cvmil/resnet-50_augmented-v2_fft

resnet-50_rice-leaf-disease-augmented-v2_fft

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: 1.1313
• Accuracy: 0.6726

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
2.0639	1.0	125	2.0235	0.3393
1.9838	2.0	250	1.9041	0.4911
1.8621	3.0	375	1.7795	0.5238
1.7579	4.0	500	1.6965	0.5446
1.6945	5.0	625	1.6616	0.5625
1.6741	6.0	750	1.6497	0.5565
1.6042	7.0	875	1.5223	0.5685
1.4807	8.0	1000	1.4272	0.5893
1.3988	9.0	1125	1.3771	0.6101
1.3575	10.0	1250	1.3642	0.6071
1.3377	11.0	1375	1.3011	0.6220
1.2331	12.0	1500	1.2030	0.6548
1.1439	13.0	1625	1.1507	0.6577
1.0902	14.0	1750	1.1259	0.6548
1.0735	15.0	1875	1.1313	0.6726

Framework versions

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