metadata
base_model: zake7749/gemma-2-2b-it-chinese-kyara-dpo
library_name: peft
license: gemma
tags:
- trl
- sft
- generated_from_trainer
model-index:
- name: ADL_Gemma4
results: []
ADL_Gemma4
This model is a fine-tuned version of zake7749/gemma-2-2b-it-chinese-kyara-dpo on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.3535
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: 5e-05
- train_batch_size: 8
- eval_batch_size: 2
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine_with_restarts
- lr_scheduler_warmup_ratio: 0.02
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.5844 | 1.0 | 1250 | 1.4583 |
| 1.4602 | 2.0 | 2500 | 1.3865 |
| 1.4141 | 3.0 | 3750 | 1.3632 |
| 1.4011 | 4.0 | 5000 | 1.3547 |
| 1.3975 | 5.0 | 6250 | 1.3535 |
Framework versions
- PEFT 0.13.2
- Transformers 4.45.1
- Pytorch 2.5.0+cu121
- Datasets 3.0.2
- Tokenizers 0.20.1