---
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: 1.6737

## 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 |
|:-------------:|:-----:|:----:|:---------------:|
| 1.9238        | 0.0   | 20   | 1.8060          |
| 1.9181        | 0.01  | 40   | 1.7781          |
| 1.8185        | 0.01  | 60   | 1.7652          |
| 1.8336        | 0.01  | 80   | 1.7504          |
| 1.8205        | 0.01  | 100  | 1.7275          |
| 1.7673        | 0.02  | 120  | 1.7090          |
| 1.7934        | 0.02  | 140  | 1.6996          |
| 1.7844        | 0.02  | 160  | 1.6953          |
| 1.7847        | 0.02  | 180  | 1.6932          |
| 1.7772        | 0.03  | 200  | 1.6897          |
| 1.7883        | 0.03  | 220  | 1.6896          |
| 1.8346        | 0.03  | 240  | 1.6852          |
| 1.6646        | 0.04  | 260  | 1.6834          |
| 1.7433        | 0.04  | 280  | 1.6822          |
| 1.7762        | 0.04  | 300  | 1.6809          |
| 1.8508        | 0.04  | 320  | 1.6796          |
| 1.7275        | 0.05  | 340  | 1.6791          |
| 1.8002        | 0.05  | 360  | 1.6755          |
| 1.855         | 0.05  | 380  | 1.6768          |
| 1.7529        | 0.05  | 400  | 1.6751          |
| 1.7728        | 0.06  | 420  | 1.6737          |
| 1.8053        | 0.06  | 440  | 1.6737          |
| 1.8579        | 0.06  | 460  | 1.6736          |
| 1.7383        | 0.07  | 480  | 1.6735          |
| 1.9282        | 0.07  | 500  | 1.6737          |


### Framework versions

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