| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.12560386473429952, | |
| "eval_steps": 10, | |
| "global_step": 13, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00966183574879227, | |
| "eval_loss": 10.882368087768555, | |
| "eval_runtime": 2.9101, | |
| "eval_samples_per_second": 239.851, | |
| "eval_steps_per_second": 30.239, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0966183574879227, | |
| "grad_norm": 18.205909729003906, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 10.4561, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0966183574879227, | |
| "eval_loss": 9.441638946533203, | |
| "eval_runtime": 2.8968, | |
| "eval_samples_per_second": 240.952, | |
| "eval_steps_per_second": 30.378, | |
| "step": 10 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 13, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 23404400345088.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |