| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.9765625, | |
| "global_step": 6000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 1.0000000000000002e-06, | |
| "loss": 9.5302, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 2.0000000000000003e-06, | |
| "loss": 9.5978, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 3e-06, | |
| "loss": 9.6702, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 9.4757, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 5e-06, | |
| "loss": 9.4232, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 6e-06, | |
| "loss": 9.3929, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 7.000000000000001e-06, | |
| "loss": 9.0641, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 8.000000000000001e-06, | |
| "loss": 9.1413, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 9e-06, | |
| "loss": 8.7706, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 1e-05, | |
| "loss": 8.7685, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "eval_loss": 8.517706871032715, | |
| "eval_runtime": 138.145, | |
| "eval_samples_per_second": 203.648, | |
| "eval_steps_per_second": 6.37, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 1.1000000000000001e-05, | |
| "loss": 8.6076, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 1.2e-05, | |
| "loss": 8.5143, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 1.3000000000000001e-05, | |
| "loss": 8.4501, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 1.4000000000000001e-05, | |
| "loss": 8.3463, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 1.5e-05, | |
| "loss": 8.2408, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 1.6000000000000003e-05, | |
| "loss": 8.1665, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 1.7000000000000003e-05, | |
| "loss": 7.8703, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 1.8e-05, | |
| "loss": 7.8592, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 1.9e-05, | |
| "loss": 7.7984, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 2e-05, | |
| "loss": 7.7686, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "eval_loss": 7.766874313354492, | |
| "eval_runtime": 138.1211, | |
| "eval_samples_per_second": 203.684, | |
| "eval_steps_per_second": 6.371, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 2.1e-05, | |
| "loss": 7.8618, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 2.2000000000000003e-05, | |
| "loss": 7.6736, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 2.3000000000000003e-05, | |
| "loss": 7.6716, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 2.4e-05, | |
| "loss": 7.4289, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 2.5e-05, | |
| "loss": 7.3674, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 2.6000000000000002e-05, | |
| "loss": 7.2308, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 2.7000000000000002e-05, | |
| "loss": 7.0519, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 2.8000000000000003e-05, | |
| "loss": 6.8731, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 2.9e-05, | |
| "loss": 6.676, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 3e-05, | |
| "loss": 6.496, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "eval_loss": 5.7125983238220215, | |
| "eval_runtime": 138.1818, | |
| "eval_samples_per_second": 203.594, | |
| "eval_steps_per_second": 6.368, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 3.1e-05, | |
| "loss": 6.0497, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 3.2000000000000005e-05, | |
| "loss": 5.4927, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 3.3e-05, | |
| "loss": 5.0328, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 3.4000000000000007e-05, | |
| "loss": 4.5907, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 3.5e-05, | |
| "loss": 3.9888, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 3.6e-05, | |
| "loss": 3.4476, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 3.7e-05, | |
| "loss": 2.8771, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 3.8e-05, | |
| "loss": 2.3019, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 3.9000000000000006e-05, | |
| "loss": 1.7391, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 4e-05, | |
| "loss": 1.3205, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "eval_loss": 0.6095399260520935, | |
| "eval_runtime": 138.1438, | |
| "eval_samples_per_second": 203.65, | |
| "eval_steps_per_second": 6.37, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 4.1e-05, | |
| "loss": 0.9919, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 4.2e-05, | |
| "loss": 0.7867, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 4.3e-05, | |
| "loss": 0.6837, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 4.4000000000000006e-05, | |
| "loss": 0.6113, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 4.5e-05, | |
| "loss": 0.6006, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 4.600000000000001e-05, | |
| "loss": 0.5477, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 4.7e-05, | |
| "loss": 0.5483, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 4.8e-05, | |
| "loss": 0.5149, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 4.9e-05, | |
| "loss": 0.5213, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 5e-05, | |
| "loss": 0.5004, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "eval_loss": 0.4818989634513855, | |
| "eval_runtime": 138.1607, | |
| "eval_samples_per_second": 203.625, | |
| "eval_steps_per_second": 6.369, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 4.9911410347271445e-05, | |
| "loss": 0.5115, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 4.982282069454288e-05, | |
| "loss": 0.5135, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 4.973423104181432e-05, | |
| "loss": 0.4966, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 4.964564138908575e-05, | |
| "loss": 0.4864, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 4.9557051736357196e-05, | |
| "loss": 0.4763, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 4.946846208362864e-05, | |
| "loss": 0.5101, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 4.9379872430900075e-05, | |
| "loss": 0.4859, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 4.929128277817151e-05, | |
| "loss": 0.5046, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 4.920269312544295e-05, | |
| "loss": 0.475, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 4.911410347271439e-05, | |
| "loss": 0.4774, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "eval_loss": 0.45798131823539734, | |
| "eval_runtime": 138.1059, | |
| "eval_samples_per_second": 203.706, | |
| "eval_steps_per_second": 6.372, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 4.902551381998583e-05, | |
| "loss": 0.4966, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 4.893692416725726e-05, | |
| "loss": 0.4836, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 4.8848334514528704e-05, | |
| "loss": 0.4713, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 4.875974486180015e-05, | |
| "loss": 0.4489, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 4.867115520907158e-05, | |
| "loss": 0.4846, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 4.8582565556343026e-05, | |
| "loss": 0.465, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 4.8493975903614455e-05, | |
| "loss": 0.4256, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 4.84053862508859e-05, | |
| "loss": 0.4559, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 4.831679659815734e-05, | |
| "loss": 0.4599, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 4.822820694542878e-05, | |
| "loss": 0.4545, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "eval_loss": 0.4460126459598541, | |
| "eval_runtime": 138.1094, | |
| "eval_samples_per_second": 203.701, | |
| "eval_steps_per_second": 6.372, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 4.813961729270022e-05, | |
| "loss": 0.459, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 4.805102763997165e-05, | |
| "loss": 0.4604, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 4.796243798724309e-05, | |
| "loss": 0.4259, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 4.7873848334514534e-05, | |
| "loss": 0.4564, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 4.778525868178597e-05, | |
| "loss": 0.434, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 4.7696669029057406e-05, | |
| "loss": 0.429, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 4.760807937632884e-05, | |
| "loss": 0.4524, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 4.7519489723600285e-05, | |
| "loss": 0.4491, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 4.743090007087173e-05, | |
| "loss": 0.4377, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 4.7342310418143164e-05, | |
| "loss": 0.4395, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "eval_loss": 0.43905675411224365, | |
| "eval_runtime": 138.1109, | |
| "eval_samples_per_second": 203.699, | |
| "eval_steps_per_second": 6.372, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 4.72537207654146e-05, | |
| "loss": 0.4382, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 4.716513111268604e-05, | |
| "loss": 0.4452, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 4.707654145995748e-05, | |
| "loss": 0.4266, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 4.698795180722892e-05, | |
| "loss": 0.4595, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 4.689936215450036e-05, | |
| "loss": 0.4168, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 4.6810772501771794e-05, | |
| "loss": 0.4291, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 4.6722182849043236e-05, | |
| "loss": 0.4807, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 4.663359319631467e-05, | |
| "loss": 0.4171, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 4.6545003543586115e-05, | |
| "loss": 0.4447, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 4.6456413890857544e-05, | |
| "loss": 0.4277, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "eval_loss": 0.43294572830200195, | |
| "eval_runtime": 138.1242, | |
| "eval_samples_per_second": 203.679, | |
| "eval_steps_per_second": 6.371, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 4.636782423812899e-05, | |
| "loss": 0.4357, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 4.627923458540043e-05, | |
| "loss": 0.4469, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 4.6190644932671866e-05, | |
| "loss": 0.4047, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 4.610205527994331e-05, | |
| "loss": 0.4343, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 4.601346562721474e-05, | |
| "loss": 0.4256, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 4.592487597448618e-05, | |
| "loss": 0.4331, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 4.5836286321757624e-05, | |
| "loss": 0.4525, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 4.574769666902906e-05, | |
| "loss": 0.411, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 4.56591070163005e-05, | |
| "loss": 0.4485, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 4.557051736357194e-05, | |
| "loss": 0.4114, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "eval_loss": 0.4274757206439972, | |
| "eval_runtime": 138.0935, | |
| "eval_samples_per_second": 203.724, | |
| "eval_steps_per_second": 6.372, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 4.5481927710843374e-05, | |
| "loss": 0.4273, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 4.539333805811482e-05, | |
| "loss": 0.4555, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 4.530474840538625e-05, | |
| "loss": 0.4108, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 4.521615875265769e-05, | |
| "loss": 0.4002, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 4.512756909992913e-05, | |
| "loss": 0.4244, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 4.503897944720057e-05, | |
| "loss": 0.4337, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 4.495038979447201e-05, | |
| "loss": 0.3895, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 4.486180014174345e-05, | |
| "loss": 0.4, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 4.477321048901488e-05, | |
| "loss": 0.4197, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 4.4684620836286326e-05, | |
| "loss": 0.4048, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "eval_loss": 0.4227732717990875, | |
| "eval_runtime": 138.0996, | |
| "eval_samples_per_second": 203.715, | |
| "eval_steps_per_second": 6.372, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 4.459603118355776e-05, | |
| "loss": 0.4341, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 4.4507441530829204e-05, | |
| "loss": 0.4447, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 4.441885187810064e-05, | |
| "loss": 0.4316, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 4.4330262225372076e-05, | |
| "loss": 0.4324, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 4.424167257264352e-05, | |
| "loss": 0.4169, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 4.4153082919914955e-05, | |
| "loss": 0.4061, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 4.40644932671864e-05, | |
| "loss": 0.3898, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 4.3975903614457834e-05, | |
| "loss": 0.4044, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 4.388731396172927e-05, | |
| "loss": 0.4002, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 4.379872430900071e-05, | |
| "loss": 0.4012, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "eval_loss": 0.41991087794303894, | |
| "eval_runtime": 138.1063, | |
| "eval_samples_per_second": 203.705, | |
| "eval_steps_per_second": 6.372, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 4.371013465627215e-05, | |
| "loss": 0.4263, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 4.362154500354359e-05, | |
| "loss": 0.4256, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 4.353295535081503e-05, | |
| "loss": 0.4282, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 4.3444365698086464e-05, | |
| "loss": 0.4265, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 4.3355776045357906e-05, | |
| "loss": 0.4326, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 4.326718639262934e-05, | |
| "loss": 0.4188, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 4.3178596739900785e-05, | |
| "loss": 0.3904, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 4.309000708717222e-05, | |
| "loss": 0.3901, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 4.300141743444366e-05, | |
| "loss": 0.3984, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 4.29128277817151e-05, | |
| "loss": 0.4071, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "eval_loss": 0.4168910086154938, | |
| "eval_runtime": 138.0833, | |
| "eval_samples_per_second": 203.739, | |
| "eval_steps_per_second": 6.373, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 4.2824238128986536e-05, | |
| "loss": 0.3994, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 4.273564847625798e-05, | |
| "loss": 0.4146, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 4.2647058823529415e-05, | |
| "loss": 0.4319, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 4.255846917080085e-05, | |
| "loss": 0.4141, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 4.2469879518072294e-05, | |
| "loss": 0.4355, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 4.238128986534373e-05, | |
| "loss": 0.4084, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 4.2292700212615166e-05, | |
| "loss": 0.4016, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 4.220411055988661e-05, | |
| "loss": 0.4154, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 4.2115520907158044e-05, | |
| "loss": 0.4022, | |
| "step": 1390 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 4.202693125442949e-05, | |
| "loss": 0.4143, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "eval_loss": 0.41502994298934937, | |
| "eval_runtime": 138.0512, | |
| "eval_samples_per_second": 203.787, | |
| "eval_steps_per_second": 6.374, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 4.193834160170092e-05, | |
| "loss": 0.4101, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 4.184975194897236e-05, | |
| "loss": 0.4162, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 4.17611622962438e-05, | |
| "loss": 0.4304, | |
| "step": 1430 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 4.167257264351524e-05, | |
| "loss": 0.4037, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 4.158398299078668e-05, | |
| "loss": 0.3952, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 4.149539333805812e-05, | |
| "loss": 0.4238, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 4.140680368532955e-05, | |
| "loss": 0.4158, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 4.1318214032600996e-05, | |
| "loss": 0.4139, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 4.122962437987243e-05, | |
| "loss": 0.4069, | |
| "step": 1490 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 4.1141034727143874e-05, | |
| "loss": 0.4028, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "eval_loss": 0.4133906662464142, | |
| "eval_runtime": 138.1272, | |
| "eval_samples_per_second": 203.675, | |
| "eval_steps_per_second": 6.371, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 4.105244507441531e-05, | |
| "loss": 0.4127, | |
| "step": 1510 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 4.0963855421686746e-05, | |
| "loss": 0.3997, | |
| "step": 1520 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 4.087526576895819e-05, | |
| "loss": 0.4113, | |
| "step": 1530 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 4.0786676116229625e-05, | |
| "loss": 0.4004, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 4.069808646350107e-05, | |
| "loss": 0.405, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 4.0609496810772504e-05, | |
| "loss": 0.3972, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 4.052090715804394e-05, | |
| "loss": 0.3986, | |
| "step": 1570 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 4.043231750531538e-05, | |
| "loss": 0.3942, | |
| "step": 1580 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 4.034372785258682e-05, | |
| "loss": 0.4, | |
| "step": 1590 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 4.025513819985826e-05, | |
| "loss": 0.4257, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "eval_loss": 0.41290345788002014, | |
| "eval_runtime": 138.0689, | |
| "eval_samples_per_second": 203.761, | |
| "eval_steps_per_second": 6.374, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 4.01665485471297e-05, | |
| "loss": 0.3852, | |
| "step": 1610 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 4.0077958894401134e-05, | |
| "loss": 0.4232, | |
| "step": 1620 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 3.9989369241672576e-05, | |
| "loss": 0.4041, | |
| "step": 1630 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 3.990077958894401e-05, | |
| "loss": 0.3955, | |
| "step": 1640 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 3.981218993621545e-05, | |
| "loss": 0.4095, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 3.972360028348689e-05, | |
| "loss": 0.3863, | |
| "step": 1660 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 3.963501063075833e-05, | |
| "loss": 0.4058, | |
| "step": 1670 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 3.954642097802977e-05, | |
| "loss": 0.4147, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 3.9457831325301206e-05, | |
| "loss": 0.3819, | |
