nlvr2_42
This model is a fine-tuned version of dandelin/vilt-b32-finetuned-nlvr2 on the nlvr2 dataset. It achieves the following results on the evaluation set:
- Loss: 0.7380
- Accuracy: 0.7453
- Test Accuracy: 0.7453
- Df Accuracy: 0.4389
- Unlearn Overall Accuracy: 0.6532
- Unlearn Time: 4925.1234
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: 32
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 2
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Overall Accuracy | Unlearn Overall Accuracy | Time |
|---|---|---|---|---|---|---|---|
| 0.2739 | 1.0 | 2700 | 0.5696 | 0.6265 | 0.5606 | 0.5606 | -1 |
| 0.1295 | 2.0 | 5400 | 0.7369 | 0.4389 | 0.6532 | 0.6532 | -1 |
Framework versions
- Transformers 4.39.3
- Pytorch 2.3.0+cu121
- Datasets 2.19.0
- Tokenizers 0.15.2