---
base_model: huggyllama/llama-13b
library_name: peft
license: other
tags:
- generated_from_trainer
model-index:
- name: llama-13b_oasst1_l0.0002_32-8-8-8-8
  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-13b_oasst1_l0.0002_32-8-8-8-8

This model is a fine-tuned version of [huggyllama/llama-13b](https://huggingface.co/huggyllama/llama-13b) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 1.5115

## 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: 1
- seed: 0
- gradient_accumulation_steps: 16
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant
- lr_scheduler_warmup_ratio: 0.03
- training_steps: 1875

### Training results

| Training Loss | Epoch  | Step | Validation Loss |
|:-------------:|:------:|:----:|:---------------:|
| 1.4264        | 0.0018 | 1    | 1.5678          |
| 1.4263        | 0.3392 | 187  | 1.2365          |
| 1.0712        | 0.6783 | 374  | 1.2313          |
| 1.2232        | 1.0175 | 561  | 1.2366          |
| 0.9766        | 1.3566 | 748  | 1.2977          |
| 0.983         | 1.6958 | 935  | 1.2653          |
| 0.5607        | 2.0349 | 1122 | 1.3461          |
| 0.7534        | 2.3741 | 1309 | 1.3852          |
| 0.5426        | 2.7132 | 1496 | 1.4808          |
| 0.2964        | 3.0524 | 1683 | 1.5780          |
| 0.3246        | 3.3915 | 1870 | 1.4927          |


### Framework versions

- PEFT 0.12.1.dev0
- Transformers 4.45.0.dev0
- Pytorch 2.3.0+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1