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: 0.7696
- Matthews Correlation: 0.5136
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 |
|---|---|---|---|---|
| 0.5284 | 1.0 | 535 | 0.4948 | 0.4093 |
| 0.3529 | 2.0 | 1070 | 0.5135 | 0.4942 |
| 0.2417 | 3.0 | 1605 | 0.6303 | 0.5083 |
| 0.1818 | 4.0 | 2140 | 0.7696 | 0.5136 |
| 0.1302 | 5.0 | 2675 | 0.8774 | 0.5123 |
Framework versions
- Transformers 4.16.2
- Pytorch 1.10.0+cu111
- Datasets 1.18.3
- Tokenizers 0.11.0
- Downloads last month
- 19
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.