| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.4, |
| "eval_steps": 500, |
| "global_step": 50, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.08, |
| "grad_norm": 2.0762882232666016, |
| "learning_rate": 0.0001952, |
| "loss": 2.921174430847168, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.16, |
| "grad_norm": 1.494314432144165, |
| "learning_rate": 0.00018986666666666668, |
| "loss": 0.8493177413940429, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.24, |
| "grad_norm": 0.8940829634666443, |
| "learning_rate": 0.00018453333333333334, |
| "loss": 0.29891698360443114, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.32, |
| "grad_norm": 0.6761481761932373, |
| "learning_rate": 0.00017920000000000002, |
| "loss": 0.24503071308135987, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.4, |
| "grad_norm": 0.8483666181564331, |
| "learning_rate": 0.00017386666666666667, |
| "loss": 0.23532724380493164, |
| "step": 50 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 375, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 3, |
| "save_steps": 50, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 2299281227093760.0, |
| "train_batch_size": 4, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
