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-gemma-ch-1
results: []
adl-hw3-gemma-ch-1
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: 3.7677
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: 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: 6
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.4381 | 0.64 | 200 | 2.2165 |
| 1.9414 | 1.28 | 400 | 2.3546 |
| 1.5135 | 1.92 | 600 | 2.3314 |
| 0.7845 | 2.56 | 800 | 2.8106 |
| 0.5724 | 3.2 | 1000 | 3.4573 |
| 0.2391 | 3.84 | 1200 | 3.4574 |
| 0.1169 | 4.48 | 1400 | 3.7176 |
| 0.0685 | 5.12 | 1600 | 3.7769 |
| 0.0195 | 5.76 | 1800 | 3.7677 |
Framework versions
- PEFT 0.13.2
- Transformers 4.45.1
- Pytorch 2.5.0+cu121
- Datasets 3.1.0
- Tokenizers 0.20.3