_time": "4:10:25", "throughput": 4425.88, "total_tokens": 65808816} {"current_steps": 30495, "total_steps": 61300, "loss": 0.3466, "lr": 2.9559737416475863e-05, "epoch": 4.974714518760196, "percentage": 49.75, "elapsed_time": "4:07:51", "remaining_time": "4:10:22", "throughput": 4425.94, "total_tokens": 65819088} {"current_steps": 30500, "total_steps": 61300, "loss": 0.323, "lr": 2.9552738643969896e-05, "epoch": 4.975530179445351, "percentage": 49.76, "elapsed_time": "4:07:53", "remaining_time": "4:10:19", "throughput": 4425.99, "total_tokens": 65830256} {"current_steps": 30505, "total_steps": 61300, "loss": 0.3192, "lr": 2.9545739502395835e-05, "epoch": 4.976345840130506, "percentage": 49.76, "elapsed_time": "4:07:55", "remaining_time": "4:10:16", "throughput": 4426.03, "total_tokens": 65839792} {"current_steps": 30510, "total_steps": 61300, "loss": 0.3136, "lr": 2.9538739992321062e-05, "epoch": 4.977161500815661, "percentage": 49.77, "elapsed_time": "4:07:57", "remaining_time": "4:10:14", "throughput": 4426.09, "total_tokens": 65850512} {"current_steps": 30515, "total_steps": 61300, "loss": 0.3326, "lr": 2.9531740114313e-05, "epoch": 4.9779771615008155, "percentage": 49.78, "elapsed_time": "4:08:00", "remaining_time": "4:10:11", "throughput": 4426.16, "total_tokens": 65861584} {"current_steps": 30520, "total_steps": 61300, "loss": 0.3594, "lr": 2.9524739868939088e-05, "epoch": 4.97879282218597, "percentage": 49.79, "elapsed_time": "4:08:02", "remaining_time": "4:10:09", "throughput": 4426.21, "total_tokens": 65872880} {"current_steps": 30525, "total_steps": 61300, "loss": 0.34, "lr": 2.9517739256766803e-05, "epoch": 4.979608482871125, "percentage": 49.8, "elapsed_time": "4:08:04", "remaining_time": "4:10:06", "throughput": 4426.26, "total_tokens": 65882544} {"current_steps": 30530, "total_steps": 61300, "loss": 0.3299, "lr": 2.9510738278363652e-05, "epoch": 4.980424143556281, "percentage": 49.8, "elapsed_time": "4:08:06", "remaining_time": "4:10:03", "throughput": 4426.32, "total_tokens": 65893456} {"current_steps": 30535, "total_steps": 61300, "loss": 0.3639, "lr": 2.950373693429717e-05, "epoch": 4.981239804241436, "percentage": 49.81, "elapsed_time": "4:08:09", "remaining_time": "4:10:01", "throughput": 4426.38, "total_tokens": 65905264} {"current_steps": 30540, "total_steps": 61300, "loss": 0.3534, "lr": 2.949673522513492e-05, "epoch": 4.9820554649265905, "percentage": 49.82, "elapsed_time": "4:08:11", "remaining_time": "4:09:58", "throughput": 4426.44, "total_tokens": 65916400} {"current_steps": 30545, "total_steps": 61300, "loss": 0.3461, "lr": 2.9489733151444497e-05, "epoch": 4.982871125611745, "percentage": 49.83, "elapsed_time": "4:08:13", "remaining_time": "4:09:56", "throughput": 4426.51, "total_tokens": 65928272} {"current_steps": 30550, "total_steps": 61300, "loss": 0.3476, "lr": 2.9482730713793526e-05, "epoch": 4.9836867862969, "percentage": 49.84, "elapsed_time": "4:08:16", "remaining_time": "4:09:53", "throughput": 4426.58, "total_tokens": 65939792} {"current_steps": 30555, "total_steps": 61300, "loss": 0.3181, "lr": 2.9475727912749656e-05, "epoch": 4.984502446982056, "percentage": 49.85, "elapsed_time": "4:08:18", "remaining_time": "4:09:51", "throughput": 4426.63, "total_tokens": 65950576} {"current_steps": 30560, "total_steps": 61300, "loss": 0.3557, "lr": 2.946872474888058e-05, "epoch": 4.985318107667211, "percentage": 49.85, "elapsed_time": "4:08:20", "remaining_time": "4:09:48", "throughput": 4426.67, "total_tokens": 65960240} {"current_steps": 30565, "total_steps": 61300, "loss": 0.3729, "lr": 2.9461721222753992e-05, "epoch": 4.986133768352365, "percentage": 49.86, "elapsed_time": "4:08:22", "remaining_time": "4:09:45", "throughput": 4426.72, "total_tokens": 65970544} {"current_steps": 30570, "total_steps": 61300, "loss": 0.3186, "lr": 2.9454717334937638e-05, "epoch": 4.98694942903752, "percentage": 49.87, "elapsed_time": "4:08:25", "remaining_time": "4:09:43", "throughput": 4426.79, "total_tokens": 65982768} {"current_steps": 30575, "total_steps": 61300, "loss": 0.3185, "lr": 2.94477130859993e-05, "epoch": 4.987765089722675, "percentage": 49.88, "elapsed_time": "4:08:27", "remaining_time": "4:09:40", "throughput": 4426.85, "total_tokens": 65993680} {"current_steps": 30580, "total_steps": 61300, "loss": 0.3763, "lr": 2.9440708476506773e-05, "epoch": 4.988580750407831, "percentage": 49.89, "elapsed_time": "4:08:29", "remaining_time": "4:09:38", "throughput": 4426.91, "total_tokens": 66005136} {"current_steps": 30585, "total_steps": 61300, "loss": 0.3586, "lr": 2.943370350702789e-05, "epoch": 4.989396411092986, "percentage": 49.89, "elapsed_time": "4:08:32", "remaining_time": "4:09:35", "throughput": 4426.97, "total_tokens": 66015376} {"current_steps": 30590, "total_steps": 61300, "loss": 0.3336, "lr": 2.9426698178130495e-05, "epoch": 4.99021207177814, "percentage": 49.9, "elapsed_time": "4:08:34", "remaining_time": "4:09:32", "throughput": 4427.03, "total_tokens": 66025904} {"current_steps": 30595, "total_steps": 61300, "loss": 0.3612, "lr": 2.9419692490382488e-05, "epoch": 4.991027732463295, "percentage": 49.91, "elapsed_time": "4:08:36", "remaining_time": "4:09:30", "throughput": 4427.09, "total_tokens": 66036560} {"current_steps": 30600, "total_steps": 61300, "loss": 0.3242, "lr": 2.9412686444351782e-05, "epoch": 4.99184339314845, "percentage": 49.92, "elapsed_time": "4:08:38", "remaining_time": "4:09:27", "throughput": 4427.15, "total_tokens": 66047856} {"current_steps": 30605, "total_steps": 61300, "loss": 0.3539, "lr": 2.9405680040606326e-05, "epoch": 4.992659053833605, "percentage": 49.93, "elapsed_time": "4:08:41", "remaining_time": "4:09:24", "throughput": 4427.21, "total_tokens": 66058736} {"current_steps": 30610, "total_steps": 61300, "loss": 0.347, "lr": 2.939867327971409e-05, "epoch": 4.993474714518761, "percentage": 49.93, "elapsed_time": "4:08:43", "remaining_time": "4:09:22", "throughput": 4427.27, "total_tokens": 66068848} {"current_steps": 30615, "total_steps": 61300, "loss": 0.3438, "lr": 2.939166616224308e-05, "epoch": 4.994290375203915, "percentage": 49.94, "elapsed_time": "4:08:45", "remaining_time": "4:09:19", "throughput": 4427.32, "total_tokens": 66079760} {"current_steps": 30620, "total_steps": 61300, "loss": 0.3013, "lr": 2.938465868876133e-05, "epoch": 4.99510603588907, "percentage": 49.95, "elapsed_time": "4:08:47", "remaining_time": "4:09:16", "throughput": 4427.36, "total_tokens": 66090128} {"current_steps": 30625, "total_steps": 61300, "loss": 0.3864, "lr": 2.9377650859836892e-05, "epoch": 4.995921696574225, "percentage": 49.96, "elapsed_time": "4:08:49", "remaining_time": "4:09:14", "throughput": 4427.41, "total_tokens": 66100304} {"current_steps": 30630, "total_steps": 61300, "loss": 0.3836, "lr": 2.9370642676037867e-05, "epoch": 4.99673735725938, "percentage": 49.97, "elapsed_time": "4:08:52", "remaining_time": "4:09:11", "throughput": 4427.46, "total_tokens": 66111696} {"current_steps": 30635, "total_steps": 61300, "loss": 0.3225, "lr": 2.936363413793237e-05, "epoch": 4.997553017944535, "percentage": 49.98, "elapsed_time": "4:08:54", "remaining_time": "4:09:08", "throughput": 4427.51, "total_tokens": 66122064} {"current_steps": 30640, "total_steps": 61300, "loss": 0.3267, "lr": 2.9356625246088554e-05, "epoch": 4.99836867862969, "percentage": 49.98, "elapsed_time": "4:08:56", "remaining_time": "4:09:06", "throughput": 4427.55, "total_tokens": 66131376} {"current_steps": 30645, "total_steps": 61300, "loss": 0.3356, "lr": 2.9349616001074588e-05, "epoch": 4.999184339314845, "percentage": 49.99, "elapsed_time": "4:08:58", "remaining_time": "4:09:03", "throughput": 4427.63, "total_tokens": 66142800} {"current_steps": 30650, "total_steps": 61300, "loss": 0.3583, "lr": 2.934260640345867e-05, "epoch": 5.0, "percentage": 50.0, "elapsed_time": "4:09:00", "remaining_time": "4:09:00", "throughput": 4427.65, "total_tokens": 66152480} {"current_steps": 30650, "total_steps": 61300, "eval_loss": 0.3383404314517975, "epoch": 5.0, "percentage": 50.0, "elapsed_time": "4:11:13", "remaining_time": "4:11:13", "throughput": 4388.69, "total_tokens": 66152480} {"current_steps": 30655, "total_steps": 61300, "loss": 0.3942, "lr": 2.9335596453809055e-05, "epoch": 5.000815660685155, "percentage": 50.01, "elapsed_time": "4:11:16", "remaining_time": "4:11:11", "throughput": 4388.38, "total_tokens": 66162912} {"current_steps": 30660, "total_steps": 61300, "loss": 0.3496, "lr": 2.9328586152693986e-05, "epoch": 5.00163132137031, "percentage": 50.02, "elapsed_time": "4:11:18", "remaining_time": "4:11:09", "throughput": 4388.45, "total_tokens": 66173312} {"current_steps": 30665, "total_steps": 61300, "loss": 0.3408, "lr": 2.9321575500681757e-05, "epoch": 5.002446982055465, "percentage": 50.02, "elapsed_time": "4:11:21", "remaining_time": "4:11:06", "throughput": 4388.51, "total_tokens": 66184832} {"current_steps": 30670, "total_steps": 61300, "loss": 0.3119, "lr": 2.93145644983407e-05, "epoch": 5.00326264274062, "percentage": 50.03, "elapsed_time": "4:11:23", "remaining_time": "4:11:04", "throughput": 4388.57, "total_tokens": 66196544} {"current_steps": 30675, "total_steps": 61300, "loss": 0.3426, "lr": 2.9307553146239146e-05, "epoch": 5.004078303425775, "percentage": 50.04, "elapsed_time": "4:11:26", "remaining_time": "4:11:01", "throughput": 4388.64, "total_tokens": 66207904} {"current_steps": 30680, "total_steps": 61300, "loss": 0.3489, "lr": 2.930054144494548e-05, "epoch": 5.00489396411093, "percentage": 50.05, "elapsed_time": "4:11:28", "remaining_time": "4:10:58", "throughput": 4388.71, "total_tokens": 66218752} {"current_steps": 30685, "total_steps": 61300, "loss": 0.3351, "lr": 2.9293529395028102e-05, "epoch": 5.005709624796085, "percentage": 50.06, "elapsed_time": "4:11:30", "remaining_time": "4:10:56", "throughput": 4388.77, "total_tokens": 66230528} {"current_steps": 30690, "total_steps": 61300, "loss": 0.3353, "lr": 2.928651699705545e-05, "epoch": 5.006525285481239, "percentage": 50.07, "elapsed_time": "4:11:32", "remaining_time": "4:10:53", "throughput": 4388.84, "total_tokens": 66240768} {"current_steps": 30695, "total_steps": 61300, "loss": 0.3426, "lr": 2.927950425159598e-05, "epoch": 5.007340946166395, "percentage": 50.07, "elapsed_time": "4:11:35", "remaining_time": "4:10:51", "throughput": 4388.91, "total_tokens": 66252672} {"current_steps": 30700, "total_steps": 61300, "loss": 0.3128, "lr": 2.927249115921818e-05, "epoch": 5.00815660685155, "percentage": 50.08, "elapsed_time": "4:11:37", "remaining_time": "4:10:48", "throughput": 4388.97, "total_tokens": 66263520} {"current_steps": 30705, "total_steps": 61300, "loss": 0.3288, "lr": 2.926547772049057e-05, "epoch": 5.008972267536705, "percentage": 50.09, "elapsed_time": "4:11:40", "remaining_time": "4:10:45", "throughput": 4389.04, "total_tokens": 66274752} {"current_steps": 30710, "total_steps": 61300, "loss": 0.3054, "lr": 2.9258463935981696e-05, "epoch": 5.00978792822186, "percentage": 50.1, "elapsed_time": "4:11:42", "remaining_time": "4:10:43", "throughput": 4389.1, "total_tokens": 66285440} {"current_steps": 30715, "total_steps": 61300, "loss": 0.3339, "lr": 2.9251449806260122e-05, "epoch": 5.010603588907014, "percentage": 50.11, "elapsed_time": "4:11:44", "remaining_time": "4:10:40", "throughput": 4389.16, "total_tokens": 66295040} {"current_steps": 30720, "total_steps": 61300, "loss": 0.3334, "lr": 2.9244435331894454e-05, "epoch": 5.011419249592169, "percentage": 50.11, "elapsed_time": "4:11:46", "remaining_time": "4:10:37", "throughput": 4389.22, "total_tokens": 66304384} {"current_steps": 30725, "total_steps": 61300, "loss": 0.3652, "lr": 2.9237420513453328e-05, "epoch": 5.012234910277325, "percentage": 50.12, "elapsed_time": "4:11:48", "remaining_time": "4:10:34", "throughput": 4389.29, "total_tokens": 66315648} {"current_steps": 30730, "total_steps": 61300, "loss": 0.299, "lr": 2.9230405351505386e-05, "epoch": 5.01305057096248, "percentage": 50.13, "elapsed_time": "4:11:50", "remaining_time": "4:10:31", "throughput": 4389.35, "total_tokens": 66325664} {"current_steps": 30735, "total_steps": 61300, "loss": 0.3219, "lr": 2.9223389846619326e-05, "epoch": 5.013866231647635, "percentage": 50.14, "elapsed_time": "4:11:52", "remaining_time": "4:10:29", "throughput": 4389.42, "total_tokens": 66336544} {"current_steps": 30740, "total_steps": 61300, "loss": 0.3379, "lr": 2.921637399936386e-05, "epoch": 5.014681892332789, "percentage": 50.15, "elapsed_time": "4:11:55", "remaining_time": "4:10:26", "throughput": 4389.47, "total_tokens": 66347360} {"current_steps": 30745, "total_steps": 61300, "loss": 0.3593, "lr": 2.920935781030772e-05, "epoch": 5.015497553017944, "percentage": 50.15, "elapsed_time": "4:11:57", "remaining_time": "4:10:23", "throughput": 4389.52, "total_tokens": 66356992} {"current_steps": 30750, "total_steps": 61300, "loss": 0.3266, "lr": 2.9202341280019675e-05, "epoch": 5.0163132137031, "percentage": 50.16, "elapsed_time": "4:11:59", "remaining_time": "4:10:21", "throughput": 4389.59, "total_tokens": 66368032} {"current_steps": 30755, "total_steps": 61300, "loss": 0.3002, "lr": 2.9195324409068525e-05, "epoch": 5.017128874388255, "percentage": 50.17, "elapsed_time": "4:12:01", "remaining_time": "4:10:18", "throughput": 4389.65, "total_tokens": 66379424} {"current_steps": 30760, "total_steps": 61300, "loss": 0.3735, "lr": 2.9188307198023095e-05, "epoch": 5.0179445350734095, "percentage": 50.18, "elapsed_time": "4:12:04", "remaining_time": "4:10:16", "throughput": 4389.71, "total_tokens": 66390752} {"current_steps": 30765, "total_steps": 61300, "loss": 0.3113, "lr": 2.918128964745223e-05, "epoch": 5.018760195758564, "percentage": 50.19, "elapsed_time": "4:12:06", "remaining_time": "4:10:13", "throughput": 4389.79, "total_tokens": 66403200} {"current_steps": 30770, "total_steps": 61300, "loss": 0.3329, "lr": 2.9174271757924814e-05, "epoch": 5.019575856443719, "percentage": 50.2, "elapsed_time": "4:12:08", "remaining_time": "4:10:10", "throughput": 4389.84, "total_tokens": 66412768} {"current_steps": 30775, "total_steps": 61300, "loss": 0.3059, "lr": 2.9167253530009748e-05, "epoch": 5.020391517128874, "percentage": 50.2, "elapsed_time": "4:12:11", "remaining_time": "4:10:08", "throughput": 4389.91, "total_tokens": 66424448} {"current_steps": 30780, "total_steps": 61300, "loss": 0.345, "lr": 2.9160234964275963e-05, "epoch": 5.02120717781403, "percentage": 50.21, "elapsed_time": "4:12:13", "remaining_time": "4:10:05", "throughput": 4389.97, "total_tokens": 66434400} {"current_steps": 30785, "total_steps": 61300, "loss": 0.3518, "lr": 2.915321606129242e-05, "epoch": 5.0220228384991845, "percentage": 50.22, "elapsed_time": "4:12:15", "remaining_time": "4:10:02", "throughput": 4390.03, "total_tokens": 66445440} {"current_steps": 30790, "total_steps": 61300, "loss": 0.3649, "lr": 2.9146196821628113e-05, "epoch": 5.022838499184339, "percentage": 50.23, "elapsed_time": "4:12:17", "remaining_time": "4:10:00", "throughput": 4390.09, "total_tokens": 66455776} {"current_steps": 30795, "total_steps": 61300, "loss": 0.3127, "lr": 2.9139177245852056e-05, "epoch": 5.023654159869494, "percentage": 50.24, "elapsed_time": "4:12:20", "remaining_time": "4:09:57", "throughput": 4390.17, "total_tokens": 66467616} {"current_steps": 30800, "total_steps": 61300, "loss": 0.3399, "lr": 2.9132157334533295e-05, "epoch": 5.024469820554649, "percentage": 50.24, "elapsed_time": "4:12:22", "remaining_time": "4:09:54", "throughput": 4390.22, "total_tokens": 66477056} {"current_steps": 30805, "total_steps": 61300, "loss": 0.328, "lr": 2.9125137088240885e-05, "epoch": 5.025285481239805, "percentage": 50.25, "elapsed_time": "4:12:24", "remaining_time": "4:09:52", "throughput": 4390.29, "total_tokens": 66488352} {"current_steps": 30810, "total_steps": 61300, "loss": 0.3368, "lr": 2.9118116507543936e-05, "epoch": 5.0261011419249595, "percentage": 50.26, "elapsed_time": "4:12:26", "remaining_time": "4:09:49", "throughput": 4390.35, "total_tokens": 66497824} {"current_steps": 30815, "total_steps": 61300, "loss": 0.3656, "lr": 2.9111095593011567e-05, "epoch": 5.026916802610114, "percentage": 50.27, "elapsed_time": "4:12:28", "remaining_time": "4:09:46", "throughput": 4390.44, "total_tokens": 66509920} {"current_steps": 30820, "total_steps": 61300, "loss": 0.3209, "lr": 2.9104074345212933e-05, "epoch": 5.027732463295269, "percentage": 50.28, "elapsed_time": "4:12:30", "remaining_time": "4:09:43", "throughput": 4390.49, "total_tokens": 66519520} {"current_steps": 30825, "total_steps": 61300, "loss": 0.3368, "lr": 2.9097052764717196e-05, "epoch": 5.028548123980424, "percentage": 50.29, "elapsed_time": "4:12:32", "remaining_time": "4:09:40", "throughput": 4390.54, "total_tokens": 66529792} {"current_steps": 30830, "total_steps": 61300, "loss": 0.3587, "lr": 2.9090030852093586e-05, "epoch": 5.029363784665579, "percentage": 50.29, "elapsed_time": "4:12:35", "remaining_time": "4:09:38", "throughput": 4390.61, "total_tokens": 66540416} {"current_steps": 30835, "total_steps": 61300, "loss": 0.3512, "lr": 2.9083008607911322e-05, "epoch": 5.0301794453507345, "percentage": 50.3, "elapsed_time": "4:12:37", "remaining_time": "4:09:35", "throughput": 4390.66, "total_tokens": 66549280} {"current_steps": 30840, "total_steps": 61300, "loss": 0.3393, "lr": 2.9075986032739656e-05, "epoch": 5.030995106035889, "percentage": 50.31, "elapsed_time": "4:12:39", "remaining_time": "4:09:32", "throughput": 4390.73, "total_tokens": 66560640} {"current_steps": 30845, "total_steps": 61300, "loss": 0.3175, "lr": 2.9068963127147886e-05, "epoch": 5.031810766721044, "percentage": 50.32, "elapsed_time": "4:12:41", "remaining_time": "4:09:29", "throughput": 4390.79, "total_tokens": 66571808} {"current_steps": 30850, "total_steps": 61300, "loss": 0.3428, "lr": 2.906193989170532e-05, "epoch": 5.032626427406199, "percentage": 50.33, "elapsed_time": "4:12:44", "remaining_time": "4:09:27", "throughput": 4390.85, "total_tokens": 66583424} {"current_steps": 30855, "total_steps": 61300, "loss": 0.3675, "lr": 2.9054916326981297e-05, "epoch": 5.033442088091354, "percentage": 50.33, "elapsed_time": "4:12:46", "remaining_time": "4:09:24", "throughput": 4390.92, "total_tokens": 66593984} {"current_steps": 30860, "total_steps": 61300, "loss": 0.3326, "lr": 2.9047892433545176e-05, "epoch": 5.034257748776509, "percentage": 50.34, "elapsed_time": "4:12:48", "remaining_time": "4:09:22", "throughput": 4390.99, "total_tokens": 66604704} {"current_steps": 30865, "total_steps": 61300, "loss": 0.3434, "lr": 2.9040868211966364e-05, "epoch": 5.035073409461664, "percentage": 50.35, "elapsed_time": "4:12:50", "remaining_time": "4:09:19", "throughput": 4391.07, "total_tokens": 66615808} {"current_steps": 30870, "total_steps": 61300, "loss": 0.3441, "lr": 2.903384366281427e-05, "epoch": 5.035889070146819, "percentage": 50.36, "elapsed_time": "4:12:53", "remaining_time": "4:09:16", "throughput": 4391.14, "total_tokens": 66627008} {"current_steps": 30875, "total_steps": 61300, "loss": 0.3279, "lr": 2.902681878665834e-05, "epoch": 5.036704730831974, "percentage": 50.37, "elapsed_time": "4:12:55", "remaining_time": "4:09:14", "throughput": 4391.22, "total_tokens": 66638464} {"current_steps": 30880, "total_steps": 61300, "loss": 0.3459, "lr": 2.9019793584068046e-05, "epoch": 5.037520391517129, "percentage": 50.38, "elapsed_time": "4:12:57", "remaining_time": "4:09:11", "throughput": 4391.27, "total_tokens": 66648544} {"current_steps": 30885, "total_steps": 61300, "loss": 0.3402, "lr": 2.9012768055612887e-05, "epoch": 5.0383360522022835, "percentage": 50.38, "elapsed_time": "4:12:59", "remaining_time": "4:09:08", "throughput": 4391.34, "total_tokens": 66660384} {"current_steps": 30890, "total_steps": 61300, "loss": 0.3298, "lr": 2.9005742201862385e-05, "epoch": 5.039151712887439, "percentage": 50.39, "elapsed_time": "4:13:02", "remaining_time": "4:09:06", "throughput": 4391.4, "total_tokens": 66671136} {"current_steps": 30895, "total_steps": 61300, "loss": 0.3663, "lr": 2.8998716023386096e-05, "epoch": 5.039967373572594, "percentage": 50.4, "elapsed_time": "4:13:04", "remaining_time": "4:09:03", "throughput": 4391.46, "total_tokens": 66681664} {"current_steps": 30900, "total_steps": 61300, "loss": 0.3606, "lr": 2.8991689520753605e-05, "epoch": 5.040783034257749, "percentage": 50.41, "elapsed_time": "4:13:06", "remaining_time": "4:09:00", "throughput": 4391.51, "total_tokens": 66691968} {"current_steps": 30905, "total_steps": 61300, "loss": 0.3499, "lr": 2.8984662694534504e-05, "epoch": 5.041598694942904, "percentage": 50.42, "elapsed_time": "4:13:08", "remaining_time": "4:08:58", "throughput": 4391.58, "total_tokens": 66703488} {"current_steps": 30910, "total_steps": 61300, "loss": 0.3329, "lr": 2.897763554529842e-05, "epoch": 5.0424143556280585, "percentage": 50.42, "elapsed_time": "4:13:11", "remaining_time": "4:08:55", "throughput": 4391.64, "total_tokens": 66714304} {"current_steps": 30915, "total_steps": 61300, "loss": 0.3245, "lr": 2.8970608073615026e-05, "epoch": 5.043230016313213, "percentage": 50.43, "elapsed_time": "4:13:13", "remaining_time": "4:08:52", "throughput": 4391.71, "total_tokens": 66724864} {"current_steps": 30920, "total_steps": 61300, "loss": 0.3693, "lr": 2.8963580280053992e-05, "epoch": 5.044045676998369, "percentage": 50.44, "elapsed_time": "4:13:15", "remaining_time": "4:08:50", "throughput": 4391.78, "total_tokens": 66736736} {"current_steps": 30925, "total_steps": 61300, "loss": 0.333, "lr": 2.8956552165185023e-05, "epoch": 5.044861337683524, "percentage": 50.45, "elapsed_time": "4:13:18", "remaining_time": "4:08:47", "throughput": 4391.85, "total_tokens": 66748128} {"current_steps": 30930, "total_steps": 61300, "loss": 0.3285, "lr": 2.894952372957787e-05, "epoch": 5.045676998368679, "percentage": 50.46, "elapsed_time": "4:13:20", "remaining_time": "4:08:45", "throughput": 4391.91, "total_tokens": 66759200} {"current_steps": 30935, "total_steps": 61300, "loss": 0.3492, "lr": 2.894249497380228e-05, "epoch": 5.0464926590538335, "percentage": 50.46, "elapsed_time": "4:13:22", "remaining_time": "4:08:42", "throughput": 4391.98, "total_tokens": 66770720} {"current_steps": 30940, "total_steps": 61300, "loss": 0.3831, "lr": 2.893546589842805e-05, "epoch": 5.047308319738988, "percentage": 50.47, "elapsed_time": "4:13:25", "remaining_time": "4:08:40", "throughput": 4392.04, "total_tokens": 66781312} {"current_steps": 30945, "total_steps": 61300, "loss": 0.3352, "lr": 2.892843650402497e-05, "epoch": 5.048123980424143, "percentage": 50.48, "elapsed_time": "4:13:27", "remaining_time": "4:08:37", "throughput": 4392.1, "total_tokens": 66792864} {"current_steps": 30950, "total_steps": 61300, "loss": 0.3396, "lr": 2.8921406791162902e-05, "epoch": 5.048939641109299, "percentage": 50.49, "elapsed_time": "4:13:29", "remaining_time": "4:08:34", "throughput": 4392.15, "total_tokens": 66802976} {"current_steps": 30955, "total_steps": 61300, "loss": 0.3635, "lr": 2.891437676041171e-05, "epoch": 5.049755301794454, "percentage": 50.5, "elapsed_time": "4:13:31", "remaining_time": "4:08:31", "throughput": 4392.2, "total_tokens": 66812768} {"current_steps": 30960, "total_steps": 61300, "loss": 0.3175, "lr": 2.890734641234127e-05, "epoch": 5.0505709624796085, "percentage": 50.51, "elapsed_time": "4:13:33", "remaining_time": "4:08:29", "throughput": 4392.26, "total_tokens": 66823072} {"current_steps": 30965, "total_steps": 61300, "loss": 0.3226, "lr": 2.8900315747521507e-05, "epoch": 5.051386623164763, "percentage": 50.51, "elapsed_time": "4:13:36", "remaining_time": "4:08:26", "throughput": 4392.31, "total_tokens": 66835200} {"current_steps": 30970, "total_steps": 61300, "loss": 0.3325, "lr": 2.8893284766522353e-05, "epoch": 5.052202283849918, "percentage": 50.52, "elapsed_time": "4:13:38", "remaining_time": "4:08:24", "throughput": 4392.38, "total_tokens": 66846528} {"current_steps": 30975, "total_steps": 61300, "loss": 0.3224, "lr": 2.8886253469913787e-05, "epoch": 5.053017944535074, "percentage": 50.53, "elapsed_time": "4:13:41", "remaining_time": "4:08:21", "throughput": 4392.44, "total_tokens": 66858080} {"current_steps": 30980, "total_steps": 61300, "loss": 0.3605, "lr": 2.8879221858265794e-05, "epoch": 5.053833605220229, "percentage": 50.54, "elapsed_time": "4:13:43", "remaining_time": "4:08:19", "throughput": 4392.52, "total_tokens": 66869888} {"current_steps": 30985, "total_steps": 61300, "loss": 0.3053, "lr": 2.8872189932148392e-05, "epoch": 5.054649265905383, "percentage": 50.55, "elapsed_time": "4:13:45", "remaining_time": "4:08:16", "throughput": 4392.57, "total_tokens": 66880256} {"current_steps": 30990, "total_steps": 61300, "loss": 0.3264, "lr": 2.8865157692131633e-05, "epoch": 5.055464926590538, "percentage": 50.55, "elapsed_time": "4:13:47", "remaining_time": "4:08:13", "throughput": 4392.63, "total_tokens": 66890784} {"current_steps": 30995, "total_steps": 61300, "loss": 0.3546, "lr": 2.8858125138785568e-05, "epoch": 5.056280587275693, "percentage": 50.56, "elapsed_time": "4:13:50", "remaining_time": "4:08:11", "throughput": 4392.7, "total_tokens": 66901920} {"current_steps": 31000, "total_steps": 61300, "loss": 0.3479, "lr": 2.8851092272680313e-05, "epoch": 5.057096247960848, "percentage": 50.57, "elapsed_time": "4:13:52", "remaining_time": "4:08:08", "throughput": 4392.76, "total_tokens": 66912608} {"current_steps": 31005, "total_steps": 61300, "loss": 0.3407, "lr": 2.8844059094385977e-05, "epoch": 5.057911908646004, "percentage": 50.58, "elapsed_time": "4:13:54", "remaining_time": "4:08:05", "throughput": 4392.82, "total_tokens": 66922336} {"current_steps": 31010, "total_steps": 61300, "loss": 0.3198, "lr": 2.883702560447271e-05, "epoch": 5.058727569331158, "percentage": 50.59, "elapsed_time": "4:13:56", "remaining_time": "4:08:02", "throughput": 4392.87, "total_tokens": 66932960} {"current_steps": 31015, "total_steps": 61300, "loss": 0.3253, "lr": 2.8829991803510675e-05, "epoch": 5.059543230016313, "percentage": 50.6, "elapsed_time": "4:13:59", "remaining_time": "4:08:00", "throughput": 4392.93, "total_tokens": 66944448} {"current_steps": 31020, "total_steps": 61300, "loss": 0.272, "lr": 2.8822957692070073e-05, "epoch": 5.060358890701468, "percentage": 50.6, "elapsed_time": "4:14:01", "remaining_time": "4:07:57", "throughput": 4393.01, "total_tokens": 66955264} {"current_steps": 31025, "total_steps": 61300, "loss": 0.3246, "lr": 2.8815923270721124e-05, "epoch": 5.061174551386623, "percentage": 50.61, "elapsed_time": "4:14:03", "remaining_time": "4:07:54", "throughput": 4393.05, "total_tokens": 66965024} {"current_steps": 31030, "total_steps": 61300, "loss": 0.3849, "lr": 2.8808888540034067e-05, "epoch": 5.061990212071779, "percentage": 50.62, "elapsed_time": "4:14:05", "remaining_time": "4:07:52", "throughput": 4393.1, "total_tokens": 66975072} {"current_steps": 31035, "total_steps": 61300, "loss": 0.3095, "lr": 2.8801853500579183e-05, "epoch": 5.062805872756933, "percentage": 50.63, "elapsed_time": "4:14:08", "remaining_time": "4:07:49", "throughput": 4393.17, "total_tokens": 66987232} {"current_steps": 31040, "total_steps": 61300, "loss": 0.3566, "lr": 2.879481815292676e-05, "epoch": 5.063621533442088, "percentage": 50.64, "elapsed_time": "4:14:09", "remaining_time": "4:07:46", "throughput": 4393.23, "total_tokens": 66995968} {"current_steps": 31045, "total_steps": 61300, "loss": 0.3057, "lr": 2.878778249764713e-05, "epoch": 5.064437194127243, "percentage": 50.64, "elapsed_time": "4:14:12", "remaining_time": "4:07:43", "throughput": 4393.29, "total_tokens": 67006912} {"current_steps": 31050, "total_steps": 61300, "loss": 0.3263, "lr": 2.8780746535310623e-05, "epoch": 5.065252854812398, "percentage": 50.65, "elapsed_time": "4:14:14", "remaining_time": "4:07:41", "throughput": 4393.36, "total_tokens": 67017824} {"current_steps": 31055, "total_steps": 61300, "loss": 0.3062, "lr": 2.8773710266487623e-05, "epoch": 5.066068515497553, "percentage": 50.66, "elapsed_time": "4:14:16", "remaining_time": "4:07:38", "throughput": 4393.41, "total_tokens": 67028736} {"current_steps": 31060, "total_steps": 61300, "loss": 0.3097, "lr": 2.8766673691748524e-05, "epoch": 5.066884176182708, "percentage": 50.67, "elapsed_time": "4:14:18", "remaining_time": "4:07:36", "throughput": 4393.47, "total_tokens": 67039936} {"current_steps": 31065, "total_steps": 61300, "loss": 0.3334, "lr": 2.875963681166373e-05, "epoch": 5.067699836867863, "percentage": 50.68, "elapsed_time": "4:14:21", "remaining_time": "4:07:33", "throughput": 4393.54, "total_tokens": 67051616} {"current_steps": 31070, "total_steps": 61300, "loss": 0.3343, "lr": 2.8752599626803717e-05, "epoch": 5.068515497553018, "percentage": 50.69, "elapsed_time": "4:14:23", "remaining_time": "4:07:30", "throughput": 4393.6, "total_tokens": 67062240} {"current_steps": 31075, "total_steps": 61300, "loss": 0.342, "lr": 2.874556213773893e-05, "epoch": 5.069331158238173, "percentage": 50.69, "elapsed_time": "4:14:25", "remaining_time": "4:07:28", "throughput": 4393.66, "total_tokens": 67073408} {"current_steps": 31080, "total_steps": 61300, "loss": 0.2972, "lr": 2.8738524345039876e-05, "epoch": 5.070146818923328, "percentage": 50.7, "elapsed_time": "4:14:28", "remaining_time": "4:07:25", "throughput": 4393.73, "total_tokens": 67084896} {"current_steps": 31085, "total_steps": 61300, "loss": 0.3508, "lr": 2.8731486249277062e-05, "epoch": 5.0709624796084825, "percentage": 50.71, "elapsed_time": "4:14:30", "remaining_time": "4:07:23", "throughput": 4393.79, "total_tokens": 67095040} {"current_steps": 31090, "total_steps": 61300, "loss": 0.3359, "lr": 2.8724447851021047e-05, "epoch": 5.071778140293638, "percentage": 50.72, "elapsed_time": "4:14:32", "remaining_time": "4:07:20", "throughput": 4393.85, "total_tokens": 67106336} {"current_steps": 31095, "total_steps": 61300, "loss": 0.3686, "lr": 2.871740915084239e-05, "epoch": 5.072593800978793, "percentage": 50.73, "elapsed_time": "4:14:34", "remaining_time": "4:07:17", "throughput": 4393.91, "total_tokens": 67116832} {"current_steps": 31100, "total_steps": 61300, "loss": 0.3017, "lr": 2.871037014931168e-05, "epoch": 5.073409461663948, "percentage": 50.73, "elapsed_time": "4:14:37", "remaining_time": "4:07:15", "throughput": 4393.96, "total_tokens": 67128736} {"current_steps": 31105, "total_steps": 61300, "loss": 0.3598, "lr": 2.870333084699954e-05, "epoch": 5.074225122349103, "percentage": 50.74, "elapsed_time": "4:14:39", "remaining_time": "4:07:12", "throughput": 4394.03, "total_tokens": 67140128} {"current_steps": 31110, "total_steps": 61300, "loss": 0.3322, "lr": 2.8696291244476613e-05, "epoch": 5.075040783034257, "percentage": 50.75, "elapsed_time": "4:14:42", "remaining_time": "4:07:10", "throughput": 4394.1, "total_tokens": 67151232} {"current_steps": 31115, "total_steps": 61300, "loss": 0.3181, "lr": 2.8689251342313562e-05, "epoch": 5.075856443719413, "percentage": 50.76, "elapsed_time": "4:14:44", "remaining_time": "4:07:07", "throughput": 4394.17, "total_tokens": 67161984} {"current_steps": 31120, "total_steps": 61300, "loss": 0.339, "lr": 2.8682211141081084e-05, "epoch": 5.076672104404568, "percentage": 50.77, "elapsed_time": "4:14:46", "remaining_time": "4:07:04", "throughput": 4394.23, "total_tokens": 67172224} {"current_steps": 31125, "total_steps": 61300, "loss": 0.3308, "lr": 2.867517064134988e-05, "epoch": 5.077487765089723, "percentage": 50.77, "elapsed_time": "4:14:48", "remaining_time": "4:07:01", "throughput": 4394.29, "total_tokens": 67182560} {"current_steps": 31130, "total_steps": 61300, "loss": 0.3591, "lr": 2.8668129843690704e-05, "epoch": 5.078303425774878, "percentage": 50.78, "elapsed_time": "4:14:50", "remaining_time": "4:06:59", "throughput": 4394.35, "total_tokens": 67193024} {"current_steps": 31135, "total_steps": 61300, "loss": 0.3364, "lr": 2.86610887486743e-05, "epoch": 5.079119086460032, "percentage": 50.79, "elapsed_time": "4:14:53", "remaining_time": "4:06:56", "throughput": 4394.41, "total_tokens": 67204096} {"current_steps": 31140, "total_steps": 61300, "loss": 0.3191, "lr": 2.8654047356871473e-05, "epoch": 5.079934747145187, "percentage": 50.8, "elapsed_time": "4:14:55", "remaining_time": "4:06:53", "throughput": 4394.46, "total_tokens": 67214432} {"current_steps": 31145, "total_steps": 61300, "loss": 0.3523, "lr": 2.8647005668853027e-05, "epoch": 5.080750407830343, "percentage": 50.81, "elapsed_time": "4:14:57", "remaining_time": "4:06:51", "throughput": 4394.53, "total_tokens": 67225792} {"current_steps": 31150, "total_steps": 61300, "loss": 0.3293, "lr": 2.8639963685189795e-05, "epoch": 5.081566068515498, "percentage": 50.82, "elapsed_time": "4:14:59", "remaining_time": "4:06:48", "throughput": 4394.59, "total_tokens": 67236128} {"current_steps": 31155, "total_steps": 61300, "loss": 0.3136, "lr": 2.8632921406452635e-05, "epoch": 5.082381729200653, "percentage": 50.82, "elapsed_time": "4:15:02", "remaining_time": "4:06:45", "throughput": 4394.66, "total_tokens": 67247072} {"current_steps": 31160, "total_steps": 61300, "loss": 0.3376, "lr": 2.862587883321244e-05, "epoch": 5.083197389885807, "percentage": 50.83, "elapsed_time": "4:15:04", "remaining_time": "4:06:43", "throughput": 4394.71, "total_tokens": 67257344} {"current_steps": 31165, "total_steps": 61300, "loss": 0.3615, "lr": 2.8618835966040104e-05, "epoch": 5.084013050570962, "percentage": 50.84, "elapsed_time": "4:15:06", "remaining_time": "4:06:40", "throughput": 4394.76, "total_tokens": 67266848} {"current_steps": 31170, "total_steps": 61300, "loss": 0.3264, "lr": 2.8611792805506565e-05, "epoch": 5.084828711256117, "percentage": 50.85, "elapsed_time": "4:15:08", "remaining_time": "4:06:37", "throughput": 4394.82, "total_tokens": 67277056} {"current_steps": 31175, "total_steps": 61300, "loss": 0.3551, "lr": 2.8604749352182776e-05, "epoch": 5.085644371941273, "percentage": 50.86, "elapsed_time": "4:15:10", "remaining_time": "4:06:34", "throughput": 4394.89, "total_tokens": 67288672} {"current_steps": 31180, "total_steps": 61300, "loss": 0.3546, "lr": 2.8597705606639707e-05, "epoch": 5.0864600326264275, "percentage": 50.86, "elapsed_time": "4:15:12", "remaining_time": "4:06:32", "throughput": 4394.94, "total_tokens": 67299424} {"current_steps": 31185, "total_steps": 61300, "loss": 0.344, "lr": 2.8590661569448372e-05, "epoch": 5.087275693311582, "percentage": 50.87, "elapsed_time": "4:15:14", "remaining_time": "4:06:29", "throughput": 4395.0, "total_tokens": 67309056} {"current_steps": 31190, "total_steps": 61300, "loss": 0.3306, "lr": 2.8583617241179796e-05, "epoch": 5.088091353996737, "percentage": 50.88, "elapsed_time": "4:15:17", "remaining_time": "4:06:26", "throughput": 4395.05, "total_tokens": 67320320} {"current_steps": 31195, "total_steps": 61300, "loss": 0.3439, "lr": 2.8576572622405017e-05, "epoch": 5.088907014681892, "percentage": 50.89, "elapsed_time": "4:15:19", "remaining_time": "4:06:24", "throughput": 4395.1, "total_tokens": 67330944} {"current_steps": 31200, "total_steps": 61300, "loss": 0.3379, "lr": 2.856952771369512e-05, "epoch": 5.089722675367048, "percentage": 50.9, "elapsed_time": "4:15:21", "remaining_time": "4:06:21", "throughput": 4395.18, "total_tokens": 67342720} {"current_steps": 31205, "total_steps": 61300, "loss": 0.3454, "lr": 2.856248251562119e-05, "epoch": 5.0905383360522025, "percentage": 50.91, "elapsed_time": "4:15:24", "remaining_time": "4:06:19", "throughput": 4395.24, "total_tokens": 67353856} {"current_steps": 31210, "total_steps": 61300, "loss": 0.352, "lr": 2.8555437028754352e-05, "epoch": 5.091353996737357, "percentage": 50.91, "elapsed_time": "4:15:26", "remaining_time": "4:06:16", "throughput": 4395.3, "total_tokens": 67364384} {"current_steps": 31215, "total_steps": 61300, "loss": 0.324, "lr": 2.8548391253665746e-05, "epoch": 5.092169657422512, "percentage": 50.92, "elapsed_time": "4:15:28", "remaining_time": "4:06:13", "throughput": 4395.36, "total_tokens": 67375328} {"current_steps": 31220, "total_steps": 61300, "loss": 0.3295, "lr": 2.854134519092654e-05, "epoch": 5.092985318107667, "percentage": 50.93, "elapsed_time": "4:15:30", "remaining_time": "4:06:11", "throughput": 4395.43, "total_tokens": 67386240} {"current_steps": 31225, "total_steps": 61300, "loss": 0.331, "lr": 2.8534298841107925e-05, "epoch": 5.093800978792822, "percentage": 50.94, "elapsed_time": "4:15:33", "remaining_time": "4:06:08", "throughput": 4395.5, "total_tokens": 67397760} {"current_steps": 31230, "total_steps": 61300, "loss": 0.3522, "lr": 2.8527252204781117e-05, "epoch": 5.0946166394779775, "percentage": 50.95, "elapsed_time": "4:15:35", "remaining_time": "4:06:06", "throughput": 4395.56, "total_tokens": 67408768} {"current_steps": 31235, "total_steps": 61300, "loss": 0.3655, "lr": 2.852020528251735e-05, "epoch": 5.095432300163132, "percentage": 50.95, "elapsed_time": "4:15:37", "remaining_time": "4:06:03", "throughput": 4395.61, "total_tokens": 67419456} {"current_steps": 31240, "total_steps": 61300, "loss": 0.3729, "lr": 2.8513158074887875e-05, "epoch": 5.096247960848287, "percentage": 50.96, "elapsed_time": "4:15:40", "remaining_time": "4:06:00", "throughput": 4395.68, "total_tokens": 67430528} {"current_steps": 31245, "total_steps": 61300, "loss": 0.3367, "lr": 2.8506110582463984e-05, "epoch": 5.097063621533442, "percentage": 50.97, "elapsed_time": "4:15:42", "remaining_time": "4:05:58", "throughput": 4395.74, "total_tokens": 67441472} {"current_steps": 31250, "total_steps": 61300, "loss": 0.3354, "lr": 2.8499062805816984e-05, "epoch": 5.097879282218597, "percentage": 50.98, "elapsed_time": "4:15:44", "remaining_time": "4:05:55", "throughput": 4395.78, "total_tokens": 67451808} {"current_steps": 31255, "total_steps": 61300, "loss": 0.3089, "lr": 2.8492014745518192e-05, "epoch": 5.0986949429037525, "percentage": 50.99, "elapsed_time": "4:15:47", "remaining_time": "4:05:52", "throughput": 4395.84, "total_tokens": 67463104} {"current_steps": 31260, "total_steps": 61300, "loss": 0.3146, "lr": 2.8484966402138968e-05, "epoch": 5.099510603588907, "percentage": 51.0, "elapsed_time": "4:15:49", "remaining_time": "4:05:50", "throughput": 4395.89, "total_tokens": 67474144} {"current_steps": 31265, "total_steps": 61300, "loss": 0.3355, "lr": 2.8477917776250683e-05, "epoch": 5.100326264274062, "percentage": 51.0, "elapsed_time": "4:15:51", "remaining_time": "4:05:47", "throughput": 4395.94, "total_tokens": 67484096} {"current_steps": 31270, "total_steps": 61300, "loss": 0.3454, "lr": 2.847086886842474e-05, "epoch": 5.101141924959217, "percentage": 51.01, "elapsed_time": "4:15:53", "remaining_time": "4:05:44", "throughput": 4396.0, "total_tokens": 67493664} {"current_steps": 31275, "total_steps": 61300, "loss": 0.321, "lr": 2.8463819679232555e-05, "epoch": 5.101957585644372, "percentage": 51.02, "elapsed_time": "4:15:55", "remaining_time": "4:05:42", "throughput": 4396.06, "total_tokens": 67504768} {"current_steps": 31280, "total_steps": 61300, "loss": 0.348, "lr": 2.845677020924557e-05, "epoch": 5.102773246329527, "percentage": 51.03, "elapsed_time": "4:15:57", "remaining_time": "4:05:39", "throughput": 4396.11, "total_tokens": 67514848} {"current_steps": 31285, "total_steps": 61300, "loss": 0.3414, "lr": 2.8449720459035256e-05, "epoch": 5.103588907014682, "percentage": 51.04, "elapsed_time": "4:16:00", "remaining_time": "4:05:36", "throughput": 4396.17, "total_tokens": 67525248} {"current_steps": 31290, "total_steps": 61300, "loss": 0.3505, "lr": 2.8442670429173098e-05, "epoch": 5.104404567699837, "percentage": 51.04, "elapsed_time": "4:16:01", "remaining_time": "4:05:33", "throughput": 4396.23, "total_tokens": 67534656} {"current_steps": 31295, "total_steps": 61300, "loss": 0.3407, "lr": 2.8435620120230595e-05, "epoch": 5.105220228384992, "percentage": 51.05, "elapsed_time": "4:16:04", "remaining_time": "4:05:30", "throughput": 4396.29, "total_tokens": 67545024} {"current_steps": 31300, "total_steps": 61300, "loss": 0.3329, "lr": 2.84285695327793e-05, "epoch": 5.106035889070147, "percentage": 51.06, "elapsed_time": "4:16:06", "remaining_time": "4:05:28", "throughput": 4396.36, "total_tokens": 67556640} {"current_steps": 31305, "total_steps": 61300, "loss": 0.3293, "lr": 2.842151866739077e-05, "epoch": 5.1068515497553015, "percentage": 51.07, "elapsed_time": "4:16:08", "remaining_time": "4:05:25", "throughput": 4396.43, "total_tokens": 67568032} {"current_steps": 31310, "total_steps": 61300, "loss": 0.3241, "lr": 2.8414467524636568e-05, "epoch": 5.107667210440456, "percentage": 51.08, "elapsed_time": "4:16:11", "remaining_time": "4:05:23", "throughput": 4396.48, "total_tokens": 67578688} {"current_steps": 31315, "total_steps": 61300, "loss": 0.3351, "lr": 2.8407416105088304e-05, "epoch": 5.108482871125612, "percentage": 51.08, "elapsed_time": "4:16:13", "remaining_time": "4:05:20", "throughput": 4396.53, "total_tokens": 67589664} {"current_steps": 31320, "total_steps": 61300, "loss": 0.3467, "lr": 2.8400364409317604e-05, "epoch": 5.109298531810767, "percentage": 51.09, "elapsed_time": "4:16:15", "remaining_time": "4:05:17", "throughput": 4396.61, "total_tokens": 67600736} {"current_steps": 31325, "total_steps": 61300, "loss": 0.3334, "lr": 2.8393312437896112e-05, "epoch": 5.110114192495922, "percentage": 51.1, "elapsed_time": "4:16:18", "remaining_time": "4:05:15", "throughput": 4396.67, "total_tokens": 67612288} {"current_steps": 31330, "total_steps": 61300, "loss": 0.3599, "lr": 2.8386260191395497e-05, "epoch": 5.1109298531810765, "percentage": 51.11, "elapsed_time": "4:16:20", "remaining_time": "4:05:12", "throughput": 4396.72, "total_tokens": 67622592} {"current_steps": 31335, "total_steps": 61300, "loss": 0.3263, "lr": 2.837920767038745e-05, "epoch": 5.111745513866231, "percentage": 51.12, "elapsed_time": "4:16:22", "remaining_time": "4:05:09", "throughput": 4396.79, "total_tokens": 67633568} {"current_steps": 31340, "total_steps": 61300, "loss": 0.3406, "lr": 2.837215487544368e-05, "epoch": 5.112561174551387, "percentage": 51.13, "elapsed_time": "4:16:24", "remaining_time": "4:05:07", "throughput": 4396.84, "total_tokens": 67644000} {"current_steps": 31345, "total_steps": 61300, "loss": 0.3459, "lr": 2.836510180713593e-05, "epoch": 5.113376835236542, "percentage": 51.13, "elapsed_time": "4:16:26", "remaining_time": "4:05:04", "throughput": 4396.9, "total_tokens": 67654816} {"current_steps": 31350, "total_steps": 61300, "loss": 0.3405, "lr": 2.835804846603595e-05, "epoch": 5.114192495921697, "percentage": 51.14, "elapsed_time": "4:16:29", "remaining_time": "4:05:02", "throughput": 4396.96, "total_tokens": 67666304} {"current_steps": 31355, "total_steps": 61300, "loss": 0.3226, "lr": 2.8350994852715522e-05, "epoch": 5.1150081566068515, "percentage": 51.15, "elapsed_time": "4:16:31", "remaining_time": "4:04:59", "throughput": 4397.04, "total_tokens": 67677536} {"current_steps": 31360, "total_steps": 61300, "loss": 0.3548, "lr": 2.8343940967746453e-05, "epoch": 5.115823817292006, "percentage": 51.16, "elapsed_time": "4:16:33", "remaining_time": "4:04:56", "throughput": 4397.11, "total_tokens": 67688608} {"current_steps": 31365, "total_steps": 61300, "loss": 0.3588, "lr": 2.8336886811700548e-05, "epoch": 5.116639477977161, "percentage": 51.17, "elapsed_time": "4:16:36", "remaining_time": "4:04:54", "throughput": 4397.17, "total_tokens": 67699200} {"current_steps": 31370, "total_steps": 61300, "loss": 0.3648, "lr": 2.8329832385149678e-05, "epoch": 5.117455138662317, "percentage": 51.17, "elapsed_time": "4:16:38", "remaining_time": "4:04:51", "throughput": 4397.22, "total_tokens": 67709568} {"current_steps": 31375, "total_steps": 61300, "loss": 0.289, "lr": 2.8322777688665704e-05, "epoch": 5.118270799347472, "percentage": 51.18, "elapsed_time": "4:16:40", "remaining_time": "4:04:48", "throughput": 4397.27, "total_tokens": 67719360} {"current_steps": 31380, "total_steps": 61300, "loss": 0.3349, "lr": 2.83157227228205e-05, "epoch": 5.1190864600326265, "percentage": 51.19, "elapsed_time": "4:16:42", "remaining_time": "4:04:45", "throughput": 4397.32, "total_tokens": 67729472} {"current_steps": 31385, "total_steps": 61300, "loss": 0.349, "lr": 2.830866748818599e-05, "epoch": 5.119902120717781, "percentage": 51.2, "elapsed_time": "4:16:44", "remaining_time": "4:04:43", "throughput": 4397.37, "total_tokens": 67739424} {"current_steps": 31390, "total_steps": 61300, "loss": 0.294, "lr": 2.8301611985334115e-05, "epoch": 5.120717781402936, "percentage": 51.21, "elapsed_time": "4:16:46", "remaining_time": "4:04:40", "throughput": 4397.42, "total_tokens": 67750624} {"current_steps": 31395, "total_steps": 61300, "loss": 0.2969, "lr": 2.8294556214836813e-05, "epoch": 5.121533442088092, "percentage": 51.22, "elapsed_time": "4:16:49", "remaining_time": "4:04:37", "throughput": 4397.47, "total_tokens": 67760960} {"current_steps": 31400, "total_steps": 61300, "loss": 0.382, "lr": 2.828750017726607e-05, "epoch": 5.122349102773247, "percentage": 51.22, "elapsed_time": "4:16:51", "remaining_time": "4:04:35", "throughput": 4397.51, "total_tokens": 67771232} {"current_steps": 31405, "total_steps": 61300, "loss": 0.3384, "lr": 2.8280443873193884e-05, "epoch": 5.123164763458401, "percentage": 51.23, "elapsed_time": "4:16:53", "remaining_time": "4:04:32", "throughput": 4397.57, "total_tokens": 67781408} {"current_steps": 31410, "total_steps": 61300, "loss": 0.3254, "lr": 2.8273387303192266e-05, "epoch": 5.123980424143556, "percentage": 51.24, "elapsed_time": "4:16:55", "remaining_time": "4:04:29", "throughput": 4397.65, "total_tokens": 67793472} {"current_steps": 31415, "total_steps": 61300, "loss": 0.384, "lr": 2.8266330467833274e-05, "epoch": 5.124796084828711, "percentage": 51.25, "elapsed_time": "4:16:58", "remaining_time": "4:04:27", "throughput": 4397.71, "total_tokens": 67804704} {"current_steps": 31420, "total_steps": 61300, "loss": 0.3538, "lr": 2.8259273367688954e-05, "epoch": 5.125611745513866, "percentage": 51.26, "elapsed_time": "4:17:00", "remaining_time": "4:04:24", "throughput": 4397.77, "total_tokens": 67815840} {"current_steps": 31425, "total_steps": 61300, "loss": 0.3399, "lr": 2.8252216003331395e-05, "epoch": 5.126427406199022, "percentage": 51.26, "elapsed_time": "4:17:02", "remaining_time": "4:04:22", "throughput": 4397.84, "total_tokens": 67827008} {"current_steps": 31430, "total_steps": 61300, "loss": 0.3325, "lr": 2.824515837533271e-05, "epoch": 5.127243066884176, "percentage": 51.27, "elapsed_time": "4:17:04", "remaining_time": "4:04:19", "throughput": 4397.9, "total_tokens": 67837024} {"current_steps": 31435, "total_steps": 61300, "loss": 0.3158, "lr": 2.823810048426502e-05, "epoch": 5.128058727569331, "percentage": 51.28, "elapsed_time": "4:17:07", "remaining_time": "4:04:16", "throughput": 4397.96, "total_tokens": 67847360} {"current_steps": 31440, "total_steps": 61300, "loss": 0.3489, "lr": 2.8231042330700473e-05, "epoch": 5.128874388254486, "percentage": 51.29, "elapsed_time": "4:17:09", "remaining_time": "4:04:13", "throughput": 4398.01, "total_tokens": 67857152} {"current_steps": 31445, "total_steps": 61300, "loss": 0.3075, "lr": 2.822398391521125e-05, "epoch": 5.129690048939641, "percentage": 51.3, "elapsed_time": "4:17:11", "remaining_time": "4:04:10", "throughput": 4398.07, "total_tokens": 67867680} {"current_steps": 31450, "total_steps": 61300, "loss": 0.3165, "lr": 2.8216925238369518e-05, "epoch": 5.130505709624796, "percentage": 51.31, "elapsed_time": "4:17:13", "remaining_time": "4:04:08", "throughput": 4398.12, "total_tokens": 67877632} {"current_steps": 31455, "total_steps": 61300, "loss": 0.3771, "lr": 2.820986630074751e-05, "epoch": 5.131321370309951, "percentage": 51.31, "elapsed_time": "4:17:15", "remaining_time": "4:04:05", "throughput": 4398.17, "total_tokens": 67886912} {"current_steps": 31460, "total_steps": 61300, "loss": 0.3909, "lr": 2.8202807102917457e-05, "epoch": 5.132137030995106, "percentage": 51.32, "elapsed_time": "4:17:16", "remaining_time": "4:04:02", "throughput": 4398.21, "total_tokens": 67895040} {"current_steps": 31465, "total_steps": 61300, "loss": 0.3481, "lr": 2.8195747645451605e-05, "epoch": 5.132952691680261, "percentage": 51.33, "elapsed_time": "4:17:19", "remaining_time": "4:03:59", "throughput": 4398.27, "total_tokens": 67906336} {"current_steps": 31470, "total_steps": 61300, "loss": 0.334, "lr": 2.8188687928922237e-05, "epoch": 5.133768352365416, "percentage": 51.34, "elapsed_time": "4:17:21", "remaining_time": "4:03:56", "throughput": 4398.33, "total_tokens": 67916992} {"current_steps": 31475, "total_steps": 61300, "loss": 0.3314, "lr": 2.818162795390164e-05, "epoch": 5.134584013050571, "percentage": 51.35, "elapsed_time": "4:17:23", "remaining_time": "4:03:54", "throughput": 4398.4, "total_tokens": 67928352} {"current_steps": 31480, "total_steps": 61300, "loss": 0.3056, "lr": 2.817456772096214e-05, "epoch": 5.135399673735726, "percentage": 51.35, "elapsed_time": "4:17:26", "remaining_time": "4:03:51", "throughput": 4398.46, "total_tokens": 67940160} {"current_steps": 31485, "total_steps": 61300, "loss": 0.3339, "lr": 2.8167507230676077e-05, "epoch": 5.136215334420881, "percentage": 51.36, "elapsed_time": "4:17:28", "remaining_time": "4:03:49", "throughput": 4398.52, "total_tokens": 67950304} {"current_steps": 31490, "total_steps": 61300, "loss": 0.3339, "lr": 2.8160446483615804e-05, "epoch": 5.137030995106036, "percentage": 51.37, "elapsed_time": "4:17:30", "remaining_time": "4:03:46", "throughput": 4398.58, "total_tokens": 67960224} {"current_steps": 31495, "total_steps": 61300, "loss": 0.3538, "lr": 2.8153385480353705e-05, "epoch": 5.137846655791191, "percentage": 51.38, "elapsed_time": "4:17:32", "remaining_time": "4:03:43", "throughput": 4398.65, "total_tokens": 67971616} {"current_steps": 31500, "total_steps": 61300, "loss": 0.3672, "lr": 2.814632422146218e-05, "epoch": 5.138662316476346, "percentage": 51.39, "elapsed_time": "4:17:35", "remaining_time": "4:03:40", "throughput": 4398.7, "total_tokens": 67982048} {"current_steps": 31505, "total_steps": 61300, "loss": 0.3336, "lr": 2.8139262707513647e-05, "epoch": 5.1394779771615005, "percentage": 51.39, "elapsed_time": "4:17:36", "remaining_time": "4:03:38", "throughput": 4398.76, "total_tokens": 67991584} {"current_steps": 31510, "total_steps": 61300, "loss": 0.3409, "lr": 2.813220093908055e-05, "epoch": 5.140293637846656, "percentage": 51.4, "elapsed_time": "4:17:39", "remaining_time": "4:03:35", "throughput": 4398.81, "total_tokens": 68002208} {"current_steps": 31515, "total_steps": 61300, "loss": 0.3458, "lr": 2.812513891673535e-05, "epoch": 5.141109298531811, "percentage": 51.41, "elapsed_time": "4:17:41", "remaining_time": "4:03:32", "throughput": 4398.88, "total_tokens": 68013344} {"current_steps": 31520, "total_steps": 61300, "loss": 0.3507, "lr": 2.8118076641050535e-05, "epoch": 5.141924959216966, "percentage": 51.42, "elapsed_time": "4:17:43", "remaining_time": "4:03:30", "throughput": 4398.94, "total_tokens": 68025056} {"current_steps": 31525, "total_steps": 61300, "loss": 0.3092, "lr": 2.81110141125986e-05, "epoch": 5.142740619902121, "percentage": 51.43, "elapsed_time": "4:17:46", "remaining_time": "4:03:27", "throughput": 4399.0, "total_tokens": 68035296} {"current_steps": 31530, "total_steps": 61300, "loss": 0.3368, "lr": 2.8103951331952083e-05, "epoch": 5.143556280587275, "percentage": 51.44, "elapsed_time": "4:17:48", "remaining_time": "4:03:24", "throughput": 4399.06, "total_tokens": 68046080} {"current_steps": 31535, "total_steps": 61300, "loss": 0.3287, "lr": 2.8096888299683515e-05, "epoch": 5.14437194127243, "percentage": 51.44, "elapsed_time": "4:17:50", "remaining_time": "4:03:22", "throughput": 4399.12, "total_tokens": 68057344} {"current_steps": 31540, "total_steps": 61300, "loss": 0.3354, "lr": 2.8089825016365478e-05, "epoch": 5.145187601957586, "percentage": 51.45, "elapsed_time": "4:17:52", "remaining_time": "4:03:19", "throughput": 4399.18, "total_tokens": 68067488} {"current_steps": 31545, "total_steps": 61300, "loss": 0.3588, "lr": 2.808276148257054e-05, "epoch": 5.146003262642741, "percentage": 51.46, "elapsed_time": "4:17:55", "remaining_time": "4:03:17", "throughput": 4399.24, "total_tokens": 68079584} {"current_steps": 31550, "total_steps": 61300, "loss": 0.3236, "lr": 2.807569769887132e-05, "epoch": 5.146818923327896, "percentage": 51.47, "elapsed_time": "4:17:57", "remaining_time": "4:03:14", "throughput": 4399.31, "total_tokens": 68090816} {"current_steps": 31555, "total_steps": 61300, "loss": 0.3229, "lr": 2.8068633665840438e-05, "epoch": 5.14763458401305, "percentage": 51.48, "elapsed_time": "4:18:00", "remaining_time": "4:03:12", "throughput": 4399.38, "total_tokens": 68102592} {"current_steps": 31560, "total_steps": 61300, "loss": 0.2917, "lr": 2.806156938405054e-05, "epoch": 5.148450244698205, "percentage": 51.48, "elapsed_time": "4:18:02", "remaining_time": "4:03:09", "throughput": 4399.44, "total_tokens": 68113664} {"current_steps": 31565, "total_steps": 61300, "loss": 0.3162, "lr": 2.8054504854074293e-05, "epoch": 5.149265905383361, "percentage": 51.49, "elapsed_time": "4:18:04", "remaining_time": "4:03:06", "throughput": 4399.5, "total_tokens": 68124480} {"current_steps": 31570, "total_steps": 61300, "loss": 0.3745, "lr": 2.8047440076484383e-05, "epoch": 5.150081566068516, "percentage": 51.5, "elapsed_time": "4:18:06", "remaining_time": "4:03:04", "throughput": 4399.56, "total_tokens": 68135424} {"current_steps": 31575, "total_steps": 61300, "loss": 0.3494, "lr": 2.8040375051853522e-05, "epoch": 5.150897226753671, "percentage": 51.51, "elapsed_time": "4:18:09", "remaining_time": "4:03:01", "throughput": 4399.63, "total_tokens": 68146784} {"current_steps": 31580, "total_steps": 61300, "loss": 0.3249, "lr": 2.803330978075443e-05, "epoch": 5.151712887438825, "percentage": 51.52, "elapsed_time": "4:18:11", "remaining_time": "4:02:58", "throughput": 4399.69, "total_tokens": 68155744} {"current_steps": 31585, "total_steps": 61300, "loss": 0.3124, "lr": 2.802624426375985e-05, "epoch": 5.15252854812398, "percentage": 51.53, "elapsed_time": "4:18:13", "remaining_time": "4:02:56", "throughput": 4399.75, "total_tokens": 68167168} {"current_steps": 31590, "total_steps": 61300, "loss": 0.3312, "lr": 2.801917850144256e-05, "epoch": 5.153344208809135, "percentage": 51.53, "elapsed_time": "4:18:15", "remaining_time": "4:02:53", "throughput": 4399.82, "total_tokens": 68178496} {"current_steps": 31595, "total_steps": 61300, "loss": 0.3118, "lr": 2.8012112494375342e-05, "epoch": 5.154159869494291, "percentage": 51.54, "elapsed_time": "4:18:18", "remaining_time": "4:02:50", "throughput": 4399.88, "total_tokens": 68189568} {"current_steps": 31600, "total_steps": 61300, "loss": 0.289, "lr": 2.8005046243131005e-05, "epoch": 5.1549755301794455, "percentage": 51.55, "elapsed_time": "4:18:19", "remaining_time": "4:02:47", "throughput": 4399.93, "total_tokens": 68198624} {"current_steps": 31605, "total_steps": 61300, "loss": 0.3379, "lr": 2.7997979748282364e-05, "epoch": 5.1557911908646, "percentage": 51.56, "elapsed_time": "4:18:22", "remaining_time": "4:02:45", "throughput": 4399.98, "total_tokens": 68210528} {"current_steps": 31610, "total_steps": 61300, "loss": 0.2838, "lr": 2.7990913010402282e-05, "epoch": 5.156606851549755, "percentage": 51.57, "elapsed_time": "4:18:24", "remaining_time": "4:02:42", "throughput": 4400.03, "total_tokens": 68220384} {"current_steps": 31615, "total_steps": 61300, "loss": 0.3352, "lr": 2.798384603006361e-05, "epoch": 5.15742251223491, "percentage": 51.57, "elapsed_time": "4:18:26", "remaining_time": "4:02:39", "throughput": 4400.09, "total_tokens": 68230464} {"current_steps": 31620, "total_steps": 61300, "loss": 0.2977, "lr": 2.7976778807839245e-05, "epoch": 5.158238172920065, "percentage": 51.58, "elapsed_time": "4:18:28", "remaining_time": "4:02:37", "throughput": 4400.14, "total_tokens": 68240384} {"current_steps": 31625, "total_steps": 61300, "loss": 0.3473, "lr": 2.796971134430208e-05, "epoch": 5.1590538336052205, "percentage": 51.59, "elapsed_time": "4:18:31", "remaining_time": "4:02:34", "throughput": 4400.21, "total_tokens": 68251840} {"current_steps": 31630, "total_steps": 61300, "loss": 0.3472, "lr": 2.7962643640025044e-05, "epoch": 5.159869494290375, "percentage": 51.6, "elapsed_time": "4:18:33", "remaining_time": "4:02:32", "throughput": 4400.28, "total_tokens": 68263008} {"current_steps": 31635, "total_steps": 61300, "loss": 0.3955, "lr": 2.7955575695581083e-05, "epoch": 5.16068515497553, "percentage": 51.61, "elapsed_time": "4:18:35", "remaining_time": "4:02:29", "throughput": 4400.35, "total_tokens": 68273920} {"current_steps": 31640, "total_steps": 61300, "loss": 0.332, "lr": 2.794850751154316e-05, "epoch": 5.161500815660685, "percentage": 51.62, "elapsed_time": "4:18:37", "remaining_time": "4:02:26", "throughput": 4400.4, "total_tokens": 68284256} {"current_steps": 31645, "total_steps": 61300, "loss": 0.3575, "lr": 2.794143908848426e-05, "epoch": 5.16231647634584, "percentage": 51.62, "elapsed_time": "4:18:40", "remaining_time": "4:02:24", "throughput": 4400.47, "total_tokens": 68296000} {"current_steps": 31650, "total_steps": 61300, "loss": 0.3025, "lr": 2.7934370426977385e-05, "epoch": 5.1631321370309955, "percentage": 51.63, "elapsed_time": "4:18:42", "remaining_time": "4:02:21", "throughput": 4400.54, "total_tokens": 68308224} {"current_steps": 31655, "total_steps": 61300, "loss": 0.3316, "lr": 2.792730152759555e-05, "epoch": 5.16394779771615, "percentage": 51.64, "elapsed_time": "4:18:44", "remaining_time": "4:02:19", "throughput": 4400.6, "total_tokens": 68318560} {"current_steps": 31660, "total_steps": 61300, "loss": 0.3353, "lr": 2.7920232390911805e-05, "epoch": 5.164763458401305, "percentage": 51.65, "elapsed_time": "4:18:46", "remaining_time": "4:02:16", "throughput": 4400.66, "total_tokens": 68328256} {"current_steps": 31665, "total_steps": 61300, "loss": 0.3334, "lr": 2.79131630174992e-05, "epoch": 5.16557911908646, "percentage": 51.66, "elapsed_time": "4:18:49", "remaining_time": "4:02:13", "throughput": 4400.73, "total_tokens": 68339648} {"current_steps": 31670, "total_steps": 61300, "loss": 0.3288, "lr": 2.790609340793082e-05, "epoch": 5.166394779771615, "percentage": 51.66, "elapsed_time": "4:18:51", "remaining_time": "4:02:11", "throughput": 4400.8, "total_tokens": 68351072} {"current_steps": 31675, "total_steps": 61300, "loss": 0.3507, "lr": 2.789902356277977e-05, "epoch": 5.16721044045677, "percentage": 51.67, "elapsed_time": "4:18:53", "remaining_time": "4:02:08", "throughput": 4400.85, "total_tokens": 68360832} {"current_steps": 31680, "total_steps": 61300, "loss": 0.3562, "lr": 2.7891953482619148e-05, "epoch": 5.168026101141925, "percentage": 51.68, "elapsed_time": "4:18:55", "remaining_time": "4:02:05", "throughput": 4400.9, "total_tokens": 68370016} {"current_steps": 31685, "total_steps": 61300, "loss": 0.341, "lr": 2.788488316802211e-05, "epoch": 5.16884176182708, "percentage": 51.69, "elapsed_time": "4:18:57", "remaining_time": "4:02:02", "throughput": 4400.96, "total_tokens": 68380768} {"current_steps": 31690, "total_steps": 61300, "loss": 0.3426, "lr": 2.78778126195618e-05, "epoch": 5.169657422512235, "percentage": 51.7, "elapsed_time": "4:19:00", "remaining_time": "4:02:00", "throughput": 4401.03, "total_tokens": 68392448} {"current_steps": 31695, "total_steps": 61300, "loss": 0.3372, "lr": 2.7870741837811404e-05, "epoch": 5.17047308319739, "percentage": 51.7, "elapsed_time": "4:19:02", "remaining_time": "4:01:57", "throughput": 4401.07, "total_tokens": 68402016} {"current_steps": 31700, "total_steps": 61300, "loss": 0.3207, "lr": 2.7863670823344106e-05, "epoch": 5.171288743882545, "percentage": 51.71, "elapsed_time": "4:19:04", "remaining_time": "4:01:54", "throughput": 4401.13, "total_tokens": 68412704} {"current_steps": 31705, "total_steps": 61300, "loss": 0.3218, "lr": 2.7856599576733124e-05, "epoch": 5.1721044045677, "percentage": 51.72, "elapsed_time": "4:19:06", "remaining_time": "4:01:52", "throughput": 4401.2, "total_tokens": 68424448} {"current_steps": 31710, "total_steps": 61300, "loss": 0.3414, "lr": 2.7849528098551682e-05, "epoch": 5.172920065252855, "percentage": 51.73, "elapsed_time": "4:19:08", "remaining_time": "4:01:49", "throughput": 4401.27, "total_tokens": 68435168} {"current_steps": 31715, "total_steps": 61300, "loss": 0.3475, "lr": 2.7842456389373032e-05, "epoch": 5.17373572593801, "percentage": 51.74, "elapsed_time": "4:19:11", "remaining_time": "4:01:46", "throughput": 4401.33, "total_tokens": 68445696} {"current_steps": 31720, "total_steps": 61300, "loss": 0.3869, "lr": 2.783538444977045e-05, "epoch": 5.174551386623165, "percentage": 51.75, "elapsed_time": "4:19:13", "remaining_time": "4:01:43", "throughput": 4401.38, "total_tokens": 68455936} {"current_steps": 31725, "total_steps": 61300, "loss": 0.3196, "lr": 2.7828312280317214e-05, "epoch": 5.1753670473083195, "percentage": 51.75, "elapsed_time": "4:19:15", "remaining_time": "4:01:41", "throughput": 4401.44, "total_tokens": 68465344} {"current_steps": 31730, "total_steps": 61300, "loss": 0.3464, "lr": 2.782123988158664e-05, "epoch": 5.176182707993474, "percentage": 51.76, "elapsed_time": "4:19:17", "remaining_time": "4:01:38", "throughput": 4401.5, "total_tokens": 68475936} {"current_steps": 31735, "total_steps": 61300, "loss": 0.3571, "lr": 2.781416725415204e-05, "epoch": 5.17699836867863, "percentage": 51.77, "elapsed_time": "4:19:19", "remaining_time": "4:01:35", "throughput": 4401.57, "total_tokens": 68486496} {"current_steps": 31740, "total_steps": 61300, "loss": 0.3371, "lr": 2.780709439858677e-05, "epoch": 5.177814029363785, "percentage": 51.78, "elapsed_time": "4:19:21", "remaining_time": "4:01:33", "throughput": 4401.63, "total_tokens": 68497408} {"current_steps": 31745, "total_steps": 61300, "loss": 0.37, "lr": 2.7800021315464176e-05, "epoch": 5.17862969004894, "percentage": 51.79, "elapsed_time": "4:19:23", "remaining_time": "4:01:30", "throughput": 4401.67, "total_tokens": 68506720} {"current_steps": 31750, "total_steps": 61300, "loss": 0.3328, "lr": 2.779294800535765e-05, "epoch": 5.1794453507340945, "percentage": 51.79, "elapsed_time": "4:19:25", "remaining_time": "4:01:27", "throughput": 4401.72, "total_tokens": 68516800} {"current_steps": 31755, "total_steps": 61300, "loss": 0.3398, "lr": 2.778587446884059e-05, "epoch": 5.180261011419249, "percentage": 51.8, "elapsed_time": "4:19:27", "remaining_time": "4:01:24", "throughput": 4401.77, "total_tokens": 68525120} {"current_steps": 31760, "total_steps": 61300, "loss": 0.3695, "lr": 2.777880070648641e-05, "epoch": 5.181076672104404, "percentage": 51.81, "elapsed_time": "4:19:29", "remaining_time": "4:01:21", "throughput": 4401.81, "total_tokens": 68535872} {"current_steps": 31765, "total_steps": 61300, "loss": 0.3585, "lr": 2.777172671886854e-05, "epoch": 5.18189233278956, "percentage": 51.82, "elapsed_time": "4:19:31", "remaining_time": "4:01:18", "throughput": 4401.87, "total_tokens": 68545760} {"current_steps": 31770, "total_steps": 61300, "loss": 0.3134, "lr": 2.776465250656044e-05, "epoch": 5.182707993474715, "percentage": 51.83, "elapsed_time": "4:19:34", "remaining_time": "4:01:15", "throughput": 4401.92, "total_tokens": 68555552} {"current_steps": 31775, "total_steps": 61300, "loss": 0.3641, "lr": 2.7757578070135588e-05, "epoch": 5.1835236541598695, "percentage": 51.84, "elapsed_time": "4:19:36", "remaining_time": "4:01:13", "throughput": 4401.97, "total_tokens": 68565760} {"current_steps": 31780, "total_steps": 61300, "loss": 0.3003, "lr": 2.775050341016746e-05, "epoch": 5.184339314845024, "percentage": 51.84, "elapsed_time": "4:19:38", "remaining_time": "4:01:10", "throughput": 4402.02, "total_tokens": 68576160} {"current_steps": 31785, "total_steps": 61300, "loss": 0.3349, "lr": 2.774342852722957e-05, "epoch": 5.185154975530179, "percentage": 51.85, "elapsed_time": "4:19:40", "remaining_time": "4:01:07", "throughput": 4402.08, "total_tokens": 68587360} {"current_steps": 31790, "total_steps": 61300, "loss": 0.3398, "lr": 2.7736353421895445e-05, "epoch": 5.185970636215335, "percentage": 51.86, "elapsed_time": "4:19:42", "remaining_time": "4:01:05", "throughput": 4402.14, "total_tokens": 68598336} {"current_steps": 31795, "total_steps": 61300, "loss": 0.3305, "lr": 2.772927809473862e-05, "epoch": 5.18678629690049, "percentage": 51.87, "elapsed_time": "4:19:45", "remaining_time": "4:01:02", "throughput": 4402.22, "total_tokens": 68610560} {"current_steps": 31800, "total_steps": 61300, "loss": 0.3256, "lr": 2.7722202546332676e-05, "epoch": 5.1876019575856445, "percentage": 51.88, "elapsed_time": "4:19:47", "remaining_time": "4:01:00", "throughput": 4402.29, "total_tokens": 68621472} {"current_steps": 31805, "total_steps": 61300, "loss": 0.3217, "lr": 2.7715126777251177e-05, "epoch": 5.188417618270799, "percentage": 51.88, "elapsed_time": "4:19:49", "remaining_time": "4:00:57", "throughput": 4402.34, "total_tokens": 68632064} {"current_steps": 31810, "total_steps": 61300, "loss": 0.3055, "lr": 2.7708050788067724e-05, "epoch": 5.189233278955954, "percentage": 51.89, "elapsed_time": "4:19:52", "remaining_time": "4:00:54", "throughput": 4402.39, "total_tokens": 68642784} {"current_steps": 31815, "total_steps": 61300, "loss": 0.3108, "lr": 2.7700974579355933e-05, "epoch": 5.190048939641109, "percentage": 51.9, "elapsed_time": "4:19:54", "remaining_time": "4:00:52", "throughput": 4402.44, "total_tokens": 68652448} {"current_steps": 31820, "total_steps": 61300, "loss": 0.3126, "lr": 2.769389815168944e-05, "epoch": 5.190864600326265, "percentage": 51.91, "elapsed_time": "4:19:56", "remaining_time": "4:00:49", "throughput": 4402.49, "total_tokens": 68662656} {"current_steps": 31825, "total_steps": 61300, "loss": 0.3551, "lr": 2.7686821505641893e-05, "epoch": 5.191680261011419, "percentage": 51.92, "elapsed_time": "4:19:58", "remaining_time": "4:00:46", "throughput": 4402.56, "total_tokens": 68673248} {"current_steps": 31830, "total_steps": 61300, "loss": 0.3342, "lr": 2.7679744641786963e-05, "epoch": 5.192495921696574, "percentage": 51.92, "elapsed_time": "4:20:00", "remaining_time": "4:00:43", "throughput": 4402.61, "total_tokens": 68683776} {"current_steps": 31835, "total_steps": 61300, "loss": 0.3591, "lr": 2.7672667560698328e-05, "epoch": 5.193311582381729, "percentage": 51.93, "elapsed_time": "4:20:02", "remaining_time": "4:00:41", "throughput": 4402.67, "total_tokens": 68694112} {"current_steps": 31840, "total_steps": 61300, "loss": 0.3429, "lr": 2.7665590262949707e-05, "epoch": 5.194127243066884, "percentage": 51.94, "elapsed_time": "4:20:04", "remaining_time": "4:00:38", "throughput": 4402.73, "total_tokens": 68704512} {"current_steps": 31845, "total_steps": 61300, "loss": 0.3131, "lr": 2.7658512749114816e-05, "epoch": 5.19494290375204, "percentage": 51.95, "elapsed_time": "4:20:07", "remaining_time": "4:00:35", "throughput": 4402.8, "total_tokens": 68715776} {"current_steps": 31850, "total_steps": 61300, "loss": 0.3318, "lr": 2.7651435019767384e-05, "epoch": 5.195758564437194, "percentage": 51.96, "elapsed_time": "4:20:09", "remaining_time": "4:00:33", "throughput": 4402.86, "total_tokens": 68725888} {"current_steps": 31855, "total_steps": 61300, "loss": 0.2863, "lr": 2.764435707548118e-05, "epoch": 5.196574225122349, "percentage": 51.97, "elapsed_time": "4:20:11", "remaining_time": "4:00:30", "throughput": 4402.92, "total_tokens": 68736864} {"current_steps": 31860, "total_steps": 61300, "loss": 0.3784, "lr": 2.7637278916829977e-05, "epoch": 5.197389885807504, "percentage": 51.97, "elapsed_time": "4:20:13", "remaining_time": "4:00:27", "throughput": 4402.98, "total_tokens": 68747264} {"current_steps": 31865, "total_steps": 61300, "loss": 0.3884, "lr": 2.7630200544387562e-05, "epoch": 5.198205546492659, "percentage": 51.98, "elapsed_time": "4:20:15", "remaining_time": "4:00:25", "throughput": 4403.04, "total_tokens": 68757792} {"current_steps": 31870, "total_steps": 61300, "loss": 0.3431, "lr": 2.762312195872775e-05, "epoch": 5.199021207177814, "percentage": 51.99, "elapsed_time": "4:20:18", "remaining_time": "4:00:22", "throughput": 4403.11, "total_tokens": 68769440} {"current_steps": 31875, "total_steps": 61300, "loss": 0.3123, "lr": 2.761604316042436e-05, "epoch": 5.199836867862969, "percentage": 52.0, "elapsed_time": "4:20:20", "remaining_time": "4:00:19", "throughput": 4403.16, "total_tokens": 68780224} {"current_steps": 31880, "total_steps": 61300, "loss": 0.321, "lr": 2.760896415005123e-05, "epoch": 5.200652528548124, "percentage": 52.01, "elapsed_time": "4:20:22", "remaining_time": "4:00:17", "throughput": 4403.22, "total_tokens": 68791008} {"current_steps": 31885, "total_steps": 61300, "loss": 0.3733, "lr": 2.7601884928182238e-05, "epoch": 5.201468189233279, "percentage": 52.01, "elapsed_time": "4:20:25", "remaining_time": "4:00:14", "throughput": 4403.27, "total_tokens": 68801088} {"current_steps": 31890, "total_steps": 61300, "loss": 0.326, "lr": 2.759480549539125e-05, "epoch": 5.202283849918434, "percentage": 52.02, "elapsed_time": "4:20:27", "remaining_time": "4:00:12", "throughput": 4403.31, "total_tokens": 68812128} {"current_steps": 31895, "total_steps": 61300, "loss": 0.3519, "lr": 2.758772585225216e-05, "epoch": 5.203099510603589, "percentage": 52.03, "elapsed_time": "4:20:29", "remaining_time": "4:00:09", "throughput": 4403.36, "total_tokens": 68822688} {"current_steps": 31900, "total_steps": 61300, "loss": 0.3618, "lr": 2.7580645999338885e-05, "epoch": 5.2039151712887435, "percentage": 52.04, "elapsed_time": "4:20:31", "remaining_time": "4:00:06", "throughput": 4403.42, "total_tokens": 68832896} {"current_steps": 31905, "total_steps": 61300, "loss": 0.3164, "lr": 2.757356593722534e-05, "epoch": 5.204730831973899, "percentage": 52.05, "elapsed_time": "4:20:34", "remaining_time": "4:00:04", "throughput": 4403.49, "total_tokens": 68844224} {"current_steps": 31910, "total_steps": 61300, "loss": 0.3654, "lr": 2.7566485666485496e-05, "epoch": 5.205546492659054, "percentage": 52.06, "elapsed_time": "4:20:36", "remaining_time": "4:00:01", "throughput": 4403.57, "total_tokens": 68856512} {"current_steps": 31915, "total_steps": 61300, "loss": 0.3433, "lr": 2.75594051876933e-05, "epoch": 5.206362153344209, "percentage": 52.06, "elapsed_time": "4:20:38", "remaining_time": "3:59:59", "throughput": 4403.62, "total_tokens": 68867552} {"current_steps": 31920, "total_steps": 61300, "loss": 0.358, "lr": 2.755232450142272e-05, "epoch": 5.207177814029364, "percentage": 52.07, "elapsed_time": "4:20:40", "remaining_time": "3:59:56", "throughput": 4403.68, "total_tokens": 68877536} {"current_steps": 31925, "total_steps": 61300, "loss": 0.3491, "lr": 2.754524360824778e-05, "epoch": 5.2079934747145185, "percentage": 52.08, "elapsed_time": "4:20:42", "remaining_time": "3:59:53", "throughput": 4403.73, "total_tokens": 68887360} {"current_steps": 31930, "total_steps": 61300, "loss": 0.34, "lr": 2.7538162508742472e-05, "epoch": 5.208809135399674, "percentage": 52.09, "elapsed_time": "4:20:45", "remaining_time": "3:59:51", "throughput": 4403.81, "total_tokens": 68899328} {"current_steps": 31935, "total_steps": 61300, "loss": 0.3486, "lr": 2.7531081203480834e-05, "epoch": 5.209624796084829, "percentage": 52.1, "elapsed_time": "4:20:47", "remaining_time": "3:59:48", "throughput": 4403.87, "total_tokens": 68909888} {"current_steps": 31940, "total_steps": 61300, "loss": 0.3429, "lr": 2.7523999693036916e-05, "epoch": 5.210440456769984, "percentage": 52.1, "elapsed_time": "4:20:49", "remaining_time": "3:59:45", "throughput": 4403.93, "total_tokens": 68920416} {"current_steps": 31945, "total_steps": 61300, "loss": 0.3502, "lr": 2.7516917977984773e-05, "epoch": 5.211256117455139, "percentage": 52.11, "elapsed_time": "4:20:52", "remaining_time": "3:59:43", "throughput": 4403.99, "total_tokens": 68931936} {"current_steps": 31950, "total_steps": 61300, "loss": 0.3716, "lr": 2.7509836058898487e-05, "epoch": 5.212071778140293, "percentage": 52.12, "elapsed_time": "4:20:54", "remaining_time": "3:59:40", "throughput": 4404.05, "total_tokens": 68942912} {"current_steps": 31955, "total_steps": 61300, "loss": 0.3697, "lr": 2.750275393635215e-05, "epoch": 5.212887438825448, "percentage": 52.13, "elapsed_time": "4:20:56", "remaining_time": "3:59:38", "throughput": 4404.11, "total_tokens": 68954400} {"current_steps": 31960, "total_steps": 61300, "loss": 0.324, "lr": 2.7495671610919886e-05, "epoch": 5.213703099510604, "percentage": 52.14, "elapsed_time": "4:20:58", "remaining_time": "3:59:35", "throughput": 4404.15, "total_tokens": 68964032} {"current_steps": 31965, "total_steps": 61300, "loss": 0.3098, "lr": 2.748858908317582e-05, "epoch": 5.214518760195759, "percentage": 52.15, "elapsed_time": "4:21:01", "remaining_time": "3:59:32", "throughput": 4404.21, "total_tokens": 68974944} {"current_steps": 31970, "total_steps": 61300, "loss": 0.3501, "lr": 2.7481506353694092e-05, "epoch": 5.215334420880914, "percentage": 52.15, "elapsed_time": "4:21:03", "remaining_time": "3:59:29", "throughput": 4404.28, "total_tokens": 68985856} {"current_steps": 31975, "total_steps": 61300, "loss": 0.3667, "lr": 2.7474423423048873e-05, "epoch": 5.216150081566068, "percentage": 52.16, "elapsed_time": "4:21:05", "remaining_time": "3:59:27", "throughput": 4404.34, "total_tokens": 68996768} {"current_steps": 31980, "total_steps": 61300, "loss": 0.3162, "lr": 2.746734029181433e-05, "epoch": 5.216965742251223, "percentage": 52.17, "elapsed_time": "4:21:07", "remaining_time": "3:59:24", "throughput": 4404.41, "total_tokens": 69008064} {"current_steps": 31985, "total_steps": 61300, "loss": 0.3508, "lr": 2.7460256960564668e-05, "epoch": 5.217781402936378, "percentage": 52.18, "elapsed_time": "4:21:10", "remaining_time": "3:59:22", "throughput": 4404.46, "total_tokens": 69018240} {"current_steps": 31990, "total_steps": 61300, "loss": 0.3532, "lr": 2.7453173429874096e-05, "epoch": 5.218597063621534, "percentage": 52.19, "elapsed_time": "4:21:12", "remaining_time": "3:59:19", "throughput": 4404.51, "total_tokens": 69028128} {"current_steps": 31995, "total_steps": 61300, "loss": 0.3291, "lr": 2.744608970031683e-05, "epoch": 5.219412724306689, "percentage": 52.19, "elapsed_time": "4:21:14", "remaining_time": "3:59:16", "throughput": 4404.56, "total_tokens": 69038720} {"current_steps": 32000, "total_steps": 61300, "loss": 0.3454, "lr": 2.7439005772467126e-05, "epoch": 5.220228384991843, "percentage": 52.2, "elapsed_time": "4:21:16", "remaining_time": "3:59:14", "throughput": 4404.63, "total_tokens": 69050368} {"current_steps": 32005, "total_steps": 61300, "loss": 0.3293, "lr": 2.743192164689924e-05, "epoch": 5.221044045676998, "percentage": 52.21, "elapsed_time": "4:21:18", "remaining_time": "3:59:11", "throughput": 4404.69, "total_tokens": 69060672} {"current_steps": 32010, "total_steps": 61300, "loss": 0.3211, "lr": 2.742483732418744e-05, "epoch": 5.221859706362153, "percentage": 52.22, "elapsed_time": "4:21:21", "remaining_time": "3:59:08", "throughput": 4404.76, "total_tokens": 69072480} {"current_steps": 32015, "total_steps": 61300, "loss": 0.3331, "lr": 2.7417752804906027e-05, "epoch": 5.222675367047309, "percentage": 52.23, "elapsed_time": "4:21:23", "remaining_time": "3:59:06", "throughput": 4404.81, "total_tokens": 69083232} {"current_steps": 32020, "total_steps": 61300, "loss": 0.3242, "lr": 2.7410668089629304e-05, "epoch": 5.2234910277324635, "percentage": 52.23, "elapsed_time": "4:21:26", "remaining_time": "3:59:03", "throughput": 4404.86, "total_tokens": 69094912} {"current_steps": 32025, "total_steps": 61300, "loss": 0.3475, "lr": 2.7403583178931597e-05, "epoch": 5.224306688417618, "percentage": 52.24, "elapsed_time": "4:21:28", "remaining_time": "3:59:01", "throughput": 4404.92, "total_tokens": 69106432} {"current_steps": 32030, "total_steps": 61300, "loss": 0.3213, "lr": 2.7396498073387245e-05, "epoch": 5.225122349102773, "percentage": 52.25, "elapsed_time": "4:21:30", "remaining_time": "3:58:58", "throughput": 4404.98, "total_tokens": 69117184} {"current_steps": 32035, "total_steps": 61300, "loss": 0.3402, "lr": 2.7389412773570595e-05, "epoch": 5.225938009787928, "percentage": 52.26, "elapsed_time": "4:21:32", "remaining_time": "3:58:55", "throughput": 4405.03, "total_tokens": 69127520} {"current_steps": 32040, "total_steps": 61300, "loss": 0.3435, "lr": 2.738232728005602e-05, "epoch": 5.226753670473083, "percentage": 52.27, "elapsed_time": "4:21:35", "remaining_time": "3:58:53", "throughput": 4405.1, "total_tokens": 69139104} {"current_steps": 32045, "total_steps": 61300, "loss": 0.3461, "lr": 2.737524159341791e-05, "epoch": 5.2275693311582385, "percentage": 52.28, "elapsed_time": "4:21:37", "remaining_time": "3:58:50", "throughput": 4405.15, "total_tokens": 69149312} {"current_steps": 32050, "total_steps": 61300, "loss": 0.3083, "lr": 2.7368155714230663e-05, "epoch": 5.228384991843393, "percentage": 52.28, "elapsed_time": "4:21:39", "remaining_time": "3:58:48", "throughput": 4405.21, "total_tokens": 69160576} {"current_steps": 32055, "total_steps": 61300, "loss": 0.3193, "lr": 2.7361069643068698e-05, "epoch": 5.229200652528548, "percentage": 52.29, "elapsed_time": "4:21:41", "remaining_time": "3:58:45", "throughput": 4405.27, "total_tokens": 69171360} {"current_steps": 32060, "total_steps": 61300, "loss": 0.327, "lr": 2.7353983380506444e-05, "epoch": 5.230016313213703, "percentage": 52.3, "elapsed_time": "4:21:44", "remaining_time": "3:58:43", "throughput": 4405.34, "total_tokens": 69183360} {"current_steps": 32065, "total_steps": 61300, "loss": 0.3136, "lr": 2.734689692711836e-05, "epoch": 5.230831973898858, "percentage": 52.31, "elapsed_time": "4:21:46", "remaining_time": "3:58:40", "throughput": 4405.41, "total_tokens": 69195392} {"current_steps": 32070, "total_steps": 61300, "loss": 0.3012, "lr": 2.73398102834789e-05, "epoch": 5.231647634584013, "percentage": 52.32, "elapsed_time": "4:21:49", "remaining_time": "3:58:38", "throughput": 4405.46, "total_tokens": 69206816} {"current_steps": 32075, "total_steps": 61300, "loss": 0.3421, "lr": 2.7332723450162544e-05, "epoch": 5.232463295269168, "percentage": 52.32, "elapsed_time": "4:21:51", "remaining_time": "3:58:35", "throughput": 4405.51, "total_tokens": 69217248} {"current_steps": 32080, "total_steps": 61300, "loss": 0.33, "lr": 2.7325636427743788e-05, "epoch": 5.233278955954323, "percentage": 52.33, "elapsed_time": "4:21:53", "remaining_time": "3:58:32", "throughput": 4405.57, "total_tokens": 69228480} {"current_steps": 32085, "total_steps": 61300, "loss": 0.3461, "lr": 2.731854921679715e-05, "epoch": 5.234094616639478, "percentage": 52.34, "elapsed_time": "4:21:56", "remaining_time": "3:58:30", "throughput": 4405.66, "total_tokens": 69240832} {"current_steps": 32090, "total_steps": 61300, "loss": 0.3695, "lr": 2.7311461817897143e-05, "epoch": 5.234910277324633, "percentage": 52.35, "elapsed_time": "4:21:58", "remaining_time": "3:58:27", "throughput": 4405.7, "total_tokens": 69250976} {"current_steps": 32095, "total_steps": 61300, "loss": 0.3419, "lr": 2.7304374231618318e-05, "epoch": 5.235725938009788, "percentage": 52.36, "elapsed_time": "4:22:00", "remaining_time": "3:58:25", "throughput": 4405.76, "total_tokens": 69261184} {"current_steps": 32100, "total_steps": 61300, "loss": 0.3562, "lr": 2.729728645853522e-05, "epoch": 5.236541598694943, "percentage": 52.37, "elapsed_time": "4:22:03", "remaining_time": "3:58:22", "throughput": 4405.82, "total_tokens": 69273024} {"current_steps": 32105, "total_steps": 61300, "loss": 0.3116, "lr": 2.729019849922243e-05, "epoch": 5.237357259380098, "percentage": 52.37, "elapsed_time": "4:22:05", "remaining_time": "3:58:20", "throughput": 4405.9, "total_tokens": 69285280} {"current_steps": 32110, "total_steps": 61300, "loss": 0.3346, "lr": 2.7283110354254526e-05, "epoch": 5.238172920065253, "percentage": 52.38, "elapsed_time": "4:22:07", "remaining_time": "3:58:17", "throughput": 4405.94, "total_tokens": 69295680} {"current_steps": 32115, "total_steps": 61300, "loss": 0.3523, "lr": 2.727602202420611e-05, "epoch": 5.238988580750408, "percentage": 52.39, "elapsed_time": "4:22:09", "remaining_time": "3:58:14", "throughput": 4406.0, "total_tokens": 69305888} {"current_steps": 32120, "total_steps": 61300, "loss": 0.3431, "lr": 2.7268933509651806e-05, "epoch": 5.239804241435563, "percentage": 52.4, "elapsed_time": "4:22:12", "remaining_time": "3:58:12", "throughput": 4406.07, "total_tokens": 69317856} {"current_steps": 32125, "total_steps": 61300, "loss": 0.3565, "lr": 2.7261844811166236e-05, "epoch": 5.240619902120717, "percentage": 52.41, "elapsed_time": "4:22:14", "remaining_time": "3:58:09", "throughput": 4406.13, "total_tokens": 69329088} {"current_steps": 32130, "total_steps": 61300, "loss": 0.3672, "lr": 2.725475592932405e-05, "epoch": 5.241435562805873, "percentage": 52.41, "elapsed_time": "4:22:17", "remaining_time": "3:58:07", "throughput": 4406.19, "total_tokens": 69340544} {"current_steps": 32135, "total_steps": 61300, "loss": 0.3456, "lr": 2.724766686469991e-05, "epoch": 5.242251223491028, "percentage": 52.42, "elapsed_time": "4:22:19", "remaining_time": "3:58:04", "throughput": 4406.25, "total_tokens": 69351104} {"current_steps": 32140, "total_steps": 61300, "loss": 0.3804, "lr": 2.724057761786849e-05, "epoch": 5.243066884176183, "percentage": 52.43, "elapsed_time": "4:22:21", "remaining_time": "3:58:02", "throughput": 4406.31, "total_tokens": 69362848} {"current_steps": 32145, "total_steps": 61300, "loss": 0.3495, "lr": 2.7233488189404478e-05, "epoch": 5.2438825448613375, "percentage": 52.44, "elapsed_time": "4:22:23", "remaining_time": "3:57:59", "throughput": 4406.36, "total_tokens": 69373504} {"current_steps": 32150, "total_steps": 61300, "loss": 0.3523, "lr": 2.7226398579882573e-05, "epoch": 5.244698205546492, "percentage": 52.45, "elapsed_time": "4:22:26", "remaining_time": "3:57:56", "throughput": 4406.42, "total_tokens": 69384256} {"current_steps": 32155, "total_steps": 61300, "loss": 0.3714, "lr": 2.7219308789877513e-05, "epoch": 5.245513866231648, "percentage": 52.46, "elapsed_time": "4:22:28", "remaining_time": "3:57:54", "throughput": 4406.47, "total_tokens": 69394880} {"current_steps": 32160, "total_steps": 61300, "loss": 0.3309, "lr": 2.7212218819964013e-05, "epoch": 5.246329526916803, "percentage": 52.46, "elapsed_time": "4:22:30", "remaining_time": "3:57:51", "throughput": 4406.52, "total_tokens": 69405120} {"current_steps": 32165, "total_steps": 61300, "loss": 0.319, "lr": 2.720512867071684e-05, "epoch": 5.247145187601958, "percentage": 52.47, "elapsed_time": "4:22:32", "remaining_time": "3:57:48", "throughput": 4406.59, "total_tokens": 69416640} {"current_steps": 32170, "total_steps": 61300, "loss": 0.3507, "lr": 2.719803834271074e-05, "epoch": 5.2479608482871125, "percentage": 52.48, "elapsed_time": "4:22:35", "remaining_time": "3:57:46", "throughput": 4406.65, "total_tokens": 69426912} {"current_steps": 32175, "total_steps": 61300, "loss": 0.3424, "lr": 2.7190947836520502e-05, "epoch": 5.248776508972267, "percentage": 52.49, "elapsed_time": "4:22:37", "remaining_time": "3:57:43", "throughput": 4406.7, "total_tokens": 69436512} {"current_steps": 32180, "total_steps": 61300, "loss": 0.3477, "lr": 2.718385715272092e-05, "epoch": 5.249592169657422, "percentage": 52.5, "elapsed_time": "4:22:39", "remaining_time": "3:57:40", "throughput": 4406.77, "total_tokens": 69447424} {"current_steps": 32185, "total_steps": 61300, "loss": 0.3206, "lr": 2.7176766291886792e-05, "epoch": 5.250407830342578, "percentage": 52.5, "elapsed_time": "4:22:41", "remaining_time": "3:57:38", "throughput": 4406.84, "total_tokens": 69459136} {"current_steps": 32190, "total_steps": 61300, "loss": 0.3948, "lr": 2.7169675254592947e-05, "epoch": 5.251223491027733, "percentage": 52.51, "elapsed_time": "4:22:43", "remaining_time": "3:57:35", "throughput": 4406.88, "total_tokens": 69470048} {"current_steps": 32195, "total_steps": 61300, "loss": 0.3789, "lr": 2.716258404141421e-05, "epoch": 5.2520391517128875, "percentage": 52.52, "elapsed_time": "4:22:46", "remaining_time": "3:57:33", "throughput": 4406.95, "total_tokens": 69480992} {"current_steps": 32200, "total_steps": 61300, "loss": 0.3537, "lr": 2.7155492652925446e-05, "epoch": 5.252854812398042, "percentage": 52.53, "elapsed_time": "4:22:48", "remaining_time": "3:57:30", "throughput": 4407.01, "total_tokens": 69491936} {"current_steps": 32205, "total_steps": 61300, "loss": 0.3107, "lr": 2.714840108970151e-05, "epoch": 5.253670473083197, "percentage": 52.54, "elapsed_time": "4:22:50", "remaining_time": "3:57:27", "throughput": 4407.06, "total_tokens": 69500896} {"current_steps": 32210, "total_steps": 61300, "loss": 0.3349, "lr": 2.7141309352317278e-05, "epoch": 5.254486133768353, "percentage": 52.54, "elapsed_time": "4:22:52", "remaining_time": "3:57:24", "throughput": 4407.11, "total_tokens": 69509888} {"current_steps": 32215, "total_steps": 61300, "loss": 0.3278, "lr": 2.7134217441347647e-05, "epoch": 5.255301794453508, "percentage": 52.55, "elapsed_time": "4:22:54", "remaining_time": "3:57:21", "throughput": 4407.15, "total_tokens": 69519840} {"current_steps": 32220, "total_steps": 61300, "loss": 0.3903, "lr": 2.7127125357367515e-05, "epoch": 5.2561174551386625, "percentage": 52.56, "elapsed_time": "4:22:56", "remaining_time": "3:57:19", "throughput": 4407.2, "total_tokens": 69530400} {"current_steps": 32225, "total_steps": 61300, "loss": 0.3623, "lr": 2.7120033100951814e-05, "epoch": 5.256933115823817, "percentage": 52.57, "elapsed_time": "4:22:58", "remaining_time": "3:57:16", "throughput": 4407.25, "total_tokens": 69540992} {"current_steps": 32230, "total_steps": 61300, "loss": 0.3355, "lr": 2.7112940672675473e-05, "epoch": 5.257748776508972, "percentage": 52.58, "elapsed_time": "4:23:01", "remaining_time": "3:57:13", "throughput": 4407.32, "total_tokens": 69552704} {"current_steps": 32235, "total_steps": 61300, "loss": 0.3155, "lr": 2.7105848073113433e-05, "epoch": 5.258564437194127, "percentage": 52.59, "elapsed_time": "4:23:03", "remaining_time": "3:57:11", "throughput": 4407.39, "total_tokens": 69563648} {"current_steps": 32240, "total_steps": 61300, "loss": 0.3191, "lr": 2.709875530284067e-05, "epoch": 5.259380097879283, "percentage": 52.59, "elapsed_time": "4:23:05", "remaining_time": "3:57:08", "throughput": 4407.45, "total_tokens": 69574880} {"current_steps": 32245, "total_steps": 61300, "loss": 0.3355, "lr": 2.7091662362432153e-05, "epoch": 5.260195758564437, "percentage": 52.6, "elapsed_time": "4:23:08", "remaining_time": "3:57:06", "throughput": 4407.51, "total_tokens": 69586496} {"current_steps": 32250, "total_steps": 61300, "loss": 0.3324, "lr": 2.7084569252462873e-05, "epoch": 5.261011419249592, "percentage": 52.61, "elapsed_time": "4:23:10", "remaining_time": "3:57:03", "throughput": 4407.56, "total_tokens": 69596704} {"current_steps": 32255, "total_steps": 61300, "loss": 0.319, "lr": 2.7077475973507832e-05, "epoch": 5.261827079934747, "percentage": 52.62, "elapsed_time": "4:23:12", "remaining_time": "3:57:00", "throughput": 4407.61, "total_tokens": 69606912} {"current_steps": 32260, "total_steps": 61300, "loss": 0.3879, "lr": 2.7070382526142045e-05, "epoch": 5.262642740619902, "percentage": 52.63, "elapsed_time": "4:23:14", "remaining_time": "3:56:58", "throughput": 4407.68, "total_tokens": 69618880} {"current_steps": 32265, "total_steps": 61300, "loss": 0.349, "lr": 2.706328891094055e-05, "epoch": 5.263458401305057, "percentage": 52.63, "elapsed_time": "4:23:17", "remaining_time": "3:56:55", "throughput": 4407.74, "total_tokens": 69629440} {"current_steps": 32270, "total_steps": 61300, "loss": 0.3221, "lr": 2.7056195128478384e-05, "epoch": 5.264274061990212, "percentage": 52.64, "elapsed_time": "4:23:19", "remaining_time": "3:56:53", "throughput": 4407.79, "total_tokens": 69640128} {"current_steps": 32275, "total_steps": 61300, "loss": 0.334, "lr": 2.7049101179330605e-05, "epoch": 5.265089722675367, "percentage": 52.65, "elapsed_time": "4:23:21", "remaining_time": "3:56:50", "throughput": 4407.85, "total_tokens": 69650816} {"current_steps": 32280, "total_steps": 61300, "loss": 0.3534, "lr": 2.7042007064072288e-05, "epoch": 5.265905383360522, "percentage": 52.66, "elapsed_time": "4:23:23", "remaining_time": "3:56:47", "throughput": 4407.91, "total_tokens": 69661376} {"current_steps": 32285, "total_steps": 61300, "loss": 0.3354, "lr": 2.703491278327852e-05, "epoch": 5.266721044045677, "percentage": 52.67, "elapsed_time": "4:23:25", "remaining_time": "3:56:44", "throughput": 4407.96, "total_tokens": 69671200} {"current_steps": 32290, "total_steps": 61300, "loss": 0.3437, "lr": 2.7027818337524396e-05, "epoch": 5.267536704730832, "percentage": 52.68, "elapsed_time": "4:23:27", "remaining_time": "3:56:42", "throughput": 4408.03, "total_tokens": 69682048} {"current_steps": 32295, "total_steps": 61300, "loss": 0.3417, "lr": 2.7020723727385027e-05, "epoch": 5.268352365415987, "percentage": 52.68, "elapsed_time": "4:23:30", "remaining_time": "3:56:39", "throughput": 4408.09, "total_tokens": 69694208} {"current_steps": 32300, "total_steps": 61300, "loss": 0.3653, "lr": 2.7013628953435544e-05, "epoch": 5.269168026101142, "percentage": 52.69, "elapsed_time": "4:23:32", "remaining_time": "3:56:36", "throughput": 4408.13, "total_tokens": 69702848} {"current_steps": 32305, "total_steps": 61300, "loss": 0.3602, "lr": 2.7006534016251072e-05, "epoch": 5.269983686786297, "percentage": 52.7, "elapsed_time": "4:23:34", "remaining_time": "3:56:34", "throughput": 4408.19, "total_tokens": 69714080} {"current_steps": 32310, "total_steps": 61300, "loss": 0.3338, "lr": 2.6999438916406777e-05, "epoch": 5.270799347471452, "percentage": 52.71, "elapsed_time": "4:23:37", "remaining_time": "3:56:31", "throughput": 4408.25, "total_tokens": 69725408} {"current_steps": 32315, "total_steps": 61300, "loss": 0.3624, "lr": 2.6992343654477825e-05, "epoch": 5.271615008156607, "percentage": 52.72, "elapsed_time": "4:23:39", "remaining_time": "3:56:29", "throughput": 4408.3, "total_tokens": 69736704} {"current_steps": 32320, "total_steps": 61300, "loss": 0.3102, "lr": 2.6985248231039378e-05, "epoch": 5.2724306688417615, "percentage": 52.72, "elapsed_time": "4:23:41", "remaining_time": "3:56:26", "throughput": 4408.36, "total_tokens": 69747264} {"current_steps": 32325, "total_steps": 61300, "loss": 0.3096, "lr": 2.6978152646666644e-05, "epoch": 5.273246329526917, "percentage": 52.73, "elapsed_time": "4:23:43", "remaining_time": "3:56:24", "throughput": 4408.42, "total_tokens": 69758592} {"current_steps": 32330, "total_steps": 61300, "loss": 0.3492, "lr": 2.697105690193481e-05, "epoch": 5.274061990212072, "percentage": 52.74, "elapsed_time": "4:23:46", "remaining_time": "3:56:21", "throughput": 4408.48, "total_tokens": 69769088} {"current_steps": 32335, "total_steps": 61300, "loss": 0.3466, "lr": 2.696396099741911e-05, "epoch": 5.274877650897227, "percentage": 52.75, "elapsed_time": "4:23:48", "remaining_time": "3:56:18", "throughput": 4408.55, "total_tokens": 69780064} {"current_steps": 32340, "total_steps": 61300, "loss": 0.3407, "lr": 2.695686493369476e-05, "epoch": 5.275693311582382, "percentage": 52.76, "elapsed_time": "4:23:50", "remaining_time": "3:56:16", "throughput": 4408.62, "total_tokens": 69792064} {"current_steps": 32345, "total_steps": 61300, "loss": 0.3657, "lr": 2.6949768711337015e-05, "epoch": 5.2765089722675365, "percentage": 52.77, "elapsed_time": "4:23:52", "remaining_time": "3:56:13", "throughput": 4408.67, "total_tokens": 69802304} {"current_steps": 32350, "total_steps": 61300, "loss": 0.3222, "lr": 2.6942672330921124e-05, "epoch": 5.277324632952691, "percentage": 52.77, "elapsed_time": "4:23:54", "remaining_time": "3:56:10", "throughput": 4408.71, "total_tokens": 69811104} {"current_steps": 32355, "total_steps": 61300, "loss": 0.3111, "lr": 2.693557579302236e-05, "epoch": 5.278140293637847, "percentage": 52.78, "elapsed_time": "4:23:57", "remaining_time": "3:56:08", "throughput": 4408.79, "total_tokens": 69823072} {"current_steps": 32360, "total_steps": 61300, "loss": 0.3195, "lr": 2.6928479098216e-05, "epoch": 5.278955954323002, "percentage": 52.79, "elapsed_time": "4:23:59", "remaining_time": "3:56:05", "throughput": 4408.86, "total_tokens": 69835104} {"current_steps": 32365, "total_steps": 61300, "loss": 0.3003, "lr": 2.6921382247077336e-05, "epoch": 5.279771615008157, "percentage": 52.8, "elapsed_time": "4:24:02", "remaining_time": "3:56:03", "throughput": 4408.93, "total_tokens": 69846784} {"current_steps": 32370, "total_steps": 61300, "loss": 0.3109, "lr": 2.691428524018168e-05, "epoch": 5.280587275693311, "percentage": 52.81, "elapsed_time": "4:24:04", "remaining_time": "3:56:00", "throughput": 4408.98, "total_tokens": 69857024} {"current_steps": 32375, "total_steps": 61300, "loss": 0.3719, "lr": 2.6907188078104352e-05, "epoch": 5.281402936378466, "percentage": 52.81, "elapsed_time": "4:24:06", "remaining_time": "3:55:57", "throughput": 4409.03, "total_tokens": 69866624} {"current_steps": 32380, "total_steps": 61300, "loss": 0.3598, "lr": 2.690009076142067e-05, "epoch": 5.282218597063622, "percentage": 52.82, "elapsed_time": "4:24:08", "remaining_time": "3:55:55", "throughput": 4409.1, "total_tokens": 69878816} {"current_steps": 32385, "total_steps": 61300, "loss": 0.3265, "lr": 2.6892993290706e-05, "epoch": 5.283034257748777, "percentage": 52.83, "elapsed_time": "4:24:10", "remaining_time": "3:55:52", "throughput": 4409.16, "total_tokens": 69889184} {"current_steps": 32390, "total_steps": 61300, "loss": 0.326, "lr": 2.6885895666535684e-05, "epoch": 5.283849918433932, "percentage": 52.84, "elapsed_time": "4:24:13", "remaining_time": "3:55:49", "throughput": 4409.21, "total_tokens": 69900160} {"current_steps": 32395, "total_steps": 61300, "loss": 0.3356, "lr": 2.6878797889485096e-05, "epoch": 5.284665579119086, "percentage": 52.85, "elapsed_time": "4:24:15", "remaining_time": "3:55:47", "throughput": 4409.28, "total_tokens": 69910848} {"current_steps": 32400, "total_steps": 61300, "loss": 0.3381, "lr": 2.687169996012962e-05, "epoch": 5.285481239804241, "percentage": 52.85, "elapsed_time": "4:24:17", "remaining_time": "3:55:44", "throughput": 4409.33, "total_tokens": 69921856} {"current_steps": 32405, "total_steps": 61300, "loss": 0.3544, "lr": 2.6864601879044653e-05, "epoch": 5.286296900489396, "percentage": 52.86, "elapsed_time": "4:24:19", "remaining_time": "3:55:42", "throughput": 4409.38, "total_tokens": 69932768} {"current_steps": 32410, "total_steps": 61300, "loss": 0.3447, "lr": 2.6857503646805593e-05, "epoch": 5.287112561174552, "percentage": 52.87, "elapsed_time": "4:24:22", "remaining_time": "3:55:39", "throughput": 4409.45, "total_tokens": 69943488} {"current_steps": 32415, "total_steps": 61300, "loss": 0.3477, "lr": 2.6850405263987867e-05, "epoch": 5.287928221859707, "percentage": 52.88, "elapsed_time": "4:24:24", "remaining_time": "3:55:36", "throughput": 4409.49, "total_tokens": 69953312} {"current_steps": 32420, "total_steps": 61300, "loss": 0.293, "lr": 2.6843306731166894e-05, "epoch": 5.288743882544861, "percentage": 52.89, "elapsed_time": "4:24:26", "remaining_time": "3:55:33", "throughput": 4409.54, "total_tokens": 69963072} {"current_steps": 32425, "total_steps": 61300, "loss": 0.3021, "lr": 2.6836208048918132e-05, "epoch": 5.289559543230016, "percentage": 52.9, "elapsed_time": "4:24:28", "remaining_time": "3:55:31", "throughput": 4409.58, "total_tokens": 69973600} {"current_steps": 32430, "total_steps": 61300, "loss": 0.3613, "lr": 2.682910921781702e-05, "epoch": 5.290375203915171, "percentage": 52.9, "elapsed_time": "4:24:30", "remaining_time": "3:55:28", "throughput": 4409.65, "total_tokens": 69984384} {"current_steps": 32435, "total_steps": 61300, "loss": 0.3587, "lr": 2.682201023843904e-05, "epoch": 5.291190864600326, "percentage": 52.91, "elapsed_time": "4:24:33", "remaining_time": "3:55:25", "throughput": 4409.7, "total_tokens": 69995616} {"current_steps": 32440, "total_steps": 61300, "loss": 0.3301, "lr": 2.6814911111359665e-05, "epoch": 5.2920065252854815, "percentage": 52.92, "elapsed_time": "4:24:35", "remaining_time": "3:55:23", "throughput": 4409.76, "total_tokens": 70006432} {"current_steps": 32445, "total_steps": 61300, "loss": 0.3551, "lr": 2.6807811837154383e-05, "epoch": 5.292822185970636, "percentage": 52.93, "elapsed_time": "4:24:37", "remaining_time": "3:55:20", "throughput": 4409.81, "total_tokens": 70017120} {"current_steps": 32450, "total_steps": 61300, "loss": 0.347, "lr": 2.6800712416398705e-05, "epoch": 5.293637846655791, "percentage": 52.94, "elapsed_time": "4:24:39", "remaining_time": "3:55:18", "throughput": 4409.87, "total_tokens": 70027744} {"current_steps": 32455, "total_steps": 61300, "loss": 0.3286, "lr": 2.6793612849668138e-05, "epoch": 5.294453507340946, "percentage": 52.94, "elapsed_time": "4:24:42", "remaining_time": "3:55:15", "throughput": 4409.93, "total_tokens": 70039360} {"current_steps": 32460, "total_steps": 61300, "loss": 0.352, "lr": 2.6786513137538216e-05, "epoch": 5.295269168026101, "percentage": 52.95, "elapsed_time": "4:24:44", "remaining_time": "3:55:12", "throughput": 4409.99, "total_tokens": 70049952} {"current_steps": 32465, "total_steps": 61300, "loss": 0.3293, "lr": 2.677941328058447e-05, "epoch": 5.2960848287112565, "percentage": 52.96, "elapsed_time": "4:24:46", "remaining_time": "3:55:10", "throughput": 4410.06, "total_tokens": 70059904} {"current_steps": 32470, "total_steps": 61300, "loss": 0.3196, "lr": 2.677231327938246e-05, "epoch": 5.296900489396411, "percentage": 52.97, "elapsed_time": "4:24:48", "remaining_time": "3:55:07", "throughput": 4410.11, "total_tokens": 70070464} {"current_steps": 32475, "total_steps": 61300, "loss": 0.3285, "lr": 2.676521313450774e-05, "epoch": 5.297716150081566, "percentage": 52.98, "elapsed_time": "4:24:50", "remaining_time": "3:55:04", "throughput": 4410.17, "total_tokens": 70081472} {"current_steps": 32480, "total_steps": 61300, "loss": 0.3415, "lr": 2.6758112846535888e-05, "epoch": 5.298531810766721, "percentage": 52.99, "elapsed_time": "4:24:52", "remaining_time": "3:55:02", "throughput": 4410.21, "total_tokens": 70091360} {"current_steps": 32485, "total_steps": 61300, "loss": 0.3264, "lr": 2.6751012416042487e-05, "epoch": 5.299347471451876, "percentage": 52.99, "elapsed_time": "4:24:54", "remaining_time": "3:54:59", "throughput": 4410.26, "total_tokens": 70101088} {"current_steps": 32490, "total_steps": 61300, "loss": 0.3568, "lr": 2.674391184360313e-05, "epoch": 5.300163132137031, "percentage": 53.0, "elapsed_time": "4:24:57", "remaining_time": "3:54:56", "throughput": 4410.32, "total_tokens": 70112608} {"current_steps": 32495, "total_steps": 61300, "loss": 0.3305, "lr": 2.6736811129793438e-05, "epoch": 5.300978792822186, "percentage": 53.01, "elapsed_time": "4:24:59", "remaining_time": "3:54:54", "throughput": 4410.38, "total_tokens": 70124128} {"current_steps": 32500, "total_steps": 61300, "loss": 0.3615, "lr": 2.6729710275189024e-05, "epoch": 5.301794453507341, "percentage": 53.02, "elapsed_time": "4:25:02", "remaining_time": "3:54:51", "throughput": 4410.44, "total_tokens": 70136736} {"current_steps": 32505, "total_steps": 61300, "loss": 0.3607, "lr": 2.672260928036552e-05, "epoch": 5.302610114192496, "percentage": 53.03, "elapsed_time": "4:25:04", "remaining_time": "3:54:49", "throughput": 4410.52, "total_tokens": 70148768} {"current_steps": 32510, "total_steps": 61300, "loss": 0.359, "lr": 2.671550814589856e-05, "epoch": 5.303425774877651, "percentage": 53.03, "elapsed_time": "4:25:06", "remaining_time": "3:54:46", "throughput": 4410.57, "total_tokens": 70158592} {"current_steps": 32515, "total_steps": 61300, "loss": 0.3655, "lr": 2.6708406872363813e-05, "epoch": 5.304241435562806, "percentage": 53.04, "elapsed_time": "4:25:09", "remaining_time": "3:54:44", "throughput": 4410.63, "total_tokens": 70169856} {"current_steps": 32520, "total_steps": 61300, "loss": 0.3318, "lr": 2.670130546033693e-05, "epoch": 5.30505709624796, "percentage": 53.05, "elapsed_time": "4:25:11", "remaining_time": "3:54:41", "throughput": 4410.69, "total_tokens": 70179680} {"current_steps": 32525, "total_steps": 61300, "loss": 0.3486, "lr": 2.6694203910393594e-05, "epoch": 5.305872756933116, "percentage": 53.06, "elapsed_time": "4:25:13", "remaining_time": "3:54:38", "throughput": 4410.75, "total_tokens": 70191104} {"current_steps": 32530, "total_steps": 61300, "loss": 0.3246, "lr": 2.66871022231095e-05, "epoch": 5.306688417618271, "percentage": 53.07, "elapsed_time": "4:25:15", "remaining_time": "3:54:36", "throughput": 4410.81, "total_tokens": 70201728} {"current_steps": 32535, "total_steps": 61300, "loss": 0.3501, "lr": 2.6680000399060327e-05, "epoch": 5.307504078303426, "percentage": 53.08, "elapsed_time": "4:25:18", "remaining_time": "3:54:33", "throughput": 4410.88, "total_tokens": 70213088} {"current_steps": 32540, "total_steps": 61300, "loss": 0.3274, "lr": 2.6672898438821808e-05, "epoch": 5.308319738988581, "percentage": 53.08, "elapsed_time": "4:25:20", "remaining_time": "3:54:30", "throughput": 4410.93, "total_tokens": 70223648} {"current_steps": 32545, "total_steps": 61300, "loss": 0.3241, "lr": 2.666579634296965e-05, "epoch": 5.309135399673735, "percentage": 53.09, "elapsed_time": "4:25:22", "remaining_time": "3:54:28", "throughput": 4410.99, "total_tokens": 70234272} {"current_steps": 32550, "total_steps": 61300, "loss": 0.3382, "lr": 2.6658694112079586e-05, "epoch": 5.309951060358891, "percentage": 53.1, "elapsed_time": "4:25:24", "remaining_time": "3:54:25", "throughput": 4411.05, "total_tokens": 70244800} {"current_steps": 32555, "total_steps": 61300, "loss": 0.3728, "lr": 2.6651591746727363e-05, "epoch": 5.310766721044046, "percentage": 53.11, "elapsed_time": "4:25:26", "remaining_time": "3:54:22", "throughput": 4411.1, "total_tokens": 70255360} {"current_steps": 32560, "total_steps": 61300, "loss": 0.3375, "lr": 2.6644489247488735e-05, "epoch": 5.311582381729201, "percentage": 53.12, "elapsed_time": "4:25:29", "remaining_time": "3:54:20", "throughput": 4411.16, "total_tokens": 70265888} {"current_steps": 32565, "total_steps": 61300, "loss": 0.3368, "lr": 2.6637386614939464e-05, "epoch": 5.3123980424143555, "percentage": 53.12, "elapsed_time": "4:25:31", "remaining_time": "3:54:17", "throughput": 4411.22, "total_tokens": 70276544} {"current_steps": 32570, "total_steps": 61300, "loss": 0.3541, "lr": 2.6630283849655326e-05, "epoch": 5.31321370309951, "percentage": 53.13, "elapsed_time": "4:25:33", "remaining_time": "3:54:15", "throughput": 4411.29, "total_tokens": 70287904} {"current_steps": 32575, "total_steps": 61300, "loss": 0.2981, "lr": 2.6623180952212106e-05, "epoch": 5.314029363784665, "percentage": 53.14, "elapsed_time": "4:25:36", "remaining_time": "3:54:12", "throughput": 4411.35, "total_tokens": 70299872} {"current_steps": 32580, "total_steps": 61300, "loss": 0.3352, "lr": 2.66160779231856e-05, "epoch": 5.314845024469821, "percentage": 53.15, "elapsed_time": "4:25:38", "remaining_time": "3:54:10", "throughput": 4411.41, "total_tokens": 70310624} {"current_steps": 32585, "total_steps": 61300, "loss": 0.3738, "lr": 2.660897476315162e-05, "epoch": 5.315660685154976, "percentage": 53.16, "elapsed_time": "4:25:40", "remaining_time": "3:54:07", "throughput": 4411.46, "total_tokens": 70321312} {"current_steps": 32590, "total_steps": 61300, "loss": 0.3435, "lr": 2.6601871472685985e-05, "epoch": 5.3164763458401305, "percentage": 53.16, "elapsed_time": "4:25:42", "remaining_time": "3:54:04", "throughput": 4411.51, "total_tokens": 70332384} {"current_steps": 32595, "total_steps": 61300, "loss": 0.3141, "lr": 2.659476805236451e-05, "epoch": 5.317292006525285, "percentage": 53.17, "elapsed_time": "4:25:45", "remaining_time": "3:54:02", "throughput": 4411.57, "total_tokens": 70343232} {"current_steps": 32600, "total_steps": 61300, "loss": 0.339, "lr": 2.6587664502763054e-05, "epoch": 5.31810766721044, "percentage": 53.18, "elapsed_time": "4:25:47", "remaining_time": "3:53:59", "throughput": 4411.64, "total_tokens": 70355104} {"current_steps": 32605, "total_steps": 61300, "loss": 0.3217, "lr": 2.6580560824457457e-05, "epoch": 5.318923327895595, "percentage": 53.19, "elapsed_time": "4:25:49", "remaining_time": "3:53:57", "throughput": 4411.7, "total_tokens": 70366400} {"current_steps": 32610, "total_steps": 61300, "loss": 0.3063, "lr": 2.657345701802358e-05, "epoch": 5.319738988580751, "percentage": 53.2, "elapsed_time": "4:25:52", "remaining_time": "3:53:54", "throughput": 4411.77, "total_tokens": 70378400} {"current_steps": 32615, "total_steps": 61300, "loss": 0.3756, "lr": 2.6566353084037295e-05, "epoch": 5.3205546492659055, "percentage": 53.21, "elapsed_time": "4:25:54", "remaining_time": "3:53:52", "throughput": 4411.83, "total_tokens": 70389952} {"current_steps": 32620, "total_steps": 61300, "loss": 0.308, "lr": 2.6559249023074474e-05, "epoch": 5.32137030995106, "percentage": 53.21, "elapsed_time": "4:25:57", "remaining_time": "3:53:49", "throughput": 4411.89, "total_tokens": 70401408} {"current_steps": 32625, "total_steps": 61300, "loss": 0.3636, "lr": 2.6552144835711017e-05, "epoch": 5.322185970636215, "percentage": 53.22, "elapsed_time": "4:25:59", "remaining_time": "3:53:47", "throughput": 4411.95, "total_tokens": 70412640} {"current_steps": 32630, "total_steps": 61300, "loss": 0.3219, "lr": 2.6545040522522828e-05, "epoch": 5.32300163132137, "percentage": 53.23, "elapsed_time": "4:26:01", "remaining_time": "3:53:44", "throughput": 4411.99, "total_tokens": 70422592} {"current_steps": 32635, "total_steps": 61300, "loss": 0.3227, "lr": 2.653793608408582e-05, "epoch": 5.323817292006526, "percentage": 53.24, "elapsed_time": "4:26:03", "remaining_time": "3:53:41", "throughput": 4412.05, "total_tokens": 70433856} {"current_steps": 32640, "total_steps": 61300, "loss": 0.3124, "lr": 2.6530831520975903e-05, "epoch": 5.3246329526916805, "percentage": 53.25, "elapsed_time": "4:26:06", "remaining_time": "3:53:39", "throughput": 4412.11, "total_tokens": 70445376} {"current_steps": 32645, "total_steps": 61300, "loss": 0.3346, "lr": 2.652372683376902e-05, "epoch": 5.325448613376835, "percentage": 53.25, "elapsed_time": "4:26:08", "remaining_time": "3:53:36", "throughput": 4412.16, "total_tokens": 70456384} {"current_steps": 32650, "total_steps": 61300, "loss": 0.3631, "lr": 2.65166220230411e-05, "epoch": 5.32626427406199, "percentage": 53.26, "elapsed_time": "4:26:10", "remaining_time": "3:53:34", "throughput": 4412.22, "total_tokens": 70467040} {"current_steps": 32655, "total_steps": 61300, "loss": 0.3565, "lr": 2.650951708936811e-05, "epoch": 5.327079934747145, "percentage": 53.27, "elapsed_time": "4:26:13", "remaining_time": "3:53:31", "throughput": 4412.27, "total_tokens": 70477248} {"current_steps": 32660, "total_steps": 61300, "loss": 0.3254, "lr": 2.6502412033326e-05, "epoch": 5.327895595432301, "percentage": 53.28, "elapsed_time": "4:26:15", "remaining_time": "3:53:28", "throughput": 4412.32, "total_tokens": 70487648} {"current_steps": 32665, "total_steps": 61300, "loss": 0.3873, "lr": 2.6495306855490754e-05, "epoch": 5.328711256117455, "percentage": 53.29, "elapsed_time": "4:26:17", "remaining_time": "3:53:26", "throughput": 4412.38, "total_tokens": 70499296} {"current_steps": 32670, "total_steps": 61300, "loss": 0.3111, "lr": 2.6488201556438346e-05, "epoch": 5.32952691680261, "percentage": 53.3, "elapsed_time": "4:26:19", "remaining_time": "3:53:23", "throughput": 4412.44, "total_tokens": 70509664} {"current_steps": 32675, "total_steps": 61300, "loss": 0.346, "lr": 2.648109613674477e-05, "epoch": 5.330342577487765, "percentage": 53.3, "elapsed_time": "4:26:21", "remaining_time": "3:53:20", "throughput": 4412.5, "total_tokens": 70520064} {"current_steps": 32680, "total_steps": 61300, "loss": 0.3495, "lr": 2.647399059698602e-05, "epoch": 5.33115823817292, "percentage": 53.31, "elapsed_time": "4:26:24", "remaining_time": "3:53:18", "throughput": 4412.56, "total_tokens": 70531104} {"current_steps": 32685, "total_steps": 61300, "loss": 0.3421, "lr": 2.646688493773812e-05, "epoch": 5.331973898858075, "percentage": 53.32, "elapsed_time": "4:26:26", "remaining_time": "3:53:15", "throughput": 4412.62, "total_tokens": 70542528} {"current_steps": 32690, "total_steps": 61300, "loss": 0.3493, "lr": 2.6459779159577077e-05, "epoch": 5.33278955954323, "percentage": 53.33, "elapsed_time": "4:26:28", "remaining_time": "3:53:13", "throughput": 4412.68, "total_tokens": 70553216} {"current_steps": 32695, "total_steps": 61300, "loss": 0.3622, "lr": 2.645267326307893e-05, "epoch": 5.333605220228385, "percentage": 53.34, "elapsed_time": "4:26:31", "remaining_time": "3:53:10", "throughput": 4412.75, "total_tokens": 70565504} {"current_steps": 32700, "total_steps": 61300, "loss": 0.3331, "lr": 2.6445567248819726e-05, "epoch": 5.33442088091354, "percentage": 53.34, "elapsed_time": "4:26:33", "remaining_time": "3:53:08", "throughput": 4412.81, "total_tokens": 70577376} {"current_steps": 32705, "total_steps": 61300, "loss": 0.317, "lr": 2.643846111737549e-05, "epoch": 5.335236541598695, "percentage": 53.35, "elapsed_time": "4:26:36", "remaining_time": "3:53:05", "throughput": 4412.88, "total_tokens": 70588960} {"current_steps": 32710, "total_steps": 61300, "loss": 0.3172, "lr": 2.643135486932231e-05, "epoch": 5.33605220228385, "percentage": 53.36, "elapsed_time": "4:26:38", "remaining_time": "3:53:03", "throughput": 4412.94, "total_tokens": 70600192} {"current_steps": 32715, "total_steps": 61300, "loss": 0.3403, "lr": 2.642424850523624e-05, "epoch": 5.3368678629690045, "percentage": 53.37, "elapsed_time": "4:26:40", "remaining_time": "3:53:00", "throughput": 4412.98, "total_tokens": 70610816} {"current_steps": 32720, "total_steps": 61300, "loss": 0.3811, "lr": 2.641714202569336e-05, "epoch": 5.33768352365416, "percentage": 53.38, "elapsed_time": "4:26:42", "remaining_time": "3:52:58", "throughput": 4413.03, "total_tokens": 70621280} {"current_steps": 32725, "total_steps": 61300, "loss": 0.3386, "lr": 2.6410035431269754e-05, "epoch": 5.338499184339315, "percentage": 53.38, "elapsed_time": "4:26:45", "remaining_time": "3:52:55", "throughput": 4413.07, "total_tokens": 70631968} {"current_steps": 32730, "total_steps": 61300, "loss": 0.2771, "lr": 2.6402928722541524e-05, "epoch": 5.33931484502447, "percentage": 53.39, "elapsed_time": "4:26:47", "remaining_time": "3:52:52", "throughput": 4413.13, "total_tokens": 70643296} {"current_steps": 32735, "total_steps": 61300, "loss": 0.3324, "lr": 2.6395821900084772e-05, "epoch": 5.340130505709625, "percentage": 53.4, "elapsed_time": "4:26:49", "remaining_time": "3:52:50", "throughput": 4413.18, "total_tokens": 70652576} {"current_steps": 32740, "total_steps": 61300, "loss": 0.3768, "lr": 2.638871496447562e-05, "epoch": 5.3409461663947795, "percentage": 53.41, "elapsed_time": "4:26:51", "remaining_time": "3:52:47", "throughput": 4413.23, "total_tokens": 70663424} {"current_steps": 32745, "total_steps": 61300, "loss": 0.3333, "lr": 2.638160791629018e-05, "epoch": 5.341761827079935, "percentage": 53.42, "elapsed_time": "4:26:53", "remaining_time": "3:52:44", "throughput": 4413.29, "total_tokens": 70673536} {"current_steps": 32750, "total_steps": 61300, "loss": 0.3391, "lr": 2.6374500756104594e-05, "epoch": 5.34257748776509, "percentage": 53.43, "elapsed_time": "4:26:55", "remaining_time": "3:52:41", "throughput": 4413.34, "total_tokens": 70683712} {"current_steps": 32755, "total_steps": 61300, "loss": 0.3306, "lr": 2.6367393484494994e-05, "epoch": 5.343393148450245, "percentage": 53.43, "elapsed_time": "4:26:58", "remaining_time": "3:52:39", "throughput": 4413.38, "total_tokens": 70693856} {"current_steps": 32760, "total_steps": 61300, "loss": 0.3301, "lr": 2.636028610203755e-05, "epoch": 5.3442088091354, "percentage": 53.44, "elapsed_time": "4:27:00", "remaining_time": "3:52:36", "throughput": 4413.45, "total_tokens": 70705024} {"current_steps": 32765, "total_steps": 61300, "loss": 0.3283, "lr": 2.635317860930841e-05, "epoch": 5.3450244698205545, "percentage": 53.45, "elapsed_time": "4:27:02", "remaining_time": "3:52:33", "throughput": 4413.49, "total_tokens": 70715040} {"current_steps": 32770, "total_steps": 61300, "loss": 0.3298, "lr": 2.6346071006883748e-05, "epoch": 5.345840130505709, "percentage": 53.46, "elapsed_time": "4:27:04", "remaining_time": "3:52:31", "throughput": 4413.54, "total_tokens": 70726080} {"current_steps": 32775, "total_steps": 61300, "loss": 0.3318, "lr": 2.6338963295339737e-05, "epoch": 5.346655791190865, "percentage": 53.47, "elapsed_time": "4:27:07", "remaining_time": "3:52:28", "throughput": 4413.6, "total_tokens": 70736800} {"current_steps": 32780, "total_steps": 61300, "loss": 0.3076, "lr": 2.633185547525257e-05, "epoch": 5.34747145187602, "percentage": 53.47, "elapsed_time": "4:27:09", "remaining_time": "3:52:26", "throughput": 4413.66, "total_tokens": 70748928} {"current_steps": 32785, "total_steps": 61300, "loss": 0.306, "lr": 2.6324747547198443e-05, "epoch": 5.348287112561175, "percentage": 53.48, "elapsed_time": "4:27:11", "remaining_time": "3:52:23", "throughput": 4413.72, "total_tokens": 70760736} {"current_steps": 32790, "total_steps": 61300, "loss": 0.3067, "lr": 2.631763951175355e-05, "epoch": 5.349102773246329, "percentage": 53.49, "elapsed_time": "4:27:14", "remaining_time": "3:52:21", "throughput": 4413.78, "total_tokens": 70771552} {"current_steps": 32795, "total_steps": 61300, "loss": 0.3285, "lr": 2.6310531369494118e-05, "epoch": 5.349918433931484, "percentage": 53.5, "elapsed_time": "4:27:16", "remaining_time": "3:52:18", "throughput": 4413.85, "total_tokens": 70782656} {"current_steps": 32800, "total_steps": 61300, "loss": 0.3833, "lr": 2.630342312099637e-05, "epoch": 5.350734094616639, "percentage": 53.51, "elapsed_time": "4:27:18", "remaining_time": "3:52:15", "throughput": 4413.9, "total_tokens": 70792736} {"current_steps": 32805, "total_steps": 61300, "loss": 0.3007, "lr": 2.629631476683652e-05, "epoch": 5.351549755301795, "percentage": 53.52, "elapsed_time": "4:27:20", "remaining_time": "3:52:13", "throughput": 4413.98, "total_tokens": 70804032} {"current_steps": 32810, "total_steps": 61300, "loss": 0.3598, "lr": 2.6289206307590815e-05, "epoch": 5.35236541598695, "percentage": 53.52, "elapsed_time": "4:27:22", "remaining_time": "3:52:10", "throughput": 4414.03, "total_tokens": 70814208} {"current_steps": 32815, "total_steps": 61300, "loss": 0.3171, "lr": 2.6282097743835517e-05, "epoch": 5.353181076672104, "percentage": 53.53, "elapsed_time": "4:27:25", "remaining_time": "3:52:08", "throughput": 4414.09, "total_tokens": 70825312} {"current_steps": 32820, "total_steps": 61300, "loss": 0.3105, "lr": 2.627498907614686e-05, "epoch": 5.353996737357259, "percentage": 53.54, "elapsed_time": "4:27:27", "remaining_time": "3:52:05", "throughput": 4414.13, "total_tokens": 70835680} {"current_steps": 32825, "total_steps": 61300, "loss": 0.313, "lr": 2.6267880305101127e-05, "epoch": 5.354812398042414, "percentage": 53.55, "elapsed_time": "4:27:29", "remaining_time": "3:52:02", "throughput": 4414.19, "total_tokens": 70846336} {"current_steps": 32830, "total_steps": 61300, "loss": 0.3497, "lr": 2.626077143127458e-05, "epoch": 5.35562805872757, "percentage": 53.56, "elapsed_time": "4:27:32", "remaining_time": "3:52:00", "throughput": 4414.25, "total_tokens": 70858016} {"current_steps": 32835, "total_steps": 61300, "loss": 0.3389, "lr": 2.6253662455243504e-05, "epoch": 5.356443719412725, "percentage": 53.56, "elapsed_time": "4:27:34", "remaining_time": "3:51:57", "throughput": 4414.3, "total_tokens": 70868704} {"current_steps": 32840, "total_steps": 61300, "loss": 0.3435, "lr": 2.6246553377584186e-05, "epoch": 5.357259380097879, "percentage": 53.57, "elapsed_time": "4:27:36", "remaining_time": "3:51:55", "throughput": 4414.34, "total_tokens": 70879392} {"current_steps": 32845, "total_steps": 61300, "loss": 0.361, "lr": 2.623944419887293e-05, "epoch": 5.358075040783034, "percentage": 53.58, "elapsed_time": "4:27:38", "remaining_time": "3:51:52", "throughput": 4414.41, "total_tokens": 70890848} {"current_steps": 32850, "total_steps": 61300, "loss": 0.3375, "lr": 2.6232334919686035e-05, "epoch": 5.358890701468189, "percentage": 53.59, "elapsed_time": "4:27:41", "remaining_time": "3:51:49", "throughput": 4414.46, "total_tokens": 70901472} {"current_steps": 32855, "total_steps": 61300, "loss": 0.2994, "lr": 2.6225225540599825e-05, "epoch": 5.359706362153344, "percentage": 53.6, "elapsed_time": "4:27:43", "remaining_time": "3:51:47", "throughput": 4414.51, "total_tokens": 70911904} {"current_steps": 32860, "total_steps": 61300, "loss": 0.3393, "lr": 2.6218116062190605e-05, "epoch": 5.3605220228384995, "percentage": 53.61, "elapsed_time": "4:27:45", "remaining_time": "3:51:44", "throughput": 4414.57, "total_tokens": 70922880} {"current_steps": 32865, "total_steps": 61300, "loss": 0.3413, "lr": 2.621100648503472e-05, "epoch": 5.361337683523654, "percentage": 53.61, "elapsed_time": "4:27:47", "remaining_time": "3:51:42", "throughput": 4414.61, "total_tokens": 70933472} {"current_steps": 32870, "total_steps": 61300, "loss": 0.3379, "lr": 2.6203896809708512e-05, "epoch": 5.362153344208809, "percentage": 53.62, "elapsed_time": "4:27:50", "remaining_time": "3:51:39", "throughput": 4414.68, "total_tokens": 70944864} {"current_steps": 32875, "total_steps": 61300, "loss": 0.3715, "lr": 2.619678703678832e-05, "epoch": 5.362969004893964, "percentage": 53.63, "elapsed_time": "4:27:52", "remaining_time": "3:51:36", "throughput": 4414.75, "total_tokens": 70956512} {"current_steps": 32880, "total_steps": 61300, "loss": 0.3148, "lr": 2.618967716685049e-05, "epoch": 5.363784665579119, "percentage": 53.64, "elapsed_time": "4:27:54", "remaining_time": "3:51:34", "throughput": 4414.8, "total_tokens": 70966400} {"current_steps": 32885, "total_steps": 61300, "loss": 0.3389, "lr": 2.6182567200471396e-05, "epoch": 5.364600326264274, "percentage": 53.65, "elapsed_time": "4:27:56", "remaining_time": "3:51:31", "throughput": 4414.85, "total_tokens": 70977120} {"current_steps": 32890, "total_steps": 61300, "loss": 0.3465, "lr": 2.6175457138227404e-05, "epoch": 5.365415986949429, "percentage": 53.65, "elapsed_time": "4:27:59", "remaining_time": "3:51:28", "throughput": 4414.89, "total_tokens": 70987712} {"current_steps": 32895, "total_steps": 61300, "loss": 0.3247, "lr": 2.6168346980694896e-05, "epoch": 5.366231647634584, "percentage": 53.66, "elapsed_time": "4:28:01", "remaining_time": "3:51:26", "throughput": 4414.95, "total_tokens": 70998080} {"current_steps": 32900, "total_steps": 61300, "loss": 0.3223, "lr": 2.6161236728450257e-05, "epoch": 5.367047308319739, "percentage": 53.67, "elapsed_time": "4:28:03", "remaining_time": "3:51:23", "throughput": 4415.01, "total_tokens": 71009568} {"current_steps": 32905, "total_steps": 61300, "loss": 0.3387, "lr": 2.6154126382069866e-05, "epoch": 5.367862969004894, "percentage": 53.68, "elapsed_time": "4:28:06", "remaining_time": "3:51:21", "throughput": 4415.08, "total_tokens": 71021728} {"current_steps": 32910, "total_steps": 61300, "loss": 0.3444, "lr": 2.6147015942130143e-05, "epoch": 5.368678629690049, "percentage": 53.69, "elapsed_time": "4:28:08", "remaining_time": "3:51:18", "throughput": 4415.13, "total_tokens": 71032704} {"current_steps": 32915, "total_steps": 61300, "loss": 0.3826, "lr": 2.6139905409207475e-05, "epoch": 5.369494290375204, "percentage": 53.69, "elapsed_time": "4:28:10", "remaining_time": "3:51:16", "throughput": 4415.2, "total_tokens": 71043808} {"current_steps": 32920, "total_steps": 61300, "loss": 0.3551, "lr": 2.61327947838783e-05, "epoch": 5.370309951060359, "percentage": 53.7, "elapsed_time": "4:28:12", "remaining_time": "3:51:13", "throughput": 4415.26, "total_tokens": 71054752} {"current_steps": 32925, "total_steps": 61300, "loss": 0.3224, "lr": 2.6125684066719036e-05, "epoch": 5.371125611745514, "percentage": 53.71, "elapsed_time": "4:28:15", "remaining_time": "3:51:10", "throughput": 4415.3, "total_tokens": 71065216} {"current_steps": 32930, "total_steps": 61300, "loss": 0.3474, "lr": 2.6118573258306106e-05, "epoch": 5.371941272430669, "percentage": 53.72, "elapsed_time": "4:28:17", "remaining_time": "3:51:08", "throughput": 4415.36, "total_tokens": 71074752} {"current_steps": 32935, "total_steps": 61300, "loss": 0.3206, "lr": 2.6111462359215944e-05, "epoch": 5.372756933115824, "percentage": 53.73, "elapsed_time": "4:28:19", "remaining_time": "3:51:05", "throughput": 4415.4, "total_tokens": 71084864} {"current_steps": 32940, "total_steps": 61300, "loss": 0.3268, "lr": 2.6104351370025014e-05, "epoch": 5.373572593800978, "percentage": 53.74, "elapsed_time": "4:28:21", "remaining_time": "3:51:02", "throughput": 4415.47, "total_tokens": 71095392} {"current_steps": 32945, "total_steps": 61300, "loss": 0.3164, "lr": 2.6097240291309756e-05, "epoch": 5.374388254486134, "percentage": 53.74, "elapsed_time": "4:28:23", "remaining_time": "3:50:59", "throughput": 4415.51, "total_tokens": 71105472} {"current_steps": 32950, "total_steps": 61300, "loss": 0.3128, "lr": 2.6090129123646633e-05, "epoch": 5.375203915171289, "percentage": 53.75, "elapsed_time": "4:28:25", "remaining_time": "3:50:57", "throughput": 4415.57, "total_tokens": 71116448} {"current_steps": 32955, "total_steps": 61300, "loss": 0.3408, "lr": 2.6083017867612115e-05, "epoch": 5.376019575856444, "percentage": 53.76, "elapsed_time": "4:28:28", "remaining_time": "3:50:54", "throughput": 4415.63, "total_tokens": 71128032} {"current_steps": 32960, "total_steps": 61300, "loss": 0.3409, "lr": 2.6075906523782666e-05, "epoch": 5.376835236541599, "percentage": 53.77, "elapsed_time": "4:28:30", "remaining_time": "3:50:52", "throughput": 4415.7, "total_tokens": 71140448} {"current_steps": 32965, "total_steps": 61300, "loss": 0.3639, "lr": 2.6068795092734783e-05, "epoch": 5.377650897226753, "percentage": 53.78, "elapsed_time": "4:28:32", "remaining_time": "3:50:49", "throughput": 4415.76, "total_tokens": 71150720} {"current_steps": 32970, "total_steps": 61300, "loss": 0.3404, "lr": 2.6061683575044937e-05, "epoch": 5.378466557911908, "percentage": 53.78, "elapsed_time": "4:28:35", "remaining_time": "3:50:47", "throughput": 4415.81, "total_tokens": 71161920} {"current_steps": 32975, "total_steps": 61300, "loss": 0.3557, "lr": 2.605457197128964e-05, "epoch": 5.379282218597064, "percentage": 53.79, "elapsed_time": "4:28:37", "remaining_time": "3:50:44", "throughput": 4415.87, "total_tokens": 71173888} {"current_steps": 32980, "total_steps": 61300, "loss": 0.3384, "lr": 2.6047460282045388e-05, "epoch": 5.380097879282219, "percentage": 53.8, "elapsed_time": "4:28:40", "remaining_time": "3:50:42", "throughput": 4415.94, "total_tokens": 71185984} {"current_steps": 32985, "total_steps": 61300, "loss": 0.3224, "lr": 2.604034850788869e-05, "epoch": 5.3809135399673735, "percentage": 53.81, "elapsed_time": "4:28:42", "remaining_time": "3:50:39", "throughput": 4415.99, "total_tokens": 71196640} {"current_steps": 32990, "total_steps": 61300, "loss": 0.3144, "lr": 2.6033236649396063e-05, "epoch": 5.381729200652528, "percentage": 53.82, "elapsed_time": "4:28:44", "remaining_time": "3:50:37", "throughput": 4416.05, "total_tokens": 71208000} {"current_steps": 32995, "total_steps": 61300, "loss": 0.3432, "lr": 2.6026124707144033e-05, "epoch": 5.382544861337683, "percentage": 53.83, "elapsed_time": "4:28:47", "remaining_time": "3:50:34", "throughput": 4416.1, "total_tokens": 71219616} {"current_steps": 33000, "total_steps": 61300, "loss": 0.3046, "lr": 2.6019012681709127e-05, "epoch": 5.383360522022839, "percentage": 53.83, "elapsed_time": "4:28:49", "remaining_time": "3:50:32", "throughput": 4416.16, "total_tokens": 71230880} {"current_steps": 33005, "total_steps": 61300, "loss": 0.3433, "lr": 2.601190057366788e-05, "epoch": 5.384176182707994, "percentage": 53.84, "elapsed_time": "4:28:51", "remaining_time": "3:50:29", "throughput": 4416.21, "total_tokens": 71240800} {"current_steps": 33010, "total_steps": 61300, "loss": 0.3394, "lr": 2.600478838359684e-05, "epoch": 5.3849918433931485, "percentage": 53.85, "elapsed_time": "4:28:53", "remaining_time": "3:50:26", "throughput": 4416.26, "total_tokens": 71250784} {"current_steps": 33015, "total_steps": 61300, "loss": 0.3217, "lr": 2.5997676112072557e-05, "epoch": 5.385807504078303, "percentage": 53.86, "elapsed_time": "4:28:55", "remaining_time": "3:50:23", "throughput": 4416.32, "total_tokens": 71260576} {"current_steps": 33020, "total_steps": 61300, "loss": 0.2955, "lr": 2.5990563759671575e-05, "epoch": 5.386623164763458, "percentage": 53.87, "elapsed_time": "4:28:57", "remaining_time": "3:50:21", "throughput": 4416.37, "total_tokens": 71270976} {"current_steps": 33025, "total_steps": 61300, "loss": 0.3405, "lr": 2.598345132697048e-05, "epoch": 5.387438825448613, "percentage": 53.87, "elapsed_time": "4:29:00", "remaining_time": "3:50:18", "throughput": 4416.42, "total_tokens": 71281216} {"current_steps": 33030, "total_steps": 61300, "loss": 0.2968, "lr": 2.597633881454583e-05, "epoch": 5.388254486133769, "percentage": 53.88, "elapsed_time": "4:29:02", "remaining_time": "3:50:16", "throughput": 4416.47, "total_tokens": 71292064} {"current_steps": 33035, "total_steps": 61300, "loss": 0.3554, "lr": 2.5969226222974196e-05, "epoch": 5.3890701468189235, "percentage": 53.89, "elapsed_time": "4:29:04", "remaining_time": "3:50:13", "throughput": 4416.54, "total_tokens": 71303392} {"current_steps": 33040, "total_steps": 61300, "loss": 0.3449, "lr": 2.5962113552832173e-05, "epoch": 5.389885807504078, "percentage": 53.9, "elapsed_time": "4:29:06", "remaining_time": "3:50:10", "throughput": 4416.6, "total_tokens": 71314016} {"current_steps": 33045, "total_steps": 61300, "loss": 0.3337, "lr": 2.5955000804696345e-05, "epoch": 5.390701468189233, "percentage": 53.91, "elapsed_time": "4:29:09", "remaining_time": "3:50:08", "throughput": 4416.66, "total_tokens": 71326016} {"current_steps": 33050, "total_steps": 61300, "loss": 0.3131, "lr": 2.5947887979143304e-05, "epoch": 5.391517128874388, "percentage": 53.92, "elapsed_time": "4:29:11", "remaining_time": "3:50:05", "throughput": 4416.71, "total_tokens": 71335840} {"current_steps": 33055, "total_steps": 61300, "loss": 0.3505, "lr": 2.594077507674965e-05, "epoch": 5.392332789559543, "percentage": 53.92, "elapsed_time": "4:29:13", "remaining_time": "3:50:03", "throughput": 4416.78, "total_tokens": 71347072} {"current_steps": 33060, "total_steps": 61300, "loss": 0.3069, "lr": 2.5933662098091997e-05, "epoch": 5.3931484502446985, "percentage": 53.93, "elapsed_time": "4:29:16", "remaining_time": "3:50:00", "throughput": 4416.83, "total_tokens": 71358464} {"current_steps": 33065, "total_steps": 61300, "loss": 0.3455, "lr": 2.5926549043746962e-05, "epoch": 5.393964110929853, "percentage": 53.94, "elapsed_time": "4:29:17", "remaining_time": "3:49:57", "throughput": 4416.88, "total_tokens": 71367776} {"current_steps": 33070, "total_steps": 61300, "loss": 0.3265, "lr": 2.591943591429115e-05, "epoch": 5.394779771615008, "percentage": 53.95, "elapsed_time": "4:29:20", "remaining_time": "3:49:55", "throughput": 4416.94, "total_tokens": 71378368} {"current_steps": 33075, "total_steps": 61300, "loss": 0.3281, "lr": 2.5912322710301202e-05, "epoch": 5.395595432300163, "percentage": 53.96, "elapsed_time": "4:29:22", "remaining_time": "3:49:52", "throughput": 4416.99, "total_tokens": 71389632} {"current_steps": 33080, "total_steps": 61300, "loss": 0.338, "lr": 2.590520943235375e-05, "epoch": 5.396411092985318, "percentage": 53.96, "elapsed_time": "4:29:24", "remaining_time": "3:49:49", "throughput": 4417.06, "total_tokens": 71400064} {"current_steps": 33085, "total_steps": 61300, "loss": 0.302, "lr": 2.5898096081025424e-05, "epoch": 5.397226753670473, "percentage": 53.97, "elapsed_time": "4:29:26", "remaining_time": "3:49:47", "throughput": 4417.11, "total_tokens": 71410784} {"current_steps": 33090, "total_steps": 61300, "loss": 0.2975, "lr": 2.589098265689287e-05, "epoch": 5.398042414355628, "percentage": 53.98, "elapsed_time": "4:29:29", "remaining_time": "3:49:44", "throughput": 4417.18, "total_tokens": 71421632} {"current_steps": 33095, "total_steps": 61300, "loss": 0.3005, "lr": 2.5883869160532743e-05, "epoch": 5.398858075040783, "percentage": 53.99, "elapsed_time": "4:29:31", "remaining_time": "3:49:41", "throughput": 4417.23, "total_tokens": 71432640} {"current_steps": 33100, "total_steps": 61300, "loss": 0.3367, "lr": 2.58767555925217e-05, "epoch": 5.399673735725938, "percentage": 54.0, "elapsed_time": "4:29:33", "remaining_time": "3:49:39", "throughput": 4417.28, "total_tokens": 71442816} {"current_steps": 33105, "total_steps": 61300, "loss": 0.319, "lr": 2.5869641953436402e-05, "epoch": 5.400489396411093, "percentage": 54.0, "elapsed_time": "4:29:35", "remaining_time": "3:49:36", "throughput": 4417.34, "total_tokens": 71453568} {"current_steps": 33110, "total_steps": 61300, "loss": 0.3516, "lr": 2.5862528243853513e-05, "epoch": 5.401305057096248, "percentage": 54.01, "elapsed_time": "4:29:37", "remaining_time": "3:49:33", "throughput": 4417.39, "total_tokens": 71464448} {"current_steps": 33115, "total_steps": 61300, "loss": 0.3256, "lr": 2.5855414464349707e-05, "epoch": 5.402120717781403, "percentage": 54.02, "elapsed_time": "4:29:40", "remaining_time": "3:49:31", "throughput": 4417.45, "total_tokens": 71475264} {"current_steps": 33120, "total_steps": 61300, "loss": 0.3358, "lr": 2.5848300615501663e-05, "epoch": 5.402936378466558, "percentage": 54.03, "elapsed_time": "4:29:42", "remaining_time": "3:49:28", "throughput": 4417.49, "total_tokens": 71484704} {"current_steps": 33125, "total_steps": 61300, "loss": 0.3742, "lr": 2.5841186697886065e-05, "epoch": 5.403752039151713, "percentage": 54.04, "elapsed_time": "4:29:44", "remaining_time": "3:49:25", "throughput": 4417.53, "total_tokens": 71494592} {"current_steps": 33130, "total_steps": 61300, "loss": 0.3297, "lr": 2.583407271207961e-05, "epoch": 5.404567699836868, "percentage": 54.05, "elapsed_time": "4:29:46", "remaining_time": "3:49:23", "throughput": 4417.6, "total_tokens": 71505568} {"current_steps": 33135, "total_steps": 61300, "loss": 0.348, "lr": 2.582695865865899e-05, "epoch": 5.4053833605220225, "percentage": 54.05, "elapsed_time": "4:29:48", "remaining_time": "3:49:20", "throughput": 4417.64, "total_tokens": 71515872} {"current_steps": 33140, "total_steps": 61300, "loss": 0.3172, "lr": 2.5819844538200906e-05, "epoch": 5.406199021207178, "percentage": 54.06, "elapsed_time": "4:29:50", "remaining_time": "3:49:17", "throughput": 4417.69, "total_tokens": 71526720} {"current_steps": 33145, "total_steps": 61300, "loss": 0.3503, "lr": 2.5812730351282056e-05, "epoch": 5.407014681892333, "percentage": 54.07, "elapsed_time": "4:29:53", "remaining_time": "3:49:15", "throughput": 4417.75, "total_tokens": 71537856} {"current_steps": 33150, "total_steps": 61300, "loss": 0.3521, "lr": 2.5805616098479167e-05, "epoch": 5.407830342577488, "percentage": 54.08, "elapsed_time": "4:29:55", "remaining_time": "3:49:12", "throughput": 4417.8, "total_tokens": 71546624} {"current_steps": 33155, "total_steps": 61300, "loss": 0.294, "lr": 2.5798501780368944e-05, "epoch": 5.408646003262643, "percentage": 54.09, "elapsed_time": "4:29:57", "remaining_time": "3:49:09", "throughput": 4417.83, "total_tokens": 71556864} {"current_steps": 33160, "total_steps": 61300, "loss": 0.3458, "lr": 2.5791387397528123e-05, "epoch": 5.4094616639477975, "percentage": 54.09, "elapsed_time": "4:29:59", "remaining_time": "3:49:06", "throughput": 4417.9, "total_tokens": 71566848} {"current_steps": 33165, "total_steps": 61300, "loss": 0.3298, "lr": 2.578427295053341e-05, "epoch": 5.410277324632952, "percentage": 54.1, "elapsed_time": "4:30:01", "remaining_time": "3:49:04", "throughput": 4417.94, "total_tokens": 71576544} {"current_steps": 33170, "total_steps": 61300, "loss": 0.3641, "lr": 2.5777158439961564e-05, "epoch": 5.411092985318108, "percentage": 54.11, "elapsed_time": "4:30:03", "remaining_time": "3:49:01", "throughput": 4418.0, "total_tokens": 71586816} {"current_steps": 33175, "total_steps": 61300, "loss": 0.3166, "lr": 2.577004386638931e-05, "epoch": 5.411908646003263, "percentage": 54.12, "elapsed_time": "4:30:05", "remaining_time": "3:48:58", "throughput": 4418.05, "total_tokens": 71596480} {"current_steps": 33180, "total_steps": 61300, "loss": 0.345, "lr": 2.576292923039339e-05, "epoch": 5.412724306688418, "percentage": 54.13, "elapsed_time": "4:30:07", "remaining_time": "3:48:56", "throughput": 4418.12, "total_tokens": 71607968} {"current_steps": 33185, "total_steps": 61300, "loss": 0.3164, "lr": 2.5755814532550553e-05, "epoch": 5.4135399673735725, "percentage": 54.14, "elapsed_time": "4:30:10", "remaining_time": "3:48:53", "throughput": 4418.16, "total_tokens": 71618560} {"current_steps": 33190, "total_steps": 61300, "loss": 0.3913, "lr": 2.574869977343756e-05, "epoch": 5.414355628058727, "percentage": 54.14, "elapsed_time": "4:30:12", "remaining_time": "3:48:50", "throughput": 4418.22, "total_tokens": 71629952} {"current_steps": 33195, "total_steps": 61300, "loss": 0.3528, "lr": 2.574158495363117e-05, "epoch": 5.415171288743883, "percentage": 54.15, "elapsed_time": "4:30:14", "remaining_time": "3:48:48", "throughput": 4418.27, "total_tokens": 71639296} {"current_steps": 33200, "total_steps": 61300, "loss": 0.3121, "lr": 2.5734470073708133e-05, "epoch": 5.415986949429038, "percentage": 54.16, "elapsed_time": "4:30:16", "remaining_time": "3:48:45", "throughput": 4418.33, "total_tokens": 71649760} {"current_steps": 33205, "total_steps": 61300, "loss": 0.36, "lr": 2.572735513424523e-05, "epoch": 5.416802610114193, "percentage": 54.17, "elapsed_time": "4:30:18", "remaining_time": "3:48:42", "throughput": 4418.38, "total_tokens": 71660800} {"current_steps": 33210, "total_steps": 61300, "loss": 0.3699, "lr": 2.5720240135819223e-05, "epoch": 5.417618270799347, "percentage": 54.18, "elapsed_time": "4:30:20", "remaining_time": "3:48:40", "throughput": 4418.43, "total_tokens": 71671104} {"current_steps": 33215, "total_steps": 61300, "loss": 0.3385, "lr": 2.57131250790069e-05, "epoch": 5.418433931484502, "percentage": 54.18, "elapsed_time": "4:30:23", "remaining_time": "3:48:37", "throughput": 4418.49, "total_tokens": 71681568} {"current_steps": 33220, "total_steps": 61300, "loss": 0.3177, "lr": 2.570600996438504e-05, "epoch": 5.419249592169657, "percentage": 54.19, "elapsed_time": "4:30:25", "remaining_time": "3:48:34", "throughput": 4418.53, "total_tokens": 71691008} {"current_steps": 33225, "total_steps": 61300, "loss": 0.3306, "lr": 2.5698894792530432e-05, "epoch": 5.420065252854813, "percentage": 54.2, "elapsed_time": "4:30:27", "remaining_time": "3:48:32", "throughput": 4418.59, "total_tokens": 71702112} {"current_steps": 33230, "total_steps": 61300, "loss": 0.3694, "lr": 2.5691779564019862e-05, "epoch": 5.420880913539968, "percentage": 54.21, "elapsed_time": "4:30:29", "remaining_time": "3:48:29", "throughput": 4418.65, "total_tokens": 71713696} {"current_steps": 33235, "total_steps": 61300, "loss": 0.3454, "lr": 2.5684664279430125e-05, "epoch": 5.421696574225122, "percentage": 54.22, "elapsed_time": "4:30:32", "remaining_time": "3:48:27", "throughput": 4418.71, "total_tokens": 71724800} {"current_steps": 33240, "total_steps": 61300, "loss": 0.3234, "lr": 2.5677548939338035e-05, "epoch": 5.422512234910277, "percentage": 54.23, "elapsed_time": "4:30:34", "remaining_time": "3:48:24", "throughput": 4418.76, "total_tokens": 71736128} {"current_steps": 33245, "total_steps": 61300, "loss": 0.3417, "lr": 2.5670433544320388e-05, "epoch": 5.423327895595432, "percentage": 54.23, "elapsed_time": "4:30:36", "remaining_time": "3:48:21", "throughput": 4418.82, "total_tokens": 71746912} {"current_steps": 33250, "total_steps": 61300, "loss": 0.3536, "lr": 2.5663318094953997e-05, "epoch": 5.424143556280587, "percentage": 54.24, "elapsed_time": "4:30:38", "remaining_time": "3:48:19", "throughput": 4418.88, "total_tokens": 71757888} {"current_steps": 33255, "total_steps": 61300, "loss": 0.3362, "lr": 2.5656202591815675e-05, "epoch": 5.424959216965743, "percentage": 54.25, "elapsed_time": "4:30:41", "remaining_time": "3:48:16", "throughput": 4418.93, "total_tokens": 71769504} {"current_steps": 33260, "total_steps": 61300, "loss": 0.3215, "lr": 2.5649087035482243e-05, "epoch": 5.425774877650897, "percentage": 54.26, "elapsed_time": "4:30:43", "remaining_time": "3:48:14", "throughput": 4418.98, "total_tokens": 71780352} {"current_steps": 33265, "total_steps": 61300, "loss": 0.3367, "lr": 2.5641971426530525e-05, "epoch": 5.426590538336052, "percentage": 54.27, "elapsed_time": "4:30:45", "remaining_time": "3:48:11", "throughput": 4419.04, "total_tokens": 71791488} {"current_steps": 33270, "total_steps": 61300, "loss": 0.3486, "lr": 2.5634855765537347e-05, "epoch": 5.427406199021207, "percentage": 54.27, "elapsed_time": "4:30:48", "remaining_time": "3:48:09", "throughput": 4419.09, "total_tokens": 71801728} {"current_steps": 33275, "total_steps": 61300, "loss": 0.3262, "lr": 2.5627740053079534e-05, "epoch": 5.428221859706362, "percentage": 54.28, "elapsed_time": "4:30:50", "remaining_time": "3:48:06", "throughput": 4419.14, "total_tokens": 71812096} {"current_steps": 33280, "total_steps": 61300, "loss": 0.337, "lr": 2.562062428973393e-05, "epoch": 5.4290375203915175, "percentage": 54.29, "elapsed_time": "4:30:52", "remaining_time": "3:48:03", "throughput": 4419.2, "total_tokens": 71822752} {"current_steps": 33285, "total_steps": 61300, "loss": 0.3063, "lr": 2.5613508476077365e-05, "epoch": 5.429853181076672, "percentage": 54.3, "elapsed_time": "4:30:54", "remaining_time": "3:48:01", "throughput": 4419.25, "total_tokens": 71833056} {"current_steps": 33290, "total_steps": 61300, "loss": 0.3243, "lr": 2.5606392612686697e-05, "epoch": 5.430668841761827, "percentage": 54.31, "elapsed_time": "4:30:56", "remaining_time": "3:47:58", "throughput": 4419.29, "total_tokens": 71842528} {"current_steps": 33295, "total_steps": 61300, "loss": 0.2818, "lr": 2.5599276700138764e-05, "epoch": 5.431484502446982, "percentage": 54.31, "elapsed_time": "4:30:58", "remaining_time": "3:47:55", "throughput": 4419.34, "total_tokens": 71853440} {"current_steps": 33300, "total_steps": 61300, "loss": 0.3574, "lr": 2.5592160739010425e-05, "epoch": 5.432300163132137, "percentage": 54.32, "elapsed_time": "4:31:00", "remaining_time": "3:47:52", "throughput": 4419.38, "total_tokens": 71863040} {"current_steps": 33305, "total_steps": 61300, "loss": 0.318, "lr": 2.5585044729878526e-05, "epoch": 5.433115823817292, "percentage": 54.33, "elapsed_time": "4:31:03", "remaining_time": "3:47:50", "throughput": 4419.44, "total_tokens": 71873792} {"current_steps": 33310, "total_steps": 61300, "loss": 0.3568, "lr": 2.557792867331994e-05, "epoch": 5.433931484502447, "percentage": 54.34, "elapsed_time": "4:31:05", "remaining_time": "3:47:47", "throughput": 4419.51, "total_tokens": 71885856} {"current_steps": 33315, "total_steps": 61300, "loss": 0.3491, "lr": 2.5570812569911518e-05, "epoch": 5.434747145187602, "percentage": 54.35, "elapsed_time": "4:31:07", "remaining_time": "3:47:45", "throughput": 4419.56, "total_tokens": 71896416} {"current_steps": 33320, "total_steps": 61300, "loss": 0.3667, "lr": 2.556369642023013e-05, "epoch": 5.435562805872757, "percentage": 54.36, "elapsed_time": "4:31:09", "remaining_time": "3:47:42", "throughput": 4419.62, "total_tokens": 71906976} {"current_steps": 33325, "total_steps": 61300, "loss": 0.3215, "lr": 2.5556580224852655e-05, "epoch": 5.436378466557912, "percentage": 54.36, "elapsed_time": "4:31:11", "remaining_time": "3:47:39", "throughput": 4419.68, "total_tokens": 71916864} {"current_steps": 33330, "total_steps": 61300, "loss": 0.2954, "lr": 2.5549463984355964e-05, "epoch": 5.437194127243067, "percentage": 54.37, "elapsed_time": "4:31:14", "remaining_time": "3:47:37", "throughput": 4419.74, "total_tokens": 71928288} {"current_steps": 33335, "total_steps": 61300, "loss": 0.2653, "lr": 2.5542347699316933e-05, "epoch": 5.438009787928221, "percentage": 54.38, "elapsed_time": "4:31:16", "remaining_time": "3:47:34", "throughput": 4419.79, "total_tokens": 71939104} {"current_steps": 33340, "total_steps": 61300, "loss": 0.3329, "lr": 2.553523137031244e-05, "epoch": 5.438825448613377, "percentage": 54.39, "elapsed_time": "4:31:18", "remaining_time": "3:47:31", "throughput": 4419.85, "total_tokens": 71950208} {"current_steps": 33345, "total_steps": 61300, "loss": 0.3819, "lr": 2.5528114997919384e-05, "epoch": 5.439641109298532, "percentage": 54.4, "elapsed_time": "4:31:21", "remaining_time": "3:47:29", "throughput": 4419.91, "total_tokens": 71961312} {"current_steps": 33350, "total_steps": 61300, "loss": 0.3639, "lr": 2.5520998582714645e-05, "epoch": 5.440456769983687, "percentage": 54.4, "elapsed_time": "4:31:23", "remaining_time": "3:47:27", "throughput": 4419.97, "total_tokens": 71973248} {"current_steps": 33355, "total_steps": 61300, "loss": 0.3383, "lr": 2.5513882125275113e-05, "epoch": 5.441272430668842, "percentage": 54.41, "elapsed_time": "4:31:25", "remaining_time": "3:47:24", "throughput": 4420.03, "total_tokens": 71983648} {"current_steps": 33360, "total_steps": 61300, "loss": 0.362, "lr": 2.5506765626177697e-05, "epoch": 5.442088091353996, "percentage": 54.42, "elapsed_time": "4:31:28", "remaining_time": "3:47:21", "throughput": 4420.09, "total_tokens": 71995072} {"current_steps": 33365, "total_steps": 61300, "loss": 0.3401, "lr": 2.5499649085999282e-05, "epoch": 5.442903752039152, "percentage": 54.43, "elapsed_time": "4:31:30", "remaining_time": "3:47:19", "throughput": 4420.14, "total_tokens": 72006112} {"current_steps": 33370, "total_steps": 61300, "loss": 0.3088, "lr": 2.549253250531678e-05, "epoch": 5.443719412724307, "percentage": 54.44, "elapsed_time": "4:31:32", "remaining_time": "3:47:16", "throughput": 4420.21, "total_tokens": 72017184} {"current_steps": 33375, "total_steps": 61300, "loss": 0.352, "lr": 2.548541588470709e-05, "epoch": 5.444535073409462, "percentage": 54.45, "elapsed_time": "4:31:35", "remaining_time": "3:47:14", "throughput": 4420.26, "total_tokens": 72028352} {"current_steps": 33380, "total_steps": 61300, "loss": 0.3523, "lr": 2.547829922474713e-05, "epoch": 5.445350734094617, "percentage": 54.45, "elapsed_time": "4:31:37", "remaining_time": "3:47:11", "throughput": 4420.3, "total_tokens": 72037664} {"current_steps": 33385, "total_steps": 61300, "loss": 0.3304, "lr": 2.5471182526013805e-05, "epoch": 5.446166394779771, "percentage": 54.46, "elapsed_time": "4:31:39", "remaining_time": "3:47:08", "throughput": 4420.35, "total_tokens": 72049120} {"current_steps": 33390, "total_steps": 61300, "loss": 0.351, "lr": 2.546406578908403e-05, "epoch": 5.446982055464926, "percentage": 54.47, "elapsed_time": "4:31:41", "remaining_time": "3:47:06", "throughput": 4420.4, "total_tokens": 72059104} {"current_steps": 33395, "total_steps": 61300, "loss": 0.3377, "lr": 2.545694901453473e-05, "epoch": 5.447797716150082, "percentage": 54.48, "elapsed_time": "4:31:43", "remaining_time": "3:47:03", "throughput": 4420.46, "total_tokens": 72070048} {"current_steps": 33400, "total_steps": 61300, "loss": 0.304, "lr": 2.5449832202942832e-05, "epoch": 5.448613376835237, "percentage": 54.49, "elapsed_time": "4:31:46", "remaining_time": "3:47:00", "throughput": 4420.51, "total_tokens": 72080928} {"current_steps": 33405, "total_steps": 61300, "loss": 0.3724, "lr": 2.5442715354885237e-05, "epoch": 5.4494290375203915, "percentage": 54.49, "elapsed_time": "4:31:48", "remaining_time": "3:46:58", "throughput": 4420.56, "total_tokens": 72091488} {"current_steps": 33410, "total_steps": 61300, "loss": 0.3313, "lr": 2.5435598470938903e-05, "epoch": 5.450244698205546, "percentage": 54.5, "elapsed_time": "4:31:50", "remaining_time": "3:46:55", "throughput": 4420.61, "total_tokens": 72102528} {"current_steps": 33415, "total_steps": 61300, "loss": 0.3416, "lr": 2.5428481551680745e-05, "epoch": 5.451060358890701, "percentage": 54.51, "elapsed_time": "4:31:52", "remaining_time": "3:46:53", "throughput": 4420.67, "total_tokens": 72112992} {"current_steps": 33420, "total_steps": 61300, "loss": 0.3188, "lr": 2.5421364597687696e-05, "epoch": 5.451876019575856, "percentage": 54.52, "elapsed_time": "4:31:54", "remaining_time": "3:46:50", "throughput": 4420.73, "total_tokens": 72124096} {"current_steps": 33425, "total_steps": 61300, "loss": 0.3348, "lr": 2.5414247609536696e-05, "epoch": 5.452691680261012, "percentage": 54.53, "elapsed_time": "4:31:57", "remaining_time": "3:46:47", "throughput": 4420.78, "total_tokens": 72134624} {"current_steps": 33430, "total_steps": 61300, "loss": 0.3557, "lr": 2.5407130587804685e-05, "epoch": 5.4535073409461665, "percentage": 54.54, "elapsed_time": "4:31:59", "remaining_time": "3:46:45", "throughput": 4420.83, "total_tokens": 72145344} {"current_steps": 33435, "total_steps": 61300, "loss": 0.3174, "lr": 2.5400013533068594e-05, "epoch": 5.454323001631321, "percentage": 54.54, "elapsed_time": "4:32:01", "remaining_time": "3:46:42", "throughput": 4420.89, "total_tokens": 72157312} {"current_steps": 33440, "total_steps": 61300, "loss": 0.3654, "lr": 2.5392896445905385e-05, "epoch": 5.455138662316476, "percentage": 54.55, "elapsed_time": "4:32:04", "remaining_time": "3:46:40", "throughput": 4420.95, "total_tokens": 72168032} {"current_steps": 33445, "total_steps": 61300, "loss": 0.3558, "lr": 2.538577932689199e-05, "epoch": 5.455954323001631, "percentage": 54.56, "elapsed_time": "4:32:06", "remaining_time": "3:46:37", "throughput": 4420.99, "total_tokens": 72178944} {"current_steps": 33450, "total_steps": 61300, "loss": 0.3501, "lr": 2.537866217660537e-05, "epoch": 5.456769983686787, "percentage": 54.57, "elapsed_time": "4:32:08", "remaining_time": "3:46:34", "throughput": 4421.04, "total_tokens": 72188640} {"current_steps": 33455, "total_steps": 61300, "loss": 0.3295, "lr": 2.5371544995622472e-05, "epoch": 5.4575856443719415, "percentage": 54.58, "elapsed_time": "4:32:10", "remaining_time": "3:46:32", "throughput": 4421.09, "total_tokens": 72198720} {"current_steps": 33460, "total_steps": 61300, "loss": 0.3176, "lr": 2.536442778452025e-05, "epoch": 5.458401305057096, "percentage": 54.58, "elapsed_time": "4:32:12", "remaining_time": "3:46:29", "throughput": 4421.14, "total_tokens": 72208704} {"current_steps": 33465, "total_steps": 61300, "loss": 0.3239, "lr": 2.5357310543875667e-05, "epoch": 5.459216965742251, "percentage": 54.59, "elapsed_time": "4:32:14", "remaining_time": "3:46:26", "throughput": 4421.2, "total_tokens": 72218688} {"current_steps": 33470, "total_steps": 61300, "loss": 0.3624, "lr": 2.5350193274265678e-05, "epoch": 5.460032626427406, "percentage": 54.6, "elapsed_time": "4:32:17", "remaining_time": "3:46:24", "throughput": 4421.27, "total_tokens": 72230336} {"current_steps": 33475, "total_steps": 61300, "loss": 0.3502, "lr": 2.5343075976267234e-05, "epoch": 5.460848287112561, "percentage": 54.61, "elapsed_time": "4:32:19", "remaining_time": "3:46:21", "throughput": 4421.31, "total_tokens": 72241024} {"current_steps": 33480, "total_steps": 61300, "loss": 0.3459, "lr": 2.533595865045732e-05, "epoch": 5.4616639477977165, "percentage": 54.62, "elapsed_time": "4:32:21", "remaining_time": "3:46:18", "throughput": 4421.37, "total_tokens": 72252064} {"current_steps": 33485, "total_steps": 61300, "loss": 0.3242, "lr": 2.532884129741289e-05, "epoch": 5.462479608482871, "percentage": 54.62, "elapsed_time": "4:32:23", "remaining_time": "3:46:16", "throughput": 4421.43, "total_tokens": 72263616} {"current_steps": 33490, "total_steps": 61300, "loss": 0.3461, "lr": 2.5321723917710923e-05, "epoch": 5.463295269168026, "percentage": 54.63, "elapsed_time": "4:32:26", "remaining_time": "3:46:13", "throughput": 4421.49, "total_tokens": 72274784} {"current_steps": 33495, "total_steps": 61300, "loss": 0.3629, "lr": 2.531460651192838e-05, "epoch": 5.464110929853181, "percentage": 54.64, "elapsed_time": "4:32:28", "remaining_time": "3:46:11", "throughput": 4421.53, "total_tokens": 72284064} {"current_steps": 33500, "total_steps": 61300, "loss": 0.3475, "lr": 2.5307489080642227e-05, "epoch": 5.464926590538336, "percentage": 54.65, "elapsed_time": "4:32:30", "remaining_time": "3:46:08", "throughput": 4421.59, "total_tokens": 72295616} {"current_steps": 33505, "total_steps": 61300, "loss": 0.3542, "lr": 2.530037162442946e-05, "epoch": 5.465742251223491, "percentage": 54.66, "elapsed_time": "4:32:32", "remaining_time": "3:46:05", "throughput": 4421.64, "total_tokens": 72305952} {"current_steps": 33510, "total_steps": 61300, "loss": 0.3391, "lr": 2.529325414386704e-05, "epoch": 5.466557911908646, "percentage": 54.67, "elapsed_time": "4:32:34", "remaining_time": "3:46:03", "throughput": 4421.7, "total_tokens": 72316512} {"current_steps": 33515, "total_steps": 61300, "loss": 0.3389, "lr": 2.5286136639531956e-05, "epoch": 5.467373572593801, "percentage": 54.67, "elapsed_time": "4:32:37", "remaining_time": "3:46:00", "throughput": 4421.75, "total_tokens": 72327328} {"current_steps": 33520, "total_steps": 61300, "loss": 0.3144, "lr": 2.527901911200118e-05, "epoch": 5.468189233278956, "percentage": 54.68, "elapsed_time": "4:32:39", "remaining_time": "3:45:58", "throughput": 4421.8, "total_tokens": 72338560} {"current_steps": 33525, "total_steps": 61300, "loss": 0.3398, "lr": 2.5271901561851703e-05, "epoch": 5.469004893964111, "percentage": 54.69, "elapsed_time": "4:32:41", "remaining_time": "3:45:55", "throughput": 4421.85, "total_tokens": 72349312} {"current_steps": 33530, "total_steps": 61300, "loss": 0.3453, "lr": 2.52647839896605e-05, "epoch": 5.4698205546492655, "percentage": 54.7, "elapsed_time": "4:32:44", "remaining_time": "3:45:53", "throughput": 4421.9, "total_tokens": 72361024} {"current_steps": 33535, "total_steps": 61300, "loss": 0.3481, "lr": 2.525766639600457e-05, "epoch": 5.470636215334421, "percentage": 54.71, "elapsed_time": "4:32:46", "remaining_time": "3:45:50", "throughput": 4421.96, "total_tokens": 72372352} {"current_steps": 33540, "total_steps": 61300, "loss": 0.3281, "lr": 2.525054878146089e-05, "epoch": 5.471451876019576, "percentage": 54.71, "elapsed_time": "4:32:48", "remaining_time": "3:45:47", "throughput": 4422.01, "total_tokens": 72383136} {"current_steps": 33545, "total_steps": 61300, "loss": 0.3226, "lr": 2.5243431146606456e-05, "epoch": 5.472267536704731, "percentage": 54.72, "elapsed_time": "4:32:50", "remaining_time": "3:45:45", "throughput": 4422.05, "total_tokens": 72392224} {"current_steps": 33550, "total_steps": 61300, "loss": 0.3433, "lr": 2.5236313492018254e-05, "epoch": 5.473083197389886, "percentage": 54.73, "elapsed_time": "4:32:52", "remaining_time": "3:45:42", "throughput": 4422.11, "total_tokens": 72402176} {"current_steps": 33555, "total_steps": 61300, "loss": 0.3164, "lr": 2.5229195818273284e-05, "epoch": 5.4738988580750405, "percentage": 54.74, "elapsed_time": "4:32:55", "remaining_time": "3:45:39", "throughput": 4422.17, "total_tokens": 72413792} {"current_steps": 33560, "total_steps": 61300, "loss": 0.329, "lr": 2.5222078125948534e-05, "epoch": 5.474714518760196, "percentage": 54.75, "elapsed_time": "4:32:57", "remaining_time": "3:45:37", "throughput": 4422.24, "total_tokens": 72425792} {"current_steps": 33565, "total_steps": 61300, "loss": 0.3542, "lr": 2.5214960415621007e-05, "epoch": 5.475530179445351, "percentage": 54.76, "elapsed_time": "4:32:59", "remaining_time": "3:45:34", "throughput": 4422.3, "total_tokens": 72436864} {"current_steps": 33570, "total_steps": 61300, "loss": 0.3379, "lr": 2.5207842687867705e-05, "epoch": 5.476345840130506, "percentage": 54.76, "elapsed_time": "4:33:02", "remaining_time": "3:45:32", "throughput": 4422.36, "total_tokens": 72448096} {"current_steps": 33575, "total_steps": 61300, "loss": 0.3562, "lr": 2.5200724943265614e-05, "epoch": 5.477161500815661, "percentage": 54.77, "elapsed_time": "4:33:04", "remaining_time": "3:45:29", "throughput": 4422.41, "total_tokens": 72459776} {"current_steps": 33580, "total_steps": 61300, "loss": 0.3009, "lr": 2.519360718239174e-05, "epoch": 5.4779771615008155, "percentage": 54.78, "elapsed_time": "4:33:06", "remaining_time": "3:45:27", "throughput": 4422.46, "total_tokens": 72470528} {"current_steps": 33585, "total_steps": 61300, "loss": 0.3251, "lr": 2.5186489405823087e-05, "epoch": 5.47879282218597, "percentage": 54.79, "elapsed_time": "4:33:09", "remaining_time": "3:45:24", "throughput": 4422.52, "total_tokens": 72482144} {"current_steps": 33590, "total_steps": 61300, "loss": 0.3549, "lr": 2.517937161413666e-05, "epoch": 5.479608482871126, "percentage": 54.8, "elapsed_time": "4:33:11", "remaining_time": "3:45:22", "throughput": 4422.58, "total_tokens": 72493504} {"current_steps": 33595, "total_steps": 61300, "loss": 0.3323, "lr": 2.517225380790946e-05, "epoch": 5.480424143556281, "percentage": 54.8, "elapsed_time": "4:33:13", "remaining_time": "3:45:19", "throughput": 4422.63, "total_tokens": 72503904} {"current_steps": 33600, "total_steps": 61300, "loss": 0.3321, "lr": 2.5165135987718486e-05, "epoch": 5.481239804241436, "percentage": 54.81, "elapsed_time": "4:33:16", "remaining_time": "3:45:16", "throughput": 4422.68, "total_tokens": 72514560} {"current_steps": 33605, "total_steps": 61300, "loss": 0.3147, "lr": 2.515801815414075e-05, "epoch": 5.4820554649265905, "percentage": 54.82, "elapsed_time": "4:33:18", "remaining_time": "3:45:14", "throughput": 4422.73, "total_tokens": 72526080} {"current_steps": 33610, "total_steps": 61300, "loss": 0.3624, "lr": 2.5150900307753267e-05, "epoch": 5.482871125611745, "percentage": 54.83, "elapsed_time": "4:33:20", "remaining_time": "3:45:11", "throughput": 4422.79, "total_tokens": 72536992} {"current_steps": 33615, "total_steps": 61300, "loss": 0.3233, "lr": 2.5143782449133036e-05, "epoch": 5.4836867862969, "percentage": 54.84, "elapsed_time": "4:33:23", "remaining_time": "3:45:09", "throughput": 4422.86, "total_tokens": 72548224} {"current_steps": 33620, "total_steps": 61300, "loss": 0.3571, "lr": 2.5136664578857072e-05, "epoch": 5.484502446982056, "percentage": 54.85, "elapsed_time": "4:33:25", "remaining_time": "3:45:06", "throughput": 4422.92, "total_tokens": 72559744} {"current_steps": 33625, "total_steps": 61300, "loss": 0.3558, "lr": 2.5129546697502382e-05, "epoch": 5.485318107667211, "percentage": 54.85, "elapsed_time": "4:33:27", "remaining_time": "3:45:04", "throughput": 4422.98, "total_tokens": 72570528} {"current_steps": 33630, "total_steps": 61300, "loss": 0.3316, "lr": 2.512242880564598e-05, "epoch": 5.486133768352365, "percentage": 54.86, "elapsed_time": "4:33:30", "remaining_time": "3:45:01", "throughput": 4423.04, "total_tokens": 72582112} {"current_steps": 33635, "total_steps": 61300, "loss": 0.3316, "lr": 2.5115310903864874e-05, "epoch": 5.48694942903752, "percentage": 54.87, "elapsed_time": "4:33:32", "remaining_time": "3:44:59", "throughput": 4423.09, "total_tokens": 72592736} {"current_steps": 33640, "total_steps": 61300, "loss": 0.3338, "lr": 2.510819299273609e-05, "epoch": 5.487765089722675, "percentage": 54.88, "elapsed_time": "4:33:34", "remaining_time": "3:44:56", "throughput": 4423.15, "total_tokens": 72604096} {"current_steps": 33645, "total_steps": 61300, "loss": 0.3342, "lr": 2.510107507283663e-05, "epoch": 5.488580750407831, "percentage": 54.89, "elapsed_time": "4:33:36", "remaining_time": "3:44:53", "throughput": 4423.2, "total_tokens": 72614560} {"current_steps": 33650, "total_steps": 61300, "loss": 0.3075, "lr": 2.5093957144743507e-05, "epoch": 5.489396411092986, "percentage": 54.89, "elapsed_time": "4:33:39", "remaining_time": "3:44:51", "throughput": 4423.26, "total_tokens": 72625536} {"current_steps": 33655, "total_steps": 61300, "loss": 0.3501, "lr": 2.5086839209033747e-05, "epoch": 5.49021207177814, "percentage": 54.9, "elapsed_time": "4:33:41", "remaining_time": "3:44:48", "throughput": 4423.31, "total_tokens": 72636384} {"current_steps": 33660, "total_steps": 61300, "loss": 0.3694, "lr": 2.507972126628435e-05, "epoch": 5.491027732463295, "percentage": 54.91, "elapsed_time": "4:33:43", "remaining_time": "3:44:46", "throughput": 4423.35, "total_tokens": 72646272} {"current_steps": 33665, "total_steps": 61300, "loss": 0.3395, "lr": 2.5072603317072353e-05, "epoch": 5.49184339314845, "percentage": 54.92, "elapsed_time": "4:33:45", "remaining_time": "3:44:43", "throughput": 4423.4, "total_tokens": 72657184} {"current_steps": 33670, "total_steps": 61300, "loss": 0.3162, "lr": 2.5065485361974754e-05, "epoch": 5.492659053833605, "percentage": 54.93, "elapsed_time": "4:33:47", "remaining_time": "3:44:41", "throughput": 4423.46, "total_tokens": 72668544} {"current_steps": 33675, "total_steps": 61300, "loss": 0.3076, "lr": 2.505836740156859e-05, "epoch": 5.493474714518761, "percentage": 54.93, "elapsed_time": "4:33:50", "remaining_time": "3:44:38", "throughput": 4423.51, "total_tokens": 72679104} {"current_steps": 33680, "total_steps": 61300, "loss": 0.3626, "lr": 2.5051249436430862e-05, "epoch": 5.494290375203915, "percentage": 54.94, "elapsed_time": "4:33:52", "remaining_time": "3:44:35", "throughput": 4423.56, "total_tokens": 72689856} {"current_steps": 33685, "total_steps": 61300, "loss": 0.3743, "lr": 2.5044131467138597e-05, "epoch": 5.49510603588907, "percentage": 54.95, "elapsed_time": "4:33:54", "remaining_time": "3:44:33", "throughput": 4423.63, "total_tokens": 72701312} {"current_steps": 33690, "total_steps": 61300, "loss": 0.3026, "lr": 2.5037013494268814e-05, "epoch": 5.495921696574225, "percentage": 54.96, "elapsed_time": "4:33:56", "remaining_time": "3:44:30", "throughput": 4423.67, "total_tokens": 72711808} {"current_steps": 33695, "total_steps": 61300, "loss": 0.2975, "lr": 2.502989551839852e-05, "epoch": 5.49673735725938, "percentage": 54.97, "elapsed_time": "4:33:59", "remaining_time": "3:44:28", "throughput": 4423.72, "total_tokens": 72722528} {"current_steps": 33700, "total_steps": 61300, "loss": 0.3949, "lr": 2.5022777540104752e-05, "epoch": 5.497553017944535, "percentage": 54.98, "elapsed_time": "4:34:01", "remaining_time": "3:44:25", "throughput": 4423.79, "total_tokens": 72733408} {"current_steps": 33705, "total_steps": 61300, "loss": 0.3583, "lr": 2.5015659559964516e-05, "epoch": 5.49836867862969, "percentage": 54.98, "elapsed_time": "4:34:03", "remaining_time": "3:44:22", "throughput": 4423.84, "total_tokens": 72744544} {"current_steps": 33710, "total_steps": 61300, "loss": 0.3314, "lr": 2.5008541578554838e-05, "epoch": 5.499184339314845, "percentage": 54.99, "elapsed_time": "4:34:06", "remaining_time": "3:44:20", "throughput": 4423.9, "total_tokens": 72755712} {"current_steps": 33715, "total_steps": 61300, "loss": 0.31, "lr": 2.5001423596452738e-05, "epoch": 5.5, "percentage": 55.0, "elapsed_time": "4:34:08", "remaining_time": "3:44:17", "throughput": 4423.95, "total_tokens": 72765696} {"current_steps": 33715, "total_steps": 61300, "eval_loss": 0.3388349115848541, "epoch": 5.5, "percentage": 55.0, "elapsed_time": "4:36:19", "remaining_time": "3:46:05", "throughput": 4388.77, "total_tokens": 72765696} {"current_steps": 33720, "total_steps": 61300, "loss": 0.326, "lr": 2.4994305614235228e-05, "epoch": 5.500815660685155, "percentage": 55.01, "elapsed_time": "4:36:23", "remaining_time": "3:46:03", "throughput": 4388.55, "total_tokens": 72776576} {"current_steps": 33725, "total_steps": 61300, "loss": 0.3159, "lr": 2.498718763247934e-05, "epoch": 5.50163132137031, "percentage": 55.02, "elapsed_time": "4:36:25", "remaining_time": "3:46:00", "throughput": 4388.61, "total_tokens": 72786112} {"current_steps": 33730, "total_steps": 61300, "loss": 0.3596, "lr": 2.4980069651762085e-05, "epoch": 5.502446982055465, "percentage": 55.02, "elapsed_time": "4:36:27", "remaining_time": "3:45:58", "throughput": 4388.67, "total_tokens": 72796384} {"current_steps": 33735, "total_steps": 61300, "loss": 0.2989, "lr": 2.4972951672660487e-05, "epoch": 5.50326264274062, "percentage": 55.03, "elapsed_time": "4:36:29", "remaining_time": "3:45:55", "throughput": 4388.73, "total_tokens": 72806720} {"current_steps": 33740, "total_steps": 61300, "loss": 0.3809, "lr": 2.4965833695751563e-05, "epoch": 5.504078303425775, "percentage": 55.04, "elapsed_time": "4:36:31", "remaining_time": "3:45:52", "throughput": 4388.78, "total_tokens": 72817408} {"current_steps": 33745, "total_steps": 61300, "loss": 0.3483, "lr": 2.4958715721612335e-05, "epoch": 5.50489396411093, "percentage": 55.05, "elapsed_time": "4:36:33", "remaining_time": "3:45:50", "throughput": 4388.84, "total_tokens": 72828096} {"current_steps": 33750, "total_steps": 61300, "loss": 0.3451, "lr": 2.495159775081982e-05, "epoch": 5.505709624796085, "percentage": 55.06, "elapsed_time": "4:36:36", "remaining_time": "3:45:47", "throughput": 4388.91, "total_tokens": 72839040} {"current_steps": 33755, "total_steps": 61300, "loss": 0.3194, "lr": 2.4944479783951037e-05, "epoch": 5.506525285481239, "percentage": 55.07, "elapsed_time": "4:36:38", "remaining_time": "3:45:44", "throughput": 4388.97, "total_tokens": 72849728} {"current_steps": 33760, "total_steps": 61300, "loss": 0.3362, "lr": 2.4937361821583e-05, "epoch": 5.507340946166395, "percentage": 55.07, "elapsed_time": "4:36:40", "remaining_time": "3:45:41", "throughput": 4389.02, "total_tokens": 72859872} {"current_steps": 33765, "total_steps": 61300, "loss": 0.3378, "lr": 2.4930243864292736e-05, "epoch": 5.50815660685155, "percentage": 55.08, "elapsed_time": "4:36:42", "remaining_time": "3:45:39", "throughput": 4389.08, "total_tokens": 72871648} {"current_steps": 33770, "total_steps": 61300, "loss": 0.3266, "lr": 2.492312591265726e-05, "epoch": 5.508972267536705, "percentage": 55.09, "elapsed_time": "4:36:45", "remaining_time": "3:45:37", "throughput": 4389.14, "total_tokens": 72883136} {"current_steps": 33775, "total_steps": 61300, "loss": 0.3624, "lr": 2.4916007967253576e-05, "epoch": 5.50978792822186, "percentage": 55.1, "elapsed_time": "4:36:47", "remaining_time": "3:45:34", "throughput": 4389.18, "total_tokens": 72892896} {"current_steps": 33780, "total_steps": 61300, "loss": 0.3381, "lr": 2.490889002865872e-05, "epoch": 5.510603588907014, "percentage": 55.11, "elapsed_time": "4:36:49", "remaining_time": "3:45:31", "throughput": 4389.24, "total_tokens": 72904576} {"current_steps": 33785, "total_steps": 61300, "loss": 0.3404, "lr": 2.4901772097449703e-05, "epoch": 5.511419249592169, "percentage": 55.11, "elapsed_time": "4:36:51", "remaining_time": "3:45:28", "throughput": 4389.29, "total_tokens": 72914016} {"current_steps": 33790, "total_steps": 61300, "loss": 0.3578, "lr": 2.4894654174203535e-05, "epoch": 5.512234910277325, "percentage": 55.12, "elapsed_time": "4:36:54", "remaining_time": "3:45:26", "throughput": 4389.35, "total_tokens": 72925152} {"current_steps": 33795, "total_steps": 61300, "loss": 0.3223, "lr": 2.488753625949723e-05, "epoch": 5.51305057096248, "percentage": 55.13, "elapsed_time": "4:36:56", "remaining_time": "3:45:23", "throughput": 4389.39, "total_tokens": 72936320} {"current_steps": 33800, "total_steps": 61300, "loss": 0.3179, "lr": 2.488041835390781e-05, "epoch": 5.513866231647635, "percentage": 55.14, "elapsed_time": "4:36:58", "remaining_time": "3:45:21", "throughput": 4389.45, "total_tokens": 72946848} {"current_steps": 33805, "total_steps": 61300, "loss": 0.3479, "lr": 2.4873300458012285e-05, "epoch": 5.514681892332789, "percentage": 55.15, "elapsed_time": "4:37:01", "remaining_time": "3:45:18", "throughput": 4389.51, "total_tokens": 72958208} {"current_steps": 33810, "total_steps": 61300, "loss": 0.3762, "lr": 2.486618257238767e-05, "epoch": 5.515497553017944, "percentage": 55.15, "elapsed_time": "4:37:03", "remaining_time": "3:45:15", "throughput": 4389.56, "total_tokens": 72969152} {"current_steps": 33815, "total_steps": 61300, "loss": 0.3395, "lr": 2.4859064697610977e-05, "epoch": 5.5163132137031, "percentage": 55.16, "elapsed_time": "4:37:05", "remaining_time": "3:45:13", "throughput": 4389.63, "total_tokens": 72981664} {"current_steps": 33820, "total_steps": 61300, "loss": 0.3248, "lr": 2.485194683425921e-05, "epoch": 5.517128874388255, "percentage": 55.17, "elapsed_time": "4:37:08", "remaining_time": "3:45:10", "throughput": 4389.68, "total_tokens": 72992224} {"current_steps": 33825, "total_steps": 61300, "loss": 0.3707, "lr": 2.4844828982909388e-05, "epoch": 5.5179445350734095, "percentage": 55.18, "elapsed_time": "4:37:10", "remaining_time": "3:45:08", "throughput": 4389.74, "total_tokens": 73003712} {"current_steps": 33830, "total_steps": 61300, "loss": 0.3224, "lr": 2.4837711144138514e-05, "epoch": 5.518760195758564, "percentage": 55.19, "elapsed_time": "4:37:12", "remaining_time": "3:45:05", "throughput": 4389.79, "total_tokens": 73015328} {"current_steps": 33835, "total_steps": 61300, "loss": 0.3449, "lr": 2.48305933185236e-05, "epoch": 5.519575856443719, "percentage": 55.2, "elapsed_time": "4:37:15", "remaining_time": "3:45:03", "throughput": 4389.85, "total_tokens": 73026304} {"current_steps": 33840, "total_steps": 61300, "loss": 0.3532, "lr": 2.4823475506641646e-05, "epoch": 5.520391517128875, "percentage": 55.2, "elapsed_time": "4:37:17", "remaining_time": "3:45:01", "throughput": 4389.91, "total_tokens": 73038688} {"current_steps": 33845, "total_steps": 61300, "loss": 0.3214, "lr": 2.481635770906967e-05, "epoch": 5.52120717781403, "percentage": 55.21, "elapsed_time": "4:37:20", "remaining_time": "3:44:58", "throughput": 4389.97, "total_tokens": 73049824} {"current_steps": 33850, "total_steps": 61300, "loss": 0.3115, "lr": 2.4809239926384664e-05, "epoch": 5.5220228384991845, "percentage": 55.22, "elapsed_time": "4:37:22", "remaining_time": "3:44:56", "throughput": 4390.03, "total_tokens": 73061760} {"current_steps": 33855, "total_steps": 61300, "loss": 0.3429, "lr": 2.480212215916364e-05, "epoch": 5.522838499184339, "percentage": 55.23, "elapsed_time": "4:37:24", "remaining_time": "3:44:53", "throughput": 4390.09, "total_tokens": 73072704} {"current_steps": 33860, "total_steps": 61300, "loss": 0.35, "lr": 2.4795004407983593e-05, "epoch": 5.523654159869494, "percentage": 55.24, "elapsed_time": "4:37:27", "remaining_time": "3:44:50", "throughput": 4390.16, "total_tokens": 73084032} {"current_steps": 33865, "total_steps": 61300, "loss": 0.3556, "lr": 2.4787886673421536e-05, "epoch": 5.524469820554649, "percentage": 55.24, "elapsed_time": "4:37:29", "remaining_time": "3:44:48", "throughput": 4390.22, "total_tokens": 73094592} {"current_steps": 33870, "total_steps": 61300, "loss": 0.3254, "lr": 2.4780768956054457e-05, "epoch": 5.525285481239804, "percentage": 55.25, "elapsed_time": "4:37:31", "remaining_time": "3:44:45", "throughput": 4390.28, "total_tokens": 73106304} {"current_steps": 33875, "total_steps": 61300, "loss": 0.3484, "lr": 2.477365125645936e-05, "epoch": 5.5261011419249595, "percentage": 55.26, "elapsed_time": "4:37:34", "remaining_time": "3:44:43", "throughput": 4390.34, "total_tokens": 73117088} {"current_steps": 33880, "total_steps": 61300, "loss": 0.3279, "lr": 2.4766533575213242e-05, "epoch": 5.526916802610114, "percentage": 55.27, "elapsed_time": "4:37:36", "remaining_time": "3:44:40", "throughput": 4390.4, "total_tokens": 73127776} {"current_steps": 33885, "total_steps": 61300, "loss": 0.3099, "lr": 2.4759415912893096e-05, "epoch": 5.527732463295269, "percentage": 55.28, "elapsed_time": "4:37:38", "remaining_time": "3:44:37", "throughput": 4390.47, "total_tokens": 73139904} {"current_steps": 33890, "total_steps": 61300, "loss": 0.2827, "lr": 2.4752298270075918e-05, "epoch": 5.528548123980424, "percentage": 55.29, "elapsed_time": "4:37:41", "remaining_time": "3:44:35", "throughput": 4390.52, "total_tokens": 73150688} {"current_steps": 33895, "total_steps": 61300, "loss": 0.3658, "lr": 2.47451806473387e-05, "epoch": 5.529363784665579, "percentage": 55.29, "elapsed_time": "4:37:43", "remaining_time": "3:44:32", "throughput": 4390.58, "total_tokens": 73160576} {"current_steps": 33900, "total_steps": 61300, "loss": 0.3437, "lr": 2.4738063045258415e-05, "epoch": 5.5301794453507345, "percentage": 55.3, "elapsed_time": "4:37:45", "remaining_time": "3:44:29", "throughput": 4390.63, "total_tokens": 73170272} {"current_steps": 33905, "total_steps": 61300, "loss": 0.3263, "lr": 2.4730945464412085e-05, "epoch": 5.530995106035889, "percentage": 55.31, "elapsed_time": "4:37:47", "remaining_time": "3:44:27", "throughput": 4390.69, "total_tokens": 73181760} {"current_steps": 33910, "total_steps": 61300, "loss": 0.2882, "lr": 2.472382790537668e-05, "epoch": 5.531810766721044, "percentage": 55.32, "elapsed_time": "4:37:49", "remaining_time": "3:44:24", "throughput": 4390.74, "total_tokens": 73192096} {"current_steps": 33915, "total_steps": 61300, "loss": 0.3086, "lr": 2.4716710368729187e-05, "epoch": 5.532626427406199, "percentage": 55.33, "elapsed_time": "4:37:51", "remaining_time": "3:44:21", "throughput": 4390.78, "total_tokens": 73201408} {"current_steps": 33920, "total_steps": 61300, "loss": 0.3207, "lr": 2.4709592855046587e-05, "epoch": 5.533442088091354, "percentage": 55.33, "elapsed_time": "4:37:53", "remaining_time": "3:44:18", "throughput": 4390.84, "total_tokens": 73211936} {"current_steps": 33925, "total_steps": 61300, "loss": 0.321, "lr": 2.4702475364905864e-05, "epoch": 5.5342577487765094, "percentage": 55.34, "elapsed_time": "4:37:56", "remaining_time": "3:44:16", "throughput": 4390.91, "total_tokens": 73223392} {"current_steps": 33930, "total_steps": 61300, "loss": 0.3466, "lr": 2.4695357898883998e-05, "epoch": 5.535073409461664, "percentage": 55.35, "elapsed_time": "4:37:58", "remaining_time": "3:44:13", "throughput": 4390.96, "total_tokens": 73233920} {"current_steps": 33935, "total_steps": 61300, "loss": 0.3202, "lr": 2.4688240457557967e-05, "epoch": 5.535889070146819, "percentage": 55.36, "elapsed_time": "4:38:00", "remaining_time": "3:44:11", "throughput": 4391.01, "total_tokens": 73244288} {"current_steps": 33940, "total_steps": 61300, "loss": 0.3003, "lr": 2.4681123041504746e-05, "epoch": 5.536704730831974, "percentage": 55.37, "elapsed_time": "4:38:02", "remaining_time": "3:44:08", "throughput": 4391.08, "total_tokens": 73256256} {"current_steps": 33945, "total_steps": 61300, "loss": 0.3702, "lr": 2.46740056513013e-05, "epoch": 5.537520391517129, "percentage": 55.38, "elapsed_time": "4:38:05", "remaining_time": "3:44:06", "throughput": 4391.13, "total_tokens": 73267264} {"current_steps": 33950, "total_steps": 61300, "loss": 0.3311, "lr": 2.466688828752462e-05, "epoch": 5.5383360522022835, "percentage": 55.38, "elapsed_time": "4:38:07", "remaining_time": "3:44:03", "throughput": 4391.2, "total_tokens": 73279168} {"current_steps": 33955, "total_steps": 61300, "loss": 0.3264, "lr": 2.4659770950751666e-05, "epoch": 5.539151712887438, "percentage": 55.39, "elapsed_time": "4:38:09", "remaining_time": "3:44:00", "throughput": 4391.24, "total_tokens": 73288128} {"current_steps": 33960, "total_steps": 61300, "loss": 0.3516, "lr": 2.4652653641559404e-05, "epoch": 5.539967373572594, "percentage": 55.4, "elapsed_time": "4:38:11", "remaining_time": "3:43:57", "throughput": 4391.29, "total_tokens": 73297472} {"current_steps": 33965, "total_steps": 61300, "loss": 0.3174, "lr": 2.46455363605248e-05, "epoch": 5.540783034257749, "percentage": 55.41, "elapsed_time": "4:38:14", "remaining_time": "3:43:55", "throughput": 4391.37, "total_tokens": 73309504} {"current_steps": 33970, "total_steps": 61300, "loss": 0.3334, "lr": 2.4638419108224817e-05, "epoch": 5.541598694942904, "percentage": 55.42, "elapsed_time": "4:38:16", "remaining_time": "3:43:52", "throughput": 4391.42, "total_tokens": 73320192} {"current_steps": 33975, "total_steps": 61300, "loss": 0.3042, "lr": 2.4631301885236415e-05, "epoch": 5.5424143556280585, "percentage": 55.42, "elapsed_time": "4:38:18", "remaining_time": "3:43:50", "throughput": 4391.48, "total_tokens": 73331168} {"current_steps": 33980, "total_steps": 61300, "loss": 0.3086, "lr": 2.4624184692136554e-05, "epoch": 5.543230016313213, "percentage": 55.43, "elapsed_time": "4:38:20", "remaining_time": "3:43:47", "throughput": 4391.54, "total_tokens": 73342944} {"current_steps": 33985, "total_steps": 61300, "loss": 0.3727, "lr": 2.4617067529502188e-05, "epoch": 5.544045676998369, "percentage": 55.44, "elapsed_time": "4:38:23", "remaining_time": "3:43:45", "throughput": 4391.6, "total_tokens": 73353920} {"current_steps": 33990, "total_steps": 61300, "loss": 0.3581, "lr": 2.460995039791027e-05, "epoch": 5.544861337683524, "percentage": 55.45, "elapsed_time": "4:38:25", "remaining_time": "3:43:42", "throughput": 4391.68, "total_tokens": 73366432} {"current_steps": 33995, "total_steps": 61300, "loss": 0.3306, "lr": 2.4602833297937755e-05, "epoch": 5.545676998368679, "percentage": 55.46, "elapsed_time": "4:38:28", "remaining_time": "3:43:40", "throughput": 4391.73, "total_tokens": 73377824} {"current_steps": 34000, "total_steps": 61300, "loss": 0.3365, "lr": 2.4595716230161586e-05, "epoch": 5.5464926590538335, "percentage": 55.46, "elapsed_time": "4:38:30", "remaining_time": "3:43:37", "throughput": 4391.77, "total_tokens": 73387840} {"current_steps": 34005, "total_steps": 61300, "loss": 0.3262, "lr": 2.45885991951587e-05, "epoch": 5.547308319738988, "percentage": 55.47, "elapsed_time": "4:38:32", "remaining_time": "3:43:34", "throughput": 4391.83, "total_tokens": 73398304} {"current_steps": 34010, "total_steps": 61300, "loss": 0.3338, "lr": 2.458148219350606e-05, "epoch": 5.548123980424144, "percentage": 55.48, "elapsed_time": "4:38:34", "remaining_time": "3:43:32", "throughput": 4391.89, "total_tokens": 73410016} {"current_steps": 34015, "total_steps": 61300, "loss": 0.3262, "lr": 2.45743652257806e-05, "epoch": 5.548939641109299, "percentage": 55.49, "elapsed_time": "4:38:37", "remaining_time": "3:43:29", "throughput": 4391.95, "total_tokens": 73420960} {"current_steps": 34020, "total_steps": 61300, "loss": 0.3255, "lr": 2.4567248292559253e-05, "epoch": 5.549755301794454, "percentage": 55.5, "elapsed_time": "4:38:39", "remaining_time": "3:43:26", "throughput": 4392.01, "total_tokens": 73431712} {"current_steps": 34025, "total_steps": 61300, "loss": 0.3265, "lr": 2.4560131394418958e-05, "epoch": 5.5505709624796085, "percentage": 55.51, "elapsed_time": "4:38:41", "remaining_time": "3:43:24", "throughput": 4392.05, "total_tokens": 73441376} {"current_steps": 34030, "total_steps": 61300, "loss": 0.3829, "lr": 2.4553014531936632e-05, "epoch": 5.551386623164763, "percentage": 55.51, "elapsed_time": "4:38:43", "remaining_time": "3:43:21", "throughput": 4392.09, "total_tokens": 73450752} {"current_steps": 34035, "total_steps": 61300, "loss": 0.3077, "lr": 2.4545897705689223e-05, "epoch": 5.552202283849918, "percentage": 55.52, "elapsed_time": "4:38:45", "remaining_time": "3:43:18", "throughput": 4392.14, "total_tokens": 73461952} {"current_steps": 34040, "total_steps": 61300, "loss": 0.3371, "lr": 2.4538780916253657e-05, "epoch": 5.553017944535073, "percentage": 55.53, "elapsed_time": "4:38:47", "remaining_time": "3:43:16", "throughput": 4392.2, "total_tokens": 73472064} {"current_steps": 34045, "total_steps": 61300, "loss": 0.3491, "lr": 2.4531664164206843e-05, "epoch": 5.553833605220229, "percentage": 55.54, "elapsed_time": "4:38:50", "remaining_time": "3:43:13", "throughput": 4392.25, "total_tokens": 73483200} {"current_steps": 34050, "total_steps": 61300, "loss": 0.3335, "lr": 2.4524547450125713e-05, "epoch": 5.554649265905383, "percentage": 55.55, "elapsed_time": "4:38:52", "remaining_time": "3:43:10", "throughput": 4392.31, "total_tokens": 73494080} {"current_steps": 34055, "total_steps": 61300, "loss": 0.3358, "lr": 2.4517430774587174e-05, "epoch": 5.555464926590538, "percentage": 55.55, "elapsed_time": "4:38:54", "remaining_time": "3:43:08", "throughput": 4392.36, "total_tokens": 73503616} {"current_steps": 34060, "total_steps": 61300, "loss": 0.3459, "lr": 2.4510314138168146e-05, "epoch": 5.556280587275693, "percentage": 55.56, "elapsed_time": "4:38:56", "remaining_time": "3:43:05", "throughput": 4392.43, "total_tokens": 73515328} {"current_steps": 34065, "total_steps": 61300, "loss": 0.3265, "lr": 2.4503197541445545e-05, "epoch": 5.557096247960848, "percentage": 55.57, "elapsed_time": "4:38:59", "remaining_time": "3:43:03", "throughput": 4392.49, "total_tokens": 73527520} {"current_steps": 34070, "total_steps": 61300, "loss": 0.3449, "lr": 2.4496080984996264e-05, "epoch": 5.557911908646004, "percentage": 55.58, "elapsed_time": "4:39:01", "remaining_time": "3:43:00", "throughput": 4392.55, "total_tokens": 73538688} {"current_steps": 34075, "total_steps": 61300, "loss": 0.3585, "lr": 2.448896446939722e-05, "epoch": 5.558727569331158, "percentage": 55.59, "elapsed_time": "4:39:03", "remaining_time": "3:42:57", "throughput": 4392.6, "total_tokens": 73548544} {"current_steps": 34080, "total_steps": 61300, "loss": 0.3809, "lr": 2.4481847995225307e-05, "epoch": 5.559543230016313, "percentage": 55.6, "elapsed_time": "4:39:06", "remaining_time": "3:42:55", "throughput": 4392.66, "total_tokens": 73559712} {"current_steps": 34085, "total_steps": 61300, "loss": 0.3457, "lr": 2.4474731563057426e-05, "epoch": 5.560358890701468, "percentage": 55.6, "elapsed_time": "4:39:08", "remaining_time": "3:42:52", "throughput": 4392.72, "total_tokens": 73570304} {"current_steps": 34090, "total_steps": 61300, "loss": 0.3093, "lr": 2.446761517347046e-05, "epoch": 5.561174551386623, "percentage": 55.61, "elapsed_time": "4:39:10", "remaining_time": "3:42:49", "throughput": 4392.77, "total_tokens": 73581056} {"current_steps": 34095, "total_steps": 61300, "loss": 0.309, "lr": 2.446049882704132e-05, "epoch": 5.561990212071779, "percentage": 55.62, "elapsed_time": "4:39:12", "remaining_time": "3:42:47", "throughput": 4392.83, "total_tokens": 73592064} {"current_steps": 34100, "total_steps": 61300, "loss": 0.3425, "lr": 2.4453382524346882e-05, "epoch": 5.562805872756933, "percentage": 55.63, "elapsed_time": "4:39:15", "remaining_time": "3:42:44", "throughput": 4392.88, "total_tokens": 73603296} {"current_steps": 34105, "total_steps": 61300, "loss": 0.3582, "lr": 2.444626626596403e-05, "epoch": 5.563621533442088, "percentage": 55.64, "elapsed_time": "4:39:17", "remaining_time": "3:42:41", "throughput": 4392.92, "total_tokens": 73612704} {"current_steps": 34110, "total_steps": 61300, "loss": 0.3484, "lr": 2.4439150052469644e-05, "epoch": 5.564437194127243, "percentage": 55.64, "elapsed_time": "4:39:19", "remaining_time": "3:42:39", "throughput": 4392.97, "total_tokens": 73623168} {"current_steps": 34115, "total_steps": 61300, "loss": 0.3154, "lr": 2.4432033884440585e-05, "epoch": 5.565252854812398, "percentage": 55.65, "elapsed_time": "4:39:21", "remaining_time": "3:42:36", "throughput": 4393.03, "total_tokens": 73633088} {"current_steps": 34120, "total_steps": 61300, "loss": 0.3248, "lr": 2.4424917762453757e-05, "epoch": 5.566068515497553, "percentage": 55.66, "elapsed_time": "4:39:23", "remaining_time": "3:42:33", "throughput": 4393.1, "total_tokens": 73644512} {"current_steps": 34125, "total_steps": 61300, "loss": 0.3314, "lr": 2.4417801687086013e-05, "epoch": 5.566884176182708, "percentage": 55.67, "elapsed_time": "4:39:25", "remaining_time": "3:42:31", "throughput": 4393.15, "total_tokens": 73655008} {"current_steps": 34130, "total_steps": 61300, "loss": 0.3289, "lr": 2.4410685658914213e-05, "epoch": 5.567699836867863, "percentage": 55.68, "elapsed_time": "4:39:28", "remaining_time": "3:42:28", "throughput": 4393.19, "total_tokens": 73665216} {"current_steps": 34135, "total_steps": 61300, "loss": 0.3801, "lr": 2.4403569678515227e-05, "epoch": 5.568515497553018, "percentage": 55.69, "elapsed_time": "4:39:30", "remaining_time": "3:42:26", "throughput": 4393.25, "total_tokens": 73676384} {"current_steps": 34140, "total_steps": 61300, "loss": 0.3307, "lr": 2.4396453746465912e-05, "epoch": 5.569331158238173, "percentage": 55.69, "elapsed_time": "4:39:32", "remaining_time": "3:42:23", "throughput": 4393.31, "total_tokens": 73687456} {"current_steps": 34145, "total_steps": 61300, "loss": 0.3097, "lr": 2.4389337863343117e-05, "epoch": 5.570146818923328, "percentage": 55.7, "elapsed_time": "4:39:35", "remaining_time": "3:42:21", "throughput": 4393.37, "total_tokens": 73699424} {"current_steps": 34150, "total_steps": 61300, "loss": 0.3333, "lr": 2.4382222029723693e-05, "epoch": 5.5709624796084825, "percentage": 55.71, "elapsed_time": "4:39:37", "remaining_time": "3:42:18", "throughput": 4393.44, "total_tokens": 73710400} {"current_steps": 34155, "total_steps": 61300, "loss": 0.3302, "lr": 2.4375106246184484e-05, "epoch": 5.571778140293638, "percentage": 55.72, "elapsed_time": "4:39:39", "remaining_time": "3:42:15", "throughput": 4393.5, "total_tokens": 73721184} {"current_steps": 34160, "total_steps": 61300, "loss": 0.3221, "lr": 2.4367990513302336e-05, "epoch": 5.572593800978793, "percentage": 55.73, "elapsed_time": "4:39:41", "remaining_time": "3:42:13", "throughput": 4393.56, "total_tokens": 73732032} {"current_steps": 34165, "total_steps": 61300, "loss": 0.3255, "lr": 2.4360874831654083e-05, "epoch": 5.573409461663948, "percentage": 55.73, "elapsed_time": "4:39:44", "remaining_time": "3:42:10", "throughput": 4393.61, "total_tokens": 73742944} {"current_steps": 34170, "total_steps": 61300, "loss": 0.3245, "lr": 2.4353759201816555e-05, "epoch": 5.574225122349103, "percentage": 55.74, "elapsed_time": "4:39:46", "remaining_time": "3:42:07", "throughput": 4393.66, "total_tokens": 73753312} {"current_steps": 34175, "total_steps": 61300, "loss": 0.3093, "lr": 2.4346643624366586e-05, "epoch": 5.575040783034257, "percentage": 55.75, "elapsed_time": "4:39:48", "remaining_time": "3:42:05", "throughput": 4393.72, "total_tokens": 73764480} {"current_steps": 34180, "total_steps": 61300, "loss": 0.3366, "lr": 2.4339528099881e-05, "epoch": 5.575856443719413, "percentage": 55.76, "elapsed_time": "4:39:50", "remaining_time": "3:42:02", "throughput": 4393.78, "total_tokens": 73774496} {"current_steps": 34185, "total_steps": 61300, "loss": 0.3574, "lr": 2.433241262893662e-05, "epoch": 5.576672104404568, "percentage": 55.77, "elapsed_time": "4:39:53", "remaining_time": "3:42:00", "throughput": 4393.83, "total_tokens": 73786688} {"current_steps": 34190, "total_steps": 61300, "loss": 0.3164, "lr": 2.432529721211026e-05, "epoch": 5.577487765089723, "percentage": 55.77, "elapsed_time": "4:39:55", "remaining_time": "3:41:57", "throughput": 4393.9, "total_tokens": 73798080} {"current_steps": 34195, "total_steps": 61300, "loss": 0.3407, "lr": 2.4318181849978733e-05, "epoch": 5.578303425774878, "percentage": 55.78, "elapsed_time": "4:39:57", "remaining_time": "3:41:54", "throughput": 4393.95, "total_tokens": 73808736} {"current_steps": 34200, "total_steps": 61300, "loss": 0.3159, "lr": 2.4311066543118842e-05, "epoch": 5.579119086460032, "percentage": 55.79, "elapsed_time": "4:39:59", "remaining_time": "3:41:52", "throughput": 4394.01, "total_tokens": 73819232} {"current_steps": 34205, "total_steps": 61300, "loss": 0.3621, "lr": 2.4303951292107395e-05, "epoch": 5.579934747145187, "percentage": 55.8, "elapsed_time": "4:40:02", "remaining_time": "3:41:49", "throughput": 4394.05, "total_tokens": 73829312} {"current_steps": 34210, "total_steps": 61300, "loss": 0.3106, "lr": 2.4296836097521186e-05, "epoch": 5.580750407830343, "percentage": 55.81, "elapsed_time": "4:40:04", "remaining_time": "3:41:46", "throughput": 4394.11, "total_tokens": 73840320} {"current_steps": 34215, "total_steps": 61300, "loss": 0.3497, "lr": 2.4289720959937008e-05, "epoch": 5.581566068515498, "percentage": 55.82, "elapsed_time": "4:40:06", "remaining_time": "3:41:44", "throughput": 4394.16, "total_tokens": 73850464} {"current_steps": 34220, "total_steps": 61300, "loss": 0.301, "lr": 2.4282605879931647e-05, "epoch": 5.582381729200653, "percentage": 55.82, "elapsed_time": "4:40:08", "remaining_time": "3:41:41", "throughput": 4394.23, "total_tokens": 73861152} {"current_steps": 34225, "total_steps": 61300, "loss": 0.3413, "lr": 2.4275490858081903e-05, "epoch": 5.583197389885807, "percentage": 55.83, "elapsed_time": "4:40:10", "remaining_time": "3:41:38", "throughput": 4394.3, "total_tokens": 73872288} {"current_steps": 34230, "total_steps": 61300, "loss": 0.3341, "lr": 2.4268375894964544e-05, "epoch": 5.584013050570962, "percentage": 55.84, "elapsed_time": "4:40:13", "remaining_time": "3:41:36", "throughput": 4394.34, "total_tokens": 73882720} {"current_steps": 34235, "total_steps": 61300, "loss": 0.3228, "lr": 2.426126099115635e-05, "epoch": 5.584828711256117, "percentage": 55.85, "elapsed_time": "4:40:15", "remaining_time": "3:41:33", "throughput": 4394.39, "total_tokens": 73892448} {"current_steps": 34240, "total_steps": 61300, "loss": 0.3463, "lr": 2.4254146147234087e-05, "epoch": 5.585644371941273, "percentage": 55.86, "elapsed_time": "4:40:17", "remaining_time": "3:41:31", "throughput": 4394.45, "total_tokens": 73904224} {"current_steps": 34245, "total_steps": 61300, "loss": 0.3368, "lr": 2.4247031363774523e-05, "epoch": 5.5864600326264275, "percentage": 55.86, "elapsed_time": "4:40:19", "remaining_time": "3:41:28", "throughput": 4394.51, "total_tokens": 73915424} {"current_steps": 34250, "total_steps": 61300, "loss": 0.3564, "lr": 2.4239916641354417e-05, "epoch": 5.587275693311582, "percentage": 55.87, "elapsed_time": "4:40:21", "remaining_time": "3:41:25", "throughput": 4394.57, "total_tokens": 73925344} {"current_steps": 34255, "total_steps": 61300, "loss": 0.3695, "lr": 2.4232801980550523e-05, "epoch": 5.588091353996737, "percentage": 55.88, "elapsed_time": "4:40:24", "remaining_time": "3:41:23", "throughput": 4394.61, "total_tokens": 73935904} {"current_steps": 34260, "total_steps": 61300, "loss": 0.3188, "lr": 2.422568738193959e-05, "epoch": 5.588907014681892, "percentage": 55.89, "elapsed_time": "4:40:26", "remaining_time": "3:41:20", "throughput": 4394.67, "total_tokens": 73947296} {"current_steps": 34265, "total_steps": 61300, "loss": 0.3556, "lr": 2.421857284609837e-05, "epoch": 5.589722675367048, "percentage": 55.9, "elapsed_time": "4:40:28", "remaining_time": "3:41:17", "throughput": 4394.7, "total_tokens": 73955680} {"current_steps": 34270, "total_steps": 61300, "loss": 0.3568, "lr": 2.42114583736036e-05, "epoch": 5.5905383360522025, "percentage": 55.91, "elapsed_time": "4:40:30", "remaining_time": "3:41:14", "throughput": 4394.76, "total_tokens": 73966304} {"current_steps": 34275, "total_steps": 61300, "loss": 0.356, "lr": 2.4204343965032015e-05, "epoch": 5.591353996737357, "percentage": 55.91, "elapsed_time": "4:40:32", "remaining_time": "3:41:12", "throughput": 4394.82, "total_tokens": 73977120} {"current_steps": 34280, "total_steps": 61300, "loss": 0.3631, "lr": 2.4197229620960347e-05, "epoch": 5.592169657422512, "percentage": 55.92, "elapsed_time": "4:40:35", "remaining_time": "3:41:09", "throughput": 4394.87, "total_tokens": 73987648} {"current_steps": 34285, "total_steps": 61300, "loss": 0.3544, "lr": 2.4190115341965316e-05, "epoch": 5.592985318107667, "percentage": 55.93, "elapsed_time": "4:40:37", "remaining_time": "3:41:06", "throughput": 4394.91, "total_tokens": 73997312} {"current_steps": 34290, "total_steps": 61300, "loss": 0.3406, "lr": 2.418300112862365e-05, "epoch": 5.593800978792823, "percentage": 55.94, "elapsed_time": "4:40:39", "remaining_time": "3:41:04", "throughput": 4394.97, "total_tokens": 74009056} {"current_steps": 34295, "total_steps": 61300, "loss": 0.3366, "lr": 2.4175886981512054e-05, "epoch": 5.5946166394779775, "percentage": 55.95, "elapsed_time": "4:40:41", "remaining_time": "3:41:01", "throughput": 4395.02, "total_tokens": 74019488} {"current_steps": 34300, "total_steps": 61300, "loss": 0.3296, "lr": 2.416877290120724e-05, "epoch": 5.595432300163132, "percentage": 55.95, "elapsed_time": "4:40:44", "remaining_time": "3:40:59", "throughput": 4395.08, "total_tokens": 74030880} {"current_steps": 34305, "total_steps": 61300, "loss": 0.3312, "lr": 2.4161658888285916e-05, "epoch": 5.596247960848287, "percentage": 55.96, "elapsed_time": "4:40:46", "remaining_time": "3:40:56", "throughput": 4395.14, "total_tokens": 74042080} {"current_steps": 34310, "total_steps": 61300, "loss": 0.2823, "lr": 2.4154544943324772e-05, "epoch": 5.597063621533442, "percentage": 55.97, "elapsed_time": "4:40:48", "remaining_time": "3:40:53", "throughput": 4395.2, "total_tokens": 74052448} {"current_steps": 34315, "total_steps": 61300, "loss": 0.3235, "lr": 2.414743106690051e-05, "epoch": 5.597879282218597, "percentage": 55.98, "elapsed_time": "4:40:50", "remaining_time": "3:40:51", "throughput": 4395.25, "total_tokens": 74063392} {"current_steps": 34320, "total_steps": 61300, "loss": 0.3319, "lr": 2.41403172595898e-05, "epoch": 5.598694942903752, "percentage": 55.99, "elapsed_time": "4:40:53", "remaining_time": "3:40:48", "throughput": 4395.31, "total_tokens": 74074720} {"current_steps": 34325, "total_steps": 61300, "loss": 0.3575, "lr": 2.413320352196934e-05, "epoch": 5.599510603588907, "percentage": 56.0, "elapsed_time": "4:40:55", "remaining_time": "3:40:45", "throughput": 4395.37, "total_tokens": 74084512} {"current_steps": 34330, "total_steps": 61300, "loss": 0.3663, "lr": 2.4126089854615802e-05, "epoch": 5.600326264274062, "percentage": 56.0, "elapsed_time": "4:40:57", "remaining_time": "3:40:43", "throughput": 4395.42, "total_tokens": 74095520} {"current_steps": 34335, "total_steps": 61300, "loss": 0.3238, "lr": 2.411897625810586e-05, "epoch": 5.601141924959217, "percentage": 56.01, "elapsed_time": "4:40:59", "remaining_time": "3:40:40", "throughput": 4395.47, "total_tokens": 74105792} {"current_steps": 34340, "total_steps": 61300, "loss": 0.3626, "lr": 2.4111862733016164e-05, "epoch": 5.601957585644372, "percentage": 56.02, "elapsed_time": "4:41:01", "remaining_time": "3:40:37", "throughput": 4395.54, "total_tokens": 74116224} {"current_steps": 34345, "total_steps": 61300, "loss": 0.3284, "lr": 2.4104749279923383e-05, "epoch": 5.602773246329527, "percentage": 56.03, "elapsed_time": "4:41:03", "remaining_time": "3:40:35", "throughput": 4395.59, "total_tokens": 74127232} {"current_steps": 34350, "total_steps": 61300, "loss": 0.3261, "lr": 2.409763589940417e-05, "epoch": 5.603588907014682, "percentage": 56.04, "elapsed_time": "4:41:06", "remaining_time": "3:40:32", "throughput": 4395.63, "total_tokens": 74137088} {"current_steps": 34355, "total_steps": 61300, "loss": 0.3502, "lr": 2.4090522592035172e-05, "epoch": 5.604404567699837, "percentage": 56.04, "elapsed_time": "4:41:08", "remaining_time": "3:40:30", "throughput": 4395.69, "total_tokens": 74148128} {"current_steps": 34360, "total_steps": 61300, "loss": 0.3149, "lr": 2.408340935839303e-05, "epoch": 5.605220228384992, "percentage": 56.05, "elapsed_time": "4:41:10", "remaining_time": "3:40:27", "throughput": 4395.75, "total_tokens": 74158432} {"current_steps": 34365, "total_steps": 61300, "loss": 0.38, "lr": 2.407629619905437e-05, "epoch": 5.606035889070147, "percentage": 56.06, "elapsed_time": "4:41:12", "remaining_time": "3:40:24", "throughput": 4395.8, "total_tokens": 74169376} {"current_steps": 34370, "total_steps": 61300, "loss": 0.2945, "lr": 2.406918311459583e-05, "epoch": 5.6068515497553015, "percentage": 56.07, "elapsed_time": "4:41:15", "remaining_time": "3:40:22", "throughput": 4395.86, "total_tokens": 74180352} {"current_steps": 34375, "total_steps": 61300, "loss": 0.3466, "lr": 2.406207010559403e-05, "epoch": 5.607667210440457, "percentage": 56.08, "elapsed_time": "4:41:17", "remaining_time": "3:40:19", "throughput": 4395.91, "total_tokens": 74190304} {"current_steps": 34380, "total_steps": 61300, "loss": 0.3293, "lr": 2.4054957172625584e-05, "epoch": 5.608482871125612, "percentage": 56.08, "elapsed_time": "4:41:19", "remaining_time": "3:40:16", "throughput": 4395.97, "total_tokens": 74201504} {"current_steps": 34385, "total_steps": 61300, "loss": 0.3623, "lr": 2.4047844316267104e-05, "epoch": 5.609298531810767, "percentage": 56.09, "elapsed_time": "4:41:21", "remaining_time": "3:40:14", "throughput": 4396.04, "total_tokens": 74211968} {"current_steps": 34390, "total_steps": 61300, "loss": 0.3118, "lr": 2.40407315370952e-05, "epoch": 5.610114192495922, "percentage": 56.1, "elapsed_time": "4:41:23", "remaining_time": "3:40:11", "throughput": 4396.1, "total_tokens": 74223232} {"current_steps": 34395, "total_steps": 61300, "loss": 0.3615, "lr": 2.4033618835686462e-05, "epoch": 5.6109298531810765, "percentage": 56.11, "elapsed_time": "4:41:26", "remaining_time": "3:40:08", "throughput": 4396.15, "total_tokens": 74234272} {"current_steps": 34400, "total_steps": 61300, "loss": 0.3172, "lr": 2.4026506212617485e-05, "epoch": 5.611745513866231, "percentage": 56.12, "elapsed_time": "4:41:28", "remaining_time": "3:40:06", "throughput": 4396.21, "total_tokens": 74244608} {"current_steps": 34405, "total_steps": 61300, "loss": 0.3495, "lr": 2.4019393668464846e-05, "epoch": 5.612561174551386, "percentage": 56.13, "elapsed_time": "4:41:30", "remaining_time": "3:40:03", "throughput": 4396.26, "total_tokens": 74255104} {"current_steps": 34410, "total_steps": 61300, "loss": 0.3522, "lr": 2.4012281203805138e-05, "epoch": 5.613376835236542, "percentage": 56.13, "elapsed_time": "4:41:32", "remaining_time": "3:40:00", "throughput": 4396.32, "total_tokens": 74265792} {"current_steps": 34415, "total_steps": 61300, "loss": 0.3097, "lr": 2.4005168819214926e-05, "epoch": 5.614192495921697, "percentage": 56.14, "elapsed_time": "4:41:35", "remaining_time": "3:39:58", "throughput": 4396.38, "total_tokens": 74277120} {"current_steps": 34420, "total_steps": 61300, "loss": 0.3527, "lr": 2.3998056515270782e-05, "epoch": 5.6150081566068515, "percentage": 56.15, "elapsed_time": "4:41:37", "remaining_time": "3:39:55", "throughput": 4396.43, "total_tokens": 74286848} {"current_steps": 34425, "total_steps": 61300, "loss": 0.3162, "lr": 2.3990944292549257e-05, "epoch": 5.615823817292006, "percentage": 56.16, "elapsed_time": "4:41:39", "remaining_time": "3:39:52", "throughput": 4396.48, "total_tokens": 74296992} {"current_steps": 34430, "total_steps": 61300, "loss": 0.3493, "lr": 2.3983832151626897e-05, "epoch": 5.616639477977161, "percentage": 56.17, "elapsed_time": "4:41:41", "remaining_time": "3:39:50", "throughput": 4396.54, "total_tokens": 74307680} {"current_steps": 34435, "total_steps": 61300, "loss": 0.3193, "lr": 2.397672009308027e-05, "epoch": 5.617455138662317, "percentage": 56.17, "elapsed_time": "4:41:43", "remaining_time": "3:39:47", "throughput": 4396.59, "total_tokens": 74318368} {"current_steps": 34440, "total_steps": 61300, "loss": 0.3123, "lr": 2.3969608117485906e-05, "epoch": 5.618270799347472, "percentage": 56.18, "elapsed_time": "4:41:45", "remaining_time": "3:39:44", "throughput": 4396.64, "total_tokens": 74328544} {"current_steps": 34445, "total_steps": 61300, "loss": 0.3008, "lr": 2.3962496225420335e-05, "epoch": 5.6190864600326265, "percentage": 56.19, "elapsed_time": "4:41:48", "remaining_time": "3:39:42", "throughput": 4396.71, "total_tokens": 74339904} {"current_steps": 34450, "total_steps": 61300, "loss": 0.3102, "lr": 2.3955384417460084e-05, "epoch": 5.619902120717781, "percentage": 56.2, "elapsed_time": "4:41:50", "remaining_time": "3:39:39", "throughput": 4396.76, "total_tokens": 74350784} {"current_steps": 34455, "total_steps": 61300, "loss": 0.3337, "lr": 2.3948272694181673e-05, "epoch": 5.620717781402936, "percentage": 56.21, "elapsed_time": "4:41:52", "remaining_time": "3:39:37", "throughput": 4396.81, "total_tokens": 74361408} {"current_steps": 34460, "total_steps": 61300, "loss": 0.3062, "lr": 2.3941161056161612e-05, "epoch": 5.621533442088092, "percentage": 56.22, "elapsed_time": "4:41:54", "remaining_time": "3:39:34", "throughput": 4396.86, "total_tokens": 74371904} {"current_steps": 34465, "total_steps": 61300, "loss": 0.3533, "lr": 2.393404950397641e-05, "epoch": 5.622349102773247, "percentage": 56.22, "elapsed_time": "4:41:57", "remaining_time": "3:39:31", "throughput": 4396.93, "total_tokens": 74383232} {"current_steps": 34470, "total_steps": 61300, "loss": 0.3968, "lr": 2.3926938038202565e-05, "epoch": 5.623164763458401, "percentage": 56.23, "elapsed_time": "4:41:59", "remaining_time": "3:39:29", "throughput": 4396.99, "total_tokens": 74394240} {"current_steps": 34475, "total_steps": 61300, "loss": 0.3665, "lr": 2.3919826659416564e-05, "epoch": 5.623980424143556, "percentage": 56.24, "elapsed_time": "4:42:01", "remaining_time": "3:39:26", "throughput": 4397.04, "total_tokens": 74404160} {"current_steps": 34480, "total_steps": 61300, "loss": 0.3299, "lr": 2.3912715368194895e-05, "epoch": 5.624796084828711, "percentage": 56.25, "elapsed_time": "4:42:03", "remaining_time": "3:39:24", "throughput": 4397.1, "total_tokens": 74415904} {"current_steps": 34485, "total_steps": 61300, "loss": 0.3662, "lr": 2.3905604165114038e-05, "epoch": 5.625611745513866, "percentage": 56.26, "elapsed_time": "4:42:06", "remaining_time": "3:39:21", "throughput": 4397.15, "total_tokens": 74426336} {"current_steps": 34490, "total_steps": 61300, "loss": 0.3291, "lr": 2.3898493050750453e-05, "epoch": 5.626427406199021, "percentage": 56.26, "elapsed_time": "4:42:07", "remaining_time": "3:39:18", "throughput": 4397.19, "total_tokens": 74434592} {"current_steps": 34495, "total_steps": 61300, "loss": 0.3656, "lr": 2.3891382025680616e-05, "epoch": 5.627243066884176, "percentage": 56.27, "elapsed_time": "4:42:10", "remaining_time": "3:39:15", "throughput": 4397.25, "total_tokens": 74446464} {"current_steps": 34500, "total_steps": 61300, "loss": 0.3305, "lr": 2.388427109048098e-05, "epoch": 5.628058727569331, "percentage": 56.28, "elapsed_time": "4:42:12", "remaining_time": "3:39:13", "throughput": 4397.3, "total_tokens": 74457056} {"current_steps": 34505, "total_steps": 61300, "loss": 0.3452, "lr": 2.3877160245727988e-05, "epoch": 5.628874388254486, "percentage": 56.29, "elapsed_time": "4:42:14", "remaining_time": "3:39:10", "throughput": 4397.35, "total_tokens": 74467584} {"current_steps": 34510, "total_steps": 61300, "loss": 0.3433, "lr": 2.3870049491998082e-05, "epoch": 5.629690048939641, "percentage": 56.3, "elapsed_time": "4:42:16", "remaining_time": "3:39:07", "throughput": 4397.41, "total_tokens": 74477376} {"current_steps": 34515, "total_steps": 61300, "loss": 0.3501, "lr": 2.3862938829867698e-05, "epoch": 5.630505709624796, "percentage": 56.31, "elapsed_time": "4:42:18", "remaining_time": "3:39:05", "throughput": 4397.46, "total_tokens": 74487648} {"current_steps": 34520, "total_steps": 61300, "loss": 0.3495, "lr": 2.3855828259913262e-05, "epoch": 5.631321370309951, "percentage": 56.31, "elapsed_time": "4:42:21", "remaining_time": "3:39:02", "throughput": 4397.52, "total_tokens": 74498496} {"current_steps": 34525, "total_steps": 61300, "loss": 0.3466, "lr": 2.3848717782711194e-05, "epoch": 5.632137030995106, "percentage": 56.32, "elapsed_time": "4:42:23", "remaining_time": "3:39:00", "throughput": 4397.57, "total_tokens": 74509664} {"current_steps": 34530, "total_steps": 61300, "loss": 0.359, "lr": 2.3841607398837902e-05, "epoch": 5.632952691680261, "percentage": 56.33, "elapsed_time": "4:42:25", "remaining_time": "3:38:57", "throughput": 4397.62, "total_tokens": 74519808} {"current_steps": 34535, "total_steps": 61300, "loss": 0.3312, "lr": 2.3834497108869797e-05, "epoch": 5.633768352365416, "percentage": 56.34, "elapsed_time": "4:42:28", "remaining_time": "3:38:54", "throughput": 4397.68, "total_tokens": 74531840} {"current_steps": 34540, "total_steps": 61300, "loss": 0.3465, "lr": 2.3827386913383254e-05, "epoch": 5.634584013050571, "percentage": 56.35, "elapsed_time": "4:42:30", "remaining_time": "3:38:52", "throughput": 4397.74, "total_tokens": 74543168} {"current_steps": 34545, "total_steps": 61300, "loss": 0.3212, "lr": 2.3820276812954688e-05, "epoch": 5.635399673735726, "percentage": 56.35, "elapsed_time": "4:42:32", "remaining_time": "3:38:49", "throughput": 4397.8, "total_tokens": 74553792} {"current_steps": 34550, "total_steps": 61300, "loss": 0.3376, "lr": 2.3813166808160472e-05, "epoch": 5.636215334420881, "percentage": 56.36, "elapsed_time": "4:42:34", "remaining_time": "3:38:47", "throughput": 4397.86, "total_tokens": 74565312} {"current_steps": 34555, "total_steps": 61300, "loss": 0.3411, "lr": 2.3806056899576978e-05, "epoch": 5.637030995106036, "percentage": 56.37, "elapsed_time": "4:42:37", "remaining_time": "3:38:44", "throughput": 4397.92, "total_tokens": 74576256} {"current_steps": 34560, "total_steps": 61300, "loss": 0.3356, "lr": 2.3798947087780567e-05, "epoch": 5.637846655791191, "percentage": 56.38, "elapsed_time": "4:42:39", "remaining_time": "3:38:41", "throughput": 4397.98, "total_tokens": 74586560} {"current_steps": 34565, "total_steps": 61300, "loss": 0.3347, "lr": 2.37918373733476e-05, "epoch": 5.638662316476346, "percentage": 56.39, "elapsed_time": "4:42:41", "remaining_time": "3:38:39", "throughput": 4398.03, "total_tokens": 74597792} {"current_steps": 34570, "total_steps": 61300, "loss": 0.3285, "lr": 2.3784727756854425e-05, "epoch": 5.6394779771615005, "percentage": 56.39, "elapsed_time": "4:42:44", "remaining_time": "3:38:36", "throughput": 4398.09, "total_tokens": 74609504} {"current_steps": 34575, "total_steps": 61300, "loss": 0.3369, "lr": 2.377761823887738e-05, "epoch": 5.640293637846656, "percentage": 56.4, "elapsed_time": "4:42:46", "remaining_time": "3:38:34", "throughput": 4398.14, "total_tokens": 74620160} {"current_steps": 34580, "total_steps": 61300, "loss": 0.3542, "lr": 2.3770508819992807e-05, "epoch": 5.641109298531811, "percentage": 56.41, "elapsed_time": "4:42:48", "remaining_time": "3:38:31", "throughput": 4398.2, "total_tokens": 74631072} {"current_steps": 34585, "total_steps": 61300, "loss": 0.3491, "lr": 2.376339950077703e-05, "epoch": 5.641924959216966, "percentage": 56.42, "elapsed_time": "4:42:50", "remaining_time": "3:38:28", "throughput": 4398.25, "total_tokens": 74641088} {"current_steps": 34590, "total_steps": 61300, "loss": 0.3422, "lr": 2.3756290281806358e-05, "epoch": 5.642740619902121, "percentage": 56.43, "elapsed_time": "4:42:52", "remaining_time": "3:38:26", "throughput": 4398.3, "total_tokens": 74650560} {"current_steps": 34595, "total_steps": 61300, "loss": 0.3186, "lr": 2.3749181163657114e-05, "epoch": 5.643556280587275, "percentage": 56.44, "elapsed_time": "4:42:54", "remaining_time": "3:38:23", "throughput": 4398.34, "total_tokens": 74660608} {"current_steps": 34600, "total_steps": 61300, "loss": 0.34, "lr": 2.3742072146905587e-05, "epoch": 5.64437194127243, "percentage": 56.44, "elapsed_time": "4:42:57", "remaining_time": "3:38:20", "throughput": 4398.41, "total_tokens": 74672064} {"current_steps": 34605, "total_steps": 61300, "loss": 0.372, "lr": 2.3734963232128072e-05, "epoch": 5.645187601957586, "percentage": 56.45, "elapsed_time": "4:42:59", "remaining_time": "3:38:18", "throughput": 4398.47, "total_tokens": 74683200} {"current_steps": 34610, "total_steps": 61300, "loss": 0.3595, "lr": 2.372785441990086e-05, "epoch": 5.646003262642741, "percentage": 56.46, "elapsed_time": "4:43:01", "remaining_time": "3:38:15", "throughput": 4398.52, "total_tokens": 74694016} {"current_steps": 34615, "total_steps": 61300, "loss": 0.3707, "lr": 2.3720745710800225e-05, "epoch": 5.646818923327896, "percentage": 56.47, "elapsed_time": "4:43:03", "remaining_time": "3:38:12", "throughput": 4398.57, "total_tokens": 74704096} {"current_steps": 34620, "total_steps": 61300, "loss": 0.3748, "lr": 2.371363710540243e-05, "epoch": 5.64763458401305, "percentage": 56.48, "elapsed_time": "4:43:05", "remaining_time": "3:38:10", "throughput": 4398.62, "total_tokens": 74714528} {"current_steps": 34625, "total_steps": 61300, "loss": 0.349, "lr": 2.370652860428374e-05, "epoch": 5.648450244698205, "percentage": 56.48, "elapsed_time": "4:43:08", "remaining_time": "3:38:07", "throughput": 4398.68, "total_tokens": 74725888} {"current_steps": 34630, "total_steps": 61300, "loss": 0.3474, "lr": 2.3699420208020403e-05, "epoch": 5.649265905383361, "percentage": 56.49, "elapsed_time": "4:43:10", "remaining_time": "3:38:05", "throughput": 4398.73, "total_tokens": 74736384} {"current_steps": 34635, "total_steps": 61300, "loss": 0.3241, "lr": 2.3692311917188658e-05, "epoch": 5.650081566068516, "percentage": 56.5, "elapsed_time": "4:43:12", "remaining_time": "3:38:02", "throughput": 4398.79, "total_tokens": 74748064} {"current_steps": 34640, "total_steps": 61300, "loss": 0.3253, "lr": 2.3685203732364754e-05, "epoch": 5.650897226753671, "percentage": 56.51, "elapsed_time": "4:43:15", "remaining_time": "3:37:59", "throughput": 4398.83, "total_tokens": 74758720} {"current_steps": 34645, "total_steps": 61300, "loss": 0.3142, "lr": 2.3678095654124893e-05, "epoch": 5.651712887438825, "percentage": 56.52, "elapsed_time": "4:43:17", "remaining_time": "3:37:57", "throughput": 4398.88, "total_tokens": 74770208} {"current_steps": 34650, "total_steps": 61300, "loss": 0.3143, "lr": 2.3670987683045317e-05, "epoch": 5.65252854812398, "percentage": 56.53, "elapsed_time": "4:43:19", "remaining_time": "3:37:54", "throughput": 4398.94, "total_tokens": 74781568} {"current_steps": 34655, "total_steps": 61300, "loss": 0.3485, "lr": 2.366387981970222e-05, "epoch": 5.653344208809135, "percentage": 56.53, "elapsed_time": "4:43:22", "remaining_time": "3:37:52", "throughput": 4398.99, "total_tokens": 74792608} {"current_steps": 34660, "total_steps": 61300, "loss": 0.387, "lr": 2.36567720646718e-05, "epoch": 5.654159869494291, "percentage": 56.54, "elapsed_time": "4:43:24", "remaining_time": "3:37:49", "throughput": 4399.03, "total_tokens": 74801760} {"current_steps": 34665, "total_steps": 61300, "loss": 0.349, "lr": 2.3649664418530258e-05, "epoch": 5.6549755301794455, "percentage": 56.55, "elapsed_time": "4:43:26", "remaining_time": "3:37:46", "throughput": 4399.08, "total_tokens": 74812256} {"current_steps": 34670, "total_steps": 61300, "loss": 0.3635, "lr": 2.364255688185377e-05, "epoch": 5.6557911908646, "percentage": 56.56, "elapsed_time": "4:43:28", "remaining_time": "3:37:44", "throughput": 4399.13, "total_tokens": 74822848} {"current_steps": 34675, "total_steps": 61300, "loss": 0.328, "lr": 2.3635449455218506e-05, "epoch": 5.656606851549755, "percentage": 56.57, "elapsed_time": "4:43:30", "remaining_time": "3:37:41", "throughput": 4399.18, "total_tokens": 74832992} {"current_steps": 34680, "total_steps": 61300, "loss": 0.3428, "lr": 2.3628342139200636e-05, "epoch": 5.65742251223491, "percentage": 56.57, "elapsed_time": "4:43:32", "remaining_time": "3:37:38", "throughput": 4399.24, "total_tokens": 74843136} {"current_steps": 34685, "total_steps": 61300, "loss": 0.3362, "lr": 2.362123493437631e-05, "epoch": 5.658238172920065, "percentage": 56.58, "elapsed_time": "4:43:34", "remaining_time": "3:37:36", "throughput": 4399.28, "total_tokens": 74852800} {"current_steps": 34690, "total_steps": 61300, "loss": 0.3381, "lr": 2.3614127841321677e-05, "epoch": 5.6590538336052205, "percentage": 56.59, "elapsed_time": "4:43:37", "remaining_time": "3:37:33", "throughput": 4399.35, "total_tokens": 74864512} {"current_steps": 34695, "total_steps": 61300, "loss": 0.2908, "lr": 2.3607020860612872e-05, "epoch": 5.659869494290375, "percentage": 56.6, "elapsed_time": "4:43:39", "remaining_time": "3:37:31", "throughput": 4399.39, "total_tokens": 74875936} {"current_steps": 34700, "total_steps": 61300, "loss": 0.361, "lr": 2.3599913992826023e-05, "epoch": 5.66068515497553, "percentage": 56.61, "elapsed_time": "4:43:41", "remaining_time": "3:37:28", "throughput": 4399.44, "total_tokens": 74885504} {"current_steps": 34705, "total_steps": 61300, "loss": 0.3197, "lr": 2.3592807238537253e-05, "epoch": 5.661500815660685, "percentage": 56.62, "elapsed_time": "4:43:44", "remaining_time": "3:37:25", "throughput": 4399.5, "total_tokens": 74897632} {"current_steps": 34710, "total_steps": 61300, "loss": 0.3008, "lr": 2.3585700598322665e-05, "epoch": 5.66231647634584, "percentage": 56.62, "elapsed_time": "4:43:46", "remaining_time": "3:37:23", "throughput": 4399.57, "total_tokens": 74908672} {"current_steps": 34715, "total_steps": 61300, "loss": 0.3117, "lr": 2.3578594072758363e-05, "epoch": 5.6631321370309955, "percentage": 56.63, "elapsed_time": "4:43:48", "remaining_time": "3:37:20", "throughput": 4399.61, "total_tokens": 74919104} {"current_steps": 34720, "total_steps": 61300, "loss": 0.3777, "lr": 2.3571487662420433e-05, "epoch": 5.66394779771615, "percentage": 56.64, "elapsed_time": "4:43:50", "remaining_time": "3:37:18", "throughput": 4399.66, "total_tokens": 74929952} {"current_steps": 34725, "total_steps": 61300, "loss": 0.3638, "lr": 2.3564381367884965e-05, "epoch": 5.664763458401305, "percentage": 56.65, "elapsed_time": "4:43:53", "remaining_time": "3:37:15", "throughput": 4399.72, "total_tokens": 74941760} {"current_steps": 34730, "total_steps": 61300, "loss": 0.3275, "lr": 2.3557275189728032e-05, "epoch": 5.66557911908646, "percentage": 56.66, "elapsed_time": "4:43:55", "remaining_time": "3:37:12", "throughput": 4399.76, "total_tokens": 74952000} {"current_steps": 34735, "total_steps": 61300, "loss": 0.3141, "lr": 2.3550169128525688e-05, "epoch": 5.666394779771615, "percentage": 56.66, "elapsed_time": "4:43:57", "remaining_time": "3:37:10", "throughput": 4399.82, "total_tokens": 74963008} {"current_steps": 34740, "total_steps": 61300, "loss": 0.3602, "lr": 2.3543063184853994e-05, "epoch": 5.6672104404567705, "percentage": 56.67, "elapsed_time": "4:43:59", "remaining_time": "3:37:07", "throughput": 4399.87, "total_tokens": 74973408} {"current_steps": 34745, "total_steps": 61300, "loss": 0.3183, "lr": 2.353595735928899e-05, "epoch": 5.668026101141925, "percentage": 56.68, "elapsed_time": "4:44:02", "remaining_time": "3:37:04", "throughput": 4399.93, "total_tokens": 74983744} {"current_steps": 34750, "total_steps": 61300, "loss": 0.3496, "lr": 2.3528851652406697e-05, "epoch": 5.66884176182708, "percentage": 56.69, "elapsed_time": "4:44:04", "remaining_time": "3:37:02", "throughput": 4399.98, "total_tokens": 74993952} {"current_steps": 34755, "total_steps": 61300, "loss": 0.352, "lr": 2.3521746064783168e-05, "epoch": 5.669657422512235, "percentage": 56.7, "elapsed_time": "4:44:06", "remaining_time": "3:36:59", "throughput": 4400.04, "total_tokens": 75004128} {"current_steps": 34760, "total_steps": 61300, "loss": 0.3748, "lr": 2.3514640596994404e-05, "epoch": 5.67047308319739, "percentage": 56.7, "elapsed_time": "4:44:08", "remaining_time": "3:36:56", "throughput": 4400.09, "total_tokens": 75014496} {"current_steps": 34765, "total_steps": 61300, "loss": 0.3755, "lr": 2.350753524961641e-05, "epoch": 5.671288743882545, "percentage": 56.71, "elapsed_time": "4:44:10", "remaining_time": "3:36:54", "throughput": 4400.15, "total_tokens": 75024704} {"current_steps": 34770, "total_steps": 61300, "loss": 0.3613, "lr": 2.3500430023225174e-05, "epoch": 5.672104404567699, "percentage": 56.72, "elapsed_time": "4:44:12", "remaining_time": "3:36:51", "throughput": 4400.2, "total_tokens": 75035488} {"current_steps": 34775, "total_steps": 61300, "loss": 0.3441, "lr": 2.3493324918396696e-05, "epoch": 5.672920065252855, "percentage": 56.73, "elapsed_time": "4:44:15", "remaining_time": "3:36:49", "throughput": 4400.28, "total_tokens": 75048192} {"current_steps": 34780, "total_steps": 61300, "loss": 0.3111, "lr": 2.3486219935706944e-05, "epoch": 5.67373572593801, "percentage": 56.74, "elapsed_time": "4:44:17", "remaining_time": "3:36:46", "throughput": 4400.33, "total_tokens": 75059680} {"current_steps": 34785, "total_steps": 61300, "loss": 0.3563, "lr": 2.3479115075731886e-05, "epoch": 5.674551386623165, "percentage": 56.75, "elapsed_time": "4:44:19", "remaining_time": "3:36:43", "throughput": 4400.38, "total_tokens": 75069696} {"current_steps": 34790, "total_steps": 61300, "loss": 0.3207, "lr": 2.3472010339047474e-05, "epoch": 5.6753670473083195, "percentage": 56.75, "elapsed_time": "4:44:22", "remaining_time": "3:36:41", "throughput": 4400.43, "total_tokens": 75080512} {"current_steps": 34795, "total_steps": 61300, "loss": 0.3302, "lr": 2.3464905726229657e-05, "epoch": 5.676182707993474, "percentage": 56.76, "elapsed_time": "4:44:24", "remaining_time": "3:36:38", "throughput": 4400.49, "total_tokens": 75092000} {"current_steps": 34800, "total_steps": 61300, "loss": 0.3551, "lr": 2.3457801237854367e-05, "epoch": 5.67699836867863, "percentage": 56.77, "elapsed_time": "4:44:26", "remaining_time": "3:36:36", "throughput": 4400.54, "total_tokens": 75102208} {"current_steps": 34805, "total_steps": 61300, "loss": 0.3505, "lr": 2.345069687449754e-05, "epoch": 5.677814029363785, "percentage": 56.78, "elapsed_time": "4:44:28", "remaining_time": "3:36:33", "throughput": 4400.6, "total_tokens": 75112960} {"current_steps": 34810, "total_steps": 61300, "loss": 0.3411, "lr": 2.3443592636735085e-05, "epoch": 5.67862969004894, "percentage": 56.79, "elapsed_time": "4:44:31", "remaining_time": "3:36:31", "throughput": 4400.67, "total_tokens": 75125824} {"current_steps": 34815, "total_steps": 61300, "loss": 0.3463, "lr": 2.3436488525142906e-05, "epoch": 5.6794453507340945, "percentage": 56.79, "elapsed_time": "4:44:33", "remaining_time": "3:36:28", "throughput": 4400.73, "total_tokens": 75136896} {"current_steps": 34820, "total_steps": 61300, "loss": 0.3204, "lr": 2.3429384540296902e-05, "epoch": 5.680261011419249, "percentage": 56.8, "elapsed_time": "4:44:35", "remaining_time": "3:36:25", "throughput": 4400.78, "total_tokens": 75146528} {"current_steps": 34825, "total_steps": 61300, "loss": 0.3174, "lr": 2.3422280682772953e-05, "epoch": 5.681076672104405, "percentage": 56.81, "elapsed_time": "4:44:37", "remaining_time": "3:36:23", "throughput": 4400.82, "total_tokens": 75157184} {"current_steps": 34830, "total_steps": 61300, "loss": 0.3516, "lr": 2.341517695314694e-05, "epoch": 5.68189233278956, "percentage": 56.82, "elapsed_time": "4:44:39", "remaining_time": "3:36:20", "throughput": 4400.86, "total_tokens": 75166016} {"current_steps": 34835, "total_steps": 61300, "loss": 0.3461, "lr": 2.3408073351994726e-05, "epoch": 5.682707993474715, "percentage": 56.83, "elapsed_time": "4:44:42", "remaining_time": "3:36:17", "throughput": 4400.92, "total_tokens": 75177824} {"current_steps": 34840, "total_steps": 61300, "loss": 0.3102, "lr": 2.340096987989216e-05, "epoch": 5.6835236541598695, "percentage": 56.84, "elapsed_time": "4:44:44", "remaining_time": "3:36:15", "throughput": 4400.97, "total_tokens": 75188128} {"current_steps": 34845, "total_steps": 61300, "loss": 0.3323, "lr": 2.3393866537415093e-05, "epoch": 5.684339314845024, "percentage": 56.84, "elapsed_time": "4:44:46", "remaining_time": "3:36:12", "throughput": 4401.03, "total_tokens": 75198016} {"current_steps": 34850, "total_steps": 61300, "loss": 0.3433, "lr": 2.3386763325139353e-05, "epoch": 5.685154975530179, "percentage": 56.85, "elapsed_time": "4:44:48", "remaining_time": "3:36:09", "throughput": 4401.09, "total_tokens": 75208768} {"current_steps": 34855, "total_steps": 61300, "loss": 0.3371, "lr": 2.337966024364076e-05, "epoch": 5.685970636215334, "percentage": 56.86, "elapsed_time": "4:44:50", "remaining_time": "3:36:07", "throughput": 4401.15, "total_tokens": 75220064} {"current_steps": 34860, "total_steps": 61300, "loss": 0.3252, "lr": 2.337255729349512e-05, "epoch": 5.68678629690049, "percentage": 56.87, "elapsed_time": "4:44:53", "remaining_time": "3:36:04", "throughput": 4401.21, "total_tokens": 75231552} {"current_steps": 34865, "total_steps": 61300, "loss": 0.3315, "lr": 2.3365454475278257e-05, "epoch": 5.6876019575856445, "percentage": 56.88, "elapsed_time": "4:44:55", "remaining_time": "3:36:02", "throughput": 4401.26, "total_tokens": 75242080} {"current_steps": 34870, "total_steps": 61300, "loss": 0.3867, "lr": 2.3358351789565945e-05, "epoch": 5.688417618270799, "percentage": 56.88, "elapsed_time": "4:44:57", "remaining_time": "3:35:59", "throughput": 4401.32, "total_tokens": 75253312} {"current_steps": 34875, "total_steps": 61300, "loss": 0.3516, "lr": 2.335124923693397e-05, "epoch": 5.689233278955954, "percentage": 56.89, "elapsed_time": "4:45:00", "remaining_time": "3:35:57", "throughput": 4401.38, "total_tokens": 75265376} {"current_steps": 34880, "total_steps": 61300, "loss": 0.3504, "lr": 2.334414681795809e-05, "epoch": 5.690048939641109, "percentage": 56.9, "elapsed_time": "4:45:02", "remaining_time": "3:35:54", "throughput": 4401.43, "total_tokens": 75275872} {"current_steps": 34885, "total_steps": 61300, "loss": 0.3172, "lr": 2.3337044533214068e-05, "epoch": 5.690864600326265, "percentage": 56.91, "elapsed_time": "4:45:05", "remaining_time": "3:35:52", "throughput": 4401.5, "total_tokens": 75288096} {"current_steps": 34890, "total_steps": 61300, "loss": 0.3328, "lr": 2.3329942383277665e-05, "epoch": 5.691680261011419, "percentage": 56.92, "elapsed_time": "4:45:07", "remaining_time": "3:35:49", "throughput": 4401.56, "total_tokens": 75298112} {"current_steps": 34895, "total_steps": 61300, "loss": 0.3314, "lr": 2.3322840368724598e-05, "epoch": 5.692495921696574, "percentage": 56.92, "elapsed_time": "4:45:09", "remaining_time": "3:35:46", "throughput": 4401.61, "total_tokens": 75308992} {"current_steps": 34900, "total_steps": 61300, "loss": 0.3204, "lr": 2.3315738490130606e-05, "epoch": 5.693311582381729, "percentage": 56.93, "elapsed_time": "4:45:11", "remaining_time": "3:35:44", "throughput": 4401.67, "total_tokens": 75320352} {"current_steps": 34905, "total_steps": 61300, "loss": 0.325, "lr": 2.3308636748071395e-05, "epoch": 5.694127243066884, "percentage": 56.94, "elapsed_time": "4:45:14", "remaining_time": "3:35:41", "throughput": 4401.75, "total_tokens": 75333056} {"current_steps": 34910, "total_steps": 61300, "loss": 0.3343, "lr": 2.3301535143122675e-05, "epoch": 5.69494290375204, "percentage": 56.95, "elapsed_time": "4:45:16", "remaining_time": "3:35:39", "throughput": 4401.81, "total_tokens": 75345248} {"current_steps": 34915, "total_steps": 61300, "loss": 0.3143, "lr": 2.3294433675860134e-05, "epoch": 5.695758564437194, "percentage": 56.96, "elapsed_time": "4:45:19", "remaining_time": "3:35:36", "throughput": 4401.87, "total_tokens": 75356576} {"current_steps": 34920, "total_steps": 61300, "loss": 0.3147, "lr": 2.328733234685945e-05, "epoch": 5.696574225122349, "percentage": 56.97, "elapsed_time": "4:45:21", "remaining_time": "3:35:34", "throughput": 4401.92, "total_tokens": 75368000} {"current_steps": 34925, "total_steps": 61300, "loss": 0.3124, "lr": 2.3280231156696297e-05, "epoch": 5.697389885807504, "percentage": 56.97, "elapsed_time": "4:45:23", "remaining_time": "3:35:31", "throughput": 4401.97, "total_tokens": 75378208} {"current_steps": 34930, "total_steps": 61300, "loss": 0.3333, "lr": 2.3273130105946333e-05, "epoch": 5.698205546492659, "percentage": 56.98, "elapsed_time": "4:45:26", "remaining_time": "3:35:29", "throughput": 4402.04, "total_tokens": 75390112} {"current_steps": 34935, "total_steps": 61300, "loss": 0.2976, "lr": 2.3266029195185204e-05, "epoch": 5.699021207177814, "percentage": 56.99, "elapsed_time": "4:45:28", "remaining_time": "3:35:26", "throughput": 4402.1, "total_tokens": 75401824} {"current_steps": 34940, "total_steps": 61300, "loss": 0.3519, "lr": 2.3258928424988548e-05, "epoch": 5.699836867862969, "percentage": 57.0, "elapsed_time": "4:45:30", "remaining_time": "3:35:24", "throughput": 4402.14, "total_tokens": 75412384} {"current_steps": 34945, "total_steps": 61300, "loss": 0.3033, "lr": 2.325182779593198e-05, "epoch": 5.700652528548124, "percentage": 57.01, "elapsed_time": "4:45:33", "remaining_time": "3:35:21", "throughput": 4402.2, "total_tokens": 75423648} {"current_steps": 34950, "total_steps": 61300, "loss": 0.3191, "lr": 2.3244727308591126e-05, "epoch": 5.701468189233279, "percentage": 57.01, "elapsed_time": "4:45:35", "remaining_time": "3:35:19", "throughput": 4402.27, "total_tokens": 75435232} {"current_steps": 34955, "total_steps": 61300, "loss": 0.3446, "lr": 2.3237626963541588e-05, "epoch": 5.702283849918434, "percentage": 57.02, "elapsed_time": "4:45:37", "remaining_time": "3:35:16", "throughput": 4402.32, "total_tokens": 75445952} {"current_steps": 34960, "total_steps": 61300, "loss": 0.3068, "lr": 2.3230526761358944e-05, "epoch": 5.703099510603589, "percentage": 57.03, "elapsed_time": "4:45:40", "remaining_time": "3:35:14", "throughput": 4402.37, "total_tokens": 75457696} {"current_steps": 34965, "total_steps": 61300, "loss": 0.3163, "lr": 2.3223426702618776e-05, "epoch": 5.7039151712887435, "percentage": 57.04, "elapsed_time": "4:45:42", "remaining_time": "3:35:11", "throughput": 4402.42, "total_tokens": 75467424} {"current_steps": 34970, "total_steps": 61300, "loss": 0.3612, "lr": 2.3216326787896652e-05, "epoch": 5.704730831973899, "percentage": 57.05, "elapsed_time": "4:45:44", "remaining_time": "3:35:08", "throughput": 4402.46, "total_tokens": 75476928} {"current_steps": 34975, "total_steps": 61300, "loss": 0.3261, "lr": 2.3209227017768137e-05, "epoch": 5.705546492659054, "percentage": 57.06, "elapsed_time": "4:45:46", "remaining_time": "3:35:05", "throughput": 4402.52, "total_tokens": 75486624} {"current_steps": 34980, "total_steps": 61300, "loss": 0.3168, "lr": 2.3202127392808768e-05, "epoch": 5.706362153344209, "percentage": 57.06, "elapsed_time": "4:45:48", "remaining_time": "3:35:03", "throughput": 4402.58, "total_tokens": 75497888} {"current_steps": 34985, "total_steps": 61300, "loss": 0.3252, "lr": 2.319502791359407e-05, "epoch": 5.707177814029364, "percentage": 57.07, "elapsed_time": "4:45:50", "remaining_time": "3:35:00", "throughput": 4402.63, "total_tokens": 75508352} {"current_steps": 34990, "total_steps": 61300, "loss": 0.3445, "lr": 2.3187928580699573e-05, "epoch": 5.7079934747145185, "percentage": 57.08, "elapsed_time": "4:45:53", "remaining_time": "3:34:58", "throughput": 4402.69, "total_tokens": 75520416} {"current_steps": 34995, "total_steps": 61300, "loss": 0.3623, "lr": 2.3180829394700775e-05, "epoch": 5.708809135399674, "percentage": 57.09, "elapsed_time": "4:45:55", "remaining_time": "3:34:55", "throughput": 4402.75, "total_tokens": 75531168} {"current_steps": 35000, "total_steps": 61300, "loss": 0.3627, "lr": 2.317373035617318e-05, "epoch": 5.709624796084829, "percentage": 57.1, "elapsed_time": "4:45:57", "remaining_time": "3:34:52", "throughput": 4402.8, "total_tokens": 75541632} {"current_steps": 35005, "total_steps": 61300, "loss": 0.3355, "lr": 2.3166631465692264e-05, "epoch": 5.710440456769984, "percentage": 57.1, "elapsed_time": "4:45:59", "remaining_time": "3:34:50", "throughput": 4402.85, "total_tokens": 75552224} {"current_steps": 35010, "total_steps": 61300, "loss": 0.3276, "lr": 2.3159532723833508e-05, "epoch": 5.711256117455139, "percentage": 57.11, "elapsed_time": "4:46:01", "remaining_time": "3:34:47", "throughput": 4402.9, "total_tokens": 75562080} {"current_steps": 35015, "total_steps": 61300, "loss": 0.339, "lr": 2.3152434131172368e-05, "epoch": 5.712071778140293, "percentage": 57.12, "elapsed_time": "4:46:03", "remaining_time": "3:34:44", "throughput": 4402.95, "total_tokens": 75571616} {"current_steps": 35020, "total_steps": 61300, "loss": 0.3409, "lr": 2.3145335688284288e-05, "epoch": 5.712887438825448, "percentage": 57.13, "elapsed_time": "4:46:06", "remaining_time": "3:34:41", "throughput": 4403.0, "total_tokens": 75581952} {"current_steps": 35025, "total_steps": 61300, "loss": 0.3732, "lr": 2.3138237395744712e-05, "epoch": 5.713703099510604, "percentage": 57.14, "elapsed_time": "4:46:08", "remaining_time": "3:34:39", "throughput": 4403.05, "total_tokens": 75592448} {"current_steps": 35030, "total_steps": 61300, "loss": 0.3206, "lr": 2.313113925412905e-05, "epoch": 5.714518760195759, "percentage": 57.15, "elapsed_time": "4:46:10", "remaining_time": "3:34:36", "throughput": 4403.1, "total_tokens": 75603872} {"current_steps": 35035, "total_steps": 61300, "loss": 0.3185, "lr": 2.312404126401273e-05, "epoch": 5.715334420880914, "percentage": 57.15, "elapsed_time": "4:46:12", "remaining_time": "3:34:34", "throughput": 4403.16, "total_tokens": 75614752} {"current_steps": 35040, "total_steps": 61300, "loss": 0.3391, "lr": 2.3116943425971144e-05, "epoch": 5.716150081566068, "percentage": 57.16, "elapsed_time": "4:46:15", "remaining_time": "3:34:31", "throughput": 4403.2, "total_tokens": 75625600} {"current_steps": 35045, "total_steps": 61300, "loss": 0.3764, "lr": 2.3109845740579676e-05, "epoch": 5.716965742251223, "percentage": 57.17, "elapsed_time": "4:46:17", "remaining_time": "3:34:28", "throughput": 4403.25, "total_tokens": 75635648} {"current_steps": 35050, "total_steps": 61300, "loss": 0.3536, "lr": 2.3102748208413706e-05, "epoch": 5.717781402936378, "percentage": 57.18, "elapsed_time": "4:46:19", "remaining_time": "3:34:26", "throughput": 4403.31, "total_tokens": 75647680} {"current_steps": 35055, "total_steps": 61300, "loss": 0.3208, "lr": 2.3095650830048595e-05, "epoch": 5.718597063621534, "percentage": 57.19, "elapsed_time": "4:46:21", "remaining_time": "3:34:23", "throughput": 4403.36, "total_tokens": 75658080} {"current_steps": 35060, "total_steps": 61300, "loss": 0.3425, "lr": 2.3088553606059686e-05, "epoch": 5.719412724306689, "percentage": 57.19, "elapsed_time": "4:46:24", "remaining_time": "3:34:21", "throughput": 4403.42, "total_tokens": 75669920} {"current_steps": 35065, "total_steps": 61300, "loss": 0.3223, "lr": 2.308145653702232e-05, "epoch": 5.720228384991843, "percentage": 57.2, "elapsed_time": "4:46:26", "remaining_time": "3:34:18", "throughput": 4403.48, "total_tokens": 75681792} {"current_steps": 35070, "total_steps": 61300, "loss": 0.3073, "lr": 2.307435962351181e-05, "epoch": 5.721044045676998, "percentage": 57.21, "elapsed_time": "4:46:29", "remaining_time": "3:34:16", "throughput": 4403.54, "total_tokens": 75692992} {"current_steps": 35075, "total_steps": 61300, "loss": 0.3043, "lr": 2.3067262866103492e-05, "epoch": 5.721859706362153, "percentage": 57.22, "elapsed_time": "4:46:31", "remaining_time": "3:34:13", "throughput": 4403.6, "total_tokens": 75704608} {"current_steps": 35080, "total_steps": 61300, "loss": 0.3557, "lr": 2.3060166265372654e-05, "epoch": 5.722675367047309, "percentage": 57.23, "elapsed_time": "4:46:33", "remaining_time": "3:34:11", "throughput": 4403.65, "total_tokens": 75715328} {"current_steps": 35085, "total_steps": 61300, "loss": 0.353, "lr": 2.3053069821894578e-05, "epoch": 5.7234910277324635, "percentage": 57.23, "elapsed_time": "4:46:35", "remaining_time": "3:34:08", "throughput": 4403.7, "total_tokens": 75725376} {"current_steps": 35090, "total_steps": 61300, "loss": 0.3156, "lr": 2.3045973536244543e-05, "epoch": 5.724306688417618, "percentage": 57.24, "elapsed_time": "4:46:38", "remaining_time": "3:34:05", "throughput": 4403.76, "total_tokens": 75736512} {"current_steps": 35095, "total_steps": 61300, "loss": 0.3581, "lr": 2.303887740899781e-05, "epoch": 5.725122349102773, "percentage": 57.25, "elapsed_time": "4:46:40", "remaining_time": "3:34:03", "throughput": 4403.82, "total_tokens": 75747552} {"current_steps": 35100, "total_steps": 61300, "loss": 0.3325, "lr": 2.3031781440729623e-05, "epoch": 5.725938009787928, "percentage": 57.26, "elapsed_time": "4:46:42", "remaining_time": "3:34:00", "throughput": 4403.87, "total_tokens": 75759136} {"current_steps": 35105, "total_steps": 61300, "loss": 0.3521, "lr": 2.3024685632015218e-05, "epoch": 5.726753670473083, "percentage": 57.27, "elapsed_time": "4:46:45", "remaining_time": "3:33:58", "throughput": 4403.94, "total_tokens": 75770208} {"current_steps": 35110, "total_steps": 61300, "loss": 0.3186, "lr": 2.3017589983429817e-05, "epoch": 5.7275693311582385, "percentage": 57.28, "elapsed_time": "4:46:47", "remaining_time": "3:33:55", "throughput": 4404.0, "total_tokens": 75780800} {"current_steps": 35115, "total_steps": 61300, "loss": 0.3168, "lr": 2.301049449554863e-05, "epoch": 5.728384991843393, "percentage": 57.28, "elapsed_time": "4:46:49", "remaining_time": "3:33:52", "throughput": 4404.05, "total_tokens": 75791328} {"current_steps": 35120, "total_steps": 61300, "loss": 0.3677, "lr": 2.3003399168946855e-05, "epoch": 5.729200652528548, "percentage": 57.29, "elapsed_time": "4:46:51", "remaining_time": "3:33:50", "throughput": 4404.11, "total_tokens": 75802688} {"current_steps": 35125, "total_steps": 61300, "loss": 0.3149, "lr": 2.2996304004199677e-05, "epoch": 5.730016313213703, "percentage": 57.3, "elapsed_time": "4:46:53", "remaining_time": "3:33:47", "throughput": 4404.16, "total_tokens": 75812640} {"current_steps": 35130, "total_steps": 61300, "loss": 0.3421, "lr": 2.298920900188226e-05, "epoch": 5.730831973898858, "percentage": 57.31, "elapsed_time": "4:46:56", "remaining_time": "3:33:45", "throughput": 4404.22, "total_tokens": 75823680} {"current_steps": 35135, "total_steps": 61300, "loss": 0.2979, "lr": 2.2982114162569766e-05, "epoch": 5.731647634584013, "percentage": 57.32, "elapsed_time": "4:46:58", "remaining_time": "3:33:42", "throughput": 4404.26, "total_tokens": 75834208} {"current_steps": 35140, "total_steps": 61300, "loss": 0.3806, "lr": 2.2975019486837334e-05, "epoch": 5.732463295269168, "percentage": 57.32, "elapsed_time": "4:47:00", "remaining_time": "3:33:40", "throughput": 4404.32, "total_tokens": 75846432} {"current_steps": 35145, "total_steps": 61300, "loss": 0.3873, "lr": 2.29679249752601e-05, "epoch": 5.733278955954323, "percentage": 57.33, "elapsed_time": "4:47:03", "remaining_time": "3:33:37", "throughput": 4404.38, "total_tokens": 75856960} {"current_steps": 35150, "total_steps": 61300, "loss": 0.3342, "lr": 2.2960830628413175e-05, "epoch": 5.734094616639478, "percentage": 57.34, "elapsed_time": "4:47:05", "remaining_time": "3:33:34", "throughput": 4404.44, "total_tokens": 75868256} {"current_steps": 35155, "total_steps": 61300, "loss": 0.3188, "lr": 2.295373644687167e-05, "epoch": 5.734910277324633, "percentage": 57.35, "elapsed_time": "4:47:07", "remaining_time": "3:33:32", "throughput": 4404.49, "total_tokens": 75879808} {"current_steps": 35160, "total_steps": 61300, "loss": 0.3111, "lr": 2.294664243121067e-05, "epoch": 5.735725938009788, "percentage": 57.36, "elapsed_time": "4:47:10", "remaining_time": "3:33:29", "throughput": 4404.55, "total_tokens": 75891168} {"current_steps": 35165, "total_steps": 61300, "loss": 0.3305, "lr": 2.2939548582005253e-05, "epoch": 5.736541598694943, "percentage": 57.37, "elapsed_time": "4:47:12", "remaining_time": "3:33:27", "throughput": 4404.6, "total_tokens": 75902080} {"current_steps": 35170, "total_steps": 61300, "loss": 0.3523, "lr": 2.293245489983048e-05, "epoch": 5.737357259380098, "percentage": 57.37, "elapsed_time": "4:47:14", "remaining_time": "3:33:24", "throughput": 4404.66, "total_tokens": 75913568} {"current_steps": 35175, "total_steps": 61300, "loss": 0.3569, "lr": 2.2925361385261402e-05, "epoch": 5.738172920065253, "percentage": 57.38, "elapsed_time": "4:47:16", "remaining_time": "3:33:22", "throughput": 4404.71, "total_tokens": 75923552} {"current_steps": 35180, "total_steps": 61300, "loss": 0.359, "lr": 2.2918268038873055e-05, "epoch": 5.738988580750408, "percentage": 57.39, "elapsed_time": "4:47:19", "remaining_time": "3:33:19", "throughput": 4404.76, "total_tokens": 75933856} {"current_steps": 35185, "total_steps": 61300, "loss": 0.3309, "lr": 2.291117486124047e-05, "epoch": 5.739804241435563, "percentage": 57.4, "elapsed_time": "4:47:21", "remaining_time": "3:33:16", "throughput": 4404.82, "total_tokens": 75944896} {"current_steps": 35190, "total_steps": 61300, "loss": 0.3286, "lr": 2.290408185293865e-05, "epoch": 5.740619902120718, "percentage": 57.41, "elapsed_time": "4:47:23", "remaining_time": "3:33:14", "throughput": 4404.88, "total_tokens": 75954880} {"current_steps": 35195, "total_steps": 61300, "loss": 0.3419, "lr": 2.2896989014542584e-05, "epoch": 5.741435562805873, "percentage": 57.41, "elapsed_time": "4:47:25", "remaining_time": "3:33:11", "throughput": 4404.93, "total_tokens": 75964800} {"current_steps": 35200, "total_steps": 61300, "loss": 0.3505, "lr": 2.2889896346627256e-05, "epoch": 5.742251223491028, "percentage": 57.42, "elapsed_time": "4:47:27", "remaining_time": "3:33:08", "throughput": 4404.98, "total_tokens": 75975264} {"current_steps": 35205, "total_steps": 61300, "loss": 0.3105, "lr": 2.2882803849767646e-05, "epoch": 5.743066884176183, "percentage": 57.43, "elapsed_time": "4:47:30", "remaining_time": "3:33:06", "throughput": 4405.04, "total_tokens": 75986976} {"current_steps": 35210, "total_steps": 61300, "loss": 0.3405, "lr": 2.2875711524538697e-05, "epoch": 5.7438825448613375, "percentage": 57.44, "elapsed_time": "4:47:32", "remaining_time": "3:33:03", "throughput": 4405.11, "total_tokens": 75998752} {"current_steps": 35215, "total_steps": 61300, "loss": 0.3589, "lr": 2.2868619371515348e-05, "epoch": 5.744698205546492, "percentage": 57.45, "elapsed_time": "4:47:34", "remaining_time": "3:33:01", "throughput": 4405.17, "total_tokens": 76010688} {"current_steps": 35220, "total_steps": 61300, "loss": 0.3631, "lr": 2.2861527391272526e-05, "epoch": 5.745513866231647, "percentage": 57.46, "elapsed_time": "4:47:37", "remaining_time": "3:32:58", "throughput": 4405.22, "total_tokens": 76021408} {"current_steps": 35225, "total_steps": 61300, "loss": 0.314, "lr": 2.285443558438515e-05, "epoch": 5.746329526916803, "percentage": 57.46, "elapsed_time": "4:47:39", "remaining_time": "3:32:56", "throughput": 4405.28, "total_tokens": 76032480} {"current_steps": 35230, "total_steps": 61300, "loss": 0.3271, "lr": 2.2847343951428106e-05, "epoch": 5.747145187601958, "percentage": 57.47, "elapsed_time": "4:47:41", "remaining_time": "3:32:53", "throughput": 4405.33, "total_tokens": 76043072} {"current_steps": 35235, "total_steps": 61300, "loss": 0.349, "lr": 2.284025249297629e-05, "epoch": 5.7479608482871125, "percentage": 57.48, "elapsed_time": "4:47:43", "remaining_time": "3:32:50", "throughput": 4405.39, "total_tokens": 76054208} {"current_steps": 35240, "total_steps": 61300, "loss": 0.3629, "lr": 2.2833161209604557e-05, "epoch": 5.748776508972267, "percentage": 57.49, "elapsed_time": "4:47:46", "remaining_time": "3:32:48", "throughput": 4405.46, "total_tokens": 76066080} {"current_steps": 35245, "total_steps": 61300, "loss": 0.3168, "lr": 2.2826070101887777e-05, "epoch": 5.749592169657422, "percentage": 57.5, "elapsed_time": "4:47:48", "remaining_time": "3:32:45", "throughput": 4405.51, "total_tokens": 76077088} {"current_steps": 35250, "total_steps": 61300, "loss": 0.3453, "lr": 2.2818979170400785e-05, "epoch": 5.750407830342578, "percentage": 57.5, "elapsed_time": "4:47:50", "remaining_time": "3:32:43", "throughput": 4405.55, "total_tokens": 76087104} {"current_steps": 35255, "total_steps": 61300, "loss": 0.359, "lr": 2.2811888415718405e-05, "epoch": 5.751223491027733, "percentage": 57.51, "elapsed_time": "4:47:53", "remaining_time": "3:32:40", "throughput": 4405.61, "total_tokens": 76098560} {"current_steps": 35260, "total_steps": 61300, "loss": 0.3612, "lr": 2.2804797838415448e-05, "epoch": 5.7520391517128875, "percentage": 57.52, "elapsed_time": "4:47:55", "remaining_time": "3:32:38", "throughput": 4405.67, "total_tokens": 76109472} {"current_steps": 35265, "total_steps": 61300, "loss": 0.3403, "lr": 2.2797707439066724e-05, "epoch": 5.752854812398042, "percentage": 57.53, "elapsed_time": "4:47:57", "remaining_time": "3:32:35", "throughput": 4405.7, "total_tokens": 76119744} {"current_steps": 35270, "total_steps": 61300, "loss": 0.31, "lr": 2.2790617218247005e-05, "epoch": 5.753670473083197, "percentage": 57.54, "elapsed_time": "4:47:59", "remaining_time": "3:32:32", "throughput": 4405.75, "total_tokens": 76129664} {"current_steps": 35275, "total_steps": 61300, "loss": 0.3525, "lr": 2.278352717653107e-05, "epoch": 5.754486133768353, "percentage": 57.54, "elapsed_time": "4:48:01", "remaining_time": "3:32:30", "throughput": 4405.81, "total_tokens": 76140384} {"current_steps": 35280, "total_steps": 61300, "loss": 0.3385, "lr": 2.2776437314493666e-05, "epoch": 5.755301794453508, "percentage": 57.55, "elapsed_time": "4:48:03", "remaining_time": "3:32:27", "throughput": 4405.86, "total_tokens": 76150624} {"current_steps": 35285, "total_steps": 61300, "loss": 0.3198, "lr": 2.2769347632709523e-05, "epoch": 5.7561174551386625, "percentage": 57.56, "elapsed_time": "4:48:06", "remaining_time": "3:32:24", "throughput": 4405.92, "total_tokens": 76161952} {"current_steps": 35290, "total_steps": 61300, "loss": 0.3348, "lr": 2.276225813175339e-05, "epoch": 5.756933115823817, "percentage": 57.57, "elapsed_time": "4:48:08", "remaining_time": "3:32:22", "throughput": 4405.99, "total_tokens": 76173600} {"current_steps": 35295, "total_steps": 61300, "loss": 0.3107, "lr": 2.275516881219997e-05, "epoch": 5.757748776508972, "percentage": 57.58, "elapsed_time": "4:48:10", "remaining_time": "3:32:19", "throughput": 4406.03, "total_tokens": 76183808} {"current_steps": 35300, "total_steps": 61300, "loss": 0.3713, "lr": 2.2748079674623954e-05, "epoch": 5.758564437194127, "percentage": 57.59, "elapsed_time": "4:48:13", "remaining_time": "3:32:17", "throughput": 4406.09, "total_tokens": 76194752} {"current_steps": 35305, "total_steps": 61300, "loss": 0.3452, "lr": 2.2740990719600026e-05, "epoch": 5.759380097879282, "percentage": 57.59, "elapsed_time": "4:48:15", "remaining_time": "3:32:14", "throughput": 4406.14, "total_tokens": 76205696} {"current_steps": 35310, "total_steps": 61300, "loss": 0.345, "lr": 2.2733901947702852e-05, "epoch": 5.760195758564437, "percentage": 57.6, "elapsed_time": "4:48:17", "remaining_time": "3:32:11", "throughput": 4406.18, "total_tokens": 76215072} {"current_steps": 35315, "total_steps": 61300, "loss": 0.386, "lr": 2.2726813359507084e-05, "epoch": 5.761011419249592, "percentage": 57.61, "elapsed_time": "4:48:19", "remaining_time": "3:32:09", "throughput": 4406.23, "total_tokens": 76225248} {"current_steps": 35320, "total_steps": 61300, "loss": 0.3354, "lr": 2.271972495558736e-05, "epoch": 5.761827079934747, "percentage": 57.62, "elapsed_time": "4:48:21", "remaining_time": "3:32:06", "throughput": 4406.28, "total_tokens": 76235552} {"current_steps": 35325, "total_steps": 61300, "loss": 0.3595, "lr": 2.27126367365183e-05, "epoch": 5.762642740619902, "percentage": 57.63, "elapsed_time": "4:48:23", "remaining_time": "3:32:03", "throughput": 4406.34, "total_tokens": 76246624} {"current_steps": 35330, "total_steps": 61300, "loss": 0.342, "lr": 2.2705548702874512e-05, "epoch": 5.763458401305057, "percentage": 57.63, "elapsed_time": "4:48:25", "remaining_time": "3:32:01", "throughput": 4406.38, "total_tokens": 76256352} {"current_steps": 35335, "total_steps": 61300, "loss": 0.3335, "lr": 2.269846085523059e-05, "epoch": 5.764274061990212, "percentage": 57.64, "elapsed_time": "4:48:28", "remaining_time": "3:31:58", "throughput": 4406.44, "total_tokens": 76266912} {"current_steps": 35340, "total_steps": 61300, "loss": 0.3695, "lr": 2.2691373194161107e-05, "epoch": 5.765089722675367, "percentage": 57.65, "elapsed_time": "4:48:30", "remaining_time": "3:31:55", "throughput": 4406.48, "total_tokens": 76277344} {"current_steps": 35345, "total_steps": 61300, "loss": 0.3406, "lr": 2.2684285720240624e-05, "epoch": 5.765905383360522, "percentage": 57.66, "elapsed_time": "4:48:32", "remaining_time": "3:31:53", "throughput": 4406.54, "total_tokens": 76288544} {"current_steps": 35350, "total_steps": 61300, "loss": 0.3253, "lr": 2.2677198434043695e-05, "epoch": 5.766721044045677, "percentage": 57.67, "elapsed_time": "4:48:34", "remaining_time": "3:31:50", "throughput": 4406.58, "total_tokens": 76299744} {"current_steps": 35355, "total_steps": 61300, "loss": 0.3682, "lr": 2.2670111336144844e-05, "epoch": 5.767536704730832, "percentage": 57.68, "elapsed_time": "4:48:36", "remaining_time": "3:31:47", "throughput": 4406.63, "total_tokens": 76309280} {"current_steps": 35360, "total_steps": 61300, "loss": 0.3336, "lr": 2.2663024427118592e-05, "epoch": 5.768352365415987, "percentage": 57.68, "elapsed_time": "4:48:38", "remaining_time": "3:31:45", "throughput": 4406.68, "total_tokens": 76319072} {"current_steps": 35365, "total_steps": 61300, "loss": 0.3842, "lr": 2.2655937707539437e-05, "epoch": 5.769168026101142, "percentage": 57.69, "elapsed_time": "4:48:41", "remaining_time": "3:31:42", "throughput": 4406.73, "total_tokens": 76329696} {"current_steps": 35370, "total_steps": 61300, "loss": 0.3566, "lr": 2.2648851177981868e-05, "epoch": 5.769983686786297, "percentage": 57.7, "elapsed_time": "4:48:43", "remaining_time": "3:31:39", "throughput": 4406.78, "total_tokens": 76339904} {"current_steps": 35375, "total_steps": 61300, "loss": 0.3613, "lr": 2.264176483902035e-05, "epoch": 5.770799347471452, "percentage": 57.71, "elapsed_time": "4:48:45", "remaining_time": "3:31:37", "throughput": 4406.84, "total_tokens": 76351776} {"current_steps": 35380, "total_steps": 61300, "loss": 0.3364, "lr": 2.263467869122934e-05, "epoch": 5.771615008156607, "percentage": 57.72, "elapsed_time": "4:48:47", "remaining_time": "3:31:34", "throughput": 4406.88, "total_tokens": 76362208} {"current_steps": 35385, "total_steps": 61300, "loss": 0.3502, "lr": 2.262759273518327e-05, "epoch": 5.7724306688417615, "percentage": 57.72, "elapsed_time": "4:48:50", "remaining_time": "3:31:32", "throughput": 4406.95, "total_tokens": 76374624} {"current_steps": 35390, "total_steps": 61300, "loss": 0.3467, "lr": 2.262050697145657e-05, "epoch": 5.773246329526917, "percentage": 57.73, "elapsed_time": "4:48:52", "remaining_time": "3:31:29", "throughput": 4406.99, "total_tokens": 76384064} {"current_steps": 35395, "total_steps": 61300, "loss": 0.3373, "lr": 2.2613421400623653e-05, "epoch": 5.774061990212072, "percentage": 57.74, "elapsed_time": "4:48:54", "remaining_time": "3:31:26", "throughput": 4407.05, "total_tokens": 76394976} {"current_steps": 35400, "total_steps": 61300, "loss": 0.3407, "lr": 2.2606336023258907e-05, "epoch": 5.774877650897227, "percentage": 57.75, "elapsed_time": "4:48:57", "remaining_time": "3:31:24", "throughput": 4407.11, "total_tokens": 76407136} {"current_steps": 35405, "total_steps": 61300, "loss": 0.3365, "lr": 2.259925083993671e-05, "epoch": 5.775693311582382, "percentage": 57.76, "elapsed_time": "4:48:59", "remaining_time": "3:31:21", "throughput": 4407.16, "total_tokens": 76417536} {"current_steps": 35410, "total_steps": 61300, "loss": 0.334, "lr": 2.2592165851231423e-05, "epoch": 5.7765089722675365, "percentage": 57.77, "elapsed_time": "4:49:01", "remaining_time": "3:31:19", "throughput": 4407.22, "total_tokens": 76428576} {"current_steps": 35415, "total_steps": 61300, "loss": 0.3271, "lr": 2.2585081057717387e-05, "epoch": 5.777324632952691, "percentage": 57.77, "elapsed_time": "4:49:03", "remaining_time": "3:31:16", "throughput": 4407.26, "total_tokens": 76439040} {"current_steps": 35420, "total_steps": 61300, "loss": 0.3314, "lr": 2.2577996459968935e-05, "epoch": 5.778140293637847, "percentage": 57.78, "elapsed_time": "4:49:06", "remaining_time": "3:31:14", "throughput": 4407.33, "total_tokens": 76450624} {"current_steps": 35425, "total_steps": 61300, "loss": 0.3297, "lr": 2.2570912058560375e-05, "epoch": 5.778955954323002, "percentage": 57.79, "elapsed_time": "4:49:08", "remaining_time": "3:31:11", "throughput": 4407.37, "total_tokens": 76459840} {"current_steps": 35430, "total_steps": 61300, "loss": 0.3281, "lr": 2.2563827854066007e-05, "epoch": 5.779771615008157, "percentage": 57.8, "elapsed_time": "4:49:10", "remaining_time": "3:31:08", "throughput": 4407.43, "total_tokens": 76470688} {"current_steps": 35435, "total_steps": 61300, "loss": 0.3338, "lr": 2.2556743847060118e-05, "epoch": 5.780587275693311, "percentage": 57.81, "elapsed_time": "4:49:12", "remaining_time": "3:31:06", "throughput": 4407.48, "total_tokens": 76481728} {"current_steps": 35440, "total_steps": 61300, "loss": 0.383, "lr": 2.254966003811697e-05, "epoch": 5.781402936378466, "percentage": 57.81, "elapsed_time": "4:49:14", "remaining_time": "3:31:03", "throughput": 4407.54, "total_tokens": 76492032} {"current_steps": 35445, "total_steps": 61300, "loss": 0.3499, "lr": 2.2542576427810813e-05, "epoch": 5.782218597063622, "percentage": 57.82, "elapsed_time": "4:49:17", "remaining_time": "3:31:00", "throughput": 4407.59, "total_tokens": 76502784} {"current_steps": 35450, "total_steps": 61300, "loss": 0.3253, "lr": 2.2535493016715882e-05, "epoch": 5.783034257748777, "percentage": 57.83, "elapsed_time": "4:49:19", "remaining_time": "3:30:58", "throughput": 4407.64, "total_tokens": 76513856} {"current_steps": 35455, "total_steps": 61300, "loss": 0.3563, "lr": 2.2528409805406388e-05, "epoch": 5.783849918433932, "percentage": 57.84, "elapsed_time": "4:49:21", "remaining_time": "3:30:55", "throughput": 4407.7, "total_tokens": 76525056} {"current_steps": 35460, "total_steps": 61300, "loss": 0.3505, "lr": 2.2521326794456537e-05, "epoch": 5.784665579119086, "percentage": 57.85, "elapsed_time": "4:49:23", "remaining_time": "3:30:53", "throughput": 4407.75, "total_tokens": 76535584} {"current_steps": 35465, "total_steps": 61300, "loss": 0.3289, "lr": 2.2514243984440512e-05, "epoch": 5.785481239804241, "percentage": 57.85, "elapsed_time": "4:49:26", "remaining_time": "3:30:50", "throughput": 4407.81, "total_tokens": 76547168} {"current_steps": 35470, "total_steps": 61300, "loss": 0.3451, "lr": 2.2507161375932484e-05, "epoch": 5.786296900489396, "percentage": 57.86, "elapsed_time": "4:49:28", "remaining_time": "3:30:48", "throughput": 4407.86, "total_tokens": 76557888} {"current_steps": 35475, "total_steps": 61300, "loss": 0.3593, "lr": 2.25000789695066e-05, "epoch": 5.787112561174552, "percentage": 57.87, "elapsed_time": "4:49:30", "remaining_time": "3:30:45", "throughput": 4407.92, "total_tokens": 76568864} {"current_steps": 35480, "total_steps": 61300, "loss": 0.3422, "lr": 2.2492996765737004e-05, "epoch": 5.787928221859707, "percentage": 57.88, "elapsed_time": "4:49:32", "remaining_time": "3:30:42", "throughput": 4407.98, "total_tokens": 76579296} {"current_steps": 35485, "total_steps": 61300, "loss": 0.3536, "lr": 2.2485914765197807e-05, "epoch": 5.788743882544861, "percentage": 57.89, "elapsed_time": "4:49:35", "remaining_time": "3:30:40", "throughput": 4408.04, "total_tokens": 76589824} {"current_steps": 35490, "total_steps": 61300, "loss": 0.3088, "lr": 2.247883296846311e-05, "epoch": 5.789559543230016, "percentage": 57.9, "elapsed_time": "4:49:37", "remaining_time": "3:30:37", "throughput": 4408.08, "total_tokens": 76599744} {"current_steps": 35495, "total_steps": 61300, "loss": 0.3323, "lr": 2.2471751376107006e-05, "epoch": 5.790375203915171, "percentage": 57.9, "elapsed_time": "4:49:39", "remaining_time": "3:30:35", "throughput": 4408.15, "total_tokens": 76612000} {"current_steps": 35500, "total_steps": 61300, "loss": 0.3162, "lr": 2.246466998870357e-05, "epoch": 5.791190864600326, "percentage": 57.91, "elapsed_time": "4:49:42", "remaining_time": "3:30:32", "throughput": 4408.21, "total_tokens": 76623936} {"current_steps": 35505, "total_steps": 61300, "loss": 0.3297, "lr": 2.245758880682685e-05, "epoch": 5.7920065252854815, "percentage": 57.92, "elapsed_time": "4:49:44", "remaining_time": "3:30:29", "throughput": 4408.26, "total_tokens": 76634240} {"current_steps": 35510, "total_steps": 61300, "loss": 0.3693, "lr": 2.2450507831050876e-05, "epoch": 5.792822185970636, "percentage": 57.93, "elapsed_time": "4:49:46", "remaining_time": "3:30:27", "throughput": 4408.32, "total_tokens": 76645344} {"current_steps": 35515, "total_steps": 61300, "loss": 0.3643, "lr": 2.2443427061949672e-05, "epoch": 5.793637846655791, "percentage": 57.94, "elapsed_time": "4:49:48", "remaining_time": "3:30:24", "throughput": 4408.37, "total_tokens": 76656000} {"current_steps": 35520, "total_steps": 61300, "loss": 0.3378, "lr": 2.2436346500097247e-05, "epoch": 5.794453507340946, "percentage": 57.94, "elapsed_time": "4:49:51", "remaining_time": "3:30:22", "throughput": 4408.42, "total_tokens": 76666976} {"current_steps": 35525, "total_steps": 61300, "loss": 0.3408, "lr": 2.2429266146067582e-05, "epoch": 5.795269168026101, "percentage": 57.95, "elapsed_time": "4:49:52", "remaining_time": "3:30:19", "throughput": 4408.45, "total_tokens": 76676192} {"current_steps": 35530, "total_steps": 61300, "loss": 0.3227, "lr": 2.242218600043465e-05, "epoch": 5.7960848287112565, "percentage": 57.96, "elapsed_time": "4:49:55", "remaining_time": "3:30:16", "throughput": 4408.5, "total_tokens": 76687104} {"current_steps": 35535, "total_steps": 61300, "loss": 0.3478, "lr": 2.2415106063772394e-05, "epoch": 5.796900489396411, "percentage": 57.97, "elapsed_time": "4:49:57", "remaining_time": "3:30:14", "throughput": 4408.56, "total_tokens": 76699104} {"current_steps": 35540, "total_steps": 61300, "loss": 0.3782, "lr": 2.240802633665476e-05, "epoch": 5.797716150081566, "percentage": 57.98, "elapsed_time": "4:50:00", "remaining_time": "3:30:11", "throughput": 4408.61, "total_tokens": 76710464} {"current_steps": 35545, "total_steps": 61300, "loss": 0.3069, "lr": 2.2400946819655663e-05, "epoch": 5.798531810766721, "percentage": 57.99, "elapsed_time": "4:50:02", "remaining_time": "3:30:09", "throughput": 4408.66, "total_tokens": 76720864} {"current_steps": 35550, "total_steps": 61300, "loss": 0.3537, "lr": 2.2393867513349002e-05, "epoch": 5.799347471451876, "percentage": 57.99, "elapsed_time": "4:50:04", "remaining_time": "3:30:06", "throughput": 4408.72, "total_tokens": 76731520} {"current_steps": 35555, "total_steps": 61300, "loss": 0.3433, "lr": 2.238678841830867e-05, "epoch": 5.800163132137031, "percentage": 58.0, "elapsed_time": "4:50:06", "remaining_time": "3:30:03", "throughput": 4408.75, "total_tokens": 76741536} {"current_steps": 35560, "total_steps": 61300, "loss": 0.3406, "lr": 2.2379709535108524e-05, "epoch": 5.800978792822186, "percentage": 58.01, "elapsed_time": "4:50:08", "remaining_time": "3:30:01", "throughput": 4408.8, "total_tokens": 76751904} {"current_steps": 35565, "total_steps": 61300, "loss": 0.343, "lr": 2.2372630864322416e-05, "epoch": 5.801794453507341, "percentage": 58.02, "elapsed_time": "4:50:10", "remaining_time": "3:29:58", "throughput": 4408.85, "total_tokens": 76761504} {"current_steps": 35570, "total_steps": 61300, "loss": 0.3405, "lr": 2.2365552406524183e-05, "epoch": 5.802610114192496, "percentage": 58.03, "elapsed_time": "4:50:12", "remaining_time": "3:29:55", "throughput": 4408.9, "total_tokens": 76771968} {"current_steps": 35575, "total_steps": 61300, "loss": 0.3214, "lr": 2.2358474162287635e-05, "epoch": 5.803425774877651, "percentage": 58.03, "elapsed_time": "4:50:15", "remaining_time": "3:29:53", "throughput": 4408.96, "total_tokens": 76782432} {"current_steps": 35580, "total_steps": 61300, "loss": 0.3662, "lr": 2.235139613218658e-05, "epoch": 5.804241435562806, "percentage": 58.04, "elapsed_time": "4:50:17", "remaining_time": "3:29:50", "throughput": 4409.01, "total_tokens": 76793152} {"current_steps": 35585, "total_steps": 61300, "loss": 0.3443, "lr": 2.234431831679479e-05, "epoch": 5.80505709624796, "percentage": 58.05, "elapsed_time": "4:50:19", "remaining_time": "3:29:48", "throughput": 4409.05, "total_tokens": 76804000} {"current_steps": 35590, "total_steps": 61300, "loss": 0.3582, "lr": 2.2337240716686035e-05, "epoch": 5.805872756933116, "percentage": 58.06, "elapsed_time": "4:50:21", "remaining_time": "3:29:45", "throughput": 4409.11, "total_tokens": 76814432} {"current_steps": 35595, "total_steps": 61300, "loss": 0.3507, "lr": 2.2330163332434056e-05, "epoch": 5.806688417618271, "percentage": 58.07, "elapsed_time": "4:50:24", "remaining_time": "3:29:42", "throughput": 4409.17, "total_tokens": 76825472} {"current_steps": 35600, "total_steps": 61300, "loss": 0.3643, "lr": 2.2323086164612584e-05, "epoch": 5.807504078303426, "percentage": 58.08, "elapsed_time": "4:50:26", "remaining_time": "3:29:40", "throughput": 4409.24, "total_tokens": 76837568} {"current_steps": 35605, "total_steps": 61300, "loss": 0.3263, "lr": 2.2316009213795323e-05, "epoch": 5.808319738988581, "percentage": 58.08, "elapsed_time": "4:50:28", "remaining_time": "3:29:37", "throughput": 4409.29, "total_tokens": 76848768} {"current_steps": 35610, "total_steps": 61300, "loss": 0.36, "lr": 2.230893248055598e-05, "epoch": 5.809135399673735, "percentage": 58.09, "elapsed_time": "4:50:31", "remaining_time": "3:29:35", "throughput": 4409.34, "total_tokens": 76860000} {"current_steps": 35615, "total_steps": 61300, "loss": 0.3445, "lr": 2.2301855965468226e-05, "epoch": 5.809951060358891, "percentage": 58.1, "elapsed_time": "4:50:33", "remaining_time": "3:29:32", "throughput": 4409.4, "total_tokens": 76871904} {"current_steps": 35620, "total_steps": 61300, "loss": 0.3402, "lr": 2.2294779669105716e-05, "epoch": 5.810766721044046, "percentage": 58.11, "elapsed_time": "4:50:35", "remaining_time": "3:29:30", "throughput": 4409.44, "total_tokens": 76881504} {"current_steps": 35625, "total_steps": 61300, "loss": 0.3403, "lr": 2.2287703592042096e-05, "epoch": 5.811582381729201, "percentage": 58.12, "elapsed_time": "4:50:38", "remaining_time": "3:29:27", "throughput": 4409.5, "total_tokens": 76894080} {"current_steps": 35630, "total_steps": 61300, "loss": 0.346, "lr": 2.2280627734850984e-05, "epoch": 5.8123980424143555, "percentage": 58.12, "elapsed_time": "4:50:40", "remaining_time": "3:29:25", "throughput": 4409.56, "total_tokens": 76904672} {"current_steps": 35635, "total_steps": 61300, "loss": 0.3647, "lr": 2.2273552098105983e-05, "epoch": 5.81321370309951, "percentage": 58.13, "elapsed_time": "4:50:42", "remaining_time": "3:29:22", "throughput": 4409.61, "total_tokens": 76914976} {"current_steps": 35640, "total_steps": 61300, "loss": 0.3366, "lr": 2.2266476682380685e-05, "epoch": 5.814029363784666, "percentage": 58.14, "elapsed_time": "4:50:44", "remaining_time": "3:29:19", "throughput": 4409.65, "total_tokens": 76925824} {"current_steps": 35645, "total_steps": 61300, "loss": 0.3209, "lr": 2.2259401488248658e-05, "epoch": 5.814845024469821, "percentage": 58.15, "elapsed_time": "4:50:47", "remaining_time": "3:29:17", "throughput": 4409.69, "total_tokens": 76936160} {"current_steps": 35650, "total_steps": 61300, "loss": 0.3651, "lr": 2.225232651628345e-05, "epoch": 5.815660685154976, "percentage": 58.16, "elapsed_time": "4:50:49", "remaining_time": "3:29:14", "throughput": 4409.75, "total_tokens": 76946016} {"current_steps": 35655, "total_steps": 61300, "loss": 0.3697, "lr": 2.2245251767058595e-05, "epoch": 5.8164763458401305, "percentage": 58.16, "elapsed_time": "4:50:51", "remaining_time": "3:29:11", "throughput": 4409.8, "total_tokens": 76956704} {"current_steps": 35660, "total_steps": 61300, "loss": 0.3605, "lr": 2.2238177241147607e-05, "epoch": 5.817292006525285, "percentage": 58.17, "elapsed_time": "4:50:53", "remaining_time": "3:29:09", "throughput": 4409.86, "total_tokens": 76967360} {"current_steps": 35665, "total_steps": 61300, "loss": 0.3563, "lr": 2.223110293912399e-05, "epoch": 5.81810766721044, "percentage": 58.18, "elapsed_time": "4:50:55", "remaining_time": "3:29:06", "throughput": 4409.92, "total_tokens": 76979008} {"current_steps": 35670, "total_steps": 61300, "loss": 0.3488, "lr": 2.2224028861561215e-05, "epoch": 5.818923327895595, "percentage": 58.19, "elapsed_time": "4:50:57", "remaining_time": "3:29:04", "throughput": 4409.98, "total_tokens": 76988800} {"current_steps": 35675, "total_steps": 61300, "loss": 0.3263, "lr": 2.2216955009032747e-05, "epoch": 5.819738988580751, "percentage": 58.2, "elapsed_time": "4:51:00", "remaining_time": "3:29:01", "throughput": 4410.03, "total_tokens": 76999616} {"current_steps": 35680, "total_steps": 61300, "loss": 0.3462, "lr": 2.2209881382112026e-05, "epoch": 5.8205546492659055, "percentage": 58.21, "elapsed_time": "4:51:02", "remaining_time": "3:28:58", "throughput": 4410.08, "total_tokens": 77010656} {"current_steps": 35685, "total_steps": 61300, "loss": 0.3267, "lr": 2.220280798137248e-05, "epoch": 5.82137030995106, "percentage": 58.21, "elapsed_time": "4:51:04", "remaining_time": "3:28:56", "throughput": 4410.14, "total_tokens": 77021920} {"current_steps": 35690, "total_steps": 61300, "loss": 0.3377, "lr": 2.219573480738751e-05, "epoch": 5.822185970636215, "percentage": 58.22, "elapsed_time": "4:51:06", "remaining_time": "3:28:53", "throughput": 4410.18, "total_tokens": 77032416} {"current_steps": 35695, "total_steps": 61300, "loss": 0.3054, "lr": 2.2188661860730507e-05, "epoch": 5.82300163132137, "percentage": 58.23, "elapsed_time": "4:51:09", "remaining_time": "3:28:51", "throughput": 4410.23, "total_tokens": 77042944} {"current_steps": 35700, "total_steps": 61300, "loss": 0.3046, "lr": 2.2181589141974836e-05, "epoch": 5.823817292006526, "percentage": 58.24, "elapsed_time": "4:51:10", "remaining_time": "3:28:48", "throughput": 4410.28, "total_tokens": 77051584} {"current_steps": 35705, "total_steps": 61300, "loss": 0.3576, "lr": 2.217451665169385e-05, "epoch": 5.8246329526916805, "percentage": 58.25, "elapsed_time": "4:51:13", "remaining_time": "3:28:45", "throughput": 4410.33, "total_tokens": 77062048} {"current_steps": 35710, "total_steps": 61300, "loss": 0.3981, "lr": 2.216744439046087e-05, "epoch": 5.825448613376835, "percentage": 58.25, "elapsed_time": "4:51:15", "remaining_time": "3:28:43", "throughput": 4410.39, "total_tokens": 77074080} {"current_steps": 35715, "total_steps": 61300, "loss": 0.3681, "lr": 2.2160372358849234e-05, "epoch": 5.82626427406199, "percentage": 58.26, "elapsed_time": "4:51:17", "remaining_time": "3:28:40", "throughput": 4410.45, "total_tokens": 77085632} {"current_steps": 35720, "total_steps": 61300, "loss": 0.3657, "lr": 2.215330055743222e-05, "epoch": 5.827079934747145, "percentage": 58.27, "elapsed_time": "4:51:20", "remaining_time": "3:28:38", "throughput": 4410.49, "total_tokens": 77097664} {"current_steps": 35725, "total_steps": 61300, "loss": 0.3551, "lr": 2.2146228986783105e-05, "epoch": 5.827895595432301, "percentage": 58.28, "elapsed_time": "4:51:23", "remaining_time": "3:28:35", "throughput": 4410.54, "total_tokens": 77109568} {"current_steps": 35730, "total_steps": 61300, "loss": 0.3477, "lr": 2.213915764747515e-05, "epoch": 5.828711256117455, "percentage": 58.29, "elapsed_time": "4:51:25", "remaining_time": "3:28:33", "throughput": 4410.59, "total_tokens": 77119648} {"current_steps": 35735, "total_steps": 61300, "loss": 0.3386, "lr": 2.2132086540081593e-05, "epoch": 5.82952691680261, "percentage": 58.3, "elapsed_time": "4:51:27", "remaining_time": "3:28:30", "throughput": 4410.64, "total_tokens": 77132064} {"current_steps": 35740, "total_steps": 61300, "loss": 0.3286, "lr": 2.212501566517565e-05, "epoch": 5.830342577487765, "percentage": 58.3, "elapsed_time": "4:51:29", "remaining_time": "3:28:28", "throughput": 4410.69, "total_tokens": 77142880} {"current_steps": 35745, "total_steps": 61300, "loss": 0.326, "lr": 2.211794502333052e-05, "epoch": 5.83115823817292, "percentage": 58.31, "elapsed_time": "4:51:32", "remaining_time": "3:28:25", "throughput": 4410.75, "total_tokens": 77154272} {"current_steps": 35750, "total_steps": 61300, "loss": 0.3446, "lr": 2.2110874615119396e-05, "epoch": 5.831973898858075, "percentage": 58.32, "elapsed_time": "4:51:34", "remaining_time": "3:28:23", "throughput": 4410.8, "total_tokens": 77165280} {"current_steps": 35755, "total_steps": 61300, "loss": 0.3594, "lr": 2.2103804441115434e-05, "epoch": 5.8327895595432295, "percentage": 58.33, "elapsed_time": "4:51:36", "remaining_time": "3:28:20", "throughput": 4410.85, "total_tokens": 77176032} {"current_steps": 35760, "total_steps": 61300, "loss": 0.3434, "lr": 2.209673450189178e-05, "epoch": 5.833605220228385, "percentage": 58.34, "elapsed_time": "4:51:39", "remaining_time": "3:28:17", "throughput": 4410.91, "total_tokens": 77186880} {"current_steps": 35765, "total_steps": 61300, "loss": 0.3336, "lr": 2.208966479802156e-05, "epoch": 5.83442088091354, "percentage": 58.34, "elapsed_time": "4:51:41", "remaining_time": "3:28:15", "throughput": 4410.97, "total_tokens": 77196704} {"current_steps": 35770, "total_steps": 61300, "loss": 0.3421, "lr": 2.2082595330077878e-05, "epoch": 5.835236541598695, "percentage": 58.35, "elapsed_time": "4:51:43", "remaining_time": "3:28:12", "throughput": 4411.02, "total_tokens": 77208064} {"current_steps": 35775, "total_steps": 61300, "loss": 0.3232, "lr": 2.2075526098633816e-05, "epoch": 5.83605220228385, "percentage": 58.36, "elapsed_time": "4:51:45", "remaining_time": "3:28:10", "throughput": 4411.07, "total_tokens": 77219328} {"current_steps": 35780, "total_steps": 61300, "loss": 0.306, "lr": 2.206845710426245e-05, "epoch": 5.8368678629690045, "percentage": 58.37, "elapsed_time": "4:51:48", "remaining_time": "3:28:07", "throughput": 4411.13, "total_tokens": 77230592} {"current_steps": 35785, "total_steps": 61300, "loss": 0.3528, "lr": 2.2061388347536828e-05, "epoch": 5.83768352365416, "percentage": 58.38, "elapsed_time": "4:51:50", "remaining_time": "3:28:04", "throughput": 4411.18, "total_tokens": 77240992} {"current_steps": 35790, "total_steps": 61300, "loss": 0.3422, "lr": 2.2054319829029975e-05, "epoch": 5.838499184339315, "percentage": 58.38, "elapsed_time": "4:51:52", "remaining_time": "3:28:02", "throughput": 4411.22, "total_tokens": 77250144} {"current_steps": 35795, "total_steps": 61300, "loss": 0.37, "lr": 2.2047251549314907e-05, "epoch": 5.83931484502447, "percentage": 58.39, "elapsed_time": "4:51:54", "remaining_time": "3:27:59", "throughput": 4411.28, "total_tokens": 77262464} {"current_steps": 35800, "total_steps": 61300, "loss": 0.3389, "lr": 2.20401835089646e-05, "epoch": 5.840130505709625, "percentage": 58.4, "elapsed_time": "4:51:57", "remaining_time": "3:27:57", "throughput": 4411.33, "total_tokens": 77273248} {"current_steps": 35805, "total_steps": 61300, "loss": 0.3863, "lr": 2.2033115708552044e-05, "epoch": 5.8409461663947795, "percentage": 58.41, "elapsed_time": "4:51:59", "remaining_time": "3:27:54", "throughput": 4411.37, "total_tokens": 77284032} {"current_steps": 35810, "total_steps": 61300, "loss": 0.3284, "lr": 2.202604814865018e-05, "epoch": 5.841761827079935, "percentage": 58.42, "elapsed_time": "4:52:01", "remaining_time": "3:27:52", "throughput": 4411.42, "total_tokens": 77295072} {"current_steps": 35815, "total_steps": 61300, "loss": 0.3238, "lr": 2.201898082983194e-05, "epoch": 5.84257748776509, "percentage": 58.43, "elapsed_time": "4:52:03", "remaining_time": "3:27:49", "throughput": 4411.47, "total_tokens": 77306208} {"current_steps": 35820, "total_steps": 61300, "loss": 0.356, "lr": 2.2011913752670242e-05, "epoch": 5.843393148450245, "percentage": 58.43, "elapsed_time": "4:52:06", "remaining_time": "3:27:46", "throughput": 4411.52, "total_tokens": 77317024} {"current_steps": 35825, "total_steps": 61300, "loss": 0.3169, "lr": 2.2004846917737978e-05, "epoch": 5.8442088091354, "percentage": 58.44, "elapsed_time": "4:52:08", "remaining_time": "3:27:44", "throughput": 4411.58, "total_tokens": 77327648} {"current_steps": 35830, "total_steps": 61300, "loss": 0.3317, "lr": 2.1997780325608013e-05, "epoch": 5.8450244698205545, "percentage": 58.45, "elapsed_time": "4:52:10", "remaining_time": "3:27:41", "throughput": 4411.62, "total_tokens": 77338304} {"current_steps": 35835, "total_steps": 61300, "loss": 0.3724, "lr": 2.1990713976853216e-05, "epoch": 5.845840130505709, "percentage": 58.46, "elapsed_time": "4:52:12", "remaining_time": "3:27:39", "throughput": 4411.67, "total_tokens": 77348768} {"current_steps": 35840, "total_steps": 61300, "loss": 0.334, "lr": 2.1983647872046412e-05, "epoch": 5.846655791190865, "percentage": 58.47, "elapsed_time": "4:52:14", "remaining_time": "3:27:36", "throughput": 4411.72, "total_tokens": 77358208} {"current_steps": 35845, "total_steps": 61300, "loss": 0.3352, "lr": 2.1976582011760415e-05, "epoch": 5.84747145187602, "percentage": 58.47, "elapsed_time": "4:52:16", "remaining_time": "3:27:33", "throughput": 4411.77, "total_tokens": 77368896} {"current_steps": 35850, "total_steps": 61300, "loss": 0.3439, "lr": 2.1969516396568023e-05, "epoch": 5.848287112561175, "percentage": 58.48, "elapsed_time": "4:52:19", "remaining_time": "3:27:31", "throughput": 4411.83, "total_tokens": 77379616} {"current_steps": 35855, "total_steps": 61300, "loss": 0.3492, "lr": 2.196245102704201e-05, "epoch": 5.849102773246329, "percentage": 58.49, "elapsed_time": "4:52:21", "remaining_time": "3:27:28", "throughput": 4411.89, "total_tokens": 77390400} {"current_steps": 35860, "total_steps": 61300, "loss": 0.3589, "lr": 2.1955385903755127e-05, "epoch": 5.849918433931484, "percentage": 58.5, "elapsed_time": "4:52:23", "remaining_time": "3:27:25", "throughput": 4411.94, "total_tokens": 77400544} {"current_steps": 35865, "total_steps": 61300, "loss": 0.3414, "lr": 2.1948321027280108e-05, "epoch": 5.850734094616639, "percentage": 58.51, "elapsed_time": "4:52:25", "remaining_time": "3:27:23", "throughput": 4411.99, "total_tokens": 77411136} {"current_steps": 35870, "total_steps": 61300, "loss": 0.3378, "lr": 2.1941256398189676e-05, "epoch": 5.851549755301795, "percentage": 58.52, "elapsed_time": "4:52:27", "remaining_time": "3:27:20", "throughput": 4412.06, "total_tokens": 77422240} {"current_steps": 35875, "total_steps": 61300, "loss": 0.3356, "lr": 2.1934192017056515e-05, "epoch": 5.85236541598695, "percentage": 58.52, "elapsed_time": "4:52:29", "remaining_time": "3:27:17", "throughput": 4412.1, "total_tokens": 77431648} {"current_steps": 35880, "total_steps": 61300, "loss": 0.3216, "lr": 2.1927127884453307e-05, "epoch": 5.853181076672104, "percentage": 58.53, "elapsed_time": "4:52:32", "remaining_time": "3:27:15", "throughput": 4412.15, "total_tokens": 77443680} {"current_steps": 35885, "total_steps": 61300, "loss": 0.3487, "lr": 2.19200640009527e-05, "epoch": 5.853996737357259, "percentage": 58.54, "elapsed_time": "4:52:34", "remaining_time": "3:27:12", "throughput": 4412.2, "total_tokens": 77453824} {"current_steps": 35890, "total_steps": 61300, "loss": 0.3207, "lr": 2.1913000367127337e-05, "epoch": 5.854812398042414, "percentage": 58.55, "elapsed_time": "4:52:36", "remaining_time": "3:27:10", "throughput": 4412.26, "total_tokens": 77464512} {"current_steps": 35895, "total_steps": 61300, "loss": 0.3303, "lr": 2.190593698354983e-05, "epoch": 5.85562805872757, "percentage": 58.56, "elapsed_time": "4:52:38", "remaining_time": "3:27:07", "throughput": 4412.31, "total_tokens": 77475584} {"current_steps": 35900, "total_steps": 61300, "loss": 0.3156, "lr": 2.1898873850792768e-05, "epoch": 5.856443719412725, "percentage": 58.56, "elapsed_time": "4:52:41", "remaining_time": "3:27:04", "throughput": 4412.36, "total_tokens": 77486464} {"current_steps": 35905, "total_steps": 61300, "loss": 0.3468, "lr": 2.1891810969428724e-05, "epoch": 5.857259380097879, "percentage": 58.57, "elapsed_time": "4:52:43", "remaining_time": "3:27:02", "throughput": 4412.4, "total_tokens": 77495168} {"current_steps": 35910, "total_steps": 61300, "loss": 0.3219, "lr": 2.1884748340030255e-05, "epoch": 5.858075040783034, "percentage": 58.58, "elapsed_time": "4:52:45", "remaining_time": "3:26:59", "throughput": 4412.44, "total_tokens": 77505632} {"current_steps": 35915, "total_steps": 61300, "loss": 0.3182, "lr": 2.1877685963169893e-05, "epoch": 5.858890701468189, "percentage": 58.59, "elapsed_time": "4:52:47", "remaining_time": "3:26:56", "throughput": 4412.49, "total_tokens": 77516512} {"current_steps": 35920, "total_steps": 61300, "loss": 0.3466, "lr": 2.187062383942015e-05, "epoch": 5.859706362153344, "percentage": 58.6, "elapsed_time": "4:52:49", "remaining_time": "3:26:54", "throughput": 4412.55, "total_tokens": 77528352} {"current_steps": 35925, "total_steps": 61300, "loss": 0.3229, "lr": 2.186356196935351e-05, "epoch": 5.8605220228384995, "percentage": 58.61, "elapsed_time": "4:52:51", "remaining_time": "3:26:51", "throughput": 4412.58, "total_tokens": 77537728} {"current_steps": 35930, "total_steps": 61300, "loss": 0.3373, "lr": 2.185650035354245e-05, "epoch": 5.861337683523654, "percentage": 58.61, "elapsed_time": "4:52:54", "remaining_time": "3:26:49", "throughput": 4412.64, "total_tokens": 77549216} {"current_steps": 35935, "total_steps": 61300, "loss": 0.3288, "lr": 2.184943899255943e-05, "epoch": 5.862153344208809, "percentage": 58.62, "elapsed_time": "4:52:56", "remaining_time": "3:26:46", "throughput": 4412.69, "total_tokens": 77560288} {"current_steps": 35940, "total_steps": 61300, "loss": 0.3492, "lr": 2.1842377886976873e-05, "epoch": 5.862969004893964, "percentage": 58.63, "elapsed_time": "4:52:59", "remaining_time": "3:26:44", "throughput": 4412.75, "total_tokens": 77571968} {"current_steps": 35945, "total_steps": 61300, "loss": 0.3647, "lr": 2.183531703736718e-05, "epoch": 5.863784665579119, "percentage": 58.64, "elapsed_time": "4:53:01", "remaining_time": "3:26:41", "throughput": 4412.81, "total_tokens": 77583872} {"current_steps": 35950, "total_steps": 61300, "loss": 0.3708, "lr": 2.182825644430275e-05, "epoch": 5.864600326264274, "percentage": 58.65, "elapsed_time": "4:53:03", "remaining_time": "3:26:39", "throughput": 4412.87, "total_tokens": 77595232} {"current_steps": 35955, "total_steps": 61300, "loss": 0.3214, "lr": 2.1821196108355944e-05, "epoch": 5.865415986949429, "percentage": 58.65, "elapsed_time": "4:53:05", "remaining_time": "3:26:36", "throughput": 4412.93, "total_tokens": 77605696} {"current_steps": 35960, "total_steps": 61300, "loss": 0.347, "lr": 2.181413603009911e-05, "epoch": 5.866231647634584, "percentage": 58.66, "elapsed_time": "4:53:08", "remaining_time": "3:26:33", "throughput": 4412.97, "total_tokens": 77616192} {"current_steps": 35965, "total_steps": 61300, "loss": 0.3437, "lr": 2.1807076210104575e-05, "epoch": 5.867047308319739, "percentage": 58.67, "elapsed_time": "4:53:10", "remaining_time": "3:26:31", "throughput": 4413.02, "total_tokens": 77626688} {"current_steps": 35970, "total_steps": 61300, "loss": 0.335, "lr": 2.1800016648944638e-05, "epoch": 5.867862969004894, "percentage": 58.68, "elapsed_time": "4:53:12", "remaining_time": "3:26:28", "throughput": 4413.07, "total_tokens": 77637152} {"current_steps": 35975, "total_steps": 61300, "loss": 0.3339, "lr": 2.1792957347191594e-05, "epoch": 5.868678629690049, "percentage": 58.69, "elapsed_time": "4:53:14", "remaining_time": "3:26:25", "throughput": 4413.1, "total_tokens": 77647328} {"current_steps": 35980, "total_steps": 61300, "loss": 0.3462, "lr": 2.1785898305417698e-05, "epoch": 5.869494290375204, "percentage": 58.69, "elapsed_time": "4:53:16", "remaining_time": "3:26:23", "throughput": 4413.15, "total_tokens": 77657824} {"current_steps": 35985, "total_steps": 61300, "loss": 0.3361, "lr": 2.1778839524195195e-05, "epoch": 5.870309951060359, "percentage": 58.7, "elapsed_time": "4:53:19", "remaining_time": "3:26:20", "throughput": 4413.21, "total_tokens": 77668768} {"current_steps": 35990, "total_steps": 61300, "loss": 0.3345, "lr": 2.1771781004096304e-05, "epoch": 5.871125611745514, "percentage": 58.71, "elapsed_time": "4:53:21", "remaining_time": "3:26:18", "throughput": 4413.26, "total_tokens": 77679040} {"current_steps": 35995, "total_steps": 61300, "loss": 0.3184, "lr": 2.1764722745693223e-05, "epoch": 5.871941272430669, "percentage": 58.72, "elapsed_time": "4:53:23", "remaining_time": "3:26:15", "throughput": 4413.31, "total_tokens": 77690304} {"current_steps": 36000, "total_steps": 61300, "loss": 0.3452, "lr": 2.1757664749558132e-05, "epoch": 5.872756933115824, "percentage": 58.73, "elapsed_time": "4:53:25", "remaining_time": "3:26:12", "throughput": 4413.36, "total_tokens": 77700480} {"current_steps": 36005, "total_steps": 61300, "loss": 0.3117, "lr": 2.1750607016263192e-05, "epoch": 5.873572593800979, "percentage": 58.74, "elapsed_time": "4:53:28", "remaining_time": "3:26:10", "throughput": 4413.41, "total_tokens": 77711552} {"current_steps": 36010, "total_steps": 61300, "loss": 0.3436, "lr": 2.1743549546380527e-05, "epoch": 5.874388254486134, "percentage": 58.74, "elapsed_time": "4:53:30", "remaining_time": "3:26:07", "throughput": 4413.45, "total_tokens": 77722944} {"current_steps": 36015, "total_steps": 61300, "loss": 0.3452, "lr": 2.1736492340482267e-05, "epoch": 5.875203915171289, "percentage": 58.75, "elapsed_time": "4:53:32", "remaining_time": "3:26:05", "throughput": 4413.51, "total_tokens": 77735072} {"current_steps": 36020, "total_steps": 61300, "loss": 0.3452, "lr": 2.172943539914049e-05, "epoch": 5.876019575856444, "percentage": 58.76, "elapsed_time": "4:53:35", "remaining_time": "3:26:03", "throughput": 4413.57, "total_tokens": 77746848} {"current_steps": 36025, "total_steps": 61300, "loss": 0.3438, "lr": 2.172237872292728e-05, "epoch": 5.876835236541599, "percentage": 58.77, "elapsed_time": "4:53:37", "remaining_time": "3:26:00", "throughput": 4413.62, "total_tokens": 77757664} {"current_steps": 36030, "total_steps": 61300, "loss": 0.3255, "lr": 2.1715322312414664e-05, "epoch": 5.877650897226753, "percentage": 58.78, "elapsed_time": "4:53:39", "remaining_time": "3:25:57", "throughput": 4413.66, "total_tokens": 77768288} {"current_steps": 36035, "total_steps": 61300, "loss": 0.33, "lr": 2.1708266168174703e-05, "epoch": 5.878466557911908, "percentage": 58.78, "elapsed_time": "4:53:41", "remaining_time": "3:25:55", "throughput": 4413.7, "total_tokens": 77778080} {"current_steps": 36040, "total_steps": 61300, "loss": 0.3598, "lr": 2.170121029077939e-05, "epoch": 5.879282218597064, "percentage": 58.79, "elapsed_time": "4:53:44", "remaining_time": "3:25:52", "throughput": 4413.77, "total_tokens": 77790784} {"current_steps": 36045, "total_steps": 61300, "loss": 0.329, "lr": 2.1694154680800706e-05, "epoch": 5.880097879282219, "percentage": 58.8, "elapsed_time": "4:53:46", "remaining_time": "3:25:50", "throughput": 4413.81, "total_tokens": 77801344} {"current_steps": 36050, "total_steps": 61300, "loss": 0.3662, "lr": 2.168709933881062e-05, "epoch": 5.8809135399673735, "percentage": 58.81, "elapsed_time": "4:53:48", "remaining_time": "3:25:47", "throughput": 4413.85, "total_tokens": 77811392} {"current_steps": 36055, "total_steps": 61300, "loss": 0.3098, "lr": 2.168004426538106e-05, "epoch": 5.881729200652528, "percentage": 58.82, "elapsed_time": "4:53:50", "remaining_time": "3:25:44", "throughput": 4413.9, "total_tokens": 77821312} {"current_steps": 36060, "total_steps": 61300, "loss": 0.3436, "lr": 2.1672989461083964e-05, "epoch": 5.882544861337683, "percentage": 58.83, "elapsed_time": "4:53:53", "remaining_time": "3:25:42", "throughput": 4413.95, "total_tokens": 77831872} {"current_steps": 36065, "total_steps": 61300, "loss": 0.3623, "lr": 2.1665934926491226e-05, "epoch": 5.883360522022839, "percentage": 58.83, "elapsed_time": "4:53:55", "remaining_time": "3:25:39", "throughput": 4414.0, "total_tokens": 77842752} {"current_steps": 36070, "total_steps": 61300, "loss": 0.3353, "lr": 2.1658880662174717e-05, "epoch": 5.884176182707994, "percentage": 58.84, "elapsed_time": "4:53:57", "remaining_time": "3:25:37", "throughput": 4414.04, "total_tokens": 77853696} {"current_steps": 36075, "total_steps": 61300, "loss": 0.3356, "lr": 2.1651826668706297e-05, "epoch": 5.8849918433931485, "percentage": 58.85, "elapsed_time": "4:53:59", "remaining_time": "3:25:34", "throughput": 4414.09, "total_tokens": 77864288} {"current_steps": 36080, "total_steps": 61300, "loss": 0.3461, "lr": 2.1644772946657795e-05, "epoch": 5.885807504078303, "percentage": 58.86, "elapsed_time": "4:54:02", "remaining_time": "3:25:31", "throughput": 4414.14, "total_tokens": 77874880} {"current_steps": 36085, "total_steps": 61300, "loss": 0.3321, "lr": 2.163771949660102e-05, "epoch": 5.886623164763458, "percentage": 58.87, "elapsed_time": "4:54:04", "remaining_time": "3:25:29", "throughput": 4414.2, "total_tokens": 77886688} {"current_steps": 36090, "total_steps": 61300, "loss": 0.3686, "lr": 2.1630666319107767e-05, "epoch": 5.887438825448614, "percentage": 58.87, "elapsed_time": "4:54:06", "remaining_time": "3:25:26", "throughput": 4414.26, "total_tokens": 77897376} {"current_steps": 36095, "total_steps": 61300, "loss": 0.3308, "lr": 2.1623613414749797e-05, "epoch": 5.888254486133769, "percentage": 58.88, "elapsed_time": "4:54:09", "remaining_time": "3:25:24", "throughput": 4414.31, "total_tokens": 77908736} {"current_steps": 36100, "total_steps": 61300, "loss": 0.3072, "lr": 2.1616560784098856e-05, "epoch": 5.8890701468189235, "percentage": 58.89, "elapsed_time": "4:54:11", "remaining_time": "3:25:21", "throughput": 4414.37, "total_tokens": 77920352} {"current_steps": 36105, "total_steps": 61300, "loss": 0.3391, "lr": 2.160950842772666e-05, "epoch": 5.889885807504078, "percentage": 58.9, "elapsed_time": "4:54:13", "remaining_time": "3:25:19", "throughput": 4414.42, "total_tokens": 77931360} {"current_steps": 36110, "total_steps": 61300, "loss": 0.3554, "lr": 2.160245634620492e-05, "epoch": 5.890701468189233, "percentage": 58.91, "elapsed_time": "4:54:16", "remaining_time": "3:25:16", "throughput": 4414.47, "total_tokens": 77942208} {"current_steps": 36115, "total_steps": 61300, "loss": 0.3369, "lr": 2.1595404540105295e-05, "epoch": 5.891517128874388, "percentage": 58.92, "elapsed_time": "4:54:18", "remaining_time": "3:25:14", "throughput": 4414.52, "total_tokens": 77953248} {"current_steps": 36120, "total_steps": 61300, "loss": 0.3466, "lr": 2.1588353009999464e-05, "epoch": 5.892332789559543, "percentage": 58.92, "elapsed_time": "4:54:20", "remaining_time": "3:25:11", "throughput": 4414.57, "total_tokens": 77963584} {"current_steps": 36125, "total_steps": 61300, "loss": 0.3511, "lr": 2.158130175645905e-05, "epoch": 5.8931484502446985, "percentage": 58.93, "elapsed_time": "4:54:22", "remaining_time": "3:25:08", "throughput": 4414.62, "total_tokens": 77973920} {"current_steps": 36130, "total_steps": 61300, "loss": 0.3106, "lr": 2.1574250780055654e-05, "epoch": 5.893964110929853, "percentage": 58.94, "elapsed_time": "4:54:24", "remaining_time": "3:25:06", "throughput": 4414.66, "total_tokens": 77984736} {"current_steps": 36135, "total_steps": 61300, "loss": 0.3461, "lr": 2.156720008136087e-05, "epoch": 5.894779771615008, "percentage": 58.95, "elapsed_time": "4:54:27", "remaining_time": "3:25:03", "throughput": 4414.72, "total_tokens": 77996160} {"current_steps": 36140, "total_steps": 61300, "loss": 0.3477, "lr": 2.156014966094627e-05, "epoch": 5.895595432300163, "percentage": 58.96, "elapsed_time": "4:54:29", "remaining_time": "3:25:01", "throughput": 4414.77, "total_tokens": 78006592} {"current_steps": 36145, "total_steps": 61300, "loss": 0.3066, "lr": 2.1553099519383394e-05, "epoch": 5.896411092985318, "percentage": 58.96, "elapsed_time": "4:54:31", "remaining_time": "3:24:58", "throughput": 4414.81, "total_tokens": 78015936} {"current_steps": 36150, "total_steps": 61300, "loss": 0.3942, "lr": 2.154604965724376e-05, "epoch": 5.897226753670473, "percentage": 58.97, "elapsed_time": "4:54:33", "remaining_time": "3:24:55", "throughput": 4414.87, "total_tokens": 78028160} {"current_steps": 36155, "total_steps": 61300, "loss": 0.3453, "lr": 2.1539000075098868e-05, "epoch": 5.898042414355628, "percentage": 58.98, "elapsed_time": "4:54:36", "remaining_time": "3:24:53", "throughput": 4414.94, "total_tokens": 78039712} {"current_steps": 36160, "total_steps": 61300, "loss": 0.3573, "lr": 2.1531950773520187e-05, "epoch": 5.898858075040783, "percentage": 58.99, "elapsed_time": "4:54:38", "remaining_time": "3:24:51", "throughput": 4415.0, "total_tokens": 78051936} {"current_steps": 36165, "total_steps": 61300, "loss": 0.3288, "lr": 2.1524901753079176e-05, "epoch": 5.899673735725938, "percentage": 59.0, "elapsed_time": "4:54:40", "remaining_time": "3:24:48", "throughput": 4415.05, "total_tokens": 78062464} {"current_steps": 36170, "total_steps": 61300, "loss": 0.3333, "lr": 2.1517853014347262e-05, "epoch": 5.900489396411093, "percentage": 59.0, "elapsed_time": "4:54:43", "remaining_time": "3:24:45", "throughput": 4415.1, "total_tokens": 78072352} {"current_steps": 36175, "total_steps": 61300, "loss": 0.3463, "lr": 2.1510804557895847e-05, "epoch": 5.901305057096248, "percentage": 59.01, "elapsed_time": "4:54:45", "remaining_time": "3:24:43", "throughput": 4415.15, "total_tokens": 78082816} {"current_steps": 36180, "total_steps": 61300, "loss": 0.3547, "lr": 2.1503756384296323e-05, "epoch": 5.902120717781403, "percentage": 59.02, "elapsed_time": "4:54:47", "remaining_time": "3:24:40", "throughput": 4415.19, "total_tokens": 78092288} {"current_steps": 36185, "total_steps": 61300, "loss": 0.3267, "lr": 2.1496708494120043e-05, "epoch": 5.902936378466558, "percentage": 59.03, "elapsed_time": "4:54:49", "remaining_time": "3:24:37", "throughput": 4415.26, "total_tokens": 78104608} {"current_steps": 36190, "total_steps": 61300, "loss": 0.2996, "lr": 2.148966088793835e-05, "epoch": 5.903752039151713, "percentage": 59.04, "elapsed_time": "4:54:52", "remaining_time": "3:24:35", "throughput": 4415.32, "total_tokens": 78116160} {"current_steps": 36195, "total_steps": 61300, "loss": 0.3611, "lr": 2.1482613566322558e-05, "epoch": 5.904567699836868, "percentage": 59.05, "elapsed_time": "4:54:54", "remaining_time": "3:24:32", "throughput": 4415.37, "total_tokens": 78127200} {"current_steps": 36200, "total_steps": 61300, "loss": 0.3305, "lr": 2.147556652984395e-05, "epoch": 5.9053833605220225, "percentage": 59.05, "elapsed_time": "4:54:56", "remaining_time": "3:24:30", "throughput": 4415.41, "total_tokens": 78136928} {"current_steps": 36205, "total_steps": 61300, "loss": 0.3315, "lr": 2.1468519779073805e-05, "epoch": 5.906199021207177, "percentage": 59.06, "elapsed_time": "4:54:58", "remaining_time": "3:24:27", "throughput": 4415.48, "total_tokens": 78148704} {"current_steps": 36210, "total_steps": 61300, "loss": 0.3692, "lr": 2.146147331458337e-05, "epoch": 5.907014681892333, "percentage": 59.07, "elapsed_time": "4:55:00", "remaining_time": "3:24:24", "throughput": 4415.53, "total_tokens": 78158752} {"current_steps": 36215, "total_steps": 61300, "loss": 0.3269, "lr": 2.1454427136943858e-05, "epoch": 5.907830342577488, "percentage": 59.08, "elapsed_time": "4:55:02", "remaining_time": "3:24:22", "throughput": 4415.57, "total_tokens": 78167968} {"current_steps": 36220, "total_steps": 61300, "loss": 0.3169, "lr": 2.1447381246726473e-05, "epoch": 5.908646003262643, "percentage": 59.09, "elapsed_time": "4:55:05", "remaining_time": "3:24:19", "throughput": 4415.61, "total_tokens": 78178688} {"current_steps": 36225, "total_steps": 61300, "loss": 0.3308, "lr": 2.144033564450239e-05, "epoch": 5.9094616639477975, "percentage": 59.09, "elapsed_time": "4:55:07", "remaining_time": "3:24:16", "throughput": 4415.67, "total_tokens": 78189376} {"current_steps": 36230, "total_steps": 61300, "loss": 0.3343, "lr": 2.1433290330842764e-05, "epoch": 5.910277324632952, "percentage": 59.1, "elapsed_time": "4:55:09", "remaining_time": "3:24:14", "throughput": 4415.7, "total_tokens": 78200000} {"current_steps": 36235, "total_steps": 61300, "loss": 0.3709, "lr": 2.142624530631872e-05, "epoch": 5.911092985318108, "percentage": 59.11, "elapsed_time": "4:55:11", "remaining_time": "3:24:11", "throughput": 4415.75, "total_tokens": 78210592} {"current_steps": 36240, "total_steps": 61300, "loss": 0.3448, "lr": 2.1419200571501363e-05, "epoch": 5.911908646003263, "percentage": 59.12, "elapsed_time": "4:55:13", "remaining_time": "3:24:09", "throughput": 4415.8, "total_tokens": 78220896} {"current_steps": 36245, "total_steps": 61300, "loss": 0.3358, "lr": 2.141215612696177e-05, "epoch": 5.912724306688418, "percentage": 59.13, "elapsed_time": "4:55:16", "remaining_time": "3:24:06", "throughput": 4415.85, "total_tokens": 78233088} {"current_steps": 36250, "total_steps": 61300, "loss": 0.3473, "lr": 2.140511197327101e-05, "epoch": 5.9135399673735725, "percentage": 59.14, "elapsed_time": "4:55:18", "remaining_time": "3:24:04", "throughput": 4415.9, "total_tokens": 78243680} {"current_steps": 36255, "total_steps": 61300, "loss": 0.3395, "lr": 2.139806811100012e-05, "epoch": 5.914355628058727, "percentage": 59.14, "elapsed_time": "4:55:20", "remaining_time": "3:24:01", "throughput": 4415.94, "total_tokens": 78253344} {"current_steps": 36260, "total_steps": 61300, "loss": 0.3649, "lr": 2.1391024540720102e-05, "epoch": 5.915171288743883, "percentage": 59.15, "elapsed_time": "4:55:22", "remaining_time": "3:23:58", "throughput": 4416.01, "total_tokens": 78264864} {"current_steps": 36265, "total_steps": 61300, "loss": 0.3449, "lr": 2.1383981263001947e-05, "epoch": 5.915986949429038, "percentage": 59.16, "elapsed_time": "4:55:25", "remaining_time": "3:23:56", "throughput": 4416.06, "total_tokens": 78276000} {"current_steps": 36270, "total_steps": 61300, "loss": 0.3681, "lr": 2.1376938278416615e-05, "epoch": 5.916802610114193, "percentage": 59.17, "elapsed_time": "4:55:27", "remaining_time": "3:23:53", "throughput": 4416.12, "total_tokens": 78287360} {"current_steps": 36275, "total_steps": 61300, "loss": 0.329, "lr": 2.1369895587535052e-05, "epoch": 5.917618270799347, "percentage": 59.18, "elapsed_time": "4:55:29", "remaining_time": "3:23:51", "throughput": 4416.16, "total_tokens": 78296608} {"current_steps": 36280, "total_steps": 61300, "loss": 0.3446, "lr": 2.1362853190928172e-05, "epoch": 5.918433931484502, "percentage": 59.18, "elapsed_time": "4:55:31", "remaining_time": "3:23:48", "throughput": 4416.21, "total_tokens": 78306848} {"current_steps": 36285, "total_steps": 61300, "loss": 0.3346, "lr": 2.135581108916686e-05, "epoch": 5.919249592169657, "percentage": 59.19, "elapsed_time": "4:55:33", "remaining_time": "3:23:45", "throughput": 4416.27, "total_tokens": 78317504} {"current_steps": 36290, "total_steps": 61300, "loss": 0.3355, "lr": 2.1348769282822e-05, "epoch": 5.920065252854813, "percentage": 59.2, "elapsed_time": "4:55:35", "remaining_time": "3:23:43", "throughput": 4416.32, "total_tokens": 78327360} {"current_steps": 36295, "total_steps": 61300, "loss": 0.3456, "lr": 2.1341727772464425e-05, "epoch": 5.920880913539968, "percentage": 59.21, "elapsed_time": "4:55:38", "remaining_time": "3:23:40", "throughput": 4416.37, "total_tokens": 78338656} {"current_steps": 36300, "total_steps": 61300, "loss": 0.319, "lr": 2.1334686558664964e-05, "epoch": 5.921696574225122, "percentage": 59.22, "elapsed_time": "4:55:40", "remaining_time": "3:23:38", "throughput": 4416.44, "total_tokens": 78350464} {"current_steps": 36305, "total_steps": 61300, "loss": 0.3314, "lr": 2.1327645641994404e-05, "epoch": 5.922512234910277, "percentage": 59.23, "elapsed_time": "4:55:42", "remaining_time": "3:23:35", "throughput": 4416.49, "total_tokens": 78360480} {"current_steps": 36310, "total_steps": 61300, "loss": 0.3423, "lr": 2.1320605023023522e-05, "epoch": 5.923327895595432, "percentage": 59.23, "elapsed_time": "4:55:44", "remaining_time": "3:23:32", "throughput": 4416.54, "total_tokens": 78371264} {"current_steps": 36315, "total_steps": 61300, "loss": 0.3363, "lr": 2.1313564702323064e-05, "epoch": 5.924143556280587, "percentage": 59.24, "elapsed_time": "4:55:47", "remaining_time": "3:23:30", "throughput": 4416.59, "total_tokens": 78382176} {"current_steps": 36320, "total_steps": 61300, "loss": 0.3331, "lr": 2.1306524680463758e-05, "epoch": 5.924959216965743, "percentage": 59.25, "elapsed_time": "4:55:49", "remaining_time": "3:23:27", "throughput": 4416.63, "total_tokens": 78392704} {"current_steps": 36325, "total_steps": 61300, "loss": 0.3356, "lr": 2.12994849580163e-05, "epoch": 5.925774877650897, "percentage": 59.26, "elapsed_time": "4:55:51", "remaining_time": "3:23:25", "throughput": 4416.69, "total_tokens": 78404544} {"current_steps": 36330, "total_steps": 61300, "loss": 0.3677, "lr": 2.129244553555137e-05, "epoch": 5.926590538336052, "percentage": 59.27, "elapsed_time": "4:55:53", "remaining_time": "3:23:22", "throughput": 4416.74, "total_tokens": 78414400} {"current_steps": 36335, "total_steps": 61300, "loss": 0.3561, "lr": 2.1285406413639616e-05, "epoch": 5.927406199021207, "percentage": 59.27, "elapsed_time": "4:55:56", "remaining_time": "3:23:19", "throughput": 4416.79, "total_tokens": 78425664} {"current_steps": 36340, "total_steps": 61300, "loss": 0.3504, "lr": 2.1278367592851668e-05, "epoch": 5.928221859706362, "percentage": 59.28, "elapsed_time": "4:55:58", "remaining_time": "3:23:17", "throughput": 4416.85, "total_tokens": 78437120} {"current_steps": 36345, "total_steps": 61300, "loss": 0.3654, "lr": 2.1271329073758118e-05, "epoch": 5.9290375203915175, "percentage": 59.29, "elapsed_time": "4:56:00", "remaining_time": "3:23:14", "throughput": 4416.91, "total_tokens": 78447456} {"current_steps": 36350, "total_steps": 61300, "loss": 0.3198, "lr": 2.1264290856929553e-05, "epoch": 5.929853181076672, "percentage": 59.3, "elapsed_time": "4:56:02", "remaining_time": "3:23:12", "throughput": 4416.95, "total_tokens": 78457760} {"current_steps": 36355, "total_steps": 61300, "loss": 0.3398, "lr": 2.125725294293653e-05, "epoch": 5.930668841761827, "percentage": 59.31, "elapsed_time": "4:56:05", "remaining_time": "3:23:09", "throughput": 4417.01, "total_tokens": 78469248} {"current_steps": 36360, "total_steps": 61300, "loss": 0.3494, "lr": 2.1250215332349575e-05, "epoch": 5.931484502446982, "percentage": 59.31, "elapsed_time": "4:56:07", "remaining_time": "3:23:07", "throughput": 4417.06, "total_tokens": 78480864} {"current_steps": 36365, "total_steps": 61300, "loss": 0.3625, "lr": 2.1243178025739193e-05, "epoch": 5.932300163132137, "percentage": 59.32, "elapsed_time": "4:56:10", "remaining_time": "3:23:04", "throughput": 4417.11, "total_tokens": 78492224} {"current_steps": 36370, "total_steps": 61300, "loss": 0.3502, "lr": 2.1236141023675855e-05, "epoch": 5.933115823817292, "percentage": 59.33, "elapsed_time": "4:56:12", "remaining_time": "3:23:02", "throughput": 4417.15, "total_tokens": 78503072} {"current_steps": 36375, "total_steps": 61300, "loss": 0.3237, "lr": 2.122910432673003e-05, "epoch": 5.933931484502447, "percentage": 59.34, "elapsed_time": "4:56:14", "remaining_time": "3:22:59", "throughput": 4417.19, "total_tokens": 78511744} {"current_steps": 36380, "total_steps": 61300, "loss": 0.3476, "lr": 2.122206793547214e-05, "epoch": 5.934747145187602, "percentage": 59.35, "elapsed_time": "4:56:16", "remaining_time": "3:22:56", "throughput": 4417.24, "total_tokens": 78522176} {"current_steps": 36385, "total_steps": 61300, "loss": 0.3318, "lr": 2.1215031850472593e-05, "epoch": 5.935562805872757, "percentage": 59.36, "elapsed_time": "4:56:18", "remaining_time": "3:22:54", "throughput": 4417.29, "total_tokens": 78532928} {"current_steps": 36390, "total_steps": 61300, "loss": 0.3592, "lr": 2.120799607230177e-05, "epoch": 5.936378466557912, "percentage": 59.36, "elapsed_time": "4:56:20", "remaining_time": "3:22:51", "throughput": 4417.33, "total_tokens": 78543552} {"current_steps": 36395, "total_steps": 61300, "loss": 0.3201, "lr": 2.1200960601530022e-05, "epoch": 5.937194127243067, "percentage": 59.37, "elapsed_time": "4:56:22", "remaining_time": "3:22:48", "throughput": 4417.39, "total_tokens": 78553824} {"current_steps": 36400, "total_steps": 61300, "loss": 0.3263, "lr": 2.119392543872769e-05, "epoch": 5.938009787928221, "percentage": 59.38, "elapsed_time": "4:56:25", "remaining_time": "3:22:46", "throughput": 4417.45, "total_tokens": 78565248} {"current_steps": 36405, "total_steps": 61300, "loss": 0.3242, "lr": 2.1186890584465068e-05, "epoch": 5.938825448613377, "percentage": 59.39, "elapsed_time": "4:56:27", "remaining_time": "3:22:43", "throughput": 4417.51, "total_tokens": 78577440} {"current_steps": 36410, "total_steps": 61300, "loss": 0.3416, "lr": 2.1179856039312446e-05, "epoch": 5.939641109298532, "percentage": 59.4, "elapsed_time": "4:56:29", "remaining_time": "3:22:41", "throughput": 4417.56, "total_tokens": 78588160} {"current_steps": 36415, "total_steps": 61300, "loss": 0.3368, "lr": 2.1172821803840077e-05, "epoch": 5.940456769983687, "percentage": 59.4, "elapsed_time": "4:56:32", "remaining_time": "3:22:38", "throughput": 4417.61, "total_tokens": 78598976} {"current_steps": 36420, "total_steps": 61300, "loss": 0.3455, "lr": 2.116578787861819e-05, "epoch": 5.941272430668842, "percentage": 59.41, "elapsed_time": "4:56:34", "remaining_time": "3:22:35", "throughput": 4417.65, "total_tokens": 78608768} {"current_steps": 36425, "total_steps": 61300, "loss": 0.3692, "lr": 2.1158754264216992e-05, "epoch": 5.942088091353996, "percentage": 59.42, "elapsed_time": "4:56:36", "remaining_time": "3:22:33", "throughput": 4417.73, "total_tokens": 78620736} {"current_steps": 36430, "total_steps": 61300, "loss": 0.354, "lr": 2.1151720961206657e-05, "epoch": 5.942903752039152, "percentage": 59.43, "elapsed_time": "4:56:38", "remaining_time": "3:22:30", "throughput": 4417.77, "total_tokens": 78629216} {"current_steps": 36435, "total_steps": 61300, "loss": 0.3491, "lr": 2.1144687970157357e-05, "epoch": 5.943719412724307, "percentage": 59.44, "elapsed_time": "4:56:40", "remaining_time": "3:22:27", "throughput": 4417.81, "total_tokens": 78639040} {"current_steps": 36440, "total_steps": 61300, "loss": 0.3344, "lr": 2.1137655291639206e-05, "epoch": 5.944535073409462, "percentage": 59.45, "elapsed_time": "4:56:42", "remaining_time": "3:22:25", "throughput": 4417.87, "total_tokens": 78650624} {"current_steps": 36445, "total_steps": 61300, "loss": 0.3606, "lr": 2.113062292622232e-05, "epoch": 5.945350734094617, "percentage": 59.45, "elapsed_time": "4:56:45", "remaining_time": "3:22:22", "throughput": 4417.92, "total_tokens": 78662368} {"current_steps": 36450, "total_steps": 61300, "loss": 0.3347, "lr": 2.112359087447677e-05, "epoch": 5.946166394779771, "percentage": 59.46, "elapsed_time": "4:56:47", "remaining_time": "3:22:20", "throughput": 4417.98, "total_tokens": 78673984} {"current_steps": 36455, "total_steps": 61300, "loss": 0.3288, "lr": 2.11165591369726e-05, "epoch": 5.946982055464927, "percentage": 59.47, "elapsed_time": "4:56:49", "remaining_time": "3:22:17", "throughput": 4418.02, "total_tokens": 78683328} {"current_steps": 36460, "total_steps": 61300, "loss": 0.3405, "lr": 2.110952771427986e-05, "epoch": 5.947797716150082, "percentage": 59.48, "elapsed_time": "4:56:51", "remaining_time": "3:22:15", "throughput": 4418.08, "total_tokens": 78694496} {"current_steps": 36465, "total_steps": 61300, "loss": 0.3234, "lr": 2.110249660696855e-05, "epoch": 5.948613376835237, "percentage": 59.49, "elapsed_time": "4:56:54", "remaining_time": "3:22:12", "throughput": 4418.12, "total_tokens": 78704832} {"current_steps": 36470, "total_steps": 61300, "loss": 0.3249, "lr": 2.1095465815608637e-05, "epoch": 5.9494290375203915, "percentage": 59.49, "elapsed_time": "4:56:56", "remaining_time": "3:22:09", "throughput": 4418.18, "total_tokens": 78715840} {"current_steps": 36475, "total_steps": 61300, "loss": 0.3391, "lr": 2.1088435340770074e-05, "epoch": 5.950244698205546, "percentage": 59.5, "elapsed_time": "4:56:58", "remaining_time": "3:22:07", "throughput": 4418.23, "total_tokens": 78726592} {"current_steps": 36480, "total_steps": 61300, "loss": 0.3299, "lr": 2.108140518302279e-05, "epoch": 5.951060358890701, "percentage": 59.51, "elapsed_time": "4:57:01", "remaining_time": "3:22:04", "throughput": 4418.27, "total_tokens": 78738048} {"current_steps": 36485, "total_steps": 61300, "loss": 0.3445, "lr": 2.107437534293669e-05, "epoch": 5.951876019575856, "percentage": 59.52, "elapsed_time": "4:57:03", "remaining_time": "3:22:02", "throughput": 4418.32, "total_tokens": 78749312} {"current_steps": 36490, "total_steps": 61300, "loss": 0.3215, "lr": 2.106734582108164e-05, "epoch": 5.952691680261012, "percentage": 59.53, "elapsed_time": "4:57:05", "remaining_time": "3:21:59", "throughput": 4418.37, "total_tokens": 78760512} {"current_steps": 36495, "total_steps": 61300, "loss": 0.3234, "lr": 2.1060316618027493e-05, "epoch": 5.9535073409461665, "percentage": 59.54, "elapsed_time": "4:57:07", "remaining_time": "3:21:57", "throughput": 4418.43, "total_tokens": 78771072} {"current_steps": 36500, "total_steps": 61300, "loss": 0.3148, "lr": 2.105328773434407e-05, "epoch": 5.954323001631321, "percentage": 59.54, "elapsed_time": "4:57:10", "remaining_time": "3:21:54", "throughput": 4418.47, "total_tokens": 78781376} {"current_steps": 36505, "total_steps": 61300, "loss": 0.3453, "lr": 2.1046259170601167e-05, "epoch": 5.955138662316476, "percentage": 59.55, "elapsed_time": "4:57:12", "remaining_time": "3:21:52", "throughput": 4418.52, "total_tokens": 78792640} {"current_steps": 36510, "total_steps": 61300, "loss": 0.3153, "lr": 2.1039230927368556e-05, "epoch": 5.955954323001631, "percentage": 59.56, "elapsed_time": "4:57:14", "remaining_time": "3:21:49", "throughput": 4418.58, "total_tokens": 78803776} {"current_steps": 36515, "total_steps": 61300, "loss": 0.3449, "lr": 2.1032203005215978e-05, "epoch": 5.956769983686787, "percentage": 59.57, "elapsed_time": "4:57:16", "remaining_time": "3:21:46", "throughput": 4418.63, "total_tokens": 78813440} {"current_steps": 36520, "total_steps": 61300, "loss": 0.3384, "lr": 2.1025175404713167e-05, "epoch": 5.9575856443719415, "percentage": 59.58, "elapsed_time": "4:57:18", "remaining_time": "3:21:44", "throughput": 4418.68, "total_tokens": 78824736} {"current_steps": 36525, "total_steps": 61300, "loss": 0.3283, "lr": 2.1018148126429797e-05, "epoch": 5.958401305057096, "percentage": 59.58, "elapsed_time": "4:57:20", "remaining_time": "3:21:41", "throughput": 4418.71, "total_tokens": 78833920} {"current_steps": 36530, "total_steps": 61300, "loss": 0.3215, "lr": 2.101112117093555e-05, "epoch": 5.959216965742251, "percentage": 59.59, "elapsed_time": "4:57:23", "remaining_time": "3:21:39", "throughput": 4418.77, "total_tokens": 78845376} {"current_steps": 36535, "total_steps": 61300, "loss": 0.3427, "lr": 2.1004094538800058e-05, "epoch": 5.960032626427406, "percentage": 59.6, "elapsed_time": "4:57:25", "remaining_time": "3:21:36", "throughput": 4418.84, "total_tokens": 78858016} {"current_steps": 36540, "total_steps": 61300, "loss": 0.3342, "lr": 2.099706823059294e-05, "epoch": 5.960848287112562, "percentage": 59.61, "elapsed_time": "4:57:28", "remaining_time": "3:21:34", "throughput": 4418.89, "total_tokens": 78869216} {"current_steps": 36545, "total_steps": 61300, "loss": 0.3217, "lr": 2.0990042246883777e-05, "epoch": 5.9616639477977165, "percentage": 59.62, "elapsed_time": "4:57:30", "remaining_time": "3:21:31", "throughput": 4418.94, "total_tokens": 78880096} {"current_steps": 36550, "total_steps": 61300, "loss": 0.3399, "lr": 2.0983016588242145e-05, "epoch": 5.962479608482871, "percentage": 59.62, "elapsed_time": "4:57:32", "remaining_time": "3:21:28", "throughput": 4418.98, "total_tokens": 78889664} {"current_steps": 36555, "total_steps": 61300, "loss": 0.3462, "lr": 2.0975991255237562e-05, "epoch": 5.963295269168026, "percentage": 59.63, "elapsed_time": "4:57:35", "remaining_time": "3:21:26", "throughput": 4419.05, "total_tokens": 78902240} {"current_steps": 36560, "total_steps": 61300, "loss": 0.3473, "lr": 2.0968966248439536e-05, "epoch": 5.964110929853181, "percentage": 59.64, "elapsed_time": "4:57:37", "remaining_time": "3:21:23", "throughput": 4419.09, "total_tokens": 78911872} {"current_steps": 36565, "total_steps": 61300, "loss": 0.3508, "lr": 2.096194156841757e-05, "epoch": 5.964926590538336, "percentage": 59.65, "elapsed_time": "4:57:39", "remaining_time": "3:21:21", "throughput": 4419.14, "total_tokens": 78922304} {"current_steps": 36570, "total_steps": 61300, "loss": 0.2856, "lr": 2.0954917215741113e-05, "epoch": 5.9657422512234906, "percentage": 59.66, "elapsed_time": "4:57:41", "remaining_time": "3:21:18", "throughput": 4419.19, "total_tokens": 78933408} {"current_steps": 36575, "total_steps": 61300, "loss": 0.376, "lr": 2.0947893190979588e-05, "epoch": 5.966557911908646, "percentage": 59.67, "elapsed_time": "4:57:43", "remaining_time": "3:21:16", "throughput": 4419.24, "total_tokens": 78944704} {"current_steps": 36580, "total_steps": 61300, "loss": 0.3369, "lr": 2.09408694947024e-05, "epoch": 5.967373572593801, "percentage": 59.67, "elapsed_time": "4:57:46", "remaining_time": "3:21:13", "throughput": 4419.3, "total_tokens": 78955584} {"current_steps": 36585, "total_steps": 61300, "loss": 0.3591, "lr": 2.0933846127478928e-05, "epoch": 5.968189233278956, "percentage": 59.68, "elapsed_time": "4:57:48", "remaining_time": "3:21:10", "throughput": 4419.35, "total_tokens": 78966272} {"current_steps": 36590, "total_steps": 61300, "loss": 0.3419, "lr": 2.092682308987852e-05, "epoch": 5.969004893964111, "percentage": 59.69, "elapsed_time": "4:57:50", "remaining_time": "3:21:08", "throughput": 4419.4, "total_tokens": 78976608} {"current_steps": 36595, "total_steps": 61300, "loss": 0.3565, "lr": 2.0919800382470503e-05, "epoch": 5.9698205546492655, "percentage": 59.7, "elapsed_time": "4:57:52", "remaining_time": "3:21:05", "throughput": 4419.45, "total_tokens": 78987360} {"current_steps": 36600, "total_steps": 61300, "loss": 0.3238, "lr": 2.091277800582416e-05, "epoch": 5.970636215334421, "percentage": 59.71, "elapsed_time": "4:57:55", "remaining_time": "3:21:03", "throughput": 4419.5, "total_tokens": 78999040} {"current_steps": 36605, "total_steps": 61300, "loss": 0.3419, "lr": 2.0905755960508778e-05, "epoch": 5.971451876019576, "percentage": 59.71, "elapsed_time": "4:57:57", "remaining_time": "3:21:00", "throughput": 4419.56, "total_tokens": 79010112} {"current_steps": 36610, "total_steps": 61300, "loss": 0.3245, "lr": 2.0898734247093592e-05, "epoch": 5.972267536704731, "percentage": 59.72, "elapsed_time": "4:57:59", "remaining_time": "3:20:58", "throughput": 4419.6, "total_tokens": 79020416} {"current_steps": 36615, "total_steps": 61300, "loss": 0.301, "lr": 2.0891712866147812e-05, "epoch": 5.973083197389886, "percentage": 59.73, "elapsed_time": "4:58:01", "remaining_time": "3:20:55", "throughput": 4419.64, "total_tokens": 79031648} {"current_steps": 36620, "total_steps": 61300, "loss": 0.3455, "lr": 2.088469181824064e-05, "epoch": 5.9738988580750405, "percentage": 59.74, "elapsed_time": "4:58:04", "remaining_time": "3:20:53", "throughput": 4419.69, "total_tokens": 79042560} {"current_steps": 36625, "total_steps": 61300, "loss": 0.3364, "lr": 2.0877671103941228e-05, "epoch": 5.974714518760196, "percentage": 59.75, "elapsed_time": "4:58:06", "remaining_time": "3:20:50", "throughput": 4419.74, "total_tokens": 79052672} {"current_steps": 36630, "total_steps": 61300, "loss": 0.3534, "lr": 2.0870650723818706e-05, "epoch": 5.975530179445351, "percentage": 59.76, "elapsed_time": "4:58:08", "remaining_time": "3:20:47", "throughput": 4419.78, "total_tokens": 79063744} {"current_steps": 36635, "total_steps": 61300, "loss": 0.3533, "lr": 2.0863630678442196e-05, "epoch": 5.976345840130506, "percentage": 59.76, "elapsed_time": "4:58:11", "remaining_time": "3:20:45", "throughput": 4419.84, "total_tokens": 79075424} {"current_steps": 36640, "total_steps": 61300, "loss": 0.3098, "lr": 2.0856610968380768e-05, "epoch": 5.977161500815661, "percentage": 59.77, "elapsed_time": "4:58:13", "remaining_time": "3:20:42", "throughput": 4419.89, "total_tokens": 79085792} {"current_steps": 36645, "total_steps": 61300, "loss": 0.3279, "lr": 2.0849591594203482e-05, "epoch": 5.9779771615008155, "percentage": 59.78, "elapsed_time": "4:58:15", "remaining_time": "3:20:40", "throughput": 4419.94, "total_tokens": 79096704} {"current_steps": 36650, "total_steps": 61300, "loss": 0.3359, "lr": 2.0842572556479355e-05, "epoch": 5.97879282218597, "percentage": 59.79, "elapsed_time": "4:58:17", "remaining_time": "3:20:37", "throughput": 4419.99, "total_tokens": 79107328} {"current_steps": 36655, "total_steps": 61300, "loss": 0.2942, "lr": 2.0835553855777396e-05, "epoch": 5.979608482871125, "percentage": 59.8, "elapsed_time": "4:58:19", "remaining_time": "3:20:34", "throughput": 4420.04, "total_tokens": 79118144} {"current_steps": 36660, "total_steps": 61300, "loss": 0.3434, "lr": 2.082853549266656e-05, "epoch": 5.980424143556281, "percentage": 59.8, "elapsed_time": "4:58:22", "remaining_time": "3:20:32", "throughput": 4420.1, "total_tokens": 79129568} {"current_steps": 36665, "total_steps": 61300, "loss": 0.3529, "lr": 2.0821517467715815e-05, "epoch": 5.981239804241436, "percentage": 59.81, "elapsed_time": "4:58:24", "remaining_time": "3:20:29", "throughput": 4420.14, "total_tokens": 79139936} {"current_steps": 36670, "total_steps": 61300, "loss": 0.3508, "lr": 2.0814499781494057e-05, "epoch": 5.9820554649265905, "percentage": 59.82, "elapsed_time": "4:58:26", "remaining_time": "3:20:27", "throughput": 4420.19, "total_tokens": 79149664} {"current_steps": 36675, "total_steps": 61300, "loss": 0.3346, "lr": 2.0807482434570187e-05, "epoch": 5.982871125611745, "percentage": 59.83, "elapsed_time": "4:58:28", "remaining_time": "3:20:24", "throughput": 4420.25, "total_tokens": 79161280} {"current_steps": 36680, "total_steps": 61300, "loss": 0.3352, "lr": 2.080046542751307e-05, "epoch": 5.9836867862969, "percentage": 59.84, "elapsed_time": "4:58:30", "remaining_time": "3:20:21", "throughput": 4420.3, "total_tokens": 79171488} {"current_steps": 36685, "total_steps": 61300, "loss": 0.3616, "lr": 2.079344876089152e-05, "epoch": 5.984502446982056, "percentage": 59.85, "elapsed_time": "4:58:33", "remaining_time": "3:20:19", "throughput": 4420.35, "total_tokens": 79182656} {"current_steps": 36690, "total_steps": 61300, "loss": 0.3558, "lr": 2.078643243527437e-05, "epoch": 5.985318107667211, "percentage": 59.85, "elapsed_time": "4:58:35", "remaining_time": "3:20:16", "throughput": 4420.41, "total_tokens": 79194016} {"current_steps": 36695, "total_steps": 61300, "loss": 0.3597, "lr": 2.0779416451230382e-05, "epoch": 5.986133768352365, "percentage": 59.86, "elapsed_time": "4:58:37", "remaining_time": "3:20:14", "throughput": 4420.46, "total_tokens": 79205472} {"current_steps": 36700, "total_steps": 61300, "loss": 0.3268, "lr": 2.0772400809328314e-05, "epoch": 5.98694942903752, "percentage": 59.87, "elapsed_time": "4:58:40", "remaining_time": "3:20:11", "throughput": 4420.5, "total_tokens": 79215904} {"current_steps": 36705, "total_steps": 61300, "loss": 0.3442, "lr": 2.0765385510136884e-05, "epoch": 5.987765089722675, "percentage": 59.88, "elapsed_time": "4:58:42", "remaining_time": "3:20:09", "throughput": 4420.57, "total_tokens": 79227776} {"current_steps": 36710, "total_steps": 61300, "loss": 0.3512, "lr": 2.0758370554224793e-05, "epoch": 5.988580750407831, "percentage": 59.89, "elapsed_time": "4:58:44", "remaining_time": "3:20:06", "throughput": 4420.62, "total_tokens": 79239488} {"current_steps": 36715, "total_steps": 61300, "loss": 0.3323, "lr": 2.0751355942160706e-05, "epoch": 5.989396411092986, "percentage": 59.89, "elapsed_time": "4:58:47", "remaining_time": "3:20:04", "throughput": 4420.66, "total_tokens": 79249600} {"current_steps": 36720, "total_steps": 61300, "loss": 0.3519, "lr": 2.0744341674513264e-05, "epoch": 5.99021207177814, "percentage": 59.9, "elapsed_time": "4:58:49", "remaining_time": "3:20:01", "throughput": 4420.7, "total_tokens": 79259840} {"current_steps": 36725, "total_steps": 61300, "loss": 0.3127, "lr": 2.0737327751851075e-05, "epoch": 5.991027732463295, "percentage": 59.91, "elapsed_time": "4:58:51", "remaining_time": "3:19:59", "throughput": 4420.76, "total_tokens": 79271488} {"current_steps": 36730, "total_steps": 61300, "loss": 0.3501, "lr": 2.0730314174742733e-05, "epoch": 5.99184339314845, "percentage": 59.92, "elapsed_time": "4:58:53", "remaining_time": "3:19:56", "throughput": 4420.82, "total_tokens": 79282752} {"current_steps": 36735, "total_steps": 61300, "loss": 0.3624, "lr": 2.0723300943756783e-05, "epoch": 5.992659053833605, "percentage": 59.93, "elapsed_time": "4:58:56", "remaining_time": "3:19:54", "throughput": 4420.87, "total_tokens": 79294336} {"current_steps": 36740, "total_steps": 61300, "loss": 0.3248, "lr": 2.0716288059461764e-05, "epoch": 5.993474714518761, "percentage": 59.93, "elapsed_time": "4:58:58", "remaining_time": "3:19:51", "throughput": 4420.92, "total_tokens": 79306272} {"current_steps": 36745, "total_steps": 61300, "loss": 0.3382, "lr": 2.0709275522426158e-05, "epoch": 5.994290375203915, "percentage": 59.94, "elapsed_time": "4:59:01", "remaining_time": "3:19:49", "throughput": 4420.97, "total_tokens": 79317120} {"current_steps": 36750, "total_steps": 61300, "loss": 0.3405, "lr": 2.070226333321846e-05, "epoch": 5.99510603588907, "percentage": 59.95, "elapsed_time": "4:59:03", "remaining_time": "3:19:46", "throughput": 4421.02, "total_tokens": 79327200} {"current_steps": 36755, "total_steps": 61300, "loss": 0.3283, "lr": 2.06952514924071e-05, "epoch": 5.995921696574225, "percentage": 59.96, "elapsed_time": "4:59:05", "remaining_time": "3:19:43", "throughput": 4421.07, "total_tokens": 79337888} {"current_steps": 36760, "total_steps": 61300, "loss": 0.3335, "lr": 2.0688240000560498e-05, "epoch": 5.99673735725938, "percentage": 59.97, "elapsed_time": "4:59:07", "remaining_time": "3:19:41", "throughput": 4421.11, "total_tokens": 79348480} {"current_steps": 36765, "total_steps": 61300, "loss": 0.3328, "lr": 2.0681228858247038e-05, "epoch": 5.997553017944535, "percentage": 59.98, "elapsed_time": "4:59:10", "remaining_time": "3:19:38", "throughput": 4421.17, "total_tokens": 79360480} {"current_steps": 36770, "total_steps": 61300, "loss": 0.3291, "lr": 2.067421806603508e-05, "epoch": 5.99836867862969, "percentage": 59.98, "elapsed_time": "4:59:12", "remaining_time": "3:19:36", "throughput": 4421.21, "total_tokens": 79370912} {"current_steps": 36775, "total_steps": 61300, "loss": 0.3591, "lr": 2.0667207624492943e-05, "epoch": 5.999184339314845, "percentage": 59.99, "elapsed_time": "4:59:14", "remaining_time": "3:19:33", "throughput": 4421.26, "total_tokens": 79380288} {"current_steps": 36780, "total_steps": 61300, "loss": 0.3494, "lr": 2.0660197534188952e-05, "epoch": 6.0, "percentage": 60.0, "elapsed_time": "4:59:16", "remaining_time": "3:19:30", "throughput": 4421.27, "total_tokens": 79389648} {"current_steps": 36780, "total_steps": 61300, "eval_loss": 0.3388760983943939, "epoch": 6.0, "percentage": 60.0, "elapsed_time": "5:01:28", "remaining_time": "3:20:58", "throughput": 4388.99, "total_tokens": 79389648} {"current_steps": 36785, "total_steps": 61300, "loss": 0.3267, "lr": 2.065318779569137e-05, "epoch": 6.000815660685155, "percentage": 60.01, "elapsed_time": "5:01:32", "remaining_time": "3:20:57", "throughput": 4388.6, "total_tokens": 79400656} {"current_steps": 36790, "total_steps": 61300, "loss": 0.3234, "lr": 2.064617840956844e-05, "epoch": 6.00163132137031, "percentage": 60.02, "elapsed_time": "5:01:34", "remaining_time": "3:20:55", "throughput": 4388.67, "total_tokens": 79412656} {"current_steps": 36795, "total_steps": 61300, "loss": 0.3311, "lr": 2.063916937638838e-05, "epoch": 6.002446982055465, "percentage": 60.02, "elapsed_time": "5:01:37", "remaining_time": "3:20:52", "throughput": 4388.73, "total_tokens": 79424048} {"current_steps": 36800, "total_steps": 61300, "loss": 0.3405, "lr": 2.063216069671937e-05, "epoch": 6.00326264274062, "percentage": 60.03, "elapsed_time": "5:01:39", "remaining_time": "3:20:49", "throughput": 4388.78, "total_tokens": 79434896} {"current_steps": 36805, "total_steps": 61300, "loss": 0.3143, "lr": 2.0625152371129585e-05, "epoch": 6.004078303425775, "percentage": 60.04, "elapsed_time": "5:01:41", "remaining_time": "3:20:47", "throughput": 4388.83, "total_tokens": 79445680} {"current_steps": 36810, "total_steps": 61300, "loss": 0.345, "lr": 2.0618144400187142e-05, "epoch": 6.00489396411093, "percentage": 60.05, "elapsed_time": "5:01:44", "remaining_time": "3:20:44", "throughput": 4388.88, "total_tokens": 79456592} {"current_steps": 36815, "total_steps": 61300, "loss": 0.3427, "lr": 2.061113678446015e-05, "epoch": 6.005709624796085, "percentage": 60.06, "elapsed_time": "5:01:46", "remaining_time": "3:20:42", "throughput": 4388.93, "total_tokens": 79466992} {"current_steps": 36820, "total_steps": 61300, "loss": 0.3012, "lr": 2.0604129524516676e-05, "epoch": 6.006525285481239, "percentage": 60.07, "elapsed_time": "5:01:48", "remaining_time": "3:20:39", "throughput": 4388.98, "total_tokens": 79477168} {"current_steps": 36825, "total_steps": 61300, "loss": 0.32, "lr": 2.059712262092477e-05, "epoch": 6.007340946166395, "percentage": 60.07, "elapsed_time": "5:01:50", "remaining_time": "3:20:36", "throughput": 4389.04, "total_tokens": 79488368} {"current_steps": 36830, "total_steps": 61300, "loss": 0.3295, "lr": 2.0590116074252438e-05, "epoch": 6.00815660685155, "percentage": 60.08, "elapsed_time": "5:01:52", "remaining_time": "3:20:34", "throughput": 4389.09, "total_tokens": 79498736} {"current_steps": 36835, "total_steps": 61300, "loss": 0.3245, "lr": 2.058310988506768e-05, "epoch": 6.008972267536705, "percentage": 60.09, "elapsed_time": "5:01:54", "remaining_time": "3:20:31", "throughput": 4389.13, "total_tokens": 79508656} {"current_steps": 36840, "total_steps": 61300, "loss": 0.3669, "lr": 2.057610405393844e-05, "epoch": 6.00978792822186, "percentage": 60.1, "elapsed_time": "5:01:57", "remaining_time": "3:20:28", "throughput": 4389.19, "total_tokens": 79519696} {"current_steps": 36845, "total_steps": 61300, "loss": 0.3227, "lr": 2.0569098581432655e-05, "epoch": 6.010603588907014, "percentage": 60.11, "elapsed_time": "5:01:59", "remaining_time": "3:20:26", "throughput": 4389.24, "total_tokens": 79529776} {"current_steps": 36850, "total_steps": 61300, "loss": 0.3531, "lr": 2.0562093468118225e-05, "epoch": 6.011419249592169, "percentage": 60.11, "elapsed_time": "5:02:01", "remaining_time": "3:20:23", "throughput": 4389.3, "total_tokens": 79541392} {"current_steps": 36855, "total_steps": 61300, "loss": 0.3518, "lr": 2.055508871456301e-05, "epoch": 6.012234910277325, "percentage": 60.12, "elapsed_time": "5:02:03", "remaining_time": "3:20:21", "throughput": 4389.37, "total_tokens": 79552720} {"current_steps": 36860, "total_steps": 61300, "loss": 0.3402, "lr": 2.054808432133486e-05, "epoch": 6.01305057096248, "percentage": 60.13, "elapsed_time": "5:02:06", "remaining_time": "3:20:18", "throughput": 4389.42, "total_tokens": 79563888} {"current_steps": 36865, "total_steps": 61300, "loss": 0.3214, "lr": 2.0541080289001584e-05, "epoch": 6.013866231647635, "percentage": 60.14, "elapsed_time": "5:02:08", "remaining_time": "3:20:16", "throughput": 4389.49, "total_tokens": 79575760} {"current_steps": 36870, "total_steps": 61300, "loss": 0.3539, "lr": 2.0534076618130965e-05, "epoch": 6.014681892332789, "percentage": 60.15, "elapsed_time": "5:02:11", "remaining_time": "3:20:13", "throughput": 4389.56, "total_tokens": 79587408} {"current_steps": 36875, "total_steps": 61300, "loss": 0.3401, "lr": 2.0527073309290755e-05, "epoch": 6.015497553017944, "percentage": 60.15, "elapsed_time": "5:02:13", "remaining_time": "3:20:11", "throughput": 4389.61, "total_tokens": 79598352} {"current_steps": 36880, "total_steps": 61300, "loss": 0.3197, "lr": 2.0520070363048667e-05, "epoch": 6.0163132137031, "percentage": 60.16, "elapsed_time": "5:02:15", "remaining_time": "3:20:08", "throughput": 4389.68, "total_tokens": 79609520} {"current_steps": 36885, "total_steps": 61300, "loss": 0.3117, "lr": 2.0513067779972415e-05, "epoch": 6.017128874388255, "percentage": 60.17, "elapsed_time": "5:02:18", "remaining_time": "3:20:06", "throughput": 4389.74, "total_tokens": 79621712} {"current_steps": 36890, "total_steps": 61300, "loss": 0.3451, "lr": 2.0506065560629655e-05, "epoch": 6.0179445350734095, "percentage": 60.18, "elapsed_time": "5:02:20", "remaining_time": "3:20:03", "throughput": 4389.77, "total_tokens": 79630576} {"current_steps": 36895, "total_steps": 61300, "loss": 0.3198, "lr": 2.0499063705588024e-05, "epoch": 6.018760195758564, "percentage": 60.19, "elapsed_time": "5:02:22", "remaining_time": "3:20:00", "throughput": 4389.83, "total_tokens": 79641360} {"current_steps": 36900, "total_steps": 61300, "loss": 0.3183, "lr": 2.0492062215415125e-05, "epoch": 6.019575856443719, "percentage": 60.2, "elapsed_time": "5:02:24", "remaining_time": "3:19:57", "throughput": 4389.87, "total_tokens": 79651792} {"current_steps": 36905, "total_steps": 61300, "loss": 0.3183, "lr": 2.048506109067854e-05, "epoch": 6.020391517128874, "percentage": 60.2, "elapsed_time": "5:02:26", "remaining_time": "3:19:55", "throughput": 4389.93, "total_tokens": 79661488} {"current_steps": 36910, "total_steps": 61300, "loss": 0.3407, "lr": 2.047806033194581e-05, "epoch": 6.02120717781403, "percentage": 60.21, "elapsed_time": "5:02:28", "remaining_time": "3:19:52", "throughput": 4389.97, "total_tokens": 79671856} {"current_steps": 36915, "total_steps": 61300, "loss": 0.2927, "lr": 2.0471059939784447e-05, "epoch": 6.0220228384991845, "percentage": 60.22, "elapsed_time": "5:02:30", "remaining_time": "3:19:49", "throughput": 4390.02, "total_tokens": 79681232} {"current_steps": 36920, "total_steps": 61300, "loss": 0.3524, "lr": 2.046405991476195e-05, "epoch": 6.022838499184339, "percentage": 60.23, "elapsed_time": "5:02:32", "remaining_time": "3:19:47", "throughput": 4390.08, "total_tokens": 79691728} {"current_steps": 36925, "total_steps": 61300, "loss": 0.3382, "lr": 2.045706025744577e-05, "epoch": 6.023654159869494, "percentage": 60.24, "elapsed_time": "5:02:34", "remaining_time": "3:19:44", "throughput": 4390.13, "total_tokens": 79702672} {"current_steps": 36930, "total_steps": 61300, "loss": 0.3227, "lr": 2.045006096840334e-05, "epoch": 6.024469820554649, "percentage": 60.24, "elapsed_time": "5:02:37", "remaining_time": "3:19:41", "throughput": 4390.19, "total_tokens": 79713552} {"current_steps": 36935, "total_steps": 61300, "loss": 0.3264, "lr": 2.044306204820205e-05, "epoch": 6.025285481239805, "percentage": 60.25, "elapsed_time": "5:02:39", "remaining_time": "3:19:39", "throughput": 4390.23, "total_tokens": 79725296} {"current_steps": 36940, "total_steps": 61300, "loss": 0.3181, "lr": 2.0436063497409274e-05, "epoch": 6.0261011419249595, "percentage": 60.26, "elapsed_time": "5:02:41", "remaining_time": "3:19:36", "throughput": 4390.29, "total_tokens": 79735792} {"current_steps": 36945, "total_steps": 61300, "loss": 0.3505, "lr": 2.042906531659235e-05, "epoch": 6.026916802610114, "percentage": 60.27, "elapsed_time": "5:02:44", "remaining_time": "3:19:34", "throughput": 4390.35, "total_tokens": 79746576} {"current_steps": 36950, "total_steps": 61300, "loss": 0.3311, "lr": 2.042206750631858e-05, "epoch": 6.027732463295269, "percentage": 60.28, "elapsed_time": "5:02:46", "remaining_time": "3:19:31", "throughput": 4390.4, "total_tokens": 79756496} {"current_steps": 36955, "total_steps": 61300, "loss": 0.3355, "lr": 2.041507006715525e-05, "epoch": 6.028548123980424, "percentage": 60.29, "elapsed_time": "5:02:48", "remaining_time": "3:19:28", "throughput": 4390.46, "total_tokens": 79767600} {"current_steps": 36960, "total_steps": 61300, "loss": 0.3495, "lr": 2.0408072999669604e-05, "epoch": 6.029363784665579, "percentage": 60.29, "elapsed_time": "5:02:50", "remaining_time": "3:19:26", "throughput": 4390.52, "total_tokens": 79779056} {"current_steps": 36965, "total_steps": 61300, "loss": 0.3204, "lr": 2.0401076304428857e-05, "epoch": 6.0301794453507345, "percentage": 60.3, "elapsed_time": "5:02:53", "remaining_time": "3:19:23", "throughput": 4390.57, "total_tokens": 79790672} {"current_steps": 36970, "total_steps": 61300, "loss": 0.3399, "lr": 2.0394079982000198e-05, "epoch": 6.030995106035889, "percentage": 60.31, "elapsed_time": "5:02:55", "remaining_time": "3:19:21", "throughput": 4390.61, "total_tokens": 79800144} {"current_steps": 36975, "total_steps": 61300, "loss": 0.3191, "lr": 2.0387084032950787e-05, "epoch": 6.031810766721044, "percentage": 60.32, "elapsed_time": "5:02:57", "remaining_time": "3:19:18", "throughput": 4390.66, "total_tokens": 79811056} {"current_steps": 36980, "total_steps": 61300, "loss": 0.3486, "lr": 2.038008845784775e-05, "epoch": 6.032626427406199, "percentage": 60.33, "elapsed_time": "5:02:59", "remaining_time": "3:19:15", "throughput": 4390.71, "total_tokens": 79821616} {"current_steps": 36985, "total_steps": 61300, "loss": 0.3508, "lr": 2.0373093257258184e-05, "epoch": 6.033442088091354, "percentage": 60.33, "elapsed_time": "5:03:02", "remaining_time": "3:19:13", "throughput": 4390.77, "total_tokens": 79833104} {"current_steps": 36990, "total_steps": 61300, "loss": 0.3363, "lr": 2.0366098431749152e-05, "epoch": 6.034257748776509, "percentage": 60.34, "elapsed_time": "5:03:04", "remaining_time": "3:19:10", "throughput": 4390.81, "total_tokens": 79842832} {"current_steps": 36995, "total_steps": 61300, "loss": 0.3227, "lr": 2.0359103981887695e-05, "epoch": 6.035073409461664, "percentage": 60.35, "elapsed_time": "5:03:06", "remaining_time": "3:19:08", "throughput": 4390.87, "total_tokens": 79853840} {"current_steps": 37000, "total_steps": 61300, "loss": 0.344, "lr": 2.035210990824082e-05, "epoch": 6.035889070146819, "percentage": 60.36, "elapsed_time": "5:03:08", "remaining_time": "3:19:05", "throughput": 4390.93, "total_tokens": 79865488} {"current_steps": 37005, "total_steps": 61300, "loss": 0.3649, "lr": 2.0345116211375496e-05, "epoch": 6.036704730831974, "percentage": 60.37, "elapsed_time": "5:03:10", "remaining_time": "3:19:02", "throughput": 4390.96, "total_tokens": 79874640} {"current_steps": 37010, "total_steps": 61300, "loss": 0.3305, "lr": 2.0338122891858677e-05, "epoch": 6.037520391517129, "percentage": 60.38, "elapsed_time": "5:03:12", "remaining_time": "3:19:00", "throughput": 4391.01, "total_tokens": 79885552} {"current_steps": 37015, "total_steps": 61300, "loss": 0.3271, "lr": 2.0331129950257266e-05, "epoch": 6.0383360522022835, "percentage": 60.38, "elapsed_time": "5:03:15", "remaining_time": "3:18:57", "throughput": 4391.07, "total_tokens": 79896336} {"current_steps": 37020, "total_steps": 61300, "loss": 0.3593, "lr": 2.0324137387138152e-05, "epoch": 6.039151712887439, "percentage": 60.39, "elapsed_time": "5:03:17", "remaining_time": "3:18:55", "throughput": 4391.12, "total_tokens": 79907184} {"current_steps": 37025, "total_steps": 61300, "loss": 0.3247, "lr": 2.031714520306819e-05, "epoch": 6.039967373572594, "percentage": 60.4, "elapsed_time": "5:03:19", "remaining_time": "3:18:52", "throughput": 4391.17, "total_tokens": 79917936} {"current_steps": 37030, "total_steps": 61300, "loss": 0.3326, "lr": 2.0310153398614192e-05, "epoch": 6.040783034257749, "percentage": 60.41, "elapsed_time": "5:03:22", "remaining_time": "3:18:49", "throughput": 4391.23, "total_tokens": 79930000} {"current_steps": 37035, "total_steps": 61300, "loss": 0.3197, "lr": 2.030316197434296e-05, "epoch": 6.041598694942904, "percentage": 60.42, "elapsed_time": "5:03:24", "remaining_time": "3:18:47", "throughput": 4391.29, "total_tokens": 79941456} {"current_steps": 37040, "total_steps": 61300, "loss": 0.3144, "lr": 2.0296170930821245e-05, "epoch": 6.0424143556280585, "percentage": 60.42, "elapsed_time": "5:03:26", "remaining_time": "3:18:44", "throughput": 4391.33, "total_tokens": 79951440} {"current_steps": 37045, "total_steps": 61300, "loss": 0.3115, "lr": 2.028918026861579e-05, "epoch": 6.043230016313213, "percentage": 60.43, "elapsed_time": "5:03:28", "remaining_time": "3:18:42", "throughput": 4391.38, "total_tokens": 79962064} {"current_steps": 37050, "total_steps": 61300, "loss": 0.3652, "lr": 2.0282189988293276e-05, "epoch": 6.044045676998369, "percentage": 60.44, "elapsed_time": "5:03:31", "remaining_time": "3:18:39", "throughput": 4391.44, "total_tokens": 79974160} {"current_steps": 37055, "total_steps": 61300, "loss": 0.2934, "lr": 2.0275200090420376e-05, "epoch": 6.044861337683524, "percentage": 60.45, "elapsed_time": "5:03:33", "remaining_time": "3:18:37", "throughput": 4391.48, "total_tokens": 79985072} {"current_steps": 37060, "total_steps": 61300, "loss": 0.3358, "lr": 2.026821057556374e-05, "epoch": 6.045676998368679, "percentage": 60.46, "elapsed_time": "5:03:36", "remaining_time": "3:18:34", "throughput": 4391.54, "total_tokens": 79996784} {"current_steps": 37065, "total_steps": 61300, "loss": 0.3403, "lr": 2.026122144428996e-05, "epoch": 6.0464926590538335, "percentage": 60.46, "elapsed_time": "5:03:38", "remaining_time": "3:18:32", "throughput": 4391.6, "total_tokens": 80008496} {"current_steps": 37070, "total_steps": 61300, "loss": 0.3766, "lr": 2.0254232697165616e-05, "epoch": 6.047308319738988, "percentage": 60.47, "elapsed_time": "5:03:40", "remaining_time": "3:18:29", "throughput": 4391.66, "total_tokens": 80019600} {"current_steps": 37075, "total_steps": 61300, "loss": 0.3434, "lr": 2.0247244334757248e-05, "epoch": 6.048123980424143, "percentage": 60.48, "elapsed_time": "5:03:43", "remaining_time": "3:18:27", "throughput": 4391.71, "total_tokens": 80030864} {"current_steps": 37080, "total_steps": 61300, "loss": 0.3237, "lr": 2.0240256357631367e-05, "epoch": 6.048939641109299, "percentage": 60.49, "elapsed_time": "5:03:45", "remaining_time": "3:18:24", "throughput": 4391.76, "total_tokens": 80041936} {"current_steps": 37085, "total_steps": 61300, "loss": 0.3223, "lr": 2.023326876635446e-05, "epoch": 6.049755301794454, "percentage": 60.5, "elapsed_time": "5:03:47", "remaining_time": "3:18:22", "throughput": 4391.83, "total_tokens": 80053552} {"current_steps": 37090, "total_steps": 61300, "loss": 0.3351, "lr": 2.022628156149297e-05, "epoch": 6.0505709624796085, "percentage": 60.51, "elapsed_time": "5:03:50", "remaining_time": "3:18:19", "throughput": 4391.89, "total_tokens": 80064688} {"current_steps": 37095, "total_steps": 61300, "loss": 0.348, "lr": 2.021929474361331e-05, "epoch": 6.051386623164763, "percentage": 60.51, "elapsed_time": "5:03:52", "remaining_time": "3:18:16", "throughput": 4391.94, "total_tokens": 80076176} {"current_steps": 37100, "total_steps": 61300, "loss": 0.3434, "lr": 2.0212308313281886e-05, "epoch": 6.052202283849918, "percentage": 60.52, "elapsed_time": "5:03:54", "remaining_time": "3:18:14", "throughput": 4391.98, "total_tokens": 80085968} {"current_steps": 37105, "total_steps": 61300, "loss": 0.3354, "lr": 2.0205322271065042e-05, "epoch": 6.053017944535074, "percentage": 60.53, "elapsed_time": "5:03:56", "remaining_time": "3:18:11", "throughput": 4392.03, "total_tokens": 80096048} {"current_steps": 37110, "total_steps": 61300, "loss": 0.3342, "lr": 2.01983366175291e-05, "epoch": 6.053833605220229, "percentage": 60.54, "elapsed_time": "5:03:58", "remaining_time": "3:18:08", "throughput": 4392.08, "total_tokens": 80106608} {"current_steps": 37115, "total_steps": 61300, "loss": 0.3356, "lr": 2.0191351353240363e-05, "epoch": 6.054649265905383, "percentage": 60.55, "elapsed_time": "5:04:00", "remaining_time": "3:18:06", "throughput": 4392.12, "total_tokens": 80116400} {"current_steps": 37120, "total_steps": 61300, "loss": 0.3496, "lr": 2.0184366478765078e-05, "epoch": 6.055464926590538, "percentage": 60.55, "elapsed_time": "5:04:03", "remaining_time": "3:18:03", "throughput": 4392.17, "total_tokens": 80127024} {"current_steps": 37125, "total_steps": 61300, "loss": 0.3213, "lr": 2.017738199466948e-05, "epoch": 6.056280587275693, "percentage": 60.56, "elapsed_time": "5:04:05", "remaining_time": "3:18:01", "throughput": 4392.23, "total_tokens": 80137936} {"current_steps": 37130, "total_steps": 61300, "loss": 0.3311, "lr": 2.0170397901519766e-05, "epoch": 6.057096247960848, "percentage": 60.57, "elapsed_time": "5:04:07", "remaining_time": "3:17:58", "throughput": 4392.28, "total_tokens": 80148752} {"current_steps": 37135, "total_steps": 61300, "loss": 0.3214, "lr": 2.016341419988211e-05, "epoch": 6.057911908646004, "percentage": 60.58, "elapsed_time": "5:04:09", "remaining_time": "3:17:55", "throughput": 4392.33, "total_tokens": 80159856} {"current_steps": 37140, "total_steps": 61300, "loss": 0.3345, "lr": 2.0156430890322627e-05, "epoch": 6.058727569331158, "percentage": 60.59, "elapsed_time": "5:04:12", "remaining_time": "3:17:53", "throughput": 4392.4, "total_tokens": 80172656} {"current_steps": 37145, "total_steps": 61300, "loss": 0.3043, "lr": 2.0149447973407443e-05, "epoch": 6.059543230016313, "percentage": 60.6, "elapsed_time": "5:04:14", "remaining_time": "3:17:51", "throughput": 4392.46, "total_tokens": 80184240} {"current_steps": 37150, "total_steps": 61300, "loss": 0.3242, "lr": 2.0142465449702612e-05, "epoch": 6.060358890701468, "percentage": 60.6, "elapsed_time": "5:04:17", "remaining_time": "3:17:48", "throughput": 4392.51, "total_tokens": 80195184} {"current_steps": 37155, "total_steps": 61300, "loss": 0.3212, "lr": 2.0135483319774183e-05, "epoch": 6.061174551386623, "percentage": 60.61, "elapsed_time": "5:04:19", "remaining_time": "3:17:45", "throughput": 4392.56, "total_tokens": 80205296} {"current_steps": 37160, "total_steps": 61300, "loss": 0.2942, "lr": 2.012850158418816e-05, "epoch": 6.061990212071779, "percentage": 60.62, "elapsed_time": "5:04:21", "remaining_time": "3:17:43", "throughput": 4392.61, "total_tokens": 80216496} {"current_steps": 37165, "total_steps": 61300, "loss": 0.3397, "lr": 2.0121520243510512e-05, "epoch": 6.062805872756933, "percentage": 60.63, "elapsed_time": "5:04:23", "remaining_time": "3:17:40", "throughput": 4392.67, "total_tokens": 80227280} {"current_steps": 37170, "total_steps": 61300, "loss": 0.3101, "lr": 2.0114539298307188e-05, "epoch": 6.063621533442088, "percentage": 60.64, "elapsed_time": "5:04:26", "remaining_time": "3:17:38", "throughput": 4392.72, "total_tokens": 80238704} {"current_steps": 37175, "total_steps": 61300, "loss": 0.368, "lr": 2.0107558749144096e-05, "epoch": 6.064437194127243, "percentage": 60.64, "elapsed_time": "5:04:28", "remaining_time": "3:17:35", "throughput": 4392.76, "total_tokens": 80248560} {"current_steps": 37180, "total_steps": 61300, "loss": 0.3341, "lr": 2.0100578596587116e-05, "epoch": 6.065252854812398, "percentage": 60.65, "elapsed_time": "5:04:30", "remaining_time": "3:17:32", "throughput": 4392.81, "total_tokens": 80258448} {"current_steps": 37185, "total_steps": 61300, "loss": 0.2939, "lr": 2.0093598841202092e-05, "epoch": 6.066068515497553, "percentage": 60.66, "elapsed_time": "5:04:32", "remaining_time": "3:17:30", "throughput": 4392.86, "total_tokens": 80269168} {"current_steps": 37190, "total_steps": 61300, "loss": 0.3547, "lr": 2.0086619483554847e-05, "epoch": 6.066884176182708, "percentage": 60.67, "elapsed_time": "5:04:34", "remaining_time": "3:17:27", "throughput": 4392.9, "total_tokens": 80278672} {"current_steps": 37195, "total_steps": 61300, "loss": 0.347, "lr": 2.0079640524211153e-05, "epoch": 6.067699836867863, "percentage": 60.68, "elapsed_time": "5:04:37", "remaining_time": "3:17:24", "throughput": 4392.96, "total_tokens": 80290128} {"current_steps": 37200, "total_steps": 61300, "loss": 0.3055, "lr": 2.0072661963736752e-05, "epoch": 6.068515497553018, "percentage": 60.69, "elapsed_time": "5:04:39", "remaining_time": "3:17:22", "throughput": 4393.02, "total_tokens": 80300816} {"current_steps": 37205, "total_steps": 61300, "loss": 0.33, "lr": 2.006568380269739e-05, "epoch": 6.069331158238173, "percentage": 60.69, "elapsed_time": "5:04:41", "remaining_time": "3:17:19", "throughput": 4393.07, "total_tokens": 80311120} {"current_steps": 37210, "total_steps": 61300, "loss": 0.3389, "lr": 2.005870604165873e-05, "epoch": 6.070146818923328, "percentage": 60.7, "elapsed_time": "5:04:43", "remaining_time": "3:17:16", "throughput": 4393.12, "total_tokens": 80321968} {"current_steps": 37215, "total_steps": 61300, "loss": 0.3665, "lr": 2.005172868118643e-05, "epoch": 6.0709624796084825, "percentage": 60.71, "elapsed_time": "5:04:45", "remaining_time": "3:17:14", "throughput": 4393.17, "total_tokens": 80332176} {"current_steps": 37220, "total_steps": 61300, "loss": 0.3524, "lr": 2.004475172184611e-05, "epoch": 6.071778140293638, "percentage": 60.72, "elapsed_time": "5:04:48", "remaining_time": "3:17:11", "throughput": 4393.22, "total_tokens": 80343376} {"current_steps": 37225, "total_steps": 61300, "loss": 0.3282, "lr": 2.0037775164203356e-05, "epoch": 6.072593800978793, "percentage": 60.73, "elapsed_time": "5:04:50", "remaining_time": "3:17:09", "throughput": 4393.28, "total_tokens": 80354032} {"current_steps": 37230, "total_steps": 61300, "loss": 0.3239, "lr": 2.0030799008823727e-05, "epoch": 6.073409461663948, "percentage": 60.73, "elapsed_time": "5:04:52", "remaining_time": "3:17:06", "throughput": 4393.33, "total_tokens": 80365072} {"current_steps": 37235, "total_steps": 61300, "loss": 0.3378, "lr": 2.0023823256272748e-05, "epoch": 6.074225122349103, "percentage": 60.74, "elapsed_time": "5:04:54", "remaining_time": "3:17:03", "throughput": 4393.38, "total_tokens": 80374512} {"current_steps": 37240, "total_steps": 61300, "loss": 0.3497, "lr": 2.00168479071159e-05, "epoch": 6.075040783034257, "percentage": 60.75, "elapsed_time": "5:04:56", "remaining_time": "3:17:00", "throughput": 4393.43, "total_tokens": 80384368} {"current_steps": 37245, "total_steps": 61300, "loss": 0.2997, "lr": 2.0009872961918648e-05, "epoch": 6.075856443719413, "percentage": 60.76, "elapsed_time": "5:04:58", "remaining_time": "3:16:58", "throughput": 4393.48, "total_tokens": 80395152} {"current_steps": 37250, "total_steps": 61300, "loss": 0.3392, "lr": 2.0002898421246414e-05, "epoch": 6.076672104404568, "percentage": 60.77, "elapsed_time": "5:05:01", "remaining_time": "3:16:55", "throughput": 4393.53, "total_tokens": 80406288} {"current_steps": 37255, "total_steps": 61300, "loss": 0.3525, "lr": 1.9995924285664587e-05, "epoch": 6.077487765089723, "percentage": 60.77, "elapsed_time": "5:05:03", "remaining_time": "3:16:53", "throughput": 4393.58, "total_tokens": 80417040} {"current_steps": 37260, "total_steps": 61300, "loss": 0.3092, "lr": 1.9988950555738528e-05, "epoch": 6.078303425774878, "percentage": 60.78, "elapsed_time": "5:05:05", "remaining_time": "3:16:50", "throughput": 4393.63, "total_tokens": 80428112} {"current_steps": 37265, "total_steps": 61300, "loss": 0.3003, "lr": 1.9981977232033563e-05, "epoch": 6.079119086460032, "percentage": 60.79, "elapsed_time": "5:05:07", "remaining_time": "3:16:48", "throughput": 4393.68, "total_tokens": 80438288} {"current_steps": 37270, "total_steps": 61300, "loss": 0.3817, "lr": 1.9975004315114988e-05, "epoch": 6.079934747145187, "percentage": 60.8, "elapsed_time": "5:05:10", "remaining_time": "3:16:45", "throughput": 4393.73, "total_tokens": 80449360} {"current_steps": 37275, "total_steps": 61300, "loss": 0.3231, "lr": 1.9968031805548056e-05, "epoch": 6.080750407830343, "percentage": 60.81, "elapsed_time": "5:05:12", "remaining_time": "3:16:42", "throughput": 4393.79, "total_tokens": 80460752} {"current_steps": 37280, "total_steps": 61300, "loss": 0.356, "lr": 1.9961059703898e-05, "epoch": 6.081566068515498, "percentage": 60.82, "elapsed_time": "5:05:14", "remaining_time": "3:16:40", "throughput": 4393.84, "total_tokens": 80472048} {"current_steps": 37285, "total_steps": 61300, "loss": 0.3291, "lr": 1.9954088010730003e-05, "epoch": 6.082381729200653, "percentage": 60.82, "elapsed_time": "5:05:16", "remaining_time": "3:16:37", "throughput": 4393.88, "total_tokens": 80481840} {"current_steps": 37290, "total_steps": 61300, "loss": 0.3578, "lr": 1.994711672660924e-05, "epoch": 6.083197389885807, "percentage": 60.83, "elapsed_time": "5:05:19", "remaining_time": "3:16:35", "throughput": 4393.96, "total_tokens": 80493648} {"current_steps": 37295, "total_steps": 61300, "loss": 0.347, "lr": 1.9940145852100836e-05, "epoch": 6.084013050570962, "percentage": 60.84, "elapsed_time": "5:05:21", "remaining_time": "3:16:32", "throughput": 4394.0, "total_tokens": 80503024} {"current_steps": 37300, "total_steps": 61300, "loss": 0.3284, "lr": 1.993317538776988e-05, "epoch": 6.084828711256117, "percentage": 60.85, "elapsed_time": "5:05:23", "remaining_time": "3:16:29", "throughput": 4394.06, "total_tokens": 80513808} {"current_steps": 37305, "total_steps": 61300, "loss": 0.3163, "lr": 1.9926205334181443e-05, "epoch": 6.085644371941273, "percentage": 60.86, "elapsed_time": "5:05:25", "remaining_time": "3:16:27", "throughput": 4394.11, "total_tokens": 80524176} {"current_steps": 37310, "total_steps": 61300, "loss": 0.3212, "lr": 1.9919235691900526e-05, "epoch": 6.0864600326264275, "percentage": 60.86, "elapsed_time": "5:05:27", "remaining_time": "3:16:24", "throughput": 4394.18, "total_tokens": 80536176} {"current_steps": 37315, "total_steps": 61300, "loss": 0.3251, "lr": 1.991226646149216e-05, "epoch": 6.087275693311582, "percentage": 60.87, "elapsed_time": "5:05:30", "remaining_time": "3:16:22", "throughput": 4394.23, "total_tokens": 80546960} {"current_steps": 37320, "total_steps": 61300, "loss": 0.3374, "lr": 1.9905297643521287e-05, "epoch": 6.088091353996737, "percentage": 60.88, "elapsed_time": "5:05:32", "remaining_time": "3:16:19", "throughput": 4394.28, "total_tokens": 80557936} {"current_steps": 37325, "total_steps": 61300, "loss": 0.3194, "lr": 1.9898329238552838e-05, "epoch": 6.088907014681892, "percentage": 60.89, "elapsed_time": "5:05:34", "remaining_time": "3:16:16", "throughput": 4394.32, "total_tokens": 80567728} {"current_steps": 37330, "total_steps": 61300, "loss": 0.3563, "lr": 1.9891361247151706e-05, "epoch": 6.089722675367048, "percentage": 60.9, "elapsed_time": "5:05:36", "remaining_time": "3:16:14", "throughput": 4394.38, "total_tokens": 80579184} {"current_steps": 37335, "total_steps": 61300, "loss": 0.3588, "lr": 1.9884393669882752e-05, "epoch": 6.0905383360522025, "percentage": 60.91, "elapsed_time": "5:05:39", "remaining_time": "3:16:11", "throughput": 4394.42, "total_tokens": 80589872} {"current_steps": 37340, "total_steps": 61300, "loss": 0.3358, "lr": 1.9877426507310802e-05, "epoch": 6.091353996737357, "percentage": 60.91, "elapsed_time": "5:05:41", "remaining_time": "3:16:09", "throughput": 4394.47, "total_tokens": 80599888} {"current_steps": 37345, "total_steps": 61300, "loss": 0.3194, "lr": 1.9870459760000654e-05, "epoch": 6.092169657422512, "percentage": 60.92, "elapsed_time": "5:05:43", "remaining_time": "3:16:06", "throughput": 4394.52, "total_tokens": 80610384} {"current_steps": 37350, "total_steps": 61300, "loss": 0.3314, "lr": 1.9863493428517066e-05, "epoch": 6.092985318107667, "percentage": 60.93, "elapsed_time": "5:05:45", "remaining_time": "3:16:03", "throughput": 4394.57, "total_tokens": 80621456} {"current_steps": 37355, "total_steps": 61300, "loss": 0.3569, "lr": 1.985652751342476e-05, "epoch": 6.093800978792822, "percentage": 60.94, "elapsed_time": "5:05:47", "remaining_time": "3:16:01", "throughput": 4394.62, "total_tokens": 80632208} {"current_steps": 37360, "total_steps": 61300, "loss": 0.3354, "lr": 1.984956201528843e-05, "epoch": 6.0946166394779775, "percentage": 60.95, "elapsed_time": "5:05:50", "remaining_time": "3:15:58", "throughput": 4394.67, "total_tokens": 80642736} {"current_steps": 37365, "total_steps": 61300, "loss": 0.3353, "lr": 1.984259693467274e-05, "epoch": 6.095432300163132, "percentage": 60.95, "elapsed_time": "5:05:52", "remaining_time": "3:15:56", "throughput": 4394.73, "total_tokens": 80654064} {"current_steps": 37370, "total_steps": 61300, "loss": 0.3296, "lr": 1.9835632272142305e-05, "epoch": 6.096247960848287, "percentage": 60.96, "elapsed_time": "5:05:54", "remaining_time": "3:15:53", "throughput": 4394.78, "total_tokens": 80664880} {"current_steps": 37375, "total_steps": 61300, "loss": 0.3522, "lr": 1.9828668028261726e-05, "epoch": 6.097063621533442, "percentage": 60.97, "elapsed_time": "5:05:57", "remaining_time": "3:15:51", "throughput": 4394.84, "total_tokens": 80676720} {"current_steps": 37380, "total_steps": 61300, "loss": 0.3103, "lr": 1.9821704203595554e-05, "epoch": 6.097879282218597, "percentage": 60.98, "elapsed_time": "5:05:59", "remaining_time": "3:15:48", "throughput": 4394.89, "total_tokens": 80688240} {"current_steps": 37385, "total_steps": 61300, "loss": 0.3237, "lr": 1.9814740798708316e-05, "epoch": 6.0986949429037525, "percentage": 60.99, "elapsed_time": "5:06:01", "remaining_time": "3:15:45", "throughput": 4394.95, "total_tokens": 80699216} {"current_steps": 37390, "total_steps": 61300, "loss": 0.3423, "lr": 1.98077778141645e-05, "epoch": 6.099510603588907, "percentage": 61.0, "elapsed_time": "5:06:04", "remaining_time": "3:15:43", "throughput": 4395.0, "total_tokens": 80710192} {"current_steps": 37395, "total_steps": 61300, "loss": 0.3731, "lr": 1.9800815250528557e-05, "epoch": 6.100326264274062, "percentage": 61.0, "elapsed_time": "5:06:06", "remaining_time": "3:15:40", "throughput": 4395.04, "total_tokens": 80720880} {"current_steps": 37400, "total_steps": 61300, "loss": 0.3294, "lr": 1.979385310836491e-05, "epoch": 6.101141924959217, "percentage": 61.01, "elapsed_time": "5:06:08", "remaining_time": "3:15:38", "throughput": 4395.1, "total_tokens": 80731760} {"current_steps": 37405, "total_steps": 61300, "loss": 0.3275, "lr": 1.9786891388237945e-05, "epoch": 6.101957585644372, "percentage": 61.02, "elapsed_time": "5:06:10", "remaining_time": "3:15:35", "throughput": 4395.14, "total_tokens": 80741712} {"current_steps": 37410, "total_steps": 61300, "loss": 0.325, "lr": 1.9779930090712017e-05, "epoch": 6.102773246329527, "percentage": 61.03, "elapsed_time": "5:06:13", "remaining_time": "3:15:33", "throughput": 4395.2, "total_tokens": 80753264} {"current_steps": 37415, "total_steps": 61300, "loss": 0.298, "lr": 1.9772969216351433e-05, "epoch": 6.103588907014682, "percentage": 61.04, "elapsed_time": "5:06:15", "remaining_time": "3:15:30", "throughput": 4395.26, "total_tokens": 80764816} {"current_steps": 37420, "total_steps": 61300, "loss": 0.3743, "lr": 1.9766008765720493e-05, "epoch": 6.104404567699837, "percentage": 61.04, "elapsed_time": "5:06:17", "remaining_time": "3:15:27", "throughput": 4395.31, "total_tokens": 80774320} {"current_steps": 37425, "total_steps": 61300, "loss": 0.3373, "lr": 1.975904873938344e-05, "epoch": 6.105220228384992, "percentage": 61.05, "elapsed_time": "5:06:19", "remaining_time": "3:15:25", "throughput": 4395.36, "total_tokens": 80784976} {"current_steps": 37430, "total_steps": 61300, "loss": 0.3567, "lr": 1.9752089137904492e-05, "epoch": 6.106035889070147, "percentage": 61.06, "elapsed_time": "5:06:21", "remaining_time": "3:15:22", "throughput": 4395.4, "total_tokens": 80794672} {"current_steps": 37435, "total_steps": 61300, "loss": 0.3265, "lr": 1.9745129961847824e-05, "epoch": 6.1068515497553015, "percentage": 61.07, "elapsed_time": "5:06:23", "remaining_time": "3:15:19", "throughput": 4395.46, "total_tokens": 80805424} {"current_steps": 37440, "total_steps": 61300, "loss": 0.3564, "lr": 1.9738171211777584e-05, "epoch": 6.107667210440456, "percentage": 61.08, "elapsed_time": "5:06:26", "remaining_time": "3:15:17", "throughput": 4395.51, "total_tokens": 80816240} {"current_steps": 37445, "total_steps": 61300, "loss": 0.3389, "lr": 1.9731212888257883e-05, "epoch": 6.108482871125612, "percentage": 61.08, "elapsed_time": "5:06:28", "remaining_time": "3:15:14", "throughput": 4395.54, "total_tokens": 80825744} {"current_steps": 37450, "total_steps": 61300, "loss": 0.2921, "lr": 1.97242549918528e-05, "epoch": 6.109298531810767, "percentage": 61.09, "elapsed_time": "5:06:30", "remaining_time": "3:15:11", "throughput": 4395.59, "total_tokens": 80835984} {"current_steps": 37455, "total_steps": 61300, "loss": 0.357, "lr": 1.9717297523126373e-05, "epoch": 6.110114192495922, "percentage": 61.1, "elapsed_time": "5:06:32", "remaining_time": "3:15:09", "throughput": 4395.65, "total_tokens": 80847184} {"current_steps": 37460, "total_steps": 61300, "loss": 0.3681, "lr": 1.9710340482642615e-05, "epoch": 6.1109298531810765, "percentage": 61.11, "elapsed_time": "5:06:34", "remaining_time": "3:15:06", "throughput": 4395.71, "total_tokens": 80858608} {"current_steps": 37465, "total_steps": 61300, "loss": 0.3412, "lr": 1.9703383870965496e-05, "epoch": 6.111745513866231, "percentage": 61.12, "elapsed_time": "5:06:37", "remaining_time": "3:15:04", "throughput": 4395.76, "total_tokens": 80869584} {"current_steps": 37470, "total_steps": 61300, "loss": 0.3069, "lr": 1.969642768865896e-05, "epoch": 6.112561174551387, "percentage": 61.13, "elapsed_time": "5:06:39", "remaining_time": "3:15:01", "throughput": 4395.81, "total_tokens": 80879408} {"current_steps": 37475, "total_steps": 61300, "loss": 0.372, "lr": 1.9689471936286902e-05, "epoch": 6.113376835236542, "percentage": 61.13, "elapsed_time": "5:06:41", "remaining_time": "3:14:58", "throughput": 4395.85, "total_tokens": 80890032} {"current_steps": 37480, "total_steps": 61300, "loss": 0.3421, "lr": 1.9682516614413194e-05, "epoch": 6.114192495921697, "percentage": 61.14, "elapsed_time": "5:06:43", "remaining_time": "3:14:56", "throughput": 4395.92, "total_tokens": 80902160} {"current_steps": 37485, "total_steps": 61300, "loss": 0.3258, "lr": 1.967556172360167e-05, "epoch": 6.1150081566068515, "percentage": 61.15, "elapsed_time": "5:06:46", "remaining_time": "3:14:53", "throughput": 4395.98, "total_tokens": 80914032} {"current_steps": 37490, "total_steps": 61300, "loss": 0.3335, "lr": 1.966860726441613e-05, "epoch": 6.115823817292006, "percentage": 61.16, "elapsed_time": "5:06:48", "remaining_time": "3:14:51", "throughput": 4396.03, "total_tokens": 80924912} {"current_steps": 37495, "total_steps": 61300, "loss": 0.3243, "lr": 1.9661653237420337e-05, "epoch": 6.116639477977161, "percentage": 61.17, "elapsed_time": "5:06:50", "remaining_time": "3:14:48", "throughput": 4396.08, "total_tokens": 80934544} {"current_steps": 37500, "total_steps": 61300, "loss": 0.354, "lr": 1.9654699643178016e-05, "epoch": 6.117455138662317, "percentage": 61.17, "elapsed_time": "5:06:52", "remaining_time": "3:14:46", "throughput": 4396.13, "total_tokens": 80945456} {"current_steps": 37505, "total_steps": 61300, "loss": 0.328, "lr": 1.9647746482252866e-05, "epoch": 6.118270799347472, "percentage": 61.18, "elapsed_time": "5:06:55", "remaining_time": "3:14:43", "throughput": 4396.18, "total_tokens": 80956368} {"current_steps": 37510, "total_steps": 61300, "loss": 0.3259, "lr": 1.9640793755208542e-05, "epoch": 6.1190864600326265, "percentage": 61.19, "elapsed_time": "5:06:57", "remaining_time": "3:14:40", "throughput": 4396.23, "total_tokens": 80967280} {"current_steps": 37515, "total_steps": 61300, "loss": 0.3285, "lr": 1.9633841462608664e-05, "epoch": 6.119902120717781, "percentage": 61.2, "elapsed_time": "5:06:59", "remaining_time": "3:14:38", "throughput": 4396.29, "total_tokens": 80978320} {"current_steps": 37520, "total_steps": 61300, "loss": 0.3254, "lr": 1.9626889605016827e-05, "epoch": 6.120717781402936, "percentage": 61.21, "elapsed_time": "5:07:01", "remaining_time": "3:14:35", "throughput": 4396.34, "total_tokens": 80988624} {"current_steps": 37525, "total_steps": 61300, "loss": 0.3277, "lr": 1.9619938182996585e-05, "epoch": 6.121533442088092, "percentage": 61.22, "elapsed_time": "5:07:04", "remaining_time": "3:14:33", "throughput": 4396.41, "total_tokens": 81000560} {"current_steps": 37530, "total_steps": 61300, "loss": 0.332, "lr": 1.961298719711145e-05, "epoch": 6.122349102773247, "percentage": 61.22, "elapsed_time": "5:07:06", "remaining_time": "3:14:30", "throughput": 4396.47, "total_tokens": 81011408} {"current_steps": 37535, "total_steps": 61300, "loss": 0.3134, "lr": 1.9606036647924907e-05, "epoch": 6.123164763458401, "percentage": 61.23, "elapsed_time": "5:07:09", "remaining_time": "3:14:28", "throughput": 4396.52, "total_tokens": 81023472} {"current_steps": 37540, "total_steps": 61300, "loss": 0.358, "lr": 1.95990865360004e-05, "epoch": 6.123980424143556, "percentage": 61.24, "elapsed_time": "5:07:11", "remaining_time": "3:14:25", "throughput": 4396.57, "total_tokens": 81033968} {"current_steps": 37545, "total_steps": 61300, "loss": 0.3211, "lr": 1.9592136861901344e-05, "epoch": 6.124796084828711, "percentage": 61.25, "elapsed_time": "5:07:13", "remaining_time": "3:14:22", "throughput": 4396.62, "total_tokens": 81044304} {"current_steps": 37550, "total_steps": 61300, "loss": 0.3103, "lr": 1.9585187626191113e-05, "epoch": 6.125611745513866, "percentage": 61.26, "elapsed_time": "5:07:15", "remaining_time": "3:14:20", "throughput": 4396.67, "total_tokens": 81055056} {"current_steps": 37555, "total_steps": 61300, "loss": 0.3127, "lr": 1.9578238829433048e-05, "epoch": 6.126427406199022, "percentage": 61.26, "elapsed_time": "5:07:17", "remaining_time": "3:14:17", "throughput": 4396.73, "total_tokens": 81066544} {"current_steps": 37560, "total_steps": 61300, "loss": 0.3316, "lr": 1.9571290472190456e-05, "epoch": 6.127243066884176, "percentage": 61.27, "elapsed_time": "5:07:20", "remaining_time": "3:14:15", "throughput": 4396.78, "total_tokens": 81077360} {"current_steps": 37565, "total_steps": 61300, "loss": 0.2979, "lr": 1.95643425550266e-05, "epoch": 6.128058727569331, "percentage": 61.28, "elapsed_time": "5:07:22", "remaining_time": "3:14:12", "throughput": 4396.83, "total_tokens": 81088816} {"current_steps": 37570, "total_steps": 61300, "loss": 0.3406, "lr": 1.955739507850472e-05, "epoch": 6.128874388254486, "percentage": 61.29, "elapsed_time": "5:07:25", "remaining_time": "3:14:10", "throughput": 4396.89, "total_tokens": 81101488} {"current_steps": 37575, "total_steps": 61300, "loss": 0.3191, "lr": 1.9550448043188007e-05, "epoch": 6.129690048939641, "percentage": 61.3, "elapsed_time": "5:07:27", "remaining_time": "3:14:07", "throughput": 4396.93, "total_tokens": 81111568} {"current_steps": 37580, "total_steps": 61300, "loss": 0.3895, "lr": 1.954350144963963e-05, "epoch": 6.130505709624796, "percentage": 61.31, "elapsed_time": "5:07:29", "remaining_time": "3:14:05", "throughput": 4396.97, "total_tokens": 81121840} {"current_steps": 37585, "total_steps": 61300, "loss": 0.3497, "lr": 1.9536555298422706e-05, "epoch": 6.131321370309951, "percentage": 61.31, "elapsed_time": "5:07:31", "remaining_time": "3:14:02", "throughput": 4397.02, "total_tokens": 81132720} {"current_steps": 37590, "total_steps": 61300, "loss": 0.3565, "lr": 1.9529609590100337e-05, "epoch": 6.132137030995106, "percentage": 61.32, "elapsed_time": "5:07:33", "remaining_time": "3:13:59", "throughput": 4397.07, "total_tokens": 81143536} {"current_steps": 37595, "total_steps": 61300, "loss": 0.3788, "lr": 1.952266432523557e-05, "epoch": 6.132952691680261, "percentage": 61.33, "elapsed_time": "5:07:36", "remaining_time": "3:13:57", "throughput": 4397.12, "total_tokens": 81154096} {"current_steps": 37600, "total_steps": 61300, "loss": 0.2866, "lr": 1.9515719504391415e-05, "epoch": 6.133768352365416, "percentage": 61.34, "elapsed_time": "5:07:38", "remaining_time": "3:13:54", "throughput": 4397.16, "total_tokens": 81165104} {"current_steps": 37605, "total_steps": 61300, "loss": 0.3427, "lr": 1.950877512813087e-05, "epoch": 6.134584013050571, "percentage": 61.35, "elapsed_time": "5:07:40", "remaining_time": "3:13:52", "throughput": 4397.21, "total_tokens": 81175952} {"current_steps": 37610, "total_steps": 61300, "loss": 0.3458, "lr": 1.950183119701688e-05, "epoch": 6.135399673735726, "percentage": 61.35, "elapsed_time": "5:07:43", "remaining_time": "3:13:49", "throughput": 4397.26, "total_tokens": 81186608} {"current_steps": 37615, "total_steps": 61300, "loss": 0.3512, "lr": 1.949488771161235e-05, "epoch": 6.136215334420881, "percentage": 61.36, "elapsed_time": "5:07:45", "remaining_time": "3:13:47", "throughput": 4397.31, "total_tokens": 81198128} {"current_steps": 37620, "total_steps": 61300, "loss": 0.3083, "lr": 1.948794467248015e-05, "epoch": 6.137030995106036, "percentage": 61.37, "elapsed_time": "5:07:47", "remaining_time": "3:13:44", "throughput": 4397.36, "total_tokens": 81207792} {"current_steps": 37625, "total_steps": 61300, "loss": 0.3507, "lr": 1.9481002080183114e-05, "epoch": 6.137846655791191, "percentage": 61.38, "elapsed_time": "5:07:49", "remaining_time": "3:13:41", "throughput": 4397.41, "total_tokens": 81219152} {"current_steps": 37630, "total_steps": 61300, "loss": 0.3196, "lr": 1.947405993528406e-05, "epoch": 6.138662316476346, "percentage": 61.39, "elapsed_time": "5:07:52", "remaining_time": "3:13:39", "throughput": 4397.47, "total_tokens": 81230800} {"current_steps": 37635, "total_steps": 61300, "loss": 0.3157, "lr": 1.9467118238345752e-05, "epoch": 6.1394779771615005, "percentage": 61.39, "elapsed_time": "5:07:54", "remaining_time": "3:13:36", "throughput": 4397.55, "total_tokens": 81243536} {"current_steps": 37640, "total_steps": 61300, "loss": 0.3587, "lr": 1.946017698993091e-05, "epoch": 6.140293637846656, "percentage": 61.4, "elapsed_time": "5:07:57", "remaining_time": "3:13:34", "throughput": 4397.61, "total_tokens": 81255344} {"current_steps": 37645, "total_steps": 61300, "loss": 0.379, "lr": 1.945323619060223e-05, "epoch": 6.141109298531811, "percentage": 61.41, "elapsed_time": "5:07:59", "remaining_time": "3:13:31", "throughput": 4397.66, "total_tokens": 81266544} {"current_steps": 37650, "total_steps": 61300, "loss": 0.3437, "lr": 1.944629584092237e-05, "epoch": 6.141924959216966, "percentage": 61.42, "elapsed_time": "5:08:01", "remaining_time": "3:13:29", "throughput": 4397.72, "total_tokens": 81276976} {"current_steps": 37655, "total_steps": 61300, "loss": 0.3123, "lr": 1.943935594145395e-05, "epoch": 6.142740619902121, "percentage": 61.43, "elapsed_time": "5:08:04", "remaining_time": "3:13:26", "throughput": 4397.78, "total_tokens": 81288656} {"current_steps": 37660, "total_steps": 61300, "loss": 0.338, "lr": 1.9432416492759548e-05, "epoch": 6.143556280587275, "percentage": 61.44, "elapsed_time": "5:08:06", "remaining_time": "3:13:24", "throughput": 4397.83, "total_tokens": 81298928} {"current_steps": 37665, "total_steps": 61300, "loss": 0.3065, "lr": 1.9425477495401716e-05, "epoch": 6.14437194127243, "percentage": 61.44, "elapsed_time": "5:08:08", "remaining_time": "3:13:21", "throughput": 4397.88, "total_tokens": 81310224} {"current_steps": 37670, "total_steps": 61300, "loss": 0.3117, "lr": 1.9418538949942962e-05, "epoch": 6.145187601957586, "percentage": 61.45, "elapsed_time": "5:08:10", "remaining_time": "3:13:19", "throughput": 4397.93, "total_tokens": 81321616} {"current_steps": 37675, "total_steps": 61300, "loss": 0.3405, "lr": 1.9411600856945763e-05, "epoch": 6.146003262642741, "percentage": 61.46, "elapsed_time": "5:08:13", "remaining_time": "3:13:16", "throughput": 4397.99, "total_tokens": 81332656} {"current_steps": 37680, "total_steps": 61300, "loss": 0.3539, "lr": 1.940466321697255e-05, "epoch": 6.146818923327896, "percentage": 61.47, "elapsed_time": "5:08:15", "remaining_time": "3:13:13", "throughput": 4398.04, "total_tokens": 81343440} {"current_steps": 37685, "total_steps": 61300, "loss": 0.3382, "lr": 1.9397726030585726e-05, "epoch": 6.14763458401305, "percentage": 61.48, "elapsed_time": "5:08:17", "remaining_time": "3:13:11", "throughput": 4398.09, "total_tokens": 81354672} {"current_steps": 37690, "total_steps": 61300, "loss": 0.2938, "lr": 1.939078929834766e-05, "epoch": 6.148450244698205, "percentage": 61.48, "elapsed_time": "5:08:19", "remaining_time": "3:13:08", "throughput": 4398.15, "total_tokens": 81365808} {"current_steps": 37695, "total_steps": 61300, "loss": 0.3275, "lr": 1.9383853020820674e-05, "epoch": 6.149265905383361, "percentage": 61.49, "elapsed_time": "5:08:22", "remaining_time": "3:13:06", "throughput": 4398.2, "total_tokens": 81375856} {"current_steps": 37700, "total_steps": 61300, "loss": 0.2834, "lr": 1.9376917198567058e-05, "epoch": 6.150081566068516, "percentage": 61.5, "elapsed_time": "5:08:24", "remaining_time": "3:13:03", "throughput": 4398.26, "total_tokens": 81387184} {"current_steps": 37705, "total_steps": 61300, "loss": 0.3396, "lr": 1.9369981832149064e-05, "epoch": 6.150897226753671, "percentage": 61.51, "elapsed_time": "5:08:26", "remaining_time": "3:13:01", "throughput": 4398.32, "total_tokens": 81397712} {"current_steps": 37710, "total_steps": 61300, "loss": 0.3527, "lr": 1.936304692212891e-05, "epoch": 6.151712887438825, "percentage": 61.52, "elapsed_time": "5:08:28", "remaining_time": "3:12:58", "throughput": 4398.37, "total_tokens": 81408592} {"current_steps": 37715, "total_steps": 61300, "loss": 0.3446, "lr": 1.9356112469068776e-05, "epoch": 6.15252854812398, "percentage": 61.53, "elapsed_time": "5:08:31", "remaining_time": "3:12:55", "throughput": 4398.42, "total_tokens": 81420176} {"current_steps": 37720, "total_steps": 61300, "loss": 0.3832, "lr": 1.93491784735308e-05, "epoch": 6.153344208809135, "percentage": 61.53, "elapsed_time": "5:08:33", "remaining_time": "3:12:53", "throughput": 4398.48, "total_tokens": 81431920} {"current_steps": 37725, "total_steps": 61300, "loss": 0.3462, "lr": 1.934224493607709e-05, "epoch": 6.154159869494291, "percentage": 61.54, "elapsed_time": "5:08:36", "remaining_time": "3:12:50", "throughput": 4398.54, "total_tokens": 81443312} {"current_steps": 37730, "total_steps": 61300, "loss": 0.2991, "lr": 1.933531185726971e-05, "epoch": 6.1549755301794455, "percentage": 61.55, "elapsed_time": "5:08:38", "remaining_time": "3:12:48", "throughput": 4398.6, "total_tokens": 81454736} {"current_steps": 37735, "total_steps": 61300, "loss": 0.3385, "lr": 1.9328379237670684e-05, "epoch": 6.1557911908646, "percentage": 61.56, "elapsed_time": "5:08:40", "remaining_time": "3:12:45", "throughput": 4398.65, "total_tokens": 81465968} {"current_steps": 37740, "total_steps": 61300, "loss": 0.3167, "lr": 1.9321447077842026e-05, "epoch": 6.156606851549755, "percentage": 61.57, "elapsed_time": "5:08:43", "remaining_time": "3:12:43", "throughput": 4398.71, "total_tokens": 81477264} {"current_steps": 37745, "total_steps": 61300, "loss": 0.3232, "lr": 1.931451537834568e-05, "epoch": 6.15742251223491, "percentage": 61.57, "elapsed_time": "5:08:45", "remaining_time": "3:12:40", "throughput": 4398.75, "total_tokens": 81488080} {"current_steps": 37750, "total_steps": 61300, "loss": 0.3302, "lr": 1.9307584139743564e-05, "epoch": 6.158238172920065, "percentage": 61.58, "elapsed_time": "5:08:47", "remaining_time": "3:12:38", "throughput": 4398.81, "total_tokens": 81499536} {"current_steps": 37755, "total_steps": 61300, "loss": 0.3924, "lr": 1.9300653362597564e-05, "epoch": 6.1590538336052205, "percentage": 61.59, "elapsed_time": "5:08:49", "remaining_time": "3:12:35", "throughput": 4398.88, "total_tokens": 81511184} {"current_steps": 37760, "total_steps": 61300, "loss": 0.3443, "lr": 1.929372304746952e-05, "epoch": 6.159869494290375, "percentage": 61.6, "elapsed_time": "5:08:52", "remaining_time": "3:12:33", "throughput": 4398.92, "total_tokens": 81521648} {"current_steps": 37765, "total_steps": 61300, "loss": 0.3209, "lr": 1.928679319492124e-05, "epoch": 6.16068515497553, "percentage": 61.61, "elapsed_time": "5:08:54", "remaining_time": "3:12:30", "throughput": 4398.98, "total_tokens": 81532016} {"current_steps": 37770, "total_steps": 61300, "loss": 0.3309, "lr": 1.9279863805514482e-05, "epoch": 6.161500815660685, "percentage": 61.62, "elapsed_time": "5:08:56", "remaining_time": "3:12:27", "throughput": 4399.04, "total_tokens": 81543440} {"current_steps": 37775, "total_steps": 61300, "loss": 0.3483, "lr": 1.9272934879810994e-05, "epoch": 6.16231647634584, "percentage": 61.62, "elapsed_time": "5:08:58", "remaining_time": "3:12:25", "throughput": 4399.09, "total_tokens": 81553680} {"current_steps": 37780, "total_steps": 61300, "loss": 0.2848, "lr": 1.9266006418372464e-05, "epoch": 6.1631321370309955, "percentage": 61.63, "elapsed_time": "5:09:01", "remaining_time": "3:12:22", "throughput": 4399.15, "total_tokens": 81564944} {"current_steps": 37785, "total_steps": 61300, "loss": 0.3218, "lr": 1.925907842176055e-05, "epoch": 6.16394779771615, "percentage": 61.64, "elapsed_time": "5:09:03", "remaining_time": "3:12:20", "throughput": 4399.2, "total_tokens": 81575376} {"current_steps": 37790, "total_steps": 61300, "loss": 0.3705, "lr": 1.925215089053687e-05, "epoch": 6.164763458401305, "percentage": 61.65, "elapsed_time": "5:09:05", "remaining_time": "3:12:17", "throughput": 4399.26, "total_tokens": 81585840} {"current_steps": 37795, "total_steps": 61300, "loss": 0.3151, "lr": 1.9245223825262997e-05, "epoch": 6.16557911908646, "percentage": 61.66, "elapsed_time": "5:09:07", "remaining_time": "3:12:14", "throughput": 4399.32, "total_tokens": 81597072} {"current_steps": 37800, "total_steps": 61300, "loss": 0.32, "lr": 1.9238297226500483e-05, "epoch": 6.166394779771615, "percentage": 61.66, "elapsed_time": "5:09:09", "remaining_time": "3:12:12", "throughput": 4399.37, "total_tokens": 81608336} {"current_steps": 37805, "total_steps": 61300, "loss": 0.3453, "lr": 1.923137109481083e-05, "epoch": 6.16721044045677, "percentage": 61.67, "elapsed_time": "5:09:12", "remaining_time": "3:12:09", "throughput": 4399.42, "total_tokens": 81619440} {"current_steps": 37810, "total_steps": 61300, "loss": 0.3371, "lr": 1.9224445430755507e-05, "epoch": 6.168026101141925, "percentage": 61.68, "elapsed_time": "5:09:14", "remaining_time": "3:12:07", "throughput": 4399.46, "total_tokens": 81629648} {"current_steps": 37815, "total_steps": 61300, "loss": 0.3552, "lr": 1.9217520234895943e-05, "epoch": 6.16884176182708, "percentage": 61.69, "elapsed_time": "5:09:16", "remaining_time": "3:12:04", "throughput": 4399.5, "total_tokens": 81639408} {"current_steps": 37820, "total_steps": 61300, "loss": 0.3466, "lr": 1.9210595507793526e-05, "epoch": 6.169657422512235, "percentage": 61.7, "elapsed_time": "5:09:18", "remaining_time": "3:12:01", "throughput": 4399.56, "total_tokens": 81650704} {"current_steps": 37825, "total_steps": 61300, "loss": 0.366, "lr": 1.9203671250009612e-05, "epoch": 6.17047308319739, "percentage": 61.7, "elapsed_time": "5:09:21", "remaining_time": "3:11:59", "throughput": 4399.61, "total_tokens": 81661328} {"current_steps": 37830, "total_steps": 61300, "loss": 0.3872, "lr": 1.9196747462105517e-05, "epoch": 6.171288743882545, "percentage": 61.71, "elapsed_time": "5:09:23", "remaining_time": "3:11:56", "throughput": 4399.66, "total_tokens": 81671728} {"current_steps": 37835, "total_steps": 61300, "loss": 0.3296, "lr": 1.918982414464252e-05, "epoch": 6.1721044045677, "percentage": 61.72, "elapsed_time": "5:09:25", "remaining_time": "3:11:54", "throughput": 4399.71, "total_tokens": 81681936} {"current_steps": 37840, "total_steps": 61300, "loss": 0.3342, "lr": 1.918290129818185e-05, "epoch": 6.172920065252855, "percentage": 61.73, "elapsed_time": "5:09:27", "remaining_time": "3:11:51", "throughput": 4399.75, "total_tokens": 81692592} {"current_steps": 37845, "total_steps": 61300, "loss": 0.3454, "lr": 1.9175978923284727e-05, "epoch": 6.17373572593801, "percentage": 61.74, "elapsed_time": "5:09:29", "remaining_time": "3:11:48", "throughput": 4399.8, "total_tokens": 81703696} {"current_steps": 37850, "total_steps": 61300, "loss": 0.3177, "lr": 1.91690570205123e-05, "epoch": 6.174551386623165, "percentage": 61.75, "elapsed_time": "5:09:32", "remaining_time": "3:11:46", "throughput": 4399.85, "total_tokens": 81714448} {"current_steps": 37855, "total_steps": 61300, "loss": 0.3355, "lr": 1.916213559042569e-05, "epoch": 6.1753670473083195, "percentage": 61.75, "elapsed_time": "5:09:34", "remaining_time": "3:11:43", "throughput": 4399.9, "total_tokens": 81724560} {"current_steps": 37860, "total_steps": 61300, "loss": 0.3111, "lr": 1.9155214633586e-05, "epoch": 6.176182707993474, "percentage": 61.76, "elapsed_time": "5:09:36", "remaining_time": "3:11:40", "throughput": 4399.94, "total_tokens": 81734384} {"current_steps": 37865, "total_steps": 61300, "loss": 0.3302, "lr": 1.9148294150554266e-05, "epoch": 6.17699836867863, "percentage": 61.77, "elapsed_time": "5:09:38", "remaining_time": "3:11:38", "throughput": 4400.0, "total_tokens": 81745552} {"current_steps": 37870, "total_steps": 61300, "loss": 0.35, "lr": 1.9141374141891498e-05, "epoch": 6.177814029363785, "percentage": 61.78, "elapsed_time": "5:09:40", "remaining_time": "3:11:35", "throughput": 4400.05, "total_tokens": 81756144} {"current_steps": 37875, "total_steps": 61300, "loss": 0.3011, "lr": 1.913445460815867e-05, "epoch": 6.17862969004894, "percentage": 61.79, "elapsed_time": "5:09:43", "remaining_time": "3:11:33", "throughput": 4400.1, "total_tokens": 81767024} {"current_steps": 37880, "total_steps": 61300, "loss": 0.3528, "lr": 1.9127535549916715e-05, "epoch": 6.1794453507340945, "percentage": 61.79, "elapsed_time": "5:09:45", "remaining_time": "3:11:30", "throughput": 4400.14, "total_tokens": 81777488} {"current_steps": 37885, "total_steps": 61300, "loss": 0.3401, "lr": 1.912061696772652e-05, "epoch": 6.180261011419249, "percentage": 61.8, "elapsed_time": "5:09:47", "remaining_time": "3:11:28", "throughput": 4400.19, "total_tokens": 81788624} {"current_steps": 37890, "total_steps": 61300, "loss": 0.3599, "lr": 1.911369886214895e-05, "epoch": 6.181076672104404, "percentage": 61.81, "elapsed_time": "5:09:49", "remaining_time": "3:11:25", "throughput": 4400.23, "total_tokens": 81798224} {"current_steps": 37895, "total_steps": 61300, "loss": 0.2885, "lr": 1.9106781233744813e-05, "epoch": 6.18189233278956, "percentage": 61.82, "elapsed_time": "5:09:51", "remaining_time": "3:11:22", "throughput": 4400.28, "total_tokens": 81808976} {"current_steps": 37900, "total_steps": 61300, "loss": 0.2985, "lr": 1.9099864083074892e-05, "epoch": 6.182707993474715, "percentage": 61.83, "elapsed_time": "5:09:53", "remaining_time": "3:11:20", "throughput": 4400.34, "total_tokens": 81819760} {"current_steps": 37905, "total_steps": 61300, "loss": 0.3084, "lr": 1.9092947410699927e-05, "epoch": 6.1835236541598695, "percentage": 61.84, "elapsed_time": "5:09:56", "remaining_time": "3:11:17", "throughput": 4400.38, "total_tokens": 81830416} {"current_steps": 37910, "total_steps": 61300, "loss": 0.3053, "lr": 1.9086031217180618e-05, "epoch": 6.184339314845024, "percentage": 61.84, "elapsed_time": "5:09:58", "remaining_time": "3:11:15", "throughput": 4400.44, "total_tokens": 81842416} {"current_steps": 37915, "total_steps": 61300, "loss": 0.3584, "lr": 1.9079115503077617e-05, "epoch": 6.185154975530179, "percentage": 61.85, "elapsed_time": "5:10:00", "remaining_time": "3:11:12", "throughput": 4400.48, "total_tokens": 81852080} {"current_steps": 37920, "total_steps": 61300, "loss": 0.3107, "lr": 1.9072200268951562e-05, "epoch": 6.185970636215335, "percentage": 61.86, "elapsed_time": "5:10:02", "remaining_time": "3:11:09", "throughput": 4400.53, "total_tokens": 81862096} {"current_steps": 37925, "total_steps": 61300, "loss": 0.3535, "lr": 1.906528551536303e-05, "epoch": 6.18678629690049, "percentage": 61.87, "elapsed_time": "5:10:05", "remaining_time": "3:11:07", "throughput": 4400.58, "total_tokens": 81872816} {"current_steps": 37930, "total_steps": 61300, "loss": 0.353, "lr": 1.905837124287257e-05, "epoch": 6.1876019575856445, "percentage": 61.88, "elapsed_time": "5:10:07", "remaining_time": "3:11:04", "throughput": 4400.63, "total_tokens": 81883120} {"current_steps": 37935, "total_steps": 61300, "loss": 0.273, "lr": 1.905145745204068e-05, "epoch": 6.188417618270799, "percentage": 61.88, "elapsed_time": "5:10:09", "remaining_time": "3:11:01", "throughput": 4400.67, "total_tokens": 81893904} {"current_steps": 37940, "total_steps": 61300, "loss": 0.3485, "lr": 1.9044544143427832e-05, "epoch": 6.189233278955954, "percentage": 61.89, "elapsed_time": "5:10:11", "remaining_time": "3:10:59", "throughput": 4400.72, "total_tokens": 81904368} {"current_steps": 37945, "total_steps": 61300, "loss": 0.3277, "lr": 1.9037631317594445e-05, "epoch": 6.190048939641109, "percentage": 61.9, "elapsed_time": "5:10:13", "remaining_time": "3:10:56", "throughput": 4400.78, "total_tokens": 81915664} {"current_steps": 37950, "total_steps": 61300, "loss": 0.3436, "lr": 1.9030718975100927e-05, "epoch": 6.190864600326265, "percentage": 61.91, "elapsed_time": "5:10:16", "remaining_time": "3:10:54", "throughput": 4400.83, "total_tokens": 81926736} {"current_steps": 37955, "total_steps": 61300, "loss": 0.357, "lr": 1.9023807116507615e-05, "epoch": 6.191680261011419, "percentage": 61.92, "elapsed_time": "5:10:18", "remaining_time": "3:10:51", "throughput": 4400.89, "total_tokens": 81937552} {"current_steps": 37960, "total_steps": 61300, "loss": 0.3331, "lr": 1.9016895742374824e-05, "epoch": 6.192495921696574, "percentage": 61.92, "elapsed_time": "5:10:20", "remaining_time": "3:10:48", "throughput": 4400.92, "total_tokens": 81947120} {"current_steps": 37965, "total_steps": 61300, "loss": 0.3423, "lr": 1.900998485326282e-05, "epoch": 6.193311582381729, "percentage": 61.93, "elapsed_time": "5:10:22", "remaining_time": "3:10:46", "throughput": 4400.96, "total_tokens": 81955216} {"current_steps": 37970, "total_steps": 61300, "loss": 0.3185, "lr": 1.9003074449731835e-05, "epoch": 6.194127243066884, "percentage": 61.94, "elapsed_time": "5:10:24", "remaining_time": "3:10:43", "throughput": 4401.0, "total_tokens": 81965360} {"current_steps": 37975, "total_steps": 61300, "loss": 0.3411, "lr": 1.8996164532342065e-05, "epoch": 6.19494290375204, "percentage": 61.95, "elapsed_time": "5:10:26", "remaining_time": "3:10:40", "throughput": 4401.04, "total_tokens": 81976112} {"current_steps": 37980, "total_steps": 61300, "loss": 0.33, "lr": 1.8989255101653662e-05, "epoch": 6.195758564437194, "percentage": 61.96, "elapsed_time": "5:10:28", "remaining_time": "3:10:38", "throughput": 4401.1, "total_tokens": 81987568} {"current_steps": 37985, "total_steps": 61300, "loss": 0.3398, "lr": 1.898234615822674e-05, "epoch": 6.196574225122349, "percentage": 61.97, "elapsed_time": "5:10:31", "remaining_time": "3:10:35", "throughput": 4401.15, "total_tokens": 81998096} {"current_steps": 37990, "total_steps": 61300, "loss": 0.3182, "lr": 1.8975437702621368e-05, "epoch": 6.197389885807504, "percentage": 61.97, "elapsed_time": "5:10:33", "remaining_time": "3:10:33", "throughput": 4401.21, "total_tokens": 82009872} {"current_steps": 37995, "total_steps": 61300, "loss": 0.3276, "lr": 1.8968529735397582e-05, "epoch": 6.198205546492659, "percentage": 61.98, "elapsed_time": "5:10:35", "remaining_time": "3:10:30", "throughput": 4401.26, "total_tokens": 82020080} {"current_steps": 38000, "total_steps": 61300, "loss": 0.3298, "lr": 1.896162225711538e-05, "epoch": 6.199021207177814, "percentage": 61.99, "elapsed_time": "5:10:37", "remaining_time": "3:10:27", "throughput": 4401.3, "total_tokens": 82030416} {"current_steps": 38005, "total_steps": 61300, "loss": 0.3566, "lr": 1.895471526833472e-05, "epoch": 6.199836867862969, "percentage": 62.0, "elapsed_time": "5:10:40", "remaining_time": "3:10:25", "throughput": 4401.35, "total_tokens": 82041296} {"current_steps": 38010, "total_steps": 61300, "loss": 0.3322, "lr": 1.8947808769615512e-05, "epoch": 6.200652528548124, "percentage": 62.01, "elapsed_time": "5:10:42", "remaining_time": "3:10:22", "throughput": 4401.39, "total_tokens": 82051024} {"current_steps": 38015, "total_steps": 61300, "loss": 0.3375, "lr": 1.8940902761517638e-05, "epoch": 6.201468189233279, "percentage": 62.01, "elapsed_time": "5:10:44", "remaining_time": "3:10:20", "throughput": 4401.45, "total_tokens": 82062288} {"current_steps": 38020, "total_steps": 61300, "loss": 0.3457, "lr": 1.8933997244600923e-05, "epoch": 6.202283849918434, "percentage": 62.02, "elapsed_time": "5:10:46", "remaining_time": "3:10:17", "throughput": 4401.51, "total_tokens": 82073808} {"current_steps": 38025, "total_steps": 61300, "loss": 0.3502, "lr": 1.8927092219425174e-05, "epoch": 6.203099510603589, "percentage": 62.03, "elapsed_time": "5:10:48", "remaining_time": "3:10:14", "throughput": 4401.55, "total_tokens": 82083728} {"current_steps": 38030, "total_steps": 61300, "loss": 0.3363, "lr": 1.892018768655014e-05, "epoch": 6.2039151712887435, "percentage": 62.04, "elapsed_time": "5:10:51", "remaining_time": "3:10:12", "throughput": 4401.61, "total_tokens": 82095600} {"current_steps": 38035, "total_steps": 61300, "loss": 0.3204, "lr": 1.8913283646535547e-05, "epoch": 6.204730831973899, "percentage": 62.05, "elapsed_time": "5:10:53", "remaining_time": "3:10:09", "throughput": 4401.65, "total_tokens": 82105136} {"current_steps": 38040, "total_steps": 61300, "loss": 0.2996, "lr": 1.890638009994106e-05, "epoch": 6.205546492659054, "percentage": 62.06, "elapsed_time": "5:10:55", "remaining_time": "3:10:07", "throughput": 4401.7, "total_tokens": 82115504} {"current_steps": 38045, "total_steps": 61300, "loss": 0.3454, "lr": 1.889947704732632e-05, "epoch": 6.206362153344209, "percentage": 62.06, "elapsed_time": "5:10:57", "remaining_time": "3:10:04", "throughput": 4401.76, "total_tokens": 82126864} {"current_steps": 38050, "total_steps": 61300, "loss": 0.3246, "lr": 1.889257448925093e-05, "epoch": 6.207177814029364, "percentage": 62.07, "elapsed_time": "5:10:59", "remaining_time": "3:10:01", "throughput": 4401.81, "total_tokens": 82137520} {"current_steps": 38055, "total_steps": 61300, "loss": 0.3592, "lr": 1.8885672426274424e-05, "epoch": 6.2079934747145185, "percentage": 62.08, "elapsed_time": "5:11:02", "remaining_time": "3:09:59", "throughput": 4401.86, "total_tokens": 82148976} {"current_steps": 38060, "total_steps": 61300, "loss": 0.3316, "lr": 1.8878770858956353e-05, "epoch": 6.208809135399674, "percentage": 62.09, "elapsed_time": "5:11:04", "remaining_time": "3:09:56", "throughput": 4401.91, "total_tokens": 82160496} {"current_steps": 38065, "total_steps": 61300, "loss": 0.3541, "lr": 1.8871869787856166e-05, "epoch": 6.209624796084829, "percentage": 62.1, "elapsed_time": "5:11:07", "remaining_time": "3:09:54", "throughput": 4401.96, "total_tokens": 82171440} {"current_steps": 38070, "total_steps": 61300, "loss": 0.368, "lr": 1.886496921353331e-05, "epoch": 6.210440456769984, "percentage": 62.1, "elapsed_time": "5:11:09", "remaining_time": "3:09:51", "throughput": 4402.02, "total_tokens": 82182704} {"current_steps": 38075, "total_steps": 61300, "loss": 0.3361, "lr": 1.8858069136547186e-05, "epoch": 6.211256117455139, "percentage": 62.11, "elapsed_time": "5:11:11", "remaining_time": "3:09:49", "throughput": 4402.06, "total_tokens": 82193392} {"current_steps": 38080, "total_steps": 61300, "loss": 0.3391, "lr": 1.8851169557457128e-05, "epoch": 6.212071778140293, "percentage": 62.12, "elapsed_time": "5:11:13", "remaining_time": "3:09:46", "throughput": 4402.1, "total_tokens": 82204080} {"current_steps": 38085, "total_steps": 61300, "loss": 0.3173, "lr": 1.8844270476822473e-05, "epoch": 6.212887438825448, "percentage": 62.13, "elapsed_time": "5:11:16", "remaining_time": "3:09:44", "throughput": 4402.14, "total_tokens": 82215440} {"current_steps": 38090, "total_steps": 61300, "loss": 0.3462, "lr": 1.883737189520249e-05, "epoch": 6.213703099510604, "percentage": 62.14, "elapsed_time": "5:11:18", "remaining_time": "3:09:41", "throughput": 4402.21, "total_tokens": 82226832} {"current_steps": 38095, "total_steps": 61300, "loss": 0.3454, "lr": 1.88304738131564e-05, "epoch": 6.214518760195759, "percentage": 62.15, "elapsed_time": "5:11:20", "remaining_time": "3:09:39", "throughput": 4402.26, "total_tokens": 82237296} {"current_steps": 38100, "total_steps": 61300, "loss": 0.3294, "lr": 1.8823576231243418e-05, "epoch": 6.215334420880914, "percentage": 62.15, "elapsed_time": "5:11:22", "remaining_time": "3:09:36", "throughput": 4402.31, "total_tokens": 82248400} {"current_steps": 38105, "total_steps": 61300, "loss": 0.3216, "lr": 1.881667915002268e-05, "epoch": 6.216150081566068, "percentage": 62.16, "elapsed_time": "5:11:25", "remaining_time": "3:09:33", "throughput": 4402.35, "total_tokens": 82259088} {"current_steps": 38110, "total_steps": 61300, "loss": 0.2974, "lr": 1.8809782570053304e-05, "epoch": 6.216965742251223, "percentage": 62.17, "elapsed_time": "5:11:27", "remaining_time": "3:09:31", "throughput": 4402.39, "total_tokens": 82269424} {"current_steps": 38115, "total_steps": 61300, "loss": 0.3305, "lr": 1.880288649189436e-05, "epoch": 6.217781402936378, "percentage": 62.18, "elapsed_time": "5:11:29", "remaining_time": "3:09:28", "throughput": 4402.44, "total_tokens": 82280144} {"current_steps": 38120, "total_steps": 61300, "loss": 0.3556, "lr": 1.8795990916104886e-05, "epoch": 6.218597063621534, "percentage": 62.19, "elapsed_time": "5:11:31", "remaining_time": "3:09:26", "throughput": 4402.48, "total_tokens": 82290672} {"current_steps": 38125, "total_steps": 61300, "loss": 0.3714, "lr": 1.8789095843243863e-05, "epoch": 6.219412724306689, "percentage": 62.19, "elapsed_time": "5:11:34", "remaining_time": "3:09:23", "throughput": 4402.53, "total_tokens": 82301456} {"current_steps": 38130, "total_steps": 61300, "loss": 0.3233, "lr": 1.878220127387025e-05, "epoch": 6.220228384991843, "percentage": 62.2, "elapsed_time": "5:11:36", "remaining_time": "3:09:20", "throughput": 4402.57, "total_tokens": 82311696} {"current_steps": 38135, "total_steps": 61300, "loss": 0.338, "lr": 1.8775307208542946e-05, "epoch": 6.221044045676998, "percentage": 62.21, "elapsed_time": "5:11:38", "remaining_time": "3:09:18", "throughput": 4402.62, "total_tokens": 82322320} {"current_steps": 38140, "total_steps": 61300, "loss": 0.3607, "lr": 1.8768413647820817e-05, "epoch": 6.221859706362153, "percentage": 62.22, "elapsed_time": "5:11:40", "remaining_time": "3:09:15", "throughput": 4402.67, "total_tokens": 82332976} {"current_steps": 38145, "total_steps": 61300, "loss": 0.3278, "lr": 1.8761520592262704e-05, "epoch": 6.222675367047309, "percentage": 62.23, "elapsed_time": "5:11:42", "remaining_time": "3:09:13", "throughput": 4402.72, "total_tokens": 82343920} {"current_steps": 38150, "total_steps": 61300, "loss": 0.3315, "lr": 1.8754628042427387e-05, "epoch": 6.2234910277324635, "percentage": 62.23, "elapsed_time": "5:11:45", "remaining_time": "3:09:10", "throughput": 4402.78, "total_tokens": 82354928} {"current_steps": 38155, "total_steps": 61300, "loss": 0.3323, "lr": 1.8747735998873604e-05, "epoch": 6.224306688417618, "percentage": 62.24, "elapsed_time": "5:11:47", "remaining_time": "3:09:08", "throughput": 4402.83, "total_tokens": 82366544} {"current_steps": 38160, "total_steps": 61300, "loss": 0.345, "lr": 1.8740844462160064e-05, "epoch": 6.225122349102773, "percentage": 62.25, "elapsed_time": "5:11:49", "remaining_time": "3:09:05", "throughput": 4402.88, "total_tokens": 82377520} {"current_steps": 38165, "total_steps": 61300, "loss": 0.3345, "lr": 1.873395343284543e-05, "epoch": 6.225938009787928, "percentage": 62.26, "elapsed_time": "5:11:52", "remaining_time": "3:09:02", "throughput": 4402.93, "total_tokens": 82388240} {"current_steps": 38170, "total_steps": 61300, "loss": 0.3529, "lr": 1.872706291148833e-05, "epoch": 6.226753670473083, "percentage": 62.27, "elapsed_time": "5:11:54", "remaining_time": "3:09:00", "throughput": 4402.98, "total_tokens": 82399984} {"current_steps": 38175, "total_steps": 61300, "loss": 0.3203, "lr": 1.8720172898647338e-05, "epoch": 6.2275693311582385, "percentage": 62.28, "elapsed_time": "5:11:56", "remaining_time": "3:08:57", "throughput": 4403.03, "total_tokens": 82410992} {"current_steps": 38180, "total_steps": 61300, "loss": 0.3319, "lr": 1.8713283394880993e-05, "epoch": 6.228384991843393, "percentage": 62.28, "elapsed_time": "5:11:59", "remaining_time": "3:08:55", "throughput": 4403.09, "total_tokens": 82422224} {"current_steps": 38185, "total_steps": 61300, "loss": 0.3047, "lr": 1.8706394400747796e-05, "epoch": 6.229200652528548, "percentage": 62.29, "elapsed_time": "5:12:01", "remaining_time": "3:08:52", "throughput": 4403.14, "total_tokens": 82432624} {"current_steps": 38190, "total_steps": 61300, "loss": 0.3584, "lr": 1.8699505916806205e-05, "epoch": 6.230016313213703, "percentage": 62.3, "elapsed_time": "5:12:03", "remaining_time": "3:08:50", "throughput": 4403.19, "total_tokens": 82443696} {"current_steps": 38195, "total_steps": 61300, "loss": 0.3482, "lr": 1.869261794361463e-05, "epoch": 6.230831973898858, "percentage": 62.31, "elapsed_time": "5:12:05", "remaining_time": "3:08:47", "throughput": 4403.24, "total_tokens": 82454736} {"current_steps": 38200, "total_steps": 61300, "loss": 0.346, "lr": 1.8685730481731444e-05, "epoch": 6.231647634584013, "percentage": 62.32, "elapsed_time": "5:12:08", "remaining_time": "3:08:45", "throughput": 4403.29, "total_tokens": 82465072} {"current_steps": 38205, "total_steps": 61300, "loss": 0.3147, "lr": 1.867884353171499e-05, "epoch": 6.232463295269168, "percentage": 62.32, "elapsed_time": "5:12:10", "remaining_time": "3:08:42", "throughput": 4403.34, "total_tokens": 82475760} {"current_steps": 38210, "total_steps": 61300, "loss": 0.3507, "lr": 1.867195709412355e-05, "epoch": 6.233278955954323, "percentage": 62.33, "elapsed_time": "5:12:12", "remaining_time": "3:08:39", "throughput": 4403.4, "total_tokens": 82487056} {"current_steps": 38215, "total_steps": 61300, "loss": 0.3084, "lr": 1.8665071169515375e-05, "epoch": 6.234094616639478, "percentage": 62.34, "elapsed_time": "5:12:14", "remaining_time": "3:08:37", "throughput": 4403.45, "total_tokens": 82498544} {"current_steps": 38220, "total_steps": 61300, "loss": 0.3188, "lr": 1.8658185758448676e-05, "epoch": 6.234910277324633, "percentage": 62.35, "elapsed_time": "5:12:17", "remaining_time": "3:08:34", "throughput": 4403.51, "total_tokens": 82510096} {"current_steps": 38225, "total_steps": 61300, "loss": 0.3637, "lr": 1.8651300861481614e-05, "epoch": 6.235725938009788, "percentage": 62.36, "elapsed_time": "5:12:19", "remaining_time": "3:08:32", "throughput": 4403.55, "total_tokens": 82520752} {"current_steps": 38230, "total_steps": 61300, "loss": 0.337, "lr": 1.8644416479172316e-05, "epoch": 6.236541598694943, "percentage": 62.37, "elapsed_time": "5:12:21", "remaining_time": "3:08:29", "throughput": 4403.6, "total_tokens": 82531760} {"current_steps": 38235, "total_steps": 61300, "loss": 0.3478, "lr": 1.8637532612078872e-05, "epoch": 6.237357259380098, "percentage": 62.37, "elapsed_time": "5:12:24", "remaining_time": "3:08:27", "throughput": 4403.65, "total_tokens": 82542576} {"current_steps": 38240, "total_steps": 61300, "loss": 0.3418, "lr": 1.8630649260759315e-05, "epoch": 6.238172920065253, "percentage": 62.38, "elapsed_time": "5:12:26", "remaining_time": "3:08:24", "throughput": 4403.71, "total_tokens": 82553168} {"current_steps": 38245, "total_steps": 61300, "loss": 0.3138, "lr": 1.8623766425771648e-05, "epoch": 6.238988580750408, "percentage": 62.39, "elapsed_time": "5:12:28", "remaining_time": "3:08:21", "throughput": 4403.76, "total_tokens": 82563280} {"current_steps": 38250, "total_steps": 61300, "loss": 0.3581, "lr": 1.8616884107673823e-05, "epoch": 6.239804241435563, "percentage": 62.4, "elapsed_time": "5:12:30", "remaining_time": "3:08:19", "throughput": 4403.82, "total_tokens": 82575120} {"current_steps": 38255, "total_steps": 61300, "loss": 0.3295, "lr": 1.8610002307023767e-05, "epoch": 6.240619902120717, "percentage": 62.41, "elapsed_time": "5:12:33", "remaining_time": "3:08:16", "throughput": 4403.86, "total_tokens": 82586032} {"current_steps": 38260, "total_steps": 61300, "loss": 0.3643, "lr": 1.860312102437934e-05, "epoch": 6.241435562805873, "percentage": 62.41, "elapsed_time": "5:12:35", "remaining_time": "3:08:14", "throughput": 4403.91, "total_tokens": 82597040} {"current_steps": 38265, "total_steps": 61300, "loss": 0.3514, "lr": 1.859624026029837e-05, "epoch": 6.242251223491028, "percentage": 62.42, "elapsed_time": "5:12:37", "remaining_time": "3:08:11", "throughput": 4403.95, "total_tokens": 82608400} {"current_steps": 38270, "total_steps": 61300, "loss": 0.3321, "lr": 1.8589360015338668e-05, "epoch": 6.243066884176183, "percentage": 62.43, "elapsed_time": "5:12:39", "remaining_time": "3:08:09", "throughput": 4403.99, "total_tokens": 82618000} {"current_steps": 38275, "total_steps": 61300, "loss": 0.3299, "lr": 1.8582480290057975e-05, "epoch": 6.2438825448613375, "percentage": 62.44, "elapsed_time": "5:12:42", "remaining_time": "3:08:06", "throughput": 4404.04, "total_tokens": 82628880} {"current_steps": 38280, "total_steps": 61300, "loss": 0.32, "lr": 1.8575601085013988e-05, "epoch": 6.244698205546492, "percentage": 62.45, "elapsed_time": "5:12:44", "remaining_time": "3:08:04", "throughput": 4404.09, "total_tokens": 82639216} {"current_steps": 38285, "total_steps": 61300, "loss": 0.3484, "lr": 1.8568722400764377e-05, "epoch": 6.245513866231648, "percentage": 62.46, "elapsed_time": "5:12:46", "remaining_time": "3:08:01", "throughput": 4404.14, "total_tokens": 82649264} {"current_steps": 38290, "total_steps": 61300, "loss": 0.34, "lr": 1.8561844237866756e-05, "epoch": 6.246329526916803, "percentage": 62.46, "elapsed_time": "5:12:48", "remaining_time": "3:07:58", "throughput": 4404.19, "total_tokens": 82660112} {"current_steps": 38295, "total_steps": 61300, "loss": 0.3334, "lr": 1.855496659687871e-05, "epoch": 6.247145187601958, "percentage": 62.47, "elapsed_time": "5:12:50", "remaining_time": "3:07:56", "throughput": 4404.24, "total_tokens": 82671408} {"current_steps": 38300, "total_steps": 61300, "loss": 0.3461, "lr": 1.8548089478357774e-05, "epoch": 6.2479608482871125, "percentage": 62.48, "elapsed_time": "5:12:53", "remaining_time": "3:07:53", "throughput": 4404.3, "total_tokens": 82682928} {"current_steps": 38305, "total_steps": 61300, "loss": 0.3517, "lr": 1.8541212882861442e-05, "epoch": 6.248776508972267, "percentage": 62.49, "elapsed_time": "5:12:55", "remaining_time": "3:07:51", "throughput": 4404.36, "total_tokens": 82694864} {"current_steps": 38310, "total_steps": 61300, "loss": 0.3494, "lr": 1.853433681094716e-05, "epoch": 6.249592169657422, "percentage": 62.5, "elapsed_time": "5:12:57", "remaining_time": "3:07:48", "throughput": 4404.42, "total_tokens": 82705296} {"current_steps": 38315, "total_steps": 61300, "loss": 0.3258, "lr": 1.8527461263172346e-05, "epoch": 6.250407830342578, "percentage": 62.5, "elapsed_time": "5:13:00", "remaining_time": "3:07:46", "throughput": 4404.46, "total_tokens": 82716304} {"current_steps": 38320, "total_steps": 61300, "loss": 0.3246, "lr": 1.852058624009436e-05, "epoch": 6.251223491027733, "percentage": 62.51, "elapsed_time": "5:13:02", "remaining_time": "3:07:43", "throughput": 4404.52, "total_tokens": 82728272} {"current_steps": 38325, "total_steps": 61300, "loss": 0.3504, "lr": 1.8513711742270535e-05, "epoch": 6.2520391517128875, "percentage": 62.52, "elapsed_time": "5:13:04", "remaining_time": "3:07:41", "throughput": 4404.56, "total_tokens": 82738896} {"current_steps": 38330, "total_steps": 61300, "loss": 0.3193, "lr": 1.8506837770258147e-05, "epoch": 6.252854812398042, "percentage": 62.53, "elapsed_time": "5:13:07", "remaining_time": "3:07:38", "throughput": 4404.61, "total_tokens": 82749712} {"current_steps": 38335, "total_steps": 61300, "loss": 0.3702, "lr": 1.8499964324614434e-05, "epoch": 6.253670473083197, "percentage": 62.54, "elapsed_time": "5:13:08", "remaining_time": "3:07:35", "throughput": 4404.64, "total_tokens": 82758608} {"current_steps": 38340, "total_steps": 61300, "loss": 0.3414, "lr": 1.8493091405896595e-05, "epoch": 6.254486133768353, "percentage": 62.54, "elapsed_time": "5:13:11", "remaining_time": "3:07:33", "throughput": 4404.71, "total_tokens": 82770288} {"current_steps": 38345, "total_steps": 61300, "loss": 0.3417, "lr": 1.8486219014661782e-05, "epoch": 6.255301794453508, "percentage": 62.55, "elapsed_time": "5:13:13", "remaining_time": "3:07:30", "throughput": 4404.76, "total_tokens": 82782448} {"current_steps": 38350, "total_steps": 61300, "loss": 0.3429, "lr": 1.8479347151467106e-05, "epoch": 6.2561174551386625, "percentage": 62.56, "elapsed_time": "5:13:16", "remaining_time": "3:07:28", "throughput": 4404.82, "total_tokens": 82793264} {"current_steps": 38355, "total_steps": 61300, "loss": 0.3318, "lr": 1.8472475816869634e-05, "epoch": 6.256933115823817, "percentage": 62.57, "elapsed_time": "5:13:18", "remaining_time": "3:07:25", "throughput": 4404.87, "total_tokens": 82804688} {"current_steps": 38360, "total_steps": 61300, "loss": 0.3453, "lr": 1.8465605011426395e-05, "epoch": 6.257748776508972, "percentage": 62.58, "elapsed_time": "5:13:20", "remaining_time": "3:07:23", "throughput": 4404.92, "total_tokens": 82816336} {"current_steps": 38365, "total_steps": 61300, "loss": 0.364, "lr": 1.8458734735694366e-05, "epoch": 6.258564437194127, "percentage": 62.59, "elapsed_time": "5:13:23", "remaining_time": "3:07:20", "throughput": 4404.97, "total_tokens": 82827408} {"current_steps": 38370, "total_steps": 61300, "loss": 0.3173, "lr": 1.8451864990230488e-05, "epoch": 6.259380097879283, "percentage": 62.59, "elapsed_time": "5:13:25", "remaining_time": "3:07:18", "throughput": 4405.02, "total_tokens": 82838128} {"current_steps": 38375, "total_steps": 61300, "loss": 0.3525, "lr": 1.8444995775591654e-05, "epoch": 6.260195758564437, "percentage": 62.6, "elapsed_time": "5:13:27", "remaining_time": "3:07:15", "throughput": 4405.07, "total_tokens": 82849072} {"current_steps": 38380, "total_steps": 61300, "loss": 0.3387, "lr": 1.8438127092334732e-05, "epoch": 6.261011419249592, "percentage": 62.61, "elapsed_time": "5:13:29", "remaining_time": "3:07:12", "throughput": 4405.11, "total_tokens": 82859088} {"current_steps": 38385, "total_steps": 61300, "loss": 0.3436, "lr": 1.843125894101652e-05, "epoch": 6.261827079934747, "percentage": 62.62, "elapsed_time": "5:13:32", "remaining_time": "3:07:10", "throughput": 4405.16, "total_tokens": 82870480} {"current_steps": 38390, "total_steps": 61300, "loss": 0.34, "lr": 1.8424391322193787e-05, "epoch": 6.262642740619902, "percentage": 62.63, "elapsed_time": "5:13:34", "remaining_time": "3:07:07", "throughput": 4405.21, "total_tokens": 82880720} {"current_steps": 38395, "total_steps": 61300, "loss": 0.3542, "lr": 1.8417524236423257e-05, "epoch": 6.263458401305057, "percentage": 62.63, "elapsed_time": "5:13:36", "remaining_time": "3:07:05", "throughput": 4405.26, "total_tokens": 82891536} {"current_steps": 38400, "total_steps": 61300, "loss": 0.3313, "lr": 1.8410657684261613e-05, "epoch": 6.264274061990212, "percentage": 62.64, "elapsed_time": "5:13:38", "remaining_time": "3:07:02", "throughput": 4405.32, "total_tokens": 82903056} {"current_steps": 38405, "total_steps": 61300, "loss": 0.3529, "lr": 1.840379166626549e-05, "epoch": 6.265089722675367, "percentage": 62.65, "elapsed_time": "5:13:40", "remaining_time": "3:07:00", "throughput": 4405.35, "total_tokens": 82912912} {"current_steps": 38410, "total_steps": 61300, "loss": 0.3462, "lr": 1.8396926182991485e-05, "epoch": 6.265905383360522, "percentage": 62.66, "elapsed_time": "5:13:43", "remaining_time": "3:06:57", "throughput": 4405.4, "total_tokens": 82923664} {"current_steps": 38415, "total_steps": 61300, "loss": 0.3309, "lr": 1.8390061234996147e-05, "epoch": 6.266721044045677, "percentage": 62.67, "elapsed_time": "5:13:45", "remaining_time": "3:06:54", "throughput": 4405.44, "total_tokens": 82934256} {"current_steps": 38420, "total_steps": 61300, "loss": 0.3516, "lr": 1.8383196822835984e-05, "epoch": 6.267536704730832, "percentage": 62.68, "elapsed_time": "5:13:47", "remaining_time": "3:06:52", "throughput": 4405.49, "total_tokens": 82945712} {"current_steps": 38425, "total_steps": 61300, "loss": 0.334, "lr": 1.837633294706746e-05, "epoch": 6.268352365415987, "percentage": 62.68, "elapsed_time": "5:13:50", "remaining_time": "3:06:49", "throughput": 4405.54, "total_tokens": 82956720} {"current_steps": 38430, "total_steps": 61300, "loss": 0.3584, "lr": 1.8369469608246993e-05, "epoch": 6.269168026101142, "percentage": 62.69, "elapsed_time": "5:13:52", "remaining_time": "3:06:47", "throughput": 4405.6, "total_tokens": 82967856} {"current_steps": 38435, "total_steps": 61300, "loss": 0.3335, "lr": 1.8362606806930964e-05, "epoch": 6.269983686786297, "percentage": 62.7, "elapsed_time": "5:13:54", "remaining_time": "3:06:44", "throughput": 4405.66, "total_tokens": 82979472} {"current_steps": 38440, "total_steps": 61300, "loss": 0.3541, "lr": 1.835574454367571e-05, "epoch": 6.270799347471452, "percentage": 62.71, "elapsed_time": "5:13:56", "remaining_time": "3:06:42", "throughput": 4405.7, "total_tokens": 82989264} {"current_steps": 38445, "total_steps": 61300, "loss": 0.3479, "lr": 1.834888281903751e-05, "epoch": 6.271615008156607, "percentage": 62.72, "elapsed_time": "5:13:59", "remaining_time": "3:06:39", "throughput": 4405.75, "total_tokens": 83000368} {"current_steps": 38450, "total_steps": 61300, "loss": 0.3585, "lr": 1.8342021633572617e-05, "epoch": 6.2724306688417615, "percentage": 62.72, "elapsed_time": "5:14:01", "remaining_time": "3:06:37", "throughput": 4405.81, "total_tokens": 83011376} {"current_steps": 38455, "total_steps": 61300, "loss": 0.3233, "lr": 1.833516098783723e-05, "epoch": 6.273246329526917, "percentage": 62.73, "elapsed_time": "5:14:03", "remaining_time": "3:06:34", "throughput": 4405.85, "total_tokens": 83021008} {"current_steps": 38460, "total_steps": 61300, "loss": 0.3089, "lr": 1.832830088238751e-05, "epoch": 6.274061990212072, "percentage": 62.74, "elapsed_time": "5:14:05", "remaining_time": "3:06:31", "throughput": 4405.89, "total_tokens": 83031888} {"current_steps": 38465, "total_steps": 61300, "loss": 0.3606, "lr": 1.832144131777958e-05, "epoch": 6.274877650897227, "percentage": 62.75, "elapsed_time": "5:14:07", "remaining_time": "3:06:29", "throughput": 4405.93, "total_tokens": 83042032} {"current_steps": 38470, "total_steps": 61300, "loss": 0.3319, "lr": 1.83145822945695e-05, "epoch": 6.275693311582382, "percentage": 62.76, "elapsed_time": "5:14:09", "remaining_time": "3:06:26", "throughput": 4405.97, "total_tokens": 83051920} {"current_steps": 38475, "total_steps": 61300, "loss": 0.3493, "lr": 1.8307723813313298e-05, "epoch": 6.2765089722675365, "percentage": 62.77, "elapsed_time": "5:14:12", "remaining_time": "3:06:23", "throughput": 4406.03, "total_tokens": 83063280} {"current_steps": 38480, "total_steps": 61300, "loss": 0.3132, "lr": 1.8300865874566953e-05, "epoch": 6.277324632952691, "percentage": 62.77, "elapsed_time": "5:14:14", "remaining_time": "3:06:21", "throughput": 4406.07, "total_tokens": 83072112} {"current_steps": 38485, "total_steps": 61300, "loss": 0.3181, "lr": 1.829400847888642e-05, "epoch": 6.278140293637847, "percentage": 62.78, "elapsed_time": "5:14:16", "remaining_time": "3:06:18", "throughput": 4406.13, "total_tokens": 83083728} {"current_steps": 38490, "total_steps": 61300, "loss": 0.325, "lr": 1.8287151626827586e-05, "epoch": 6.278955954323002, "percentage": 62.79, "elapsed_time": "5:14:18", "remaining_time": "3:06:16", "throughput": 4406.17, "total_tokens": 83094256} {"current_steps": 38495, "total_steps": 61300, "loss": 0.3001, "lr": 1.8280295318946304e-05, "epoch": 6.279771615008157, "percentage": 62.8, "elapsed_time": "5:14:20", "remaining_time": "3:06:13", "throughput": 4406.23, "total_tokens": 83105552} {"current_steps": 38500, "total_steps": 61300, "loss": 0.3605, "lr": 1.827343955579838e-05, "epoch": 6.280587275693311, "percentage": 62.81, "elapsed_time": "5:14:23", "remaining_time": "3:06:11", "throughput": 4406.28, "total_tokens": 83117296} {"current_steps": 38505, "total_steps": 61300, "loss": 0.2885, "lr": 1.8266584337939568e-05, "epoch": 6.281402936378466, "percentage": 62.81, "elapsed_time": "5:14:25", "remaining_time": "3:06:08", "throughput": 4406.34, "total_tokens": 83127824} {"current_steps": 38510, "total_steps": 61300, "loss": 0.3432, "lr": 1.82597296659256e-05, "epoch": 6.282218597063622, "percentage": 62.82, "elapsed_time": "5:14:27", "remaining_time": "3:06:05", "throughput": 4406.39, "total_tokens": 83138608} {"current_steps": 38515, "total_steps": 61300, "loss": 0.321, "lr": 1.8252875540312143e-05, "epoch": 6.283034257748777, "percentage": 62.83, "elapsed_time": "5:14:30", "remaining_time": "3:06:03", "throughput": 4406.45, "total_tokens": 83149936} {"current_steps": 38520, "total_steps": 61300, "loss": 0.3329, "lr": 1.824602196165483e-05, "epoch": 6.283849918433932, "percentage": 62.84, "elapsed_time": "5:14:32", "remaining_time": "3:06:00", "throughput": 4406.5, "total_tokens": 83160528} {"current_steps": 38525, "total_steps": 61300, "loss": 0.3087, "lr": 1.823916893050925e-05, "epoch": 6.284665579119086, "percentage": 62.85, "elapsed_time": "5:14:34", "remaining_time": "3:05:58", "throughput": 4406.54, "total_tokens": 83170640} {"current_steps": 38530, "total_steps": 61300, "loss": 0.3664, "lr": 1.8232316447430936e-05, "epoch": 6.285481239804241, "percentage": 62.85, "elapsed_time": "5:14:36", "remaining_time": "3:05:55", "throughput": 4406.61, "total_tokens": 83182128} {"current_steps": 38535, "total_steps": 61300, "loss": 0.3337, "lr": 1.822546451297539e-05, "epoch": 6.286296900489396, "percentage": 62.86, "elapsed_time": "5:14:38", "remaining_time": "3:05:52", "throughput": 4406.65, "total_tokens": 83192368} {"current_steps": 38540, "total_steps": 61300, "loss": 0.3184, "lr": 1.8218613127698058e-05, "epoch": 6.287112561174552, "percentage": 62.87, "elapsed_time": "5:14:41", "remaining_time": "3:05:50", "throughput": 4406.7, "total_tokens": 83203024} {"current_steps": 38545, "total_steps": 61300, "loss": 0.345, "lr": 1.8211762292154362e-05, "epoch": 6.287928221859707, "percentage": 62.88, "elapsed_time": "5:14:43", "remaining_time": "3:05:47", "throughput": 4406.76, "total_tokens": 83214160} {"current_steps": 38550, "total_steps": 61300, "loss": 0.323, "lr": 1.820491200689966e-05, "epoch": 6.288743882544861, "percentage": 62.89, "elapsed_time": "5:14:45", "remaining_time": "3:05:45", "throughput": 4406.82, "total_tokens": 83224784} {"current_steps": 38555, "total_steps": 61300, "loss": 0.3369, "lr": 1.8198062272489263e-05, "epoch": 6.289559543230016, "percentage": 62.9, "elapsed_time": "5:14:47", "remaining_time": "3:05:42", "throughput": 4406.87, "total_tokens": 83235344} {"current_steps": 38560, "total_steps": 61300, "loss": 0.3365, "lr": 1.8191213089478455e-05, "epoch": 6.290375203915171, "percentage": 62.9, "elapsed_time": "5:14:49", "remaining_time": "3:05:39", "throughput": 4406.91, "total_tokens": 83246384} {"current_steps": 38565, "total_steps": 61300, "loss": 0.3296, "lr": 1.818436445842246e-05, "epoch": 6.291190864600326, "percentage": 62.91, "elapsed_time": "5:14:52", "remaining_time": "3:05:37", "throughput": 4406.96, "total_tokens": 83257520} {"current_steps": 38570, "total_steps": 61300, "loss": 0.3276, "lr": 1.8177516379876463e-05, "epoch": 6.2920065252854815, "percentage": 62.92, "elapsed_time": "5:14:54", "remaining_time": "3:05:34", "throughput": 4407.01, "total_tokens": 83267824} {"current_steps": 38575, "total_steps": 61300, "loss": 0.3342, "lr": 1.817066885439561e-05, "epoch": 6.292822185970636, "percentage": 62.93, "elapsed_time": "5:14:56", "remaining_time": "3:05:32", "throughput": 4407.05, "total_tokens": 83277904} {"current_steps": 38580, "total_steps": 61300, "loss": 0.3097, "lr": 1.8163821882534986e-05, "epoch": 6.293637846655791, "percentage": 62.94, "elapsed_time": "5:14:58", "remaining_time": "3:05:29", "throughput": 4407.1, "total_tokens": 83287280} {"current_steps": 38585, "total_steps": 61300, "loss": 0.3561, "lr": 1.815697546484964e-05, "epoch": 6.294453507340946, "percentage": 62.94, "elapsed_time": "5:15:00", "remaining_time": "3:05:26", "throughput": 4407.14, "total_tokens": 83297520} {"current_steps": 38590, "total_steps": 61300, "loss": 0.3532, "lr": 1.8150129601894592e-05, "epoch": 6.295269168026101, "percentage": 62.95, "elapsed_time": "5:15:02", "remaining_time": "3:05:24", "throughput": 4407.19, "total_tokens": 83308400} {"current_steps": 38595, "total_steps": 61300, "loss": 0.3333, "lr": 1.8143284294224794e-05, "epoch": 6.2960848287112565, "percentage": 62.96, "elapsed_time": "5:15:05", "remaining_time": "3:05:21", "throughput": 4407.26, "total_tokens": 83321008} {"current_steps": 38600, "total_steps": 61300, "loss": 0.3897, "lr": 1.813643954239516e-05, "epoch": 6.296900489396411, "percentage": 62.97, "elapsed_time": "5:15:07", "remaining_time": "3:05:19", "throughput": 4407.32, "total_tokens": 83333264} {"current_steps": 38605, "total_steps": 61300, "loss": 0.3262, "lr": 1.8129595346960568e-05, "epoch": 6.297716150081566, "percentage": 62.98, "elapsed_time": "5:15:10", "remaining_time": "3:05:16", "throughput": 4407.35, "total_tokens": 83343856} {"current_steps": 38610, "total_steps": 61300, "loss": 0.3303, "lr": 1.812275170847583e-05, "epoch": 6.298531810766721, "percentage": 62.99, "elapsed_time": "5:15:12", "remaining_time": "3:05:14", "throughput": 4407.41, "total_tokens": 83354832} {"current_steps": 38615, "total_steps": 61300, "loss": 0.3302, "lr": 1.8115908627495742e-05, "epoch": 6.299347471451876, "percentage": 62.99, "elapsed_time": "5:15:14", "remaining_time": "3:05:11", "throughput": 4407.45, "total_tokens": 83365488} {"current_steps": 38620, "total_steps": 61300, "loss": 0.3321, "lr": 1.8109066104575023e-05, "epoch": 6.300163132137031, "percentage": 63.0, "elapsed_time": "5:15:16", "remaining_time": "3:05:09", "throughput": 4407.51, "total_tokens": 83376688} {"current_steps": 38625, "total_steps": 61300, "loss": 0.3192, "lr": 1.810222414026837e-05, "epoch": 6.300978792822186, "percentage": 63.01, "elapsed_time": "5:15:19", "remaining_time": "3:05:06", "throughput": 4407.56, "total_tokens": 83387056} {"current_steps": 38630, "total_steps": 61300, "loss": 0.3324, "lr": 1.809538273513043e-05, "epoch": 6.301794453507341, "percentage": 63.02, "elapsed_time": "5:15:21", "remaining_time": "3:05:04", "throughput": 4407.61, "total_tokens": 83398224} {"current_steps": 38635, "total_steps": 61300, "loss": 0.3327, "lr": 1.8088541889715795e-05, "epoch": 6.302610114192496, "percentage": 63.03, "elapsed_time": "5:15:23", "remaining_time": "3:05:01", "throughput": 4407.67, "total_tokens": 83408880} {"current_steps": 38640, "total_steps": 61300, "loss": 0.3188, "lr": 1.8081701604579025e-05, "epoch": 6.303425774877651, "percentage": 63.03, "elapsed_time": "5:15:25", "remaining_time": "3:04:58", "throughput": 4407.72, "total_tokens": 83419504} {"current_steps": 38645, "total_steps": 61300, "loss": 0.3424, "lr": 1.807486188027463e-05, "epoch": 6.304241435562806, "percentage": 63.04, "elapsed_time": "5:15:27", "remaining_time": "3:04:56", "throughput": 4407.76, "total_tokens": 83429296} {"current_steps": 38650, "total_steps": 61300, "loss": 0.3124, "lr": 1.8068022717357066e-05, "epoch": 6.30505709624796, "percentage": 63.05, "elapsed_time": "5:15:30", "remaining_time": "3:04:53", "throughput": 4407.82, "total_tokens": 83440912} {"current_steps": 38655, "total_steps": 61300, "loss": 0.3727, "lr": 1.8061184116380754e-05, "epoch": 6.305872756933116, "percentage": 63.06, "elapsed_time": "5:15:32", "remaining_time": "3:04:51", "throughput": 4407.86, "total_tokens": 83451568} {"current_steps": 38660, "total_steps": 61300, "loss": 0.3031, "lr": 1.8054346077900065e-05, "epoch": 6.306688417618271, "percentage": 63.07, "elapsed_time": "5:15:34", "remaining_time": "3:04:48", "throughput": 4407.91, "total_tokens": 83461200} {"current_steps": 38665, "total_steps": 61300, "loss": 0.367, "lr": 1.8047508602469322e-05, "epoch": 6.307504078303426, "percentage": 63.08, "elapsed_time": "5:15:36", "remaining_time": "3:04:45", "throughput": 4407.96, "total_tokens": 83472016} {"current_steps": 38670, "total_steps": 61300, "loss": 0.3055, "lr": 1.804067169064281e-05, "epoch": 6.308319738988581, "percentage": 63.08, "elapsed_time": "5:15:38", "remaining_time": "3:04:43", "throughput": 4408.0, "total_tokens": 83482896} {"current_steps": 38675, "total_steps": 61300, "loss": 0.3275, "lr": 1.8033835342974763e-05, "epoch": 6.309135399673735, "percentage": 63.09, "elapsed_time": "5:15:41", "remaining_time": "3:04:40", "throughput": 4408.05, "total_tokens": 83494384} {"current_steps": 38680, "total_steps": 61300, "loss": 0.2989, "lr": 1.8026999560019366e-05, "epoch": 6.309951060358891, "percentage": 63.1, "elapsed_time": "5:15:43", "remaining_time": "3:04:38", "throughput": 4408.09, "total_tokens": 83504848} {"current_steps": 38685, "total_steps": 61300, "loss": 0.3884, "lr": 1.8020164342330763e-05, "epoch": 6.310766721044046, "percentage": 63.11, "elapsed_time": "5:15:45", "remaining_time": "3:04:35", "throughput": 4408.15, "total_tokens": 83516208} {"current_steps": 38690, "total_steps": 61300, "loss": 0.3261, "lr": 1.8013329690463056e-05, "epoch": 6.311582381729201, "percentage": 63.12, "elapsed_time": "5:15:48", "remaining_time": "3:04:33", "throughput": 4408.2, "total_tokens": 83527056} {"current_steps": 38695, "total_steps": 61300, "loss": 0.3288, "lr": 1.8006495604970295e-05, "epoch": 6.3123980424143555, "percentage": 63.12, "elapsed_time": "5:15:50", "remaining_time": "3:04:30", "throughput": 4408.25, "total_tokens": 83537392} {"current_steps": 38700, "total_steps": 61300, "loss": 0.3478, "lr": 1.7999662086406484e-05, "epoch": 6.31321370309951, "percentage": 63.13, "elapsed_time": "5:15:52", "remaining_time": "3:04:27", "throughput": 4408.3, "total_tokens": 83548944} {"current_steps": 38705, "total_steps": 61300, "loss": 0.3294, "lr": 1.799282913532559e-05, "epoch": 6.314029363784665, "percentage": 63.14, "elapsed_time": "5:15:54", "remaining_time": "3:04:25", "throughput": 4408.35, "total_tokens": 83558832} {"current_steps": 38710, "total_steps": 61300, "loss": 0.3157, "lr": 1.798599675228151e-05, "epoch": 6.314845024469821, "percentage": 63.15, "elapsed_time": "5:15:56", "remaining_time": "3:04:22", "throughput": 4408.38, "total_tokens": 83567696} {"current_steps": 38715, "total_steps": 61300, "loss": 0.3455, "lr": 1.7979164937828127e-05, "epoch": 6.315660685154976, "percentage": 63.16, "elapsed_time": "5:15:58", "remaining_time": "3:04:19", "throughput": 4408.43, "total_tokens": 83578480} {"current_steps": 38720, "total_steps": 61300, "loss": 0.3106, "lr": 1.797233369251926e-05, "epoch": 6.3164763458401305, "percentage": 63.16, "elapsed_time": "5:16:00", "remaining_time": "3:04:17", "throughput": 4408.47, "total_tokens": 83588496} {"current_steps": 38725, "total_steps": 61300, "loss": 0.3411, "lr": 1.796550301690868e-05, "epoch": 6.317292006525285, "percentage": 63.17, "elapsed_time": "5:16:03", "remaining_time": "3:04:14", "throughput": 4408.51, "total_tokens": 83599376} {"current_steps": 38730, "total_steps": 61300, "loss": 0.3583, "lr": 1.7958672911550117e-05, "epoch": 6.31810766721044, "percentage": 63.18, "elapsed_time": "5:16:05", "remaining_time": "3:04:12", "throughput": 4408.56, "total_tokens": 83610032} {"current_steps": 38735, "total_steps": 61300, "loss": 0.3121, "lr": 1.7951843376997256e-05, "epoch": 6.318923327895595, "percentage": 63.19, "elapsed_time": "5:16:07", "remaining_time": "3:04:09", "throughput": 4408.61, "total_tokens": 83621392} {"current_steps": 38740, "total_steps": 61300, "loss": 0.3368, "lr": 1.7945014413803737e-05, "epoch": 6.319738988580751, "percentage": 63.2, "elapsed_time": "5:16:10", "remaining_time": "3:04:07", "throughput": 4408.66, "total_tokens": 83632368} {"current_steps": 38745, "total_steps": 61300, "loss": 0.3483, "lr": 1.7938186022523144e-05, "epoch": 6.3205546492659055, "percentage": 63.21, "elapsed_time": "5:16:12", "remaining_time": "3:04:04", "throughput": 4408.7, "total_tokens": 83642800} {"current_steps": 38750, "total_steps": 61300, "loss": 0.308, "lr": 1.793135820370902e-05, "epoch": 6.32137030995106, "percentage": 63.21, "elapsed_time": "5:16:14", "remaining_time": "3:04:01", "throughput": 4408.75, "total_tokens": 83653552} {"current_steps": 38755, "total_steps": 61300, "loss": 0.3513, "lr": 1.792453095791487e-05, "epoch": 6.322185970636215, "percentage": 63.22, "elapsed_time": "5:16:16", "remaining_time": "3:03:59", "throughput": 4408.8, "total_tokens": 83664624} {"current_steps": 38760, "total_steps": 61300, "loss": 0.3044, "lr": 1.791770428569414e-05, "epoch": 6.32300163132137, "percentage": 63.23, "elapsed_time": "5:16:18", "remaining_time": "3:03:56", "throughput": 4408.85, "total_tokens": 83675536} {"current_steps": 38765, "total_steps": 61300, "loss": 0.3146, "lr": 1.7910878187600232e-05, "epoch": 6.323817292006526, "percentage": 63.24, "elapsed_time": "5:16:21", "remaining_time": "3:03:54", "throughput": 4408.89, "total_tokens": 83685712} {"current_steps": 38770, "total_steps": 61300, "loss": 0.3635, "lr": 1.790405266418651e-05, "epoch": 6.3246329526916805, "percentage": 63.25, "elapsed_time": "5:16:23", "remaining_time": "3:03:51", "throughput": 4408.93, "total_tokens": 83696112} {"current_steps": 38775, "total_steps": 61300, "loss": 0.3309, "lr": 1.789722771600628e-05, "epoch": 6.325448613376835, "percentage": 63.25, "elapsed_time": "5:16:25", "remaining_time": "3:03:48", "throughput": 4408.98, "total_tokens": 83706608} {"current_steps": 38780, "total_steps": 61300, "loss": 0.3613, "lr": 1.789040334361282e-05, "epoch": 6.32626427406199, "percentage": 63.26, "elapsed_time": "5:16:27", "remaining_time": "3:03:46", "throughput": 4409.04, "total_tokens": 83718288} {"current_steps": 38785, "total_steps": 61300, "loss": 0.3554, "lr": 1.788357954755933e-05, "epoch": 6.327079934747145, "percentage": 63.27, "elapsed_time": "5:16:30", "remaining_time": "3:03:43", "throughput": 4409.1, "total_tokens": 83729328} {"current_steps": 38790, "total_steps": 61300, "loss": 0.354, "lr": 1.7876756328398998e-05, "epoch": 6.327895595432301, "percentage": 63.28, "elapsed_time": "5:16:32", "remaining_time": "3:03:41", "throughput": 4409.14, "total_tokens": 83740016} {"current_steps": 38795, "total_steps": 61300, "loss": 0.3237, "lr": 1.7869933686684938e-05, "epoch": 6.328711256117455, "percentage": 63.29, "elapsed_time": "5:16:34", "remaining_time": "3:03:38", "throughput": 4409.19, "total_tokens": 83751120} {"current_steps": 38800, "total_steps": 61300, "loss": 0.3278, "lr": 1.786311162297022e-05, "epoch": 6.32952691680261, "percentage": 63.3, "elapsed_time": "5:16:36", "remaining_time": "3:03:36", "throughput": 4409.24, "total_tokens": 83760880} {"current_steps": 38805, "total_steps": 61300, "loss": 0.3491, "lr": 1.7856290137807893e-05, "epoch": 6.330342577487765, "percentage": 63.3, "elapsed_time": "5:16:38", "remaining_time": "3:03:33", "throughput": 4409.28, "total_tokens": 83771440} {"current_steps": 38810, "total_steps": 61300, "loss": 0.3863, "lr": 1.7849469231750936e-05, "epoch": 6.33115823817292, "percentage": 63.31, "elapsed_time": "5:16:40", "remaining_time": "3:03:30", "throughput": 4409.33, "total_tokens": 83781424} {"current_steps": 38815, "total_steps": 61300, "loss": 0.3404, "lr": 1.784264890535229e-05, "epoch": 6.331973898858075, "percentage": 63.32, "elapsed_time": "5:16:43", "remaining_time": "3:03:28", "throughput": 4409.38, "total_tokens": 83792848} {"current_steps": 38820, "total_steps": 61300, "loss": 0.3707, "lr": 1.7835829159164835e-05, "epoch": 6.33278955954323, "percentage": 63.33, "elapsed_time": "5:16:45", "remaining_time": "3:03:25", "throughput": 4409.42, "total_tokens": 83803152} {"current_steps": 38825, "total_steps": 61300, "loss": 0.3366, "lr": 1.7829009993741418e-05, "epoch": 6.333605220228385, "percentage": 63.34, "elapsed_time": "5:16:47", "remaining_time": "3:03:23", "throughput": 4409.48, "total_tokens": 83814672} {"current_steps": 38830, "total_steps": 61300, "loss": 0.3514, "lr": 1.782219140963484e-05, "epoch": 6.33442088091354, "percentage": 63.34, "elapsed_time": "5:16:50", "remaining_time": "3:03:20", "throughput": 4409.53, "total_tokens": 83825904} {"current_steps": 38835, "total_steps": 61300, "loss": 0.3151, "lr": 1.781537340739784e-05, "epoch": 6.335236541598695, "percentage": 63.35, "elapsed_time": "5:16:52", "remaining_time": "3:03:18", "throughput": 4409.58, "total_tokens": 83837936} {"current_steps": 38840, "total_steps": 61300, "loss": 0.3257, "lr": 1.780855598758313e-05, "epoch": 6.33605220228385, "percentage": 63.36, "elapsed_time": "5:16:55", "remaining_time": "3:03:15", "throughput": 4409.62, "total_tokens": 83848944} {"current_steps": 38845, "total_steps": 61300, "loss": 0.3092, "lr": 1.7801739150743363e-05, "epoch": 6.3368678629690045, "percentage": 63.37, "elapsed_time": "5:16:57", "remaining_time": "3:03:13", "throughput": 4409.68, "total_tokens": 83861136} {"current_steps": 38850, "total_steps": 61300, "loss": 0.3218, "lr": 1.7794922897431145e-05, "epoch": 6.33768352365416, "percentage": 63.38, "elapsed_time": "5:17:00", "remaining_time": "3:03:10", "throughput": 4409.72, "total_tokens": 83873136} {"current_steps": 38855, "total_steps": 61300, "loss": 0.3515, "lr": 1.7788107228199023e-05, "epoch": 6.338499184339315, "percentage": 63.38, "elapsed_time": "5:17:02", "remaining_time": "3:03:08", "throughput": 4409.77, "total_tokens": 83884496} {"current_steps": 38860, "total_steps": 61300, "loss": 0.3246, "lr": 1.7781292143599532e-05, "epoch": 6.33931484502447, "percentage": 63.39, "elapsed_time": "5:17:04", "remaining_time": "3:03:05", "throughput": 4409.83, "total_tokens": 83895664} {"current_steps": 38865, "total_steps": 61300, "loss": 0.3257, "lr": 1.7774477644185125e-05, "epoch": 6.340130505709625, "percentage": 63.4, "elapsed_time": "5:17:07", "remaining_time": "3:03:03", "throughput": 4409.88, "total_tokens": 83907664} {"current_steps": 38870, "total_steps": 61300, "loss": 0.3603, "lr": 1.7767663730508222e-05, "epoch": 6.3409461663947795, "percentage": 63.41, "elapsed_time": "5:17:09", "remaining_time": "3:03:00", "throughput": 4409.94, "total_tokens": 83918896} {"current_steps": 38875, "total_steps": 61300, "loss": 0.3526, "lr": 1.7760850403121195e-05, "epoch": 6.341761827079935, "percentage": 63.42, "elapsed_time": "5:17:11", "remaining_time": "3:02:58", "throughput": 4409.99, "total_tokens": 83929008} {"current_steps": 38880, "total_steps": 61300, "loss": 0.3504, "lr": 1.7754037662576365e-05, "epoch": 6.34257748776509, "percentage": 63.43, "elapsed_time": "5:17:13", "remaining_time": "3:02:55", "throughput": 4410.02, "total_tokens": 83937776} {"current_steps": 38885, "total_steps": 61300, "loss": 0.3265, "lr": 1.7747225509426008e-05, "epoch": 6.343393148450245, "percentage": 63.43, "elapsed_time": "5:17:15", "remaining_time": "3:02:53", "throughput": 4410.07, "total_tokens": 83948816} {"current_steps": 38890, "total_steps": 61300, "loss": 0.3506, "lr": 1.774041394422235e-05, "epoch": 6.3442088091354, "percentage": 63.44, "elapsed_time": "5:17:17", "remaining_time": "3:02:50", "throughput": 4410.12, "total_tokens": 83959440} {"current_steps": 38895, "total_steps": 61300, "loss": 0.2974, "lr": 1.7733602967517578e-05, "epoch": 6.3450244698205545, "percentage": 63.45, "elapsed_time": "5:17:20", "remaining_time": "3:02:47", "throughput": 4410.16, "total_tokens": 83971248} {"current_steps": 38900, "total_steps": 61300, "loss": 0.3431, "lr": 1.772679257986381e-05, "epoch": 6.345840130505709, "percentage": 63.46, "elapsed_time": "5:17:22", "remaining_time": "3:02:45", "throughput": 4410.2, "total_tokens": 83981584} {"current_steps": 38905, "total_steps": 61300, "loss": 0.3319, "lr": 1.7719982781813135e-05, "epoch": 6.346655791190865, "percentage": 63.47, "elapsed_time": "5:17:24", "remaining_time": "3:02:42", "throughput": 4410.25, "total_tokens": 83992112} {"current_steps": 38910, "total_steps": 61300, "loss": 0.33, "lr": 1.7713173573917603e-05, "epoch": 6.34747145187602, "percentage": 63.47, "elapsed_time": "5:17:27", "remaining_time": "3:02:40", "throughput": 4410.3, "total_tokens": 84003472} {"current_steps": 38915, "total_steps": 61300, "loss": 0.3299, "lr": 1.7706364956729195e-05, "epoch": 6.348287112561175, "percentage": 63.48, "elapsed_time": "5:17:29", "remaining_time": "3:02:37", "throughput": 4410.35, "total_tokens": 84013840} {"current_steps": 38920, "total_steps": 61300, "loss": 0.3368, "lr": 1.769955693079985e-05, "epoch": 6.349102773246329, "percentage": 63.49, "elapsed_time": "5:17:31", "remaining_time": "3:02:35", "throughput": 4410.39, "total_tokens": 84024912} {"current_steps": 38925, "total_steps": 61300, "loss": 0.3175, "lr": 1.769274949668146e-05, "epoch": 6.349918433931484, "percentage": 63.5, "elapsed_time": "5:17:33", "remaining_time": "3:02:32", "throughput": 4410.44, "total_tokens": 84035632} {"current_steps": 38930, "total_steps": 61300, "loss": 0.3364, "lr": 1.7685942654925876e-05, "epoch": 6.350734094616639, "percentage": 63.51, "elapsed_time": "5:17:36", "remaining_time": "3:02:30", "throughput": 4410.48, "total_tokens": 84046448} {"current_steps": 38935, "total_steps": 61300, "loss": 0.3464, "lr": 1.767913640608489e-05, "epoch": 6.351549755301795, "percentage": 63.52, "elapsed_time": "5:17:38", "remaining_time": "3:02:27", "throughput": 4410.53, "total_tokens": 84057648} {"current_steps": 38940, "total_steps": 61300, "loss": 0.2928, "lr": 1.7672330750710247e-05, "epoch": 6.35236541598695, "percentage": 63.52, "elapsed_time": "5:17:40", "remaining_time": "3:02:24", "throughput": 4410.59, "total_tokens": 84068880} {"current_steps": 38945, "total_steps": 61300, "loss": 0.3525, "lr": 1.766552568935366e-05, "epoch": 6.353181076672104, "percentage": 63.53, "elapsed_time": "5:17:42", "remaining_time": "3:02:22", "throughput": 4410.64, "total_tokens": 84079696} {"current_steps": 38950, "total_steps": 61300, "loss": 0.3379, "lr": 1.7658721222566775e-05, "epoch": 6.353996737357259, "percentage": 63.54, "elapsed_time": "5:17:44", "remaining_time": "3:02:19", "throughput": 4410.67, "total_tokens": 84089456} {"current_steps": 38955, "total_steps": 61300, "loss": 0.3086, "lr": 1.76519173509012e-05, "epoch": 6.354812398042414, "percentage": 63.55, "elapsed_time": "5:17:47", "remaining_time": "3:02:17", "throughput": 4410.72, "total_tokens": 84099440} {"current_steps": 38960, "total_steps": 61300, "loss": 0.3296, "lr": 1.764511407490848e-05, "epoch": 6.35562805872757, "percentage": 63.56, "elapsed_time": "5:17:49", "remaining_time": "3:02:14", "throughput": 4410.76, "total_tokens": 84109232} {"current_steps": 38965, "total_steps": 61300, "loss": 0.3403, "lr": 1.763831139514014e-05, "epoch": 6.356443719412725, "percentage": 63.56, "elapsed_time": "5:17:51", "remaining_time": "3:02:12", "throughput": 4410.82, "total_tokens": 84121712} {"current_steps": 38970, "total_steps": 61300, "loss": 0.3456, "lr": 1.7631509312147626e-05, "epoch": 6.357259380097879, "percentage": 63.57, "elapsed_time": "5:17:53", "remaining_time": "3:02:09", "throughput": 4410.87, "total_tokens": 84132688} {"current_steps": 38975, "total_steps": 61300, "loss": 0.3344, "lr": 1.7624707826482356e-05, "epoch": 6.358075040783034, "percentage": 63.58, "elapsed_time": "5:17:56", "remaining_time": "3:02:06", "throughput": 4410.91, "total_tokens": 84142544} {"current_steps": 38980, "total_steps": 61300, "loss": 0.3624, "lr": 1.7617906938695694e-05, "epoch": 6.358890701468189, "percentage": 63.59, "elapsed_time": "5:17:57", "remaining_time": "3:02:03", "throughput": 4410.96, "total_tokens": 84151312} {"current_steps": 38985, "total_steps": 61300, "loss": 0.3412, "lr": 1.761110664933895e-05, "epoch": 6.359706362153344, "percentage": 63.6, "elapsed_time": "5:18:00", "remaining_time": "3:02:01", "throughput": 4411.0, "total_tokens": 84162512} {"current_steps": 38990, "total_steps": 61300, "loss": 0.3144, "lr": 1.760430695896339e-05, "epoch": 6.3605220228384995, "percentage": 63.61, "elapsed_time": "5:18:02", "remaining_time": "3:01:59", "throughput": 4411.05, "total_tokens": 84174480} {"current_steps": 38995, "total_steps": 61300, "loss": 0.3294, "lr": 1.7597507868120227e-05, "epoch": 6.361337683523654, "percentage": 63.61, "elapsed_time": "5:18:04", "remaining_time": "3:01:56", "throughput": 4411.11, "total_tokens": 84185712} {"current_steps": 39000, "total_steps": 61300, "loss": 0.3319, "lr": 1.7590709377360648e-05, "epoch": 6.362153344208809, "percentage": 63.62, "elapsed_time": "5:18:07", "remaining_time": "3:01:53", "throughput": 4411.14, "total_tokens": 84195824} {"current_steps": 39005, "total_steps": 61300, "loss": 0.3486, "lr": 1.7583911487235753e-05, "epoch": 6.362969004893964, "percentage": 63.63, "elapsed_time": "5:18:09", "remaining_time": "3:01:51", "throughput": 4411.2, "total_tokens": 84207344} {"current_steps": 39010, "total_steps": 61300, "loss": 0.3378, "lr": 1.7577114198296623e-05, "epoch": 6.363784665579119, "percentage": 63.64, "elapsed_time": "5:18:11", "remaining_time": "3:01:48", "throughput": 4411.24, "total_tokens": 84218512} {"current_steps": 39015, "total_steps": 61300, "loss": 0.3389, "lr": 1.757031751109428e-05, "epoch": 6.364600326264274, "percentage": 63.65, "elapsed_time": "5:18:14", "remaining_time": "3:01:46", "throughput": 4411.28, "total_tokens": 84229520} {"current_steps": 39020, "total_steps": 61300, "loss": 0.3244, "lr": 1.75635214261797e-05, "epoch": 6.365415986949429, "percentage": 63.65, "elapsed_time": "5:18:16", "remaining_time": "3:01:43", "throughput": 4411.34, "total_tokens": 84240752} {"current_steps": 39025, "total_steps": 61300, "loss": 0.341, "lr": 1.7556725944103803e-05, "epoch": 6.366231647634584, "percentage": 63.66, "elapsed_time": "5:18:18", "remaining_time": "3:01:41", "throughput": 4411.39, "total_tokens": 84250224} {"current_steps": 39030, "total_steps": 61300, "loss": 0.3544, "lr": 1.754993106541747e-05, "epoch": 6.367047308319739, "percentage": 63.67, "elapsed_time": "5:18:20", "remaining_time": "3:01:38", "throughput": 4411.43, "total_tokens": 84260784} {"current_steps": 39035, "total_steps": 61300, "loss": 0.3171, "lr": 1.7543136790671524e-05, "epoch": 6.367862969004894, "percentage": 63.68, "elapsed_time": "5:18:22", "remaining_time": "3:01:36", "throughput": 4411.49, "total_tokens": 84272560} {"current_steps": 39040, "total_steps": 61300, "loss": 0.3264, "lr": 1.753634312041675e-05, "epoch": 6.368678629690049, "percentage": 63.69, "elapsed_time": "5:18:25", "remaining_time": "3:01:33", "throughput": 4411.53, "total_tokens": 84282640} {"current_steps": 39045, "total_steps": 61300, "loss": 0.324, "lr": 1.752955005520387e-05, "epoch": 6.369494290375204, "percentage": 63.69, "elapsed_time": "5:18:27", "remaining_time": "3:01:30", "throughput": 4411.58, "total_tokens": 84293936} {"current_steps": 39050, "total_steps": 61300, "loss": 0.3345, "lr": 1.7522757595583567e-05, "epoch": 6.370309951060359, "percentage": 63.7, "elapsed_time": "5:18:29", "remaining_time": "3:01:28", "throughput": 4411.63, "total_tokens": 84303376} {"current_steps": 39055, "total_steps": 61300, "loss": 0.3379, "lr": 1.751596574210647e-05, "epoch": 6.371125611745514, "percentage": 63.71, "elapsed_time": "5:18:31", "remaining_time": "3:01:25", "throughput": 4411.67, "total_tokens": 84313968} {"current_steps": 39060, "total_steps": 61300, "loss": 0.3254, "lr": 1.750917449532317e-05, "epoch": 6.371941272430669, "percentage": 63.72, "elapsed_time": "5:18:33", "remaining_time": "3:01:23", "throughput": 4411.72, "total_tokens": 84325520} {"current_steps": 39065, "total_steps": 61300, "loss": 0.3473, "lr": 1.7502383855784187e-05, "epoch": 6.372756933115824, "percentage": 63.73, "elapsed_time": "5:18:36", "remaining_time": "3:01:20", "throughput": 4411.77, "total_tokens": 84336496} {"current_steps": 39070, "total_steps": 61300, "loss": 0.3575, "lr": 1.7495593824040014e-05, "epoch": 6.373572593800978, "percentage": 63.74, "elapsed_time": "5:18:38", "remaining_time": "3:01:17", "throughput": 4411.81, "total_tokens": 84346928} {"current_steps": 39075, "total_steps": 61300, "loss": 0.3405, "lr": 1.7488804400641084e-05, "epoch": 6.374388254486134, "percentage": 63.74, "elapsed_time": "5:18:40", "remaining_time": "3:01:15", "throughput": 4411.86, "total_tokens": 84358032} {"current_steps": 39080, "total_steps": 61300, "loss": 0.3178, "lr": 1.7482015586137774e-05, "epoch": 6.375203915171289, "percentage": 63.75, "elapsed_time": "5:18:42", "remaining_time": "3:01:12", "throughput": 4411.91, "total_tokens": 84368816} {"current_steps": 39085, "total_steps": 61300, "loss": 0.3093, "lr": 1.7475227381080434e-05, "epoch": 6.376019575856444, "percentage": 63.76, "elapsed_time": "5:18:45", "remaining_time": "3:01:10", "throughput": 4411.96, "total_tokens": 84378800} {"current_steps": 39090, "total_steps": 61300, "loss": 0.3248, "lr": 1.746843978601934e-05, "epoch": 6.376835236541599, "percentage": 63.77, "elapsed_time": "5:18:47", "remaining_time": "3:01:07", "throughput": 4411.99, "total_tokens": 84389584} {"current_steps": 39095, "total_steps": 61300, "loss": 0.3586, "lr": 1.746165280150473e-05, "epoch": 6.377650897226753, "percentage": 63.78, "elapsed_time": "5:18:49", "remaining_time": "3:01:04", "throughput": 4412.03, "total_tokens": 84398768} {"current_steps": 39100, "total_steps": 61300, "loss": 0.3186, "lr": 1.7454866428086797e-05, "epoch": 6.378466557911908, "percentage": 63.78, "elapsed_time": "5:18:51", "remaining_time": "3:01:02", "throughput": 4412.08, "total_tokens": 84408464} {"current_steps": 39105, "total_steps": 61300, "loss": 0.3439, "lr": 1.7448080666315675e-05, "epoch": 6.379282218597064, "percentage": 63.79, "elapsed_time": "5:18:53", "remaining_time": "3:00:59", "throughput": 4412.12, "total_tokens": 84419600} {"current_steps": 39110, "total_steps": 61300, "loss": 0.3433, "lr": 1.744129551674145e-05, "epoch": 6.380097879282219, "percentage": 63.8, "elapsed_time": "5:18:55", "remaining_time": "3:00:56", "throughput": 4412.16, "total_tokens": 84428784} {"current_steps": 39115, "total_steps": 61300, "loss": 0.3244, "lr": 1.7434510979914166e-05, "epoch": 6.3809135399673735, "percentage": 63.81, "elapsed_time": "5:18:57", "remaining_time": "3:00:54", "throughput": 4412.19, "total_tokens": 84439696} {"current_steps": 39120, "total_steps": 61300, "loss": 0.3278, "lr": 1.7427727056383795e-05, "epoch": 6.381729200652528, "percentage": 63.82, "elapsed_time": "5:19:00", "remaining_time": "3:00:51", "throughput": 4412.25, "total_tokens": 84451280} {"current_steps": 39125, "total_steps": 61300, "loss": 0.3283, "lr": 1.74209437467003e-05, "epoch": 6.382544861337683, "percentage": 63.83, "elapsed_time": "5:19:02", "remaining_time": "3:00:49", "throughput": 4412.3, "total_tokens": 84462512} {"current_steps": 39130, "total_steps": 61300, "loss": 0.322, "lr": 1.7414161051413565e-05, "epoch": 6.383360522022839, "percentage": 63.83, "elapsed_time": "5:19:04", "remaining_time": "3:00:46", "throughput": 4412.35, "total_tokens": 84473616} {"current_steps": 39135, "total_steps": 61300, "loss": 0.3169, "lr": 1.740737897107342e-05, "epoch": 6.384176182707994, "percentage": 63.84, "elapsed_time": "5:19:07", "remaining_time": "3:00:44", "throughput": 4412.41, "total_tokens": 84485776} {"current_steps": 39140, "total_steps": 61300, "loss": 0.3225, "lr": 1.7400597506229667e-05, "epoch": 6.3849918433931485, "percentage": 63.85, "elapsed_time": "5:19:09", "remaining_time": "3:00:42", "throughput": 4412.47, "total_tokens": 84498064} {"current_steps": 39145, "total_steps": 61300, "loss": 0.3285, "lr": 1.739381665743203e-05, "epoch": 6.385807504078303, "percentage": 63.86, "elapsed_time": "5:19:12", "remaining_time": "3:00:39", "throughput": 4412.52, "total_tokens": 84509296} {"current_steps": 39150, "total_steps": 61300, "loss": 0.3209, "lr": 1.7387036425230214e-05, "epoch": 6.386623164763458, "percentage": 63.87, "elapsed_time": "5:19:14", "remaining_time": "3:00:36", "throughput": 4412.58, "total_tokens": 84519888} {"current_steps": 39155, "total_steps": 61300, "loss": 0.366, "lr": 1.7380256810173854e-05, "epoch": 6.387438825448613, "percentage": 63.87, "elapsed_time": "5:19:16", "remaining_time": "3:00:34", "throughput": 4412.62, "total_tokens": 84530352} {"current_steps": 39160, "total_steps": 61300, "loss": 0.354, "lr": 1.7373477812812538e-05, "epoch": 6.388254486133769, "percentage": 63.88, "elapsed_time": "5:19:18", "remaining_time": "3:00:31", "throughput": 4412.68, "total_tokens": 84540912} {"current_steps": 39165, "total_steps": 61300, "loss": 0.3603, "lr": 1.73666994336958e-05, "epoch": 6.3890701468189235, "percentage": 63.89, "elapsed_time": "5:19:20", "remaining_time": "3:00:29", "throughput": 4412.72, "total_tokens": 84551760} {"current_steps": 39170, "total_steps": 61300, "loss": 0.3619, "lr": 1.735992167337314e-05, "epoch": 6.389885807504078, "percentage": 63.9, "elapsed_time": "5:19:23", "remaining_time": "3:00:26", "throughput": 4412.76, "total_tokens": 84562960} {"current_steps": 39175, "total_steps": 61300, "loss": 0.3439, "lr": 1.7353144532394e-05, "epoch": 6.390701468189233, "percentage": 63.91, "elapsed_time": "5:19:25", "remaining_time": "3:00:24", "throughput": 4412.81, "total_tokens": 84573264} {"current_steps": 39180, "total_steps": 61300, "loss": 0.3246, "lr": 1.734636801130776e-05, "epoch": 6.391517128874388, "percentage": 63.92, "elapsed_time": "5:19:27", "remaining_time": "3:00:21", "throughput": 4412.86, "total_tokens": 84583632} {"current_steps": 39185, "total_steps": 61300, "loss": 0.3384, "lr": 1.7339592110663768e-05, "epoch": 6.392332789559543, "percentage": 63.92, "elapsed_time": "5:19:29", "remaining_time": "3:00:19", "throughput": 4412.9, "total_tokens": 84594960} {"current_steps": 39190, "total_steps": 61300, "loss": 0.3636, "lr": 1.7332816831011307e-05, "epoch": 6.3931484502446985, "percentage": 63.93, "elapsed_time": "5:19:31", "remaining_time": "3:00:16", "throughput": 4412.95, "total_tokens": 84604912} {"current_steps": 39195, "total_steps": 61300, "loss": 0.3429, "lr": 1.7326042172899616e-05, "epoch": 6.393964110929853, "percentage": 63.94, "elapsed_time": "5:19:34", "remaining_time": "3:00:13", "throughput": 4412.99, "total_tokens": 84615344} {"current_steps": 39200, "total_steps": 61300, "loss": 0.3547, "lr": 1.731926813687788e-05, "epoch": 6.394779771615008, "percentage": 63.95, "elapsed_time": "5:19:36", "remaining_time": "3:00:11", "throughput": 4413.02, "total_tokens": 84625744} {"current_steps": 39205, "total_steps": 61300, "loss": 0.3386, "lr": 1.7312494723495243e-05, "epoch": 6.395595432300163, "percentage": 63.96, "elapsed_time": "5:19:38", "remaining_time": "3:00:08", "throughput": 4413.08, "total_tokens": 84636784} {"current_steps": 39210, "total_steps": 61300, "loss": 0.3152, "lr": 1.730572193330079e-05, "epoch": 6.396411092985318, "percentage": 63.96, "elapsed_time": "5:19:41", "remaining_time": "3:00:06", "throughput": 4413.12, "total_tokens": 84648656} {"current_steps": 39215, "total_steps": 61300, "loss": 0.3337, "lr": 1.7298949766843558e-05, "epoch": 6.397226753670473, "percentage": 63.97, "elapsed_time": "5:19:43", "remaining_time": "3:00:03", "throughput": 4413.17, "total_tokens": 84659728} {"current_steps": 39220, "total_steps": 61300, "loss": 0.3098, "lr": 1.7292178224672528e-05, "epoch": 6.398042414355628, "percentage": 63.98, "elapsed_time": "5:19:45", "remaining_time": "3:00:01", "throughput": 4413.22, "total_tokens": 84670672} {"current_steps": 39225, "total_steps": 61300, "loss": 0.3404, "lr": 1.7285407307336636e-05, "epoch": 6.398858075040783, "percentage": 63.99, "elapsed_time": "5:19:47", "remaining_time": "2:59:58", "throughput": 4413.25, "total_tokens": 84679952} {"current_steps": 39230, "total_steps": 61300, "loss": 0.339, "lr": 1.727863701538478e-05, "epoch": 6.399673735725938, "percentage": 64.0, "elapsed_time": "5:19:49", "remaining_time": "2:59:55", "throughput": 4413.31, "total_tokens": 84691024} {"current_steps": 39235, "total_steps": 61300, "loss": 0.3537, "lr": 1.7271867349365782e-05, "epoch": 6.400489396411093, "percentage": 64.0, "elapsed_time": "5:19:51", "remaining_time": "2:59:53", "throughput": 4413.36, "total_tokens": 84700976} {"current_steps": 39240, "total_steps": 61300, "loss": 0.3233, "lr": 1.7265098309828433e-05, "epoch": 6.401305057096248, "percentage": 64.01, "elapsed_time": "5:19:53", "remaining_time": "2:59:50", "throughput": 4413.41, "total_tokens": 84710896} {"current_steps": 39245, "total_steps": 61300, "loss": 0.3435, "lr": 1.725832989732146e-05, "epoch": 6.402120717781403, "percentage": 64.02, "elapsed_time": "5:19:56", "remaining_time": "2:59:48", "throughput": 4413.45, "total_tokens": 84722448} {"current_steps": 39250, "total_steps": 61300, "loss": 0.325, "lr": 1.725156211239354e-05, "epoch": 6.402936378466558, "percentage": 64.03, "elapsed_time": "5:19:58", "remaining_time": "2:59:45", "throughput": 4413.5, "total_tokens": 84733168} {"current_steps": 39255, "total_steps": 61300, "loss": 0.3359, "lr": 1.7244794955593316e-05, "epoch": 6.403752039151713, "percentage": 64.04, "elapsed_time": "5:20:00", "remaining_time": "2:59:42", "throughput": 4413.54, "total_tokens": 84744176} {"current_steps": 39260, "total_steps": 61300, "loss": 0.3267, "lr": 1.7238028427469363e-05, "epoch": 6.404567699836868, "percentage": 64.05, "elapsed_time": "5:20:03", "remaining_time": "2:59:40", "throughput": 4413.59, "total_tokens": 84754704} {"current_steps": 39265, "total_steps": 61300, "loss": 0.3672, "lr": 1.7231262528570207e-05, "epoch": 6.4053833605220225, "percentage": 64.05, "elapsed_time": "5:20:05", "remaining_time": "2:59:37", "throughput": 4413.63, "total_tokens": 84765584} {"current_steps": 39270, "total_steps": 61300, "loss": 0.3335, "lr": 1.7224497259444334e-05, "epoch": 6.406199021207178, "percentage": 64.06, "elapsed_time": "5:20:07", "remaining_time": "2:59:35", "throughput": 4413.68, "total_tokens": 84776144} {"current_steps": 39275, "total_steps": 61300, "loss": 0.3543, "lr": 1.7217732620640163e-05, "epoch": 6.407014681892333, "percentage": 64.07, "elapsed_time": "5:20:09", "remaining_time": "2:59:32", "throughput": 4413.72, "total_tokens": 84785488} {"current_steps": 39280, "total_steps": 61300, "loss": 0.3224, "lr": 1.721096861270607e-05, "epoch": 6.407830342577488, "percentage": 64.08, "elapsed_time": "5:20:11", "remaining_time": "2:59:29", "throughput": 4413.77, "total_tokens": 84796080} {"current_steps": 39285, "total_steps": 61300, "loss": 0.3485, "lr": 1.7204205236190385e-05, "epoch": 6.408646003262643, "percentage": 64.09, "elapsed_time": "5:20:13", "remaining_time": "2:59:27", "throughput": 4413.81, "total_tokens": 84805520} {"current_steps": 39290, "total_steps": 61300, "loss": 0.3312, "lr": 1.719744249164138e-05, "epoch": 6.4094616639477975, "percentage": 64.09, "elapsed_time": "5:20:15", "remaining_time": "2:59:24", "throughput": 4413.85, "total_tokens": 84816464} {"current_steps": 39295, "total_steps": 61300, "loss": 0.3515, "lr": 1.7190680379607278e-05, "epoch": 6.410277324632952, "percentage": 64.1, "elapsed_time": "5:20:18", "remaining_time": "2:59:22", "throughput": 4413.89, "total_tokens": 84826640} {"current_steps": 39300, "total_steps": 61300, "loss": 0.3373, "lr": 1.718391890063624e-05, "epoch": 6.411092985318108, "percentage": 64.11, "elapsed_time": "5:20:20", "remaining_time": "2:59:19", "throughput": 4413.93, "total_tokens": 84836304} {"current_steps": 39305, "total_steps": 61300, "loss": 0.324, "lr": 1.7177158055276405e-05, "epoch": 6.411908646003263, "percentage": 64.12, "elapsed_time": "5:20:22", "remaining_time": "2:59:16", "throughput": 4413.98, "total_tokens": 84847280} {"current_steps": 39310, "total_steps": 61300, "loss": 0.3224, "lr": 1.717039784407582e-05, "epoch": 6.412724306688418, "percentage": 64.13, "elapsed_time": "5:20:24", "remaining_time": "2:59:14", "throughput": 4414.04, "total_tokens": 84859696} {"current_steps": 39315, "total_steps": 61300, "loss": 0.2974, "lr": 1.7163638267582516e-05, "epoch": 6.4135399673735725, "percentage": 64.14, "elapsed_time": "5:20:27", "remaining_time": "2:59:11", "throughput": 4414.07, "total_tokens": 84870576} {"current_steps": 39320, "total_steps": 61300, "loss": 0.366, "lr": 1.715687932634446e-05, "epoch": 6.414355628058727, "percentage": 64.14, "elapsed_time": "5:20:29", "remaining_time": "2:59:09", "throughput": 4414.13, "total_tokens": 84882224} {"current_steps": 39325, "total_steps": 61300, "loss": 0.3821, "lr": 1.715012102090956e-05, "epoch": 6.415171288743883, "percentage": 64.15, "elapsed_time": "5:20:31", "remaining_time": "2:59:06", "throughput": 4414.18, "total_tokens": 84892496} {"current_steps": 39330, "total_steps": 61300, "loss": 0.3281, "lr": 1.714336335182567e-05, "epoch": 6.415986949429038, "percentage": 64.16, "elapsed_time": "5:20:34", "remaining_time": "2:59:04", "throughput": 4414.23, "total_tokens": 84903440} {"current_steps": 39335, "total_steps": 61300, "loss": 0.3656, "lr": 1.7136606319640616e-05, "epoch": 6.416802610114193, "percentage": 64.17, "elapsed_time": "5:20:36", "remaining_time": "2:59:01", "throughput": 4414.28, "total_tokens": 84914608} {"current_steps": 39340, "total_steps": 61300, "loss": 0.3397, "lr": 1.7129849924902157e-05, "epoch": 6.417618270799347, "percentage": 64.18, "elapsed_time": "5:20:38", "remaining_time": "2:58:59", "throughput": 4414.33, "total_tokens": 84926768} {"current_steps": 39345, "total_steps": 61300, "loss": 0.326, "lr": 1.7123094168157994e-05, "epoch": 6.418433931484502, "percentage": 64.18, "elapsed_time": "5:20:41", "remaining_time": "2:58:56", "throughput": 4414.37, "total_tokens": 84937488} {"current_steps": 39350, "total_steps": 61300, "loss": 0.3343, "lr": 1.7116339049955788e-05, "epoch": 6.419249592169657, "percentage": 64.19, "elapsed_time": "5:20:43", "remaining_time": "2:58:54", "throughput": 4414.43, "total_tokens": 84949840} {"current_steps": 39355, "total_steps": 61300, "loss": 0.3519, "lr": 1.7109584570843136e-05, "epoch": 6.420065252854813, "percentage": 64.2, "elapsed_time": "5:20:45", "remaining_time": "2:58:51", "throughput": 4414.47, "total_tokens": 84959088} {"current_steps": 39360, "total_steps": 61300, "loss": 0.3188, "lr": 1.7102830731367593e-05, "epoch": 6.420880913539968, "percentage": 64.21, "elapsed_time": "5:20:47", "remaining_time": "2:58:49", "throughput": 4414.51, "total_tokens": 84969232} {"current_steps": 39365, "total_steps": 61300, "loss": 0.3068, "lr": 1.7096077532076666e-05, "epoch": 6.421696574225122, "percentage": 64.22, "elapsed_time": "5:20:50", "remaining_time": "2:58:46", "throughput": 4414.57, "total_tokens": 84981488} {"current_steps": 39370, "total_steps": 61300, "loss": 0.3499, "lr": 1.7089324973517794e-05, "epoch": 6.422512234910277, "percentage": 64.23, "elapsed_time": "5:20:52", "remaining_time": "2:58:44", "throughput": 4414.61, "total_tokens": 84992688} {"current_steps": 39375, "total_steps": 61300, "loss": 0.3461, "lr": 1.708257305623838e-05, "epoch": 6.423327895595432, "percentage": 64.23, "elapsed_time": "5:20:54", "remaining_time": "2:58:41", "throughput": 4414.67, "total_tokens": 85004144} {"current_steps": 39380, "total_steps": 61300, "loss": 0.3201, "lr": 1.7075821780785766e-05, "epoch": 6.424143556280587, "percentage": 64.24, "elapsed_time": "5:20:57", "remaining_time": "2:58:39", "throughput": 4414.72, "total_tokens": 85015408} {"current_steps": 39385, "total_steps": 61300, "loss": 0.3484, "lr": 1.7069071147707248e-05, "epoch": 6.424959216965743, "percentage": 64.25, "elapsed_time": "5:20:59", "remaining_time": "2:58:36", "throughput": 4414.76, "total_tokens": 85026064} {"current_steps": 39390, "total_steps": 61300, "loss": 0.3627, "lr": 1.706232115755006e-05, "epoch": 6.425774877650897, "percentage": 64.26, "elapsed_time": "5:21:01", "remaining_time": "2:58:34", "throughput": 4414.82, "total_tokens": 85037232} {"current_steps": 39395, "total_steps": 61300, "loss": 0.3322, "lr": 1.705557181086139e-05, "epoch": 6.426590538336052, "percentage": 64.27, "elapsed_time": "5:21:03", "remaining_time": "2:58:31", "throughput": 4414.87, "total_tokens": 85047888} {"current_steps": 39400, "total_steps": 61300, "loss": 0.3588, "lr": 1.704882310818839e-05, "epoch": 6.427406199021207, "percentage": 64.27, "elapsed_time": "5:21:06", "remaining_time": "2:58:28", "throughput": 4414.92, "total_tokens": 85058768} {"current_steps": 39405, "total_steps": 61300, "loss": 0.3478, "lr": 1.704207505007813e-05, "epoch": 6.428221859706362, "percentage": 64.28, "elapsed_time": "5:21:08", "remaining_time": "2:58:26", "throughput": 4414.96, "total_tokens": 85069296} {"current_steps": 39410, "total_steps": 61300, "loss": 0.3534, "lr": 1.703532763707764e-05, "epoch": 6.4290375203915175, "percentage": 64.29, "elapsed_time": "5:21:10", "remaining_time": "2:58:23", "throughput": 4415.0, "total_tokens": 85080528} {"current_steps": 39415, "total_steps": 61300, "loss": 0.3305, "lr": 1.7028580869733905e-05, "epoch": 6.429853181076672, "percentage": 64.3, "elapsed_time": "5:21:12", "remaining_time": "2:58:21", "throughput": 4415.05, "total_tokens": 85091024} {"current_steps": 39420, "total_steps": 61300, "loss": 0.3417, "lr": 1.702183474859385e-05, "epoch": 6.430668841761827, "percentage": 64.31, "elapsed_time": "5:21:14", "remaining_time": "2:58:18", "throughput": 4415.1, "total_tokens": 85100656} {"current_steps": 39425, "total_steps": 61300, "loss": 0.355, "lr": 1.7015089274204354e-05, "epoch": 6.431484502446982, "percentage": 64.31, "elapsed_time": "5:21:17", "remaining_time": "2:58:16", "throughput": 4415.14, "total_tokens": 85111856} {"current_steps": 39430, "total_steps": 61300, "loss": 0.3262, "lr": 1.7008344447112238e-05, "epoch": 6.432300163132137, "percentage": 64.32, "elapsed_time": "5:21:19", "remaining_time": "2:58:13", "throughput": 4415.18, "total_tokens": 85120944} {"current_steps": 39435, "total_steps": 61300, "loss": 0.3363, "lr": 1.7001600267864266e-05, "epoch": 6.433115823817292, "percentage": 64.33, "elapsed_time": "5:21:21", "remaining_time": "2:58:10", "throughput": 4415.22, "total_tokens": 85131440} {"current_steps": 39440, "total_steps": 61300, "loss": 0.3546, "lr": 1.6994856737007154e-05, "epoch": 6.433931484502447, "percentage": 64.34, "elapsed_time": "5:21:23", "remaining_time": "2:58:07", "throughput": 4415.26, "total_tokens": 85140720} {"current_steps": 39445, "total_steps": 61300, "loss": 0.369, "lr": 1.698811385508758e-05, "epoch": 6.434747145187602, "percentage": 64.35, "elapsed_time": "5:21:25", "remaining_time": "2:58:05", "throughput": 4415.29, "total_tokens": 85151152} {"current_steps": 39450, "total_steps": 61300, "loss": 0.3315, "lr": 1.698137162265215e-05, "epoch": 6.435562805872757, "percentage": 64.36, "elapsed_time": "5:21:27", "remaining_time": "2:58:02", "throughput": 4415.34, "total_tokens": 85161392} {"current_steps": 39455, "total_steps": 61300, "loss": 0.3509, "lr": 1.6974630040247425e-05, "epoch": 6.436378466557912, "percentage": 64.36, "elapsed_time": "5:21:29", "remaining_time": "2:58:00", "throughput": 4415.39, "total_tokens": 85172656} {"current_steps": 39460, "total_steps": 61300, "loss": 0.3338, "lr": 1.6967889108419903e-05, "epoch": 6.437194127243067, "percentage": 64.37, "elapsed_time": "5:21:32", "remaining_time": "2:57:57", "throughput": 4415.45, "total_tokens": 85184784} {"current_steps": 39465, "total_steps": 61300, "loss": 0.3248, "lr": 1.696114882771605e-05, "epoch": 6.438009787928221, "percentage": 64.38, "elapsed_time": "5:21:34", "remaining_time": "2:57:55", "throughput": 4415.5, "total_tokens": 85195248} {"current_steps": 39470, "total_steps": 61300, "loss": 0.3315, "lr": 1.695440919868226e-05, "epoch": 6.438825448613377, "percentage": 64.39, "elapsed_time": "5:21:36", "remaining_time": "2:57:52", "throughput": 4415.54, "total_tokens": 85205040} {"current_steps": 39475, "total_steps": 61300, "loss": 0.3459, "lr": 1.694767022186488e-05, "epoch": 6.439641109298532, "percentage": 64.4, "elapsed_time": "5:21:38", "remaining_time": "2:57:49", "throughput": 4415.58, "total_tokens": 85215344} {"current_steps": 39480, "total_steps": 61300, "loss": 0.3264, "lr": 1.6940931897810208e-05, "epoch": 6.440456769983687, "percentage": 64.4, "elapsed_time": "5:21:41", "remaining_time": "2:57:47", "throughput": 4415.63, "total_tokens": 85226352} {"current_steps": 39485, "total_steps": 61300, "loss": 0.3443, "lr": 1.693419422706449e-05, "epoch": 6.441272430668842, "percentage": 64.41, "elapsed_time": "5:21:42", "remaining_time": "2:57:44", "throughput": 4415.66, "total_tokens": 85235408} {"current_steps": 39490, "total_steps": 61300, "loss": 0.3508, "lr": 1.6927457210173915e-05, "epoch": 6.442088091353996, "percentage": 64.42, "elapsed_time": "5:21:45", "remaining_time": "2:57:42", "throughput": 4415.72, "total_tokens": 85246352} {"current_steps": 39495, "total_steps": 61300, "loss": 0.3363, "lr": 1.6920720847684617e-05, "epoch": 6.442903752039152, "percentage": 64.43, "elapsed_time": "5:21:47", "remaining_time": "2:57:39", "throughput": 4415.76, "total_tokens": 85256368} {"current_steps": 39500, "total_steps": 61300, "loss": 0.3541, "lr": 1.6913985140142682e-05, "epoch": 6.443719412724307, "percentage": 64.44, "elapsed_time": "5:21:49", "remaining_time": "2:57:36", "throughput": 4415.81, "total_tokens": 85267856} {"current_steps": 39505, "total_steps": 61300, "loss": 0.3374, "lr": 1.690725008809414e-05, "epoch": 6.444535073409462, "percentage": 64.45, "elapsed_time": "5:21:52", "remaining_time": "2:57:34", "throughput": 4415.86, "total_tokens": 85280112} {"current_steps": 39510, "total_steps": 61300, "loss": 0.3543, "lr": 1.6900515692084966e-05, "epoch": 6.445350734094617, "percentage": 64.45, "elapsed_time": "5:21:54", "remaining_time": "2:57:31", "throughput": 4415.89, "total_tokens": 85288688} {"current_steps": 39515, "total_steps": 61300, "loss": 0.3484, "lr": 1.689378195266109e-05, "epoch": 6.446166394779771, "percentage": 64.46, "elapsed_time": "5:21:56", "remaining_time": "2:57:29", "throughput": 4415.94, "total_tokens": 85299888} {"current_steps": 39520, "total_steps": 61300, "loss": 0.3321, "lr": 1.6887048870368377e-05, "epoch": 6.446982055464926, "percentage": 64.47, "elapsed_time": "5:21:58", "remaining_time": "2:57:26", "throughput": 4415.99, "total_tokens": 85310128} {"current_steps": 39525, "total_steps": 61300, "loss": 0.3176, "lr": 1.688031644575265e-05, "epoch": 6.447797716150082, "percentage": 64.48, "elapsed_time": "5:22:00", "remaining_time": "2:57:24", "throughput": 4416.04, "total_tokens": 85321072} {"current_steps": 39530, "total_steps": 61300, "loss": 0.3377, "lr": 1.6873584679359665e-05, "epoch": 6.448613376835237, "percentage": 64.49, "elapsed_time": "5:22:03", "remaining_time": "2:57:21", "throughput": 4416.09, "total_tokens": 85333008} {"current_steps": 39535, "total_steps": 61300, "loss": 0.3662, "lr": 1.686685357173514e-05, "epoch": 6.4494290375203915, "percentage": 64.49, "elapsed_time": "5:22:05", "remaining_time": "2:57:19", "throughput": 4416.15, "total_tokens": 85344048} {"current_steps": 39540, "total_steps": 61300, "loss": 0.3449, "lr": 1.6860123123424733e-05, "epoch": 6.450244698205546, "percentage": 64.5, "elapsed_time": "5:22:07", "remaining_time": "2:57:16", "throughput": 4416.19, "total_tokens": 85353136} {"current_steps": 39545, "total_steps": 61300, "loss": 0.3436, "lr": 1.6853393334974044e-05, "epoch": 6.451060358890701, "percentage": 64.51, "elapsed_time": "5:22:09", "remaining_time": "2:57:13", "throughput": 4416.23, "total_tokens": 85364016} {"current_steps": 39550, "total_steps": 61300, "loss": 0.3471, "lr": 1.684666420692863e-05, "epoch": 6.451876019575856, "percentage": 64.52, "elapsed_time": "5:22:11", "remaining_time": "2:57:11", "throughput": 4416.28, "total_tokens": 85374928} {"current_steps": 39555, "total_steps": 61300, "loss": 0.3566, "lr": 1.6839935739833986e-05, "epoch": 6.452691680261012, "percentage": 64.53, "elapsed_time": "5:22:13", "remaining_time": "2:57:08", "throughput": 4416.31, "total_tokens": 85383888} {"current_steps": 39560, "total_steps": 61300, "loss": 0.3501, "lr": 1.683320793423555e-05, "epoch": 6.4535073409461665, "percentage": 64.54, "elapsed_time": "5:22:16", "remaining_time": "2:57:06", "throughput": 4416.35, "total_tokens": 85394736} {"current_steps": 39565, "total_steps": 61300, "loss": 0.3359, "lr": 1.6826480790678718e-05, "epoch": 6.454323001631321, "percentage": 64.54, "elapsed_time": "5:22:18", "remaining_time": "2:57:03", "throughput": 4416.4, "total_tokens": 85405232} {"current_steps": 39570, "total_steps": 61300, "loss": 0.3423, "lr": 1.681975430970883e-05, "epoch": 6.455138662316476, "percentage": 64.55, "elapsed_time": "5:22:20", "remaining_time": "2:57:00", "throughput": 4416.44, "total_tokens": 85416176} {"current_steps": 39575, "total_steps": 61300, "loss": 0.3311, "lr": 1.681302849187116e-05, "epoch": 6.455954323001631, "percentage": 64.56, "elapsed_time": "5:22:22", "remaining_time": "2:56:58", "throughput": 4416.49, "total_tokens": 85426800} {"current_steps": 39580, "total_steps": 61300, "loss": 0.3465, "lr": 1.6806303337710942e-05, "epoch": 6.456769983686787, "percentage": 64.57, "elapsed_time": "5:22:24", "remaining_time": "2:56:55", "throughput": 4416.54, "total_tokens": 85437520} {"current_steps": 39585, "total_steps": 61300, "loss": 0.3491, "lr": 1.679957884777335e-05, "epoch": 6.4575856443719415, "percentage": 64.58, "elapsed_time": "5:22:27", "remaining_time": "2:56:53", "throughput": 4416.58, "total_tokens": 85447888} {"current_steps": 39590, "total_steps": 61300, "loss": 0.3379, "lr": 1.6792855022603508e-05, "epoch": 6.458401305057096, "percentage": 64.58, "elapsed_time": "5:22:29", "remaining_time": "2:56:50", "throughput": 4416.63, "total_tokens": 85459344} {"current_steps": 39595, "total_steps": 61300, "loss": 0.3415, "lr": 1.678613186274648e-05, "epoch": 6.459216965742251, "percentage": 64.59, "elapsed_time": "5:22:31", "remaining_time": "2:56:48", "throughput": 4416.67, "total_tokens": 85469744} {"current_steps": 39600, "total_steps": 61300, "loss": 0.3523, "lr": 1.6779409368747274e-05, "epoch": 6.460032626427406, "percentage": 64.6, "elapsed_time": "5:22:34", "remaining_time": "2:56:45", "throughput": 4416.72, "total_tokens": 85481168} {"current_steps": 39605, "total_steps": 61300, "loss": 0.3218, "lr": 1.677268754115086e-05, "epoch": 6.460848287112561, "percentage": 64.61, "elapsed_time": "5:22:36", "remaining_time": "2:56:43", "throughput": 4416.78, "total_tokens": 85492976} {"current_steps": 39610, "total_steps": 61300, "loss": 0.3457, "lr": 1.676596638050214e-05, "epoch": 6.4616639477977165, "percentage": 64.62, "elapsed_time": "5:22:38", "remaining_time": "2:56:40", "throughput": 4416.82, "total_tokens": 85502896} {"current_steps": 39615, "total_steps": 61300, "loss": 0.3376, "lr": 1.6759245887345966e-05, "epoch": 6.462479608482871, "percentage": 64.62, "elapsed_time": "5:22:40", "remaining_time": "2:56:37", "throughput": 4416.87, "total_tokens": 85513680} {"current_steps": 39620, "total_steps": 61300, "loss": 0.3438, "lr": 1.6752526062227127e-05, "epoch": 6.463295269168026, "percentage": 64.63, "elapsed_time": "5:22:42", "remaining_time": "2:56:35", "throughput": 4416.93, "total_tokens": 85524784} {"current_steps": 39625, "total_steps": 61300, "loss": 0.3341, "lr": 1.674580690569037e-05, "epoch": 6.464110929853181, "percentage": 64.64, "elapsed_time": "5:22:45", "remaining_time": "2:56:32", "throughput": 4416.98, "total_tokens": 85536208} {"current_steps": 39630, "total_steps": 61300, "loss": 0.3394, "lr": 1.6739088418280395e-05, "epoch": 6.464926590538336, "percentage": 64.65, "elapsed_time": "5:22:47", "remaining_time": "2:56:30", "throughput": 4417.02, "total_tokens": 85545936} {"current_steps": 39635, "total_steps": 61300, "loss": 0.3316, "lr": 1.6732370600541823e-05, "epoch": 6.465742251223491, "percentage": 64.66, "elapsed_time": "5:22:49", "remaining_time": "2:56:27", "throughput": 4417.06, "total_tokens": 85556080} {"current_steps": 39640, "total_steps": 61300, "loss": 0.3293, "lr": 1.6725653453019244e-05, "epoch": 6.466557911908646, "percentage": 64.67, "elapsed_time": "5:22:51", "remaining_time": "2:56:24", "throughput": 4417.11, "total_tokens": 85565840} {"current_steps": 39645, "total_steps": 61300, "loss": 0.3392, "lr": 1.6718936976257177e-05, "epoch": 6.467373572593801, "percentage": 64.67, "elapsed_time": "5:22:53", "remaining_time": "2:56:22", "throughput": 4417.15, "total_tokens": 85576912} {"current_steps": 39650, "total_steps": 61300, "loss": 0.3739, "lr": 1.6712221170800087e-05, "epoch": 6.468189233278956, "percentage": 64.68, "elapsed_time": "5:22:55", "remaining_time": "2:56:19", "throughput": 4417.21, "total_tokens": 85587760} {"current_steps": 39655, "total_steps": 61300, "loss": 0.3381, "lr": 1.670550603719241e-05, "epoch": 6.469004893964111, "percentage": 64.69, "elapsed_time": "5:22:58", "remaining_time": "2:56:17", "throughput": 4417.25, "total_tokens": 85597552} {"current_steps": 39660, "total_steps": 61300, "loss": 0.3588, "lr": 1.66987915759785e-05, "epoch": 6.4698205546492655, "percentage": 64.7, "elapsed_time": "5:23:00", "remaining_time": "2:56:14", "throughput": 4417.3, "total_tokens": 85608368} {"current_steps": 39665, "total_steps": 61300, "loss": 0.3044, "lr": 1.6692077787702666e-05, "epoch": 6.470636215334421, "percentage": 64.71, "elapsed_time": "5:23:02", "remaining_time": "2:56:11", "throughput": 4417.34, "total_tokens": 85618096} {"current_steps": 39670, "total_steps": 61300, "loss": 0.3346, "lr": 1.6685364672909163e-05, "epoch": 6.471451876019576, "percentage": 64.71, "elapsed_time": "5:23:04", "remaining_time": "2:56:09", "throughput": 4417.39, "total_tokens": 85628656} {"current_steps": 39675, "total_steps": 61300, "loss": 0.3697, "lr": 1.6678652232142185e-05, "epoch": 6.472267536704731, "percentage": 64.72, "elapsed_time": "5:23:06", "remaining_time": "2:56:06", "throughput": 4417.45, "total_tokens": 85639632} {"current_steps": 39680, "total_steps": 61300, "loss": 0.3199, "lr": 1.667194046594588e-05, "epoch": 6.473083197389886, "percentage": 64.73, "elapsed_time": "5:23:09", "remaining_time": "2:56:04", "throughput": 4417.49, "total_tokens": 85650832} {"current_steps": 39685, "total_steps": 61300, "loss": 0.3332, "lr": 1.666522937486433e-05, "epoch": 6.4738988580750405, "percentage": 64.74, "elapsed_time": "5:23:11", "remaining_time": "2:56:01", "throughput": 4417.53, "total_tokens": 85661296} {"current_steps": 39690, "total_steps": 61300, "loss": 0.3231, "lr": 1.6658518959441584e-05, "epoch": 6.474714518760196, "percentage": 64.75, "elapsed_time": "5:23:13", "remaining_time": "2:55:59", "throughput": 4417.57, "total_tokens": 85672368} {"current_steps": 39695, "total_steps": 61300, "loss": 0.3539, "lr": 1.6651809220221614e-05, "epoch": 6.475530179445351, "percentage": 64.76, "elapsed_time": "5:23:15", "remaining_time": "2:55:56", "throughput": 4417.62, "total_tokens": 85682160} {"current_steps": 39700, "total_steps": 61300, "loss": 0.346, "lr": 1.664510015774835e-05, "epoch": 6.476345840130506, "percentage": 64.76, "elapsed_time": "5:23:17", "remaining_time": "2:55:53", "throughput": 4417.67, "total_tokens": 85692656} {"current_steps": 39705, "total_steps": 61300, "loss": 0.3006, "lr": 1.6638391772565658e-05, "epoch": 6.477161500815661, "percentage": 64.77, "elapsed_time": "5:23:19", "remaining_time": "2:55:51", "throughput": 4417.72, "total_tokens": 85703600} {"current_steps": 39710, "total_steps": 61300, "loss": 0.3158, "lr": 1.6631684065217344e-05, "epoch": 6.4779771615008155, "percentage": 64.78, "elapsed_time": "5:23:22", "remaining_time": "2:55:48", "throughput": 4417.76, "total_tokens": 85714512} {"current_steps": 39715, "total_steps": 61300, "loss": 0.3997, "lr": 1.662497703624719e-05, "epoch": 6.47879282218597, "percentage": 64.79, "elapsed_time": "5:23:24", "remaining_time": "2:55:46", "throughput": 4417.81, "total_tokens": 85723888} {"current_steps": 39720, "total_steps": 61300, "loss": 0.3547, "lr": 1.6618270686198895e-05, "epoch": 6.479608482871126, "percentage": 64.8, "elapsed_time": "5:23:26", "remaining_time": "2:55:43", "throughput": 4417.86, "total_tokens": 85734992} {"current_steps": 39725, "total_steps": 61300, "loss": 0.3069, "lr": 1.6611565015616106e-05, "epoch": 6.480424143556281, "percentage": 64.8, "elapsed_time": "5:23:28", "remaining_time": "2:55:41", "throughput": 4417.91, "total_tokens": 85746768} {"current_steps": 39730, "total_steps": 61300, "loss": 0.3186, "lr": 1.6604860025042412e-05, "epoch": 6.481239804241436, "percentage": 64.81, "elapsed_time": "5:23:31", "remaining_time": "2:55:38", "throughput": 4417.96, "total_tokens": 85758352} {"current_steps": 39735, "total_steps": 61300, "loss": 0.3296, "lr": 1.6598155715021368e-05, "epoch": 6.4820554649265905, "percentage": 64.82, "elapsed_time": "5:23:33", "remaining_time": "2:55:36", "throughput": 4418.01, "total_tokens": 85769424} {"current_steps": 39740, "total_steps": 61300, "loss": 0.3516, "lr": 1.6591452086096448e-05, "epoch": 6.482871125611745, "percentage": 64.83, "elapsed_time": "5:23:35", "remaining_time": "2:55:33", "throughput": 4418.06, "total_tokens": 85780816} {"current_steps": 39745, "total_steps": 61300, "loss": 0.3295, "lr": 1.658474913881109e-05, "epoch": 6.4836867862969, "percentage": 64.84, "elapsed_time": "5:23:38", "remaining_time": "2:55:31", "throughput": 4418.11, "total_tokens": 85792528} {"current_steps": 39750, "total_steps": 61300, "loss": 0.3292, "lr": 1.6578046873708663e-05, "epoch": 6.484502446982056, "percentage": 64.85, "elapsed_time": "5:23:40", "remaining_time": "2:55:28", "throughput": 4418.17, "total_tokens": 85802448} {"current_steps": 39755, "total_steps": 61300, "loss": 0.3236, "lr": 1.657134529133248e-05, "epoch": 6.485318107667211, "percentage": 64.85, "elapsed_time": "5:23:42", "remaining_time": "2:55:25", "throughput": 4418.2, "total_tokens": 85813104} {"current_steps": 39760, "total_steps": 61300, "loss": 0.3468, "lr": 1.6564644392225824e-05, "epoch": 6.486133768352365, "percentage": 64.86, "elapsed_time": "5:23:44", "remaining_time": "2:55:23", "throughput": 4418.25, "total_tokens": 85823248} {"current_steps": 39765, "total_steps": 61300, "loss": 0.3303, "lr": 1.6557944176931894e-05, "epoch": 6.48694942903752, "percentage": 64.87, "elapsed_time": "5:23:46", "remaining_time": "2:55:20", "throughput": 4418.31, "total_tokens": 85834384} {"current_steps": 39770, "total_steps": 61300, "loss": 0.3607, "lr": 1.6551244645993847e-05, "epoch": 6.487765089722675, "percentage": 64.88, "elapsed_time": "5:23:49", "remaining_time": "2:55:18", "throughput": 4418.36, "total_tokens": 85844848} {"current_steps": 39775, "total_steps": 61300, "loss": 0.3839, "lr": 1.654454579995477e-05, "epoch": 6.488580750407831, "percentage": 64.89, "elapsed_time": "5:23:51", "remaining_time": "2:55:15", "throughput": 4418.4, "total_tokens": 85856528} {"current_steps": 39780, "total_steps": 61300, "loss": 0.3626, "lr": 1.653784763935772e-05, "epoch": 6.489396411092986, "percentage": 64.89, "elapsed_time": "5:23:53", "remaining_time": "2:55:13", "throughput": 4418.46, "total_tokens": 85868112} {"current_steps": 39785, "total_steps": 61300, "loss": 0.3352, "lr": 1.6531150164745674e-05, "epoch": 6.49021207177814, "percentage": 64.9, "elapsed_time": "5:23:56", "remaining_time": "2:55:10", "throughput": 4418.51, "total_tokens": 85878256} {"current_steps": 39790, "total_steps": 61300, "loss": 0.3391, "lr": 1.6524453376661568e-05, "epoch": 6.491027732463295, "percentage": 64.91, "elapsed_time": "5:23:57", "remaining_time": "2:55:07", "throughput": 4418.53, "total_tokens": 85887440} {"current_steps": 39795, "total_steps": 61300, "loss": 0.3196, "lr": 1.6517757275648267e-05, "epoch": 6.49184339314845, "percentage": 64.92, "elapsed_time": "5:24:00", "remaining_time": "2:55:05", "throughput": 4418.57, "total_tokens": 85897872} {"current_steps": 39800, "total_steps": 61300, "loss": 0.3284, "lr": 1.6511061862248605e-05, "epoch": 6.492659053833605, "percentage": 64.93, "elapsed_time": "5:24:02", "remaining_time": "2:55:02", "throughput": 4418.62, "total_tokens": 85909776} {"current_steps": 39805, "total_steps": 61300, "loss": 0.3379, "lr": 1.6504367137005344e-05, "epoch": 6.493474714518761, "percentage": 64.93, "elapsed_time": "5:24:04", "remaining_time": "2:55:00", "throughput": 4418.66, "total_tokens": 85919984} {"current_steps": 39810, "total_steps": 61300, "loss": 0.3448, "lr": 1.649767310046119e-05, "epoch": 6.494290375203915, "percentage": 64.94, "elapsed_time": "5:24:07", "remaining_time": "2:54:57", "throughput": 4418.71, "total_tokens": 85931632} {"current_steps": 39815, "total_steps": 61300, "loss": 0.3355, "lr": 1.649097975315879e-05, "epoch": 6.49510603588907, "percentage": 64.95, "elapsed_time": "5:24:09", "remaining_time": "2:54:55", "throughput": 4418.76, "total_tokens": 85944176} {"current_steps": 39820, "total_steps": 61300, "loss": 0.3466, "lr": 1.648428709564075e-05, "epoch": 6.495921696574225, "percentage": 64.96, "elapsed_time": "5:24:12", "remaining_time": "2:54:53", "throughput": 4418.82, "total_tokens": 85956016} {"current_steps": 39825, "total_steps": 61300, "loss": 0.3335, "lr": 1.6477595128449605e-05, "epoch": 6.49673735725938, "percentage": 64.97, "elapsed_time": "5:24:14", "remaining_time": "2:54:50", "throughput": 4418.87, "total_tokens": 85966704} {"current_steps": 39830, "total_steps": 61300, "loss": 0.3695, "lr": 1.647090385212784e-05, "epoch": 6.497553017944535, "percentage": 64.98, "elapsed_time": "5:24:16", "remaining_time": "2:54:47", "throughput": 4418.9, "total_tokens": 85976048} {"current_steps": 39835, "total_steps": 61300, "loss": 0.3438, "lr": 1.6464213267217888e-05, "epoch": 6.49836867862969, "percentage": 64.98, "elapsed_time": "5:24:18", "remaining_time": "2:54:45", "throughput": 4418.94, "total_tokens": 85985424} {"current_steps": 39840, "total_steps": 61300, "loss": 0.341, "lr": 1.6457523374262117e-05, "epoch": 6.499184339314845, "percentage": 64.99, "elapsed_time": "5:24:20", "remaining_time": "2:54:42", "throughput": 4418.98, "total_tokens": 85996976} {"current_steps": 39845, "total_steps": 61300, "loss": 0.3433, "lr": 1.645083417380284e-05, "epoch": 6.5, "percentage": 65.0, "elapsed_time": "5:24:23", "remaining_time": "2:54:40", "throughput": 4419.04, "total_tokens": 86008784} {"current_steps": 39845, "total_steps": 61300, "eval_loss": 0.3397892117500305, "epoch": 6.5, "percentage": 65.0, "elapsed_time": "5:26:35", "remaining_time": "2:55:51", "throughput": 4389.31, "total_tokens": 86008784} {"current_steps": 39850, "total_steps": 61300, "loss": 0.3312, "lr": 1.644414566638233e-05, "epoch": 6.500815660685155, "percentage": 65.01, "elapsed_time": "5:26:38", "remaining_time": "2:55:49", "throughput": 4389.08, "total_tokens": 86019568} {"current_steps": 39855, "total_steps": 61300, "loss": 0.3236, "lr": 1.643745785254278e-05, "epoch": 6.50163132137031, "percentage": 65.02, "elapsed_time": "5:26:40", "remaining_time": "2:55:46", "throughput": 4389.13, "total_tokens": 86030448} {"current_steps": 39860, "total_steps": 61300, "loss": 0.3292, "lr": 1.6430770732826346e-05, "epoch": 6.502446982055465, "percentage": 65.02, "elapsed_time": "5:26:42", "remaining_time": "2:55:44", "throughput": 4389.18, "total_tokens": 86041040} {"current_steps": 39865, "total_steps": 61300, "loss": 0.3428, "lr": 1.6424084307775107e-05, "epoch": 6.50326264274062, "percentage": 65.03, "elapsed_time": "5:26:45", "remaining_time": "2:55:41", "throughput": 4389.24, "total_tokens": 86052624} {"current_steps": 39870, "total_steps": 61300, "loss": 0.3651, "lr": 1.6417398577931116e-05, "epoch": 6.504078303425775, "percentage": 65.04, "elapsed_time": "5:26:47", "remaining_time": "2:55:39", "throughput": 4389.27, "total_tokens": 86063472} {"current_steps": 39875, "total_steps": 61300, "loss": 0.3366, "lr": 1.6410713543836342e-05, "epoch": 6.50489396411093, "percentage": 65.05, "elapsed_time": "5:26:49", "remaining_time": "2:55:36", "throughput": 4389.32, "total_tokens": 86074320} {"current_steps": 39880, "total_steps": 61300, "loss": 0.3518, "lr": 1.6404029206032708e-05, "epoch": 6.505709624796085, "percentage": 65.06, "elapsed_time": "5:26:52", "remaining_time": "2:55:34", "throughput": 4389.36, "total_tokens": 86086320} {"current_steps": 39885, "total_steps": 61300, "loss": 0.318, "lr": 1.6397345565062082e-05, "epoch": 6.506525285481239, "percentage": 65.07, "elapsed_time": "5:26:54", "remaining_time": "2:55:31", "throughput": 4389.42, "total_tokens": 86098000} {"current_steps": 39890, "total_steps": 61300, "loss": 0.3352, "lr": 1.639066262146628e-05, "epoch": 6.507340946166395, "percentage": 65.07, "elapsed_time": "5:26:56", "remaining_time": "2:55:28", "throughput": 4389.47, "total_tokens": 86107088} {"current_steps": 39895, "total_steps": 61300, "loss": 0.3258, "lr": 1.6383980375787044e-05, "epoch": 6.50815660685155, "percentage": 65.08, "elapsed_time": "5:26:59", "remaining_time": "2:55:26", "throughput": 4389.52, "total_tokens": 86118096} {"current_steps": 39900, "total_steps": 61300, "loss": 0.3068, "lr": 1.637729882856608e-05, "epoch": 6.508972267536705, "percentage": 65.09, "elapsed_time": "5:27:01", "remaining_time": "2:55:23", "throughput": 4389.56, "total_tokens": 86129136} {"current_steps": 39905, "total_steps": 61300, "loss": 0.3195, "lr": 1.6370617980345022e-05, "epoch": 6.50978792822186, "percentage": 65.1, "elapsed_time": "5:27:03", "remaining_time": "2:55:21", "throughput": 4389.61, "total_tokens": 86140816} {"current_steps": 39910, "total_steps": 61300, "loss": 0.3472, "lr": 1.6363937831665458e-05, "epoch": 6.510603588907014, "percentage": 65.11, "elapsed_time": "5:27:06", "remaining_time": "2:55:18", "throughput": 4389.66, "total_tokens": 86151664} {"current_steps": 39915, "total_steps": 61300, "loss": 0.3231, "lr": 1.635725838306891e-05, "epoch": 6.511419249592169, "percentage": 65.11, "elapsed_time": "5:27:08", "remaining_time": "2:55:16", "throughput": 4389.7, "total_tokens": 86161744} {"current_steps": 39920, "total_steps": 61300, "loss": 0.3262, "lr": 1.6350579635096852e-05, "epoch": 6.512234910277325, "percentage": 65.12, "elapsed_time": "5:27:10", "remaining_time": "2:55:13", "throughput": 4389.75, "total_tokens": 86171312} {"current_steps": 39925, "total_steps": 61300, "loss": 0.2853, "lr": 1.6343901588290695e-05, "epoch": 6.51305057096248, "percentage": 65.13, "elapsed_time": "5:27:12", "remaining_time": "2:55:10", "throughput": 4389.79, "total_tokens": 86181392} {"current_steps": 39930, "total_steps": 61300, "loss": 0.3405, "lr": 1.633722424319179e-05, "epoch": 6.513866231647635, "percentage": 65.14, "elapsed_time": "5:27:14", "remaining_time": "2:55:08", "throughput": 4389.83, "total_tokens": 86191728} {"current_steps": 39935, "total_steps": 61300, "loss": 0.3489, "lr": 1.633054760034145e-05, "epoch": 6.514681892332789, "percentage": 65.15, "elapsed_time": "5:27:16", "remaining_time": "2:55:05", "throughput": 4389.88, "total_tokens": 86201712} {"current_steps": 39940, "total_steps": 61300, "loss": 0.3556, "lr": 1.6323871660280904e-05, "epoch": 6.515497553017944, "percentage": 65.15, "elapsed_time": "5:27:18", "remaining_time": "2:55:02", "throughput": 4389.93, "total_tokens": 86212464} {"current_steps": 39945, "total_steps": 61300, "loss": 0.3323, "lr": 1.6317196423551347e-05, "epoch": 6.5163132137031, "percentage": 65.16, "elapsed_time": "5:27:21", "remaining_time": "2:55:00", "throughput": 4389.99, "total_tokens": 86224208} {"current_steps": 39950, "total_steps": 61300, "loss": 0.3211, "lr": 1.6310521890693904e-05, "epoch": 6.517128874388255, "percentage": 65.17, "elapsed_time": "5:27:23", "remaining_time": "2:54:57", "throughput": 4390.03, "total_tokens": 86234544} {"current_steps": 39955, "total_steps": 61300, "loss": 0.3465, "lr": 1.6303848062249643e-05, "epoch": 6.5179445350734095, "percentage": 65.18, "elapsed_time": "5:27:25", "remaining_time": "2:54:55", "throughput": 4390.09, "total_tokens": 86245776} {"current_steps": 39960, "total_steps": 61300, "loss": 0.359, "lr": 1.6297174938759584e-05, "epoch": 6.518760195758564, "percentage": 65.19, "elapsed_time": "5:27:27", "remaining_time": "2:54:52", "throughput": 4390.14, "total_tokens": 86256976} {"current_steps": 39965, "total_steps": 61300, "loss": 0.3129, "lr": 1.6290502520764687e-05, "epoch": 6.519575856443719, "percentage": 65.2, "elapsed_time": "5:27:30", "remaining_time": "2:54:50", "throughput": 4390.18, "total_tokens": 86267568} {"current_steps": 39970, "total_steps": 61300, "loss": 0.3152, "lr": 1.6283830808805832e-05, "epoch": 6.520391517128875, "percentage": 65.2, "elapsed_time": "5:27:32", "remaining_time": "2:54:47", "throughput": 4390.25, "total_tokens": 86278768} {"current_steps": 39975, "total_steps": 61300, "loss": 0.3245, "lr": 1.6277159803423888e-05, "epoch": 6.52120717781403, "percentage": 65.21, "elapsed_time": "5:27:34", "remaining_time": "2:54:44", "throughput": 4390.29, "total_tokens": 86288080} {"current_steps": 39980, "total_steps": 61300, "loss": 0.2921, "lr": 1.627048950515963e-05, "epoch": 6.5220228384991845, "percentage": 65.22, "elapsed_time": "5:27:36", "remaining_time": "2:54:42", "throughput": 4390.34, "total_tokens": 86299120} {"current_steps": 39985, "total_steps": 61300, "loss": 0.3432, "lr": 1.6263819914553786e-05, "epoch": 6.522838499184339, "percentage": 65.23, "elapsed_time": "5:27:39", "remaining_time": "2:54:39", "throughput": 4390.39, "total_tokens": 86311056} {"current_steps": 39990, "total_steps": 61300, "loss": 0.3246, "lr": 1.6257151032147028e-05, "epoch": 6.523654159869494, "percentage": 65.24, "elapsed_time": "5:27:41", "remaining_time": "2:54:37", "throughput": 4390.43, "total_tokens": 86321904} {"current_steps": 39995, "total_steps": 61300, "loss": 0.3632, "lr": 1.6250482858479964e-05, "epoch": 6.524469820554649, "percentage": 65.24, "elapsed_time": "5:27:43", "remaining_time": "2:54:34", "throughput": 4390.47, "total_tokens": 86332880} {"current_steps": 40000, "total_steps": 61300, "loss": 0.3042, "lr": 1.624381539409316e-05, "epoch": 6.525285481239804, "percentage": 65.25, "elapsed_time": "5:27:46", "remaining_time": "2:54:32", "throughput": 4390.52, "total_tokens": 86344080} {"current_steps": 40005, "total_steps": 61300, "loss": 0.3323, "lr": 1.6237148639527106e-05, "epoch": 6.5261011419249595, "percentage": 65.26, "elapsed_time": "5:27:48", "remaining_time": "2:54:29", "throughput": 4390.58, "total_tokens": 86356240} {"current_steps": 40010, "total_steps": 61300, "loss": 0.3251, "lr": 1.6230482595322244e-05, "epoch": 6.526916802610114, "percentage": 65.27, "elapsed_time": "5:27:50", "remaining_time": "2:54:27", "throughput": 4390.64, "total_tokens": 86367824} {"current_steps": 40015, "total_steps": 61300, "loss": 0.3528, "lr": 1.6223817262018958e-05, "epoch": 6.527732463295269, "percentage": 65.28, "elapsed_time": "5:27:53", "remaining_time": "2:54:24", "throughput": 4390.7, "total_tokens": 86379632} {"current_steps": 40020, "total_steps": 61300, "loss": 0.3197, "lr": 1.6217152640157577e-05, "epoch": 6.528548123980424, "percentage": 65.29, "elapsed_time": "5:27:55", "remaining_time": "2:54:22", "throughput": 4390.75, "total_tokens": 86391248} {"current_steps": 40025, "total_steps": 61300, "loss": 0.3262, "lr": 1.621048873027836e-05, "epoch": 6.529363784665579, "percentage": 65.29, "elapsed_time": "5:27:57", "remaining_time": "2:54:19", "throughput": 4390.8, "total_tokens": 86401104} {"current_steps": 40030, "total_steps": 61300, "loss": 0.3127, "lr": 1.6203825532921533e-05, "epoch": 6.5301794453507345, "percentage": 65.3, "elapsed_time": "5:28:00", "remaining_time": "2:54:17", "throughput": 4390.85, "total_tokens": 86412528} {"current_steps": 40035, "total_steps": 61300, "loss": 0.3316, "lr": 1.6197163048627237e-05, "epoch": 6.530995106035889, "percentage": 65.31, "elapsed_time": "5:28:02", "remaining_time": "2:54:14", "throughput": 4390.89, "total_tokens": 86422800} {"current_steps": 40040, "total_steps": 61300, "loss": 0.369, "lr": 1.619050127793557e-05, "epoch": 6.531810766721044, "percentage": 65.32, "elapsed_time": "5:28:04", "remaining_time": "2:54:11", "throughput": 4390.95, "total_tokens": 86434448} {"current_steps": 40045, "total_steps": 61300, "loss": 0.3219, "lr": 1.6183840221386567e-05, "epoch": 6.532626427406199, "percentage": 65.33, "elapsed_time": "5:28:07", "remaining_time": "2:54:09", "throughput": 4391.01, "total_tokens": 86447312} {"current_steps": 40050, "total_steps": 61300, "loss": 0.3592, "lr": 1.617717987952021e-05, "epoch": 6.533442088091354, "percentage": 65.33, "elapsed_time": "5:28:09", "remaining_time": "2:54:07", "throughput": 4391.06, "total_tokens": 86458800} {"current_steps": 40055, "total_steps": 61300, "loss": 0.3089, "lr": 1.6170520252876416e-05, "epoch": 6.5342577487765094, "percentage": 65.34, "elapsed_time": "5:28:12", "remaining_time": "2:54:04", "throughput": 4391.11, "total_tokens": 86470928} {"current_steps": 40060, "total_steps": 61300, "loss": 0.3429, "lr": 1.616386134199505e-05, "epoch": 6.535073409461664, "percentage": 65.35, "elapsed_time": "5:28:14", "remaining_time": "2:54:02", "throughput": 4391.16, "total_tokens": 86481520} {"current_steps": 40065, "total_steps": 61300, "loss": 0.3506, "lr": 1.6157203147415923e-05, "epoch": 6.535889070146819, "percentage": 65.36, "elapsed_time": "5:28:16", "remaining_time": "2:53:59", "throughput": 4391.2, "total_tokens": 86492080} {"current_steps": 40070, "total_steps": 61300, "loss": 0.3117, "lr": 1.6150545669678773e-05, "epoch": 6.536704730831974, "percentage": 65.37, "elapsed_time": "5:28:18", "remaining_time": "2:53:56", "throughput": 4391.26, "total_tokens": 86503280} {"current_steps": 40075, "total_steps": 61300, "loss": 0.3491, "lr": 1.6143888909323286e-05, "epoch": 6.537520391517129, "percentage": 65.38, "elapsed_time": "5:28:21", "remaining_time": "2:53:54", "throughput": 4391.3, "total_tokens": 86513808} {"current_steps": 40080, "total_steps": 61300, "loss": 0.3445, "lr": 1.6137232866889107e-05, "epoch": 6.5383360522022835, "percentage": 65.38, "elapsed_time": "5:28:23", "remaining_time": "2:53:51", "throughput": 4391.35, "total_tokens": 86524944} {"current_steps": 40085, "total_steps": 61300, "loss": 0.3685, "lr": 1.6130577542915798e-05, "epoch": 6.539151712887438, "percentage": 65.39, "elapsed_time": "5:28:25", "remaining_time": "2:53:49", "throughput": 4391.4, "total_tokens": 86535824} {"current_steps": 40090, "total_steps": 61300, "loss": 0.3429, "lr": 1.6123922937942883e-05, "epoch": 6.539967373572594, "percentage": 65.4, "elapsed_time": "5:28:28", "remaining_time": "2:53:46", "throughput": 4391.45, "total_tokens": 86546992} {"current_steps": 40095, "total_steps": 61300, "loss": 0.3347, "lr": 1.6117269052509803e-05, "epoch": 6.540783034257749, "percentage": 65.41, "elapsed_time": "5:28:30", "remaining_time": "2:53:44", "throughput": 4391.51, "total_tokens": 86558352} {"current_steps": 40100, "total_steps": 61300, "loss": 0.3488, "lr": 1.6110615887155972e-05, "epoch": 6.541598694942904, "percentage": 65.42, "elapsed_time": "5:28:32", "remaining_time": "2:53:41", "throughput": 4391.55, "total_tokens": 86569424} {"current_steps": 40105, "total_steps": 61300, "loss": 0.338, "lr": 1.6103963442420717e-05, "epoch": 6.5424143556280585, "percentage": 65.42, "elapsed_time": "5:28:34", "remaining_time": "2:53:38", "throughput": 4391.6, "total_tokens": 86579024} {"current_steps": 40110, "total_steps": 61300, "loss": 0.3199, "lr": 1.6097311718843322e-05, "epoch": 6.543230016313213, "percentage": 65.43, "elapsed_time": "5:28:37", "remaining_time": "2:53:36", "throughput": 4391.65, "total_tokens": 86590832} {"current_steps": 40115, "total_steps": 61300, "loss": 0.3361, "lr": 1.6090660716963014e-05, "epoch": 6.544045676998369, "percentage": 65.44, "elapsed_time": "5:28:39", "remaining_time": "2:53:34", "throughput": 4391.7, "total_tokens": 86602736} {"current_steps": 40120, "total_steps": 61300, "loss": 0.3483, "lr": 1.608401043731895e-05, "epoch": 6.544861337683524, "percentage": 65.45, "elapsed_time": "5:28:41", "remaining_time": "2:53:31", "throughput": 4391.75, "total_tokens": 86613712} {"current_steps": 40125, "total_steps": 61300, "loss": 0.3547, "lr": 1.6077360880450244e-05, "epoch": 6.545676998368679, "percentage": 65.46, "elapsed_time": "5:28:44", "remaining_time": "2:53:28", "throughput": 4391.79, "total_tokens": 86624112} {"current_steps": 40130, "total_steps": 61300, "loss": 0.3424, "lr": 1.6070712046895936e-05, "epoch": 6.5464926590538335, "percentage": 65.46, "elapsed_time": "5:28:46", "remaining_time": "2:53:26", "throughput": 4391.83, "total_tokens": 86634000} {"current_steps": 40135, "total_steps": 61300, "loss": 0.3365, "lr": 1.6064063937195017e-05, "epoch": 6.547308319738988, "percentage": 65.47, "elapsed_time": "5:28:48", "remaining_time": "2:53:23", "throughput": 4391.89, "total_tokens": 86644816} {"current_steps": 40140, "total_steps": 61300, "loss": 0.3358, "lr": 1.6057416551886418e-05, "epoch": 6.548123980424144, "percentage": 65.48, "elapsed_time": "5:28:50", "remaining_time": "2:53:21", "throughput": 4391.94, "total_tokens": 86656496} {"current_steps": 40145, "total_steps": 61300, "loss": 0.3534, "lr": 1.6050769891509005e-05, "epoch": 6.548939641109299, "percentage": 65.49, "elapsed_time": "5:28:53", "remaining_time": "2:53:18", "throughput": 4392.0, "total_tokens": 86668400} {"current_steps": 40150, "total_steps": 61300, "loss": 0.3173, "lr": 1.6044123956601593e-05, "epoch": 6.549755301794454, "percentage": 65.5, "elapsed_time": "5:28:55", "remaining_time": "2:53:16", "throughput": 4392.05, "total_tokens": 86678832} {"current_steps": 40155, "total_steps": 61300, "loss": 0.3074, "lr": 1.6037478747702932e-05, "epoch": 6.5505709624796085, "percentage": 65.51, "elapsed_time": "5:28:57", "remaining_time": "2:53:13", "throughput": 4392.09, "total_tokens": 86689040} {"current_steps": 40160, "total_steps": 61300, "loss": 0.3758, "lr": 1.6030834265351724e-05, "epoch": 6.551386623164763, "percentage": 65.51, "elapsed_time": "5:28:59", "remaining_time": "2:53:10", "throughput": 4392.13, "total_tokens": 86699952} {"current_steps": 40165, "total_steps": 61300, "loss": 0.3447, "lr": 1.602419051008659e-05, "epoch": 6.552202283849918, "percentage": 65.52, "elapsed_time": "5:29:01", "remaining_time": "2:53:08", "throughput": 4392.18, "total_tokens": 86710320} {"current_steps": 40170, "total_steps": 61300, "loss": 0.3218, "lr": 1.6017547482446127e-05, "epoch": 6.553017944535073, "percentage": 65.53, "elapsed_time": "5:29:04", "remaining_time": "2:53:05", "throughput": 4392.23, "total_tokens": 86721648} {"current_steps": 40175, "total_steps": 61300, "loss": 0.3567, "lr": 1.6010905182968837e-05, "epoch": 6.553833605220229, "percentage": 65.54, "elapsed_time": "5:29:06", "remaining_time": "2:53:03", "throughput": 4392.27, "total_tokens": 86732560} {"current_steps": 40180, "total_steps": 61300, "loss": 0.3112, "lr": 1.6004263612193182e-05, "epoch": 6.554649265905383, "percentage": 65.55, "elapsed_time": "5:29:08", "remaining_time": "2:53:00", "throughput": 4392.32, "total_tokens": 86743408} {"current_steps": 40185, "total_steps": 61300, "loss": 0.3663, "lr": 1.599762277065756e-05, "epoch": 6.555464926590538, "percentage": 65.55, "elapsed_time": "5:29:11", "remaining_time": "2:52:58", "throughput": 4392.37, "total_tokens": 86754384} {"current_steps": 40190, "total_steps": 61300, "loss": 0.3473, "lr": 1.599098265890031e-05, "epoch": 6.556280587275693, "percentage": 65.56, "elapsed_time": "5:29:13", "remaining_time": "2:52:55", "throughput": 4392.42, "total_tokens": 86764592} {"current_steps": 40195, "total_steps": 61300, "loss": 0.3023, "lr": 1.598434327745973e-05, "epoch": 6.557096247960848, "percentage": 65.57, "elapsed_time": "5:29:15", "remaining_time": "2:52:52", "throughput": 4392.48, "total_tokens": 86776176} {"current_steps": 40200, "total_steps": 61300, "loss": 0.3598, "lr": 1.5977704626874023e-05, "epoch": 6.557911908646004, "percentage": 65.58, "elapsed_time": "5:29:17", "remaining_time": "2:52:50", "throughput": 4392.52, "total_tokens": 86786320} {"current_steps": 40205, "total_steps": 61300, "loss": 0.3384, "lr": 1.597106670768136e-05, "epoch": 6.558727569331158, "percentage": 65.59, "elapsed_time": "5:29:20", "remaining_time": "2:52:47", "throughput": 4392.57, "total_tokens": 86798288} {"current_steps": 40210, "total_steps": 61300, "loss": 0.3191, "lr": 1.5964429520419836e-05, "epoch": 6.559543230016313, "percentage": 65.6, "elapsed_time": "5:29:22", "remaining_time": "2:52:45", "throughput": 4392.63, "total_tokens": 86809456} {"current_steps": 40215, "total_steps": 61300, "loss": 0.3514, "lr": 1.595779306562751e-05, "epoch": 6.560358890701468, "percentage": 65.6, "elapsed_time": "5:29:24", "remaining_time": "2:52:42", "throughput": 4392.68, "total_tokens": 86819824} {"current_steps": 40220, "total_steps": 61300, "loss": 0.3411, "lr": 1.5951157343842352e-05, "epoch": 6.561174551386623, "percentage": 65.61, "elapsed_time": "5:29:26", "remaining_time": "2:52:40", "throughput": 4392.71, "total_tokens": 86829872} {"current_steps": 40225, "total_steps": 61300, "loss": 0.3487, "lr": 1.5944522355602297e-05, "epoch": 6.561990212071779, "percentage": 65.62, "elapsed_time": "5:29:28", "remaining_time": "2:52:37", "throughput": 4392.75, "total_tokens": 86839472} {"current_steps": 40230, "total_steps": 61300, "loss": 0.3309, "lr": 1.59378881014452e-05, "epoch": 6.562805872756933, "percentage": 65.63, "elapsed_time": "5:29:31", "remaining_time": "2:52:34", "throughput": 4392.81, "total_tokens": 86851184} {"current_steps": 40235, "total_steps": 61300, "loss": 0.3523, "lr": 1.5931254581908882e-05, "epoch": 6.563621533442088, "percentage": 65.64, "elapsed_time": "5:29:33", "remaining_time": "2:52:32", "throughput": 4392.86, "total_tokens": 86861136} {"current_steps": 40240, "total_steps": 61300, "loss": 0.3361, "lr": 1.592462179753108e-05, "epoch": 6.564437194127243, "percentage": 65.64, "elapsed_time": "5:29:35", "remaining_time": "2:52:29", "throughput": 4392.89, "total_tokens": 86871344} {"current_steps": 40245, "total_steps": 61300, "loss": 0.3307, "lr": 1.591798974884948e-05, "epoch": 6.565252854812398, "percentage": 65.65, "elapsed_time": "5:29:37", "remaining_time": "2:52:27", "throughput": 4392.94, "total_tokens": 86881488} {"current_steps": 40250, "total_steps": 61300, "loss": 0.3495, "lr": 1.5911358436401708e-05, "epoch": 6.566068515497553, "percentage": 65.66, "elapsed_time": "5:29:39", "remaining_time": "2:52:24", "throughput": 4393.0, "total_tokens": 86893264} {"current_steps": 40255, "total_steps": 61300, "loss": 0.3058, "lr": 1.5904727860725344e-05, "epoch": 6.566884176182708, "percentage": 65.67, "elapsed_time": "5:29:42", "remaining_time": "2:52:21", "throughput": 4393.05, "total_tokens": 86904208} {"current_steps": 40260, "total_steps": 61300, "loss": 0.3211, "lr": 1.589809802235789e-05, "epoch": 6.567699836867863, "percentage": 65.68, "elapsed_time": "5:29:44", "remaining_time": "2:52:19", "throughput": 4393.11, "total_tokens": 86916080} {"current_steps": 40265, "total_steps": 61300, "loss": 0.3056, "lr": 1.589146892183679e-05, "epoch": 6.568515497553018, "percentage": 65.69, "elapsed_time": "5:29:46", "remaining_time": "2:52:16", "throughput": 4393.16, "total_tokens": 86926640} {"current_steps": 40270, "total_steps": 61300, "loss": 0.3409, "lr": 1.5884840559699436e-05, "epoch": 6.569331158238173, "percentage": 65.69, "elapsed_time": "5:29:48", "remaining_time": "2:52:14", "throughput": 4393.2, "total_tokens": 86936688} {"current_steps": 40275, "total_steps": 61300, "loss": 0.3181, "lr": 1.5878212936483156e-05, "epoch": 6.570146818923328, "percentage": 65.7, "elapsed_time": "5:29:51", "remaining_time": "2:52:11", "throughput": 4393.25, "total_tokens": 86948272} {"current_steps": 40280, "total_steps": 61300, "loss": 0.3235, "lr": 1.5871586052725216e-05, "epoch": 6.5709624796084825, "percentage": 65.71, "elapsed_time": "5:29:53", "remaining_time": "2:52:09", "throughput": 4393.3, "total_tokens": 86959184} {"current_steps": 40285, "total_steps": 61300, "loss": 0.3453, "lr": 1.5864959908962832e-05, "epoch": 6.571778140293638, "percentage": 65.72, "elapsed_time": "5:29:55", "remaining_time": "2:52:06", "throughput": 4393.34, "total_tokens": 86970032} {"current_steps": 40290, "total_steps": 61300, "loss": 0.3369, "lr": 1.5858334505733137e-05, "epoch": 6.572593800978793, "percentage": 65.73, "elapsed_time": "5:29:57", "remaining_time": "2:52:04", "throughput": 4393.38, "total_tokens": 86980048} {"current_steps": 40295, "total_steps": 61300, "loss": 0.3106, "lr": 1.585170984357324e-05, "epoch": 6.573409461663948, "percentage": 65.73, "elapsed_time": "5:30:00", "remaining_time": "2:52:01", "throughput": 4393.44, "total_tokens": 86991888} {"current_steps": 40300, "total_steps": 61300, "loss": 0.3511, "lr": 1.5845085923020165e-05, "epoch": 6.574225122349103, "percentage": 65.74, "elapsed_time": "5:30:02", "remaining_time": "2:51:59", "throughput": 4393.48, "total_tokens": 87003056} {"current_steps": 40305, "total_steps": 61300, "loss": 0.329, "lr": 1.5838462744610872e-05, "epoch": 6.575040783034257, "percentage": 65.75, "elapsed_time": "5:30:05", "remaining_time": "2:51:56", "throughput": 4393.52, "total_tokens": 87014192} {"current_steps": 40310, "total_steps": 61300, "loss": 0.332, "lr": 1.5831840308882276e-05, "epoch": 6.575856443719413, "percentage": 65.76, "elapsed_time": "5:30:07", "remaining_time": "2:51:53", "throughput": 4393.57, "total_tokens": 87024112} {"current_steps": 40315, "total_steps": 61300, "loss": 0.3361, "lr": 1.5825218616371224e-05, "epoch": 6.576672104404568, "percentage": 65.77, "elapsed_time": "5:30:09", "remaining_time": "2:51:51", "throughput": 4393.63, "total_tokens": 87034896} {"current_steps": 40320, "total_steps": 61300, "loss": 0.3416, "lr": 1.5818597667614503e-05, "epoch": 6.577487765089723, "percentage": 65.77, "elapsed_time": "5:30:11", "remaining_time": "2:51:48", "throughput": 4393.67, "total_tokens": 87045392} {"current_steps": 40325, "total_steps": 61300, "loss": 0.3178, "lr": 1.581197746314884e-05, "epoch": 6.578303425774878, "percentage": 65.78, "elapsed_time": "5:30:13", "remaining_time": "2:51:46", "throughput": 4393.72, "total_tokens": 87056432} {"current_steps": 40330, "total_steps": 61300, "loss": 0.3646, "lr": 1.5805358003510902e-05, "epoch": 6.579119086460032, "percentage": 65.79, "elapsed_time": "5:30:16", "remaining_time": "2:51:43", "throughput": 4393.77, "total_tokens": 87067440} {"current_steps": 40335, "total_steps": 61300, "loss": 0.3036, "lr": 1.5798739289237298e-05, "epoch": 6.579934747145187, "percentage": 65.8, "elapsed_time": "5:30:18", "remaining_time": "2:51:41", "throughput": 4393.81, "total_tokens": 87078064} {"current_steps": 40340, "total_steps": 61300, "loss": 0.2947, "lr": 1.5792121320864573e-05, "epoch": 6.580750407830343, "percentage": 65.81, "elapsed_time": "5:30:20", "remaining_time": "2:51:38", "throughput": 4393.86, "total_tokens": 87087920} {"current_steps": 40345, "total_steps": 61300, "loss": 0.3168, "lr": 1.5785504098929217e-05, "epoch": 6.581566068515498, "percentage": 65.82, "elapsed_time": "5:30:22", "remaining_time": "2:51:35", "throughput": 4393.9, "total_tokens": 87098032} {"current_steps": 40350, "total_steps": 61300, "loss": 0.3402, "lr": 1.5778887623967654e-05, "epoch": 6.582381729200653, "percentage": 65.82, "elapsed_time": "5:30:24", "remaining_time": "2:51:33", "throughput": 4393.94, "total_tokens": 87108304} {"current_steps": 40355, "total_steps": 61300, "loss": 0.3077, "lr": 1.5772271896516245e-05, "epoch": 6.583197389885807, "percentage": 65.83, "elapsed_time": "5:30:26", "remaining_time": "2:51:30", "throughput": 4393.99, "total_tokens": 87119088} {"current_steps": 40360, "total_steps": 61300, "loss": 0.3257, "lr": 1.57656569171113e-05, "epoch": 6.584013050570962, "percentage": 65.84, "elapsed_time": "5:30:29", "remaining_time": "2:51:27", "throughput": 4394.03, "total_tokens": 87130032} {"current_steps": 40365, "total_steps": 61300, "loss": 0.318, "lr": 1.5759042686289056e-05, "epoch": 6.584828711256117, "percentage": 65.85, "elapsed_time": "5:30:31", "remaining_time": "2:51:25", "throughput": 4394.08, "total_tokens": 87141104} {"current_steps": 40370, "total_steps": 61300, "loss": 0.3244, "lr": 1.5752429204585702e-05, "epoch": 6.585644371941273, "percentage": 65.86, "elapsed_time": "5:30:33", "remaining_time": "2:51:22", "throughput": 4394.13, "total_tokens": 87151472} {"current_steps": 40375, "total_steps": 61300, "loss": 0.2988, "lr": 1.5745816472537355e-05, "epoch": 6.5864600326264275, "percentage": 65.86, "elapsed_time": "5:30:35", "remaining_time": "2:51:20", "throughput": 4394.17, "total_tokens": 87161680} {"current_steps": 40380, "total_steps": 61300, "loss": 0.3322, "lr": 1.5739204490680085e-05, "epoch": 6.587275693311582, "percentage": 65.87, "elapsed_time": "5:30:37", "remaining_time": "2:51:17", "throughput": 4394.21, "total_tokens": 87172080} {"current_steps": 40385, "total_steps": 61300, "loss": 0.3677, "lr": 1.5732593259549885e-05, "epoch": 6.588091353996737, "percentage": 65.88, "elapsed_time": "5:30:39", "remaining_time": "2:51:14", "throughput": 4394.26, "total_tokens": 87181168} {"current_steps": 40390, "total_steps": 61300, "loss": 0.307, "lr": 1.57259827796827e-05, "epoch": 6.588907014681892, "percentage": 65.89, "elapsed_time": "5:30:42", "remaining_time": "2:51:12", "throughput": 4394.3, "total_tokens": 87192144} {"current_steps": 40395, "total_steps": 61300, "loss": 0.3403, "lr": 1.5719373051614393e-05, "epoch": 6.589722675367048, "percentage": 65.9, "elapsed_time": "5:30:44", "remaining_time": "2:51:09", "throughput": 4394.35, "total_tokens": 87203344} {"current_steps": 40400, "total_steps": 61300, "loss": 0.2856, "lr": 1.571276407588081e-05, "epoch": 6.5905383360522025, "percentage": 65.91, "elapsed_time": "5:30:46", "remaining_time": "2:51:07", "throughput": 4394.39, "total_tokens": 87214416} {"current_steps": 40405, "total_steps": 61300, "loss": 0.3388, "lr": 1.570615585301769e-05, "epoch": 6.591353996737357, "percentage": 65.91, "elapsed_time": "5:30:48", "remaining_time": "2:51:04", "throughput": 4394.44, "total_tokens": 87225168} {"current_steps": 40410, "total_steps": 61300, "loss": 0.3178, "lr": 1.5699548383560736e-05, "epoch": 6.592169657422512, "percentage": 65.92, "elapsed_time": "5:30:51", "remaining_time": "2:51:02", "throughput": 4394.5, "total_tokens": 87237232} {"current_steps": 40415, "total_steps": 61300, "loss": 0.2967, "lr": 1.569294166804558e-05, "epoch": 6.592985318107667, "percentage": 65.93, "elapsed_time": "5:30:53", "remaining_time": "2:50:59", "throughput": 4394.55, "total_tokens": 87247696} {"current_steps": 40420, "total_steps": 61300, "loss": 0.3302, "lr": 1.5686335707007794e-05, "epoch": 6.593800978792823, "percentage": 65.94, "elapsed_time": "5:30:55", "remaining_time": "2:50:57", "throughput": 4394.6, "total_tokens": 87258448} {"current_steps": 40425, "total_steps": 61300, "loss": 0.3669, "lr": 1.5679730500982892e-05, "epoch": 6.5946166394779775, "percentage": 65.95, "elapsed_time": "5:30:58", "remaining_time": "2:50:54", "throughput": 4394.63, "total_tokens": 87268880} {"current_steps": 40430, "total_steps": 61300, "loss": 0.2568, "lr": 1.5673126050506327e-05, "epoch": 6.595432300163132, "percentage": 65.95, "elapsed_time": "5:31:00", "remaining_time": "2:50:51", "throughput": 4394.68, "total_tokens": 87279568} {"current_steps": 40435, "total_steps": 61300, "loss": 0.3336, "lr": 1.5666522356113488e-05, "epoch": 6.596247960848287, "percentage": 65.96, "elapsed_time": "5:31:02", "remaining_time": "2:50:49", "throughput": 4394.72, "total_tokens": 87289776} {"current_steps": 40440, "total_steps": 61300, "loss": 0.3063, "lr": 1.5659919418339707e-05, "epoch": 6.597063621533442, "percentage": 65.97, "elapsed_time": "5:31:04", "remaining_time": "2:50:46", "throughput": 4394.78, "total_tokens": 87301488} {"current_steps": 40445, "total_steps": 61300, "loss": 0.3503, "lr": 1.565331723772025e-05, "epoch": 6.597879282218597, "percentage": 65.98, "elapsed_time": "5:31:07", "remaining_time": "2:50:44", "throughput": 4394.82, "total_tokens": 87312112} {"current_steps": 40450, "total_steps": 61300, "loss": 0.31, "lr": 1.5646715814790318e-05, "epoch": 6.598694942903752, "percentage": 65.99, "elapsed_time": "5:31:09", "remaining_time": "2:50:41", "throughput": 4394.87, "total_tokens": 87322416} {"current_steps": 40455, "total_steps": 61300, "loss": 0.3477, "lr": 1.5640115150085067e-05, "epoch": 6.599510603588907, "percentage": 66.0, "elapsed_time": "5:31:11", "remaining_time": "2:50:38", "throughput": 4394.92, "total_tokens": 87333040} {"current_steps": 40460, "total_steps": 61300, "loss": 0.2824, "lr": 1.5633515244139567e-05, "epoch": 6.600326264274062, "percentage": 66.0, "elapsed_time": "5:31:13", "remaining_time": "2:50:36", "throughput": 4394.96, "total_tokens": 87344112} {"current_steps": 40465, "total_steps": 61300, "loss": 0.3118, "lr": 1.562691609748885e-05, "epoch": 6.601141924959217, "percentage": 66.01, "elapsed_time": "5:31:15", "remaining_time": "2:50:33", "throughput": 4395.0, "total_tokens": 87353680} {"current_steps": 40470, "total_steps": 61300, "loss": 0.3729, "lr": 1.562031771066787e-05, "epoch": 6.601957585644372, "percentage": 66.02, "elapsed_time": "5:31:17", "remaining_time": "2:50:31", "throughput": 4395.04, "total_tokens": 87363536} {"current_steps": 40475, "total_steps": 61300, "loss": 0.3225, "lr": 1.561372008421153e-05, "epoch": 6.602773246329527, "percentage": 66.03, "elapsed_time": "5:31:20", "remaining_time": "2:50:28", "throughput": 4395.1, "total_tokens": 87374992} {"current_steps": 40480, "total_steps": 61300, "loss": 0.3632, "lr": 1.560712321865466e-05, "epoch": 6.603588907014682, "percentage": 66.04, "elapsed_time": "5:31:22", "remaining_time": "2:50:26", "throughput": 4395.15, "total_tokens": 87386448} {"current_steps": 40485, "total_steps": 61300, "loss": 0.3151, "lr": 1.5600527114532042e-05, "epoch": 6.604404567699837, "percentage": 66.04, "elapsed_time": "5:31:24", "remaining_time": "2:50:23", "throughput": 4395.2, "total_tokens": 87395760} {"current_steps": 40490, "total_steps": 61300, "loss": 0.3535, "lr": 1.5593931772378395e-05, "epoch": 6.605220228384992, "percentage": 66.05, "elapsed_time": "5:31:26", "remaining_time": "2:50:20", "throughput": 4395.26, "total_tokens": 87407088} {"current_steps": 40495, "total_steps": 61300, "loss": 0.3524, "lr": 1.5587337192728365e-05, "epoch": 6.606035889070147, "percentage": 66.06, "elapsed_time": "5:31:29", "remaining_time": "2:50:18", "throughput": 4395.3, "total_tokens": 87418256} {"current_steps": 40500, "total_steps": 61300, "loss": 0.3798, "lr": 1.5580743376116536e-05, "epoch": 6.6068515497553015, "percentage": 66.07, "elapsed_time": "5:31:31", "remaining_time": "2:50:15", "throughput": 4395.34, "total_tokens": 87427984} {"current_steps": 40505, "total_steps": 61300, "loss": 0.325, "lr": 1.5574150323077432e-05, "epoch": 6.607667210440457, "percentage": 66.08, "elapsed_time": "5:31:33", "remaining_time": "2:50:12", "throughput": 4395.37, "total_tokens": 87437424} {"current_steps": 40510, "total_steps": 61300, "loss": 0.3476, "lr": 1.556755803414554e-05, "epoch": 6.608482871125612, "percentage": 66.08, "elapsed_time": "5:31:35", "remaining_time": "2:50:10", "throughput": 4395.41, "total_tokens": 87447504} {"current_steps": 40515, "total_steps": 61300, "loss": 0.3305, "lr": 1.5560966509855256e-05, "epoch": 6.609298531810767, "percentage": 66.09, "elapsed_time": "5:31:37", "remaining_time": "2:50:07", "throughput": 4395.46, "total_tokens": 87457456} {"current_steps": 40520, "total_steps": 61300, "loss": 0.2963, "lr": 1.5554375750740917e-05, "epoch": 6.610114192495922, "percentage": 66.1, "elapsed_time": "5:31:39", "remaining_time": "2:50:05", "throughput": 4395.51, "total_tokens": 87468464} {"current_steps": 40525, "total_steps": 61300, "loss": 0.348, "lr": 1.554778575733681e-05, "epoch": 6.6109298531810765, "percentage": 66.11, "elapsed_time": "5:31:41", "remaining_time": "2:50:02", "throughput": 4395.56, "total_tokens": 87479504} {"current_steps": 40530, "total_steps": 61300, "loss": 0.3493, "lr": 1.5541196530177148e-05, "epoch": 6.611745513866231, "percentage": 66.12, "elapsed_time": "5:31:43", "remaining_time": "2:49:59", "throughput": 4395.6, "total_tokens": 87489840} {"current_steps": 40535, "total_steps": 61300, "loss": 0.3018, "lr": 1.5534608069796085e-05, "epoch": 6.612561174551386, "percentage": 66.13, "elapsed_time": "5:31:46", "remaining_time": "2:49:57", "throughput": 4395.65, "total_tokens": 87501424} {"current_steps": 40540, "total_steps": 61300, "loss": 0.3444, "lr": 1.5528020376727725e-05, "epoch": 6.613376835236542, "percentage": 66.13, "elapsed_time": "5:31:48", "remaining_time": "2:49:54", "throughput": 4395.7, "total_tokens": 87512688} {"current_steps": 40545, "total_steps": 61300, "loss": 0.3431, "lr": 1.5521433451506088e-05, "epoch": 6.614192495921697, "percentage": 66.14, "elapsed_time": "5:31:50", "remaining_time": "2:49:52", "throughput": 4395.75, "total_tokens": 87523056} {"current_steps": 40550, "total_steps": 61300, "loss": 0.3813, "lr": 1.5514847294665152e-05, "epoch": 6.6150081566068515, "percentage": 66.15, "elapsed_time": "5:31:52", "remaining_time": "2:49:49", "throughput": 4395.79, "total_tokens": 87532784} {"current_steps": 40555, "total_steps": 61300, "loss": 0.3154, "lr": 1.5508261906738824e-05, "epoch": 6.615823817292006, "percentage": 66.16, "elapsed_time": "5:31:54", "remaining_time": "2:49:46", "throughput": 4395.83, "total_tokens": 87542224} {"current_steps": 40560, "total_steps": 61300, "loss": 0.3332, "lr": 1.5501677288260943e-05, "epoch": 6.616639477977161, "percentage": 66.17, "elapsed_time": "5:31:57", "remaining_time": "2:49:44", "throughput": 4395.88, "total_tokens": 87554224} {"current_steps": 40565, "total_steps": 61300, "loss": 0.3431, "lr": 1.549509343976529e-05, "epoch": 6.617455138662317, "percentage": 66.17, "elapsed_time": "5:31:59", "remaining_time": "2:49:42", "throughput": 4395.92, "total_tokens": 87564944} {"current_steps": 40570, "total_steps": 61300, "loss": 0.3251, "lr": 1.5488510361785597e-05, "epoch": 6.618270799347472, "percentage": 66.18, "elapsed_time": "5:32:01", "remaining_time": "2:49:39", "throughput": 4395.97, "total_tokens": 87575696} {"current_steps": 40575, "total_steps": 61300, "loss": 0.335, "lr": 1.5481928054855512e-05, "epoch": 6.6190864600326265, "percentage": 66.19, "elapsed_time": "5:32:04", "remaining_time": "2:49:36", "throughput": 4396.02, "total_tokens": 87587216} {"current_steps": 40580, "total_steps": 61300, "loss": 0.3231, "lr": 1.5475346519508637e-05, "epoch": 6.619902120717781, "percentage": 66.2, "elapsed_time": "5:32:06", "remaining_time": "2:49:34", "throughput": 4396.06, "total_tokens": 87597872} {"current_steps": 40585, "total_steps": 61300, "loss": 0.3529, "lr": 1.5468765756278498e-05, "epoch": 6.620717781402936, "percentage": 66.21, "elapsed_time": "5:32:08", "remaining_time": "2:49:31", "throughput": 4396.11, "total_tokens": 87608816} {"current_steps": 40590, "total_steps": 61300, "loss": 0.3526, "lr": 1.5462185765698568e-05, "epoch": 6.621533442088092, "percentage": 66.22, "elapsed_time": "5:32:11", "remaining_time": "2:49:29", "throughput": 4396.15, "total_tokens": 87619600} {"current_steps": 40595, "total_steps": 61300, "loss": 0.3256, "lr": 1.5455606548302253e-05, "epoch": 6.622349102773247, "percentage": 66.22, "elapsed_time": "5:32:12", "remaining_time": "2:49:26", "throughput": 4396.19, "total_tokens": 87629168} {"current_steps": 40600, "total_steps": 61300, "loss": 0.3328, "lr": 1.5449028104622905e-05, "epoch": 6.623164763458401, "percentage": 66.23, "elapsed_time": "5:32:15", "remaining_time": "2:49:24", "throughput": 4396.25, "total_tokens": 87640144} {"current_steps": 40605, "total_steps": 61300, "loss": 0.3479, "lr": 1.5442450435193795e-05, "epoch": 6.623980424143556, "percentage": 66.24, "elapsed_time": "5:32:17", "remaining_time": "2:49:21", "throughput": 4396.28, "total_tokens": 87650128} {"current_steps": 40610, "total_steps": 61300, "loss": 0.3346, "lr": 1.5435873540548135e-05, "epoch": 6.624796084828711, "percentage": 66.25, "elapsed_time": "5:32:19", "remaining_time": "2:49:18", "throughput": 4396.33, "total_tokens": 87661264} {"current_steps": 40615, "total_steps": 61300, "loss": 0.3409, "lr": 1.5429297421219107e-05, "epoch": 6.625611745513866, "percentage": 66.26, "elapsed_time": "5:32:21", "remaining_time": "2:49:16", "throughput": 4396.39, "total_tokens": 87672464} {"current_steps": 40620, "total_steps": 61300, "loss": 0.3311, "lr": 1.5422722077739794e-05, "epoch": 6.626427406199021, "percentage": 66.26, "elapsed_time": "5:32:24", "remaining_time": "2:49:13", "throughput": 4396.45, "total_tokens": 87684400} {"current_steps": 40625, "total_steps": 61300, "loss": 0.3809, "lr": 1.541614751064322e-05, "epoch": 6.627243066884176, "percentage": 66.27, "elapsed_time": "5:32:26", "remaining_time": "2:49:11", "throughput": 4396.5, "total_tokens": 87695728} {"current_steps": 40630, "total_steps": 61300, "loss": 0.3428, "lr": 1.5409573720462357e-05, "epoch": 6.628058727569331, "percentage": 66.28, "elapsed_time": "5:32:28", "remaining_time": "2:49:08", "throughput": 4396.54, "total_tokens": 87705456} {"current_steps": 40635, "total_steps": 61300, "loss": 0.3176, "lr": 1.540300070773011e-05, "epoch": 6.628874388254486, "percentage": 66.29, "elapsed_time": "5:32:31", "remaining_time": "2:49:06", "throughput": 4396.6, "total_tokens": 87716816} {"current_steps": 40640, "total_steps": 61300, "loss": 0.3424, "lr": 1.539642847297932e-05, "epoch": 6.629690048939641, "percentage": 66.3, "elapsed_time": "5:32:33", "remaining_time": "2:49:03", "throughput": 4396.64, "total_tokens": 87727216} {"current_steps": 40645, "total_steps": 61300, "loss": 0.3369, "lr": 1.5389857016742764e-05, "epoch": 6.630505709624796, "percentage": 66.31, "elapsed_time": "5:32:35", "remaining_time": "2:49:00", "throughput": 4396.69, "total_tokens": 87737040} {"current_steps": 40650, "total_steps": 61300, "loss": 0.3619, "lr": 1.538328633955316e-05, "epoch": 6.631321370309951, "percentage": 66.31, "elapsed_time": "5:32:37", "remaining_time": "2:48:58", "throughput": 4396.73, "total_tokens": 87746928} {"current_steps": 40655, "total_steps": 61300, "loss": 0.3336, "lr": 1.5376716441943162e-05, "epoch": 6.632137030995106, "percentage": 66.32, "elapsed_time": "5:32:39", "remaining_time": "2:48:55", "throughput": 4396.78, "total_tokens": 87757424} {"current_steps": 40660, "total_steps": 61300, "loss": 0.3276, "lr": 1.5370147324445354e-05, "epoch": 6.632952691680261, "percentage": 66.33, "elapsed_time": "5:32:41", "remaining_time": "2:48:53", "throughput": 4396.82, "total_tokens": 87768816} {"current_steps": 40665, "total_steps": 61300, "loss": 0.3785, "lr": 1.536357898759227e-05, "epoch": 6.633768352365416, "percentage": 66.34, "elapsed_time": "5:32:44", "remaining_time": "2:48:50", "throughput": 4396.88, "total_tokens": 87780912} {"current_steps": 40670, "total_steps": 61300, "loss": 0.3708, "lr": 1.535701143191637e-05, "epoch": 6.634584013050571, "percentage": 66.35, "elapsed_time": "5:32:46", "remaining_time": "2:48:48", "throughput": 4396.92, "total_tokens": 87791920} {"current_steps": 40675, "total_steps": 61300, "loss": 0.3458, "lr": 1.535044465795005e-05, "epoch": 6.635399673735726, "percentage": 66.35, "elapsed_time": "5:32:48", "remaining_time": "2:48:45", "throughput": 4396.97, "total_tokens": 87802352} {"current_steps": 40680, "total_steps": 61300, "loss": 0.3374, "lr": 1.534387866622564e-05, "epoch": 6.636215334420881, "percentage": 66.36, "elapsed_time": "5:32:51", "remaining_time": "2:48:43", "throughput": 4397.01, "total_tokens": 87813488} {"current_steps": 40685, "total_steps": 61300, "loss": 0.3565, "lr": 1.5337313457275428e-05, "epoch": 6.637030995106036, "percentage": 66.37, "elapsed_time": "5:32:53", "remaining_time": "2:48:40", "throughput": 4397.05, "total_tokens": 87824016} {"current_steps": 40690, "total_steps": 61300, "loss": 0.3226, "lr": 1.533074903163161e-05, "epoch": 6.637846655791191, "percentage": 66.38, "elapsed_time": "5:32:55", "remaining_time": "2:48:37", "throughput": 4397.1, "total_tokens": 87835120} {"current_steps": 40695, "total_steps": 61300, "loss": 0.3403, "lr": 1.5324185389826338e-05, "epoch": 6.638662316476346, "percentage": 66.39, "elapsed_time": "5:32:58", "remaining_time": "2:48:35", "throughput": 4397.15, "total_tokens": 87846480} {"current_steps": 40700, "total_steps": 61300, "loss": 0.3508, "lr": 1.5317622532391694e-05, "epoch": 6.6394779771615005, "percentage": 66.39, "elapsed_time": "5:33:00", "remaining_time": "2:48:32", "throughput": 4397.19, "total_tokens": 87856304} {"current_steps": 40705, "total_steps": 61300, "loss": 0.3488, "lr": 1.53110604598597e-05, "epoch": 6.640293637846656, "percentage": 66.4, "elapsed_time": "5:33:02", "remaining_time": "2:48:30", "throughput": 4397.25, "total_tokens": 87868080} {"current_steps": 40710, "total_steps": 61300, "loss": 0.3654, "lr": 1.5304499172762293e-05, "epoch": 6.641109298531811, "percentage": 66.41, "elapsed_time": "5:33:04", "remaining_time": "2:48:27", "throughput": 4397.29, "total_tokens": 87878416} {"current_steps": 40715, "total_steps": 61300, "loss": 0.3674, "lr": 1.5297938671631386e-05, "epoch": 6.641924959216966, "percentage": 66.42, "elapsed_time": "5:33:06", "remaining_time": "2:48:25", "throughput": 4397.33, "total_tokens": 87888720} {"current_steps": 40720, "total_steps": 61300, "loss": 0.3305, "lr": 1.5291378956998793e-05, "epoch": 6.642740619902121, "percentage": 66.43, "elapsed_time": "5:33:09", "remaining_time": "2:48:22", "throughput": 4397.38, "total_tokens": 87900528} {"current_steps": 40725, "total_steps": 61300, "loss": 0.3352, "lr": 1.528482002939629e-05, "epoch": 6.643556280587275, "percentage": 66.44, "elapsed_time": "5:33:11", "remaining_time": "2:48:20", "throughput": 4397.44, "total_tokens": 87911984} {"current_steps": 40730, "total_steps": 61300, "loss": 0.3671, "lr": 1.5278261889355568e-05, "epoch": 6.64437194127243, "percentage": 66.44, "elapsed_time": "5:33:13", "remaining_time": "2:48:17", "throughput": 4397.49, "total_tokens": 87922608} {"current_steps": 40735, "total_steps": 61300, "loss": 0.3435, "lr": 1.527170453740826e-05, "epoch": 6.645187601957586, "percentage": 66.45, "elapsed_time": "5:33:16", "remaining_time": "2:48:15", "throughput": 4397.54, "total_tokens": 87933936} {"current_steps": 40740, "total_steps": 61300, "loss": 0.3166, "lr": 1.5265147974085947e-05, "epoch": 6.646003262642741, "percentage": 66.46, "elapsed_time": "5:33:18", "remaining_time": "2:48:12", "throughput": 4397.59, "total_tokens": 87945488} {"current_steps": 40745, "total_steps": 61300, "loss": 0.3488, "lr": 1.5258592199920135e-05, "epoch": 6.646818923327896, "percentage": 66.47, "elapsed_time": "5:33:20", "remaining_time": "2:48:09", "throughput": 4397.65, "total_tokens": 87956112} {"current_steps": 40750, "total_steps": 61300, "loss": 0.34, "lr": 1.5252037215442266e-05, "epoch": 6.64763458401305, "percentage": 66.48, "elapsed_time": "5:33:22", "remaining_time": "2:48:07", "throughput": 4397.69, "total_tokens": 87965584} {"current_steps": 40755, "total_steps": 61300, "loss": 0.3322, "lr": 1.5245483021183722e-05, "epoch": 6.648450244698205, "percentage": 66.48, "elapsed_time": "5:33:24", "remaining_time": "2:48:04", "throughput": 4397.73, "total_tokens": 87975056} {"current_steps": 40760, "total_steps": 61300, "loss": 0.323, "lr": 1.5238929617675817e-05, "epoch": 6.649265905383361, "percentage": 66.49, "elapsed_time": "5:33:26", "remaining_time": "2:48:01", "throughput": 4397.77, "total_tokens": 87985712} {"current_steps": 40765, "total_steps": 61300, "loss": 0.3363, "lr": 1.5232377005449805e-05, "epoch": 6.650081566068516, "percentage": 66.5, "elapsed_time": "5:33:29", "remaining_time": "2:47:59", "throughput": 4397.82, "total_tokens": 87996336} {"current_steps": 40770, "total_steps": 61300, "loss": 0.3193, "lr": 1.5225825185036874e-05, "epoch": 6.650897226753671, "percentage": 66.51, "elapsed_time": "5:33:31", "remaining_time": "2:47:56", "throughput": 4397.86, "total_tokens": 88007184} {"current_steps": 40775, "total_steps": 61300, "loss": 0.3464, "lr": 1.5219274156968143e-05, "epoch": 6.651712887438825, "percentage": 66.52, "elapsed_time": "5:33:33", "remaining_time": "2:47:54", "throughput": 4397.9, "total_tokens": 88017008} {"current_steps": 40780, "total_steps": 61300, "loss": 0.349, "lr": 1.521272392177468e-05, "epoch": 6.65252854812398, "percentage": 66.53, "elapsed_time": "5:33:35", "remaining_time": "2:47:51", "throughput": 4397.95, "total_tokens": 88027760} {"current_steps": 40785, "total_steps": 61300, "loss": 0.3125, "lr": 1.5206174479987475e-05, "epoch": 6.653344208809135, "percentage": 66.53, "elapsed_time": "5:33:38", "remaining_time": "2:47:49", "throughput": 4398.0, "total_tokens": 88039696} {"current_steps": 40790, "total_steps": 61300, "loss": 0.3453, "lr": 1.5199625832137459e-05, "epoch": 6.654159869494291, "percentage": 66.54, "elapsed_time": "5:33:40", "remaining_time": "2:47:46", "throughput": 4398.05, "total_tokens": 88050544} {"current_steps": 40795, "total_steps": 61300, "loss": 0.3301, "lr": 1.5193077978755499e-05, "epoch": 6.6549755301794455, "percentage": 66.55, "elapsed_time": "5:33:42", "remaining_time": "2:47:44", "throughput": 4398.1, "total_tokens": 88061840} {"current_steps": 40800, "total_steps": 61300, "loss": 0.3819, "lr": 1.5186530920372399e-05, "epoch": 6.6557911908646, "percentage": 66.56, "elapsed_time": "5:33:44", "remaining_time": "2:47:41", "throughput": 4398.15, "total_tokens": 88072816} {"current_steps": 40805, "total_steps": 61300, "loss": 0.338, "lr": 1.5179984657518895e-05, "epoch": 6.656606851549755, "percentage": 66.57, "elapsed_time": "5:33:47", "remaining_time": "2:47:39", "throughput": 4398.19, "total_tokens": 88083536} {"current_steps": 40810, "total_steps": 61300, "loss": 0.3149, "lr": 1.5173439190725663e-05, "epoch": 6.65742251223491, "percentage": 66.57, "elapsed_time": "5:33:49", "remaining_time": "2:47:36", "throughput": 4398.24, "total_tokens": 88094704} {"current_steps": 40815, "total_steps": 61300, "loss": 0.3019, "lr": 1.5166894520523305e-05, "epoch": 6.658238172920065, "percentage": 66.58, "elapsed_time": "5:33:51", "remaining_time": "2:47:33", "throughput": 4398.3, "total_tokens": 88106288} {"current_steps": 40820, "total_steps": 61300, "loss": 0.3141, "lr": 1.5160350647442367e-05, "epoch": 6.6590538336052205, "percentage": 66.59, "elapsed_time": "5:33:53", "remaining_time": "2:47:31", "throughput": 4398.33, "total_tokens": 88114960} {"current_steps": 40825, "total_steps": 61300, "loss": 0.3523, "lr": 1.5153807572013338e-05, "epoch": 6.659869494290375, "percentage": 66.6, "elapsed_time": "5:33:55", "remaining_time": "2:47:28", "throughput": 4398.38, "total_tokens": 88124944} {"current_steps": 40830, "total_steps": 61300, "loss": 0.3592, "lr": 1.5147265294766624e-05, "epoch": 6.66068515497553, "percentage": 66.61, "elapsed_time": "5:33:57", "remaining_time": "2:47:25", "throughput": 4398.41, "total_tokens": 88135056} {"current_steps": 40835, "total_steps": 61300, "loss": 0.334, "lr": 1.5140723816232583e-05, "epoch": 6.661500815660685, "percentage": 66.62, "elapsed_time": "5:34:00", "remaining_time": "2:47:23", "throughput": 4398.47, "total_tokens": 88146768} {"current_steps": 40840, "total_steps": 61300, "loss": 0.3439, "lr": 1.5134183136941487e-05, "epoch": 6.66231647634584, "percentage": 66.62, "elapsed_time": "5:34:02", "remaining_time": "2:47:20", "throughput": 4398.52, "total_tokens": 88157968} {"current_steps": 40845, "total_steps": 61300, "loss": 0.332, "lr": 1.5127643257423572e-05, "epoch": 6.6631321370309955, "percentage": 66.63, "elapsed_time": "5:34:04", "remaining_time": "2:47:18", "throughput": 4398.56, "total_tokens": 88168912} {"current_steps": 40850, "total_steps": 61300, "loss": 0.3146, "lr": 1.5121104178208984e-05, "epoch": 6.66394779771615, "percentage": 66.64, "elapsed_time": "5:34:07", "remaining_time": "2:47:15", "throughput": 4398.61, "total_tokens": 88179632} {"current_steps": 40855, "total_steps": 61300, "loss": 0.3194, "lr": 1.5114565899827815e-05, "epoch": 6.664763458401305, "percentage": 66.65, "elapsed_time": "5:34:09", "remaining_time": "2:47:13", "throughput": 4398.66, "total_tokens": 88191472} {"current_steps": 40860, "total_steps": 61300, "loss": 0.3158, "lr": 1.5108028422810094e-05, "epoch": 6.66557911908646, "percentage": 66.66, "elapsed_time": "5:34:11", "remaining_time": "2:47:10", "throughput": 4398.71, "total_tokens": 88202800} {"current_steps": 40865, "total_steps": 61300, "loss": 0.346, "lr": 1.510149174768578e-05, "epoch": 6.666394779771615, "percentage": 66.66, "elapsed_time": "5:34:14", "remaining_time": "2:47:08", "throughput": 4398.75, "total_tokens": 88212848} {"current_steps": 40870, "total_steps": 61300, "loss": 0.3548, "lr": 1.5094955874984767e-05, "epoch": 6.6672104404567705, "percentage": 66.67, "elapsed_time": "5:34:16", "remaining_time": "2:47:05", "throughput": 4398.8, "total_tokens": 88224112} {"current_steps": 40875, "total_steps": 61300, "loss": 0.3314, "lr": 1.5088420805236892e-05, "epoch": 6.668026101141925, "percentage": 66.68, "elapsed_time": "5:34:18", "remaining_time": "2:47:03", "throughput": 4398.85, "total_tokens": 88234704} {"current_steps": 40880, "total_steps": 61300, "loss": 0.3383, "lr": 1.5081886538971911e-05, "epoch": 6.66884176182708, "percentage": 66.69, "elapsed_time": "5:34:21", "remaining_time": "2:47:00", "throughput": 4398.91, "total_tokens": 88247216} {"current_steps": 40885, "total_steps": 61300, "loss": 0.2639, "lr": 1.5075353076719536e-05, "epoch": 6.669657422512235, "percentage": 66.7, "elapsed_time": "5:34:23", "remaining_time": "2:46:58", "throughput": 4398.98, "total_tokens": 88259664} {"current_steps": 40890, "total_steps": 61300, "loss": 0.3173, "lr": 1.50688204190094e-05, "epoch": 6.67047308319739, "percentage": 66.7, "elapsed_time": "5:34:25", "remaining_time": "2:46:55", "throughput": 4399.02, "total_tokens": 88270128} {"current_steps": 40895, "total_steps": 61300, "loss": 0.2916, "lr": 1.5062288566371069e-05, "epoch": 6.671288743882545, "percentage": 66.71, "elapsed_time": "5:34:27", "remaining_time": "2:46:53", "throughput": 4399.07, "total_tokens": 88280176} {"current_steps": 40900, "total_steps": 61300, "loss": 0.2795, "lr": 1.5055757519334048e-05, "epoch": 6.672104404567699, "percentage": 66.72, "elapsed_time": "5:34:30", "remaining_time": "2:46:50", "throughput": 4399.11, "total_tokens": 88290288} {"current_steps": 40905, "total_steps": 61300, "loss": 0.3378, "lr": 1.5049227278427782e-05, "epoch": 6.672920065252855, "percentage": 66.73, "elapsed_time": "5:34:32", "remaining_time": "2:46:47", "throughput": 4399.15, "total_tokens": 88301296} {"current_steps": 40910, "total_steps": 61300, "loss": 0.3421, "lr": 1.504269784418164e-05, "epoch": 6.67373572593801, "percentage": 66.74, "elapsed_time": "5:34:34", "remaining_time": "2:46:45", "throughput": 4399.2, "total_tokens": 88312752} {"current_steps": 40915, "total_steps": 61300, "loss": 0.3447, "lr": 1.5036169217124938e-05, "epoch": 6.674551386623165, "percentage": 66.75, "elapsed_time": "5:34:37", "remaining_time": "2:46:42", "throughput": 4399.25, "total_tokens": 88324144} {"current_steps": 40920, "total_steps": 61300, "loss": 0.3562, "lr": 1.5029641397786912e-05, "epoch": 6.6753670473083195, "percentage": 66.75, "elapsed_time": "5:34:39", "remaining_time": "2:46:40", "throughput": 4399.29, "total_tokens": 88335088} {"current_steps": 40925, "total_steps": 61300, "loss": 0.3286, "lr": 1.5023114386696746e-05, "epoch": 6.676182707993474, "percentage": 66.76, "elapsed_time": "5:34:41", "remaining_time": "2:46:37", "throughput": 4399.34, "total_tokens": 88345360} {"current_steps": 40930, "total_steps": 61300, "loss": 0.3375, "lr": 1.5016588184383536e-05, "epoch": 6.67699836867863, "percentage": 66.77, "elapsed_time": "5:34:43", "remaining_time": "2:46:35", "throughput": 4399.39, "total_tokens": 88355888} {"current_steps": 40935, "total_steps": 61300, "loss": 0.3247, "lr": 1.5010062791376355e-05, "epoch": 6.677814029363785, "percentage": 66.78, "elapsed_time": "5:34:45", "remaining_time": "2:46:32", "throughput": 4399.44, "total_tokens": 88366832} {"current_steps": 40940, "total_steps": 61300, "loss": 0.3736, "lr": 1.5003538208204173e-05, "epoch": 6.67862969004894, "percentage": 66.79, "elapsed_time": "5:34:48", "remaining_time": "2:46:30", "throughput": 4399.48, "total_tokens": 88378320} {"current_steps": 40945, "total_steps": 61300, "loss": 0.3689, "lr": 1.4997014435395906e-05, "epoch": 6.6794453507340945, "percentage": 66.79, "elapsed_time": "5:34:50", "remaining_time": "2:46:27", "throughput": 4399.54, "total_tokens": 88388656} {"current_steps": 40950, "total_steps": 61300, "loss": 0.3553, "lr": 1.4990491473480403e-05, "epoch": 6.680261011419249, "percentage": 66.8, "elapsed_time": "5:34:52", "remaining_time": "2:46:25", "throughput": 4399.58, "total_tokens": 88399632} {"current_steps": 40955, "total_steps": 61300, "loss": 0.3034, "lr": 1.4983969322986446e-05, "epoch": 6.681076672104405, "percentage": 66.81, "elapsed_time": "5:34:54", "remaining_time": "2:46:22", "throughput": 4399.62, "total_tokens": 88410032} {"current_steps": 40960, "total_steps": 61300, "loss": 0.3457, "lr": 1.497744798444276e-05, "epoch": 6.68189233278956, "percentage": 66.82, "elapsed_time": "5:34:57", "remaining_time": "2:46:19", "throughput": 4399.67, "total_tokens": 88421008} {"current_steps": 40965, "total_steps": 61300, "loss": 0.3743, "lr": 1.497092745837799e-05, "epoch": 6.682707993474715, "percentage": 66.83, "elapsed_time": "5:34:59", "remaining_time": "2:46:17", "throughput": 4399.72, "total_tokens": 88432144} {"current_steps": 40970, "total_steps": 61300, "loss": 0.3279, "lr": 1.496440774532073e-05, "epoch": 6.6835236541598695, "percentage": 66.84, "elapsed_time": "5:35:01", "remaining_time": "2:46:14", "throughput": 4399.77, "total_tokens": 88442576} {"current_steps": 40975, "total_steps": 61300, "loss": 0.3015, "lr": 1.49578888457995e-05, "epoch": 6.684339314845024, "percentage": 66.84, "elapsed_time": "5:35:03", "remaining_time": "2:46:12", "throughput": 4399.81, "total_tokens": 88452048} {"current_steps": 40980, "total_steps": 61300, "loss": 0.3318, "lr": 1.4951370760342754e-05, "epoch": 6.685154975530179, "percentage": 66.85, "elapsed_time": "5:35:05", "remaining_time": "2:46:09", "throughput": 4399.86, "total_tokens": 88463280} {"current_steps": 40985, "total_steps": 61300, "loss": 0.3114, "lr": 1.4944853489478878e-05, "epoch": 6.685970636215334, "percentage": 66.86, "elapsed_time": "5:35:08", "remaining_time": "2:46:06", "throughput": 4399.9, "total_tokens": 88473488} {"current_steps": 40990, "total_steps": 61300, "loss": 0.3546, "lr": 1.4938337033736196e-05, "epoch": 6.68678629690049, "percentage": 66.87, "elapsed_time": "5:35:10", "remaining_time": "2:46:04", "throughput": 4399.95, "total_tokens": 88484304} {"current_steps": 40995, "total_steps": 61300, "loss": 0.3217, "lr": 1.4931821393642969e-05, "epoch": 6.6876019575856445, "percentage": 66.88, "elapsed_time": "5:35:12", "remaining_time": "2:46:01", "throughput": 4399.99, "total_tokens": 88495088} {"current_steps": 41000, "total_steps": 61300, "loss": 0.3491, "lr": 1.4925306569727385e-05, "epoch": 6.688417618270799, "percentage": 66.88, "elapsed_time": "5:35:14", "remaining_time": "2:45:59", "throughput": 4400.04, "total_tokens": 88506512} {"current_steps": 41005, "total_steps": 61300, "loss": 0.3506, "lr": 1.491879256251757e-05, "epoch": 6.689233278955954, "percentage": 66.89, "elapsed_time": "5:35:17", "remaining_time": "2:45:56", "throughput": 4400.1, "total_tokens": 88518192} {"current_steps": 41010, "total_steps": 61300, "loss": 0.3176, "lr": 1.4912279372541577e-05, "epoch": 6.690048939641109, "percentage": 66.9, "elapsed_time": "5:35:19", "remaining_time": "2:45:54", "throughput": 4400.14, "total_tokens": 88526928} {"current_steps": 41015, "total_steps": 61300, "loss": 0.3582, "lr": 1.4905767000327409e-05, "epoch": 6.690864600326265, "percentage": 66.91, "elapsed_time": "5:35:21", "remaining_time": "2:45:51", "throughput": 4400.19, "total_tokens": 88537616} {"current_steps": 41020, "total_steps": 61300, "loss": 0.3069, "lr": 1.4899255446402982e-05, "epoch": 6.691680261011419, "percentage": 66.92, "elapsed_time": "5:35:23", "remaining_time": "2:45:48", "throughput": 4400.23, "total_tokens": 88547408} {"current_steps": 41025, "total_steps": 61300, "loss": 0.3339, "lr": 1.4892744711296152e-05, "epoch": 6.692495921696574, "percentage": 66.92, "elapsed_time": "5:35:25", "remaining_time": "2:45:46", "throughput": 4400.26, "total_tokens": 88557232} {"current_steps": 41030, "total_steps": 61300, "loss": 0.3498, "lr": 1.488623479553473e-05, "epoch": 6.693311582381729, "percentage": 66.93, "elapsed_time": "5:35:27", "remaining_time": "2:45:43", "throughput": 4400.31, "total_tokens": 88567632} {"current_steps": 41035, "total_steps": 61300, "loss": 0.369, "lr": 1.4879725699646424e-05, "epoch": 6.694127243066884, "percentage": 66.94, "elapsed_time": "5:35:29", "remaining_time": "2:45:41", "throughput": 4400.37, "total_tokens": 88579312} {"current_steps": 41040, "total_steps": 61300, "loss": 0.3599, "lr": 1.4873217424158906e-05, "epoch": 6.69494290375204, "percentage": 66.95, "elapsed_time": "5:35:32", "remaining_time": "2:45:38", "throughput": 4400.41, "total_tokens": 88590608} {"current_steps": 41045, "total_steps": 61300, "loss": 0.3577, "lr": 1.4866709969599767e-05, "epoch": 6.695758564437194, "percentage": 66.96, "elapsed_time": "5:35:34", "remaining_time": "2:45:36", "throughput": 4400.47, "total_tokens": 88601904} {"current_steps": 41050, "total_steps": 61300, "loss": 0.3429, "lr": 1.486020333649653e-05, "epoch": 6.696574225122349, "percentage": 66.97, "elapsed_time": "5:35:36", "remaining_time": "2:45:33", "throughput": 4400.51, "total_tokens": 88611088} {"current_steps": 41055, "total_steps": 61300, "loss": 0.3481, "lr": 1.4853697525376665e-05, "epoch": 6.697389885807504, "percentage": 66.97, "elapsed_time": "5:35:39", "remaining_time": "2:45:30", "throughput": 4400.56, "total_tokens": 88623120} {"current_steps": 41060, "total_steps": 61300, "loss": 0.3589, "lr": 1.484719253676756e-05, "epoch": 6.698205546492659, "percentage": 66.98, "elapsed_time": "5:35:41", "remaining_time": "2:45:28", "throughput": 4400.61, "total_tokens": 88634064} {"current_steps": 41065, "total_steps": 61300, "loss": 0.3513, "lr": 1.4840688371196543e-05, "epoch": 6.699021207177814, "percentage": 66.99, "elapsed_time": "5:35:43", "remaining_time": "2:45:25", "throughput": 4400.66, "total_tokens": 88645392} {"current_steps": 41070, "total_steps": 61300, "loss": 0.3386, "lr": 1.4834185029190873e-05, "epoch": 6.699836867862969, "percentage": 67.0, "elapsed_time": "5:35:46", "remaining_time": "2:45:23", "throughput": 4400.71, "total_tokens": 88657808} {"current_steps": 41075, "total_steps": 61300, "loss": 0.3381, "lr": 1.4827682511277746e-05, "epoch": 6.700652528548124, "percentage": 67.01, "elapsed_time": "5:35:48", "remaining_time": "2:45:20", "throughput": 4400.76, "total_tokens": 88668048} {"current_steps": 41080, "total_steps": 61300, "loss": 0.3351, "lr": 1.4821180817984288e-05, "epoch": 6.701468189233279, "percentage": 67.01, "elapsed_time": "5:35:50", "remaining_time": "2:45:18", "throughput": 4400.8, "total_tokens": 88677456} {"current_steps": 41085, "total_steps": 61300, "loss": 0.336, "lr": 1.4814679949837563e-05, "epoch": 6.702283849918434, "percentage": 67.02, "elapsed_time": "5:35:52", "remaining_time": "2:45:15", "throughput": 4400.84, "total_tokens": 88688592} {"current_steps": 41090, "total_steps": 61300, "loss": 0.3209, "lr": 1.4808179907364555e-05, "epoch": 6.703099510603589, "percentage": 67.03, "elapsed_time": "5:35:54", "remaining_time": "2:45:13", "throughput": 4400.88, "total_tokens": 88699152} {"current_steps": 41095, "total_steps": 61300, "loss": 0.328, "lr": 1.48016806910922e-05, "epoch": 6.7039151712887435, "percentage": 67.04, "elapsed_time": "5:35:57", "remaining_time": "2:45:10", "throughput": 4400.92, "total_tokens": 88709776} {"current_steps": 41100, "total_steps": 61300, "loss": 0.3261, "lr": 1.4795182301547356e-05, "epoch": 6.704730831973899, "percentage": 67.05, "elapsed_time": "5:35:59", "remaining_time": "2:45:08", "throughput": 4400.98, "total_tokens": 88721328} {"current_steps": 41105, "total_steps": 61300, "loss": 0.3507, "lr": 1.4788684739256808e-05, "epoch": 6.705546492659054, "percentage": 67.06, "elapsed_time": "5:36:01", "remaining_time": "2:45:05", "throughput": 4401.03, "total_tokens": 88732432} {"current_steps": 41110, "total_steps": 61300, "loss": 0.3175, "lr": 1.4782188004747289e-05, "epoch": 6.706362153344209, "percentage": 67.06, "elapsed_time": "5:36:04", "remaining_time": "2:45:02", "throughput": 4401.07, "total_tokens": 88743312} {"current_steps": 41115, "total_steps": 61300, "loss": 0.3449, "lr": 1.4775692098545451e-05, "epoch": 6.707177814029364, "percentage": 67.07, "elapsed_time": "5:36:06", "remaining_time": "2:45:00", "throughput": 4401.12, "total_tokens": 88754096} {"current_steps": 41120, "total_steps": 61300, "loss": 0.3674, "lr": 1.4769197021177896e-05, "epoch": 6.7079934747145185, "percentage": 67.08, "elapsed_time": "5:36:08", "remaining_time": "2:44:57", "throughput": 4401.17, "total_tokens": 88765200} {"current_steps": 41125, "total_steps": 61300, "loss": 0.3453, "lr": 1.476270277317114e-05, "epoch": 6.708809135399674, "percentage": 67.09, "elapsed_time": "5:36:10", "remaining_time": "2:44:55", "throughput": 4401.23, "total_tokens": 88777136} {"current_steps": 41130, "total_steps": 61300, "loss": 0.3364, "lr": 1.475620935505164e-05, "epoch": 6.709624796084829, "percentage": 67.1, "elapsed_time": "5:36:13", "remaining_time": "2:44:52", "throughput": 4401.29, "total_tokens": 88789040} {"current_steps": 41135, "total_steps": 61300, "loss": 0.358, "lr": 1.4749716767345784e-05, "epoch": 6.710440456769984, "percentage": 67.1, "elapsed_time": "5:36:15", "remaining_time": "2:44:50", "throughput": 4401.33, "total_tokens": 88799792} {"current_steps": 41140, "total_steps": 61300, "loss": 0.3137, "lr": 1.4743225010579889e-05, "epoch": 6.711256117455139, "percentage": 67.11, "elapsed_time": "5:36:17", "remaining_time": "2:44:47", "throughput": 4401.37, "total_tokens": 88810224} {"current_steps": 41145, "total_steps": 61300, "loss": 0.3184, "lr": 1.4736734085280226e-05, "epoch": 6.712071778140293, "percentage": 67.12, "elapsed_time": "5:36:19", "remaining_time": "2:44:45", "throughput": 4401.41, "total_tokens": 88820112} {"current_steps": 41150, "total_steps": 61300, "loss": 0.3432, "lr": 1.4730243991972976e-05, "epoch": 6.712887438825448, "percentage": 67.13, "elapsed_time": "5:36:22", "remaining_time": "2:44:42", "throughput": 4401.45, "total_tokens": 88830864} {"current_steps": 41155, "total_steps": 61300, "loss": 0.3464, "lr": 1.4723754731184253e-05, "epoch": 6.713703099510604, "percentage": 67.14, "elapsed_time": "5:36:24", "remaining_time": "2:44:40", "throughput": 4401.5, "total_tokens": 88842096} {"current_steps": 41160, "total_steps": 61300, "loss": 0.3097, "lr": 1.4717266303440113e-05, "epoch": 6.714518760195759, "percentage": 67.15, "elapsed_time": "5:36:26", "remaining_time": "2:44:37", "throughput": 4401.55, "total_tokens": 88853232} {"current_steps": 41165, "total_steps": 61300, "loss": 0.3374, "lr": 1.471077870926654e-05, "epoch": 6.715334420880914, "percentage": 67.15, "elapsed_time": "5:36:28", "remaining_time": "2:44:35", "throughput": 4401.59, "total_tokens": 88863408} {"current_steps": 41170, "total_steps": 61300, "loss": 0.3185, "lr": 1.4704291949189452e-05, "epoch": 6.716150081566068, "percentage": 67.16, "elapsed_time": "5:36:31", "remaining_time": "2:44:32", "throughput": 4401.63, "total_tokens": 88873648} {"current_steps": 41175, "total_steps": 61300, "loss": 0.3142, "lr": 1.46978060237347e-05, "epoch": 6.716965742251223, "percentage": 67.17, "elapsed_time": "5:36:33", "remaining_time": "2:44:29", "throughput": 4401.68, "total_tokens": 88884720} {"current_steps": 41180, "total_steps": 61300, "loss": 0.3399, "lr": 1.4691320933428066e-05, "epoch": 6.717781402936378, "percentage": 67.18, "elapsed_time": "5:36:35", "remaining_time": "2:44:27", "throughput": 4401.73, "total_tokens": 88895632} {"current_steps": 41185, "total_steps": 61300, "loss": 0.3199, "lr": 1.4684836678795259e-05, "epoch": 6.718597063621534, "percentage": 67.19, "elapsed_time": "5:36:37", "remaining_time": "2:44:24", "throughput": 4401.76, "total_tokens": 88905456} {"current_steps": 41190, "total_steps": 61300, "loss": 0.3189, "lr": 1.4678353260361927e-05, "epoch": 6.719412724306689, "percentage": 67.19, "elapsed_time": "5:36:40", "remaining_time": "2:44:22", "throughput": 4401.81, "total_tokens": 88916848} {"current_steps": 41195, "total_steps": 61300, "loss": 0.3448, "lr": 1.4671870678653653e-05, "epoch": 6.720228384991843, "percentage": 67.2, "elapsed_time": "5:36:42", "remaining_time": "2:44:19", "throughput": 4401.86, "total_tokens": 88928240} {"current_steps": 41200, "total_steps": 61300, "loss": 0.3248, "lr": 1.466538893419595e-05, "epoch": 6.721044045676998, "percentage": 67.21, "elapsed_time": "5:36:44", "remaining_time": "2:44:17", "throughput": 4401.91, "total_tokens": 88940016} {"current_steps": 41205, "total_steps": 61300, "loss": 0.3296, "lr": 1.4658908027514256e-05, "epoch": 6.721859706362153, "percentage": 67.22, "elapsed_time": "5:36:47", "remaining_time": "2:44:14", "throughput": 4401.96, "total_tokens": 88950544} {"current_steps": 41210, "total_steps": 61300, "loss": 0.3501, "lr": 1.4652427959133947e-05, "epoch": 6.722675367047309, "percentage": 67.23, "elapsed_time": "5:36:49", "remaining_time": "2:44:12", "throughput": 4402.0, "total_tokens": 88961520} {"current_steps": 41215, "total_steps": 61300, "loss": 0.311, "lr": 1.4645948729580331e-05, "epoch": 6.7234910277324635, "percentage": 67.23, "elapsed_time": "5:36:51", "remaining_time": "2:44:09", "throughput": 4402.05, "total_tokens": 88971952} {"current_steps": 41220, "total_steps": 61300, "loss": 0.3316, "lr": 1.4639470339378647e-05, "epoch": 6.724306688417618, "percentage": 67.24, "elapsed_time": "5:36:53", "remaining_time": "2:44:06", "throughput": 4402.1, "total_tokens": 88981840} {"current_steps": 41225, "total_steps": 61300, "loss": 0.3355, "lr": 1.4632992789054064e-05, "epoch": 6.725122349102773, "percentage": 67.25, "elapsed_time": "5:36:55", "remaining_time": "2:44:04", "throughput": 4402.14, "total_tokens": 88992656} {"current_steps": 41230, "total_steps": 61300, "loss": 0.3257, "lr": 1.4626516079131692e-05, "epoch": 6.725938009787928, "percentage": 67.26, "elapsed_time": "5:36:58", "remaining_time": "2:44:01", "throughput": 4402.21, "total_tokens": 89004432} {"current_steps": 41235, "total_steps": 61300, "loss": 0.3691, "lr": 1.4620040210136557e-05, "epoch": 6.726753670473083, "percentage": 67.27, "elapsed_time": "5:37:00", "remaining_time": "2:43:59", "throughput": 4402.24, "total_tokens": 89014736} {"current_steps": 41240, "total_steps": 61300, "loss": 0.3305, "lr": 1.461356518259363e-05, "epoch": 6.7275693311582385, "percentage": 67.28, "elapsed_time": "5:37:02", "remaining_time": "2:43:56", "throughput": 4402.28, "total_tokens": 89024976} {"current_steps": 41245, "total_steps": 61300, "loss": 0.3336, "lr": 1.4607090997027812e-05, "epoch": 6.728384991843393, "percentage": 67.28, "elapsed_time": "5:37:04", "remaining_time": "2:43:54", "throughput": 4402.33, "total_tokens": 89035440} {"current_steps": 41250, "total_steps": 61300, "loss": 0.3231, "lr": 1.4600617653963918e-05, "epoch": 6.729200652528548, "percentage": 67.29, "elapsed_time": "5:37:06", "remaining_time": "2:43:51", "throughput": 4402.37, "total_tokens": 89046608} {"current_steps": 41255, "total_steps": 61300, "loss": 0.3509, "lr": 1.4594145153926737e-05, "epoch": 6.730016313213703, "percentage": 67.3, "elapsed_time": "5:37:09", "remaining_time": "2:43:48", "throughput": 4402.41, "total_tokens": 89056912} {"current_steps": 41260, "total_steps": 61300, "loss": 0.3152, "lr": 1.4587673497440946e-05, "epoch": 6.730831973898858, "percentage": 67.31, "elapsed_time": "5:37:11", "remaining_time": "2:43:46", "throughput": 4402.45, "total_tokens": 89068048} {"current_steps": 41265, "total_steps": 61300, "loss": 0.3408, "lr": 1.458120268503117e-05, "epoch": 6.731647634584013, "percentage": 67.32, "elapsed_time": "5:37:13", "remaining_time": "2:43:43", "throughput": 4402.5, "total_tokens": 89078544} {"current_steps": 41270, "total_steps": 61300, "loss": 0.3084, "lr": 1.4574732717221972e-05, "epoch": 6.732463295269168, "percentage": 67.32, "elapsed_time": "5:37:16", "remaining_time": "2:43:41", "throughput": 4402.55, "total_tokens": 89090768} {"current_steps": 41275, "total_steps": 61300, "loss": 0.338, "lr": 1.456826359453784e-05, "epoch": 6.733278955954323, "percentage": 67.33, "elapsed_time": "5:37:18", "remaining_time": "2:43:38", "throughput": 4402.59, "total_tokens": 89101040} {"current_steps": 41280, "total_steps": 61300, "loss": 0.3281, "lr": 1.4561795317503185e-05, "epoch": 6.734094616639478, "percentage": 67.34, "elapsed_time": "5:37:20", "remaining_time": "2:43:36", "throughput": 4402.63, "total_tokens": 89112112} {"current_steps": 41285, "total_steps": 61300, "loss": 0.3412, "lr": 1.455532788664237e-05, "epoch": 6.734910277324633, "percentage": 67.35, "elapsed_time": "5:37:22", "remaining_time": "2:43:33", "throughput": 4402.68, "total_tokens": 89123056} {"current_steps": 41290, "total_steps": 61300, "loss": 0.3437, "lr": 1.4548861302479672e-05, "epoch": 6.735725938009788, "percentage": 67.36, "elapsed_time": "5:37:25", "remaining_time": "2:43:31", "throughput": 4402.74, "total_tokens": 89135120} {"current_steps": 41295, "total_steps": 61300, "loss": 0.323, "lr": 1.4542395565539302e-05, "epoch": 6.736541598694943, "percentage": 67.37, "elapsed_time": "5:37:27", "remaining_time": "2:43:28", "throughput": 4402.79, "total_tokens": 89147184} {"current_steps": 41300, "total_steps": 61300, "loss": 0.3245, "lr": 1.453593067634541e-05, "epoch": 6.737357259380098, "percentage": 67.37, "elapsed_time": "5:37:29", "remaining_time": "2:43:26", "throughput": 4402.83, "total_tokens": 89156912} {"current_steps": 41305, "total_steps": 61300, "loss": 0.3157, "lr": 1.4529466635422063e-05, "epoch": 6.738172920065253, "percentage": 67.38, "elapsed_time": "5:37:32", "remaining_time": "2:43:23", "throughput": 4402.87, "total_tokens": 89167184} {"current_steps": 41310, "total_steps": 61300, "loss": 0.3157, "lr": 1.4523003443293285e-05, "epoch": 6.738988580750408, "percentage": 67.39, "elapsed_time": "5:37:34", "remaining_time": "2:43:21", "throughput": 4402.92, "total_tokens": 89178448} {"current_steps": 41315, "total_steps": 61300, "loss": 0.3582, "lr": 1.4516541100483008e-05, "epoch": 6.739804241435563, "percentage": 67.4, "elapsed_time": "5:37:36", "remaining_time": "2:43:18", "throughput": 4402.96, "total_tokens": 89189072} {"current_steps": 41320, "total_steps": 61300, "loss": 0.3429, "lr": 1.4510079607515104e-05, "epoch": 6.740619902120718, "percentage": 67.41, "elapsed_time": "5:37:38", "remaining_time": "2:43:16", "throughput": 4403.01, "total_tokens": 89200496} {"current_steps": 41325, "total_steps": 61300, "loss": 0.3752, "lr": 1.4503618964913368e-05, "epoch": 6.741435562805873, "percentage": 67.41, "elapsed_time": "5:37:40", "remaining_time": "2:43:13", "throughput": 4403.05, "total_tokens": 89209840} {"current_steps": 41330, "total_steps": 61300, "loss": 0.3173, "lr": 1.4497159173201541e-05, "epoch": 6.742251223491028, "percentage": 67.42, "elapsed_time": "5:37:43", "remaining_time": "2:43:10", "throughput": 4403.09, "total_tokens": 89220240} {"current_steps": 41335, "total_steps": 61300, "loss": 0.3341, "lr": 1.4490700232903281e-05, "epoch": 6.743066884176183, "percentage": 67.43, "elapsed_time": "5:37:45", "remaining_time": "2:43:08", "throughput": 4403.15, "total_tokens": 89232400} {"current_steps": 41340, "total_steps": 61300, "loss": 0.3201, "lr": 1.4484242144542184e-05, "epoch": 6.7438825448613375, "percentage": 67.44, "elapsed_time": "5:37:47", "remaining_time": "2:43:05", "throughput": 4403.19, "total_tokens": 89242608} {"current_steps": 41345, "total_steps": 61300, "loss": 0.3357, "lr": 1.4477784908641775e-05, "epoch": 6.744698205546492, "percentage": 67.45, "elapsed_time": "5:37:49", "remaining_time": "2:43:03", "throughput": 4403.23, "total_tokens": 89253328} {"current_steps": 41350, "total_steps": 61300, "loss": 0.3595, "lr": 1.4471328525725512e-05, "epoch": 6.745513866231647, "percentage": 67.46, "elapsed_time": "5:37:52", "remaining_time": "2:43:00", "throughput": 4403.28, "total_tokens": 89263984} {"current_steps": 41355, "total_steps": 61300, "loss": 0.3162, "lr": 1.446487299631677e-05, "epoch": 6.746329526916803, "percentage": 67.46, "elapsed_time": "5:37:54", "remaining_time": "2:42:58", "throughput": 4403.32, "total_tokens": 89275856} {"current_steps": 41360, "total_steps": 61300, "loss": 0.324, "lr": 1.4458418320938886e-05, "epoch": 6.747145187601958, "percentage": 67.47, "elapsed_time": "5:37:57", "remaining_time": "2:42:55", "throughput": 4403.36, "total_tokens": 89287024} {"current_steps": 41365, "total_steps": 61300, "loss": 0.325, "lr": 1.4451964500115101e-05, "epoch": 6.7479608482871125, "percentage": 67.48, "elapsed_time": "5:37:59", "remaining_time": "2:42:53", "throughput": 4403.41, "total_tokens": 89298032} {"current_steps": 41370, "total_steps": 61300, "loss": 0.3283, "lr": 1.4445511534368595e-05, "epoch": 6.748776508972267, "percentage": 67.49, "elapsed_time": "5:38:01", "remaining_time": "2:42:50", "throughput": 4403.46, "total_tokens": 89309424} {"current_steps": 41375, "total_steps": 61300, "loss": 0.3325, "lr": 1.4439059424222474e-05, "epoch": 6.749592169657422, "percentage": 67.5, "elapsed_time": "5:38:04", "remaining_time": "2:42:48", "throughput": 4403.51, "total_tokens": 89320880} {"current_steps": 41380, "total_steps": 61300, "loss": 0.3273, "lr": 1.4432608170199785e-05, "epoch": 6.750407830342578, "percentage": 67.5, "elapsed_time": "5:38:06", "remaining_time": "2:42:45", "throughput": 4403.56, "total_tokens": 89332624} {"current_steps": 41385, "total_steps": 61300, "loss": 0.3584, "lr": 1.4426157772823495e-05, "epoch": 6.751223491027733, "percentage": 67.51, "elapsed_time": "5:38:08", "remaining_time": "2:42:43", "throughput": 4403.6, "total_tokens": 89343344} {"current_steps": 41390, "total_steps": 61300, "loss": 0.3648, "lr": 1.4419708232616508e-05, "epoch": 6.7520391517128875, "percentage": 67.52, "elapsed_time": "5:38:11", "remaining_time": "2:42:40", "throughput": 4403.65, "total_tokens": 89355344} {"current_steps": 41395, "total_steps": 61300, "loss": 0.3296, "lr": 1.4413259550101654e-05, "epoch": 6.752854812398042, "percentage": 67.53, "elapsed_time": "5:38:13", "remaining_time": "2:42:38", "throughput": 4403.69, "total_tokens": 89366160} {"current_steps": 41400, "total_steps": 61300, "loss": 0.3431, "lr": 1.4406811725801696e-05, "epoch": 6.753670473083197, "percentage": 67.54, "elapsed_time": "5:38:15", "remaining_time": "2:42:35", "throughput": 4403.74, "total_tokens": 89376976} {"current_steps": 41405, "total_steps": 61300, "loss": 0.3578, "lr": 1.4400364760239333e-05, "epoch": 6.754486133768353, "percentage": 67.54, "elapsed_time": "5:38:18", "remaining_time": "2:42:33", "throughput": 4403.79, "total_tokens": 89388176} {"current_steps": 41410, "total_steps": 61300, "loss": 0.3743, "lr": 1.4393918653937183e-05, "epoch": 6.755301794453508, "percentage": 67.55, "elapsed_time": "5:38:20", "remaining_time": "2:42:30", "throughput": 4403.84, "total_tokens": 89399152} {"current_steps": 41415, "total_steps": 61300, "loss": 0.3193, "lr": 1.4387473407417801e-05, "epoch": 6.7561174551386625, "percentage": 67.56, "elapsed_time": "5:38:22", "remaining_time": "2:42:28", "throughput": 4403.89, "total_tokens": 89409968} {"current_steps": 41420, "total_steps": 61300, "loss": 0.308, "lr": 1.438102902120367e-05, "epoch": 6.756933115823817, "percentage": 67.57, "elapsed_time": "5:38:24", "remaining_time": "2:42:25", "throughput": 4403.93, "total_tokens": 89420560} {"current_steps": 41425, "total_steps": 61300, "loss": 0.3271, "lr": 1.437458549581721e-05, "epoch": 6.757748776508972, "percentage": 67.58, "elapsed_time": "5:38:27", "remaining_time": "2:42:23", "throughput": 4403.97, "total_tokens": 89431952} {"current_steps": 41430, "total_steps": 61300, "loss": 0.3588, "lr": 1.4368142831780763e-05, "epoch": 6.758564437194127, "percentage": 67.59, "elapsed_time": "5:38:29", "remaining_time": "2:42:20", "throughput": 4404.01, "total_tokens": 89443152} {"current_steps": 41435, "total_steps": 61300, "loss": 0.3402, "lr": 1.4361701029616598e-05, "epoch": 6.759380097879282, "percentage": 67.59, "elapsed_time": "5:38:31", "remaining_time": "2:42:18", "throughput": 4404.06, "total_tokens": 89454576} {"current_steps": 41440, "total_steps": 61300, "loss": 0.34, "lr": 1.4355260089846931e-05, "epoch": 6.760195758564437, "percentage": 67.6, "elapsed_time": "5:38:34", "remaining_time": "2:42:15", "throughput": 4404.11, "total_tokens": 89465840} {"current_steps": 41445, "total_steps": 61300, "loss": 0.3738, "lr": 1.434882001299389e-05, "epoch": 6.761011419249592, "percentage": 67.61, "elapsed_time": "5:38:36", "remaining_time": "2:42:12", "throughput": 4404.16, "total_tokens": 89476400} {"current_steps": 41450, "total_steps": 61300, "loss": 0.3335, "lr": 1.4342380799579533e-05, "epoch": 6.761827079934747, "percentage": 67.62, "elapsed_time": "5:38:38", "remaining_time": "2:42:10", "throughput": 4404.2, "total_tokens": 89487568} {"current_steps": 41455, "total_steps": 61300, "loss": 0.3522, "lr": 1.4335942450125872e-05, "epoch": 6.762642740619902, "percentage": 67.63, "elapsed_time": "5:38:40", "remaining_time": "2:42:07", "throughput": 4404.24, "total_tokens": 89496400} {"current_steps": 41460, "total_steps": 61300, "loss": 0.3382, "lr": 1.4329504965154827e-05, "epoch": 6.763458401305057, "percentage": 67.63, "elapsed_time": "5:38:42", "remaining_time": "2:42:05", "throughput": 4404.3, "total_tokens": 89507440} {"current_steps": 41465, "total_steps": 61300, "loss": 0.3535, "lr": 1.4323068345188253e-05, "epoch": 6.764274061990212, "percentage": 67.64, "elapsed_time": "5:38:44", "remaining_time": "2:42:02", "throughput": 4404.33, "total_tokens": 89516624} {"current_steps": 41470, "total_steps": 61300, "loss": 0.3178, "lr": 1.431663259074793e-05, "epoch": 6.765089722675367, "percentage": 67.65, "elapsed_time": "5:38:46", "remaining_time": "2:41:59", "throughput": 4404.37, "total_tokens": 89526352} {"current_steps": 41475, "total_steps": 61300, "loss": 0.3355, "lr": 1.4310197702355572e-05, "epoch": 6.765905383360522, "percentage": 67.66, "elapsed_time": "5:38:49", "remaining_time": "2:41:57", "throughput": 4404.43, "total_tokens": 89538128} {"current_steps": 41480, "total_steps": 61300, "loss": 0.3529, "lr": 1.430376368053283e-05, "epoch": 6.766721044045677, "percentage": 67.67, "elapsed_time": "5:38:51", "remaining_time": "2:41:54", "throughput": 4404.47, "total_tokens": 89549136} {"current_steps": 41485, "total_steps": 61300, "loss": 0.3455, "lr": 1.429733052580128e-05, "epoch": 6.767536704730832, "percentage": 67.68, "elapsed_time": "5:38:53", "remaining_time": "2:41:52", "throughput": 4404.52, "total_tokens": 89559728} {"current_steps": 41490, "total_steps": 61300, "loss": 0.3191, "lr": 1.4290898238682421e-05, "epoch": 6.768352365415987, "percentage": 67.68, "elapsed_time": "5:38:55", "remaining_time": "2:41:49", "throughput": 4404.56, "total_tokens": 89569904} {"current_steps": 41495, "total_steps": 61300, "loss": 0.3116, "lr": 1.428446681969769e-05, "epoch": 6.769168026101142, "percentage": 67.69, "elapsed_time": "5:38:58", "remaining_time": "2:41:47", "throughput": 4404.6, "total_tokens": 89581008} {"current_steps": 41500, "total_steps": 61300, "loss": 0.3636, "lr": 1.427803626936845e-05, "epoch": 6.769983686786297, "percentage": 67.7, "elapsed_time": "5:39:00", "remaining_time": "2:41:44", "throughput": 4404.65, "total_tokens": 89591728} {"current_steps": 41505, "total_steps": 61300, "loss": 0.3047, "lr": 1.4271606588215988e-05, "epoch": 6.770799347471452, "percentage": 67.71, "elapsed_time": "5:39:02", "remaining_time": "2:41:41", "throughput": 4404.69, "total_tokens": 89601456} {"current_steps": 41510, "total_steps": 61300, "loss": 0.3401, "lr": 1.4265177776761534e-05, "epoch": 6.771615008156607, "percentage": 67.72, "elapsed_time": "5:39:04", "remaining_time": "2:41:39", "throughput": 4404.73, "total_tokens": 89612368} {"current_steps": 41515, "total_steps": 61300, "loss": 0.327, "lr": 1.4258749835526235e-05, "epoch": 6.7724306688417615, "percentage": 67.72, "elapsed_time": "5:39:06", "remaining_time": "2:41:36", "throughput": 4404.77, "total_tokens": 89623312} {"current_steps": 41520, "total_steps": 61300, "loss": 0.3186, "lr": 1.4252322765031179e-05, "epoch": 6.773246329526917, "percentage": 67.73, "elapsed_time": "5:39:09", "remaining_time": "2:41:34", "throughput": 4404.83, "total_tokens": 89633936} {"current_steps": 41525, "total_steps": 61300, "loss": 0.3176, "lr": 1.4245896565797373e-05, "epoch": 6.774061990212072, "percentage": 67.74, "elapsed_time": "5:39:11", "remaining_time": "2:41:31", "throughput": 4404.86, "total_tokens": 89643696} {"current_steps": 41530, "total_steps": 61300, "loss": 0.333, "lr": 1.4239471238345753e-05, "epoch": 6.774877650897227, "percentage": 67.75, "elapsed_time": "5:39:13", "remaining_time": "2:41:28", "throughput": 4404.91, "total_tokens": 89653936} {"current_steps": 41535, "total_steps": 61300, "loss": 0.2917, "lr": 1.4233046783197195e-05, "epoch": 6.775693311582382, "percentage": 67.76, "elapsed_time": "5:39:15", "remaining_time": "2:41:26", "throughput": 4404.96, "total_tokens": 89664752} {"current_steps": 41540, "total_steps": 61300, "loss": 0.3148, "lr": 1.4226623200872496e-05, "epoch": 6.7765089722675365, "percentage": 67.77, "elapsed_time": "5:39:17", "remaining_time": "2:41:23", "throughput": 4405.02, "total_tokens": 89675984} {"current_steps": 41545, "total_steps": 61300, "loss": 0.3281, "lr": 1.4220200491892383e-05, "epoch": 6.777324632952691, "percentage": 67.77, "elapsed_time": "5:39:19", "remaining_time": "2:41:21", "throughput": 4405.05, "total_tokens": 89686704} {"current_steps": 41550, "total_steps": 61300, "loss": 0.3078, "lr": 1.4213778656777515e-05, "epoch": 6.778140293637847, "percentage": 67.78, "elapsed_time": "5:39:22", "remaining_time": "2:41:18", "throughput": 4405.1, "total_tokens": 89697040} {"current_steps": 41555, "total_steps": 61300, "loss": 0.3875, "lr": 1.4207357696048479e-05, "epoch": 6.778955954323002, "percentage": 67.79, "elapsed_time": "5:39:24", "remaining_time": "2:41:16", "throughput": 4405.15, "total_tokens": 89708208} {"current_steps": 41560, "total_steps": 61300, "loss": 0.2992, "lr": 1.4200937610225787e-05, "epoch": 6.779771615008157, "percentage": 67.8, "elapsed_time": "5:39:26", "remaining_time": "2:41:13", "throughput": 4405.2, "total_tokens": 89719120} {"current_steps": 41565, "total_steps": 61300, "loss": 0.3679, "lr": 1.4194518399829887e-05, "epoch": 6.780587275693311, "percentage": 67.81, "elapsed_time": "5:39:28", "remaining_time": "2:41:11", "throughput": 4405.24, "total_tokens": 89730384} {"current_steps": 41570, "total_steps": 61300, "loss": 0.3331, "lr": 1.4188100065381144e-05, "epoch": 6.781402936378466, "percentage": 67.81, "elapsed_time": "5:39:31", "remaining_time": "2:41:08", "throughput": 4405.3, "total_tokens": 89742128} {"current_steps": 41575, "total_steps": 61300, "loss": 0.3292, "lr": 1.4181682607399877e-05, "epoch": 6.782218597063622, "percentage": 67.82, "elapsed_time": "5:39:33", "remaining_time": "2:41:06", "throughput": 4405.34, "total_tokens": 89752944} {"current_steps": 41580, "total_steps": 61300, "loss": 0.3862, "lr": 1.4175266026406308e-05, "epoch": 6.783034257748777, "percentage": 67.83, "elapsed_time": "5:39:35", "remaining_time": "2:41:03", "throughput": 4405.38, "total_tokens": 89762448} {"current_steps": 41585, "total_steps": 61300, "loss": 0.3211, "lr": 1.4168850322920602e-05, "epoch": 6.783849918433932, "percentage": 67.84, "elapsed_time": "5:39:37", "remaining_time": "2:41:00", "throughput": 4405.43, "total_tokens": 89773200} {"current_steps": 41590, "total_steps": 61300, "loss": 0.3068, "lr": 1.4162435497462842e-05, "epoch": 6.784665579119086, "percentage": 67.85, "elapsed_time": "5:39:40", "remaining_time": "2:40:58", "throughput": 4405.48, "total_tokens": 89783952} {"current_steps": 41595, "total_steps": 61300, "loss": 0.3545, "lr": 1.415602155055305e-05, "epoch": 6.785481239804241, "percentage": 67.85, "elapsed_time": "5:39:42", "remaining_time": "2:40:55", "throughput": 4405.53, "total_tokens": 89796528} {"current_steps": 41600, "total_steps": 61300, "loss": 0.3226, "lr": 1.4149608482711177e-05, "epoch": 6.786296900489396, "percentage": 67.86, "elapsed_time": "5:39:44", "remaining_time": "2:40:53", "throughput": 4405.58, "total_tokens": 89807664} {"current_steps": 41605, "total_steps": 61300, "loss": 0.319, "lr": 1.4143196294457092e-05, "epoch": 6.787112561174552, "percentage": 67.87, "elapsed_time": "5:39:47", "remaining_time": "2:40:50", "throughput": 4405.62, "total_tokens": 89817552} {"current_steps": 41610, "total_steps": 61300, "loss": 0.3115, "lr": 1.4136784986310603e-05, "epoch": 6.787928221859707, "percentage": 67.88, "elapsed_time": "5:39:49", "remaining_time": "2:40:48", "throughput": 4405.68, "total_tokens": 89829008} {"current_steps": 41615, "total_steps": 61300, "loss": 0.343, "lr": 1.4130374558791442e-05, "epoch": 6.788743882544861, "percentage": 67.89, "elapsed_time": "5:39:51", "remaining_time": "2:40:45", "throughput": 4405.71, "total_tokens": 89839856} {"current_steps": 41620, "total_steps": 61300, "loss": 0.3509, "lr": 1.412396501241926e-05, "epoch": 6.789559543230016, "percentage": 67.9, "elapsed_time": "5:39:54", "remaining_time": "2:40:43", "throughput": 4405.76, "total_tokens": 89851312} {"current_steps": 41625, "total_steps": 61300, "loss": 0.3273, "lr": 1.411755634771367e-05, "epoch": 6.790375203915171, "percentage": 67.9, "elapsed_time": "5:39:56", "remaining_time": "2:40:40", "throughput": 4405.82, "total_tokens": 89863248} {"current_steps": 41630, "total_steps": 61300, "loss": 0.3404, "lr": 1.411114856519418e-05, "epoch": 6.791190864600326, "percentage": 67.91, "elapsed_time": "5:39:58", "remaining_time": "2:40:38", "throughput": 4405.87, "total_tokens": 89875344} {"current_steps": 41635, "total_steps": 61300, "loss": 0.3412, "lr": 1.4104741665380236e-05, "epoch": 6.7920065252854815, "percentage": 67.92, "elapsed_time": "5:40:01", "remaining_time": "2:40:35", "throughput": 4405.92, "total_tokens": 89887056} {"current_steps": 41640, "total_steps": 61300, "loss": 0.3364, "lr": 1.4098335648791216e-05, "epoch": 6.792822185970636, "percentage": 67.93, "elapsed_time": "5:40:03", "remaining_time": "2:40:33", "throughput": 4405.97, "total_tokens": 89898064} {"current_steps": 41645, "total_steps": 61300, "loss": 0.3312, "lr": 1.4091930515946422e-05, "epoch": 6.793637846655791, "percentage": 67.94, "elapsed_time": "5:40:05", "remaining_time": "2:40:30", "throughput": 4406.02, "total_tokens": 89908816} {"current_steps": 41650, "total_steps": 61300, "loss": 0.3457, "lr": 1.4085526267365084e-05, "epoch": 6.794453507340946, "percentage": 67.94, "elapsed_time": "5:40:08", "remaining_time": "2:40:28", "throughput": 4406.06, "total_tokens": 89918896} {"current_steps": 41655, "total_steps": 61300, "loss": 0.3239, "lr": 1.4079122903566371e-05, "epoch": 6.795269168026101, "percentage": 67.95, "elapsed_time": "5:40:10", "remaining_time": "2:40:25", "throughput": 4406.09, "total_tokens": 89928880} {"current_steps": 41660, "total_steps": 61300, "loss": 0.3411, "lr": 1.4072720425069364e-05, "epoch": 6.7960848287112565, "percentage": 67.96, "elapsed_time": "5:40:12", "remaining_time": "2:40:23", "throughput": 4406.14, "total_tokens": 89939952} {"current_steps": 41665, "total_steps": 61300, "loss": 0.3666, "lr": 1.4066318832393086e-05, "epoch": 6.796900489396411, "percentage": 67.97, "elapsed_time": "5:40:14", "remaining_time": "2:40:20", "throughput": 4406.17, "total_tokens": 89949360} {"current_steps": 41670, "total_steps": 61300, "loss": 0.3576, "lr": 1.4059918126056478e-05, "epoch": 6.797716150081566, "percentage": 67.98, "elapsed_time": "5:40:16", "remaining_time": "2:40:17", "throughput": 4406.22, "total_tokens": 89960144} {"current_steps": 41675, "total_steps": 61300, "loss": 0.3562, "lr": 1.405351830657841e-05, "epoch": 6.798531810766721, "percentage": 67.99, "elapsed_time": "5:40:18", "remaining_time": "2:40:15", "throughput": 4406.26, "total_tokens": 89971184} {"current_steps": 41680, "total_steps": 61300, "loss": 0.3347, "lr": 1.4047119374477696e-05, "epoch": 6.799347471451876, "percentage": 67.99, "elapsed_time": "5:40:21", "remaining_time": "2:40:12", "throughput": 4406.31, "total_tokens": 89982288} {"current_steps": 41685, "total_steps": 61300, "loss": 0.3293, "lr": 1.4040721330273062e-05, "epoch": 6.800163132137031, "percentage": 68.0, "elapsed_time": "5:40:23", "remaining_time": "2:40:10", "throughput": 4406.37, "total_tokens": 89993744} {"current_steps": 41690, "total_steps": 61300, "loss": 0.3129, "lr": 1.4034324174483166e-05, "epoch": 6.800978792822186, "percentage": 68.01, "elapsed_time": "5:40:25", "remaining_time": "2:40:07", "throughput": 4406.42, "total_tokens": 90005232} {"current_steps": 41695, "total_steps": 61300, "loss": 0.3189, "lr": 1.4027927907626586e-05, "epoch": 6.801794453507341, "percentage": 68.02, "elapsed_time": "5:40:28", "remaining_time": "2:40:05", "throughput": 4406.46, "total_tokens": 90016240} {"current_steps": 41700, "total_steps": 61300, "loss": 0.3044, "lr": 1.4021532530221846e-05, "epoch": 6.802610114192496, "percentage": 68.03, "elapsed_time": "5:40:30", "remaining_time": "2:40:02", "throughput": 4406.51, "total_tokens": 90026736} {"current_steps": 41705, "total_steps": 61300, "loss": 0.337, "lr": 1.4015138042787381e-05, "epoch": 6.803425774877651, "percentage": 68.03, "elapsed_time": "5:40:32", "remaining_time": "2:40:00", "throughput": 4406.54, "total_tokens": 90037296} {"current_steps": 41710, "total_steps": 61300, "loss": 0.3088, "lr": 1.4008744445841566e-05, "epoch": 6.804241435562806, "percentage": 68.04, "elapsed_time": "5:40:34", "remaining_time": "2:39:57", "throughput": 4406.58, "total_tokens": 90048176} {"current_steps": 41715, "total_steps": 61300, "loss": 0.3389, "lr": 1.4002351739902691e-05, "epoch": 6.80505709624796, "percentage": 68.05, "elapsed_time": "5:40:37", "remaining_time": "2:39:55", "throughput": 4406.63, "total_tokens": 90059056} {"current_steps": 41720, "total_steps": 61300, "loss": 0.3172, "lr": 1.3995959925488988e-05, "epoch": 6.805872756933116, "percentage": 68.06, "elapsed_time": "5:40:39", "remaining_time": "2:39:52", "throughput": 4406.67, "total_tokens": 90069456} {"current_steps": 41725, "total_steps": 61300, "loss": 0.3353, "lr": 1.3989569003118609e-05, "epoch": 6.806688417618271, "percentage": 68.07, "elapsed_time": "5:40:41", "remaining_time": "2:39:50", "throughput": 4406.73, "total_tokens": 90081840} {"current_steps": 41730, "total_steps": 61300, "loss": 0.3265, "lr": 1.398317897330963e-05, "epoch": 6.807504078303426, "percentage": 68.08, "elapsed_time": "5:40:43", "remaining_time": "2:39:47", "throughput": 4406.76, "total_tokens": 90091600} {"current_steps": 41735, "total_steps": 61300, "loss": 0.3253, "lr": 1.3976789836580062e-05, "epoch": 6.808319738988581, "percentage": 68.08, "elapsed_time": "5:40:46", "remaining_time": "2:39:45", "throughput": 4406.81, "total_tokens": 90103344} {"current_steps": 41740, "total_steps": 61300, "loss": 0.3101, "lr": 1.3970401593447843e-05, "epoch": 6.809135399673735, "percentage": 68.09, "elapsed_time": "5:40:48", "remaining_time": "2:39:42", "throughput": 4406.86, "total_tokens": 90114352} {"current_steps": 41745, "total_steps": 61300, "loss": 0.355, "lr": 1.3964014244430834e-05, "epoch": 6.809951060358891, "percentage": 68.1, "elapsed_time": "5:40:50", "remaining_time": "2:39:40", "throughput": 4406.91, "total_tokens": 90125584} {"current_steps": 41750, "total_steps": 61300, "loss": 0.3235, "lr": 1.3957627790046826e-05, "epoch": 6.810766721044046, "percentage": 68.11, "elapsed_time": "5:40:53", "remaining_time": "2:39:37", "throughput": 4406.94, "total_tokens": 90136304} {"current_steps": 41755, "total_steps": 61300, "loss": 0.2928, "lr": 1.3951242230813538e-05, "epoch": 6.811582381729201, "percentage": 68.12, "elapsed_time": "5:40:55", "remaining_time": "2:39:34", "throughput": 4406.99, "total_tokens": 90147088} {"current_steps": 41760, "total_steps": 61300, "loss": 0.3361, "lr": 1.3944857567248615e-05, "epoch": 6.8123980424143555, "percentage": 68.12, "elapsed_time": "5:40:57", "remaining_time": "2:39:32", "throughput": 4407.05, "total_tokens": 90158512} {"current_steps": 41765, "total_steps": 61300, "loss": 0.323, "lr": 1.3938473799869622e-05, "epoch": 6.81321370309951, "percentage": 68.13, "elapsed_time": "5:40:59", "remaining_time": "2:39:29", "throughput": 4407.08, "total_tokens": 90168880} {"current_steps": 41770, "total_steps": 61300, "loss": 0.3279, "lr": 1.3932090929194075e-05, "epoch": 6.814029363784666, "percentage": 68.14, "elapsed_time": "5:41:02", "remaining_time": "2:39:27", "throughput": 4407.13, "total_tokens": 90179696} {"current_steps": 41775, "total_steps": 61300, "loss": 0.3194, "lr": 1.39257089557394e-05, "epoch": 6.814845024469821, "percentage": 68.15, "elapsed_time": "5:41:04", "remaining_time": "2:39:24", "throughput": 4407.18, "total_tokens": 90190960} {"current_steps": 41780, "total_steps": 61300, "loss": 0.3471, "lr": 1.3919327880022945e-05, "epoch": 6.815660685154976, "percentage": 68.16, "elapsed_time": "5:41:06", "remaining_time": "2:39:22", "throughput": 4407.22, "total_tokens": 90202288} {"current_steps": 41785, "total_steps": 61300, "loss": 0.3831, "lr": 1.3912947702561995e-05, "epoch": 6.8164763458401305, "percentage": 68.16, "elapsed_time": "5:41:09", "remaining_time": "2:39:19", "throughput": 4407.28, "total_tokens": 90214288} {"current_steps": 41790, "total_steps": 61300, "loss": 0.3648, "lr": 1.390656842387375e-05, "epoch": 6.817292006525285, "percentage": 68.17, "elapsed_time": "5:41:11", "remaining_time": "2:39:17", "throughput": 4407.33, "total_tokens": 90225168} {"current_steps": 41795, "total_steps": 61300, "loss": 0.3299, "lr": 1.3900190044475364e-05, "epoch": 6.81810766721044, "percentage": 68.18, "elapsed_time": "5:41:13", "remaining_time": "2:39:14", "throughput": 4407.37, "total_tokens": 90235760} {"current_steps": 41800, "total_steps": 61300, "loss": 0.3048, "lr": 1.3893812564883896e-05, "epoch": 6.818923327895595, "percentage": 68.19, "elapsed_time": "5:41:16", "remaining_time": "2:39:12", "throughput": 4407.42, "total_tokens": 90246864} {"current_steps": 41805, "total_steps": 61300, "loss": 0.3376, "lr": 1.3887435985616332e-05, "epoch": 6.819738988580751, "percentage": 68.2, "elapsed_time": "5:41:18", "remaining_time": "2:39:09", "throughput": 4407.46, "total_tokens": 90257680} {"current_steps": 41810, "total_steps": 61300, "loss": 0.329, "lr": 1.3881060307189592e-05, "epoch": 6.8205546492659055, "percentage": 68.21, "elapsed_time": "5:41:20", "remaining_time": "2:39:07", "throughput": 4407.5, "total_tokens": 90268976} {"current_steps": 41815, "total_steps": 61300, "loss": 0.3145, "lr": 1.387468553012052e-05, "epoch": 6.82137030995106, "percentage": 68.21, "elapsed_time": "5:41:22", "remaining_time": "2:39:04", "throughput": 4407.55, "total_tokens": 90279696} {"current_steps": 41820, "total_steps": 61300, "loss": 0.3165, "lr": 1.386831165492589e-05, "epoch": 6.822185970636215, "percentage": 68.22, "elapsed_time": "5:41:24", "remaining_time": "2:39:01", "throughput": 4407.57, "total_tokens": 90288624} {"current_steps": 41825, "total_steps": 61300, "loss": 0.3062, "lr": 1.3861938682122396e-05, "epoch": 6.82300163132137, "percentage": 68.23, "elapsed_time": "5:41:27", "remaining_time": "2:38:59", "throughput": 4407.63, "total_tokens": 90299984} {"current_steps": 41830, "total_steps": 61300, "loss": 0.3156, "lr": 1.3855566612226666e-05, "epoch": 6.823817292006526, "percentage": 68.24, "elapsed_time": "5:41:29", "remaining_time": "2:38:56", "throughput": 4407.67, "total_tokens": 90309264} {"current_steps": 41835, "total_steps": 61300, "loss": 0.3307, "lr": 1.3849195445755258e-05, "epoch": 6.8246329526916805, "percentage": 68.25, "elapsed_time": "5:41:31", "remaining_time": "2:38:54", "throughput": 4407.71, "total_tokens": 90320528} {"current_steps": 41840, "total_steps": 61300, "loss": 0.3936, "lr": 1.3842825183224642e-05, "epoch": 6.825448613376835, "percentage": 68.25, "elapsed_time": "5:41:33", "remaining_time": "2:38:51", "throughput": 4407.76, "total_tokens": 90331184} {"current_steps": 41845, "total_steps": 61300, "loss": 0.3114, "lr": 1.3836455825151229e-05, "epoch": 6.82626427406199, "percentage": 68.26, "elapsed_time": "5:41:35", "remaining_time": "2:38:49", "throughput": 4407.8, "total_tokens": 90341200} {"current_steps": 41850, "total_steps": 61300, "loss": 0.3244, "lr": 1.3830087372051347e-05, "epoch": 6.827079934747145, "percentage": 68.27, "elapsed_time": "5:41:37", "remaining_time": "2:38:46", "throughput": 4407.84, "total_tokens": 90350992} {"current_steps": 41855, "total_steps": 61300, "loss": 0.3108, "lr": 1.3823719824441262e-05, "epoch": 6.827895595432301, "percentage": 68.28, "elapsed_time": "5:41:39", "remaining_time": "2:38:43", "throughput": 4407.89, "total_tokens": 90361520} {"current_steps": 41860, "total_steps": 61300, "loss": 0.3654, "lr": 1.3817353182837151e-05, "epoch": 6.828711256117455, "percentage": 68.29, "elapsed_time": "5:41:42", "remaining_time": "2:38:41", "throughput": 4407.93, "total_tokens": 90372112} {"current_steps": 41865, "total_steps": 61300, "loss": 0.312, "lr": 1.3810987447755136e-05, "epoch": 6.82952691680261, "percentage": 68.3, "elapsed_time": "5:41:44", "remaining_time": "2:38:38", "throughput": 4407.98, "total_tokens": 90383856} {"current_steps": 41870, "total_steps": 61300, "loss": 0.3422, "lr": 1.380462261971125e-05, "epoch": 6.830342577487765, "percentage": 68.3, "elapsed_time": "5:41:46", "remaining_time": "2:38:36", "throughput": 4408.01, "total_tokens": 90393552} {"current_steps": 41875, "total_steps": 61300, "loss": 0.3085, "lr": 1.3798258699221456e-05, "epoch": 6.83115823817292, "percentage": 68.31, "elapsed_time": "5:41:48", "remaining_time": "2:38:33", "throughput": 4408.05, "total_tokens": 90403056} {"current_steps": 41880, "total_steps": 61300, "loss": 0.35, "lr": 1.3791895686801653e-05, "epoch": 6.831973898858075, "percentage": 68.32, "elapsed_time": "5:41:50", "remaining_time": "2:38:31", "throughput": 4408.09, "total_tokens": 90414160} {"current_steps": 41885, "total_steps": 61300, "loss": 0.3399, "lr": 1.3785533582967642e-05, "epoch": 6.8327895595432295, "percentage": 68.33, "elapsed_time": "5:41:53", "remaining_time": "2:38:28", "throughput": 4408.15, "total_tokens": 90426160} {"current_steps": 41890, "total_steps": 61300, "loss": 0.3149, "lr": 1.3779172388235192e-05, "epoch": 6.833605220228385, "percentage": 68.34, "elapsed_time": "5:41:55", "remaining_time": "2:38:26", "throughput": 4408.19, "total_tokens": 90436816} {"current_steps": 41895, "total_steps": 61300, "loss": 0.3333, "lr": 1.3772812103119964e-05, "epoch": 6.83442088091354, "percentage": 68.34, "elapsed_time": "5:41:57", "remaining_time": "2:38:23", "throughput": 4408.24, "total_tokens": 90448144} {"current_steps": 41900, "total_steps": 61300, "loss": 0.2926, "lr": 1.376645272813755e-05, "epoch": 6.835236541598695, "percentage": 68.35, "elapsed_time": "5:42:00", "remaining_time": "2:38:20", "throughput": 4408.28, "total_tokens": 90458352} {"current_steps": 41905, "total_steps": 61300, "loss": 0.3007, "lr": 1.3760094263803474e-05, "epoch": 6.83605220228385, "percentage": 68.36, "elapsed_time": "5:42:02", "remaining_time": "2:38:18", "throughput": 4408.31, "total_tokens": 90469264} {"current_steps": 41910, "total_steps": 61300, "loss": 0.2944, "lr": 1.3753736710633192e-05, "epoch": 6.8368678629690045, "percentage": 68.37, "elapsed_time": "5:42:04", "remaining_time": "2:38:15", "throughput": 4408.34, "total_tokens": 90478832} {"current_steps": 41915, "total_steps": 61300, "loss": 0.3367, "lr": 1.3747380069142073e-05, "epoch": 6.83768352365416, "percentage": 68.38, "elapsed_time": "5:42:06", "remaining_time": "2:38:13", "throughput": 4408.39, "total_tokens": 90489840} {"current_steps": 41920, "total_steps": 61300, "loss": 0.3544, "lr": 1.3741024339845426e-05, "epoch": 6.838499184339315, "percentage": 68.38, "elapsed_time": "5:42:09", "remaining_time": "2:38:10", "throughput": 4408.44, "total_tokens": 90501232} {"current_steps": 41925, "total_steps": 61300, "loss": 0.3339, "lr": 1.373466952325847e-05, "epoch": 6.83931484502447, "percentage": 68.39, "elapsed_time": "5:42:11", "remaining_time": "2:38:08", "throughput": 4408.49, "total_tokens": 90512560} {"current_steps": 41930, "total_steps": 61300, "loss": 0.3422, "lr": 1.372831561989636e-05, "epoch": 6.840130505709625, "percentage": 68.4, "elapsed_time": "5:42:13", "remaining_time": "2:38:05", "throughput": 4408.54, "total_tokens": 90523856} {"current_steps": 41935, "total_steps": 61300, "loss": 0.3704, "lr": 1.3721962630274171e-05, "epoch": 6.8409461663947795, "percentage": 68.41, "elapsed_time": "5:42:15", "remaining_time": "2:38:03", "throughput": 4408.58, "total_tokens": 90532720} {"current_steps": 41940, "total_steps": 61300, "loss": 0.3541, "lr": 1.3715610554906922e-05, "epoch": 6.841761827079935, "percentage": 68.42, "elapsed_time": "5:42:17", "remaining_time": "2:38:00", "throughput": 4408.62, "total_tokens": 90543888} {"current_steps": 41945, "total_steps": 61300, "loss": 0.3174, "lr": 1.370925939430954e-05, "epoch": 6.84257748776509, "percentage": 68.43, "elapsed_time": "5:42:19", "remaining_time": "2:37:57", "throughput": 4408.67, "total_tokens": 90553712} {"current_steps": 41950, "total_steps": 61300, "loss": 0.3387, "lr": 1.3702909148996878e-05, "epoch": 6.843393148450245, "percentage": 68.43, "elapsed_time": "5:42:22", "remaining_time": "2:37:55", "throughput": 4408.71, "total_tokens": 90563920} {"current_steps": 41955, "total_steps": 61300, "loss": 0.36, "lr": 1.3696559819483722e-05, "epoch": 6.8442088091354, "percentage": 68.44, "elapsed_time": "5:42:24", "remaining_time": "2:37:52", "throughput": 4408.76, "total_tokens": 90574544} {"current_steps": 41960, "total_steps": 61300, "loss": 0.3433, "lr": 1.3690211406284784e-05, "epoch": 6.8450244698205545, "percentage": 68.45, "elapsed_time": "5:42:26", "remaining_time": "2:37:50", "throughput": 4408.8, "total_tokens": 90586384} {"current_steps": 41965, "total_steps": 61300, "loss": 0.329, "lr": 1.368386390991469e-05, "epoch": 6.845840130505709, "percentage": 68.46, "elapsed_time": "5:42:29", "remaining_time": "2:37:47", "throughput": 4408.85, "total_tokens": 90597776} {"current_steps": 41970, "total_steps": 61300, "loss": 0.3688, "lr": 1.3677517330888007e-05, "epoch": 6.846655791190865, "percentage": 68.47, "elapsed_time": "5:42:31", "remaining_time": "2:37:45", "throughput": 4408.91, "total_tokens": 90610128} {"current_steps": 41975, "total_steps": 61300, "loss": 0.3364, "lr": 1.3671171669719218e-05, "epoch": 6.84747145187602, "percentage": 68.47, "elapsed_time": "5:42:33", "remaining_time": "2:37:42", "throughput": 4408.96, "total_tokens": 90621168} {"current_steps": 41980, "total_steps": 61300, "loss": 0.3043, "lr": 1.3664826926922736e-05, "epoch": 6.848287112561175, "percentage": 68.48, "elapsed_time": "5:42:36", "remaining_time": "2:37:40", "throughput": 4409.0, "total_tokens": 90631536} {"current_steps": 41985, "total_steps": 61300, "loss": 0.3279, "lr": 1.3658483103012898e-05, "epoch": 6.849102773246329, "percentage": 68.49, "elapsed_time": "5:42:38", "remaining_time": "2:37:37", "throughput": 4409.04, "total_tokens": 90641168} {"current_steps": 41990, "total_steps": 61300, "loss": 0.3448, "lr": 1.3652140198503966e-05, "epoch": 6.849918433931484, "percentage": 68.5, "elapsed_time": "5:42:40", "remaining_time": "2:37:35", "throughput": 4409.08, "total_tokens": 90651632} {"current_steps": 41995, "total_steps": 61300, "loss": 0.314, "lr": 1.364579821391012e-05, "epoch": 6.850734094616639, "percentage": 68.51, "elapsed_time": "5:42:42", "remaining_time": "2:37:32", "throughput": 4409.11, "total_tokens": 90662128} {"current_steps": 42000, "total_steps": 61300, "loss": 0.3368, "lr": 1.3639457149745489e-05, "epoch": 6.851549755301795, "percentage": 68.52, "elapsed_time": "5:42:44", "remaining_time": "2:37:30", "throughput": 4409.17, "total_tokens": 90673808} {"current_steps": 42005, "total_steps": 61300, "loss": 0.3153, "lr": 1.3633117006524102e-05, "epoch": 6.85236541598695, "percentage": 68.52, "elapsed_time": "5:42:47", "remaining_time": "2:37:27", "throughput": 4409.21, "total_tokens": 90684752} {"current_steps": 42010, "total_steps": 61300, "loss": 0.3234, "lr": 1.3626777784759925e-05, "epoch": 6.853181076672104, "percentage": 68.53, "elapsed_time": "5:42:49", "remaining_time": "2:37:24", "throughput": 4409.25, "total_tokens": 90695312} {"current_steps": 42015, "total_steps": 61300, "loss": 0.3047, "lr": 1.3620439484966851e-05, "epoch": 6.853996737357259, "percentage": 68.54, "elapsed_time": "5:42:51", "remaining_time": "2:37:22", "throughput": 4409.29, "total_tokens": 90705520} {"current_steps": 42020, "total_steps": 61300, "loss": 0.3151, "lr": 1.3614102107658693e-05, "epoch": 6.854812398042414, "percentage": 68.55, "elapsed_time": "5:42:53", "remaining_time": "2:37:19", "throughput": 4409.34, "total_tokens": 90717584} {"current_steps": 42025, "total_steps": 61300, "loss": 0.3429, "lr": 1.3607765653349185e-05, "epoch": 6.85562805872757, "percentage": 68.56, "elapsed_time": "5:42:56", "remaining_time": "2:37:17", "throughput": 4409.4, "total_tokens": 90728496} {"current_steps": 42030, "total_steps": 61300, "loss": 0.3219, "lr": 1.3601430122552e-05, "epoch": 6.856443719412725, "percentage": 68.56, "elapsed_time": "5:42:58", "remaining_time": "2:37:14", "throughput": 4409.44, "total_tokens": 90738960} {"current_steps": 42035, "total_steps": 61300, "loss": 0.3439, "lr": 1.3595095515780726e-05, "epoch": 6.857259380097879, "percentage": 68.57, "elapsed_time": "5:43:00", "remaining_time": "2:37:12", "throughput": 4409.48, "total_tokens": 90750352} {"current_steps": 42040, "total_steps": 61300, "loss": 0.3158, "lr": 1.3588761833548875e-05, "epoch": 6.858075040783034, "percentage": 68.58, "elapsed_time": "5:43:02", "remaining_time": "2:37:09", "throughput": 4409.52, "total_tokens": 90761040} {"current_steps": 42045, "total_steps": 61300, "loss": 0.3665, "lr": 1.358242907636989e-05, "epoch": 6.858890701468189, "percentage": 68.59, "elapsed_time": "5:43:05", "remaining_time": "2:37:07", "throughput": 4409.56, "total_tokens": 90770992} {"current_steps": 42050, "total_steps": 61300, "loss": 0.3532, "lr": 1.3576097244757138e-05, "epoch": 6.859706362153344, "percentage": 68.6, "elapsed_time": "5:43:06", "remaining_time": "2:37:04", "throughput": 4409.6, "total_tokens": 90779088} {"current_steps": 42055, "total_steps": 61300, "loss": 0.2832, "lr": 1.3569766339223907e-05, "epoch": 6.8605220228384995, "percentage": 68.61, "elapsed_time": "5:43:08", "remaining_time": "2:37:01", "throughput": 4409.63, "total_tokens": 90789616} {"current_steps": 42060, "total_steps": 61300, "loss": 0.3463, "lr": 1.3563436360283412e-05, "epoch": 6.861337683523654, "percentage": 68.61, "elapsed_time": "5:43:11", "remaining_time": "2:36:59", "throughput": 4409.67, "total_tokens": 90800496} {"current_steps": 42065, "total_steps": 61300, "loss": 0.3256, "lr": 1.3557107308448796e-05, "epoch": 6.862153344208809, "percentage": 68.62, "elapsed_time": "5:43:13", "remaining_time": "2:36:56", "throughput": 4409.71, "total_tokens": 90809808} {"current_steps": 42070, "total_steps": 61300, "loss": 0.3434, "lr": 1.355077918423312e-05, "epoch": 6.862969004893964, "percentage": 68.63, "elapsed_time": "5:43:15", "remaining_time": "2:36:54", "throughput": 4409.75, "total_tokens": 90820880} {"current_steps": 42075, "total_steps": 61300, "loss": 0.3098, "lr": 1.3544451988149376e-05, "epoch": 6.863784665579119, "percentage": 68.64, "elapsed_time": "5:43:17", "remaining_time": "2:36:51", "throughput": 4409.79, "total_tokens": 90831696} {"current_steps": 42080, "total_steps": 61300, "loss": 0.343, "lr": 1.353812572071047e-05, "epoch": 6.864600326264274, "percentage": 68.65, "elapsed_time": "5:43:19", "remaining_time": "2:36:49", "throughput": 4409.84, "total_tokens": 90842512} {"current_steps": 42085, "total_steps": 61300, "loss": 0.3199, "lr": 1.353180038242926e-05, "epoch": 6.865415986949429, "percentage": 68.65, "elapsed_time": "5:43:22", "remaining_time": "2:36:46", "throughput": 4409.88, "total_tokens": 90852784} {"current_steps": 42090, "total_steps": 61300, "loss": 0.3902, "lr": 1.3525475973818502e-05, "epoch": 6.866231647634584, "percentage": 68.66, "elapsed_time": "5:43:24", "remaining_time": "2:36:43", "throughput": 4409.92, "total_tokens": 90863280} {"current_steps": 42095, "total_steps": 61300, "loss": 0.3342, "lr": 1.351915249539088e-05, "epoch": 6.867047308319739, "percentage": 68.67, "elapsed_time": "5:43:26", "remaining_time": "2:36:41", "throughput": 4409.97, "total_tokens": 90874160} {"current_steps": 42100, "total_steps": 61300, "loss": 0.3683, "lr": 1.3512829947659011e-05, "epoch": 6.867862969004894, "percentage": 68.68, "elapsed_time": "5:43:28", "remaining_time": "2:36:38", "throughput": 4410.01, "total_tokens": 90884752} {"current_steps": 42105, "total_steps": 61300, "loss": 0.3177, "lr": 1.350650833113542e-05, "epoch": 6.868678629690049, "percentage": 68.69, "elapsed_time": "5:43:30", "remaining_time": "2:36:36", "throughput": 4410.04, "total_tokens": 90894704} {"current_steps": 42110, "total_steps": 61300, "loss": 0.3338, "lr": 1.3500187646332593e-05, "epoch": 6.869494290375204, "percentage": 68.69, "elapsed_time": "5:43:32", "remaining_time": "2:36:33", "throughput": 4410.08, "total_tokens": 90904528} {"current_steps": 42115, "total_steps": 61300, "loss": 0.2837, "lr": 1.3493867893762904e-05, "epoch": 6.870309951060359, "percentage": 68.7, "elapsed_time": "5:43:35", "remaining_time": "2:36:31", "throughput": 4410.13, "total_tokens": 90915696} {"current_steps": 42120, "total_steps": 61300, "loss": 0.3746, "lr": 1.3487549073938666e-05, "epoch": 6.871125611745514, "percentage": 68.71, "elapsed_time": "5:43:37", "remaining_time": "2:36:28", "throughput": 4410.18, "total_tokens": 90925776} {"current_steps": 42125, "total_steps": 61300, "loss": 0.3622, "lr": 1.3481231187372111e-05, "epoch": 6.871941272430669, "percentage": 68.72, "elapsed_time": "5:43:39", "remaining_time": "2:36:25", "throughput": 4410.22, "total_tokens": 90936144} {"current_steps": 42130, "total_steps": 61300, "loss": 0.3417, "lr": 1.3474914234575406e-05, "epoch": 6.872756933115824, "percentage": 68.73, "elapsed_time": "5:43:41", "remaining_time": "2:36:23", "throughput": 4410.26, "total_tokens": 90946480} {"current_steps": 42135, "total_steps": 61300, "loss": 0.3055, "lr": 1.346859821606063e-05, "epoch": 6.873572593800979, "percentage": 68.74, "elapsed_time": "5:43:43", "remaining_time": "2:36:20", "throughput": 4410.3, "total_tokens": 90956720} {"current_steps": 42140, "total_steps": 61300, "loss": 0.3, "lr": 1.3462283132339787e-05, "epoch": 6.874388254486134, "percentage": 68.74, "elapsed_time": "5:43:45", "remaining_time": "2:36:18", "throughput": 4410.34, "total_tokens": 90967312} {"current_steps": 42145, "total_steps": 61300, "loss": 0.3152, "lr": 1.3455968983924822e-05, "epoch": 6.875203915171289, "percentage": 68.75, "elapsed_time": "5:43:48", "remaining_time": "2:36:15", "throughput": 4410.38, "total_tokens": 90978000} {"current_steps": 42150, "total_steps": 61300, "loss": 0.3274, "lr": 1.344965577132758e-05, "epoch": 6.876019575856444, "percentage": 68.76, "elapsed_time": "5:43:50", "remaining_time": "2:36:12", "throughput": 4410.42, "total_tokens": 90988304} {"current_steps": 42155, "total_steps": 61300, "loss": 0.3039, "lr": 1.344334349505985e-05, "epoch": 6.876835236541599, "percentage": 68.77, "elapsed_time": "5:43:52", "remaining_time": "2:36:10", "throughput": 4410.46, "total_tokens": 90998288} {"current_steps": 42160, "total_steps": 61300, "loss": 0.3164, "lr": 1.3437032155633333e-05, "epoch": 6.877650897226753, "percentage": 68.78, "elapsed_time": "5:43:54", "remaining_time": "2:36:07", "throughput": 4410.51, "total_tokens": 91009936} {"current_steps": 42165, "total_steps": 61300, "loss": 0.3377, "lr": 1.343072175355966e-05, "epoch": 6.878466557911908, "percentage": 68.78, "elapsed_time": "5:43:57", "remaining_time": "2:36:05", "throughput": 4410.55, "total_tokens": 91021456} {"current_steps": 42170, "total_steps": 61300, "loss": 0.3606, "lr": 1.342441228935038e-05, "epoch": 6.879282218597064, "percentage": 68.79, "elapsed_time": "5:43:59", "remaining_time": "2:36:02", "throughput": 4410.6, "total_tokens": 91032784} {"current_steps": 42175, "total_steps": 61300, "loss": 0.3351, "lr": 1.3418103763516979e-05, "epoch": 6.880097879282219, "percentage": 68.8, "elapsed_time": "5:44:01", "remaining_time": "2:36:00", "throughput": 4410.65, "total_tokens": 91043952} {"current_steps": 42180, "total_steps": 61300, "loss": 0.3417, "lr": 1.3411796176570852e-05, "epoch": 6.8809135399673735, "percentage": 68.81, "elapsed_time": "5:44:04", "remaining_time": "2:35:57", "throughput": 4410.68, "total_tokens": 91054704} {"current_steps": 42185, "total_steps": 61300, "loss": 0.3855, "lr": 1.3405489529023322e-05, "epoch": 6.881729200652528, "percentage": 68.82, "elapsed_time": "5:44:06", "remaining_time": "2:35:55", "throughput": 4410.72, "total_tokens": 91064176} {"current_steps": 42190, "total_steps": 61300, "loss": 0.3329, "lr": 1.339918382138564e-05, "epoch": 6.882544861337683, "percentage": 68.83, "elapsed_time": "5:44:08", "remaining_time": "2:35:52", "throughput": 4410.76, "total_tokens": 91074768} {"current_steps": 42195, "total_steps": 61300, "loss": 0.3482, "lr": 1.3392879054168983e-05, "epoch": 6.883360522022839, "percentage": 68.83, "elapsed_time": "5:44:10", "remaining_time": "2:35:50", "throughput": 4410.81, "total_tokens": 91085520} {"current_steps": 42200, "total_steps": 61300, "loss": 0.3177, "lr": 1.3386575227884443e-05, "epoch": 6.884176182707994, "percentage": 68.84, "elapsed_time": "5:44:12", "remaining_time": "2:35:47", "throughput": 4410.85, "total_tokens": 91094800} {"current_steps": 42205, "total_steps": 61300, "loss": 0.3149, "lr": 1.3380272343043032e-05, "epoch": 6.8849918433931485, "percentage": 68.85, "elapsed_time": "5:44:14", "remaining_time": "2:35:44", "throughput": 4410.89, "total_tokens": 91105840} {"current_steps": 42210, "total_steps": 61300, "loss": 0.3414, "lr": 1.337397040015571e-05, "epoch": 6.885807504078303, "percentage": 68.86, "elapsed_time": "5:44:17", "remaining_time": "2:35:42", "throughput": 4410.93, "total_tokens": 91116624} {"current_steps": 42215, "total_steps": 61300, "loss": 0.3635, "lr": 1.336766939973334e-05, "epoch": 6.886623164763458, "percentage": 68.87, "elapsed_time": "5:44:19", "remaining_time": "2:35:39", "throughput": 4410.97, "total_tokens": 91128176} {"current_steps": 42220, "total_steps": 61300, "loss": 0.3861, "lr": 1.3361369342286706e-05, "epoch": 6.887438825448614, "percentage": 68.87, "elapsed_time": "5:44:21", "remaining_time": "2:35:37", "throughput": 4411.0, "total_tokens": 91138544} {"current_steps": 42225, "total_steps": 61300, "loss": 0.3172, "lr": 1.3355070228326533e-05, "epoch": 6.888254486133769, "percentage": 68.88, "elapsed_time": "5:44:23", "remaining_time": "2:35:34", "throughput": 4411.04, "total_tokens": 91148624} {"current_steps": 42230, "total_steps": 61300, "loss": 0.3213, "lr": 1.3348772058363448e-05, "epoch": 6.8890701468189235, "percentage": 68.89, "elapsed_time": "5:44:25", "remaining_time": "2:35:32", "throughput": 4411.08, "total_tokens": 91158672} {"current_steps": 42235, "total_steps": 61300, "loss": 0.3494, "lr": 1.334247483290802e-05, "epoch": 6.889885807504078, "percentage": 68.9, "elapsed_time": "5:44:28", "remaining_time": "2:35:29", "throughput": 4411.13, "total_tokens": 91169648} {"current_steps": 42240, "total_steps": 61300, "loss": 0.3565, "lr": 1.3336178552470729e-05, "epoch": 6.890701468189233, "percentage": 68.91, "elapsed_time": "5:44:30", "remaining_time": "2:35:27", "throughput": 4411.18, "total_tokens": 91180496} {"current_steps": 42245, "total_steps": 61300, "loss": 0.3556, "lr": 1.332988321756198e-05, "epoch": 6.891517128874388, "percentage": 68.92, "elapsed_time": "5:44:32", "remaining_time": "2:35:24", "throughput": 4411.23, "total_tokens": 91191440} {"current_steps": 42250, "total_steps": 61300, "loss": 0.3357, "lr": 1.3323588828692119e-05, "epoch": 6.892332789559543, "percentage": 68.92, "elapsed_time": "5:44:34", "remaining_time": "2:35:21", "throughput": 4411.26, "total_tokens": 91201584} {"current_steps": 42255, "total_steps": 61300, "loss": 0.3411, "lr": 1.3317295386371396e-05, "epoch": 6.8931484502446985, "percentage": 68.93, "elapsed_time": "5:44:37", "remaining_time": "2:35:19", "throughput": 4411.31, "total_tokens": 91213104} {"current_steps": 42260, "total_steps": 61300, "loss": 0.3473, "lr": 1.3311002891109981e-05, "epoch": 6.893964110929853, "percentage": 68.94, "elapsed_time": "5:44:39", "remaining_time": "2:35:17", "throughput": 4411.36, "total_tokens": 91224560} {"current_steps": 42265, "total_steps": 61300, "loss": 0.3187, "lr": 1.3304711343417985e-05, "epoch": 6.894779771615008, "percentage": 68.95, "elapsed_time": "5:44:41", "remaining_time": "2:35:14", "throughput": 4411.4, "total_tokens": 91235824} {"current_steps": 42270, "total_steps": 61300, "loss": 0.3248, "lr": 1.329842074380543e-05, "epoch": 6.895595432300163, "percentage": 68.96, "elapsed_time": "5:44:44", "remaining_time": "2:35:12", "throughput": 4411.46, "total_tokens": 91247600} {"current_steps": 42275, "total_steps": 61300, "loss": 0.305, "lr": 1.3292131092782259e-05, "epoch": 6.896411092985318, "percentage": 68.96, "elapsed_time": "5:44:46", "remaining_time": "2:35:09", "throughput": 4411.51, "total_tokens": 91259120} {"current_steps": 42280, "total_steps": 61300, "loss": 0.3373, "lr": 1.328584239085835e-05, "epoch": 6.897226753670473, "percentage": 68.97, "elapsed_time": "5:44:48", "remaining_time": "2:35:06", "throughput": 4411.55, "total_tokens": 91269040} {"current_steps": 42285, "total_steps": 61300, "loss": 0.352, "lr": 1.327955463854349e-05, "epoch": 6.898042414355628, "percentage": 68.98, "elapsed_time": "5:44:51", "remaining_time": "2:35:04", "throughput": 4411.58, "total_tokens": 91280208} {"current_steps": 42290, "total_steps": 61300, "loss": 0.3339, "lr": 1.3273267836347403e-05, "epoch": 6.898858075040783, "percentage": 68.99, "elapsed_time": "5:44:53", "remaining_time": "2:35:01", "throughput": 4411.63, "total_tokens": 91291088} {"current_steps": 42295, "total_steps": 61300, "loss": 0.3417, "lr": 1.3266981984779725e-05, "epoch": 6.899673735725938, "percentage": 69.0, "elapsed_time": "5:44:55", "remaining_time": "2:34:59", "throughput": 4411.67, "total_tokens": 91302032} {"current_steps": 42300, "total_steps": 61300, "loss": 0.3249, "lr": 1.3260697084350018e-05, "epoch": 6.900489396411093, "percentage": 69.0, "elapsed_time": "5:44:57", "remaining_time": "2:34:56", "throughput": 4411.71, "total_tokens": 91313552} {"current_steps": 42305, "total_steps": 61300, "loss": 0.3657, "lr": 1.3254413135567773e-05, "epoch": 6.901305057096248, "percentage": 69.01, "elapsed_time": "5:45:00", "remaining_time": "2:34:54", "throughput": 4411.76, "total_tokens": 91323728} {"current_steps": 42310, "total_steps": 61300, "loss": 0.3566, "lr": 1.3248130138942394e-05, "epoch": 6.902120717781403, "percentage": 69.02, "elapsed_time": "5:45:02", "remaining_time": "2:34:51", "throughput": 4411.8, "total_tokens": 91334960} {"current_steps": 42315, "total_steps": 61300, "loss": 0.3475, "lr": 1.3241848094983206e-05, "epoch": 6.902936378466558, "percentage": 69.03, "elapsed_time": "5:45:04", "remaining_time": "2:34:49", "throughput": 4411.85, "total_tokens": 91346896} {"current_steps": 42320, "total_steps": 61300, "loss": 0.3189, "lr": 1.3235567004199481e-05, "epoch": 6.903752039151713, "percentage": 69.04, "elapsed_time": "5:45:07", "remaining_time": "2:34:46", "throughput": 4411.89, "total_tokens": 91357168} {"current_steps": 42325, "total_steps": 61300, "loss": 0.3422, "lr": 1.3229286867100388e-05, "epoch": 6.904567699836868, "percentage": 69.05, "elapsed_time": "5:45:09", "remaining_time": "2:34:44", "throughput": 4411.94, "total_tokens": 91368688} {"current_steps": 42330, "total_steps": 61300, "loss": 0.3522, "lr": 1.3223007684195021e-05, "epoch": 6.9053833605220225, "percentage": 69.05, "elapsed_time": "5:45:11", "remaining_time": "2:34:41", "throughput": 4411.98, "total_tokens": 91379600} {"current_steps": 42335, "total_steps": 61300, "loss": 0.3636, "lr": 1.321672945599241e-05, "epoch": 6.906199021207177, "percentage": 69.06, "elapsed_time": "5:45:13", "remaining_time": "2:34:39", "throughput": 4412.03, "total_tokens": 91389872} {"current_steps": 42340, "total_steps": 61300, "loss": 0.3414, "lr": 1.3210452183001497e-05, "epoch": 6.907014681892333, "percentage": 69.07, "elapsed_time": "5:45:16", "remaining_time": "2:34:36", "throughput": 4412.07, "total_tokens": 91400944} {"current_steps": 42345, "total_steps": 61300, "loss": 0.3416, "lr": 1.320417586573115e-05, "epoch": 6.907830342577488, "percentage": 69.08, "elapsed_time": "5:45:18", "remaining_time": "2:34:34", "throughput": 4412.13, "total_tokens": 91412080} {"current_steps": 42350, "total_steps": 61300, "loss": 0.3417, "lr": 1.3197900504690161e-05, "epoch": 6.908646003262643, "percentage": 69.09, "elapsed_time": "5:45:20", "remaining_time": "2:34:31", "throughput": 4412.18, "total_tokens": 91423952} {"current_steps": 42355, "total_steps": 61300, "loss": 0.3425, "lr": 1.3191626100387238e-05, "epoch": 6.9094616639477975, "percentage": 69.09, "elapsed_time": "5:45:23", "remaining_time": "2:34:29", "throughput": 4412.22, "total_tokens": 91434480} {"current_steps": 42360, "total_steps": 61300, "loss": 0.3353, "lr": 1.3185352653331018e-05, "epoch": 6.910277324632952, "percentage": 69.1, "elapsed_time": "5:45:25", "remaining_time": "2:34:26", "throughput": 4412.26, "total_tokens": 91444464} {"current_steps": 42365, "total_steps": 61300, "loss": 0.3251, "lr": 1.3179080164030059e-05, "epoch": 6.911092985318108, "percentage": 69.11, "elapsed_time": "5:45:26", "remaining_time": "2:34:23", "throughput": 4412.29, "total_tokens": 91453104} {"current_steps": 42370, "total_steps": 61300, "loss": 0.3093, "lr": 1.317280863299284e-05, "epoch": 6.911908646003263, "percentage": 69.12, "elapsed_time": "5:45:28", "remaining_time": "2:34:21", "throughput": 4412.34, "total_tokens": 91463120} {"current_steps": 42375, "total_steps": 61300, "loss": 0.3624, "lr": 1.3166538060727765e-05, "epoch": 6.912724306688418, "percentage": 69.13, "elapsed_time": "5:45:31", "remaining_time": "2:34:18", "throughput": 4412.38, "total_tokens": 91473104} {"current_steps": 42380, "total_steps": 61300, "loss": 0.348, "lr": 1.3160268447743157e-05, "epoch": 6.9135399673735725, "percentage": 69.14, "elapsed_time": "5:45:33", "remaining_time": "2:34:16", "throughput": 4412.42, "total_tokens": 91484304} {"current_steps": 42385, "total_steps": 61300, "loss": 0.3444, "lr": 1.3153999794547261e-05, "epoch": 6.914355628058727, "percentage": 69.14, "elapsed_time": "5:45:35", "remaining_time": "2:34:13", "throughput": 4412.47, "total_tokens": 91495536} {"current_steps": 42390, "total_steps": 61300, "loss": 0.3288, "lr": 1.3147732101648242e-05, "epoch": 6.915171288743883, "percentage": 69.15, "elapsed_time": "5:45:37", "remaining_time": "2:34:11", "throughput": 4412.51, "total_tokens": 91505392} {"current_steps": 42395, "total_steps": 61300, "loss": 0.3238, "lr": 1.31414653695542e-05, "epoch": 6.915986949429038, "percentage": 69.16, "elapsed_time": "5:45:40", "remaining_time": "2:34:08", "throughput": 4412.55, "total_tokens": 91517200} {"current_steps": 42400, "total_steps": 61300, "loss": 0.3324, "lr": 1.3135199598773152e-05, "epoch": 6.916802610114193, "percentage": 69.17, "elapsed_time": "5:45:42", "remaining_time": "2:34:06", "throughput": 4412.6, "total_tokens": 91528592} {"current_steps": 42405, "total_steps": 61300, "loss": 0.3794, "lr": 1.3128934789813021e-05, "epoch": 6.917618270799347, "percentage": 69.18, "elapsed_time": "5:45:44", "remaining_time": "2:34:03", "throughput": 4412.64, "total_tokens": 91539216} {"current_steps": 42410, "total_steps": 61300, "loss": 0.3142, "lr": 1.312267094318167e-05, "epoch": 6.918433931484502, "percentage": 69.18, "elapsed_time": "5:45:46", "remaining_time": "2:34:00", "throughput": 4412.68, "total_tokens": 91549616} {"current_steps": 42415, "total_steps": 61300, "loss": 0.3482, "lr": 1.3116408059386881e-05, "epoch": 6.919249592169657, "percentage": 69.19, "elapsed_time": "5:45:49", "remaining_time": "2:33:58", "throughput": 4412.72, "total_tokens": 91560496} {"current_steps": 42420, "total_steps": 61300, "loss": 0.3254, "lr": 1.3110146138936335e-05, "epoch": 6.920065252854813, "percentage": 69.2, "elapsed_time": "5:45:51", "remaining_time": "2:33:55", "throughput": 4412.76, "total_tokens": 91571408} {"current_steps": 42425, "total_steps": 61300, "loss": 0.3435, "lr": 1.3103885182337688e-05, "epoch": 6.920880913539968, "percentage": 69.21, "elapsed_time": "5:45:53", "remaining_time": "2:33:53", "throughput": 4412.8, "total_tokens": 91580496} {"current_steps": 42430, "total_steps": 61300, "loss": 0.3566, "lr": 1.3097625190098464e-05, "epoch": 6.921696574225122, "percentage": 69.22, "elapsed_time": "5:45:55", "remaining_time": "2:33:50", "throughput": 4412.85, "total_tokens": 91591984} {"current_steps": 42435, "total_steps": 61300, "loss": 0.3138, "lr": 1.3091366162726136e-05, "epoch": 6.922512234910277, "percentage": 69.23, "elapsed_time": "5:45:57", "remaining_time": "2:33:48", "throughput": 4412.89, "total_tokens": 91602672} {"current_steps": 42440, "total_steps": 61300, "loss": 0.3091, "lr": 1.3085108100728089e-05, "epoch": 6.923327895595432, "percentage": 69.23, "elapsed_time": "5:46:00", "remaining_time": "2:33:45", "throughput": 4412.94, "total_tokens": 91612752} {"current_steps": 42445, "total_steps": 61300, "loss": 0.3391, "lr": 1.3078851004611636e-05, "epoch": 6.924143556280587, "percentage": 69.24, "elapsed_time": "5:46:02", "remaining_time": "2:33:43", "throughput": 4412.98, "total_tokens": 91623184} {"current_steps": 42450, "total_steps": 61300, "loss": 0.3333, "lr": 1.3072594874884008e-05, "epoch": 6.924959216965743, "percentage": 69.25, "elapsed_time": "5:46:04", "remaining_time": "2:33:40", "throughput": 4413.02, "total_tokens": 91633488} {"current_steps": 42455, "total_steps": 61300, "loss": 0.3429, "lr": 1.3066339712052359e-05, "epoch": 6.925774877650897, "percentage": 69.26, "elapsed_time": "5:46:06", "remaining_time": "2:33:38", "throughput": 4413.06, "total_tokens": 91645456} {"current_steps": 42460, "total_steps": 61300, "loss": 0.3122, "lr": 1.3060085516623763e-05, "epoch": 6.926590538336052, "percentage": 69.27, "elapsed_time": "5:46:09", "remaining_time": "2:33:35", "throughput": 4413.1, "total_tokens": 91656016} {"current_steps": 42465, "total_steps": 61300, "loss": 0.3416, "lr": 1.3053832289105216e-05, "epoch": 6.927406199021207, "percentage": 69.27, "elapsed_time": "5:46:11", "remaining_time": "2:33:33", "throughput": 4413.15, "total_tokens": 91667728} {"current_steps": 42470, "total_steps": 61300, "loss": 0.3363, "lr": 1.3047580030003642e-05, "epoch": 6.928221859706362, "percentage": 69.28, "elapsed_time": "5:46:13", "remaining_time": "2:33:30", "throughput": 4413.2, "total_tokens": 91679280} {"current_steps": 42475, "total_steps": 61300, "loss": 0.3208, "lr": 1.3041328739825873e-05, "epoch": 6.9290375203915175, "percentage": 69.29, "elapsed_time": "5:46:16", "remaining_time": "2:33:28", "throughput": 4413.24, "total_tokens": 91690032} {"current_steps": 42480, "total_steps": 61300, "loss": 0.3418, "lr": 1.3035078419078675e-05, "epoch": 6.929853181076672, "percentage": 69.3, "elapsed_time": "5:46:18", "remaining_time": "2:33:25", "throughput": 4413.29, "total_tokens": 91700944} {"current_steps": 42485, "total_steps": 61300, "loss": 0.3431, "lr": 1.302882906826873e-05, "epoch": 6.930668841761827, "percentage": 69.31, "elapsed_time": "5:46:20", "remaining_time": "2:33:22", "throughput": 4413.32, "total_tokens": 91710096} {"current_steps": 42490, "total_steps": 61300, "loss": 0.3455, "lr": 1.3022580687902641e-05, "epoch": 6.931484502446982, "percentage": 69.31, "elapsed_time": "5:46:22", "remaining_time": "2:33:20", "throughput": 4413.36, "total_tokens": 91719856} {"current_steps": 42495, "total_steps": 61300, "loss": 0.333, "lr": 1.3016333278486936e-05, "epoch": 6.932300163132137, "percentage": 69.32, "elapsed_time": "5:46:24", "remaining_time": "2:33:17", "throughput": 4413.41, "total_tokens": 91730448} {"current_steps": 42500, "total_steps": 61300, "loss": 0.3068, "lr": 1.301008684052806e-05, "epoch": 6.933115823817292, "percentage": 69.33, "elapsed_time": "5:46:26", "remaining_time": "2:33:15", "throughput": 4413.45, "total_tokens": 91742256} {"current_steps": 42505, "total_steps": 61300, "loss": 0.365, "lr": 1.300384137453238e-05, "epoch": 6.933931484502447, "percentage": 69.34, "elapsed_time": "5:46:29", "remaining_time": "2:33:12", "throughput": 4413.5, "total_tokens": 91752848} {"current_steps": 42510, "total_steps": 61300, "loss": 0.3504, "lr": 1.2997596881006185e-05, "epoch": 6.934747145187602, "percentage": 69.35, "elapsed_time": "5:46:31", "remaining_time": "2:33:10", "throughput": 4413.54, "total_tokens": 91764240} {"current_steps": 42515, "total_steps": 61300, "loss": 0.3493, "lr": 1.2991353360455688e-05, "epoch": 6.935562805872757, "percentage": 69.36, "elapsed_time": "5:46:33", "remaining_time": "2:33:07", "throughput": 4413.59, "total_tokens": 91775696} {"current_steps": 42520, "total_steps": 61300, "loss": 0.3344, "lr": 1.298511081338702e-05, "epoch": 6.936378466557912, "percentage": 69.36, "elapsed_time": "5:46:36", "remaining_time": "2:33:05", "throughput": 4413.63, "total_tokens": 91786576} {"current_steps": 42525, "total_steps": 61300, "loss": 0.3274, "lr": 1.2978869240306219e-05, "epoch": 6.937194127243067, "percentage": 69.37, "elapsed_time": "5:46:38", "remaining_time": "2:33:02", "throughput": 4413.68, "total_tokens": 91796880} {"current_steps": 42530, "total_steps": 61300, "loss": 0.3262, "lr": 1.2972628641719286e-05, "epoch": 6.938009787928221, "percentage": 69.38, "elapsed_time": "5:46:40", "remaining_time": "2:32:59", "throughput": 4413.72, "total_tokens": 91807344} {"current_steps": 42535, "total_steps": 61300, "loss": 0.3282, "lr": 1.2966389018132097e-05, "epoch": 6.938825448613377, "percentage": 69.39, "elapsed_time": "5:46:42", "remaining_time": "2:32:57", "throughput": 4413.76, "total_tokens": 91818640} {"current_steps": 42540, "total_steps": 61300, "loss": 0.3506, "lr": 1.2960150370050475e-05, "epoch": 6.939641109298532, "percentage": 69.4, "elapsed_time": "5:46:45", "remaining_time": "2:32:54", "throughput": 4413.8, "total_tokens": 91829616} {"current_steps": 42545, "total_steps": 61300, "loss": 0.3215, "lr": 1.2953912697980152e-05, "epoch": 6.940456769983687, "percentage": 69.4, "elapsed_time": "5:46:47", "remaining_time": "2:32:52", "throughput": 4413.83, "total_tokens": 91839376} {"current_steps": 42550, "total_steps": 61300, "loss": 0.3064, "lr": 1.2947676002426789e-05, "epoch": 6.941272430668842, "percentage": 69.41, "elapsed_time": "5:46:49", "remaining_time": "2:32:49", "throughput": 4413.87, "total_tokens": 91849776} {"current_steps": 42555, "total_steps": 61300, "loss": 0.3152, "lr": 1.2941440283895961e-05, "epoch": 6.942088091353996, "percentage": 69.42, "elapsed_time": "5:46:51", "remaining_time": "2:32:47", "throughput": 4413.92, "total_tokens": 91861520} {"current_steps": 42560, "total_steps": 61300, "loss": 0.3387, "lr": 1.2935205542893158e-05, "epoch": 6.942903752039152, "percentage": 69.43, "elapsed_time": "5:46:54", "remaining_time": "2:32:44", "throughput": 4413.98, "total_tokens": 91872880} {"current_steps": 42565, "total_steps": 61300, "loss": 0.3503, "lr": 1.2928971779923821e-05, "epoch": 6.943719412724307, "percentage": 69.44, "elapsed_time": "5:46:56", "remaining_time": "2:32:42", "throughput": 4414.02, "total_tokens": 91884016} {"current_steps": 42570, "total_steps": 61300, "loss": 0.3615, "lr": 1.2922738995493277e-05, "epoch": 6.944535073409462, "percentage": 69.45, "elapsed_time": "5:46:58", "remaining_time": "2:32:39", "throughput": 4414.07, "total_tokens": 91895504} {"current_steps": 42575, "total_steps": 61300, "loss": 0.3867, "lr": 1.2916507190106792e-05, "epoch": 6.945350734094617, "percentage": 69.45, "elapsed_time": "5:47:01", "remaining_time": "2:32:37", "throughput": 4414.11, "total_tokens": 91906288} {"current_steps": 42580, "total_steps": 61300, "loss": 0.3422, "lr": 1.2910276364269546e-05, "epoch": 6.946166394779771, "percentage": 69.46, "elapsed_time": "5:47:03", "remaining_time": "2:32:34", "throughput": 4414.16, "total_tokens": 91916752} {"current_steps": 42585, "total_steps": 61300, "loss": 0.323, "lr": 1.2904046518486637e-05, "epoch": 6.946982055464927, "percentage": 69.47, "elapsed_time": "5:47:05", "remaining_time": "2:32:32", "throughput": 4414.19, "total_tokens": 91926992} {"current_steps": 42590, "total_steps": 61300, "loss": 0.356, "lr": 1.2897817653263095e-05, "epoch": 6.947797716150082, "percentage": 69.48, "elapsed_time": "5:47:07", "remaining_time": "2:32:29", "throughput": 4414.23, "total_tokens": 91935504} {"current_steps": 42595, "total_steps": 61300, "loss": 0.3472, "lr": 1.2891589769103856e-05, "epoch": 6.948613376835237, "percentage": 69.49, "elapsed_time": "5:47:09", "remaining_time": "2:32:26", "throughput": 4414.28, "total_tokens": 91946320} {"current_steps": 42600, "total_steps": 61300, "loss": 0.2888, "lr": 1.288536286651379e-05, "epoch": 6.9494290375203915, "percentage": 69.49, "elapsed_time": "5:47:11", "remaining_time": "2:32:24", "throughput": 4414.32, "total_tokens": 91957008} {"current_steps": 42605, "total_steps": 61300, "loss": 0.3179, "lr": 1.2879136945997677e-05, "epoch": 6.950244698205546, "percentage": 69.5, "elapsed_time": "5:47:13", "remaining_time": "2:32:21", "throughput": 4414.36, "total_tokens": 91967824} {"current_steps": 42610, "total_steps": 61300, "loss": 0.3008, "lr": 1.2872912008060228e-05, "epoch": 6.951060358890701, "percentage": 69.51, "elapsed_time": "5:47:16", "remaining_time": "2:32:19", "throughput": 4414.41, "total_tokens": 91979024} {"current_steps": 42615, "total_steps": 61300, "loss": 0.3434, "lr": 1.286668805320606e-05, "epoch": 6.951876019575856, "percentage": 69.52, "elapsed_time": "5:47:18", "remaining_time": "2:32:16", "throughput": 4414.46, "total_tokens": 91990288} {"current_steps": 42620, "total_steps": 61300, "loss": 0.2761, "lr": 1.2860465081939727e-05, "epoch": 6.952691680261012, "percentage": 69.53, "elapsed_time": "5:47:20", "remaining_time": "2:32:14", "throughput": 4414.5, "total_tokens": 92000592} {"current_steps": 42625, "total_steps": 61300, "loss": 0.3058, "lr": 1.2854243094765683e-05, "epoch": 6.9535073409461665, "percentage": 69.54, "elapsed_time": "5:47:22", "remaining_time": "2:32:11", "throughput": 4414.53, "total_tokens": 92009520} {"current_steps": 42630, "total_steps": 61300, "loss": 0.3594, "lr": 1.2848022092188328e-05, "epoch": 6.954323001631321, "percentage": 69.54, "elapsed_time": "5:47:24", "remaining_time": "2:32:09", "throughput": 4414.59, "total_tokens": 92020848} {"current_steps": 42635, "total_steps": 61300, "loss": 0.3588, "lr": 1.2841802074711945e-05, "epoch": 6.955138662316476, "percentage": 69.55, "elapsed_time": "5:47:26", "remaining_time": "2:32:06", "throughput": 4414.63, "total_tokens": 92030384} {"current_steps": 42640, "total_steps": 61300, "loss": 0.3042, "lr": 1.2835583042840788e-05, "epoch": 6.955954323001631, "percentage": 69.56, "elapsed_time": "5:47:28", "remaining_time": "2:32:03", "throughput": 4414.67, "total_tokens": 92040528} {"current_steps": 42645, "total_steps": 61300, "loss": 0.3506, "lr": 1.282936499707899e-05, "epoch": 6.956769983686787, "percentage": 69.57, "elapsed_time": "5:47:31", "remaining_time": "2:32:01", "throughput": 4414.71, "total_tokens": 92052368} {"current_steps": 42650, "total_steps": 61300, "loss": 0.2677, "lr": 1.282314793793062e-05, "epoch": 6.9575856443719415, "percentage": 69.58, "elapsed_time": "5:47:33", "remaining_time": "2:31:58", "throughput": 4414.76, "total_tokens": 92063152} {"current_steps": 42655, "total_steps": 61300, "loss": 0.3658, "lr": 1.2816931865899662e-05, "epoch": 6.958401305057096, "percentage": 69.58, "elapsed_time": "5:47:35", "remaining_time": "2:31:56", "throughput": 4414.8, "total_tokens": 92073296} {"current_steps": 42660, "total_steps": 61300, "loss": 0.3339, "lr": 1.2810716781490024e-05, "epoch": 6.959216965742251, "percentage": 69.59, "elapsed_time": "5:47:37", "remaining_time": "2:31:53", "throughput": 4414.85, "total_tokens": 92084176} {"current_steps": 42665, "total_steps": 61300, "loss": 0.3623, "lr": 1.2804502685205532e-05, "epoch": 6.960032626427406, "percentage": 69.6, "elapsed_time": "5:47:40", "remaining_time": "2:31:51", "throughput": 4414.89, "total_tokens": 92095344} {"current_steps": 42670, "total_steps": 61300, "loss": 0.2973, "lr": 1.2798289577549932e-05, "epoch": 6.960848287112562, "percentage": 69.61, "elapsed_time": "5:47:42", "remaining_time": "2:31:48", "throughput": 4414.94, "total_tokens": 92106384} {"current_steps": 42675, "total_steps": 61300, "loss": 0.3767, "lr": 1.2792077459026886e-05, "epoch": 6.9616639477977165, "percentage": 69.62, "elapsed_time": "5:47:44", "remaining_time": "2:31:46", "throughput": 4414.98, "total_tokens": 92117104} {"current_steps": 42680, "total_steps": 61300, "loss": 0.3276, "lr": 1.278586633013999e-05, "epoch": 6.962479608482871, "percentage": 69.62, "elapsed_time": "5:47:46", "remaining_time": "2:31:43", "throughput": 4415.02, "total_tokens": 92127600} {"current_steps": 42685, "total_steps": 61300, "loss": 0.3317, "lr": 1.2779656191392736e-05, "epoch": 6.963295269168026, "percentage": 69.63, "elapsed_time": "5:47:49", "remaining_time": "2:31:41", "throughput": 4415.07, "total_tokens": 92138448} {"current_steps": 42690, "total_steps": 61300, "loss": 0.2978, "lr": 1.2773447043288561e-05, "epoch": 6.964110929853181, "percentage": 69.64, "elapsed_time": "5:47:51", "remaining_time": "2:31:38", "throughput": 4415.1, "total_tokens": 92148144} {"current_steps": 42695, "total_steps": 61300, "loss": 0.3719, "lr": 1.2767238886330805e-05, "epoch": 6.964926590538336, "percentage": 69.65, "elapsed_time": "5:47:53", "remaining_time": "2:31:35", "throughput": 4415.14, "total_tokens": 92158640} {"current_steps": 42700, "total_steps": 61300, "loss": 0.3184, "lr": 1.2761031721022732e-05, "epoch": 6.9657422512234906, "percentage": 69.66, "elapsed_time": "5:47:55", "remaining_time": "2:31:33", "throughput": 4415.18, "total_tokens": 92169008} {"current_steps": 42705, "total_steps": 61300, "loss": 0.3312, "lr": 1.2754825547867519e-05, "epoch": 6.966557911908646, "percentage": 69.67, "elapsed_time": "5:47:57", "remaining_time": "2:31:30", "throughput": 4415.22, "total_tokens": 92180432} {"current_steps": 42710, "total_steps": 61300, "loss": 0.341, "lr": 1.2748620367368286e-05, "epoch": 6.967373572593801, "percentage": 69.67, "elapsed_time": "5:48:00", "remaining_time": "2:31:28", "throughput": 4415.27, "total_tokens": 92191376} {"current_steps": 42715, "total_steps": 61300, "loss": 0.3399, "lr": 1.2742416180028053e-05, "epoch": 6.968189233278956, "percentage": 69.68, "elapsed_time": "5:48:02", "remaining_time": "2:31:25", "throughput": 4415.31, "total_tokens": 92202256} {"current_steps": 42720, "total_steps": 61300, "loss": 0.3135, "lr": 1.2736212986349755e-05, "epoch": 6.969004893964111, "percentage": 69.69, "elapsed_time": "5:48:04", "remaining_time": "2:31:23", "throughput": 4415.35, "total_tokens": 92212400} {"current_steps": 42725, "total_steps": 61300, "loss": 0.3282, "lr": 1.2730010786836261e-05, "epoch": 6.9698205546492655, "percentage": 69.7, "elapsed_time": "5:48:06", "remaining_time": "2:31:20", "throughput": 4415.4, "total_tokens": 92223216} {"current_steps": 42730, "total_steps": 61300, "loss": 0.3475, "lr": 1.2723809581990348e-05, "epoch": 6.970636215334421, "percentage": 69.71, "elapsed_time": "5:48:09", "remaining_time": "2:31:18", "throughput": 4415.45, "total_tokens": 92234928} {"current_steps": 42735, "total_steps": 61300, "loss": 0.3155, "lr": 1.271760937231472e-05, "epoch": 6.971451876019576, "percentage": 69.71, "elapsed_time": "5:48:11", "remaining_time": "2:31:15", "throughput": 4415.49, "total_tokens": 92245392} {"current_steps": 42740, "total_steps": 61300, "loss": 0.3036, "lr": 1.2711410158311987e-05, "epoch": 6.972267536704731, "percentage": 69.72, "elapsed_time": "5:48:13", "remaining_time": "2:31:13", "throughput": 4415.53, "total_tokens": 92255824} {"current_steps": 42745, "total_steps": 61300, "loss": 0.3064, "lr": 1.2705211940484707e-05, "epoch": 6.973083197389886, "percentage": 69.73, "elapsed_time": "5:48:15", "remaining_time": "2:31:10", "throughput": 4415.57, "total_tokens": 92265904} {"current_steps": 42750, "total_steps": 61300, "loss": 0.3506, "lr": 1.2699014719335329e-05, "epoch": 6.9738988580750405, "percentage": 69.74, "elapsed_time": "5:48:17", "remaining_time": "2:31:07", "throughput": 4415.6, "total_tokens": 92276176} {"current_steps": 42755, "total_steps": 61300, "loss": 0.3226, "lr": 1.2692818495366236e-05, "epoch": 6.974714518760196, "percentage": 69.75, "elapsed_time": "5:48:19", "remaining_time": "2:31:05", "throughput": 4415.64, "total_tokens": 92285744} {"current_steps": 42760, "total_steps": 61300, "loss": 0.2931, "lr": 1.2686623269079717e-05, "epoch": 6.975530179445351, "percentage": 69.76, "elapsed_time": "5:48:22", "remaining_time": "2:31:02", "throughput": 4415.69, "total_tokens": 92298128} {"current_steps": 42765, "total_steps": 61300, "loss": 0.3301, "lr": 1.2680429040977998e-05, "epoch": 6.976345840130506, "percentage": 69.76, "elapsed_time": "5:48:24", "remaining_time": "2:31:00", "throughput": 4415.73, "total_tokens": 92308752} {"current_steps": 42770, "total_steps": 61300, "loss": 0.3329, "lr": 1.2674235811563206e-05, "epoch": 6.977161500815661, "percentage": 69.77, "elapsed_time": "5:48:26", "remaining_time": "2:30:57", "throughput": 4415.78, "total_tokens": 92319632} {"current_steps": 42775, "total_steps": 61300, "loss": 0.3154, "lr": 1.2668043581337401e-05, "epoch": 6.9779771615008155, "percentage": 69.78, "elapsed_time": "5:48:29", "remaining_time": "2:30:55", "throughput": 4415.83, "total_tokens": 92330576} {"current_steps": 42780, "total_steps": 61300, "loss": 0.3314, "lr": 1.2661852350802556e-05, "epoch": 6.97879282218597, "percentage": 69.79, "elapsed_time": "5:48:31", "remaining_time": "2:30:52", "throughput": 4415.86, "total_tokens": 92340304} {"current_steps": 42785, "total_steps": 61300, "loss": 0.354, "lr": 1.2655662120460564e-05, "epoch": 6.979608482871125, "percentage": 69.8, "elapsed_time": "5:48:33", "remaining_time": "2:30:50", "throughput": 4415.89, "total_tokens": 92350576} {"current_steps": 42790, "total_steps": 61300, "loss": 0.3445, "lr": 1.2649472890813232e-05, "epoch": 6.980424143556281, "percentage": 69.8, "elapsed_time": "5:48:35", "remaining_time": "2:30:47", "throughput": 4415.93, "total_tokens": 92359664} {"current_steps": 42795, "total_steps": 61300, "loss": 0.34, "lr": 1.2643284662362295e-05, "epoch": 6.981239804241436, "percentage": 69.81, "elapsed_time": "5:48:37", "remaining_time": "2:30:44", "throughput": 4415.96, "total_tokens": 92370032} {"current_steps": 42800, "total_steps": 61300, "loss": 0.3575, "lr": 1.2637097435609402e-05, "epoch": 6.9820554649265905, "percentage": 69.82, "elapsed_time": "5:48:39", "remaining_time": "2:30:42", "throughput": 4416.0, "total_tokens": 92380976} {"current_steps": 42805, "total_steps": 61300, "loss": 0.3279, "lr": 1.2630911211056116e-05, "epoch": 6.982871125611745, "percentage": 69.83, "elapsed_time": "5:48:42", "remaining_time": "2:30:39", "throughput": 4416.05, "total_tokens": 92393136} {"current_steps": 42810, "total_steps": 61300, "loss": 0.3573, "lr": 1.2624725989203929e-05, "epoch": 6.9836867862969, "percentage": 69.84, "elapsed_time": "5:48:44", "remaining_time": "2:30:37", "throughput": 4416.09, "total_tokens": 92404208} {"current_steps": 42815, "total_steps": 61300, "loss": 0.3701, "lr": 1.2618541770554243e-05, "epoch": 6.984502446982056, "percentage": 69.85, "elapsed_time": "5:48:46", "remaining_time": "2:30:34", "throughput": 4416.13, "total_tokens": 92415152} {"current_steps": 42820, "total_steps": 61300, "loss": 0.3285, "lr": 1.2612358555608388e-05, "epoch": 6.985318107667211, "percentage": 69.85, "elapsed_time": "5:48:48", "remaining_time": "2:30:32", "throughput": 4416.18, "total_tokens": 92426192} {"current_steps": 42825, "total_steps": 61300, "loss": 0.3152, "lr": 1.2606176344867598e-05, "epoch": 6.986133768352365, "percentage": 69.86, "elapsed_time": "5:48:51", "remaining_time": "2:30:29", "throughput": 4416.23, "total_tokens": 92438064} {"current_steps": 42830, "total_steps": 61300, "loss": 0.32, "lr": 1.2599995138833043e-05, "epoch": 6.98694942903752, "percentage": 69.87, "elapsed_time": "5:48:53", "remaining_time": "2:30:27", "throughput": 4416.25, "total_tokens": 92447280} {"current_steps": 42835, "total_steps": 61300, "loss": 0.3646, "lr": 1.25938149380058e-05, "epoch": 6.987765089722675, "percentage": 69.88, "elapsed_time": "5:48:55", "remaining_time": "2:30:24", "throughput": 4416.3, "total_tokens": 92458416} {"current_steps": 42840, "total_steps": 61300, "loss": 0.349, "lr": 1.258763574288686e-05, "epoch": 6.988580750407831, "percentage": 69.89, "elapsed_time": "5:48:58", "remaining_time": "2:30:22", "throughput": 4416.35, "total_tokens": 92469680} {"current_steps": 42845, "total_steps": 61300, "loss": 0.398, "lr": 1.2581457553977144e-05, "epoch": 6.989396411092986, "percentage": 69.89, "elapsed_time": "5:49:00", "remaining_time": "2:30:19", "throughput": 4416.39, "total_tokens": 92480592} {"current_steps": 42850, "total_steps": 61300, "loss": 0.3422, "lr": 1.2575280371777496e-05, "epoch": 6.99021207177814, "percentage": 69.9, "elapsed_time": "5:49:02", "remaining_time": "2:30:17", "throughput": 4416.43, "total_tokens": 92492336} {"current_steps": 42855, "total_steps": 61300, "loss": 0.3648, "lr": 1.2569104196788665e-05, "epoch": 6.991027732463295, "percentage": 69.91, "elapsed_time": "5:49:04", "remaining_time": "2:30:14", "throughput": 4416.47, "total_tokens": 92502608} {"current_steps": 42860, "total_steps": 61300, "loss": 0.3444, "lr": 1.256292902951132e-05, "epoch": 6.99184339314845, "percentage": 69.92, "elapsed_time": "5:49:07", "remaining_time": "2:30:12", "throughput": 4416.52, "total_tokens": 92513520} {"current_steps": 42865, "total_steps": 61300, "loss": 0.3313, "lr": 1.2556754870446053e-05, "epoch": 6.992659053833605, "percentage": 69.93, "elapsed_time": "5:49:09", "remaining_time": "2:30:09", "throughput": 4416.57, "total_tokens": 92524656} {"current_steps": 42870, "total_steps": 61300, "loss": 0.3367, "lr": 1.255058172009337e-05, "epoch": 6.993474714518761, "percentage": 69.93, "elapsed_time": "5:49:11", "remaining_time": "2:30:07", "throughput": 4416.61, "total_tokens": 92535408} {"current_steps": 42875, "total_steps": 61300, "loss": 0.3315, "lr": 1.2544409578953697e-05, "epoch": 6.994290375203915, "percentage": 69.94, "elapsed_time": "5:49:13", "remaining_time": "2:30:04", "throughput": 4416.66, "total_tokens": 92545744} {"current_steps": 42880, "total_steps": 61300, "loss": 0.3358, "lr": 1.253823844752739e-05, "epoch": 6.99510603588907, "percentage": 69.95, "elapsed_time": "5:49:16", "remaining_time": "2:30:02", "throughput": 4416.69, "total_tokens": 92556432} {"current_steps": 42885, "total_steps": 61300, "loss": 0.3331, "lr": 1.25320683263147e-05, "epoch": 6.995921696574225, "percentage": 69.96, "elapsed_time": "5:49:18", "remaining_time": "2:29:59", "throughput": 4416.74, "total_tokens": 92568592} {"current_steps": 42890, "total_steps": 61300, "loss": 0.3561, "lr": 1.2525899215815818e-05, "epoch": 6.99673735725938, "percentage": 69.97, "elapsed_time": "5:49:20", "remaining_time": "2:29:57", "throughput": 4416.79, "total_tokens": 92579632} {"current_steps": 42895, "total_steps": 61300, "loss": 0.3294, "lr": 1.2519731116530837e-05, "epoch": 6.997553017944535, "percentage": 69.98, "elapsed_time": "5:49:23", "remaining_time": "2:29:54", "throughput": 4416.84, "total_tokens": 92591344} {"current_steps": 42900, "total_steps": 61300, "loss": 0.3519, "lr": 1.2513564028959777e-05, "epoch": 6.99836867862969, "percentage": 69.98, "elapsed_time": "5:49:25", "remaining_time": "2:29:52", "throughput": 4416.89, "total_tokens": 92601264} {"current_steps": 42905, "total_steps": 61300, "loss": 0.33, "lr": 1.2507397953602574e-05, "epoch": 6.999184339314845, "percentage": 69.99, "elapsed_time": "5:49:27", "remaining_time": "2:29:49", "throughput": 4416.94, "total_tokens": 92612464} {"current_steps": 42910, "total_steps": 61300, "loss": 0.3374, "lr": 1.2501232890959075e-05, "epoch": 7.0, "percentage": 70.0, "elapsed_time": "5:49:29", "remaining_time": "2:29:47", "throughput": 4416.94, "total_tokens": 92621824} {"current_steps": 42910, "total_steps": 61300, "eval_loss": 0.3413711190223694, "epoch": 7.0, "percentage": 70.0, "elapsed_time": "5:51:41", "remaining_time": "2:30:43", "throughput": 4389.3, "total_tokens": 92621824} {"current_steps": 42915, "total_steps": 61300, "loss": 0.355, "lr": 1.2495068841529058e-05, "epoch": 7.000815660685155, "percentage": 70.01, "elapsed_time": "5:51:45", "remaining_time": "2:30:41", "throughput": 4389.05, "total_tokens": 92633024} {"current_steps": 42920, "total_steps": 61300, "loss": 0.357, "lr": 1.248890580581221e-05, "epoch": 7.00163132137031, "percentage": 70.02, "elapsed_time": "5:51:47", "remaining_time": "2:30:39", "throughput": 4389.11, "total_tokens": 92644768} {"current_steps": 42925, "total_steps": 61300, "loss": 0.3105, "lr": 1.248274378430814e-05, "epoch": 7.002446982055465, "percentage": 70.02, "elapsed_time": "5:51:49", "remaining_time": "2:30:36", "throughput": 4389.15, "total_tokens": 92654240} {"current_steps": 42930, "total_steps": 61300, "loss": 0.3534, "lr": 1.2476582777516368e-05, "epoch": 7.00326264274062, "percentage": 70.03, "elapsed_time": "5:51:51", "remaining_time": "2:30:33", "throughput": 4389.2, "total_tokens": 92664288} {"current_steps": 42935, "total_steps": 61300, "loss": 0.3305, "lr": 1.2470422785936339e-05, "epoch": 7.004078303425775, "percentage": 70.04, "elapsed_time": "5:51:54", "remaining_time": "2:30:31", "throughput": 4389.24, "total_tokens": 92675104} {"current_steps": 42940, "total_steps": 61300, "loss": 0.3597, "lr": 1.2464263810067417e-05, "epoch": 7.00489396411093, "percentage": 70.05, "elapsed_time": "5:51:56", "remaining_time": "2:30:28", "throughput": 4389.28, "total_tokens": 92685056} {"current_steps": 42945, "total_steps": 61300, "loss": 0.3455, "lr": 1.2458105850408874e-05, "epoch": 7.005709624796085, "percentage": 70.06, "elapsed_time": "5:51:58", "remaining_time": "2:30:26", "throughput": 4389.33, "total_tokens": 92696000} {"current_steps": 42950, "total_steps": 61300, "loss": 0.3285, "lr": 1.2451948907459907e-05, "epoch": 7.006525285481239, "percentage": 70.07, "elapsed_time": "5:52:00", "remaining_time": "2:30:23", "throughput": 4389.37, "total_tokens": 92706272} {"current_steps": 42955, "total_steps": 61300, "loss": 0.347, "lr": 1.2445792981719622e-05, "epoch": 7.007340946166395, "percentage": 70.07, "elapsed_time": "5:52:02", "remaining_time": "2:30:21", "throughput": 4389.42, "total_tokens": 92717120} {"current_steps": 42960, "total_steps": 61300, "loss": 0.2935, "lr": 1.2439638073687065e-05, "epoch": 7.00815660685155, "percentage": 70.08, "elapsed_time": "5:52:04", "remaining_time": "2:30:18", "throughput": 4389.46, "total_tokens": 92726432} {"current_steps": 42965, "total_steps": 61300, "loss": 0.3629, "lr": 1.2433484183861178e-05, "epoch": 7.008972267536705, "percentage": 70.09, "elapsed_time": "5:52:06", "remaining_time": "2:30:15", "throughput": 4389.51, "total_tokens": 92736896} {"current_steps": 42970, "total_steps": 61300, "loss": 0.361, "lr": 1.2427331312740822e-05, "epoch": 7.00978792822186, "percentage": 70.1, "elapsed_time": "5:52:09", "remaining_time": "2:30:13", "throughput": 4389.55, "total_tokens": 92747904} {"current_steps": 42975, "total_steps": 61300, "loss": 0.3524, "lr": 1.2421179460824787e-05, "epoch": 7.010603588907014, "percentage": 70.11, "elapsed_time": "5:52:11", "remaining_time": "2:30:10", "throughput": 4389.59, "total_tokens": 92757920} {"current_steps": 42980, "total_steps": 61300, "loss": 0.3164, "lr": 1.2415028628611767e-05, "epoch": 7.011419249592169, "percentage": 70.11, "elapsed_time": "5:52:13", "remaining_time": "2:30:08", "throughput": 4389.63, "total_tokens": 92769664} {"current_steps": 42985, "total_steps": 61300, "loss": 0.3466, "lr": 1.2408878816600384e-05, "epoch": 7.012234910277325, "percentage": 70.12, "elapsed_time": "5:52:16", "remaining_time": "2:30:05", "throughput": 4389.67, "total_tokens": 92780256} {"current_steps": 42990, "total_steps": 61300, "loss": 0.3213, "lr": 1.2402730025289166e-05, "epoch": 7.01305057096248, "percentage": 70.13, "elapsed_time": "5:52:18", "remaining_time": "2:30:03", "throughput": 4389.73, "total_tokens": 92791744} {"current_steps": 42995, "total_steps": 61300, "loss": 0.3299, "lr": 1.2396582255176575e-05, "epoch": 7.013866231647635, "percentage": 70.14, "elapsed_time": "5:52:20", "remaining_time": "2:30:00", "throughput": 4389.77, "total_tokens": 92800928} {"current_steps": 43000, "total_steps": 61300, "loss": 0.3099, "lr": 1.2390435506760973e-05, "epoch": 7.014681892332789, "percentage": 70.15, "elapsed_time": "5:52:22", "remaining_time": "2:29:57", "throughput": 4389.82, "total_tokens": 92812352} {"current_steps": 43005, "total_steps": 61300, "loss": 0.2973, "lr": 1.238428978054065e-05, "epoch": 7.015497553017944, "percentage": 70.15, "elapsed_time": "5:52:24", "remaining_time": "2:29:55", "throughput": 4389.86, "total_tokens": 92822944} {"current_steps": 43010, "total_steps": 61300, "loss": 0.3285, "lr": 1.2378145077013808e-05, "epoch": 7.0163132137031, "percentage": 70.16, "elapsed_time": "5:52:26", "remaining_time": "2:29:52", "throughput": 4389.91, "total_tokens": 92832960} {"current_steps": 43015, "total_steps": 61300, "loss": 0.336, "lr": 1.237200139667857e-05, "epoch": 7.017128874388255, "percentage": 70.17, "elapsed_time": "5:52:29", "remaining_time": "2:29:50", "throughput": 4389.95, "total_tokens": 92843584} {"current_steps": 43020, "total_steps": 61300, "loss": 0.3215, "lr": 1.2365858740032962e-05, "epoch": 7.0179445350734095, "percentage": 70.18, "elapsed_time": "5:52:31", "remaining_time": "2:29:47", "throughput": 4389.99, "total_tokens": 92853440} {"current_steps": 43025, "total_steps": 61300, "loss": 0.3202, "lr": 1.2359717107574959e-05, "epoch": 7.018760195758564, "percentage": 70.19, "elapsed_time": "5:52:32", "remaining_time": "2:29:44", "throughput": 4390.03, "total_tokens": 92862112} {"current_steps": 43030, "total_steps": 61300, "loss": 0.3518, "lr": 1.2353576499802425e-05, "epoch": 7.019575856443719, "percentage": 70.2, "elapsed_time": "5:52:35", "remaining_time": "2:29:42", "throughput": 4390.07, "total_tokens": 92872000} {"current_steps": 43035, "total_steps": 61300, "loss": 0.327, "lr": 1.2347436917213145e-05, "epoch": 7.020391517128874, "percentage": 70.2, "elapsed_time": "5:52:37", "remaining_time": "2:29:39", "throughput": 4390.11, "total_tokens": 92881856} {"current_steps": 43040, "total_steps": 61300, "loss": 0.3049, "lr": 1.2341298360304828e-05, "epoch": 7.02120717781403, "percentage": 70.21, "elapsed_time": "5:52:39", "remaining_time": "2:29:36", "throughput": 4390.15, "total_tokens": 92892768} {"current_steps": 43045, "total_steps": 61300, "loss": 0.3531, "lr": 1.2335160829575096e-05, "epoch": 7.0220228384991845, "percentage": 70.22, "elapsed_time": "5:52:41", "remaining_time": "2:29:34", "throughput": 4390.2, "total_tokens": 92904384} {"current_steps": 43050, "total_steps": 61300, "loss": 0.3057, "lr": 1.2329024325521488e-05, "epoch": 7.022838499184339, "percentage": 70.23, "elapsed_time": "5:52:44", "remaining_time": "2:29:32", "throughput": 4390.25, "total_tokens": 92916160} {"current_steps": 43055, "total_steps": 61300, "loss": 0.3667, "lr": 1.2322888848641458e-05, "epoch": 7.023654159869494, "percentage": 70.24, "elapsed_time": "5:52:45", "remaining_time": "2:29:29", "throughput": 4390.28, "total_tokens": 92924640} {"current_steps": 43060, "total_steps": 61300, "loss": 0.3051, "lr": 1.2316754399432374e-05, "epoch": 7.024469820554649, "percentage": 70.24, "elapsed_time": "5:52:48", "remaining_time": "2:29:26", "throughput": 4390.32, "total_tokens": 92935264} {"current_steps": 43065, "total_steps": 61300, "loss": 0.342, "lr": 1.231062097839154e-05, "epoch": 7.025285481239805, "percentage": 70.25, "elapsed_time": "5:52:50", "remaining_time": "2:29:24", "throughput": 4390.37, "total_tokens": 92947232} {"current_steps": 43070, "total_steps": 61300, "loss": 0.3251, "lr": 1.2304488586016156e-05, "epoch": 7.0261011419249595, "percentage": 70.26, "elapsed_time": "5:52:53", "remaining_time": "2:29:21", "throughput": 4390.42, "total_tokens": 92958816} {"current_steps": 43075, "total_steps": 61300, "loss": 0.3417, "lr": 1.2298357222803341e-05, "epoch": 7.026916802610114, "percentage": 70.27, "elapsed_time": "5:52:55", "remaining_time": "2:29:19", "throughput": 4390.47, "total_tokens": 92969824} {"current_steps": 43080, "total_steps": 61300, "loss": 0.351, "lr": 1.2292226889250142e-05, "epoch": 7.027732463295269, "percentage": 70.28, "elapsed_time": "5:52:57", "remaining_time": "2:29:16", "throughput": 4390.52, "total_tokens": 92980928} {"current_steps": 43085, "total_steps": 61300, "loss": 0.3619, "lr": 1.2286097585853507e-05, "epoch": 7.028548123980424, "percentage": 70.29, "elapsed_time": "5:53:00", "remaining_time": "2:29:14", "throughput": 4390.56, "total_tokens": 92992480} {"current_steps": 43090, "total_steps": 61300, "loss": 0.3109, "lr": 1.2279969313110313e-05, "epoch": 7.029363784665579, "percentage": 70.29, "elapsed_time": "5:53:02", "remaining_time": "2:29:11", "throughput": 4390.62, "total_tokens": 93003232} {"current_steps": 43095, "total_steps": 61300, "loss": 0.3288, "lr": 1.2273842071517344e-05, "epoch": 7.0301794453507345, "percentage": 70.3, "elapsed_time": "5:53:04", "remaining_time": "2:29:09", "throughput": 4390.66, "total_tokens": 93013952} {"current_steps": 43100, "total_steps": 61300, "loss": 0.3446, "lr": 1.2267715861571311e-05, "epoch": 7.030995106035889, "percentage": 70.31, "elapsed_time": "5:53:06", "remaining_time": "2:29:06", "throughput": 4390.7, "total_tokens": 93024064} {"current_steps": 43105, "total_steps": 61300, "loss": 0.3179, "lr": 1.2261590683768831e-05, "epoch": 7.031810766721044, "percentage": 70.32, "elapsed_time": "5:53:09", "remaining_time": "2:29:04", "throughput": 4390.75, "total_tokens": 93036128} {"current_steps": 43110, "total_steps": 61300, "loss": 0.3632, "lr": 1.2255466538606447e-05, "epoch": 7.032626427406199, "percentage": 70.33, "elapsed_time": "5:53:11", "remaining_time": "2:29:01", "throughput": 4390.8, "total_tokens": 93047904} {"current_steps": 43115, "total_steps": 61300, "loss": 0.3202, "lr": 1.224934342658061e-05, "epoch": 7.033442088091354, "percentage": 70.33, "elapsed_time": "5:53:13", "remaining_time": "2:28:58", "throughput": 4390.84, "total_tokens": 93057568} {"current_steps": 43120, "total_steps": 61300, "loss": 0.3604, "lr": 1.224322134818769e-05, "epoch": 7.034257748776509, "percentage": 70.34, "elapsed_time": "5:53:15", "remaining_time": "2:28:56", "throughput": 4390.89, "total_tokens": 93068192} {"current_steps": 43125, "total_steps": 61300, "loss": 0.3649, "lr": 1.2237100303923977e-05, "epoch": 7.035073409461664, "percentage": 70.35, "elapsed_time": "5:53:18", "remaining_time": "2:28:53", "throughput": 4390.93, "total_tokens": 93080032} {"current_steps": 43130, "total_steps": 61300, "loss": 0.327, "lr": 1.2230980294285669e-05, "epoch": 7.035889070146819, "percentage": 70.36, "elapsed_time": "5:53:20", "remaining_time": "2:28:51", "throughput": 4390.97, "total_tokens": 93090784} {"current_steps": 43135, "total_steps": 61300, "loss": 0.3276, "lr": 1.2224861319768887e-05, "epoch": 7.036704730831974, "percentage": 70.37, "elapsed_time": "5:53:22", "remaining_time": "2:28:48", "throughput": 4391.02, "total_tokens": 93102176} {"current_steps": 43140, "total_steps": 61300, "loss": 0.327, "lr": 1.2218743380869669e-05, "epoch": 7.037520391517129, "percentage": 70.38, "elapsed_time": "5:53:25", "remaining_time": "2:28:46", "throughput": 4391.06, "total_tokens": 93112928} {"current_steps": 43145, "total_steps": 61300, "loss": 0.3401, "lr": 1.2212626478083964e-05, "epoch": 7.0383360522022835, "percentage": 70.38, "elapsed_time": "5:53:27", "remaining_time": "2:28:43", "throughput": 4391.11, "total_tokens": 93123872} {"current_steps": 43150, "total_steps": 61300, "loss": 0.3298, "lr": 1.2206510611907638e-05, "epoch": 7.039151712887439, "percentage": 70.39, "elapsed_time": "5:53:29", "remaining_time": "2:28:41", "throughput": 4391.16, "total_tokens": 93134368} {"current_steps": 43155, "total_steps": 61300, "loss": 0.3319, "lr": 1.2200395782836477e-05, "epoch": 7.039967373572594, "percentage": 70.4, "elapsed_time": "5:53:32", "remaining_time": "2:28:38", "throughput": 4391.21, "total_tokens": 93146720} {"current_steps": 43160, "total_steps": 61300, "loss": 0.3191, "lr": 1.2194281991366176e-05, "epoch": 7.040783034257749, "percentage": 70.41, "elapsed_time": "5:53:34", "remaining_time": "2:28:36", "throughput": 4391.26, "total_tokens": 93157632} {"current_steps": 43165, "total_steps": 61300, "loss": 0.3336, "lr": 1.2188169237992345e-05, "epoch": 7.041598694942904, "percentage": 70.42, "elapsed_time": "5:53:36", "remaining_time": "2:28:33", "throughput": 4391.3, "total_tokens": 93167264} {"current_steps": 43170, "total_steps": 61300, "loss": 0.343, "lr": 1.218205752321053e-05, "epoch": 7.0424143556280585, "percentage": 70.42, "elapsed_time": "5:53:38", "remaining_time": "2:28:31", "throughput": 4391.33, "total_tokens": 93179136} {"current_steps": 43175, "total_steps": 61300, "loss": 0.3459, "lr": 1.217594684751617e-05, "epoch": 7.043230016313213, "percentage": 70.43, "elapsed_time": "5:53:41", "remaining_time": "2:28:28", "throughput": 4391.38, "total_tokens": 93189536} {"current_steps": 43180, "total_steps": 61300, "loss": 0.3394, "lr": 1.2169837211404627e-05, "epoch": 7.044045676998369, "percentage": 70.44, "elapsed_time": "5:53:43", "remaining_time": "2:28:26", "throughput": 4391.43, "total_tokens": 93201568} {"current_steps": 43185, "total_steps": 61300, "loss": 0.3668, "lr": 1.2163728615371181e-05, "epoch": 7.044861337683524, "percentage": 70.45, "elapsed_time": "5:53:45", "remaining_time": "2:28:23", "throughput": 4391.48, "total_tokens": 93212128} {"current_steps": 43190, "total_steps": 61300, "loss": 0.3316, "lr": 1.2157621059911014e-05, "epoch": 7.045676998368679, "percentage": 70.46, "elapsed_time": "5:53:47", "remaining_time": "2:28:21", "throughput": 4391.52, "total_tokens": 93222784} {"current_steps": 43195, "total_steps": 61300, "loss": 0.3338, "lr": 1.2151514545519254e-05, "epoch": 7.0464926590538335, "percentage": 70.46, "elapsed_time": "5:53:50", "remaining_time": "2:28:18", "throughput": 4391.56, "total_tokens": 93234016} {"current_steps": 43200, "total_steps": 61300, "loss": 0.3264, "lr": 1.214540907269092e-05, "epoch": 7.047308319738988, "percentage": 70.47, "elapsed_time": "5:53:52", "remaining_time": "2:28:15", "throughput": 4391.59, "total_tokens": 93243200} {"current_steps": 43205, "total_steps": 61300, "loss": 0.3146, "lr": 1.2139304641920946e-05, "epoch": 7.048123980424143, "percentage": 70.48, "elapsed_time": "5:53:54", "remaining_time": "2:28:13", "throughput": 4391.64, "total_tokens": 93254432} {"current_steps": 43210, "total_steps": 61300, "loss": 0.3362, "lr": 1.2133201253704196e-05, "epoch": 7.048939641109299, "percentage": 70.49, "elapsed_time": "5:53:56", "remaining_time": "2:28:10", "throughput": 4391.67, "total_tokens": 93263360} {"current_steps": 43215, "total_steps": 61300, "loss": 0.3219, "lr": 1.2127098908535434e-05, "epoch": 7.049755301794454, "percentage": 70.5, "elapsed_time": "5:53:58", "remaining_time": "2:28:08", "throughput": 4391.72, "total_tokens": 93273376} {"current_steps": 43220, "total_steps": 61300, "loss": 0.3528, "lr": 1.2120997606909354e-05, "epoch": 7.0505709624796085, "percentage": 70.51, "elapsed_time": "5:54:00", "remaining_time": "2:28:05", "throughput": 4391.76, "total_tokens": 93284416} {"current_steps": 43225, "total_steps": 61300, "loss": 0.3495, "lr": 1.2114897349320553e-05, "epoch": 7.051386623164763, "percentage": 70.51, "elapsed_time": "5:54:03", "remaining_time": "2:28:03", "throughput": 4391.82, "total_tokens": 93295776} {"current_steps": 43230, "total_steps": 61300, "loss": 0.3448, "lr": 1.2108798136263555e-05, "epoch": 7.052202283849918, "percentage": 70.52, "elapsed_time": "5:54:05", "remaining_time": "2:28:00", "throughput": 4391.86, "total_tokens": 93305408} {"current_steps": 43235, "total_steps": 61300, "loss": 0.3441, "lr": 1.2102699968232787e-05, "epoch": 7.053017944535074, "percentage": 70.53, "elapsed_time": "5:54:07", "remaining_time": "2:27:57", "throughput": 4391.91, "total_tokens": 93316192} {"current_steps": 43240, "total_steps": 61300, "loss": 0.3544, "lr": 1.2096602845722598e-05, "epoch": 7.053833605220229, "percentage": 70.54, "elapsed_time": "5:54:09", "remaining_time": "2:27:55", "throughput": 4391.95, "total_tokens": 93327072} {"current_steps": 43245, "total_steps": 61300, "loss": 0.3036, "lr": 1.2090506769227256e-05, "epoch": 7.054649265905383, "percentage": 70.55, "elapsed_time": "5:54:11", "remaining_time": "2:27:52", "throughput": 4392.0, "total_tokens": 93338368} {"current_steps": 43250, "total_steps": 61300, "loss": 0.3358, "lr": 1.2084411739240936e-05, "epoch": 7.055464926590538, "percentage": 70.55, "elapsed_time": "5:54:14", "remaining_time": "2:27:50", "throughput": 4392.05, "total_tokens": 93349952} {"current_steps": 43255, "total_steps": 61300, "loss": 0.3316, "lr": 1.2078317756257735e-05, "epoch": 7.056280587275693, "percentage": 70.56, "elapsed_time": "5:54:16", "remaining_time": "2:27:47", "throughput": 4392.09, "total_tokens": 93360480} {"current_steps": 43260, "total_steps": 61300, "loss": 0.3429, "lr": 1.207222482077166e-05, "epoch": 7.057096247960848, "percentage": 70.57, "elapsed_time": "5:54:18", "remaining_time": "2:27:45", "throughput": 4392.13, "total_tokens": 93371104} {"current_steps": 43265, "total_steps": 61300, "loss": 0.3422, "lr": 1.2066132933276636e-05, "epoch": 7.057911908646004, "percentage": 70.58, "elapsed_time": "5:54:20", "remaining_time": "2:27:42", "throughput": 4392.17, "total_tokens": 93381792} {"current_steps": 43270, "total_steps": 61300, "loss": 0.3685, "lr": 1.2060042094266495e-05, "epoch": 7.058727569331158, "percentage": 70.59, "elapsed_time": "5:54:23", "remaining_time": "2:27:40", "throughput": 4392.23, "total_tokens": 93393024} {"current_steps": 43275, "total_steps": 61300, "loss": 0.3248, "lr": 1.2053952304235002e-05, "epoch": 7.059543230016313, "percentage": 70.6, "elapsed_time": "5:54:25", "remaining_time": "2:27:37", "throughput": 4392.27, "total_tokens": 93403968} {"current_steps": 43280, "total_steps": 61300, "loss": 0.3701, "lr": 1.2047863563675826e-05, "epoch": 7.060358890701468, "percentage": 70.6, "elapsed_time": "5:54:27", "remaining_time": "2:27:34", "throughput": 4392.31, "total_tokens": 93414336} {"current_steps": 43285, "total_steps": 61300, "loss": 0.3422, "lr": 1.204177587308255e-05, "epoch": 7.061174551386623, "percentage": 70.61, "elapsed_time": "5:54:29", "remaining_time": "2:27:32", "throughput": 4392.36, "total_tokens": 93425312} {"current_steps": 43290, "total_steps": 61300, "loss": 0.2944, "lr": 1.2035689232948669e-05, "epoch": 7.061990212071779, "percentage": 70.62, "elapsed_time": "5:54:31", "remaining_time": "2:27:29", "throughput": 4392.39, "total_tokens": 93434368} {"current_steps": 43295, "total_steps": 61300, "loss": 0.3427, "lr": 1.20296036437676e-05, "epoch": 7.062805872756933, "percentage": 70.63, "elapsed_time": "5:54:34", "remaining_time": "2:27:27", "throughput": 4392.44, "total_tokens": 93445696} {"current_steps": 43300, "total_steps": 61300, "loss": 0.3361, "lr": 1.2023519106032672e-05, "epoch": 7.063621533442088, "percentage": 70.64, "elapsed_time": "5:54:36", "remaining_time": "2:27:24", "throughput": 4392.49, "total_tokens": 93456768} {"current_steps": 43305, "total_steps": 61300, "loss": 0.3262, "lr": 1.2017435620237125e-05, "epoch": 7.064437194127243, "percentage": 70.64, "elapsed_time": "5:54:38", "remaining_time": "2:27:22", "throughput": 4392.55, "total_tokens": 93468320} {"current_steps": 43310, "total_steps": 61300, "loss": 0.3376, "lr": 1.201135318687412e-05, "epoch": 7.065252854812398, "percentage": 70.65, "elapsed_time": "5:54:41", "remaining_time": "2:27:19", "throughput": 4392.59, "total_tokens": 93480832} {"current_steps": 43315, "total_steps": 61300, "loss": 0.3279, "lr": 1.2005271806436727e-05, "epoch": 7.066068515497553, "percentage": 70.66, "elapsed_time": "5:54:43", "remaining_time": "2:27:17", "throughput": 4392.64, "total_tokens": 93490880} {"current_steps": 43320, "total_steps": 61300, "loss": 0.3399, "lr": 1.199919147941794e-05, "epoch": 7.066884176182708, "percentage": 70.67, "elapsed_time": "5:54:45", "remaining_time": "2:27:14", "throughput": 4392.68, "total_tokens": 93501600} {"current_steps": 43325, "total_steps": 61300, "loss": 0.3321, "lr": 1.1993112206310656e-05, "epoch": 7.067699836867863, "percentage": 70.68, "elapsed_time": "5:54:48", "remaining_time": "2:27:12", "throughput": 4392.73, "total_tokens": 93512832} {"current_steps": 43330, "total_steps": 61300, "loss": 0.3422, "lr": 1.1987033987607681e-05, "epoch": 7.068515497553018, "percentage": 70.69, "elapsed_time": "5:54:50", "remaining_time": "2:27:09", "throughput": 4392.79, "total_tokens": 93524416} {"current_steps": 43335, "total_steps": 61300, "loss": 0.311, "lr": 1.198095682380177e-05, "epoch": 7.069331158238173, "percentage": 70.69, "elapsed_time": "5:54:52", "remaining_time": "2:27:07", "throughput": 4392.84, "total_tokens": 93535744} {"current_steps": 43340, "total_steps": 61300, "loss": 0.3463, "lr": 1.1974880715385557e-05, "epoch": 7.070146818923328, "percentage": 70.7, "elapsed_time": "5:54:54", "remaining_time": "2:27:04", "throughput": 4392.88, "total_tokens": 93546016} {"current_steps": 43345, "total_steps": 61300, "loss": 0.3359, "lr": 1.1968805662851601e-05, "epoch": 7.0709624796084825, "percentage": 70.71, "elapsed_time": "5:54:56", "remaining_time": "2:27:01", "throughput": 4392.91, "total_tokens": 93555040} {"current_steps": 43350, "total_steps": 61300, "loss": 0.3234, "lr": 1.1962731666692378e-05, "epoch": 7.071778140293638, "percentage": 70.72, "elapsed_time": "5:54:58", "remaining_time": "2:26:59", "throughput": 4392.95, "total_tokens": 93565184} {"current_steps": 43355, "total_steps": 61300, "loss": 0.3271, "lr": 1.1956658727400277e-05, "epoch": 7.072593800978793, "percentage": 70.73, "elapsed_time": "5:55:01", "remaining_time": "2:26:56", "throughput": 4393.0, "total_tokens": 93576352} {"current_steps": 43360, "total_steps": 61300, "loss": 0.332, "lr": 1.1950586845467602e-05, "epoch": 7.073409461663948, "percentage": 70.73, "elapsed_time": "5:55:03", "remaining_time": "2:26:54", "throughput": 4393.04, "total_tokens": 93586880} {"current_steps": 43365, "total_steps": 61300, "loss": 0.2956, "lr": 1.1944516021386565e-05, "epoch": 7.074225122349103, "percentage": 70.74, "elapsed_time": "5:55:05", "remaining_time": "2:26:51", "throughput": 4393.09, "total_tokens": 93598560} {"current_steps": 43370, "total_steps": 61300, "loss": 0.3269, "lr": 1.1938446255649305e-05, "epoch": 7.075040783034257, "percentage": 70.75, "elapsed_time": "5:55:08", "remaining_time": "2:26:49", "throughput": 4393.13, "total_tokens": 93608928} {"current_steps": 43375, "total_steps": 61300, "loss": 0.3216, "lr": 1.1932377548747867e-05, "epoch": 7.075856443719413, "percentage": 70.76, "elapsed_time": "5:55:10", "remaining_time": "2:26:46", "throughput": 4393.17, "total_tokens": 93619552} {"current_steps": 43380, "total_steps": 61300, "loss": 0.2961, "lr": 1.1926309901174196e-05, "epoch": 7.076672104404568, "percentage": 70.77, "elapsed_time": "5:55:12", "remaining_time": "2:26:44", "throughput": 4393.22, "total_tokens": 93631264} {"current_steps": 43385, "total_steps": 61300, "loss": 0.3683, "lr": 1.192024331342019e-05, "epoch": 7.077487765089723, "percentage": 70.77, "elapsed_time": "5:55:14", "remaining_time": "2:26:41", "throughput": 4393.27, "total_tokens": 93641792} {"current_steps": 43390, "total_steps": 61300, "loss": 0.3107, "lr": 1.1914177785977629e-05, "epoch": 7.078303425774878, "percentage": 70.78, "elapsed_time": "5:55:17", "remaining_time": "2:26:39", "throughput": 4393.31, "total_tokens": 93652992} {"current_steps": 43395, "total_steps": 61300, "loss": 0.3171, "lr": 1.1908113319338212e-05, "epoch": 7.079119086460032, "percentage": 70.79, "elapsed_time": "5:55:19", "remaining_time": "2:26:36", "throughput": 4393.34, "total_tokens": 93663552} {"current_steps": 43400, "total_steps": 61300, "loss": 0.3133, "lr": 1.1902049913993558e-05, "epoch": 7.079934747145187, "percentage": 70.8, "elapsed_time": "5:55:21", "remaining_time": "2:26:33", "throughput": 4393.39, "total_tokens": 93674272} {"current_steps": 43405, "total_steps": 61300, "loss": 0.3354, "lr": 1.1895987570435196e-05, "epoch": 7.080750407830343, "percentage": 70.81, "elapsed_time": "5:55:23", "remaining_time": "2:26:31", "throughput": 4393.44, "total_tokens": 93685536} {"current_steps": 43410, "total_steps": 61300, "loss": 0.3175, "lr": 1.188992628915457e-05, "epoch": 7.081566068515498, "percentage": 70.82, "elapsed_time": "5:55:26", "remaining_time": "2:26:28", "throughput": 4393.48, "total_tokens": 93696640} {"current_steps": 43415, "total_steps": 61300, "loss": 0.3879, "lr": 1.1883866070643041e-05, "epoch": 7.082381729200653, "percentage": 70.82, "elapsed_time": "5:55:28", "remaining_time": "2:26:26", "throughput": 4393.53, "total_tokens": 93707008} {"current_steps": 43420, "total_steps": 61300, "loss": 0.3368, "lr": 1.1877806915391875e-05, "epoch": 7.083197389885807, "percentage": 70.83, "elapsed_time": "5:55:30", "remaining_time": "2:26:23", "throughput": 4393.57, "total_tokens": 93717376} {"current_steps": 43425, "total_steps": 61300, "loss": 0.3314, "lr": 1.1871748823892264e-05, "epoch": 7.084013050570962, "percentage": 70.84, "elapsed_time": "5:55:32", "remaining_time": "2:26:21", "throughput": 4393.62, "total_tokens": 93728032} {"current_steps": 43430, "total_steps": 61300, "loss": 0.3086, "lr": 1.1865691796635306e-05, "epoch": 7.084828711256117, "percentage": 70.85, "elapsed_time": "5:55:34", "remaining_time": "2:26:18", "throughput": 4393.65, "total_tokens": 93737792} {"current_steps": 43435, "total_steps": 61300, "loss": 0.3214, "lr": 1.1859635834112012e-05, "epoch": 7.085644371941273, "percentage": 70.86, "elapsed_time": "5:55:37", "remaining_time": "2:26:16", "throughput": 4393.7, "total_tokens": 93749088} {"current_steps": 43440, "total_steps": 61300, "loss": 0.3353, "lr": 1.1853580936813313e-05, "epoch": 7.0864600326264275, "percentage": 70.86, "elapsed_time": "5:55:39", "remaining_time": "2:26:13", "throughput": 4393.75, "total_tokens": 93760512} {"current_steps": 43445, "total_steps": 61300, "loss": 0.3737, "lr": 1.1847527105230047e-05, "epoch": 7.087275693311582, "percentage": 70.87, "elapsed_time": "5:55:41", "remaining_time": "2:26:11", "throughput": 4393.8, "total_tokens": 93771712} {"current_steps": 43450, "total_steps": 61300, "loss": 0.3507, "lr": 1.1841474339852968e-05, "epoch": 7.088091353996737, "percentage": 70.88, "elapsed_time": "5:55:44", "remaining_time": "2:26:08", "throughput": 4393.85, "total_tokens": 93783008} {"current_steps": 43455, "total_steps": 61300, "loss": 0.3412, "lr": 1.1835422641172744e-05, "epoch": 7.088907014681892, "percentage": 70.89, "elapsed_time": "5:55:46", "remaining_time": "2:26:05", "throughput": 4393.89, "total_tokens": 93792928} {"current_steps": 43460, "total_steps": 61300, "loss": 0.324, "lr": 1.182937200967996e-05, "epoch": 7.089722675367048, "percentage": 70.9, "elapsed_time": "5:55:48", "remaining_time": "2:26:03", "throughput": 4393.94, "total_tokens": 93803872} {"current_steps": 43465, "total_steps": 61300, "loss": 0.3317, "lr": 1.1823322445865103e-05, "epoch": 7.0905383360522025, "percentage": 70.91, "elapsed_time": "5:55:50", "remaining_time": "2:26:00", "throughput": 4393.99, "total_tokens": 93815584} {"current_steps": 43470, "total_steps": 61300, "loss": 0.3293, "lr": 1.1817273950218591e-05, "epoch": 7.091353996737357, "percentage": 70.91, "elapsed_time": "5:55:53", "remaining_time": "2:25:58", "throughput": 4394.05, "total_tokens": 93827040} {"current_steps": 43475, "total_steps": 61300, "loss": 0.3355, "lr": 1.1811226523230731e-05, "epoch": 7.092169657422512, "percentage": 70.92, "elapsed_time": "5:55:55", "remaining_time": "2:25:55", "throughput": 4394.08, "total_tokens": 93836800} {"current_steps": 43480, "total_steps": 61300, "loss": 0.3388, "lr": 1.1805180165391774e-05, "epoch": 7.092985318107667, "percentage": 70.93, "elapsed_time": "5:55:57", "remaining_time": "2:25:53", "throughput": 4394.13, "total_tokens": 93848032} {"current_steps": 43485, "total_steps": 61300, "loss": 0.3297, "lr": 1.1799134877191867e-05, "epoch": 7.093800978792822, "percentage": 70.94, "elapsed_time": "5:55:59", "remaining_time": "2:25:50", "throughput": 4394.17, "total_tokens": 93858720} {"current_steps": 43490, "total_steps": 61300, "loss": 0.347, "lr": 1.1793090659121065e-05, "epoch": 7.0946166394779775, "percentage": 70.95, "elapsed_time": "5:56:02", "remaining_time": "2:25:48", "throughput": 4394.22, "total_tokens": 93869696} {"current_steps": 43495, "total_steps": 61300, "loss": 0.3304, "lr": 1.1787047511669347e-05, "epoch": 7.095432300163132, "percentage": 70.95, "elapsed_time": "5:56:04", "remaining_time": "2:25:45", "throughput": 4394.26, "total_tokens": 93880672} {"current_steps": 43500, "total_steps": 61300, "loss": 0.3451, "lr": 1.178100543532659e-05, "epoch": 7.096247960848287, "percentage": 70.96, "elapsed_time": "5:56:06", "remaining_time": "2:25:43", "throughput": 4394.31, "total_tokens": 93891840} {"current_steps": 43505, "total_steps": 61300, "loss": 0.3252, "lr": 1.1774964430582614e-05, "epoch": 7.097063621533442, "percentage": 70.97, "elapsed_time": "5:56:08", "remaining_time": "2:25:40", "throughput": 4394.33, "total_tokens": 93900928} {"current_steps": 43510, "total_steps": 61300, "loss": 0.3299, "lr": 1.1768924497927123e-05, "epoch": 7.097879282218597, "percentage": 70.98, "elapsed_time": "5:56:11", "remaining_time": "2:25:38", "throughput": 4394.38, "total_tokens": 93912480} {"current_steps": 43515, "total_steps": 61300, "loss": 0.3317, "lr": 1.1762885637849746e-05, "epoch": 7.0986949429037525, "percentage": 70.99, "elapsed_time": "5:56:13", "remaining_time": "2:25:35", "throughput": 4394.43, "total_tokens": 93924192} {"current_steps": 43520, "total_steps": 61300, "loss": 0.3322, "lr": 1.1756847850840024e-05, "epoch": 7.099510603588907, "percentage": 71.0, "elapsed_time": "5:56:15", "remaining_time": "2:25:32", "throughput": 4394.47, "total_tokens": 93934304} {"current_steps": 43525, "total_steps": 61300, "loss": 0.3384, "lr": 1.1750811137387414e-05, "epoch": 7.100326264274062, "percentage": 71.0, "elapsed_time": "5:56:17", "remaining_time": "2:25:30", "throughput": 4394.51, "total_tokens": 93944032} {"current_steps": 43530, "total_steps": 61300, "loss": 0.3451, "lr": 1.1744775497981273e-05, "epoch": 7.101141924959217, "percentage": 71.01, "elapsed_time": "5:56:19", "remaining_time": "2:25:27", "throughput": 4394.55, "total_tokens": 93954304} {"current_steps": 43535, "total_steps": 61300, "loss": 0.3735, "lr": 1.173874093311089e-05, "epoch": 7.101957585644372, "percentage": 71.02, "elapsed_time": "5:56:21", "remaining_time": "2:25:25", "throughput": 4394.59, "total_tokens": 93964864} {"current_steps": 43540, "total_steps": 61300, "loss": 0.3374, "lr": 1.1732707443265453e-05, "epoch": 7.102773246329527, "percentage": 71.03, "elapsed_time": "5:56:24", "remaining_time": "2:25:22", "throughput": 4394.64, "total_tokens": 93976448} {"current_steps": 43545, "total_steps": 61300, "loss": 0.3263, "lr": 1.172667502893407e-05, "epoch": 7.103588907014682, "percentage": 71.04, "elapsed_time": "5:56:26", "remaining_time": "2:25:20", "throughput": 4394.68, "total_tokens": 93986848} {"current_steps": 43550, "total_steps": 61300, "loss": 0.3464, "lr": 1.1720643690605754e-05, "epoch": 7.104404567699837, "percentage": 71.04, "elapsed_time": "5:56:28", "remaining_time": "2:25:17", "throughput": 4394.73, "total_tokens": 93997472} {"current_steps": 43555, "total_steps": 61300, "loss": 0.3388, "lr": 1.1714613428769442e-05, "epoch": 7.105220228384992, "percentage": 71.05, "elapsed_time": "5:56:30", "remaining_time": "2:25:14", "throughput": 4394.77, "total_tokens": 94007744} {"current_steps": 43560, "total_steps": 61300, "loss": 0.3292, "lr": 1.1708584243913972e-05, "epoch": 7.106035889070147, "percentage": 71.06, "elapsed_time": "5:56:33", "remaining_time": "2:25:12", "throughput": 4394.81, "total_tokens": 94018880} {"current_steps": 43565, "total_steps": 61300, "loss": 0.3215, "lr": 1.1702556136528106e-05, "epoch": 7.1068515497553015, "percentage": 71.07, "elapsed_time": "5:56:35", "remaining_time": "2:25:09", "throughput": 4394.85, "total_tokens": 94030112} {"current_steps": 43570, "total_steps": 61300, "loss": 0.3327, "lr": 1.169652910710051e-05, "epoch": 7.107667210440456, "percentage": 71.08, "elapsed_time": "5:56:37", "remaining_time": "2:25:07", "throughput": 4394.9, "total_tokens": 94041120} {"current_steps": 43575, "total_steps": 61300, "loss": 0.3221, "lr": 1.1690503156119764e-05, "epoch": 7.108482871125612, "percentage": 71.08, "elapsed_time": "5:56:40", "remaining_time": "2:25:04", "throughput": 4394.96, "total_tokens": 94052928} {"current_steps": 43580, "total_steps": 61300, "loss": 0.3407, "lr": 1.1684478284074365e-05, "epoch": 7.109298531810767, "percentage": 71.09, "elapsed_time": "5:56:42", "remaining_time": "2:25:02", "throughput": 4395.0, "total_tokens": 94064480} {"current_steps": 43585, "total_steps": 61300, "loss": 0.3218, "lr": 1.1678454491452717e-05, "epoch": 7.110114192495922, "percentage": 71.1, "elapsed_time": "5:56:45", "remaining_time": "2:25:00", "throughput": 4395.04, "total_tokens": 94076064} {"current_steps": 43590, "total_steps": 61300, "loss": 0.3062, "lr": 1.1672431778743133e-05, "epoch": 7.1109298531810765, "percentage": 71.11, "elapsed_time": "5:56:46", "remaining_time": "2:24:57", "throughput": 4395.08, "total_tokens": 94085216} {"current_steps": 43595, "total_steps": 61300, "loss": 0.3278, "lr": 1.1666410146433861e-05, "epoch": 7.111745513866231, "percentage": 71.12, "elapsed_time": "5:56:49", "remaining_time": "2:24:54", "throughput": 4395.13, "total_tokens": 94095904} {"current_steps": 43600, "total_steps": 61300, "loss": 0.3116, "lr": 1.1660389595013038e-05, "epoch": 7.112561174551387, "percentage": 71.13, "elapsed_time": "5:56:51", "remaining_time": "2:24:52", "throughput": 4395.17, "total_tokens": 94108288} {"current_steps": 43605, "total_steps": 61300, "loss": 0.3239, "lr": 1.165437012496872e-05, "epoch": 7.113376835236542, "percentage": 71.13, "elapsed_time": "5:56:53", "remaining_time": "2:24:49", "throughput": 4395.21, "total_tokens": 94117440} {"current_steps": 43610, "total_steps": 61300, "loss": 0.3178, "lr": 1.1648351736788871e-05, "epoch": 7.114192495921697, "percentage": 71.14, "elapsed_time": "5:56:55", "remaining_time": "2:24:47", "throughput": 4395.24, "total_tokens": 94127488} {"current_steps": 43615, "total_steps": 61300, "loss": 0.3161, "lr": 1.1642334430961377e-05, "epoch": 7.1150081566068515, "percentage": 71.15, "elapsed_time": "5:56:57", "remaining_time": "2:24:44", "throughput": 4395.29, "total_tokens": 94137824} {"current_steps": 43620, "total_steps": 61300, "loss": 0.3577, "lr": 1.163631820797403e-05, "epoch": 7.115823817292006, "percentage": 71.16, "elapsed_time": "5:57:00", "remaining_time": "2:24:42", "throughput": 4395.34, "total_tokens": 94149632} {"current_steps": 43625, "total_steps": 61300, "loss": 0.3102, "lr": 1.1630303068314538e-05, "epoch": 7.116639477977161, "percentage": 71.17, "elapsed_time": "5:57:02", "remaining_time": "2:24:39", "throughput": 4395.39, "total_tokens": 94161184} {"current_steps": 43630, "total_steps": 61300, "loss": 0.3408, "lr": 1.1624289012470513e-05, "epoch": 7.117455138662317, "percentage": 71.17, "elapsed_time": "5:57:04", "remaining_time": "2:24:36", "throughput": 4395.44, "total_tokens": 94170656} {"current_steps": 43635, "total_steps": 61300, "loss": 0.3453, "lr": 1.161827604092949e-05, "epoch": 7.118270799347472, "percentage": 71.18, "elapsed_time": "5:57:06", "remaining_time": "2:24:34", "throughput": 4395.48, "total_tokens": 94180384} {"current_steps": 43640, "total_steps": 61300, "loss": 0.3456, "lr": 1.161226415417891e-05, "epoch": 7.1190864600326265, "percentage": 71.19, "elapsed_time": "5:57:08", "remaining_time": "2:24:31", "throughput": 4395.52, "total_tokens": 94191456} {"current_steps": 43645, "total_steps": 61300, "loss": 0.3457, "lr": 1.1606253352706118e-05, "epoch": 7.119902120717781, "percentage": 71.2, "elapsed_time": "5:57:11", "remaining_time": "2:24:29", "throughput": 4395.57, "total_tokens": 94202112} {"current_steps": 43650, "total_steps": 61300, "loss": 0.3688, "lr": 1.1600243636998396e-05, "epoch": 7.120717781402936, "percentage": 71.21, "elapsed_time": "5:57:13", "remaining_time": "2:24:26", "throughput": 4395.62, "total_tokens": 94213312} {"current_steps": 43655, "total_steps": 61300, "loss": 0.3688, "lr": 1.1594235007542914e-05, "epoch": 7.121533442088092, "percentage": 71.22, "elapsed_time": "5:57:15", "remaining_time": "2:24:24", "throughput": 4395.67, "total_tokens": 94225248} {"current_steps": 43660, "total_steps": 61300, "loss": 0.3299, "lr": 1.1588227464826763e-05, "epoch": 7.122349102773247, "percentage": 71.22, "elapsed_time": "5:57:18", "remaining_time": "2:24:21", "throughput": 4395.72, "total_tokens": 94236416} {"current_steps": 43665, "total_steps": 61300, "loss": 0.3065, "lr": 1.1582221009336944e-05, "epoch": 7.123164763458401, "percentage": 71.23, "elapsed_time": "5:57:20", "remaining_time": "2:24:19", "throughput": 4395.77, "total_tokens": 94247040} {"current_steps": 43670, "total_steps": 61300, "loss": 0.3196, "lr": 1.157621564156037e-05, "epoch": 7.123980424143556, "percentage": 71.24, "elapsed_time": "5:57:22", "remaining_time": "2:24:16", "throughput": 4395.81, "total_tokens": 94257472} {"current_steps": 43675, "total_steps": 61300, "loss": 0.3358, "lr": 1.157021136198387e-05, "epoch": 7.124796084828711, "percentage": 71.25, "elapsed_time": "5:57:24", "remaining_time": "2:24:13", "throughput": 4395.86, "total_tokens": 94267776} {"current_steps": 43680, "total_steps": 61300, "loss": 0.3765, "lr": 1.156420817109418e-05, "epoch": 7.125611745513866, "percentage": 71.26, "elapsed_time": "5:57:27", "remaining_time": "2:24:11", "throughput": 4395.91, "total_tokens": 94279552} {"current_steps": 43685, "total_steps": 61300, "loss": 0.3335, "lr": 1.1558206069377945e-05, "epoch": 7.126427406199022, "percentage": 71.26, "elapsed_time": "5:57:29", "remaining_time": "2:24:09", "throughput": 4395.96, "total_tokens": 94291424} {"current_steps": 43690, "total_steps": 61300, "loss": 0.3681, "lr": 1.155220505732173e-05, "epoch": 7.127243066884176, "percentage": 71.27, "elapsed_time": "5:57:31", "remaining_time": "2:24:06", "throughput": 4395.99, "total_tokens": 94302080} {"current_steps": 43695, "total_steps": 61300, "loss": 0.3489, "lr": 1.1546205135412008e-05, "epoch": 7.128058727569331, "percentage": 71.28, "elapsed_time": "5:57:34", "remaining_time": "2:24:04", "throughput": 4396.04, "total_tokens": 94313440} {"current_steps": 43700, "total_steps": 61300, "loss": 0.3438, "lr": 1.1540206304135152e-05, "epoch": 7.128874388254486, "percentage": 71.29, "elapsed_time": "5:57:36", "remaining_time": "2:24:01", "throughput": 4396.07, "total_tokens": 94322784} {"current_steps": 43705, "total_steps": 61300, "loss": 0.3141, "lr": 1.1534208563977475e-05, "epoch": 7.129690048939641, "percentage": 71.3, "elapsed_time": "5:57:38", "remaining_time": "2:23:58", "throughput": 4396.11, "total_tokens": 94333280} {"current_steps": 43710, "total_steps": 61300, "loss": 0.3089, "lr": 1.1528211915425177e-05, "epoch": 7.130505709624796, "percentage": 71.31, "elapsed_time": "5:57:40", "remaining_time": "2:23:56", "throughput": 4396.16, "total_tokens": 94344032} {"current_steps": 43715, "total_steps": 61300, "loss": 0.2957, "lr": 1.1522216358964377e-05, "epoch": 7.131321370309951, "percentage": 71.31, "elapsed_time": "5:57:42", "remaining_time": "2:23:53", "throughput": 4396.2, "total_tokens": 94354816} {"current_steps": 43720, "total_steps": 61300, "loss": 0.3166, "lr": 1.1516221895081104e-05, "epoch": 7.132137030995106, "percentage": 71.32, "elapsed_time": "5:57:44", "remaining_time": "2:23:51", "throughput": 4396.24, "total_tokens": 94364896} {"current_steps": 43725, "total_steps": 61300, "loss": 0.3176, "lr": 1.1510228524261302e-05, "epoch": 7.132952691680261, "percentage": 71.33, "elapsed_time": "5:57:47", "remaining_time": "2:23:48", "throughput": 4396.28, "total_tokens": 94375648} {"current_steps": 43730, "total_steps": 61300, "loss": 0.373, "lr": 1.1504236246990819e-05, "epoch": 7.133768352365416, "percentage": 71.34, "elapsed_time": "5:57:49", "remaining_time": "2:23:46", "throughput": 4396.33, "total_tokens": 94386816} {"current_steps": 43735, "total_steps": 61300, "loss": 0.3141, "lr": 1.1498245063755425e-05, "epoch": 7.134584013050571, "percentage": 71.35, "elapsed_time": "5:57:51", "remaining_time": "2:23:43", "throughput": 4396.38, "total_tokens": 94397856} {"current_steps": 43740, "total_steps": 61300, "loss": 0.3027, "lr": 1.1492254975040792e-05, "epoch": 7.135399673735726, "percentage": 71.35, "elapsed_time": "5:57:53", "remaining_time": "2:23:40", "throughput": 4396.42, "total_tokens": 94408128} {"current_steps": 43745, "total_steps": 61300, "loss": 0.2944, "lr": 1.148626598133251e-05, "epoch": 7.136215334420881, "percentage": 71.36, "elapsed_time": "5:57:56", "remaining_time": "2:23:38", "throughput": 4396.46, "total_tokens": 94418912} {"current_steps": 43750, "total_steps": 61300, "loss": 0.3514, "lr": 1.1480278083116074e-05, "epoch": 7.137030995106036, "percentage": 71.37, "elapsed_time": "5:57:58", "remaining_time": "2:23:35", "throughput": 4396.5, "total_tokens": 94428576} {"current_steps": 43755, "total_steps": 61300, "loss": 0.3255, "lr": 1.1474291280876894e-05, "epoch": 7.137846655791191, "percentage": 71.38, "elapsed_time": "5:58:00", "remaining_time": "2:23:33", "throughput": 4396.53, "total_tokens": 94439232} {"current_steps": 43760, "total_steps": 61300, "loss": 0.3189, "lr": 1.1468305575100294e-05, "epoch": 7.138662316476346, "percentage": 71.39, "elapsed_time": "5:58:02", "remaining_time": "2:23:30", "throughput": 4396.58, "total_tokens": 94450144} {"current_steps": 43765, "total_steps": 61300, "loss": 0.3249, "lr": 1.1462320966271503e-05, "epoch": 7.1394779771615005, "percentage": 71.39, "elapsed_time": "5:58:05", "remaining_time": "2:23:28", "throughput": 4396.63, "total_tokens": 94461664} {"current_steps": 43770, "total_steps": 61300, "loss": 0.3242, "lr": 1.1456337454875663e-05, "epoch": 7.140293637846656, "percentage": 71.4, "elapsed_time": "5:58:07", "remaining_time": "2:23:25", "throughput": 4396.66, "total_tokens": 94471392} {"current_steps": 43775, "total_steps": 61300, "loss": 0.3297, "lr": 1.1450355041397829e-05, "epoch": 7.141109298531811, "percentage": 71.41, "elapsed_time": "5:58:09", "remaining_time": "2:23:23", "throughput": 4396.72, "total_tokens": 94482848} {"current_steps": 43780, "total_steps": 61300, "loss": 0.3436, "lr": 1.1444373726322966e-05, "epoch": 7.141924959216966, "percentage": 71.42, "elapsed_time": "5:58:11", "remaining_time": "2:23:20", "throughput": 4396.77, "total_tokens": 94493792} {"current_steps": 43785, "total_steps": 61300, "loss": 0.3469, "lr": 1.143839351013595e-05, "epoch": 7.142740619902121, "percentage": 71.43, "elapsed_time": "5:58:13", "remaining_time": "2:23:18", "throughput": 4396.82, "total_tokens": 94504448} {"current_steps": 43790, "total_steps": 61300, "loss": 0.3539, "lr": 1.1432414393321556e-05, "epoch": 7.143556280587275, "percentage": 71.44, "elapsed_time": "5:58:16", "remaining_time": "2:23:15", "throughput": 4396.86, "total_tokens": 94515296} {"current_steps": 43795, "total_steps": 61300, "loss": 0.3392, "lr": 1.1426436376364502e-05, "epoch": 7.14437194127243, "percentage": 71.44, "elapsed_time": "5:58:18", "remaining_time": "2:23:12", "throughput": 4396.91, "total_tokens": 94525984} {"current_steps": 43800, "total_steps": 61300, "loss": 0.3704, "lr": 1.1420459459749385e-05, "epoch": 7.145187601957586, "percentage": 71.45, "elapsed_time": "5:58:20", "remaining_time": "2:23:10", "throughput": 4396.95, "total_tokens": 94536512} {"current_steps": 43805, "total_steps": 61300, "loss": 0.3188, "lr": 1.141448364396073e-05, "epoch": 7.146003262642741, "percentage": 71.46, "elapsed_time": "5:58:22", "remaining_time": "2:23:07", "throughput": 4396.99, "total_tokens": 94546208} {"current_steps": 43810, "total_steps": 61300, "loss": 0.3175, "lr": 1.1408508929482961e-05, "epoch": 7.146818923327896, "percentage": 71.47, "elapsed_time": "5:58:25", "remaining_time": "2:23:05", "throughput": 4397.04, "total_tokens": 94558656} {"current_steps": 43815, "total_steps": 61300, "loss": 0.3107, "lr": 1.1402535316800414e-05, "epoch": 7.14763458401305, "percentage": 71.48, "elapsed_time": "5:58:27", "remaining_time": "2:23:02", "throughput": 4397.1, "total_tokens": 94568832} {"current_steps": 43820, "total_steps": 61300, "loss": 0.336, "lr": 1.1396562806397354e-05, "epoch": 7.148450244698205, "percentage": 71.48, "elapsed_time": "5:58:29", "remaining_time": "2:23:00", "throughput": 4397.15, "total_tokens": 94580512} {"current_steps": 43825, "total_steps": 61300, "loss": 0.3354, "lr": 1.1390591398757935e-05, "epoch": 7.149265905383361, "percentage": 71.49, "elapsed_time": "5:58:32", "remaining_time": "2:22:57", "throughput": 4397.2, "total_tokens": 94592608} {"current_steps": 43830, "total_steps": 61300, "loss": 0.3383, "lr": 1.1384621094366232e-05, "epoch": 7.150081566068516, "percentage": 71.5, "elapsed_time": "5:58:34", "remaining_time": "2:22:55", "throughput": 4397.23, "total_tokens": 94603200} {"current_steps": 43835, "total_steps": 61300, "loss": 0.3091, "lr": 1.1378651893706227e-05, "epoch": 7.150897226753671, "percentage": 71.51, "elapsed_time": "5:58:36", "remaining_time": "2:22:52", "throughput": 4397.27, "total_tokens": 94614656} {"current_steps": 43840, "total_steps": 61300, "loss": 0.3025, "lr": 1.1372683797261814e-05, "epoch": 7.151712887438825, "percentage": 71.52, "elapsed_time": "5:58:38", "remaining_time": "2:22:50", "throughput": 4397.31, "total_tokens": 94624512} {"current_steps": 43845, "total_steps": 61300, "loss": 0.3432, "lr": 1.1366716805516794e-05, "epoch": 7.15252854812398, "percentage": 71.53, "elapsed_time": "5:58:40", "remaining_time": "2:22:47", "throughput": 4397.35, "total_tokens": 94635360} {"current_steps": 43850, "total_steps": 61300, "loss": 0.3504, "lr": 1.1360750918954887e-05, "epoch": 7.153344208809135, "percentage": 71.53, "elapsed_time": "5:58:43", "remaining_time": "2:22:45", "throughput": 4397.4, "total_tokens": 94645440} {"current_steps": 43855, "total_steps": 61300, "loss": 0.3311, "lr": 1.1354786138059715e-05, "epoch": 7.154159869494291, "percentage": 71.54, "elapsed_time": "5:58:45", "remaining_time": "2:22:42", "throughput": 4397.45, "total_tokens": 94656832} {"current_steps": 43860, "total_steps": 61300, "loss": 0.3563, "lr": 1.1348822463314815e-05, "epoch": 7.1549755301794455, "percentage": 71.55, "elapsed_time": "5:58:47", "remaining_time": "2:22:39", "throughput": 4397.49, "total_tokens": 94666816} {"current_steps": 43865, "total_steps": 61300, "loss": 0.3676, "lr": 1.1342859895203629e-05, "epoch": 7.1557911908646, "percentage": 71.56, "elapsed_time": "5:58:49", "remaining_time": "2:22:37", "throughput": 4397.54, "total_tokens": 94677888} {"current_steps": 43870, "total_steps": 61300, "loss": 0.3678, "lr": 1.1336898434209517e-05, "epoch": 7.156606851549755, "percentage": 71.57, "elapsed_time": "5:58:52", "remaining_time": "2:22:34", "throughput": 4397.59, "total_tokens": 94689088} {"current_steps": 43875, "total_steps": 61300, "loss": 0.3514, "lr": 1.1330938080815743e-05, "epoch": 7.15742251223491, "percentage": 71.57, "elapsed_time": "5:58:54", "remaining_time": "2:22:32", "throughput": 4397.63, "total_tokens": 94700992} {"current_steps": 43880, "total_steps": 61300, "loss": 0.3029, "lr": 1.1324978835505483e-05, "epoch": 7.158238172920065, "percentage": 71.58, "elapsed_time": "5:58:56", "remaining_time": "2:22:29", "throughput": 4397.67, "total_tokens": 94710112} {"current_steps": 43885, "total_steps": 61300, "loss": 0.2999, "lr": 1.1319020698761828e-05, "epoch": 7.1590538336052205, "percentage": 71.59, "elapsed_time": "5:58:58", "remaining_time": "2:22:27", "throughput": 4397.71, "total_tokens": 94720544} {"current_steps": 43890, "total_steps": 61300, "loss": 0.3383, "lr": 1.1313063671067769e-05, "epoch": 7.159869494290375, "percentage": 71.6, "elapsed_time": "5:59:00", "remaining_time": "2:22:24", "throughput": 4397.74, "total_tokens": 94730496} {"current_steps": 43895, "total_steps": 61300, "loss": 0.3083, "lr": 1.1307107752906218e-05, "epoch": 7.16068515497553, "percentage": 71.61, "elapsed_time": "5:59:03", "remaining_time": "2:22:22", "throughput": 4397.78, "total_tokens": 94741696} {"current_steps": 43900, "total_steps": 61300, "loss": 0.3372, "lr": 1.1301152944759988e-05, "epoch": 7.161500815660685, "percentage": 71.62, "elapsed_time": "5:59:05", "remaining_time": "2:22:19", "throughput": 4397.82, "total_tokens": 94752000} {"current_steps": 43905, "total_steps": 61300, "loss": 0.3425, "lr": 1.129519924711181e-05, "epoch": 7.16231647634584, "percentage": 71.62, "elapsed_time": "5:59:07", "remaining_time": "2:22:17", "throughput": 4397.86, "total_tokens": 94763264} {"current_steps": 43910, "total_steps": 61300, "loss": 0.3363, "lr": 1.1289246660444306e-05, "epoch": 7.1631321370309955, "percentage": 71.63, "elapsed_time": "5:59:09", "remaining_time": "2:22:14", "throughput": 4397.9, "total_tokens": 94773504} {"current_steps": 43915, "total_steps": 61300, "loss": 0.3726, "lr": 1.1283295185240048e-05, "epoch": 7.16394779771615, "percentage": 71.64, "elapsed_time": "5:59:11", "remaining_time": "2:22:11", "throughput": 4397.94, "total_tokens": 94783328} {"current_steps": 43920, "total_steps": 61300, "loss": 0.3208, "lr": 1.1277344821981475e-05, "epoch": 7.164763458401305, "percentage": 71.65, "elapsed_time": "5:59:14", "remaining_time": "2:22:09", "throughput": 4397.99, "total_tokens": 94795584} {"current_steps": 43925, "total_steps": 61300, "loss": 0.3037, "lr": 1.1271395571150964e-05, "epoch": 7.16557911908646, "percentage": 71.66, "elapsed_time": "5:59:16", "remaining_time": "2:22:06", "throughput": 4398.03, "total_tokens": 94805408} {"current_steps": 43930, "total_steps": 61300, "loss": 0.3118, "lr": 1.1265447433230784e-05, "epoch": 7.166394779771615, "percentage": 71.66, "elapsed_time": "5:59:18", "remaining_time": "2:22:04", "throughput": 4398.07, "total_tokens": 94817024} {"current_steps": 43935, "total_steps": 61300, "loss": 0.3158, "lr": 1.1259500408703124e-05, "epoch": 7.16721044045677, "percentage": 71.67, "elapsed_time": "5:59:21", "remaining_time": "2:22:01", "throughput": 4398.12, "total_tokens": 94828480} {"current_steps": 43940, "total_steps": 61300, "loss": 0.3181, "lr": 1.1253554498050078e-05, "epoch": 7.168026101141925, "percentage": 71.68, "elapsed_time": "5:59:23", "remaining_time": "2:21:59", "throughput": 4398.17, "total_tokens": 94839552} {"current_steps": 43945, "total_steps": 61300, "loss": 0.3219, "lr": 1.1247609701753656e-05, "epoch": 7.16884176182708, "percentage": 71.69, "elapsed_time": "5:59:25", "remaining_time": "2:21:56", "throughput": 4398.21, "total_tokens": 94851200} {"current_steps": 43950, "total_steps": 61300, "loss": 0.312, "lr": 1.1241666020295768e-05, "epoch": 7.169657422512235, "percentage": 71.7, "elapsed_time": "5:59:28", "remaining_time": "2:21:54", "throughput": 4398.27, "total_tokens": 94863744} {"current_steps": 43955, "total_steps": 61300, "loss": 0.3251, "lr": 1.1235723454158242e-05, "epoch": 7.17047308319739, "percentage": 71.7, "elapsed_time": "5:59:30", "remaining_time": "2:21:51", "throughput": 4398.31, "total_tokens": 94873504} {"current_steps": 43960, "total_steps": 61300, "loss": 0.3329, "lr": 1.1229782003822803e-05, "epoch": 7.171288743882545, "percentage": 71.71, "elapsed_time": "5:59:32", "remaining_time": "2:21:49", "throughput": 4398.34, "total_tokens": 94883232} {"current_steps": 43965, "total_steps": 61300, "loss": 0.2883, "lr": 1.1223841669771113e-05, "epoch": 7.1721044045677, "percentage": 71.72, "elapsed_time": "5:59:34", "remaining_time": "2:21:46", "throughput": 4398.38, "total_tokens": 94893984} {"current_steps": 43970, "total_steps": 61300, "loss": 0.3384, "lr": 1.121790245248472e-05, "epoch": 7.172920065252855, "percentage": 71.73, "elapsed_time": "5:59:37", "remaining_time": "2:21:44", "throughput": 4398.43, "total_tokens": 94904960} {"current_steps": 43975, "total_steps": 61300, "loss": 0.3553, "lr": 1.1211964352445078e-05, "epoch": 7.17373572593801, "percentage": 71.74, "elapsed_time": "5:59:39", "remaining_time": "2:21:41", "throughput": 4398.47, "total_tokens": 94914656} {"current_steps": 43980, "total_steps": 61300, "loss": 0.3508, "lr": 1.120602737013357e-05, "epoch": 7.174551386623165, "percentage": 71.75, "elapsed_time": "5:59:41", "remaining_time": "2:21:39", "throughput": 4398.52, "total_tokens": 94925632} {"current_steps": 43985, "total_steps": 61300, "loss": 0.3164, "lr": 1.120009150603147e-05, "epoch": 7.1753670473083195, "percentage": 71.75, "elapsed_time": "5:59:43", "remaining_time": "2:21:36", "throughput": 4398.57, "total_tokens": 94937376} {"current_steps": 43990, "total_steps": 61300, "loss": 0.3487, "lr": 1.1194156760619976e-05, "epoch": 7.176182707993474, "percentage": 71.76, "elapsed_time": "5:59:46", "remaining_time": "2:21:34", "throughput": 4398.62, "total_tokens": 94948608} {"current_steps": 43995, "total_steps": 61300, "loss": 0.3284, "lr": 1.1188223134380183e-05, "epoch": 7.17699836867863, "percentage": 71.77, "elapsed_time": "5:59:48", "remaining_time": "2:21:31", "throughput": 4398.65, "total_tokens": 94958368} {"current_steps": 44000, "total_steps": 61300, "loss": 0.3141, "lr": 1.1182290627793105e-05, "epoch": 7.177814029363785, "percentage": 71.78, "elapsed_time": "5:59:50", "remaining_time": "2:21:28", "throughput": 4398.68, "total_tokens": 94968576} {"current_steps": 44005, "total_steps": 61300, "loss": 0.3196, "lr": 1.1176359241339656e-05, "epoch": 7.17862969004894, "percentage": 71.79, "elapsed_time": "5:59:52", "remaining_time": "2:21:26", "throughput": 4398.72, "total_tokens": 94979552} {"current_steps": 44010, "total_steps": 61300, "loss": 0.3766, "lr": 1.1170428975500668e-05, "epoch": 7.1794453507340945, "percentage": 71.79, "elapsed_time": "5:59:54", "remaining_time": "2:21:23", "throughput": 4398.77, "total_tokens": 94990656} {"current_steps": 44015, "total_steps": 61300, "loss": 0.3194, "lr": 1.116449983075688e-05, "epoch": 7.180261011419249, "percentage": 71.8, "elapsed_time": "5:59:56", "remaining_time": "2:21:21", "throughput": 4398.81, "total_tokens": 95000480} {"current_steps": 44020, "total_steps": 61300, "loss": 0.359, "lr": 1.1158571807588924e-05, "epoch": 7.181076672104404, "percentage": 71.81, "elapsed_time": "5:59:59", "remaining_time": "2:21:18", "throughput": 4398.85, "total_tokens": 95011584} {"current_steps": 44025, "total_steps": 61300, "loss": 0.3561, "lr": 1.115264490647738e-05, "epoch": 7.18189233278956, "percentage": 71.82, "elapsed_time": "6:00:01", "remaining_time": "2:21:16", "throughput": 4398.88, "total_tokens": 95021824} {"current_steps": 44030, "total_steps": 61300, "loss": 0.3197, "lr": 1.11467191279027e-05, "epoch": 7.182707993474715, "percentage": 71.83, "elapsed_time": "6:00:03", "remaining_time": "2:21:13", "throughput": 4398.94, "total_tokens": 95033696} {"current_steps": 44035, "total_steps": 61300, "loss": 0.3169, "lr": 1.1140794472345259e-05, "epoch": 7.1835236541598695, "percentage": 71.84, "elapsed_time": "6:00:05", "remaining_time": "2:21:11", "throughput": 4398.98, "total_tokens": 95043936} {"current_steps": 44040, "total_steps": 61300, "loss": 0.3377, "lr": 1.1134870940285339e-05, "epoch": 7.184339314845024, "percentage": 71.84, "elapsed_time": "6:00:08", "remaining_time": "2:21:08", "throughput": 4399.03, "total_tokens": 95055040} {"current_steps": 44045, "total_steps": 61300, "loss": 0.356, "lr": 1.112894853220313e-05, "epoch": 7.185154975530179, "percentage": 71.85, "elapsed_time": "6:00:10", "remaining_time": "2:21:06", "throughput": 4399.07, "total_tokens": 95066368} {"current_steps": 44050, "total_steps": 61300, "loss": 0.3395, "lr": 1.1123027248578736e-05, "epoch": 7.185970636215335, "percentage": 71.86, "elapsed_time": "6:00:12", "remaining_time": "2:21:03", "throughput": 4399.12, "total_tokens": 95077728} {"current_steps": 44055, "total_steps": 61300, "loss": 0.3184, "lr": 1.1117107089892162e-05, "epoch": 7.18678629690049, "percentage": 71.87, "elapsed_time": "6:00:15", "remaining_time": "2:21:01", "throughput": 4399.16, "total_tokens": 95088160} {"current_steps": 44060, "total_steps": 61300, "loss": 0.329, "lr": 1.1111188056623328e-05, "epoch": 7.1876019575856445, "percentage": 71.88, "elapsed_time": "6:00:17", "remaining_time": "2:20:58", "throughput": 4399.2, "total_tokens": 95099424} {"current_steps": 44065, "total_steps": 61300, "loss": 0.3174, "lr": 1.1105270149252062e-05, "epoch": 7.188417618270799, "percentage": 71.88, "elapsed_time": "6:00:19", "remaining_time": "2:20:55", "throughput": 4399.23, "total_tokens": 95109600} {"current_steps": 44070, "total_steps": 61300, "loss": 0.3367, "lr": 1.10993533682581e-05, "epoch": 7.189233278955954, "percentage": 71.89, "elapsed_time": "6:00:21", "remaining_time": "2:20:53", "throughput": 4399.27, "total_tokens": 95119424} {"current_steps": 44075, "total_steps": 61300, "loss": 0.3339, "lr": 1.1093437714121085e-05, "epoch": 7.190048939641109, "percentage": 71.9, "elapsed_time": "6:00:23", "remaining_time": "2:20:50", "throughput": 4399.31, "total_tokens": 95130368} {"current_steps": 44080, "total_steps": 61300, "loss": 0.3508, "lr": 1.108752318732057e-05, "epoch": 7.190864600326265, "percentage": 71.91, "elapsed_time": "6:00:26", "remaining_time": "2:20:48", "throughput": 4399.36, "total_tokens": 95142400} {"current_steps": 44085, "total_steps": 61300, "loss": 0.3602, "lr": 1.1081609788336014e-05, "epoch": 7.191680261011419, "percentage": 71.92, "elapsed_time": "6:00:28", "remaining_time": "2:20:45", "throughput": 4399.41, "total_tokens": 95153472} {"current_steps": 44090, "total_steps": 61300, "loss": 0.3455, "lr": 1.1075697517646794e-05, "epoch": 7.192495921696574, "percentage": 71.92, "elapsed_time": "6:00:30", "remaining_time": "2:20:43", "throughput": 4399.45, "total_tokens": 95163072} {"current_steps": 44095, "total_steps": 61300, "loss": 0.3577, "lr": 1.1069786375732181e-05, "epoch": 7.193311582381729, "percentage": 71.93, "elapsed_time": "6:00:33", "remaining_time": "2:20:40", "throughput": 4399.49, "total_tokens": 95174656} {"current_steps": 44100, "total_steps": 61300, "loss": 0.3317, "lr": 1.1063876363071368e-05, "epoch": 7.194127243066884, "percentage": 71.94, "elapsed_time": "6:00:35", "remaining_time": "2:20:38", "throughput": 4399.54, "total_tokens": 95184960} {"current_steps": 44105, "total_steps": 61300, "loss": 0.332, "lr": 1.1057967480143438e-05, "epoch": 7.19494290375204, "percentage": 71.95, "elapsed_time": "6:00:37", "remaining_time": "2:20:35", "throughput": 4399.57, "total_tokens": 95194848} {"current_steps": 44110, "total_steps": 61300, "loss": 0.3254, "lr": 1.1052059727427414e-05, "epoch": 7.195758564437194, "percentage": 71.96, "elapsed_time": "6:00:39", "remaining_time": "2:20:33", "throughput": 4399.63, "total_tokens": 95207072} {"current_steps": 44115, "total_steps": 61300, "loss": 0.3489, "lr": 1.1046153105402199e-05, "epoch": 7.196574225122349, "percentage": 71.97, "elapsed_time": "6:00:42", "remaining_time": "2:20:30", "throughput": 4399.67, "total_tokens": 95217920} {"current_steps": 44120, "total_steps": 61300, "loss": 0.3297, "lr": 1.1040247614546617e-05, "epoch": 7.197389885807504, "percentage": 71.97, "elapsed_time": "6:00:44", "remaining_time": "2:20:28", "throughput": 4399.71, "total_tokens": 95228224} {"current_steps": 44125, "total_steps": 61300, "loss": 0.3652, "lr": 1.1034343255339391e-05, "epoch": 7.198205546492659, "percentage": 71.98, "elapsed_time": "6:00:46", "remaining_time": "2:20:25", "throughput": 4399.76, "total_tokens": 95239008} {"current_steps": 44130, "total_steps": 61300, "loss": 0.327, "lr": 1.1028440028259154e-05, "epoch": 7.199021207177814, "percentage": 71.99, "elapsed_time": "6:00:48", "remaining_time": "2:20:22", "throughput": 4399.79, "total_tokens": 95248800} {"current_steps": 44135, "total_steps": 61300, "loss": 0.3214, "lr": 1.1022537933784472e-05, "epoch": 7.199836867862969, "percentage": 72.0, "elapsed_time": "6:00:50", "remaining_time": "2:20:20", "throughput": 4399.84, "total_tokens": 95259840} {"current_steps": 44140, "total_steps": 61300, "loss": 0.3453, "lr": 1.1016636972393782e-05, "epoch": 7.200652528548124, "percentage": 72.01, "elapsed_time": "6:00:53", "remaining_time": "2:20:17", "throughput": 4399.88, "total_tokens": 95270848} {"current_steps": 44145, "total_steps": 61300, "loss": 0.3513, "lr": 1.101073714456545e-05, "epoch": 7.201468189233279, "percentage": 72.01, "elapsed_time": "6:00:55", "remaining_time": "2:20:15", "throughput": 4399.91, "total_tokens": 95281472} {"current_steps": 44150, "total_steps": 61300, "loss": 0.3387, "lr": 1.1004838450777747e-05, "epoch": 7.202283849918434, "percentage": 72.02, "elapsed_time": "6:00:57", "remaining_time": "2:20:12", "throughput": 4399.96, "total_tokens": 95292160} {"current_steps": 44155, "total_steps": 61300, "loss": 0.3158, "lr": 1.099894089150885e-05, "epoch": 7.203099510603589, "percentage": 72.03, "elapsed_time": "6:00:59", "remaining_time": "2:20:10", "throughput": 4400.0, "total_tokens": 95302208} {"current_steps": 44160, "total_steps": 61300, "loss": 0.352, "lr": 1.0993044467236843e-05, "epoch": 7.2039151712887435, "percentage": 72.04, "elapsed_time": "6:01:01", "remaining_time": "2:20:07", "throughput": 4400.03, "total_tokens": 95312032} {"current_steps": 44165, "total_steps": 61300, "loss": 0.3283, "lr": 1.0987149178439726e-05, "epoch": 7.204730831973899, "percentage": 72.05, "elapsed_time": "6:01:04", "remaining_time": "2:20:05", "throughput": 4400.08, "total_tokens": 95323744} {"current_steps": 44170, "total_steps": 61300, "loss": 0.3138, "lr": 1.0981255025595394e-05, "epoch": 7.205546492659054, "percentage": 72.06, "elapsed_time": "6:01:06", "remaining_time": "2:20:02", "throughput": 4400.12, "total_tokens": 95333856} {"current_steps": 44175, "total_steps": 61300, "loss": 0.3112, "lr": 1.097536200918166e-05, "epoch": 7.206362153344209, "percentage": 72.06, "elapsed_time": "6:01:08", "remaining_time": "2:20:00", "throughput": 4400.18, "total_tokens": 95344864} {"current_steps": 44180, "total_steps": 61300, "loss": 0.3693, "lr": 1.0969470129676243e-05, "epoch": 7.207177814029364, "percentage": 72.07, "elapsed_time": "6:01:10", "remaining_time": "2:19:57", "throughput": 4400.22, "total_tokens": 95355520} {"current_steps": 44185, "total_steps": 61300, "loss": 0.3491, "lr": 1.096357938755677e-05, "epoch": 7.2079934747145185, "percentage": 72.08, "elapsed_time": "6:01:12", "remaining_time": "2:19:54", "throughput": 4400.26, "total_tokens": 95366752} {"current_steps": 44190, "total_steps": 61300, "loss": 0.3543, "lr": 1.0957689783300767e-05, "epoch": 7.208809135399674, "percentage": 72.09, "elapsed_time": "6:01:15", "remaining_time": "2:19:52", "throughput": 4400.31, "total_tokens": 95378304} {"current_steps": 44195, "total_steps": 61300, "loss": 0.3295, "lr": 1.0951801317385682e-05, "epoch": 7.209624796084829, "percentage": 72.1, "elapsed_time": "6:01:17", "remaining_time": "2:19:49", "throughput": 4400.36, "total_tokens": 95389024} {"current_steps": 44200, "total_steps": 61300, "loss": 0.3528, "lr": 1.0945913990288862e-05, "epoch": 7.210440456769984, "percentage": 72.1, "elapsed_time": "6:01:19", "remaining_time": "2:19:47", "throughput": 4400.39, "total_tokens": 95398656} {"current_steps": 44205, "total_steps": 61300, "loss": 0.3354, "lr": 1.0940027802487565e-05, "epoch": 7.211256117455139, "percentage": 72.11, "elapsed_time": "6:01:21", "remaining_time": "2:19:44", "throughput": 4400.43, "total_tokens": 95408160} {"current_steps": 44210, "total_steps": 61300, "loss": 0.3225, "lr": 1.0934142754458954e-05, "epoch": 7.212071778140293, "percentage": 72.12, "elapsed_time": "6:01:23", "remaining_time": "2:19:42", "throughput": 4400.48, "total_tokens": 95419936} {"current_steps": 44215, "total_steps": 61300, "loss": 0.3369, "lr": 1.0928258846680097e-05, "epoch": 7.212887438825448, "percentage": 72.13, "elapsed_time": "6:01:26", "remaining_time": "2:19:39", "throughput": 4400.52, "total_tokens": 95429952} {"current_steps": 44220, "total_steps": 61300, "loss": 0.3149, "lr": 1.092237607962798e-05, "epoch": 7.213703099510604, "percentage": 72.14, "elapsed_time": "6:01:28", "remaining_time": "2:19:37", "throughput": 4400.57, "total_tokens": 95441024} {"current_steps": 44225, "total_steps": 61300, "loss": 0.3106, "lr": 1.0916494453779489e-05, "epoch": 7.214518760195759, "percentage": 72.15, "elapsed_time": "6:01:30", "remaining_time": "2:19:34", "throughput": 4400.62, "total_tokens": 95452448} {"current_steps": 44230, "total_steps": 61300, "loss": 0.317, "lr": 1.0910613969611406e-05, "epoch": 7.215334420880914, "percentage": 72.15, "elapsed_time": "6:01:32", "remaining_time": "2:19:32", "throughput": 4400.66, "total_tokens": 95462432} {"current_steps": 44235, "total_steps": 61300, "loss": 0.3211, "lr": 1.0904734627600448e-05, "epoch": 7.216150081566068, "percentage": 72.16, "elapsed_time": "6:01:35", "remaining_time": "2:19:29", "throughput": 4400.7, "total_tokens": 95473312} {"current_steps": 44240, "total_steps": 61300, "loss": 0.3317, "lr": 1.0898856428223225e-05, "epoch": 7.216965742251223, "percentage": 72.17, "elapsed_time": "6:01:36", "remaining_time": "2:19:26", "throughput": 4400.73, "total_tokens": 95482624} {"current_steps": 44245, "total_steps": 61300, "loss": 0.3466, "lr": 1.0892979371956246e-05, "epoch": 7.217781402936378, "percentage": 72.18, "elapsed_time": "6:01:39", "remaining_time": "2:19:24", "throughput": 4400.78, "total_tokens": 95494304} {"current_steps": 44250, "total_steps": 61300, "loss": 0.3234, "lr": 1.088710345927594e-05, "epoch": 7.218597063621534, "percentage": 72.19, "elapsed_time": "6:01:41", "remaining_time": "2:19:21", "throughput": 4400.82, "total_tokens": 95505024} {"current_steps": 44255, "total_steps": 61300, "loss": 0.3216, "lr": 1.0881228690658634e-05, "epoch": 7.219412724306689, "percentage": 72.19, "elapsed_time": "6:01:43", "remaining_time": "2:19:19", "throughput": 4400.86, "total_tokens": 95516224} {"current_steps": 44260, "total_steps": 61300, "loss": 0.3318, "lr": 1.087535506658057e-05, "epoch": 7.220228384991843, "percentage": 72.2, "elapsed_time": "6:01:46", "remaining_time": "2:19:16", "throughput": 4400.9, "total_tokens": 95527168} {"current_steps": 44265, "total_steps": 61300, "loss": 0.2967, "lr": 1.086948258751789e-05, "epoch": 7.221044045676998, "percentage": 72.21, "elapsed_time": "6:01:48", "remaining_time": "2:19:14", "throughput": 4400.94, "total_tokens": 95537152} {"current_steps": 44270, "total_steps": 61300, "loss": 0.3137, "lr": 1.0863611253946651e-05, "epoch": 7.221859706362153, "percentage": 72.22, "elapsed_time": "6:01:50", "remaining_time": "2:19:11", "throughput": 4401.0, "total_tokens": 95549248} {"current_steps": 44275, "total_steps": 61300, "loss": 0.3284, "lr": 1.08577410663428e-05, "epoch": 7.222675367047309, "percentage": 72.23, "elapsed_time": "6:01:53", "remaining_time": "2:19:09", "throughput": 4401.05, "total_tokens": 95560704} {"current_steps": 44280, "total_steps": 61300, "loss": 0.3478, "lr": 1.0851872025182225e-05, "epoch": 7.2234910277324635, "percentage": 72.23, "elapsed_time": "6:01:55", "remaining_time": "2:19:06", "throughput": 4401.09, "total_tokens": 95572864} {"current_steps": 44285, "total_steps": 61300, "loss": 0.3162, "lr": 1.084600413094069e-05, "epoch": 7.224306688417618, "percentage": 72.24, "elapsed_time": "6:01:57", "remaining_time": "2:19:04", "throughput": 4401.12, "total_tokens": 95582944} {"current_steps": 44290, "total_steps": 61300, "loss": 0.3549, "lr": 1.0840137384093876e-05, "epoch": 7.225122349102773, "percentage": 72.25, "elapsed_time": "6:02:00", "remaining_time": "2:19:01", "throughput": 4401.16, "total_tokens": 95593472} {"current_steps": 44295, "total_steps": 61300, "loss": 0.3228, "lr": 1.0834271785117376e-05, "epoch": 7.225938009787928, "percentage": 72.26, "elapsed_time": "6:02:02", "remaining_time": "2:18:59", "throughput": 4401.2, "total_tokens": 95604064} {"current_steps": 44300, "total_steps": 61300, "loss": 0.3331, "lr": 1.0828407334486676e-05, "epoch": 7.226753670473083, "percentage": 72.27, "elapsed_time": "6:02:04", "remaining_time": "2:18:56", "throughput": 4401.25, "total_tokens": 95616192} {"current_steps": 44305, "total_steps": 61300, "loss": 0.3515, "lr": 1.0822544032677187e-05, "epoch": 7.2275693311582385, "percentage": 72.28, "elapsed_time": "6:02:07", "remaining_time": "2:18:54", "throughput": 4401.29, "total_tokens": 95626976} {"current_steps": 44310, "total_steps": 61300, "loss": 0.3348, "lr": 1.0816681880164215e-05, "epoch": 7.228384991843393, "percentage": 72.28, "elapsed_time": "6:02:08", "remaining_time": "2:18:51", "throughput": 4401.32, "total_tokens": 95635328} {"current_steps": 44315, "total_steps": 61300, "loss": 0.3655, "lr": 1.0810820877422973e-05, "epoch": 7.229200652528548, "percentage": 72.29, "elapsed_time": "6:02:10", "remaining_time": "2:18:48", "throughput": 4401.35, "total_tokens": 95645248} {"current_steps": 44320, "total_steps": 61300, "loss": 0.3653, "lr": 1.0804961024928587e-05, "epoch": 7.230016313213703, "percentage": 72.3, "elapsed_time": "6:02:13", "remaining_time": "2:18:46", "throughput": 4401.41, "total_tokens": 95656928} {"current_steps": 44325, "total_steps": 61300, "loss": 0.3521, "lr": 1.0799102323156082e-05, "epoch": 7.230831973898858, "percentage": 72.31, "elapsed_time": "6:02:15", "remaining_time": "2:18:43", "throughput": 4401.45, "total_tokens": 95667200} {"current_steps": 44330, "total_steps": 61300, "loss": 0.3441, "lr": 1.0793244772580402e-05, "epoch": 7.231647634584013, "percentage": 72.32, "elapsed_time": "6:02:17", "remaining_time": "2:18:41", "throughput": 4401.49, "total_tokens": 95677248} {"current_steps": 44335, "total_steps": 61300, "loss": 0.3493, "lr": 1.0787388373676374e-05, "epoch": 7.232463295269168, "percentage": 72.32, "elapsed_time": "6:02:19", "remaining_time": "2:18:38", "throughput": 4401.54, "total_tokens": 95687104} {"current_steps": 44340, "total_steps": 61300, "loss": 0.3195, "lr": 1.0781533126918767e-05, "epoch": 7.233278955954323, "percentage": 72.33, "elapsed_time": "6:02:21", "remaining_time": "2:18:36", "throughput": 4401.58, "total_tokens": 95697792} {"current_steps": 44345, "total_steps": 61300, "loss": 0.346, "lr": 1.077567903278223e-05, "epoch": 7.234094616639478, "percentage": 72.34, "elapsed_time": "6:02:23", "remaining_time": "2:18:33", "throughput": 4401.63, "total_tokens": 95708800} {"current_steps": 44350, "total_steps": 61300, "loss": 0.3497, "lr": 1.0769826091741323e-05, "epoch": 7.234910277324633, "percentage": 72.35, "elapsed_time": "6:02:26", "remaining_time": "2:18:31", "throughput": 4401.67, "total_tokens": 95719296} {"current_steps": 44355, "total_steps": 61300, "loss": 0.3422, "lr": 1.0763974304270516e-05, "epoch": 7.235725938009788, "percentage": 72.36, "elapsed_time": "6:02:28", "remaining_time": "2:18:28", "throughput": 4401.71, "total_tokens": 95730336} {"current_steps": 44360, "total_steps": 61300, "loss": 0.3546, "lr": 1.0758123670844186e-05, "epoch": 7.236541598694943, "percentage": 72.37, "elapsed_time": "6:02:30", "remaining_time": "2:18:26", "throughput": 4401.76, "total_tokens": 95741760} {"current_steps": 44365, "total_steps": 61300, "loss": 0.3332, "lr": 1.0752274191936611e-05, "epoch": 7.237357259380098, "percentage": 72.37, "elapsed_time": "6:02:33", "remaining_time": "2:18:23", "throughput": 4401.79, "total_tokens": 95752896} {"current_steps": 44370, "total_steps": 61300, "loss": 0.3349, "lr": 1.0746425868021986e-05, "epoch": 7.238172920065253, "percentage": 72.38, "elapsed_time": "6:02:35", "remaining_time": "2:18:21", "throughput": 4401.84, "total_tokens": 95763968} {"current_steps": 44375, "total_steps": 61300, "loss": 0.3391, "lr": 1.07405786995744e-05, "epoch": 7.238988580750408, "percentage": 72.39, "elapsed_time": "6:02:37", "remaining_time": "2:18:18", "throughput": 4401.88, "total_tokens": 95774528} {"current_steps": 44380, "total_steps": 61300, "loss": 0.3459, "lr": 1.0734732687067856e-05, "epoch": 7.239804241435563, "percentage": 72.4, "elapsed_time": "6:02:39", "remaining_time": "2:18:16", "throughput": 4401.93, "total_tokens": 95785600} {"current_steps": 44385, "total_steps": 61300, "loss": 0.3391, "lr": 1.0728887830976261e-05, "epoch": 7.240619902120717, "percentage": 72.41, "elapsed_time": "6:02:41", "remaining_time": "2:18:13", "throughput": 4401.95, "total_tokens": 95795104} {"current_steps": 44390, "total_steps": 61300, "loss": 0.3274, "lr": 1.0723044131773433e-05, "epoch": 7.241435562805873, "percentage": 72.41, "elapsed_time": "6:02:44", "remaining_time": "2:18:10", "throughput": 4402.0, "total_tokens": 95807104} {"current_steps": 44395, "total_steps": 61300, "loss": 0.3442, "lr": 1.0717201589933085e-05, "epoch": 7.242251223491028, "percentage": 72.42, "elapsed_time": "6:02:46", "remaining_time": "2:18:08", "throughput": 4402.04, "total_tokens": 95816832} {"current_steps": 44400, "total_steps": 61300, "loss": 0.3253, "lr": 1.0711360205928847e-05, "epoch": 7.243066884176183, "percentage": 72.43, "elapsed_time": "6:02:48", "remaining_time": "2:18:05", "throughput": 4402.08, "total_tokens": 95826688} {"current_steps": 44405, "total_steps": 61300, "loss": 0.3213, "lr": 1.070551998023425e-05, "epoch": 7.2438825448613375, "percentage": 72.44, "elapsed_time": "6:02:50", "remaining_time": "2:18:03", "throughput": 4402.12, "total_tokens": 95835904} {"current_steps": 44410, "total_steps": 61300, "loss": 0.3396, "lr": 1.0699680913322736e-05, "epoch": 7.244698205546492, "percentage": 72.45, "elapsed_time": "6:02:52", "remaining_time": "2:18:00", "throughput": 4402.16, "total_tokens": 95847136} {"current_steps": 44415, "total_steps": 61300, "loss": 0.3359, "lr": 1.0693843005667633e-05, "epoch": 7.245513866231648, "percentage": 72.46, "elapsed_time": "6:02:55", "remaining_time": "2:17:58", "throughput": 4402.21, "total_tokens": 95858368} {"current_steps": 44420, "total_steps": 61300, "loss": 0.3414, "lr": 1.0688006257742214e-05, "epoch": 7.246329526916803, "percentage": 72.46, "elapsed_time": "6:02:57", "remaining_time": "2:17:55", "throughput": 4402.24, "total_tokens": 95868544} {"current_steps": 44425, "total_steps": 61300, "loss": 0.324, "lr": 1.0682170670019628e-05, "epoch": 7.247145187601958, "percentage": 72.47, "elapsed_time": "6:02:59", "remaining_time": "2:17:52", "throughput": 4402.28, "total_tokens": 95878944} {"current_steps": 44430, "total_steps": 61300, "loss": 0.3336, "lr": 1.0676336242972934e-05, "epoch": 7.2479608482871125, "percentage": 72.48, "elapsed_time": "6:03:01", "remaining_time": "2:17:50", "throughput": 4402.33, "total_tokens": 95889792} {"current_steps": 44435, "total_steps": 61300, "loss": 0.3108, "lr": 1.0670502977075103e-05, "epoch": 7.248776508972267, "percentage": 72.49, "elapsed_time": "6:03:03", "remaining_time": "2:17:47", "throughput": 4402.37, "total_tokens": 95900896} {"current_steps": 44440, "total_steps": 61300, "loss": 0.3556, "lr": 1.0664670872799006e-05, "epoch": 7.249592169657422, "percentage": 72.5, "elapsed_time": "6:03:06", "remaining_time": "2:17:45", "throughput": 4402.42, "total_tokens": 95911808} {"current_steps": 44445, "total_steps": 61300, "loss": 0.3332, "lr": 1.065883993061742e-05, "epoch": 7.250407830342578, "percentage": 72.5, "elapsed_time": "6:03:08", "remaining_time": "2:17:42", "throughput": 4402.45, "total_tokens": 95921696} {"current_steps": 44450, "total_steps": 61300, "loss": 0.3444, "lr": 1.065301015100304e-05, "epoch": 7.251223491027733, "percentage": 72.51, "elapsed_time": "6:03:10", "remaining_time": "2:17:40", "throughput": 4402.49, "total_tokens": 95931104} {"current_steps": 44455, "total_steps": 61300, "loss": 0.3248, "lr": 1.0647181534428455e-05, "epoch": 7.2520391517128875, "percentage": 72.52, "elapsed_time": "6:03:12", "remaining_time": "2:17:37", "throughput": 4402.53, "total_tokens": 95941376} {"current_steps": 44460, "total_steps": 61300, "loss": 0.3126, "lr": 1.0641354081366161e-05, "epoch": 7.252854812398042, "percentage": 72.53, "elapsed_time": "6:03:14", "remaining_time": "2:17:34", "throughput": 4402.56, "total_tokens": 95950496} {"current_steps": 44465, "total_steps": 61300, "loss": 0.343, "lr": 1.0635527792288558e-05, "epoch": 7.253670473083197, "percentage": 72.54, "elapsed_time": "6:03:16", "remaining_time": "2:17:32", "throughput": 4402.61, "total_tokens": 95961824} {"current_steps": 44470, "total_steps": 61300, "loss": 0.3276, "lr": 1.0629702667667959e-05, "epoch": 7.254486133768353, "percentage": 72.54, "elapsed_time": "6:03:18", "remaining_time": "2:17:29", "throughput": 4402.65, "total_tokens": 95972768} {"current_steps": 44475, "total_steps": 61300, "loss": 0.3341, "lr": 1.0623878707976575e-05, "epoch": 7.255301794453508, "percentage": 72.55, "elapsed_time": "6:03:21", "remaining_time": "2:17:27", "throughput": 4402.7, "total_tokens": 95985024} {"current_steps": 44480, "total_steps": 61300, "loss": 0.3342, "lr": 1.0618055913686525e-05, "epoch": 7.2561174551386625, "percentage": 72.56, "elapsed_time": "6:03:23", "remaining_time": "2:17:25", "throughput": 4402.75, "total_tokens": 95996768} {"current_steps": 44485, "total_steps": 61300, "loss": 0.3531, "lr": 1.061223428526984e-05, "epoch": 7.256933115823817, "percentage": 72.57, "elapsed_time": "6:03:26", "remaining_time": "2:17:22", "throughput": 4402.78, "total_tokens": 96007328} {"current_steps": 44490, "total_steps": 61300, "loss": 0.3372, "lr": 1.0606413823198444e-05, "epoch": 7.257748776508972, "percentage": 72.58, "elapsed_time": "6:03:28", "remaining_time": "2:17:19", "throughput": 4402.81, "total_tokens": 96017472} {"current_steps": 44495, "total_steps": 61300, "loss": 0.3557, "lr": 1.0600594527944174e-05, "epoch": 7.258564437194127, "percentage": 72.59, "elapsed_time": "6:03:30", "remaining_time": "2:17:17", "throughput": 4402.84, "total_tokens": 96026048} {"current_steps": 44500, "total_steps": 61300, "loss": 0.3007, "lr": 1.0594776399978776e-05, "epoch": 7.259380097879283, "percentage": 72.59, "elapsed_time": "6:03:32", "remaining_time": "2:17:14", "throughput": 4402.88, "total_tokens": 96037024} {"current_steps": 44505, "total_steps": 61300, "loss": 0.3631, "lr": 1.0588959439773893e-05, "epoch": 7.260195758564437, "percentage": 72.6, "elapsed_time": "6:03:34", "remaining_time": "2:17:12", "throughput": 4402.93, "total_tokens": 96048640} {"current_steps": 44510, "total_steps": 61300, "loss": 0.3059, "lr": 1.058314364780108e-05, "epoch": 7.261011419249592, "percentage": 72.61, "elapsed_time": "6:03:37", "remaining_time": "2:17:09", "throughput": 4402.98, "total_tokens": 96059968} {"current_steps": 44515, "total_steps": 61300, "loss": 0.3264, "lr": 1.0577329024531792e-05, "epoch": 7.261827079934747, "percentage": 72.62, "elapsed_time": "6:03:39", "remaining_time": "2:17:07", "throughput": 4403.01, "total_tokens": 96070592} {"current_steps": 44520, "total_steps": 61300, "loss": 0.3328, "lr": 1.0571515570437396e-05, "epoch": 7.262642740619902, "percentage": 72.63, "elapsed_time": "6:03:41", "remaining_time": "2:17:04", "throughput": 4403.05, "total_tokens": 96080768} {"current_steps": 44525, "total_steps": 61300, "loss": 0.3105, "lr": 1.0565703285989154e-05, "epoch": 7.263458401305057, "percentage": 72.63, "elapsed_time": "6:03:43", "remaining_time": "2:17:02", "throughput": 4403.09, "total_tokens": 96091584} {"current_steps": 44530, "total_steps": 61300, "loss": 0.3261, "lr": 1.0559892171658245e-05, "epoch": 7.264274061990212, "percentage": 72.64, "elapsed_time": "6:03:46", "remaining_time": "2:16:59", "throughput": 4403.13, "total_tokens": 96103264} {"current_steps": 44535, "total_steps": 61300, "loss": 0.3255, "lr": 1.0554082227915743e-05, "epoch": 7.265089722675367, "percentage": 72.65, "elapsed_time": "6:03:48", "remaining_time": "2:16:57", "throughput": 4403.17, "total_tokens": 96112992} {"current_steps": 44540, "total_steps": 61300, "loss": 0.307, "lr": 1.0548273455232634e-05, "epoch": 7.265905383360522, "percentage": 72.66, "elapsed_time": "6:03:50", "remaining_time": "2:16:54", "throughput": 4403.21, "total_tokens": 96124480} {"current_steps": 44545, "total_steps": 61300, "loss": 0.3295, "lr": 1.0542465854079806e-05, "epoch": 7.266721044045677, "percentage": 72.67, "elapsed_time": "6:03:52", "remaining_time": "2:16:52", "throughput": 4403.26, "total_tokens": 96134848} {"current_steps": 44550, "total_steps": 61300, "loss": 0.3375, "lr": 1.0536659424928044e-05, "epoch": 7.267536704730832, "percentage": 72.68, "elapsed_time": "6:03:55", "remaining_time": "2:16:49", "throughput": 4403.3, "total_tokens": 96146176} {"current_steps": 44555, "total_steps": 61300, "loss": 0.3385, "lr": 1.0530854168248064e-05, "epoch": 7.268352365415987, "percentage": 72.68, "elapsed_time": "6:03:57", "remaining_time": "2:16:47", "throughput": 4403.34, "total_tokens": 96157824} {"current_steps": 44560, "total_steps": 61300, "loss": 0.3447, "lr": 1.052505008451046e-05, "epoch": 7.269168026101142, "percentage": 72.69, "elapsed_time": "6:03:59", "remaining_time": "2:16:44", "throughput": 4403.39, "total_tokens": 96168992} {"current_steps": 44565, "total_steps": 61300, "loss": 0.3137, "lr": 1.0519247174185742e-05, "epoch": 7.269983686786297, "percentage": 72.7, "elapsed_time": "6:04:02", "remaining_time": "2:16:42", "throughput": 4403.42, "total_tokens": 96179712} {"current_steps": 44570, "total_steps": 61300, "loss": 0.3331, "lr": 1.0513445437744323e-05, "epoch": 7.270799347471452, "percentage": 72.71, "elapsed_time": "6:04:04", "remaining_time": "2:16:39", "throughput": 4403.47, "total_tokens": 96190656} {"current_steps": 44575, "total_steps": 61300, "loss": 0.2772, "lr": 1.0507644875656523e-05, "epoch": 7.271615008156607, "percentage": 72.72, "elapsed_time": "6:04:06", "remaining_time": "2:16:37", "throughput": 4403.51, "total_tokens": 96201120} {"current_steps": 44580, "total_steps": 61300, "loss": 0.3127, "lr": 1.0501845488392558e-05, "epoch": 7.2724306688417615, "percentage": 72.72, "elapsed_time": "6:04:08", "remaining_time": "2:16:34", "throughput": 4403.54, "total_tokens": 96210304} {"current_steps": 44585, "total_steps": 61300, "loss": 0.3333, "lr": 1.0496047276422554e-05, "epoch": 7.273246329526917, "percentage": 72.73, "elapsed_time": "6:04:10", "remaining_time": "2:16:31", "throughput": 4403.58, "total_tokens": 96221472} {"current_steps": 44590, "total_steps": 61300, "loss": 0.338, "lr": 1.0490250240216562e-05, "epoch": 7.274061990212072, "percentage": 72.74, "elapsed_time": "6:04:13", "remaining_time": "2:16:29", "throughput": 4403.63, "total_tokens": 96232736} {"current_steps": 44595, "total_steps": 61300, "loss": 0.335, "lr": 1.0484454380244505e-05, "epoch": 7.274877650897227, "percentage": 72.75, "elapsed_time": "6:04:15", "remaining_time": "2:16:26", "throughput": 4403.69, "total_tokens": 96244352} {"current_steps": 44600, "total_steps": 61300, "loss": 0.3455, "lr": 1.0478659696976225e-05, "epoch": 7.275693311582382, "percentage": 72.76, "elapsed_time": "6:04:17", "remaining_time": "2:16:24", "throughput": 4403.72, "total_tokens": 96254240} {"current_steps": 44605, "total_steps": 61300, "loss": 0.3087, "lr": 1.0472866190881473e-05, "epoch": 7.2765089722675365, "percentage": 72.77, "elapsed_time": "6:04:19", "remaining_time": "2:16:21", "throughput": 4403.77, "total_tokens": 96265696} {"current_steps": 44610, "total_steps": 61300, "loss": 0.3614, "lr": 1.0467073862429897e-05, "epoch": 7.277324632952691, "percentage": 72.77, "elapsed_time": "6:04:22", "remaining_time": "2:16:19", "throughput": 4403.82, "total_tokens": 96277664} {"current_steps": 44615, "total_steps": 61300, "loss": 0.3037, "lr": 1.0461282712091053e-05, "epoch": 7.278140293637847, "percentage": 72.78, "elapsed_time": "6:04:24", "remaining_time": "2:16:16", "throughput": 4403.86, "total_tokens": 96288448} {"current_steps": 44620, "total_steps": 61300, "loss": 0.2707, "lr": 1.0455492740334399e-05, "epoch": 7.278955954323002, "percentage": 72.79, "elapsed_time": "6:04:26", "remaining_time": "2:16:14", "throughput": 4403.9, "total_tokens": 96298432} {"current_steps": 44625, "total_steps": 61300, "loss": 0.3189, "lr": 1.0449703947629305e-05, "epoch": 7.279771615008157, "percentage": 72.8, "elapsed_time": "6:04:28", "remaining_time": "2:16:11", "throughput": 4403.93, "total_tokens": 96309568} {"current_steps": 44630, "total_steps": 61300, "loss": 0.3773, "lr": 1.0443916334445034e-05, "epoch": 7.280587275693311, "percentage": 72.81, "elapsed_time": "6:04:31", "remaining_time": "2:16:09", "throughput": 4403.97, "total_tokens": 96319968} {"current_steps": 44635, "total_steps": 61300, "loss": 0.3371, "lr": 1.0438129901250762e-05, "epoch": 7.281402936378466, "percentage": 72.81, "elapsed_time": "6:04:33", "remaining_time": "2:16:06", "throughput": 4404.01, "total_tokens": 96331232} {"current_steps": 44640, "total_steps": 61300, "loss": 0.3388, "lr": 1.0432344648515569e-05, "epoch": 7.282218597063622, "percentage": 72.82, "elapsed_time": "6:04:35", "remaining_time": "2:16:04", "throughput": 4404.05, "total_tokens": 96341696} {"current_steps": 44645, "total_steps": 61300, "loss": 0.3759, "lr": 1.042656057670843e-05, "epoch": 7.283034257748777, "percentage": 72.83, "elapsed_time": "6:04:37", "remaining_time": "2:16:01", "throughput": 4404.1, "total_tokens": 96352160} {"current_steps": 44650, "total_steps": 61300, "loss": 0.3358, "lr": 1.042077768629824e-05, "epoch": 7.283849918433932, "percentage": 72.84, "elapsed_time": "6:04:40", "remaining_time": "2:15:59", "throughput": 4404.13, "total_tokens": 96362592} {"current_steps": 44655, "total_steps": 61300, "loss": 0.3156, "lr": 1.0414995977753772e-05, "epoch": 7.284665579119086, "percentage": 72.85, "elapsed_time": "6:04:42", "remaining_time": "2:15:56", "throughput": 4404.18, "total_tokens": 96375424} {"current_steps": 44660, "total_steps": 61300, "loss": 0.3313, "lr": 1.0409215451543746e-05, "epoch": 7.285481239804241, "percentage": 72.85, "elapsed_time": "6:04:45", "remaining_time": "2:15:54", "throughput": 4404.23, "total_tokens": 96387296} {"current_steps": 44665, "total_steps": 61300, "loss": 0.3195, "lr": 1.0403436108136747e-05, "epoch": 7.286296900489396, "percentage": 72.86, "elapsed_time": "6:04:47", "remaining_time": "2:15:51", "throughput": 4404.27, "total_tokens": 96397632} {"current_steps": 44670, "total_steps": 61300, "loss": 0.3675, "lr": 1.039765794800128e-05, "epoch": 7.287112561174552, "percentage": 72.87, "elapsed_time": "6:04:49", "remaining_time": "2:15:49", "throughput": 4404.31, "total_tokens": 96408096} {"current_steps": 44675, "total_steps": 61300, "loss": 0.3104, "lr": 1.0391880971605749e-05, "epoch": 7.287928221859707, "percentage": 72.88, "elapsed_time": "6:04:51", "remaining_time": "2:15:46", "throughput": 4404.35, "total_tokens": 96417408} {"current_steps": 44680, "total_steps": 61300, "loss": 0.3346, "lr": 1.0386105179418467e-05, "epoch": 7.288743882544861, "percentage": 72.89, "elapsed_time": "6:04:53", "remaining_time": "2:15:43", "throughput": 4404.38, "total_tokens": 96427328} {"current_steps": 44685, "total_steps": 61300, "loss": 0.3316, "lr": 1.0380330571907654e-05, "epoch": 7.289559543230016, "percentage": 72.9, "elapsed_time": "6:04:55", "remaining_time": "2:15:41", "throughput": 4404.42, "total_tokens": 96437920} {"current_steps": 44690, "total_steps": 61300, "loss": 0.3253, "lr": 1.037455714954142e-05, "epoch": 7.290375203915171, "percentage": 72.9, "elapsed_time": "6:04:57", "remaining_time": "2:15:38", "throughput": 4404.46, "total_tokens": 96447872} {"current_steps": 44695, "total_steps": 61300, "loss": 0.3644, "lr": 1.0368784912787794e-05, "epoch": 7.291190864600326, "percentage": 72.91, "elapsed_time": "6:04:59", "remaining_time": "2:15:36", "throughput": 4404.5, "total_tokens": 96458592} {"current_steps": 44700, "total_steps": 61300, "loss": 0.3238, "lr": 1.03630138621147e-05, "epoch": 7.2920065252854815, "percentage": 72.92, "elapsed_time": "6:05:02", "remaining_time": "2:15:33", "throughput": 4404.54, "total_tokens": 96469312} {"current_steps": 44705, "total_steps": 61300, "loss": 0.3338, "lr": 1.035724399798997e-05, "epoch": 7.292822185970636, "percentage": 72.93, "elapsed_time": "6:05:04", "remaining_time": "2:15:31", "throughput": 4404.59, "total_tokens": 96478976} {"current_steps": 44710, "total_steps": 61300, "loss": 0.3187, "lr": 1.035147532088134e-05, "epoch": 7.293637846655791, "percentage": 72.94, "elapsed_time": "6:05:06", "remaining_time": "2:15:28", "throughput": 4404.63, "total_tokens": 96489952} {"current_steps": 44715, "total_steps": 61300, "loss": 0.3631, "lr": 1.0345707831256443e-05, "epoch": 7.294453507340946, "percentage": 72.94, "elapsed_time": "6:05:08", "remaining_time": "2:15:26", "throughput": 4404.67, "total_tokens": 96500672} {"current_steps": 44720, "total_steps": 61300, "loss": 0.3598, "lr": 1.0339941529582828e-05, "epoch": 7.295269168026101, "percentage": 72.95, "elapsed_time": "6:05:10", "remaining_time": "2:15:23", "throughput": 4404.71, "total_tokens": 96511488} {"current_steps": 44725, "total_steps": 61300, "loss": 0.3101, "lr": 1.0334176416327935e-05, "epoch": 7.2960848287112565, "percentage": 72.96, "elapsed_time": "6:05:13", "remaining_time": "2:15:20", "throughput": 4404.75, "total_tokens": 96522336} {"current_steps": 44730, "total_steps": 61300, "loss": 0.3294, "lr": 1.0328412491959104e-05, "epoch": 7.296900489396411, "percentage": 72.97, "elapsed_time": "6:05:15", "remaining_time": "2:15:18", "throughput": 4404.79, "total_tokens": 96533088} {"current_steps": 44735, "total_steps": 61300, "loss": 0.338, "lr": 1.0322649756943611e-05, "epoch": 7.297716150081566, "percentage": 72.98, "elapsed_time": "6:05:17", "remaining_time": "2:15:15", "throughput": 4404.83, "total_tokens": 96543552} {"current_steps": 44740, "total_steps": 61300, "loss": 0.3209, "lr": 1.0316888211748601e-05, "epoch": 7.298531810766721, "percentage": 72.99, "elapsed_time": "6:05:19", "remaining_time": "2:15:13", "throughput": 4404.87, "total_tokens": 96554432} {"current_steps": 44745, "total_steps": 61300, "loss": 0.3666, "lr": 1.0311127856841136e-05, "epoch": 7.299347471451876, "percentage": 72.99, "elapsed_time": "6:05:22", "remaining_time": "2:15:10", "throughput": 4404.91, "total_tokens": 96565536} {"current_steps": 44750, "total_steps": 61300, "loss": 0.3337, "lr": 1.0305368692688174e-05, "epoch": 7.300163132137031, "percentage": 73.0, "elapsed_time": "6:05:24", "remaining_time": "2:15:08", "throughput": 4404.96, "total_tokens": 96576576} {"current_steps": 44755, "total_steps": 61300, "loss": 0.3139, "lr": 1.0299610719756587e-05, "epoch": 7.300978792822186, "percentage": 73.01, "elapsed_time": "6:05:27", "remaining_time": "2:15:05", "throughput": 4405.0, "total_tokens": 96588640} {"current_steps": 44760, "total_steps": 61300, "loss": 0.3638, "lr": 1.0293853938513142e-05, "epoch": 7.301794453507341, "percentage": 73.02, "elapsed_time": "6:05:29", "remaining_time": "2:15:03", "throughput": 4405.05, "total_tokens": 96600160} {"current_steps": 44765, "total_steps": 61300, "loss": 0.3291, "lr": 1.028809834942451e-05, "epoch": 7.302610114192496, "percentage": 73.03, "elapsed_time": "6:05:31", "remaining_time": "2:15:00", "throughput": 4405.09, "total_tokens": 96610944} {"current_steps": 44770, "total_steps": 61300, "loss": 0.3278, "lr": 1.028234395295728e-05, "epoch": 7.303425774877651, "percentage": 73.03, "elapsed_time": "6:05:33", "remaining_time": "2:14:58", "throughput": 4405.13, "total_tokens": 96620960} {"current_steps": 44775, "total_steps": 61300, "loss": 0.3481, "lr": 1.0276590749577924e-05, "epoch": 7.304241435562806, "percentage": 73.04, "elapsed_time": "6:05:35", "remaining_time": "2:14:55", "throughput": 4405.17, "total_tokens": 96630592} {"current_steps": 44780, "total_steps": 61300, "loss": 0.315, "lr": 1.027083873975283e-05, "epoch": 7.30505709624796, "percentage": 73.05, "elapsed_time": "6:05:38", "remaining_time": "2:14:53", "throughput": 4405.22, "total_tokens": 96642368} {"current_steps": 44785, "total_steps": 61300, "loss": 0.357, "lr": 1.0265087923948283e-05, "epoch": 7.305872756933116, "percentage": 73.06, "elapsed_time": "6:05:40", "remaining_time": "2:14:50", "throughput": 4405.27, "total_tokens": 96654464} {"current_steps": 44790, "total_steps": 61300, "loss": 0.3309, "lr": 1.0259338302630472e-05, "epoch": 7.306688417618271, "percentage": 73.07, "elapsed_time": "6:05:42", "remaining_time": "2:14:48", "throughput": 4405.3, "total_tokens": 96664992} {"current_steps": 44795, "total_steps": 61300, "loss": 0.3238, "lr": 1.025358987626549e-05, "epoch": 7.307504078303426, "percentage": 73.08, "elapsed_time": "6:05:44", "remaining_time": "2:14:45", "throughput": 4405.34, "total_tokens": 96675168} {"current_steps": 44800, "total_steps": 61300, "loss": 0.3532, "lr": 1.0247842645319339e-05, "epoch": 7.308319738988581, "percentage": 73.08, "elapsed_time": "6:05:47", "remaining_time": "2:14:43", "throughput": 4405.38, "total_tokens": 96684992} {"current_steps": 44805, "total_steps": 61300, "loss": 0.3216, "lr": 1.0242096610257911e-05, "epoch": 7.309135399673735, "percentage": 73.09, "elapsed_time": "6:05:49", "remaining_time": "2:14:40", "throughput": 4405.42, "total_tokens": 96695808} {"current_steps": 44810, "total_steps": 61300, "loss": 0.3377, "lr": 1.0236351771547014e-05, "epoch": 7.309951060358891, "percentage": 73.1, "elapsed_time": "6:05:51", "remaining_time": "2:14:38", "throughput": 4405.47, "total_tokens": 96707840} {"current_steps": 44815, "total_steps": 61300, "loss": 0.3151, "lr": 1.0230608129652355e-05, "epoch": 7.310766721044046, "percentage": 73.11, "elapsed_time": "6:05:54", "remaining_time": "2:14:35", "throughput": 4405.51, "total_tokens": 96718784} {"current_steps": 44820, "total_steps": 61300, "loss": 0.3216, "lr": 1.022486568503954e-05, "epoch": 7.311582381729201, "percentage": 73.12, "elapsed_time": "6:05:56", "remaining_time": "2:14:33", "throughput": 4405.55, "total_tokens": 96729376} {"current_steps": 44825, "total_steps": 61300, "loss": 0.3239, "lr": 1.0219124438174076e-05, "epoch": 7.3123980424143555, "percentage": 73.12, "elapsed_time": "6:05:58", "remaining_time": "2:14:30", "throughput": 4405.59, "total_tokens": 96740640} {"current_steps": 44830, "total_steps": 61300, "loss": 0.3443, "lr": 1.0213384389521385e-05, "epoch": 7.31321370309951, "percentage": 73.13, "elapsed_time": "6:06:00", "remaining_time": "2:14:28", "throughput": 4405.63, "total_tokens": 96751104} {"current_steps": 44835, "total_steps": 61300, "loss": 0.3278, "lr": 1.0207645539546784e-05, "epoch": 7.314029363784665, "percentage": 73.14, "elapsed_time": "6:06:02", "remaining_time": "2:14:25", "throughput": 4405.66, "total_tokens": 96760672} {"current_steps": 44840, "total_steps": 61300, "loss": 0.3203, "lr": 1.020190788871549e-05, "epoch": 7.314845024469821, "percentage": 73.15, "elapsed_time": "6:06:05", "remaining_time": "2:14:23", "throughput": 4405.7, "total_tokens": 96771840} {"current_steps": 44845, "total_steps": 61300, "loss": 0.3316, "lr": 1.0196171437492627e-05, "epoch": 7.315660685154976, "percentage": 73.16, "elapsed_time": "6:06:07", "remaining_time": "2:14:20", "throughput": 4405.75, "total_tokens": 96782592} {"current_steps": 44850, "total_steps": 61300, "loss": 0.3153, "lr": 1.0190436186343218e-05, "epoch": 7.3164763458401305, "percentage": 73.16, "elapsed_time": "6:06:09", "remaining_time": "2:14:17", "throughput": 4405.8, "total_tokens": 96794016} {"current_steps": 44855, "total_steps": 61300, "loss": 0.3247, "lr": 1.01847021357322e-05, "epoch": 7.317292006525285, "percentage": 73.17, "elapsed_time": "6:06:11", "remaining_time": "2:14:15", "throughput": 4405.84, "total_tokens": 96803968} {"current_steps": 44860, "total_steps": 61300, "loss": 0.3022, "lr": 1.0178969286124396e-05, "epoch": 7.31810766721044, "percentage": 73.18, "elapsed_time": "6:06:13", "remaining_time": "2:14:12", "throughput": 4405.87, "total_tokens": 96814304} {"current_steps": 44865, "total_steps": 61300, "loss": 0.3289, "lr": 1.0173237637984542e-05, "epoch": 7.318923327895595, "percentage": 73.19, "elapsed_time": "6:06:15", "remaining_time": "2:14:10", "throughput": 4405.91, "total_tokens": 96824128} {"current_steps": 44870, "total_steps": 61300, "loss": 0.3448, "lr": 1.016750719177727e-05, "epoch": 7.319738988580751, "percentage": 73.2, "elapsed_time": "6:06:18", "remaining_time": "2:14:07", "throughput": 4405.97, "total_tokens": 96835712} {"current_steps": 44875, "total_steps": 61300, "loss": 0.3192, "lr": 1.016177794796713e-05, "epoch": 7.3205546492659055, "percentage": 73.21, "elapsed_time": "6:06:20", "remaining_time": "2:14:05", "throughput": 4406.0, "total_tokens": 96846272} {"current_steps": 44880, "total_steps": 61300, "loss": 0.3114, "lr": 1.0156049907018562e-05, "epoch": 7.32137030995106, "percentage": 73.21, "elapsed_time": "6:06:22", "remaining_time": "2:14:02", "throughput": 4406.05, "total_tokens": 96857408} {"current_steps": 44885, "total_steps": 61300, "loss": 0.2983, "lr": 1.0150323069395901e-05, "epoch": 7.322185970636215, "percentage": 73.22, "elapsed_time": "6:06:25", "remaining_time": "2:14:00", "throughput": 4406.09, "total_tokens": 96868032} {"current_steps": 44890, "total_steps": 61300, "loss": 0.3261, "lr": 1.01445974355634e-05, "epoch": 7.32300163132137, "percentage": 73.23, "elapsed_time": "6:06:27", "remaining_time": "2:13:57", "throughput": 4406.15, "total_tokens": 96879136} {"current_steps": 44895, "total_steps": 61300, "loss": 0.355, "lr": 1.0138873005985208e-05, "epoch": 7.323817292006526, "percentage": 73.24, "elapsed_time": "6:06:29", "remaining_time": "2:13:55", "throughput": 4406.19, "total_tokens": 96890016} {"current_steps": 44900, "total_steps": 61300, "loss": 0.3284, "lr": 1.0133149781125365e-05, "epoch": 7.3246329526916805, "percentage": 73.25, "elapsed_time": "6:06:31", "remaining_time": "2:13:52", "throughput": 4406.22, "total_tokens": 96900160} {"current_steps": 44905, "total_steps": 61300, "loss": 0.3373, "lr": 1.0127427761447842e-05, "epoch": 7.325448613376835, "percentage": 73.25, "elapsed_time": "6:06:33", "remaining_time": "2:13:49", "throughput": 4406.25, "total_tokens": 96909856} {"current_steps": 44910, "total_steps": 61300, "loss": 0.3296, "lr": 1.012170694741649e-05, "epoch": 7.32626427406199, "percentage": 73.26, "elapsed_time": "6:06:36", "remaining_time": "2:13:47", "throughput": 4406.3, "total_tokens": 96921280} {"current_steps": 44915, "total_steps": 61300, "loss": 0.3507, "lr": 1.0115987339495061e-05, "epoch": 7.327079934747145, "percentage": 73.27, "elapsed_time": "6:06:38", "remaining_time": "2:13:44", "throughput": 4406.34, "total_tokens": 96931136} {"current_steps": 44920, "total_steps": 61300, "loss": 0.2761, "lr": 1.0110268938147222e-05, "epoch": 7.327895595432301, "percentage": 73.28, "elapsed_time": "6:06:40", "remaining_time": "2:13:42", "throughput": 4406.39, "total_tokens": 96942112} {"current_steps": 44925, "total_steps": 61300, "loss": 0.3197, "lr": 1.0104551743836532e-05, "epoch": 7.328711256117455, "percentage": 73.29, "elapsed_time": "6:06:42", "remaining_time": "2:13:39", "throughput": 4406.43, "total_tokens": 96953664} {"current_steps": 44930, "total_steps": 61300, "loss": 0.3343, "lr": 1.0098835757026457e-05, "epoch": 7.32952691680261, "percentage": 73.3, "elapsed_time": "6:06:45", "remaining_time": "2:13:37", "throughput": 4406.47, "total_tokens": 96964800} {"current_steps": 44935, "total_steps": 61300, "loss": 0.3322, "lr": 1.009312097818036e-05, "epoch": 7.330342577487765, "percentage": 73.3, "elapsed_time": "6:06:47", "remaining_time": "2:13:34", "throughput": 4406.51, "total_tokens": 96975680} {"current_steps": 44940, "total_steps": 61300, "loss": 0.3508, "lr": 1.0087407407761515e-05, "epoch": 7.33115823817292, "percentage": 73.31, "elapsed_time": "6:06:49", "remaining_time": "2:13:32", "throughput": 4406.56, "total_tokens": 96986496} {"current_steps": 44945, "total_steps": 61300, "loss": 0.3213, "lr": 1.0081695046233091e-05, "epoch": 7.331973898858075, "percentage": 73.32, "elapsed_time": "6:06:51", "remaining_time": "2:13:29", "throughput": 4406.6, "total_tokens": 96997184} {"current_steps": 44950, "total_steps": 61300, "loss": 0.3362, "lr": 1.0075983894058163e-05, "epoch": 7.33278955954323, "percentage": 73.33, "elapsed_time": "6:06:54", "remaining_time": "2:13:27", "throughput": 4406.64, "total_tokens": 97008416} {"current_steps": 44955, "total_steps": 61300, "loss": 0.3071, "lr": 1.0070273951699704e-05, "epoch": 7.333605220228385, "percentage": 73.34, "elapsed_time": "6:06:56", "remaining_time": "2:13:24", "throughput": 4406.7, "total_tokens": 97020000} {"current_steps": 44960, "total_steps": 61300, "loss": 0.3345, "lr": 1.0064565219620593e-05, "epoch": 7.33442088091354, "percentage": 73.34, "elapsed_time": "6:06:58", "remaining_time": "2:13:22", "throughput": 4406.74, "total_tokens": 97030752} {"current_steps": 44965, "total_steps": 61300, "loss": 0.3421, "lr": 1.0058857698283603e-05, "epoch": 7.335236541598695, "percentage": 73.35, "elapsed_time": "6:07:00", "remaining_time": "2:13:19", "throughput": 4406.77, "total_tokens": 97040416} {"current_steps": 44970, "total_steps": 61300, "loss": 0.3135, "lr": 1.0053151388151418e-05, "epoch": 7.33605220228385, "percentage": 73.36, "elapsed_time": "6:07:03", "remaining_time": "2:13:17", "throughput": 4406.82, "total_tokens": 97051936} {"current_steps": 44975, "total_steps": 61300, "loss": 0.35, "lr": 1.0047446289686615e-05, "epoch": 7.3368678629690045, "percentage": 73.37, "elapsed_time": "6:07:04", "remaining_time": "2:13:14", "throughput": 4406.86, "total_tokens": 97060864} {"current_steps": 44980, "total_steps": 61300, "loss": 0.3113, "lr": 1.0041742403351693e-05, "epoch": 7.33768352365416, "percentage": 73.38, "elapsed_time": "6:07:07", "remaining_time": "2:13:12", "throughput": 4406.9, "total_tokens": 97073376} {"current_steps": 44985, "total_steps": 61300, "loss": 0.3426, "lr": 1.0036039729609029e-05, "epoch": 7.338499184339315, "percentage": 73.38, "elapsed_time": "6:07:10", "remaining_time": "2:13:09", "throughput": 4406.95, "total_tokens": 97085696} {"current_steps": 44990, "total_steps": 61300, "loss": 0.3802, "lr": 1.0030338268920911e-05, "epoch": 7.33931484502447, "percentage": 73.39, "elapsed_time": "6:07:12", "remaining_time": "2:13:07", "throughput": 4407.0, "total_tokens": 97097856} {"current_steps": 44995, "total_steps": 61300, "loss": 0.3259, "lr": 1.0024638021749527e-05, "epoch": 7.340130505709625, "percentage": 73.4, "elapsed_time": "6:07:15", "remaining_time": "2:13:04", "throughput": 4407.04, "total_tokens": 97109280} {"current_steps": 45000, "total_steps": 61300, "loss": 0.3549, "lr": 1.001893898855697e-05, "epoch": 7.3409461663947795, "percentage": 73.41, "elapsed_time": "6:07:17", "remaining_time": "2:13:02", "throughput": 4407.09, "total_tokens": 97121728} {"current_steps": 45005, "total_steps": 61300, "loss": 0.325, "lr": 1.0013241169805232e-05, "epoch": 7.341761827079935, "percentage": 73.42, "elapsed_time": "6:07:19", "remaining_time": "2:12:59", "throughput": 4407.13, "total_tokens": 97132480} {"current_steps": 45010, "total_steps": 61300, "loss": 0.3551, "lr": 1.0007544565956206e-05, "epoch": 7.34257748776509, "percentage": 73.43, "elapsed_time": "6:07:22", "remaining_time": "2:12:57", "throughput": 4407.18, "total_tokens": 97143904} {"current_steps": 45015, "total_steps": 61300, "loss": 0.3366, "lr": 1.0001849177471687e-05, "epoch": 7.343393148450245, "percentage": 73.43, "elapsed_time": "6:07:24", "remaining_time": "2:12:54", "throughput": 4407.22, "total_tokens": 97154816} {"current_steps": 45020, "total_steps": 61300, "loss": 0.306, "lr": 9.996155004813376e-06, "epoch": 7.3442088091354, "percentage": 73.44, "elapsed_time": "6:07:26", "remaining_time": "2:12:52", "throughput": 4407.26, "total_tokens": 97165664} {"current_steps": 45025, "total_steps": 61300, "loss": 0.3498, "lr": 9.99046204844287e-06, "epoch": 7.3450244698205545, "percentage": 73.45, "elapsed_time": "6:07:28", "remaining_time": "2:12:49", "throughput": 4407.29, "total_tokens": 97174976} {"current_steps": 45030, "total_steps": 61300, "loss": 0.3035, "lr": 9.984770308821664e-06, "epoch": 7.345840130505709, "percentage": 73.46, "elapsed_time": "6:07:31", "remaining_time": "2:12:47", "throughput": 4407.34, "total_tokens": 97186720} {"current_steps": 45035, "total_steps": 61300, "loss": 0.3149, "lr": 9.979079786411167e-06, "epoch": 7.346655791190865, "percentage": 73.47, "elapsed_time": "6:07:33", "remaining_time": "2:12:44", "throughput": 4407.38, "total_tokens": 97196608} {"current_steps": 45040, "total_steps": 61300, "loss": 0.3403, "lr": 9.973390481672676e-06, "epoch": 7.34747145187602, "percentage": 73.47, "elapsed_time": "6:07:35", "remaining_time": "2:12:42", "throughput": 4407.42, "total_tokens": 97208352} {"current_steps": 45045, "total_steps": 61300, "loss": 0.3571, "lr": 9.967702395067388e-06, "epoch": 7.348287112561175, "percentage": 73.48, "elapsed_time": "6:07:37", "remaining_time": "2:12:39", "throughput": 4407.47, "total_tokens": 97218048} {"current_steps": 45050, "total_steps": 61300, "loss": 0.3485, "lr": 9.962015527056429e-06, "epoch": 7.349102773246329, "percentage": 73.49, "elapsed_time": "6:07:40", "remaining_time": "2:12:37", "throughput": 4407.51, "total_tokens": 97229920} {"current_steps": 45055, "total_steps": 61300, "loss": 0.3559, "lr": 9.95632987810079e-06, "epoch": 7.349918433931484, "percentage": 73.5, "elapsed_time": "6:07:42", "remaining_time": "2:12:34", "throughput": 4407.57, "total_tokens": 97242816} {"current_steps": 45060, "total_steps": 61300, "loss": 0.3287, "lr": 9.950645448661381e-06, "epoch": 7.350734094616639, "percentage": 73.51, "elapsed_time": "6:07:45", "remaining_time": "2:12:32", "throughput": 4407.62, "total_tokens": 97254656} {"current_steps": 45065, "total_steps": 61300, "loss": 0.3288, "lr": 9.944962239199013e-06, "epoch": 7.351549755301795, "percentage": 73.52, "elapsed_time": "6:07:47", "remaining_time": "2:12:29", "throughput": 4407.67, "total_tokens": 97266432} {"current_steps": 45070, "total_steps": 61300, "loss": 0.3246, "lr": 9.939280250174396e-06, "epoch": 7.35236541598695, "percentage": 73.52, "elapsed_time": "6:07:49", "remaining_time": "2:12:27", "throughput": 4407.71, "total_tokens": 97278080} {"current_steps": 45075, "total_steps": 61300, "loss": 0.3343, "lr": 9.933599482048136e-06, "epoch": 7.353181076672104, "percentage": 73.53, "elapsed_time": "6:07:52", "remaining_time": "2:12:25", "throughput": 4407.74, "total_tokens": 97288672} {"current_steps": 45080, "total_steps": 61300, "loss": 0.3272, "lr": 9.927919935280752e-06, "epoch": 7.353996737357259, "percentage": 73.54, "elapsed_time": "6:07:54", "remaining_time": "2:12:22", "throughput": 4407.79, "total_tokens": 97300736} {"current_steps": 45085, "total_steps": 61300, "loss": 0.3381, "lr": 9.922241610332641e-06, "epoch": 7.354812398042414, "percentage": 73.55, "elapsed_time": "6:07:56", "remaining_time": "2:12:20", "throughput": 4407.84, "total_tokens": 97311808} {"current_steps": 45090, "total_steps": 61300, "loss": 0.324, "lr": 9.91656450766414e-06, "epoch": 7.35562805872757, "percentage": 73.56, "elapsed_time": "6:07:58", "remaining_time": "2:12:17", "throughput": 4407.87, "total_tokens": 97321120} {"current_steps": 45095, "total_steps": 61300, "loss": 0.3222, "lr": 9.91088862773545e-06, "epoch": 7.356443719412725, "percentage": 73.56, "elapsed_time": "6:08:01", "remaining_time": "2:12:14", "throughput": 4407.91, "total_tokens": 97331712} {"current_steps": 45100, "total_steps": 61300, "loss": 0.3335, "lr": 9.90521397100669e-06, "epoch": 7.357259380097879, "percentage": 73.57, "elapsed_time": "6:08:03", "remaining_time": "2:12:12", "throughput": 4407.95, "total_tokens": 97342720} {"current_steps": 45105, "total_steps": 61300, "loss": 0.3274, "lr": 9.899540537937879e-06, "epoch": 7.358075040783034, "percentage": 73.58, "elapsed_time": "6:08:05", "remaining_time": "2:12:09", "throughput": 4407.99, "total_tokens": 97353920} {"current_steps": 45110, "total_steps": 61300, "loss": 0.3377, "lr": 9.893868328988928e-06, "epoch": 7.358890701468189, "percentage": 73.59, "elapsed_time": "6:08:07", "remaining_time": "2:12:07", "throughput": 4408.03, "total_tokens": 97364320} {"current_steps": 45115, "total_steps": 61300, "loss": 0.3423, "lr": 9.888197344619657e-06, "epoch": 7.359706362153344, "percentage": 73.6, "elapsed_time": "6:08:10", "remaining_time": "2:12:04", "throughput": 4408.06, "total_tokens": 97374656} {"current_steps": 45120, "total_steps": 61300, "loss": 0.3266, "lr": 9.882527585289788e-06, "epoch": 7.3605220228384995, "percentage": 73.61, "elapsed_time": "6:08:12", "remaining_time": "2:12:02", "throughput": 4408.1, "total_tokens": 97386272} {"current_steps": 45125, "total_steps": 61300, "loss": 0.3172, "lr": 9.876859051458937e-06, "epoch": 7.361337683523654, "percentage": 73.61, "elapsed_time": "6:08:14", "remaining_time": "2:11:59", "throughput": 4408.15, "total_tokens": 97396992} {"current_steps": 45130, "total_steps": 61300, "loss": 0.3575, "lr": 9.871191743586624e-06, "epoch": 7.362153344208809, "percentage": 73.62, "elapsed_time": "6:08:16", "remaining_time": "2:11:57", "throughput": 4408.19, "total_tokens": 97407296} {"current_steps": 45135, "total_steps": 61300, "loss": 0.3639, "lr": 9.865525662132274e-06, "epoch": 7.362969004893964, "percentage": 73.63, "elapsed_time": "6:08:19", "remaining_time": "2:11:54", "throughput": 4408.22, "total_tokens": 97417824} {"current_steps": 45140, "total_steps": 61300, "loss": 0.288, "lr": 9.859860807555204e-06, "epoch": 7.363784665579119, "percentage": 73.64, "elapsed_time": "6:08:21", "remaining_time": "2:11:52", "throughput": 4408.26, "total_tokens": 97428096} {"current_steps": 45145, "total_steps": 61300, "loss": 0.33, "lr": 9.854197180314639e-06, "epoch": 7.364600326264274, "percentage": 73.65, "elapsed_time": "6:08:23", "remaining_time": "2:11:49", "throughput": 4408.3, "total_tokens": 97439680} {"current_steps": 45150, "total_steps": 61300, "loss": 0.2815, "lr": 9.848534780869698e-06, "epoch": 7.365415986949429, "percentage": 73.65, "elapsed_time": "6:08:26", "remaining_time": "2:11:47", "throughput": 4408.34, "total_tokens": 97450880} {"current_steps": 45155, "total_steps": 61300, "loss": 0.3707, "lr": 9.842873609679404e-06, "epoch": 7.366231647634584, "percentage": 73.66, "elapsed_time": "6:08:28", "remaining_time": "2:11:44", "throughput": 4408.39, "total_tokens": 97461568} {"current_steps": 45160, "total_steps": 61300, "loss": 0.3029, "lr": 9.837213667202682e-06, "epoch": 7.367047308319739, "percentage": 73.67, "elapsed_time": "6:08:30", "remaining_time": "2:11:42", "throughput": 4408.44, "total_tokens": 97472416} {"current_steps": 45165, "total_steps": 61300, "loss": 0.3387, "lr": 9.83155495389836e-06, "epoch": 7.367862969004894, "percentage": 73.68, "elapsed_time": "6:08:32", "remaining_time": "2:11:39", "throughput": 4408.48, "total_tokens": 97483744} {"current_steps": 45170, "total_steps": 61300, "loss": 0.309, "lr": 9.82589747022515e-06, "epoch": 7.368678629690049, "percentage": 73.69, "elapsed_time": "6:08:35", "remaining_time": "2:11:37", "throughput": 4408.52, "total_tokens": 97494752} {"current_steps": 45175, "total_steps": 61300, "loss": 0.3424, "lr": 9.82024121664169e-06, "epoch": 7.369494290375204, "percentage": 73.69, "elapsed_time": "6:08:37", "remaining_time": "2:11:34", "throughput": 4408.56, "total_tokens": 97505056} {"current_steps": 45180, "total_steps": 61300, "loss": 0.3244, "lr": 9.814586193606496e-06, "epoch": 7.370309951060359, "percentage": 73.7, "elapsed_time": "6:08:39", "remaining_time": "2:11:32", "throughput": 4408.61, "total_tokens": 97516352} {"current_steps": 45185, "total_steps": 61300, "loss": 0.3228, "lr": 9.808932401577994e-06, "epoch": 7.371125611745514, "percentage": 73.71, "elapsed_time": "6:08:41", "remaining_time": "2:11:29", "throughput": 4408.65, "total_tokens": 97526784} {"current_steps": 45190, "total_steps": 61300, "loss": 0.3144, "lr": 9.803279841014501e-06, "epoch": 7.371941272430669, "percentage": 73.72, "elapsed_time": "6:08:44", "remaining_time": "2:11:27", "throughput": 4408.69, "total_tokens": 97538368} {"current_steps": 45195, "total_steps": 61300, "loss": 0.3326, "lr": 9.797628512374262e-06, "epoch": 7.372756933115824, "percentage": 73.73, "elapsed_time": "6:08:46", "remaining_time": "2:11:24", "throughput": 4408.74, "total_tokens": 97549440} {"current_steps": 45200, "total_steps": 61300, "loss": 0.3171, "lr": 9.791978416115393e-06, "epoch": 7.373572593800978, "percentage": 73.74, "elapsed_time": "6:08:48", "remaining_time": "2:11:22", "throughput": 4408.78, "total_tokens": 97559264} {"current_steps": 45205, "total_steps": 61300, "loss": 0.3069, "lr": 9.786329552695916e-06, "epoch": 7.374388254486134, "percentage": 73.74, "elapsed_time": "6:08:50", "remaining_time": "2:11:19", "throughput": 4408.82, "total_tokens": 97569312} {"current_steps": 45210, "total_steps": 61300, "loss": 0.3494, "lr": 9.780681922573759e-06, "epoch": 7.375203915171289, "percentage": 73.75, "elapsed_time": "6:08:52", "remaining_time": "2:11:16", "throughput": 4408.86, "total_tokens": 97579712} {"current_steps": 45215, "total_steps": 61300, "loss": 0.3276, "lr": 9.775035526206741e-06, "epoch": 7.376019575856444, "percentage": 73.76, "elapsed_time": "6:08:54", "remaining_time": "2:11:14", "throughput": 4408.9, "total_tokens": 97590912} {"current_steps": 45220, "total_steps": 61300, "loss": 0.3157, "lr": 9.7693903640526e-06, "epoch": 7.376835236541599, "percentage": 73.77, "elapsed_time": "6:08:57", "remaining_time": "2:11:11", "throughput": 4408.95, "total_tokens": 97602176} {"current_steps": 45225, "total_steps": 61300, "loss": 0.3415, "lr": 9.763746436568957e-06, "epoch": 7.377650897226753, "percentage": 73.78, "elapsed_time": "6:08:59", "remaining_time": "2:11:09", "throughput": 4408.98, "total_tokens": 97612128} {"current_steps": 45230, "total_steps": 61300, "loss": 0.3832, "lr": 9.758103744213334e-06, "epoch": 7.378466557911908, "percentage": 73.78, "elapsed_time": "6:09:01", "remaining_time": "2:11:06", "throughput": 4409.01, "total_tokens": 97622528} {"current_steps": 45235, "total_steps": 61300, "loss": 0.3611, "lr": 9.752462287443163e-06, "epoch": 7.379282218597064, "percentage": 73.79, "elapsed_time": "6:09:04", "remaining_time": "2:11:04", "throughput": 4409.06, "total_tokens": 97634304} {"current_steps": 45240, "total_steps": 61300, "loss": 0.3264, "lr": 9.746822066715757e-06, "epoch": 7.380097879282219, "percentage": 73.8, "elapsed_time": "6:09:06", "remaining_time": "2:11:01", "throughput": 4409.1, "total_tokens": 97644864} {"current_steps": 45245, "total_steps": 61300, "loss": 0.3384, "lr": 9.741183082488354e-06, "epoch": 7.3809135399673735, "percentage": 73.81, "elapsed_time": "6:09:08", "remaining_time": "2:10:59", "throughput": 4409.15, "total_tokens": 97656768} {"current_steps": 45250, "total_steps": 61300, "loss": 0.3319, "lr": 9.73554533521807e-06, "epoch": 7.381729200652528, "percentage": 73.82, "elapsed_time": "6:09:11", "remaining_time": "2:10:56", "throughput": 4409.2, "total_tokens": 97668416} {"current_steps": 45255, "total_steps": 61300, "loss": 0.3735, "lr": 9.729908825361933e-06, "epoch": 7.382544861337683, "percentage": 73.83, "elapsed_time": "6:09:13", "remaining_time": "2:10:54", "throughput": 4409.24, "total_tokens": 97679392} {"current_steps": 45260, "total_steps": 61300, "loss": 0.3153, "lr": 9.724273553376864e-06, "epoch": 7.383360522022839, "percentage": 73.83, "elapsed_time": "6:09:15", "remaining_time": "2:10:51", "throughput": 4409.28, "total_tokens": 97689312} {"current_steps": 45265, "total_steps": 61300, "loss": 0.3282, "lr": 9.718639519719695e-06, "epoch": 7.384176182707994, "percentage": 73.84, "elapsed_time": "6:09:17", "remaining_time": "2:10:49", "throughput": 4409.32, "total_tokens": 97700448} {"current_steps": 45270, "total_steps": 61300, "loss": 0.3406, "lr": 9.713006724847137e-06, "epoch": 7.3849918433931485, "percentage": 73.85, "elapsed_time": "6:09:19", "remaining_time": "2:10:46", "throughput": 4409.35, "total_tokens": 97710528} {"current_steps": 45275, "total_steps": 61300, "loss": 0.345, "lr": 9.70737516921582e-06, "epoch": 7.385807504078303, "percentage": 73.86, "elapsed_time": "6:09:21", "remaining_time": "2:10:44", "throughput": 4409.38, "total_tokens": 97718720} {"current_steps": 45280, "total_steps": 61300, "loss": 0.3131, "lr": 9.70174485328227e-06, "epoch": 7.386623164763458, "percentage": 73.87, "elapsed_time": "6:09:23", "remaining_time": "2:10:41", "throughput": 4409.41, "total_tokens": 97727744} {"current_steps": 45285, "total_steps": 61300, "loss": 0.3208, "lr": 9.6961157775029e-06, "epoch": 7.387438825448613, "percentage": 73.87, "elapsed_time": "6:09:25", "remaining_time": "2:10:38", "throughput": 4409.45, "total_tokens": 97738112} {"current_steps": 45290, "total_steps": 61300, "loss": 0.346, "lr": 9.69048794233404e-06, "epoch": 7.388254486133769, "percentage": 73.88, "elapsed_time": "6:09:27", "remaining_time": "2:10:36", "throughput": 4409.48, "total_tokens": 97748320} {"current_steps": 45295, "total_steps": 61300, "loss": 0.3321, "lr": 9.684861348231897e-06, "epoch": 7.3890701468189235, "percentage": 73.89, "elapsed_time": "6:09:30", "remaining_time": "2:10:33", "throughput": 4409.54, "total_tokens": 97760480} {"current_steps": 45300, "total_steps": 61300, "loss": 0.3136, "lr": 9.67923599565261e-06, "epoch": 7.389885807504078, "percentage": 73.9, "elapsed_time": "6:09:32", "remaining_time": "2:10:31", "throughput": 4409.58, "total_tokens": 97770912} {"current_steps": 45305, "total_steps": 61300, "loss": 0.3276, "lr": 9.673611885052189e-06, "epoch": 7.390701468189233, "percentage": 73.91, "elapsed_time": "6:09:34", "remaining_time": "2:10:28", "throughput": 4409.62, "total_tokens": 97781984} {"current_steps": 45310, "total_steps": 61300, "loss": 0.3363, "lr": 9.667989016886555e-06, "epoch": 7.391517128874388, "percentage": 73.92, "elapsed_time": "6:09:36", "remaining_time": "2:10:26", "throughput": 4409.67, "total_tokens": 97793152} {"current_steps": 45315, "total_steps": 61300, "loss": 0.3194, "lr": 9.662367391611526e-06, "epoch": 7.392332789559543, "percentage": 73.92, "elapsed_time": "6:09:39", "remaining_time": "2:10:23", "throughput": 4409.72, "total_tokens": 97804896} {"current_steps": 45320, "total_steps": 61300, "loss": 0.328, "lr": 9.656747009682817e-06, "epoch": 7.3931484502446985, "percentage": 73.93, "elapsed_time": "6:09:41", "remaining_time": "2:10:21", "throughput": 4409.76, "total_tokens": 97815008} {"current_steps": 45325, "total_steps": 61300, "loss": 0.3232, "lr": 9.651127871556049e-06, "epoch": 7.393964110929853, "percentage": 73.94, "elapsed_time": "6:09:43", "remaining_time": "2:10:18", "throughput": 4409.79, "total_tokens": 97826400} {"current_steps": 45330, "total_steps": 61300, "loss": 0.3282, "lr": 9.645509977686731e-06, "epoch": 7.394779771615008, "percentage": 73.95, "elapsed_time": "6:09:46", "remaining_time": "2:10:16", "throughput": 4409.83, "total_tokens": 97837024} {"current_steps": 45335, "total_steps": 61300, "loss": 0.3411, "lr": 9.639893328530283e-06, "epoch": 7.395595432300163, "percentage": 73.96, "elapsed_time": "6:09:48", "remaining_time": "2:10:13", "throughput": 4409.87, "total_tokens": 97847616} {"current_steps": 45340, "total_steps": 61300, "loss": 0.3231, "lr": 9.63427792454202e-06, "epoch": 7.396411092985318, "percentage": 73.96, "elapsed_time": "6:09:50", "remaining_time": "2:10:11", "throughput": 4409.91, "total_tokens": 97858464} {"current_steps": 45345, "total_steps": 61300, "loss": 0.3342, "lr": 9.628663766177154e-06, "epoch": 7.397226753670473, "percentage": 73.97, "elapsed_time": "6:09:52", "remaining_time": "2:10:08", "throughput": 4409.95, "total_tokens": 97868224} {"current_steps": 45350, "total_steps": 61300, "loss": 0.3121, "lr": 9.623050853890795e-06, "epoch": 7.398042414355628, "percentage": 73.98, "elapsed_time": "6:09:54", "remaining_time": "2:10:06", "throughput": 4410.0, "total_tokens": 97879520} {"current_steps": 45355, "total_steps": 61300, "loss": 0.3581, "lr": 9.617439188137956e-06, "epoch": 7.398858075040783, "percentage": 73.99, "elapsed_time": "6:09:56", "remaining_time": "2:10:03", "throughput": 4410.04, "total_tokens": 97889568} {"current_steps": 45360, "total_steps": 61300, "loss": 0.3435, "lr": 9.611828769373538e-06, "epoch": 7.399673735725938, "percentage": 74.0, "elapsed_time": "6:09:59", "remaining_time": "2:10:01", "throughput": 4410.07, "total_tokens": 97899840} {"current_steps": 45365, "total_steps": 61300, "loss": 0.3334, "lr": 9.606219598052366e-06, "epoch": 7.400489396411093, "percentage": 74.0, "elapsed_time": "6:10:01", "remaining_time": "2:09:58", "throughput": 4410.12, "total_tokens": 97910112} {"current_steps": 45370, "total_steps": 61300, "loss": 0.3283, "lr": 9.600611674629143e-06, "epoch": 7.401305057096248, "percentage": 74.01, "elapsed_time": "6:10:03", "remaining_time": "2:09:55", "throughput": 4410.17, "total_tokens": 97921664} {"current_steps": 45375, "total_steps": 61300, "loss": 0.349, "lr": 9.595004999558471e-06, "epoch": 7.402120717781403, "percentage": 74.02, "elapsed_time": "6:10:06", "remaining_time": "2:09:53", "throughput": 4410.21, "total_tokens": 97934112} {"current_steps": 45380, "total_steps": 61300, "loss": 0.3149, "lr": 9.58939957329486e-06, "epoch": 7.402936378466558, "percentage": 74.03, "elapsed_time": "6:10:08", "remaining_time": "2:09:51", "throughput": 4410.26, "total_tokens": 97945760} {"current_steps": 45385, "total_steps": 61300, "loss": 0.3372, "lr": 9.58379539629271e-06, "epoch": 7.403752039151713, "percentage": 74.04, "elapsed_time": "6:10:10", "remaining_time": "2:09:48", "throughput": 4410.29, "total_tokens": 97956320} {"current_steps": 45390, "total_steps": 61300, "loss": 0.3299, "lr": 9.578192469006328e-06, "epoch": 7.404567699836868, "percentage": 74.05, "elapsed_time": "6:10:12", "remaining_time": "2:09:46", "throughput": 4410.34, "total_tokens": 97966368} {"current_steps": 45395, "total_steps": 61300, "loss": 0.3152, "lr": 9.572590791889916e-06, "epoch": 7.4053833605220225, "percentage": 74.05, "elapsed_time": "6:10:15", "remaining_time": "2:09:43", "throughput": 4410.38, "total_tokens": 97976736} {"current_steps": 45400, "total_steps": 61300, "loss": 0.377, "lr": 9.56699036539756e-06, "epoch": 7.406199021207178, "percentage": 74.06, "elapsed_time": "6:10:17", "remaining_time": "2:09:40", "throughput": 4410.42, "total_tokens": 97987616} {"current_steps": 45405, "total_steps": 61300, "loss": 0.2939, "lr": 9.561391189983281e-06, "epoch": 7.407014681892333, "percentage": 74.07, "elapsed_time": "6:10:19", "remaining_time": "2:09:38", "throughput": 4410.47, "total_tokens": 97999424} {"current_steps": 45410, "total_steps": 61300, "loss": 0.2924, "lr": 9.555793266100969e-06, "epoch": 7.407830342577488, "percentage": 74.08, "elapsed_time": "6:10:22", "remaining_time": "2:09:35", "throughput": 4410.52, "total_tokens": 98010688} {"current_steps": 45415, "total_steps": 61300, "loss": 0.3248, "lr": 9.550196594204413e-06, "epoch": 7.408646003262643, "percentage": 74.09, "elapsed_time": "6:10:24", "remaining_time": "2:09:33", "throughput": 4410.56, "total_tokens": 98022304} {"current_steps": 45420, "total_steps": 61300, "loss": 0.2988, "lr": 9.544601174747316e-06, "epoch": 7.4094616639477975, "percentage": 74.09, "elapsed_time": "6:10:26", "remaining_time": "2:09:30", "throughput": 4410.6, "total_tokens": 98032448} {"current_steps": 45425, "total_steps": 61300, "loss": 0.323, "lr": 9.539007008183267e-06, "epoch": 7.410277324632952, "percentage": 74.1, "elapsed_time": "6:10:28", "remaining_time": "2:09:28", "throughput": 4410.64, "total_tokens": 98043936} {"current_steps": 45430, "total_steps": 61300, "loss": 0.2979, "lr": 9.533414094965759e-06, "epoch": 7.411092985318108, "percentage": 74.11, "elapsed_time": "6:10:31", "remaining_time": "2:09:26", "throughput": 4410.68, "total_tokens": 98054880} {"current_steps": 45435, "total_steps": 61300, "loss": 0.3525, "lr": 9.527822435548181e-06, "epoch": 7.411908646003263, "percentage": 74.12, "elapsed_time": "6:10:33", "remaining_time": "2:09:23", "throughput": 4410.72, "total_tokens": 98065440} {"current_steps": 45440, "total_steps": 61300, "loss": 0.3131, "lr": 9.522232030383822e-06, "epoch": 7.412724306688418, "percentage": 74.13, "elapsed_time": "6:10:35", "remaining_time": "2:09:20", "throughput": 4410.77, "total_tokens": 98076256} {"current_steps": 45445, "total_steps": 61300, "loss": 0.3356, "lr": 9.516642879925865e-06, "epoch": 7.4135399673735725, "percentage": 74.14, "elapsed_time": "6:10:37", "remaining_time": "2:09:18", "throughput": 4410.82, "total_tokens": 98087648} {"current_steps": 45450, "total_steps": 61300, "loss": 0.357, "lr": 9.511054984627402e-06, "epoch": 7.414355628058727, "percentage": 74.14, "elapsed_time": "6:10:40", "remaining_time": "2:09:15", "throughput": 4410.86, "total_tokens": 98097952} {"current_steps": 45455, "total_steps": 61300, "loss": 0.3251, "lr": 9.50546834494141e-06, "epoch": 7.415171288743883, "percentage": 74.15, "elapsed_time": "6:10:42", "remaining_time": "2:09:13", "throughput": 4410.91, "total_tokens": 98109440} {"current_steps": 45460, "total_steps": 61300, "loss": 0.3295, "lr": 9.499882961320771e-06, "epoch": 7.415986949429038, "percentage": 74.16, "elapsed_time": "6:10:44", "remaining_time": "2:09:10", "throughput": 4410.94, "total_tokens": 98120160} {"current_steps": 45465, "total_steps": 61300, "loss": 0.308, "lr": 9.494298834218268e-06, "epoch": 7.416802610114193, "percentage": 74.17, "elapsed_time": "6:10:47", "remaining_time": "2:09:08", "throughput": 4410.98, "total_tokens": 98131488} {"current_steps": 45470, "total_steps": 61300, "loss": 0.2943, "lr": 9.488715964086575e-06, "epoch": 7.417618270799347, "percentage": 74.18, "elapsed_time": "6:10:49", "remaining_time": "2:09:05", "throughput": 4411.02, "total_tokens": 98142528} {"current_steps": 45475, "total_steps": 61300, "loss": 0.3158, "lr": 9.48313435137827e-06, "epoch": 7.418433931484502, "percentage": 74.18, "elapsed_time": "6:10:51", "remaining_time": "2:09:03", "throughput": 4411.06, "total_tokens": 98153472} {"current_steps": 45480, "total_steps": 61300, "loss": 0.3326, "lr": 9.47755399654583e-06, "epoch": 7.419249592169657, "percentage": 74.19, "elapsed_time": "6:10:53", "remaining_time": "2:09:00", "throughput": 4411.09, "total_tokens": 98162784} {"current_steps": 45485, "total_steps": 61300, "loss": 0.3294, "lr": 9.47197490004162e-06, "epoch": 7.420065252854813, "percentage": 74.2, "elapsed_time": "6:10:55", "remaining_time": "2:08:58", "throughput": 4411.13, "total_tokens": 98173376} {"current_steps": 45490, "total_steps": 61300, "loss": 0.3598, "lr": 9.466397062317911e-06, "epoch": 7.420880913539968, "percentage": 74.21, "elapsed_time": "6:10:58", "remaining_time": "2:08:55", "throughput": 4411.17, "total_tokens": 98183872} {"current_steps": 45495, "total_steps": 61300, "loss": 0.2906, "lr": 9.460820483826874e-06, "epoch": 7.421696574225122, "percentage": 74.22, "elapsed_time": "6:11:00", "remaining_time": "2:08:53", "throughput": 4411.21, "total_tokens": 98195200} {"current_steps": 45500, "total_steps": 61300, "loss": 0.3213, "lr": 9.455245165020565e-06, "epoch": 7.422512234910277, "percentage": 74.23, "elapsed_time": "6:11:02", "remaining_time": "2:08:50", "throughput": 4411.25, "total_tokens": 98205344} {"current_steps": 45505, "total_steps": 61300, "loss": 0.3298, "lr": 9.449671106350966e-06, "epoch": 7.423327895595432, "percentage": 74.23, "elapsed_time": "6:11:04", "remaining_time": "2:08:48", "throughput": 4411.31, "total_tokens": 98216896} {"current_steps": 45510, "total_steps": 61300, "loss": 0.3157, "lr": 9.444098308269931e-06, "epoch": 7.424143556280587, "percentage": 74.24, "elapsed_time": "6:11:07", "remaining_time": "2:08:45", "throughput": 4411.35, "total_tokens": 98228896} {"current_steps": 45515, "total_steps": 61300, "loss": 0.3123, "lr": 9.438526771229212e-06, "epoch": 7.424959216965743, "percentage": 74.25, "elapsed_time": "6:11:09", "remaining_time": "2:08:43", "throughput": 4411.39, "total_tokens": 98239488} {"current_steps": 45520, "total_steps": 61300, "loss": 0.319, "lr": 9.432956495680473e-06, "epoch": 7.425774877650897, "percentage": 74.26, "elapsed_time": "6:11:11", "remaining_time": "2:08:40", "throughput": 4411.43, "total_tokens": 98251232} {"current_steps": 45525, "total_steps": 61300, "loss": 0.3143, "lr": 9.42738748207526e-06, "epoch": 7.426590538336052, "percentage": 74.27, "elapsed_time": "6:11:14", "remaining_time": "2:08:38", "throughput": 4411.47, "total_tokens": 98262432} {"current_steps": 45530, "total_steps": 61300, "loss": 0.3029, "lr": 9.421819730865039e-06, "epoch": 7.427406199021207, "percentage": 74.27, "elapsed_time": "6:11:16", "remaining_time": "2:08:35", "throughput": 4411.52, "total_tokens": 98272320} {"current_steps": 45535, "total_steps": 61300, "loss": 0.3202, "lr": 9.416253242501155e-06, "epoch": 7.428221859706362, "percentage": 74.28, "elapsed_time": "6:11:18", "remaining_time": "2:08:33", "throughput": 4411.57, "total_tokens": 98283904} {"current_steps": 45540, "total_steps": 61300, "loss": 0.3312, "lr": 9.410688017434852e-06, "epoch": 7.4290375203915175, "percentage": 74.29, "elapsed_time": "6:11:21", "remaining_time": "2:08:30", "throughput": 4411.62, "total_tokens": 98295840} {"current_steps": 45545, "total_steps": 61300, "loss": 0.3084, "lr": 9.40512405611728e-06, "epoch": 7.429853181076672, "percentage": 74.3, "elapsed_time": "6:11:23", "remaining_time": "2:08:28", "throughput": 4411.65, "total_tokens": 98307072} {"current_steps": 45550, "total_steps": 61300, "loss": 0.3466, "lr": 9.399561358999479e-06, "epoch": 7.430668841761827, "percentage": 74.31, "elapsed_time": "6:11:25", "remaining_time": "2:08:25", "throughput": 4411.7, "total_tokens": 98318144} {"current_steps": 45555, "total_steps": 61300, "loss": 0.3752, "lr": 9.393999926532387e-06, "epoch": 7.431484502446982, "percentage": 74.31, "elapsed_time": "6:11:28", "remaining_time": "2:08:23", "throughput": 4411.74, "total_tokens": 98329728} {"current_steps": 45560, "total_steps": 61300, "loss": 0.3135, "lr": 9.38843975916685e-06, "epoch": 7.432300163132137, "percentage": 74.32, "elapsed_time": "6:11:30", "remaining_time": "2:08:20", "throughput": 4411.78, "total_tokens": 98340256} {"current_steps": 45565, "total_steps": 61300, "loss": 0.2977, "lr": 9.382880857353596e-06, "epoch": 7.433115823817292, "percentage": 74.33, "elapsed_time": "6:11:32", "remaining_time": "2:08:18", "throughput": 4411.82, "total_tokens": 98350976} {"current_steps": 45570, "total_steps": 61300, "loss": 0.3631, "lr": 9.37732322154326e-06, "epoch": 7.433931484502447, "percentage": 74.34, "elapsed_time": "6:11:34", "remaining_time": "2:08:15", "throughput": 4411.87, "total_tokens": 98361536} {"current_steps": 45575, "total_steps": 61300, "loss": 0.3146, "lr": 9.371766852186373e-06, "epoch": 7.434747145187602, "percentage": 74.35, "elapsed_time": "6:11:36", "remaining_time": "2:08:13", "throughput": 4411.91, "total_tokens": 98372064} {"current_steps": 45580, "total_steps": 61300, "loss": 0.3202, "lr": 9.366211749733361e-06, "epoch": 7.435562805872757, "percentage": 74.36, "elapsed_time": "6:11:39", "remaining_time": "2:08:10", "throughput": 4411.94, "total_tokens": 98382688} {"current_steps": 45585, "total_steps": 61300, "loss": 0.3421, "lr": 9.36065791463455e-06, "epoch": 7.436378466557912, "percentage": 74.36, "elapsed_time": "6:11:41", "remaining_time": "2:08:08", "throughput": 4411.98, "total_tokens": 98393312} {"current_steps": 45590, "total_steps": 61300, "loss": 0.3371, "lr": 9.355105347340163e-06, "epoch": 7.437194127243067, "percentage": 74.37, "elapsed_time": "6:11:43", "remaining_time": "2:08:05", "throughput": 4412.02, "total_tokens": 98403136} {"current_steps": 45595, "total_steps": 61300, "loss": 0.3384, "lr": 9.349554048300316e-06, "epoch": 7.438009787928221, "percentage": 74.38, "elapsed_time": "6:11:45", "remaining_time": "2:08:03", "throughput": 4412.06, "total_tokens": 98414752} {"current_steps": 45600, "total_steps": 61300, "loss": 0.3027, "lr": 9.344004017965027e-06, "epoch": 7.438825448613377, "percentage": 74.39, "elapsed_time": "6:11:48", "remaining_time": "2:08:00", "throughput": 4412.1, "total_tokens": 98426496} {"current_steps": 45605, "total_steps": 61300, "loss": 0.3015, "lr": 9.338455256784212e-06, "epoch": 7.439641109298532, "percentage": 74.4, "elapsed_time": "6:11:50", "remaining_time": "2:07:58", "throughput": 4412.15, "total_tokens": 98437696} {"current_steps": 45610, "total_steps": 61300, "loss": 0.3029, "lr": 9.33290776520768e-06, "epoch": 7.440456769983687, "percentage": 74.4, "elapsed_time": "6:11:52", "remaining_time": "2:07:55", "throughput": 4412.19, "total_tokens": 98448640} {"current_steps": 45615, "total_steps": 61300, "loss": 0.3668, "lr": 9.32736154368513e-06, "epoch": 7.441272430668842, "percentage": 74.41, "elapsed_time": "6:11:55", "remaining_time": "2:07:53", "throughput": 4412.23, "total_tokens": 98459360} {"current_steps": 45620, "total_steps": 61300, "loss": 0.2961, "lr": 9.32181659266618e-06, "epoch": 7.442088091353996, "percentage": 74.42, "elapsed_time": "6:11:57", "remaining_time": "2:07:50", "throughput": 4412.26, "total_tokens": 98470560} {"current_steps": 45625, "total_steps": 61300, "loss": 0.3457, "lr": 9.316272912600332e-06, "epoch": 7.442903752039152, "percentage": 74.43, "elapsed_time": "6:11:59", "remaining_time": "2:07:48", "throughput": 4412.31, "total_tokens": 98482432} {"current_steps": 45630, "total_steps": 61300, "loss": 0.3, "lr": 9.310730503936976e-06, "epoch": 7.443719412724307, "percentage": 74.44, "elapsed_time": "6:12:02", "remaining_time": "2:07:45", "throughput": 4412.34, "total_tokens": 98493056} {"current_steps": 45635, "total_steps": 61300, "loss": 0.3347, "lr": 9.305189367125416e-06, "epoch": 7.444535073409462, "percentage": 74.45, "elapsed_time": "6:12:04", "remaining_time": "2:07:43", "throughput": 4412.37, "total_tokens": 98503904} {"current_steps": 45640, "total_steps": 61300, "loss": 0.2779, "lr": 9.299649502614838e-06, "epoch": 7.445350734094617, "percentage": 74.45, "elapsed_time": "6:12:06", "remaining_time": "2:07:40", "throughput": 4412.41, "total_tokens": 98514848} {"current_steps": 45645, "total_steps": 61300, "loss": 0.3232, "lr": 9.294110910854337e-06, "epoch": 7.446166394779771, "percentage": 74.46, "elapsed_time": "6:12:08", "remaining_time": "2:07:38", "throughput": 4412.46, "total_tokens": 98525696} {"current_steps": 45650, "total_steps": 61300, "loss": 0.3412, "lr": 9.288573592292893e-06, "epoch": 7.446982055464926, "percentage": 74.47, "elapsed_time": "6:12:11", "remaining_time": "2:07:35", "throughput": 4412.5, "total_tokens": 98536672} {"current_steps": 45655, "total_steps": 61300, "loss": 0.328, "lr": 9.283037547379394e-06, "epoch": 7.447797716150082, "percentage": 74.48, "elapsed_time": "6:12:13", "remaining_time": "2:07:33", "throughput": 4412.54, "total_tokens": 98546912} {"current_steps": 45660, "total_steps": 61300, "loss": 0.3533, "lr": 9.27750277656262e-06, "epoch": 7.448613376835237, "percentage": 74.49, "elapsed_time": "6:12:15", "remaining_time": "2:07:30", "throughput": 4412.58, "total_tokens": 98558336} {"current_steps": 45665, "total_steps": 61300, "loss": 0.383, "lr": 9.271969280291243e-06, "epoch": 7.4494290375203915, "percentage": 74.49, "elapsed_time": "6:12:17", "remaining_time": "2:07:28", "throughput": 4412.61, "total_tokens": 98568096} {"current_steps": 45670, "total_steps": 61300, "loss": 0.3047, "lr": 9.266437059013834e-06, "epoch": 7.450244698205546, "percentage": 74.5, "elapsed_time": "6:12:20", "remaining_time": "2:07:25", "throughput": 4412.65, "total_tokens": 98579072} {"current_steps": 45675, "total_steps": 61300, "loss": 0.3317, "lr": 9.260906113178875e-06, "epoch": 7.451060358890701, "percentage": 74.51, "elapsed_time": "6:12:22", "remaining_time": "2:07:23", "throughput": 4412.69, "total_tokens": 98589600} {"current_steps": 45680, "total_steps": 61300, "loss": 0.351, "lr": 9.255376443234725e-06, "epoch": 7.451876019575856, "percentage": 74.52, "elapsed_time": "6:12:24", "remaining_time": "2:07:20", "throughput": 4412.74, "total_tokens": 98600864} {"current_steps": 45685, "total_steps": 61300, "loss": 0.3354, "lr": 9.24984804962965e-06, "epoch": 7.452691680261012, "percentage": 74.53, "elapsed_time": "6:12:26", "remaining_time": "2:07:18", "throughput": 4412.77, "total_tokens": 98611968} {"current_steps": 45690, "total_steps": 61300, "loss": 0.3087, "lr": 9.244320932811806e-06, "epoch": 7.4535073409461665, "percentage": 74.54, "elapsed_time": "6:12:29", "remaining_time": "2:07:15", "throughput": 4412.81, "total_tokens": 98622912} {"current_steps": 45695, "total_steps": 61300, "loss": 0.336, "lr": 9.238795093229252e-06, "epoch": 7.454323001631321, "percentage": 74.54, "elapsed_time": "6:12:31", "remaining_time": "2:07:13", "throughput": 4412.85, "total_tokens": 98634592} {"current_steps": 45700, "total_steps": 61300, "loss": 0.308, "lr": 9.233270531329937e-06, "epoch": 7.455138662316476, "percentage": 74.55, "elapsed_time": "6:12:33", "remaining_time": "2:07:10", "throughput": 4412.89, "total_tokens": 98644096} {"current_steps": 45705, "total_steps": 61300, "loss": 0.3057, "lr": 9.227747247561713e-06, "epoch": 7.455954323001631, "percentage": 74.56, "elapsed_time": "6:12:35", "remaining_time": "2:07:08", "throughput": 4412.91, "total_tokens": 98654400} {"current_steps": 45710, "total_steps": 61300, "loss": 0.3325, "lr": 9.222225242372326e-06, "epoch": 7.456769983686787, "percentage": 74.57, "elapsed_time": "6:12:38", "remaining_time": "2:07:05", "throughput": 4412.96, "total_tokens": 98665568} {"current_steps": 45715, "total_steps": 61300, "loss": 0.3072, "lr": 9.216704516209417e-06, "epoch": 7.4575856443719415, "percentage": 74.58, "elapsed_time": "6:12:40", "remaining_time": "2:07:02", "throughput": 4412.99, "total_tokens": 98674624} {"current_steps": 45720, "total_steps": 61300, "loss": 0.3236, "lr": 9.211185069520514e-06, "epoch": 7.458401305057096, "percentage": 74.58, "elapsed_time": "6:12:42", "remaining_time": "2:07:00", "throughput": 4413.02, "total_tokens": 98685536} {"current_steps": 45725, "total_steps": 61300, "loss": 0.3448, "lr": 9.205666902753071e-06, "epoch": 7.459216965742251, "percentage": 74.59, "elapsed_time": "6:12:44", "remaining_time": "2:06:57", "throughput": 4413.06, "total_tokens": 98696352} {"current_steps": 45730, "total_steps": 61300, "loss": 0.3023, "lr": 9.200150016354406e-06, "epoch": 7.460032626427406, "percentage": 74.6, "elapsed_time": "6:12:46", "remaining_time": "2:06:55", "throughput": 4413.1, "total_tokens": 98707808} {"current_steps": 45735, "total_steps": 61300, "loss": 0.3124, "lr": 9.19463441077175e-06, "epoch": 7.460848287112561, "percentage": 74.61, "elapsed_time": "6:12:49", "remaining_time": "2:06:52", "throughput": 4413.14, "total_tokens": 98718112} {"current_steps": 45740, "total_steps": 61300, "loss": 0.347, "lr": 9.189120086452224e-06, "epoch": 7.4616639477977165, "percentage": 74.62, "elapsed_time": "6:12:51", "remaining_time": "2:06:50", "throughput": 4413.18, "total_tokens": 98729312} {"current_steps": 45745, "total_steps": 61300, "loss": 0.3265, "lr": 9.183607043842846e-06, "epoch": 7.462479608482871, "percentage": 74.62, "elapsed_time": "6:12:53", "remaining_time": "2:06:47", "throughput": 4413.22, "total_tokens": 98739168} {"current_steps": 45750, "total_steps": 61300, "loss": 0.3569, "lr": 9.178095283390533e-06, "epoch": 7.463295269168026, "percentage": 74.63, "elapsed_time": "6:12:55", "remaining_time": "2:06:45", "throughput": 4413.24, "total_tokens": 98749376} {"current_steps": 45755, "total_steps": 61300, "loss": 0.377, "lr": 9.172584805542098e-06, "epoch": 7.464110929853181, "percentage": 74.64, "elapsed_time": "6:12:58", "remaining_time": "2:06:42", "throughput": 4413.29, "total_tokens": 98760928} {"current_steps": 45760, "total_steps": 61300, "loss": 0.3473, "lr": 9.167075610744244e-06, "epoch": 7.464926590538336, "percentage": 74.65, "elapsed_time": "6:13:00", "remaining_time": "2:06:40", "throughput": 4413.33, "total_tokens": 98770560} {"current_steps": 45765, "total_steps": 61300, "loss": 0.3604, "lr": 9.161567699443577e-06, "epoch": 7.465742251223491, "percentage": 74.66, "elapsed_time": "6:13:02", "remaining_time": "2:06:37", "throughput": 4413.37, "total_tokens": 98780512} {"current_steps": 45770, "total_steps": 61300, "loss": 0.3361, "lr": 9.156061072086597e-06, "epoch": 7.466557911908646, "percentage": 74.67, "elapsed_time": "6:13:04", "remaining_time": "2:06:35", "throughput": 4413.41, "total_tokens": 98792192} {"current_steps": 45775, "total_steps": 61300, "loss": 0.3583, "lr": 9.150555729119697e-06, "epoch": 7.467373572593801, "percentage": 74.67, "elapsed_time": "6:13:06", "remaining_time": "2:06:32", "throughput": 4413.45, "total_tokens": 98802752} {"current_steps": 45780, "total_steps": 61300, "loss": 0.3633, "lr": 9.14505167098917e-06, "epoch": 7.468189233278956, "percentage": 74.68, "elapsed_time": "6:13:09", "remaining_time": "2:06:30", "throughput": 4413.48, "total_tokens": 98813600} {"current_steps": 45785, "total_steps": 61300, "loss": 0.3079, "lr": 9.139548898141198e-06, "epoch": 7.469004893964111, "percentage": 74.69, "elapsed_time": "6:13:11", "remaining_time": "2:06:27", "throughput": 4413.53, "total_tokens": 98825280} {"current_steps": 45790, "total_steps": 61300, "loss": 0.3204, "lr": 9.13404741102187e-06, "epoch": 7.4698205546492655, "percentage": 74.7, "elapsed_time": "6:13:13", "remaining_time": "2:06:25", "throughput": 4413.58, "total_tokens": 98836480} {"current_steps": 45795, "total_steps": 61300, "loss": 0.3317, "lr": 9.128547210077162e-06, "epoch": 7.470636215334421, "percentage": 74.71, "elapsed_time": "6:13:16", "remaining_time": "2:06:22", "throughput": 4413.62, "total_tokens": 98847424} {"current_steps": 45800, "total_steps": 61300, "loss": 0.3408, "lr": 9.123048295752948e-06, "epoch": 7.471451876019576, "percentage": 74.71, "elapsed_time": "6:13:18", "remaining_time": "2:06:20", "throughput": 4413.65, "total_tokens": 98858016} {"current_steps": 45805, "total_steps": 61300, "loss": 0.2895, "lr": 9.117550668494998e-06, "epoch": 7.472267536704731, "percentage": 74.72, "elapsed_time": "6:13:20", "remaining_time": "2:06:17", "throughput": 4413.69, "total_tokens": 98868864} {"current_steps": 45810, "total_steps": 61300, "loss": 0.2985, "lr": 9.112054328748975e-06, "epoch": 7.473083197389886, "percentage": 74.73, "elapsed_time": "6:13:22", "remaining_time": "2:06:15", "throughput": 4413.73, "total_tokens": 98879936} {"current_steps": 45815, "total_steps": 61300, "loss": 0.3323, "lr": 9.106559276960439e-06, "epoch": 7.4738988580750405, "percentage": 74.74, "elapsed_time": "6:13:25", "remaining_time": "2:06:12", "throughput": 4413.77, "total_tokens": 98891328} {"current_steps": 45820, "total_steps": 61300, "loss": 0.3058, "lr": 9.101065513574856e-06, "epoch": 7.474714518760196, "percentage": 74.75, "elapsed_time": "6:13:27", "remaining_time": "2:06:10", "throughput": 4413.81, "total_tokens": 98902592} {"current_steps": 45825, "total_steps": 61300, "loss": 0.3743, "lr": 9.095573039037574e-06, "epoch": 7.475530179445351, "percentage": 74.76, "elapsed_time": "6:13:29", "remaining_time": "2:06:07", "throughput": 4413.85, "total_tokens": 98913440} {"current_steps": 45830, "total_steps": 61300, "loss": 0.3092, "lr": 9.090081853793838e-06, "epoch": 7.476345840130506, "percentage": 74.76, "elapsed_time": "6:13:31", "remaining_time": "2:06:05", "throughput": 4413.89, "total_tokens": 98923808} {"current_steps": 45835, "total_steps": 61300, "loss": 0.3631, "lr": 9.084591958288797e-06, "epoch": 7.477161500815661, "percentage": 74.77, "elapsed_time": "6:13:34", "remaining_time": "2:06:02", "throughput": 4413.92, "total_tokens": 98933856} {"current_steps": 45840, "total_steps": 61300, "loss": 0.3181, "lr": 9.079103352967471e-06, "epoch": 7.4779771615008155, "percentage": 74.78, "elapsed_time": "6:13:36", "remaining_time": "2:06:00", "throughput": 4413.97, "total_tokens": 98944960} {"current_steps": 45845, "total_steps": 61300, "loss": 0.3321, "lr": 9.073616038274823e-06, "epoch": 7.47879282218597, "percentage": 74.79, "elapsed_time": "6:13:38", "remaining_time": "2:05:57", "throughput": 4414.01, "total_tokens": 98956512} {"current_steps": 45850, "total_steps": 61300, "loss": 0.3485, "lr": 9.068130014655665e-06, "epoch": 7.479608482871126, "percentage": 74.8, "elapsed_time": "6:13:41", "remaining_time": "2:05:55", "throughput": 4414.05, "total_tokens": 98967520} {"current_steps": 45855, "total_steps": 61300, "loss": 0.3395, "lr": 9.06264528255473e-06, "epoch": 7.480424143556281, "percentage": 74.8, "elapsed_time": "6:13:43", "remaining_time": "2:05:52", "throughput": 4414.09, "total_tokens": 98977920} {"current_steps": 45860, "total_steps": 61300, "loss": 0.3491, "lr": 9.057161842416628e-06, "epoch": 7.481239804241436, "percentage": 74.81, "elapsed_time": "6:13:45", "remaining_time": "2:05:50", "throughput": 4414.13, "total_tokens": 98987392} {"current_steps": 45865, "total_steps": 61300, "loss": 0.3727, "lr": 9.051679694685885e-06, "epoch": 7.4820554649265905, "percentage": 74.82, "elapsed_time": "6:13:47", "remaining_time": "2:05:47", "throughput": 4414.16, "total_tokens": 98998304} {"current_steps": 45870, "total_steps": 61300, "loss": 0.3228, "lr": 9.046198839806905e-06, "epoch": 7.482871125611745, "percentage": 74.83, "elapsed_time": "6:13:49", "remaining_time": "2:05:44", "throughput": 4414.2, "total_tokens": 99008480} {"current_steps": 45875, "total_steps": 61300, "loss": 0.3313, "lr": 9.040719278223997e-06, "epoch": 7.4836867862969, "percentage": 74.84, "elapsed_time": "6:13:51", "remaining_time": "2:05:42", "throughput": 4414.25, "total_tokens": 99019584} {"current_steps": 45880, "total_steps": 61300, "loss": 0.3194, "lr": 9.03524101038136e-06, "epoch": 7.484502446982056, "percentage": 74.85, "elapsed_time": "6:13:53", "remaining_time": "2:05:39", "throughput": 4414.28, "total_tokens": 99029920} {"current_steps": 45885, "total_steps": 61300, "loss": 0.3678, "lr": 9.02976403672309e-06, "epoch": 7.485318107667211, "percentage": 74.85, "elapsed_time": "6:13:56", "remaining_time": "2:05:37", "throughput": 4414.32, "total_tokens": 99040288} {"current_steps": 45890, "total_steps": 61300, "loss": 0.3489, "lr": 9.02428835769318e-06, "epoch": 7.486133768352365, "percentage": 74.86, "elapsed_time": "6:13:58", "remaining_time": "2:05:35", "throughput": 4414.37, "total_tokens": 99053024} {"current_steps": 45895, "total_steps": 61300, "loss": 0.3307, "lr": 9.018813973735515e-06, "epoch": 7.48694942903752, "percentage": 74.87, "elapsed_time": "6:14:00", "remaining_time": "2:05:32", "throughput": 4414.4, "total_tokens": 99062720} {"current_steps": 45900, "total_steps": 61300, "loss": 0.2832, "lr": 9.013340885293878e-06, "epoch": 7.487765089722675, "percentage": 74.88, "elapsed_time": "6:14:03", "remaining_time": "2:05:29", "throughput": 4414.45, "total_tokens": 99073728} {"current_steps": 45905, "total_steps": 61300, "loss": 0.3706, "lr": 9.007869092811944e-06, "epoch": 7.488580750407831, "percentage": 74.89, "elapsed_time": "6:14:05", "remaining_time": "2:05:27", "throughput": 4414.48, "total_tokens": 99084704} {"current_steps": 45910, "total_steps": 61300, "loss": 0.3544, "lr": 9.002398596733287e-06, "epoch": 7.489396411092986, "percentage": 74.89, "elapsed_time": "6:14:07", "remaining_time": "2:05:24", "throughput": 4414.51, "total_tokens": 99095744} {"current_steps": 45915, "total_steps": 61300, "loss": 0.3638, "lr": 8.996929397501366e-06, "epoch": 7.49021207177814, "percentage": 74.9, "elapsed_time": "6:14:10", "remaining_time": "2:05:22", "throughput": 4414.55, "total_tokens": 99107168} {"current_steps": 45920, "total_steps": 61300, "loss": 0.3499, "lr": 8.99146149555955e-06, "epoch": 7.491027732463295, "percentage": 74.91, "elapsed_time": "6:14:12", "remaining_time": "2:05:19", "throughput": 4414.59, "total_tokens": 99118208} {"current_steps": 45925, "total_steps": 61300, "loss": 0.3185, "lr": 8.98599489135109e-06, "epoch": 7.49184339314845, "percentage": 74.92, "elapsed_time": "6:14:14", "remaining_time": "2:05:17", "throughput": 4414.63, "total_tokens": 99129152} {"current_steps": 45930, "total_steps": 61300, "loss": 0.3466, "lr": 8.980529585319142e-06, "epoch": 7.492659053833605, "percentage": 74.93, "elapsed_time": "6:14:16", "remaining_time": "2:05:14", "throughput": 4414.67, "total_tokens": 99140192} {"current_steps": 45935, "total_steps": 61300, "loss": 0.3177, "lr": 8.975065577906735e-06, "epoch": 7.493474714518761, "percentage": 74.93, "elapsed_time": "6:14:19", "remaining_time": "2:05:12", "throughput": 4414.71, "total_tokens": 99150368} {"current_steps": 45940, "total_steps": 61300, "loss": 0.3164, "lr": 8.969602869556834e-06, "epoch": 7.494290375203915, "percentage": 74.94, "elapsed_time": "6:14:21", "remaining_time": "2:05:09", "throughput": 4414.74, "total_tokens": 99161728} {"current_steps": 45945, "total_steps": 61300, "loss": 0.3225, "lr": 8.964141460712258e-06, "epoch": 7.49510603588907, "percentage": 74.95, "elapsed_time": "6:14:23", "remaining_time": "2:05:07", "throughput": 4414.79, "total_tokens": 99173024} {"current_steps": 45950, "total_steps": 61300, "loss": 0.3014, "lr": 8.958681351815742e-06, "epoch": 7.495921696574225, "percentage": 74.96, "elapsed_time": "6:14:25", "remaining_time": "2:05:04", "throughput": 4414.83, "total_tokens": 99183008} {"current_steps": 45955, "total_steps": 61300, "loss": 0.3254, "lr": 8.95322254330991e-06, "epoch": 7.49673735725938, "percentage": 74.97, "elapsed_time": "6:14:28", "remaining_time": "2:05:02", "throughput": 4414.88, "total_tokens": 99194976} {"current_steps": 45960, "total_steps": 61300, "loss": 0.3382, "lr": 8.947765035637278e-06, "epoch": 7.497553017944535, "percentage": 74.98, "elapsed_time": "6:14:30", "remaining_time": "2:04:59", "throughput": 4414.92, "total_tokens": 99205760} {"current_steps": 45965, "total_steps": 61300, "loss": 0.3376, "lr": 8.942308829240262e-06, "epoch": 7.49836867862969, "percentage": 74.98, "elapsed_time": "6:14:32", "remaining_time": "2:04:57", "throughput": 4414.96, "total_tokens": 99215808} {"current_steps": 45970, "total_steps": 61300, "loss": 0.3332, "lr": 8.936853924561167e-06, "epoch": 7.499184339314845, "percentage": 74.99, "elapsed_time": "6:14:34", "remaining_time": "2:04:54", "throughput": 4415.0, "total_tokens": 99226848} {"current_steps": 45975, "total_steps": 61300, "loss": 0.3568, "lr": 8.931400322042193e-06, "epoch": 7.5, "percentage": 75.0, "elapsed_time": "6:14:37", "remaining_time": "2:04:52", "throughput": 4415.03, "total_tokens": 99237152} {"current_steps": 45975, "total_steps": 61300, "eval_loss": 0.3353175222873688, "epoch": 7.5, "percentage": 75.0, "elapsed_time": "6:16:48", "remaining_time": "2:05:36", "throughput": 4389.28, "total_tokens": 99237152} {"current_steps": 45980, "total_steps": 61300, "loss": 0.3718, "lr": 8.925948022125446e-06, "epoch": 7.500815660685155, "percentage": 75.01, "elapsed_time": "6:16:52", "remaining_time": "2:05:34", "throughput": 4389.0, "total_tokens": 99247936} {"current_steps": 45985, "total_steps": 61300, "loss": 0.323, "lr": 8.9204970252529e-06, "epoch": 7.50163132137031, "percentage": 75.02, "elapsed_time": "6:16:55", "remaining_time": "2:05:31", "throughput": 4389.04, "total_tokens": 99259456} {"current_steps": 45990, "total_steps": 61300, "loss": 0.3221, "lr": 8.91504733186646e-06, "epoch": 7.502446982055465, "percentage": 75.02, "elapsed_time": "6:16:57", "remaining_time": "2:05:29", "throughput": 4389.08, "total_tokens": 99269760} {"current_steps": 45995, "total_steps": 61300, "loss": 0.3185, "lr": 8.909598942407898e-06, "epoch": 7.50326264274062, "percentage": 75.03, "elapsed_time": "6:16:59", "remaining_time": "2:05:26", "throughput": 4389.12, "total_tokens": 99280256} {"current_steps": 46000, "total_steps": 61300, "loss": 0.3261, "lr": 8.904151857318888e-06, "epoch": 7.504078303425775, "percentage": 75.04, "elapsed_time": "6:17:01", "remaining_time": "2:05:24", "throughput": 4389.16, "total_tokens": 99289600} {"current_steps": 46005, "total_steps": 61300, "loss": 0.3649, "lr": 8.898706077040997e-06, "epoch": 7.50489396411093, "percentage": 75.05, "elapsed_time": "6:17:03", "remaining_time": "2:05:21", "throughput": 4389.21, "total_tokens": 99300128} {"current_steps": 46010, "total_steps": 61300, "loss": 0.3265, "lr": 8.893261602015687e-06, "epoch": 7.505709624796085, "percentage": 75.06, "elapsed_time": "6:17:06", "remaining_time": "2:05:19", "throughput": 4389.25, "total_tokens": 99311680} {"current_steps": 46015, "total_steps": 61300, "loss": 0.3445, "lr": 8.88781843268432e-06, "epoch": 7.506525285481239, "percentage": 75.07, "elapsed_time": "6:17:08", "remaining_time": "2:05:16", "throughput": 4389.3, "total_tokens": 99322976} {"current_steps": 46020, "total_steps": 61300, "loss": 0.2987, "lr": 8.88237656948814e-06, "epoch": 7.507340946166395, "percentage": 75.07, "elapsed_time": "6:17:11", "remaining_time": "2:05:14", "throughput": 4389.35, "total_tokens": 99335584} {"current_steps": 46025, "total_steps": 61300, "loss": 0.3447, "lr": 8.876936012868297e-06, "epoch": 7.50815660685155, "percentage": 75.08, "elapsed_time": "6:17:13", "remaining_time": "2:05:11", "throughput": 4389.39, "total_tokens": 99346528} {"current_steps": 46030, "total_steps": 61300, "loss": 0.397, "lr": 8.87149676326583e-06, "epoch": 7.508972267536705, "percentage": 75.09, "elapsed_time": "6:17:15", "remaining_time": "2:05:09", "throughput": 4389.43, "total_tokens": 99357280} {"current_steps": 46035, "total_steps": 61300, "loss": 0.3797, "lr": 8.866058821121667e-06, "epoch": 7.50978792822186, "percentage": 75.1, "elapsed_time": "6:17:17", "remaining_time": "2:05:06", "throughput": 4389.48, "total_tokens": 99368192} {"current_steps": 46040, "total_steps": 61300, "loss": 0.3145, "lr": 8.860622186876632e-06, "epoch": 7.510603588907014, "percentage": 75.11, "elapsed_time": "6:17:20", "remaining_time": "2:05:04", "throughput": 4389.52, "total_tokens": 99379104} {"current_steps": 46045, "total_steps": 61300, "loss": 0.3513, "lr": 8.855186860971462e-06, "epoch": 7.511419249592169, "percentage": 75.11, "elapsed_time": "6:17:22", "remaining_time": "2:05:01", "throughput": 4389.57, "total_tokens": 99391200} {"current_steps": 46050, "total_steps": 61300, "loss": 0.3058, "lr": 8.849752843846762e-06, "epoch": 7.512234910277325, "percentage": 75.12, "elapsed_time": "6:17:24", "remaining_time": "2:04:59", "throughput": 4389.62, "total_tokens": 99402272} {"current_steps": 46055, "total_steps": 61300, "loss": 0.3178, "lr": 8.844320135943042e-06, "epoch": 7.51305057096248, "percentage": 75.13, "elapsed_time": "6:17:27", "remaining_time": "2:04:56", "throughput": 4389.67, "total_tokens": 99414016} {"current_steps": 46060, "total_steps": 61300, "loss": 0.3312, "lr": 8.838888737700707e-06, "epoch": 7.513866231647635, "percentage": 75.14, "elapsed_time": "6:17:29", "remaining_time": "2:04:54", "throughput": 4389.71, "total_tokens": 99423424} {"current_steps": 46065, "total_steps": 61300, "loss": 0.3168, "lr": 8.833458649560051e-06, "epoch": 7.514681892332789, "percentage": 75.15, "elapsed_time": "6:17:31", "remaining_time": "2:04:51", "throughput": 4389.75, "total_tokens": 99434592} {"current_steps": 46070, "total_steps": 61300, "loss": 0.3434, "lr": 8.828029871961263e-06, "epoch": 7.515497553017944, "percentage": 75.15, "elapsed_time": "6:17:33", "remaining_time": "2:04:48", "throughput": 4389.79, "total_tokens": 99444096} {"current_steps": 46075, "total_steps": 61300, "loss": 0.3421, "lr": 8.82260240534443e-06, "epoch": 7.5163132137031, "percentage": 75.16, "elapsed_time": "6:17:35", "remaining_time": "2:04:46", "throughput": 4389.84, "total_tokens": 99455328} {"current_steps": 46080, "total_steps": 61300, "loss": 0.3425, "lr": 8.817176250149528e-06, "epoch": 7.517128874388255, "percentage": 75.17, "elapsed_time": "6:17:37", "remaining_time": "2:04:43", "throughput": 4389.88, "total_tokens": 99465152} {"current_steps": 46085, "total_steps": 61300, "loss": 0.3445, "lr": 8.811751406816432e-06, "epoch": 7.5179445350734095, "percentage": 75.18, "elapsed_time": "6:17:39", "remaining_time": "2:04:41", "throughput": 4389.91, "total_tokens": 99475072} {"current_steps": 46090, "total_steps": 61300, "loss": 0.3222, "lr": 8.806327875784906e-06, "epoch": 7.518760195758564, "percentage": 75.19, "elapsed_time": "6:17:42", "remaining_time": "2:04:38", "throughput": 4389.95, "total_tokens": 99485344} {"current_steps": 46095, "total_steps": 61300, "loss": 0.3275, "lr": 8.800905657494607e-06, "epoch": 7.519575856443719, "percentage": 75.2, "elapsed_time": "6:17:44", "remaining_time": "2:04:36", "throughput": 4389.99, "total_tokens": 99496864} {"current_steps": 46100, "total_steps": 61300, "loss": 0.3237, "lr": 8.795484752385088e-06, "epoch": 7.520391517128875, "percentage": 75.2, "elapsed_time": "6:17:46", "remaining_time": "2:04:33", "throughput": 4390.04, "total_tokens": 99507520} {"current_steps": 46105, "total_steps": 61300, "loss": 0.3445, "lr": 8.790065160895797e-06, "epoch": 7.52120717781403, "percentage": 75.21, "elapsed_time": "6:17:48", "remaining_time": "2:04:31", "throughput": 4390.08, "total_tokens": 99517664} {"current_steps": 46110, "total_steps": 61300, "loss": 0.3392, "lr": 8.784646883466072e-06, "epoch": 7.5220228384991845, "percentage": 75.22, "elapsed_time": "6:17:50", "remaining_time": "2:04:28", "throughput": 4390.12, "total_tokens": 99527392} {"current_steps": 46115, "total_steps": 61300, "loss": 0.3473, "lr": 8.779229920535148e-06, "epoch": 7.522838499184339, "percentage": 75.23, "elapsed_time": "6:17:53", "remaining_time": "2:04:25", "throughput": 4390.17, "total_tokens": 99538784} {"current_steps": 46120, "total_steps": 61300, "loss": 0.2925, "lr": 8.77381427254215e-06, "epoch": 7.523654159869494, "percentage": 75.24, "elapsed_time": "6:17:55", "remaining_time": "2:04:23", "throughput": 4390.21, "total_tokens": 99549024} {"current_steps": 46125, "total_steps": 61300, "loss": 0.3554, "lr": 8.768399939926095e-06, "epoch": 7.524469820554649, "percentage": 75.24, "elapsed_time": "6:17:57", "remaining_time": "2:04:20", "throughput": 4390.26, "total_tokens": 99560480} {"current_steps": 46130, "total_steps": 61300, "loss": 0.3307, "lr": 8.762986923125894e-06, "epoch": 7.525285481239804, "percentage": 75.25, "elapsed_time": "6:17:59", "remaining_time": "2:04:18", "throughput": 4390.31, "total_tokens": 99571968} {"current_steps": 46135, "total_steps": 61300, "loss": 0.3353, "lr": 8.757575222580364e-06, "epoch": 7.5261011419249595, "percentage": 75.26, "elapsed_time": "6:18:02", "remaining_time": "2:04:15", "throughput": 4390.34, "total_tokens": 99582112} {"current_steps": 46140, "total_steps": 61300, "loss": 0.3561, "lr": 8.752164838728203e-06, "epoch": 7.526916802610114, "percentage": 75.27, "elapsed_time": "6:18:04", "remaining_time": "2:04:13", "throughput": 4390.37, "total_tokens": 99591360} {"current_steps": 46145, "total_steps": 61300, "loss": 0.311, "lr": 8.746755772007998e-06, "epoch": 7.527732463295269, "percentage": 75.28, "elapsed_time": "6:18:06", "remaining_time": "2:04:10", "throughput": 4390.4, "total_tokens": 99601696} {"current_steps": 46150, "total_steps": 61300, "loss": 0.3193, "lr": 8.74134802285824e-06, "epoch": 7.528548123980424, "percentage": 75.29, "elapsed_time": "6:18:08", "remaining_time": "2:04:08", "throughput": 4390.45, "total_tokens": 99612928} {"current_steps": 46155, "total_steps": 61300, "loss": 0.3166, "lr": 8.735941591717297e-06, "epoch": 7.529363784665579, "percentage": 75.29, "elapsed_time": "6:18:10", "remaining_time": "2:04:05", "throughput": 4390.5, "total_tokens": 99622720} {"current_steps": 46160, "total_steps": 61300, "loss": 0.3286, "lr": 8.730536479023463e-06, "epoch": 7.5301794453507345, "percentage": 75.3, "elapsed_time": "6:18:12", "remaining_time": "2:04:03", "throughput": 4390.54, "total_tokens": 99633888} {"current_steps": 46165, "total_steps": 61300, "loss": 0.3192, "lr": 8.72513268521489e-06, "epoch": 7.530995106035889, "percentage": 75.31, "elapsed_time": "6:18:15", "remaining_time": "2:04:00", "throughput": 4390.59, "total_tokens": 99644960} {"current_steps": 46170, "total_steps": 61300, "loss": 0.338, "lr": 8.719730210729638e-06, "epoch": 7.531810766721044, "percentage": 75.32, "elapsed_time": "6:18:17", "remaining_time": "2:03:58", "throughput": 4390.63, "total_tokens": 99656096} {"current_steps": 46175, "total_steps": 61300, "loss": 0.3388, "lr": 8.714329056005663e-06, "epoch": 7.532626427406199, "percentage": 75.33, "elapsed_time": "6:18:19", "remaining_time": "2:03:55", "throughput": 4390.67, "total_tokens": 99666752} {"current_steps": 46180, "total_steps": 61300, "loss": 0.3121, "lr": 8.708929221480808e-06, "epoch": 7.533442088091354, "percentage": 75.33, "elapsed_time": "6:18:22", "remaining_time": "2:03:52", "throughput": 4390.7, "total_tokens": 99678016} {"current_steps": 46185, "total_steps": 61300, "loss": 0.3365, "lr": 8.703530707592807e-06, "epoch": 7.5342577487765094, "percentage": 75.34, "elapsed_time": "6:18:24", "remaining_time": "2:03:50", "throughput": 4390.74, "total_tokens": 99687456} {"current_steps": 46190, "total_steps": 61300, "loss": 0.3479, "lr": 8.698133514779297e-06, "epoch": 7.535073409461664, "percentage": 75.35, "elapsed_time": "6:18:26", "remaining_time": "2:03:47", "throughput": 4390.8, "total_tokens": 99699584} {"current_steps": 46195, "total_steps": 61300, "loss": 0.345, "lr": 8.692737643477796e-06, "epoch": 7.535889070146819, "percentage": 75.36, "elapsed_time": "6:18:28", "remaining_time": "2:03:45", "throughput": 4390.84, "total_tokens": 99710624} {"current_steps": 46200, "total_steps": 61300, "loss": 0.3579, "lr": 8.687343094125726e-06, "epoch": 7.536704730831974, "percentage": 75.37, "elapsed_time": "6:18:30", "remaining_time": "2:03:42", "throughput": 4390.88, "total_tokens": 99720704} {"current_steps": 46205, "total_steps": 61300, "loss": 0.3308, "lr": 8.681949867160396e-06, "epoch": 7.537520391517129, "percentage": 75.38, "elapsed_time": "6:18:32", "remaining_time": "2:03:40", "throughput": 4390.91, "total_tokens": 99729984} {"current_steps": 46210, "total_steps": 61300, "loss": 0.3248, "lr": 8.676557963019005e-06, "epoch": 7.5383360522022835, "percentage": 75.38, "elapsed_time": "6:18:35", "remaining_time": "2:03:37", "throughput": 4390.96, "total_tokens": 99741632} {"current_steps": 46215, "total_steps": 61300, "loss": 0.3041, "lr": 8.67116738213865e-06, "epoch": 7.539151712887438, "percentage": 75.39, "elapsed_time": "6:18:37", "remaining_time": "2:03:35", "throughput": 4391.0, "total_tokens": 99750688} {"current_steps": 46220, "total_steps": 61300, "loss": 0.3331, "lr": 8.66577812495632e-06, "epoch": 7.539967373572594, "percentage": 75.4, "elapsed_time": "6:18:39", "remaining_time": "2:03:32", "throughput": 4391.04, "total_tokens": 99761440} {"current_steps": 46225, "total_steps": 61300, "loss": 0.3269, "lr": 8.660390191908892e-06, "epoch": 7.540783034257749, "percentage": 75.41, "elapsed_time": "6:18:41", "remaining_time": "2:03:29", "throughput": 4391.08, "total_tokens": 99770912} {"current_steps": 46230, "total_steps": 61300, "loss": 0.3614, "lr": 8.655003583433144e-06, "epoch": 7.541598694942904, "percentage": 75.42, "elapsed_time": "6:18:43", "remaining_time": "2:03:27", "throughput": 4391.13, "total_tokens": 99782368} {"current_steps": 46235, "total_steps": 61300, "loss": 0.3545, "lr": 8.649618299965736e-06, "epoch": 7.5424143556280585, "percentage": 75.42, "elapsed_time": "6:18:46", "remaining_time": "2:03:24", "throughput": 4391.18, "total_tokens": 99794560} {"current_steps": 46240, "total_steps": 61300, "loss": 0.3269, "lr": 8.644234341943232e-06, "epoch": 7.543230016313213, "percentage": 75.43, "elapsed_time": "6:18:48", "remaining_time": "2:03:22", "throughput": 4391.23, "total_tokens": 99805184} {"current_steps": 46245, "total_steps": 61300, "loss": 0.3202, "lr": 8.638851709802082e-06, "epoch": 7.544045676998369, "percentage": 75.44, "elapsed_time": "6:18:50", "remaining_time": "2:03:19", "throughput": 4391.27, "total_tokens": 99816160} {"current_steps": 46250, "total_steps": 61300, "loss": 0.3265, "lr": 8.633470403978625e-06, "epoch": 7.544861337683524, "percentage": 75.45, "elapsed_time": "6:18:52", "remaining_time": "2:03:17", "throughput": 4391.31, "total_tokens": 99826784} {"current_steps": 46255, "total_steps": 61300, "loss": 0.3339, "lr": 8.628090424909091e-06, "epoch": 7.545676998368679, "percentage": 75.46, "elapsed_time": "6:18:55", "remaining_time": "2:03:14", "throughput": 4391.36, "total_tokens": 99837920} {"current_steps": 46260, "total_steps": 61300, "loss": 0.3563, "lr": 8.62271177302963e-06, "epoch": 7.5464926590538335, "percentage": 75.46, "elapsed_time": "6:18:57", "remaining_time": "2:03:12", "throughput": 4391.4, "total_tokens": 99848672} {"current_steps": 46265, "total_steps": 61300, "loss": 0.3331, "lr": 8.617334448776246e-06, "epoch": 7.547308319738988, "percentage": 75.47, "elapsed_time": "6:18:59", "remaining_time": "2:03:09", "throughput": 4391.45, "total_tokens": 99861216} {"current_steps": 46270, "total_steps": 61300, "loss": 0.3504, "lr": 8.611958452584859e-06, "epoch": 7.548123980424144, "percentage": 75.48, "elapsed_time": "6:19:01", "remaining_time": "2:03:07", "throughput": 4391.48, "total_tokens": 99870784} {"current_steps": 46275, "total_steps": 61300, "loss": 0.3321, "lr": 8.60658378489127e-06, "epoch": 7.548939641109299, "percentage": 75.49, "elapsed_time": "6:19:04", "remaining_time": "2:03:04", "throughput": 4391.52, "total_tokens": 99882272} {"current_steps": 46280, "total_steps": 61300, "loss": 0.3399, "lr": 8.60121044613118e-06, "epoch": 7.549755301794454, "percentage": 75.5, "elapsed_time": "6:19:06", "remaining_time": "2:03:02", "throughput": 4391.57, "total_tokens": 99892992} {"current_steps": 46285, "total_steps": 61300, "loss": 0.3288, "lr": 8.595838436740178e-06, "epoch": 7.5505709624796085, "percentage": 75.51, "elapsed_time": "6:19:08", "remaining_time": "2:02:59", "throughput": 4391.61, "total_tokens": 99903744} {"current_steps": 46290, "total_steps": 61300, "loss": 0.3167, "lr": 8.590467757153744e-06, "epoch": 7.551386623164763, "percentage": 75.51, "elapsed_time": "6:19:11", "remaining_time": "2:02:57", "throughput": 4391.65, "total_tokens": 99914688} {"current_steps": 46295, "total_steps": 61300, "loss": 0.3655, "lr": 8.585098407807258e-06, "epoch": 7.552202283849918, "percentage": 75.52, "elapsed_time": "6:19:13", "remaining_time": "2:02:54", "throughput": 4391.7, "total_tokens": 99925632} {"current_steps": 46300, "total_steps": 61300, "loss": 0.3109, "lr": 8.579730389135973e-06, "epoch": 7.553017944535073, "percentage": 75.53, "elapsed_time": "6:19:15", "remaining_time": "2:02:52", "throughput": 4391.74, "total_tokens": 99935552} {"current_steps": 46305, "total_steps": 61300, "loss": 0.3503, "lr": 8.574363701575067e-06, "epoch": 7.553833605220229, "percentage": 75.54, "elapsed_time": "6:19:17", "remaining_time": "2:02:49", "throughput": 4391.78, "total_tokens": 99946880} {"current_steps": 46310, "total_steps": 61300, "loss": 0.3009, "lr": 8.568998345559581e-06, "epoch": 7.554649265905383, "percentage": 75.55, "elapsed_time": "6:19:19", "remaining_time": "2:02:47", "throughput": 4391.83, "total_tokens": 99957792} {"current_steps": 46315, "total_steps": 61300, "loss": 0.3602, "lr": 8.56363432152446e-06, "epoch": 7.555464926590538, "percentage": 75.55, "elapsed_time": "6:19:21", "remaining_time": "2:02:44", "throughput": 4391.86, "total_tokens": 99967168} {"current_steps": 46320, "total_steps": 61300, "loss": 0.3149, "lr": 8.55827162990454e-06, "epoch": 7.556280587275693, "percentage": 75.56, "elapsed_time": "6:19:24", "remaining_time": "2:02:42", "throughput": 4391.9, "total_tokens": 99978784} {"current_steps": 46325, "total_steps": 61300, "loss": 0.3716, "lr": 8.552910271134545e-06, "epoch": 7.557096247960848, "percentage": 75.57, "elapsed_time": "6:19:26", "remaining_time": "2:02:39", "throughput": 4391.95, "total_tokens": 99990144} {"current_steps": 46330, "total_steps": 61300, "loss": 0.3446, "lr": 8.547550245649095e-06, "epoch": 7.557911908646004, "percentage": 75.58, "elapsed_time": "6:19:29", "remaining_time": "2:02:37", "throughput": 4392.0, "total_tokens": 100001568} {"current_steps": 46335, "total_steps": 61300, "loss": 0.301, "lr": 8.542191553882701e-06, "epoch": 7.558727569331158, "percentage": 75.59, "elapsed_time": "6:19:31", "remaining_time": "2:02:34", "throughput": 4392.04, "total_tokens": 100012128} {"current_steps": 46340, "total_steps": 61300, "loss": 0.3177, "lr": 8.536834196269766e-06, "epoch": 7.559543230016313, "percentage": 75.6, "elapsed_time": "6:19:33", "remaining_time": "2:02:32", "throughput": 4392.08, "total_tokens": 100023936} {"current_steps": 46345, "total_steps": 61300, "loss": 0.3685, "lr": 8.531478173244583e-06, "epoch": 7.560358890701468, "percentage": 75.6, "elapsed_time": "6:19:36", "remaining_time": "2:02:29", "throughput": 4392.13, "total_tokens": 100035552} {"current_steps": 46350, "total_steps": 61300, "loss": 0.364, "lr": 8.52612348524134e-06, "epoch": 7.561174551386623, "percentage": 75.61, "elapsed_time": "6:19:38", "remaining_time": "2:02:27", "throughput": 4392.16, "total_tokens": 100045408} {"current_steps": 46355, "total_steps": 61300, "loss": 0.3086, "lr": 8.520770132694118e-06, "epoch": 7.561990212071779, "percentage": 75.62, "elapsed_time": "6:19:40", "remaining_time": "2:02:24", "throughput": 4392.21, "total_tokens": 100057184} {"current_steps": 46360, "total_steps": 61300, "loss": 0.3225, "lr": 8.515418116036872e-06, "epoch": 7.562805872756933, "percentage": 75.63, "elapsed_time": "6:19:42", "remaining_time": "2:02:22", "throughput": 4392.25, "total_tokens": 100068384} {"current_steps": 46365, "total_steps": 61300, "loss": 0.3201, "lr": 8.510067435703484e-06, "epoch": 7.563621533442088, "percentage": 75.64, "elapsed_time": "6:19:45", "remaining_time": "2:02:19", "throughput": 4392.29, "total_tokens": 100079488} {"current_steps": 46370, "total_steps": 61300, "loss": 0.287, "lr": 8.5047180921277e-06, "epoch": 7.564437194127243, "percentage": 75.64, "elapsed_time": "6:19:47", "remaining_time": "2:02:17", "throughput": 4392.33, "total_tokens": 100090720} {"current_steps": 46375, "total_steps": 61300, "loss": 0.3346, "lr": 8.499370085743163e-06, "epoch": 7.565252854812398, "percentage": 75.65, "elapsed_time": "6:19:49", "remaining_time": "2:02:14", "throughput": 4392.38, "total_tokens": 100101248} {"current_steps": 46380, "total_steps": 61300, "loss": 0.3394, "lr": 8.49402341698341e-06, "epoch": 7.566068515497553, "percentage": 75.66, "elapsed_time": "6:19:52", "remaining_time": "2:02:11", "throughput": 4392.42, "total_tokens": 100112224} {"current_steps": 46385, "total_steps": 61300, "loss": 0.3907, "lr": 8.48867808628187e-06, "epoch": 7.566884176182708, "percentage": 75.67, "elapsed_time": "6:19:53", "remaining_time": "2:02:09", "throughput": 4392.46, "total_tokens": 100121632} {"current_steps": 46390, "total_steps": 61300, "loss": 0.277, "lr": 8.483334094071862e-06, "epoch": 7.567699836867863, "percentage": 75.68, "elapsed_time": "6:19:56", "remaining_time": "2:02:06", "throughput": 4392.5, "total_tokens": 100133024} {"current_steps": 46395, "total_steps": 61300, "loss": 0.3366, "lr": 8.477991440786597e-06, "epoch": 7.568515497553018, "percentage": 75.69, "elapsed_time": "6:19:58", "remaining_time": "2:02:04", "throughput": 4392.54, "total_tokens": 100143008} {"current_steps": 46400, "total_steps": 61300, "loss": 0.3358, "lr": 8.472650126859177e-06, "epoch": 7.569331158238173, "percentage": 75.69, "elapsed_time": "6:20:00", "remaining_time": "2:02:01", "throughput": 4392.58, "total_tokens": 100153408} {"current_steps": 46405, "total_steps": 61300, "loss": 0.3382, "lr": 8.467310152722599e-06, "epoch": 7.570146818923328, "percentage": 75.7, "elapsed_time": "6:20:02", "remaining_time": "2:01:59", "throughput": 4392.62, "total_tokens": 100163744} {"current_steps": 46410, "total_steps": 61300, "loss": 0.3796, "lr": 8.461971518809744e-06, "epoch": 7.5709624796084825, "percentage": 75.71, "elapsed_time": "6:20:04", "remaining_time": "2:01:56", "throughput": 4392.65, "total_tokens": 100172608} {"current_steps": 46415, "total_steps": 61300, "loss": 0.3378, "lr": 8.456634225553389e-06, "epoch": 7.571778140293638, "percentage": 75.72, "elapsed_time": "6:20:06", "remaining_time": "2:01:53", "throughput": 4392.69, "total_tokens": 100182400} {"current_steps": 46420, "total_steps": 61300, "loss": 0.3539, "lr": 8.451298273386207e-06, "epoch": 7.572593800978793, "percentage": 75.73, "elapsed_time": "6:20:08", "remaining_time": "2:01:51", "throughput": 4392.73, "total_tokens": 100191936} {"current_steps": 46425, "total_steps": 61300, "loss": 0.3722, "lr": 8.445963662740752e-06, "epoch": 7.573409461663948, "percentage": 75.73, "elapsed_time": "6:20:10", "remaining_time": "2:01:48", "throughput": 4392.76, "total_tokens": 100202048} {"current_steps": 46430, "total_steps": 61300, "loss": 0.3033, "lr": 8.440630394049479e-06, "epoch": 7.574225122349103, "percentage": 75.74, "elapsed_time": "6:20:13", "remaining_time": "2:01:46", "throughput": 4392.8, "total_tokens": 100213632} {"current_steps": 46435, "total_steps": 61300, "loss": 0.3674, "lr": 8.435298467744726e-06, "epoch": 7.575040783034257, "percentage": 75.75, "elapsed_time": "6:20:15", "remaining_time": "2:01:43", "throughput": 4392.83, "total_tokens": 100224096} {"current_steps": 46440, "total_steps": 61300, "loss": 0.3323, "lr": 8.429967884258721e-06, "epoch": 7.575856443719413, "percentage": 75.76, "elapsed_time": "6:20:17", "remaining_time": "2:01:41", "throughput": 4392.88, "total_tokens": 100234368} {"current_steps": 46445, "total_steps": 61300, "loss": 0.3302, "lr": 8.424638644023603e-06, "epoch": 7.576672104404568, "percentage": 75.77, "elapsed_time": "6:20:19", "remaining_time": "2:01:38", "throughput": 4392.91, "total_tokens": 100244256} {"current_steps": 46450, "total_steps": 61300, "loss": 0.3428, "lr": 8.419310747471377e-06, "epoch": 7.577487765089723, "percentage": 75.77, "elapsed_time": "6:20:21", "remaining_time": "2:01:36", "throughput": 4392.96, "total_tokens": 100255360} {"current_steps": 46455, "total_steps": 61300, "loss": 0.3536, "lr": 8.413984195033953e-06, "epoch": 7.578303425774878, "percentage": 75.78, "elapsed_time": "6:20:23", "remaining_time": "2:01:33", "throughput": 4393.0, "total_tokens": 100265824} {"current_steps": 46460, "total_steps": 61300, "loss": 0.3917, "lr": 8.408658987143125e-06, "epoch": 7.579119086460032, "percentage": 75.79, "elapsed_time": "6:20:26", "remaining_time": "2:01:31", "throughput": 4393.04, "total_tokens": 100276512} {"current_steps": 46465, "total_steps": 61300, "loss": 0.3252, "lr": 8.403335124230586e-06, "epoch": 7.579934747145187, "percentage": 75.8, "elapsed_time": "6:20:28", "remaining_time": "2:01:28", "throughput": 4393.08, "total_tokens": 100286560} {"current_steps": 46470, "total_steps": 61300, "loss": 0.307, "lr": 8.3980126067279e-06, "epoch": 7.580750407830343, "percentage": 75.81, "elapsed_time": "6:20:30", "remaining_time": "2:01:25", "throughput": 4393.12, "total_tokens": 100297856} {"current_steps": 46475, "total_steps": 61300, "loss": 0.2977, "lr": 8.392691435066563e-06, "epoch": 7.581566068515498, "percentage": 75.82, "elapsed_time": "6:20:32", "remaining_time": "2:01:23", "throughput": 4393.16, "total_tokens": 100308352} {"current_steps": 46480, "total_steps": 61300, "loss": 0.3531, "lr": 8.387371609677921e-06, "epoch": 7.582381729200653, "percentage": 75.82, "elapsed_time": "6:20:34", "remaining_time": "2:01:20", "throughput": 4393.19, "total_tokens": 100317536} {"current_steps": 46485, "total_steps": 61300, "loss": 0.3422, "lr": 8.382053130993226e-06, "epoch": 7.583197389885807, "percentage": 75.83, "elapsed_time": "6:20:36", "remaining_time": "2:01:18", "throughput": 4393.23, "total_tokens": 100327808} {"current_steps": 46490, "total_steps": 61300, "loss": 0.3283, "lr": 8.376735999443624e-06, "epoch": 7.584013050570962, "percentage": 75.84, "elapsed_time": "6:20:39", "remaining_time": "2:01:15", "throughput": 4393.29, "total_tokens": 100339712} {"current_steps": 46495, "total_steps": 61300, "loss": 0.3327, "lr": 8.371420215460149e-06, "epoch": 7.584828711256117, "percentage": 75.85, "elapsed_time": "6:20:41", "remaining_time": "2:01:13", "throughput": 4393.32, "total_tokens": 100349696} {"current_steps": 46500, "total_steps": 61300, "loss": 0.3634, "lr": 8.366105779473723e-06, "epoch": 7.585644371941273, "percentage": 75.86, "elapsed_time": "6:20:43", "remaining_time": "2:01:10", "throughput": 4393.36, "total_tokens": 100360160} {"current_steps": 46505, "total_steps": 61300, "loss": 0.3295, "lr": 8.360792691915163e-06, "epoch": 7.5864600326264275, "percentage": 75.86, "elapsed_time": "6:20:45", "remaining_time": "2:01:08", "throughput": 4393.4, "total_tokens": 100370848} {"current_steps": 46510, "total_steps": 61300, "loss": 0.326, "lr": 8.35548095321517e-06, "epoch": 7.587275693311582, "percentage": 75.87, "elapsed_time": "6:20:47", "remaining_time": "2:01:05", "throughput": 4393.44, "total_tokens": 100381248} {"current_steps": 46515, "total_steps": 61300, "loss": 0.3424, "lr": 8.350170563804349e-06, "epoch": 7.588091353996737, "percentage": 75.88, "elapsed_time": "6:20:49", "remaining_time": "2:01:02", "throughput": 4393.47, "total_tokens": 100389888} {"current_steps": 46520, "total_steps": 61300, "loss": 0.3326, "lr": 8.344861524113178e-06, "epoch": 7.588907014681892, "percentage": 75.89, "elapsed_time": "6:20:51", "remaining_time": "2:01:00", "throughput": 4393.5, "total_tokens": 100399840} {"current_steps": 46525, "total_steps": 61300, "loss": 0.3232, "lr": 8.339553834572043e-06, "epoch": 7.589722675367048, "percentage": 75.9, "elapsed_time": "6:20:54", "remaining_time": "2:00:57", "throughput": 4393.55, "total_tokens": 100410848} {"current_steps": 46530, "total_steps": 61300, "loss": 0.3218, "lr": 8.334247495611208e-06, "epoch": 7.5905383360522025, "percentage": 75.91, "elapsed_time": "6:20:56", "remaining_time": "2:00:55", "throughput": 4393.59, "total_tokens": 100422368} {"current_steps": 46535, "total_steps": 61300, "loss": 0.3308, "lr": 8.32894250766083e-06, "epoch": 7.591353996737357, "percentage": 75.91, "elapsed_time": "6:20:58", "remaining_time": "2:00:52", "throughput": 4393.63, "total_tokens": 100433504} {"current_steps": 46540, "total_steps": 61300, "loss": 0.3606, "lr": 8.323638871150962e-06, "epoch": 7.592169657422512, "percentage": 75.92, "elapsed_time": "6:21:01", "remaining_time": "2:00:50", "throughput": 4393.66, "total_tokens": 100443584} {"current_steps": 46545, "total_steps": 61300, "loss": 0.3411, "lr": 8.31833658651154e-06, "epoch": 7.592985318107667, "percentage": 75.93, "elapsed_time": "6:21:03", "remaining_time": "2:00:47", "throughput": 4393.7, "total_tokens": 100453216} {"current_steps": 46550, "total_steps": 61300, "loss": 0.3256, "lr": 8.313035654172399e-06, "epoch": 7.593800978792823, "percentage": 75.94, "elapsed_time": "6:21:05", "remaining_time": "2:00:45", "throughput": 4393.74, "total_tokens": 100463296} {"current_steps": 46555, "total_steps": 61300, "loss": 0.3418, "lr": 8.307736074563257e-06, "epoch": 7.5946166394779775, "percentage": 75.95, "elapsed_time": "6:21:07", "remaining_time": "2:00:42", "throughput": 4393.78, "total_tokens": 100473728} {"current_steps": 46560, "total_steps": 61300, "loss": 0.3075, "lr": 8.302437848113722e-06, "epoch": 7.595432300163132, "percentage": 75.95, "elapsed_time": "6:21:09", "remaining_time": "2:00:40", "throughput": 4393.83, "total_tokens": 100485344} {"current_steps": 46565, "total_steps": 61300, "loss": 0.3498, "lr": 8.297140975253302e-06, "epoch": 7.596247960848287, "percentage": 75.96, "elapsed_time": "6:21:11", "remaining_time": "2:00:37", "throughput": 4393.87, "total_tokens": 100495552} {"current_steps": 46570, "total_steps": 61300, "loss": 0.3224, "lr": 8.291845456411378e-06, "epoch": 7.597063621533442, "percentage": 75.97, "elapsed_time": "6:21:14", "remaining_time": "2:00:35", "throughput": 4393.91, "total_tokens": 100506944} {"current_steps": 46575, "total_steps": 61300, "loss": 0.3272, "lr": 8.286551292017233e-06, "epoch": 7.597879282218597, "percentage": 75.98, "elapsed_time": "6:21:16", "remaining_time": "2:00:32", "throughput": 4393.95, "total_tokens": 100517760} {"current_steps": 46580, "total_steps": 61300, "loss": 0.3292, "lr": 8.281258482500052e-06, "epoch": 7.598694942903752, "percentage": 75.99, "elapsed_time": "6:21:18", "remaining_time": "2:00:30", "throughput": 4393.99, "total_tokens": 100528768} {"current_steps": 46585, "total_steps": 61300, "loss": 0.328, "lr": 8.275967028288886e-06, "epoch": 7.599510603588907, "percentage": 76.0, "elapsed_time": "6:21:20", "remaining_time": "2:00:27", "throughput": 4394.03, "total_tokens": 100539392} {"current_steps": 46590, "total_steps": 61300, "loss": 0.3222, "lr": 8.270676929812692e-06, "epoch": 7.600326264274062, "percentage": 76.0, "elapsed_time": "6:21:23", "remaining_time": "2:00:24", "throughput": 4394.07, "total_tokens": 100550176} {"current_steps": 46595, "total_steps": 61300, "loss": 0.3523, "lr": 8.265388187500309e-06, "epoch": 7.601141924959217, "percentage": 76.01, "elapsed_time": "6:21:25", "remaining_time": "2:00:22", "throughput": 4394.12, "total_tokens": 100561216} {"current_steps": 46600, "total_steps": 61300, "loss": 0.3604, "lr": 8.26010080178047e-06, "epoch": 7.601957585644372, "percentage": 76.02, "elapsed_time": "6:21:27", "remaining_time": "2:00:19", "throughput": 4394.16, "total_tokens": 100571648} {"current_steps": 46605, "total_steps": 61300, "loss": 0.3299, "lr": 8.254814773081798e-06, "epoch": 7.602773246329527, "percentage": 76.03, "elapsed_time": "6:21:30", "remaining_time": "2:00:17", "throughput": 4394.21, "total_tokens": 100583776} {"current_steps": 46610, "total_steps": 61300, "loss": 0.3402, "lr": 8.249530101832795e-06, "epoch": 7.603588907014682, "percentage": 76.04, "elapsed_time": "6:21:31", "remaining_time": "2:00:14", "throughput": 4394.25, "total_tokens": 100592992} {"current_steps": 46615, "total_steps": 61300, "loss": 0.3368, "lr": 8.244246788461882e-06, "epoch": 7.604404567699837, "percentage": 76.04, "elapsed_time": "6:21:34", "remaining_time": "2:00:12", "throughput": 4394.29, "total_tokens": 100603680} {"current_steps": 46620, "total_steps": 61300, "loss": 0.3608, "lr": 8.238964833397341e-06, "epoch": 7.605220228384992, "percentage": 76.05, "elapsed_time": "6:21:36", "remaining_time": "2:00:09", "throughput": 4394.35, "total_tokens": 100615808} {"current_steps": 46625, "total_steps": 61300, "loss": 0.3193, "lr": 8.233684237067358e-06, "epoch": 7.606035889070147, "percentage": 76.06, "elapsed_time": "6:21:38", "remaining_time": "2:00:07", "throughput": 4394.39, "total_tokens": 100625696} {"current_steps": 46630, "total_steps": 61300, "loss": 0.3229, "lr": 8.2284049999e-06, "epoch": 7.6068515497553015, "percentage": 76.07, "elapsed_time": "6:21:40", "remaining_time": "2:00:04", "throughput": 4394.43, "total_tokens": 100635968} {"current_steps": 46635, "total_steps": 61300, "loss": 0.3417, "lr": 8.223127122323231e-06, "epoch": 7.607667210440457, "percentage": 76.08, "elapsed_time": "6:21:43", "remaining_time": "2:00:02", "throughput": 4394.47, "total_tokens": 100647104} {"current_steps": 46640, "total_steps": 61300, "loss": 0.316, "lr": 8.217850604764903e-06, "epoch": 7.608482871125612, "percentage": 76.08, "elapsed_time": "6:21:45", "remaining_time": "1:59:59", "throughput": 4394.51, "total_tokens": 100656992} {"current_steps": 46645, "total_steps": 61300, "loss": 0.3199, "lr": 8.212575447652757e-06, "epoch": 7.609298531810767, "percentage": 76.09, "elapsed_time": "6:21:47", "remaining_time": "1:59:57", "throughput": 4394.55, "total_tokens": 100668288} {"current_steps": 46650, "total_steps": 61300, "loss": 0.3165, "lr": 8.207301651414423e-06, "epoch": 7.610114192495922, "percentage": 76.1, "elapsed_time": "6:21:50", "remaining_time": "1:59:54", "throughput": 4394.6, "total_tokens": 100680736} {"current_steps": 46655, "total_steps": 61300, "loss": 0.3689, "lr": 8.202029216477425e-06, "epoch": 7.6109298531810765, "percentage": 76.11, "elapsed_time": "6:21:52", "remaining_time": "1:59:52", "throughput": 4394.64, "total_tokens": 100692000} {"current_steps": 46660, "total_steps": 61300, "loss": 0.3722, "lr": 8.196758143269168e-06, "epoch": 7.611745513866231, "percentage": 76.12, "elapsed_time": "6:21:54", "remaining_time": "1:59:49", "throughput": 4394.68, "total_tokens": 100701440} {"current_steps": 46665, "total_steps": 61300, "loss": 0.3413, "lr": 8.191488432216957e-06, "epoch": 7.612561174551386, "percentage": 76.13, "elapsed_time": "6:21:56", "remaining_time": "1:59:47", "throughput": 4394.72, "total_tokens": 100712224} {"current_steps": 46670, "total_steps": 61300, "loss": 0.3354, "lr": 8.186220083747975e-06, "epoch": 7.613376835236542, "percentage": 76.13, "elapsed_time": "6:21:58", "remaining_time": "1:59:44", "throughput": 4394.76, "total_tokens": 100722912} {"current_steps": 46675, "total_steps": 61300, "loss": 0.3316, "lr": 8.18095309828931e-06, "epoch": 7.614192495921697, "percentage": 76.14, "elapsed_time": "6:22:00", "remaining_time": "1:59:41", "throughput": 4394.8, "total_tokens": 100732384} {"current_steps": 46680, "total_steps": 61300, "loss": 0.3441, "lr": 8.175687476267915e-06, "epoch": 7.6150081566068515, "percentage": 76.15, "elapsed_time": "6:22:03", "remaining_time": "1:59:39", "throughput": 4394.84, "total_tokens": 100743328} {"current_steps": 46685, "total_steps": 61300, "loss": 0.3482, "lr": 8.170423218110667e-06, "epoch": 7.615823817292006, "percentage": 76.16, "elapsed_time": "6:22:05", "remaining_time": "1:59:36", "throughput": 4394.87, "total_tokens": 100754944} {"current_steps": 46690, "total_steps": 61300, "loss": 0.3202, "lr": 8.165160324244305e-06, "epoch": 7.616639477977161, "percentage": 76.17, "elapsed_time": "6:22:08", "remaining_time": "1:59:34", "throughput": 4394.91, "total_tokens": 100767200} {"current_steps": 46695, "total_steps": 61300, "loss": 0.3593, "lr": 8.15989879509547e-06, "epoch": 7.617455138662317, "percentage": 76.17, "elapsed_time": "6:22:10", "remaining_time": "1:59:31", "throughput": 4394.96, "total_tokens": 100777408} {"current_steps": 46700, "total_steps": 61300, "loss": 0.3412, "lr": 8.15463863109068e-06, "epoch": 7.618270799347472, "percentage": 76.18, "elapsed_time": "6:22:12", "remaining_time": "1:59:29", "throughput": 4395.0, "total_tokens": 100787584} {"current_steps": 46705, "total_steps": 61300, "loss": 0.3356, "lr": 8.149379832656356e-06, "epoch": 7.6190864600326265, "percentage": 76.19, "elapsed_time": "6:22:14", "remaining_time": "1:59:26", "throughput": 4395.03, "total_tokens": 100796800} {"current_steps": 46710, "total_steps": 61300, "loss": 0.3226, "lr": 8.144122400218804e-06, "epoch": 7.619902120717781, "percentage": 76.2, "elapsed_time": "6:22:16", "remaining_time": "1:59:24", "throughput": 4395.06, "total_tokens": 100806528} {"current_steps": 46715, "total_steps": 61300, "loss": 0.2804, "lr": 8.138866334204215e-06, "epoch": 7.620717781402936, "percentage": 76.21, "elapsed_time": "6:22:18", "remaining_time": "1:59:21", "throughput": 4395.11, "total_tokens": 100817120} {"current_steps": 46720, "total_steps": 61300, "loss": 0.3703, "lr": 8.133611635038674e-06, "epoch": 7.621533442088092, "percentage": 76.22, "elapsed_time": "6:22:20", "remaining_time": "1:59:19", "throughput": 4395.16, "total_tokens": 100828000} {"current_steps": 46725, "total_steps": 61300, "loss": 0.3166, "lr": 8.12835830314815e-06, "epoch": 7.622349102773247, "percentage": 76.22, "elapsed_time": "6:22:23", "remaining_time": "1:59:16", "throughput": 4395.21, "total_tokens": 100839424} {"current_steps": 46730, "total_steps": 61300, "loss": 0.3128, "lr": 8.123106338958511e-06, "epoch": 7.623164763458401, "percentage": 76.23, "elapsed_time": "6:22:25", "remaining_time": "1:59:14", "throughput": 4395.25, "total_tokens": 100849472} {"current_steps": 46735, "total_steps": 61300, "loss": 0.3642, "lr": 8.117855742895506e-06, "epoch": 7.623980424143556, "percentage": 76.24, "elapsed_time": "6:22:27", "remaining_time": "1:59:11", "throughput": 4395.29, "total_tokens": 100859232} {"current_steps": 46740, "total_steps": 61300, "loss": 0.3411, "lr": 8.112606515384772e-06, "epoch": 7.624796084828711, "percentage": 76.25, "elapsed_time": "6:22:29", "remaining_time": "1:59:08", "throughput": 4395.33, "total_tokens": 100869888} {"current_steps": 46745, "total_steps": 61300, "loss": 0.3528, "lr": 8.107358656851838e-06, "epoch": 7.625611745513866, "percentage": 76.26, "elapsed_time": "6:22:31", "remaining_time": "1:59:06", "throughput": 4395.38, "total_tokens": 100881440} {"current_steps": 46750, "total_steps": 61300, "loss": 0.3287, "lr": 8.102112167722125e-06, "epoch": 7.626427406199021, "percentage": 76.26, "elapsed_time": "6:22:33", "remaining_time": "1:59:03", "throughput": 4395.42, "total_tokens": 100892160} {"current_steps": 46755, "total_steps": 61300, "loss": 0.3365, "lr": 8.096867048420932e-06, "epoch": 7.627243066884176, "percentage": 76.27, "elapsed_time": "6:22:35", "remaining_time": "1:59:01", "throughput": 4395.45, "total_tokens": 100901280} {"current_steps": 46760, "total_steps": 61300, "loss": 0.3136, "lr": 8.091623299373467e-06, "epoch": 7.628058727569331, "percentage": 76.28, "elapsed_time": "6:22:38", "remaining_time": "1:58:58", "throughput": 4395.51, "total_tokens": 100913440} {"current_steps": 46765, "total_steps": 61300, "loss": 0.3545, "lr": 8.08638092100481e-06, "epoch": 7.628874388254486, "percentage": 76.29, "elapsed_time": "6:22:40", "remaining_time": "1:58:56", "throughput": 4395.55, "total_tokens": 100923840} {"current_steps": 46770, "total_steps": 61300, "loss": 0.3278, "lr": 8.081139913739936e-06, "epoch": 7.629690048939641, "percentage": 76.3, "elapsed_time": "6:22:42", "remaining_time": "1:58:53", "throughput": 4395.59, "total_tokens": 100933824} {"current_steps": 46775, "total_steps": 61300, "loss": 0.3321, "lr": 8.075900278003703e-06, "epoch": 7.630505709624796, "percentage": 76.31, "elapsed_time": "6:22:44", "remaining_time": "1:58:51", "throughput": 4395.63, "total_tokens": 100943424} {"current_steps": 46780, "total_steps": 61300, "loss": 0.3334, "lr": 8.07066201422087e-06, "epoch": 7.631321370309951, "percentage": 76.31, "elapsed_time": "6:22:46", "remaining_time": "1:58:48", "throughput": 4395.67, "total_tokens": 100955040} {"current_steps": 46785, "total_steps": 61300, "loss": 0.3747, "lr": 8.065425122816061e-06, "epoch": 7.632137030995106, "percentage": 76.32, "elapsed_time": "6:22:49", "remaining_time": "1:58:46", "throughput": 4395.72, "total_tokens": 100966848} {"current_steps": 46790, "total_steps": 61300, "loss": 0.3253, "lr": 8.060189604213827e-06, "epoch": 7.632952691680261, "percentage": 76.33, "elapsed_time": "6:22:51", "remaining_time": "1:58:43", "throughput": 4395.76, "total_tokens": 100977888} {"current_steps": 46795, "total_steps": 61300, "loss": 0.3419, "lr": 8.054955458838576e-06, "epoch": 7.633768352365416, "percentage": 76.34, "elapsed_time": "6:22:53", "remaining_time": "1:58:41", "throughput": 4395.8, "total_tokens": 100988736} {"current_steps": 46800, "total_steps": 61300, "loss": 0.3355, "lr": 8.049722687114611e-06, "epoch": 7.634584013050571, "percentage": 76.35, "elapsed_time": "6:22:56", "remaining_time": "1:58:38", "throughput": 4395.84, "total_tokens": 100999360} {"current_steps": 46805, "total_steps": 61300, "loss": 0.3384, "lr": 8.044491289466133e-06, "epoch": 7.635399673735726, "percentage": 76.35, "elapsed_time": "6:22:58", "remaining_time": "1:58:36", "throughput": 4395.89, "total_tokens": 101011104} {"current_steps": 46810, "total_steps": 61300, "loss": 0.2971, "lr": 8.039261266317219e-06, "epoch": 7.636215334420881, "percentage": 76.36, "elapsed_time": "6:23:00", "remaining_time": "1:58:33", "throughput": 4395.93, "total_tokens": 101021664} {"current_steps": 46815, "total_steps": 61300, "loss": 0.3411, "lr": 8.034032618091846e-06, "epoch": 7.637030995106036, "percentage": 76.37, "elapsed_time": "6:23:02", "remaining_time": "1:58:31", "throughput": 4395.97, "total_tokens": 101032576} {"current_steps": 46820, "total_steps": 61300, "loss": 0.3298, "lr": 8.028805345213875e-06, "epoch": 7.637846655791191, "percentage": 76.38, "elapsed_time": "6:23:05", "remaining_time": "1:58:28", "throughput": 4396.02, "total_tokens": 101043040} {"current_steps": 46825, "total_steps": 61300, "loss": 0.3321, "lr": 8.023579448107053e-06, "epoch": 7.638662316476346, "percentage": 76.39, "elapsed_time": "6:23:07", "remaining_time": "1:58:26", "throughput": 4396.06, "total_tokens": 101054400} {"current_steps": 46830, "total_steps": 61300, "loss": 0.3363, "lr": 8.018354927195017e-06, "epoch": 7.6394779771615005, "percentage": 76.39, "elapsed_time": "6:23:09", "remaining_time": "1:58:23", "throughput": 4396.11, "total_tokens": 101064896} {"current_steps": 46835, "total_steps": 61300, "loss": 0.3526, "lr": 8.013131782901295e-06, "epoch": 7.640293637846656, "percentage": 76.4, "elapsed_time": "6:23:11", "remaining_time": "1:58:20", "throughput": 4396.14, "total_tokens": 101074848} {"current_steps": 46840, "total_steps": 61300, "loss": 0.4076, "lr": 8.007910015649304e-06, "epoch": 7.641109298531811, "percentage": 76.41, "elapsed_time": "6:23:13", "remaining_time": "1:58:18", "throughput": 4396.17, "total_tokens": 101085312} {"current_steps": 46845, "total_steps": 61300, "loss": 0.3554, "lr": 8.002689625862342e-06, "epoch": 7.641924959216966, "percentage": 76.42, "elapsed_time": "6:23:16", "remaining_time": "1:58:15", "throughput": 4396.21, "total_tokens": 101095584} {"current_steps": 46850, "total_steps": 61300, "loss": 0.3213, "lr": 7.997470613963601e-06, "epoch": 7.642740619902121, "percentage": 76.43, "elapsed_time": "6:23:18", "remaining_time": "1:58:13", "throughput": 4396.25, "total_tokens": 101105760} {"current_steps": 46855, "total_steps": 61300, "loss": 0.3398, "lr": 7.992252980376164e-06, "epoch": 7.643556280587275, "percentage": 76.44, "elapsed_time": "6:23:20", "remaining_time": "1:58:10", "throughput": 4396.29, "total_tokens": 101116576} {"current_steps": 46860, "total_steps": 61300, "loss": 0.3641, "lr": 7.987036725522995e-06, "epoch": 7.64437194127243, "percentage": 76.44, "elapsed_time": "6:23:22", "remaining_time": "1:58:08", "throughput": 4396.33, "total_tokens": 101127840} {"current_steps": 46865, "total_steps": 61300, "loss": 0.3493, "lr": 7.981821849826954e-06, "epoch": 7.645187601957586, "percentage": 76.45, "elapsed_time": "6:23:25", "remaining_time": "1:58:05", "throughput": 4396.38, "total_tokens": 101140192} {"current_steps": 46870, "total_steps": 61300, "loss": 0.3571, "lr": 7.976608353710782e-06, "epoch": 7.646003262642741, "percentage": 76.46, "elapsed_time": "6:23:27", "remaining_time": "1:58:03", "throughput": 4396.42, "total_tokens": 101150336} {"current_steps": 46875, "total_steps": 61300, "loss": 0.3359, "lr": 7.971396237597114e-06, "epoch": 7.646818923327896, "percentage": 76.47, "elapsed_time": "6:23:29", "remaining_time": "1:58:00", "throughput": 4396.46, "total_tokens": 101161088} {"current_steps": 46880, "total_steps": 61300, "loss": 0.3321, "lr": 7.966185501908469e-06, "epoch": 7.64763458401305, "percentage": 76.48, "elapsed_time": "6:23:31", "remaining_time": "1:57:58", "throughput": 4396.5, "total_tokens": 101171776} {"current_steps": 46885, "total_steps": 61300, "loss": 0.3633, "lr": 7.960976147067254e-06, "epoch": 7.648450244698205, "percentage": 76.48, "elapsed_time": "6:23:33", "remaining_time": "1:57:55", "throughput": 4396.53, "total_tokens": 101180544} {"current_steps": 46890, "total_steps": 61300, "loss": 0.355, "lr": 7.95576817349577e-06, "epoch": 7.649265905383361, "percentage": 76.49, "elapsed_time": "6:23:36", "remaining_time": "1:57:53", "throughput": 4396.58, "total_tokens": 101192448} {"current_steps": 46895, "total_steps": 61300, "loss": 0.3278, "lr": 7.95056158161619e-06, "epoch": 7.650081566068516, "percentage": 76.5, "elapsed_time": "6:23:38", "remaining_time": "1:57:50", "throughput": 4396.61, "total_tokens": 101203168} {"current_steps": 46900, "total_steps": 61300, "loss": 0.3591, "lr": 7.945356371850604e-06, "epoch": 7.650897226753671, "percentage": 76.51, "elapsed_time": "6:23:40", "remaining_time": "1:57:48", "throughput": 4396.65, "total_tokens": 101213216} {"current_steps": 46905, "total_steps": 61300, "loss": 0.3063, "lr": 7.940152544620966e-06, "epoch": 7.651712887438825, "percentage": 76.52, "elapsed_time": "6:23:42", "remaining_time": "1:57:45", "throughput": 4396.7, "total_tokens": 101224960} {"current_steps": 46910, "total_steps": 61300, "loss": 0.3296, "lr": 7.934950100349123e-06, "epoch": 7.65252854812398, "percentage": 76.53, "elapsed_time": "6:23:45", "remaining_time": "1:57:43", "throughput": 4396.73, "total_tokens": 101235296} {"current_steps": 46915, "total_steps": 61300, "loss": 0.3223, "lr": 7.929749039456813e-06, "epoch": 7.653344208809135, "percentage": 76.53, "elapsed_time": "6:23:47", "remaining_time": "1:57:40", "throughput": 4396.78, "total_tokens": 101246784} {"current_steps": 46920, "total_steps": 61300, "loss": 0.3445, "lr": 7.924549362365658e-06, "epoch": 7.654159869494291, "percentage": 76.54, "elapsed_time": "6:23:49", "remaining_time": "1:57:38", "throughput": 4396.82, "total_tokens": 101257440} {"current_steps": 46925, "total_steps": 61300, "loss": 0.3106, "lr": 7.919351069497163e-06, "epoch": 7.6549755301794455, "percentage": 76.55, "elapsed_time": "6:23:52", "remaining_time": "1:57:35", "throughput": 4396.86, "total_tokens": 101268672} {"current_steps": 46930, "total_steps": 61300, "loss": 0.3496, "lr": 7.914154161272746e-06, "epoch": 7.6557911908646, "percentage": 76.56, "elapsed_time": "6:23:54", "remaining_time": "1:57:33", "throughput": 4396.9, "total_tokens": 101279168} {"current_steps": 46935, "total_steps": 61300, "loss": 0.3428, "lr": 7.908958638113687e-06, "epoch": 7.656606851549755, "percentage": 76.57, "elapsed_time": "6:23:56", "remaining_time": "1:57:30", "throughput": 4396.95, "total_tokens": 101290336} {"current_steps": 46940, "total_steps": 61300, "loss": 0.3177, "lr": 7.903764500441157e-06, "epoch": 7.65742251223491, "percentage": 76.57, "elapsed_time": "6:23:58", "remaining_time": "1:57:28", "throughput": 4396.99, "total_tokens": 101301344} {"current_steps": 46945, "total_steps": 61300, "loss": 0.3269, "lr": 7.898571748676223e-06, "epoch": 7.658238172920065, "percentage": 76.58, "elapsed_time": "6:24:01", "remaining_time": "1:57:25", "throughput": 4397.03, "total_tokens": 101312160} {"current_steps": 46950, "total_steps": 61300, "loss": 0.323, "lr": 7.893380383239835e-06, "epoch": 7.6590538336052205, "percentage": 76.59, "elapsed_time": "6:24:03", "remaining_time": "1:57:23", "throughput": 4397.07, "total_tokens": 101322720} {"current_steps": 46955, "total_steps": 61300, "loss": 0.3434, "lr": 7.888190404552832e-06, "epoch": 7.659869494290375, "percentage": 76.6, "elapsed_time": "6:24:05", "remaining_time": "1:57:20", "throughput": 4397.11, "total_tokens": 101334048} {"current_steps": 46960, "total_steps": 61300, "loss": 0.3326, "lr": 7.883001813035937e-06, "epoch": 7.66068515497553, "percentage": 76.61, "elapsed_time": "6:24:08", "remaining_time": "1:57:18", "throughput": 4397.15, "total_tokens": 101345760} {"current_steps": 46965, "total_steps": 61300, "loss": 0.3504, "lr": 7.877814609109769e-06, "epoch": 7.661500815660685, "percentage": 76.62, "elapsed_time": "6:24:10", "remaining_time": "1:57:15", "throughput": 4397.19, "total_tokens": 101356416} {"current_steps": 46970, "total_steps": 61300, "loss": 0.3151, "lr": 7.872628793194823e-06, "epoch": 7.66231647634584, "percentage": 76.62, "elapsed_time": "6:24:12", "remaining_time": "1:57:13", "throughput": 4397.22, "total_tokens": 101367360} {"current_steps": 46975, "total_steps": 61300, "loss": 0.3435, "lr": 7.86744436571149e-06, "epoch": 7.6631321370309955, "percentage": 76.63, "elapsed_time": "6:24:14", "remaining_time": "1:57:10", "throughput": 4397.27, "total_tokens": 101378848} {"current_steps": 46980, "total_steps": 61300, "loss": 0.3345, "lr": 7.86226132708005e-06, "epoch": 7.66394779771615, "percentage": 76.64, "elapsed_time": "6:24:17", "remaining_time": "1:57:08", "throughput": 4397.32, "total_tokens": 101389184} {"current_steps": 46985, "total_steps": 61300, "loss": 0.3536, "lr": 7.85707967772066e-06, "epoch": 7.664763458401305, "percentage": 76.65, "elapsed_time": "6:24:19", "remaining_time": "1:57:05", "throughput": 4397.35, "total_tokens": 101399840} {"current_steps": 46990, "total_steps": 61300, "loss": 0.349, "lr": 7.851899418053374e-06, "epoch": 7.66557911908646, "percentage": 76.66, "elapsed_time": "6:24:21", "remaining_time": "1:57:02", "throughput": 4397.39, "total_tokens": 101410112} {"current_steps": 46995, "total_steps": 61300, "loss": 0.3293, "lr": 7.846720548498132e-06, "epoch": 7.666394779771615, "percentage": 76.66, "elapsed_time": "6:24:23", "remaining_time": "1:57:00", "throughput": 4397.42, "total_tokens": 101420224} {"current_steps": 47000, "total_steps": 61300, "loss": 0.3112, "lr": 7.841543069474747e-06, "epoch": 7.6672104404567705, "percentage": 76.67, "elapsed_time": "6:24:25", "remaining_time": "1:56:57", "throughput": 4397.45, "total_tokens": 101430080} {"current_steps": 47005, "total_steps": 61300, "loss": 0.3189, "lr": 7.836366981402951e-06, "epoch": 7.668026101141925, "percentage": 76.68, "elapsed_time": "6:24:28", "remaining_time": "1:56:55", "throughput": 4397.5, "total_tokens": 101441856} {"current_steps": 47010, "total_steps": 61300, "loss": 0.3187, "lr": 7.831192284702334e-06, "epoch": 7.66884176182708, "percentage": 76.69, "elapsed_time": "6:24:30", "remaining_time": "1:56:52", "throughput": 4397.53, "total_tokens": 101451232} {"current_steps": 47015, "total_steps": 61300, "loss": 0.34, "lr": 7.826018979792385e-06, "epoch": 7.669657422512235, "percentage": 76.7, "elapsed_time": "6:24:32", "remaining_time": "1:56:50", "throughput": 4397.57, "total_tokens": 101461792} {"current_steps": 47020, "total_steps": 61300, "loss": 0.3554, "lr": 7.820847067092477e-06, "epoch": 7.67047308319739, "percentage": 76.7, "elapsed_time": "6:24:34", "remaining_time": "1:56:47", "throughput": 4397.61, "total_tokens": 101472096} {"current_steps": 47025, "total_steps": 61300, "loss": 0.3453, "lr": 7.815676547021871e-06, "epoch": 7.671288743882545, "percentage": 76.71, "elapsed_time": "6:24:36", "remaining_time": "1:56:45", "throughput": 4397.65, "total_tokens": 101482784} {"current_steps": 47030, "total_steps": 61300, "loss": 0.3296, "lr": 7.810507419999716e-06, "epoch": 7.672104404567699, "percentage": 76.72, "elapsed_time": "6:24:38", "remaining_time": "1:56:42", "throughput": 4397.69, "total_tokens": 101493248} {"current_steps": 47035, "total_steps": 61300, "loss": 0.3365, "lr": 7.805339686445051e-06, "epoch": 7.672920065252855, "percentage": 76.73, "elapsed_time": "6:24:41", "remaining_time": "1:56:40", "throughput": 4397.73, "total_tokens": 101504128} {"current_steps": 47040, "total_steps": 61300, "loss": 0.3107, "lr": 7.800173346776793e-06, "epoch": 7.67373572593801, "percentage": 76.74, "elapsed_time": "6:24:43", "remaining_time": "1:56:37", "throughput": 4397.77, "total_tokens": 101515808} {"current_steps": 47045, "total_steps": 61300, "loss": 0.3127, "lr": 7.795008401413756e-06, "epoch": 7.674551386623165, "percentage": 76.75, "elapsed_time": "6:24:45", "remaining_time": "1:56:35", "throughput": 4397.82, "total_tokens": 101526976} {"current_steps": 47050, "total_steps": 61300, "loss": 0.329, "lr": 7.789844850774636e-06, "epoch": 7.6753670473083195, "percentage": 76.75, "elapsed_time": "6:24:47", "remaining_time": "1:56:32", "throughput": 4397.85, "total_tokens": 101537440} {"current_steps": 47055, "total_steps": 61300, "loss": 0.3242, "lr": 7.784682695278014e-06, "epoch": 7.676182707993474, "percentage": 76.76, "elapsed_time": "6:24:50", "remaining_time": "1:56:30", "throughput": 4397.9, "total_tokens": 101549280} {"current_steps": 47060, "total_steps": 61300, "loss": 0.3262, "lr": 7.779521935342363e-06, "epoch": 7.67699836867863, "percentage": 76.77, "elapsed_time": "6:24:52", "remaining_time": "1:56:27", "throughput": 4397.93, "total_tokens": 101558720} {"current_steps": 47065, "total_steps": 61300, "loss": 0.3146, "lr": 7.77436257138604e-06, "epoch": 7.677814029363785, "percentage": 76.78, "elapsed_time": "6:24:54", "remaining_time": "1:56:25", "throughput": 4397.98, "total_tokens": 101570400} {"current_steps": 47070, "total_steps": 61300, "loss": 0.3053, "lr": 7.769204603827282e-06, "epoch": 7.67862969004894, "percentage": 76.79, "elapsed_time": "6:24:57", "remaining_time": "1:56:22", "throughput": 4398.02, "total_tokens": 101581472} {"current_steps": 47075, "total_steps": 61300, "loss": 0.3431, "lr": 7.764048033084235e-06, "epoch": 7.6794453507340945, "percentage": 76.79, "elapsed_time": "6:24:59", "remaining_time": "1:56:20", "throughput": 4398.07, "total_tokens": 101592480} {"current_steps": 47080, "total_steps": 61300, "loss": 0.3051, "lr": 7.758892859574906e-06, "epoch": 7.680261011419249, "percentage": 76.8, "elapsed_time": "6:25:01", "remaining_time": "1:56:17", "throughput": 4398.1, "total_tokens": 101601952} {"current_steps": 47085, "total_steps": 61300, "loss": 0.3612, "lr": 7.753739083717204e-06, "epoch": 7.681076672104405, "percentage": 76.81, "elapsed_time": "6:25:03", "remaining_time": "1:56:14", "throughput": 4398.14, "total_tokens": 101612384} {"current_steps": 47090, "total_steps": 61300, "loss": 0.3144, "lr": 7.748586705928917e-06, "epoch": 7.68189233278956, "percentage": 76.82, "elapsed_time": "6:25:05", "remaining_time": "1:56:12", "throughput": 4398.19, "total_tokens": 101623872} {"current_steps": 47095, "total_steps": 61300, "loss": 0.336, "lr": 7.743435726627726e-06, "epoch": 7.682707993474715, "percentage": 76.83, "elapsed_time": "6:25:08", "remaining_time": "1:56:09", "throughput": 4398.23, "total_tokens": 101635072} {"current_steps": 47100, "total_steps": 61300, "loss": 0.3484, "lr": 7.738286146231194e-06, "epoch": 7.6835236541598695, "percentage": 76.84, "elapsed_time": "6:25:10", "remaining_time": "1:56:07", "throughput": 4398.27, "total_tokens": 101644896} {"current_steps": 47105, "total_steps": 61300, "loss": 0.3117, "lr": 7.733137965156764e-06, "epoch": 7.684339314845024, "percentage": 76.84, "elapsed_time": "6:25:12", "remaining_time": "1:56:04", "throughput": 4398.3, "total_tokens": 101655584} {"current_steps": 47110, "total_steps": 61300, "loss": 0.3218, "lr": 7.727991183821792e-06, "epoch": 7.685154975530179, "percentage": 76.85, "elapsed_time": "6:25:14", "remaining_time": "1:56:02", "throughput": 4398.35, "total_tokens": 101666912} {"current_steps": 47115, "total_steps": 61300, "loss": 0.3355, "lr": 7.722845802643489e-06, "epoch": 7.685970636215334, "percentage": 76.86, "elapsed_time": "6:25:16", "remaining_time": "1:55:59", "throughput": 4398.38, "total_tokens": 101676768} {"current_steps": 47120, "total_steps": 61300, "loss": 0.3235, "lr": 7.71770182203897e-06, "epoch": 7.68678629690049, "percentage": 76.87, "elapsed_time": "6:25:19", "remaining_time": "1:55:57", "throughput": 4398.42, "total_tokens": 101687936} {"current_steps": 47125, "total_steps": 61300, "loss": 0.3354, "lr": 7.71255924242523e-06, "epoch": 7.6876019575856445, "percentage": 76.88, "elapsed_time": "6:25:21", "remaining_time": "1:55:54", "throughput": 4398.47, "total_tokens": 101698592} {"current_steps": 47130, "total_steps": 61300, "loss": 0.3255, "lr": 7.707418064219152e-06, "epoch": 7.688417618270799, "percentage": 76.88, "elapsed_time": "6:25:23", "remaining_time": "1:55:52", "throughput": 4398.51, "total_tokens": 101709312} {"current_steps": 47135, "total_steps": 61300, "loss": 0.333, "lr": 7.702278287837509e-06, "epoch": 7.689233278955954, "percentage": 76.89, "elapsed_time": "6:25:25", "remaining_time": "1:55:49", "throughput": 4398.55, "total_tokens": 101720512} {"current_steps": 47140, "total_steps": 61300, "loss": 0.3521, "lr": 7.697139913696955e-06, "epoch": 7.690048939641109, "percentage": 76.9, "elapsed_time": "6:25:28", "remaining_time": "1:55:47", "throughput": 4398.61, "total_tokens": 101732640} {"current_steps": 47145, "total_steps": 61300, "loss": 0.3489, "lr": 7.692002942214035e-06, "epoch": 7.690864600326265, "percentage": 76.91, "elapsed_time": "6:25:30", "remaining_time": "1:55:44", "throughput": 4398.64, "total_tokens": 101742400} {"current_steps": 47150, "total_steps": 61300, "loss": 0.3086, "lr": 7.686867373805176e-06, "epoch": 7.691680261011419, "percentage": 76.92, "elapsed_time": "6:25:32", "remaining_time": "1:55:42", "throughput": 4398.67, "total_tokens": 101751936} {"current_steps": 47155, "total_steps": 61300, "loss": 0.3392, "lr": 7.681733208886693e-06, "epoch": 7.692495921696574, "percentage": 76.92, "elapsed_time": "6:25:34", "remaining_time": "1:55:39", "throughput": 4398.71, "total_tokens": 101763136} {"current_steps": 47160, "total_steps": 61300, "loss": 0.3188, "lr": 7.676600447874788e-06, "epoch": 7.693311582381729, "percentage": 76.93, "elapsed_time": "6:25:36", "remaining_time": "1:55:37", "throughput": 4398.75, "total_tokens": 101773440} {"current_steps": 47165, "total_steps": 61300, "loss": 0.335, "lr": 7.67146909118555e-06, "epoch": 7.694127243066884, "percentage": 76.94, "elapsed_time": "6:25:38", "remaining_time": "1:55:34", "throughput": 4398.79, "total_tokens": 101783264} {"current_steps": 47170, "total_steps": 61300, "loss": 0.3413, "lr": 7.666339139234949e-06, "epoch": 7.69494290375204, "percentage": 76.95, "elapsed_time": "6:25:41", "remaining_time": "1:55:32", "throughput": 4398.82, "total_tokens": 101793856} {"current_steps": 47175, "total_steps": 61300, "loss": 0.3344, "lr": 7.66121059243885e-06, "epoch": 7.695758564437194, "percentage": 76.96, "elapsed_time": "6:25:43", "remaining_time": "1:55:29", "throughput": 4398.86, "total_tokens": 101804832} {"current_steps": 47180, "total_steps": 61300, "loss": 0.3203, "lr": 7.656083451212995e-06, "epoch": 7.696574225122349, "percentage": 76.97, "elapsed_time": "6:25:45", "remaining_time": "1:55:27", "throughput": 4398.9, "total_tokens": 101815808} {"current_steps": 47185, "total_steps": 61300, "loss": 0.3457, "lr": 7.650957715973017e-06, "epoch": 7.697389885807504, "percentage": 76.97, "elapsed_time": "6:25:47", "remaining_time": "1:55:24", "throughput": 4398.93, "total_tokens": 101825120} {"current_steps": 47190, "total_steps": 61300, "loss": 0.3112, "lr": 7.645833387134437e-06, "epoch": 7.698205546492659, "percentage": 76.98, "elapsed_time": "6:25:50", "remaining_time": "1:55:21", "throughput": 4398.97, "total_tokens": 101836416} {"current_steps": 47195, "total_steps": 61300, "loss": 0.3652, "lr": 7.640710465112654e-06, "epoch": 7.699021207177814, "percentage": 76.99, "elapsed_time": "6:25:52", "remaining_time": "1:55:19", "throughput": 4399.01, "total_tokens": 101846240} {"current_steps": 47200, "total_steps": 61300, "loss": 0.3283, "lr": 7.635588950322964e-06, "epoch": 7.699836867862969, "percentage": 77.0, "elapsed_time": "6:25:54", "remaining_time": "1:55:16", "throughput": 4399.05, "total_tokens": 101857152} {"current_steps": 47205, "total_steps": 61300, "loss": 0.3202, "lr": 7.630468843180538e-06, "epoch": 7.700652528548124, "percentage": 77.01, "elapsed_time": "6:25:56", "remaining_time": "1:55:14", "throughput": 4399.09, "total_tokens": 101867296} {"current_steps": 47210, "total_steps": 61300, "loss": 0.3414, "lr": 7.625350144100441e-06, "epoch": 7.701468189233279, "percentage": 77.01, "elapsed_time": "6:25:58", "remaining_time": "1:55:11", "throughput": 4399.12, "total_tokens": 101876000} {"current_steps": 47215, "total_steps": 61300, "loss": 0.3276, "lr": 7.620232853497611e-06, "epoch": 7.702283849918434, "percentage": 77.02, "elapsed_time": "6:26:00", "remaining_time": "1:55:09", "throughput": 4399.15, "total_tokens": 101886080} {"current_steps": 47220, "total_steps": 61300, "loss": 0.3668, "lr": 7.615116971786895e-06, "epoch": 7.703099510603589, "percentage": 77.03, "elapsed_time": "6:26:02", "remaining_time": "1:55:06", "throughput": 4399.19, "total_tokens": 101896480} {"current_steps": 47225, "total_steps": 61300, "loss": 0.3058, "lr": 7.610002499383012e-06, "epoch": 7.7039151712887435, "percentage": 77.04, "elapsed_time": "6:26:04", "remaining_time": "1:55:04", "throughput": 4399.23, "total_tokens": 101907136} {"current_steps": 47230, "total_steps": 61300, "loss": 0.3402, "lr": 7.60488943670056e-06, "epoch": 7.704730831973899, "percentage": 77.05, "elapsed_time": "6:26:07", "remaining_time": "1:55:01", "throughput": 4399.28, "total_tokens": 101918624} {"current_steps": 47235, "total_steps": 61300, "loss": 0.3402, "lr": 7.59977778415403e-06, "epoch": 7.705546492659054, "percentage": 77.06, "elapsed_time": "6:26:09", "remaining_time": "1:54:59", "throughput": 4399.32, "total_tokens": 101929408} {"current_steps": 47240, "total_steps": 61300, "loss": 0.3686, "lr": 7.594667542157796e-06, "epoch": 7.706362153344209, "percentage": 77.06, "elapsed_time": "6:26:11", "remaining_time": "1:54:56", "throughput": 4399.37, "total_tokens": 101940736} {"current_steps": 47245, "total_steps": 61300, "loss": 0.3164, "lr": 7.5895587111261325e-06, "epoch": 7.707177814029364, "percentage": 77.07, "elapsed_time": "6:26:13", "remaining_time": "1:54:54", "throughput": 4399.4, "total_tokens": 101950848} {"current_steps": 47250, "total_steps": 61300, "loss": 0.338, "lr": 7.584451291473177e-06, "epoch": 7.7079934747145185, "percentage": 77.08, "elapsed_time": "6:26:15", "remaining_time": "1:54:51", "throughput": 4399.45, "total_tokens": 101961376} {"current_steps": 47255, "total_steps": 61300, "loss": 0.2993, "lr": 7.579345283612968e-06, "epoch": 7.708809135399674, "percentage": 77.09, "elapsed_time": "6:26:18", "remaining_time": "1:54:48", "throughput": 4399.5, "total_tokens": 101972448} {"current_steps": 47260, "total_steps": 61300, "loss": 0.3303, "lr": 7.574240687959422e-06, "epoch": 7.709624796084829, "percentage": 77.1, "elapsed_time": "6:26:20", "remaining_time": "1:54:46", "throughput": 4399.54, "total_tokens": 101983712} {"current_steps": 47265, "total_steps": 61300, "loss": 0.3621, "lr": 7.56913750492634e-06, "epoch": 7.710440456769984, "percentage": 77.1, "elapsed_time": "6:26:22", "remaining_time": "1:54:43", "throughput": 4399.57, "total_tokens": 101993792} {"current_steps": 47270, "total_steps": 61300, "loss": 0.3362, "lr": 7.564035734927419e-06, "epoch": 7.711256117455139, "percentage": 77.11, "elapsed_time": "6:26:24", "remaining_time": "1:54:41", "throughput": 4399.61, "total_tokens": 102004800} {"current_steps": 47275, "total_steps": 61300, "loss": 0.3293, "lr": 7.558935378376228e-06, "epoch": 7.712071778140293, "percentage": 77.12, "elapsed_time": "6:26:27", "remaining_time": "1:54:38", "throughput": 4399.65, "total_tokens": 102015936} {"current_steps": 47280, "total_steps": 61300, "loss": 0.3408, "lr": 7.553836435686232e-06, "epoch": 7.712887438825448, "percentage": 77.13, "elapsed_time": "6:26:29", "remaining_time": "1:54:36", "throughput": 4399.69, "total_tokens": 102026592} {"current_steps": 47285, "total_steps": 61300, "loss": 0.315, "lr": 7.5487389072707744e-06, "epoch": 7.713703099510604, "percentage": 77.14, "elapsed_time": "6:26:31", "remaining_time": "1:54:33", "throughput": 4399.73, "total_tokens": 102036448} {"current_steps": 47290, "total_steps": 61300, "loss": 0.3216, "lr": 7.543642793543088e-06, "epoch": 7.714518760195759, "percentage": 77.15, "elapsed_time": "6:26:34", "remaining_time": "1:54:31", "throughput": 4399.78, "total_tokens": 102048800} {"current_steps": 47295, "total_steps": 61300, "loss": 0.3368, "lr": 7.53854809491629e-06, "epoch": 7.715334420880914, "percentage": 77.15, "elapsed_time": "6:26:36", "remaining_time": "1:54:28", "throughput": 4399.82, "total_tokens": 102060000} {"current_steps": 47300, "total_steps": 61300, "loss": 0.3429, "lr": 7.533454811803381e-06, "epoch": 7.716150081566068, "percentage": 77.16, "elapsed_time": "6:26:38", "remaining_time": "1:54:26", "throughput": 4399.86, "total_tokens": 102071104} {"current_steps": 47305, "total_steps": 61300, "loss": 0.3243, "lr": 7.528362944617251e-06, "epoch": 7.716965742251223, "percentage": 77.17, "elapsed_time": "6:26:41", "remaining_time": "1:54:23", "throughput": 4399.91, "total_tokens": 102082880} {"current_steps": 47310, "total_steps": 61300, "loss": 0.338, "lr": 7.523272493770669e-06, "epoch": 7.717781402936378, "percentage": 77.18, "elapsed_time": "6:26:43", "remaining_time": "1:54:21", "throughput": 4399.96, "total_tokens": 102094816} {"current_steps": 47315, "total_steps": 61300, "loss": 0.3058, "lr": 7.518183459676295e-06, "epoch": 7.718597063621534, "percentage": 77.19, "elapsed_time": "6:26:45", "remaining_time": "1:54:18", "throughput": 4400.0, "total_tokens": 102105632} {"current_steps": 47320, "total_steps": 61300, "loss": 0.3398, "lr": 7.513095842746665e-06, "epoch": 7.719412724306689, "percentage": 77.19, "elapsed_time": "6:26:47", "remaining_time": "1:54:16", "throughput": 4400.04, "total_tokens": 102115808} {"current_steps": 47325, "total_steps": 61300, "loss": 0.3082, "lr": 7.5080096433942204e-06, "epoch": 7.720228384991843, "percentage": 77.2, "elapsed_time": "6:26:50", "remaining_time": "1:54:13", "throughput": 4400.09, "total_tokens": 102127392} {"current_steps": 47330, "total_steps": 61300, "loss": 0.3471, "lr": 7.502924862031269e-06, "epoch": 7.721044045676998, "percentage": 77.21, "elapsed_time": "6:26:52", "remaining_time": "1:54:11", "throughput": 4400.14, "total_tokens": 102139136} {"current_steps": 47335, "total_steps": 61300, "loss": 0.3564, "lr": 7.497841499070005e-06, "epoch": 7.721859706362153, "percentage": 77.22, "elapsed_time": "6:26:55", "remaining_time": "1:54:09", "throughput": 4400.18, "total_tokens": 102150688} {"current_steps": 47340, "total_steps": 61300, "loss": 0.4031, "lr": 7.4927595549225155e-06, "epoch": 7.722675367047309, "percentage": 77.23, "elapsed_time": "6:26:57", "remaining_time": "1:54:06", "throughput": 4400.22, "total_tokens": 102161568} {"current_steps": 47345, "total_steps": 61300, "loss": 0.301, "lr": 7.487679030000769e-06, "epoch": 7.7234910277324635, "percentage": 77.23, "elapsed_time": "6:26:59", "remaining_time": "1:54:04", "throughput": 4400.27, "total_tokens": 102173440} {"current_steps": 47350, "total_steps": 61300, "loss": 0.3458, "lr": 7.482599924716613e-06, "epoch": 7.724306688417618, "percentage": 77.24, "elapsed_time": "6:27:02", "remaining_time": "1:54:01", "throughput": 4400.31, "total_tokens": 102185376} {"current_steps": 47355, "total_steps": 61300, "loss": 0.332, "lr": 7.477522239481793e-06, "epoch": 7.725122349102773, "percentage": 77.25, "elapsed_time": "6:27:04", "remaining_time": "1:53:59", "throughput": 4400.35, "total_tokens": 102195456} {"current_steps": 47360, "total_steps": 61300, "loss": 0.3514, "lr": 7.472445974707928e-06, "epoch": 7.725938009787928, "percentage": 77.26, "elapsed_time": "6:27:06", "remaining_time": "1:53:56", "throughput": 4400.38, "total_tokens": 102206080} {"current_steps": 47365, "total_steps": 61300, "loss": 0.3258, "lr": 7.467371130806524e-06, "epoch": 7.726753670473083, "percentage": 77.27, "elapsed_time": "6:27:08", "remaining_time": "1:53:54", "throughput": 4400.42, "total_tokens": 102216736} {"current_steps": 47370, "total_steps": 61300, "loss": 0.3231, "lr": 7.462297708188978e-06, "epoch": 7.7275693311582385, "percentage": 77.28, "elapsed_time": "6:27:11", "remaining_time": "1:53:51", "throughput": 4400.46, "total_tokens": 102227904} {"current_steps": 47375, "total_steps": 61300, "loss": 0.3304, "lr": 7.457225707266566e-06, "epoch": 7.728384991843393, "percentage": 77.28, "elapsed_time": "6:27:13", "remaining_time": "1:53:49", "throughput": 4400.5, "total_tokens": 102239200} {"current_steps": 47380, "total_steps": 61300, "loss": 0.2995, "lr": 7.452155128450447e-06, "epoch": 7.729200652528548, "percentage": 77.29, "elapsed_time": "6:27:16", "remaining_time": "1:53:46", "throughput": 4400.55, "total_tokens": 102251264} {"current_steps": 47385, "total_steps": 61300, "loss": 0.3247, "lr": 7.447085972151663e-06, "epoch": 7.730016313213703, "percentage": 77.3, "elapsed_time": "6:27:18", "remaining_time": "1:53:44", "throughput": 4400.59, "total_tokens": 102262432} {"current_steps": 47390, "total_steps": 61300, "loss": 0.3396, "lr": 7.4420182387811596e-06, "epoch": 7.730831973898858, "percentage": 77.31, "elapsed_time": "6:27:20", "remaining_time": "1:53:41", "throughput": 4400.65, "total_tokens": 102274912} {"current_steps": 47395, "total_steps": 61300, "loss": 0.3624, "lr": 7.436951928749747e-06, "epoch": 7.731647634584013, "percentage": 77.32, "elapsed_time": "6:27:23", "remaining_time": "1:53:39", "throughput": 4400.69, "total_tokens": 102285696} {"current_steps": 47400, "total_steps": 61300, "loss": 0.3584, "lr": 7.431887042468125e-06, "epoch": 7.732463295269168, "percentage": 77.32, "elapsed_time": "6:27:25", "remaining_time": "1:53:36", "throughput": 4400.72, "total_tokens": 102296160} {"current_steps": 47405, "total_steps": 61300, "loss": 0.3416, "lr": 7.426823580346881e-06, "epoch": 7.733278955954323, "percentage": 77.33, "elapsed_time": "6:27:27", "remaining_time": "1:53:34", "throughput": 4400.77, "total_tokens": 102307712} {"current_steps": 47410, "total_steps": 61300, "loss": 0.3465, "lr": 7.421761542796479e-06, "epoch": 7.734094616639478, "percentage": 77.34, "elapsed_time": "6:27:30", "remaining_time": "1:53:31", "throughput": 4400.82, "total_tokens": 102320032} {"current_steps": 47415, "total_steps": 61300, "loss": 0.3462, "lr": 7.41670093022728e-06, "epoch": 7.734910277324633, "percentage": 77.35, "elapsed_time": "6:27:32", "remaining_time": "1:53:29", "throughput": 4400.86, "total_tokens": 102330656} {"current_steps": 47420, "total_steps": 61300, "loss": 0.3246, "lr": 7.411641743049522e-06, "epoch": 7.735725938009788, "percentage": 77.36, "elapsed_time": "6:27:34", "remaining_time": "1:53:26", "throughput": 4400.9, "total_tokens": 102340704} {"current_steps": 47425, "total_steps": 61300, "loss": 0.3259, "lr": 7.406583981673315e-06, "epoch": 7.736541598694943, "percentage": 77.37, "elapsed_time": "6:27:36", "remaining_time": "1:53:24", "throughput": 4400.95, "total_tokens": 102350752} {"current_steps": 47430, "total_steps": 61300, "loss": 0.3314, "lr": 7.401527646508691e-06, "epoch": 7.737357259380098, "percentage": 77.37, "elapsed_time": "6:27:38", "remaining_time": "1:53:21", "throughput": 4400.99, "total_tokens": 102360800} {"current_steps": 47435, "total_steps": 61300, "loss": 0.3448, "lr": 7.396472737965526e-06, "epoch": 7.738172920065253, "percentage": 77.38, "elapsed_time": "6:27:40", "remaining_time": "1:53:19", "throughput": 4401.03, "total_tokens": 102372096} {"current_steps": 47440, "total_steps": 61300, "loss": 0.3183, "lr": 7.391419256453602e-06, "epoch": 7.738988580750408, "percentage": 77.39, "elapsed_time": "6:27:43", "remaining_time": "1:53:16", "throughput": 4401.07, "total_tokens": 102382112} {"current_steps": 47445, "total_steps": 61300, "loss": 0.3592, "lr": 7.386367202382577e-06, "epoch": 7.739804241435563, "percentage": 77.4, "elapsed_time": "6:27:44", "remaining_time": "1:53:13", "throughput": 4401.1, "total_tokens": 102391392} {"current_steps": 47450, "total_steps": 61300, "loss": 0.3387, "lr": 7.3813165761619975e-06, "epoch": 7.740619902120718, "percentage": 77.41, "elapsed_time": "6:27:47", "remaining_time": "1:53:11", "throughput": 4401.14, "total_tokens": 102402720} {"current_steps": 47455, "total_steps": 61300, "loss": 0.323, "lr": 7.376267378201293e-06, "epoch": 7.741435562805873, "percentage": 77.41, "elapsed_time": "6:27:49", "remaining_time": "1:53:08", "throughput": 4401.18, "total_tokens": 102412992} {"current_steps": 47460, "total_steps": 61300, "loss": 0.2997, "lr": 7.371219608909777e-06, "epoch": 7.742251223491028, "percentage": 77.42, "elapsed_time": "6:27:51", "remaining_time": "1:53:06", "throughput": 4401.22, "total_tokens": 102424416} {"current_steps": 47465, "total_steps": 61300, "loss": 0.3136, "lr": 7.366173268696646e-06, "epoch": 7.743066884176183, "percentage": 77.43, "elapsed_time": "6:27:54", "remaining_time": "1:53:03", "throughput": 4401.26, "total_tokens": 102435296} {"current_steps": 47470, "total_steps": 61300, "loss": 0.3443, "lr": 7.3611283579709835e-06, "epoch": 7.7438825448613375, "percentage": 77.44, "elapsed_time": "6:27:56", "remaining_time": "1:53:01", "throughput": 4401.3, "total_tokens": 102445856} {"current_steps": 47475, "total_steps": 61300, "loss": 0.3479, "lr": 7.356084877141756e-06, "epoch": 7.744698205546492, "percentage": 77.45, "elapsed_time": "6:27:58", "remaining_time": "1:52:58", "throughput": 4401.35, "total_tokens": 102457024} {"current_steps": 47480, "total_steps": 61300, "loss": 0.3328, "lr": 7.35104282661781e-06, "epoch": 7.745513866231647, "percentage": 77.46, "elapsed_time": "6:28:00", "remaining_time": "1:52:56", "throughput": 4401.39, "total_tokens": 102467744} {"current_steps": 47485, "total_steps": 61300, "loss": 0.2914, "lr": 7.346002206807887e-06, "epoch": 7.746329526916803, "percentage": 77.46, "elapsed_time": "6:28:02", "remaining_time": "1:52:53", "throughput": 4401.41, "total_tokens": 102477408} {"current_steps": 47490, "total_steps": 61300, "loss": 0.343, "lr": 7.340963018120597e-06, "epoch": 7.747145187601958, "percentage": 77.47, "elapsed_time": "6:28:05", "remaining_time": "1:52:51", "throughput": 4401.45, "total_tokens": 102487840} {"current_steps": 47495, "total_steps": 61300, "loss": 0.3532, "lr": 7.335925260964446e-06, "epoch": 7.7479608482871125, "percentage": 77.48, "elapsed_time": "6:28:07", "remaining_time": "1:52:48", "throughput": 4401.49, "total_tokens": 102498624} {"current_steps": 47500, "total_steps": 61300, "loss": 0.3142, "lr": 7.330888935747821e-06, "epoch": 7.748776508972267, "percentage": 77.49, "elapsed_time": "6:28:09", "remaining_time": "1:52:46", "throughput": 4401.53, "total_tokens": 102509952} {"current_steps": 47505, "total_steps": 61300, "loss": 0.2844, "lr": 7.325854042878991e-06, "epoch": 7.749592169657422, "percentage": 77.5, "elapsed_time": "6:28:11", "remaining_time": "1:52:43", "throughput": 4401.58, "total_tokens": 102521120} {"current_steps": 47510, "total_steps": 61300, "loss": 0.3505, "lr": 7.320820582766108e-06, "epoch": 7.750407830342578, "percentage": 77.5, "elapsed_time": "6:28:14", "remaining_time": "1:52:41", "throughput": 4401.63, "total_tokens": 102532832} {"current_steps": 47515, "total_steps": 61300, "loss": 0.3364, "lr": 7.315788555817215e-06, "epoch": 7.751223491027733, "percentage": 77.51, "elapsed_time": "6:28:16", "remaining_time": "1:52:38", "throughput": 4401.65, "total_tokens": 102542752} {"current_steps": 47520, "total_steps": 61300, "loss": 0.2987, "lr": 7.3107579624402286e-06, "epoch": 7.7520391517128875, "percentage": 77.52, "elapsed_time": "6:28:18", "remaining_time": "1:52:36", "throughput": 4401.7, "total_tokens": 102553920} {"current_steps": 47525, "total_steps": 61300, "loss": 0.3378, "lr": 7.305728803042949e-06, "epoch": 7.752854812398042, "percentage": 77.53, "elapsed_time": "6:28:21", "remaining_time": "1:52:33", "throughput": 4401.74, "total_tokens": 102565088} {"current_steps": 47530, "total_steps": 61300, "loss": 0.3475, "lr": 7.3007010780330785e-06, "epoch": 7.753670473083197, "percentage": 77.54, "elapsed_time": "6:28:23", "remaining_time": "1:52:31", "throughput": 4401.79, "total_tokens": 102576704} {"current_steps": 47535, "total_steps": 61300, "loss": 0.3133, "lr": 7.295674787818188e-06, "epoch": 7.754486133768353, "percentage": 77.54, "elapsed_time": "6:28:25", "remaining_time": "1:52:28", "throughput": 4401.83, "total_tokens": 102588000} {"current_steps": 47540, "total_steps": 61300, "loss": 0.3671, "lr": 7.290649932805726e-06, "epoch": 7.755301794453508, "percentage": 77.55, "elapsed_time": "6:28:27", "remaining_time": "1:52:26", "throughput": 4401.87, "total_tokens": 102598144} {"current_steps": 47545, "total_steps": 61300, "loss": 0.3292, "lr": 7.285626513403038e-06, "epoch": 7.7561174551386625, "percentage": 77.56, "elapsed_time": "6:28:29", "remaining_time": "1:52:23", "throughput": 4401.91, "total_tokens": 102608256} {"current_steps": 47550, "total_steps": 61300, "loss": 0.3365, "lr": 7.2806045300173484e-06, "epoch": 7.756933115823817, "percentage": 77.57, "elapsed_time": "6:28:32", "remaining_time": "1:52:21", "throughput": 4401.95, "total_tokens": 102618528} {"current_steps": 47555, "total_steps": 61300, "loss": 0.3329, "lr": 7.275583983055753e-06, "epoch": 7.757748776508972, "percentage": 77.58, "elapsed_time": "6:28:34", "remaining_time": "1:52:18", "throughput": 4401.99, "total_tokens": 102629632} {"current_steps": 47560, "total_steps": 61300, "loss": 0.3365, "lr": 7.2705648729252615e-06, "epoch": 7.758564437194127, "percentage": 77.59, "elapsed_time": "6:28:36", "remaining_time": "1:52:16", "throughput": 4402.03, "total_tokens": 102639712} {"current_steps": 47565, "total_steps": 61300, "loss": 0.348, "lr": 7.265547200032738e-06, "epoch": 7.759380097879282, "percentage": 77.59, "elapsed_time": "6:28:38", "remaining_time": "1:52:13", "throughput": 4402.07, "total_tokens": 102650272} {"current_steps": 47570, "total_steps": 61300, "loss": 0.3099, "lr": 7.260530964784945e-06, "epoch": 7.760195758564437, "percentage": 77.6, "elapsed_time": "6:28:40", "remaining_time": "1:52:11", "throughput": 4402.12, "total_tokens": 102661216} {"current_steps": 47575, "total_steps": 61300, "loss": 0.3617, "lr": 7.2555161675885195e-06, "epoch": 7.761011419249592, "percentage": 77.61, "elapsed_time": "6:28:42", "remaining_time": "1:52:08", "throughput": 4402.17, "total_tokens": 102671200} {"current_steps": 47580, "total_steps": 61300, "loss": 0.3509, "lr": 7.250502808849988e-06, "epoch": 7.761827079934747, "percentage": 77.62, "elapsed_time": "6:28:45", "remaining_time": "1:52:05", "throughput": 4402.2, "total_tokens": 102682144} {"current_steps": 47585, "total_steps": 61300, "loss": 0.3616, "lr": 7.2454908889757586e-06, "epoch": 7.762642740619902, "percentage": 77.63, "elapsed_time": "6:28:47", "remaining_time": "1:52:03", "throughput": 4402.24, "total_tokens": 102693376} {"current_steps": 47590, "total_steps": 61300, "loss": 0.3046, "lr": 7.240480408372125e-06, "epoch": 7.763458401305057, "percentage": 77.63, "elapsed_time": "6:28:49", "remaining_time": "1:52:01", "throughput": 4402.29, "total_tokens": 102704800} {"current_steps": 47595, "total_steps": 61300, "loss": 0.3427, "lr": 7.235471367445257e-06, "epoch": 7.764274061990212, "percentage": 77.64, "elapsed_time": "6:28:52", "remaining_time": "1:51:58", "throughput": 4402.33, "total_tokens": 102715776} {"current_steps": 47600, "total_steps": 61300, "loss": 0.326, "lr": 7.2304637666012195e-06, "epoch": 7.765089722675367, "percentage": 77.65, "elapsed_time": "6:28:54", "remaining_time": "1:51:56", "throughput": 4402.38, "total_tokens": 102727232} {"current_steps": 47605, "total_steps": 61300, "loss": 0.3117, "lr": 7.22545760624595e-06, "epoch": 7.765905383360522, "percentage": 77.66, "elapsed_time": "6:28:56", "remaining_time": "1:51:53", "throughput": 4402.42, "total_tokens": 102737568} {"current_steps": 47610, "total_steps": 61300, "loss": 0.3069, "lr": 7.2204528867852725e-06, "epoch": 7.766721044045677, "percentage": 77.67, "elapsed_time": "6:28:59", "remaining_time": "1:51:51", "throughput": 4402.46, "total_tokens": 102749728} {"current_steps": 47615, "total_steps": 61300, "loss": 0.3221, "lr": 7.215449608624899e-06, "epoch": 7.767536704730832, "percentage": 77.68, "elapsed_time": "6:29:01", "remaining_time": "1:51:48", "throughput": 4402.5, "total_tokens": 102760256} {"current_steps": 47620, "total_steps": 61300, "loss": 0.3444, "lr": 7.210447772170418e-06, "epoch": 7.768352365415987, "percentage": 77.68, "elapsed_time": "6:29:03", "remaining_time": "1:51:46", "throughput": 4402.54, "total_tokens": 102771648} {"current_steps": 47625, "total_steps": 61300, "loss": 0.3345, "lr": 7.205447377827301e-06, "epoch": 7.769168026101142, "percentage": 77.69, "elapsed_time": "6:29:06", "remaining_time": "1:51:43", "throughput": 4402.58, "total_tokens": 102782912} {"current_steps": 47630, "total_steps": 61300, "loss": 0.3235, "lr": 7.200448426000911e-06, "epoch": 7.769983686786297, "percentage": 77.7, "elapsed_time": "6:29:08", "remaining_time": "1:51:41", "throughput": 4402.63, "total_tokens": 102795200} {"current_steps": 47635, "total_steps": 61300, "loss": 0.3788, "lr": 7.195450917096483e-06, "epoch": 7.770799347471452, "percentage": 77.71, "elapsed_time": "6:29:10", "remaining_time": "1:51:38", "throughput": 4402.67, "total_tokens": 102805600} {"current_steps": 47640, "total_steps": 61300, "loss": 0.3075, "lr": 7.190454851519138e-06, "epoch": 7.771615008156607, "percentage": 77.72, "elapsed_time": "6:29:13", "remaining_time": "1:51:36", "throughput": 4402.71, "total_tokens": 102816800} {"current_steps": 47645, "total_steps": 61300, "loss": 0.3307, "lr": 7.185460229673893e-06, "epoch": 7.7724306688417615, "percentage": 77.72, "elapsed_time": "6:29:15", "remaining_time": "1:51:33", "throughput": 4402.76, "total_tokens": 102827968} {"current_steps": 47650, "total_steps": 61300, "loss": 0.3026, "lr": 7.180467051965634e-06, "epoch": 7.773246329526917, "percentage": 77.73, "elapsed_time": "6:29:17", "remaining_time": "1:51:31", "throughput": 4402.8, "total_tokens": 102838400} {"current_steps": 47655, "total_steps": 61300, "loss": 0.3349, "lr": 7.17547531879913e-06, "epoch": 7.774061990212072, "percentage": 77.74, "elapsed_time": "6:29:19", "remaining_time": "1:51:28", "throughput": 4402.83, "total_tokens": 102848704} {"current_steps": 47660, "total_steps": 61300, "loss": 0.3229, "lr": 7.170485030579038e-06, "epoch": 7.774877650897227, "percentage": 77.75, "elapsed_time": "6:29:21", "remaining_time": "1:51:26", "throughput": 4402.87, "total_tokens": 102859296} {"current_steps": 47665, "total_steps": 61300, "loss": 0.3099, "lr": 7.165496187709894e-06, "epoch": 7.775693311582382, "percentage": 77.76, "elapsed_time": "6:29:24", "remaining_time": "1:51:23", "throughput": 4402.92, "total_tokens": 102870592} {"current_steps": 47670, "total_steps": 61300, "loss": 0.3338, "lr": 7.160508790596121e-06, "epoch": 7.7765089722675365, "percentage": 77.77, "elapsed_time": "6:29:26", "remaining_time": "1:51:21", "throughput": 4402.96, "total_tokens": 102881568} {"current_steps": 47675, "total_steps": 61300, "loss": 0.3372, "lr": 7.155522839642023e-06, "epoch": 7.777324632952691, "percentage": 77.77, "elapsed_time": "6:29:28", "remaining_time": "1:51:18", "throughput": 4403.0, "total_tokens": 102892320} {"current_steps": 47680, "total_steps": 61300, "loss": 0.3222, "lr": 7.150538335251786e-06, "epoch": 7.778140293637847, "percentage": 77.78, "elapsed_time": "6:29:30", "remaining_time": "1:51:16", "throughput": 4403.04, "total_tokens": 102903456} {"current_steps": 47685, "total_steps": 61300, "loss": 0.3527, "lr": 7.1455552778294775e-06, "epoch": 7.778955954323002, "percentage": 77.79, "elapsed_time": "6:29:33", "remaining_time": "1:51:13", "throughput": 4403.08, "total_tokens": 102914208} {"current_steps": 47690, "total_steps": 61300, "loss": 0.3576, "lr": 7.140573667779052e-06, "epoch": 7.779771615008157, "percentage": 77.8, "elapsed_time": "6:29:35", "remaining_time": "1:51:11", "throughput": 4403.12, "total_tokens": 102925152} {"current_steps": 47695, "total_steps": 61300, "loss": 0.3378, "lr": 7.1355935055043314e-06, "epoch": 7.780587275693311, "percentage": 77.81, "elapsed_time": "6:29:37", "remaining_time": "1:51:08", "throughput": 4403.16, "total_tokens": 102936064} {"current_steps": 47700, "total_steps": 61300, "loss": 0.334, "lr": 7.130614791409057e-06, "epoch": 7.781402936378466, "percentage": 77.81, "elapsed_time": "6:29:40", "remaining_time": "1:51:06", "throughput": 4403.21, "total_tokens": 102947200} {"current_steps": 47705, "total_steps": 61300, "loss": 0.332, "lr": 7.125637525896814e-06, "epoch": 7.782218597063622, "percentage": 77.82, "elapsed_time": "6:29:42", "remaining_time": "1:51:03", "throughput": 4403.25, "total_tokens": 102957216} {"current_steps": 47710, "total_steps": 61300, "loss": 0.3414, "lr": 7.1206617093710845e-06, "epoch": 7.783034257748777, "percentage": 77.83, "elapsed_time": "6:29:44", "remaining_time": "1:51:00", "throughput": 4403.28, "total_tokens": 102968160} {"current_steps": 47715, "total_steps": 61300, "loss": 0.3245, "lr": 7.115687342235239e-06, "epoch": 7.783849918433932, "percentage": 77.84, "elapsed_time": "6:29:46", "remaining_time": "1:50:58", "throughput": 4403.32, "total_tokens": 102978912} {"current_steps": 47720, "total_steps": 61300, "loss": 0.3323, "lr": 7.11071442489252e-06, "epoch": 7.784665579119086, "percentage": 77.85, "elapsed_time": "6:29:48", "remaining_time": "1:50:55", "throughput": 4403.36, "total_tokens": 102989568} {"current_steps": 47725, "total_steps": 61300, "loss": 0.3542, "lr": 7.1057429577460584e-06, "epoch": 7.785481239804241, "percentage": 77.85, "elapsed_time": "6:29:51", "remaining_time": "1:50:53", "throughput": 4403.4, "total_tokens": 103000512} {"current_steps": 47730, "total_steps": 61300, "loss": 0.3291, "lr": 7.100772941198869e-06, "epoch": 7.786296900489396, "percentage": 77.86, "elapsed_time": "6:29:53", "remaining_time": "1:50:50", "throughput": 4403.45, "total_tokens": 103012320} {"current_steps": 47735, "total_steps": 61300, "loss": 0.3088, "lr": 7.095804375653844e-06, "epoch": 7.787112561174552, "percentage": 77.87, "elapsed_time": "6:29:55", "remaining_time": "1:50:48", "throughput": 4403.49, "total_tokens": 103023936} {"current_steps": 47740, "total_steps": 61300, "loss": 0.3195, "lr": 7.090837261513764e-06, "epoch": 7.787928221859707, "percentage": 77.88, "elapsed_time": "6:29:58", "remaining_time": "1:50:45", "throughput": 4403.53, "total_tokens": 103033696} {"current_steps": 47745, "total_steps": 61300, "loss": 0.331, "lr": 7.085871599181274e-06, "epoch": 7.788743882544861, "percentage": 77.89, "elapsed_time": "6:30:00", "remaining_time": "1:50:43", "throughput": 4403.57, "total_tokens": 103045280} {"current_steps": 47750, "total_steps": 61300, "loss": 0.3329, "lr": 7.0809073890589356e-06, "epoch": 7.789559543230016, "percentage": 77.9, "elapsed_time": "6:30:02", "remaining_time": "1:50:40", "throughput": 4403.62, "total_tokens": 103055584} {"current_steps": 47755, "total_steps": 61300, "loss": 0.365, "lr": 7.075944631549167e-06, "epoch": 7.790375203915171, "percentage": 77.9, "elapsed_time": "6:30:04", "remaining_time": "1:50:38", "throughput": 4403.65, "total_tokens": 103066880} {"current_steps": 47760, "total_steps": 61300, "loss": 0.3293, "lr": 7.07098332705427e-06, "epoch": 7.791190864600326, "percentage": 77.91, "elapsed_time": "6:30:07", "remaining_time": "1:50:35", "throughput": 4403.7, "total_tokens": 103077568} {"current_steps": 47765, "total_steps": 61300, "loss": 0.3248, "lr": 7.066023475976438e-06, "epoch": 7.7920065252854815, "percentage": 77.92, "elapsed_time": "6:30:09", "remaining_time": "1:50:33", "throughput": 4403.74, "total_tokens": 103088672} {"current_steps": 47770, "total_steps": 61300, "loss": 0.3251, "lr": 7.061065078717738e-06, "epoch": 7.792822185970636, "percentage": 77.93, "elapsed_time": "6:30:11", "remaining_time": "1:50:30", "throughput": 4403.78, "total_tokens": 103098496} {"current_steps": 47775, "total_steps": 61300, "loss": 0.3427, "lr": 7.056108135680123e-06, "epoch": 7.793637846655791, "percentage": 77.94, "elapsed_time": "6:30:13", "remaining_time": "1:50:28", "throughput": 4403.82, "total_tokens": 103109856} {"current_steps": 47780, "total_steps": 61300, "loss": 0.3697, "lr": 7.05115264726543e-06, "epoch": 7.794453507340946, "percentage": 77.94, "elapsed_time": "6:30:15", "remaining_time": "1:50:25", "throughput": 4403.85, "total_tokens": 103120032} {"current_steps": 47785, "total_steps": 61300, "loss": 0.3041, "lr": 7.046198613875374e-06, "epoch": 7.795269168026101, "percentage": 77.95, "elapsed_time": "6:30:18", "remaining_time": "1:50:23", "throughput": 4403.89, "total_tokens": 103131072} {"current_steps": 47790, "total_steps": 61300, "loss": 0.3702, "lr": 7.0412460359115555e-06, "epoch": 7.7960848287112565, "percentage": 77.96, "elapsed_time": "6:30:20", "remaining_time": "1:50:20", "throughput": 4403.93, "total_tokens": 103142240} {"current_steps": 47795, "total_steps": 61300, "loss": 0.3619, "lr": 7.0362949137754565e-06, "epoch": 7.796900489396411, "percentage": 77.97, "elapsed_time": "6:30:22", "remaining_time": "1:50:18", "throughput": 4403.96, "total_tokens": 103152960} {"current_steps": 47800, "total_steps": 61300, "loss": 0.3087, "lr": 7.031345247868437e-06, "epoch": 7.797716150081566, "percentage": 77.98, "elapsed_time": "6:30:25", "remaining_time": "1:50:15", "throughput": 4404.01, "total_tokens": 103164352} {"current_steps": 47805, "total_steps": 61300, "loss": 0.3154, "lr": 7.026397038591745e-06, "epoch": 7.798531810766721, "percentage": 77.99, "elapsed_time": "6:30:27", "remaining_time": "1:50:13", "throughput": 4404.04, "total_tokens": 103175680} {"current_steps": 47810, "total_steps": 61300, "loss": 0.3421, "lr": 7.021450286346503e-06, "epoch": 7.799347471451876, "percentage": 77.99, "elapsed_time": "6:30:29", "remaining_time": "1:50:10", "throughput": 4404.08, "total_tokens": 103185952} {"current_steps": 47815, "total_steps": 61300, "loss": 0.3559, "lr": 7.016504991533726e-06, "epoch": 7.800163132137031, "percentage": 78.0, "elapsed_time": "6:30:31", "remaining_time": "1:50:08", "throughput": 4404.12, "total_tokens": 103195840} {"current_steps": 47820, "total_steps": 61300, "loss": 0.3153, "lr": 7.011561154554303e-06, "epoch": 7.800978792822186, "percentage": 78.01, "elapsed_time": "6:30:34", "remaining_time": "1:50:05", "throughput": 4404.15, "total_tokens": 103207104} {"current_steps": 47825, "total_steps": 61300, "loss": 0.3139, "lr": 7.006618775809001e-06, "epoch": 7.801794453507341, "percentage": 78.02, "elapsed_time": "6:30:36", "remaining_time": "1:50:03", "throughput": 4404.19, "total_tokens": 103218624} {"current_steps": 47830, "total_steps": 61300, "loss": 0.2919, "lr": 7.001677855698482e-06, "epoch": 7.802610114192496, "percentage": 78.03, "elapsed_time": "6:30:38", "remaining_time": "1:50:00", "throughput": 4404.24, "total_tokens": 103230592} {"current_steps": 47835, "total_steps": 61300, "loss": 0.3326, "lr": 6.996738394623279e-06, "epoch": 7.803425774877651, "percentage": 78.03, "elapsed_time": "6:30:41", "remaining_time": "1:49:58", "throughput": 4404.28, "total_tokens": 103241984} {"current_steps": 47840, "total_steps": 61300, "loss": 0.3274, "lr": 6.991800392983799e-06, "epoch": 7.804241435562806, "percentage": 78.04, "elapsed_time": "6:30:43", "remaining_time": "1:49:55", "throughput": 4404.32, "total_tokens": 103252800} {"current_steps": 47845, "total_steps": 61300, "loss": 0.327, "lr": 6.9868638511803615e-06, "epoch": 7.80505709624796, "percentage": 78.05, "elapsed_time": "6:30:46", "remaining_time": "1:49:53", "throughput": 4404.36, "total_tokens": 103265440} {"current_steps": 47850, "total_steps": 61300, "loss": 0.336, "lr": 6.9819287696131355e-06, "epoch": 7.805872756933116, "percentage": 78.06, "elapsed_time": "6:30:48", "remaining_time": "1:49:50", "throughput": 4404.4, "total_tokens": 103274976} {"current_steps": 47855, "total_steps": 61300, "loss": 0.3549, "lr": 6.9769951486821885e-06, "epoch": 7.806688417618271, "percentage": 78.07, "elapsed_time": "6:30:50", "remaining_time": "1:49:48", "throughput": 4404.43, "total_tokens": 103285344} {"current_steps": 47860, "total_steps": 61300, "loss": 0.3217, "lr": 6.972062988787462e-06, "epoch": 7.807504078303426, "percentage": 78.08, "elapsed_time": "6:30:52", "remaining_time": "1:49:45", "throughput": 4404.48, "total_tokens": 103296576} {"current_steps": 47865, "total_steps": 61300, "loss": 0.3156, "lr": 6.9671322903287765e-06, "epoch": 7.808319738988581, "percentage": 78.08, "elapsed_time": "6:30:54", "remaining_time": "1:49:43", "throughput": 4404.51, "total_tokens": 103306880} {"current_steps": 47870, "total_steps": 61300, "loss": 0.3383, "lr": 6.962203053705851e-06, "epoch": 7.809135399673735, "percentage": 78.09, "elapsed_time": "6:30:57", "remaining_time": "1:49:40", "throughput": 4404.55, "total_tokens": 103317760} {"current_steps": 47875, "total_steps": 61300, "loss": 0.3285, "lr": 6.957275279318268e-06, "epoch": 7.809951060358891, "percentage": 78.1, "elapsed_time": "6:30:59", "remaining_time": "1:49:38", "throughput": 4404.59, "total_tokens": 103328096} {"current_steps": 47880, "total_steps": 61300, "loss": 0.2981, "lr": 6.9523489675655e-06, "epoch": 7.810766721044046, "percentage": 78.11, "elapsed_time": "6:31:01", "remaining_time": "1:49:35", "throughput": 4404.62, "total_tokens": 103338560} {"current_steps": 47885, "total_steps": 61300, "loss": 0.2957, "lr": 6.9474241188468985e-06, "epoch": 7.811582381729201, "percentage": 78.12, "elapsed_time": "6:31:03", "remaining_time": "1:49:33", "throughput": 4404.66, "total_tokens": 103349824} {"current_steps": 47890, "total_steps": 61300, "loss": 0.3218, "lr": 6.942500733561694e-06, "epoch": 7.8123980424143555, "percentage": 78.12, "elapsed_time": "6:31:06", "remaining_time": "1:49:30", "throughput": 4404.71, "total_tokens": 103361056} {"current_steps": 47895, "total_steps": 61300, "loss": 0.3377, "lr": 6.937578812109005e-06, "epoch": 7.81321370309951, "percentage": 78.13, "elapsed_time": "6:31:08", "remaining_time": "1:49:28", "throughput": 4404.75, "total_tokens": 103371520} {"current_steps": 47900, "total_steps": 61300, "loss": 0.3105, "lr": 6.932658354887825e-06, "epoch": 7.814029363784666, "percentage": 78.14, "elapsed_time": "6:31:10", "remaining_time": "1:49:25", "throughput": 4404.79, "total_tokens": 103382784} {"current_steps": 47905, "total_steps": 61300, "loss": 0.3281, "lr": 6.927739362297028e-06, "epoch": 7.814845024469821, "percentage": 78.15, "elapsed_time": "6:31:12", "remaining_time": "1:49:23", "throughput": 4404.83, "total_tokens": 103393376} {"current_steps": 47910, "total_steps": 61300, "loss": 0.335, "lr": 6.92282183473538e-06, "epoch": 7.815660685154976, "percentage": 78.16, "elapsed_time": "6:31:14", "remaining_time": "1:49:20", "throughput": 4404.87, "total_tokens": 103404000} {"current_steps": 47915, "total_steps": 61300, "loss": 0.3047, "lr": 6.917905772601516e-06, "epoch": 7.8164763458401305, "percentage": 78.16, "elapsed_time": "6:31:17", "remaining_time": "1:49:18", "throughput": 4404.9, "total_tokens": 103414848} {"current_steps": 47920, "total_steps": 61300, "loss": 0.3633, "lr": 6.912991176293957e-06, "epoch": 7.817292006525285, "percentage": 78.17, "elapsed_time": "6:31:19", "remaining_time": "1:49:15", "throughput": 4404.95, "total_tokens": 103426144} {"current_steps": 47925, "total_steps": 61300, "loss": 0.3255, "lr": 6.908078046211105e-06, "epoch": 7.81810766721044, "percentage": 78.18, "elapsed_time": "6:31:21", "remaining_time": "1:49:13", "throughput": 4404.98, "total_tokens": 103435584} {"current_steps": 47930, "total_steps": 61300, "loss": 0.3915, "lr": 6.903166382751244e-06, "epoch": 7.818923327895595, "percentage": 78.19, "elapsed_time": "6:31:23", "remaining_time": "1:49:10", "throughput": 4405.02, "total_tokens": 103446464} {"current_steps": 47935, "total_steps": 61300, "loss": 0.3397, "lr": 6.8982561863125405e-06, "epoch": 7.819738988580751, "percentage": 78.2, "elapsed_time": "6:31:26", "remaining_time": "1:49:08", "throughput": 4405.06, "total_tokens": 103457248} {"current_steps": 47940, "total_steps": 61300, "loss": 0.3321, "lr": 6.893347457293036e-06, "epoch": 7.8205546492659055, "percentage": 78.21, "elapsed_time": "6:31:28", "remaining_time": "1:49:05", "throughput": 4405.09, "total_tokens": 103468128} {"current_steps": 47945, "total_steps": 61300, "loss": 0.3774, "lr": 6.888440196090659e-06, "epoch": 7.82137030995106, "percentage": 78.21, "elapsed_time": "6:31:30", "remaining_time": "1:49:03", "throughput": 4405.13, "total_tokens": 103478656} {"current_steps": 47950, "total_steps": 61300, "loss": 0.3238, "lr": 6.8835344031032175e-06, "epoch": 7.822185970636215, "percentage": 78.22, "elapsed_time": "6:31:32", "remaining_time": "1:49:00", "throughput": 4405.16, "total_tokens": 103489472} {"current_steps": 47955, "total_steps": 61300, "loss": 0.3704, "lr": 6.878630078728399e-06, "epoch": 7.82300163132137, "percentage": 78.23, "elapsed_time": "6:31:35", "remaining_time": "1:48:58", "throughput": 4405.2, "total_tokens": 103500384} {"current_steps": 47960, "total_steps": 61300, "loss": 0.3686, "lr": 6.873727223363766e-06, "epoch": 7.823817292006526, "percentage": 78.24, "elapsed_time": "6:31:37", "remaining_time": "1:48:55", "throughput": 4405.23, "total_tokens": 103510432} {"current_steps": 47965, "total_steps": 61300, "loss": 0.3025, "lr": 6.868825837406784e-06, "epoch": 7.8246329526916805, "percentage": 78.25, "elapsed_time": "6:31:39", "remaining_time": "1:48:53", "throughput": 4405.27, "total_tokens": 103520544} {"current_steps": 47970, "total_steps": 61300, "loss": 0.3324, "lr": 6.8639259212547764e-06, "epoch": 7.825448613376835, "percentage": 78.25, "elapsed_time": "6:31:41", "remaining_time": "1:48:50", "throughput": 4405.31, "total_tokens": 103531264} {"current_steps": 47975, "total_steps": 61300, "loss": 0.3304, "lr": 6.859027475304955e-06, "epoch": 7.82626427406199, "percentage": 78.26, "elapsed_time": "6:31:43", "remaining_time": "1:48:48", "throughput": 4405.35, "total_tokens": 103542176} {"current_steps": 47980, "total_steps": 61300, "loss": 0.3494, "lr": 6.854130499954411e-06, "epoch": 7.827079934747145, "percentage": 78.27, "elapsed_time": "6:31:45", "remaining_time": "1:48:45", "throughput": 4405.38, "total_tokens": 103552608} {"current_steps": 47985, "total_steps": 61300, "loss": 0.3383, "lr": 6.849234995600121e-06, "epoch": 7.827895595432301, "percentage": 78.28, "elapsed_time": "6:31:48", "remaining_time": "1:48:43", "throughput": 4405.41, "total_tokens": 103563552} {"current_steps": 47990, "total_steps": 61300, "loss": 0.3339, "lr": 6.84434096263894e-06, "epoch": 7.828711256117455, "percentage": 78.29, "elapsed_time": "6:31:50", "remaining_time": "1:48:40", "throughput": 4405.46, "total_tokens": 103575296} {"current_steps": 47995, "total_steps": 61300, "loss": 0.3325, "lr": 6.839448401467599e-06, "epoch": 7.82952691680261, "percentage": 78.3, "elapsed_time": "6:31:52", "remaining_time": "1:48:38", "throughput": 4405.49, "total_tokens": 103586304} {"current_steps": 48000, "total_steps": 61300, "loss": 0.3738, "lr": 6.834557312482717e-06, "epoch": 7.830342577487765, "percentage": 78.3, "elapsed_time": "6:31:55", "remaining_time": "1:48:35", "throughput": 4405.54, "total_tokens": 103596768} {"current_steps": 48005, "total_steps": 61300, "loss": 0.3206, "lr": 6.8296676960807906e-06, "epoch": 7.83115823817292, "percentage": 78.31, "elapsed_time": "6:31:57", "remaining_time": "1:48:33", "throughput": 4405.58, "total_tokens": 103607808} {"current_steps": 48010, "total_steps": 61300, "loss": 0.3369, "lr": 6.824779552658189e-06, "epoch": 7.831973898858075, "percentage": 78.32, "elapsed_time": "6:31:59", "remaining_time": "1:48:30", "throughput": 4405.62, "total_tokens": 103618848} {"current_steps": 48015, "total_steps": 61300, "loss": 0.3226, "lr": 6.819892882611184e-06, "epoch": 7.8327895595432295, "percentage": 78.33, "elapsed_time": "6:32:01", "remaining_time": "1:48:28", "throughput": 4405.66, "total_tokens": 103629600} {"current_steps": 48020, "total_steps": 61300, "loss": 0.3289, "lr": 6.8150076863359054e-06, "epoch": 7.833605220228385, "percentage": 78.34, "elapsed_time": "6:32:04", "remaining_time": "1:48:25", "throughput": 4405.69, "total_tokens": 103639744} {"current_steps": 48025, "total_steps": 61300, "loss": 0.3641, "lr": 6.810123964228374e-06, "epoch": 7.83442088091354, "percentage": 78.34, "elapsed_time": "6:32:06", "remaining_time": "1:48:23", "throughput": 4405.73, "total_tokens": 103649472} {"current_steps": 48030, "total_steps": 61300, "loss": 0.3221, "lr": 6.8052417166844905e-06, "epoch": 7.835236541598695, "percentage": 78.35, "elapsed_time": "6:32:08", "remaining_time": "1:48:20", "throughput": 4405.76, "total_tokens": 103659968} {"current_steps": 48035, "total_steps": 61300, "loss": 0.3212, "lr": 6.800360944100031e-06, "epoch": 7.83605220228385, "percentage": 78.36, "elapsed_time": "6:32:10", "remaining_time": "1:48:18", "throughput": 4405.79, "total_tokens": 103671584} {"current_steps": 48040, "total_steps": 61300, "loss": 0.3428, "lr": 6.795481646870658e-06, "epoch": 7.8368678629690045, "percentage": 78.37, "elapsed_time": "6:32:12", "remaining_time": "1:48:15", "throughput": 4405.83, "total_tokens": 103681984} {"current_steps": 48045, "total_steps": 61300, "loss": 0.3455, "lr": 6.790603825391912e-06, "epoch": 7.83768352365416, "percentage": 78.38, "elapsed_time": "6:32:15", "remaining_time": "1:48:13", "throughput": 4405.86, "total_tokens": 103692544} {"current_steps": 48050, "total_steps": 61300, "loss": 0.2909, "lr": 6.785727480059212e-06, "epoch": 7.838499184339315, "percentage": 78.38, "elapsed_time": "6:32:17", "remaining_time": "1:48:10", "throughput": 4405.9, "total_tokens": 103703488} {"current_steps": 48055, "total_steps": 61300, "loss": 0.3468, "lr": 6.78085261126786e-06, "epoch": 7.83931484502447, "percentage": 78.39, "elapsed_time": "6:32:19", "remaining_time": "1:48:08", "throughput": 4405.96, "total_tokens": 103714464} {"current_steps": 48060, "total_steps": 61300, "loss": 0.3292, "lr": 6.775979219413042e-06, "epoch": 7.840130505709625, "percentage": 78.4, "elapsed_time": "6:32:21", "remaining_time": "1:48:05", "throughput": 4405.99, "total_tokens": 103725184} {"current_steps": 48065, "total_steps": 61300, "loss": 0.3196, "lr": 6.771107304889807e-06, "epoch": 7.8409461663947795, "percentage": 78.41, "elapsed_time": "6:32:23", "remaining_time": "1:48:02", "throughput": 4406.03, "total_tokens": 103735520} {"current_steps": 48070, "total_steps": 61300, "loss": 0.3653, "lr": 6.766236868093112e-06, "epoch": 7.841761827079935, "percentage": 78.42, "elapsed_time": "6:32:26", "remaining_time": "1:48:00", "throughput": 4406.08, "total_tokens": 103747072} {"current_steps": 48075, "total_steps": 61300, "loss": 0.335, "lr": 6.761367909417776e-06, "epoch": 7.84257748776509, "percentage": 78.43, "elapsed_time": "6:32:28", "remaining_time": "1:47:57", "throughput": 4406.12, "total_tokens": 103757632} {"current_steps": 48080, "total_steps": 61300, "loss": 0.3114, "lr": 6.756500429258497e-06, "epoch": 7.843393148450245, "percentage": 78.43, "elapsed_time": "6:32:30", "remaining_time": "1:47:55", "throughput": 4406.16, "total_tokens": 103768576} {"current_steps": 48085, "total_steps": 61300, "loss": 0.3163, "lr": 6.751634428009862e-06, "epoch": 7.8442088091354, "percentage": 78.44, "elapsed_time": "6:32:33", "remaining_time": "1:47:53", "throughput": 4406.2, "total_tokens": 103779840} {"current_steps": 48090, "total_steps": 61300, "loss": 0.3573, "lr": 6.7467699060663305e-06, "epoch": 7.8450244698205545, "percentage": 78.45, "elapsed_time": "6:32:35", "remaining_time": "1:47:50", "throughput": 4406.23, "total_tokens": 103789664} {"current_steps": 48095, "total_steps": 61300, "loss": 0.3433, "lr": 6.741906863822248e-06, "epoch": 7.845840130505709, "percentage": 78.46, "elapsed_time": "6:32:37", "remaining_time": "1:47:47", "throughput": 4406.27, "total_tokens": 103800832} {"current_steps": 48100, "total_steps": 61300, "loss": 0.3811, "lr": 6.737045301671832e-06, "epoch": 7.846655791190865, "percentage": 78.47, "elapsed_time": "6:32:39", "remaining_time": "1:47:45", "throughput": 4406.31, "total_tokens": 103811616} {"current_steps": 48105, "total_steps": 61300, "loss": 0.3367, "lr": 6.7321852200091935e-06, "epoch": 7.84747145187602, "percentage": 78.47, "elapsed_time": "6:32:42", "remaining_time": "1:47:42", "throughput": 4406.34, "total_tokens": 103822464} {"current_steps": 48110, "total_steps": 61300, "loss": 0.3569, "lr": 6.727326619228308e-06, "epoch": 7.848287112561175, "percentage": 78.48, "elapsed_time": "6:32:44", "remaining_time": "1:47:40", "throughput": 4406.38, "total_tokens": 103833984} {"current_steps": 48115, "total_steps": 61300, "loss": 0.3065, "lr": 6.722469499723042e-06, "epoch": 7.849102773246329, "percentage": 78.49, "elapsed_time": "6:32:46", "remaining_time": "1:47:38", "throughput": 4406.43, "total_tokens": 103845664} {"current_steps": 48120, "total_steps": 61300, "loss": 0.3365, "lr": 6.717613861887137e-06, "epoch": 7.849918433931484, "percentage": 78.5, "elapsed_time": "6:32:48", "remaining_time": "1:47:35", "throughput": 4406.47, "total_tokens": 103855936} {"current_steps": 48125, "total_steps": 61300, "loss": 0.3256, "lr": 6.712759706114219e-06, "epoch": 7.850734094616639, "percentage": 78.51, "elapsed_time": "6:32:51", "remaining_time": "1:47:32", "throughput": 4406.51, "total_tokens": 103866304} {"current_steps": 48130, "total_steps": 61300, "loss": 0.3252, "lr": 6.707907032797786e-06, "epoch": 7.851549755301795, "percentage": 78.52, "elapsed_time": "6:32:53", "remaining_time": "1:47:30", "throughput": 4406.54, "total_tokens": 103877280} {"current_steps": 48135, "total_steps": 61300, "loss": 0.3256, "lr": 6.703055842331221e-06, "epoch": 7.85236541598695, "percentage": 78.52, "elapsed_time": "6:32:55", "remaining_time": "1:47:27", "throughput": 4406.58, "total_tokens": 103888192} {"current_steps": 48140, "total_steps": 61300, "loss": 0.3332, "lr": 6.698206135107787e-06, "epoch": 7.853181076672104, "percentage": 78.53, "elapsed_time": "6:32:57", "remaining_time": "1:47:25", "throughput": 4406.62, "total_tokens": 103897568} {"current_steps": 48145, "total_steps": 61300, "loss": 0.3123, "lr": 6.6933579115206284e-06, "epoch": 7.853996737357259, "percentage": 78.54, "elapsed_time": "6:32:59", "remaining_time": "1:47:22", "throughput": 4406.65, "total_tokens": 103908448} {"current_steps": 48150, "total_steps": 61300, "loss": 0.3372, "lr": 6.6885111719627635e-06, "epoch": 7.854812398042414, "percentage": 78.55, "elapsed_time": "6:33:01", "remaining_time": "1:47:20", "throughput": 4406.68, "total_tokens": 103917856} {"current_steps": 48155, "total_steps": 61300, "loss": 0.3385, "lr": 6.683665916827087e-06, "epoch": 7.85562805872757, "percentage": 78.56, "elapsed_time": "6:33:04", "remaining_time": "1:47:17", "throughput": 4406.72, "total_tokens": 103929792} {"current_steps": 48160, "total_steps": 61300, "loss": 0.3423, "lr": 6.678822146506394e-06, "epoch": 7.856443719412725, "percentage": 78.56, "elapsed_time": "6:33:06", "remaining_time": "1:47:15", "throughput": 4406.75, "total_tokens": 103939488} {"current_steps": 48165, "total_steps": 61300, "loss": 0.3417, "lr": 6.67397986139334e-06, "epoch": 7.857259380097879, "percentage": 78.57, "elapsed_time": "6:33:08", "remaining_time": "1:47:12", "throughput": 4406.79, "total_tokens": 103949600} {"current_steps": 48170, "total_steps": 61300, "loss": 0.3504, "lr": 6.669139061880464e-06, "epoch": 7.858075040783034, "percentage": 78.58, "elapsed_time": "6:33:10", "remaining_time": "1:47:10", "throughput": 4406.83, "total_tokens": 103959936} {"current_steps": 48175, "total_steps": 61300, "loss": 0.3155, "lr": 6.664299748360184e-06, "epoch": 7.858890701468189, "percentage": 78.59, "elapsed_time": "6:33:12", "remaining_time": "1:47:07", "throughput": 4406.87, "total_tokens": 103971136} {"current_steps": 48180, "total_steps": 61300, "loss": 0.3567, "lr": 6.659461921224794e-06, "epoch": 7.859706362153344, "percentage": 78.6, "elapsed_time": "6:33:15", "remaining_time": "1:47:05", "throughput": 4406.9, "total_tokens": 103981760} {"current_steps": 48185, "total_steps": 61300, "loss": 0.3237, "lr": 6.654625580866486e-06, "epoch": 7.8605220228384995, "percentage": 78.61, "elapsed_time": "6:33:17", "remaining_time": "1:47:02", "throughput": 4406.94, "total_tokens": 103992480} {"current_steps": 48190, "total_steps": 61300, "loss": 0.3463, "lr": 6.649790727677313e-06, "epoch": 7.861337683523654, "percentage": 78.61, "elapsed_time": "6:33:19", "remaining_time": "1:47:00", "throughput": 4406.98, "total_tokens": 104002720} {"current_steps": 48195, "total_steps": 61300, "loss": 0.3313, "lr": 6.644957362049212e-06, "epoch": 7.862153344208809, "percentage": 78.62, "elapsed_time": "6:33:21", "remaining_time": "1:46:57", "throughput": 4407.01, "total_tokens": 104011968} {"current_steps": 48200, "total_steps": 61300, "loss": 0.3731, "lr": 6.640125484373999e-06, "epoch": 7.862969004893964, "percentage": 78.63, "elapsed_time": "6:33:23", "remaining_time": "1:46:55", "throughput": 4407.06, "total_tokens": 104023328} {"current_steps": 48205, "total_steps": 61300, "loss": 0.3287, "lr": 6.635295095043373e-06, "epoch": 7.863784665579119, "percentage": 78.64, "elapsed_time": "6:33:25", "remaining_time": "1:46:52", "throughput": 4407.1, "total_tokens": 104032896} {"current_steps": 48210, "total_steps": 61300, "loss": 0.3424, "lr": 6.630466194448906e-06, "epoch": 7.864600326264274, "percentage": 78.65, "elapsed_time": "6:33:28", "remaining_time": "1:46:50", "throughput": 4407.14, "total_tokens": 104044128} {"current_steps": 48215, "total_steps": 61300, "loss": 0.3428, "lr": 6.625638782982058e-06, "epoch": 7.865415986949429, "percentage": 78.65, "elapsed_time": "6:33:30", "remaining_time": "1:46:47", "throughput": 4407.19, "total_tokens": 104055808} {"current_steps": 48220, "total_steps": 61300, "loss": 0.32, "lr": 6.620812861034159e-06, "epoch": 7.866231647634584, "percentage": 78.66, "elapsed_time": "6:33:32", "remaining_time": "1:46:45", "throughput": 4407.23, "total_tokens": 104066816} {"current_steps": 48225, "total_steps": 61300, "loss": 0.3374, "lr": 6.615988428996426e-06, "epoch": 7.867047308319739, "percentage": 78.67, "elapsed_time": "6:33:35", "remaining_time": "1:46:42", "throughput": 4407.27, "total_tokens": 104078624} {"current_steps": 48230, "total_steps": 61300, "loss": 0.3464, "lr": 6.611165487259946e-06, "epoch": 7.867862969004894, "percentage": 78.68, "elapsed_time": "6:33:37", "remaining_time": "1:46:40", "throughput": 4407.31, "total_tokens": 104090592} {"current_steps": 48235, "total_steps": 61300, "loss": 0.3305, "lr": 6.6063440362157e-06, "epoch": 7.868678629690049, "percentage": 78.69, "elapsed_time": "6:33:39", "remaining_time": "1:46:37", "throughput": 4407.36, "total_tokens": 104101376} {"current_steps": 48240, "total_steps": 61300, "loss": 0.347, "lr": 6.601524076254534e-06, "epoch": 7.869494290375204, "percentage": 78.69, "elapsed_time": "6:33:42", "remaining_time": "1:46:35", "throughput": 4407.4, "total_tokens": 104111968} {"current_steps": 48245, "total_steps": 61300, "loss": 0.3272, "lr": 6.5967056077671785e-06, "epoch": 7.870309951060359, "percentage": 78.7, "elapsed_time": "6:33:44", "remaining_time": "1:46:32", "throughput": 4407.44, "total_tokens": 104123616} {"current_steps": 48250, "total_steps": 61300, "loss": 0.3279, "lr": 6.591888631144244e-06, "epoch": 7.871125611745514, "percentage": 78.71, "elapsed_time": "6:33:46", "remaining_time": "1:46:30", "throughput": 4407.47, "total_tokens": 104134176} {"current_steps": 48255, "total_steps": 61300, "loss": 0.3278, "lr": 6.587073146776221e-06, "epoch": 7.871941272430669, "percentage": 78.72, "elapsed_time": "6:33:48", "remaining_time": "1:46:27", "throughput": 4407.51, "total_tokens": 104144704} {"current_steps": 48260, "total_steps": 61300, "loss": 0.3753, "lr": 6.582259155053472e-06, "epoch": 7.872756933115824, "percentage": 78.73, "elapsed_time": "6:33:51", "remaining_time": "1:46:25", "throughput": 4407.55, "total_tokens": 104155648} {"current_steps": 48265, "total_steps": 61300, "loss": 0.3144, "lr": 6.577446656366248e-06, "epoch": 7.873572593800979, "percentage": 78.74, "elapsed_time": "6:33:53", "remaining_time": "1:46:22", "throughput": 4407.59, "total_tokens": 104166080} {"current_steps": 48270, "total_steps": 61300, "loss": 0.3583, "lr": 6.572635651104672e-06, "epoch": 7.874388254486134, "percentage": 78.74, "elapsed_time": "6:33:55", "remaining_time": "1:46:20", "throughput": 4407.63, "total_tokens": 104177152} {"current_steps": 48275, "total_steps": 61300, "loss": 0.3387, "lr": 6.56782613965875e-06, "epoch": 7.875203915171289, "percentage": 78.75, "elapsed_time": "6:33:57", "remaining_time": "1:46:17", "throughput": 4407.66, "total_tokens": 104187104} {"current_steps": 48280, "total_steps": 61300, "loss": 0.3256, "lr": 6.56301812241836e-06, "epoch": 7.876019575856444, "percentage": 78.76, "elapsed_time": "6:34:00", "remaining_time": "1:46:15", "throughput": 4407.71, "total_tokens": 104198176} {"current_steps": 48285, "total_steps": 61300, "loss": 0.3748, "lr": 6.558211599773273e-06, "epoch": 7.876835236541599, "percentage": 78.77, "elapsed_time": "6:34:02", "remaining_time": "1:46:12", "throughput": 4407.74, "total_tokens": 104208896} {"current_steps": 48290, "total_steps": 61300, "loss": 0.3386, "lr": 6.55340657211313e-06, "epoch": 7.877650897226753, "percentage": 78.78, "elapsed_time": "6:34:04", "remaining_time": "1:46:10", "throughput": 4407.78, "total_tokens": 104220512} {"current_steps": 48295, "total_steps": 61300, "loss": 0.3346, "lr": 6.5486030398274444e-06, "epoch": 7.878466557911908, "percentage": 78.78, "elapsed_time": "6:34:06", "remaining_time": "1:46:07", "throughput": 4407.81, "total_tokens": 104230816} {"current_steps": 48300, "total_steps": 61300, "loss": 0.3668, "lr": 6.543801003305619e-06, "epoch": 7.879282218597064, "percentage": 78.79, "elapsed_time": "6:34:09", "remaining_time": "1:46:05", "throughput": 4407.86, "total_tokens": 104242240} {"current_steps": 48305, "total_steps": 61300, "loss": 0.3447, "lr": 6.539000462936931e-06, "epoch": 7.880097879282219, "percentage": 78.8, "elapsed_time": "6:34:11", "remaining_time": "1:46:02", "throughput": 4407.9, "total_tokens": 104253376} {"current_steps": 48310, "total_steps": 61300, "loss": 0.3083, "lr": 6.534201419110536e-06, "epoch": 7.8809135399673735, "percentage": 78.81, "elapsed_time": "6:34:13", "remaining_time": "1:46:00", "throughput": 4407.94, "total_tokens": 104264864} {"current_steps": 48315, "total_steps": 61300, "loss": 0.3143, "lr": 6.529403872215467e-06, "epoch": 7.881729200652528, "percentage": 78.82, "elapsed_time": "6:34:16", "remaining_time": "1:45:57", "throughput": 4407.98, "total_tokens": 104275712} {"current_steps": 48320, "total_steps": 61300, "loss": 0.346, "lr": 6.524607822640638e-06, "epoch": 7.882544861337683, "percentage": 78.83, "elapsed_time": "6:34:18", "remaining_time": "1:45:55", "throughput": 4408.02, "total_tokens": 104287328} {"current_steps": 48325, "total_steps": 61300, "loss": 0.3191, "lr": 6.519813270774835e-06, "epoch": 7.883360522022839, "percentage": 78.83, "elapsed_time": "6:34:20", "remaining_time": "1:45:52", "throughput": 4408.06, "total_tokens": 104297344} {"current_steps": 48330, "total_steps": 61300, "loss": 0.3429, "lr": 6.515020217006745e-06, "epoch": 7.884176182707994, "percentage": 78.84, "elapsed_time": "6:34:23", "remaining_time": "1:45:50", "throughput": 4408.1, "total_tokens": 104308992} {"current_steps": 48335, "total_steps": 61300, "loss": 0.3182, "lr": 6.510228661724907e-06, "epoch": 7.8849918433931485, "percentage": 78.85, "elapsed_time": "6:34:25", "remaining_time": "1:45:47", "throughput": 4408.13, "total_tokens": 104319616} {"current_steps": 48340, "total_steps": 61300, "loss": 0.3281, "lr": 6.5054386053177515e-06, "epoch": 7.885807504078303, "percentage": 78.86, "elapsed_time": "6:34:27", "remaining_time": "1:45:45", "throughput": 4408.17, "total_tokens": 104331520} {"current_steps": 48345, "total_steps": 61300, "loss": 0.3272, "lr": 6.500650048173582e-06, "epoch": 7.886623164763458, "percentage": 78.87, "elapsed_time": "6:34:29", "remaining_time": "1:45:42", "throughput": 4408.21, "total_tokens": 104341664} {"current_steps": 48350, "total_steps": 61300, "loss": 0.3577, "lr": 6.495862990680585e-06, "epoch": 7.887438825448614, "percentage": 78.87, "elapsed_time": "6:34:32", "remaining_time": "1:45:40", "throughput": 4408.25, "total_tokens": 104352640} {"current_steps": 48355, "total_steps": 61300, "loss": 0.3349, "lr": 6.4910774332268195e-06, "epoch": 7.888254486133769, "percentage": 78.88, "elapsed_time": "6:34:34", "remaining_time": "1:45:37", "throughput": 4408.29, "total_tokens": 104362496} {"current_steps": 48360, "total_steps": 61300, "loss": 0.3394, "lr": 6.486293376200234e-06, "epoch": 7.8890701468189235, "percentage": 78.89, "elapsed_time": "6:34:36", "remaining_time": "1:45:35", "throughput": 4408.32, "total_tokens": 104372192} {"current_steps": 48365, "total_steps": 61300, "loss": 0.3274, "lr": 6.481510819988645e-06, "epoch": 7.889885807504078, "percentage": 78.9, "elapsed_time": "6:34:38", "remaining_time": "1:45:32", "throughput": 4408.35, "total_tokens": 104383168} {"current_steps": 48370, "total_steps": 61300, "loss": 0.3306, "lr": 6.47672976497975e-06, "epoch": 7.890701468189233, "percentage": 78.91, "elapsed_time": "6:34:40", "remaining_time": "1:45:30", "throughput": 4408.39, "total_tokens": 104393632} {"current_steps": 48375, "total_steps": 61300, "loss": 0.3257, "lr": 6.471950211561125e-06, "epoch": 7.891517128874388, "percentage": 78.92, "elapsed_time": "6:34:42", "remaining_time": "1:45:27", "throughput": 4408.42, "total_tokens": 104404096} {"current_steps": 48380, "total_steps": 61300, "loss": 0.3268, "lr": 6.46717216012023e-06, "epoch": 7.892332789559543, "percentage": 78.92, "elapsed_time": "6:34:45", "remaining_time": "1:45:25", "throughput": 4408.46, "total_tokens": 104414592} {"current_steps": 48385, "total_steps": 61300, "loss": 0.3406, "lr": 6.462395611044383e-06, "epoch": 7.8931484502446985, "percentage": 78.93, "elapsed_time": "6:34:47", "remaining_time": "1:45:22", "throughput": 4408.5, "total_tokens": 104424736} {"current_steps": 48390, "total_steps": 61300, "loss": 0.326, "lr": 6.457620564720815e-06, "epoch": 7.893964110929853, "percentage": 78.94, "elapsed_time": "6:34:49", "remaining_time": "1:45:20", "throughput": 4408.54, "total_tokens": 104434976} {"current_steps": 48395, "total_steps": 61300, "loss": 0.3279, "lr": 6.452847021536609e-06, "epoch": 7.894779771615008, "percentage": 78.95, "elapsed_time": "6:34:51", "remaining_time": "1:45:17", "throughput": 4408.57, "total_tokens": 104445920} {"current_steps": 48400, "total_steps": 61300, "loss": 0.3186, "lr": 6.44807498187873e-06, "epoch": 7.895595432300163, "percentage": 78.96, "elapsed_time": "6:34:53", "remaining_time": "1:45:15", "throughput": 4408.6, "total_tokens": 104455584} {"current_steps": 48405, "total_steps": 61300, "loss": 0.3381, "lr": 6.443304446134024e-06, "epoch": 7.896411092985318, "percentage": 78.96, "elapsed_time": "6:34:55", "remaining_time": "1:45:12", "throughput": 4408.64, "total_tokens": 104466304} {"current_steps": 48410, "total_steps": 61300, "loss": 0.3172, "lr": 6.438535414689215e-06, "epoch": 7.897226753670473, "percentage": 78.97, "elapsed_time": "6:34:57", "remaining_time": "1:45:09", "throughput": 4408.68, "total_tokens": 104476096} {"current_steps": 48415, "total_steps": 61300, "loss": 0.3221, "lr": 6.4337678879309055e-06, "epoch": 7.898042414355628, "percentage": 78.98, "elapsed_time": "6:35:00", "remaining_time": "1:45:07", "throughput": 4408.71, "total_tokens": 104486656} {"current_steps": 48420, "total_steps": 61300, "loss": 0.3209, "lr": 6.4290018662455764e-06, "epoch": 7.898858075040783, "percentage": 78.99, "elapsed_time": "6:35:02", "remaining_time": "1:45:04", "throughput": 4408.76, "total_tokens": 104497600} {"current_steps": 48425, "total_steps": 61300, "loss": 0.3377, "lr": 6.424237350019582e-06, "epoch": 7.899673735725938, "percentage": 79.0, "elapsed_time": "6:35:04", "remaining_time": "1:45:02", "throughput": 4408.8, "total_tokens": 104508384} {"current_steps": 48430, "total_steps": 61300, "loss": 0.3342, "lr": 6.419474339639161e-06, "epoch": 7.900489396411093, "percentage": 79.0, "elapsed_time": "6:35:06", "remaining_time": "1:44:59", "throughput": 4408.84, "total_tokens": 104519136} {"current_steps": 48435, "total_steps": 61300, "loss": 0.3545, "lr": 6.414712835490428e-06, "epoch": 7.901305057096248, "percentage": 79.01, "elapsed_time": "6:35:08", "remaining_time": "1:44:57", "throughput": 4408.87, "total_tokens": 104529728} {"current_steps": 48440, "total_steps": 61300, "loss": 0.3226, "lr": 6.409952837959374e-06, "epoch": 7.902120717781403, "percentage": 79.02, "elapsed_time": "6:35:11", "remaining_time": "1:44:54", "throughput": 4408.93, "total_tokens": 104541888} {"current_steps": 48445, "total_steps": 61300, "loss": 0.3214, "lr": 6.405194347431864e-06, "epoch": 7.902936378466558, "percentage": 79.03, "elapsed_time": "6:35:13", "remaining_time": "1:44:52", "throughput": 4408.97, "total_tokens": 104552736} {"current_steps": 48450, "total_steps": 61300, "loss": 0.3242, "lr": 6.400437364293655e-06, "epoch": 7.903752039151713, "percentage": 79.04, "elapsed_time": "6:35:15", "remaining_time": "1:44:49", "throughput": 4409.01, "total_tokens": 104562464} {"current_steps": 48455, "total_steps": 61300, "loss": 0.3072, "lr": 6.395681888930361e-06, "epoch": 7.904567699836868, "percentage": 79.05, "elapsed_time": "6:35:17", "remaining_time": "1:44:47", "throughput": 4409.05, "total_tokens": 104573600} {"current_steps": 48460, "total_steps": 61300, "loss": 0.306, "lr": 6.390927921727494e-06, "epoch": 7.9053833605220225, "percentage": 79.05, "elapsed_time": "6:35:20", "remaining_time": "1:44:44", "throughput": 4409.09, "total_tokens": 104584800} {"current_steps": 48465, "total_steps": 61300, "loss": 0.3335, "lr": 6.386175463070429e-06, "epoch": 7.906199021207177, "percentage": 79.06, "elapsed_time": "6:35:22", "remaining_time": "1:44:42", "throughput": 4409.14, "total_tokens": 104596192} {"current_steps": 48470, "total_steps": 61300, "loss": 0.3185, "lr": 6.3814245133444196e-06, "epoch": 7.907014681892333, "percentage": 79.07, "elapsed_time": "6:35:24", "remaining_time": "1:44:39", "throughput": 4409.18, "total_tokens": 104606976} {"current_steps": 48475, "total_steps": 61300, "loss": 0.3264, "lr": 6.376675072934618e-06, "epoch": 7.907830342577488, "percentage": 79.08, "elapsed_time": "6:35:27", "remaining_time": "1:44:37", "throughput": 4409.22, "total_tokens": 104618304} {"current_steps": 48480, "total_steps": 61300, "loss": 0.3393, "lr": 6.371927142226028e-06, "epoch": 7.908646003262643, "percentage": 79.09, "elapsed_time": "6:35:29", "remaining_time": "1:44:34", "throughput": 4409.25, "total_tokens": 104627840} {"current_steps": 48485, "total_steps": 61300, "loss": 0.3248, "lr": 6.367180721603541e-06, "epoch": 7.9094616639477975, "percentage": 79.09, "elapsed_time": "6:35:31", "remaining_time": "1:44:32", "throughput": 4409.29, "total_tokens": 104639296} {"current_steps": 48490, "total_steps": 61300, "loss": 0.3385, "lr": 6.3624358114519275e-06, "epoch": 7.910277324632952, "percentage": 79.1, "elapsed_time": "6:35:33", "remaining_time": "1:44:29", "throughput": 4409.32, "total_tokens": 104648992} {"current_steps": 48495, "total_steps": 61300, "loss": 0.3543, "lr": 6.3576924121558246e-06, "epoch": 7.911092985318108, "percentage": 79.11, "elapsed_time": "6:35:35", "remaining_time": "1:44:27", "throughput": 4409.36, "total_tokens": 104659680} {"current_steps": 48500, "total_steps": 61300, "loss": 0.3198, "lr": 6.352950524099774e-06, "epoch": 7.911908646003263, "percentage": 79.12, "elapsed_time": "6:35:38", "remaining_time": "1:44:24", "throughput": 4409.4, "total_tokens": 104670688} {"current_steps": 48505, "total_steps": 61300, "loss": 0.293, "lr": 6.348210147668165e-06, "epoch": 7.912724306688418, "percentage": 79.13, "elapsed_time": "6:35:40", "remaining_time": "1:44:22", "throughput": 4409.45, "total_tokens": 104681600} {"current_steps": 48510, "total_steps": 61300, "loss": 0.3438, "lr": 6.343471283245283e-06, "epoch": 7.9135399673735725, "percentage": 79.14, "elapsed_time": "6:35:42", "remaining_time": "1:44:19", "throughput": 4409.49, "total_tokens": 104692672} {"current_steps": 48515, "total_steps": 61300, "loss": 0.3074, "lr": 6.33873393121528e-06, "epoch": 7.914355628058727, "percentage": 79.14, "elapsed_time": "6:35:44", "remaining_time": "1:44:17", "throughput": 4409.52, "total_tokens": 104703296} {"current_steps": 48520, "total_steps": 61300, "loss": 0.3028, "lr": 6.33399809196219e-06, "epoch": 7.915171288743883, "percentage": 79.15, "elapsed_time": "6:35:47", "remaining_time": "1:44:14", "throughput": 4409.57, "total_tokens": 104715648} {"current_steps": 48525, "total_steps": 61300, "loss": 0.331, "lr": 6.329263765869925e-06, "epoch": 7.915986949429038, "percentage": 79.16, "elapsed_time": "6:35:49", "remaining_time": "1:44:12", "throughput": 4409.61, "total_tokens": 104724864} {"current_steps": 48530, "total_steps": 61300, "loss": 0.3362, "lr": 6.324530953322275e-06, "epoch": 7.916802610114193, "percentage": 79.17, "elapsed_time": "6:35:51", "remaining_time": "1:44:09", "throughput": 4409.64, "total_tokens": 104734592} {"current_steps": 48535, "total_steps": 61300, "loss": 0.303, "lr": 6.319799654702904e-06, "epoch": 7.917618270799347, "percentage": 79.18, "elapsed_time": "6:35:53", "remaining_time": "1:44:07", "throughput": 4409.67, "total_tokens": 104744992} {"current_steps": 48540, "total_steps": 61300, "loss": 0.3397, "lr": 6.315069870395354e-06, "epoch": 7.918433931484502, "percentage": 79.18, "elapsed_time": "6:35:55", "remaining_time": "1:44:04", "throughput": 4409.72, "total_tokens": 104756512} {"current_steps": 48545, "total_steps": 61300, "loss": 0.3406, "lr": 6.310341600783049e-06, "epoch": 7.919249592169657, "percentage": 79.19, "elapsed_time": "6:35:58", "remaining_time": "1:44:02", "throughput": 4409.76, "total_tokens": 104767840} {"current_steps": 48550, "total_steps": 61300, "loss": 0.3723, "lr": 6.305614846249283e-06, "epoch": 7.920065252854813, "percentage": 79.2, "elapsed_time": "6:36:00", "remaining_time": "1:43:59", "throughput": 4409.8, "total_tokens": 104778944} {"current_steps": 48555, "total_steps": 61300, "loss": 0.3016, "lr": 6.300889607177229e-06, "epoch": 7.920880913539968, "percentage": 79.21, "elapsed_time": "6:36:02", "remaining_time": "1:43:57", "throughput": 4409.84, "total_tokens": 104789088} {"current_steps": 48560, "total_steps": 61300, "loss": 0.3216, "lr": 6.296165883949947e-06, "epoch": 7.921696574225122, "percentage": 79.22, "elapsed_time": "6:36:04", "remaining_time": "1:43:54", "throughput": 4409.88, "total_tokens": 104800032} {"current_steps": 48565, "total_steps": 61300, "loss": 0.3389, "lr": 6.291443676950357e-06, "epoch": 7.922512234910277, "percentage": 79.23, "elapsed_time": "6:36:07", "remaining_time": "1:43:52", "throughput": 4409.91, "total_tokens": 104810720} {"current_steps": 48570, "total_steps": 61300, "loss": 0.3, "lr": 6.286722986561272e-06, "epoch": 7.923327895595432, "percentage": 79.23, "elapsed_time": "6:36:09", "remaining_time": "1:43:49", "throughput": 4409.95, "total_tokens": 104820896} {"current_steps": 48575, "total_steps": 61300, "loss": 0.3043, "lr": 6.282003813165368e-06, "epoch": 7.924143556280587, "percentage": 79.24, "elapsed_time": "6:36:11", "remaining_time": "1:43:47", "throughput": 4409.99, "total_tokens": 104831808} {"current_steps": 48580, "total_steps": 61300, "loss": 0.3408, "lr": 6.2772861571452125e-06, "epoch": 7.924959216965743, "percentage": 79.25, "elapsed_time": "6:36:13", "remaining_time": "1:43:44", "throughput": 4410.02, "total_tokens": 104841920} {"current_steps": 48585, "total_steps": 61300, "loss": 0.3266, "lr": 6.272570018883236e-06, "epoch": 7.925774877650897, "percentage": 79.26, "elapsed_time": "6:36:15", "remaining_time": "1:43:42", "throughput": 4410.06, "total_tokens": 104853408} {"current_steps": 48590, "total_steps": 61300, "loss": 0.3626, "lr": 6.26785539876176e-06, "epoch": 7.926590538336052, "percentage": 79.27, "elapsed_time": "6:36:17", "remaining_time": "1:43:39", "throughput": 4410.09, "total_tokens": 104862880} {"current_steps": 48595, "total_steps": 61300, "loss": 0.3288, "lr": 6.2631422971629605e-06, "epoch": 7.927406199021207, "percentage": 79.27, "elapsed_time": "6:36:20", "remaining_time": "1:43:37", "throughput": 4410.13, "total_tokens": 104873952} {"current_steps": 48600, "total_steps": 61300, "loss": 0.3141, "lr": 6.2584307144689245e-06, "epoch": 7.928221859706362, "percentage": 79.28, "elapsed_time": "6:36:22", "remaining_time": "1:43:34", "throughput": 4410.17, "total_tokens": 104884128} {"current_steps": 48605, "total_steps": 61300, "loss": 0.3306, "lr": 6.25372065106159e-06, "epoch": 7.9290375203915175, "percentage": 79.29, "elapsed_time": "6:36:24", "remaining_time": "1:43:32", "throughput": 4410.21, "total_tokens": 104895296} {"current_steps": 48610, "total_steps": 61300, "loss": 0.3734, "lr": 6.249012107322774e-06, "epoch": 7.929853181076672, "percentage": 79.3, "elapsed_time": "6:36:26", "remaining_time": "1:43:29", "throughput": 4410.24, "total_tokens": 104905760} {"current_steps": 48615, "total_steps": 61300, "loss": 0.3233, "lr": 6.244305083634181e-06, "epoch": 7.930668841761827, "percentage": 79.31, "elapsed_time": "6:36:29", "remaining_time": "1:43:27", "throughput": 4410.28, "total_tokens": 104916864} {"current_steps": 48620, "total_steps": 61300, "loss": 0.3364, "lr": 6.239599580377381e-06, "epoch": 7.931484502446982, "percentage": 79.31, "elapsed_time": "6:36:31", "remaining_time": "1:43:24", "throughput": 4410.32, "total_tokens": 104927104} {"current_steps": 48625, "total_steps": 61300, "loss": 0.3253, "lr": 6.234895597933832e-06, "epoch": 7.932300163132137, "percentage": 79.32, "elapsed_time": "6:36:33", "remaining_time": "1:43:22", "throughput": 4410.36, "total_tokens": 104937632} {"current_steps": 48630, "total_steps": 61300, "loss": 0.3371, "lr": 6.2301931366848555e-06, "epoch": 7.933115823817292, "percentage": 79.33, "elapsed_time": "6:36:35", "remaining_time": "1:43:19", "throughput": 4410.4, "total_tokens": 104948448} {"current_steps": 48635, "total_steps": 61300, "loss": 0.3351, "lr": 6.225492197011654e-06, "epoch": 7.933931484502447, "percentage": 79.34, "elapsed_time": "6:36:37", "remaining_time": "1:43:17", "throughput": 4410.44, "total_tokens": 104958688} {"current_steps": 48640, "total_steps": 61300, "loss": 0.3377, "lr": 6.220792779295326e-06, "epoch": 7.934747145187602, "percentage": 79.35, "elapsed_time": "6:36:40", "remaining_time": "1:43:14", "throughput": 4410.47, "total_tokens": 104969408} {"current_steps": 48645, "total_steps": 61300, "loss": 0.3135, "lr": 6.216094883916815e-06, "epoch": 7.935562805872757, "percentage": 79.36, "elapsed_time": "6:36:42", "remaining_time": "1:43:12", "throughput": 4410.51, "total_tokens": 104979968} {"current_steps": 48650, "total_steps": 61300, "loss": 0.35, "lr": 6.211398511256966e-06, "epoch": 7.936378466557912, "percentage": 79.36, "elapsed_time": "6:36:44", "remaining_time": "1:43:09", "throughput": 4410.55, "total_tokens": 104990688} {"current_steps": 48655, "total_steps": 61300, "loss": 0.3689, "lr": 6.206703661696484e-06, "epoch": 7.937194127243067, "percentage": 79.37, "elapsed_time": "6:36:46", "remaining_time": "1:43:07", "throughput": 4410.58, "total_tokens": 105002048} {"current_steps": 48660, "total_steps": 61300, "loss": 0.3453, "lr": 6.20201033561596e-06, "epoch": 7.938009787928221, "percentage": 79.38, "elapsed_time": "6:36:49", "remaining_time": "1:43:04", "throughput": 4410.62, "total_tokens": 105013056} {"current_steps": 48665, "total_steps": 61300, "loss": 0.3292, "lr": 6.197318533395858e-06, "epoch": 7.938825448613377, "percentage": 79.39, "elapsed_time": "6:36:50", "remaining_time": "1:43:02", "throughput": 4410.65, "total_tokens": 105021856} {"current_steps": 48670, "total_steps": 61300, "loss": 0.3347, "lr": 6.192628255416519e-06, "epoch": 7.939641109298532, "percentage": 79.4, "elapsed_time": "6:36:53", "remaining_time": "1:42:59", "throughput": 4410.68, "total_tokens": 105031936} {"current_steps": 48675, "total_steps": 61300, "loss": 0.3348, "lr": 6.18793950205816e-06, "epoch": 7.940456769983687, "percentage": 79.4, "elapsed_time": "6:36:55", "remaining_time": "1:42:57", "throughput": 4410.73, "total_tokens": 105044000} {"current_steps": 48680, "total_steps": 61300, "loss": 0.331, "lr": 6.183252273700879e-06, "epoch": 7.941272430668842, "percentage": 79.41, "elapsed_time": "6:36:57", "remaining_time": "1:42:54", "throughput": 4410.75, "total_tokens": 105054272} {"current_steps": 48685, "total_steps": 61300, "loss": 0.2875, "lr": 6.178566570724642e-06, "epoch": 7.942088091353996, "percentage": 79.42, "elapsed_time": "6:37:00", "remaining_time": "1:42:52", "throughput": 4410.8, "total_tokens": 105065984} {"current_steps": 48690, "total_steps": 61300, "loss": 0.2772, "lr": 6.1738823935092975e-06, "epoch": 7.942903752039152, "percentage": 79.43, "elapsed_time": "6:37:02", "remaining_time": "1:42:49", "throughput": 4410.84, "total_tokens": 105077440} {"current_steps": 48695, "total_steps": 61300, "loss": 0.3484, "lr": 6.16919974243457e-06, "epoch": 7.943719412724307, "percentage": 79.44, "elapsed_time": "6:37:04", "remaining_time": "1:42:47", "throughput": 4410.87, "total_tokens": 105087104} {"current_steps": 48700, "total_steps": 61300, "loss": 0.3563, "lr": 6.164518617880058e-06, "epoch": 7.944535073409462, "percentage": 79.45, "elapsed_time": "6:37:06", "remaining_time": "1:42:44", "throughput": 4410.91, "total_tokens": 105097824} {"current_steps": 48705, "total_steps": 61300, "loss": 0.3317, "lr": 6.159839020225231e-06, "epoch": 7.945350734094617, "percentage": 79.45, "elapsed_time": "6:37:08", "remaining_time": "1:42:42", "throughput": 4410.94, "total_tokens": 105108064} {"current_steps": 48710, "total_steps": 61300, "loss": 0.3439, "lr": 6.155160949849453e-06, "epoch": 7.946166394779771, "percentage": 79.46, "elapsed_time": "6:37:11", "remaining_time": "1:42:39", "throughput": 4410.98, "total_tokens": 105118784} {"current_steps": 48715, "total_steps": 61300, "loss": 0.3306, "lr": 6.150484407131945e-06, "epoch": 7.946982055464927, "percentage": 79.47, "elapsed_time": "6:37:13", "remaining_time": "1:42:37", "throughput": 4411.01, "total_tokens": 105128608} {"current_steps": 48720, "total_steps": 61300, "loss": 0.3118, "lr": 6.145809392451815e-06, "epoch": 7.947797716150082, "percentage": 79.48, "elapsed_time": "6:37:15", "remaining_time": "1:42:34", "throughput": 4411.05, "total_tokens": 105138720} {"current_steps": 48725, "total_steps": 61300, "loss": 0.363, "lr": 6.141135906188039e-06, "epoch": 7.948613376835237, "percentage": 79.49, "elapsed_time": "6:37:17", "remaining_time": "1:42:32", "throughput": 4411.09, "total_tokens": 105150368} {"current_steps": 48730, "total_steps": 61300, "loss": 0.325, "lr": 6.136463948719475e-06, "epoch": 7.9494290375203915, "percentage": 79.49, "elapsed_time": "6:37:19", "remaining_time": "1:42:29", "throughput": 4411.13, "total_tokens": 105160544} {"current_steps": 48735, "total_steps": 61300, "loss": 0.3346, "lr": 6.131793520424859e-06, "epoch": 7.950244698205546, "percentage": 79.5, "elapsed_time": "6:37:22", "remaining_time": "1:42:27", "throughput": 4411.16, "total_tokens": 105170784} {"current_steps": 48740, "total_steps": 61300, "loss": 0.3543, "lr": 6.1271246216827945e-06, "epoch": 7.951060358890701, "percentage": 79.51, "elapsed_time": "6:37:24", "remaining_time": "1:42:24", "throughput": 4411.19, "total_tokens": 105180960} {"current_steps": 48745, "total_steps": 61300, "loss": 0.3381, "lr": 6.122457252871769e-06, "epoch": 7.951876019575856, "percentage": 79.52, "elapsed_time": "6:37:26", "remaining_time": "1:42:21", "throughput": 4411.22, "total_tokens": 105191200} {"current_steps": 48750, "total_steps": 61300, "loss": 0.3536, "lr": 6.117791414370141e-06, "epoch": 7.952691680261012, "percentage": 79.53, "elapsed_time": "6:37:28", "remaining_time": "1:42:19", "throughput": 4411.27, "total_tokens": 105202176} {"current_steps": 48755, "total_steps": 61300, "loss": 0.3241, "lr": 6.113127106556149e-06, "epoch": 7.9535073409461665, "percentage": 79.54, "elapsed_time": "6:37:30", "remaining_time": "1:42:16", "throughput": 4411.3, "total_tokens": 105212352} {"current_steps": 48760, "total_steps": 61300, "loss": 0.264, "lr": 6.108464329807903e-06, "epoch": 7.954323001631321, "percentage": 79.54, "elapsed_time": "6:37:32", "remaining_time": "1:42:14", "throughput": 4411.33, "total_tokens": 105222464} {"current_steps": 48765, "total_steps": 61300, "loss": 0.3196, "lr": 6.1038030845033956e-06, "epoch": 7.955138662316476, "percentage": 79.55, "elapsed_time": "6:37:35", "remaining_time": "1:42:11", "throughput": 4411.37, "total_tokens": 105233984} {"current_steps": 48770, "total_steps": 61300, "loss": 0.3177, "lr": 6.0991433710204885e-06, "epoch": 7.955954323001631, "percentage": 79.56, "elapsed_time": "6:37:37", "remaining_time": "1:42:09", "throughput": 4411.41, "total_tokens": 105244768} {"current_steps": 48775, "total_steps": 61300, "loss": 0.335, "lr": 6.0944851897369206e-06, "epoch": 7.956769983686787, "percentage": 79.57, "elapsed_time": "6:37:39", "remaining_time": "1:42:06", "throughput": 4411.45, "total_tokens": 105255680} {"current_steps": 48780, "total_steps": 61300, "loss": 0.3589, "lr": 6.0898285410303015e-06, "epoch": 7.9575856443719415, "percentage": 79.58, "elapsed_time": "6:37:42", "remaining_time": "1:42:04", "throughput": 4411.5, "total_tokens": 105268608} {"current_steps": 48785, "total_steps": 61300, "loss": 0.3732, "lr": 6.085173425278137e-06, "epoch": 7.958401305057096, "percentage": 79.58, "elapsed_time": "6:37:44", "remaining_time": "1:42:02", "throughput": 4411.53, "total_tokens": 105278464} {"current_steps": 48790, "total_steps": 61300, "loss": 0.2896, "lr": 6.080519842857787e-06, "epoch": 7.959216965742251, "percentage": 79.59, "elapsed_time": "6:37:46", "remaining_time": "1:41:59", "throughput": 4411.57, "total_tokens": 105289856} {"current_steps": 48795, "total_steps": 61300, "loss": 0.3331, "lr": 6.075867794146497e-06, "epoch": 7.960032626427406, "percentage": 79.6, "elapsed_time": "6:37:48", "remaining_time": "1:41:57", "throughput": 4411.61, "total_tokens": 105300160} {"current_steps": 48800, "total_steps": 61300, "loss": 0.2944, "lr": 6.071217279521382e-06, "epoch": 7.960848287112562, "percentage": 79.61, "elapsed_time": "6:37:51", "remaining_time": "1:41:54", "throughput": 4411.65, "total_tokens": 105312352} {"current_steps": 48805, "total_steps": 61300, "loss": 0.2952, "lr": 6.06656829935944e-06, "epoch": 7.9616639477977165, "percentage": 79.62, "elapsed_time": "6:37:53", "remaining_time": "1:41:52", "throughput": 4411.69, "total_tokens": 105324544} {"current_steps": 48810, "total_steps": 61300, "loss": 0.3552, "lr": 6.061920854037531e-06, "epoch": 7.962479608482871, "percentage": 79.62, "elapsed_time": "6:37:56", "remaining_time": "1:41:49", "throughput": 4411.72, "total_tokens": 105335072} {"current_steps": 48815, "total_steps": 61300, "loss": 0.3289, "lr": 6.0572749439324146e-06, "epoch": 7.963295269168026, "percentage": 79.63, "elapsed_time": "6:37:58", "remaining_time": "1:41:47", "throughput": 4411.76, "total_tokens": 105344960} {"current_steps": 48820, "total_steps": 61300, "loss": 0.3904, "lr": 6.052630569420706e-06, "epoch": 7.964110929853181, "percentage": 79.64, "elapsed_time": "6:38:00", "remaining_time": "1:41:44", "throughput": 4411.8, "total_tokens": 105355264} {"current_steps": 48825, "total_steps": 61300, "loss": 0.3391, "lr": 6.047987730878904e-06, "epoch": 7.964926590538336, "percentage": 79.65, "elapsed_time": "6:38:02", "remaining_time": "1:41:42", "throughput": 4411.84, "total_tokens": 105366624} {"current_steps": 48830, "total_steps": 61300, "loss": 0.3364, "lr": 6.043346428683375e-06, "epoch": 7.9657422512234906, "percentage": 79.66, "elapsed_time": "6:38:05", "remaining_time": "1:41:39", "throughput": 4411.88, "total_tokens": 105377888} {"current_steps": 48835, "total_steps": 61300, "loss": 0.3198, "lr": 6.0387066632103695e-06, "epoch": 7.966557911908646, "percentage": 79.67, "elapsed_time": "6:38:07", "remaining_time": "1:41:37", "throughput": 4411.93, "total_tokens": 105388192} {"current_steps": 48840, "total_steps": 61300, "loss": 0.3607, "lr": 6.034068434836013e-06, "epoch": 7.967373572593801, "percentage": 79.67, "elapsed_time": "6:38:09", "remaining_time": "1:41:34", "throughput": 4411.97, "total_tokens": 105400256} {"current_steps": 48845, "total_steps": 61300, "loss": 0.334, "lr": 6.029431743936298e-06, "epoch": 7.968189233278956, "percentage": 79.68, "elapsed_time": "6:38:11", "remaining_time": "1:41:32", "throughput": 4412.01, "total_tokens": 105411328} {"current_steps": 48850, "total_steps": 61300, "loss": 0.3017, "lr": 6.024796590887105e-06, "epoch": 7.969004893964111, "percentage": 79.69, "elapsed_time": "6:38:14", "remaining_time": "1:41:29", "throughput": 4412.04, "total_tokens": 105421408} {"current_steps": 48855, "total_steps": 61300, "loss": 0.3579, "lr": 6.020162976064178e-06, "epoch": 7.9698205546492655, "percentage": 79.7, "elapsed_time": "6:38:16", "remaining_time": "1:41:27", "throughput": 4412.09, "total_tokens": 105431872} {"current_steps": 48860, "total_steps": 61300, "loss": 0.3317, "lr": 6.0155308998431415e-06, "epoch": 7.970636215334421, "percentage": 79.71, "elapsed_time": "6:38:18", "remaining_time": "1:41:24", "throughput": 4412.13, "total_tokens": 105443776} {"current_steps": 48865, "total_steps": 61300, "loss": 0.3237, "lr": 6.0109003625994975e-06, "epoch": 7.971451876019576, "percentage": 79.71, "elapsed_time": "6:38:20", "remaining_time": "1:41:22", "throughput": 4412.16, "total_tokens": 105453088} {"current_steps": 48870, "total_steps": 61300, "loss": 0.31, "lr": 6.006271364708621e-06, "epoch": 7.972267536704731, "percentage": 79.72, "elapsed_time": "6:38:22", "remaining_time": "1:41:19", "throughput": 4412.19, "total_tokens": 105463744} {"current_steps": 48875, "total_steps": 61300, "loss": 0.322, "lr": 6.0016439065457595e-06, "epoch": 7.973083197389886, "percentage": 79.73, "elapsed_time": "6:38:25", "remaining_time": "1:41:17", "throughput": 4412.23, "total_tokens": 105474752} {"current_steps": 48880, "total_steps": 61300, "loss": 0.3207, "lr": 5.997017988486039e-06, "epoch": 7.9738988580750405, "percentage": 79.74, "elapsed_time": "6:38:27", "remaining_time": "1:41:14", "throughput": 4412.27, "total_tokens": 105486016} {"current_steps": 48885, "total_steps": 61300, "loss": 0.3346, "lr": 5.992393610904465e-06, "epoch": 7.974714518760196, "percentage": 79.75, "elapsed_time": "6:38:29", "remaining_time": "1:41:12", "throughput": 4412.31, "total_tokens": 105496800} {"current_steps": 48890, "total_steps": 61300, "loss": 0.3408, "lr": 5.987770774175905e-06, "epoch": 7.975530179445351, "percentage": 79.76, "elapsed_time": "6:38:31", "remaining_time": "1:41:09", "throughput": 4412.34, "total_tokens": 105506528} {"current_steps": 48895, "total_steps": 61300, "loss": 0.2915, "lr": 5.983149478675113e-06, "epoch": 7.976345840130506, "percentage": 79.76, "elapsed_time": "6:38:33", "remaining_time": "1:41:07", "throughput": 4412.38, "total_tokens": 105517312} {"current_steps": 48900, "total_steps": 61300, "loss": 0.3353, "lr": 5.978529724776713e-06, "epoch": 7.977161500815661, "percentage": 79.77, "elapsed_time": "6:38:35", "remaining_time": "1:41:04", "throughput": 4412.41, "total_tokens": 105526976} {"current_steps": 48905, "total_steps": 61300, "loss": 0.3359, "lr": 5.97391151285521e-06, "epoch": 7.9779771615008155, "percentage": 79.78, "elapsed_time": "6:38:38", "remaining_time": "1:41:02", "throughput": 4412.45, "total_tokens": 105537408} {"current_steps": 48910, "total_steps": 61300, "loss": 0.3735, "lr": 5.969294843284978e-06, "epoch": 7.97879282218597, "percentage": 79.79, "elapsed_time": "6:38:40", "remaining_time": "1:40:59", "throughput": 4412.49, "total_tokens": 105547712} {"current_steps": 48915, "total_steps": 61300, "loss": 0.3587, "lr": 5.964679716440258e-06, "epoch": 7.979608482871125, "percentage": 79.8, "elapsed_time": "6:38:42", "remaining_time": "1:40:56", "throughput": 4412.52, "total_tokens": 105557760} {"current_steps": 48920, "total_steps": 61300, "loss": 0.3455, "lr": 5.9600661326951916e-06, "epoch": 7.980424143556281, "percentage": 79.8, "elapsed_time": "6:38:44", "remaining_time": "1:40:54", "throughput": 4412.57, "total_tokens": 105568800} {"current_steps": 48925, "total_steps": 61300, "loss": 0.3676, "lr": 5.955454092423773e-06, "epoch": 7.981239804241436, "percentage": 79.81, "elapsed_time": "6:38:46", "remaining_time": "1:40:51", "throughput": 4412.6, "total_tokens": 105578944} {"current_steps": 48930, "total_steps": 61300, "loss": 0.3139, "lr": 5.950843595999877e-06, "epoch": 7.9820554649265905, "percentage": 79.82, "elapsed_time": "6:38:48", "remaining_time": "1:40:49", "throughput": 4412.65, "total_tokens": 105589664} {"current_steps": 48935, "total_steps": 61300, "loss": 0.2896, "lr": 5.946234643797252e-06, "epoch": 7.982871125611745, "percentage": 79.83, "elapsed_time": "6:38:51", "remaining_time": "1:40:46", "throughput": 4412.69, "total_tokens": 105601056} {"current_steps": 48940, "total_steps": 61300, "loss": 0.3289, "lr": 5.941627236189526e-06, "epoch": 7.9836867862969, "percentage": 79.84, "elapsed_time": "6:38:53", "remaining_time": "1:40:44", "throughput": 4412.73, "total_tokens": 105611808} {"current_steps": 48945, "total_steps": 61300, "loss": 0.2878, "lr": 5.9370213735501974e-06, "epoch": 7.984502446982056, "percentage": 79.85, "elapsed_time": "6:38:55", "remaining_time": "1:40:42", "throughput": 4412.76, "total_tokens": 105622944} {"current_steps": 48950, "total_steps": 61300, "loss": 0.3677, "lr": 5.9324170562526345e-06, "epoch": 7.985318107667211, "percentage": 79.85, "elapsed_time": "6:38:58", "remaining_time": "1:40:39", "throughput": 4412.79, "total_tokens": 105633920} {"current_steps": 48955, "total_steps": 61300, "loss": 0.3706, "lr": 5.927814284670097e-06, "epoch": 7.986133768352365, "percentage": 79.86, "elapsed_time": "6:39:00", "remaining_time": "1:40:37", "throughput": 4412.83, "total_tokens": 105645280} {"current_steps": 48960, "total_steps": 61300, "loss": 0.3404, "lr": 5.923213059175709e-06, "epoch": 7.98694942903752, "percentage": 79.87, "elapsed_time": "6:39:02", "remaining_time": "1:40:34", "throughput": 4412.87, "total_tokens": 105656032} {"current_steps": 48965, "total_steps": 61300, "loss": 0.321, "lr": 5.918613380142463e-06, "epoch": 7.987765089722675, "percentage": 79.88, "elapsed_time": "6:39:04", "remaining_time": "1:40:32", "throughput": 4412.91, "total_tokens": 105666208} {"current_steps": 48970, "total_steps": 61300, "loss": 0.3082, "lr": 5.914015247943233e-06, "epoch": 7.988580750407831, "percentage": 79.89, "elapsed_time": "6:39:07", "remaining_time": "1:40:29", "throughput": 4412.94, "total_tokens": 105677600} {"current_steps": 48975, "total_steps": 61300, "loss": 0.3547, "lr": 5.909418662950769e-06, "epoch": 7.989396411092986, "percentage": 79.89, "elapsed_time": "6:39:09", "remaining_time": "1:40:27", "throughput": 4412.99, "total_tokens": 105688256} {"current_steps": 48980, "total_steps": 61300, "loss": 0.3568, "lr": 5.904823625537695e-06, "epoch": 7.99021207177814, "percentage": 79.9, "elapsed_time": "6:39:11", "remaining_time": "1:40:24", "throughput": 4413.02, "total_tokens": 105698560} {"current_steps": 48985, "total_steps": 61300, "loss": 0.3042, "lr": 5.900230136076504e-06, "epoch": 7.991027732463295, "percentage": 79.91, "elapsed_time": "6:39:13", "remaining_time": "1:40:22", "throughput": 4413.06, "total_tokens": 105709792} {"current_steps": 48990, "total_steps": 61300, "loss": 0.3031, "lr": 5.895638194939568e-06, "epoch": 7.99184339314845, "percentage": 79.92, "elapsed_time": "6:39:16", "remaining_time": "1:40:19", "throughput": 4413.09, "total_tokens": 105720608} {"current_steps": 48995, "total_steps": 61300, "loss": 0.3455, "lr": 5.891047802499136e-06, "epoch": 7.992659053833605, "percentage": 79.93, "elapsed_time": "6:39:18", "remaining_time": "1:40:17", "throughput": 4413.14, "total_tokens": 105732192} {"current_steps": 49000, "total_steps": 61300, "loss": 0.316, "lr": 5.886458959127328e-06, "epoch": 7.993474714518761, "percentage": 79.93, "elapsed_time": "6:39:20", "remaining_time": "1:40:14", "throughput": 4413.17, "total_tokens": 105742688} {"current_steps": 49005, "total_steps": 61300, "loss": 0.3166, "lr": 5.881871665196137e-06, "epoch": 7.994290375203915, "percentage": 79.94, "elapsed_time": "6:39:23", "remaining_time": "1:40:12", "throughput": 4413.22, "total_tokens": 105754208} {"current_steps": 49010, "total_steps": 61300, "loss": 0.3682, "lr": 5.877285921077433e-06, "epoch": 7.99510603588907, "percentage": 79.95, "elapsed_time": "6:39:25", "remaining_time": "1:40:09", "throughput": 4413.25, "total_tokens": 105765920} {"current_steps": 49015, "total_steps": 61300, "loss": 0.3661, "lr": 5.872701727142963e-06, "epoch": 7.995921696574225, "percentage": 79.96, "elapsed_time": "6:39:27", "remaining_time": "1:40:07", "throughput": 4413.29, "total_tokens": 105776992} {"current_steps": 49020, "total_steps": 61300, "loss": 0.3646, "lr": 5.868119083764337e-06, "epoch": 7.99673735725938, "percentage": 79.97, "elapsed_time": "6:39:30", "remaining_time": "1:40:04", "throughput": 4413.33, "total_tokens": 105788576} {"current_steps": 49025, "total_steps": 61300, "loss": 0.3546, "lr": 5.863537991313047e-06, "epoch": 7.997553017944535, "percentage": 79.98, "elapsed_time": "6:39:32", "remaining_time": "1:40:02", "throughput": 4413.37, "total_tokens": 105800384} {"current_steps": 49030, "total_steps": 61300, "loss": 0.3381, "lr": 5.858958450160473e-06, "epoch": 7.99836867862969, "percentage": 79.98, "elapsed_time": "6:39:34", "remaining_time": "1:39:59", "throughput": 4413.41, "total_tokens": 105810528} {"current_steps": 49035, "total_steps": 61300, "loss": 0.3065, "lr": 5.854380460677847e-06, "epoch": 7.999184339314845, "percentage": 79.99, "elapsed_time": "6:39:37", "remaining_time": "1:39:57", "throughput": 4413.44, "total_tokens": 105821440} {"current_steps": 49040, "total_steps": 61300, "loss": 0.3462, "lr": 5.849804023236285e-06, "epoch": 8.0, "percentage": 80.0, "elapsed_time": "6:39:39", "remaining_time": "1:39:54", "throughput": 4413.45, "total_tokens": 105830544} {"current_steps": 49040, "total_steps": 61300, "eval_loss": 0.3341042995452881, "epoch": 8.0, "percentage": 80.0, "elapsed_time": "6:41:50", "remaining_time": "1:40:27", "throughput": 4389.31, "total_tokens": 105830544} {"current_steps": 49045, "total_steps": 61300, "loss": 0.2736, "lr": 5.845229138206776e-06, "epoch": 8.000815660685156, "percentage": 80.01, "elapsed_time": "6:41:55", "remaining_time": "1:40:25", "throughput": 4389.09, "total_tokens": 105843312} {"current_steps": 49050, "total_steps": 61300, "loss": 0.3225, "lr": 5.8406558059601825e-06, "epoch": 8.00163132137031, "percentage": 80.02, "elapsed_time": "6:41:56", "remaining_time": "1:40:23", "throughput": 4389.13, "total_tokens": 105851248} {"current_steps": 49055, "total_steps": 61300, "loss": 0.2882, "lr": 5.836084026867244e-06, "epoch": 8.002446982055465, "percentage": 80.02, "elapsed_time": "6:41:59", "remaining_time": "1:40:20", "throughput": 4389.16, "total_tokens": 105862352} {"current_steps": 49060, "total_steps": 61300, "loss": 0.3361, "lr": 5.831513801298572e-06, "epoch": 8.00326264274062, "percentage": 80.03, "elapsed_time": "6:42:01", "remaining_time": "1:40:18", "throughput": 4389.2, "total_tokens": 105873264} {"current_steps": 49065, "total_steps": 61300, "loss": 0.3366, "lr": 5.82694512962465e-06, "epoch": 8.004078303425775, "percentage": 80.04, "elapsed_time": "6:42:03", "remaining_time": "1:40:15", "throughput": 4389.25, "total_tokens": 105884272} {"current_steps": 49070, "total_steps": 61300, "loss": 0.3663, "lr": 5.822378012215837e-06, "epoch": 8.00489396411093, "percentage": 80.05, "elapsed_time": "6:42:05", "remaining_time": "1:40:12", "throughput": 4389.29, "total_tokens": 105894832} {"current_steps": 49075, "total_steps": 61300, "loss": 0.287, "lr": 5.81781244944237e-06, "epoch": 8.005709624796085, "percentage": 80.06, "elapsed_time": "6:42:07", "remaining_time": "1:40:10", "throughput": 4389.33, "total_tokens": 105905520} {"current_steps": 49080, "total_steps": 61300, "loss": 0.3433, "lr": 5.813248441674357e-06, "epoch": 8.00652528548124, "percentage": 80.07, "elapsed_time": "6:42:10", "remaining_time": "1:40:08", "throughput": 4389.38, "total_tokens": 105917424} {"current_steps": 49085, "total_steps": 61300, "loss": 0.3275, "lr": 5.8086859892817755e-06, "epoch": 8.007340946166394, "percentage": 80.07, "elapsed_time": "6:42:12", "remaining_time": "1:40:05", "throughput": 4389.42, "total_tokens": 105928560} {"current_steps": 49090, "total_steps": 61300, "loss": 0.385, "lr": 5.804125092634485e-06, "epoch": 8.00815660685155, "percentage": 80.08, "elapsed_time": "6:42:14", "remaining_time": "1:40:02", "throughput": 4389.46, "total_tokens": 105939120} {"current_steps": 49095, "total_steps": 61300, "loss": 0.3595, "lr": 5.799565752102207e-06, "epoch": 8.008972267536704, "percentage": 80.09, "elapsed_time": "6:42:17", "remaining_time": "1:40:00", "throughput": 4389.49, "total_tokens": 105949424} {"current_steps": 49100, "total_steps": 61300, "loss": 0.342, "lr": 5.795007968054555e-06, "epoch": 8.00978792822186, "percentage": 80.1, "elapsed_time": "6:42:19", "remaining_time": "1:39:57", "throughput": 4389.52, "total_tokens": 105959280} {"current_steps": 49105, "total_steps": 61300, "loss": 0.3395, "lr": 5.790451740861005e-06, "epoch": 8.010603588907015, "percentage": 80.11, "elapsed_time": "6:42:21", "remaining_time": "1:39:55", "throughput": 4389.55, "total_tokens": 105968272} {"current_steps": 49110, "total_steps": 61300, "loss": 0.3017, "lr": 5.7858970708909056e-06, "epoch": 8.01141924959217, "percentage": 80.11, "elapsed_time": "6:42:23", "remaining_time": "1:39:52", "throughput": 4389.59, "total_tokens": 105978736} {"current_steps": 49115, "total_steps": 61300, "loss": 0.2941, "lr": 5.78134395851348e-06, "epoch": 8.012234910277325, "percentage": 80.12, "elapsed_time": "6:42:25", "remaining_time": "1:39:50", "throughput": 4389.63, "total_tokens": 105989872} {"current_steps": 49120, "total_steps": 61300, "loss": 0.3534, "lr": 5.7767924040978275e-06, "epoch": 8.013050570962479, "percentage": 80.13, "elapsed_time": "6:42:27", "remaining_time": "1:39:47", "throughput": 4389.66, "total_tokens": 105999792} {"current_steps": 49125, "total_steps": 61300, "loss": 0.3176, "lr": 5.772242408012921e-06, "epoch": 8.013866231647635, "percentage": 80.14, "elapsed_time": "6:42:29", "remaining_time": "1:39:45", "throughput": 4389.7, "total_tokens": 106010256} {"current_steps": 49130, "total_steps": 61300, "loss": 0.3693, "lr": 5.767693970627597e-06, "epoch": 8.01468189233279, "percentage": 80.15, "elapsed_time": "6:42:31", "remaining_time": "1:39:42", "throughput": 4389.73, "total_tokens": 106020496} {"current_steps": 49135, "total_steps": 61300, "loss": 0.3307, "lr": 5.763147092310592e-06, "epoch": 8.015497553017944, "percentage": 80.15, "elapsed_time": "6:42:34", "remaining_time": "1:39:40", "throughput": 4389.77, "total_tokens": 106031248} {"current_steps": 49140, "total_steps": 61300, "loss": 0.2859, "lr": 5.758601773430489e-06, "epoch": 8.0163132137031, "percentage": 80.16, "elapsed_time": "6:42:36", "remaining_time": "1:39:37", "throughput": 4389.81, "total_tokens": 106041232} {"current_steps": 49145, "total_steps": 61300, "loss": 0.3591, "lr": 5.7540580143557564e-06, "epoch": 8.017128874388254, "percentage": 80.17, "elapsed_time": "6:42:38", "remaining_time": "1:39:35", "throughput": 4389.86, "total_tokens": 106051696} {"current_steps": 49150, "total_steps": 61300, "loss": 0.3176, "lr": 5.7495158154547365e-06, "epoch": 8.01794453507341, "percentage": 80.18, "elapsed_time": "6:42:40", "remaining_time": "1:39:32", "throughput": 4389.9, "total_tokens": 106062672} {"current_steps": 49155, "total_steps": 61300, "loss": 0.3264, "lr": 5.744975177095638e-06, "epoch": 8.018760195758565, "percentage": 80.19, "elapsed_time": "6:42:42", "remaining_time": "1:39:30", "throughput": 4389.93, "total_tokens": 106072784} {"current_steps": 49160, "total_steps": 61300, "loss": 0.3264, "lr": 5.740436099646551e-06, "epoch": 8.01957585644372, "percentage": 80.2, "elapsed_time": "6:42:45", "remaining_time": "1:39:27", "throughput": 4389.97, "total_tokens": 106083952} {"current_steps": 49165, "total_steps": 61300, "loss": 0.3055, "lr": 5.735898583475438e-06, "epoch": 8.020391517128875, "percentage": 80.2, "elapsed_time": "6:42:47", "remaining_time": "1:39:25", "throughput": 4390.01, "total_tokens": 106095632} {"current_steps": 49170, "total_steps": 61300, "loss": 0.3241, "lr": 5.731362628950129e-06, "epoch": 8.021207177814029, "percentage": 80.21, "elapsed_time": "6:42:49", "remaining_time": "1:39:22", "throughput": 4390.05, "total_tokens": 106106160} {"current_steps": 49175, "total_steps": 61300, "loss": 0.3394, "lr": 5.726828236438334e-06, "epoch": 8.022022838499185, "percentage": 80.22, "elapsed_time": "6:42:51", "remaining_time": "1:39:20", "throughput": 4390.09, "total_tokens": 106116784} {"current_steps": 49180, "total_steps": 61300, "loss": 0.3556, "lr": 5.722295406307632e-06, "epoch": 8.022838499184338, "percentage": 80.23, "elapsed_time": "6:42:54", "remaining_time": "1:39:17", "throughput": 4390.13, "total_tokens": 106127088} {"current_steps": 49185, "total_steps": 61300, "loss": 0.315, "lr": 5.71776413892548e-06, "epoch": 8.023654159869494, "percentage": 80.24, "elapsed_time": "6:42:56", "remaining_time": "1:39:14", "throughput": 4390.16, "total_tokens": 106136912} {"current_steps": 49190, "total_steps": 61300, "loss": 0.3476, "lr": 5.713234434659203e-06, "epoch": 8.02446982055465, "percentage": 80.24, "elapsed_time": "6:42:58", "remaining_time": "1:39:12", "throughput": 4390.21, "total_tokens": 106148816} {"current_steps": 49195, "total_steps": 61300, "loss": 0.3028, "lr": 5.708706293876004e-06, "epoch": 8.025285481239804, "percentage": 80.25, "elapsed_time": "6:43:00", "remaining_time": "1:39:09", "throughput": 4390.25, "total_tokens": 106158672} {"current_steps": 49200, "total_steps": 61300, "loss": 0.3477, "lr": 5.7041797169429536e-06, "epoch": 8.02610114192496, "percentage": 80.26, "elapsed_time": "6:43:02", "remaining_time": "1:39:07", "throughput": 4390.29, "total_tokens": 106169744} {"current_steps": 49205, "total_steps": 61300, "loss": 0.3014, "lr": 5.699654704227003e-06, "epoch": 8.026916802610113, "percentage": 80.27, "elapsed_time": "6:43:04", "remaining_time": "1:39:04", "throughput": 4390.33, "total_tokens": 106179824} {"current_steps": 49210, "total_steps": 61300, "loss": 0.3776, "lr": 5.695131256094971e-06, "epoch": 8.02773246329527, "percentage": 80.28, "elapsed_time": "6:43:07", "remaining_time": "1:39:02", "throughput": 4390.36, "total_tokens": 106190640} {"current_steps": 49215, "total_steps": 61300, "loss": 0.3004, "lr": 5.6906093729135495e-06, "epoch": 8.028548123980425, "percentage": 80.29, "elapsed_time": "6:43:09", "remaining_time": "1:38:59", "throughput": 4390.39, "total_tokens": 106200112} {"current_steps": 49220, "total_steps": 61300, "loss": 0.3146, "lr": 5.6860890550493095e-06, "epoch": 8.029363784665579, "percentage": 80.29, "elapsed_time": "6:43:11", "remaining_time": "1:38:57", "throughput": 4390.44, "total_tokens": 106211440} {"current_steps": 49225, "total_steps": 61300, "loss": 0.3218, "lr": 5.681570302868688e-06, "epoch": 8.030179445350734, "percentage": 80.3, "elapsed_time": "6:43:13", "remaining_time": "1:38:54", "throughput": 4390.48, "total_tokens": 106222224} {"current_steps": 49230, "total_steps": 61300, "loss": 0.2929, "lr": 5.677053116737999e-06, "epoch": 8.030995106035888, "percentage": 80.31, "elapsed_time": "6:43:16", "remaining_time": "1:38:52", "throughput": 4390.52, "total_tokens": 106233968} {"current_steps": 49235, "total_steps": 61300, "loss": 0.3525, "lr": 5.67253749702342e-06, "epoch": 8.031810766721044, "percentage": 80.32, "elapsed_time": "6:43:18", "remaining_time": "1:38:49", "throughput": 4390.56, "total_tokens": 106244944} {"current_steps": 49240, "total_steps": 61300, "loss": 0.3858, "lr": 5.668023444091025e-06, "epoch": 8.0326264274062, "percentage": 80.33, "elapsed_time": "6:43:20", "remaining_time": "1:38:47", "throughput": 4390.6, "total_tokens": 106255664} {"current_steps": 49245, "total_steps": 61300, "loss": 0.3224, "lr": 5.663510958306739e-06, "epoch": 8.033442088091354, "percentage": 80.33, "elapsed_time": "6:43:23", "remaining_time": "1:38:44", "throughput": 4390.64, "total_tokens": 106266672} {"current_steps": 49250, "total_steps": 61300, "loss": 0.3282, "lr": 5.659000040036366e-06, "epoch": 8.03425774877651, "percentage": 80.34, "elapsed_time": "6:43:25", "remaining_time": "1:38:42", "throughput": 4390.68, "total_tokens": 106278288} {"current_steps": 49255, "total_steps": 61300, "loss": 0.3136, "lr": 5.654490689645589e-06, "epoch": 8.035073409461663, "percentage": 80.35, "elapsed_time": "6:43:27", "remaining_time": "1:38:39", "throughput": 4390.73, "total_tokens": 106289744} {"current_steps": 49260, "total_steps": 61300, "loss": 0.3399, "lr": 5.649982907499951e-06, "epoch": 8.035889070146819, "percentage": 80.36, "elapsed_time": "6:43:29", "remaining_time": "1:38:37", "throughput": 4390.76, "total_tokens": 106298480} {"current_steps": 49265, "total_steps": 61300, "loss": 0.3523, "lr": 5.645476693964874e-06, "epoch": 8.036704730831975, "percentage": 80.37, "elapsed_time": "6:43:32", "remaining_time": "1:38:34", "throughput": 4390.8, "total_tokens": 106310800} {"current_steps": 49270, "total_steps": 61300, "loss": 0.3141, "lr": 5.640972049405666e-06, "epoch": 8.037520391517129, "percentage": 80.38, "elapsed_time": "6:43:34", "remaining_time": "1:38:32", "throughput": 4390.84, "total_tokens": 106322000} {"current_steps": 49275, "total_steps": 61300, "loss": 0.3476, "lr": 5.636468974187492e-06, "epoch": 8.038336052202284, "percentage": 80.38, "elapsed_time": "6:43:36", "remaining_time": "1:38:29", "throughput": 4390.88, "total_tokens": 106331632} {"current_steps": 49280, "total_steps": 61300, "loss": 0.3409, "lr": 5.631967468675392e-06, "epoch": 8.039151712887438, "percentage": 80.39, "elapsed_time": "6:43:38", "remaining_time": "1:38:27", "throughput": 4390.93, "total_tokens": 106343344} {"current_steps": 49285, "total_steps": 61300, "loss": 0.3201, "lr": 5.627467533234282e-06, "epoch": 8.039967373572594, "percentage": 80.4, "elapsed_time": "6:43:41", "remaining_time": "1:38:24", "throughput": 4390.97, "total_tokens": 106354288} {"current_steps": 49290, "total_steps": 61300, "loss": 0.3563, "lr": 5.622969168228947e-06, "epoch": 8.040783034257748, "percentage": 80.41, "elapsed_time": "6:43:43", "remaining_time": "1:38:22", "throughput": 4391.0, "total_tokens": 106365168} {"current_steps": 49295, "total_steps": 61300, "loss": 0.3163, "lr": 5.61847237402405e-06, "epoch": 8.041598694942904, "percentage": 80.42, "elapsed_time": "6:43:45", "remaining_time": "1:38:19", "throughput": 4391.03, "total_tokens": 106375440} {"current_steps": 49300, "total_steps": 61300, "loss": 0.3216, "lr": 5.613977150984123e-06, "epoch": 8.04241435562806, "percentage": 80.42, "elapsed_time": "6:43:47", "remaining_time": "1:38:17", "throughput": 4391.07, "total_tokens": 106386032} {"current_steps": 49305, "total_steps": 61300, "loss": 0.352, "lr": 5.609483499473575e-06, "epoch": 8.043230016313213, "percentage": 80.43, "elapsed_time": "6:43:50", "remaining_time": "1:38:14", "throughput": 4391.11, "total_tokens": 106398160} {"current_steps": 49310, "total_steps": 61300, "loss": 0.3387, "lr": 5.604991419856678e-06, "epoch": 8.044045676998369, "percentage": 80.44, "elapsed_time": "6:43:52", "remaining_time": "1:38:12", "throughput": 4391.16, "total_tokens": 106408432} {"current_steps": 49315, "total_steps": 61300, "loss": 0.3467, "lr": 5.600500912497586e-06, "epoch": 8.044861337683523, "percentage": 80.45, "elapsed_time": "6:43:54", "remaining_time": "1:38:09", "throughput": 4391.19, "total_tokens": 106419440} {"current_steps": 49320, "total_steps": 61300, "loss": 0.278, "lr": 5.596011977760324e-06, "epoch": 8.045676998368679, "percentage": 80.46, "elapsed_time": "6:43:56", "remaining_time": "1:38:07", "throughput": 4391.23, "total_tokens": 106430000} {"current_steps": 49325, "total_steps": 61300, "loss": 0.3664, "lr": 5.591524616008784e-06, "epoch": 8.046492659053834, "percentage": 80.46, "elapsed_time": "6:43:59", "remaining_time": "1:38:04", "throughput": 4391.27, "total_tokens": 106441392} {"current_steps": 49330, "total_steps": 61300, "loss": 0.3417, "lr": 5.587038827606736e-06, "epoch": 8.047308319738988, "percentage": 80.47, "elapsed_time": "6:44:01", "remaining_time": "1:38:02", "throughput": 4391.3, "total_tokens": 106452688} {"current_steps": 49335, "total_steps": 61300, "loss": 0.3663, "lr": 5.582554612917823e-06, "epoch": 8.048123980424144, "percentage": 80.48, "elapsed_time": "6:44:03", "remaining_time": "1:37:59", "throughput": 4391.34, "total_tokens": 106462352} {"current_steps": 49340, "total_steps": 61300, "loss": 0.3524, "lr": 5.578071972305554e-06, "epoch": 8.048939641109298, "percentage": 80.49, "elapsed_time": "6:44:05", "remaining_time": "1:37:57", "throughput": 4391.37, "total_tokens": 106472208} {"current_steps": 49345, "total_steps": 61300, "loss": 0.3732, "lr": 5.57359090613331e-06, "epoch": 8.049755301794454, "percentage": 80.5, "elapsed_time": "6:44:07", "remaining_time": "1:37:54", "throughput": 4391.4, "total_tokens": 106481840} {"current_steps": 49350, "total_steps": 61300, "loss": 0.3077, "lr": 5.569111414764363e-06, "epoch": 8.05057096247961, "percentage": 80.51, "elapsed_time": "6:44:10", "remaining_time": "1:37:52", "throughput": 4391.45, "total_tokens": 106492912} {"current_steps": 49355, "total_steps": 61300, "loss": 0.3121, "lr": 5.564633498561839e-06, "epoch": 8.051386623164763, "percentage": 80.51, "elapsed_time": "6:44:12", "remaining_time": "1:37:49", "throughput": 4391.49, "total_tokens": 106503440} {"current_steps": 49360, "total_steps": 61300, "loss": 0.3632, "lr": 5.560157157888735e-06, "epoch": 8.052202283849919, "percentage": 80.52, "elapsed_time": "6:44:14", "remaining_time": "1:37:47", "throughput": 4391.52, "total_tokens": 106512880} {"current_steps": 49365, "total_steps": 61300, "loss": 0.34, "lr": 5.555682393107928e-06, "epoch": 8.053017944535073, "percentage": 80.53, "elapsed_time": "6:44:16", "remaining_time": "1:37:44", "throughput": 4391.57, "total_tokens": 106525296} {"current_steps": 49370, "total_steps": 61300, "loss": 0.3397, "lr": 5.551209204582167e-06, "epoch": 8.053833605220229, "percentage": 80.54, "elapsed_time": "6:44:18", "remaining_time": "1:37:42", "throughput": 4391.6, "total_tokens": 106535536} {"current_steps": 49375, "total_steps": 61300, "loss": 0.3484, "lr": 5.54673759267407e-06, "epoch": 8.054649265905383, "percentage": 80.55, "elapsed_time": "6:44:21", "remaining_time": "1:37:39", "throughput": 4391.64, "total_tokens": 106546160} {"current_steps": 49380, "total_steps": 61300, "loss": 0.3067, "lr": 5.542267557746128e-06, "epoch": 8.055464926590538, "percentage": 80.55, "elapsed_time": "6:44:23", "remaining_time": "1:37:37", "throughput": 4391.69, "total_tokens": 106558064} {"current_steps": 49385, "total_steps": 61300, "loss": 0.3008, "lr": 5.537799100160704e-06, "epoch": 8.056280587275694, "percentage": 80.56, "elapsed_time": "6:44:25", "remaining_time": "1:37:34", "throughput": 4391.73, "total_tokens": 106568400} {"current_steps": 49390, "total_steps": 61300, "loss": 0.3429, "lr": 5.533332220280038e-06, "epoch": 8.057096247960848, "percentage": 80.57, "elapsed_time": "6:44:27", "remaining_time": "1:37:31", "throughput": 4391.76, "total_tokens": 106578192} {"current_steps": 49395, "total_steps": 61300, "loss": 0.3127, "lr": 5.5288669184662325e-06, "epoch": 8.057911908646004, "percentage": 80.58, "elapsed_time": "6:44:29", "remaining_time": "1:37:29", "throughput": 4391.79, "total_tokens": 106587312} {"current_steps": 49400, "total_steps": 61300, "loss": 0.301, "lr": 5.524403195081271e-06, "epoch": 8.058727569331158, "percentage": 80.59, "elapsed_time": "6:44:32", "remaining_time": "1:37:26", "throughput": 4391.83, "total_tokens": 106598672} {"current_steps": 49405, "total_steps": 61300, "loss": 0.3553, "lr": 5.519941050487007e-06, "epoch": 8.059543230016313, "percentage": 80.6, "elapsed_time": "6:44:33", "remaining_time": "1:37:24", "throughput": 4391.87, "total_tokens": 106608208} {"current_steps": 49410, "total_steps": 61300, "loss": 0.3283, "lr": 5.515480485045152e-06, "epoch": 8.060358890701469, "percentage": 80.6, "elapsed_time": "6:44:36", "remaining_time": "1:37:21", "throughput": 4391.91, "total_tokens": 106619984} {"current_steps": 49415, "total_steps": 61300, "loss": 0.3294, "lr": 5.511021499117322e-06, "epoch": 8.061174551386623, "percentage": 80.61, "elapsed_time": "6:44:38", "remaining_time": "1:37:19", "throughput": 4391.95, "total_tokens": 106631792} {"current_steps": 49420, "total_steps": 61300, "loss": 0.3769, "lr": 5.5065640930649725e-06, "epoch": 8.061990212071779, "percentage": 80.62, "elapsed_time": "6:44:41", "remaining_time": "1:37:16", "throughput": 4391.99, "total_tokens": 106643600} {"current_steps": 49425, "total_steps": 61300, "loss": 0.3159, "lr": 5.502108267249448e-06, "epoch": 8.062805872756933, "percentage": 80.63, "elapsed_time": "6:44:43", "remaining_time": "1:37:14", "throughput": 4392.04, "total_tokens": 106654672} {"current_steps": 49430, "total_steps": 61300, "loss": 0.3769, "lr": 5.497654022031959e-06, "epoch": 8.063621533442088, "percentage": 80.64, "elapsed_time": "6:44:45", "remaining_time": "1:37:11", "throughput": 4392.07, "total_tokens": 106665456} {"current_steps": 49435, "total_steps": 61300, "loss": 0.3699, "lr": 5.493201357773589e-06, "epoch": 8.064437194127244, "percentage": 80.64, "elapsed_time": "6:44:48", "remaining_time": "1:37:09", "throughput": 4392.12, "total_tokens": 106676880} {"current_steps": 49440, "total_steps": 61300, "loss": 0.3629, "lr": 5.488750274835291e-06, "epoch": 8.065252854812398, "percentage": 80.65, "elapsed_time": "6:44:50", "remaining_time": "1:37:07", "throughput": 4392.15, "total_tokens": 106688528} {"current_steps": 49445, "total_steps": 61300, "loss": 0.3317, "lr": 5.4843007735778996e-06, "epoch": 8.066068515497554, "percentage": 80.66, "elapsed_time": "6:44:52", "remaining_time": "1:37:04", "throughput": 4392.19, "total_tokens": 106698992} {"current_steps": 49450, "total_steps": 61300, "loss": 0.329, "lr": 5.4798528543620965e-06, "epoch": 8.066884176182707, "percentage": 80.67, "elapsed_time": "6:44:55", "remaining_time": "1:37:01", "throughput": 4392.23, "total_tokens": 106709168} {"current_steps": 49455, "total_steps": 61300, "loss": 0.3023, "lr": 5.475406517548476e-06, "epoch": 8.067699836867863, "percentage": 80.68, "elapsed_time": "6:44:57", "remaining_time": "1:36:59", "throughput": 4392.26, "total_tokens": 106719920} {"current_steps": 49460, "total_steps": 61300, "loss": 0.3306, "lr": 5.47096176349747e-06, "epoch": 8.068515497553017, "percentage": 80.69, "elapsed_time": "6:44:59", "remaining_time": "1:36:56", "throughput": 4392.29, "total_tokens": 106729872} {"current_steps": 49465, "total_steps": 61300, "loss": 0.3251, "lr": 5.466518592569391e-06, "epoch": 8.069331158238173, "percentage": 80.69, "elapsed_time": "6:45:01", "remaining_time": "1:36:54", "throughput": 4392.32, "total_tokens": 106741168} {"current_steps": 49470, "total_steps": 61300, "loss": 0.3191, "lr": 5.4620770051244275e-06, "epoch": 8.070146818923329, "percentage": 80.7, "elapsed_time": "6:45:03", "remaining_time": "1:36:51", "throughput": 4392.36, "total_tokens": 106751376} {"current_steps": 49475, "total_steps": 61300, "loss": 0.3507, "lr": 5.457637001522636e-06, "epoch": 8.070962479608482, "percentage": 80.71, "elapsed_time": "6:45:06", "remaining_time": "1:36:49", "throughput": 4392.4, "total_tokens": 106761904} {"current_steps": 49480, "total_steps": 61300, "loss": 0.345, "lr": 5.453198582123947e-06, "epoch": 8.071778140293638, "percentage": 80.72, "elapsed_time": "6:45:08", "remaining_time": "1:36:46", "throughput": 4392.43, "total_tokens": 106772240} {"current_steps": 49485, "total_steps": 61300, "loss": 0.3429, "lr": 5.448761747288161e-06, "epoch": 8.072593800978792, "percentage": 80.73, "elapsed_time": "6:45:10", "remaining_time": "1:36:44", "throughput": 4392.47, "total_tokens": 106783216} {"current_steps": 49490, "total_steps": 61300, "loss": 0.3444, "lr": 5.444326497374949e-06, "epoch": 8.073409461663948, "percentage": 80.73, "elapsed_time": "6:45:12", "remaining_time": "1:36:41", "throughput": 4392.52, "total_tokens": 106794896} {"current_steps": 49495, "total_steps": 61300, "loss": 0.2956, "lr": 5.439892832743856e-06, "epoch": 8.074225122349104, "percentage": 80.74, "elapsed_time": "6:45:15", "remaining_time": "1:36:39", "throughput": 4392.55, "total_tokens": 106805360} {"current_steps": 49500, "total_steps": 61300, "loss": 0.3377, "lr": 5.435460753754296e-06, "epoch": 8.075040783034257, "percentage": 80.75, "elapsed_time": "6:45:17", "remaining_time": "1:36:36", "throughput": 4392.59, "total_tokens": 106816144} {"current_steps": 49505, "total_steps": 61300, "loss": 0.3635, "lr": 5.431030260765557e-06, "epoch": 8.075856443719413, "percentage": 80.76, "elapsed_time": "6:45:19", "remaining_time": "1:36:34", "throughput": 4392.63, "total_tokens": 106827088} {"current_steps": 49510, "total_steps": 61300, "loss": 0.3094, "lr": 5.426601354136799e-06, "epoch": 8.076672104404567, "percentage": 80.77, "elapsed_time": "6:45:21", "remaining_time": "1:36:31", "throughput": 4392.66, "total_tokens": 106837488} {"current_steps": 49515, "total_steps": 61300, "loss": 0.3378, "lr": 5.4221740342270455e-06, "epoch": 8.077487765089723, "percentage": 80.77, "elapsed_time": "6:45:24", "remaining_time": "1:36:29", "throughput": 4392.71, "total_tokens": 106849520} {"current_steps": 49520, "total_steps": 61300, "loss": 0.3089, "lr": 5.4177483013952065e-06, "epoch": 8.078303425774878, "percentage": 80.78, "elapsed_time": "6:45:26", "remaining_time": "1:36:26", "throughput": 4392.75, "total_tokens": 106860528} {"current_steps": 49525, "total_steps": 61300, "loss": 0.3409, "lr": 5.413324156000046e-06, "epoch": 8.079119086460032, "percentage": 80.79, "elapsed_time": "6:45:28", "remaining_time": "1:36:24", "throughput": 4392.78, "total_tokens": 106869936} {"current_steps": 49530, "total_steps": 61300, "loss": 0.316, "lr": 5.408901598400212e-06, "epoch": 8.079934747145188, "percentage": 80.8, "elapsed_time": "6:45:30", "remaining_time": "1:36:21", "throughput": 4392.83, "total_tokens": 106881936} {"current_steps": 49535, "total_steps": 61300, "loss": 0.3414, "lr": 5.40448062895422e-06, "epoch": 8.080750407830342, "percentage": 80.81, "elapsed_time": "6:45:32", "remaining_time": "1:36:19", "throughput": 4392.87, "total_tokens": 106891376} {"current_steps": 49540, "total_steps": 61300, "loss": 0.2868, "lr": 5.400061248020452e-06, "epoch": 8.081566068515498, "percentage": 80.82, "elapsed_time": "6:45:34", "remaining_time": "1:36:16", "throughput": 4392.91, "total_tokens": 106901168} {"current_steps": 49545, "total_steps": 61300, "loss": 0.3272, "lr": 5.395643455957172e-06, "epoch": 8.082381729200652, "percentage": 80.82, "elapsed_time": "6:45:37", "remaining_time": "1:36:14", "throughput": 4392.95, "total_tokens": 106912432} {"current_steps": 49550, "total_steps": 61300, "loss": 0.3674, "lr": 5.391227253122502e-06, "epoch": 8.083197389885807, "percentage": 80.83, "elapsed_time": "6:45:39", "remaining_time": "1:36:11", "throughput": 4393.0, "total_tokens": 106924592} {"current_steps": 49555, "total_steps": 61300, "loss": 0.3206, "lr": 5.386812639874439e-06, "epoch": 8.084013050570963, "percentage": 80.84, "elapsed_time": "6:45:41", "remaining_time": "1:36:09", "throughput": 4393.03, "total_tokens": 106934704} {"current_steps": 49560, "total_steps": 61300, "loss": 0.3615, "lr": 5.382399616570869e-06, "epoch": 8.084828711256117, "percentage": 80.85, "elapsed_time": "6:45:44", "remaining_time": "1:36:06", "throughput": 4393.07, "total_tokens": 106945936} {"current_steps": 49565, "total_steps": 61300, "loss": 0.3101, "lr": 5.377988183569521e-06, "epoch": 8.085644371941273, "percentage": 80.86, "elapsed_time": "6:45:46", "remaining_time": "1:36:04", "throughput": 4393.12, "total_tokens": 106957264} {"current_steps": 49570, "total_steps": 61300, "loss": 0.3224, "lr": 5.3735783412280134e-06, "epoch": 8.086460032626427, "percentage": 80.86, "elapsed_time": "6:45:49", "remaining_time": "1:36:01", "throughput": 4393.15, "total_tokens": 106968816} {"current_steps": 49575, "total_steps": 61300, "loss": 0.3444, "lr": 5.36917008990383e-06, "epoch": 8.087275693311582, "percentage": 80.87, "elapsed_time": "6:45:51", "remaining_time": "1:35:59", "throughput": 4393.2, "total_tokens": 106981680} {"current_steps": 49580, "total_steps": 61300, "loss": 0.3199, "lr": 5.364763429954317e-06, "epoch": 8.088091353996738, "percentage": 80.88, "elapsed_time": "6:45:53", "remaining_time": "1:35:56", "throughput": 4393.23, "total_tokens": 106992048} {"current_steps": 49585, "total_steps": 61300, "loss": 0.3881, "lr": 5.360358361736714e-06, "epoch": 8.088907014681892, "percentage": 80.89, "elapsed_time": "6:45:56", "remaining_time": "1:35:54", "throughput": 4393.28, "total_tokens": 107004016} {"current_steps": 49590, "total_steps": 61300, "loss": 0.3314, "lr": 5.3559548856081135e-06, "epoch": 8.089722675367048, "percentage": 80.9, "elapsed_time": "6:45:58", "remaining_time": "1:35:51", "throughput": 4393.32, "total_tokens": 107015024} {"current_steps": 49595, "total_steps": 61300, "loss": 0.331, "lr": 5.351553001925486e-06, "epoch": 8.090538336052202, "percentage": 80.91, "elapsed_time": "6:46:00", "remaining_time": "1:35:49", "throughput": 4393.35, "total_tokens": 107025008} {"current_steps": 49600, "total_steps": 61300, "loss": 0.3309, "lr": 5.347152711045664e-06, "epoch": 8.091353996737357, "percentage": 80.91, "elapsed_time": "6:46:02", "remaining_time": "1:35:46", "throughput": 4393.39, "total_tokens": 107035408} {"current_steps": 49605, "total_steps": 61300, "loss": 0.3319, "lr": 5.342754013325363e-06, "epoch": 8.092169657422513, "percentage": 80.92, "elapsed_time": "6:46:05", "remaining_time": "1:35:44", "throughput": 4393.43, "total_tokens": 107046960} {"current_steps": 49610, "total_steps": 61300, "loss": 0.2887, "lr": 5.338356909121159e-06, "epoch": 8.092985318107667, "percentage": 80.93, "elapsed_time": "6:46:07", "remaining_time": "1:35:41", "throughput": 4393.48, "total_tokens": 107058736} {"current_steps": 49615, "total_steps": 61300, "loss": 0.3442, "lr": 5.3339613987895084e-06, "epoch": 8.093800978792823, "percentage": 80.94, "elapsed_time": "6:46:09", "remaining_time": "1:35:39", "throughput": 4393.52, "total_tokens": 107069872} {"current_steps": 49620, "total_steps": 61300, "loss": 0.3256, "lr": 5.329567482686729e-06, "epoch": 8.094616639477977, "percentage": 80.95, "elapsed_time": "6:46:12", "remaining_time": "1:35:36", "throughput": 4393.55, "total_tokens": 107080400} {"current_steps": 49625, "total_steps": 61300, "loss": 0.3621, "lr": 5.325175161169019e-06, "epoch": 8.095432300163132, "percentage": 80.95, "elapsed_time": "6:46:14", "remaining_time": "1:35:34", "throughput": 4393.6, "total_tokens": 107091696} {"current_steps": 49630, "total_steps": 61300, "loss": 0.3125, "lr": 5.320784434592438e-06, "epoch": 8.096247960848286, "percentage": 80.96, "elapsed_time": "6:46:16", "remaining_time": "1:35:31", "throughput": 4393.63, "total_tokens": 107101168} {"current_steps": 49635, "total_steps": 61300, "loss": 0.2931, "lr": 5.316395303312921e-06, "epoch": 8.097063621533442, "percentage": 80.97, "elapsed_time": "6:46:18", "remaining_time": "1:35:29", "throughput": 4393.66, "total_tokens": 107112464} {"current_steps": 49640, "total_steps": 61300, "loss": 0.3157, "lr": 5.3120077676862754e-06, "epoch": 8.097879282218598, "percentage": 80.98, "elapsed_time": "6:46:21", "remaining_time": "1:35:26", "throughput": 4393.7, "total_tokens": 107123280} {"current_steps": 49645, "total_steps": 61300, "loss": 0.3417, "lr": 5.307621828068177e-06, "epoch": 8.098694942903752, "percentage": 80.99, "elapsed_time": "6:46:23", "remaining_time": "1:35:24", "throughput": 4393.74, "total_tokens": 107134800} {"current_steps": 49650, "total_steps": 61300, "loss": 0.3398, "lr": 5.303237484814169e-06, "epoch": 8.099510603588907, "percentage": 81.0, "elapsed_time": "6:46:25", "remaining_time": "1:35:21", "throughput": 4393.78, "total_tokens": 107145904} {"current_steps": 49655, "total_steps": 61300, "loss": 0.2907, "lr": 5.2988547382796735e-06, "epoch": 8.100326264274061, "percentage": 81.0, "elapsed_time": "6:46:28", "remaining_time": "1:35:19", "throughput": 4393.82, "total_tokens": 107156464} {"current_steps": 49660, "total_steps": 61300, "loss": 0.3392, "lr": 5.294473588819968e-06, "epoch": 8.101141924959217, "percentage": 81.01, "elapsed_time": "6:46:30", "remaining_time": "1:35:16", "throughput": 4393.86, "total_tokens": 107167824} {"current_steps": 49665, "total_steps": 61300, "loss": 0.3086, "lr": 5.2900940367902245e-06, "epoch": 8.101957585644373, "percentage": 81.02, "elapsed_time": "6:46:32", "remaining_time": "1:35:14", "throughput": 4393.9, "total_tokens": 107178928} {"current_steps": 49670, "total_steps": 61300, "loss": 0.33, "lr": 5.2857160825454635e-06, "epoch": 8.102773246329527, "percentage": 81.03, "elapsed_time": "6:46:35", "remaining_time": "1:35:12", "throughput": 4393.93, "total_tokens": 107191120} {"current_steps": 49675, "total_steps": 61300, "loss": 0.3559, "lr": 5.28133972644059e-06, "epoch": 8.103588907014682, "percentage": 81.04, "elapsed_time": "6:46:37", "remaining_time": "1:35:09", "throughput": 4393.97, "total_tokens": 107201872} {"current_steps": 49680, "total_steps": 61300, "loss": 0.3276, "lr": 5.276964968830367e-06, "epoch": 8.104404567699836, "percentage": 81.04, "elapsed_time": "6:46:39", "remaining_time": "1:35:07", "throughput": 4394.03, "total_tokens": 107214192} {"current_steps": 49685, "total_steps": 61300, "loss": 0.3504, "lr": 5.272591810069438e-06, "epoch": 8.105220228384992, "percentage": 81.05, "elapsed_time": "6:46:42", "remaining_time": "1:35:04", "throughput": 4394.07, "total_tokens": 107225616} {"current_steps": 49690, "total_steps": 61300, "loss": 0.3663, "lr": 5.268220250512315e-06, "epoch": 8.106035889070148, "percentage": 81.06, "elapsed_time": "6:46:44", "remaining_time": "1:35:02", "throughput": 4394.12, "total_tokens": 107236208} {"current_steps": 49695, "total_steps": 61300, "loss": 0.3094, "lr": 5.263850290513373e-06, "epoch": 8.106851549755302, "percentage": 81.07, "elapsed_time": "6:46:46", "remaining_time": "1:34:59", "throughput": 4394.16, "total_tokens": 107247632} {"current_steps": 49700, "total_steps": 61300, "loss": 0.3205, "lr": 5.259481930426869e-06, "epoch": 8.107667210440457, "percentage": 81.08, "elapsed_time": "6:46:49", "remaining_time": "1:34:57", "throughput": 4394.2, "total_tokens": 107258288} {"current_steps": 49705, "total_steps": 61300, "loss": 0.335, "lr": 5.2551151706069225e-06, "epoch": 8.108482871125611, "percentage": 81.08, "elapsed_time": "6:46:51", "remaining_time": "1:34:54", "throughput": 4394.24, "total_tokens": 107268944} {"current_steps": 49710, "total_steps": 61300, "loss": 0.3739, "lr": 5.250750011407521e-06, "epoch": 8.109298531810767, "percentage": 81.09, "elapsed_time": "6:46:53", "remaining_time": "1:34:52", "throughput": 4394.27, "total_tokens": 107279472} {"current_steps": 49715, "total_steps": 61300, "loss": 0.3451, "lr": 5.246386453182533e-06, "epoch": 8.11011419249592, "percentage": 81.1, "elapsed_time": "6:46:55", "remaining_time": "1:34:49", "throughput": 4394.32, "total_tokens": 107290064} {"current_steps": 49720, "total_steps": 61300, "loss": 0.3171, "lr": 5.242024496285683e-06, "epoch": 8.110929853181077, "percentage": 81.11, "elapsed_time": "6:46:57", "remaining_time": "1:34:47", "throughput": 4394.36, "total_tokens": 107300560} {"current_steps": 49725, "total_steps": 61300, "loss": 0.2984, "lr": 5.237664141070583e-06, "epoch": 8.111745513866232, "percentage": 81.12, "elapsed_time": "6:46:59", "remaining_time": "1:34:44", "throughput": 4394.38, "total_tokens": 107310512} {"current_steps": 49730, "total_steps": 61300, "loss": 0.323, "lr": 5.2333053878907e-06, "epoch": 8.112561174551386, "percentage": 81.13, "elapsed_time": "6:47:02", "remaining_time": "1:34:41", "throughput": 4394.42, "total_tokens": 107321296} {"current_steps": 49735, "total_steps": 61300, "loss": 0.351, "lr": 5.228948237099379e-06, "epoch": 8.113376835236542, "percentage": 81.13, "elapsed_time": "6:47:04", "remaining_time": "1:34:39", "throughput": 4394.46, "total_tokens": 107331920} {"current_steps": 49740, "total_steps": 61300, "loss": 0.3585, "lr": 5.224592689049832e-06, "epoch": 8.114192495921696, "percentage": 81.14, "elapsed_time": "6:47:06", "remaining_time": "1:34:36", "throughput": 4394.5, "total_tokens": 107342768} {"current_steps": 49745, "total_steps": 61300, "loss": 0.3413, "lr": 5.220238744095137e-06, "epoch": 8.115008156606851, "percentage": 81.15, "elapsed_time": "6:47:08", "remaining_time": "1:34:34", "throughput": 4394.53, "total_tokens": 107352304} {"current_steps": 49750, "total_steps": 61300, "loss": 0.3051, "lr": 5.215886402588255e-06, "epoch": 8.115823817292007, "percentage": 81.16, "elapsed_time": "6:47:10", "remaining_time": "1:34:31", "throughput": 4394.57, "total_tokens": 107362448} {"current_steps": 49755, "total_steps": 61300, "loss": 0.3047, "lr": 5.211535664882003e-06, "epoch": 8.116639477977161, "percentage": 81.17, "elapsed_time": "6:47:12", "remaining_time": "1:34:29", "throughput": 4394.6, "total_tokens": 107372368} {"current_steps": 49760, "total_steps": 61300, "loss": 0.3423, "lr": 5.207186531329075e-06, "epoch": 8.117455138662317, "percentage": 81.17, "elapsed_time": "6:47:15", "remaining_time": "1:34:26", "throughput": 4394.64, "total_tokens": 107383120} {"current_steps": 49765, "total_steps": 61300, "loss": 0.3527, "lr": 5.202839002282037e-06, "epoch": 8.11827079934747, "percentage": 81.18, "elapsed_time": "6:47:17", "remaining_time": "1:34:24", "throughput": 4394.68, "total_tokens": 107394576} {"current_steps": 49770, "total_steps": 61300, "loss": 0.3284, "lr": 5.198493078093311e-06, "epoch": 8.119086460032626, "percentage": 81.19, "elapsed_time": "6:47:19", "remaining_time": "1:34:21", "throughput": 4394.71, "total_tokens": 107404752} {"current_steps": 49775, "total_steps": 61300, "loss": 0.3301, "lr": 5.194148759115214e-06, "epoch": 8.119902120717782, "percentage": 81.2, "elapsed_time": "6:47:21", "remaining_time": "1:34:19", "throughput": 4394.74, "total_tokens": 107414288} {"current_steps": 49780, "total_steps": 61300, "loss": 0.3482, "lr": 5.189806045699913e-06, "epoch": 8.120717781402936, "percentage": 81.21, "elapsed_time": "6:47:23", "remaining_time": "1:34:16", "throughput": 4394.79, "total_tokens": 107425648} {"current_steps": 49785, "total_steps": 61300, "loss": 0.3153, "lr": 5.185464938199449e-06, "epoch": 8.121533442088092, "percentage": 81.22, "elapsed_time": "6:47:26", "remaining_time": "1:34:14", "throughput": 4394.84, "total_tokens": 107437936} {"current_steps": 49790, "total_steps": 61300, "loss": 0.2898, "lr": 5.181125436965739e-06, "epoch": 8.122349102773246, "percentage": 81.22, "elapsed_time": "6:47:28", "remaining_time": "1:34:11", "throughput": 4394.87, "total_tokens": 107448336} {"current_steps": 49795, "total_steps": 61300, "loss": 0.3573, "lr": 5.176787542350558e-06, "epoch": 8.123164763458401, "percentage": 81.23, "elapsed_time": "6:47:30", "remaining_time": "1:34:09", "throughput": 4394.91, "total_tokens": 107458416} {"current_steps": 49800, "total_steps": 61300, "loss": 0.3066, "lr": 5.172451254705559e-06, "epoch": 8.123980424143557, "percentage": 81.24, "elapsed_time": "6:47:33", "remaining_time": "1:34:06", "throughput": 4394.95, "total_tokens": 107469872} {"current_steps": 49805, "total_steps": 61300, "loss": 0.3419, "lr": 5.1681165743822676e-06, "epoch": 8.124796084828711, "percentage": 81.25, "elapsed_time": "6:47:35", "remaining_time": "1:34:04", "throughput": 4394.98, "total_tokens": 107479760} {"current_steps": 49810, "total_steps": 61300, "loss": 0.3278, "lr": 5.1637835017320726e-06, "epoch": 8.125611745513867, "percentage": 81.26, "elapsed_time": "6:47:37", "remaining_time": "1:34:01", "throughput": 4395.02, "total_tokens": 107490096} {"current_steps": 49815, "total_steps": 61300, "loss": 0.3469, "lr": 5.159452037106236e-06, "epoch": 8.12642740619902, "percentage": 81.26, "elapsed_time": "6:47:39", "remaining_time": "1:33:59", "throughput": 4395.05, "total_tokens": 107500368} {"current_steps": 49820, "total_steps": 61300, "loss": 0.3114, "lr": 5.155122180855884e-06, "epoch": 8.127243066884176, "percentage": 81.27, "elapsed_time": "6:47:41", "remaining_time": "1:33:56", "throughput": 4395.09, "total_tokens": 107511600} {"current_steps": 49825, "total_steps": 61300, "loss": 0.3421, "lr": 5.150793933332024e-06, "epoch": 8.12805872756933, "percentage": 81.28, "elapsed_time": "6:47:44", "remaining_time": "1:33:54", "throughput": 4395.13, "total_tokens": 107522672} {"current_steps": 49830, "total_steps": 61300, "loss": 0.3007, "lr": 5.146467294885518e-06, "epoch": 8.128874388254486, "percentage": 81.29, "elapsed_time": "6:47:46", "remaining_time": "1:33:51", "throughput": 4395.18, "total_tokens": 107534096} {"current_steps": 49835, "total_steps": 61300, "loss": 0.3623, "lr": 5.142142265867112e-06, "epoch": 8.129690048939642, "percentage": 81.3, "elapsed_time": "6:47:48", "remaining_time": "1:33:49", "throughput": 4395.21, "total_tokens": 107543472} {"current_steps": 49840, "total_steps": 61300, "loss": 0.3214, "lr": 5.137818846627409e-06, "epoch": 8.130505709624796, "percentage": 81.31, "elapsed_time": "6:47:50", "remaining_time": "1:33:46", "throughput": 4395.25, "total_tokens": 107554224} {"current_steps": 49845, "total_steps": 61300, "loss": 0.337, "lr": 5.13349703751689e-06, "epoch": 8.131321370309951, "percentage": 81.31, "elapsed_time": "6:47:52", "remaining_time": "1:33:44", "throughput": 4395.29, "total_tokens": 107564240} {"current_steps": 49850, "total_steps": 61300, "loss": 0.3513, "lr": 5.129176838885905e-06, "epoch": 8.132137030995105, "percentage": 81.32, "elapsed_time": "6:47:54", "remaining_time": "1:33:41", "throughput": 4395.32, "total_tokens": 107574800} {"current_steps": 49855, "total_steps": 61300, "loss": 0.3094, "lr": 5.124858251084666e-06, "epoch": 8.132952691680261, "percentage": 81.33, "elapsed_time": "6:47:57", "remaining_time": "1:33:39", "throughput": 4395.35, "total_tokens": 107585520} {"current_steps": 49860, "total_steps": 61300, "loss": 0.3378, "lr": 5.120541274463264e-06, "epoch": 8.133768352365417, "percentage": 81.34, "elapsed_time": "6:47:59", "remaining_time": "1:33:36", "throughput": 4395.38, "total_tokens": 107596112} {"current_steps": 49865, "total_steps": 61300, "loss": 0.3325, "lr": 5.116225909371649e-06, "epoch": 8.13458401305057, "percentage": 81.35, "elapsed_time": "6:48:01", "remaining_time": "1:33:34", "throughput": 4395.42, "total_tokens": 107607120} {"current_steps": 49870, "total_steps": 61300, "loss": 0.3673, "lr": 5.111912156159657e-06, "epoch": 8.135399673735726, "percentage": 81.35, "elapsed_time": "6:48:03", "remaining_time": "1:33:31", "throughput": 4395.46, "total_tokens": 107618000} {"current_steps": 49875, "total_steps": 61300, "loss": 0.3247, "lr": 5.107600015176975e-06, "epoch": 8.13621533442088, "percentage": 81.36, "elapsed_time": "6:48:06", "remaining_time": "1:33:29", "throughput": 4395.5, "total_tokens": 107629232} {"current_steps": 49880, "total_steps": 61300, "loss": 0.3519, "lr": 5.103289486773169e-06, "epoch": 8.137030995106036, "percentage": 81.37, "elapsed_time": "6:48:08", "remaining_time": "1:33:26", "throughput": 4395.54, "total_tokens": 107640784} {"current_steps": 49885, "total_steps": 61300, "loss": 0.3674, "lr": 5.098980571297673e-06, "epoch": 8.137846655791192, "percentage": 81.38, "elapsed_time": "6:48:10", "remaining_time": "1:33:24", "throughput": 4395.57, "total_tokens": 107650576} {"current_steps": 49890, "total_steps": 61300, "loss": 0.3407, "lr": 5.094673269099781e-06, "epoch": 8.138662316476346, "percentage": 81.39, "elapsed_time": "6:48:12", "remaining_time": "1:33:21", "throughput": 4395.61, "total_tokens": 107660368} {"current_steps": 49895, "total_steps": 61300, "loss": 0.388, "lr": 5.090367580528679e-06, "epoch": 8.139477977161501, "percentage": 81.39, "elapsed_time": "6:48:14", "remaining_time": "1:33:19", "throughput": 4395.64, "total_tokens": 107670096} {"current_steps": 49900, "total_steps": 61300, "loss": 0.3386, "lr": 5.086063505933403e-06, "epoch": 8.140293637846655, "percentage": 81.4, "elapsed_time": "6:48:16", "remaining_time": "1:33:16", "throughput": 4395.67, "total_tokens": 107680240} {"current_steps": 49905, "total_steps": 61300, "loss": 0.3402, "lr": 5.081761045662861e-06, "epoch": 8.141109298531811, "percentage": 81.41, "elapsed_time": "6:48:19", "remaining_time": "1:33:14", "throughput": 4395.71, "total_tokens": 107691504} {"current_steps": 49910, "total_steps": 61300, "loss": 0.3632, "lr": 5.077460200065834e-06, "epoch": 8.141924959216965, "percentage": 81.42, "elapsed_time": "6:48:21", "remaining_time": "1:33:11", "throughput": 4395.75, "total_tokens": 107701968} {"current_steps": 49915, "total_steps": 61300, "loss": 0.3589, "lr": 5.073160969490967e-06, "epoch": 8.14274061990212, "percentage": 81.43, "elapsed_time": "6:48:23", "remaining_time": "1:33:09", "throughput": 4395.78, "total_tokens": 107713136} {"current_steps": 49920, "total_steps": 61300, "loss": 0.3121, "lr": 5.068863354286779e-06, "epoch": 8.143556280587276, "percentage": 81.44, "elapsed_time": "6:48:26", "remaining_time": "1:33:06", "throughput": 4395.82, "total_tokens": 107724080} {"current_steps": 49925, "total_steps": 61300, "loss": 0.322, "lr": 5.064567354801658e-06, "epoch": 8.14437194127243, "percentage": 81.44, "elapsed_time": "6:48:28", "remaining_time": "1:33:04", "throughput": 4395.86, "total_tokens": 107735792} {"current_steps": 49930, "total_steps": 61300, "loss": 0.3483, "lr": 5.060272971383862e-06, "epoch": 8.145187601957586, "percentage": 81.45, "elapsed_time": "6:48:30", "remaining_time": "1:33:01", "throughput": 4395.9, "total_tokens": 107747280} {"current_steps": 49935, "total_steps": 61300, "loss": 0.3138, "lr": 5.055980204381508e-06, "epoch": 8.14600326264274, "percentage": 81.46, "elapsed_time": "6:48:33", "remaining_time": "1:32:59", "throughput": 4395.94, "total_tokens": 107758448} {"current_steps": 49940, "total_steps": 61300, "loss": 0.3253, "lr": 5.051689054142594e-06, "epoch": 8.146818923327896, "percentage": 81.47, "elapsed_time": "6:48:35", "remaining_time": "1:32:56", "throughput": 4395.99, "total_tokens": 107769712} {"current_steps": 49945, "total_steps": 61300, "loss": 0.3167, "lr": 5.047399521014984e-06, "epoch": 8.147634584013051, "percentage": 81.48, "elapsed_time": "6:48:37", "remaining_time": "1:32:54", "throughput": 4396.03, "total_tokens": 107780624} {"current_steps": 49950, "total_steps": 61300, "loss": 0.3635, "lr": 5.043111605346404e-06, "epoch": 8.148450244698205, "percentage": 81.48, "elapsed_time": "6:48:39", "remaining_time": "1:32:51", "throughput": 4396.06, "total_tokens": 107790800} {"current_steps": 49955, "total_steps": 61300, "loss": 0.3771, "lr": 5.03882530748446e-06, "epoch": 8.149265905383361, "percentage": 81.49, "elapsed_time": "6:48:42", "remaining_time": "1:32:49", "throughput": 4396.12, "total_tokens": 107802736} {"current_steps": 49960, "total_steps": 61300, "loss": 0.336, "lr": 5.034540627776618e-06, "epoch": 8.150081566068515, "percentage": 81.5, "elapsed_time": "6:48:44", "remaining_time": "1:32:46", "throughput": 4396.16, "total_tokens": 107813552} {"current_steps": 49965, "total_steps": 61300, "loss": 0.3371, "lr": 5.030257566570215e-06, "epoch": 8.15089722675367, "percentage": 81.51, "elapsed_time": "6:48:46", "remaining_time": "1:32:44", "throughput": 4396.2, "total_tokens": 107825264} {"current_steps": 49970, "total_steps": 61300, "loss": 0.337, "lr": 5.025976124212461e-06, "epoch": 8.151712887438826, "percentage": 81.52, "elapsed_time": "6:48:49", "remaining_time": "1:32:41", "throughput": 4396.25, "total_tokens": 107836880} {"current_steps": 49975, "total_steps": 61300, "loss": 0.3181, "lr": 5.0216963010504295e-06, "epoch": 8.15252854812398, "percentage": 81.53, "elapsed_time": "6:48:51", "remaining_time": "1:32:39", "throughput": 4396.29, "total_tokens": 107849392} {"current_steps": 49980, "total_steps": 61300, "loss": 0.3184, "lr": 5.017418097431059e-06, "epoch": 8.153344208809136, "percentage": 81.53, "elapsed_time": "6:48:54", "remaining_time": "1:32:36", "throughput": 4396.34, "total_tokens": 107860144} {"current_steps": 49985, "total_steps": 61300, "loss": 0.3374, "lr": 5.013141513701173e-06, "epoch": 8.15415986949429, "percentage": 81.54, "elapsed_time": "6:48:56", "remaining_time": "1:32:34", "throughput": 4396.37, "total_tokens": 107869520} {"current_steps": 49990, "total_steps": 61300, "loss": 0.3235, "lr": 5.008866550207447e-06, "epoch": 8.154975530179446, "percentage": 81.55, "elapsed_time": "6:48:58", "remaining_time": "1:32:31", "throughput": 4396.4, "total_tokens": 107879792} {"current_steps": 49995, "total_steps": 61300, "loss": 0.2962, "lr": 5.004593207296434e-06, "epoch": 8.1557911908646, "percentage": 81.56, "elapsed_time": "6:49:00", "remaining_time": "1:32:29", "throughput": 4396.44, "total_tokens": 107890672} {"current_steps": 50000, "total_steps": 61300, "loss": 0.3253, "lr": 5.000321485314552e-06, "epoch": 8.156606851549755, "percentage": 81.57, "elapsed_time": "6:49:02", "remaining_time": "1:32:26", "throughput": 4396.47, "total_tokens": 107900528} {"current_steps": 50005, "total_steps": 61300, "loss": 0.3283, "lr": 4.9960513846080885e-06, "epoch": 8.15742251223491, "percentage": 81.57, "elapsed_time": "6:49:04", "remaining_time": "1:32:24", "throughput": 4396.51, "total_tokens": 107911248} {"current_steps": 50010, "total_steps": 61300, "loss": 0.3399, "lr": 4.991782905523196e-06, "epoch": 8.158238172920065, "percentage": 81.58, "elapsed_time": "6:49:07", "remaining_time": "1:32:21", "throughput": 4396.54, "total_tokens": 107922800} {"current_steps": 50015, "total_steps": 61300, "loss": 0.3033, "lr": 4.987516048405905e-06, "epoch": 8.15905383360522, "percentage": 81.59, "elapsed_time": "6:49:09", "remaining_time": "1:32:19", "throughput": 4396.59, "total_tokens": 107934032} {"current_steps": 50020, "total_steps": 61300, "loss": 0.3107, "lr": 4.983250813602103e-06, "epoch": 8.159869494290374, "percentage": 81.6, "elapsed_time": "6:49:12", "remaining_time": "1:32:16", "throughput": 4396.62, "total_tokens": 107946128} {"current_steps": 50025, "total_steps": 61300, "loss": 0.351, "lr": 4.978987201457555e-06, "epoch": 8.16068515497553, "percentage": 81.61, "elapsed_time": "6:49:14", "remaining_time": "1:32:14", "throughput": 4396.66, "total_tokens": 107956912} {"current_steps": 50030, "total_steps": 61300, "loss": 0.3384, "lr": 4.97472521231789e-06, "epoch": 8.161500815660686, "percentage": 81.62, "elapsed_time": "6:49:16", "remaining_time": "1:32:11", "throughput": 4396.71, "total_tokens": 107968112} {"current_steps": 50035, "total_steps": 61300, "loss": 0.3388, "lr": 4.9704648465286e-06, "epoch": 8.16231647634584, "percentage": 81.62, "elapsed_time": "6:49:18", "remaining_time": "1:32:09", "throughput": 4396.74, "total_tokens": 107978352} {"current_steps": 50040, "total_steps": 61300, "loss": 0.3267, "lr": 4.966206104435064e-06, "epoch": 8.163132137030995, "percentage": 81.63, "elapsed_time": "6:49:21", "remaining_time": "1:32:06", "throughput": 4396.78, "total_tokens": 107989264} {"current_steps": 50045, "total_steps": 61300, "loss": 0.3388, "lr": 4.961948986382511e-06, "epoch": 8.16394779771615, "percentage": 81.64, "elapsed_time": "6:49:23", "remaining_time": "1:32:04", "throughput": 4396.82, "total_tokens": 107999888} {"current_steps": 50050, "total_steps": 61300, "loss": 0.3372, "lr": 4.957693492716048e-06, "epoch": 8.164763458401305, "percentage": 81.65, "elapsed_time": "6:49:25", "remaining_time": "1:32:01", "throughput": 4396.85, "total_tokens": 108009680} {"current_steps": 50055, "total_steps": 61300, "loss": 0.3431, "lr": 4.953439623780643e-06, "epoch": 8.16557911908646, "percentage": 81.66, "elapsed_time": "6:49:27", "remaining_time": "1:31:59", "throughput": 4396.88, "total_tokens": 108020368} {"current_steps": 50060, "total_steps": 61300, "loss": 0.3381, "lr": 4.949187379921136e-06, "epoch": 8.166394779771615, "percentage": 81.66, "elapsed_time": "6:49:29", "remaining_time": "1:31:56", "throughput": 4396.92, "total_tokens": 108030736} {"current_steps": 50065, "total_steps": 61300, "loss": 0.3272, "lr": 4.9449367614822384e-06, "epoch": 8.16721044045677, "percentage": 81.67, "elapsed_time": "6:49:31", "remaining_time": "1:31:54", "throughput": 4396.96, "total_tokens": 108041232} {"current_steps": 50070, "total_steps": 61300, "loss": 0.3395, "lr": 4.940687768808525e-06, "epoch": 8.168026101141924, "percentage": 81.68, "elapsed_time": "6:49:34", "remaining_time": "1:31:51", "throughput": 4397.01, "total_tokens": 108053264} {"current_steps": 50075, "total_steps": 61300, "loss": 0.3268, "lr": 4.936440402244441e-06, "epoch": 8.16884176182708, "percentage": 81.69, "elapsed_time": "6:49:36", "remaining_time": "1:31:49", "throughput": 4397.04, "total_tokens": 108063088} {"current_steps": 50080, "total_steps": 61300, "loss": 0.3312, "lr": 4.932194662134298e-06, "epoch": 8.169657422512234, "percentage": 81.7, "elapsed_time": "6:49:38", "remaining_time": "1:31:46", "throughput": 4397.08, "total_tokens": 108072688} {"current_steps": 50085, "total_steps": 61300, "loss": 0.3226, "lr": 4.92795054882228e-06, "epoch": 8.17047308319739, "percentage": 81.7, "elapsed_time": "6:49:40", "remaining_time": "1:31:44", "throughput": 4397.13, "total_tokens": 108085296} {"current_steps": 50090, "total_steps": 61300, "loss": 0.3237, "lr": 4.9237080626524294e-06, "epoch": 8.171288743882545, "percentage": 81.71, "elapsed_time": "6:49:43", "remaining_time": "1:31:41", "throughput": 4397.18, "total_tokens": 108096816} {"current_steps": 50095, "total_steps": 61300, "loss": 0.3342, "lr": 4.919467203968675e-06, "epoch": 8.1721044045677, "percentage": 81.72, "elapsed_time": "6:49:45", "remaining_time": "1:31:39", "throughput": 4397.21, "total_tokens": 108107280} {"current_steps": 50100, "total_steps": 61300, "loss": 0.3387, "lr": 4.915227973114797e-06, "epoch": 8.172920065252855, "percentage": 81.73, "elapsed_time": "6:49:47", "remaining_time": "1:31:36", "throughput": 4397.24, "total_tokens": 108117552} {"current_steps": 50105, "total_steps": 61300, "loss": 0.3047, "lr": 4.910990370434449e-06, "epoch": 8.173735725938009, "percentage": 81.74, "elapsed_time": "6:49:49", "remaining_time": "1:31:34", "throughput": 4397.29, "total_tokens": 108129264} {"current_steps": 50110, "total_steps": 61300, "loss": 0.3339, "lr": 4.906754396271152e-06, "epoch": 8.174551386623165, "percentage": 81.75, "elapsed_time": "6:49:52", "remaining_time": "1:31:31", "throughput": 4397.32, "total_tokens": 108139472} {"current_steps": 50115, "total_steps": 61300, "loss": 0.3576, "lr": 4.902520050968293e-06, "epoch": 8.17536704730832, "percentage": 81.75, "elapsed_time": "6:49:54", "remaining_time": "1:31:29", "throughput": 4397.36, "total_tokens": 108149712} {"current_steps": 50120, "total_steps": 61300, "loss": 0.3406, "lr": 4.898287334869134e-06, "epoch": 8.176182707993474, "percentage": 81.76, "elapsed_time": "6:49:56", "remaining_time": "1:31:26", "throughput": 4397.39, "total_tokens": 108160464} {"current_steps": 50125, "total_steps": 61300, "loss": 0.3369, "lr": 4.8940562483168005e-06, "epoch": 8.17699836867863, "percentage": 81.77, "elapsed_time": "6:49:58", "remaining_time": "1:31:24", "throughput": 4397.43, "total_tokens": 108171312} {"current_steps": 50130, "total_steps": 61300, "loss": 0.3035, "lr": 4.889826791654281e-06, "epoch": 8.177814029363784, "percentage": 81.78, "elapsed_time": "6:50:00", "remaining_time": "1:31:21", "throughput": 4397.47, "total_tokens": 108181616} {"current_steps": 50135, "total_steps": 61300, "loss": 0.316, "lr": 4.8855989652244415e-06, "epoch": 8.17862969004894, "percentage": 81.79, "elapsed_time": "6:50:02", "remaining_time": "1:31:19", "throughput": 4397.51, "total_tokens": 108191792} {"current_steps": 50140, "total_steps": 61300, "loss": 0.3257, "lr": 4.8813727693700104e-06, "epoch": 8.179445350734095, "percentage": 81.79, "elapsed_time": "6:50:05", "remaining_time": "1:31:16", "throughput": 4397.55, "total_tokens": 108203216} {"current_steps": 50145, "total_steps": 61300, "loss": 0.3389, "lr": 4.877148204433582e-06, "epoch": 8.18026101141925, "percentage": 81.8, "elapsed_time": "6:50:07", "remaining_time": "1:31:14", "throughput": 4397.59, "total_tokens": 108214000} {"current_steps": 50150, "total_steps": 61300, "loss": 0.2982, "lr": 4.872925270757623e-06, "epoch": 8.181076672104405, "percentage": 81.81, "elapsed_time": "6:50:09", "remaining_time": "1:31:11", "throughput": 4397.63, "total_tokens": 108224528} {"current_steps": 50155, "total_steps": 61300, "loss": 0.3212, "lr": 4.868703968684466e-06, "epoch": 8.181892332789559, "percentage": 81.82, "elapsed_time": "6:50:11", "remaining_time": "1:31:09", "throughput": 4397.67, "total_tokens": 108235088} {"current_steps": 50160, "total_steps": 61300, "loss": 0.324, "lr": 4.86448429855631e-06, "epoch": 8.182707993474715, "percentage": 81.83, "elapsed_time": "6:50:14", "remaining_time": "1:31:06", "throughput": 4397.7, "total_tokens": 108245616} {"current_steps": 50165, "total_steps": 61300, "loss": 0.3178, "lr": 4.860266260715221e-06, "epoch": 8.18352365415987, "percentage": 81.84, "elapsed_time": "6:50:16", "remaining_time": "1:31:04", "throughput": 4397.73, "total_tokens": 108256144} {"current_steps": 50170, "total_steps": 61300, "loss": 0.2926, "lr": 4.856049855503139e-06, "epoch": 8.184339314845024, "percentage": 81.84, "elapsed_time": "6:50:18", "remaining_time": "1:31:01", "throughput": 4397.77, "total_tokens": 108267248} {"current_steps": 50175, "total_steps": 61300, "loss": 0.3417, "lr": 4.8518350832618655e-06, "epoch": 8.18515497553018, "percentage": 81.85, "elapsed_time": "6:50:20", "remaining_time": "1:30:59", "throughput": 4397.81, "total_tokens": 108278128} {"current_steps": 50180, "total_steps": 61300, "loss": 0.3346, "lr": 4.847621944333064e-06, "epoch": 8.185970636215334, "percentage": 81.86, "elapsed_time": "6:50:23", "remaining_time": "1:30:56", "throughput": 4397.86, "total_tokens": 108290352} {"current_steps": 50185, "total_steps": 61300, "loss": 0.3367, "lr": 4.8434104390582855e-06, "epoch": 8.18678629690049, "percentage": 81.87, "elapsed_time": "6:50:25", "remaining_time": "1:30:54", "throughput": 4397.9, "total_tokens": 108301776} {"current_steps": 50190, "total_steps": 61300, "loss": 0.3636, "lr": 4.839200567778932e-06, "epoch": 8.187601957585644, "percentage": 81.88, "elapsed_time": "6:50:27", "remaining_time": "1:30:51", "throughput": 4397.94, "total_tokens": 108312208} {"current_steps": 50195, "total_steps": 61300, "loss": 0.3542, "lr": 4.834992330836274e-06, "epoch": 8.1884176182708, "percentage": 81.88, "elapsed_time": "6:50:30", "remaining_time": "1:30:49", "throughput": 4397.97, "total_tokens": 108322480} {"current_steps": 50200, "total_steps": 61300, "loss": 0.3081, "lr": 4.8307857285714545e-06, "epoch": 8.189233278955955, "percentage": 81.89, "elapsed_time": "6:50:32", "remaining_time": "1:30:46", "throughput": 4398.02, "total_tokens": 108333392} {"current_steps": 50205, "total_steps": 61300, "loss": 0.3174, "lr": 4.826580761325475e-06, "epoch": 8.190048939641109, "percentage": 81.9, "elapsed_time": "6:50:34", "remaining_time": "1:30:44", "throughput": 4398.05, "total_tokens": 108343856} {"current_steps": 50210, "total_steps": 61300, "loss": 0.3401, "lr": 4.822377429439223e-06, "epoch": 8.190864600326265, "percentage": 81.91, "elapsed_time": "6:50:37", "remaining_time": "1:30:41", "throughput": 4398.09, "total_tokens": 108355728} {"current_steps": 50215, "total_steps": 61300, "loss": 0.3362, "lr": 4.818175733253438e-06, "epoch": 8.191680261011419, "percentage": 81.92, "elapsed_time": "6:50:39", "remaining_time": "1:30:39", "throughput": 4398.13, "total_tokens": 108366736} {"current_steps": 50220, "total_steps": 61300, "loss": 0.3605, "lr": 4.813975673108731e-06, "epoch": 8.192495921696574, "percentage": 81.92, "elapsed_time": "6:50:41", "remaining_time": "1:30:36", "throughput": 4398.16, "total_tokens": 108376912} {"current_steps": 50225, "total_steps": 61300, "loss": 0.3203, "lr": 4.809777249345576e-06, "epoch": 8.19331158238173, "percentage": 81.93, "elapsed_time": "6:50:43", "remaining_time": "1:30:34", "throughput": 4398.19, "total_tokens": 108387440} {"current_steps": 50230, "total_steps": 61300, "loss": 0.3147, "lr": 4.8055804623043235e-06, "epoch": 8.194127243066884, "percentage": 81.94, "elapsed_time": "6:50:45", "remaining_time": "1:30:31", "throughput": 4398.22, "total_tokens": 108397232} {"current_steps": 50235, "total_steps": 61300, "loss": 0.335, "lr": 4.801385312325182e-06, "epoch": 8.19494290375204, "percentage": 81.95, "elapsed_time": "6:50:47", "remaining_time": "1:30:29", "throughput": 4398.26, "total_tokens": 108408016} {"current_steps": 50240, "total_steps": 61300, "loss": 0.344, "lr": 4.7971917997482376e-06, "epoch": 8.195758564437194, "percentage": 81.96, "elapsed_time": "6:50:50", "remaining_time": "1:30:26", "throughput": 4398.29, "total_tokens": 108419024} {"current_steps": 50245, "total_steps": 61300, "loss": 0.3204, "lr": 4.79299992491343e-06, "epoch": 8.19657422512235, "percentage": 81.97, "elapsed_time": "6:50:52", "remaining_time": "1:30:24", "throughput": 4398.34, "total_tokens": 108430320} {"current_steps": 50250, "total_steps": 61300, "loss": 0.3381, "lr": 4.788809688160581e-06, "epoch": 8.197389885807505, "percentage": 81.97, "elapsed_time": "6:50:54", "remaining_time": "1:30:21", "throughput": 4398.37, "total_tokens": 108441104} {"current_steps": 50255, "total_steps": 61300, "loss": 0.2933, "lr": 4.784621089829366e-06, "epoch": 8.198205546492659, "percentage": 81.98, "elapsed_time": "6:50:57", "remaining_time": "1:30:19", "throughput": 4398.41, "total_tokens": 108452656} {"current_steps": 50260, "total_steps": 61300, "loss": 0.3784, "lr": 4.780434130259339e-06, "epoch": 8.199021207177815, "percentage": 81.99, "elapsed_time": "6:50:59", "remaining_time": "1:30:16", "throughput": 4398.44, "total_tokens": 108462992} {"current_steps": 50265, "total_steps": 61300, "loss": 0.3146, "lr": 4.7762488097899154e-06, "epoch": 8.199836867862969, "percentage": 82.0, "elapsed_time": "6:51:01", "remaining_time": "1:30:14", "throughput": 4398.47, "total_tokens": 108473744} {"current_steps": 50270, "total_steps": 61300, "loss": 0.3007, "lr": 4.772065128760375e-06, "epoch": 8.200652528548124, "percentage": 82.01, "elapsed_time": "6:51:04", "remaining_time": "1:30:11", "throughput": 4398.5, "total_tokens": 108485136} {"current_steps": 50275, "total_steps": 61300, "loss": 0.3164, "lr": 4.767883087509872e-06, "epoch": 8.201468189233278, "percentage": 82.01, "elapsed_time": "6:51:06", "remaining_time": "1:30:09", "throughput": 4398.55, "total_tokens": 108496720} {"current_steps": 50280, "total_steps": 61300, "loss": 0.3211, "lr": 4.763702686377425e-06, "epoch": 8.202283849918434, "percentage": 82.02, "elapsed_time": "6:51:08", "remaining_time": "1:30:06", "throughput": 4398.59, "total_tokens": 108508016} {"current_steps": 50285, "total_steps": 61300, "loss": 0.3367, "lr": 4.759523925701914e-06, "epoch": 8.20309951060359, "percentage": 82.03, "elapsed_time": "6:51:10", "remaining_time": "1:30:04", "throughput": 4398.62, "total_tokens": 108517872} {"current_steps": 50290, "total_steps": 61300, "loss": 0.3304, "lr": 4.7553468058220915e-06, "epoch": 8.203915171288743, "percentage": 82.04, "elapsed_time": "6:51:12", "remaining_time": "1:30:01", "throughput": 4398.66, "total_tokens": 108527280} {"current_steps": 50295, "total_steps": 61300, "loss": 0.3364, "lr": 4.751171327076579e-06, "epoch": 8.2047308319739, "percentage": 82.05, "elapsed_time": "6:51:15", "remaining_time": "1:29:59", "throughput": 4398.69, "total_tokens": 108538192} {"current_steps": 50300, "total_steps": 61300, "loss": 0.351, "lr": 4.746997489803853e-06, "epoch": 8.205546492659053, "percentage": 82.06, "elapsed_time": "6:51:16", "remaining_time": "1:29:56", "throughput": 4398.71, "total_tokens": 108546960} {"current_steps": 50305, "total_steps": 61300, "loss": 0.3587, "lr": 4.7428252943422794e-06, "epoch": 8.206362153344209, "percentage": 82.06, "elapsed_time": "6:51:19", "remaining_time": "1:29:54", "throughput": 4398.75, "total_tokens": 108556912} {"current_steps": 50310, "total_steps": 61300, "loss": 0.3371, "lr": 4.738654741030074e-06, "epoch": 8.207177814029365, "percentage": 82.07, "elapsed_time": "6:51:21", "remaining_time": "1:29:51", "throughput": 4398.78, "total_tokens": 108568144} {"current_steps": 50315, "total_steps": 61300, "loss": 0.2965, "lr": 4.734485830205318e-06, "epoch": 8.207993474714518, "percentage": 82.08, "elapsed_time": "6:51:23", "remaining_time": "1:29:49", "throughput": 4398.81, "total_tokens": 108578160} {"current_steps": 50320, "total_steps": 61300, "loss": 0.3183, "lr": 4.730318562205965e-06, "epoch": 8.208809135399674, "percentage": 82.09, "elapsed_time": "6:51:25", "remaining_time": "1:29:46", "throughput": 4398.86, "total_tokens": 108589296} {"current_steps": 50325, "total_steps": 61300, "loss": 0.3277, "lr": 4.7261529373698404e-06, "epoch": 8.209624796084828, "percentage": 82.1, "elapsed_time": "6:51:28", "remaining_time": "1:29:44", "throughput": 4398.89, "total_tokens": 108600240} {"current_steps": 50330, "total_steps": 61300, "loss": 0.3259, "lr": 4.721988956034626e-06, "epoch": 8.210440456769984, "percentage": 82.1, "elapsed_time": "6:51:30", "remaining_time": "1:29:41", "throughput": 4398.93, "total_tokens": 108611056} {"current_steps": 50335, "total_steps": 61300, "loss": 0.3471, "lr": 4.717826618537874e-06, "epoch": 8.21125611745514, "percentage": 82.11, "elapsed_time": "6:51:32", "remaining_time": "1:29:38", "throughput": 4398.96, "total_tokens": 108620400} {"current_steps": 50340, "total_steps": 61300, "loss": 0.3036, "lr": 4.713665925217009e-06, "epoch": 8.212071778140293, "percentage": 82.12, "elapsed_time": "6:51:34", "remaining_time": "1:29:36", "throughput": 4399.0, "total_tokens": 108632432} {"current_steps": 50345, "total_steps": 61300, "loss": 0.3027, "lr": 4.709506876409317e-06, "epoch": 8.21288743882545, "percentage": 82.13, "elapsed_time": "6:51:36", "remaining_time": "1:29:34", "throughput": 4399.04, "total_tokens": 108642896} {"current_steps": 50350, "total_steps": 61300, "loss": 0.336, "lr": 4.705349472451942e-06, "epoch": 8.213703099510603, "percentage": 82.14, "elapsed_time": "6:51:39", "remaining_time": "1:29:31", "throughput": 4399.08, "total_tokens": 108652816} {"current_steps": 50355, "total_steps": 61300, "loss": 0.3146, "lr": 4.70119371368192e-06, "epoch": 8.214518760195759, "percentage": 82.15, "elapsed_time": "6:51:41", "remaining_time": "1:29:28", "throughput": 4399.11, "total_tokens": 108663792} {"current_steps": 50360, "total_steps": 61300, "loss": 0.3422, "lr": 4.697039600436132e-06, "epoch": 8.215334420880913, "percentage": 82.15, "elapsed_time": "6:51:43", "remaining_time": "1:29:26", "throughput": 4399.15, "total_tokens": 108674896} {"current_steps": 50365, "total_steps": 61300, "loss": 0.3618, "lr": 4.6928871330513296e-06, "epoch": 8.216150081566068, "percentage": 82.16, "elapsed_time": "6:51:45", "remaining_time": "1:29:24", "throughput": 4399.19, "total_tokens": 108685584} {"current_steps": 50370, "total_steps": 61300, "loss": 0.3314, "lr": 4.6887363118641335e-06, "epoch": 8.216965742251224, "percentage": 82.17, "elapsed_time": "6:51:48", "remaining_time": "1:29:21", "throughput": 4399.22, "total_tokens": 108696560} {"current_steps": 50375, "total_steps": 61300, "loss": 0.2986, "lr": 4.68458713721103e-06, "epoch": 8.217781402936378, "percentage": 82.18, "elapsed_time": "6:51:50", "remaining_time": "1:29:18", "throughput": 4399.26, "total_tokens": 108706512} {"current_steps": 50380, "total_steps": 61300, "loss": 0.3279, "lr": 4.680439609428372e-06, "epoch": 8.218597063621534, "percentage": 82.19, "elapsed_time": "6:51:52", "remaining_time": "1:29:16", "throughput": 4399.3, "total_tokens": 108717808} {"current_steps": 50385, "total_steps": 61300, "loss": 0.3576, "lr": 4.676293728852379e-06, "epoch": 8.219412724306688, "percentage": 82.19, "elapsed_time": "6:51:54", "remaining_time": "1:29:14", "throughput": 4399.33, "total_tokens": 108729040} {"current_steps": 50390, "total_steps": 61300, "loss": 0.3232, "lr": 4.6721494958191395e-06, "epoch": 8.220228384991843, "percentage": 82.2, "elapsed_time": "6:51:57", "remaining_time": "1:29:11", "throughput": 4399.37, "total_tokens": 108739536} {"current_steps": 50395, "total_steps": 61300, "loss": 0.3539, "lr": 4.6680069106646014e-06, "epoch": 8.221044045676999, "percentage": 82.21, "elapsed_time": "6:51:59", "remaining_time": "1:29:09", "throughput": 4399.41, "total_tokens": 108750640} {"current_steps": 50400, "total_steps": 61300, "loss": 0.374, "lr": 4.663865973724591e-06, "epoch": 8.221859706362153, "percentage": 82.22, "elapsed_time": "6:52:01", "remaining_time": "1:29:06", "throughput": 4399.44, "total_tokens": 108760368} {"current_steps": 50405, "total_steps": 61300, "loss": 0.313, "lr": 4.659726685334786e-06, "epoch": 8.222675367047309, "percentage": 82.23, "elapsed_time": "6:52:03", "remaining_time": "1:29:04", "throughput": 4399.48, "total_tokens": 108772336} {"current_steps": 50410, "total_steps": 61300, "loss": 0.3417, "lr": 4.655589045830735e-06, "epoch": 8.223491027732463, "percentage": 82.23, "elapsed_time": "6:52:06", "remaining_time": "1:29:01", "throughput": 4399.52, "total_tokens": 108782800} {"current_steps": 50415, "total_steps": 61300, "loss": 0.2954, "lr": 4.651453055547872e-06, "epoch": 8.224306688417618, "percentage": 82.24, "elapsed_time": "6:52:08", "remaining_time": "1:28:59", "throughput": 4399.55, "total_tokens": 108794000} {"current_steps": 50420, "total_steps": 61300, "loss": 0.3424, "lr": 4.647318714821469e-06, "epoch": 8.225122349102774, "percentage": 82.25, "elapsed_time": "6:52:10", "remaining_time": "1:28:56", "throughput": 4399.6, "total_tokens": 108805392} {"current_steps": 50425, "total_steps": 61300, "loss": 0.3224, "lr": 4.643186023986681e-06, "epoch": 8.225938009787928, "percentage": 82.26, "elapsed_time": "6:52:13", "remaining_time": "1:28:54", "throughput": 4399.65, "total_tokens": 108817616} {"current_steps": 50430, "total_steps": 61300, "loss": 0.3359, "lr": 4.639054983378521e-06, "epoch": 8.226753670473084, "percentage": 82.27, "elapsed_time": "6:52:15", "remaining_time": "1:28:51", "throughput": 4399.7, "total_tokens": 108829360} {"current_steps": 50435, "total_steps": 61300, "loss": 0.3233, "lr": 4.634925593331876e-06, "epoch": 8.227569331158238, "percentage": 82.28, "elapsed_time": "6:52:17", "remaining_time": "1:28:49", "throughput": 4399.73, "total_tokens": 108839696} {"current_steps": 50440, "total_steps": 61300, "loss": 0.3142, "lr": 4.630797854181495e-06, "epoch": 8.228384991843393, "percentage": 82.28, "elapsed_time": "6:52:20", "remaining_time": "1:28:46", "throughput": 4399.77, "total_tokens": 108851184} {"current_steps": 50445, "total_steps": 61300, "loss": 0.3413, "lr": 4.626671766261992e-06, "epoch": 8.229200652528547, "percentage": 82.29, "elapsed_time": "6:52:22", "remaining_time": "1:28:44", "throughput": 4399.81, "total_tokens": 108861744} {"current_steps": 50450, "total_steps": 61300, "loss": 0.3672, "lr": 4.622547329907848e-06, "epoch": 8.230016313213703, "percentage": 82.3, "elapsed_time": "6:52:24", "remaining_time": "1:28:41", "throughput": 4399.85, "total_tokens": 108872816} {"current_steps": 50455, "total_steps": 61300, "loss": 0.3247, "lr": 4.618424545453409e-06, "epoch": 8.230831973898859, "percentage": 82.31, "elapsed_time": "6:52:27", "remaining_time": "1:28:39", "throughput": 4399.9, "total_tokens": 108884688} {"current_steps": 50460, "total_steps": 61300, "loss": 0.312, "lr": 4.6143034132328955e-06, "epoch": 8.231647634584013, "percentage": 82.32, "elapsed_time": "6:52:29", "remaining_time": "1:28:36", "throughput": 4399.94, "total_tokens": 108896208} {"current_steps": 50465, "total_steps": 61300, "loss": 0.3203, "lr": 4.610183933580381e-06, "epoch": 8.232463295269168, "percentage": 82.32, "elapsed_time": "6:52:31", "remaining_time": "1:28:34", "throughput": 4399.98, "total_tokens": 108907536} {"current_steps": 50470, "total_steps": 61300, "loss": 0.3409, "lr": 4.606066106829815e-06, "epoch": 8.233278955954322, "percentage": 82.33, "elapsed_time": "6:52:33", "remaining_time": "1:28:31", "throughput": 4400.02, "total_tokens": 108917360} {"current_steps": 50475, "total_steps": 61300, "loss": 0.3329, "lr": 4.601949933315009e-06, "epoch": 8.234094616639478, "percentage": 82.34, "elapsed_time": "6:52:36", "remaining_time": "1:28:29", "throughput": 4400.06, "total_tokens": 108927952} {"current_steps": 50480, "total_steps": 61300, "loss": 0.3115, "lr": 4.597835413369639e-06, "epoch": 8.234910277324634, "percentage": 82.35, "elapsed_time": "6:52:38", "remaining_time": "1:28:26", "throughput": 4400.1, "total_tokens": 108939248} {"current_steps": 50485, "total_steps": 61300, "loss": 0.3528, "lr": 4.593722547327248e-06, "epoch": 8.235725938009788, "percentage": 82.36, "elapsed_time": "6:52:40", "remaining_time": "1:28:24", "throughput": 4400.15, "total_tokens": 108950832} {"current_steps": 50490, "total_steps": 61300, "loss": 0.3226, "lr": 4.589611335521249e-06, "epoch": 8.236541598694943, "percentage": 82.37, "elapsed_time": "6:52:42", "remaining_time": "1:28:21", "throughput": 4400.19, "total_tokens": 108961488} {"current_steps": 50495, "total_steps": 61300, "loss": 0.3553, "lr": 4.585501778284912e-06, "epoch": 8.237357259380097, "percentage": 82.37, "elapsed_time": "6:52:45", "remaining_time": "1:28:19", "throughput": 4400.22, "total_tokens": 108971888} {"current_steps": 50500, "total_steps": 61300, "loss": 0.3634, "lr": 4.581393875951387e-06, "epoch": 8.238172920065253, "percentage": 82.38, "elapsed_time": "6:52:47", "remaining_time": "1:28:16", "throughput": 4400.27, "total_tokens": 108983856} {"current_steps": 50505, "total_steps": 61300, "loss": 0.3336, "lr": 4.577287628853677e-06, "epoch": 8.238988580750409, "percentage": 82.39, "elapsed_time": "6:52:49", "remaining_time": "1:28:14", "throughput": 4400.31, "total_tokens": 108995408} {"current_steps": 50510, "total_steps": 61300, "loss": 0.3243, "lr": 4.5731830373246574e-06, "epoch": 8.239804241435563, "percentage": 82.4, "elapsed_time": "6:52:52", "remaining_time": "1:28:11", "throughput": 4400.35, "total_tokens": 109006736} {"current_steps": 50515, "total_steps": 61300, "loss": 0.3091, "lr": 4.5690801016970655e-06, "epoch": 8.240619902120718, "percentage": 82.41, "elapsed_time": "6:52:54", "remaining_time": "1:28:09", "throughput": 4400.38, "total_tokens": 109016528} {"current_steps": 50520, "total_steps": 61300, "loss": 0.3421, "lr": 4.564978822303498e-06, "epoch": 8.241435562805872, "percentage": 82.41, "elapsed_time": "6:52:56", "remaining_time": "1:28:06", "throughput": 4400.43, "total_tokens": 109028688} {"current_steps": 50525, "total_steps": 61300, "loss": 0.3551, "lr": 4.560879199476442e-06, "epoch": 8.242251223491028, "percentage": 82.42, "elapsed_time": "6:52:59", "remaining_time": "1:28:04", "throughput": 4400.47, "total_tokens": 109039792} {"current_steps": 50530, "total_steps": 61300, "loss": 0.3191, "lr": 4.5567812335482244e-06, "epoch": 8.243066884176184, "percentage": 82.43, "elapsed_time": "6:53:01", "remaining_time": "1:28:01", "throughput": 4400.5, "total_tokens": 109050416} {"current_steps": 50535, "total_steps": 61300, "loss": 0.356, "lr": 4.5526849248510475e-06, "epoch": 8.243882544861338, "percentage": 82.44, "elapsed_time": "6:53:03", "remaining_time": "1:27:59", "throughput": 4400.54, "total_tokens": 109060816} {"current_steps": 50540, "total_steps": 61300, "loss": 0.3146, "lr": 4.548590273716979e-06, "epoch": 8.244698205546493, "percentage": 82.45, "elapsed_time": "6:53:05", "remaining_time": "1:27:56", "throughput": 4400.58, "total_tokens": 109071920} {"current_steps": 50545, "total_steps": 61300, "loss": 0.3155, "lr": 4.5444972804779525e-06, "epoch": 8.245513866231647, "percentage": 82.46, "elapsed_time": "6:53:07", "remaining_time": "1:27:54", "throughput": 4400.63, "total_tokens": 109082512} {"current_steps": 50550, "total_steps": 61300, "loss": 0.3737, "lr": 4.540405945465767e-06, "epoch": 8.246329526916803, "percentage": 82.46, "elapsed_time": "6:53:10", "remaining_time": "1:27:51", "throughput": 4400.67, "total_tokens": 109093744} {"current_steps": 50555, "total_steps": 61300, "loss": 0.2955, "lr": 4.536316269012086e-06, "epoch": 8.247145187601957, "percentage": 82.47, "elapsed_time": "6:53:12", "remaining_time": "1:27:49", "throughput": 4400.71, "total_tokens": 109104368} {"current_steps": 50560, "total_steps": 61300, "loss": 0.3605, "lr": 4.532228251448439e-06, "epoch": 8.247960848287113, "percentage": 82.48, "elapsed_time": "6:53:14", "remaining_time": "1:27:46", "throughput": 4400.75, "total_tokens": 109115920} {"current_steps": 50565, "total_steps": 61300, "loss": 0.3227, "lr": 4.528141893106225e-06, "epoch": 8.248776508972268, "percentage": 82.49, "elapsed_time": "6:53:17", "remaining_time": "1:27:44", "throughput": 4400.79, "total_tokens": 109127088} {"current_steps": 50570, "total_steps": 61300, "loss": 0.3298, "lr": 4.5240571943167e-06, "epoch": 8.249592169657422, "percentage": 82.5, "elapsed_time": "6:53:19", "remaining_time": "1:27:41", "throughput": 4400.84, "total_tokens": 109138736} {"current_steps": 50575, "total_steps": 61300, "loss": 0.3264, "lr": 4.519974155410992e-06, "epoch": 8.250407830342578, "percentage": 82.5, "elapsed_time": "6:53:21", "remaining_time": "1:27:39", "throughput": 4400.87, "total_tokens": 109149488} {"current_steps": 50580, "total_steps": 61300, "loss": 0.3611, "lr": 4.515892776720096e-06, "epoch": 8.251223491027732, "percentage": 82.51, "elapsed_time": "6:53:24", "remaining_time": "1:27:37", "throughput": 4400.92, "total_tokens": 109160656} {"current_steps": 50585, "total_steps": 61300, "loss": 0.3659, "lr": 4.5118130585748655e-06, "epoch": 8.252039151712887, "percentage": 82.52, "elapsed_time": "6:53:26", "remaining_time": "1:27:34", "throughput": 4400.96, "total_tokens": 109171312} {"current_steps": 50590, "total_steps": 61300, "loss": 0.2937, "lr": 4.507735001306024e-06, "epoch": 8.252854812398043, "percentage": 82.53, "elapsed_time": "6:53:28", "remaining_time": "1:27:32", "throughput": 4401.0, "total_tokens": 109182384} {"current_steps": 50595, "total_steps": 61300, "loss": 0.3162, "lr": 4.503658605244163e-06, "epoch": 8.253670473083197, "percentage": 82.54, "elapsed_time": "6:53:30", "remaining_time": "1:27:29", "throughput": 4401.03, "total_tokens": 109191792} {"current_steps": 50600, "total_steps": 61300, "loss": 0.3394, "lr": 4.499583870719728e-06, "epoch": 8.254486133768353, "percentage": 82.54, "elapsed_time": "6:53:32", "remaining_time": "1:27:26", "throughput": 4401.07, "total_tokens": 109202960} {"current_steps": 50605, "total_steps": 61300, "loss": 0.3333, "lr": 4.495510798063046e-06, "epoch": 8.255301794453507, "percentage": 82.55, "elapsed_time": "6:53:35", "remaining_time": "1:27:24", "throughput": 4401.11, "total_tokens": 109214288} {"current_steps": 50610, "total_steps": 61300, "loss": 0.3548, "lr": 4.4914393876042984e-06, "epoch": 8.256117455138662, "percentage": 82.56, "elapsed_time": "6:53:37", "remaining_time": "1:27:22", "throughput": 4401.15, "total_tokens": 109225328} {"current_steps": 50615, "total_steps": 61300, "loss": 0.3359, "lr": 4.48736963967353e-06, "epoch": 8.256933115823816, "percentage": 82.57, "elapsed_time": "6:53:39", "remaining_time": "1:27:19", "throughput": 4401.19, "total_tokens": 109236016} {"current_steps": 50620, "total_steps": 61300, "loss": 0.3007, "lr": 4.483301554600655e-06, "epoch": 8.257748776508972, "percentage": 82.58, "elapsed_time": "6:53:42", "remaining_time": "1:27:17", "throughput": 4401.23, "total_tokens": 109247344} {"current_steps": 50625, "total_steps": 61300, "loss": 0.31, "lr": 4.479235132715462e-06, "epoch": 8.258564437194128, "percentage": 82.59, "elapsed_time": "6:53:44", "remaining_time": "1:27:14", "throughput": 4401.27, "total_tokens": 109258864} {"current_steps": 50630, "total_steps": 61300, "loss": 0.3228, "lr": 4.4751703743475895e-06, "epoch": 8.259380097879282, "percentage": 82.59, "elapsed_time": "6:53:46", "remaining_time": "1:27:12", "throughput": 4401.31, "total_tokens": 109270192} {"current_steps": 50635, "total_steps": 61300, "loss": 0.3092, "lr": 4.47110727982655e-06, "epoch": 8.260195758564437, "percentage": 82.6, "elapsed_time": "6:53:48", "remaining_time": "1:27:09", "throughput": 4401.34, "total_tokens": 109280016} {"current_steps": 50640, "total_steps": 61300, "loss": 0.356, "lr": 4.467045849481716e-06, "epoch": 8.261011419249591, "percentage": 82.61, "elapsed_time": "6:53:50", "remaining_time": "1:27:07", "throughput": 4401.38, "total_tokens": 109290256} {"current_steps": 50645, "total_steps": 61300, "loss": 0.3315, "lr": 4.462986083642329e-06, "epoch": 8.261827079934747, "percentage": 82.62, "elapsed_time": "6:53:52", "remaining_time": "1:27:04", "throughput": 4401.41, "total_tokens": 109300208} {"current_steps": 50650, "total_steps": 61300, "loss": 0.3674, "lr": 4.4589279826374955e-06, "epoch": 8.262642740619903, "percentage": 82.63, "elapsed_time": "6:53:55", "remaining_time": "1:27:02", "throughput": 4401.45, "total_tokens": 109310960} {"current_steps": 50655, "total_steps": 61300, "loss": 0.3093, "lr": 4.454871546796182e-06, "epoch": 8.263458401305057, "percentage": 82.63, "elapsed_time": "6:53:57", "remaining_time": "1:26:59", "throughput": 4401.48, "total_tokens": 109321040} {"current_steps": 50660, "total_steps": 61300, "loss": 0.3029, "lr": 4.4508167764472254e-06, "epoch": 8.264274061990212, "percentage": 82.64, "elapsed_time": "6:53:59", "remaining_time": "1:26:56", "throughput": 4401.51, "total_tokens": 109331056} {"current_steps": 50665, "total_steps": 61300, "loss": 0.3328, "lr": 4.446763671919321e-06, "epoch": 8.265089722675366, "percentage": 82.65, "elapsed_time": "6:54:01", "remaining_time": "1:26:54", "throughput": 4401.55, "total_tokens": 109340816} {"current_steps": 50670, "total_steps": 61300, "loss": 0.3256, "lr": 4.442712233541046e-06, "epoch": 8.265905383360522, "percentage": 82.66, "elapsed_time": "6:54:03", "remaining_time": "1:26:51", "throughput": 4401.58, "total_tokens": 109351984} {"current_steps": 50675, "total_steps": 61300, "loss": 0.3252, "lr": 4.438662461640825e-06, "epoch": 8.266721044045678, "percentage": 82.67, "elapsed_time": "6:54:05", "remaining_time": "1:26:49", "throughput": 4401.61, "total_tokens": 109361616} {"current_steps": 50680, "total_steps": 61300, "loss": 0.3338, "lr": 4.4346143565469485e-06, "epoch": 8.267536704730832, "percentage": 82.68, "elapsed_time": "6:54:07", "remaining_time": "1:26:46", "throughput": 4401.65, "total_tokens": 109372240} {"current_steps": 50685, "total_steps": 61300, "loss": 0.3045, "lr": 4.430567918587583e-06, "epoch": 8.268352365415987, "percentage": 82.68, "elapsed_time": "6:54:10", "remaining_time": "1:26:44", "throughput": 4401.69, "total_tokens": 109383120} {"current_steps": 50690, "total_steps": 61300, "loss": 0.3502, "lr": 4.42652314809075e-06, "epoch": 8.269168026101141, "percentage": 82.69, "elapsed_time": "6:54:12", "remaining_time": "1:26:41", "throughput": 4401.72, "total_tokens": 109391952} {"current_steps": 50695, "total_steps": 61300, "loss": 0.367, "lr": 4.4224800453843394e-06, "epoch": 8.269983686786297, "percentage": 82.7, "elapsed_time": "6:54:14", "remaining_time": "1:26:39", "throughput": 4401.76, "total_tokens": 109402576} {"current_steps": 50700, "total_steps": 61300, "loss": 0.3953, "lr": 4.418438610796105e-06, "epoch": 8.270799347471453, "percentage": 82.71, "elapsed_time": "6:54:16", "remaining_time": "1:26:36", "throughput": 4401.79, "total_tokens": 109412976} {"current_steps": 50705, "total_steps": 61300, "loss": 0.3224, "lr": 4.414398844653666e-06, "epoch": 8.271615008156607, "percentage": 82.72, "elapsed_time": "6:54:18", "remaining_time": "1:26:34", "throughput": 4401.83, "total_tokens": 109425040} {"current_steps": 50710, "total_steps": 61300, "loss": 0.3454, "lr": 4.410360747284508e-06, "epoch": 8.272430668841762, "percentage": 82.72, "elapsed_time": "6:54:21", "remaining_time": "1:26:31", "throughput": 4401.87, "total_tokens": 109436592} {"current_steps": 50715, "total_steps": 61300, "loss": 0.3426, "lr": 4.406324319015978e-06, "epoch": 8.273246329526916, "percentage": 82.73, "elapsed_time": "6:54:23", "remaining_time": "1:26:29", "throughput": 4401.91, "total_tokens": 109447184} {"current_steps": 50720, "total_steps": 61300, "loss": 0.3473, "lr": 4.4022895601752905e-06, "epoch": 8.274061990212072, "percentage": 82.74, "elapsed_time": "6:54:25", "remaining_time": "1:26:26", "throughput": 4401.95, "total_tokens": 109457616} {"current_steps": 50725, "total_steps": 61300, "loss": 0.3105, "lr": 4.398256471089518e-06, "epoch": 8.274877650897226, "percentage": 82.75, "elapsed_time": "6:54:27", "remaining_time": "1:26:24", "throughput": 4401.97, "total_tokens": 109466896} {"current_steps": 50730, "total_steps": 61300, "loss": 0.3471, "lr": 4.394225052085613e-06, "epoch": 8.275693311582382, "percentage": 82.76, "elapsed_time": "6:54:30", "remaining_time": "1:26:21", "throughput": 4402.02, "total_tokens": 109478800} {"current_steps": 50735, "total_steps": 61300, "loss": 0.3351, "lr": 4.390195303490377e-06, "epoch": 8.276508972267537, "percentage": 82.77, "elapsed_time": "6:54:32", "remaining_time": "1:26:19", "throughput": 4402.06, "total_tokens": 109488272} {"current_steps": 50740, "total_steps": 61300, "loss": 0.356, "lr": 4.3861672256304835e-06, "epoch": 8.277324632952691, "percentage": 82.77, "elapsed_time": "6:54:34", "remaining_time": "1:26:16", "throughput": 4402.1, "total_tokens": 109499248} {"current_steps": 50745, "total_steps": 61300, "loss": 0.3377, "lr": 4.382140818832467e-06, "epoch": 8.278140293637847, "percentage": 82.78, "elapsed_time": "6:54:36", "remaining_time": "1:26:14", "throughput": 4402.13, "total_tokens": 109509584} {"current_steps": 50750, "total_steps": 61300, "loss": 0.325, "lr": 4.378116083422732e-06, "epoch": 8.278955954323001, "percentage": 82.79, "elapsed_time": "6:54:38", "remaining_time": "1:26:11", "throughput": 4402.16, "total_tokens": 109520656} {"current_steps": 50755, "total_steps": 61300, "loss": 0.3302, "lr": 4.374093019727541e-06, "epoch": 8.279771615008157, "percentage": 82.8, "elapsed_time": "6:54:41", "remaining_time": "1:26:09", "throughput": 4402.2, "total_tokens": 109531600} {"current_steps": 50760, "total_steps": 61300, "loss": 0.3496, "lr": 4.370071628073025e-06, "epoch": 8.280587275693312, "percentage": 82.81, "elapsed_time": "6:54:43", "remaining_time": "1:26:06", "throughput": 4402.24, "total_tokens": 109541936} {"current_steps": 50765, "total_steps": 61300, "loss": 0.3448, "lr": 4.366051908785177e-06, "epoch": 8.281402936378466, "percentage": 82.81, "elapsed_time": "6:54:45", "remaining_time": "1:26:04", "throughput": 4402.28, "total_tokens": 109552336} {"current_steps": 50770, "total_steps": 61300, "loss": 0.3509, "lr": 4.3620338621898575e-06, "epoch": 8.282218597063622, "percentage": 82.82, "elapsed_time": "6:54:47", "remaining_time": "1:26:01", "throughput": 4402.31, "total_tokens": 109563376} {"current_steps": 50775, "total_steps": 61300, "loss": 0.3254, "lr": 4.35801748861279e-06, "epoch": 8.283034257748776, "percentage": 82.83, "elapsed_time": "6:54:50", "remaining_time": "1:25:59", "throughput": 4402.35, "total_tokens": 109575216} {"current_steps": 50780, "total_steps": 61300, "loss": 0.3328, "lr": 4.354002788379558e-06, "epoch": 8.283849918433932, "percentage": 82.84, "elapsed_time": "6:54:52", "remaining_time": "1:25:56", "throughput": 4402.39, "total_tokens": 109585904} {"current_steps": 50785, "total_steps": 61300, "loss": 0.3209, "lr": 4.34998976181562e-06, "epoch": 8.284665579119087, "percentage": 82.85, "elapsed_time": "6:54:54", "remaining_time": "1:25:54", "throughput": 4402.43, "total_tokens": 109597936} {"current_steps": 50790, "total_steps": 61300, "loss": 0.354, "lr": 4.345978409246287e-06, "epoch": 8.285481239804241, "percentage": 82.85, "elapsed_time": "6:54:57", "remaining_time": "1:25:51", "throughput": 4402.47, "total_tokens": 109609424} {"current_steps": 50795, "total_steps": 61300, "loss": 0.339, "lr": 4.341968730996743e-06, "epoch": 8.286296900489397, "percentage": 82.86, "elapsed_time": "6:54:59", "remaining_time": "1:25:49", "throughput": 4402.51, "total_tokens": 109621488} {"current_steps": 50800, "total_steps": 61300, "loss": 0.323, "lr": 4.337960727392032e-06, "epoch": 8.28711256117455, "percentage": 82.87, "elapsed_time": "6:55:01", "remaining_time": "1:25:47", "throughput": 4402.55, "total_tokens": 109631696} {"current_steps": 50805, "total_steps": 61300, "loss": 0.3413, "lr": 4.333954398757054e-06, "epoch": 8.287928221859707, "percentage": 82.88, "elapsed_time": "6:55:04", "remaining_time": "1:25:44", "throughput": 4402.59, "total_tokens": 109642544} {"current_steps": 50810, "total_steps": 61300, "loss": 0.3609, "lr": 4.329949745416598e-06, "epoch": 8.28874388254486, "percentage": 82.89, "elapsed_time": "6:55:06", "remaining_time": "1:25:42", "throughput": 4402.62, "total_tokens": 109652752} {"current_steps": 50815, "total_steps": 61300, "loss": 0.3279, "lr": 4.325946767695297e-06, "epoch": 8.289559543230016, "percentage": 82.9, "elapsed_time": "6:55:08", "remaining_time": "1:25:39", "throughput": 4402.66, "total_tokens": 109664496} {"current_steps": 50820, "total_steps": 61300, "loss": 0.3722, "lr": 4.321945465917646e-06, "epoch": 8.290375203915172, "percentage": 82.9, "elapsed_time": "6:55:11", "remaining_time": "1:25:37", "throughput": 4402.7, "total_tokens": 109676752} {"current_steps": 50825, "total_steps": 61300, "loss": 0.3255, "lr": 4.317945840408019e-06, "epoch": 8.291190864600326, "percentage": 82.91, "elapsed_time": "6:55:13", "remaining_time": "1:25:34", "throughput": 4402.73, "total_tokens": 109687792} {"current_steps": 50830, "total_steps": 61300, "loss": 0.3426, "lr": 4.313947891490638e-06, "epoch": 8.292006525285482, "percentage": 82.92, "elapsed_time": "6:55:15", "remaining_time": "1:25:32", "throughput": 4402.78, "total_tokens": 109698416} {"current_steps": 50835, "total_steps": 61300, "loss": 0.3314, "lr": 4.309951619489597e-06, "epoch": 8.292822185970635, "percentage": 82.93, "elapsed_time": "6:55:18", "remaining_time": "1:25:29", "throughput": 4402.81, "total_tokens": 109709488} {"current_steps": 50840, "total_steps": 61300, "loss": 0.3506, "lr": 4.3059570247288624e-06, "epoch": 8.293637846655791, "percentage": 82.94, "elapsed_time": "6:55:20", "remaining_time": "1:25:27", "throughput": 4402.86, "total_tokens": 109720912} {"current_steps": 50845, "total_steps": 61300, "loss": 0.3181, "lr": 4.301964107532255e-06, "epoch": 8.294453507340947, "percentage": 82.94, "elapsed_time": "6:55:22", "remaining_time": "1:25:24", "throughput": 4402.89, "total_tokens": 109731600} {"current_steps": 50850, "total_steps": 61300, "loss": 0.308, "lr": 4.297972868223457e-06, "epoch": 8.2952691680261, "percentage": 82.95, "elapsed_time": "6:55:24", "remaining_time": "1:25:22", "throughput": 4402.92, "total_tokens": 109742064} {"current_steps": 50855, "total_steps": 61300, "loss": 0.3467, "lr": 4.293983307126018e-06, "epoch": 8.296084828711257, "percentage": 82.96, "elapsed_time": "6:55:27", "remaining_time": "1:25:19", "throughput": 4402.96, "total_tokens": 109752848} {"current_steps": 50860, "total_steps": 61300, "loss": 0.3357, "lr": 4.289995424563353e-06, "epoch": 8.29690048939641, "percentage": 82.97, "elapsed_time": "6:55:29", "remaining_time": "1:25:17", "throughput": 4403.0, "total_tokens": 109763728} {"current_steps": 50865, "total_steps": 61300, "loss": 0.3264, "lr": 4.286009220858742e-06, "epoch": 8.297716150081566, "percentage": 82.98, "elapsed_time": "6:55:31", "remaining_time": "1:25:14", "throughput": 4403.05, "total_tokens": 109774864} {"current_steps": 50870, "total_steps": 61300, "loss": 0.2947, "lr": 4.282024696335324e-06, "epoch": 8.298531810766722, "percentage": 82.99, "elapsed_time": "6:55:33", "remaining_time": "1:25:12", "throughput": 4403.09, "total_tokens": 109785296} {"current_steps": 50875, "total_steps": 61300, "loss": 0.3073, "lr": 4.278041851316106e-06, "epoch": 8.299347471451876, "percentage": 82.99, "elapsed_time": "6:55:35", "remaining_time": "1:25:09", "throughput": 4403.12, "total_tokens": 109795856} {"current_steps": 50880, "total_steps": 61300, "loss": 0.3225, "lr": 4.274060686123959e-06, "epoch": 8.300163132137031, "percentage": 83.0, "elapsed_time": "6:55:38", "remaining_time": "1:25:07", "throughput": 4403.16, "total_tokens": 109806480} {"current_steps": 50885, "total_steps": 61300, "loss": 0.3622, "lr": 4.270081201081613e-06, "epoch": 8.300978792822185, "percentage": 83.01, "elapsed_time": "6:55:40", "remaining_time": "1:25:04", "throughput": 4403.21, "total_tokens": 109817680} {"current_steps": 50890, "total_steps": 61300, "loss": 0.2955, "lr": 4.2661033965116695e-06, "epoch": 8.301794453507341, "percentage": 83.02, "elapsed_time": "6:55:42", "remaining_time": "1:25:02", "throughput": 4403.25, "total_tokens": 109829616} {"current_steps": 50895, "total_steps": 61300, "loss": 0.3066, "lr": 4.2621272727365875e-06, "epoch": 8.302610114192497, "percentage": 83.03, "elapsed_time": "6:55:44", "remaining_time": "1:24:59", "throughput": 4403.29, "total_tokens": 109839632} {"current_steps": 50900, "total_steps": 61300, "loss": 0.3488, "lr": 4.2581528300786906e-06, "epoch": 8.30342577487765, "percentage": 83.03, "elapsed_time": "6:55:47", "remaining_time": "1:24:57", "throughput": 4403.33, "total_tokens": 109851344} {"current_steps": 50905, "total_steps": 61300, "loss": 0.3138, "lr": 4.2541800688601696e-06, "epoch": 8.304241435562806, "percentage": 83.04, "elapsed_time": "6:55:49", "remaining_time": "1:24:54", "throughput": 4403.36, "total_tokens": 109861072} {"current_steps": 50910, "total_steps": 61300, "loss": 0.3309, "lr": 4.250208989403073e-06, "epoch": 8.30505709624796, "percentage": 83.05, "elapsed_time": "6:55:51", "remaining_time": "1:24:52", "throughput": 4403.4, "total_tokens": 109872144} {"current_steps": 50915, "total_steps": 61300, "loss": 0.3574, "lr": 4.2462395920293215e-06, "epoch": 8.305872756933116, "percentage": 83.06, "elapsed_time": "6:55:53", "remaining_time": "1:24:49", "throughput": 4403.44, "total_tokens": 109883152} {"current_steps": 50920, "total_steps": 61300, "loss": 0.3376, "lr": 4.242271877060691e-06, "epoch": 8.30668841761827, "percentage": 83.07, "elapsed_time": "6:55:56", "remaining_time": "1:24:47", "throughput": 4403.48, "total_tokens": 109894672} {"current_steps": 50925, "total_steps": 61300, "loss": 0.313, "lr": 4.238305844818827e-06, "epoch": 8.307504078303426, "percentage": 83.08, "elapsed_time": "6:55:58", "remaining_time": "1:24:44", "throughput": 4403.53, "total_tokens": 109905456} {"current_steps": 50930, "total_steps": 61300, "loss": 0.3405, "lr": 4.234341495625233e-06, "epoch": 8.308319738988581, "percentage": 83.08, "elapsed_time": "6:56:00", "remaining_time": "1:24:42", "throughput": 4403.56, "total_tokens": 109915024} {"current_steps": 50935, "total_steps": 61300, "loss": 0.3217, "lr": 4.230378829801282e-06, "epoch": 8.309135399673735, "percentage": 83.09, "elapsed_time": "6:56:02", "remaining_time": "1:24:39", "throughput": 4403.58, "total_tokens": 109923728} {"current_steps": 50940, "total_steps": 61300, "loss": 0.3466, "lr": 4.226417847668201e-06, "epoch": 8.309951060358891, "percentage": 83.1, "elapsed_time": "6:56:04", "remaining_time": "1:24:37", "throughput": 4403.62, "total_tokens": 109934128} {"current_steps": 50945, "total_steps": 61300, "loss": 0.3208, "lr": 4.222458549547101e-06, "epoch": 8.310766721044045, "percentage": 83.11, "elapsed_time": "6:56:06", "remaining_time": "1:24:34", "throughput": 4403.66, "total_tokens": 109945072} {"current_steps": 50950, "total_steps": 61300, "loss": 0.3402, "lr": 4.218500935758935e-06, "epoch": 8.3115823817292, "percentage": 83.12, "elapsed_time": "6:56:08", "remaining_time": "1:24:32", "throughput": 4403.69, "total_tokens": 109955184} {"current_steps": 50955, "total_steps": 61300, "loss": 0.3356, "lr": 4.214545006624526e-06, "epoch": 8.312398042414356, "percentage": 83.12, "elapsed_time": "6:56:10", "remaining_time": "1:24:29", "throughput": 4403.73, "total_tokens": 109965232} {"current_steps": 50960, "total_steps": 61300, "loss": 0.3325, "lr": 4.210590762464564e-06, "epoch": 8.31321370309951, "percentage": 83.13, "elapsed_time": "6:56:13", "remaining_time": "1:24:27", "throughput": 4403.78, "total_tokens": 109976944} {"current_steps": 50965, "total_steps": 61300, "loss": 0.3326, "lr": 4.206638203599597e-06, "epoch": 8.314029363784666, "percentage": 83.14, "elapsed_time": "6:56:15", "remaining_time": "1:24:24", "throughput": 4403.81, "total_tokens": 109987504} {"current_steps": 50970, "total_steps": 61300, "loss": 0.325, "lr": 4.202687330350044e-06, "epoch": 8.31484502446982, "percentage": 83.15, "elapsed_time": "6:56:17", "remaining_time": "1:24:22", "throughput": 4403.85, "total_tokens": 109998160} {"current_steps": 50975, "total_steps": 61300, "loss": 0.3044, "lr": 4.1987381430361735e-06, "epoch": 8.315660685154976, "percentage": 83.16, "elapsed_time": "6:56:19", "remaining_time": "1:24:19", "throughput": 4403.89, "total_tokens": 110008464} {"current_steps": 50980, "total_steps": 61300, "loss": 0.2976, "lr": 4.194790641978141e-06, "epoch": 8.31647634584013, "percentage": 83.16, "elapsed_time": "6:56:22", "remaining_time": "1:24:17", "throughput": 4403.92, "total_tokens": 110020080} {"current_steps": 50985, "total_steps": 61300, "loss": 0.333, "lr": 4.1908448274959436e-06, "epoch": 8.317292006525285, "percentage": 83.17, "elapsed_time": "6:56:24", "remaining_time": "1:24:14", "throughput": 4403.96, "total_tokens": 110029104} {"current_steps": 50990, "total_steps": 61300, "loss": 0.3288, "lr": 4.186900699909446e-06, "epoch": 8.318107667210441, "percentage": 83.18, "elapsed_time": "6:56:26", "remaining_time": "1:24:12", "throughput": 4404.0, "total_tokens": 110040528} {"current_steps": 50995, "total_steps": 61300, "loss": 0.3339, "lr": 4.182958259538386e-06, "epoch": 8.318923327895595, "percentage": 83.19, "elapsed_time": "6:56:28", "remaining_time": "1:24:09", "throughput": 4404.03, "total_tokens": 110049744} {"current_steps": 51000, "total_steps": 61300, "loss": 0.2956, "lr": 4.179017506702351e-06, "epoch": 8.31973898858075, "percentage": 83.2, "elapsed_time": "6:56:30", "remaining_time": "1:24:07", "throughput": 4404.06, "total_tokens": 110061680} {"current_steps": 51005, "total_steps": 61300, "loss": 0.334, "lr": 4.1750784417208065e-06, "epoch": 8.320554649265905, "percentage": 83.21, "elapsed_time": "6:56:33", "remaining_time": "1:24:04", "throughput": 4404.1, "total_tokens": 110072880} {"current_steps": 51010, "total_steps": 61300, "loss": 0.3414, "lr": 4.171141064913061e-06, "epoch": 8.32137030995106, "percentage": 83.21, "elapsed_time": "6:56:35", "remaining_time": "1:24:02", "throughput": 4404.14, "total_tokens": 110084464} {"current_steps": 51015, "total_steps": 61300, "loss": 0.3219, "lr": 4.16720537659831e-06, "epoch": 8.322185970636216, "percentage": 83.22, "elapsed_time": "6:56:37", "remaining_time": "1:23:59", "throughput": 4404.18, "total_tokens": 110095536} {"current_steps": 51020, "total_steps": 61300, "loss": 0.3281, "lr": 4.1632713770955956e-06, "epoch": 8.32300163132137, "percentage": 83.23, "elapsed_time": "6:56:39", "remaining_time": "1:23:57", "throughput": 4404.21, "total_tokens": 110104496} {"current_steps": 51025, "total_steps": 61300, "loss": 0.2906, "lr": 4.159339066723827e-06, "epoch": 8.323817292006526, "percentage": 83.24, "elapsed_time": "6:56:42", "remaining_time": "1:23:54", "throughput": 4404.25, "total_tokens": 110115888} {"current_steps": 51030, "total_steps": 61300, "loss": 0.3204, "lr": 4.155408445801779e-06, "epoch": 8.32463295269168, "percentage": 83.25, "elapsed_time": "6:56:44", "remaining_time": "1:23:52", "throughput": 4404.28, "total_tokens": 110125104} {"current_steps": 51035, "total_steps": 61300, "loss": 0.3101, "lr": 4.151479514648085e-06, "epoch": 8.325448613376835, "percentage": 83.25, "elapsed_time": "6:56:46", "remaining_time": "1:23:49", "throughput": 4404.31, "total_tokens": 110135728} {"current_steps": 51040, "total_steps": 61300, "loss": 0.3696, "lr": 4.147552273581248e-06, "epoch": 8.326264274061991, "percentage": 83.26, "elapsed_time": "6:56:48", "remaining_time": "1:23:47", "throughput": 4404.35, "total_tokens": 110146832} {"current_steps": 51045, "total_steps": 61300, "loss": 0.3134, "lr": 4.143626722919619e-06, "epoch": 8.327079934747145, "percentage": 83.27, "elapsed_time": "6:56:50", "remaining_time": "1:23:44", "throughput": 4404.38, "total_tokens": 110157520} {"current_steps": 51050, "total_steps": 61300, "loss": 0.3122, "lr": 4.139702862981443e-06, "epoch": 8.3278955954323, "percentage": 83.28, "elapsed_time": "6:56:53", "remaining_time": "1:23:42", "throughput": 4404.43, "total_tokens": 110168688} {"current_steps": 51055, "total_steps": 61300, "loss": 0.323, "lr": 4.135780694084793e-06, "epoch": 8.328711256117455, "percentage": 83.29, "elapsed_time": "6:56:55", "remaining_time": "1:23:39", "throughput": 4404.47, "total_tokens": 110179056} {"current_steps": 51060, "total_steps": 61300, "loss": 0.2977, "lr": 4.131860216547623e-06, "epoch": 8.32952691680261, "percentage": 83.3, "elapsed_time": "6:56:57", "remaining_time": "1:23:37", "throughput": 4404.51, "total_tokens": 110190160} {"current_steps": 51065, "total_steps": 61300, "loss": 0.3171, "lr": 4.127941430687751e-06, "epoch": 8.330342577487766, "percentage": 83.3, "elapsed_time": "6:56:59", "remaining_time": "1:23:34", "throughput": 4404.54, "total_tokens": 110201424} {"current_steps": 51070, "total_steps": 61300, "loss": 0.3473, "lr": 4.1240243368228485e-06, "epoch": 8.33115823817292, "percentage": 83.31, "elapsed_time": "6:57:02", "remaining_time": "1:23:32", "throughput": 4404.58, "total_tokens": 110212304} {"current_steps": 51075, "total_steps": 61300, "loss": 0.3112, "lr": 4.120108935270459e-06, "epoch": 8.331973898858076, "percentage": 83.32, "elapsed_time": "6:57:04", "remaining_time": "1:23:29", "throughput": 4404.62, "total_tokens": 110223216} {"current_steps": 51080, "total_steps": 61300, "loss": 0.3209, "lr": 4.11619522634798e-06, "epoch": 8.33278955954323, "percentage": 83.33, "elapsed_time": "6:57:06", "remaining_time": "1:23:27", "throughput": 4404.66, "total_tokens": 110234160} {"current_steps": 51085, "total_steps": 61300, "loss": 0.3046, "lr": 4.11228321037268e-06, "epoch": 8.333605220228385, "percentage": 83.34, "elapsed_time": "6:57:09", "remaining_time": "1:23:24", "throughput": 4404.7, "total_tokens": 110245264} {"current_steps": 51090, "total_steps": 61300, "loss": 0.3518, "lr": 4.108372887661688e-06, "epoch": 8.33442088091354, "percentage": 83.34, "elapsed_time": "6:57:11", "remaining_time": "1:23:22", "throughput": 4404.73, "total_tokens": 110256560} {"current_steps": 51095, "total_steps": 61300, "loss": 0.3779, "lr": 4.10446425853199e-06, "epoch": 8.335236541598695, "percentage": 83.35, "elapsed_time": "6:57:13", "remaining_time": "1:23:19", "throughput": 4404.77, "total_tokens": 110267920} {"current_steps": 51100, "total_steps": 61300, "loss": 0.2892, "lr": 4.100557323300444e-06, "epoch": 8.33605220228385, "percentage": 83.36, "elapsed_time": "6:57:15", "remaining_time": "1:23:17", "throughput": 4404.8, "total_tokens": 110278032} {"current_steps": 51105, "total_steps": 61300, "loss": 0.3507, "lr": 4.096652082283764e-06, "epoch": 8.336867862969005, "percentage": 83.37, "elapsed_time": "6:57:18", "remaining_time": "1:23:14", "throughput": 4404.83, "total_tokens": 110289232} {"current_steps": 51110, "total_steps": 61300, "loss": 0.3498, "lr": 4.092748535798527e-06, "epoch": 8.33768352365416, "percentage": 83.38, "elapsed_time": "6:57:20", "remaining_time": "1:23:12", "throughput": 4404.87, "total_tokens": 110299664} {"current_steps": 51115, "total_steps": 61300, "loss": 0.3728, "lr": 4.088846684161177e-06, "epoch": 8.338499184339314, "percentage": 83.38, "elapsed_time": "6:57:22", "remaining_time": "1:23:09", "throughput": 4404.91, "total_tokens": 110310480} {"current_steps": 51120, "total_steps": 61300, "loss": 0.3699, "lr": 4.0849465276880105e-06, "epoch": 8.33931484502447, "percentage": 83.39, "elapsed_time": "6:57:25", "remaining_time": "1:23:07", "throughput": 4404.96, "total_tokens": 110322640} {"current_steps": 51125, "total_steps": 61300, "loss": 0.316, "lr": 4.081048066695209e-06, "epoch": 8.340130505709626, "percentage": 83.4, "elapsed_time": "6:57:27", "remaining_time": "1:23:05", "throughput": 4405.0, "total_tokens": 110334992} {"current_steps": 51130, "total_steps": 61300, "loss": 0.3465, "lr": 4.077151301498791e-06, "epoch": 8.34094616639478, "percentage": 83.41, "elapsed_time": "6:57:29", "remaining_time": "1:23:02", "throughput": 4405.04, "total_tokens": 110345616} {"current_steps": 51135, "total_steps": 61300, "loss": 0.3294, "lr": 4.073256232414649e-06, "epoch": 8.341761827079935, "percentage": 83.42, "elapsed_time": "6:57:32", "remaining_time": "1:23:00", "throughput": 4405.08, "total_tokens": 110356752} {"current_steps": 51140, "total_steps": 61300, "loss": 0.3241, "lr": 4.069362859758541e-06, "epoch": 8.34257748776509, "percentage": 83.43, "elapsed_time": "6:57:34", "remaining_time": "1:22:57", "throughput": 4405.12, "total_tokens": 110367568} {"current_steps": 51145, "total_steps": 61300, "loss": 0.313, "lr": 4.065471183846079e-06, "epoch": 8.343393148450245, "percentage": 83.43, "elapsed_time": "6:57:36", "remaining_time": "1:22:55", "throughput": 4405.15, "total_tokens": 110378576} {"current_steps": 51150, "total_steps": 61300, "loss": 0.3257, "lr": 4.061581204992742e-06, "epoch": 8.3442088091354, "percentage": 83.44, "elapsed_time": "6:57:38", "remaining_time": "1:22:52", "throughput": 4405.19, "total_tokens": 110389072} {"current_steps": 51155, "total_steps": 61300, "loss": 0.3122, "lr": 4.057692923513867e-06, "epoch": 8.345024469820554, "percentage": 83.45, "elapsed_time": "6:57:41", "remaining_time": "1:22:50", "throughput": 4405.22, "total_tokens": 110400464} {"current_steps": 51160, "total_steps": 61300, "loss": 0.3588, "lr": 4.0538063397246725e-06, "epoch": 8.34584013050571, "percentage": 83.46, "elapsed_time": "6:57:43", "remaining_time": "1:22:47", "throughput": 4405.26, "total_tokens": 110411728} {"current_steps": 51165, "total_steps": 61300, "loss": 0.3512, "lr": 4.049921453940214e-06, "epoch": 8.346655791190864, "percentage": 83.47, "elapsed_time": "6:57:45", "remaining_time": "1:22:45", "throughput": 4405.3, "total_tokens": 110422480} {"current_steps": 51170, "total_steps": 61300, "loss": 0.3254, "lr": 4.046038266475421e-06, "epoch": 8.34747145187602, "percentage": 83.47, "elapsed_time": "6:57:48", "remaining_time": "1:22:42", "throughput": 4405.33, "total_tokens": 110433680} {"current_steps": 51175, "total_steps": 61300, "loss": 0.336, "lr": 4.0421567776450895e-06, "epoch": 8.348287112561174, "percentage": 83.48, "elapsed_time": "6:57:50", "remaining_time": "1:22:40", "throughput": 4405.36, "total_tokens": 110442512} {"current_steps": 51180, "total_steps": 61300, "loss": 0.3253, "lr": 4.038276987763864e-06, "epoch": 8.34910277324633, "percentage": 83.49, "elapsed_time": "6:57:52", "remaining_time": "1:22:37", "throughput": 4405.4, "total_tokens": 110454032} {"current_steps": 51185, "total_steps": 61300, "loss": 0.3436, "lr": 4.034398897146269e-06, "epoch": 8.349918433931485, "percentage": 83.5, "elapsed_time": "6:57:54", "remaining_time": "1:22:35", "throughput": 4405.43, "total_tokens": 110464432} {"current_steps": 51190, "total_steps": 61300, "loss": 0.3644, "lr": 4.0305225061066735e-06, "epoch": 8.350734094616639, "percentage": 83.51, "elapsed_time": "6:57:57", "remaining_time": "1:22:32", "throughput": 4405.48, "total_tokens": 110476176} {"current_steps": 51195, "total_steps": 61300, "loss": 0.326, "lr": 4.026647814959325e-06, "epoch": 8.351549755301795, "percentage": 83.52, "elapsed_time": "6:57:59", "remaining_time": "1:22:30", "throughput": 4405.52, "total_tokens": 110486800} {"current_steps": 51200, "total_steps": 61300, "loss": 0.3201, "lr": 4.022774824018321e-06, "epoch": 8.352365415986949, "percentage": 83.52, "elapsed_time": "6:58:01", "remaining_time": "1:22:27", "throughput": 4405.56, "total_tokens": 110498448} {"current_steps": 51205, "total_steps": 61300, "loss": 0.303, "lr": 4.018903533597629e-06, "epoch": 8.353181076672104, "percentage": 83.53, "elapsed_time": "6:58:03", "remaining_time": "1:22:25", "throughput": 4405.61, "total_tokens": 110510064} {"current_steps": 51210, "total_steps": 61300, "loss": 0.3397, "lr": 4.015033944011071e-06, "epoch": 8.35399673735726, "percentage": 83.54, "elapsed_time": "6:58:06", "remaining_time": "1:22:22", "throughput": 4405.65, "total_tokens": 110522352} {"current_steps": 51215, "total_steps": 61300, "loss": 0.325, "lr": 4.011166055572338e-06, "epoch": 8.354812398042414, "percentage": 83.55, "elapsed_time": "6:58:08", "remaining_time": "1:22:20", "throughput": 4405.71, "total_tokens": 110534640} {"current_steps": 51220, "total_steps": 61300, "loss": 0.3156, "lr": 4.007299868594983e-06, "epoch": 8.35562805872757, "percentage": 83.56, "elapsed_time": "6:58:11", "remaining_time": "1:22:17", "throughput": 4405.74, "total_tokens": 110546608} {"current_steps": 51225, "total_steps": 61300, "loss": 0.312, "lr": 4.003435383392415e-06, "epoch": 8.356443719412724, "percentage": 83.56, "elapsed_time": "6:58:13", "remaining_time": "1:22:15", "throughput": 4405.77, "total_tokens": 110556656} {"current_steps": 51230, "total_steps": 61300, "loss": 0.3701, "lr": 3.999572600277912e-06, "epoch": 8.35725938009788, "percentage": 83.57, "elapsed_time": "6:58:15", "remaining_time": "1:22:12", "throughput": 4405.81, "total_tokens": 110567184} {"current_steps": 51235, "total_steps": 61300, "loss": 0.3485, "lr": 3.995711519564607e-06, "epoch": 8.358075040783035, "percentage": 83.58, "elapsed_time": "6:58:17", "remaining_time": "1:22:10", "throughput": 4405.84, "total_tokens": 110576848} {"current_steps": 51240, "total_steps": 61300, "loss": 0.3119, "lr": 3.991852141565503e-06, "epoch": 8.358890701468189, "percentage": 83.59, "elapsed_time": "6:58:20", "remaining_time": "1:22:07", "throughput": 4405.89, "total_tokens": 110587920} {"current_steps": 51245, "total_steps": 61300, "loss": 0.3391, "lr": 3.987994466593456e-06, "epoch": 8.359706362153345, "percentage": 83.6, "elapsed_time": "6:58:22", "remaining_time": "1:22:05", "throughput": 4405.92, "total_tokens": 110599184} {"current_steps": 51250, "total_steps": 61300, "loss": 0.3311, "lr": 3.9841384949611924e-06, "epoch": 8.360522022838499, "percentage": 83.61, "elapsed_time": "6:58:24", "remaining_time": "1:22:02", "throughput": 4405.97, "total_tokens": 110610768} {"current_steps": 51255, "total_steps": 61300, "loss": 0.364, "lr": 3.980284226981299e-06, "epoch": 8.361337683523654, "percentage": 83.61, "elapsed_time": "6:58:26", "remaining_time": "1:22:00", "throughput": 4406.01, "total_tokens": 110621136} {"current_steps": 51260, "total_steps": 61300, "loss": 0.3588, "lr": 3.976431662966209e-06, "epoch": 8.362153344208808, "percentage": 83.62, "elapsed_time": "6:58:28", "remaining_time": "1:21:57", "throughput": 4406.04, "total_tokens": 110631088} {"current_steps": 51265, "total_steps": 61300, "loss": 0.3612, "lr": 3.972580803228249e-06, "epoch": 8.362969004893964, "percentage": 83.63, "elapsed_time": "6:58:31", "remaining_time": "1:21:55", "throughput": 4406.09, "total_tokens": 110643184} {"current_steps": 51270, "total_steps": 61300, "loss": 0.3209, "lr": 3.96873164807958e-06, "epoch": 8.36378466557912, "percentage": 83.64, "elapsed_time": "6:58:33", "remaining_time": "1:21:53", "throughput": 4406.12, "total_tokens": 110653712} {"current_steps": 51275, "total_steps": 61300, "loss": 0.3646, "lr": 3.964884197832236e-06, "epoch": 8.364600326264274, "percentage": 83.65, "elapsed_time": "6:58:35", "remaining_time": "1:21:50", "throughput": 4406.16, "total_tokens": 110663600} {"current_steps": 51280, "total_steps": 61300, "loss": 0.3182, "lr": 3.96103845279811e-06, "epoch": 8.36541598694943, "percentage": 83.65, "elapsed_time": "6:58:37", "remaining_time": "1:21:47", "throughput": 4406.19, "total_tokens": 110674192} {"current_steps": 51285, "total_steps": 61300, "loss": 0.3406, "lr": 3.957194413288956e-06, "epoch": 8.366231647634583, "percentage": 83.66, "elapsed_time": "6:58:40", "remaining_time": "1:21:45", "throughput": 4406.23, "total_tokens": 110684880} {"current_steps": 51290, "total_steps": 61300, "loss": 0.326, "lr": 3.953352079616387e-06, "epoch": 8.367047308319739, "percentage": 83.67, "elapsed_time": "6:58:42", "remaining_time": "1:21:42", "throughput": 4406.26, "total_tokens": 110695120} {"current_steps": 51295, "total_steps": 61300, "loss": 0.3409, "lr": 3.949511452091898e-06, "epoch": 8.367862969004895, "percentage": 83.68, "elapsed_time": "6:58:44", "remaining_time": "1:21:40", "throughput": 4406.29, "total_tokens": 110704912} {"current_steps": 51300, "total_steps": 61300, "loss": 0.3134, "lr": 3.945672531026817e-06, "epoch": 8.368678629690049, "percentage": 83.69, "elapsed_time": "6:58:46", "remaining_time": "1:21:37", "throughput": 4406.34, "total_tokens": 110715952} {"current_steps": 51305, "total_steps": 61300, "loss": 0.3332, "lr": 3.941835316732348e-06, "epoch": 8.369494290375204, "percentage": 83.69, "elapsed_time": "6:58:48", "remaining_time": "1:21:35", "throughput": 4406.38, "total_tokens": 110727312} {"current_steps": 51310, "total_steps": 61300, "loss": 0.33, "lr": 3.9379998095195606e-06, "epoch": 8.370309951060358, "percentage": 83.7, "elapsed_time": "6:58:51", "remaining_time": "1:21:33", "throughput": 4406.42, "total_tokens": 110738448} {"current_steps": 51315, "total_steps": 61300, "loss": 0.3183, "lr": 3.9341660096993725e-06, "epoch": 8.371125611745514, "percentage": 83.71, "elapsed_time": "6:58:53", "remaining_time": "1:21:30", "throughput": 4406.47, "total_tokens": 110750960} {"current_steps": 51320, "total_steps": 61300, "loss": 0.3023, "lr": 3.9303339175825736e-06, "epoch": 8.37194127243067, "percentage": 83.72, "elapsed_time": "6:58:55", "remaining_time": "1:21:28", "throughput": 4406.51, "total_tokens": 110761584} {"current_steps": 51325, "total_steps": 61300, "loss": 0.3294, "lr": 3.926503533479817e-06, "epoch": 8.372756933115824, "percentage": 83.73, "elapsed_time": "6:58:58", "remaining_time": "1:21:25", "throughput": 4406.54, "total_tokens": 110771792} {"current_steps": 51330, "total_steps": 61300, "loss": 0.3347, "lr": 3.922674857701608e-06, "epoch": 8.37357259380098, "percentage": 83.74, "elapsed_time": "6:59:00", "remaining_time": "1:21:23", "throughput": 4406.59, "total_tokens": 110783472} {"current_steps": 51335, "total_steps": 61300, "loss": 0.3016, "lr": 3.918847890558322e-06, "epoch": 8.374388254486133, "percentage": 83.74, "elapsed_time": "6:59:02", "remaining_time": "1:21:20", "throughput": 4406.62, "total_tokens": 110793584} {"current_steps": 51340, "total_steps": 61300, "loss": 0.3481, "lr": 3.915022632360188e-06, "epoch": 8.375203915171289, "percentage": 83.75, "elapsed_time": "6:59:04", "remaining_time": "1:21:18", "throughput": 4406.65, "total_tokens": 110803440} {"current_steps": 51345, "total_steps": 61300, "loss": 0.3307, "lr": 3.911199083417305e-06, "epoch": 8.376019575856443, "percentage": 83.76, "elapsed_time": "6:59:06", "remaining_time": "1:21:15", "throughput": 4406.69, "total_tokens": 110813808} {"current_steps": 51350, "total_steps": 61300, "loss": 0.3073, "lr": 3.9073772440396285e-06, "epoch": 8.376835236541599, "percentage": 83.77, "elapsed_time": "6:59:08", "remaining_time": "1:21:13", "throughput": 4406.72, "total_tokens": 110824016} {"current_steps": 51355, "total_steps": 61300, "loss": 0.3016, "lr": 3.903557114536973e-06, "epoch": 8.377650897226754, "percentage": 83.78, "elapsed_time": "6:59:11", "remaining_time": "1:21:10", "throughput": 4406.76, "total_tokens": 110834672} {"current_steps": 51360, "total_steps": 61300, "loss": 0.3191, "lr": 3.899738695219024e-06, "epoch": 8.378466557911908, "percentage": 83.78, "elapsed_time": "6:59:13", "remaining_time": "1:21:08", "throughput": 4406.79, "total_tokens": 110845456} {"current_steps": 51365, "total_steps": 61300, "loss": 0.3142, "lr": 3.89592198639531e-06, "epoch": 8.379282218597064, "percentage": 83.79, "elapsed_time": "6:59:15", "remaining_time": "1:21:05", "throughput": 4406.82, "total_tokens": 110856080} {"current_steps": 51370, "total_steps": 61300, "loss": 0.3391, "lr": 3.8921069883752465e-06, "epoch": 8.380097879282218, "percentage": 83.8, "elapsed_time": "6:59:17", "remaining_time": "1:21:03", "throughput": 4406.87, "total_tokens": 110867056} {"current_steps": 51375, "total_steps": 61300, "loss": 0.324, "lr": 3.88829370146809e-06, "epoch": 8.380913539967374, "percentage": 83.81, "elapsed_time": "6:59:20", "remaining_time": "1:21:00", "throughput": 4406.91, "total_tokens": 110878352} {"current_steps": 51380, "total_steps": 61300, "loss": 0.3422, "lr": 3.884482125982969e-06, "epoch": 8.38172920065253, "percentage": 83.82, "elapsed_time": "6:59:22", "remaining_time": "1:20:58", "throughput": 4406.95, "total_tokens": 110889584} {"current_steps": 51385, "total_steps": 61300, "loss": 0.3631, "lr": 3.880672262228863e-06, "epoch": 8.382544861337683, "percentage": 83.83, "elapsed_time": "6:59:24", "remaining_time": "1:20:55", "throughput": 4406.98, "total_tokens": 110900464} {"current_steps": 51390, "total_steps": 61300, "loss": 0.3813, "lr": 3.876864110514622e-06, "epoch": 8.383360522022839, "percentage": 83.83, "elapsed_time": "6:59:27", "remaining_time": "1:20:53", "throughput": 4407.02, "total_tokens": 110911568} {"current_steps": 51395, "total_steps": 61300, "loss": 0.3149, "lr": 3.8730576711489555e-06, "epoch": 8.384176182707993, "percentage": 83.84, "elapsed_time": "6:59:29", "remaining_time": "1:20:50", "throughput": 4407.06, "total_tokens": 110922640} {"current_steps": 51400, "total_steps": 61300, "loss": 0.3583, "lr": 3.86925294444043e-06, "epoch": 8.384991843393149, "percentage": 83.85, "elapsed_time": "6:59:31", "remaining_time": "1:20:48", "throughput": 4407.1, "total_tokens": 110933872} {"current_steps": 51405, "total_steps": 61300, "loss": 0.3437, "lr": 3.8654499306974765e-06, "epoch": 8.385807504078304, "percentage": 83.86, "elapsed_time": "6:59:34", "remaining_time": "1:20:45", "throughput": 4407.14, "total_tokens": 110945648} {"current_steps": 51410, "total_steps": 61300, "loss": 0.3857, "lr": 3.86164863022839e-06, "epoch": 8.386623164763458, "percentage": 83.87, "elapsed_time": "6:59:36", "remaining_time": "1:20:43", "throughput": 4407.18, "total_tokens": 110956528} {"current_steps": 51415, "total_steps": 61300, "loss": 0.3123, "lr": 3.857849043341316e-06, "epoch": 8.387438825448614, "percentage": 83.87, "elapsed_time": "6:59:38", "remaining_time": "1:20:40", "throughput": 4407.21, "total_tokens": 110966224} {"current_steps": 51420, "total_steps": 61300, "loss": 0.3073, "lr": 3.854051170344278e-06, "epoch": 8.388254486133768, "percentage": 83.88, "elapsed_time": "6:59:40", "remaining_time": "1:20:38", "throughput": 4407.25, "total_tokens": 110976912} {"current_steps": 51425, "total_steps": 61300, "loss": 0.3584, "lr": 3.8502550115451425e-06, "epoch": 8.389070146818923, "percentage": 83.89, "elapsed_time": "6:59:42", "remaining_time": "1:20:35", "throughput": 4407.29, "total_tokens": 110988080} {"current_steps": 51430, "total_steps": 61300, "loss": 0.3253, "lr": 3.846460567251648e-06, "epoch": 8.38988580750408, "percentage": 83.9, "elapsed_time": "6:59:45", "remaining_time": "1:20:33", "throughput": 4407.33, "total_tokens": 110999472} {"current_steps": 51435, "total_steps": 61300, "loss": 0.3255, "lr": 3.8426678377713884e-06, "epoch": 8.390701468189233, "percentage": 83.91, "elapsed_time": "6:59:47", "remaining_time": "1:20:30", "throughput": 4407.37, "total_tokens": 111011184} {"current_steps": 51440, "total_steps": 61300, "loss": 0.3461, "lr": 3.8388768234118275e-06, "epoch": 8.391517128874389, "percentage": 83.92, "elapsed_time": "6:59:49", "remaining_time": "1:20:28", "throughput": 4407.4, "total_tokens": 111022480} {"current_steps": 51445, "total_steps": 61300, "loss": 0.3479, "lr": 3.8350875244802855e-06, "epoch": 8.392332789559543, "percentage": 83.92, "elapsed_time": "6:59:52", "remaining_time": "1:20:25", "throughput": 4407.43, "total_tokens": 111032912} {"current_steps": 51450, "total_steps": 61300, "loss": 0.3151, "lr": 3.831299941283936e-06, "epoch": 8.393148450244698, "percentage": 83.93, "elapsed_time": "6:59:54", "remaining_time": "1:20:23", "throughput": 4407.47, "total_tokens": 111044272} {"current_steps": 51455, "total_steps": 61300, "loss": 0.3603, "lr": 3.827514074129823e-06, "epoch": 8.393964110929852, "percentage": 83.94, "elapsed_time": "6:59:56", "remaining_time": "1:20:20", "throughput": 4407.51, "total_tokens": 111054704} {"current_steps": 51460, "total_steps": 61300, "loss": 0.3222, "lr": 3.823729923324848e-06, "epoch": 8.394779771615008, "percentage": 83.95, "elapsed_time": "6:59:58", "remaining_time": "1:20:18", "throughput": 4407.55, "total_tokens": 111065040} {"current_steps": 51465, "total_steps": 61300, "loss": 0.3427, "lr": 3.819947489175771e-06, "epoch": 8.395595432300164, "percentage": 83.96, "elapsed_time": "7:00:01", "remaining_time": "1:20:15", "throughput": 4407.59, "total_tokens": 111077200} {"current_steps": 51470, "total_steps": 61300, "loss": 0.3208, "lr": 3.816166771989218e-06, "epoch": 8.396411092985318, "percentage": 83.96, "elapsed_time": "7:00:03", "remaining_time": "1:20:13", "throughput": 4407.63, "total_tokens": 111088016} {"current_steps": 51475, "total_steps": 61300, "loss": 0.326, "lr": 3.812387772071668e-06, "epoch": 8.397226753670473, "percentage": 83.97, "elapsed_time": "7:00:05", "remaining_time": "1:20:11", "throughput": 4407.66, "total_tokens": 111098320} {"current_steps": 51480, "total_steps": 61300, "loss": 0.3267, "lr": 3.808610489729472e-06, "epoch": 8.398042414355627, "percentage": 83.98, "elapsed_time": "7:00:07", "remaining_time": "1:20:08", "throughput": 4407.7, "total_tokens": 111108528} {"current_steps": 51485, "total_steps": 61300, "loss": 0.3238, "lr": 3.804834925268838e-06, "epoch": 8.398858075040783, "percentage": 83.99, "elapsed_time": "7:00:10", "remaining_time": "1:20:06", "throughput": 4407.74, "total_tokens": 111120080} {"current_steps": 51490, "total_steps": 61300, "loss": 0.3497, "lr": 3.801061078995827e-06, "epoch": 8.399673735725939, "percentage": 84.0, "elapsed_time": "7:00:12", "remaining_time": "1:20:03", "throughput": 4407.77, "total_tokens": 111130512} {"current_steps": 51495, "total_steps": 61300, "loss": 0.3095, "lr": 3.7972889512163656e-06, "epoch": 8.400489396411093, "percentage": 84.0, "elapsed_time": "7:00:14", "remaining_time": "1:20:01", "throughput": 4407.81, "total_tokens": 111141520} {"current_steps": 51500, "total_steps": 61300, "loss": 0.3105, "lr": 3.7935185422362433e-06, "epoch": 8.401305057096248, "percentage": 84.01, "elapsed_time": "7:00:16", "remaining_time": "1:19:58", "throughput": 4407.85, "total_tokens": 111152112} {"current_steps": 51505, "total_steps": 61300, "loss": 0.3224, "lr": 3.7897498523611104e-06, "epoch": 8.402120717781402, "percentage": 84.02, "elapsed_time": "7:00:19", "remaining_time": "1:19:56", "throughput": 4407.88, "total_tokens": 111162896} {"current_steps": 51510, "total_steps": 61300, "loss": 0.318, "lr": 3.7859828818964716e-06, "epoch": 8.402936378466558, "percentage": 84.03, "elapsed_time": "7:00:21", "remaining_time": "1:19:53", "throughput": 4407.92, "total_tokens": 111173616} {"current_steps": 51515, "total_steps": 61300, "loss": 0.338, "lr": 3.7822176311477027e-06, "epoch": 8.403752039151712, "percentage": 84.04, "elapsed_time": "7:00:23", "remaining_time": "1:19:51", "throughput": 4407.96, "total_tokens": 111183856} {"current_steps": 51520, "total_steps": 61300, "loss": 0.3487, "lr": 3.7784541004200287e-06, "epoch": 8.404567699836868, "percentage": 84.05, "elapsed_time": "7:00:25", "remaining_time": "1:19:48", "throughput": 4407.99, "total_tokens": 111193936} {"current_steps": 51525, "total_steps": 61300, "loss": 0.3076, "lr": 3.774692290018542e-06, "epoch": 8.405383360522023, "percentage": 84.05, "elapsed_time": "7:00:27", "remaining_time": "1:19:46", "throughput": 4408.02, "total_tokens": 111204912} {"current_steps": 51530, "total_steps": 61300, "loss": 0.3387, "lr": 3.770932200248195e-06, "epoch": 8.406199021207177, "percentage": 84.06, "elapsed_time": "7:00:30", "remaining_time": "1:19:43", "throughput": 4408.06, "total_tokens": 111215408} {"current_steps": 51535, "total_steps": 61300, "loss": 0.3007, "lr": 3.7671738314137978e-06, "epoch": 8.407014681892333, "percentage": 84.07, "elapsed_time": "7:00:32", "remaining_time": "1:19:41", "throughput": 4408.09, "total_tokens": 111227056} {"current_steps": 51540, "total_steps": 61300, "loss": 0.3517, "lr": 3.7634171838200253e-06, "epoch": 8.407830342577487, "percentage": 84.08, "elapsed_time": "7:00:34", "remaining_time": "1:19:38", "throughput": 4408.13, "total_tokens": 111238512} {"current_steps": 51545, "total_steps": 61300, "loss": 0.3392, "lr": 3.75966225777141e-06, "epoch": 8.408646003262643, "percentage": 84.09, "elapsed_time": "7:00:37", "remaining_time": "1:19:36", "throughput": 4408.17, "total_tokens": 111249392} {"current_steps": 51550, "total_steps": 61300, "loss": 0.3466, "lr": 3.7559090535723427e-06, "epoch": 8.409461663947798, "percentage": 84.09, "elapsed_time": "7:00:39", "remaining_time": "1:19:33", "throughput": 4408.21, "total_tokens": 111259600} {"current_steps": 51555, "total_steps": 61300, "loss": 0.3285, "lr": 3.7521575715270817e-06, "epoch": 8.410277324632952, "percentage": 84.1, "elapsed_time": "7:00:41", "remaining_time": "1:19:31", "throughput": 4408.24, "total_tokens": 111270032} {"current_steps": 51560, "total_steps": 61300, "loss": 0.3411, "lr": 3.748407811939736e-06, "epoch": 8.411092985318108, "percentage": 84.11, "elapsed_time": "7:00:43", "remaining_time": "1:19:28", "throughput": 4408.27, "total_tokens": 111279504} {"current_steps": 51565, "total_steps": 61300, "loss": 0.3523, "lr": 3.7446597751142844e-06, "epoch": 8.411908646003262, "percentage": 84.12, "elapsed_time": "7:00:45", "remaining_time": "1:19:26", "throughput": 4408.31, "total_tokens": 111291504} {"current_steps": 51570, "total_steps": 61300, "loss": 0.3767, "lr": 3.7409134613545587e-06, "epoch": 8.412724306688418, "percentage": 84.13, "elapsed_time": "7:00:48", "remaining_time": "1:19:23", "throughput": 4408.36, "total_tokens": 111303152} {"current_steps": 51575, "total_steps": 61300, "loss": 0.3638, "lr": 3.7371688709642555e-06, "epoch": 8.413539967373573, "percentage": 84.14, "elapsed_time": "7:00:50", "remaining_time": "1:19:21", "throughput": 4408.4, "total_tokens": 111313232} {"current_steps": 51580, "total_steps": 61300, "loss": 0.3168, "lr": 3.7334260042469232e-06, "epoch": 8.414355628058727, "percentage": 84.14, "elapsed_time": "7:00:52", "remaining_time": "1:19:18", "throughput": 4408.43, "total_tokens": 111324240} {"current_steps": 51585, "total_steps": 61300, "loss": 0.3209, "lr": 3.7296848615059913e-06, "epoch": 8.415171288743883, "percentage": 84.15, "elapsed_time": "7:00:54", "remaining_time": "1:19:16", "throughput": 4408.47, "total_tokens": 111335056} {"current_steps": 51590, "total_steps": 61300, "loss": 0.3338, "lr": 3.725945443044729e-06, "epoch": 8.415986949429037, "percentage": 84.16, "elapsed_time": "7:00:56", "remaining_time": "1:19:13", "throughput": 4408.5, "total_tokens": 111345200} {"current_steps": 51595, "total_steps": 61300, "loss": 0.3347, "lr": 3.722207749166273e-06, "epoch": 8.416802610114193, "percentage": 84.17, "elapsed_time": "7:00:58", "remaining_time": "1:19:11", "throughput": 4408.53, "total_tokens": 111354640} {"current_steps": 51600, "total_steps": 61300, "loss": 0.3687, "lr": 3.7184717801736186e-06, "epoch": 8.417618270799348, "percentage": 84.18, "elapsed_time": "7:01:01", "remaining_time": "1:19:08", "throughput": 4408.56, "total_tokens": 111365008} {"current_steps": 51605, "total_steps": 61300, "loss": 0.3551, "lr": 3.7147375363696168e-06, "epoch": 8.418433931484502, "percentage": 84.18, "elapsed_time": "7:01:03", "remaining_time": "1:19:06", "throughput": 4408.6, "total_tokens": 111376080} {"current_steps": 51610, "total_steps": 61300, "loss": 0.3478, "lr": 3.7110050180569985e-06, "epoch": 8.419249592169658, "percentage": 84.19, "elapsed_time": "7:01:05", "remaining_time": "1:19:03", "throughput": 4408.64, "total_tokens": 111387376} {"current_steps": 51615, "total_steps": 61300, "loss": 0.3376, "lr": 3.707274225538332e-06, "epoch": 8.420065252854812, "percentage": 84.2, "elapsed_time": "7:01:07", "remaining_time": "1:19:01", "throughput": 4408.67, "total_tokens": 111398224} {"current_steps": 51620, "total_steps": 61300, "loss": 0.3459, "lr": 3.7035451591160535e-06, "epoch": 8.420880913539968, "percentage": 84.21, "elapsed_time": "7:01:10", "remaining_time": "1:18:58", "throughput": 4408.71, "total_tokens": 111408624} {"current_steps": 51625, "total_steps": 61300, "loss": 0.3277, "lr": 3.699817819092463e-06, "epoch": 8.421696574225122, "percentage": 84.22, "elapsed_time": "7:01:12", "remaining_time": "1:18:56", "throughput": 4408.75, "total_tokens": 111419664} {"current_steps": 51630, "total_steps": 61300, "loss": 0.3034, "lr": 3.6960922057697163e-06, "epoch": 8.422512234910277, "percentage": 84.23, "elapsed_time": "7:01:14", "remaining_time": "1:18:53", "throughput": 4408.78, "total_tokens": 111430480} {"current_steps": 51635, "total_steps": 61300, "loss": 0.3214, "lr": 3.6923683194498295e-06, "epoch": 8.423327895595433, "percentage": 84.23, "elapsed_time": "7:01:16", "remaining_time": "1:18:51", "throughput": 4408.81, "total_tokens": 111439984} {"current_steps": 51640, "total_steps": 61300, "loss": 0.3705, "lr": 3.6886461604346807e-06, "epoch": 8.424143556280587, "percentage": 84.24, "elapsed_time": "7:01:19", "remaining_time": "1:18:48", "throughput": 4408.85, "total_tokens": 111451472} {"current_steps": 51645, "total_steps": 61300, "loss": 0.3442, "lr": 3.6849257290260066e-06, "epoch": 8.424959216965743, "percentage": 84.25, "elapsed_time": "7:01:21", "remaining_time": "1:18:46", "throughput": 4408.89, "total_tokens": 111462544} {"current_steps": 51650, "total_steps": 61300, "loss": 0.3318, "lr": 3.6812070255254043e-06, "epoch": 8.425774877650896, "percentage": 84.26, "elapsed_time": "7:01:23", "remaining_time": "1:18:43", "throughput": 4408.95, "total_tokens": 111474800} {"current_steps": 51655, "total_steps": 61300, "loss": 0.3194, "lr": 3.677490050234331e-06, "epoch": 8.426590538336052, "percentage": 84.27, "elapsed_time": "7:01:26", "remaining_time": "1:18:41", "throughput": 4408.98, "total_tokens": 111485776} {"current_steps": 51660, "total_steps": 61300, "loss": 0.3665, "lr": 3.6737748034541054e-06, "epoch": 8.427406199021208, "percentage": 84.27, "elapsed_time": "7:01:28", "remaining_time": "1:18:38", "throughput": 4409.02, "total_tokens": 111497616} {"current_steps": 51665, "total_steps": 61300, "loss": 0.3159, "lr": 3.670061285485901e-06, "epoch": 8.428221859706362, "percentage": 84.28, "elapsed_time": "7:01:30", "remaining_time": "1:18:36", "throughput": 4409.06, "total_tokens": 111508848} {"current_steps": 51670, "total_steps": 61300, "loss": 0.3135, "lr": 3.6663494966307553e-06, "epoch": 8.429037520391518, "percentage": 84.29, "elapsed_time": "7:01:33", "remaining_time": "1:18:34", "throughput": 4409.11, "total_tokens": 111520816} {"current_steps": 51675, "total_steps": 61300, "loss": 0.3278, "lr": 3.662639437189566e-06, "epoch": 8.429853181076671, "percentage": 84.3, "elapsed_time": "7:01:35", "remaining_time": "1:18:31", "throughput": 4409.14, "total_tokens": 111531984} {"current_steps": 51680, "total_steps": 61300, "loss": 0.3405, "lr": 3.65893110746309e-06, "epoch": 8.430668841761827, "percentage": 84.31, "elapsed_time": "7:01:37", "remaining_time": "1:18:29", "throughput": 4409.17, "total_tokens": 111542800} {"current_steps": 51685, "total_steps": 61300, "loss": 0.3519, "lr": 3.655224507751934e-06, "epoch": 8.431484502446983, "percentage": 84.31, "elapsed_time": "7:01:39", "remaining_time": "1:18:26", "throughput": 4409.21, "total_tokens": 111553040} {"current_steps": 51690, "total_steps": 61300, "loss": 0.3261, "lr": 3.6515196383565873e-06, "epoch": 8.432300163132137, "percentage": 84.32, "elapsed_time": "7:01:42", "remaining_time": "1:18:24", "throughput": 4409.25, "total_tokens": 111563120} {"current_steps": 51695, "total_steps": 61300, "loss": 0.3348, "lr": 3.6478164995773807e-06, "epoch": 8.433115823817293, "percentage": 84.33, "elapsed_time": "7:01:44", "remaining_time": "1:18:21", "throughput": 4409.28, "total_tokens": 111573776} {"current_steps": 51700, "total_steps": 61300, "loss": 0.3288, "lr": 3.644115091714509e-06, "epoch": 8.433931484502446, "percentage": 84.34, "elapsed_time": "7:01:46", "remaining_time": "1:18:19", "throughput": 4409.32, "total_tokens": 111584080} {"current_steps": 51705, "total_steps": 61300, "loss": 0.3527, "lr": 3.640415415068027e-06, "epoch": 8.434747145187602, "percentage": 84.35, "elapsed_time": "7:01:48", "remaining_time": "1:18:16", "throughput": 4409.36, "total_tokens": 111594480} {"current_steps": 51710, "total_steps": 61300, "loss": 0.3114, "lr": 3.6367174699378476e-06, "epoch": 8.435562805872756, "percentage": 84.36, "elapsed_time": "7:01:50", "remaining_time": "1:18:14", "throughput": 4409.39, "total_tokens": 111604656} {"current_steps": 51715, "total_steps": 61300, "loss": 0.3427, "lr": 3.6330212566237477e-06, "epoch": 8.436378466557912, "percentage": 84.36, "elapsed_time": "7:01:53", "remaining_time": "1:18:11", "throughput": 4409.44, "total_tokens": 111616304} {"current_steps": 51720, "total_steps": 61300, "loss": 0.3754, "lr": 3.6293267754253566e-06, "epoch": 8.437194127243067, "percentage": 84.37, "elapsed_time": "7:01:55", "remaining_time": "1:18:09", "throughput": 4409.47, "total_tokens": 111627920} {"current_steps": 51725, "total_steps": 61300, "loss": 0.324, "lr": 3.6256340266421747e-06, "epoch": 8.438009787928221, "percentage": 84.38, "elapsed_time": "7:01:57", "remaining_time": "1:18:06", "throughput": 4409.51, "total_tokens": 111638864} {"current_steps": 51730, "total_steps": 61300, "loss": 0.3494, "lr": 3.6219430105735476e-06, "epoch": 8.438825448613377, "percentage": 84.39, "elapsed_time": "7:01:59", "remaining_time": "1:18:04", "throughput": 4409.55, "total_tokens": 111649296} {"current_steps": 51735, "total_steps": 61300, "loss": 0.3138, "lr": 3.6182537275186947e-06, "epoch": 8.439641109298531, "percentage": 84.4, "elapsed_time": "7:02:01", "remaining_time": "1:18:01", "throughput": 4409.58, "total_tokens": 111659152} {"current_steps": 51740, "total_steps": 61300, "loss": 0.3568, "lr": 3.614566177776682e-06, "epoch": 8.440456769983687, "percentage": 84.4, "elapsed_time": "7:02:04", "remaining_time": "1:17:59", "throughput": 4409.61, "total_tokens": 111669744} {"current_steps": 51745, "total_steps": 61300, "loss": 0.3364, "lr": 3.6108803616464376e-06, "epoch": 8.441272430668842, "percentage": 84.41, "elapsed_time": "7:02:06", "remaining_time": "1:17:56", "throughput": 4409.65, "total_tokens": 111680304} {"current_steps": 51750, "total_steps": 61300, "loss": 0.3262, "lr": 3.6071962794267667e-06, "epoch": 8.442088091353996, "percentage": 84.42, "elapsed_time": "7:02:08", "remaining_time": "1:17:54", "throughput": 4409.69, "total_tokens": 111692400} {"current_steps": 51755, "total_steps": 61300, "loss": 0.3405, "lr": 3.603513931416311e-06, "epoch": 8.442903752039152, "percentage": 84.43, "elapsed_time": "7:02:10", "remaining_time": "1:17:51", "throughput": 4409.73, "total_tokens": 111702160} {"current_steps": 51760, "total_steps": 61300, "loss": 0.3188, "lr": 3.5998333179135783e-06, "epoch": 8.443719412724306, "percentage": 84.44, "elapsed_time": "7:02:13", "remaining_time": "1:17:49", "throughput": 4409.77, "total_tokens": 111713712} {"current_steps": 51765, "total_steps": 61300, "loss": 0.3148, "lr": 3.596154439216942e-06, "epoch": 8.444535073409462, "percentage": 84.45, "elapsed_time": "7:02:15", "remaining_time": "1:17:46", "throughput": 4409.8, "total_tokens": 111724112} {"current_steps": 51770, "total_steps": 61300, "loss": 0.332, "lr": 3.5924772956246273e-06, "epoch": 8.445350734094617, "percentage": 84.45, "elapsed_time": "7:02:17", "remaining_time": "1:17:44", "throughput": 4409.84, "total_tokens": 111735504} {"current_steps": 51775, "total_steps": 61300, "loss": 0.3479, "lr": 3.5888018874347257e-06, "epoch": 8.446166394779771, "percentage": 84.46, "elapsed_time": "7:02:19", "remaining_time": "1:17:41", "throughput": 4409.87, "total_tokens": 111744912} {"current_steps": 51780, "total_steps": 61300, "loss": 0.3139, "lr": 3.5851282149451798e-06, "epoch": 8.446982055464927, "percentage": 84.47, "elapsed_time": "7:02:22", "remaining_time": "1:17:39", "throughput": 4409.91, "total_tokens": 111756080} {"current_steps": 51785, "total_steps": 61300, "loss": 0.3152, "lr": 3.5814562784538012e-06, "epoch": 8.447797716150081, "percentage": 84.48, "elapsed_time": "7:02:24", "remaining_time": "1:17:36", "throughput": 4409.94, "total_tokens": 111766928} {"current_steps": 51790, "total_steps": 61300, "loss": 0.3234, "lr": 3.5777860782582523e-06, "epoch": 8.448613376835237, "percentage": 84.49, "elapsed_time": "7:02:26", "remaining_time": "1:17:34", "throughput": 4409.97, "total_tokens": 111775760} {"current_steps": 51795, "total_steps": 61300, "loss": 0.353, "lr": 3.5741176146560558e-06, "epoch": 8.449429037520392, "percentage": 84.49, "elapsed_time": "7:02:28", "remaining_time": "1:17:31", "throughput": 4410.02, "total_tokens": 111787184} {"current_steps": 51800, "total_steps": 61300, "loss": 0.3311, "lr": 3.570450887944601e-06, "epoch": 8.450244698205546, "percentage": 84.5, "elapsed_time": "7:02:30", "remaining_time": "1:17:29", "throughput": 4410.04, "total_tokens": 111798064} {"current_steps": 51805, "total_steps": 61300, "loss": 0.365, "lr": 3.5667858984211323e-06, "epoch": 8.451060358890702, "percentage": 84.51, "elapsed_time": "7:02:32", "remaining_time": "1:17:26", "throughput": 4410.07, "total_tokens": 111808016} {"current_steps": 51810, "total_steps": 61300, "loss": 0.3361, "lr": 3.5631226463827492e-06, "epoch": 8.451876019575856, "percentage": 84.52, "elapsed_time": "7:02:35", "remaining_time": "1:17:24", "throughput": 4410.12, "total_tokens": 111819568} {"current_steps": 51815, "total_steps": 61300, "loss": 0.3516, "lr": 3.5594611321264125e-06, "epoch": 8.452691680261012, "percentage": 84.53, "elapsed_time": "7:02:37", "remaining_time": "1:17:21", "throughput": 4410.14, "total_tokens": 111829840} {"current_steps": 51820, "total_steps": 61300, "loss": 0.3257, "lr": 3.5558013559489457e-06, "epoch": 8.453507340946166, "percentage": 84.54, "elapsed_time": "7:02:39", "remaining_time": "1:17:19", "throughput": 4410.18, "total_tokens": 111841136} {"current_steps": 51825, "total_steps": 61300, "loss": 0.3198, "lr": 3.5521433181470306e-06, "epoch": 8.454323001631321, "percentage": 84.54, "elapsed_time": "7:02:42", "remaining_time": "1:17:16", "throughput": 4410.22, "total_tokens": 111852208} {"current_steps": 51830, "total_steps": 61300, "loss": 0.3078, "lr": 3.5484870190171994e-06, "epoch": 8.455138662316477, "percentage": 84.55, "elapsed_time": "7:02:44", "remaining_time": "1:17:14", "throughput": 4410.25, "total_tokens": 111862608} {"current_steps": 51835, "total_steps": 61300, "loss": 0.3358, "lr": 3.5448324588558566e-06, "epoch": 8.455954323001631, "percentage": 84.56, "elapsed_time": "7:02:46", "remaining_time": "1:17:11", "throughput": 4410.28, "total_tokens": 111873424} {"current_steps": 51840, "total_steps": 61300, "loss": 0.319, "lr": 3.541179637959255e-06, "epoch": 8.456769983686787, "percentage": 84.57, "elapsed_time": "7:02:48", "remaining_time": "1:17:09", "throughput": 4410.31, "total_tokens": 111884016} {"current_steps": 51845, "total_steps": 61300, "loss": 0.3157, "lr": 3.537528556623515e-06, "epoch": 8.45758564437194, "percentage": 84.58, "elapsed_time": "7:02:51", "remaining_time": "1:17:06", "throughput": 4410.36, "total_tokens": 111895440} {"current_steps": 51850, "total_steps": 61300, "loss": 0.2942, "lr": 3.5338792151446087e-06, "epoch": 8.458401305057096, "percentage": 84.58, "elapsed_time": "7:02:53", "remaining_time": "1:17:04", "throughput": 4410.39, "total_tokens": 111907120} {"current_steps": 51855, "total_steps": 61300, "loss": 0.3499, "lr": 3.530231613818372e-06, "epoch": 8.459216965742252, "percentage": 84.59, "elapsed_time": "7:02:55", "remaining_time": "1:17:01", "throughput": 4410.43, "total_tokens": 111916464} {"current_steps": 51860, "total_steps": 61300, "loss": 0.3395, "lr": 3.526585752940495e-06, "epoch": 8.460032626427406, "percentage": 84.6, "elapsed_time": "7:02:57", "remaining_time": "1:16:59", "throughput": 4410.47, "total_tokens": 111927376} {"current_steps": 51865, "total_steps": 61300, "loss": 0.3194, "lr": 3.522941632806534e-06, "epoch": 8.460848287112562, "percentage": 84.61, "elapsed_time": "7:02:59", "remaining_time": "1:16:56", "throughput": 4410.51, "total_tokens": 111937392} {"current_steps": 51870, "total_steps": 61300, "loss": 0.2969, "lr": 3.519299253711897e-06, "epoch": 8.461663947797716, "percentage": 84.62, "elapsed_time": "7:03:02", "remaining_time": "1:16:54", "throughput": 4410.55, "total_tokens": 111948848} {"current_steps": 51875, "total_steps": 61300, "loss": 0.3293, "lr": 3.515658615951856e-06, "epoch": 8.462479608482871, "percentage": 84.62, "elapsed_time": "7:03:04", "remaining_time": "1:16:51", "throughput": 4410.58, "total_tokens": 111959664} {"current_steps": 51880, "total_steps": 61300, "loss": 0.3346, "lr": 3.5120197198215356e-06, "epoch": 8.463295269168025, "percentage": 84.63, "elapsed_time": "7:03:06", "remaining_time": "1:16:49", "throughput": 4410.61, "total_tokens": 111969712} {"current_steps": 51885, "total_steps": 61300, "loss": 0.3242, "lr": 3.508382565615928e-06, "epoch": 8.464110929853181, "percentage": 84.64, "elapsed_time": "7:03:08", "remaining_time": "1:16:47", "throughput": 4410.65, "total_tokens": 111981168} {"current_steps": 51890, "total_steps": 61300, "loss": 0.3431, "lr": 3.5047471536298697e-06, "epoch": 8.464926590538337, "percentage": 84.65, "elapsed_time": "7:03:11", "remaining_time": "1:16:44", "throughput": 4410.69, "total_tokens": 111991952} {"current_steps": 51895, "total_steps": 61300, "loss": 0.3408, "lr": 3.5011134841580805e-06, "epoch": 8.46574225122349, "percentage": 84.66, "elapsed_time": "7:03:13", "remaining_time": "1:16:42", "throughput": 4410.72, "total_tokens": 112003024} {"current_steps": 51900, "total_steps": 61300, "loss": 0.3042, "lr": 3.4974815574951135e-06, "epoch": 8.466557911908646, "percentage": 84.67, "elapsed_time": "7:03:15", "remaining_time": "1:16:39", "throughput": 4410.76, "total_tokens": 112013360} {"current_steps": 51905, "total_steps": 61300, "loss": 0.3205, "lr": 3.4938513739353973e-06, "epoch": 8.4673735725938, "percentage": 84.67, "elapsed_time": "7:03:17", "remaining_time": "1:16:37", "throughput": 4410.78, "total_tokens": 112023664} {"current_steps": 51910, "total_steps": 61300, "loss": 0.3558, "lr": 3.4902229337732074e-06, "epoch": 8.468189233278956, "percentage": 84.68, "elapsed_time": "7:03:20", "remaining_time": "1:16:34", "throughput": 4410.82, "total_tokens": 112034928} {"current_steps": 51915, "total_steps": 61300, "loss": 0.364, "lr": 3.4865962373026805e-06, "epoch": 8.469004893964112, "percentage": 84.69, "elapsed_time": "7:03:22", "remaining_time": "1:16:32", "throughput": 4410.86, "total_tokens": 112046128} {"current_steps": 51920, "total_steps": 61300, "loss": 0.3386, "lr": 3.4829712848178293e-06, "epoch": 8.469820554649266, "percentage": 84.7, "elapsed_time": "7:03:24", "remaining_time": "1:16:29", "throughput": 4410.91, "total_tokens": 112056944} {"current_steps": 51925, "total_steps": 61300, "loss": 0.2945, "lr": 3.4793480766124986e-06, "epoch": 8.470636215334421, "percentage": 84.71, "elapsed_time": "7:03:26", "remaining_time": "1:16:27", "throughput": 4410.94, "total_tokens": 112067472} {"current_steps": 51930, "total_steps": 61300, "loss": 0.3488, "lr": 3.4757266129804093e-06, "epoch": 8.471451876019575, "percentage": 84.71, "elapsed_time": "7:03:28", "remaining_time": "1:16:24", "throughput": 4410.96, "total_tokens": 112076400} {"current_steps": 51935, "total_steps": 61300, "loss": 0.3216, "lr": 3.4721068942151324e-06, "epoch": 8.47226753670473, "percentage": 84.72, "elapsed_time": "7:03:30", "remaining_time": "1:16:22", "throughput": 4411.01, "total_tokens": 112087312} {"current_steps": 51940, "total_steps": 61300, "loss": 0.3183, "lr": 3.4684889206101025e-06, "epoch": 8.473083197389887, "percentage": 84.73, "elapsed_time": "7:03:33", "remaining_time": "1:16:19", "throughput": 4411.05, "total_tokens": 112098544} {"current_steps": 51945, "total_steps": 61300, "loss": 0.3677, "lr": 3.464872692458612e-06, "epoch": 8.47389885807504, "percentage": 84.74, "elapsed_time": "7:03:35", "remaining_time": "1:16:17", "throughput": 4411.08, "total_tokens": 112108304} {"current_steps": 51950, "total_steps": 61300, "loss": 0.3389, "lr": 3.4612582100538082e-06, "epoch": 8.474714518760196, "percentage": 84.75, "elapsed_time": "7:03:37", "remaining_time": "1:16:14", "throughput": 4411.12, "total_tokens": 112119600} {"current_steps": 51955, "total_steps": 61300, "loss": 0.3188, "lr": 3.4576454736887003e-06, "epoch": 8.47553017944535, "percentage": 84.76, "elapsed_time": "7:03:39", "remaining_time": "1:16:12", "throughput": 4411.16, "total_tokens": 112130192} {"current_steps": 51960, "total_steps": 61300, "loss": 0.3494, "lr": 3.4540344836561546e-06, "epoch": 8.476345840130506, "percentage": 84.76, "elapsed_time": "7:03:42", "remaining_time": "1:16:09", "throughput": 4411.2, "total_tokens": 112142288} {"current_steps": 51965, "total_steps": 61300, "loss": 0.3405, "lr": 3.4504252402488974e-06, "epoch": 8.477161500815662, "percentage": 84.77, "elapsed_time": "7:03:44", "remaining_time": "1:16:07", "throughput": 4411.24, "total_tokens": 112154032} {"current_steps": 51970, "total_steps": 61300, "loss": 0.3081, "lr": 3.446817743759512e-06, "epoch": 8.477977161500815, "percentage": 84.78, "elapsed_time": "7:03:46", "remaining_time": "1:16:04", "throughput": 4411.28, "total_tokens": 112165520} {"current_steps": 51975, "total_steps": 61300, "loss": 0.3474, "lr": 3.443211994480439e-06, "epoch": 8.478792822185971, "percentage": 84.79, "elapsed_time": "7:03:49", "remaining_time": "1:16:02", "throughput": 4411.31, "total_tokens": 112176560} {"current_steps": 51980, "total_steps": 61300, "loss": 0.3343, "lr": 3.4396079927039804e-06, "epoch": 8.479608482871125, "percentage": 84.8, "elapsed_time": "7:03:51", "remaining_time": "1:15:59", "throughput": 4411.35, "total_tokens": 112187248} {"current_steps": 51985, "total_steps": 61300, "loss": 0.3223, "lr": 3.436005738722292e-06, "epoch": 8.48042414355628, "percentage": 84.8, "elapsed_time": "7:03:53", "remaining_time": "1:15:57", "throughput": 4411.38, "total_tokens": 112198128} {"current_steps": 51990, "total_steps": 61300, "loss": 0.3323, "lr": 3.432405232827396e-06, "epoch": 8.481239804241435, "percentage": 84.81, "elapsed_time": "7:03:56", "remaining_time": "1:15:54", "throughput": 4411.42, "total_tokens": 112209680} {"current_steps": 51995, "total_steps": 61300, "loss": 0.3175, "lr": 3.428806475311164e-06, "epoch": 8.48205546492659, "percentage": 84.82, "elapsed_time": "7:03:58", "remaining_time": "1:15:52", "throughput": 4411.46, "total_tokens": 112220688} {"current_steps": 52000, "total_steps": 61300, "loss": 0.3264, "lr": 3.4252094664653316e-06, "epoch": 8.482871125611746, "percentage": 84.83, "elapsed_time": "7:04:00", "remaining_time": "1:15:49", "throughput": 4411.5, "total_tokens": 112231632} {"current_steps": 52005, "total_steps": 61300, "loss": 0.3436, "lr": 3.4216142065814806e-06, "epoch": 8.4836867862969, "percentage": 84.84, "elapsed_time": "7:04:02", "remaining_time": "1:15:47", "throughput": 4411.53, "total_tokens": 112240592} {"current_steps": 52010, "total_steps": 61300, "loss": 0.3414, "lr": 3.418020695951077e-06, "epoch": 8.484502446982056, "percentage": 84.85, "elapsed_time": "7:04:04", "remaining_time": "1:15:44", "throughput": 4411.56, "total_tokens": 112251440} {"current_steps": 52015, "total_steps": 61300, "loss": 0.3216, "lr": 3.414428934865421e-06, "epoch": 8.48531810766721, "percentage": 84.85, "elapsed_time": "7:04:07", "remaining_time": "1:15:42", "throughput": 4411.59, "total_tokens": 112262192} {"current_steps": 52020, "total_steps": 61300, "loss": 0.3419, "lr": 3.4108389236156806e-06, "epoch": 8.486133768352365, "percentage": 84.86, "elapsed_time": "7:04:09", "remaining_time": "1:15:40", "throughput": 4411.64, "total_tokens": 112273808} {"current_steps": 52025, "total_steps": 61300, "loss": 0.3206, "lr": 3.4072506624928808e-06, "epoch": 8.486949429037521, "percentage": 84.87, "elapsed_time": "7:04:11", "remaining_time": "1:15:37", "throughput": 4411.68, "total_tokens": 112284304} {"current_steps": 52030, "total_steps": 61300, "loss": 0.3291, "lr": 3.4036641517878997e-06, "epoch": 8.487765089722675, "percentage": 84.88, "elapsed_time": "7:04:13", "remaining_time": "1:15:35", "throughput": 4411.72, "total_tokens": 112295152} {"current_steps": 52035, "total_steps": 61300, "loss": 0.3719, "lr": 3.400079391791483e-06, "epoch": 8.48858075040783, "percentage": 84.89, "elapsed_time": "7:04:15", "remaining_time": "1:15:32", "throughput": 4411.76, "total_tokens": 112305648} {"current_steps": 52040, "total_steps": 61300, "loss": 0.3139, "lr": 3.3964963827942257e-06, "epoch": 8.489396411092985, "percentage": 84.89, "elapsed_time": "7:04:18", "remaining_time": "1:15:30", "throughput": 4411.79, "total_tokens": 112316144} {"current_steps": 52045, "total_steps": 61300, "loss": 0.3251, "lr": 3.3929151250865903e-06, "epoch": 8.49021207177814, "percentage": 84.9, "elapsed_time": "7:04:20", "remaining_time": "1:15:27", "throughput": 4411.82, "total_tokens": 112328560} {"current_steps": 52050, "total_steps": 61300, "loss": 0.3519, "lr": 3.389335618958886e-06, "epoch": 8.491027732463296, "percentage": 84.91, "elapsed_time": "7:04:22", "remaining_time": "1:15:25", "throughput": 4411.86, "total_tokens": 112338640} {"current_steps": 52055, "total_steps": 61300, "loss": 0.3327, "lr": 3.385757864701286e-06, "epoch": 8.49184339314845, "percentage": 84.92, "elapsed_time": "7:04:25", "remaining_time": "1:15:22", "throughput": 4411.89, "total_tokens": 112349232} {"current_steps": 52060, "total_steps": 61300, "loss": 0.3706, "lr": 3.3821818626038198e-06, "epoch": 8.492659053833606, "percentage": 84.93, "elapsed_time": "7:04:27", "remaining_time": "1:15:20", "throughput": 4411.93, "total_tokens": 112360400} {"current_steps": 52065, "total_steps": 61300, "loss": 0.365, "lr": 3.378607612956386e-06, "epoch": 8.49347471451876, "percentage": 84.93, "elapsed_time": "7:04:29", "remaining_time": "1:15:17", "throughput": 4411.97, "total_tokens": 112371408} {"current_steps": 52070, "total_steps": 61300, "loss": 0.3076, "lr": 3.375035116048722e-06, "epoch": 8.494290375203915, "percentage": 84.94, "elapsed_time": "7:04:32", "remaining_time": "1:15:15", "throughput": 4412.0, "total_tokens": 112382544} {"current_steps": 52075, "total_steps": 61300, "loss": 0.3689, "lr": 3.371464372170438e-06, "epoch": 8.49510603588907, "percentage": 84.95, "elapsed_time": "7:04:34", "remaining_time": "1:15:12", "throughput": 4412.03, "total_tokens": 112392688} {"current_steps": 52080, "total_steps": 61300, "loss": 0.3145, "lr": 3.3678953816109916e-06, "epoch": 8.495921696574225, "percentage": 84.96, "elapsed_time": "7:04:36", "remaining_time": "1:15:10", "throughput": 4412.07, "total_tokens": 112404240} {"current_steps": 52085, "total_steps": 61300, "loss": 0.3119, "lr": 3.3643281446597092e-06, "epoch": 8.49673735725938, "percentage": 84.97, "elapsed_time": "7:04:38", "remaining_time": "1:15:07", "throughput": 4412.1, "total_tokens": 112414768} {"current_steps": 52090, "total_steps": 61300, "loss": 0.3378, "lr": 3.3607626616057624e-06, "epoch": 8.497553017944535, "percentage": 84.98, "elapsed_time": "7:04:40", "remaining_time": "1:15:05", "throughput": 4412.14, "total_tokens": 112425424} {"current_steps": 52095, "total_steps": 61300, "loss": 0.3119, "lr": 3.3571989327381923e-06, "epoch": 8.49836867862969, "percentage": 84.98, "elapsed_time": "7:04:43", "remaining_time": "1:15:02", "throughput": 4412.18, "total_tokens": 112436720} {"current_steps": 52100, "total_steps": 61300, "loss": 0.3368, "lr": 3.3536369583458905e-06, "epoch": 8.499184339314844, "percentage": 84.99, "elapsed_time": "7:04:45", "remaining_time": "1:15:00", "throughput": 4412.21, "total_tokens": 112446896} {"current_steps": 52105, "total_steps": 61300, "loss": 0.3273, "lr": 3.3500767387176114e-06, "epoch": 8.5, "percentage": 85.0, "elapsed_time": "7:04:47", "remaining_time": "1:14:57", "throughput": 4412.24, "total_tokens": 112458064} {"current_steps": 52105, "total_steps": 61300, "eval_loss": 0.3358362317085266, "epoch": 8.5, "percentage": 85.0, "elapsed_time": "7:06:59", "remaining_time": "1:15:21", "throughput": 4389.54, "total_tokens": 112458064} {"current_steps": 52110, "total_steps": 61300, "loss": 0.3168, "lr": 3.3465182741419547e-06, "epoch": 8.500815660685156, "percentage": 85.01, "elapsed_time": "7:07:03", "remaining_time": "1:15:18", "throughput": 4389.36, "total_tokens": 112469200} {"current_steps": 52115, "total_steps": 61300, "loss": 0.3316, "lr": 3.3429615649074013e-06, "epoch": 8.50163132137031, "percentage": 85.02, "elapsed_time": "7:07:05", "remaining_time": "1:15:16", "throughput": 4389.39, "total_tokens": 112479888} {"current_steps": 52120, "total_steps": 61300, "loss": 0.3381, "lr": 3.3394066113022706e-06, "epoch": 8.502446982055465, "percentage": 85.02, "elapsed_time": "7:07:07", "remaining_time": "1:15:13", "throughput": 4389.44, "total_tokens": 112490896} {"current_steps": 52125, "total_steps": 61300, "loss": 0.3448, "lr": 3.335853413614745e-06, "epoch": 8.50326264274062, "percentage": 85.03, "elapsed_time": "7:07:10", "remaining_time": "1:15:11", "throughput": 4389.48, "total_tokens": 112503152} {"current_steps": 52130, "total_steps": 61300, "loss": 0.3231, "lr": 3.332301972132862e-06, "epoch": 8.504078303425775, "percentage": 85.04, "elapsed_time": "7:07:12", "remaining_time": "1:15:08", "throughput": 4389.53, "total_tokens": 112513936} {"current_steps": 52135, "total_steps": 61300, "loss": 0.3252, "lr": 3.3287522871445263e-06, "epoch": 8.50489396411093, "percentage": 85.05, "elapsed_time": "7:07:14", "remaining_time": "1:15:06", "throughput": 4389.56, "total_tokens": 112523536} {"current_steps": 52140, "total_steps": 61300, "loss": 0.3095, "lr": 3.3252043589374866e-06, "epoch": 8.505709624796085, "percentage": 85.06, "elapsed_time": "7:07:16", "remaining_time": "1:15:03", "throughput": 4389.59, "total_tokens": 112534512} {"current_steps": 52145, "total_steps": 61300, "loss": 0.3253, "lr": 3.3216581877993564e-06, "epoch": 8.50652528548124, "percentage": 85.07, "elapsed_time": "7:07:19", "remaining_time": "1:15:01", "throughput": 4389.63, "total_tokens": 112546032} {"current_steps": 52150, "total_steps": 61300, "loss": 0.3368, "lr": 3.3181137740176118e-06, "epoch": 8.507340946166394, "percentage": 85.07, "elapsed_time": "7:07:21", "remaining_time": "1:14:58", "throughput": 4389.66, "total_tokens": 112556016} {"current_steps": 52155, "total_steps": 61300, "loss": 0.3219, "lr": 3.3145711178795753e-06, "epoch": 8.50815660685155, "percentage": 85.08, "elapsed_time": "7:07:23", "remaining_time": "1:14:56", "throughput": 4389.69, "total_tokens": 112565520} {"current_steps": 52160, "total_steps": 61300, "loss": 0.3121, "lr": 3.3110302196724368e-06, "epoch": 8.508972267536706, "percentage": 85.09, "elapsed_time": "7:07:25", "remaining_time": "1:14:53", "throughput": 4389.73, "total_tokens": 112575824} {"current_steps": 52165, "total_steps": 61300, "loss": 0.3571, "lr": 3.3074910796832363e-06, "epoch": 8.50978792822186, "percentage": 85.1, "elapsed_time": "7:07:27", "remaining_time": "1:14:51", "throughput": 4389.77, "total_tokens": 112587056} {"current_steps": 52170, "total_steps": 61300, "loss": 0.3244, "lr": 3.303953698198875e-06, "epoch": 8.510603588907015, "percentage": 85.11, "elapsed_time": "7:07:29", "remaining_time": "1:14:48", "throughput": 4389.8, "total_tokens": 112598192} {"current_steps": 52175, "total_steps": 61300, "loss": 0.3247, "lr": 3.300418075506112e-06, "epoch": 8.51141924959217, "percentage": 85.11, "elapsed_time": "7:07:32", "remaining_time": "1:14:46", "throughput": 4389.84, "total_tokens": 112609584} {"current_steps": 52180, "total_steps": 61300, "loss": 0.3299, "lr": 3.296884211891563e-06, "epoch": 8.512234910277325, "percentage": 85.12, "elapsed_time": "7:07:34", "remaining_time": "1:14:43", "throughput": 4389.88, "total_tokens": 112620720} {"current_steps": 52185, "total_steps": 61300, "loss": 0.3508, "lr": 3.293352107641698e-06, "epoch": 8.513050570962479, "percentage": 85.13, "elapsed_time": "7:07:36", "remaining_time": "1:14:41", "throughput": 4389.91, "total_tokens": 112631696} {"current_steps": 52190, "total_steps": 61300, "loss": 0.3382, "lr": 3.2898217630428523e-06, "epoch": 8.513866231647635, "percentage": 85.14, "elapsed_time": "7:07:39", "remaining_time": "1:14:38", "throughput": 4389.95, "total_tokens": 112641872} {"current_steps": 52195, "total_steps": 61300, "loss": 0.3099, "lr": 3.2862931783812083e-06, "epoch": 8.51468189233279, "percentage": 85.15, "elapsed_time": "7:07:41", "remaining_time": "1:14:36", "throughput": 4389.99, "total_tokens": 112652240} {"current_steps": 52200, "total_steps": 61300, "loss": 0.3172, "lr": 3.282766353942815e-06, "epoch": 8.515497553017944, "percentage": 85.15, "elapsed_time": "7:07:43", "remaining_time": "1:14:33", "throughput": 4390.03, "total_tokens": 112663824} {"current_steps": 52205, "total_steps": 61300, "loss": 0.3133, "lr": 3.279241290013568e-06, "epoch": 8.5163132137031, "percentage": 85.16, "elapsed_time": "7:07:45", "remaining_time": "1:14:31", "throughput": 4390.08, "total_tokens": 112675216} {"current_steps": 52210, "total_steps": 61300, "loss": 0.3198, "lr": 3.275717986879237e-06, "epoch": 8.517128874388254, "percentage": 85.17, "elapsed_time": "7:07:47", "remaining_time": "1:14:28", "throughput": 4390.11, "total_tokens": 112684464} {"current_steps": 52215, "total_steps": 61300, "loss": 0.3281, "lr": 3.2721964448254345e-06, "epoch": 8.51794453507341, "percentage": 85.18, "elapsed_time": "7:07:50", "remaining_time": "1:14:26", "throughput": 4390.15, "total_tokens": 112695120} {"current_steps": 52220, "total_steps": 61300, "loss": 0.3281, "lr": 3.268676664137635e-06, "epoch": 8.518760195758565, "percentage": 85.19, "elapsed_time": "7:07:52", "remaining_time": "1:14:23", "throughput": 4390.18, "total_tokens": 112705776} {"current_steps": 52225, "total_steps": 61300, "loss": 0.3262, "lr": 3.2651586451011657e-06, "epoch": 8.51957585644372, "percentage": 85.2, "elapsed_time": "7:07:54", "remaining_time": "1:14:21", "throughput": 4390.21, "total_tokens": 112716368} {"current_steps": 52230, "total_steps": 61300, "loss": 0.3306, "lr": 3.2616423880012153e-06, "epoch": 8.520391517128875, "percentage": 85.2, "elapsed_time": "7:07:56", "remaining_time": "1:14:18", "throughput": 4390.25, "total_tokens": 112727440} {"current_steps": 52235, "total_steps": 61300, "loss": 0.334, "lr": 3.2581278931228363e-06, "epoch": 8.521207177814029, "percentage": 85.21, "elapsed_time": "7:07:58", "remaining_time": "1:14:16", "throughput": 4390.29, "total_tokens": 112736336} {"current_steps": 52240, "total_steps": 61300, "loss": 0.3483, "lr": 3.254615160750926e-06, "epoch": 8.522022838499185, "percentage": 85.22, "elapsed_time": "7:08:00", "remaining_time": "1:14:13", "throughput": 4390.32, "total_tokens": 112747312} {"current_steps": 52245, "total_steps": 61300, "loss": 0.3495, "lr": 3.2511041911702483e-06, "epoch": 8.522838499184338, "percentage": 85.23, "elapsed_time": "7:08:03", "remaining_time": "1:14:11", "throughput": 4390.36, "total_tokens": 112758160} {"current_steps": 52250, "total_steps": 61300, "loss": 0.3769, "lr": 3.247594984665417e-06, "epoch": 8.523654159869494, "percentage": 85.24, "elapsed_time": "7:08:05", "remaining_time": "1:14:08", "throughput": 4390.4, "total_tokens": 112768080} {"current_steps": 52255, "total_steps": 61300, "loss": 0.348, "lr": 3.244087541520907e-06, "epoch": 8.52446982055465, "percentage": 85.24, "elapsed_time": "7:08:07", "remaining_time": "1:14:06", "throughput": 4390.43, "total_tokens": 112778416} {"current_steps": 52260, "total_steps": 61300, "loss": 0.3263, "lr": 3.24058186202105e-06, "epoch": 8.525285481239804, "percentage": 85.25, "elapsed_time": "7:08:09", "remaining_time": "1:14:03", "throughput": 4390.47, "total_tokens": 112788944} {"current_steps": 52265, "total_steps": 61300, "loss": 0.2954, "lr": 3.2370779464500317e-06, "epoch": 8.52610114192496, "percentage": 85.26, "elapsed_time": "7:08:11", "remaining_time": "1:14:01", "throughput": 4390.5, "total_tokens": 112799664} {"current_steps": 52270, "total_steps": 61300, "loss": 0.3481, "lr": 3.2335757950919003e-06, "epoch": 8.526916802610113, "percentage": 85.27, "elapsed_time": "7:08:13", "remaining_time": "1:13:58", "throughput": 4390.54, "total_tokens": 112809840} {"current_steps": 52275, "total_steps": 61300, "loss": 0.3364, "lr": 3.230075408230557e-06, "epoch": 8.52773246329527, "percentage": 85.28, "elapsed_time": "7:08:16", "remaining_time": "1:13:56", "throughput": 4390.57, "total_tokens": 112820240} {"current_steps": 52280, "total_steps": 61300, "loss": 0.3345, "lr": 3.2265767861497597e-06, "epoch": 8.528548123980425, "percentage": 85.29, "elapsed_time": "7:08:18", "remaining_time": "1:13:53", "throughput": 4390.61, "total_tokens": 112830704} {"current_steps": 52285, "total_steps": 61300, "loss": 0.3395, "lr": 3.2230799291331244e-06, "epoch": 8.529363784665579, "percentage": 85.29, "elapsed_time": "7:08:20", "remaining_time": "1:13:51", "throughput": 4390.65, "total_tokens": 112842352} {"current_steps": 52290, "total_steps": 61300, "loss": 0.3529, "lr": 3.219584837464126e-06, "epoch": 8.530179445350734, "percentage": 85.3, "elapsed_time": "7:08:22", "remaining_time": "1:13:48", "throughput": 4390.69, "total_tokens": 112853904} {"current_steps": 52295, "total_steps": 61300, "loss": 0.3564, "lr": 3.2160915114260947e-06, "epoch": 8.530995106035888, "percentage": 85.31, "elapsed_time": "7:08:24", "remaining_time": "1:13:46", "throughput": 4390.73, "total_tokens": 112863504} {"current_steps": 52300, "total_steps": 61300, "loss": 0.3144, "lr": 3.212599951302214e-06, "epoch": 8.531810766721044, "percentage": 85.32, "elapsed_time": "7:08:27", "remaining_time": "1:13:43", "throughput": 4390.76, "total_tokens": 112873808} {"current_steps": 52305, "total_steps": 61300, "loss": 0.2837, "lr": 3.2091101573755306e-06, "epoch": 8.5326264274062, "percentage": 85.33, "elapsed_time": "7:08:29", "remaining_time": "1:13:41", "throughput": 4390.8, "total_tokens": 112883696} {"current_steps": 52310, "total_steps": 61300, "loss": 0.3598, "lr": 3.2056221299289423e-06, "epoch": 8.533442088091354, "percentage": 85.33, "elapsed_time": "7:08:31", "remaining_time": "1:13:38", "throughput": 4390.83, "total_tokens": 112893424} {"current_steps": 52315, "total_steps": 61300, "loss": 0.3403, "lr": 3.20213586924521e-06, "epoch": 8.53425774877651, "percentage": 85.34, "elapsed_time": "7:08:33", "remaining_time": "1:13:36", "throughput": 4390.86, "total_tokens": 112904016} {"current_steps": 52320, "total_steps": 61300, "loss": 0.3384, "lr": 3.1986513756069426e-06, "epoch": 8.535073409461663, "percentage": 85.35, "elapsed_time": "7:08:35", "remaining_time": "1:13:33", "throughput": 4390.91, "total_tokens": 112915376} {"current_steps": 52325, "total_steps": 61300, "loss": 0.2914, "lr": 3.1951686492966094e-06, "epoch": 8.535889070146819, "percentage": 85.36, "elapsed_time": "7:08:37", "remaining_time": "1:13:31", "throughput": 4390.95, "total_tokens": 112925424} {"current_steps": 52330, "total_steps": 61300, "loss": 0.3463, "lr": 3.1916876905965483e-06, "epoch": 8.536704730831975, "percentage": 85.37, "elapsed_time": "7:08:40", "remaining_time": "1:13:28", "throughput": 4390.99, "total_tokens": 112936656} {"current_steps": 52335, "total_steps": 61300, "loss": 0.346, "lr": 3.188208499788936e-06, "epoch": 8.537520391517129, "percentage": 85.38, "elapsed_time": "7:08:42", "remaining_time": "1:13:26", "throughput": 4391.02, "total_tokens": 112947600} {"current_steps": 52340, "total_steps": 61300, "loss": 0.3356, "lr": 3.184731077155817e-06, "epoch": 8.538336052202284, "percentage": 85.38, "elapsed_time": "7:08:44", "remaining_time": "1:13:23", "throughput": 4391.05, "total_tokens": 112957840} {"current_steps": 52345, "total_steps": 61300, "loss": 0.313, "lr": 3.1812554229790848e-06, "epoch": 8.539151712887438, "percentage": 85.39, "elapsed_time": "7:08:46", "remaining_time": "1:13:21", "throughput": 4391.09, "total_tokens": 112969488} {"current_steps": 52350, "total_steps": 61300, "loss": 0.3393, "lr": 3.1777815375404944e-06, "epoch": 8.539967373572594, "percentage": 85.4, "elapsed_time": "7:08:48", "remaining_time": "1:13:18", "throughput": 4391.13, "total_tokens": 112979216} {"current_steps": 52355, "total_steps": 61300, "loss": 0.307, "lr": 3.17430942112166e-06, "epoch": 8.540783034257748, "percentage": 85.41, "elapsed_time": "7:08:51", "remaining_time": "1:13:16", "throughput": 4391.17, "total_tokens": 112990736} {"current_steps": 52360, "total_steps": 61300, "loss": 0.3402, "lr": 3.170839074004045e-06, "epoch": 8.541598694942904, "percentage": 85.42, "elapsed_time": "7:08:53", "remaining_time": "1:13:13", "throughput": 4391.21, "total_tokens": 113001296} {"current_steps": 52365, "total_steps": 61300, "loss": 0.3632, "lr": 3.1673704964689743e-06, "epoch": 8.54241435562806, "percentage": 85.42, "elapsed_time": "7:08:55", "remaining_time": "1:13:11", "throughput": 4391.25, "total_tokens": 113011312} {"current_steps": 52370, "total_steps": 61300, "loss": 0.3154, "lr": 3.1639036887976286e-06, "epoch": 8.543230016313213, "percentage": 85.43, "elapsed_time": "7:08:57", "remaining_time": "1:13:08", "throughput": 4391.28, "total_tokens": 113020688} {"current_steps": 52375, "total_steps": 61300, "loss": 0.3021, "lr": 3.1604386512710387e-06, "epoch": 8.544045676998369, "percentage": 85.44, "elapsed_time": "7:08:59", "remaining_time": "1:13:06", "throughput": 4391.31, "total_tokens": 113031888} {"current_steps": 52380, "total_steps": 61300, "loss": 0.3383, "lr": 3.1569753841701106e-06, "epoch": 8.544861337683523, "percentage": 85.45, "elapsed_time": "7:09:02", "remaining_time": "1:13:03", "throughput": 4391.34, "total_tokens": 113042800} {"current_steps": 52385, "total_steps": 61300, "loss": 0.335, "lr": 3.1535138877755887e-06, "epoch": 8.545676998368679, "percentage": 85.46, "elapsed_time": "7:09:04", "remaining_time": "1:13:01", "throughput": 4391.37, "total_tokens": 113052176} {"current_steps": 52390, "total_steps": 61300, "loss": 0.3375, "lr": 3.1500541623680795e-06, "epoch": 8.546492659053834, "percentage": 85.46, "elapsed_time": "7:09:06", "remaining_time": "1:12:58", "throughput": 4391.4, "total_tokens": 113062608} {"current_steps": 52395, "total_steps": 61300, "loss": 0.3371, "lr": 3.1465962082280474e-06, "epoch": 8.547308319738988, "percentage": 85.47, "elapsed_time": "7:09:08", "remaining_time": "1:12:56", "throughput": 4391.44, "total_tokens": 113075248} {"current_steps": 52400, "total_steps": 61300, "loss": 0.3417, "lr": 3.1431400256358073e-06, "epoch": 8.548123980424144, "percentage": 85.48, "elapsed_time": "7:09:11", "remaining_time": "1:12:53", "throughput": 4391.48, "total_tokens": 113086256} {"current_steps": 52405, "total_steps": 61300, "loss": 0.3014, "lr": 3.1396856148715375e-06, "epoch": 8.548939641109298, "percentage": 85.49, "elapsed_time": "7:09:13", "remaining_time": "1:12:51", "throughput": 4391.51, "total_tokens": 113096752} {"current_steps": 52410, "total_steps": 61300, "loss": 0.353, "lr": 3.13623297621527e-06, "epoch": 8.549755301794454, "percentage": 85.5, "elapsed_time": "7:09:15", "remaining_time": "1:12:48", "throughput": 4391.54, "total_tokens": 113106480} {"current_steps": 52415, "total_steps": 61300, "loss": 0.3437, "lr": 3.1327821099468915e-06, "epoch": 8.550570962479608, "percentage": 85.51, "elapsed_time": "7:09:17", "remaining_time": "1:12:46", "throughput": 4391.57, "total_tokens": 113117424} {"current_steps": 52420, "total_steps": 61300, "loss": 0.3536, "lr": 3.1293330163461503e-06, "epoch": 8.551386623164763, "percentage": 85.51, "elapsed_time": "7:09:19", "remaining_time": "1:12:43", "throughput": 4391.61, "total_tokens": 113127728} {"current_steps": 52425, "total_steps": 61300, "loss": 0.3315, "lr": 3.125885695692646e-06, "epoch": 8.552202283849919, "percentage": 85.52, "elapsed_time": "7:09:22", "remaining_time": "1:12:41", "throughput": 4391.64, "total_tokens": 113138000} {"current_steps": 52430, "total_steps": 61300, "loss": 0.3706, "lr": 3.122440148265829e-06, "epoch": 8.553017944535073, "percentage": 85.53, "elapsed_time": "7:09:24", "remaining_time": "1:12:38", "throughput": 4391.66, "total_tokens": 113148752} {"current_steps": 52435, "total_steps": 61300, "loss": 0.34, "lr": 3.1189963743450235e-06, "epoch": 8.553833605220229, "percentage": 85.54, "elapsed_time": "7:09:26", "remaining_time": "1:12:36", "throughput": 4391.7, "total_tokens": 113159600} {"current_steps": 52440, "total_steps": 61300, "loss": 0.331, "lr": 3.115554374209395e-06, "epoch": 8.554649265905383, "percentage": 85.55, "elapsed_time": "7:09:28", "remaining_time": "1:12:33", "throughput": 4391.73, "total_tokens": 113170416} {"current_steps": 52445, "total_steps": 61300, "loss": 0.3087, "lr": 3.1121141481379735e-06, "epoch": 8.555464926590538, "percentage": 85.55, "elapsed_time": "7:09:30", "remaining_time": "1:12:31", "throughput": 4391.77, "total_tokens": 113179984} {"current_steps": 52450, "total_steps": 61300, "loss": 0.3485, "lr": 3.1086756964096327e-06, "epoch": 8.556280587275694, "percentage": 85.56, "elapsed_time": "7:09:32", "remaining_time": "1:12:28", "throughput": 4391.8, "total_tokens": 113189680} {"current_steps": 52455, "total_steps": 61300, "loss": 0.3245, "lr": 3.105239019303116e-06, "epoch": 8.557096247960848, "percentage": 85.57, "elapsed_time": "7:09:35", "remaining_time": "1:12:26", "throughput": 4391.83, "total_tokens": 113200112} {"current_steps": 52460, "total_steps": 61300, "loss": 0.3298, "lr": 3.101804117097018e-06, "epoch": 8.557911908646004, "percentage": 85.58, "elapsed_time": "7:09:37", "remaining_time": "1:12:23", "throughput": 4391.87, "total_tokens": 113210416} {"current_steps": 52465, "total_steps": 61300, "loss": 0.3134, "lr": 3.0983709900697903e-06, "epoch": 8.558727569331158, "percentage": 85.59, "elapsed_time": "7:09:39", "remaining_time": "1:12:21", "throughput": 4391.91, "total_tokens": 113221392} {"current_steps": 52470, "total_steps": 61300, "loss": 0.3441, "lr": 3.0949396384997357e-06, "epoch": 8.559543230016313, "percentage": 85.6, "elapsed_time": "7:09:41", "remaining_time": "1:12:18", "throughput": 4391.95, "total_tokens": 113232528} {"current_steps": 52475, "total_steps": 61300, "loss": 0.3313, "lr": 3.0915100626650206e-06, "epoch": 8.560358890701469, "percentage": 85.6, "elapsed_time": "7:09:44", "remaining_time": "1:12:16", "throughput": 4391.98, "total_tokens": 113243056} {"current_steps": 52480, "total_steps": 61300, "loss": 0.3701, "lr": 3.0880822628436613e-06, "epoch": 8.561174551386623, "percentage": 85.61, "elapsed_time": "7:09:46", "remaining_time": "1:12:13", "throughput": 4392.03, "total_tokens": 113254576} {"current_steps": 52485, "total_steps": 61300, "loss": 0.3266, "lr": 3.0846562393135352e-06, "epoch": 8.561990212071779, "percentage": 85.62, "elapsed_time": "7:09:48", "remaining_time": "1:12:11", "throughput": 4392.06, "total_tokens": 113263472} {"current_steps": 52490, "total_steps": 61300, "loss": 0.3234, "lr": 3.0812319923523706e-06, "epoch": 8.562805872756933, "percentage": 85.63, "elapsed_time": "7:09:50", "remaining_time": "1:12:08", "throughput": 4392.1, "total_tokens": 113276112} {"current_steps": 52495, "total_steps": 61300, "loss": 0.3347, "lr": 3.077809522237754e-06, "epoch": 8.563621533442088, "percentage": 85.64, "elapsed_time": "7:09:52", "remaining_time": "1:12:06", "throughput": 4392.14, "total_tokens": 113285520} {"current_steps": 52500, "total_steps": 61300, "loss": 0.3137, "lr": 3.0743888292471322e-06, "epoch": 8.564437194127244, "percentage": 85.64, "elapsed_time": "7:09:55", "remaining_time": "1:12:03", "throughput": 4392.18, "total_tokens": 113296304} {"current_steps": 52505, "total_steps": 61300, "loss": 0.3278, "lr": 3.0709699136578006e-06, "epoch": 8.565252854812398, "percentage": 85.65, "elapsed_time": "7:09:57", "remaining_time": "1:12:01", "throughput": 4392.21, "total_tokens": 113307632} {"current_steps": 52510, "total_steps": 61300, "loss": 0.3305, "lr": 3.0675527757469124e-06, "epoch": 8.566068515497554, "percentage": 85.66, "elapsed_time": "7:09:59", "remaining_time": "1:11:58", "throughput": 4392.24, "total_tokens": 113318352} {"current_steps": 52515, "total_steps": 61300, "loss": 0.3361, "lr": 3.064137415791485e-06, "epoch": 8.566884176182707, "percentage": 85.67, "elapsed_time": "7:10:01", "remaining_time": "1:11:56", "throughput": 4392.28, "total_tokens": 113329552} {"current_steps": 52520, "total_steps": 61300, "loss": 0.2982, "lr": 3.0607238340683713e-06, "epoch": 8.567699836867863, "percentage": 85.68, "elapsed_time": "7:10:04", "remaining_time": "1:11:53", "throughput": 4392.31, "total_tokens": 113339216} {"current_steps": 52525, "total_steps": 61300, "loss": 0.3545, "lr": 3.057312030854306e-06, "epoch": 8.568515497553017, "percentage": 85.69, "elapsed_time": "7:10:06", "remaining_time": "1:11:51", "throughput": 4392.35, "total_tokens": 113349904} {"current_steps": 52530, "total_steps": 61300, "loss": 0.3175, "lr": 3.0539020064258682e-06, "epoch": 8.569331158238173, "percentage": 85.69, "elapsed_time": "7:10:08", "remaining_time": "1:11:48", "throughput": 4392.38, "total_tokens": 113358832} {"current_steps": 52535, "total_steps": 61300, "loss": 0.3389, "lr": 3.0504937610594837e-06, "epoch": 8.570146818923329, "percentage": 85.7, "elapsed_time": "7:10:10", "remaining_time": "1:11:46", "throughput": 4392.42, "total_tokens": 113370480} {"current_steps": 52540, "total_steps": 61300, "loss": 0.331, "lr": 3.0470872950314476e-06, "epoch": 8.570962479608482, "percentage": 85.71, "elapsed_time": "7:10:12", "remaining_time": "1:11:43", "throughput": 4392.45, "total_tokens": 113380592} {"current_steps": 52545, "total_steps": 61300, "loss": 0.3178, "lr": 3.043682608617898e-06, "epoch": 8.571778140293638, "percentage": 85.72, "elapsed_time": "7:10:15", "remaining_time": "1:11:41", "throughput": 4392.49, "total_tokens": 113392112} {"current_steps": 52550, "total_steps": 61300, "loss": 0.3552, "lr": 3.0402797020948446e-06, "epoch": 8.572593800978792, "percentage": 85.73, "elapsed_time": "7:10:17", "remaining_time": "1:11:38", "throughput": 4392.52, "total_tokens": 113403152} {"current_steps": 52555, "total_steps": 61300, "loss": 0.3381, "lr": 3.0368785757381418e-06, "epoch": 8.573409461663948, "percentage": 85.73, "elapsed_time": "7:10:19", "remaining_time": "1:11:36", "throughput": 4392.56, "total_tokens": 113413424} {"current_steps": 52560, "total_steps": 61300, "loss": 0.3136, "lr": 3.033479229823502e-06, "epoch": 8.574225122349104, "percentage": 85.74, "elapsed_time": "7:10:21", "remaining_time": "1:11:33", "throughput": 4392.6, "total_tokens": 113424848} {"current_steps": 52565, "total_steps": 61300, "loss": 0.3237, "lr": 3.030081664626494e-06, "epoch": 8.575040783034257, "percentage": 85.75, "elapsed_time": "7:10:23", "remaining_time": "1:11:31", "throughput": 4392.63, "total_tokens": 113434608} {"current_steps": 52570, "total_steps": 61300, "loss": 0.3171, "lr": 3.0266858804225388e-06, "epoch": 8.575856443719413, "percentage": 85.76, "elapsed_time": "7:10:26", "remaining_time": "1:11:28", "throughput": 4392.68, "total_tokens": 113446224} {"current_steps": 52575, "total_steps": 61300, "loss": 0.3239, "lr": 3.0232918774869194e-06, "epoch": 8.576672104404567, "percentage": 85.77, "elapsed_time": "7:10:28", "remaining_time": "1:11:26", "throughput": 4392.72, "total_tokens": 113457296} {"current_steps": 52580, "total_steps": 61300, "loss": 0.3403, "lr": 3.0198996560947657e-06, "epoch": 8.577487765089723, "percentage": 85.77, "elapsed_time": "7:10:30", "remaining_time": "1:11:23", "throughput": 4392.76, "total_tokens": 113468720} {"current_steps": 52585, "total_steps": 61300, "loss": 0.3183, "lr": 3.016509216521074e-06, "epoch": 8.578303425774878, "percentage": 85.78, "elapsed_time": "7:10:33", "remaining_time": "1:11:21", "throughput": 4392.8, "total_tokens": 113479152} {"current_steps": 52590, "total_steps": 61300, "loss": 0.3385, "lr": 3.0131205590406886e-06, "epoch": 8.579119086460032, "percentage": 85.79, "elapsed_time": "7:10:35", "remaining_time": "1:11:18", "throughput": 4392.83, "total_tokens": 113490608} {"current_steps": 52595, "total_steps": 61300, "loss": 0.3302, "lr": 3.0097336839283118e-06, "epoch": 8.579934747145188, "percentage": 85.8, "elapsed_time": "7:10:37", "remaining_time": "1:11:16", "throughput": 4392.88, "total_tokens": 113501968} {"current_steps": 52600, "total_steps": 61300, "loss": 0.3012, "lr": 3.0063485914584995e-06, "epoch": 8.580750407830342, "percentage": 85.81, "elapsed_time": "7:10:39", "remaining_time": "1:11:13", "throughput": 4392.92, "total_tokens": 113512944} {"current_steps": 52605, "total_steps": 61300, "loss": 0.347, "lr": 3.0029652819056646e-06, "epoch": 8.581566068515498, "percentage": 85.82, "elapsed_time": "7:10:42", "remaining_time": "1:11:11", "throughput": 4392.95, "total_tokens": 113524304} {"current_steps": 52610, "total_steps": 61300, "loss": 0.3189, "lr": 2.9995837555440748e-06, "epoch": 8.582381729200652, "percentage": 85.82, "elapsed_time": "7:10:44", "remaining_time": "1:11:08", "throughput": 4392.99, "total_tokens": 113536400} {"current_steps": 52615, "total_steps": 61300, "loss": 0.3524, "lr": 2.9962040126478548e-06, "epoch": 8.583197389885807, "percentage": 85.83, "elapsed_time": "7:10:47", "remaining_time": "1:11:06", "throughput": 4393.04, "total_tokens": 113546992} {"current_steps": 52620, "total_steps": 61300, "loss": 0.3536, "lr": 2.992826053490985e-06, "epoch": 8.584013050570963, "percentage": 85.84, "elapsed_time": "7:10:49", "remaining_time": "1:11:04", "throughput": 4393.08, "total_tokens": 113557808} {"current_steps": 52625, "total_steps": 61300, "loss": 0.3138, "lr": 2.9894498783473e-06, "epoch": 8.584828711256117, "percentage": 85.85, "elapsed_time": "7:10:51", "remaining_time": "1:11:01", "throughput": 4393.11, "total_tokens": 113568336} {"current_steps": 52630, "total_steps": 61300, "loss": 0.3218, "lr": 2.986075487490486e-06, "epoch": 8.585644371941273, "percentage": 85.86, "elapsed_time": "7:10:53", "remaining_time": "1:10:59", "throughput": 4393.15, "total_tokens": 113579280} {"current_steps": 52635, "total_steps": 61300, "loss": 0.3147, "lr": 2.982702881194091e-06, "epoch": 8.586460032626427, "percentage": 85.86, "elapsed_time": "7:10:56", "remaining_time": "1:10:56", "throughput": 4393.19, "total_tokens": 113591024} {"current_steps": 52640, "total_steps": 61300, "loss": 0.313, "lr": 2.9793320597315154e-06, "epoch": 8.587275693311582, "percentage": 85.87, "elapsed_time": "7:10:58", "remaining_time": "1:10:54", "throughput": 4393.22, "total_tokens": 113602032} {"current_steps": 52645, "total_steps": 61300, "loss": 0.3173, "lr": 2.975963023376008e-06, "epoch": 8.588091353996738, "percentage": 85.88, "elapsed_time": "7:11:00", "remaining_time": "1:10:51", "throughput": 4393.26, "total_tokens": 113612688} {"current_steps": 52650, "total_steps": 61300, "loss": 0.3348, "lr": 2.9725957724006936e-06, "epoch": 8.588907014681892, "percentage": 85.89, "elapsed_time": "7:11:02", "remaining_time": "1:10:49", "throughput": 4393.29, "total_tokens": 113622224} {"current_steps": 52655, "total_steps": 61300, "loss": 0.3343, "lr": 2.9692303070785325e-06, "epoch": 8.589722675367048, "percentage": 85.9, "elapsed_time": "7:11:04", "remaining_time": "1:10:46", "throughput": 4393.33, "total_tokens": 113631920} {"current_steps": 52660, "total_steps": 61300, "loss": 0.356, "lr": 2.9658666276823427e-06, "epoch": 8.590538336052202, "percentage": 85.91, "elapsed_time": "7:11:06", "remaining_time": "1:10:44", "throughput": 4393.36, "total_tokens": 113642672} {"current_steps": 52665, "total_steps": 61300, "loss": 0.3556, "lr": 2.9625047344848082e-06, "epoch": 8.591353996737357, "percentage": 85.91, "elapsed_time": "7:11:09", "remaining_time": "1:10:41", "throughput": 4393.4, "total_tokens": 113653456} {"current_steps": 52670, "total_steps": 61300, "loss": 0.3489, "lr": 2.959144627758453e-06, "epoch": 8.592169657422513, "percentage": 85.92, "elapsed_time": "7:11:11", "remaining_time": "1:10:39", "throughput": 4393.43, "total_tokens": 113664304} {"current_steps": 52675, "total_steps": 61300, "loss": 0.3403, "lr": 2.955786307775671e-06, "epoch": 8.592985318107667, "percentage": 85.93, "elapsed_time": "7:11:13", "remaining_time": "1:10:36", "throughput": 4393.47, "total_tokens": 113675024} {"current_steps": 52680, "total_steps": 61300, "loss": 0.3269, "lr": 2.9524297748087014e-06, "epoch": 8.593800978792823, "percentage": 85.94, "elapsed_time": "7:11:15", "remaining_time": "1:10:34", "throughput": 4393.51, "total_tokens": 113685200} {"current_steps": 52685, "total_steps": 61300, "loss": 0.332, "lr": 2.949075029129644e-06, "epoch": 8.594616639477977, "percentage": 85.95, "elapsed_time": "7:11:18", "remaining_time": "1:10:31", "throughput": 4393.55, "total_tokens": 113696528} {"current_steps": 52690, "total_steps": 61300, "loss": 0.2728, "lr": 2.945722071010443e-06, "epoch": 8.595432300163132, "percentage": 85.95, "elapsed_time": "7:11:20", "remaining_time": "1:10:29", "throughput": 4393.58, "total_tokens": 113707568} {"current_steps": 52695, "total_steps": 61300, "loss": 0.3474, "lr": 2.9423709007229184e-06, "epoch": 8.596247960848288, "percentage": 85.96, "elapsed_time": "7:11:22", "remaining_time": "1:10:26", "throughput": 4393.62, "total_tokens": 113719280} {"current_steps": 52700, "total_steps": 61300, "loss": 0.3302, "lr": 2.9390215185387287e-06, "epoch": 8.597063621533442, "percentage": 85.97, "elapsed_time": "7:11:24", "remaining_time": "1:10:24", "throughput": 4393.65, "total_tokens": 113729072} {"current_steps": 52705, "total_steps": 61300, "loss": 0.3573, "lr": 2.93567392472939e-06, "epoch": 8.597879282218598, "percentage": 85.98, "elapsed_time": "7:11:27", "remaining_time": "1:10:21", "throughput": 4393.7, "total_tokens": 113740784} {"current_steps": 52710, "total_steps": 61300, "loss": 0.3137, "lr": 2.932328119566277e-06, "epoch": 8.598694942903752, "percentage": 85.99, "elapsed_time": "7:11:29", "remaining_time": "1:10:19", "throughput": 4393.74, "total_tokens": 113751088} {"current_steps": 52715, "total_steps": 61300, "loss": 0.324, "lr": 2.928984103320617e-06, "epoch": 8.599510603588907, "percentage": 86.0, "elapsed_time": "7:11:31", "remaining_time": "1:10:16", "throughput": 4393.78, "total_tokens": 113762672} {"current_steps": 52720, "total_steps": 61300, "loss": 0.3519, "lr": 2.9256418762634936e-06, "epoch": 8.600326264274061, "percentage": 86.0, "elapsed_time": "7:11:33", "remaining_time": "1:10:14", "throughput": 4393.81, "total_tokens": 113773072} {"current_steps": 52725, "total_steps": 61300, "loss": 0.3344, "lr": 2.922301438665842e-06, "epoch": 8.601141924959217, "percentage": 86.01, "elapsed_time": "7:11:36", "remaining_time": "1:10:11", "throughput": 4393.85, "total_tokens": 113784080} {"current_steps": 52730, "total_steps": 61300, "loss": 0.3305, "lr": 2.9189627907984576e-06, "epoch": 8.601957585644373, "percentage": 86.02, "elapsed_time": "7:11:38", "remaining_time": "1:10:09", "throughput": 4393.88, "total_tokens": 113794704} {"current_steps": 52735, "total_steps": 61300, "loss": 0.3274, "lr": 2.9156259329319867e-06, "epoch": 8.602773246329527, "percentage": 86.03, "elapsed_time": "7:11:40", "remaining_time": "1:10:06", "throughput": 4393.93, "total_tokens": 113806512} {"current_steps": 52740, "total_steps": 61300, "loss": 0.3531, "lr": 2.9122908653369335e-06, "epoch": 8.603588907014682, "percentage": 86.04, "elapsed_time": "7:11:43", "remaining_time": "1:10:04", "throughput": 4393.97, "total_tokens": 113817872} {"current_steps": 52745, "total_steps": 61300, "loss": 0.3101, "lr": 2.908957588283656e-06, "epoch": 8.604404567699836, "percentage": 86.04, "elapsed_time": "7:11:45", "remaining_time": "1:10:01", "throughput": 4394.01, "total_tokens": 113829808} {"current_steps": 52750, "total_steps": 61300, "loss": 0.3408, "lr": 2.9056261020423582e-06, "epoch": 8.605220228384992, "percentage": 86.05, "elapsed_time": "7:11:47", "remaining_time": "1:09:59", "throughput": 4394.04, "total_tokens": 113840656} {"current_steps": 52755, "total_steps": 61300, "loss": 0.3377, "lr": 2.9022964068831204e-06, "epoch": 8.606035889070148, "percentage": 86.06, "elapsed_time": "7:11:50", "remaining_time": "1:09:56", "throughput": 4394.09, "total_tokens": 113851664} {"current_steps": 52760, "total_steps": 61300, "loss": 0.3088, "lr": 2.898968503075858e-06, "epoch": 8.606851549755302, "percentage": 86.07, "elapsed_time": "7:11:52", "remaining_time": "1:09:54", "throughput": 4394.12, "total_tokens": 113862288} {"current_steps": 52765, "total_steps": 61300, "loss": 0.3177, "lr": 2.895642390890349e-06, "epoch": 8.607667210440457, "percentage": 86.08, "elapsed_time": "7:11:54", "remaining_time": "1:09:51", "throughput": 4394.16, "total_tokens": 113873456} {"current_steps": 52770, "total_steps": 61300, "loss": 0.3118, "lr": 2.8923180705962226e-06, "epoch": 8.608482871125611, "percentage": 86.08, "elapsed_time": "7:11:56", "remaining_time": "1:09:49", "throughput": 4394.19, "total_tokens": 113883536} {"current_steps": 52775, "total_steps": 61300, "loss": 0.3304, "lr": 2.888995542462969e-06, "epoch": 8.609298531810767, "percentage": 86.09, "elapsed_time": "7:11:58", "remaining_time": "1:09:46", "throughput": 4394.22, "total_tokens": 113893520} {"current_steps": 52780, "total_steps": 61300, "loss": 0.3177, "lr": 2.885674806759925e-06, "epoch": 8.61011419249592, "percentage": 86.1, "elapsed_time": "7:12:01", "remaining_time": "1:09:44", "throughput": 4394.26, "total_tokens": 113904592} {"current_steps": 52785, "total_steps": 61300, "loss": 0.351, "lr": 2.8823558637562893e-06, "epoch": 8.610929853181077, "percentage": 86.11, "elapsed_time": "7:12:03", "remaining_time": "1:09:41", "throughput": 4394.3, "total_tokens": 113916272} {"current_steps": 52790, "total_steps": 61300, "loss": 0.3637, "lr": 2.8790387137211105e-06, "epoch": 8.611745513866232, "percentage": 86.12, "elapsed_time": "7:12:06", "remaining_time": "1:09:39", "throughput": 4394.34, "total_tokens": 113928336} {"current_steps": 52795, "total_steps": 61300, "loss": 0.3119, "lr": 2.8757233569232933e-06, "epoch": 8.612561174551386, "percentage": 86.13, "elapsed_time": "7:12:08", "remaining_time": "1:09:36", "throughput": 4394.38, "total_tokens": 113939920} {"current_steps": 52800, "total_steps": 61300, "loss": 0.3547, "lr": 2.8724097936316004e-06, "epoch": 8.613376835236542, "percentage": 86.13, "elapsed_time": "7:12:10", "remaining_time": "1:09:34", "throughput": 4394.41, "total_tokens": 113949616} {"current_steps": 52805, "total_steps": 61300, "loss": 0.319, "lr": 2.8690980241146415e-06, "epoch": 8.614192495921696, "percentage": 86.14, "elapsed_time": "7:12:12", "remaining_time": "1:09:31", "throughput": 4394.45, "total_tokens": 113959408} {"current_steps": 52810, "total_steps": 61300, "loss": 0.3234, "lr": 2.8657880486408884e-06, "epoch": 8.615008156606851, "percentage": 86.15, "elapsed_time": "7:12:14", "remaining_time": "1:09:29", "throughput": 4394.48, "total_tokens": 113970736} {"current_steps": 52815, "total_steps": 61300, "loss": 0.3257, "lr": 2.862479867478665e-06, "epoch": 8.615823817292007, "percentage": 86.16, "elapsed_time": "7:12:17", "remaining_time": "1:09:26", "throughput": 4394.52, "total_tokens": 113981008} {"current_steps": 52820, "total_steps": 61300, "loss": 0.3474, "lr": 2.859173480896149e-06, "epoch": 8.616639477977161, "percentage": 86.17, "elapsed_time": "7:12:19", "remaining_time": "1:09:24", "throughput": 4394.56, "total_tokens": 113992816} {"current_steps": 52825, "total_steps": 61300, "loss": 0.3143, "lr": 2.85586888916137e-06, "epoch": 8.617455138662317, "percentage": 86.17, "elapsed_time": "7:12:22", "remaining_time": "1:09:22", "throughput": 4394.6, "total_tokens": 114005392} {"current_steps": 52830, "total_steps": 61300, "loss": 0.3434, "lr": 2.852566092542211e-06, "epoch": 8.61827079934747, "percentage": 86.18, "elapsed_time": "7:12:24", "remaining_time": "1:09:19", "throughput": 4394.64, "total_tokens": 114015600} {"current_steps": 52835, "total_steps": 61300, "loss": 0.3422, "lr": 2.8492650913064274e-06, "epoch": 8.619086460032626, "percentage": 86.19, "elapsed_time": "7:12:26", "remaining_time": "1:09:17", "throughput": 4394.67, "total_tokens": 114026448} {"current_steps": 52840, "total_steps": 61300, "loss": 0.3582, "lr": 2.8459658857216074e-06, "epoch": 8.619902120717782, "percentage": 86.2, "elapsed_time": "7:12:28", "remaining_time": "1:09:14", "throughput": 4394.7, "total_tokens": 114037552} {"current_steps": 52845, "total_steps": 61300, "loss": 0.3247, "lr": 2.8426684760551993e-06, "epoch": 8.620717781402936, "percentage": 86.21, "elapsed_time": "7:12:31", "remaining_time": "1:09:12", "throughput": 4394.74, "total_tokens": 114049072} {"current_steps": 52850, "total_steps": 61300, "loss": 0.3261, "lr": 2.83937286257451e-06, "epoch": 8.621533442088092, "percentage": 86.22, "elapsed_time": "7:12:33", "remaining_time": "1:09:09", "throughput": 4394.78, "total_tokens": 114059824} {"current_steps": 52855, "total_steps": 61300, "loss": 0.2927, "lr": 2.8360790455466996e-06, "epoch": 8.622349102773246, "percentage": 86.22, "elapsed_time": "7:12:35", "remaining_time": "1:09:07", "throughput": 4394.8, "total_tokens": 114070960} {"current_steps": 52860, "total_steps": 61300, "loss": 0.314, "lr": 2.8327870252387727e-06, "epoch": 8.623164763458401, "percentage": 86.23, "elapsed_time": "7:12:38", "remaining_time": "1:09:04", "throughput": 4394.84, "total_tokens": 114082224} {"current_steps": 52865, "total_steps": 61300, "loss": 0.3309, "lr": 2.829496801917611e-06, "epoch": 8.623980424143557, "percentage": 86.24, "elapsed_time": "7:12:40", "remaining_time": "1:09:02", "throughput": 4394.87, "total_tokens": 114091760} {"current_steps": 52870, "total_steps": 61300, "loss": 0.3728, "lr": 2.826208375849931e-06, "epoch": 8.624796084828711, "percentage": 86.25, "elapsed_time": "7:12:42", "remaining_time": "1:08:59", "throughput": 4394.9, "total_tokens": 114100912} {"current_steps": 52875, "total_steps": 61300, "loss": 0.3416, "lr": 2.8229217473023094e-06, "epoch": 8.625611745513867, "percentage": 86.26, "elapsed_time": "7:12:44", "remaining_time": "1:08:57", "throughput": 4394.94, "total_tokens": 114111856} {"current_steps": 52880, "total_steps": 61300, "loss": 0.3507, "lr": 2.8196369165411767e-06, "epoch": 8.62642740619902, "percentage": 86.26, "elapsed_time": "7:12:46", "remaining_time": "1:08:54", "throughput": 4394.97, "total_tokens": 114121872} {"current_steps": 52885, "total_steps": 61300, "loss": 0.368, "lr": 2.8163538838328176e-06, "epoch": 8.627243066884176, "percentage": 86.27, "elapsed_time": "7:12:48", "remaining_time": "1:08:52", "throughput": 4395.0, "total_tokens": 114132304} {"current_steps": 52890, "total_steps": 61300, "loss": 0.3296, "lr": 2.8130726494433684e-06, "epoch": 8.62805872756933, "percentage": 86.28, "elapsed_time": "7:12:50", "remaining_time": "1:08:49", "throughput": 4395.04, "total_tokens": 114142160} {"current_steps": 52895, "total_steps": 61300, "loss": 0.3461, "lr": 2.8097932136388285e-06, "epoch": 8.628874388254486, "percentage": 86.29, "elapsed_time": "7:12:53", "remaining_time": "1:08:47", "throughput": 4395.08, "total_tokens": 114153392} {"current_steps": 52900, "total_steps": 61300, "loss": 0.3128, "lr": 2.8065155766850425e-06, "epoch": 8.629690048939642, "percentage": 86.3, "elapsed_time": "7:12:55", "remaining_time": "1:08:44", "throughput": 4395.12, "total_tokens": 114165648} {"current_steps": 52905, "total_steps": 61300, "loss": 0.3017, "lr": 2.8032397388477098e-06, "epoch": 8.630505709624796, "percentage": 86.31, "elapsed_time": "7:12:57", "remaining_time": "1:08:42", "throughput": 4395.15, "total_tokens": 114175248} {"current_steps": 52910, "total_steps": 61300, "loss": 0.3268, "lr": 2.799965700392393e-06, "epoch": 8.631321370309951, "percentage": 86.31, "elapsed_time": "7:12:59", "remaining_time": "1:08:39", "throughput": 4395.19, "total_tokens": 114186256} {"current_steps": 52915, "total_steps": 61300, "loss": 0.29, "lr": 2.7966934615844957e-06, "epoch": 8.632137030995105, "percentage": 86.32, "elapsed_time": "7:13:02", "remaining_time": "1:08:37", "throughput": 4395.22, "total_tokens": 114197264} {"current_steps": 52920, "total_steps": 61300, "loss": 0.3221, "lr": 2.793423022689284e-06, "epoch": 8.632952691680261, "percentage": 86.33, "elapsed_time": "7:13:04", "remaining_time": "1:08:34", "throughput": 4395.27, "total_tokens": 114208944} {"current_steps": 52925, "total_steps": 61300, "loss": 0.3351, "lr": 2.7901543839718795e-06, "epoch": 8.633768352365417, "percentage": 86.34, "elapsed_time": "7:13:06", "remaining_time": "1:08:32", "throughput": 4395.3, "total_tokens": 114219504} {"current_steps": 52930, "total_steps": 61300, "loss": 0.3478, "lr": 2.7868875456972534e-06, "epoch": 8.63458401305057, "percentage": 86.35, "elapsed_time": "7:13:08", "remaining_time": "1:08:29", "throughput": 4395.34, "total_tokens": 114229072} {"current_steps": 52935, "total_steps": 61300, "loss": 0.3223, "lr": 2.783622508130229e-06, "epoch": 8.635399673735726, "percentage": 86.35, "elapsed_time": "7:13:10", "remaining_time": "1:08:27", "throughput": 4395.37, "total_tokens": 114238768} {"current_steps": 52940, "total_steps": 61300, "loss": 0.3546, "lr": 2.7803592715354877e-06, "epoch": 8.63621533442088, "percentage": 86.36, "elapsed_time": "7:13:13", "remaining_time": "1:08:24", "throughput": 4395.41, "total_tokens": 114250256} {"current_steps": 52945, "total_steps": 61300, "loss": 0.3241, "lr": 2.7770978361775667e-06, "epoch": 8.637030995106036, "percentage": 86.37, "elapsed_time": "7:13:15", "remaining_time": "1:08:22", "throughput": 4395.44, "total_tokens": 114259696} {"current_steps": 52950, "total_steps": 61300, "loss": 0.3372, "lr": 2.7738382023208526e-06, "epoch": 8.63784665579119, "percentage": 86.38, "elapsed_time": "7:13:17", "remaining_time": "1:08:19", "throughput": 4395.48, "total_tokens": 114270288} {"current_steps": 52955, "total_steps": 61300, "loss": 0.3372, "lr": 2.770580370229589e-06, "epoch": 8.638662316476346, "percentage": 86.39, "elapsed_time": "7:13:19", "remaining_time": "1:08:17", "throughput": 4395.51, "total_tokens": 114280784} {"current_steps": 52960, "total_steps": 61300, "loss": 0.3358, "lr": 2.7673243401678704e-06, "epoch": 8.639477977161501, "percentage": 86.39, "elapsed_time": "7:13:21", "remaining_time": "1:08:14", "throughput": 4395.54, "total_tokens": 114290832} {"current_steps": 52965, "total_steps": 61300, "loss": 0.3626, "lr": 2.7640701123996445e-06, "epoch": 8.640293637846655, "percentage": 86.4, "elapsed_time": "7:13:23", "remaining_time": "1:08:12", "throughput": 4395.58, "total_tokens": 114301648} {"current_steps": 52970, "total_steps": 61300, "loss": 0.3461, "lr": 2.7608176871887242e-06, "epoch": 8.641109298531811, "percentage": 86.41, "elapsed_time": "7:13:25", "remaining_time": "1:08:09", "throughput": 4395.61, "total_tokens": 114311728} {"current_steps": 52975, "total_steps": 61300, "loss": 0.3098, "lr": 2.7575670647987606e-06, "epoch": 8.641924959216965, "percentage": 86.42, "elapsed_time": "7:13:28", "remaining_time": "1:08:07", "throughput": 4395.64, "total_tokens": 114322512} {"current_steps": 52980, "total_steps": 61300, "loss": 0.3043, "lr": 2.7543182454932705e-06, "epoch": 8.64274061990212, "percentage": 86.43, "elapsed_time": "7:13:30", "remaining_time": "1:08:04", "throughput": 4395.67, "total_tokens": 114332592} {"current_steps": 52985, "total_steps": 61300, "loss": 0.3304, "lr": 2.751071229535615e-06, "epoch": 8.643556280587276, "percentage": 86.44, "elapsed_time": "7:13:32", "remaining_time": "1:08:02", "throughput": 4395.72, "total_tokens": 114343696} {"current_steps": 52990, "total_steps": 61300, "loss": 0.3733, "lr": 2.7478260171890175e-06, "epoch": 8.64437194127243, "percentage": 86.44, "elapsed_time": "7:13:34", "remaining_time": "1:07:59", "throughput": 4395.75, "total_tokens": 114354928} {"current_steps": 52995, "total_steps": 61300, "loss": 0.3213, "lr": 2.744582608716548e-06, "epoch": 8.645187601957586, "percentage": 86.45, "elapsed_time": "7:13:37", "remaining_time": "1:07:57", "throughput": 4395.79, "total_tokens": 114365392} {"current_steps": 53000, "total_steps": 61300, "loss": 0.3261, "lr": 2.741341004381129e-06, "epoch": 8.64600326264274, "percentage": 86.46, "elapsed_time": "7:13:39", "remaining_time": "1:07:54", "throughput": 4395.81, "total_tokens": 114374992} {"current_steps": 53005, "total_steps": 61300, "loss": 0.2945, "lr": 2.7381012044455535e-06, "epoch": 8.646818923327896, "percentage": 86.47, "elapsed_time": "7:13:41", "remaining_time": "1:07:52", "throughput": 4395.85, "total_tokens": 114385808} {"current_steps": 53010, "total_steps": 61300, "loss": 0.3125, "lr": 2.73486320917245e-06, "epoch": 8.647634584013051, "percentage": 86.48, "elapsed_time": "7:13:43", "remaining_time": "1:07:49", "throughput": 4395.89, "total_tokens": 114397072} {"current_steps": 53015, "total_steps": 61300, "loss": 0.3492, "lr": 2.7316270188243064e-06, "epoch": 8.648450244698205, "percentage": 86.48, "elapsed_time": "7:13:46", "remaining_time": "1:07:47", "throughput": 4395.93, "total_tokens": 114408624} {"current_steps": 53020, "total_steps": 61300, "loss": 0.3149, "lr": 2.728392633663468e-06, "epoch": 8.649265905383361, "percentage": 86.49, "elapsed_time": "7:13:48", "remaining_time": "1:07:44", "throughput": 4395.96, "total_tokens": 114418512} {"current_steps": 53025, "total_steps": 61300, "loss": 0.3147, "lr": 2.7251600539521248e-06, "epoch": 8.650081566068515, "percentage": 86.5, "elapsed_time": "7:13:50", "remaining_time": "1:07:42", "throughput": 4395.99, "total_tokens": 114427792} {"current_steps": 53030, "total_steps": 61300, "loss": 0.3903, "lr": 2.7219292799523316e-06, "epoch": 8.65089722675367, "percentage": 86.51, "elapsed_time": "7:13:52", "remaining_time": "1:07:39", "throughput": 4396.03, "total_tokens": 114439888} {"current_steps": 53035, "total_steps": 61300, "loss": 0.3297, "lr": 2.718700311925987e-06, "epoch": 8.651712887438826, "percentage": 86.52, "elapsed_time": "7:13:54", "remaining_time": "1:07:37", "throughput": 4396.07, "total_tokens": 114451280} {"current_steps": 53040, "total_steps": 61300, "loss": 0.3216, "lr": 2.715473150134848e-06, "epoch": 8.65252854812398, "percentage": 86.53, "elapsed_time": "7:13:57", "remaining_time": "1:07:34", "throughput": 4396.11, "total_tokens": 114463376} {"current_steps": 53045, "total_steps": 61300, "loss": 0.3042, "lr": 2.7122477948405277e-06, "epoch": 8.653344208809136, "percentage": 86.53, "elapsed_time": "7:13:59", "remaining_time": "1:07:32", "throughput": 4396.16, "total_tokens": 114474896} {"current_steps": 53050, "total_steps": 61300, "loss": 0.3153, "lr": 2.7090242463044896e-06, "epoch": 8.65415986949429, "percentage": 86.54, "elapsed_time": "7:14:02", "remaining_time": "1:07:29", "throughput": 4396.19, "total_tokens": 114486000} {"current_steps": 53055, "total_steps": 61300, "loss": 0.2867, "lr": 2.7058025047880466e-06, "epoch": 8.654975530179446, "percentage": 86.55, "elapsed_time": "7:14:04", "remaining_time": "1:07:27", "throughput": 4396.24, "total_tokens": 114497456} {"current_steps": 53060, "total_steps": 61300, "loss": 0.3114, "lr": 2.702582570552373e-06, "epoch": 8.655791190864601, "percentage": 86.56, "elapsed_time": "7:14:06", "remaining_time": "1:07:24", "throughput": 4396.27, "total_tokens": 114508368} {"current_steps": 53065, "total_steps": 61300, "loss": 0.3448, "lr": 2.699364443858493e-06, "epoch": 8.656606851549755, "percentage": 86.57, "elapsed_time": "7:14:09", "remaining_time": "1:07:22", "throughput": 4396.31, "total_tokens": 114519888} {"current_steps": 53070, "total_steps": 61300, "loss": 0.347, "lr": 2.6961481249672765e-06, "epoch": 8.65742251223491, "percentage": 86.57, "elapsed_time": "7:14:11", "remaining_time": "1:07:19", "throughput": 4396.35, "total_tokens": 114529712} {"current_steps": 53075, "total_steps": 61300, "loss": 0.3664, "lr": 2.69293361413947e-06, "epoch": 8.658238172920065, "percentage": 86.58, "elapsed_time": "7:14:13", "remaining_time": "1:07:17", "throughput": 4396.38, "total_tokens": 114540528} {"current_steps": 53080, "total_steps": 61300, "loss": 0.3615, "lr": 2.6897209116356457e-06, "epoch": 8.65905383360522, "percentage": 86.59, "elapsed_time": "7:14:15", "remaining_time": "1:07:15", "throughput": 4396.42, "total_tokens": 114552016} {"current_steps": 53085, "total_steps": 61300, "loss": 0.3421, "lr": 2.6865100177162484e-06, "epoch": 8.659869494290374, "percentage": 86.6, "elapsed_time": "7:14:17", "remaining_time": "1:07:12", "throughput": 4396.45, "total_tokens": 114562672} {"current_steps": 53090, "total_steps": 61300, "loss": 0.3273, "lr": 2.6833009326415663e-06, "epoch": 8.66068515497553, "percentage": 86.61, "elapsed_time": "7:14:20", "remaining_time": "1:07:10", "throughput": 4396.49, "total_tokens": 114574320} {"current_steps": 53095, "total_steps": 61300, "loss": 0.326, "lr": 2.680093656671745e-06, "epoch": 8.661500815660686, "percentage": 86.62, "elapsed_time": "7:14:22", "remaining_time": "1:07:07", "throughput": 4396.53, "total_tokens": 114585456} {"current_steps": 53100, "total_steps": 61300, "loss": 0.3054, "lr": 2.6768881900667787e-06, "epoch": 8.66231647634584, "percentage": 86.62, "elapsed_time": "7:14:25", "remaining_time": "1:07:05", "throughput": 4396.56, "total_tokens": 114596400} {"current_steps": 53105, "total_steps": 61300, "loss": 0.324, "lr": 2.673684533086526e-06, "epoch": 8.663132137030995, "percentage": 86.63, "elapsed_time": "7:14:27", "remaining_time": "1:07:02", "throughput": 4396.59, "total_tokens": 114607120} {"current_steps": 53110, "total_steps": 61300, "loss": 0.3429, "lr": 2.6704826859906858e-06, "epoch": 8.66394779771615, "percentage": 86.64, "elapsed_time": "7:14:29", "remaining_time": "1:07:00", "throughput": 4396.62, "total_tokens": 114617808} {"current_steps": 53115, "total_steps": 61300, "loss": 0.3421, "lr": 2.667282649038816e-06, "epoch": 8.664763458401305, "percentage": 86.65, "elapsed_time": "7:14:31", "remaining_time": "1:06:57", "throughput": 4396.65, "total_tokens": 114627664} {"current_steps": 53120, "total_steps": 61300, "loss": 0.3474, "lr": 2.6640844224903318e-06, "epoch": 8.66557911908646, "percentage": 86.66, "elapsed_time": "7:14:33", "remaining_time": "1:06:55", "throughput": 4396.69, "total_tokens": 114638064} {"current_steps": 53125, "total_steps": 61300, "loss": 0.3108, "lr": 2.660888006604498e-06, "epoch": 8.666394779771615, "percentage": 86.66, "elapsed_time": "7:14:35", "remaining_time": "1:06:52", "throughput": 4396.72, "total_tokens": 114647760} {"current_steps": 53130, "total_steps": 61300, "loss": 0.363, "lr": 2.6576934016404264e-06, "epoch": 8.66721044045677, "percentage": 86.67, "elapsed_time": "7:14:37", "remaining_time": "1:06:50", "throughput": 4396.75, "total_tokens": 114658192} {"current_steps": 53135, "total_steps": 61300, "loss": 0.335, "lr": 2.654500607857091e-06, "epoch": 8.668026101141924, "percentage": 86.68, "elapsed_time": "7:14:40", "remaining_time": "1:06:47", "throughput": 4396.79, "total_tokens": 114669392} {"current_steps": 53140, "total_steps": 61300, "loss": 0.3022, "lr": 2.651309625513318e-06, "epoch": 8.66884176182708, "percentage": 86.69, "elapsed_time": "7:14:42", "remaining_time": "1:06:45", "throughput": 4396.83, "total_tokens": 114681168} {"current_steps": 53145, "total_steps": 61300, "loss": 0.3265, "lr": 2.648120454867778e-06, "epoch": 8.669657422512234, "percentage": 86.7, "elapsed_time": "7:14:45", "remaining_time": "1:06:42", "throughput": 4396.87, "total_tokens": 114692688} {"current_steps": 53150, "total_steps": 61300, "loss": 0.3026, "lr": 2.6449330961790116e-06, "epoch": 8.67047308319739, "percentage": 86.7, "elapsed_time": "7:14:47", "remaining_time": "1:06:40", "throughput": 4396.9, "total_tokens": 114703472} {"current_steps": 53155, "total_steps": 61300, "loss": 0.2982, "lr": 2.641747549705395e-06, "epoch": 8.671288743882545, "percentage": 86.71, "elapsed_time": "7:14:49", "remaining_time": "1:06:37", "throughput": 4396.94, "total_tokens": 114714704} {"current_steps": 53160, "total_steps": 61300, "loss": 0.2879, "lr": 2.638563815705167e-06, "epoch": 8.6721044045677, "percentage": 86.72, "elapsed_time": "7:14:51", "remaining_time": "1:06:35", "throughput": 4396.97, "total_tokens": 114725200} {"current_steps": 53165, "total_steps": 61300, "loss": 0.3311, "lr": 2.635381894436417e-06, "epoch": 8.672920065252855, "percentage": 86.73, "elapsed_time": "7:14:53", "remaining_time": "1:06:32", "throughput": 4397.01, "total_tokens": 114735568} {"current_steps": 53170, "total_steps": 61300, "loss": 0.321, "lr": 2.63220178615709e-06, "epoch": 8.673735725938009, "percentage": 86.74, "elapsed_time": "7:14:56", "remaining_time": "1:06:30", "throughput": 4397.04, "total_tokens": 114746448} {"current_steps": 53175, "total_steps": 61300, "loss": 0.3258, "lr": 2.629023491124971e-06, "epoch": 8.674551386623165, "percentage": 86.75, "elapsed_time": "7:14:58", "remaining_time": "1:06:27", "throughput": 4397.1, "total_tokens": 114758704} {"current_steps": 53180, "total_steps": 61300, "loss": 0.3028, "lr": 2.6258470095977262e-06, "epoch": 8.67536704730832, "percentage": 86.75, "elapsed_time": "7:15:01", "remaining_time": "1:06:25", "throughput": 4397.13, "total_tokens": 114769744} {"current_steps": 53185, "total_steps": 61300, "loss": 0.3005, "lr": 2.6226723418328437e-06, "epoch": 8.676182707993474, "percentage": 86.76, "elapsed_time": "7:15:03", "remaining_time": "1:06:22", "throughput": 4397.17, "total_tokens": 114780112} {"current_steps": 53190, "total_steps": 61300, "loss": 0.3339, "lr": 2.6194994880876843e-06, "epoch": 8.67699836867863, "percentage": 86.77, "elapsed_time": "7:15:05", "remaining_time": "1:06:20", "throughput": 4397.21, "total_tokens": 114790384} {"current_steps": 53195, "total_steps": 61300, "loss": 0.3103, "lr": 2.616328448619454e-06, "epoch": 8.677814029363784, "percentage": 86.78, "elapsed_time": "7:15:07", "remaining_time": "1:06:17", "throughput": 4397.24, "total_tokens": 114801168} {"current_steps": 53200, "total_steps": 61300, "loss": 0.3264, "lr": 2.613159223685213e-06, "epoch": 8.67862969004894, "percentage": 86.79, "elapsed_time": "7:15:09", "remaining_time": "1:06:15", "throughput": 4397.28, "total_tokens": 114812560} {"current_steps": 53205, "total_steps": 61300, "loss": 0.3086, "lr": 2.609991813541876e-06, "epoch": 8.679445350734095, "percentage": 86.79, "elapsed_time": "7:15:12", "remaining_time": "1:06:12", "throughput": 4397.32, "total_tokens": 114823664} {"current_steps": 53210, "total_steps": 61300, "loss": 0.3463, "lr": 2.6068262184462066e-06, "epoch": 8.68026101141925, "percentage": 86.8, "elapsed_time": "7:15:14", "remaining_time": "1:06:10", "throughput": 4397.37, "total_tokens": 114835056} {"current_steps": 53215, "total_steps": 61300, "loss": 0.3509, "lr": 2.6036624386548277e-06, "epoch": 8.681076672104405, "percentage": 86.81, "elapsed_time": "7:15:16", "remaining_time": "1:06:07", "throughput": 4397.41, "total_tokens": 114845744} {"current_steps": 53220, "total_steps": 61300, "loss": 0.3246, "lr": 2.6005004744242082e-06, "epoch": 8.681892332789559, "percentage": 86.82, "elapsed_time": "7:15:19", "remaining_time": "1:06:05", "throughput": 4397.45, "total_tokens": 114857072} {"current_steps": 53225, "total_steps": 61300, "loss": 0.3212, "lr": 2.597340326010675e-06, "epoch": 8.682707993474715, "percentage": 86.83, "elapsed_time": "7:15:21", "remaining_time": "1:06:02", "throughput": 4397.48, "total_tokens": 114868304} {"current_steps": 53230, "total_steps": 61300, "loss": 0.3247, "lr": 2.5941819936704053e-06, "epoch": 8.68352365415987, "percentage": 86.84, "elapsed_time": "7:15:23", "remaining_time": "1:06:00", "throughput": 4397.51, "total_tokens": 114877360} {"current_steps": 53235, "total_steps": 61300, "loss": 0.3019, "lr": 2.5910254776594256e-06, "epoch": 8.684339314845024, "percentage": 86.84, "elapsed_time": "7:15:25", "remaining_time": "1:05:57", "throughput": 4397.55, "total_tokens": 114888496} {"current_steps": 53240, "total_steps": 61300, "loss": 0.321, "lr": 2.587870778233625e-06, "epoch": 8.68515497553018, "percentage": 86.85, "elapsed_time": "7:15:28", "remaining_time": "1:05:55", "throughput": 4397.59, "total_tokens": 114900656} {"current_steps": 53245, "total_steps": 61300, "loss": 0.3184, "lr": 2.584717895648739e-06, "epoch": 8.685970636215334, "percentage": 86.86, "elapsed_time": "7:15:30", "remaining_time": "1:05:53", "throughput": 4397.62, "total_tokens": 114912208} {"current_steps": 53250, "total_steps": 61300, "loss": 0.3418, "lr": 2.5815668301603537e-06, "epoch": 8.68678629690049, "percentage": 86.87, "elapsed_time": "7:15:32", "remaining_time": "1:05:50", "throughput": 4397.67, "total_tokens": 114924144} {"current_steps": 53255, "total_steps": 61300, "loss": 0.3282, "lr": 2.5784175820239094e-06, "epoch": 8.687601957585644, "percentage": 86.88, "elapsed_time": "7:15:35", "remaining_time": "1:05:48", "throughput": 4397.71, "total_tokens": 114936496} {"current_steps": 53260, "total_steps": 61300, "loss": 0.343, "lr": 2.575270151494702e-06, "epoch": 8.6884176182708, "percentage": 86.88, "elapsed_time": "7:15:37", "remaining_time": "1:05:45", "throughput": 4397.74, "total_tokens": 114946928} {"current_steps": 53265, "total_steps": 61300, "loss": 0.3324, "lr": 2.5721245388278805e-06, "epoch": 8.689233278955955, "percentage": 86.89, "elapsed_time": "7:15:39", "remaining_time": "1:05:43", "throughput": 4397.78, "total_tokens": 114957392} {"current_steps": 53270, "total_steps": 61300, "loss": 0.3371, "lr": 2.5689807442784404e-06, "epoch": 8.690048939641109, "percentage": 86.9, "elapsed_time": "7:15:42", "remaining_time": "1:05:40", "throughput": 4397.82, "total_tokens": 114968816} {"current_steps": 53275, "total_steps": 61300, "loss": 0.3233, "lr": 2.5658387681012337e-06, "epoch": 8.690864600326265, "percentage": 86.91, "elapsed_time": "7:15:44", "remaining_time": "1:05:38", "throughput": 4397.85, "total_tokens": 114979408} {"current_steps": 53280, "total_steps": 61300, "loss": 0.3776, "lr": 2.5626986105509677e-06, "epoch": 8.691680261011419, "percentage": 86.92, "elapsed_time": "7:15:46", "remaining_time": "1:05:35", "throughput": 4397.88, "total_tokens": 114989776} {"current_steps": 53285, "total_steps": 61300, "loss": 0.3355, "lr": 2.5595602718821916e-06, "epoch": 8.692495921696574, "percentage": 86.92, "elapsed_time": "7:15:48", "remaining_time": "1:05:33", "throughput": 4397.91, "total_tokens": 115000976} {"current_steps": 53290, "total_steps": 61300, "loss": 0.345, "lr": 2.5564237523493295e-06, "epoch": 8.69331158238173, "percentage": 86.93, "elapsed_time": "7:15:50", "remaining_time": "1:05:30", "throughput": 4397.95, "total_tokens": 115010608} {"current_steps": 53295, "total_steps": 61300, "loss": 0.3373, "lr": 2.553289052206634e-06, "epoch": 8.694127243066884, "percentage": 86.94, "elapsed_time": "7:15:53", "remaining_time": "1:05:28", "throughput": 4397.99, "total_tokens": 115021904} {"current_steps": 53300, "total_steps": 61300, "loss": 0.3036, "lr": 2.5501561717082204e-06, "epoch": 8.69494290375204, "percentage": 86.95, "elapsed_time": "7:15:55", "remaining_time": "1:05:25", "throughput": 4398.02, "total_tokens": 115032240} {"current_steps": 53305, "total_steps": 61300, "loss": 0.302, "lr": 2.547025111108056e-06, "epoch": 8.695758564437194, "percentage": 86.96, "elapsed_time": "7:15:57", "remaining_time": "1:05:23", "throughput": 4398.06, "total_tokens": 115043024} {"current_steps": 53310, "total_steps": 61300, "loss": 0.3321, "lr": 2.5438958706599623e-06, "epoch": 8.69657422512235, "percentage": 86.97, "elapsed_time": "7:15:59", "remaining_time": "1:05:20", "throughput": 4398.09, "total_tokens": 115053584} {"current_steps": 53315, "total_steps": 61300, "loss": 0.3538, "lr": 2.540768450617609e-06, "epoch": 8.697389885807503, "percentage": 86.97, "elapsed_time": "7:16:02", "remaining_time": "1:05:18", "throughput": 4398.13, "total_tokens": 115064368} {"current_steps": 53320, "total_steps": 61300, "loss": 0.3109, "lr": 2.537642851234523e-06, "epoch": 8.698205546492659, "percentage": 86.98, "elapsed_time": "7:16:04", "remaining_time": "1:05:15", "throughput": 4398.16, "total_tokens": 115073712} {"current_steps": 53325, "total_steps": 61300, "loss": 0.3073, "lr": 2.5345190727640828e-06, "epoch": 8.699021207177815, "percentage": 86.99, "elapsed_time": "7:16:06", "remaining_time": "1:05:13", "throughput": 4398.21, "total_tokens": 115085616} {"current_steps": 53330, "total_steps": 61300, "loss": 0.3821, "lr": 2.5313971154595135e-06, "epoch": 8.699836867862969, "percentage": 87.0, "elapsed_time": "7:16:08", "remaining_time": "1:05:10", "throughput": 4398.24, "total_tokens": 115096080} {"current_steps": 53335, "total_steps": 61300, "loss": 0.2995, "lr": 2.5282769795738987e-06, "epoch": 8.700652528548124, "percentage": 87.01, "elapsed_time": "7:16:10", "remaining_time": "1:05:08", "throughput": 4398.28, "total_tokens": 115107344} {"current_steps": 53340, "total_steps": 61300, "loss": 0.3397, "lr": 2.5251586653601722e-06, "epoch": 8.701468189233278, "percentage": 87.01, "elapsed_time": "7:16:13", "remaining_time": "1:05:05", "throughput": 4398.31, "total_tokens": 115117712} {"current_steps": 53345, "total_steps": 61300, "loss": 0.3282, "lr": 2.522042173071121e-06, "epoch": 8.702283849918434, "percentage": 87.02, "elapsed_time": "7:16:15", "remaining_time": "1:05:03", "throughput": 4398.35, "total_tokens": 115128048} {"current_steps": 53350, "total_steps": 61300, "loss": 0.3139, "lr": 2.518927502959384e-06, "epoch": 8.70309951060359, "percentage": 87.03, "elapsed_time": "7:16:17", "remaining_time": "1:05:00", "throughput": 4398.39, "total_tokens": 115139152} {"current_steps": 53355, "total_steps": 61300, "loss": 0.3119, "lr": 2.5158146552774486e-06, "epoch": 8.703915171288743, "percentage": 87.04, "elapsed_time": "7:16:19", "remaining_time": "1:04:58", "throughput": 4398.42, "total_tokens": 115150032} {"current_steps": 53360, "total_steps": 61300, "loss": 0.2809, "lr": 2.512703630277663e-06, "epoch": 8.7047308319739, "percentage": 87.05, "elapsed_time": "7:16:21", "remaining_time": "1:04:55", "throughput": 4398.45, "total_tokens": 115159536} {"current_steps": 53365, "total_steps": 61300, "loss": 0.3388, "lr": 2.5095944282122226e-06, "epoch": 8.705546492659053, "percentage": 87.06, "elapsed_time": "7:16:24", "remaining_time": "1:04:53", "throughput": 4398.48, "total_tokens": 115170576} {"current_steps": 53370, "total_steps": 61300, "loss": 0.3225, "lr": 2.50648704933317e-06, "epoch": 8.706362153344209, "percentage": 87.06, "elapsed_time": "7:16:26", "remaining_time": "1:04:50", "throughput": 4398.52, "total_tokens": 115182160} {"current_steps": 53375, "total_steps": 61300, "loss": 0.291, "lr": 2.5033814938924095e-06, "epoch": 8.707177814029365, "percentage": 87.07, "elapsed_time": "7:16:28", "remaining_time": "1:04:48", "throughput": 4398.55, "total_tokens": 115190960} {"current_steps": 53380, "total_steps": 61300, "loss": 0.384, "lr": 2.500277762141692e-06, "epoch": 8.707993474714518, "percentage": 87.08, "elapsed_time": "7:16:30", "remaining_time": "1:04:45", "throughput": 4398.58, "total_tokens": 115201680} {"current_steps": 53385, "total_steps": 61300, "loss": 0.274, "lr": 2.49717585433262e-06, "epoch": 8.708809135399674, "percentage": 87.09, "elapsed_time": "7:16:32", "remaining_time": "1:04:43", "throughput": 4398.62, "total_tokens": 115212496} {"current_steps": 53390, "total_steps": 61300, "loss": 0.3472, "lr": 2.4940757707166474e-06, "epoch": 8.709624796084828, "percentage": 87.1, "elapsed_time": "7:16:35", "remaining_time": "1:04:40", "throughput": 4398.66, "total_tokens": 115223888} {"current_steps": 53395, "total_steps": 61300, "loss": 0.351, "lr": 2.490977511545092e-06, "epoch": 8.710440456769984, "percentage": 87.1, "elapsed_time": "7:16:37", "remaining_time": "1:04:38", "throughput": 4398.69, "total_tokens": 115233616} {"current_steps": 53400, "total_steps": 61300, "loss": 0.3743, "lr": 2.4878810770691096e-06, "epoch": 8.71125611745514, "percentage": 87.11, "elapsed_time": "7:16:39", "remaining_time": "1:04:35", "throughput": 4398.73, "total_tokens": 115244496} {"current_steps": 53405, "total_steps": 61300, "loss": 0.3309, "lr": 2.48478646753971e-06, "epoch": 8.712071778140293, "percentage": 87.12, "elapsed_time": "7:16:41", "remaining_time": "1:04:33", "throughput": 4398.76, "total_tokens": 115255216} {"current_steps": 53410, "total_steps": 61300, "loss": 0.3204, "lr": 2.4816936832077615e-06, "epoch": 8.71288743882545, "percentage": 87.13, "elapsed_time": "7:16:43", "remaining_time": "1:04:30", "throughput": 4398.79, "total_tokens": 115264720} {"current_steps": 53415, "total_steps": 61300, "loss": 0.2857, "lr": 2.478602724323981e-06, "epoch": 8.713703099510603, "percentage": 87.14, "elapsed_time": "7:16:46", "remaining_time": "1:04:28", "throughput": 4398.83, "total_tokens": 115276080} {"current_steps": 53420, "total_steps": 61300, "loss": 0.3236, "lr": 2.4755135911389364e-06, "epoch": 8.714518760195759, "percentage": 87.15, "elapsed_time": "7:16:48", "remaining_time": "1:04:25", "throughput": 4398.86, "total_tokens": 115286576} {"current_steps": 53425, "total_steps": 61300, "loss": 0.3346, "lr": 2.472426283903048e-06, "epoch": 8.715334420880914, "percentage": 87.15, "elapsed_time": "7:16:50", "remaining_time": "1:04:23", "throughput": 4398.9, "total_tokens": 115297200} {"current_steps": 53430, "total_steps": 61300, "loss": 0.3103, "lr": 2.4693408028665878e-06, "epoch": 8.716150081566068, "percentage": 87.16, "elapsed_time": "7:16:52", "remaining_time": "1:04:21", "throughput": 4398.93, "total_tokens": 115308240} {"current_steps": 53435, "total_steps": 61300, "loss": 0.326, "lr": 2.4662571482796797e-06, "epoch": 8.716965742251224, "percentage": 87.17, "elapsed_time": "7:16:55", "remaining_time": "1:04:18", "throughput": 4398.97, "total_tokens": 115319600} {"current_steps": 53440, "total_steps": 61300, "loss": 0.2994, "lr": 2.4631753203923052e-06, "epoch": 8.717781402936378, "percentage": 87.18, "elapsed_time": "7:16:57", "remaining_time": "1:04:16", "throughput": 4399.01, "total_tokens": 115330736} {"current_steps": 53445, "total_steps": 61300, "loss": 0.3731, "lr": 2.460095319454289e-06, "epoch": 8.718597063621534, "percentage": 87.19, "elapsed_time": "7:16:59", "remaining_time": "1:04:13", "throughput": 4399.05, "total_tokens": 115342672} {"current_steps": 53450, "total_steps": 61300, "loss": 0.3403, "lr": 2.4570171457153123e-06, "epoch": 8.719412724306688, "percentage": 87.19, "elapsed_time": "7:17:02", "remaining_time": "1:04:11", "throughput": 4399.08, "total_tokens": 115354320} {"current_steps": 53455, "total_steps": 61300, "loss": 0.3541, "lr": 2.4539407994249088e-06, "epoch": 8.720228384991843, "percentage": 87.2, "elapsed_time": "7:17:04", "remaining_time": "1:04:08", "throughput": 4399.11, "total_tokens": 115364880} {"current_steps": 53460, "total_steps": 61300, "loss": 0.3217, "lr": 2.450866280832456e-06, "epoch": 8.721044045676999, "percentage": 87.21, "elapsed_time": "7:17:06", "remaining_time": "1:04:06", "throughput": 4399.15, "total_tokens": 115375824} {"current_steps": 53465, "total_steps": 61300, "loss": 0.2851, "lr": 2.4477935901872e-06, "epoch": 8.721859706362153, "percentage": 87.22, "elapsed_time": "7:17:09", "remaining_time": "1:04:03", "throughput": 4399.18, "total_tokens": 115386992} {"current_steps": 53470, "total_steps": 61300, "loss": 0.3279, "lr": 2.4447227277382244e-06, "epoch": 8.722675367047309, "percentage": 87.23, "elapsed_time": "7:17:11", "remaining_time": "1:04:01", "throughput": 4399.21, "total_tokens": 115397008} {"current_steps": 53475, "total_steps": 61300, "loss": 0.3329, "lr": 2.441653693734472e-06, "epoch": 8.723491027732463, "percentage": 87.23, "elapsed_time": "7:17:13", "remaining_time": "1:03:58", "throughput": 4399.25, "total_tokens": 115407888} {"current_steps": 53480, "total_steps": 61300, "loss": 0.3189, "lr": 2.438586488424727e-06, "epoch": 8.724306688417618, "percentage": 87.24, "elapsed_time": "7:17:15", "remaining_time": "1:03:56", "throughput": 4399.28, "total_tokens": 115417936} {"current_steps": 53485, "total_steps": 61300, "loss": 0.3159, "lr": 2.435521112057637e-06, "epoch": 8.725122349102774, "percentage": 87.25, "elapsed_time": "7:17:17", "remaining_time": "1:03:53", "throughput": 4399.32, "total_tokens": 115429200} {"current_steps": 53490, "total_steps": 61300, "loss": 0.3329, "lr": 2.432457564881699e-06, "epoch": 8.725938009787928, "percentage": 87.26, "elapsed_time": "7:17:20", "remaining_time": "1:03:51", "throughput": 4399.35, "total_tokens": 115439920} {"current_steps": 53495, "total_steps": 61300, "loss": 0.3831, "lr": 2.429395847145252e-06, "epoch": 8.726753670473084, "percentage": 87.27, "elapsed_time": "7:17:22", "remaining_time": "1:03:48", "throughput": 4399.38, "total_tokens": 115450608} {"current_steps": 53500, "total_steps": 61300, "loss": 0.35, "lr": 2.4263359590965042e-06, "epoch": 8.727569331158238, "percentage": 87.28, "elapsed_time": "7:17:24", "remaining_time": "1:03:46", "throughput": 4399.42, "total_tokens": 115461680} {"current_steps": 53505, "total_steps": 61300, "loss": 0.3064, "lr": 2.4232779009835006e-06, "epoch": 8.728384991843393, "percentage": 87.28, "elapsed_time": "7:17:27", "remaining_time": "1:03:43", "throughput": 4399.46, "total_tokens": 115472752} {"current_steps": 53510, "total_steps": 61300, "loss": 0.3108, "lr": 2.420221673054143e-06, "epoch": 8.729200652528547, "percentage": 87.29, "elapsed_time": "7:17:29", "remaining_time": "1:03:41", "throughput": 4399.49, "total_tokens": 115483536} {"current_steps": 53515, "total_steps": 61300, "loss": 0.3347, "lr": 2.417167275556187e-06, "epoch": 8.730016313213703, "percentage": 87.3, "elapsed_time": "7:17:31", "remaining_time": "1:03:38", "throughput": 4399.53, "total_tokens": 115494736} {"current_steps": 53520, "total_steps": 61300, "loss": 0.3573, "lr": 2.4141147087372336e-06, "epoch": 8.730831973898859, "percentage": 87.31, "elapsed_time": "7:17:33", "remaining_time": "1:03:36", "throughput": 4399.56, "total_tokens": 115505552} {"current_steps": 53525, "total_steps": 61300, "loss": 0.2992, "lr": 2.4110639728447433e-06, "epoch": 8.731647634584013, "percentage": 87.32, "elapsed_time": "7:17:35", "remaining_time": "1:03:33", "throughput": 4399.6, "total_tokens": 115515920} {"current_steps": 53530, "total_steps": 61300, "loss": 0.3031, "lr": 2.4080150681260212e-06, "epoch": 8.732463295269168, "percentage": 87.32, "elapsed_time": "7:17:38", "remaining_time": "1:03:31", "throughput": 4399.64, "total_tokens": 115526896} {"current_steps": 53535, "total_steps": 61300, "loss": 0.306, "lr": 2.4049679948282305e-06, "epoch": 8.733278955954322, "percentage": 87.33, "elapsed_time": "7:17:40", "remaining_time": "1:03:28", "throughput": 4399.68, "total_tokens": 115536912} {"current_steps": 53540, "total_steps": 61300, "loss": 0.348, "lr": 2.401922753198377e-06, "epoch": 8.734094616639478, "percentage": 87.34, "elapsed_time": "7:17:42", "remaining_time": "1:03:26", "throughput": 4399.71, "total_tokens": 115547728} {"current_steps": 53545, "total_steps": 61300, "loss": 0.2922, "lr": 2.398879343483329e-06, "epoch": 8.734910277324634, "percentage": 87.35, "elapsed_time": "7:17:44", "remaining_time": "1:03:23", "throughput": 4399.75, "total_tokens": 115559184} {"current_steps": 53550, "total_steps": 61300, "loss": 0.3265, "lr": 2.3958377659297983e-06, "epoch": 8.735725938009788, "percentage": 87.36, "elapsed_time": "7:17:47", "remaining_time": "1:03:21", "throughput": 4399.79, "total_tokens": 115569552} {"current_steps": 53555, "total_steps": 61300, "loss": 0.331, "lr": 2.392798020784348e-06, "epoch": 8.736541598694943, "percentage": 87.37, "elapsed_time": "7:17:49", "remaining_time": "1:03:18", "throughput": 4399.82, "total_tokens": 115578928} {"current_steps": 53560, "total_steps": 61300, "loss": 0.3478, "lr": 2.3897601082934013e-06, "epoch": 8.737357259380097, "percentage": 87.37, "elapsed_time": "7:17:51", "remaining_time": "1:03:16", "throughput": 4399.85, "total_tokens": 115589904} {"current_steps": 53565, "total_steps": 61300, "loss": 0.3526, "lr": 2.3867240287032214e-06, "epoch": 8.738172920065253, "percentage": 87.38, "elapsed_time": "7:17:53", "remaining_time": "1:03:13", "throughput": 4399.89, "total_tokens": 115599440} {"current_steps": 53570, "total_steps": 61300, "loss": 0.3238, "lr": 2.3836897822599317e-06, "epoch": 8.738988580750409, "percentage": 87.39, "elapsed_time": "7:17:55", "remaining_time": "1:03:11", "throughput": 4399.92, "total_tokens": 115610064} {"current_steps": 53575, "total_steps": 61300, "loss": 0.3272, "lr": 2.380657369209502e-06, "epoch": 8.739804241435563, "percentage": 87.4, "elapsed_time": "7:17:57", "remaining_time": "1:03:09", "throughput": 4399.96, "total_tokens": 115621360} {"current_steps": 53580, "total_steps": 61300, "loss": 0.3355, "lr": 2.3776267897977543e-06, "epoch": 8.740619902120718, "percentage": 87.41, "elapsed_time": "7:18:00", "remaining_time": "1:03:06", "throughput": 4399.99, "total_tokens": 115632272} {"current_steps": 53585, "total_steps": 61300, "loss": 0.325, "lr": 2.374598044270365e-06, "epoch": 8.741435562805872, "percentage": 87.41, "elapsed_time": "7:18:02", "remaining_time": "1:03:04", "throughput": 4400.04, "total_tokens": 115643280} {"current_steps": 53590, "total_steps": 61300, "loss": 0.3455, "lr": 2.3715711328728575e-06, "epoch": 8.742251223491028, "percentage": 87.42, "elapsed_time": "7:18:04", "remaining_time": "1:03:01", "throughput": 4400.07, "total_tokens": 115654128} {"current_steps": 53595, "total_steps": 61300, "loss": 0.3289, "lr": 2.3685460558506097e-06, "epoch": 8.743066884176184, "percentage": 87.43, "elapsed_time": "7:18:06", "remaining_time": "1:02:59", "throughput": 4400.11, "total_tokens": 115664528} {"current_steps": 53600, "total_steps": 61300, "loss": 0.3446, "lr": 2.3655228134488505e-06, "epoch": 8.743882544861338, "percentage": 87.44, "elapsed_time": "7:18:08", "remaining_time": "1:02:56", "throughput": 4400.14, "total_tokens": 115675024} {"current_steps": 53605, "total_steps": 61300, "loss": 0.3039, "lr": 2.362501405912651e-06, "epoch": 8.744698205546493, "percentage": 87.45, "elapsed_time": "7:18:11", "remaining_time": "1:02:54", "throughput": 4400.19, "total_tokens": 115687056} {"current_steps": 53610, "total_steps": 61300, "loss": 0.3292, "lr": 2.3594818334869568e-06, "epoch": 8.745513866231647, "percentage": 87.46, "elapsed_time": "7:18:13", "remaining_time": "1:02:51", "throughput": 4400.22, "total_tokens": 115697840} {"current_steps": 53615, "total_steps": 61300, "loss": 0.3514, "lr": 2.3564640964165386e-06, "epoch": 8.746329526916803, "percentage": 87.46, "elapsed_time": "7:18:15", "remaining_time": "1:02:49", "throughput": 4400.25, "total_tokens": 115708848} {"current_steps": 53620, "total_steps": 61300, "loss": 0.3153, "lr": 2.353448194946037e-06, "epoch": 8.747145187601957, "percentage": 87.47, "elapsed_time": "7:18:18", "remaining_time": "1:02:46", "throughput": 4400.29, "total_tokens": 115719568} {"current_steps": 53625, "total_steps": 61300, "loss": 0.3695, "lr": 2.350434129319928e-06, "epoch": 8.747960848287113, "percentage": 87.48, "elapsed_time": "7:18:20", "remaining_time": "1:02:44", "throughput": 4400.32, "total_tokens": 115730768} {"current_steps": 53630, "total_steps": 61300, "loss": 0.3085, "lr": 2.347421899782551e-06, "epoch": 8.748776508972268, "percentage": 87.49, "elapsed_time": "7:18:22", "remaining_time": "1:02:41", "throughput": 4400.36, "total_tokens": 115741840} {"current_steps": 53635, "total_steps": 61300, "loss": 0.3063, "lr": 2.3444115065780953e-06, "epoch": 8.749592169657422, "percentage": 87.5, "elapsed_time": "7:18:25", "remaining_time": "1:02:39", "throughput": 4400.39, "total_tokens": 115752208} {"current_steps": 53640, "total_steps": 61300, "loss": 0.3296, "lr": 2.341402949950594e-06, "epoch": 8.750407830342578, "percentage": 87.5, "elapsed_time": "7:18:27", "remaining_time": "1:02:36", "throughput": 4400.42, "total_tokens": 115762992} {"current_steps": 53645, "total_steps": 61300, "loss": 0.3328, "lr": 2.338396230143941e-06, "epoch": 8.751223491027732, "percentage": 87.51, "elapsed_time": "7:18:29", "remaining_time": "1:02:34", "throughput": 4400.46, "total_tokens": 115774224} {"current_steps": 53650, "total_steps": 61300, "loss": 0.3258, "lr": 2.335391347401872e-06, "epoch": 8.752039151712887, "percentage": 87.52, "elapsed_time": "7:18:31", "remaining_time": "1:02:31", "throughput": 4400.5, "total_tokens": 115785776} {"current_steps": 53655, "total_steps": 61300, "loss": 0.3406, "lr": 2.3323883019679805e-06, "epoch": 8.752854812398043, "percentage": 87.53, "elapsed_time": "7:18:34", "remaining_time": "1:02:29", "throughput": 4400.54, "total_tokens": 115796656} {"current_steps": 53660, "total_steps": 61300, "loss": 0.3031, "lr": 2.3293870940857084e-06, "epoch": 8.753670473083197, "percentage": 87.54, "elapsed_time": "7:18:36", "remaining_time": "1:02:26", "throughput": 4400.58, "total_tokens": 115808272} {"current_steps": 53665, "total_steps": 61300, "loss": 0.3284, "lr": 2.326387723998347e-06, "epoch": 8.754486133768353, "percentage": 87.54, "elapsed_time": "7:18:39", "remaining_time": "1:02:24", "throughput": 4400.62, "total_tokens": 115820144} {"current_steps": 53670, "total_steps": 61300, "loss": 0.3276, "lr": 2.3233901919490404e-06, "epoch": 8.755301794453507, "percentage": 87.55, "elapsed_time": "7:18:41", "remaining_time": "1:02:21", "throughput": 4400.66, "total_tokens": 115831888} {"current_steps": 53675, "total_steps": 61300, "loss": 0.3203, "lr": 2.3203944981807835e-06, "epoch": 8.756117455138662, "percentage": 87.56, "elapsed_time": "7:18:43", "remaining_time": "1:02:19", "throughput": 4400.69, "total_tokens": 115843024} {"current_steps": 53680, "total_steps": 61300, "loss": 0.3088, "lr": 2.3174006429364263e-06, "epoch": 8.756933115823816, "percentage": 87.57, "elapsed_time": "7:18:46", "remaining_time": "1:02:17", "throughput": 4400.73, "total_tokens": 115854288} {"current_steps": 53685, "total_steps": 61300, "loss": 0.3228, "lr": 2.314408626458664e-06, "epoch": 8.757748776508972, "percentage": 87.58, "elapsed_time": "7:18:48", "remaining_time": "1:02:14", "throughput": 4400.77, "total_tokens": 115865296} {"current_steps": 53690, "total_steps": 61300, "loss": 0.3405, "lr": 2.311418448990041e-06, "epoch": 8.758564437194128, "percentage": 87.59, "elapsed_time": "7:18:50", "remaining_time": "1:02:12", "throughput": 4400.8, "total_tokens": 115876304} {"current_steps": 53695, "total_steps": 61300, "loss": 0.3314, "lr": 2.3084301107729633e-06, "epoch": 8.759380097879282, "percentage": 87.59, "elapsed_time": "7:18:53", "remaining_time": "1:02:09", "throughput": 4400.83, "total_tokens": 115887632} {"current_steps": 53700, "total_steps": 61300, "loss": 0.3245, "lr": 2.3054436120496736e-06, "epoch": 8.760195758564437, "percentage": 87.6, "elapsed_time": "7:18:55", "remaining_time": "1:02:07", "throughput": 4400.87, "total_tokens": 115898640} {"current_steps": 53705, "total_steps": 61300, "loss": 0.3365, "lr": 2.302458953062275e-06, "epoch": 8.761011419249591, "percentage": 87.61, "elapsed_time": "7:18:57", "remaining_time": "1:02:04", "throughput": 4400.91, "total_tokens": 115909392} {"current_steps": 53710, "total_steps": 61300, "loss": 0.3683, "lr": 2.2994761340527195e-06, "epoch": 8.761827079934747, "percentage": 87.62, "elapsed_time": "7:18:59", "remaining_time": "1:02:02", "throughput": 4400.94, "total_tokens": 115920080} {"current_steps": 53715, "total_steps": 61300, "loss": 0.2857, "lr": 2.2964951552628096e-06, "epoch": 8.762642740619903, "percentage": 87.63, "elapsed_time": "7:19:02", "remaining_time": "1:01:59", "throughput": 4400.97, "total_tokens": 115930640} {"current_steps": 53720, "total_steps": 61300, "loss": 0.3368, "lr": 2.293516016934202e-06, "epoch": 8.763458401305057, "percentage": 87.63, "elapsed_time": "7:19:04", "remaining_time": "1:01:57", "throughput": 4401.0, "total_tokens": 115941392} {"current_steps": 53725, "total_steps": 61300, "loss": 0.2907, "lr": 2.2905387193083965e-06, "epoch": 8.764274061990212, "percentage": 87.64, "elapsed_time": "7:19:06", "remaining_time": "1:01:54", "throughput": 4401.03, "total_tokens": 115952176} {"current_steps": 53730, "total_steps": 61300, "loss": 0.3438, "lr": 2.287563262626749e-06, "epoch": 8.765089722675366, "percentage": 87.65, "elapsed_time": "7:19:08", "remaining_time": "1:01:52", "throughput": 4401.07, "total_tokens": 115962896} {"current_steps": 53735, "total_steps": 61300, "loss": 0.3273, "lr": 2.2845896471304667e-06, "epoch": 8.765905383360522, "percentage": 87.66, "elapsed_time": "7:19:10", "remaining_time": "1:01:49", "throughput": 4401.1, "total_tokens": 115972944} {"current_steps": 53740, "total_steps": 61300, "loss": 0.3688, "lr": 2.2816178730606012e-06, "epoch": 8.766721044045678, "percentage": 87.67, "elapsed_time": "7:19:13", "remaining_time": "1:01:47", "throughput": 4401.13, "total_tokens": 115983600} {"current_steps": 53745, "total_steps": 61300, "loss": 0.3706, "lr": 2.2786479406580658e-06, "epoch": 8.767536704730832, "percentage": 87.68, "elapsed_time": "7:19:15", "remaining_time": "1:01:44", "throughput": 4401.17, "total_tokens": 115994832} {"current_steps": 53750, "total_steps": 61300, "loss": 0.3171, "lr": 2.2756798501636146e-06, "epoch": 8.768352365415987, "percentage": 87.68, "elapsed_time": "7:19:17", "remaining_time": "1:01:42", "throughput": 4401.2, "total_tokens": 116004848} {"current_steps": 53755, "total_steps": 61300, "loss": 0.3256, "lr": 2.272713601817855e-06, "epoch": 8.769168026101141, "percentage": 87.69, "elapsed_time": "7:19:19", "remaining_time": "1:01:39", "throughput": 4401.24, "total_tokens": 116016016} {"current_steps": 53760, "total_steps": 61300, "loss": 0.3359, "lr": 2.269749195861251e-06, "epoch": 8.769983686786297, "percentage": 87.7, "elapsed_time": "7:19:22", "remaining_time": "1:01:37", "throughput": 4401.28, "total_tokens": 116027088} {"current_steps": 53765, "total_steps": 61300, "loss": 0.3433, "lr": 2.266786632534107e-06, "epoch": 8.770799347471453, "percentage": 87.71, "elapsed_time": "7:19:24", "remaining_time": "1:01:34", "throughput": 4401.31, "total_tokens": 116038192} {"current_steps": 53770, "total_steps": 61300, "loss": 0.3525, "lr": 2.2638259120765864e-06, "epoch": 8.771615008156607, "percentage": 87.72, "elapsed_time": "7:19:26", "remaining_time": "1:01:32", "throughput": 4401.34, "total_tokens": 116048272} {"current_steps": 53775, "total_steps": 61300, "loss": 0.3515, "lr": 2.2608670347286947e-06, "epoch": 8.772430668841762, "percentage": 87.72, "elapsed_time": "7:19:29", "remaining_time": "1:01:29", "throughput": 4401.38, "total_tokens": 116060112} {"current_steps": 53780, "total_steps": 61300, "loss": 0.3338, "lr": 2.257910000730304e-06, "epoch": 8.773246329526916, "percentage": 87.73, "elapsed_time": "7:19:31", "remaining_time": "1:01:27", "throughput": 4401.42, "total_tokens": 116071216} {"current_steps": 53785, "total_steps": 61300, "loss": 0.3188, "lr": 2.2549548103211222e-06, "epoch": 8.774061990212072, "percentage": 87.74, "elapsed_time": "7:19:33", "remaining_time": "1:01:24", "throughput": 4401.46, "total_tokens": 116081360} {"current_steps": 53790, "total_steps": 61300, "loss": 0.3152, "lr": 2.2520014637407076e-06, "epoch": 8.774877650897226, "percentage": 87.75, "elapsed_time": "7:19:35", "remaining_time": "1:01:22", "throughput": 4401.49, "total_tokens": 116091216} {"current_steps": 53795, "total_steps": 61300, "loss": 0.3397, "lr": 2.2490499612284777e-06, "epoch": 8.775693311582382, "percentage": 87.76, "elapsed_time": "7:19:37", "remaining_time": "1:01:19", "throughput": 4401.51, "total_tokens": 116101168} {"current_steps": 53800, "total_steps": 61300, "loss": 0.298, "lr": 2.246100303023696e-06, "epoch": 8.776508972267537, "percentage": 87.77, "elapsed_time": "7:19:39", "remaining_time": "1:01:17", "throughput": 4401.55, "total_tokens": 116112272} {"current_steps": 53805, "total_steps": 61300, "loss": 0.3422, "lr": 2.2431524893654743e-06, "epoch": 8.777324632952691, "percentage": 87.77, "elapsed_time": "7:19:42", "remaining_time": "1:01:15", "throughput": 4401.59, "total_tokens": 116123184} {"current_steps": 53810, "total_steps": 61300, "loss": 0.3731, "lr": 2.2402065204927797e-06, "epoch": 8.778140293637847, "percentage": 87.78, "elapsed_time": "7:19:44", "remaining_time": "1:01:12", "throughput": 4401.63, "total_tokens": 116133776} {"current_steps": 53815, "total_steps": 61300, "loss": 0.3288, "lr": 2.237262396644421e-06, "epoch": 8.778955954323001, "percentage": 87.79, "elapsed_time": "7:19:46", "remaining_time": "1:01:10", "throughput": 4401.66, "total_tokens": 116144688} {"current_steps": 53820, "total_steps": 61300, "loss": 0.3337, "lr": 2.2343201180590745e-06, "epoch": 8.779771615008157, "percentage": 87.8, "elapsed_time": "7:19:48", "remaining_time": "1:01:07", "throughput": 4401.69, "total_tokens": 116154288} {"current_steps": 53825, "total_steps": 61300, "loss": 0.3506, "lr": 2.2313796849752516e-06, "epoch": 8.780587275693312, "percentage": 87.81, "elapsed_time": "7:19:50", "remaining_time": "1:01:05", "throughput": 4401.73, "total_tokens": 116165584} {"current_steps": 53830, "total_steps": 61300, "loss": 0.3168, "lr": 2.2284410976313174e-06, "epoch": 8.781402936378466, "percentage": 87.81, "elapsed_time": "7:19:53", "remaining_time": "1:01:02", "throughput": 4401.77, "total_tokens": 116176848} {"current_steps": 53835, "total_steps": 61300, "loss": 0.3285, "lr": 2.2255043562654926e-06, "epoch": 8.782218597063622, "percentage": 87.82, "elapsed_time": "7:19:55", "remaining_time": "1:01:00", "throughput": 4401.79, "total_tokens": 116186800} {"current_steps": 53840, "total_steps": 61300, "loss": 0.3358, "lr": 2.2225694611158366e-06, "epoch": 8.783034257748776, "percentage": 87.83, "elapsed_time": "7:19:57", "remaining_time": "1:00:57", "throughput": 4401.82, "total_tokens": 116196656} {"current_steps": 53845, "total_steps": 61300, "loss": 0.3834, "lr": 2.2196364124202756e-06, "epoch": 8.783849918433932, "percentage": 87.84, "elapsed_time": "7:19:59", "remaining_time": "1:00:55", "throughput": 4401.86, "total_tokens": 116207760} {"current_steps": 53850, "total_steps": 61300, "loss": 0.3162, "lr": 2.2167052104165724e-06, "epoch": 8.784665579119086, "percentage": 87.85, "elapsed_time": "7:20:01", "remaining_time": "1:00:52", "throughput": 4401.89, "total_tokens": 116216752} {"current_steps": 53855, "total_steps": 61300, "loss": 0.3203, "lr": 2.2137758553423454e-06, "epoch": 8.785481239804241, "percentage": 87.85, "elapsed_time": "7:20:03", "remaining_time": "1:00:50", "throughput": 4401.92, "total_tokens": 116227568} {"current_steps": 53860, "total_steps": 61300, "loss": 0.308, "lr": 2.2108483474350626e-06, "epoch": 8.786296900489397, "percentage": 87.86, "elapsed_time": "7:20:06", "remaining_time": "1:00:47", "throughput": 4401.96, "total_tokens": 116238736} {"current_steps": 53865, "total_steps": 61300, "loss": 0.345, "lr": 2.207922686932046e-06, "epoch": 8.78711256117455, "percentage": 87.87, "elapsed_time": "7:20:08", "remaining_time": "1:00:45", "throughput": 4401.99, "total_tokens": 116249584} {"current_steps": 53870, "total_steps": 61300, "loss": 0.3567, "lr": 2.2049988740704604e-06, "epoch": 8.787928221859707, "percentage": 87.88, "elapsed_time": "7:20:10", "remaining_time": "1:00:42", "throughput": 4402.03, "total_tokens": 116259664} {"current_steps": 53875, "total_steps": 61300, "loss": 0.3504, "lr": 2.202076909087328e-06, "epoch": 8.78874388254486, "percentage": 87.89, "elapsed_time": "7:20:12", "remaining_time": "1:00:40", "throughput": 4402.06, "total_tokens": 116270352} {"current_steps": 53880, "total_steps": 61300, "loss": 0.3189, "lr": 2.199156792219517e-06, "epoch": 8.789559543230016, "percentage": 87.9, "elapsed_time": "7:20:14", "remaining_time": "1:00:37", "throughput": 4402.09, "total_tokens": 116281232} {"current_steps": 53885, "total_steps": 61300, "loss": 0.3062, "lr": 2.1962385237037445e-06, "epoch": 8.790375203915172, "percentage": 87.9, "elapsed_time": "7:20:17", "remaining_time": "1:00:35", "throughput": 4402.13, "total_tokens": 116291728} {"current_steps": 53890, "total_steps": 61300, "loss": 0.3414, "lr": 2.193322103776585e-06, "epoch": 8.791190864600326, "percentage": 87.91, "elapsed_time": "7:20:19", "remaining_time": "1:00:32", "throughput": 4402.16, "total_tokens": 116302480} {"current_steps": 53895, "total_steps": 61300, "loss": 0.3402, "lr": 2.1904075326744543e-06, "epoch": 8.792006525285482, "percentage": 87.92, "elapsed_time": "7:20:21", "remaining_time": "1:00:30", "throughput": 4402.2, "total_tokens": 116314192} {"current_steps": 53900, "total_steps": 61300, "loss": 0.3183, "lr": 2.1874948106336254e-06, "epoch": 8.792822185970635, "percentage": 87.93, "elapsed_time": "7:20:24", "remaining_time": "1:00:27", "throughput": 4402.24, "total_tokens": 116325616} {"current_steps": 53905, "total_steps": 61300, "loss": 0.302, "lr": 2.1845839378902167e-06, "epoch": 8.793637846655791, "percentage": 87.94, "elapsed_time": "7:20:26", "remaining_time": "1:00:25", "throughput": 4402.27, "total_tokens": 116335344} {"current_steps": 53910, "total_steps": 61300, "loss": 0.3411, "lr": 2.181674914680196e-06, "epoch": 8.794453507340947, "percentage": 87.94, "elapsed_time": "7:20:28", "remaining_time": "1:00:22", "throughput": 4402.3, "total_tokens": 116346480} {"current_steps": 53915, "total_steps": 61300, "loss": 0.3433, "lr": 2.178767741239382e-06, "epoch": 8.7952691680261, "percentage": 87.95, "elapsed_time": "7:20:31", "remaining_time": "1:00:20", "throughput": 4402.34, "total_tokens": 116358576} {"current_steps": 53920, "total_steps": 61300, "loss": 0.3198, "lr": 2.1758624178034537e-06, "epoch": 8.796084828711257, "percentage": 87.96, "elapsed_time": "7:20:33", "remaining_time": "1:00:17", "throughput": 4402.37, "total_tokens": 116369872} {"current_steps": 53925, "total_steps": 61300, "loss": 0.3463, "lr": 2.1729589446079252e-06, "epoch": 8.79690048939641, "percentage": 87.97, "elapsed_time": "7:20:35", "remaining_time": "1:00:15", "throughput": 4402.41, "total_tokens": 116380432} {"current_steps": 53930, "total_steps": 61300, "loss": 0.3301, "lr": 2.1700573218881694e-06, "epoch": 8.797716150081566, "percentage": 87.98, "elapsed_time": "7:20:37", "remaining_time": "1:00:12", "throughput": 4402.45, "total_tokens": 116390544} {"current_steps": 53935, "total_steps": 61300, "loss": 0.3518, "lr": 2.167157549879406e-06, "epoch": 8.798531810766722, "percentage": 87.99, "elapsed_time": "7:20:40", "remaining_time": "1:00:10", "throughput": 4402.49, "total_tokens": 116402512} {"current_steps": 53940, "total_steps": 61300, "loss": 0.338, "lr": 2.1642596288166976e-06, "epoch": 8.799347471451876, "percentage": 87.99, "elapsed_time": "7:20:42", "remaining_time": "1:00:08", "throughput": 4402.52, "total_tokens": 116413488} {"current_steps": 53945, "total_steps": 61300, "loss": 0.3643, "lr": 2.1613635589349756e-06, "epoch": 8.800163132137031, "percentage": 88.0, "elapsed_time": "7:20:44", "remaining_time": "1:00:05", "throughput": 4402.57, "total_tokens": 116424976} {"current_steps": 53950, "total_steps": 61300, "loss": 0.3548, "lr": 2.1584693404690076e-06, "epoch": 8.800978792822185, "percentage": 88.01, "elapsed_time": "7:20:47", "remaining_time": "1:00:03", "throughput": 4402.6, "total_tokens": 116435856} {"current_steps": 53955, "total_steps": 61300, "loss": 0.3516, "lr": 2.155576973653409e-06, "epoch": 8.801794453507341, "percentage": 88.02, "elapsed_time": "7:20:49", "remaining_time": "1:00:00", "throughput": 4402.64, "total_tokens": 116447472} {"current_steps": 53960, "total_steps": 61300, "loss": 0.3554, "lr": 2.1526864587226525e-06, "epoch": 8.802610114192497, "percentage": 88.03, "elapsed_time": "7:20:51", "remaining_time": "0:59:58", "throughput": 4402.68, "total_tokens": 116458064} {"current_steps": 53965, "total_steps": 61300, "loss": 0.2897, "lr": 2.14979779591106e-06, "epoch": 8.80342577487765, "percentage": 88.03, "elapsed_time": "7:20:53", "remaining_time": "0:59:55", "throughput": 4402.71, "total_tokens": 116468464} {"current_steps": 53970, "total_steps": 61300, "loss": 0.3209, "lr": 2.1469109854527993e-06, "epoch": 8.804241435562806, "percentage": 88.04, "elapsed_time": "7:20:55", "remaining_time": "0:59:53", "throughput": 4402.73, "total_tokens": 116477488} {"current_steps": 53975, "total_steps": 61300, "loss": 0.3474, "lr": 2.1440260275818856e-06, "epoch": 8.80505709624796, "percentage": 88.05, "elapsed_time": "7:20:57", "remaining_time": "0:59:50", "throughput": 4402.77, "total_tokens": 116488368} {"current_steps": 53980, "total_steps": 61300, "loss": 0.3452, "lr": 2.1411429225321965e-06, "epoch": 8.805872756933116, "percentage": 88.06, "elapsed_time": "7:21:00", "remaining_time": "0:59:48", "throughput": 4402.81, "total_tokens": 116498704} {"current_steps": 53985, "total_steps": 61300, "loss": 0.345, "lr": 2.138261670537445e-06, "epoch": 8.80668841761827, "percentage": 88.07, "elapsed_time": "7:21:02", "remaining_time": "0:59:45", "throughput": 4402.85, "total_tokens": 116510000} {"current_steps": 53990, "total_steps": 61300, "loss": 0.3237, "lr": 2.1353822718312016e-06, "epoch": 8.807504078303426, "percentage": 88.08, "elapsed_time": "7:21:04", "remaining_time": "0:59:43", "throughput": 4402.89, "total_tokens": 116521552} {"current_steps": 53995, "total_steps": 61300, "loss": 0.3029, "lr": 2.132504726646883e-06, "epoch": 8.808319738988581, "percentage": 88.08, "elapsed_time": "7:21:06", "remaining_time": "0:59:40", "throughput": 4402.93, "total_tokens": 116532208} {"current_steps": 54000, "total_steps": 61300, "loss": 0.3282, "lr": 2.1296290352177644e-06, "epoch": 8.809135399673735, "percentage": 88.09, "elapsed_time": "7:21:09", "remaining_time": "0:59:38", "throughput": 4402.96, "total_tokens": 116542608} {"current_steps": 54005, "total_steps": 61300, "loss": 0.3103, "lr": 2.1267551977769555e-06, "epoch": 8.809951060358891, "percentage": 88.1, "elapsed_time": "7:21:11", "remaining_time": "0:59:35", "throughput": 4403.0, "total_tokens": 116552656} {"current_steps": 54010, "total_steps": 61300, "loss": 0.3335, "lr": 2.123883214557429e-06, "epoch": 8.810766721044045, "percentage": 88.11, "elapsed_time": "7:21:13", "remaining_time": "0:59:33", "throughput": 4403.04, "total_tokens": 116565008} {"current_steps": 54015, "total_steps": 61300, "loss": 0.3455, "lr": 2.1210130857920034e-06, "epoch": 8.8115823817292, "percentage": 88.12, "elapsed_time": "7:21:15", "remaining_time": "0:59:30", "throughput": 4403.06, "total_tokens": 116574576} {"current_steps": 54020, "total_steps": 61300, "loss": 0.324, "lr": 2.1181448117133408e-06, "epoch": 8.812398042414356, "percentage": 88.12, "elapsed_time": "7:21:17", "remaining_time": "0:59:28", "throughput": 4403.09, "total_tokens": 116584944} {"current_steps": 54025, "total_steps": 61300, "loss": 0.3236, "lr": 2.115278392553963e-06, "epoch": 8.81321370309951, "percentage": 88.13, "elapsed_time": "7:21:20", "remaining_time": "0:59:25", "throughput": 4403.12, "total_tokens": 116595920} {"current_steps": 54030, "total_steps": 61300, "loss": 0.3515, "lr": 2.112413828546231e-06, "epoch": 8.814029363784666, "percentage": 88.14, "elapsed_time": "7:21:22", "remaining_time": "0:59:23", "throughput": 4403.16, "total_tokens": 116606704} {"current_steps": 54035, "total_steps": 61300, "loss": 0.3212, "lr": 2.1095511199223676e-06, "epoch": 8.81484502446982, "percentage": 88.15, "elapsed_time": "7:21:24", "remaining_time": "0:59:20", "throughput": 4403.19, "total_tokens": 116618032} {"current_steps": 54040, "total_steps": 61300, "loss": 0.3322, "lr": 2.106690266914435e-06, "epoch": 8.815660685154976, "percentage": 88.16, "elapsed_time": "7:21:27", "remaining_time": "0:59:18", "throughput": 4403.23, "total_tokens": 116628464} {"current_steps": 54045, "total_steps": 61300, "loss": 0.3159, "lr": 2.10383126975435e-06, "epoch": 8.81647634584013, "percentage": 88.16, "elapsed_time": "7:21:29", "remaining_time": "0:59:15", "throughput": 4403.27, "total_tokens": 116639408} {"current_steps": 54050, "total_steps": 61300, "loss": 0.353, "lr": 2.1009741286738745e-06, "epoch": 8.817292006525285, "percentage": 88.17, "elapsed_time": "7:21:31", "remaining_time": "0:59:13", "throughput": 4403.3, "total_tokens": 116649808} {"current_steps": 54055, "total_steps": 61300, "loss": 0.3441, "lr": 2.098118843904626e-06, "epoch": 8.818107667210441, "percentage": 88.18, "elapsed_time": "7:21:33", "remaining_time": "0:59:10", "throughput": 4403.34, "total_tokens": 116661584} {"current_steps": 54060, "total_steps": 61300, "loss": 0.3214, "lr": 2.0952654156780686e-06, "epoch": 8.818923327895595, "percentage": 88.19, "elapsed_time": "7:21:35", "remaining_time": "0:59:08", "throughput": 4403.38, "total_tokens": 116671664} {"current_steps": 54065, "total_steps": 61300, "loss": 0.3401, "lr": 2.09241384422551e-06, "epoch": 8.81973898858075, "percentage": 88.2, "elapsed_time": "7:21:38", "remaining_time": "0:59:06", "throughput": 4403.42, "total_tokens": 116683248} {"current_steps": 54070, "total_steps": 61300, "loss": 0.3275, "lr": 2.089564129778121e-06, "epoch": 8.820554649265905, "percentage": 88.21, "elapsed_time": "7:21:40", "remaining_time": "0:59:03", "throughput": 4403.46, "total_tokens": 116693936} {"current_steps": 54075, "total_steps": 61300, "loss": 0.3294, "lr": 2.0867162725669077e-06, "epoch": 8.82137030995106, "percentage": 88.21, "elapsed_time": "7:21:42", "remaining_time": "0:59:01", "throughput": 4403.49, "total_tokens": 116703856} {"current_steps": 54080, "total_steps": 61300, "loss": 0.3381, "lr": 2.0838702728227356e-06, "epoch": 8.822185970636216, "percentage": 88.22, "elapsed_time": "7:21:44", "remaining_time": "0:58:58", "throughput": 4403.52, "total_tokens": 116713136} {"current_steps": 54085, "total_steps": 61300, "loss": 0.3412, "lr": 2.081026130776309e-06, "epoch": 8.82300163132137, "percentage": 88.23, "elapsed_time": "7:21:46", "remaining_time": "0:58:56", "throughput": 4403.56, "total_tokens": 116723696} {"current_steps": 54090, "total_steps": 61300, "loss": 0.361, "lr": 2.078183846658199e-06, "epoch": 8.823817292006526, "percentage": 88.24, "elapsed_time": "7:21:49", "remaining_time": "0:58:53", "throughput": 4403.59, "total_tokens": 116735280} {"current_steps": 54095, "total_steps": 61300, "loss": 0.3219, "lr": 2.075343420698811e-06, "epoch": 8.82463295269168, "percentage": 88.25, "elapsed_time": "7:21:51", "remaining_time": "0:58:51", "throughput": 4403.62, "total_tokens": 116746416} {"current_steps": 54100, "total_steps": 61300, "loss": 0.3352, "lr": 2.0725048531284015e-06, "epoch": 8.825448613376835, "percentage": 88.25, "elapsed_time": "7:21:53", "remaining_time": "0:58:48", "throughput": 4403.66, "total_tokens": 116757232} {"current_steps": 54105, "total_steps": 61300, "loss": 0.3228, "lr": 2.0696681441770836e-06, "epoch": 8.826264274061991, "percentage": 88.26, "elapsed_time": "7:21:55", "remaining_time": "0:58:46", "throughput": 4403.69, "total_tokens": 116768304} {"current_steps": 54110, "total_steps": 61300, "loss": 0.3183, "lr": 2.066833294074813e-06, "epoch": 8.827079934747145, "percentage": 88.27, "elapsed_time": "7:21:58", "remaining_time": "0:58:43", "throughput": 4403.73, "total_tokens": 116779216} {"current_steps": 54115, "total_steps": 61300, "loss": 0.338, "lr": 2.064000303051397e-06, "epoch": 8.8278955954323, "percentage": 88.28, "elapsed_time": "7:22:00", "remaining_time": "0:58:41", "throughput": 4403.76, "total_tokens": 116790160} {"current_steps": 54120, "total_steps": 61300, "loss": 0.3194, "lr": 2.061169171336494e-06, "epoch": 8.828711256117455, "percentage": 88.29, "elapsed_time": "7:22:02", "remaining_time": "0:58:38", "throughput": 4403.8, "total_tokens": 116801936} {"current_steps": 54125, "total_steps": 61300, "loss": 0.3011, "lr": 2.058339899159606e-06, "epoch": 8.82952691680261, "percentage": 88.3, "elapsed_time": "7:22:05", "remaining_time": "0:58:36", "throughput": 4403.83, "total_tokens": 116812816} {"current_steps": 54130, "total_steps": 61300, "loss": 0.338, "lr": 2.0555124867500915e-06, "epoch": 8.830342577487766, "percentage": 88.3, "elapsed_time": "7:22:07", "remaining_time": "0:58:33", "throughput": 4403.86, "total_tokens": 116821840} {"current_steps": 54135, "total_steps": 61300, "loss": 0.3341, "lr": 2.05268693433715e-06, "epoch": 8.83115823817292, "percentage": 88.31, "elapsed_time": "7:22:09", "remaining_time": "0:58:31", "throughput": 4403.9, "total_tokens": 116832912} {"current_steps": 54140, "total_steps": 61300, "loss": 0.3514, "lr": 2.049863242149844e-06, "epoch": 8.831973898858076, "percentage": 88.32, "elapsed_time": "7:22:11", "remaining_time": "0:58:28", "throughput": 4403.94, "total_tokens": 116842896} {"current_steps": 54145, "total_steps": 61300, "loss": 0.3486, "lr": 2.0470414104170694e-06, "epoch": 8.83278955954323, "percentage": 88.33, "elapsed_time": "7:22:13", "remaining_time": "0:58:26", "throughput": 4403.97, "total_tokens": 116853744} {"current_steps": 54150, "total_steps": 61300, "loss": 0.3054, "lr": 2.044221439367583e-06, "epoch": 8.833605220228385, "percentage": 88.34, "elapsed_time": "7:22:15", "remaining_time": "0:58:23", "throughput": 4404.0, "total_tokens": 116863824} {"current_steps": 54155, "total_steps": 61300, "loss": 0.3243, "lr": 2.0414033292299823e-06, "epoch": 8.83442088091354, "percentage": 88.34, "elapsed_time": "7:22:18", "remaining_time": "0:58:21", "throughput": 4404.04, "total_tokens": 116875056} {"current_steps": 54160, "total_steps": 61300, "loss": 0.3217, "lr": 2.0385870802327176e-06, "epoch": 8.835236541598695, "percentage": 88.35, "elapsed_time": "7:22:20", "remaining_time": "0:58:18", "throughput": 4404.09, "total_tokens": 116886768} {"current_steps": 54165, "total_steps": 61300, "loss": 0.3298, "lr": 2.0357726926040875e-06, "epoch": 8.83605220228385, "percentage": 88.36, "elapsed_time": "7:22:22", "remaining_time": "0:58:16", "throughput": 4404.12, "total_tokens": 116898032} {"current_steps": 54170, "total_steps": 61300, "loss": 0.2921, "lr": 2.0329601665722453e-06, "epoch": 8.836867862969005, "percentage": 88.37, "elapsed_time": "7:22:25", "remaining_time": "0:58:13", "throughput": 4404.15, "total_tokens": 116909008} {"current_steps": 54175, "total_steps": 61300, "loss": 0.2919, "lr": 2.030149502365186e-06, "epoch": 8.83768352365416, "percentage": 88.38, "elapsed_time": "7:22:27", "remaining_time": "0:58:11", "throughput": 4404.19, "total_tokens": 116920464} {"current_steps": 54180, "total_steps": 61300, "loss": 0.3477, "lr": 2.027340700210753e-06, "epoch": 8.838499184339314, "percentage": 88.38, "elapsed_time": "7:22:29", "remaining_time": "0:58:09", "throughput": 4404.22, "total_tokens": 116931568} {"current_steps": 54185, "total_steps": 61300, "loss": 0.3148, "lr": 2.0245337603366472e-06, "epoch": 8.83931484502447, "percentage": 88.39, "elapsed_time": "7:22:32", "remaining_time": "0:58:06", "throughput": 4404.26, "total_tokens": 116943312} {"current_steps": 54190, "total_steps": 61300, "loss": 0.3447, "lr": 2.0217286829704115e-06, "epoch": 8.840130505709626, "percentage": 88.4, "elapsed_time": "7:22:34", "remaining_time": "0:58:04", "throughput": 4404.29, "total_tokens": 116954480} {"current_steps": 54195, "total_steps": 61300, "loss": 0.3201, "lr": 2.018925468339436e-06, "epoch": 8.84094616639478, "percentage": 88.41, "elapsed_time": "7:22:36", "remaining_time": "0:58:01", "throughput": 4404.32, "total_tokens": 116964880} {"current_steps": 54200, "total_steps": 61300, "loss": 0.3522, "lr": 2.01612411667097e-06, "epoch": 8.841761827079935, "percentage": 88.42, "elapsed_time": "7:22:38", "remaining_time": "0:57:59", "throughput": 4404.35, "total_tokens": 116974896} {"current_steps": 54205, "total_steps": 61300, "loss": 0.3129, "lr": 2.013324628192101e-06, "epoch": 8.84257748776509, "percentage": 88.43, "elapsed_time": "7:22:41", "remaining_time": "0:57:56", "throughput": 4404.39, "total_tokens": 116985072} {"current_steps": 54210, "total_steps": 61300, "loss": 0.3513, "lr": 2.0105270031297725e-06, "epoch": 8.843393148450245, "percentage": 88.43, "elapsed_time": "7:22:43", "remaining_time": "0:57:54", "throughput": 4404.42, "total_tokens": 116995856} {"current_steps": 54215, "total_steps": 61300, "loss": 0.3392, "lr": 2.0077312417107695e-06, "epoch": 8.844208809135399, "percentage": 88.44, "elapsed_time": "7:22:45", "remaining_time": "0:57:51", "throughput": 4404.46, "total_tokens": 117007152} {"current_steps": 54220, "total_steps": 61300, "loss": 0.3031, "lr": 2.0049373441617363e-06, "epoch": 8.845024469820554, "percentage": 88.45, "elapsed_time": "7:22:47", "remaining_time": "0:57:49", "throughput": 4404.49, "total_tokens": 117017040} {"current_steps": 54225, "total_steps": 61300, "loss": 0.3117, "lr": 2.002145310709155e-06, "epoch": 8.84584013050571, "percentage": 88.46, "elapsed_time": "7:22:50", "remaining_time": "0:57:46", "throughput": 4404.52, "total_tokens": 117028304} {"current_steps": 54230, "total_steps": 61300, "loss": 0.3457, "lr": 1.9993551415793647e-06, "epoch": 8.846655791190864, "percentage": 88.47, "elapsed_time": "7:22:52", "remaining_time": "0:57:44", "throughput": 4404.56, "total_tokens": 117039120} {"current_steps": 54235, "total_steps": 61300, "loss": 0.3007, "lr": 1.9965668369985507e-06, "epoch": 8.84747145187602, "percentage": 88.47, "elapsed_time": "7:22:54", "remaining_time": "0:57:41", "throughput": 4404.59, "total_tokens": 117050032} {"current_steps": 54240, "total_steps": 61300, "loss": 0.3154, "lr": 1.993780397192749e-06, "epoch": 8.848287112561174, "percentage": 88.48, "elapsed_time": "7:22:56", "remaining_time": "0:57:39", "throughput": 4404.62, "total_tokens": 117058448} {"current_steps": 54245, "total_steps": 61300, "loss": 0.31, "lr": 1.9909958223878424e-06, "epoch": 8.84910277324633, "percentage": 88.49, "elapsed_time": "7:22:58", "remaining_time": "0:57:36", "throughput": 4404.65, "total_tokens": 117068880} {"current_steps": 54250, "total_steps": 61300, "loss": 0.3542, "lr": 1.988213112809559e-06, "epoch": 8.849918433931485, "percentage": 88.5, "elapsed_time": "7:23:00", "remaining_time": "0:57:34", "throughput": 4404.69, "total_tokens": 117079312} {"current_steps": 54255, "total_steps": 61300, "loss": 0.314, "lr": 1.9854322686834766e-06, "epoch": 8.850734094616639, "percentage": 88.51, "elapsed_time": "7:23:02", "remaining_time": "0:57:31", "throughput": 4404.72, "total_tokens": 117089776} {"current_steps": 54260, "total_steps": 61300, "loss": 0.3629, "lr": 1.982653290235034e-06, "epoch": 8.851549755301795, "percentage": 88.52, "elapsed_time": "7:23:04", "remaining_time": "0:57:29", "throughput": 4404.75, "total_tokens": 117100304} {"current_steps": 54265, "total_steps": 61300, "loss": 0.324, "lr": 1.979876177689505e-06, "epoch": 8.852365415986949, "percentage": 88.52, "elapsed_time": "7:23:07", "remaining_time": "0:57:26", "throughput": 4404.78, "total_tokens": 117110064} {"current_steps": 54270, "total_steps": 61300, "loss": 0.3431, "lr": 1.9771009312720164e-06, "epoch": 8.853181076672104, "percentage": 88.53, "elapsed_time": "7:23:09", "remaining_time": "0:57:24", "throughput": 4404.82, "total_tokens": 117121872} {"current_steps": 54275, "total_steps": 61300, "loss": 0.3707, "lr": 1.9743275512075417e-06, "epoch": 8.85399673735726, "percentage": 88.54, "elapsed_time": "7:23:11", "remaining_time": "0:57:21", "throughput": 4404.86, "total_tokens": 117133040} {"current_steps": 54280, "total_steps": 61300, "loss": 0.3688, "lr": 1.9715560377209093e-06, "epoch": 8.854812398042414, "percentage": 88.55, "elapsed_time": "7:23:14", "remaining_time": "0:57:19", "throughput": 4404.9, "total_tokens": 117145488} {"current_steps": 54285, "total_steps": 61300, "loss": 0.3491, "lr": 1.9687863910367866e-06, "epoch": 8.85562805872757, "percentage": 88.56, "elapsed_time": "7:23:16", "remaining_time": "0:57:16", "throughput": 4404.94, "total_tokens": 117156464} {"current_steps": 54290, "total_steps": 61300, "loss": 0.3128, "lr": 1.9660186113796996e-06, "epoch": 8.856443719412724, "percentage": 88.56, "elapsed_time": "7:23:18", "remaining_time": "0:57:14", "throughput": 4404.97, "total_tokens": 117166128} {"current_steps": 54295, "total_steps": 61300, "loss": 0.3407, "lr": 1.963252698974019e-06, "epoch": 8.85725938009788, "percentage": 88.57, "elapsed_time": "7:23:20", "remaining_time": "0:57:11", "throughput": 4405.01, "total_tokens": 117176272} {"current_steps": 54300, "total_steps": 61300, "loss": 0.3428, "lr": 1.96048865404396e-06, "epoch": 8.858075040783035, "percentage": 88.58, "elapsed_time": "7:23:23", "remaining_time": "0:57:09", "throughput": 4405.04, "total_tokens": 117187440} {"current_steps": 54305, "total_steps": 61300, "loss": 0.3006, "lr": 1.9577264768135927e-06, "epoch": 8.858890701468189, "percentage": 88.59, "elapsed_time": "7:23:25", "remaining_time": "0:57:07", "throughput": 4405.08, "total_tokens": 117198416} {"current_steps": 54310, "total_steps": 61300, "loss": 0.3321, "lr": 1.9549661675068303e-06, "epoch": 8.859706362153345, "percentage": 88.6, "elapsed_time": "7:23:27", "remaining_time": "0:57:04", "throughput": 4405.12, "total_tokens": 117209104} {"current_steps": 54315, "total_steps": 61300, "loss": 0.3397, "lr": 1.9522077263474436e-06, "epoch": 8.860522022838499, "percentage": 88.61, "elapsed_time": "7:23:29", "remaining_time": "0:57:02", "throughput": 4405.16, "total_tokens": 117220592} {"current_steps": 54320, "total_steps": 61300, "loss": 0.3574, "lr": 1.94945115355904e-06, "epoch": 8.861337683523654, "percentage": 88.61, "elapsed_time": "7:23:32", "remaining_time": "0:56:59", "throughput": 4405.19, "total_tokens": 117231280} {"current_steps": 54325, "total_steps": 61300, "loss": 0.3494, "lr": 1.946696449365082e-06, "epoch": 8.86215334420881, "percentage": 88.62, "elapsed_time": "7:23:34", "remaining_time": "0:56:57", "throughput": 4405.23, "total_tokens": 117243216} {"current_steps": 54330, "total_steps": 61300, "loss": 0.2947, "lr": 1.943943613988883e-06, "epoch": 8.862969004893964, "percentage": 88.63, "elapsed_time": "7:23:36", "remaining_time": "0:56:54", "throughput": 4405.26, "total_tokens": 117252976} {"current_steps": 54335, "total_steps": 61300, "loss": 0.3485, "lr": 1.9411926476535976e-06, "epoch": 8.86378466557912, "percentage": 88.64, "elapsed_time": "7:23:38", "remaining_time": "0:56:52", "throughput": 4405.3, "total_tokens": 117264016} {"current_steps": 54340, "total_steps": 61300, "loss": 0.3371, "lr": 1.938443550582239e-06, "epoch": 8.864600326264274, "percentage": 88.65, "elapsed_time": "7:23:41", "remaining_time": "0:56:49", "throughput": 4405.33, "total_tokens": 117274864} {"current_steps": 54345, "total_steps": 61300, "loss": 0.3642, "lr": 1.935696322997657e-06, "epoch": 8.86541598694943, "percentage": 88.65, "elapsed_time": "7:23:43", "remaining_time": "0:56:47", "throughput": 4405.36, "total_tokens": 117285552} {"current_steps": 54350, "total_steps": 61300, "loss": 0.3201, "lr": 1.932950965122554e-06, "epoch": 8.866231647634583, "percentage": 88.66, "elapsed_time": "7:23:45", "remaining_time": "0:56:44", "throughput": 4405.39, "total_tokens": 117295728} {"current_steps": 54355, "total_steps": 61300, "loss": 0.3318, "lr": 1.930207477179491e-06, "epoch": 8.867047308319739, "percentage": 88.67, "elapsed_time": "7:23:47", "remaining_time": "0:56:42", "throughput": 4405.43, "total_tokens": 117307408} {"current_steps": 54360, "total_steps": 61300, "loss": 0.2911, "lr": 1.9274658593908647e-06, "epoch": 8.867862969004895, "percentage": 88.68, "elapsed_time": "7:23:50", "remaining_time": "0:56:39", "throughput": 4405.47, "total_tokens": 117318832} {"current_steps": 54365, "total_steps": 61300, "loss": 0.3216, "lr": 1.9247261119789252e-06, "epoch": 8.868678629690049, "percentage": 88.69, "elapsed_time": "7:23:52", "remaining_time": "0:56:37", "throughput": 4405.5, "total_tokens": 117329712} {"current_steps": 54370, "total_steps": 61300, "loss": 0.3683, "lr": 1.9219882351657696e-06, "epoch": 8.869494290375204, "percentage": 88.69, "elapsed_time": "7:23:54", "remaining_time": "0:56:34", "throughput": 4405.53, "total_tokens": 117339728} {"current_steps": 54375, "total_steps": 61300, "loss": 0.3036, "lr": 1.9192522291733434e-06, "epoch": 8.870309951060358, "percentage": 88.7, "elapsed_time": "7:23:57", "remaining_time": "0:56:32", "throughput": 4405.56, "total_tokens": 117351408} {"current_steps": 54380, "total_steps": 61300, "loss": 0.3648, "lr": 1.9165180942234435e-06, "epoch": 8.871125611745514, "percentage": 88.71, "elapsed_time": "7:23:59", "remaining_time": "0:56:29", "throughput": 4405.6, "total_tokens": 117361904} {"current_steps": 54385, "total_steps": 61300, "loss": 0.3108, "lr": 1.913785830537712e-06, "epoch": 8.87194127243067, "percentage": 88.72, "elapsed_time": "7:24:01", "remaining_time": "0:56:27", "throughput": 4405.63, "total_tokens": 117371536} {"current_steps": 54390, "total_steps": 61300, "loss": 0.342, "lr": 1.911055438337639e-06, "epoch": 8.872756933115824, "percentage": 88.73, "elapsed_time": "7:24:03", "remaining_time": "0:56:24", "throughput": 4405.65, "total_tokens": 117379984} {"current_steps": 54395, "total_steps": 61300, "loss": 0.3028, "lr": 1.9083269178445636e-06, "epoch": 8.87357259380098, "percentage": 88.74, "elapsed_time": "7:24:05", "remaining_time": "0:56:22", "throughput": 4405.69, "total_tokens": 117390416} {"current_steps": 54400, "total_steps": 61300, "loss": 0.3337, "lr": 1.9056002692796698e-06, "epoch": 8.874388254486133, "percentage": 88.74, "elapsed_time": "7:24:07", "remaining_time": "0:56:19", "throughput": 4405.72, "total_tokens": 117401136} {"current_steps": 54405, "total_steps": 61300, "loss": 0.3167, "lr": 1.9028754928640008e-06, "epoch": 8.875203915171289, "percentage": 88.75, "elapsed_time": "7:24:09", "remaining_time": "0:56:17", "throughput": 4405.76, "total_tokens": 117411344} {"current_steps": 54410, "total_steps": 61300, "loss": 0.3305, "lr": 1.9001525888184407e-06, "epoch": 8.876019575856443, "percentage": 88.76, "elapsed_time": "7:24:11", "remaining_time": "0:56:14", "throughput": 4405.79, "total_tokens": 117421680} {"current_steps": 54415, "total_steps": 61300, "loss": 0.334, "lr": 1.8974315573637185e-06, "epoch": 8.876835236541599, "percentage": 88.77, "elapsed_time": "7:24:13", "remaining_time": "0:56:12", "throughput": 4405.82, "total_tokens": 117432048} {"current_steps": 54420, "total_steps": 61300, "loss": 0.3275, "lr": 1.8947123987204135e-06, "epoch": 8.877650897226754, "percentage": 88.78, "elapsed_time": "7:24:16", "remaining_time": "0:56:10", "throughput": 4405.86, "total_tokens": 117444080} {"current_steps": 54425, "total_steps": 61300, "loss": 0.2918, "lr": 1.8919951131089602e-06, "epoch": 8.878466557911908, "percentage": 88.78, "elapsed_time": "7:24:18", "remaining_time": "0:56:07", "throughput": 4405.89, "total_tokens": 117454864} {"current_steps": 54430, "total_steps": 61300, "loss": 0.3258, "lr": 1.88927970074963e-06, "epoch": 8.879282218597064, "percentage": 88.79, "elapsed_time": "7:24:20", "remaining_time": "0:56:05", "throughput": 4405.93, "total_tokens": 117464944} {"current_steps": 54435, "total_steps": 61300, "loss": 0.336, "lr": 1.8865661618625491e-06, "epoch": 8.880097879282218, "percentage": 88.8, "elapsed_time": "7:24:22", "remaining_time": "0:56:02", "throughput": 4405.96, "total_tokens": 117475344} {"current_steps": 54440, "total_steps": 61300, "loss": 0.3433, "lr": 1.883854496667692e-06, "epoch": 8.880913539967374, "percentage": 88.81, "elapsed_time": "7:24:25", "remaining_time": "0:56:00", "throughput": 4405.99, "total_tokens": 117486288} {"current_steps": 54445, "total_steps": 61300, "loss": 0.3136, "lr": 1.8811447053848796e-06, "epoch": 8.88172920065253, "percentage": 88.82, "elapsed_time": "7:24:27", "remaining_time": "0:55:57", "throughput": 4406.02, "total_tokens": 117496432} {"current_steps": 54450, "total_steps": 61300, "loss": 0.3184, "lr": 1.878436788233781e-06, "epoch": 8.882544861337683, "percentage": 88.83, "elapsed_time": "7:24:29", "remaining_time": "0:55:55", "throughput": 4406.06, "total_tokens": 117506960} {"current_steps": 54455, "total_steps": 61300, "loss": 0.3446, "lr": 1.8757307454339095e-06, "epoch": 8.883360522022839, "percentage": 88.83, "elapsed_time": "7:24:31", "remaining_time": "0:55:52", "throughput": 4406.09, "total_tokens": 117517360} {"current_steps": 54460, "total_steps": 61300, "loss": 0.3131, "lr": 1.8730265772046396e-06, "epoch": 8.884176182707993, "percentage": 88.84, "elapsed_time": "7:24:33", "remaining_time": "0:55:50", "throughput": 4406.13, "total_tokens": 117527376} {"current_steps": 54465, "total_steps": 61300, "loss": 0.3675, "lr": 1.8703242837651818e-06, "epoch": 8.884991843393149, "percentage": 88.85, "elapsed_time": "7:24:35", "remaining_time": "0:55:47", "throughput": 4406.17, "total_tokens": 117537104} {"current_steps": 54470, "total_steps": 61300, "loss": 0.3232, "lr": 1.8676238653345945e-06, "epoch": 8.885807504078304, "percentage": 88.86, "elapsed_time": "7:24:37", "remaining_time": "0:55:45", "throughput": 4406.2, "total_tokens": 117546896} {"current_steps": 54475, "total_steps": 61300, "loss": 0.31, "lr": 1.8649253221317914e-06, "epoch": 8.886623164763458, "percentage": 88.87, "elapsed_time": "7:24:39", "remaining_time": "0:55:42", "throughput": 4406.23, "total_tokens": 117557328} {"current_steps": 54480, "total_steps": 61300, "loss": 0.3343, "lr": 1.8622286543755252e-06, "epoch": 8.887438825448614, "percentage": 88.87, "elapsed_time": "7:24:41", "remaining_time": "0:55:40", "throughput": 4406.27, "total_tokens": 117567568} {"current_steps": 54485, "total_steps": 61300, "loss": 0.338, "lr": 1.8595338622844072e-06, "epoch": 8.888254486133768, "percentage": 88.88, "elapsed_time": "7:24:44", "remaining_time": "0:55:37", "throughput": 4406.3, "total_tokens": 117578032} {"current_steps": 54490, "total_steps": 61300, "loss": 0.3411, "lr": 1.8568409460768848e-06, "epoch": 8.889070146818923, "percentage": 88.89, "elapsed_time": "7:24:46", "remaining_time": "0:55:35", "throughput": 4406.33, "total_tokens": 117589456} {"current_steps": 54495, "total_steps": 61300, "loss": 0.3334, "lr": 1.8541499059712641e-06, "epoch": 8.88988580750408, "percentage": 88.9, "elapsed_time": "7:24:48", "remaining_time": "0:55:32", "throughput": 4406.37, "total_tokens": 117599952} {"current_steps": 54500, "total_steps": 61300, "loss": 0.3027, "lr": 1.8514607421856928e-06, "epoch": 8.890701468189233, "percentage": 88.91, "elapsed_time": "7:24:50", "remaining_time": "0:55:30", "throughput": 4406.4, "total_tokens": 117610288} {"current_steps": 54505, "total_steps": 61300, "loss": 0.3175, "lr": 1.8487734549381686e-06, "epoch": 8.891517128874389, "percentage": 88.92, "elapsed_time": "7:24:52", "remaining_time": "0:55:27", "throughput": 4406.43, "total_tokens": 117620528} {"current_steps": 54510, "total_steps": 61300, "loss": 0.3123, "lr": 1.8460880444465367e-06, "epoch": 8.892332789559543, "percentage": 88.92, "elapsed_time": "7:24:55", "remaining_time": "0:55:25", "throughput": 4406.46, "total_tokens": 117631984} {"current_steps": 54515, "total_steps": 61300, "loss": 0.3271, "lr": 1.843404510928487e-06, "epoch": 8.893148450244698, "percentage": 88.93, "elapsed_time": "7:24:57", "remaining_time": "0:55:22", "throughput": 4406.5, "total_tokens": 117642800} {"current_steps": 54520, "total_steps": 61300, "loss": 0.3119, "lr": 1.8407228546015648e-06, "epoch": 8.893964110929852, "percentage": 88.94, "elapsed_time": "7:25:00", "remaining_time": "0:55:20", "throughput": 4406.53, "total_tokens": 117654544} {"current_steps": 54525, "total_steps": 61300, "loss": 0.2999, "lr": 1.8380430756831574e-06, "epoch": 8.894779771615008, "percentage": 88.95, "elapsed_time": "7:25:02", "remaining_time": "0:55:17", "throughput": 4406.56, "total_tokens": 117664688} {"current_steps": 54530, "total_steps": 61300, "loss": 0.358, "lr": 1.835365174390502e-06, "epoch": 8.895595432300164, "percentage": 88.96, "elapsed_time": "7:25:04", "remaining_time": "0:55:15", "throughput": 4406.59, "total_tokens": 117675664} {"current_steps": 54535, "total_steps": 61300, "loss": 0.3116, "lr": 1.8326891509406808e-06, "epoch": 8.896411092985318, "percentage": 88.96, "elapsed_time": "7:25:06", "remaining_time": "0:55:12", "throughput": 4406.63, "total_tokens": 117685744} {"current_steps": 54540, "total_steps": 61300, "loss": 0.3118, "lr": 1.8300150055506254e-06, "epoch": 8.897226753670473, "percentage": 88.97, "elapsed_time": "7:25:08", "remaining_time": "0:55:10", "throughput": 4406.67, "total_tokens": 117697104} {"current_steps": 54545, "total_steps": 61300, "loss": 0.3252, "lr": 1.8273427384371127e-06, "epoch": 8.898042414355627, "percentage": 88.98, "elapsed_time": "7:25:11", "remaining_time": "0:55:07", "throughput": 4406.71, "total_tokens": 117708272} {"current_steps": 54550, "total_steps": 61300, "loss": 0.3432, "lr": 1.8246723498167806e-06, "epoch": 8.898858075040783, "percentage": 88.99, "elapsed_time": "7:25:13", "remaining_time": "0:55:05", "throughput": 4406.75, "total_tokens": 117718832} {"current_steps": 54555, "total_steps": 61300, "loss": 0.3259, "lr": 1.8220038399060973e-06, "epoch": 8.899673735725939, "percentage": 89.0, "elapsed_time": "7:25:15", "remaining_time": "0:55:03", "throughput": 4406.78, "total_tokens": 117729744} {"current_steps": 54560, "total_steps": 61300, "loss": 0.3342, "lr": 1.8193372089213872e-06, "epoch": 8.900489396411093, "percentage": 89.0, "elapsed_time": "7:25:17", "remaining_time": "0:55:00", "throughput": 4406.81, "total_tokens": 117741104} {"current_steps": 54565, "total_steps": 61300, "loss": 0.3199, "lr": 1.816672457078819e-06, "epoch": 8.901305057096248, "percentage": 89.01, "elapsed_time": "7:25:20", "remaining_time": "0:54:58", "throughput": 4406.84, "total_tokens": 117751280} {"current_steps": 54570, "total_steps": 61300, "loss": 0.3681, "lr": 1.8140095845944117e-06, "epoch": 8.902120717781402, "percentage": 89.02, "elapsed_time": "7:25:22", "remaining_time": "0:54:55", "throughput": 4406.87, "total_tokens": 117761200} {"current_steps": 54575, "total_steps": 61300, "loss": 0.3333, "lr": 1.811348591684031e-06, "epoch": 8.902936378466558, "percentage": 89.03, "elapsed_time": "7:25:24", "remaining_time": "0:54:53", "throughput": 4406.91, "total_tokens": 117771536} {"current_steps": 54580, "total_steps": 61300, "loss": 0.2965, "lr": 1.8086894785633969e-06, "epoch": 8.903752039151712, "percentage": 89.04, "elapsed_time": "7:25:26", "remaining_time": "0:54:50", "throughput": 4406.95, "total_tokens": 117781808} {"current_steps": 54585, "total_steps": 61300, "loss": 0.3194, "lr": 1.806032245448061e-06, "epoch": 8.904567699836868, "percentage": 89.05, "elapsed_time": "7:25:28", "remaining_time": "0:54:48", "throughput": 4406.98, "total_tokens": 117793296} {"current_steps": 54590, "total_steps": 61300, "loss": 0.3269, "lr": 1.8033768925534378e-06, "epoch": 8.905383360522023, "percentage": 89.05, "elapsed_time": "7:25:30", "remaining_time": "0:54:45", "throughput": 4407.01, "total_tokens": 117803568} {"current_steps": 54595, "total_steps": 61300, "loss": 0.3197, "lr": 1.8007234200947826e-06, "epoch": 8.906199021207177, "percentage": 89.06, "elapsed_time": "7:25:33", "remaining_time": "0:54:43", "throughput": 4407.04, "total_tokens": 117813648} {"current_steps": 54600, "total_steps": 61300, "loss": 0.2908, "lr": 1.7980718282871982e-06, "epoch": 8.907014681892333, "percentage": 89.07, "elapsed_time": "7:25:35", "remaining_time": "0:54:40", "throughput": 4407.07, "total_tokens": 117824816} {"current_steps": 54605, "total_steps": 61300, "loss": 0.3477, "lr": 1.7954221173456382e-06, "epoch": 8.907830342577487, "percentage": 89.08, "elapsed_time": "7:25:37", "remaining_time": "0:54:38", "throughput": 4407.1, "total_tokens": 117835312} {"current_steps": 54610, "total_steps": 61300, "loss": 0.3562, "lr": 1.7927742874848997e-06, "epoch": 8.908646003262643, "percentage": 89.09, "elapsed_time": "7:25:39", "remaining_time": "0:54:35", "throughput": 4407.13, "total_tokens": 117845616} {"current_steps": 54615, "total_steps": 61300, "loss": 0.3313, "lr": 1.7901283389196278e-06, "epoch": 8.909461663947798, "percentage": 89.09, "elapsed_time": "7:25:42", "remaining_time": "0:54:33", "throughput": 4407.16, "total_tokens": 117856656} {"current_steps": 54620, "total_steps": 61300, "loss": 0.3309, "lr": 1.7874842718643203e-06, "epoch": 8.910277324632952, "percentage": 89.1, "elapsed_time": "7:25:44", "remaining_time": "0:54:30", "throughput": 4407.2, "total_tokens": 117867056} {"current_steps": 54625, "total_steps": 61300, "loss": 0.2841, "lr": 1.7848420865333172e-06, "epoch": 8.911092985318108, "percentage": 89.11, "elapsed_time": "7:25:46", "remaining_time": "0:54:28", "throughput": 4407.23, "total_tokens": 117877552} {"current_steps": 54630, "total_steps": 61300, "loss": 0.3223, "lr": 1.782201783140805e-06, "epoch": 8.911908646003262, "percentage": 89.12, "elapsed_time": "7:25:48", "remaining_time": "0:54:25", "throughput": 4407.26, "total_tokens": 117888624} {"current_steps": 54635, "total_steps": 61300, "loss": 0.3422, "lr": 1.779563361900824e-06, "epoch": 8.912724306688418, "percentage": 89.13, "elapsed_time": "7:25:50", "remaining_time": "0:54:23", "throughput": 4407.29, "total_tokens": 117897520} {"current_steps": 54640, "total_steps": 61300, "loss": 0.3161, "lr": 1.7769268230272557e-06, "epoch": 8.913539967373573, "percentage": 89.14, "elapsed_time": "7:25:52", "remaining_time": "0:54:20", "throughput": 4407.33, "total_tokens": 117907920} {"current_steps": 54645, "total_steps": 61300, "loss": 0.3586, "lr": 1.774292166733832e-06, "epoch": 8.914355628058727, "percentage": 89.14, "elapsed_time": "7:25:55", "remaining_time": "0:54:18", "throughput": 4407.36, "total_tokens": 117919088} {"current_steps": 54650, "total_steps": 61300, "loss": 0.309, "lr": 1.7716593932341319e-06, "epoch": 8.915171288743883, "percentage": 89.15, "elapsed_time": "7:25:57", "remaining_time": "0:54:15", "throughput": 4407.39, "total_tokens": 117928848} {"current_steps": 54655, "total_steps": 61300, "loss": 0.3476, "lr": 1.7690285027415792e-06, "epoch": 8.915986949429037, "percentage": 89.16, "elapsed_time": "7:25:59", "remaining_time": "0:54:13", "throughput": 4407.43, "total_tokens": 117939984} {"current_steps": 54660, "total_steps": 61300, "loss": 0.3207, "lr": 1.7663994954694508e-06, "epoch": 8.916802610114193, "percentage": 89.17, "elapsed_time": "7:26:02", "remaining_time": "0:54:11", "throughput": 4407.47, "total_tokens": 117952784} {"current_steps": 54665, "total_steps": 61300, "loss": 0.3211, "lr": 1.7637723716308646e-06, "epoch": 8.917618270799348, "percentage": 89.18, "elapsed_time": "7:26:04", "remaining_time": "0:54:08", "throughput": 4407.51, "total_tokens": 117963504} {"current_steps": 54670, "total_steps": 61300, "loss": 0.3461, "lr": 1.7611471314387867e-06, "epoch": 8.918433931484502, "percentage": 89.18, "elapsed_time": "7:26:06", "remaining_time": "0:54:06", "throughput": 4407.53, "total_tokens": 117973808} {"current_steps": 54675, "total_steps": 61300, "loss": 0.3178, "lr": 1.7585237751060357e-06, "epoch": 8.919249592169658, "percentage": 89.19, "elapsed_time": "7:26:08", "remaining_time": "0:54:03", "throughput": 4407.57, "total_tokens": 117984464} {"current_steps": 54680, "total_steps": 61300, "loss": 0.3273, "lr": 1.7559023028452748e-06, "epoch": 8.920065252854812, "percentage": 89.2, "elapsed_time": "7:26:10", "remaining_time": "0:54:01", "throughput": 4407.6, "total_tokens": 117994928} {"current_steps": 54685, "total_steps": 61300, "loss": 0.3611, "lr": 1.7532827148690145e-06, "epoch": 8.920880913539968, "percentage": 89.21, "elapsed_time": "7:26:12", "remaining_time": "0:53:58", "throughput": 4407.63, "total_tokens": 118004304} {"current_steps": 54690, "total_steps": 61300, "loss": 0.3438, "lr": 1.75066501138961e-06, "epoch": 8.921696574225122, "percentage": 89.22, "elapsed_time": "7:26:14", "remaining_time": "0:53:56", "throughput": 4407.67, "total_tokens": 118015152} {"current_steps": 54695, "total_steps": 61300, "loss": 0.326, "lr": 1.7480491926192638e-06, "epoch": 8.922512234910277, "percentage": 89.23, "elapsed_time": "7:26:17", "remaining_time": "0:53:53", "throughput": 4407.71, "total_tokens": 118027344} {"current_steps": 54700, "total_steps": 61300, "loss": 0.3532, "lr": 1.7454352587700284e-06, "epoch": 8.923327895595433, "percentage": 89.23, "elapsed_time": "7:26:19", "remaining_time": "0:53:51", "throughput": 4407.74, "total_tokens": 118038672} {"current_steps": 54705, "total_steps": 61300, "loss": 0.3483, "lr": 1.7428232100538067e-06, "epoch": 8.924143556280587, "percentage": 89.24, "elapsed_time": "7:26:22", "remaining_time": "0:53:48", "throughput": 4407.77, "total_tokens": 118050576} {"current_steps": 54710, "total_steps": 61300, "loss": 0.3288, "lr": 1.7402130466823373e-06, "epoch": 8.924959216965743, "percentage": 89.25, "elapsed_time": "7:26:24", "remaining_time": "0:53:46", "throughput": 4407.81, "total_tokens": 118061520} {"current_steps": 54715, "total_steps": 61300, "loss": 0.3245, "lr": 1.7376047688672182e-06, "epoch": 8.925774877650896, "percentage": 89.26, "elapsed_time": "7:26:26", "remaining_time": "0:53:43", "throughput": 4407.84, "total_tokens": 118072080} {"current_steps": 54720, "total_steps": 61300, "loss": 0.3523, "lr": 1.734998376819888e-06, "epoch": 8.926590538336052, "percentage": 89.27, "elapsed_time": "7:26:28", "remaining_time": "0:53:41", "throughput": 4407.87, "total_tokens": 118082416} {"current_steps": 54725, "total_steps": 61300, "loss": 0.3052, "lr": 1.732393870751639e-06, "epoch": 8.927406199021208, "percentage": 89.27, "elapsed_time": "7:26:31", "remaining_time": "0:53:38", "throughput": 4407.9, "total_tokens": 118092880} {"current_steps": 54730, "total_steps": 61300, "loss": 0.3483, "lr": 1.729791250873597e-06, "epoch": 8.928221859706362, "percentage": 89.28, "elapsed_time": "7:26:33", "remaining_time": "0:53:36", "throughput": 4407.94, "total_tokens": 118105136} {"current_steps": 54735, "total_steps": 61300, "loss": 0.33, "lr": 1.7271905173967513e-06, "epoch": 8.929037520391518, "percentage": 89.29, "elapsed_time": "7:26:35", "remaining_time": "0:53:33", "throughput": 4407.97, "total_tokens": 118114736} {"current_steps": 54740, "total_steps": 61300, "loss": 0.3431, "lr": 1.7245916705319276e-06, "epoch": 8.929853181076671, "percentage": 89.3, "elapsed_time": "7:26:38", "remaining_time": "0:53:31", "throughput": 4408.01, "total_tokens": 118126064} {"current_steps": 54745, "total_steps": 61300, "loss": 0.3109, "lr": 1.7219947104897994e-06, "epoch": 8.930668841761827, "percentage": 89.31, "elapsed_time": "7:26:40", "remaining_time": "0:53:29", "throughput": 4408.05, "total_tokens": 118137456} {"current_steps": 54750, "total_steps": 61300, "loss": 0.3221, "lr": 1.7193996374808924e-06, "epoch": 8.931484502446983, "percentage": 89.31, "elapsed_time": "7:26:42", "remaining_time": "0:53:26", "throughput": 4408.08, "total_tokens": 118147376} {"current_steps": 54755, "total_steps": 61300, "loss": 0.3285, "lr": 1.7168064517155747e-06, "epoch": 8.932300163132137, "percentage": 89.32, "elapsed_time": "7:26:44", "remaining_time": "0:53:24", "throughput": 4408.12, "total_tokens": 118158096} {"current_steps": 54760, "total_steps": 61300, "loss": 0.3392, "lr": 1.714215153404064e-06, "epoch": 8.933115823817293, "percentage": 89.33, "elapsed_time": "7:26:46", "remaining_time": "0:53:21", "throughput": 4408.15, "total_tokens": 118168688} {"current_steps": 54765, "total_steps": 61300, "loss": 0.3475, "lr": 1.7116257427564259e-06, "epoch": 8.933931484502446, "percentage": 89.34, "elapsed_time": "7:26:49", "remaining_time": "0:53:19", "throughput": 4408.18, "total_tokens": 118179792} {"current_steps": 54770, "total_steps": 61300, "loss": 0.3285, "lr": 1.7090382199825672e-06, "epoch": 8.934747145187602, "percentage": 89.35, "elapsed_time": "7:26:51", "remaining_time": "0:53:16", "throughput": 4408.22, "total_tokens": 118190736} {"current_steps": 54775, "total_steps": 61300, "loss": 0.3368, "lr": 1.7064525852922424e-06, "epoch": 8.935562805872756, "percentage": 89.36, "elapsed_time": "7:26:53", "remaining_time": "0:53:14", "throughput": 4408.26, "total_tokens": 118201584} {"current_steps": 54780, "total_steps": 61300, "loss": 0.3127, "lr": 1.7038688388950675e-06, "epoch": 8.936378466557912, "percentage": 89.36, "elapsed_time": "7:26:55", "remaining_time": "0:53:11", "throughput": 4408.29, "total_tokens": 118212624} {"current_steps": 54785, "total_steps": 61300, "loss": 0.3069, "lr": 1.7012869810004856e-06, "epoch": 8.937194127243067, "percentage": 89.37, "elapsed_time": "7:26:58", "remaining_time": "0:53:09", "throughput": 4408.32, "total_tokens": 118222800} {"current_steps": 54790, "total_steps": 61300, "loss": 0.3343, "lr": 1.698707011817799e-06, "epoch": 8.938009787928221, "percentage": 89.38, "elapsed_time": "7:27:00", "remaining_time": "0:53:06", "throughput": 4408.35, "total_tokens": 118232592} {"current_steps": 54795, "total_steps": 61300, "loss": 0.3329, "lr": 1.6961289315561512e-06, "epoch": 8.938825448613377, "percentage": 89.39, "elapsed_time": "7:27:02", "remaining_time": "0:53:04", "throughput": 4408.39, "total_tokens": 118244464} {"current_steps": 54800, "total_steps": 61300, "loss": 0.3044, "lr": 1.6935527404245366e-06, "epoch": 8.939641109298531, "percentage": 89.4, "elapsed_time": "7:27:04", "remaining_time": "0:53:01", "throughput": 4408.42, "total_tokens": 118253552} {"current_steps": 54805, "total_steps": 61300, "loss": 0.3054, "lr": 1.6909784386317906e-06, "epoch": 8.940456769983687, "percentage": 89.4, "elapsed_time": "7:27:06", "remaining_time": "0:52:59", "throughput": 4408.45, "total_tokens": 118263824} {"current_steps": 54810, "total_steps": 61300, "loss": 0.3169, "lr": 1.688406026386602e-06, "epoch": 8.941272430668842, "percentage": 89.41, "elapsed_time": "7:27:08", "remaining_time": "0:52:56", "throughput": 4408.49, "total_tokens": 118275216} {"current_steps": 54815, "total_steps": 61300, "loss": 0.354, "lr": 1.6858355038975038e-06, "epoch": 8.942088091353996, "percentage": 89.42, "elapsed_time": "7:27:11", "remaining_time": "0:52:54", "throughput": 4408.52, "total_tokens": 118286224} {"current_steps": 54820, "total_steps": 61300, "loss": 0.3251, "lr": 1.6832668713728711e-06, "epoch": 8.942903752039152, "percentage": 89.43, "elapsed_time": "7:27:13", "remaining_time": "0:52:51", "throughput": 4408.55, "total_tokens": 118296240} {"current_steps": 54825, "total_steps": 61300, "loss": 0.3116, "lr": 1.6807001290209374e-06, "epoch": 8.943719412724306, "percentage": 89.44, "elapsed_time": "7:27:15", "remaining_time": "0:52:49", "throughput": 4408.59, "total_tokens": 118305680} {"current_steps": 54830, "total_steps": 61300, "loss": 0.3405, "lr": 1.6781352770497694e-06, "epoch": 8.944535073409462, "percentage": 89.45, "elapsed_time": "7:27:17", "remaining_time": "0:52:46", "throughput": 4408.62, "total_tokens": 118316880} {"current_steps": 54835, "total_steps": 61300, "loss": 0.3589, "lr": 1.6755723156672925e-06, "epoch": 8.945350734094617, "percentage": 89.45, "elapsed_time": "7:27:19", "remaining_time": "0:52:44", "throughput": 4408.66, "total_tokens": 118328304} {"current_steps": 54840, "total_steps": 61300, "loss": 0.3525, "lr": 1.6730112450812685e-06, "epoch": 8.946166394779771, "percentage": 89.46, "elapsed_time": "7:27:22", "remaining_time": "0:52:41", "throughput": 4408.69, "total_tokens": 118339728} {"current_steps": 54845, "total_steps": 61300, "loss": 0.3448, "lr": 1.6704520654993145e-06, "epoch": 8.946982055464927, "percentage": 89.47, "elapsed_time": "7:27:24", "remaining_time": "0:52:39", "throughput": 4408.72, "total_tokens": 118349872} {"current_steps": 54850, "total_steps": 61300, "loss": 0.3237, "lr": 1.6678947771288866e-06, "epoch": 8.947797716150081, "percentage": 89.48, "elapsed_time": "7:27:26", "remaining_time": "0:52:36", "throughput": 4408.75, "total_tokens": 118359888} {"current_steps": 54855, "total_steps": 61300, "loss": 0.339, "lr": 1.665339380177297e-06, "epoch": 8.948613376835237, "percentage": 89.49, "elapsed_time": "7:27:28", "remaining_time": "0:52:34", "throughput": 4408.78, "total_tokens": 118370544} {"current_steps": 54860, "total_steps": 61300, "loss": 0.3442, "lr": 1.6627858748516912e-06, "epoch": 8.949429037520392, "percentage": 89.49, "elapsed_time": "7:27:31", "remaining_time": "0:52:32", "throughput": 4408.82, "total_tokens": 118381584} {"current_steps": 54865, "total_steps": 61300, "loss": 0.34, "lr": 1.6602342613590754e-06, "epoch": 8.950244698205546, "percentage": 89.5, "elapsed_time": "7:27:33", "remaining_time": "0:52:29", "throughput": 4408.85, "total_tokens": 118392624} {"current_steps": 54870, "total_steps": 61300, "loss": 0.2918, "lr": 1.6576845399062985e-06, "epoch": 8.951060358890702, "percentage": 89.51, "elapsed_time": "7:27:35", "remaining_time": "0:52:27", "throughput": 4408.88, "total_tokens": 118402768} {"current_steps": 54875, "total_steps": 61300, "loss": 0.3086, "lr": 1.6551367107000503e-06, "epoch": 8.951876019575856, "percentage": 89.52, "elapsed_time": "7:27:37", "remaining_time": "0:52:24", "throughput": 4408.92, "total_tokens": 118413584} {"current_steps": 54880, "total_steps": 61300, "loss": 0.3234, "lr": 1.6525907739468689e-06, "epoch": 8.952691680261012, "percentage": 89.53, "elapsed_time": "7:27:39", "remaining_time": "0:52:22", "throughput": 4408.95, "total_tokens": 118424400} {"current_steps": 54885, "total_steps": 61300, "loss": 0.3309, "lr": 1.6500467298531414e-06, "epoch": 8.953507340946166, "percentage": 89.54, "elapsed_time": "7:27:42", "remaining_time": "0:52:19", "throughput": 4408.99, "total_tokens": 118435696} {"current_steps": 54890, "total_steps": 61300, "loss": 0.3593, "lr": 1.6475045786251059e-06, "epoch": 8.954323001631321, "percentage": 89.54, "elapsed_time": "7:27:44", "remaining_time": "0:52:17", "throughput": 4409.02, "total_tokens": 118446544} {"current_steps": 54895, "total_steps": 61300, "loss": 0.3529, "lr": 1.6449643204688364e-06, "epoch": 8.955138662316477, "percentage": 89.55, "elapsed_time": "7:27:46", "remaining_time": "0:52:14", "throughput": 4409.06, "total_tokens": 118457616} {"current_steps": 54900, "total_steps": 61300, "loss": 0.3018, "lr": 1.6424259555902627e-06, "epoch": 8.955954323001631, "percentage": 89.56, "elapsed_time": "7:27:49", "remaining_time": "0:52:12", "throughput": 4409.09, "total_tokens": 118468816} {"current_steps": 54905, "total_steps": 61300, "loss": 0.3382, "lr": 1.6398894841951561e-06, "epoch": 8.956769983686787, "percentage": 89.57, "elapsed_time": "7:27:51", "remaining_time": "0:52:09", "throughput": 4409.13, "total_tokens": 118480176} {"current_steps": 54910, "total_steps": 61300, "loss": 0.3407, "lr": 1.6373549064891358e-06, "epoch": 8.95758564437194, "percentage": 89.58, "elapsed_time": "7:27:53", "remaining_time": "0:52:07", "throughput": 4409.15, "total_tokens": 118491024} {"current_steps": 54915, "total_steps": 61300, "loss": 0.3487, "lr": 1.6348222226776705e-06, "epoch": 8.958401305057096, "percentage": 89.58, "elapsed_time": "7:27:56", "remaining_time": "0:52:04", "throughput": 4409.19, "total_tokens": 118502096} {"current_steps": 54920, "total_steps": 61300, "loss": 0.3425, "lr": 1.6322914329660655e-06, "epoch": 8.959216965742252, "percentage": 89.59, "elapsed_time": "7:27:58", "remaining_time": "0:52:02", "throughput": 4409.22, "total_tokens": 118512464} {"current_steps": 54925, "total_steps": 61300, "loss": 0.3195, "lr": 1.629762537559487e-06, "epoch": 8.960032626427406, "percentage": 89.6, "elapsed_time": "7:28:00", "remaining_time": "0:51:59", "throughput": 4409.26, "total_tokens": 118523728} {"current_steps": 54930, "total_steps": 61300, "loss": 0.3232, "lr": 1.6272355366629327e-06, "epoch": 8.960848287112562, "percentage": 89.61, "elapsed_time": "7:28:02", "remaining_time": "0:51:57", "throughput": 4409.29, "total_tokens": 118533680} {"current_steps": 54935, "total_steps": 61300, "loss": 0.3283, "lr": 1.6247104304812604e-06, "epoch": 8.961663947797716, "percentage": 89.62, "elapsed_time": "7:28:04", "remaining_time": "0:51:54", "throughput": 4409.32, "total_tokens": 118544176} {"current_steps": 54940, "total_steps": 61300, "loss": 0.33, "lr": 1.6221872192191651e-06, "epoch": 8.962479608482871, "percentage": 89.62, "elapsed_time": "7:28:07", "remaining_time": "0:51:52", "throughput": 4409.35, "total_tokens": 118554384} {"current_steps": 54945, "total_steps": 61300, "loss": 0.3235, "lr": 1.6196659030811938e-06, "epoch": 8.963295269168025, "percentage": 89.63, "elapsed_time": "7:28:09", "remaining_time": "0:51:50", "throughput": 4409.39, "total_tokens": 118566064} {"current_steps": 54950, "total_steps": 61300, "loss": 0.3536, "lr": 1.6171464822717337e-06, "epoch": 8.964110929853181, "percentage": 89.64, "elapsed_time": "7:28:11", "remaining_time": "0:51:47", "throughput": 4409.42, "total_tokens": 118575952} {"current_steps": 54955, "total_steps": 61300, "loss": 0.3556, "lr": 1.6146289569950208e-06, "epoch": 8.964926590538337, "percentage": 89.65, "elapsed_time": "7:28:13", "remaining_time": "0:51:45", "throughput": 4409.46, "total_tokens": 118587408} {"current_steps": 54960, "total_steps": 61300, "loss": 0.3037, "lr": 1.612113327455142e-06, "epoch": 8.96574225122349, "percentage": 89.66, "elapsed_time": "7:28:16", "remaining_time": "0:51:42", "throughput": 4409.5, "total_tokens": 118598320} {"current_steps": 54965, "total_steps": 61300, "loss": 0.3192, "lr": 1.6095995938560288e-06, "epoch": 8.966557911908646, "percentage": 89.67, "elapsed_time": "7:28:18", "remaining_time": "0:51:40", "throughput": 4409.53, "total_tokens": 118609488} {"current_steps": 54970, "total_steps": 61300, "loss": 0.3089, "lr": 1.6070877564014514e-06, "epoch": 8.9673735725938, "percentage": 89.67, "elapsed_time": "7:28:20", "remaining_time": "0:51:37", "throughput": 4409.57, "total_tokens": 118621040} {"current_steps": 54975, "total_steps": 61300, "loss": 0.3141, "lr": 1.6045778152950357e-06, "epoch": 8.968189233278956, "percentage": 89.68, "elapsed_time": "7:28:23", "remaining_time": "0:51:35", "throughput": 4409.61, "total_tokens": 118632720} {"current_steps": 54980, "total_steps": 61300, "loss": 0.3615, "lr": 1.6020697707402472e-06, "epoch": 8.969004893964112, "percentage": 89.69, "elapsed_time": "7:28:25", "remaining_time": "0:51:32", "throughput": 4409.64, "total_tokens": 118643024} {"current_steps": 54985, "total_steps": 61300, "loss": 0.3392, "lr": 1.599563622940406e-06, "epoch": 8.969820554649266, "percentage": 89.7, "elapsed_time": "7:28:27", "remaining_time": "0:51:30", "throughput": 4409.68, "total_tokens": 118653712} {"current_steps": 54990, "total_steps": 61300, "loss": 0.3366, "lr": 1.5970593720986666e-06, "epoch": 8.970636215334421, "percentage": 89.71, "elapsed_time": "7:28:29", "remaining_time": "0:51:27", "throughput": 4409.71, "total_tokens": 118664400} {"current_steps": 54995, "total_steps": 61300, "loss": 0.3342, "lr": 1.5945570184180413e-06, "epoch": 8.971451876019575, "percentage": 89.71, "elapsed_time": "7:28:32", "remaining_time": "0:51:25", "throughput": 4409.75, "total_tokens": 118675504} {"current_steps": 55000, "total_steps": 61300, "loss": 0.3256, "lr": 1.5920565621013822e-06, "epoch": 8.97226753670473, "percentage": 89.72, "elapsed_time": "7:28:34", "remaining_time": "0:51:22", "throughput": 4409.78, "total_tokens": 118686192} {"current_steps": 55005, "total_steps": 61300, "loss": 0.3407, "lr": 1.5895580033513908e-06, "epoch": 8.973083197389887, "percentage": 89.73, "elapsed_time": "7:28:36", "remaining_time": "0:51:20", "throughput": 4409.82, "total_tokens": 118697776} {"current_steps": 55010, "total_steps": 61300, "loss": 0.3244, "lr": 1.5870613423706103e-06, "epoch": 8.97389885807504, "percentage": 89.74, "elapsed_time": "7:28:38", "remaining_time": "0:51:17", "throughput": 4409.87, "total_tokens": 118708720} {"current_steps": 55015, "total_steps": 61300, "loss": 0.3614, "lr": 1.5845665793614322e-06, "epoch": 8.974714518760196, "percentage": 89.75, "elapsed_time": "7:28:41", "remaining_time": "0:51:15", "throughput": 4409.9, "total_tokens": 118720112} {"current_steps": 55020, "total_steps": 61300, "loss": 0.2992, "lr": 1.5820737145260972e-06, "epoch": 8.97553017944535, "percentage": 89.76, "elapsed_time": "7:28:43", "remaining_time": "0:51:13", "throughput": 4409.93, "total_tokens": 118731184} {"current_steps": 55025, "total_steps": 61300, "loss": 0.3134, "lr": 1.5795827480666852e-06, "epoch": 8.976345840130506, "percentage": 89.76, "elapsed_time": "7:28:45", "remaining_time": "0:51:10", "throughput": 4409.97, "total_tokens": 118741392} {"current_steps": 55030, "total_steps": 61300, "loss": 0.3197, "lr": 1.5770936801851322e-06, "epoch": 8.977161500815662, "percentage": 89.77, "elapsed_time": "7:28:47", "remaining_time": "0:51:08", "throughput": 4410.0, "total_tokens": 118751984} {"current_steps": 55035, "total_steps": 61300, "loss": 0.3209, "lr": 1.5746065110832124e-06, "epoch": 8.977977161500815, "percentage": 89.78, "elapsed_time": "7:28:50", "remaining_time": "0:51:05", "throughput": 4410.03, "total_tokens": 118763600} {"current_steps": 55040, "total_steps": 61300, "loss": 0.3248, "lr": 1.5721212409625485e-06, "epoch": 8.978792822185971, "percentage": 89.79, "elapsed_time": "7:28:52", "remaining_time": "0:51:03", "throughput": 4410.07, "total_tokens": 118774512} {"current_steps": 55045, "total_steps": 61300, "loss": 0.3393, "lr": 1.5696378700246094e-06, "epoch": 8.979608482871125, "percentage": 89.8, "elapsed_time": "7:28:54", "remaining_time": "0:51:00", "throughput": 4410.1, "total_tokens": 118785072} {"current_steps": 55050, "total_steps": 61300, "loss": 0.3159, "lr": 1.5671563984707066e-06, "epoch": 8.98042414355628, "percentage": 89.8, "elapsed_time": "7:28:57", "remaining_time": "0:50:58", "throughput": 4410.13, "total_tokens": 118795984} {"current_steps": 55055, "total_steps": 61300, "loss": 0.3247, "lr": 1.564676826502004e-06, "epoch": 8.981239804241435, "percentage": 89.81, "elapsed_time": "7:28:58", "remaining_time": "0:50:55", "throughput": 4410.16, "total_tokens": 118804656} {"current_steps": 55060, "total_steps": 61300, "loss": 0.3324, "lr": 1.5621991543195103e-06, "epoch": 8.98205546492659, "percentage": 89.82, "elapsed_time": "7:29:00", "remaining_time": "0:50:53", "throughput": 4410.18, "total_tokens": 118814224} {"current_steps": 55065, "total_steps": 61300, "loss": 0.3469, "lr": 1.5597233821240732e-06, "epoch": 8.982871125611746, "percentage": 89.83, "elapsed_time": "7:29:03", "remaining_time": "0:50:50", "throughput": 4410.22, "total_tokens": 118825552} {"current_steps": 55070, "total_steps": 61300, "loss": 0.3128, "lr": 1.557249510116393e-06, "epoch": 8.9836867862969, "percentage": 89.84, "elapsed_time": "7:29:05", "remaining_time": "0:50:48", "throughput": 4410.26, "total_tokens": 118836752} {"current_steps": 55075, "total_steps": 61300, "loss": 0.3394, "lr": 1.5547775384970154e-06, "epoch": 8.984502446982056, "percentage": 89.85, "elapsed_time": "7:29:07", "remaining_time": "0:50:45", "throughput": 4410.29, "total_tokens": 118846160} {"current_steps": 55080, "total_steps": 61300, "loss": 0.3118, "lr": 1.5523074674663296e-06, "epoch": 8.98531810766721, "percentage": 89.85, "elapsed_time": "7:29:09", "remaining_time": "0:50:43", "throughput": 4410.32, "total_tokens": 118857168} {"current_steps": 55085, "total_steps": 61300, "loss": 0.3375, "lr": 1.549839297224573e-06, "epoch": 8.986133768352365, "percentage": 89.86, "elapsed_time": "7:29:12", "remaining_time": "0:50:40", "throughput": 4410.36, "total_tokens": 118868432} {"current_steps": 55090, "total_steps": 61300, "loss": 0.3235, "lr": 1.5473730279718296e-06, "epoch": 8.986949429037521, "percentage": 89.87, "elapsed_time": "7:29:14", "remaining_time": "0:50:38", "throughput": 4410.39, "total_tokens": 118879120} {"current_steps": 55095, "total_steps": 61300, "loss": 0.3426, "lr": 1.5449086599080204e-06, "epoch": 8.987765089722675, "percentage": 89.88, "elapsed_time": "7:29:16", "remaining_time": "0:50:35", "throughput": 4410.42, "total_tokens": 118889040} {"current_steps": 55100, "total_steps": 61300, "loss": 0.3618, "lr": 1.5424461932329298e-06, "epoch": 8.98858075040783, "percentage": 89.89, "elapsed_time": "7:29:18", "remaining_time": "0:50:33", "throughput": 4410.45, "total_tokens": 118898608} {"current_steps": 55105, "total_steps": 61300, "loss": 0.2985, "lr": 1.5399856281461734e-06, "epoch": 8.989396411092985, "percentage": 89.89, "elapsed_time": "7:29:20", "remaining_time": "0:50:30", "throughput": 4410.49, "total_tokens": 118909264} {"current_steps": 55110, "total_steps": 61300, "loss": 0.3372, "lr": 1.5375269648472162e-06, "epoch": 8.99021207177814, "percentage": 89.9, "elapsed_time": "7:29:22", "remaining_time": "0:50:28", "throughput": 4410.52, "total_tokens": 118920048} {"current_steps": 55115, "total_steps": 61300, "loss": 0.3187, "lr": 1.5350702035353716e-06, "epoch": 8.991027732463294, "percentage": 89.91, "elapsed_time": "7:29:25", "remaining_time": "0:50:26", "throughput": 4410.56, "total_tokens": 118931120} {"current_steps": 55120, "total_steps": 61300, "loss": 0.3166, "lr": 1.5326153444097934e-06, "epoch": 8.99184339314845, "percentage": 89.92, "elapsed_time": "7:29:27", "remaining_time": "0:50:23", "throughput": 4410.59, "total_tokens": 118940464} {"current_steps": 55125, "total_steps": 61300, "loss": 0.3064, "lr": 1.5301623876694898e-06, "epoch": 8.992659053833606, "percentage": 89.93, "elapsed_time": "7:29:29", "remaining_time": "0:50:21", "throughput": 4410.62, "total_tokens": 118951120} {"current_steps": 55130, "total_steps": 61300, "loss": 0.3149, "lr": 1.5277113335133097e-06, "epoch": 8.99347471451876, "percentage": 89.93, "elapsed_time": "7:29:31", "remaining_time": "0:50:18", "throughput": 4410.65, "total_tokens": 118961616} {"current_steps": 55135, "total_steps": 61300, "loss": 0.3051, "lr": 1.5252621821399443e-06, "epoch": 8.994290375203915, "percentage": 89.94, "elapsed_time": "7:29:33", "remaining_time": "0:50:16", "throughput": 4410.69, "total_tokens": 118973296} {"current_steps": 55140, "total_steps": 61300, "loss": 0.3549, "lr": 1.5228149337479347e-06, "epoch": 8.99510603588907, "percentage": 89.95, "elapsed_time": "7:29:35", "remaining_time": "0:50:13", "throughput": 4410.72, "total_tokens": 118983344} {"current_steps": 55145, "total_steps": 61300, "loss": 0.285, "lr": 1.5203695885356694e-06, "epoch": 8.995921696574225, "percentage": 89.96, "elapsed_time": "7:29:38", "remaining_time": "0:50:11", "throughput": 4410.76, "total_tokens": 118994544} {"current_steps": 55150, "total_steps": 61300, "loss": 0.3607, "lr": 1.5179261467013817e-06, "epoch": 8.99673735725938, "percentage": 89.97, "elapsed_time": "7:29:40", "remaining_time": "0:50:08", "throughput": 4410.79, "total_tokens": 119005264} {"current_steps": 55155, "total_steps": 61300, "loss": 0.38, "lr": 1.5154846084431463e-06, "epoch": 8.997553017944535, "percentage": 89.98, "elapsed_time": "7:29:42", "remaining_time": "0:50:06", "throughput": 4410.82, "total_tokens": 119016688} {"current_steps": 55160, "total_steps": 61300, "loss": 0.3307, "lr": 1.513044973958888e-06, "epoch": 8.99836867862969, "percentage": 89.98, "elapsed_time": "7:29:45", "remaining_time": "0:50:03", "throughput": 4410.85, "total_tokens": 119027856} {"current_steps": 55165, "total_steps": 61300, "loss": 0.3474, "lr": 1.5106072434463742e-06, "epoch": 8.999184339314844, "percentage": 89.99, "elapsed_time": "7:29:47", "remaining_time": "0:50:01", "throughput": 4410.89, "total_tokens": 119038000} {"current_steps": 55170, "total_steps": 61300, "loss": 0.3189, "lr": 1.5081714171032186e-06, "epoch": 9.0, "percentage": 90.0, "elapsed_time": "7:29:49", "remaining_time": "0:49:58", "throughput": 4410.9, "total_tokens": 119047920} {"current_steps": 55170, "total_steps": 61300, "eval_loss": 0.3333175480365753, "epoch": 9.0, "percentage": 90.0, "elapsed_time": "7:32:01", "remaining_time": "0:50:13", "throughput": 4389.46, "total_tokens": 119047920} {"current_steps": 55175, "total_steps": 61300, "loss": 0.3254, "lr": 1.5057374951268883e-06, "epoch": 9.000815660685156, "percentage": 90.01, "elapsed_time": "7:32:04", "remaining_time": "0:50:11", "throughput": 4389.27, "total_tokens": 119058096} {"current_steps": 55180, "total_steps": 61300, "loss": 0.3111, "lr": 1.5033054777146838e-06, "epoch": 9.00163132137031, "percentage": 90.02, "elapsed_time": "7:32:06", "remaining_time": "0:50:08", "throughput": 4389.31, "total_tokens": 119068080} {"current_steps": 55185, "total_steps": 61300, "loss": 0.3226, "lr": 1.5008753650637585e-06, "epoch": 9.002446982055465, "percentage": 90.02, "elapsed_time": "7:32:09", "remaining_time": "0:50:06", "throughput": 4389.34, "total_tokens": 119078576} {"current_steps": 55190, "total_steps": 61300, "loss": 0.3201, "lr": 1.4984471573711105e-06, "epoch": 9.00326264274062, "percentage": 90.03, "elapsed_time": "7:32:11", "remaining_time": "0:50:03", "throughput": 4389.38, "total_tokens": 119089808} {"current_steps": 55195, "total_steps": 61300, "loss": 0.3608, "lr": 1.4960208548335825e-06, "epoch": 9.004078303425775, "percentage": 90.04, "elapsed_time": "7:32:13", "remaining_time": "0:50:01", "throughput": 4389.41, "total_tokens": 119100208} {"current_steps": 55200, "total_steps": 61300, "loss": 0.3114, "lr": 1.4935964576478584e-06, "epoch": 9.00489396411093, "percentage": 90.05, "elapsed_time": "7:32:15", "remaining_time": "0:49:58", "throughput": 4389.45, "total_tokens": 119111632} {"current_steps": 55205, "total_steps": 61300, "loss": 0.3613, "lr": 1.4911739660104785e-06, "epoch": 9.005709624796085, "percentage": 90.06, "elapsed_time": "7:32:18", "remaining_time": "0:49:56", "throughput": 4389.48, "total_tokens": 119122608} {"current_steps": 55210, "total_steps": 61300, "loss": 0.3123, "lr": 1.4887533801178188e-06, "epoch": 9.00652528548124, "percentage": 90.07, "elapsed_time": "7:32:20", "remaining_time": "0:49:53", "throughput": 4389.51, "total_tokens": 119132976} {"current_steps": 55215, "total_steps": 61300, "loss": 0.3185, "lr": 1.486334700166106e-06, "epoch": 9.007340946166394, "percentage": 90.07, "elapsed_time": "7:32:22", "remaining_time": "0:49:51", "throughput": 4389.55, "total_tokens": 119143984} {"current_steps": 55220, "total_steps": 61300, "loss": 0.3371, "lr": 1.483917926351408e-06, "epoch": 9.00815660685155, "percentage": 90.08, "elapsed_time": "7:32:24", "remaining_time": "0:49:48", "throughput": 4389.58, "total_tokens": 119154256} {"current_steps": 55225, "total_steps": 61300, "loss": 0.3053, "lr": 1.4815030588696432e-06, "epoch": 9.008972267536704, "percentage": 90.09, "elapsed_time": "7:32:27", "remaining_time": "0:49:46", "throughput": 4389.61, "total_tokens": 119165712} {"current_steps": 55230, "total_steps": 61300, "loss": 0.3293, "lr": 1.4790900979165717e-06, "epoch": 9.00978792822186, "percentage": 90.1, "elapsed_time": "7:32:29", "remaining_time": "0:49:43", "throughput": 4389.64, "total_tokens": 119176496} {"current_steps": 55235, "total_steps": 61300, "loss": 0.3253, "lr": 1.4766790436878035e-06, "epoch": 9.010603588907015, "percentage": 90.11, "elapsed_time": "7:32:31", "remaining_time": "0:49:41", "throughput": 4389.67, "total_tokens": 119186640} {"current_steps": 55240, "total_steps": 61300, "loss": 0.3104, "lr": 1.4742698963787854e-06, "epoch": 9.01141924959217, "percentage": 90.11, "elapsed_time": "7:32:33", "remaining_time": "0:49:38", "throughput": 4389.71, "total_tokens": 119197680} {"current_steps": 55245, "total_steps": 61300, "loss": 0.3369, "lr": 1.4718626561848193e-06, "epoch": 9.012234910277325, "percentage": 90.12, "elapsed_time": "7:32:36", "remaining_time": "0:49:36", "throughput": 4389.74, "total_tokens": 119208080} {"current_steps": 55250, "total_steps": 61300, "loss": 0.3231, "lr": 1.469457323301046e-06, "epoch": 9.013050570962479, "percentage": 90.13, "elapsed_time": "7:32:38", "remaining_time": "0:49:33", "throughput": 4389.77, "total_tokens": 119218896} {"current_steps": 55255, "total_steps": 61300, "loss": 0.3421, "lr": 1.4670538979224547e-06, "epoch": 9.013866231647635, "percentage": 90.14, "elapsed_time": "7:32:40", "remaining_time": "0:49:31", "throughput": 4389.81, "total_tokens": 119230032} {"current_steps": 55260, "total_steps": 61300, "loss": 0.327, "lr": 1.4646523802438805e-06, "epoch": 9.01468189233279, "percentage": 90.15, "elapsed_time": "7:32:42", "remaining_time": "0:49:28", "throughput": 4389.84, "total_tokens": 119240112} {"current_steps": 55265, "total_steps": 61300, "loss": 0.3143, "lr": 1.4622527704599986e-06, "epoch": 9.015497553017944, "percentage": 90.15, "elapsed_time": "7:32:45", "remaining_time": "0:49:26", "throughput": 4389.88, "total_tokens": 119251184} {"current_steps": 55270, "total_steps": 61300, "loss": 0.348, "lr": 1.4598550687653394e-06, "epoch": 9.0163132137031, "percentage": 90.16, "elapsed_time": "7:32:47", "remaining_time": "0:49:23", "throughput": 4389.92, "total_tokens": 119263216} {"current_steps": 55275, "total_steps": 61300, "loss": 0.3302, "lr": 1.4574592753542698e-06, "epoch": 9.017128874388254, "percentage": 90.17, "elapsed_time": "7:32:49", "remaining_time": "0:49:21", "throughput": 4389.95, "total_tokens": 119272112} {"current_steps": 55280, "total_steps": 61300, "loss": 0.3295, "lr": 1.4550653904210038e-06, "epoch": 9.01794453507341, "percentage": 90.18, "elapsed_time": "7:32:51", "remaining_time": "0:49:18", "throughput": 4389.98, "total_tokens": 119282352} {"current_steps": 55285, "total_steps": 61300, "loss": 0.3656, "lr": 1.4526734141596026e-06, "epoch": 9.018760195758565, "percentage": 90.19, "elapsed_time": "7:32:53", "remaining_time": "0:49:16", "throughput": 4390.02, "total_tokens": 119293488} {"current_steps": 55290, "total_steps": 61300, "loss": 0.3149, "lr": 1.4502833467639725e-06, "epoch": 9.01957585644372, "percentage": 90.2, "elapsed_time": "7:32:56", "remaining_time": "0:49:14", "throughput": 4390.05, "total_tokens": 119304592} {"current_steps": 55295, "total_steps": 61300, "loss": 0.3571, "lr": 1.4478951884278669e-06, "epoch": 9.020391517128875, "percentage": 90.2, "elapsed_time": "7:32:58", "remaining_time": "0:49:11", "throughput": 4390.09, "total_tokens": 119315088} {"current_steps": 55300, "total_steps": 61300, "loss": 0.3803, "lr": 1.4455089393448778e-06, "epoch": 9.021207177814029, "percentage": 90.21, "elapsed_time": "7:33:00", "remaining_time": "0:49:09", "throughput": 4390.12, "total_tokens": 119326416} {"current_steps": 55305, "total_steps": 61300, "loss": 0.3403, "lr": 1.4431245997084425e-06, "epoch": 9.022022838499185, "percentage": 90.22, "elapsed_time": "7:33:02", "remaining_time": "0:49:06", "throughput": 4390.16, "total_tokens": 119337296} {"current_steps": 55310, "total_steps": 61300, "loss": 0.3258, "lr": 1.4407421697118617e-06, "epoch": 9.022838499184338, "percentage": 90.23, "elapsed_time": "7:33:05", "remaining_time": "0:49:04", "throughput": 4390.19, "total_tokens": 119347824} {"current_steps": 55315, "total_steps": 61300, "loss": 0.3101, "lr": 1.438361649548256e-06, "epoch": 9.023654159869494, "percentage": 90.24, "elapsed_time": "7:33:07", "remaining_time": "0:49:01", "throughput": 4390.23, "total_tokens": 119359216} {"current_steps": 55320, "total_steps": 61300, "loss": 0.3595, "lr": 1.4359830394106071e-06, "epoch": 9.02446982055465, "percentage": 90.24, "elapsed_time": "7:33:09", "remaining_time": "0:48:59", "throughput": 4390.27, "total_tokens": 119370800} {"current_steps": 55325, "total_steps": 61300, "loss": 0.3347, "lr": 1.4336063394917333e-06, "epoch": 9.025285481239804, "percentage": 90.25, "elapsed_time": "7:33:11", "remaining_time": "0:48:56", "throughput": 4390.3, "total_tokens": 119380944} {"current_steps": 55330, "total_steps": 61300, "loss": 0.3371, "lr": 1.4312315499843077e-06, "epoch": 9.02610114192496, "percentage": 90.26, "elapsed_time": "7:33:14", "remaining_time": "0:48:54", "throughput": 4390.32, "total_tokens": 119390608} {"current_steps": 55335, "total_steps": 61300, "loss": 0.3314, "lr": 1.428858671080835e-06, "epoch": 9.026916802610113, "percentage": 90.27, "elapsed_time": "7:33:16", "remaining_time": "0:48:51", "throughput": 4390.36, "total_tokens": 119401328} {"current_steps": 55340, "total_steps": 61300, "loss": 0.3549, "lr": 1.4264877029736778e-06, "epoch": 9.02773246329527, "percentage": 90.28, "elapsed_time": "7:33:18", "remaining_time": "0:48:49", "throughput": 4390.39, "total_tokens": 119411472} {"current_steps": 55345, "total_steps": 61300, "loss": 0.3317, "lr": 1.424118645855041e-06, "epoch": 9.028548123980425, "percentage": 90.29, "elapsed_time": "7:33:20", "remaining_time": "0:48:46", "throughput": 4390.43, "total_tokens": 119423152} {"current_steps": 55350, "total_steps": 61300, "loss": 0.3256, "lr": 1.4217514999169678e-06, "epoch": 9.029363784665579, "percentage": 90.29, "elapsed_time": "7:33:23", "remaining_time": "0:48:44", "throughput": 4390.47, "total_tokens": 119434992} {"current_steps": 55355, "total_steps": 61300, "loss": 0.3169, "lr": 1.4193862653513524e-06, "epoch": 9.030179445350734, "percentage": 90.3, "elapsed_time": "7:33:25", "remaining_time": "0:48:41", "throughput": 4390.5, "total_tokens": 119445520} {"current_steps": 55360, "total_steps": 61300, "loss": 0.3628, "lr": 1.4170229423499353e-06, "epoch": 9.030995106035888, "percentage": 90.31, "elapsed_time": "7:33:27", "remaining_time": "0:48:39", "throughput": 4390.54, "total_tokens": 119456080} {"current_steps": 55365, "total_steps": 61300, "loss": 0.3285, "lr": 1.4146615311042972e-06, "epoch": 9.031810766721044, "percentage": 90.32, "elapsed_time": "7:33:30", "remaining_time": "0:48:36", "throughput": 4390.57, "total_tokens": 119467504} {"current_steps": 55370, "total_steps": 61300, "loss": 0.3298, "lr": 1.4123020318058649e-06, "epoch": 9.0326264274062, "percentage": 90.33, "elapsed_time": "7:33:32", "remaining_time": "0:48:34", "throughput": 4390.61, "total_tokens": 119478896} {"current_steps": 55375, "total_steps": 61300, "loss": 0.3229, "lr": 1.4099444446459138e-06, "epoch": 9.033442088091354, "percentage": 90.33, "elapsed_time": "7:33:34", "remaining_time": "0:48:31", "throughput": 4390.65, "total_tokens": 119489840} {"current_steps": 55380, "total_steps": 61300, "loss": 0.327, "lr": 1.4075887698155599e-06, "epoch": 9.03425774877651, "percentage": 90.34, "elapsed_time": "7:33:36", "remaining_time": "0:48:29", "throughput": 4390.68, "total_tokens": 119499472} {"current_steps": 55385, "total_steps": 61300, "loss": 0.3221, "lr": 1.4052350075057673e-06, "epoch": 9.035073409461663, "percentage": 90.35, "elapsed_time": "7:33:38", "remaining_time": "0:48:26", "throughput": 4390.71, "total_tokens": 119510768} {"current_steps": 55390, "total_steps": 61300, "loss": 0.2997, "lr": 1.4028831579073448e-06, "epoch": 9.035889070146819, "percentage": 90.36, "elapsed_time": "7:33:41", "remaining_time": "0:48:24", "throughput": 4390.75, "total_tokens": 119521968} {"current_steps": 55395, "total_steps": 61300, "loss": 0.3212, "lr": 1.4005332212109424e-06, "epoch": 9.036704730831975, "percentage": 90.37, "elapsed_time": "7:33:43", "remaining_time": "0:48:21", "throughput": 4390.79, "total_tokens": 119532912} {"current_steps": 55400, "total_steps": 61300, "loss": 0.3216, "lr": 1.3981851976070603e-06, "epoch": 9.037520391517129, "percentage": 90.38, "elapsed_time": "7:33:45", "remaining_time": "0:48:19", "throughput": 4390.84, "total_tokens": 119544208} {"current_steps": 55405, "total_steps": 61300, "loss": 0.3477, "lr": 1.395839087286041e-06, "epoch": 9.038336052202284, "percentage": 90.38, "elapsed_time": "7:33:48", "remaining_time": "0:48:17", "throughput": 4390.88, "total_tokens": 119554960} {"current_steps": 55410, "total_steps": 61300, "loss": 0.3418, "lr": 1.3934948904380712e-06, "epoch": 9.039151712887438, "percentage": 90.39, "elapsed_time": "7:33:50", "remaining_time": "0:48:14", "throughput": 4390.92, "total_tokens": 119566224} {"current_steps": 55415, "total_steps": 61300, "loss": 0.3378, "lr": 1.3911526072531795e-06, "epoch": 9.039967373572594, "percentage": 90.4, "elapsed_time": "7:33:52", "remaining_time": "0:48:12", "throughput": 4390.95, "total_tokens": 119577424} {"current_steps": 55420, "total_steps": 61300, "loss": 0.3203, "lr": 1.3888122379212527e-06, "epoch": 9.040783034257748, "percentage": 90.41, "elapsed_time": "7:33:55", "remaining_time": "0:48:09", "throughput": 4390.98, "total_tokens": 119588752} {"current_steps": 55425, "total_steps": 61300, "loss": 0.3466, "lr": 1.3864737826320058e-06, "epoch": 9.041598694942904, "percentage": 90.42, "elapsed_time": "7:33:57", "remaining_time": "0:48:07", "throughput": 4391.02, "total_tokens": 119600048} {"current_steps": 55430, "total_steps": 61300, "loss": 0.3686, "lr": 1.3841372415750093e-06, "epoch": 9.04241435562806, "percentage": 90.42, "elapsed_time": "7:33:59", "remaining_time": "0:48:04", "throughput": 4391.05, "total_tokens": 119608944} {"current_steps": 55435, "total_steps": 61300, "loss": 0.3207, "lr": 1.381802614939673e-06, "epoch": 9.043230016313213, "percentage": 90.43, "elapsed_time": "7:34:01", "remaining_time": "0:48:02", "throughput": 4391.08, "total_tokens": 119618512} {"current_steps": 55440, "total_steps": 61300, "loss": 0.3269, "lr": 1.3794699029152563e-06, "epoch": 9.044045676998369, "percentage": 90.44, "elapsed_time": "7:34:03", "remaining_time": "0:47:59", "throughput": 4391.11, "total_tokens": 119629040} {"current_steps": 55445, "total_steps": 61300, "loss": 0.3109, "lr": 1.3771391056908555e-06, "epoch": 9.044861337683523, "percentage": 90.45, "elapsed_time": "7:34:05", "remaining_time": "0:47:57", "throughput": 4391.15, "total_tokens": 119639248} {"current_steps": 55450, "total_steps": 61300, "loss": 0.3284, "lr": 1.3748102234554222e-06, "epoch": 9.045676998368679, "percentage": 90.46, "elapsed_time": "7:34:07", "remaining_time": "0:47:54", "throughput": 4391.18, "total_tokens": 119648848} {"current_steps": 55455, "total_steps": 61300, "loss": 0.3115, "lr": 1.372483256397744e-06, "epoch": 9.046492659053834, "percentage": 90.46, "elapsed_time": "7:34:10", "remaining_time": "0:47:52", "throughput": 4391.21, "total_tokens": 119660624} {"current_steps": 55460, "total_steps": 61300, "loss": 0.3442, "lr": 1.3701582047064592e-06, "epoch": 9.047308319738988, "percentage": 90.47, "elapsed_time": "7:34:12", "remaining_time": "0:47:49", "throughput": 4391.24, "total_tokens": 119671120} {"current_steps": 55465, "total_steps": 61300, "loss": 0.356, "lr": 1.3678350685700447e-06, "epoch": 9.048123980424144, "percentage": 90.48, "elapsed_time": "7:34:14", "remaining_time": "0:47:47", "throughput": 4391.27, "total_tokens": 119680720} {"current_steps": 55470, "total_steps": 61300, "loss": 0.3296, "lr": 1.3655138481768303e-06, "epoch": 9.048939641109298, "percentage": 90.49, "elapsed_time": "7:34:16", "remaining_time": "0:47:44", "throughput": 4391.31, "total_tokens": 119690896} {"current_steps": 55475, "total_steps": 61300, "loss": 0.3412, "lr": 1.3631945437149823e-06, "epoch": 9.049755301794454, "percentage": 90.5, "elapsed_time": "7:34:18", "remaining_time": "0:47:42", "throughput": 4391.34, "total_tokens": 119699824} {"current_steps": 55480, "total_steps": 61300, "loss": 0.3235, "lr": 1.3608771553725168e-06, "epoch": 9.05057096247961, "percentage": 90.51, "elapsed_time": "7:34:20", "remaining_time": "0:47:39", "throughput": 4391.37, "total_tokens": 119709552} {"current_steps": 55485, "total_steps": 61300, "loss": 0.3622, "lr": 1.3585616833372894e-06, "epoch": 9.051386623164763, "percentage": 90.51, "elapsed_time": "7:34:22", "remaining_time": "0:47:37", "throughput": 4391.42, "total_tokens": 119721136} {"current_steps": 55490, "total_steps": 61300, "loss": 0.3408, "lr": 1.3562481277970108e-06, "epoch": 9.052202283849919, "percentage": 90.52, "elapsed_time": "7:34:24", "remaining_time": "0:47:34", "throughput": 4391.45, "total_tokens": 119731408} {"current_steps": 55495, "total_steps": 61300, "loss": 0.3185, "lr": 1.3539364889392281e-06, "epoch": 9.053017944535073, "percentage": 90.53, "elapsed_time": "7:34:27", "remaining_time": "0:47:32", "throughput": 4391.5, "total_tokens": 119743728} {"current_steps": 55500, "total_steps": 61300, "loss": 0.3204, "lr": 1.3516267669513305e-06, "epoch": 9.053833605220229, "percentage": 90.54, "elapsed_time": "7:34:29", "remaining_time": "0:47:29", "throughput": 4391.53, "total_tokens": 119754992} {"current_steps": 55505, "total_steps": 61300, "loss": 0.3281, "lr": 1.3493189620205572e-06, "epoch": 9.054649265905383, "percentage": 90.55, "elapsed_time": "7:34:31", "remaining_time": "0:47:27", "throughput": 4391.57, "total_tokens": 119765936} {"current_steps": 55510, "total_steps": 61300, "loss": 0.3035, "lr": 1.3470130743339914e-06, "epoch": 9.055464926590538, "percentage": 90.55, "elapsed_time": "7:34:34", "remaining_time": "0:47:24", "throughput": 4391.6, "total_tokens": 119776688} {"current_steps": 55515, "total_steps": 61300, "loss": 0.2926, "lr": 1.3447091040785619e-06, "epoch": 9.056280587275694, "percentage": 90.56, "elapsed_time": "7:34:36", "remaining_time": "0:47:22", "throughput": 4391.64, "total_tokens": 119787088} {"current_steps": 55520, "total_steps": 61300, "loss": 0.2781, "lr": 1.342407051441033e-06, "epoch": 9.057096247960848, "percentage": 90.57, "elapsed_time": "7:34:38", "remaining_time": "0:47:19", "throughput": 4391.68, "total_tokens": 119798576} {"current_steps": 55525, "total_steps": 61300, "loss": 0.3119, "lr": 1.3401069166080278e-06, "epoch": 9.057911908646004, "percentage": 90.58, "elapsed_time": "7:34:40", "remaining_time": "0:47:17", "throughput": 4391.72, "total_tokens": 119809424} {"current_steps": 55530, "total_steps": 61300, "loss": 0.323, "lr": 1.3378086997660077e-06, "epoch": 9.058727569331158, "percentage": 90.59, "elapsed_time": "7:34:43", "remaining_time": "0:47:14", "throughput": 4391.76, "total_tokens": 119821232} {"current_steps": 55535, "total_steps": 61300, "loss": 0.3461, "lr": 1.3355124011012744e-06, "epoch": 9.059543230016313, "percentage": 90.6, "elapsed_time": "7:34:45", "remaining_time": "0:47:12", "throughput": 4391.79, "total_tokens": 119832688} {"current_steps": 55540, "total_steps": 61300, "loss": 0.3402, "lr": 1.3332180207999783e-06, "epoch": 9.060358890701469, "percentage": 90.6, "elapsed_time": "7:34:47", "remaining_time": "0:47:09", "throughput": 4391.83, "total_tokens": 119842736} {"current_steps": 55545, "total_steps": 61300, "loss": 0.3178, "lr": 1.3309255590481129e-06, "epoch": 9.061174551386623, "percentage": 90.61, "elapsed_time": "7:34:49", "remaining_time": "0:47:07", "throughput": 4391.86, "total_tokens": 119853808} {"current_steps": 55550, "total_steps": 61300, "loss": 0.3588, "lr": 1.3286350160315181e-06, "epoch": 9.061990212071779, "percentage": 90.62, "elapsed_time": "7:34:52", "remaining_time": "0:47:05", "throughput": 4391.9, "total_tokens": 119864976} {"current_steps": 55555, "total_steps": 61300, "loss": 0.3507, "lr": 1.3263463919358759e-06, "epoch": 9.062805872756933, "percentage": 90.63, "elapsed_time": "7:34:54", "remaining_time": "0:47:02", "throughput": 4391.93, "total_tokens": 119875312} {"current_steps": 55560, "total_steps": 61300, "loss": 0.3795, "lr": 1.3240596869467158e-06, "epoch": 9.063621533442088, "percentage": 90.64, "elapsed_time": "7:34:56", "remaining_time": "0:47:00", "throughput": 4391.96, "total_tokens": 119886704} {"current_steps": 55565, "total_steps": 61300, "loss": 0.2946, "lr": 1.3217749012494062e-06, "epoch": 9.064437194127244, "percentage": 90.64, "elapsed_time": "7:34:59", "remaining_time": "0:46:57", "throughput": 4392.0, "total_tokens": 119897424} {"current_steps": 55570, "total_steps": 61300, "loss": 0.315, "lr": 1.3194920350291657e-06, "epoch": 9.065252854812398, "percentage": 90.65, "elapsed_time": "7:35:01", "remaining_time": "0:46:55", "throughput": 4392.04, "total_tokens": 119909520} {"current_steps": 55575, "total_steps": 61300, "loss": 0.3453, "lr": 1.3172110884710541e-06, "epoch": 9.066068515497554, "percentage": 90.66, "elapsed_time": "7:35:03", "remaining_time": "0:46:52", "throughput": 4392.07, "total_tokens": 119919056} {"current_steps": 55580, "total_steps": 61300, "loss": 0.3319, "lr": 1.314932061759977e-06, "epoch": 9.066884176182707, "percentage": 90.67, "elapsed_time": "7:35:05", "remaining_time": "0:46:50", "throughput": 4392.11, "total_tokens": 119930448} {"current_steps": 55585, "total_steps": 61300, "loss": 0.3134, "lr": 1.3126549550806832e-06, "epoch": 9.067699836867863, "percentage": 90.68, "elapsed_time": "7:35:07", "remaining_time": "0:46:47", "throughput": 4392.14, "total_tokens": 119939824} {"current_steps": 55590, "total_steps": 61300, "loss": 0.3749, "lr": 1.310379768617767e-06, "epoch": 9.068515497553017, "percentage": 90.69, "elapsed_time": "7:35:10", "remaining_time": "0:46:45", "throughput": 4392.18, "total_tokens": 119951152} {"current_steps": 55595, "total_steps": 61300, "loss": 0.3154, "lr": 1.308106502555667e-06, "epoch": 9.069331158238173, "percentage": 90.69, "elapsed_time": "7:35:12", "remaining_time": "0:46:42", "throughput": 4392.2, "total_tokens": 119961104} {"current_steps": 55600, "total_steps": 61300, "loss": 0.3852, "lr": 1.3058351570786665e-06, "epoch": 9.070146818923329, "percentage": 90.7, "elapsed_time": "7:35:14", "remaining_time": "0:46:40", "throughput": 4392.23, "total_tokens": 119971920} {"current_steps": 55605, "total_steps": 61300, "loss": 0.3465, "lr": 1.3035657323708927e-06, "epoch": 9.070962479608482, "percentage": 90.71, "elapsed_time": "7:35:16", "remaining_time": "0:46:37", "throughput": 4392.26, "total_tokens": 119980944} {"current_steps": 55610, "total_steps": 61300, "loss": 0.3535, "lr": 1.3012982286163129e-06, "epoch": 9.071778140293638, "percentage": 90.72, "elapsed_time": "7:35:18", "remaining_time": "0:46:35", "throughput": 4392.29, "total_tokens": 119991792} {"current_steps": 55615, "total_steps": 61300, "loss": 0.3029, "lr": 1.2990326459987434e-06, "epoch": 9.072593800978792, "percentage": 90.73, "elapsed_time": "7:35:20", "remaining_time": "0:46:32", "throughput": 4392.32, "total_tokens": 120002064} {"current_steps": 55620, "total_steps": 61300, "loss": 0.3373, "lr": 1.296768984701846e-06, "epoch": 9.073409461663948, "percentage": 90.73, "elapsed_time": "7:35:23", "remaining_time": "0:46:30", "throughput": 4392.36, "total_tokens": 120012560} {"current_steps": 55625, "total_steps": 61300, "loss": 0.3294, "lr": 1.2945072449091212e-06, "epoch": 9.074225122349104, "percentage": 90.74, "elapsed_time": "7:35:25", "remaining_time": "0:46:27", "throughput": 4392.39, "total_tokens": 120023568} {"current_steps": 55630, "total_steps": 61300, "loss": 0.3406, "lr": 1.292247426803922e-06, "epoch": 9.075040783034257, "percentage": 90.75, "elapsed_time": "7:35:27", "remaining_time": "0:46:25", "throughput": 4392.42, "total_tokens": 120034448} {"current_steps": 55635, "total_steps": 61300, "loss": 0.297, "lr": 1.2899895305694408e-06, "epoch": 9.075856443719413, "percentage": 90.76, "elapsed_time": "7:35:29", "remaining_time": "0:46:22", "throughput": 4392.47, "total_tokens": 120046096} {"current_steps": 55640, "total_steps": 61300, "loss": 0.3249, "lr": 1.2877335563887095e-06, "epoch": 9.076672104404567, "percentage": 90.77, "elapsed_time": "7:35:31", "remaining_time": "0:46:20", "throughput": 4392.5, "total_tokens": 120055344} {"current_steps": 55645, "total_steps": 61300, "loss": 0.3486, "lr": 1.2854795044446116e-06, "epoch": 9.077487765089723, "percentage": 90.77, "elapsed_time": "7:35:34", "remaining_time": "0:46:17", "throughput": 4392.53, "total_tokens": 120065808} {"current_steps": 55650, "total_steps": 61300, "loss": 0.3, "lr": 1.2832273749198708e-06, "epoch": 9.078303425774878, "percentage": 90.78, "elapsed_time": "7:35:36", "remaining_time": "0:46:15", "throughput": 4392.56, "total_tokens": 120075472} {"current_steps": 55655, "total_steps": 61300, "loss": 0.388, "lr": 1.2809771679970522e-06, "epoch": 9.079119086460032, "percentage": 90.79, "elapsed_time": "7:35:38", "remaining_time": "0:46:12", "throughput": 4392.59, "total_tokens": 120085072} {"current_steps": 55660, "total_steps": 61300, "loss": 0.3219, "lr": 1.2787288838585793e-06, "epoch": 9.079934747145188, "percentage": 90.8, "elapsed_time": "7:35:40", "remaining_time": "0:46:10", "throughput": 4392.63, "total_tokens": 120096304} {"current_steps": 55665, "total_steps": 61300, "loss": 0.3576, "lr": 1.2764825226867005e-06, "epoch": 9.080750407830342, "percentage": 90.81, "elapsed_time": "7:35:42", "remaining_time": "0:46:07", "throughput": 4392.66, "total_tokens": 120105968} {"current_steps": 55670, "total_steps": 61300, "loss": 0.3432, "lr": 1.2742380846635231e-06, "epoch": 9.081566068515498, "percentage": 90.82, "elapsed_time": "7:35:44", "remaining_time": "0:46:05", "throughput": 4392.71, "total_tokens": 120117360} {"current_steps": 55675, "total_steps": 61300, "loss": 0.3372, "lr": 1.2719955699709907e-06, "epoch": 9.082381729200652, "percentage": 90.82, "elapsed_time": "7:35:47", "remaining_time": "0:46:02", "throughput": 4392.74, "total_tokens": 120128464} {"current_steps": 55680, "total_steps": 61300, "loss": 0.3304, "lr": 1.2697549787908908e-06, "epoch": 9.083197389885807, "percentage": 90.83, "elapsed_time": "7:35:49", "remaining_time": "0:46:00", "throughput": 4392.77, "total_tokens": 120139440} {"current_steps": 55685, "total_steps": 61300, "loss": 0.3049, "lr": 1.267516311304856e-06, "epoch": 9.084013050570963, "percentage": 90.84, "elapsed_time": "7:35:51", "remaining_time": "0:45:57", "throughput": 4392.8, "total_tokens": 120149392} {"current_steps": 55690, "total_steps": 61300, "loss": 0.3078, "lr": 1.265279567694369e-06, "epoch": 9.084828711256117, "percentage": 90.85, "elapsed_time": "7:35:53", "remaining_time": "0:45:55", "throughput": 4392.84, "total_tokens": 120160848} {"current_steps": 55695, "total_steps": 61300, "loss": 0.3349, "lr": 1.2630447481407486e-06, "epoch": 9.085644371941273, "percentage": 90.86, "elapsed_time": "7:35:56", "remaining_time": "0:45:53", "throughput": 4392.88, "total_tokens": 120172368} {"current_steps": 55700, "total_steps": 61300, "loss": 0.3286, "lr": 1.2608118528251611e-06, "epoch": 9.086460032626427, "percentage": 90.86, "elapsed_time": "7:35:58", "remaining_time": "0:45:50", "throughput": 4392.91, "total_tokens": 120183184} {"current_steps": 55705, "total_steps": 61300, "loss": 0.3267, "lr": 1.2585808819286172e-06, "epoch": 9.087275693311582, "percentage": 90.87, "elapsed_time": "7:36:00", "remaining_time": "0:45:48", "throughput": 4392.95, "total_tokens": 120194480} {"current_steps": 55710, "total_steps": 61300, "loss": 0.3648, "lr": 1.2563518356319664e-06, "epoch": 9.088091353996738, "percentage": 90.88, "elapsed_time": "7:36:03", "remaining_time": "0:45:45", "throughput": 4392.98, "total_tokens": 120205616} {"current_steps": 55715, "total_steps": 61300, "loss": 0.3025, "lr": 1.2541247141159119e-06, "epoch": 9.088907014681892, "percentage": 90.89, "elapsed_time": "7:36:05", "remaining_time": "0:45:43", "throughput": 4393.01, "total_tokens": 120216496} {"current_steps": 55720, "total_steps": 61300, "loss": 0.3206, "lr": 1.2518995175609949e-06, "epoch": 9.089722675367048, "percentage": 90.9, "elapsed_time": "7:36:07", "remaining_time": "0:45:40", "throughput": 4393.05, "total_tokens": 120226896} {"current_steps": 55725, "total_steps": 61300, "loss": 0.3228, "lr": 1.2496762461475992e-06, "epoch": 9.090538336052202, "percentage": 90.91, "elapsed_time": "7:36:09", "remaining_time": "0:45:38", "throughput": 4393.08, "total_tokens": 120236400} {"current_steps": 55730, "total_steps": 61300, "loss": 0.3238, "lr": 1.2474549000559527e-06, "epoch": 9.091353996737357, "percentage": 90.91, "elapsed_time": "7:36:11", "remaining_time": "0:45:35", "throughput": 4393.12, "total_tokens": 120247920} {"current_steps": 55735, "total_steps": 61300, "loss": 0.3479, "lr": 1.245235479466131e-06, "epoch": 9.092169657422513, "percentage": 90.92, "elapsed_time": "7:36:14", "remaining_time": "0:45:33", "throughput": 4393.15, "total_tokens": 120258512} {"current_steps": 55740, "total_steps": 61300, "loss": 0.33, "lr": 1.2430179845580537e-06, "epoch": 9.092985318107667, "percentage": 90.93, "elapsed_time": "7:36:16", "remaining_time": "0:45:30", "throughput": 4393.18, "total_tokens": 120270032} {"current_steps": 55745, "total_steps": 61300, "loss": 0.3686, "lr": 1.24080241551148e-06, "epoch": 9.093800978792823, "percentage": 90.94, "elapsed_time": "7:36:18", "remaining_time": "0:45:28", "throughput": 4393.22, "total_tokens": 120280816} {"current_steps": 55750, "total_steps": 61300, "loss": 0.3302, "lr": 1.2385887725060135e-06, "epoch": 9.094616639477977, "percentage": 90.95, "elapsed_time": "7:36:21", "remaining_time": "0:45:25", "throughput": 4393.25, "total_tokens": 120291664} {"current_steps": 55755, "total_steps": 61300, "loss": 0.3186, "lr": 1.236377055721108e-06, "epoch": 9.095432300163132, "percentage": 90.95, "elapsed_time": "7:36:23", "remaining_time": "0:45:23", "throughput": 4393.28, "total_tokens": 120302320} {"current_steps": 55760, "total_steps": 61300, "loss": 0.3475, "lr": 1.234167265336053e-06, "epoch": 9.096247960848286, "percentage": 90.96, "elapsed_time": "7:36:25", "remaining_time": "0:45:20", "throughput": 4393.32, "total_tokens": 120312688} {"current_steps": 55765, "total_steps": 61300, "loss": 0.3254, "lr": 1.2319594015299862e-06, "epoch": 9.097063621533442, "percentage": 90.97, "elapsed_time": "7:36:27", "remaining_time": "0:45:18", "throughput": 4393.35, "total_tokens": 120322928} {"current_steps": 55770, "total_steps": 61300, "loss": 0.3355, "lr": 1.2297534644818891e-06, "epoch": 9.097879282218598, "percentage": 90.98, "elapsed_time": "7:36:29", "remaining_time": "0:45:15", "throughput": 4393.38, "total_tokens": 120332080} {"current_steps": 55775, "total_steps": 61300, "loss": 0.3294, "lr": 1.227549454370583e-06, "epoch": 9.098694942903752, "percentage": 90.99, "elapsed_time": "7:36:31", "remaining_time": "0:45:13", "throughput": 4393.42, "total_tokens": 120344400} {"current_steps": 55780, "total_steps": 61300, "loss": 0.355, "lr": 1.225347371374741e-06, "epoch": 9.099510603588907, "percentage": 91.0, "elapsed_time": "7:36:34", "remaining_time": "0:45:10", "throughput": 4393.45, "total_tokens": 120355344} {"current_steps": 55785, "total_steps": 61300, "loss": 0.3158, "lr": 1.2231472156728707e-06, "epoch": 9.100326264274061, "percentage": 91.0, "elapsed_time": "7:36:36", "remaining_time": "0:45:08", "throughput": 4393.49, "total_tokens": 120366640} {"current_steps": 55790, "total_steps": 61300, "loss": 0.342, "lr": 1.2209489874433294e-06, "epoch": 9.101141924959217, "percentage": 91.01, "elapsed_time": "7:36:38", "remaining_time": "0:45:06", "throughput": 4393.52, "total_tokens": 120377584} {"current_steps": 55795, "total_steps": 61300, "loss": 0.3523, "lr": 1.2187526868643162e-06, "epoch": 9.101957585644373, "percentage": 91.02, "elapsed_time": "7:36:41", "remaining_time": "0:45:03", "throughput": 4393.56, "total_tokens": 120388368} {"current_steps": 55800, "total_steps": 61300, "loss": 0.349, "lr": 1.2165583141138748e-06, "epoch": 9.102773246329527, "percentage": 91.03, "elapsed_time": "7:36:43", "remaining_time": "0:45:01", "throughput": 4393.6, "total_tokens": 120399312} {"current_steps": 55805, "total_steps": 61300, "loss": 0.3347, "lr": 1.2143658693698933e-06, "epoch": 9.103588907014682, "percentage": 91.04, "elapsed_time": "7:36:45", "remaining_time": "0:44:58", "throughput": 4393.63, "total_tokens": 120409616} {"current_steps": 55810, "total_steps": 61300, "loss": 0.3301, "lr": 1.212175352810102e-06, "epoch": 9.104404567699836, "percentage": 91.04, "elapsed_time": "7:36:47", "remaining_time": "0:44:56", "throughput": 4393.67, "total_tokens": 120421424} {"current_steps": 55815, "total_steps": 61300, "loss": 0.3205, "lr": 1.2099867646120754e-06, "epoch": 9.105220228384992, "percentage": 91.05, "elapsed_time": "7:36:49", "remaining_time": "0:44:53", "throughput": 4393.71, "total_tokens": 120431088} {"current_steps": 55820, "total_steps": 61300, "loss": 0.3425, "lr": 1.20780010495323e-06, "epoch": 9.106035889070148, "percentage": 91.06, "elapsed_time": "7:36:52", "remaining_time": "0:44:51", "throughput": 4393.75, "total_tokens": 120442320} {"current_steps": 55825, "total_steps": 61300, "loss": 0.3394, "lr": 1.2056153740108295e-06, "epoch": 9.106851549755302, "percentage": 91.07, "elapsed_time": "7:36:54", "remaining_time": "0:44:48", "throughput": 4393.78, "total_tokens": 120453104} {"current_steps": 55830, "total_steps": 61300, "loss": 0.3327, "lr": 1.2034325719619794e-06, "epoch": 9.107667210440457, "percentage": 91.08, "elapsed_time": "7:36:56", "remaining_time": "0:44:46", "throughput": 4393.81, "total_tokens": 120463536} {"current_steps": 55835, "total_steps": 61300, "loss": 0.3222, "lr": 1.2012516989836242e-06, "epoch": 9.108482871125611, "percentage": 91.08, "elapsed_time": "7:36:58", "remaining_time": "0:44:43", "throughput": 4393.85, "total_tokens": 120474672} {"current_steps": 55840, "total_steps": 61300, "loss": 0.3761, "lr": 1.1990727552525588e-06, "epoch": 9.109298531810767, "percentage": 91.09, "elapsed_time": "7:37:00", "remaining_time": "0:44:41", "throughput": 4393.87, "total_tokens": 120484208} {"current_steps": 55845, "total_steps": 61300, "loss": 0.3565, "lr": 1.196895740945425e-06, "epoch": 9.11011419249592, "percentage": 91.1, "elapsed_time": "7:37:03", "remaining_time": "0:44:38", "throughput": 4393.91, "total_tokens": 120494896} {"current_steps": 55850, "total_steps": 61300, "loss": 0.339, "lr": 1.194720656238696e-06, "epoch": 9.110929853181077, "percentage": 91.11, "elapsed_time": "7:37:05", "remaining_time": "0:44:36", "throughput": 4393.95, "total_tokens": 120505936} {"current_steps": 55855, "total_steps": 61300, "loss": 0.329, "lr": 1.1925475013086968e-06, "epoch": 9.111745513866232, "percentage": 91.12, "elapsed_time": "7:37:07", "remaining_time": "0:44:33", "throughput": 4393.99, "total_tokens": 120516944} {"current_steps": 55860, "total_steps": 61300, "loss": 0.3096, "lr": 1.190376276331598e-06, "epoch": 9.112561174551386, "percentage": 91.13, "elapsed_time": "7:37:09", "remaining_time": "0:44:31", "throughput": 4394.02, "total_tokens": 120527344} {"current_steps": 55865, "total_steps": 61300, "loss": 0.3313, "lr": 1.1882069814834057e-06, "epoch": 9.113376835236542, "percentage": 91.13, "elapsed_time": "7:37:11", "remaining_time": "0:44:28", "throughput": 4394.05, "total_tokens": 120537520} {"current_steps": 55870, "total_steps": 61300, "loss": 0.3415, "lr": 1.186039616939974e-06, "epoch": 9.114192495921696, "percentage": 91.14, "elapsed_time": "7:37:14", "remaining_time": "0:44:26", "throughput": 4394.09, "total_tokens": 120549072} {"current_steps": 55875, "total_steps": 61300, "loss": 0.3036, "lr": 1.1838741828770039e-06, "epoch": 9.115008156606851, "percentage": 91.15, "elapsed_time": "7:37:16", "remaining_time": "0:44:23", "throughput": 4394.13, "total_tokens": 120559888} {"current_steps": 55880, "total_steps": 61300, "loss": 0.3259, "lr": 1.1817106794700327e-06, "epoch": 9.115823817292007, "percentage": 91.16, "elapsed_time": "7:37:18", "remaining_time": "0:44:21", "throughput": 4394.17, "total_tokens": 120571504} {"current_steps": 55885, "total_steps": 61300, "loss": 0.375, "lr": 1.1795491068944453e-06, "epoch": 9.116639477977161, "percentage": 91.17, "elapsed_time": "7:37:21", "remaining_time": "0:44:18", "throughput": 4394.2, "total_tokens": 120581456} {"current_steps": 55890, "total_steps": 61300, "loss": 0.3379, "lr": 1.1773894653254736e-06, "epoch": 9.117455138662317, "percentage": 91.17, "elapsed_time": "7:37:23", "remaining_time": "0:44:16", "throughput": 4394.24, "total_tokens": 120592080} {"current_steps": 55895, "total_steps": 61300, "loss": 0.3496, "lr": 1.1752317549381857e-06, "epoch": 9.11827079934747, "percentage": 91.18, "elapsed_time": "7:37:25", "remaining_time": "0:44:13", "throughput": 4394.27, "total_tokens": 120602128} {"current_steps": 55900, "total_steps": 61300, "loss": 0.3272, "lr": 1.1730759759074978e-06, "epoch": 9.119086460032626, "percentage": 91.19, "elapsed_time": "7:37:27", "remaining_time": "0:44:11", "throughput": 4394.31, "total_tokens": 120614352} {"current_steps": 55905, "total_steps": 61300, "loss": 0.3209, "lr": 1.1709221284081666e-06, "epoch": 9.119902120717782, "percentage": 91.2, "elapsed_time": "7:37:30", "remaining_time": "0:44:09", "throughput": 4394.35, "total_tokens": 120625424} {"current_steps": 55910, "total_steps": 61300, "loss": 0.3137, "lr": 1.1687702126147976e-06, "epoch": 9.120717781402936, "percentage": 91.21, "elapsed_time": "7:37:32", "remaining_time": "0:44:06", "throughput": 4394.37, "total_tokens": 120635536} {"current_steps": 55915, "total_steps": 61300, "loss": 0.3258, "lr": 1.1666202287018313e-06, "epoch": 9.121533442088092, "percentage": 91.22, "elapsed_time": "7:37:34", "remaining_time": "0:44:04", "throughput": 4394.4, "total_tokens": 120646064} {"current_steps": 55920, "total_steps": 61300, "loss": 0.3033, "lr": 1.1644721768435617e-06, "epoch": 9.122349102773246, "percentage": 91.22, "elapsed_time": "7:37:36", "remaining_time": "0:44:01", "throughput": 4394.45, "total_tokens": 120657072} {"current_steps": 55925, "total_steps": 61300, "loss": 0.3317, "lr": 1.1623260572141137e-06, "epoch": 9.123164763458401, "percentage": 91.23, "elapsed_time": "7:37:39", "remaining_time": "0:43:59", "throughput": 4394.48, "total_tokens": 120668816} {"current_steps": 55930, "total_steps": 61300, "loss": 0.3446, "lr": 1.16018186998747e-06, "epoch": 9.123980424143557, "percentage": 91.24, "elapsed_time": "7:37:41", "remaining_time": "0:43:56", "throughput": 4394.51, "total_tokens": 120679248} {"current_steps": 55935, "total_steps": 61300, "loss": 0.2957, "lr": 1.1580396153374446e-06, "epoch": 9.124796084828711, "percentage": 91.25, "elapsed_time": "7:37:43", "remaining_time": "0:43:54", "throughput": 4394.55, "total_tokens": 120690096} {"current_steps": 55940, "total_steps": 61300, "loss": 0.3224, "lr": 1.1558992934376982e-06, "epoch": 9.125611745513867, "percentage": 91.26, "elapsed_time": "7:37:46", "remaining_time": "0:43:51", "throughput": 4394.58, "total_tokens": 120702352} {"current_steps": 55945, "total_steps": 61300, "loss": 0.327, "lr": 1.1537609044617398e-06, "epoch": 9.12642740619902, "percentage": 91.26, "elapsed_time": "7:37:48", "remaining_time": "0:43:49", "throughput": 4394.62, "total_tokens": 120713072} {"current_steps": 55950, "total_steps": 61300, "loss": 0.3217, "lr": 1.1516244485829193e-06, "epoch": 9.127243066884176, "percentage": 91.27, "elapsed_time": "7:37:50", "remaining_time": "0:43:46", "throughput": 4394.66, "total_tokens": 120725200} {"current_steps": 55955, "total_steps": 61300, "loss": 0.3175, "lr": 1.1494899259744258e-06, "epoch": 9.12805872756933, "percentage": 91.28, "elapsed_time": "7:37:53", "remaining_time": "0:43:44", "throughput": 4394.69, "total_tokens": 120735696} {"current_steps": 55960, "total_steps": 61300, "loss": 0.3622, "lr": 1.147357336809296e-06, "epoch": 9.128874388254486, "percentage": 91.29, "elapsed_time": "7:37:55", "remaining_time": "0:43:41", "throughput": 4394.73, "total_tokens": 120747344} {"current_steps": 55965, "total_steps": 61300, "loss": 0.3225, "lr": 1.1452266812604056e-06, "epoch": 9.129690048939642, "percentage": 91.3, "elapsed_time": "7:37:57", "remaining_time": "0:43:39", "throughput": 4394.77, "total_tokens": 120758416} {"current_steps": 55970, "total_steps": 61300, "loss": 0.3364, "lr": 1.1430979595004777e-06, "epoch": 9.130505709624796, "percentage": 91.31, "elapsed_time": "7:38:00", "remaining_time": "0:43:36", "throughput": 4394.8, "total_tokens": 120769552} {"current_steps": 55975, "total_steps": 61300, "loss": 0.3111, "lr": 1.1409711717020794e-06, "epoch": 9.131321370309951, "percentage": 91.31, "elapsed_time": "7:38:02", "remaining_time": "0:43:34", "throughput": 4394.83, "total_tokens": 120780656} {"current_steps": 55980, "total_steps": 61300, "loss": 0.3459, "lr": 1.1388463180376175e-06, "epoch": 9.132137030995105, "percentage": 91.32, "elapsed_time": "7:38:04", "remaining_time": "0:43:31", "throughput": 4394.87, "total_tokens": 120792048} {"current_steps": 55985, "total_steps": 61300, "loss": 0.3374, "lr": 1.1367233986793429e-06, "epoch": 9.132952691680261, "percentage": 91.33, "elapsed_time": "7:38:06", "remaining_time": "0:43:29", "throughput": 4394.91, "total_tokens": 120802224} {"current_steps": 55990, "total_steps": 61300, "loss": 0.3265, "lr": 1.1346024137993516e-06, "epoch": 9.133768352365417, "percentage": 91.34, "elapsed_time": "7:38:09", "remaining_time": "0:43:27", "throughput": 4394.95, "total_tokens": 120812720} {"current_steps": 55995, "total_steps": 61300, "loss": 0.3154, "lr": 1.1324833635695808e-06, "epoch": 9.13458401305057, "percentage": 91.35, "elapsed_time": "7:38:11", "remaining_time": "0:43:24", "throughput": 4394.99, "total_tokens": 120824880} {"current_steps": 56000, "total_steps": 61300, "loss": 0.3707, "lr": 1.13036624816181e-06, "epoch": 9.135399673735726, "percentage": 91.35, "elapsed_time": "7:38:13", "remaining_time": "0:43:22", "throughput": 4395.03, "total_tokens": 120835632} {"current_steps": 56005, "total_steps": 61300, "loss": 0.339, "lr": 1.1282510677476655e-06, "epoch": 9.13621533442088, "percentage": 91.36, "elapsed_time": "7:38:16", "remaining_time": "0:43:19", "throughput": 4395.07, "total_tokens": 120847984} {"current_steps": 56010, "total_steps": 61300, "loss": 0.2991, "lr": 1.126137822498613e-06, "epoch": 9.137030995106036, "percentage": 91.37, "elapsed_time": "7:38:18", "remaining_time": "0:43:17", "throughput": 4395.1, "total_tokens": 120858832} {"current_steps": 56015, "total_steps": 61300, "loss": 0.298, "lr": 1.1240265125859628e-06, "epoch": 9.137846655791192, "percentage": 91.38, "elapsed_time": "7:38:20", "remaining_time": "0:43:14", "throughput": 4395.14, "total_tokens": 120869872} {"current_steps": 56020, "total_steps": 61300, "loss": 0.3562, "lr": 1.1219171381808696e-06, "epoch": 9.138662316476346, "percentage": 91.39, "elapsed_time": "7:38:22", "remaining_time": "0:43:12", "throughput": 4395.17, "total_tokens": 120879920} {"current_steps": 56025, "total_steps": 61300, "loss": 0.3357, "lr": 1.11980969945433e-06, "epoch": 9.139477977161501, "percentage": 91.39, "elapsed_time": "7:38:25", "remaining_time": "0:43:09", "throughput": 4395.21, "total_tokens": 120891088} {"current_steps": 56030, "total_steps": 61300, "loss": 0.3171, "lr": 1.1177041965771823e-06, "epoch": 9.140293637846655, "percentage": 91.4, "elapsed_time": "7:38:27", "remaining_time": "0:43:07", "throughput": 4395.24, "total_tokens": 120901968} {"current_steps": 56035, "total_steps": 61300, "loss": 0.3433, "lr": 1.1156006297201093e-06, "epoch": 9.141109298531811, "percentage": 91.41, "elapsed_time": "7:38:29", "remaining_time": "0:43:04", "throughput": 4395.27, "total_tokens": 120912176} {"current_steps": 56040, "total_steps": 61300, "loss": 0.3476, "lr": 1.1134989990536387e-06, "epoch": 9.141924959216965, "percentage": 91.42, "elapsed_time": "7:38:31", "remaining_time": "0:43:02", "throughput": 4395.3, "total_tokens": 120923216} {"current_steps": 56045, "total_steps": 61300, "loss": 0.3549, "lr": 1.1113993047481369e-06, "epoch": 9.14274061990212, "percentage": 91.43, "elapsed_time": "7:38:34", "remaining_time": "0:42:59", "throughput": 4395.35, "total_tokens": 120934448} {"current_steps": 56050, "total_steps": 61300, "loss": 0.351, "lr": 1.1093015469738177e-06, "epoch": 9.143556280587276, "percentage": 91.44, "elapsed_time": "7:38:36", "remaining_time": "0:42:57", "throughput": 4395.37, "total_tokens": 120944880} {"current_steps": 56055, "total_steps": 61300, "loss": 0.3307, "lr": 1.107205725900734e-06, "epoch": 9.14437194127243, "percentage": 91.44, "elapsed_time": "7:38:38", "remaining_time": "0:42:54", "throughput": 4395.41, "total_tokens": 120956304} {"current_steps": 56060, "total_steps": 61300, "loss": 0.3315, "lr": 1.105111841698786e-06, "epoch": 9.145187601957586, "percentage": 91.45, "elapsed_time": "7:38:40", "remaining_time": "0:42:52", "throughput": 4395.44, "total_tokens": 120966320} {"current_steps": 56065, "total_steps": 61300, "loss": 0.2957, "lr": 1.1030198945377128e-06, "epoch": 9.14600326264274, "percentage": 91.46, "elapsed_time": "7:38:43", "remaining_time": "0:42:49", "throughput": 4395.47, "total_tokens": 120977648} {"current_steps": 56070, "total_steps": 61300, "loss": 0.3232, "lr": 1.1009298845871013e-06, "epoch": 9.146818923327896, "percentage": 91.47, "elapsed_time": "7:38:45", "remaining_time": "0:42:47", "throughput": 4395.5, "total_tokens": 120987728} {"current_steps": 56075, "total_steps": 61300, "loss": 0.3192, "lr": 1.098841812016374e-06, "epoch": 9.147634584013051, "percentage": 91.48, "elapsed_time": "7:38:47", "remaining_time": "0:42:44", "throughput": 4395.54, "total_tokens": 120998640} {"current_steps": 56080, "total_steps": 61300, "loss": 0.3486, "lr": 1.096755676994804e-06, "epoch": 9.148450244698205, "percentage": 91.48, "elapsed_time": "7:38:49", "remaining_time": "0:42:42", "throughput": 4395.58, "total_tokens": 121008912} {"current_steps": 56085, "total_steps": 61300, "loss": 0.3733, "lr": 1.0946714796915032e-06, "epoch": 9.149265905383361, "percentage": 91.49, "elapsed_time": "7:38:51", "remaining_time": "0:42:40", "throughput": 4395.61, "total_tokens": 121019184} {"current_steps": 56090, "total_steps": 61300, "loss": 0.3469, "lr": 1.092589220275425e-06, "epoch": 9.150081566068515, "percentage": 91.5, "elapsed_time": "7:38:54", "remaining_time": "0:42:37", "throughput": 4395.65, "total_tokens": 121031184} {"current_steps": 56095, "total_steps": 61300, "loss": 0.315, "lr": 1.0905088989153712e-06, "epoch": 9.15089722675367, "percentage": 91.51, "elapsed_time": "7:38:56", "remaining_time": "0:42:35", "throughput": 4395.69, "total_tokens": 121042672} {"current_steps": 56100, "total_steps": 61300, "loss": 0.3528, "lr": 1.0884305157799785e-06, "epoch": 9.151712887438826, "percentage": 91.52, "elapsed_time": "7:38:58", "remaining_time": "0:42:32", "throughput": 4395.72, "total_tokens": 121053520} {"current_steps": 56105, "total_steps": 61300, "loss": 0.3636, "lr": 1.0863540710377373e-06, "epoch": 9.15252854812398, "percentage": 91.53, "elapsed_time": "7:39:01", "remaining_time": "0:42:30", "throughput": 4395.76, "total_tokens": 121064688} {"current_steps": 56110, "total_steps": 61300, "loss": 0.2937, "lr": 1.0842795648569688e-06, "epoch": 9.153344208809136, "percentage": 91.53, "elapsed_time": "7:39:03", "remaining_time": "0:42:27", "throughput": 4395.79, "total_tokens": 121075088} {"current_steps": 56115, "total_steps": 61300, "loss": 0.3426, "lr": 1.0822069974058464e-06, "epoch": 9.15415986949429, "percentage": 91.54, "elapsed_time": "7:39:05", "remaining_time": "0:42:25", "throughput": 4395.83, "total_tokens": 121085424} {"current_steps": 56120, "total_steps": 61300, "loss": 0.354, "lr": 1.0801363688523858e-06, "epoch": 9.154975530179446, "percentage": 91.55, "elapsed_time": "7:39:07", "remaining_time": "0:42:22", "throughput": 4395.87, "total_tokens": 121097072} {"current_steps": 56125, "total_steps": 61300, "loss": 0.3578, "lr": 1.0780676793644362e-06, "epoch": 9.1557911908646, "percentage": 91.56, "elapsed_time": "7:39:10", "remaining_time": "0:42:20", "throughput": 4395.91, "total_tokens": 121108880} {"current_steps": 56130, "total_steps": 61300, "loss": 0.3713, "lr": 1.0760009291097022e-06, "epoch": 9.156606851549755, "percentage": 91.57, "elapsed_time": "7:39:12", "remaining_time": "0:42:17", "throughput": 4395.95, "total_tokens": 121120432} {"current_steps": 56135, "total_steps": 61300, "loss": 0.3396, "lr": 1.0739361182557194e-06, "epoch": 9.15742251223491, "percentage": 91.57, "elapsed_time": "7:39:15", "remaining_time": "0:42:15", "throughput": 4395.98, "total_tokens": 121131952} {"current_steps": 56140, "total_steps": 61300, "loss": 0.3405, "lr": 1.071873246969876e-06, "epoch": 9.158238172920065, "percentage": 91.58, "elapsed_time": "7:39:16", "remaining_time": "0:42:12", "throughput": 4396.01, "total_tokens": 121140304} {"current_steps": 56145, "total_steps": 61300, "loss": 0.3378, "lr": 1.0698123154193967e-06, "epoch": 9.15905383360522, "percentage": 91.59, "elapsed_time": "7:39:19", "remaining_time": "0:42:10", "throughput": 4396.03, "total_tokens": 121150608} {"current_steps": 56150, "total_steps": 61300, "loss": 0.3081, "lr": 1.0677533237713533e-06, "epoch": 9.159869494290374, "percentage": 91.6, "elapsed_time": "7:39:21", "remaining_time": "0:42:07", "throughput": 4396.06, "total_tokens": 121161296} {"current_steps": 56155, "total_steps": 61300, "loss": 0.3185, "lr": 1.0656962721926539e-06, "epoch": 9.16068515497553, "percentage": 91.61, "elapsed_time": "7:39:23", "remaining_time": "0:42:05", "throughput": 4396.1, "total_tokens": 121172976} {"current_steps": 56160, "total_steps": 61300, "loss": 0.3148, "lr": 1.063641160850054e-06, "epoch": 9.161500815660686, "percentage": 91.62, "elapsed_time": "7:39:25", "remaining_time": "0:42:02", "throughput": 4396.14, "total_tokens": 121183024} {"current_steps": 56165, "total_steps": 61300, "loss": 0.325, "lr": 1.0615879899101567e-06, "epoch": 9.16231647634584, "percentage": 91.62, "elapsed_time": "7:39:28", "remaining_time": "0:42:00", "throughput": 4396.17, "total_tokens": 121194032} {"current_steps": 56170, "total_steps": 61300, "loss": 0.3221, "lr": 1.0595367595393978e-06, "epoch": 9.163132137030995, "percentage": 91.63, "elapsed_time": "7:39:30", "remaining_time": "0:41:58", "throughput": 4396.2, "total_tokens": 121205296} {"current_steps": 56175, "total_steps": 61300, "loss": 0.3703, "lr": 1.0574874699040643e-06, "epoch": 9.16394779771615, "percentage": 91.64, "elapsed_time": "7:39:32", "remaining_time": "0:41:55", "throughput": 4396.24, "total_tokens": 121217168} {"current_steps": 56180, "total_steps": 61300, "loss": 0.3214, "lr": 1.0554401211702787e-06, "epoch": 9.164763458401305, "percentage": 91.65, "elapsed_time": "7:39:35", "remaining_time": "0:41:53", "throughput": 4396.28, "total_tokens": 121228176} {"current_steps": 56185, "total_steps": 61300, "loss": 0.3294, "lr": 1.0533947135040106e-06, "epoch": 9.16557911908646, "percentage": 91.66, "elapsed_time": "7:39:37", "remaining_time": "0:41:50", "throughput": 4396.3, "total_tokens": 121237968} {"current_steps": 56190, "total_steps": 61300, "loss": 0.3315, "lr": 1.0513512470710695e-06, "epoch": 9.166394779771615, "percentage": 91.66, "elapsed_time": "7:39:39", "remaining_time": "0:41:48", "throughput": 4396.33, "total_tokens": 121248048} {"current_steps": 56195, "total_steps": 61300, "loss": 0.29, "lr": 1.0493097220371117e-06, "epoch": 9.16721044045677, "percentage": 91.67, "elapsed_time": "7:39:41", "remaining_time": "0:41:45", "throughput": 4396.36, "total_tokens": 121259088} {"current_steps": 56200, "total_steps": 61300, "loss": 0.3362, "lr": 1.0472701385676326e-06, "epoch": 9.168026101141924, "percentage": 91.68, "elapsed_time": "7:39:44", "remaining_time": "0:41:43", "throughput": 4396.4, "total_tokens": 121270416} {"current_steps": 56205, "total_steps": 61300, "loss": 0.3411, "lr": 1.045232496827972e-06, "epoch": 9.16884176182708, "percentage": 91.69, "elapsed_time": "7:39:46", "remaining_time": "0:41:40", "throughput": 4396.43, "total_tokens": 121281424} {"current_steps": 56210, "total_steps": 61300, "loss": 0.3718, "lr": 1.043196796983309e-06, "epoch": 9.169657422512234, "percentage": 91.7, "elapsed_time": "7:39:48", "remaining_time": "0:41:38", "throughput": 4396.47, "total_tokens": 121292496} {"current_steps": 56215, "total_steps": 61300, "loss": 0.3369, "lr": 1.0411630391986698e-06, "epoch": 9.17047308319739, "percentage": 91.7, "elapsed_time": "7:39:50", "remaining_time": "0:41:35", "throughput": 4396.5, "total_tokens": 121303280} {"current_steps": 56220, "total_steps": 61300, "loss": 0.3674, "lr": 1.03913122363892e-06, "epoch": 9.171288743882545, "percentage": 91.71, "elapsed_time": "7:39:53", "remaining_time": "0:41:33", "throughput": 4396.54, "total_tokens": 121315248} {"current_steps": 56225, "total_steps": 61300, "loss": 0.3292, "lr": 1.0371013504687692e-06, "epoch": 9.1721044045677, "percentage": 91.72, "elapsed_time": "7:39:55", "remaining_time": "0:41:30", "throughput": 4396.58, "total_tokens": 121326256} {"current_steps": 56230, "total_steps": 61300, "loss": 0.3186, "lr": 1.0350734198527696e-06, "epoch": 9.172920065252855, "percentage": 91.73, "elapsed_time": "7:39:57", "remaining_time": "0:41:28", "throughput": 4396.61, "total_tokens": 121337264} {"current_steps": 56235, "total_steps": 61300, "loss": 0.3328, "lr": 1.033047431955317e-06, "epoch": 9.173735725938009, "percentage": 91.74, "elapsed_time": "7:40:00", "remaining_time": "0:41:25", "throughput": 4396.64, "total_tokens": 121347600} {"current_steps": 56240, "total_steps": 61300, "loss": 0.3201, "lr": 1.0310233869406437e-06, "epoch": 9.174551386623165, "percentage": 91.75, "elapsed_time": "7:40:02", "remaining_time": "0:41:23", "throughput": 4396.67, "total_tokens": 121358800} {"current_steps": 56245, "total_steps": 61300, "loss": 0.3107, "lr": 1.0290012849728358e-06, "epoch": 9.17536704730832, "percentage": 91.75, "elapsed_time": "7:40:04", "remaining_time": "0:41:20", "throughput": 4396.7, "total_tokens": 121369712} {"current_steps": 56250, "total_steps": 61300, "loss": 0.3452, "lr": 1.0269811262158092e-06, "epoch": 9.176182707993474, "percentage": 91.76, "elapsed_time": "7:40:07", "remaining_time": "0:41:18", "throughput": 4396.73, "total_tokens": 121380784} {"current_steps": 56255, "total_steps": 61300, "loss": 0.3191, "lr": 1.024962910833327e-06, "epoch": 9.17699836867863, "percentage": 91.77, "elapsed_time": "7:40:09", "remaining_time": "0:41:16", "throughput": 4396.76, "total_tokens": 121392752} {"current_steps": 56260, "total_steps": 61300, "loss": 0.3248, "lr": 1.022946638989003e-06, "epoch": 9.177814029363784, "percentage": 91.78, "elapsed_time": "7:40:11", "remaining_time": "0:41:13", "throughput": 4396.79, "total_tokens": 121402928} {"current_steps": 56265, "total_steps": 61300, "loss": 0.3474, "lr": 1.0209323108462816e-06, "epoch": 9.17862969004894, "percentage": 91.79, "elapsed_time": "7:40:13", "remaining_time": "0:41:11", "throughput": 4396.83, "total_tokens": 121413008} {"current_steps": 56270, "total_steps": 61300, "loss": 0.3667, "lr": 1.018919926568457e-06, "epoch": 9.179445350734095, "percentage": 91.79, "elapsed_time": "7:40:15", "remaining_time": "0:41:08", "throughput": 4396.86, "total_tokens": 121422896} {"current_steps": 56275, "total_steps": 61300, "loss": 0.3315, "lr": 1.0169094863186623e-06, "epoch": 9.18026101141925, "percentage": 91.8, "elapsed_time": "7:40:18", "remaining_time": "0:41:06", "throughput": 4396.9, "total_tokens": 121434512} {"current_steps": 56280, "total_steps": 61300, "loss": 0.3279, "lr": 1.0149009902598706e-06, "epoch": 9.181076672104405, "percentage": 91.81, "elapsed_time": "7:40:20", "remaining_time": "0:41:03", "throughput": 4396.93, "total_tokens": 121445840} {"current_steps": 56285, "total_steps": 61300, "loss": 0.3249, "lr": 1.0128944385549038e-06, "epoch": 9.181892332789559, "percentage": 91.82, "elapsed_time": "7:40:22", "remaining_time": "0:41:01", "throughput": 4396.97, "total_tokens": 121457264} {"current_steps": 56290, "total_steps": 61300, "loss": 0.2891, "lr": 1.0108898313664267e-06, "epoch": 9.182707993474715, "percentage": 91.83, "elapsed_time": "7:40:25", "remaining_time": "0:40:58", "throughput": 4397.0, "total_tokens": 121467728} {"current_steps": 56295, "total_steps": 61300, "loss": 0.3245, "lr": 1.0088871688569397e-06, "epoch": 9.18352365415987, "percentage": 91.84, "elapsed_time": "7:40:27", "remaining_time": "0:40:56", "throughput": 4397.04, "total_tokens": 121478608} {"current_steps": 56300, "total_steps": 61300, "loss": 0.3272, "lr": 1.006886451188785e-06, "epoch": 9.184339314845024, "percentage": 91.84, "elapsed_time": "7:40:29", "remaining_time": "0:40:53", "throughput": 4397.07, "total_tokens": 121489488} {"current_steps": 56305, "total_steps": 61300, "loss": 0.3262, "lr": 1.0048876785241578e-06, "epoch": 9.18515497553018, "percentage": 91.85, "elapsed_time": "7:40:31", "remaining_time": "0:40:51", "throughput": 4397.1, "total_tokens": 121500400} {"current_steps": 56310, "total_steps": 61300, "loss": 0.3637, "lr": 1.0028908510250846e-06, "epoch": 9.185970636215334, "percentage": 91.86, "elapsed_time": "7:40:34", "remaining_time": "0:40:48", "throughput": 4397.14, "total_tokens": 121511088} {"current_steps": 56315, "total_steps": 61300, "loss": 0.3158, "lr": 1.000895968853438e-06, "epoch": 9.18678629690049, "percentage": 91.87, "elapsed_time": "7:40:36", "remaining_time": "0:40:46", "throughput": 4397.17, "total_tokens": 121523088} {"current_steps": 56320, "total_steps": 61300, "loss": 0.2983, "lr": 9.989030321709336e-07, "epoch": 9.187601957585644, "percentage": 91.88, "elapsed_time": "7:40:38", "remaining_time": "0:40:43", "throughput": 4397.21, "total_tokens": 121533808} {"current_steps": 56325, "total_steps": 61300, "loss": 0.3186, "lr": 9.969120411391308e-07, "epoch": 9.1884176182708, "percentage": 91.88, "elapsed_time": "7:40:41", "remaining_time": "0:40:41", "throughput": 4397.24, "total_tokens": 121544240} {"current_steps": 56330, "total_steps": 61300, "loss": 0.35, "lr": 9.949229959194313e-07, "epoch": 9.189233278955955, "percentage": 91.89, "elapsed_time": "7:40:43", "remaining_time": "0:40:38", "throughput": 4397.28, "total_tokens": 121554992} {"current_steps": 56335, "total_steps": 61300, "loss": 0.3695, "lr": 9.929358966730696e-07, "epoch": 9.190048939641109, "percentage": 91.9, "elapsed_time": "7:40:45", "remaining_time": "0:40:36", "throughput": 4397.3, "total_tokens": 121565424} {"current_steps": 56340, "total_steps": 61300, "loss": 0.2855, "lr": 9.909507435611365e-07, "epoch": 9.190864600326265, "percentage": 91.91, "elapsed_time": "7:40:47", "remaining_time": "0:40:34", "throughput": 4397.34, "total_tokens": 121575504} {"current_steps": 56345, "total_steps": 61300, "loss": 0.3352, "lr": 9.889675367445589e-07, "epoch": 9.191680261011419, "percentage": 91.92, "elapsed_time": "7:40:49", "remaining_time": "0:40:31", "throughput": 4397.38, "total_tokens": 121586320} {"current_steps": 56350, "total_steps": 61300, "loss": 0.3104, "lr": 9.869862763841026e-07, "epoch": 9.192495921696574, "percentage": 91.92, "elapsed_time": "7:40:51", "remaining_time": "0:40:29", "throughput": 4397.41, "total_tokens": 121596976} {"current_steps": 56355, "total_steps": 61300, "loss": 0.3164, "lr": 9.85006962640378e-07, "epoch": 9.19331158238173, "percentage": 91.93, "elapsed_time": "7:40:54", "remaining_time": "0:40:26", "throughput": 4397.44, "total_tokens": 121607344} {"current_steps": 56360, "total_steps": 61300, "loss": 0.3464, "lr": 9.8302959567384e-07, "epoch": 9.194127243066884, "percentage": 91.94, "elapsed_time": "7:40:56", "remaining_time": "0:40:24", "throughput": 4397.47, "total_tokens": 121617424} {"current_steps": 56365, "total_steps": 61300, "loss": 0.3738, "lr": 9.810541756447855e-07, "epoch": 9.19494290375204, "percentage": 91.95, "elapsed_time": "7:40:58", "remaining_time": "0:40:21", "throughput": 4397.51, "total_tokens": 121629744} {"current_steps": 56370, "total_steps": 61300, "loss": 0.3022, "lr": 9.790807027133446e-07, "epoch": 9.195758564437194, "percentage": 91.96, "elapsed_time": "7:41:01", "remaining_time": "0:40:19", "throughput": 4397.54, "total_tokens": 121641008} {"current_steps": 56375, "total_steps": 61300, "loss": 0.3524, "lr": 9.77109177039509e-07, "epoch": 9.19657422512235, "percentage": 91.97, "elapsed_time": "7:41:03", "remaining_time": "0:40:16", "throughput": 4397.58, "total_tokens": 121652528} {"current_steps": 56380, "total_steps": 61300, "loss": 0.3295, "lr": 9.751395987830924e-07, "epoch": 9.197389885807505, "percentage": 91.97, "elapsed_time": "7:41:05", "remaining_time": "0:40:14", "throughput": 4397.62, "total_tokens": 121663856} {"current_steps": 56385, "total_steps": 61300, "loss": 0.3233, "lr": 9.731719681037616e-07, "epoch": 9.198205546492659, "percentage": 91.98, "elapsed_time": "7:41:08", "remaining_time": "0:40:11", "throughput": 4397.65, "total_tokens": 121676112} {"current_steps": 56390, "total_steps": 61300, "loss": 0.3745, "lr": 9.712062851610222e-07, "epoch": 9.199021207177815, "percentage": 91.99, "elapsed_time": "7:41:11", "remaining_time": "0:40:09", "throughput": 4397.68, "total_tokens": 121688400} {"current_steps": 56395, "total_steps": 61300, "loss": 0.3298, "lr": 9.692425501142217e-07, "epoch": 9.199836867862969, "percentage": 92.0, "elapsed_time": "7:41:13", "remaining_time": "0:40:06", "throughput": 4397.72, "total_tokens": 121698928} {"current_steps": 56400, "total_steps": 61300, "loss": 0.347, "lr": 9.672807631225521e-07, "epoch": 9.200652528548124, "percentage": 92.01, "elapsed_time": "7:41:15", "remaining_time": "0:40:04", "throughput": 4397.75, "total_tokens": 121708496} {"current_steps": 56405, "total_steps": 61300, "loss": 0.3108, "lr": 9.65320924345045e-07, "epoch": 9.201468189233278, "percentage": 92.01, "elapsed_time": "7:41:17", "remaining_time": "0:40:01", "throughput": 4397.79, "total_tokens": 121720240} {"current_steps": 56410, "total_steps": 61300, "loss": 0.3138, "lr": 9.633630339405731e-07, "epoch": 9.202283849918434, "percentage": 92.02, "elapsed_time": "7:41:20", "remaining_time": "0:39:59", "throughput": 4397.83, "total_tokens": 121732080} {"current_steps": 56415, "total_steps": 61300, "loss": 0.3073, "lr": 9.614070920678536e-07, "epoch": 9.20309951060359, "percentage": 92.03, "elapsed_time": "7:41:22", "remaining_time": "0:39:57", "throughput": 4397.86, "total_tokens": 121742096} {"current_steps": 56420, "total_steps": 61300, "loss": 0.3212, "lr": 9.59453098885446e-07, "epoch": 9.203915171288743, "percentage": 92.04, "elapsed_time": "7:41:24", "remaining_time": "0:39:54", "throughput": 4397.89, "total_tokens": 121752496} {"current_steps": 56425, "total_steps": 61300, "loss": 0.3398, "lr": 9.575010545517487e-07, "epoch": 9.2047308319739, "percentage": 92.05, "elapsed_time": "7:41:26", "remaining_time": "0:39:52", "throughput": 4397.92, "total_tokens": 121763024} {"current_steps": 56430, "total_steps": 61300, "loss": 0.3069, "lr": 9.5555095922501e-07, "epoch": 9.205546492659053, "percentage": 92.06, "elapsed_time": "7:41:28", "remaining_time": "0:39:49", "throughput": 4397.96, "total_tokens": 121774352} {"current_steps": 56435, "total_steps": 61300, "loss": 0.3169, "lr": 9.53602813063309e-07, "epoch": 9.206362153344209, "percentage": 92.06, "elapsed_time": "7:41:31", "remaining_time": "0:39:47", "throughput": 4398.0, "total_tokens": 121785296} {"current_steps": 56440, "total_steps": 61300, "loss": 0.3379, "lr": 9.516566162245749e-07, "epoch": 9.207177814029365, "percentage": 92.07, "elapsed_time": "7:41:33", "remaining_time": "0:39:44", "throughput": 4398.04, "total_tokens": 121796752} {"current_steps": 56445, "total_steps": 61300, "loss": 0.3179, "lr": 9.49712368866576e-07, "epoch": 9.207993474714518, "percentage": 92.08, "elapsed_time": "7:41:35", "remaining_time": "0:39:42", "throughput": 4398.08, "total_tokens": 121807440} {"current_steps": 56450, "total_steps": 61300, "loss": 0.3536, "lr": 9.477700711469223e-07, "epoch": 9.208809135399674, "percentage": 92.09, "elapsed_time": "7:41:37", "remaining_time": "0:39:39", "throughput": 4398.11, "total_tokens": 121818640} {"current_steps": 56455, "total_steps": 61300, "loss": 0.2967, "lr": 9.458297232230684e-07, "epoch": 9.209624796084828, "percentage": 92.1, "elapsed_time": "7:41:40", "remaining_time": "0:39:37", "throughput": 4398.13, "total_tokens": 121828560} {"current_steps": 56460, "total_steps": 61300, "loss": 0.3597, "lr": 9.438913252523024e-07, "epoch": 9.210440456769984, "percentage": 92.1, "elapsed_time": "7:41:42", "remaining_time": "0:39:34", "throughput": 4398.16, "total_tokens": 121839088} {"current_steps": 56465, "total_steps": 61300, "loss": 0.3622, "lr": 9.41954877391768e-07, "epoch": 9.21125611745514, "percentage": 92.11, "elapsed_time": "7:41:44", "remaining_time": "0:39:32", "throughput": 4398.2, "total_tokens": 121849744} {"current_steps": 56470, "total_steps": 61300, "loss": 0.345, "lr": 9.400203797984397e-07, "epoch": 9.212071778140293, "percentage": 92.12, "elapsed_time": "7:41:46", "remaining_time": "0:39:29", "throughput": 4398.23, "total_tokens": 121859696} {"current_steps": 56475, "total_steps": 61300, "loss": 0.3365, "lr": 9.380878326291392e-07, "epoch": 9.21288743882545, "percentage": 92.13, "elapsed_time": "7:41:48", "remaining_time": "0:39:27", "throughput": 4398.26, "total_tokens": 121869840} {"current_steps": 56480, "total_steps": 61300, "loss": 0.3047, "lr": 9.361572360405246e-07, "epoch": 9.213703099510603, "percentage": 92.14, "elapsed_time": "7:41:50", "remaining_time": "0:39:24", "throughput": 4398.3, "total_tokens": 121880432} {"current_steps": 56485, "total_steps": 61300, "loss": 0.316, "lr": 9.342285901891068e-07, "epoch": 9.214518760195759, "percentage": 92.15, "elapsed_time": "7:41:52", "remaining_time": "0:39:22", "throughput": 4398.32, "total_tokens": 121889264} {"current_steps": 56490, "total_steps": 61300, "loss": 0.3106, "lr": 9.323018952312273e-07, "epoch": 9.215334420880913, "percentage": 92.15, "elapsed_time": "7:41:54", "remaining_time": "0:39:19", "throughput": 4398.35, "total_tokens": 121900016} {"current_steps": 56495, "total_steps": 61300, "loss": 0.3078, "lr": 9.303771513230752e-07, "epoch": 9.216150081566068, "percentage": 92.16, "elapsed_time": "7:41:57", "remaining_time": "0:39:17", "throughput": 4398.38, "total_tokens": 121911312} {"current_steps": 56500, "total_steps": 61300, "loss": 0.3146, "lr": 9.284543586206784e-07, "epoch": 9.216965742251224, "percentage": 92.17, "elapsed_time": "7:41:59", "remaining_time": "0:39:14", "throughput": 4398.42, "total_tokens": 121923088} {"current_steps": 56505, "total_steps": 61300, "loss": 0.3519, "lr": 9.265335172799094e-07, "epoch": 9.217781402936378, "percentage": 92.18, "elapsed_time": "7:42:01", "remaining_time": "0:39:12", "throughput": 4398.45, "total_tokens": 121932720} {"current_steps": 56510, "total_steps": 61300, "loss": 0.3149, "lr": 9.246146274564798e-07, "epoch": 9.218597063621534, "percentage": 92.19, "elapsed_time": "7:42:03", "remaining_time": "0:39:09", "throughput": 4398.48, "total_tokens": 121943248} {"current_steps": 56515, "total_steps": 61300, "loss": 0.3435, "lr": 9.226976893059458e-07, "epoch": 9.219412724306688, "percentage": 92.19, "elapsed_time": "7:42:06", "remaining_time": "0:39:07", "throughput": 4398.51, "total_tokens": 121953712} {"current_steps": 56520, "total_steps": 61300, "loss": 0.2998, "lr": 9.207827029837052e-07, "epoch": 9.220228384991843, "percentage": 92.2, "elapsed_time": "7:42:08", "remaining_time": "0:39:05", "throughput": 4398.55, "total_tokens": 121965456} {"current_steps": 56525, "total_steps": 61300, "loss": 0.3289, "lr": 9.188696686449949e-07, "epoch": 9.221044045676999, "percentage": 92.21, "elapsed_time": "7:42:10", "remaining_time": "0:39:02", "throughput": 4398.58, "total_tokens": 121975120} {"current_steps": 56530, "total_steps": 61300, "loss": 0.3455, "lr": 9.169585864448965e-07, "epoch": 9.221859706362153, "percentage": 92.22, "elapsed_time": "7:42:13", "remaining_time": "0:39:00", "throughput": 4398.62, "total_tokens": 121987344} {"current_steps": 56535, "total_steps": 61300, "loss": 0.3058, "lr": 9.150494565383305e-07, "epoch": 9.222675367047309, "percentage": 92.23, "elapsed_time": "7:42:15", "remaining_time": "0:38:57", "throughput": 4398.65, "total_tokens": 121998448} {"current_steps": 56540, "total_steps": 61300, "loss": 0.2912, "lr": 9.13142279080062e-07, "epoch": 9.223491027732463, "percentage": 92.23, "elapsed_time": "7:42:17", "remaining_time": "0:38:55", "throughput": 4398.68, "total_tokens": 122009104} {"current_steps": 56545, "total_steps": 61300, "loss": 0.3107, "lr": 9.112370542246978e-07, "epoch": 9.224306688417618, "percentage": 92.24, "elapsed_time": "7:42:19", "remaining_time": "0:38:52", "throughput": 4398.72, "total_tokens": 122019952} {"current_steps": 56550, "total_steps": 61300, "loss": 0.3198, "lr": 9.093337821266784e-07, "epoch": 9.225122349102774, "percentage": 92.25, "elapsed_time": "7:42:22", "remaining_time": "0:38:50", "throughput": 4398.76, "total_tokens": 122031280} {"current_steps": 56555, "total_steps": 61300, "loss": 0.3191, "lr": 9.074324629403025e-07, "epoch": 9.225938009787928, "percentage": 92.26, "elapsed_time": "7:42:24", "remaining_time": "0:38:47", "throughput": 4398.79, "total_tokens": 122041584} {"current_steps": 56560, "total_steps": 61300, "loss": 0.322, "lr": 9.055330968196912e-07, "epoch": 9.226753670473084, "percentage": 92.27, "elapsed_time": "7:42:26", "remaining_time": "0:38:45", "throughput": 4398.82, "total_tokens": 122051312} {"current_steps": 56565, "total_steps": 61300, "loss": 0.3506, "lr": 9.036356839188243e-07, "epoch": 9.227569331158238, "percentage": 92.28, "elapsed_time": "7:42:28", "remaining_time": "0:38:42", "throughput": 4398.85, "total_tokens": 122061552} {"current_steps": 56570, "total_steps": 61300, "loss": 0.3185, "lr": 9.017402243915091e-07, "epoch": 9.228384991843393, "percentage": 92.28, "elapsed_time": "7:42:30", "remaining_time": "0:38:40", "throughput": 4398.88, "total_tokens": 122071184} {"current_steps": 56575, "total_steps": 61300, "loss": 0.3532, "lr": 8.998467183914061e-07, "epoch": 9.229200652528547, "percentage": 92.29, "elapsed_time": "7:42:33", "remaining_time": "0:38:37", "throughput": 4398.92, "total_tokens": 122083344} {"current_steps": 56580, "total_steps": 61300, "loss": 0.3405, "lr": 8.97955166072012e-07, "epoch": 9.230016313213703, "percentage": 92.3, "elapsed_time": "7:42:35", "remaining_time": "0:38:35", "throughput": 4398.96, "total_tokens": 122094832} {"current_steps": 56585, "total_steps": 61300, "loss": 0.3087, "lr": 8.960655675866653e-07, "epoch": 9.230831973898859, "percentage": 92.31, "elapsed_time": "7:42:37", "remaining_time": "0:38:32", "throughput": 4399.0, "total_tokens": 122106032} {"current_steps": 56590, "total_steps": 61300, "loss": 0.3406, "lr": 8.941779230885433e-07, "epoch": 9.231647634584013, "percentage": 92.32, "elapsed_time": "7:42:39", "remaining_time": "0:38:30", "throughput": 4399.03, "total_tokens": 122116304} {"current_steps": 56595, "total_steps": 61300, "loss": 0.3422, "lr": 8.92292232730671e-07, "epoch": 9.232463295269168, "percentage": 92.32, "elapsed_time": "7:42:42", "remaining_time": "0:38:28", "throughput": 4399.06, "total_tokens": 122128176} {"current_steps": 56600, "total_steps": 61300, "loss": 0.331, "lr": 8.904084966659121e-07, "epoch": 9.233278955954322, "percentage": 92.33, "elapsed_time": "7:42:44", "remaining_time": "0:38:25", "throughput": 4399.1, "total_tokens": 122139696} {"current_steps": 56605, "total_steps": 61300, "loss": 0.3411, "lr": 8.885267150469723e-07, "epoch": 9.234094616639478, "percentage": 92.34, "elapsed_time": "7:42:47", "remaining_time": "0:38:23", "throughput": 4399.14, "total_tokens": 122151024} {"current_steps": 56610, "total_steps": 61300, "loss": 0.3257, "lr": 8.866468880263961e-07, "epoch": 9.234910277324634, "percentage": 92.35, "elapsed_time": "7:42:49", "remaining_time": "0:38:20", "throughput": 4399.17, "total_tokens": 122161648} {"current_steps": 56615, "total_steps": 61300, "loss": 0.3199, "lr": 8.847690157565758e-07, "epoch": 9.235725938009788, "percentage": 92.36, "elapsed_time": "7:42:51", "remaining_time": "0:38:18", "throughput": 4399.21, "total_tokens": 122172656} {"current_steps": 56620, "total_steps": 61300, "loss": 0.3428, "lr": 8.828930983897366e-07, "epoch": 9.236541598694943, "percentage": 92.37, "elapsed_time": "7:42:53", "remaining_time": "0:38:15", "throughput": 4399.24, "total_tokens": 122183056} {"current_steps": 56625, "total_steps": 61300, "loss": 0.3228, "lr": 8.810191360779513e-07, "epoch": 9.237357259380097, "percentage": 92.37, "elapsed_time": "7:42:55", "remaining_time": "0:38:13", "throughput": 4399.28, "total_tokens": 122194224} {"current_steps": 56630, "total_steps": 61300, "loss": 0.3323, "lr": 8.791471289731346e-07, "epoch": 9.238172920065253, "percentage": 92.38, "elapsed_time": "7:42:58", "remaining_time": "0:38:10", "throughput": 4399.31, "total_tokens": 122204784} {"current_steps": 56635, "total_steps": 61300, "loss": 0.3065, "lr": 8.7727707722704e-07, "epoch": 9.238988580750409, "percentage": 92.39, "elapsed_time": "7:43:00", "remaining_time": "0:38:08", "throughput": 4399.34, "total_tokens": 122215280} {"current_steps": 56640, "total_steps": 61300, "loss": 0.3841, "lr": 8.75408980991263e-07, "epoch": 9.239804241435563, "percentage": 92.4, "elapsed_time": "7:43:02", "remaining_time": "0:38:05", "throughput": 4399.37, "total_tokens": 122226128} {"current_steps": 56645, "total_steps": 61300, "loss": 0.3103, "lr": 8.735428404172408e-07, "epoch": 9.240619902120718, "percentage": 92.41, "elapsed_time": "7:43:05", "remaining_time": "0:38:03", "throughput": 4399.4, "total_tokens": 122237552} {"current_steps": 56650, "total_steps": 61300, "loss": 0.3404, "lr": 8.716786556562495e-07, "epoch": 9.241435562805872, "percentage": 92.41, "elapsed_time": "7:43:07", "remaining_time": "0:38:00", "throughput": 4399.44, "total_tokens": 122248880} {"current_steps": 56655, "total_steps": 61300, "loss": 0.3461, "lr": 8.698164268594155e-07, "epoch": 9.242251223491028, "percentage": 92.42, "elapsed_time": "7:43:09", "remaining_time": "0:37:58", "throughput": 4399.48, "total_tokens": 122259760} {"current_steps": 56660, "total_steps": 61300, "loss": 0.3278, "lr": 8.679561541776959e-07, "epoch": 9.243066884176184, "percentage": 92.43, "elapsed_time": "7:43:11", "remaining_time": "0:37:55", "throughput": 4399.52, "total_tokens": 122271120} {"current_steps": 56665, "total_steps": 61300, "loss": 0.3154, "lr": 8.660978377618951e-07, "epoch": 9.243882544861338, "percentage": 92.44, "elapsed_time": "7:43:14", "remaining_time": "0:37:53", "throughput": 4399.55, "total_tokens": 122281424} {"current_steps": 56670, "total_steps": 61300, "loss": 0.3018, "lr": 8.64241477762659e-07, "epoch": 9.244698205546493, "percentage": 92.45, "elapsed_time": "7:43:16", "remaining_time": "0:37:50", "throughput": 4399.59, "total_tokens": 122292784} {"current_steps": 56675, "total_steps": 61300, "loss": 0.3006, "lr": 8.62387074330473e-07, "epoch": 9.245513866231647, "percentage": 92.46, "elapsed_time": "7:43:18", "remaining_time": "0:37:48", "throughput": 4399.62, "total_tokens": 122302992} {"current_steps": 56680, "total_steps": 61300, "loss": 0.3168, "lr": 8.605346276156611e-07, "epoch": 9.246329526916803, "percentage": 92.46, "elapsed_time": "7:43:20", "remaining_time": "0:37:46", "throughput": 4399.65, "total_tokens": 122314320} {"current_steps": 56685, "total_steps": 61300, "loss": 0.3262, "lr": 8.586841377683951e-07, "epoch": 9.247145187601957, "percentage": 92.47, "elapsed_time": "7:43:23", "remaining_time": "0:37:43", "throughput": 4399.68, "total_tokens": 122324848} {"current_steps": 56690, "total_steps": 61300, "loss": 0.3457, "lr": 8.568356049386827e-07, "epoch": 9.247960848287113, "percentage": 92.48, "elapsed_time": "7:43:25", "remaining_time": "0:37:41", "throughput": 4399.72, "total_tokens": 122335760} {"current_steps": 56695, "total_steps": 61300, "loss": 0.3387, "lr": 8.549890292763819e-07, "epoch": 9.248776508972268, "percentage": 92.49, "elapsed_time": "7:43:27", "remaining_time": "0:37:38", "throughput": 4399.75, "total_tokens": 122346416} {"current_steps": 56700, "total_steps": 61300, "loss": 0.3307, "lr": 8.531444109311781e-07, "epoch": 9.249592169657422, "percentage": 92.5, "elapsed_time": "7:43:30", "remaining_time": "0:37:36", "throughput": 4399.79, "total_tokens": 122358608} {"current_steps": 56705, "total_steps": 61300, "loss": 0.3246, "lr": 8.513017500526105e-07, "epoch": 9.250407830342578, "percentage": 92.5, "elapsed_time": "7:43:32", "remaining_time": "0:37:33", "throughput": 4399.82, "total_tokens": 122369264} {"current_steps": 56710, "total_steps": 61300, "loss": 0.362, "lr": 8.49461046790051e-07, "epoch": 9.251223491027732, "percentage": 92.51, "elapsed_time": "7:43:34", "remaining_time": "0:37:31", "throughput": 4399.86, "total_tokens": 122380528} {"current_steps": 56715, "total_steps": 61300, "loss": 0.308, "lr": 8.476223012927193e-07, "epoch": 9.252039151712887, "percentage": 92.52, "elapsed_time": "7:43:36", "remaining_time": "0:37:28", "throughput": 4399.9, "total_tokens": 122391856} {"current_steps": 56720, "total_steps": 61300, "loss": 0.3124, "lr": 8.457855137096682e-07, "epoch": 9.252854812398043, "percentage": 92.53, "elapsed_time": "7:43:39", "remaining_time": "0:37:26", "throughput": 4399.93, "total_tokens": 122402672} {"current_steps": 56725, "total_steps": 61300, "loss": 0.3, "lr": 8.439506841898037e-07, "epoch": 9.253670473083197, "percentage": 92.54, "elapsed_time": "7:43:41", "remaining_time": "0:37:23", "throughput": 4399.96, "total_tokens": 122412368} {"current_steps": 56730, "total_steps": 61300, "loss": 0.3461, "lr": 8.421178128818624e-07, "epoch": 9.254486133768353, "percentage": 92.54, "elapsed_time": "7:43:43", "remaining_time": "0:37:21", "throughput": 4400.0, "total_tokens": 122423248} {"current_steps": 56735, "total_steps": 61300, "loss": 0.3106, "lr": 8.402868999344283e-07, "epoch": 9.255301794453507, "percentage": 92.55, "elapsed_time": "7:43:45", "remaining_time": "0:37:18", "throughput": 4400.03, "total_tokens": 122433040} {"current_steps": 56740, "total_steps": 61300, "loss": 0.3128, "lr": 8.384579454959185e-07, "epoch": 9.256117455138662, "percentage": 92.56, "elapsed_time": "7:43:47", "remaining_time": "0:37:16", "throughput": 4400.06, "total_tokens": 122442928} {"current_steps": 56745, "total_steps": 61300, "loss": 0.2965, "lr": 8.366309497146063e-07, "epoch": 9.256933115823816, "percentage": 92.57, "elapsed_time": "7:43:49", "remaining_time": "0:37:13", "throughput": 4400.09, "total_tokens": 122453488} {"current_steps": 56750, "total_steps": 61300, "loss": 0.3089, "lr": 8.348059127385926e-07, "epoch": 9.257748776508972, "percentage": 92.58, "elapsed_time": "7:43:51", "remaining_time": "0:37:11", "throughput": 4400.13, "total_tokens": 122463632} {"current_steps": 56755, "total_steps": 61300, "loss": 0.3038, "lr": 8.329828347158231e-07, "epoch": 9.258564437194128, "percentage": 92.59, "elapsed_time": "7:43:54", "remaining_time": "0:37:08", "throughput": 4400.17, "total_tokens": 122474736} {"current_steps": 56760, "total_steps": 61300, "loss": 0.3063, "lr": 8.311617157940904e-07, "epoch": 9.259380097879282, "percentage": 92.59, "elapsed_time": "7:43:56", "remaining_time": "0:37:06", "throughput": 4400.2, "total_tokens": 122485776} {"current_steps": 56765, "total_steps": 61300, "loss": 0.3067, "lr": 8.293425561210183e-07, "epoch": 9.260195758564437, "percentage": 92.6, "elapsed_time": "7:43:58", "remaining_time": "0:37:04", "throughput": 4400.23, "total_tokens": 122496176} {"current_steps": 56770, "total_steps": 61300, "loss": 0.3175, "lr": 8.275253558440776e-07, "epoch": 9.261011419249591, "percentage": 92.61, "elapsed_time": "7:44:00", "remaining_time": "0:37:01", "throughput": 4400.27, "total_tokens": 122507760} {"current_steps": 56775, "total_steps": 61300, "loss": 0.3486, "lr": 8.257101151105839e-07, "epoch": 9.261827079934747, "percentage": 92.62, "elapsed_time": "7:44:03", "remaining_time": "0:36:59", "throughput": 4400.3, "total_tokens": 122518768} {"current_steps": 56780, "total_steps": 61300, "loss": 0.3122, "lr": 8.23896834067689e-07, "epoch": 9.262642740619903, "percentage": 92.63, "elapsed_time": "7:44:05", "remaining_time": "0:36:56", "throughput": 4400.34, "total_tokens": 122531216} {"current_steps": 56785, "total_steps": 61300, "loss": 0.3486, "lr": 8.220855128623805e-07, "epoch": 9.263458401305057, "percentage": 92.63, "elapsed_time": "7:44:07", "remaining_time": "0:36:54", "throughput": 4400.37, "total_tokens": 122541552} {"current_steps": 56790, "total_steps": 61300, "loss": 0.3232, "lr": 8.202761516415025e-07, "epoch": 9.264274061990212, "percentage": 92.64, "elapsed_time": "7:44:10", "remaining_time": "0:36:51", "throughput": 4400.41, "total_tokens": 122553712} {"current_steps": 56795, "total_steps": 61300, "loss": 0.3214, "lr": 8.184687505517236e-07, "epoch": 9.265089722675366, "percentage": 92.65, "elapsed_time": "7:44:12", "remaining_time": "0:36:49", "throughput": 4400.45, "total_tokens": 122564976} {"current_steps": 56800, "total_steps": 61300, "loss": 0.3642, "lr": 8.166633097395626e-07, "epoch": 9.265905383360522, "percentage": 92.66, "elapsed_time": "7:44:15", "remaining_time": "0:36:46", "throughput": 4400.48, "total_tokens": 122576272} {"current_steps": 56805, "total_steps": 61300, "loss": 0.3485, "lr": 8.148598293513804e-07, "epoch": 9.266721044045678, "percentage": 92.67, "elapsed_time": "7:44:17", "remaining_time": "0:36:44", "throughput": 4400.51, "total_tokens": 122586576} {"current_steps": 56810, "total_steps": 61300, "loss": 0.3182, "lr": 8.130583095333739e-07, "epoch": 9.267536704730832, "percentage": 92.68, "elapsed_time": "7:44:19", "remaining_time": "0:36:41", "throughput": 4400.55, "total_tokens": 122598000} {"current_steps": 56815, "total_steps": 61300, "loss": 0.2921, "lr": 8.112587504315844e-07, "epoch": 9.268352365415987, "percentage": 92.68, "elapsed_time": "7:44:21", "remaining_time": "0:36:39", "throughput": 4400.57, "total_tokens": 122606896} {"current_steps": 56820, "total_steps": 61300, "loss": 0.3351, "lr": 8.094611521918927e-07, "epoch": 9.269168026101141, "percentage": 92.69, "elapsed_time": "7:44:23", "remaining_time": "0:36:36", "throughput": 4400.6, "total_tokens": 122617200} {"current_steps": 56825, "total_steps": 61300, "loss": 0.3475, "lr": 8.076655149600237e-07, "epoch": 9.269983686786297, "percentage": 92.7, "elapsed_time": "7:44:25", "remaining_time": "0:36:34", "throughput": 4400.62, "total_tokens": 122626512} {"current_steps": 56830, "total_steps": 61300, "loss": 0.3196, "lr": 8.058718388815362e-07, "epoch": 9.270799347471453, "percentage": 92.71, "elapsed_time": "7:44:27", "remaining_time": "0:36:31", "throughput": 4400.65, "total_tokens": 122636848} {"current_steps": 56835, "total_steps": 61300, "loss": 0.351, "lr": 8.040801241018386e-07, "epoch": 9.271615008156607, "percentage": 92.72, "elapsed_time": "7:44:29", "remaining_time": "0:36:29", "throughput": 4400.69, "total_tokens": 122646928} {"current_steps": 56840, "total_steps": 61300, "loss": 0.2939, "lr": 8.022903707661761e-07, "epoch": 9.272430668841762, "percentage": 92.72, "elapsed_time": "7:44:32", "remaining_time": "0:36:27", "throughput": 4400.71, "total_tokens": 122656752} {"current_steps": 56845, "total_steps": 61300, "loss": 0.3139, "lr": 8.005025790196325e-07, "epoch": 9.273246329526916, "percentage": 92.73, "elapsed_time": "7:44:34", "remaining_time": "0:36:24", "throughput": 4400.75, "total_tokens": 122668656} {"current_steps": 56850, "total_steps": 61300, "loss": 0.2938, "lr": 7.987167490071362e-07, "epoch": 9.274061990212072, "percentage": 92.74, "elapsed_time": "7:44:36", "remaining_time": "0:36:22", "throughput": 4400.78, "total_tokens": 122679728} {"current_steps": 56855, "total_steps": 61300, "loss": 0.3259, "lr": 7.969328808734577e-07, "epoch": 9.274877650897226, "percentage": 92.75, "elapsed_time": "7:44:39", "remaining_time": "0:36:19", "throughput": 4400.82, "total_tokens": 122691536} {"current_steps": 56860, "total_steps": 61300, "loss": 0.3446, "lr": 7.951509747632063e-07, "epoch": 9.275693311582382, "percentage": 92.76, "elapsed_time": "7:44:41", "remaining_time": "0:36:17", "throughput": 4400.84, "total_tokens": 122701488} {"current_steps": 56865, "total_steps": 61300, "loss": 0.3193, "lr": 7.933710308208275e-07, "epoch": 9.276508972267537, "percentage": 92.77, "elapsed_time": "7:44:43", "remaining_time": "0:36:14", "throughput": 4400.87, "total_tokens": 122712784} {"current_steps": 56870, "total_steps": 61300, "loss": 0.3409, "lr": 7.915930491906198e-07, "epoch": 9.277324632952691, "percentage": 92.77, "elapsed_time": "7:44:45", "remaining_time": "0:36:12", "throughput": 4400.9, "total_tokens": 122723184} {"current_steps": 56875, "total_steps": 61300, "loss": 0.3262, "lr": 7.898170300167096e-07, "epoch": 9.278140293637847, "percentage": 92.78, "elapsed_time": "7:44:48", "remaining_time": "0:36:09", "throughput": 4400.94, "total_tokens": 122733808} {"current_steps": 56880, "total_steps": 61300, "loss": 0.3282, "lr": 7.880429734430706e-07, "epoch": 9.278955954323001, "percentage": 92.79, "elapsed_time": "7:44:50", "remaining_time": "0:36:07", "throughput": 4400.97, "total_tokens": 122745552} {"current_steps": 56885, "total_steps": 61300, "loss": 0.3428, "lr": 7.862708796135182e-07, "epoch": 9.279771615008157, "percentage": 92.8, "elapsed_time": "7:44:52", "remaining_time": "0:36:04", "throughput": 4401.0, "total_tokens": 122755632} {"current_steps": 56890, "total_steps": 61300, "loss": 0.3845, "lr": 7.845007486717099e-07, "epoch": 9.280587275693312, "percentage": 92.81, "elapsed_time": "7:44:55", "remaining_time": "0:36:02", "throughput": 4401.04, "total_tokens": 122767696} {"current_steps": 56895, "total_steps": 61300, "loss": 0.3454, "lr": 7.827325807611391e-07, "epoch": 9.281402936378466, "percentage": 92.81, "elapsed_time": "7:44:57", "remaining_time": "0:35:59", "throughput": 4401.08, "total_tokens": 122779376} {"current_steps": 56900, "total_steps": 61300, "loss": 0.304, "lr": 7.80966376025144e-07, "epoch": 9.282218597063622, "percentage": 92.82, "elapsed_time": "7:44:59", "remaining_time": "0:35:57", "throughput": 4401.12, "total_tokens": 122790832} {"current_steps": 56905, "total_steps": 61300, "loss": 0.3587, "lr": 7.792021346068989e-07, "epoch": 9.283034257748776, "percentage": 92.83, "elapsed_time": "7:45:02", "remaining_time": "0:35:54", "throughput": 4401.15, "total_tokens": 122801456} {"current_steps": 56910, "total_steps": 61300, "loss": 0.3553, "lr": 7.774398566494201e-07, "epoch": 9.283849918433932, "percentage": 92.84, "elapsed_time": "7:45:04", "remaining_time": "0:35:52", "throughput": 4401.19, "total_tokens": 122813520} {"current_steps": 56915, "total_steps": 61300, "loss": 0.3401, "lr": 7.756795422955737e-07, "epoch": 9.284665579119087, "percentage": 92.85, "elapsed_time": "7:45:06", "remaining_time": "0:35:50", "throughput": 4401.22, "total_tokens": 122823344} {"current_steps": 56920, "total_steps": 61300, "loss": 0.3078, "lr": 7.739211916880595e-07, "epoch": 9.285481239804241, "percentage": 92.85, "elapsed_time": "7:45:08", "remaining_time": "0:35:47", "throughput": 4401.26, "total_tokens": 122834128} {"current_steps": 56925, "total_steps": 61300, "loss": 0.3595, "lr": 7.721648049694108e-07, "epoch": 9.286296900489397, "percentage": 92.86, "elapsed_time": "7:45:11", "remaining_time": "0:35:45", "throughput": 4401.29, "total_tokens": 122845456} {"current_steps": 56930, "total_steps": 61300, "loss": 0.3255, "lr": 7.704103822820164e-07, "epoch": 9.28711256117455, "percentage": 92.87, "elapsed_time": "7:45:13", "remaining_time": "0:35:42", "throughput": 4401.33, "total_tokens": 122856272} {"current_steps": 56935, "total_steps": 61300, "loss": 0.3373, "lr": 7.686579237680957e-07, "epoch": 9.287928221859707, "percentage": 92.88, "elapsed_time": "7:45:15", "remaining_time": "0:35:40", "throughput": 4401.36, "total_tokens": 122866544} {"current_steps": 56940, "total_steps": 61300, "loss": 0.3159, "lr": 7.669074295697132e-07, "epoch": 9.28874388254486, "percentage": 92.89, "elapsed_time": "7:45:17", "remaining_time": "0:35:37", "throughput": 4401.38, "total_tokens": 122876432} {"current_steps": 56945, "total_steps": 61300, "loss": 0.3502, "lr": 7.651588998287717e-07, "epoch": 9.289559543230016, "percentage": 92.9, "elapsed_time": "7:45:20", "remaining_time": "0:35:35", "throughput": 4401.42, "total_tokens": 122888432} {"current_steps": 56950, "total_steps": 61300, "loss": 0.3076, "lr": 7.634123346870165e-07, "epoch": 9.290375203915172, "percentage": 92.9, "elapsed_time": "7:45:22", "remaining_time": "0:35:32", "throughput": 4401.46, "total_tokens": 122900016} {"current_steps": 56955, "total_steps": 61300, "loss": 0.3557, "lr": 7.616677342860312e-07, "epoch": 9.291190864600326, "percentage": 92.91, "elapsed_time": "7:45:24", "remaining_time": "0:35:30", "throughput": 4401.48, "total_tokens": 122910096} {"current_steps": 56960, "total_steps": 61300, "loss": 0.3568, "lr": 7.599250987672446e-07, "epoch": 9.292006525285482, "percentage": 92.92, "elapsed_time": "7:45:26", "remaining_time": "0:35:27", "throughput": 4401.52, "total_tokens": 122920336} {"current_steps": 56965, "total_steps": 61300, "loss": 0.3024, "lr": 7.581844282719213e-07, "epoch": 9.292822185970635, "percentage": 92.93, "elapsed_time": "7:45:29", "remaining_time": "0:35:25", "throughput": 4401.55, "total_tokens": 122931632} {"current_steps": 56970, "total_steps": 61300, "loss": 0.3076, "lr": 7.564457229411709e-07, "epoch": 9.293637846655791, "percentage": 92.94, "elapsed_time": "7:45:31", "remaining_time": "0:35:22", "throughput": 4401.59, "total_tokens": 122943728} {"current_steps": 56975, "total_steps": 61300, "loss": 0.3432, "lr": 7.547089829159415e-07, "epoch": 9.294453507340947, "percentage": 92.94, "elapsed_time": "7:45:33", "remaining_time": "0:35:20", "throughput": 4401.62, "total_tokens": 122953264} {"current_steps": 56980, "total_steps": 61300, "loss": 0.3302, "lr": 7.529742083370206e-07, "epoch": 9.2952691680261, "percentage": 92.95, "elapsed_time": "7:45:36", "remaining_time": "0:35:18", "throughput": 4401.66, "total_tokens": 122965296} {"current_steps": 56985, "total_steps": 61300, "loss": 0.3416, "lr": 7.512413993450373e-07, "epoch": 9.296084828711257, "percentage": 92.96, "elapsed_time": "7:45:38", "remaining_time": "0:35:15", "throughput": 4401.68, "total_tokens": 122974384} {"current_steps": 56990, "total_steps": 61300, "loss": 0.3533, "lr": 7.495105560804627e-07, "epoch": 9.29690048939641, "percentage": 92.97, "elapsed_time": "7:45:40", "remaining_time": "0:35:13", "throughput": 4401.72, "total_tokens": 122985296} {"current_steps": 56995, "total_steps": 61300, "loss": 0.3515, "lr": 7.477816786836122e-07, "epoch": 9.297716150081566, "percentage": 92.98, "elapsed_time": "7:45:42", "remaining_time": "0:35:10", "throughput": 4401.75, "total_tokens": 122996272} {"current_steps": 57000, "total_steps": 61300, "loss": 0.303, "lr": 7.460547672946294e-07, "epoch": 9.298531810766722, "percentage": 92.99, "elapsed_time": "7:45:44", "remaining_time": "0:35:08", "throughput": 4401.78, "total_tokens": 123007440} {"current_steps": 57005, "total_steps": 61300, "loss": 0.2931, "lr": 7.443298220535106e-07, "epoch": 9.299347471451876, "percentage": 92.99, "elapsed_time": "7:45:47", "remaining_time": "0:35:05", "throughput": 4401.81, "total_tokens": 123018096} {"current_steps": 57010, "total_steps": 61300, "loss": 0.3488, "lr": 7.426068431000882e-07, "epoch": 9.300163132137031, "percentage": 93.0, "elapsed_time": "7:45:49", "remaining_time": "0:35:03", "throughput": 4401.84, "total_tokens": 123029072} {"current_steps": 57015, "total_steps": 61300, "loss": 0.3649, "lr": 7.408858305740368e-07, "epoch": 9.300978792822185, "percentage": 93.01, "elapsed_time": "7:45:51", "remaining_time": "0:35:00", "throughput": 4401.88, "total_tokens": 123040816} {"current_steps": 57020, "total_steps": 61300, "loss": 0.3111, "lr": 7.391667846148697e-07, "epoch": 9.301794453507341, "percentage": 93.02, "elapsed_time": "7:45:54", "remaining_time": "0:34:58", "throughput": 4401.91, "total_tokens": 123051376} {"current_steps": 57025, "total_steps": 61300, "loss": 0.3017, "lr": 7.374497053619423e-07, "epoch": 9.302610114192497, "percentage": 93.03, "elapsed_time": "7:45:56", "remaining_time": "0:34:55", "throughput": 4401.94, "total_tokens": 123061232} {"current_steps": 57030, "total_steps": 61300, "loss": 0.3048, "lr": 7.357345929544485e-07, "epoch": 9.30342577487765, "percentage": 93.03, "elapsed_time": "7:45:58", "remaining_time": "0:34:53", "throughput": 4401.97, "total_tokens": 123071632} {"current_steps": 57035, "total_steps": 61300, "loss": 0.3417, "lr": 7.340214475314244e-07, "epoch": 9.304241435562806, "percentage": 93.04, "elapsed_time": "7:46:00", "remaining_time": "0:34:50", "throughput": 4402.02, "total_tokens": 123083600} {"current_steps": 57040, "total_steps": 61300, "loss": 0.3161, "lr": 7.323102692317452e-07, "epoch": 9.30505709624796, "percentage": 93.05, "elapsed_time": "7:46:02", "remaining_time": "0:34:48", "throughput": 4402.05, "total_tokens": 123093392} {"current_steps": 57045, "total_steps": 61300, "loss": 0.3332, "lr": 7.306010581941275e-07, "epoch": 9.305872756933116, "percentage": 93.06, "elapsed_time": "7:46:05", "remaining_time": "0:34:45", "throughput": 4402.08, "total_tokens": 123104784} {"current_steps": 57050, "total_steps": 61300, "loss": 0.3278, "lr": 7.288938145571328e-07, "epoch": 9.30668841761827, "percentage": 93.07, "elapsed_time": "7:46:07", "remaining_time": "0:34:43", "throughput": 4402.11, "total_tokens": 123115344} {"current_steps": 57055, "total_steps": 61300, "loss": 0.3512, "lr": 7.271885384591503e-07, "epoch": 9.307504078303426, "percentage": 93.08, "elapsed_time": "7:46:09", "remaining_time": "0:34:40", "throughput": 4402.14, "total_tokens": 123125520} {"current_steps": 57060, "total_steps": 61300, "loss": 0.3653, "lr": 7.25485230038428e-07, "epoch": 9.308319738988581, "percentage": 93.08, "elapsed_time": "7:46:11", "remaining_time": "0:34:38", "throughput": 4402.18, "total_tokens": 123136016} {"current_steps": 57065, "total_steps": 61300, "loss": 0.3247, "lr": 7.237838894330412e-07, "epoch": 9.309135399673735, "percentage": 93.09, "elapsed_time": "7:46:14", "remaining_time": "0:34:36", "throughput": 4402.21, "total_tokens": 123147536} {"current_steps": 57070, "total_steps": 61300, "loss": 0.3464, "lr": 7.220845167809076e-07, "epoch": 9.309951060358891, "percentage": 93.1, "elapsed_time": "7:46:16", "remaining_time": "0:34:33", "throughput": 4402.24, "total_tokens": 123157904} {"current_steps": 57075, "total_steps": 61300, "loss": 0.3535, "lr": 7.203871122197891e-07, "epoch": 9.310766721044045, "percentage": 93.11, "elapsed_time": "7:46:18", "remaining_time": "0:34:31", "throughput": 4402.27, "total_tokens": 123168720} {"current_steps": 57080, "total_steps": 61300, "loss": 0.3178, "lr": 7.186916758872841e-07, "epoch": 9.3115823817292, "percentage": 93.12, "elapsed_time": "7:46:20", "remaining_time": "0:34:28", "throughput": 4402.3, "total_tokens": 123180144} {"current_steps": 57085, "total_steps": 61300, "loss": 0.3049, "lr": 7.169982079208326e-07, "epoch": 9.312398042414356, "percentage": 93.12, "elapsed_time": "7:46:23", "remaining_time": "0:34:26", "throughput": 4402.33, "total_tokens": 123190896} {"current_steps": 57090, "total_steps": 61300, "loss": 0.3188, "lr": 7.153067084577192e-07, "epoch": 9.31321370309951, "percentage": 93.13, "elapsed_time": "7:46:25", "remaining_time": "0:34:23", "throughput": 4402.36, "total_tokens": 123201424} {"current_steps": 57095, "total_steps": 61300, "loss": 0.3451, "lr": 7.13617177635062e-07, "epoch": 9.314029363784666, "percentage": 93.14, "elapsed_time": "7:46:27", "remaining_time": "0:34:21", "throughput": 4402.39, "total_tokens": 123211536} {"current_steps": 57100, "total_steps": 61300, "loss": 0.3182, "lr": 7.119296155898236e-07, "epoch": 9.31484502446982, "percentage": 93.15, "elapsed_time": "7:46:29", "remaining_time": "0:34:18", "throughput": 4402.42, "total_tokens": 123222896} {"current_steps": 57105, "total_steps": 61300, "loss": 0.3334, "lr": 7.102440224588086e-07, "epoch": 9.315660685154976, "percentage": 93.16, "elapsed_time": "7:46:32", "remaining_time": "0:34:16", "throughput": 4402.45, "total_tokens": 123235280} {"current_steps": 57110, "total_steps": 61300, "loss": 0.3498, "lr": 7.085603983786576e-07, "epoch": 9.31647634584013, "percentage": 93.16, "elapsed_time": "7:46:34", "remaining_time": "0:34:13", "throughput": 4402.5, "total_tokens": 123246416} {"current_steps": 57115, "total_steps": 61300, "loss": 0.3286, "lr": 7.068787434858532e-07, "epoch": 9.317292006525285, "percentage": 93.17, "elapsed_time": "7:46:36", "remaining_time": "0:34:11", "throughput": 4402.53, "total_tokens": 123257200} {"current_steps": 57120, "total_steps": 61300, "loss": 0.2937, "lr": 7.051990579167195e-07, "epoch": 9.318107667210441, "percentage": 93.18, "elapsed_time": "7:46:39", "remaining_time": "0:34:08", "throughput": 4402.56, "total_tokens": 123268816} {"current_steps": 57125, "total_steps": 61300, "loss": 0.3352, "lr": 7.035213418074227e-07, "epoch": 9.318923327895595, "percentage": 93.19, "elapsed_time": "7:46:41", "remaining_time": "0:34:06", "throughput": 4402.59, "total_tokens": 123279408} {"current_steps": 57130, "total_steps": 61300, "loss": 0.3222, "lr": 7.018455952939651e-07, "epoch": 9.31973898858075, "percentage": 93.2, "elapsed_time": "7:46:43", "remaining_time": "0:34:04", "throughput": 4402.62, "total_tokens": 123289232} {"current_steps": 57135, "total_steps": 61300, "loss": 0.3258, "lr": 7.001718185121908e-07, "epoch": 9.320554649265905, "percentage": 93.21, "elapsed_time": "7:46:45", "remaining_time": "0:34:01", "throughput": 4402.66, "total_tokens": 123299984} {"current_steps": 57140, "total_steps": 61300, "loss": 0.3237, "lr": 6.98500011597783e-07, "epoch": 9.32137030995106, "percentage": 93.21, "elapsed_time": "7:46:48", "remaining_time": "0:33:59", "throughput": 4402.69, "total_tokens": 123310768} {"current_steps": 57145, "total_steps": 61300, "loss": 0.3194, "lr": 6.96830174686272e-07, "epoch": 9.322185970636216, "percentage": 93.22, "elapsed_time": "7:46:50", "remaining_time": "0:33:56", "throughput": 4402.71, "total_tokens": 123321232} {"current_steps": 57150, "total_steps": 61300, "loss": 0.3426, "lr": 6.951623079130192e-07, "epoch": 9.32300163132137, "percentage": 93.23, "elapsed_time": "7:46:52", "remaining_time": "0:33:54", "throughput": 4402.75, "total_tokens": 123332432} {"current_steps": 57155, "total_steps": 61300, "loss": 0.3323, "lr": 6.934964114132303e-07, "epoch": 9.323817292006526, "percentage": 93.24, "elapsed_time": "7:46:54", "remaining_time": "0:33:51", "throughput": 4402.79, "total_tokens": 123344240} {"current_steps": 57160, "total_steps": 61300, "loss": 0.3483, "lr": 6.918324853219527e-07, "epoch": 9.32463295269168, "percentage": 93.25, "elapsed_time": "7:46:57", "remaining_time": "0:33:49", "throughput": 4402.83, "total_tokens": 123354672} {"current_steps": 57165, "total_steps": 61300, "loss": 0.3447, "lr": 6.901705297740729e-07, "epoch": 9.325448613376835, "percentage": 93.25, "elapsed_time": "7:46:59", "remaining_time": "0:33:46", "throughput": 4402.86, "total_tokens": 123365168} {"current_steps": 57170, "total_steps": 61300, "loss": 0.3137, "lr": 6.885105449043138e-07, "epoch": 9.326264274061991, "percentage": 93.26, "elapsed_time": "7:47:01", "remaining_time": "0:33:44", "throughput": 4402.89, "total_tokens": 123375696} {"current_steps": 57175, "total_steps": 61300, "loss": 0.3303, "lr": 6.868525308472484e-07, "epoch": 9.327079934747145, "percentage": 93.27, "elapsed_time": "7:47:03", "remaining_time": "0:33:41", "throughput": 4402.93, "total_tokens": 123387344} {"current_steps": 57180, "total_steps": 61300, "loss": 0.3377, "lr": 6.851964877372802e-07, "epoch": 9.3278955954323, "percentage": 93.28, "elapsed_time": "7:47:06", "remaining_time": "0:33:39", "throughput": 4402.96, "total_tokens": 123398992} {"current_steps": 57185, "total_steps": 61300, "loss": 0.3411, "lr": 6.835424157086573e-07, "epoch": 9.328711256117455, "percentage": 93.29, "elapsed_time": "7:47:08", "remaining_time": "0:33:36", "throughput": 4402.99, "total_tokens": 123409168} {"current_steps": 57190, "total_steps": 61300, "loss": 0.3488, "lr": 6.818903148954642e-07, "epoch": 9.32952691680261, "percentage": 93.3, "elapsed_time": "7:47:11", "remaining_time": "0:33:34", "throughput": 4403.03, "total_tokens": 123421488} {"current_steps": 57195, "total_steps": 61300, "loss": 0.3421, "lr": 6.802401854316298e-07, "epoch": 9.330342577487766, "percentage": 93.3, "elapsed_time": "7:47:13", "remaining_time": "0:33:32", "throughput": 4403.07, "total_tokens": 123432816} {"current_steps": 57200, "total_steps": 61300, "loss": 0.3286, "lr": 6.78592027450925e-07, "epoch": 9.33115823817292, "percentage": 93.31, "elapsed_time": "7:47:15", "remaining_time": "0:33:29", "throughput": 4403.11, "total_tokens": 123444048} {"current_steps": 57205, "total_steps": 61300, "loss": 0.3077, "lr": 6.769458410869595e-07, "epoch": 9.331973898858076, "percentage": 93.32, "elapsed_time": "7:47:17", "remaining_time": "0:33:27", "throughput": 4403.14, "total_tokens": 123454320} {"current_steps": 57210, "total_steps": 61300, "loss": 0.3339, "lr": 6.753016264731738e-07, "epoch": 9.33278955954323, "percentage": 93.33, "elapsed_time": "7:47:20", "remaining_time": "0:33:24", "throughput": 4403.17, "total_tokens": 123465424} {"current_steps": 57215, "total_steps": 61300, "loss": 0.3508, "lr": 6.736593837428639e-07, "epoch": 9.333605220228385, "percentage": 93.34, "elapsed_time": "7:47:22", "remaining_time": "0:33:22", "throughput": 4403.21, "total_tokens": 123475856} {"current_steps": 57220, "total_steps": 61300, "loss": 0.3444, "lr": 6.720191130291514e-07, "epoch": 9.33442088091354, "percentage": 93.34, "elapsed_time": "7:47:24", "remaining_time": "0:33:19", "throughput": 4403.24, "total_tokens": 123484816} {"current_steps": 57225, "total_steps": 61300, "loss": 0.349, "lr": 6.703808144650076e-07, "epoch": 9.335236541598695, "percentage": 93.35, "elapsed_time": "7:47:26", "remaining_time": "0:33:17", "throughput": 4403.27, "total_tokens": 123495920} {"current_steps": 57230, "total_steps": 61300, "loss": 0.3323, "lr": 6.687444881832455e-07, "epoch": 9.33605220228385, "percentage": 93.36, "elapsed_time": "7:47:28", "remaining_time": "0:33:14", "throughput": 4403.3, "total_tokens": 123507344} {"current_steps": 57235, "total_steps": 61300, "loss": 0.3293, "lr": 6.67110134316512e-07, "epoch": 9.336867862969005, "percentage": 93.37, "elapsed_time": "7:47:30", "remaining_time": "0:33:12", "throughput": 4403.34, "total_tokens": 123517808} {"current_steps": 57240, "total_steps": 61300, "loss": 0.308, "lr": 6.654777529972928e-07, "epoch": 9.33768352365416, "percentage": 93.38, "elapsed_time": "7:47:33", "remaining_time": "0:33:09", "throughput": 4403.38, "total_tokens": 123529456} {"current_steps": 57245, "total_steps": 61300, "loss": 0.3699, "lr": 6.638473443579179e-07, "epoch": 9.338499184339314, "percentage": 93.38, "elapsed_time": "7:47:35", "remaining_time": "0:33:07", "throughput": 4403.4, "total_tokens": 123538960} {"current_steps": 57250, "total_steps": 61300, "loss": 0.3631, "lr": 6.622189085305597e-07, "epoch": 9.33931484502447, "percentage": 93.39, "elapsed_time": "7:47:37", "remaining_time": "0:33:04", "throughput": 4403.44, "total_tokens": 123549200} {"current_steps": 57255, "total_steps": 61300, "loss": 0.3182, "lr": 6.605924456472262e-07, "epoch": 9.340130505709626, "percentage": 93.4, "elapsed_time": "7:47:39", "remaining_time": "0:33:02", "throughput": 4403.47, "total_tokens": 123560176} {"current_steps": 57260, "total_steps": 61300, "loss": 0.3639, "lr": 6.589679558397648e-07, "epoch": 9.34094616639478, "percentage": 93.41, "elapsed_time": "7:47:42", "remaining_time": "0:32:59", "throughput": 4403.5, "total_tokens": 123571280} {"current_steps": 57265, "total_steps": 61300, "loss": 0.2802, "lr": 6.573454392398648e-07, "epoch": 9.341761827079935, "percentage": 93.42, "elapsed_time": "7:47:44", "remaining_time": "0:32:57", "throughput": 4403.53, "total_tokens": 123581296} {"current_steps": 57270, "total_steps": 61300, "loss": 0.3414, "lr": 6.557248959790596e-07, "epoch": 9.34257748776509, "percentage": 93.43, "elapsed_time": "7:47:46", "remaining_time": "0:32:54", "throughput": 4403.57, "total_tokens": 123592016} {"current_steps": 57275, "total_steps": 61300, "loss": 0.3717, "lr": 6.541063261887137e-07, "epoch": 9.343393148450245, "percentage": 93.43, "elapsed_time": "7:47:48", "remaining_time": "0:32:52", "throughput": 4403.6, "total_tokens": 123602992} {"current_steps": 57280, "total_steps": 61300, "loss": 0.3562, "lr": 6.524897300000388e-07, "epoch": 9.3442088091354, "percentage": 93.44, "elapsed_time": "7:47:50", "remaining_time": "0:32:50", "throughput": 4403.64, "total_tokens": 123614384} {"current_steps": 57285, "total_steps": 61300, "loss": 0.3377, "lr": 6.508751075440856e-07, "epoch": 9.345024469820554, "percentage": 93.45, "elapsed_time": "7:47:53", "remaining_time": "0:32:47", "throughput": 4403.68, "total_tokens": 123625744} {"current_steps": 57290, "total_steps": 61300, "loss": 0.3294, "lr": 6.49262458951741e-07, "epoch": 9.34584013050571, "percentage": 93.46, "elapsed_time": "7:47:55", "remaining_time": "0:32:45", "throughput": 4403.71, "total_tokens": 123636816} {"current_steps": 57295, "total_steps": 61300, "loss": 0.3402, "lr": 6.476517843537395e-07, "epoch": 9.346655791190864, "percentage": 93.47, "elapsed_time": "7:47:58", "remaining_time": "0:32:42", "throughput": 4403.75, "total_tokens": 123648656} {"current_steps": 57300, "total_steps": 61300, "loss": 0.3209, "lr": 6.46043083880643e-07, "epoch": 9.34747145187602, "percentage": 93.47, "elapsed_time": "7:48:00", "remaining_time": "0:32:40", "throughput": 4403.78, "total_tokens": 123658672} {"current_steps": 57305, "total_steps": 61300, "loss": 0.2943, "lr": 6.44436357662867e-07, "epoch": 9.348287112561174, "percentage": 93.48, "elapsed_time": "7:48:02", "remaining_time": "0:32:37", "throughput": 4403.82, "total_tokens": 123669968} {"current_steps": 57310, "total_steps": 61300, "loss": 0.3298, "lr": 6.428316058306571e-07, "epoch": 9.34910277324633, "percentage": 93.49, "elapsed_time": "7:48:04", "remaining_time": "0:32:35", "throughput": 4403.85, "total_tokens": 123680880} {"current_steps": 57315, "total_steps": 61300, "loss": 0.3524, "lr": 6.412288285141066e-07, "epoch": 9.349918433931485, "percentage": 93.5, "elapsed_time": "7:48:06", "remaining_time": "0:32:32", "throughput": 4403.89, "total_tokens": 123691536} {"current_steps": 57320, "total_steps": 61300, "loss": 0.3497, "lr": 6.396280258431391e-07, "epoch": 9.350734094616639, "percentage": 93.51, "elapsed_time": "7:48:09", "remaining_time": "0:32:30", "throughput": 4403.92, "total_tokens": 123701904} {"current_steps": 57325, "total_steps": 61300, "loss": 0.3105, "lr": 6.38029197947529e-07, "epoch": 9.351549755301795, "percentage": 93.52, "elapsed_time": "7:48:11", "remaining_time": "0:32:27", "throughput": 4403.95, "total_tokens": 123712528} {"current_steps": 57330, "total_steps": 61300, "loss": 0.3198, "lr": 6.364323449568804e-07, "epoch": 9.352365415986949, "percentage": 93.52, "elapsed_time": "7:48:13", "remaining_time": "0:32:25", "throughput": 4403.98, "total_tokens": 123723184} {"current_steps": 57335, "total_steps": 61300, "loss": 0.32, "lr": 6.348374670006485e-07, "epoch": 9.353181076672104, "percentage": 93.53, "elapsed_time": "7:48:15", "remaining_time": "0:32:22", "throughput": 4404.01, "total_tokens": 123733968} {"current_steps": 57340, "total_steps": 61300, "loss": 0.3081, "lr": 6.332445642081214e-07, "epoch": 9.35399673735726, "percentage": 93.54, "elapsed_time": "7:48:17", "remaining_time": "0:32:20", "throughput": 4404.03, "total_tokens": 123743120} {"current_steps": 57345, "total_steps": 61300, "loss": 0.3249, "lr": 6.316536367084236e-07, "epoch": 9.354812398042414, "percentage": 93.55, "elapsed_time": "7:48:20", "remaining_time": "0:32:18", "throughput": 4404.08, "total_tokens": 123754992} {"current_steps": 57350, "total_steps": 61300, "loss": 0.3332, "lr": 6.300646846305241e-07, "epoch": 9.35562805872757, "percentage": 93.56, "elapsed_time": "7:48:22", "remaining_time": "0:32:15", "throughput": 4404.11, "total_tokens": 123765488} {"current_steps": 57355, "total_steps": 61300, "loss": 0.3287, "lr": 6.28477708103234e-07, "epoch": 9.356443719412724, "percentage": 93.56, "elapsed_time": "7:48:24", "remaining_time": "0:32:13", "throughput": 4404.14, "total_tokens": 123776944} {"current_steps": 57360, "total_steps": 61300, "loss": 0.3468, "lr": 6.268927072552028e-07, "epoch": 9.35725938009788, "percentage": 93.57, "elapsed_time": "7:48:27", "remaining_time": "0:32:10", "throughput": 4404.19, "total_tokens": 123789168} {"current_steps": 57365, "total_steps": 61300, "loss": 0.3482, "lr": 6.253096822149113e-07, "epoch": 9.358075040783035, "percentage": 93.58, "elapsed_time": "7:48:29", "remaining_time": "0:32:08", "throughput": 4404.22, "total_tokens": 123799536} {"current_steps": 57370, "total_steps": 61300, "loss": 0.347, "lr": 6.237286331106984e-07, "epoch": 9.358890701468189, "percentage": 93.59, "elapsed_time": "7:48:31", "remaining_time": "0:32:05", "throughput": 4404.25, "total_tokens": 123811536} {"current_steps": 57375, "total_steps": 61300, "loss": 0.3307, "lr": 6.221495600707227e-07, "epoch": 9.359706362153345, "percentage": 93.6, "elapsed_time": "7:48:33", "remaining_time": "0:32:03", "throughput": 4404.28, "total_tokens": 123820848} {"current_steps": 57380, "total_steps": 61300, "loss": 0.3351, "lr": 6.205724632229987e-07, "epoch": 9.360522022838499, "percentage": 93.61, "elapsed_time": "7:48:36", "remaining_time": "0:32:00", "throughput": 4404.32, "total_tokens": 123832112} {"current_steps": 57385, "total_steps": 61300, "loss": 0.3317, "lr": 6.18997342695371e-07, "epoch": 9.361337683523654, "percentage": 93.61, "elapsed_time": "7:48:38", "remaining_time": "0:31:58", "throughput": 4404.34, "total_tokens": 123842544} {"current_steps": 57390, "total_steps": 61300, "loss": 0.3231, "lr": 6.174241986155238e-07, "epoch": 9.362153344208808, "percentage": 93.62, "elapsed_time": "7:48:40", "remaining_time": "0:31:55", "throughput": 4404.38, "total_tokens": 123852816} {"current_steps": 57395, "total_steps": 61300, "loss": 0.3385, "lr": 6.158530311109884e-07, "epoch": 9.362969004893964, "percentage": 93.63, "elapsed_time": "7:48:42", "remaining_time": "0:31:53", "throughput": 4404.41, "total_tokens": 123863312} {"current_steps": 57400, "total_steps": 61300, "loss": 0.3209, "lr": 6.142838403091322e-07, "epoch": 9.36378466557912, "percentage": 93.64, "elapsed_time": "7:48:44", "remaining_time": "0:31:50", "throughput": 4404.44, "total_tokens": 123873936} {"current_steps": 57405, "total_steps": 61300, "loss": 0.312, "lr": 6.127166263371592e-07, "epoch": 9.364600326264274, "percentage": 93.65, "elapsed_time": "7:48:47", "remaining_time": "0:31:48", "throughput": 4404.48, "total_tokens": 123885648} {"current_steps": 57410, "total_steps": 61300, "loss": 0.3237, "lr": 6.111513893221149e-07, "epoch": 9.36541598694943, "percentage": 93.65, "elapsed_time": "7:48:49", "remaining_time": "0:31:46", "throughput": 4404.51, "total_tokens": 123896528} {"current_steps": 57415, "total_steps": 61300, "loss": 0.3254, "lr": 6.095881293908867e-07, "epoch": 9.366231647634583, "percentage": 93.66, "elapsed_time": "7:48:51", "remaining_time": "0:31:43", "throughput": 4404.54, "total_tokens": 123907728} {"current_steps": 57420, "total_steps": 61300, "loss": 0.3586, "lr": 6.080268466702011e-07, "epoch": 9.367047308319739, "percentage": 93.67, "elapsed_time": "7:48:54", "remaining_time": "0:31:41", "throughput": 4404.57, "total_tokens": 123918128} {"current_steps": 57425, "total_steps": 61300, "loss": 0.3368, "lr": 6.064675412866233e-07, "epoch": 9.367862969004895, "percentage": 93.68, "elapsed_time": "7:48:56", "remaining_time": "0:31:38", "throughput": 4404.6, "total_tokens": 123929392} {"current_steps": 57430, "total_steps": 61300, "loss": 0.3576, "lr": 6.049102133665552e-07, "epoch": 9.368678629690049, "percentage": 93.69, "elapsed_time": "7:48:58", "remaining_time": "0:31:36", "throughput": 4404.63, "total_tokens": 123940688} {"current_steps": 57435, "total_steps": 61300, "loss": 0.3382, "lr": 6.033548630362457e-07, "epoch": 9.369494290375204, "percentage": 93.69, "elapsed_time": "7:49:00", "remaining_time": "0:31:33", "throughput": 4404.66, "total_tokens": 123950704} {"current_steps": 57440, "total_steps": 61300, "loss": 0.3309, "lr": 6.018014904217801e-07, "epoch": 9.370309951060358, "percentage": 93.7, "elapsed_time": "7:49:03", "remaining_time": "0:31:31", "throughput": 4404.7, "total_tokens": 123961552} {"current_steps": 57445, "total_steps": 61300, "loss": 0.3455, "lr": 6.002500956490798e-07, "epoch": 9.371125611745514, "percentage": 93.71, "elapsed_time": "7:49:05", "remaining_time": "0:31:28", "throughput": 4404.74, "total_tokens": 123971408} {"current_steps": 57450, "total_steps": 61300, "loss": 0.3444, "lr": 5.987006788439109e-07, "epoch": 9.37194127243067, "percentage": 93.72, "elapsed_time": "7:49:07", "remaining_time": "0:31:26", "throughput": 4404.77, "total_tokens": 123981264} {"current_steps": 57455, "total_steps": 61300, "loss": 0.3196, "lr": 5.971532401318758e-07, "epoch": 9.372756933115824, "percentage": 93.73, "elapsed_time": "7:49:09", "remaining_time": "0:31:23", "throughput": 4404.81, "total_tokens": 123992944} {"current_steps": 57460, "total_steps": 61300, "loss": 0.3204, "lr": 5.956077796384185e-07, "epoch": 9.37357259380098, "percentage": 93.74, "elapsed_time": "7:49:11", "remaining_time": "0:31:21", "throughput": 4404.85, "total_tokens": 124004464} {"current_steps": 57465, "total_steps": 61300, "loss": 0.322, "lr": 5.940642974888195e-07, "epoch": 9.374388254486133, "percentage": 93.74, "elapsed_time": "7:49:14", "remaining_time": "0:31:18", "throughput": 4404.89, "total_tokens": 124017072} {"current_steps": 57470, "total_steps": 61300, "loss": 0.3402, "lr": 5.925227938082034e-07, "epoch": 9.375203915171289, "percentage": 93.75, "elapsed_time": "7:49:16", "remaining_time": "0:31:16", "throughput": 4404.92, "total_tokens": 124027792} {"current_steps": 57475, "total_steps": 61300, "loss": 0.3097, "lr": 5.909832687215317e-07, "epoch": 9.376019575856443, "percentage": 93.76, "elapsed_time": "7:49:19", "remaining_time": "0:31:14", "throughput": 4404.95, "total_tokens": 124039440} {"current_steps": 57480, "total_steps": 61300, "loss": 0.3038, "lr": 5.894457223536071e-07, "epoch": 9.376835236541599, "percentage": 93.77, "elapsed_time": "7:49:21", "remaining_time": "0:31:11", "throughput": 4404.98, "total_tokens": 124050608} {"current_steps": 57485, "total_steps": 61300, "loss": 0.3253, "lr": 5.879101548290716e-07, "epoch": 9.377650897226754, "percentage": 93.78, "elapsed_time": "7:49:23", "remaining_time": "0:31:09", "throughput": 4405.01, "total_tokens": 124061296} {"current_steps": 57490, "total_steps": 61300, "loss": 0.3438, "lr": 5.863765662724036e-07, "epoch": 9.378466557911908, "percentage": 93.78, "elapsed_time": "7:49:25", "remaining_time": "0:31:06", "throughput": 4405.04, "total_tokens": 124071920} {"current_steps": 57495, "total_steps": 61300, "loss": 0.3344, "lr": 5.848449568079228e-07, "epoch": 9.379282218597064, "percentage": 93.79, "elapsed_time": "7:49:28", "remaining_time": "0:31:04", "throughput": 4405.08, "total_tokens": 124082608} {"current_steps": 57500, "total_steps": 61300, "loss": 0.3188, "lr": 5.83315326559794e-07, "epoch": 9.380097879282218, "percentage": 93.8, "elapsed_time": "7:49:30", "remaining_time": "0:31:01", "throughput": 4405.12, "total_tokens": 124094416} {"current_steps": 57505, "total_steps": 61300, "loss": 0.3128, "lr": 5.817876756520125e-07, "epoch": 9.380913539967374, "percentage": 93.81, "elapsed_time": "7:49:32", "remaining_time": "0:30:59", "throughput": 4405.15, "total_tokens": 124105168} {"current_steps": 57510, "total_steps": 61300, "loss": 0.3072, "lr": 5.80262004208415e-07, "epoch": 9.38172920065253, "percentage": 93.82, "elapsed_time": "7:49:34", "remaining_time": "0:30:56", "throughput": 4405.18, "total_tokens": 124114992} {"current_steps": 57515, "total_steps": 61300, "loss": 0.3563, "lr": 5.787383123526891e-07, "epoch": 9.382544861337683, "percentage": 93.83, "elapsed_time": "7:49:37", "remaining_time": "0:30:54", "throughput": 4405.21, "total_tokens": 124125936} {"current_steps": 57520, "total_steps": 61300, "loss": 0.3523, "lr": 5.772166002083467e-07, "epoch": 9.383360522022839, "percentage": 93.83, "elapsed_time": "7:49:39", "remaining_time": "0:30:51", "throughput": 4405.25, "total_tokens": 124137616} {"current_steps": 57525, "total_steps": 61300, "loss": 0.2962, "lr": 5.756968678987451e-07, "epoch": 9.384176182707993, "percentage": 93.84, "elapsed_time": "7:49:41", "remaining_time": "0:30:49", "throughput": 4405.28, "total_tokens": 124147856} {"current_steps": 57530, "total_steps": 61300, "loss": 0.3467, "lr": 5.741791155470854e-07, "epoch": 9.384991843393149, "percentage": 93.85, "elapsed_time": "7:49:44", "remaining_time": "0:30:46", "throughput": 4405.32, "total_tokens": 124159824} {"current_steps": 57535, "total_steps": 61300, "loss": 0.3304, "lr": 5.726633432764e-07, "epoch": 9.385807504078304, "percentage": 93.86, "elapsed_time": "7:49:45", "remaining_time": "0:30:44", "throughput": 4405.35, "total_tokens": 124169168} {"current_steps": 57540, "total_steps": 61300, "loss": 0.3274, "lr": 5.711495512095682e-07, "epoch": 9.386623164763458, "percentage": 93.87, "elapsed_time": "7:49:48", "remaining_time": "0:30:41", "throughput": 4405.39, "total_tokens": 124179952} {"current_steps": 57545, "total_steps": 61300, "loss": 0.3179, "lr": 5.696377394693003e-07, "epoch": 9.387438825448614, "percentage": 93.87, "elapsed_time": "7:49:50", "remaining_time": "0:30:39", "throughput": 4405.42, "total_tokens": 124189648} {"current_steps": 57550, "total_steps": 61300, "loss": 0.3364, "lr": 5.681279081781593e-07, "epoch": 9.388254486133768, "percentage": 93.88, "elapsed_time": "7:49:52", "remaining_time": "0:30:37", "throughput": 4405.45, "total_tokens": 124200336} {"current_steps": 57555, "total_steps": 61300, "loss": 0.3529, "lr": 5.66620057458539e-07, "epoch": 9.389070146818923, "percentage": 93.89, "elapsed_time": "7:49:54", "remaining_time": "0:30:34", "throughput": 4405.47, "total_tokens": 124209264} {"current_steps": 57560, "total_steps": 61300, "loss": 0.3061, "lr": 5.651141874326666e-07, "epoch": 9.38988580750408, "percentage": 93.9, "elapsed_time": "7:49:56", "remaining_time": "0:30:32", "throughput": 4405.51, "total_tokens": 124219184} {"current_steps": 57565, "total_steps": 61300, "loss": 0.3186, "lr": 5.636102982226221e-07, "epoch": 9.390701468189233, "percentage": 93.91, "elapsed_time": "7:49:58", "remaining_time": "0:30:29", "throughput": 4405.54, "total_tokens": 124230800} {"current_steps": 57570, "total_steps": 61300, "loss": 0.3869, "lr": 5.621083899503138e-07, "epoch": 9.391517128874389, "percentage": 93.92, "elapsed_time": "7:50:01", "remaining_time": "0:30:27", "throughput": 4405.58, "total_tokens": 124242224} {"current_steps": 57575, "total_steps": 61300, "loss": 0.3209, "lr": 5.606084627374969e-07, "epoch": 9.392332789559543, "percentage": 93.92, "elapsed_time": "7:50:03", "remaining_time": "0:30:24", "throughput": 4405.61, "total_tokens": 124252592} {"current_steps": 57580, "total_steps": 61300, "loss": 0.3835, "lr": 5.591105167057631e-07, "epoch": 9.393148450244698, "percentage": 93.93, "elapsed_time": "7:50:05", "remaining_time": "0:30:22", "throughput": 4405.65, "total_tokens": 124263760} {"current_steps": 57585, "total_steps": 61300, "loss": 0.2823, "lr": 5.576145519765402e-07, "epoch": 9.393964110929852, "percentage": 93.94, "elapsed_time": "7:50:07", "remaining_time": "0:30:19", "throughput": 4405.68, "total_tokens": 124274704} {"current_steps": 57590, "total_steps": 61300, "loss": 0.3241, "lr": 5.561205686711035e-07, "epoch": 9.394779771615008, "percentage": 93.95, "elapsed_time": "7:50:09", "remaining_time": "0:30:17", "throughput": 4405.71, "total_tokens": 124284784} {"current_steps": 57595, "total_steps": 61300, "loss": 0.3243, "lr": 5.546285669105589e-07, "epoch": 9.395595432300164, "percentage": 93.96, "elapsed_time": "7:50:11", "remaining_time": "0:30:14", "throughput": 4405.74, "total_tokens": 124294512} {"current_steps": 57600, "total_steps": 61300, "loss": 0.3109, "lr": 5.531385468158595e-07, "epoch": 9.396411092985318, "percentage": 93.96, "elapsed_time": "7:50:14", "remaining_time": "0:30:12", "throughput": 4405.78, "total_tokens": 124306096} {"current_steps": 57605, "total_steps": 61300, "loss": 0.3218, "lr": 5.516505085077895e-07, "epoch": 9.397226753670473, "percentage": 93.97, "elapsed_time": "7:50:16", "remaining_time": "0:30:09", "throughput": 4405.82, "total_tokens": 124317104} {"current_steps": 57610, "total_steps": 61300, "loss": 0.2978, "lr": 5.501644521069799e-07, "epoch": 9.398042414355627, "percentage": 93.98, "elapsed_time": "7:50:18", "remaining_time": "0:30:07", "throughput": 4405.86, "total_tokens": 124327792} {"current_steps": 57615, "total_steps": 61300, "loss": 0.352, "lr": 5.486803777338956e-07, "epoch": 9.398858075040783, "percentage": 93.99, "elapsed_time": "7:50:21", "remaining_time": "0:30:05", "throughput": 4405.89, "total_tokens": 124340112} {"current_steps": 57620, "total_steps": 61300, "loss": 0.2924, "lr": 5.471982855088459e-07, "epoch": 9.399673735725939, "percentage": 94.0, "elapsed_time": "7:50:23", "remaining_time": "0:30:02", "throughput": 4405.92, "total_tokens": 124351184} {"current_steps": 57625, "total_steps": 61300, "loss": 0.317, "lr": 5.457181755519763e-07, "epoch": 9.400489396411093, "percentage": 94.0, "elapsed_time": "7:50:25", "remaining_time": "0:30:00", "throughput": 4405.95, "total_tokens": 124361456} {"current_steps": 57630, "total_steps": 61300, "loss": 0.3403, "lr": 5.442400479832715e-07, "epoch": 9.401305057096248, "percentage": 94.01, "elapsed_time": "7:50:28", "remaining_time": "0:29:57", "throughput": 4405.98, "total_tokens": 124372848} {"current_steps": 57635, "total_steps": 61300, "loss": 0.3296, "lr": 5.427639029225551e-07, "epoch": 9.402120717781402, "percentage": 94.02, "elapsed_time": "7:50:30", "remaining_time": "0:29:55", "throughput": 4406.01, "total_tokens": 124383664} {"current_steps": 57640, "total_steps": 61300, "loss": 0.3115, "lr": 5.412897404894896e-07, "epoch": 9.402936378466558, "percentage": 94.03, "elapsed_time": "7:50:32", "remaining_time": "0:29:52", "throughput": 4406.04, "total_tokens": 124394160} {"current_steps": 57645, "total_steps": 61300, "loss": 0.3269, "lr": 5.398175608035821e-07, "epoch": 9.403752039151712, "percentage": 94.04, "elapsed_time": "7:50:35", "remaining_time": "0:29:50", "throughput": 4406.07, "total_tokens": 124405584} {"current_steps": 57650, "total_steps": 61300, "loss": 0.3287, "lr": 5.38347363984168e-07, "epoch": 9.404567699836868, "percentage": 94.05, "elapsed_time": "7:50:37", "remaining_time": "0:29:47", "throughput": 4406.11, "total_tokens": 124416560} {"current_steps": 57655, "total_steps": 61300, "loss": 0.3226, "lr": 5.368791501504378e-07, "epoch": 9.405383360522023, "percentage": 94.05, "elapsed_time": "7:50:39", "remaining_time": "0:29:45", "throughput": 4406.14, "total_tokens": 124426864} {"current_steps": 57660, "total_steps": 61300, "loss": 0.3515, "lr": 5.354129194214103e-07, "epoch": 9.406199021207177, "percentage": 94.06, "elapsed_time": "7:50:41", "remaining_time": "0:29:42", "throughput": 4406.17, "total_tokens": 124438384} {"current_steps": 57665, "total_steps": 61300, "loss": 0.3509, "lr": 5.339486719159404e-07, "epoch": 9.407014681892333, "percentage": 94.07, "elapsed_time": "7:50:44", "remaining_time": "0:29:40", "throughput": 4406.21, "total_tokens": 124449936} {"current_steps": 57670, "total_steps": 61300, "loss": 0.345, "lr": 5.324864077527331e-07, "epoch": 9.407830342577487, "percentage": 94.08, "elapsed_time": "7:50:46", "remaining_time": "0:29:37", "throughput": 4406.25, "total_tokens": 124461040} {"current_steps": 57675, "total_steps": 61300, "loss": 0.324, "lr": 5.310261270503214e-07, "epoch": 9.408646003262643, "percentage": 94.09, "elapsed_time": "7:50:48", "remaining_time": "0:29:35", "throughput": 4406.28, "total_tokens": 124472144} {"current_steps": 57680, "total_steps": 61300, "loss": 0.314, "lr": 5.295678299270884e-07, "epoch": 9.409461663947798, "percentage": 94.09, "elapsed_time": "7:50:51", "remaining_time": "0:29:33", "throughput": 4406.31, "total_tokens": 124483792} {"current_steps": 57685, "total_steps": 61300, "loss": 0.3306, "lr": 5.281115165012479e-07, "epoch": 9.410277324632952, "percentage": 94.1, "elapsed_time": "7:50:53", "remaining_time": "0:29:30", "throughput": 4406.35, "total_tokens": 124495152} {"current_steps": 57690, "total_steps": 61300, "loss": 0.3063, "lr": 5.266571868908582e-07, "epoch": 9.411092985318108, "percentage": 94.11, "elapsed_time": "7:50:55", "remaining_time": "0:29:28", "throughput": 4406.38, "total_tokens": 124505360} {"current_steps": 57695, "total_steps": 61300, "loss": 0.3366, "lr": 5.252048412138111e-07, "epoch": 9.411908646003262, "percentage": 94.12, "elapsed_time": "7:50:57", "remaining_time": "0:29:25", "throughput": 4406.41, "total_tokens": 124515184} {"current_steps": 57700, "total_steps": 61300, "loss": 0.3143, "lr": 5.237544795878457e-07, "epoch": 9.412724306688418, "percentage": 94.13, "elapsed_time": "7:51:00", "remaining_time": "0:29:23", "throughput": 4406.44, "total_tokens": 124526416} {"current_steps": 57705, "total_steps": 61300, "loss": 0.3557, "lr": 5.22306102130532e-07, "epoch": 9.413539967373573, "percentage": 94.14, "elapsed_time": "7:51:02", "remaining_time": "0:29:20", "throughput": 4406.47, "total_tokens": 124537648} {"current_steps": 57710, "total_steps": 61300, "loss": 0.3741, "lr": 5.208597089592871e-07, "epoch": 9.414355628058727, "percentage": 94.14, "elapsed_time": "7:51:04", "remaining_time": "0:29:18", "throughput": 4406.5, "total_tokens": 124547920} {"current_steps": 57715, "total_steps": 61300, "loss": 0.3114, "lr": 5.194153001913588e-07, "epoch": 9.415171288743883, "percentage": 94.15, "elapsed_time": "7:51:06", "remaining_time": "0:29:15", "throughput": 4406.53, "total_tokens": 124556624} {"current_steps": 57720, "total_steps": 61300, "loss": 0.3206, "lr": 5.179728759438368e-07, "epoch": 9.415986949429037, "percentage": 94.16, "elapsed_time": "7:51:08", "remaining_time": "0:29:13", "throughput": 4406.56, "total_tokens": 124566448} {"current_steps": 57725, "total_steps": 61300, "loss": 0.284, "lr": 5.165324363336582e-07, "epoch": 9.416802610114193, "percentage": 94.17, "elapsed_time": "7:51:10", "remaining_time": "0:29:10", "throughput": 4406.59, "total_tokens": 124576624} {"current_steps": 57730, "total_steps": 61300, "loss": 0.3443, "lr": 5.150939814775852e-07, "epoch": 9.417618270799348, "percentage": 94.18, "elapsed_time": "7:51:12", "remaining_time": "0:29:08", "throughput": 4406.62, "total_tokens": 124587184} {"current_steps": 57735, "total_steps": 61300, "loss": 0.3134, "lr": 5.136575114922299e-07, "epoch": 9.418433931484502, "percentage": 94.18, "elapsed_time": "7:51:15", "remaining_time": "0:29:05", "throughput": 4406.65, "total_tokens": 124598448} {"current_steps": 57740, "total_steps": 61300, "loss": 0.3393, "lr": 5.122230264940409e-07, "epoch": 9.419249592169658, "percentage": 94.19, "elapsed_time": "7:51:17", "remaining_time": "0:29:03", "throughput": 4406.69, "total_tokens": 124610576} {"current_steps": 57745, "total_steps": 61300, "loss": 0.328, "lr": 5.107905265993001e-07, "epoch": 9.420065252854812, "percentage": 94.2, "elapsed_time": "7:51:19", "remaining_time": "0:29:01", "throughput": 4406.71, "total_tokens": 124620656} {"current_steps": 57750, "total_steps": 61300, "loss": 0.3156, "lr": 5.09360011924137e-07, "epoch": 9.420880913539968, "percentage": 94.21, "elapsed_time": "7:51:21", "remaining_time": "0:28:58", "throughput": 4406.75, "total_tokens": 124631344} {"current_steps": 57755, "total_steps": 61300, "loss": 0.3243, "lr": 5.079314825845144e-07, "epoch": 9.421696574225122, "percentage": 94.22, "elapsed_time": "7:51:24", "remaining_time": "0:28:56", "throughput": 4406.79, "total_tokens": 124641872} {"current_steps": 57760, "total_steps": 61300, "loss": 0.3296, "lr": 5.065049386962395e-07, "epoch": 9.422512234910277, "percentage": 94.23, "elapsed_time": "7:51:26", "remaining_time": "0:28:53", "throughput": 4406.82, "total_tokens": 124652464} {"current_steps": 57765, "total_steps": 61300, "loss": 0.3602, "lr": 5.050803803749532e-07, "epoch": 9.423327895595433, "percentage": 94.23, "elapsed_time": "7:51:28", "remaining_time": "0:28:51", "throughput": 4406.85, "total_tokens": 124662896} {"current_steps": 57770, "total_steps": 61300, "loss": 0.307, "lr": 5.036578077361381e-07, "epoch": 9.424143556280587, "percentage": 94.24, "elapsed_time": "7:51:30", "remaining_time": "0:28:48", "throughput": 4406.88, "total_tokens": 124674480} {"current_steps": 57775, "total_steps": 61300, "loss": 0.3443, "lr": 5.022372208951131e-07, "epoch": 9.424959216965743, "percentage": 94.25, "elapsed_time": "7:51:32", "remaining_time": "0:28:46", "throughput": 4406.91, "total_tokens": 124684240} {"current_steps": 57780, "total_steps": 61300, "loss": 0.3743, "lr": 5.008186199670389e-07, "epoch": 9.425774877650896, "percentage": 94.26, "elapsed_time": "7:51:35", "remaining_time": "0:28:43", "throughput": 4406.95, "total_tokens": 124696336} {"current_steps": 57785, "total_steps": 61300, "loss": 0.3432, "lr": 4.994020050669152e-07, "epoch": 9.426590538336052, "percentage": 94.27, "elapsed_time": "7:51:37", "remaining_time": "0:28:41", "throughput": 4406.98, "total_tokens": 124708432} {"current_steps": 57790, "total_steps": 61300, "loss": 0.3085, "lr": 4.979873763095805e-07, "epoch": 9.427406199021208, "percentage": 94.27, "elapsed_time": "7:51:40", "remaining_time": "0:28:38", "throughput": 4407.02, "total_tokens": 124721072} {"current_steps": 57795, "total_steps": 61300, "loss": 0.2924, "lr": 4.965747338097099e-07, "epoch": 9.428221859706362, "percentage": 94.28, "elapsed_time": "7:51:42", "remaining_time": "0:28:36", "throughput": 4407.06, "total_tokens": 124731696} {"current_steps": 57800, "total_steps": 61300, "loss": 0.3199, "lr": 4.951640776818228e-07, "epoch": 9.429037520391518, "percentage": 94.29, "elapsed_time": "7:51:44", "remaining_time": "0:28:33", "throughput": 4407.1, "total_tokens": 124742416} {"current_steps": 57805, "total_steps": 61300, "loss": 0.3166, "lr": 4.937554080402695e-07, "epoch": 9.429853181076671, "percentage": 94.3, "elapsed_time": "7:51:47", "remaining_time": "0:28:31", "throughput": 4407.13, "total_tokens": 124752784} {"current_steps": 57810, "total_steps": 61300, "loss": 0.3421, "lr": 4.923487249992476e-07, "epoch": 9.430668841761827, "percentage": 94.31, "elapsed_time": "7:51:49", "remaining_time": "0:28:29", "throughput": 4407.16, "total_tokens": 124763248} {"current_steps": 57815, "total_steps": 61300, "loss": 0.3261, "lr": 4.909440286727879e-07, "epoch": 9.431484502446983, "percentage": 94.31, "elapsed_time": "7:51:52", "remaining_time": "0:28:26", "throughput": 4407.12, "total_tokens": 124774576} {"current_steps": 57820, "total_steps": 61300, "loss": 0.3249, "lr": 4.895413191747633e-07, "epoch": 9.432300163132137, "percentage": 94.32, "elapsed_time": "7:51:54", "remaining_time": "0:28:24", "throughput": 4407.14, "total_tokens": 124784368} {"current_steps": 57825, "total_steps": 61300, "loss": 0.2931, "lr": 4.881405966188801e-07, "epoch": 9.433115823817293, "percentage": 94.33, "elapsed_time": "7:51:56", "remaining_time": "0:28:21", "throughput": 4407.17, "total_tokens": 124793904} {"current_steps": 57830, "total_steps": 61300, "loss": 0.3427, "lr": 4.867418611186974e-07, "epoch": 9.433931484502446, "percentage": 94.34, "elapsed_time": "7:51:58", "remaining_time": "0:28:19", "throughput": 4407.2, "total_tokens": 124804848} {"current_steps": 57835, "total_steps": 61300, "loss": 0.3145, "lr": 4.853451127875968e-07, "epoch": 9.434747145187602, "percentage": 94.35, "elapsed_time": "7:52:01", "remaining_time": "0:28:16", "throughput": 4407.24, "total_tokens": 124817840} {"current_steps": 57840, "total_steps": 61300, "loss": 0.3132, "lr": 4.839503517388072e-07, "epoch": 9.435562805872756, "percentage": 94.36, "elapsed_time": "7:52:03", "remaining_time": "0:28:14", "throughput": 4407.27, "total_tokens": 124828080} {"current_steps": 57845, "total_steps": 61300, "loss": 0.3625, "lr": 4.825575780853964e-07, "epoch": 9.436378466557912, "percentage": 94.36, "elapsed_time": "7:52:05", "remaining_time": "0:28:11", "throughput": 4407.31, "total_tokens": 124839632} {"current_steps": 57850, "total_steps": 61300, "loss": 0.3342, "lr": 4.811667919402685e-07, "epoch": 9.437194127243067, "percentage": 94.37, "elapsed_time": "7:52:08", "remaining_time": "0:28:09", "throughput": 4407.34, "total_tokens": 124852176} {"current_steps": 57855, "total_steps": 61300, "loss": 0.3338, "lr": 4.797779934161667e-07, "epoch": 9.438009787928221, "percentage": 94.38, "elapsed_time": "7:52:10", "remaining_time": "0:28:06", "throughput": 4407.37, "total_tokens": 124862768} {"current_steps": 57860, "total_steps": 61300, "loss": 0.3785, "lr": 4.78391182625676e-07, "epoch": 9.438825448613377, "percentage": 94.39, "elapsed_time": "7:52:12", "remaining_time": "0:28:04", "throughput": 4407.4, "total_tokens": 124873936} {"current_steps": 57865, "total_steps": 61300, "loss": 0.3298, "lr": 4.770063596812146e-07, "epoch": 9.439641109298531, "percentage": 94.4, "elapsed_time": "7:52:15", "remaining_time": "0:28:02", "throughput": 4407.44, "total_tokens": 124884912} {"current_steps": 57870, "total_steps": 61300, "loss": 0.3708, "lr": 4.7562352469504855e-07, "epoch": 9.440456769983687, "percentage": 94.4, "elapsed_time": "7:52:17", "remaining_time": "0:27:59", "throughput": 4407.47, "total_tokens": 124895632} {"current_steps": 57875, "total_steps": 61300, "loss": 0.3182, "lr": 4.7424267777927414e-07, "epoch": 9.441272430668842, "percentage": 94.41, "elapsed_time": "7:52:19", "remaining_time": "0:27:57", "throughput": 4407.51, "total_tokens": 124906640} {"current_steps": 57880, "total_steps": 61300, "loss": 0.3211, "lr": 4.728638190458323e-07, "epoch": 9.442088091353996, "percentage": 94.42, "elapsed_time": "7:52:21", "remaining_time": "0:27:54", "throughput": 4407.54, "total_tokens": 124917392} {"current_steps": 57885, "total_steps": 61300, "loss": 0.3266, "lr": 4.7148694860649765e-07, "epoch": 9.442903752039152, "percentage": 94.43, "elapsed_time": "7:52:23", "remaining_time": "0:27:52", "throughput": 4407.57, "total_tokens": 124927408} {"current_steps": 57890, "total_steps": 61300, "loss": 0.3159, "lr": 4.701120665728892e-07, "epoch": 9.443719412724306, "percentage": 94.44, "elapsed_time": "7:52:26", "remaining_time": "0:27:49", "throughput": 4407.6, "total_tokens": 124938160} {"current_steps": 57895, "total_steps": 61300, "loss": 0.3239, "lr": 4.687391730564594e-07, "epoch": 9.444535073409462, "percentage": 94.45, "elapsed_time": "7:52:27", "remaining_time": "0:27:47", "throughput": 4407.63, "total_tokens": 124947376} {"current_steps": 57900, "total_steps": 61300, "loss": 0.3449, "lr": 4.673682681684999e-07, "epoch": 9.445350734094617, "percentage": 94.45, "elapsed_time": "7:52:30", "remaining_time": "0:27:44", "throughput": 4407.67, "total_tokens": 124958576} {"current_steps": 57905, "total_steps": 61300, "loss": 0.3693, "lr": 4.6599935202014943e-07, "epoch": 9.446166394779771, "percentage": 94.46, "elapsed_time": "7:52:32", "remaining_time": "0:27:42", "throughput": 4407.7, "total_tokens": 124968944} {"current_steps": 57910, "total_steps": 61300, "loss": 0.3599, "lr": 4.646324247223749e-07, "epoch": 9.446982055464927, "percentage": 94.47, "elapsed_time": "7:52:34", "remaining_time": "0:27:39", "throughput": 4407.73, "total_tokens": 124980496} {"current_steps": 57915, "total_steps": 61300, "loss": 0.3382, "lr": 4.6326748638598485e-07, "epoch": 9.447797716150081, "percentage": 94.48, "elapsed_time": "7:52:36", "remaining_time": "0:27:37", "throughput": 4407.76, "total_tokens": 124990256} {"current_steps": 57920, "total_steps": 61300, "loss": 0.3482, "lr": 4.619045371216324e-07, "epoch": 9.448613376835237, "percentage": 94.49, "elapsed_time": "7:52:39", "remaining_time": "0:27:34", "throughput": 4407.8, "total_tokens": 125001840} {"current_steps": 57925, "total_steps": 61300, "loss": 0.34, "lr": 4.605435770398042e-07, "epoch": 9.449429037520392, "percentage": 94.49, "elapsed_time": "7:52:41", "remaining_time": "0:27:32", "throughput": 4407.82, "total_tokens": 125012272} {"current_steps": 57930, "total_steps": 61300, "loss": 0.3357, "lr": 4.591846062508232e-07, "epoch": 9.450244698205546, "percentage": 94.5, "elapsed_time": "7:52:43", "remaining_time": "0:27:30", "throughput": 4407.85, "total_tokens": 125023024} {"current_steps": 57935, "total_steps": 61300, "loss": 0.3456, "lr": 4.578276248648594e-07, "epoch": 9.451060358890702, "percentage": 94.51, "elapsed_time": "7:52:46", "remaining_time": "0:27:27", "throughput": 4407.89, "total_tokens": 125035184} {"current_steps": 57940, "total_steps": 61300, "loss": 0.3127, "lr": 4.5647263299191113e-07, "epoch": 9.451876019575856, "percentage": 94.52, "elapsed_time": "7:52:48", "remaining_time": "0:27:25", "throughput": 4407.93, "total_tokens": 125045424} {"current_steps": 57945, "total_steps": 61300, "loss": 0.3257, "lr": 4.5511963074182653e-07, "epoch": 9.452691680261012, "percentage": 94.53, "elapsed_time": "7:52:50", "remaining_time": "0:27:22", "throughput": 4407.96, "total_tokens": 125055504} {"current_steps": 57950, "total_steps": 61300, "loss": 0.3224, "lr": 4.5376861822428176e-07, "epoch": 9.453507340946166, "percentage": 94.54, "elapsed_time": "7:52:52", "remaining_time": "0:27:20", "throughput": 4407.99, "total_tokens": 125065744} {"current_steps": 57955, "total_steps": 61300, "loss": 0.3466, "lr": 4.524195955488031e-07, "epoch": 9.454323001631321, "percentage": 94.54, "elapsed_time": "7:52:54", "remaining_time": "0:27:17", "throughput": 4408.02, "total_tokens": 125076720} {"current_steps": 57960, "total_steps": 61300, "loss": 0.3243, "lr": 4.5107256282474196e-07, "epoch": 9.455138662316477, "percentage": 94.55, "elapsed_time": "7:52:57", "remaining_time": "0:27:15", "throughput": 4408.05, "total_tokens": 125087504} {"current_steps": 57965, "total_steps": 61300, "loss": 0.3057, "lr": 4.4972752016129995e-07, "epoch": 9.455954323001631, "percentage": 94.56, "elapsed_time": "7:52:59", "remaining_time": "0:27:12", "throughput": 4408.09, "total_tokens": 125099408} {"current_steps": 57970, "total_steps": 61300, "loss": 0.3417, "lr": 4.483844676675092e-07, "epoch": 9.456769983686787, "percentage": 94.57, "elapsed_time": "7:53:01", "remaining_time": "0:27:10", "throughput": 4408.12, "total_tokens": 125109904} {"current_steps": 57975, "total_steps": 61300, "loss": 0.3062, "lr": 4.4704340545224934e-07, "epoch": 9.45758564437194, "percentage": 94.58, "elapsed_time": "7:53:03", "remaining_time": "0:27:07", "throughput": 4408.15, "total_tokens": 125120144} {"current_steps": 57980, "total_steps": 61300, "loss": 0.3331, "lr": 4.457043336242306e-07, "epoch": 9.458401305057096, "percentage": 94.58, "elapsed_time": "7:53:06", "remaining_time": "0:27:05", "throughput": 4408.18, "total_tokens": 125131056} {"current_steps": 57985, "total_steps": 61300, "loss": 0.3242, "lr": 4.443672522920078e-07, "epoch": 9.459216965742252, "percentage": 94.59, "elapsed_time": "7:53:08", "remaining_time": "0:27:02", "throughput": 4408.21, "total_tokens": 125141072} {"current_steps": 57990, "total_steps": 61300, "loss": 0.3206, "lr": 4.4303216156396933e-07, "epoch": 9.460032626427406, "percentage": 94.6, "elapsed_time": "7:53:10", "remaining_time": "0:27:00", "throughput": 4408.24, "total_tokens": 125152656} {"current_steps": 57995, "total_steps": 61300, "loss": 0.3292, "lr": 4.416990615483396e-07, "epoch": 9.460848287112562, "percentage": 94.61, "elapsed_time": "7:53:13", "remaining_time": "0:26:58", "throughput": 4408.28, "total_tokens": 125164880} {"current_steps": 58000, "total_steps": 61300, "loss": 0.3645, "lr": 4.4036795235319617e-07, "epoch": 9.461663947797716, "percentage": 94.62, "elapsed_time": "7:53:15", "remaining_time": "0:26:55", "throughput": 4408.32, "total_tokens": 125175792} {"current_steps": 58005, "total_steps": 61300, "loss": 0.3612, "lr": 4.390388340864415e-07, "epoch": 9.462479608482871, "percentage": 94.62, "elapsed_time": "7:53:17", "remaining_time": "0:26:53", "throughput": 4408.35, "total_tokens": 125187152} {"current_steps": 58010, "total_steps": 61300, "loss": 0.3311, "lr": 4.377117068558201e-07, "epoch": 9.463295269168025, "percentage": 94.63, "elapsed_time": "7:53:19", "remaining_time": "0:26:50", "throughput": 4408.39, "total_tokens": 125197072} {"current_steps": 58015, "total_steps": 61300, "loss": 0.3015, "lr": 4.363865707689152e-07, "epoch": 9.464110929853181, "percentage": 94.64, "elapsed_time": "7:53:22", "remaining_time": "0:26:48", "throughput": 4408.42, "total_tokens": 125208144} {"current_steps": 58020, "total_steps": 61300, "loss": 0.3221, "lr": 4.350634259331465e-07, "epoch": 9.464926590538337, "percentage": 94.65, "elapsed_time": "7:53:24", "remaining_time": "0:26:45", "throughput": 4408.45, "total_tokens": 125218448} {"current_steps": 58025, "total_steps": 61300, "loss": 0.3477, "lr": 4.33742272455781e-07, "epoch": 9.46574225122349, "percentage": 94.66, "elapsed_time": "7:53:26", "remaining_time": "0:26:43", "throughput": 4408.48, "total_tokens": 125229168} {"current_steps": 58030, "total_steps": 61300, "loss": 0.31, "lr": 4.324231104439136e-07, "epoch": 9.466557911908646, "percentage": 94.67, "elapsed_time": "7:53:28", "remaining_time": "0:26:40", "throughput": 4408.51, "total_tokens": 125240496} {"current_steps": 58035, "total_steps": 61300, "loss": 0.3263, "lr": 4.3110594000448365e-07, "epoch": 9.4673735725938, "percentage": 94.67, "elapsed_time": "7:53:31", "remaining_time": "0:26:38", "throughput": 4408.55, "total_tokens": 125251408} {"current_steps": 58040, "total_steps": 61300, "loss": 0.3149, "lr": 4.29790761244267e-07, "epoch": 9.468189233278956, "percentage": 94.68, "elapsed_time": "7:53:33", "remaining_time": "0:26:35", "throughput": 4408.57, "total_tokens": 125262128} {"current_steps": 58045, "total_steps": 61300, "loss": 0.3323, "lr": 4.2847757426988097e-07, "epoch": 9.469004893964112, "percentage": 94.69, "elapsed_time": "7:53:35", "remaining_time": "0:26:33", "throughput": 4408.6, "total_tokens": 125272816} {"current_steps": 58050, "total_steps": 61300, "loss": 0.3179, "lr": 4.271663791877767e-07, "epoch": 9.469820554649266, "percentage": 94.7, "elapsed_time": "7:53:37", "remaining_time": "0:26:31", "throughput": 4408.63, "total_tokens": 125283792} {"current_steps": 58055, "total_steps": 61300, "loss": 0.3422, "lr": 4.258571761042468e-07, "epoch": 9.470636215334421, "percentage": 94.71, "elapsed_time": "7:53:40", "remaining_time": "0:26:28", "throughput": 4408.66, "total_tokens": 125294960} {"current_steps": 58060, "total_steps": 61300, "loss": 0.3204, "lr": 4.2454996512542033e-07, "epoch": 9.471451876019575, "percentage": 94.71, "elapsed_time": "7:53:42", "remaining_time": "0:26:26", "throughput": 4408.68, "total_tokens": 125304816} {"current_steps": 58065, "total_steps": 61300, "loss": 0.3103, "lr": 4.2324474635727085e-07, "epoch": 9.47226753670473, "percentage": 94.72, "elapsed_time": "7:53:44", "remaining_time": "0:26:23", "throughput": 4408.71, "total_tokens": 125314448} {"current_steps": 58070, "total_steps": 61300, "loss": 0.336, "lr": 4.219415199056026e-07, "epoch": 9.473083197389887, "percentage": 94.73, "elapsed_time": "7:53:46", "remaining_time": "0:26:21", "throughput": 4408.74, "total_tokens": 125325584} {"current_steps": 58075, "total_steps": 61300, "loss": 0.2971, "lr": 4.2064028587606163e-07, "epoch": 9.47389885807504, "percentage": 94.74, "elapsed_time": "7:53:49", "remaining_time": "0:26:18", "throughput": 4408.78, "total_tokens": 125337328} {"current_steps": 58080, "total_steps": 61300, "loss": 0.3167, "lr": 4.19341044374133e-07, "epoch": 9.474714518760196, "percentage": 94.75, "elapsed_time": "7:53:51", "remaining_time": "0:26:16", "throughput": 4408.81, "total_tokens": 125348336} {"current_steps": 58085, "total_steps": 61300, "loss": 0.3555, "lr": 4.180437955051436e-07, "epoch": 9.47553017944535, "percentage": 94.76, "elapsed_time": "7:53:53", "remaining_time": "0:26:13", "throughput": 4408.84, "total_tokens": 125359152} {"current_steps": 58090, "total_steps": 61300, "loss": 0.2982, "lr": 4.167485393742482e-07, "epoch": 9.476345840130506, "percentage": 94.76, "elapsed_time": "7:53:56", "remaining_time": "0:26:11", "throughput": 4408.87, "total_tokens": 125371792} {"current_steps": 58095, "total_steps": 61300, "loss": 0.3318, "lr": 4.1545527608645163e-07, "epoch": 9.477161500815662, "percentage": 94.77, "elapsed_time": "7:53:58", "remaining_time": "0:26:08", "throughput": 4408.91, "total_tokens": 125382960} {"current_steps": 58100, "total_steps": 61300, "loss": 0.3511, "lr": 4.1416400574659233e-07, "epoch": 9.477977161500815, "percentage": 94.78, "elapsed_time": "7:54:00", "remaining_time": "0:26:06", "throughput": 4408.94, "total_tokens": 125392752} {"current_steps": 58105, "total_steps": 61300, "loss": 0.3141, "lr": 4.128747284593448e-07, "epoch": 9.478792822185971, "percentage": 94.79, "elapsed_time": "7:54:02", "remaining_time": "0:26:03", "throughput": 4408.97, "total_tokens": 125404080} {"current_steps": 58110, "total_steps": 61300, "loss": 0.3384, "lr": 4.1158744432922835e-07, "epoch": 9.479608482871125, "percentage": 94.8, "elapsed_time": "7:54:05", "remaining_time": "0:26:01", "throughput": 4409.0, "total_tokens": 125415568} {"current_steps": 58115, "total_steps": 61300, "loss": 0.3544, "lr": 4.1030215346059e-07, "epoch": 9.48042414355628, "percentage": 94.8, "elapsed_time": "7:54:07", "remaining_time": "0:25:59", "throughput": 4409.03, "total_tokens": 125426832} {"current_steps": 58120, "total_steps": 61300, "loss": 0.3486, "lr": 4.090188559576269e-07, "epoch": 9.481239804241435, "percentage": 94.81, "elapsed_time": "7:54:09", "remaining_time": "0:25:56", "throughput": 4409.06, "total_tokens": 125436656} {"current_steps": 58125, "total_steps": 61300, "loss": 0.342, "lr": 4.077375519243698e-07, "epoch": 9.48205546492659, "percentage": 94.82, "elapsed_time": "7:54:12", "remaining_time": "0:25:54", "throughput": 4409.08, "total_tokens": 125447440} {"current_steps": 58130, "total_steps": 61300, "loss": 0.3586, "lr": 4.0645824146468834e-07, "epoch": 9.482871125611746, "percentage": 94.83, "elapsed_time": "7:54:14", "remaining_time": "0:25:51", "throughput": 4409.11, "total_tokens": 125458928} {"current_steps": 58135, "total_steps": 61300, "loss": 0.3437, "lr": 4.0518092468228297e-07, "epoch": 9.4836867862969, "percentage": 94.84, "elapsed_time": "7:54:16", "remaining_time": "0:25:49", "throughput": 4409.14, "total_tokens": 125469520} {"current_steps": 58140, "total_steps": 61300, "loss": 0.3389, "lr": 4.0390560168070966e-07, "epoch": 9.484502446982056, "percentage": 94.85, "elapsed_time": "7:54:18", "remaining_time": "0:25:46", "throughput": 4409.17, "total_tokens": 125480016} {"current_steps": 58145, "total_steps": 61300, "loss": 0.3476, "lr": 4.026322725633441e-07, "epoch": 9.48531810766721, "percentage": 94.85, "elapsed_time": "7:54:21", "remaining_time": "0:25:44", "throughput": 4409.2, "total_tokens": 125490608} {"current_steps": 58150, "total_steps": 61300, "loss": 0.3589, "lr": 4.0136093743341485e-07, "epoch": 9.486133768352365, "percentage": 94.86, "elapsed_time": "7:54:23", "remaining_time": "0:25:41", "throughput": 4409.23, "total_tokens": 125501392} {"current_steps": 58155, "total_steps": 61300, "loss": 0.3443, "lr": 4.000915963939783e-07, "epoch": 9.486949429037521, "percentage": 94.87, "elapsed_time": "7:54:25", "remaining_time": "0:25:39", "throughput": 4409.26, "total_tokens": 125510448} {"current_steps": 58160, "total_steps": 61300, "loss": 0.34, "lr": 3.988242495479383e-07, "epoch": 9.487765089722675, "percentage": 94.88, "elapsed_time": "7:54:27", "remaining_time": "0:25:36", "throughput": 4409.29, "total_tokens": 125521968} {"current_steps": 58165, "total_steps": 61300, "loss": 0.3355, "lr": 3.9755889699802926e-07, "epoch": 9.48858075040783, "percentage": 94.89, "elapsed_time": "7:54:29", "remaining_time": "0:25:34", "throughput": 4409.33, "total_tokens": 125533360} {"current_steps": 58170, "total_steps": 61300, "loss": 0.3208, "lr": 3.962955388468248e-07, "epoch": 9.489396411092985, "percentage": 94.89, "elapsed_time": "7:54:32", "remaining_time": "0:25:32", "throughput": 4409.36, "total_tokens": 125544400} {"current_steps": 58175, "total_steps": 61300, "loss": 0.4026, "lr": 3.950341751967457e-07, "epoch": 9.49021207177814, "percentage": 94.9, "elapsed_time": "7:54:34", "remaining_time": "0:25:29", "throughput": 4409.4, "total_tokens": 125555568} {"current_steps": 58180, "total_steps": 61300, "loss": 0.3099, "lr": 3.9377480615003794e-07, "epoch": 9.491027732463296, "percentage": 94.91, "elapsed_time": "7:54:36", "remaining_time": "0:25:27", "throughput": 4409.43, "total_tokens": 125566224} {"current_steps": 58185, "total_steps": 61300, "loss": 0.3454, "lr": 3.9251743180879483e-07, "epoch": 9.49184339314845, "percentage": 94.92, "elapsed_time": "7:54:38", "remaining_time": "0:25:24", "throughput": 4409.46, "total_tokens": 125576976} {"current_steps": 58190, "total_steps": 61300, "loss": 0.3376, "lr": 3.9126205227494605e-07, "epoch": 9.492659053833606, "percentage": 94.93, "elapsed_time": "7:54:41", "remaining_time": "0:25:22", "throughput": 4409.49, "total_tokens": 125587856} {"current_steps": 58195, "total_steps": 61300, "loss": 0.3281, "lr": 3.900086676502601e-07, "epoch": 9.49347471451876, "percentage": 94.93, "elapsed_time": "7:54:43", "remaining_time": "0:25:19", "throughput": 4409.52, "total_tokens": 125598832} {"current_steps": 58200, "total_steps": 61300, "loss": 0.3174, "lr": 3.8875727803634186e-07, "epoch": 9.494290375203915, "percentage": 94.94, "elapsed_time": "7:54:46", "remaining_time": "0:25:17", "throughput": 4409.56, "total_tokens": 125610832} {"current_steps": 58205, "total_steps": 61300, "loss": 0.341, "lr": 3.8750788353463243e-07, "epoch": 9.49510603588907, "percentage": 94.95, "elapsed_time": "7:54:48", "remaining_time": "0:25:14", "throughput": 4409.6, "total_tokens": 125621104} {"current_steps": 58210, "total_steps": 61300, "loss": 0.3107, "lr": 3.862604842464201e-07, "epoch": 9.495921696574225, "percentage": 94.96, "elapsed_time": "7:54:50", "remaining_time": "0:25:12", "throughput": 4409.63, "total_tokens": 125632752} {"current_steps": 58215, "total_steps": 61300, "loss": 0.3359, "lr": 3.8501508027281865e-07, "epoch": 9.49673735725938, "percentage": 94.97, "elapsed_time": "7:54:52", "remaining_time": "0:25:09", "throughput": 4409.66, "total_tokens": 125642832} {"current_steps": 58220, "total_steps": 61300, "loss": 0.3368, "lr": 3.8377167171479154e-07, "epoch": 9.497553017944535, "percentage": 94.98, "elapsed_time": "7:54:54", "remaining_time": "0:25:07", "throughput": 4409.69, "total_tokens": 125653840} {"current_steps": 58225, "total_steps": 61300, "loss": 0.3076, "lr": 3.825302586731333e-07, "epoch": 9.49836867862969, "percentage": 94.98, "elapsed_time": "7:54:57", "remaining_time": "0:25:05", "throughput": 4409.72, "total_tokens": 125665104} {"current_steps": 58230, "total_steps": 61300, "loss": 0.3319, "lr": 3.8129084124848e-07, "epoch": 9.499184339314844, "percentage": 94.99, "elapsed_time": "7:54:59", "remaining_time": "0:25:02", "throughput": 4409.75, "total_tokens": 125675824} {"current_steps": 58235, "total_steps": 61300, "loss": 0.3519, "lr": 3.800534195413069e-07, "epoch": 9.5, "percentage": 95.0, "elapsed_time": "7:55:01", "remaining_time": "0:25:00", "throughput": 4409.78, "total_tokens": 125686064} {"current_steps": 58235, "total_steps": 61300, "eval_loss": 0.33483001589775085, "epoch": 9.5, "percentage": 95.0, "elapsed_time": "7:57:13", "remaining_time": "0:25:07", "throughput": 4389.49, "total_tokens": 125686064} {"current_steps": 58240, "total_steps": 61300, "loss": 0.3386, "lr": 3.788179936519226e-07, "epoch": 9.500815660685156, "percentage": 95.01, "elapsed_time": "7:57:17", "remaining_time": "0:25:04", "throughput": 4389.32, "total_tokens": 125697296} {"current_steps": 58245, "total_steps": 61300, "loss": 0.3316, "lr": 3.775845636804776e-07, "epoch": 9.50163132137031, "percentage": 95.02, "elapsed_time": "7:57:19", "remaining_time": "0:25:02", "throughput": 4389.36, "total_tokens": 125708688} {"current_steps": 58250, "total_steps": 61300, "loss": 0.3245, "lr": 3.7635312972696404e-07, "epoch": 9.502446982055465, "percentage": 95.02, "elapsed_time": "7:57:21", "remaining_time": "0:24:59", "throughput": 4389.4, "total_tokens": 125719792} {"current_steps": 58255, "total_steps": 61300, "loss": 0.3109, "lr": 3.751236918912021e-07, "epoch": 9.50326264274062, "percentage": 95.03, "elapsed_time": "7:57:23", "remaining_time": "0:24:57", "throughput": 4389.43, "total_tokens": 125729680} {"current_steps": 58260, "total_steps": 61300, "loss": 0.3036, "lr": 3.7389625027285936e-07, "epoch": 9.504078303425775, "percentage": 95.04, "elapsed_time": "7:57:25", "remaining_time": "0:24:54", "throughput": 4389.46, "total_tokens": 125739472} {"current_steps": 58265, "total_steps": 61300, "loss": 0.339, "lr": 3.726708049714367e-07, "epoch": 9.50489396411093, "percentage": 95.05, "elapsed_time": "7:57:28", "remaining_time": "0:24:52", "throughput": 4389.51, "total_tokens": 125751952} {"current_steps": 58270, "total_steps": 61300, "loss": 0.3179, "lr": 3.714473560862797e-07, "epoch": 9.505709624796085, "percentage": 95.06, "elapsed_time": "7:57:30", "remaining_time": "0:24:49", "throughput": 4389.54, "total_tokens": 125762992} {"current_steps": 58275, "total_steps": 61300, "loss": 0.3521, "lr": 3.702259037165617e-07, "epoch": 9.50652528548124, "percentage": 95.07, "elapsed_time": "7:57:32", "remaining_time": "0:24:47", "throughput": 4389.58, "total_tokens": 125774480} {"current_steps": 58280, "total_steps": 61300, "loss": 0.3553, "lr": 3.690064479613009e-07, "epoch": 9.507340946166394, "percentage": 95.07, "elapsed_time": "7:57:35", "remaining_time": "0:24:44", "throughput": 4389.61, "total_tokens": 125784944} {"current_steps": 58285, "total_steps": 61300, "loss": 0.3568, "lr": 3.67788988919357e-07, "epoch": 9.50815660685155, "percentage": 95.08, "elapsed_time": "7:57:37", "remaining_time": "0:24:42", "throughput": 4389.64, "total_tokens": 125795120} {"current_steps": 58290, "total_steps": 61300, "loss": 0.3109, "lr": 3.665735266894177e-07, "epoch": 9.508972267536706, "percentage": 95.09, "elapsed_time": "7:57:39", "remaining_time": "0:24:39", "throughput": 4389.68, "total_tokens": 125806640} {"current_steps": 58295, "total_steps": 61300, "loss": 0.3229, "lr": 3.653600613700209e-07, "epoch": 9.50978792822186, "percentage": 95.1, "elapsed_time": "7:57:41", "remaining_time": "0:24:37", "throughput": 4389.72, "total_tokens": 125817712} {"current_steps": 58300, "total_steps": 61300, "loss": 0.3203, "lr": 3.6414859305952955e-07, "epoch": 9.510603588907015, "percentage": 95.11, "elapsed_time": "7:57:44", "remaining_time": "0:24:35", "throughput": 4389.74, "total_tokens": 125829008} {"current_steps": 58305, "total_steps": 61300, "loss": 0.3556, "lr": 3.629391218561512e-07, "epoch": 9.51141924959217, "percentage": 95.11, "elapsed_time": "7:57:46", "remaining_time": "0:24:32", "throughput": 4389.78, "total_tokens": 125840016} {"current_steps": 58310, "total_steps": 61300, "loss": 0.3446, "lr": 3.6173164785794076e-07, "epoch": 9.512234910277325, "percentage": 95.12, "elapsed_time": "7:57:48", "remaining_time": "0:24:30", "throughput": 4389.81, "total_tokens": 125850608} {"current_steps": 58315, "total_steps": 61300, "loss": 0.3331, "lr": 3.605261711627728e-07, "epoch": 9.513050570962479, "percentage": 95.13, "elapsed_time": "7:57:51", "remaining_time": "0:24:27", "throughput": 4389.86, "total_tokens": 125863312} {"current_steps": 58320, "total_steps": 61300, "loss": 0.327, "lr": 3.593226918683745e-07, "epoch": 9.513866231647635, "percentage": 95.14, "elapsed_time": "7:57:53", "remaining_time": "0:24:25", "throughput": 4389.89, "total_tokens": 125874960} {"current_steps": 58325, "total_steps": 61300, "loss": 0.3206, "lr": 3.5812121007230414e-07, "epoch": 9.51468189233279, "percentage": 95.15, "elapsed_time": "7:57:55", "remaining_time": "0:24:22", "throughput": 4389.92, "total_tokens": 125885264} {"current_steps": 58330, "total_steps": 61300, "loss": 0.3431, "lr": 3.569217258719587e-07, "epoch": 9.515497553017944, "percentage": 95.15, "elapsed_time": "7:57:58", "remaining_time": "0:24:20", "throughput": 4389.95, "total_tokens": 125896624} {"current_steps": 58335, "total_steps": 61300, "loss": 0.3761, "lr": 3.557242393645771e-07, "epoch": 9.5163132137031, "percentage": 95.16, "elapsed_time": "7:58:00", "remaining_time": "0:24:17", "throughput": 4389.98, "total_tokens": 125907056} {"current_steps": 58340, "total_steps": 61300, "loss": 0.3261, "lr": 3.5452875064723445e-07, "epoch": 9.517128874388254, "percentage": 95.17, "elapsed_time": "7:58:02", "remaining_time": "0:24:15", "throughput": 4390.02, "total_tokens": 125917616} {"current_steps": 58345, "total_steps": 61300, "loss": 0.3181, "lr": 3.5333525981683937e-07, "epoch": 9.51794453507341, "percentage": 95.18, "elapsed_time": "7:58:04", "remaining_time": "0:24:12", "throughput": 4390.04, "total_tokens": 125927984} {"current_steps": 58350, "total_steps": 61300, "loss": 0.3659, "lr": 3.521437669701422e-07, "epoch": 9.518760195758565, "percentage": 95.19, "elapsed_time": "7:58:07", "remaining_time": "0:24:10", "throughput": 4390.08, "total_tokens": 125938736} {"current_steps": 58355, "total_steps": 61300, "loss": 0.309, "lr": 3.5095427220373513e-07, "epoch": 9.51957585644372, "percentage": 95.2, "elapsed_time": "7:58:09", "remaining_time": "0:24:07", "throughput": 4390.12, "total_tokens": 125948816} {"current_steps": 58360, "total_steps": 61300, "loss": 0.3315, "lr": 3.497667756140438e-07, "epoch": 9.520391517128875, "percentage": 95.2, "elapsed_time": "7:58:11", "remaining_time": "0:24:05", "throughput": 4390.15, "total_tokens": 125959504} {"current_steps": 58365, "total_steps": 61300, "loss": 0.3323, "lr": 3.4858127729733015e-07, "epoch": 9.521207177814029, "percentage": 95.21, "elapsed_time": "7:58:13", "remaining_time": "0:24:02", "throughput": 4390.19, "total_tokens": 125971504} {"current_steps": 58370, "total_steps": 61300, "loss": 0.3149, "lr": 3.473977773496978e-07, "epoch": 9.522022838499185, "percentage": 95.22, "elapsed_time": "7:58:16", "remaining_time": "0:24:00", "throughput": 4390.22, "total_tokens": 125981840} {"current_steps": 58375, "total_steps": 61300, "loss": 0.3014, "lr": 3.462162758670895e-07, "epoch": 9.522838499184338, "percentage": 95.23, "elapsed_time": "7:58:18", "remaining_time": "0:23:57", "throughput": 4390.25, "total_tokens": 125992432} {"current_steps": 58380, "total_steps": 61300, "loss": 0.3314, "lr": 3.4503677294527857e-07, "epoch": 9.523654159869494, "percentage": 95.24, "elapsed_time": "7:58:20", "remaining_time": "0:23:55", "throughput": 4390.28, "total_tokens": 126002576} {"current_steps": 58385, "total_steps": 61300, "loss": 0.3272, "lr": 3.438592686798886e-07, "epoch": 9.52446982055465, "percentage": 95.24, "elapsed_time": "7:58:22", "remaining_time": "0:23:53", "throughput": 4390.3, "total_tokens": 126011920} {"current_steps": 58390, "total_steps": 61300, "loss": 0.322, "lr": 3.4268376316636816e-07, "epoch": 9.525285481239804, "percentage": 95.25, "elapsed_time": "7:58:24", "remaining_time": "0:23:50", "throughput": 4390.33, "total_tokens": 126022864} {"current_steps": 58395, "total_steps": 61300, "loss": 0.3246, "lr": 3.4151025650001056e-07, "epoch": 9.52610114192496, "percentage": 95.26, "elapsed_time": "7:58:27", "remaining_time": "0:23:48", "throughput": 4390.37, "total_tokens": 126034960} {"current_steps": 58400, "total_steps": 61300, "loss": 0.3173, "lr": 3.4033874877595074e-07, "epoch": 9.526916802610113, "percentage": 95.27, "elapsed_time": "7:58:29", "remaining_time": "0:23:45", "throughput": 4390.41, "total_tokens": 126046672} {"current_steps": 58405, "total_steps": 61300, "loss": 0.3535, "lr": 3.3916924008915163e-07, "epoch": 9.52773246329527, "percentage": 95.28, "elapsed_time": "7:58:31", "remaining_time": "0:23:43", "throughput": 4390.44, "total_tokens": 126058000} {"current_steps": 58410, "total_steps": 61300, "loss": 0.3147, "lr": 3.3800173053442354e-07, "epoch": 9.528548123980425, "percentage": 95.29, "elapsed_time": "7:58:34", "remaining_time": "0:23:40", "throughput": 4390.48, "total_tokens": 126068496} {"current_steps": 58415, "total_steps": 61300, "loss": 0.3385, "lr": 3.3683622020640736e-07, "epoch": 9.529363784665579, "percentage": 95.29, "elapsed_time": "7:58:36", "remaining_time": "0:23:38", "throughput": 4390.51, "total_tokens": 126078544} {"current_steps": 58420, "total_steps": 61300, "loss": 0.3301, "lr": 3.356727091995859e-07, "epoch": 9.530179445350734, "percentage": 95.3, "elapsed_time": "7:58:38", "remaining_time": "0:23:35", "throughput": 4390.54, "total_tokens": 126089712} {"current_steps": 58425, "total_steps": 61300, "loss": 0.3468, "lr": 3.3451119760828374e-07, "epoch": 9.530995106035888, "percentage": 95.31, "elapsed_time": "7:58:40", "remaining_time": "0:23:33", "throughput": 4390.58, "total_tokens": 126100656} {"current_steps": 58430, "total_steps": 61300, "loss": 0.3486, "lr": 3.333516855266533e-07, "epoch": 9.531810766721044, "percentage": 95.32, "elapsed_time": "7:58:42", "remaining_time": "0:23:30", "throughput": 4390.62, "total_tokens": 126111376} {"current_steps": 58435, "total_steps": 61300, "loss": 0.3474, "lr": 3.321941730486916e-07, "epoch": 9.5326264274062, "percentage": 95.33, "elapsed_time": "7:58:45", "remaining_time": "0:23:28", "throughput": 4390.65, "total_tokens": 126122640} {"current_steps": 58440, "total_steps": 61300, "loss": 0.3304, "lr": 3.3103866026823473e-07, "epoch": 9.533442088091354, "percentage": 95.33, "elapsed_time": "7:58:47", "remaining_time": "0:23:25", "throughput": 4390.68, "total_tokens": 126132432} {"current_steps": 58445, "total_steps": 61300, "loss": 0.3002, "lr": 3.2988514727895217e-07, "epoch": 9.53425774877651, "percentage": 95.34, "elapsed_time": "7:58:49", "remaining_time": "0:23:23", "throughput": 4390.7, "total_tokens": 126142576} {"current_steps": 58450, "total_steps": 61300, "loss": 0.3284, "lr": 3.287336341743524e-07, "epoch": 9.535073409461663, "percentage": 95.35, "elapsed_time": "7:58:51", "remaining_time": "0:23:20", "throughput": 4390.73, "total_tokens": 126153552} {"current_steps": 58455, "total_steps": 61300, "loss": 0.3125, "lr": 3.275841210477887e-07, "epoch": 9.535889070146819, "percentage": 95.36, "elapsed_time": "7:58:54", "remaining_time": "0:23:18", "throughput": 4390.77, "total_tokens": 126165072} {"current_steps": 58460, "total_steps": 61300, "loss": 0.345, "lr": 3.264366079924419e-07, "epoch": 9.536704730831975, "percentage": 95.37, "elapsed_time": "7:58:56", "remaining_time": "0:23:16", "throughput": 4390.8, "total_tokens": 126175696} {"current_steps": 58465, "total_steps": 61300, "loss": 0.3233, "lr": 3.252910951013349e-07, "epoch": 9.537520391517129, "percentage": 95.38, "elapsed_time": "7:58:58", "remaining_time": "0:23:13", "throughput": 4390.84, "total_tokens": 126187088} {"current_steps": 58470, "total_steps": 61300, "loss": 0.3115, "lr": 3.2414758246733234e-07, "epoch": 9.538336052202284, "percentage": 95.38, "elapsed_time": "7:59:01", "remaining_time": "0:23:11", "throughput": 4390.87, "total_tokens": 126198480} {"current_steps": 58475, "total_steps": 61300, "loss": 0.3213, "lr": 3.2300607018312944e-07, "epoch": 9.539151712887438, "percentage": 95.39, "elapsed_time": "7:59:03", "remaining_time": "0:23:08", "throughput": 4390.91, "total_tokens": 126209904} {"current_steps": 58480, "total_steps": 61300, "loss": 0.3379, "lr": 3.2186655834126335e-07, "epoch": 9.539967373572594, "percentage": 95.4, "elapsed_time": "7:59:05", "remaining_time": "0:23:06", "throughput": 4390.94, "total_tokens": 126219792} {"current_steps": 58485, "total_steps": 61300, "loss": 0.299, "lr": 3.207290470341101e-07, "epoch": 9.540783034257748, "percentage": 95.41, "elapsed_time": "7:59:07", "remaining_time": "0:23:03", "throughput": 4390.97, "total_tokens": 126230256} {"current_steps": 58490, "total_steps": 61300, "loss": 0.3426, "lr": 3.1959353635388214e-07, "epoch": 9.541598694942904, "percentage": 95.42, "elapsed_time": "7:59:09", "remaining_time": "0:23:01", "throughput": 4391.0, "total_tokens": 126241136} {"current_steps": 58495, "total_steps": 61300, "loss": 0.3237, "lr": 3.1846002639263074e-07, "epoch": 9.54241435562806, "percentage": 95.42, "elapsed_time": "7:59:12", "remaining_time": "0:22:58", "throughput": 4391.03, "total_tokens": 126252048} {"current_steps": 58500, "total_steps": 61300, "loss": 0.3272, "lr": 3.17328517242238e-07, "epoch": 9.543230016313213, "percentage": 95.43, "elapsed_time": "7:59:14", "remaining_time": "0:22:56", "throughput": 4391.07, "total_tokens": 126262320} {"current_steps": 58505, "total_steps": 61300, "loss": 0.3088, "lr": 3.161990089944389e-07, "epoch": 9.544045676998369, "percentage": 95.44, "elapsed_time": "7:59:16", "remaining_time": "0:22:53", "throughput": 4391.1, "total_tokens": 126272464} {"current_steps": 58510, "total_steps": 61300, "loss": 0.3112, "lr": 3.150715017407907e-07, "epoch": 9.544861337683523, "percentage": 95.45, "elapsed_time": "7:59:18", "remaining_time": "0:22:51", "throughput": 4391.14, "total_tokens": 126283984} {"current_steps": 58515, "total_steps": 61300, "loss": 0.3375, "lr": 3.1394599557269534e-07, "epoch": 9.545676998368679, "percentage": 95.46, "elapsed_time": "7:59:21", "remaining_time": "0:22:48", "throughput": 4391.17, "total_tokens": 126295024} {"current_steps": 58520, "total_steps": 61300, "loss": 0.357, "lr": 3.128224905813965e-07, "epoch": 9.546492659053834, "percentage": 95.46, "elapsed_time": "7:59:23", "remaining_time": "0:22:46", "throughput": 4391.2, "total_tokens": 126305296} {"current_steps": 58525, "total_steps": 61300, "loss": 0.332, "lr": 3.1170098685796565e-07, "epoch": 9.547308319738988, "percentage": 95.47, "elapsed_time": "7:59:25", "remaining_time": "0:22:43", "throughput": 4391.24, "total_tokens": 126317264} {"current_steps": 58530, "total_steps": 61300, "loss": 0.2979, "lr": 3.1058148449331914e-07, "epoch": 9.548123980424144, "percentage": 95.48, "elapsed_time": "7:59:27", "remaining_time": "0:22:41", "throughput": 4391.27, "total_tokens": 126326640} {"current_steps": 58535, "total_steps": 61300, "loss": 0.3177, "lr": 3.09463983578212e-07, "epoch": 9.548939641109298, "percentage": 95.49, "elapsed_time": "7:59:29", "remaining_time": "0:22:38", "throughput": 4391.31, "total_tokens": 126337840} {"current_steps": 58540, "total_steps": 61300, "loss": 0.3068, "lr": 3.0834848420323305e-07, "epoch": 9.549755301794454, "percentage": 95.5, "elapsed_time": "7:59:32", "remaining_time": "0:22:36", "throughput": 4391.34, "total_tokens": 126347792} {"current_steps": 58545, "total_steps": 61300, "loss": 0.3312, "lr": 3.0723498645880976e-07, "epoch": 9.550570962479608, "percentage": 95.51, "elapsed_time": "7:59:34", "remaining_time": "0:22:34", "throughput": 4391.38, "total_tokens": 126359344} {"current_steps": 58550, "total_steps": 61300, "loss": 0.3308, "lr": 3.061234904352089e-07, "epoch": 9.551386623164763, "percentage": 95.51, "elapsed_time": "7:59:36", "remaining_time": "0:22:31", "throughput": 4391.42, "total_tokens": 126370064} {"current_steps": 58555, "total_steps": 61300, "loss": 0.3212, "lr": 3.0501399622253344e-07, "epoch": 9.552202283849919, "percentage": 95.52, "elapsed_time": "7:59:38", "remaining_time": "0:22:29", "throughput": 4391.45, "total_tokens": 126380080} {"current_steps": 58560, "total_steps": 61300, "loss": 0.3369, "lr": 3.0390650391072527e-07, "epoch": 9.553017944535073, "percentage": 95.53, "elapsed_time": "7:59:40", "remaining_time": "0:22:26", "throughput": 4391.49, "total_tokens": 126390864} {"current_steps": 58565, "total_steps": 61300, "loss": 0.3258, "lr": 3.028010135895598e-07, "epoch": 9.553833605220229, "percentage": 95.54, "elapsed_time": "7:59:43", "remaining_time": "0:22:24", "throughput": 4391.53, "total_tokens": 126402224} {"current_steps": 58570, "total_steps": 61300, "loss": 0.3327, "lr": 3.016975253486598e-07, "epoch": 9.554649265905383, "percentage": 95.55, "elapsed_time": "7:59:45", "remaining_time": "0:22:21", "throughput": 4391.56, "total_tokens": 126412464} {"current_steps": 58575, "total_steps": 61300, "loss": 0.3113, "lr": 3.0059603927747313e-07, "epoch": 9.555464926590538, "percentage": 95.55, "elapsed_time": "7:59:47", "remaining_time": "0:22:19", "throughput": 4391.58, "total_tokens": 126423600} {"current_steps": 58580, "total_steps": 61300, "loss": 0.2996, "lr": 2.9949655546529785e-07, "epoch": 9.556280587275694, "percentage": 95.56, "elapsed_time": "7:59:50", "remaining_time": "0:22:16", "throughput": 4391.62, "total_tokens": 126434928} {"current_steps": 58585, "total_steps": 61300, "loss": 0.3279, "lr": 2.9839907400125986e-07, "epoch": 9.557096247960848, "percentage": 95.57, "elapsed_time": "7:59:52", "remaining_time": "0:22:14", "throughput": 4391.65, "total_tokens": 126444944} {"current_steps": 58590, "total_steps": 61300, "loss": 0.3205, "lr": 2.973035949743269e-07, "epoch": 9.557911908646004, "percentage": 95.58, "elapsed_time": "7:59:54", "remaining_time": "0:22:11", "throughput": 4391.68, "total_tokens": 126456208} {"current_steps": 58595, "total_steps": 61300, "loss": 0.3348, "lr": 2.9621011847330293e-07, "epoch": 9.558727569331158, "percentage": 95.59, "elapsed_time": "7:59:56", "remaining_time": "0:22:09", "throughput": 4391.72, "total_tokens": 126467312} {"current_steps": 58600, "total_steps": 61300, "loss": 0.3096, "lr": 2.951186445868337e-07, "epoch": 9.559543230016313, "percentage": 95.6, "elapsed_time": "7:59:58", "remaining_time": "0:22:06", "throughput": 4391.74, "total_tokens": 126476656} {"current_steps": 58605, "total_steps": 61300, "loss": 0.3133, "lr": 2.940291734034012e-07, "epoch": 9.560358890701469, "percentage": 95.6, "elapsed_time": "8:00:01", "remaining_time": "0:22:04", "throughput": 4391.78, "total_tokens": 126487920} {"current_steps": 58610, "total_steps": 61300, "loss": 0.3441, "lr": 2.929417050113181e-07, "epoch": 9.561174551386623, "percentage": 95.61, "elapsed_time": "8:00:03", "remaining_time": "0:22:01", "throughput": 4391.82, "total_tokens": 126499216} {"current_steps": 58615, "total_steps": 61300, "loss": 0.3487, "lr": 2.918562394987445e-07, "epoch": 9.561990212071779, "percentage": 95.62, "elapsed_time": "8:00:05", "remaining_time": "0:21:59", "throughput": 4391.85, "total_tokens": 126509936} {"current_steps": 58620, "total_steps": 61300, "loss": 0.3504, "lr": 2.907727769536683e-07, "epoch": 9.562805872756933, "percentage": 95.63, "elapsed_time": "8:00:08", "remaining_time": "0:21:57", "throughput": 4391.88, "total_tokens": 126521776} {"current_steps": 58625, "total_steps": 61300, "loss": 0.3212, "lr": 2.8969131746392763e-07, "epoch": 9.563621533442088, "percentage": 95.64, "elapsed_time": "8:00:10", "remaining_time": "0:21:54", "throughput": 4391.92, "total_tokens": 126532464} {"current_steps": 58630, "total_steps": 61300, "loss": 0.3138, "lr": 2.886118611171884e-07, "epoch": 9.564437194127244, "percentage": 95.64, "elapsed_time": "8:00:12", "remaining_time": "0:21:52", "throughput": 4391.95, "total_tokens": 126542992} {"current_steps": 58635, "total_steps": 61300, "loss": 0.3189, "lr": 2.875344080009529e-07, "epoch": 9.565252854812398, "percentage": 95.65, "elapsed_time": "8:00:14", "remaining_time": "0:21:49", "throughput": 4391.98, "total_tokens": 126553680} {"current_steps": 58640, "total_steps": 61300, "loss": 0.3255, "lr": 2.8645895820257065e-07, "epoch": 9.566068515497554, "percentage": 95.66, "elapsed_time": "8:00:16", "remaining_time": "0:21:47", "throughput": 4392.01, "total_tokens": 126563440} {"current_steps": 58645, "total_steps": 61300, "loss": 0.3173, "lr": 2.8538551180921913e-07, "epoch": 9.566884176182707, "percentage": 95.67, "elapsed_time": "8:00:18", "remaining_time": "0:21:44", "throughput": 4392.04, "total_tokens": 126573904} {"current_steps": 58650, "total_steps": 61300, "loss": 0.3309, "lr": 2.8431406890792045e-07, "epoch": 9.567699836867863, "percentage": 95.68, "elapsed_time": "8:00:21", "remaining_time": "0:21:42", "throughput": 4392.07, "total_tokens": 126584560} {"current_steps": 58655, "total_steps": 61300, "loss": 0.3411, "lr": 2.8324462958552735e-07, "epoch": 9.568515497553017, "percentage": 95.69, "elapsed_time": "8:00:23", "remaining_time": "0:21:39", "throughput": 4392.1, "total_tokens": 126595632} {"current_steps": 58660, "total_steps": 61300, "loss": 0.3143, "lr": 2.821771939287371e-07, "epoch": 9.569331158238173, "percentage": 95.69, "elapsed_time": "8:00:25", "remaining_time": "0:21:37", "throughput": 4392.14, "total_tokens": 126606800} {"current_steps": 58665, "total_steps": 61300, "loss": 0.3324, "lr": 2.811117620240833e-07, "epoch": 9.570146818923329, "percentage": 95.7, "elapsed_time": "8:00:28", "remaining_time": "0:21:34", "throughput": 4392.17, "total_tokens": 126617808} {"current_steps": 58670, "total_steps": 61300, "loss": 0.3441, "lr": 2.800483339579274e-07, "epoch": 9.570962479608482, "percentage": 95.71, "elapsed_time": "8:00:30", "remaining_time": "0:21:32", "throughput": 4392.19, "total_tokens": 126628720} {"current_steps": 58675, "total_steps": 61300, "loss": 0.33, "lr": 2.789869098164838e-07, "epoch": 9.571778140293638, "percentage": 95.72, "elapsed_time": "8:00:32", "remaining_time": "0:21:29", "throughput": 4392.23, "total_tokens": 126639664} {"current_steps": 58680, "total_steps": 61300, "loss": 0.3155, "lr": 2.779274896857947e-07, "epoch": 9.572593800978792, "percentage": 95.73, "elapsed_time": "8:00:34", "remaining_time": "0:21:27", "throughput": 4392.26, "total_tokens": 126650736} {"current_steps": 58685, "total_steps": 61300, "loss": 0.293, "lr": 2.768700736517416e-07, "epoch": 9.573409461663948, "percentage": 95.73, "elapsed_time": "8:00:37", "remaining_time": "0:21:24", "throughput": 4392.3, "total_tokens": 126662224} {"current_steps": 58690, "total_steps": 61300, "loss": 0.3827, "lr": 2.7581466180004454e-07, "epoch": 9.574225122349104, "percentage": 95.74, "elapsed_time": "8:00:39", "remaining_time": "0:21:22", "throughput": 4392.33, "total_tokens": 126673040} {"current_steps": 58695, "total_steps": 61300, "loss": 0.3323, "lr": 2.747612542162603e-07, "epoch": 9.575040783034257, "percentage": 95.75, "elapsed_time": "8:00:41", "remaining_time": "0:21:20", "throughput": 4392.37, "total_tokens": 126683824} {"current_steps": 58700, "total_steps": 61300, "loss": 0.3619, "lr": 2.737098509857816e-07, "epoch": 9.575856443719413, "percentage": 95.76, "elapsed_time": "8:00:43", "remaining_time": "0:21:17", "throughput": 4392.4, "total_tokens": 126693488} {"current_steps": 58705, "total_steps": 61300, "loss": 0.3431, "lr": 2.726604521938458e-07, "epoch": 9.576672104404567, "percentage": 95.77, "elapsed_time": "8:00:45", "remaining_time": "0:21:15", "throughput": 4392.43, "total_tokens": 126703888} {"current_steps": 58710, "total_steps": 61300, "loss": 0.3303, "lr": 2.716130579255155e-07, "epoch": 9.577487765089723, "percentage": 95.77, "elapsed_time": "8:00:48", "remaining_time": "0:21:12", "throughput": 4392.47, "total_tokens": 126715440} {"current_steps": 58715, "total_steps": 61300, "loss": 0.3337, "lr": 2.7056766826570045e-07, "epoch": 9.578303425774878, "percentage": 95.78, "elapsed_time": "8:00:50", "remaining_time": "0:21:10", "throughput": 4392.5, "total_tokens": 126725680} {"current_steps": 58720, "total_steps": 61300, "loss": 0.3087, "lr": 2.6952428329914956e-07, "epoch": 9.579119086460032, "percentage": 95.79, "elapsed_time": "8:00:52", "remaining_time": "0:21:07", "throughput": 4392.53, "total_tokens": 126736144} {"current_steps": 58725, "total_steps": 61300, "loss": 0.3136, "lr": 2.684829031104397e-07, "epoch": 9.579934747145188, "percentage": 95.8, "elapsed_time": "8:00:55", "remaining_time": "0:21:05", "throughput": 4392.57, "total_tokens": 126747504} {"current_steps": 58730, "total_steps": 61300, "loss": 0.3328, "lr": 2.6744352778399204e-07, "epoch": 9.580750407830342, "percentage": 95.81, "elapsed_time": "8:00:57", "remaining_time": "0:21:02", "throughput": 4392.59, "total_tokens": 126757904} {"current_steps": 58735, "total_steps": 61300, "loss": 0.3671, "lr": 2.6640615740406436e-07, "epoch": 9.581566068515498, "percentage": 95.82, "elapsed_time": "8:00:59", "remaining_time": "0:21:00", "throughput": 4392.63, "total_tokens": 126768400} {"current_steps": 58740, "total_steps": 61300, "loss": 0.3396, "lr": 2.6537079205475323e-07, "epoch": 9.582381729200652, "percentage": 95.82, "elapsed_time": "8:01:01", "remaining_time": "0:20:57", "throughput": 4392.66, "total_tokens": 126779440} {"current_steps": 58745, "total_steps": 61300, "loss": 0.3068, "lr": 2.6433743181998316e-07, "epoch": 9.583197389885807, "percentage": 95.83, "elapsed_time": "8:01:03", "remaining_time": "0:20:55", "throughput": 4392.69, "total_tokens": 126790672} {"current_steps": 58750, "total_steps": 61300, "loss": 0.3137, "lr": 2.633060767835316e-07, "epoch": 9.584013050570963, "percentage": 95.84, "elapsed_time": "8:01:05", "remaining_time": "0:20:52", "throughput": 4392.71, "total_tokens": 126799824} {"current_steps": 58755, "total_steps": 61300, "loss": 0.3659, "lr": 2.6227672702900106e-07, "epoch": 9.584828711256117, "percentage": 95.85, "elapsed_time": "8:01:08", "remaining_time": "0:20:50", "throughput": 4392.75, "total_tokens": 126811248} {"current_steps": 58760, "total_steps": 61300, "loss": 0.2843, "lr": 2.61249382639836e-07, "epoch": 9.585644371941273, "percentage": 95.86, "elapsed_time": "8:01:10", "remaining_time": "0:20:47", "throughput": 4392.78, "total_tokens": 126822256} {"current_steps": 58765, "total_steps": 61300, "loss": 0.3246, "lr": 2.6022404369931976e-07, "epoch": 9.586460032626427, "percentage": 95.86, "elapsed_time": "8:01:13", "remaining_time": "0:20:45", "throughput": 4392.82, "total_tokens": 126833840} {"current_steps": 58770, "total_steps": 61300, "loss": 0.3079, "lr": 2.592007102905719e-07, "epoch": 9.587275693311582, "percentage": 95.87, "elapsed_time": "8:01:15", "remaining_time": "0:20:43", "throughput": 4392.86, "total_tokens": 126846160} {"current_steps": 58775, "total_steps": 61300, "loss": 0.3484, "lr": 2.581793824965484e-07, "epoch": 9.588091353996738, "percentage": 95.88, "elapsed_time": "8:01:18", "remaining_time": "0:20:40", "throughput": 4392.89, "total_tokens": 126857904} {"current_steps": 58780, "total_steps": 61300, "loss": 0.325, "lr": 2.5716006040004123e-07, "epoch": 9.588907014681892, "percentage": 95.89, "elapsed_time": "8:01:20", "remaining_time": "0:20:38", "throughput": 4392.92, "total_tokens": 126869232} {"current_steps": 58785, "total_steps": 61300, "loss": 0.3045, "lr": 2.5614274408368444e-07, "epoch": 9.589722675367048, "percentage": 95.9, "elapsed_time": "8:01:22", "remaining_time": "0:20:35", "throughput": 4392.96, "total_tokens": 126880784} {"current_steps": 58790, "total_steps": 61300, "loss": 0.3049, "lr": 2.5512743362994527e-07, "epoch": 9.590538336052202, "percentage": 95.91, "elapsed_time": "8:01:25", "remaining_time": "0:20:33", "throughput": 4392.99, "total_tokens": 126891600} {"current_steps": 58795, "total_steps": 61300, "loss": 0.3919, "lr": 2.541141291211302e-07, "epoch": 9.591353996737357, "percentage": 95.91, "elapsed_time": "8:01:27", "remaining_time": "0:20:30", "throughput": 4393.03, "total_tokens": 126903056} {"current_steps": 58800, "total_steps": 61300, "loss": 0.3537, "lr": 2.5310283063938457e-07, "epoch": 9.592169657422513, "percentage": 95.92, "elapsed_time": "8:01:29", "remaining_time": "0:20:28", "throughput": 4393.07, "total_tokens": 126914032} {"current_steps": 58805, "total_steps": 61300, "loss": 0.3687, "lr": 2.5209353826668726e-07, "epoch": 9.592985318107667, "percentage": 95.93, "elapsed_time": "8:01:31", "remaining_time": "0:20:25", "throughput": 4393.09, "total_tokens": 126923920} {"current_steps": 58810, "total_steps": 61300, "loss": 0.3207, "lr": 2.510862520848589e-07, "epoch": 9.593800978792823, "percentage": 95.94, "elapsed_time": "8:01:34", "remaining_time": "0:20:23", "throughput": 4393.13, "total_tokens": 126935216} {"current_steps": 58815, "total_steps": 61300, "loss": 0.3327, "lr": 2.500809721755509e-07, "epoch": 9.594616639477977, "percentage": 95.95, "elapsed_time": "8:01:36", "remaining_time": "0:20:20", "throughput": 4393.15, "total_tokens": 126944752} {"current_steps": 58820, "total_steps": 61300, "loss": 0.3381, "lr": 2.490776986202592e-07, "epoch": 9.595432300163132, "percentage": 95.95, "elapsed_time": "8:01:38", "remaining_time": "0:20:18", "throughput": 4393.19, "total_tokens": 126955856} {"current_steps": 58825, "total_steps": 61300, "loss": 0.3383, "lr": 2.480764315003159e-07, "epoch": 9.596247960848288, "percentage": 95.96, "elapsed_time": "8:01:40", "remaining_time": "0:20:15", "throughput": 4393.21, "total_tokens": 126966064} {"current_steps": 58830, "total_steps": 61300, "loss": 0.339, "lr": 2.470771708968866e-07, "epoch": 9.597063621533442, "percentage": 95.97, "elapsed_time": "8:01:42", "remaining_time": "0:20:13", "throughput": 4393.25, "total_tokens": 126977424} {"current_steps": 58835, "total_steps": 61300, "loss": 0.3556, "lr": 2.4607991689097607e-07, "epoch": 9.597879282218598, "percentage": 95.98, "elapsed_time": "8:01:44", "remaining_time": "0:20:11", "throughput": 4393.28, "total_tokens": 126987728} {"current_steps": 58840, "total_steps": 61300, "loss": 0.3354, "lr": 2.4508466956343066e-07, "epoch": 9.598694942903752, "percentage": 95.99, "elapsed_time": "8:01:47", "remaining_time": "0:20:08", "throughput": 4393.33, "total_tokens": 126999536} {"current_steps": 58845, "total_steps": 61300, "loss": 0.3376, "lr": 2.4409142899492474e-07, "epoch": 9.599510603588907, "percentage": 96.0, "elapsed_time": "8:01:49", "remaining_time": "0:20:06", "throughput": 4393.36, "total_tokens": 127010384} {"current_steps": 58850, "total_steps": 61300, "loss": 0.3304, "lr": 2.4310019526597726e-07, "epoch": 9.600326264274061, "percentage": 96.0, "elapsed_time": "8:01:51", "remaining_time": "0:20:03", "throughput": 4393.39, "total_tokens": 127020176} {"current_steps": 58855, "total_steps": 61300, "loss": 0.3382, "lr": 2.4211096845694336e-07, "epoch": 9.601141924959217, "percentage": 96.01, "elapsed_time": "8:01:53", "remaining_time": "0:20:01", "throughput": 4393.43, "total_tokens": 127030192} {"current_steps": 58860, "total_steps": 61300, "loss": 0.3465, "lr": 2.411237486480145e-07, "epoch": 9.601957585644373, "percentage": 96.02, "elapsed_time": "8:01:56", "remaining_time": "0:19:58", "throughput": 4393.47, "total_tokens": 127041808} {"current_steps": 58865, "total_steps": 61300, "loss": 0.3215, "lr": 2.4013853591922097e-07, "epoch": 9.602773246329527, "percentage": 96.03, "elapsed_time": "8:01:58", "remaining_time": "0:19:56", "throughput": 4393.5, "total_tokens": 127052400} {"current_steps": 58870, "total_steps": 61300, "loss": 0.3407, "lr": 2.391553303504296e-07, "epoch": 9.603588907014682, "percentage": 96.04, "elapsed_time": "8:02:00", "remaining_time": "0:19:53", "throughput": 4393.53, "total_tokens": 127063056} {"current_steps": 58875, "total_steps": 61300, "loss": 0.3221, "lr": 2.3817413202134041e-07, "epoch": 9.604404567699836, "percentage": 96.04, "elapsed_time": "8:02:02", "remaining_time": "0:19:51", "throughput": 4393.56, "total_tokens": 127073840} {"current_steps": 58880, "total_steps": 61300, "loss": 0.3171, "lr": 2.3719494101149543e-07, "epoch": 9.605220228384992, "percentage": 96.05, "elapsed_time": "8:02:04", "remaining_time": "0:19:48", "throughput": 4393.6, "total_tokens": 127084656} {"current_steps": 58885, "total_steps": 61300, "loss": 0.3169, "lr": 2.3621775740027553e-07, "epoch": 9.606035889070148, "percentage": 96.06, "elapsed_time": "8:02:07", "remaining_time": "0:19:46", "throughput": 4393.64, "total_tokens": 127095984} {"current_steps": 58890, "total_steps": 61300, "loss": 0.3157, "lr": 2.3524258126689235e-07, "epoch": 9.606851549755302, "percentage": 96.07, "elapsed_time": "8:02:09", "remaining_time": "0:19:43", "throughput": 4393.66, "total_tokens": 127105776} {"current_steps": 58895, "total_steps": 61300, "loss": 0.3349, "lr": 2.3426941269040213e-07, "epoch": 9.607667210440457, "percentage": 96.08, "elapsed_time": "8:02:11", "remaining_time": "0:19:41", "throughput": 4393.7, "total_tokens": 127117424} {"current_steps": 58900, "total_steps": 61300, "loss": 0.3542, "lr": 2.3329825174969455e-07, "epoch": 9.608482871125611, "percentage": 96.08, "elapsed_time": "8:02:13", "remaining_time": "0:19:38", "throughput": 4393.74, "total_tokens": 127128240} {"current_steps": 58905, "total_steps": 61300, "loss": 0.3233, "lr": 2.3232909852349273e-07, "epoch": 9.609298531810767, "percentage": 96.09, "elapsed_time": "8:02:16", "remaining_time": "0:19:36", "throughput": 4393.77, "total_tokens": 127140176} {"current_steps": 58910, "total_steps": 61300, "loss": 0.3477, "lr": 2.3136195309036435e-07, "epoch": 9.61011419249592, "percentage": 96.1, "elapsed_time": "8:02:18", "remaining_time": "0:19:34", "throughput": 4393.81, "total_tokens": 127149392} {"current_steps": 58915, "total_steps": 61300, "loss": 0.3113, "lr": 2.303968155287134e-07, "epoch": 9.610929853181077, "percentage": 96.11, "elapsed_time": "8:02:20", "remaining_time": "0:19:31", "throughput": 4393.84, "total_tokens": 127160496} {"current_steps": 58920, "total_steps": 61300, "loss": 0.3049, "lr": 2.294336859167745e-07, "epoch": 9.611745513866232, "percentage": 96.12, "elapsed_time": "8:02:22", "remaining_time": "0:19:29", "throughput": 4393.86, "total_tokens": 127170544} {"current_steps": 58925, "total_steps": 61300, "loss": 0.3327, "lr": 2.2847256433262686e-07, "epoch": 9.612561174551386, "percentage": 96.13, "elapsed_time": "8:02:25", "remaining_time": "0:19:26", "throughput": 4393.9, "total_tokens": 127182992} {"current_steps": 58930, "total_steps": 61300, "loss": 0.3581, "lr": 2.2751345085418042e-07, "epoch": 9.613376835236542, "percentage": 96.13, "elapsed_time": "8:02:27", "remaining_time": "0:19:24", "throughput": 4393.94, "total_tokens": 127194320} {"current_steps": 58935, "total_steps": 61300, "loss": 0.3362, "lr": 2.265563455591896e-07, "epoch": 9.614192495921696, "percentage": 96.14, "elapsed_time": "8:02:30", "remaining_time": "0:19:21", "throughput": 4393.97, "total_tokens": 127205776} {"current_steps": 58940, "total_steps": 61300, "loss": 0.3034, "lr": 2.2560124852523955e-07, "epoch": 9.615008156606851, "percentage": 96.15, "elapsed_time": "8:02:32", "remaining_time": "0:19:19", "throughput": 4394.01, "total_tokens": 127217264} {"current_steps": 58945, "total_steps": 61300, "loss": 0.3228, "lr": 2.246481598297573e-07, "epoch": 9.615823817292007, "percentage": 96.16, "elapsed_time": "8:02:34", "remaining_time": "0:19:16", "throughput": 4394.05, "total_tokens": 127229584} {"current_steps": 58950, "total_steps": 61300, "loss": 0.3397, "lr": 2.2369707955000318e-07, "epoch": 9.616639477977161, "percentage": 96.17, "elapsed_time": "8:02:37", "remaining_time": "0:19:14", "throughput": 4394.08, "total_tokens": 127239824} {"current_steps": 58955, "total_steps": 61300, "loss": 0.3278, "lr": 2.2274800776307946e-07, "epoch": 9.617455138662317, "percentage": 96.17, "elapsed_time": "8:02:39", "remaining_time": "0:19:11", "throughput": 4394.11, "total_tokens": 127250672} {"current_steps": 58960, "total_steps": 61300, "loss": 0.34, "lr": 2.2180094454591903e-07, "epoch": 9.61827079934747, "percentage": 96.18, "elapsed_time": "8:02:41", "remaining_time": "0:19:09", "throughput": 4394.13, "total_tokens": 127260496} {"current_steps": 58965, "total_steps": 61300, "loss": 0.2827, "lr": 2.2085588997529938e-07, "epoch": 9.619086460032626, "percentage": 96.19, "elapsed_time": "8:02:43", "remaining_time": "0:19:06", "throughput": 4394.17, "total_tokens": 127272336} {"current_steps": 58970, "total_steps": 61300, "loss": 0.3299, "lr": 2.1991284412782864e-07, "epoch": 9.619902120717782, "percentage": 96.2, "elapsed_time": "8:02:46", "remaining_time": "0:19:04", "throughput": 4394.22, "total_tokens": 127284368} {"current_steps": 58975, "total_steps": 61300, "loss": 0.3071, "lr": 2.18971807079954e-07, "epoch": 9.620717781402936, "percentage": 96.21, "elapsed_time": "8:02:48", "remaining_time": "0:19:02", "throughput": 4394.25, "total_tokens": 127294032} {"current_steps": 58980, "total_steps": 61300, "loss": 0.3403, "lr": 2.1803277890796447e-07, "epoch": 9.621533442088092, "percentage": 96.22, "elapsed_time": "8:02:50", "remaining_time": "0:18:59", "throughput": 4394.28, "total_tokens": 127304080} {"current_steps": 58985, "total_steps": 61300, "loss": 0.3396, "lr": 2.170957596879797e-07, "epoch": 9.622349102773246, "percentage": 96.22, "elapsed_time": "8:02:52", "remaining_time": "0:18:57", "throughput": 4394.31, "total_tokens": 127315888} {"current_steps": 58990, "total_steps": 61300, "loss": 0.2877, "lr": 2.1616074949595832e-07, "epoch": 9.623164763458401, "percentage": 96.23, "elapsed_time": "8:02:55", "remaining_time": "0:18:54", "throughput": 4394.35, "total_tokens": 127326864} {"current_steps": 58995, "total_steps": 61300, "loss": 0.3223, "lr": 2.1522774840770087e-07, "epoch": 9.623980424143557, "percentage": 96.24, "elapsed_time": "8:02:57", "remaining_time": "0:18:52", "throughput": 4394.37, "total_tokens": 127336368} {"current_steps": 59000, "total_steps": 61300, "loss": 0.3187, "lr": 2.1429675649883575e-07, "epoch": 9.624796084828711, "percentage": 96.25, "elapsed_time": "8:02:59", "remaining_time": "0:18:49", "throughput": 4394.41, "total_tokens": 127347824} {"current_steps": 59005, "total_steps": 61300, "loss": 0.3137, "lr": 2.1336777384484141e-07, "epoch": 9.625611745513867, "percentage": 96.26, "elapsed_time": "8:03:01", "remaining_time": "0:18:47", "throughput": 4394.44, "total_tokens": 127356656} {"current_steps": 59010, "total_steps": 61300, "loss": 0.3204, "lr": 2.1244080052101879e-07, "epoch": 9.62642740619902, "percentage": 96.26, "elapsed_time": "8:03:03", "remaining_time": "0:18:44", "throughput": 4394.47, "total_tokens": 127367120} {"current_steps": 59015, "total_steps": 61300, "loss": 0.3081, "lr": 2.115158366025133e-07, "epoch": 9.627243066884176, "percentage": 96.27, "elapsed_time": "8:03:05", "remaining_time": "0:18:42", "throughput": 4394.51, "total_tokens": 127378800} {"current_steps": 59020, "total_steps": 61300, "loss": 0.3129, "lr": 2.1059288216431217e-07, "epoch": 9.62805872756933, "percentage": 96.28, "elapsed_time": "8:03:08", "remaining_time": "0:18:39", "throughput": 4394.55, "total_tokens": 127390000} {"current_steps": 59025, "total_steps": 61300, "loss": 0.3104, "lr": 2.0967193728123334e-07, "epoch": 9.628874388254486, "percentage": 96.29, "elapsed_time": "8:03:10", "remaining_time": "0:18:37", "throughput": 4394.58, "total_tokens": 127400144} {"current_steps": 59030, "total_steps": 61300, "loss": 0.308, "lr": 2.0875300202793101e-07, "epoch": 9.629690048939642, "percentage": 96.3, "elapsed_time": "8:03:12", "remaining_time": "0:18:34", "throughput": 4394.62, "total_tokens": 127411568} {"current_steps": 59035, "total_steps": 61300, "loss": 0.3353, "lr": 2.0783607647889837e-07, "epoch": 9.630505709624796, "percentage": 96.31, "elapsed_time": "8:03:14", "remaining_time": "0:18:32", "throughput": 4394.65, "total_tokens": 127421520} {"current_steps": 59040, "total_steps": 61300, "loss": 0.3287, "lr": 2.0692116070847035e-07, "epoch": 9.631321370309951, "percentage": 96.31, "elapsed_time": "8:03:17", "remaining_time": "0:18:29", "throughput": 4394.69, "total_tokens": 127433424} {"current_steps": 59045, "total_steps": 61300, "loss": 0.334, "lr": 2.0600825479080986e-07, "epoch": 9.632137030995105, "percentage": 96.32, "elapsed_time": "8:03:19", "remaining_time": "0:18:27", "throughput": 4394.72, "total_tokens": 127443408} {"current_steps": 59050, "total_steps": 61300, "loss": 0.3644, "lr": 2.0509735879992442e-07, "epoch": 9.632952691680261, "percentage": 96.33, "elapsed_time": "8:03:21", "remaining_time": "0:18:25", "throughput": 4394.75, "total_tokens": 127454256} {"current_steps": 59055, "total_steps": 61300, "loss": 0.315, "lr": 2.041884728096549e-07, "epoch": 9.633768352365417, "percentage": 96.34, "elapsed_time": "8:03:23", "remaining_time": "0:18:22", "throughput": 4394.78, "total_tokens": 127464624} {"current_steps": 59060, "total_steps": 61300, "loss": 0.315, "lr": 2.0328159689368133e-07, "epoch": 9.63458401305057, "percentage": 96.35, "elapsed_time": "8:03:25", "remaining_time": "0:18:20", "throughput": 4394.82, "total_tokens": 127474192} {"current_steps": 59065, "total_steps": 61300, "loss": 0.3508, "lr": 2.0237673112551704e-07, "epoch": 9.635399673735726, "percentage": 96.35, "elapsed_time": "8:03:27", "remaining_time": "0:18:17", "throughput": 4394.84, "total_tokens": 127483056} {"current_steps": 59070, "total_steps": 61300, "loss": 0.3452, "lr": 2.0147387557851727e-07, "epoch": 9.63621533442088, "percentage": 96.36, "elapsed_time": "8:03:29", "remaining_time": "0:18:15", "throughput": 4394.87, "total_tokens": 127493360} {"current_steps": 59075, "total_steps": 61300, "loss": 0.3185, "lr": 2.005730303258735e-07, "epoch": 9.637030995106036, "percentage": 96.37, "elapsed_time": "8:03:31", "remaining_time": "0:18:12", "throughput": 4394.9, "total_tokens": 127503728} {"current_steps": 59080, "total_steps": 61300, "loss": 0.358, "lr": 1.9967419544060784e-07, "epoch": 9.63784665579119, "percentage": 96.38, "elapsed_time": "8:03:34", "remaining_time": "0:18:10", "throughput": 4394.93, "total_tokens": 127514672} {"current_steps": 59085, "total_steps": 61300, "loss": 0.3142, "lr": 1.987773709955898e-07, "epoch": 9.638662316476346, "percentage": 96.39, "elapsed_time": "8:03:36", "remaining_time": "0:18:07", "throughput": 4394.96, "total_tokens": 127525200} {"current_steps": 59090, "total_steps": 61300, "loss": 0.3348, "lr": 1.9788255706351678e-07, "epoch": 9.639477977161501, "percentage": 96.39, "elapsed_time": "8:03:38", "remaining_time": "0:18:05", "throughput": 4395.0, "total_tokens": 127535824} {"current_steps": 59095, "total_steps": 61300, "loss": 0.3093, "lr": 1.9698975371693075e-07, "epoch": 9.640293637846655, "percentage": 96.4, "elapsed_time": "8:03:40", "remaining_time": "0:18:02", "throughput": 4395.03, "total_tokens": 127546960} {"current_steps": 59100, "total_steps": 61300, "loss": 0.3553, "lr": 1.9609896102820157e-07, "epoch": 9.641109298531811, "percentage": 96.41, "elapsed_time": "8:03:42", "remaining_time": "0:18:00", "throughput": 4395.06, "total_tokens": 127557680} {"current_steps": 59105, "total_steps": 61300, "loss": 0.3043, "lr": 1.9521017906954654e-07, "epoch": 9.641924959216965, "percentage": 96.42, "elapsed_time": "8:03:45", "remaining_time": "0:17:57", "throughput": 4395.09, "total_tokens": 127567696} {"current_steps": 59110, "total_steps": 61300, "loss": 0.3383, "lr": 1.9432340791301073e-07, "epoch": 9.64274061990212, "percentage": 96.43, "elapsed_time": "8:03:47", "remaining_time": "0:17:55", "throughput": 4395.13, "total_tokens": 127578736} {"current_steps": 59115, "total_steps": 61300, "loss": 0.3297, "lr": 1.9343864763048392e-07, "epoch": 9.643556280587276, "percentage": 96.44, "elapsed_time": "8:03:49", "remaining_time": "0:17:52", "throughput": 4395.16, "total_tokens": 127590224} {"current_steps": 59120, "total_steps": 61300, "loss": 0.323, "lr": 1.925558982936865e-07, "epoch": 9.64437194127243, "percentage": 96.44, "elapsed_time": "8:03:51", "remaining_time": "0:17:50", "throughput": 4395.2, "total_tokens": 127601328} {"current_steps": 59125, "total_steps": 61300, "loss": 0.3146, "lr": 1.916751599741806e-07, "epoch": 9.645187601957586, "percentage": 96.45, "elapsed_time": "8:03:54", "remaining_time": "0:17:48", "throughput": 4395.23, "total_tokens": 127612464} {"current_steps": 59130, "total_steps": 61300, "loss": 0.3129, "lr": 1.90796432743362e-07, "epoch": 9.64600326264274, "percentage": 96.46, "elapsed_time": "8:03:56", "remaining_time": "0:17:45", "throughput": 4395.26, "total_tokens": 127622864} {"current_steps": 59135, "total_steps": 61300, "loss": 0.3857, "lr": 1.8991971667246533e-07, "epoch": 9.646818923327896, "percentage": 96.47, "elapsed_time": "8:03:58", "remaining_time": "0:17:43", "throughput": 4395.29, "total_tokens": 127634000} {"current_steps": 59140, "total_steps": 61300, "loss": 0.3191, "lr": 1.8904501183256152e-07, "epoch": 9.647634584013051, "percentage": 96.48, "elapsed_time": "8:04:01", "remaining_time": "0:17:40", "throughput": 4395.32, "total_tokens": 127645264} {"current_steps": 59145, "total_steps": 61300, "loss": 0.332, "lr": 1.8817231829455773e-07, "epoch": 9.648450244698205, "percentage": 96.48, "elapsed_time": "8:04:03", "remaining_time": "0:17:38", "throughput": 4395.35, "total_tokens": 127655376} {"current_steps": 59150, "total_steps": 61300, "loss": 0.3237, "lr": 1.8730163612920015e-07, "epoch": 9.649265905383361, "percentage": 96.49, "elapsed_time": "8:04:05", "remaining_time": "0:17:35", "throughput": 4395.38, "total_tokens": 127665584} {"current_steps": 59155, "total_steps": 61300, "loss": 0.3438, "lr": 1.8643296540707121e-07, "epoch": 9.650081566068515, "percentage": 96.5, "elapsed_time": "8:04:07", "remaining_time": "0:17:33", "throughput": 4395.41, "total_tokens": 127675920} {"current_steps": 59160, "total_steps": 61300, "loss": 0.3506, "lr": 1.855663061985896e-07, "epoch": 9.65089722675367, "percentage": 96.51, "elapsed_time": "8:04:09", "remaining_time": "0:17:30", "throughput": 4395.45, "total_tokens": 127686928} {"current_steps": 59165, "total_steps": 61300, "loss": 0.3253, "lr": 1.8470165857401023e-07, "epoch": 9.651712887438826, "percentage": 96.52, "elapsed_time": "8:04:11", "remaining_time": "0:17:28", "throughput": 4395.48, "total_tokens": 127697296} {"current_steps": 59170, "total_steps": 61300, "loss": 0.324, "lr": 1.8383902260342422e-07, "epoch": 9.65252854812398, "percentage": 96.53, "elapsed_time": "8:04:14", "remaining_time": "0:17:25", "throughput": 4395.51, "total_tokens": 127707312} {"current_steps": 59175, "total_steps": 61300, "loss": 0.3345, "lr": 1.8297839835676456e-07, "epoch": 9.653344208809136, "percentage": 96.53, "elapsed_time": "8:04:16", "remaining_time": "0:17:23", "throughput": 4395.54, "total_tokens": 127719056} {"current_steps": 59180, "total_steps": 61300, "loss": 0.3266, "lr": 1.8211978590379486e-07, "epoch": 9.65415986949429, "percentage": 96.54, "elapsed_time": "8:04:18", "remaining_time": "0:17:20", "throughput": 4395.58, "total_tokens": 127730864} {"current_steps": 59185, "total_steps": 61300, "loss": 0.3205, "lr": 1.8126318531412056e-07, "epoch": 9.654975530179446, "percentage": 96.55, "elapsed_time": "8:04:21", "remaining_time": "0:17:18", "throughput": 4395.61, "total_tokens": 127740944} {"current_steps": 59190, "total_steps": 61300, "loss": 0.324, "lr": 1.8040859665718057e-07, "epoch": 9.655791190864601, "percentage": 96.56, "elapsed_time": "8:04:23", "remaining_time": "0:17:16", "throughput": 4395.64, "total_tokens": 127752016} {"current_steps": 59195, "total_steps": 61300, "loss": 0.3157, "lr": 1.795560200022528e-07, "epoch": 9.656606851549755, "percentage": 96.57, "elapsed_time": "8:04:25", "remaining_time": "0:17:13", "throughput": 4395.68, "total_tokens": 127762480} {"current_steps": 59200, "total_steps": 61300, "loss": 0.3009, "lr": 1.7870545541845418e-07, "epoch": 9.65742251223491, "percentage": 96.57, "elapsed_time": "8:04:27", "remaining_time": "0:17:11", "throughput": 4395.7, "total_tokens": 127773232} {"current_steps": 59205, "total_steps": 61300, "loss": 0.3284, "lr": 1.7785690297473234e-07, "epoch": 9.658238172920065, "percentage": 96.58, "elapsed_time": "8:04:30", "remaining_time": "0:17:08", "throughput": 4395.73, "total_tokens": 127784112} {"current_steps": 59210, "total_steps": 61300, "loss": 0.3016, "lr": 1.770103627398767e-07, "epoch": 9.65905383360522, "percentage": 96.59, "elapsed_time": "8:04:32", "remaining_time": "0:17:06", "throughput": 4395.77, "total_tokens": 127795600} {"current_steps": 59215, "total_steps": 61300, "loss": 0.3423, "lr": 1.7616583478251013e-07, "epoch": 9.659869494290374, "percentage": 96.6, "elapsed_time": "8:04:34", "remaining_time": "0:17:03", "throughput": 4395.8, "total_tokens": 127805648} {"current_steps": 59220, "total_steps": 61300, "loss": 0.2991, "lr": 1.7532331917109457e-07, "epoch": 9.66068515497553, "percentage": 96.61, "elapsed_time": "8:04:36", "remaining_time": "0:17:01", "throughput": 4395.84, "total_tokens": 127816560} {"current_steps": 59225, "total_steps": 61300, "loss": 0.3463, "lr": 1.7448281597393368e-07, "epoch": 9.661500815660686, "percentage": 96.62, "elapsed_time": "8:04:39", "remaining_time": "0:16:58", "throughput": 4395.88, "total_tokens": 127828784} {"current_steps": 59230, "total_steps": 61300, "loss": 0.3705, "lr": 1.736443252591563e-07, "epoch": 9.66231647634584, "percentage": 96.62, "elapsed_time": "8:04:41", "remaining_time": "0:16:56", "throughput": 4395.91, "total_tokens": 127839088} {"current_steps": 59235, "total_steps": 61300, "loss": 0.32, "lr": 1.7280784709473862e-07, "epoch": 9.663132137030995, "percentage": 96.63, "elapsed_time": "8:04:43", "remaining_time": "0:16:53", "throughput": 4395.93, "total_tokens": 127848016} {"current_steps": 59240, "total_steps": 61300, "loss": 0.3145, "lr": 1.719733815484903e-07, "epoch": 9.66394779771615, "percentage": 96.64, "elapsed_time": "8:04:45", "remaining_time": "0:16:51", "throughput": 4395.96, "total_tokens": 127858320} {"current_steps": 59245, "total_steps": 61300, "loss": 0.3559, "lr": 1.7114092868805443e-07, "epoch": 9.664763458401305, "percentage": 96.65, "elapsed_time": "8:04:47", "remaining_time": "0:16:48", "throughput": 4396.0, "total_tokens": 127869936} {"current_steps": 59250, "total_steps": 61300, "loss": 0.3397, "lr": 1.7031048858091313e-07, "epoch": 9.66557911908646, "percentage": 96.66, "elapsed_time": "8:04:50", "remaining_time": "0:16:46", "throughput": 4396.03, "total_tokens": 127881040} {"current_steps": 59255, "total_steps": 61300, "loss": 0.3263, "lr": 1.6948206129439037e-07, "epoch": 9.666394779771615, "percentage": 96.66, "elapsed_time": "8:04:52", "remaining_time": "0:16:44", "throughput": 4396.07, "total_tokens": 127891792} {"current_steps": 59260, "total_steps": 61300, "loss": 0.3581, "lr": 1.6865564689564074e-07, "epoch": 9.66721044045677, "percentage": 96.67, "elapsed_time": "8:04:54", "remaining_time": "0:16:41", "throughput": 4396.1, "total_tokens": 127903376} {"current_steps": 59265, "total_steps": 61300, "loss": 0.315, "lr": 1.6783124545165785e-07, "epoch": 9.668026101141924, "percentage": 96.68, "elapsed_time": "8:04:56", "remaining_time": "0:16:39", "throughput": 4396.14, "total_tokens": 127914576} {"current_steps": 59270, "total_steps": 61300, "loss": 0.3192, "lr": 1.6700885702926882e-07, "epoch": 9.66884176182708, "percentage": 96.69, "elapsed_time": "8:04:59", "remaining_time": "0:16:36", "throughput": 4396.18, "total_tokens": 127924784} {"current_steps": 59275, "total_steps": 61300, "loss": 0.3123, "lr": 1.6618848169514533e-07, "epoch": 9.669657422512234, "percentage": 96.7, "elapsed_time": "8:05:01", "remaining_time": "0:16:34", "throughput": 4396.21, "total_tokens": 127934800} {"current_steps": 59280, "total_steps": 61300, "loss": 0.332, "lr": 1.6537011951578974e-07, "epoch": 9.67047308319739, "percentage": 96.7, "elapsed_time": "8:05:03", "remaining_time": "0:16:31", "throughput": 4396.24, "total_tokens": 127945584} {"current_steps": 59285, "total_steps": 61300, "loss": 0.3088, "lr": 1.645537705575406e-07, "epoch": 9.671288743882545, "percentage": 96.71, "elapsed_time": "8:05:05", "remaining_time": "0:16:29", "throughput": 4396.28, "total_tokens": 127956272} {"current_steps": 59290, "total_steps": 61300, "loss": 0.3222, "lr": 1.6373943488657562e-07, "epoch": 9.6721044045677, "percentage": 96.72, "elapsed_time": "8:05:07", "remaining_time": "0:16:26", "throughput": 4396.31, "total_tokens": 127966672} {"current_steps": 59295, "total_steps": 61300, "loss": 0.3515, "lr": 1.6292711256891134e-07, "epoch": 9.672920065252855, "percentage": 96.73, "elapsed_time": "8:05:10", "remaining_time": "0:16:24", "throughput": 4396.35, "total_tokens": 127978032} {"current_steps": 59300, "total_steps": 61300, "loss": 0.3119, "lr": 1.6211680367039793e-07, "epoch": 9.673735725938009, "percentage": 96.74, "elapsed_time": "8:05:12", "remaining_time": "0:16:21", "throughput": 4396.38, "total_tokens": 127989072} {"current_steps": 59305, "total_steps": 61300, "loss": 0.344, "lr": 1.6130850825672173e-07, "epoch": 9.674551386623165, "percentage": 96.75, "elapsed_time": "8:05:14", "remaining_time": "0:16:19", "throughput": 4396.41, "total_tokens": 127999568} {"current_steps": 59310, "total_steps": 61300, "loss": 0.2928, "lr": 1.6050222639340807e-07, "epoch": 9.67536704730832, "percentage": 96.75, "elapsed_time": "8:05:16", "remaining_time": "0:16:16", "throughput": 4396.43, "total_tokens": 128010256} {"current_steps": 59315, "total_steps": 61300, "loss": 0.3147, "lr": 1.5969795814581856e-07, "epoch": 9.676182707993474, "percentage": 96.76, "elapsed_time": "8:05:18", "remaining_time": "0:16:14", "throughput": 4396.47, "total_tokens": 128020176} {"current_steps": 59320, "total_steps": 61300, "loss": 0.3713, "lr": 1.5889570357915108e-07, "epoch": 9.67699836867863, "percentage": 96.77, "elapsed_time": "8:05:21", "remaining_time": "0:16:12", "throughput": 4396.51, "total_tokens": 128032496} {"current_steps": 59325, "total_steps": 61300, "loss": 0.3188, "lr": 1.5809546275843968e-07, "epoch": 9.677814029363784, "percentage": 96.78, "elapsed_time": "8:05:23", "remaining_time": "0:16:09", "throughput": 4396.54, "total_tokens": 128043632} {"current_steps": 59330, "total_steps": 61300, "loss": 0.3444, "lr": 1.572972357485575e-07, "epoch": 9.67862969004894, "percentage": 96.79, "elapsed_time": "8:05:25", "remaining_time": "0:16:07", "throughput": 4396.58, "total_tokens": 128054608} {"current_steps": 59335, "total_steps": 61300, "loss": 0.3636, "lr": 1.5650102261421107e-07, "epoch": 9.679445350734095, "percentage": 96.79, "elapsed_time": "8:05:28", "remaining_time": "0:16:04", "throughput": 4396.61, "total_tokens": 128065360} {"current_steps": 59340, "total_steps": 61300, "loss": 0.3306, "lr": 1.557068234199488e-07, "epoch": 9.68026101141925, "percentage": 96.8, "elapsed_time": "8:05:30", "remaining_time": "0:16:02", "throughput": 4396.64, "total_tokens": 128076464} {"current_steps": 59345, "total_steps": 61300, "loss": 0.2966, "lr": 1.5491463823014697e-07, "epoch": 9.681076672104405, "percentage": 96.81, "elapsed_time": "8:05:32", "remaining_time": "0:15:59", "throughput": 4396.68, "total_tokens": 128086320} {"current_steps": 59350, "total_steps": 61300, "loss": 0.323, "lr": 1.5412446710902917e-07, "epoch": 9.681892332789559, "percentage": 96.82, "elapsed_time": "8:05:34", "remaining_time": "0:15:57", "throughput": 4396.71, "total_tokens": 128096208} {"current_steps": 59355, "total_steps": 61300, "loss": 0.3141, "lr": 1.5333631012064698e-07, "epoch": 9.682707993474715, "percentage": 96.83, "elapsed_time": "8:05:36", "remaining_time": "0:15:54", "throughput": 4396.74, "total_tokens": 128107376} {"current_steps": 59360, "total_steps": 61300, "loss": 0.336, "lr": 1.5255016732889648e-07, "epoch": 9.68352365415987, "percentage": 96.84, "elapsed_time": "8:05:39", "remaining_time": "0:15:52", "throughput": 4396.77, "total_tokens": 128118800} {"current_steps": 59365, "total_steps": 61300, "loss": 0.3232, "lr": 1.5176603879750173e-07, "epoch": 9.684339314845024, "percentage": 96.84, "elapsed_time": "8:05:41", "remaining_time": "0:15:49", "throughput": 4396.81, "total_tokens": 128131152} {"current_steps": 59370, "total_steps": 61300, "loss": 0.3044, "lr": 1.509839245900313e-07, "epoch": 9.68515497553018, "percentage": 96.85, "elapsed_time": "8:05:44", "remaining_time": "0:15:47", "throughput": 4396.84, "total_tokens": 128142480} {"current_steps": 59375, "total_steps": 61300, "loss": 0.3343, "lr": 1.5020382476988726e-07, "epoch": 9.685970636215334, "percentage": 96.86, "elapsed_time": "8:05:46", "remaining_time": "0:15:44", "throughput": 4396.87, "total_tokens": 128152816} {"current_steps": 59380, "total_steps": 61300, "loss": 0.3194, "lr": 1.4942573940030791e-07, "epoch": 9.68678629690049, "percentage": 96.87, "elapsed_time": "8:05:48", "remaining_time": "0:15:42", "throughput": 4396.91, "total_tokens": 128163632} {"current_steps": 59385, "total_steps": 61300, "loss": 0.3594, "lr": 1.4864966854437056e-07, "epoch": 9.687601957585644, "percentage": 96.88, "elapsed_time": "8:05:50", "remaining_time": "0:15:40", "throughput": 4396.95, "total_tokens": 128174640} {"current_steps": 59390, "total_steps": 61300, "loss": 0.3588, "lr": 1.4787561226498048e-07, "epoch": 9.6884176182708, "percentage": 96.88, "elapsed_time": "8:05:52", "remaining_time": "0:15:37", "throughput": 4396.98, "total_tokens": 128184144} {"current_steps": 59395, "total_steps": 61300, "loss": 0.3173, "lr": 1.4710357062489577e-07, "epoch": 9.689233278955955, "percentage": 96.89, "elapsed_time": "8:05:54", "remaining_time": "0:15:35", "throughput": 4397.01, "total_tokens": 128192976} {"current_steps": 59400, "total_steps": 61300, "loss": 0.3792, "lr": 1.4633354368669694e-07, "epoch": 9.690048939641109, "percentage": 96.9, "elapsed_time": "8:05:56", "remaining_time": "0:15:32", "throughput": 4397.04, "total_tokens": 128204144} {"current_steps": 59405, "total_steps": 61300, "loss": 0.316, "lr": 1.4556553151280628e-07, "epoch": 9.690864600326265, "percentage": 96.91, "elapsed_time": "8:05:59", "remaining_time": "0:15:30", "throughput": 4397.06, "total_tokens": 128215600} {"current_steps": 59410, "total_steps": 61300, "loss": 0.3261, "lr": 1.447995341654851e-07, "epoch": 9.691680261011419, "percentage": 96.92, "elapsed_time": "8:06:01", "remaining_time": "0:15:27", "throughput": 4397.1, "total_tokens": 128226672} {"current_steps": 59415, "total_steps": 61300, "loss": 0.3241, "lr": 1.4403555170682816e-07, "epoch": 9.692495921696574, "percentage": 96.92, "elapsed_time": "8:06:03", "remaining_time": "0:15:25", "throughput": 4397.13, "total_tokens": 128237936} {"current_steps": 59420, "total_steps": 61300, "loss": 0.3535, "lr": 1.4327358419876646e-07, "epoch": 9.69331158238173, "percentage": 96.93, "elapsed_time": "8:06:06", "remaining_time": "0:15:22", "throughput": 4397.17, "total_tokens": 128248688} {"current_steps": 59425, "total_steps": 61300, "loss": 0.3575, "lr": 1.4251363170307008e-07, "epoch": 9.694127243066884, "percentage": 96.94, "elapsed_time": "8:06:08", "remaining_time": "0:15:20", "throughput": 4397.2, "total_tokens": 128259440} {"current_steps": 59430, "total_steps": 61300, "loss": 0.3139, "lr": 1.4175569428134527e-07, "epoch": 9.69494290375204, "percentage": 96.95, "elapsed_time": "8:06:10", "remaining_time": "0:15:17", "throughput": 4397.23, "total_tokens": 128268880} {"current_steps": 59435, "total_steps": 61300, "loss": 0.328, "lr": 1.4099977199503178e-07, "epoch": 9.695758564437194, "percentage": 96.96, "elapsed_time": "8:06:12", "remaining_time": "0:15:15", "throughput": 4397.25, "total_tokens": 128277744} {"current_steps": 59440, "total_steps": 61300, "loss": 0.3209, "lr": 1.4024586490540837e-07, "epoch": 9.69657422512235, "percentage": 96.97, "elapsed_time": "8:06:14", "remaining_time": "0:15:12", "throughput": 4397.28, "total_tokens": 128288176} {"current_steps": 59445, "total_steps": 61300, "loss": 0.3088, "lr": 1.3949397307359557e-07, "epoch": 9.697389885807503, "percentage": 96.97, "elapsed_time": "8:06:16", "remaining_time": "0:15:10", "throughput": 4397.32, "total_tokens": 128298672} {"current_steps": 59450, "total_steps": 61300, "loss": 0.3199, "lr": 1.3874409656054189e-07, "epoch": 9.698205546492659, "percentage": 96.98, "elapsed_time": "8:06:18", "remaining_time": "0:15:08", "throughput": 4397.35, "total_tokens": 128309264} {"current_steps": 59455, "total_steps": 61300, "loss": 0.2837, "lr": 1.3799623542703478e-07, "epoch": 9.699021207177815, "percentage": 96.99, "elapsed_time": "8:06:21", "remaining_time": "0:15:05", "throughput": 4397.38, "total_tokens": 128320656} {"current_steps": 59460, "total_steps": 61300, "loss": 0.328, "lr": 1.3725038973370076e-07, "epoch": 9.699836867862969, "percentage": 97.0, "elapsed_time": "8:06:23", "remaining_time": "0:15:03", "throughput": 4397.42, "total_tokens": 128332016} {"current_steps": 59465, "total_steps": 61300, "loss": 0.331, "lr": 1.3650655954100532e-07, "epoch": 9.700652528548124, "percentage": 97.01, "elapsed_time": "8:06:25", "remaining_time": "0:15:00", "throughput": 4397.46, "total_tokens": 128342448} {"current_steps": 59470, "total_steps": 61300, "loss": 0.3568, "lr": 1.3576474490924195e-07, "epoch": 9.701468189233278, "percentage": 97.01, "elapsed_time": "8:06:27", "remaining_time": "0:14:58", "throughput": 4397.48, "total_tokens": 128352368} {"current_steps": 59475, "total_steps": 61300, "loss": 0.3139, "lr": 1.3502494589855142e-07, "epoch": 9.702283849918434, "percentage": 97.02, "elapsed_time": "8:06:29", "remaining_time": "0:14:55", "throughput": 4397.5, "total_tokens": 128361488} {"current_steps": 59480, "total_steps": 61300, "loss": 0.3733, "lr": 1.3428716256889962e-07, "epoch": 9.70309951060359, "percentage": 97.03, "elapsed_time": "8:06:31", "remaining_time": "0:14:53", "throughput": 4397.53, "total_tokens": 128371632} {"current_steps": 59485, "total_steps": 61300, "loss": 0.3547, "lr": 1.3355139498009706e-07, "epoch": 9.703915171288743, "percentage": 97.04, "elapsed_time": "8:06:33", "remaining_time": "0:14:50", "throughput": 4397.57, "total_tokens": 128380688} {"current_steps": 59490, "total_steps": 61300, "loss": 0.3228, "lr": 1.3281764319179046e-07, "epoch": 9.7047308319739, "percentage": 97.05, "elapsed_time": "8:06:35", "remaining_time": "0:14:48", "throughput": 4397.6, "total_tokens": 128390480} {"current_steps": 59495, "total_steps": 61300, "loss": 0.3261, "lr": 1.320859072634628e-07, "epoch": 9.705546492659053, "percentage": 97.06, "elapsed_time": "8:06:37", "remaining_time": "0:14:45", "throughput": 4397.63, "total_tokens": 128401712} {"current_steps": 59500, "total_steps": 61300, "loss": 0.3001, "lr": 1.3135618725442778e-07, "epoch": 9.706362153344209, "percentage": 97.06, "elapsed_time": "8:06:40", "remaining_time": "0:14:43", "throughput": 4397.67, "total_tokens": 128413040} {"current_steps": 59505, "total_steps": 61300, "loss": 0.3011, "lr": 1.3062848322384357e-07, "epoch": 9.707177814029365, "percentage": 97.07, "elapsed_time": "8:06:42", "remaining_time": "0:14:40", "throughput": 4397.69, "total_tokens": 128421744} {"current_steps": 59510, "total_steps": 61300, "loss": 0.332, "lr": 1.2990279523069916e-07, "epoch": 9.707993474714518, "percentage": 97.08, "elapsed_time": "8:06:44", "remaining_time": "0:14:38", "throughput": 4397.72, "total_tokens": 128432528} {"current_steps": 59515, "total_steps": 61300, "loss": 0.3603, "lr": 1.291791233338252e-07, "epoch": 9.708809135399674, "percentage": 97.09, "elapsed_time": "8:06:46", "remaining_time": "0:14:35", "throughput": 4397.76, "total_tokens": 128443664} {"current_steps": 59520, "total_steps": 61300, "loss": 0.3032, "lr": 1.2845746759188314e-07, "epoch": 9.709624796084828, "percentage": 97.1, "elapsed_time": "8:06:48", "remaining_time": "0:14:33", "throughput": 4397.79, "total_tokens": 128454256} {"current_steps": 59525, "total_steps": 61300, "loss": 0.3257, "lr": 1.277378280633762e-07, "epoch": 9.710440456769984, "percentage": 97.1, "elapsed_time": "8:06:51", "remaining_time": "0:14:31", "throughput": 4397.83, "total_tokens": 128466768} {"current_steps": 59530, "total_steps": 61300, "loss": 0.3173, "lr": 1.27020204806641e-07, "epoch": 9.71125611745514, "percentage": 97.11, "elapsed_time": "8:06:53", "remaining_time": "0:14:28", "throughput": 4397.87, "total_tokens": 128477264} {"current_steps": 59535, "total_steps": 61300, "loss": 0.3071, "lr": 1.2630459787985326e-07, "epoch": 9.712071778140293, "percentage": 97.12, "elapsed_time": "8:06:55", "remaining_time": "0:14:26", "throughput": 4397.9, "total_tokens": 128489040} {"current_steps": 59540, "total_steps": 61300, "loss": 0.3186, "lr": 1.2559100734102214e-07, "epoch": 9.71288743882545, "percentage": 97.13, "elapsed_time": "8:06:58", "remaining_time": "0:14:23", "throughput": 4397.94, "total_tokens": 128500176} {"current_steps": 59545, "total_steps": 61300, "loss": 0.3547, "lr": 1.248794332479958e-07, "epoch": 9.713703099510603, "percentage": 97.14, "elapsed_time": "8:07:00", "remaining_time": "0:14:21", "throughput": 4397.97, "total_tokens": 128510096} {"current_steps": 59550, "total_steps": 61300, "loss": 0.3109, "lr": 1.2416987565845861e-07, "epoch": 9.714518760195759, "percentage": 97.15, "elapsed_time": "8:07:02", "remaining_time": "0:14:18", "throughput": 4398.0, "total_tokens": 128520976} {"current_steps": 59555, "total_steps": 61300, "loss": 0.3004, "lr": 1.2346233462992852e-07, "epoch": 9.715334420880914, "percentage": 97.15, "elapsed_time": "8:07:04", "remaining_time": "0:14:16", "throughput": 4398.03, "total_tokens": 128532080} {"current_steps": 59560, "total_steps": 61300, "loss": 0.3017, "lr": 1.2275681021976515e-07, "epoch": 9.716150081566068, "percentage": 97.16, "elapsed_time": "8:07:07", "remaining_time": "0:14:13", "throughput": 4398.07, "total_tokens": 128544176} {"current_steps": 59565, "total_steps": 61300, "loss": 0.3684, "lr": 1.220533024851589e-07, "epoch": 9.716965742251224, "percentage": 97.17, "elapsed_time": "8:07:09", "remaining_time": "0:14:11", "throughput": 4398.1, "total_tokens": 128555472} {"current_steps": 59570, "total_steps": 61300, "loss": 0.3189, "lr": 1.213518114831419e-07, "epoch": 9.717781402936378, "percentage": 97.18, "elapsed_time": "8:07:11", "remaining_time": "0:14:08", "throughput": 4398.14, "total_tokens": 128565968} {"current_steps": 59575, "total_steps": 61300, "loss": 0.3207, "lr": 1.206523372705798e-07, "epoch": 9.718597063621534, "percentage": 97.19, "elapsed_time": "8:07:14", "remaining_time": "0:14:06", "throughput": 4398.17, "total_tokens": 128576528} {"current_steps": 59580, "total_steps": 61300, "loss": 0.3289, "lr": 1.199548799041772e-07, "epoch": 9.719412724306688, "percentage": 97.19, "elapsed_time": "8:07:16", "remaining_time": "0:14:04", "throughput": 4398.21, "total_tokens": 128586928} {"current_steps": 59585, "total_steps": 61300, "loss": 0.3369, "lr": 1.1925943944047225e-07, "epoch": 9.720228384991843, "percentage": 97.2, "elapsed_time": "8:07:18", "remaining_time": "0:14:01", "throughput": 4398.24, "total_tokens": 128599280} {"current_steps": 59590, "total_steps": 61300, "loss": 0.3376, "lr": 1.1856601593583928e-07, "epoch": 9.721044045676999, "percentage": 97.21, "elapsed_time": "8:07:20", "remaining_time": "0:13:59", "throughput": 4398.27, "total_tokens": 128609424} {"current_steps": 59595, "total_steps": 61300, "loss": 0.3112, "lr": 1.1787460944649443e-07, "epoch": 9.721859706362153, "percentage": 97.22, "elapsed_time": "8:07:23", "remaining_time": "0:13:56", "throughput": 4398.31, "total_tokens": 128620368} {"current_steps": 59600, "total_steps": 61300, "loss": 0.3252, "lr": 1.1718522002848175e-07, "epoch": 9.722675367047309, "percentage": 97.23, "elapsed_time": "8:07:25", "remaining_time": "0:13:54", "throughput": 4398.34, "total_tokens": 128631792} {"current_steps": 59605, "total_steps": 61300, "loss": 0.3501, "lr": 1.164978477376899e-07, "epoch": 9.723491027732463, "percentage": 97.23, "elapsed_time": "8:07:27", "remaining_time": "0:13:51", "throughput": 4398.37, "total_tokens": 128641584} {"current_steps": 59610, "total_steps": 61300, "loss": 0.3785, "lr": 1.1581249262984096e-07, "epoch": 9.724306688417618, "percentage": 97.24, "elapsed_time": "8:07:29", "remaining_time": "0:13:49", "throughput": 4398.4, "total_tokens": 128651824} {"current_steps": 59615, "total_steps": 61300, "loss": 0.3238, "lr": 1.1512915476049325e-07, "epoch": 9.725122349102774, "percentage": 97.25, "elapsed_time": "8:07:31", "remaining_time": "0:13:46", "throughput": 4398.43, "total_tokens": 128661616} {"current_steps": 59620, "total_steps": 61300, "loss": 0.3277, "lr": 1.1444783418503857e-07, "epoch": 9.725938009787928, "percentage": 97.26, "elapsed_time": "8:07:33", "remaining_time": "0:13:44", "throughput": 4398.46, "total_tokens": 128671952} {"current_steps": 59625, "total_steps": 61300, "loss": 0.3408, "lr": 1.1376853095871332e-07, "epoch": 9.726753670473084, "percentage": 97.27, "elapsed_time": "8:07:36", "remaining_time": "0:13:41", "throughput": 4398.49, "total_tokens": 128682928} {"current_steps": 59630, "total_steps": 61300, "loss": 0.3326, "lr": 1.1309124513657899e-07, "epoch": 9.727569331158238, "percentage": 97.28, "elapsed_time": "8:07:38", "remaining_time": "0:13:39", "throughput": 4398.51, "total_tokens": 128692592} {"current_steps": 59635, "total_steps": 61300, "loss": 0.3299, "lr": 1.124159767735472e-07, "epoch": 9.728384991843393, "percentage": 97.28, "elapsed_time": "8:07:40", "remaining_time": "0:13:36", "throughput": 4398.55, "total_tokens": 128703280} {"current_steps": 59640, "total_steps": 61300, "loss": 0.3616, "lr": 1.1174272592435197e-07, "epoch": 9.729200652528547, "percentage": 97.29, "elapsed_time": "8:07:42", "remaining_time": "0:13:34", "throughput": 4398.58, "total_tokens": 128713904} {"current_steps": 59645, "total_steps": 61300, "loss": 0.3084, "lr": 1.1107149264357186e-07, "epoch": 9.730016313213703, "percentage": 97.3, "elapsed_time": "8:07:44", "remaining_time": "0:13:32", "throughput": 4398.61, "total_tokens": 128723696} {"current_steps": 59650, "total_steps": 61300, "loss": 0.3101, "lr": 1.1040227698562445e-07, "epoch": 9.730831973898859, "percentage": 97.31, "elapsed_time": "8:07:46", "remaining_time": "0:13:29", "throughput": 4398.65, "total_tokens": 128735120} {"current_steps": 59655, "total_steps": 61300, "loss": 0.3318, "lr": 1.0973507900475521e-07, "epoch": 9.731647634584013, "percentage": 97.32, "elapsed_time": "8:07:49", "remaining_time": "0:13:27", "throughput": 4398.68, "total_tokens": 128745232} {"current_steps": 59660, "total_steps": 61300, "loss": 0.3606, "lr": 1.0906989875505425e-07, "epoch": 9.732463295269168, "percentage": 97.32, "elapsed_time": "8:07:51", "remaining_time": "0:13:24", "throughput": 4398.72, "total_tokens": 128755856} {"current_steps": 59665, "total_steps": 61300, "loss": 0.3208, "lr": 1.0840673629044228e-07, "epoch": 9.733278955954322, "percentage": 97.33, "elapsed_time": "8:07:53", "remaining_time": "0:13:22", "throughput": 4398.76, "total_tokens": 128766768} {"current_steps": 59670, "total_steps": 61300, "loss": 0.2856, "lr": 1.0774559166467912e-07, "epoch": 9.734094616639478, "percentage": 97.34, "elapsed_time": "8:07:55", "remaining_time": "0:13:19", "throughput": 4398.8, "total_tokens": 128778448} {"current_steps": 59675, "total_steps": 61300, "loss": 0.3641, "lr": 1.0708646493135799e-07, "epoch": 9.734910277324634, "percentage": 97.35, "elapsed_time": "8:07:57", "remaining_time": "0:13:17", "throughput": 4398.82, "total_tokens": 128788176} {"current_steps": 59680, "total_steps": 61300, "loss": 0.3062, "lr": 1.0642935614391392e-07, "epoch": 9.735725938009788, "percentage": 97.36, "elapsed_time": "8:08:00", "remaining_time": "0:13:14", "throughput": 4398.86, "total_tokens": 128799280} {"current_steps": 59685, "total_steps": 61300, "loss": 0.3009, "lr": 1.0577426535561541e-07, "epoch": 9.736541598694943, "percentage": 97.37, "elapsed_time": "8:08:02", "remaining_time": "0:13:12", "throughput": 4398.88, "total_tokens": 128808752} {"current_steps": 59690, "total_steps": 61300, "loss": 0.3098, "lr": 1.0512119261956999e-07, "epoch": 9.737357259380097, "percentage": 97.37, "elapsed_time": "8:08:04", "remaining_time": "0:13:09", "throughput": 4398.91, "total_tokens": 128819728} {"current_steps": 59695, "total_steps": 61300, "loss": 0.3431, "lr": 1.0447013798871308e-07, "epoch": 9.738172920065253, "percentage": 97.38, "elapsed_time": "8:08:06", "remaining_time": "0:13:07", "throughput": 4398.95, "total_tokens": 128831440} {"current_steps": 59700, "total_steps": 61300, "loss": 0.3031, "lr": 1.0382110151582469e-07, "epoch": 9.738988580750409, "percentage": 97.39, "elapsed_time": "8:08:08", "remaining_time": "0:13:04", "throughput": 4398.99, "total_tokens": 128841200} {"current_steps": 59705, "total_steps": 61300, "loss": 0.3208, "lr": 1.0317408325352107e-07, "epoch": 9.739804241435563, "percentage": 97.4, "elapsed_time": "8:08:11", "remaining_time": "0:13:02", "throughput": 4399.02, "total_tokens": 128852112} {"current_steps": 59710, "total_steps": 61300, "loss": 0.3028, "lr": 1.0252908325425192e-07, "epoch": 9.740619902120718, "percentage": 97.41, "elapsed_time": "8:08:13", "remaining_time": "0:13:00", "throughput": 4399.06, "total_tokens": 128864592} {"current_steps": 59715, "total_steps": 61300, "loss": 0.3489, "lr": 1.018861015703032e-07, "epoch": 9.741435562805872, "percentage": 97.41, "elapsed_time": "8:08:16", "remaining_time": "0:12:57", "throughput": 4399.1, "total_tokens": 128876272} {"current_steps": 59720, "total_steps": 61300, "loss": 0.3003, "lr": 1.0124513825379989e-07, "epoch": 9.742251223491028, "percentage": 97.42, "elapsed_time": "8:08:18", "remaining_time": "0:12:55", "throughput": 4399.13, "total_tokens": 128887056} {"current_steps": 59725, "total_steps": 61300, "loss": 0.3231, "lr": 1.0060619335669764e-07, "epoch": 9.743066884176184, "percentage": 97.43, "elapsed_time": "8:08:20", "remaining_time": "0:12:52", "throughput": 4399.17, "total_tokens": 128898128} {"current_steps": 59730, "total_steps": 61300, "loss": 0.3301, "lr": 9.996926693079945e-08, "epoch": 9.743882544861338, "percentage": 97.44, "elapsed_time": "8:08:22", "remaining_time": "0:12:50", "throughput": 4399.19, "total_tokens": 128909040} {"current_steps": 59735, "total_steps": 61300, "loss": 0.3474, "lr": 9.93343590277307e-08, "epoch": 9.744698205546493, "percentage": 97.45, "elapsed_time": "8:08:24", "remaining_time": "0:12:47", "throughput": 4399.23, "total_tokens": 128918288} {"current_steps": 59740, "total_steps": 61300, "loss": 0.3462, "lr": 9.870146969896688e-08, "epoch": 9.745513866231647, "percentage": 97.46, "elapsed_time": "8:08:27", "remaining_time": "0:12:45", "throughput": 4399.26, "total_tokens": 128929584} {"current_steps": 59745, "total_steps": 61300, "loss": 0.314, "lr": 9.807059899580861e-08, "epoch": 9.746329526916803, "percentage": 97.46, "elapsed_time": "8:08:29", "remaining_time": "0:12:42", "throughput": 4399.29, "total_tokens": 128940208} {"current_steps": 59750, "total_steps": 61300, "loss": 0.3101, "lr": 9.744174696939834e-08, "epoch": 9.747145187601957, "percentage": 97.47, "elapsed_time": "8:08:31", "remaining_time": "0:12:40", "throughput": 4399.32, "total_tokens": 128950224} {"current_steps": 59755, "total_steps": 61300, "loss": 0.3282, "lr": 9.681491367071193e-08, "epoch": 9.747960848287113, "percentage": 97.48, "elapsed_time": "8:08:33", "remaining_time": "0:12:37", "throughput": 4399.35, "total_tokens": 128961072} {"current_steps": 59760, "total_steps": 61300, "loss": 0.3328, "lr": 9.619009915056987e-08, "epoch": 9.748776508972268, "percentage": 97.49, "elapsed_time": "8:08:36", "remaining_time": "0:12:35", "throughput": 4399.39, "total_tokens": 128972528} {"current_steps": 59765, "total_steps": 61300, "loss": 0.3137, "lr": 9.556730345961773e-08, "epoch": 9.749592169657422, "percentage": 97.5, "elapsed_time": "8:08:38", "remaining_time": "0:12:33", "throughput": 4399.42, "total_tokens": 128982480} {"current_steps": 59770, "total_steps": 61300, "loss": 0.3006, "lr": 9.494652664834292e-08, "epoch": 9.750407830342578, "percentage": 97.5, "elapsed_time": "8:08:40", "remaining_time": "0:12:30", "throughput": 4399.45, "total_tokens": 128992304} {"current_steps": 59775, "total_steps": 61300, "loss": 0.3591, "lr": 9.432776876707183e-08, "epoch": 9.751223491027732, "percentage": 97.51, "elapsed_time": "8:08:42", "remaining_time": "0:12:28", "throughput": 4399.48, "total_tokens": 129003344} {"current_steps": 59780, "total_steps": 61300, "loss": 0.3626, "lr": 9.371102986595881e-08, "epoch": 9.752039151712887, "percentage": 97.52, "elapsed_time": "8:08:44", "remaining_time": "0:12:25", "throughput": 4399.52, "total_tokens": 129014224} {"current_steps": 59785, "total_steps": 61300, "loss": 0.3063, "lr": 9.309630999500551e-08, "epoch": 9.752854812398043, "percentage": 97.53, "elapsed_time": "8:08:46", "remaining_time": "0:12:23", "throughput": 4399.55, "total_tokens": 129024016} {"current_steps": 59790, "total_steps": 61300, "loss": 0.3432, "lr": 9.248360920404154e-08, "epoch": 9.753670473083197, "percentage": 97.54, "elapsed_time": "8:08:48", "remaining_time": "0:12:20", "throughput": 4399.58, "total_tokens": 129033840} {"current_steps": 59795, "total_steps": 61300, "loss": 0.3098, "lr": 9.187292754273269e-08, "epoch": 9.754486133768353, "percentage": 97.54, "elapsed_time": "8:08:50", "remaining_time": "0:12:18", "throughput": 4399.62, "total_tokens": 129044848} {"current_steps": 59800, "total_steps": 61300, "loss": 0.3213, "lr": 9.126426506058938e-08, "epoch": 9.755301794453507, "percentage": 97.55, "elapsed_time": "8:08:53", "remaining_time": "0:12:15", "throughput": 4399.65, "total_tokens": 129055664} {"current_steps": 59805, "total_steps": 61300, "loss": 0.3394, "lr": 9.06576218069527e-08, "epoch": 9.756117455138662, "percentage": 97.56, "elapsed_time": "8:08:55", "remaining_time": "0:12:13", "throughput": 4399.68, "total_tokens": 129066288} {"current_steps": 59810, "total_steps": 61300, "loss": 0.3199, "lr": 9.005299783099441e-08, "epoch": 9.756933115823816, "percentage": 97.57, "elapsed_time": "8:08:57", "remaining_time": "0:12:10", "throughput": 4399.71, "total_tokens": 129076016} {"current_steps": 59815, "total_steps": 61300, "loss": 0.317, "lr": 8.945039318173365e-08, "epoch": 9.757748776508972, "percentage": 97.58, "elapsed_time": "8:08:59", "remaining_time": "0:12:08", "throughput": 4399.74, "total_tokens": 129086704} {"current_steps": 59820, "total_steps": 61300, "loss": 0.3104, "lr": 8.884980790801745e-08, "epoch": 9.758564437194128, "percentage": 97.59, "elapsed_time": "8:09:01", "remaining_time": "0:12:05", "throughput": 4399.77, "total_tokens": 129096560} {"current_steps": 59825, "total_steps": 61300, "loss": 0.3274, "lr": 8.825124205853463e-08, "epoch": 9.759380097879282, "percentage": 97.59, "elapsed_time": "8:09:03", "remaining_time": "0:12:03", "throughput": 4399.81, "total_tokens": 129107984} {"current_steps": 59830, "total_steps": 61300, "loss": 0.3339, "lr": 8.76546956818075e-08, "epoch": 9.760195758564437, "percentage": 97.6, "elapsed_time": "8:09:06", "remaining_time": "0:12:01", "throughput": 4399.84, "total_tokens": 129118352} {"current_steps": 59835, "total_steps": 61300, "loss": 0.331, "lr": 8.706016882619461e-08, "epoch": 9.761011419249591, "percentage": 97.61, "elapsed_time": "8:09:08", "remaining_time": "0:11:58", "throughput": 4399.87, "total_tokens": 129129072} {"current_steps": 59840, "total_steps": 61300, "loss": 0.3319, "lr": 8.646766153989072e-08, "epoch": 9.761827079934747, "percentage": 97.62, "elapsed_time": "8:09:10", "remaining_time": "0:11:56", "throughput": 4399.91, "total_tokens": 129140496} {"current_steps": 59845, "total_steps": 61300, "loss": 0.32, "lr": 8.587717387092686e-08, "epoch": 9.762642740619903, "percentage": 97.63, "elapsed_time": "8:09:13", "remaining_time": "0:11:53", "throughput": 4399.94, "total_tokens": 129151952} {"current_steps": 59850, "total_steps": 61300, "loss": 0.3604, "lr": 8.528870586717308e-08, "epoch": 9.763458401305057, "percentage": 97.63, "elapsed_time": "8:09:15", "remaining_time": "0:11:51", "throughput": 4399.98, "total_tokens": 129165008} {"current_steps": 59855, "total_steps": 61300, "loss": 0.3598, "lr": 8.470225757633565e-08, "epoch": 9.764274061990212, "percentage": 97.64, "elapsed_time": "8:09:18", "remaining_time": "0:11:48", "throughput": 4400.02, "total_tokens": 129176272} {"current_steps": 59860, "total_steps": 61300, "loss": 0.3179, "lr": 8.411782904594879e-08, "epoch": 9.765089722675366, "percentage": 97.65, "elapsed_time": "8:09:20", "remaining_time": "0:11:46", "throughput": 4400.05, "total_tokens": 129187504} {"current_steps": 59865, "total_steps": 61300, "loss": 0.3406, "lr": 8.3535420323394e-08, "epoch": 9.765905383360522, "percentage": 97.66, "elapsed_time": "8:09:22", "remaining_time": "0:11:43", "throughput": 4400.09, "total_tokens": 129198928} {"current_steps": 59870, "total_steps": 61300, "loss": 0.3211, "lr": 8.295503145588357e-08, "epoch": 9.766721044045678, "percentage": 97.67, "elapsed_time": "8:09:25", "remaining_time": "0:11:41", "throughput": 4400.13, "total_tokens": 129211024} {"current_steps": 59875, "total_steps": 61300, "loss": 0.3383, "lr": 8.237666249046593e-08, "epoch": 9.767536704730832, "percentage": 97.68, "elapsed_time": "8:09:27", "remaining_time": "0:11:38", "throughput": 4400.16, "total_tokens": 129222096} {"current_steps": 59880, "total_steps": 61300, "loss": 0.3282, "lr": 8.180031347402583e-08, "epoch": 9.768352365415987, "percentage": 97.68, "elapsed_time": "8:09:29", "remaining_time": "0:11:36", "throughput": 4400.19, "total_tokens": 129232880} {"current_steps": 59885, "total_steps": 61300, "loss": 0.3351, "lr": 8.122598445328699e-08, "epoch": 9.769168026101141, "percentage": 97.69, "elapsed_time": "8:09:32", "remaining_time": "0:11:34", "throughput": 4400.22, "total_tokens": 129244560} {"current_steps": 59890, "total_steps": 61300, "loss": 0.3181, "lr": 8.065367547480384e-08, "epoch": 9.769983686786297, "percentage": 97.7, "elapsed_time": "8:09:34", "remaining_time": "0:11:31", "throughput": 4400.26, "total_tokens": 129255824} {"current_steps": 59895, "total_steps": 61300, "loss": 0.3417, "lr": 8.008338658497538e-08, "epoch": 9.770799347471453, "percentage": 97.71, "elapsed_time": "8:09:36", "remaining_time": "0:11:29", "throughput": 4400.3, "total_tokens": 129267248} {"current_steps": 59900, "total_steps": 61300, "loss": 0.3168, "lr": 7.95151178300313e-08, "epoch": 9.771615008156607, "percentage": 97.72, "elapsed_time": "8:09:39", "remaining_time": "0:11:26", "throughput": 4400.33, "total_tokens": 129277616} {"current_steps": 59905, "total_steps": 61300, "loss": 0.3179, "lr": 7.894886925603473e-08, "epoch": 9.772430668841762, "percentage": 97.72, "elapsed_time": "8:09:41", "remaining_time": "0:11:24", "throughput": 4400.36, "total_tokens": 129288112} {"current_steps": 59910, "total_steps": 61300, "loss": 0.3429, "lr": 7.838464090889342e-08, "epoch": 9.773246329526916, "percentage": 97.73, "elapsed_time": "8:09:43", "remaining_time": "0:11:21", "throughput": 4400.39, "total_tokens": 129298064} {"current_steps": 59915, "total_steps": 61300, "loss": 0.3429, "lr": 7.782243283434299e-08, "epoch": 9.774061990212072, "percentage": 97.74, "elapsed_time": "8:09:45", "remaining_time": "0:11:19", "throughput": 4400.42, "total_tokens": 129307408} {"current_steps": 59920, "total_steps": 61300, "loss": 0.3756, "lr": 7.726224507795809e-08, "epoch": 9.774877650897226, "percentage": 97.75, "elapsed_time": "8:09:47", "remaining_time": "0:11:16", "throughput": 4400.45, "total_tokens": 129318128} {"current_steps": 59925, "total_steps": 61300, "loss": 0.3123, "lr": 7.67040776851552e-08, "epoch": 9.775693311582382, "percentage": 97.76, "elapsed_time": "8:09:49", "remaining_time": "0:11:14", "throughput": 4400.48, "total_tokens": 129328080} {"current_steps": 59930, "total_steps": 61300, "loss": 0.3269, "lr": 7.614793070117865e-08, "epoch": 9.776508972267537, "percentage": 97.77, "elapsed_time": "8:09:51", "remaining_time": "0:11:11", "throughput": 4400.52, "total_tokens": 129339120} {"current_steps": 59935, "total_steps": 61300, "loss": 0.313, "lr": 7.559380417111184e-08, "epoch": 9.777324632952691, "percentage": 97.77, "elapsed_time": "8:09:53", "remaining_time": "0:11:09", "throughput": 4400.55, "total_tokens": 129349648} {"current_steps": 59940, "total_steps": 61300, "loss": 0.3553, "lr": 7.504169813987716e-08, "epoch": 9.778140293637847, "percentage": 97.78, "elapsed_time": "8:09:56", "remaining_time": "0:11:06", "throughput": 4400.58, "total_tokens": 129360400} {"current_steps": 59945, "total_steps": 61300, "loss": 0.3506, "lr": 7.449161265223048e-08, "epoch": 9.778955954323001, "percentage": 97.79, "elapsed_time": "8:09:58", "remaining_time": "0:11:04", "throughput": 4400.62, "total_tokens": 129373168} {"current_steps": 59950, "total_steps": 61300, "loss": 0.3, "lr": 7.394354775276391e-08, "epoch": 9.779771615008157, "percentage": 97.8, "elapsed_time": "8:10:00", "remaining_time": "0:11:02", "throughput": 4400.65, "total_tokens": 129382736} {"current_steps": 59955, "total_steps": 61300, "loss": 0.321, "lr": 7.339750348590857e-08, "epoch": 9.780587275693312, "percentage": 97.81, "elapsed_time": "8:10:03", "remaining_time": "0:10:59", "throughput": 4400.69, "total_tokens": 129394160} {"current_steps": 59960, "total_steps": 61300, "loss": 0.3331, "lr": 7.285347989592628e-08, "epoch": 9.781402936378466, "percentage": 97.81, "elapsed_time": "8:10:05", "remaining_time": "0:10:57", "throughput": 4400.72, "total_tokens": 129405744} {"current_steps": 59965, "total_steps": 61300, "loss": 0.3067, "lr": 7.231147702692065e-08, "epoch": 9.782218597063622, "percentage": 97.82, "elapsed_time": "8:10:07", "remaining_time": "0:10:54", "throughput": 4400.76, "total_tokens": 129416368} {"current_steps": 59970, "total_steps": 61300, "loss": 0.3483, "lr": 7.177149492282876e-08, "epoch": 9.783034257748776, "percentage": 97.83, "elapsed_time": "8:10:09", "remaining_time": "0:10:52", "throughput": 4400.79, "total_tokens": 129426928} {"current_steps": 59975, "total_steps": 61300, "loss": 0.324, "lr": 7.123353362742391e-08, "epoch": 9.783849918433932, "percentage": 97.84, "elapsed_time": "8:10:12", "remaining_time": "0:10:49", "throughput": 4400.83, "total_tokens": 129438896} {"current_steps": 59980, "total_steps": 61300, "loss": 0.3281, "lr": 7.069759318431567e-08, "epoch": 9.784665579119086, "percentage": 97.85, "elapsed_time": "8:10:14", "remaining_time": "0:10:47", "throughput": 4400.86, "total_tokens": 129449808} {"current_steps": 59985, "total_steps": 61300, "loss": 0.3092, "lr": 7.016367363694986e-08, "epoch": 9.785481239804241, "percentage": 97.85, "elapsed_time": "8:10:17", "remaining_time": "0:10:44", "throughput": 4400.89, "total_tokens": 129461232} {"current_steps": 59990, "total_steps": 61300, "loss": 0.3606, "lr": 6.963177502861129e-08, "epoch": 9.786296900489397, "percentage": 97.86, "elapsed_time": "8:10:19", "remaining_time": "0:10:42", "throughput": 4400.92, "total_tokens": 129471984} {"current_steps": 59995, "total_steps": 61300, "loss": 0.3148, "lr": 6.910189740241269e-08, "epoch": 9.78711256117455, "percentage": 97.87, "elapsed_time": "8:10:21", "remaining_time": "0:10:39", "throughput": 4400.96, "total_tokens": 129483088} {"current_steps": 60000, "total_steps": 61300, "loss": 0.3279, "lr": 6.857404080131691e-08, "epoch": 9.787928221859707, "percentage": 97.88, "elapsed_time": "8:10:23", "remaining_time": "0:10:37", "throughput": 4400.98, "total_tokens": 129492144} {"current_steps": 60005, "total_steps": 61300, "loss": 0.3589, "lr": 6.804820526810917e-08, "epoch": 9.78874388254486, "percentage": 97.89, "elapsed_time": "8:10:25", "remaining_time": "0:10:35", "throughput": 4401.01, "total_tokens": 129502128} {"current_steps": 60010, "total_steps": 61300, "loss": 0.3129, "lr": 6.75243908454165e-08, "epoch": 9.789559543230016, "percentage": 97.9, "elapsed_time": "8:10:27", "remaining_time": "0:10:32", "throughput": 4401.04, "total_tokens": 129512848} {"current_steps": 60015, "total_steps": 61300, "loss": 0.3317, "lr": 6.700259757570216e-08, "epoch": 9.790375203915172, "percentage": 97.9, "elapsed_time": "8:10:29", "remaining_time": "0:10:30", "throughput": 4401.07, "total_tokens": 129522992} {"current_steps": 60020, "total_steps": 61300, "loss": 0.3335, "lr": 6.648282550126562e-08, "epoch": 9.791190864600326, "percentage": 97.91, "elapsed_time": "8:10:32", "remaining_time": "0:10:27", "throughput": 4401.1, "total_tokens": 129533328} {"current_steps": 60025, "total_steps": 61300, "loss": 0.3295, "lr": 6.59650746642454e-08, "epoch": 9.792006525285482, "percentage": 97.92, "elapsed_time": "8:10:33", "remaining_time": "0:10:25", "throughput": 4401.13, "total_tokens": 129542768} {"current_steps": 60030, "total_steps": 61300, "loss": 0.3539, "lr": 6.544934510660794e-08, "epoch": 9.792822185970635, "percentage": 97.93, "elapsed_time": "8:10:36", "remaining_time": "0:10:22", "throughput": 4401.16, "total_tokens": 129554448} {"current_steps": 60035, "total_steps": 61300, "loss": 0.2908, "lr": 6.493563687016424e-08, "epoch": 9.793637846655791, "percentage": 97.94, "elapsed_time": "8:10:39", "remaining_time": "0:10:20", "throughput": 4401.19, "total_tokens": 129566736} {"current_steps": 60040, "total_steps": 61300, "loss": 0.3456, "lr": 6.442394999655599e-08, "epoch": 9.794453507340947, "percentage": 97.94, "elapsed_time": "8:10:41", "remaining_time": "0:10:17", "throughput": 4401.22, "total_tokens": 129577392} {"current_steps": 60045, "total_steps": 61300, "loss": 0.3128, "lr": 6.391428452726389e-08, "epoch": 9.7952691680261, "percentage": 97.95, "elapsed_time": "8:10:43", "remaining_time": "0:10:15", "throughput": 4401.25, "total_tokens": 129588080} {"current_steps": 60050, "total_steps": 61300, "loss": 0.3174, "lr": 6.340664050360767e-08, "epoch": 9.796084828711257, "percentage": 97.96, "elapsed_time": "8:10:45", "remaining_time": "0:10:12", "throughput": 4401.29, "total_tokens": 129599312} {"current_steps": 60055, "total_steps": 61300, "loss": 0.3378, "lr": 6.29010179667322e-08, "epoch": 9.79690048939641, "percentage": 97.97, "elapsed_time": "8:10:47", "remaining_time": "0:10:10", "throughput": 4401.33, "total_tokens": 129609488} {"current_steps": 60060, "total_steps": 61300, "loss": 0.3479, "lr": 6.239741695763246e-08, "epoch": 9.797716150081566, "percentage": 97.98, "elapsed_time": "8:10:50", "remaining_time": "0:10:08", "throughput": 4401.36, "total_tokens": 129620944} {"current_steps": 60065, "total_steps": 61300, "loss": 0.3212, "lr": 6.189583751712857e-08, "epoch": 9.798531810766722, "percentage": 97.99, "elapsed_time": "8:10:52", "remaining_time": "0:10:05", "throughput": 4401.39, "total_tokens": 129631920} {"current_steps": 60070, "total_steps": 61300, "loss": 0.3288, "lr": 6.139627968588524e-08, "epoch": 9.799347471451876, "percentage": 97.99, "elapsed_time": "8:10:54", "remaining_time": "0:10:03", "throughput": 4401.43, "total_tokens": 129643696} {"current_steps": 60075, "total_steps": 61300, "loss": 0.3292, "lr": 6.089874350439506e-08, "epoch": 9.800163132137031, "percentage": 98.0, "elapsed_time": "8:10:57", "remaining_time": "0:10:00", "throughput": 4401.47, "total_tokens": 129655184} {"current_steps": 60080, "total_steps": 61300, "loss": 0.3404, "lr": 6.040322901299245e-08, "epoch": 9.800978792822185, "percentage": 98.01, "elapsed_time": "8:10:59", "remaining_time": "0:09:58", "throughput": 4401.5, "total_tokens": 129665008} {"current_steps": 60085, "total_steps": 61300, "loss": 0.3575, "lr": 5.990973625184526e-08, "epoch": 9.801794453507341, "percentage": 98.02, "elapsed_time": "8:11:01", "remaining_time": "0:09:55", "throughput": 4401.54, "total_tokens": 129675344} {"current_steps": 60090, "total_steps": 61300, "loss": 0.3889, "lr": 5.9418265260960394e-08, "epoch": 9.802610114192497, "percentage": 98.03, "elapsed_time": "8:11:03", "remaining_time": "0:09:53", "throughput": 4401.57, "total_tokens": 129687120} {"current_steps": 60095, "total_steps": 61300, "loss": 0.3198, "lr": 5.892881608017819e-08, "epoch": 9.80342577487765, "percentage": 98.03, "elapsed_time": "8:11:06", "remaining_time": "0:09:50", "throughput": 4401.61, "total_tokens": 129697936} {"current_steps": 60100, "total_steps": 61300, "loss": 0.3471, "lr": 5.844138874917526e-08, "epoch": 9.804241435562806, "percentage": 98.04, "elapsed_time": "8:11:07", "remaining_time": "0:09:48", "throughput": 4401.63, "total_tokens": 129707312} {"current_steps": 60105, "total_steps": 61300, "loss": 0.3496, "lr": 5.795598330746721e-08, "epoch": 9.80505709624796, "percentage": 98.05, "elapsed_time": "8:11:10", "remaining_time": "0:09:45", "throughput": 4401.67, "total_tokens": 129718256} {"current_steps": 60110, "total_steps": 61300, "loss": 0.2919, "lr": 5.747259979440034e-08, "epoch": 9.805872756933116, "percentage": 98.06, "elapsed_time": "8:11:12", "remaining_time": "0:09:43", "throughput": 4401.7, "total_tokens": 129728336} {"current_steps": 60115, "total_steps": 61300, "loss": 0.3432, "lr": 5.699123824916275e-08, "epoch": 9.80668841761827, "percentage": 98.07, "elapsed_time": "8:11:14", "remaining_time": "0:09:41", "throughput": 4401.74, "total_tokens": 129738960} {"current_steps": 60120, "total_steps": 61300, "loss": 0.3403, "lr": 5.6511898710776e-08, "epoch": 9.807504078303426, "percentage": 98.08, "elapsed_time": "8:11:16", "remaining_time": "0:09:38", "throughput": 4401.76, "total_tokens": 129748752} {"current_steps": 60125, "total_steps": 61300, "loss": 0.3627, "lr": 5.603458121809513e-08, "epoch": 9.808319738988581, "percentage": 98.08, "elapsed_time": "8:11:18", "remaining_time": "0:09:36", "throughput": 4401.79, "total_tokens": 129758864} {"current_steps": 60130, "total_steps": 61300, "loss": 0.3155, "lr": 5.555928580981418e-08, "epoch": 9.809135399673735, "percentage": 98.09, "elapsed_time": "8:11:20", "remaining_time": "0:09:33", "throughput": 4401.81, "total_tokens": 129768112} {"current_steps": 60135, "total_steps": 61300, "loss": 0.3323, "lr": 5.5086012524466216e-08, "epoch": 9.809951060358891, "percentage": 98.1, "elapsed_time": "8:11:22", "remaining_time": "0:09:31", "throughput": 4401.85, "total_tokens": 129779440} {"current_steps": 60140, "total_steps": 61300, "loss": 0.3101, "lr": 5.4614761400414996e-08, "epoch": 9.810766721044045, "percentage": 98.11, "elapsed_time": "8:11:25", "remaining_time": "0:09:28", "throughput": 4401.88, "total_tokens": 129790320} {"current_steps": 60145, "total_steps": 61300, "loss": 0.3044, "lr": 5.414553247586329e-08, "epoch": 9.8115823817292, "percentage": 98.12, "elapsed_time": "8:11:27", "remaining_time": "0:09:26", "throughput": 4401.91, "total_tokens": 129799792} {"current_steps": 60150, "total_steps": 61300, "loss": 0.3252, "lr": 5.367832578884735e-08, "epoch": 9.812398042414356, "percentage": 98.12, "elapsed_time": "8:11:29", "remaining_time": "0:09:23", "throughput": 4401.95, "total_tokens": 129811472} {"current_steps": 60155, "total_steps": 61300, "loss": 0.3283, "lr": 5.3213141377245205e-08, "epoch": 9.81321370309951, "percentage": 98.13, "elapsed_time": "8:11:31", "remaining_time": "0:09:21", "throughput": 4401.98, "total_tokens": 129822512} {"current_steps": 60160, "total_steps": 61300, "loss": 0.3213, "lr": 5.2749979278762794e-08, "epoch": 9.814029363784666, "percentage": 98.14, "elapsed_time": "8:11:34", "remaining_time": "0:09:18", "throughput": 4402.02, "total_tokens": 129834608} {"current_steps": 60165, "total_steps": 61300, "loss": 0.2876, "lr": 5.228883953094788e-08, "epoch": 9.81484502446982, "percentage": 98.15, "elapsed_time": "8:11:36", "remaining_time": "0:09:16", "throughput": 4402.05, "total_tokens": 129845008} {"current_steps": 60170, "total_steps": 61300, "loss": 0.3513, "lr": 5.182972217118165e-08, "epoch": 9.815660685154976, "percentage": 98.16, "elapsed_time": "8:11:38", "remaining_time": "0:09:13", "throughput": 4402.07, "total_tokens": 129854928} {"current_steps": 60175, "total_steps": 61300, "loss": 0.3207, "lr": 5.137262723668712e-08, "epoch": 9.81647634584013, "percentage": 98.16, "elapsed_time": "8:11:40", "remaining_time": "0:09:11", "throughput": 4402.11, "total_tokens": 129865904} {"current_steps": 60180, "total_steps": 61300, "loss": 0.346, "lr": 5.0917554764515206e-08, "epoch": 9.817292006525285, "percentage": 98.17, "elapsed_time": "8:11:43", "remaining_time": "0:09:09", "throughput": 4402.15, "total_tokens": 129878288} {"current_steps": 60185, "total_steps": 61300, "loss": 0.3168, "lr": 5.0464504791553066e-08, "epoch": 9.818107667210441, "percentage": 98.18, "elapsed_time": "8:11:45", "remaining_time": "0:09:06", "throughput": 4402.19, "total_tokens": 129890512} {"current_steps": 60190, "total_steps": 61300, "loss": 0.3253, "lr": 5.001347735453521e-08, "epoch": 9.818923327895595, "percentage": 98.19, "elapsed_time": "8:11:47", "remaining_time": "0:09:04", "throughput": 4402.22, "total_tokens": 129900560} {"current_steps": 60195, "total_steps": 61300, "loss": 0.3135, "lr": 4.95644724900185e-08, "epoch": 9.81973898858075, "percentage": 98.2, "elapsed_time": "8:11:50", "remaining_time": "0:09:01", "throughput": 4402.25, "total_tokens": 129912272} {"current_steps": 60200, "total_steps": 61300, "loss": 0.3171, "lr": 4.91174902344016e-08, "epoch": 9.820554649265905, "percentage": 98.21, "elapsed_time": "8:11:52", "remaining_time": "0:08:59", "throughput": 4402.29, "total_tokens": 129923120} {"current_steps": 60205, "total_steps": 61300, "loss": 0.3387, "lr": 4.867253062391941e-08, "epoch": 9.82137030995106, "percentage": 98.21, "elapsed_time": "8:11:55", "remaining_time": "0:08:56", "throughput": 4402.32, "total_tokens": 129935280} {"current_steps": 60210, "total_steps": 61300, "loss": 0.3312, "lr": 4.822959369464586e-08, "epoch": 9.822185970636216, "percentage": 98.22, "elapsed_time": "8:11:57", "remaining_time": "0:08:54", "throughput": 4402.35, "total_tokens": 129946032} {"current_steps": 60215, "total_steps": 61300, "loss": 0.3344, "lr": 4.7788679482485556e-08, "epoch": 9.82300163132137, "percentage": 98.23, "elapsed_time": "8:11:59", "remaining_time": "0:08:51", "throughput": 4402.38, "total_tokens": 129956784} {"current_steps": 60220, "total_steps": 61300, "loss": 0.3303, "lr": 4.734978802318213e-08, "epoch": 9.823817292006526, "percentage": 98.24, "elapsed_time": "8:12:01", "remaining_time": "0:08:49", "throughput": 4402.41, "total_tokens": 129967504} {"current_steps": 60225, "total_steps": 61300, "loss": 0.3523, "lr": 4.69129193523099e-08, "epoch": 9.82463295269168, "percentage": 98.25, "elapsed_time": "8:12:04", "remaining_time": "0:08:46", "throughput": 4402.43, "total_tokens": 129977840} {"current_steps": 60230, "total_steps": 61300, "loss": 0.327, "lr": 4.6478073505290544e-08, "epoch": 9.825448613376835, "percentage": 98.25, "elapsed_time": "8:12:06", "remaining_time": "0:08:44", "throughput": 4402.46, "total_tokens": 129988080} {"current_steps": 60235, "total_steps": 61300, "loss": 0.2867, "lr": 4.6045250517370854e-08, "epoch": 9.826264274061991, "percentage": 98.26, "elapsed_time": "8:12:08", "remaining_time": "0:08:42", "throughput": 4402.5, "total_tokens": 129999728} {"current_steps": 60240, "total_steps": 61300, "loss": 0.3589, "lr": 4.561445042363666e-08, "epoch": 9.827079934747145, "percentage": 98.27, "elapsed_time": "8:12:10", "remaining_time": "0:08:39", "throughput": 4402.53, "total_tokens": 130010352} {"current_steps": 60245, "total_steps": 61300, "loss": 0.3299, "lr": 4.518567325901279e-08, "epoch": 9.8278955954323, "percentage": 98.28, "elapsed_time": "8:12:13", "remaining_time": "0:08:37", "throughput": 4402.57, "total_tokens": 130021776} {"current_steps": 60250, "total_steps": 61300, "loss": 0.3227, "lr": 4.475891905825758e-08, "epoch": 9.828711256117455, "percentage": 98.29, "elapsed_time": "8:12:15", "remaining_time": "0:08:34", "throughput": 4402.61, "total_tokens": 130032304} {"current_steps": 60255, "total_steps": 61300, "loss": 0.3292, "lr": 4.4334187855968326e-08, "epoch": 9.82952691680261, "percentage": 98.3, "elapsed_time": "8:12:17", "remaining_time": "0:08:32", "throughput": 4402.63, "total_tokens": 130041840} {"current_steps": 60260, "total_steps": 61300, "loss": 0.3367, "lr": 4.391147968657028e-08, "epoch": 9.830342577487766, "percentage": 98.3, "elapsed_time": "8:12:19", "remaining_time": "0:08:29", "throughput": 4402.66, "total_tokens": 130051216} {"current_steps": 60265, "total_steps": 61300, "loss": 0.3118, "lr": 4.3490794584336024e-08, "epoch": 9.83115823817292, "percentage": 98.31, "elapsed_time": "8:12:21", "remaining_time": "0:08:27", "throughput": 4402.69, "total_tokens": 130061872} {"current_steps": 60270, "total_steps": 61300, "loss": 0.3022, "lr": 4.307213258336606e-08, "epoch": 9.831973898858076, "percentage": 98.32, "elapsed_time": "8:12:23", "remaining_time": "0:08:24", "throughput": 4402.73, "total_tokens": 130072944} {"current_steps": 60275, "total_steps": 61300, "loss": 0.3911, "lr": 4.2655493717597137e-08, "epoch": 9.83278955954323, "percentage": 98.33, "elapsed_time": "8:12:25", "remaining_time": "0:08:22", "throughput": 4402.76, "total_tokens": 130082704} {"current_steps": 60280, "total_steps": 61300, "loss": 0.3333, "lr": 4.224087802080778e-08, "epoch": 9.833605220228385, "percentage": 98.34, "elapsed_time": "8:12:28", "remaining_time": "0:08:19", "throughput": 4402.79, "total_tokens": 130093936} {"current_steps": 60285, "total_steps": 61300, "loss": 0.3306, "lr": 4.182828552660722e-08, "epoch": 9.83442088091354, "percentage": 98.34, "elapsed_time": "8:12:30", "remaining_time": "0:08:17", "throughput": 4402.82, "total_tokens": 130103888} {"current_steps": 60290, "total_steps": 61300, "loss": 0.3148, "lr": 4.141771626844093e-08, "epoch": 9.835236541598695, "percentage": 98.35, "elapsed_time": "8:12:32", "remaining_time": "0:08:15", "throughput": 4402.85, "total_tokens": 130114864} {"current_steps": 60295, "total_steps": 61300, "loss": 0.3622, "lr": 4.100917027959617e-08, "epoch": 9.83605220228385, "percentage": 98.36, "elapsed_time": "8:12:34", "remaining_time": "0:08:12", "throughput": 4402.87, "total_tokens": 130125136} {"current_steps": 60300, "total_steps": 61300, "loss": 0.304, "lr": 4.0602647593185325e-08, "epoch": 9.836867862969005, "percentage": 98.37, "elapsed_time": "8:12:36", "remaining_time": "0:08:10", "throughput": 4402.91, "total_tokens": 130136240} {"current_steps": 60305, "total_steps": 61300, "loss": 0.3659, "lr": 4.0198148242168163e-08, "epoch": 9.83768352365416, "percentage": 98.38, "elapsed_time": "8:12:39", "remaining_time": "0:08:07", "throughput": 4402.95, "total_tokens": 130146864} {"current_steps": 60310, "total_steps": 61300, "loss": 0.3184, "lr": 3.979567225933234e-08, "epoch": 9.838499184339314, "percentage": 98.38, "elapsed_time": "8:12:41", "remaining_time": "0:08:05", "throughput": 4402.97, "total_tokens": 130156560} {"current_steps": 60315, "total_steps": 61300, "loss": 0.327, "lr": 3.939521967730731e-08, "epoch": 9.83931484502447, "percentage": 98.39, "elapsed_time": "8:12:43", "remaining_time": "0:08:02", "throughput": 4403.01, "total_tokens": 130167664} {"current_steps": 60320, "total_steps": 61300, "loss": 0.3449, "lr": 3.8996790528555985e-08, "epoch": 9.840130505709626, "percentage": 98.4, "elapsed_time": "8:12:45", "remaining_time": "0:08:00", "throughput": 4403.05, "total_tokens": 130178992} {"current_steps": 60325, "total_steps": 61300, "loss": 0.3364, "lr": 3.860038484537476e-08, "epoch": 9.84094616639478, "percentage": 98.41, "elapsed_time": "8:12:47", "remaining_time": "0:07:57", "throughput": 4403.08, "total_tokens": 130188944} {"current_steps": 60330, "total_steps": 61300, "loss": 0.355, "lr": 3.820600265989904e-08, "epoch": 9.841761827079935, "percentage": 98.42, "elapsed_time": "8:12:49", "remaining_time": "0:07:55", "throughput": 4403.1, "total_tokens": 130199408} {"current_steps": 60335, "total_steps": 61300, "loss": 0.3339, "lr": 3.78136440040977e-08, "epoch": 9.84257748776509, "percentage": 98.43, "elapsed_time": "8:12:52", "remaining_time": "0:07:52", "throughput": 4403.14, "total_tokens": 130211152} {"current_steps": 60340, "total_steps": 61300, "loss": 0.3107, "lr": 3.742330890978141e-08, "epoch": 9.843393148450245, "percentage": 98.43, "elapsed_time": "8:12:54", "remaining_time": "0:07:50", "throughput": 4403.18, "total_tokens": 130222192} {"current_steps": 60345, "total_steps": 61300, "loss": 0.3018, "lr": 3.703499740859151e-08, "epoch": 9.844208809135399, "percentage": 98.44, "elapsed_time": "8:12:56", "remaining_time": "0:07:48", "throughput": 4403.21, "total_tokens": 130232912} {"current_steps": 60350, "total_steps": 61300, "loss": 0.3563, "lr": 3.6648709532002835e-08, "epoch": 9.845024469820554, "percentage": 98.45, "elapsed_time": "8:12:58", "remaining_time": "0:07:45", "throughput": 4403.23, "total_tokens": 130242704} {"current_steps": 60355, "total_steps": 61300, "loss": 0.3455, "lr": 3.6264445311334774e-08, "epoch": 9.84584013050571, "percentage": 98.46, "elapsed_time": "8:13:01", "remaining_time": "0:07:43", "throughput": 4403.27, "total_tokens": 130254224} {"current_steps": 60360, "total_steps": 61300, "loss": 0.345, "lr": 3.588220477773463e-08, "epoch": 9.846655791190864, "percentage": 98.47, "elapsed_time": "8:13:03", "remaining_time": "0:07:40", "throughput": 4403.31, "total_tokens": 130265392} {"current_steps": 60365, "total_steps": 61300, "loss": 0.3469, "lr": 3.5501987962191505e-08, "epoch": 9.84747145187602, "percentage": 98.47, "elapsed_time": "8:13:05", "remaining_time": "0:07:38", "throughput": 4403.34, "total_tokens": 130276048} {"current_steps": 60370, "total_steps": 61300, "loss": 0.3222, "lr": 3.5123794895522425e-08, "epoch": 9.848287112561174, "percentage": 98.48, "elapsed_time": "8:13:08", "remaining_time": "0:07:35", "throughput": 4403.38, "total_tokens": 130287472} {"current_steps": 60375, "total_steps": 61300, "loss": 0.3272, "lr": 3.4747625608391735e-08, "epoch": 9.84910277324633, "percentage": 98.49, "elapsed_time": "8:13:10", "remaining_time": "0:07:33", "throughput": 4403.41, "total_tokens": 130298832} {"current_steps": 60380, "total_steps": 61300, "loss": 0.33, "lr": 3.4373480131288936e-08, "epoch": 9.849918433931485, "percentage": 98.5, "elapsed_time": "8:13:12", "remaining_time": "0:07:30", "throughput": 4403.44, "total_tokens": 130308432} {"current_steps": 60385, "total_steps": 61300, "loss": 0.3542, "lr": 3.400135849454811e-08, "epoch": 9.850734094616639, "percentage": 98.51, "elapsed_time": "8:13:14", "remaining_time": "0:07:28", "throughput": 4403.46, "total_tokens": 130318544} {"current_steps": 60390, "total_steps": 61300, "loss": 0.3267, "lr": 3.363126072833123e-08, "epoch": 9.851549755301795, "percentage": 98.52, "elapsed_time": "8:13:16", "remaining_time": "0:07:25", "throughput": 4403.48, "total_tokens": 130328176} {"current_steps": 60395, "total_steps": 61300, "loss": 0.3535, "lr": 3.326318686264485e-08, "epoch": 9.852365415986949, "percentage": 98.52, "elapsed_time": "8:13:18", "remaining_time": "0:07:23", "throughput": 4403.52, "total_tokens": 130338896} {"current_steps": 60400, "total_steps": 61300, "loss": 0.3075, "lr": 3.2897136927323436e-08, "epoch": 9.853181076672104, "percentage": 98.53, "elapsed_time": "8:13:21", "remaining_time": "0:07:21", "throughput": 4403.55, "total_tokens": 130350160} {"current_steps": 60405, "total_steps": 61300, "loss": 0.3336, "lr": 3.253311095204048e-08, "epoch": 9.85399673735726, "percentage": 98.54, "elapsed_time": "8:13:23", "remaining_time": "0:07:18", "throughput": 4403.59, "total_tokens": 130360976} {"current_steps": 60410, "total_steps": 61300, "loss": 0.3131, "lr": 3.2171108966308486e-08, "epoch": 9.854812398042414, "percentage": 98.55, "elapsed_time": "8:13:25", "remaining_time": "0:07:16", "throughput": 4403.62, "total_tokens": 130371184} {"current_steps": 60415, "total_steps": 61300, "loss": 0.3146, "lr": 3.1811130999473415e-08, "epoch": 9.85562805872757, "percentage": 98.56, "elapsed_time": "8:13:27", "remaining_time": "0:07:13", "throughput": 4403.65, "total_tokens": 130381168} {"current_steps": 60420, "total_steps": 61300, "loss": 0.3349, "lr": 3.145317708071194e-08, "epoch": 9.856443719412724, "percentage": 98.56, "elapsed_time": "8:13:29", "remaining_time": "0:07:11", "throughput": 4403.67, "total_tokens": 130390544} {"current_steps": 60425, "total_steps": 61300, "loss": 0.2997, "lr": 3.1097247239048057e-08, "epoch": 9.85725938009788, "percentage": 98.57, "elapsed_time": "8:13:31", "remaining_time": "0:07:08", "throughput": 4403.71, "total_tokens": 130401232} {"current_steps": 60430, "total_steps": 61300, "loss": 0.3194, "lr": 3.074334150333091e-08, "epoch": 9.858075040783035, "percentage": 98.58, "elapsed_time": "8:13:34", "remaining_time": "0:07:06", "throughput": 4403.75, "total_tokens": 130412560} {"current_steps": 60435, "total_steps": 61300, "loss": 0.3336, "lr": 3.039145990225145e-08, "epoch": 9.858890701468189, "percentage": 98.59, "elapsed_time": "8:13:36", "remaining_time": "0:07:03", "throughput": 4403.78, "total_tokens": 130423472} {"current_steps": 60440, "total_steps": 61300, "loss": 0.3158, "lr": 3.0041602464334076e-08, "epoch": 9.859706362153345, "percentage": 98.6, "elapsed_time": "8:13:38", "remaining_time": "0:07:01", "throughput": 4403.8, "total_tokens": 130433008} {"current_steps": 60445, "total_steps": 61300, "loss": 0.3181, "lr": 2.9693769217942203e-08, "epoch": 9.860522022838499, "percentage": 98.61, "elapsed_time": "8:13:40", "remaining_time": "0:06:58", "throughput": 4403.85, "total_tokens": 130445776} {"current_steps": 60450, "total_steps": 61300, "loss": 0.2921, "lr": 2.9347960191269952e-08, "epoch": 9.861337683523654, "percentage": 98.61, "elapsed_time": "8:13:43", "remaining_time": "0:06:56", "throughput": 4403.89, "total_tokens": 130456720} {"current_steps": 60455, "total_steps": 61300, "loss": 0.3384, "lr": 2.900417541235323e-08, "epoch": 9.86215334420881, "percentage": 98.62, "elapsed_time": "8:13:45", "remaining_time": "0:06:54", "throughput": 4403.93, "total_tokens": 130468176} {"current_steps": 60460, "total_steps": 61300, "loss": 0.3675, "lr": 2.8662414909058634e-08, "epoch": 9.862969004893964, "percentage": 98.63, "elapsed_time": "8:13:47", "remaining_time": "0:06:51", "throughput": 4403.97, "total_tokens": 130479344} {"current_steps": 60465, "total_steps": 61300, "loss": 0.3046, "lr": 2.8322678709094553e-08, "epoch": 9.86378466557912, "percentage": 98.64, "elapsed_time": "8:13:50", "remaining_time": "0:06:49", "throughput": 4403.99, "total_tokens": 130490672} {"current_steps": 60470, "total_steps": 61300, "loss": 0.3178, "lr": 2.7984966839997294e-08, "epoch": 9.864600326264274, "percentage": 98.65, "elapsed_time": "8:13:52", "remaining_time": "0:06:46", "throughput": 4404.03, "total_tokens": 130502160} {"current_steps": 60475, "total_steps": 61300, "loss": 0.3367, "lr": 2.7649279329142185e-08, "epoch": 9.86541598694943, "percentage": 98.65, "elapsed_time": "8:13:54", "remaining_time": "0:06:44", "throughput": 4404.07, "total_tokens": 130514160} {"current_steps": 60480, "total_steps": 61300, "loss": 0.3177, "lr": 2.7315616203749118e-08, "epoch": 9.866231647634583, "percentage": 98.66, "elapsed_time": "8:13:56", "remaining_time": "0:06:41", "throughput": 4404.1, "total_tokens": 130524336} {"current_steps": 60485, "total_steps": 61300, "loss": 0.3632, "lr": 2.6983977490860345e-08, "epoch": 9.867047308319739, "percentage": 98.67, "elapsed_time": "8:13:59", "remaining_time": "0:06:39", "throughput": 4404.14, "total_tokens": 130535440} {"current_steps": 60490, "total_steps": 61300, "loss": 0.3283, "lr": 2.6654363217362698e-08, "epoch": 9.867862969004895, "percentage": 98.68, "elapsed_time": "8:14:01", "remaining_time": "0:06:36", "throughput": 4404.17, "total_tokens": 130546832} {"current_steps": 60495, "total_steps": 61300, "loss": 0.3366, "lr": 2.632677340997647e-08, "epoch": 9.868678629690049, "percentage": 98.69, "elapsed_time": "8:14:03", "remaining_time": "0:06:34", "throughput": 4404.2, "total_tokens": 130557168} {"current_steps": 60500, "total_steps": 61300, "loss": 0.3314, "lr": 2.6001208095258188e-08, "epoch": 9.869494290375204, "percentage": 98.69, "elapsed_time": "8:14:05", "remaining_time": "0:06:32", "throughput": 4404.23, "total_tokens": 130567664} {"current_steps": 60505, "total_steps": 61300, "loss": 0.3231, "lr": 2.5677667299597863e-08, "epoch": 9.870309951060358, "percentage": 98.7, "elapsed_time": "8:14:08", "remaining_time": "0:06:29", "throughput": 4404.26, "total_tokens": 130577520} {"current_steps": 60510, "total_steps": 61300, "loss": 0.3376, "lr": 2.5356151049221734e-08, "epoch": 9.871125611745514, "percentage": 98.71, "elapsed_time": "8:14:10", "remaining_time": "0:06:27", "throughput": 4404.29, "total_tokens": 130589328} {"current_steps": 60515, "total_steps": 61300, "loss": 0.3117, "lr": 2.5036659370197836e-08, "epoch": 9.87194127243067, "percentage": 98.72, "elapsed_time": "8:14:12", "remaining_time": "0:06:24", "throughput": 4404.33, "total_tokens": 130599760} {"current_steps": 60520, "total_steps": 61300, "loss": 0.3491, "lr": 2.4719192288424896e-08, "epoch": 9.872756933115824, "percentage": 98.73, "elapsed_time": "8:14:14", "remaining_time": "0:06:22", "throughput": 4404.36, "total_tokens": 130610576} {"current_steps": 60525, "total_steps": 61300, "loss": 0.3681, "lr": 2.440374982963789e-08, "epoch": 9.87357259380098, "percentage": 98.74, "elapsed_time": "8:14:16", "remaining_time": "0:06:19", "throughput": 4404.4, "total_tokens": 130621168} {"current_steps": 60530, "total_steps": 61300, "loss": 0.3285, "lr": 2.409033201940525e-08, "epoch": 9.874388254486133, "percentage": 98.74, "elapsed_time": "8:14:18", "remaining_time": "0:06:17", "throughput": 4404.43, "total_tokens": 130630736} {"current_steps": 60535, "total_steps": 61300, "loss": 0.3354, "lr": 2.3778938883139977e-08, "epoch": 9.875203915171289, "percentage": 98.75, "elapsed_time": "8:14:21", "remaining_time": "0:06:14", "throughput": 4404.46, "total_tokens": 130641840} {"current_steps": 60540, "total_steps": 61300, "loss": 0.306, "lr": 2.3469570446080223e-08, "epoch": 9.876019575856443, "percentage": 98.76, "elapsed_time": "8:14:23", "remaining_time": "0:06:12", "throughput": 4404.5, "total_tokens": 130652816} {"current_steps": 60545, "total_steps": 61300, "loss": 0.3369, "lr": 2.3162226733305925e-08, "epoch": 9.876835236541599, "percentage": 98.77, "elapsed_time": "8:14:25", "remaining_time": "0:06:09", "throughput": 4404.53, "total_tokens": 130663248} {"current_steps": 60550, "total_steps": 61300, "loss": 0.346, "lr": 2.2856907769736037e-08, "epoch": 9.877650897226754, "percentage": 98.78, "elapsed_time": "8:14:28", "remaining_time": "0:06:07", "throughput": 4404.57, "total_tokens": 130675184} {"current_steps": 60555, "total_steps": 61300, "loss": 0.3295, "lr": 2.255361358011465e-08, "epoch": 9.878466557911908, "percentage": 98.78, "elapsed_time": "8:14:30", "remaining_time": "0:06:05", "throughput": 4404.6, "total_tokens": 130686576} {"current_steps": 60560, "total_steps": 61300, "loss": 0.3426, "lr": 2.2252344189033213e-08, "epoch": 9.879282218597064, "percentage": 98.79, "elapsed_time": "8:14:32", "remaining_time": "0:06:02", "throughput": 4404.63, "total_tokens": 130696240} {"current_steps": 60565, "total_steps": 61300, "loss": 0.3196, "lr": 2.1953099620911076e-08, "epoch": 9.880097879282218, "percentage": 98.8, "elapsed_time": "8:14:34", "remaining_time": "0:06:00", "throughput": 4404.65, "total_tokens": 130706064} {"current_steps": 60570, "total_steps": 61300, "loss": 0.3417, "lr": 2.165587990000939e-08, "epoch": 9.880913539967374, "percentage": 98.81, "elapsed_time": "8:14:36", "remaining_time": "0:05:57", "throughput": 4404.68, "total_tokens": 130716720} {"current_steps": 60575, "total_steps": 61300, "loss": 0.3526, "lr": 2.1360685050419994e-08, "epoch": 9.88172920065253, "percentage": 98.82, "elapsed_time": "8:14:38", "remaining_time": "0:05:55", "throughput": 4404.71, "total_tokens": 130726288} {"current_steps": 60580, "total_steps": 61300, "loss": 0.341, "lr": 2.106751509607374e-08, "epoch": 9.882544861337683, "percentage": 98.83, "elapsed_time": "8:14:40", "remaining_time": "0:05:52", "throughput": 4404.74, "total_tokens": 130736368} {"current_steps": 60585, "total_steps": 61300, "loss": 0.3547, "lr": 2.0776370060737737e-08, "epoch": 9.883360522022839, "percentage": 98.83, "elapsed_time": "8:14:42", "remaining_time": "0:05:50", "throughput": 4404.77, "total_tokens": 130746160} {"current_steps": 60590, "total_steps": 61300, "loss": 0.3215, "lr": 2.0487249968012546e-08, "epoch": 9.884176182707993, "percentage": 98.84, "elapsed_time": "8:14:44", "remaining_time": "0:05:47", "throughput": 4404.8, "total_tokens": 130755728} {"current_steps": 60595, "total_steps": 61300, "loss": 0.281, "lr": 2.020015484133497e-08, "epoch": 9.884991843393149, "percentage": 98.85, "elapsed_time": "8:14:47", "remaining_time": "0:05:45", "throughput": 4404.83, "total_tokens": 130767088} {"current_steps": 60600, "total_steps": 61300, "loss": 0.3332, "lr": 1.9915084703980845e-08, "epoch": 9.885807504078304, "percentage": 98.86, "elapsed_time": "8:14:49", "remaining_time": "0:05:42", "throughput": 4404.86, "total_tokens": 130776944} {"current_steps": 60605, "total_steps": 61300, "loss": 0.3404, "lr": 1.9632039579053907e-08, "epoch": 9.886623164763458, "percentage": 98.87, "elapsed_time": "8:14:51", "remaining_time": "0:05:40", "throughput": 4404.89, "total_tokens": 130786480} {"current_steps": 60610, "total_steps": 61300, "loss": 0.3314, "lr": 1.935101948950524e-08, "epoch": 9.887438825448614, "percentage": 98.87, "elapsed_time": "8:14:53", "remaining_time": "0:05:38", "throughput": 4404.92, "total_tokens": 130797968} {"current_steps": 60615, "total_steps": 61300, "loss": 0.3537, "lr": 1.9072024458113847e-08, "epoch": 9.888254486133768, "percentage": 98.88, "elapsed_time": "8:14:55", "remaining_time": "0:05:35", "throughput": 4404.95, "total_tokens": 130808272} {"current_steps": 60620, "total_steps": 61300, "loss": 0.3099, "lr": 1.8795054507494967e-08, "epoch": 9.889070146818923, "percentage": 98.89, "elapsed_time": "8:14:57", "remaining_time": "0:05:33", "throughput": 4404.98, "total_tokens": 130817488} {"current_steps": 60625, "total_steps": 61300, "loss": 0.3297, "lr": 1.852010966010287e-08, "epoch": 9.88988580750408, "percentage": 98.9, "elapsed_time": "8:14:59", "remaining_time": "0:05:30", "throughput": 4405.01, "total_tokens": 130828432} {"current_steps": 60630, "total_steps": 61300, "loss": 0.3138, "lr": 1.8247189938225274e-08, "epoch": 9.890701468189233, "percentage": 98.91, "elapsed_time": "8:15:02", "remaining_time": "0:05:28", "throughput": 4405.04, "total_tokens": 130838416} {"current_steps": 60635, "total_steps": 61300, "loss": 0.3011, "lr": 1.7976295363988927e-08, "epoch": 9.891517128874389, "percentage": 98.92, "elapsed_time": "8:15:03", "remaining_time": "0:05:25", "throughput": 4405.06, "total_tokens": 130847920} {"current_steps": 60640, "total_steps": 61300, "loss": 0.3052, "lr": 1.7707425959348488e-08, "epoch": 9.892332789559543, "percentage": 98.92, "elapsed_time": "8:15:06", "remaining_time": "0:05:23", "throughput": 4405.1, "total_tokens": 130859184} {"current_steps": 60645, "total_steps": 61300, "loss": 0.3217, "lr": 1.744058174610319e-08, "epoch": 9.893148450244698, "percentage": 98.93, "elapsed_time": "8:15:08", "remaining_time": "0:05:20", "throughput": 4405.13, "total_tokens": 130869808} {"current_steps": 60650, "total_steps": 61300, "loss": 0.3224, "lr": 1.7175762745885727e-08, "epoch": 9.893964110929852, "percentage": 98.94, "elapsed_time": "8:15:10", "remaining_time": "0:05:18", "throughput": 4405.16, "total_tokens": 130880912} {"current_steps": 60655, "total_steps": 61300, "loss": 0.3267, "lr": 1.6912968980162257e-08, "epoch": 9.894779771615008, "percentage": 98.95, "elapsed_time": "8:15:13", "remaining_time": "0:05:15", "throughput": 4405.19, "total_tokens": 130892336} {"current_steps": 60660, "total_steps": 61300, "loss": 0.3109, "lr": 1.665220047023519e-08, "epoch": 9.895595432300164, "percentage": 98.96, "elapsed_time": "8:15:14", "remaining_time": "0:05:13", "throughput": 4405.21, "total_tokens": 130900752} {"current_steps": 60665, "total_steps": 61300, "loss": 0.3366, "lr": 1.639345723724872e-08, "epoch": 9.896411092985318, "percentage": 98.96, "elapsed_time": "8:15:17", "remaining_time": "0:05:11", "throughput": 4405.25, "total_tokens": 130911600} {"current_steps": 60670, "total_steps": 61300, "loss": 0.3025, "lr": 1.6136739302169412e-08, "epoch": 9.897226753670473, "percentage": 98.97, "elapsed_time": "8:15:19", "remaining_time": "0:05:08", "throughput": 4405.28, "total_tokens": 130922640} {"current_steps": 60675, "total_steps": 61300, "loss": 0.3458, "lr": 1.588204668581672e-08, "epoch": 9.898042414355627, "percentage": 98.98, "elapsed_time": "8:15:21", "remaining_time": "0:05:06", "throughput": 4405.3, "total_tokens": 130933136} {"current_steps": 60680, "total_steps": 61300, "loss": 0.3298, "lr": 1.5629379408832468e-08, "epoch": 9.898858075040783, "percentage": 98.99, "elapsed_time": "8:15:24", "remaining_time": "0:05:03", "throughput": 4405.33, "total_tokens": 130944336} {"current_steps": 60685, "total_steps": 61300, "loss": 0.3178, "lr": 1.537873749169749e-08, "epoch": 9.899673735725939, "percentage": 99.0, "elapsed_time": "8:15:25", "remaining_time": "0:05:01", "throughput": 4405.35, "total_tokens": 130952848} {"current_steps": 60690, "total_steps": 61300, "loss": 0.3293, "lr": 1.513012095473443e-08, "epoch": 9.900489396411093, "percentage": 99.0, "elapsed_time": "8:15:28", "remaining_time": "0:04:58", "throughput": 4405.39, "total_tokens": 130963536} {"current_steps": 60695, "total_steps": 61300, "loss": 0.3496, "lr": 1.4883529818096598e-08, "epoch": 9.901305057096248, "percentage": 99.01, "elapsed_time": "8:15:30", "remaining_time": "0:04:56", "throughput": 4405.42, "total_tokens": 130973840} {"current_steps": 60700, "total_steps": 61300, "loss": 0.3069, "lr": 1.4638964101773568e-08, "epoch": 9.902120717781402, "percentage": 99.02, "elapsed_time": "8:15:32", "remaining_time": "0:04:53", "throughput": 4405.45, "total_tokens": 130984304} {"current_steps": 60705, "total_steps": 61300, "loss": 0.3217, "lr": 1.4396423825588367e-08, "epoch": 9.902936378466558, "percentage": 99.03, "elapsed_time": "8:15:34", "remaining_time": "0:04:51", "throughput": 4405.48, "total_tokens": 130995504} {"current_steps": 60710, "total_steps": 61300, "loss": 0.3283, "lr": 1.4155909009205826e-08, "epoch": 9.903752039151712, "percentage": 99.04, "elapsed_time": "8:15:36", "remaining_time": "0:04:48", "throughput": 4405.51, "total_tokens": 131005968} {"current_steps": 60715, "total_steps": 61300, "loss": 0.3169, "lr": 1.3917419672124233e-08, "epoch": 9.904567699836868, "percentage": 99.05, "elapsed_time": "8:15:39", "remaining_time": "0:04:46", "throughput": 4405.56, "total_tokens": 131018160} {"current_steps": 60720, "total_steps": 61300, "loss": 0.3373, "lr": 1.368095583367257e-08, "epoch": 9.905383360522023, "percentage": 99.05, "elapsed_time": "8:15:41", "remaining_time": "0:04:44", "throughput": 4405.59, "total_tokens": 131029008} {"current_steps": 60725, "total_steps": 61300, "loss": 0.3416, "lr": 1.3446517513021617e-08, "epoch": 9.906199021207177, "percentage": 99.06, "elapsed_time": "8:15:43", "remaining_time": "0:04:41", "throughput": 4405.62, "total_tokens": 131038960} {"current_steps": 60730, "total_steps": 61300, "loss": 0.3711, "lr": 1.321410472917839e-08, "epoch": 9.907014681892333, "percentage": 99.07, "elapsed_time": "8:15:45", "remaining_time": "0:04:39", "throughput": 4405.66, "total_tokens": 131050160} {"current_steps": 60735, "total_steps": 61300, "loss": 0.3204, "lr": 1.2983717500977822e-08, "epoch": 9.907830342577487, "percentage": 99.08, "elapsed_time": "8:15:47", "remaining_time": "0:04:36", "throughput": 4405.69, "total_tokens": 131060048} {"current_steps": 60740, "total_steps": 61300, "loss": 0.355, "lr": 1.275535584710219e-08, "epoch": 9.908646003262643, "percentage": 99.09, "elapsed_time": "8:15:49", "remaining_time": "0:04:34", "throughput": 4405.71, "total_tokens": 131069360} {"current_steps": 60745, "total_steps": 61300, "loss": 0.3333, "lr": 1.2529019786061691e-08, "epoch": 9.909461663947798, "percentage": 99.09, "elapsed_time": "8:15:52", "remaining_time": "0:04:31", "throughput": 4405.74, "total_tokens": 131079888} {"current_steps": 60750, "total_steps": 61300, "loss": 0.3421, "lr": 1.2304709336205533e-08, "epoch": 9.910277324632952, "percentage": 99.1, "elapsed_time": "8:15:54", "remaining_time": "0:04:29", "throughput": 4405.77, "total_tokens": 131090512} {"current_steps": 60755, "total_steps": 61300, "loss": 0.326, "lr": 1.2082424515713619e-08, "epoch": 9.911092985318108, "percentage": 99.11, "elapsed_time": "8:15:56", "remaining_time": "0:04:26", "throughput": 4405.81, "total_tokens": 131101680} {"current_steps": 60760, "total_steps": 61300, "loss": 0.36, "lr": 1.1862165342607645e-08, "epoch": 9.911908646003262, "percentage": 99.12, "elapsed_time": "8:15:58", "remaining_time": "0:04:24", "throughput": 4405.84, "total_tokens": 131112336} {"current_steps": 60765, "total_steps": 61300, "loss": 0.3186, "lr": 1.1643931834745548e-08, "epoch": 9.912724306688418, "percentage": 99.13, "elapsed_time": "8:16:01", "remaining_time": "0:04:22", "throughput": 4405.87, "total_tokens": 131123088} {"current_steps": 60770, "total_steps": 61300, "loss": 0.3516, "lr": 1.1427724009813179e-08, "epoch": 9.913539967373573, "percentage": 99.14, "elapsed_time": "8:16:02", "remaining_time": "0:04:19", "throughput": 4405.89, "total_tokens": 131132368} {"current_steps": 60775, "total_steps": 61300, "loss": 0.3451, "lr": 1.1213541885340962e-08, "epoch": 9.914355628058727, "percentage": 99.14, "elapsed_time": "8:16:05", "remaining_time": "0:04:17", "throughput": 4405.93, "total_tokens": 131143600} {"current_steps": 60780, "total_steps": 61300, "loss": 0.3559, "lr": 1.1001385478692783e-08, "epoch": 9.915171288743883, "percentage": 99.15, "elapsed_time": "8:16:07", "remaining_time": "0:04:14", "throughput": 4405.95, "total_tokens": 131153872} {"current_steps": 60785, "total_steps": 61300, "loss": 0.3075, "lr": 1.0791254807063223e-08, "epoch": 9.915986949429037, "percentage": 99.16, "elapsed_time": "8:16:09", "remaining_time": "0:04:12", "throughput": 4405.98, "total_tokens": 131164848} {"current_steps": 60790, "total_steps": 61300, "loss": 0.3185, "lr": 1.0583149887488653e-08, "epoch": 9.916802610114193, "percentage": 99.17, "elapsed_time": "8:16:11", "remaining_time": "0:04:09", "throughput": 4406.01, "total_tokens": 131175280} {"current_steps": 60795, "total_steps": 61300, "loss": 0.3331, "lr": 1.0377070736838912e-08, "epoch": 9.917618270799348, "percentage": 99.18, "elapsed_time": "8:16:14", "remaining_time": "0:04:07", "throughput": 4406.04, "total_tokens": 131185776} {"current_steps": 60800, "total_steps": 61300, "loss": 0.2959, "lr": 1.017301737182008e-08, "epoch": 9.918433931484502, "percentage": 99.18, "elapsed_time": "8:16:16", "remaining_time": "0:04:04", "throughput": 4406.07, "total_tokens": 131196944} {"current_steps": 60805, "total_steps": 61300, "loss": 0.3413, "lr": 9.970989808974485e-09, "epoch": 9.919249592169658, "percentage": 99.19, "elapsed_time": "8:16:18", "remaining_time": "0:04:02", "throughput": 4406.11, "total_tokens": 131208752} {"current_steps": 60810, "total_steps": 61300, "loss": 0.322, "lr": 9.77098806467791e-09, "epoch": 9.920065252854812, "percentage": 99.2, "elapsed_time": "8:16:20", "remaining_time": "0:03:59", "throughput": 4406.13, "total_tokens": 131217360} {"current_steps": 60815, "total_steps": 61300, "loss": 0.3383, "lr": 9.573012155145166e-09, "epoch": 9.920880913539968, "percentage": 99.21, "elapsed_time": "8:16:22", "remaining_time": "0:03:57", "throughput": 4406.17, "total_tokens": 131228304} {"current_steps": 60820, "total_steps": 61300, "loss": 0.3458, "lr": 9.37706209642175e-09, "epoch": 9.921696574225122, "percentage": 99.22, "elapsed_time": "8:16:25", "remaining_time": "0:03:55", "throughput": 4406.2, "total_tokens": 131239568} {"current_steps": 60825, "total_steps": 61300, "loss": 0.3138, "lr": 9.183137904397732e-09, "epoch": 9.922512234910277, "percentage": 99.23, "elapsed_time": "8:16:27", "remaining_time": "0:03:52", "throughput": 4406.24, "total_tokens": 131250576} {"current_steps": 60830, "total_steps": 61300, "loss": 0.3358, "lr": 8.991239594788315e-09, "epoch": 9.923327895595433, "percentage": 99.23, "elapsed_time": "8:16:29", "remaining_time": "0:03:50", "throughput": 4406.27, "total_tokens": 131261616} {"current_steps": 60835, "total_steps": 61300, "loss": 0.338, "lr": 8.801367183153276e-09, "epoch": 9.924143556280587, "percentage": 99.24, "elapsed_time": "8:16:32", "remaining_time": "0:03:47", "throughput": 4406.3, "total_tokens": 131272400} {"current_steps": 60840, "total_steps": 61300, "loss": 0.3322, "lr": 8.61352068488308e-09, "epoch": 9.924959216965743, "percentage": 99.25, "elapsed_time": "8:16:34", "remaining_time": "0:03:45", "throughput": 4406.32, "total_tokens": 131283280} {"current_steps": 60845, "total_steps": 61300, "loss": 0.3363, "lr": 8.427700115207216e-09, "epoch": 9.925774877650896, "percentage": 99.26, "elapsed_time": "8:16:36", "remaining_time": "0:03:42", "throughput": 4406.36, "total_tokens": 131293808} {"current_steps": 60850, "total_steps": 61300, "loss": 0.2767, "lr": 8.243905489185855e-09, "epoch": 9.926590538336052, "percentage": 99.27, "elapsed_time": "8:16:38", "remaining_time": "0:03:40", "throughput": 4406.4, "total_tokens": 131304016} {"current_steps": 60855, "total_steps": 61300, "loss": 0.3666, "lr": 8.062136821723742e-09, "epoch": 9.927406199021208, "percentage": 99.27, "elapsed_time": "8:16:40", "remaining_time": "0:03:37", "throughput": 4406.42, "total_tokens": 131314032} {"current_steps": 60860, "total_steps": 61300, "loss": 0.304, "lr": 7.882394127550763e-09, "epoch": 9.928221859706362, "percentage": 99.28, "elapsed_time": "8:16:42", "remaining_time": "0:03:35", "throughput": 4406.46, "total_tokens": 131324112} {"current_steps": 60865, "total_steps": 61300, "loss": 0.3152, "lr": 7.704677421238593e-09, "epoch": 9.929037520391518, "percentage": 99.29, "elapsed_time": "8:16:44", "remaining_time": "0:03:33", "throughput": 4406.48, "total_tokens": 131334352} {"current_steps": 60870, "total_steps": 61300, "loss": 0.347, "lr": 7.528986717195152e-09, "epoch": 9.929853181076671, "percentage": 99.3, "elapsed_time": "8:16:46", "remaining_time": "0:03:30", "throughput": 4406.52, "total_tokens": 131344656} {"current_steps": 60875, "total_steps": 61300, "loss": 0.3704, "lr": 7.355322029661826e-09, "epoch": 9.930668841761827, "percentage": 99.31, "elapsed_time": "8:16:49", "remaining_time": "0:03:28", "throughput": 4406.55, "total_tokens": 131355984} {"current_steps": 60880, "total_steps": 61300, "loss": 0.3218, "lr": 7.183683372719019e-09, "epoch": 9.931484502446983, "percentage": 99.31, "elapsed_time": "8:16:51", "remaining_time": "0:03:25", "throughput": 4406.59, "total_tokens": 131367056} {"current_steps": 60885, "total_steps": 61300, "loss": 0.3357, "lr": 7.0140707602805995e-09, "epoch": 9.932300163132137, "percentage": 99.32, "elapsed_time": "8:16:53", "remaining_time": "0:03:23", "throughput": 4406.62, "total_tokens": 131378192} {"current_steps": 60890, "total_steps": 61300, "loss": 0.3347, "lr": 6.846484206091131e-09, "epoch": 9.933115823817293, "percentage": 99.33, "elapsed_time": "8:16:56", "remaining_time": "0:03:20", "throughput": 4406.66, "total_tokens": 131389040} {"current_steps": 60895, "total_steps": 61300, "loss": 0.3222, "lr": 6.6809237237425156e-09, "epoch": 9.933931484502446, "percentage": 99.34, "elapsed_time": "8:16:58", "remaining_time": "0:03:18", "throughput": 4406.7, "total_tokens": 131399664} {"current_steps": 60900, "total_steps": 61300, "loss": 0.3513, "lr": 6.517389326651801e-09, "epoch": 9.934747145187602, "percentage": 99.35, "elapsed_time": "8:17:00", "remaining_time": "0:03:15", "throughput": 4406.72, "total_tokens": 131409680} {"current_steps": 60905, "total_steps": 61300, "loss": 0.3291, "lr": 6.3558810280778254e-09, "epoch": 9.935562805872756, "percentage": 99.36, "elapsed_time": "8:17:02", "remaining_time": "0:03:13", "throughput": 4406.75, "total_tokens": 131420240} {"current_steps": 60910, "total_steps": 61300, "loss": 0.2757, "lr": 6.196398841112893e-09, "epoch": 9.936378466557912, "percentage": 99.36, "elapsed_time": "8:17:04", "remaining_time": "0:03:10", "throughput": 4406.78, "total_tokens": 131429488} {"current_steps": 60915, "total_steps": 61300, "loss": 0.3308, "lr": 6.038942778685553e-09, "epoch": 9.937194127243067, "percentage": 99.37, "elapsed_time": "8:17:06", "remaining_time": "0:03:08", "throughput": 4406.81, "total_tokens": 131439792} {"current_steps": 60920, "total_steps": 61300, "loss": 0.3081, "lr": 5.883512853557816e-09, "epoch": 9.938009787928221, "percentage": 99.38, "elapsed_time": "8:17:08", "remaining_time": "0:03:06", "throughput": 4406.83, "total_tokens": 131448976} {"current_steps": 60925, "total_steps": 61300, "loss": 0.3351, "lr": 5.730109078330714e-09, "epoch": 9.938825448613377, "percentage": 99.39, "elapsed_time": "8:17:10", "remaining_time": "0:03:03", "throughput": 4406.86, "total_tokens": 131459088} {"current_steps": 60930, "total_steps": 61300, "loss": 0.3356, "lr": 5.578731465444298e-09, "epoch": 9.939641109298531, "percentage": 99.4, "elapsed_time": "8:17:12", "remaining_time": "0:03:01", "throughput": 4406.89, "total_tokens": 131470096} {"current_steps": 60935, "total_steps": 61300, "loss": 0.3581, "lr": 5.429380027163755e-09, "epoch": 9.940456769983687, "percentage": 99.4, "elapsed_time": "8:17:14", "remaining_time": "0:02:58", "throughput": 4406.91, "total_tokens": 131479376} {"current_steps": 60940, "total_steps": 61300, "loss": 0.3147, "lr": 5.2820547755988434e-09, "epoch": 9.941272430668842, "percentage": 99.41, "elapsed_time": "8:17:17", "remaining_time": "0:02:56", "throughput": 4406.95, "total_tokens": 131491792} {"current_steps": 60945, "total_steps": 61300, "loss": 0.2994, "lr": 5.1367557226927875e-09, "epoch": 9.942088091353996, "percentage": 99.42, "elapsed_time": "8:17:19", "remaining_time": "0:02:53", "throughput": 4406.98, "total_tokens": 131502512} {"current_steps": 60950, "total_steps": 61300, "loss": 0.3413, "lr": 4.9934828802250535e-09, "epoch": 9.942903752039152, "percentage": 99.43, "elapsed_time": "8:17:21", "remaining_time": "0:02:51", "throughput": 4407.02, "total_tokens": 131514224} {"current_steps": 60955, "total_steps": 61300, "loss": 0.3092, "lr": 4.852236259805798e-09, "epoch": 9.943719412724306, "percentage": 99.44, "elapsed_time": "8:17:24", "remaining_time": "0:02:48", "throughput": 4407.06, "total_tokens": 131525840} {"current_steps": 60960, "total_steps": 61300, "loss": 0.3293, "lr": 4.7130158728925236e-09, "epoch": 9.944535073409462, "percentage": 99.45, "elapsed_time": "8:17:26", "remaining_time": "0:02:46", "throughput": 4407.09, "total_tokens": 131536208} {"current_steps": 60965, "total_steps": 61300, "loss": 0.279, "lr": 4.575821730765095e-09, "epoch": 9.945350734094617, "percentage": 99.45, "elapsed_time": "8:17:28", "remaining_time": "0:02:44", "throughput": 4407.12, "total_tokens": 131547344} {"current_steps": 60970, "total_steps": 61300, "loss": 0.3507, "lr": 4.440653844545173e-09, "epoch": 9.946166394779771, "percentage": 99.46, "elapsed_time": "8:17:31", "remaining_time": "0:02:41", "throughput": 4407.14, "total_tokens": 131558544} {"current_steps": 60975, "total_steps": 61300, "loss": 0.3433, "lr": 4.307512225196209e-09, "epoch": 9.946982055464927, "percentage": 99.47, "elapsed_time": "8:17:33", "remaining_time": "0:02:39", "throughput": 4407.17, "total_tokens": 131569136} {"current_steps": 60980, "total_steps": 61300, "loss": 0.3321, "lr": 4.176396883504019e-09, "epoch": 9.947797716150081, "percentage": 99.48, "elapsed_time": "8:17:35", "remaining_time": "0:02:36", "throughput": 4407.21, "total_tokens": 131580848} {"current_steps": 60985, "total_steps": 61300, "loss": 0.3267, "lr": 4.047307830101765e-09, "epoch": 9.948613376835237, "percentage": 99.49, "elapsed_time": "8:17:38", "remaining_time": "0:02:34", "throughput": 4407.24, "total_tokens": 131591664} {"current_steps": 60990, "total_steps": 61300, "loss": 0.3377, "lr": 3.9202450754533e-09, "epoch": 9.949429037520392, "percentage": 99.49, "elapsed_time": "8:17:40", "remaining_time": "0:02:31", "throughput": 4407.27, "total_tokens": 131602032} {"current_steps": 60995, "total_steps": 61300, "loss": 0.3565, "lr": 3.79520862985594e-09, "epoch": 9.950244698205546, "percentage": 99.5, "elapsed_time": "8:17:42", "remaining_time": "0:02:29", "throughput": 4407.31, "total_tokens": 131613520} {"current_steps": 61000, "total_steps": 61300, "loss": 0.3222, "lr": 3.6721985034515738e-09, "epoch": 9.951060358890702, "percentage": 99.51, "elapsed_time": "8:17:44", "remaining_time": "0:02:26", "throughput": 4407.35, "total_tokens": 131624624} {"current_steps": 61005, "total_steps": 61300, "loss": 0.3131, "lr": 3.5512147062072287e-09, "epoch": 9.951876019575856, "percentage": 99.52, "elapsed_time": "8:17:46", "remaining_time": "0:02:24", "throughput": 4407.37, "total_tokens": 131634416} {"current_steps": 61010, "total_steps": 61300, "loss": 0.3527, "lr": 3.4322572479345005e-09, "epoch": 9.952691680261012, "percentage": 99.53, "elapsed_time": "8:17:49", "remaining_time": "0:02:21", "throughput": 4407.41, "total_tokens": 131645232} {"current_steps": 61015, "total_steps": 61300, "loss": 0.342, "lr": 3.3153261382729008e-09, "epoch": 9.953507340946166, "percentage": 99.54, "elapsed_time": "8:17:51", "remaining_time": "0:02:19", "throughput": 4407.44, "total_tokens": 131655824} {"current_steps": 61020, "total_steps": 61300, "loss": 0.3627, "lr": 3.2004213867009582e-09, "epoch": 9.954323001631321, "percentage": 99.54, "elapsed_time": "8:17:53", "remaining_time": "0:02:17", "throughput": 4407.47, "total_tokens": 131666640} {"current_steps": 61025, "total_steps": 61300, "loss": 0.3308, "lr": 3.0875430025362197e-09, "epoch": 9.955138662316477, "percentage": 99.55, "elapsed_time": "8:17:55", "remaining_time": "0:02:14", "throughput": 4407.49, "total_tokens": 131675120} {"current_steps": 61030, "total_steps": 61300, "loss": 0.3184, "lr": 2.9766909949296983e-09, "epoch": 9.955954323001631, "percentage": 99.56, "elapsed_time": "8:17:57", "remaining_time": "0:02:12", "throughput": 4407.52, "total_tokens": 131686096} {"current_steps": 61035, "total_steps": 61300, "loss": 0.3409, "lr": 2.8678653728658746e-09, "epoch": 9.956769983686787, "percentage": 99.57, "elapsed_time": "8:18:00", "remaining_time": "0:02:09", "throughput": 4407.55, "total_tokens": 131697968} {"current_steps": 61040, "total_steps": 61300, "loss": 0.3204, "lr": 2.761066145168245e-09, "epoch": 9.95758564437194, "percentage": 99.58, "elapsed_time": "8:18:02", "remaining_time": "0:02:07", "throughput": 4407.59, "total_tokens": 131709168} {"current_steps": 61045, "total_steps": 61300, "loss": 0.319, "lr": 2.656293320490999e-09, "epoch": 9.958401305057096, "percentage": 99.58, "elapsed_time": "8:18:04", "remaining_time": "0:02:04", "throughput": 4407.63, "total_tokens": 131720656} {"current_steps": 61050, "total_steps": 61300, "loss": 0.3238, "lr": 2.5535469073301176e-09, "epoch": 9.959216965742252, "percentage": 99.59, "elapsed_time": "8:18:06", "remaining_time": "0:02:02", "throughput": 4407.66, "total_tokens": 131731536} {"current_steps": 61055, "total_steps": 61300, "loss": 0.3384, "lr": 2.4528269140150497e-09, "epoch": 9.960032626427406, "percentage": 99.6, "elapsed_time": "8:18:09", "remaining_time": "0:01:59", "throughput": 4407.69, "total_tokens": 131742928} {"current_steps": 61060, "total_steps": 61300, "loss": 0.3519, "lr": 2.354133348711485e-09, "epoch": 9.960848287112562, "percentage": 99.61, "elapsed_time": "8:18:11", "remaining_time": "0:01:57", "throughput": 4407.73, "total_tokens": 131752496} {"current_steps": 61065, "total_steps": 61300, "loss": 0.3286, "lr": 2.2574662194158047e-09, "epoch": 9.961663947797716, "percentage": 99.62, "elapsed_time": "8:18:13", "remaining_time": "0:01:55", "throughput": 4407.77, "total_tokens": 131764048} {"current_steps": 61070, "total_steps": 61300, "loss": 0.3093, "lr": 2.1628255339689596e-09, "epoch": 9.962479608482871, "percentage": 99.62, "elapsed_time": "8:18:15", "remaining_time": "0:01:52", "throughput": 4407.8, "total_tokens": 131774352} {"current_steps": 61075, "total_steps": 61300, "loss": 0.3502, "lr": 2.0702113000425903e-09, "epoch": 9.963295269168025, "percentage": 99.63, "elapsed_time": "8:18:17", "remaining_time": "0:01:50", "throughput": 4407.83, "total_tokens": 131783696} {"current_steps": 61080, "total_steps": 61300, "loss": 0.3131, "lr": 1.979623525141805e-09, "epoch": 9.964110929853181, "percentage": 99.64, "elapsed_time": "8:18:20", "remaining_time": "0:01:47", "throughput": 4407.87, "total_tokens": 131795696} {"current_steps": 61085, "total_steps": 61300, "loss": 0.2873, "lr": 1.891062216610728e-09, "epoch": 9.964926590538337, "percentage": 99.65, "elapsed_time": "8:18:22", "remaining_time": "0:01:45", "throughput": 4407.9, "total_tokens": 131805616} {"current_steps": 61090, "total_steps": 61300, "loss": 0.3282, "lr": 1.804527381629728e-09, "epoch": 9.96574225122349, "percentage": 99.66, "elapsed_time": "8:18:24", "remaining_time": "0:01:42", "throughput": 4407.94, "total_tokens": 131815056} {"current_steps": 61095, "total_steps": 61300, "loss": 0.3088, "lr": 1.7200190272126382e-09, "epoch": 9.966557911908646, "percentage": 99.67, "elapsed_time": "8:18:26", "remaining_time": "0:01:40", "throughput": 4407.96, "total_tokens": 131825392} {"current_steps": 61100, "total_steps": 61300, "loss": 0.3168, "lr": 1.6375371602123103e-09, "epoch": 9.9673735725938, "percentage": 99.67, "elapsed_time": "8:18:28", "remaining_time": "0:01:37", "throughput": 4407.99, "total_tokens": 131836144} {"current_steps": 61105, "total_steps": 61300, "loss": 0.3154, "lr": 1.5570817873122868e-09, "epoch": 9.968189233278956, "percentage": 99.68, "elapsed_time": "8:18:30", "remaining_time": "0:01:35", "throughput": 4408.02, "total_tokens": 131846672} {"current_steps": 61110, "total_steps": 61300, "loss": 0.3097, "lr": 1.4786529150379036e-09, "epoch": 9.969004893964112, "percentage": 99.69, "elapsed_time": "8:18:33", "remaining_time": "0:01:33", "throughput": 4408.05, "total_tokens": 131858544} {"current_steps": 61115, "total_steps": 61300, "loss": 0.3226, "lr": 1.4022505497424122e-09, "epoch": 9.969820554649266, "percentage": 99.7, "elapsed_time": "8:18:35", "remaining_time": "0:01:30", "throughput": 4408.09, "total_tokens": 131869296} {"current_steps": 61120, "total_steps": 61300, "loss": 0.3459, "lr": 1.3278746976236322e-09, "epoch": 9.970636215334421, "percentage": 99.71, "elapsed_time": "8:18:37", "remaining_time": "0:01:28", "throughput": 4408.11, "total_tokens": 131879376} {"current_steps": 61125, "total_steps": 61300, "loss": 0.3565, "lr": 1.255525364710075e-09, "epoch": 9.971451876019575, "percentage": 99.71, "elapsed_time": "8:18:39", "remaining_time": "0:01:25", "throughput": 4408.15, "total_tokens": 131890768} {"current_steps": 61130, "total_steps": 61300, "loss": 0.3224, "lr": 1.1852025568637183e-09, "epoch": 9.97226753670473, "percentage": 99.72, "elapsed_time": "8:18:41", "remaining_time": "0:01:23", "throughput": 4408.18, "total_tokens": 131901104} {"current_steps": 61135, "total_steps": 61300, "loss": 0.3215, "lr": 1.116906279791108e-09, "epoch": 9.973083197389887, "percentage": 99.73, "elapsed_time": "8:18:44", "remaining_time": "0:01:20", "throughput": 4408.21, "total_tokens": 131912208} {"current_steps": 61140, "total_steps": 61300, "loss": 0.3178, "lr": 1.0506365390211547e-09, "epoch": 9.97389885807504, "percentage": 99.74, "elapsed_time": "8:18:46", "remaining_time": "0:01:18", "throughput": 4408.25, "total_tokens": 131923472} {"current_steps": 61145, "total_steps": 61300, "loss": 0.304, "lr": 9.863933399328895e-10, "epoch": 9.974714518760196, "percentage": 99.75, "elapsed_time": "8:18:48", "remaining_time": "0:01:15", "throughput": 4408.28, "total_tokens": 131934384} {"current_steps": 61150, "total_steps": 61300, "loss": 0.3266, "lr": 9.241766877304825e-10, "epoch": 9.97553017944535, "percentage": 99.76, "elapsed_time": "8:18:50", "remaining_time": "0:01:13", "throughput": 4408.31, "total_tokens": 131944784} {"current_steps": 61155, "total_steps": 61300, "loss": 0.3391, "lr": 8.639865874571218e-10, "epoch": 9.976345840130506, "percentage": 99.76, "elapsed_time": "8:18:53", "remaining_time": "0:01:10", "throughput": 4408.34, "total_tokens": 131955088} {"current_steps": 61160, "total_steps": 61300, "loss": 0.3717, "lr": 8.058230439950132e-10, "epoch": 9.977161500815662, "percentage": 99.77, "elapsed_time": "8:18:55", "remaining_time": "0:01:08", "throughput": 4408.38, "total_tokens": 131966384} {"current_steps": 61165, "total_steps": 61300, "loss": 0.2954, "lr": 7.496860620570534e-10, "epoch": 9.977977161500815, "percentage": 99.78, "elapsed_time": "8:18:57", "remaining_time": "0:01:06", "throughput": 4408.4, "total_tokens": 131977200} {"current_steps": 61170, "total_steps": 61300, "loss": 0.3088, "lr": 6.955756461951568e-10, "epoch": 9.978792822185971, "percentage": 99.79, "elapsed_time": "8:19:00", "remaining_time": "0:01:03", "throughput": 4408.44, "total_tokens": 131988848} {"current_steps": 61175, "total_steps": 61300, "loss": 0.3696, "lr": 6.434918007947044e-10, "epoch": 9.979608482871125, "percentage": 99.8, "elapsed_time": "8:19:02", "remaining_time": "0:01:01", "throughput": 4408.48, "total_tokens": 132000752} {"current_steps": 61180, "total_steps": 61300, "loss": 0.3262, "lr": 5.934345300773192e-10, "epoch": 9.98042414355628, "percentage": 99.8, "elapsed_time": "8:19:04", "remaining_time": "0:00:58", "throughput": 4408.51, "total_tokens": 132010544} {"current_steps": 61185, "total_steps": 61300, "loss": 0.3243, "lr": 5.454038381008664e-10, "epoch": 9.981239804241435, "percentage": 99.81, "elapsed_time": "8:19:06", "remaining_time": "0:00:56", "throughput": 4408.54, "total_tokens": 132021552} {"current_steps": 61190, "total_steps": 61300, "loss": 0.3213, "lr": 4.993997287622287e-10, "epoch": 9.98205546492659, "percentage": 99.82, "elapsed_time": "8:19:09", "remaining_time": "0:00:53", "throughput": 4408.58, "total_tokens": 132032752} {"current_steps": 61195, "total_steps": 61300, "loss": 0.331, "lr": 4.554222057889801e-10, "epoch": 9.982871125611746, "percentage": 99.83, "elapsed_time": "8:19:11", "remaining_time": "0:00:51", "throughput": 4408.61, "total_tokens": 132043536} {"current_steps": 61200, "total_steps": 61300, "loss": 0.313, "lr": 4.1347127274493635e-10, "epoch": 9.9836867862969, "percentage": 99.84, "elapsed_time": "8:19:13", "remaining_time": "0:00:48", "throughput": 4408.64, "total_tokens": 132053840} {"current_steps": 61205, "total_steps": 61300, "loss": 0.3401, "lr": 3.735469330301555e-10, "epoch": 9.984502446982056, "percentage": 99.85, "elapsed_time": "8:19:15", "remaining_time": "0:00:46", "throughput": 4408.67, "total_tokens": 132064400} {"current_steps": 61210, "total_steps": 61300, "loss": 0.314, "lr": 3.356491898837133e-10, "epoch": 9.98531810766721, "percentage": 99.85, "elapsed_time": "8:19:17", "remaining_time": "0:00:44", "throughput": 4408.7, "total_tokens": 132073552} {"current_steps": 61215, "total_steps": 61300, "loss": 0.3538, "lr": 2.997780463753763e-10, "epoch": 9.986133768352365, "percentage": 99.86, "elapsed_time": "8:19:19", "remaining_time": "0:00:41", "throughput": 4408.73, "total_tokens": 132084400} {"current_steps": 61220, "total_steps": 61300, "loss": 0.3605, "lr": 2.659335054139289e-10, "epoch": 9.986949429037521, "percentage": 99.87, "elapsed_time": "8:19:22", "remaining_time": "0:00:39", "throughput": 4408.77, "total_tokens": 132095856} {"current_steps": 61225, "total_steps": 61300, "loss": 0.3278, "lr": 2.341155697471731e-10, "epoch": 9.987765089722675, "percentage": 99.88, "elapsed_time": "8:19:24", "remaining_time": "0:00:36", "throughput": 4408.81, "total_tokens": 132108368} {"current_steps": 61230, "total_steps": 61300, "loss": 0.3195, "lr": 2.043242419452751e-10, "epoch": 9.98858075040783, "percentage": 99.89, "elapsed_time": "8:19:27", "remaining_time": "0:00:34", "throughput": 4408.85, "total_tokens": 132120432} {"current_steps": 61235, "total_steps": 61300, "loss": 0.3215, "lr": 1.7655952443129675e-10, "epoch": 9.989396411092985, "percentage": 99.89, "elapsed_time": "8:19:29", "remaining_time": "0:00:31", "throughput": 4408.88, "total_tokens": 132131568} {"current_steps": 61240, "total_steps": 61300, "loss": 0.3532, "lr": 1.5082141945343963e-10, "epoch": 9.99021207177814, "percentage": 99.9, "elapsed_time": "8:19:31", "remaining_time": "0:00:29", "throughput": 4408.92, "total_tokens": 132142992} {"current_steps": 61245, "total_steps": 61300, "loss": 0.3088, "lr": 1.2710992909892306e-10, "epoch": 9.991027732463294, "percentage": 99.91, "elapsed_time": "8:19:33", "remaining_time": "0:00:26", "throughput": 4408.95, "total_tokens": 132153520} {"current_steps": 61250, "total_steps": 61300, "loss": 0.3074, "lr": 1.0542505528565727e-10, "epoch": 9.99184339314845, "percentage": 99.92, "elapsed_time": "8:19:36", "remaining_time": "0:00:24", "throughput": 4408.98, "total_tokens": 132164368} {"current_steps": 61255, "total_steps": 61300, "loss": 0.3284, "lr": 8.57667997788969e-11, "epoch": 9.992659053833606, "percentage": 99.93, "elapsed_time": "8:19:38", "remaining_time": "0:00:22", "throughput": 4409.02, "total_tokens": 132174992} {"current_steps": 61260, "total_steps": 61300, "loss": 0.3376, "lr": 6.813516416626087e-11, "epoch": 9.99347471451876, "percentage": 99.93, "elapsed_time": "8:19:40", "remaining_time": "0:00:19", "throughput": 4409.05, "total_tokens": 132186320} {"current_steps": 61265, "total_steps": 61300, "loss": 0.3382, "lr": 5.2530149877161315e-11, "epoch": 9.994290375203915, "percentage": 99.94, "elapsed_time": "8:19:43", "remaining_time": "0:00:17", "throughput": 4409.08, "total_tokens": 132198000} {"current_steps": 61270, "total_steps": 61300, "loss": 0.343, "lr": 3.895175818002805e-11, "epoch": 9.99510603588907, "percentage": 99.95, "elapsed_time": "8:19:45", "remaining_time": "0:00:14", "throughput": 4409.12, "total_tokens": 132209840} {"current_steps": 61275, "total_steps": 61300, "loss": 0.3374, "lr": 2.7399990173981872e-11, "epoch": 9.995921696574225, "percentage": 99.96, "elapsed_time": "8:19:47", "remaining_time": "0:00:12", "throughput": 4409.15, "total_tokens": 132220848} {"current_steps": 61280, "total_steps": 61300, "loss": 0.3399, "lr": 1.7874846797161228e-11, "epoch": 9.99673735725938, "percentage": 99.97, "elapsed_time": "8:19:49", "remaining_time": "0:00:09", "throughput": 4409.18, "total_tokens": 132230384} {"current_steps": 61285, "total_steps": 61300, "loss": 0.3211, "lr": 1.0376328818395564e-11, "epoch": 9.997553017944535, "percentage": 99.98, "elapsed_time": "8:19:52", "remaining_time": "0:00:07", "throughput": 4409.21, "total_tokens": 132241200} {"current_steps": 61290, "total_steps": 61300, "loss": 0.3165, "lr": 4.90443684553199e-12, "epoch": 9.99836867862969, "percentage": 99.98, "elapsed_time": "8:19:54", "remaining_time": "0:00:04", "throughput": 4409.24, "total_tokens": 132251664} {"current_steps": 61295, "total_steps": 61300, "loss": 0.3514, "lr": 1.4591713254352712e-12, "epoch": 9.999184339314844, "percentage": 99.99, "elapsed_time": "8:19:56", "remaining_time": "0:00:02", "throughput": 4409.27, "total_tokens": 132262576} {"current_steps": 61300, "total_steps": 61300, "loss": 0.388, "lr": 4.053253843672167e-14, "epoch": 10.0, "percentage": 100.0, "elapsed_time": "8:19:58", "remaining_time": "0:00:00", "throughput": 4409.28, "total_tokens": 132272272} {"current_steps": 61300, "total_steps": 61300, "eval_loss": 0.33371150493621826, "epoch": 10.0, "percentage": 100.0, "elapsed_time": "8:22:09", "remaining_time": "0:00:00", "throughput": 4390.07, "total_tokens": 132272272} {"current_steps": 61300, "total_steps": 61300, "epoch": 10.0, "percentage": 100.0, "elapsed_time": "8:22:11", "remaining_time": "0:00:00", "throughput": 4389.88, "total_tokens": 132272272}