| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0002310280265874754, | |
| "eval_steps": 3, | |
| "global_step": 3, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 7.700934219582514e-05, | |
| "grad_norm": 0.44221264123916626, | |
| "learning_rate": 1e-05, | |
| "loss": 0.918, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 7.700934219582514e-05, | |
| "eval_loss": 1.0547187328338623, | |
| "eval_runtime": 980.5874, | |
| "eval_samples_per_second": 22.304, | |
| "eval_steps_per_second": 11.152, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00015401868439165027, | |
| "grad_norm": 0.40297988057136536, | |
| "learning_rate": 2e-05, | |
| "loss": 0.9651, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0002310280265874754, | |
| "grad_norm": 0.6582609415054321, | |
| "learning_rate": 3e-05, | |
| "loss": 1.003, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0002310280265874754, | |
| "eval_loss": 1.0451246500015259, | |
| "eval_runtime": 846.3252, | |
| "eval_samples_per_second": 25.842, | |
| "eval_steps_per_second": 12.922, | |
| "step": 3 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 10, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 3, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3726628261724160.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |