---
base_model: meta-llama/Llama-2-7b-hf
tags:
- generated_from_trainer
model-index:
- name: Llama-2-7b-hf-eli5-cleaned-1024_qlora
  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. -->

# Llama-2-7b-hf-eli5-cleaned-1024_qlora

This model is a fine-tuned version of [meta-llama/Llama-2-7b-hf](https://huggingface.co/meta-llama/Llama-2-7b-hf) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 2.2063

## 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: 32
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.03
- num_epochs: 3

### Training results

| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 2.1545        | 0.3   | 91   | 2.1962          |
| 2.1436        | 0.6   | 182  | 2.1883          |
| 2.1159        | 0.9   | 273  | 2.1853          |
| 2.0772        | 1.21  | 364  | 2.1907          |
| 2.076         | 1.51  | 455  | 2.1981          |
| 2.0961        | 1.81  | 546  | 2.1883          |
| 2.0357        | 2.11  | 637  | 2.1906          |
| 2.0721        | 2.41  | 728  | 2.1973          |
| 1.9755        | 2.71  | 819  | 2.2063          |


### Framework versions

- Transformers 4.34.0.dev0
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3