SauerkrautLM-Gemma-7b-Nous.md

Model	AGIEval	GPT4All	TruthfulQA	Bigbench	Average
SauerkrautLM-Gemma-7b	20.75	39.29	46.2	28.88	33.78

AGIEval

Task	Version	Metric	Value		Stderr
agieval_aqua_rat	0	acc	13.39	±	2.14
		acc_norm	14.96	±	2.24
agieval_logiqa_en	0	acc	23.20	±	1.66
		acc_norm	27.96	±	1.76
agieval_lsat_ar	0	acc	15.65	±	2.40
		acc_norm	16.52	±	2.45
agieval_lsat_lr	0	acc	14.71	±	1.57
		acc_norm	20.20	±	1.78
agieval_lsat_rc	0	acc	19.70	±	2.43
		acc_norm	21.19	±	2.50
agieval_sat_en	0	acc	23.30	±	2.95
		acc_norm	18.93	±	2.74
agieval_sat_en_without_passage	0	acc	21.36	±	2.86
		acc_norm	19.90	±	2.79
agieval_sat_math	0	acc	28.18	±	3.04
		acc_norm	26.36	±	2.98

Average: 20.75%

GPT4All

Task	Version	Metric	Value		Stderr
arc_challenge	0	acc	20.56	±	1.18
		acc_norm	24.06	±	1.25
arc_easy	0	acc	26.64	±	0.91
		acc_norm	29.08	±	0.93
boolq	1	acc	61.96	±	0.85
hellaswag	0	acc	26.16	±	0.44
		acc_norm	27.88	±	0.45
openbookqa	0	acc	15.20	±	1.61
		acc_norm	28.20	±	2.01
piqa	0	acc	55.06	±	1.16
		acc_norm	52.77	±	1.16
winogrande	0	acc	51.07	±	1.40

Average: 39.29%

TruthfulQA

Task	Version	Metric	Value		Stderr
truthfulqa_mc	1	mc1	22.28	±	1.46
		mc2	46.20	±	1.67

Average: 46.2%

Bigbench

Task	Version	Metric	Value		Stderr
bigbench_causal_judgement	0	multiple_choice_grade	52.11	±	3.63
bigbench_date_understanding	0	multiple_choice_grade	18.16	±	2.01
bigbench_disambiguation_qa	0	multiple_choice_grade	33.72	±	2.95
bigbench_geometric_shapes	0	multiple_choice_grade	4.46	±	1.09
		exact_str_match	0.00	±	0.00
bigbench_logical_deduction_five_objects	0	multiple_choice_grade	21.40	±	1.84
bigbench_logical_deduction_seven_objects	0	multiple_choice_grade	15.00	±	1.35
bigbench_logical_deduction_three_objects	0	multiple_choice_grade	37.33	±	2.80
bigbench_movie_recommendation	0	multiple_choice_grade	27.20	±	1.99
bigbench_navigate	0	multiple_choice_grade	50.80	±	1.58
bigbench_reasoning_about_colored_objects	0	multiple_choice_grade	19.05	±	0.88
bigbench_ruin_names	0	multiple_choice_grade	34.38	±	2.25
bigbench_salient_translation_error_detection	0	multiple_choice_grade	16.83	±	1.18
bigbench_snarks	0	multiple_choice_grade	42.54	±	3.69
bigbench_sports_understanding	0	multiple_choice_grade	49.70	±	1.59
bigbench_temporal_sequences	0	multiple_choice_grade	25.00	±	1.37
bigbench_tracking_shuffled_objects_five_objects	0	multiple_choice_grade	20.08	±	1.13
bigbench_tracking_shuffled_objects_seven_objects	0	multiple_choice_grade	14.69	±	0.85
bigbench_tracking_shuffled_objects_three_objects	0	multiple_choice_grade	37.33	±	2.80

Average: 28.88%

Average score: 33.78%

Elapsed time: 04:34:07