| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.23335861384983372, |
| "eval_steps": 1000, |
| "global_step": 2000, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.11667930692491686, |
| "grad_norm": 0.23207834362983704, |
| "learning_rate": 4.988869348264693e-05, |
| "loss": 0.3873, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.11667930692491686, |
| "eval_loss": 0.3395228683948517, |
| "eval_runtime": 127.7691, |
| "eval_samples_per_second": 30.524, |
| "eval_steps_per_second": 1.91, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.23335861384983372, |
| "grad_norm": 0.2957199215888977, |
| "learning_rate": 4.9004179305859345e-05, |
| "loss": 0.3799, |
| "step": 2000 |
| }, |
| { |
| "epoch": 0.23335861384983372, |
| "eval_loss": 0.3378797769546509, |
| "eval_runtime": 128.234, |
| "eval_samples_per_second": 30.413, |
| "eval_steps_per_second": 1.903, |
| "step": 2000 |
| } |
| ], |
| "logging_steps": 1000, |
| "max_steps": 17140, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 2, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 0.0, |
| "train_batch_size": 16, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
