| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.05044136191677175, |
| "eval_steps": 100, |
| "global_step": 20, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.0025220680958385876, |
| "grad_norm": 25.350475311279297, |
| "learning_rate": 0.0, |
| "loss": 2.5568, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.005044136191677175, |
| "grad_norm": 24.538068771362305, |
| "learning_rate": 4.000000000000001e-06, |
| "loss": 2.7748, |
| "step": 2 |
| }, |
| { |
| "epoch": 0.007566204287515763, |
| "grad_norm": 23.780784606933594, |
| "learning_rate": 8.000000000000001e-06, |
| "loss": 2.5911, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.01008827238335435, |
| "grad_norm": 24.780380249023438, |
| "learning_rate": 1.2e-05, |
| "loss": 2.8427, |
| "step": 4 |
| }, |
| { |
| "epoch": 0.012610340479192938, |
| "grad_norm": 22.699949264526367, |
| "learning_rate": 1.6000000000000003e-05, |
| "loss": 2.709, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.015132408575031526, |
| "grad_norm": 22.106008529663086, |
| "learning_rate": 2e-05, |
| "loss": 2.5854, |
| "step": 6 |
| }, |
| { |
| "epoch": 0.017654476670870115, |
| "grad_norm": 22.497045516967773, |
| "learning_rate": 1.9948979591836737e-05, |
| "loss": 2.5427, |
| "step": 7 |
| }, |
| { |
| "epoch": 0.0201765447667087, |
| "grad_norm": 27.103275299072266, |
| "learning_rate": 1.9897959183673473e-05, |
| "loss": 2.6599, |
| "step": 8 |
| }, |
| { |
| "epoch": 0.02269861286254729, |
| "grad_norm": 21.081985473632812, |
| "learning_rate": 1.9846938775510205e-05, |
| "loss": 2.5145, |
| "step": 9 |
| }, |
| { |
| "epoch": 0.025220680958385876, |
| "grad_norm": 25.964981079101562, |
| "learning_rate": 1.979591836734694e-05, |
| "loss": 2.4247, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.027742749054224466, |
| "grad_norm": 25.353195190429688, |
| "learning_rate": 1.9744897959183677e-05, |
| "loss": 2.5092, |
| "step": 11 |
| }, |
| { |
| "epoch": 0.03026481715006305, |
| "grad_norm": 18.94191551208496, |
| "learning_rate": 1.969387755102041e-05, |
| "loss": 2.4335, |
| "step": 12 |
| }, |
| { |
| "epoch": 0.03278688524590164, |
| "grad_norm": 23.60140037536621, |
| "learning_rate": 1.9642857142857145e-05, |
| "loss": 2.544, |
| "step": 13 |
| }, |
| { |
| "epoch": 0.03530895334174023, |
| "grad_norm": 24.298965454101562, |
| "learning_rate": 1.9591836734693877e-05, |
| "loss": 2.4987, |
| "step": 14 |
| }, |
| { |
| "epoch": 0.03783102143757881, |
| "grad_norm": 20.745506286621094, |
| "learning_rate": 1.9540816326530613e-05, |
| "loss": 2.4985, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.0403530895334174, |
| "grad_norm": 22.54330062866211, |
| "learning_rate": 1.948979591836735e-05, |
| "loss": 2.6892, |
| "step": 16 |
| }, |
| { |
| "epoch": 0.04287515762925599, |
| "grad_norm": 21.46229362487793, |
| "learning_rate": 1.9438775510204085e-05, |
| "loss": 2.3998, |
| "step": 17 |
| }, |
| { |
| "epoch": 0.04539722572509458, |
| "grad_norm": 20.54530143737793, |
| "learning_rate": 1.9387755102040817e-05, |
| "loss": 2.4244, |
| "step": 18 |
| }, |
| { |
| "epoch": 0.04791929382093316, |
| "grad_norm": 18.8839111328125, |
| "learning_rate": 1.9336734693877553e-05, |
| "loss": 2.3911, |
| "step": 19 |
| }, |
| { |
| "epoch": 0.05044136191677175, |
| "grad_norm": 16.924652099609375, |
| "learning_rate": 1.928571428571429e-05, |
| "loss": 2.3588, |
| "step": 20 |
| } |
| ], |
| "logging_steps": 1, |
| "max_steps": 397, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 10, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 291584891437056.0, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
