Starting training at Fri 29 May 14:36:05 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=1.2593 ev=-0.005 agents=109 avg_r=-0.4716 sum_r=-120.74 x<0=0.69 elig=0.58 dorfler_tail=0.09 floor=0 sel=35 8.7s
     2/401 | loss=1.1660 ev=0.023 agents=193 avg_r=1.8712 sum_r=479.03 x<0=0.62 elig=0.58 dorfler_tail=0.08 floor=0 sel=32 7.8s
     3/401 | loss=1.1102 ev=0.044 agents=39 avg_r=-1.2724 sum_r=-325.74 x<0=0.60 elig=0.59 dorfler_tail=0.08 floor=0 sel=32 7.8s
     4/401 | loss=1.1780 ev=0.065 agents=34 avg_r=2.1552 sum_r=551.73 x<0=0.61 elig=0.58 dorfler_tail=0.09 floor=0 sel=35 8.3s
     5/401 | loss=1.1065 ev=0.091 agents=88 avg_r=-1.4642 sum_r=-374.83 x<0=0.52 elig=0.59 dorfler_tail=0.08 floor=0 sel=32 8.0s
     6/401 | loss=1.2564 ev=0.098 agents=36 avg_r=1.5516 sum_r=397.20 x<0=0.49 elig=0.59 dorfler_tail=0.08 floor=0 sel=32 7.8s
     7/401 | loss=1.0063 ev=0.172 agents=34 avg_r=0.8841 sum_r=226.33 x<0=0.47 elig=0.58 dorfler_tail=0.09 floor=0 sel=35 8.1s
     8/401 | loss=1.3696 ev=0.168 agents=133 avg_r=0.6858 sum_r=175.58 x<0=0.44 elig=0.59 dorfler_tail=0.08 floor=0 sel=33 7.9s
     9/401 | loss=1.1844 ev=0.215 agents=79 avg_r=0.2644 sum_r=67.68 x<0=0.45 elig=0.59 dorfler_tail=0.08 floor=0 sel=31 7.7s
    10/401 | loss=1.0413 ev=0.216 agents=82 avg_r=-1.0025 sum_r=-256.64 x<0=0.42 elig=0.59 dorfler_tail=0.08 floor=0 sel=34 8.0s
    11/401 | loss=1.2795 ev=0.256 agents=60 avg_r=2.6849 sum_r=687.34 x<0=0.39 elig=0.59 dorfler_tail=0.08 floor=0 sel=31 7.8s
    12/401 | loss=0.8503 ev=0.306 agents=48 avg_r=0.5254 sum_r=134.49 x<0=0.40 elig=0.59 dorfler_tail=0.08 floor=0 sel=33 7.9s
    13/401 | loss=0.8283 ev=0.322 agents=88 avg_r=0.9044 sum_r=231.52 x<0=0.42 elig=0.58 dorfler_tail=0.08 floor=0 sel=33 7.9s
    14/401 | loss=0.8950 ev=0.298 agents=40 avg_r=0.4961 sum_r=127.00 x<0=0.39 elig=0.59 dorfler_tail=0.08 floor=0 sel=33 7.9s
    15/401 | loss=0.8561 ev=0.342 agents=101 avg_r=0.5456 sum_r=139.67 x<0=0.41 elig=0.58 dorfler_tail=0.08 floor=0 sel=34 8.0s
    16/401 | loss=1.1581 ev=0.283 agents=34 avg_r=-1.9177 sum_r=-490.92 x<0=0.33 elig=0.59 dorfler_tail=0.08 floor=0 sel=29 7.5s
    17/401 | loss=0.8868 ev=0.364 agents=132 avg_r=3.2843 sum_r=840.77 x<0=0.33 elig=0.59 dorfler_tail=0.08 floor=0 sel=33 8.0s
    18/401 | loss=0.8571 ev=0.349 agents=34 avg_r=1.1258 sum_r=288.21 x<0=0.30 elig=0.58 dorfler_tail=0.08 floor=0 sel=32 7.9s
    19/401 | loss=0.7991 ev=0.374 agents=201 avg_r=-0.2317 sum_r=-59.32 x<0=0.28 elig=0.59 dorfler_tail=0.08 floor=0 sel=35 8.1s
    20/401 | loss=0.8149 ev=0.386 agents=120 avg_r=1.5704 sum_r=402.02 x<0=0.21 elig=0.59 dorfler_tail=0.08 floor=0 sel=31 7.7s
    21/401 | loss=0.8764 ev=0.357 agents=78 avg_r=0.5421 sum_r=138.78 x<0=0.22 elig=0.59 dorfler_tail=0.08 floor=0 sel=32 7.7s
    22/401 | loss=0.7788 ev=0.367 agents=44 avg_r=0.6768 sum_r=173.27 x<0=0.17 elig=0.59 dorfler_tail=0.08 floor=0 sel=32 7.7s
    23/401 | loss=0.7429 ev=0.382 agents=36 avg_r=0.6276 sum_r=160.68 x<0=0.16 elig=0.59 dorfler_tail=0.08 floor=0 sel=32 7.8s
    24/401 | loss=0.8267 ev=0.404 agents=175 avg_r=3.4114 sum_r=873.33 x<0=0.13 elig=0.59 dorfler_tail=0.08 floor=0 sel=33 7.9s
    25/401 | loss=0.7211 ev=0.390 agents=34 avg_r=0.2581 sum_r=66.07 x<0=0.12 elig=0.59 dorfler_tail=0.08 floor=0 sel=29 7.4s
    26/401 | loss=0.9829 ev=0.350 agents=34 avg_r=-0.0098 sum_r=-2.50 x<0=0.13 elig=0.59 dorfler_tail=0.08 floor=0 sel=34 8.0s
    27/401 | loss=0.7973 ev=0.356 agents=176 avg_r=0.8028 sum_r=205.51 x<0=0.12 elig=0.59 dorfler_tail=0.08 floor=0 sel=31 8.1s
    28/401 | loss=0.7603 ev=0.414 agents=219 avg_r=0.7955 sum_r=203.65 x<0=0.10 elig=0.59 dorfler_tail=0.08 floor=0 sel=32 8.1s
    29/401 | loss=0.7585 ev=0.375 agents=44 avg_r=1.5867 sum_r=406.19 x<0=0.09 elig=0.59 dorfler_tail=0.08 floor=0 sel=32 8.0s
    30/401 | loss=0.6940 ev=0.425 agents=133 avg_r=2.4328 sum_r=622.81 x<0=0.09 elig=0.59 dorfler_tail=0.08 floor=0 sel=30 7.6s
    31/401 | loss=0.9083 ev=0.370 agents=44 avg_r=2.5351 sum_r=648.99 x<0=0.13 elig=0.59 dorfler_tail=0.08 floor=0 sel=32 7.8s
    32/401 | loss=1.0825 ev=0.356 agents=34 avg_r=0.0954 sum_r=24.43 x<0=0.16 elig=0.59 dorfler_tail=0.08 floor=0 sel=33 8.0s
    33/401 | loss=0.6799 ev=0.430 agents=752 avg_r=2.1090 sum_r=539.90 x<0=0.15 elig=0.59 dorfler_tail=0.07 floor=0 sel=31 7.7s
    34/401 | loss=1.0309 ev=0.325 agents=132 avg_r=-0.3870 sum_r=-99.07 x<0=0.14 elig=0.60 dorfler_tail=0.07 floor=0 sel=31 7.6s
    35/401 | loss=0.7810 ev=0.385 agents=60 avg_r=2.1370 sum_r=547.06 x<0=0.10 elig=0.59 dorfler_tail=0.08 floor=0 sel=31 7.5s
    36/401 | loss=0.7733 ev=0.381 agents=139 avg_r=0.5555 sum_r=142.22 x<0=0.09 elig=0.59 dorfler_tail=0.08 floor=0 sel=29 7.4s
    37/401 | loss=0.7242 ev=0.386 agents=752 avg_r=1.7036 sum_r=436.12 x<0=0.10 elig=0.59 dorfler_tail=0.07 floor=0 sel=31 7.5s
    38/401 | loss=0.7454 ev=0.402 agents=34 avg_r=1.7798 sum_r=455.64 x<0=0.09 elig=0.59 dorfler_tail=0.07 floor=0 sel=31 7.5s
    39/401 | loss=0.6106 ev=0.445 agents=87 avg_r=2.2153 sum_r=567.13 x<0=0.06 elig=0.60 dorfler_tail=0.08 floor=0 sel=30 7.5s
    40/401 | loss=0.8085 ev=0.381 agents=88 avg_r=2.2893 sum_r=586.06 x<0=0.06 elig=0.59 dorfler_tail=0.08 floor=0 sel=33 7.7s
    41/401 | loss=0.6706 ev=0.419 agents=301 avg_r=1.4149 sum_r=362.21 x<0=0.05 elig=0.59 dorfler_tail=0.07 floor=0 sel=29 7.2s
    42/401 | loss=0.6504 ev=0.440 agents=1563 avg_r=2.3614 sum_r=604.52 x<0=0.06 elig=0.59 dorfler_tail=0.07 floor=0 sel=31 7.5s
    43/401 | loss=0.6548 ev=0.389 agents=905 avg_r=2.1166 sum_r=541.85 x<0=0.05 elig=0.59 dorfler_tail=0.08 floor=0 sel=30 7.5s
    44/401 | loss=0.6763 ev=0.392 agents=603 avg_r=2.1965 sum_r=562.30 x<0=0.05 elig=0.60 dorfler_tail=0.08 floor=0 sel=31 7.6s
    45/401 | loss=0.6371 ev=0.417 agents=321 avg_r=1.2079 sum_r=309.23 x<0=0.04 elig=0.59 dorfler_tail=0.07 floor=0 sel=29 7.3s
    46/401 | loss=0.7580 ev=0.419 agents=64 avg_r=2.3964 sum_r=613.47 x<0=0.05 elig=0.59 dorfler_tail=0.07 floor=0 sel=31 7.6s
    47/401 | loss=0.8826 ev=0.357 agents=648 avg_r=1.9237 sum_r=492.46 x<0=0.07 elig=0.60 dorfler_tail=0.08 floor=0 sel=30 7.4s
    48/401 | loss=0.7618 ev=0.374 agents=72 avg_r=1.9302 sum_r=494.14 x<0=0.04 elig=0.59 dorfler_tail=0.07 floor=0 sel=31 7.4s
    49/401 | loss=1.0496 ev=0.349 agents=1113 avg_r=1.6100 sum_r=412.15 x<0=0.05 elig=0.59 dorfler_tail=0.07 floor=0 sel=31 8.0s
    50/401 | loss=1.0966 ev=0.355 agents=207 avg_r=0.2694 sum_r=68.96 x<0=0.04 elig=0.59 dorfler_tail=0.07 floor=0 sel=30 7.7s
[Checkpoint] saved → checkpoints/model_iter0050.pt
    51/401 | loss=0.7497 ev=0.362 agents=88 avg_r=2.4859 sum_r=636.39 x<0=0.04 elig=0.59 dorfler_tail=0.07 floor=0 sel=30 7.6s
    52/401 | loss=0.7117 ev=0.376 agents=34 avg_r=1.3932 sum_r=356.65 x<0=0.04 elig=0.60 dorfler_tail=0.07 floor=0 sel=29 7.5s
    53/401 | loss=0.8732 ev=0.428 agents=482 avg_r=2.5241 sum_r=646.16 x<0=0.05 elig=0.60 dorfler_tail=0.07 floor=0 sel=30 7.5s
    54/401 | loss=0.7275 ev=0.414 agents=797 avg_r=2.5614 sum_r=655.71 x<0=0.03 elig=0.60 dorfler_tail=0.07 floor=0 sel=31 7.6s
    55/401 | loss=1.0015 ev=0.267 agents=238 avg_r=1.7553 sum_r=449.35 x<0=0.03 elig=0.60 dorfler_tail=0.07 floor=0 sel=31 7.7s
    56/401 | loss=0.9532 ev=0.328 agents=78 avg_r=1.6596 sum_r=424.86 x<0=0.04 elig=0.61 dorfler_tail=0.07 floor=0 sel=27 7.3s
    57/401 | loss=0.9659 ev=0.392 agents=180 avg_r=0.1315 sum_r=33.67 x<0=0.04 elig=0.60 dorfler_tail=0.07 floor=0 sel=30 7.6s
    58/401 | loss=0.5575 ev=0.479 agents=1467 avg_r=3.9607 sum_r=1013.94 x<0=0.04 elig=0.59 dorfler_tail=0.08 floor=0 sel=31 7.6s
    59/401 | loss=0.6323 ev=0.412 agents=257 avg_r=1.1701 sum_r=299.54 x<0=0.03 elig=0.60 dorfler_tail=0.07 floor=0 sel=30 7.6s
    60/401 | loss=0.7717 ev=0.429 agents=278 avg_r=1.1557 sum_r=295.85 x<0=0.04 elig=0.60 dorfler_tail=0.08 floor=0 sel=28 7.3s
    61/401 | loss=0.6149 ev=0.436 agents=162 avg_r=2.4661 sum_r=631.33 x<0=0.03 elig=0.60 dorfler_tail=0.07 floor=0 sel=29 7.5s
    62/401 | loss=0.5705 ev=0.410 agents=269 avg_r=3.6565 sum_r=936.06 x<0=0.03 elig=0.59 dorfler_tail=0.08 floor=0 sel=32 7.6s
    63/401 | loss=0.7479 ev=0.391 agents=34 avg_r=1.1095 sum_r=284.04 x<0=0.02 elig=0.60 dorfler_tail=0.07 floor=0 sel=29 7.3s
    64/401 | loss=0.9662 ev=0.418 agents=149 avg_r=1.0548 sum_r=270.02 x<0=0.02 elig=0.60 dorfler_tail=0.07 floor=0 sel=30 7.4s
    65/401 | loss=0.8020 ev=0.379 agents=139 avg_r=2.3568 sum_r=603.34 x<0=0.01 elig=0.60 dorfler_tail=0.07 floor=0 sel=29 7.3s
    66/401 | loss=0.9130 ev=0.401 agents=140 avg_r=0.8920 sum_r=228.35 x<0=0.01 elig=0.60 dorfler_tail=0.07 floor=0 sel=30 7.5s
    67/401 | loss=0.6314 ev=0.411 agents=82 avg_r=2.2832 sum_r=584.50 x<0=0.01 elig=0.60 dorfler_tail=0.07 floor=0 sel=30 7.4s
    68/401 | loss=0.8747 ev=0.437 agents=258 avg_r=0.8502 sum_r=217.65 x<0=0.01 elig=0.60 dorfler_tail=0.08 floor=0 sel=30 7.6s
    69/401 | loss=0.7156 ev=0.397 agents=649 avg_r=2.6260 sum_r=672.26 x<0=0.01 elig=0.60 dorfler_tail=0.07 floor=0 sel=29 7.3s
    70/401 | loss=0.7031 ev=0.427 agents=520 avg_r=2.5518 sum_r=653.26 x<0=0.01 elig=0.60 dorfler_tail=0.07 floor=0 sel=30 7.4s
    71/401 | loss=0.6538 ev=0.393 agents=412 avg_r=2.4192 sum_r=619.32 x<0=0.01 elig=0.60 dorfler_tail=0.07 floor=0 sel=31 7.6s
    72/401 | loss=0.6831 ev=0.418 agents=84 avg_r=2.0187 sum_r=516.80 x<0=0.01 elig=0.61 dorfler_tail=0.07 floor=0 sel=28 7.8s
    73/401 | loss=0.7298 ev=0.426 agents=438 avg_r=2.5987 sum_r=665.26 x<0=0.00 elig=0.60 dorfler_tail=0.07 floor=0 sel=30 7.7s
    74/401 | loss=0.6047 ev=0.470 agents=301 avg_r=3.4593 sum_r=885.58 x<0=0.00 elig=0.60 dorfler_tail=0.07 floor=0 sel=29 7.6s
    75/401 | loss=0.6847 ev=0.412 agents=515 avg_r=0.6582 sum_r=168.49 x<0=0.00 elig=0.60 dorfler_tail=0.07 floor=0 sel=29 7.4s
    76/401 | loss=0.9368 ev=0.393 agents=503 avg_r=2.7642 sum_r=707.63 x<0=0.00 elig=0.60 dorfler_tail=0.07 floor=0 sel=30 7.7s
    77/401 | loss=0.9459 ev=0.432 agents=261 avg_r=1.2000 sum_r=307.20 x<0=0.01 elig=0.60 dorfler_tail=0.07 floor=0 sel=28 7.3s
    78/401 | loss=0.7438 ev=0.411 agents=221 avg_r=2.1195 sum_r=542.58 x<0=0.00 elig=0.61 dorfler_tail=0.07 floor=0 sel=30 7.6s
    79/401 | loss=0.7466 ev=0.450 agents=232 avg_r=4.4824 sum_r=1147.50 x<0=0.01 elig=0.60 dorfler_tail=0.08 floor=0 sel=32 7.7s
    80/401 | loss=1.1380 ev=0.460 agents=814 avg_r=0.3357 sum_r=85.95 x<0=0.01 elig=0.61 dorfler_tail=0.07 floor=0 sel=27 7.2s
    81/401 | loss=0.8259 ev=0.394 agents=568 avg_r=1.8428 sum_r=471.75 x<0=0.00 elig=0.60 dorfler_tail=0.07 floor=0 sel=29 7.3s
    82/401 | loss=0.5936 ev=0.436 agents=237 avg_r=3.5513 sum_r=909.14 x<0=0.00 elig=0.60 dorfler_tail=0.07 floor=0 sel=29 7.5s
    83/401 | loss=0.6978 ev=0.432 agents=389 avg_r=2.7072 sum_r=693.05 x<0=0.00 elig=0.61 dorfler_tail=0.07 floor=0 sel=28 7.5s
    84/401 | loss=0.8955 ev=0.404 agents=80 avg_r=3.3064 sum_r=846.43 x<0=0.00 elig=0.61 dorfler_tail=0.07 floor=0 sel=31 7.8s
    85/401 | loss=0.8506 ev=0.432 agents=34 avg_r=0.2730 sum_r=69.89 x<0=0.00 elig=0.61 dorfler_tail=0.07 floor=0 sel=24 6.9s
    86/401 | loss=0.7781 ev=0.412 agents=391 avg_r=3.9846 sum_r=1020.05 x<0=0.01 elig=0.62 dorfler_tail=0.07 floor=0 sel=30 7.9s
    87/401 | loss=0.8894 ev=0.397 agents=418 avg_r=2.6888 sum_r=688.32 x<0=0.00 elig=0.62 dorfler_tail=0.07 floor=0 sel=28 7.5s
    88/401 | loss=1.0689 ev=0.411 agents=80 avg_r=3.0347 sum_r=776.89 x<0=0.01 elig=0.62 dorfler_tail=0.07 floor=0 sel=28 7.6s
    89/401 | loss=0.8925 ev=0.358 agents=862 avg_r=2.9356 sum_r=751.50 x<0=0.01 elig=0.62 dorfler_tail=0.07 floor=0 sel=29 7.8s
    90/401 | loss=0.7441 ev=0.464 agents=549 avg_r=4.5978 sum_r=1177.04 x<0=0.01 elig=0.62 dorfler_tail=0.07 floor=0 sel=28 7.6s
    91/401 | loss=1.1180 ev=0.386 agents=101 avg_r=2.1914 sum_r=560.99 x<0=0.00 elig=0.62 dorfler_tail=0.07 floor=0 sel=29 7.6s
    92/401 | loss=0.9271 ev=0.439 agents=60 avg_r=3.2678 sum_r=836.57 x<0=0.00 elig=0.63 dorfler_tail=0.07 floor=0 sel=27 7.5s
    93/401 | loss=0.9531 ev=0.437 agents=291 avg_r=3.1621 sum_r=809.49 x<0=0.00 elig=0.63 dorfler_tail=0.07 floor=0 sel=28 7.6s
    94/401 | loss=0.8870 ev=0.439 agents=101 avg_r=3.1353 sum_r=802.65 x<0=0.00 elig=0.63 dorfler_tail=0.07 floor=0 sel=28 8.0s
    95/401 | loss=0.9440 ev=0.434 agents=34 avg_r=5.3761 sum_r=1376.27 x<0=0.01 elig=0.63 dorfler_tail=0.07 floor=0 sel=30 8.4s
    96/401 | loss=1.1221 ev=0.381 agents=62 avg_r=2.8338 sum_r=725.45 x<0=0.00 elig=0.63 dorfler_tail=0.07 floor=0 sel=28 7.9s
    97/401 | loss=0.9903 ev=0.452 agents=180 avg_r=4.0017 sum_r=1024.43 x<0=0.00 elig=0.63 dorfler_tail=0.07 floor=0 sel=28 7.9s
    98/401 | loss=1.0881 ev=0.436 agents=419 avg_r=4.6007 sum_r=1177.77 x<0=0.01 elig=0.63 dorfler_tail=0.07 floor=0 sel=29 7.9s
    99/401 | loss=0.8982 ev=0.432 agents=85 avg_r=2.9775 sum_r=762.24 x<0=0.01 elig=0.63 dorfler_tail=0.07 floor=0 sel=28 7.8s
   100/401 | loss=1.0656 ev=0.359 agents=691 avg_r=3.0152 sum_r=771.89 x<0=0.01 elig=0.63 dorfler_tail=0.07 floor=0 sel=28 7.7s
[Checkpoint] saved → checkpoints/model_iter0100.pt
   101/401 | loss=0.8757 ev=0.449 agents=147 avg_r=4.0589 sum_r=1039.07 x<0=0.00 elig=0.62 dorfler_tail=0.08 floor=0 sel=29 7.7s
   102/401 | loss=0.9537 ev=0.441 agents=802 avg_r=4.1671 sum_r=1066.79 x<0=0.00 elig=0.62 dorfler_tail=0.07 floor=0 sel=29 7.7s
   103/401 | loss=1.1348 ev=0.457 agents=120 avg_r=4.9407 sum_r=1264.81 x<0=0.00 elig=0.62 dorfler_tail=0.07 floor=0 sel=29 7.9s
   104/401 | loss=1.0887 ev=0.415 agents=48 avg_r=3.7664 sum_r=964.21 x<0=0.01 elig=0.63 dorfler_tail=0.07 floor=0 sel=29 7.8s
   105/401 | loss=0.7257 ev=0.441 agents=245 avg_r=1.1230 sum_r=287.49 x<0=0.00 elig=0.62 dorfler_tail=0.07 floor=0 sel=26 7.5s
   106/401 | loss=0.9558 ev=0.429 agents=193 avg_r=3.9291 sum_r=1005.86 x<0=0.00 elig=0.63 dorfler_tail=0.07 floor=0 sel=28 7.7s
   107/401 | loss=1.1960 ev=0.461 agents=140 avg_r=3.8453 sum_r=984.40 x<0=0.01 elig=0.63 dorfler_tail=0.07 floor=0 sel=29 8.0s
   108/401 | loss=1.0023 ev=0.425 agents=34 avg_r=3.5098 sum_r=898.50 x<0=0.00 elig=0.63 dorfler_tail=0.07 floor=0 sel=26 7.5s
   109/401 | loss=1.0553 ev=0.437 agents=155 avg_r=4.4515 sum_r=1139.58 x<0=0.00 elig=0.63 dorfler_tail=0.07 floor=0 sel=29 7.8s
   110/401 | loss=0.8946 ev=0.458 agents=317 avg_r=2.2184 sum_r=567.91 x<0=0.00 elig=0.62 dorfler_tail=0.07 floor=0 sel=28 7.6s
   111/401 | loss=0.8399 ev=0.475 agents=322 avg_r=3.8648 sum_r=989.39 x<0=0.00 elig=0.63 dorfler_tail=0.07 floor=0 sel=28 7.6s
   112/401 | loss=0.8203 ev=0.450 agents=661 avg_r=4.3269 sum_r=1107.69 x<0=0.01 elig=0.63 dorfler_tail=0.07 floor=0 sel=29 7.9s
   113/401 | loss=1.2963 ev=0.414 agents=88 avg_r=4.9068 sum_r=1256.15 x<0=0.01 elig=0.63 dorfler_tail=0.07 floor=0 sel=30 8.0s
   114/401 | loss=0.8770 ev=0.434 agents=96 avg_r=2.3554 sum_r=602.99 x<0=0.00 elig=0.64 dorfler_tail=0.06 floor=0 sel=25 7.3s
   115/401 | loss=1.0023 ev=0.462 agents=1043 avg_r=4.6932 sum_r=1201.45 x<0=0.01 elig=0.64 dorfler_tail=0.07 floor=0 sel=29 7.7s
   116/401 | loss=0.9185 ev=0.471 agents=574 avg_r=4.3713 sum_r=1119.05 x<0=0.00 elig=0.64 dorfler_tail=0.07 floor=0 sel=28 7.7s
   117/401 | loss=0.9487 ev=0.445 agents=461 avg_r=3.4812 sum_r=891.18 x<0=0.00 elig=0.63 dorfler_tail=0.07 floor=0 sel=29 7.8s
   118/401 | loss=1.1328 ev=0.459 agents=186 avg_r=4.4079 sum_r=1128.43 x<0=0.00 elig=0.63 dorfler_tail=0.07 floor=0 sel=27 8.2s
   119/401 | loss=0.8739 ev=0.454 agents=659 avg_r=3.6846 sum_r=943.26 x<0=0.00 elig=0.63 dorfler_tail=0.07 floor=0 sel=28 8.0s
   120/401 | loss=0.8952 ev=0.490 agents=78 avg_r=4.0254 sum_r=1030.50 x<0=0.00 elig=0.63 dorfler_tail=0.07 floor=0 sel=29 8.0s
   121/401 | loss=1.1642 ev=0.444 agents=180 avg_r=5.1341 sum_r=1314.33 x<0=0.00 elig=0.63 dorfler_tail=0.07 floor=0 sel=29 8.0s
   122/401 | loss=1.0194 ev=0.449 agents=1241 avg_r=3.6450 sum_r=933.12 x<0=0.00 elig=0.63 dorfler_tail=0.07 floor=0 sel=27 7.7s
   123/401 | loss=0.9362 ev=0.425 agents=227 avg_r=3.2675 sum_r=836.47 x<0=0.00 elig=0.64 dorfler_tail=0.07 floor=0 sel=28 7.8s
   124/401 | loss=1.0467 ev=0.420 agents=34 avg_r=4.8397 sum_r=1238.97 x<0=0.00 elig=0.64 dorfler_tail=0.07 floor=0 sel=29 7.9s
   125/401 | loss=0.9613 ev=0.467 agents=592 avg_r=5.1937 sum_r=1329.58 x<0=0.00 elig=0.64 dorfler_tail=0.07 floor=0 sel=30 8.0s
   126/401 | loss=0.9090 ev=0.439 agents=44 avg_r=4.2965 sum_r=1099.89 x<0=0.00 elig=0.64 dorfler_tail=0.07 floor=0 sel=27 7.6s
   127/401 | loss=1.0189 ev=0.451 agents=184 avg_r=4.2159 sum_r=1079.27 x<0=0.00 elig=0.63 dorfler_tail=0.07 floor=0 sel=31 8.0s
   128/401 | loss=1.1045 ev=0.459 agents=808 avg_r=2.0674 sum_r=529.25 x<0=0.00 elig=0.63 dorfler_tail=0.07 floor=0 sel=26 7.3s
   129/401 | loss=1.0547 ev=0.487 agents=705 avg_r=2.0413 sum_r=522.57 x<0=0.00 elig=0.63 dorfler_tail=0.07 floor=0 sel=28 7.6s
   130/401 | loss=0.8997 ev=0.489 agents=119 avg_r=5.8658 sum_r=1501.65 x<0=0.00 elig=0.64 dorfler_tail=0.07 floor=0 sel=30 7.9s
   131/401 | loss=1.1464 ev=0.463 agents=514 avg_r=5.3146 sum_r=1360.55 x<0=0.00 elig=0.64 dorfler_tail=0.07 floor=0 sel=30 8.0s
   132/401 | loss=0.9049 ev=0.468 agents=176 avg_r=3.2288 sum_r=826.57 x<0=0.00 elig=0.64 dorfler_tail=0.07 floor=0 sel=25 7.3s
   133/401 | loss=0.9787 ev=0.465 agents=1140 avg_r=3.8684 sum_r=990.30 x<0=0.00 elig=0.65 dorfler_tail=0.07 floor=0 sel=28 7.8s
   134/401 | loss=0.9619 ev=0.454 agents=44 avg_r=3.6363 sum_r=930.90 x<0=0.00 elig=0.64 dorfler_tail=0.07 floor=0 sel=29 7.7s
   135/401 | loss=1.1247 ev=0.476 agents=71 avg_r=6.3209 sum_r=1618.16 x<0=0.00 elig=0.63 dorfler_tail=0.07 floor=0 sel=29 7.8s
   136/401 | loss=0.9569 ev=0.428 agents=637 avg_r=2.3333 sum_r=597.34 x<0=0.00 elig=0.63 dorfler_tail=0.07 floor=0 sel=26 7.4s
   137/401 | loss=1.3365 ev=0.372 agents=132 avg_r=3.3031 sum_r=845.59 x<0=0.00 elig=0.63 dorfler_tail=0.07 floor=0 sel=30 7.8s
   138/401 | loss=1.0446 ev=0.487 agents=197 avg_r=4.3467 sum_r=1112.75 x<0=0.00 elig=0.63 dorfler_tail=0.07 floor=0 sel=28 7.6s
   139/401 | loss=0.9965 ev=0.493 agents=1239 avg_r=3.0278 sum_r=775.11 x<0=0.00 elig=0.64 dorfler_tail=0.07 floor=0 sel=29 7.9s
   140/401 | loss=0.8756 ev=0.491 agents=34 avg_r=4.0575 sum_r=1038.73 x<0=0.00 elig=0.64 dorfler_tail=0.07 floor=0 sel=26 7.8s
   141/401 | loss=1.0863 ev=0.455 agents=202 avg_r=4.4626 sum_r=1142.43 x<0=0.00 elig=0.64 dorfler_tail=0.07 floor=0 sel=28 8.2s
   142/401 | loss=0.8633 ev=0.492 agents=599 avg_r=3.6977 sum_r=946.60 x<0=0.00 elig=0.63 dorfler_tail=0.07 floor=0 sel=27 7.7s
   143/401 | loss=1.2714 ev=0.450 agents=83 avg_r=3.4606 sum_r=885.91 x<0=0.00 elig=0.63 dorfler_tail=0.07 floor=0 sel=27 7.8s
   144/401 | loss=0.8689 ev=0.480 agents=212 avg_r=5.9020 sum_r=1510.92 x<0=0.00 elig=0.64 dorfler_tail=0.07 floor=0 sel=31 8.2s
   145/401 | loss=0.8527 ev=0.457 agents=466 avg_r=3.3779 sum_r=864.73 x<0=0.00 elig=0.64 dorfler_tail=0.07 floor=0 sel=28 7.7s
   146/401 | loss=1.0791 ev=0.436 agents=41 avg_r=3.9742 sum_r=1017.40 x<0=0.00 elig=0.64 dorfler_tail=0.07 floor=0 sel=27 7.6s
   147/401 | loss=1.0243 ev=0.483 agents=201 avg_r=4.0608 sum_r=1039.56 x<0=0.00 elig=0.64 dorfler_tail=0.07 floor=0 sel=27 7.7s
   148/401 | loss=0.8642 ev=0.439 agents=169 avg_r=5.0525 sum_r=1293.44 x<0=0.00 elig=0.64 dorfler_tail=0.07 floor=0 sel=29 7.9s
   149/401 | loss=1.2060 ev=0.492 agents=1118 avg_r=3.4406 sum_r=880.81 x<0=0.00 elig=0.64 dorfler_tail=0.07 floor=0 sel=28 7.8s
   150/401 | loss=0.8956 ev=0.491 agents=139 avg_r=4.4020 sum_r=1126.90 x<0=0.00 elig=0.63 dorfler_tail=0.07 floor=0 sel=28 7.7s
[Checkpoint] saved → checkpoints/model_iter0150.pt
   151/401 | loss=0.8862 ev=0.439 agents=36 avg_r=3.6186 sum_r=926.35 x<0=0.00 elig=0.64 dorfler_tail=0.07 floor=0 sel=26 7.4s
   152/401 | loss=1.1976 ev=0.436 agents=374 avg_r=5.2749 sum_r=1350.39 x<0=0.00 elig=0.64 dorfler_tail=0.07 floor=0 sel=30 8.0s
   153/401 | loss=0.7750 ev=0.453 agents=203 avg_r=3.3719 sum_r=863.21 x<0=0.00 elig=0.64 dorfler_tail=0.07 floor=0 sel=26 7.5s
   154/401 | loss=1.1222 ev=0.448 agents=498 avg_r=5.2013 sum_r=1331.52 x<0=0.00 elig=0.64 dorfler_tail=0.07 floor=0 sel=29 7.8s
   155/401 | loss=0.8401 ev=0.498 agents=174 avg_r=4.3179 sum_r=1105.39 x<0=0.00 elig=0.64 dorfler_tail=0.07 floor=0 sel=27 7.5s
   156/401 | loss=1.1951 ev=0.475 agents=144 avg_r=4.7607 sum_r=1218.73 x<0=0.00 elig=0.64 dorfler_tail=0.07 floor=0 sel=29 7.9s
   157/401 | loss=1.0364 ev=0.488 agents=233 avg_r=4.6508 sum_r=1190.61 x<0=0.00 elig=0.64 dorfler_tail=0.07 floor=0 sel=29 7.9s
   158/401 | loss=1.1938 ev=0.437 agents=40 avg_r=4.8137 sum_r=1232.31 x<0=0.00 elig=0.65 dorfler_tail=0.07 floor=0 sel=28 7.7s
   159/401 | loss=0.7339 ev=0.442 agents=401 avg_r=2.6907 sum_r=688.82 x<0=0.00 elig=0.64 dorfler_tail=0.06 floor=0 sel=27 7.5s
   160/401 | loss=0.9124 ev=0.494 agents=377 avg_r=5.1447 sum_r=1317.04 x<0=0.00 elig=0.65 dorfler_tail=0.07 floor=0 sel=27 7.7s
   161/401 | loss=1.1279 ev=0.482 agents=34 avg_r=5.6036 sum_r=1434.53 x<0=0.00 elig=0.64 dorfler_tail=0.07 floor=0 sel=30 8.0s
   162/401 | loss=0.9648 ev=0.472 agents=725 avg_r=4.8624 sum_r=1244.77 x<0=0.00 elig=0.65 dorfler_tail=0.07 floor=0 sel=29 7.8s
   163/401 | loss=0.8031 ev=0.507 agents=276 avg_r=2.6097 sum_r=668.09 x<0=0.00 elig=0.64 dorfler_tail=0.06 floor=0 sel=23 7.6s
   164/401 | loss=1.3767 ev=0.402 agents=177 avg_r=5.0539 sum_r=1293.81 x<0=0.00 elig=0.64 dorfler_tail=0.07 floor=0 sel=31 8.4s
   165/401 | loss=0.9780 ev=0.513 agents=158 avg_r=4.9213 sum_r=1259.84 x<0=0.00 elig=0.64 dorfler_tail=0.07 floor=0 sel=29 8.0s
   166/401 | loss=0.9135 ev=0.480 agents=397 avg_r=3.7623 sum_r=963.14 x<0=0.00 elig=0.65 dorfler_tail=0.07 floor=0 sel=27 7.8s
   167/401 | loss=1.1074 ev=0.503 agents=193 avg_r=5.2436 sum_r=1342.35 x<0=0.00 elig=0.64 dorfler_tail=0.07 floor=0 sel=30 8.0s
   168/401 | loss=1.1870 ev=0.476 agents=1235 avg_r=3.8139 sum_r=976.35 x<0=0.00 elig=0.65 dorfler_tail=0.07 floor=0 sel=27 7.6s
   169/401 | loss=1.2314 ev=0.459 agents=476 avg_r=2.9524 sum_r=755.82 x<0=0.00 elig=0.65 dorfler_tail=0.07 floor=0 sel=29 7.9s
slurmstepd: error: *** JOB 4533 ON node06 CANCELLED AT 2026-05-29T14:58:13 ***