| { | |
| "best_metric": 0.4649004638195038, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-1050", | |
| "epoch": 0.3981042654028436, | |
| "eval_steps": 150, | |
| "global_step": 1050, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0003791469194312796, | |
| "eval_loss": 1.7795168161392212, | |
| "eval_runtime": 209.8549, | |
| "eval_samples_per_second": 21.167, | |
| "eval_steps_per_second": 5.294, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0037914691943127963, | |
| "grad_norm": 2.3918707370758057, | |
| "learning_rate": 2e-05, | |
| "loss": 2.1878, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.007582938388625593, | |
| "grad_norm": 1.775721788406372, | |
| "learning_rate": 4e-05, | |
| "loss": 1.257, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.011374407582938388, | |
| "grad_norm": 1.3155328035354614, | |
| "learning_rate": 6e-05, | |
| "loss": 0.7683, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.015165876777251185, | |
| "grad_norm": 1.3514695167541504, | |
| "learning_rate": 8e-05, | |
| "loss": 0.5549, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.018957345971563982, | |
| "grad_norm": 1.1452535390853882, | |
| "learning_rate": 0.0001, | |
| "loss": 0.3957, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.022748815165876776, | |
| "grad_norm": 1.4056144952774048, | |
| "learning_rate": 9.999631611658893e-05, | |
| "loss": 1.3166, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.026540284360189573, | |
| "grad_norm": 1.0476895570755005, | |
| "learning_rate": 9.998526500919558e-05, | |
| "loss": 0.6856, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.03033175355450237, | |
| "grad_norm": 1.057721495628357, | |
| "learning_rate": 9.996684830625961e-05, | |
| "loss": 0.5876, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.034123222748815164, | |
| "grad_norm": 0.8883450627326965, | |
| "learning_rate": 9.99410687215805e-05, | |
| "loss": 0.5092, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.037914691943127965, | |
| "grad_norm": 1.0792176723480225, | |
| "learning_rate": 9.990793005391757e-05, | |
| "loss": 0.3727, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.04170616113744076, | |
| "grad_norm": 0.9899026155471802, | |
| "learning_rate": 9.986743718643037e-05, | |
| "loss": 1.0962, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.04549763033175355, | |
| "grad_norm": 0.9852607250213623, | |
| "learning_rate": 9.981959608595904e-05, | |
| "loss": 0.6074, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.04928909952606635, | |
| "grad_norm": 0.8935758471488953, | |
| "learning_rate": 9.976441380214499e-05, | |
| "loss": 0.5443, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.05308056872037915, | |
| "grad_norm": 0.8601885437965393, | |
| "learning_rate": 9.970189846639224e-05, | |
| "loss": 0.4588, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.05687203791469194, | |
| "grad_norm": 0.8278557658195496, | |
| "learning_rate": 9.963205929066912e-05, | |
| "loss": 0.3571, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.05687203791469194, | |
| "eval_loss": 0.6163225173950195, | |
| "eval_runtime": 211.3771, | |
| "eval_samples_per_second": 21.015, | |
| "eval_steps_per_second": 5.256, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.06066350710900474, | |
| "grad_norm": 0.9639042019844055, | |
| "learning_rate": 9.955490656615086e-05, | |
| "loss": 0.9907, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.06445497630331753, | |
| "grad_norm": 1.0571763515472412, | |
| "learning_rate": 9.947045166170315e-05, | |
| "loss": 0.6059, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.06824644549763033, | |
| "grad_norm": 0.8203420639038086, | |
| "learning_rate": 9.937870702220684e-05, | |
| "loss": 0.5407, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.07203791469194312, | |
| "grad_norm": 0.7809204459190369, | |
| "learning_rate": 9.927968616672416e-05, | |
| "loss": 0.4592, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.07582938388625593, | |
| "grad_norm": 0.6434981226921082, | |
| "learning_rate": 9.917340368650657e-05, | |
| "loss": 0.3295, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.07962085308056872, | |
| "grad_norm": 0.8934921026229858, | |
| "learning_rate": 9.905987524284471e-05, | |
| "loss": 0.9521, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.08341232227488152, | |
| "grad_norm": 0.8254252672195435, | |
| "learning_rate": 9.89391175647606e-05, | |
| "loss": 0.5738, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.08720379146919431, | |
| "grad_norm": 0.840071976184845, | |
| "learning_rate": 9.881114844654249e-05, | |
| "loss": 0.5222, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.0909952606635071, | |
| "grad_norm": 0.8142471313476562, | |
| "learning_rate": 9.867598674512288e-05, | |
| "loss": 0.4142, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.0947867298578199, | |
| "grad_norm": 0.6625562310218811, | |
| "learning_rate": 9.853365237729976e-05, | |
| "loss": 0.3158, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.0985781990521327, | |
| "grad_norm": 0.9738134145736694, | |
| "learning_rate": 9.838416631680176e-05, | |
| "loss": 0.9377, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.1023696682464455, | |
| "grad_norm": 0.919395387172699, | |
| "learning_rate": 9.822755059119765e-05, | |
| "loss": 0.5472, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.1061611374407583, | |
| "grad_norm": 0.9126551151275635, | |
| "learning_rate": 9.806382827865035e-05, | |
| "loss": 0.4959, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.10995260663507109, | |
| "grad_norm": 0.7662134766578674, | |
| "learning_rate": 9.78930235045163e-05, | |
| "loss": 0.4471, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.11374407582938388, | |
| "grad_norm": 0.6991143226623535, | |
| "learning_rate": 9.771516143779049e-05, | |
| "loss": 0.345, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.11374407582938388, | |
| "eval_loss": 0.5615507960319519, | |
| "eval_runtime": 210.9515, | |
| "eval_samples_per_second": 21.057, | |
| "eval_steps_per_second": 5.267, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.11753554502369669, | |
| "grad_norm": 0.8847883343696594, | |
| "learning_rate": 9.753026828739756e-05, | |
| "loss": 0.9371, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.12132701421800948, | |
| "grad_norm": 0.840414822101593, | |
| "learning_rate": 9.733837129832993e-05, | |
| "loss": 0.5609, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.12511848341232226, | |
| "grad_norm": 0.8552011251449585, | |
| "learning_rate": 9.713949874763296e-05, | |
| "loss": 0.4904, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.12890995260663507, | |
| "grad_norm": 0.7504507899284363, | |
| "learning_rate": 9.693367994023828e-05, | |
| "loss": 0.4276, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.13270142180094788, | |
| "grad_norm": 0.7728025317192078, | |
| "learning_rate": 9.672094520464552e-05, | |
| "loss": 0.3153, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.13649289099526066, | |
| "grad_norm": 0.8927388191223145, | |
| "learning_rate": 9.650132588845318e-05, | |
| "loss": 0.8539, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.14028436018957346, | |
| "grad_norm": 0.9280526638031006, | |
| "learning_rate": 9.627485435373948e-05, | |
| "loss": 0.5319, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.14407582938388624, | |
| "grad_norm": 0.8443691730499268, | |
| "learning_rate": 9.604156397229367e-05, | |
| "loss": 0.4799, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.14786729857819905, | |
| "grad_norm": 0.8244546055793762, | |
| "learning_rate": 9.580148912069836e-05, | |
| "loss": 0.4255, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.15165876777251186, | |
| "grad_norm": 0.587851881980896, | |
| "learning_rate": 9.555466517526405e-05, | |
| "loss": 0.3149, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.15545023696682464, | |
| "grad_norm": 0.9294399619102478, | |
| "learning_rate": 9.53011285068163e-05, | |
| "loss": 0.8398, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.15924170616113745, | |
| "grad_norm": 0.8756105303764343, | |
| "learning_rate": 9.50409164753362e-05, | |
| "loss": 0.5178, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.16303317535545023, | |
| "grad_norm": 0.7490562796592712, | |
| "learning_rate": 9.477406742445516e-05, | |
| "loss": 0.4677, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.16682464454976303, | |
| "grad_norm": 0.8731195330619812, | |
| "learning_rate": 9.450062067580488e-05, | |
| "loss": 0.4073, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.17061611374407584, | |
| "grad_norm": 0.7838053107261658, | |
| "learning_rate": 9.422061652322298e-05, | |
| "loss": 0.2986, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.17061611374407584, | |
| "eval_loss": 0.53005450963974, | |
| "eval_runtime": 211.0482, | |
| "eval_samples_per_second": 21.047, | |
| "eval_steps_per_second": 5.264, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.17440758293838862, | |
| "grad_norm": 0.840986430644989, | |
| "learning_rate": 9.393409622681559e-05, | |
| "loss": 0.8218, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.17819905213270143, | |
| "grad_norm": 0.8100599050521851, | |
| "learning_rate": 9.364110200687738e-05, | |
| "loss": 0.5342, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.1819905213270142, | |
| "grad_norm": 0.8114942908287048, | |
| "learning_rate": 9.33416770376702e-05, | |
| "loss": 0.4595, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.18578199052132702, | |
| "grad_norm": 0.6884726285934448, | |
| "learning_rate": 9.303586544106115e-05, | |
| "loss": 0.411, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.1895734597156398, | |
| "grad_norm": 0.8265155553817749, | |
| "learning_rate": 9.272371228002091e-05, | |
| "loss": 0.3095, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.1933649289099526, | |
| "grad_norm": 0.8282197117805481, | |
| "learning_rate": 9.240526355198353e-05, | |
| "loss": 0.8212, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 0.1971563981042654, | |
| "grad_norm": 0.783984899520874, | |
| "learning_rate": 9.208056618206853e-05, | |
| "loss": 0.5332, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.2009478672985782, | |
| "grad_norm": 0.7088342905044556, | |
| "learning_rate": 9.174966801616603e-05, | |
| "loss": 0.459, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 0.204739336492891, | |
| "grad_norm": 0.7358261942863464, | |
| "learning_rate": 9.141261781388664e-05, | |
| "loss": 0.3989, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.20853080568720378, | |
| "grad_norm": 0.686541736125946, | |
| "learning_rate": 9.10694652413763e-05, | |
| "loss": 0.3132, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.2123222748815166, | |
| "grad_norm": 0.8187770247459412, | |
| "learning_rate": 9.072026086399777e-05, | |
| "loss": 0.8469, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.2161137440758294, | |
| "grad_norm": 0.8380711674690247, | |
| "learning_rate": 9.03650561388796e-05, | |
| "loss": 0.5158, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 0.21990521327014217, | |
| "grad_norm": 0.7505501508712769, | |
| "learning_rate": 9.000390340733353e-05, | |
| "loss": 0.4408, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.22369668246445498, | |
| "grad_norm": 0.7203567028045654, | |
| "learning_rate": 8.963685588714185e-05, | |
| "loss": 0.3953, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 0.22748815165876776, | |
| "grad_norm": 0.6150539517402649, | |
| "learning_rate": 8.926396766471537e-05, | |
| "loss": 0.2903, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.22748815165876776, | |
| "eval_loss": 0.5122374892234802, | |
| "eval_runtime": 211.7681, | |
| "eval_samples_per_second": 20.976, | |
| "eval_steps_per_second": 5.246, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.23127962085308057, | |
| "grad_norm": 0.8199161291122437, | |
| "learning_rate": 8.888529368712357e-05, | |
| "loss": 0.8378, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 0.23507109004739338, | |
| "grad_norm": 0.7916120886802673, | |
| "learning_rate": 8.850088975399781e-05, | |
| "loss": 0.5298, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 0.23886255924170616, | |
| "grad_norm": 0.836801290512085, | |
| "learning_rate": 8.811081250930902e-05, | |
| "loss": 0.4505, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 0.24265402843601896, | |
| "grad_norm": 0.688791036605835, | |
