---
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: 1.9773

## 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 |
|:-------------:|:-------:|:----:|:---------------:|
| 1.7658        | 1.3158  | 25   | 1.2514          |
| 0.798         | 2.6316  | 50   | 1.2960          |
| 0.4432        | 3.9474  | 75   | 1.3901          |
| 0.1598        | 5.2632  | 100  | 1.6723          |
| 0.0867        | 6.5789  | 125  | 1.7080          |
| 0.0397        | 7.8947  | 150  | 1.7470          |
| 0.0356        | 9.2105  | 175  | 1.7648          |
| 0.0225        | 10.5263 | 200  | 1.7194          |
| 0.0122        | 11.8421 | 225  | 1.7498          |
| 0.0055        | 13.1579 | 250  | 1.8408          |
| 0.0034        | 14.4737 | 275  | 1.9249          |
| 0.003         | 15.7895 | 300  | 1.8917          |
| 0.0027        | 17.1053 | 325  | 1.8668          |
| 0.0023        | 18.4211 | 350  | 1.9104          |
| 0.0023        | 19.7368 | 375  | 1.9403          |
| 0.0022        | 21.0526 | 400  | 1.9561          |
| 0.0018        | 22.3684 | 425  | 1.9670          |
| 0.0019        | 23.6842 | 450  | 1.9720          |
| 0.002         | 25.0    | 475  | 1.9760          |
| 0.0015        | 26.3158 | 500  | 1.9773          |


### Framework versions

- PEFT 0.12.0
- Transformers 4.44.2
- Pytorch 2.4.0+cu121
- Datasets 3.0.0
- Tokenizers 0.19.1