vit-msn-small-wbc-blur-detector
This model is a fine-tuned version of facebook/vit-msn-small on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 0.2045
- Accuracy: 0.9251
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: 64
- eval_batch_size: 64
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 256
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.3471 | 1.0 | 208 | 0.2960 | 0.8940 |
| 0.3113 | 2.0 | 416 | 0.2551 | 0.9088 |
| 0.3104 | 3.0 | 624 | 0.2106 | 0.9212 |
| 0.2855 | 4.0 | 832 | 0.2101 | 0.9221 |
| 0.2497 | 5.0 | 1040 | 0.2045 | 0.9251 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.1+cu121
- Datasets 3.2.0
- Tokenizers 0.19.1
- Downloads last month
- 56
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.