medsiglip-448-ft-crc100k

This model is a fine-tuned version of google/medsiglip-448 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 2.5488

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: 0.0001
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 8
• total_train_batch_size: 64
• 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: cosine
• lr_scheduler_warmup_steps: 5
• num_epochs: 2

Training results

Training Loss	Epoch	Step	Validation Loss
3.5095	0.9756	50	2.8196
2.6344	1.9366	100	2.5488

Framework versions

• Transformers 4.54.0
• Pytorch 2.6.0+cu124
• Datasets 4.0.0
• Tokenizers 0.21.2