queue status update
Browse files- queue_status.json +388 -388
queue_status.json
CHANGED
|
@@ -1,10 +1,10 @@
|
|
| 1 |
{
|
| 2 |
-
"timestamp": "2026-04-12 08:
|
| 3 |
"total": 120,
|
| 4 |
-
"pending":
|
| 5 |
-
"running":
|
| 6 |
"done": 15,
|
| 7 |
-
"failed":
|
| 8 |
"stale": 0,
|
| 9 |
"retrying": 0,
|
| 10 |
"jobs": [
|
|
@@ -15,7 +15,7 @@
|
|
| 15 |
"gpu": 0,
|
| 16 |
"status": "done",
|
| 17 |
"elapsed": 1786,
|
| 18 |
-
"idle_time":
|
| 19 |
"exit_code": 0,
|
| 20 |
"retries": 0,
|
| 21 |
"log_file": "/tmp/gpu_queue/job_000_add_sub_baseline_10K_gpu0.log"
|
|
@@ -27,7 +27,7 @@
|
|
| 27 |
"gpu": 1,
|
| 28 |
"status": "done",
|
| 29 |
"elapsed": 2101,
|
| 30 |
-
"idle_time":
|
| 31 |
"exit_code": 0,
|
| 32 |
"retries": 0,
|
| 33 |
"log_file": "/tmp/gpu_queue/job_001_add_sub_baseline_25K_gpu1.log"
|
|
@@ -39,7 +39,7 @@
|
|
| 39 |
"gpu": 2,
|
| 40 |
"status": "done",
|
| 41 |
"elapsed": 4753,
|
| 42 |
-
"idle_time":
|
| 43 |
"exit_code": 0,
|
| 44 |
"retries": 0,
|
| 45 |
"log_file": "/tmp/gpu_queue/job_002_as_sorl_abs10_K1_25K_gpu2.log"
|
|
@@ -51,7 +51,7 @@
|
|
| 51 |
"gpu": 0,
|
| 52 |
"status": "done",
|
| 53 |
"elapsed": 2366,
|
| 54 |
-
"idle_time":
|
| 55 |
"exit_code": 0,
|
| 56 |
"retries": 0,
|
| 57 |
"log_file": "/tmp/gpu_queue/job_003_add_sub_baseline_50K_gpu0.log"
|
|
@@ -63,7 +63,7 @@
|
|
| 63 |
"gpu": 1,
|
| 64 |
"status": "done",
|
| 65 |
"elapsed": 6727,
|
| 66 |
-
"idle_time":
|
| 67 |
"exit_code": 0,
|
| 68 |
"retries": 0,
|
| 69 |
"log_file": "/tmp/gpu_queue/job_004_as_sorl_abs10_K1_50K_gpu1.log"
|
|
@@ -75,7 +75,7 @@
|
|
| 75 |
"gpu": 2,
|
| 76 |
"status": "done",
|
| 77 |
"elapsed": 3112,
|
| 78 |
-
"idle_time":
|
| 79 |
"exit_code": 0,
|
| 80 |
"retries": 0,
|
| 81 |
"log_file": "/tmp/gpu_queue/job_005_add_sub_baseline_100K_gpu2.log"
|
|
@@ -87,7 +87,7 @@
|
|
| 87 |
"gpu": 0,
|
| 88 |
"status": "done",
|
| 89 |
"elapsed": 8856,
|
| 90 |
-
"idle_time":
|
| 91 |
"exit_code": 0,
|
| 92 |
"retries": 0,
|
| 93 |
"log_file": "/tmp/gpu_queue/job_006_as_sorl_abs10_K1_100K_gpu0.log"
|
|
@@ -120,25 +120,25 @@
|
|
| 120 |
"job_id": 9,
|
| 121 |
"name": "add_sub_baseline_500K",
|
| 122 |
"cmd": "python -m arithmetic.train --mode baseline --ops add_sub --dataset_size 500000 --num_epochs 20 --pus",
|
| 123 |
-
"gpu":
|
| 124 |
-
"status": "
|
| 125 |
-
"elapsed":
|
| 126 |
-
"idle_time":
|
| 127 |
-
"exit_code": -
|
| 128 |
-
"retries":
|
| 129 |
-
"log_file": ""
|
| 130 |
},
|
| 131 |
{
|
| 132 |
"job_id": 10,
|
| 133 |
"name": "as_sorl_abs10_K1_10K",
|
| 134 |
"cmd": "python -m arithmetic.train --mode sorl --ops add_sub --dataset_size 10000 --abs_vocab 10 --K 1 --num",
|
| 135 |
-
"gpu":
|
| 136 |
-
"status": "
|
| 137 |
-
"elapsed":
|
| 138 |
-
"idle_time":
|
| 139 |
-
"exit_code": -
|
| 140 |
-
"retries":
|
| 141 |
-
"log_file": ""
|
| 142 |
},
|
| 143 |
{
|
| 144 |
"job_id": 11,
|
|
@@ -147,7 +147,7 @@
|
|
| 147 |
"gpu": 2,
|
| 148 |
"status": "failed",
|
| 149 |
"elapsed": 5,
|
| 150 |
-
"idle_time":
|
| 151 |
"exit_code": -9,
|
| 152 |
"retries": 1,
|
| 153 |
"log_file": "/tmp/gpu_queue/job_011_as_sorl_abs2_K4_500K_gpu2.log"
|
|
@@ -156,13 +156,13 @@
|
|
| 156 |
"job_id": 12,
|
| 157 |
"name": "as_sorl_abs5_K4_500K",
|
| 158 |
"cmd": "python -m arithmetic.train --mode sorl --ops add_sub --dataset_size 500000 --abs_vocab 5 --K 4 --num",
|
| 159 |
-
"gpu":
|
| 160 |
-
"status": "
|
| 161 |
-
"elapsed":
|
| 162 |
-
"idle_time":
|
| 163 |
-
"exit_code": -
|
| 164 |
-
"retries":
|
| 165 |
-
"log_file": ""
|
| 166 |
},
|
| 167 |
{
|
| 168 |
"job_id": 13,
|
|
@@ -171,7 +171,7 @@
|
|
| 171 |
"gpu": 0,
|
| 172 |
"status": "failed",
|
| 173 |
"elapsed": 5,
|
| 174 |
-
"idle_time":
|
| 175 |
"exit_code": -9,
|
| 176 |
"retries": 1,
|
| 177 |
"log_file": "/tmp/gpu_queue/job_013_as_sorl_abs10_K4_500K_gpu0.log"
|
|
@@ -180,109 +180,109 @@
|
|
| 180 |
"job_id": 14,
|
| 181 |
"name": "as_sorl_abs16_K4_500K",
|
| 182 |
"cmd": "python -m arithmetic.train --mode sorl --ops add_sub --dataset_size 500000 --abs_vocab 16 --K 4 --nu",
|
| 183 |
-
"gpu":
|
| 184 |
-
"status": "
|
| 185 |
-
"elapsed":
|
| 186 |
-
"idle_time":
|
| 187 |
-
"exit_code": -
|
| 188 |
-
"retries":
|
| 189 |
-
"log_file": ""
|
| 190 |
},
|
| 191 |
{
|
| 192 |
"job_id": 15,
|
| 193 |
"name": "as_sorl_abs20_K4_500K",
|
| 194 |
"cmd": "python -m arithmetic.train --mode sorl --ops add_sub --dataset_size 500000 --abs_vocab 20 --K 4 --nu",
|
| 195 |
-
"gpu":
|
| 196 |
-
"status": "
|
| 197 |
-
"elapsed":
|
| 198 |
-
"idle_time":
|
| 199 |
-
"exit_code": -
|
| 200 |
-
"retries":
|
| 201 |
-
"log_file": ""
|
| 202 |
},
|
| 203 |
{
|
| 204 |
"job_id": 16,
|
| 205 |
"name": "as_sorl_abs50_K4_500K",
|
| 206 |
"cmd": "python -m arithmetic.train --mode sorl --ops add_sub --dataset_size 500000 --abs_vocab 50 --K 4 --nu",
|
| 207 |
-
"gpu":
|
| 208 |
-
"status": "
|
| 209 |
-
"elapsed":
|
| 210 |
-
"idle_time":
|
| 211 |
-
"exit_code": -
|
| 212 |
-
"retries":
|
| 213 |
-
"log_file": ""
|
| 214 |
},
|
| 215 |
{
|
| 216 |
