siglip-flickr30k-ptbr-5ep

This model is a fine-tuned version of google/siglip-base-patch16-256-multilingual on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.0170

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: 32
• eval_batch_size: 32
• 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: linear
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss
0.0113	0.6803	500	0.0112
0.0059	1.3605	1000	0.0107
0.006	2.0408	1500	0.0127
0.0036	2.7211	2000	0.0132
0.0022	3.4014	2500	0.0149
0.0024	4.0816	3000	0.0175
0.0019	4.7619	3500	0.0170

Framework versions

• Transformers 4.57.1
• Pytorch 2.6.0+cu124
• Datasets 4.4.1
• Tokenizers 0.22.1