| { |
| "best_metric": 0.9166666666666666, |
| "best_model_checkpoint": "test/checkpoint-16", |
| "epoch": 19.727272727272727, |
| "global_step": 40, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.73, |
| "eval_accuracy": 0.6388888888888888, |
| "eval_f1": 0.5581699346405229, |
| "eval_loss": 0.6255224943161011, |
| "eval_precision": 0.6481481481481481, |
| "eval_recall": 0.6388888888888888, |
| "eval_runtime": 5.2731, |
| "eval_samples_per_second": 6.827, |
| "eval_steps_per_second": 0.19, |
| "step": 2 |
| }, |
| { |
| "epoch": 1.73, |
| "eval_accuracy": 0.75, |
| "eval_f1": 0.7120158887785502, |
| "eval_loss": 0.4980746805667877, |
| "eval_precision": 0.8225806451612904, |
| "eval_recall": 0.75, |
| "eval_runtime": 6.1411, |
| "eval_samples_per_second": 5.862, |
| "eval_steps_per_second": 0.163, |
| "step": 4 |
| }, |
| { |
| "epoch": 2.73, |
| "eval_accuracy": 0.75, |
| "eval_f1": 0.7429787234042554, |
| "eval_loss": 0.4359954297542572, |
| "eval_precision": 0.7472727272727272, |
| "eval_recall": 0.75, |
| "eval_runtime": 4.7783, |
| "eval_samples_per_second": 7.534, |
| "eval_steps_per_second": 0.209, |
| "step": 6 |
| }, |
| { |
| "epoch": 3.73, |
| "eval_accuracy": 0.8055555555555556, |
| "eval_f1": 0.7943409247757074, |
| "eval_loss": 0.38212475180625916, |
| "eval_precision": 0.8209876543209876, |
| "eval_recall": 0.8055555555555556, |
| "eval_runtime": 4.9721, |
| "eval_samples_per_second": 7.24, |
| "eval_steps_per_second": 0.201, |
| "step": 8 |
| }, |
| { |
| "epoch": 4.73, |
| "learning_rate": 0.0001, |
| "loss": 0.4879, |
| "step": 10 |
| }, |
| { |
| "epoch": 4.73, |
| "eval_accuracy": 0.8611111111111112, |
| "eval_f1": 0.857210401891253, |
| "eval_loss": 0.26968610286712646, |
| "eval_precision": 0.8668686868686869, |
| "eval_recall": 0.8611111111111112, |
| "eval_runtime": 4.5739, |
| "eval_samples_per_second": 7.871, |
| "eval_steps_per_second": 0.219, |
| "step": 10 |
| }, |
| { |
| "epoch": 5.73, |
| "eval_accuracy": 0.8333333333333334, |
| "eval_f1": 0.8263888888888888, |
| "eval_loss": 0.3342033922672272, |
| "eval_precision": 0.8435897435897436, |
| "eval_recall": 0.8333333333333334, |
| "eval_runtime": 4.9205, |
| "eval_samples_per_second": 7.316, |
| "eval_steps_per_second": 0.203, |
| "step": 12 |
| }, |
| { |
| "epoch": 6.73, |
| "eval_accuracy": 0.8611111111111112, |
| "eval_f1": 0.857210401891253, |
| "eval_loss": 0.26710909605026245, |
| "eval_precision": 0.8668686868686869, |
| "eval_recall": 0.8611111111111112, |
| "eval_runtime": 5.0847, |
| "eval_samples_per_second": 7.08, |
| "eval_steps_per_second": 0.197, |
| "step": 14 |
| }, |
| { |
| "epoch": 7.73, |
| "eval_accuracy": 0.9166666666666666, |
| "eval_f1": 0.9160493827160493, |
| "eval_loss": 0.2436762899160385, |
| "eval_precision": 0.9169453734671126, |
| "eval_recall": 0.9166666666666666, |
| "eval_runtime": 4.7098, |
| "eval_samples_per_second": 7.644, |
| "eval_steps_per_second": 0.212, |
| "step": 16 |
| }, |
| { |
| "epoch": 8.73, |
| "eval_accuracy": 0.9166666666666666, |
| "eval_f1": 0.9160493827160493, |
| "eval_loss": 0.23434966802597046, |
| "eval_precision": 0.9169453734671126, |
| "eval_recall": 0.9166666666666666, |
| "eval_runtime": 4.6359, |
| "eval_samples_per_second": 7.766, |
| "eval_steps_per_second": 0.216, |
| "step": 18 |
| }, |
| { |
| "epoch": 9.73, |
| "learning_rate": 6.666666666666667e-05, |
| "loss": 0.0279, |
| "step": 20 |
| }, |
| { |
| "epoch": 9.73, |
| "eval_accuracy": 0.9166666666666666, |
| "eval_f1": 0.9160493827160493, |
| "eval_loss": 0.24419277906417847, |
| "eval_precision": 0.9169453734671126, |
| "eval_recall": 0.9166666666666666, |
| "eval_runtime": 4.7814, |
| "eval_samples_per_second": 7.529, |
| "eval_steps_per_second": 0.209, |
| "step": 20 |
| }, |
| { |
| "epoch": 10.73, |
| "eval_accuracy": 0.8611111111111112, |
| "eval_f1": 0.857210401891253, |
| "eval_loss": 0.253448486328125, |
| "eval_precision": 0.8668686868686869, |
| "eval_recall": 0.8611111111111112, |
| "eval_runtime": 6.6388, |
| "eval_samples_per_second": 5.423, |
| "eval_steps_per_second": 0.151, |
| "step": 22 |
| }, |
| { |
| "epoch": 11.73, |
| "eval_accuracy": 0.8611111111111112, |
| "eval_f1": 0.857210401891253, |
| "eval_loss": 0.28706809878349304, |
| "eval_precision": 0.8668686868686869, |
| "eval_recall": 0.8611111111111112, |
| "eval_runtime": 4.5584, |
| "eval_samples_per_second": 7.898, |
| "eval_steps_per_second": 0.219, |
| "step": 24 |
| }, |
| { |
| "epoch": 12.73, |
| "eval_accuracy": 0.8611111111111112, |
| "eval_f1": 0.857210401891253, |
| "eval_loss": 0.27148592472076416, |
| "eval_precision": 0.8668686868686869, |
| "eval_recall": 0.8611111111111112, |
| "eval_runtime": 4.6864, |
| "eval_samples_per_second": 7.682, |
| "eval_steps_per_second": 0.213, |
| "step": 26 |
| }, |
| { |
| "epoch": 13.73, |
| "eval_accuracy": 0.8611111111111112, |
| "eval_f1": 0.857210401891253, |
| "eval_loss": 0.28809821605682373, |
| "eval_precision": 0.8668686868686869, |
| "eval_recall": 0.8611111111111112, |
| "eval_runtime": 4.7378, |
| "eval_samples_per_second": 7.598, |
| "eval_steps_per_second": 0.211, |
| "step": 28 |
| }, |
| { |
| "epoch": 14.73, |
| "learning_rate": 3.3333333333333335e-05, |
| "loss": 0.0021, |
| "step": 30 |
| }, |
| { |
| "epoch": 14.73, |
| "eval_accuracy": 0.8611111111111112, |
| "eval_f1": 0.857210401891253, |
| "eval_loss": 0.27546411752700806, |
| "eval_precision": 0.8668686868686869, |
| "eval_recall": 0.8611111111111112, |
| "eval_runtime": 4.6181, |
| "eval_samples_per_second": 7.795, |
| "eval_steps_per_second": 0.217, |
| "step": 30 |
| }, |
| { |
| "epoch": 15.73, |
| "eval_accuracy": 0.8888888888888888, |
| "eval_f1": 0.8870308435525827, |
| "eval_loss": 0.2769797444343567, |
| "eval_precision": 0.8912037037037036, |
| "eval_recall": 0.8888888888888888, |
| "eval_runtime": 4.8337, |
| "eval_samples_per_second": 7.448, |
| "eval_steps_per_second": 0.207, |
| "step": 32 |
| }, |
| { |
| "epoch": 16.73, |
| "eval_accuracy": 0.8888888888888888, |
| "eval_f1": 0.8870308435525827, |
| "eval_loss": 0.2637002766132355, |
| "eval_precision": 0.8912037037037036, |
| "eval_recall": 0.8888888888888888, |
| "eval_runtime": 4.74, |
| "eval_samples_per_second": 7.595, |
| "eval_steps_per_second": 0.211, |
| "step": 34 |
| }, |
| { |
| "epoch": 17.73, |
| "eval_accuracy": 0.9166666666666666, |
| "eval_f1": 0.9160493827160493, |
| "eval_loss": 0.24998606741428375, |
| "eval_precision": 0.9169453734671126, |
| "eval_recall": 0.9166666666666666, |
| "eval_runtime": 4.6548, |
| "eval_samples_per_second": 7.734, |
| "eval_steps_per_second": 0.215, |
| "step": 36 |
| }, |
| { |
| "epoch": 18.73, |
| "eval_accuracy": 0.9166666666666666, |
| "eval_f1": 0.9160493827160493, |
| "eval_loss": 0.25946107506752014, |
| "eval_precision": 0.9169453734671126, |
| "eval_recall": 0.9166666666666666, |
| "eval_runtime": 4.7568, |
| "eval_samples_per_second": 7.568, |
| "eval_steps_per_second": 0.21, |
| "step": 38 |
| }, |
| { |
| "epoch": 19.73, |
| "learning_rate": 0.0, |
| "loss": 0.0008, |
| "step": 40 |
| }, |
| { |
| "epoch": 19.73, |
| "eval_accuracy": 0.9166666666666666, |
| "eval_f1": 0.9160493827160493, |
| "eval_loss": 0.26713693141937256, |
| "eval_precision": 0.9169453734671126, |
| "eval_recall": 0.9166666666666666, |
| "eval_runtime": 5.5818, |
| "eval_samples_per_second": 6.45, |
| "eval_steps_per_second": 0.179, |
| "step": 40 |
| }, |
| { |
| "epoch": 19.73, |
| "step": 40, |
| "total_flos": 1.0467617957139087e+18, |
| "train_loss": 0.12968791872262955, |
| "train_runtime": 733.2509, |
| "train_samples_per_second": 18.657, |
| "train_steps_per_second": 0.055 |
| } |
| ], |
| "max_steps": 40, |
| "num_train_epochs": 20, |
| "total_flos": 1.0467617957139087e+18, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
