python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:xstorycloze" --languages="te" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:lambada_openai_mt_stablelm" --languages="en" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:m_mmlu" --languages="sv" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="glot500" --tasks="lm-eval-harness:hellaswag" --languages="te" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:lambada_openai_mt_stablelm" --languages="fr" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-l" --tasks="lm-eval-harness:m_mmlu" --languages="sr" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="glot500" --tasks="lm-eval-harness:m_mmlu" --languages="it" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:lambada_openai_mt_stablelm" --languages="it" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="glot500" --tasks="lm-eval-harness:m_mmlu" --languages="es" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-l" --tasks="lm-eval-harness:m_mmlu" --languages="ne" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:truthfulqa_mc1" --languages="fr" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-xl" --tasks="lm-eval-harness:m_mmlu" --languages="ml" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:hellaswag" --languages="ro" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-xl" --tasks="lm-eval-harness:m_mmlu" --languages="sk" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mt5-xl" --tasks="lm-eval-harness:hellaswag" --languages="te" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-l" --tasks="lm-eval-harness:m_mmlu" --languages="fr" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:arc" --languages="nl" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="bloom7b1" --tasks="lm-eval-harness:hellaswag" --languages="bn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="glot500" --tasks="lm-eval-harness:m_mmlu" --languages="ta" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:arc" --languages="es" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-l" --tasks="lm-eval-harness:m_mmlu" --languages="pt" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-l" --tasks="lm-eval-harness:m_mmlu" --languages="eu" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:mgsm_native_cot" --languages="de" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="glot500" --tasks="lm-eval-harness:hellaswag" --languages="eu" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-l" --tasks="lm-eval-harness:m_mmlu" --languages="vi" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:m_mmlu" --languages="sk" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:mgsm_native_cot" --languages="en" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-l" --tasks="lm-eval-harness:hellaswag" --languages="bn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="bloom1b7" --tasks="lm-eval-harness:hellaswag" --languages="ta" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:m_mmlu" --languages="vi" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mt5-xl" --tasks="lm-eval-harness:hellaswag" --languages="sr" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:xwinograd" --languages="fr" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="m2m" --tasks="lm-eval-harness:hellaswag" --languages="gu" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:paws" --languages="de" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:arc" --languages="hu" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:hellaswag" --languages="ta" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:hellaswag" --languages="fr" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-l" --tasks="lm-eval-harness:m_mmlu" --languages="hy" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:arc" --languages="hy" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:arc" --languages="mr" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="bloom7b1" --tasks="lm-eval-harness:hellaswag" --languages="te" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:mgsm_direct" --languages="th" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="glot500" --tasks="lm-eval-harness:hellaswag" --languages="kn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="bloom1b7" --tasks="lm-eval-harness:hellaswag" --languages="ml" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:arc" --languages="gu" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:m_mmlu" --languages="te" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:arc" --languages="ta" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="glot500" --tasks="lm-eval-harness:m_mmlu" --languages="hu" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="glot500" --tasks="lm-eval-harness:m_mmlu" --languages="sv" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mt5-xl" --tasks="lm-eval-harness:hellaswag" --languages="eu" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:truthfulqa_mc1" --languages="hi" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-l" --tasks="lm-eval-harness:m_mmlu" --languages="hr" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mt5-xl" --tasks="lm-eval-harness:hellaswag" --languages="pt" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="m2m" --tasks="lm-eval-harness:hellaswag" --languages="nl" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="bloom7b1" --tasks="lm-eval-harness:hellaswag" --languages="nl" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="bloom1b1" --tasks="lm-eval-harness:hellaswag" --languages="gu" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:xwinograd" --languages="zh" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:hellaswag" --languages="uk" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-l" --tasks="lm-eval-harness:m_mmlu" --languages="sk" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mt5-xl" --tasks="lm-eval-harness:hellaswag" --languages="es" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="m2m" --tasks="lm-eval-harness:hellaswag" --languages="ml" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:xstorycloze" --languages="zh" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mt5-xl" --tasks="lm-eval-harness:hellaswag" --languages="ta" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:truthfulqa_mc1" --languages="de" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mt5-xl" --tasks="lm-eval-harness:hellaswag" --languages="kn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:arc" --languages="ne" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:hellaswag" --languages="bn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mt5-l" --tasks="lm-eval-harness:hellaswag" --languages="ml" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="m2m" --tasks="lm-eval-harness:hellaswag" --languages="ta" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-l" --tasks="lm-eval-harness:m_mmlu" --languages="uk" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:arc" --languages="ca" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-l" --tasks="lm-eval-harness:m_mmlu" --languages="is" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="glot500" --tasks="lm-eval-harness:m_mmlu" --languages="hi" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:m_mmlu" --languages="ar" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="glot500" --tasks="lm-eval-harness:m_mmlu" --languages="nb" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:truthfulqa_mc1" --languages="gu" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-l" --tasks="lm-eval-harness:m_mmlu" --languages="nb" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:m_mmlu" --languages="fr" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:arc" --languages="id" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:m_mmlu" --languages="hy" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-xl" --tasks="lm-eval-harness:m_mmlu" --languages="ru" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-l" --tasks="lm-eval-harness:hellaswag" --languages="ml" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:m_mmlu" --languages="ro" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:xcopa" --languages="et" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="bloom7b1" --tasks="lm-eval-harness:hellaswag" --languages="ta" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="m2m" --tasks="lm-eval-harness:hellaswag" --languages="mr" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:mgsm_direct" --languages="sw" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:truthfulqa_mc1" --languages="ca" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-xl" --tasks="lm-eval-harness:m_mmlu" --languages="sr" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:mgsm_direct" --languages="zh" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-xl" --tasks="lm-eval-harness:m_mmlu" --languages="vi" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:truthfulqa_mc1" --languages="uk" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-l" --tasks="lm-eval-harness:m_mmlu" --languages="te" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-l" --tasks="lm-eval-harness:hellaswag" --languages="ne" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:m_mmlu" --languages="ne" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mt5-xl" --tasks="lm-eval-harness:hellaswag" --languages="ne" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="glot500" --tasks="lm-eval-harness:m_mmlu" --languages="sk" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:hellaswag" --languages="ru" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:hellaswag" --languages="ml" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:m_mmlu" --languages="da" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:mgsm_direct" --languages="de" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:hellaswag" --languages="mr" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:xcopa" --languages="it" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="glot500" --tasks="lm-eval-harness:m_mmlu" --languages="is" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:m_mmlu" --languages="es" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:m_mmlu" --languages="pt" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mt5-xl" --tasks="lm-eval-harness:hellaswag" --languages="ro" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:xstorycloze" --languages="es" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="bloom1b1" --tasks="lm-eval-harness:hellaswag" --languages="ne" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-l" --tasks="lm-eval-harness:m_mmlu" --languages="en" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:hellaswag" --languages="hu" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:xnli" --languages="bg" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-l" --tasks="lm-eval-harness:m_mmlu" --languages="ca" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="bloom1b1" --tasks="lm-eval-harness:hellaswag" --languages="te" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:m_mmlu" --languages="kn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-l" --tasks="lm-eval-harness:lambada_openai_mt_stablelm" --languages="fr" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-xl" --tasks="lm-eval-harness:m_mmlu" --languages="bn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-xl" --tasks="lm-eval-harness:m_mmlu" --languages="gu" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:truthfulqa_mc1" --languages="hy" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="m2m" --tasks="lm-eval-harness:hellaswag" --languages="ne" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mt5-l" --tasks="lm-eval-harness:hellaswag" --languages="bn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="bloom1b7" --tasks="lm-eval-harness:hellaswag" --languages="bn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-l" --tasks="lm-eval-harness:m_mmlu" --languages="gu" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:truthfulqa_mc1" --languages="zh" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:m_mmlu" --languages="ca" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:xstorycloze" --languages="hi" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:xcopa" --languages="ta" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:hellaswag" --languages="ca" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="bloom1b7" --tasks="lm-eval-harness:hellaswag" --languages="mr" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:hellaswag" --languages="es" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-xl" --tasks="lm-eval-harness:m_mmlu" --languages="kn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="seallm-7b-v2" --tasks="lm-eval-harness:xstorycloze" --languages="te" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:mgsm_native_cot" --languages="fr" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:paws" --languages="es" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:mgsm_direct" --languages="ru" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-l" --tasks="lm-eval-harness:m_mmlu" --languages="id" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:truthfulqa_mc1" --languages="mr" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:truthfulqa_mc1" --languages="nl" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-l" --tasks="lm-eval-harness:m_mmlu" --languages="ml" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:m_mmlu" --languages="ta" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="glot500" --tasks="lm-eval-harness:hellaswag" --languages="ml" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:xwinograd" --languages="en" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="glot500" --tasks="lm-eval-harness:m_mmlu" --languages="ru" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-l" --tasks="lm-eval-harness:m_mmlu" --languages="da" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-xl" --tasks="lm-eval-harness:m_mmlu" --languages="id" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:xcopa" --languages="tr" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:truthfulqa_mc1" --languages="pt" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:xcopa" --languages="qu" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:arc" --languages="fr" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="glot500" --tasks="lm-eval-harness:m_mmlu" --languages="ca" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="lola" --tasks="lm-eval-harness:truthfulqa_mc1" --languages="it" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:truthfulqa_mc1" --languages="ro" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:m_mmlu" --languages="id" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:arc" --languages="ar" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:mgsm_native_cot" --languages="ja" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="m2m" --tasks="lm-eval-harness:hellaswag" --languages="te" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:hellaswag" --languages="sv" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:arc" --languages="bn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:arc" --languages="ro" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-xl" --tasks="lm-eval-harness:m_mmlu" --languages="sv" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:hellaswag" --languages="pt" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:m_mmlu" --languages="nl" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:mgsm_native_cot" --languages="bn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mt5-xl" --tasks="lm-eval-harness:hellaswag" --languages="nl" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:hellaswag" --languages="hr" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="glot500" --tasks="lm-eval-harness:m_mmlu" --languages="de" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:truthfulqa_mc1" --languages="it" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-l" --tasks="lm-eval-harness:m_mmlu" --languages="mr" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-l" --tasks="lm-eval-harness:m_mmlu" --languages="ar" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:hellaswag" --languages="vi" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:mgsm_native_cot" --languages="th" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:arc" --languages="de" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-xl" --tasks="lm-eval-harness:m_mmlu" --languages="hr" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-xl" --tasks="lm-eval-harness:m_mmlu" --languages="hy" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:mgsm_native_cot" --languages="te" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="glot500" --tasks="lm-eval-harness:m_mmlu" --languages="gu" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="bloom7b1" --tasks="lm-eval-harness:hellaswag" --languages="ne" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:m_mmlu" --languages="bn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-xl" --tasks="lm-eval-harness:m_mmlu" --languages="zh" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:hellaswag" --languages="kn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="glot500" --tasks="lm-eval-harness:m_mmlu" --languages="kn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="m2m" --tasks="lm-eval-harness:hellaswag" --languages="eu" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:xnli" --languages="hi" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="lola" --tasks="lm-eval-harness:truthfulqa_mc1" --languages="pt" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mt5-xl" --tasks="lm-eval-harness:hellaswag" --languages="ar" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:hellaswag" --languages="hy" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-xl" --tasks="lm-eval-harness:m_mmlu" --languages="ca" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="bloom1b7" --tasks="lm-eval-harness:hellaswag" --languages="gu" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:hellaswag" --languages="te" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:mgsm_direct" --languages="bn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="glot500" --tasks="lm-eval-harness:m_mmlu" --languages="mr" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-l" --tasks="lm-eval-harness:m_mmlu" --languages="hu" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="bloom1b1" --tasks="lm-eval-harness:hellaswag" --languages="kn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-l" --tasks="lm-eval-harness:m_mmlu" --languages="nl" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:lambada_openai_mt_stablelm" --languages="de" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="bloom1b1" --tasks="lm-eval-harness:hellaswag" --languages="mr" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-xl" --tasks="lm-eval-harness:m_mmlu" --languages="uk" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-xl" --tasks="lm-eval-harness:m_mmlu" --languages="hu" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="glot500" --tasks="lm-eval-harness:m_mmlu" --languages="fr" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mt5-xl" --tasks="lm-eval-harness:hellaswag" --languages="ml" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mt5-xl" --tasks="lm-eval-harness:hellaswag" --languages="gu" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:arc" --languages="te" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:truthfulqa_mc1" --languages="ta" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-xl" --tasks="lm-eval-harness:m_mmlu" --languages="mr" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-l" --tasks="lm-eval-harness:m_mmlu" --languages="hi" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="bloom7b1" --tasks="lm-eval-harness:hellaswag" --languages="gu" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:m_mmlu" --languages="eu" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-l" --tasks="lm-eval-harness:hellaswag" --languages="gu" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="bloom1b1" --tasks="lm-eval-harness:hellaswag" --languages="ml" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:paws" --languages="ja" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="m2m" --tasks="lm-eval-harness:hellaswag" --languages="bn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="m2m" --tasks="lm-eval-harness:hellaswag" --languages="kn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="glot500" --tasks="lm-eval-harness:m_mmlu" --languages="ml" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:xcopa" --languages="id" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-xl" --tasks="lm-eval-harness:m_mmlu" --languages="ta" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:paws" --languages="en" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:hellaswag" --languages="de" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:xnli" --languages="ar" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-l" --tasks="lm-eval-harness:hellaswag" --languages="mr" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="bloom1b1" --tasks="lm-eval-harness:hellaswag" --languages="ta" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mt5-l" --tasks="lm-eval-harness:hellaswag" --languages="mr" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:truthfulqa_mc1" --languages="vi" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:hellaswag" --languages="da" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:xcopa" --languages="ht" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:arc" --languages="eu" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="glot500" --tasks="lm-eval-harness:m_mmlu" --languages="uk" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:mgsm_direct" --languages="fr" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:truthfulqa_mc1" --languages="ar" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-l" --tasks="lm-eval-harness:hellaswag" --languages="nl" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mt5-xl" --tasks="lm-eval-harness:hellaswag" --languages="sv" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="glot500" --tasks="lm-eval-harness:m_mmlu" --languages="ro" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:m_mmlu" --languages="nb" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:m_mmlu" --languages="sr" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:arc" --languages="sv" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="glot500" --tasks="lm-eval-harness:m_mmlu" --languages="eu" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:m_mmlu" --languages="uk" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-l" --tasks="lm-eval-harness:m_mmlu" --languages="zh" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:xnli" --languages="tr" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="glot500" --tasks="lm-eval-harness:hellaswag" --languages="ta" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:m_mmlu" --languages="gu" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:xwinograd" --languages="ja" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-l" --tasks="lm-eval-harness:hellaswag" --languages="kn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="bloom1b7" --tasks="lm-eval-harness:hellaswag" --languages="eu" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:xstorycloze" --languages="ar" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:arc" --languages="hr" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:arc" --languages="zh" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:xnli" --languages="ru" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mt5-xl" --tasks="lm-eval-harness:hellaswag" --languages="bn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-l" --tasks="lm-eval-harness:hellaswag" --languages="te" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="bloom1b7" --tasks="lm-eval-harness:hellaswag" --languages="kn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-xl" --tasks="lm-eval-harness:m_mmlu" --languages="da" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="glot500" --tasks="lm-eval-harness:m_mmlu" --languages="nl" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-xl" --tasks="lm-eval-harness:m_mmlu" --languages="de" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:xnli" --languages="de" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:xnli" --languages="zh" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="glot500" --tasks="lm-eval-harness:m_mmlu" --languages="bn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-l" --tasks="lm-eval-harness:hellaswag" --languages="eu" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mt5-l" --tasks="lm-eval-harness:hellaswag" --languages="ta" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-xl" --tasks="lm-eval-harness:m_mmlu" --languages="fr" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mt5-l" --tasks="lm-eval-harness:hellaswag" --languages="te" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:mgsm_direct" --languages="ja" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-xl" --tasks="lm-eval-harness:m_mmlu" --languages="pt" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:truthfulqa_mc1" --languages="ne" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:truthfulqa_mc1" --languages="sr" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="glot500" --tasks="lm-eval-harness:m_mmlu" --languages="pt" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-xl" --tasks="lm-eval-harness:m_mmlu" --languages="nl" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:mgsm_direct" --languages="en" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-l" --tasks="lm-eval-harness:m_mmlu" --languages="ru" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:truthfulqa_mc1" --languages="es" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:xnli" --languages="el" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="glot500" --tasks="lm-eval-harness:m_mmlu" --languages="hy" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-l" --tasks="lm-eval-harness:m_mmlu" --languages="es" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:truthfulqa_mc1" --languages="eu" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:arc" --languages="uk" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:m_mmlu" --languages="hi" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:xcopa" --languages="th" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:hellaswag" --languages="id" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:mgsm_native_cot" --languages="ru" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mt5-l" --tasks="lm-eval-harness:hellaswag" --languages="ne" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="glot500" --tasks="lm-eval-harness:m_mmlu" --languages="te" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="glot500" --tasks="lm-eval-harness:m_mmlu" --languages="id" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:hellaswag" --languages="it" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-xl" --tasks="lm-eval-harness:m_mmlu" --languages="ar" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-xl" --tasks="lm-eval-harness:m_mmlu" --languages="ne" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-l" --tasks="lm-eval-harness:m_mmlu" --languages="de" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:xnli" --languages="th" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:truthfulqa_mc1" --languages="da" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-xl" --tasks="lm-eval-harness:m_mmlu" --languages="is" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:hellaswag" --languages="eu" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-xl" --tasks="lm-eval-harness:m_mmlu" --languages="it" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:truthfulqa_mc1" --languages="te" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:truthfulqa_mc1" --languages="hu" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:hellaswag" --languages="nl" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="glot500" --tasks="lm-eval-harness:hellaswag" --languages="mr" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="glot500" --tasks="lm-eval-harness:hellaswag" --languages="nl" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:hellaswag" --languages="ar" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mt5-l" --tasks="lm-eval-harness:hellaswag" --languages="gu" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="bloom7b1" --tasks="lm-eval-harness:hellaswag" --languages="mr" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mt5-xl" --tasks="lm-eval-harness:hellaswag" --languages="mr" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:m_mmlu" --languages="ru" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="bloom7b1" --tasks="lm-eval-harness:hellaswag" --languages="eu" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="glot500" --tasks="lm-eval-harness:hellaswag" --languages="bn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:m_mmlu" --languages="it" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:arc" --languages="it" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mt5-xl" --tasks="lm-eval-harness:lambada_openai_mt_stablelm" --languages="fr" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="glot500" --tasks="lm-eval-harness:m_mmlu" --languages="ne" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:xstorycloze" --languages="en" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:xstorycloze" --languages="my" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:m_mmlu" --languages="en" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:arc" --languages="pt" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="glot500" --tasks="lm-eval-harness:m_mmlu" --languages="hr" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="glot500" --tasks="lm-eval-harness:m_mmlu" --languages="ar" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:hellaswag" --languages="gu" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="bloom1b1" --tasks="lm-eval-harness:hellaswag" --languages="nl" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-xl" --tasks="lm-eval-harness:m_mmlu" --languages="eu" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-xl" --tasks="lm-eval-harness:m_mmlu" --languages="en" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:xwinograd" --languages="pt" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:xnli" --languages="vi" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mt5-xl" --tasks="lm-eval-harness:hellaswag" --languages="de" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:truthfulqa_mc1" --languages="hr" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-xl" --tasks="lm-eval-harness:m_mmlu" --languages="nb" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="bloom1b7" --tasks="lm-eval-harness:hellaswag" --languages="ne" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-l" --tasks="lm-eval-harness:m_mmlu" --languages="sv" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:xnli" --languages="sw" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:xnli" --languages="en" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="glot500" --tasks="lm-eval-harness:m_mmlu" --languages="sr" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="glot500" --tasks="lm-eval-harness:hellaswag" --languages="gu" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:xwinograd" --languages="ru" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:arc" --languages="ml" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:arc" --languages="vi" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:arc" --languages="ru" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:m_mmlu" --languages="hu" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:arc" --languages="da" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-l" --tasks="lm-eval-harness:m_mmlu" --languages="ro" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:xnli" --languages="fr" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:arc" --languages="hi" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="glot500" --tasks="lm-eval-harness:m_mmlu" --languages="vi" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:mgsm_native_cot" --languages="zh" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="m2m" --tasks="lm-eval-harness:lambada_openai_mt_stablelm" --languages="fr" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:m_mmlu" --languages="de" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mt5-l" --tasks="lm-eval-harness:hellaswag" --languages="nl" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:arc" --languages="kn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:m_mmlu" --languages="hr" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:mgsm_direct" --languages="te" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:truthfulqa_mc1" --languages="id" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:truthfulqa_mc1" --languages="ru" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:truthfulqa_mc1" --languages="kn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-xl" --tasks="lm-eval-harness:m_mmlu" --languages="ro" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mt5-l" --tasks="lm-eval-harness:hellaswag" --languages="kn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:paws" --languages="fr" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="glot500" --tasks="lm-eval-harness:m_mmlu" --languages="da" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="bloom1b1" --tasks="lm-eval-harness:hellaswag" --languages="bn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:arc" --languages="sk" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="bloom1b7" --tasks="lm-eval-harness:hellaswag" --languages="te" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:xcopa" --languages="zh" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:xstorycloze" --languages="sw" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:mgsm_native_cot" --languages="sw" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-l" --tasks="lm-eval-harness:m_mmlu" --languages="bn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:xstorycloze" --languages="id" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:truthfulqa_mc1" --languages="ml" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="bloom1b1" --tasks="lm-eval-harness:hellaswag" --languages="eu" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:truthfulqa_mc1" --languages="bn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:arc" --languages="sr" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mt5-xl" --tasks="lm-eval-harness:hellaswag" --languages="ru" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:paws" --languages="zh" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="lola" --tasks="lm-eval-harness:truthfulqa_mc1" --languages="zh" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:truthfulqa_mc1" --languages="sv" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:hellaswag" --languages="sr" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-l" --tasks="lm-eval-harness:m_mmlu" --languages="kn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:xcopa" --languages="sw" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="glot500" --tasks="lm-eval-harness:m_mmlu" --languages="en" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-xl" --tasks="lm-eval-harness:m_mmlu" --languages="te" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:xnli" --languages="es" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="bloom7b1" --tasks="lm-eval-harness:hellaswag" --languages="ml" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:hellaswag" --languages="hi" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:m_mmlu" --languages="is" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:m_mmlu" --languages="mr" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:mgsm_direct" --languages="es" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="glot500" --tasks="lm-eval-harness:lambada_openai_mt_stablelm" --languages="fr" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-l" --tasks="lm-eval-harness:m_mmlu" --languages="it" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:truthfulqa_mc1" --languages="sk" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:xcopa" --languages="vi" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="bloom7b1" --tasks="lm-eval-harness:hellaswag" --languages="kn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:m_mmlu" --languages="zh" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:xstorycloze" --languages="ru" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:m_mmlu" --languages="ml" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:xstorycloze" --languages="eu" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:lambada_openai_mt_stablelm" --languages="es" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:xnli" --languages="ur" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:paws" --languages="ko" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:mgsm_native_cot" --languages="es" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-xl" --tasks="lm-eval-harness:m_mmlu" --languages="hi" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="bloom1b7" --tasks="lm-eval-harness:hellaswag" --languages="nl" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-l" --tasks="lm-eval-harness:m_mmlu" --languages="ta" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:hellaswag" --languages="ne" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-xl" --tasks="lm-eval-harness:m_mmlu" --languages="es" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-l" --tasks="lm-eval-harness:hellaswag" --languages="ta" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:hellaswag" --languages="sk" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="glot500" --tasks="lm-eval-harness:m_mmlu" --languages="zh" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="glot500" --tasks="lm-eval-harness:hellaswag" --languages="ne" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mt5-l" --tasks="lm-eval-harness:hellaswag" --languages="eu" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mt5-l" --tasks="lm-eval-harness:lambada_openai_mt_stablelm" --languages="fr" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:belebele" --languages="kan_Knda" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-xl" --tasks="lm-eval-harness:belebele" --languages="shn_Mymr" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:belebele" --languages="pol_Latn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:belebele" --languages="tgl_Latn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:belebele" --languages="mri_Latn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-xl" --tasks="lm-eval-harness:belebele" --languages="pbt_Arab" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-xl" --tasks="lm-eval-harness:belebele" --languages="fra_Latn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-l" --tasks="lm-eval-harness:belebele" --languages="ceb_Latn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-xl" --tasks="lm-eval-harness:belebele" --languages="npi_Latn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-l" --tasks="lm-eval-harness:belebele" --languages="arb_Latn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-xl" --tasks="lm-eval-harness:belebele" --languages="nya_Latn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="glot500" --tasks="lm-eval-harness:belebele" --languages="pbt_Arab" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="glot500" --tasks="lm-eval-harness:belebele" --languages="tir_Ethi" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-l" --tasks="lm-eval-harness:belebele" --languages="som_Latn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:belebele" --languages="tam_Taml" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-l" --tasks="lm-eval-harness:belebele" --languages="fra_Latn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:belebele" --languages="ibo_Latn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-xl" --tasks="lm-eval-harness:belebele" --languages="snd_Arab" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="seallm-1_5b-v3" --tasks="lm-eval-harness:belebele" --languages="ary_arab" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-xl" --tasks="lm-eval-harness:belebele" --languages="war_Latn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:belebele" --languages="kea_Latn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:belebele" --languages="npi_Deva" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-l" --tasks="lm-eval-harness:belebele" --languages="sin_Latn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:belebele" --languages="sin_Sinh" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-l" --tasks="lm-eval-harness:belebele" --languages="bam_Latn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-l" --tasks="lm-eval-harness:belebele" --languages="grn_Latn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:belebele" --languages="nob_Latn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:belebele" --languages="ars_Arab" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="glot500" --tasks="lm-eval-harness:belebele" --languages="kan_Knda" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="glot500" --tasks="lm-eval-harness:belebele" --languages="snd_Arab" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-l" --tasks="lm-eval-harness:belebele" --languages="luo_Latn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="glot500" --tasks="lm-eval-harness:belebele" --languages="arb_Latn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-l" --tasks="lm-eval-harness:belebele" --languages="yor_Latn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:belebele" --languages="srp_Cyrl" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:belebele" --languages="fra_Latn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:belebele" --languages="kat_Geor" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-l" --tasks="lm-eval-harness:belebele" --languages="guj_Gujr" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="glot500" --tasks="lm-eval-harness:belebele" --languages="plt_Latn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-l" --tasks="lm-eval-harness:belebele" --languages="lao_Laoo" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:belebele" --languages="som_Latn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:belebele" --languages="pan_Guru" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="glot500" --tasks="lm-eval-harness:belebele" --languages="ell_Grek" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="glot500" --tasks="lm-eval-harness:belebele" --languages="kat_Geor" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-l" --tasks="lm-eval-harness:belebele" --languages="hin_Latn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-l" --tasks="lm-eval-harness:belebele" --languages="tel_Telu" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-l" --tasks="lm-eval-harness:belebele" --languages="mri_Latn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:belebele" --languages="nld_Latn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="glot500" --tasks="lm-eval-harness:belebele" --languages="kac_Latn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-xl" --tasks="lm-eval-harness:belebele" --languages="ell_Grek" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:belebele" --languages="hat_Latn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:belebele" --languages="kaz_Cyrl" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-xl" --tasks="lm-eval-harness:belebele" --languages="lin_Latn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-l" --tasks="lm-eval-harness:belebele" --languages="ary_arab" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-xl" --tasks="lm-eval-harness:belebele" --languages="ceb_Latn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:belebele" --languages="vie_Latn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-l" --tasks="lm-eval-harness:belebele" --languages="kin_Latn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-l" --tasks="lm-eval-harness:belebele" --languages="sot_Latn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-l" --tasks="lm-eval-harness:belebele" --languages="sin_Sinh" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-l" --tasks="lm-eval-harness:belebele" --languages="urd_Latn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="glot500" --tasks="lm-eval-harness:belebele" --languages="shn_Mymr" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-xl" --tasks="lm-eval-harness:belebele" --languages="grn_Latn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:belebele" --languages="lvs_Latn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-xl" --tasks="lm-eval-harness:belebele" --languages="ukr_Cyrl" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-l" --tasks="lm-eval-harness:belebele" --languages="nya_Latn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:belebele" --languages="urd_Arab" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-xl" --tasks="lm-eval-harness:belebele" --languages="pan_Guru" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-l" --tasks="lm-eval-harness:belebele" --languages="khm_Khmr" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-l" --tasks="lm-eval-harness:belebele" --languages="tir_Ethi" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-xl" --tasks="lm-eval-harness:belebele" --languages="kin_Latn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:belebele" --languages="swh_Latn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-l" --tasks="lm-eval-harness:belebele" --languages="war_Latn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="glot500" --tasks="lm-eval-harness:belebele" --languages="war_Latn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:belebele" --languages="bam_Latn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:belebele" --languages="sun_Latn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:belebele" --languages="jpn_Jpan" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:belebele" --languages="war_Latn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-xl" --tasks="lm-eval-harness:belebele" --languages="tso_Latn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-l" --tasks="lm-eval-harness:belebele" --languages="lin_Latn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:belebele" --languages="tsn_Latn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-l" --tasks="lm-eval-harness:belebele" --languages="tso_Latn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-l" --tasks="lm-eval-harness:belebele" --languages="asm_Beng" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:belebele" --languages="zho_Hant" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:belebele" --languages="apc_Arab" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-xl" --tasks="lm-eval-harness:belebele" --languages="sot_Latn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-l" --tasks="lm-eval-harness:belebele" --languages="kac_Latn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:belebele" --languages="zho_Hans" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="glot500" --tasks="lm-eval-harness:belebele" --languages="uzn_Latn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:belebele" --languages="ben_Latn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-xl" --tasks="lm-eval-harness:belebele" --languages="ben_Latn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-xl" --tasks="lm-eval-harness:belebele" --languages="tgk_Cyrl" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:belebele" --languages="mkd_Cyrl" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:belebele" --languages="sin_Latn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-l" --tasks="lm-eval-harness:belebele" --languages="uzn_Latn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-xl" --tasks="lm-eval-harness:belebele" --languages="wol_Latn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-l" --tasks="lm-eval-harness:belebele" --languages="zul_Latn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="glot500" --tasks="lm-eval-harness:belebele" --languages="mlt_Latn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:belebele" --languages="zsm_Latn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="glot500" --tasks="lm-eval-harness:belebele" --languages="lao_Laoo" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:belebele" --languages="kir_Cyrl" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-l" --tasks="lm-eval-harness:belebele" --languages="tsn_Latn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-l" --tasks="lm-eval-harness:belebele" --languages="mar_Deva" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:belebele" --languages="uzn_Latn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:belebele" --languages="isl_Latn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-xl" --tasks="lm-eval-harness:belebele" --languages="hye_Armn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:belebele" --languages="ron_Latn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-xl" --tasks="lm-eval-harness:belebele" --languages="lug_Latn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:belebele" --languages="arb_Latn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-l" --tasks="lm-eval-harness:belebele" --languages="tgk_Cyrl" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:belebele" --languages="lin_Latn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-xl" --tasks="lm-eval-harness:belebele" --languages="ckb_Arab" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-xl" --tasks="lm-eval-harness:belebele" --languages="arb_Latn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="glot500" --tasks="lm-eval-harness:belebele" --languages="mya_Mymr" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:belebele" --languages="lug_Latn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:belebele" --languages="deu_Latn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:belebele" --languages="azj_Latn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:belebele" --languages="yor_Latn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-xl" --tasks="lm-eval-harness:belebele" --languages="urd_Latn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-xl" --tasks="lm-eval-harness:belebele" --languages="fuv_Latn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="glot500" --tasks="lm-eval-harness:belebele" --languages="hin_Latn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:belebele" --languages="acm_Arab" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-l" --tasks="lm-eval-harness:belebele" --languages="tam_Taml" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:belebele" --languages="ssw_Latn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-xl" --tasks="lm-eval-harness:belebele" --languages="tgl_Latn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-xl" --tasks="lm-eval-harness:belebele" --languages="amh_Ethi" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-l" --tasks="lm-eval-harness:belebele" --languages="npi_Latn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-xl" --tasks="lm-eval-harness:belebele" --languages="asm_Beng" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:belebele" --languages="swe_Latn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-l" --tasks="lm-eval-harness:belebele" --languages="pan_Guru" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="zephyr" --tasks="lm-eval-harness:belebele" --languages="ary_arab" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:belebele" --languages="fuv_Latn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-xl" --tasks="lm-eval-harness:belebele" --languages="mlt_Latn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-xl" --tasks="lm-eval-harness:belebele" --languages="mri_Latn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:belebele" --languages="arb_Arab" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:belebele" --languages="slk_Latn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:belebele" --languages="cat_Latn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:belebele" --languages="afr_Latn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-l" --tasks="lm-eval-harness:belebele" --languages="hau_Latn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="glot500" --tasks="lm-eval-harness:belebele" --languages="ary_arab" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:belebele" --languages="hin_Latn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="glot500" --tasks="lm-eval-harness:belebele" --languages="urd_Latn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="glot500" --tasks="lm-eval-harness:belebele" --languages="sin_Sinh" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="glot500" --tasks="lm-eval-harness:belebele" --languages="ssw_Latn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-xl" --tasks="lm-eval-harness:belebele" --languages="kat_Geor" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:belebele" --languages="hrv_Latn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-xl" --tasks="lm-eval-harness:belebele" --languages="mar_Deva" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:belebele" --languages="als_Latn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="glot500" --tasks="lm-eval-harness:belebele" --languages="ben_Latn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:belebele" --languages="kin_Latn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-xl" --tasks="lm-eval-harness:belebele" --languages="khm_Khmr" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mgpt" --tasks="lm-eval-harness:belebele" --languages="ary_arab" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:belebele" --languages="zul_Latn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="glot500" --tasks="lm-eval-harness:belebele" --languages="ilo_Latn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:belebele" --languages="kor_Hang" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-xl" --tasks="lm-eval-harness:belebele" --languages="plt_Latn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="glot500" --tasks="lm-eval-harness:belebele" --languages="mal_Mlym" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:belebele" --languages="luo_Latn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="glot500" --tasks="lm-eval-harness:belebele" --languages="sin_Latn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="bloom1b1" --tasks="lm-eval-harness:belebele" --languages="ary_arab" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="falcon" --tasks="lm-eval-harness:belebele" --languages="ary_arab" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-l" --tasks="lm-eval-harness:belebele" --languages="hye_Armn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="glot500" --tasks="lm-eval-harness:belebele" --languages="som_Latn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:belebele" --languages="ben_Beng" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-l" --tasks="lm-eval-harness:belebele" --languages="kat_Geor" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-l" --tasks="lm-eval-harness:belebele" --languages="ibo_Latn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:belebele" --languages="jav_Latn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-l" --tasks="lm-eval-harness:belebele" --languages="shn_Mymr" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:belebele" --languages="ukr_Cyrl" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="glot500" --tasks="lm-eval-harness:belebele" --languages="mri_Latn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="glot500" --tasks="lm-eval-harness:belebele" --languages="asm_Beng" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:belebele" --languages="tso_Latn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:belebele" --languages="khk_Cyrl" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-l" --tasks="lm-eval-harness:belebele" --languages="ben_Beng" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-xl" --tasks="lm-eval-harness:belebele" --languages="hau_Latn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:belebele" --languages="xho_Latn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:belebele" --languages="tur_Latn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="glot500" --tasks="lm-eval-harness:belebele" --languages="tso_Latn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:belebele" --languages="rus_Cyrl" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-xl" --tasks="lm-eval-harness:belebele" --languages="mal_Mlym" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="glot500" --tasks="lm-eval-harness:belebele" --languages="als_Latn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="towerbase" --tasks="lm-eval-harness:belebele" --languages="ary_arab" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mt5-l" --tasks="lm-eval-harness:belebele" --languages="ary_arab" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:belebele" --languages="ind_Latn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:belebele" --languages="plt_Latn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-xl" --tasks="lm-eval-harness:belebele" --languages="ary_arab" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-l" --tasks="lm-eval-harness:belebele" --languages="xho_Latn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:belebele" --languages="wol_Latn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-l" --tasks="lm-eval-harness:belebele" --languages="pbt_Arab" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:belebele" --languages="grn_Latn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:belebele" --languages="ces_Latn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-l" --tasks="lm-eval-harness:belebele" --languages="ben_Latn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:belebele" --languages="eus_Latn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-xl" --tasks="lm-eval-harness:belebele" --languages="tel_Telu" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="seallm-7b-v2" --tasks="lm-eval-harness:belebele" --languages="ary_arab" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:belebele" --languages="tgk_Cyrl" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="seallm-7b-v2_5" --tasks="lm-eval-harness:belebele" --languages="ary_arab" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-l" --tasks="lm-eval-harness:belebele" --languages="hat_Latn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-l" --tasks="lm-eval-harness:belebele" --languages="kea_Latn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:belebele" --languages="sna_Latn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-xl" --tasks="lm-eval-harness:belebele" --languages="ssw_Latn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:belebele" --languages="ceb_Latn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="lola" --tasks="lm-eval-harness:belebele" --languages="ary_arab" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:belebele" --languages="guj_Gujr" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:belebele" --languages="ell_Grek" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-xl" --tasks="lm-eval-harness:belebele" --languages="sin_Latn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-xl" --tasks="lm-eval-harness:belebele" --languages="xho_Latn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mt5-xl" --tasks="lm-eval-harness:belebele" --languages="ary_arab" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:belebele" --languages="ckb_Arab" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-xl" --tasks="lm-eval-harness:belebele" --languages="hin_Latn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:belebele" --languages="tha_Thai" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:belebele" --languages="lao_Laoo" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:belebele" --languages="ary_arab" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="glot500" --tasks="lm-eval-harness:belebele" --languages="tgk_Cyrl" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="glot500" --tasks="lm-eval-harness:belebele" --languages="gaz_Latn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-xl" --tasks="lm-eval-harness:belebele" --languages="kac_Latn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:belebele" --languages="ory_Orya" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-l" --tasks="lm-eval-harness:belebele" --languages="amh_Ethi" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-l" --tasks="lm-eval-harness:belebele" --languages="ssw_Latn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:belebele" --languages="hin_Deva" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-xl" --tasks="lm-eval-harness:belebele" --languages="lao_Laoo" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-l" --tasks="lm-eval-harness:belebele" --languages="mal_Mlym" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-l" --tasks="lm-eval-harness:belebele" --languages="ory_Orya" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:belebele" --languages="ilo_Latn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-l" --tasks="lm-eval-harness:belebele" --languages="mlt_Latn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:belebele" --languages="hye_Armn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-xl" --tasks="lm-eval-harness:belebele" --languages="kan_Knda" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="glot500" --tasks="lm-eval-harness:belebele" --languages="pan_Guru" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:belebele" --languages="bul_Cyrl" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:belebele" --languages="npi_Latn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-l" --tasks="lm-eval-harness:belebele" --languages="fuv_Latn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:belebele" --languages="gaz_Latn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:belebele" --languages="eng_Latn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:belebele" --languages="lit_Latn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:belebele" --languages="bod_Tibt" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-xl" --tasks="lm-eval-harness:belebele" --languages="som_Latn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:belebele" --languages="mal_Mlym" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:belebele" --languages="hau_Latn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-xl" --tasks="lm-eval-harness:belebele" --languages="sin_Sinh" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:belebele" --languages="dan_Latn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="glot500" --tasks="lm-eval-harness:belebele" --languages="tsn_Latn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-l" --tasks="lm-eval-harness:belebele" --languages="snd_Arab" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="breeze" --tasks="lm-eval-harness:belebele" --languages="ary_arab" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-xl" --tasks="lm-eval-harness:belebele" --languages="gaz_Latn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-xl" --tasks="lm-eval-harness:belebele" --languages="tir_Ethi" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-xl" --tasks="lm-eval-harness:belebele" --languages="tam_Taml" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:belebele" --languages="hun_Latn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="m2m" --tasks="lm-eval-harness:belebele" --languages="ary_arab" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-xl" --tasks="lm-eval-harness:belebele" --languages="guj_Gujr" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="glot500" --tasks="lm-eval-harness:belebele" --languages="kin_Latn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-l" --tasks="lm-eval-harness:belebele" --languages="plt_Latn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:belebele" --languages="amh_Ethi" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-l" --tasks="lm-eval-harness:belebele" --languages="ell_Grek" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-xl" --tasks="lm-eval-harness:belebele" --languages="hat_Latn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:belebele" --languages="por_Latn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-l" --tasks="lm-eval-harness:belebele" --languages="tgl_Latn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="glot500" --tasks="lm-eval-harness:belebele" --languages="nso_Latn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-xl" --tasks="lm-eval-harness:belebele" --languages="bam_Latn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-xl" --tasks="lm-eval-harness:belebele" --languages="uzn_Latn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-xl" --tasks="lm-eval-harness:belebele" --languages="yor_Latn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="bloom7b1" --tasks="lm-eval-harness:belebele" --languages="ary_arab" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:belebele" --languages="fin_Latn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-xl" --tasks="lm-eval-harness:belebele" --languages="ibo_Latn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="glot500" --tasks="lm-eval-harness:belebele" --languages="khm_Khmr" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-l" --tasks="lm-eval-harness:belebele" --languages="ukr_Cyrl" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-l" --tasks="lm-eval-harness:belebele" --languages="mya_Mymr" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-xl" --tasks="lm-eval-harness:belebele" --languages="luo_Latn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:belebele" --languages="tir_Ethi" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:belebele" --languages="slv_Latn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-xl" --tasks="lm-eval-harness:belebele" --languages="ilo_Latn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:belebele" --languages="mya_Mymr" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="glot500" --tasks="lm-eval-harness:belebele" --languages="ory_Orya" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:belebele" --languages="tel_Telu" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:belebele" --languages="heb_Hebr" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:belebele" --languages="pes_Arab" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-xl" --tasks="lm-eval-harness:belebele" --languages="mya_Mymr" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:belebele" --languages="snd_Arab" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:belebele" --languages="ita_Latn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-l" --tasks="lm-eval-harness:belebele" --languages="gaz_Latn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-xl" --tasks="lm-eval-harness:belebele" --languages="als_Latn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-xl" --tasks="lm-eval-harness:belebele" --languages="ory_Orya" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-l" --tasks="lm-eval-harness:belebele" --languages="als_Latn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-l" --tasks="lm-eval-harness:belebele" --languages="ilo_Latn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-l" --tasks="lm-eval-harness:belebele" --languages="wol_Latn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-l" --tasks="lm-eval-harness:belebele" --languages="nso_Latn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-xl" --tasks="lm-eval-harness:belebele" --languages="tsn_Latn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:belebele" --languages="arz_Arab" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-l" --tasks="lm-eval-harness:belebele" --languages="sna_Latn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:belebele" --languages="khm_Khmr" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:belebele" --languages="urd_Latn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:belebele" --languages="pbt_Arab" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:belebele" --languages="kac_Latn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-l" --tasks="lm-eval-harness:belebele" --languages="ckb_Arab" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:belebele" --languages="nso_Latn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:belebele" --languages="spa_Latn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-xl" --tasks="lm-eval-harness:belebele" --languages="kea_Latn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="glot500" --tasks="lm-eval-harness:belebele" --languages="yor_Latn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:belebele" --languages="est_Latn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-xl" --tasks="lm-eval-harness:belebele" --languages="nso_Latn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="glot500" --tasks="lm-eval-harness:belebele" --languages="bod_Tibt" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:belebele" --languages="mar_Deva" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:belebele" --languages="asm_Beng" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:belebele" --languages="sot_Latn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:belebele" --languages="mlt_Latn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="glot500" --tasks="lm-eval-harness:belebele" --languages="tgl_Latn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-l" --tasks="lm-eval-harness:belebele" --languages="kan_Knda" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-l" --tasks="lm-eval-harness:belebele" --languages="lug_Latn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-xl" --tasks="lm-eval-harness:belebele" --languages="ben_Beng" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-xl" --tasks="lm-eval-harness:belebele" --languages="zul_Latn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:belebele" --languages="nya_Latn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="bloom1b7" --tasks="lm-eval-harness:belebele" --languages="ary_arab" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="xlmr-xl" --tasks="lm-eval-harness:belebele" --languages="sna_Latn" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"
python3 noctua2_run_evaluation.py --models="mbart" --tasks="lm-eval-harness:belebele" --languages="shn_Mymr" --results_dir="/scratch/hpc-prf-lola/nikit/repos/LOLA-Evaluate/lola_ws/evaluate/output-test"