| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.984, |
| "eval_steps": 500, |
| "global_step": 124, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.4, |
| "grad_norm": 8.975930213928223, |
| "learning_rate": 4.8e-05, |
| "loss": 5.9644, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.8, |
| "grad_norm": 4.640599250793457, |
| "learning_rate": 9.6e-05, |
| "loss": 0.2692, |
| "step": 50 |
| }, |
| { |
| "epoch": 1.2, |
| "grad_norm": 4.38785457611084, |
| "learning_rate": 6.891891891891892e-05, |
| "loss": 0.2169, |
| "step": 75 |
| }, |
| { |
| "epoch": 1.6, |
| "grad_norm": 5.062775135040283, |
| "learning_rate": 3.513513513513514e-05, |
| "loss": 0.1758, |
| "step": 100 |
| } |
| ], |
| "logging_steps": 25, |
| "max_steps": 124, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 2, |
| "save_steps": 25, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 9930726476237952.0, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
