|
|
--- |
|
|
library_name: transformers |
|
|
license: apache-2.0 |
|
|
base_model: dandelin/vilt-b32-finetuned-nlvr2 |
|
|
tags: |
|
|
- image-text-classification |
|
|
- generated_from_trainer |
|
|
metrics: |
|
|
- accuracy |
|
|
model-index: |
|
|
- name: '42' |
|
|
results: [] |
|
|
--- |
|
|
|
|
|
<!-- 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. --> |
|
|
|
|
|
# 42 |
|
|
|
|
|
This model is a fine-tuned version of [dandelin/vilt-b32-finetuned-nlvr2](https://huggingface.co/dandelin/vilt-b32-finetuned-nlvr2) on the nlvr2 dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: -9.3285 |
|
|
- Accuracy: 0.5103 |
|
|
- Dt Accuracy: 0.5103 |
|
|
- Df Accuracy: 0.5251 |
|
|
- Unlearn Overall Accuracy: 0.7754 |
|
|
- Unlearn Time: None |
|
|
|
|
|
## 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: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments |
|
|
- 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 | 162 | -6.0727 | 0.6168 | 0.7600 | 0.7600 | None | |
|
|
| No log | 2.0 | 324 | -9.3285 | 0.5251 | 0.7754 | 0.7754 | None | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.48.0 |
|
|
- Pytorch 2.3.0+cu121 |
|
|
- Datasets 2.18.0 |
|
|
- Tokenizers 0.21.0 |
|
|
|
