| [2026-07-08 22:23:15,550][model][INFO] - Setting pad_token as eos token: <|end_of_text|> |
| [2026-07-08 22:24:15,064][trainer][INFO] - GradDiff Trainer loaded, output_dir: ./saves/unlearn/multilingual/Llama-3.1-8B/books.all/chapters.all/GradDiff.KL/de |
| [2026-07-08 23:51:00,315][lm_eval.models.huggingface][WARNING] - `pretrained` model kwarg is not of type `str`. Many other model arguments may be ignored. Please do not launch via accelerate or use `parallelize=True` if passing an existing model this way. |
| [2026-07-08 23:51:02,471][lm_eval.models.huggingface][WARNING] - Passed an already-initialized model through `pretrained`, assuming single-process call to evaluate() or custom distributed integration |
| [2026-07-08 23:51:02,473][lm_eval.evaluator][INFO] - Setting random seed to 0 | Setting numpy seed to 1234 | Setting torch manual seed to 1234 | Setting fewshot manual seed to 1234 |
| [2026-07-08 23:51:02,474][lm_eval.evaluator][INFO] - Using pre-initialized model |
| [2026-07-08 23:52:46,722][lm_eval.evaluator_utils][INFO] - Selected tasks: |
| [2026-07-08 23:52:46,724][lm_eval.evaluator_utils][INFO] - Group: mmlu |
| [2026-07-08 23:52:46,724][lm_eval.evaluator_utils][INFO] - Group: mmlu_stem |
| [2026-07-08 23:52:46,725][lm_eval.evaluator_utils][INFO] - Task: mmlu_abstract_algebra (mmlu/default/mmlu_abstract_algebra.yaml) |
| [2026-07-08 23:52:46,725][lm_eval.evaluator_utils][INFO] - Task: mmlu_anatomy (mmlu/default/mmlu_anatomy.yaml) |
| [2026-07-08 23:52:46,726][lm_eval.evaluator_utils][INFO] - Task: mmlu_astronomy (mmlu/default/mmlu_astronomy.yaml) |
| [2026-07-08 23:52:46,726][lm_eval.evaluator_utils][INFO] - Task: mmlu_college_biology (mmlu/default/mmlu_college_biology.yaml) |
| [2026-07-08 23:52:46,726][lm_eval.evaluator_utils][INFO] - Task: mmlu_college_chemistry (mmlu/default/mmlu_college_chemistry.yaml) |
| [2026-07-08 23:52:46,727][lm_eval.evaluator_utils][INFO] - Task: mmlu_college_computer_science (mmlu/default/mmlu_college_computer_science.yaml) |
| [2026-07-08 23:52:46,727][lm_eval.evaluator_utils][INFO] - Task: mmlu_college_mathematics (mmlu/default/mmlu_college_mathematics.yaml) |
| [2026-07-08 23:52:46,727][lm_eval.evaluator_utils][INFO] - Task: mmlu_college_physics (mmlu/default/mmlu_college_physics.yaml) |
| [2026-07-08 23:52:46,728][lm_eval.evaluator_utils][INFO] - Task: mmlu_computer_security (mmlu/default/mmlu_computer_security.yaml) |
| [2026-07-08 23:52:46,728][lm_eval.evaluator_utils][INFO] - Task: mmlu_conceptual_physics (mmlu/default/mmlu_conceptual_physics.yaml) |
| [2026-07-08 23:52:46,728][lm_eval.evaluator_utils][INFO] - Task: mmlu_electrical_engineering (mmlu/default/mmlu_electrical_engineering.yaml) |
| [2026-07-08 23:52:46,729][lm_eval.evaluator_utils][INFO] - Task: mmlu_elementary_mathematics (mmlu/default/mmlu_elementary_mathematics.yaml) |
| [2026-07-08 23:52:46,729][lm_eval.evaluator_utils][INFO] - Task: mmlu_high_school_biology (mmlu/default/mmlu_high_school_biology.yaml) |
| [2026-07-08 23:52:46,730][lm_eval.evaluator_utils][INFO] - Task: mmlu_high_school_chemistry (mmlu/default/mmlu_high_school_chemistry.yaml) |
| [2026-07-08 23:52:46,730][lm_eval.evaluator_utils][INFO] - Task: mmlu_high_school_computer_science (mmlu/default/mmlu_high_school_computer_science.yaml) |
| [2026-07-08 23:52:46,731][lm_eval.evaluator_utils][INFO] - Task: mmlu_high_school_mathematics (mmlu/default/mmlu_high_school_mathematics.yaml) |
| [2026-07-08 23:52:46,731][lm_eval.evaluator_utils][INFO] - Task: mmlu_high_school_physics (mmlu/default/mmlu_high_school_physics.yaml) |
| [2026-07-08 23:52:46,731][lm_eval.evaluator_utils][INFO] - Task: mmlu_high_school_statistics (mmlu/default/mmlu_high_school_statistics.yaml) |
| [2026-07-08 23:52:46,732][lm_eval.evaluator_utils][INFO] - Task: mmlu_machine_learning (mmlu/default/mmlu_machine_learning.yaml) |
| [2026-07-08 23:52:46,732][lm_eval.evaluator_utils][INFO] - Group: mmlu_other |
| [2026-07-08 23:52:46,732][lm_eval.evaluator_utils][INFO] - Task: mmlu_business_ethics (mmlu/default/mmlu_business_ethics.yaml) |
| [2026-07-08 23:52:46,732][lm_eval.evaluator_utils][INFO] - Task: mmlu_clinical_knowledge (mmlu/default/mmlu_clinical_knowledge.yaml) |
| [2026-07-08 23:52:46,733][lm_eval.evaluator_utils][INFO] - Task: mmlu_college_medicine (mmlu/default/mmlu_college_medicine.yaml) |
| [2026-07-08 23:52:46,733][lm_eval.evaluator_utils][INFO] - Task: mmlu_global_facts (mmlu/default/mmlu_global_facts.yaml) |
| [2026-07-08 23:52:46,734][lm_eval.evaluator_utils][INFO] - Task: mmlu_human_aging (mmlu/default/mmlu_human_aging.yaml) |
| [2026-07-08 23:52:46,734][lm_eval.evaluator_utils][INFO] - Task: mmlu_management (mmlu/default/mmlu_management.yaml) |
| [2026-07-08 23:52:46,735][lm_eval.evaluator_utils][INFO] - Task: mmlu_marketing (mmlu/default/mmlu_marketing.yaml) |
| [2026-07-08 23:52:46,735][lm_eval.evaluator_utils][INFO] - Task: mmlu_medical_genetics (mmlu/default/mmlu_medical_genetics.yaml) |
| [2026-07-08 23:52:46,736][lm_eval.evaluator_utils][INFO] - Task: mmlu_miscellaneous (mmlu/default/mmlu_miscellaneous.yaml) |
| [2026-07-08 23:52:46,736][lm_eval.evaluator_utils][INFO] - Task: mmlu_nutrition (mmlu/default/mmlu_nutrition.yaml) |
| [2026-07-08 23:52:46,736][lm_eval.evaluator_utils][INFO] - Task: mmlu_professional_accounting (mmlu/default/mmlu_professional_accounting.yaml) |
| [2026-07-08 23:52:46,736][lm_eval.evaluator_utils][INFO] - Task: mmlu_professional_medicine (mmlu/default/mmlu_professional_medicine.yaml) |
| [2026-07-08 23:52:46,737][lm_eval.evaluator_utils][INFO] - Task: mmlu_virology (mmlu/default/mmlu_virology.yaml) |
| [2026-07-08 23:52:46,737][lm_eval.evaluator_utils][INFO] - Group: mmlu_social_sciences |
| [2026-07-08 23:52:46,737][lm_eval.evaluator_utils][INFO] - Task: mmlu_econometrics (mmlu/default/mmlu_econometrics.yaml) |
| [2026-07-08 23:52:46,738][lm_eval.evaluator_utils][INFO] - Task: mmlu_high_school_geography (mmlu/default/mmlu_high_school_geography.yaml) |
| [2026-07-08 23:52:46,738][lm_eval.evaluator_utils][INFO] - Task: mmlu_high_school_government_and_politics (mmlu/default/mmlu_high_school_government_and_politics.yaml) |
| [2026-07-08 23:52:46,738][lm_eval.evaluator_utils][INFO] - Task: mmlu_high_school_macroeconomics (mmlu/default/mmlu_high_school_macroeconomics.yaml) |
| [2026-07-08 23:52:46,739][lm_eval.evaluator_utils][INFO] - Task: mmlu_high_school_microeconomics (mmlu/default/mmlu_high_school_microeconomics.yaml) |
| [2026-07-08 23:52:46,739][lm_eval.evaluator_utils][INFO] - Task: mmlu_high_school_psychology (mmlu/default/mmlu_high_school_psychology.yaml) |
| [2026-07-08 23:52:46,740][lm_eval.evaluator_utils][INFO] - Task: mmlu_human_sexuality (mmlu/default/mmlu_human_sexuality.yaml) |
| [2026-07-08 23:52:46,741][lm_eval.evaluator_utils][INFO] - Task: mmlu_professional_psychology (mmlu/default/mmlu_professional_psychology.yaml) |
| [2026-07-08 23:52:46,741][lm_eval.evaluator_utils][INFO] - Task: mmlu_public_relations (mmlu/default/mmlu_public_relations.yaml) |
| [2026-07-08 23:52:46,741][lm_eval.evaluator_utils][INFO] - Task: mmlu_security_studies (mmlu/default/mmlu_security_studies.yaml) |
| [2026-07-08 23:52:46,742][lm_eval.evaluator_utils][INFO] - Task: mmlu_sociology (mmlu/default/mmlu_sociology.yaml) |
| [2026-07-08 23:52:46,742][lm_eval.evaluator_utils][INFO] - Task: mmlu_us_foreign_policy (mmlu/default/mmlu_us_foreign_policy.yaml) |
| [2026-07-08 23:52:46,742][lm_eval.evaluator_utils][INFO] - Group: mmlu_humanities |
| [2026-07-08 23:52:46,742][lm_eval.evaluator_utils][INFO] - Task: mmlu_formal_logic (mmlu/default/mmlu_formal_logic.yaml) |
| [2026-07-08 23:52:46,743][lm_eval.evaluator_utils][INFO] - Task: mmlu_high_school_european_history (mmlu/default/mmlu_high_school_european_history.yaml) |
| [2026-07-08 23:52:46,743][lm_eval.evaluator_utils][INFO] - Task: mmlu_high_school_us_history (mmlu/default/mmlu_high_school_us_history.yaml) |
| [2026-07-08 23:52:46,743][lm_eval.evaluator_utils][INFO] - Task: mmlu_high_school_world_history (mmlu/default/mmlu_high_school_world_history.yaml) |
| [2026-07-08 23:52:46,744][lm_eval.evaluator_utils][INFO] - Task: mmlu_international_law (mmlu/default/mmlu_international_law.yaml) |
| [2026-07-08 23:52:46,744][lm_eval.evaluator_utils][INFO] - Task: mmlu_jurisprudence (mmlu/default/mmlu_jurisprudence.yaml) |
| [2026-07-08 23:52:46,744][lm_eval.evaluator_utils][INFO] - Task: mmlu_logical_fallacies (mmlu/default/mmlu_logical_fallacies.yaml) |
| [2026-07-08 23:52:46,745][lm_eval.evaluator_utils][INFO] - Task: mmlu_moral_disputes (mmlu/default/mmlu_moral_disputes.yaml) |
| [2026-07-08 23:52:46,745][lm_eval.evaluator_utils][INFO] - Task: mmlu_moral_scenarios (mmlu/default/mmlu_moral_scenarios.yaml) |
| [2026-07-08 23:52:46,745][lm_eval.evaluator_utils][INFO] - Task: mmlu_philosophy (mmlu/default/mmlu_philosophy.yaml) |
| [2026-07-08 23:52:46,745][lm_eval.evaluator_utils][INFO] - Task: mmlu_prehistory (mmlu/default/mmlu_prehistory.yaml) |
| [2026-07-08 23:52:46,746][lm_eval.evaluator_utils][INFO] - Task: mmlu_professional_law (mmlu/default/mmlu_professional_law.yaml) |
| [2026-07-08 23:52:46,746][lm_eval.evaluator_utils][INFO] - Task: mmlu_world_religions (mmlu/default/mmlu_world_religions.yaml) |
| [2026-07-08 23:52:46,746][lm_eval.evaluator_utils][INFO] - Group: multilingual_unlearning |
| [2026-07-08 23:52:46,747][lm_eval.evaluator_utils][INFO] - Task: multilingual_unlearning_harry_potter_en (multilingual_unlearning/multilingual_unlearning_harry_potter_en.yaml) |
| [2026-07-08 23:52:46,747][lm_eval.evaluator_utils][INFO] - Task: multilingual_unlearning_harry_potter_fr (multilingual_unlearning/multilingual_unlearning_harry_potter_fr.yaml) |
| [2026-07-08 23:52:46,747][lm_eval.evaluator_utils][INFO] - Task: multilingual_unlearning_harry_potter_ja (multilingual_unlearning/multilingual_unlearning_harry_potter_ja.yaml) |
| [2026-07-08 23:52:46,748][lm_eval.evaluator_utils][INFO] - Task: multilingual_unlearning_harry_potter_vi (multilingual_unlearning/multilingual_unlearning_harry_potter_vi.yaml) |
| [2026-07-08 23:52:46,748][lm_eval.evaluator_utils][INFO] - Task: multilingual_unlearning_harry_potter_zh (multilingual_unlearning/multilingual_unlearning_harry_potter_zh.yaml) |
| [2026-07-08 23:52:46,749][lm_eval.evaluator_utils][INFO] - Task: multilingual_unlearning_harry_potter_ko (multilingual_unlearning/multilingual_unlearning_harry_potter_ko.yaml) |
| [2026-07-08 23:52:46,749][lm_eval.evaluator_utils][INFO] - Task: multilingual_unlearning_harry_potter_es (multilingual_unlearning/multilingual_unlearning_harry_potter_es.yaml) |
| [2026-07-08 23:52:46,750][lm_eval.evaluator_utils][INFO] - Task: multilingual_unlearning_harry_potter_de (multilingual_unlearning/multilingual_unlearning_harry_potter_de.yaml) |
| [2026-07-08 23:52:46,750][lm_eval.evaluator_utils][INFO] - Task: multilingual_unlearning_harry_potter_th (multilingual_unlearning/multilingual_unlearning_harry_potter_th.yaml) |
| [2026-07-08 23:52:46,753][lm_eval.api.task][INFO] - Building contexts for multilingual_unlearning_harry_potter_en on rank 0... |
| [2026-07-08 23:52:54,082][lm_eval.api.task][INFO] - Building contexts for multilingual_unlearning_harry_potter_fr on rank 0... |
| [2026-07-08 23:53:00,226][lm_eval.api.task][INFO] - Building contexts for multilingual_unlearning_harry_potter_ja on rank 0... |
| [2026-07-08 23:53:06,809][lm_eval.api.task][INFO] - Building contexts for multilingual_unlearning_harry_potter_vi on rank 0... |
| [2026-07-08 23:53:13,011][lm_eval.api.task][INFO] - Building contexts for multilingual_unlearning_harry_potter_zh on rank 0... |
| [2026-07-08 23:53:19,202][lm_eval.api.task][INFO] - Building contexts for multilingual_unlearning_harry_potter_ko on rank 0... |
| [2026-07-08 23:53:25,749][lm_eval.api.task][INFO] - Building contexts for multilingual_unlearning_harry_potter_es on rank 0... |
| [2026-07-08 23:53:32,314][lm_eval.api.task][INFO] - Building contexts for multilingual_unlearning_harry_potter_de on rank 0... |
| [2026-07-08 23:53:38,449][lm_eval.api.task][INFO] - Building contexts for multilingual_unlearning_harry_potter_th on rank 0... |
| [2026-07-08 23:53:45,201][lm_eval.api.task][INFO] - Building contexts for mmlu_abstract_algebra on rank 0... |
| [2026-07-08 23:53:45,307][lm_eval.api.task][INFO] - Building contexts for mmlu_anatomy on rank 0... |
| [2026-07-08 23:53:45,452][lm_eval.api.task][INFO] - Building contexts for mmlu_astronomy on rank 0... |
| [2026-07-08 23:53:45,615][lm_eval.api.task][INFO] - Building contexts for mmlu_college_biology on rank 0... |
| [2026-07-08 23:53:45,769][lm_eval.api.task][INFO] - Building contexts for mmlu_college_chemistry on rank 0... |
| [2026-07-08 23:53:45,878][lm_eval.api.task][INFO] - Building contexts for mmlu_college_computer_science on rank 0... |
| [2026-07-08 23:53:45,985][lm_eval.api.task][INFO] - Building contexts for mmlu_college_mathematics on rank 0... |
| [2026-07-08 23:53:46,091][lm_eval.api.task][INFO] - Building contexts for mmlu_college_physics on rank 0... |
| [2026-07-08 23:53:46,200][lm_eval.api.task][INFO] - Building contexts for mmlu_computer_security on rank 0... |
| [2026-07-08 23:53:46,306][lm_eval.api.task][INFO] - Building contexts for mmlu_conceptual_physics on rank 0... |
| [2026-07-08 23:53:46,556][lm_eval.api.task][INFO] - Building contexts for mmlu_electrical_engineering on rank 0... |
| [2026-07-08 23:53:46,708][lm_eval.api.task][INFO] - Building contexts for mmlu_elementary_mathematics on rank 0... |
| [2026-07-08 23:53:47,100][lm_eval.api.task][INFO] - Building contexts for mmlu_high_school_biology on rank 0... |
| [2026-07-08 23:53:47,422][lm_eval.api.task][INFO] - Building contexts for mmlu_high_school_chemistry on rank 0... |
| [2026-07-08 23:53:47,638][lm_eval.api.task][INFO] - Building contexts for mmlu_high_school_computer_science on rank 0... |
| [2026-07-08 23:53:47,745][lm_eval.api.task][INFO] - Building contexts for mmlu_high_school_mathematics on rank 0... |
| [2026-07-08 23:53:48,026][lm_eval.api.task][INFO] - Building contexts for mmlu_high_school_physics on rank 0... |
| [2026-07-08 23:53:48,185][lm_eval.api.task][INFO] - Building contexts for mmlu_high_school_statistics on rank 0... |
| [2026-07-08 23:53:48,412][lm_eval.api.task][INFO] - Building contexts for mmlu_machine_learning on rank 0... |
| [2026-07-08 23:53:48,532][lm_eval.api.task][INFO] - Building contexts for mmlu_business_ethics on rank 0... |
| [2026-07-08 23:53:48,643][lm_eval.api.task][INFO] - Building contexts for mmlu_clinical_knowledge on rank 0... |
| [2026-07-08 23:53:48,934][lm_eval.api.task][INFO] - Building contexts for mmlu_college_medicine on rank 0... |
| [2026-07-08 23:53:49,123][lm_eval.api.task][INFO] - Building contexts for mmlu_global_facts on rank 0... |
| [2026-07-08 23:53:49,230][lm_eval.api.task][INFO] - Building contexts for mmlu_human_aging on rank 0... |
| [2026-07-08 23:53:49,471][lm_eval.api.task][INFO] - Building contexts for mmlu_management on rank 0... |
| [2026-07-08 23:53:49,581][lm_eval.api.task][INFO] - Building contexts for mmlu_marketing on rank 0... |
| [2026-07-08 23:53:49,828][lm_eval.api.task][INFO] - Building contexts for mmlu_medical_genetics on rank 0... |
| [2026-07-08 23:53:49,941][lm_eval.api.task][INFO] - Building contexts for mmlu_miscellaneous on rank 0... |
| [2026-07-08 23:53:50,767][lm_eval.api.task][INFO] - Building contexts for mmlu_nutrition on rank 0... |
| [2026-07-08 23:53:51,088][lm_eval.api.task][INFO] - Building contexts for mmlu_professional_accounting on rank 0... |
| [2026-07-08 23:53:51,391][lm_eval.api.task][INFO] - Building contexts for mmlu_professional_medicine on rank 0... |
| [2026-07-08 23:53:51,678][lm_eval.api.task][INFO] - Building contexts for mmlu_virology on rank 0... |
| [2026-07-08 23:53:51,851][lm_eval.api.task][INFO] - Building contexts for mmlu_econometrics on rank 0... |
| [2026-07-08 23:53:51,977][lm_eval.api.task][INFO] - Building contexts for mmlu_high_school_geography on rank 0... |
| [2026-07-08 23:53:52,195][lm_eval.api.task][INFO] - Building contexts for mmlu_high_school_government_and_politics on rank 0... |
| [2026-07-08 23:53:52,404][lm_eval.api.task][INFO] - Building contexts for mmlu_high_school_macroeconomics on rank 0... |
| [2026-07-08 23:53:52,815][lm_eval.api.task][INFO] - Building contexts for mmlu_high_school_microeconomics on rank 0... |
| [2026-07-08 23:53:53,063][lm_eval.api.task][INFO] - Building contexts for mmlu_high_school_psychology on rank 0... |
| [2026-07-08 23:53:53,631][lm_eval.api.task][INFO] - Building contexts for mmlu_human_sexuality on rank 0... |
| [2026-07-08 23:53:54,388][lm_eval.api.task][INFO] - Building contexts for mmlu_professional_psychology on rank 0... |
| [2026-07-08 23:53:55,032][lm_eval.api.task][INFO] - Building contexts for mmlu_public_relations on rank 0... |
| [2026-07-08 23:53:55,149][lm_eval.api.task][INFO] - Building contexts for mmlu_security_studies on rank 0... |
| [2026-07-08 23:53:55,408][lm_eval.api.task][INFO] - Building contexts for mmlu_sociology on rank 0... |
| [2026-07-08 23:53:55,618][lm_eval.api.task][INFO] - Building contexts for mmlu_us_foreign_policy on rank 0... |
| [2026-07-08 23:53:55,724][lm_eval.api.task][INFO] - Building contexts for mmlu_formal_logic on rank 0... |
| [2026-07-08 23:53:55,857][lm_eval.api.task][INFO] - Building contexts for mmlu_high_school_european_history on rank 0... |
| [2026-07-08 23:53:56,032][lm_eval.api.task][INFO] - Building contexts for mmlu_high_school_us_history on rank 0... |
| [2026-07-08 23:53:56,247][lm_eval.api.task][INFO] - Building contexts for mmlu_high_school_world_history on rank 0... |
| [2026-07-08 23:53:56,498][lm_eval.api.task][INFO] - Building contexts for mmlu_international_law on rank 0... |
| [2026-07-08 23:53:56,625][lm_eval.api.task][INFO] - Building contexts for mmlu_jurisprudence on rank 0... |
| [2026-07-08 23:53:56,737][lm_eval.api.task][INFO] - Building contexts for mmlu_logical_fallacies on rank 0... |
| [2026-07-08 23:53:56,907][lm_eval.api.task][INFO] - Building contexts for mmlu_moral_disputes on rank 0... |
| [2026-07-08 23:53:57,271][lm_eval.api.task][INFO] - Building contexts for mmlu_moral_scenarios on rank 0... |
| [2026-07-08 23:53:58,197][lm_eval.api.task][INFO] - Building contexts for mmlu_philosophy on rank 0... |
| [2026-07-08 23:53:58,519][lm_eval.api.task][INFO] - Building contexts for mmlu_prehistory on rank 0... |
| [2026-07-08 23:53:58,853][lm_eval.api.task][INFO] - Building contexts for mmlu_professional_law on rank 0... |
| [2026-07-08 23:54:00,452][lm_eval.api.task][INFO] - Building contexts for mmlu_world_religions on rank 0... |
| [2026-07-08 23:54:00,630][lm_eval.evaluator][INFO] - Running loglikelihood requests |
|
|
