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: 0.7436
- Matthews Correlation: 0.5396
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 |
|---|---|---|---|---|
| 0.5216 | 1.0 | 535 | 0.4678 | 0.4810 |
| 0.3433 | 2.0 | 1070 | 0.5100 | 0.4923 |
| 0.2273 | 3.0 | 1605 | 0.5989 | 0.5131 |
| 0.175 | 4.0 | 2140 | 0.7436 | 0.5396 |
| 0.1264 | 5.0 | 2675 | 0.8338 | 0.5361 |
Framework versions
- Transformers 4.32.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.4
- Tokenizers 0.13.3
- Downloads last month
- 6
Model tree for Danxtshake/distilbert-base-uncased-finetuned-cola
Base model
distilbert/distilbert-base-uncasedDataset used to train Danxtshake/distilbert-base-uncased-finetuned-cola
Evaluation results
- Matthews Correlation on gluevalidation set self-reported0.540