Adding Evaluation Results
#41
by
amannadcab
- opened
README.md
CHANGED
@@ -1,5 +1,4 @@
|
|
1 |
---
|
2 |
-
license: bigscience-bloom-rail-1.0
|
3 |
language:
|
4 |
- ak
|
5 |
- ar
|
@@ -49,6 +48,7 @@ language:
|
|
49 |
- zhs
|
50 |
- zht
|
51 |
- zu
|
|
|
52 |
pipeline_tag: text-generation
|
53 |
model-index:
|
54 |
- name: bloom
|
@@ -60,9 +60,9 @@ model-index:
|
|
60 |
name: arc_challenge
|
61 |
type: arc_challenge
|
62 |
metrics:
|
63 |
-
-
|
64 |
-
type: acc
|
65 |
value: 0.27986348122866894
|
|
|
66 |
verified: false
|
67 |
- task:
|
68 |
type: text-generation
|
@@ -71,9 +71,9 @@ model-index:
|
|
71 |
name: arc_easy
|
72 |
type: arc_easy
|
73 |
metrics:
|
74 |
-
-
|
75 |
-
type: acc
|
76 |
value: 0.5946969696969697
|
|
|
77 |
verified: false
|
78 |
- task:
|
79 |
type: text-generation
|
@@ -82,9 +82,9 @@ model-index:
|
|
82 |
name: axb
|
83 |
type: axb
|
84 |
metrics:
|
85 |
-
-
|
86 |
-
type: acc
|
87 |
value: 0.4433876811594203
|
|
|
88 |
verified: false
|
89 |
- task:
|
90 |
type: text-generation
|
@@ -93,9 +93,9 @@ model-index:
|
|
93 |
name: axg
|
94 |
type: axg
|
95 |
metrics:
|
96 |
-
-
|
97 |
-
type: acc
|
98 |
value: 0.5
|
|
|
99 |
verified: false
|
100 |
- task:
|
101 |
type: text-generation
|
@@ -104,9 +104,9 @@ model-index:
|
|
104 |
name: boolq
|
105 |
type: boolq
|
106 |
metrics:
|
107 |
-
-
|
108 |
-
type: acc
|
109 |
value: 0.6165137614678899
|
|
|
110 |
verified: false
|
111 |
- task:
|
112 |
type: text-generation
|
@@ -115,9 +115,9 @@ model-index:
|
|
115 |
name: cb
|
116 |
type: cb
|
117 |
metrics:
|
118 |
-
-
|
119 |
-
type: acc
|
120 |
value: 0.30357142857142855
|
|
|
121 |
verified: false
|
122 |
- task:
|
123 |
type: text-generation
|
@@ -126,9 +126,9 @@ model-index:
|
|
126 |
name: cola
|
127 |
type: cola
|
128 |
metrics:
|
129 |
-
-
|
130 |
-
type: acc
|
131 |
value: 0.610738255033557
|
|
|
132 |
verified: false
|
133 |
- task:
|
134 |
type: text-generation
|
@@ -137,9 +137,9 @@ model-index:
|
|
137 |
name: copa
|
138 |
type: copa
|
139 |
metrics:
|
140 |
-
-
|
141 |
-
type: acc
|
142 |
value: 0.63
|
|
|
143 |
verified: false
|
144 |
- task:
|
145 |
type: text-generation
|
@@ -148,9 +148,9 @@ model-index:
|
|
148 |
name: crows_pairs_english
|
149 |
type: crows_pairs_english
|
150 |
metrics:
|
151 |
-
-
|
152 |
-
type: acc
|
153 |
value: 0.4973166368515206
|
|
|
154 |
verified: false
|
155 |
- task:
|
156 |
type: text-generation
|
@@ -159,9 +159,9 @@ model-index:
|
|
159 |
name: crows_pairs_french
|
160 |
type: crows_pairs_french
|
161 |
metrics:
|
162 |
-
-
|
163 |
-
type: acc
|
164 |
value: 0.5032796660703638
|
|
|
165 |
verified: false
|
166 |
- task:
|
167 |
type: text-generation
|
@@ -170,9 +170,9 @@ model-index:
|
|
170 |
name: diabla
|
171 |
type: diabla
|
172 |
metrics:
|
173 |
-
-
|
174 |
-
type: acc
|
175 |
value: 0.28888308977035493
|
|
|
176 |
verified: false
|
177 |
- task:
|
178 |
type: text-generation
|
@@ -181,9 +181,9 @@ model-index:
|
|
181 |
name: gsarti/flores_101_afr
|
182 |
type: gsarti/flores_101_afr
|
183 |
metrics:
|
184 |
-
-
|
185 |
-
type: byte_perplexity
|
186 |
value: 6.500798737976343
|
|
|
187 |
verified: false
|
188 |
- task:
|
189 |
type: text-generation
|
@@ -192,9 +192,9 @@ model-index:
|
|
192 |
name: gsarti/flores_101_amh
|
193 |
type: gsarti/flores_101_amh
|
194 |
metrics:
|
195 |
-
-
|
196 |
-
type: byte_perplexity
|
197 |
value: 3.9726863338897145
|
|
|
198 |
verified: false
|
199 |
- task:
|
200 |
type: text-generation
|
@@ -203,9 +203,9 @@ model-index:
|
|
203 |
name: gsarti/flores_101_ara
|
204 |
type: gsarti/flores_101_ara
|
205 |
metrics:
|
206 |
-
-
|
207 |
-
type: byte_perplexity
|
208 |
value: 1.8083841089875814
|
|
|
209 |
verified: false
|
210 |
- task:
|
211 |
type: text-generation
|
@@ -214,9 +214,9 @@ model-index:
|
|
214 |
name: gsarti/flores_101_asm
|
215 |
type: gsarti/flores_101_asm
|
216 |
metrics:
|
217 |
-
-
|
218 |
-
type: byte_perplexity
|
219 |
value: 5.699102962086425
|
|
|
220 |
verified: false
|
221 |
- task:
|
222 |
type: text-generation
|
@@ -225,9 +225,9 @@ model-index:
|
|
225 |
name: gsarti/flores_101_ast
|
226 |
type: gsarti/flores_101_ast
|
227 |
metrics:
|
228 |
-
-
|
229 |
-
type: byte_perplexity
|
230 |
value: 3.9252047073429384
|
|
|
231 |
verified: false
|
232 |
- task:
|
233 |
type: text-generation
|
@@ -236,9 +236,9 @@ model-index:
|
|
236 |
name: gsarti/flores_101_azj
|
237 |
type: gsarti/flores_101_azj
|
238 |
metrics:
|
239 |
-
-
|
240 |
-
type: byte_perplexity
|
241 |
value: 6.942805054270002
|
|
|
242 |
verified: false
|
243 |
- task:
|
244 |
type: text-generation
|
@@ -247,9 +247,9 @@ model-index:
|
|
247 |
name: gsarti/flores_101_bel
|
248 |
type: gsarti/flores_101_bel
|
249 |
metrics:
|
250 |
-
-
|
251 |
-
type: byte_perplexity
|
252 |
value: 3.614136245847082
|
|
|
253 |
verified: false
|
254 |
- task:
|
255 |
type: text-generation
|
@@ -258,9 +258,9 @@ model-index:
|
|
258 |
name: gsarti/flores_101_ben
|
259 |
type: gsarti/flores_101_ben
|
260 |
metrics:
|
261 |
-
-
|
262 |
-
type: byte_perplexity
|
263 |
value: 5.121491534300969
|
|
|
264 |
verified: false
|
265 |
- task:
|
266 |
type: text-generation
|
@@ -269,9 +269,9 @@ model-index:
|
|
269 |
name: gsarti/flores_101_bos
|
270 |
type: gsarti/flores_101_bos
|
271 |
metrics:
|
272 |
-
-
|
273 |
-
type: byte_perplexity
|
274 |
value: 5.653353469118798
|
|
|
275 |
verified: false
|
276 |
- task:
|
277 |
type: text-generation
|
@@ -280,9 +280,9 @@ model-index:
|
|
280 |
name: gsarti/flores_101_bul
|
281 |
type: gsarti/flores_101_bul
|
282 |
metrics:
|
283 |
-
-
|
284 |
-
type: byte_perplexity
|
285 |
value: 2.7014693938055068
|
|
|
286 |
verified: false
|
287 |
- task:
|
288 |
type: text-generation
|
@@ -291,9 +291,9 @@ model-index:
|
|
291 |
name: gsarti/flores_101_cat
|
292 |
type: gsarti/flores_101_cat
|
293 |
metrics:
|
294 |
-
-
|
295 |
-
type: byte_perplexity
|
296 |
value: 2.305190041967345
|
|
|
297 |
verified: false
|
298 |
- task:
|
299 |
type: text-generation
|
@@ -302,9 +302,9 @@ model-index:
|
|
302 |
name: gsarti/flores_101_ceb
|
303 |
type: gsarti/flores_101_ceb
|
304 |
metrics:
|
305 |
-
-
|
306 |
-
type: byte_perplexity
|
307 |
value: 6.291000321323428
|
|
|
308 |
verified: false
|
309 |
- task:
|
310 |
type: text-generation
|
@@ -313,9 +313,9 @@ model-index:
|
|
313 |
name: gsarti/flores_101_ces
|
314 |
type: gsarti/flores_101_ces
|
315 |
metrics:
|
316 |
-
-
|
317 |
-
type: byte_perplexity
|
318 |
value: 5.447322753586386
|
|
|
319 |
verified: false
|
320 |
- task:
|
321 |
type: text-generation
|
@@ -324,9 +324,9 @@ model-index:
|
|
324 |
name: gsarti/flores_101_ckb
|
325 |
type: gsarti/flores_101_ckb
|
326 |
metrics:
|
327 |
-
-
|
328 |
-
type: byte_perplexity
|
329 |
value: 3.7255124939234765
|
|
|
330 |
verified: false
|
331 |
- task:
|
332 |
type: text-generation
|
@@ -335,9 +335,9 @@ model-index:
|
|
335 |
name: gsarti/flores_101_cym
|
336 |
type: gsarti/flores_101_cym
|
337 |
metrics:
|
338 |
-
-
|
339 |
-
type: byte_perplexity
|
340 |
value: 12.539424151448149
|
|
|
341 |
verified: false
|
342 |
- task:
|
343 |
type: text-generation
|
@@ -346,9 +346,9 @@ model-index:
|
|
346 |
name: gsarti/flores_101_dan
|
347 |
type: gsarti/flores_101_dan
|
348 |
metrics:
|
349 |
-
-
|
350 |
-
type: byte_perplexity
|
351 |
value: 5.183309001005672
|
|
|
352 |
verified: false
|
353 |
- task:
|
354 |
type: text-generation
|
@@ -357,9 +357,9 @@ model-index:
|
|
357 |
name: gsarti/flores_101_deu
|
358 |
type: gsarti/flores_101_deu
|
359 |
metrics:
|
360 |
-
-
|
361 |
-
type: byte_perplexity
|
362 |
value: 3.1180422286591347
|
|
|
363 |
verified: false
|
364 |
- task:
|
365 |
type: text-generation
|
@@ -368,9 +368,9 @@ model-index:
|
|
368 |
name: gsarti/flores_101_ell
|
369 |
type: gsarti/flores_101_ell
|
370 |
metrics:
|
371 |
-
-
|
372 |
-
type: byte_perplexity
|
373 |
value: 2.467943456164706
|
|
|
374 |
verified: false
|
375 |
- task:
|
376 |
type: text-generation
|
@@ -379,9 +379,9 @@ model-index:
|
|
379 |
name: gsarti/flores_101_eng
|
380 |
type: gsarti/flores_101_eng
|
381 |
metrics:
|
382 |
-
-
|
383 |
-
type: byte_perplexity
|
384 |
value: 2.018740628193298
|
|
|
385 |
verified: false
|
386 |
- task:
|
387 |
type: text-generation
|
@@ -390,9 +390,9 @@ model-index:
|
|
390 |
name: gsarti/flores_101_est
|
391 |
type: gsarti/flores_101_est
|
392 |
metrics:
|
393 |
-
-
|
394 |
-
type: byte_perplexity
|
395 |
value: 9.11654425176368
|
|
|
396 |
verified: false
|
397 |
- task:
|
398 |
type: text-generation
|
@@ -401,9 +401,9 @@ model-index:
|
|
401 |
name: gsarti/flores_101_fas
|
402 |
type: gsarti/flores_101_fas
|
403 |
metrics:
|
404 |
-
-
|
405 |
-
type: byte_perplexity
|
406 |
value: 3.058009097116482
|
|
|
407 |
verified: false
|
408 |
- task:
|
409 |
type: text-generation
|
@@ -412,9 +412,9 @@ model-index:
|
|
412 |
name: gsarti/flores_101_fin
|
413 |
type: gsarti/flores_101_fin
|
414 |
metrics:
|
415 |
-
-
|
416 |
-
type: byte_perplexity
|
417 |
value: 6.847047959628553
|
|
|
418 |
verified: false
|
419 |
- task:
|
420 |
type: text-generation
|
@@ -423,9 +423,9 @@ model-index:
|
|
423 |
name: gsarti/flores_101_fra
|
424 |
type: gsarti/flores_101_fra
|
425 |
metrics:
|
426 |
-
-
|
427 |
-
type: byte_perplexity
|
428 |
value: 1.9975177011840075
|
|
|
429 |
verified: false
|
430 |
- task:
|
431 |
type: text-generation
|
@@ -434,9 +434,9 @@ model-index:
|
|
434 |
name: gsarti/flores_101_ful
|
435 |
type: gsarti/flores_101_ful
|
436 |
metrics:
|
437 |
-
-
|
438 |
-
type: byte_perplexity
|
439 |
value: 11.465912731488828
|
|
|
440 |
verified: false
|
441 |
- task:
|
442 |
type: text-generation
|
@@ -445,9 +445,9 @@ model-index:
|
|
445 |
name: gsarti/flores_101_gle
|
446 |
type: gsarti/flores_101_gle
|
447 |
metrics:
|
448 |
-
-
|
449 |
-
type: byte_perplexity
|
450 |
value: 8.681491663539422
|
|
|
451 |
verified: false
|
452 |
- task:
|
453 |
type: text-generation
|
@@ -456,9 +456,9 @@ model-index:
|
|
456 |
name: gsarti/flores_101_glg
|
457 |
type: gsarti/flores_101_glg
|
458 |
metrics:
|
459 |
-
-
|
460 |
-
type: byte_perplexity
|
461 |
value: 3.029991089015508
|
|
|
462 |
verified: false
|
463 |
- task:
|
464 |
type: text-generation
|
@@ -467,9 +467,9 @@ model-index:
|
|
467 |
name: gsarti/flores_101_guj
|
468 |
type: gsarti/flores_101_guj
|
469 |
metrics:
|
470 |
-
-
|
471 |
-
type: byte_perplexity
|
472 |
value: 4.955224230286231
|
|
|
473 |
verified: false
|
474 |
- task:
|
475 |
type: text-generation
|
@@ -478,9 +478,9 @@ model-index:
|
|
478 |
name: gsarti/flores_101_hau
|
479 |
type: gsarti/flores_101_hau
|
480 |
metrics:
|
481 |
-
-
|
482 |
-
type: byte_perplexity
|
483 |
value: 10.758347356372159
|
|
|
484 |
verified: false
|
485 |
- task:
|
486 |
type: text-generation
|
@@ -489,9 +489,9 @@ model-index:
|
|
489 |
name: gsarti/flores_101_heb
|
490 |
type: gsarti/flores_101_heb
|
491 |
metrics:
|
492 |
-
-
|
493 |
-
type: byte_perplexity
|
494 |
value: 3.6004478129801667
|
|
|
495 |
verified: false
|
496 |
- task:
|
497 |
type: text-generation
|
@@ -500,9 +500,9 @@ model-index:
|
|
500 |
name: gsarti/flores_101_hin
|
501 |
type: gsarti/flores_101_hin
|
502 |
metrics:
|
503 |
-
-
|
504 |
-
type: byte_perplexity
|
505 |
value: 4.712530650588064
|
|
|
506 |
verified: false
|
507 |
- task:
|
508 |
type: text-generation
|
@@ -511,9 +511,9 @@ model-index:
|
|
511 |
name: gsarti/flores_101_hrv
|
512 |
type: gsarti/flores_101_hrv
|
513 |
metrics:
|
514 |
-
-
|
515 |
-
type: byte_perplexity
|
516 |
value: 5.822418943372185
|
|
|
517 |
verified: false
|
518 |
- task:
|
519 |
type: text-generation
|
@@ -522,9 +522,9 @@ model-index:
|
|
522 |
name: gsarti/flores_101_hun
|
523 |
type: gsarti/flores_101_hun
|
524 |
metrics:
|
525 |
-
-
|
526 |
-
type: byte_perplexity
|
527 |
value: 6.440482646965992
|
|
|
528 |
verified: false
|
529 |
- task:
|
530 |
type: text-generation
|
@@ -533,9 +533,9 @@ model-index:
|
|
533 |
name: gsarti/flores_101_hye
|
534 |
type: gsarti/flores_101_hye
|
535 |
metrics:
|
536 |
-
-
|
537 |
-
type: byte_perplexity
|
538 |
value: 3.657718918347166
|
|
|
539 |
verified: false
|
540 |
- task:
|
541 |
type: text-generation
|
@@ -544,9 +544,9 @@ model-index:
|
|
544 |
name: gsarti/flores_101_ibo
|
545 |
type: gsarti/flores_101_ibo
|
546 |
metrics:
|
547 |
-
-
|
548 |
-
type: byte_perplexity
|
549 |
value: 5.564814003872672
|
|
|
550 |
verified: false
|
551 |
- task:
|
552 |
type: text-generation
|
@@ -555,9 +555,9 @@ model-index:
|
|
555 |
name: gsarti/flores_101_ind
|
556 |
type: gsarti/flores_101_ind
|
557 |
metrics:
|
558 |
-
-
|
559 |
-
type: byte_perplexity
|
560 |
value: 2.1597101468869373
|
|
|
561 |
verified: false
|
562 |
- task:
|
563 |
type: text-generation
|
@@ -566,9 +566,9 @@ model-index:
|
|
566 |
name: gsarti/flores_101_isl
|
567 |
type: gsarti/flores_101_isl
|
568 |
metrics:
|
569 |
-
-
|
570 |
-
type: byte_perplexity
|
571 |
value: 8.082349269518136
|
|
|
572 |
verified: false
|
573 |
- task:
|
574 |
type: text-generation
|
@@ -577,9 +577,9 @@ model-index:
|
|
577 |
name: gsarti/flores_101_ita
|
578 |
type: gsarti/flores_101_ita
|
579 |
metrics:
|
580 |
-
-
|
581 |
-
type: byte_perplexity
|
582 |
value: 2.9687591414176207
|
|
|
583 |
verified: false
|
584 |
- task:
|
585 |
type: text-generation
|
@@ -588,9 +588,9 @@ model-index:
|
|
588 |
name: gsarti/flores_101_jav
|
589 |
type: gsarti/flores_101_jav
|
590 |
metrics:
|
591 |
-
-
|
592 |
-
type: byte_perplexity
|
593 |
value: 7.0573805415708994
|
|
|
594 |
verified: false
|
595 |
- task:
|
596 |
type: text-generation
|
@@ -599,9 +599,9 @@ model-index:
|
|
599 |
name: gsarti/flores_101_jpn
|
600 |
type: gsarti/flores_101_jpn
|
601 |
metrics:
|
602 |
-
-
|
603 |
-
type: byte_perplexity
|
604 |
value: 2.7758864197116933
|
|
|
605 |
verified: false
|
606 |
- task:
|
607 |
type: text-generation
|
@@ -610,9 +610,9 @@ model-index:
|
|
610 |
name: gsarti/flores_101_kam
|
611 |
type: gsarti/flores_101_kam
|
612 |
metrics:
|
613 |
-
-
|
614 |
-
type: byte_perplexity
|
615 |
value: 11.072949642861332
|
|
|
616 |
verified: false
|
617 |
- task:
|
618 |
type: text-generation
|
@@ -621,9 +621,9 @@ model-index:
|
|
621 |
name: gsarti/flores_101_kan
|
622 |
type: gsarti/flores_101_kan
|
623 |
metrics:
|
624 |
-
-
|
625 |
-
type: byte_perplexity
|
626 |
value: 5.551730651007082
|
|
|
627 |
verified: false
|
628 |
- task:
|
629 |
type: text-generation
|
@@ -632,9 +632,9 @@ model-index:
|
|
632 |
name: gsarti/flores_101_kat
|
633 |
type: gsarti/flores_101_kat
|
634 |
metrics:
|
635 |
-
-
|
636 |
-
type: byte_perplexity
|
637 |
value: 2.522630524283745
|
|
|
638 |
verified: false
|
639 |
- task:
|
640 |
type: text-generation
|
@@ -643,9 +643,9 @@ model-index:
|
|
643 |
name: gsarti/flores_101_kaz
|
644 |
type: gsarti/flores_101_kaz
|
645 |
metrics:
|
646 |
-
-
|
647 |
-
type: byte_perplexity
|
648 |
value: 3.3901748516975574
|
|
|
649 |
verified: false
|
650 |
- task:
|
651 |
type: text-generation
|
@@ -654,9 +654,9 @@ model-index:
|
|
654 |
name: gsarti/flores_101_kea
|
655 |
type: gsarti/flores_101_kea
|
656 |
metrics:
|
657 |
-
-
|
658 |
-
type: byte_perplexity
|
659 |
value: 8.918534182590863
|
|
|
660 |
verified: false
|
661 |
- task:
|
662 |
type: text-generation
|
@@ -665,9 +665,9 @@ model-index:
|
|
665 |
name: gsarti/flores_101_kir
|
666 |
type: gsarti/flores_101_kir
|
667 |
metrics:
|
668 |
-
-
|
669 |
-
type: byte_perplexity
|
670 |
value: 3.729278369847201
|
|
|
671 |
verified: false
|
672 |
- task:
|
673 |
type: text-generation
|
@@ -676,9 +676,9 @@ model-index:
|
|
676 |
name: gsarti/flores_101_kor
|
677 |
type: gsarti/flores_101_kor
|
678 |
metrics:
|
679 |
-
-
|
680 |
-
type: byte_perplexity
|
681 |
value: 3.932884847226212
|
|
|
682 |
verified: false
|
683 |
- task:
|
684 |
type: text-generation
|
@@ -687,9 +687,9 @@ model-index:
|
|
687 |
name: gsarti/flores_101_lao
|
688 |
type: gsarti/flores_101_lao
|
689 |
metrics:
|
690 |
-
-
|
691 |
-
type: byte_perplexity
|
692 |
value: 2.9077314760849924
|
|
|
693 |
verified: false
|
694 |
- task:
|
695 |
type: text-generation
|
@@ -698,9 +698,9 @@ model-index:
|
|
698 |
name: gsarti/flores_101_lav
|
699 |
type: gsarti/flores_101_lav
|
700 |
metrics:
|
701 |
-
-
|
702 |
-
type: byte_perplexity
|
703 |
value: 7.777221919194806
|
|
|
704 |
verified: false
|
705 |
- task:
|
706 |
type: text-generation
|
@@ -709,9 +709,9 @@ model-index:
|
|
709 |
name: gsarti/flores_101_lin
|
710 |
type: gsarti/flores_101_lin
|
711 |
metrics:
|
712 |
-
-
|
713 |
-
type: byte_perplexity
|
714 |
value: 7.524842908050988
|
|
|
715 |
verified: false
|
716 |
- task:
|
717 |
type: text-generation
|
@@ -720,9 +720,9 @@ model-index:
|
|
720 |
name: gsarti/flores_101_lit
|
721 |
type: gsarti/flores_101_lit
|
722 |
metrics:
|
723 |
-
-
|
724 |
-
type: byte_perplexity
|
725 |
value: 7.369179434621725
|
|
|
726 |
verified: false
|
727 |
- task:
|
728 |
type: text-generation
|
@@ -731,9 +731,9 @@ model-index:
|
|
731 |
name: gsarti/flores_101_ltz
|
732 |
type: gsarti/flores_101_ltz
|
733 |
metrics:
|
734 |
-
-
|
735 |
-
type: byte_perplexity
|
736 |
value: 8.801059747949214
|
|
|
737 |
verified: false
|
738 |
- task:
|
739 |
type: text-generation
|
@@ -742,9 +742,9 @@ model-index:
|
|
742 |
name: gsarti/flores_101_lug
|
743 |
type: gsarti/flores_101_lug
|
744 |
metrics:
|
745 |
-
-
|
746 |
-
type: byte_perplexity
|
747 |
value: 8.483203026364786
|
|
|
748 |
verified: false
|
749 |
- task:
|
750 |
type: text-generation
|
@@ -753,9 +753,9 @@ model-index:
|
|
753 |
name: gsarti/flores_101_luo
|
754 |
type: gsarti/flores_101_luo
|
755 |
metrics:
|
756 |
-
-
|
757 |
-
type: byte_perplexity
|
758 |
value: 11.975963093623681
|
|
|
759 |
verified: false
|
760 |
- task:
|
761 |
type: text-generation
|
@@ -764,9 +764,9 @@ model-index:
|
|
764 |
name: gsarti/flores_101_mal
|
765 |
type: gsarti/flores_101_mal
|
766 |
metrics:
|
767 |
-
-
|
768 |
-
type: byte_perplexity
|
769 |
value: 4.615948455160037
|
|
|
770 |
verified: false
|
771 |
- task:
|
772 |
type: text-generation
|
@@ -775,9 +775,9 @@ model-index:
|
|
775 |
name: gsarti/flores_101_mar
|
776 |
type: gsarti/flores_101_mar
|
777 |
metrics:
|
778 |
-
-
|
779 |
-
type: byte_perplexity
|
780 |
value: 5.483253482821379
|
|
|
781 |
verified: false
|
782 |
- task:
|
783 |
type: text-generation
|
@@ -786,9 +786,9 @@ model-index:
|
|
786 |
name: gsarti/flores_101_mkd
|
787 |
type: gsarti/flores_101_mkd
|
788 |
metrics:
|
789 |
-
-
|
790 |
-
type: byte_perplexity
|
791 |
value: 2.9656732291754087
|
|
|
792 |
verified: false
|
793 |
- task:
|
794 |
type: text-generation
|
@@ -797,9 +797,9 @@ model-index:
|
|
797 |
name: gsarti/flores_101_mlt
|
798 |
type: gsarti/flores_101_mlt
|
799 |
metrics:
|
800 |
-
-
|
801 |
-
type: byte_perplexity
|
802 |
value: 15.004773437665275
|
|
|
803 |
verified: false
|
804 |
- task:
|
805 |
type: text-generation
|
@@ -808,9 +808,9 @@ model-index:
|
|
808 |
name: gsarti/flores_101_mon
|
809 |
type: gsarti/flores_101_mon
|
810 |
metrics:
|
811 |
-
-
|
812 |
-
type: byte_perplexity
|
813 |
value: 3.410598542315402
|
|
|
814 |
verified: false
|
815 |
- task:
|
816 |
type: text-generation
|
@@ -819,9 +819,9 @@ model-index:
|
|
819 |
name: gsarti/flores_101_mri
|
820 |
type: gsarti/flores_101_mri
|
821 |
metrics:
|
822 |
-
-
|
823 |
-
type: byte_perplexity
|
824 |
value: 7.474035895661322
|
|
|
825 |
verified: false
|
826 |
- task:
|
827 |
type: text-generation
|
@@ -830,9 +830,9 @@ model-index:
|
|
830 |
name: gsarti/flores_101_msa
|
831 |
type: gsarti/flores_101_msa
|
832 |
metrics:
|
833 |
-
-
|
834 |
-
type: byte_perplexity
|
835 |
value: 2.5710001772665634
|
|
|
836 |
verified: false
|
837 |
- task:
|
838 |
type: text-generation
|
@@ -841,9 +841,9 @@ model-index:
|
|
841 |
name: gsarti/flores_101_mya
|
842 |
type: gsarti/flores_101_mya
|
843 |
metrics:
|
844 |
-
-
|
845 |
-
type: byte_perplexity
|
846 |
value: 2.413577969878331
|
|
|
847 |
verified: false
|
848 |
- task:
|
849 |
type: text-generation
|
@@ -852,9 +852,9 @@ model-index:
|
|
852 |
name: gsarti/flores_101_nld
|
853 |
type: gsarti/flores_101_nld
|
854 |
metrics:
|
855 |
-
-
|
856 |
-
type: byte_perplexity
|
857 |
value: 4.127831721885065
|
|
|
858 |
verified: false
|
859 |
- task:
|
860 |
type: text-generation
|
@@ -863,9 +863,9 @@ model-index:
|
|
863 |
name: gsarti/flores_101_nob
|
864 |
type: gsarti/flores_101_nob
|
865 |
metrics:
|
866 |
-
-
|
867 |
-
type: byte_perplexity
|
868 |
value: 5.402763169129877
|
|
|
869 |
verified: false
|
870 |
- task:
|
871 |
type: text-generation
|
@@ -874,9 +874,9 @@ model-index:
|
|
874 |
name: gsarti/flores_101_npi
|
875 |
type: gsarti/flores_101_npi
|
876 |
metrics:
|
877 |
-
-
|
878 |
-
type: byte_perplexity
|
879 |
value: 5.199342701937889
|
|
|
880 |
verified: false
|
881 |
- task:
|
882 |
type: text-generation
|
@@ -885,9 +885,9 @@ model-index:
|
|
885 |
name: gsarti/flores_101_nso
|
886 |
type: gsarti/flores_101_nso
|
887 |
metrics:
|
888 |
-
-
|
889 |
-
type: byte_perplexity
|
890 |
value: 8.154626800955667
|
|
|
891 |
verified: false
|
892 |
- task:
|
893 |
type: text-generation
|
@@ -896,9 +896,9 @@ model-index:
|
|
896 |
name: gsarti/flores_101_nya
|
897 |
type: gsarti/flores_101_nya
|
898 |
metrics:
|
899 |
-
-
|
900 |
-
type: byte_perplexity
|
901 |
value: 8.179860208369393
|
|
|
902 |
verified: false
|
903 |
- task:
|
904 |
type: text-generation
|
@@ -907,9 +907,9 @@ model-index:
|
|
907 |
name: gsarti/flores_101_oci
|
908 |
type: gsarti/flores_101_oci
|
909 |
metrics:
|
910 |
-
-
|
911 |
-
type: byte_perplexity
|
912 |
value: 4.8617357393685845
|
|
|
913 |
verified: false
|
914 |
- task:
|
915 |
type: text-generation
|
@@ -918,9 +918,9 @@ model-index:
|
|
918 |
name: gsarti/flores_101_orm
|
919 |
type: gsarti/flores_101_orm
|
920 |
metrics:
|
921 |
-
-
|
922 |
-
type: byte_perplexity
|
923 |
value: 12.911595421079408
|
|
|
924 |
verified: false
|
925 |
- task:
|
926 |
type: text-generation
|
@@ -929,9 +929,9 @@ model-index:
|
|
929 |
name: gsarti/flores_101_ory
|
930 |
type: gsarti/flores_101_ory
|
931 |
metrics:
|
932 |
-
-
|
933 |
-
type: byte_perplexity
|
934 |
value: 5.189421861225964
|
|
|
935 |
verified: false
|
936 |
- task:
|
937 |
type: text-generation
|
@@ -940,9 +940,9 @@ model-index:
|
|
940 |
name: gsarti/flores_101_pan
|
941 |
type: gsarti/flores_101_pan
|
942 |
metrics:
|
943 |
-
-
|
944 |
-
type: byte_perplexity
|
945 |
value: 4.698477289331806
|
|
|
946 |
verified: false
|
947 |
- task:
|
948 |
type: text-generation
|
@@ -951,9 +951,9 @@ model-index:
|
|
951 |
name: gsarti/flores_101_pol
|
952 |
type: gsarti/flores_101_pol
|
953 |
metrics:
|
954 |
-
-
|
955 |
-
type: byte_perplexity
|
956 |
value: 4.625550458479643
|
|
|
957 |
verified: false
|
958 |
- task:
|
959 |
type: text-generation
|
@@ -962,9 +962,9 @@ model-index:
|
|
962 |
name: gsarti/flores_101_por
|
963 |
type: gsarti/flores_101_por
|
964 |
metrics:
|
965 |
-
-
|
966 |
-
type: byte_perplexity
|
967 |
value: 1.9754515986213523
|
|
|
968 |
verified: false
|
969 |
- task:
|
970 |
type: text-generation
|
@@ -973,9 +973,9 @@ model-index:
|
|
973 |
name: gsarti/flores_101_pus
|
974 |
type: gsarti/flores_101_pus
|
975 |
metrics:
|
976 |
-
-
|
977 |
-
type: byte_perplexity
|
978 |
value: 4.4963371422771585
|
|
|
979 |
verified: false
|
980 |
- task:
|
981 |
type: text-generation
|
@@ -984,9 +984,9 @@ model-index:
|
|
984 |
name: gsarti/flores_101_ron
|
985 |
type: gsarti/flores_101_ron
|
986 |
metrics:
|
987 |
-
-
|
988 |
-
type: byte_perplexity
|
989 |
value: 4.965456830031304
|
|
|
990 |
verified: false
|
991 |
- task:
|
992 |
type: text-generation
|
@@ -995,9 +995,9 @@ model-index:
|
|
995 |
name: gsarti/flores_101_rus
|
996 |
type: gsarti/flores_101_rus
|
997 |
metrics:
|
998 |
-
-
|
999 |
-
type: byte_perplexity
|
1000 |
value: 2.0498020542445303
|
|
|
1001 |
verified: false
|
1002 |
- task:
|
1003 |
type: text-generation
|
@@ -1006,9 +1006,9 @@ model-index:
|
|
1006 |
name: gsarti/flores_101_slk
|
1007 |
type: gsarti/flores_101_slk
|
1008 |
metrics:
|
1009 |
-
-
|
1010 |
-
type: byte_perplexity
|
1011 |
value: 6.450822127057479
|
|
|
1012 |
verified: false
|
1013 |
- task:
|
1014 |
type: text-generation
|
@@ -1017,9 +1017,9 @@ model-index:
|
|
1017 |
name: gsarti/flores_101_slv
|
1018 |
type: gsarti/flores_101_slv
|
1019 |
metrics:
|
1020 |
-
-
|
1021 |
-
type: byte_perplexity
|
1022 |
value: 6.620252120186232
|
|
|
1023 |
verified: false
|
1024 |
- task:
|
1025 |
type: text-generation
|
@@ -1028,9 +1028,9 @@ model-index:
|
|
1028 |
name: gsarti/flores_101_sna
|
1029 |
type: gsarti/flores_101_sna
|
1030 |
metrics:
|
1031 |
-
-
|
1032 |
-
type: byte_perplexity
|
1033 |
value: 8.462166771382726
|
|
|
1034 |
verified: false
|
1035 |
- task:
|
1036 |
type: text-generation
|
@@ -1039,9 +1039,9 @@ model-index:
|
|
1039 |
name: gsarti/flores_101_snd
|
1040 |
type: gsarti/flores_101_snd
|
1041 |
metrics:
|
1042 |
-
-
|
1043 |
-
type: byte_perplexity
|
1044 |
value: 5.466066951221973
|
|
|
1045 |
verified: false
|
1046 |
- task:
|
1047 |
type: text-generation
|
@@ -1050,9 +1050,9 @@ model-index:
|
|
1050 |
name: gsarti/flores_101_som
|
1051 |
type: gsarti/flores_101_som
|
1052 |
metrics:
|
1053 |
-
-
|
1054 |
-
type: byte_perplexity
|
1055 |
value: 11.95918054093392
|
|
|
1056 |
verified: false
|
1057 |
- task:
|
1058 |
type: text-generation
|
@@ -1061,9 +1061,9 @@ model-index:
|
|
1061 |
name: gsarti/flores_101_spa
|
1062 |
type: gsarti/flores_101_spa
|
1063 |
metrics:
|
1064 |
-
-
|
1065 |
-
type: byte_perplexity
|
1066 |
value: 1.8965140104323535
|
|
|
1067 |
verified: false
|
1068 |
- task:
|
1069 |
type: text-generation
|
@@ -1072,9 +1072,9 @@ model-index:
|
|
1072 |
name: gsarti/flores_101_srp
|
1073 |
type: gsarti/flores_101_srp
|
1074 |
metrics:
|
1075 |
-
-
|
1076 |
-
type: byte_perplexity
|
1077 |
value: 2.871214785885079
|
|
|
1078 |
verified: false
|
1079 |
- task:
|
1080 |
type: text-generation
|
@@ -1083,9 +1083,9 @@ model-index:
|
|
1083 |
name: gsarti/flores_101_swe
|
1084 |
type: gsarti/flores_101_swe
|
1085 |
metrics:
|
1086 |
-
-
|
1087 |
-
type: byte_perplexity
|
1088 |
value: 5.054972008155866
|
|
|
1089 |
verified: false
|
1090 |
- task:
|
1091 |
type: text-generation
|
@@ -1094,9 +1094,9 @@ model-index:
|
|
1094 |
name: gsarti/flores_101_swh
|
1095 |
type: gsarti/flores_101_swh
|
1096 |
metrics:
|
1097 |
-
-
|
1098 |
-
type: byte_perplexity
|
1099 |
value: 3.6973091886730676
|
|
|
1100 |
verified: false
|
1101 |
- task:
|
1102 |
type: text-generation
|
@@ -1105,9 +1105,9 @@ model-index:
|
|
1105 |
name: gsarti/flores_101_tam
|
1106 |
type: gsarti/flores_101_tam
|
1107 |
metrics:
|
1108 |
-
-
|
1109 |
-
type: byte_perplexity
|
1110 |
value: 4.539493400469833
|
|
|
1111 |
verified: false
|
1112 |
- task:
|
1113 |
type: text-generation
|
@@ -1116,9 +1116,9 @@ model-index:
|
|
1116 |
name: gsarti/flores_101_tel
|
1117 |
type: gsarti/flores_101_tel
|
1118 |
metrics:
|
1119 |
-
-
|
1120 |
-
type: byte_perplexity
|
1121 |
value: 5.807499987508966
|
|
|
1122 |
verified: false
|
1123 |
- task:
|
1124 |
type: text-generation
|
@@ -1127,9 +1127,9 @@ model-index:
|
|
1127 |
name: gsarti/flores_101_tgk
|
1128 |
type: gsarti/flores_101_tgk
|
1129 |
metrics:
|
1130 |
-
-
|
1131 |
-
type: byte_perplexity
|
1132 |
value: 3.5994818827380426
|
|
|
1133 |
verified: false
|
1134 |
- task:
|
1135 |
type: text-generation
|
@@ -1138,9 +1138,9 @@ model-index:
|
|
1138 |
name: gsarti/flores_101_tgl
|
1139 |
type: gsarti/flores_101_tgl
|
1140 |
metrics:
|
1141 |
-
-
|
1142 |
-
type: byte_perplexity
|
1143 |
value: 5.667053833119858
|
|
|
1144 |
verified: false
|
1145 |
- task:
|
1146 |
type: text-generation
|
@@ -1149,9 +1149,9 @@ model-index:
|
|
1149 |
name: gsarti/flores_101_tha
|
1150 |
type: gsarti/flores_101_tha
|
1151 |
metrics:
|
1152 |
-
-
|
1153 |
-
type: byte_perplexity
|
1154 |
value: 2.365940201944242
|
|
|
1155 |
verified: false
|
1156 |
- task:
|
1157 |
type: text-generation
|
@@ -1160,9 +1160,9 @@ model-index:
|
|
1160 |
name: gsarti/flores_101_tur
|
1161 |
type: gsarti/flores_101_tur
|
1162 |
metrics:
|
1163 |
-
-
|
1164 |
-
type: byte_perplexity
|
1165 |
value: 4.885014749844601
|
|
|
1166 |
verified: false
|
1167 |
- task:
|
1168 |
type: text-generation
|
@@ -1171,9 +1171,9 @@ model-index:
|
|
1171 |
name: gsarti/flores_101_ukr
|
1172 |
type: gsarti/flores_101_ukr
|
1173 |
metrics:
|
1174 |
-
-
|
1175 |
-
type: byte_perplexity
|
1176 |
value: 2.7240934990288483
|
|
|
1177 |
verified: false
|
1178 |
- task:
|
1179 |
type: text-generation
|
@@ -1182,9 +1182,9 @@ model-index:
|
|
1182 |
name: gsarti/flores_101_umb
|
1183 |
type: gsarti/flores_101_umb
|
1184 |
metrics:
|
1185 |
-
-
|
1186 |
-
type: byte_perplexity
|
1187 |
value: 12.766915508610673
|
|
|
1188 |
verified: false
|
1189 |
- task:
|
1190 |
type: text-generation
|
@@ -1193,9 +1193,9 @@ model-index:
|
|
1193 |
name: gsarti/flores_101_urd
|
1194 |
type: gsarti/flores_101_urd
|
1195 |
metrics:
|
1196 |
-
-
|
1197 |
-
type: byte_perplexity
|
1198 |
value: 1.9797467071381232
|
|
|
1199 |
verified: false
|
1200 |
- task:
|
1201 |
type: text-generation
|
@@ -1204,9 +1204,9 @@ model-index:
|
|
1204 |
name: gsarti/flores_101_uzb
|
1205 |
type: gsarti/flores_101_uzb
|
1206 |
metrics:
|
1207 |
-
-
|
1208 |
-
type: byte_perplexity
|
1209 |
value: 12.002337637722146
|
|
|
1210 |
verified: false
|
1211 |
- task:
|
1212 |
type: text-generation
|
@@ -1215,9 +1215,9 @@ model-index:
|
|
1215 |
name: gsarti/flores_101_vie
|
1216 |
type: gsarti/flores_101_vie
|
1217 |
metrics:
|
1218 |
-
-
|
1219 |
-
type: byte_perplexity
|
1220 |
value: 1.76578415476397
|
|
|
1221 |
verified: false
|
1222 |
- task:
|
1223 |
type: text-generation
|
@@ -1226,9 +1226,9 @@ model-index:
|
|
1226 |
name: gsarti/flores_101_wol
|
1227 |
type: gsarti/flores_101_wol
|
1228 |
metrics:
|
1229 |
-
-
|
1230 |
-
type: byte_perplexity
|
1231 |
value: 9.144285650306488
|
|
|
1232 |
verified: false
|
1233 |
- task:
|
1234 |
type: text-generation
|
@@ -1237,9 +1237,9 @@ model-index:
|
|
1237 |
name: gsarti/flores_101_xho
|
1238 |
type: gsarti/flores_101_xho
|
1239 |
metrics:
|
1240 |
-
-
|
1241 |
-
type: byte_perplexity
|
1242 |
value: 7.403240538286952
|
|
|
1243 |
verified: false
|
1244 |
- task:
|
1245 |
type: text-generation
|
@@ -1248,9 +1248,9 @@ model-index:
|
|
1248 |
name: gsarti/flores_101_yor
|
1249 |
type: gsarti/flores_101_yor
|
1250 |
metrics:
|
1251 |
-
-
|
1252 |
-
type: byte_perplexity
|
1253 |
value: 5.91272037551173
|
|
|
1254 |
verified: false
|
1255 |
- task:
|
1256 |
type: text-generation
|
@@ -1259,9 +1259,9 @@ model-index:
|
|
1259 |
name: gsarti/flores_101_zho_simpl
|
1260 |
type: gsarti/flores_101_zho_simpl
|
1261 |
metrics:
|
1262 |
-
-
|
1263 |
-
type: byte_perplexity
|
1264 |
value: 2.2769070822768533
|
|
|
1265 |
verified: false
|
1266 |
- task:
|
1267 |
type: text-generation
|
@@ -1270,9 +1270,9 @@ model-index:
|
|
1270 |
name: gsarti/flores_101_zho_trad
|
1271 |
type: gsarti/flores_101_zho_trad
|
1272 |
metrics:
|
1273 |
-
-
|
1274 |
-
type: byte_perplexity
|
1275 |
value: 2.5180582198242383
|
|
|
1276 |
verified: false
|
1277 |
- task:
|
1278 |
type: text-generation
|
@@ -1281,9 +1281,9 @@ model-index:
|
|
1281 |
name: gsarti/flores_101_zul
|
1282 |
type: gsarti/flores_101_zul
|
1283 |
metrics:
|
1284 |
-
-
|
1285 |
-
type: byte_perplexity
|
1286 |
value: 8.53353320693145
|
|
|
1287 |
verified: false
|
1288 |
- task:
|
1289 |
type: text-generation
|
@@ -1292,9 +1292,9 @@ model-index:
|
|
1292 |
name: headqa
|
1293 |
type: headqa
|
1294 |
metrics:
|
1295 |
-
-
|
1296 |
-
type: acc
|
1297 |
value: 0.26440554339897887
|
|
|
1298 |
verified: false
|
1299 |
- task:
|
1300 |
type: text-generation
|
@@ -1303,9 +1303,9 @@ model-index:
|
|
1303 |
name: hellaswag
|
1304 |
type: hellaswag
|
1305 |
metrics:
|
1306 |
-
-
|
1307 |
-
type: acc
|
1308 |
value: 0.41236805417247563
|
|
|
1309 |
verified: false
|
1310 |
- task:
|
1311 |
type: text-generation
|
@@ -1314,9 +1314,9 @@ model-index:
|
|
1314 |
name: logiqa
|
1315 |
type: logiqa
|
1316 |
metrics:
|
1317 |
-
-
|
1318 |
-
type: acc
|
1319 |
value: 0.2073732718894009
|
|
|
1320 |
verified: false
|
1321 |
- task:
|
1322 |
type: text-generation
|
@@ -1325,9 +1325,9 @@ model-index:
|
|
1325 |
name: mathqa
|
1326 |
type: mathqa
|
1327 |
metrics:
|
1328 |
-
-
|
1329 |
-
type: acc
|
1330 |
value: 0.24958123953098826
|
|
|
1331 |
verified: false
|
1332 |
- task:
|
1333 |
type: text-generation
|
@@ -1336,9 +1336,9 @@ model-index:
|
|
1336 |
name: mc_taco
|
1337 |
type: mc_taco
|
1338 |
metrics:
|
1339 |
-
-
|
1340 |
-
type: em
|
1341 |
value: 0.11936936936936937
|
|
|
1342 |
verified: false
|
1343 |
- task:
|
1344 |
type: text-generation
|
@@ -1347,9 +1347,9 @@ model-index:
|
|
1347 |
name: mnli
|
1348 |
type: mnli
|
1349 |
metrics:
|
1350 |
-
-
|
1351 |
-
type: acc
|
1352 |
value: 0.35496688741721855
|
|
|
1353 |
verified: false
|
1354 |
- task:
|
1355 |
type: text-generation
|
@@ -1358,9 +1358,9 @@ model-index:
|
|
1358 |
name: mnli_mismatched
|
1359 |
type: mnli_mismatched
|
1360 |
metrics:
|
1361 |
-
-
|
1362 |
-
type: acc
|
1363 |
value: 0.35211554109031734
|
|
|
1364 |
verified: false
|
1365 |
- task:
|
1366 |
type: text-generation
|
@@ -1369,9 +1369,9 @@ model-index:
|
|
1369 |
name: mrpc
|
1370 |
type: mrpc
|
1371 |
metrics:
|
1372 |
-
-
|
1373 |
-
type: acc
|
1374 |
value: 0.5857843137254902
|
|
|
1375 |
verified: false
|
1376 |
- task:
|
1377 |
type: text-generation
|
@@ -1380,9 +1380,9 @@ model-index:
|
|
1380 |
name: multirc
|
1381 |
type: multirc
|
1382 |
metrics:
|
1383 |
-
-
|
1384 |
-
type: acc
|
1385 |
value: 0.5375412541254125
|
|
|
1386 |
verified: false
|
1387 |
- task:
|
1388 |
type: text-generation
|
@@ -1391,9 +1391,9 @@ model-index:
|
|
1391 |
name: openbookqa
|
1392 |
type: openbookqa
|
1393 |
metrics:
|
1394 |
-
-
|
1395 |
-
type: acc
|
1396 |
value: 0.216
|
|
|
1397 |
verified: false
|
1398 |
- task:
|
1399 |
type: text-generation
|
@@ -1402,9 +1402,9 @@ model-index:
|
|
1402 |
name: piqa
|
1403 |
type: piqa
|
1404 |
metrics:
|
1405 |
-
-
|
1406 |
-
type: acc
|
1407 |
value: 0.7078346028291621
|
|
|
1408 |
verified: false
|
1409 |
- task:
|
1410 |
type: text-generation
|
@@ -1413,9 +1413,9 @@ model-index:
|
|
1413 |
name: prost
|
1414 |
type: prost
|
1415 |
metrics:
|
1416 |
-
-
|
1417 |
-
type: acc
|
1418 |
value: 0.22683603757472245
|
|
|
1419 |
verified: false
|
1420 |
- task:
|
1421 |
type: text-generation
|
@@ -1424,9 +1424,9 @@ model-index:
|
|
1424 |
name: pubmedqa
|
1425 |
type: pubmedqa
|
1426 |
metrics:
|
1427 |
-
-
|
1428 |
-
type: acc
|
1429 |
value: 0.616
|
|
|
1430 |
verified: false
|
1431 |
- task:
|
1432 |
type: text-generation
|
@@ -1435,9 +1435,9 @@ model-index:
|
|
1435 |
name: qnli
|
1436 |
type: qnli
|
1437 |
metrics:
|
1438 |
-
-
|
1439 |
-
type: acc
|
1440 |
value: 0.5072304594545122
|
|
|
1441 |
verified: false
|
1442 |
- task:
|
1443 |
type: text-generation
|
@@ -1446,9 +1446,9 @@ model-index:
|
|
1446 |
name: qqp
|
1447 |
type: qqp
|
1448 |
metrics:
|
1449 |
-
-
|
1450 |
-
type: acc
|
1451 |
value: 0.3842443729903537
|
|
|
1452 |
verified: false
|
1453 |
- task:
|
1454 |
type: text-generation
|
@@ -1457,9 +1457,9 @@ model-index:
|
|
1457 |
name: race
|
1458 |
type: race
|
1459 |
metrics:
|
1460 |
-
-
|
1461 |
-
type: acc
|
1462 |
value: 0.3521531100478469
|
|
|
1463 |
verified: false
|
1464 |
- task:
|
1465 |
type: text-generation
|
@@ -1468,9 +1468,9 @@ model-index:
|
|
1468 |
name: rte
|
1469 |
type: rte
|
1470 |
metrics:
|
1471 |
-
-
|
1472 |
-
type: acc
|
1473 |
value: 0.47653429602888087
|
|
|
1474 |
verified: false
|
1475 |
- task:
|
1476 |
type: text-generation
|
@@ -1479,9 +1479,9 @@ model-index:
|
|
1479 |
name: sciq
|
1480 |
type: sciq
|
1481 |
metrics:
|
1482 |
-
-
|
1483 |
-
type: acc
|
1484 |
value: 0.892
|
|
|
1485 |
verified: false
|
1486 |
- task:
|
1487 |
type: text-generation
|
@@ -1490,9 +1490,9 @@ model-index:
|
|
1490 |
name: sst
|
1491 |
type: sst
|
1492 |
metrics:
|
1493 |
-
-
|
1494 |
-
type: acc
|
1495 |
value: 0.5177752293577982
|
|
|
1496 |
verified: false
|
1497 |
- task:
|
1498 |
type: text-generation
|
@@ -1501,9 +1501,9 @@ model-index:
|
|
1501 |
name: triviaqa
|
1502 |
type: triviaqa
|
1503 |
metrics:
|
1504 |
-
-
|
1505 |
-
type: acc
|
1506 |
value: 0.041633518960487934
|
|
|
1507 |
verified: false
|
1508 |
- task:
|
1509 |
type: text-generation
|
@@ -1512,9 +1512,9 @@ model-index:
|
|
1512 |
name: tydiqa_primary
|
1513 |
type: tydiqa_primary
|
1514 |
metrics:
|
1515 |
-
-
|
1516 |
-
type: acc
|
1517 |
value: 0.3011337608795236
|
|
|
1518 |
verified: false
|
1519 |
- task:
|
1520 |
type: text-generation
|
@@ -1523,9 +1523,9 @@ model-index:
|
|
1523 |
name: webqs
|
1524 |
type: webqs
|
1525 |
metrics:
|
1526 |
-
-
|
1527 |
-
type: acc
|
1528 |
value: 0.01673228346456693
|
|
|
1529 |
verified: false
|
1530 |
- task:
|
1531 |
type: text-generation
|
@@ -1534,9 +1534,9 @@ model-index:
|
|
1534 |
name: wic
|
1535 |
type: wic
|
1536 |
metrics:
|
1537 |
-
-
|
1538 |
-
type: acc
|
1539 |
value: 0.5015673981191222
|
|
|
1540 |
verified: false
|
1541 |
- task:
|
1542 |
type: text-generation
|
@@ -1545,9 +1545,9 @@ model-index:
|
|
1545 |
name: winogrande
|
1546 |
type: winogrande
|
1547 |
metrics:
|
1548 |
-
-
|
1549 |
-
type: acc
|
1550 |
value: 0.5864246250986582
|
|
|
1551 |
verified: false
|
1552 |
- task:
|
1553 |
type: text-generation
|
@@ -1556,9 +1556,9 @@ model-index:
|
|
1556 |
name: wnli
|
1557 |
type: wnli
|
1558 |
metrics:
|
1559 |
-
-
|
1560 |
-
type: acc
|
1561 |
value: 0.471830985915493
|
|
|
1562 |
verified: false
|
1563 |
- task:
|
1564 |
type: text-generation
|
@@ -1567,9 +1567,9 @@ model-index:
|
|
1567 |
name: wsc
|
1568 |
type: wsc
|
1569 |
metrics:
|
1570 |
-
-
|
1571 |
-
type: acc
|
1572 |
value: 0.4423076923076923
|
|
|
1573 |
verified: false
|
1574 |
- task:
|
1575 |
type: text-generation
|
@@ -1578,18 +1578,110 @@ model-index:
|
|
1578 |
name: humaneval
|
1579 |
type: humaneval
|
1580 |
metrics:
|
1581 |
-
-
|
1582 |
-
type: pass@1
|
1583 |
value: 0.15524390243902436
|
|
|
1584 |
verified: false
|
1585 |
-
-
|
1586 |
-
type: pass@10
|
1587 |
value: 0.3220367632383857
|
|
|
1588 |
verified: false
|
1589 |
-
-
|
1590 |
-
type: pass@100
|
1591 |
value: 0.5545431515723145
|
|
|
1592 |
verified: false
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1593 |
---
|
1594 |
|
1595 |
<h1 style='text-align: center '>BLOOM LM</h1>
|
@@ -2240,3 +2332,17 @@ Initial prompting experiments using interim checkpoints: https://huggingface.co/
|
|
2240 |
|
2241 |
Margaret Mitchell, Giada Pistilli, Yacine Jernite, Ezinwanne Ozoani, Marissa Gerchick, Nazneen Rajani, Sasha Luccioni, Irene Solaiman, Maraim Masoud, Somaieh Nikpoor, Carlos Muñoz Ferrandis, Stas Bekman, Christopher Akiki, Danish Contractor, David Lansky, Angelina McMillan-Major, Tristan Thrush, Suzana Ilić, Gérard Dupont, Shayne Longpre, Manan Dey, Stella Biderman, Douwe Kiela, Emi Baylor, Teven Le Scao, Aaron Gokaslan, Julien Launay, Niklas Muennighoff
|
2242 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
---
|
|
|
2 |
language:
|
3 |
- ak
|
4 |
- ar
|
|
|
48 |
- zhs
|
49 |
- zht
|
50 |
- zu
|
51 |
+
license: bigscience-bloom-rail-1.0
|
52 |
pipeline_tag: text-generation
|
53 |
model-index:
|
54 |
- name: bloom
|
|
|
60 |
name: arc_challenge
|
61 |
type: arc_challenge
|
62 |
metrics:
|
63 |
+
- type: acc
|
|
|
64 |
value: 0.27986348122866894
|
65 |
+
name: acc
|
66 |
verified: false
|
67 |
- task:
|
68 |
type: text-generation
|
|
|
71 |
name: arc_easy
|
72 |
type: arc_easy
|
73 |
metrics:
|
74 |
+
- type: acc
|
|
|
75 |
value: 0.5946969696969697
|
76 |
+
name: acc
|
77 |
verified: false
|
78 |
- task:
|
79 |
type: text-generation
|
|
|
82 |
name: axb
|
83 |
type: axb
|
84 |
metrics:
|
85 |
+
- type: acc
|
|
|
86 |
value: 0.4433876811594203
|
87 |
+
name: acc
|
88 |
verified: false
|
89 |
- task:
|
90 |
type: text-generation
|
|
|
93 |
name: axg
|
94 |
type: axg
|
95 |
metrics:
|
96 |
+
- type: acc
|
|
|
97 |
value: 0.5
|
98 |
+
name: acc
|
99 |
verified: false
|
100 |
- task:
|
101 |
type: text-generation
|
|
|
104 |
name: boolq
|
105 |
type: boolq
|
106 |
metrics:
|
107 |
+
- type: acc
|
|
|
108 |
value: 0.6165137614678899
|
109 |
+
name: acc
|
110 |
verified: false
|
111 |
- task:
|
112 |
type: text-generation
|
|
|
115 |
name: cb
|
116 |
type: cb
|
117 |
metrics:
|
118 |
+
- type: acc
|
|
|
119 |
value: 0.30357142857142855
|
120 |
+
name: acc
|
121 |
verified: false
|
122 |
- task:
|
123 |
type: text-generation
|
|
|
126 |
name: cola
|
127 |
type: cola
|
128 |
metrics:
|
129 |
+
- type: acc
|
|
|
130 |
value: 0.610738255033557
|
131 |
+
name: acc
|
132 |
verified: false
|
133 |
- task:
|
134 |
type: text-generation
|
|
|
137 |
name: copa
|
138 |
type: copa
|
139 |
metrics:
|
140 |
+
- type: acc
|
|
|
141 |
value: 0.63
|
142 |
+
name: acc
|
143 |
verified: false
|
144 |
- task:
|
145 |
type: text-generation
|
|
|
148 |
name: crows_pairs_english
|
149 |
type: crows_pairs_english
|
150 |
metrics:
|
151 |
+
- type: acc
|
|
|
152 |
value: 0.4973166368515206
|
153 |
+
name: acc
|
154 |
verified: false
|
155 |
- task:
|
156 |
type: text-generation
|
|
|
159 |
name: crows_pairs_french
|
160 |
type: crows_pairs_french
|
161 |
metrics:
|
162 |
+
- type: acc
|
|
|
163 |
value: 0.5032796660703638
|
164 |
+
name: acc
|
165 |
verified: false
|
166 |
- task:
|
167 |
type: text-generation
|
|
|
170 |
name: diabla
|
171 |
type: diabla
|
172 |
metrics:
|
173 |
+
- type: acc
|
|
|
174 |
value: 0.28888308977035493
|
175 |
+
name: acc
|
176 |
verified: false
|
177 |
- task:
|
178 |
type: text-generation
|
|
|
181 |
name: gsarti/flores_101_afr
|
182 |
type: gsarti/flores_101_afr
|
183 |
metrics:
|
184 |
+
- type: byte_perplexity
|
|
|
185 |
value: 6.500798737976343
|
186 |
+
name: byte_perplexity
|
187 |
verified: false
|
188 |
- task:
|
189 |
type: text-generation
|
|
|
192 |
name: gsarti/flores_101_amh
|
193 |
type: gsarti/flores_101_amh
|
194 |
metrics:
|
195 |
+
- type: byte_perplexity
|
|
|
196 |
value: 3.9726863338897145
|
197 |
+
name: byte_perplexity
|
198 |
verified: false
|
199 |
- task:
|
200 |
type: text-generation
|
|
|
203 |
name: gsarti/flores_101_ara
|
204 |
type: gsarti/flores_101_ara
|
205 |
metrics:
|
206 |
+
- type: byte_perplexity
|
|
|
207 |
value: 1.8083841089875814
|
208 |
+
name: byte_perplexity
|
209 |
verified: false
|
210 |
- task:
|
211 |
type: text-generation
|
|
|
214 |
name: gsarti/flores_101_asm
|
215 |
type: gsarti/flores_101_asm
|
216 |
metrics:
|
217 |
+
- type: byte_perplexity
|
|
|
218 |
value: 5.699102962086425
|
219 |
+
name: byte_perplexity
|
220 |
verified: false
|
221 |
- task:
|
222 |
type: text-generation
|
|
|
225 |
name: gsarti/flores_101_ast
|
226 |
type: gsarti/flores_101_ast
|
227 |
metrics:
|
228 |
+
- type: byte_perplexity
|
|
|
229 |
value: 3.9252047073429384
|
230 |
+
name: byte_perplexity
|
231 |
verified: false
|
232 |
- task:
|
233 |
type: text-generation
|
|
|
236 |
name: gsarti/flores_101_azj
|
237 |
type: gsarti/flores_101_azj
|
238 |
metrics:
|
239 |
+
- type: byte_perplexity
|
|
|
240 |
value: 6.942805054270002
|
241 |
+
name: byte_perplexity
|
242 |
verified: false
|
243 |
- task:
|
244 |
type: text-generation
|
|
|
247 |
name: gsarti/flores_101_bel
|
248 |
type: gsarti/flores_101_bel
|
249 |
metrics:
|
250 |
+
- type: byte_perplexity
|
|
|
251 |
value: 3.614136245847082
|
252 |
+
name: byte_perplexity
|
253 |
verified: false
|
254 |
- task:
|
255 |
type: text-generation
|
|
|
258 |
name: gsarti/flores_101_ben
|
259 |
type: gsarti/flores_101_ben
|
260 |
metrics:
|
261 |
+
- type: byte_perplexity
|
|
|
262 |
value: 5.121491534300969
|
263 |
+
name: byte_perplexity
|
264 |
verified: false
|
265 |
- task:
|
266 |
type: text-generation
|
|
|
269 |
name: gsarti/flores_101_bos
|
270 |
type: gsarti/flores_101_bos
|
271 |
metrics:
|
272 |
+
- type: byte_perplexity
|
|
|
273 |
value: 5.653353469118798
|
274 |
+
name: byte_perplexity
|
275 |
verified: false
|
276 |
- task:
|
277 |
type: text-generation
|
|
|
280 |
name: gsarti/flores_101_bul
|
281 |
type: gsarti/flores_101_bul
|
282 |
metrics:
|
283 |
+
- type: byte_perplexity
|
|
|
284 |
value: 2.7014693938055068
|
285 |
+
name: byte_perplexity
|
286 |
verified: false
|
287 |
- task:
|
288 |
type: text-generation
|
|
|
291 |
name: gsarti/flores_101_cat
|
292 |
type: gsarti/flores_101_cat
|
293 |
metrics:
|
294 |
+
- type: byte_perplexity
|
|
|
295 |
value: 2.305190041967345
|
296 |
+
name: byte_perplexity
|
297 |
verified: false
|
298 |
- task:
|
299 |
type: text-generation
|
|
|
302 |
name: gsarti/flores_101_ceb
|
303 |
type: gsarti/flores_101_ceb
|
304 |
metrics:
|
305 |
+
- type: byte_perplexity
|
|
|
306 |
value: 6.291000321323428
|
307 |
+
name: byte_perplexity
|
308 |
verified: false
|
309 |
- task:
|
310 |
type: text-generation
|
|
|
313 |
name: gsarti/flores_101_ces
|
314 |
type: gsarti/flores_101_ces
|
315 |
metrics:
|
316 |
+
- type: byte_perplexity
|
|
|
317 |
value: 5.447322753586386
|
318 |
+
name: byte_perplexity
|
319 |
verified: false
|
320 |
- task:
|
321 |
type: text-generation
|
|
|
324 |
name: gsarti/flores_101_ckb
|
325 |
type: gsarti/flores_101_ckb
|
326 |
metrics:
|
327 |
+
- type: byte_perplexity
|
|
|
328 |
value: 3.7255124939234765
|
329 |
+
name: byte_perplexity
|
330 |
verified: false
|
331 |
- task:
|
332 |
type: text-generation
|
|
|
335 |
name: gsarti/flores_101_cym
|
336 |
type: gsarti/flores_101_cym
|
337 |
metrics:
|
338 |
+
- type: byte_perplexity
|
|
|
339 |
value: 12.539424151448149
|
340 |
+
name: byte_perplexity
|
341 |
verified: false
|
342 |
- task:
|
343 |
type: text-generation
|
|
|
346 |
name: gsarti/flores_101_dan
|
347 |
type: gsarti/flores_101_dan
|
348 |
metrics:
|
349 |
+
- type: byte_perplexity
|
|
|
350 |
value: 5.183309001005672
|
351 |
+
name: byte_perplexity
|
352 |
verified: false
|
353 |
- task:
|
354 |
type: text-generation
|
|
|
357 |
name: gsarti/flores_101_deu
|
358 |
type: gsarti/flores_101_deu
|
359 |
metrics:
|
360 |
+
- type: byte_perplexity
|
|
|
361 |
value: 3.1180422286591347
|
362 |
+
name: byte_perplexity
|
363 |
verified: false
|
364 |
- task:
|
365 |
type: text-generation
|
|
|
368 |
name: gsarti/flores_101_ell
|
369 |
type: gsarti/flores_101_ell
|
370 |
metrics:
|
371 |
+
- type: byte_perplexity
|
|
|
372 |
value: 2.467943456164706
|
373 |
+
name: byte_perplexity
|
374 |
verified: false
|
375 |
- task:
|
376 |
type: text-generation
|
|
|
379 |
name: gsarti/flores_101_eng
|
380 |
type: gsarti/flores_101_eng
|
381 |
metrics:
|
382 |
+
- type: byte_perplexity
|
|
|
383 |
value: 2.018740628193298
|
384 |
+
name: byte_perplexity
|
385 |
verified: false
|
386 |
- task:
|
387 |
type: text-generation
|
|
|
390 |
name: gsarti/flores_101_est
|
391 |
type: gsarti/flores_101_est
|
392 |
metrics:
|
393 |
+
- type: byte_perplexity
|
|
|
394 |
value: 9.11654425176368
|
395 |
+
name: byte_perplexity
|
396 |
verified: false
|
397 |
- task:
|
398 |
type: text-generation
|
|
|
401 |
name: gsarti/flores_101_fas
|
402 |
type: gsarti/flores_101_fas
|
403 |
metrics:
|
404 |
+
- type: byte_perplexity
|
|
|
405 |
value: 3.058009097116482
|
406 |
+
name: byte_perplexity
|
407 |
verified: false
|
408 |
- task:
|
409 |
type: text-generation
|
|
|
412 |
name: gsarti/flores_101_fin
|
413 |
type: gsarti/flores_101_fin
|
414 |
metrics:
|
415 |
+
- type: byte_perplexity
|
|
|
416 |
value: 6.847047959628553
|
417 |
+
name: byte_perplexity
|
418 |
verified: false
|
419 |
- task:
|
420 |
type: text-generation
|
|
|
423 |
name: gsarti/flores_101_fra
|
424 |
type: gsarti/flores_101_fra
|
425 |
metrics:
|
426 |
+
- type: byte_perplexity
|
|
|
427 |
value: 1.9975177011840075
|
428 |
+
name: byte_perplexity
|
429 |
verified: false
|
430 |
- task:
|
431 |
type: text-generation
|
|
|
434 |
name: gsarti/flores_101_ful
|
435 |
type: gsarti/flores_101_ful
|
436 |
metrics:
|
437 |
+
- type: byte_perplexity
|
|
|
438 |
value: 11.465912731488828
|
439 |
+
name: byte_perplexity
|
440 |
verified: false
|
441 |
- task:
|
442 |
type: text-generation
|
|
|
445 |
name: gsarti/flores_101_gle
|
446 |
type: gsarti/flores_101_gle
|
447 |
metrics:
|
448 |
+
- type: byte_perplexity
|
|
|
449 |
value: 8.681491663539422
|
450 |
+
name: byte_perplexity
|
451 |
verified: false
|
452 |
- task:
|
453 |
type: text-generation
|
|
|
456 |
name: gsarti/flores_101_glg
|
457 |
type: gsarti/flores_101_glg
|
458 |
metrics:
|
459 |
+
- type: byte_perplexity
|
|
|
460 |
value: 3.029991089015508
|
461 |
+
name: byte_perplexity
|
462 |
verified: false
|
463 |
- task:
|
464 |
type: text-generation
|
|
|
467 |
name: gsarti/flores_101_guj
|
468 |
type: gsarti/flores_101_guj
|
469 |
metrics:
|
470 |
+
- type: byte_perplexity
|
|
|
471 |
value: 4.955224230286231
|
472 |
+
name: byte_perplexity
|
473 |
verified: false
|
474 |
- task:
|
475 |
type: text-generation
|
|
|
478 |
name: gsarti/flores_101_hau
|
479 |
type: gsarti/flores_101_hau
|
480 |
metrics:
|
481 |
+
- type: byte_perplexity
|
|
|
482 |
value: 10.758347356372159
|
483 |
+
name: byte_perplexity
|
484 |
verified: false
|
485 |
- task:
|
486 |
type: text-generation
|
|
|
489 |
name: gsarti/flores_101_heb
|
490 |
type: gsarti/flores_101_heb
|
491 |
metrics:
|
492 |
+
- type: byte_perplexity
|
|
|
493 |
value: 3.6004478129801667
|
494 |
+
name: byte_perplexity
|
495 |
verified: false
|
496 |
- task:
|
497 |
type: text-generation
|
|
|
500 |
name: gsarti/flores_101_hin
|
501 |
type: gsarti/flores_101_hin
|
502 |
metrics:
|
503 |
+
- type: byte_perplexity
|
|
|
504 |
value: 4.712530650588064
|
505 |
+
name: byte_perplexity
|
506 |
verified: false
|
507 |
- task:
|
508 |
type: text-generation
|
|
|
511 |
name: gsarti/flores_101_hrv
|
512 |
type: gsarti/flores_101_hrv
|
513 |
metrics:
|
514 |
+
- type: byte_perplexity
|
|
|
515 |
value: 5.822418943372185
|
516 |
+
name: byte_perplexity
|
517 |
verified: false
|
518 |
- task:
|
519 |
type: text-generation
|
|
|
522 |
name: gsarti/flores_101_hun
|
523 |
type: gsarti/flores_101_hun
|
524 |
metrics:
|
525 |
+
- type: byte_perplexity
|
|
|
526 |
value: 6.440482646965992
|
527 |
+
name: byte_perplexity
|
528 |
verified: false
|
529 |
- task:
|
530 |
type: text-generation
|
|
|
533 |
name: gsarti/flores_101_hye
|
534 |
type: gsarti/flores_101_hye
|
535 |
metrics:
|
536 |
+
- type: byte_perplexity
|
|
|
537 |
value: 3.657718918347166
|
538 |
+
name: byte_perplexity
|
539 |
verified: false
|
540 |
- task:
|
541 |
type: text-generation
|
|
|
544 |
name: gsarti/flores_101_ibo
|
545 |
type: gsarti/flores_101_ibo
|
546 |
metrics:
|
547 |
+
- type: byte_perplexity
|
|
|
548 |
value: 5.564814003872672
|
549 |
+
name: byte_perplexity
|
550 |
verified: false
|
551 |
- task:
|
552 |
type: text-generation
|
|
|
555 |
name: gsarti/flores_101_ind
|
556 |
type: gsarti/flores_101_ind
|
557 |
metrics:
|
558 |
+
- type: byte_perplexity
|
|
|
559 |
value: 2.1597101468869373
|
560 |
+
name: byte_perplexity
|
561 |
verified: false
|
562 |
- task:
|
563 |
type: text-generation
|
|
|
566 |
name: gsarti/flores_101_isl
|
567 |
type: gsarti/flores_101_isl
|
568 |
metrics:
|
569 |
+
- type: byte_perplexity
|
|
|
570 |
value: 8.082349269518136
|
571 |
+
name: byte_perplexity
|
572 |
verified: false
|
573 |
- task:
|
574 |
type: text-generation
|
|
|
577 |
name: gsarti/flores_101_ita
|
578 |
type: gsarti/flores_101_ita
|
579 |
metrics:
|
580 |
+
- type: byte_perplexity
|
|
|
581 |
value: 2.9687591414176207
|
582 |
+
name: byte_perplexity
|
583 |
verified: false
|
584 |
- task:
|
585 |
type: text-generation
|
|
|
588 |
name: gsarti/flores_101_jav
|
589 |
type: gsarti/flores_101_jav
|
590 |
metrics:
|
591 |
+
- type: byte_perplexity
|
|
|
592 |
value: 7.0573805415708994
|
593 |
+
name: byte_perplexity
|
594 |
verified: false
|
595 |
- task:
|
596 |
type: text-generation
|
|
|
599 |
name: gsarti/flores_101_jpn
|
600 |
type: gsarti/flores_101_jpn
|
601 |
metrics:
|
602 |
+
- type: byte_perplexity
|
|
|
603 |
value: 2.7758864197116933
|
604 |
+
name: byte_perplexity
|
605 |
verified: false
|
606 |
- task:
|
607 |
type: text-generation
|
|
|
610 |
name: gsarti/flores_101_kam
|
611 |
type: gsarti/flores_101_kam
|
612 |
metrics:
|
613 |
+
- type: byte_perplexity
|
|
|
614 |
value: 11.072949642861332
|
615 |
+
name: byte_perplexity
|
616 |
verified: false
|
617 |
- task:
|
618 |
type: text-generation
|
|
|
621 |
name: gsarti/flores_101_kan
|
622 |
type: gsarti/flores_101_kan
|
623 |
metrics:
|
624 |
+
- type: byte_perplexity
|
|
|
625 |
value: 5.551730651007082
|
626 |
+
name: byte_perplexity
|
627 |
verified: false
|
628 |
- task:
|
629 |
type: text-generation
|
|
|
632 |
name: gsarti/flores_101_kat
|
633 |
type: gsarti/flores_101_kat
|
634 |
metrics:
|
635 |
+
- type: byte_perplexity
|
|
|
636 |
value: 2.522630524283745
|
637 |
+
name: byte_perplexity
|
638 |
verified: false
|
639 |
- task:
|
640 |
type: text-generation
|
|
|
643 |
name: gsarti/flores_101_kaz
|
644 |
type: gsarti/flores_101_kaz
|
645 |
metrics:
|
646 |
+
- type: byte_perplexity
|
|
|
647 |
value: 3.3901748516975574
|
648 |
+
name: byte_perplexity
|
649 |
verified: false
|
650 |
- task:
|
651 |
type: text-generation
|
|
|
654 |
name: gsarti/flores_101_kea
|
655 |
type: gsarti/flores_101_kea
|
656 |
metrics:
|
657 |
+
- type: byte_perplexity
|
|
|
658 |
value: 8.918534182590863
|
659 |
+
name: byte_perplexity
|
660 |
verified: false
|
661 |
- task:
|
662 |
type: text-generation
|
|
|
665 |
name: gsarti/flores_101_kir
|
666 |
type: gsarti/flores_101_kir
|
667 |
metrics:
|
668 |
+
- type: byte_perplexity
|
|
|
669 |
value: 3.729278369847201
|
670 |
+
name: byte_perplexity
|
671 |
verified: false
|
672 |
- task:
|
673 |
type: text-generation
|
|
|
676 |
name: gsarti/flores_101_kor
|
677 |
type: gsarti/flores_101_kor
|
678 |
metrics:
|
679 |
+
- type: byte_perplexity
|
|
|
680 |
value: 3.932884847226212
|
681 |
+
name: byte_perplexity
|
682 |
verified: false
|
683 |
- task:
|
684 |
type: text-generation
|
|
|
687 |
name: gsarti/flores_101_lao
|
688 |
type: gsarti/flores_101_lao
|
689 |
metrics:
|
690 |
+
- type: byte_perplexity
|
|
|
691 |
value: 2.9077314760849924
|
692 |
+
name: byte_perplexity
|
693 |
verified: false
|
694 |
- task:
|
695 |
type: text-generation
|
|
|
698 |
name: gsarti/flores_101_lav
|
699 |
type: gsarti/flores_101_lav
|
700 |
metrics:
|
701 |
+
- type: byte_perplexity
|
|
|
702 |
value: 7.777221919194806
|
703 |
+
name: byte_perplexity
|
704 |
verified: false
|
705 |
- task:
|
706 |
type: text-generation
|
|
|
709 |
name: gsarti/flores_101_lin
|
710 |
type: gsarti/flores_101_lin
|
711 |
metrics:
|
712 |
+
- type: byte_perplexity
|
|
|
713 |
value: 7.524842908050988
|
714 |
+
name: byte_perplexity
|
715 |
verified: false
|
716 |
- task:
|
717 |
type: text-generation
|
|
|
720 |
name: gsarti/flores_101_lit
|
721 |
type: gsarti/flores_101_lit
|
722 |
metrics:
|
723 |
+
- type: byte_perplexity
|
|
|
724 |
value: 7.369179434621725
|
725 |
+
name: byte_perplexity
|
726 |
verified: false
|
727 |
- task:
|
728 |
type: text-generation
|
|
|
731 |
name: gsarti/flores_101_ltz
|
732 |
type: gsarti/flores_101_ltz
|
733 |
metrics:
|
734 |
+
- type: byte_perplexity
|
|
|
735 |
value: 8.801059747949214
|
736 |
+
name: byte_perplexity
|
737 |
verified: false
|
738 |
- task:
|
739 |
type: text-generation
|
|
|
742 |
name: gsarti/flores_101_lug
|
743 |
type: gsarti/flores_101_lug
|
744 |
metrics:
|
745 |
+
- type: byte_perplexity
|
|
|
746 |
value: 8.483203026364786
|
747 |
+
name: byte_perplexity
|
748 |
verified: false
|
749 |
- task:
|
750 |
type: text-generation
|
|
|
753 |
name: gsarti/flores_101_luo
|
754 |
type: gsarti/flores_101_luo
|
755 |
metrics:
|
756 |
+
- type: byte_perplexity
|
|
|
757 |
value: 11.975963093623681
|
758 |
+
name: byte_perplexity
|
759 |
verified: false
|
760 |
- task:
|
761 |
type: text-generation
|
|
|
764 |
name: gsarti/flores_101_mal
|
765 |
type: gsarti/flores_101_mal
|
766 |
metrics:
|
767 |
+
- type: byte_perplexity
|
|
|
768 |
value: 4.615948455160037
|
769 |
+
name: byte_perplexity
|
770 |
verified: false
|
771 |
- task:
|
772 |
type: text-generation
|
|
|
775 |
name: gsarti/flores_101_mar
|
776 |
type: gsarti/flores_101_mar
|
777 |
metrics:
|
778 |
+
- type: byte_perplexity
|
|
|
779 |
value: 5.483253482821379
|
780 |
+
name: byte_perplexity
|
781 |
verified: false
|
782 |
- task:
|
783 |
type: text-generation
|
|
|
786 |
name: gsarti/flores_101_mkd
|
787 |
type: gsarti/flores_101_mkd
|
788 |
metrics:
|
789 |
+
- type: byte_perplexity
|
|
|
790 |
value: 2.9656732291754087
|
791 |
+
name: byte_perplexity
|
792 |
verified: false
|
793 |
- task:
|
794 |
type: text-generation
|
|
|
797 |
name: gsarti/flores_101_mlt
|
798 |
type: gsarti/flores_101_mlt
|
799 |
metrics:
|
800 |
+
- type: byte_perplexity
|
|
|
801 |
value: 15.004773437665275
|
802 |
+
name: byte_perplexity
|
803 |
verified: false
|
804 |
- task:
|
805 |
type: text-generation
|
|
|
808 |
name: gsarti/flores_101_mon
|
809 |
type: gsarti/flores_101_mon
|
810 |
metrics:
|
811 |
+
- type: byte_perplexity
|
|
|
812 |
value: 3.410598542315402
|
813 |
+
name: byte_perplexity
|
814 |
verified: false
|
815 |
- task:
|
816 |
type: text-generation
|
|
|
819 |
name: gsarti/flores_101_mri
|
820 |
type: gsarti/flores_101_mri
|
821 |
metrics:
|
822 |
+
- type: byte_perplexity
|
|
|
823 |
value: 7.474035895661322
|
824 |
+
name: byte_perplexity
|
825 |
verified: false
|
826 |
- task:
|
827 |
type: text-generation
|
|
|
830 |
name: gsarti/flores_101_msa
|
831 |
type: gsarti/flores_101_msa
|
832 |
metrics:
|
833 |
+
- type: byte_perplexity
|
|
|
834 |
value: 2.5710001772665634
|
835 |
+
name: byte_perplexity
|
836 |
verified: false
|
837 |
- task:
|
838 |
type: text-generation
|
|
|
841 |
name: gsarti/flores_101_mya
|
842 |
type: gsarti/flores_101_mya
|
843 |
metrics:
|
844 |
+
- type: byte_perplexity
|
|
|
845 |
value: 2.413577969878331
|
846 |
+
name: byte_perplexity
|
847 |
verified: false
|
848 |
- task:
|
849 |
type: text-generation
|
|
|
852 |
name: gsarti/flores_101_nld
|
853 |
type: gsarti/flores_101_nld
|
854 |
metrics:
|
855 |
+
- type: byte_perplexity
|
|
|
856 |
value: 4.127831721885065
|
857 |
+
name: byte_perplexity
|
858 |
verified: false
|
859 |
- task:
|
860 |
type: text-generation
|
|
|
863 |
name: gsarti/flores_101_nob
|
864 |
type: gsarti/flores_101_nob
|
865 |
metrics:
|
866 |
+
- type: byte_perplexity
|
|
|
867 |
value: 5.402763169129877
|
868 |
+
name: byte_perplexity
|
869 |
verified: false
|
870 |
- task:
|
871 |
type: text-generation
|
|
|
874 |
name: gsarti/flores_101_npi
|
875 |
type: gsarti/flores_101_npi
|
876 |
metrics:
|
877 |
+
- type: byte_perplexity
|
|
|
878 |
value: 5.199342701937889
|
879 |
+
name: byte_perplexity
|
880 |
verified: false
|
881 |
- task:
|
882 |
type: text-generation
|
|
|
885 |
name: gsarti/flores_101_nso
|
886 |
type: gsarti/flores_101_nso
|
887 |
metrics:
|
888 |
+
- type: byte_perplexity
|
|
|
889 |
value: 8.154626800955667
|
890 |
+
name: byte_perplexity
|
891 |
verified: false
|
892 |
- task:
|
893 |
type: text-generation
|
|
|
896 |
name: gsarti/flores_101_nya
|
897 |
type: gsarti/flores_101_nya
|
898 |
metrics:
|
899 |
+
- type: byte_perplexity
|
|
|
900 |
value: 8.179860208369393
|
901 |
+
name: byte_perplexity
|
902 |
verified: false
|
903 |
- task:
|
904 |
type: text-generation
|
|
|
907 |
name: gsarti/flores_101_oci
|
908 |
type: gsarti/flores_101_oci
|
909 |
metrics:
|
910 |
+
- type: byte_perplexity
|
|
|
911 |
value: 4.8617357393685845
|
912 |
+
name: byte_perplexity
|
913 |
verified: false
|
914 |
- task:
|
915 |
type: text-generation
|
|
|
918 |
name: gsarti/flores_101_orm
|
919 |
type: gsarti/flores_101_orm
|
920 |
metrics:
|
921 |
+
- type: byte_perplexity
|
|
|
922 |
value: 12.911595421079408
|
923 |
+
name: byte_perplexity
|
924 |
verified: false
|
925 |
- task:
|
926 |
type: text-generation
|
|
|
929 |
name: gsarti/flores_101_ory
|
930 |
type: gsarti/flores_101_ory
|
931 |
metrics:
|
932 |
+
- type: byte_perplexity
|
|
|
933 |
value: 5.189421861225964
|
934 |
+
name: byte_perplexity
|
935 |
verified: false
|
936 |
- task:
|
937 |
type: text-generation
|
|
|
940 |
name: gsarti/flores_101_pan
|
941 |
type: gsarti/flores_101_pan
|
942 |
metrics:
|
943 |
+
- type: byte_perplexity
|
|
|
944 |
value: 4.698477289331806
|
945 |
+
name: byte_perplexity
|
946 |
verified: false
|
947 |
- task:
|
948 |
type: text-generation
|
|
|
951 |
name: gsarti/flores_101_pol
|
952 |
type: gsarti/flores_101_pol
|
953 |
metrics:
|
954 |
+
- type: byte_perplexity
|
|
|
955 |
value: 4.625550458479643
|
956 |
+
name: byte_perplexity
|
957 |
verified: false
|
958 |
- task:
|
959 |
type: text-generation
|
|
|
962 |
name: gsarti/flores_101_por
|
963 |
type: gsarti/flores_101_por
|
964 |
metrics:
|
965 |
+
- type: byte_perplexity
|
|
|
966 |
value: 1.9754515986213523
|
967 |
+
name: byte_perplexity
|
968 |
verified: false
|
969 |
- task:
|
970 |
type: text-generation
|
|
|
973 |
name: gsarti/flores_101_pus
|
974 |
type: gsarti/flores_101_pus
|
975 |
metrics:
|
976 |
+
- type: byte_perplexity
|
|
|
977 |
value: 4.4963371422771585
|
978 |
+
name: byte_perplexity
|
979 |
verified: false
|
980 |
- task:
|
981 |
type: text-generation
|
|
|
984 |
name: gsarti/flores_101_ron
|
985 |
type: gsarti/flores_101_ron
|
986 |
metrics:
|
987 |
+
- type: byte_perplexity
|
|
|
988 |
value: 4.965456830031304
|
989 |
+
name: byte_perplexity
|
990 |
verified: false
|
991 |
- task:
|
992 |
type: text-generation
|
|
|
995 |
name: gsarti/flores_101_rus
|
996 |
type: gsarti/flores_101_rus
|
997 |
metrics:
|
998 |
+
- type: byte_perplexity
|
|
|
999 |
value: 2.0498020542445303
|
1000 |
+
name: byte_perplexity
|
1001 |
verified: false
|
1002 |
- task:
|
1003 |
type: text-generation
|
|
|
1006 |
name: gsarti/flores_101_slk
|
1007 |
type: gsarti/flores_101_slk
|
1008 |
metrics:
|
1009 |
+
- type: byte_perplexity
|
|
|
1010 |
value: 6.450822127057479
|
1011 |
+
name: byte_perplexity
|
1012 |
verified: false
|
1013 |
- task:
|
1014 |
type: text-generation
|
|
|
1017 |
name: gsarti/flores_101_slv
|
1018 |
type: gsarti/flores_101_slv
|
1019 |
metrics:
|
1020 |
+
- type: byte_perplexity
|
|
|
1021 |
value: 6.620252120186232
|
1022 |
+
name: byte_perplexity
|
1023 |
verified: false
|
1024 |
- task:
|
1025 |
type: text-generation
|
|
|
1028 |
name: gsarti/flores_101_sna
|
1029 |
type: gsarti/flores_101_sna
|
1030 |
metrics:
|
1031 |
+
- type: byte_perplexity
|
|
|
1032 |
value: 8.462166771382726
|
1033 |
+
name: byte_perplexity
|
1034 |
verified: false
|
1035 |
- task:
|
1036 |
type: text-generation
|
|
|
1039 |
name: gsarti/flores_101_snd
|
1040 |
type: gsarti/flores_101_snd
|
1041 |
metrics:
|
1042 |
+
- type: byte_perplexity
|
|
|
1043 |
value: 5.466066951221973
|
1044 |
+
name: byte_perplexity
|
1045 |
verified: false
|
1046 |
- task:
|
1047 |
type: text-generation
|
|
|
1050 |
name: gsarti/flores_101_som
|
1051 |
type: gsarti/flores_101_som
|
1052 |
metrics:
|
1053 |
+
- type: byte_perplexity
|
|
|
1054 |
value: 11.95918054093392
|
1055 |
+
name: byte_perplexity
|
1056 |
verified: false
|
1057 |
- task:
|
1058 |
type: text-generation
|
|
|
1061 |
name: gsarti/flores_101_spa
|
1062 |
type: gsarti/flores_101_spa
|
1063 |
metrics:
|
1064 |
+
- type: byte_perplexity
|
|
|
1065 |
value: 1.8965140104323535
|
1066 |
+
name: byte_perplexity
|
1067 |
verified: false
|
1068 |
- task:
|
1069 |
type: text-generation
|
|
|
1072 |
name: gsarti/flores_101_srp
|
1073 |
type: gsarti/flores_101_srp
|
1074 |
metrics:
|
1075 |
+
- type: byte_perplexity
|
|
|
1076 |
value: 2.871214785885079
|
1077 |
+
name: byte_perplexity
|
1078 |
verified: false
|
1079 |
- task:
|
1080 |
type: text-generation
|
|
|
1083 |
name: gsarti/flores_101_swe
|
1084 |
type: gsarti/flores_101_swe
|
1085 |
metrics:
|
1086 |
+
- type: byte_perplexity
|
|
|
1087 |
value: 5.054972008155866
|
1088 |
+
name: byte_perplexity
|
1089 |
verified: false
|
1090 |
- task:
|
1091 |
type: text-generation
|
|
|
1094 |
name: gsarti/flores_101_swh
|
1095 |
type: gsarti/flores_101_swh
|
1096 |
metrics:
|
1097 |
+
- type: byte_perplexity
|
|
|
1098 |
value: 3.6973091886730676
|
1099 |
+
name: byte_perplexity
|
1100 |
verified: false
|
1101 |
- task:
|
1102 |
type: text-generation
|
|
|
1105 |
name: gsarti/flores_101_tam
|
1106 |
type: gsarti/flores_101_tam
|
1107 |
metrics:
|
1108 |
+
- type: byte_perplexity
|
|
|
1109 |
value: 4.539493400469833
|
1110 |
+
name: byte_perplexity
|
1111 |
verified: false
|
1112 |
- task:
|
1113 |
type: text-generation
|
|
|
1116 |
name: gsarti/flores_101_tel
|
1117 |
type: gsarti/flores_101_tel
|
1118 |
metrics:
|
1119 |
+
- type: byte_perplexity
|
|
|
1120 |
value: 5.807499987508966
|
1121 |
+
name: byte_perplexity
|
1122 |
verified: false
|
1123 |
- task:
|
1124 |
type: text-generation
|
|
|
1127 |
name: gsarti/flores_101_tgk
|
1128 |
type: gsarti/flores_101_tgk
|
1129 |
metrics:
|
1130 |
+
- type: byte_perplexity
|
|
|
1131 |
value: 3.5994818827380426
|
1132 |
+
name: byte_perplexity
|
1133 |
verified: false
|
1134 |
- task:
|
1135 |
type: text-generation
|
|
|
1138 |
name: gsarti/flores_101_tgl
|
1139 |
type: gsarti/flores_101_tgl
|
1140 |
metrics:
|
1141 |
+
- type: byte_perplexity
|
|
|
1142 |
value: 5.667053833119858
|
1143 |
+
name: byte_perplexity
|
1144 |
verified: false
|
1145 |
- task:
|
1146 |
type: text-generation
|
|
|
1149 |
name: gsarti/flores_101_tha
|
1150 |
type: gsarti/flores_101_tha
|
1151 |
metrics:
|
1152 |
+
- type: byte_perplexity
|
|
|
1153 |
value: 2.365940201944242
|
1154 |
+
name: byte_perplexity
|
1155 |
verified: false
|
1156 |
- task:
|
1157 |
type: text-generation
|
|
|
1160 |
name: gsarti/flores_101_tur
|
1161 |
type: gsarti/flores_101_tur
|
1162 |
metrics:
|
1163 |
+
- type: byte_perplexity
|
|
|
1164 |
value: 4.885014749844601
|
1165 |
+
name: byte_perplexity
|
1166 |
verified: false
|
1167 |
- task:
|
1168 |
type: text-generation
|
|
|
1171 |
name: gsarti/flores_101_ukr
|
1172 |
type: gsarti/flores_101_ukr
|
1173 |
metrics:
|
1174 |
+
- type: byte_perplexity
|
|
|
1175 |
value: 2.7240934990288483
|
1176 |
+
name: byte_perplexity
|
1177 |
verified: false
|
1178 |
- task:
|
1179 |
type: text-generation
|
|
|
1182 |
name: gsarti/flores_101_umb
|
1183 |
type: gsarti/flores_101_umb
|
1184 |
metrics:
|
1185 |
+
- type: byte_perplexity
|
|
|
1186 |
value: 12.766915508610673
|
1187 |
+
name: byte_perplexity
|
1188 |
verified: false
|
1189 |
- task:
|
1190 |
type: text-generation
|
|
|
1193 |
name: gsarti/flores_101_urd
|
1194 |
type: gsarti/flores_101_urd
|
1195 |
metrics:
|
1196 |
+
- type: byte_perplexity
|
|
|
1197 |
value: 1.9797467071381232
|
1198 |
+
name: byte_perplexity
|
1199 |
verified: false
|
1200 |
- task:
|
1201 |
type: text-generation
|
|
|
1204 |
name: gsarti/flores_101_uzb
|
1205 |
type: gsarti/flores_101_uzb
|
1206 |
metrics:
|
1207 |
+
- type: byte_perplexity
|
|
|
1208 |
value: 12.002337637722146
|
1209 |
+
name: byte_perplexity
|
1210 |
verified: false
|
1211 |
- task:
|
1212 |
type: text-generation
|
|
|
1215 |
name: gsarti/flores_101_vie
|
1216 |
type: gsarti/flores_101_vie
|
1217 |
metrics:
|
1218 |
+
- type: byte_perplexity
|
|
|
1219 |
value: 1.76578415476397
|
1220 |
+
name: byte_perplexity
|
1221 |
verified: false
|
1222 |
- task:
|
1223 |
type: text-generation
|
|
|
1226 |
name: gsarti/flores_101_wol
|
1227 |
type: gsarti/flores_101_wol
|
1228 |
metrics:
|
1229 |
+
- type: byte_perplexity
|
|
|
1230 |
value: 9.144285650306488
|
1231 |
+
name: byte_perplexity
|
1232 |
verified: false
|
1233 |
- task:
|
1234 |
type: text-generation
|
|
|
1237 |
name: gsarti/flores_101_xho
|
1238 |
type: gsarti/flores_101_xho
|
1239 |
metrics:
|
1240 |
+
- type: byte_perplexity
|
|
|
1241 |
value: 7.403240538286952
|
1242 |
+
name: byte_perplexity
|
1243 |
verified: false
|
1244 |
- task:
|
1245 |
type: text-generation
|
|
|
1248 |
name: gsarti/flores_101_yor
|
1249 |
type: gsarti/flores_101_yor
|
1250 |
metrics:
|
1251 |
+
- type: byte_perplexity
|
|
|
1252 |
value: 5.91272037551173
|
1253 |
+
name: byte_perplexity
|
1254 |
verified: false
|
1255 |
- task:
|
1256 |
type: text-generation
|
|
|
1259 |
name: gsarti/flores_101_zho_simpl
|
1260 |
type: gsarti/flores_101_zho_simpl
|
1261 |
metrics:
|
1262 |
+
- type: byte_perplexity
|
|
|
1263 |
value: 2.2769070822768533
|
1264 |
+
name: byte_perplexity
|
1265 |
verified: false
|
1266 |
- task:
|
1267 |
type: text-generation
|
|
|
1270 |
name: gsarti/flores_101_zho_trad
|
1271 |
type: gsarti/flores_101_zho_trad
|
1272 |
metrics:
|
1273 |
+
- type: byte_perplexity
|
|
|
1274 |
value: 2.5180582198242383
|
1275 |
+
name: byte_perplexity
|
1276 |
verified: false
|
1277 |
- task:
|
1278 |
type: text-generation
|
|
|
1281 |
name: gsarti/flores_101_zul
|
1282 |
type: gsarti/flores_101_zul
|
1283 |
metrics:
|
1284 |
+
- type: byte_perplexity
|
|
|
1285 |
value: 8.53353320693145
|
1286 |
+
name: byte_perplexity
|
1287 |
verified: false
|
1288 |
- task:
|
1289 |
type: text-generation
|
|
|
1292 |
name: headqa
|
1293 |
type: headqa
|
1294 |
metrics:
|
1295 |
+
- type: acc
|
|
|
1296 |
value: 0.26440554339897887
|
1297 |
+
name: acc
|
1298 |
verified: false
|
1299 |
- task:
|
1300 |
type: text-generation
|
|
|
1303 |
name: hellaswag
|
1304 |
type: hellaswag
|
1305 |
metrics:
|
1306 |
+
- type: acc
|
|
|
1307 |
value: 0.41236805417247563
|
1308 |
+
name: acc
|
1309 |
verified: false
|
1310 |
- task:
|
1311 |
type: text-generation
|
|
|
1314 |
name: logiqa
|
1315 |
type: logiqa
|
1316 |
metrics:
|
1317 |
+
- type: acc
|
|
|
1318 |
value: 0.2073732718894009
|
1319 |
+
name: acc
|
1320 |
verified: false
|
1321 |
- task:
|
1322 |
type: text-generation
|
|
|
1325 |
name: mathqa
|
1326 |
type: mathqa
|
1327 |
metrics:
|
1328 |
+
- type: acc
|
|
|
1329 |
value: 0.24958123953098826
|
1330 |
+
name: acc
|
1331 |
verified: false
|
1332 |
- task:
|
1333 |
type: text-generation
|
|
|
1336 |
name: mc_taco
|
1337 |
type: mc_taco
|
1338 |
metrics:
|
1339 |
+
- type: em
|
|
|
1340 |
value: 0.11936936936936937
|
1341 |
+
name: em
|
1342 |
verified: false
|
1343 |
- task:
|
1344 |
type: text-generation
|
|
|
1347 |
name: mnli
|
1348 |
type: mnli
|
1349 |
metrics:
|
1350 |
+
- type: acc
|
|
|
1351 |
value: 0.35496688741721855
|
1352 |
+
name: acc
|
1353 |
verified: false
|
1354 |
- task:
|
1355 |
type: text-generation
|
|
|
1358 |
name: mnli_mismatched
|
1359 |
type: mnli_mismatched
|
1360 |
metrics:
|
1361 |
+
- type: acc
|
|
|
1362 |
value: 0.35211554109031734
|
1363 |
+
name: acc
|
1364 |
verified: false
|
1365 |
- task:
|
1366 |
type: text-generation
|
|
|
1369 |
name: mrpc
|
1370 |
type: mrpc
|
1371 |
metrics:
|
1372 |
+
- type: acc
|
|
|
1373 |
value: 0.5857843137254902
|
1374 |
+
name: acc
|
1375 |
verified: false
|
1376 |
- task:
|
1377 |
type: text-generation
|
|
|
1380 |
name: multirc
|
1381 |
type: multirc
|
1382 |
metrics:
|
1383 |
+
- type: acc
|
|
|
1384 |
value: 0.5375412541254125
|
1385 |
+
name: acc
|
1386 |
verified: false
|
1387 |
- task:
|
1388 |
type: text-generation
|
|
|
1391 |
name: openbookqa
|
1392 |
type: openbookqa
|
1393 |
metrics:
|
1394 |
+
- type: acc
|
|
|
1395 |
value: 0.216
|
1396 |
+
name: acc
|
1397 |
verified: false
|
1398 |
- task:
|
1399 |
type: text-generation
|
|
|
1402 |
name: piqa
|
1403 |
type: piqa
|
1404 |
metrics:
|
1405 |
+
- type: acc
|
|
|
1406 |
value: 0.7078346028291621
|
1407 |
+
name: acc
|
1408 |
verified: false
|
1409 |
- task:
|
1410 |
type: text-generation
|
|
|
1413 |
name: prost
|
1414 |
type: prost
|
1415 |
metrics:
|
1416 |
+
- type: acc
|
|
|
1417 |
value: 0.22683603757472245
|
1418 |
+
name: acc
|
1419 |
verified: false
|
1420 |
- task:
|
1421 |
type: text-generation
|
|
|
1424 |
name: pubmedqa
|
1425 |
type: pubmedqa
|
1426 |
metrics:
|
1427 |
+
- type: acc
|
|
|
1428 |
value: 0.616
|
1429 |
+
name: acc
|
1430 |
verified: false
|
1431 |
- task:
|
1432 |
type: text-generation
|
|
|
1435 |
name: qnli
|
1436 |
type: qnli
|
1437 |
metrics:
|
1438 |
+
- type: acc
|
|
|
1439 |
value: 0.5072304594545122
|
1440 |
+
name: acc
|
1441 |
verified: false
|
1442 |
- task:
|
1443 |
type: text-generation
|
|
|
1446 |
name: qqp
|
1447 |
type: qqp
|
1448 |
metrics:
|
1449 |
+
- type: acc
|
|
|
1450 |
value: 0.3842443729903537
|
1451 |
+
name: acc
|
1452 |
verified: false
|
1453 |
- task:
|
1454 |
type: text-generation
|
|
|
1457 |
name: race
|
1458 |
type: race
|
1459 |
metrics:
|
1460 |
+
- type: acc
|
|
|
1461 |
value: 0.3521531100478469
|
1462 |
+
name: acc
|
1463 |
verified: false
|
1464 |
- task:
|
1465 |
type: text-generation
|
|
|
1468 |
name: rte
|
1469 |
type: rte
|
1470 |
metrics:
|
1471 |
+
- type: acc
|
|
|
1472 |
value: 0.47653429602888087
|
1473 |
+
name: acc
|
1474 |
verified: false
|
1475 |
- task:
|
1476 |
type: text-generation
|
|
|
1479 |
name: sciq
|
1480 |
type: sciq
|
1481 |
metrics:
|
1482 |
+
- type: acc
|
|
|
1483 |
value: 0.892
|
1484 |
+
name: acc
|
1485 |
verified: false
|
1486 |
- task:
|
1487 |
type: text-generation
|
|
|
1490 |
name: sst
|
1491 |
type: sst
|
1492 |
metrics:
|
1493 |
+
- type: acc
|
|
|
1494 |
value: 0.5177752293577982
|
1495 |
+
name: acc
|
1496 |
verified: false
|
1497 |
- task:
|
1498 |
type: text-generation
|
|
|
1501 |
name: triviaqa
|
1502 |
type: triviaqa
|
1503 |
metrics:
|
1504 |
+
- type: acc
|
|
|
1505 |
value: 0.041633518960487934
|
1506 |
+
name: acc
|
1507 |
verified: false
|
1508 |
- task:
|
1509 |
type: text-generation
|
|
|
1512 |
name: tydiqa_primary
|
1513 |
type: tydiqa_primary
|
1514 |
metrics:
|
1515 |
+
- type: acc
|
|
|
1516 |
value: 0.3011337608795236
|
1517 |
+
name: acc
|
1518 |
verified: false
|
1519 |
- task:
|
1520 |
type: text-generation
|
|
|
1523 |
name: webqs
|
1524 |
type: webqs
|
1525 |
metrics:
|
1526 |
+
- type: acc
|
|
|
1527 |
value: 0.01673228346456693
|
1528 |
+
name: acc
|
1529 |
verified: false
|
1530 |
- task:
|
1531 |
type: text-generation
|
|
|
1534 |
name: wic
|
1535 |
type: wic
|
1536 |
metrics:
|
1537 |
+
- type: acc
|
|
|
1538 |
value: 0.5015673981191222
|
1539 |
+
name: acc
|
1540 |
verified: false
|
1541 |
- task:
|
1542 |
type: text-generation
|
|
|
1545 |
name: winogrande
|
1546 |
type: winogrande
|
1547 |
metrics:
|
1548 |
+
- type: acc
|
|
|
1549 |
value: 0.5864246250986582
|
1550 |
+
name: acc
|
1551 |
verified: false
|
1552 |
- task:
|
1553 |
type: text-generation
|
|
|
1556 |
name: wnli
|
1557 |
type: wnli
|
1558 |
metrics:
|
1559 |
+
- type: acc
|
|
|
1560 |
value: 0.471830985915493
|
1561 |
+
name: acc
|
1562 |
verified: false
|
1563 |
- task:
|
1564 |
type: text-generation
|
|
|
1567 |
name: wsc
|
1568 |
type: wsc
|
1569 |
metrics:
|
1570 |
+
- type: acc
|
|
|
1571 |
value: 0.4423076923076923
|
1572 |
+
name: acc
|
1573 |
verified: false
|
1574 |
- task:
|
1575 |
type: text-generation
|
|
|
1578 |
name: humaneval
|
1579 |
type: humaneval
|
1580 |
metrics:
|
1581 |
+
- type: pass@1
|
|
|
1582 |
value: 0.15524390243902436
|
1583 |
+
name: pass@1
|
1584 |
verified: false
|
1585 |
+
- type: pass@10
|
|
|
1586 |
value: 0.3220367632383857
|
1587 |
+
name: pass@10
|
1588 |
verified: false
|
1589 |
+
- type: pass@100
|
|
|
1590 |
value: 0.5545431515723145
|
1591 |
+
name: pass@100
|
1592 |
verified: false
|
1593 |
+
- task:
|
1594 |
+
type: text-generation
|
1595 |
+
name: Text Generation
|
1596 |
+
dataset:
|
1597 |
+
name: IFEval (0-Shot)
|
1598 |
+
type: HuggingFaceH4/ifeval
|
1599 |
+
args:
|
1600 |
+
num_few_shot: 0
|
1601 |
+
metrics:
|
1602 |
+
- type: inst_level_strict_acc and prompt_level_strict_acc
|
1603 |
+
value: 12.71
|
1604 |
+
name: strict accuracy
|
1605 |
+
source:
|
1606 |
+
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bigscience/bloom-3b
|
1607 |
+
name: Open LLM Leaderboard
|
1608 |
+
- task:
|
1609 |
+
type: text-generation
|
1610 |
+
name: Text Generation
|
1611 |
+
dataset:
|
1612 |
+
name: BBH (3-Shot)
|
1613 |
+
type: BBH
|
1614 |
+
args:
|
1615 |
+
num_few_shot: 3
|
1616 |
+
metrics:
|
1617 |
+
- type: acc_norm
|
1618 |
+
value: 3.42
|
1619 |
+
name: normalized accuracy
|
1620 |
+
source:
|
1621 |
+
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bigscience/bloom-3b
|
1622 |
+
name: Open LLM Leaderboard
|
1623 |
+
- task:
|
1624 |
+
type: text-generation
|
1625 |
+
name: Text Generation
|
1626 |
+
dataset:
|
1627 |
+
name: MATH Lvl 5 (4-Shot)
|
1628 |
+
type: hendrycks/competition_math
|
1629 |
+
args:
|
1630 |
+
num_few_shot: 4
|
1631 |
+
metrics:
|
1632 |
+
- type: exact_match
|
1633 |
+
value: 0.08
|
1634 |
+
name: exact match
|
1635 |
+
source:
|
1636 |
+
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bigscience/bloom-3b
|
1637 |
+
name: Open LLM Leaderboard
|
1638 |
+
- task:
|
1639 |
+
type: text-generation
|
1640 |
+
name: Text Generation
|
1641 |
+
dataset:
|
1642 |
+
name: GPQA (0-shot)
|
1643 |
+
type: Idavidrein/gpqa
|
1644 |
+
args:
|
1645 |
+
num_few_shot: 0
|
1646 |
+
metrics:
|
1647 |
+
- type: acc_norm
|
1648 |
+
value: 0.0
|
1649 |
+
name: acc_norm
|
1650 |
+
source:
|
1651 |
+
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bigscience/bloom-3b
|
1652 |
+
name: Open LLM Leaderboard
|
1653 |
+
- task:
|
1654 |
+
type: text-generation
|
1655 |
+
name: Text Generation
|
1656 |
+
dataset:
|
1657 |
+
name: MuSR (0-shot)
|
1658 |
+
type: TAUR-Lab/MuSR
|
1659 |
+
args:
|
1660 |
+
num_few_shot: 0
|
1661 |
+
metrics:
|
1662 |
+
- type: acc_norm
|
1663 |
+
value: 7.89
|
1664 |
+
name: acc_norm
|
1665 |
+
source:
|
1666 |
+
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bigscience/bloom-3b
|
1667 |
+
name: Open LLM Leaderboard
|
1668 |
+
- task:
|
1669 |
+
type: text-generation
|
1670 |
+
name: Text Generation
|
1671 |
+
dataset:
|
1672 |
+
name: MMLU-PRO (5-shot)
|
1673 |
+
type: TIGER-Lab/MMLU-Pro
|
1674 |
+
config: main
|
1675 |
+
split: test
|
1676 |
+
args:
|
1677 |
+
num_few_shot: 5
|
1678 |
+
metrics:
|
1679 |
+
- type: acc
|
1680 |
+
value: 1.48
|
1681 |
+
name: accuracy
|
1682 |
+
source:
|
1683 |
+
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bigscience/bloom-3b
|
1684 |
+
name: Open LLM Leaderboard
|
1685 |
---
|
1686 |
|
1687 |
<h1 style='text-align: center '>BLOOM LM</h1>
|
|
|
2332 |
|
2333 |
Margaret Mitchell, Giada Pistilli, Yacine Jernite, Ezinwanne Ozoani, Marissa Gerchick, Nazneen Rajani, Sasha Luccioni, Irene Solaiman, Maraim Masoud, Somaieh Nikpoor, Carlos Muñoz Ferrandis, Stas Bekman, Christopher Akiki, Danish Contractor, David Lansky, Angelina McMillan-Major, Tristan Thrush, Suzana Ilić, Gérard Dupont, Shayne Longpre, Manan Dey, Stella Biderman, Douwe Kiela, Emi Baylor, Teven Le Scao, Aaron Gokaslan, Julien Launay, Niklas Muennighoff
|
2334 |
|
2335 |
+
|
2336 |
+
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard)
|
2337 |
+
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/bigscience__bloom-3b-details)
|
2338 |
+
|
2339 |
+
| Metric |Value|
|
2340 |
+
|-------------------|----:|
|
2341 |
+
|Avg. | 4.26|
|
2342 |
+
|IFEval (0-Shot) |12.71|
|
2343 |
+
|BBH (3-Shot) | 3.42|
|
2344 |
+
|MATH Lvl 5 (4-Shot)| 0.08|
|
2345 |
+
|GPQA (0-shot) | 0.00|
|
2346 |
+
|MuSR (0-shot) | 7.89|
|
2347 |
+
|MMLU-PRO (5-shot) | 1.48|
|
2348 |
+
|