distilbert-base-uncased-finetuned-cola-v2
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: 1.2087
- Matthews Correlation: 0.7439
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: 6.253420148763903e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 25
- 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 |
|---|---|---|---|---|
| No log | 1.0 | 8 | 1.7954 | 0.4437 |
| No log | 2.0 | 16 | 1.6033 | 0.2381 |
| No log | 3.0 | 24 | 1.4112 | 0.4904 |
| No log | 4.0 | 32 | 1.2758 | 0.5401 |
| No log | 5.0 | 40 | 1.2087 | 0.7439 |
Framework versions
- Transformers 4.24.0
- Pytorch 1.12.1+cu113
- Datasets 2.7.1
- Tokenizers 0.13.2