| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.0, |
| "eval_steps": 4000, |
| "global_step": 9134, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.00010948105977665864, |
| "grad_norm": 5.878234386444092, |
| "learning_rate": 0.0, |
| "loss": 3.3696, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.4379242391066345, |
| "grad_norm": 4.34870719909668, |
| "learning_rate": 1.0944170771756979e-05, |
| "loss": 2.7485, |
| "step": 4000 |
| }, |
| { |
| "epoch": 0.4379242391066345, |
| "eval_cosine_accuracy": 0.948341429233551, |
| "eval_loss": 1.1948620080947876, |
| "eval_runtime": 24.3202, |
| "eval_samples_per_second": 389.224, |
| "eval_steps_per_second": 1.521, |
| "step": 4000 |
| }, |
| { |
| "epoch": 0.875848478213269, |
| "grad_norm": 6.708064079284668, |
| "learning_rate": 1.997258984476735e-05, |
| "loss": 2.6312, |
| "step": 8000 |
| }, |
| { |
| "epoch": 0.875848478213269, |
| "eval_cosine_accuracy": 0.8973166942596436, |
| "eval_loss": 1.4613265991210938, |
| "eval_runtime": 22.6953, |
| "eval_samples_per_second": 417.09, |
| "eval_steps_per_second": 1.63, |
| "step": 8000 |
| } |
| ], |
| "logging_steps": 4000, |
| "max_steps": 36536, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 4, |
| "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": 256, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
