Shiki42's picture
insert_key single-task dev3 checkpoint (178ee15, 96.9% deterministic mixed-reset eval) and its reset caches
b292463 verified
Raw History Blame Contribute Delete
5.95 kB
[02:48:45] environment check ok: /home/coder/contact_rl/runtime/learner312/bin/python python 3.12.13
[02:48:45] simulator insert_key: /home/coder/agentic-robodojo/venv/bin/python -u /home/coder/contact_rl/src_insert_key/scripts/contact_rl.py serve --task insert_key --output /home/coder/contact_rl/runs/insert_key-rl-dev3/sim_0_insert_key --socket /home/coder/contact_rl/runs/insert_key-rl-dev3/sim_0_insert_key.sock --num_envs 1024 --cache /home/coder/contact_rl/caches/insert_key/cache.pt --seed 0 --instances train
[02:54:57] task insert_key: 1024 envs, 168 points, ids [0, 0, 1, -1], cache 72288 entries
[02:55:06] it=0 min=0.1 fps=4064 kl=0.0139 lr=3.00e-04 std=0.498 grip_std=0.300 success_ema: insert_key=0.086
[02:56:19] it=10 min=1.4 fps=3448 kl=0.0100 lr=1.14e-04 std=0.488 grip_std=0.298 success_ema: insert_key=0.214
[02:58:22] it=20 min=3.4 fps=2415 kl=0.0132 lr=1.71e-04 std=0.480 grip_std=0.297 success_ema: insert_key=0.339
[03:00:37] it=30 min=5.7 fps=2424 kl=0.0132 lr=5.06e-05 std=0.469 grip_std=0.297 success_ema: insert_key=0.394
[03:02:51] it=40 min=7.9 fps=2496 kl=0.0146 lr=3.38e-05 std=0.459 grip_std=0.296 success_ema: insert_key=0.45
[03:05:02] it=50 min=10.1 fps=2476 kl=0.0118 lr=3.38e-05 std=0.453 grip_std=0.295 success_ema: insert_key=0.49
[03:07:15] it=60 min=12.3 fps=2465 kl=0.0089 lr=3.38e-05 std=0.450 grip_std=0.295 success_ema: insert_key=0.516
[03:09:18] it=70 min=14.3 fps=3204 kl=0.0132 lr=7.59e-05 std=0.448 grip_std=0.294 success_ema: insert_key=0.538
[03:11:21] it=80 min=16.4 fps=2522 kl=0.0181 lr=1.00e-05 std=0.446 grip_std=0.294 success_ema: insert_key=0.549
[03:13:17] it=90 min=18.3 fps=3207 kl=0.0124 lr=2.25e-05 std=0.444 grip_std=0.293 success_ema: insert_key=0.555
[03:15:02] it=100 min=20.1 fps=2549 kl=0.0138 lr=3.38e-05 std=0.443 grip_std=0.293 success_ema: insert_key=0.565
[03:16:56] it=110 min=22.0 fps=3136 kl=0.0111 lr=1.50e-05 std=0.442 grip_std=0.293 success_ema: insert_key=0.575
[03:18:37] it=120 min=23.7 fps=3276 kl=0.0115 lr=3.38e-05 std=0.441 grip_std=0.293 success_ema: insert_key=0.578
[03:20:17] it=130 min=25.3 fps=3321 kl=0.0114 lr=3.38e-05 std=0.439 grip_std=0.292 success_ema: insert_key=0.587
[03:21:57] it=140 min=27.0 fps=3291 kl=0.0141 lr=2.25e-05 std=0.439 grip_std=0.292 success_ema: insert_key=0.603
[03:23:48] it=150 min=28.8 fps=2551 kl=0.0124 lr=1.00e-05 std=0.437 grip_std=0.292 success_ema: insert_key=0.616
[03:25:33] it=160 min=30.6 fps=3325 kl=0.0136 lr=2.25e-05 std=0.437 grip_std=0.292 success_ema: insert_key=0.626
[03:27:12] it=170 min=32.2 fps=3304 kl=0.0118 lr=2.25e-05 std=0.436 grip_std=0.292 success_ema: insert_key=0.64
[03:28:49] it=180 min=33.9 fps=3335 kl=0.0085 lr=2.25e-05 std=0.435 grip_std=0.291 success_ema: insert_key=0.654
[03:30:27] it=190 min=35.5 fps=3388 kl=0.0128 lr=5.06e-05 std=0.434 grip_std=0.291 success_ema: insert_key=0.672
