fabric-classifier
This model is a fine-tuned version of google/vit-base-patch16-224-in21k on the 0x-Jayveersinh-Raj/fabric_classification_dataset dataset. It achieves the following results on the evaluation set:
- Loss: 1.7256
- Accuracy: 0.5042
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
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 109
- num_epochs: 3.0
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 2.0179 | 1.0 | 366 | 1.9668 | 0.4365 |
| 1.6601 | 2.0 | 732 | 1.7640 | 0.4850 |
| 1.6036 | 3.0 | 1098 | 1.7256 | 0.5042 |
Framework versions
- Transformers 5.18.0
- Pytorch 2.14.1+cu130
- Datasets 2.19.1
- Tokenizers 0.23.2
- Downloads last month
- -
Model tree for yuplpp/fabric-classifier
Base model
google/vit-base-patch16-224-in21kSpace using yuplpp/fabric-classifier 1
Evaluation results
- Accuracy on 0x-Jayveersinh-Raj/fabric_classification_datasetself-reported0.504