HW1 HC3 Detector
This is my fine-tuned model for Homework 1.
The model classifies HC3 answers as:
- 0: human
- 1: ChatGPT
Base model:
sentence-transformers/all-MiniLM-L6-v2
Results:
- Baseline accuracy: 0.8449
- Fine-tuned test accuracy: 0.9914
Training settings:
- learning rate: 2e-5
- epochs: 5
- batch size: 32
- max length: 256
I used the fixed dataset splits provided in the notebook.
- Downloads last month
- 30