---
base_model: zake7749/gemma-2-2b-it-chinese-kyara-dpo
library_name: peft
license: gemma
tags:
- generated_from_trainer
model-index:
- name: adl-hw3-finetune-gemma-2-chinese-kyara-3
  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. -->

# adl-hw3-finetune-gemma-2-chinese-kyara-3

This model is a fine-tuned version of [zake7749/gemma-2-2b-it-chinese-kyara-dpo](https://huggingface.co/zake7749/gemma-2-2b-it-chinese-kyara-dpo) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 1.9876

## 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: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 64
- 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 |
|:-------------:|:------:|:----:|:---------------:|
| 2.411         | 0.1778 | 25   | 2.1908          |
| 2.1761        | 0.3556 | 50   | 2.0986          |
| 2.112         | 0.5333 | 75   | 2.0473          |
| 2.0094        | 0.7111 | 100  | 2.0131          |
| 1.9921        | 0.8889 | 125  | 1.9900          |
| 1.9151        | 1.0667 | 150  | 1.9888          |
| 1.757         | 1.2444 | 175  | 1.9812          |
| 1.7965        | 1.4222 | 200  | 1.9721          |
| 1.809         | 1.6    | 225  | 1.9549          |
| 1.771         | 1.7778 | 250  | 1.9485          |
| 1.7242        | 1.9556 | 275  | 1.9445          |
| 1.6151        | 2.1333 | 300  | 1.9957          |
| 1.5499        | 2.3111 | 325  | 1.9892          |
| 1.5169        | 2.4889 | 350  | 1.9909          |
| 1.5429        | 2.6667 | 375  | 1.9832          |
| 1.5409        | 2.8444 | 400  | 1.9876          |


### Framework versions

- PEFT 0.13.2
- Transformers 4.45.1
- Pytorch 2.5.0+cu121
- Datasets 3.1.0
- Tokenizers 0.20.2