| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 10.0, |
| "eval_steps": 500, |
| "global_step": 430, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.0, |
| "eval_loss": 0.0004615767684299499, |
| "eval_runtime": 0.1569, |
| "eval_samples_per_second": 191.198, |
| "eval_steps_per_second": 12.747, |
| "step": 43 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_loss": 0.0002889486204367131, |
| "eval_runtime": 0.1564, |
| "eval_samples_per_second": 191.862, |
| "eval_steps_per_second": 12.791, |
| "step": 86 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_loss": 1.567967228766065e-05, |
| "eval_runtime": 0.1559, |
| "eval_samples_per_second": 192.463, |
| "eval_steps_per_second": 12.831, |
| "step": 129 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_loss": 7.753499630780425e-06, |
| "eval_runtime": 0.1566, |
| "eval_samples_per_second": 191.515, |
| "eval_steps_per_second": 12.768, |
| "step": 172 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_loss": 6.22713605480385e-06, |
| "eval_runtime": 0.1561, |
| "eval_samples_per_second": 192.175, |
| "eval_steps_per_second": 12.812, |
| "step": 215 |
| }, |
| { |
| "epoch": 6.0, |
| "eval_loss": 3.138812644465361e-06, |
| "eval_runtime": 0.156, |
| "eval_samples_per_second": 192.273, |
| "eval_steps_per_second": 12.818, |
| "step": 258 |
| }, |
| { |
| "epoch": 7.0, |
| "eval_loss": 2.120739281963324e-06, |
| "eval_runtime": 0.1558, |
| "eval_samples_per_second": 192.545, |
| "eval_steps_per_second": 12.836, |
| "step": 301 |
| }, |
| { |
| "epoch": 8.0, |
| "eval_loss": 1.6976943015833967e-06, |
| "eval_runtime": 0.1557, |
| "eval_samples_per_second": 192.72, |
| "eval_steps_per_second": 12.848, |
| "step": 344 |
| }, |
| { |
| "epoch": 9.0, |
| "eval_loss": 1.493080389991519e-06, |
| "eval_runtime": 0.1558, |
| "eval_samples_per_second": 192.52, |
| "eval_steps_per_second": 12.835, |
| "step": 387 |
| }, |
| { |
| "epoch": 10.0, |
| "eval_loss": 1.48043568515277e-06, |
| "eval_runtime": 0.1558, |
| "eval_samples_per_second": 192.59, |
| "eval_steps_per_second": 12.839, |
| "step": 430 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 430, |
| "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": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 1109286387580800.0, |
| "train_batch_size": 16, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
