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: -5.5292
- Accuracy: 0.6346
- Test Accuracy: 0.6346
- Df Accuracy: 0.7313
- Unlearn Overall Accuracy: 0.4517
- Unlearn Time: 583.1439
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: 1e-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 |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 54 | -2.7721 | 0.8008 | 0.4383 | 0.4383 | -1 |
| No log | 2.0 | 108 | -5.5992 | 0.7313 | 0.4517 | 0.4517 | -1 |
Framework versions
- Transformers 4.39.3
- Pytorch 2.3.0+cu121
- Datasets 2.19.0
- Tokenizers 0.15.2