|
--- |
|
license: apache-2.0 |
|
base_model: dandelin/vilt-b32-finetuned-vqa |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: ViLT_Binary_Classifier_Abstract_Scenes |
|
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. --> |
|
|
|
# ViLT_Binary_Classifier_Abstract_Scenes |
|
|
|
This model is a fine-tuned version of [dandelin/vilt-b32-finetuned-vqa](https://huggingface.co/dandelin/vilt-b32-finetuned-vqa) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 1.3099 |
|
|
|
## 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: 0.0005 |
|
- train_batch_size: 8 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 1 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| 1.4285 | 0.08 | 100 | 1.4508 | |
|
| 1.4158 | 0.17 | 200 | 1.6115 | |
|
| 1.4004 | 0.25 | 300 | 1.3504 | |
|
| 1.3907 | 0.34 | 400 | 1.3577 | |
|
| 1.3568 | 0.42 | 500 | 1.3397 | |
|
| 1.3562 | 0.5 | 600 | 1.3216 | |
|
| 1.3566 | 0.59 | 700 | 1.3190 | |
|
| 1.3255 | 0.67 | 800 | 1.3227 | |
|
| 1.341 | 0.76 | 900 | 1.3411 | |
|
| 1.3654 | 0.84 | 1000 | 1.3144 | |
|
| 1.3343 | 0.92 | 1100 | 1.3099 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.37.2 |
|
- Pytorch 2.1.0+cu121 |
|
- Datasets 2.17.0 |
|
- Tokenizers 0.15.2 |
|
|