---
license: llama3.1
library_name: peft
tags:
- generated_from_trainer
base_model: meta-llama/Meta-Llama-3.1-8B-Instruct
model-index:
- name: llama3_8b_instruct_BWRM
  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. -->

# llama3_8b_instruct_BWRM

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 None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.2710

## 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: 0.0005
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 32
- total_train_batch_size: 1024
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3

### Training results

| Training Loss | Epoch  | Step | Validation Loss |
|:-------------:|:------:|:----:|:---------------:|
| 0.8058        | 0.1840 | 20   | 0.5918          |
| 0.5986        | 0.3680 | 40   | 0.5643          |
| 0.5513        | 0.5520 | 60   | 0.5113          |
| 0.5039        | 0.7361 | 80   | 0.4433          |
| 0.4539        | 0.9201 | 100  | 0.4424          |
| 0.4083        | 1.1041 | 120  | 0.4024          |
| 0.3823        | 1.2881 | 140  | 0.3805          |
| 0.3644        | 1.4721 | 160  | 0.3400          |
| 0.336         | 1.6561 | 180  | 0.3206          |
| 0.3314        | 1.8401 | 200  | 0.3185          |
| 0.3105        | 2.0242 | 220  | 0.3078          |
| 0.2929        | 2.2082 | 240  | 0.2948          |
| 0.2855        | 2.3922 | 260  | 0.2831          |
| 0.2787        | 2.5762 | 280  | 0.2821          |
| 0.2717        | 2.7602 | 300  | 0.2757          |
| 0.2703        | 2.9442 | 320  | 0.2710          |


### Framework versions

- PEFT 0.10.0
- Transformers 4.44.0
- Pytorch 2.3.0+cu121
- Datasets 3.0.0
- Tokenizers 0.19.1