distilbert-base-uncased-finetuned-cola
This model is a fine-tuned version of distilbert-base-uncased on the glue dataset. It achieves the following results on the evaluation set:
- Loss: 1.0766
- Matthews Correlation: 0.5238
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: 2.403175733231667e-05
- train_batch_size: 8
- eval_batch_size: 16
- seed: 33
- 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 |
|---|---|---|---|---|
| 0.4954 | 1.0 | 1069 | 0.4770 | 0.4589 |
| 0.3627 | 2.0 | 2138 | 0.5464 | 0.4998 |
| 0.2576 | 3.0 | 3207 | 0.8439 | 0.4933 |
| 0.1488 | 4.0 | 4276 | 1.0184 | 0.5035 |
| 0.1031 | 5.0 | 5345 | 1.0766 | 0.5238 |
Framework versions
- Transformers 4.17.0
- Pytorch 1.10.0+cu111
- Datasets 2.0.0
- Tokenizers 0.11.6
- Downloads last month
- 8
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.