提出するにあたって行ったファインチューニングの手順
使用環境
Omnicampusの演習環境（Jupyter Notebook）
事前準備
- Jupyter Notebookで
LoRA_template_20241127.ipynbを開く
elyza-tasks-100-TV_0.jsonlと学習用データセットをJupyter Notebookに読み込ませる。- Kernelに
LoRA_template_20241127.ipynbを選択（おそらくこの手順は不要？）
実行
早送りマークのRestart the kernel, then re-run the whole notebookをクリック。
LoRA_template_20241127.ipynbではSFT実行直後にelyza-tasks-100-TV_0.jsonlをインプットとした推論が実行され、jsonlで出力される。
合計所要時間は45分程度だった。（うちSFT30分、推論15分）
参考
LLMでの出力方法
LoRA_template_20241127.ipynbからの直接引用ではあるが、以下のコードでモデルを実行できるはずである。
1
2# モデルによるタスクの推論。
3from tqdm import tqdm
4
5results = []
6for data in tqdm(datasets):
7
8 input = data["input"]
9
10 prompt = f"""### 指示
11 {input}
12 ### 回答
13 """
14
15 tokenized_input = tokenizer.encode(prompt, add_special_tokens=False, return_tensors="pt").to(model.device)
16 attention_mask = torch.ones_like(tokenized_input)
17
18 with torch.no_grad():
19 outputs = model.generate(
20 tokenized_input,
21 attention_mask=attention_mask,
22 max_new_tokens=100,
23 do_sample=False,
24 repetition_penalty=1.2,
25 pad_token_id=tokenizer.eos_token_id
26 )[0]
27 output = tokenizer.decode(outputs[tokenized_input.size(1):], skip_special_tokens=True)
28
29 results.append({"task_id": data["task_id"], "input": input, "output": output})
30
31
32# jsonlで保存
33with open(f"{new_model_id}_output.jsonl", 'w', encoding='utf-8') as f:
34 for result in results:
35 json.dump(result, f, ensure_ascii=False)
36 f.write('\n')
Model Card for Model ID
Model Details
Model Description
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- Developed by: [More Information Needed]
- Funded by [optional]: [More Information Needed]
- Shared by [optional]: [More Information Needed]
- Model type: [More Information Needed]
- Language(s) (NLP): [More Information Needed]
- License: [More Information Needed]
- Finetuned from model [optional]: [More Information Needed]
Model Sources [optional]
- Repository: [More Information Needed]
- Paper [optional]: [More Information Needed]
- Demo [optional]: [More Information Needed]
Uses
Direct Use
[More Information Needed]
Downstream Use [optional]
[More Information Needed]
Out-of-Scope Use
[More Information Needed]
Bias, Risks, and Limitations
[More Information Needed]
Recommendations
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
Training Details
Training Data
[More Information Needed]
Training Procedure
Preprocessing [optional]
[More Information Needed]
Training Hyperparameters
- Training regime: [More Information Needed]
Speeds, Sizes, Times [optional]
[More Information Needed]
Evaluation
Testing Data, Factors & Metrics
Testing Data
[More Information Needed]
Factors
[More Information Needed]
Metrics
[More Information Needed]
Results
[More Information Needed]
Summary
Model Examination [optional]
[More Information Needed]
Environmental Impact
Carbon emissions can be estimated using the
Machine Learning Impact calculator presented in
Lacoste et al. (2019).
- Hardware Type: [More Information Needed]
- Hours used: [More Information Needed]
- Cloud Provider: [More Information Needed]
- Compute Region: [More Information Needed]
- Carbon Emitted: [More Information Needed]
Technical Specifications [optional]
Model Architecture and Objective
[More Information Needed]
Compute Infrastructure
[More Information Needed]
Hardware
[More Information Needed]
Software
[More Information Needed]
Citation [optional]
BibTeX:
[More Information Needed]
APA:
[More Information Needed]
Glossary [optional]
[More Information Needed]
More Information [optional]
[More Information Needed]
Model Card Authors [optional]
[More Information Needed]
Model Card Contact
[More Information Needed]
