vit-base-patch16-224_rice-leaf-disease-augmented-v4_tl

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

• Loss: 0.5193
• Accuracy: 0.8087

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
• 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	Accuracy	Validation Loss
2.1191	0.5	64	0.2047	2.0173
1.8193	1.0	128	0.4832	1.6229
1.44	1.5	192	0.6174	1.2769
1.1762	2.0	256	0.6980	1.0259
0.9676	2.5	320	0.6980	0.9041
0.8685	3.0	384	0.7383	0.7951
0.7844	3.5	448	0.7517	0.7532
0.733	4.0	512	0.7785	0.7018
0.7003	4.5	576	0.7651	0.6940
0.6781	5.0	640	0.7651	0.6819
0.6612	5.5	704	0.7550	0.6835
0.666	6.0	768	0.7718	0.6758
0.6791	6.5	832	0.7617	0.6722
0.6181	7.0	896	0.7752	0.6301
0.6064	7.5	960	0.7919	0.6013
0.5787	8.0	1024	0.7953	0.5856
0.5507	8.5	1088	0.7919	0.5859
0.5554	9.0	1152	0.7953	0.5857
0.536	9.5	1216	0.7987	0.5689
0.5298	10.0	1280	0.8020	0.5709
0.5244	10.5	1344	0.8054	0.5704
0.5301	11.0	1408	0.8054	0.5655
0.5172	11.5	1472	0.8020	0.5619
0.499	12.0	1536	0.8154	0.5307
0.4796	12.5	1600	0.8087	0.5256
0.477	13.0	1664	0.8087	0.5268
0.4648	13.5	1728	0.8054	0.5203
0.4564	14.0	1792	0.8087	0.5198
0.46	14.5	1856	0.5198	0.8121
0.4465	15.0	1920	0.5193	0.8087

Framework versions

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