idefics2-8b-vqa_path-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: 0.9422

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: 3
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
0.874	0.4070	2000	0.9289
1.4829	0.8140	4000	1.3919
1.5202	1.2210	6000	1.3825
1.2891	1.6280	8000	1.2521
1.0616	2.0350	10000	1.1445
0.9254	2.4420	12000	1.0195
0.8157	2.8490	14000	0.9422

Framework versions

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