| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.0, |
| "eval_steps": 500, |
| "global_step": 1057, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.47303689687795647, |
| "grad_norm": 0.267578125, |
| "learning_rate": 1.0539262062440872e-05, |
| "loss": 0.072, |
| "mean_token_accuracy": 0.9245506889820099, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.9460737937559129, |
| "grad_norm": 0.2578125, |
| "learning_rate": 1.078524124881741e-06, |
| "loss": 0.0606, |
| "mean_token_accuracy": 0.933465634226799, |
| "step": 1000 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 1057, |
| "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": 1.4402620808429568e+17, |
| "train_batch_size": 8, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
