cvmil/beit-base-patch16-224_augmented-v2_tl

beit-base-patch16-224_rice-leaf-disease-augmented-v2_tl

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

• Loss: 0.4947
• Accuracy: 0.8512

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: 128
• eval_batch_size: 128
• 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_ratio: 0.1
• num_epochs: 20
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
2.0747	1.0	63	1.7043	0.4435
1.3282	2.0	126	1.0444	0.6845
0.8626	3.0	189	0.7962	0.7470
0.6929	4.0	252	0.6883	0.8125
0.5935	5.0	315	0.6247	0.8214
0.5427	6.0	378	0.5926	0.8244
0.5002	7.0	441	0.5735	0.8452
0.4704	8.0	504	0.5520	0.8482
0.4521	9.0	567	0.5330	0.8363
0.4311	10.0	630	0.5249	0.8512
0.4096	11.0	693	0.5185	0.8512
0.3999	12.0	756	0.5112	0.8542
0.3918	13.0	819	0.5042	0.8512
0.3862	14.0	882	0.4984	0.8542
0.3784	15.0	945	0.4985	0.8512
0.3733	16.0	1008	0.4967	0.8512
0.3763	17.0	1071	0.4947	0.8512
0.3736	18.0	1134	0.4949	0.8512
0.3718	19.0	1197	0.4948	0.8512
0.3722	20.0	1260	0.4947	0.8512

Framework versions

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