| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.9994879672299027, | |
| "eval_steps": 500, | |
| "global_step": 1464, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.3413551800648575, | |
| "grad_norm": 0.6665239930152893, | |
| "learning_rate": 1.3469945355191258e-05, | |
| "loss": 0.5281, | |
| "mean_token_accuracy": 0.8302740135490895, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.682710360129715, | |
| "grad_norm": 0.45956236124038696, | |
| "learning_rate": 6.6393442622950825e-06, | |
| "loss": 0.4675, | |
| "mean_token_accuracy": 0.8439739998281002, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.9994879672299027, | |
| "mean_token_accuracy": 0.8493433923878032, | |
| "step": 1464, | |
| "total_flos": 8.126438214090097e+18, | |
| "train_loss": 0.48108977437670764, | |
| "train_runtime": 50119.848, | |
| "train_samples_per_second": 1.87, | |
| "train_steps_per_second": 0.029 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 1464, | |
| "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": 8.126438214090097e+18, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |