<!-- 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. -->
BERT_MNLI_YN
This model is a fine-tuned version of textattack/bert-base-uncased-MNLI on the circa dataset. It achieves the following results on the evaluation set:
- Loss: 0.3958
- Accuracy: 0.8979
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: 3e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.4866 | 1.0 | 619 | 0.3442 | 0.8854 |
| 0.2853 | 2.0 | 1238 | 0.3432 | 0.8962 |
| 0.1806 | 3.0 | 1857 | 0.3958 | 0.8979 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.13.1+cu116
- Datasets 2.10.1
- Tokenizers 0.13.2
