| { |
| "best_metric": 0.9405740225181408, |
| "best_model_checkpoint": "model_saves/xlnet-large_lemon_5k_1_p3/checkpoint-536", |
| "epoch": 5.0, |
| "global_step": 1340, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.939696329341786, |
| "eval_loss": 0.43273577094078064, |
| "eval_runtime": 4.7619, |
| "eval_samples_per_second": 920.217, |
| "eval_steps_per_second": 7.35, |
| "step": 268 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.9405740225181408, |
| "eval_loss": 0.44831612706184387, |
| "eval_runtime": 4.7379, |
| "eval_samples_per_second": 924.88, |
| "eval_steps_per_second": 7.387, |
| "step": 536 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.9403615872270487, |
| "eval_loss": 0.48137167096138, |
| "eval_runtime": 4.7244, |
| "eval_samples_per_second": 927.534, |
| "eval_steps_per_second": 7.408, |
| "step": 804 |
| }, |
| { |
| "epoch": 3.73, |
| "learning_rate": 1e-05, |
| "loss": 0.3281, |
| "step": 1000 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_accuracy": 0.9393776764051477, |
| "eval_loss": 0.5127309560775757, |
| "eval_runtime": 4.736, |
| "eval_samples_per_second": 925.249, |
| "eval_steps_per_second": 7.39, |
| "step": 1072 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_accuracy": 0.9391484699068638, |
| "eval_loss": 0.5563333034515381, |
| "eval_runtime": 4.7452, |
| "eval_samples_per_second": 923.467, |
| "eval_steps_per_second": 7.376, |
| "step": 1340 |
| }, |
| { |
| "epoch": 5.0, |
| "step": 1340, |
| "total_flos": 2.12276846002176e+16, |
| "train_loss": 0.2986501779129256, |
| "train_runtime": 548.098, |
| "train_samples_per_second": 938.81, |
| "train_steps_per_second": 7.334 |
| } |
| ], |
| "max_steps": 4020, |
| "num_train_epochs": 15, |
| "total_flos": 2.12276846002176e+16, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
