<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
distilbert-base-uncased-response-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: 0.9774
- Matthews Correlation: 0.3330
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 | 23 | 1.0662 | 0.0 |
| No log | 2.0 | 46 | 1.0175 | 0.0 |
| No log | 3.0 | 69 | 1.0001 | 0.0 |
| No log | 4.0 | 92 | 0.9852 | 0.1196 |
| No log | 5.0 | 115 | 0.9836 | 0.2326 |
| No log | 6.0 | 138 | 0.9680 | 0.1808 |
| No log | 7.0 | 161 | 0.9774 | 0.3330 |
| No log | 8.0 | 184 | 0.9786 | 0.2881 |
| No log | 9.0 | 207 | 0.9974 | 0.2235 |
| No log | 10.0 | 230 | 0.9957 | 0.2031 |
Framework versions
- Transformers 4.24.0
- Pytorch 1.12.1+cu113
- Datasets 2.6.1
- Tokenizers 0.13.2
