| { | |
| "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 | |
| } | |