| "step": 1690 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 3.936924167257264e-05, | |
| "loss": 0.3786, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "eval_loss": 0.4112655222415924, | |
| "eval_runtime": 138.0649, | |
| "eval_samples_per_second": 203.766, | |
| "eval_steps_per_second": 6.374, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 3.9280652019844085e-05, | |
| "loss": 0.3672, | |
| "step": 1710 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 3.919206236711552e-05, | |
| "loss": 0.3881, | |
| "step": 1720 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 3.9103472714386964e-05, | |
| "loss": 0.3904, | |
| "step": 1730 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 3.90148830616584e-05, | |
| "loss": 0.4021, | |
| "step": 1740 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 3.8926293408929836e-05, | |
| "loss": 0.385, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 3.883770375620128e-05, | |
| "loss": 0.4194, | |
| "step": 1760 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 3.8749114103472714e-05, | |
| "loss": 0.4043, | |
| "step": 1770 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 3.866052445074416e-05, | |
| "loss": 0.391, | |
| "step": 1780 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 3.857193479801559e-05, | |
| "loss": 0.3976, | |
| "step": 1790 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 3.848334514528703e-05, | |
| "loss": 0.4006, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "eval_loss": 0.40891483426094055, | |
| "eval_runtime": 138.0756, | |
| "eval_samples_per_second": 203.751, | |
| "eval_steps_per_second": 6.373, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 3.839475549255847e-05, | |
| "loss": 0.3823, | |
| "step": 1810 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 3.830616583982991e-05, | |
| "loss": 0.3779, | |
| "step": 1820 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 3.821757618710135e-05, | |
| "loss": 0.447, | |
| "step": 1830 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 3.812898653437279e-05, | |
| "loss": 0.387, | |
| "step": 1840 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 3.804039688164422e-05, | |
| "loss": 0.3958, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 3.7951807228915666e-05, | |
| "loss": 0.3903, | |
| "step": 1860 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 3.78632175761871e-05, | |
| "loss": 0.4026, | |
| "step": 1870 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 3.7774627923458544e-05, | |
| "loss": 0.4113, | |
| "step": 1880 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 3.768603827072998e-05, | |
| "loss": 0.3806, | |
| "step": 1890 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 3.7597448618001416e-05, | |
| "loss": 0.4016, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "eval_loss": 0.40891408920288086, | |
| "eval_runtime": 138.1603, | |
| "eval_samples_per_second": 203.626, | |
| "eval_steps_per_second": 6.369, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 3.750885896527286e-05, | |
| "loss": 0.399, | |
| "step": 1910 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 3.7420269312544295e-05, | |
| "loss": 0.4028, | |
| "step": 1920 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 3.733167965981573e-05, | |
| "loss": 0.4029, | |
| "step": 1930 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 3.7243090007087174e-05, | |
| "loss": 0.4031, | |
| "step": 1940 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 3.715450035435861e-05, | |
| "loss": 0.3945, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 3.706591070163005e-05, | |
| "loss": 0.3965, | |
| "step": 1960 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 3.697732104890149e-05, | |
| "loss": 0.3928, | |
| "step": 1970 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 3.6888731396172925e-05, | |
| "loss": 0.3866, | |
| "step": 1980 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 3.680014174344437e-05, | |
| "loss": 0.3722, | |
| "step": 1990 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 3.6711552090715804e-05, | |
| "loss": 0.3963, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "eval_loss": 0.40644311904907227, | |
| "eval_runtime": 138.3589, | |
| "eval_samples_per_second": 203.334, | |
| "eval_steps_per_second": 6.36, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 3.6622962437987246e-05, | |
| "loss": 0.3999, | |
| "step": 2010 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 3.653437278525869e-05, | |
| "loss": 0.3749, | |
| "step": 2020 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 3.644578313253012e-05, | |
| "loss": 0.4157, | |
| "step": 2030 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 3.635719347980156e-05, | |
| "loss": 0.4045, | |
| "step": 2040 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 3.6268603827073e-05, | |
| "loss": 0.4307, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 3.618001417434444e-05, | |
| "loss": 0.392, | |
| "step": 2060 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 3.609142452161588e-05, | |
| "loss": 0.4116, | |
| "step": 2070 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 3.600283486888731e-05, | |
| "loss": 0.4095, | |
| "step": 2080 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 3.5914245216158755e-05, | |
| "loss": 0.4091, | |
| "step": 2090 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 3.582565556343019e-05, | |
| "loss": 0.3591, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "eval_loss": 0.4051670730113983, | |
| "eval_runtime": 138.2882, | |
| "eval_samples_per_second": 203.437, | |
| "eval_steps_per_second": 6.364, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 3.5737065910701634e-05, | |
| "loss": 0.4117, | |
| "step": 2110 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 3.564847625797307e-05, | |
| "loss": 0.387, | |
| "step": 2120 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 3.5559886605244506e-05, | |
| "loss": 0.4078, | |
| "step": 2130 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 3.547129695251595e-05, | |
| "loss": 0.3885, | |
| "step": 2140 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 3.5382707299787384e-05, | |
| "loss": 0.3947, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 3.529411764705883e-05, | |
| "loss": 0.3855, | |
| "step": 2160 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 3.520552799433026e-05, | |
| "loss": 0.4188, | |
| "step": 2170 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 3.51169383416017e-05, | |
| "loss": 0.3786, | |
| "step": 2180 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 3.502834868887314e-05, | |
| "loss": 0.3861, | |
| "step": 2190 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 3.4939759036144585e-05, | |
| "loss": 0.3995, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "eval_loss": 0.40360766649246216, | |
| "eval_runtime": 138.2299, | |
| "eval_samples_per_second": 203.523, | |
| "eval_steps_per_second": 6.366, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 3.485116938341602e-05, | |
| "loss": 0.3947, | |
| "step": 2210 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 3.476257973068746e-05, | |
| "loss": 0.3798, | |
| "step": 2220 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 3.467399007795889e-05, | |
| "loss": 0.3783, | |
| "step": 2230 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 3.4585400425230336e-05, | |
| "loss": 0.3756, | |
| "step": 2240 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 3.449681077250178e-05, | |
| "loss": 0.4065, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 3.440822111977321e-05, | |
| "loss": 0.3917, | |
| "step": 2260 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 3.431963146704465e-05, | |
| "loss": 0.3934, | |
| "step": 2270 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 3.4231041814316086e-05, | |
| "loss": 0.3628, | |
| "step": 2280 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 3.414245216158753e-05, | |
| "loss": 0.3838, | |
| "step": 2290 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 3.405386250885897e-05, | |
| "loss": 0.3773, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "eval_loss": 0.40338262915611267, | |
| "eval_runtime": 138.1211, | |
| "eval_samples_per_second": 203.684, | |
| "eval_steps_per_second": 6.371, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 3.39652728561304e-05, | |
| "loss": 0.3693, | |
| "step": 2310 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 3.3876683203401844e-05, | |
| "loss": 0.4011, | |
| "step": 2320 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 3.378809355067328e-05, | |
| "loss": 0.3992, | |
| "step": 2330 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 3.369950389794472e-05, | |
| "loss": 0.3754, | |
| "step": 2340 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 3.3610914245216166e-05, | |
| "loss": 0.3694, | |
| "step": 2350 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 3.3522324592487595e-05, | |
| "loss": 0.3937, | |
| "step": 2360 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 3.343373493975904e-05, | |
| "loss": 0.377, | |
| "step": 2370 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 3.3345145287030474e-05, | |
| "loss": 0.3939, | |
| "step": 2380 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 3.3256555634301916e-05, | |
| "loss": 0.3998, | |
| "step": 2390 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 3.316796598157335e-05, | |
| "loss": 0.3758, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "eval_loss": 0.40262076258659363, | |
| "eval_runtime": 138.1252, | |
| "eval_samples_per_second": 203.678, | |
| "eval_steps_per_second": 6.371, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 3.307937632884479e-05, | |
| "loss": 0.3703, | |
| "step": 2410 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 3.299078667611623e-05, | |
| "loss": 0.391, | |
| "step": 2420 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 3.2902197023387674e-05, | |
| "loss": 0.3804, | |
| "step": 2430 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 3.281360737065911e-05, | |
| "loss": 0.3909, | |
| "step": 2440 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 3.2725017717930546e-05, | |
| "loss": 0.3904, | |
| "step": 2450 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 3.263642806520198e-05, | |
| "loss": 0.3892, | |
| "step": 2460 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 3.2547838412473425e-05, | |
| "loss": 0.3925, | |
| "step": 2470 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 3.245924875974487e-05, | |
| "loss": 0.3827, | |
| "step": 2480 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 3.2370659107016304e-05, | |
| "loss": 0.3816, | |
| "step": 2490 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 3.228206945428774e-05, | |
| "loss": 0.3751, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "eval_loss": 0.4022020995616913, | |
| "eval_runtime": 138.0981, | |
| "eval_samples_per_second": 203.718, | |
| "eval_steps_per_second": 6.372, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 3.2193479801559176e-05, | |
| "loss": 0.3725, | |
| "step": 2510 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 3.210489014883062e-05, | |
| "loss": 0.3864, | |
| "step": 2520 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 3.201630049610206e-05, | |
| "loss": 0.3553, | |
| "step": 2530 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 3.192771084337349e-05, | |
| "loss": 0.357, | |
| "step": 2540 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 3.183912119064493e-05, | |
| "loss": 0.4031, | |
| "step": 2550 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 3.175053153791637e-05, | |
| "loss": 0.3691, | |
| "step": 2560 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 3.166194188518781e-05, | |
| "loss": 0.4035, | |
| "step": 2570 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 3.1573352232459255e-05, | |
| "loss": 0.3978, | |
| "step": 2580 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 3.1484762579730684e-05, | |
| "loss": 0.3844, | |
| "step": 2590 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 3.139617292700213e-05, | |
| "loss": 0.3833, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "eval_loss": 0.39937448501586914, | |
| "eval_runtime": 138.8709, | |
| "eval_samples_per_second": 202.584, | |
| "eval_steps_per_second": 6.337, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 3.130758327427357e-05, | |
| "loss": 0.3883, | |
| "step": 2610 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 3.1218993621545006e-05, | |
| "loss": 0.3797, | |
| "step": 2620 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 3.113040396881645e-05, | |
| "loss": 0.3992, | |
| "step": 2630 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 3.104181431608788e-05, | |
| "loss": 0.3818, | |
| "step": 2640 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 3.095322466335932e-05, | |
| "loss": 0.3872, | |
| "step": 2650 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 3.086463501063076e-05, | |
| "loss": 0.4047, | |
| "step": 2660 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 3.07760453579022e-05, | |
| "loss": 0.4149, | |
| "step": 2670 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 3.0687455705173635e-05, | |
| "loss": 0.3741, | |
| "step": 2680 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 3.059886605244507e-05, | |
| "loss": 0.3898, | |
| "step": 2690 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 3.0510276399716514e-05, | |
| "loss": 0.381, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "eval_loss": 0.39839911460876465, | |
| "eval_runtime": 138.3419, | |
| "eval_samples_per_second": 203.359, | |
| "eval_steps_per_second": 6.361, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 3.0421686746987953e-05, | |
| "loss": 0.3634, | |
| "step": 2710 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 3.0333097094259393e-05, | |
| "loss": 0.3783, | |
| "step": 2720 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 3.024450744153083e-05, | |
| "loss": 0.3854, | |
| "step": 2730 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 3.0155917788802268e-05, | |
| "loss": 0.3931, | |
| "step": 2740 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 3.0067328136073708e-05, | |
| "loss": 0.371, | |
| "step": 2750 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 2.9978738483345147e-05, | |
| "loss": 0.4089, | |
| "step": 2760 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 2.9890148830616586e-05, | |
| "loss": 0.3854, | |
| "step": 2770 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 2.9801559177888022e-05, | |
| "loss": 0.3921, | |
| "step": 2780 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 2.9712969525159462e-05, | |
| "loss": 0.3753, | |
| "step": 2790 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 2.96243798724309e-05, | |
| "loss": 0.377, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "eval_loss": 0.3989295959472656, | |
| "eval_runtime": 138.1703, | |
| "eval_samples_per_second": 203.611, | |
| "eval_steps_per_second": 6.369, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 2.953579021970234e-05, | |
| "loss": 0.4242, | |
| "step": 2810 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 2.944720056697378e-05, | |
| "loss": 0.3857, | |
| "step": 2820 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 2.9358610914245216e-05, | |
| "loss": 0.3678, | |
| "step": 2830 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 2.9270021261516655e-05, | |
| "loss": 0.3798, | |
| "step": 2840 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 2.9181431608788095e-05, | |
| "loss": 0.3798, | |
| "step": 2850 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 2.9092841956059534e-05, | |
| "loss": 0.3932, | |
| "step": 2860 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 2.900425230333097e-05, | |
| "loss": 0.3635, | |
| "step": 2870 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 2.891566265060241e-05, | |
| "loss": 0.3933, | |
| "step": 2880 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 2.882707299787385e-05, | |
| "loss": 0.3749, | |
| "step": 2890 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 2.873848334514529e-05, | |
| "loss": 0.3974, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "eval_loss": 0.3973732888698578, | |
| "eval_runtime": 138.1232, | |
| "eval_samples_per_second": 203.681, | |
| "eval_steps_per_second": 6.371, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 2.8649893692416728e-05, | |
| "loss": 0.3573, | |
| "step": 2910 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 2.8561304039688164e-05, | |
| "loss": 0.3608, | |
| "step": 2920 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 2.8472714386959603e-05, | |
| "loss": 0.373, | |
| "step": 2930 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 2.8384124734231043e-05, | |
| "loss": 0.357, | |
| "step": 2940 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 2.8295535081502482e-05, | |
| "loss": 0.3894, | |
| "step": 2950 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 2.8206945428773925e-05, | |
| "loss": 0.3674, | |
| "step": 2960 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 2.8118355776045357e-05, | |
| "loss": 0.3855, | |
| "step": 2970 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 2.8029766123316797e-05, | |
| "loss": 0.3838, | |
| "step": 2980 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 2.7941176470588236e-05, | |
| "loss": 0.3675, | |
| "step": 2990 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 2.7852586817859676e-05, | |
| "loss": 0.3687, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "eval_loss": 0.3975074291229248, | |
| "eval_runtime": 138.0969, | |
| "eval_samples_per_second": 203.719, | |
| "eval_steps_per_second": 6.372, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 2.776399716513111e-05, | |
| "loss": 0.3982, | |
| "step": 3010 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 2.767540751240255e-05, | |
| "loss": 0.3792, | |
| "step": 3020 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 2.758681785967399e-05, | |
| "loss": 0.3771, | |
| "step": 3030 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 2.749822820694543e-05, | |
| "loss": 0.3795, | |
| "step": 3040 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 2.7409638554216873e-05, | |
| "loss": 0.3865, | |
| "step": 3050 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 2.7321048901488305e-05, | |
| "loss": 0.3795, | |
| "step": 3060 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 2.7232459248759745e-05, | |
| "loss": 0.3694, | |
| "step": 3070 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 2.7143869596031184e-05, | |
| "loss": 0.3661, | |
| "step": 3080 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 2.7055279943302623e-05, | |
| "loss": 0.3678, | |
| "step": 3090 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 2.6966690290574066e-05, | |
| "loss": 0.3817, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "eval_loss": 0.39725953340530396, | |
| "eval_runtime": 138.119, | |
| "eval_samples_per_second": 203.687, | |
| "eval_steps_per_second": 6.371, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 2.68781006378455e-05, | |
| "loss": 0.3815, | |
| "step": 3110 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 2.6789510985116938e-05, | |
| "loss": 0.3784, | |
| "step": 3120 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 2.6700921332388378e-05, | |
| "loss": 0.3681, | |
| "step": 3130 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 2.661233167965982e-05, | |
| "loss": 0.4035, | |
| "step": 3140 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 2.6523742026931253e-05, | |
| "loss": 0.3744, | |
| "step": 3150 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 2.6435152374202692e-05, | |
| "loss": 0.3783, | |
| "step": 3160 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 2.6346562721474132e-05, | |
| "loss": 0.404, | |
| "step": 3170 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 2.625797306874557e-05, | |
| "loss": 0.3678, | |
| "step": 3180 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 2.6169383416017014e-05, | |
| "loss": 0.3958, | |
| "step": 3190 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 2.6080793763288447e-05, | |
| "loss": 0.3771, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "eval_loss": 0.39562681317329407, | |
| "eval_runtime": 138.1817, | |
| "eval_samples_per_second": 203.594, | |
| "eval_steps_per_second": 6.368, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 2.5992204110559886e-05, | |
| "loss": 0.3917, | |
| "step": 3210 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 2.5903614457831325e-05, | |
| "loss": 0.3648, | |
| "step": 3220 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 2.5815024805102768e-05, | |
| "loss": 0.3944, | |
| "step": 3230 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 2.5726435152374208e-05, | |
| "loss": 0.3715, | |
| "step": 3240 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 2.563784549964564e-05, | |
| "loss": 0.3784, | |
| "step": 3250 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 2.554925584691708e-05, | |
| "loss": 0.3666, | |
| "step": 3260 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 2.546066619418852e-05, | |
| "loss": 0.3876, | |
| "step": 3270 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 2.5372076541459962e-05, | |
| "loss": 0.395, | |
| "step": 3280 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 2.5283486888731394e-05, | |
| "loss": 0.3936, | |
| "step": 3290 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 2.5194897236002834e-05, | |
| "loss": 0.3756, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "eval_loss": 0.39499565958976746, | |
| "eval_runtime": 138.1729, | |
| "eval_samples_per_second": 203.607, | |
| "eval_steps_per_second": 6.369, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 2.5106307583274273e-05, | |
| "loss": 0.3641, | |
| "step": 3310 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 2.5017717930545713e-05, | |
| "loss": 0.3718, | |
| "step": 3320 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 2.4929128277817152e-05, | |
| "loss": 0.3719, | |
| "step": 3330 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 2.484053862508859e-05, | |
| "loss": 0.3883, | |
| "step": 3340 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 2.4751948972360027e-05, | |
| "loss": 0.3869, | |
| "step": 3350 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 2.4663359319631467e-05, | |
| "loss": 0.3566, | |
| "step": 3360 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 2.457476966690291e-05, | |
| "loss": 0.3876, | |
| "step": 3370 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 2.4486180014174346e-05, | |
| "loss": 0.3719, | |
| "step": 3380 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 2.4397590361445785e-05, | |
| "loss": 0.3655, | |
| "step": 3390 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 2.430900070871722e-05, | |
| "loss": 0.3809, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "eval_loss": 0.39441797137260437, | |
| "eval_runtime": 138.0968, | |
| "eval_samples_per_second": 203.719, | |
| "eval_steps_per_second": 6.372, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 2.422041105598866e-05, | |
| "loss": 0.3613, | |
| "step": 3410 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 2.41318214032601e-05, | |
| "loss": 0.389, | |
| "step": 3420 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 2.404323175053154e-05, | |
| "loss": 0.3595, | |
| "step": 3430 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 2.395464209780298e-05, | |
| "loss": 0.3718, | |
| "step": 3440 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 2.3866052445074415e-05, | |
| "loss": 0.3757, | |
| "step": 3450 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 2.3777462792345857e-05, | |
| "loss": 0.3724, | |
| "step": 3460 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 2.3688873139617293e-05, | |
| "loss": 0.3796, | |
| "step": 3470 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 2.3600283486888733e-05, | |
| "loss": 0.3801, | |
| "step": 3480 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 2.351169383416017e-05, | |
| "loss": 0.3712, | |
| "step": 3490 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 2.3423104181431608e-05, | |
| "loss": 0.3941, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "eval_loss": 0.3938775360584259, | |
| "eval_runtime": 138.1358, | |
| "eval_samples_per_second": 203.662, | |
| "eval_steps_per_second": 6.371, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 2.333451452870305e-05, | |
| "loss": 0.3727, | |
| "step": 3510 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 2.3245924875974487e-05, | |
| "loss": 0.3784, | |
| "step": 3520 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 2.3157335223245926e-05, | |
| "loss": 0.379, | |
| "step": 3530 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 2.3068745570517362e-05, | |
| "loss": 0.3657, | |
| "step": 3540 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 2.2980155917788805e-05, | |
| "loss": 0.3863, | |
| "step": 3550 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 2.289156626506024e-05, | |
| "loss": 0.3848, | |
| "step": 3560 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 2.280297661233168e-05, | |
| "loss": 0.3764, | |
| "step": 3570 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 2.271438695960312e-05, | |
| "loss": 0.3739, | |
| "step": 3580 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 2.2625797306874556e-05, | |
| "loss": 0.3836, | |
| "step": 3590 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 2.2537207654146e-05, | |
| "loss": 0.3751, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "eval_loss": 0.3936668634414673, | |
| "eval_runtime": 138.1758, | |
| "eval_samples_per_second": 203.603, | |
| "eval_steps_per_second": 6.369, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 2.2448618001417435e-05, | |
| "loss": 0.3827, | |
| "step": 3610 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 2.2360028348688874e-05, | |
| "loss": 0.3943, | |
| "step": 3620 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 2.227143869596031e-05, | |
| "loss": 0.3678, | |
| "step": 3630 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 2.2182849043231753e-05, | |
| "loss": 0.3613, | |
| "step": 3640 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 2.2094259390503192e-05, | |
| "loss": 0.3802, | |
| "step": 3650 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 2.200566973777463e-05, | |
| "loss": 0.3937, | |
| "step": 3660 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 2.1917080085046068e-05, | |
| "loss": 0.3737, | |
| "step": 3670 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 2.1828490432317504e-05, | |
| "loss": 0.3755, | |
| "step": 3680 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 2.1739900779588947e-05, | |
| "loss": 0.3602, | |
| "step": 3690 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 2.1651311126860383e-05, | |
| "loss": 0.3771, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "eval_loss": 0.39319226145744324, | |
| "eval_runtime": 138.1244, | |
| "eval_samples_per_second": 203.679, | |
| "eval_steps_per_second": 6.371, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 2.1562721474131822e-05, | |
| "loss": 0.3838, | |
| "step": 3710 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 2.147413182140326e-05, | |
| "loss": 0.3674, | |
| "step": 3720 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 2.13855421686747e-05, | |
| "loss": 0.3547, | |
| "step": 3730 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 2.129695251594614e-05, | |
| "loss": 0.3734, | |
| "step": 3740 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 2.1208362863217576e-05, | |
| "loss": 0.3758, | |
| "step": 3750 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 2.1119773210489016e-05, | |
| "loss": 0.3705, | |
| "step": 3760 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 2.103118355776045e-05, | |
| "loss": 0.3827, | |
| "step": 3770 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 2.0942593905031894e-05, | |
| "loss": 0.375, | |
| "step": 3780 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 2.0854004252303334e-05, | |
| "loss": 0.3836, | |
| "step": 3790 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 2.076541459957477e-05, | |
| "loss": 0.3624, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "eval_loss": 0.3926844894886017, | |
| "eval_runtime": 138.1212, | |
| "eval_samples_per_second": 203.683, | |
| "eval_steps_per_second": 6.371, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 2.067682494684621e-05, | |
| "loss": 0.394, | |
| "step": 3810 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 2.058823529411765e-05, | |
| "loss": 0.3529, | |
| "step": 3820 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 2.0499645641389088e-05, | |
| "loss": 0.3796, | |
| "step": 3830 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 2.0411055988660524e-05, | |
| "loss": 0.3557, | |
| "step": 3840 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 2.0322466335931963e-05, | |
| "loss": 0.3607, | |
| "step": 3850 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 2.0233876683203403e-05, | |
| "loss": 0.3765, | |
| "step": 3860 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 2.0145287030474842e-05, | |
| "loss": 0.3682, | |
| "step": 3870 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 2.005669737774628e-05, | |
| "loss": 0.3771, | |
| "step": 3880 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 1.9968107725017718e-05, | |
| "loss": 0.3793, | |
| "step": 3890 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 1.9879518072289157e-05, | |
| "loss": 0.3504, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "eval_loss": 0.3924194574356079, | |
| "eval_runtime": 138.059, | |
| "eval_samples_per_second": 203.775, | |
| "eval_steps_per_second": 6.374, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 1.9790928419560596e-05, | |
| "loss": 0.3469, | |
| "step": 3910 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 1.9702338766832036e-05, | |
| "loss": 0.3801, | |
| "step": 3920 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 1.9613749114103475e-05, | |
| "loss": 0.3841, | |
| "step": 3930 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 1.952515946137491e-05, | |
| "loss": 0.3513, | |
| "step": 3940 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 1.943656980864635e-05, | |
| "loss": 0.3553, | |
| "step": 3950 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 1.934798015591779e-05, | |
| "loss": 0.3862, | |
| "step": 3960 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 1.925939050318923e-05, | |
| "loss": 0.3854, | |
| "step": 3970 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 1.917080085046067e-05, | |
| "loss": 0.3646, | |
| "step": 3980 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 1.9082211197732105e-05, | |
| "loss": 0.3793, | |
| "step": 3990 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 1.8993621545003544e-05, | |
| "loss": 0.3738, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "eval_loss": 0.39233776926994324, | |
| "eval_runtime": 138.3177, | |
| "eval_samples_per_second": 203.394, | |
| "eval_steps_per_second": 6.362, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 1.8905031892274984e-05, | |
| "loss": 0.3729, | |
| "step": 4010 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 1.8816442239546423e-05, | |
| "loss": 0.3629, | |
| "step": 4020 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 1.872785258681786e-05, | |
| "loss": 0.3743, | |
| "step": 4030 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 1.86392629340893e-05, | |
| "loss": 0.3722, | |
| "step": 4040 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 1.8550673281360738e-05, | |
| "loss": 0.3612, | |
| "step": 4050 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 1.8462083628632177e-05, | |
| "loss": 0.3705, | |
| "step": 4060 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 1.8373493975903617e-05, | |
| "loss": 0.3557, | |
| "step": 4070 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 1.8284904323175053e-05, | |
| "loss": 0.3723, | |
| "step": 4080 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 1.8196314670446492e-05, | |
| "loss": 0.3726, | |
| "step": 4090 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 1.810772501771793e-05, | |
| "loss": 0.3642, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "eval_loss": 0.39176103472709656, | |
| "eval_runtime": 139.016, | |
| "eval_samples_per_second": 202.372, | |
| "eval_steps_per_second": 6.33, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 1.801913536498937e-05, | |
| "loss": 0.3592, | |
| "step": 4110 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 1.793054571226081e-05, | |
| "loss": 0.3506, | |
| "step": 4120 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 1.7841956059532246e-05, | |
| "loss": 0.3834, | |
| "step": 4130 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 1.7753366406803686e-05, | |
| "loss": 0.355, | |
| "step": 4140 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 1.7664776754075125e-05, | |
| "loss": 0.3745, | |
| "step": 4150 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 1.7576187101346564e-05, | |
| "loss": 0.383, | |
| "step": 4160 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 1.7487597448618e-05, | |
| "loss": 0.3733, | |
| "step": 4170 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 1.739900779588944e-05, | |
| "loss": 0.3686, | |
| "step": 4180 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 1.731041814316088e-05, | |
| "loss": 0.3766, | |
| "step": 4190 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 1.722182849043232e-05, | |
| "loss": 0.3681, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "eval_loss": 0.39138132333755493, | |
| "eval_runtime": 138.2113, | |
| "eval_samples_per_second": 203.551, | |
| "eval_steps_per_second": 6.367, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 1.7133238837703758e-05, | |
| "loss": 0.3727, | |
| "step": 4210 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 1.7044649184975194e-05, | |
| "loss": 0.3811, | |
| "step": 4220 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 1.6956059532246633e-05, | |
| "loss": 0.3719, | |
| "step": 4230 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 1.6867469879518073e-05, | |
| "loss": 0.3538, | |
| "step": 4240 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 1.6778880226789512e-05, | |
| "loss": 0.3778, | |
| "step": 4250 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 1.669029057406095e-05, | |
| "loss": 0.3711, | |
| "step": 4260 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 1.6601700921332388e-05, | |
| "loss": 0.3785, | |
| "step": 4270 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 1.6513111268603827e-05, | |
| "loss": 0.3657, | |
| "step": 4280 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 1.6424521615875266e-05, | |
| "loss": 0.3825, | |
| "step": 4290 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 1.6335931963146706e-05, | |
| "loss": 0.3602, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "eval_loss": 0.3910753130912781, | |
| "eval_runtime": 138.112, | |
| "eval_samples_per_second": 203.697, | |
| "eval_steps_per_second": 6.372, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 1.6247342310418142e-05, | |
| "loss": 0.3474, | |
| "step": 4310 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 1.615875265768958e-05, | |
| "loss": 0.3464, | |
| "step": 4320 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 1.6070163004961024e-05, | |
| "loss": 0.3618, | |
| "step": 4330 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 1.598157335223246e-05, | |
| "loss": 0.4017, | |
| "step": 4340 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 1.58929836995039e-05, | |
| "loss": 0.3742, | |
| "step": 4350 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 1.5804394046775335e-05, | |
| "loss": 0.3679, | |
| "step": 4360 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 1.5715804394046775e-05, | |
| "loss": 0.3797, | |
| "step": 4370 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 1.5627214741318214e-05, | |
| "loss": 0.3547, | |
| "step": 4380 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 1.5538625088589654e-05, | |
| "loss": 0.383, | |
| "step": 4390 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 1.5450035435861093e-05, | |
| "loss": 0.3667, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "eval_loss": 0.39077791571617126, | |
| "eval_runtime": 138.1368, | |
| "eval_samples_per_second": 203.66, | |
| "eval_steps_per_second": 6.37, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 1.536144578313253e-05, | |
| "loss": 0.3816, | |
| "step": 4410 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 1.5272856130403972e-05, | |
| "loss": 0.3754, | |
| "step": 4420 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 1.5184266477675408e-05, | |
| "loss": 0.3622, | |
| "step": 4430 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 1.5095676824946847e-05, | |
| "loss": 0.3861, | |
| "step": 4440 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 1.5007087172218285e-05, | |
| "loss": 0.3876, | |
| "step": 4450 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 1.4918497519489724e-05, | |
| "loss": 0.3609, | |
| "step": 4460 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 1.4829907866761164e-05, | |
| "loss": 0.3666, | |
| "step": 4470 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 1.4741318214032601e-05, | |
| "loss": 0.3468, | |
| "step": 4480 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 1.4652728561304041e-05, | |
| "loss": 0.3719, | |
| "step": 4490 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 1.4564138908575479e-05, | |
| "loss": 0.3828, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "eval_loss": 0.39073827862739563, | |
| "eval_runtime": 138.1539, | |
| "eval_samples_per_second": 203.635, | |
| "eval_steps_per_second": 6.37, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 1.4475549255846918e-05, | |
| "loss": 0.3625, | |
| "step": 4510 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 1.4386959603118356e-05, | |
| "loss": 0.3575, | |
| "step": 4520 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 1.4298369950389795e-05, | |
| "loss": 0.3582, | |
| "step": 4530 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 1.4209780297661234e-05, | |
| "loss": 0.384, | |
| "step": 4540 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 1.4121190644932672e-05, | |
| "loss": 0.3652, | |
| "step": 4550 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 1.4032600992204112e-05, | |
| "loss": 0.3643, | |
| "step": 4560 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 1.394401133947555e-05, | |
| "loss": 0.3648, | |
| "step": 4570 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 1.3855421686746989e-05, | |
| "loss": 0.3733, | |
| "step": 4580 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 1.3766832034018428e-05, | |
| "loss": 0.3619, | |
| "step": 4590 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 1.3678242381289866e-05, | |
