Gemmalpaca-7B-Nous.md

Model	AGIEval	GPT4All	TruthfulQA	Bigbench	Average
Gemmalpaca-7B	21.68	40.93	44.76	30.38	34.44

AGIEval

Task	Version	Metric	Value		Stderr
agieval_aqua_rat	0	acc	20.87	±	2.55
		acc_norm	21.26	±	2.57
agieval_logiqa_en	0	acc	21.04	±	1.60
		acc_norm	27.80	±	1.76
agieval_lsat_ar	0	acc	23.04	±	2.78
		acc_norm	25.22	±	2.87
agieval_lsat_lr	0	acc	18.24	±	1.71
		acc_norm	19.80	±	1.77
agieval_lsat_rc	0	acc	19.33	±	2.41
		acc_norm	15.99	±	2.24
agieval_sat_en	0	acc	26.21	±	3.07
		acc_norm	27.18	±	3.11
agieval_sat_en_without_passage	0	acc	22.33	±	2.91
		acc_norm	18.45	±	2.71
agieval_sat_math	0	acc	21.36	±	2.77
		acc_norm	17.73	±	2.58

Average: 21.68%

GPT4All

Task	Version	Metric	Value		Stderr
arc_challenge	0	acc	20.14	±	1.17
		acc_norm	22.27	±	1.22
arc_easy	0	acc	36.74	±	0.99
		acc_norm	34.13	±	0.97
boolq	1	acc	61.71	±	0.85
hellaswag	0	acc	30.15	±	0.46
		acc_norm	33.77	±	0.47
openbookqa	0	acc	16.60	±	1.67
		acc_norm	26.60	±	1.98
piqa	0	acc	59.14	±	1.15
		acc_norm	58.22	±	1.15
winogrande	0	acc	49.80	±	1.41

Average: 40.93%

TruthfulQA

Task	Version	Metric	Value		Stderr
truthfulqa_mc	1	mc1	25.21	±	1.52
		mc2	44.76	±	1.59

Average: 44.76%

Bigbench

Task	Version	Metric	Value		Stderr
bigbench_causal_judgement	0	multiple_choice_grade	53.68	±	3.63
bigbench_date_understanding	0	multiple_choice_grade	26.56	±	2.30
bigbench_disambiguation_qa	0	multiple_choice_grade	30.23	±	2.86
bigbench_geometric_shapes	0	multiple_choice_grade	10.03	±	1.59
		exact_str_match	0.00	±	0.00
bigbench_logical_deduction_five_objects	0	multiple_choice_grade	27.20	±	1.99
bigbench_logical_deduction_seven_objects	0	multiple_choice_grade	20.14	±	1.52
bigbench_logical_deduction_three_objects	0	multiple_choice_grade	40.33	±	2.84
bigbench_movie_recommendation	0	multiple_choice_grade	27.80	±	2.01
bigbench_navigate	0	multiple_choice_grade	50.00	±	1.58
bigbench_reasoning_about_colored_objects	0	multiple_choice_grade	23.65	±	0.95
bigbench_ruin_names	0	multiple_choice_grade	23.88	±	2.02
bigbench_salient_translation_error_detection	0	multiple_choice_grade	24.95	±	1.37
bigbench_snarks	0	multiple_choice_grade	53.59	±	3.72
bigbench_sports_understanding	0	multiple_choice_grade	49.80	±	1.59
bigbench_temporal_sequences	0	multiple_choice_grade	14.50	±	1.11
bigbench_tracking_shuffled_objects_five_objects	0	multiple_choice_grade	17.60	±	1.08
bigbench_tracking_shuffled_objects_seven_objects	0	multiple_choice_grade	12.57	±	0.79
bigbench_tracking_shuffled_objects_three_objects	0	multiple_choice_grade	40.33	±	2.84

Average: 30.38%

Average score: 34.44%

Elapsed time: 03:50:31