Modelpublic

sanjeevani-04/indian-crop-disease-mobilenetv2

sourceHugging Faceotherupdated 7mo agoView on Hugging Face

0likes30downloads

Model Card

indian-crop-disease-mobilenetv2

This model is a fine-tuned version of google/mobilenet_v2_1.0_224 on the None dataset. It achieves the following results on the evaluation set:

—Loss: 0.5007
—Accuracy: 0.9732
—F1 Macro: 0.8895

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: 0.0003
—trainbatchsize: 32
—evalbatchsize: 64
—seed: 42
—optimizer: Use OptimizerNames.ADAMWTORCHFUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
—lrschedulertype: linear
—lrschedulerwarmup_steps: 0.05
—num_epochs: 14
—mixedprecisiontraining: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1 Macro
1.0766	1.0	390	0.9140	0.8451	0.6712
0.6926	2.0	780	0.7118	0.8692	0.6990
0.5250	3.0	1170	0.6181	0.9164	0.7680
0.3568	4.0	1560	0.7161	0.9183	0.7873
0.3801	5.0	1950	0.6101	0.9246	0.8000
0.2705	6.0	2340	0.6013	0.9396	0.8163
0.2626	7.0	2730	0.4861	0.9523	0.8340
0.1720	8.0	3120	0.5602	0.9391	0.8102
0.1387	9.0	3510	0.5884	0.9550	0.8541
0.0810	10.0	3900	0.5129	0.9628	0.8619
0.0565	11.0	4290	0.4028	0.9678	0.8836
0.0515	12.0	4680	0.4511	0.9741	0.8725
0.0640	13.0	5070	0.4910	0.9709	0.8737
0.0616	14.0	5460	0.5007	0.9732	0.8895

Framework versions

—Transformers 5.0.0
—Pytorch 2.10.0+cu128
—Datasets 4.0.0
—Tokenizers 0.22.2