| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 12, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.4166666666666667, | |
| "grad_norm": 6.961626052856445, | |
| "learning_rate": 3.6846837792542446e-05, | |
| "loss": 1.0007, | |
| "mean_token_accuracy": 0.7392964333295822, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.8333333333333334, | |
| "grad_norm": 1.220391035079956, | |
| "learning_rate": 8.571795511298423e-06, | |
| "loss": 0.6902, | |
| "mean_token_accuracy": 0.7992854446172715, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "mean_token_accuracy": 0.8175339177250862, | |
| "step": 12, | |
| "total_flos": 12236517015552.0, | |
| "train_loss": 0.7996856272220612, | |
| "train_runtime": 454.1356, | |
| "train_samples_per_second": 0.843, | |
| "train_steps_per_second": 0.026 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 12, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 100, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 12236517015552.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |