fine-tuned-visionllama

This model is a fine-tuned version of meta-llama/Llama-3.2-11B-Vision-Instruct on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.2764
• Accuracy: 0.0262
• F1: 0.0263

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: 0.0002
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 8
• total_train_batch_size: 64
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: constant
• lr_scheduler_warmup_ratio: 0.03
• num_epochs: 2

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1
0.6989	0.9778	22	0.6079	0.0001	0.0001
0.3177	1.9556	44	0.2764	0.0262	0.0263

Framework versions

• PEFT 0.13.0
• Transformers 4.45.1
• Pytorch 2.4.0+cu121
• Datasets 3.0.1
• Tokenizers 0.20.3