"job_id": 17,
|
| 217 |
"name": "as_sorl_abs70_K4_500K",
|
| 218 |
"cmd": "python -m arithmetic.train --mode sorl --ops add_sub --dataset_size 500000 --abs_vocab 70 --K 4 --nu",
|
| 219 |
-
"gpu":
|
| 220 |
-
"status": "
|
| 221 |
-
"elapsed":
|
| 222 |
-
"idle_time":
|
| 223 |
-
"exit_code": -
|
| 224 |
-
"retries":
|
| 225 |
-
"log_file": ""
|
| 226 |
},
|
| 227 |
{
|
| 228 |
"job_id": 18,
|
| 229 |
"name": "as_sorl_abs100_K4_500K",
|
| 230 |
"cmd": "python -m arithmetic.train --mode sorl --ops add_sub --dataset_size 500000 --abs_vocab 100 --K 4 --n",
|
| 231 |
"gpu": 2,
|
| 232 |
-
"status": "
|
| 233 |
-
"elapsed":
|
| 234 |
-
"idle_time":
|
| 235 |
-
"exit_code": -
|
| 236 |
-
"retries":
|
| 237 |
"log_file": "/tmp/gpu_queue/job_018_as_sorl_abs100_K4_500K_gpu2.log"
|
| 238 |
},
|
| 239 |
{
|
| 240 |
"job_id": 19,
|
| 241 |
"name": "as_sorl_abs2_K1_500K",
|
| 242 |
"cmd": "python -m arithmetic.train --mode sorl --ops add_sub --dataset_size 500000 --abs_vocab 2 --K 1 --num",
|
| 243 |
-
"gpu":
|
| 244 |
-
"status": "
|
| 245 |
-
"elapsed":
|
| 246 |
-
"idle_time":
|
| 247 |
"exit_code": -1,
|
| 248 |
-
"retries":
|
| 249 |
-
"log_file": ""
|
| 250 |
},
|
| 251 |
{
|
| 252 |
"job_id": 20,
|
| 253 |
"name": "as_sorl_abs5_K1_500K",
|
| 254 |
"cmd": "python -m arithmetic.train --mode sorl --ops add_sub --dataset_size 500000 --abs_vocab 5 --K 1 --num",
|
| 255 |
-
"gpu":
|
| 256 |
-
"status": "
|
| 257 |
-
"elapsed":
|
| 258 |
-
"idle_time":
|
| 259 |
"exit_code": -1,
|
| 260 |
-
"retries":
|
| 261 |
-
"log_file": ""
|
| 262 |
},
|
| 263 |
{
|
| 264 |
"job_id": 21,
|
| 265 |
"name": "as_sorl_abs10_K1_500K",
|
| 266 |
"cmd": "python -m arithmetic.train --mode sorl --ops add_sub --dataset_size 500000 --abs_vocab 10 --K 1 --nu",
|
| 267 |
-
"gpu":
|
| 268 |
-
"status": "
|
| 269 |
-
"elapsed":
|
| 270 |
-
"idle_time":
|
| 271 |
-
"exit_code": -
|
| 272 |
-
"retries":
|
| 273 |
-
"log_file": ""
|
| 274 |
},
|
| 275 |
{
|
| 276 |
"job_id": 22,
|
| 277 |
"name": "as_sorl_abs16_K1_500K",
|
| 278 |
"cmd": "python -m arithmetic.train --mode sorl --ops add_sub --dataset_size 500000 --abs_vocab 16 --K 1 --nu",
|
| 279 |
-
"gpu":
|
| 280 |
-
"status": "
|
| 281 |
-
"elapsed":
|
| 282 |
-
"idle_time":
|
| 283 |
"exit_code": -1,
|
| 284 |
-
"retries":
|
| 285 |
-
"log_file": ""
|
| 286 |
},
|
| 287 |
{
|
| 288 |
"job_id": 23,
|
|
@@ -300,37 +300,37 @@
|
|
| 300 |
"job_id": 24,
|
| 301 |
"name": "as_sorl_abs50_K1_500K",
|
| 302 |
