msi
This model is a fine-tuned version of shi-labs/nat-mini-in1k-224 on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 1.4627
- Accuracy: 0.6215
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: 16
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.2672 | 1.0 | 2015 | 1.0553 | 0.6028 |
| 0.1972 | 2.0 | 4031 | 1.1869 | 0.6437 |
| 0.1732 | 3.0 | 6045 | 1.4627 | 0.6215 |
Framework versions
- Transformers 4.36.0
- Pytorch 2.0.1
- Datasets 2.15.0
- Tokenizers 0.15.0