llm-jp-3-13b-finetune5

Uploaded Model

Finetuned from model: llm-jp/llm-jp-3-13b

# python 3.10.12
!pip install -U pip
!pip install -U transformers
!pip install -U bitsandbytes
!pip install -U accelerate
!pip install -U datasets
!pip install -U peft
!pip install -U trl
!pip install -U wandb
!pip install ipywidgets --upgrade

from transformers import (
    AutoModelForCausalLM,
    AutoTokenizer,
    BitsAndBytesConfig,
    TrainingArguments,
    logging,
    EarlyStoppingCallback
)
from peft import (
    LoraConfig,
    PeftModel,
    get_peft_model,
)
import os, torch, gc
from datasets import load_dataset
import bitsandbytes as bnb
from trl import SFTTrainer

# Hugging Face Token
HF_TOKEN = "Hugging Faceのトークンを入力"

# モデルを読み込み。
base_model_id = "models/models--llm-jp--llm-jp-3-13b/snapshots/cd3823f4c1fcbb0ad2e2af46036ab1b0ca13192a" #Fine-Tuningするベースモデル
new_model_id = "llm-jp-3-13b-finetune5" #Fine-Tuningしたモデルにつけたい名前

# 量子化の設定
bnb_config = BitsAndBytesConfig(
    load_in_4bit=True,
    bnb_4bit_quant_type="nf4", # nf4は通常のINT4より精度が高く、ニューラルネットワークの分布に最適です
    bnb_4bit_compute_dtype=torch.bfloat16,
)

# モデルの設定
model = AutoModelForCausalLM.from_pretrained(
    base_model_id,
    quantization_config=bnb_config,
    device_map="auto"
)

tokenizer = AutoTokenizer.from_pretrained(base_model_id, trust_remote_code=True)

# モデル内の4bit量子化線形層の探索
def find_all_linear_names(model):
    cls = bnb.nn.Linear4bit # 4bit量子化線形層クラスを指定
    lora_module_names = set() # ここに取得した線形層を保持します。

    # モデル内の全てのモジュールを探索します
    for name, module in model.named_modules():
        if isinstance(module, cls): # モジュールが4bit量子化線形層の場合
            names = name.split('.') # モジュールの名前を分割 (ネストされてる際などに対処)
            lora_module_names.add(names[0] if len(names) == 1 else names[-1]) # 最下層の名前をlora_module_namesに追加

    # 'lm_head' は16ビット演算の際に除外する必要があるため、lora_module_namesから削除
    if 'lm_head' in lora_module_names:
        lora_module_names.remove('lm_head')

    return list(lora_module_names) # lora_module_namesをリストに変換して返します。

modules = find_all_linear_names(model)

# PEFTの構成設定
peft_config = LoraConfig(
    r=16,
    lora_alpha=32,
    lora_dropout=0.05,
    bias="none",
    task_type="CAUSAL_LM",
    target_modules=modules,
)

model = get_peft_model(model, peft_config)

# 学習に用いるデータセットの設定
# LLM-jpが公開しているIchikara Instructionを使用
# Distribution20241221_all内のjsonファイルを結合して使用（ichikara-instruction-003-002-1.jsonは除く）
data_dir = "./Distribution20241221_all"
files = os.listdir(data_dir)
json_files = [f"{data_dir}/{f}" for f in files if f.endswith(".json") == True]
dataset = load_dataset("json", data_files=json_files)
dataset

# 学習時のプロンプトフォーマットの定義
EOS_TOKEN = tokenizer.eos_token # トークナイザーのEOSトークン（文末トークン）
def formatting_prompts_func(examples):
    input = examples["text"] # 入力データ
    output = examples["output"] # 出力データ
    text = prompt.format(input, output) + EOS_TOKEN # プロンプトの作成
    return { "formatted_text" : text, } # 新しいフィールド "formatted_text" を返す
pass

# # 各データにフォーマットを適用
dataset = dataset.map(
    formatting_prompts_func,
    num_proc= 4, # 並列処理数を指定
)

dataset

# データを確認
print(dataset["train"]["formatted_text"][3])

# データをtrainデータとtestデータに分割 (test_sizeの比率に)
dataset = dataset["train"].train_test_split(test_size=0.1)
dataset

# 学習の設定
training_arguments = TrainingArguments(
    output_dir=new_model_id,
    per_device_train_batch_size=1,
    per_device_eval_batch_size=1,
    gradient_accumulation_steps=2,
    optim="paged_adamw_32bit",
    num_train_epochs=1,
    logging_strategy="steps",
    logging_steps=10,
    eval_strategy="steps",
    eval_steps = 100,
    warmup_steps=10,
    save_steps=100,
    save_total_limit = 2,
    max_steps = -1,
    learning_rate=5e-5,
    fp16=False,
    bf16=False,
    seed = 3407,
    group_by_length=True,
    report_to="none",
    load_best_model_at_end=True,
)


