---
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-6
  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-6

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: 2.1672

## 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: 2
- total_train_batch_size: 16
- 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 |
|:-------------:|:------:|:----:|:---------------:|
| 2.3052        | 0.3556 | 200  | 2.1474          |
| 2.1059        | 0.7111 | 400  | 2.0666          |
| 1.9761        | 1.0667 | 600  | 2.0535          |
| 1.7046        | 1.4222 | 800  | 2.0527          |
| 1.7285        | 1.7778 | 1000 | 2.0320          |
| 1.5505        | 2.1333 | 1200 | 2.1532          |
| 1.3239        | 2.4889 | 1400 | 2.1683          |
| 1.3304        | 2.8444 | 1600 | 2.1672          |


### Framework versions

- PEFT 0.13.2
- Transformers 4.45.1
- Pytorch 2.5.0+cu121
- Datasets 3.1.0
- Tokenizers 0.20.3