| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.9982905982905983, | |
| "eval_steps": 500, | |
| "global_step": 2631, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.011396011396011397, | |
| "grad_norm": 1.1062365284901086, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7552, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.022792022792022793, | |
| "grad_norm": 1.023752202077829, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7051, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.03418803418803419, | |
| "grad_norm": 1.0176219936883037, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6821, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.045584045584045586, | |
| "grad_norm": 0.7858042820189418, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6856, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.05698005698005698, | |
| "grad_norm": 0.7933715158385674, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6637, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.06837606837606838, | |
| "grad_norm": 0.8447246301495516, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6622, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.07977207977207977, | |
| "grad_norm": 0.5473425796189046, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6663, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.09116809116809117, | |
| "grad_norm": 0.4937146235526688, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6571, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.10256410256410256, | |
| "grad_norm": 0.44446776727990156, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6638, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.11396011396011396, | |
| "grad_norm": 0.41849443527281166, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6579, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.12535612535612536, | |
| "grad_norm": 0.45940085033829986, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6526, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.13675213675213677, | |
| "grad_norm": 0.45931809899313636, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6369, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.14814814814814814, | |
| "grad_norm": 0.40591863341923856, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6341, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.15954415954415954, | |
| "grad_norm": 0.42649491292164343, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6573, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.17094017094017094, | |
| "grad_norm": 0.42419739622977437, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6449, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.18233618233618235, | |
| "grad_norm": 0.41999442196069786, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6558, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.19373219373219372, | |
| "grad_norm": 0.4637200181201795, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6287, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.20512820512820512, | |
| "grad_norm": 0.41547705456707573, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6439, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.21652421652421652, | |
| "grad_norm": 0.43068607713697277, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6396, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.22792022792022792, | |
| "grad_norm": 0.4469322057262852, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6356, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.23931623931623933, | |
| "grad_norm": 0.4680911563203023, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6306, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.25071225071225073, | |
| "grad_norm": 0.4095294859092795, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6277, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.2621082621082621, | |
| "grad_norm": 0.45759740926828324, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6339, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.27350427350427353, | |
| "grad_norm": 0.4140379707131278, | |
| "learning_rate": 5e-06, | |
| "loss": 0.641, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.2849002849002849, | |
| "grad_norm": 0.4150377896672994, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6372, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.2962962962962963, | |
| "grad_norm": 0.402341599576737, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6403, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.3076923076923077, | |
| "grad_norm": 0.42585340932157245, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6415, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.3190883190883191, | |
| "grad_norm": 0.45653778556147656, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6399, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.33048433048433046, | |
| "grad_norm": 0.4195393934267986, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6336, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.3418803418803419, | |
| "grad_norm": 0.46802670579447797, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6337, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.35327635327635326, | |
| "grad_norm": 0.4203687337846972, | |
| "learning_rate": 5e-06, | |
| "loss": 0.637, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.3646723646723647, | |
| "grad_norm": 0.421822849143681, | |
| "learning_rate": 5e-06, | |
| "loss": 0.64, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.37606837606837606, | |
| "grad_norm": 0.4283596513144174, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6252, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.38746438746438744, | |
| "grad_norm": 0.42324206057009117, | |
| "learning_rate": 5e-06, | |
| "loss": 0.636, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.39886039886039887, | |
| "grad_norm": 0.4062746526152, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6387, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.41025641025641024, | |
| "grad_norm": 0.43787430045384385, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6338, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.42165242165242167, | |
| "grad_norm": 0.4067600081663935, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6337, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.43304843304843305, | |
| "grad_norm": 0.405651618692542, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6235, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.4444444444444444, | |
| "grad_norm": 0.39893273449497857, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6305, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.45584045584045585, | |
| "grad_norm": 0.4181843535226299, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6424, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.4672364672364672, | |
| "grad_norm": 0.42805555885189545, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6319, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.47863247863247865, | |
| "grad_norm": 0.44895050300003103, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6332, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.49002849002849, | |
| "grad_norm": 0.3919946319959885, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6328, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.5014245014245015, | |
| "grad_norm": 0.415410598131448, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6402, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.5128205128205128, | |
| "grad_norm": 0.4393590856709396, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6306, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.5242165242165242, | |
| "grad_norm": 0.43301735874135633, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6344, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.5356125356125356, | |
| "grad_norm": 0.44449051507968934, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6231, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.5470085470085471, | |
| "grad_norm": 0.41409814672813067, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6341, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.5584045584045584, | |
| "grad_norm": 0.404549684025027, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6351, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.5698005698005698, | |
| "grad_norm": 0.4180598818867765, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6309, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.5811965811965812, | |
| "grad_norm": 0.40656312646305987, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6331, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 0.5925925925925926, | |
| "grad_norm": 0.40247877044565616, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6303, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.603988603988604, | |
| "grad_norm": 0.4186724709073127, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6295, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 0.6153846153846154, | |
| "grad_norm": 0.3956067792496914, | |
| "learning_rate": 5e-06, | |
| "loss": 0.629, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.6267806267806267, | |
| "grad_norm": 0.43010520803632213, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6418, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.6381766381766382, | |
| "grad_norm": 0.4242582783709579, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6365, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.6495726495726496, | |
| "grad_norm": 0.4574479642511814, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6298, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 0.6609686609686609, | |
| "grad_norm": 0.3999462091117723, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6264, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.6723646723646723, | |
| "grad_norm": 0.43650664891174007, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6338, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 0.6837606837606838, | |
| "grad_norm": 0.4209881207979195, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6185, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.6951566951566952, | |
| "grad_norm": 0.4356837089917804, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6285, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 0.7065527065527065, | |
| "grad_norm": 0.4267755900128707, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6249, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 0.717948717948718, | |
| "grad_norm": 0.4252749404036598, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6297, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 0.7293447293447294, | |
| "grad_norm": 0.43616986641525424, | |
| "learning_rate": 5e-06, | |
| "loss": 0.624, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 0.7407407407407407, | |
| "grad_norm": 0.4164486549654651, | |
| "learning_rate": 5e-06, | |
| "loss": 0.629, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.7521367521367521, | |
| "grad_norm": 0.476343190261518, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6177, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 0.7635327635327636, | |
| "grad_norm": 0.40486827396324065, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6261, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 0.7749287749287749, | |
| "grad_norm": 0.4212351136466915, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6304, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 0.7863247863247863, | |
| "grad_norm": 0.41575901401793347, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6398, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 0.7977207977207977, | |
| "grad_norm": 0.4285454155969582, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6319, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.8091168091168092, | |
| "grad_norm": 0.40726171067131095, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6314, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 0.8205128205128205, | |
| "grad_norm": 0.41168149111216795, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6243, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 0.8319088319088319, | |
| "grad_norm": 0.435567753751087, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6226, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 0.8433048433048433, | |
| "grad_norm": 0.43940850789677355, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6208, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 0.8547008547008547, | |
| "grad_norm": 0.4188384621992378, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6338, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.8660968660968661, | |
| "grad_norm": 0.3960108041735021, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6337, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 0.8774928774928775, | |
| "grad_norm": 0.40675640823017994, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6296, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 0.8888888888888888, | |
| "grad_norm": 0.43353876595216656, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6357, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 0.9002849002849003, | |
| "grad_norm": 0.43992543662793077, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6333, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 0.9116809116809117, | |
| "grad_norm": 0.41627535741522503, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6384, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.9230769230769231, | |
| "grad_norm": 0.4274496512159185, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6309, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 0.9344729344729344, | |
| "grad_norm": 0.5000942948514508, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6323, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 0.9458689458689459, | |
| "grad_norm": 0.39649163621370453, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6117, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 0.9572649572649573, | |
| "grad_norm": 0.45128894713654466, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6258, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 0.9686609686609686, | |
| "grad_norm": 0.4053334632337957, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6334, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.98005698005698, | |
| "grad_norm": 0.4570308695791834, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6299, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 0.9914529914529915, | |
| "grad_norm": 0.4142729888175128, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6134, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 0.9994301994301994, | |
| "eval_loss": 0.622437059879303, | |
| "eval_runtime": 442.3461, | |
| "eval_samples_per_second": 26.728, | |
| "eval_steps_per_second": 0.418, | |
| "step": 877 | |
| }, | |
| { | |
| "epoch": 1.002849002849003, | |
| "grad_norm": 0.467206811021719, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6384, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 1.0142450142450143, | |
| "grad_norm": 0.4575873633037112, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5855, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 1.0256410256410255, | |
| "grad_norm": 0.4094192073196508, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5924, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 1.037037037037037, | |
| "grad_norm": 0.41727147235729756, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5882, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 1.0484330484330484, | |
| "grad_norm": 0.40097390374474684, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5834, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 1.0598290598290598, | |
| "grad_norm": 0.3988722663272877, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5875, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 1.0712250712250713, | |
| "grad_norm": 0.409835543782938, | |
| "learning_rate": 5e-06, | |
| "loss": 0.578, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 1.0826210826210827, | |
| "grad_norm": 0.4348656181993297, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5945, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 1.0940170940170941, | |
| "grad_norm": 0.4560769367527893, | |
| "learning_rate": 5e-06, | |
| "loss": 0.591, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 1.1054131054131053, | |
| "grad_norm": 0.3987301391233058, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5947, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 1.1168091168091168, | |
| "grad_norm": 0.4310263093448157, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5989, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 1.1282051282051282, | |
| "grad_norm": 0.3988555704488419, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5883, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 1.1396011396011396, | |
| "grad_norm": 0.41694498325264395, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5857, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.150997150997151, | |
| "grad_norm": 0.4261280155159663, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5846, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 1.1623931623931625, | |
| "grad_norm": 0.4090258551630524, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5862, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 1.173789173789174, | |
| "grad_norm": 0.39703392125897946, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5828, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 1.1851851851851851, | |
| "grad_norm": 0.4171232168803472, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5969, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 1.1965811965811965, | |
| "grad_norm": 0.3986677142839061, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5849, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 1.207977207977208, | |
| "grad_norm": 0.4210046425391405, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5866, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 1.2193732193732194, | |
| "grad_norm": 0.4497366233089093, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5963, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 1.2307692307692308, | |
| "grad_norm": 0.43086405644231185, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5872, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 1.242165242165242, | |
| "grad_norm": 0.4519037391850927, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5952, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 1.2535612535612537, | |
| "grad_norm": 0.41349582244683747, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5903, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 1.264957264957265, | |
| "grad_norm": 0.3837938001947666, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5989, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 1.2763532763532763, | |
| "grad_norm": 0.38645298038964926, | |
| "learning_rate": 5e-06, | |
| "loss": 0.583, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 1.2877492877492878, | |
| "grad_norm": 0.39026828874261793, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5938, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 1.2991452991452992, | |
| "grad_norm": 0.48601873116831096, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5805, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 1.3105413105413106, | |
| "grad_norm": 0.4496341989317277, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5862, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 1.3219373219373218, | |
| "grad_norm": 0.43314588815183497, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5883, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 1.3333333333333333, | |
| "grad_norm": 0.4373497446033339, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5833, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 1.3447293447293447, | |
| "grad_norm": 0.4061985333964508, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5824, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 1.3561253561253561, | |
| "grad_norm": 0.4144234110159319, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6004, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 1.3675213675213675, | |
| "grad_norm": 0.4373239103878606, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5818, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 1.378917378917379, | |
| "grad_norm": 0.4210723366091624, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5859, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 1.3903133903133904, | |
| "grad_norm": 0.4052006957338942, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5906, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 1.4017094017094016, | |
| "grad_norm": 0.4292623892695985, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5927, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 1.413105413105413, | |
| "grad_norm": 0.4232783608596394, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5956, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 1.4245014245014245, | |
| "grad_norm": 0.43895695326546535, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6033, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 1.435897435897436, | |
| "grad_norm": 0.4349281709940867, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5825, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 1.4472934472934473, | |
| "grad_norm": 0.4124297881341476, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5842, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 1.4586894586894588, | |
| "grad_norm": 0.4103899829789082, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5851, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 1.4700854700854702, | |
| "grad_norm": 0.4187405725906187, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5815, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 1.4814814814814814, | |
| "grad_norm": 0.4335514785672904, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5893, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 1.4928774928774928, | |
| "grad_norm": 0.4095416189258966, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5812, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 1.5042735042735043, | |
| "grad_norm": 0.4327159045023668, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5872, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 1.5156695156695157, | |
| "grad_norm": 0.42071355477765043, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5894, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 1.5270655270655271, | |
| "grad_norm": 0.41206489314047035, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5948, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 1.5384615384615383, | |
| "grad_norm": 0.4743925797235051, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5755, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 1.54985754985755, | |
| "grad_norm": 0.40595707601991954, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5892, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 1.5612535612535612, | |
| "grad_norm": 0.3947481991815675, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5784, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 1.5726495726495726, | |
| "grad_norm": 0.38785299206305784, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5864, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 1.584045584045584, | |
| "grad_norm": 0.4149251097325744, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6075, | |
| "step": 1390 | |
| }, | |
| { | |
| "epoch": 1.5954415954415955, | |
| "grad_norm": 0.43637706913229096, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5944, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 1.606837606837607, | |
| "grad_norm": 0.4169030325172147, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5915, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 1.618233618233618, | |
| "grad_norm": 0.40313516644365976, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5817, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 1.6296296296296298, | |
| "grad_norm": 0.39503546583616356, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5983, | |
| "step": 1430 | |
| }, | |
| { | |
| "epoch": 1.641025641025641, | |
| "grad_norm": 0.3985527253164314, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5826, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 1.6524216524216524, | |
| "grad_norm": 0.4244488951950044, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5889, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 1.6638176638176638, | |
| "grad_norm": 0.39693307887587553, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5859, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 1.6752136752136753, | |
| "grad_norm": 0.3849679459506633, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5806, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 1.6866096866096867, | |
| "grad_norm": 0.4201985578364686, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5866, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 1.698005698005698, | |
| "grad_norm": 0.42432125023319545, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5803, | |
| "step": 1490 | |
| }, | |
| { | |
| "epoch": 1.7094017094017095, | |
| "grad_norm": 0.40730542273295467, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5913, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 1.7207977207977208, | |
| "grad_norm": 0.42837414750466624, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5795, | |
| "step": 1510 | |
| }, | |
| { | |
| "epoch": 1.7321937321937322, | |
| "grad_norm": 0.44083872834956234, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5888, | |
| "step": 1520 | |
| }, | |
| { | |
| "epoch": 1.7435897435897436, | |
| "grad_norm": 0.41133942102181764, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5865, | |
| "step": 1530 | |
| }, | |
| { | |
| "epoch": 1.7549857549857548, | |
| "grad_norm": 0.40260223356507924, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5816, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 1.7663817663817665, | |
| "grad_norm": 0.4054088563875919, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5952, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 1.7777777777777777, | |
| "grad_norm": 0.4218451424068199, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5879, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 1.7891737891737893, | |
| "grad_norm": 0.4423529568236007, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5907, | |
| "step": 1570 | |
| }, | |
| { | |
| "epoch": 1.8005698005698005, | |
| "grad_norm": 0.41215301182035746, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5841, | |
| "step": 1580 | |
| }, | |
| { | |
| "epoch": 1.811965811965812, | |
| "grad_norm": 0.4555696841177031, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5849, | |
| "step": 1590 | |
| }, | |
| { | |
| "epoch": 1.8233618233618234, | |
| "grad_norm": 0.41997083905529, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5712, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 1.8347578347578346, | |
| "grad_norm": 0.40350765403827904, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5773, | |
| "step": 1610 | |
| }, | |
| { | |
| "epoch": 1.8461538461538463, | |
| "grad_norm": 0.41505233462990104, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5828, | |
| "step": 1620 | |
| }, | |
| { | |
| "epoch": 1.8575498575498575, | |
| "grad_norm": 0.4094044224106121, | |
| "learning_rate": 5e-06, | |
| "loss": 0.577, | |
| "step": 1630 | |
| }, | |
| { | |
| "epoch": 1.868945868945869, | |
| "grad_norm": 0.3989458077194491, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5852, | |
| "step": 1640 | |
| }, | |
| { | |
| "epoch": 1.8803418803418803, | |
| "grad_norm": 0.3968449176678109, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5765, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 1.8917378917378918, | |
| "grad_norm": 0.3975827713442406, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5941, | |
| "step": 1660 | |
| }, | |
| { | |
| "epoch": 1.9031339031339032, | |
| "grad_norm": 0.4591167052806216, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5958, | |
| "step": 1670 | |
| }, | |
| { | |
| "epoch": 1.9145299145299144, | |
| "grad_norm": 0.4763985809192953, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5822, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 1.925925925925926, | |
| "grad_norm": 0.40816873290685, | |
| "learning_rate": 5e-06, | |
| "loss": 0.591, | |
| "step": 1690 | |
| }, | |
| { | |
| "epoch": 1.9373219373219372, | |
| "grad_norm": 0.43451011164507114, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5866, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 1.9487179487179487, | |
| "grad_norm": 0.42502005410583105, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5812, | |
| "step": 1710 | |
| }, | |
| { | |
| "epoch": 1.96011396011396, | |
| "grad_norm": 0.3868140358085357, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5952, | |
| "step": 1720 | |
| }, | |
| { | |
| "epoch": 1.9715099715099715, | |
| "grad_norm": 0.4233434645527226, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5905, | |
| "step": 1730 | |
| }, | |
| { | |
| "epoch": 1.982905982905983, | |
| "grad_norm": 0.46128367957303146, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5835, | |
| "step": 1740 | |
| }, | |
| { | |
| "epoch": 1.9943019943019942, | |
| "grad_norm": 0.41962900843595113, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5823, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 0.6174917817115784, | |
| "eval_runtime": 442.5819, | |
| "eval_samples_per_second": 26.714, | |
| "eval_steps_per_second": 0.418, | |
| "step": 1755 | |
| }, | |
| { | |
| "epoch": 2.005698005698006, | |
| "grad_norm": 0.43638289381677664, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6003, | |
| "step": 1760 | |
| }, | |
| { | |
| "epoch": 2.017094017094017, | |
| "grad_norm": 0.4032954694771035, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5295, | |
| "step": 1770 | |
| }, | |
| { | |
| "epoch": 2.0284900284900287, | |
| "grad_norm": 0.3978342138531873, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5396, | |
| "step": 1780 | |
| }, | |
| { | |
| "epoch": 2.03988603988604, | |
| "grad_norm": 0.3941941742542143, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5498, | |
| "step": 1790 | |
| }, | |
| { | |
| "epoch": 2.051282051282051, | |
| "grad_norm": 0.40614413388153375, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5485, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 2.0626780626780628, | |
| "grad_norm": 0.4062005374187212, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5443, | |
| "step": 1810 | |
| }, | |
| { | |
| "epoch": 2.074074074074074, | |
| "grad_norm": 0.38632662394247547, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5499, | |
| "step": 1820 | |
| }, | |
| { | |
| "epoch": 2.0854700854700856, | |
| "grad_norm": 0.3877796238652637, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5472, | |
| "step": 1830 | |
| }, | |
| { | |
| "epoch": 2.096866096866097, | |
| "grad_norm": 0.4031396151639763, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5557, | |
| "step": 1840 | |
| }, | |
| { | |
| "epoch": 2.1082621082621085, | |
| "grad_norm": 0.3758020305089208, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5423, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 2.1196581196581197, | |
| "grad_norm": 0.46333515136342907, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5556, | |
| "step": 1860 | |
| }, | |
| { | |
| "epoch": 2.131054131054131, | |
| "grad_norm": 0.3990721210469113, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5464, | |
| "step": 1870 | |
| }, | |
| { | |
| "epoch": 2.1424501424501425, | |
| "grad_norm": 0.41896529664740606, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5459, | |
| "step": 1880 | |
| }, | |
| { | |
| "epoch": 2.1538461538461537, | |
| "grad_norm": 0.40224292638674486, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5432, | |
| "step": 1890 | |
| }, | |
| { | |
| "epoch": 2.1652421652421654, | |
| "grad_norm": 0.3703829495333715, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5434, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 2.1766381766381766, | |
| "grad_norm": 0.4195807512147461, | |
| "learning_rate": 5e-06, | |
| "loss": 0.548, | |
| "step": 1910 | |
| }, | |
| { | |
| "epoch": 2.1880341880341883, | |
| "grad_norm": 0.42078014349068604, | |
| "learning_rate": 5e-06, | |
| "loss": 0.551, | |
| "step": 1920 | |
| }, | |
| { | |
| "epoch": 2.1994301994301995, | |
| "grad_norm": 0.39550870444336733, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5487, | |
| "step": 1930 | |
| }, | |
| { | |
| "epoch": 2.2108262108262107, | |
| "grad_norm": 0.403560752581769, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5518, | |
| "step": 1940 | |
| }, | |
| { | |
| "epoch": 2.2222222222222223, | |
| "grad_norm": 0.4148295164570796, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5455, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 2.2336182336182335, | |
| "grad_norm": 0.37681071283125916, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5371, | |
| "step": 1960 | |
| }, | |
| { | |
| "epoch": 2.245014245014245, | |
| "grad_norm": 0.4085602540294654, | |
| "learning_rate": 5e-06, | |
| "loss": 0.548, | |
| "step": 1970 | |
| }, | |
| { | |
| "epoch": 2.2564102564102564, | |
| "grad_norm": 0.42666262080387535, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5489, | |
| "step": 1980 | |
| }, | |
| { | |
| "epoch": 2.267806267806268, | |
| "grad_norm": 0.413370914720578, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5452, | |
| "step": 1990 | |
| }, | |
| { | |
| "epoch": 2.2792022792022792, | |
| "grad_norm": 0.3924258676572947, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5506, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 2.2905982905982905, | |
| "grad_norm": 0.4347195110430224, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5495, | |
| "step": 2010 | |
| }, | |
| { | |
| "epoch": 2.301994301994302, | |
| "grad_norm": 0.40213883875930767, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5447, | |
| "step": 2020 | |
| }, | |
| { | |
| "epoch": 2.3133903133903133, | |
| "grad_norm": 0.42546941310471453, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5533, | |
| "step": 2030 | |
| }, | |
| { | |
| "epoch": 2.324786324786325, | |
| "grad_norm": 0.40042388002057316, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5493, | |
| "step": 2040 | |
| }, | |
| { | |
| "epoch": 2.336182336182336, | |
| "grad_norm": 0.40985989196559397, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5484, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 2.347578347578348, | |
| "grad_norm": 0.4262197347046128, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5561, | |
| "step": 2060 | |
| }, | |
| { | |
| "epoch": 2.358974358974359, | |
| "grad_norm": 0.4079997903297647, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5479, | |
| "step": 2070 | |
| }, | |
| { | |
| "epoch": 2.3703703703703702, | |
| "grad_norm": 0.4171995256710412, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5482, | |
| "step": 2080 | |
| }, | |
| { | |
| "epoch": 2.381766381766382, | |
| "grad_norm": 0.4067288627883757, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5495, | |
| "step": 2090 | |
| }, | |
| { | |
| "epoch": 2.393162393162393, | |
| "grad_norm": 0.39812759486187826, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5475, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 2.4045584045584047, | |
| "grad_norm": 0.4252046487226247, | |
| "learning_rate": 5e-06, | |
| "loss": 0.564, | |
| "step": 2110 | |
| }, | |
| { | |
| "epoch": 2.415954415954416, | |
| "grad_norm": 0.385246050290494, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5495, | |
| "step": 2120 | |
| }, | |
| { | |
| "epoch": 2.427350427350427, | |
| "grad_norm": 0.4086146276427414, | |
| "learning_rate": 5e-06, | |
| "loss": 0.56, | |
| "step": 2130 | |
| }, | |
| { | |
| "epoch": 2.438746438746439, | |
| "grad_norm": 0.40396684063143223, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5592, | |
| "step": 2140 | |
| }, | |
| { | |
| "epoch": 2.45014245014245, | |
| "grad_norm": 0.40575491064321195, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5633, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 2.4615384615384617, | |
| "grad_norm": 0.4073296395669543, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5488, | |
| "step": 2160 | |
| }, | |
| { | |
| "epoch": 2.472934472934473, | |
| "grad_norm": 0.43882905338245753, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5513, | |
| "step": 2170 | |
| }, | |
| { | |
| "epoch": 2.484330484330484, | |
| "grad_norm": 0.4031322481681622, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5554, | |
| "step": 2180 | |
| }, | |
| { | |
| "epoch": 2.4957264957264957, | |
| "grad_norm": 0.42227630442588826, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5574, | |
| "step": 2190 | |
| }, | |
| { | |
| "epoch": 2.5071225071225074, | |
| "grad_norm": 0.4277624308363176, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5629, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 2.5185185185185186, | |
| "grad_norm": 0.40043500855114567, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5444, | |
| "step": 2210 | |
| }, | |
| { | |
| "epoch": 2.52991452991453, | |
| "grad_norm": 0.427445344908136, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5591, | |
| "step": 2220 | |
| }, | |
| { | |
| "epoch": 2.5413105413105415, | |
| "grad_norm": 0.4197028690010052, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5513, | |
| "step": 2230 | |
| }, | |
| { | |
| "epoch": 2.5527065527065527, | |
| "grad_norm": 0.41806376493939207, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5501, | |
| "step": 2240 | |
| }, | |
| { | |
| "epoch": 2.564102564102564, | |
| "grad_norm": 0.4080384204790527, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5488, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 2.5754985754985755, | |
| "grad_norm": 0.4339972064470789, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5534, | |
| "step": 2260 | |
| }, | |
| { | |
| "epoch": 2.5868945868945867, | |
| "grad_norm": 0.4139873128656014, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5509, | |
| "step": 2270 | |
| }, | |
| { | |
| "epoch": 2.5982905982905984, | |
| "grad_norm": 0.39593523779791756, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5515, | |
| "step": 2280 | |
| }, | |
| { | |
| "epoch": 2.6096866096866096, | |
| "grad_norm": 0.3887745966959367, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5567, | |
| "step": 2290 | |
| }, | |
| { | |
| "epoch": 2.6210826210826212, | |
| "grad_norm": 0.3899940114191536, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5429, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 2.6324786324786325, | |
| "grad_norm": 0.4176311832860518, | |
| "learning_rate": 5e-06, | |
| "loss": 0.553, | |
| "step": 2310 | |
| }, | |
| { | |
| "epoch": 2.6438746438746437, | |
| "grad_norm": 0.46727727994302587, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5524, | |
| "step": 2320 | |
| }, | |
| { | |
| "epoch": 2.6552706552706553, | |
| "grad_norm": 0.4368321834367039, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5552, | |
| "step": 2330 | |
| }, | |
| { | |
| "epoch": 2.6666666666666665, | |
| "grad_norm": 0.4479324367839254, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5534, | |
| "step": 2340 | |
| }, | |
| { | |
| "epoch": 2.678062678062678, | |
| "grad_norm": 0.41411545835899133, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5467, | |
| "step": 2350 | |
| }, | |
| { | |
| "epoch": 2.6894586894586894, | |
| "grad_norm": 0.4201299885965421, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5565, | |
| "step": 2360 | |
| }, | |
| { | |
| "epoch": 2.700854700854701, | |
| "grad_norm": 0.40978702073303064, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5444, | |
| "step": 2370 | |
| }, | |
| { | |
| "epoch": 2.7122507122507122, | |
| "grad_norm": 0.4233459449335634, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5563, | |
| "step": 2380 | |
| }, | |
| { | |
| "epoch": 2.7236467236467234, | |
| "grad_norm": 0.4159458912952842, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5551, | |
| "step": 2390 | |
| }, | |
| { | |
| "epoch": 2.735042735042735, | |
| "grad_norm": 0.41425606346483057, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5539, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 2.7464387464387463, | |
| "grad_norm": 0.4166133827092343, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5588, | |
| "step": 2410 | |
| }, | |
| { | |
| "epoch": 2.757834757834758, | |
| "grad_norm": 0.4263688845736852, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5575, | |
| "step": 2420 | |
| }, | |
| { | |
| "epoch": 2.769230769230769, | |
| "grad_norm": 0.41269883049053624, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5471, | |
| "step": 2430 | |
| }, | |
| { | |
| "epoch": 2.780626780626781, | |
| "grad_norm": 0.3894335667283599, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5468, | |
| "step": 2440 | |
| }, | |
| { | |
| "epoch": 2.792022792022792, | |
| "grad_norm": 0.40933546113606567, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5501, | |
| "step": 2450 | |
| }, | |
| { | |
| "epoch": 2.8034188034188032, | |
| "grad_norm": 0.39714648665213204, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5444, | |
| "step": 2460 | |
| }, | |
| { | |
| "epoch": 2.814814814814815, | |
| "grad_norm": 0.40517136322070096, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5601, | |
| "step": 2470 | |
| }, | |
| { | |
| "epoch": 2.826210826210826, | |
| "grad_norm": 0.44447910033491683, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5623, | |
| "step": 2480 | |
| }, | |
| { | |
| "epoch": 2.8376068376068377, | |
| "grad_norm": 0.388103652560322, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5543, | |
| "step": 2490 | |
| }, | |
| { | |
| "epoch": 2.849002849002849, | |
| "grad_norm": 0.40171877838716236, | |
| "learning_rate": 5e-06, | |
| "loss": 0.562, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 2.8603988603988606, | |
| "grad_norm": 0.41856657884436094, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5536, | |
| "step": 2510 | |
| }, | |
| { | |
| "epoch": 2.871794871794872, | |
| "grad_norm": 0.4173395435456696, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5539, | |
| "step": 2520 | |
| }, | |
| { | |
| "epoch": 2.883190883190883, | |
| "grad_norm": 0.39093712576995243, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5601, | |
| "step": 2530 | |
| }, | |
| { | |
| "epoch": 2.8945868945868947, | |
| "grad_norm": 0.4255070470787294, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5557, | |
| "step": 2540 | |
| }, | |
| { | |
| "epoch": 2.905982905982906, | |
| "grad_norm": 0.45247644117965885, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5528, | |
| "step": 2550 | |
| }, | |
| { | |
| "epoch": 2.9173789173789175, | |
| "grad_norm": 0.41729192613775734, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5416, | |
| "step": 2560 | |
| }, | |
| { | |
| "epoch": 2.9287749287749287, | |
| "grad_norm": 0.3959874387272076, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5471, | |
| "step": 2570 | |
| }, | |
| { | |
| "epoch": 2.9401709401709404, | |
| "grad_norm": 0.40279780924522723, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5438, | |
| "step": 2580 | |
| }, | |
| { | |
| "epoch": 2.9515669515669516, | |
| "grad_norm": 0.41492112649690777, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5533, | |
| "step": 2590 | |
| }, | |
| { | |
| "epoch": 2.962962962962963, | |
| "grad_norm": 0.4072236941032463, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5446, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 2.9743589743589745, | |
| "grad_norm": 0.3967690970697916, | |
| "learning_rate": 5e-06, | |
| "loss": 0.556, | |
| "step": 2610 | |
| }, | |
| { | |
| "epoch": 2.9857549857549857, | |
| "grad_norm": 0.4004788690287786, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5571, | |
| "step": 2620 | |
| }, | |
| { | |
| "epoch": 2.9971509971509973, | |
| "grad_norm": 0.39905352277311656, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5443, | |
| "step": 2630 | |
| }, | |
| { | |
| "epoch": 2.9982905982905983, | |
| "eval_loss": 0.6213015913963318, | |
| "eval_runtime": 442.3632, | |
| "eval_samples_per_second": 26.727, | |
| "eval_steps_per_second": 0.418, | |
| "step": 2631 | |
| }, | |
| { | |
| "epoch": 2.9982905982905983, | |
| "step": 2631, | |
| "total_flos": 2758364765356032.0, | |
| "train_loss": 0.5923774672614808, | |
| "train_runtime": 70850.8498, | |
| "train_samples_per_second": 9.511, | |
| "train_steps_per_second": 0.037 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 2631, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2758364765356032.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |