distilbert-base-uncased-finetuned-cola
This model is a fine-tuned version of distilbert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.9675
- Matthews Correlation: 0.5347
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 |
---|---|---|---|---|
0.3536 | 1.0 | 535 | 0.4962 | 0.4748 |
0.2332 | 2.0 | 1070 | 0.6062 | 0.5024 |
0.1681 | 3.0 | 1605 | 0.7948 | 0.5262 |
0.137 | 4.0 | 2140 | 0.9381 | 0.5023 |
0.0804 | 5.0 | 2675 | 0.9675 | 0.5347 |
Framework versions
- Transformers 4.41.0.dev0
- Pytorch 2.2.1+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1
- Downloads last month
- 0