cvmil/beit-base-patch16-224_augmented-v2_fft

beit-base-patch16-224_rice-leaf-disease-augmented-v2_fft

This model is a fine-tuned version of microsoft/beit-base-patch16-224 on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.5324
• Accuracy: 0.9137

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: 64
• eval_batch_size: 64
• seed: 42
• optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: cosine_with_restarts
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 15
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
1.6553	1.0	125	0.7916	0.7530
0.481	2.0	250	0.3628	0.8810
0.1631	3.0	375	0.2895	0.8988
0.0609	4.0	500	0.3242	0.9167
0.0293	5.0	625	0.3503	0.9196
0.0223	6.0	750	0.3411	0.9226
0.0302	7.0	875	0.3786	0.9226
0.014	8.0	1000	0.4169	0.9256
0.0069	9.0	1125	0.4648	0.9137
0.006	10.0	1250	0.4697	0.9137
0.0053	11.0	1375	0.5192	0.8958
0.0093	12.0	1500	0.5058	0.9048
0.0069	13.0	1625	0.5486	0.9077
0.005	14.0	1750	0.5252	0.9167
0.004	15.0	1875	0.5324	0.9137

Framework versions

• Transformers 4.48.3
• Pytorch 2.5.1+cu124
• Datasets 3.3.2
• Tokenizers 0.21.0