| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.0, |
| "eval_steps": 500, |
| "global_step": 65, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "entropy": 1.7120087901502847, |
| "epoch": 0.38910505836575876, |
| "grad_norm": 0.10009765625, |
| "learning_rate": 0.0001456210657353163, |
| "loss": 1.7259098815917968, |
| "mean_token_accuracy": 0.6165898694097995, |
| "num_tokens": 153849.0, |
| "step": 25 |
| }, |
| { |
| "entropy": 1.209397535175085, |
| "epoch": 0.7782101167315175, |
| "grad_norm": 0.11669921875, |
| "learning_rate": 3.0176318191392726e-05, |
| "loss": 1.1618038177490235, |
| "mean_token_accuracy": 0.7371345187723637, |
| "num_tokens": 310508.0, |
| "step": 50 |
| } |
| ], |
| "logging_steps": 25, |
| "max_steps": 65, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 1.6916915575440384e+16, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
