bert-base-uncased-wnli
This model is a fine-tuned version of bert-base-uncased on the GLUE WNLI dataset. It achieves the following results on the evaluation set:
- Loss: 0.6959
- Accuracy: 0.5634
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: 32
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3.0
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| No log | 1.0 | 20 | 0.6933 | 0.5493 |
| No log | 2.0 | 40 | 0.6959 | 0.5634 |
| No log | 3.0 | 60 | 0.6978 | 0.5352 |
Framework versions
- Transformers 4.20.0.dev0
- Pytorch 1.11.0+cu113
- Datasets 2.1.0
- Tokenizers 0.12.1