gm-lora-bfloat16-idefics2-8b-xrayvqa-finetuned-4

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: 0.7114

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: 20
• total_train_batch_size: 160
• 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
1.2963	0.2632	50	0.7880
0.7353	0.5263	100	0.7475
0.716	0.7895	150	0.7302
0.6689	1.0526	200	0.7295
0.5496	1.3158	250	0.7256
0.5534	1.5789	300	0.7177
0.5419	1.8421	350	0.7114

Framework versions

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