bert-base-uncased-finetuned-cola
This model is a fine-tuned version of bert-base-uncased on the glue dataset. It achieves the following results on the evaluation set:
- Loss: 1.2150
- Matthews Correlation: 0.5788
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: 1.1521858230688484e-05
- train_batch_size: 8
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 8
Training results
Training Loss | Epoch | Step | Validation Loss | Matthews Correlation |
---|---|---|---|---|
0.4531 | 1.0 | 1069 | 0.4530 | 0.5275 |
0.3349 | 2.0 | 2138 | 0.5377 | 0.5475 |
0.2624 | 3.0 | 3207 | 0.8287 | 0.5574 |
0.1903 | 4.0 | 4276 | 0.8971 | 0.5525 |
0.1356 | 5.0 | 5345 | 0.9994 | 0.5662 |
0.0861 | 6.0 | 6414 | 1.0434 | 0.5731 |
0.0576 | 7.0 | 7483 | 1.1683 | 0.5735 |
0.0504 | 8.0 | 8552 | 1.2150 | 0.5788 |
Framework versions
- Transformers 4.28.1
- Pytorch 2.0.0+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3
- Downloads last month
- 11
Dataset used to train Attakuan/bert-base-uncased-finetuned-cola
Evaluation results
- Matthews Correlation on gluevalidation set self-reported0.579