| { | |
| "best_metric": 0.396539568901062, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-2550", | |
| "epoch": 0.966824644549763, | |
| "eval_steps": 150, | |
| "global_step": 2550, | |
| "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 | |
| }, | |
| { | |
| "epoch": 0.4018957345971564, | |
| "grad_norm": 0.7516476511955261, | |
| "learning_rate": 6.689805741036036e-05, | |
| "loss": 0.7771, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 0.4056872037914692, | |
| "grad_norm": 0.7608417272567749, | |
| "learning_rate": 6.632558579328114e-05, | |
| "loss": 0.4676, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 0.409478672985782, | |
| "grad_norm": 0.6563961505889893, | |
| "learning_rate": 6.575070851401475e-05, | |
| "loss": 0.4352, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 0.4132701421800948, | |
| "grad_norm": 0.6930544376373291, | |
| "learning_rate": 6.517351028379603e-05, | |
| "loss": 0.3728, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 0.41706161137440756, | |
| "grad_norm": 0.5903217792510986, | |
| "learning_rate": 6.459407615586446e-05, | |
| "loss": 0.2605, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.4208530805687204, | |
| "grad_norm": 0.7866091728210449, | |
| "learning_rate": 6.401249151293084e-05, | |
| "loss": 0.7243, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 0.4246445497630332, | |
| "grad_norm": 0.7677907347679138, | |
| "learning_rate": 6.342884205459594e-05, | |
| "loss": 0.4912, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 0.42843601895734595, | |
| "grad_norm": 0.7357597947120667, | |
| "learning_rate": 6.284321378472204e-05, | |
| "loss": 0.4106, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 0.4322274881516588, | |
| "grad_norm": 0.6618098020553589, | |
| "learning_rate": 6.225569299875989e-05, | |
| "loss": 0.3532, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 0.43601895734597157, | |
| "grad_norm": 0.7327076196670532, | |
| "learning_rate": 6.166636627103256e-05, | |
| "loss": 0.2859, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 0.43981042654028435, | |
| "grad_norm": 0.7591701149940491, | |
| "learning_rate": 6.107532044197828e-05, | |
| "loss": 0.726, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 0.44360189573459713, | |
| "grad_norm": 0.7473875284194946, | |
| "learning_rate": 6.0482642605354075e-05, | |
| "loss": 0.4789, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 0.44739336492890996, | |
| "grad_norm": 0.7394768595695496, | |
| "learning_rate": 5.988842009540194e-05, | |
| "loss": 0.4183, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 0.45118483412322274, | |
| "grad_norm": 0.662466287612915, | |
| "learning_rate": 5.929274047397977e-05, | |
| "loss": 0.3523, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 0.4549763033175355, | |
| "grad_norm": 0.66697096824646, | |
| "learning_rate": 5.869569151765857e-05, | |
| "loss": 0.2846, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.4549763033175355, | |
| "eval_loss": 0.45658260583877563, | |
| "eval_runtime": 211.0895, | |
| "eval_samples_per_second": 21.043, | |
| "eval_steps_per_second": 5.263, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.45876777251184836, | |
| "grad_norm": 0.8443006277084351, | |
| "learning_rate": 5.809736120478817e-05, | |
| "loss": 0.7046, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 0.46255924170616114, | |
| "grad_norm": 0.7299622893333435, | |
| "learning_rate": 5.749783770253315e-05, | |
| "loss": 0.4708, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 0.4663507109004739, | |
| "grad_norm": 0.7422939538955688, | |
| "learning_rate": 5.6897209353880885e-05, | |
| "loss": 0.4123, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 0.47014218009478675, | |
| "grad_norm": 0.723355770111084, | |
| "learning_rate": 5.629556466462376e-05, | |
| "loss": 0.3656, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 0.47393364928909953, | |
| "grad_norm": 0.611301839351654, | |
| "learning_rate": 5.5692992290317366e-05, | |
| "loss": 0.2865, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 0.4777251184834123, | |
| "grad_norm": 0.7408523559570312, | |
| "learning_rate": 5.508958102321666e-05, | |
| "loss": 0.7044, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 0.4815165876777251, | |
| "grad_norm": 0.779376745223999, | |
| "learning_rate": 5.448541977919195e-05, | |
| "loss": 0.4626, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 0.48530805687203793, | |
| "grad_norm": 0.824704110622406, | |
| "learning_rate": 5.388059758462658e-05, | |
| "loss": 0.4017, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 0.4890995260663507, | |
| "grad_norm": 0.7132182717323303, | |
| "learning_rate": 5.327520356329853e-05, | |
| "loss": 0.3587, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 0.4928909952606635, | |
| "grad_norm": 0.6510176062583923, | |
| "learning_rate": 5.266932692324747e-05, | |
| "loss": 0.2709, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.4966824644549763, | |
| "grad_norm": 0.8185328245162964, | |
| "learning_rate": 5.206305694362959e-05, | |
| "loss": 0.6967, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 0.500473933649289, | |
| "grad_norm": 0.8479395508766174, | |
| "learning_rate": 5.1456482961561656e-05, | |
| "loss": 0.4754, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 0.5042654028436019, | |
| "grad_norm": 0.7257512211799622, | |
| "learning_rate": 5.084969435895691e-05, | |
| "loss": 0.4183, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 0.5080568720379147, | |
| "grad_norm": 0.6470847725868225, | |
| "learning_rate": 5.024278054935403e-05, | |
| "loss": 0.3574, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 0.5118483412322274, | |
| "grad_norm": 0.5835993885993958, | |
| "learning_rate": 4.963583096474159e-05, | |
| "loss": 0.2612, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 0.5118483412322274, | |
| "eval_loss": 0.4398421049118042, | |
| "eval_runtime": 211.1019, | |
| "eval_samples_per_second": 21.042, | |
| "eval_steps_per_second": 5.263, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 0.5156398104265403, | |
| "grad_norm": 0.7083640694618225, | |
| "learning_rate": 4.9028935042379894e-05, | |
| "loss": 0.7199, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 0.5194312796208531, | |
| "grad_norm": 0.7591987252235413, | |
| "learning_rate": 4.842218221162174e-05, | |
| "loss": 0.4614, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 0.5232227488151658, | |
| "grad_norm": 0.6956468820571899, | |
| "learning_rate": 4.78156618807346e-05, | |
| "loss": 0.4092, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 0.5270142180094787, | |
| "grad_norm": 0.6942465901374817, | |
| "learning_rate": 4.720946342372596e-05, | |
| "loss": 0.3517, | |
| "step": 1390 | |
| }, | |
| { | |
| "epoch": 0.5308056872037915, | |
| "grad_norm": 0.6259123086929321, | |
| "learning_rate": 4.660367616717337e-05, | |
| "loss": 0.258, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.5345971563981042, | |
| "grad_norm": 0.7933112978935242, | |
| "learning_rate": 4.599838937706183e-05, | |
| "loss": 0.6823, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 0.5383886255924171, | |
| "grad_norm": 0.8216676115989685, | |
| "learning_rate": 4.5393692245629936e-05, | |
| "loss": 0.4629, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 0.5421800947867299, | |
| "grad_norm": 0.6931918263435364, | |
| "learning_rate": 4.478967387822697e-05, | |
| "loss": 0.402, | |
| "step": 1430 | |
| }, | |
| { | |
| "epoch": 0.5459715639810426, | |
| "grad_norm": 0.6871898174285889, | |
| "learning_rate": 4.418642328018265e-05, | |
| "loss": 0.3666, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 0.5497630331753555, | |
| "grad_norm": 0.7060806751251221, | |
| "learning_rate": 4.3584029343691805e-05, | |
| "loss": 0.2629, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 0.5535545023696683, | |
| "grad_norm": 0.7377336025238037, | |
| "learning_rate": 4.298258083471563e-05, | |
| "loss": 0.7025, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 0.557345971563981, | |
| "grad_norm": 0.718527615070343, | |
| "learning_rate": 4.238216637990152e-05, | |
| "loss": 0.4684, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 0.5611374407582939, | |
| "grad_norm": 0.7513172626495361, | |
| "learning_rate": 4.178287445352348e-05, | |
| "loss": 0.4107, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 0.5649289099526066, | |
| "grad_norm": 0.6840953826904297, | |
| "learning_rate": 4.118479336444492e-05, | |
| "loss": 0.3441, | |
| "step": 1490 | |
| }, | |
| { | |
| "epoch": 0.5687203791469194, | |
| "grad_norm": 0.5901861190795898, | |
| "learning_rate": 4.058801124310595e-05, | |
| "loss": 0.2717, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.5687203791469194, | |
| "eval_loss": 0.43063661456108093, | |
| "eval_runtime": 211.4062, | |
| "eval_samples_per_second": 21.012, | |
| "eval_steps_per_second": 5.255, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.5725118483412323, | |
| "grad_norm": 0.7785443067550659, | |
| "learning_rate": 3.999261602853686e-05, | |
| "loss": 0.6699, | |
| "step": 1510 | |
| }, | |
| { | |
| "epoch": 0.576303317535545, | |
| "grad_norm": 0.6982720494270325, | |
| "learning_rate": 3.93986954553998e-05, | |
| "loss": 0.4564, | |
| "step": 1520 | |
| }, | |
| { | |
| "epoch": 0.5800947867298578, | |
| "grad_norm": 0.7283275127410889, | |
| "learning_rate": 3.880633704106066e-05, | |
| "loss": 0.4075, | |
| "step": 1530 | |
| }, | |
| { | |
| "epoch": 0.5838862559241706, | |
| "grad_norm": 0.7250307202339172, | |
| "learning_rate": 3.821562807269284e-05, | |
| "loss": 0.3547, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 0.5876777251184834, | |
| "grad_norm": 0.8150220513343811, | |
| "learning_rate": 3.762665559441513e-05, | |
| "loss": 0.2715, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 0.5914691943127962, | |
| "grad_norm": 0.6675704717636108, | |
| "learning_rate": 3.703950639446525e-05, | |
| "loss": 0.6556, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 0.595260663507109, | |
| "grad_norm": 0.7834139466285706, | |
| "learning_rate": 3.6454266992411084e-05, | |
| "loss": 0.4595, | |
| "step": 1570 | |
| }, | |
| { | |
| "epoch": 0.5990521327014218, | |
| "grad_norm": 0.6742093563079834, | |
| "learning_rate": 3.5871023626401605e-05, | |
| "loss": 0.3832, | |
| "step": 1580 | |
| }, | |
| { | |
| "epoch": 0.6028436018957346, | |
| "grad_norm": 0.6419682502746582, | |
| "learning_rate": 3.5289862240459255e-05, | |
| "loss": 0.3495, | |
| "step": 1590 | |
| }, | |
| { | |
| "epoch": 0.6066350710900474, | |
| "grad_norm": 0.6275917291641235, | |
| "learning_rate": 3.4710868471815586e-05, | |
| "loss": 0.2515, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.6104265402843602, | |
| "grad_norm": 0.7566835284233093, | |
| "learning_rate": 3.413412763829218e-05, | |
| "loss": 0.6413, | |
| "step": 1610 | |
| }, | |
| { | |
| "epoch": 0.614218009478673, | |
| "grad_norm": 0.6755979657173157, | |
| "learning_rate": 3.355972472572859e-05, | |
| "loss": 0.4296, | |
| "step": 1620 | |
| }, | |
| { | |
| "epoch": 0.6180094786729858, | |
| "grad_norm": 0.7301715612411499, | |
| "learning_rate": 3.298774437545924e-05, | |
| "loss": 0.4115, | |
| "step": 1630 | |
| }, | |
| { | |
| "epoch": 0.6218009478672986, | |
| "grad_norm": 0.6284864544868469, | |
| "learning_rate": 3.241827087184112e-05, | |
| "loss": 0.3517, | |
| "step": 1640 | |
| }, | |
| { | |
| "epoch": 0.6255924170616114, | |
| "grad_norm": 0.6837667226791382, | |
| "learning_rate": 3.185138812983393e-05, | |
| "loss": 0.2677, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 0.6255924170616114, | |
| "eval_loss": 0.4205625653266907, | |
| "eval_runtime": 211.4182, | |
| "eval_samples_per_second": 21.01, | |
| "eval_steps_per_second": 5.255, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 0.6293838862559241, | |
| "grad_norm": 0.7050827741622925, | |
| "learning_rate": 3.128717968263484e-05, | |
| "loss": 0.6622, | |
| "step": 1660 | |
| }, | |
| { | |
| "epoch": 0.633175355450237, | |
| "grad_norm": 0.7003112435340881, | |
| "learning_rate": 3.072572866936939e-05, | |
| "loss": 0.4541, | |
| "step": 1670 | |
| }, | |
| { | |
| "epoch": 0.6369668246445498, | |
| "grad_norm": 0.7300443053245544, | |
| "learning_rate": 3.016711782284058e-05, | |
| "loss": 0.4091, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 0.6407582938388625, | |
| "grad_norm": 0.6804115176200867, | |
| "learning_rate": 2.9611429457337613e-05, | |
| "loss": 0.3318, | |
| "step": 1690 | |
| }, | |
| { | |
| "epoch": 0.6445497630331753, | |
| "grad_norm": 0.6225182414054871, | |
| "learning_rate": 2.905874545650656e-05, | |
| "loss": 0.2427, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 0.6483412322274882, | |
| "grad_norm": 0.7422319650650024, | |
| "learning_rate": 2.8509147261284287e-05, | |
| "loss": 0.6641, | |
| "step": 1710 | |
| }, | |
| { | |
| "epoch": 0.6521327014218009, | |
| "grad_norm": 0.7763936519622803, | |
| "learning_rate": 2.796271585789778e-05, | |
| "loss": 0.4526, | |
| "step": 1720 | |
| }, | |
| { | |
| "epoch": 0.6559241706161137, | |
| "grad_norm": 0.6862651705741882, | |
| "learning_rate": 2.7419531765930324e-05, | |
| "loss": 0.3974, | |
| "step": 1730 | |
| }, | |
| { | |
| "epoch": 0.6597156398104266, | |
| "grad_norm": 0.6718897223472595, | |
| "learning_rate": 2.6879675026456553e-05, | |
| "loss": 0.3427, | |
| "step": 1740 | |
| }, | |
| { | |
| "epoch": 0.6635071090047393, | |
| "grad_norm": 0.5931557416915894, | |
| "learning_rate": 2.634322519024791e-05, | |
| "loss": 0.2467, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 0.6672985781990521, | |
| "grad_norm": 0.8312835097312927, | |
| "learning_rate": 2.58102613060505e-05, | |
| "loss": 0.6196, | |
| "step": 1760 | |
| }, | |
| { | |
| "epoch": 0.671090047393365, | |
| "grad_norm": 0.7139614224433899, | |
| "learning_rate": 2.5280861908936843e-05, | |
| "loss": 0.4495, | |
| "step": 1770 | |
| }, | |
| { | |
| "epoch": 0.6748815165876777, | |
| "grad_norm": 0.7517569065093994, | |
| "learning_rate": 2.4755105008733154e-05, | |
| "loss": 0.4067, | |
| "step": 1780 | |
| }, | |
| { | |
| "epoch": 0.6786729857819905, | |
| "grad_norm": 0.7141692638397217, | |
| "learning_rate": 2.4233068078524375e-05, | |
| "loss": 0.3508, | |
| "step": 1790 | |
| }, | |
| { | |
| "epoch": 0.6824644549763034, | |
| "grad_norm": 0.739683985710144, | |
| "learning_rate": 2.371482804323798e-05, | |
| "loss": 0.2417, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.6824644549763034, | |
| "eval_loss": 0.41478267312049866, | |
| "eval_runtime": 211.5519, | |
| "eval_samples_per_second": 20.997, | |
| "eval_steps_per_second": 5.252, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.6862559241706161, | |
| "grad_norm": 0.7674782872200012, | |
| "learning_rate": 2.3200461268308744e-05, | |
| "loss": 0.6349, | |
| "step": 1810 | |
| }, | |
| { | |
| "epoch": 0.6900473933649289, | |
| "grad_norm": 0.776074230670929, | |
| "learning_rate": 2.269004354842585e-05, | |
| "loss": 0.4471, | |
| "step": 1820 | |
| }, | |
| { | |
| "epoch": 0.6938388625592417, | |
| "grad_norm": 0.7232591509819031, | |
| "learning_rate": 2.2183650096364095e-05, | |
| "loss": 0.3975, | |
| "step": 1830 | |
| }, | |
| { | |
| "epoch": 0.6976303317535545, | |
| "grad_norm": 0.6470640897750854, | |
| "learning_rate": 2.1681355531901016e-05, | |
| "loss": 0.342, | |
| "step": 1840 | |
| }, | |
| { | |
| "epoch": 0.7014218009478673, | |
| "grad_norm": 0.5892198085784912, | |
| "learning_rate": 2.118323387082114e-05, | |
| "loss": 0.2566, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 0.70521327014218, | |
| "grad_norm": 0.7599971890449524, | |
| "learning_rate": 2.0689358514009425e-05, | |
| "loss": 0.6659, | |
| "step": 1860 | |
| }, | |
| { | |
| "epoch": 0.7090047393364929, | |
| "grad_norm": 0.717060387134552, | |
| "learning_rate": 2.0199802236635257e-05, | |
| "loss": 0.4457, | |
| "step": 1870 | |
| }, | |
| { | |
| "epoch": 0.7127962085308057, | |
| "grad_norm": 0.6696526408195496, | |
| "learning_rate": 1.971463717742854e-05, | |
| "loss": 0.4077, | |
| "step": 1880 | |
| }, | |
| { | |
| "epoch": 0.7165876777251184, | |
| "grad_norm": 0.7238730192184448, | |
| "learning_rate": 1.9233934828049884e-05, | |
| "loss": 0.3367, | |
| "step": 1890 | |
| }, | |
| { | |
| "epoch": 0.7203791469194313, | |
| "grad_norm": 0.6004287600517273, | |
| "learning_rate": 1.875776602255564e-05, | |
| "loss": 0.2508, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 0.7241706161137441, | |
| "grad_norm": 0.7491863965988159, | |
| "learning_rate": 1.828620092696038e-05, | |
| "loss": 0.6121, | |
| "step": 1910 | |
| }, | |
| { | |
| "epoch": 0.7279620853080568, | |
| "grad_norm": 0.7434119582176208, | |
| "learning_rate": 1.781930902889741e-05, | |
| "loss": 0.4215, | |
| "step": 1920 | |
| }, | |
| { | |
| "epoch": 0.7317535545023697, | |
| "grad_norm": 0.6918310523033142, | |
| "learning_rate": 1.735715912737946e-05, | |
| "loss": 0.3903, | |
| "step": 1930 | |
| }, | |
| { | |
| "epoch": 0.7355450236966825, | |
| "grad_norm": 0.6157026886940002, | |
| "learning_rate": 1.6899819322660744e-05, | |
| "loss": 0.3268, | |
| "step": 1940 | |
| }, | |
| { | |
| "epoch": 0.7393364928909952, | |
| "grad_norm": 0.757264256477356, | |
| "learning_rate": 1.6447357006202074e-05, | |
| "loss": 0.2544, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 0.7393364928909952, | |
| "eval_loss": 0.40772125124931335, | |
| "eval_runtime": 211.58, | |
| "eval_samples_per_second": 20.994, | |
| "eval_steps_per_second": 5.251, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 0.7431279620853081, | |
| "grad_norm": 0.7177047729492188, | |
| "learning_rate": 1.5999838850740295e-05, | |
| "loss": 0.5998, | |
| "step": 1960 | |
| }, | |
| { | |
| "epoch": 0.7469194312796209, | |
| "grad_norm": 0.7692488431930542, | |
| "learning_rate": 1.555733080046378e-05, | |
| "loss": 0.4557, | |
| "step": 1970 | |
| }, | |
| { | |
| "epoch": 0.7507109004739336, | |
| "grad_norm": 0.7131124138832092, | |
| "learning_rate": 1.5119898061295162e-05, | |
| "loss": 0.3787, | |
| "step": 1980 | |
| }, | |
| { | |
| "epoch": 0.7545023696682465, | |
| "grad_norm": 0.7252326011657715, | |
| "learning_rate": 1.468760509128288e-05, | |
