<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
SwinT
This model is a fine-tuned version of bucuralexandra/SwinT on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 0.2254
- Accuracy: 0.9156
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: 6
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
0.3285 | 1.0 | 118 | 0.2617 | 0.9026 |
0.2934 | 2.0 | 237 | 0.2401 | 0.9061 |
0.2963 | 3.0 | 355 | 0.2417 | 0.9079 |
0.305 | 4.0 | 474 | 0.2318 | 0.9127 |
0.2607 | 5.0 | 592 | 0.2703 | 0.9085 |
0.268 | 5.97 | 708 | 0.2254 | 0.9156 |
Framework versions
- Transformers 4.28.0
- Pytorch 2.0.1+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3