nli-distilroberta-base-finetuned-cola
This model is a fine-tuned version of cross-encoder/nli-distilroberta-base on the glue dataset. It achieves the following results on the evaluation set:
- Loss: 0.8280
- Matthews Correlation: 0.4957
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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Matthews Correlation |
|---|---|---|---|---|
| 0.5646 | 1.0 | 535 | 0.6462 | 0.3422 |
| 0.4267 | 2.0 | 1070 | 0.5672 | 0.4422 |
| 0.3354 | 3.0 | 1605 | 0.6441 | 0.4698 |
| 0.2723 | 4.0 | 2140 | 0.7464 | 0.4670 |
| 0.2204 | 5.0 | 2675 | 0.8280 | 0.4957 |
Framework versions
- Transformers 4.25.1
- Pytorch 1.12.1+cu113
- Datasets 2.7.1
- Tokenizers 0.13.2