| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 9.89247311827957, | |
| "eval_steps": 500, | |
| "global_step": 460, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.21505376344086022, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019976687691905393, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.43010752688172044, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019906859460363307, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.6451612903225806, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019790840876823232, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.8602150537634409, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019629172873477995, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.075268817204301, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019422609221188207, | |
| "loss": 0.0, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.2903225806451613, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019172113015054532, | |
| "loss": 0.0, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 1.5053763440860215, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001887885218402375, | |
| "loss": 0.0, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 1.7204301075268817, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018544194045464886, | |
| "loss": 0.0, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.935483870967742, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001816969893010442, | |
| "loss": 0.0, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 2.150537634408602, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.000177571129070442, | |
| "loss": 0.0, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 2.3655913978494625, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00017308359642781242, | |
| "loss": 0.0, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 2.5806451612903225, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00016825531432186543, | |
| "loss": 0.0, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 2.795698924731183, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00016310879443260528, | |
| "loss": 0.0, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 3.010752688172043, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00015766803221148673, | |
| "loss": 0.0, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 3.225806451612903, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00015195839500354335, | |
| "loss": 0.0, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 3.4408602150537635, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00014600650377311522, | |
| "loss": 0.0, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 3.6559139784946235, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00013984010898462416, | |
| "loss": 0.0, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 3.870967741935484, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00013348796121709862, | |
| "loss": 0.0, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 4.086021505376344, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00012697967711570242, | |
| "loss": 0.0, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 4.301075268817204, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001203456013052634, | |
| "loss": 0.0, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 4.516129032258064, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00011361666490962468, | |
| "loss": 0.0, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 4.731182795698925, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001068242413364671, | |
| "loss": 0.0, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 4.946236559139785, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 5.161290322580645, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.317575866353292e-05, | |
| "loss": 0.0, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 5.376344086021505, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.638333509037536e-05, | |
| "loss": 0.0, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 5.591397849462366, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.965439869473664e-05, | |
| "loss": 0.0, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 5.806451612903226, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.302032288429756e-05, | |
| "loss": 0.0, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 6.021505376344086, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.651203878290139e-05, | |
| "loss": 0.0, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 6.236559139784946, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.015989101537586e-05, | |
| "loss": 0.0, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 6.451612903225806, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.399349622688479e-05, | |
| "loss": 0.0, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 6.666666666666667, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.804160499645667e-05, | |
| "loss": 0.0, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 6.881720430107527, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.2331967788513295e-05, | |
| "loss": 0.0, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 7.096774193548387, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.689120556739475e-05, | |
| "loss": 0.0, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 7.311827956989247, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.174468567813461e-05, | |
| "loss": 0.0, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 7.526881720430108, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.691640357218759e-05, | |
| "loss": 0.0, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 7.741935483870968, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.242887092955801e-05, | |
| "loss": 0.0, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 7.956989247311828, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.8303010698955804e-05, | |
| "loss": 0.0, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 8.172043010752688, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.4558059545351143e-05, | |
| "loss": 0.0, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 8.387096774193548, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.1211478159762478e-05, | |
| "loss": 0.0, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 8.602150537634408, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.278869849454718e-06, | |
| "loss": 0.0, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 8.817204301075268, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.77390778811796e-06, | |
| "loss": 0.0, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 9.03225806451613, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.7082712652200867e-06, | |
| "loss": 0.0, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 9.24731182795699, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.091591231767709e-06, | |
| "loss": 0.0, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 9.46236559139785, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.314053963669245e-07, | |
| "loss": 0.0, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 9.67741935483871, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.3312308094607382e-07, | |
| "loss": 0.0, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 9.89247311827957, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 9.89247311827957, | |
| "step": 460, | |
| "total_flos": 2.262683294367744e+16, | |
| "train_loss": 0.0, | |
| "train_runtime": 377.8672, | |
| "train_samples_per_second": 4.922, | |
| "train_steps_per_second": 1.217 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 460, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 10, | |
| "save_steps": 500, | |
| "total_flos": 2.262683294367744e+16, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |