MergeTrix-7B-v2-Nous.md

MergeTrix-7B-v2-Nous.md

Model	AGIEval	GPT4All	TruthfulQA	Bigbench	Average
MergeTrix-7B-v2	44.7	77.66	67.52	48.23	59.53

AGIEval

Task	Version	Metric	Value		Stderr
agieval_aqua_rat	0	acc	25.20	±	2.73
		acc_norm	24.80	±	2.72
agieval_logiqa_en	0	acc	39.32	±	1.92
		acc_norm	40.09	±	1.92
agieval_lsat_ar	0	acc	24.78	±	2.85
		acc_norm	23.48	±	2.80
agieval_lsat_lr	0	acc	50.59	±	2.22
		acc_norm	52.35	±	2.21
agieval_lsat_rc	0	acc	65.06	±	2.91
		acc_norm	65.06	±	2.91
agieval_sat_en	0	acc	79.61	±	2.81
		acc_norm	80.10	±	2.79
agieval_sat_en_without_passage	0	acc	42.23	±	3.45
		acc_norm	41.26	±	3.44
agieval_sat_math	0	acc	32.73	±	3.17
		acc_norm	30.45	±	3.11

Average: 44.7%

GPT4All

Task	Version	Metric	Value		Stderr
arc_challenge	0	acc	67.15	±	1.37
		acc_norm	67.83	±	1.37
arc_easy	0	acc	86.83	±	0.69
		acc_norm	82.49	±	0.78
boolq	1	acc	88.26	±	0.56
hellaswag	0	acc	70.20	±	0.46
		acc_norm	87.15	±	0.33
openbookqa	0	acc	38.40	±	2.18
		acc_norm	48.80	±	2.24
piqa	0	acc	83.62	±	0.86
		acc_norm	85.20	±	0.83
winogrande	0	acc	83.90	±	1.03

Average: 77.66%

TruthfulQA

Task	Version	Metric	Value		Stderr
truthfulqa_mc	1	mc1	53.98	±	1.74
		mc2	67.52	±	1.53

Average: 67.52%

Bigbench

Task	Version	Metric	Value		Stderr
bigbench_causal_judgement	0	multiple_choice_grade	58.42	±	3.59
bigbench_date_understanding	0	multiple_choice_grade	64.23	±	2.50
bigbench_disambiguation_qa	0	multiple_choice_grade	46.12	±	3.11
bigbench_geometric_shapes	0	multiple_choice_grade	22.84	±	2.22
		exact_str_match	0.28	±	0.28
bigbench_logical_deduction_five_objects	0	multiple_choice_grade	33.20	±	2.11
bigbench_logical_deduction_seven_objects	0	multiple_choice_grade	23.14	±	1.60
bigbench_logical_deduction_three_objects	0	multiple_choice_grade	55.67	±	2.87
bigbench_movie_recommendation	0	multiple_choice_grade	48.80	±	2.24
bigbench_navigate	0	multiple_choice_grade	54.70	±	1.57
bigbench_reasoning_about_colored_objects	0	multiple_choice_grade	71.55	±	1.01
bigbench_ruin_names	0	multiple_choice_grade	54.46	±	2.36
bigbench_salient_translation_error_detection	0	multiple_choice_grade	32.06	±	1.48
bigbench_snarks	0	multiple_choice_grade	78.45	±	3.06
bigbench_sports_understanding	0	multiple_choice_grade	74.95	±	1.38
bigbench_temporal_sequences	0	multiple_choice_grade	51.10	±	1.58
bigbench_tracking_shuffled_objects_five_objects	0	multiple_choice_grade	23.36	±	1.20
bigbench_tracking_shuffled_objects_seven_objects	0	multiple_choice_grade	19.49	±	0.95
bigbench_tracking_shuffled_objects_three_objects	0	multiple_choice_grade	55.67	±	2.87

Average: 48.23%

Average score: 59.53%

Elapsed time: 02:30:58