| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.0, |
| "eval_steps": 10, |
| "global_step": 20, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.5, |
| "grad_norm": 3.601167678833008, |
| "learning_rate": 2.1186440677966103e-05, |
| "loss": 2.0164, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.5, |
| "eval_loss": 1.3784161806106567, |
| "eval_runtime": 15.5303, |
| "eval_samples_per_second": 0.451, |
| "eval_steps_per_second": 0.064, |
| "step": 10 |
| }, |
| { |
| "epoch": 1.0, |
| "grad_norm": 3.292940378189087, |
| "learning_rate": 1.694915254237288e-05, |
| "loss": 0.9838, |
| "step": 20 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_loss": 0.6041695475578308, |
| "eval_runtime": 15.4203, |
| "eval_samples_per_second": 0.454, |
| "eval_steps_per_second": 0.065, |
| "step": 20 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 60, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 3, |
| "save_steps": 10, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 884207769354240.0, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
