| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.2333994631812347, |
| "eval_steps": 250, |
| "global_step": 250, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.2333994631812347, |
| "grad_norm": 8.384697914123535, |
| "learning_rate": 8.959847237666421e-05, |
| "loss": 0.3776, |
| "step": 250 |
| }, |
| { |
| "epoch": 0.2333994631812347, |
| "eval_loss": 0.2075573056936264, |
| "eval_runtime": 14.5853, |
| "eval_samples_per_second": 5.965, |
| "eval_steps_per_second": 5.965, |
| "step": 250 |
| } |
| ], |
| "logging_steps": 250, |
| "max_steps": 1071, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 250, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 6785029677735936.0, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
