| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 5.0, | |
| "eval_steps": 500, | |
| "global_step": 5, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 4.522542485937369e-06, | |
| "loss": 1.3095, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "grad_norm": 22.8277053138044, | |
| "learning_rate": 0.0, | |
| "loss": 1.1166, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "step": 5, | |
| "total_flos": 9941630593269760.0, | |
| "train_loss": 1.1551473617553711, | |
| "train_runtime": 182.6188, | |
| "train_samples_per_second": 1.588, | |
| "train_steps_per_second": 0.027 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 5, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 5, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": false, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 9941630593269760.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |