Hammer2.1-7b-GGUF / scores /Hammer2.1-7b-q4_k_m-naive.arc
eaddario's picture
Generate Perplexity, KLD, ARC, HellaSwag, MMLU, Truthful QA and WinoGrande scores
ed91853 verified
common_init_from_params: setting dry_penalty_last_n to ctx_size = 768
common_init_from_params: warming up the model with an empty run - please wait ... (--no-warmup to disable)
system_info: n_threads = 6 (n_threads_batch = 6) / 12 | Metal : EMBED_LIBRARY = 1 | CPU : NEON = 1 | ARM_FMA = 1 | FP16_VA = 1 | DOTPROD = 1 | LLAMAFILE = 1 | ACCELERATE = 1 | AARCH64_REPACK = 1 |
multiple_choice_score: there are 869 tasks in prompt
multiple_choice_score: selecting 750 random tasks from 869 tasks available
multiple_choice_score: preparing task data...done
multiple_choice_score : calculating TruthfulQA score over 750 tasks.
task acc_norm
1 0.00000000
2 50.00000000
3 66.66666667
4 50.00000000
5 60.00000000
6 66.66666667
7 57.14285714
8 62.50000000
9 55.55555556
10 60.00000000
11 54.54545455
12 58.33333333
13 61.53846154
14 64.28571429
15 60.00000000
16 62.50000000
17 64.70588235
18 61.11111111
19 57.89473684
20 55.00000000
21 57.14285714
22 59.09090909
23 56.52173913
24 58.33333333
25 56.00000000
26 53.84615385
27 55.55555556
28 53.57142857
29 55.17241379
30 56.66666667
31 54.83870968
32 53.12500000
33 54.54545455
34 52.94117647
35 54.28571429
36 52.77777778
37 54.05405405
38 55.26315789
39 56.41025641
40 57.50000000
41 58.53658537
42 59.52380952
43 60.46511628
44 59.09090909
45 60.00000000
46 60.86956522
47 61.70212766
48 60.41666667
49 59.18367347
50 60.00000000
51 58.82352941
52 59.61538462
53 60.37735849
54 59.25925926
55 58.18181818
56 58.92857143
57 59.64912281
58 60.34482759
59 61.01694915
60 61.66666667
61 60.65573770
62 59.67741935
63 60.31746032
64 60.93750000
65 60.00000000
66 60.60606061
67 61.19402985
68 61.76470588
69 60.86956522
70 60.00000000
71 59.15492958
72 58.33333333
73 58.90410959
74 59.45945946
75 60.00000000
76 60.52631579
77 61.03896104
78 61.53846154
79 60.75949367
80 61.25000000
81 60.49382716
82 60.97560976
83 60.24096386
84 59.52380952
85 60.00000000
86 60.46511628
87 60.91954023
88 61.36363636
89 61.79775281
90 61.11111111
91 61.53846154
92 61.95652174
93 61.29032258
94 60.63829787
95 61.05263158
96 61.45833333
97 60.82474227
98 60.20408163
99 60.60606061
100 61.00000000
101 60.39603960
102 60.78431373
103 60.19417476
104 59.61538462
105 60.00000000
106 59.43396226
107 59.81308411
108 59.25925926
109 58.71559633
110 59.09090909
111 59.45945946
112 59.82142857
113 59.29203540
114 59.64912281
115 60.00000000
116 59.48275862
117 58.97435897
118 59.32203390
119 58.82352941
120 59.16666667
121 58.67768595
122 59.01639344
123 59.34959350
124 58.87096774
125 59.20000000
126 59.52380952
127 59.05511811
128 59.37500000
129 58.91472868
130 58.46153846
131 58.77862595
132 59.09090909
133 59.39849624
134 58.95522388
135 59.25925926
136 58.82352941
137 59.12408759
138 59.42028986
139 59.71223022
140 59.28571429
141 59.57446809
142 59.15492958
143 59.44055944
144 59.02777778
145 59.31034483
146 58.90410959
147 59.18367347
148 59.45945946
149 59.73154362
150 60.00000000
151 60.26490066
152 60.52631579
153 60.78431373
154 60.38961039
155 60.64516129
156 60.89743590
157 61.14649682
158 61.39240506
159 61.63522013
160 61.25000000
161 60.86956522
162 61.11111111
163 60.73619632
164 60.36585366
165 60.60606061
166 60.84337349
167 60.47904192
168 60.71428571
169 60.94674556
170 60.58823529
171 60.23391813
172 60.46511628
173 60.69364162
174 60.91954023
175 60.57142857
176 60.22727273
177 60.45197740
178 60.11235955
179 60.33519553
180 60.00000000
181 60.22099448
182 60.43956044
183 60.10928962
184 59.78260870
185 60.00000000
186 60.21505376
187 60.42780749
188 60.10638298
189 59.78835979
190 59.47368421
191 59.68586387
192 59.37500000
193 59.06735751
194 59.27835052
195 59.48717949
196 59.69387755
197 59.89847716
198 59.59595960
199 59.29648241
200 59.50000000
201 59.70149254
202 59.90099010
203 60.09852217
204 60.29411765
205 60.00000000
206 59.70873786
207 59.90338164
208 60.09615385
209 60.28708134
210 60.47619048
211 60.66350711
212 60.37735849
213 60.56338028
214 60.74766355
215 60.93023256
216 60.64814815
217 60.36866359
218 60.09174312
219 60.27397260
220 60.00000000
221 59.72850679
222 59.90990991
223 59.64125561
224 59.82142857
225 59.55555556
226 59.29203540
227 59.47136564
228 59.64912281
229 59.82532751
230 60.00000000
231 59.74025974
232 59.48275862
233 59.65665236
234 59.82905983
235 59.57446809
236 59.74576271
237 59.91561181
238 60.08403361
239 60.25104603
240 60.41666667
241 60.58091286
242 60.33057851
243 60.49382716
244 60.24590164
245 60.40816327
246 60.56910569
247 60.72874494
248 60.88709677
249 60.64257028
250 60.80000000
251 60.95617530
252 61.11111111
253 61.26482213
254 61.02362205
255 61.17647059
256 61.32812500
257 61.47859922
258 61.62790698
259 61.38996139
260 61.53846154
261 61.68582375
262 61.45038168
263 61.59695817
264 61.74242424
265 61.88679245
266 61.65413534
267 61.79775281
268 61.94029851
269 62.08178439
270 62.22222222
271 62.36162362
272 62.13235294
273 61.90476190
274 61.67883212
275 61.45454545
276 61.59420290
277 61.73285199
278 61.51079137
279 61.64874552
280 61.78571429
281 61.92170819
282 62.05673759
283 61.83745583
284 61.97183099
285 62.10526316
286 62.23776224
287 62.02090592
288 62.15277778
289 61.93771626
290 62.06896552
291 62.19931271
292 61.98630137
293 62.11604096
294 61.90476190
295 62.03389831
296 62.16216216
297 62.28956229
298 62.41610738
299 62.54180602
300 62.33333333
301 62.12624585
302 62.25165563
303 62.37623762
304 62.50000000
305 62.62295082
306 62.41830065
307 62.21498371
308 62.33766234
309 62.45954693
310 62.25806452
311 62.37942122
312 62.17948718
313 62.30031949
314 62.10191083
315 61.90476190
316 62.02531646
317 62.14511041
318 61.94968553
319 61.75548589
320 61.56250000
321 61.37071651
322 61.49068323
323 61.60990712
324 61.41975309
325 61.23076923
326 61.34969325
327 61.16207951
328 61.28048780
329 61.39817629
330 61.51515152
331 61.63141994
332 61.74698795
333 61.86186186
334 61.67664671
335 61.49253731
336 61.30952381
337 61.12759644
338 60.94674556
339 61.06194690
340 61.17647059
341 61.29032258
342 61.40350877
343 61.51603499
344 61.62790698
345 61.44927536
346 61.56069364
347 61.38328530
348 61.20689655
349 61.31805158
350 61.14285714
351 61.25356125
352 61.36363636
353 61.47308782
354 61.29943503
355 61.12676056
356 60.95505618
357 60.78431373
358 60.89385475
359 60.72423398
360 60.83333333
361 60.94182825
362 61.04972376
363 61.15702479
364 60.98901099
365 60.82191781
366 60.92896175
367 61.03542234
368 61.14130435
369 60.97560976
370 60.81081081
371 60.64690027
372 60.48387097
373 60.32171582
374 60.42780749
375 60.53333333
376 60.37234043
377 60.21220159
378 60.31746032
379 60.42216359
380 60.52631579
381 60.36745407
382 60.20942408
383 60.05221932
384 60.15625000
385 60.25974026
386 60.36269430
387 60.20671835
388 60.05154639
389 60.15424165
390 60.00000000
391 59.84654731
392 59.94897959
393 59.79643766
394 59.89847716
395 60.00000000
396 59.84848485
397 59.94962217
398 59.79899497
399 59.89974937
400 60.00000000
401 60.09975062
402 59.95024876
403 60.04962779
404 60.14851485
405 60.24691358
406 60.34482759
407 60.44226044
408 60.53921569
409 60.39119804
410 60.48780488
411 60.58394161
412 60.67961165
413 60.53268765
414 60.62801932
415 60.48192771
416 60.33653846
417 60.19184652
418 60.28708134
419 60.14319809
420 60.00000000
421 60.09501188
422 60.18957346
423 60.28368794
424 60.14150943
425 60.23529412
426 60.09389671
427 60.18735363
428 60.04672897
429 60.13986014
430 60.00000000
431 60.09280742
432 60.18518519
433 60.04618938
434 60.13824885
435 60.22988506
436 60.32110092
437 60.18306636
438 60.04566210
439 60.13667426
440 60.00000000
441 60.09070295
442 59.95475113
443 59.81941309
444 59.90990991
445 60.00000000
446 60.08968610
447 60.17897092
448 60.04464286
449 60.13363029
450 60.22222222
451 60.31042129
452 60.39823009
453 60.26490066
454 60.13215859
455 60.21978022
456 60.08771930
457 60.17505470
458 60.26200873
459 60.34858388
460 60.21739130
461 60.08676790
462 60.17316017
463 60.04319654
464 59.91379310
465 59.78494624
466 59.87124464
467 59.95717345
468 60.04273504
469 59.91471215
470 60.00000000
471 60.08492569
472 60.16949153
473 60.04228330
474 60.12658228
475 60.00000000
476 59.87394958
477 59.95807128
478 60.04184100
479 60.12526096
480 60.20833333
481 60.08316008
482 60.16597510
483 60.24844720
484 60.12396694
485 60.20618557
486 60.28806584
487 60.16427105
488 60.24590164
489 60.12269939
490 60.00000000
491 60.08146640
492 60.16260163
493 60.04056795
494 60.12145749
495 60.00000000
496 60.08064516
497 60.16096579
498 60.24096386
499 60.32064128
500 60.40000000
501 60.27944112
502 60.35856574
503 60.43737575
504 60.31746032
505 60.39603960
506 60.27667984
507 60.15779093
508 60.03937008
509 59.92141454
510 60.00000000
511 59.88258317
512 59.96093750
513 59.84405458
514 59.92217899
515 60.00000000
516 59.88372093
517 59.96131528
518 60.03861004
519 59.92292871
520 59.80769231
521 59.88483685
522 59.77011494
523 59.65583174
524 59.54198473
525 59.42857143
526 59.31558935
527 59.20303605
528 59.09090909
529 58.97920605
530 59.05660377
531 59.13370998
532 59.21052632
533 59.28705441
534 59.17602996
535 59.06542056
536 59.14179104
537 59.21787709
538 59.10780669
539 59.18367347
540 59.07407407
541 59.14972274
542 59.04059041
543 59.11602210
544 59.00735294
545 59.08256881
546 58.97435897
547 58.86654479
548 58.94160584
549 59.01639344
550 59.09090909
551 58.98366606
552 58.87681159
553 58.95117541
554 59.02527076
555 59.09909910
556 58.99280576
557 59.06642729
558 58.96057348
559 59.03398927
560 59.10714286
561 59.18003565
562 59.25266904
563 59.32504440
564 59.21985816
565 59.11504425
566 59.18727915
567 59.08289242
568 59.15492958
569 59.05096661
570 58.94736842
571 59.01926445
572 58.91608392
573 58.81326353
574 58.88501742
575 58.95652174
576 59.02777778
577 59.09878683
578 59.16955017
579 59.24006908
580 59.13793103
581 59.03614458
582 59.10652921
583 59.17667238
584 59.24657534
585 59.31623932
586 59.38566553
587 59.28449744
588 59.18367347
589 59.25297114
590 59.32203390
591 59.39086294
592 59.29054054
593 59.35919056
594 59.42760943
595 59.32773109
596 59.22818792
597 59.12897822
598 59.03010033
599 59.09849750
600 59.16666667
601 59.23460899
602 59.13621262
603 59.03814262
604 58.94039735
605 58.84297521
606 58.91089109
607 58.97858320
608 59.04605263
609 58.94909688
610 59.01639344
611 58.91980360
612 58.82352941
613 58.72756933
614 58.63192182
615 58.53658537
616 58.44155844
617 58.50891410
618 58.41423948
619 58.31987076
620 58.38709677
621 58.45410628
622 58.36012862
623 58.42696629
624 58.33333333
625 58.24000000
626 58.14696486
627 58.21371611
628 58.12101911
629 58.02861685
630 58.09523810
631 58.00316957
632 57.91139241
633 57.81990521
634 57.88643533
635 57.95275591
636 58.01886792
637 57.92778650
638 57.99373041
639 57.90297340
640 57.81250000
641 57.72230889
642 57.63239875
643 57.54276827
644 57.60869565
645 57.51937984
646 57.58513932
647 57.65069552
648 57.56172840
649 57.47303544
650 57.38461538
651 57.45007680
652 57.36196319
653 57.42725881
654 57.49235474
655 57.40458015
656 57.46951220
657 57.38203957
658 57.29483283
659 57.35963581
660 57.42424242
661 57.33736762
662 57.40181269
663 57.46606335
664 57.53012048
665 57.59398496
666 57.50750751
667 57.57121439
668 57.48502994
669 57.39910314
670 57.46268657
671 57.52608048
672 57.44047619
673 57.35512630
674 57.41839763
675 57.48148148
676 57.39644970
677 57.45937962
678 57.52212389
679 57.58468336
680 57.64705882
681 57.56240822
682 57.47800587
683 57.39385066
684 57.30994152
685 57.37226277
686 57.28862974
687 57.35080058
688 57.41279070
689 57.47460087
690 57.53623188
691 57.59768452
692 57.65895954
693 57.72005772
694 57.78097983
695 57.69784173
696 57.61494253
697 57.67575323
698 57.59312321
699 57.51072961
700 57.57142857
701 57.48930100
702 57.54985755
703 57.61024182
704 57.67045455
705 57.73049645
706 57.79036827
707 57.85007072
708 57.90960452
709 57.96897038
710 58.02816901
711 58.08720113
712 58.14606742
713 58.20476858
714 58.12324930
715 58.04195804
716 58.10055866
717 58.01952580
718 57.93871866
719 57.85813630
720 57.91666667
721 57.83633842
722 57.89473684
723 57.95297372
724 58.01104972
725 58.06896552
726 57.98898072
727 57.90921596
728 57.96703297
729 58.02469136
730 58.08219178
731 58.13953488
732 58.19672131
733 58.25375171
734 58.31062670
735 58.23129252
736 58.28804348
737 58.20895522
738 58.13008130
739 58.05142084
740 57.97297297
741 58.02968961
742 58.08625337
743 58.14266487
744 58.06451613
745 58.12080537
746 58.04289544
747 57.96519411
748 57.88770053
749 57.94392523
750 58.00000000
Final result: 58.0000 +/- 1.8034
Random chance: 25.0083 +/- 1.5824