---
library_name: peft
license: llama3.2
base_model: meta-llama/Llama-3.2-3B-Instruct
tags:
- trl
- sft
- generated_from_trainer
datasets:
- generator
model-index:
- name: TWON-Agent-OSN-Post-de
  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. -->

# TWON-Agent-OSN-Post-de

This model is a fine-tuned version of [meta-llama/Llama-3.2-3B-Instruct](https://huggingface.co/meta-llama/Llama-3.2-3B-Instruct) on the generator dataset.
It achieves the following results on the evaluation set:
- Loss: 0.7415

## 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: 4
- eval_batch_size: 8
- seed: 42
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 8

### Training results

| Training Loss | Epoch  | Step | Validation Loss |
|:-------------:|:------:|:----:|:---------------:|
| 1.8045        | 1.1173 | 200  | 1.4317          |
| 1.2908        | 2.2346 | 400  | 1.1496          |
| 1.0523        | 3.3520 | 600  | 0.9740          |
| 0.8996        | 4.4693 | 800  | 0.8645          |
| 0.7967        | 5.5866 | 1000 | 0.7943          |
| 0.7339        | 6.7039 | 1200 | 0.7595          |
| 0.6986        | 7.8212 | 1400 | 0.7417          |


### Framework versions

- PEFT 0.12.0
- Transformers 4.47.1
- Pytorch 2.5.1+cu124
- Datasets 3.2.0
- Tokenizers 0.21.0