Skip to content

Instantly share code, notes, and snippets.

@CultriX-Github
Created February 23, 2024 00:48
Show Gist options
  • Save CultriX-Github/9761ba895dc35aef183411a11aa42857 to your computer and use it in GitHub Desktop.
Save CultriX-Github/9761ba895dc35aef183411a11aa42857 to your computer and use it in GitHub Desktop.
Model AGIEval GPT4All TruthfulQA Bigbench Average
DominaTrix-7B-v2 36.81 74.12 72.09 43.17 56.55

AGIEval

Task Version Metric Value Stderr
agieval_aqua_rat 0 acc 22.44 ± 2.62
acc_norm 22.44 ± 2.62
agieval_logiqa_en 0 acc 34.56 ± 1.87
acc_norm 35.18 ± 1.87
agieval_lsat_ar 0 acc 22.61 ± 2.76
acc_norm 21.74 ± 2.73
agieval_lsat_lr 0 acc 43.14 ± 2.20
acc_norm 43.73 ± 2.20
agieval_lsat_rc 0 acc 45.35 ± 3.04
acc_norm 44.98 ± 3.04
agieval_sat_en 0 acc 50.97 ± 3.49
acc_norm 49.51 ± 3.49
agieval_sat_en_without_passage 0 acc 45.63 ± 3.48
acc_norm 44.66 ± 3.47
agieval_sat_math 0 acc 35.91 ± 3.24
acc_norm 32.27 ± 3.16

Average: 36.81%

GPT4All

Task Version Metric Value Stderr
arc_challenge 0 acc 62.63 ± 1.41
acc_norm 63.74 ± 1.40
arc_easy 0 acc 84.26 ± 0.75
acc_norm 78.54 ± 0.84
boolq 1 acc 83.98 ± 0.64
hellaswag 0 acc 64.42 ± 0.48
acc_norm 84.65 ± 0.36
openbookqa 0 acc 37.80 ± 2.17
acc_norm 46.60 ± 2.23
piqa 0 acc 81.61 ± 0.90
acc_norm 83.30 ± 0.87
winogrande 0 acc 78.06 ± 1.16

Average: 74.12%

TruthfulQA

Task Version Metric Value Stderr
truthfulqa_mc 1 mc1 53.86 ± 1.75
mc2 72.09 ± 1.49

Average: 72.09%

Bigbench

Task Version Metric Value Stderr
bigbench_causal_judgement 0 multiple_choice_grade 56.84 ± 3.60
bigbench_date_understanding 0 multiple_choice_grade 59.89 ± 2.55
bigbench_disambiguation_qa 0 multiple_choice_grade 35.66 ± 2.99
bigbench_geometric_shapes 0 multiple_choice_grade 37.88 ± 2.56
exact_str_match 1.11 ± 0.55
bigbench_logical_deduction_five_objects 0 multiple_choice_grade 29.80 ± 2.05
bigbench_logical_deduction_seven_objects 0 multiple_choice_grade 21.71 ± 1.56
bigbench_logical_deduction_three_objects 0 multiple_choice_grade 51.00 ± 2.89
bigbench_movie_recommendation 0 multiple_choice_grade 58.00 ± 2.21
bigbench_navigate 0 multiple_choice_grade 50.90 ± 1.58
bigbench_reasoning_about_colored_objects 0 multiple_choice_grade 55.70 ± 1.11
bigbench_ruin_names 0 multiple_choice_grade 37.28 ± 2.29
bigbench_salient_translation_error_detection 0 multiple_choice_grade 25.15 ± 1.37
bigbench_snarks 0 multiple_choice_grade 62.43 ± 3.61
bigbench_sports_understanding 0 multiple_choice_grade 64.71 ± 1.52
bigbench_temporal_sequences 0 multiple_choice_grade 42.70 ± 1.56
bigbench_tracking_shuffled_objects_five_objects 0 multiple_choice_grade 20.88 ± 1.15
bigbench_tracking_shuffled_objects_seven_objects 0 multiple_choice_grade 15.54 ± 0.87
bigbench_tracking_shuffled_objects_three_objects 0 multiple_choice_grade 51.00 ± 2.89

Average: 43.17%

Average score: 56.55%

Elapsed time: 02:57:00

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