---
base_model: shenzhi-wang/Llama3.1-8B-Chinese-Chat
library_name: peft
license: other
tags:
- llama-factory
- lora
- generated_from_trainer
model-index:
- name: Llama3.1-8B-Chinese-Chat
  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. -->

# Llama3.1-8B-Chinese-Chat

This model is a fine-tuned version of [shenzhi-wang/Llama3.1-8B-Chinese-Chat](https://huggingface.co./shenzhi-wang/Llama3.1-8B-Chinese-Chat) on the alpaca_mgtv_p2 dataset.
It achieves the following results on the evaluation set:
- Loss: 0.2191

## 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: 16
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 2.0

### Training results

| Training Loss | Epoch  | Step | Validation Loss |
|:-------------:|:------:|:----:|:---------------:|
| 0.3253        | 0.1990 | 35   | 0.2875          |
| 0.2868        | 0.3980 | 70   | 0.2600          |
| 0.2583        | 0.5970 | 105  | 0.2508          |
| 0.2559        | 0.7960 | 140  | 0.2279          |
| 0.2516        | 0.9950 | 175  | 0.2221          |
| 0.2086        | 1.1940 | 210  | 0.2271          |
| 0.238         | 1.3930 | 245  | 0.2183          |
| 0.2176        | 1.5920 | 280  | 0.2206          |
| 0.2022        | 1.7910 | 315  | 0.2209          |
| 0.209         | 1.9900 | 350  | 0.2191          |


### Framework versions

- PEFT 0.11.1
- Transformers 4.43.3
- Pytorch 2.4.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1