DeiT

This model is a fine-tuned version of facebook/deit-base-distilled-patch16-224 on the imagefolder dataset. It achieves the following results on the evaluation set:

• Loss: 0.0278

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
• 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: linear
• num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss
0.2356	1.0	77	0.0631
0.1409	2.0	154	0.0930
0.0694	3.0	231	0.0223
0.0719	4.0	308	0.0346
0.0651	5.0	385	0.0374
0.0454	6.0	462	0.0241
0.0179	7.0	539	0.0436
0.0252	8.0	616	0.0318
0.0182	9.0	693	0.0346
0.0114	10.0	770	0.0278

Framework versions

• Transformers 5.22.1
• Pytorch 2.14.1+cu130
• Datasets 4.8.5
• Tokenizers 0.23.3