---
base_model: meta-llama/Llama-3.2-11B-Vision
library_name: peft
license: llama3.2
metrics:
- bleu
- rouge
tags:
- trl
- sft
- generated_from_trainer
model-index:
- name: Llama-3.2_sft
  results: []
---

<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->

# Llama-3.2_sft

This model is a fine-tuned version of [meta-llama/Llama-3.2-11B-Vision](https://huggingface.co/meta-llama/Llama-3.2-11B-Vision) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 1.7029
- Bleu: 0.3190
- Rouge1: 0.6446
- Rouge2: 0.3444
- Rougel: 0.5512
- Bertscore Precision: 0.8782
- Bertscore Recall: 0.8935
- Bertscore F1: 0.8858

## 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: 5e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 50
- num_epochs: 5.0

### Training results

| Training Loss | Epoch  | Step | Validation Loss | Bleu   | Rouge1 | Rouge2 | Rougel | Bertscore Precision | Bertscore Recall | Bertscore F1 |
|:-------------:|:------:|:----:|:---------------:|:------:|:------:|:------:|:------:|:-------------------:|:----------------:|:------------:|
| 1.7104        | 1.2403 | 100  | 1.7210          | 0.3168 | 0.6444 | 0.3460 | 0.5505 | 0.8774              | 0.8931           | 0.8852       |
| 1.677         | 2.4806 | 200  | 1.7063          | 0.3191 | 0.6462 | 0.3472 | 0.5524 | 0.8781              | 0.8935           | 0.8857       |
| 1.6343        | 3.7209 | 300  | 1.7020          | 0.3188 | 0.6448 | 0.3445 | 0.5513 | 0.8782              | 0.8934           | 0.8857       |
| 1.6163        | 4.9612 | 400  | 1.7029          | 0.3190 | 0.6446 | 0.3444 | 0.5512 | 0.8782              | 0.8935           | 0.8858       |


### Framework versions

- PEFT 0.13.2
- Transformers 4.45.2
- Pytorch 2.2.0a0+81ea7a4
- Datasets 3.0.1
- Tokenizers 0.20.1