resnet-50_rice-leaf-disease-augmented_fft_020125

This model is a fine-tuned version of microsoft/resnet-50 on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.6406
• Accuracy: 0.779

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: linear
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 15

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
2.0532	1.0	250	1.9924	0.3795
1.8952	2.0	500	1.7562	0.5
1.6491	3.0	750	1.5051	0.5685
1.4229	4.0	1000	1.2998	0.6105
1.2276	5.0	1250	1.1287	0.661
1.0723	6.0	1500	0.9887	0.6965
0.9462	7.0	1750	0.8832	0.7235
0.8542	8.0	2000	0.8107	0.7375
0.7818	9.0	2250	0.7554	0.754
0.7259	10.0	2500	0.7115	0.7585
0.6918	11.0	2750	0.6865	0.7685
0.6616	12.0	3000	0.6611	0.77
0.6407	13.0	3250	0.6528	0.774
0.6286	14.0	3500	0.6438	0.7795
0.6218	15.0	3750	0.6406	0.779

Framework versions

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