| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 10.0, |
| "eval_steps": 500, |
| "global_step": 440, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 2.2742857142857145, |
| "grad_norm": 168256.046875, |
| "learning_rate": 9.900000000000002e-06, |
| "loss": 0.6343, |
| "step": 100 |
| }, |
| { |
| "epoch": 4.548571428571429, |
| "grad_norm": 430370.875, |
| "learning_rate": 1.9900000000000003e-05, |
| "loss": 0.2013, |
| "step": 200 |
| }, |
| { |
| "epoch": 6.822857142857143, |
| "grad_norm": 111049.3671875, |
| "learning_rate": 2.9900000000000002e-05, |
| "loss": 0.0447, |
| "step": 300 |
| }, |
| { |
| "epoch": 9.09142857142857, |
| "grad_norm": 58188.171875, |
| "learning_rate": 3.99e-05, |
| "loss": 0.1352, |
| "step": 400 |
| } |
| ], |
| "logging_steps": 100, |
| "max_steps": 440, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 10, |
| "save_steps": 1000, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 0.0, |
| "train_batch_size": 8, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
