| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 3.3557046979865772, |
| "eval_steps": 500, |
| "global_step": 500, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.5050505050505051, |
| "eval_loss": 2.2999494075775146, |
| "eval_runtime": 8.1743, |
| "eval_samples_per_second": 36.333, |
| "eval_steps_per_second": 4.649, |
| "step": 149 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.6195286195286195, |
| "eval_loss": 1.9136502742767334, |
| "eval_runtime": 8.1758, |
| "eval_samples_per_second": 36.327, |
| "eval_steps_per_second": 4.648, |
| "step": 298 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.6599326599326599, |
| "eval_loss": 1.7068243026733398, |
| "eval_runtime": 8.1915, |
| "eval_samples_per_second": 36.257, |
| "eval_steps_per_second": 4.639, |
| "step": 447 |
| }, |
| { |
| "epoch": 3.3557046979865772, |
| "grad_norm": 15.295294761657715, |
| "learning_rate": 3.3255033557046986e-05, |
| "loss": 2.0179, |
| "step": 500 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 1490, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 10, |
| "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": 1050398581358592.0, |
| "train_batch_size": 8, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