[03:32:20] it=200 min=37.4 fps=2624 kl=0.0143 lr=2.25e-05 std=0.432 grip_std=0.291 success_ema: insert_key=0.68
[03:33:59] it=210 min=39.0 fps=3380 kl=0.0109 lr=3.38e-05 std=0.432 grip_std=0.291 success_ema: insert_key=0.699
[03:35:36] it=220 min=40.6 fps=3354 kl=0.0089 lr=2.25e-05 std=0.431 grip_std=0.291 success_ema: insert_key=0.717
[03:37:12] it=230 min=42.2 fps=3450 kl=0.0142 lr=1.00e-05 std=0.430 grip_std=0.291 success_ema: insert_key=0.731
[03:38:48] it=240 min=43.8 fps=3386 kl=0.0123 lr=1.00e-05 std=0.429 grip_std=0.291 success_ema: insert_key=0.748
[03:40:48] it=250 min=45.8 fps=2512 kl=0.0107 lr=1.00e-05 std=0.427 grip_std=0.291 success_ema: insert_key=0.754
[03:43:03] it=260 min=48.1 fps=2440 kl=0.0111 lr=3.38e-05 std=0.426 grip_std=0.290 success_ema: insert_key=0.762
[03:45:19] it=270 min=50.3 fps=2461 kl=0.0140 lr=1.00e-05 std=0.425 grip_std=0.290 success_ema: insert_key=0.771
[03:47:35] it=280 min=52.6 fps=2432 kl=0.0151 lr=1.00e-05 std=0.424 grip_std=0.290 success_ema: insert_key=0.779
[03:49:53] it=290 min=54.9 fps=2411 kl=0.0098 lr=3.38e-05 std=0.423 grip_std=0.289 success_ema: insert_key=0.785
[03:52:09] it=300 min=57.2 fps=2459 kl=0.0139 lr=2.25e-05 std=0.422 grip_std=0.289 success_ema: insert_key=0.79
[03:54:25] it=310 min=59.5 fps=2429 kl=0.0104 lr=1.50e-05 std=0.421 grip_std=0.289 success_ema: insert_key=0.804
[03:56:42] it=320 min=61.7 fps=2423 kl=0.0135 lr=1.00e-05 std=0.420 grip_std=0.289 success_ema: insert_key=0.813
[03:58:59] it=330 min=64.0 fps=2441 kl=0.0138 lr=1.00e-05 std=0.419 grip_std=0.289 success_ema: insert_key=0.814
[04:01:16] it=340 min=66.3 fps=2405 kl=0.0110 lr=1.00e-05 std=0.418 grip_std=0.289 success_ema: insert_key=0.823
[04:03:33] it=350 min=68.6 fps=2420 kl=0.0127 lr=1.50e-05 std=0.417 grip_std=0.289 success_ema: insert_key=0.824
[04:05:49] it=360 min=70.8 fps=2427 kl=0.0118 lr=1.50e-05 std=0.416 grip_std=0.289 success_ema: insert_key=0.829
[04:08:06] it=370 min=73.1 fps=2313 kl=0.0126 lr=1.50e-05 std=0.415 grip_std=0.289 success_ema: insert_key=0.842
[04:10:23] it=380 min=75.4 fps=2313 kl=0.0155 lr=1.00e-05 std=0.414 grip_std=0.289 success_ema: insert_key=0.842
[04:12:34] it=390 min=77.6 fps=3322 kl=0.0135 lr=1.50e-05 std=0.413 grip_std=0.290 success_ema: insert_key=0.848
[04:14:11] it=400 min=79.2 fps=3380 kl=0.0131 lr=1.00e-05 std=0.412 grip_std=0.290 success_ema: insert_key=0.856
[04:15:48] it=410 min=80.8 fps=3427 kl=0.0142 lr=2.25e-05 std=0.411 grip_std=0.289 success_ema: insert_key=0.867
[04:17:25] it=420 min=82.5 fps=3336 kl=0.0107 lr=2.25e-05 std=0.410 grip_std=0.289 success_ema: insert_key=0.865
[04:19:02] it=430 min=84.1 fps=3371 kl=0.0172 lr=1.00e-05 std=0.409 grip_std=0.289 success_ema: insert_key=0.874
[04:20:40] it=440 min=85.7 fps=3335 kl=0.0140 lr=1.00e-05 std=0.408 grip_std=0.289 success_ema: insert_key=0.878
[04:22:17] it=450 min=87.3 fps=3422 kl=0.0131 lr=1.00e-05 std=0.407 grip_std=0.289 success_ema: insert_key=0.879
[04:23:54] it=460 min=88.9 fps=3392 kl=0.0140 lr=1.00e-05 std=0.406 grip_std=0.289 success_ema: insert_key=0.878
[04:25:02] time budget reached after 468 iterations