419 lines
51 KiB
Plaintext
419 lines
51 KiB
Plaintext
Starting training at Fri 29 May 14:58:18 CST 2026
|
|
Running on node: node06
|
|
[Device] cuda
|
|
[Env] node_feats=14 edge_feats=1 act_dim=1
|
|
[Model] params=92,804
|
|
1/401 | loss=1.4128 ev=-0.004 agents=109 avg_r=-2.9617 sum_r=-758.20 x<0=0.69 elig=0.58 dorfler_tail=0.09 floor=0 sel=35 8.6s
|
|
2/401 | loss=1.3206 ev=0.021 agents=193 avg_r=-0.3258 sum_r=-83.41 x<0=0.62 elig=0.58 dorfler_tail=0.08 floor=0 sel=32 7.8s
|
|
3/401 | loss=1.2607 ev=0.053 agents=39 avg_r=-3.3286 sum_r=-852.13 x<0=0.56 elig=0.59 dorfler_tail=0.08 floor=0 sel=32 7.7s
|
|
4/401 | loss=1.3325 ev=0.075 agents=34 avg_r=0.7804 sum_r=199.78 x<0=0.52 elig=0.58 dorfler_tail=0.09 floor=0 sel=35 8.2s
|
|
5/401 | loss=1.2579 ev=0.094 agents=88 avg_r=-3.0086 sum_r=-770.19 x<0=0.43 elig=0.59 dorfler_tail=0.08 floor=0 sel=32 8.0s
|
|
6/401 | loss=1.2490 ev=0.117 agents=36 avg_r=-0.7408 sum_r=-189.63 x<0=0.40 elig=0.59 dorfler_tail=0.08 floor=0 sel=32 7.7s
|
|
7/401 | loss=1.1303 ev=0.172 agents=34 avg_r=-0.5650 sum_r=-144.65 x<0=0.35 elig=0.58 dorfler_tail=0.08 floor=0 sel=35 8.0s
|
|
8/401 | loss=1.1519 ev=0.223 agents=133 avg_r=-0.3562 sum_r=-91.18 x<0=0.29 elig=0.59 dorfler_tail=0.08 floor=0 sel=33 7.8s
|
|
9/401 | loss=1.0561 ev=0.265 agents=79 avg_r=0.0758 sum_r=19.41 x<0=0.28 elig=0.59 dorfler_tail=0.08 floor=0 sel=31 7.6s
|
|
10/401 | loss=1.0494 ev=0.258 agents=82 avg_r=-2.5148 sum_r=-643.78 x<0=0.34 elig=0.59 dorfler_tail=0.08 floor=0 sel=34 7.8s
|
|
11/401 | loss=1.0812 ev=0.302 agents=60 avg_r=2.1651 sum_r=554.27 x<0=0.30 elig=0.59 dorfler_tail=0.08 floor=0 sel=31 7.6s
|
|
12/401 | loss=0.9418 ev=0.317 agents=48 avg_r=1.0822 sum_r=277.04 x<0=0.28 elig=0.59 dorfler_tail=0.08 floor=0 sel=33 7.7s
|
|
13/401 | loss=0.9202 ev=0.317 agents=88 avg_r=0.3357 sum_r=85.94 x<0=0.33 elig=0.59 dorfler_tail=0.08 floor=0 sel=33 7.8s
|
|
14/401 | loss=0.9721 ev=0.318 agents=40 avg_r=0.2343 sum_r=59.99 x<0=0.28 elig=0.59 dorfler_tail=0.08 floor=0 sel=32 7.7s
|
|
15/401 | loss=0.9063 ev=0.352 agents=101 avg_r=0.5217 sum_r=133.55 x<0=0.25 elig=0.59 dorfler_tail=0.08 floor=0 sel=33 7.8s
|
|
16/401 | loss=1.0478 ev=0.353 agents=34 avg_r=-1.6244 sum_r=-415.85 x<0=0.21 elig=0.59 dorfler_tail=0.08 floor=0 sel=29 7.4s
|
|
17/401 | loss=0.9633 ev=0.345 agents=132 avg_r=2.7550 sum_r=705.27 x<0=0.24 elig=0.59 dorfler_tail=0.08 floor=0 sel=33 7.8s
|
|
18/401 | loss=0.9338 ev=0.365 agents=34 avg_r=0.5794 sum_r=148.32 x<0=0.30 elig=0.58 dorfler_tail=0.08 floor=0 sel=32 7.7s
|
|
19/401 | loss=0.8862 ev=0.393 agents=201 avg_r=0.2777 sum_r=71.08 x<0=0.27 elig=0.59 dorfler_tail=0.08 floor=0 sel=34 7.9s
|
|
20/401 | loss=0.8669 ev=0.394 agents=120 avg_r=0.4671 sum_r=119.58 x<0=0.19 elig=0.59 dorfler_tail=0.08 floor=0 sel=31 7.6s
|
|
21/401 | loss=0.9409 ev=0.369 agents=78 avg_r=0.5001 sum_r=128.03 x<0=0.17 elig=0.59 dorfler_tail=0.08 floor=0 sel=31 7.6s
|
|
22/401 | loss=0.8863 ev=0.373 agents=44 avg_r=-0.1458 sum_r=-37.33 x<0=0.19 elig=0.59 dorfler_tail=0.08 floor=0 sel=32 7.6s
|
|
23/401 | loss=0.8574 ev=0.378 agents=36 avg_r=0.1385 sum_r=35.46 x<0=0.18 elig=0.59 dorfler_tail=0.08 floor=0 sel=32 7.6s
|
|
24/401 | loss=0.8286 ev=0.432 agents=175 avg_r=3.1860 sum_r=815.61 x<0=0.16 elig=0.59 dorfler_tail=0.08 floor=0 sel=33 7.7s
|
|
25/401 | loss=0.9002 ev=0.363 agents=34 avg_r=-0.0388 sum_r=-9.93 x<0=0.14 elig=0.59 dorfler_tail=0.08 floor=0 sel=28 7.2s
|
|
26/401 | loss=0.8252 ev=0.385 agents=34 avg_r=-0.2623 sum_r=-67.15 x<0=0.12 elig=0.58 dorfler_tail=0.08 floor=0 sel=34 7.8s
|
|
27/401 | loss=0.8039 ev=0.408 agents=176 avg_r=0.3361 sum_r=86.04 x<0=0.11 elig=0.59 dorfler_tail=0.08 floor=0 sel=31 7.9s
|
|
28/401 | loss=0.8841 ev=0.404 agents=219 avg_r=-0.2521 sum_r=-64.55 x<0=0.10 elig=0.59 dorfler_tail=0.08 floor=0 sel=32 8.1s
|
|
29/401 | loss=0.8608 ev=0.345 agents=44 avg_r=1.4892 sum_r=381.24 x<0=0.10 elig=0.59 dorfler_tail=0.08 floor=0 sel=32 7.9s
|
|
30/401 | loss=0.7754 ev=0.444 agents=133 avg_r=1.3507 sum_r=345.79 x<0=0.09 elig=0.59 dorfler_tail=0.08 floor=0 sel=30 7.5s
|
|
31/401 | loss=0.8501 ev=0.406 agents=44 avg_r=1.3255 sum_r=339.33 x<0=0.09 elig=0.59 dorfler_tail=0.08 floor=0 sel=32 7.7s
|
|
32/401 | loss=0.8750 ev=0.418 agents=34 avg_r=0.3083 sum_r=78.94 x<0=0.06 elig=0.59 dorfler_tail=0.08 floor=0 sel=33 7.7s
|
|
33/401 | loss=0.7966 ev=0.438 agents=745 avg_r=2.5903 sum_r=663.13 x<0=0.06 elig=0.59 dorfler_tail=0.08 floor=0 sel=31 7.5s
|
|
34/401 | loss=0.8724 ev=0.418 agents=132 avg_r=0.1713 sum_r=43.85 x<0=0.06 elig=0.59 dorfler_tail=0.07 floor=0 sel=31 7.5s
|
|
35/401 | loss=0.7984 ev=0.436 agents=60 avg_r=1.5414 sum_r=394.60 x<0=0.05 elig=0.59 dorfler_tail=0.08 floor=0 sel=31 7.6s
|
|
36/401 | loss=0.8868 ev=0.401 agents=139 avg_r=0.2042 sum_r=52.28 x<0=0.04 elig=0.59 dorfler_tail=0.08 floor=0 sel=30 7.4s
|
|
37/401 | loss=0.9037 ev=0.426 agents=228 avg_r=0.5137 sum_r=131.52 x<0=0.04 elig=0.59 dorfler_tail=0.08 floor=0 sel=31 7.5s
|
|
38/401 | loss=0.9280 ev=0.353 agents=34 avg_r=1.7908 sum_r=458.45 x<0=0.05 elig=0.59 dorfler_tail=0.07 floor=0 sel=31 7.5s
|
|
39/401 | loss=0.7340 ev=0.438 agents=194 avg_r=1.8975 sum_r=485.76 x<0=0.05 elig=0.59 dorfler_tail=0.08 floor=0 sel=31 7.4s
|
|
40/401 | loss=0.8670 ev=0.364 agents=228 avg_r=2.4297 sum_r=621.99 x<0=0.07 elig=0.59 dorfler_tail=0.08 floor=0 sel=33 7.7s
|
|
41/401 | loss=0.8306 ev=0.403 agents=199 avg_r=1.3996 sum_r=358.30 x<0=0.06 elig=0.59 dorfler_tail=0.07 floor=0 sel=29 7.3s
|
|
42/401 | loss=0.7935 ev=0.456 agents=40 avg_r=2.2913 sum_r=586.59 x<0=0.06 elig=0.59 dorfler_tail=0.07 floor=0 sel=31 7.5s
|
|
43/401 | loss=0.7569 ev=0.425 agents=34 avg_r=1.5674 sum_r=401.25 x<0=0.05 elig=0.59 dorfler_tail=0.08 floor=0 sel=31 7.5s
|
|
44/401 | loss=0.8324 ev=0.425 agents=193 avg_r=1.5056 sum_r=385.44 x<0=0.07 elig=0.59 dorfler_tail=0.08 floor=0 sel=32 7.5s
|
|
45/401 | loss=0.8032 ev=0.458 agents=230 avg_r=1.1388 sum_r=291.54 x<0=0.06 elig=0.59 dorfler_tail=0.07 floor=0 sel=29 7.3s
|
|
46/401 | loss=0.8043 ev=0.436 agents=34 avg_r=2.3922 sum_r=612.39 x<0=0.07 elig=0.59 dorfler_tail=0.08 floor=0 sel=31 7.5s
|
|
47/401 | loss=0.7410 ev=0.443 agents=120 avg_r=3.2861 sum_r=841.24 x<0=0.08 elig=0.59 dorfler_tail=0.08 floor=0 sel=31 7.4s
|
|
48/401 | loss=0.8324 ev=0.403 agents=34 avg_r=0.2820 sum_r=72.19 x<0=0.05 elig=0.59 dorfler_tail=0.08 floor=0 sel=31 7.5s
|
|
49/401 | loss=0.7722 ev=0.461 agents=118 avg_r=3.1596 sum_r=808.87 x<0=0.06 elig=0.59 dorfler_tail=0.08 floor=0 sel=32 8.0s
|
|
50/401 | loss=0.7615 ev=0.445 agents=203 avg_r=1.2732 sum_r=325.95 x<0=0.03 elig=0.59 dorfler_tail=0.07 floor=0 sel=30 7.7s
|
|
[Checkpoint] saved → checkpoints/model_iter0050.pt
|
|
51/401 | loss=0.7829 ev=0.428 agents=1574 avg_r=1.8165 sum_r=465.03 x<0=0.02 elig=0.59 dorfler_tail=0.08 floor=0 sel=31 7.7s
|
|
52/401 | loss=0.7954 ev=0.432 agents=278 avg_r=2.1507 sum_r=550.57 x<0=0.02 elig=0.59 dorfler_tail=0.08 floor=0 sel=31 7.5s
|
|
53/401 | loss=0.6962 ev=0.449 agents=133 avg_r=2.0534 sum_r=525.66 x<0=0.02 elig=0.59 dorfler_tail=0.07 floor=0 sel=29 7.4s
|
|
54/401 | loss=0.7625 ev=0.454 agents=231 avg_r=1.5343 sum_r=392.79 x<0=0.02 elig=0.59 dorfler_tail=0.08 floor=0 sel=31 7.5s
|
|
55/401 | loss=0.7736 ev=0.414 agents=97 avg_r=1.6580 sum_r=424.46 x<0=0.02 elig=0.59 dorfler_tail=0.08 floor=0 sel=32 7.6s
|
|
56/401 | loss=0.8158 ev=0.454 agents=108 avg_r=1.4593 sum_r=373.59 x<0=0.03 elig=0.60 dorfler_tail=0.07 floor=0 sel=28 7.3s
|
|
57/401 | loss=0.8160 ev=0.384 agents=140 avg_r=1.2522 sum_r=320.57 x<0=0.04 elig=0.59 dorfler_tail=0.08 floor=0 sel=31 7.5s
|
|
58/401 | loss=0.7392 ev=0.444 agents=534 avg_r=3.1169 sum_r=797.93 x<0=0.04 elig=0.59 dorfler_tail=0.08 floor=0 sel=31 7.6s
|
|
59/401 | loss=0.7812 ev=0.401 agents=112 avg_r=1.2579 sum_r=322.03 x<0=0.03 elig=0.60 dorfler_tail=0.07 floor=0 sel=29 7.3s
|
|
60/401 | loss=0.7958 ev=0.444 agents=64 avg_r=0.6857 sum_r=175.55 x<0=0.02 elig=0.59 dorfler_tail=0.08 floor=0 sel=31 7.5s
|
|
61/401 | loss=0.7650 ev=0.447 agents=303 avg_r=2.2103 sum_r=565.84 x<0=0.02 elig=0.60 dorfler_tail=0.07 floor=0 sel=29 7.4s
|
|
62/401 | loss=0.7742 ev=0.476 agents=82 avg_r=1.9037 sum_r=487.34 x<0=0.02 elig=0.59 dorfler_tail=0.08 floor=0 sel=33 7.7s
|
|
63/401 | loss=0.8447 ev=0.351 agents=66 avg_r=1.7917 sum_r=458.68 x<0=0.02 elig=0.60 dorfler_tail=0.07 floor=0 sel=30 7.4s
|
|
64/401 | loss=0.7786 ev=0.394 agents=93 avg_r=1.5619 sum_r=399.83 x<0=0.02 elig=0.60 dorfler_tail=0.08 floor=0 sel=31 7.5s
|
|
65/401 | loss=0.7889 ev=0.429 agents=93 avg_r=3.1505 sum_r=806.54 x<0=0.03 elig=0.60 dorfler_tail=0.08 floor=0 sel=30 7.3s
|
|
66/401 | loss=0.7486 ev=0.411 agents=82 avg_r=3.4632 sum_r=886.58 x<0=0.03 elig=0.60 dorfler_tail=0.07 floor=0 sel=31 7.5s
|
|
67/401 | loss=0.8361 ev=0.387 agents=89 avg_r=2.5091 sum_r=642.33 x<0=0.04 elig=0.60 dorfler_tail=0.07 floor=0 sel=30 7.4s
|
|
68/401 | loss=0.8049 ev=0.455 agents=1246 avg_r=1.6280 sum_r=416.76 x<0=0.02 elig=0.59 dorfler_tail=0.08 floor=0 sel=31 7.6s
|
|
69/401 | loss=0.7406 ev=0.469 agents=169 avg_r=3.0316 sum_r=776.10 x<0=0.02 elig=0.60 dorfler_tail=0.07 floor=0 sel=29 7.3s
|
|
70/401 | loss=0.7916 ev=0.431 agents=666 avg_r=1.2786 sum_r=327.33 x<0=0.02 elig=0.60 dorfler_tail=0.07 floor=0 sel=30 7.4s
|
|
71/401 | loss=0.7455 ev=0.448 agents=219 avg_r=1.7504 sum_r=448.09 x<0=0.02 elig=0.60 dorfler_tail=0.07 floor=0 sel=28 7.4s
|
|
72/401 | loss=0.7722 ev=0.408 agents=255 avg_r=3.3442 sum_r=856.10 x<0=0.03 elig=0.60 dorfler_tail=0.07 floor=0 sel=31 8.0s
|
|
73/401 | loss=0.7531 ev=0.422 agents=334 avg_r=2.3709 sum_r=606.95 x<0=0.02 elig=0.60 dorfler_tail=0.07 floor=0 sel=30 7.5s
|
|
74/401 | loss=0.7534 ev=0.445 agents=34 avg_r=4.3503 sum_r=1113.68 x<0=0.03 elig=0.60 dorfler_tail=0.07 floor=0 sel=29 7.6s
|
|
75/401 | loss=0.8434 ev=0.401 agents=144 avg_r=0.4869 sum_r=124.64 x<0=0.03 elig=0.60 dorfler_tail=0.07 floor=0 sel=30 7.5s
|
|
76/401 | loss=0.8142 ev=0.417 agents=728 avg_r=3.7060 sum_r=948.74 x<0=0.04 elig=0.60 dorfler_tail=0.07 floor=0 sel=31 7.6s
|
|
77/401 | loss=0.8339 ev=0.382 agents=607 avg_r=3.4045 sum_r=871.55 x<0=0.04 elig=0.61 dorfler_tail=0.08 floor=0 sel=29 7.6s
|
|
78/401 | loss=0.9084 ev=0.413 agents=483 avg_r=1.5291 sum_r=391.46 x<0=0.05 elig=0.61 dorfler_tail=0.07 floor=0 sel=30 7.5s
|
|
79/401 | loss=0.8091 ev=0.434 agents=241 avg_r=5.4058 sum_r=1383.89 x<0=0.07 elig=0.61 dorfler_tail=0.08 floor=0 sel=33 8.1s
|
|
80/401 | loss=0.8532 ev=0.444 agents=299 avg_r=3.2896 sum_r=842.13 x<0=0.06 elig=0.63 dorfler_tail=0.07 floor=0 sel=26 7.3s
|
|
81/401 | loss=0.9505 ev=0.414 agents=812 avg_r=2.3540 sum_r=602.61 x<0=0.06 elig=0.61 dorfler_tail=0.07 floor=0 sel=30 7.6s
|
|
82/401 | loss=0.8656 ev=0.370 agents=557 avg_r=1.9931 sum_r=510.22 x<0=0.06 elig=0.62 dorfler_tail=0.07 floor=0 sel=27 7.4s
|
|
83/401 | loss=0.8751 ev=0.454 agents=34 avg_r=4.0672 sum_r=1041.20 x<0=0.07 elig=0.61 dorfler_tail=0.08 floor=0 sel=30 7.7s
|
|
84/401 | loss=1.0631 ev=0.385 agents=527 avg_r=2.2599 sum_r=578.52 x<0=0.06 elig=0.62 dorfler_tail=0.07 floor=0 sel=29 7.6s
|
|
85/401 | loss=0.8861 ev=0.371 agents=110 avg_r=2.5793 sum_r=660.29 x<0=0.06 elig=0.61 dorfler_tail=0.07 floor=0 sel=26 7.2s
|
|
86/401 | loss=1.0104 ev=0.399 agents=692 avg_r=3.1834 sum_r=814.94 x<0=0.07 elig=0.61 dorfler_tail=0.08 floor=0 sel=31 7.9s
|
|
87/401 | loss=1.0484 ev=0.337 agents=265 avg_r=3.8907 sum_r=996.02 x<0=0.11 elig=0.63 dorfler_tail=0.07 floor=0 sel=29 7.9s
|
|
88/401 | loss=0.9365 ev=0.374 agents=1076 avg_r=3.6280 sum_r=928.78 x<0=0.10 elig=0.62 dorfler_tail=0.07 floor=0 sel=29 7.7s
|
|
89/401 | loss=1.0322 ev=0.379 agents=738 avg_r=3.2173 sum_r=823.64 x<0=0.09 elig=0.62 dorfler_tail=0.07 floor=0 sel=28 7.6s
|
|
90/401 | loss=1.0024 ev=0.440 agents=814 avg_r=4.1741 sum_r=1068.56 x<0=0.14 elig=0.62 dorfler_tail=0.07 floor=0 sel=29 7.7s
|
|
91/401 | loss=1.0702 ev=0.415 agents=103 avg_r=2.9575 sum_r=757.12 x<0=0.11 elig=0.62 dorfler_tail=0.08 floor=0 sel=29 7.8s
|
|
92/401 | loss=1.0768 ev=0.393 agents=222 avg_r=2.3631 sum_r=604.95 x<0=0.09 elig=0.62 dorfler_tail=0.07 floor=0 sel=28 7.6s
|
|
93/401 | loss=0.8536 ev=0.446 agents=817 avg_r=2.8966 sum_r=741.53 x<0=0.10 elig=0.62 dorfler_tail=0.07 floor=0 sel=28 7.5s
|
|
94/401 | loss=1.0326 ev=0.381 agents=263 avg_r=3.2866 sum_r=841.36 x<0=0.11 elig=0.62 dorfler_tail=0.07 floor=0 sel=28 7.9s
|
|
95/401 | loss=0.9661 ev=0.438 agents=457 avg_r=4.7830 sum_r=1224.46 x<0=0.14 elig=0.62 dorfler_tail=0.08 floor=0 sel=32 8.7s
|
|
96/401 | loss=1.0307 ev=0.410 agents=146 avg_r=1.6996 sum_r=435.09 x<0=0.12 elig=0.62 dorfler_tail=0.07 floor=0 sel=28 7.6s
|
|
97/401 | loss=1.0506 ev=0.374 agents=1822 avg_r=4.6356 sum_r=1186.73 x<0=0.13 elig=0.62 dorfler_tail=0.07 floor=0 sel=28 8.0s
|
|
98/401 | loss=1.0002 ev=0.431 agents=247 avg_r=3.5428 sum_r=906.95 x<0=0.13 elig=0.63 dorfler_tail=0.07 floor=0 sel=27 7.6s
|
|
99/401 | loss=0.9919 ev=0.429 agents=438 avg_r=2.5796 sum_r=660.39 x<0=0.15 elig=0.63 dorfler_tail=0.07 floor=0 sel=28 7.7s
|
|
100/401 | loss=1.1839 ev=0.424 agents=80 avg_r=2.8253 sum_r=723.27 x<0=0.12 elig=0.62 dorfler_tail=0.07 floor=0 sel=29 7.7s
|
|
[Checkpoint] saved → checkpoints/model_iter0100.pt
|
|
101/401 | loss=1.0950 ev=0.459 agents=897 avg_r=3.8530 sum_r=986.37 x<0=0.18 elig=0.63 dorfler_tail=0.08 floor=0 sel=28 7.8s
|
|
102/401 | loss=1.0915 ev=0.416 agents=82 avg_r=4.4633 sum_r=1142.59 x<0=0.13 elig=0.62 dorfler_tail=0.07 floor=0 sel=29 7.7s
|
|
103/401 | loss=0.9961 ev=0.445 agents=228 avg_r=5.0288 sum_r=1287.37 x<0=0.16 elig=0.63 dorfler_tail=0.07 floor=0 sel=29 7.8s
|
|
104/401 | loss=1.0334 ev=0.390 agents=42 avg_r=4.6071 sum_r=1179.43 x<0=0.17 elig=0.63 dorfler_tail=0.07 floor=0 sel=27 7.6s
|
|
105/401 | loss=1.0714 ev=0.429 agents=375 avg_r=2.9595 sum_r=757.64 x<0=0.14 elig=0.62 dorfler_tail=0.07 floor=0 sel=29 7.6s
|
|
106/401 | loss=1.0984 ev=0.407 agents=34 avg_r=4.7091 sum_r=1205.54 x<0=0.16 elig=0.63 dorfler_tail=0.07 floor=0 sel=29 7.7s
|
|
107/401 | loss=1.0159 ev=0.444 agents=66 avg_r=5.0649 sum_r=1296.62 x<0=0.16 elig=0.63 dorfler_tail=0.07 floor=0 sel=30 7.9s
|
|
108/401 | loss=1.0474 ev=0.424 agents=92 avg_r=3.6964 sum_r=946.27 x<0=0.14 elig=0.63 dorfler_tail=0.07 floor=0 sel=26 7.4s
|
|
109/401 | loss=1.0957 ev=0.424 agents=225 avg_r=4.3635 sum_r=1117.06 x<0=0.15 elig=0.62 dorfler_tail=0.07 floor=0 sel=30 7.9s
|
|
110/401 | loss=1.0859 ev=0.396 agents=182 avg_r=2.8480 sum_r=729.08 x<0=0.15 elig=0.63 dorfler_tail=0.07 floor=0 sel=29 7.6s
|
|
111/401 | loss=0.9448 ev=0.422 agents=171 avg_r=4.1148 sum_r=1053.38 x<0=0.13 elig=0.63 dorfler_tail=0.07 floor=0 sel=28 7.5s
|
|
112/401 | loss=1.0549 ev=0.444 agents=175 avg_r=4.9807 sum_r=1275.05 x<0=0.15 elig=0.63 dorfler_tail=0.07 floor=0 sel=30 7.8s
|
|
113/401 | loss=1.0457 ev=0.431 agents=132 avg_r=4.3526 sum_r=1114.27 x<0=0.13 elig=0.63 dorfler_tail=0.07 floor=0 sel=31 8.0s
|
|
114/401 | loss=0.9811 ev=0.431 agents=219 avg_r=1.9930 sum_r=510.21 x<0=0.11 elig=0.63 dorfler_tail=0.07 floor=0 sel=26 7.2s
|
|
115/401 | loss=1.0557 ev=0.400 agents=39 avg_r=4.7748 sum_r=1222.35 x<0=0.17 elig=0.63 dorfler_tail=0.07 floor=0 sel=28 7.7s
|
|
116/401 | loss=1.1500 ev=0.432 agents=504 avg_r=4.6241 sum_r=1183.76 x<0=0.17 elig=0.63 dorfler_tail=0.07 floor=0 sel=28 7.6s
|
|
117/401 | loss=1.0410 ev=0.412 agents=39 avg_r=3.2529 sum_r=832.73 x<0=0.15 elig=0.63 dorfler_tail=0.07 floor=0 sel=29 7.6s
|
|
118/401 | loss=1.0850 ev=0.452 agents=333 avg_r=4.1276 sum_r=1056.66 x<0=0.16 elig=0.62 dorfler_tail=0.07 floor=0 sel=29 8.3s
|
|
119/401 | loss=1.0983 ev=0.418 agents=261 avg_r=4.2111 sum_r=1078.04 x<0=0.16 elig=0.63 dorfler_tail=0.07 floor=0 sel=28 7.9s
|
|
120/401 | loss=1.1755 ev=0.452 agents=201 avg_r=5.2366 sum_r=1340.57 x<0=0.17 elig=0.63 dorfler_tail=0.07 floor=0 sel=29 7.9s
|
|
121/401 | loss=1.2066 ev=0.441 agents=101 avg_r=4.9395 sum_r=1264.51 x<0=0.17 elig=0.63 dorfler_tail=0.07 floor=0 sel=29 8.0s
|
|
122/401 | loss=1.1325 ev=0.462 agents=411 avg_r=3.0792 sum_r=788.29 x<0=0.21 elig=0.63 dorfler_tail=0.07 floor=0 sel=28 7.6s
|
|
123/401 | loss=1.0326 ev=0.444 agents=625 avg_r=4.2090 sum_r=1077.51 x<0=0.17 elig=0.63 dorfler_tail=0.07 floor=0 sel=29 7.6s
|
|
124/401 | loss=1.1518 ev=0.423 agents=157 avg_r=4.9204 sum_r=1259.61 x<0=0.19 elig=0.64 dorfler_tail=0.07 floor=0 sel=29 7.8s
|
|
125/401 | loss=1.1643 ev=0.456 agents=77 avg_r=5.4202 sum_r=1387.57 x<0=0.17 elig=0.63 dorfler_tail=0.07 floor=0 sel=29 7.8s
|
|
126/401 | loss=1.1922 ev=0.445 agents=112 avg_r=4.2411 sum_r=1085.71 x<0=0.17 elig=0.64 dorfler_tail=0.07 floor=0 sel=27 7.5s
|
|
127/401 | loss=1.3675 ev=0.408 agents=118 avg_r=5.1671 sum_r=1322.77 x<0=0.17 elig=0.64 dorfler_tail=0.08 floor=0 sel=31 7.9s
|
|
128/401 | loss=1.0731 ev=0.426 agents=341 avg_r=4.4974 sum_r=1151.33 x<0=0.15 elig=0.64 dorfler_tail=0.07 floor=0 sel=25 7.3s
|
|
129/401 | loss=1.2627 ev=0.413 agents=143 avg_r=2.6131 sum_r=668.96 x<0=0.14 elig=0.64 dorfler_tail=0.07 floor=0 sel=27 7.5s
|
|
130/401 | loss=1.2541 ev=0.396 agents=919 avg_r=5.7318 sum_r=1467.35 x<0=0.18 elig=0.64 dorfler_tail=0.07 floor=0 sel=29 7.8s
|
|
131/401 | loss=1.1595 ev=0.459 agents=568 avg_r=5.8106 sum_r=1487.51 x<0=0.14 elig=0.64 dorfler_tail=0.07 floor=0 sel=31 7.9s
|
|
132/401 | loss=1.0261 ev=0.464 agents=159 avg_r=3.7017 sum_r=947.63 x<0=0.15 elig=0.64 dorfler_tail=0.07 floor=0 sel=27 7.4s
|
|
133/401 | loss=1.1509 ev=0.457 agents=180 avg_r=4.5674 sum_r=1169.27 x<0=0.13 elig=0.63 dorfler_tail=0.07 floor=0 sel=28 7.6s
|
|
134/401 | loss=1.2367 ev=0.399 agents=34 avg_r=3.3756 sum_r=864.15 x<0=0.12 elig=0.64 dorfler_tail=0.07 floor=0 sel=29 7.7s
|
|
135/401 | loss=1.2713 ev=0.472 agents=42 avg_r=6.9697 sum_r=1784.24 x<0=0.11 elig=0.64 dorfler_tail=0.07 floor=0 sel=29 7.8s
|
|
136/401 | loss=1.1949 ev=0.393 agents=252 avg_r=2.6102 sum_r=668.20 x<0=0.11 elig=0.63 dorfler_tail=0.07 floor=0 sel=27 7.3s
|
|
137/401 | loss=1.1157 ev=0.439 agents=1066 avg_r=5.3136 sum_r=1360.29 x<0=0.09 elig=0.63 dorfler_tail=0.07 floor=0 sel=31 7.9s
|
|
138/401 | loss=1.0746 ev=0.449 agents=214 avg_r=4.6555 sum_r=1191.80 x<0=0.12 elig=0.63 dorfler_tail=0.07 floor=0 sel=29 7.6s
|
|
139/401 | loss=1.1177 ev=0.460 agents=1208 avg_r=3.3845 sum_r=866.43 x<0=0.08 elig=0.63 dorfler_tail=0.07 floor=0 sel=31 7.9s
|
|
140/401 | loss=1.1579 ev=0.498 agents=74 avg_r=3.9158 sum_r=1002.45 x<0=0.10 elig=0.63 dorfler_tail=0.07 floor=0 sel=27 7.6s
|
|
141/401 | loss=1.1397 ev=0.452 agents=227 avg_r=4.6873 sum_r=1199.94 x<0=0.11 elig=0.64 dorfler_tail=0.07 floor=0 sel=29 8.1s
|
|
142/401 | loss=1.0311 ev=0.451 agents=272 avg_r=4.3273 sum_r=1107.79 x<0=0.09 elig=0.63 dorfler_tail=0.07 floor=0 sel=27 7.6s
|
|
143/401 | loss=1.2372 ev=0.429 agents=586 avg_r=3.5519 sum_r=909.28 x<0=0.07 elig=0.63 dorfler_tail=0.07 floor=0 sel=27 7.8s
|
|
144/401 | loss=1.1732 ev=0.431 agents=137 avg_r=5.6718 sum_r=1451.99 x<0=0.10 elig=0.64 dorfler_tail=0.07 floor=0 sel=31 8.1s
|
|
145/401 | loss=1.1318 ev=0.423 agents=1531 avg_r=3.6947 sum_r=945.84 x<0=0.07 elig=0.63 dorfler_tail=0.07 floor=0 sel=30 7.8s
|
|
146/401 | loss=1.2082 ev=0.371 agents=468 avg_r=2.9619 sum_r=758.24 x<0=0.08 elig=0.63 dorfler_tail=0.07 floor=0 sel=26 7.3s
|
|
147/401 | loss=1.0488 ev=0.490 agents=34 avg_r=4.6683 sum_r=1195.08 x<0=0.09 elig=0.63 dorfler_tail=0.07 floor=0 sel=29 7.8s
|
|
148/401 | loss=1.0228 ev=0.425 agents=199 avg_r=3.9396 sum_r=1008.54 x<0=0.10 elig=0.63 dorfler_tail=0.07 floor=0 sel=30 7.6s
|
|
149/401 | loss=1.1164 ev=0.460 agents=34 avg_r=5.2988 sum_r=1356.48 x<0=0.11 elig=0.63 dorfler_tail=0.08 floor=0 sel=29 7.8s
|
|
150/401 | loss=1.2006 ev=0.420 agents=224 avg_r=4.6276 sum_r=1184.65 x<0=0.14 elig=0.63 dorfler_tail=0.07 floor=0 sel=28 7.6s
|
|
[Checkpoint] saved → checkpoints/model_iter0150.pt
|
|
151/401 | loss=1.1592 ev=0.461 agents=219 avg_r=3.2275 sum_r=826.23 x<0=0.14 elig=0.64 dorfler_tail=0.07 floor=0 sel=26 7.3s
|
|
152/401 | loss=1.1567 ev=0.491 agents=66 avg_r=5.4326 sum_r=1390.76 x<0=0.13 elig=0.64 dorfler_tail=0.07 floor=0 sel=32 8.1s
|
|
153/401 | loss=1.0849 ev=0.410 agents=44 avg_r=3.2665 sum_r=836.23 x<0=0.13 elig=0.63 dorfler_tail=0.07 floor=0 sel=25 7.2s
|
|
154/401 | loss=1.2139 ev=0.451 agents=144 avg_r=5.5749 sum_r=1427.18 x<0=0.13 elig=0.64 dorfler_tail=0.07 floor=0 sel=30 7.8s
|
|
155/401 | loss=1.2641 ev=0.374 agents=72 avg_r=3.8995 sum_r=998.28 x<0=0.08 elig=0.63 dorfler_tail=0.07 floor=0 sel=29 7.7s
|
|
156/401 | loss=1.1181 ev=0.448 agents=305 avg_r=4.0441 sum_r=1035.29 x<0=0.08 elig=0.63 dorfler_tail=0.07 floor=0 sel=28 7.4s
|
|
157/401 | loss=1.1287 ev=0.426 agents=193 avg_r=5.2623 sum_r=1347.16 x<0=0.09 elig=0.63 dorfler_tail=0.08 floor=0 sel=31 7.9s
|
|
158/401 | loss=1.0094 ev=0.439 agents=112 avg_r=3.9313 sum_r=1006.42 x<0=0.10 elig=0.64 dorfler_tail=0.07 floor=0 sel=27 7.5s
|
|
159/401 | loss=1.2058 ev=0.424 agents=208 avg_r=4.5753 sum_r=1171.28 x<0=0.10 elig=0.63 dorfler_tail=0.07 floor=0 sel=29 7.7s
|
|
160/401 | loss=1.0749 ev=0.436 agents=272 avg_r=4.3559 sum_r=1115.11 x<0=0.10 elig=0.63 dorfler_tail=0.07 floor=0 sel=28 7.6s
|
|
161/401 | loss=1.2113 ev=0.476 agents=157 avg_r=5.9866 sum_r=1532.58 x<0=0.09 elig=0.63 dorfler_tail=0.07 floor=0 sel=30 7.9s
|
|
162/401 | loss=1.2021 ev=0.410 agents=178 avg_r=2.3998 sum_r=614.36 x<0=0.07 elig=0.63 dorfler_tail=0.07 floor=0 sel=27 7.5s
|
|
163/401 | loss=1.2304 ev=0.489 agents=1031 avg_r=4.5909 sum_r=1175.26 x<0=0.08 elig=0.63 dorfler_tail=0.07 floor=0 sel=31 8.3s
|
|
164/401 | loss=1.1285 ev=0.477 agents=932 avg_r=4.0162 sum_r=1028.14 x<0=0.07 elig=0.63 dorfler_tail=0.07 floor=0 sel=29 7.9s
|
|
165/401 | loss=1.2368 ev=0.421 agents=222 avg_r=5.6582 sum_r=1448.51 x<0=0.08 elig=0.64 dorfler_tail=0.07 floor=0 sel=29 7.9s
|
|
166/401 | loss=1.1362 ev=0.451 agents=41 avg_r=4.6464 sum_r=1189.47 x<0=0.05 elig=0.63 dorfler_tail=0.07 floor=0 sel=29 7.7s
|
|
167/401 | loss=1.1229 ev=0.462 agents=562 avg_r=4.0773 sum_r=1043.78 x<0=0.06 elig=0.63 dorfler_tail=0.07 floor=0 sel=30 7.8s
|
|
168/401 | loss=1.1106 ev=0.454 agents=92 avg_r=3.3590 sum_r=859.91 x<0=0.06 elig=0.63 dorfler_tail=0.07 floor=0 sel=27 7.5s
|
|
169/401 | loss=1.1281 ev=0.476 agents=280 avg_r=4.4418 sum_r=1137.09 x<0=0.06 elig=0.63 dorfler_tail=0.07 floor=0 sel=30 7.8s
|
|
170/401 | loss=1.1614 ev=0.480 agents=89 avg_r=5.0368 sum_r=1289.41 x<0=0.07 elig=0.64 dorfler_tail=0.07 floor=0 sel=28 7.7s
|
|
171/401 | loss=1.1519 ev=0.472 agents=798 avg_r=4.8366 sum_r=1238.17 x<0=0.07 elig=0.65 dorfler_tail=0.07 floor=0 sel=28 7.7s
|
|
172/401 | loss=1.1491 ev=0.486 agents=1228 avg_r=3.9325 sum_r=1006.73 x<0=0.06 elig=0.63 dorfler_tail=0.07 floor=0 sel=28 7.5s
|
|
173/401 | loss=1.1892 ev=0.433 agents=34 avg_r=5.7898 sum_r=1482.19 x<0=0.07 elig=0.64 dorfler_tail=0.07 floor=0 sel=31 7.9s
|
|
174/401 | loss=1.2609 ev=0.441 agents=34 avg_r=4.9001 sum_r=1254.42 x<0=0.09 elig=0.64 dorfler_tail=0.07 floor=0 sel=28 7.5s
|
|
175/401 | loss=1.0890 ev=0.490 agents=302 avg_r=4.3919 sum_r=1124.32 x<0=0.09 elig=0.64 dorfler_tail=0.07 floor=0 sel=28 7.4s
|
|
176/401 | loss=1.2669 ev=0.509 agents=413 avg_r=5.4385 sum_r=1392.26 x<0=0.08 elig=0.64 dorfler_tail=0.07 floor=0 sel=29 7.7s
|
|
177/401 | loss=1.1942 ev=0.431 agents=34 avg_r=5.7676 sum_r=1476.51 x<0=0.05 elig=0.63 dorfler_tail=0.07 floor=0 sel=31 7.9s
|
|
178/401 | loss=1.2717 ev=0.397 agents=708 avg_r=3.3482 sum_r=857.14 x<0=0.05 elig=0.63 dorfler_tail=0.07 floor=0 sel=27 7.3s
|
|
179/401 | loss=1.2435 ev=0.422 agents=132 avg_r=4.4943 sum_r=1150.54 x<0=0.05 elig=0.64 dorfler_tail=0.07 floor=0 sel=27 7.6s
|
|
180/401 | loss=1.2206 ev=0.416 agents=1685 avg_r=6.0635 sum_r=1552.26 x<0=0.05 elig=0.63 dorfler_tail=0.07 floor=0 sel=31 7.8s
|
|
181/401 | loss=1.2401 ev=0.426 agents=74 avg_r=4.4630 sum_r=1142.54 x<0=0.03 elig=0.64 dorfler_tail=0.07 floor=0 sel=28 7.6s
|
|
182/401 | loss=1.1143 ev=0.503 agents=101 avg_r=5.8115 sum_r=1487.76 x<0=0.05 elig=0.64 dorfler_tail=0.07 floor=0 sel=27 7.5s
|
|
183/401 | loss=1.1343 ev=0.482 agents=1198 avg_r=4.8445 sum_r=1240.20 x<0=0.05 elig=0.64 dorfler_tail=0.07 floor=0 sel=31 7.9s
|
|
184/401 | loss=1.1171 ev=0.467 agents=146 avg_r=3.7889 sum_r=969.97 x<0=0.05 elig=0.63 dorfler_tail=0.07 floor=0 sel=27 7.4s
|
|
185/401 | loss=1.1019 ev=0.453 agents=55 avg_r=3.1546 sum_r=807.57 x<0=0.04 elig=0.64 dorfler_tail=0.07 floor=0 sel=26 7.3s
|
|
186/401 | loss=1.2893 ev=0.487 agents=241 avg_r=7.1095 sum_r=1820.03 x<0=0.05 elig=0.64 dorfler_tail=0.07 floor=0 sel=30 7.8s
|
|
187/401 | loss=1.2431 ev=0.484 agents=1392 avg_r=4.2931 sum_r=1099.02 x<0=0.03 elig=0.64 dorfler_tail=0.07 floor=0 sel=30 8.2s
|
|
188/401 | loss=1.2041 ev=0.489 agents=371 avg_r=4.5463 sum_r=1163.85 x<0=0.03 elig=0.63 dorfler_tail=0.07 floor=0 sel=30 8.0s
|
|
189/401 | loss=1.1026 ev=0.500 agents=84 avg_r=5.3215 sum_r=1362.30 x<0=0.04 elig=0.64 dorfler_tail=0.07 floor=0 sel=29 7.8s
|
|
190/401 | loss=1.1617 ev=0.490 agents=1313 avg_r=3.7937 sum_r=971.19 x<0=0.04 elig=0.64 dorfler_tail=0.07 floor=0 sel=27 7.6s
|
|
191/401 | loss=1.2295 ev=0.445 agents=92 avg_r=5.4176 sum_r=1386.91 x<0=0.04 elig=0.64 dorfler_tail=0.07 floor=0 sel=28 7.7s
|
|
192/401 | loss=1.1866 ev=0.459 agents=101 avg_r=4.6249 sum_r=1183.98 x<0=0.03 elig=0.64 dorfler_tail=0.07 floor=0 sel=30 7.8s
|
|
193/401 | loss=1.1729 ev=0.450 agents=85 avg_r=4.5923 sum_r=1175.63 x<0=0.03 elig=0.64 dorfler_tail=0.07 floor=0 sel=29 7.6s
|
|
194/401 | loss=1.1481 ev=0.475 agents=144 avg_r=3.5323 sum_r=904.26 x<0=0.03 elig=0.64 dorfler_tail=0.07 floor=0 sel=29 7.7s
|
|
195/401 | loss=1.0329 ev=0.503 agents=452 avg_r=5.7863 sum_r=1481.30 x<0=0.02 elig=0.64 dorfler_tail=0.07 floor=0 sel=27 7.5s
|
|
196/401 | loss=1.1833 ev=0.481 agents=80 avg_r=5.2709 sum_r=1349.34 x<0=0.04 elig=0.64 dorfler_tail=0.07 floor=0 sel=30 7.7s
|
|
197/401 | loss=1.0276 ev=0.526 agents=345 avg_r=4.4862 sum_r=1148.48 x<0=0.04 elig=0.64 dorfler_tail=0.07 floor=0 sel=27 7.4s
|
|
198/401 | loss=1.1872 ev=0.502 agents=112 avg_r=4.0325 sum_r=1032.33 x<0=0.04 elig=0.64 dorfler_tail=0.07 floor=0 sel=31 7.8s
|
|
199/401 | loss=1.1178 ev=0.506 agents=55 avg_r=5.9643 sum_r=1526.87 x<0=0.04 elig=0.64 dorfler_tail=0.07 floor=0 sel=30 7.8s
|
|
200/401 | loss=1.1306 ev=0.477 agents=383 avg_r=3.5642 sum_r=912.45 x<0=0.03 elig=0.64 dorfler_tail=0.07 floor=0 sel=28 7.5s
|
|
[Checkpoint] saved → checkpoints/model_iter0200.pt
|
|
201/401 | loss=1.2014 ev=0.489 agents=358 avg_r=4.1907 sum_r=1072.82 x<0=0.04 elig=0.64 dorfler_tail=0.07 floor=0 sel=28 7.6s
|
|
202/401 | loss=1.0706 ev=0.486 agents=1012 avg_r=6.4612 sum_r=1654.08 x<0=0.03 elig=0.64 dorfler_tail=0.07 floor=0 sel=31 7.9s
|
|
203/401 | loss=1.1745 ev=0.434 agents=112 avg_r=4.4139 sum_r=1129.95 x<0=0.03 elig=0.64 dorfler_tail=0.07 floor=0 sel=29 7.7s
|
|
204/401 | loss=1.1475 ev=0.441 agents=66 avg_r=2.0276 sum_r=519.07 x<0=0.03 elig=0.63 dorfler_tail=0.07 floor=0 sel=27 7.3s
|
|
205/401 | loss=1.2463 ev=0.448 agents=608 avg_r=4.3842 sum_r=1122.34 x<0=0.02 elig=0.64 dorfler_tail=0.07 floor=0 sel=29 7.7s
|
|
206/401 | loss=1.0930 ev=0.507 agents=199 avg_r=3.6852 sum_r=943.42 x<0=0.04 elig=0.63 dorfler_tail=0.07 floor=0 sel=28 7.4s
|
|
207/401 | loss=1.0337 ev=0.492 agents=78 avg_r=5.9192 sum_r=1515.31 x<0=0.04 elig=0.63 dorfler_tail=0.08 floor=0 sel=31 7.9s
|
|
208/401 | loss=1.0812 ev=0.511 agents=239 avg_r=2.7268 sum_r=698.05 x<0=0.03 elig=0.64 dorfler_tail=0.07 floor=0 sel=28 7.5s
|
|
209/401 | loss=1.1193 ev=0.488 agents=290 avg_r=4.8390 sum_r=1238.78 x<0=0.03 elig=0.63 dorfler_tail=0.08 floor=0 sel=31 8.3s
|
|
210/401 | loss=1.0216 ev=0.512 agents=560 avg_r=4.4400 sum_r=1136.65 x<0=0.04 elig=0.64 dorfler_tail=0.07 floor=0 sel=27 7.8s
|
|
211/401 | loss=1.1425 ev=0.489 agents=82 avg_r=4.0555 sum_r=1038.20 x<0=0.04 elig=0.63 dorfler_tail=0.08 floor=0 sel=30 8.0s
|
|
212/401 | loss=1.0860 ev=0.510 agents=159 avg_r=3.0865 sum_r=790.16 x<0=0.02 elig=0.63 dorfler_tail=0.07 floor=0 sel=30 7.9s
|
|
213/401 | loss=1.1143 ev=0.461 agents=466 avg_r=4.2296 sum_r=1082.79 x<0=0.04 elig=0.63 dorfler_tail=0.07 floor=0 sel=29 7.7s
|
|
214/401 | loss=1.1696 ev=0.455 agents=594 avg_r=3.4831 sum_r=891.68 x<0=0.03 elig=0.63 dorfler_tail=0.07 floor=0 sel=30 7.9s
|
|
215/401 | loss=0.9946 ev=0.541 agents=34 avg_r=4.5702 sum_r=1169.98 x<0=0.05 elig=0.62 dorfler_tail=0.08 floor=0 sel=28 7.7s
|
|
216/401 | loss=0.9747 ev=0.476 agents=118 avg_r=1.9068 sum_r=488.14 x<0=0.03 elig=0.63 dorfler_tail=0.07 floor=0 sel=27 7.4s
|
|
217/401 | loss=1.0586 ev=0.485 agents=463 avg_r=4.5953 sum_r=1176.40 x<0=0.03 elig=0.63 dorfler_tail=0.08 floor=0 sel=32 8.0s
|
|
218/401 | loss=0.9961 ev=0.517 agents=782 avg_r=4.2842 sum_r=1096.75 x<0=0.02 elig=0.62 dorfler_tail=0.08 floor=0 sel=31 7.8s
|
|
219/401 | loss=0.9959 ev=0.509 agents=455 avg_r=3.9179 sum_r=1002.98 x<0=0.03 elig=0.62 dorfler_tail=0.07 floor=0 sel=27 7.4s
|
|
220/401 | loss=1.0537 ev=0.484 agents=104 avg_r=3.2154 sum_r=823.14 x<0=0.02 elig=0.63 dorfler_tail=0.07 floor=0 sel=32 8.0s
|
|
221/401 | loss=1.0243 ev=0.528 agents=367 avg_r=3.3715 sum_r=863.11 x<0=0.03 elig=0.62 dorfler_tail=0.08 floor=0 sel=28 7.4s
|
|
222/401 | loss=1.0120 ev=0.533 agents=244 avg_r=3.1987 sum_r=818.87 x<0=0.02 elig=0.63 dorfler_tail=0.07 floor=0 sel=30 7.8s
|
|
223/401 | loss=1.0247 ev=0.525 agents=544 avg_r=4.3206 sum_r=1106.08 x<0=0.02 elig=0.62 dorfler_tail=0.07 floor=0 sel=29 7.5s
|
|
224/401 | loss=1.1590 ev=0.478 agents=86 avg_r=4.5344 sum_r=1160.79 x<0=0.04 elig=0.64 dorfler_tail=0.07 floor=0 sel=29 7.7s
|
|
225/401 | loss=1.2170 ev=0.509 agents=154 avg_r=2.9427 sum_r=753.34 x<0=0.02 elig=0.64 dorfler_tail=0.07 floor=0 sel=28 7.5s
|
|
226/401 | loss=1.0551 ev=0.507 agents=688 avg_r=4.8525 sum_r=1242.24 x<0=0.02 elig=0.63 dorfler_tail=0.07 floor=0 sel=29 7.6s
|
|
227/401 | loss=1.0929 ev=0.495 agents=1389 avg_r=3.4812 sum_r=891.19 x<0=0.03 elig=0.64 dorfler_tail=0.07 floor=0 sel=28 7.5s
|
|
228/401 | loss=1.0829 ev=0.484 agents=552 avg_r=4.0013 sum_r=1024.33 x<0=0.02 elig=0.62 dorfler_tail=0.08 floor=0 sel=32 7.8s
|
|
229/401 | loss=1.0821 ev=0.543 agents=537 avg_r=4.6780 sum_r=1197.58 x<0=0.03 elig=0.64 dorfler_tail=0.07 floor=0 sel=27 7.4s
|
|
230/401 | loss=1.0237 ev=0.517 agents=245 avg_r=4.9465 sum_r=1266.29 x<0=0.02 elig=0.63 dorfler_tail=0.08 floor=0 sel=30 7.8s
|
|
231/401 | loss=0.9584 ev=0.520 agents=80 avg_r=3.6329 sum_r=930.02 x<0=0.03 elig=0.63 dorfler_tail=0.07 floor=0 sel=28 7.5s
|
|
232/401 | loss=1.0787 ev=0.525 agents=34 avg_r=3.9045 sum_r=999.56 x<0=0.02 elig=0.63 dorfler_tail=0.07 floor=0 sel=30 7.9s
|
|
233/401 | loss=0.9447 ev=0.450 agents=78 avg_r=1.3955 sum_r=357.24 x<0=0.02 elig=0.62 dorfler_tail=0.07 floor=0 sel=26 7.9s
|
|
234/401 | loss=0.9411 ev=0.544 agents=1678 avg_r=4.2359 sum_r=1084.38 x<0=0.02 elig=0.62 dorfler_tail=0.08 floor=0 sel=33 8.5s
|
|
235/401 | loss=1.0497 ev=0.498 agents=1671 avg_r=2.7100 sum_r=693.76 x<0=0.02 elig=0.62 dorfler_tail=0.07 floor=0 sel=27 7.6s
|
|
236/401 | loss=1.0309 ev=0.519 agents=34 avg_r=5.2648 sum_r=1347.78 x<0=0.02 elig=0.63 dorfler_tail=0.08 floor=0 sel=32 8.2s
|
|
237/401 | loss=1.0213 ev=0.455 agents=89 avg_r=2.4790 sum_r=634.62 x<0=0.03 elig=0.63 dorfler_tail=0.07 floor=0 sel=26 7.2s
|
|
238/401 | loss=0.9939 ev=0.543 agents=197 avg_r=4.4294 sum_r=1133.92 x<0=0.03 elig=0.62 dorfler_tail=0.08 floor=0 sel=31 8.0s
|
|
239/401 | loss=0.9712 ev=0.480 agents=764 avg_r=1.1436 sum_r=292.76 x<0=0.02 elig=0.62 dorfler_tail=0.08 floor=0 sel=30 7.6s
|
|
240/401 | loss=1.0520 ev=0.520 agents=98 avg_r=3.5913 sum_r=919.36 x<0=0.02 elig=0.63 dorfler_tail=0.08 floor=0 sel=29 7.7s
|
|
241/401 | loss=1.0733 ev=0.529 agents=242 avg_r=3.8688 sum_r=990.40 x<0=0.03 elig=0.63 dorfler_tail=0.07 floor=0 sel=30 7.9s
|
|
242/401 | loss=0.9550 ev=0.471 agents=334 avg_r=1.7380 sum_r=444.92 x<0=0.03 elig=0.62 dorfler_tail=0.08 floor=0 sel=28 7.4s
|
|
243/401 | loss=1.0333 ev=0.485 agents=219 avg_r=2.4626 sum_r=630.44 x<0=0.04 elig=0.62 dorfler_tail=0.08 floor=0 sel=30 7.7s
|
|
244/401 | loss=0.9276 ev=0.522 agents=34 avg_r=3.0563 sum_r=782.41 x<0=0.04 elig=0.62 dorfler_tail=0.07 floor=0 sel=29 7.7s
|
|
245/401 | loss=0.9300 ev=0.556 agents=707 avg_r=3.2084 sum_r=821.35 x<0=0.04 elig=0.62 dorfler_tail=0.08 floor=0 sel=31 7.8s
|
|
246/401 | loss=0.9332 ev=0.523 agents=90 avg_r=2.4516 sum_r=627.62 x<0=0.03 elig=0.62 dorfler_tail=0.07 floor=0 sel=29 7.6s
|
|
247/401 | loss=0.8789 ev=0.527 agents=34 avg_r=2.0551 sum_r=526.11 x<0=0.04 elig=0.62 dorfler_tail=0.08 floor=0 sel=29 7.7s
|
|
248/401 | loss=0.9587 ev=0.532 agents=81 avg_r=3.7530 sum_r=960.77 x<0=0.04 elig=0.61 dorfler_tail=0.08 floor=0 sel=29 7.6s
|
|
249/401 | loss=0.9774 ev=0.505 agents=431 avg_r=2.2023 sum_r=563.78 x<0=0.03 elig=0.61 dorfler_tail=0.08 floor=0 sel=31 7.8s
|
|
250/401 | loss=0.9413 ev=0.535 agents=299 avg_r=3.2959 sum_r=843.75 x<0=0.04 elig=0.62 dorfler_tail=0.08 floor=0 sel=30 7.9s
|
|
[Checkpoint] saved → checkpoints/model_iter0250.pt
|
|
251/401 | loss=0.8520 ev=0.529 agents=179 avg_r=1.5290 sum_r=391.43 x<0=0.03 elig=0.61 dorfler_tail=0.08 floor=0 sel=28 7.4s
|
|
252/401 | loss=0.9216 ev=0.545 agents=1237 avg_r=3.0161 sum_r=772.13 x<0=0.04 elig=0.62 dorfler_tail=0.07 floor=0 sel=30 7.7s
|
|
253/401 | loss=0.9574 ev=0.523 agents=34 avg_r=2.6567 sum_r=680.11 x<0=0.05 elig=0.62 dorfler_tail=0.08 floor=0 sel=29 7.6s
|
|
254/401 | loss=0.8550 ev=0.545 agents=438 avg_r=3.3394 sum_r=854.87 x<0=0.04 elig=0.62 dorfler_tail=0.08 floor=0 sel=30 7.7s
|
|
255/401 | loss=0.9844 ev=0.498 agents=1420 avg_r=2.4418 sum_r=625.11 x<0=0.06 elig=0.61 dorfler_tail=0.07 floor=0 sel=29 7.9s
|
|
256/401 | loss=0.9256 ev=0.573 agents=571 avg_r=5.8027 sum_r=1485.49 x<0=0.05 elig=0.62 dorfler_tail=0.08 floor=0 sel=31 8.5s
|
|
257/401 | loss=0.9898 ev=0.483 agents=95 avg_r=1.5702 sum_r=401.96 x<0=0.04 elig=0.62 dorfler_tail=0.08 floor=0 sel=29 7.7s
|
|
258/401 | loss=0.9519 ev=0.534 agents=199 avg_r=2.4135 sum_r=617.85 x<0=0.05 elig=0.62 dorfler_tail=0.08 floor=0 sel=28 7.7s
|
|
259/401 | loss=0.8724 ev=0.542 agents=235 avg_r=4.1436 sum_r=1060.77 x<0=0.04 elig=0.62 dorfler_tail=0.08 floor=0 sel=31 8.0s
|
|
260/401 | loss=0.9030 ev=0.547 agents=306 avg_r=3.4969 sum_r=895.20 x<0=0.03 elig=0.62 dorfler_tail=0.08 floor=0 sel=30 8.0s
|
|
261/401 | loss=0.8940 ev=0.553 agents=278 avg_r=1.2701 sum_r=325.14 x<0=0.03 elig=0.62 dorfler_tail=0.08 floor=0 sel=29 7.7s
|
|
262/401 | loss=0.9520 ev=0.522 agents=247 avg_r=2.2571 sum_r=577.81 x<0=0.05 elig=0.62 dorfler_tail=0.07 floor=0 sel=26 7.2s
|
|
263/401 | loss=0.9901 ev=0.538 agents=34 avg_r=3.7187 sum_r=952.00 x<0=0.05 elig=0.62 dorfler_tail=0.08 floor=0 sel=31 7.9s
|
|
264/401 | loss=0.8780 ev=0.551 agents=210 avg_r=2.6562 sum_r=680.00 x<0=0.03 elig=0.62 dorfler_tail=0.08 floor=0 sel=30 7.8s
|
|
265/401 | loss=0.9646 ev=0.551 agents=1333 avg_r=2.6470 sum_r=677.63 x<0=0.07 elig=0.63 dorfler_tail=0.08 floor=0 sel=26 7.3s
|
|
266/401 | loss=0.8954 ev=0.553 agents=1474 avg_r=4.4314 sum_r=1134.44 x<0=0.05 elig=0.62 dorfler_tail=0.08 floor=0 sel=34 8.4s
|
|
267/401 | loss=0.9252 ev=0.547 agents=219 avg_r=1.3921 sum_r=356.39 x<0=0.07 elig=0.62 dorfler_tail=0.08 floor=0 sel=28 7.5s
|
|
268/401 | loss=0.9428 ev=0.529 agents=448 avg_r=2.0273 sum_r=518.98 x<0=0.08 elig=0.62 dorfler_tail=0.08 floor=0 sel=28 7.5s
|
|
269/401 | loss=1.0055 ev=0.512 agents=119 avg_r=3.3292 sum_r=852.28 x<0=0.06 elig=0.61 dorfler_tail=0.08 floor=0 sel=30 7.7s
|
|
270/401 | loss=0.8147 ev=0.546 agents=713 avg_r=2.1123 sum_r=540.76 x<0=0.08 elig=0.62 dorfler_tail=0.08 floor=0 sel=27 7.5s
|
|
271/401 | loss=0.8906 ev=0.516 agents=283 avg_r=1.6996 sum_r=435.11 x<0=0.10 elig=0.61 dorfler_tail=0.08 floor=0 sel=30 7.6s
|
|
272/401 | loss=0.8740 ev=0.539 agents=615 avg_r=2.0937 sum_r=536.00 x<0=0.09 elig=0.61 dorfler_tail=0.08 floor=0 sel=29 7.6s
|
|
273/401 | loss=0.8926 ev=0.534 agents=148 avg_r=3.3738 sum_r=863.69 x<0=0.06 elig=0.62 dorfler_tail=0.08 floor=0 sel=31 8.0s
|
|
274/401 | loss=0.9262 ev=0.517 agents=1373 avg_r=1.4594 sum_r=373.60 x<0=0.10 elig=0.61 dorfler_tail=0.08 floor=0 sel=27 7.4s
|
|
275/401 | loss=0.8819 ev=0.544 agents=534 avg_r=3.1571 sum_r=808.21 x<0=0.06 elig=0.62 dorfler_tail=0.08 floor=0 sel=30 7.7s
|
|
276/401 | loss=0.9410 ev=0.555 agents=197 avg_r=1.4638 sum_r=374.73 x<0=0.06 elig=0.62 dorfler_tail=0.08 floor=0 sel=29 7.6s
|
|
277/401 | loss=0.9281 ev=0.544 agents=461 avg_r=3.8103 sum_r=975.44 x<0=0.06 elig=0.62 dorfler_tail=0.08 floor=0 sel=30 8.2s
|
|
278/401 | loss=0.9413 ev=0.482 agents=132 avg_r=0.8562 sum_r=219.19 x<0=0.07 elig=0.61 dorfler_tail=0.08 floor=0 sel=27 7.6s
|
|
279/401 | loss=1.0616 ev=0.511 agents=387 avg_r=2.8525 sum_r=730.25 x<0=0.04 elig=0.62 dorfler_tail=0.08 floor=0 sel=32 8.2s
|
|
280/401 | loss=0.8064 ev=0.565 agents=34 avg_r=2.3635 sum_r=605.05 x<0=0.08 elig=0.61 dorfler_tail=0.08 floor=0 sel=30 8.0s
|
|
281/401 | loss=0.9595 ev=0.516 agents=42 avg_r=1.2882 sum_r=329.77 x<0=0.08 elig=0.61 dorfler_tail=0.08 floor=0 sel=28 7.7s
|
|
282/401 | loss=0.8745 ev=0.544 agents=212 avg_r=2.6701 sum_r=683.56 x<0=0.08 elig=0.62 dorfler_tail=0.08 floor=0 sel=30 7.8s
|
|
283/401 | loss=0.8034 ev=0.556 agents=700 avg_r=1.2154 sum_r=311.15 x<0=0.09 elig=0.61 dorfler_tail=0.08 floor=0 sel=28 7.6s
|
|
284/401 | loss=0.9041 ev=0.526 agents=165 avg_r=3.3568 sum_r=859.33 x<0=0.09 elig=0.61 dorfler_tail=0.08 floor=0 sel=31 7.9s
|
|
285/401 | loss=0.8815 ev=0.556 agents=92 avg_r=3.1372 sum_r=803.13 x<0=0.10 elig=0.61 dorfler_tail=0.08 floor=0 sel=29 7.7s
|
|
286/401 | loss=0.8307 ev=0.536 agents=118 avg_r=1.5978 sum_r=409.03 x<0=0.06 elig=0.61 dorfler_tail=0.08 floor=0 sel=28 7.6s
|
|
287/401 | loss=0.8403 ev=0.562 agents=423 avg_r=2.7292 sum_r=698.68 x<0=0.10 elig=0.62 dorfler_tail=0.08 floor=0 sel=29 7.8s
|
|
288/401 | loss=0.9074 ev=0.520 agents=169 avg_r=3.6068 sum_r=923.33 x<0=0.07 elig=0.62 dorfler_tail=0.08 floor=0 sel=32 7.9s
|
|
289/401 | loss=0.9122 ev=0.561 agents=206 avg_r=2.3035 sum_r=589.70 x<0=0.07 elig=0.62 dorfler_tail=0.08 floor=0 sel=29 7.6s
|
|
290/401 | loss=0.9271 ev=0.523 agents=472 avg_r=1.9889 sum_r=509.16 x<0=0.12 elig=0.61 dorfler_tail=0.08 floor=0 sel=28 7.5s
|
|
291/401 | loss=0.8706 ev=0.563 agents=811 avg_r=2.7751 sum_r=710.43 x<0=0.10 elig=0.61 dorfler_tail=0.08 floor=0 sel=30 7.8s
|
|
292/401 | loss=0.9530 ev=0.524 agents=80 avg_r=2.5786 sum_r=660.13 x<0=0.11 elig=0.62 dorfler_tail=0.08 floor=0 sel=27 7.4s
|
|
293/401 | loss=0.8116 ev=0.540 agents=154 avg_r=0.2428 sum_r=62.17 x<0=0.11 elig=0.61 dorfler_tail=0.07 floor=0 sel=28 7.3s
|
|
294/401 | loss=0.9140 ev=0.518 agents=175 avg_r=2.3269 sum_r=595.68 x<0=0.09 elig=0.61 dorfler_tail=0.08 floor=0 sel=30 7.8s
|
|
295/401 | loss=0.8169 ev=0.527 agents=220 avg_r=3.0412 sum_r=778.55 x<0=0.10 elig=0.60 dorfler_tail=0.08 floor=0 sel=29 7.6s
|
|
296/401 | loss=0.8810 ev=0.542 agents=1189 avg_r=2.2746 sum_r=582.29 x<0=0.14 elig=0.62 dorfler_tail=0.08 floor=0 sel=29 7.7s
|
|
297/401 | loss=0.8664 ev=0.514 agents=120 avg_r=2.9741 sum_r=761.37 x<0=0.11 elig=0.61 dorfler_tail=0.08 floor=0 sel=29 7.6s
|
|
298/401 | loss=0.7806 ev=0.525 agents=399 avg_r=1.6251 sum_r=416.02 x<0=0.11 elig=0.60 dorfler_tail=0.09 floor=0 sel=32 7.6s
|
|
299/401 | loss=0.7862 ev=0.541 agents=253 avg_r=0.9686 sum_r=247.97 x<0=0.16 elig=0.61 dorfler_tail=0.08 floor=0 sel=27 7.2s
|
|
300/401 | loss=0.8033 ev=0.530 agents=400 avg_r=1.6370 sum_r=419.07 x<0=0.10 elig=0.60 dorfler_tail=0.09 floor=0 sel=34 8.1s
|
|
[Checkpoint] saved → checkpoints/model_iter0300.pt
|
|
301/401 | loss=0.6913 ev=0.558 agents=86 avg_r=2.2967 sum_r=587.97 x<0=0.17 elig=0.61 dorfler_tail=0.08 floor=0 sel=27 7.8s
|
|
302/401 | loss=0.8170 ev=0.548 agents=581 avg_r=0.8235 sum_r=210.82 x<0=0.15 elig=0.60 dorfler_tail=0.08 floor=0 sel=30 7.8s
|
|
303/401 | loss=0.6984 ev=0.563 agents=1661 avg_r=-0.4295 sum_r=-109.96 x<0=0.16 elig=0.60 dorfler_tail=0.08 floor=0 sel=29 7.6s
|
|
304/401 | loss=0.7311 ev=0.548 agents=224 avg_r=0.8700 sum_r=222.71 x<0=0.14 elig=0.60 dorfler_tail=0.08 floor=0 sel=30 7.7s
|
|
305/401 | loss=0.7374 ev=0.523 agents=36 avg_r=1.8769 sum_r=480.49 x<0=0.18 elig=0.60 dorfler_tail=0.08 floor=0 sel=28 7.4s
|
|
306/401 | loss=0.7575 ev=0.528 agents=34 avg_r=0.2656 sum_r=67.99 x<0=0.12 elig=0.60 dorfler_tail=0.09 floor=0 sel=32 7.8s
|
|
307/401 | loss=0.7143 ev=0.558 agents=383 avg_r=1.9704 sum_r=504.43 x<0=0.15 elig=0.60 dorfler_tail=0.08 floor=0 sel=33 7.7s
|
|
308/401 | loss=0.6706 ev=0.578 agents=354 avg_r=1.0502 sum_r=268.85 x<0=0.16 elig=0.60 dorfler_tail=0.08 floor=0 sel=28 7.3s
|
|
309/401 | loss=0.7886 ev=0.535 agents=658 avg_r=0.7953 sum_r=203.59 x<0=0.16 elig=0.60 dorfler_tail=0.08 floor=0 sel=29 7.6s
|
|
310/401 | loss=0.7315 ev=0.544 agents=101 avg_r=2.9009 sum_r=742.62 x<0=0.15 elig=0.60 dorfler_tail=0.08 floor=0 sel=29 7.6s
|
|
311/401 | loss=0.8253 ev=0.511 agents=133 avg_r=-0.0058 sum_r=-1.49 x<0=0.14 elig=0.61 dorfler_tail=0.08 floor=0 sel=30 7.6s
|
|
312/401 | loss=0.7325 ev=0.559 agents=710 avg_r=1.4958 sum_r=382.94 x<0=0.17 elig=0.60 dorfler_tail=0.08 floor=0 sel=28 7.3s
|
|
313/401 | loss=0.7200 ev=0.561 agents=815 avg_r=2.1457 sum_r=549.29 x<0=0.14 elig=0.60 dorfler_tail=0.08 floor=0 sel=31 7.8s
|
|
314/401 | loss=0.7983 ev=0.533 agents=112 avg_r=2.3176 sum_r=593.31 x<0=0.19 elig=0.60 dorfler_tail=0.08 floor=0 sel=31 7.6s
|
|
315/401 | loss=0.7438 ev=0.549 agents=1189 avg_r=0.7720 sum_r=197.64 x<0=0.14 elig=0.60 dorfler_tail=0.08 floor=0 sel=29 7.4s
|
|
316/401 | loss=0.7035 ev=0.572 agents=255 avg_r=1.6356 sum_r=418.72 x<0=0.14 elig=0.60 dorfler_tail=0.08 floor=0 sel=29 7.4s
|
|
317/401 | loss=0.7101 ev=0.532 agents=34 avg_r=3.0508 sum_r=781.01 x<0=0.14 elig=0.61 dorfler_tail=0.07 floor=0 sel=29 7.6s
|
|
318/401 | loss=0.8912 ev=0.501 agents=355 avg_r=1.0975 sum_r=280.95 x<0=0.19 elig=0.60 dorfler_tail=0.08 floor=0 sel=30 7.5s
|
|
319/401 | loss=0.7239 ev=0.544 agents=248 avg_r=1.5235 sum_r=390.01 x<0=0.15 elig=0.60 dorfler_tail=0.08 floor=0 sel=30 7.5s
|
|
320/401 | loss=0.7092 ev=0.565 agents=925 avg_r=1.4157 sum_r=362.42 x<0=0.16 elig=0.60 dorfler_tail=0.08 floor=0 sel=29 7.4s
|
|
321/401 | loss=0.7461 ev=0.514 agents=311 avg_r=0.2240 sum_r=57.35 x<0=0.14 elig=0.61 dorfler_tail=0.08 floor=0 sel=28 7.2s
|
|
322/401 | loss=0.7413 ev=0.558 agents=963 avg_r=2.1983 sum_r=562.76 x<0=0.15 elig=0.60 dorfler_tail=0.08 floor=0 sel=31 7.7s
|
|
323/401 | loss=0.7404 ev=0.539 agents=564 avg_r=-0.1535 sum_r=-39.29 x<0=0.14 elig=0.60 dorfler_tail=0.08 floor=0 sel=28 7.6s
|
|
324/401 | loss=0.7739 ev=0.520 agents=377 avg_r=2.4348 sum_r=623.30 x<0=0.17 elig=0.60 dorfler_tail=0.08 floor=0 sel=31 7.9s
|
|
325/401 | loss=0.7664 ev=0.514 agents=92 avg_r=-0.3153 sum_r=-80.72 x<0=0.16 elig=0.60 dorfler_tail=0.08 floor=0 sel=29 7.6s
|
|
326/401 | loss=0.6448 ev=0.571 agents=1442 avg_r=2.9909 sum_r=765.66 x<0=0.17 elig=0.60 dorfler_tail=0.08 floor=0 sel=31 7.7s
|
|
327/401 | loss=0.7037 ev=0.571 agents=1470 avg_r=1.2222 sum_r=312.89 x<0=0.13 elig=0.59 dorfler_tail=0.09 floor=0 sel=28 7.4s
|
|
328/401 | loss=0.6932 ev=0.561 agents=301 avg_r=0.1858 sum_r=47.56 x<0=0.18 elig=0.61 dorfler_tail=0.08 floor=0 sel=27 7.3s
|
|
329/401 | loss=0.7244 ev=0.546 agents=72 avg_r=0.3477 sum_r=89.02 x<0=0.17 elig=0.60 dorfler_tail=0.08 floor=0 sel=30 7.5s
|
|
330/401 | loss=0.7251 ev=0.550 agents=415 avg_r=1.7594 sum_r=450.41 x<0=0.15 elig=0.60 dorfler_tail=0.08 floor=0 sel=30 7.5s
|
|
331/401 | loss=0.6579 ev=0.571 agents=1310 avg_r=0.9986 sum_r=255.65 x<0=0.15 elig=0.60 dorfler_tail=0.08 floor=0 sel=30 7.6s
|
|
332/401 | loss=0.6545 ev=0.573 agents=221 avg_r=0.5318 sum_r=136.14 x<0=0.18 elig=0.59 dorfler_tail=0.08 floor=0 sel=30 7.4s
|
|
333/401 | loss=0.6258 ev=0.555 agents=112 avg_r=2.1892 sum_r=560.44 x<0=0.14 elig=0.60 dorfler_tail=0.08 floor=0 sel=30 7.5s
|
|
334/401 | loss=0.6942 ev=0.558 agents=97 avg_r=-0.7035 sum_r=-180.09 x<0=0.13 elig=0.59 dorfler_tail=0.08 floor=0 sel=27 7.1s
|
|
335/401 | loss=0.7479 ev=0.497 agents=761 avg_r=1.5436 sum_r=395.16 x<0=0.13 elig=0.60 dorfler_tail=0.08 floor=0 sel=29 7.4s
|
|
336/401 | loss=0.6501 ev=0.602 agents=34 avg_r=1.0316 sum_r=264.09 x<0=0.14 elig=0.59 dorfler_tail=0.08 floor=0 sel=30 7.3s
|
|
337/401 | loss=0.6053 ev=0.583 agents=428 avg_r=-0.0724 sum_r=-18.53 x<0=0.13 elig=0.59 dorfler_tail=0.08 floor=0 sel=31 7.4s
|
|
338/401 | loss=0.6485 ev=0.555 agents=34 avg_r=1.4593 sum_r=373.58 x<0=0.10 elig=0.59 dorfler_tail=0.08 floor=0 sel=31 7.4s
|
|
339/401 | loss=0.6234 ev=0.577 agents=615 avg_r=2.0301 sum_r=519.70 x<0=0.17 elig=0.60 dorfler_tail=0.08 floor=0 sel=28 7.2s
|
|
340/401 | loss=0.6056 ev=0.551 agents=234 avg_r=-0.4751 sum_r=-121.63 x<0=0.19 elig=0.59 dorfler_tail=0.08 floor=0 sel=29 7.2s
|
|
341/401 | loss=0.5780 ev=0.592 agents=186 avg_r=1.5097 sum_r=386.49 x<0=0.12 elig=0.60 dorfler_tail=0.08 floor=0 sel=31 7.4s
|
|
342/401 | loss=0.6112 ev=0.590 agents=241 avg_r=1.3269 sum_r=339.69 x<0=0.16 elig=0.59 dorfler_tail=0.08 floor=0 sel=29 7.3s
|
|
343/401 | loss=0.7043 ev=0.532 agents=44 avg_r=1.0479 sum_r=268.27 x<0=0.14 elig=0.59 dorfler_tail=0.08 floor=0 sel=31 7.4s
|
|
344/401 | loss=0.6269 ev=0.553 agents=308 avg_r=1.5500 sum_r=396.81 x<0=0.15 elig=0.59 dorfler_tail=0.08 floor=0 sel=30 7.3s
|
|
345/401 | loss=0.5842 ev=0.580 agents=704 avg_r=2.1546 sum_r=551.57 x<0=0.12 elig=0.59 dorfler_tail=0.08 floor=0 sel=29 7.6s
|
|
346/401 | loss=0.6299 ev=0.570 agents=41 avg_r=0.7011 sum_r=179.49 x<0=0.16 elig=0.59 dorfler_tail=0.08 floor=0 sel=33 8.0s
|
|
347/401 | loss=0.6316 ev=0.571 agents=278 avg_r=1.6173 sum_r=414.03 x<0=0.15 elig=0.59 dorfler_tail=0.08 floor=0 sel=28 7.3s
|
|
348/401 | loss=0.6115 ev=0.573 agents=34 avg_r=0.1809 sum_r=46.32 x<0=0.17 elig=0.59 dorfler_tail=0.08 floor=0 sel=29 7.4s
|
|
349/401 | loss=0.6532 ev=0.557 agents=242 avg_r=0.8962 sum_r=229.43 x<0=0.12 elig=0.59 dorfler_tail=0.08 floor=0 sel=31 7.5s
|
|
350/401 | loss=0.6516 ev=0.582 agents=44 avg_r=1.0303 sum_r=263.76 x<0=0.15 elig=0.59 dorfler_tail=0.08 floor=0 sel=31 7.6s
|
|
[Checkpoint] saved → checkpoints/model_iter0350.pt
|
|
351/401 | loss=0.6227 ev=0.554 agents=201 avg_r=0.7558 sum_r=193.50 x<0=0.15 elig=0.59 dorfler_tail=0.08 floor=0 sel=30 7.3s
|
|
352/401 | loss=0.5750 ev=0.605 agents=34 avg_r=0.5050 sum_r=129.29 x<0=0.14 elig=0.58 dorfler_tail=0.08 floor=0 sel=30 7.4s
|
|
353/401 | loss=0.6413 ev=0.544 agents=457 avg_r=0.2005 sum_r=51.32 x<0=0.17 elig=0.60 dorfler_tail=0.07 floor=0 sel=26 6.9s
|
|
354/401 | loss=0.6211 ev=0.589 agents=120 avg_r=2.0601 sum_r=527.38 x<0=0.12 elig=0.59 dorfler_tail=0.08 floor=0 sel=33 7.6s
|
|
355/401 | loss=0.6174 ev=0.574 agents=34 avg_r=1.1792 sum_r=301.88 x<0=0.15 elig=0.59 dorfler_tail=0.08 floor=0 sel=30 7.3s
|
|
356/401 | loss=0.6271 ev=0.563 agents=267 avg_r=0.9035 sum_r=231.30 x<0=0.15 elig=0.59 dorfler_tail=0.08 floor=0 sel=31 7.4s
|
|
357/401 | loss=0.6969 ev=0.569 agents=34 avg_r=-0.5932 sum_r=-151.87 x<0=0.14 elig=0.59 dorfler_tail=0.08 floor=0 sel=31 7.4s
|
|
358/401 | loss=0.6315 ev=0.543 agents=34 avg_r=0.1535 sum_r=39.30 x<0=0.15 elig=0.59 dorfler_tail=0.08 floor=0 sel=31 7.4s
|
|
359/401 | loss=0.5787 ev=0.598 agents=64 avg_r=-0.8402 sum_r=-215.10 x<0=0.10 elig=0.59 dorfler_tail=0.08 floor=0 sel=30 7.3s
|
|
360/401 | loss=0.6417 ev=0.555 agents=174 avg_r=0.4168 sum_r=106.70 x<0=0.19 elig=0.59 dorfler_tail=0.08 floor=0 sel=31 7.4s
|
|
361/401 | loss=0.6239 ev=0.563 agents=210 avg_r=0.3188 sum_r=81.61 x<0=0.13 elig=0.59 dorfler_tail=0.08 floor=0 sel=29 7.2s
|
|
362/401 | loss=0.5985 ev=0.578 agents=1136 avg_r=0.0481 sum_r=12.32 x<0=0.15 elig=0.59 dorfler_tail=0.08 floor=0 sel=30 7.3s
|
|
363/401 | loss=0.5902 ev=0.569 agents=34 avg_r=-0.3036 sum_r=-77.73 x<0=0.15 elig=0.59 dorfler_tail=0.08 floor=0 sel=31 7.4s
|
|
364/401 | loss=0.6606 ev=0.567 agents=147 avg_r=-1.4026 sum_r=-359.07 x<0=0.14 elig=0.59 dorfler_tail=0.08 floor=0 sel=30 7.3s
|
|
365/401 | loss=0.6312 ev=0.553 agents=150 avg_r=0.4739 sum_r=121.33 x<0=0.13 elig=0.59 dorfler_tail=0.08 floor=0 sel=32 7.6s
|
|
366/401 | loss=0.6945 ev=0.551 agents=219 avg_r=-1.1566 sum_r=-296.08 x<0=0.14 elig=0.59 dorfler_tail=0.07 floor=0 sel=27 7.0s
|
|
367/401 | loss=0.5808 ev=0.596 agents=85 avg_r=1.6020 sum_r=410.10 x<0=0.13 elig=0.58 dorfler_tail=0.09 floor=0 sel=32 7.7s
|
|
368/401 | loss=0.6056 ev=0.568 agents=762 avg_r=-1.3623 sum_r=-348.74 x<0=0.12 elig=0.59 dorfler_tail=0.08 floor=0 sel=30 7.7s
|
|
369/401 | loss=0.6481 ev=0.558 agents=177 avg_r=-0.9408 sum_r=-240.85 x<0=0.17 elig=0.59 dorfler_tail=0.08 floor=0 sel=31 7.7s
|
|
370/401 | loss=0.6171 ev=0.589 agents=1015 avg_r=-0.9711 sum_r=-248.60 x<0=0.14 elig=0.59 dorfler_tail=0.08 floor=0 sel=30 7.5s
|
|
371/401 | loss=0.6382 ev=0.581 agents=97 avg_r=-0.9976 sum_r=-255.40 x<0=0.15 elig=0.59 dorfler_tail=0.08 floor=0 sel=30 7.5s
|
|
372/401 | loss=0.6350 ev=0.563 agents=553 avg_r=-2.2484 sum_r=-575.58 x<0=0.14 elig=0.59 dorfler_tail=0.08 floor=0 sel=31 7.5s
|
|
373/401 | loss=0.6417 ev=0.550 agents=83 avg_r=-1.2092 sum_r=-309.56 x<0=0.17 elig=0.59 dorfler_tail=0.09 floor=0 sel=30 7.4s
|
|
374/401 | loss=0.5959 ev=0.596 agents=72 avg_r=-2.0364 sum_r=-521.32 x<0=0.13 elig=0.58 dorfler_tail=0.09 floor=0 sel=34 7.8s
|
|
375/401 | loss=0.5694 ev=0.598 agents=154 avg_r=-0.1396 sum_r=-35.75 x<0=0.17 elig=0.59 dorfler_tail=0.08 floor=0 sel=28 7.3s
|
|
376/401 | loss=0.6582 ev=0.562 agents=141 avg_r=-3.1031 sum_r=-794.39 x<0=0.17 elig=0.59 dorfler_tail=0.08 floor=0 sel=30 7.4s
|
|
377/401 | loss=0.5972 ev=0.597 agents=1262 avg_r=-1.6131 sum_r=-412.95 x<0=0.15 elig=0.58 dorfler_tail=0.09 floor=0 sel=31 7.5s
|
|
378/401 | loss=0.6511 ev=0.595 agents=509 avg_r=-3.4710 sum_r=-888.58 x<0=0.18 elig=0.59 dorfler_tail=0.08 floor=0 sel=30 7.3s
|
|
379/401 | loss=0.6209 ev=0.573 agents=36 avg_r=-2.1022 sum_r=-538.17 x<0=0.14 elig=0.59 dorfler_tail=0.08 floor=0 sel=32 7.6s
|
|
380/401 | loss=0.5629 ev=0.624 agents=600 avg_r=-1.5907 sum_r=-407.23 x<0=0.14 elig=0.58 dorfler_tail=0.09 floor=0 sel=30 7.4s
|
|
381/401 | loss=0.6222 ev=0.572 agents=200 avg_r=-1.0094 sum_r=-258.41 x<0=0.13 elig=0.59 dorfler_tail=0.08 floor=0 sel=31 7.4s
|
|
382/401 | loss=0.6545 ev=0.550 agents=388 avg_r=-3.5082 sum_r=-898.10 x<0=0.23 elig=0.60 dorfler_tail=0.08 floor=0 sel=28 7.2s
|
|
383/401 | loss=0.5294 ev=0.636 agents=85 avg_r=-0.4136 sum_r=-105.88 x<0=0.12 elig=0.58 dorfler_tail=0.09 floor=0 sel=32 7.5s
|
|
384/401 | loss=0.5944 ev=0.579 agents=453 avg_r=-2.0541 sum_r=-525.84 x<0=0.18 elig=0.59 dorfler_tail=0.08 floor=0 sel=30 7.4s
|
|
385/401 | loss=0.6282 ev=0.578 agents=171 avg_r=-1.6239 sum_r=-415.72 x<0=0.17 elig=0.59 dorfler_tail=0.08 floor=0 sel=30 7.3s
|
|
386/401 | loss=0.6290 ev=0.570 agents=561 avg_r=-1.0137 sum_r=-259.51 x<0=0.15 elig=0.59 dorfler_tail=0.08 floor=0 sel=30 7.4s
|
|
387/401 | loss=0.5582 ev=0.611 agents=404 avg_r=-0.5416 sum_r=-138.65 x<0=0.14 elig=0.59 dorfler_tail=0.09 floor=0 sel=31 7.4s
|
|
388/401 | loss=0.5969 ev=0.559 agents=154 avg_r=-5.0462 sum_r=-1291.82 x<0=0.17 elig=0.59 dorfler_tail=0.08 floor=0 sel=28 7.2s
|
|
389/401 | loss=0.6544 ev=0.548 agents=278 avg_r=-1.2462 sum_r=-319.03 x<0=0.18 elig=0.59 dorfler_tail=0.08 floor=0 sel=31 7.4s
|
|
390/401 | loss=0.6538 ev=0.587 agents=856 avg_r=-1.0032 sum_r=-256.82 x<0=0.17 elig=0.58 dorfler_tail=0.08 floor=0 sel=31 7.9s
|
|
391/401 | loss=0.5737 ev=0.593 agents=101 avg_r=-2.4208 sum_r=-619.72 x<0=0.15 elig=0.58 dorfler_tail=0.08 floor=0 sel=31 8.0s
|
|
392/401 | loss=0.5898 ev=0.601 agents=101 avg_r=-1.4010 sum_r=-358.67 x<0=0.19 elig=0.59 dorfler_tail=0.08 floor=0 sel=29 7.5s
|
|
393/401 | loss=0.5977 ev=0.587 agents=219 avg_r=-2.3206 sum_r=-594.07 x<0=0.11 elig=0.58 dorfler_tail=0.09 floor=0 sel=31 7.7s
|
|
394/401 | loss=0.5978 ev=0.583 agents=832 avg_r=-2.7761 sum_r=-710.69 x<0=0.19 elig=0.59 dorfler_tail=0.08 floor=0 sel=32 7.8s
|
|
395/401 | loss=0.5630 ev=0.607 agents=118 avg_r=-2.8482 sum_r=-729.14 x<0=0.15 elig=0.58 dorfler_tail=0.08 floor=0 sel=30 7.5s
|
|
396/401 | loss=0.6266 ev=0.557 agents=980 avg_r=-1.5726 sum_r=-402.60 x<0=0.20 elig=0.58 dorfler_tail=0.08 floor=0 sel=30 7.4s
|
|
397/401 | loss=0.5852 ev=0.599 agents=55 avg_r=-4.5732 sum_r=-1170.75 x<0=0.18 elig=0.59 dorfler_tail=0.08 floor=0 sel=31 7.5s
|
|
398/401 | loss=0.6173 ev=0.583 agents=604 avg_r=-1.0687 sum_r=-273.59 x<0=0.16 elig=0.58 dorfler_tail=0.09 floor=0 sel=30 7.4s
|
|
399/401 | loss=0.5544 ev=0.622 agents=278 avg_r=-2.7659 sum_r=-708.06 x<0=0.18 elig=0.58 dorfler_tail=0.08 floor=0 sel=30 7.4s
|
|
400/401 | loss=0.6305 ev=0.572 agents=400 avg_r=-2.0476 sum_r=-524.18 x<0=0.20 elig=0.59 dorfler_tail=0.08 floor=0 sel=30 7.4s
|
|
[Checkpoint] saved → checkpoints/model_iter0400.pt
|
|
401/401 | loss=0.6506 ev=0.589 agents=230 avg_r=0.0894 sum_r=22.90 x<0=0.13 elig=0.59 dorfler_tail=0.08 floor=0 sel=31 7.4s
|
|
[Checkpoint] saved → checkpoints/model_iter0401.pt
|
|
[Checkpoint] saved → checkpoints/model_final.pt
|
|
[Train] done, total time 3065.4s
|
|
Training finished at Fri 29 May 15:49:40 CST 2026
|