"cmd": "python -m arithmetic.train --mode sorl --ops add_sub --dataset_size 500000 --abs_vocab 50 --K 1 --nu",
|
| 303 |
-
"gpu":
|
| 304 |
-
"status": "
|
| 305 |
-
"elapsed":
|
| 306 |
-
"idle_time":
|
| 307 |
-
"exit_code": -
|
| 308 |
-
"retries":
|
| 309 |
-
"log_file": ""
|
| 310 |
},
|
| 311 |
{
|
| 312 |
"job_id": 25,
|
| 313 |
"name": "as_sorl_abs70_K1_500K",
|
| 314 |
"cmd": "python -m arithmetic.train --mode sorl --ops add_sub --dataset_size 500000 --abs_vocab 70 --K 1 --nu",
|
| 315 |
-
"gpu":
|
| 316 |
-
"status": "
|
| 317 |
-
"elapsed":
|
| 318 |
-
"idle_time":
|
| 319 |
-
"exit_code": -
|
| 320 |
-
"retries":
|
| 321 |
-
"log_file": ""
|
| 322 |
},
|
| 323 |
{
|
| 324 |
"job_id": 26,
|
| 325 |
"name": "as_sorl_abs100_K1_500K",
|
| 326 |
"cmd": "python -m arithmetic.train --mode sorl --ops add_sub --dataset_size 500000 --abs_vocab 100 --K 1 --n",
|
| 327 |
-
"gpu":
|
| 328 |
-
"status": "
|
| 329 |
-
"elapsed":
|
| 330 |
-
"idle_time":
|
| 331 |
-
"exit_code": -
|
| 332 |
-
"retries":
|
| 333 |
-
"log_file": ""
|
| 334 |
},
|
| 335 |
{
|
| 336 |
"job_id": 27,
|
|
@@ -339,7 +339,7 @@
|
|
| 339 |
"gpu": 0,
|
| 340 |
"status": "failed",
|
| 341 |
"elapsed": 6,
|
| 342 |
-
"idle_time":
|
| 343 |
"exit_code": -9,
|
| 344 |
"retries": 1,
|
| 345 |
"log_file": "/tmp/gpu_queue/job_027_as_sorl_abs5_K1_25K_gpu0.log"
|
|
@@ -348,109 +348,109 @@
|
|
| 348 |
"job_id": 28,
|
| 349 |
"name": "as_sorl_abs30_K1_25K",
|
| 350 |
"cmd": "python -m arithmetic.train --mode sorl --ops add_sub --dataset_size 25000 --abs_vocab 30 --K 1 --num",
|
| 351 |
-
"gpu":
|
| 352 |
-
"status": "
|
| 353 |
-
"elapsed":
|
| 354 |
-
"idle_time":
|
| 355 |
-
"exit_code": -
|
| 356 |
-
"retries":
|
| 357 |
-
"log_file": ""
|
| 358 |
},
|
| 359 |
{
|
| 360 |
"job_id": 29,
|
| 361 |
"name": "as_sorl_abs50_K1_25K",
|
| 362 |
"cmd": "python -m arithmetic.train --mode sorl --ops add_sub --dataset_size 25000 --abs_vocab 50 --K 1 --num",
|
| 363 |
-
"gpu":
|
| 364 |
-
"status": "
|
| 365 |
-
"elapsed":
|
| 366 |
-
"idle_time":
|
| 367 |
"exit_code": -1,
|
| 368 |
"retries": 0,
|
| 369 |
-
"log_file": ""
|
| 370 |
},
|
| 371 |
{
|
| 372 |
"job_id": 30,
|
| 373 |
"name": "as_sorl_abs5_K1_50K",
|
| 374 |
"cmd": "python -m arithmetic.train --mode sorl --ops add_sub --dataset_size 50000 --abs_vocab 5 --K 1 --num_",
|
| 375 |
-
"gpu":
|
| 376 |
-
"status": "
|
| 377 |
-
"elapsed":
|
| 378 |
"idle_time": 0,
|
| 379 |
-
"exit_code": -
|
| 380 |
-
"retries":
|
| 381 |
-
"log_file": ""
|
| 382 |
},
|
| 383 |
{
|
| 384 |
"job_id": 31,
|
| 385 |
"name": "as_sorl_abs30_K1_50K",
|
| 386 |
"cmd": "python -m arithmetic.train --mode sorl --ops add_sub --dataset_size 50000 --abs_vocab 30 --K 1 --num",
|
| 387 |
-
"gpu":
|
| 388 |
-
"status": "
|
| 389 |
-
"elapsed":
|
| 390 |
-
"idle_time":
|
| 391 |
-
"exit_code": -
|
| 392 |
-
"retries":
|
| 393 |
-
"log_file": ""
|
| 394 |
},
|
| 395 |
{
|
| 396 |
"job_id": 32,
|
| 397 |
"name": "as_sorl_abs50_K1_50K",
|
| 398 |
"cmd": "python -m arithmetic.train --mode sorl --ops add_sub --dataset_size 50000 --abs_vocab 50 --K 1 --num",
|
| 399 |
-
"gpu":
|
| 400 |
-
"status": "
|
| 401 |
-
"elapsed":
|
| 402 |
-
"idle_time":
|
| 403 |
-
"exit_code": -
|
| 404 |
-
"retries":
|
| 405 |
-
"log_file": ""
|
| 406 |
},
|
| 407 |
{
|
| 408 |
"job_id": 33,
|
| 409 |
"name": "as_sorl_abs5_K1_100K",
|
| 410 |
"cmd": "python -m arithmetic.train --mode sorl --ops add_sub --dataset_size 100000 --abs_vocab 5 --K 1 --num",
|
| 411 |
-
"gpu":
|
| 412 |
-
"status": "
|
| 413 |
-
"elapsed":
|
| 414 |
-
"idle_time":
|
| 415 |
-
"exit_code": -
|
| 416 |
-
"retries":
|
| 417 |
-
"log_file": ""
|
| 418 |
},
|
| 419 |
{
|
| 420 |
"job_id": 34,
|
| 421 |
"name": "as_sorl_abs30_K1_100K",
|
| 422 |
"cmd": "python -m arithmetic.train --mode sorl --ops add_sub --dataset_size 100000 --abs_vocab 30 --K 1 --nu",
|
| 423 |
-
"gpu":
|
| 424 |
-
"status": "
|
| 425 |
-
"elapsed":
|
| 426 |
-
"idle_time":
|
| 427 |
-
"exit_code": -
|
| 428 |
-
"retries":
|
| 429 |
-
"log_file": ""
|
| 430 |
},
|
| 431 |
{
|
| 432 |
"job_id": 35,
|
| 433 |
"name": "as_sorl_abs50_K1_100K",
|
| 434 |
"cmd": "python -m arithmetic.train --mode sorl --ops add_sub --dataset_size 100000 --abs_vocab 50 --K 1 --nu",
|
| 435 |
-
"gpu":
|
| 436 |
-
"status": "
|
| 437 |
-
"elapsed":
|
| 438 |
-
"idle_time":
|
| 439 |
-
"exit_code": -
|
| 440 |
-
"retries":
|
| 441 |
-
"log_file": ""
|
| 442 |
},
|
| 443 |
{
|
| 444 |
"job_id": 36,
|
| 445 |
"name": "as_sorl_abs5_K4_25K",
|
| 446 |
"cmd": "python -m arithmetic.train --mode sorl --ops add_sub --dataset_size 25000 --abs_vocab 5 --K 4 --num_",
|
| 447 |
-
"gpu":
|
| 448 |
-
"status": "
|
| 449 |
-
"elapsed":
|
| 450 |
"idle_time": 0,
|
| 451 |
-
"exit_code": -
|
| 452 |
-
"retries":
|
| 453 |
-
"log_file": ""
|
| 454 |
},
|
| 455 |
{
|
| 456 |
"job_id": 37,
|
|
@@ -459,7 +459,7 @@
|
|
| 459 |
"gpu": 0,
|
| 460 |
"status": "done",
|
| 461 |
"elapsed": 4510,
|
| 462 |
-
"idle_time":
|
| 463 |
"exit_code": 0,
|
| 464 |
"retries": 0,
|
| 465 |
"log_file": "/tmp/gpu_queue/job_037_as_sorl_abs10_K4_25K_gpu0.log"
|
|
@@ -468,25 +468,25 @@
|
|
| 468 |
"job_id": 38,
|
| 469 |
"name": "as_sorl_abs30_K4_25K",
|
| 470 |
"cmd": "python -m arithmetic.train --mode sorl --ops add_sub --dataset_size 25000 --abs_vocab 30 --K 4 --num",
|
| 471 |
-
"gpu":
|
| 472 |
-
"status": "
|
| 473 |
-
"elapsed":
|
| 474 |
-
"idle_time":
|
| 475 |
-
"exit_code": -
|
| 476 |
-
"retries":
|
| 477 |
-
"log_file": ""
|
| 478 |
},
|
| 479 |
{
|
| 480 |
"job_id": 39,
|
| 481 |
"name": "as_sorl_abs50_K4_25K",
|
| 482 |
"cmd": "python -m arithmetic.train --mode sorl --ops add_sub --dataset_size 25000 --abs_vocab 50 --K 4 --num",
|
| 483 |
-
"gpu":
|
| 484 |
-
"status": "
|
| 485 |
-
"elapsed":
|
| 486 |
-
"idle_time":
|
| 487 |
-
"exit_code": -
|
| 488 |
-
"retries":
|
| 489 |
-
"log_file": ""
|
| 490 |
},
|
| 491 |
{
|
| 492 |
"job_id": 40,
|
|
@@ -507,7 +507,7 @@
|
|
| 507 |
"gpu": 2,
|
| 508 |
"status": "failed",
|
| 509 |
"elapsed": 6,
|
| 510 |
-
"idle_time":
|
| 511 |
"exit_code": -9,
|
| 512 |
"retries": 1,
|
| 513 |
"log_file": "/tmp/gpu_queue/job_041_as_sorl_abs10_K4_50K_gpu2.log"
|
|
@@ -531,7 +531,7 @@
|
|
| 531 |
"gpu": 0,
|
| 532 |
"status": "done",
|
| 533 |
"elapsed": 5510,
|
| 534 |
-
"idle_time":
|
| 535 |
"exit_code": 0,
|
| 536 |
"retries": 0,
|
| 537 |
"log_file": "/tmp/gpu_queue/job_043_as_sorl_abs50_K4_50K_gpu0.log"
|
|
@@ -540,49 +540,49 @@
|
|
| 540 |
"job_id": 44,
|
| 541 |
"name": "as_sorl_abs5_K4_100K",
|
| 542 |
"cmd": "python -m arithmetic.train --mode sorl --ops add_sub --dataset_size 100000 --abs_vocab 5 --K 4 --num",
|
| 543 |
-
"gpu":
|
| 544 |
-
"status": "
|
| 545 |
-
"elapsed":
|
| 546 |
-
"idle_time":
|
| 547 |
-
"exit_code": -
|
| 548 |
-
"retries":
|
| 549 |
-
"log_file": ""
|
| 550 |
},
|
| 551 |
{
|
| 552 |
"job_id": 45,
|
| 553 |
"name": "as_sorl_abs10_K4_100K",
|
| 554 |
"cmd": "python -m arithmetic.train --mode sorl --ops add_sub --dataset_size 100000 --abs_vocab 10 --K 4 --nu",
|
| 555 |
"gpu": 0,
|
| 556 |
-
"status": "
|
| 557 |
-
"elapsed":
|
| 558 |
-
"idle_time":
|
| 559 |
-
"exit_code": -
|
| 560 |
-
"retries":
|
| 561 |
"log_file": "/tmp/gpu_queue/job_045_as_sorl_abs10_K4_100K_gpu0.log"
|
| 562 |
},
|
| 563 |
{
|
| 564 |
"job_id": 46,
|
| 565 |
"name": "as_sorl_abs30_K4_100K",
|
| 566 |
"cmd": "python -m arithmetic.train --mode sorl --ops add_sub --dataset_size 100000 --abs_vocab 30 --K 4 --nu",
|
| 567 |
-
"gpu":
|
| 568 |
-
"status": "
|
| 569 |
-
"elapsed":
|
| 570 |
