| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 20.0, |
| "eval_steps": 500, |
| "global_step": 860, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.0, |
| "eval_loss": 0.1848125457763672, |
| "eval_runtime": 0.1624, |
| "eval_samples_per_second": 184.776, |
| "eval_steps_per_second": 12.318, |
| "step": 43 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_loss": 0.1869390457868576, |
| "eval_runtime": 0.1559, |
| "eval_samples_per_second": 192.491, |
| "eval_steps_per_second": 12.833, |
| "step": 86 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_loss": 0.16996455192565918, |
| "eval_runtime": 0.1555, |
| "eval_samples_per_second": 192.951, |
| "eval_steps_per_second": 12.863, |
| "step": 129 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_loss": 0.18744808435440063, |
| "eval_runtime": 0.1559, |
| "eval_samples_per_second": 192.397, |
| "eval_steps_per_second": 12.826, |
| "step": 172 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_loss": 0.19191579520702362, |
| "eval_runtime": 0.1554, |
| "eval_samples_per_second": 193.082, |
| "eval_steps_per_second": 12.872, |
| "step": 215 |
| }, |
| { |
| "epoch": 6.0, |
| "eval_loss": 0.2175399214029312, |
| "eval_runtime": 0.1557, |
| "eval_samples_per_second": 192.712, |
| "eval_steps_per_second": 12.847, |
| "step": 258 |
| }, |
| { |
| "epoch": 7.0, |
| "eval_loss": 0.21879200637340546, |
| "eval_runtime": 0.2731, |
| "eval_samples_per_second": 109.862, |
| "eval_steps_per_second": 7.324, |
| "step": 301 |
| }, |
| { |
| "epoch": 8.0, |
| "eval_loss": 0.23720744252204895, |
| "eval_runtime": 0.1555, |
| "eval_samples_per_second": 192.879, |
| "eval_steps_per_second": 12.859, |
| "step": 344 |
| }, |
| { |
| "epoch": 9.0, |
| "eval_loss": 0.21279582381248474, |
| "eval_runtime": 0.1555, |
| "eval_samples_per_second": 192.91, |
| "eval_steps_per_second": 12.861, |
| "step": 387 |
| }, |
| { |
| "epoch": 10.0, |
| "eval_loss": 0.2320726364850998, |
| "eval_runtime": 0.1553, |
| "eval_samples_per_second": 193.12, |
| "eval_steps_per_second": 12.875, |
| "step": 430 |
| }, |
| { |
| "epoch": 11.0, |
| "eval_loss": 0.2363985925912857, |
| "eval_runtime": 0.1555, |
| "eval_samples_per_second": 192.904, |
| "eval_steps_per_second": 12.86, |
| "step": 473 |
| }, |
| { |
| "epoch": 11.627906976744185, |
| "grad_norm": 0.004475043620914221, |
| "learning_rate": 2.0930232558139536e-05, |
| "loss": 0.0218, |
| "step": 500 |
| }, |
| { |
| "epoch": 12.0, |
| "eval_loss": 0.2457895576953888, |
| "eval_runtime": 0.1554, |
| "eval_samples_per_second": 193.009, |
| "eval_steps_per_second": 12.867, |
| "step": 516 |
| }, |
| { |
| "epoch": 13.0, |
| "eval_loss": 0.24754366278648376, |
| "eval_runtime": 0.156, |
| "eval_samples_per_second": 192.33, |
| "eval_steps_per_second": 12.822, |
| "step": 559 |
| }, |
| { |
| "epoch": 14.0, |
| "eval_loss": 0.25531861186027527, |
| "eval_runtime": 0.1554, |
| "eval_samples_per_second": 192.995, |
| "eval_steps_per_second": 12.866, |
| "step": 602 |
| }, |
| { |
| "epoch": 15.0, |
| "eval_loss": 0.255403608083725, |
| "eval_runtime": 0.1555, |
| "eval_samples_per_second": 192.923, |
| "eval_steps_per_second": 12.862, |
| "step": 645 |
| }, |
| { |
| "epoch": 16.0, |
| "eval_loss": 0.2558601498603821, |
| "eval_runtime": 0.1557, |
| "eval_samples_per_second": 192.702, |
| "eval_steps_per_second": 12.847, |
| "step": 688 |
| }, |
| { |
| "epoch": 17.0, |
| "eval_loss": 0.2556142210960388, |
| "eval_runtime": 0.1555, |
| "eval_samples_per_second": 192.986, |
| "eval_steps_per_second": 12.866, |
| "step": 731 |
| }, |
| { |
| "epoch": 18.0, |
| "eval_loss": 0.2558564245700836, |
| "eval_runtime": 0.1555, |
| "eval_samples_per_second": 192.968, |
| "eval_steps_per_second": 12.865, |
| "step": 774 |
| }, |
| { |
| "epoch": 19.0, |
| "eval_loss": 0.25610417127609253, |
| "eval_runtime": 0.1555, |
| "eval_samples_per_second": 192.974, |
| "eval_steps_per_second": 12.865, |
| "step": 817 |
| }, |
| { |
| "epoch": 20.0, |
| "eval_loss": 0.2562636733055115, |
| "eval_runtime": 0.1555, |
| "eval_samples_per_second": 192.888, |
| "eval_steps_per_second": 12.859, |
| "step": 860 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 860, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 20, |
| "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": 2214650181888000.0, |
| "train_batch_size": 16, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
