distilbert-base-uncased-finetuned-cola-4
This model is a fine-tuned version of distilbert-base-uncased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0011
- Matthews Correlation: 1.0
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: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Matthews Correlation |
|---|---|---|---|---|
| No log | 1.0 | 104 | 0.0243 | 1.0 |
| No log | 2.0 | 208 | 0.0074 | 1.0 |
| No log | 3.0 | 312 | 0.0041 | 1.0 |
| No log | 4.0 | 416 | 0.0028 | 1.0 |
| 0.0929 | 5.0 | 520 | 0.0021 | 1.0 |
| 0.0929 | 6.0 | 624 | 0.0016 | 1.0 |
| 0.0929 | 7.0 | 728 | 0.0014 | 1.0 |
| 0.0929 | 8.0 | 832 | 0.0012 | 1.0 |
| 0.0929 | 9.0 | 936 | 0.0012 | 1.0 |
| 0.0021 | 10.0 | 1040 | 0.0011 | 1.0 |
Framework versions
- Transformers 4.12.3
- Pytorch 1.10.0+cu111
- Datasets 1.15.1
- Tokenizers 0.10.3