---
base_model: meta-llama/Meta-Llama-3.1-8B-Instruct
datasets:
- generator
library_name: peft
license: llama3.1
tags:
- trl
- sft
- generated_from_trainer
model-index:
- name: llama38binstruct_summarize
  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. -->

# llama38binstruct_summarize

This model is a fine-tuned version of [meta-llama/Meta-Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct) on the generator dataset.
It achieves the following results on the evaluation set:
- Loss: 1.7064

## 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: 2e-05
- train_batch_size: 2
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 8
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant
- lr_scheduler_warmup_steps: 3
- training_steps: 100

### Training results

| Training Loss | Epoch   | Step | Validation Loss |
|:-------------:|:-------:|:----:|:---------------:|
| 1.5991        | 9.0909  | 25   | 1.4645          |
| 1.0686        | 18.1818 | 50   | 1.3393          |
| 0.8047        | 27.2727 | 75   | 1.3950          |
| 0.3302        | 36.3636 | 100  | 1.7064          |


### Framework versions

- PEFT 0.12.0
- Transformers 4.44.2
- Pytorch 2.1.0+cu118
- Datasets 3.0.0
- Tokenizers 0.19.1