Configuration Parsing
Warning:
In adapter_config.json: "peft.base_model_name_or_path" must be a string
chineseChat-ft
This model is a fine-tuned version of charent/ChatLM-mini-Chinese on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.5714
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: 0.0005
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 2
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.5608 | 0.8 | 1 | 0.9636 |
| 1.5192 | 1.6 | 2 | 0.9396 |
| 1.4317 | 2.4 | 3 | 0.8800 |
| 0.6634 | 4.0 | 5 | 0.7525 |
| 1.1704 | 4.8 | 6 | 0.6948 |
| 1.0617 | 5.6 | 7 | 0.6460 |
| 1.0182 | 6.4 | 8 | 0.6089 |
| 0.4789 | 8.0 | 10 | 0.5714 |
Framework versions
- PEFT 0.11.1
- Transformers 4.41.2
- Pytorch 2.3.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1
- Downloads last month
- 5
Model tree for ytke/chineseChat-ft
Base model
charent/ChatLM-mini-Chinese