metadata
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-8
results: []
adl-hw3-finetune-gemma-2-chinese-kyara-8
This model is a fine-tuned version of zake7749/gemma-2-2b-it-chinese-kyara-dpo on the None dataset. It achieves the following results on the evaluation set:
- Loss: 2.3677
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 |
|---|---|---|---|
| 2.4006 | 0.3556 | 200 | 2.2401 |
| 2.2057 | 0.7111 | 400 | 2.1517 |
| 2.0418 | 1.0667 | 600 | 2.1563 |
| 1.6718 | 1.4222 | 800 | 2.1595 |
| 1.7035 | 1.7778 | 1000 | 2.1365 |
| 1.4773 | 2.1333 | 1200 | 2.3602 |
| 1.1692 | 2.4889 | 1400 | 2.3637 |
| 1.1725 | 2.8444 | 1600 | 2.3677 |
Framework versions
- PEFT 0.13.2
- Transformers 4.45.1
- Pytorch 2.5.0+cu121
- Datasets 3.1.0
- Tokenizers 0.20.3