| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.0, | |
| "eval_steps": 500, | |
| "global_step": 52, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.038461538461538464, | |
| "grad_norm": 20.85754319226794, | |
| "learning_rate": 3.3333333333333333e-06, | |
| "loss": 1.2667, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.07692307692307693, | |
| "grad_norm": 24.246870301808055, | |
| "learning_rate": 6.666666666666667e-06, | |
| "loss": 1.3048, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.11538461538461539, | |
| "grad_norm": 19.58236853178882, | |
| "learning_rate": 1e-05, | |
| "loss": 1.1097, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.15384615384615385, | |
| "grad_norm": 30.55885846320602, | |
| "learning_rate": 1.3333333333333333e-05, | |
| "loss": 0.9511, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.19230769230769232, | |
| "grad_norm": 20.08985298506213, | |
| "learning_rate": 1.6666666666666667e-05, | |
| "loss": 0.7813, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.23076923076923078, | |
| "grad_norm": 14.162855282317404, | |
| "learning_rate": 2e-05, | |
| "loss": 0.6916, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.2692307692307692, | |
| "grad_norm": 20.028553980740814, | |
| "learning_rate": 1.9976687691905394e-05, | |
| "loss": 0.6448, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.3076923076923077, | |
| "grad_norm": 29.62124108104504, | |
| "learning_rate": 1.9906859460363307e-05, | |
| "loss": 0.8493, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.34615384615384615, | |
| "grad_norm": 50.58398328205813, | |
| "learning_rate": 1.979084087682323e-05, | |
| "loss": 0.9227, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.38461538461538464, | |
| "grad_norm": 3.960885136166706, | |
| "learning_rate": 1.9629172873477995e-05, | |
| "loss": 0.495, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.4230769230769231, | |
| "grad_norm": 4.1877316087885035, | |
| "learning_rate": 1.9422609221188208e-05, | |
| "loss": 0.495, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.46153846153846156, | |
| "grad_norm": 4.998304642102752, | |
| "learning_rate": 1.917211301505453e-05, | |
| "loss": 0.4478, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "grad_norm": 2.4596034942030065, | |
| "learning_rate": 1.8878852184023754e-05, | |
| "loss": 0.4657, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.5384615384615384, | |
| "grad_norm": 1.6865528982507465, | |
| "learning_rate": 1.8544194045464888e-05, | |
| "loss": 0.4078, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.5769230769230769, | |
| "grad_norm": 1.7910809046492557, | |
| "learning_rate": 1.816969893010442e-05, | |
| "loss": 0.327, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.6153846153846154, | |
| "grad_norm": 1.8011895949239238, | |
| "learning_rate": 1.77571129070442e-05, | |
| "loss": 0.3845, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.6538461538461539, | |
| "grad_norm": 1.5712375007924961, | |
| "learning_rate": 1.730835964278124e-05, | |
| "loss": 0.3304, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.6923076923076923, | |
| "grad_norm": 1.2482964114523387, | |
| "learning_rate": 1.6825531432186545e-05, | |
| "loss": 0.3108, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.7307692307692307, | |
| "grad_norm": 1.3162781011551596, | |
| "learning_rate": 1.631087944326053e-05, | |
| "loss": 0.299, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.7692307692307693, | |
| "grad_norm": 1.2534379605750423, | |
| "learning_rate": 1.5766803221148676e-05, | |
| "loss": 0.2795, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.8076923076923077, | |
| "grad_norm": 1.171621258475382, | |
| "learning_rate": 1.5195839500354337e-05, | |
| "loss": 0.2945, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.8461538461538461, | |
| "grad_norm": 1.3353357877056748, | |
| "learning_rate": 1.4600650377311523e-05, | |
| "loss": 0.3072, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.8846153846153846, | |
| "grad_norm": 1.3675590758455805, | |
| "learning_rate": 1.3984010898462417e-05, | |
| "loss": 0.3407, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.9230769230769231, | |
| "grad_norm": 1.1353873052293306, | |
| "learning_rate": 1.3348796121709862e-05, | |
| "loss": 0.2404, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.9615384615384616, | |
| "grad_norm": 1.1094661531678627, | |
| "learning_rate": 1.2697967711570243e-05, | |
| "loss": 0.2822, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 1.0173771864310912, | |
| "learning_rate": 1.2034560130526341e-05, | |
| "loss": 0.2431, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.0384615384615385, | |
| "grad_norm": 0.9157192989332598, | |
| "learning_rate": 1.1361666490962468e-05, | |
| "loss": 0.1622, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.0769230769230769, | |
| "grad_norm": 1.170626036383389, | |
| "learning_rate": 1.0682424133646712e-05, | |
| "loss": 0.201, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.1153846153846154, | |
| "grad_norm": 1.2399773954594682, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2164, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.1538461538461537, | |
| "grad_norm": 1.1889650956121858, | |
| "learning_rate": 9.317575866353293e-06, | |
| "loss": 0.2319, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.1923076923076923, | |
| "grad_norm": 0.8825986428496552, | |
| "learning_rate": 8.638333509037537e-06, | |
| "loss": 0.1528, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.2307692307692308, | |
| "grad_norm": 0.8783022286148305, | |
| "learning_rate": 7.965439869473664e-06, | |
| "loss": 0.1559, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.2692307692307692, | |
| "grad_norm": 0.8516056967052127, | |
| "learning_rate": 7.3020322884297565e-06, | |
| "loss": 0.1342, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.3076923076923077, | |
| "grad_norm": 0.936682816255717, | |
| "learning_rate": 6.651203878290139e-06, | |
| "loss": 0.1363, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.3461538461538463, | |
| "grad_norm": 0.8791979974362931, | |
| "learning_rate": 6.015989101537586e-06, | |
| "loss": 0.1312, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.3846153846153846, | |
| "grad_norm": 1.015695664235406, | |
| "learning_rate": 5.399349622688479e-06, | |
| "loss": 0.1569, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 1.4230769230769231, | |
| "grad_norm": 0.9985258223852007, | |
| "learning_rate": 4.804160499645667e-06, | |
| "loss": 0.1861, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 1.4615384615384617, | |
| "grad_norm": 0.7719062123826321, | |
| "learning_rate": 4.2331967788513295e-06, | |
| "loss": 0.1337, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "grad_norm": 0.8094923832822339, | |
| "learning_rate": 3.689120556739475e-06, | |
| "loss": 0.1124, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 1.5384615384615383, | |
| "grad_norm": 0.9478634316121923, | |
| "learning_rate": 3.174468567813461e-06, | |
| "loss": 0.1355, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.5769230769230769, | |
| "grad_norm": 0.8471602530287855, | |
| "learning_rate": 2.691640357218759e-06, | |
| "loss": 0.1413, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 1.6153846153846154, | |
| "grad_norm": 0.8304448666983464, | |
| "learning_rate": 2.2428870929558012e-06, | |
| "loss": 0.1577, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.6538461538461537, | |
| "grad_norm": 0.7703268512000083, | |
| "learning_rate": 1.8303010698955803e-06, | |
| "loss": 0.128, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 1.6923076923076923, | |
| "grad_norm": 0.729939761686708, | |
| "learning_rate": 1.4558059545351144e-06, | |
| "loss": 0.1228, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 1.7307692307692308, | |
| "grad_norm": 0.8254947214606744, | |
| "learning_rate": 1.121147815976248e-06, | |
| "loss": 0.1437, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.7692307692307692, | |
| "grad_norm": 0.9952352246915486, | |
| "learning_rate": 8.278869849454718e-07, | |
| "loss": 0.1767, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 1.8076923076923077, | |
| "grad_norm": 0.779109190144192, | |
| "learning_rate": 5.77390778811796e-07, | |
| "loss": 0.1246, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 1.8461538461538463, | |
| "grad_norm": 0.6748859845108214, | |
| "learning_rate": 3.708271265220087e-07, | |
| "loss": 0.099, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.8846153846153846, | |
| "grad_norm": 0.782405714927644, | |
| "learning_rate": 2.091591231767709e-07, | |
| "loss": 0.1078, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 1.9230769230769231, | |
| "grad_norm": 0.9311280352392743, | |
| "learning_rate": 9.314053963669245e-08, | |
| "loss": 0.156, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.9615384615384617, | |
| "grad_norm": 0.8677277651118928, | |
| "learning_rate": 2.3312308094607382e-08, | |
| "loss": 0.1369, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 0.616841312096149, | |
| "learning_rate": 0.0, | |
| "loss": 0.1033, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "step": 52, | |
| "total_flos": 2404393205760.0, | |
| "train_loss": 0.3522481211962608, | |
| "train_runtime": 190.3027, | |
| "train_samples_per_second": 4.288, | |
| "train_steps_per_second": 0.273 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 52, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "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": 2404393205760.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |