| { | |
| "best_metric": 0.6078431372549019, | |
| "best_model_checkpoint": "videomae-base-finetuned-kinetics-finetuned-right-hand-conflab-v3/checkpoint-826", | |
| "epoch": 7.117521367521367, | |
| "eval_steps": 500, | |
| "global_step": 936, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.010683760683760684, | |
| "grad_norm": 7.551811218261719, | |
| "learning_rate": 5.319148936170213e-06, | |
| "loss": 2.0365, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.021367521367521368, | |
| "grad_norm": 6.67141580581665, | |
| "learning_rate": 1.0638297872340426e-05, | |
| "loss": 2.0409, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.03205128205128205, | |
| "grad_norm": 7.671868801116943, | |
| "learning_rate": 1.595744680851064e-05, | |
| "loss": 2.0454, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.042735042735042736, | |
| "grad_norm": 8.299155235290527, | |
| "learning_rate": 2.1276595744680852e-05, | |
| "loss": 1.9744, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.053418803418803416, | |
| "grad_norm": 8.462949752807617, | |
| "learning_rate": 2.6595744680851064e-05, | |
| "loss": 1.9464, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0641025641025641, | |
| "grad_norm": 10.244002342224121, | |
| "learning_rate": 3.191489361702128e-05, | |
| "loss": 1.937, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.07478632478632478, | |
| "grad_norm": 5.489703178405762, | |
| "learning_rate": 3.723404255319149e-05, | |
| "loss": 1.8308, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.08547008547008547, | |
| "grad_norm": 9.307482719421387, | |
| "learning_rate": 4.2553191489361704e-05, | |
| "loss": 1.9194, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.09615384615384616, | |
| "grad_norm": 6.383068084716797, | |
| "learning_rate": 4.787234042553192e-05, | |
| "loss": 1.8826, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.10683760683760683, | |
| "grad_norm": 7.77570915222168, | |
| "learning_rate": 4.96437054631829e-05, | |
| "loss": 1.9247, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.11752136752136752, | |
| "grad_norm": 5.738762378692627, | |
| "learning_rate": 4.90498812351544e-05, | |
| "loss": 1.9096, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.12606837606837606, | |
| "eval_accuracy": 0.3333333333333333, | |
| "eval_loss": 1.688755750656128, | |
| "eval_runtime": 17.8148, | |
| "eval_samples_per_second": 11.451, | |
| "eval_steps_per_second": 1.459, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 1.0021367521367521, | |
| "grad_norm": 6.397932052612305, | |
| "learning_rate": 4.845605700712589e-05, | |
| "loss": 1.7919, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.0128205128205128, | |
| "grad_norm": 6.429988384246826, | |
| "learning_rate": 4.7862232779097386e-05, | |
| "loss": 1.7007, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 1.0235042735042734, | |
| "grad_norm": 9.103757858276367, | |
| "learning_rate": 4.7268408551068886e-05, | |
| "loss": 1.8668, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.0341880341880343, | |
| "grad_norm": 8.578359603881836, | |
| "learning_rate": 4.667458432304038e-05, | |
| "loss": 1.8187, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.044871794871795, | |
| "grad_norm": 9.773784637451172, | |
| "learning_rate": 4.6080760095011874e-05, | |
| "loss": 1.7984, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.0555555555555556, | |
| "grad_norm": 8.500809669494629, | |
| "learning_rate": 4.5486935866983374e-05, | |
| "loss": 1.6211, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 1.0662393162393162, | |
| "grad_norm": 5.273374557495117, | |
| "learning_rate": 4.4893111638954874e-05, | |
| "loss": 1.6033, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.0769230769230769, | |
| "grad_norm": 9.878400802612305, | |
| "learning_rate": 4.429928741092637e-05, | |
| "loss": 1.6822, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.0876068376068375, | |
| "grad_norm": 9.135309219360352, | |
| "learning_rate": 4.370546318289787e-05, | |
| "loss": 1.5063, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.0982905982905984, | |
| "grad_norm": 7.596296787261963, | |
| "learning_rate": 4.311163895486936e-05, | |
| "loss": 1.4128, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 1.108974358974359, | |
| "grad_norm": 7.444425582885742, | |
| "learning_rate": 4.2517814726840856e-05, | |
| "loss": 1.6052, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 1.1196581196581197, | |
| "grad_norm": 8.690657615661621, | |
| "learning_rate": 4.1923990498812356e-05, | |
| "loss": 1.628, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 1.126068376068376, | |
| "eval_accuracy": 0.4117647058823529, | |
| "eval_loss": 1.6285208463668823, | |
| "eval_runtime": 14.5186, | |
| "eval_samples_per_second": 14.051, | |
| "eval_steps_per_second": 1.791, | |
| "step": 236 | |
| }, | |
| { | |
| "epoch": 2.0042735042735043, | |
| "grad_norm": 6.66658878326416, | |
| "learning_rate": 4.133016627078385e-05, | |
| "loss": 1.5841, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 2.014957264957265, | |
| "grad_norm": 7.023474216461182, | |
| "learning_rate": 4.073634204275535e-05, | |
| "loss": 1.3114, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 2.0256410256410255, | |
| "grad_norm": 5.985867500305176, | |
| "learning_rate": 4.0142517814726843e-05, | |
| "loss": 1.3695, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 2.036324786324786, | |
| "grad_norm": 6.7717719078063965, | |
| "learning_rate": 3.954869358669834e-05, | |
| "loss": 1.4598, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 2.047008547008547, | |
| "grad_norm": 12.264374732971191, | |
| "learning_rate": 3.895486935866984e-05, | |
| "loss": 1.337, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 2.0576923076923075, | |
| "grad_norm": 10.283348083496094, | |
| "learning_rate": 3.836104513064133e-05, | |
| "loss": 1.4704, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 2.0683760683760686, | |
| "grad_norm": 9.656314849853516, | |
| "learning_rate": 3.7767220902612825e-05, | |
| "loss": 1.5234, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 2.0790598290598292, | |
| "grad_norm": 7.528780937194824, | |
| "learning_rate": 3.7173396674584325e-05, | |
| "loss": 1.4436, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 2.08974358974359, | |
| "grad_norm": 8.336195945739746, | |
| "learning_rate": 3.657957244655582e-05, | |
| "loss": 1.2449, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 2.1004273504273505, | |
| "grad_norm": 10.961182594299316, | |
| "learning_rate": 3.598574821852731e-05, | |
| "loss": 1.4239, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 2.111111111111111, | |
| "grad_norm": 7.471282482147217, | |
| "learning_rate": 3.539192399049881e-05, | |
| "loss": 1.4062, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 2.121794871794872, | |
| "grad_norm": 8.72683334350586, | |
| "learning_rate": 3.479809976247031e-05, | |
| "loss": 1.3656, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 2.126068376068376, | |
| "eval_accuracy": 0.5147058823529411, | |
| "eval_loss": 1.3947311639785767, | |
| "eval_runtime": 14.5916, | |
| "eval_samples_per_second": 13.981, | |
| "eval_steps_per_second": 1.782, | |
| "step": 354 | |
| }, | |
| { | |
| "epoch": 3.0064102564102564, | |
| "grad_norm": 10.454861640930176, | |
| "learning_rate": 3.4204275534441806e-05, | |
| "loss": 1.1968, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 3.017094017094017, | |
| "grad_norm": 7.894044876098633, | |
| "learning_rate": 3.361045130641331e-05, | |
| "loss": 1.0705, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 3.0277777777777777, | |
| "grad_norm": 11.178865432739258, | |
| "learning_rate": 3.30166270783848e-05, | |
| "loss": 1.0553, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 3.0384615384615383, | |
| "grad_norm": 13.55367374420166, | |
| "learning_rate": 3.24228028503563e-05, | |
| "loss": 0.8611, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 3.049145299145299, | |
| "grad_norm": 11.7691650390625, | |
| "learning_rate": 3.1828978622327794e-05, | |
| "loss": 1.1736, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 3.0598290598290596, | |
| "grad_norm": 9.843459129333496, | |
| "learning_rate": 3.123515439429929e-05, | |
| "loss": 0.9042, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 3.0705128205128207, | |
| "grad_norm": 12.834084510803223, | |
| "learning_rate": 3.064133016627079e-05, | |
| "loss": 1.0035, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 3.0811965811965814, | |
| "grad_norm": 11.492711067199707, | |
| "learning_rate": 3.0047505938242282e-05, | |
| "loss": 1.0545, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 3.091880341880342, | |
| "grad_norm": 11.115935325622559, | |
| "learning_rate": 2.9453681710213776e-05, | |
| "loss": 1.046, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 3.1025641025641026, | |
| "grad_norm": 11.434919357299805, | |
| "learning_rate": 2.8859857482185276e-05, | |
| "loss": 0.9765, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 3.1132478632478633, | |
| "grad_norm": 13.18517017364502, | |
| "learning_rate": 2.826603325415677e-05, | |
| "loss": 1.0194, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 3.123931623931624, | |
| "grad_norm": 9.168006896972656, | |
| "learning_rate": 2.7672209026128266e-05, | |
| "loss": 1.1498, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 3.126068376068376, | |
| "eval_accuracy": 0.5735294117647058, | |
| "eval_loss": 1.2639243602752686, | |
| "eval_runtime": 15.2962, | |
| "eval_samples_per_second": 13.337, | |
| "eval_steps_per_second": 1.7, | |
| "step": 472 | |
| }, | |
| { | |
| "epoch": 4.0085470085470085, | |
| "grad_norm": 10.556476593017578, | |
| "learning_rate": 2.7078384798099763e-05, | |
| "loss": 0.7885, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 4.019230769230769, | |
| "grad_norm": 9.74152660369873, | |
| "learning_rate": 2.648456057007126e-05, | |
| "loss": 0.6999, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 4.02991452991453, | |
| "grad_norm": 8.711644172668457, | |
| "learning_rate": 2.5890736342042754e-05, | |
| "loss": 0.7566, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 4.0405982905982905, | |
| "grad_norm": 13.662306785583496, | |
| "learning_rate": 2.5296912114014254e-05, | |
| "loss": 0.7932, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 4.051282051282051, | |
| "grad_norm": 9.280159950256348, | |
| "learning_rate": 2.4703087885985748e-05, | |
| "loss": 0.7025, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 4.061965811965812, | |
| "grad_norm": 7.840063095092773, | |
| "learning_rate": 2.4109263657957245e-05, | |
| "loss": 0.6106, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 4.072649572649572, | |
| "grad_norm": 3.8308825492858887, | |
| "learning_rate": 2.3515439429928742e-05, | |
| "loss": 0.6493, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 4.083333333333333, | |
| "grad_norm": 13.45524787902832, | |
| "learning_rate": 2.292161520190024e-05, | |
| "loss": 1.0321, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 4.094017094017094, | |
| "grad_norm": 13.148232460021973, | |
| "learning_rate": 2.2327790973871736e-05, | |
| "loss": 0.756, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 4.104700854700854, | |
| "grad_norm": 6.532124042510986, | |
| "learning_rate": 2.1733966745843233e-05, | |
| "loss": 0.8232, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 4.115384615384615, | |
| "grad_norm": 8.199164390563965, | |
| "learning_rate": 2.114014251781473e-05, | |
| "loss": 0.6284, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 4.1260683760683765, | |
| "grad_norm": 16.024168014526367, | |
| "learning_rate": 2.0546318289786223e-05, | |
| "loss": 0.6546, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 4.1260683760683765, | |
| "eval_accuracy": 0.5882352941176471, | |
| "eval_loss": 1.2053728103637695, | |
| "eval_runtime": 14.7556, | |
