ADL_Gemma6
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: 1.2804
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: 0.0004
- 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
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.35 | 1.0 | 1250 | 1.2978 |
| 1.3365 | 2.0 | 2500 | 1.2999 |
| 1.3023 | 3.0 | 3750 | 1.2839 |
| 1.3025 | 4.0 | 5000 | 1.2844 |
| 1.2701 | 5.0 | 6250 | 1.2804 |
Framework versions
- PEFT 0.13.2
- Transformers 4.45.1
- Pytorch 2.5.0+cu121
- Datasets 3.0.2
- Tokenizers 0.20.1
- Downloads last month
- 7
Model tree for b09501048/ADL_Gemma6
Base model
google/gemma-2-2b
Finetuned
google/gemma-2-2b-it
Finetuned
zake7749/gemma-2-2b-it-chinese-kyara-dpo