| { |
| "best_metric": 2.8668248653411865, |
| "best_model_checkpoint": "/home/ubuntu/klue-bert-base-sentiment/ckpt/checkpoint-8000", |
| "epoch": 4.80439258750858, |
| "global_step": 14000, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.69, |
| "learning_rate": 1.9171814230153285e-05, |
| "loss": 3.5906, |
| "step": 2000 |
| }, |
| { |
| "epoch": 0.69, |
| "eval_accuracy": 0.24888450317487557, |
| "eval_f1": 0.2428758491014593, |
| "eval_loss": 3.097123622894287, |
| "eval_runtime": 51.8822, |
| "eval_samples_per_second": 449.249, |
| "eval_steps_per_second": 14.051, |
| "step": 2000 |
| }, |
| { |
| "epoch": 1.37, |
| "learning_rate": 1.6121406238084344e-05, |
| "loss": 2.9898, |
| "step": 4000 |
| }, |
| { |
| "epoch": 1.37, |
| "eval_accuracy": 0.27591384932212115, |
| "eval_f1": 0.27566530866405486, |
| "eval_loss": 2.9477760791778564, |
| "eval_runtime": 50.8962, |
| "eval_samples_per_second": 457.952, |
| "eval_steps_per_second": 14.323, |
| "step": 4000 |
| }, |
| { |
| "epoch": 2.06, |
| "learning_rate": 1.3070998246015405e-05, |
| "loss": 2.8459, |
| "step": 6000 |
| }, |
| { |
| "epoch": 2.06, |
| "eval_accuracy": 0.28659687660888966, |
| "eval_f1": 0.2826091515090862, |
| "eval_loss": 2.8875882625579834, |
| "eval_runtime": 50.8821, |
| "eval_samples_per_second": 458.078, |
| "eval_steps_per_second": 14.327, |
| "step": 6000 |
| }, |
| { |
| "epoch": 2.75, |
| "learning_rate": 1.0020590253946467e-05, |
| "loss": 2.6296, |
| "step": 8000 |
| }, |
| { |
| "epoch": 2.75, |
| "eval_accuracy": 0.29371889480006863, |
| "eval_f1": 0.29102037288558685, |
| "eval_loss": 2.8668248653411865, |
| "eval_runtime": 47.4836, |
| "eval_samples_per_second": 490.864, |
| "eval_steps_per_second": 15.353, |
| "step": 8000 |
| }, |
| { |
| "epoch": 3.43, |
| "learning_rate": 6.9701822618775275e-06, |
| "loss": 2.4791, |
| "step": 10000 |
| }, |
| { |
| "epoch": 3.43, |
| "eval_accuracy": 0.29573536983010124, |
| "eval_f1": 0.29324160202994004, |
| "eval_loss": 2.8735780715942383, |
| "eval_runtime": 46.5634, |
| "eval_samples_per_second": 500.565, |
| "eval_steps_per_second": 15.656, |
| "step": 10000 |
| }, |
| { |
| "epoch": 4.12, |
| "learning_rate": 3.919774269808587e-06, |
| "loss": 2.3754, |
| "step": 12000 |
| }, |
| { |
| "epoch": 4.12, |
| "eval_accuracy": 0.29963960871803674, |
| "eval_f1": 0.2981925753127358, |
| "eval_loss": 2.8763158321380615, |
| "eval_runtime": 50.6623, |
| "eval_samples_per_second": 460.066, |
| "eval_steps_per_second": 14.389, |
| "step": 12000 |
| }, |
| { |
| "epoch": 4.8, |
| "learning_rate": 8.693662777396478e-07, |
| "loss": 2.2536, |
| "step": 14000 |
| }, |
| { |
| "epoch": 4.8, |
| "eval_accuracy": 0.30096962416337736, |
| "eval_f1": 0.29941923278028376, |
| "eval_loss": 2.8771862983703613, |
| "eval_runtime": 52.0168, |
| "eval_samples_per_second": 448.086, |
| "eval_steps_per_second": 14.015, |
| "step": 14000 |
| } |
| ], |
| "max_steps": 14570, |
| "num_train_epochs": 5, |
| "total_flos": 1.3559570938389888e+16, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
