---
library_name: peft
tags:
- trl
- sft
- generated_from_trainer
datasets:
- generator
base_model: NousResearch/Llama-2-7b-hf
model-index:
- name: llama2_instruct_generation
  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. -->

# llama2_instruct_generation

This model is a fine-tuned version of [NousResearch/Llama-2-7b-hf](https://huggingface.co/NousResearch/Llama-2-7b-hf) on the generator dataset.
It achieves the following results on the evaluation set:
- Loss: 1.6730

## 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: 4
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant
- lr_scheduler_warmup_steps: 0.03
- training_steps: 500

### Training results

| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 1.8384        | 0.0   | 20   | 1.8088          |
| 1.8698        | 0.01  | 40   | 1.7806          |
| 1.9017        | 0.01  | 60   | 1.7659          |
| 1.8842        | 0.01  | 80   | 1.7552          |
| 1.8097        | 0.01  | 100  | 1.7439          |
| 1.843         | 0.02  | 120  | 1.7153          |
| 1.793         | 0.02  | 140  | 1.7046          |
| 1.8985        | 0.02  | 160  | 1.7015          |
| 1.8716        | 0.02  | 180  | 1.6976          |
| 1.8351        | 0.03  | 200  | 1.6949          |
| 1.8368        | 0.03  | 220  | 1.6933          |
| 1.8696        | 0.03  | 240  | 1.6879          |
| 1.8218        | 0.04  | 260  | 1.6866          |
| 1.6993        | 0.04  | 280  | 1.6847          |
| 1.8128        | 0.04  | 300  | 1.6832          |
| 1.875         | 0.04  | 320  | 1.6820          |
| 1.8388        | 0.05  | 340  | 1.6799          |
| 1.7753        | 0.05  | 360  | 1.6791          |
| 1.7578        | 0.05  | 380  | 1.6793          |
| 1.8476        | 0.05  | 400  | 1.6770          |
| 1.8183        | 0.06  | 420  | 1.6766          |
| 1.6523        | 0.06  | 440  | 1.6760          |
| 1.8046        | 0.06  | 460  | 1.6756          |
| 1.8347        | 0.07  | 480  | 1.6745          |
| 1.7741        | 0.07  | 500  | 1.6730          |


### Framework versions

- PEFT 0.7.1
- Transformers 4.36.2
- Pytorch 2.1.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.0