siglip-finetuned-artdatasets

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: 0.1192

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
1.458	0.3139	500	0.3211
1.1107	0.6277	1000	0.2249
0.928	0.9416	1500	0.1843
0.6952	1.2555	2000	0.1574
0.6393	1.5694	2500	0.1432
0.5702	1.8832	3000	0.1336
0.4676	2.1971	3500	0.1277
0.4588	2.5110	4000	0.1220
0.4416	2.8249	4500	0.1192

Framework versions

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