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: 0.8486
- Matthews Correlation: 0.5209
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 |
|---|---|---|---|---|
| 0.5265 | 1.0 | 535 | 0.5479 | 0.4049 |
| 0.3571 | 2.0 | 1070 | 0.5002 | 0.5164 |
| 0.2432 | 3.0 | 1605 | 0.6242 | 0.5091 |
| 0.173 | 4.0 | 2140 | 0.7559 | 0.5120 |
| 0.1352 | 5.0 | 2675 | 0.8486 | 0.5209 |
Framework versions
- Transformers 4.9.1
- Pytorch 1.9.0+cu102
- Datasets 1.10.2
- Tokenizers 0.10.3
- Downloads last month
- 11
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.