---
base_model: meta-llama/Meta-Llama-3.1-8B-Instruct
datasets:
- GaetanMichelet/chat-60_ft_task-3
- GaetanMichelet/chat-120_ft_task-3
- GaetanMichelet/chat-180_ft_task-3
library_name: peft
license: llama3.1
tags:
- alignment-handbook
- trl
- sft
- generated_from_trainer
model-index:
- name: Llama-31-8B_task-3_180-samples_config-2
  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-31-8B_task-3_180-samples_config-2

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 GaetanMichelet/chat-60_ft_task-3, the GaetanMichelet/chat-120_ft_task-3 and the GaetanMichelet/chat-180_ft_task-3 datasets.
It achieves the following results on the evaluation set:
- Loss: 0.4326

## 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: 0.0001
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- distributed_type: multi-GPU
- gradient_accumulation_steps: 16
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 50

### Training results

| Training Loss | Epoch   | Step | Validation Loss |
|:-------------:|:-------:|:----:|:---------------:|
| 2.3768        | 0.9412  | 8    | 2.2322          |
| 1.3409        | 2.0     | 17   | 1.0478          |
| 0.6367        | 2.9412  | 25   | 0.6137          |
| 0.4263        | 4.0     | 34   | 0.5192          |
| 0.3991        | 4.9412  | 42   | 0.4931          |
| 0.4279        | 6.0     | 51   | 0.4564          |
| 0.3042        | 6.9412  | 59   | 0.4439          |
| 0.2975        | 8.0     | 68   | 0.4326          |
| 0.2668        | 8.9412  | 76   | 0.4597          |
| 0.179         | 10.0    | 85   | 0.4859          |
| 0.1451        | 10.9412 | 93   | 0.5927          |
| 0.053         | 12.0    | 102  | 0.7126          |
| 0.0246        | 12.9412 | 110  | 0.8255          |
| 0.0229        | 14.0    | 119  | 0.8520          |
| 0.0233        | 14.9412 | 127  | 0.8418          |


### Framework versions

- PEFT 0.12.0
- Transformers 4.44.0
- Pytorch 2.1.2+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1