| { | |
| "best_global_step": 1700, | |
| "best_metric": 0.011158278211951256, | |
| "best_model_checkpoint": "/output/x3d_finetuned_model/checkpoint-1500", | |
| "epoch": 3.0, | |
| "eval_steps": 100, | |
| "global_step": 1782, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.016842105263157894, | |
| "grad_norm": 0.2378891110420227, | |
| "learning_rate": 1.8e-05, | |
| "loss": 0.8901, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.03368421052631579, | |
| "grad_norm": 0.18149839341640472, | |
| "learning_rate": 3.8e-05, | |
| "loss": 0.7969, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.05052631578947368, | |
| "grad_norm": 0.1667049527168274, | |
| "learning_rate": 5.8e-05, | |
| "loss": 0.6762, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.06736842105263158, | |
| "grad_norm": 0.15869387984275818, | |
| "learning_rate": 7.800000000000001e-05, | |
| "loss": 0.5698, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.08421052631578947, | |
| "grad_norm": 0.16361284255981445, | |
| "learning_rate": 9.8e-05, | |
| "loss": 0.5225, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.10105263157894737, | |
| "grad_norm": 0.14269448816776276, | |
| "learning_rate": 0.000118, | |
| "loss": 0.465, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.11789473684210526, | |
| "grad_norm": 0.18330006301403046, | |
| "learning_rate": 0.000138, | |
| "loss": 0.4562, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.13473684210526315, | |
| "grad_norm": 0.20621822774410248, | |
| "learning_rate": 0.00015800000000000002, | |
| "loss": 0.4291, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.15157894736842106, | |
| "grad_norm": 0.21223391592502594, | |
| "learning_rate": 0.00017800000000000002, | |
| "loss": 0.3939, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.16842105263157894, | |
| "grad_norm": 0.19762997329235077, | |
| "learning_rate": 0.00019800000000000002, | |
| "loss": 0.3753, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.16842105263157894, | |
| "eval_loss": 0.35540345311164856, | |
| "eval_runtime": 224.1519, | |
| "eval_samples_per_second": 2.231, | |
| "eval_steps_per_second": 2.231, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.18526315789473685, | |
| "grad_norm": 0.18955057859420776, | |
| "learning_rate": 0.00019998587161376442, | |
| "loss": 0.3407, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.20210526315789473, | |
| "grad_norm": 0.24190108478069305, | |
| "learning_rate": 0.00019993703787315803, | |
| "loss": 0.346, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.21894736842105264, | |
| "grad_norm": 0.1914621889591217, | |
| "learning_rate": 0.00019985334138511237, | |
| "loss": 0.3288, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.23578947368421052, | |
| "grad_norm": 0.1650117188692093, | |
| "learning_rate": 0.00019973481134690592, | |
| "loss": 0.2942, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.25263157894736843, | |
| "grad_norm": 0.22298051416873932, | |
| "learning_rate": 0.00019958148910740063, | |
| "loss": 0.2904, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.2694736842105263, | |
| "grad_norm": 0.24592551589012146, | |
| "learning_rate": 0.0001993934281526176, | |
| "loss": 0.2918, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.2863157894736842, | |
| "grad_norm": 0.19984672963619232, | |
| "learning_rate": 0.00019917069408707848, | |
| "loss": 0.2461, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.3031578947368421, | |
| "grad_norm": 0.22812137007713318, | |
| "learning_rate": 0.00019891336461091966, | |
| "loss": 0.2577, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "grad_norm": 0.21963553130626678, | |
| "learning_rate": 0.0001986215294927868, | |
| "loss": 0.2267, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.3368421052631579, | |
| "grad_norm": 0.24446611106395721, | |
| "learning_rate": 0.00019829529053851919, | |
| "loss": 0.2412, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.3368421052631579, | |
| "eval_loss": 0.23451316356658936, | |
| "eval_runtime": 224.1089, | |
| "eval_samples_per_second": 2.231, | |
| "eval_steps_per_second": 2.231, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.35368421052631577, | |
| "grad_norm": 0.19283448159694672, | |
| "learning_rate": 0.00019793476155563507, | |
| "loss": 0.2324, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.3705263157894737, | |
| "grad_norm": 0.2276701033115387, | |
| "learning_rate": 0.00019754006831363042, | |
| "loss": 0.2055, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.3873684210526316, | |
| "grad_norm": 0.28741592168807983, | |
| "learning_rate": 0.00019711134850010432, | |
| "loss": 0.2068, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.40421052631578946, | |
| "grad_norm": 0.2498358190059662, | |
| "learning_rate": 0.00019664875167272735, | |
| "loss": 0.1945, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.42105263157894735, | |
| "grad_norm": 0.21750546991825104, | |
| "learning_rate": 0.00019615243920706853, | |
| "loss": 0.1811, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.4378947368421053, | |
| "grad_norm": 0.22553850710391998, | |
| "learning_rate": 0.00019562258424030016, | |
| "loss": 0.18, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.45473684210526316, | |
| "grad_norm": 0.2156210094690323, | |
| "learning_rate": 0.00019505937161079927, | |
| "loss": 0.1623, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.47157894736842104, | |
| "grad_norm": 0.3091757595539093, | |
| "learning_rate": 0.0001944629977936673, | |
| "loss": 0.1635, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.4884210526315789, | |
| "grad_norm": 0.23857639729976654, | |
| "learning_rate": 0.0001938336708321904, | |
| "loss": 0.1458, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.5052631578947369, | |
| "grad_norm": 0.2157812863588333, | |
| "learning_rate": 0.0001931716102652641, | |
| "loss": 0.1602, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.5052631578947369, | |
| "eval_loss": 0.14944693446159363, | |
| "eval_runtime": 224.1903, | |
| "eval_samples_per_second": 2.23, | |
| "eval_steps_per_second": 2.23, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.5221052631578947, | |
| "grad_norm": 0.3185126483440399, | |
| "learning_rate": 0.00019247704705080773, | |
| "loss": 0.1531, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.5389473684210526, | |
| "grad_norm": 0.2601878345012665, | |
| "learning_rate": 0.00019175022348519554, | |
| "loss": 0.1403, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.5557894736842105, | |
| "grad_norm": 0.22638513147830963, | |
| "learning_rate": 0.00019099139311873215, | |
| "loss": 0.1176, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.5726315789473684, | |
| "grad_norm": 0.2953122854232788, | |
| "learning_rate": 0.00019020082066720245, | |
| "loss": 0.1192, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.5894736842105263, | |
| "grad_norm": 0.300016313791275, | |
| "learning_rate": 0.00018937878191952606, | |
| "loss": 0.1225, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.6063157894736843, | |
| "grad_norm": 0.21774296462535858, | |
| "learning_rate": 0.0001885255636415494, | |
| "loss": 0.1051, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.6231578947368421, | |
| "grad_norm": 0.19208350777626038, | |
| "learning_rate": 0.00018764146347600793, | |
| "loss": 0.0987, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "grad_norm": 0.2341982126235962, | |
| "learning_rate": 0.00018672678983869463, | |
| "loss": 0.1071, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.6568421052631579, | |
| "grad_norm": 0.22858911752700806, | |
| "learning_rate": 0.00018578186181086997, | |
| "loss": 0.0983, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.6736842105263158, | |
| "grad_norm": 0.238422691822052, | |
| "learning_rate": 0.0001848070090279512, | |
| "loss": 0.0997, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.6736842105263158, | |
| "eval_loss": 0.09719416499137878, | |
| "eval_runtime": 224.0873, | |
| "eval_samples_per_second": 2.231, | |
| "eval_steps_per_second": 2.231, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.6905263157894737, | |
| "grad_norm": 0.23865894973278046, | |
| "learning_rate": 0.00018380257156452013, | |
| "loss": 0.0894, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.7073684210526315, | |
| "grad_norm": 0.21594248712062836, | |
| "learning_rate": 0.00018276889981568906, | |
| "loss": 0.0871, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.7242105263157895, | |
| "grad_norm": 0.26310935616493225, | |
| "learning_rate": 0.0001817063543748664, | |
| "loss": 0.0933, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.7410526315789474, | |
| "grad_norm": 0.20604920387268066, | |
| "learning_rate": 0.00018061530590796475, | |
| "loss": 0.0832, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.7578947368421053, | |
| "grad_norm": 0.2668643593788147, | |
| "learning_rate": 0.0001794961350240951, | |
| "loss": 0.0822, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.7747368421052632, | |
| "grad_norm": 0.1784186065196991, | |
| "learning_rate": 0.00017834923214279268, | |
| "loss": 0.0783, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.791578947368421, | |
| "grad_norm": 0.2419017106294632, | |
| "learning_rate": 0.00017717499735781983, | |
| "loss": 0.0727, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.8084210526315789, | |
| "grad_norm": 0.25795748829841614, | |
| "learning_rate": 0.00017597384029759475, | |
| "loss": 0.0765, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.8252631578947368, | |
| "grad_norm": 0.25549963116645813, | |
| "learning_rate": 0.00017474617998229373, | |
| "loss": 0.0678, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.8421052631578947, | |
| "grad_norm": 0.3272872865200043, | |
| "learning_rate": 0.00017349244467767708, | |
| "loss": 0.0741, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.8421052631578947, | |
| "eval_loss": 0.0688847005367279, | |
| "eval_runtime": 224.164, | |
| "eval_samples_per_second": 2.231, | |
| "eval_steps_per_second": 2.231, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.8589473684210527, | |
| "grad_norm": 0.20569807291030884, | |
| "learning_rate": 0.0001722130717456901, | |
| "loss": 0.0648, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 0.8757894736842106, | |
| "grad_norm": 0.2218085080385208, | |
| "learning_rate": 0.00017090850749189022, | |
| "loss": 0.0659, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.8926315789473684, | |
| "grad_norm": 0.18904639780521393, | |
| "learning_rate": 0.00016957920700975504, | |
| "loss": 0.0636, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 0.9094736842105263, | |
| "grad_norm": 0.24751749634742737, | |
| "learning_rate": 0.00016822563402192397, | |
| "loss": 0.0612, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.9263157894736842, | |
| "grad_norm": 0.19475597143173218, | |
| "learning_rate": 0.00016684826071843004, | |
| "loss": 0.065, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.9431578947368421, | |
| "grad_norm": 0.2451489120721817, | |
| "learning_rate": 0.00016544756759197778, | |
| "loss": 0.0588, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "grad_norm": 0.16222433745861053, | |
| "learning_rate": 0.0001640240432703247, | |
| "loss": 0.0585, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 0.9768421052631578, | |
| "grad_norm": 0.13785243034362793, | |
| "learning_rate": 0.0001625781843458249, | |
| "loss": 0.0606, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.9936842105263158, | |
| "grad_norm": 0.1904134750366211, | |
| "learning_rate": 0.00016111049520219428, | |
| "loss": 0.0491, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 1.0101052631578948, | |
| "grad_norm": 0.19465769827365875, | |
| "learning_rate": 0.00015962148783855767, | |
| "loss": 0.0535, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.0101052631578948, | |
| "eval_loss": 0.053230032324790955, | |
| "eval_runtime": 224.1426, | |
| "eval_samples_per_second": 2.231, | |
| "eval_steps_per_second": 2.231, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.0269473684210526, | |
| "grad_norm": 0.19065628945827484, | |
| "learning_rate": 0.00015811168169083955, | |
| "loss": 0.05, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 1.0437894736842106, | |
| "grad_norm": 0.20831789076328278, | |
| "learning_rate": 0.00015658160345056023, | |
| "loss": 0.0493, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 1.0606315789473684, | |
| "grad_norm": 0.12762245535850525, | |
| "learning_rate": 0.000155031786881101, | |
| "loss": 0.0461, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 1.0774736842105264, | |
| "grad_norm": 0.14034190773963928, | |
| "learning_rate": 0.0001534627726315023, | |
| "loss": 0.0437, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 1.0943157894736841, | |
| "grad_norm": 0.21654851734638214, | |
| "learning_rate": 0.00015187510804786012, | |
| "loss": 0.0417, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 1.1111578947368421, | |
| "grad_norm": 0.21853309869766235, | |
| "learning_rate": 0.0001502693469823855, | |
| "loss": 0.0416, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 1.1280000000000001, | |
| "grad_norm": 0.1370641142129898, | |
| "learning_rate": 0.00014864604960019504, | |
| "loss": 0.0425, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 1.1448421052631579, | |
| "grad_norm": 0.2183496206998825, | |
| "learning_rate": 0.00014700578218389892, | |
| "loss": 0.0392, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 1.1616842105263159, | |
| "grad_norm": 0.17953278124332428, | |
| "learning_rate": 0.00014534911693605464, | |
| "loss": 0.0407, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 1.1785263157894736, | |
| "grad_norm": 0.17893248796463013, | |
| "learning_rate": 0.00014367663177955605, | |
| "loss": 0.04, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.1785263157894736, | |
| "eval_loss": 0.04435127228498459, | |
| "eval_runtime": 224.0979, | |
| "eval_samples_per_second": 2.231, | |
| "eval_steps_per_second": 2.231, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.1953684210526316, | |
| "grad_norm": 0.15027707815170288, | |
| "learning_rate": 0.00014198891015602646, | |
| "loss": 0.042, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 1.2122105263157894, | |
| "grad_norm": 0.2271127700805664, | |
| "learning_rate": 0.00014028654082228682, | |
| "loss": 0.0413, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 1.2290526315789474, | |
| "grad_norm": 0.16139471530914307, | |
| "learning_rate": 0.00013857011764496942, | |
| "loss": 0.0415, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 1.2458947368421052, | |
| "grad_norm": 0.17120322585105896, | |
| "learning_rate": 0.0001368402393933495, | |
| "loss": 0.0444, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 1.2627368421052632, | |
| "grad_norm": 0.12668217718601227, | |
| "learning_rate": 0.00013509750953046606, | |
| "loss": 0.0359, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 1.279578947368421, | |
| "grad_norm": 0.1568315625190735, | |
| "learning_rate": 0.00013334253600260563, | |
| "loss": 0.0375, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 1.296421052631579, | |
| "grad_norm": 0.1669214367866516, | |
| "learning_rate": 0.00013157593102722205, | |
| "loss": 0.0402, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 1.313263157894737, | |
| "grad_norm": 0.1692507565021515, | |
| "learning_rate": 0.00012979831087936598, | |
| "loss": 0.0353, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 1.3301052631578947, | |
| "grad_norm": 0.16156762838363647, | |
| "learning_rate": 0.00012801029567669926, | |
| "loss": 0.0328, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 1.3469473684210527, | |
| "grad_norm": 0.14826713502407074, | |
| "learning_rate": 0.00012621250916316864, | |
| "loss": 0.0342, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.3469473684210527, | |
| "eval_loss": 0.036476925015449524, | |
| "eval_runtime": 224.0704, | |
| "eval_samples_per_second": 2.231, | |
| "eval_steps_per_second": 2.231, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.3637894736842107, | |
| "grad_norm": 0.10823637247085571, | |
| "learning_rate": 0.00012440557849141448, | |
| "loss": 0.032, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 1.3806315789473684, | |
| "grad_norm": 0.1409875601530075, | |
| "learning_rate": 0.0001225901340039903, | |
| "loss": 0.0359, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 1.3974736842105262, | |
| "grad_norm": 0.174799844622612, | |
| "learning_rate": 0.00012076680901346981, | |
| "loss": 0.034, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 1.4143157894736842, | |
| "grad_norm": 0.14141526818275452, | |
| "learning_rate": 0.00011893623958151732, | |
| "loss": 0.0283, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 1.4311578947368422, | |
| "grad_norm": 0.24268820881843567, | |
| "learning_rate": 0.00011709906429699977, | |
| "loss": 0.0333, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 1.448, | |
| "grad_norm": 0.11979827284812927, | |
| "learning_rate": 0.00011525592405321666, | |
| "loss": 0.0286, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 1.464842105263158, | |
| "grad_norm": 0.12912440299987793, | |
| "learning_rate": 0.00011340746182432633, | |
| "loss": 0.0291, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 1.4816842105263157, | |
| "grad_norm": 0.11993803083896637, | |
| "learning_rate": 0.00011155432244104627, | |
| "loss": 0.0241, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 1.4985263157894737, | |
| "grad_norm": 0.18345041573047638, | |
| "learning_rate": 0.00010969715236570586, | |
| "loss": 0.0293, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 1.5153684210526315, | |
| "grad_norm": 0.1686432659626007, | |
| "learning_rate": 0.00010783659946672964, | |
| "loss": 0.0304, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 1.5153684210526315, | |
| "eval_loss": 0.031156836077570915, | |
| "eval_runtime": 224.1681, | |
| "eval_samples_per_second": 2.23, | |
| "eval_steps_per_second": 2.23, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 1.5322105263157895, | |
| "grad_norm": 0.10962788015604019, | |
| "learning_rate": 0.00010597331279263057, | |
| "loss": 0.0283, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 1.5490526315789475, | |
| "grad_norm": 0.1417897343635559, | |
| "learning_rate": 0.00010410794234559107, | |
| "loss": 0.0271, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 1.5658947368421052, | |
| "grad_norm": 0.1917513608932495, | |
| "learning_rate": 0.00010224113885471183, | |
| "loss": 0.0248, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 1.582736842105263, | |
| "grad_norm": 0.1399783492088318, | |
| "learning_rate": 0.00010037355354900661, | |
| "loss": 0.0239, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 1.5995789473684212, | |
| "grad_norm": 0.11135450005531311, | |
| "learning_rate": 9.850583793022319e-05, | |
| "loss": 0.0244, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 1.616421052631579, | |
| "grad_norm": 0.11133313179016113, | |
| "learning_rate": 9.663864354556858e-05, | |
| "loss": 0.0283, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 1.6332631578947368, | |
| "grad_norm": 0.1533219963312149, | |
| "learning_rate": 9.477262176041883e-05, | |
| "loss": 0.0266, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 1.6501052631578947, | |
| "grad_norm": 0.13194741308689117, | |
| "learning_rate": 9.290842353109195e-05, | |
| "loss": 0.0265, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 1.6669473684210527, | |
| "grad_norm": 0.11617199331521988, | |
| "learning_rate": 9.104669917776383e-05, | |
| "loss": 0.0225, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 1.6837894736842105, | |
| "grad_norm": 0.11771562695503235, | |
| "learning_rate": 8.918809815760585e-05, | |
| "loss": 0.0233, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.6837894736842105, | |
| "eval_loss": 0.02681094780564308, | |
| "eval_runtime": 224.15, | |
| "eval_samples_per_second": 2.231, | |
| "eval_steps_per_second": 2.231, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.7006315789473683, | |
| "grad_norm": 0.1440223902463913, | |
| "learning_rate": 8.733326883822356e-05, | |
| "loss": 0.0252, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 1.7174736842105263, | |
| "grad_norm": 0.15115946531295776, | |
| "learning_rate": 8.548285827147568e-05, | |
| "loss": 0.0244, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 1.7343157894736843, | |
| "grad_norm": 0.10699623823165894, | |
| "learning_rate": 8.363751196775172e-05, | |
| "loss": 0.0216, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 1.751157894736842, | |
| "grad_norm": 0.10448223352432251, | |
| "learning_rate": 8.17978736707877e-05, | |
| "loss": 0.0227, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 1.768, | |
| "grad_norm": 0.12821614742279053, | |
| "learning_rate": 7.996458513309787e-05, | |
| "loss": 0.0198, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 1.784842105263158, | |
| "grad_norm": 0.1228765919804573, | |
| "learning_rate": 7.813828589210138e-05, | |
| "loss": 0.023, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 1.8016842105263158, | |
| "grad_norm": 0.1160237044095993, | |
| "learning_rate": 7.631961304702124e-05, | |
| "loss": 0.0235, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 1.8185263157894735, | |
| "grad_norm": 0.097357377409935, | |
| "learning_rate": 7.450920103663443e-05, | |
| "loss": 0.0219, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 1.8353684210526315, | |
| "grad_norm": 0.169428288936615, | |
| "learning_rate": 7.270768141794942e-05, | |
| "loss": 0.0207, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 1.8522105263157895, | |
| "grad_norm": 0.12443847209215164, | |
| "learning_rate": 7.091568264588952e-05, | |
| "loss": 0.0195, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 1.8522105263157895, | |
| "eval_loss": 0.02066013775765896, | |
| "eval_runtime": 224.1852, | |
| "eval_samples_per_second": 2.23, | |
| "eval_steps_per_second": 2.23, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 1.8690526315789473, | |
| "grad_norm": 0.11752050369977951, | |
| "learning_rate": 6.913382985405814e-05, | |
| "loss": 0.0186, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 1.8858947368421053, | |
| "grad_norm": 0.12359823286533356, | |
| "learning_rate": 6.736274463666283e-05, | |
| "loss": 0.0193, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 1.9027368421052633, | |
| "grad_norm": 0.10313016176223755, | |
| "learning_rate": 6.560304483167368e-05, | |
| "loss": 0.0191, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 1.919578947368421, | |
| "grad_norm": 0.12194198369979858, | |
| "learning_rate": 6.385534430529275e-05, | |
| "loss": 0.0189, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 1.9364210526315788, | |
| "grad_norm": 0.1172875314950943, | |
| "learning_rate": 6.212025273780815e-05, | |
| "loss": 0.0155, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 1.9532631578947368, | |
| "grad_norm": 0.09735918790102005, | |
| "learning_rate": 6.039837541090913e-05, | |
| "loss": 0.0169, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 1.9701052631578948, | |
| "grad_norm": 0.09256832301616669, | |
| "learning_rate": 5.869031299653518e-05, | |
| "loss": 0.0174, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 1.9869473684210526, | |
| "grad_norm": 0.10335566103458405, | |
| "learning_rate": 5.699666134733349e-05, | |
| "loss": 0.0171, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 2.0033684210526315, | |
| "grad_norm": 0.10647857934236526, | |
| "learning_rate": 5.5318011288797237e-05, | |
| "loss": 0.0158, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 2.0202105263157897, | |
| "grad_norm": 0.12479748576879501, | |
| "learning_rate": 5.365494841315808e-05, | |
| "loss": 0.0136, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 2.0202105263157897, | |
| "eval_loss": 0.017488960176706314, | |
| "eval_runtime": 224.1495, | |
| "eval_samples_per_second": 2.231, | |
| "eval_steps_per_second": 2.231, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 2.0370526315789474, | |
| "grad_norm": 0.09349500387907028, | |
| "learning_rate": 5.2008052875103886e-05, | |
| "loss": 0.0137, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 2.053894736842105, | |
| "grad_norm": 0.06680870801210403, | |
| "learning_rate": 5.037789918939335e-05, | |
| "loss": 0.0126, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 2.070736842105263, | |
| "grad_norm": 0.09055491536855698, | |
| "learning_rate": 4.876505603043826e-05, | |
| "loss": 0.0128, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 2.087578947368421, | |
| "grad_norm": 0.12399008870124817, | |
| "learning_rate": 4.717008603392318e-05, | |
| "loss": 0.0131, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 2.104421052631579, | |
| "grad_norm": 0.09043820202350616, | |
| "learning_rate": 4.559354560053135e-05, | |
| "loss": 0.0118, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 2.1212631578947367, | |
| "grad_norm": 0.07968771457672119, | |
| "learning_rate": 4.4035984701846234e-05, | |
| "loss": 0.0122, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 2.138105263157895, | |
| "grad_norm": 0.07125072926282883, | |
| "learning_rate": 4.2497946688495184e-05, | |
| "loss": 0.0117, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 2.1549473684210527, | |
| "grad_norm": 0.07947332412004471, | |
| "learning_rate": 4.097996810060346e-05, | |
| "loss": 0.0112, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 2.1717894736842105, | |
| "grad_norm": 0.06901393830776215, | |
| "learning_rate": 3.948257848062351e-05, | |
| "loss": 0.0119, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 2.1886315789473683, | |
| "grad_norm": 0.07422488927841187, | |
| "learning_rate": 3.8006300188605705e-05, | |
| "loss": 0.0111, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 2.1886315789473683, | |
| "eval_loss": 0.015334118157625198, | |
| "eval_runtime": 224.1161, | |
| "eval_samples_per_second": 2.231, | |
| "eval_steps_per_second": 2.231, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 2.2054736842105265, | |
| "grad_norm": 0.10787979513406754, | |
| "learning_rate": 3.655164821997451e-05, | |
| "loss": 0.0123, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 2.2223157894736842, | |
| "grad_norm": 0.07865067571401596, | |
| "learning_rate": 3.5119130025874034e-05, | |
| "loss": 0.0107, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 2.239157894736842, | |
| "grad_norm": 0.07730992138385773, | |
| "learning_rate": 3.3709245336144777e-05, | |
| "loss": 0.0112, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 2.2560000000000002, | |
| "grad_norm": 0.0723709836602211, | |
| "learning_rate": 3.232248598499459e-05, | |
| "loss": 0.0114, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 2.272842105263158, | |
| "grad_norm": 0.08348905295133591, | |
| "learning_rate": 3.09593357394236e-05, | |
| "loss": 0.01, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 2.2896842105263158, | |
| "grad_norm": 0.07650898396968842, | |
| "learning_rate": 2.9620270130463667e-05, | |
| "loss": 0.0109, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 2.3065263157894735, | |
| "grad_norm": 0.06670452654361725, | |
| "learning_rate": 2.8305756287290484e-05, | |
| "loss": 0.0114, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 2.3233684210526317, | |
| "grad_norm": 0.07205783575773239, | |
| "learning_rate": 2.7016252774267192e-05, | |
| "loss": 0.0109, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 2.3402105263157895, | |
| "grad_norm": 0.07499977201223373, | |
| "learning_rate": 2.575220943097526e-05, | |
| "loss": 0.0113, | |
| "step": 1390 | |
| }, | |
| { | |
| "epoch": 2.3570526315789473, | |
| "grad_norm": 0.07749755680561066, | |
| "learning_rate": 2.4514067215289503e-05, | |
| "loss": 0.0102, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 2.3570526315789473, | |
| "eval_loss": 0.013460199348628521, | |
| "eval_runtime": 224.1893, | |
| "eval_samples_per_second": 2.23, | |
| "eval_steps_per_second": 2.23, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 2.3738947368421055, | |
| "grad_norm": 0.07490992546081543, | |
| "learning_rate": 2.3302258049550974e-05, | |
| "loss": 0.0103, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 2.3907368421052633, | |
| "grad_norm": 0.07824037969112396, | |
| "learning_rate": 2.2117204669892198e-05, | |
| "loss": 0.0104, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 2.407578947368421, | |
| "grad_norm": 0.07291096448898315, | |
| "learning_rate": 2.0959320478766965e-05, | |
| "loss": 0.0101, | |
| "step": 1430 | |
| }, | |
| { | |
| "epoch": 2.424421052631579, | |
| "grad_norm": 0.09640032798051834, | |
| "learning_rate": 1.9829009400735977e-05, | |
| "loss": 0.011, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 2.441263157894737, | |
| "grad_norm": 0.07188956439495087, | |
| "learning_rate": 1.8726665741558923e-05, | |
| "loss": 0.0105, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 2.458105263157895, | |
| "grad_norm": 0.0596754252910614, | |
| "learning_rate": 1.765267405064206e-05, | |
| "loss": 0.009, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 2.4749473684210526, | |
| "grad_norm": 0.0846128836274147, | |
| "learning_rate": 1.6607408986889384e-05, | |
| "loss": 0.0096, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 2.4917894736842103, | |
| "grad_norm": 0.10189133137464523, | |
| "learning_rate": 1.559123518800376e-05, | |
| "loss": 0.0105, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 2.5086315789473685, | |
| "grad_norm": 0.06304220855236053, | |
| "learning_rate": 1.460450714328423e-05, | |
| "loss": 0.0104, | |
| "step": 1490 | |
| }, | |
| { | |
| "epoch": 2.5254736842105263, | |
| "grad_norm": 0.06267323344945908, | |
| "learning_rate": 1.364756906996345e-05, | |
| "loss": 0.0095, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 2.5254736842105263, | |
| "eval_loss": 0.01212456077337265, | |
| "eval_runtime": 224.2724, | |
| "eval_samples_per_second": 2.229, | |
| "eval_steps_per_second": 2.229, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 2.542315789473684, | |
| "grad_norm": 0.09089558571577072, | |
| "learning_rate": 1.2720754793128464e-05, | |
| "loss": 0.0096, | |
| "step": 1510 | |
| }, | |
| { | |
| "epoch": 2.559157894736842, | |
| "grad_norm": 0.0663435310125351, | |
| "learning_rate": 1.1824387629266742e-05, | |
| "loss": 0.0094, | |
| "step": 1520 | |
| }, | |
| { | |
| "epoch": 2.576, | |
| "grad_norm": 0.06648425757884979, | |
| "learning_rate": 1.0958780273478253e-05, | |
| "loss": 0.0095, | |
| "step": 1530 | |
| }, | |
| { | |
| "epoch": 2.592842105263158, | |
| "grad_norm": 0.09527198225259781, | |
| "learning_rate": 1.0124234690392586e-05, | |
| "loss": 0.0098, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 2.609684210526316, | |
| "grad_norm": 0.08171885460615158, | |
| "learning_rate": 9.321042008829562e-06, | |
| "loss": 0.0095, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 2.626526315789474, | |
| "grad_norm": 0.06150711327791214, | |
| "learning_rate": 8.549482420239707e-06, | |
| "loss": 0.0098, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 2.6433684210526316, | |
| "grad_norm": 0.058401718735694885, | |
| "learning_rate": 7.809825080960276e-06, | |
| "loss": 0.0096, | |
| "step": 1570 | |
| }, | |
| { | |
| "epoch": 2.6602105263157894, | |
| "grad_norm": 0.0481596402823925, | |
| "learning_rate": 7.102328018320858e-06, | |
| "loss": 0.0096, | |
| "step": 1580 | |
| }, | |
| { | |
| "epoch": 2.677052631578947, | |
| "grad_norm": 0.07530257105827332, | |
| "learning_rate": 6.4272380406313334e-06, | |
| "loss": 0.0091, | |
| "step": 1590 | |
| }, | |
| { | |
| "epoch": 2.6938947368421053, | |
| "grad_norm": 0.062257252633571625, | |
| "learning_rate": 5.784790651083405e-06, | |
| "loss": 0.0097, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 2.6938947368421053, | |
| "eval_loss": 0.011450879275798798, | |
| "eval_runtime": 224.0976, | |
| "eval_samples_per_second": 2.231, | |
| "eval_steps_per_second": 2.231, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 2.710736842105263, | |
| "grad_norm": 0.0579669252038002, | |
| "learning_rate": 5.175209965596084e-06, | |
| "loss": 0.0094, | |
| "step": 1610 | |
| }, | |
| { | |
| "epoch": 2.7275789473684213, | |
| "grad_norm": 0.06278079748153687, | |
| "learning_rate": 4.598708634633442e-06, | |
| "loss": 0.009, | |
| "step": 1620 | |
| }, | |
| { | |
| "epoch": 2.744421052631579, | |
| "grad_norm": 0.05131611227989197, | |
| "learning_rate": 4.055487769022137e-06, | |
| "loss": 0.0095, | |
| "step": 1630 | |
| }, | |
| { | |
| "epoch": 2.761263157894737, | |
| "grad_norm": 0.05207466334104538, | |
| "learning_rate": 3.545736869794458e-06, | |
| "loss": 0.0092, | |
| "step": 1640 | |
| }, | |
| { | |
| "epoch": 2.7781052631578946, | |
| "grad_norm": 0.06517709046602249, | |
| "learning_rate": 3.0696337620814364e-06, | |
| "loss": 0.0091, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 2.7949473684210524, | |
| "grad_norm": 0.06492120027542114, | |
| "learning_rate": 2.6273445330791234e-06, | |
| "loss": 0.0093, | |
| "step": 1660 | |
| }, | |
| { | |
| "epoch": 2.8117894736842106, | |
| "grad_norm": 0.06431007385253906, | |
| "learning_rate": 2.219023474109483e-06, | |
| "loss": 0.0091, | |
| "step": 1670 | |
| }, | |
| { | |
| "epoch": 2.8286315789473684, | |
| "grad_norm": 0.05567321926355362, | |
| "learning_rate": 1.8448130267962992e-06, | |
| "loss": 0.0087, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 2.845473684210526, | |
| "grad_norm": 0.08136210590600967, | |
| "learning_rate": 1.5048437333748833e-06, | |
| "loss": 0.0094, | |
| "step": 1690 | |
| }, | |
| { | |
| "epoch": 2.8623157894736844, | |
| "grad_norm": 0.08303703367710114, | |
| "learning_rate": 1.1992341911527649e-06, | |
| "loss": 0.0085, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 2.8623157894736844, | |
| "eval_loss": 0.011158278211951256, | |
| "eval_runtime": 224.1949, | |
| "eval_samples_per_second": 2.23, | |
| "eval_steps_per_second": 2.23, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 2.879157894736842, | |
| "grad_norm": 0.05584060773253441, | |
| "learning_rate": 9.280910111373553e-07, | |
| "loss": 0.0083, | |
| "step": 1710 | |
| }, | |
| { | |
| "epoch": 2.896, | |
| "grad_norm": 0.060032352805137634, | |
| "learning_rate": 6.91508780844996e-07, | |
| "loss": 0.0093, | |
| "step": 1720 | |
| }, | |
| { | |
| "epoch": 2.9128421052631577, | |
| "grad_norm": 0.054556239396333694, | |
| "learning_rate": 4.895700313044315e-07, | |
| "loss": 0.0091, | |
| "step": 1730 | |
| }, | |
| { | |
| "epoch": 2.929684210526316, | |
| "grad_norm": 0.05352412536740303, | |
| "learning_rate": 3.223452082660394e-07, | |
| "loss": 0.0089, | |
| "step": 1740 | |
| }, | |
| { | |
| "epoch": 2.9465263157894737, | |
| "grad_norm": 0.0548105351626873, | |
| "learning_rate": 1.898926476270546e-07, | |
| "loss": 0.0083, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 2.9633684210526314, | |
| "grad_norm": 0.0906362310051918, | |
| "learning_rate": 9.225855508123715e-08, | |
| "loss": 0.009, | |
| "step": 1760 | |
| }, | |
| { | |
| "epoch": 2.9802105263157896, | |
| "grad_norm": 0.053922925144433975, | |
| "learning_rate": 2.947699000021009e-08, | |
| "loss": 0.0091, | |
| "step": 1770 | |
| }, | |
| { | |
| "epoch": 2.9970526315789474, | |
| "grad_norm": 0.08347595483064651, | |
| "learning_rate": 1.5698535518748892e-09, | |
| "loss": 0.0086, | |
| "step": 1780 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 1782, | |
| "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": 2.504463303573504e+18, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |