siglip-finetuned-fashion

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

• Loss: 0.0374

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-06
• train_batch_size: 64
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.01
• num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss
0.5064	0.3514	500	0.0788
0.3764	0.7027	1000	0.0544
0.2874	1.0541	1500	0.0469
0.2472	1.4055	2000	0.0429
0.2589	1.7569	2500	0.0407
0.2105	2.1082	3000	0.0396
0.1906	2.4596	3500	0.0381
0.1814	2.8110	4000	0.0374

Framework versions

• Transformers 4.44.2
• Pytorch 2.5.1+cu124
• Datasets 2.20.0
• Tokenizers 0.19.1