SmolVLM-500M-Instruct-med-vqav1

This model is a fine-tuned version of HuggingFaceTB/SmolVLM-500M-Instruct on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.3924

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: 4
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 8
• optimizer: Use OptimizerNames.ADAMW_HF with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 50
• num_epochs: 2

Training results

Training Loss	Epoch	Step	Validation Loss
1.0375	0.4454	100	0.4305
0.4064	0.8909	200	0.4024
0.3378	1.3341	300	0.3941
0.3348	1.7795	400	0.3924

Framework versions

• Transformers 4.48.2
• Pytorch 2.5.1+cu124
• Datasets 3.3.0
• Tokenizers 0.21.0