---
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: 2.6176

## 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: linear
- lr_scheduler_warmup_steps: 30
- training_steps: 500

### Training results

| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 1.6519        | 1.25  | 25   | 1.8402          |
| 0.7039        | 2.5   | 50   | 1.7272          |
| 0.3793        | 3.75  | 75   | 1.7206          |
| 0.1875        | 5.0   | 100  | 1.7496          |
| 0.115         | 6.25  | 125  | 1.9070          |
| 0.027         | 7.5   | 150  | 2.2242          |
| 0.0211        | 8.75  | 175  | 2.2373          |
| 0.0227        | 10.0  | 200  | 2.3110          |
| 0.0138        | 11.25 | 225  | 2.3410          |
| 0.0053        | 12.5  | 250  | 2.4058          |
| 0.0037        | 13.75 | 275  | 2.4090          |
| 0.0036        | 15.0  | 300  | 2.4907          |
| 0.0024        | 16.25 | 325  | 2.5411          |
| 0.0024        | 17.5  | 350  | 2.5661          |
| 0.0021        | 18.75 | 375  | 2.5838          |
| 0.0021        | 20.0  | 400  | 2.5969          |
| 0.0018        | 21.25 | 425  | 2.6064          |
| 0.0017        | 22.5  | 450  | 2.6128          |
| 0.0015        | 23.75 | 475  | 2.6165          |
| 0.0019        | 25.0  | 500  | 2.6176          |


### Framework versions

- PEFT 0.12.0
- Transformers 4.44.2
- Pytorch 2.4.1+cu121
- Datasets 3.0.0
- Tokenizers 0.19.1