| { | |
| "best_metric": 2.21439266204834, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.8264462809917356, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01652892561983471, | |
| "grad_norm": 8.88481330871582, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 4.7285, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.01652892561983471, | |
| "eval_loss": 5.146731376647949, | |
| "eval_runtime": 4.3989, | |
| "eval_samples_per_second": 5.911, | |
| "eval_steps_per_second": 2.955, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.03305785123966942, | |
| "grad_norm": 11.944966316223145, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 5.53, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.049586776859504134, | |
| "grad_norm": 8.875107765197754, | |
| "learning_rate": 0.0001, | |
| "loss": 4.5313, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.06611570247933884, | |
| "grad_norm": 9.8264741897583, | |
| "learning_rate": 9.992667069255619e-05, | |
| "loss": 4.5137, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.08264462809917356, | |
| "grad_norm": 10.575345039367676, | |
| "learning_rate": 9.970689785771798e-05, | |
| "loss": 4.0278, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.09917355371900827, | |
| "grad_norm": 12.0147123336792, | |
| "learning_rate": 9.934132612707632e-05, | |
| "loss": 3.6279, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.11570247933884298, | |
| "grad_norm": 9.258858680725098, | |
| "learning_rate": 9.883102778550434e-05, | |
| "loss": 3.2625, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.1322314049586777, | |
| "grad_norm": 8.09635066986084, | |
| "learning_rate": 9.817749962596115e-05, | |
| "loss": 2.8438, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.1487603305785124, | |
| "grad_norm": 9.932831764221191, | |
| "learning_rate": 9.738265855914013e-05, | |
| "loss": 2.8447, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.1652892561983471, | |
| "grad_norm": 10.23928451538086, | |
| "learning_rate": 9.644883599083958e-05, | |
| "loss": 2.7394, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.18181818181818182, | |
| "grad_norm": 9.848809242248535, | |
| "learning_rate": 9.537877098354786e-05, | |
| "loss": 2.5748, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.19834710743801653, | |
| "grad_norm": 8.457206726074219, | |
| "learning_rate": 9.417560222230115e-05, | |
| "loss": 3.1279, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.21487603305785125, | |
| "grad_norm": 9.018540382385254, | |
| "learning_rate": 9.284285880837946e-05, | |
| "loss": 2.6837, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.23140495867768596, | |
| "grad_norm": 9.167037010192871, | |
| "learning_rate": 9.138444990784453e-05, | |
| "loss": 2.5647, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.24793388429752067, | |
| "grad_norm": 12.68354606628418, | |
| "learning_rate": 8.980465328528219e-05, | |
| "loss": 2.9151, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.2644628099173554, | |
| "grad_norm": 8.708942413330078, | |
| "learning_rate": 8.810810275638183e-05, | |
| "loss": 3.2871, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.2809917355371901, | |
| "grad_norm": 7.528436660766602, | |
| "learning_rate": 8.629977459615655e-05, | |
| "loss": 3.1734, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.2975206611570248, | |
| "grad_norm": 8.341012001037598, | |
| "learning_rate": 8.438497294267117e-05, | |
| "loss": 2.3823, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.3140495867768595, | |
| "grad_norm": 8.260071754455566, | |
| "learning_rate": 8.236931423909138e-05, | |
| "loss": 2.3359, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.3305785123966942, | |
| "grad_norm": 9.664773941040039, | |
| "learning_rate": 8.025871075968828e-05, | |
| "loss": 2.2876, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.34710743801652894, | |
| "grad_norm": 9.267929077148438, | |
| "learning_rate": 7.805935326811912e-05, | |
| "loss": 2.4783, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.36363636363636365, | |
| "grad_norm": 9.94819450378418, | |
| "learning_rate": 7.577769285885109e-05, | |
| "loss": 3.06, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.38016528925619836, | |
| "grad_norm": 6.440147876739502, | |
| "learning_rate": 7.342042203498951e-05, | |
| "loss": 2.4391, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.39669421487603307, | |
| "grad_norm": 11.975261688232422, | |
| "learning_rate": 7.099445507801323e-05, | |
| "loss": 3.1622, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.4132231404958678, | |
| "grad_norm": 12.1334867477417, | |
| "learning_rate": 6.850690776699573e-05, | |
| "loss": 2.4117, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.4132231404958678, | |
| "eval_loss": 2.364795446395874, | |
| "eval_runtime": 4.4813, | |
| "eval_samples_per_second": 5.802, | |
| "eval_steps_per_second": 2.901, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.4297520661157025, | |
| "grad_norm": 10.043116569519043, | |
| "learning_rate": 6.5965076506799e-05, | |
| "loss": 2.9622, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.4462809917355372, | |
| "grad_norm": 16.373950958251953, | |
| "learning_rate": 6.337641692646106e-05, | |
| "loss": 2.9865, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.4628099173553719, | |
| "grad_norm": 7.408267498016357, | |
| "learning_rate": 6.0748522010551215e-05, | |
| "loss": 2.1804, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.4793388429752066, | |
| "grad_norm": 9.184383392333984, | |
| "learning_rate": 5.808909982763825e-05, | |
| "loss": 2.4657, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.49586776859504134, | |
| "grad_norm": 9.664917945861816, | |
| "learning_rate": 5.540595092119709e-05, | |
| "loss": 2.2407, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.512396694214876, | |
| "grad_norm": 11.779993057250977, | |
| "learning_rate": 5.270694542927088e-05, | |
| "loss": 3.5904, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.5289256198347108, | |
| "grad_norm": 6.609020233154297, | |
| "learning_rate": 5e-05, | |
| "loss": 2.1943, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.5454545454545454, | |
| "grad_norm": 7.8492889404296875, | |
| "learning_rate": 4.729305457072913e-05, | |
| "loss": 2.1845, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.5619834710743802, | |
| "grad_norm": 8.724394798278809, | |
| "learning_rate": 4.4594049078802925e-05, | |
| "loss": 2.3286, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.5785123966942148, | |
| "grad_norm": 9.296069145202637, | |
| "learning_rate": 4.1910900172361764e-05, | |
| "loss": 2.3771, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.5950413223140496, | |
| "grad_norm": 8.15500259399414, | |
| "learning_rate": 3.92514779894488e-05, | |
| "loss": 2.4083, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.6115702479338843, | |
| "grad_norm": 9.642007827758789, | |
| "learning_rate": 3.6623583073538966e-05, | |
| "loss": 2.2474, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.628099173553719, | |
| "grad_norm": 6.308684825897217, | |
| "learning_rate": 3.403492349320101e-05, | |
| "loss": 2.4492, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.6446280991735537, | |
| "grad_norm": 6.576019763946533, | |
| "learning_rate": 3.149309223300428e-05, | |
| "loss": 2.3185, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.6611570247933884, | |
| "grad_norm": 9.71943187713623, | |
| "learning_rate": 2.900554492198677e-05, | |
| "loss": 2.6858, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.6776859504132231, | |
| "grad_norm": 11.457530975341797, | |
| "learning_rate": 2.65795779650105e-05, | |
| "loss": 3.1241, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.6942148760330579, | |
| "grad_norm": 9.567526817321777, | |
| "learning_rate": 2.422230714114891e-05, | |
| "loss": 2.3865, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.7107438016528925, | |
| "grad_norm": 6.879986763000488, | |
| "learning_rate": 2.194064673188089e-05, | |
| "loss": 2.2602, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.7272727272727273, | |
| "grad_norm": 7.776947498321533, | |
| "learning_rate": 1.9741289240311755e-05, | |
| "loss": 2.0642, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.743801652892562, | |
| "grad_norm": 7.914689540863037, | |
| "learning_rate": 1.7630685760908622e-05, | |
| "loss": 2.3686, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.7603305785123967, | |
| "grad_norm": 8.547547340393066, | |
| "learning_rate": 1.561502705732883e-05, | |
| "loss": 2.9245, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.7768595041322314, | |
| "grad_norm": 7.577058792114258, | |
| "learning_rate": 1.3700225403843469e-05, | |
| "loss": 2.2968, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.7933884297520661, | |
| "grad_norm": 7.617032527923584, | |
| "learning_rate": 1.1891897243618182e-05, | |
| "loss": 2.1618, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.8099173553719008, | |
| "grad_norm": 6.652332782745361, | |
| "learning_rate": 1.0195346714717813e-05, | |
| "loss": 1.725, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.8264462809917356, | |
| "grad_norm": 7.552050590515137, | |
| "learning_rate": 8.615550092155478e-06, | |
| "loss": 2.0762, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.8264462809917356, | |
| "eval_loss": 2.21439266204834, | |
| "eval_runtime": 4.4905, | |
| "eval_samples_per_second": 5.79, | |
| "eval_steps_per_second": 2.895, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 61, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3.83447180771328e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |