resnet-152_rice-leaf-disease-augmented-v4_fft

This model is a fine-tuned version of microsoft/resnet-152 on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.4358
• Accuracy: 0.8826

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_steps: 256
• num_epochs: 15
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
2.0697	0.5	64	2.0540	0.2383
2.0249	1.0	128	1.9791	0.4128
1.9118	1.5	192	1.8160	0.5503
1.6801	2.0	256	1.4791	0.6208
1.2937	2.5	320	1.0910	0.7013
0.9457	3.0	384	0.7744	0.7651
0.6634	3.5	448	0.6534	0.7852
0.5443	4.0	512	0.5658	0.8255
0.415	4.5	576	0.5184	0.8322
0.3648	5.0	640	0.4861	0.8456
0.3178	5.5	704	0.4788	0.8557
0.3126	6.0	768	0.4815	0.8423
0.3164	6.5	832	0.4723	0.8591
0.2484	7.0	896	0.4324	0.8523
0.1767	7.5	960	0.4159	0.8691
0.1414	8.0	1024	0.3875	0.8893
0.0888	8.5	1088	0.4114	0.8826
0.0807	9.0	1152	0.3925	0.8893
0.0513	9.5	1216	0.3893	0.8859
0.0537	10.0	1280	0.4182	0.8826
0.046	10.5	1344	0.4078	0.8893
0.0444	11.0	1408	0.4308	0.8792
0.0356	11.5	1472	0.4438	0.8826
0.0327	12.0	1536	0.4852	0.8725
0.0209	12.5	1600	0.4623	0.8859
0.0196	13.0	1664	0.4616	0.8859
0.0124	13.5	1728	0.4645	0.8792
0.0135	14.0	1792	0.4367	0.8926
0.0107	14.5	1856	0.4623	0.8859
0.0101	15.0	1920	0.4358	0.8826

Framework versions

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