| "eval_samples_per_second": 13.825, | |
| "eval_steps_per_second": 1.762, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 5.010683760683761, | |
| "grad_norm": 8.120397567749023, | |
| "learning_rate": 1.995249406175772e-05, | |
| "loss": 0.5882, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 5.021367521367521, | |
| "grad_norm": 8.652383804321289, | |
| "learning_rate": 1.9358669833729217e-05, | |
| "loss": 0.584, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 5.032051282051282, | |
| "grad_norm": 13.461187362670898, | |
| "learning_rate": 1.876484560570071e-05, | |
| "loss": 0.6268, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 5.042735042735043, | |
| "grad_norm": 4.858776569366455, | |
| "learning_rate": 1.8171021377672208e-05, | |
| "loss": 0.503, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 5.053418803418803, | |
| "grad_norm": 9.537641525268555, | |
| "learning_rate": 1.7577197149643705e-05, | |
| "loss": 0.5206, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 5.064102564102564, | |
| "grad_norm": 12.624528884887695, | |
| "learning_rate": 1.6983372921615205e-05, | |
| "loss": 0.4366, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 5.0747863247863245, | |
| "grad_norm": 12.749320030212402, | |
| "learning_rate": 1.63895486935867e-05, | |
| "loss": 0.4381, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 5.085470085470085, | |
| "grad_norm": 10.724397659301758, | |
| "learning_rate": 1.5795724465558196e-05, | |
| "loss": 0.3677, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 5.096153846153846, | |
| "grad_norm": 4.257500171661377, | |
| "learning_rate": 1.5201900237529693e-05, | |
| "loss": 0.5245, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 5.1068376068376065, | |
| "grad_norm": 11.950453758239746, | |
| "learning_rate": 1.4608076009501186e-05, | |
| "loss": 0.3506, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 5.117521367521367, | |
| "grad_norm": 15.27865219116211, | |
| "learning_rate": 1.4014251781472683e-05, | |
| "loss": 0.4812, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 5.1260683760683765, | |
| "eval_accuracy": 0.5490196078431373, | |
| "eval_loss": 1.2694668769836426, | |
| "eval_runtime": 14.7973, | |
| "eval_samples_per_second": 13.786, | |
| "eval_steps_per_second": 1.757, | |
| "step": 708 | |
| }, | |
| { | |
| "epoch": 6.002136752136752, | |
| "grad_norm": 3.3596088886260986, | |
| "learning_rate": 1.3420427553444182e-05, | |
| "loss": 0.3931, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 6.012820512820513, | |
| "grad_norm": 13.172847747802734, | |
| "learning_rate": 1.2826603325415679e-05, | |
| "loss": 0.2829, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 6.023504273504273, | |
| "grad_norm": 4.362306594848633, | |
| "learning_rate": 1.2232779097387174e-05, | |
| "loss": 0.2584, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 6.034188034188034, | |
| "grad_norm": 10.034035682678223, | |
| "learning_rate": 1.163895486935867e-05, | |
| "loss": 0.4665, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 6.044871794871795, | |
| "grad_norm": 6.337015151977539, | |
| "learning_rate": 1.1045130641330167e-05, | |
| "loss": 0.4468, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 6.055555555555555, | |
| "grad_norm": 8.211027145385742, | |
| "learning_rate": 1.0451306413301664e-05, | |
| "loss": 0.2763, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 6.066239316239316, | |
| "grad_norm": 10.967971801757812, | |
| "learning_rate": 9.857482185273159e-06, | |
| "loss": 0.4814, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 6.076923076923077, | |
| "grad_norm": 4.332571506500244, | |
| "learning_rate": 9.263657957244656e-06, | |
| "loss": 0.3561, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 6.087606837606837, | |
| "grad_norm": 21.54241180419922, | |
| "learning_rate": 8.669833729216153e-06, | |
| "loss": 0.2402, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 6.098290598290598, | |
| "grad_norm": 9.541482925415039, | |
| "learning_rate": 8.07600950118765e-06, | |
| "loss": 0.4022, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 6.108974358974359, | |
| "grad_norm": 12.201172828674316, | |
| "learning_rate": 7.482185273159145e-06, | |
| "loss": 0.3603, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 6.119658119658119, | |
| "grad_norm": 2.7810683250427246, | |
| "learning_rate": 6.888361045130641e-06, | |
| "loss": 0.4631, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 6.1260683760683765, | |
| "eval_accuracy": 0.6078431372549019, | |
| "eval_loss": 1.209458351135254, | |
| "eval_runtime": 16.1617, | |
| "eval_samples_per_second": 12.622, | |
| "eval_steps_per_second": 1.609, | |
| "step": 826 | |
| }, | |
| { | |
| "epoch": 7.004273504273504, | |
| "grad_norm": 9.450981140136719, | |
| "learning_rate": 6.294536817102138e-06, | |
| "loss": 0.4533, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 7.014957264957265, | |
| "grad_norm": 8.65283489227295, | |
| "learning_rate": 5.700712589073634e-06, | |
| "loss": 0.2189, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 7.0256410256410255, | |
| "grad_norm": 2.8259940147399902, | |
| "learning_rate": 5.1068883610451305e-06, | |
| "loss": 0.266, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 7.036324786324786, | |
| "grad_norm": 11.976675033569336, | |
| "learning_rate": 4.513064133016627e-06, | |
| "loss": 0.3194, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 7.047008547008547, | |
| "grad_norm": 9.489921569824219, | |
| "learning_rate": 3.919239904988124e-06, | |
| "loss": 0.3841, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 7.0576923076923075, | |
| "grad_norm": 5.314388751983643, | |
| "learning_rate": 3.3254156769596202e-06, | |
| "loss": 0.2449, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 7.068376068376068, | |
| "grad_norm": 20.23029327392578, | |
| "learning_rate": 2.7315914489311168e-06, | |
| "loss": 0.314, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 7.079059829059829, | |
| "grad_norm": 10.66151237487793, | |
| "learning_rate": 2.137767220902613e-06, | |
| "loss": 0.254, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 7.089743589743589, | |
| "grad_norm": 5.35306978225708, | |
| "learning_rate": 1.5439429928741092e-06, | |
| "loss": 0.4233, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 7.10042735042735, | |
| "grad_norm": 6.157220363616943, | |
| "learning_rate": 9.501187648456058e-07, | |
| "loss": 0.343, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 7.111111111111111, | |
| "grad_norm": 12.305887222290039, | |
| "learning_rate": 3.5629453681710215e-07, | |
| "loss": 0.2311, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 7.117521367521367, | |
| "eval_accuracy": 0.5980392156862745, | |
| "eval_loss": 1.1960477828979492, | |
| "eval_runtime": 14.4874, | |
| "eval_samples_per_second": 14.081, | |
| "eval_steps_per_second": 1.795, | |
| "step": 936 | |
| }, | |
| { | |
| "epoch": 7.117521367521367, | |
| "step": 936, | |
| "total_flos": 9.31358507420772e+18, | |
| "train_loss": 0.996516230269375, | |
| "train_runtime": 1255.4154, | |
| "train_samples_per_second": 5.965, | |
| "train_steps_per_second": 0.746 | |
| }, | |
| { | |
| "epoch": 7.117521367521367, | |
| "eval_accuracy": 0.5812807881773399, | |
| "eval_loss": 1.3488672971725464, | |
| "eval_runtime": 28.5732, | |
| "eval_samples_per_second": 7.105, | |
| "eval_steps_per_second": 0.91, | |
| "step": 936 | |
| }, | |
| { | |
| "epoch": 7.117521367521367, | |
| "eval_accuracy": 0.5812807881773399, | |
| "eval_loss": 1.3488672971725464, | |
| "eval_runtime": 14.5651, | |
| "eval_samples_per_second": 13.937, | |
| "eval_steps_per_second": 1.785, | |
| "step": 936 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 936, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 9223372036854775807, | |
| "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": 9.31358507420772e+18, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |