| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 3.0, |
| "eval_steps": 500, |
| "global_step": 42, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.7142857142857143, |
| "grad_norm": 0.5629768967628479, |
| "learning_rate": 0.00015714285714285716, |
| "loss": 3.0696025848388673, |
| "step": 10 |
| }, |
| { |
| "epoch": 1.4285714285714286, |
| "grad_norm": 0.6383734941482544, |
| "learning_rate": 0.00010952380952380953, |
| "loss": 2.9755151748657225, |
| "step": 20 |
| }, |
| { |
| "epoch": 2.142857142857143, |
| "grad_norm": 0.4793911576271057, |
| "learning_rate": 6.19047619047619e-05, |
| "loss": 2.8452743530273437, |
| "step": 30 |
| }, |
| { |
| "epoch": 2.857142857142857, |
| "grad_norm": 0.5271763205528259, |
| "learning_rate": 1.4285714285714285e-05, |
| "loss": 2.8660940170288085, |
| "step": 40 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 42, |
| "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": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 367227367981056.0, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
