training/training_log.csv

step,training_loss,reward,reward_std,completions_mean_length,completions_min_length,completions_max_length,completions_clipped_ratio,kl
1,-0.060018,0.625000,0.517549,43.250000,27.000000,56.000000,0.000000,0.002182
2,-0.047053,0.875000,0.353553,40.375000,31.000000,55.000000,0.000000,0.001492
3,-0.029097,0.750000,0.462910,41.750000,34.000000,49.000000,0.000000,0.001947
4,0.057362,0.625000,0.517549,42.625000,32.000000,58.000000,0.000000,0.002306
5,0.000002,1.000000,0.000000,46.375000,31.000000,60.000000,0.125000,0.002317
6,0.071317,0.750000,0.462910,53.000000,41.000000,60.000000,0.500000,0.003499
7,0.132661,0.375000,0.517549,49.375000,34.000000,60.000000,0.125000,0.001893
8,0.000003,1.000000,0.000000,43.750000,32.000000,60.000000,0.125000,0.002778
9,-0.006705,0.625000,0.517549,36.000000,25.000000,50.000000,0.000000,0.002747
10,0.000003,1.000000,0.000000,50.000000,32.000000,60.000000,0.250000,0.002621
11,-0.117493,0.375000,0.517549,41.875000,25.000000,60.000000,0.250000,0.002014
12,0.062407,0.250000,0.462910,49.750000,30.000000,60.000000,0.375000,0.001363
13,-0.027897,0.750000,0.462910,41.125000,29.000000,55.000000,0.000000,0.002789
14,0.024585,0.375000,0.517549,41.750000,28.000000,60.000000,0.000000,0.002910
15,0.000001,1.000000,0.000000,46.000000,37.000000,60.000000,0.125000,0.001280
16,0.000002,1.000000,0.000000,38.750000,23.000000,47.000000,0.000000,0.001852