bert-fine-tuned-cola
This model is a fine-tuned version of bert-base-cased on the glue dataset. It achieves the following results on the evaluation set:
- Loss: 0.9503
- Matthews Correlation: 0.5765
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: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 4
Training results
Training Loss | Epoch | Step | Validation Loss | Matthews Correlation |
---|---|---|---|---|
0.4827 | 1.0 | 1069 | 0.5936 | 0.4448 |
0.3538 | 2.0 | 2138 | 0.5796 | 0.6023 |
0.2028 | 3.0 | 3207 | 0.7589 | 0.5779 |
0.1219 | 4.0 | 4276 | 0.9503 | 0.5765 |
Framework versions
- Transformers 4.27.3
- Pytorch 2.0.0+cu117
- Datasets 2.10.1
- Tokenizers 0.13.2
- Downloads last month
- 13
Dataset used to train joagonzalez/bert-fine-tuned-cola
Evaluation results
- Matthews Correlation on gluevalidation set self-reported0.576