# Supervised Fine-Tuningに関する設定
# 過学習防止のため、early_stoppingを設定
early_stopping = EarlyStoppingCallback(
    early_stopping_patience=50,
    early_stopping_threshold=0.01
)

trainer = SFTTrainer(
    model=model,
    train_dataset=dataset["train"],
    eval_dataset=dataset["test"],
    peft_config=peft_config,
    max_seq_length= 512,
    dataset_text_field="formatted_text",
    tokenizer=tokenizer,
    args=training_arguments,
    packing= False,
    callbacks=[early_stopping],
)

model.config.use_cache = False # キャッシュ機能を無効化
trainer.train() # トレーニングを実行

# タスクとなるデータの読み込み。
import json
datasets = []
with open("./elyza-tasks-100-TV_0.jsonl", "r") as f:
    item = ""
    for line in f:
      line = line.strip()
      item += line
      if item.endswith("}"):
        datasets.append(json.loads(item))
        item = ""

# モデルによるタスクの推論。
from tqdm import tqdm

results = []
for data in tqdm(datasets):

  input = data["input"]

  prompt = f"""### 指示
  \n{input} 簡潔に回答してください
  \n### 回答 \n
  """
    
  tokenized_input = tokenizer.encode(prompt, add_special_tokens=False, return_tensors="pt").to(model.device)
  attention_mask = torch.ones_like(tokenized_input)

  with torch.no_grad():
      outputs = model.generate(
          tokenized_input,
          attention_mask=attention_mask,
          max_new_tokens=100,
          do_sample=False,
          repetition_penalty=1.2,
          pad_token_id=tokenizer.eos_token_id
      )[0]
  output = tokenizer.decode(outputs[tokenized_input.size(1):], skip_special_tokens=True)

  results.append({"task_id": data["task_id"], "input": input, "output": output})

# 生成結果のjsolファイルの作成
import re
jsonl_id = re.sub(".*/", "", new_model_id)
with open(f"./{jsonl_id}-outputs.jsonl", 'w', encoding='utf-8') as f:
    for result in results:
        json.dump(result, f, ensure_ascii=False)  # ensure_ascii=False for handling non-ASCII characters
        f.write('\n')

# モデルとトークナイザーをHugging Faceにアップロード
model.push_to_hub(new_model_id, token=HF_TOKEN, private=True) # Online saving
tokenizer.push_to_hub(new_model_id, token=HF_TOKEN, private=True) # Online saving

Model Card for Model ID

<!-- Provide a quick summary of what the model is/does. -->

Model Details

Model Description

<!-- Provide a longer summary of what this model is. -->

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]

<!-- Provide the basic links for the model. -->

• Repository: [More Information Needed]
• Paper [optional]: [More Information Needed]
• Demo [optional]: [More Information Needed]

Uses

<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->

Direct Use

<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->

[More Information Needed]

Downstream Use [optional]

<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->

[More Information Needed]

Out-of-Scope Use

<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->

[More Information Needed]

Bias, Risks, and Limitations

<!-- This section is meant to convey both technical and sociotechnical limitations. -->

[More Information Needed]

Recommendations

<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->

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

<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->

[More Information Needed]

Training Procedure

<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->

Preprocessing [optional]

[More Information Needed]

Training Hyperparameters

• Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->

Speeds, Sizes, Times [optional]

<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->

[More Information Needed]

Evaluation

<!-- This section describes the evaluation protocols and provides the results. -->

Testing Data, Factors & Metrics

Testing Data

<!-- This should link to a Dataset Card if possible. -->

[More Information Needed]

Factors

<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->

[More Information Needed]

Metrics

<!-- These are the evaluation metrics being used, ideally with a description of why. -->

[More Information Needed]

Results

[More Information Needed]

Summary

Model Examination [optional]

<!-- Relevant interpretability work for the model goes here -->

[More Information Needed]

Environmental Impact

<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->

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]

<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->

BibTeX:

[More Information Needed]

APA:

[More Information Needed]

Glossary [optional]

<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->

[More Information Needed]

More Information [optional]

[More Information Needed]

Model Card Authors [optional]

[More Information Needed]

Model Card Contact

[More Information Needed]