DeepSeek-R1-Distill-Llama-8B-GGUF / scores /DeepSeek-R1-Distill-Llama-8B-iq3_m.arc
eaddario's picture
Generate Perplexity, KLD, ARC, HellaSwag, MMLU, Truthful QA and WinoGrande scores
afa61ba 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 0.00000000
2 0.00000000
3 0.00000000
4 0.00000000
5 20.00000000
6 16.66666667
7 28.57142857
8 25.00000000
9 22.22222222
10 30.00000000
11 27.27272727
12 33.33333333
13 30.76923077
14 28.57142857
15 33.33333333
16 31.25000000
17 35.29411765
18 38.88888889
19 42.10526316
20 40.00000000
21 42.85714286
22 45.45454545
23 43.47826087
24 45.83333333
25 44.00000000
26 42.30769231
27 44.44444444
28 42.85714286
29 44.82758621
30 46.66666667
31 45.16129032
32 46.87500000
33 45.45454545
34 44.11764706
35 42.85714286
36 41.66666667
37 43.24324324
38 42.10526316
39 41.02564103
40 42.50000000
41 41.46341463
42 40.47619048
43 39.53488372
44 38.63636364
45 40.00000000
46 41.30434783
47 42.55319149
48 41.66666667
49 42.85714286
50 44.00000000
51 45.09803922
52 46.15384615
53 47.16981132
54 46.29629630
55 45.45454545
56 44.64285714
57 45.61403509
58 46.55172414
59 47.45762712
60 48.33333333
61 49.18032787
62 48.38709677
63 49.20634921
64 50.00000000
65 49.23076923
66 50.00000000
67 50.74626866
68 51.47058824
69 50.72463768
70 50.00000000
71 49.29577465
72 48.61111111
73 49.31506849
74 48.64864865
75 49.33333333
76 50.00000000
77 49.35064935
78 50.00000000
79 49.36708861
80 48.75000000
81 48.14814815
82 48.78048780
83 48.19277108
84 47.61904762
85 48.23529412
86 47.67441860
87 47.12643678
88 47.72727273
89 48.31460674
90 48.88888889
91 49.45054945
92 50.00000000
93 49.46236559
94 48.93617021
95 49.47368421
96 50.00000000
97 49.48453608
98 48.97959184
99 49.49494949
100 49.00000000
101 49.50495050
102 50.00000000
103 49.51456311
104 50.00000000
105 50.47619048
106 50.00000000
107 50.46728972
108 50.00000000
109 49.54128440
110 50.00000000
111 50.45045045
112 50.89285714
113 50.44247788
114 50.87719298
115 51.30434783
116 51.72413793
117 51.28205128
118 51.69491525
119 51.26050420
120 50.83333333
121 50.41322314
122 50.81967213
123 51.21951220
124 50.80645161
125 51.20000000
126 51.58730159
127 51.18110236
128 51.56250000
129 51.16279070
130 50.76923077
131 51.14503817
132 50.75757576
133 51.12781955
134 50.74626866
135 50.37037037
136 50.00000000
137 50.36496350
138 50.72463768
139 51.07913669
140 50.71428571
141 50.35460993
142 50.70422535
143 51.04895105
144 51.38888889
145 51.72413793
146 51.36986301
147 51.70068027
148 51.35135135
149 51.67785235
150 52.00000000
151 52.31788079
152 52.63157895
153 52.28758170
154 51.94805195
155 51.61290323
156 51.92307692
157 52.22929936
158 51.89873418
159 52.20125786
160 51.87500000
161 51.55279503
162 51.23456790
163 51.53374233
164 51.21951220
165 51.51515152
166 51.80722892
167 51.49700599
168 51.78571429
169 51.47928994
170 51.17647059
171 51.46198830
172 51.74418605
173 52.02312139
174 52.29885057
175 52.00000000
176 51.70454545
177 51.97740113
178 52.24719101
179 51.95530726
180 51.66666667
181 51.38121547
182 51.64835165
183 51.36612022
184 51.08695652
185 51.35135135
186 51.61290323
187 51.87165775
188 51.59574468
189 51.32275132
190 51.05263158
191 51.30890052
192 51.04166667
193 50.77720207
194 51.03092784
195 51.28205128
196 51.53061224
197 51.77664975
198 51.51515152
199 51.75879397
200 52.00000000
201 52.23880597
202 51.98019802
203 51.72413793
204 51.96078431
205 51.70731707
206 51.45631068
207 51.69082126
208 51.44230769
209 51.19617225
210 51.42857143
211 51.65876777
212 51.41509434
213 51.64319249
214 51.86915888
215 52.09302326
216 51.85185185
217 52.07373272
218 51.83486239
219 51.59817352
220 51.36363636
221 51.58371041
222 51.80180180
223 51.56950673
224 51.78571429
225 51.55555556
226 51.76991150
227 51.98237885
228 52.19298246
229 52.40174672
230 52.60869565
231 52.38095238
232 52.15517241
233 51.93133047
234 51.70940171
235 51.48936170
236 51.27118644
237 51.05485232
238 51.26050420
239 51.46443515
240 51.66666667
241 51.86721992
242 51.65289256
243 51.85185185
244 51.63934426
245 51.83673469
246 52.03252033
247 52.22672065
248 52.41935484
249 52.20883534
250 52.40000000
251 52.58964143
252 52.77777778
253 52.96442688
254 52.75590551
255 52.94117647
256 53.12500000
257 53.30739300
258 53.10077519
259 52.89575290
260 52.69230769
261 52.87356322
262 52.67175573
263 52.85171103
264 52.65151515
265 52.45283019
266 52.25563910
267 52.43445693
268 52.61194030
269 52.41635688
270 52.59259259
271 52.76752768
272 52.57352941
273 52.38095238
274 52.18978102
275 52.00000000
276 51.81159420
277 51.98555957
278 51.79856115
279 51.97132616
280 52.14285714
281 52.31316726
282 52.48226950
283 52.29681979
284 52.46478873
285 52.63157895
286 52.44755245
287 52.26480836
288 52.43055556
289 52.24913495
290 52.41379310
291 52.23367698
292 52.39726027
293 52.55972696
294 52.38095238
295 52.54237288
296 52.70270270
297 52.86195286
298 53.02013423
299 52.84280936
300 53.00000000
301 52.82392027
302 52.98013245
303 53.13531353
304 52.96052632
305 53.11475410
306 52.94117647
307 53.09446254
308 53.24675325
309 53.39805825
310 53.54838710
311 53.69774920
312 53.52564103
313 53.67412141
314 53.50318471
315 53.33333333
316 53.48101266
317 53.62776025
318 53.45911950
319 53.29153605
320 53.12500000
321 52.95950156
322 53.10559006
323 52.94117647
324 52.77777778
325 52.92307692
326 53.06748466
327 52.90519878
328 53.04878049
329 52.88753799
330 52.72727273
331 52.87009063
332 53.01204819
333 53.15315315
334 53.29341317
335 53.13432836
336 53.27380952
337 53.11572700
338 52.95857988
339 53.09734513
340 53.23529412
341 53.07917889
342 52.92397661
343 53.06122449
344 53.19767442
345 53.04347826
346 53.17919075
347 53.02593660
348 52.87356322
349 52.72206304
350 52.85714286
351 52.99145299
352 52.84090909
353 52.69121813
354 52.54237288
355 52.39436620
356 52.52808989
357 52.38095238
358 52.51396648
359 52.36768802
360 52.50000000
361 52.63157895
362 52.76243094
363 52.89256198
364 52.74725275
365 52.60273973
366 52.45901639
367 52.58855586
368 52.44565217
369 52.30352304
370 52.43243243
371 52.29110512
372 52.15053763
373 52.01072386
374 52.13903743
375 52.26666667
376 52.12765957
377 52.25464191
378 52.38095238
379 52.24274406
380 52.36842105
381 52.23097113
382 52.09424084
383 51.95822454
384 51.82291667
385 51.94805195
386 51.81347150
387 51.67958656
388 51.54639175
389 51.41388175
390 51.28205128
391 51.15089514
392 51.27551020
393 51.14503817
394 51.01522843
395 51.13924051
396 51.01010101
397 50.88161209
398 50.75376884
399 50.87719298
400 51.00000000
401 50.87281796
402 50.99502488
403 51.11662531
404 50.99009901
405 50.86419753
406 50.98522167
407 51.10565111
408 51.22549020
409 51.10024450
410 51.21951220
411 51.09489051
412 51.21359223
413 51.08958838
414 51.20772947
415 51.08433735
416 50.96153846
417 50.83932854
418 50.71770335
419 50.59665871
420 50.47619048
421 50.59382423
422 50.71090047
423 50.82742317
424 50.70754717
425 50.58823529
426 50.46948357
427 50.58548009
428 50.46728972
429 50.58275058
430 50.46511628
431 50.34802784
432 50.46296296
433 50.34642032
434 50.46082949
435 50.57471264
436 50.68807339
437 50.57208238
438 50.45662100
439 50.56947608
440 50.45454545
441 50.56689342
442 50.45248869
443 50.33860045
444 50.22522523
445 50.33707865
446 50.44843049
447 50.33557047
448 50.22321429
449 50.33407572
450 50.22222222
451 50.11086475
452 50.22123894
453 50.33112583
454 50.22026432
455 50.32967033
456 50.21929825
457 50.10940919
458 50.00000000
459 50.10893246
460 50.00000000
461 49.89154013
462 50.00000000
463 49.89200864
464 49.78448276
465 49.89247312
466 49.78540773
467 49.89293362
468 50.00000000
469 49.89339019
470 49.78723404
471 49.89384289
472 50.00000000
473 49.89429175
474 50.00000000
475 49.89473684
476 49.78991597
477 49.89517820
478 50.00000000
479 50.10438413
480 50.20833333
481 50.10395010
482 50.20746888
483 50.31055901
484 50.41322314
485 50.51546392
486 50.41152263
487 50.30800821
488 50.40983607
489 50.30674847
490 50.20408163
491 50.10183299
492 50.00000000
493 49.89858012
494 50.00000000
495 49.89898990
496 49.79838710
497 49.89939638
498 50.00000000
499 50.10020040
500 50.00000000
501 49.90019960
502 50.00000000
503 50.09940358
504 50.00000000
505 50.09900990
506 50.00000000
507 49.90138067
508 50.00000000
509 49.90176817
510 49.80392157
511 49.90215264
512 49.80468750
513 49.70760234
514 49.80544747
515 49.90291262
516 49.80620155
517 49.70986460
518 49.80694981
519 49.71098266
520 49.61538462
521 49.71209213
522 49.61685824
523 49.52198853
524 49.42748092
525 49.33333333
526 49.23954373
527 49.14611006
528 49.05303030
529 48.96030246
530 49.05660377
531 49.15254237
532 49.24812030
533 49.34333959
534 49.25093633
535 49.34579439
536 49.44029851
537 49.53445065
538 49.44237918
539 49.53617811
540 49.44444444
541 49.35304991
542 49.44649446
543 49.53959484
544 49.63235294
545 49.54128440
546 49.63369963
547 49.54296161
548 49.63503650
549 49.54462659
550 49.63636364
551 49.54627949
552 49.63768116
553 49.72875226
554 49.63898917
555 49.72972973
556 49.64028777
557 49.73070018
558 49.64157706
559 49.73166369
560 49.82142857
561 49.91087344
562 50.00000000
563 49.91119005
564 49.82269504
565 49.73451327
566 49.82332155
567 49.73544974
568 49.82394366
569 49.73637961
570 49.64912281
571 49.73730298
572 49.65034965
573 49.56369983
574 49.65156794
575 49.56521739
576 49.65277778
577 49.74003466
578 49.82698962
579 49.91364421
580 50.00000000
581 49.91394148
582 50.00000000
583 50.08576329
584 50.17123288
585 50.25641026
586 50.17064846
587 50.08517888
588 50.17006803
589 50.08488964
590 50.16949153
591 50.25380711
592 50.33783784
593 50.25295110
594 50.33670034
595 50.25210084
596 50.16778523
597 50.08375209
598 50.00000000
599 50.08347245
600 50.16666667
601 50.24958403
602 50.16611296
603 50.08291874
604 50.00000000
605 49.91735537
606 50.00000000
607 50.08237232
608 50.16447368
609 50.08210181
610 50.16393443
611 50.08183306
612 50.16339869
613 50.08156607
614 50.00000000
615 50.08130081
616 50.00000000
617 50.08103728
618 50.16181230
619 50.08077544
620 50.16129032
621 50.24154589
622 50.16077170
623 50.24077047
624 50.16025641
625 50.24000000
626 50.15974441
627 50.23923445
628 50.31847134
629 50.23847377
630 50.31746032
631 50.23771791
632 50.15822785
633 50.07898894
634 50.00000000
635 50.07874016
636 50.15723270
637 50.07849294
638 50.15673981
639 50.23474178
640 50.15625000
641 50.23400936
642 50.15576324
643 50.07776050
644 50.15527950
645 50.07751938
646 50.15479876
647 50.07727975
648 50.00000000
649 49.92295840
650 50.00000000
651 50.07680492
652 50.00000000
653 49.92343032
654 49.84709480
655 49.77099237
656 49.69512195
657 49.61948250
658 49.69604863
659 49.77238240
660 49.84848485
661 49.77307110
662 49.84894260
663 49.92458522
664 50.00000000
665 50.07518797
666 50.00000000
667 50.07496252
668 50.00000000
669 49.92526158
670 50.00000000
671 50.07451565
672 50.00000000
673 49.92570579
674 49.85163205
675 49.77777778
676 49.70414201
677 49.77843427
678 49.85250737
679 49.77908689
680 49.85294118
681 49.77973568
682 49.85337243
683 49.78038067
684 49.70760234
685 49.78102190
686 49.70845481
687 49.63609898
688 49.70930233
689 49.63715530
690 49.56521739
691 49.49348770
692 49.56647399
693 49.49494949
694 49.42363112
695 49.35251799
696 49.28160920
697 49.21090387
698 49.14040115
699 49.07010014
700 49.14285714
701 49.07275321
702 49.14529915
703 49.21763869
704 49.28977273
705 49.36170213
706 49.29178470
707 49.36350778
708 49.43502825
709 49.50634697
710 49.57746479
711 49.64838256
712 49.71910112
713 49.64936886
714 49.57983193
715 49.51048951
716 49.44134078
717 49.37238494
718 49.30362117
719 49.23504868
720 49.30555556
721 49.23717060
722 49.30747922
723 49.37759336
724 49.44751381
725 49.51724138
726 49.44903581
727 49.38101788
728 49.31318681
729 49.24554184
730 49.31506849
731 49.38440492
732 49.31693989
733 49.38608458
734 49.45504087
735 49.38775510
736 49.45652174
737 49.38941655
738 49.45799458
739 49.39106901
740 49.32432432
741 49.39271255
742 49.46091644
743 49.52893674
744 49.46236559
745 49.39597315
746 49.32975871
747 49.26372155
748 49.19786096
749 49.13217623
750 49.20000000
Final result: 49.2000 +/- 1.8267
Random chance: 25.0083 +/- 1.5824