adl-hw3-finetune-gemma-2-chinese-kyara-9
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: 2.4161
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 |
---|---|---|---|
2.3905 | 0.3556 | 200 | 2.2320 |
2.1861 | 0.7111 | 400 | 2.1389 |
2.0197 | 1.0667 | 600 | 2.1465 |
1.6156 | 1.4222 | 800 | 2.1497 |
1.6436 | 1.7778 | 1000 | 2.1270 |
1.3931 | 2.1333 | 1200 | 2.4114 |
1.0559 | 2.4889 | 1400 | 2.4010 |
1.0551 | 2.8444 | 1600 | 2.4161 |
Framework versions
- PEFT 0.13.2
- Transformers 4.45.1
- Pytorch 2.5.0+cu121
- Datasets 3.1.0
- Tokenizers 0.20.3
- Downloads last month
- 13
Model tree for jazzson/adl-hw3-finetune-gemma-2-chinese-kyara-9
Base model
google/gemma-2-2b
Finetuned
google/gemma-2-2b-it
Finetuned
zake7749/gemma-2-2b-it-chinese-kyara-dpo