vit-large-patch32-384
This model is a fine-tuned version of google/vit-large-patch32-384 on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 0.0127
- F1: 0.9763
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 | F1 |
|---|---|---|---|---|
| 0.1312 | 0.99 | 53 | 0.1215 | 0.7860 |
| 0.0831 | 1.99 | 107 | 0.0570 | 0.9350 |
| 0.0441 | 3.0 | 161 | 0.0348 | 0.9475 |
| 0.0423 | 4.0 | 215 | 0.0342 | 0.9186 |
| 0.0249 | 4.99 | 268 | 0.0232 | 0.9594 |
| 0.0168 | 5.99 | 322 | 0.0279 | 0.9414 |
| 0.0098 | 7.0 | 376 | 0.0242 | 0.9460 |
| 0.0133 | 8.0 | 430 | 0.0181 | 0.9637 |
| 0.0156 | 8.99 | 483 | 0.0101 | 0.9804 |
| 0.0114 | 9.86 | 530 | 0.0127 | 0.9763 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.1
- Downloads last month
- 0
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.