| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 2.0, |
| "eval_steps": 500, |
| "global_step": 56, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.7142857142857143, |
| "grad_norm": 2.331707167384823, |
| "learning_rate": 2.526820658893033e-06, |
| "loss": 1.3719, |
| "step": 20 |
| }, |
| { |
| "epoch": 1.4285714285714286, |
| "grad_norm": 1.2150077774278196, |
| "learning_rate": 7.773694888474268e-07, |
| "loss": 1.144, |
| "step": 40 |
| }, |
| { |
| "epoch": 2.0, |
| "step": 56, |
| "total_flos": 8368828973056.0, |
| "train_loss": 1.207296916416713, |
| "train_runtime": 321.0192, |
| "train_samples_per_second": 1.371, |
| "train_steps_per_second": 0.174 |
| } |
| ], |
| "logging_steps": 20, |
| "max_steps": 56, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 2, |
| "save_steps": 5000, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 8368828973056.0, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
