metadata
license: apache-2.0
base_model: google/vit-base-patch16-224
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: vit-base-patch16-224-finetuned-masked-hateful-meme-restructured
results:
- task:
name: Image Classification
type: image-classification
dataset:
name: imagefolder
type: imagefolder
config: default
split: validation
args: default
metrics:
- name: Accuracy
type: accuracy
value: 0.54
vit-base-patch16-224-finetuned-masked-hateful-meme-restructured
This model is a fine-tuned version of google/vit-base-patch16-224 on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 0.7518
- Accuracy: 0.54
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: 32
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.6625 | 0.99 | 66 | 0.7385 | 0.518 |
| 0.6413 | 2.0 | 133 | 0.6980 | 0.538 |
| 0.6063 | 2.99 | 199 | 0.7422 | 0.53 |
| 0.5813 | 4.0 | 266 | 0.7794 | 0.52 |
| 0.5551 | 4.99 | 332 | 0.7975 | 0.52 |
| 0.5249 | 6.0 | 399 | 0.7518 | 0.54 |
| 0.5254 | 6.99 | 465 | 0.8074 | 0.53 |
| 0.5335 | 8.0 | 532 | 0.7907 | 0.52 |
| 0.4867 | 8.99 | 598 | 0.8286 | 0.524 |
| 0.4746 | 9.92 | 660 | 0.8262 | 0.522 |
Framework versions
- Transformers 4.31.0
- Pytorch 2.0.1+cu117
- Datasets 2.13.1
- Tokenizers 0.13.3