| "loss": 0.3477, | |
| "step": 1990 | |
| }, | |
| { | |
| "epoch": 0.7582938388625592, | |
| "grad_norm": 0.6361256241798401, | |
| "learning_rate": 1.4260515591103002e-05, | |
| "loss": 0.2685, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.762085308056872, | |
| "grad_norm": 0.741794228553772, | |
| "learning_rate": 1.3838692494672462e-05, | |
| "loss": 0.6092, | |
| "step": 2010 | |
| }, | |
| { | |
| "epoch": 0.7658767772511849, | |
| "grad_norm": 0.7934831976890564, | |
| "learning_rate": 1.3422197959875615e-05, | |
| "loss": 0.4335, | |
| "step": 2020 | |
| }, | |
| { | |
| "epoch": 0.7696682464454976, | |
| "grad_norm": 0.7226603031158447, | |
| "learning_rate": 1.3011093359404725e-05, | |
| "loss": 0.3835, | |
| "step": 2030 | |
| }, | |
| { | |
| "epoch": 0.7734597156398104, | |
| "grad_norm": 0.7291485667228699, | |
| "learning_rate": 1.2605439271716517e-05, | |
| "loss": 0.3368, | |
| "step": 2040 | |
| }, | |
| { | |
| "epoch": 0.7772511848341233, | |
| "grad_norm": 0.47125428915023804, | |
| "learning_rate": 1.220529547210556e-05, | |
| "loss": 0.239, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 0.781042654028436, | |
| "grad_norm": 0.7346218824386597, | |
| "learning_rate": 1.181072092389608e-05, | |
| "loss": 0.5992, | |
| "step": 2060 | |
| }, | |
| { | |
| "epoch": 0.7848341232227488, | |
| "grad_norm": 0.7117639780044556, | |
| "learning_rate": 1.1421773769753386e-05, | |
| "loss": 0.4201, | |
| "step": 2070 | |
| }, | |
| { | |
| "epoch": 0.7886255924170616, | |
| "grad_norm": 0.7014518976211548, | |
| "learning_rate": 1.1038511323116208e-05, | |
| "loss": 0.387, | |
| "step": 2080 | |
| }, | |
| { | |
| "epoch": 0.7924170616113744, | |
| "grad_norm": 0.6080646514892578, | |
| "learning_rate": 1.066099005975132e-05, | |
| "loss": 0.3142, | |
| "step": 2090 | |
| }, | |
| { | |
| "epoch": 0.7962085308056872, | |
| "grad_norm": 0.7223226428031921, | |
| "learning_rate": 1.0289265609431536e-05, | |
| "loss": 0.2375, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 0.7962085308056872, | |
| "eval_loss": 0.40230637788772583, | |
| "eval_runtime": 211.0367, | |
| "eval_samples_per_second": 21.048, | |
| "eval_steps_per_second": 5.264, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": 0.7154859900474548, | |
| "learning_rate": 9.923392747738264e-06, | |
| "loss": 0.6162, | |
| "step": 2110 | |
| }, | |
| { | |
| "epoch": 0.8037914691943128, | |
| "grad_norm": 0.7427191734313965, | |
| "learning_rate": 9.563425387990149e-06, | |
| "loss": 0.4395, | |
| "step": 2120 | |
| }, | |
| { | |
| "epoch": 0.8075829383886256, | |
| "grad_norm": 0.6783840656280518, | |
| "learning_rate": 9.209416573298567e-06, | |
| "loss": 0.3985, | |
| "step": 2130 | |
| }, | |
| { | |
| "epoch": 0.8113744075829384, | |
| "grad_norm": 0.7031378149986267, | |
| "learning_rate": 8.861418468751542e-06, | |
| "loss": 0.3239, | |
| "step": 2140 | |
| }, | |
| { | |
| "epoch": 0.8151658767772512, | |
| "grad_norm": 0.7050457000732422, | |
| "learning_rate": 8.51948235372686e-06, | |
| "loss": 0.2472, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 0.818957345971564, | |
| "grad_norm": 0.7675678133964539, | |
| "learning_rate": 8.183658614335754e-06, | |
| "loss": 0.6221, | |
| "step": 2160 | |
| }, | |
| { | |
| "epoch": 0.8227488151658767, | |
| "grad_norm": 0.7096587419509888, | |
| "learning_rate": 7.853996735998353e-06, | |
| "loss": 0.404, | |
| "step": 2170 | |
| }, | |
| { | |
| "epoch": 0.8265402843601896, | |
| "grad_norm": 0.7109266519546509, | |
| "learning_rate": 7.530545296151642e-06, | |
| "loss": 0.3859, | |
| "step": 2180 | |
| }, | |
| { | |
| "epoch": 0.8303317535545024, | |
| "grad_norm": 0.6554428339004517, | |
| "learning_rate": 7.213351957091369e-06, | |
| "loss": 0.3142, | |
| "step": 2190 | |
| }, | |
| { | |
| "epoch": 0.8341232227488151, | |
| "grad_norm": 0.5105351805686951, | |
| "learning_rate": 6.902463458948738e-06, | |
| "loss": 0.2497, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 0.837914691943128, | |
| "grad_norm": 0.8070971965789795, | |
| "learning_rate": 6.597925612802969e-06, | |
| "loss": 0.6438, | |
| "step": 2210 | |
| }, | |
| { | |
| "epoch": 0.8417061611374408, | |
| "grad_norm": 0.8927067518234253, | |
| "learning_rate": 6.299783293930844e-06, | |
| "loss": 0.4307, | |
| "step": 2220 | |
| }, | |
| { | |
| "epoch": 0.8454976303317535, | |
| "grad_norm": 0.6909337043762207, | |
| "learning_rate": 6.008080435194074e-06, | |
| "loss": 0.3953, | |
| "step": 2230 | |
| }, | |
| { | |
| "epoch": 0.8492890995260663, | |
| "grad_norm": 0.7040910720825195, | |
| "learning_rate": 5.722860020565551e-06, | |
| "loss": 0.3385, | |
| "step": 2240 | |
| }, | |
| { | |
| "epoch": 0.8530805687203792, | |
| "grad_norm": 0.5680156350135803, | |
| "learning_rate": 5.444164078795444e-06, | |
| "loss": 0.247, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 0.8530805687203792, | |
| "eval_loss": 0.39911842346191406, | |
| "eval_runtime": 211.2832, | |
| "eval_samples_per_second": 21.024, | |
| "eval_steps_per_second": 5.258, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 0.8568720379146919, | |
| "grad_norm": 0.7242756485939026, | |
| "learning_rate": 5.17203367721798e-06, | |
| "loss": 0.617, | |
| "step": 2260 | |
| }, | |
| { | |
| "epoch": 0.8606635071090047, | |
| "grad_norm": 0.7452470660209656, | |
| "learning_rate": 4.906508915700081e-06, | |
| "loss": 0.4308, | |
| "step": 2270 | |
| }, | |
| { | |
| "epoch": 0.8644549763033176, | |
| "grad_norm": 0.6811374425888062, | |
| "learning_rate": 4.647628920732294e-06, | |
| "loss": 0.368, | |
| "step": 2280 | |
| }, | |
| { | |
| "epoch": 0.8682464454976303, | |
| "grad_norm": 0.6746857762336731, | |
| "learning_rate": 4.395431839663378e-06, | |
| "loss": 0.3232, | |
| "step": 2290 | |
| }, | |
| { | |
| "epoch": 0.8720379146919431, | |
| "grad_norm": 0.6928372979164124, | |
| "learning_rate": 4.149954835079067e-06, | |
| "loss": 0.2431, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 0.875829383886256, | |
| "grad_norm": 0.6891263127326965, | |
| "learning_rate": 3.911234079325954e-06, | |
| "loss": 0.6067, | |
| "step": 2310 | |
| }, | |
| { | |
| "epoch": 0.8796208530805687, | |
| "grad_norm": 0.7079217433929443, | |
| "learning_rate": 3.679304749181328e-06, | |
| "loss": 0.4293, | |
| "step": 2320 | |
| }, | |
| { | |
| "epoch": 0.8834123222748815, | |
| "grad_norm": 0.7635899782180786, | |
| "learning_rate": 3.4542010206696674e-06, | |
| "loss": 0.3754, | |
| "step": 2330 | |
| }, | |
| { | |
| "epoch": 0.8872037914691943, | |
| "grad_norm": 0.710638165473938, | |
| "learning_rate": 3.2359560640265963e-06, | |
| "loss": 0.3347, | |
| "step": 2340 | |
| }, | |
| { | |
| "epoch": 0.8909952606635071, | |
| "grad_norm": 0.5463706851005554, | |
| "learning_rate": 3.024602038811164e-06, | |
| "loss": 0.2286, | |
| "step": 2350 | |
| }, | |
| { | |
| "epoch": 0.8947867298578199, | |
| "grad_norm": 0.7083713412284851, | |
| "learning_rate": 2.820170089166835e-06, | |
| "loss": 0.6061, | |
| "step": 2360 | |
| }, | |
| { | |
| "epoch": 0.8985781990521327, | |
| "grad_norm": 0.8036705255508423, | |
| "learning_rate": 2.622690339232342e-06, | |
| "loss": 0.4524, | |
| "step": 2370 | |
| }, | |
| { | |
| "epoch": 0.9023696682464455, | |
| "grad_norm": 0.6927635073661804, | |
| "learning_rate": 2.432191888702684e-06, | |
| "loss": 0.3962, | |
| "step": 2380 | |
| }, | |
| { | |
| "epoch": 0.9061611374407583, | |
| "grad_norm": 0.686084508895874, | |
| "learning_rate": 2.2487028085411035e-06, | |
| "loss": 0.3254, | |
| "step": 2390 | |
| }, | |
| { | |
| "epoch": 0.909952606635071, | |
| "grad_norm": 0.559173047542572, | |
| "learning_rate": 2.0722501368427736e-06, | |
| "loss": 0.2291, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 0.909952606635071, | |
| "eval_loss": 0.39714062213897705, | |
| "eval_runtime": 211.4195, | |
| "eval_samples_per_second": 21.01, | |
| "eval_steps_per_second": 5.255, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 0.9137440758293839, | |
| "grad_norm": 0.7534606456756592, | |
| "learning_rate": 1.9028598748504767e-06, | |
| "loss": 0.631, | |
| "step": 2410 | |
| }, | |
| { | |
| "epoch": 0.9175355450236967, | |
| "grad_norm": 0.7881170511245728, | |
| "learning_rate": 1.7405569831232704e-06, | |
| "loss": 0.4308, | |
| "step": 2420 | |
| }, | |
| { | |
| "epoch": 0.9213270142180094, | |
| "grad_norm": 0.7743288278579712, | |
| "learning_rate": 1.5853653778583666e-06, | |
| "loss": 0.3928, | |
| "step": 2430 | |
| }, | |
| { | |
| "epoch": 0.9251184834123223, | |
| "grad_norm": 0.6832749247550964, | |
| "learning_rate": 1.437307927366971e-06, | |
| "loss": 0.3336, | |
| "step": 2440 | |
| }, | |
| { | |
| "epoch": 0.9289099526066351, | |
| "grad_norm": 0.6585612297058105, | |
| "learning_rate": 1.2964064487045236e-06, | |
| "loss": 0.2391, | |
| "step": 2450 | |
| }, | |
| { | |
| "epoch": 0.9327014218009478, | |
| "grad_norm": 0.7330191135406494, | |
| "learning_rate": 1.162681704455798e-06, | |
| "loss": 0.6028, | |
| "step": 2460 | |
| }, | |
| { | |
| "epoch": 0.9364928909952607, | |
| "grad_norm": 0.8107926249504089, | |
| "learning_rate": 1.036153399675488e-06, | |
| "loss": 0.4511, | |
| "step": 2470 | |
| }, | |
| { | |
| "epoch": 0.9402843601895735, | |
| "grad_norm": 0.7075092792510986, | |
| "learning_rate": 9.168401789845183e-07, | |
| "loss": 0.3733, | |
| "step": 2480 | |
| }, | |
| { | |
| "epoch": 0.9440758293838862, | |
| "grad_norm": 0.6632401347160339, | |
| "learning_rate": 8.04759623822654e-07, | |
| "loss": 0.3243, | |
| "step": 2490 | |
| }, | |
| { | |
| "epoch": 0.9478672985781991, | |
| "grad_norm": 0.6346734166145325, | |
| "learning_rate": 6.999282498578174e-07, | |
| "loss": 0.2299, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.9516587677725118, | |
| "grad_norm": 0.7297029495239258, | |
| "learning_rate": 6.023615045523844e-07, | |
| "loss": 0.6426, | |
| "step": 2510 | |
| }, | |
| { | |
| "epoch": 0.9554502369668246, | |
| "grad_norm": 0.6962762475013733, | |
| "learning_rate": 5.120737648869389e-07, | |
| "loss": 0.4379, | |
| "step": 2520 | |
| }, | |
| { | |
| "epoch": 0.9592417061611375, | |
| "grad_norm": 0.7509403824806213, | |
| "learning_rate": 4.290783352417338e-07, | |
| "loss": 0.3845, | |
| "step": 2530 | |
| }, | |
| { | |
| "epoch": 0.9630331753554502, | |
| "grad_norm": 0.7338268160820007, | |
| "learning_rate": 3.5338744543622627e-07, | |
| "loss": 0.332, | |
| "step": 2540 | |
| }, | |
| { | |
| "epoch": 0.966824644549763, | |
| "grad_norm": 0.5980384945869446, | |
| "learning_rate": 2.8501224892695245e-07, | |
| "loss": 0.2342, | |
| "step": 2550 | |
| }, | |
| { | |
| "epoch": 0.966824644549763, | |
| "eval_loss": 0.396539568901062, | |
| "eval_runtime": 211.4226, | |
| "eval_samples_per_second": 21.01, | |
| "eval_steps_per_second": 5.255, | |
| "step": 2550 | |
| } | |
| ], | |
| "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": 2.2657873952762757e+18, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |