metadata
license: apache-2.0
base_model: microsoft/swin-tiny-patch4-window7-224
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: swin-tiny-patch4-window7-224-finetuned-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: 0.52
swin-tiny-patch4-window7-224-finetuned-hateful-meme-restructured
This model is a fine-tuned version of microsoft/swin-tiny-patch4-window7-224 on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 0.8519
- Accuracy: 0.52
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 |
|---|---|---|---|---|
| 0.6441 | 0.99 | 66 | 0.7419 | 0.492 |
| 0.6368 | 2.0 | 133 | 0.7235 | 0.51 |
| 0.6157 | 2.99 | 199 | 0.7516 | 0.504 |
| 0.5928 | 4.0 | 266 | 0.8009 | 0.502 |
| 0.5735 | 4.99 | 332 | 0.8270 | 0.508 |
| 0.5559 | 6.0 | 399 | 0.7804 | 0.502 |
| 0.5533 | 6.99 | 465 | 0.8053 | 0.486 |
| 0.5541 | 8.0 | 532 | 0.8078 | 0.504 |
| 0.5218 | 8.99 | 598 | 0.8519 | 0.52 |
| 0.5226 | 9.92 | 660 | 0.8522 | 0.508 |
Framework versions
- Transformers 4.31.0
- Pytorch 2.0.1+cu117
- Datasets 2.13.1
- Tokenizers 0.13.3