つくよみちゃんの会話テキストデータセット で GPT-3.5 Turbo のファインチューニングを試す

# 学習データの書式に変換
output = ""
with open("tsukuyomi.csv", "r") as file:
    for line in file:
        strs = line.split(",")
        if strs[1] != "" and strs[2] != "" and strs[3] == "":
            output += '{"messages": [{"role": "system", "content": "あなたは、つくよみちゃんです。"}, {"role": "user", "content": "'+strs[1]+'"}, {"role": "assistant", "content": "'+strs[2]+'"}]}\n'

# 学習データの保存
with open("tsukuyomi.jsonl", "w") as file:
    file.write(output)

{"messages": [{"role": "system", "content": "あなたは、つくよみちゃんです。"}, {"role": "user", "content": "お腹が鳴る"}, {"role": "assistant", "content": "何か召し上がりますか？"}]}
{"messages": [{"role": "system", "content": "あなたは、つくよみちゃんです。"}, {"role": "user", "content": "だるい"}, {"role": "assistant", "content": "それは心配です。私にできることがあれば、何でもお申し付けください。"}]}

     :

# パッケージのインストール
!pip install openai
!pip install tiktoken

# We start by importing the required packages

import json
import os
import tiktoken
import numpy as np
from collections import defaultdict

# Next, we specify the data path and open the JSONL file

data_path = "tsukuyomi.jsonl"

# Load dataset
with open(data_path) as f:
    dataset = [json.loads(line) for line in f]

# We can inspect the data quickly by checking the number of examples and the first item

# Initial dataset stats
print("Num examples:", len(dataset))
print("First example:")
for message in dataset[0]["messages"]:
    print(message)

# Now that we have a sense of the data, we need to go through all the different examples and check to make sure the formatting is correct and matches the Chat completions message structure

# Format error checks
format_errors = defaultdict(int)

for ex in dataset:
    if not isinstance(ex, dict):
        format_errors["data_type"] += 1
        continue

    messages = ex.get("messages", None)
    if not messages:
        format_errors["missing_messages_list"] += 1
        continue

    for message in messages:
        if "role" not in message or "content" not in message:
            format_errors["message_missing_key"] += 1

        if any(k not in ("role", "content", "name") for k in message):
            format_errors["message_unrecognized_key"] += 1

        if message.get("role", None) not in ("system", "user", "assistant"):
            format_errors["unrecognized_role"] += 1

        content = message.get("content", None)
        if not content or not isinstance(content, str):
            format_errors["missing_content"] += 1

    if not any(message.get("role", None) == "assistant" for message in messages):
        format_errors["example_missing_assistant_message"] += 1

if format_errors:
    print("Found errors:")
    for k, v in format_errors.items():
        print(f"{k}: {v}")
else:
    print("No errors found")

# Beyond the structure of the message, we also need to ensure that the length does not exceed the 4096 token limit.

# Token counting functions
encoding = tiktoken.get_encoding("cl100k_base")

# not exact!
# simplified from https://github.com/openai/openai-cookbook/blob/main/examples/How_to_count_tokens_with_tiktoken.ipynb
def num_tokens_from_messages(messages, tokens_per_message=3, tokens_per_name=1):
    num_tokens = 0
    for message in messages:
        num_tokens += tokens_per_message
        for key, value in message.items():
            num_tokens += len(encoding.encode(value))
            if key == "name":
                num_tokens += tokens_per_name
    num_tokens += 3
    return num_tokens

def num_assistant_tokens_from_messages(messages):
    num_tokens = 0
    for message in messages:
        if message["role"] == "assistant":
            num_tokens += len(encoding.encode(message["content"]))
    return num_tokens

def print_distribution(values, name):
    print(f"\n#### Distribution of {name}:")
    print(f"min / max: {min(values)}, {max(values)}")
    print(f"mean / median: {np.mean(values)}, {np.median(values)}")
    print(f"p5 / p95: {np.quantile(values, 0.1)}, {np.quantile(values, 0.9)}")

# Last, we can look at the results of the different formatting operations before proceeding with creating a fine-tuning job:

# Warnings and tokens counts
n_missing_system = 0
n_missing_user = 0
n_messages = []
convo_lens = []
assistant_message_lens = []

for ex in dataset:
    messages = ex["messages"]
    if not any(message["role"] == "system" for message in messages):
        n_missing_system += 1
    if not any(message["role"] == "user" for message in messages):
        n_missing_user += 1
    n_messages.append(len(messages))
    convo_lens.append(num_tokens_from_messages(messages))
    assistant_message_lens.append(num_assistant_tokens_from_messages(messages))

print("Num examples missing system message:", n_missing_system)
print("Num examples missing user message:", n_missing_user)
print_distribution(n_messages, "num_messages_per_example")
print_distribution(convo_lens, "num_total_tokens_per_example")
print_distribution(assistant_message_lens, "num_assistant_tokens_per_example")
n_too_long = sum(l > 4096 for l in convo_lens)
print(f"\n{n_too_long} examples may be over the 4096 token limit, they will be truncated during fine-tuning")

# Pricing and default n_epochs estimate
MAX_TOKENS_PER_EXAMPLE = 4096

MIN_TARGET_EXAMPLES = 100
MAX_TARGET_EXAMPLES = 25000
TARGET_EPOCHS = 3
MIN_EPOCHS = 1
MAX_EPOCHS = 25

n_epochs = TARGET_EPOCHS
n_train_examples = len(dataset)
if n_train_examples * TARGET_EPOCHS < MIN_TARGET_EXAMPLES:
    n_epochs = min(MAX_EPOCHS, MIN_TARGET_EXAMPLES // n_train_examples)
elif n_train_examples * TARGET_EPOCHS > MAX_TARGET_EXAMPLES:
    n_epochs = max(MIN_EPOCHS, MAX_TARGET_EXAMPLES // n_train_examples)

n_billing_tokens_in_dataset = sum(min(MAX_TOKENS_PER_EXAMPLE, length) for length in convo_lens)
print(f"Dataset has ~{n_billing_tokens_in_dataset} tokens that will be charged for during training")
print(f"By default, you'll train for {n_epochs} epochs on this dataset")
print(f"By default, you'll be charged for ~{n_epochs * n_billing_tokens_in_dataset} tokens")
print("See pricing page to estimate total costs")

Num examples: 430
First example:
{'role': 'system', 'content': 'あなたは、つくよみちゃんです。'}
{'role': 'user', 'content': 'お腹が鳴る'}
{'role': 'assistant', 'content': '何か召し上がりますか？'}
No errors found
Num examples missing system message: 0
Num examples missing user message: 0

#### Distribution of num_messages_per_example:
min / max: 3, 3
mean / median: 3.0, 3.0
p5 / p95: 3.0, 3.0

#### Distribution of num_total_tokens_per_example:
min / max: 36, 130
mean / median: 70.07674418604651, 68.0
p5 / p95: 48.0, 95.0

#### Distribution of num_assistant_tokens_per_example:
min / max: 3, 71
mean / median: 27.946511627906975, 26.0
p5 / p95: 9.900000000000006, 52.0

0 examples may be over the 4096 token limit, they will be truncated during fine-tuning
Dataset has ~30133 tokens that will be charged for during training
By default, you'll train for 3 epochs on this dataset
By default, you'll be charged for ~90399 tokens
See pricing page to estimate total costs

import openai

# 学習データのアップロード
openai.File.create(
    file=open("tsukuyomi.jsonl", "rb"),
    purpose="fine-tune"
)

<File file id=file-XXXXXXXXXXXXXXXXXXXXXXXX at 0x7ea2aeb29e40> JSON: {
  "object": "file",
  "id": "file-XXXXXXXXXXXXXXXXXXXXXXXX",
  "purpose": "fine-tune",
  "filename": "file",
  "bytes": 121790,
  "created_at": 1692777470,
  "status": "uploaded",
  "status_details": null
}

import openai

# OpenAI APIキーの準備
openai.api_key = "<OpenAI_APIのAPIキー>"

import os

# ファインチューニングの実行
openai.FineTuningJob.create(
    training_file="file-XXXXXXXXXXXXXXXXXXXXXXXX", 
    model="gpt-3.5-turbo"
)

<FineTuningJob fine_tuning.job id=ftjob-XXXXXXXXXXXXXXXXXXXXXXXX at 0x7ea2ae8ce840> JSON: {
  "object": "fine_tuning.job",
  "id": "ftjob-XXXXXXXXXXXXXXXXXXXXXXXX",
  "model": "gpt-3.5-turbo-0613",
  "created_at": 1692777596,
  "finished_at": null,
  "fine_tuned_model": null,
  "organization_id": "org-XXXXXXXXXXXXXXXXXXXXXXXX",
  "result_files": [],
  "status": "created",
  "validation_file": null,
  "training_file": "file-XXXXXXXXXXXXXXXXXXXXXXXX",
  "hyperparameters": {
    "n_epochs": 3
  },
  "trained_tokens": null
}

import os

# 推論の実行
completion = openai.ChatCompletion.create(
    model="ft:gpt-3.5-turbo-0613:personal::XXXXXXXX",
    messages=[
        {"role": "system", "content": "あなたは、つくよみちゃんです。"},
        {"role": "user", "content": "好きな食べ物は？"}
    ]
)
print(completion.choices[0].message["content"])

絵に描いた餅です！