| { |
| "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": 9.125, |
| "learning_rate": 9.285714285714286e-08, |
| "loss": 0.013596177101135254, |
| "step": 5 |
| }, |
| { |
| "epoch": 3.4, |
| "grad_norm": 11.25, |
| "learning_rate": 7.5e-08, |
| "loss": 0.005204639583826065, |
| "step": 10 |
| }, |
| { |
| "epoch": 5.0, |
| "grad_norm": 12.8125, |
| "learning_rate": 5.714285714285714e-08, |
| "loss": 0.03554368019104004, |
| "step": 15 |
| }, |
| { |
| "epoch": 6.8, |
| "grad_norm": 10.75, |
| "learning_rate": 3.9285714285714285e-08, |
| "loss": 0.019325479865074158, |
| "step": 20 |
| }, |
| { |
| "epoch": 8.4, |
| "grad_norm": 11.8125, |
| "learning_rate": 2.1428571428571426e-08, |
| "loss": 0.0375984936952591, |
| "step": 25 |
| }, |
| { |
| "epoch": 10.0, |
| "grad_norm": 12.9375, |
| "learning_rate": 3.571428571428571e-09, |
| "loss": 0.010456722229719162, |
| "step": 30 |
| }, |
| { |
| "epoch": 10.0, |
| "step": 30, |
| "total_flos": 0.0, |
| "train_loss": 0.020287532111008963, |
| "train_runtime": 55.3657, |
| "train_samples_per_second": 7.225, |
| "train_steps_per_second": 0.542 |
| } |
| ], |
| "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 |
| } |
|
|
