Downloads · 30 days
13
17% of all-time downloads
ViLT_FT_Balanced_Binary_Abstract_Scenes
VladGK/ViLT_FT_Balanced_Binary_Abstract_Scenes
ViLT_FT_Balanced_Binary_Abstract_Scenes is a visual question answering model from VladGK. Use it for the visual question answering task on the model card, and read the license before you ship it in a product. It is set up for transformers. The card lists the license as apache-2.0.
should probably proofread and complete it, then remove this comment. --
All-time downloads
76
Public
Parameters
118M
1.4 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors470 MB · 100%
At a glance
- Task
- Visual Question Answering
- Library
- transformers
- License
- apache-2.0
- Model type
- vilt
- Access
- Public
- Created
- Feb 16, 2024
- Updated
- Feb 17, 2024
- SHA
- c8ccb47c
Base models
Model card
From the Hugging Face model README
<!-- 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_FT_Balanced_Binary_Abstract_Scenes
This model is a fine-tuned version of dandelin/vilt-b32-finetuned-vqa on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.3521
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: 3
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.6688 | 0.17 | 200 | 1.6769 |
| 1.3841 | 0.34 | 400 | 1.6145 |
| 1.3773 | 0.5 | 600 | 1.5574 |
| 1.3539 | 0.67 | 800 | 1.5374 |
| 1.3458 | 0.84 | 1000 | 1.5044 |
| 1.3653 | 1.01 | 1200 | 1.4956 |
| 1.3222 | 1.18 | 1400 | 1.4968 |
| 1.3362 | 1.34 | 1600 | 1.4855 |
| 1.3557 | 1.51 | 1800 | 1.3809 |
| 1.3207 | 1.68 | 2000 | 1.3806 |
| 1.348 | 1.85 | 2200 | 1.3718 |
| 1.3215 | 2.02 | 2400 | 1.3677 |
| 1.3299 | 2.18 | 2600 | 1.3793 |
| 1.335 | 2.35 | 2800 | 1.3662 |
| 1.3033 | 2.52 | 3000 | 1.3628 |
| 1.3377 | 2.69 | 3200 | 1.3525 |
| 1.3001 | 2.85 | 3400 | 1.3521 |
Framework versions
- Transformers 4.37.2
- Pytorch 2.1.0+cu121
- Datasets 2.17.0
- Tokenizers 0.15.2
- Task
- Visual Question Answering
- Library
- transformers
- Type
- vilt
- License
- apache-2.0
- Created
- Feb 16, 2024
- Updated
- Feb 17, 2024