Marcoro14-7B-slerp-Nous.md

Model	AGIEval	GPT4ALL	TruthfulQA	Bigbench	Average
Marcoro14-7B-slerp	44.66	76.24	64.15	45.64	57.67

AGIEval

Task	Version	Metric	Value		Stderr
agieval_aqua_rat	0	acc	26.38	±	2.77
		acc_norm	24.41	±	2.70
agieval_logiqa_en	0	acc	38.25	±	1.91
		acc_norm	39.32	±	1.92
agieval_lsat_ar	0	acc	24.35	±	2.84
		acc_norm	25.22	±	2.87
agieval_lsat_lr	0	acc	50.00	±	2.22
		acc_norm	50.59	±	2.22
agieval_lsat_rc	0	acc	62.83	±	2.95
		acc_norm	62.08	±	2.96
agieval_sat_en	0	acc	79.61	±	2.81
		acc_norm	79.61	±	2.81
agieval_sat_en_without_passage	0	acc	45.15	±	3.48
		acc_norm	45.63	±	3.48
agieval_sat_math	0	acc	33.18	±	3.18
		acc_norm	30.45	±	3.11

Average: 44.66%

GPT4ALL

Task	Version	Metric	Value		Stderr
arc_challenge	0	acc	63.91	±	1.40
		acc_norm	64.93	±	1.39
arc_easy	0	acc	86.07	±	0.71
		acc_norm	83.75	±	0.76
boolq	1	acc	88.56	±	0.56
hellaswag	0	acc	67.31	±	0.47
		acc_norm	85.28	±	0.35
openbookqa	0	acc	36.40	±	2.15
		acc_norm	48.20	±	2.24
piqa	0	acc	82.59	±	0.88
		acc_norm	84.39	±	0.85
winogrande	0	acc	78.53	±	1.15

Average: 76.24%

TruthfulQA

Task	Version	Metric	Value		Stderr
truthfulqa_mc	1	mc1	46.88	±	1.75
		mc2	64.15	±	1.52

Average: 64.15%

Bigbench

Task	Version	Metric	Value		Stderr
bigbench_causal_judgement	0	multiple_choice_grade	56.32	±	3.61
bigbench_date_understanding	0	multiple_choice_grade	66.40	±	2.46
bigbench_disambiguation_qa	0	multiple_choice_grade	45.35	±	3.11
bigbench_geometric_shapes	0	multiple_choice_grade	20.33	±	2.13
		exact_str_match	4.74	±	1.12
bigbench_logical_deduction_five_objects	0	multiple_choice_grade	30.00	±	2.05
bigbench_logical_deduction_seven_objects	0	multiple_choice_grade	21.43	±	1.55
bigbench_logical_deduction_three_objects	0	multiple_choice_grade	52.33	±	2.89
bigbench_movie_recommendation	0	multiple_choice_grade	39.20	±	2.19
bigbench_navigate	0	multiple_choice_grade	53.90	±	1.58
bigbench_reasoning_about_colored_objects	0	multiple_choice_grade	72.15	±	1.00
bigbench_ruin_names	0	multiple_choice_grade	52.46	±	2.36
bigbench_salient_translation_error_detection	0	multiple_choice_grade	25.75	±	1.38
bigbench_snarks	0	multiple_choice_grade	72.38	±	3.33
bigbench_sports_understanding	0	multiple_choice_grade	73.63	±	1.40
bigbench_temporal_sequences	0	multiple_choice_grade	45.70	±	1.58
bigbench_tracking_shuffled_objects_five_objects	0	multiple_choice_grade	23.44	±	1.20
bigbench_tracking_shuffled_objects_seven_objects	0	multiple_choice_grade	18.51	±	0.93
bigbench_tracking_shuffled_objects_three_objects	0	multiple_choice_grade	52.33	±	2.89

Average: 45.64%

Average score: 57.67%