| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.00024234590839324662, | |
| "eval_steps": 3, | |
| "global_step": 3, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 8.078196946441554e-05, | |
| "grad_norm": 10.836163520812988, | |
| "learning_rate": 2e-05, | |
| "loss": 5.2973, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 8.078196946441554e-05, | |
| "eval_loss": 6.08513069152832, | |
| "eval_runtime": 190.4047, | |
| "eval_samples_per_second": 27.379, | |
| "eval_steps_per_second": 13.692, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00016156393892883107, | |
| "grad_norm": 15.810860633850098, | |
| "learning_rate": 4e-05, | |
| "loss": 6.7627, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00024234590839324662, | |
| "grad_norm": 11.094259262084961, | |
| "learning_rate": 6e-05, | |
| "loss": 5.5142, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00024234590839324662, | |
| "eval_loss": 5.897503852844238, | |
| "eval_runtime": 185.1619, | |
| "eval_samples_per_second": 28.154, | |
| "eval_steps_per_second": 14.08, | |
| "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": 146843338014720.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |