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

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

• Loss: 0.6434
• Accuracy: 0.7953

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	Validation Loss	Accuracy
2.1222	0.5	64	2.0509	0.1510
1.9017	1.0	128	1.7781	0.4497
1.5825	1.5	192	1.4769	0.5839
1.3241	2.0	256	1.2365	0.6477
1.1218	2.5	320	1.0798	0.7081
1.0	3.0	384	0.9780	0.7148
0.9197	3.5	448	0.9174	0.7181
0.8642	4.0	512	0.8803	0.7450
0.8318	4.5	576	0.8597	0.7617
0.8052	5.0	640	0.8468	0.7584
0.8015	5.5	704	0.8442	0.7584
0.7837	6.0	768	0.8387	0.7617
0.8052	6.5	832	0.8286	0.7584
0.7411	7.0	896	0.7934	0.7685
0.7309	7.5	960	0.7547	0.7785
0.6879	8.0	1024	0.7408	0.7819
0.6677	8.5	1088	0.7244	0.7987
0.6653	9.0	1152	0.7210	0.7886
0.6526	9.5	1216	0.7123	0.7919
0.6396	10.0	1280	0.7103	0.7919
0.6415	10.5	1344	0.7097	0.7919
0.638	11.0	1408	0.6948	0.7953
0.629	11.5	1472	0.6902	0.7953
0.5986	12.0	1536	0.6603	0.7953
0.5859	12.5	1600	0.6631	0.7987
0.5776	13.0	1664	0.6511	0.7953
0.5639	13.5	1728	0.6433	0.7953
0.5643	14.0	1792	0.6448	0.8020
0.5626	14.5	1856	0.6434	0.7953
0.5522	15.0	1920	0.6434	0.7953

Framework versions

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