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

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-1, the GaetanMichelet/chat-120_ft_task-1 and the GaetanMichelet/chat-180_ft_task-1 datasets.
It achieves the following results on the evaluation set:
- Loss: 0.8679

## 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: 8
- total_train_batch_size: 8
- 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 |
|:-------------:|:-----:|:----:|:---------------:|
| 2.203         | 1.0   | 17   | 2.1026          |
| 1.4704        | 2.0   | 34   | 1.3812          |
| 0.9871        | 3.0   | 51   | 1.0200          |
| 0.8739        | 4.0   | 68   | 0.9493          |
| 0.8392        | 5.0   | 85   | 0.8938          |
| 0.7701        | 6.0   | 102  | 0.8679          |
| 0.6585        | 7.0   | 119  | 0.8812          |
| 0.5569        | 8.0   | 136  | 0.9444          |
| 0.3568        | 9.0   | 153  | 1.1293          |
| 0.2586        | 10.0  | 170  | 1.2246          |
| 0.1738        | 11.0  | 187  | 1.3852          |
| 0.1252        | 12.0  | 204  | 1.4786          |
| 0.1           | 13.0  | 221  | 1.6062          |


### Framework versions

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