phi-2-instruct-Nous.md

Model	AGIEval	GPT4All	TruthfulQA	Bigbench	Average
phi-2-instruct	25.8	67.93	44.82	36.88	43.86

AGIEval

Task	Version	Metric	Value		Stderr
agieval_aqua_rat	0	acc	16.14	±	2.31
		acc_norm	18.90	±	2.46
agieval_logiqa_en	0	acc	26.88	±	1.74
		acc_norm	30.88	±	1.81
agieval_lsat_ar	0	acc	16.52	±	2.45
		acc_norm	18.26	±	2.55
agieval_lsat_lr	0	acc	29.41	±	2.02
		acc_norm	27.45	±	1.98
agieval_lsat_rc	0	acc	28.25	±	2.75
		acc_norm	23.42	±	2.59
agieval_sat_en	0	acc	39.81	±	3.42
		acc_norm	33.01	±	3.28
agieval_sat_en_without_passage	0	acc	34.95	±	3.33
		acc_norm	28.16	±	3.14
agieval_sat_math	0	acc	25.45	±	2.94
		acc_norm	26.36	±	2.98

Average: 25.8%

GPT4All

Task	Version	Metric	Value		Stderr
arc_challenge	0	acc	48.98	±	1.46
		acc_norm	49.66	±	1.46
arc_easy	0	acc	79.12	±	0.83
		acc_norm	71.80	±	0.92
boolq	1	acc	83.46	±	0.65
hellaswag	0	acc	52.70	±	0.50
		acc_norm	71.10	±	0.45
openbookqa	0	acc	33.60	±	2.11
		acc_norm	43.80	±	2.22
piqa	0	acc	79.71	±	0.94
		acc_norm	78.94	±	0.95
winogrande	0	acc	76.72	±	1.19

Average: 67.93%

TruthfulQA

Task	Version	Metric	Value		Stderr
truthfulqa_mc	1	mc1	31.58	±	1.63
		mc2	44.82	±	1.51

Average: 44.82%

Bigbench

Task	Version	Metric	Value		Stderr
bigbench_causal_judgement	0	multiple_choice_grade	57.37	±	3.60
bigbench_date_understanding	0	multiple_choice_grade	58.27	±	2.57
bigbench_disambiguation_qa	0	multiple_choice_grade	40.70	±	3.06
bigbench_geometric_shapes	0	multiple_choice_grade	7.52	±	1.39
		exact_str_match	0.00	±	0.00
bigbench_logical_deduction_five_objects	0	multiple_choice_grade	23.80	±	1.91
bigbench_logical_deduction_seven_objects	0	multiple_choice_grade	17.86	±	1.45
bigbench_logical_deduction_three_objects	0	multiple_choice_grade	43.33	±	2.87
bigbench_movie_recommendation	0	multiple_choice_grade	33.20	±	2.11
bigbench_navigate	0	multiple_choice_grade	49.40	±	1.58
bigbench_reasoning_about_colored_objects	0	multiple_choice_grade	61.15	±	1.09
bigbench_ruin_names	0	multiple_choice_grade	27.23	±	2.11
bigbench_salient_translation_error_detection	0	multiple_choice_grade	24.95	±	1.37
bigbench_snarks	0	multiple_choice_grade	72.38	±	3.33
bigbench_sports_understanding	0	multiple_choice_grade	49.70	±	1.59
bigbench_temporal_sequences	0	multiple_choice_grade	21.50	±	1.30
bigbench_tracking_shuffled_objects_five_objects	0	multiple_choice_grade	18.96	±	1.11
bigbench_tracking_shuffled_objects_seven_objects	0	multiple_choice_grade	13.26	±	0.81
bigbench_tracking_shuffled_objects_three_objects	0	multiple_choice_grade	43.33	±	2.87

Average: 36.88%

Average score: 43.86%

Elapsed time: 02:02:47