| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.0, |
| "eval_steps": 500, |
| "global_step": 23, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.43478260869565216, |
| "grad_norm": 7.840970039367676, |
| "learning_rate": 1.4539904997395468e-05, |
| "loss": 1.3694, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.8695652173913043, |
| "grad_norm": 2.1000635623931885, |
| "learning_rate": 1.0899347581163222e-06, |
| "loss": 1.1062, |
| "step": 20 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_loss": 1.0602577924728394, |
| "eval_runtime": 3.2349, |
| "eval_samples_per_second": 190.731, |
| "eval_steps_per_second": 3.091, |
| "step": 23 |
| }, |
| { |
| "epoch": 1.0, |
| "step": 23, |
| "total_flos": 2.572343380583383e+17, |
| "train_loss": 1.2197923452957817, |
| "train_runtime": 1476.3308, |
| "train_samples_per_second": 7.938, |
| "train_steps_per_second": 0.016 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 23, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 2.572343380583383e+17, |
| "train_batch_size": 16, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
