| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.0, |
| "eval_steps": 0, |
| "global_step": 7, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.14285714285714285, |
| "grad_norm": 9.457938194274902, |
| "learning_rate": 8.571428571428571e-06, |
| "loss": 6.9794, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.2857142857142857, |
| "grad_norm": 9.459606170654297, |
| "learning_rate": 7.1428571428571436e-06, |
| "loss": 6.9527, |
| "step": 2 |
| }, |
| { |
| "epoch": 0.42857142857142855, |
| "grad_norm": 9.331229209899902, |
| "learning_rate": 5.7142857142857145e-06, |
| "loss": 6.9309, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.5714285714285714, |
| "grad_norm": 9.504999160766602, |
| "learning_rate": 4.2857142857142855e-06, |
| "loss": 6.9477, |
| "step": 4 |
| }, |
| { |
| "epoch": 0.7142857142857143, |
| "grad_norm": 9.457680702209473, |
| "learning_rate": 2.8571428571428573e-06, |
| "loss": 6.9407, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.8571428571428571, |
| "grad_norm": 9.489648818969727, |
| "learning_rate": 1.4285714285714286e-06, |
| "loss": 6.9444, |
| "step": 6 |
| }, |
| { |
| "epoch": 1.0, |
| "grad_norm": 9.480498313903809, |
| "learning_rate": 0.0, |
| "loss": 6.8947, |
| "step": 7 |
| } |
| ], |
| "logging_steps": 1.0, |
| "max_steps": 7, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 0, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 673527443226624.0, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
