|
--- |
|
base_model: shenzhi-wang/Llama3-8B-Chinese-Chat |
|
library_name: peft |
|
license: llama3 |
|
tags: |
|
- llama-factory |
|
- lora |
|
- generated_from_trainer |
|
model-index: |
|
- name: wenjie_6k |
|
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. --> |
|
|
|
# wenjie_6k |
|
|
|
This model is a fine-tuned version of [shenzhi-wang/Llama3-8B-Chinese-Chat](https://huggingface.co/shenzhi-wang/Llama3-8B-Chinese-Chat) on the data_large2, the target_QA_short and the append_QA datasets. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.9191 |
|
|
|
## 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: 8e-06 |
|
- train_batch_size: 4 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- distributed_type: multi-GPU |
|
- num_devices: 4 |
|
- gradient_accumulation_steps: 4 |
|
- total_train_batch_size: 64 |
|
- total_eval_batch_size: 32 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: cosine |
|
- lr_scheduler_warmup_ratio: 0.05 |
|
- num_epochs: 4 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:------:|:----:|:---------------:| |
|
| 0.9918 | 2.1448 | 200 | 0.9989 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.12.0 |
|
- Transformers 4.43.3 |
|
- Pytorch 2.4.1+cu121 |
|
- Datasets 2.20.0 |
|
- Tokenizers 0.19.1 |
