Quantifying the Carbon Emissions of Machine Learning
Paper
•
1910.09700
•
Published
•
23
Convert natural language queries into SQL.
A text-to-sql LoRA adapter for m5-small finetuned on the b-mc2/sql-create-context, Clinton/Text-to-sql-v1, and knowrohit07/know_sql datasets.
Train-Eval-Test split: 8:1:1
'rouge1': 0.9281907395888822, 'rouge2': 0.8917983416395394, 'rougeL': 0.9182615264948171, 'rougeLsum': 0.9191261027066355
This adapter helps m5-small achieve a ROUGE score of over 90% on text to SQL tasks.
Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).
Hardware Type: RTX 4000
Hours used: 2
Cloud Provider: Paperspace
PEFT 0.6.2
Base model
google-t5/t5-small