Tucano-160m / EVALS-small.csv
nicholasKluge's picture
Upload EVALS-small.csv with huggingface_hub
b92a108 verified
raw
history blame
1.57 kB
step,enem,bluex,oab_exams,assin2_rte,assin2_sts,faquad_nli,hatebr,hatespeech_pt,tweet_br,calame_pt,arc_pt,hellaswag_pt,truthfulqa,lambada_pt
20000,19.73,20.72,24.28,42.64,4.41,43.97,44.6,49.57,15.07,45.95,25.13,30.41,41.2,21.99
40000,19.31,21.55,25.19,49.16,0.0,43.97,44.89,48.85,15.91,47.11,25.81,30.9,41.33,22.61
60000,18.96,19.47,24.51,38.23,3.82,49.93,51.77,52.37,20.72,47.78,26.58,31.2,41.34,21.41
80000,19.31,23.92,12.35,41.1,6.51,43.97,45.3,44.38,21.08,49.47,25.38,31.4,43.55,23.91
100000,20.36,24.34,24.15,33.42,1.55,43.97,34.58,23.17,26.42,48.94,25.9,31.96,42.29,24.45
120000,20.01,23.64,25.56,33.33,2.16,44.12,33.49,22.99,21.61,49.86,25.38,32.16,41.97,25.64
140000,20.36,20.72,23.74,33.33,1.57,44.23,34.39,23.17,30.22,50.0,26.67,32.17,43.75,22.88
160000,18.19,20.72,22.46,33.33,3.42,43.63,33.33,22.99,19.67,51.54,25.21,32.71,42.78,26.0
180000,19.52,20.03,23.96,33.33,10.83,43.97,33.33,22.99,16.7,51.4,26.24,32.73,41.75,26.99
200000,19.1,20.58,24.6,33.33,7.45,43.97,33.33,22.99,24.22,51.4,26.32,32.39,41.62,28.59
220000,19.45,23.5,25.19,33.33,5.65,43.97,33.33,22.99,18.7,52.55,26.41,32.74,42.44,28.43
240000,19.73,22.25,25.69,56.57,16.72,43.97,45.65,22.99,19.13,52.17,27.01,33.06,41.9,29.65
260000,19.45,20.31,25.19,33.42,17.28,43.97,34.49,22.99,23.82,52.31,27.01,33.16,41.53,27.5
280000,19.8,22.11,25.65,33.33,9.42,43.97,33.49,22.99,25.77,52.46,27.44,32.94,41.5,28.33
300000,20.71,20.45,25.42,33.7,2.23,43.97,33.33,22.99,21.99,52.17,26.92,33.17,41.43,28.35
320000,19.03,22.11,25.1,33.51,11.02,43.97,36.56,22.99,16.86,52.31,27.01,33.07,41.53,28.16