OPENAI API 微调 GPT-3 的 Ada 模型

https://platform.openai.com/account/usage 

https://openai.com/pricing 

from sklearn.datasets import fetch_20newsgroups
import pandas as pd
import openai
categories = ['rec.sport.baseball', 'rec.sport.hockey']
sports_dataset = fetch_20newsgroups(subset='train', shuffle=True, random_state=42, categories=categories)
len_all, len_baseball, len_hockey = len(sports_dataset.data), len([e for e in sports_dataset.target if e == 0]), len([e for e in sports_dataset.target if e == 1])
print(f"Total examples: {len_all}, Baseball examples: {len_baseball}, Hockey examples: {len_hockey}")

Total examples: 1197, Baseball examples: 597, Hockey examples: 600

labels = [sports_dataset.target_names[x].split('.')[-1] for x in sports_dataset['target']]
texts = [text.strip() for text in sports_dataset['data']]
df = pd.DataFrame(zip(texts, labels), columns = ['prompt','completion']) 
df = df[:100]

df.to_json("sport2.jsonl", orient='records', lines=True)
!openai tools fine_tunes.prepare_data -f sport2.jsonl -q

!openai api fine_tunes.create -t "sport2_prepared_train.jsonl" -v "sport2_prepared_valid.jsonl" --compute_classification_metrics --classification_positive_class " baseball" -m ada

Uploaded file from sport2_prepared_train.jsonl: file-wx9c3lYQB6Z4pWrrCqBabWUh
Uploaded file from sport2_prepared_valid.jsonl: file-aujZlpbhXZnevKzJNjF06q85
Created fine-tune: ft-aEHXhd8q9dfG8MOKt43ph7wk
Streaming events until fine-tuning is complete...
[2023-03-28 09:57:12] Created fine-tune: ft-aEHXhd8q9dfG8MOKt43ph7wk
[2023-03-28 09:59:16] Fine-tune costs $0.06
[2023-03-28 09:59:16] Fine-tune enqueued. Queue number: 2
[2023-03-28 09:59:32] Fine-tune is in the queue. Queue number: 1
(Ctrl-C will interrupt the stream, but not cancel the fine-tune)
[2023-03-28 09:57:12] Created fine-tune: ft-aEHXhd8q9dfG8MOKt43ph7wk
Stream interrupted (client disconnected).
To resume the stream, run:
  openai api fine_tunes.follow -i ft-aEHXhd8q9dfG8MOKt43ph7wk

!openai api fine_tunes.results -i ft-aEHXhd8q9dfG8MOKt43ph7wk > result.csv
results = pd.read_csv('result.csv')
results[results['classification/accuracy'].notnull()].tail(1)

	step	elapsed_tokens	elapsed_examples	training_loss	training_sequence_accuracy	training_token_accuracy	validation_loss	validation_sequence_accuracy	validation_token_accuracy	classification/accuracy	classification/precision	classification/recall	classification/auroc	classification/auprc	classification/f1.0
316	317	143557	317	0.02417	1.0	1.0	NaN	NaN	NaN	1.0	1.0	1.0	1.0	1.0	1.0

test = pd.read_json('sport2_prepared_valid.jsonl', lines=True)
res = openai.Completion.create(model= 'ada:ft-personal-2023-03-28-02-15-26', prompt=test['prompt'][0] + '\n\n###\n\n', max_tokens=1, temperature=0)
res['choices'][0]['text']

' hockey'

sample_hockey_tweet = """Thank you to the 
@Canes
 and all you amazing Caniacs that have been so supportive! You guys are some of the best fans in the NHL without a doubt! Really excited to start this new chapter in my career with the 
@DetroitRedWings
 !!"""
res = openai.Completion.create(model='ada:ft-personal-2023-03-28-02-15-26', prompt=sample_hockey_tweet + '\n\n###\n\n', max_tokens=1, temperature=0, logprobs=2)
res['choices'][0]['text']