|
--- |
|
license: other |
|
library_name: peft |
|
tags: |
|
- llama-factory |
|
- lora |
|
- generated_from_trainer |
|
base_model: THUDM/chatglm3-6b |
|
model-index: |
|
- name: LangGPT |
|
results: [] |
|
--- |
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
# LangGPT |
|
|
|
This model is a fine-tuned version of [/datas/huangyijie/my_model/chatglm3-6b](https://huggingface.co.//datas/huangyijie/my_model/chatglm3-6b) on the LangGPT dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.8991 |
|
|
|
## 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: 12 |
|
- eval_batch_size: 4 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 8 |
|
- total_train_batch_size: 96 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: cosine |
|
- lr_scheduler_warmup_steps: 20 |
|
- num_epochs: 9.0 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| 1.0558 | 1.25 | 100 | 1.0500 | |
|
| 0.9566 | 2.5 | 200 | 0.9630 | |
|
| 0.9082 | 3.75 | 300 | 0.9288 | |
|
| 0.8992 | 5.0 | 400 | 0.9108 | |
|
| 0.8874 | 6.25 | 500 | 0.9028 | |
|
| 0.8835 | 7.5 | 600 | 0.8997 | |
|
| 0.8912 | 8.75 | 700 | 0.8991 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.10.0 |
|
- Transformers 4.40.1 |
|
- Pytorch 2.2.0+cu121 |
|
- Datasets 2.16.1 |
|
- Tokenizers 0.19.1 |
