llama32-rocov2-4bit

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: 1.1132

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: 3

Training results

Training Loss	Epoch	Step	Validation Loss
1.1566	0.9991	817	1.1272
1.1108	1.9994	1635	1.1157
1.062	2.9972	2451	1.1132

Framework versions

• PEFT 0.13.2
• Transformers 4.45.2
• Pytorch 2.4.1+cu121
• Datasets 3.0.1
• Tokenizers 0.20.1