mlabonne/Daredevil-8B-Nous.md Secret

Created May 25, 2024 22:21

Star (0) You must be signed in to star a gist
Fork (0) You must be signed in to fork a gist

Select an option

Learn more about clone URLs
Clone this repository at <script src="https://gist.github.com/mlabonne/080f9c5f153ea57a7ab7d932cf896f21.js"></script>
Save mlabonne/080f9c5f153ea57a7ab7d932cf896f21 to your computer and use it in GitHub Desktop.

Download ZIP

Raw

Daredevil-8B-Nous.md

Model	AGIEval	GPT4All	TruthfulQA	Bigbench	Average
Daredevil-8B	44.13	73.52	59.05	46.77	55.87

AGIEval

Task	Version	Metric	Value		Stderr
agieval_aqua_rat	0	acc	28.74	±	2.85
		acc_norm	27.17	±	2.80
agieval_logiqa_en	0	acc	38.25	±	1.91
		acc_norm	39.32	±	1.92
agieval_lsat_ar	0	acc	21.30	±	2.71
		acc_norm	20.43	±	2.66
agieval_lsat_lr	0	acc	46.67	±	2.21
		acc_norm	46.67	±	2.21
agieval_lsat_rc	0	acc	68.03	±	2.85
		acc_norm	66.17	±	2.89
agieval_sat_en	0	acc	75.24	±	3.01
		acc_norm	73.30	±	3.09
agieval_sat_en_without_passage	0	acc	44.66	±	3.47
		acc_norm	42.72	±	3.45
agieval_sat_math	0	acc	41.36	±	3.33
		acc_norm	37.27	±	3.27

Average: 44.13%

GPT4All

Task	Version	Metric	Value		Stderr
arc_challenge	0	acc	61.35	±	1.42
		acc_norm	63.31	±	1.41
arc_easy	0	acc	84.89	±	0.73
		acc_norm	83.96	±	0.75
boolq	1	acc	84.83	±	0.63
hellaswag	0	acc	62.30	±	0.48
		acc_norm	80.98	±	0.39
openbookqa	0	acc	36.00	±	2.15
		acc_norm	46.00	±	2.23
piqa	0	acc	80.36	±	0.93
		acc_norm	81.39	±	0.91
winogrande	0	acc	74.19	±	1.23

Average: 73.52%

TruthfulQA

Task	Version	Metric	Value		Stderr
truthfulqa_mc	1	mc1	41.49	±	1.72
		mc2	59.05	±	1.53

Average: 59.05%

Bigbench

Task	Version	Metric	Value		Stderr
bigbench_causal_judgement	0	multiple_choice_grade	60.53	±	3.56
bigbench_date_understanding	0	multiple_choice_grade	69.65	±	2.40
bigbench_disambiguation_qa	0	multiple_choice_grade	34.88	±	2.97
bigbench_geometric_shapes	0	multiple_choice_grade	31.20	±	2.45
		exact_str_match	0.00	±	0.00
bigbench_logical_deduction_five_objects	0	multiple_choice_grade	35.40	±	2.14
bigbench_logical_deduction_seven_objects	0	multiple_choice_grade	24.71	±	1.63
bigbench_logical_deduction_three_objects	0	multiple_choice_grade	65.33	±	2.75
bigbench_movie_recommendation	0	multiple_choice_grade	33.60	±	2.11
bigbench_navigate	0	multiple_choice_grade	54.70	±	1.57
bigbench_reasoning_about_colored_objects	0	multiple_choice_grade	69.40	±	1.03
bigbench_ruin_names	0	multiple_choice_grade	49.78	±	2.36
bigbench_salient_translation_error_detection	0	multiple_choice_grade	31.46	±	1.47
bigbench_snarks	0	multiple_choice_grade	62.43	±	3.61
bigbench_sports_understanding	0	multiple_choice_grade	51.52	±	1.59
bigbench_temporal_sequences	0	multiple_choice_grade	62.10	±	1.53
bigbench_tracking_shuffled_objects_five_objects	0	multiple_choice_grade	22.16	±	1.18
bigbench_tracking_shuffled_objects_seven_objects	0	multiple_choice_grade	17.66	±	0.91
bigbench_tracking_shuffled_objects_three_objects	0	multiple_choice_grade	65.33	±	2.75

Average: 46.77%

Average score: 55.87%

Elapsed time: 03:17:26

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment