Remove incorrect evaluation results.

README.md

@@ -172,1579 +172,6 @@ widget:
 model-index:
 - name: bloom
   results:
-  - task:
-      type: text-generation
-      name: text generation
-    dataset:
-      name: arc_challenge
-      type: arc_challenge
-    metrics:
-    - name: acc
-      type: acc
-      value: 0.4112627986348123
-      verified: false
-  - task:
-      type: text-generation
-      name: text generation
-    dataset:
-      name: arc_easy
-      type: arc_easy
-    metrics:
-    - name: acc
-      type: acc
-      value: 0.726010101010101
-      verified: false
-  - task:
-      type: text-generation
-      name: text generation
-    dataset:
-      name: axb
-      type: axb
-    metrics:
-    - name: acc
-      type: acc
-      value: 0.5751811594202898
-      verified: false
-  - task:
-      type: text-generation
-      name: text generation
-    dataset:
-      name: axg
-      type: axg
-    metrics:
-    - name: acc
-      type: acc
-      value: 0.5252808988764045
-      verified: false
-  - task:
-      type: text-generation
-      name: text generation
-    dataset:
-      name: boolq
-      type: boolq
-    metrics:
-    - name: acc
-      type: acc
-      value: 0.6345565749235474
-      verified: false
-  - task:
-      type: text-generation
-      name: text generation
-    dataset:
-      name: cb
-      type: cb
-    metrics:
-    - name: acc
-      type: acc
-      value: 0.3392857142857143
-      verified: false
-  - task:
-      type: text-generation
-      name: text generation
-    dataset:
-      name: cola
-      type: cola
-    metrics:
-    - name: acc
-      type: acc
-      value: 0.39022051773729627
-      verified: false
-  - task:
-      type: text-generation
-      name: text generation
-    dataset:
-      name: copa
-      type: copa
-    metrics:
-    - name: acc
-      type: acc
-      value: 0.56
-      verified: false
-  - task:
-      type: text-generation
-      name: text generation
-    dataset:
-      name: crows_pairs_english
-      type: crows_pairs_english
-    metrics:
-    - name: acc
-      type: acc
-      value: 0.5
-      verified: false
-  - task:
-      type: text-generation
-      name: text generation
-    dataset:
-      name: crows_pairs_french
-      type: crows_pairs_french
-    metrics:
-    - name: acc
-      type: acc
-      value: 0.505664877757901
-      verified: false
-  - task:
-      type: text-generation
-      name: text generation
-    dataset:
-      name: diabla
-      type: diabla
-    metrics:
-    - name: acc
-      type: acc
-      value: 0.2947981906750174
-      verified: false
-  - task:
-      type: text-generation
-      name: text generation
-    dataset:
-      name: gsarti/flores_101_afr
-      type: gsarti/flores_101_afr
-    metrics:
-    - name: byte_perplexity
-      type: byte_perplexity
-      value: 4.25431550058444
-      verified: false
-  - task:
-      type: text-generation
-      name: text generation
-    dataset:
-      name: gsarti/flores_101_amh
-      type: gsarti/flores_101_amh
-    metrics:
-    - name: byte_perplexity
-      type: byte_perplexity
-      value: 3.716877477347089
-      verified: false
-  - task:
-      type: text-generation
-      name: text generation
-    dataset:
-      name: gsarti/flores_101_ara
-      type: gsarti/flores_101_ara
-    metrics:
-    - name: byte_perplexity
-      type: byte_perplexity
-      value: 1.7049030137120964
-      verified: false
-  - task:
-      type: text-generation
-      name: text generation
-    dataset:
-      name: gsarti/flores_101_asm
-      type: gsarti/flores_101_asm
-    metrics:
-    - name: byte_perplexity
-      type: byte_perplexity
-      value: 6.576581380404954
-      verified: false
-  - task:
-      type: text-generation
-      name: text generation
-    dataset:
-      name: gsarti/flores_101_ast
-      type: gsarti/flores_101_ast
-    metrics:
-    - name: byte_perplexity
-      type: byte_perplexity
-      value: 2.8562364775797944
-      verified: false
-  - task:
-      type: text-generation
-      name: text generation
-    dataset:
-      name: gsarti/flores_101_azj
-      type: gsarti/flores_101_azj
-    metrics:
-    - name: byte_perplexity
-      type: byte_perplexity
-      value: 4.80721528624391
-      verified: false
-  - task:
-      type: text-generation
-      name: text generation
-    dataset:
-      name: gsarti/flores_101_bel
-      type: gsarti/flores_101_bel
-    metrics:
-    - name: byte_perplexity
-      type: byte_perplexity
-      value: 2.7312177406635065
-      verified: false
-  - task:
-      type: text-generation
-      name: text generation
-    dataset:
-      name: gsarti/flores_101_ben
-      type: gsarti/flores_101_ben
-    metrics:
-    - name: byte_perplexity
-      type: byte_perplexity
-      value: 5.993409478990023
-      verified: false
-  - task:
-      type: text-generation
-      name: text generation
-    dataset:
-      name: gsarti/flores_101_bos
-      type: gsarti/flores_101_bos
-    metrics:
-    - name: byte_perplexity
-      type: byte_perplexity
-      value: 3.5936169095529493
-      verified: false
-  - task:
-      type: text-generation
-      name: text generation
-    dataset:
-      name: gsarti/flores_101_bul
-      type: gsarti/flores_101_bul
-    metrics:
-    - name: byte_perplexity
-      type: byte_perplexity
-      value: 2.159035321398085
-      verified: false
-  - task:
-      type: text-generation
-      name: text generation
-    dataset:
-      name: gsarti/flores_101_cat
-      type: gsarti/flores_101_cat
-    metrics:
-    - name: byte_perplexity
-      type: byte_perplexity
-      value: 2.167873680006659
-      verified: false
-  - task:
-      type: text-generation
-      name: text generation
-    dataset:
-      name: gsarti/flores_101_ceb
-      type: gsarti/flores_101_ceb
-    metrics:
-    - name: byte_perplexity
-      type: byte_perplexity
-      value: 5.286975089885673
-      verified: false
-  - task:
-      type: text-generation
-      name: text generation
-    dataset:
-      name: gsarti/flores_101_ces
-      type: gsarti/flores_101_ces
-    metrics:
-    - name: byte_perplexity
-      type: byte_perplexity
-      value: 3.4516208322236017
-      verified: false
-  - task:
-      type: text-generation
-      name: text generation
-    dataset:
-      name: gsarti/flores_101_ckb
-      type: gsarti/flores_101_ckb
-    metrics:
-    - name: byte_perplexity
-      type: byte_perplexity
-      value: 3.7051034724765612
-      verified: false
-  - task:
-      type: text-generation
-      name: text generation
-    dataset:
-      name: gsarti/flores_101_cym
-      type: gsarti/flores_101_cym
-    metrics:
-    - name: byte_perplexity
-      type: byte_perplexity
-      value: 7.0889312398688125
-      verified: false
-  - task:
-      type: text-generation
-      name: text generation
-    dataset:
-      name: gsarti/flores_101_dan
-      type: gsarti/flores_101_dan
-    metrics:
-    - name: byte_perplexity
-      type: byte_perplexity
-      value: 3.4300748208111838
-      verified: false
-  - task:
-      type: text-generation
-      name: text generation
-    dataset:
-      name: gsarti/flores_101_deu
-      type: gsarti/flores_101_deu
-    metrics:
-    - name: byte_perplexity
-      type: byte_perplexity
-      value: 2.3380585896268107
-      verified: false
-  - task:
-      type: text-generation
-      name: text generation
-    dataset:
-      name: gsarti/flores_101_ell
-      type: gsarti/flores_101_ell
-    metrics:
-    - name: byte_perplexity
-      type: byte_perplexity
-      value: 1.9595604725375586
-      verified: false
-  - task:
-      type: text-generation
-      name: text generation
-    dataset:
-      name: gsarti/flores_101_eng
-      type: gsarti/flores_101_eng
-    metrics:
-    - name: byte_perplexity
-      type: byte_perplexity
-      value: 1.8819637649637901
-      verified: false
-  - task:
-      type: text-generation
-      name: text generation
-    dataset:
-      name: gsarti/flores_101_est
-      type: gsarti/flores_101_est
-    metrics:
-    - name: byte_perplexity
-      type: byte_perplexity
-      value: 5.773850600380297
-      verified: false
-  - task:
-      type: text-generation
-      name: text generation
-    dataset:
-      name: gsarti/flores_101_fas
-      type: gsarti/flores_101_fas
-    metrics:
-    - name: byte_perplexity
-      type: byte_perplexity
-      value: 2.4306140728294086
-      verified: false
-  - task:
-      type: text-generation
-      name: text generation
-    dataset:
-      name: gsarti/flores_101_fin
-      type: gsarti/flores_101_fin
-    metrics:
-    - name: byte_perplexity
-      type: byte_perplexity
-      value: 4.304305536244342
-      verified: false
-  - task:
-      type: text-generation
-      name: text generation
-    dataset:
-      name: gsarti/flores_101_fra
-      type: gsarti/flores_101_fra
-    metrics:
-    - name: byte_perplexity
-      type: byte_perplexity
-      value: 1.9374688438541796
-      verified: false
-  - task:
-      type: text-generation
-      name: text generation
-    dataset:
-      name: gsarti/flores_101_ful
-      type: gsarti/flores_101_ful
-    metrics:
-    - name: byte_perplexity
-      type: byte_perplexity
-      value: 9.740353097219378
-      verified: false
-  - task:
-      type: text-generation
-      name: text generation
-    dataset:
-      name: gsarti/flores_101_gle
-      type: gsarti/flores_101_gle
-    metrics:
-    - name: byte_perplexity
-      type: byte_perplexity
-      value: 6.035269765075012
-      verified: false
-  - task:
-      type: text-generation
-      name: text generation
-    dataset:
-      name: gsarti/flores_101_glg
-      type: gsarti/flores_101_glg
-    metrics:
-    - name: byte_perplexity
-      type: byte_perplexity
-      value: 2.365451129546636
-      verified: false
-  - task:
-      type: text-generation
-      name: text generation
-    dataset:
-      name: gsarti/flores_101_guj
-      type: gsarti/flores_101_guj
-    metrics:
-    - name: byte_perplexity
-      type: byte_perplexity
-      value: 5.70676742569154
-      verified: false
-  - task:
-      type: text-generation
-      name: text generation
-    dataset:
-      name: gsarti/flores_101_hau
-      type: gsarti/flores_101_hau
-    metrics:
-    - name: byte_perplexity
-      type: byte_perplexity
-      value: 8.855204288260023
-      verified: false
-  - task:
-      type: text-generation
-      name: text generation
-    dataset:
-      name: gsarti/flores_101_heb
-      type: gsarti/flores_101_heb
-    metrics:
-    - name: byte_perplexity
-      type: byte_perplexity
-      value: 2.920943798471208
-      verified: false
-  - task:
-      type: text-generation
-      name: text generation
-    dataset:
-      name: gsarti/flores_101_hin
-      type: gsarti/flores_101_hin
-    metrics:
-    - name: byte_perplexity
-      type: byte_perplexity
-      value: 5.452028001573195
-      verified: false
-  - task:
-      type: text-generation
-      name: text generation
-    dataset:
-      name: gsarti/flores_101_hrv
-      type: gsarti/flores_101_hrv
-    metrics:
-    - name: byte_perplexity
-      type: byte_perplexity
-      value: 3.7056829077179225
-      verified: false
-  - task:
-      type: text-generation
-      name: text generation
-    dataset:
-      name: gsarti/flores_101_hun
-      type: gsarti/flores_101_hun
-    metrics:
-    - name: byte_perplexity
-      type: byte_perplexity
-      value: 4.058579478967854
-      verified: false
-  - task:
-      type: text-generation
-      name: text generation
-    dataset:
-      name: gsarti/flores_101_hye
-      type: gsarti/flores_101_hye
-    metrics:
-    - name: byte_perplexity
-      type: byte_perplexity
-      value: 3.127237816041562
-      verified: false
-  - task:
-      type: text-generation
-      name: text generation
-    dataset:
-      name: gsarti/flores_101_ibo
-      type: gsarti/flores_101_ibo
-    metrics:
-    - name: byte_perplexity
-      type: byte_perplexity
-      value: 3.9500357969906683
-      verified: false
-  - task:
-      type: text-generation
-      name: text generation
-    dataset:
-      name: gsarti/flores_101_ind
-      type: gsarti/flores_101_ind
-    metrics:
-    - name: byte_perplexity
-      type: byte_perplexity
-      value: 1.976163584180101
-      verified: false
-  - task:
-      type: text-generation
-      name: text generation
-    dataset:
-      name: gsarti/flores_101_isl
-      type: gsarti/flores_101_isl
-    metrics:
-    - name: byte_perplexity
-      type: byte_perplexity
-      value: 5.500542085165231
-      verified: false
-  - task:
-      type: text-generation
-      name: text generation
-    dataset:
-      name: gsarti/flores_101_ita
-      type: gsarti/flores_101_ita
-    metrics:
-    - name: byte_perplexity
-      type: byte_perplexity
-      value: 2.314465100752677
-      verified: false
-  - task:
-      type: text-generation
-      name: text generation
-    dataset:
-      name: gsarti/flores_101_jav
-      type: gsarti/flores_101_jav
-    metrics:
-    - name: byte_perplexity
-      type: byte_perplexity
-      value: 4.942322446550142
-      verified: false
-  - task:
-      type: text-generation
-      name: text generation
-    dataset:
-      name: gsarti/flores_101_jpn
-      type: gsarti/flores_101_jpn
-    metrics:
-    - name: byte_perplexity
-      type: byte_perplexity
-      value: 2.259421750521777
-      verified: false
-  - task:
-      type: text-generation
-      name: text generation
-    dataset:
-      name: gsarti/flores_101_kam
-      type: gsarti/flores_101_kam
-    metrics:
-    - name: byte_perplexity
-      type: byte_perplexity
-      value: 9.743025325635475
-      verified: false
-  - task:
-      type: text-generation
-      name: text generation
-    dataset:
-      name: gsarti/flores_101_kan
-      type: gsarti/flores_101_kan
-    metrics:
-    - name: byte_perplexity
-      type: byte_perplexity
-      value: 6.233724699944989
-      verified: false
-  - task:
-      type: text-generation
-      name: text generation
-    dataset:
-      name: gsarti/flores_101_kat
-      type: gsarti/flores_101_kat
-    metrics:
-    - name: byte_perplexity
-      type: byte_perplexity
-      value: 2.0508893415872107
-      verified: false
-  - task:
-      type: text-generation
-      name: text generation
-    dataset:
-      name: gsarti/flores_101_kaz
-      type: gsarti/flores_101_kaz
-    metrics:
-    - name: byte_perplexity
-      type: byte_perplexity
-      value: 3.0390148516287927
-      verified: false
-  - task:
-      type: text-generation
-      name: text generation
-    dataset:
-      name: gsarti/flores_101_kea
-      type: gsarti/flores_101_kea
-    metrics:
-    - name: byte_perplexity
-      type: byte_perplexity
-      value: 7.147132270533836
-      verified: false
-  - task:
-      type: text-generation
-      name: text generation
-    dataset:
-      name: gsarti/flores_101_khm
-      type: gsarti/flores_101_khm
-    metrics:
-    - name: byte_perplexity
-      type: byte_perplexity
-      value: 3.366514710252477
-      verified: false
-  - task:
-      type: text-generation
-      name: text generation
-    dataset:
-      name: gsarti/flores_101_kir
-      type: gsarti/flores_101_kir
-    metrics:
-    - name: byte_perplexity
-      type: byte_perplexity
-      value: 3.2413845359487885
-      verified: false
-  - task:
-      type: text-generation
-      name: text generation
-    dataset:
-      name: gsarti/flores_101_kor
-      type: gsarti/flores_101_kor
-    metrics:
-    - name: byte_perplexity
-      type: byte_perplexity
-      value: 2.9023196482741027
-      verified: false
-  - task:
-      type: text-generation
-      name: text generation
-    dataset:
-      name: gsarti/flores_101_lao
-      type: gsarti/flores_101_lao
-    metrics:
-    - name: byte_perplexity
-      type: byte_perplexity
-      value: 2.331446855837494
-      verified: false
-  - task:
-      type: text-generation
-      name: text generation
-    dataset:
-      name: gsarti/flores_101_lav
-      type: gsarti/flores_101_lav
-    metrics:
-    - name: byte_perplexity
-      type: byte_perplexity
-      value: 5.223609016485348
-      verified: false
-  - task:
-      type: text-generation
-      name: text generation
-    dataset:
-      name: gsarti/flores_101_lin
-      type: gsarti/flores_101_lin
-    metrics:
-    - name: byte_perplexity
-      type: byte_perplexity
-      value: 4.847471204107301
-      verified: false
-  - task:
-      type: text-generation
-      name: text generation
-    dataset:
-      name: gsarti/flores_101_lit
-      type: gsarti/flores_101_lit
-    metrics:
-    - name: byte_perplexity
-      type: byte_perplexity
-      value: 4.5432035498036765
-      verified: false
-  - task:
-      type: text-generation
-      name: text generation
-    dataset:
-      name: gsarti/flores_101_ltz
-      type: gsarti/flores_101_ltz
-    metrics:
-    - name: byte_perplexity
-      type: byte_perplexity
-      value: 5.5910516978201015
-      verified: false
-  - task:
-      type: text-generation
-      name: text generation
-    dataset:
-      name: gsarti/flores_101_lug
-      type: gsarti/flores_101_lug
-    metrics:
-    - name: byte_perplexity
-      type: byte_perplexity
-      value: 5.4301049946044175
-      verified: false
-  - task:
-      type: text-generation
-      name: text generation
-    dataset:
-      name: gsarti/flores_101_luo
-      type: gsarti/flores_101_luo
-    metrics:
-    - name: byte_perplexity
-      type: byte_perplexity
-      value: 12.031029857399394
-      verified: false
-  - task:
-      type: text-generation
-      name: text generation
-    dataset:
-      name: gsarti/flores_101_mal
-      type: gsarti/flores_101_mal
-    metrics:
-    - name: byte_perplexity
-      type: byte_perplexity
-      value: 4.794302548141229
-      verified: false
-  - task:
-      type: text-generation
-      name: text generation
-    dataset:
-      name: gsarti/flores_101_mar
-      type: gsarti/flores_101_mar
-    metrics:
-    - name: byte_perplexity
-      type: byte_perplexity
-      value: 6.856682255407709
-      verified: false
-  - task:
-      type: text-generation
-      name: text generation
-    dataset:
-      name: gsarti/flores_101_mkd
-      type: gsarti/flores_101_mkd
-    metrics:
-    - name: byte_perplexity
-      type: byte_perplexity
-      value: 2.3354144607382983
-      verified: false
-  - task:
-      type: text-generation
-      name: text generation
-    dataset:
-      name: gsarti/flores_101_mlt
-      type: gsarti/flores_101_mlt
-    metrics:
-    - name: byte_perplexity
-      type: byte_perplexity
-      value: 9.04135227904975
-      verified: false
-  - task:
-      type: text-generation
-      name: text generation
-    dataset:
-      name: gsarti/flores_101_mon
-      type: gsarti/flores_101_mon
-    metrics:
-    - name: byte_perplexity
-      type: byte_perplexity
-      value: 3.094907723618666
-      verified: false
-  - task:
-      type: text-generation
-      name: text generation
-    dataset:
-      name: gsarti/flores_101_mri
-      type: gsarti/flores_101_mri
-    metrics:
-    - name: byte_perplexity
-      type: byte_perplexity
-      value: 5.2659698341456505
-      verified: false
-  - task:
-      type: text-generation
-      name: text generation
-    dataset:
-      name: gsarti/flores_101_msa
-      type: gsarti/flores_101_msa
-    metrics:
-    - name: byte_perplexity
-      type: byte_perplexity
-      value: 2.2220779892820985
-      verified: false
-  - task:
-      type: text-generation
-      name: text generation
-    dataset:
-      name: gsarti/flores_101_mya
-      type: gsarti/flores_101_mya
-    metrics:
-    - name: byte_perplexity
-      type: byte_perplexity
-      value: 2.5229159853414433
-      verified: false
-  - task:
-      type: text-generation
-      name: text generation
-    dataset:
-      name: gsarti/flores_101_nld
-      type: gsarti/flores_101_nld
-    metrics:
-    - name: byte_perplexity
-      type: byte_perplexity
-      value: 2.799153089002766
-      verified: false
-  - task:
-      type: text-generation
-      name: text generation
-    dataset:
-      name: gsarti/flores_101_nob
-      type: gsarti/flores_101_nob
-    metrics:
-    - name: byte_perplexity
-      type: byte_perplexity
-      value: 3.628942049758715
-      verified: false
-  - task:
-      type: text-generation
-      name: text generation
-    dataset:
-      name: gsarti/flores_101_npi
-      type: gsarti/flores_101_npi
-    metrics:
-    - name: byte_perplexity
-      type: byte_perplexity
-      value: 6.666236527803879
-      verified: false
-  - task:
-      type: text-generation
-      name: text generation
-    dataset:
-      name: gsarti/flores_101_nso
-      type: gsarti/flores_101_nso
-    metrics:
-    - name: byte_perplexity
-      type: byte_perplexity
-      value: 5.015319074943932
-      verified: false
-  - task:
-      type: text-generation
-      name: text generation
-    dataset:
-      name: gsarti/flores_101_nya
-      type: gsarti/flores_101_nya
-    metrics:
-    - name: byte_perplexity
-      type: byte_perplexity
-      value: 4.938044040751036
-      verified: false
-  - task:
-      type: text-generation
-      name: text generation
-    dataset:
-      name: gsarti/flores_101_oci
-      type: gsarti/flores_101_oci
-    metrics:
-    - name: byte_perplexity
-      type: byte_perplexity
-      value: 3.607440766288032
-      verified: false
-  - task:
-      type: text-generation
-      name: text generation
-    dataset:
-      name: gsarti/flores_101_orm
-      type: gsarti/flores_101_orm
-    metrics:
-    - name: byte_perplexity
-      type: byte_perplexity
-      value: 11.31585044916705
-      verified: false
-  - task:
-      type: text-generation
-      name: text generation
-    dataset:
-      name: gsarti/flores_101_ory
-      type: gsarti/flores_101_ory
-    metrics:
-    - name: byte_perplexity
-      type: byte_perplexity
-      value: 5.981891184515959
-      verified: false
-  - task:
-      type: text-generation
-      name: text generation
-    dataset:
-      name: gsarti/flores_101_pan
-      type: gsarti/flores_101_pan
-    metrics:
-    - name: byte_perplexity
-      type: byte_perplexity
-      value: 4.7716086841502685
-      verified: false
-  - task:
-      type: text-generation
-      name: text generation
-    dataset:
-      name: gsarti/flores_101_pol
-      type: gsarti/flores_101_pol
-    metrics:
-    - name: byte_perplexity
-      type: byte_perplexity
-      value: 3.01200174157614
-      verified: false
-  - task:
-      type: text-generation
-      name: text generation
-    dataset:
-      name: gsarti/flores_101_por
-      type: gsarti/flores_101_por
-    metrics:
-    - name: byte_perplexity
-      type: byte_perplexity
-      value: 1.8411472115156693
-      verified: false
-  - task:
-      type: text-generation
-      name: text generation
-    dataset:
-      name: gsarti/flores_101_pus
-      type: gsarti/flores_101_pus
-    metrics:
-    - name: byte_perplexity
-      type: byte_perplexity
-      value: 4.623872921169341
-      verified: false
-  - task:
-      type: text-generation
-      name: text generation
-    dataset:
-      name: gsarti/flores_101_ron
-      type: gsarti/flores_101_ron
-    metrics:
-    - name: byte_perplexity
-      type: byte_perplexity
-      value: 3.049829411973529
-      verified: false
-  - task:
-      type: text-generation
-      name: text generation
-    dataset:
-      name: gsarti/flores_101_rus
-      type: gsarti/flores_101_rus
-    metrics:
-    - name: byte_perplexity
-      type: byte_perplexity
-      value: 1.7083443875791493
-      verified: false
-  - task:
-      type: text-generation
-      name: text generation
-    dataset:
-      name: gsarti/flores_101_slk
-      type: gsarti/flores_101_slk
-    metrics:
-    - name: byte_perplexity
-      type: byte_perplexity
-      value: 4.037719650548048
-      verified: false
-  - task:
-      type: text-generation
-      name: text generation
-    dataset:
-      name: gsarti/flores_101_slv
-      type: gsarti/flores_101_slv
-    metrics:
-    - name: byte_perplexity
-      type: byte_perplexity
-      value: 4.141036287764831
-      verified: false
-  - task:
-      type: text-generation
-      name: text generation
-    dataset:
-      name: gsarti/flores_101_sna
-      type: gsarti/flores_101_sna
-    metrics:
-    - name: byte_perplexity
-      type: byte_perplexity
-      value: 4.7109183690601295
-      verified: false
-  - task:
-      type: text-generation
-      name: text generation
-    dataset:
-      name: gsarti/flores_101_snd
-      type: gsarti/flores_101_snd
-    metrics:
-    - name: byte_perplexity
-      type: byte_perplexity
-      value: 4.206170931541356
-      verified: false
-  - task:
-      type: text-generation
-      name: text generation
-    dataset:
-      name: gsarti/flores_101_som
-      type: gsarti/flores_101_som
-    metrics:
-    - name: byte_perplexity
-      type: byte_perplexity
-      value: 9.154342083821405
-      verified: false
-  - task:
-      type: text-generation
-      name: text generation
-    dataset:
-      name: gsarti/flores_101_spa
-      type: gsarti/flores_101_spa
-    metrics:
-    - name: byte_perplexity
-      type: byte_perplexity
-      value: 1.7955816311143258
-      verified: false
-  - task:
-      type: text-generation
-      name: text generation
-    dataset:
-      name: gsarti/flores_101_srp
-      type: gsarti/flores_101_srp
-    metrics:
-    - name: byte_perplexity
-      type: byte_perplexity
-      value: 2.241096141430147
-      verified: false
-  - task:
-      type: text-generation
-      name: text generation
-    dataset:
-      name: gsarti/flores_101_swe
-      type: gsarti/flores_101_swe
-    metrics:
-    - name: byte_perplexity
-      type: byte_perplexity
-      value: 3.344977179674293
-      verified: false
-  - task:
-      type: text-generation
-      name: text generation
-    dataset:
-      name: gsarti/flores_101_swh
-      type: gsarti/flores_101_swh
-    metrics:
-    - name: byte_perplexity
-      type: byte_perplexity
-      value: 2.6844272218041634
-      verified: false
-  - task:
-      type: text-generation
-      name: text generation
-    dataset:
-      name: gsarti/flores_101_tam
-      type: gsarti/flores_101_tam
-    metrics:
-    - name: byte_perplexity
-      type: byte_perplexity
-      value: 5.1645951632801745
-      verified: false
-  - task:
-      type: text-generation
-      name: text generation
-    dataset:
-      name: gsarti/flores_101_tel
-      type: gsarti/flores_101_tel
-    metrics:
-    - name: byte_perplexity
-      type: byte_perplexity
-      value: 6.8098996634099445
-      verified: false
-  - task:
-      type: text-generation
-      name: text generation
-    dataset:
-      name: gsarti/flores_101_tgk
-      type: gsarti/flores_101_tgk
-    metrics:
-    - name: byte_perplexity
-      type: byte_perplexity
-      value: 3.785457016715163
-      verified: false
-  - task:
-      type: text-generation
-      name: text generation
-    dataset:
-      name: gsarti/flores_101_tgl
-      type: gsarti/flores_101_tgl
-    metrics:
-    - name: byte_perplexity
-      type: byte_perplexity
-      value: 3.7498953645610875
-      verified: false
-  - task:
-      type: text-generation
-      name: text generation
-    dataset:
-      name: gsarti/flores_101_tha
-      type: gsarti/flores_101_tha
-    metrics:
-    - name: byte_perplexity
-      type: byte_perplexity
-      value: 2.104151663233468
-      verified: false
-  - task:
-      type: text-generation
-      name: text generation
-    dataset:
-      name: gsarti/flores_101_tur
-      type: gsarti/flores_101_tur
-    metrics:
-    - name: byte_perplexity
-      type: byte_perplexity
-      value: 3.3178240103796037
-      verified: false
-  - task:
-      type: text-generation
-      name: text generation
-    dataset:
-      name: gsarti/flores_101_ukr
-      type: gsarti/flores_101_ukr
-    metrics:
-    - name: byte_perplexity
-      type: byte_perplexity
-      value: 2.088543437159643
-      verified: false
-  - task:
-      type: text-generation
-      name: text generation
-    dataset:
-      name: gsarti/flores_101_umb
-      type: gsarti/flores_101_umb
-    metrics:
-    - name: byte_perplexity
-      type: byte_perplexity
-      value: 11.766013385445124
-      verified: false
-  - task:
-      type: text-generation
-      name: text generation
-    dataset:
-      name: gsarti/flores_101_urd
-      type: gsarti/flores_101_urd
-    metrics:
-    - name: byte_perplexity
-      type: byte_perplexity
-      value: 1.7788699847612357
-      verified: false
-  - task:
-      type: text-generation
-      name: text generation
-    dataset:
-      name: gsarti/flores_101_uzb
-      type: gsarti/flores_101_uzb
-    metrics:
-    - name: byte_perplexity
-      type: byte_perplexity
-      value: 8.499879863290486
-      verified: false
-  - task:
-      type: text-generation
-      name: text generation
-    dataset:
-      name: gsarti/flores_101_vie
-      type: gsarti/flores_101_vie
-    metrics:
-    - name: byte_perplexity
-      type: byte_perplexity
-      value: 1.65901207387262
-      verified: false
-  - task:
-      type: text-generation
-      name: text generation
-    dataset:
-      name: gsarti/flores_101_wol
-      type: gsarti/flores_101_wol
-    metrics:
-    - name: byte_perplexity
-      type: byte_perplexity
-      value: 6.141703791276928
-      verified: false
-  - task:
-      type: text-generation
-      name: text generation
-    dataset:
-      name: gsarti/flores_101_xho
-      type: gsarti/flores_101_xho
-    metrics:
-    - name: byte_perplexity
-      type: byte_perplexity
-      value: 4.690199677955254
-      verified: false
-  - task:
-      type: text-generation
-      name: text generation
-    dataset:
-      name: gsarti/flores_101_yor
-      type: gsarti/flores_101_yor
-    metrics:
-    - name: byte_perplexity
-      type: byte_perplexity
-      value: 4.360585696242932
-      verified: false
-  - task:
-      type: text-generation
-      name: text generation
-    dataset:
-      name: gsarti/flores_101_zho_simpl
-      type: gsarti/flores_101_zho_simpl
-    metrics:
-    - name: byte_perplexity
-      type: byte_perplexity
-      value: 2.1183545781883515
-      verified: false
-  - task:
-      type: text-generation
-      name: text generation
-    dataset:
-      name: gsarti/flores_101_zho_trad
-      type: gsarti/flores_101_zho_trad
-    metrics:
-    - name: byte_perplexity
-      type: byte_perplexity
-      value: 2.273787884962656
-      verified: false
-  - task:
-      type: text-generation
-      name: text generation
-    dataset:
-      name: gsarti/flores_101_zul
-      type: gsarti/flores_101_zul
-    metrics:
-    - name: byte_perplexity
-      type: byte_perplexity
-      value: 6.016954767729589
-      verified: false
-  - task:
-      type: text-generation
-      name: text generation
-    dataset:
-      name: headqa
-      type: headqa
-    metrics:
-    - name: acc
-      type: acc
-      value: 0.3464624361779723
-      verified: false
-  - task:
-      type: text-generation
-      name: text generation
-    dataset:
-      name: hellaswag
-      type: hellaswag
-    metrics:
-    - name: acc
-      type: acc
-      value: 0.5353515236008763
-      verified: false
-  - task:
-      type: text-generation
-      name: text generation
-    dataset:
-      name: lambada_mt_de
-      type: lambada_mt_de
-    metrics:
-    - name: acc
-      type: acc
-      value: 0.3291286629148069
-      verified: false
-  - task:
-      type: text-generation
-      name: text generation
-    dataset:
-      name: lambada_mt_en
-      type: lambada_mt_en
-    metrics:
-    - name: acc
-      type: acc
-      value: 0.6720357073549389
-      verified: false
-  - task:
-      type: text-generation
-      name: text generation
-    dataset:
-      name: lambada_mt_es
-      type: lambada_mt_es
-    metrics:
-    - name: acc
-      type: acc
-      value: 0.476421502037648
-      verified: false
-  - task:
-      type: text-generation
-      name: text generation
-    dataset:
-      name: lambada_mt_it
-      type: lambada_mt_it
-    metrics:
-    - name: acc
-      type: acc
-      value: 0.4061711624296526
-      verified: false
-  - task:
-      type: text-generation
-      name: text generation
-    dataset:
-      name: logiqa
-      type: logiqa
-    metrics:
-    - name: acc
-      type: acc
-      value: 0.2350230414746544
-      verified: false
-  - task:
-      type: text-generation
-      name: text generation
-    dataset:
-      name: mathqa
-      type: mathqa
-    metrics:
-    - name: acc
-      type: acc
-      value: 0.27671691792294806
-      verified: false
-  - task:
-      type: text-generation
-      name: text generation
-    dataset:
-      name: mc_taco
-      type: mc_taco
-    metrics:
-    - name: em
-      type: em
-      value: 0.13063063063063063
-      verified: false
-  - task:
-      type: text-generation
-      name: text generation
-    dataset:
-      name: mnli
-      type: mnli
-    metrics:
-    - name: acc
-      type: acc
-      value: 0.3545565500406835
-      verified: false
-  - task:
-      type: text-generation
-      name: text generation
-    dataset:
-      name: mnli_mismatched
-      type: mnli_mismatched
-    metrics:
-    - name: acc
-      type: acc
-      value: 0.3545565500406835
-      verified: false
-  - task:
-      type: text-generation
-      name: text generation
-    dataset:
-      name: mrpc
-      type: mrpc
-    metrics:
-    - name: acc
-      type: acc
-      value: 0.3872549019607843
-      verified: false
-  - task:
-      type: text-generation
-      name: text generation
-    dataset:
-      name: multirc
-      type: multirc
-    metrics:
-    - name: acc
-      type: acc
-      value: 0.570957095709571
-      verified: false
-  - task:
-      type: text-generation
-      name: text generation
-    dataset:
-      name: openbookqa
-      type: openbookqa
-    metrics:
-    - name: acc
-      type: acc
-      value: 0.312
-      verified: false
-  - task:
-      type: text-generation
-      name: text generation
-    dataset:
-      name: piqa
-      type: piqa
-    metrics:
-    - name: acc
-      type: acc
-      value: 0.7812840043525572
-      verified: false
-  - task:
-      type: text-generation
-      name: text generation
-    dataset:
-      name: prost
-      type: prost
-    metrics:
-    - name: acc
-      type: acc
-      value: 0.2977156276686593
-      verified: false
-  - task:
-      type: text-generation
-      name: text generation
-    dataset:
-      name: pubmedqa
-      type: pubmedqa
-    metrics:
-    - name: acc
-      type: acc
-      value: 0.741
-      verified: false
-  - task:
-      type: text-generation
-      name: text generation
-    dataset:
-      name: qnli
-      type: qnli
-    metrics:
-    - name: acc
-      type: acc
-      value: 0.5172981878088962
-      verified: false
-  - task:
-      type: text-generation
-      name: text generation
-    dataset:
-      name: qqp
-      type: qqp
-    metrics:
-    - name: acc
-      type: acc
-      value: 0.5883007667573584
-      verified: false
-  - task:
-      type: text-generation
-      name: text generation
-    dataset:
-      name: race
-      type: race
-    metrics:
-    - name: acc
-      type: acc
-      value: 0.39043062200956935
-      verified: false
-  - task:
-      type: text-generation
-      name: text generation
-    dataset:
-      name: rte
-      type: rte
-    metrics:
-    - name: acc
-      type: acc
-      value: 0.5198555956678701
-      verified: false
-  - task:
-      type: text-generation
-      name: text generation
-    dataset:
-      name: sciq
-      type: sciq
-    metrics:
-    - name: acc
-      type: acc
-      value: 0.936
-      verified: false
-  - task:
-      type: text-generation
-      name: text generation
-    dataset:
-      name: sst
-      type: sst
-    metrics:
-    - name: acc
-      type: acc
-      value: 0.6043577981651376
-      verified: false
-  - task:
-      type: text-generation
-      name: text generation
-    dataset:
-      name: triviaqa
-      type: triviaqa
-    metrics:
-    - name: acc
-      type: acc
-      value: 0.18332891363917617
-      verified: false
-  - task:
-      type: text-generation
-      name: text generation
-    dataset:
-      name: tydiqa_primary
-      type: tydiqa_primary
-    metrics:
-    - name: acc
-      type: acc
-      value: 0.2809817301342725
-      verified: false
-  - task:
-      type: text-generation
-      name: text generation
-    dataset:
-      name: webqs
-      type: webqs
-    metrics:
-    - name: acc
-      type: acc
-      value: 0.061515748031496065
-      verified: false
-  - task:
-      type: text-generation
-      name: text generation
-    dataset:
-      name: wic
-      type: wic
-    metrics:
-    - name: acc
-      type: acc
-      value: 0.5062695924764891
-      verified: false
-  - task:
-      type: text-generation
-      name: text generation
-    dataset:
-      name: winogrande
-      type: winogrande
-    metrics:
-    - name: acc
-      type: acc
-      value: 0.7095501183898973
-      verified: false
-  - task:
-      type: text-generation
-      name: text generation
-    dataset:
-      name: wnli
-      type: wnli
-    metrics:
-    - name: acc
-      type: acc
-      value: 0.5704225352112676
-      verified: false
-  - task:
-      type: text-generation
-      name: text generation
-    dataset:
-      name: wsc
-      type: wsc
-    metrics:
-    - name: acc
-      type: acc
-      value: 0.5192307692307693
-      verified: false
   - task:
       type: text-generation
       name: text generation
@@ -2164,7 +591,6 @@ Model may:
 ## Metrics 
 *This section describes the different ways performance is calculated and why.*
 
-
 Includes:
 
 | Metric             | Why chosen                                                         |
@@ -2188,155 +614,12 @@ And multiple different metrics for specific tasks. _(More evaluation metrics for
 
 **Zero-shot evaluations:**
 
-# <span style="color:red"><b>WARNING:</b> These are <b>intermediate results</b></span>
+<span style="color:red"><b>WARNING:</b> This section used to contain much more results, however they were not correct and we released without the approval of the evaluation working group. We are currently in the process of fixing the evaluations.</span>
 
 See this repository for JSON files: https://github.com/bigscience-workshop/evaluation-results
 
 | Task | Language | Metric | BLOOM-176B | OPT-175B* |
-|:--------|:-----------------|:------------------------|-------------:|------------:|
-| arc_challenge | eng | acc ↑ | 0.411 | 0.412 |
-| arc_easy | eng | acc ↑ | 0.726 | 0.751 |
-| axb (Median of 10 prompts) | eng | acc ↑ | 0.575 | 0.532 |
-| axg (Median of 10 prompts) | eng | acc ↑ | 0.525 | 0.548 |
-| boolq (Median of 11 prompts) | eng | acc ↑ | 0.635 | 0.622 |
-| cb (Median of 15 prompts) | eng | acc ↑ | 0.339 | 0.411 |
-| cola (Median of 5 prompts) | eng | acc ↑ | 0.39 | 0.444 |
-| copa (Median of 9 prompts) | eng | acc ↑ | 0.56 | 0.55 |
-| crows_pairs_english (Median of 6 prompts) | eng | acc ↑ | 0.5 | 0.502 |
-| crows_pairs_french (Median of 7 prompts) | fra | acc ↑ | 0.506 | 0.499 |
-| diabla (Median of 2 prompts) | eng | acc ↑ | 0.295 | 0.289 |
-| gsarti/flores_101_afr | afr | byte_perplexity ↓ | 4.254 | 3.381 |
-| gsarti/flores_101_amh | amh | byte_perplexity ↓ | 3.717 | 3.87 |
-| gsarti/flores_101_ara | ara | byte_perplexity ↓ | 1.705 | 2.42 |
-| gsarti/flores_101_asm | asm | byte_perplexity ↓ | 6.577 | 3.028 |
-| gsarti/flores_101_ast | ast | byte_perplexity ↓ | 2.856 | 4.737 |
-| gsarti/flores_101_azj | azj | byte_perplexity ↓ | 4.807 | 4.767 |
-| gsarti/flores_101_bel | bel | byte_perplexity ↓ | 2.731 | 2.557 |
-| gsarti/flores_101_ben | ben | byte_perplexity ↓ | 5.993 | 2.243 |
-| gsarti/flores_101_bos | bos | byte_perplexity ↓ | 3.594 | 2.668 |
-| gsarti/flores_101_bul | bul | byte_perplexity ↓ | 2.159 | 2.099 |
-| gsarti/flores_101_cat | cat | byte_perplexity ↓ | 2.168 | 2.837 |
-| gsarti/flores_101_ceb | ceb | byte_perplexity ↓ | 5.287 | 3.636 |
-| gsarti/flores_101_ces | ces | byte_perplexity ↓ | 3.452 | 2.749 |
-| gsarti/flores_101_ckb | ckb | byte_perplexity ↓ | 3.705 | 4.688 |
-| gsarti/flores_101_cym | cym | byte_perplexity ↓ | 7.089 | 5.075 |
-| gsarti/flores_101_dan | dan | byte_perplexity ↓ | 3.43 | 2.492 |
-| gsarti/flores_101_deu | deu | byte_perplexity ↓ | 2.338 | 2.099 |
-| gsarti/flores_101_ell | ell | byte_perplexity ↓ | 1.96 | 1.811 |
-| gsarti/flores_101_eng | eng | byte_perplexity ↓ | 1.882 | 1.9 |
-| gsarti/flores_101_est | est | byte_perplexity ↓ | 5.774 | 3.533 |
-| gsarti/flores_101_fas | fas | byte_perplexity ↓ | 2.431 | 2.444 |
-| gsarti/flores_101_fin | fin | byte_perplexity ↓ | 4.304 | 2.601 |
-| gsarti/flores_101_fra | fra | byte_perplexity ↓ | 1.937 | 1.984 |
-| gsarti/flores_101_ful | ful | byte_perplexity ↓ | 9.74 | 11.84 |
-| gsarti/flores_101_gle | gle | byte_perplexity ↓ | 6.035 | 3.914 |
-| gsarti/flores_101_glg | glg | byte_perplexity ↓ | 2.365 | 3.015 |
-| gsarti/flores_101_guj | guj | byte_perplexity ↓ | 5.707 | 2.438 |
-| gsarti/flores_101_hau | hau | byte_perplexity ↓ | 8.855 | 5.283 |
-| gsarti/flores_101_heb | heb | byte_perplexity ↓ | 2.921 | 2.903 |
-| gsarti/flores_101_hin | hin | byte_perplexity ↓ | 5.452 | 1.86 |
-| gsarti/flores_101_hrv | hrv | byte_perplexity ↓ | 3.706 | 2.715 |
-| gsarti/flores_101_hun | hun | byte_perplexity ↓ | 4.059 | 2.865 |
-| gsarti/flores_101_hye | hye | byte_perplexity ↓ | 3.127 | 3.411 |
-| gsarti/flores_101_ibo | ibo | byte_perplexity ↓ | 3.95 | 8.008 |
-| gsarti/flores_101_ind | ind | byte_perplexity ↓ | 1.976 | 2.632 |
-| gsarti/flores_101_isl | isl | byte_perplexity ↓ | 5.501 | 4.701 |
-| gsarti/flores_101_ita | ita | byte_perplexity ↓ | 2.314 | 2.104 |
-| gsarti/flores_101_jav | jav | byte_perplexity ↓ | 4.942 | 8.16 |
-| gsarti/flores_101_jpn | jpn | byte_perplexity ↓ | 2.259 | 2.198 |
-| gsarti/flores_101_kam | kam | byte_perplexity ↓ | 9.743 | 10.981 |
-| gsarti/flores_101_kan | kan | byte_perplexity ↓ | 6.234 | 2.373 |
-| gsarti/flores_101_kat | kat | byte_perplexity ↓ | 2.051 | 2.466 |
-| gsarti/flores_101_kaz | kaz | byte_perplexity ↓ | 3.039 | 4.376 |
-| gsarti/flores_101_kea | kea | byte_perplexity ↓ | 7.147 | 9.632 |
-| gsarti/flores_101_khm | khm | byte_perplexity ↓ | 3.367 | 2.646 |
-| gsarti/flores_101_kir | kir | byte_perplexity ↓ | 3.241 | 4.522 |
-| gsarti/flores_101_kor | kor | byte_perplexity ↓ | 2.902 | 3.376 |
-| gsarti/flores_101_lao | lao | byte_perplexity ↓ | 2.331 | 3.106 |
-| gsarti/flores_101_lav | lav | byte_perplexity ↓ | 5.224 | 4.811 |
-| gsarti/flores_101_lin | lin | byte_perplexity ↓ | 4.847 | 8.871 |
-| gsarti/flores_101_lit | lit | byte_perplexity ↓ | 4.543 | 5.183 |
-| gsarti/flores_101_ltz | ltz | byte_perplexity ↓ | 5.591 | 7.158 |
-| gsarti/flores_101_lug | lug | byte_perplexity ↓ | 5.43 | 7.399 |
-| gsarti/flores_101_luo | luo | byte_perplexity ↓ | 12.031 | 11.951 |
-| gsarti/flores_101_mal | mal | byte_perplexity ↓ | 4.794 | 2.054 |
-| gsarti/flores_101_mar | mar | byte_perplexity ↓ | 6.857 | 2.274 |
-| gsarti/flores_101_mkd | mkd | byte_perplexity ↓ | 2.335 | 2.538 |
-| gsarti/flores_101_mlt | mlt | byte_perplexity ↓ | 9.041 | 5.996 |
-| gsarti/flores_101_mon | mon | byte_perplexity ↓ | 3.095 | 4.519 |
-| gsarti/flores_101_mri | mri | byte_perplexity ↓ | 5.266 | 4.438 |
-| gsarti/flores_101_msa | msa | byte_perplexity ↓ | 2.222 | 2.935 |
-| gsarti/flores_101_mya | mya | byte_perplexity ↓ | 2.523 | 2.413 |
-| gsarti/flores_101_nld | nld | byte_perplexity ↓ | 2.799 | 2.293 |
-| gsarti/flores_101_nob | nob | byte_perplexity ↓ | 3.629 | 2.593 |
-| gsarti/flores_101_npi | npi | byte_perplexity ↓ | 6.666 | 2.499 |
-| gsarti/flores_101_nso | nso | byte_perplexity ↓ | 5.015 | 8.485 |
-| gsarti/flores_101_nya | nya | byte_perplexity ↓ | 4.938 | 7.548 |
-| gsarti/flores_101_oci | oci | byte_perplexity ↓ | 3.607 | 4.936 |
-| gsarti/flores_101_orm | orm | byte_perplexity ↓ | 11.316 | 7.145 |
-| gsarti/flores_101_ory | ory | byte_perplexity ↓ | 5.982 | 2.668 |
-| gsarti/flores_101_pan | pan | byte_perplexity ↓ | 4.772 | 2.782 |
-| gsarti/flores_101_pol | pol | byte_perplexity ↓ | 3.012 | 2.432 |
-| gsarti/flores_101_por | por | byte_perplexity ↓ | 1.841 | 2.178 |
-| gsarti/flores_101_pus | pus | byte_perplexity ↓ | 4.624 | 4.785 |
-| gsarti/flores_101_ron | ron | byte_perplexity ↓ | 3.05 | 2.197 |
-| gsarti/flores_101_rus | rus | byte_perplexity ↓ | 1.708 | 1.689 |
-| gsarti/flores_101_slk | slk | byte_perplexity ↓ | 4.038 | 3.419 |
-| gsarti/flores_101_slv | slv | byte_perplexity ↓ | 4.141 | 3.582 |
-| gsarti/flores_101_sna | sna | byte_perplexity ↓ | 4.711 | 5.588 |
-| gsarti/flores_101_snd | snd | byte_perplexity ↓ | 4.206 | 5.667 |
-| gsarti/flores_101_som | som | byte_perplexity ↓ | 9.154 | 4.788 |
-| gsarti/flores_101_spa | spa | byte_perplexity ↓ | 1.796 | 2.098 |
-| gsarti/flores_101_srp | srp | byte_perplexity ↓ | 2.241 | 2.688 |
-| gsarti/flores_101_swe | swe | byte_perplexity ↓ | 3.345 | 2.468 |
-| gsarti/flores_101_swh | swh | byte_perplexity ↓ | 2.684 | 4.473 |
-| gsarti/flores_101_tam | tam | byte_perplexity ↓ | 5.165 | 2.024 |
-| gsarti/flores_101_tel | tel | byte_perplexity ↓ | 6.81 | 2.407 |
-| gsarti/flores_101_tgk | tgk | byte_perplexity ↓ | 3.785 | 4.899 |
-| gsarti/flores_101_tgl | tgl | byte_perplexity ↓ | 3.75 | 2.738 |
-| gsarti/flores_101_tha | tha | byte_perplexity ↓ | 2.104 | 2.035 |
-| gsarti/flores_101_tur | tur | byte_perplexity ↓ | 3.318 | 2.622 |
-| gsarti/flores_101_ukr | ukr | byte_perplexity ↓ | 2.089 | 1.93 |
-| gsarti/flores_101_umb | umb | byte_perplexity ↓ | 11.766 | 11.64 |
-| gsarti/flores_101_urd | urd | byte_perplexity ↓ | 1.779 | 2.982 |
-| gsarti/flores_101_uzb | uzb | byte_perplexity ↓ | 8.5 | 13.209 |
-| gsarti/flores_101_vie | vie | byte_perplexity ↓ | 1.659 | 2.229 |
-| gsarti/flores_101_wol | wol | byte_perplexity ↓ | 6.142 | 13.945 |
-| gsarti/flores_101_xho | xho | byte_perplexity ↓ | 4.69 | 8.42 |
-| gsarti/flores_101_yor | yor | byte_perplexity ↓ | 4.361 | 7.636 |
-| gsarti/flores_101_zho_simpl | zho_simpl | byte_perplexity ↓ | 2.118 | 5.113 |
-| gsarti/flores_101_zho_trad | zho_trad | byte_perplexity ↓ | 2.274 | 5.67 |
-| gsarti/flores_101_zul | zul | byte_perplexity ↓ | 6.017 | 7.341 |
-| headqa | esp | acc ↑ | 0.346 | 0.244 |
-| hellaswag | eng | acc ↑ | 0.535 | 0.592 |
-| lambada_mt_de | deu | acc ↑ | 0.329 | 0.358 |
-| lambada_mt_en | eng | acc ↑ | 0.672 | 0.747 |
-| lambada_mt_es | esp | acc ↑ | 0.476 | 0.397 |
-| lambada_mt_it | ita | acc ↑ | 0.406 | 0.409 |
-| logiqa | eng | acc ↑ | 0.235 | 0.244 |
-| mathqa | eng | acc ↑ | 0.277 | 0.268 |
-| mc_taco | eng | em ↑ | 0.131 | 0.124 |
-| mnli (Median of 15 prompts) | eng | acc ↑ | 0.355 | 0.36 |
-| mnli_mismatched (Median of 15 prompts) | eng | acc ↑ | 0.355 | 0.36 |
-| mrpc | eng | acc ↑ | 0.387 | 0.446 |
-| multirc (Median of 11 prompts) | eng | acc ↑ | 0.571 | 0.599 |
-| openbookqa | eng | acc ↑ | 0.312 | 0.322 |
-| piqa | eng | acc ↑ | 0.781 | 0.791 |
-| prost | eng | acc ↑ | 0.298 | 0.299 |
-| pubmedqa | eng | acc ↑ | 0.741 | 0.709 |
-| qnli | eng | acc ↑ | 0.517 | 0.554 |
-| qqp (Median of 7 prompts) | eng | acc ↑ | 0.588 | 0.395 |
-| race | eng | acc ↑ | 0.39 | 0.402 |
-| rte (Median of 6 prompts) | eng | acc ↑ | 0.52 | 0.495 |
-| sciq | eng | acc ↑ | 0.936 | 0.948 |
-| sst (Median of 6 prompts) | eng | acc ↑ | 0.604 | 0.647 |
-| triviaqa | eng | acc ↑ | 0.183 | 0.342 |
-| tydiqa_primary (Median of 16 prompts) | eng | acc ↑ | 0.281 | 0.148 |
-| webqs | eng | acc ↑ | 0.062 | 0.159 |
-| wic (Median of 11 prompts) | eng | acc ↑ | 0.506 | 0.498 |
-| winogrande | eng | acc ↑ | 0.71 | 0.736 |
-| wnli (Median of 6 prompts) | eng | acc ↑ | 0.57 | 0.563 |
-| wsc (Median of 11 prompts) | eng | acc ↑ | 0.519 | 0.413 |
+|:--------|:-----------------|:------------------------|-------------:|------------:|jjj
 | humaneval | python | pass@1 ↑ | 0.155 | 0.0 |
 | humaneval | python | pass@10 ↑ | 0.328 | 0.0 |
 | humaneval | python | pass@100 ↑ | 0.572 | 0.003 |