使用GPT-3训练垃圾短信分类器示例详解

pip install --upgrade openai

export OPENAI_API_KEY="<填你的openai密钥>" // linux系统 
set OPENAI_API_KEY="<填你的openai密钥>" // windows系统

{"prompt": "输入的提示", "completion": "输出的结果"}
...

{"prompt":"sms: 今天上午可以安装吗老板 ->", "completion":" 正常短信"}
……

openai tools fine_tunes.prepare_data -f <样本文件地址>
openai tools fine_tunes.prepare_data -f sms_classifier/sms_sample_500_converted.csv

openai tools fine_tunes.prepare_data -f sms_classifier/sms_sample_500_converted.csv

(venv) D:\dev2023\openai-tutorial>openai tools fine_tunes.prepare_data -f sms_classifier/sms_sample_500_converted.csv
Analyzing...
- Based on your file extension, your file is formatted as a CSV file
- Your file contains 441 prompt-completion pairs
- Based on your data it seems like you're trying to fine-tune a model for classification
- For classification, we recommend you try one of the faster and cheaper models, such as `ada`
- For classification, you can estimate the expected model performance by keeping a held out dataset, which is not used for training
- All prompts end with suffix ` ##`
- All prompts start with prefix `sms: `
- The completion should start with a whitespace character (` `). This tends to produce better results due to the tokenization we use. See https://beta.openai.com/docs/guides/fine-tuning/preparing-your-dataset for 
more details
Based on the analysis we will perform the following actions:
- [Necessary] Your format `CSV` will be converted to `JSONL`
- [Recommended] Add a whitespace character to the beginning of the completion [Y/n]: y
- [Recommended] Would you like to split into training and validation set? [Y/n]: y
Your data will be written to a new JSONL file. Proceed [Y/n]: y
Wrote modified files to `sms_classifier/sms_sample_500_converted_prepared_train.jsonl` and `sms_classifier/sms_sample_500_converted_prepared_valid.jsonl`
Feel free to take a look!
Now use that file when fine-tuning:
> openai api fine_tunes.create -t "sms_classifier/sms_sample_500_converted_prepared_train.jsonl" -v "sms_classifier/sms_sample_500_converted_prepared_valid.jsonl" --compute_classification_metrics --classification_n_classes 4
After you've fine-tuned a model, remember that your prompt has to end with the indicator string ` ##` for the model to start generating completions, rather than continuing with the prompt.
Once your model starts training, it'll approximately take 12.92 minutes to train a `curie` model, and less for `ada` and `babbage`. Queue will approximately take half an hour per job ahead of you.

(venv) D:\dev2023\openai-tutorial>openai api fine_tunes.create -m ada --suffix "sms_classifier" -t "sms_classifier/sms_sample_500_converted_prepared_train.jsonl" -v "sms_classifier/sms_sample_500_converted_prepared_valid.jsonl" --compute_classification_metrics --classification_n_classes 4
Upload progress: 100%|██████████████████████████████████████████| 97.6k/97.6k [00:00<00:00, 95.8Mit/s]
Uploaded file from sms_classifier/sms_sample_500_converted_prepared_train.jsonl: file-HQgXiRZBxwn7In0sUax1WVdj
Upload progress: 100%|██████████████████████████████████████████| 24.3k/24.3k [00:00<?, ?it/s]
Uploaded file from sms_classifier/sms_sample_500_converted_prepared_valid.jsonl: file-gtmsXSjMpmdFowRQ8Hn0FxbX
Created fine-tune: ft-tEt9Oo95zgJ42KJvP4nS8nee
Streaming events until fine-tuning is complete...
(Ctrl-C will interrupt the stream, but not cancel the fine-tune)
[2023-02-14 11:56:00] Created fine-tune: ft-tEt9Oo95zgJ42KJvP4nS8nee

openai api fine_tunes.follow -i <任务ID>

(venv) D:\dev2023\openai-tutorial>openai api fine_tunes.follow -i ft-wHXGw263e8ujLaDHNQGqYB6K
[2023-02-14 13:36:56] Created fine-tune: ft-wHXGw263e8ujLaDHNQGqYB6K
[2023-02-14 13:44:57] Fine-tune costs $0.10
[2023-02-14 13:44:58] Fine-tune enqueued. Queue number: 1
[2023-02-14 13:44:58] Fine-tune is in the queue. Queue number: 0
[2023-02-14 13:45:01] Fine-tune started
[2023-02-14 13:46:10] Completed epoch 1/4
[2023-02-14 13:47:07] Completed epoch 2/4
[2023-02-14 13:48:03] Completed epoch 3/4
[2023-02-14 13:48:59] Completed epoch 4/4
[2023-02-14 13:49:24] Uploaded model: ada:ft-personal:sms-classifier-2023-02-14-05-49-24
[2023-02-14 13:49:25] Uploaded result file: file-SaX4z4avlLH8KXDFM3UyNFoU
[2023-02-14 13:49:25] Fine-tune succeeded
Job complete! Status: succeeded ?
Try out your fine-tuned model:
openai api completions.create -m ada:ft-personal:sms-classifier-2023-02-14-05-49-24 -p <YOUR_PROMPT>

(venv) D:\dev2023\openai-tutorial>openai api completions.create -m ada:ft-personal:sms-classifier-2023-02-14-05-49-24 -p "sms: 你在哪里###" -M 1
sms: 你在哪里### 1
(venv) D:\dev2023\openai-tutorial>openai api completions.create -m ada:ft-personal:sms-classifier-2023-02-14-05-49-24 -p "sms: 【京东】邀您参与调研，有机会得800京豆，点 3.cn/1EgRyx-J 回复TD8退订###" -M 1          
sms: 【京东】邀您参与调研，有机会得800京豆，点 3.cn/1EgRyx-J 回复TD8退订### 4

import openai
def model_predict(sms):
    response = openai.Completion.create(
        # 指定要使用的模型：这里使用的是我们训练好的模型
        model="ada:ft-personal:sms-classifier-2023-02-14-05-49-24",
        prompt="""sms: {sms}###""".format(sms=sms),
        temperature=0.6,
        max_tokens=1,
    )
    return response
if __name__ == '__main__':
    sms = "【腾讯云】尊敬的用户，您好，我是腾讯云技术顾问。您（账号ID: 123*****"
    category = {"1": "短信", "2": "通知短信", "3": "公益告短信", "4": " 垃圾短信"}
    response = model_predict(sms)
    print("判断结果：", category[response.choices[0].text])

(venv) D:\dev2023\openai-tutorial>python sms_classifier/test.py  
判断结果：通知短信

-m curie: ft-< org >-< date >

openai api fine_tunes.create -m ada --suffix "sms_classifier" -t "sms_classifier/sms_sample_500_converted_prepared_train.jsonl" -v "sms_classifier/sms_sample_500_converted_prepared_valid.jsonl" --compute_classification_metrics --classification_n_classes 4 -m ada:ft-personal:sms-classifier-2023-02-14-05-49-24