<!-- 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-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: 0.6968
- Accuracy: 0.4789
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: 5e-05
- train_batch_size: 128
- eval_batch_size: 128
- seed: 10
- distributed_type: multi-GPU
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 50
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.7192 | 1.0 | 5 | 0.6968 | 0.4789 |
| 0.6928 | 2.0 | 10 | 0.7003 | 0.2676 |
| 0.6921 | 3.0 | 15 | 0.7057 | 0.5211 |
| 0.6931 | 4.0 | 20 | 0.7282 | 0.3944 |
| 0.6922 | 5.0 | 25 | 0.7579 | 0.2535 |
| 0.68 | 6.0 | 30 | 0.8314 | 0.2254 |
| 0.6652 | 7.0 | 35 | 0.8990 | 0.1831 |
| 0.627 | 8.0 | 40 | 1.0187 | 0.2254 |
Framework versions
- Transformers 4.26.0
- Pytorch 1.14.0a0+410ce96
- Datasets 2.9.0
- Tokenizers 0.13.2
