| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.00029289588356802836, |
| "eval_steps": 500, |
| "global_step": 100, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 2.9289588356802836e-05, |
| "grad_norm": 43.412994384765625, |
| "learning_rate": 4.8e-07, |
| "loss": 9.4322, |
| "step": 10 |
| }, |
| { |
| "epoch": 5.857917671360567e-05, |
| "grad_norm": 24.38200569152832, |
| "learning_rate": 1.0799999999999998e-06, |
| "loss": 9.4165, |
| "step": 20 |
| }, |
| { |
| "epoch": 8.786876507040851e-05, |
| "grad_norm": 25.624269485473633, |
| "learning_rate": 1.6799999999999998e-06, |
| "loss": 9.3983, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.00011715835342721134, |
| "grad_norm": 25.8831729888916, |
| "learning_rate": 2.2799999999999998e-06, |
| "loss": 9.4015, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.00014644794178401418, |
| "grad_norm": 18.858943939208984, |
| "learning_rate": 2.8799999999999995e-06, |
| "loss": 9.369, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.00017573753014081702, |
| "grad_norm": 32.19478225708008, |
| "learning_rate": 3.4799999999999993e-06, |
| "loss": 9.3743, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.00020502711849761985, |
| "grad_norm": 29.089111328125, |
| "learning_rate": 4.079999999999999e-06, |
| "loss": 9.3628, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.0002343167068544227, |
| "grad_norm": 45.67530822753906, |
| "learning_rate": 4.679999999999999e-06, |
| "loss": 9.359, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.0002636062952112255, |
| "grad_norm": 33.06043243408203, |
| "learning_rate": 5.28e-06, |
| "loss": 9.3381, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.00029289588356802836, |
| "grad_norm": 32.19873809814453, |
| "learning_rate": 5.88e-06, |
| "loss": 9.3304, |
| "step": 100 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 1000000, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 3, |
| "save_steps": 100, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 264410978304000.0, |
| "train_batch_size": 4, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
