| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.9954430379746837, | |
| "eval_steps": 500, | |
| "global_step": 1479, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.020253164556962026, | |
| "grad_norm": 2.885547078147127, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7569, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.04050632911392405, | |
| "grad_norm": 2.495074884201663, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6505, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.060759493670886074, | |
| "grad_norm": 1.4494679184264316, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6287, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0810126582278481, | |
| "grad_norm": 1.5946667362615687, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6129, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.10126582278481013, | |
| "grad_norm": 1.9565183764150875, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6033, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.12151898734177215, | |
| "grad_norm": 1.3262566363510297, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5978, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.14177215189873418, | |
| "grad_norm": 1.3099857139734539, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5922, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.1620253164556962, | |
| "grad_norm": 1.7564267216576885, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5873, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.18227848101265823, | |
| "grad_norm": 1.7966641588811492, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5866, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.20253164556962025, | |
| "grad_norm": 1.4037139082476304, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5895, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.22278481012658227, | |
| "grad_norm": 1.2681438952944815, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5812, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.2430379746835443, | |
| "grad_norm": 1.3044060682806486, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5789, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.26329113924050634, | |
| "grad_norm": 1.9136183957269688, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5786, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.28354430379746837, | |
| "grad_norm": 2.0166518316596638, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5682, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.3037974683544304, | |
| "grad_norm": 1.5514341149552169, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5766, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.3240506329113924, | |
| "grad_norm": 1.5737143551220265, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5744, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.34430379746835443, | |
| "grad_norm": 1.7758971307975986, | |
| "learning_rate": 5e-06, | |
| "loss": 0.576, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.36455696202531646, | |
| "grad_norm": 1.580498934481851, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5728, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.3848101265822785, | |
| "grad_norm": 1.8056607278926153, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5717, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.4050632911392405, | |
| "grad_norm": 1.9109942235188584, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5662, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.4253164556962025, | |
| "grad_norm": 1.4847626120358335, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5619, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.44556962025316454, | |
| "grad_norm": 1.6919639912725837, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5674, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.46582278481012657, | |
| "grad_norm": 1.9684660452084943, | |
| "learning_rate": 5e-06, | |
| "loss": 0.566, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.4860759493670886, | |
| "grad_norm": 2.0798545843989418, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5624, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.5063291139240507, | |
| "grad_norm": 1.7839019525115993, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5674, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.5265822784810127, | |
| "grad_norm": 1.1782099652479336, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5522, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.5468354430379747, | |
| "grad_norm": 1.4390067240704327, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5621, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.5670886075949367, | |
| "grad_norm": 1.3688578881078988, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5593, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.5873417721518988, | |
| "grad_norm": 1.3176878819963564, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5601, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.6075949367088608, | |
| "grad_norm": 1.2516676639625397, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5597, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.6278481012658228, | |
| "grad_norm": 1.3155720230479686, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5657, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.6481012658227848, | |
| "grad_norm": 1.1567226384682006, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5617, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.6683544303797468, | |
| "grad_norm": 1.4117244237423334, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5615, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.6886075949367089, | |
| "grad_norm": 1.4131749561169458, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5612, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.7088607594936709, | |
| "grad_norm": 1.32228013632383, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5623, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.7291139240506329, | |
| "grad_norm": 1.2433991345816242, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5642, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.7493670886075949, | |
| "grad_norm": 1.3722330468020378, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5566, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.769620253164557, | |
| "grad_norm": 1.2335431398129195, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5531, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.789873417721519, | |
| "grad_norm": 1.178096002715601, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5558, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.810126582278481, | |
| "grad_norm": 1.1868183612045804, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5565, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.830379746835443, | |
| "grad_norm": 1.2263570817651148, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5511, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.850632911392405, | |
| "grad_norm": 1.216346948689932, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5588, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.8708860759493671, | |
| "grad_norm": 1.0539475940897078, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5524, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.8911392405063291, | |
| "grad_norm": 1.3655899315530047, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5577, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.9113924050632911, | |
| "grad_norm": 1.0751711730332192, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5491, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.9316455696202531, | |
| "grad_norm": 1.044247882147309, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5533, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.9518987341772152, | |
| "grad_norm": 1.1299698377993244, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5541, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.9721518987341772, | |
| "grad_norm": 1.5494789397341884, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5514, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.9924050632911392, | |
| "grad_norm": 1.8313289890816216, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5473, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.9984810126582279, | |
| "eval_loss": 0.06876106560230255, | |
| "eval_runtime": 503.1903, | |
| "eval_samples_per_second": 26.439, | |
| "eval_steps_per_second": 0.413, | |
| "step": 493 | |
| }, | |
| { | |
| "epoch": 1.0126582278481013, | |
| "grad_norm": 1.9002405757093357, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5063, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.0329113924050632, | |
| "grad_norm": 1.5776031756633961, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4716, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 1.0531645569620254, | |
| "grad_norm": 1.8103122731451111, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4669, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 1.0734177215189873, | |
| "grad_norm": 1.9619957868074516, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4692, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 1.0936708860759494, | |
| "grad_norm": 1.9807540470714573, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4662, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 1.1139240506329113, | |
| "grad_norm": 1.537272476547359, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4687, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 1.1341772151898735, | |
| "grad_norm": 1.4973760499322122, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4652, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 1.1544303797468354, | |
| "grad_norm": 1.7283144827000974, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4711, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 1.1746835443037975, | |
| "grad_norm": 1.5294678920220792, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4702, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 1.1949367088607594, | |
| "grad_norm": 1.4108625570691335, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4635, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 1.2151898734177216, | |
| "grad_norm": 1.5123531181966368, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4704, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.2354430379746835, | |
| "grad_norm": 1.4227674203147886, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4669, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 1.2556962025316456, | |
| "grad_norm": 1.422468712696545, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4714, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 1.2759493670886077, | |
| "grad_norm": 1.2997064899970294, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4725, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 1.2962025316455696, | |
| "grad_norm": 1.5698526220163205, | |
| "learning_rate": 5e-06, | |
| "loss": 0.473, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 1.3164556962025316, | |
| "grad_norm": 1.2841012656293609, | |
| "learning_rate": 5e-06, | |
| "loss": 0.477, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 1.3367088607594937, | |
| "grad_norm": 1.3685285973157235, | |
| "learning_rate": 5e-06, | |
| "loss": 0.466, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 1.3569620253164558, | |
| "grad_norm": 1.4366353563549255, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4804, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 1.3772151898734177, | |
| "grad_norm": 1.251696492785539, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4771, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 1.3974683544303796, | |
| "grad_norm": 1.1982910303381988, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4766, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 1.4177215189873418, | |
| "grad_norm": 1.2426575797031298, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4744, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.437974683544304, | |
| "grad_norm": 1.2190457328386777, | |
| "learning_rate": 5e-06, | |
| "loss": 0.48, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 1.4582278481012658, | |
| "grad_norm": 1.262517745038301, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4801, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 1.4784810126582277, | |
| "grad_norm": 1.2562449402121465, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4819, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 1.4987341772151899, | |
| "grad_norm": 1.2309054536068773, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4744, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 1.518987341772152, | |
| "grad_norm": 1.2673546030674252, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4776, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 1.539240506329114, | |
| "grad_norm": 1.1434431124420779, | |
| "learning_rate": 5e-06, | |
| "loss": 0.479, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 1.5594936708860758, | |
| "grad_norm": 1.3365840611159339, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4785, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 1.579746835443038, | |
| "grad_norm": 1.2618397363705225, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4786, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "grad_norm": 1.650699005818255, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4815, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 1.620253164556962, | |
| "grad_norm": 1.586705974306574, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4767, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.640506329113924, | |
| "grad_norm": 1.522128689021405, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4683, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 1.660759493670886, | |
| "grad_norm": 1.3994356199314153, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4771, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 1.6810126582278482, | |
| "grad_norm": 1.3102684894617447, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4728, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 1.70126582278481, | |
| "grad_norm": 1.108750059912028, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4744, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 1.721518987341772, | |
| "grad_norm": 1.1928750663249632, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4768, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 1.7417721518987341, | |
| "grad_norm": 1.2190705159625037, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4781, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 1.7620253164556963, | |
| "grad_norm": 1.1764688816330593, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4817, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 1.7822784810126582, | |
| "grad_norm": 1.160008536894214, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4822, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 1.80253164556962, | |
| "grad_norm": 1.2460416665279064, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4792, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 1.8227848101265822, | |
| "grad_norm": 1.1759496011631037, | |
| "learning_rate": 5e-06, | |
| "loss": 0.479, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 1.8430379746835444, | |
| "grad_norm": 1.2589996340033103, | |
| "learning_rate": 5e-06, | |
| "loss": 0.481, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 1.8632911392405065, | |
| "grad_norm": 1.2677365782140158, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4802, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 1.8835443037974684, | |
| "grad_norm": 1.1164811846995375, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4761, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 1.9037974683544303, | |
| "grad_norm": 1.1708936028637509, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4801, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 1.9240506329113924, | |
| "grad_norm": 1.4145467187216907, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4812, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 1.9443037974683546, | |
| "grad_norm": 1.4914828599337713, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4852, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 1.9645569620253165, | |
| "grad_norm": 1.4882626152132608, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4834, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 1.9848101265822784, | |
| "grad_norm": 1.223839289736079, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4831, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 1.998987341772152, | |
| "eval_loss": 0.06883130222558975, | |
| "eval_runtime": 504.1651, | |
| "eval_samples_per_second": 26.388, | |
| "eval_steps_per_second": 0.413, | |
| "step": 987 | |
| }, | |
| { | |
| "epoch": 2.0050632911392405, | |
| "grad_norm": 2.0379155308456087, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4554, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 2.0253164556962027, | |
| "grad_norm": 1.9856812523383658, | |
| "learning_rate": 5e-06, | |
| "loss": 0.3897, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 2.0455696202531644, | |
| "grad_norm": 1.4742395305323177, | |
| "learning_rate": 5e-06, | |
| "loss": 0.3854, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 2.0658227848101265, | |
| "grad_norm": 1.4432938964893065, | |
| "learning_rate": 5e-06, | |
| "loss": 0.3809, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 2.0860759493670886, | |
| "grad_norm": 1.3244721031213045, | |
| "learning_rate": 5e-06, | |
| "loss": 0.381, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 2.1063291139240508, | |
| "grad_norm": 1.2969397210110625, | |
| "learning_rate": 5e-06, | |
| "loss": 0.3791, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 2.1265822784810124, | |
| "grad_norm": 1.3889237557236214, | |
| "learning_rate": 5e-06, | |
| "loss": 0.3897, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 2.1468354430379746, | |
| "grad_norm": 1.4703130735790695, | |
| "learning_rate": 5e-06, | |
| "loss": 0.3846, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 2.1670886075949367, | |
| "grad_norm": 1.3052373259714332, | |
| "learning_rate": 5e-06, | |
| "loss": 0.3887, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 2.187341772151899, | |
| "grad_norm": 1.3708534863438968, | |
| "learning_rate": 5e-06, | |
| "loss": 0.3865, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 2.207594936708861, | |
| "grad_norm": 1.3156269439867756, | |
| "learning_rate": 5e-06, | |
| "loss": 0.3844, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 2.2278481012658227, | |
| "grad_norm": 1.4148174693846889, | |
| "learning_rate": 5e-06, | |
| "loss": 0.3937, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 2.248101265822785, | |
| "grad_norm": 1.3812950055247692, | |
| "learning_rate": 5e-06, | |
| "loss": 0.3899, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 2.268354430379747, | |
| "grad_norm": 1.3608012089126769, | |
| "learning_rate": 5e-06, | |
| "loss": 0.3924, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 2.2886075949367086, | |
| "grad_norm": 1.3253173467652029, | |
| "learning_rate": 5e-06, | |
| "loss": 0.3929, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 2.3088607594936708, | |
| "grad_norm": 1.3424810465072317, | |
| "learning_rate": 5e-06, | |
| "loss": 0.3893, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 2.329113924050633, | |
| "grad_norm": 1.4334228557784645, | |
| "learning_rate": 5e-06, | |
| "loss": 0.3955, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 2.349367088607595, | |
| "grad_norm": 2.018060885934422, | |
| "learning_rate": 5e-06, | |
| "loss": 0.3959, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 2.369620253164557, | |
| "grad_norm": 1.6895986759865973, | |
| "learning_rate": 5e-06, | |
| "loss": 0.3972, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 2.389873417721519, | |
| "grad_norm": 1.6715587539126657, | |
| "learning_rate": 5e-06, | |
| "loss": 0.3959, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 2.410126582278481, | |
| "grad_norm": 1.9121406942293506, | |
| "learning_rate": 5e-06, | |
| "loss": 0.3942, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 2.430379746835443, | |
| "grad_norm": 1.7066632002596256, | |
| "learning_rate": 5e-06, | |
| "loss": 0.3919, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 2.4506329113924052, | |
| "grad_norm": 1.5768472265423912, | |
| "learning_rate": 5e-06, | |
| "loss": 0.3915, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 2.470886075949367, | |
| "grad_norm": 1.5193798935650198, | |
| "learning_rate": 5e-06, | |
| "loss": 0.3947, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 2.491139240506329, | |
| "grad_norm": 1.3240812842714824, | |
| "learning_rate": 5e-06, | |
| "loss": 0.3944, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 2.511392405063291, | |
| "grad_norm": 1.4824424624981367, | |
| "learning_rate": 5e-06, | |
| "loss": 0.3997, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 2.5316455696202533, | |
| "grad_norm": 1.374555919545804, | |
| "learning_rate": 5e-06, | |
| "loss": 0.3933, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 2.5518987341772155, | |
| "grad_norm": 1.4729601183509637, | |
| "learning_rate": 5e-06, | |
| "loss": 0.3898, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 2.572151898734177, | |
| "grad_norm": 1.3416480856457806, | |
| "learning_rate": 5e-06, | |
| "loss": 0.3958, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 2.5924050632911393, | |
| "grad_norm": 1.3694804363466173, | |
| "learning_rate": 5e-06, | |
| "loss": 0.3983, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 2.6126582278481014, | |
| "grad_norm": 1.3754365513217537, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4032, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 2.632911392405063, | |
| "grad_norm": 1.4466028242926396, | |
| "learning_rate": 5e-06, | |
| "loss": 0.3984, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 2.6531645569620252, | |
| "grad_norm": 1.3920559082521193, | |
| "learning_rate": 5e-06, | |
| "loss": 0.3977, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 2.6734177215189874, | |
| "grad_norm": 1.3489283086614927, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4007, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 2.6936708860759495, | |
| "grad_norm": 1.3562659797143723, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4031, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 2.7139240506329116, | |
| "grad_norm": 1.3565961156694943, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4014, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 2.7341772151898733, | |
| "grad_norm": 1.2851334588574934, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4011, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 2.7544303797468355, | |
| "grad_norm": 1.2675823074442725, | |
| "learning_rate": 5e-06, | |
| "loss": 0.397, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 2.7746835443037976, | |
| "grad_norm": 1.54097380730308, | |
| "learning_rate": 5e-06, | |
| "loss": 0.403, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 2.7949367088607593, | |
| "grad_norm": 1.344725491328599, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4007, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 2.8151898734177214, | |
| "grad_norm": 1.4579046408580612, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4031, | |
| "step": 1390 | |
| }, | |
| { | |
| "epoch": 2.8354430379746836, | |
| "grad_norm": 1.407951177884183, | |
| "learning_rate": 5e-06, | |
| "loss": 0.3968, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 2.8556962025316457, | |
| "grad_norm": 1.3359063234229096, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4054, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 2.875949367088608, | |
| "grad_norm": 1.2761461564463534, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4017, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 2.8962025316455695, | |
| "grad_norm": 1.2456275639246757, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4024, | |
| "step": 1430 | |
| }, | |
| { | |
| "epoch": 2.9164556962025316, | |
| "grad_norm": 1.3059110583364901, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4048, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 2.9367088607594938, | |
| "grad_norm": 1.3374737766143971, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4137, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 2.9569620253164555, | |
| "grad_norm": 1.2720594162696406, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4019, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 2.9772151898734176, | |
| "grad_norm": 1.274749005947656, | |
| "learning_rate": 5e-06, | |
| "loss": 0.406, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 2.9954430379746837, | |
| "eval_loss": 0.07269246131181717, | |
| "eval_runtime": 506.3527, | |
| "eval_samples_per_second": 26.274, | |
| "eval_steps_per_second": 0.411, | |
| "step": 1479 | |
| }, | |
| { | |
| "epoch": 2.9954430379746837, | |
| "step": 1479, | |
| "total_flos": 2477170706350080.0, | |
| "train_loss": 0.48186860832513545, | |
| "train_runtime": 83877.5248, | |
| "train_samples_per_second": 9.04, | |
| "train_steps_per_second": 0.018 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 1479, | |
| "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": 2477170706350080.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |