|
--- |
|
license: cc-by-nc-4.0 |
|
base_model: KT-AI/midm-bitext-S-7B-inst-v1 |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: lora-midm-7b-nsmc-understanding |
|
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. --> |
|
|
|
# lora-midm-7b-nsmc-understanding |
|
|
|
This model is a fine-tuned version of [KT-AI/midm-bitext-S-7B-inst-v1](https://huggingface.co/KT-AI/midm-bitext-S-7B-inst-v1) on an unknown dataset. |
|
|
|
## 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: 1 |
|
- eval_batch_size: 1 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 2 |
|
- total_train_batch_size: 2 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: cosine |
|
- lr_scheduler_warmup_ratio: 0.03 |
|
- training_steps: 1500 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.35.2 |
|
- Pytorch 2.1.0+cu118 |
|
- Datasets 2.15.0 |
|
- Tokenizers 0.15.0 |
|
|
|
|
|
### test accuracy |
|
kt-ai-midm |
|
- Confusion Matrix: |
|
||Predicted 0|Predicted 1| |
|
|:---|---:|---:| |
|
|Actual 0|443|49| |
|
|Actual 1|46|462| |
|
**Accuracy: 0.905** |
|
|
|
llama-2 |
|
- Confusion Matrix: |
|
||Predicted 0|Predicted 1| |
|
|:---|---:|---:| |
|
|Actual 0|450|42| |
|
|Actual 1|56|452| |
|
**Accuracy: 0.902** |
|
|
|
### ์์ ๋ถ๋ถ |
|
- ๋ฐ์ดํฐ๋ก๋ฉ |
|
- prepare_sample_text() : ์์คํ
๋ฉ์์ง ๋ณ๊ฒฝ ๋ฐ ํ๋กฌํํธ ํฌ๋ฉง ์ค์ |
|
- create_datasets() : train ๋ฐ์ดํฐ ์์ 2000๊ฐ ์ ํ |
|
- ๋ฏธ์ธํ๋์ฉ ๋ชจ๋ธ ๋ก๋ฉ |
|
- script_args : ์ฌ์ฉ ๋ฐ์ดํฐ๋ช
nsmc ์ค์ ๋ฐ ๋ชจ๋ธ๋ช
KT-AI/midm-bitext-S-7B-inst-v1 ์ค์ |
|
- max_steps : ์ต๋ ํ๋ จ ๋จ๊ณ 1500 ์ค์ (300->1000->1500 ์์ ๊ฒฐ๊ณผ ๋์ ์ ํ๋) |
|
- save : ์ฒดํฌํฌ์ธํธ ์ธ์ด๋ธ๋ฅผ ์ํ ํ๋ผ๋ฏธํฐ ์ง์ |
|
- ํ๊น
ํ์ด์ค push_to_hub ๋ก push |
|
- ์ถ๋ก ํ
์คํธ |
|
- ํ๋กฌํํธ ํ
ํ๋ฆฟ ์์ ๋ฐ ์์คํ
๋ฉ์์ง ๋ณ๊ฒฝ |
|
- valid_dataset : test ๋ฐ์ดํฐ ์์ 1000๊ฐ ์ ํ |
|
- ๋ฏธ์ธํ๋๋ ๋ชจ๋ธ ๋ก๋ฉ ํ ํ
์คํธ |
|
- eval_dic : valid_dataset ํ์ตํ ๊ฒฐ๊ณผ ์ถ๋ ฅ |
|
- ์ ํ๋ |
|
- valid_dataset ๊ณผ ๋ชจ๋ธ ํ๋ จ ๊ฒฐ๊ณผ true_labels ๋ฅผ ์ด์ฉํ ์ ํ๋ ๋ถ์ |