| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.998463901689708, | |
| "eval_steps": 500, | |
| "global_step": 1952, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.5120327700972862, | |
| "grad_norm": 0.4637981355190277, | |
| "learning_rate": 3.7653688524590166e-05, | |
| "loss": 0.6064, | |
| "mean_token_accuracy": 0.8113186240792275, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.0235535074244753, | |
| "grad_norm": 0.4264345169067383, | |
| "learning_rate": 2.4871926229508198e-05, | |
| "loss": 0.5381, | |
| "mean_token_accuracy": 0.8267606166867284, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.5355862775217615, | |
| "grad_norm": 0.3826408386230469, | |
| "learning_rate": 1.206454918032787e-05, | |
| "loss": 0.4632, | |
| "mean_token_accuracy": 0.8461171215772629, | |
| "step": 1500 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 1952, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "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": 3.016512968302002e+18, | |
| "train_batch_size": 6, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |