| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.5, |
| "eval_steps": 500, |
| "global_step": 50, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "grad_norm": 0.38351285457611084, |
| "learning_rate": 9.956320346634876e-05, |
| "loss": 1.2186, |
| "step": 10 |
| }, |
| { |
| "grad_norm": 0.453412801027298, |
| "learning_rate": 9.473646649103818e-05, |
| "loss": 1.176, |
| "step": 20 |
| }, |
| { |
| "grad_norm": 0.3962445557117462, |
| "learning_rate": 8.506183921362443e-05, |
| "loss": 1.1279, |
| "step": 30 |
| }, |
| { |
| "grad_norm": 0.33287128806114197, |
| "learning_rate": 7.158771761692464e-05, |
| "loss": 1.0833, |
| "step": 40 |
| }, |
| { |
| "grad_norm": 0.34996676445007324, |
| "learning_rate": 5.577423184847932e-05, |
| "loss": 1.0655, |
| "step": 50 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 100, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 9223372036854775807, |
| "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": 0.0, |
| "train_batch_size": 48, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
