Modelpublic

cvmil/dinov2-base_rice-leaf-disease-augmented_fft

sourceHugging Faceapache-2.0updated 2y agoView on Hugging Face

0likes3.9kdownloads

Model Card

dinov2-baserice-leaf-disease-augmentedfft_012825

This model is a fine-tuned version of facebook/dinov2-base on an unknown dataset. It achieves the following results on the evaluation set:

—Loss: 0.0125
—Accuracy: 0.9965

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
—trainbatchsize: 64
—evalbatchsize: 64
—seed: 42
—optimizer: Use OptimizerNames.ADAMWTORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizerargs=No additional optimizer arguments
—lrschedulertype: linear
—lrschedulerwarmup_ratio: 0.1
—num_epochs: 15

Training results

Training Loss	Epoch	Step	Accuracy	Validation Loss
0.8384	1.0	250	0.931	0.2042
0.1037	2.0	500	0.96	0.1290
0.0574	3.0	750	0.977	0.0657
0.0255	4.0	1000	0.985	0.0527
0.0096	5.0	1250	0.988	0.0374
0.0052	6.0	1500	0.997	0.0128
0.0018	7.0	1750	0.9945	0.0131
0.0027	8.0	2000	0.997	0.0122
0.0004	9.0	2250	0.997	0.0153
0.0013	10.0	2500	0.997	0.0128
0.0004	11.0	2750	0.9965	0.0147
0.0004	12.0	3000	0.997	0.0155
0.0003	13.0	3250	0.9955	0.0118
0.0004	14.0	3500	0.9955	0.0123
0.0003	15.0	3750	0.9965	0.0125

Framework versions

—Transformers 4.47.1
—Pytorch 2.5.1+cu124
—Datasets 3.2.0
—Tokenizers 0.21.0