gm-lora-bfloat16-idefics2-8b-xrayvqa-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: 0.7025

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-05
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 10
• total_train_batch_size: 80
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 50
• num_epochs: 2

Training results

Training Loss	Epoch	Step	Validation Loss
1.1149	0.2632	100	0.7762
0.7216	0.5263	200	0.7406
0.7044	0.7895	300	0.7175
0.6617	1.0526	400	0.7204
0.5562	1.3158	500	0.7129
0.5614	1.5789	600	0.7067
0.5483	1.8421	700	0.7025

Framework versions

• Transformers 4.41.0.dev0
• Pytorch 1.13.1+cu117
• Datasets 2.19.0
• Tokenizers 0.19.1