afem/logs/train_4537.out

419 lines
51 KiB
Plaintext

Starting training at Sat 30 May 15:16:09 CST 2026
Running on node: node06
[Device] cuda
[Env] node_feats=13 edge_feats=1 act_dim=1
[Model] params=92,740
1/401 | loss=1.4016 ev=-0.007 agents=109 avg_r=-3.9659 sum_r=-1015.28 x<0=0.79 elig=0.58 dorfler_tail=0.09 floor=0 sel=35 8.7s
2/401 | loss=1.2826 ev=0.030 agents=193 avg_r=-2.0419 sum_r=-522.72 x<0=0.80 elig=0.58 dorfler_tail=0.08 floor=0 sel=32 7.9s
3/401 | loss=1.2362 ev=0.058 agents=39 avg_r=-4.8186 sum_r=-1233.57 x<0=0.80 elig=0.59 dorfler_tail=0.08 floor=0 sel=32 7.8s
4/401 | loss=1.2801 ev=0.101 agents=34 avg_r=-0.7326 sum_r=-187.54 x<0=0.77 elig=0.58 dorfler_tail=0.09 floor=0 sel=35 8.3s
5/401 | loss=1.1594 ev=0.132 agents=88 avg_r=-3.2420 sum_r=-829.95 x<0=0.74 elig=0.59 dorfler_tail=0.08 floor=0 sel=32 8.0s
6/401 | loss=1.1517 ev=0.181 agents=36 avg_r=-1.5350 sum_r=-392.96 x<0=0.70 elig=0.59 dorfler_tail=0.08 floor=0 sel=32 7.9s
7/401 | loss=1.0153 ev=0.253 agents=34 avg_r=-0.7087 sum_r=-181.42 x<0=0.67 elig=0.58 dorfler_tail=0.08 floor=0 sel=35 8.1s
8/401 | loss=1.0623 ev=0.283 agents=133 avg_r=-0.8781 sum_r=-224.79 x<0=0.65 elig=0.59 dorfler_tail=0.08 floor=0 sel=33 7.9s
9/401 | loss=0.9819 ev=0.304 agents=79 avg_r=-0.5083 sum_r=-130.11 x<0=0.61 elig=0.59 dorfler_tail=0.08 floor=0 sel=31 7.7s
10/401 | loss=0.9743 ev=0.299 agents=82 avg_r=-2.3678 sum_r=-606.16 x<0=0.59 elig=0.59 dorfler_tail=0.08 floor=0 sel=33 7.9s
11/401 | loss=1.0183 ev=0.320 agents=60 avg_r=1.3849 sum_r=354.54 x<0=0.53 elig=0.59 dorfler_tail=0.08 floor=0 sel=31 7.6s
12/401 | loss=0.9395 ev=0.343 agents=48 avg_r=0.4274 sum_r=109.42 x<0=0.50 elig=0.59 dorfler_tail=0.08 floor=0 sel=33 7.8s
13/401 | loss=0.8380 ev=0.367 agents=88 avg_r=-0.3599 sum_r=-92.14 x<0=0.45 elig=0.59 dorfler_tail=0.08 floor=0 sel=32 7.8s
14/401 | loss=0.9338 ev=0.341 agents=40 avg_r=0.1794 sum_r=45.93 x<0=0.42 elig=0.59 dorfler_tail=0.08 floor=0 sel=32 7.7s
15/401 | loss=0.8502 ev=0.381 agents=101 avg_r=0.1944 sum_r=49.77 x<0=0.42 elig=0.59 dorfler_tail=0.08 floor=0 sel=33 8.0s
16/401 | loss=0.9830 ev=0.370 agents=34 avg_r=-1.4113 sum_r=-361.30 x<0=0.40 elig=0.59 dorfler_tail=0.08 floor=0 sel=29 7.4s
17/401 | loss=0.8119 ev=0.428 agents=132 avg_r=1.8346 sum_r=469.66 x<0=0.42 elig=0.59 dorfler_tail=0.08 floor=0 sel=33 7.8s
18/401 | loss=0.8296 ev=0.394 agents=34 avg_r=-0.0265 sum_r=-6.80 x<0=0.36 elig=0.59 dorfler_tail=0.08 floor=0 sel=32 7.7s
19/401 | loss=0.8208 ev=0.414 agents=201 avg_r=-0.1825 sum_r=-46.71 x<0=0.34 elig=0.59 dorfler_tail=0.08 floor=0 sel=34 7.9s
20/401 | loss=0.8558 ev=0.396 agents=120 avg_r=0.8307 sum_r=212.65 x<0=0.30 elig=0.59 dorfler_tail=0.08 floor=0 sel=31 7.7s
21/401 | loss=0.8402 ev=0.410 agents=78 avg_r=-0.2640 sum_r=-67.58 x<0=0.33 elig=0.59 dorfler_tail=0.08 floor=0 sel=31 7.7s
22/401 | loss=0.8100 ev=0.413 agents=44 avg_r=0.1745 sum_r=44.68 x<0=0.33 elig=0.59 dorfler_tail=0.08 floor=0 sel=32 7.7s
23/401 | loss=0.7978 ev=0.416 agents=36 avg_r=-0.3726 sum_r=-95.38 x<0=0.27 elig=0.59 dorfler_tail=0.08 floor=0 sel=32 7.7s
24/401 | loss=0.7886 ev=0.456 agents=175 avg_r=2.2911 sum_r=586.53 x<0=0.23 elig=0.59 dorfler_tail=0.08 floor=0 sel=33 7.9s
25/401 | loss=0.8188 ev=0.402 agents=34 avg_r=0.0163 sum_r=4.18 x<0=0.24 elig=0.59 dorfler_tail=0.07 floor=0 sel=28 7.4s
26/401 | loss=0.8580 ev=0.417 agents=34 avg_r=-0.2140 sum_r=-54.78 x<0=0.23 elig=0.59 dorfler_tail=0.08 floor=0 sel=33 7.9s
27/401 | loss=0.7731 ev=0.413 agents=176 avg_r=-0.0139 sum_r=-3.56 x<0=0.22 elig=0.59 dorfler_tail=0.07 floor=0 sel=31 8.0s
28/401 | loss=0.8363 ev=0.407 agents=219 avg_r=-0.2731 sum_r=-69.90 x<0=0.21 elig=0.59 dorfler_tail=0.08 floor=0 sel=32 8.3s
29/401 | loss=0.8037 ev=0.407 agents=44 avg_r=1.4718 sum_r=376.77 x<0=0.22 elig=0.59 dorfler_tail=0.08 floor=0 sel=32 8.0s
30/401 | loss=0.7398 ev=0.460 agents=133 avg_r=1.9308 sum_r=494.30 x<0=0.21 elig=0.59 dorfler_tail=0.08 floor=0 sel=29 7.6s
31/401 | loss=0.8308 ev=0.421 agents=44 avg_r=1.0891 sum_r=278.82 x<0=0.19 elig=0.59 dorfler_tail=0.08 floor=0 sel=32 7.8s
32/401 | loss=0.8537 ev=0.451 agents=34 avg_r=0.4553 sum_r=116.57 x<0=0.16 elig=0.59 dorfler_tail=0.07 floor=0 sel=33 7.9s
33/401 | loss=0.7271 ev=0.457 agents=193 avg_r=2.1602 sum_r=553.02 x<0=0.11 elig=0.59 dorfler_tail=0.08 floor=0 sel=31 7.7s
34/401 | loss=0.8864 ev=0.395 agents=132 avg_r=0.0379 sum_r=9.71 x<0=0.13 elig=0.60 dorfler_tail=0.07 floor=0 sel=31 7.6s
35/401 | loss=0.7846 ev=0.418 agents=60 avg_r=1.8461 sum_r=472.61 x<0=0.11 elig=0.59 dorfler_tail=0.08 floor=0 sel=30 7.5s
36/401 | loss=0.8040 ev=0.428 agents=139 avg_r=0.1920 sum_r=49.14 x<0=0.08 elig=0.59 dorfler_tail=0.07 floor=0 sel=29 7.5s
37/401 | loss=0.8225 ev=0.432 agents=228 avg_r=0.9105 sum_r=233.08 x<0=0.11 elig=0.59 dorfler_tail=0.07 floor=0 sel=30 7.6s
38/401 | loss=0.7612 ev=0.431 agents=34 avg_r=1.5990 sum_r=409.35 x<0=0.11 elig=0.60 dorfler_tail=0.07 floor=0 sel=31 7.7s
39/401 | loss=0.7474 ev=0.474 agents=60 avg_r=2.1517 sum_r=550.82 x<0=0.10 elig=0.60 dorfler_tail=0.07 floor=0 sel=29 7.4s
40/401 | loss=0.7913 ev=0.417 agents=228 avg_r=2.7027 sum_r=691.89 x<0=0.09 elig=0.59 dorfler_tail=0.08 floor=0 sel=33 7.8s
41/401 | loss=0.7976 ev=0.453 agents=199 avg_r=1.2828 sum_r=328.39 x<0=0.10 elig=0.60 dorfler_tail=0.07 floor=0 sel=28 7.3s
42/401 | loss=0.7862 ev=0.467 agents=40 avg_r=2.1315 sum_r=545.65 x<0=0.07 elig=0.60 dorfler_tail=0.07 floor=0 sel=30 7.5s
43/401 | loss=0.7528 ev=0.447 agents=34 avg_r=1.6585 sum_r=424.58 x<0=0.09 elig=0.60 dorfler_tail=0.07 floor=0 sel=30 7.5s
44/401 | loss=0.8170 ev=0.432 agents=193 avg_r=1.4874 sum_r=380.76 x<0=0.09 elig=0.60 dorfler_tail=0.07 floor=0 sel=31 7.6s
45/401 | loss=0.8174 ev=0.455 agents=230 avg_r=1.1440 sum_r=292.86 x<0=0.08 elig=0.60 dorfler_tail=0.07 floor=0 sel=29 7.3s
46/401 | loss=0.7965 ev=0.445 agents=34 avg_r=2.3036 sum_r=589.72 x<0=0.09 elig=0.60 dorfler_tail=0.07 floor=0 sel=30 7.5s
47/401 | loss=0.7296 ev=0.437 agents=120 avg_r=3.0991 sum_r=793.37 x<0=0.09 elig=0.59 dorfler_tail=0.07 floor=0 sel=30 7.4s
48/401 | loss=0.7574 ev=0.426 agents=34 avg_r=1.4336 sum_r=366.99 x<0=0.06 elig=0.60 dorfler_tail=0.07 floor=0 sel=30 7.4s
49/401 | loss=0.7115 ev=0.452 agents=314 avg_r=4.5889 sum_r=1174.75 x<0=0.09 elig=0.60 dorfler_tail=0.07 floor=0 sel=31 8.1s
50/401 | loss=0.8021 ev=0.447 agents=309 avg_r=1.0066 sum_r=257.70 x<0=0.08 elig=0.60 dorfler_tail=0.07 floor=0 sel=29 7.7s
[Checkpoint] saved → checkpoints/model_iter0050.pt
51/401 | loss=0.7353 ev=0.461 agents=220 avg_r=2.4559 sum_r=628.70 x<0=0.08 elig=0.60 dorfler_tail=0.07 floor=0 sel=29 7.5s
52/401 | loss=0.7844 ev=0.429 agents=75 avg_r=1.7472 sum_r=447.29 x<0=0.08 elig=0.60 dorfler_tail=0.07 floor=0 sel=29 7.5s
53/401 | loss=0.7153 ev=0.484 agents=34 avg_r=4.0922 sum_r=1047.60 x<0=0.08 elig=0.60 dorfler_tail=0.07 floor=0 sel=29 7.4s
54/401 | loss=0.6924 ev=0.475 agents=325 avg_r=2.5784 sum_r=660.07 x<0=0.07 elig=0.60 dorfler_tail=0.07 floor=0 sel=30 7.6s
55/401 | loss=0.7292 ev=0.441 agents=1592 avg_r=2.6958 sum_r=690.12 x<0=0.07 elig=0.60 dorfler_tail=0.07 floor=0 sel=31 7.6s
56/401 | loss=0.7136 ev=0.448 agents=81 avg_r=2.9107 sum_r=745.14 x<0=0.07 elig=0.61 dorfler_tail=0.07 floor=0 sel=27 7.2s
57/401 | loss=0.7957 ev=0.442 agents=221 avg_r=2.5431 sum_r=651.03 x<0=0.08 elig=0.60 dorfler_tail=0.07 floor=0 sel=30 7.5s
58/401 | loss=0.7484 ev=0.477 agents=592 avg_r=3.0523 sum_r=781.38 x<0=0.08 elig=0.60 dorfler_tail=0.07 floor=0 sel=31 7.6s
59/401 | loss=0.8223 ev=0.424 agents=260 avg_r=1.2105 sum_r=309.90 x<0=0.06 elig=0.60 dorfler_tail=0.07 floor=0 sel=29 7.4s
60/401 | loss=0.7966 ev=0.463 agents=34 avg_r=1.3681 sum_r=350.25 x<0=0.05 elig=0.60 dorfler_tail=0.07 floor=0 sel=30 7.5s
61/401 | loss=0.6900 ev=0.478 agents=589 avg_r=3.2758 sum_r=838.62 x<0=0.05 elig=0.60 dorfler_tail=0.07 floor=0 sel=28 7.3s
62/401 | loss=0.7203 ev=0.462 agents=404 avg_r=3.5533 sum_r=909.64 x<0=0.07 elig=0.59 dorfler_tail=0.08 floor=0 sel=31 7.6s
63/401 | loss=0.7498 ev=0.437 agents=88 avg_r=1.3140 sum_r=336.38 x<0=0.08 elig=0.60 dorfler_tail=0.07 floor=0 sel=29 7.3s
64/401 | loss=0.6874 ev=0.460 agents=87 avg_r=3.1493 sum_r=806.22 x<0=0.08 elig=0.60 dorfler_tail=0.07 floor=0 sel=31 7.6s
65/401 | loss=0.7238 ev=0.479 agents=504 avg_r=2.8049 sum_r=718.04 x<0=0.08 elig=0.60 dorfler_tail=0.07 floor=0 sel=29 7.5s
66/401 | loss=0.7026 ev=0.479 agents=612 avg_r=3.3964 sum_r=869.48 x<0=0.08 elig=0.60 dorfler_tail=0.07 floor=0 sel=30 7.4s
67/401 | loss=0.7430 ev=0.449 agents=34 avg_r=2.2715 sum_r=581.51 x<0=0.08 elig=0.60 dorfler_tail=0.07 floor=0 sel=29 7.4s
68/401 | loss=0.6981 ev=0.444 agents=563 avg_r=2.3441 sum_r=600.10 x<0=0.07 elig=0.59 dorfler_tail=0.07 floor=0 sel=30 7.5s
69/401 | loss=0.7046 ev=0.472 agents=82 avg_r=2.8354 sum_r=725.87 x<0=0.08 elig=0.60 dorfler_tail=0.07 floor=0 sel=29 7.4s
70/401 | loss=0.7231 ev=0.466 agents=679 avg_r=2.1406 sum_r=547.99 x<0=0.08 elig=0.60 dorfler_tail=0.07 floor=0 sel=29 7.4s
71/401 | loss=0.6765 ev=0.461 agents=177 avg_r=2.7769 sum_r=710.88 x<0=0.07 elig=0.60 dorfler_tail=0.07 floor=0 sel=28 7.4s
72/401 | loss=0.7200 ev=0.467 agents=417 avg_r=2.5203 sum_r=645.20 x<0=0.07 elig=0.60 dorfler_tail=0.07 floor=0 sel=29 7.7s
73/401 | loss=0.7056 ev=0.470 agents=406 avg_r=2.4355 sum_r=623.49 x<0=0.06 elig=0.60 dorfler_tail=0.07 floor=0 sel=29 7.4s
74/401 | loss=0.7596 ev=0.469 agents=39 avg_r=3.4787 sum_r=890.55 x<0=0.07 elig=0.60 dorfler_tail=0.07 floor=0 sel=29 7.4s
75/401 | loss=0.8122 ev=0.437 agents=76 avg_r=0.1922 sum_r=49.19 x<0=0.06 elig=0.60 dorfler_tail=0.07 floor=0 sel=29 7.5s
76/401 | loss=0.7356 ev=0.480 agents=743 avg_r=3.3444 sum_r=856.16 x<0=0.06 elig=0.60 dorfler_tail=0.07 floor=0 sel=29 7.4s
77/401 | loss=0.6961 ev=0.463 agents=868 avg_r=3.1062 sum_r=795.20 x<0=0.05 elig=0.60 dorfler_tail=0.07 floor=0 sel=29 7.4s
78/401 | loss=0.6751 ev=0.472 agents=239 avg_r=2.1832 sum_r=558.90 x<0=0.07 elig=0.60 dorfler_tail=0.07 floor=0 sel=29 7.3s
79/401 | loss=0.7819 ev=0.463 agents=92 avg_r=3.4287 sum_r=877.75 x<0=0.07 elig=0.60 dorfler_tail=0.07 floor=0 sel=31 7.5s
80/401 | loss=0.7031 ev=0.443 agents=100 avg_r=3.0162 sum_r=772.14 x<0=0.09 elig=0.60 dorfler_tail=0.07 floor=0 sel=29 7.3s
81/401 | loss=0.7328 ev=0.468 agents=216 avg_r=1.5925 sum_r=407.67 x<0=0.08 elig=0.60 dorfler_tail=0.07 floor=0 sel=29 7.3s
82/401 | loss=0.6882 ev=0.478 agents=500 avg_r=4.0837 sum_r=1045.44 x<0=0.09 elig=0.60 dorfler_tail=0.07 floor=0 sel=30 7.5s
83/401 | loss=0.7674 ev=0.439 agents=209 avg_r=2.4277 sum_r=621.49 x<0=0.10 elig=0.60 dorfler_tail=0.07 floor=0 sel=27 7.1s
84/401 | loss=0.6714 ev=0.467 agents=226 avg_r=3.4643 sum_r=886.86 x<0=0.09 elig=0.60 dorfler_tail=0.07 floor=0 sel=28 7.3s
85/401 | loss=0.6888 ev=0.457 agents=661 avg_r=3.5194 sum_r=900.96 x<0=0.09 elig=0.60 dorfler_tail=0.07 floor=0 sel=29 7.3s
86/401 | loss=0.7823 ev=0.465 agents=78 avg_r=3.6703 sum_r=939.61 x<0=0.10 elig=0.61 dorfler_tail=0.07 floor=0 sel=29 7.5s
87/401 | loss=0.7369 ev=0.441 agents=426 avg_r=3.0157 sum_r=772.03 x<0=0.08 elig=0.60 dorfler_tail=0.07 floor=0 sel=29 7.3s
88/401 | loss=0.7635 ev=0.440 agents=445 avg_r=2.9807 sum_r=763.05 x<0=0.07 elig=0.61 dorfler_tail=0.07 floor=0 sel=28 7.3s
89/401 | loss=0.6536 ev=0.493 agents=42 avg_r=4.4092 sum_r=1128.74 x<0=0.09 elig=0.61 dorfler_tail=0.07 floor=0 sel=28 7.3s
90/401 | loss=0.7260 ev=0.459 agents=174 avg_r=2.2528 sum_r=576.72 x<0=0.08 elig=0.61 dorfler_tail=0.07 floor=0 sel=29 7.3s
91/401 | loss=0.8182 ev=0.451 agents=189 avg_r=2.7882 sum_r=713.78 x<0=0.07 elig=0.61 dorfler_tail=0.07 floor=0 sel=27 7.2s
92/401 | loss=0.7171 ev=0.475 agents=930 avg_r=2.9107 sum_r=745.14 x<0=0.08 elig=0.61 dorfler_tail=0.07 floor=0 sel=27 7.3s
93/401 | loss=0.7178 ev=0.462 agents=950 avg_r=2.5842 sum_r=661.56 x<0=0.09 elig=0.61 dorfler_tail=0.07 floor=0 sel=28 7.2s
94/401 | loss=0.6635 ev=0.480 agents=278 avg_r=4.6649 sum_r=1194.22 x<0=0.08 elig=0.61 dorfler_tail=0.07 floor=0 sel=30 8.0s
95/401 | loss=0.8666 ev=0.417 agents=516 avg_r=2.5170 sum_r=644.35 x<0=0.09 elig=0.61 dorfler_tail=0.07 floor=0 sel=29 7.5s
96/401 | loss=0.6856 ev=0.473 agents=225 avg_r=3.6171 sum_r=925.98 x<0=0.09 elig=0.60 dorfler_tail=0.07 floor=0 sel=28 7.5s
97/401 | loss=0.7293 ev=0.466 agents=139 avg_r=3.4967 sum_r=895.16 x<0=0.09 elig=0.61 dorfler_tail=0.07 floor=0 sel=29 7.6s
98/401 | loss=0.6989 ev=0.477 agents=386 avg_r=3.2573 sum_r=833.87 x<0=0.08 elig=0.61 dorfler_tail=0.07 floor=0 sel=27 7.3s
99/401 | loss=0.7278 ev=0.456 agents=607 avg_r=3.5721 sum_r=914.45 x<0=0.06 elig=0.60 dorfler_tail=0.07 floor=0 sel=29 7.6s
100/401 | loss=0.6917 ev=0.488 agents=395 avg_r=2.5313 sum_r=648.00 x<0=0.06 elig=0.60 dorfler_tail=0.07 floor=0 sel=28 7.4s
[Checkpoint] saved → checkpoints/model_iter0100.pt
101/401 | loss=0.6450 ev=0.482 agents=118 avg_r=3.6129 sum_r=924.89 x<0=0.06 elig=0.60 dorfler_tail=0.07 floor=0 sel=29 7.4s
102/401 | loss=0.6719 ev=0.502 agents=82 avg_r=3.9205 sum_r=1003.65 x<0=0.07 elig=0.60 dorfler_tail=0.07 floor=0 sel=28 7.2s
103/401 | loss=0.8262 ev=0.444 agents=34 avg_r=0.9714 sum_r=248.68 x<0=0.07 elig=0.61 dorfler_tail=0.06 floor=0 sel=28 7.3s
104/401 | loss=0.6693 ev=0.473 agents=205 avg_r=4.0583 sum_r=1038.93 x<0=0.09 elig=0.60 dorfler_tail=0.07 floor=0 sel=30 7.4s
105/401 | loss=0.7109 ev=0.493 agents=278 avg_r=3.3932 sum_r=868.66 x<0=0.07 elig=0.61 dorfler_tail=0.07 floor=0 sel=30 7.5s
106/401 | loss=0.7028 ev=0.490 agents=80 avg_r=3.2735 sum_r=838.02 x<0=0.08 elig=0.61 dorfler_tail=0.07 floor=0 sel=26 7.0s
107/401 | loss=0.6651 ev=0.484 agents=72 avg_r=2.5184 sum_r=644.70 x<0=0.07 elig=0.60 dorfler_tail=0.07 floor=0 sel=29 7.3s
108/401 | loss=0.6931 ev=0.461 agents=157 avg_r=1.9714 sum_r=504.68 x<0=0.07 elig=0.60 dorfler_tail=0.07 floor=0 sel=31 7.4s
109/401 | loss=0.6012 ev=0.517 agents=169 avg_r=3.9352 sum_r=1007.42 x<0=0.07 elig=0.60 dorfler_tail=0.07 floor=0 sel=29 7.3s
110/401 | loss=0.7184 ev=0.484 agents=34 avg_r=2.9819 sum_r=763.37 x<0=0.06 elig=0.61 dorfler_tail=0.07 floor=0 sel=27 7.3s
111/401 | loss=0.6751 ev=0.493 agents=403 avg_r=3.0738 sum_r=786.90 x<0=0.06 elig=0.60 dorfler_tail=0.07 floor=0 sel=30 7.4s
112/401 | loss=0.6429 ev=0.488 agents=161 avg_r=2.6077 sum_r=667.57 x<0=0.06 elig=0.60 dorfler_tail=0.07 floor=0 sel=28 7.2s
113/401 | loss=0.6752 ev=0.502 agents=55 avg_r=3.7771 sum_r=966.93 x<0=0.06 elig=0.60 dorfler_tail=0.07 floor=0 sel=28 7.3s
114/401 | loss=0.7463 ev=0.451 agents=278 avg_r=2.8845 sum_r=738.44 x<0=0.06 elig=0.61 dorfler_tail=0.07 floor=0 sel=30 7.4s
115/401 | loss=0.7711 ev=0.449 agents=1458 avg_r=1.9170 sum_r=490.75 x<0=0.05 elig=0.61 dorfler_tail=0.07 floor=0 sel=27 7.1s
116/401 | loss=0.6691 ev=0.478 agents=322 avg_r=2.8004 sum_r=716.90 x<0=0.05 elig=0.61 dorfler_tail=0.07 floor=0 sel=28 7.2s
117/401 | loss=0.7584 ev=0.482 agents=157 avg_r=1.9519 sum_r=499.68 x<0=0.05 elig=0.61 dorfler_tail=0.07 floor=0 sel=30 7.4s
118/401 | loss=0.6645 ev=0.505 agents=34 avg_r=4.1436 sum_r=1060.76 x<0=0.05 elig=0.61 dorfler_tail=0.07 floor=0 sel=29 7.9s
119/401 | loss=0.7026 ev=0.482 agents=525 avg_r=2.6891 sum_r=688.42 x<0=0.05 elig=0.61 dorfler_tail=0.07 floor=0 sel=28 7.5s
120/401 | loss=0.6424 ev=0.476 agents=449 avg_r=3.1357 sum_r=802.74 x<0=0.04 elig=0.60 dorfler_tail=0.07 floor=0 sel=29 7.4s
121/401 | loss=0.6441 ev=0.485 agents=751 avg_r=3.1465 sum_r=805.51 x<0=0.04 elig=0.61 dorfler_tail=0.07 floor=0 sel=28 7.5s
122/401 | loss=0.7017 ev=0.468 agents=97 avg_r=2.4756 sum_r=633.75 x<0=0.05 elig=0.61 dorfler_tail=0.07 floor=0 sel=27 7.4s
123/401 | loss=0.8205 ev=0.460 agents=88 avg_r=3.0468 sum_r=779.99 x<0=0.06 elig=0.61 dorfler_tail=0.07 floor=0 sel=29 7.6s
124/401 | loss=0.7868 ev=0.486 agents=34 avg_r=3.0342 sum_r=776.75 x<0=0.05 elig=0.61 dorfler_tail=0.07 floor=0 sel=28 7.4s
125/401 | loss=0.7189 ev=0.456 agents=631 avg_r=3.7444 sum_r=958.57 x<0=0.06 elig=0.60 dorfler_tail=0.07 floor=0 sel=29 7.4s
126/401 | loss=0.7631 ev=0.462 agents=205 avg_r=3.6346 sum_r=930.47 x<0=0.05 elig=0.61 dorfler_tail=0.07 floor=0 sel=26 7.3s
127/401 | loss=0.8456 ev=0.490 agents=276 avg_r=3.9878 sum_r=1020.87 x<0=0.05 elig=0.62 dorfler_tail=0.07 floor=0 sel=31 7.9s
128/401 | loss=0.7728 ev=0.453 agents=216 avg_r=3.3635 sum_r=861.06 x<0=0.05 elig=0.61 dorfler_tail=0.07 floor=0 sel=27 7.3s
129/401 | loss=0.6854 ev=0.497 agents=171 avg_r=3.1932 sum_r=817.45 x<0=0.05 elig=0.60 dorfler_tail=0.07 floor=0 sel=29 7.4s
130/401 | loss=0.6694 ev=0.502 agents=773 avg_r=3.1194 sum_r=798.57 x<0=0.05 elig=0.61 dorfler_tail=0.07 floor=0 sel=29 7.4s
131/401 | loss=0.8146 ev=0.475 agents=417 avg_r=4.4338 sum_r=1135.05 x<0=0.05 elig=0.61 dorfler_tail=0.07 floor=0 sel=29 7.6s
132/401 | loss=0.6740 ev=0.434 agents=199 avg_r=1.0849 sum_r=277.74 x<0=0.04 elig=0.61 dorfler_tail=0.07 floor=0 sel=25 6.9s
133/401 | loss=0.6344 ev=0.538 agents=199 avg_r=4.8060 sum_r=1230.34 x<0=0.05 elig=0.60 dorfler_tail=0.07 floor=0 sel=30 7.5s
134/401 | loss=0.7608 ev=0.484 agents=109 avg_r=2.4116 sum_r=617.37 x<0=0.04 elig=0.61 dorfler_tail=0.07 floor=0 sel=29 7.4s
135/401 | loss=0.6871 ev=0.497 agents=81 avg_r=2.6706 sum_r=683.68 x<0=0.04 elig=0.61 dorfler_tail=0.07 floor=0 sel=29 7.5s
136/401 | loss=0.6854 ev=0.500 agents=349 avg_r=3.1550 sum_r=807.67 x<0=0.04 elig=0.60 dorfler_tail=0.07 floor=0 sel=28 7.3s
137/401 | loss=0.6222 ev=0.475 agents=309 avg_r=2.9599 sum_r=757.74 x<0=0.04 elig=0.60 dorfler_tail=0.07 floor=0 sel=27 7.2s
138/401 | loss=0.7838 ev=0.473 agents=34 avg_r=3.0775 sum_r=787.84 x<0=0.03 elig=0.61 dorfler_tail=0.07 floor=0 sel=28 7.3s
139/401 | loss=0.6776 ev=0.469 agents=137 avg_r=4.6078 sum_r=1179.59 x<0=0.04 elig=0.60 dorfler_tail=0.07 floor=0 sel=31 7.6s
140/401 | loss=0.7131 ev=0.482 agents=34 avg_r=2.7598 sum_r=706.51 x<0=0.03 elig=0.60 dorfler_tail=0.07 floor=0 sel=29 7.6s
141/401 | loss=0.6298 ev=0.510 agents=716 avg_r=2.6834 sum_r=686.95 x<0=0.03 elig=0.60 dorfler_tail=0.07 floor=0 sel=29 7.7s
142/401 | loss=0.6687 ev=0.482 agents=118 avg_r=2.9901 sum_r=765.46 x<0=0.03 elig=0.60 dorfler_tail=0.07 floor=0 sel=29 7.5s
143/401 | loss=0.6278 ev=0.538 agents=684 avg_r=4.2436 sum_r=1086.37 x<0=0.03 elig=0.60 dorfler_tail=0.07 floor=0 sel=31 7.7s
144/401 | loss=0.6646 ev=0.496 agents=1317 avg_r=1.9731 sum_r=505.11 x<0=0.03 elig=0.61 dorfler_tail=0.07 floor=0 sel=26 7.2s
145/401 | loss=0.7301 ev=0.477 agents=324 avg_r=2.6170 sum_r=669.96 x<0=0.03 elig=0.60 dorfler_tail=0.07 floor=0 sel=29 7.5s
146/401 | loss=0.7054 ev=0.474 agents=318 avg_r=3.0373 sum_r=777.55 x<0=0.02 elig=0.60 dorfler_tail=0.07 floor=0 sel=32 7.6s
147/401 | loss=0.6366 ev=0.503 agents=260 avg_r=1.7196 sum_r=440.21 x<0=0.02 elig=0.60 dorfler_tail=0.07 floor=0 sel=26 7.1s
148/401 | loss=0.6500 ev=0.527 agents=64 avg_r=3.5001 sum_r=896.04 x<0=0.02 elig=0.60 dorfler_tail=0.07 floor=0 sel=31 7.5s
149/401 | loss=0.7272 ev=0.504 agents=406 avg_r=1.2588 sum_r=322.26 x<0=0.02 elig=0.60 dorfler_tail=0.07 floor=0 sel=29 7.2s
150/401 | loss=0.5931 ev=0.548 agents=494 avg_r=3.0807 sum_r=788.65 x<0=0.02 elig=0.60 dorfler_tail=0.07 floor=0 sel=28 7.2s
[Checkpoint] saved → checkpoints/model_iter0150.pt
151/401 | loss=0.7106 ev=0.473 agents=276 avg_r=2.7628 sum_r=707.27 x<0=0.02 elig=0.60 dorfler_tail=0.08 floor=0 sel=31 7.5s
152/401 | loss=0.7196 ev=0.509 agents=917 avg_r=0.6032 sum_r=154.42 x<0=0.02 elig=0.60 dorfler_tail=0.07 floor=0 sel=28 7.2s
153/401 | loss=0.6383 ev=0.494 agents=252 avg_r=4.4047 sum_r=1127.62 x<0=0.02 elig=0.60 dorfler_tail=0.07 floor=0 sel=30 7.4s
154/401 | loss=0.6348 ev=0.535 agents=310 avg_r=3.2224 sum_r=824.94 x<0=0.02 elig=0.60 dorfler_tail=0.07 floor=0 sel=30 7.4s
155/401 | loss=0.7558 ev=0.478 agents=550 avg_r=2.0697 sum_r=529.83 x<0=0.01 elig=0.60 dorfler_tail=0.07 floor=0 sel=29 7.3s
156/401 | loss=0.7824 ev=0.471 agents=759 avg_r=2.2078 sum_r=565.21 x<0=0.03 elig=0.61 dorfler_tail=0.07 floor=0 sel=27 7.2s
157/401 | loss=0.6814 ev=0.487 agents=66 avg_r=2.7153 sum_r=695.12 x<0=0.02 elig=0.60 dorfler_tail=0.07 floor=0 sel=30 7.4s
158/401 | loss=0.6918 ev=0.475 agents=157 avg_r=4.0377 sum_r=1033.66 x<0=0.01 elig=0.60 dorfler_tail=0.07 floor=0 sel=28 7.3s
159/401 | loss=0.6960 ev=0.497 agents=210 avg_r=4.4194 sum_r=1131.36 x<0=0.02 elig=0.61 dorfler_tail=0.07 floor=0 sel=28 7.4s
160/401 | loss=0.8230 ev=0.463 agents=72 avg_r=3.2715 sum_r=837.50 x<0=0.01 elig=0.61 dorfler_tail=0.07 floor=0 sel=29 7.6s
161/401 | loss=0.8833 ev=0.462 agents=101 avg_r=3.1055 sum_r=795.01 x<0=0.01 elig=0.61 dorfler_tail=0.07 floor=0 sel=28 7.5s
162/401 | loss=0.7523 ev=0.439 agents=1039 avg_r=2.8131 sum_r=720.15 x<0=0.01 elig=0.60 dorfler_tail=0.07 floor=0 sel=28 7.3s
163/401 | loss=0.7434 ev=0.484 agents=857 avg_r=5.0866 sum_r=1302.18 x<0=0.01 elig=0.61 dorfler_tail=0.07 floor=0 sel=29 8.0s
164/401 | loss=0.9129 ev=0.448 agents=208 avg_r=3.0212 sum_r=773.42 x<0=0.02 elig=0.62 dorfler_tail=0.06 floor=0 sel=27 7.7s
165/401 | loss=0.8110 ev=0.503 agents=72 avg_r=5.2848 sum_r=1352.92 x<0=0.02 elig=0.62 dorfler_tail=0.08 floor=0 sel=30 8.1s
166/401 | loss=0.9153 ev=0.417 agents=443 avg_r=2.6762 sum_r=685.11 x<0=0.02 elig=0.62 dorfler_tail=0.07 floor=0 sel=26 7.5s
167/401 | loss=0.8216 ev=0.435 agents=72 avg_r=4.6195 sum_r=1182.58 x<0=0.02 elig=0.63 dorfler_tail=0.07 floor=0 sel=28 7.8s
168/401 | loss=0.8799 ev=0.468 agents=218 avg_r=5.6227 sum_r=1439.40 x<0=0.02 elig=0.62 dorfler_tail=0.07 floor=0 sel=27 7.8s
169/401 | loss=0.9677 ev=0.464 agents=64 avg_r=3.2444 sum_r=830.56 x<0=0.02 elig=0.62 dorfler_tail=0.07 floor=0 sel=28 7.5s
170/401 | loss=0.8684 ev=0.450 agents=1183 avg_r=4.2454 sum_r=1086.82 x<0=0.02 elig=0.62 dorfler_tail=0.07 floor=0 sel=27 7.5s
171/401 | loss=0.9914 ev=0.457 agents=248 avg_r=5.2504 sum_r=1344.10 x<0=0.02 elig=0.62 dorfler_tail=0.07 floor=0 sel=28 7.7s
172/401 | loss=0.9352 ev=0.455 agents=66 avg_r=4.8499 sum_r=1241.57 x<0=0.02 elig=0.62 dorfler_tail=0.07 floor=0 sel=30 7.8s
173/401 | loss=0.8915 ev=0.475 agents=195 avg_r=4.3840 sum_r=1122.30 x<0=0.02 elig=0.63 dorfler_tail=0.07 floor=0 sel=27 7.6s
174/401 | loss=0.9410 ev=0.477 agents=366 avg_r=5.2875 sum_r=1353.60 x<0=0.02 elig=0.62 dorfler_tail=0.07 floor=0 sel=27 7.5s
175/401 | loss=0.9022 ev=0.454 agents=78 avg_r=4.4750 sum_r=1145.59 x<0=0.01 elig=0.62 dorfler_tail=0.07 floor=0 sel=31 8.0s
176/401 | loss=0.9084 ev=0.455 agents=282 avg_r=3.4913 sum_r=893.77 x<0=0.01 elig=0.62 dorfler_tail=0.07 floor=0 sel=26 7.3s
177/401 | loss=0.8292 ev=0.478 agents=252 avg_r=3.6340 sum_r=930.31 x<0=0.01 elig=0.62 dorfler_tail=0.07 floor=0 sel=28 7.5s
178/401 | loss=0.9954 ev=0.469 agents=193 avg_r=5.3305 sum_r=1364.61 x<0=0.01 elig=0.62 dorfler_tail=0.07 floor=0 sel=27 7.5s
179/401 | loss=1.0011 ev=0.426 agents=1246 avg_r=4.4377 sum_r=1136.05 x<0=0.01 elig=0.62 dorfler_tail=0.07 floor=0 sel=29 7.7s
180/401 | loss=0.9708 ev=0.457 agents=772 avg_r=5.4786 sum_r=1402.53 x<0=0.01 elig=0.62 dorfler_tail=0.07 floor=0 sel=29 7.8s
181/401 | loss=0.9704 ev=0.452 agents=132 avg_r=4.8561 sum_r=1243.16 x<0=0.01 elig=0.63 dorfler_tail=0.07 floor=0 sel=27 7.6s
182/401 | loss=1.0905 ev=0.437 agents=119 avg_r=4.0510 sum_r=1037.06 x<0=0.01 elig=0.62 dorfler_tail=0.07 floor=0 sel=27 7.4s
183/401 | loss=1.0880 ev=0.459 agents=762 avg_r=4.7612 sum_r=1218.87 x<0=0.01 elig=0.63 dorfler_tail=0.07 floor=0 sel=29 7.8s
184/401 | loss=1.0019 ev=0.454 agents=212 avg_r=3.7824 sum_r=968.29 x<0=0.01 elig=0.63 dorfler_tail=0.07 floor=0 sel=28 7.6s
185/401 | loss=0.9900 ev=0.466 agents=120 avg_r=5.3904 sum_r=1379.95 x<0=0.01 elig=0.63 dorfler_tail=0.07 floor=0 sel=28 7.6s
186/401 | loss=1.0037 ev=0.463 agents=70 avg_r=4.2867 sum_r=1097.39 x<0=0.01 elig=0.62 dorfler_tail=0.07 floor=0 sel=28 7.6s
187/401 | loss=1.2264 ev=0.454 agents=694 avg_r=6.6090 sum_r=1691.90 x<0=0.01 elig=0.63 dorfler_tail=0.07 floor=0 sel=29 8.3s
188/401 | loss=1.0584 ev=0.455 agents=761 avg_r=4.4357 sum_r=1135.54 x<0=0.01 elig=0.63 dorfler_tail=0.07 floor=0 sel=27 7.7s
189/401 | loss=1.0834 ev=0.435 agents=101 avg_r=3.8870 sum_r=995.07 x<0=0.01 elig=0.63 dorfler_tail=0.07 floor=0 sel=27 7.7s
190/401 | loss=0.9906 ev=0.480 agents=82 avg_r=5.7419 sum_r=1469.92 x<0=0.01 elig=0.63 dorfler_tail=0.07 floor=0 sel=29 7.9s
191/401 | loss=1.0026 ev=0.489 agents=112 avg_r=4.7027 sum_r=1203.90 x<0=0.01 elig=0.63 dorfler_tail=0.07 floor=0 sel=28 7.7s
192/401 | loss=0.9754 ev=0.470 agents=212 avg_r=3.5024 sum_r=896.62 x<0=0.00 elig=0.62 dorfler_tail=0.07 floor=0 sel=27 7.5s
193/401 | loss=0.9544 ev=0.504 agents=206 avg_r=6.2049 sum_r=1588.45 x<0=0.00 elig=0.62 dorfler_tail=0.07 floor=0 sel=30 8.0s
194/401 | loss=1.0699 ev=0.470 agents=92 avg_r=3.5192 sum_r=900.92 x<0=0.00 elig=0.63 dorfler_tail=0.07 floor=0 sel=27 7.5s
195/401 | loss=1.0682 ev=0.455 agents=1062 avg_r=4.7573 sum_r=1217.87 x<0=0.00 elig=0.62 dorfler_tail=0.07 floor=0 sel=28 7.7s
196/401 | loss=1.0261 ev=0.476 agents=73 avg_r=3.4637 sum_r=886.70 x<0=0.00 elig=0.63 dorfler_tail=0.07 floor=0 sel=26 7.4s
197/401 | loss=1.1041 ev=0.477 agents=82 avg_r=5.4997 sum_r=1407.91 x<0=0.00 elig=0.63 dorfler_tail=0.07 floor=0 sel=28 7.6s
198/401 | loss=1.0685 ev=0.475 agents=137 avg_r=4.8297 sum_r=1236.40 x<0=0.01 elig=0.63 dorfler_tail=0.08 floor=0 sel=29 7.8s
199/401 | loss=1.0788 ev=0.478 agents=617 avg_r=5.8426 sum_r=1495.71 x<0=0.00 elig=0.63 dorfler_tail=0.07 floor=0 sel=28 7.8s
200/401 | loss=1.0358 ev=0.482 agents=346 avg_r=5.6052 sum_r=1434.92 x<0=0.00 elig=0.63 dorfler_tail=0.07 floor=0 sel=29 7.8s
[Checkpoint] saved → checkpoints/model_iter0200.pt
201/401 | loss=0.8902 ev=0.500 agents=366 avg_r=4.7006 sum_r=1203.36 x<0=0.01 elig=0.62 dorfler_tail=0.07 floor=0 sel=26 7.3s
202/401 | loss=1.2783 ev=0.462 agents=438 avg_r=6.6009 sum_r=1689.82 x<0=0.01 elig=0.63 dorfler_tail=0.07 floor=0 sel=29 7.8s
203/401 | loss=0.9705 ev=0.479 agents=66 avg_r=4.4767 sum_r=1146.04 x<0=0.00 elig=0.62 dorfler_tail=0.07 floor=0 sel=27 7.6s
204/401 | loss=1.0327 ev=0.470 agents=174 avg_r=4.7346 sum_r=1212.06 x<0=0.00 elig=0.63 dorfler_tail=0.07 floor=0 sel=27 7.4s
205/401 | loss=1.0545 ev=0.486 agents=454 avg_r=5.4121 sum_r=1385.49 x<0=0.00 elig=0.62 dorfler_tail=0.07 floor=0 sel=29 7.7s
206/401 | loss=0.9817 ev=0.477 agents=482 avg_r=5.1323 sum_r=1313.87 x<0=0.00 elig=0.62 dorfler_tail=0.07 floor=0 sel=26 7.4s
207/401 | loss=0.9354 ev=0.464 agents=526 avg_r=2.5360 sum_r=649.22 x<0=0.00 elig=0.62 dorfler_tail=0.07 floor=0 sel=25 7.3s
208/401 | loss=1.0478 ev=0.484 agents=64 avg_r=6.3611 sum_r=1628.44 x<0=0.00 elig=0.63 dorfler_tail=0.07 floor=0 sel=30 8.2s
209/401 | loss=1.0140 ev=0.494 agents=77 avg_r=6.1189 sum_r=1566.43 x<0=0.00 elig=0.62 dorfler_tail=0.07 floor=0 sel=30 8.3s
210/401 | loss=1.0858 ev=0.489 agents=34 avg_r=4.5550 sum_r=1166.07 x<0=0.00 elig=0.63 dorfler_tail=0.07 floor=0 sel=25 7.5s
211/401 | loss=1.0737 ev=0.478 agents=473 avg_r=6.0945 sum_r=1560.20 x<0=0.00 elig=0.63 dorfler_tail=0.07 floor=0 sel=32 8.4s
212/401 | loss=1.1049 ev=0.498 agents=370 avg_r=3.9285 sum_r=1005.70 x<0=0.00 elig=0.62 dorfler_tail=0.07 floor=0 sel=25 7.3s
213/401 | loss=1.0843 ev=0.467 agents=199 avg_r=5.7006 sum_r=1459.35 x<0=0.00 elig=0.63 dorfler_tail=0.07 floor=0 sel=29 7.9s
214/401 | loss=0.9703 ev=0.500 agents=1681 avg_r=6.1949 sum_r=1585.90 x<0=0.00 elig=0.63 dorfler_tail=0.07 floor=0 sel=28 7.7s
215/401 | loss=1.1585 ev=0.454 agents=95 avg_r=4.3943 sum_r=1124.94 x<0=0.00 elig=0.63 dorfler_tail=0.07 floor=0 sel=28 7.7s
216/401 | loss=1.0844 ev=0.490 agents=132 avg_r=3.6609 sum_r=937.19 x<0=0.00 elig=0.63 dorfler_tail=0.07 floor=0 sel=26 7.4s
217/401 | loss=1.0243 ev=0.480 agents=650 avg_r=5.7942 sum_r=1483.30 x<0=0.00 elig=0.62 dorfler_tail=0.07 floor=0 sel=30 7.9s
218/401 | loss=0.9701 ev=0.494 agents=222 avg_r=4.2069 sum_r=1076.96 x<0=0.00 elig=0.62 dorfler_tail=0.07 floor=0 sel=26 7.4s
219/401 | loss=1.1205 ev=0.474 agents=340 avg_r=4.9871 sum_r=1276.71 x<0=0.00 elig=0.63 dorfler_tail=0.07 floor=0 sel=29 7.8s
220/401 | loss=1.0831 ev=0.505 agents=199 avg_r=4.2395 sum_r=1085.30 x<0=0.00 elig=0.62 dorfler_tail=0.07 floor=0 sel=27 7.5s
221/401 | loss=1.0350 ev=0.478 agents=205 avg_r=7.2874 sum_r=1865.56 x<0=0.00 elig=0.63 dorfler_tail=0.08 floor=0 sel=30 7.9s
222/401 | loss=1.1288 ev=0.485 agents=884 avg_r=3.2765 sum_r=838.78 x<0=0.00 elig=0.62 dorfler_tail=0.07 floor=0 sel=26 7.4s
223/401 | loss=1.0799 ev=0.494 agents=440 avg_r=5.8995 sum_r=1510.28 x<0=0.00 elig=0.63 dorfler_tail=0.07 floor=0 sel=29 7.7s
224/401 | loss=0.9680 ev=0.448 agents=41 avg_r=1.7854 sum_r=457.07 x<0=0.00 elig=0.63 dorfler_tail=0.07 floor=0 sel=25 7.3s
225/401 | loss=1.0479 ev=0.507 agents=377 avg_r=8.4851 sum_r=2172.19 x<0=0.00 elig=0.63 dorfler_tail=0.08 floor=0 sel=33 8.2s
226/401 | loss=1.0476 ev=0.484 agents=60 avg_r=4.7891 sum_r=1226.01 x<0=0.00 elig=0.63 dorfler_tail=0.07 floor=0 sel=26 7.4s
227/401 | loss=1.1226 ev=0.506 agents=87 avg_r=6.0974 sum_r=1560.94 x<0=0.00 elig=0.64 dorfler_tail=0.07 floor=0 sel=28 7.6s
228/401 | loss=1.0392 ev=0.481 agents=113 avg_r=5.0643 sum_r=1296.45 x<0=0.00 elig=0.63 dorfler_tail=0.07 floor=0 sel=27 7.6s
229/401 | loss=1.1729 ev=0.515 agents=220 avg_r=6.9283 sum_r=1773.65 x<0=0.00 elig=0.63 dorfler_tail=0.08 floor=0 sel=30 7.9s
230/401 | loss=1.1397 ev=0.481 agents=153 avg_r=4.7461 sum_r=1215.01 x<0=0.00 elig=0.64 dorfler_tail=0.07 floor=0 sel=28 7.7s
231/401 | loss=1.1618 ev=0.486 agents=983 avg_r=4.4464 sum_r=1138.29 x<0=0.00 elig=0.64 dorfler_tail=0.07 floor=0 sel=27 7.6s
232/401 | loss=1.0145 ev=0.533 agents=908 avg_r=6.6488 sum_r=1702.09 x<0=0.00 elig=0.63 dorfler_tail=0.07 floor=0 sel=29 8.3s
233/401 | loss=0.9984 ev=0.466 agents=60 avg_r=3.0361 sum_r=777.24 x<0=0.00 elig=0.63 dorfler_tail=0.07 floor=0 sel=26 7.7s
234/401 | loss=1.1600 ev=0.477 agents=34 avg_r=5.4348 sum_r=1391.32 x<0=0.00 elig=0.63 dorfler_tail=0.08 floor=0 sel=28 7.9s
235/401 | loss=1.0123 ev=0.500 agents=1033 avg_r=5.7679 sum_r=1476.59 x<0=0.00 elig=0.62 dorfler_tail=0.07 floor=0 sel=28 7.9s
236/401 | loss=0.9871 ev=0.493 agents=267 avg_r=5.4802 sum_r=1402.94 x<0=0.00 elig=0.63 dorfler_tail=0.07 floor=0 sel=28 7.7s
237/401 | loss=1.0411 ev=0.493 agents=823 avg_r=4.2589 sum_r=1090.27 x<0=0.00 elig=0.64 dorfler_tail=0.07 floor=0 sel=27 7.6s
238/401 | loss=0.9391 ev=0.471 agents=258 avg_r=4.8508 sum_r=1241.81 x<0=0.00 elig=0.63 dorfler_tail=0.07 floor=0 sel=28 7.7s
239/401 | loss=0.9220 ev=0.526 agents=80 avg_r=5.5145 sum_r=1411.71 x<0=0.00 elig=0.62 dorfler_tail=0.07 floor=0 sel=27 7.6s
240/401 | loss=1.0007 ev=0.516 agents=414 avg_r=4.9083 sum_r=1256.51 x<0=0.00 elig=0.62 dorfler_tail=0.07 floor=0 sel=29 7.7s
241/401 | loss=1.0398 ev=0.481 agents=387 avg_r=3.9976 sum_r=1023.38 x<0=0.00 elig=0.62 dorfler_tail=0.07 floor=0 sel=28 7.6s
242/401 | loss=0.9385 ev=0.508 agents=78 avg_r=4.1453 sum_r=1061.20 x<0=0.00 elig=0.62 dorfler_tail=0.07 floor=0 sel=26 7.3s
243/401 | loss=0.9188 ev=0.506 agents=166 avg_r=4.2940 sum_r=1099.26 x<0=0.00 elig=0.62 dorfler_tail=0.07 floor=0 sel=28 7.6s
244/401 | loss=0.8709 ev=0.493 agents=229 avg_r=3.3207 sum_r=850.10 x<0=0.00 elig=0.62 dorfler_tail=0.07 floor=0 sel=27 7.5s
245/401 | loss=0.8569 ev=0.526 agents=276 avg_r=4.4382 sum_r=1136.18 x<0=0.00 elig=0.62 dorfler_tail=0.07 floor=0 sel=28 7.6s
246/401 | loss=0.7959 ev=0.494 agents=383 avg_r=2.7136 sum_r=694.68 x<0=0.00 elig=0.61 dorfler_tail=0.07 floor=0 sel=27 7.4s
247/401 | loss=0.8470 ev=0.525 agents=197 avg_r=6.1670 sum_r=1578.75 x<0=0.00 elig=0.61 dorfler_tail=0.08 floor=0 sel=28 7.7s
248/401 | loss=0.7863 ev=0.449 agents=800 avg_r=2.1261 sum_r=544.28 x<0=0.00 elig=0.61 dorfler_tail=0.07 floor=0 sel=27 7.2s
249/401 | loss=0.8609 ev=0.504 agents=423 avg_r=3.3115 sum_r=847.74 x<0=0.00 elig=0.61 dorfler_tail=0.08 floor=0 sel=27 7.4s
250/401 | loss=0.8243 ev=0.524 agents=94 avg_r=4.7484 sum_r=1215.58 x<0=0.01 elig=0.61 dorfler_tail=0.08 floor=0 sel=29 7.7s
[Checkpoint] saved → checkpoints/model_iter0250.pt
251/401 | loss=0.8358 ev=0.497 agents=221 avg_r=3.1797 sum_r=814.00 x<0=0.00 elig=0.61 dorfler_tail=0.07 floor=0 sel=28 7.4s
252/401 | loss=0.7213 ev=0.529 agents=318 avg_r=3.7237 sum_r=953.26 x<0=0.00 elig=0.60 dorfler_tail=0.08 floor=0 sel=28 7.4s
253/401 | loss=0.7174 ev=0.530 agents=1013 avg_r=1.8543 sum_r=474.70 x<0=0.00 elig=0.61 dorfler_tail=0.07 floor=0 sel=25 7.1s
254/401 | loss=0.8496 ev=0.486 agents=101 avg_r=4.5127 sum_r=1155.26 x<0=0.00 elig=0.61 dorfler_tail=0.08 floor=0 sel=29 8.0s
255/401 | loss=0.7620 ev=0.526 agents=39 avg_r=2.8203 sum_r=721.99 x<0=0.00 elig=0.61 dorfler_tail=0.07 floor=0 sel=27 7.7s
256/401 | loss=0.7307 ev=0.534 agents=628 avg_r=4.4600 sum_r=1141.76 x<0=0.01 elig=0.61 dorfler_tail=0.08 floor=0 sel=27 7.6s
257/401 | loss=0.7684 ev=0.513 agents=395 avg_r=3.4904 sum_r=893.53 x<0=0.00 elig=0.61 dorfler_tail=0.07 floor=0 sel=27 7.7s
258/401 | loss=0.7384 ev=0.533 agents=244 avg_r=4.2749 sum_r=1094.38 x<0=0.00 elig=0.61 dorfler_tail=0.07 floor=0 sel=28 7.6s
259/401 | loss=0.8468 ev=0.500 agents=199 avg_r=2.7803 sum_r=711.75 x<0=0.00 elig=0.62 dorfler_tail=0.07 floor=0 sel=25 7.4s
260/401 | loss=0.8891 ev=0.471 agents=113 avg_r=4.3324 sum_r=1109.10 x<0=0.01 elig=0.62 dorfler_tail=0.07 floor=0 sel=27 7.5s
261/401 | loss=0.8631 ev=0.491 agents=573 avg_r=4.3577 sum_r=1115.56 x<0=0.00 elig=0.62 dorfler_tail=0.07 floor=0 sel=28 7.6s
262/401 | loss=0.8856 ev=0.504 agents=658 avg_r=4.7877 sum_r=1225.66 x<0=0.01 elig=0.62 dorfler_tail=0.08 floor=0 sel=29 7.7s
263/401 | loss=0.7890 ev=0.531 agents=215 avg_r=3.1940 sum_r=817.65 x<0=0.00 elig=0.62 dorfler_tail=0.07 floor=0 sel=26 7.4s
264/401 | loss=0.7539 ev=0.491 agents=44 avg_r=2.2303 sum_r=570.95 x<0=0.00 elig=0.61 dorfler_tail=0.07 floor=0 sel=25 7.2s
265/401 | loss=0.7910 ev=0.521 agents=34 avg_r=4.1604 sum_r=1065.05 x<0=0.00 elig=0.62 dorfler_tail=0.08 floor=0 sel=28 7.6s
266/401 | loss=0.7827 ev=0.525 agents=97 avg_r=4.0291 sum_r=1031.44 x<0=0.00 elig=0.62 dorfler_tail=0.07 floor=0 sel=27 7.4s
267/401 | loss=0.8642 ev=0.539 agents=64 avg_r=4.4701 sum_r=1144.35 x<0=0.00 elig=0.62 dorfler_tail=0.07 floor=0 sel=28 7.6s
268/401 | loss=0.7770 ev=0.503 agents=813 avg_r=3.0955 sum_r=792.44 x<0=0.00 elig=0.62 dorfler_tail=0.07 floor=0 sel=25 7.1s
269/401 | loss=0.6881 ev=0.513 agents=34 avg_r=2.4608 sum_r=629.97 x<0=0.00 elig=0.61 dorfler_tail=0.07 floor=0 sel=29 7.4s
270/401 | loss=0.6843 ev=0.513 agents=523 avg_r=3.8834 sum_r=994.14 x<0=0.00 elig=0.61 dorfler_tail=0.08 floor=0 sel=27 7.4s
271/401 | loss=0.7640 ev=0.497 agents=34 avg_r=3.2820 sum_r=840.20 x<0=0.00 elig=0.61 dorfler_tail=0.08 floor=0 sel=28 7.4s
272/401 | loss=0.8417 ev=0.493 agents=204 avg_r=2.4556 sum_r=628.62 x<0=0.01 elig=0.61 dorfler_tail=0.07 floor=0 sel=28 7.5s
273/401 | loss=0.7486 ev=0.517 agents=155 avg_r=1.8537 sum_r=474.56 x<0=0.01 elig=0.60 dorfler_tail=0.08 floor=0 sel=27 7.2s
274/401 | loss=0.6343 ev=0.551 agents=245 avg_r=3.7625 sum_r=963.20 x<0=0.00 elig=0.60 dorfler_tail=0.08 floor=0 sel=28 7.4s
275/401 | loss=0.5988 ev=0.554 agents=140 avg_r=2.5426 sum_r=650.91 x<0=0.01 elig=0.60 dorfler_tail=0.08 floor=0 sel=28 7.2s
276/401 | loss=0.7488 ev=0.529 agents=34 avg_r=1.9313 sum_r=494.41 x<0=0.01 elig=0.60 dorfler_tail=0.08 floor=0 sel=28 7.7s
277/401 | loss=0.7258 ev=0.496 agents=104 avg_r=2.8360 sum_r=726.01 x<0=0.01 elig=0.61 dorfler_tail=0.07 floor=0 sel=28 7.8s
278/401 | loss=0.6367 ev=0.539 agents=86 avg_r=3.5156 sum_r=900.00 x<0=0.00 elig=0.60 dorfler_tail=0.08 floor=0 sel=29 7.6s
279/401 | loss=0.6267 ev=0.548 agents=1453 avg_r=3.0546 sum_r=781.97 x<0=0.01 elig=0.60 dorfler_tail=0.08 floor=0 sel=28 7.6s
280/401 | loss=0.6415 ev=0.533 agents=225 avg_r=2.5181 sum_r=644.63 x<0=0.00 elig=0.59 dorfler_tail=0.08 floor=0 sel=28 7.3s
281/401 | loss=0.6360 ev=0.550 agents=211 avg_r=2.4619 sum_r=630.24 x<0=0.01 elig=0.60 dorfler_tail=0.08 floor=0 sel=27 7.4s
282/401 | loss=0.6967 ev=0.496 agents=141 avg_r=1.4766 sum_r=378.01 x<0=0.00 elig=0.61 dorfler_tail=0.07 floor=0 sel=28 7.3s
283/401 | loss=0.7013 ev=0.536 agents=77 avg_r=2.8570 sum_r=731.40 x<0=0.01 elig=0.61 dorfler_tail=0.08 floor=0 sel=27 7.3s
284/401 | loss=0.7681 ev=0.518 agents=34 avg_r=2.8556 sum_r=731.02 x<0=0.01 elig=0.60 dorfler_tail=0.08 floor=0 sel=28 7.4s
285/401 | loss=0.7100 ev=0.530 agents=146 avg_r=3.9244 sum_r=1004.65 x<0=0.01 elig=0.60 dorfler_tail=0.08 floor=0 sel=29 7.6s
286/401 | loss=0.6773 ev=0.557 agents=118 avg_r=4.1812 sum_r=1070.38 x<0=0.01 elig=0.60 dorfler_tail=0.08 floor=0 sel=29 7.6s
287/401 | loss=0.7370 ev=0.542 agents=79 avg_r=3.1609 sum_r=809.20 x<0=0.00 elig=0.61 dorfler_tail=0.08 floor=0 sel=27 7.4s
288/401 | loss=0.7687 ev=0.522 agents=34 avg_r=2.3589 sum_r=603.88 x<0=0.01 elig=0.61 dorfler_tail=0.07 floor=0 sel=25 7.2s
289/401 | loss=0.7368 ev=0.546 agents=144 avg_r=4.4971 sum_r=1151.27 x<0=0.01 elig=0.61 dorfler_tail=0.08 floor=0 sel=29 7.6s
290/401 | loss=0.8127 ev=0.523 agents=112 avg_r=3.2128 sum_r=822.48 x<0=0.00 elig=0.61 dorfler_tail=0.08 floor=0 sel=28 7.6s
291/401 | loss=0.8122 ev=0.544 agents=167 avg_r=5.3077 sum_r=1358.76 x<0=0.01 elig=0.62 dorfler_tail=0.07 floor=0 sel=26 7.4s
292/401 | loss=0.8049 ev=0.548 agents=779 avg_r=4.8604 sum_r=1244.27 x<0=0.00 elig=0.62 dorfler_tail=0.08 floor=0 sel=29 7.7s
293/401 | loss=0.8547 ev=0.510 agents=1224 avg_r=5.0976 sum_r=1304.98 x<0=0.01 elig=0.62 dorfler_tail=0.08 floor=0 sel=26 7.5s
294/401 | loss=0.7872 ev=0.549 agents=34 avg_r=4.3640 sum_r=1117.20 x<0=0.01 elig=0.61 dorfler_tail=0.08 floor=0 sel=27 7.5s
295/401 | loss=0.7772 ev=0.535 agents=133 avg_r=3.8117 sum_r=975.79 x<0=0.01 elig=0.62 dorfler_tail=0.07 floor=0 sel=27 7.3s
296/401 | loss=0.8143 ev=0.530 agents=171 avg_r=5.1571 sum_r=1320.22 x<0=0.00 elig=0.61 dorfler_tail=0.08 floor=0 sel=29 7.8s
297/401 | loss=0.8086 ev=0.544 agents=198 avg_r=5.4123 sum_r=1385.56 x<0=0.01 elig=0.62 dorfler_tail=0.08 floor=0 sel=30 8.0s
298/401 | loss=0.7918 ev=0.512 agents=66 avg_r=3.1244 sum_r=799.85 x<0=0.00 elig=0.61 dorfler_tail=0.07 floor=0 sel=24 7.0s
299/401 | loss=0.8891 ev=0.549 agents=200 avg_r=4.3910 sum_r=1124.10 x<0=0.01 elig=0.62 dorfler_tail=0.08 floor=0 sel=27 7.5s
300/401 | loss=0.8565 ev=0.548 agents=349 avg_r=5.9245 sum_r=1516.67 x<0=0.00 elig=0.62 dorfler_tail=0.08 floor=0 sel=28 8.2s
[Checkpoint] saved → checkpoints/model_iter0300.pt
301/401 | loss=0.8460 ev=0.520 agents=918 avg_r=3.2190 sum_r=824.07 x<0=0.01 elig=0.61 dorfler_tail=0.08 floor=0 sel=28 8.0s
302/401 | loss=0.8789 ev=0.531 agents=85 avg_r=4.0706 sum_r=1042.08 x<0=0.02 elig=0.62 dorfler_tail=0.08 floor=0 sel=26 7.5s
303/401 | loss=0.7883 ev=0.535 agents=324 avg_r=5.4005 sum_r=1382.52 x<0=0.00 elig=0.61 dorfler_tail=0.08 floor=0 sel=28 7.9s
304/401 | loss=0.7395 ev=0.538 agents=34 avg_r=5.0499 sum_r=1292.78 x<0=0.01 elig=0.61 dorfler_tail=0.08 floor=0 sel=30 8.0s
305/401 | loss=0.7911 ev=0.510 agents=304 avg_r=3.1696 sum_r=811.42 x<0=0.01 elig=0.61 dorfler_tail=0.08 floor=0 sel=26 7.3s
306/401 | loss=0.7920 ev=0.557 agents=383 avg_r=6.0517 sum_r=1549.24 x<0=0.00 elig=0.62 dorfler_tail=0.08 floor=0 sel=30 8.0s
307/401 | loss=0.8841 ev=0.522 agents=206 avg_r=4.6808 sum_r=1198.28 x<0=0.01 elig=0.62 dorfler_tail=0.07 floor=0 sel=27 7.4s
308/401 | loss=0.8185 ev=0.531 agents=98 avg_r=4.2498 sum_r=1087.96 x<0=0.01 elig=0.61 dorfler_tail=0.08 floor=0 sel=28 7.5s
309/401 | loss=0.7786 ev=0.553 agents=92 avg_r=4.5267 sum_r=1158.84 x<0=0.01 elig=0.62 dorfler_tail=0.08 floor=0 sel=28 7.7s
310/401 | loss=0.8129 ev=0.557 agents=232 avg_r=4.8459 sum_r=1240.55 x<0=0.00 elig=0.62 dorfler_tail=0.08 floor=0 sel=26 7.4s
311/401 | loss=0.7548 ev=0.544 agents=85 avg_r=3.9997 sum_r=1023.93 x<0=0.01 elig=0.62 dorfler_tail=0.08 floor=0 sel=28 7.6s
312/401 | loss=0.8005 ev=0.574 agents=112 avg_r=5.2808 sum_r=1351.89 x<0=0.00 elig=0.61 dorfler_tail=0.08 floor=0 sel=28 7.6s
313/401 | loss=0.7345 ev=0.581 agents=34 avg_r=4.7019 sum_r=1203.69 x<0=0.00 elig=0.62 dorfler_tail=0.08 floor=0 sel=28 7.6s
314/401 | loss=0.9237 ev=0.478 agents=1299 avg_r=1.9343 sum_r=495.18 x<0=0.02 elig=0.62 dorfler_tail=0.08 floor=0 sel=26 7.3s
315/401 | loss=0.7310 ev=0.615 agents=90 avg_r=5.8569 sum_r=1499.36 x<0=0.01 elig=0.62 dorfler_tail=0.08 floor=0 sel=29 7.8s
316/401 | loss=0.8623 ev=0.555 agents=125 avg_r=5.8924 sum_r=1508.45 x<0=0.00 elig=0.62 dorfler_tail=0.08 floor=0 sel=30 7.9s
317/401 | loss=0.9039 ev=0.531 agents=790 avg_r=4.9057 sum_r=1255.87 x<0=0.01 elig=0.62 dorfler_tail=0.08 floor=0 sel=28 7.7s
318/401 | loss=0.8584 ev=0.544 agents=667 avg_r=5.5581 sum_r=1422.86 x<0=0.01 elig=0.62 dorfler_tail=0.08 floor=0 sel=29 7.8s
319/401 | loss=0.7933 ev=0.559 agents=217 avg_r=3.9606 sum_r=1013.91 x<0=0.01 elig=0.62 dorfler_tail=0.07 floor=0 sel=26 7.4s
320/401 | loss=0.7544 ev=0.577 agents=260 avg_r=4.5550 sum_r=1166.08 x<0=0.00 elig=0.61 dorfler_tail=0.08 floor=0 sel=28 7.5s
321/401 | loss=0.9524 ev=0.525 agents=189 avg_r=5.2861 sum_r=1353.23 x<0=0.01 elig=0.62 dorfler_tail=0.08 floor=0 sel=29 7.8s
322/401 | loss=0.7658 ev=0.588 agents=228 avg_r=4.9868 sum_r=1276.62 x<0=0.00 elig=0.62 dorfler_tail=0.08 floor=0 sel=29 8.0s
323/401 | loss=0.8794 ev=0.551 agents=228 avg_r=5.1649 sum_r=1322.20 x<0=0.01 elig=0.62 dorfler_tail=0.08 floor=0 sel=28 8.0s
324/401 | loss=0.8258 ev=0.560 agents=926 avg_r=5.6783 sum_r=1453.65 x<0=0.01 elig=0.62 dorfler_tail=0.08 floor=0 sel=29 8.1s
325/401 | loss=0.8111 ev=0.546 agents=92 avg_r=3.8608 sum_r=988.37 x<0=0.00 elig=0.62 dorfler_tail=0.08 floor=0 sel=26 7.7s
326/401 | loss=0.8054 ev=0.537 agents=44 avg_r=5.0405 sum_r=1290.36 x<0=0.01 elig=0.62 dorfler_tail=0.08 floor=0 sel=28 7.8s
327/401 | loss=0.7261 ev=0.572 agents=34 avg_r=4.9393 sum_r=1264.47 x<0=0.01 elig=0.62 dorfler_tail=0.08 floor=0 sel=27 7.6s
328/401 | loss=0.8017 ev=0.541 agents=230 avg_r=4.4739 sum_r=1145.32 x<0=0.01 elig=0.62 dorfler_tail=0.08 floor=0 sel=28 7.8s
329/401 | loss=0.7753 ev=0.572 agents=485 avg_r=7.0645 sum_r=1808.50 x<0=0.00 elig=0.62 dorfler_tail=0.08 floor=0 sel=30 7.9s
330/401 | loss=0.7878 ev=0.545 agents=64 avg_r=4.5437 sum_r=1163.19 x<0=0.01 elig=0.62 dorfler_tail=0.07 floor=0 sel=25 7.4s
331/401 | loss=0.7565 ev=0.557 agents=412 avg_r=4.9920 sum_r=1277.95 x<0=0.01 elig=0.61 dorfler_tail=0.08 floor=0 sel=29 7.8s
332/401 | loss=0.8143 ev=0.552 agents=172 avg_r=3.6211 sum_r=927.01 x<0=0.01 elig=0.62 dorfler_tail=0.08 floor=0 sel=25 7.3s
333/401 | loss=0.9173 ev=0.551 agents=320 avg_r=6.9295 sum_r=1773.94 x<0=0.01 elig=0.62 dorfler_tail=0.09 floor=0 sel=33 8.3s
334/401 | loss=0.8137 ev=0.582 agents=713 avg_r=3.8566 sum_r=987.28 x<0=0.02 elig=0.62 dorfler_tail=0.08 floor=0 sel=26 7.3s
335/401 | loss=0.8842 ev=0.545 agents=60 avg_r=6.7041 sum_r=1716.25 x<0=0.01 elig=0.62 dorfler_tail=0.09 floor=0 sel=28 7.9s
336/401 | loss=0.9756 ev=0.549 agents=1171 avg_r=5.2897 sum_r=1354.17 x<0=0.02 elig=0.62 dorfler_tail=0.09 floor=0 sel=29 7.9s
337/401 | loss=0.9149 ev=0.543 agents=248 avg_r=4.5455 sum_r=1163.64 x<0=0.02 elig=0.62 dorfler_tail=0.08 floor=0 sel=27 7.5s
338/401 | loss=0.8112 ev=0.572 agents=622 avg_r=6.2201 sum_r=1592.33 x<0=0.02 elig=0.62 dorfler_tail=0.08 floor=0 sel=31 7.9s
339/401 | loss=0.8142 ev=0.568 agents=199 avg_r=3.9913 sum_r=1021.77 x<0=0.01 elig=0.61 dorfler_tail=0.08 floor=0 sel=25 7.4s
340/401 | loss=0.8424 ev=0.559 agents=96 avg_r=5.2087 sum_r=1333.43 x<0=0.01 elig=0.62 dorfler_tail=0.08 floor=0 sel=29 7.8s
341/401 | loss=0.9293 ev=0.514 agents=81 avg_r=6.3846 sum_r=1634.47 x<0=0.01 elig=0.62 dorfler_tail=0.08 floor=0 sel=29 7.9s
342/401 | loss=0.7994 ev=0.581 agents=229 avg_r=4.3458 sum_r=1112.52 x<0=0.01 elig=0.61 dorfler_tail=0.08 floor=0 sel=28 7.5s
343/401 | loss=0.8801 ev=0.527 agents=34 avg_r=4.7860 sum_r=1225.21 x<0=0.01 elig=0.62 dorfler_tail=0.08 floor=0 sel=29 7.7s
344/401 | loss=0.7951 ev=0.552 agents=388 avg_r=4.7995 sum_r=1228.67 x<0=0.01 elig=0.62 dorfler_tail=0.08 floor=0 sel=26 7.8s
345/401 | loss=0.9618 ev=0.521 agents=230 avg_r=5.5096 sum_r=1410.46 x<0=0.01 elig=0.62 dorfler_tail=0.08 floor=0 sel=30 8.1s
346/401 | loss=0.8626 ev=0.531 agents=225 avg_r=3.1414 sum_r=804.19 x<0=0.01 elig=0.62 dorfler_tail=0.07 floor=0 sel=24 7.2s
347/401 | loss=0.9345 ev=0.559 agents=591 avg_r=7.0921 sum_r=1815.57 x<0=0.00 elig=0.62 dorfler_tail=0.09 floor=0 sel=33 8.5s
348/401 | loss=0.9702 ev=0.535 agents=306 avg_r=4.1943 sum_r=1073.73 x<0=0.02 elig=0.62 dorfler_tail=0.08 floor=0 sel=27 7.5s
349/401 | loss=0.9282 ev=0.554 agents=169 avg_r=5.7926 sum_r=1482.90 x<0=0.01 elig=0.62 dorfler_tail=0.08 floor=0 sel=30 7.9s
350/401 | loss=0.8965 ev=0.529 agents=228 avg_r=4.0997 sum_r=1049.54 x<0=0.01 elig=0.63 dorfler_tail=0.08 floor=0 sel=28 7.6s
[Checkpoint] saved → checkpoints/model_iter0350.pt
351/401 | loss=0.9006 ev=0.536 agents=86 avg_r=4.7264 sum_r=1209.97 x<0=0.01 elig=0.63 dorfler_tail=0.08 floor=0 sel=27 7.6s
352/401 | loss=0.9423 ev=0.549 agents=400 avg_r=6.4270 sum_r=1645.32 x<0=0.01 elig=0.62 dorfler_tail=0.08 floor=0 sel=31 7.9s
353/401 | loss=0.8666 ev=0.526 agents=430 avg_r=4.5322 sum_r=1160.24 x<0=0.00 elig=0.62 dorfler_tail=0.08 floor=0 sel=28 7.5s
354/401 | loss=0.9237 ev=0.542 agents=90 avg_r=4.8545 sum_r=1242.75 x<0=0.01 elig=0.62 dorfler_tail=0.07 floor=0 sel=29 7.6s
355/401 | loss=0.9779 ev=0.510 agents=171 avg_r=4.5744 sum_r=1171.05 x<0=0.01 elig=0.62 dorfler_tail=0.08 floor=0 sel=29 7.6s
356/401 | loss=1.0088 ev=0.528 agents=85 avg_r=4.8350 sum_r=1237.76 x<0=0.00 elig=0.63 dorfler_tail=0.08 floor=0 sel=27 7.4s
357/401 | loss=1.0785 ev=0.467 agents=84 avg_r=3.3997 sum_r=870.32 x<0=0.01 elig=0.62 dorfler_tail=0.08 floor=0 sel=29 7.6s
358/401 | loss=0.9516 ev=0.541 agents=123 avg_r=6.2179 sum_r=1591.79 x<0=0.01 elig=0.62 dorfler_tail=0.08 floor=0 sel=31 7.8s
359/401 | loss=0.8837 ev=0.540 agents=64 avg_r=5.3393 sum_r=1366.87 x<0=0.00 elig=0.62 dorfler_tail=0.08 floor=0 sel=30 7.8s
360/401 | loss=1.0886 ev=0.507 agents=829 avg_r=3.6631 sum_r=937.76 x<0=0.01 elig=0.62 dorfler_tail=0.07 floor=0 sel=28 7.5s
361/401 | loss=1.0488 ev=0.483 agents=215 avg_r=6.7987 sum_r=1740.47 x<0=0.00 elig=0.62 dorfler_tail=0.08 floor=0 sel=30 7.7s
362/401 | loss=0.9141 ev=0.505 agents=743 avg_r=3.4182 sum_r=875.05 x<0=0.01 elig=0.62 dorfler_tail=0.08 floor=0 sel=29 7.6s
363/401 | loss=0.9284 ev=0.548 agents=94 avg_r=4.6619 sum_r=1193.46 x<0=0.00 elig=0.62 dorfler_tail=0.08 floor=0 sel=27 7.3s
364/401 | loss=0.8426 ev=0.520 agents=157 avg_r=3.2013 sum_r=819.54 x<0=0.01 elig=0.62 dorfler_tail=0.07 floor=0 sel=28 7.4s
365/401 | loss=1.0450 ev=0.499 agents=409 avg_r=5.9785 sum_r=1530.48 x<0=0.00 elig=0.62 dorfler_tail=0.08 floor=0 sel=31 7.8s
366/401 | loss=1.0103 ev=0.517 agents=118 avg_r=4.5559 sum_r=1166.30 x<0=0.01 elig=0.63 dorfler_tail=0.08 floor=0 sel=30 8.0s
367/401 | loss=0.8992 ev=0.548 agents=304 avg_r=5.5253 sum_r=1414.48 x<0=0.01 elig=0.63 dorfler_tail=0.08 floor=0 sel=29 8.1s
368/401 | loss=0.8896 ev=0.542 agents=236 avg_r=4.8329 sum_r=1237.22 x<0=0.01 elig=0.62 dorfler_tail=0.08 floor=0 sel=28 7.8s
369/401 | loss=0.9038 ev=0.547 agents=34 avg_r=4.3783 sum_r=1120.85 x<0=0.01 elig=0.62 dorfler_tail=0.08 floor=0 sel=30 8.0s
370/401 | loss=0.9561 ev=0.534 agents=34 avg_r=4.7629 sum_r=1219.31 x<0=0.02 elig=0.62 dorfler_tail=0.08 floor=0 sel=27 7.5s
371/401 | loss=0.9814 ev=0.522 agents=611 avg_r=4.7171 sum_r=1207.57 x<0=0.01 elig=0.62 dorfler_tail=0.08 floor=0 sel=29 7.7s
372/401 | loss=0.9877 ev=0.540 agents=119 avg_r=4.1701 sum_r=1067.53 x<0=0.02 elig=0.62 dorfler_tail=0.08 floor=0 sel=29 7.7s
373/401 | loss=0.8940 ev=0.547 agents=39 avg_r=5.0060 sum_r=1281.53 x<0=0.01 elig=0.63 dorfler_tail=0.08 floor=0 sel=30 7.8s
374/401 | loss=1.0368 ev=0.562 agents=197 avg_r=4.9253 sum_r=1260.87 x<0=0.01 elig=0.63 dorfler_tail=0.08 floor=0 sel=27 7.6s
375/401 | loss=0.9746 ev=0.504 agents=200 avg_r=4.9331 sum_r=1262.88 x<0=0.02 elig=0.63 dorfler_tail=0.08 floor=0 sel=27 7.5s
376/401 | loss=0.9767 ev=0.546 agents=276 avg_r=5.4246 sum_r=1388.70 x<0=0.01 elig=0.63 dorfler_tail=0.08 floor=0 sel=30 7.8s
377/401 | loss=0.9836 ev=0.524 agents=198 avg_r=5.0625 sum_r=1296.01 x<0=0.01 elig=0.64 dorfler_tail=0.08 floor=0 sel=27 7.6s
378/401 | loss=1.0488 ev=0.497 agents=745 avg_r=4.0224 sum_r=1029.73 x<0=0.02 elig=0.63 dorfler_tail=0.07 floor=0 sel=27 7.5s
379/401 | loss=0.9358 ev=0.572 agents=337 avg_r=6.0321 sum_r=1544.22 x<0=0.01 elig=0.63 dorfler_tail=0.08 floor=0 sel=29 7.8s
380/401 | loss=0.9310 ev=0.564 agents=193 avg_r=6.7029 sum_r=1715.94 x<0=0.02 elig=0.63 dorfler_tail=0.08 floor=0 sel=29 7.6s
381/401 | loss=0.9425 ev=0.524 agents=1211 avg_r=3.9985 sum_r=1023.62 x<0=0.02 elig=0.63 dorfler_tail=0.09 floor=0 sel=27 7.6s
382/401 | loss=1.0188 ev=0.566 agents=482 avg_r=5.5721 sum_r=1426.45 x<0=0.04 elig=0.63 dorfler_tail=0.08 floor=0 sel=29 7.7s
383/401 | loss=0.9704 ev=0.528 agents=209 avg_r=6.0485 sum_r=1548.41 x<0=0.03 elig=0.64 dorfler_tail=0.08 floor=0 sel=28 7.6s
384/401 | loss=0.9859 ev=0.534 agents=1230 avg_r=5.8093 sum_r=1487.18 x<0=0.02 elig=0.63 dorfler_tail=0.08 floor=0 sel=29 7.8s
385/401 | loss=1.0294 ev=0.542 agents=200 avg_r=4.0988 sum_r=1049.30 x<0=0.02 elig=0.63 dorfler_tail=0.08 floor=0 sel=28 7.6s
386/401 | loss=0.9570 ev=0.537 agents=397 avg_r=5.4463 sum_r=1394.26 x<0=0.02 elig=0.63 dorfler_tail=0.08 floor=0 sel=27 7.5s
387/401 | loss=0.9889 ev=0.533 agents=34 avg_r=6.3465 sum_r=1624.69 x<0=0.01 elig=0.64 dorfler_tail=0.08 floor=0 sel=29 7.6s
388/401 | loss=1.0284 ev=0.518 agents=242 avg_r=6.6849 sum_r=1711.35 x<0=0.01 elig=0.63 dorfler_tail=0.08 floor=0 sel=31 7.9s
389/401 | loss=0.9674 ev=0.506 agents=1219 avg_r=2.7841 sum_r=712.73 x<0=0.01 elig=0.64 dorfler_tail=0.07 floor=0 sel=24 7.3s
390/401 | loss=1.0035 ev=0.524 agents=147 avg_r=7.6948 sum_r=1969.86 x<0=0.00 elig=0.64 dorfler_tail=0.08 floor=0 sel=32 8.5s
391/401 | loss=0.9791 ev=0.521 agents=749 avg_r=4.6773 sum_r=1197.40 x<0=0.01 elig=0.63 dorfler_tail=0.07 floor=0 sel=28 7.8s
392/401 | loss=1.0303 ev=0.538 agents=506 avg_r=5.7889 sum_r=1481.96 x<0=0.01 elig=0.63 dorfler_tail=0.08 floor=0 sel=30 7.9s
393/401 | loss=0.9156 ev=0.530 agents=34 avg_r=4.9215 sum_r=1259.91 x<0=0.01 elig=0.63 dorfler_tail=0.07 floor=0 sel=27 7.4s
394/401 | loss=0.9221 ev=0.550 agents=566 avg_r=6.1226 sum_r=1567.39 x<0=0.00 elig=0.63 dorfler_tail=0.08 floor=0 sel=30 7.9s
395/401 | loss=1.0507 ev=0.505 agents=278 avg_r=3.6668 sum_r=938.69 x<0=0.01 elig=0.63 dorfler_tail=0.07 floor=0 sel=28 7.5s
396/401 | loss=1.0621 ev=0.495 agents=535 avg_r=5.1409 sum_r=1316.06 x<0=0.02 elig=0.64 dorfler_tail=0.08 floor=0 sel=27 7.4s
397/401 | loss=0.8922 ev=0.549 agents=145 avg_r=5.6600 sum_r=1448.95 x<0=0.01 elig=0.64 dorfler_tail=0.08 floor=0 sel=29 7.9s
398/401 | loss=1.0484 ev=0.536 agents=62 avg_r=5.7253 sum_r=1465.68 x<0=0.02 elig=0.64 dorfler_tail=0.08 floor=0 sel=26 7.5s
399/401 | loss=1.0258 ev=0.542 agents=146 avg_r=6.1057 sum_r=1563.07 x<0=0.02 elig=0.64 dorfler_tail=0.08 floor=0 sel=29 7.8s
400/401 | loss=0.9834 ev=0.526 agents=697 avg_r=4.9534 sum_r=1268.06 x<0=0.02 elig=0.63 dorfler_tail=0.08 floor=0 sel=28 7.6s
[Checkpoint] saved → checkpoints/model_iter0400.pt
401/401 | loss=0.9563 ev=0.563 agents=177 avg_r=7.3312 sum_r=1876.79 x<0=0.02 elig=0.64 dorfler_tail=0.08 floor=0 sel=30 7.9s
[Checkpoint] saved → checkpoints/model_iter0401.pt
[Checkpoint] saved → checkpoints/model_final.pt
[Train] done, total time 3050.1s
Training finished at Sat 30 May 16:07:16 CST 2026