fine-tuned-visionllama_5

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:

• eval_loss: 2.0710
• eval_runtime: 8.0583
• eval_samples_per_second: 0.62
• eval_steps_per_second: 0.124
• epoch: 0.0489
• step: 425

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: 1
• eval_batch_size: 8
• seed: 42
• 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

Framework versions

• PEFT 0.13.0
• Transformers 4.45.1
• Pytorch 2.2.2+cu121
• Datasets 3.0.1
• Tokenizers 0.20.3