idefics2-8b-vqa_rad-finetuned

This model is a fine-tuned version of HuggingFaceM4/idefics2-8b on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 1.1974

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: 0.0003
• train_batch_size: 4
• eval_batch_size: 2
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.3
• num_epochs: 5
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
1.0095	1.1136	500	1.0882
2.1057	2.2272	1000	1.8082
1.416	3.3408	1500	1.4141
1.0619	4.4543	2000	1.1974

Framework versions

• Transformers 4.42.2
• Pytorch 2.3.1+cu118
• Datasets 2.20.0
• Tokenizers 0.19.1