File size: 1,060 Bytes
e3edc3d |
1 2 3 4 5 6 7 8 9 10 11 12 13 |
global_step,aime24_acc_avg4,aime25_acc_avg4,amc23_acc_avg4,aime24_acc,aime25_acc,amc23_acc,gsm8k_acc,math500_acc,minerva_math_acc,olympiadbench_acc,mmlu_stem_acc,prompt_level_strict_acc_ood,gpqa_pass@1:1_samples_ood
0,0.80,1.70,24.40,3.30,0.00,12.50,61.70,49.00,15.40,16.70,40.10,18.9,0.23
10,2.50,4.20,26.20,13.30,10.00,20.00,74.50,55.40,20.60,24.30,43.30,21.1,0.23
20,6.70,3.30,37.50,0.00,3.30,37.50,79.50,61.80,23.20,22.20,46.50,20.5,0.27
30,5.00,1.70,35.00,3.30,0.00,32.50,79.90,62.20,22.40,24.90,48.50,25.7,0.32
40,8.30,1.70,36.20,6.70,3.30,27.50,80.20,62.80,27.90,25.30,52.00,24.2,0.21
50,10.00,1.70,39.40,6.70,6.70,37.50,80.30,65.40,27.90,28.60,53.40,24.2,0.27
60,5.00,4.20,36.20,6.70,0.00,30.00,81.10,65.00,26.10,25.00,54.20,23.8,0.27
70,10.00,7.50,34.40,3.30,6.70,40.00,81.00,63.80,28.70,28.30,57.00,26.8,0.28
80,11.70,2.50,39.40,6.70,0.00,30.00,81.90,64.40,28.30,28.90,59.00,23.7,0.27
90,9.20,3.30,36.20,13.30,0.00,37.50,81.40,66.40,28.70,28.90,59.80,23.7,0.27
100,10.00,0.80,38.10,6.70,6.70,35.00,82.20,64.00,27.90,28.40,59.30,26.6,0.28
|