Task,13M GDN,13M MixerLoop,13M FullLoop,100M GDN,100M MixerLoop,100M FullLoop
hellaswag_zeroshot,0.034898,0.033526,0.029675,0.132842,0.133771,0.167231
jeopardy,0.000315,0.000157,0.000630,0.007085,0.006613,0.010392
bigbench_qa_wikidata,0.040106,0.031396,0.071863,0.214950,0.257074,0.282811
arc_easy,0.155069,0.152076,0.151702,0.317621,0.341190,0.385522
arc_challenge,-0.037922,-0.054228,-0.037543,-0.001138,0.018203,0.045506
copa,-0.113333,-0.093333,-0.120000,0.000000,0.020000,0.020000
commonsense_qa,-0.180258,-0.234217,-0.246564,-0.244278,-0.015177,-0.306011
piqa,0.162858,0.167211,0.166123,0.316649,0.334059,0.355822
openbook_qa,0.035556,0.041778,0.042667,0.090667,0.088000,0.098667
lambada_openai,0.105764,0.117407,0.116825,0.253639,0.246264,0.263536
hellaswag,0.028923,0.029277,0.023479,0.125938,0.126734,0.163513
winograd,0.072039,0.030525,0.050061,0.172161,0.113553,0.172161
winogrande,0.027624,0.020258,0.031834,0.027624,0.000789,0.029203
bigbench_dyck_languages,0.001333,0.008333,0.005667,0.128000,0.172000,0.093000
agi_eval_lsat_ar,-0.051208,-0.004831,-0.016425,-0.014493,0.072464,0.049275
bigbench_cs_algorithms,0.239394,0.306566,0.221717,0.351515,0.351515,0.352273
bigbench_operators,0.134921,0.139683,0.139682,0.095238,0.090476,0.090476
bigbench_repeat_copy_logic,0.000000,0.000000,0.000000,0.000000,0.000000,0.000000
squad,0.013844,0.008514,0.011542,0.070766,0.047114,0.049669
coqa,0.044135,0.031484,0.036077,0.113366,0.116623,0.123888
boolq,-0.408874,-0.361661,-0.354418,-0.187832,-0.059070,-0.054241
bigbench_language_identification,0.001689,0.007733,0.002755,-0.003467,0.010000,0.002533
Core,0.013949,0.017166,0.014880,0.089402,0.112373,0.108874