Modelpublic

vishnun0027/Crop_Disease_model_1

sourceHugging Faceapache-2.0updated 2y agoView on Hugging Face

2likes97downloads

Model Card

CropDiseasemodel_1

This model is a fine-tuned version of google/vit-base-patch16-224-in21k on an unknown dataset. It achieves the following results on the evaluation set:

—Loss: 1.2482
—Accuracy: 0.7

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: 32
—evalbatchsize: 32
—seed: 42
—gradientaccumulationsteps: 4
—totaltrainbatch_size: 128
—optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
—lrschedulertype: linear
—lrschedulerwarmup_ratio: 0.1
—num_epochs: 18

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
2.974	0.9787	23	2.9288	0.1573
2.8301	2.0	47	2.6713	0.5173
2.3995	2.9787	70	2.3223	0.5707
2.112	4.0	94	2.0321	0.604
1.8965	4.9787	117	1.8377	0.6133
1.6807	6.0	141	1.6895	0.6307
1.4942	6.9787	164	1.5807	0.6693
1.3849	8.0	188	1.5080	0.664
1.2975	8.9787	211	1.4605	0.6613
1.1747	10.0	235	1.3888	0.692
1.1457	10.9787	258	1.3622	0.692
1.0602	12.0	282	1.3318	0.6893
1.0296	12.9787	305	1.2968	0.7133
0.9556	14.0	329	1.2999	0.676
0.9317	14.9787	352	1.2625	0.7053
0.9134	16.0	376	1.2656	0.696
0.914	16.9787	399	1.2593	0.7013
0.9013	17.6170	414	1.2482	0.7

Framework versions

—Transformers 4.41.2
—Pytorch 2.1.2
—Datasets 2.19.2
—Tokenizers 0.19.1