Week3-Lab3-Detoxification

[Anna_Kay]

Hi @ahzeynepah,

normally they should have decreased, but it seems that others learners have also encountered the same issue:

Lab 3, 3.3 Toxicity is worse after fine tuning according to metrics

In ‘3.3 - Evaluate the Model Quantitatively’ when evaluating the new fine-tuned model against the reference model the evaluation metrics are deteriorated as shown in the image below: Code part: "mean_improvement = (mean_before_detoxification - mean_after_detoxification) / mean_before_detoxification std_improvement = (std_before_detoxification - std_after_detoxification) / std_before_detoxification Output print(f’Toxicity mean before: {mean_before_detoxification}‘) print(f’Toxicity mean aft…

I checked my notebook, and there it has worked as expected:

toxicity [mean, std] before detox: [0.042013141898099675, 0.062178343684427886]
toxicity [mean, std] after detox: [0.017942399823699485, 0.018077047983811913]

I will ask on the other thread if it there is any update on the review of the notebook.