| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.9991286668602962, | |
| "eval_steps": 500, | |
| "global_step": 430, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.9991286668602962, | |
| "mean_token_accuracy": 2.0028690203109237e-05, | |
| "step": 430, | |
| "total_flos": 456093583015936.0, | |
| "train_loss": 13.683566497093024, | |
| "train_runtime": 13295.3238, | |
| "train_samples_per_second": 0.518, | |
| "train_steps_per_second": 0.032 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 430, | |
| "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": 456093583015936.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |