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: 0.8456
- Matthews Correlation: 0.5500
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 |
---|---|---|---|---|
0.5197 | 1.0 | 535 | 0.5477 | 0.4130 |
0.3456 | 2.0 | 1070 | 0.5035 | 0.5239 |
0.2342 | 3.0 | 1605 | 0.6100 | 0.5285 |
0.1698 | 4.0 | 2140 | 0.7556 | 0.5456 |
0.1295 | 5.0 | 2675 | 0.8456 | 0.5500 |
Framework versions
- Transformers 4.18.0
- Pytorch 1.10.1+cu113
- Datasets 2.1.0
- Tokenizers 0.12.1
- Downloads last month
- 9
Inference Providers
NEW
This model is not currently available via any of the supported third-party Inference Providers, and
the model is not deployed on the HF Inference API.