Watt-Tool-8B-GGUF / scores /Watt-Tool-8B-q4_k_m.arc
eaddario's picture
Generate Perplexity, KLD, ARC, HellaSwag, MMLU, Truthful QA and WinoGrande scores
6583e65 verified
raw
history blame
12.6 kB
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
1 100.00000000
2 100.00000000
3 100.00000000
4 75.00000000
5 80.00000000
6 83.33333333
7 71.42857143
8 75.00000000
9 66.66666667
10 70.00000000
11 63.63636364
12 66.66666667
13 61.53846154
14 64.28571429
15 66.66666667
16 68.75000000
17 70.58823529
18 66.66666667
19 68.42105263
20 65.00000000
21 66.66666667
22 68.18181818
23 65.21739130
24 66.66666667
25 64.00000000
26 61.53846154
27 62.96296296
28 60.71428571
29 62.06896552
30 63.33333333
31 61.29032258
32 59.37500000
33 57.57575758
34 55.88235294
35 57.14285714
36 55.55555556
37 56.75675676
38 55.26315789
39 56.41025641
40 57.50000000
41 58.53658537
42 57.14285714
43 55.81395349
44 54.54545455
45 55.55555556
46 56.52173913
47 57.44680851
48 58.33333333
49 59.18367347
50 58.00000000
51 56.86274510
52 57.69230769
53 56.60377358
54 55.55555556
55 54.54545455
56 55.35714286
57 56.14035088
58 56.89655172
59 57.62711864
60 58.33333333
61 59.01639344
62 58.06451613
63 58.73015873
64 59.37500000
65 58.46153846
66 59.09090909
67 59.70149254
68 60.29411765
69 60.86956522
70 60.00000000
71 59.15492958
72 58.33333333
73 58.90410959
74 59.45945946
75 60.00000000
76 59.21052632
77 59.74025974
78 60.25641026
79 59.49367089
80 60.00000000
81 59.25925926
82 59.75609756
83 59.03614458
84 59.52380952
85 60.00000000
86 60.46511628
87 60.91954023
88 61.36363636
89 61.79775281
90 62.22222222
91 62.63736264
92 63.04347826
93 62.36559140
94 61.70212766
95 62.10526316
96 62.50000000
97 61.85567010
98 62.24489796
99 62.62626263
100 63.00000000
101 62.37623762
102 62.74509804
103 62.13592233
104 61.53846154
105 61.90476190
106 61.32075472
107 61.68224299
108 61.11111111
109 60.55045872
110 60.90909091
111 61.26126126
112 61.60714286
113 61.94690265
114 61.40350877
115 61.73913043
116 61.20689655
117 60.68376068
118 61.01694915
119 60.50420168
120 60.83333333
121 60.33057851
122 60.65573770
123 60.97560976
124 60.48387097
125 60.80000000
126 61.11111111
127 61.41732283
128 61.71875000
129 61.24031008
130 61.53846154
131 61.83206107
132 62.12121212
133 62.40601504
134 61.94029851
135 61.48148148
136 61.02941176
137 61.31386861
138 61.59420290
139 61.87050360
140 62.14285714
141 61.70212766
142 61.97183099
143 62.23776224
144 62.50000000
145 62.75862069
146 62.32876712
147 62.58503401
148 62.83783784
149 63.08724832
150 63.33333333
151 62.91390728
152 63.15789474
153 63.39869281
154 62.98701299
155 63.22580645
156 63.46153846
157 63.69426752
158 63.29113924
159 63.52201258
160 63.12500000
161 63.35403727
162 63.58024691
163 63.19018405
164 63.41463415
165 63.03030303
166 63.25301205
167 62.87425150
168 63.09523810
169 62.72189349
170 62.35294118
171 62.57309942
172 62.79069767
173 63.00578035
174 63.21839080
175 62.85714286
176 63.06818182
177 63.27683616
178 63.48314607
179 63.68715084
180 63.88888889
181 63.53591160
182 63.73626374
183 63.38797814
184 63.58695652
185 63.78378378
186 63.97849462
187 63.63636364
188 63.29787234
189 62.96296296
190 62.63157895
191 62.82722513
192 63.02083333
193 62.69430052
194 62.88659794
195 63.07692308
196 63.26530612
197 63.45177665
198 63.13131313
199 62.81407035
200 63.00000000
201 63.18407960
202 63.36633663
203 63.54679803
204 63.72549020
205 63.41463415
206 63.10679612
207 63.28502415
208 63.46153846
209 63.63636364
210 63.80952381
211 63.98104265
212 63.67924528
213 63.84976526
214 64.01869159
215 64.18604651
216 63.88888889
217 64.05529954
218 63.76146789
219 63.92694064
220 63.63636364
221 63.80090498
222 63.96396396
223 63.67713004
224 63.83928571
225 63.55555556
226 63.71681416
227 63.87665198
228 64.03508772
229 64.19213974
230 64.34782609
231 64.06926407
232 63.79310345
233 63.94849785
234 64.10256410
235 63.82978723
236 63.55932203
237 63.71308017
238 63.86554622
239 64.01673640
240 64.16666667
241 64.31535270
242 64.46280992
243 64.19753086
244 63.93442623
245 64.08163265
246 64.22764228
247 64.37246964
248 64.51612903
249 64.25702811
250 64.40000000
251 64.54183267
252 64.68253968
253 64.82213439
254 64.56692913
255 64.70588235
256 64.45312500
257 64.20233463
258 64.34108527
259 64.09266409
260 64.23076923
261 64.36781609
262 64.50381679
263 64.63878327
264 64.77272727
265 64.90566038
266 64.66165414
267 64.79400749
268 64.92537313
269 65.05576208
270 65.18518519
271 65.31365314
272 65.07352941
273 64.83516484
274 64.59854015
275 64.36363636
276 64.49275362
277 64.62093863
278 64.38848921
279 64.51612903
280 64.64285714
281 64.76868327
282 64.89361702
283 64.66431095
284 64.78873239
285 64.91228070
286 65.03496503
287 65.15679443
288 65.27777778
289 65.05190311
290 65.17241379
291 65.29209622
292 65.41095890
293 65.52901024
294 65.30612245
295 65.42372881
296 65.54054054
297 65.65656566
298 65.77181208
299 65.88628763
300 66.00000000
301 65.78073090
302 65.89403974
303 66.00660066
304 66.11842105
305 66.22950820
306 66.01307190
307 66.12377850
308 66.23376623
309 66.34304207
310 66.45161290
311 66.55948553
312 66.66666667
313 66.77316294
314 66.56050955
315 66.66666667
316 66.77215190
317 66.87697161
318 66.66666667
319 66.45768025
320 66.25000000
321 66.35514019
322 66.45962733
323 66.56346749
324 66.35802469
325 66.46153846
326 66.56441718
327 66.36085627
328 66.46341463
329 66.56534954
330 66.66666667
331 66.76737160
332 66.86746988
333 66.96696697
334 67.06586826
335 66.86567164
336 66.96428571
337 67.06231454
338 66.86390533
339 66.96165192
340 67.05882353
341 67.15542522
342 67.25146199
343 67.34693878
344 67.44186047
345 67.24637681
346 67.34104046
347 67.14697406
348 66.95402299
349 67.04871060
350 66.85714286
351 66.95156695
352 67.04545455
353 67.13881020
354 66.94915254
355 66.76056338
356 66.85393258
357 66.66666667
358 66.75977654
359 66.57381616
360 66.66666667
361 66.75900277
362 66.85082873
363 66.66666667
364 66.75824176
365 66.84931507
366 66.66666667
367 66.48501362
368 66.30434783
369 66.39566396
370 66.48648649
371 66.57681941
372 66.66666667
373 66.75603217
374 66.84491979
375 66.66666667
376 66.75531915
377 66.57824934
378 66.66666667
379 66.49076517
380 66.57894737
381 66.40419948
382 66.23036649
383 66.05744125
384 66.14583333
385 65.97402597
386 66.06217617
387 66.14987080
388 65.97938144
389 66.06683805
390 65.89743590
391 65.72890026
392 65.81632653
393 65.90330789
394 65.98984772
395 66.07594937
396 65.90909091
397 65.99496222
398 65.82914573
399 65.91478697
400 65.75000000
401 65.83541147
402 65.67164179
403 65.75682382
404 65.84158416
405 65.92592593
406 66.00985222
407 66.09336609
408 66.17647059
409 66.01466993
410 66.09756098
411 66.18004866
412 66.26213592
413 66.34382567
414 66.42512077
415 66.26506024
416 66.34615385
417 66.18705036
418 66.26794258
419 66.10978520
420 66.19047619
421 66.03325416
422 65.87677725
423 65.95744681
424 65.80188679
425 65.88235294
426 65.72769953
427 65.80796253
428 65.65420561
429 65.73426573
430 65.81395349
431 65.89327146
432 65.97222222
433 65.81986143
434 65.89861751
435 65.97701149
436 66.05504587
437 66.13272311
438 65.98173516
439 66.05922551
440 65.90909091
441 65.98639456
442 65.83710407
443 65.68848758
444 65.76576577
445 65.84269663
446 65.91928251
447 65.99552573
448 66.07142857
449 66.14699332
450 66.00000000
451 66.07538803
452 66.15044248
453 66.22516556
454 66.29955947
455 66.15384615
456 66.22807018
457 66.30196937
458 66.37554585
459 66.44880174
460 66.30434783
461 66.37744035
462 66.45021645
463 66.30669546
464 66.16379310
465 66.23655914
466 66.30901288
467 66.38115632
468 66.45299145
469 66.31130064
470 66.38297872
471 66.45435244
472 66.52542373
473 66.38477801
474 66.45569620
475 66.31578947
476 66.38655462
477 66.45702306
478 66.52719665
479 66.59707724
480 66.66666667
481 66.73596674
482 66.80497925
483 66.87370600
484 66.94214876
485 67.01030928
486 67.07818930
487 66.94045175
488 67.00819672
489 67.07566462
490 66.93877551
491 66.80244399
492 66.86991870
493 66.73427992
494 66.80161943
495 66.86868687
496 66.93548387
497 67.00201207
498 67.06827309
499 67.13426854
500 67.20000000
501 67.06586826
502 67.13147410
503 67.19681909
504 67.26190476
505 67.32673267
506 67.19367589
507 67.06114398
508 67.12598425
509 66.99410609
510 66.86274510
511 66.73189824
512 66.79687500
513 66.66666667
514 66.73151751
515 66.79611650
516 66.86046512
517 66.92456480
518 66.98841699
519 67.05202312
520 66.92307692
521 66.98656430
522 67.04980843
523 66.92160612
524 66.98473282
525 66.85714286
526 66.73003802
527 66.60341556
528 66.47727273
529 66.35160681
530 66.41509434
531 66.47834275
532 66.54135338
533 66.60412758
534 66.47940075
535 66.35514019
536 66.41791045
537 66.48044693
538 66.54275093
539 66.60482375
540 66.48148148
541 66.54343808
542 66.60516605
543 66.48250460
544 66.54411765
545 66.60550459
546 66.48351648
547 66.36197441
548 66.42335766
549 66.48451730
550 66.54545455
551 66.42468240
552 66.30434783
553 66.36528029
554 66.42599278
555 66.48648649
556 66.36690647
557 66.42728905
558 66.30824373
559 66.36851521
560 66.42857143
561 66.48841355
562 66.54804270
563 66.60746004
564 66.48936170
565 66.37168142
566 66.43109541
567 66.49029982
568 66.54929577
569 66.43233743
570 66.31578947
571 66.37478109
572 66.25874126
573 66.31762653
574 66.37630662
575 66.43478261
576 66.49305556
577 66.55112652
578 66.60899654
579 66.66666667
580 66.55172414
581 66.43717728
582 66.49484536
583 66.55231561
584 66.60958904
585 66.66666667
586 66.55290102
587 66.60988075
588 66.66666667
589 66.72325976
590 66.77966102
591 66.83587140
592 66.72297297
593 66.61045531
594 66.66666667
595 66.72268908
596 66.61073826
597 66.49916248
598 66.38795987
599 66.44407346
600 66.50000000
601 66.55574043
602 66.44518272
603 66.33499171
604 66.39072848
605 66.44628099
606 66.50165017
607 66.55683690
608 66.61184211
609 66.50246305
610 66.55737705
611 66.44844517
612 66.50326797
613 66.39477977
614 66.44951140
615 66.34146341
616 66.23376623
617 66.28849271
618 66.34304207
619 66.23586430
620 66.29032258
621 66.34460548
622 66.23794212
623 66.29213483
624 66.34615385
625 66.24000000
626 66.13418530
627 66.18819777
628 66.24203822
629 66.13672496
630 66.19047619
631 66.24405705
632 66.13924051
633 66.03475513
634 66.08832808
635 66.14173228
636 66.19496855
637 66.09105181
638 66.14420063
639 66.19718310
640 66.09375000
641 66.14664587
642 66.04361371
643 65.94090202
644 65.99378882
645 65.89147287
646 65.94427245
647 65.84234930
648 65.74074074
649 65.63944530
650 65.69230769
651 65.74500768
652 65.79754601
653 65.69678407
654 65.59633028
655 65.49618321
656 65.39634146
657 65.29680365
658 65.19756839
659 65.09863429
660 65.15151515
661 65.05295008
662 65.10574018
663 65.15837104
664 65.21084337
665 65.26315789
666 65.16516517
667 65.21739130
668 65.11976048
669 65.02242152
670 65.07462687
671 64.97764531
672 65.02976190
673 64.93313522
674 64.98516320
675 64.88888889
676 64.79289941
677 64.84490399
678 64.89675516
679 64.94845361
680 65.00000000
681 64.90455213
682 64.80938416
683 64.71449488
684 64.76608187
685 64.81751825
686 64.72303207
687 64.62882096
688 64.68023256
689 64.58635704
690 64.63768116
691 64.54413893
692 64.59537572
693 64.64646465
694 64.69740634
695 64.60431655
696 64.51149425
697 64.41893831
698 64.32664756
699 64.37768240
700 64.42857143
701 64.47931526
702 64.52991453
703 64.58036984
704 64.63068182
705 64.68085106
706 64.73087819
707 64.78076379
708 64.83050847
709 64.88011283
710 64.92957746
711 64.97890295
712 65.02808989
713 65.07713885
714 64.98599440
715 64.89510490
716 64.94413408
717 64.85355649
718 64.76323120
719 64.67315716
720 64.72222222
721 64.63245492
722 64.68144044
723 64.73029046
724 64.64088398
725 64.68965517
726 64.60055096
727 64.51169188
728 64.56043956
729 64.60905350
730 64.65753425
731 64.70588235
732 64.75409836
733 64.80218281
734 64.85013624
735 64.89795918
736 64.94565217
737 64.85753053
738 64.90514905
739 64.81732070
740 64.72972973
741 64.77732794
742 64.69002695
743 64.73755047
744 64.65053763
745 64.69798658
746 64.74530831
747 64.65863454
748 64.57219251
749 64.48598131
750 64.53333333
Final result: 64.5333 +/- 1.7481
Random chance: 25.0083 +/- 1.5824