| "learning_rate": 8.771511943302079e-05, | |
| "loss": 0.4163, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 0.24644549763033174, | |
| "grad_norm": 0.7080439925193787, | |
| "learning_rate": 8.731386883261952e-05, | |
| "loss": 0.3036, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.2502369668246445, | |
| "grad_norm": 0.7296505570411682, | |
| "learning_rate": 8.690711983452243e-05, | |
| "loss": 0.8379, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 0.25402843601895736, | |
| "grad_norm": 0.7905020117759705, | |
| "learning_rate": 8.649493237536499e-05, | |
| "loss": 0.5306, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 0.25781990521327014, | |
| "grad_norm": 0.8950763940811157, | |
| "learning_rate": 8.60773671931689e-05, | |
| "loss": 0.46, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 0.2616113744075829, | |
| "grad_norm": 0.7092387080192566, | |
| "learning_rate": 8.56544858183921e-05, | |
| "loss": 0.3971, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 0.26540284360189575, | |
| "grad_norm": 0.7552494406700134, | |
| "learning_rate": 8.522635056486181e-05, | |
| "loss": 0.2735, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.26919431279620853, | |
| "grad_norm": 0.7642441391944885, | |
| "learning_rate": 8.479302452059238e-05, | |
| "loss": 0.7899, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 0.2729857819905213, | |
| "grad_norm": 0.773184061050415, | |
| "learning_rate": 8.435457153848887e-05, | |
| "loss": 0.5101, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 0.27677725118483415, | |
| "grad_norm": 0.8441540002822876, | |
| "learning_rate": 8.391105622693793e-05, | |
| "loss": 0.4299, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 0.28056872037914693, | |
| "grad_norm": 0.6840046048164368, | |
| "learning_rate": 8.346254394028754e-05, | |
| "loss": 0.3795, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 0.2843601895734597, | |
| "grad_norm": 0.5915653705596924, | |
| "learning_rate": 8.30091007692166e-05, | |
| "loss": 0.2805, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.2843601895734597, | |
| "eval_loss": 0.49101725220680237, | |
| "eval_runtime": 211.5623, | |
| "eval_samples_per_second": 20.996, | |
| "eval_steps_per_second": 5.251, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.2881516587677725, | |
| "grad_norm": 0.8108296394348145, | |
| "learning_rate": 8.255079353099611e-05, | |
| "loss": 0.7564, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 0.2919431279620853, | |
| "grad_norm": 0.778976559638977, | |
| "learning_rate": 8.208768975964338e-05, | |
| "loss": 0.5116, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 0.2957345971563981, | |
| "grad_norm": 0.7423689961433411, | |
| "learning_rate": 8.161985769597045e-05, | |
| "loss": 0.4358, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 0.2995260663507109, | |
| "grad_norm": 0.7508371472358704, | |
| "learning_rate": 8.114736627752846e-05, | |
| "loss": 0.3686, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 0.3033175355450237, | |
| "grad_norm": 0.5939842462539673, | |
| "learning_rate": 8.067028512844929e-05, | |
| "loss": 0.2847, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.3071090047393365, | |
| "grad_norm": 0.8010008931159973, | |
| "learning_rate": 8.018868454918627e-05, | |
| "loss": 0.7743, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 0.3109004739336493, | |
| "grad_norm": 0.8660693764686584, | |
| "learning_rate": 7.970263550615469e-05, | |
| "loss": 0.5334, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 0.31469194312796206, | |
| "grad_norm": 0.708128035068512, | |
| "learning_rate": 7.921220962127487e-05, | |
| "loss": 0.4534, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 0.3184834123222749, | |
| "grad_norm": 0.7724855542182922, | |
| "learning_rate": 7.871747916141808e-05, | |
| "loss": 0.3683, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 0.3222748815165877, | |
| "grad_norm": 0.6242368817329407, | |
| "learning_rate": 7.821851702775765e-05, | |
| "loss": 0.2945, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.32606635071090045, | |
| "grad_norm": 0.8044713139533997, | |
| "learning_rate": 7.771539674502667e-05, | |
| "loss": 0.7826, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 0.3298578199052133, | |
| "grad_norm": 0.7477179765701294, | |
| "learning_rate": 7.720819245068368e-05, | |
| "loss": 0.4976, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 0.33364928909952607, | |
| "grad_norm": 0.7895752191543579, | |
| "learning_rate": 7.669697888398812e-05, | |
| "loss": 0.4432, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 0.33744075829383885, | |
| "grad_norm": 0.7435291409492493, | |
| "learning_rate": 7.618183137498709e-05, | |
| "loss": 0.3796, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 0.3412322274881517, | |
| "grad_norm": 0.8892961144447327, | |
| "learning_rate": 7.56628258334151e-05, | |
| "loss": 0.2694, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.3412322274881517, | |
| "eval_loss": 0.48085248470306396, | |
| "eval_runtime": 211.2971, | |
| "eval_samples_per_second": 21.023, | |
| "eval_steps_per_second": 5.258, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.34502369668246446, | |
| "grad_norm": 0.7861023545265198, | |
| "learning_rate": 7.514003873750836e-05, | |
| "loss": 0.7591, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 0.34881516587677724, | |
| "grad_norm": 0.7269836068153381, | |
| "learning_rate": 7.461354712273526e-05, | |
| "loss": 0.502, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 0.35260663507109, | |
| "grad_norm": 0.7629136443138123, | |
| "learning_rate": 7.408342857044484e-05, | |
| "loss": 0.4215, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 0.35639810426540286, | |
| "grad_norm": 0.668658435344696, | |
| "learning_rate": 7.354976119643472e-05, | |
| "loss": 0.3744, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 0.36018957345971564, | |
| "grad_norm": 0.6049548387527466, | |
| "learning_rate": 7.301262363944035e-05, | |
| "loss": 0.2709, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 0.3639810426540284, | |
| "grad_norm": 0.8917579650878906, | |
| "learning_rate": 7.247209504954715e-05, | |
| "loss": 0.7532, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 0.36777251184834125, | |
| "grad_norm": 0.7818393111228943, | |
| "learning_rate": 7.192825507652734e-05, | |
| "loss": 0.4742, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 0.37156398104265403, | |
| "grad_norm": 0.7396854162216187, | |
| "learning_rate": 7.138118385810313e-05, | |
| "loss": 0.4385, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 0.3753554502369668, | |
| "grad_norm": 0.8227097392082214, | |
| "learning_rate": 7.083096200813794e-05, | |
| "loss": 0.3656, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 0.3791469194312796, | |
| "grad_norm": 0.6364562511444092, | |
| "learning_rate": 7.027767060475764e-05, | |
| "loss": 0.2728, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.38293838862559243, | |
| "grad_norm": 0.7405619025230408, | |
| "learning_rate": 6.972139117840307e-05, | |
| "loss": 0.7329, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 0.3867298578199052, | |
| "grad_norm": 0.761043131351471, | |
| "learning_rate": 6.91622056998163e-05, | |
| "loss": 0.4928, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 0.390521327014218, | |
| "grad_norm": 0.7283722758293152, | |
| "learning_rate": 6.860019656796163e-05, | |
| "loss": 0.4324, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 0.3943127962085308, | |
| "grad_norm": 0.6700026392936707, | |
| "learning_rate": 6.80354465978838e-05, | |
| "loss": 0.371, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 0.3981042654028436, | |
| "grad_norm": 0.6622222065925598, | |
| "learning_rate": 6.746803900850462e-05, | |
| "loss": 0.2729, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 0.3981042654028436, | |
| "eval_loss": 0.4649004638195038, | |
| "eval_runtime": 211.8681, | |
| "eval_samples_per_second": 20.966, | |
| "eval_steps_per_second": 5.244, | |
| "step": 1050 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 2638, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 150, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 2, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 9.315071348755661e+17, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |