kevin2909/img_app_source_v2

20260126163812

This model is a fine-tuned version of google/siglip2-base-patch16-224 on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.2250
• F1: 0.9205
• Accuracy: 0.9205

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: 0.0002
• train_batch_size: 64
• eval_batch_size: 64
• seed: 42
• optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: cosine
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss	F1	Accuracy
0.5197	1.1710	500	0.3835	0.8664	0.8664
0.3574	2.3419	1000	0.3039	0.8959	0.8959
0.2635	3.5129	1500	0.2393	0.9162	0.9162
0.2119	4.6838	2000	0.2250	0.9205	0.9205

Framework versions

• Transformers 4.57.6
• Pytorch 2.7.1+cu126
• Datasets 3.6.0
• Tokenizers 0.22.0