| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 1918, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.26068821689259647, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.393117831074036e-06, | |
| "loss": 1.1435, | |
| "mean_token_accuracy": 0.44466638553142546, | |
| "num_tokens": 3999914.0, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.5213764337851929, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.7862356621480715e-06, | |
| "loss": 0.0, | |
| "mean_token_accuracy": 0.0, | |
| "num_tokens": 7989385.0, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.7820646506777894, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.1793534932221064e-06, | |
| "loss": 0.0, | |
| "mean_token_accuracy": 0.0, | |
| "num_tokens": 3993373.0, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "mean_token_accuracy": 0.0, | |
| "num_tokens": 7324027.0, | |
| "step": 1918, | |
| "total_flos": 3.336499157376e+17, | |
| "train_loss": 0.0, | |
| "train_runtime": 2859.1765, | |
| "train_samples_per_second": 1.342, | |
| "train_steps_per_second": 0.671 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 1918, | |
| "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": 3.336499157376e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |