metadata

library_name: transformers
license: apache-2.0
base_model: facebook/dinov2-base
tags:
  - generated_from_trainer
metrics:
  - accuracy
model-index:
  - name: dinov2-base_rice-leaf-disease-augmented-v4_fft
    results: []

dinov2-base_rice-leaf-disease-augmented-v4_fft

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: 0.3577
Accuracy: 0.9329

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
1.3845	0.5	64	0.4749	0.8389
0.2617	1.0	128	0.4180	0.8557
0.1422	1.5	192	0.3623	0.8893
0.1562	2.0	256	0.3631	0.8826
0.125	2.5	320	0.3037	0.9262
0.098	3.0	384	0.3326	0.9195
0.07	3.5	448	0.3849	0.9094
0.045	4.0	512	0.2490	0.9195
0.0136	4.5	576	0.3664	0.9228
0.0021	5.0	640	0.3443	0.9362
0.0002	5.5	704	0.3226	0.9362
0.0002	6.0	768	0.3354	0.9329
0.0	6.5	832	0.3349	0.9329
0.0	7.0	896	0.3515	0.9329
0.0	7.5	960	0.3634	0.9329
0.0	8.0	1024	0.3543	0.9329
0.0	8.5	1088	0.3555	0.9329
0.0	9.0	1152	0.3531	0.9329
0.0	9.5	1216	0.3532	0.9329
0.0	10.0	1280	0.3536	0.9329
0.0	10.5	1344	0.3538	0.9329
0.0	11.0	1408	0.3529	0.9329
0.0	11.5	1472	0.3559	0.9329
0.0	12.0	1536	0.3563	0.9329
0.0	12.5	1600	0.3553	0.9329
0.0	13.0	1664	0.3575	0.9329
0.0	13.5	1728	0.3570	0.9329
0.0	14.0	1792	0.3577	0.9329
0.0	14.5	1856	0.3577	0.9329
0.0	15.0	1920	0.3577	0.9329

Framework versions

Transformers 4.48.3
Pytorch 2.5.1+cu124
Datasets 3.3.2
Tokenizers 0.21.0