| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.0, |
| "eval_steps": 1000, |
| "global_step": 67, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.15023474178403756, |
| "grad_norm": 31.56661033630371, |
| "learning_rate": 9.972609476841368e-06, |
| "loss": 1.7659, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.3004694835680751, |
| "grad_norm": 35.23997497558594, |
| "learning_rate": 9.045084971874738e-06, |
| "loss": 0.5183, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.4507042253521127, |
| "grad_norm": 5.03916072845459, |
| "learning_rate": 7.033683215379002e-06, |
| "loss": 0.278, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.6009389671361502, |
| "grad_norm": 3.3426177501678467, |
| "learning_rate": 4.477357683661734e-06, |
| "loss": 0.2194, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.7511737089201878, |
| "grad_norm": 3.752589702606201, |
| "learning_rate": 2.061073738537635e-06, |
| "loss": 0.1969, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.9014084507042254, |
| "grad_norm": 5.254862308502197, |
| "learning_rate": 4.322727117869951e-07, |
| "loss": 0.1813, |
| "step": 60 |
| }, |
| { |
| "epoch": 1.0, |
| "step": 67, |
| "total_flos": 265909239283712.0, |
| "train_loss": 0.48691165269310793, |
| "train_runtime": 25225.3606, |
| "train_samples_per_second": 0.338, |
| "train_steps_per_second": 0.003 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 67, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 100, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 265909239283712.0, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
