---
base_model: NousResearch/Meta-Llama-3.1-8B-Instruct
datasets:
- generator
library_name: peft
license: llama3.1
tags:
- trl
- sft
- generated_from_trainer
model-index:
- name: llama381binstruct_summarize_short
  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. -->

# llama381binstruct_summarize_short

This model is a fine-tuned version of [NousResearch/Meta-Llama-3.1-8B-Instruct](https://huggingface.co/NousResearch/Meta-Llama-3.1-8B-Instruct) on the generator dataset.
It achieves the following results on the evaluation set:
- Loss: 1.4181

## 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: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 6
- training_steps: 100

### Training results

| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 1.5775        | 0.25  | 5    | 1.5695          |
| 1.7351        | 0.5   | 10   | 1.3455          |
| 2.0074        | 0.75  | 15   | 1.2429          |
| 1.6972        | 1.0   | 20   | 1.1852          |
| 1.2054        | 1.25  | 25   | 1.1672          |
| 1.4255        | 1.5   | 30   | 1.1778          |
| 0.9758        | 1.75  | 35   | 1.1446          |
| 1.3851        | 2.0   | 40   | 1.1498          |
| 0.8252        | 2.25  | 45   | 1.1879          |
| 1.0266        | 2.5   | 50   | 1.2851          |
| 0.6106        | 2.75  | 55   | 1.2537          |
| 0.9328        | 3.0   | 60   | 1.2100          |
| 0.5083        | 3.25  | 65   | 1.2748          |
| 0.4762        | 3.5   | 70   | 1.4306          |
| 0.7648        | 3.75  | 75   | 1.4550          |
| 0.2807        | 4.0   | 80   | 1.3928          |
| 0.3343        | 4.25  | 85   | 1.3819          |
| 0.4685        | 4.5   | 90   | 1.3942          |
| 0.1421        | 4.75  | 95   | 1.4113          |
| 0.2701        | 5.0   | 100  | 1.4181          |


### Framework versions

- PEFT 0.13.2
- Transformers 4.46.1
- Pytorch 2.5.0+cu121
- Datasets 3.1.0
- Tokenizers 0.20.1