| { | |
| "best_metric": 0.14586713910102844, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.21413276231263384, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.004282655246252677, | |
| "grad_norm": 3.160764217376709, | |
| "learning_rate": 5e-05, | |
| "loss": 2.6639, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.004282655246252677, | |
| "eval_loss": 1.5559602975845337, | |
| "eval_runtime": 199.6049, | |
| "eval_samples_per_second": 7.881, | |
| "eval_steps_per_second": 0.987, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.008565310492505354, | |
| "grad_norm": 7.239842414855957, | |
| "learning_rate": 0.0001, | |
| "loss": 5.6338, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.01284796573875803, | |
| "grad_norm": 13.343408584594727, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 9.5668, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.017130620985010708, | |
| "grad_norm": 16.45089340209961, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 11.2367, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.021413276231263382, | |
| "grad_norm": 23.170324325561523, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 13.8774, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.02569593147751606, | |
| "grad_norm": 23.8188533782959, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 16.1712, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.029978586723768737, | |
| "grad_norm": 42.79240036010742, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 25.3108, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.034261241970021415, | |
| "grad_norm": 36.134769439697266, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 22.0572, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.03854389721627409, | |
| "grad_norm": 24.382131576538086, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 8.7099, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.042826552462526764, | |
| "grad_norm": 24.774818420410156, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 9.2793, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.047109207708779445, | |
| "grad_norm": 17.21798324584961, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 7.8617, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.05139186295503212, | |
| "grad_norm": 16.688526153564453, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 8.0255, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.055674518201284794, | |
| "grad_norm": 24.14105987548828, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 9.2376, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.059957173447537475, | |
| "grad_norm": 19.978376388549805, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 5.086, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.06423982869379015, | |
| "grad_norm": 10.810022354125977, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 4.8862, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.06852248394004283, | |
| "grad_norm": 6.9038591384887695, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 4.7906, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0728051391862955, | |
| "grad_norm": 8.449569702148438, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 5.445, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.07708779443254818, | |
| "grad_norm": 14.337495803833008, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 6.6103, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.08137044967880086, | |
| "grad_norm": 25.457244873046875, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 10.0523, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.08565310492505353, | |
| "grad_norm": 52.93375015258789, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 17.4195, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.08993576017130621, | |
| "grad_norm": 10.496536254882812, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 3.515, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.09421841541755889, | |
| "grad_norm": 8.345087051391602, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 3.6381, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.09850107066381156, | |
| "grad_norm": 8.501402854919434, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 3.7853, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.10278372591006424, | |
| "grad_norm": 8.740056991577148, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 3.4082, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.10706638115631692, | |
| "grad_norm": 18.512205123901367, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 3.6867, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.10706638115631692, | |
| "eval_loss": 0.22251036763191223, | |
| "eval_runtime": 199.1833, | |
| "eval_samples_per_second": 7.897, | |
| "eval_steps_per_second": 0.989, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.11134903640256959, | |
| "grad_norm": 19.137922286987305, | |
| "learning_rate": 5e-05, | |
| "loss": 3.0908, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.11563169164882227, | |
| "grad_norm": 13.688855171203613, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 3.3774, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.11991434689507495, | |
| "grad_norm": 6.846719264984131, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 2.7852, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.12419700214132762, | |
| "grad_norm": 6.931698799133301, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 3.1304, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.1284796573875803, | |
| "grad_norm": 8.356529235839844, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 3.1389, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.13276231263383298, | |
| "grad_norm": 13.247598648071289, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 3.6286, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.13704496788008566, | |
| "grad_norm": 57.86114501953125, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 10.0856, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.14132762312633834, | |
| "grad_norm": 7.757084846496582, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 3.2319, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.145610278372591, | |
| "grad_norm": 6.383694171905518, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 2.4734, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.14989293361884368, | |
| "grad_norm": 7.215427875518799, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 2.2606, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.15417558886509636, | |
| "grad_norm": 9.813756942749023, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 1.9801, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.15845824411134904, | |
| "grad_norm": 7.98891544342041, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 2.4118, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.16274089935760172, | |
| "grad_norm": 8.596599578857422, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 2.3784, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.1670235546038544, | |
| "grad_norm": 3.399794578552246, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 1.9948, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.17130620985010706, | |
| "grad_norm": 3.525446891784668, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 2.3627, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.17558886509635974, | |
| "grad_norm": 4.740527153015137, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 2.5379, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.17987152034261242, | |
| "grad_norm": 5.45485258102417, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 2.402, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.1841541755888651, | |
| "grad_norm": 7.981726169586182, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 2.2083, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.18843683083511778, | |
| "grad_norm": 16.032129287719727, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 3.695, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.19271948608137046, | |
| "grad_norm": 14.371125221252441, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 4.4968, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.19700214132762311, | |
| "grad_norm": 5.07935094833374, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 1.9599, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.2012847965738758, | |
| "grad_norm": 6.442592144012451, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 1.7358, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.20556745182012848, | |
| "grad_norm": 7.287022590637207, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 1.9093, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.20985010706638116, | |
| "grad_norm": 9.049643516540527, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 2.0813, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.21413276231263384, | |
| "grad_norm": 16.802932739257812, | |
| "learning_rate": 0.0, | |
| "loss": 2.601, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.21413276231263384, | |
| "eval_loss": 0.14586713910102844, | |
| "eval_runtime": 199.3411, | |
| "eval_samples_per_second": 7.891, | |
| "eval_steps_per_second": 0.988, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 1, | |
| "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": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 8.227212051810877e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |