| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 10.0, |
| "eval_steps": 500, |
| "global_step": 30, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.8, |
| "grad_norm": 9.5, |
| "learning_rate": 2.785714285714286e-06, |
| "loss": 0.01084165945649147, |
| "step": 5 |
| }, |
| { |
| "epoch": 3.4, |
| "grad_norm": 13.1875, |
| "learning_rate": 2.25e-06, |
| "loss": -0.018919241428375245, |
| "step": 10 |
| }, |
| { |
| "epoch": 5.0, |
| "grad_norm": 15.125, |
| "learning_rate": 1.7142857142857143e-06, |
| "loss": 0.0004279181361198425, |
| "step": 15 |
| }, |
| { |
| "epoch": 6.8, |
| "grad_norm": 12.9375, |
| "learning_rate": 1.1785714285714285e-06, |
| "loss": -0.02924223244190216, |
| "step": 20 |
| }, |
| { |
| "epoch": 8.4, |
| "grad_norm": 14.9375, |
| "learning_rate": 6.428571428571428e-07, |
| "loss": -0.013675640523433685, |
| "step": 25 |
| }, |
| { |
| "epoch": 10.0, |
| "grad_norm": 17.0, |
| "learning_rate": 1.0714285714285714e-07, |
| "loss": -0.04322903156280518, |
| "step": 30 |
| }, |
| { |
| "epoch": 10.0, |
| "step": 30, |
| "total_flos": 0.0, |
| "train_loss": -0.01563276139398416, |
| "train_runtime": 56.3734, |
| "train_samples_per_second": 7.096, |
| "train_steps_per_second": 0.532 |
| } |
| ], |
| "logging_steps": 5, |
| "max_steps": 30, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 10, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": false, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 0.0, |
| "train_batch_size": 8, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
