---
library_name: peft
tags:
- llama-factory
- lora
- generated_from_trainer
base_model: meta-llama/Meta-Llama-3-8B
model-index:
- name: Llama3_AAID_new_mixed_train
  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_AAID_new_mixed_train

This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B) on the AAID_new_mixed dataset.
It achieves the following results on the evaluation set:
- Loss: 0.8102

## 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: 0.0003
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 256
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- num_epochs: 3.0

### Training results

| Training Loss | Epoch  | Step | Validation Loss |
|:-------------:|:------:|:----:|:---------------:|
| 1.0078        | 0.0109 | 10   | 0.9154          |
| 0.5077        | 0.0219 | 20   | 0.8372          |
| 0.4613        | 0.0328 | 30   | 0.8333          |
| 0.4794        | 0.0438 | 40   | 0.8321          |
| 0.4624        | 0.0547 | 50   | 0.8181          |
| 0.4366        | 0.0656 | 60   | 0.8192          |
| 0.4323        | 0.0766 | 70   | 0.8175          |
| 0.433         | 0.0875 | 80   | 0.8255          |
| 0.4401        | 0.0984 | 90   | 0.8293          |
| 0.4019        | 0.1094 | 100  | 0.8467          |
| 0.4112        | 0.1203 | 110  | 0.8102          |
| 0.4009        | 0.1313 | 120  | 0.8458          |
| 0.4023        | 0.1422 | 130  | 0.8430          |
| 0.3924        | 0.1531 | 140  | 0.8300          |
| 0.4079        | 0.1641 | 150  | 0.8370          |
| 0.3898        | 0.1750 | 160  | 0.8523          |


### Framework versions

- PEFT 0.11.1
- Transformers 4.41.1
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1