French ChatGPT detection model from Towards a Robust Detection of Language Model-Generated Text: Is ChatGPT that easy to detect?
This model is a fine-tuned version of almanach/camemberta-base on the HC3 FULL_FR_1.0_0.5_0.5 dataset with noise added. It achieves the following results on the
- Loss: 0.0430
- F1: 0.9791
- F1: 0.97
- F1: 0.45
This a model trained to detect text created by ChatGPT in French.
The training data is the
hc3_fr_full subset of almanach/hc3_multi, but with added misspelling and homoglyph attacks.
This model is for research purposes only. It is not intended to be used in production as we said in our paper:
We would like to emphasize that our study does not claim to have produced an universally accurate detector. Our strong results are based on in-domain testing and, unsurprisingly, do not generalize in out-of-domain scenarios. This is even more so when used on text specifically designed to fool language model detectors and on text intentionally stylistically similar to ChatGPT-generated text, especially instructional text.
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 25
- gradient_accumulation_steps: 4
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 5.0
- mixed_precision_training: Native AMP
|Training Loss||Epoch||Step||Validation Loss||F1|
- Transformers 4.26.1
- Pytorch 1.11.0+cu115
- Datasets 2.8.0
- Tokenizers 0.13.2
- Downloads last month