siglip2-base-patch16-512

This model was trained from scratch on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.5239
• Roc Auc: 0.9741

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: 1e-05
• train_batch_size: 4
• eval_batch_size: 4
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 16
• optimizer: Use 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_steps: 5
• num_epochs: 7

Training results

Training Loss	Epoch	Step	Validation Loss	Roc Auc
1.9038	1.9268	40	0.5393	0.9497
0.5604	3.8293	80	0.3889	0.9759
0.1351	5.7317	120	0.5239	0.9741

Framework versions

• Transformers 4.57.3
• Pytorch 2.9.0+cu128
• Datasets 4.4.1
• Tokenizers 0.22.1