| "loss": 0.3862, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "eval_loss": 0.38958612084388733, | |
| "eval_runtime": 138.6074, | |
| "eval_samples_per_second": 202.969, | |
| "eval_steps_per_second": 6.349, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 1.3589652728561305e-05, | |
| "loss": 0.3763, | |
| "step": 4610 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 1.3501063075832743e-05, | |
| "loss": 0.3628, | |
| "step": 4620 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 1.3412473423104182e-05, | |
| "loss": 0.3716, | |
| "step": 4630 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 1.332388377037562e-05, | |
| "loss": 0.3409, | |
| "step": 4640 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 1.323529411764706e-05, | |
| "loss": 0.3749, | |
| "step": 4650 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 1.3146704464918499e-05, | |
| "loss": 0.3732, | |
| "step": 4660 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 1.3058114812189936e-05, | |
| "loss": 0.3566, | |
| "step": 4670 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 1.2969525159461376e-05, | |
| "loss": 0.3507, | |
| "step": 4680 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 1.2880935506732814e-05, | |
| "loss": 0.3546, | |
| "step": 4690 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 1.2792345854004253e-05, | |
| "loss": 0.3929, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "eval_loss": 0.3902750611305237, | |
| "eval_runtime": 138.1169, | |
| "eval_samples_per_second": 203.69, | |
| "eval_steps_per_second": 6.371, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 1.270375620127569e-05, | |
| "loss": 0.3738, | |
| "step": 4710 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 1.261516654854713e-05, | |
| "loss": 0.379, | |
| "step": 4720 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 1.252657689581857e-05, | |
| "loss": 0.3727, | |
| "step": 4730 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 1.2437987243090007e-05, | |
| "loss": 0.3525, | |
| "step": 4740 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 1.2349397590361447e-05, | |
| "loss": 0.3796, | |
| "step": 4750 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 1.2260807937632884e-05, | |
| "loss": 0.3811, | |
| "step": 4760 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 1.2172218284904324e-05, | |
| "loss": 0.3569, | |
| "step": 4770 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 1.2083628632175763e-05, | |
| "loss": 0.3749, | |
| "step": 4780 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 1.19950389794472e-05, | |
| "loss": 0.3537, | |
| "step": 4790 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 1.190644932671864e-05, | |
| "loss": 0.3749, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "eval_loss": 0.3902783989906311, | |
| "eval_runtime": 138.1622, | |
| "eval_samples_per_second": 203.623, | |
| "eval_steps_per_second": 6.369, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 1.1817859673990078e-05, | |
| "loss": 0.3788, | |
| "step": 4810 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 1.1729270021261517e-05, | |
| "loss": 0.3719, | |
| "step": 4820 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 1.1640680368532957e-05, | |
| "loss": 0.3612, | |
| "step": 4830 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 1.1552090715804394e-05, | |
| "loss": 0.3716, | |
| "step": 4840 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 1.1463501063075834e-05, | |
| "loss": 0.3788, | |
| "step": 4850 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 1.1374911410347271e-05, | |
| "loss": 0.3742, | |
| "step": 4860 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 1.1286321757618711e-05, | |
| "loss": 0.3616, | |
| "step": 4870 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 1.1197732104890149e-05, | |
| "loss": 0.3746, | |
| "step": 4880 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 1.1109142452161588e-05, | |
| "loss": 0.3922, | |
| "step": 4890 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 1.1020552799433027e-05, | |
| "loss": 0.37, | |
| "step": 4900 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "eval_loss": 0.3897284269332886, | |
| "eval_runtime": 138.1234, | |
| "eval_samples_per_second": 203.68, | |
| "eval_steps_per_second": 6.371, | |
| "step": 4900 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 1.0931963146704465e-05, | |
| "loss": 0.3741, | |
| "step": 4910 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 1.0843373493975904e-05, | |
| "loss": 0.3902, | |
| "step": 4920 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 1.0754783841247342e-05, | |
| "loss": 0.3426, | |
| "step": 4930 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 1.0666194188518782e-05, | |
| "loss": 0.3825, | |
| "step": 4940 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 1.057760453579022e-05, | |
| "loss": 0.3594, | |
| "step": 4950 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 1.0489014883061659e-05, | |
| "loss": 0.3404, | |
| "step": 4960 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 1.0400425230333098e-05, | |
| "loss": 0.3725, | |
| "step": 4970 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 1.0311835577604537e-05, | |
| "loss": 0.3662, | |
| "step": 4980 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 1.0223245924875975e-05, | |
| "loss": 0.3688, | |
| "step": 4990 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 1.0134656272147413e-05, | |
| "loss": 0.374, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "eval_loss": 0.389631450176239, | |
| "eval_runtime": 138.1297, | |
| "eval_samples_per_second": 203.671, | |
| "eval_steps_per_second": 6.371, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 1.0046066619418852e-05, | |
| "loss": 0.3866, | |
| "step": 5010 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 9.95747696669029e-06, | |
| "loss": 0.3423, | |
| "step": 5020 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 9.86888731396173e-06, | |
| "loss": 0.3497, | |
| "step": 5030 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 9.780297661233169e-06, | |
| "loss": 0.3625, | |
| "step": 5040 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 9.691708008504608e-06, | |
| "loss": 0.3752, | |
| "step": 5050 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 9.603118355776046e-06, | |
| "loss": 0.3732, | |
| "step": 5060 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 9.514528703047485e-06, | |
| "loss": 0.3546, | |
| "step": 5070 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 9.425939050318923e-06, | |
| "loss": 0.366, | |
| "step": 5080 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 9.33734939759036e-06, | |
| "loss": 0.3713, | |
| "step": 5090 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 9.2487597448618e-06, | |
| "loss": 0.3495, | |
| "step": 5100 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "eval_loss": 0.38959911465644836, | |
| "eval_runtime": 139.3255, | |
| "eval_samples_per_second": 201.923, | |
| "eval_steps_per_second": 6.316, | |
| "step": 5100 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 9.16017009213324e-06, | |
| "loss": 0.3578, | |
| "step": 5110 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 9.071580439404679e-06, | |
| "loss": 0.351, | |
| "step": 5120 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 8.982990786676117e-06, | |
| "loss": 0.4097, | |
| "step": 5130 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 8.894401133947556e-06, | |
| "loss": 0.3707, | |
| "step": 5140 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 8.805811481218994e-06, | |
| "loss": 0.3492, | |
| "step": 5150 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 8.717221828490433e-06, | |
| "loss": 0.3668, | |
| "step": 5160 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 8.628632175761872e-06, | |
| "loss": 0.3609, | |
| "step": 5170 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 8.54004252303331e-06, | |
| "loss": 0.3528, | |
| "step": 5180 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 8.45145287030475e-06, | |
| "loss": 0.3693, | |
| "step": 5190 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 8.362863217576187e-06, | |
| "loss": 0.3768, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "eval_loss": 0.3894375264644623, | |
| "eval_runtime": 138.7537, | |
| "eval_samples_per_second": 202.755, | |
| "eval_steps_per_second": 6.342, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 8.274273564847627e-06, | |
| "loss": 0.3619, | |
| "step": 5210 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 8.185683912119064e-06, | |
| "loss": 0.3742, | |
| "step": 5220 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 8.097094259390504e-06, | |
| "loss": 0.3461, | |
| "step": 5230 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 8.008504606661943e-06, | |
| "loss": 0.3743, | |
| "step": 5240 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 7.919914953933381e-06, | |
| "loss": 0.3434, | |
| "step": 5250 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 7.83132530120482e-06, | |
| "loss": 0.3784, | |
| "step": 5260 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 7.742735648476258e-06, | |
| "loss": 0.3671, | |
| "step": 5270 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 7.654145995747697e-06, | |
| "loss": 0.367, | |
| "step": 5280 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 7.565556343019135e-06, | |
| "loss": 0.3714, | |
| "step": 5290 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 7.476966690290574e-06, | |
| "loss": 0.348, | |
| "step": 5300 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "eval_loss": 0.38949331641197205, | |
| "eval_runtime": 138.1986, | |
| "eval_samples_per_second": 203.569, | |
| "eval_steps_per_second": 6.368, | |
| "step": 5300 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 7.388377037562014e-06, | |
| "loss": 0.3743, | |
| "step": 5310 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 7.299787384833452e-06, | |
| "loss": 0.3569, | |
| "step": 5320 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 7.211197732104891e-06, | |
| "loss": 0.3434, | |
| "step": 5330 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 7.1226080793763295e-06, | |
| "loss": 0.3783, | |
| "step": 5340 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 7.034018426647768e-06, | |
| "loss": 0.3399, | |
| "step": 5350 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 6.945428773919206e-06, | |
| "loss": 0.3433, | |
| "step": 5360 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 6.856839121190644e-06, | |
| "loss": 0.3667, | |
| "step": 5370 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 6.7682494684620846e-06, | |
| "loss": 0.3848, | |
| "step": 5380 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 6.679659815733523e-06, | |
| "loss": 0.3624, | |
| "step": 5390 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 6.591070163004962e-06, | |
| "loss": 0.3771, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "eval_loss": 0.38931286334991455, | |
| "eval_runtime": 138.1336, | |
| "eval_samples_per_second": 203.665, | |
| "eval_steps_per_second": 6.371, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 6.5024805102764e-06, | |
| "loss": 0.3726, | |
| "step": 5410 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 6.413890857547839e-06, | |
| "loss": 0.3551, | |
| "step": 5420 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 6.325301204819277e-06, | |
| "loss": 0.3743, | |
| "step": 5430 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 6.236711552090716e-06, | |
| "loss": 0.3744, | |
| "step": 5440 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 6.148121899362154e-06, | |
| "loss": 0.3712, | |
| "step": 5450 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 6.059532246633594e-06, | |
| "loss": 0.3535, | |
| "step": 5460 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 5.970942593905032e-06, | |
| "loss": 0.3534, | |
| "step": 5470 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 5.882352941176471e-06, | |
| "loss": 0.3498, | |
| "step": 5480 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 5.7937632884479095e-06, | |
| "loss": 0.3767, | |
| "step": 5490 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 5.705173635719349e-06, | |
| "loss": 0.3584, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "eval_loss": 0.3893459141254425, | |
| "eval_runtime": 138.1479, | |
| "eval_samples_per_second": 203.644, | |
| "eval_steps_per_second": 6.37, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 5.6165839829907866e-06, | |
| "loss": 0.3928, | |
| "step": 5510 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 5.527994330262225e-06, | |
| "loss": 0.339, | |
| "step": 5520 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 5.4394046775336645e-06, | |
| "loss": 0.3619, | |
| "step": 5530 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 5.350815024805103e-06, | |
| "loss": 0.3679, | |
| "step": 5540 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 5.262225372076542e-06, | |
| "loss": 0.3678, | |
| "step": 5550 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 5.17363571934798e-06, | |
| "loss": 0.3864, | |
| "step": 5560 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 5.0850460666194196e-06, | |
| "loss": 0.3724, | |
| "step": 5570 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 4.996456413890858e-06, | |
| "loss": 0.3632, | |
| "step": 5580 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 4.907866761162296e-06, | |
| "loss": 0.3617, | |
| "step": 5590 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 4.819277108433735e-06, | |
| "loss": 0.3609, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "eval_loss": 0.3893371820449829, | |
| "eval_runtime": 138.139, | |
| "eval_samples_per_second": 203.657, | |
| "eval_steps_per_second": 6.37, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 4.730687455705174e-06, | |
| "loss": 0.3732, | |
| "step": 5610 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 4.642097802976612e-06, | |
| "loss": 0.354, | |
| "step": 5620 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 4.553508150248052e-06, | |
| "loss": 0.3518, | |
| "step": 5630 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 4.46491849751949e-06, | |
| "loss": 0.3579, | |
| "step": 5640 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 4.376328844790929e-06, | |
| "loss": 0.3636, | |
| "step": 5650 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 4.287739192062367e-06, | |
| "loss": 0.3509, | |
| "step": 5660 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 4.199149539333806e-06, | |
| "loss": 0.3624, | |
| "step": 5670 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 4.1105598866052445e-06, | |
| "loss": 0.3735, | |
| "step": 5680 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 4.021970233876683e-06, | |
| "loss": 0.3573, | |
| "step": 5690 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 3.933380581148122e-06, | |
| "loss": 0.3707, | |
| "step": 5700 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "eval_loss": 0.3889307379722595, | |
| "eval_runtime": 138.1382, | |
| "eval_samples_per_second": 203.658, | |
| "eval_steps_per_second": 6.37, | |
| "step": 5700 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 3.844790928419561e-06, | |
| "loss": 0.3446, | |
| "step": 5710 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 3.7562012756909995e-06, | |
| "loss": 0.366, | |
| "step": 5720 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 3.6676116229624377e-06, | |
| "loss": 0.3686, | |
| "step": 5730 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 3.579021970233877e-06, | |
| "loss": 0.3696, | |
| "step": 5740 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 3.4904323175053156e-06, | |
| "loss": 0.388, | |
| "step": 5750 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 3.401842664776754e-06, | |
| "loss": 0.3788, | |
| "step": 5760 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 3.313253012048193e-06, | |
| "loss": 0.3843, | |
| "step": 5770 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 3.2246633593196317e-06, | |
| "loss": 0.3731, | |
| "step": 5780 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 3.1360737065910702e-06, | |
| "loss": 0.3626, | |
| "step": 5790 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 3.047484053862509e-06, | |
| "loss": 0.3787, | |
| "step": 5800 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "eval_loss": 0.3886876702308655, | |
| "eval_runtime": 138.1679, | |
| "eval_samples_per_second": 203.615, | |
| "eval_steps_per_second": 6.369, | |
| "step": 5800 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 2.9588944011339477e-06, | |
| "loss": 0.3721, | |
| "step": 5810 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 2.8703047484053863e-06, | |
| "loss": 0.3575, | |
| "step": 5820 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 2.7817150956768253e-06, | |
| "loss": 0.3607, | |
| "step": 5830 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 2.693125442948264e-06, | |
| "loss": 0.3633, | |
| "step": 5840 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 2.6045357902197024e-06, | |
| "loss": 0.3506, | |
| "step": 5850 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 2.5159461374911414e-06, | |
| "loss": 0.3471, | |
| "step": 5860 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 2.42735648476258e-06, | |
| "loss": 0.3693, | |
| "step": 5870 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 2.3387668320340185e-06, | |
| "loss": 0.3577, | |
| "step": 5880 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 2.250177179305457e-06, | |
| "loss": 0.3685, | |
| "step": 5890 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 2.161587526576896e-06, | |
| "loss": 0.3694, | |
| "step": 5900 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "eval_loss": 0.3885899484157562, | |
| "eval_runtime": 138.158, | |
| "eval_samples_per_second": 203.629, | |
| "eval_steps_per_second": 6.37, | |
| "step": 5900 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 2.0729978738483345e-06, | |
| "loss": 0.3645, | |
| "step": 5910 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 1.984408221119773e-06, | |
| "loss": 0.3786, | |
| "step": 5920 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 1.895818568391212e-06, | |
| "loss": 0.368, | |
| "step": 5930 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 1.8072289156626506e-06, | |
| "loss": 0.3771, | |
| "step": 5940 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 1.7186392629340894e-06, | |
| "loss": 0.3614, | |
| "step": 5950 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 1.630049610205528e-06, | |
| "loss": 0.3739, | |
| "step": 5960 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 1.5414599574769667e-06, | |
| "loss": 0.3649, | |
| "step": 5970 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 1.4528703047484054e-06, | |
| "loss": 0.353, | |
| "step": 5980 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 1.364280652019844e-06, | |
| "loss": 0.3623, | |
| "step": 5990 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 1.2756909992912828e-06, | |
| "loss": 0.3832, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "eval_loss": 0.3886074423789978, | |
| "eval_runtime": 138.1707, | |
| "eval_samples_per_second": 203.61, | |
| "eval_steps_per_second": 6.369, | |
| "step": 6000 | |
| } | |
| ], | |
| "max_steps": 6144, | |
| "num_train_epochs": 1, | |
| "total_flos": 3.250647465984e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |