--- language: - en license: apache-2.0 tags: - generated_from_trainer datasets: - glue metrics: - matthews_correlation model-index: - name: first_try results: - task: name: Text Classification type: text-classification dataset: name: GLUE COLA type: glue config: cola split: validation args: cola metrics: - name: Matthews Correlation type: matthews_correlation value: 0.554912808282685 --- # first_try This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the GLUE COLA dataset. It achieves the following results on the evaluation set: - Loss: 0.8516 - Matthews Correlation: 0.5549 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 2e-05 - train_batch_size: 32 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 30 - mixed_precision_training: Native AMP ### Training results | Training Loss | Epoch | Step | Validation Loss | Matthews Correlation | | |:-------------:|:-----:|:----:|:---------------:|:--------------------:|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------:| | No log | 1.0 | 268 | 0.7150 | 0.3947 | OrderedDict([(, {0: 512, 1: 256, 2: 320, 3: 448, 4: 640, 5: 640, 6: 768, 7: 576, 8: 448, 9: 256, 10: 384, 11: 320, 12: 949, 13: 959, 14: 1110, 15: 1096, 16: 1158, 17: 1062, 18: 1028, 19: 1014, 20: 670, 21: 436, 22: 348, 23: 370})]) | | No log | 1.0 | 268 | 0.6399 | 0.5222 | OrderedDict([(, {0: 768, 1: 768, 2: 768, 3: 768, 4: 768, 5: 768, 6: 768, 7: 768, 8: 768, 9: 768, 10: 768, 11: 768, 12: 3072, 13: 3072, 14: 3072, 15: 3072, 16: 3072, 17: 3072, 18: 3072, 19: 3072, 20: 3072, 21: 3072, 22: 3072, 23: 3072})]) | | 0.8522 | 2.0 | 536 | 0.7287 | 0.4630 | OrderedDict([(, {0: 512, 1: 256, 2: 320, 3: 448, 4: 640, 5: 640, 6: 768, 7: 576, 8: 448, 9: 256, 10: 384, 11: 320, 12: 949, 13: 959, 14: 1110, 15: 1096, 16: 1158, 17: 1062, 18: 1028, 19: 1014, 20: 670, 21: 436, 22: 348, 23: 370})]) | | 0.8522 | 2.0 | 536 | 0.6622 | 0.5624 | OrderedDict([(, {0: 768, 1: 768, 2: 768, 3: 768, 4: 768, 5: 768, 6: 768, 7: 768, 8: 768, 9: 768, 10: 768, 11: 768, 12: 3072, 13: 3072, 14: 3072, 15: 3072, 16: 3072, 17: 3072, 18: 3072, 19: 3072, 20: 3072, 21: 3072, 22: 3072, 23: 3072})]) | | 0.8522 | 3.0 | 804 | 0.7320 | 0.4775 | OrderedDict([(, {0: 512, 1: 256, 2: 320, 3: 448, 4: 640, 5: 640, 6: 768, 7: 576, 8: 448, 9: 256, 10: 384, 11: 320, 12: 949, 13: 959, 14: 1110, 15: 1096, 16: 1158, 17: 1062, 18: 1028, 19: 1014, 20: 670, 21: 436, 22: 348, 23: 370})]) | | 0.8522 | 3.0 | 804 | 0.6782 | 0.5573 | OrderedDict([(, {0: 768, 1: 768, 2: 768, 3: 768, 4: 768, 5: 768, 6: 768, 7: 768, 8: 768, 9: 768, 10: 768, 11: 768, 12: 3072, 13: 3072, 14: 3072, 15: 3072, 16: 3072, 17: 3072, 18: 3072, 19: 3072, 20: 3072, 21: 3072, 22: 3072, 23: 3072})]) | | 0.3135 | 4.0 | 1072 | 0.8995 | 0.4830 | OrderedDict([(, {0: 512, 1: 256, 2: 320, 3: 448, 4: 640, 5: 640, 6: 768, 7: 576, 8: 448, 9: 256, 10: 384, 11: 320, 12: 949, 13: 959, 14: 1110, 15: 1096, 16: 1158, 17: 1062, 18: 1028, 19: 1014, 20: 670, 21: 436, 22: 348, 23: 370})]) | | 0.3135 | 4.0 | 1072 | 0.7692 | 0.5549 | OrderedDict([(, {0: 768, 1: 768, 2: 768, 3: 768, 4: 768, 5: 768, 6: 768, 7: 768, 8: 768, 9: 768, 10: 768, 11: 768, 12: 3072, 13: 3072, 14: 3072, 15: 3072, 16: 3072, 17: 3072, 18: 3072, 19: 3072, 20: 3072, 21: 3072, 22: 3072, 23: 3072})]) | | 0.3135 | 5.0 | 1340 | 0.8262 | 0.5107 | OrderedDict([(, {0: 512, 1: 256, 2: 320, 3: 448, 4: 640, 5: 640, 6: 768, 7: 576, 8: 448, 9: 256, 10: 384, 11: 320, 12: 949, 13: 959, 14: 1110, 15: 1096, 16: 1158, 17: 1062, 18: 1028, 19: 1014, 20: 670, 21: 436, 22: 348, 23: 370})]) | | 0.3135 | 5.0 | 1340 | 0.6901 | 0.5834 | OrderedDict([(, {0: 768, 1: 768, 2: 768, 3: 768, 4: 768, 5: 768, 6: 768, 7: 768, 8: 768, 9: 768, 10: 768, 11: 768, 12: 3072, 13: 3072, 14: 3072, 15: 3072, 16: 3072, 17: 3072, 18: 3072, 19: 3072, 20: 3072, 21: 3072, 22: 3072, 23: 3072})]) | | 0.155 | 6.0 | 1608 | 0.8722 | 0.5076 | OrderedDict([(, {0: 512, 1: 256, 2: 320, 3: 448, 4: 640, 5: 640, 6: 768, 7: 576, 8: 448, 9: 256, 10: 384, 11: 320, 12: 949, 13: 959, 14: 1110, 15: 1096, 16: 1158, 17: 1062, 18: 1028, 19: 1014, 20: 670, 21: 436, 22: 348, 23: 370})]) | | 0.155 | 6.0 | 1608 | 0.7215 | 0.5925 | OrderedDict([(, {0: 768, 1: 768, 2: 768, 3: 768, 4: 768, 5: 768, 6: 768, 7: 768, 8: 768, 9: 768, 10: 768, 11: 768, 12: 3072, 13: 3072, 14: 3072, 15: 3072, 16: 3072, 17: 3072, 18: 3072, 19: 3072, 20: 3072, 21: 3072, 22: 3072, 23: 3072})]) | | 0.155 | 7.0 | 1876 | 0.9456 | 0.5054 | OrderedDict([(, {0: 512, 1: 256, 2: 320, 3: 448, 4: 640, 5: 640, 6: 768, 7: 576, 8: 448, 9: 256, 10: 384, 11: 320, 12: 949, 13: 959, 14: 1110, 15: 1096, 16: 1158, 17: 1062, 18: 1028, 19: 1014, 20: 670, 21: 436, 22: 348, 23: 370})]) | | 0.155 | 7.0 | 1876 | 0.8113 | 0.5765 | OrderedDict([(, {0: 768, 1: 768, 2: 768, 3: 768, 4: 768, 5: 768, 6: 768, 7: 768, 8: 768, 9: 768, 10: 768, 11: 768, 12: 3072, 13: 3072, 14: 3072, 15: 3072, 16: 3072, 17: 3072, 18: 3072, 19: 3072, 20: 3072, 21: 3072, 22: 3072, 23: 3072})]) | | 0.0957 | 8.0 | 2144 | 0.9191 | 0.5049 | OrderedDict([(, {0: 512, 1: 256, 2: 320, 3: 448, 4: 640, 5: 640, 6: 768, 7: 576, 8: 448, 9: 256, 10: 384, 11: 320, 12: 949, 13: 959, 14: 1110, 15: 1096, 16: 1158, 17: 1062, 18: 1028, 19: 1014, 20: 670, 21: 436, 22: 348, 23: 370})]) | | 0.0957 | 8.0 | 2144 | 0.7811 | 0.5885 | OrderedDict([(, {0: 768, 1: 768, 2: 768, 3: 768, 4: 768, 5: 768, 6: 768, 7: 768, 8: 768, 9: 768, 10: 768, 11: 768, 12: 3072, 13: 3072, 14: 3072, 15: 3072, 16: 3072, 17: 3072, 18: 3072, 19: 3072, 20: 3072, 21: 3072, 22: 3072, 23: 3072})]) | | 0.0957 | 9.0 | 2412 | 0.9647 | 0.4994 | OrderedDict([(, {0: 512, 1: 256, 2: 320, 3: 448, 4: 640, 5: 640, 6: 768, 7: 576, 8: 448, 9: 256, 10: 384, 11: 320, 12: 949, 13: 959, 14: 1110, 15: 1096, 16: 1158, 17: 1062, 18: 1028, 19: 1014, 20: 670, 21: 436, 22: 348, 23: 370})]) | | 0.0957 | 9.0 | 2412 | 0.8087 | 0.5598 | OrderedDict([(, {0: 768, 1: 768, 2: 768, 3: 768, 4: 768, 5: 768, 6: 768, 7: 768, 8: 768, 9: 768, 10: 768, 11: 768, 12: 3072, 13: 3072, 14: 3072, 15: 3072, 16: 3072, 17: 3072, 18: 3072, 19: 3072, 20: 3072, 21: 3072, 22: 3072, 23: 3072})]) | | 0.0729 | 10.0 | 2680 | 0.9290 | 0.4990 | OrderedDict([(, {0: 512, 1: 256, 2: 320, 3: 448, 4: 640, 5: 640, 6: 768, 7: 576, 8: 448, 9: 256, 10: 384, 11: 320, 12: 949, 13: 959, 14: 1110, 15: 1096, 16: 1158, 17: 1062, 18: 1028, 19: 1014, 20: 670, 21: 436, 22: 348, 23: 370})]) | | 0.0729 | 10.0 | 2680 | 0.8079 | 0.5754 | OrderedDict([(, {0: 768, 1: 768, 2: 768, 3: 768, 4: 768, 5: 768, 6: 768, 7: 768, 8: 768, 9: 768, 10: 768, 11: 768, 12: 3072, 13: 3072, 14: 3072, 15: 3072, 16: 3072, 17: 3072, 18: 3072, 19: 3072, 20: 3072, 21: 3072, 22: 3072, 23: 3072})]) | | 0.0729 | 11.0 | 2948 | 0.9496 | 0.4982 | OrderedDict([(, {0: 512, 1: 256, 2: 320, 3: 448, 4: 640, 5: 640, 6: 768, 7: 576, 8: 448, 9: 256, 10: 384, 11: 320, 12: 949, 13: 959, 14: 1110, 15: 1096, 16: 1158, 17: 1062, 18: 1028, 19: 1014, 20: 670, 21: 436, 22: 348, 23: 370})]) | | 0.0729 | 11.0 | 2948 | 0.8124 | 0.5728 | OrderedDict([(, {0: 768, 1: 768, 2: 768, 3: 768, 4: 768, 5: 768, 6: 768, 7: 768, 8: 768, 9: 768, 10: 768, 11: 768, 12: 3072, 13: 3072, 14: 3072, 15: 3072, 16: 3072, 17: 3072, 18: 3072, 19: 3072, 20: 3072, 21: 3072, 22: 3072, 23: 3072})]) | | 0.0626 | 12.0 | 3216 | 0.9496 | 0.4982 | OrderedDict([(, {0: 512, 1: 256, 2: 320, 3: 448, 4: 640, 5: 640, 6: 768, 7: 576, 8: 448, 9: 256, 10: 384, 11: 320, 12: 949, 13: 959, 14: 1110, 15: 1096, 16: 1158, 17: 1062, 18: 1028, 19: 1014, 20: 670, 21: 436, 22: 348, 23: 370})]) | | 0.0626 | 12.0 | 3216 | 0.8131 | 0.5728 | OrderedDict([(, {0: 768, 1: 768, 2: 768, 3: 768, 4: 768, 5: 768, 6: 768, 7: 768, 8: 768, 9: 768, 10: 768, 11: 768, 12: 3072, 13: 3072, 14: 3072, 15: 3072, 16: 3072, 17: 3072, 18: 3072, 19: 3072, 20: 3072, 21: 3072, 22: 3072, 23: 3072})]) | ### Framework versions - Transformers 4.29.1 - Pytorch 1.12.1 - Datasets 2.13.1 - Tokenizers 0.13.3