File size: 62,878 Bytes
6571f40
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
c127ce7
6571f40
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
{
  "results": {
    "bbh_fewshot": {
      "exact_match,none": 0.0,
      "exact_match_stderr,none": 0.0,
      "alias": "bbh_fewshot"
    },
    "bbh_fewshot_boolean_expressions": {
      "exact_match,none": 0.0,
      "exact_match_stderr,none": 0.0,
      "alias": " - bbh_fewshot_boolean_expressions"
    },
    "bbh_fewshot_causal_judgement": {
      "exact_match,none": 0.0,
      "exact_match_stderr,none": 0.0,
      "alias": " - bbh_fewshot_causal_judgement"
    },
    "bbh_fewshot_date_understanding": {
      "exact_match,none": 0.0,
      "exact_match_stderr,none": 0.0,
      "alias": " - bbh_fewshot_date_understanding"
    },
    "bbh_fewshot_disambiguation_qa": {
      "exact_match,none": 0.0,
      "exact_match_stderr,none": 0.0,
      "alias": " - bbh_fewshot_disambiguation_qa"
    },
    "bbh_fewshot_dyck_languages": {
      "exact_match,none": 0.0,
      "exact_match_stderr,none": 0.0,
      "alias": " - bbh_fewshot_dyck_languages"
    },
    "bbh_fewshot_formal_fallacies": {
      "exact_match,none": 0.0,
      "exact_match_stderr,none": 0.0,
      "alias": " - bbh_fewshot_formal_fallacies"
    },
    "bbh_fewshot_geometric_shapes": {
      "exact_match,none": 0.0,
      "exact_match_stderr,none": 0.0,
      "alias": " - bbh_fewshot_geometric_shapes"
    },
    "bbh_fewshot_hyperbaton": {
      "exact_match,none": 0.0,
      "exact_match_stderr,none": 0.0,
      "alias": " - bbh_fewshot_hyperbaton"
    },
    "bbh_fewshot_logical_deduction_five_objects": {
      "exact_match,none": 0.0,
      "exact_match_stderr,none": 0.0,
      "alias": " - bbh_fewshot_logical_deduction_five_objects"
    },
    "bbh_fewshot_logical_deduction_seven_objects": {
      "exact_match,none": 0.0,
      "exact_match_stderr,none": 0.0,
      "alias": " - bbh_fewshot_logical_deduction_seven_objects"
    },
    "bbh_fewshot_logical_deduction_three_objects": {
      "exact_match,none": 0.0,
      "exact_match_stderr,none": 0.0,
      "alias": " - bbh_fewshot_logical_deduction_three_objects"
    },
    "bbh_fewshot_movie_recommendation": {
      "exact_match,none": 0.0,
      "exact_match_stderr,none": 0.0,
      "alias": " - bbh_fewshot_movie_recommendation"
    },
    "bbh_fewshot_multistep_arithmetic_two": {
      "exact_match,none": 0.0,
      "exact_match_stderr,none": 0.0,
      "alias": " - bbh_fewshot_multistep_arithmetic_two"
    },
    "bbh_fewshot_navigate": {
      "exact_match,none": 0.0,
      "exact_match_stderr,none": 0.0,
      "alias": " - bbh_fewshot_navigate"
    },
    "bbh_fewshot_object_counting": {
      "exact_match,none": 0.0,
      "exact_match_stderr,none": 0.0,
      "alias": " - bbh_fewshot_object_counting"
    },
    "bbh_fewshot_penguins_in_a_table": {
      "exact_match,none": 0.0,
      "exact_match_stderr,none": 0.0,
      "alias": " - bbh_fewshot_penguins_in_a_table"
    },
    "bbh_fewshot_reasoning_about_colored_objects": {
      "exact_match,none": 0.0,
      "exact_match_stderr,none": 0.0,
      "alias": " - bbh_fewshot_reasoning_about_colored_objects"
    },
    "bbh_fewshot_ruin_names": {
      "exact_match,none": 0.0,
      "exact_match_stderr,none": 0.0,
      "alias": " - bbh_fewshot_ruin_names"
    },
    "bbh_fewshot_salient_translation_error_detection": {
      "exact_match,none": 0.0,
      "exact_match_stderr,none": 0.0,
      "alias": " - bbh_fewshot_salient_translation_error_detection"
    },
    "bbh_fewshot_snarks": {
      "exact_match,none": 0.0,
      "exact_match_stderr,none": 0.0,
      "alias": " - bbh_fewshot_snarks"
    },
    "bbh_fewshot_sports_understanding": {
      "exact_match,none": 0.0,
      "exact_match_stderr,none": 0.0,
      "alias": " - bbh_fewshot_sports_understanding"
    },
    "bbh_fewshot_temporal_sequences": {
      "exact_match,none": 0.0,
      "exact_match_stderr,none": 0.0,
      "alias": " - bbh_fewshot_temporal_sequences"
    },
    "bbh_fewshot_tracking_shuffled_objects_five_objects": {
      "exact_match,none": 0.0,
      "exact_match_stderr,none": 0.0,
      "alias": " - bbh_fewshot_tracking_shuffled_objects_five_objects"
    },
    "bbh_fewshot_tracking_shuffled_objects_seven_objects": {
      "exact_match,none": 0.0,
      "exact_match_stderr,none": 0.0,
      "alias": " - bbh_fewshot_tracking_shuffled_objects_seven_objects"
    },
    "bbh_fewshot_tracking_shuffled_objects_three_objects": {
      "exact_match,none": 0.0,
      "exact_match_stderr,none": 0.0,
      "alias": " - bbh_fewshot_tracking_shuffled_objects_three_objects"
    },
    "bbh_fewshot_web_of_lies": {
      "exact_match,none": 0.0,
      "exact_match_stderr,none": 0.0,
      "alias": " - bbh_fewshot_web_of_lies"
    },
    "bbh_fewshot_word_sorting": {
      "exact_match,none": 0.0,
      "exact_match_stderr,none": 0.0,
      "alias": " - bbh_fewshot_word_sorting"
    }
  },
  "groups": {
    "bbh_fewshot": {
      "exact_match,none": 0.0,
      "exact_match_stderr,none": 0.0,
      "alias": "bbh_fewshot"
    }
  },
  "configs": {
    "bbh_fewshot_boolean_expressions": {
      "task": "bbh_fewshot_boolean_expressions",
      "group": "bbh_fewshot",
      "dataset_path": "lukaemon/bbh",
      "dataset_name": "boolean_expressions",
      "test_split": "test",
      "doc_to_text": "Q: not ( ( not not True ) ) is\nA: False\n\nQ: True and False and not True and True is\nA: False\n\nQ: not not ( not ( False ) ) is\nA: True\n\nQ: {{input}}\nA:",
      "doc_to_target": "{{target}}",
      "description": "Evaluate the result of a random Boolean expression.\n\n",
      "target_delimiter": " ",
      "fewshot_delimiter": "\n\n",
      "num_fewshot": 0,
      "metric_list": [
        {
          "metric": "exact_match",
          "aggregation": "mean",
          "higher_is_better": true
        }
      ],
      "output_type": "generate_until",
      "generation_kwargs": {
        "until": [
          "</s>",
          "Q",
          "\n\n"
        ],
        "do_sample": false,
        "temperature": 0.0
      },
      "repeats": 1,
      "should_decontaminate": false,
      "metadata": {
        "version": 1.0,
        "num_fewshot": 3
      }
    },
    "bbh_fewshot_causal_judgement": {
      "task": "bbh_fewshot_causal_judgement",
      "group": "bbh_fewshot",
      "dataset_path": "lukaemon/bbh",
      "dataset_name": "causal_judgement",
      "test_split": "test",
      "doc_to_text": "Q: How would a typical person answer each of the following questions about causation?\nFrank T., had an ongoing dispute with his neighbor over a stretch of land and one day decided to shoot his neighbor in the body. Frank T. had no experience with guns, his hand slipped on the barrel of the gun, and the shot went wild. Nonetheless, the bullet bounced off a large boulder several feet away and hit the neighbor's body, causing significant injury. Did Frank T. intentionally shoot his neighbor in the body?\nOptions:\n- Yes\n- No\nA: No\n\nQ: How would a typical person answer each of the following questions about causation?\nSuzy and Billy are working on a project that is very important for our nation's security. The boss tells them both: \"Be sure that you are here at exactly 9 am. It is absolutely essential that you arrive at that time.\" Both Billy and Suzy arrive at 9 am. As it happens, there was a motion detector installed in the room where they arrived. The motion detector was set up to be triggered if at least one person appeared in the room at the same time. So the motion detector went off. Did Billy cause the motion detector to go off?\nOptions:\n- Yes\n- No\nA: Yes\n\nQ: How would a typical person answer each of the following questions about causation?\nGeorge and his sister Lena reunite at their parents' house for Thanksgiving. Whereas George just got into medical school, Lena is unhappy in her marriage and recently lost her job. Over the course of the day, George and Lena get into a number of heated arguments. Later in the afternoon they play a game of darts. They split the first two games, and the third game is close until the end. Who will win comes down to George's last shot. If he hits a high point region, he wins; if he hits a low point region, Lena wins. George thinks of the difficult time Lena is having, and he really wants to let her win. He aims the dart at the low point region. He sets up his shot and the dart lands in the low point region. After his shot, Lena wins the game and is very happy. Did George hit the low point region intentionally?\nOptions:\n- Yes\n- No\nA: Yes\n\nQ: {{input}}\nA:",
      "doc_to_target": "{{target}}",
      "description": "Answer questions about causal attribution.\n\n",
      "target_delimiter": " ",
      "fewshot_delimiter": "\n\n",
      "num_fewshot": 0,
      "metric_list": [
        {
          "metric": "exact_match",
          "aggregation": "mean",
          "higher_is_better": true
        }
      ],
      "output_type": "generate_until",
      "generation_kwargs": {
        "until": [
          "</s>",
          "Q",
          "\n\n"
        ],
        "do_sample": false,
        "temperature": 0.0
      },
      "repeats": 1,
      "should_decontaminate": false,
      "metadata": {
        "version": 1.0,
        "num_fewshot": 3
      }
    },
    "bbh_fewshot_date_understanding": {
      "task": "bbh_fewshot_date_understanding",
      "group": "bbh_fewshot",
      "dataset_path": "lukaemon/bbh",
      "dataset_name": "date_understanding",
      "test_split": "test",
      "doc_to_text": "Q: Today is Christmas Eve of 1937. What is the date 10 days ago in MM/DD/YYYY?\nOptions:\n(A) 12/14/2026\n(B) 12/14/1950\n(C) 12/14/2007\n(D) 12/14/1937\n(E) 07/14/1938\n(F) 12/14/1988\nA: (D)\n\nQ: Tomorrow is 11/12/2019. What is the date one year ago from today in MM/DD/YYYY?\nOptions:\n(A) 09/04/2018\n(B) 11/11/2018\n(C) 08/25/2018\n(D) 11/02/2018\n(E) 11/04/2018\nA: (B)\n\nQ: Jane and John married on Jan 2, 1958. It is their 5-year anniversary today. What is the date tomorrow in MM/DD/YYYY?\nOptions:\n(A) 01/11/1961\n(B) 01/03/1963\n(C) 01/18/1961\n(D) 10/14/1960\n(E) 01/03/1982\n(F) 12/03/1960\nA: (B)\n\nQ: {{input}}\nA:",
      "doc_to_target": "{{target}}",
      "description": "Infer the date from context.\n\n",
      "target_delimiter": " ",
      "fewshot_delimiter": "\n\n",
      "num_fewshot": 0,
      "metric_list": [
        {
          "metric": "exact_match",
          "aggregation": "mean",
          "higher_is_better": true
        }
      ],
      "output_type": "generate_until",
      "generation_kwargs": {
        "until": [
          "</s>",
          "Q",
          "\n\n"
        ],
        "do_sample": false,
        "temperature": 0.0
      },
      "repeats": 1,
      "should_decontaminate": false,
      "metadata": {
        "version": 1.0,
        "num_fewshot": 3
      }
    },
    "bbh_fewshot_disambiguation_qa": {
      "task": "bbh_fewshot_disambiguation_qa",
      "group": "bbh_fewshot",
      "dataset_path": "lukaemon/bbh",
      "dataset_name": "disambiguation_qa",
      "test_split": "test",
      "doc_to_text": "Q: In the following sentences, explain the antecedent of the pronoun (which thing the pronoun refers to), or state that it is ambiguous.\nSentence: The chief told the counselor that they took the day off.\nOptions:\n(A) The chief took the day off\n(B) The counselor took the day off\n(C) Ambiguous\nA: (A)\n\nQ: In the following sentences, explain the antecedent of the pronoun (which thing the pronoun refers to), or state that it is ambiguous.\nSentence: The manager sent a message to the secretary, but he didn't reply yet.\nOptions:\n(A) The secretary didn't reply yet\n(B) The manager didn't reply yet\n(C) Ambiguous\nA: (A)\n\nQ: In the following sentences, explain the antecedent of the pronoun (which thing the pronoun refers to), or state that it is ambiguous.\nSentence: Bailey will plan to meet the director at his office\nOptions:\n(A) It will be Bailey's office\n(B) It will be the director's office\n(C) Ambiguous\nA: (C)\n\nQ: {{input}}\nA:",
      "doc_to_target": "{{target}}",
      "description": "Clarify the meaning of sentences with ambiguous pronouns.\n\n",
      "target_delimiter": " ",
      "fewshot_delimiter": "\n\n",
      "num_fewshot": 0,
      "metric_list": [
        {
          "metric": "exact_match",
          "aggregation": "mean",
          "higher_is_better": true
        }
      ],
      "output_type": "generate_until",
      "generation_kwargs": {
        "until": [
          "</s>",
          "Q",
          "\n\n"
        ],
        "do_sample": false,
        "temperature": 0.0
      },
      "repeats": 1,
      "should_decontaminate": false,
      "metadata": {
        "version": 1.0,
        "num_fewshot": 3
      }
    },
    "bbh_fewshot_dyck_languages": {
      "task": "bbh_fewshot_dyck_languages",
      "group": "bbh_fewshot",
      "dataset_path": "lukaemon/bbh",
      "dataset_name": "dyck_languages",
      "test_split": "test",
      "doc_to_text": "Q: Complete the rest of the sequence, making sure that the parentheses are closed properly. Input: [ { [\nA: ] } ]\n\nQ: Complete the rest of the sequence, making sure that the parentheses are closed properly. Input: < > ( ( [ [ ( { } ) [ < > ] ]\nA: ] ) )\n\nQ: Complete the rest of the sequence, making sure that the parentheses are closed properly. Input: < [ < [ { < [ ] < { } > > } ] > { { ( ) } { < [ < > ] > }\nA: } ] >\n\nQ: {{input}}\nA:",
      "doc_to_target": "{{target}}",
      "description": "Correctly close a Dyck-n word.\n\n",
      "target_delimiter": " ",
      "fewshot_delimiter": "\n\n",
      "num_fewshot": 0,
      "metric_list": [
        {
          "metric": "exact_match",
          "aggregation": "mean",
          "higher_is_better": true
        }
      ],
      "output_type": "generate_until",
      "generation_kwargs": {
        "until": [
          "</s>",
          "Q",
          "\n\n"
        ],
        "do_sample": false,
        "temperature": 0.0
      },
      "repeats": 1,
      "should_decontaminate": false,
      "metadata": {
        "version": 1.0,
        "num_fewshot": 3
      }
    },
    "bbh_fewshot_formal_fallacies": {
      "task": "bbh_fewshot_formal_fallacies",
      "group": "bbh_fewshot",
      "dataset_path": "lukaemon/bbh",
      "dataset_name": "formal_fallacies",
      "test_split": "test",
      "doc_to_text": "Q: \"It is not always easy to see who is related to whom -- and in which ways. The following argument pertains to this question: To begin with, Lesley is a close friend of Fernando. Moreover, being a close friend of Fernando or a schoolmate of Lowell is sufficient for being a great-grandfather of Leroy. It follows that Lesley is a great-grandfather of Leroy.\"\nIs the argument, given the explicitly stated premises, deductively valid or invalid?\nOptions:\n- valid\n- invalid\nA: valid\n\nQ: \"It is not always easy to see who is related to whom -- and in which ways. The following argument pertains to this question: Whoever is not a great-grandfather of Clyde is a stepbrother of Brian. Being an ancestor of Dana is sufficient for not being a great-grandfather of Clyde. We may conclude: Everyone who is an ancestor of Dana is a stepbrother of Brian, too.\"\nIs the argument, given the explicitly stated premises, deductively valid or invalid?\nOptions:\n- valid\n- invalid\nA: valid\n\nQ: \"It is not always easy to grasp who is consuming which products. The following argument pertains to this question: Every infrequent user of Paul Mitchell shampoo is either a rare consumer of Nioxin shampoo or a loyal buyer of Caress soap, or both. No regular consumer of Lush soap is a rare consumer of Nioxin shampoo and, in the same time, a loyal buyer of Caress soap. It follows that whoever is an infrequent user of Paul Mitchell shampoo is not a regular consumer of Lush soap.\"\nIs the argument, given the explicitly stated premises, deductively valid or invalid?\nOptions:\n- valid\n- invalid\nA: invalid\n\nQ: {{input}}\nA:",
      "doc_to_target": "{{target}}",
      "description": "Distinguish deductively valid arguments from formal fallacies.\n\n",
      "target_delimiter": " ",
      "fewshot_delimiter": "\n\n",
      "num_fewshot": 0,
      "metric_list": [
        {
          "metric": "exact_match",
          "aggregation": "mean",
          "higher_is_better": true
        }
      ],
      "output_type": "generate_until",
      "generation_kwargs": {
        "until": [
          "</s>",
          "Q",
          "\n\n"
        ],
        "do_sample": false,
        "temperature": 0.0
      },
      "repeats": 1,
      "should_decontaminate": false,
      "metadata": {
        "version": 1.0,
        "num_fewshot": 3
      }
    },
    "bbh_fewshot_geometric_shapes": {
      "task": "bbh_fewshot_geometric_shapes",
      "group": "bbh_fewshot",
      "dataset_path": "lukaemon/bbh",
      "dataset_name": "geometric_shapes",
      "test_split": "test",
      "doc_to_text": "Q: This SVG path element <path d=\"M 31.00,73.00 L 32.00,59.00 L 44.00,50.00 L 49.00,41.00 L 64.00,37.00 L 71.00,55.00 L 64.00,76.00 L 52.00,61.00 L 31.00,73.00\"/> draws a\nOptions:\n(A) circle\n(B) heptagon\n(C) hexagon\n(D) kite\n(E) line\n(F) octagon\n(G) pentagon\n(H) rectangle\n(I) sector\n(J) triangle\nA: (F)\n\nQ: This SVG path element <path d=\"M 14.19,26.04 L 51.43,39.21 L 58.44,36.69 L 56.63,30.17 L 48.53,26.66 L 14.19,26.04\"/> draws a\nOptions:\n(A) circle\n(B) heptagon\n(C) hexagon\n(D) kite\n(E) line\n(F) octagon\n(G) pentagon\n(H) rectangle\n(I) sector\n(J) triangle\nA: (G)\n\nQ: This SVG path element <path d=\"M 41.00,43.00 L 37.00,34.00 L 41.00,33.00 L 45.00,34.00 L 41.00,43.00\"/> draws a\nOptions:\n(A) circle\n(B) heptagon\n(C) hexagon\n(D) kite\n(E) line\n(F) octagon\n(G) pentagon\n(H) rectangle\n(I) sector\n(J) triangle\nA: (D)\n\nQ: {{input}}\nA:",
      "doc_to_target": "{{target}}",
      "description": "Name geometric shapes from their SVG paths.\n\n",
      "target_delimiter": " ",
      "fewshot_delimiter": "\n\n",
      "num_fewshot": 0,
      "metric_list": [
        {
          "metric": "exact_match",
          "aggregation": "mean",
          "higher_is_better": true
        }
      ],
      "output_type": "generate_until",
      "generation_kwargs": {
        "until": [
          "</s>",
          "Q",
          "\n\n"
        ],
        "do_sample": false,
        "temperature": 0.0
      },
      "repeats": 1,
      "should_decontaminate": false,
      "metadata": {
        "version": 1.0,
        "num_fewshot": 3
      }
    },
    "bbh_fewshot_hyperbaton": {
      "task": "bbh_fewshot_hyperbaton",
      "group": "bbh_fewshot",
      "dataset_path": "lukaemon/bbh",
      "dataset_name": "hyperbaton",
      "test_split": "test",
      "doc_to_text": "Q: Which sentence has the correct adjective order:\nOptions:\n(A) rubber terrible ship\n(B) terrible rubber ship\nA: (B)\n\nQ: Which sentence has the correct adjective order:\nOptions:\n(A) repulsive small Brazilian exercise ship\n(B) Brazilian repulsive exercise small ship\nA: (A)\n\nQ: Which sentence has the correct adjective order:\nOptions:\n(A) blue gold wonderful square shoe\n(B) wonderful square blue gold shoe\nA: (B)\n\nQ: {{input}}\nA:",
      "doc_to_target": "{{target}}",
      "description": "Order adjectives correctly in English sentences.\n\n",
      "target_delimiter": " ",
      "fewshot_delimiter": "\n\n",
      "num_fewshot": 0,
      "metric_list": [
        {
          "metric": "exact_match",
          "aggregation": "mean",
          "higher_is_better": true
        }
      ],
      "output_type": "generate_until",
      "generation_kwargs": {
        "until": [
          "</s>",
          "Q",
          "\n\n"
        ],
        "do_sample": false,
        "temperature": 0.0
      },
      "repeats": 1,
      "should_decontaminate": false,
      "metadata": {
        "version": 1.0,
        "num_fewshot": 3
      }
    },
    "bbh_fewshot_logical_deduction_five_objects": {
      "task": "bbh_fewshot_logical_deduction_five_objects",
      "group": "bbh_fewshot",
      "dataset_path": "lukaemon/bbh",
      "dataset_name": "logical_deduction_five_objects",
      "test_split": "test",
      "doc_to_text": "Q: The following paragraphs each describe a set of three objects arranged in a fixed order. The statements are logically consistent within each paragraph. In a golf tournament, there were three golfers: Amy, Eli, and Eve. Eve finished above Amy. Eli finished below Amy.\nOptions:\n(A) Amy finished last\n(B) Eli finished last\n(C) Eve finished last\nA: (B)\n\nQ: The following paragraphs each describe a set of three objects arranged in a fixed order. The statements are logically consistent within each paragraph. On a shelf, there are three books: a white book, a green book, and an orange book. The green book is to the right of the white book. The orange book is the rightmost.\nOptions:\n(A) The white book is the leftmost\n(B) The green book is the leftmost\n(C) The orange book is the leftmost\nA: (A)\n\nQ: The following paragraphs each describe a set of three objects arranged in a fixed order. The statements are logically consistent within each paragraph. On a shelf, there are three books: a red book, a gray book, and a white book. The white book is to the left of the gray book. The red book is the second from the left.\nOptions:\n(A) The red book is the leftmost\n(B) The gray book is the leftmost\n(C) The white book is the leftmost\nA: (C)\n\nQ: {{input}}\nA:",
      "doc_to_target": "{{target}}",
      "description": "A logical deduction task which requires deducing the order of a sequence of objects.\n\n",
      "target_delimiter": " ",
      "fewshot_delimiter": "\n\n",
      "num_fewshot": 0,
      "metric_list": [
        {
          "metric": "exact_match",
          "aggregation": "mean",
          "higher_is_better": true
        }
      ],
      "output_type": "generate_until",
      "generation_kwargs": {
        "until": [
          "</s>",
          "Q",
          "\n\n"
        ],
        "do_sample": false,
        "temperature": 0.0
      },
      "repeats": 1,
      "should_decontaminate": false,
      "metadata": {
        "version": 1.0,
        "num_fewshot": 3
      }
    },
    "bbh_fewshot_logical_deduction_seven_objects": {
      "task": "bbh_fewshot_logical_deduction_seven_objects",
      "group": "bbh_fewshot",
      "dataset_path": "lukaemon/bbh",
      "dataset_name": "logical_deduction_seven_objects",
      "test_split": "test",
      "doc_to_text": "Q: The following paragraphs each describe a set of three objects arranged in a fixed order. The statements are logically consistent within each paragraph. In a golf tournament, there were three golfers: Amy, Eli, and Eve. Eve finished above Amy. Eli finished below Amy.\nOptions:\n(A) Amy finished last\n(B) Eli finished last\n(C) Eve finished last\nA: (B)\n\nQ: The following paragraphs each describe a set of three objects arranged in a fixed order. The statements are logically consistent within each paragraph. On a shelf, there are three books: a white book, a green book, and an orange book. The green book is to the right of the white book. The orange book is the rightmost.\nOptions:\n(A) The white book is the leftmost\n(B) The green book is the leftmost\n(C) The orange book is the leftmost\nA: (A)\n\nQ: The following paragraphs each describe a set of three objects arranged in a fixed order. The statements are logically consistent within each paragraph. On a shelf, there are three books: a red book, a gray book, and a white book. The white book is to the left of the gray book. The red book is the second from the left.\nOptions:\n(A) The red book is the leftmost\n(B) The gray book is the leftmost\n(C) The white book is the leftmost\nA: (C)\n\nQ: {{input}}\nA:",
      "doc_to_target": "{{target}}",
      "description": "A logical deduction task which requires deducing the order of a sequence of objects.\n\n",
      "target_delimiter": " ",
      "fewshot_delimiter": "\n\n",
      "num_fewshot": 0,
      "metric_list": [
        {
          "metric": "exact_match",
          "aggregation": "mean",
          "higher_is_better": true
        }
      ],
      "output_type": "generate_until",
      "generation_kwargs": {
        "until": [
          "</s>",
          "Q",
          "\n\n"
        ],
        "do_sample": false,
        "temperature": 0.0
      },
      "repeats": 1,
      "should_decontaminate": false,
      "metadata": {
        "version": 1.0,
        "num_fewshot": 3
      }
    },
    "bbh_fewshot_logical_deduction_three_objects": {
      "task": "bbh_fewshot_logical_deduction_three_objects",
      "group": "bbh_fewshot",
      "dataset_path": "lukaemon/bbh",
      "dataset_name": "logical_deduction_three_objects",
      "test_split": "test",
      "doc_to_text": "Q: The following paragraphs each describe a set of three objects arranged in a fixed order. The statements are logically consistent within each paragraph. In a golf tournament, there were three golfers: Amy, Eli, and Eve. Eve finished above Amy. Eli finished below Amy.\nOptions:\n(A) Amy finished last\n(B) Eli finished last\n(C) Eve finished last\nA: (B)\n\nQ: The following paragraphs each describe a set of three objects arranged in a fixed order. The statements are logically consistent within each paragraph. On a shelf, there are three books: a white book, a green book, and an orange book. The green book is to the right of the white book. The orange book is the rightmost.\nOptions:\n(A) The white book is the leftmost\n(B) The green book is the leftmost\n(C) The orange book is the leftmost\nA: (A)\n\nQ: The following paragraphs each describe a set of three objects arranged in a fixed order. The statements are logically consistent within each paragraph. On a shelf, there are three books: a red book, a gray book, and a white book. The white book is to the left of the gray book. The red book is the second from the left.\nOptions:\n(A) The red book is the leftmost\n(B) The gray book is the leftmost\n(C) The white book is the leftmost\nA: (C)\n\nQ: {{input}}\nA:",
      "doc_to_target": "{{target}}",
      "description": "A logical deduction task which requires deducing the order of a sequence of objects.\n\n",
      "target_delimiter": " ",
      "fewshot_delimiter": "\n\n",
      "num_fewshot": 0,
      "metric_list": [
        {
          "metric": "exact_match",
          "aggregation": "mean",
          "higher_is_better": true
        }
      ],
      "output_type": "generate_until",
      "generation_kwargs": {
        "until": [
          "</s>",
          "Q",
          "\n\n"
        ],
        "do_sample": false,
        "temperature": 0.0
      },
      "repeats": 1,
      "should_decontaminate": false,
      "metadata": {
        "version": 1.0,
        "num_fewshot": 3
      }
    },
    "bbh_fewshot_movie_recommendation": {
      "task": "bbh_fewshot_movie_recommendation",
      "group": "bbh_fewshot",
      "dataset_path": "lukaemon/bbh",
      "dataset_name": "movie_recommendation",
      "test_split": "test",
      "doc_to_text": "Q: Find a movie similar to Star Wars Episode IV - A New Hope, Indiana Jones and the Last Crusade, Star Wars Episode V - The Empire Strikes Back, The Big Lebowski:\nOptions:\n(A) Tetsuo\n(B) the Ironman\n(C) The Princess Bride\n(D) The Barkley Marathons The Race That Eats Its Young\n(E) Bug\nA: (C)\n\nQ: Find a movie similar to Twister, The Silence of the Lambs, Independence Day, Braveheart:\nOptions:\n(A) They Shoot Horses\n(B) Don't They\n(C) Forrest Gump\n(D) The Salton Sea\n(E) Extreme Days\nA: (C)\n\nQ: Find a movie similar to Minority Report, Total Recall, Inside Out, Forrest Gump:\nOptions:\n(A) Phenomena\n(B) Lilting\n(C) Catwoman\n(D) Edge of Tomorrow\nA: (D)\n\nQ: {{input}}\nA:",
      "doc_to_target": "{{target}}",
      "description": "Recommend movies similar to the given list of movies.\n\n",
      "target_delimiter": " ",
      "fewshot_delimiter": "\n\n",
      "num_fewshot": 0,
      "metric_list": [
        {
          "metric": "exact_match",
          "aggregation": "mean",
          "higher_is_better": true
        }
      ],
      "output_type": "generate_until",
      "generation_kwargs": {
        "until": [
          "</s>",
          "Q",
          "\n\n"
        ],
        "do_sample": false,
        "temperature": 0.0
      },
      "repeats": 1,
      "should_decontaminate": false,
      "metadata": {
        "version": 1.0,
        "num_fewshot": 3
      }
    },
    "bbh_fewshot_multistep_arithmetic_two": {
      "task": "bbh_fewshot_multistep_arithmetic_two",
      "group": "bbh_fewshot",
      "dataset_path": "lukaemon/bbh",
      "dataset_name": "multistep_arithmetic_two",
      "test_split": "test",
      "doc_to_text": "Q: ((-5 + 9 * -4 - 0) * (4 + -7 + 0 * -5)) =\nA: 123\n\nQ: ((-9 * 7 * 7 * -9) + (4 * -9 - 8 - -4)) =\nA: 3929\n\nQ: ((-3 + 5 * 8 * -4) - (9 - 8 * -7 + -9)) =\nA: -219\n\nQ: {{input}}\nA:",
      "doc_to_target": "{{target}}",
      "description": "Solve multi-step arithmetic problems.\n\n",
      "target_delimiter": " ",
      "fewshot_delimiter": "\n\n",
      "num_fewshot": 0,
      "metric_list": [
        {
          "metric": "exact_match",
          "aggregation": "mean",
          "higher_is_better": true
        }
      ],
      "output_type": "generate_until",
      "generation_kwargs": {
        "until": [
          "</s>",
          "Q",
          "\n\n"
        ],
        "do_sample": false,
        "temperature": 0.0
      },
      "repeats": 1,
      "should_decontaminate": false,
      "metadata": {
        "version": 1.0,
        "num_fewshot": 3
      }
    },
    "bbh_fewshot_navigate": {
      "task": "bbh_fewshot_navigate",
      "group": "bbh_fewshot",
      "dataset_path": "lukaemon/bbh",
      "dataset_name": "navigate",
      "test_split": "test",
      "doc_to_text": "Q: If you follow these instructions, do you return to the starting point? Turn left. Turn around. Turn left. Take 7 steps. Take 2 steps. Take 4 steps. Take 8 steps.\nOptions:\n- Yes\n- No\nA: No\n\nQ: If you follow these instructions, do you return to the starting point? Turn around. Take 1 step. Take 6 steps. Turn around. Take 6 steps. Take 9 steps. Take 1 step.\nOptions:\n- Yes\n- No\nA: No\n\nQ: If you follow these instructions, do you return to the starting point? Always face forward. Take 2 steps right. Take 9 steps left. Take 7 steps right.\nOptions:\n- Yes\n- No\nA: Yes\n\nQ: {{input}}\nA:",
      "doc_to_target": "{{target}}",
      "description": "Given a series of navigation instructions, determine whether one would end up back at the starting point.\n\n",
      "target_delimiter": " ",
      "fewshot_delimiter": "\n\n",
      "num_fewshot": 0,
      "metric_list": [
        {
          "metric": "exact_match",
          "aggregation": "mean",
          "higher_is_better": true
        }
      ],
      "output_type": "generate_until",
      "generation_kwargs": {
        "until": [
          "</s>",
          "Q",
          "\n\n"
        ],
        "do_sample": false,
        "temperature": 0.0
      },
      "repeats": 1,
      "should_decontaminate": false,
      "metadata": {
        "version": 1.0,
        "num_fewshot": 3
      }
    },
    "bbh_fewshot_object_counting": {
      "task": "bbh_fewshot_object_counting",
      "group": "bbh_fewshot",
      "dataset_path": "lukaemon/bbh",
      "dataset_name": "object_counting",
      "test_split": "test",
      "doc_to_text": "Q: I have a blackberry, a clarinet, a nectarine, a plum, a strawberry, a banana, a flute, an orange, and a violin. How many fruits do I have?\nA: 6\n\nQ: I have an orange, a raspberry, two peaches, a blackberry, an apple, a grape, a nectarine, and three plums. How many fruits do I have?\nA: 11\n\nQ: I have a lettuce head, a head of broccoli, an onion, a stalk of celery, two carrots, a garlic, and a yam. How many vegetables do I have?\nA: 8\n\nQ: {{input}}\nA:",
      "doc_to_target": "{{target}}",
      "description": "Questions that involve enumerating objects and asking the model to count them.\n\n",
      "target_delimiter": " ",
      "fewshot_delimiter": "\n\n",
      "num_fewshot": 0,
      "metric_list": [
        {
          "metric": "exact_match",
          "aggregation": "mean",
          "higher_is_better": true
        }
      ],
      "output_type": "generate_until",
      "generation_kwargs": {
        "until": [
          "</s>",
          "Q",
          "\n\n"
        ],
        "do_sample": false,
        "temperature": 0.0
      },
      "repeats": 1,
      "should_decontaminate": false,
      "metadata": {
        "version": 1.0,
        "num_fewshot": 3
      }
    },
    "bbh_fewshot_penguins_in_a_table": {
      "task": "bbh_fewshot_penguins_in_a_table",
      "group": "bbh_fewshot",
      "dataset_path": "lukaemon/bbh",
      "dataset_name": "penguins_in_a_table",
      "test_split": "test",
      "doc_to_text": "Q: Here is a table where the first line is a header and each subsequent line is a penguin:  name, age, height (cm), weight (kg) Louis, 7, 50, 11 Bernard, 5, 80, 13 Vincent, 9, 60, 11 Gwen, 8, 70, 15  For example: the age of Louis is 7, the weight of Gwen is 15 kg, the height of Bernard is 80 cm.  We now add a penguin to the table:\nJames, 12, 90, 12\nHow many penguins are less than 8 years old?\nOptions:\n(A) 1\n(B) 2\n(C) 3\n(D) 4\n(E) 5\nA: (B)\n\nQ: Here is a table where the first line is a header and each subsequent line is a penguin:  name, age, height (cm), weight (kg) Louis, 7, 50, 11 Bernard, 5, 80, 13 Vincent, 9, 60, 11 Gwen, 8, 70, 15  For example: the age of Louis is 7, the weight of Gwen is 15 kg, the height of Bernard is 80 cm.  Which is the youngest penguin?\nOptions:\n(A) Louis\n(B) Bernard\n(C) Vincent\n(D) Gwen\n(E) James\nA: (B)\n\nQ: Here is a table where the first line is a header and each subsequent line is a penguin:  name, age, height (cm), weight (kg) Louis, 7, 50, 11 Bernard, 5, 80, 13 Vincent, 9, 60, 11 Gwen, 8, 70, 15  For example: the age of Louis is 7, the weight of Gwen is 15 kg, the height of Bernard is 80 cm.  What is the name of the second penguin sorted by alphabetic order?\nOptions:\n(A) Louis\n(B) Bernard\n(C) Vincent\n(D) Gwen\n(E) James\nA: (D)\n\nQ: {{input}}\nA:",
      "doc_to_target": "{{target}}",
      "description": "Answer questions about a table of penguins and their attributes.\n\n",
      "target_delimiter": " ",
      "fewshot_delimiter": "\n\n",
      "num_fewshot": 0,
      "metric_list": [
        {
          "metric": "exact_match",
          "aggregation": "mean",
          "higher_is_better": true
        }
      ],
      "output_type": "generate_until",
      "generation_kwargs": {
        "until": [
          "</s>",
          "Q",
          "\n\n"
        ],
        "do_sample": false,
        "temperature": 0.0
      },
      "repeats": 1,
      "should_decontaminate": false,
      "metadata": {
        "version": 1.0,
        "num_fewshot": 3
      }
    },
    "bbh_fewshot_reasoning_about_colored_objects": {
      "task": "bbh_fewshot_reasoning_about_colored_objects",
      "group": "bbh_fewshot",
      "dataset_path": "lukaemon/bbh",
      "dataset_name": "reasoning_about_colored_objects",
      "test_split": "test",
      "doc_to_text": "Q: On the nightstand, there is a red pencil, a purple mug, a burgundy keychain, a fuchsia teddy bear, a black plate, and a blue stress ball. What color is the stress ball?\nOptions:\n(A) red\n(B) orange\n(C) yellow\n(D) green\n(E) blue\n(F) brown\n(G) magenta\n(H) fuchsia\n(I) mauve\n(J) teal\n(K) turquoise\n(L) burgundy\n(M) silver\n(N) gold\n(O) black\n(P) grey\n(Q) purple\n(R) pink\nA: (E)\n\nQ: On the table, you see a bunch of objects arranged in a row: a purple paperclip, a pink stress ball, a brown keychain, a green scrunchiephone charger, a mauve fidget spinner, and a burgundy pen. What is the color of the object directly to the right of the stress ball?\nOptions:\n(A) red\n(B) orange\n(C) yellow\n(D) green\n(E) blue\n(F) brown\n(G) magenta\n(H) fuchsia\n(I) mauve\n(J) teal\n(K) turquoise\n(L) burgundy\n(M) silver\n(N) gold\n(O) black\n(P) grey\n(Q) purple\n(R) pink\nA: (F)\n\nQ: On the nightstand, you see the following items arranged in a row: a teal plate, a burgundy keychain, a yellow scrunchiephone charger, an orange mug, a pink notebook, and a grey cup. How many non-orange items do you see to the left of the teal item?\nOptions:\n(A) zero\n(B) one\n(C) two\n(D) three\n(E) four\n(F) five\n(G) six\nA: (A)\n\nQ: {{input}}\nA:",
      "doc_to_target": "{{target}}",
      "description": "Answer extremely simple questions about the colors of objects on a surface.\n\n",
      "target_delimiter": " ",
      "fewshot_delimiter": "\n\n",
      "num_fewshot": 0,
      "metric_list": [
        {
          "metric": "exact_match",
          "aggregation": "mean",
          "higher_is_better": true
        }
      ],
      "output_type": "generate_until",
      "generation_kwargs": {
        "until": [
          "</s>",
          "Q",
          "\n\n"
        ],
        "do_sample": false,
        "temperature": 0.0
      },
      "repeats": 1,
      "should_decontaminate": false,
      "metadata": {
        "version": 1.0,
        "num_fewshot": 3
      }
    },
    "bbh_fewshot_ruin_names": {
      "task": "bbh_fewshot_ruin_names",
      "group": "bbh_fewshot",
      "dataset_path": "lukaemon/bbh",
      "dataset_name": "ruin_names",
      "test_split": "test",
      "doc_to_text": "Q: Which of the following is a humorous edit of this artist or movie name: 'whitesnake'?\nOptions:\n(A) whitesnape\n(B) whitesnapke\n(C) whitesnuake\n(D) mwhitesnake\nA: (A)\n\nQ: Which of the following is a humorous edit of this artist or movie name: 'one of our dinosaurs is missing'?\nOptions:\n(A) ofne of our dinosaurs is missing\n(B) one af our dinosaurs is missing\n(C) one of our dinosaurs is pissing\n(D) one of our dinosaur is missing\nA: (C)\n\nQ: Which of the following is a humorous edit of this artist or movie name: 'counting crows'?\nOptions:\n(A) countingy crows\n(B) counting cows\n(C) courting crows\n(D) coutnting crows\nA: (B)\n\nQ: {{input}}\nA:",
      "doc_to_target": "{{target}}",
      "description": "Select the humorous edit that 'ruins' the input movie or musical artist name.\n\n",
      "target_delimiter": " ",
      "fewshot_delimiter": "\n\n",
      "num_fewshot": 0,
      "metric_list": [
        {
          "metric": "exact_match",
          "aggregation": "mean",
          "higher_is_better": true
        }
      ],
      "output_type": "generate_until",
      "generation_kwargs": {
        "until": [
          "</s>",
          "Q",
          "\n\n"
        ],
        "do_sample": false,
        "temperature": 0.0
      },
      "repeats": 1,
      "should_decontaminate": false,
      "metadata": {
        "version": 1.0,
        "num_fewshot": 3
      }
    },
    "bbh_fewshot_salient_translation_error_detection": {
      "task": "bbh_fewshot_salient_translation_error_detection",
      "group": "bbh_fewshot",
      "dataset_path": "lukaemon/bbh",
      "dataset_name": "salient_translation_error_detection",
      "test_split": "test",
      "doc_to_text": "Q: The following translations from German to English contain a particular error. That error will be one of the following types: Named Entities: An entity (names, places, locations, etc.) is changed to a different entity. Numerical Values: Numerical values (ordinals or cardinals), dates, and/or units are changed. Modifiers or Adjectives: The modifiers and adjectives pertaining to a noun are changed. Negation or Antonyms: Introduce or remove a negation or change comparatives to their antonyms. Facts: Trivial factual errors not pertaining to the above classes are introduced in the translations. Dropped Content: A significant clause in the translation is removed. Please identify that error.  Source: In der Liste der Baudenkmale in Lenzen (Elbe) sind alle Baudenkmale der brandenburgischen Stadt Lenzen (Elbe) und ihrer Ortsteile aufgelistet.\nTranslation: In the list of architectural monuments in Lenzen all architectural monuments of the Brandenburg city of Lenzen and its districts are listed.\nThe translation contains an error pertaining to\nOptions:\n(A) Modifiers or Adjectives\n(B) Numerical Values\n(C) Negation or Antonyms\n(D) Named Entities\n(E) Dropped Content\n(F) Facts\nA: (D)\n\nQ: The following translations from German to English contain a particular error. That error will be one of the following types: Named Entities: An entity (names, places, locations, etc.) is changed to a different entity. Numerical Values: Numerical values (ordinals or cardinals), dates, and/or units are changed. Modifiers or Adjectives: The modifiers and adjectives pertaining to a noun are changed. Negation or Antonyms: Introduce or remove a negation or change comparatives to their antonyms. Facts: Trivial factual errors not pertaining to the above classes are introduced in the translations. Dropped Content: A significant clause in the translation is removed. Please identify that error.  Source: Auf dieser Seite sind die Baudenkmäler der oberbayerischen Großen Kreisstadt Landsberg am Lech zusammengestellt.\nTranslation: On this page are compiled the architectural monuments of the town of Landsberg am Lech.\nThe translation contains an error pertaining to\nOptions:\n(A) Modifiers or Adjectives\n(B) Numerical Values\n(C) Negation or Antonyms\n(D) Named Entities\n(E) Dropped Content\n(F) Facts\nA: (E)\n\nQ: The following translations from German to English contain a particular error. That error will be one of the following types: Named Entities: An entity (names, places, locations, etc.) is changed to a different entity. Numerical Values: Numerical values (ordinals or cardinals), dates, and/or units are changed. Modifiers or Adjectives: The modifiers and adjectives pertaining to a noun are changed. Negation or Antonyms: Introduce or remove a negation or change comparatives to their antonyms. Facts: Trivial factual errors not pertaining to the above classes are introduced in the translations. Dropped Content: A significant clause in the translation is removed. Please identify that error.  Source: Łeba ist eine Kleinstadt und ein Badeort im Powiat Lęborski der polnischen Woiwodschaft Pommern.\nTranslation: Eba is not a small town and seaside resort in the Powiat Léborski county of the Pomeranian Voivodeship of Poland.\nThe translation contains an error pertaining to\nOptions:\n(A) Modifiers or Adjectives\n(B) Numerical Values\n(C) Negation or Antonyms\n(D) Named Entities\n(E) Dropped Content\n(F) Facts\nA: (C)\n\nQ: {{input}}\nA:",
      "doc_to_target": "{{target}}",
      "description": "Detect the type of error in an English translation of a German source sentence.\n\n",
      "target_delimiter": " ",
      "fewshot_delimiter": "\n\n",
      "num_fewshot": 0,
      "metric_list": [
        {
          "metric": "exact_match",
          "aggregation": "mean",
          "higher_is_better": true
        }
      ],
      "output_type": "generate_until",
      "generation_kwargs": {
        "until": [
          "</s>",
          "Q",
          "\n\n"
        ],
        "do_sample": false,
        "temperature": 0.0
      },
      "repeats": 1,
      "should_decontaminate": false,
      "metadata": {
        "version": 1.0,
        "num_fewshot": 3
      }
    },
    "bbh_fewshot_snarks": {
      "task": "bbh_fewshot_snarks",
      "group": "bbh_fewshot",
      "dataset_path": "lukaemon/bbh",
      "dataset_name": "snarks",
      "test_split": "test",
      "doc_to_text": "Q: Which statement is sarcastic?\nOptions:\n(A) Yes, because having interests and actively researching them is a huge waste\n(B) Yes, because having interests and actively researching them is a huge deal\nA: (A)\n\nQ: Which statement is sarcastic?\nOptions:\n(A) No one is going to disagree with you on this. Avoiding ad hominem attacks really help your case\n(B) No one is going to disagree with you on this. Ad hominem attacks really help your case\nA: (B)\n\nQ: Which statement is sarcastic?\nOptions:\n(A) Consistency in the league's punishments? What do you think this is supposed to be, politics?\n(B) Consistency in the league's punishments? What do you think this is supposed to be, moral?\nA: (A)\n\nQ: {{input}}\nA:",
      "doc_to_target": "{{target}}",
      "description": "Determine which of two sentences is sarcastic.\n\nAccording to Cambridge University Dictionary, sarcasm is \"the use of remarks that clearly mean the opposite of what they say, made in order to hurt someone's feelings or to criticize something in a humorous way.\" Sarcastic sentences often contain satirical or ironic utterances, hyperboles, ambivalent or witty remarks.\n\n",
      "target_delimiter": " ",
      "fewshot_delimiter": "\n\n",
      "num_fewshot": 0,
      "metric_list": [
        {
          "metric": "exact_match",
          "aggregation": "mean",
          "higher_is_better": true
        }
      ],
      "output_type": "generate_until",
      "generation_kwargs": {
        "until": [
          "</s>",
          "Q",
          "\n\n"
        ],
        "do_sample": false,
        "temperature": 0.0
      },
      "repeats": 1,
      "should_decontaminate": false,
      "metadata": {
        "version": 1.0,
        "num_fewshot": 3
      }
    },
    "bbh_fewshot_sports_understanding": {
      "task": "bbh_fewshot_sports_understanding",
      "group": "bbh_fewshot",
      "dataset_path": "lukaemon/bbh",
      "dataset_name": "sports_understanding",
      "test_split": "test",
      "doc_to_text": "Q: Is the following sentence plausible? \"Bam Adebayo scored a reverse layup in the Western Conference Finals.\"\nA: yes\n\nQ: Is the following sentence plausible? \"Santi Cazorla scored a touchdown.\"\nA: no\n\nQ: Is the following sentence plausible? \"DeMar DeRozan was called for the goal tend.\"\nA: yes\n\nQ: {{input}}\nA:",
      "doc_to_target": "{{target}}",
      "description": "Determine whether an artificially constructed sentence relating to sports is plausible or not.\n\n",
      "target_delimiter": " ",
      "fewshot_delimiter": "\n\n",
      "num_fewshot": 0,
      "metric_list": [
        {
          "metric": "exact_match",
          "aggregation": "mean",
          "higher_is_better": true
        }
      ],
      "output_type": "generate_until",
      "generation_kwargs": {
        "until": [
          "</s>",
          "Q",
          "\n\n"
        ],
        "do_sample": false,
        "temperature": 0.0
      },
      "repeats": 1,
      "should_decontaminate": false,
      "metadata": {
        "version": 1.0,
        "num_fewshot": 3
      }
    },
    "bbh_fewshot_temporal_sequences": {
      "task": "bbh_fewshot_temporal_sequences",
      "group": "bbh_fewshot",
      "dataset_path": "lukaemon/bbh",
      "dataset_name": "temporal_sequences",
      "test_split": "test",
      "doc_to_text": "Q: Today, Emily went to the museum. Between what times could they have gone?\nWe know that:\nEmily woke up at 1pm.\nElizabeth saw Emily reading at the library from 2pm to 4pm.\nJessica saw Emily watching a movie at the theater from 4pm to 5pm.\nLeslie saw Emily waiting at the airport from 5pm to 6pm.\nWilliam saw Emily buying clothes at the mall from 6pm to 7pm.\nThe museum was closed after 7pm.\nBetween what times could Emily have gone to the museum?\nOptions:\n(A) 1pm to 2pm\n(B) 6pm to 7pm\n(C) 5pm to 6pm\n(D) 2pm to 4pm\nA: (A)\n\nQ: Today, Elizabeth went to the amusement park. Between what times could they have gone?\nWe know that:\nElizabeth woke up at 7am.\nDavid saw Elizabeth fixing their computer at the electronic store from 1pm to 2pm.\nSarah saw Elizabeth playing tennis at the tennis court from 2pm to 3pm.\nSusan saw Elizabeth walking towards the Statue of Liberty from 3pm to 6pm.\nAndrew saw Elizabeth taking photos near the Eiffel Tower from 6pm to 9pm.\nEmily saw Elizabeth getting a coffee at the cafe from 9pm to 10pm.\nThe amusement park was closed after 10pm.\nBetween what times could Elizabeth have gone to the amusement park?\nOptions:\n(A) 7am to 1pm\n(B) 9pm to 10pm\n(C) 1pm to 2pm\n(D) 3pm to 6pm\nA: (A)\n\nQ: Today, Tiffany went to the beach. Between what times could they have gone?\nWe know that:\nTiffany woke up at 5am.\nBetty saw Tiffany getting a coffee at the cafe from 5am to 6am.\nJessica saw Tiffany working at the office from 6am to 9am.\nJohn saw Tiffany stretching at a yoga studio from 9am to 12pm.\nSean saw Tiffany sitting on a rooftop from 12pm to 2pm.\nSarah saw Tiffany playing tennis at the tennis court from 2pm to 3pm.\nThe beach was closed after 4pm.\nBetween what times could Tiffany have gone to the beach?\nOptions:\n(A) 9am to 12pm\n(B) 12pm to 2pm\n(C) 5am to 6am\n(D) 3pm to 4pm\nA: (D)\n\nQ: {{input}}\nA:",
      "doc_to_target": "{{target}}",
      "description": "Task description: Answer questions about which times certain events could have occurred.\n\n",
      "target_delimiter": " ",
      "fewshot_delimiter": "\n\n",
      "num_fewshot": 0,
      "metric_list": [
        {
          "metric": "exact_match",
          "aggregation": "mean",
          "higher_is_better": true
        }
      ],
      "output_type": "generate_until",
      "generation_kwargs": {
        "until": [
          "</s>",
          "Q",
          "\n\n"
        ],
        "do_sample": false,
        "temperature": 0.0
      },
      "repeats": 1,
      "should_decontaminate": false,
      "metadata": {
        "version": 1.0,
        "num_fewshot": 3
      }
    },
    "bbh_fewshot_tracking_shuffled_objects_five_objects": {
      "task": "bbh_fewshot_tracking_shuffled_objects_five_objects",
      "group": "bbh_fewshot",
      "dataset_path": "lukaemon/bbh",
      "dataset_name": "tracking_shuffled_objects_five_objects",
      "test_split": "test",
      "doc_to_text": "Q: Alice, Bob, and Claire are playing a game. At the start of the game, they are each holding a ball: Alice has a yellow ball, Bob has a blue ball, and Claire has a pink ball.\nAs the game progresses, pairs of players trade balls. First, Claire and Alice swap balls. Then, Alice and Bob swap balls. Finally, Claire and Bob swap balls. At the end of the game, Bob has the\nOptions:\n(A) yellow ball\n(B) blue ball\n(C) pink ball\nA: (A)\n\nQ: Alice, Bob, and Claire are playing a game. At the start of the game, they are each holding a ball: Alice has a white ball, Bob has a purple ball, and Claire has a pink ball.\nAs the game progresses, pairs of players trade balls. First, Bob and Alice swap balls. Then, Bob and Claire swap balls. Finally, Bob and Alice swap balls. At the end of the game, Alice has the\nOptions:\n(A) white ball\n(B) purple ball\n(C) pink ball\nA: (C)\n\nQ: Alice, Bob, and Claire are dancers at a square dance. At the start of a song, they each have a partner: Alice is dancing with Lola, Bob is dancing with Rodrigo, and Claire is dancing with Patrick.\nThroughout the song, the dancers often trade partners. First, Alice and Bob switch partners. Then, Claire and Bob switch partners. Finally, Bob and Alice switch partners. At the end of the dance, Alice is dancing with\nOptions:\n(A) Lola\n(B) Rodrigo\n(C) Patrick\nA: (C)\n\nQ: {{input}}\nA:",
      "doc_to_target": "{{target}}",
      "description": "A task requiring determining the final positions of a set of objects given their initial positions and a description of a sequence of swaps.\n\n",
      "target_delimiter": " ",
      "fewshot_delimiter": "\n\n",
      "num_fewshot": 0,
      "metric_list": [
        {
          "metric": "exact_match",
          "aggregation": "mean",
          "higher_is_better": true
        }
      ],
      "output_type": "generate_until",
      "generation_kwargs": {
        "until": [
          "</s>",
          "Q",
          "\n\n"
        ],
        "do_sample": false,
        "temperature": 0.0
      },
      "repeats": 1,
      "should_decontaminate": false,
      "metadata": {
        "version": 1.0,
        "num_fewshot": 3
      }
    },
    "bbh_fewshot_tracking_shuffled_objects_seven_objects": {
      "task": "bbh_fewshot_tracking_shuffled_objects_seven_objects",
      "group": "bbh_fewshot",
      "dataset_path": "lukaemon/bbh",
      "dataset_name": "tracking_shuffled_objects_seven_objects",
      "test_split": "test",
      "doc_to_text": "Q: Alice, Bob, and Claire are playing a game. At the start of the game, they are each holding a ball: Alice has a yellow ball, Bob has a blue ball, and Claire has a pink ball.\nAs the game progresses, pairs of players trade balls. First, Claire and Alice swap balls. Then, Alice and Bob swap balls. Finally, Claire and Bob swap balls. At the end of the game, Bob has the\nOptions:\n(A) yellow ball\n(B) blue ball\n(C) pink ball\nA: (A)\n\nQ: Alice, Bob, and Claire are playing a game. At the start of the game, they are each holding a ball: Alice has a white ball, Bob has a purple ball, and Claire has a pink ball.\nAs the game progresses, pairs of players trade balls. First, Bob and Alice swap balls. Then, Bob and Claire swap balls. Finally, Bob and Alice swap balls. At the end of the game, Alice has the\nOptions:\n(A) white ball\n(B) purple ball\n(C) pink ball\nA: (C)\n\nQ: Alice, Bob, and Claire are dancers at a square dance. At the start of a song, they each have a partner: Alice is dancing with Lola, Bob is dancing with Rodrigo, and Claire is dancing with Patrick.\nThroughout the song, the dancers often trade partners. First, Alice and Bob switch partners. Then, Claire and Bob switch partners. Finally, Bob and Alice switch partners. At the end of the dance, Alice is dancing with\nOptions:\n(A) Lola\n(B) Rodrigo\n(C) Patrick\nA: (C)\n\nQ: {{input}}\nA:",
      "doc_to_target": "{{target}}",
      "description": "A task requiring determining the final positions of a set of objects given their initial positions and a description of a sequence of swaps.\n\n",
      "target_delimiter": " ",
      "fewshot_delimiter": "\n\n",
      "num_fewshot": 0,
      "metric_list": [
        {
          "metric": "exact_match",
          "aggregation": "mean",
          "higher_is_better": true
        }
      ],
      "output_type": "generate_until",
      "generation_kwargs": {
        "until": [
          "</s>",
          "Q",
          "\n\n"
        ],
        "do_sample": false,
        "temperature": 0.0
      },
      "repeats": 1,
      "should_decontaminate": false,
      "metadata": {
        "version": 1.0,
        "num_fewshot": 3
      }
    },
    "bbh_fewshot_tracking_shuffled_objects_three_objects": {
      "task": "bbh_fewshot_tracking_shuffled_objects_three_objects",
      "group": "bbh_fewshot",
      "dataset_path": "lukaemon/bbh",
      "dataset_name": "tracking_shuffled_objects_three_objects",
      "test_split": "test",
      "doc_to_text": "Q: Alice, Bob, and Claire are playing a game. At the start of the game, they are each holding a ball: Alice has a yellow ball, Bob has a blue ball, and Claire has a pink ball.\nAs the game progresses, pairs of players trade balls. First, Claire and Alice swap balls. Then, Alice and Bob swap balls. Finally, Claire and Bob swap balls. At the end of the game, Bob has the\nOptions:\n(A) yellow ball\n(B) blue ball\n(C) pink ball\nA: (A)\n\nQ: Alice, Bob, and Claire are playing a game. At the start of the game, they are each holding a ball: Alice has a white ball, Bob has a purple ball, and Claire has a pink ball.\nAs the game progresses, pairs of players trade balls. First, Bob and Alice swap balls. Then, Bob and Claire swap balls. Finally, Bob and Alice swap balls. At the end of the game, Alice has the\nOptions:\n(A) white ball\n(B) purple ball\n(C) pink ball\nA: (C)\n\nQ: Alice, Bob, and Claire are dancers at a square dance. At the start of a song, they each have a partner: Alice is dancing with Lola, Bob is dancing with Rodrigo, and Claire is dancing with Patrick.\nThroughout the song, the dancers often trade partners. First, Alice and Bob switch partners. Then, Claire and Bob switch partners. Finally, Bob and Alice switch partners. At the end of the dance, Alice is dancing with\nOptions:\n(A) Lola\n(B) Rodrigo\n(C) Patrick\nA: (C)\n\nQ: {{input}}\nA:",
      "doc_to_target": "{{target}}",
      "description": "A task requiring determining the final positions of a set of objects given their initial positions and a description of a sequence of swaps.\n\n",
      "target_delimiter": " ",
      "fewshot_delimiter": "\n\n",
      "num_fewshot": 0,
      "metric_list": [
        {
          "metric": "exact_match",
          "aggregation": "mean",
          "higher_is_better": true
        }
      ],
      "output_type": "generate_until",
      "generation_kwargs": {
        "until": [
          "</s>",
          "Q",
          "\n\n"
        ],
        "do_sample": false,
        "temperature": 0.0
      },
      "repeats": 1,
      "should_decontaminate": false,
      "metadata": {
        "version": 1.0,
        "num_fewshot": 3
      }
    },
    "bbh_fewshot_web_of_lies": {
      "task": "bbh_fewshot_web_of_lies",
      "group": "bbh_fewshot",
      "dataset_path": "lukaemon/bbh",
      "dataset_name": "web_of_lies",
      "test_split": "test",
      "doc_to_text": "Q: Question: Fidel tells the truth. Jerry says Fidel tells the truth. Vina says Jerry tells the truth. Millicent says Vina lies. Raymond says Millicent lies. Does Raymond tell the truth?\nA: Yes\n\nQ: Question: Kristian lies. Millie says Kristian lies. Maybelle says Millie tells the truth. Fidel says Maybelle lies. Leda says Fidel lies. Does Leda tell the truth?\nA: Yes\n\nQ: Question: Kristian tells the truth. Michaela says Kristian lies. Raymond says Michaela tells the truth. Osvaldo says Raymond tells the truth. Jamey says Osvaldo tells the truth. Does Jamey tell the truth?\nA: No\n\nQ: {{input}}\nA:",
      "doc_to_target": "{{target}}",
      "description": "Evaluate a random boolean function expressed as a word problem.\n\n",
      "target_delimiter": " ",
      "fewshot_delimiter": "\n\n",
      "num_fewshot": 0,
      "metric_list": [
        {
          "metric": "exact_match",
          "aggregation": "mean",
          "higher_is_better": true
        }
      ],
      "output_type": "generate_until",
      "generation_kwargs": {
        "until": [
          "</s>",
          "Q",
          "\n\n"
        ],
        "do_sample": false,
        "temperature": 0.0
      },
      "repeats": 1,
      "should_decontaminate": false,
      "metadata": {
        "version": 1.0,
        "num_fewshot": 3
      }
    },
    "bbh_fewshot_word_sorting": {
      "task": "bbh_fewshot_word_sorting",
      "group": "bbh_fewshot",
      "dataset_path": "lukaemon/bbh",
      "dataset_name": "word_sorting",
      "test_split": "test",
      "doc_to_text": "Q: Sort the following words alphabetically: List: oven costume counterpart\nA: costume counterpart oven\n\nQ: Sort the following words alphabetically: List: hypochlorite ponderosa phone credulity\nA: credulity hypochlorite phone ponderosa\n\nQ: Sort the following words alphabetically: List: newt arson parthia seismography mugho aspect census\nA: arson aspect census mugho newt parthia seismography\n\nQ: {{input}}\nA:",
      "doc_to_target": "{{target}}",
      "description": "Sort a list of words.\n\n",
      "target_delimiter": " ",
      "fewshot_delimiter": "\n\n",
      "num_fewshot": 0,
      "metric_list": [
        {
          "metric": "exact_match",
          "aggregation": "mean",
          "higher_is_better": true
        }
      ],
      "output_type": "generate_until",
      "generation_kwargs": {
        "until": [
          "</s>",
          "Q",
          "\n\n"
        ],
        "do_sample": false,
        "temperature": 0.0
      },
      "repeats": 1,
      "should_decontaminate": false,
      "metadata": {
        "version": 1.0,
        "num_fewshot": 3
      }
    }
  },
  "versions": {
    "bbh_fewshot": "N/A",
    "bbh_fewshot_boolean_expressions": 1.0,
    "bbh_fewshot_causal_judgement": 1.0,
    "bbh_fewshot_date_understanding": 1.0,
    "bbh_fewshot_disambiguation_qa": 1.0,
    "bbh_fewshot_dyck_languages": 1.0,
    "bbh_fewshot_formal_fallacies": 1.0,
    "bbh_fewshot_geometric_shapes": 1.0,
    "bbh_fewshot_hyperbaton": 1.0,
    "bbh_fewshot_logical_deduction_five_objects": 1.0,
    "bbh_fewshot_logical_deduction_seven_objects": 1.0,
    "bbh_fewshot_logical_deduction_three_objects": 1.0,
    "bbh_fewshot_movie_recommendation": 1.0,
    "bbh_fewshot_multistep_arithmetic_two": 1.0,
    "bbh_fewshot_navigate": 1.0,
    "bbh_fewshot_object_counting": 1.0,
    "bbh_fewshot_penguins_in_a_table": 1.0,
    "bbh_fewshot_reasoning_about_colored_objects": 1.0,
    "bbh_fewshot_ruin_names": 1.0,
    "bbh_fewshot_salient_translation_error_detection": 1.0,
    "bbh_fewshot_snarks": 1.0,
    "bbh_fewshot_sports_understanding": 1.0,
    "bbh_fewshot_temporal_sequences": 1.0,
    "bbh_fewshot_tracking_shuffled_objects_five_objects": 1.0,
    "bbh_fewshot_tracking_shuffled_objects_seven_objects": 1.0,
    "bbh_fewshot_tracking_shuffled_objects_three_objects": 1.0,
    "bbh_fewshot_web_of_lies": 1.0,
    "bbh_fewshot_word_sorting": 1.0
  },
  "n-shot": {
    "bbh_fewshot": 3,
    "bbh_fewshot_boolean_expressions": 3,
    "bbh_fewshot_causal_judgement": 3,
    "bbh_fewshot_date_understanding": 3,
    "bbh_fewshot_disambiguation_qa": 3,
    "bbh_fewshot_dyck_languages": 3,
    "bbh_fewshot_formal_fallacies": 3,
    "bbh_fewshot_geometric_shapes": 3,
    "bbh_fewshot_hyperbaton": 3,
    "bbh_fewshot_logical_deduction_five_objects": 3,
    "bbh_fewshot_logical_deduction_seven_objects": 3,
    "bbh_fewshot_logical_deduction_three_objects": 3,
    "bbh_fewshot_movie_recommendation": 3,
    "bbh_fewshot_multistep_arithmetic_two": 3,
    "bbh_fewshot_navigate": 3,
    "bbh_fewshot_object_counting": 3,
    "bbh_fewshot_penguins_in_a_table": 3,
    "bbh_fewshot_reasoning_about_colored_objects": 3,
    "bbh_fewshot_ruin_names": 3,
    "bbh_fewshot_salient_translation_error_detection": 3,
    "bbh_fewshot_snarks": 3,
    "bbh_fewshot_sports_understanding": 3,
    "bbh_fewshot_temporal_sequences": 3,
    "bbh_fewshot_tracking_shuffled_objects_five_objects": 3,
    "bbh_fewshot_tracking_shuffled_objects_seven_objects": 3,
    "bbh_fewshot_tracking_shuffled_objects_three_objects": 3,
    "bbh_fewshot_web_of_lies": 3,
    "bbh_fewshot_word_sorting": 3
  },
  "config": {
    "model": "hf",
    "model_args": "pretrained=Qwen/Qwen1.5-0.5B-Chat,revision=main,dtype=bfloat16",
    "batch_size": "auto",
    "batch_sizes": [],
    "device": null,
    "use_cache": null,
    "limit": null,
    "bootstrap_iters": 100000,
    "gen_kwargs": null
  },
  "git_hash": "901c20b"
}