Tucano-630m / EVALS-medium.csv
nicholasKluge's picture
Upload EVALS-medium.csv with huggingface_hub
7ad32b9 verified
raw
history blame
1.94 kB
step,enem,bluex,oab_exams,assin2_rte,assin2_sts,faquad_nli,hatebr,hatespeech_pt,tweet_br,arc_pt,hellaswag_pt,truthfulqa,calame_pt,lambada_pt
20000,19.52,20.58,24.28,34.02,2.76,43.97,33.9,22.99,23.16,25.64,33.28,41.74,52.26,26.12
40000,20.71,22.67,24.87,35.61,1.89,43.97,22.21,22.99,15.07,27.61,34.51,39.61,51.93,28.24
60000,20.01,24.62,27.02,33.33,0.87,43.97,33.33,41.23,15.49,27.01,34.73,40.51,52.5,27.23
80000,18.75,21.84,24.33,33.42,7.28,43.97,33.71,42.02,19.81,26.24,35.88,39.9,53.03,29.69
100000,20.64,19.89,24.56,33.33,3.06,43.97,33.33,41.23,20.73,28.55,36.18,41.75,53.47,28.76
120000,19.52,19.33,24.37,34.95,0.78,43.97,37.58,42.26,20.73,27.95,36.63,42.25,53.18,29.32
140000,20.43,24.48,24.1,33.33,3.33,43.97,53.0,42.42,20.73,27.01,36.91,40.61,53.9,27.65
160000,20.57,23.09,27.11,47.31,0.52,43.97,33.49,22.99,21.83,26.84,37.45,41.91,54.19,29.96
180000,20.5,19.75,24.74,38.51,1.59,43.97,33.65,22.99,20.73,29.32,37.51,40.27,55.2,30.25
200000,20.36,24.76,25.83,49.77,1.24,43.97,38.38,23.85,24.36,27.26,38.26,39.82,54.48,32.78
220000,18.96,24.2,25.24,37.53,5.04,43.97,33.65,22.99,20.73,28.46,38.4,42.24,55.39,33.34
240000,20.57,21.56,23.96,55.96,1.67,43.97,42.21,31.62,20.73,28.21,38.9,41.12,55.78,32.66
260000,20.01,18.92,23.64,36.61,1.66,43.97,48.63,25.06,20.73,28.38,39.04,41.25,55.44,33.57
280000,19.17,21.14,25.6,53.23,0.18,43.97,53.36,45.31,20.73,28.38,39.5,41.92,55.64,32.29
300000,19.8,19.89,25.47,57.79,2.57,43.97,34.46,22.99,20.72,27.78,39.4,41.9,55.83,33.44
320000,18.61,22.39,25.88,61.51,7.66,43.97,55.62,39.26,24.75,28.8,39.39,42.82,56.55,33.32
340000,20.22,21.7,25.69,55.58,2.74,43.97,56.21,35.7,20.73,28.63,39.48,42.34,56.89,33.18
360000,18.96,24.48,25.74,59.17,10.57,43.97,55.6,26.08,28.63,28.46,39.48,42.37,56.17,33.5
380000,18.12,24.34,25.65,41.19,2.13,43.97,33.78,23.17,22.64,28.63,39.31,43.2,56.5,33.73
400000,19.17,24.76,25.28,57.79,1.99,43.97,53.73,30.01,20.73,28.89,39.41,42.76,56.55,33.13