dinov2-base_rice-leaf-disease-augmented-v4_tl

This model is a fine-tuned version of facebook/dinov2-base on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.2961
• Accuracy: 0.9060

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
2.1181	0.5	64	0.3658	1.7085
1.3815	1.0	128	0.7047	1.0554
0.8981	1.5	192	0.7785	0.7380
0.6515	2.0	256	0.7987	0.5983
0.5233	2.5	320	0.8255	0.5212
0.4535	3.0	384	0.8356	0.4803
0.3959	3.5	448	0.8557	0.4428
0.3614	4.0	512	0.8725	0.4040
0.3391	4.5	576	0.8691	0.4082
0.318	5.0	640	0.3749	0.8859
0.3134	5.5	704	0.3922	0.8758
0.3025	6.0	768	0.3802	0.8826
0.3098	6.5	832	0.3856	0.8725
0.2986	7.0	896	0.3666	0.8859
0.2856	7.5	960	0.3525	0.8826
0.2549	8.0	1024	0.3327	0.8725
0.24	8.5	1088	0.3428	0.9027
0.2422	9.0	1152	0.3304	0.8993
0.2178	9.5	1216	0.3238	0.9027
0.2297	10.0	1280	0.3273	0.9027
0.2176	10.5	1344	0.3285	0.9027
0.2236	11.0	1408	0.3411	0.8792
0.2198	11.5	1472	0.3342	0.8893
0.2056	12.0	1536	0.3108	0.9060
0.1915	12.5	1600	0.2995	0.8993
0.1911	13.0	1664	0.3058	0.9027
0.1787	13.5	1728	0.2928	0.9128
0.1776	14.0	1792	0.2979	0.9060
0.1724	14.5	1856	0.2966	0.9060
0.168	15.0	1920	0.2961	0.9060

Framework versions

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