-
"idle_time":
|
| 571 |
-
"exit_code": -
|
| 572 |
-
"retries":
|
| 573 |
-
"log_file": ""
|
| 574 |
},
|
| 575 |
{
|
| 576 |
"job_id": 47,
|
| 577 |
"name": "as_sorl_abs50_K4_100K",
|
| 578 |
"cmd": "python -m arithmetic.train --mode sorl --ops add_sub --dataset_size 100000 --abs_vocab 50 --K 4 --nu",
|
| 579 |
-
"gpu":
|
| 580 |
-
"status": "
|
| 581 |
-
"elapsed":
|
| 582 |
-
"idle_time":
|
| 583 |
-
"exit_code": -
|
| 584 |
-
"retries":
|
| 585 |
-
"log_file": ""
|
| 586 |
},
|
| 587 |
{
|
| 588 |
"job_id": 48,
|
|
@@ -615,7 +615,7 @@
|
|
| 615 |
"gpu": 2,
|
| 616 |
"status": "failed",
|
| 617 |
"elapsed": 6,
|
| 618 |
-
"idle_time":
|
| 619 |
"exit_code": -9,
|
| 620 |
"retries": 1,
|
| 621 |
"log_file": "/tmp/gpu_queue/job_050_as_sorl_abs10_K1_zipf10.0_500K_gpu2.log"
|
|
@@ -636,13 +636,13 @@
|
|
| 636 |
"job_id": 52,
|
| 637 |
"name": "as_sorl_abs10_K4_zipf5.0_500K",
|
| 638 |
"cmd": "python -m arithmetic.train --mode sorl --ops add_sub --dataset_size 500000 --abs_vocab 10 --K 4 --al",
|
| 639 |
-
"gpu":
|
| 640 |
-
"status": "
|
| 641 |
-
"elapsed":
|
| 642 |
-
"idle_time":
|
| 643 |
-
"exit_code": -
|
| 644 |
-
"retries":
|
| 645 |
-
"log_file": ""
|
| 646 |
},
|
| 647 |
{
|
| 648 |
"job_id": 53,
|
|
@@ -651,7 +651,7 @@
|
|
| 651 |
"gpu": 1,
|
| 652 |
"status": "failed",
|
| 653 |
"elapsed": 5,
|
| 654 |
-
"idle_time":
|
| 655 |
"exit_code": -9,
|
| 656 |
"retries": 1,
|
| 657 |
"log_file": "/tmp/gpu_queue/job_053_as_sorl_abs10_K4_zipf10.0_500K_gpu1.log"
|
|
@@ -660,13 +660,13 @@
|
|
| 660 |
"job_id": 54,
|
| 661 |
"name": "as_sorl_abs100_K1_zipf2.0_500K",
|
| 662 |
"cmd": "python -m arithmetic.train --mode sorl --ops add_sub --dataset_size 500000 --abs_vocab 100 --K 1 --a",
|
| 663 |
-
"gpu":
|
| 664 |
-
"status": "
|
| 665 |
-
"elapsed":
|
| 666 |
-
"idle_time":
|
| 667 |
-
"exit_code": -
|
| 668 |
-
"retries":
|
| 669 |
-
"log_file": ""
|
| 670 |
},
|
| 671 |
{
|
| 672 |
"job_id": 55,
|
|
@@ -675,7 +675,7 @@
|
|
| 675 |
"gpu": 0,
|
| 676 |
"status": "failed",
|
| 677 |
"elapsed": 5,
|
| 678 |
-
"idle_time":
|
| 679 |
"exit_code": -9,
|
| 680 |
"retries": 1,
|
| 681 |
"log_file": "/tmp/gpu_queue/job_055_as_sorl_abs100_K1_zipf5.0_500K_gpu0.log"
|
|
@@ -696,49 +696,49 @@
|
|
| 696 |
"job_id": 57,
|
| 697 |
"name": "as_sorl_abs100_K4_zipf2.0_500K",
|
| 698 |
"cmd": "python -m arithmetic.train --mode sorl --ops add_sub --dataset_size 500000 --abs_vocab 100 --K 4 --a",
|
| 699 |
-
"gpu":
|
| 700 |
-
"status": "
|
| 701 |
-
"elapsed":
|
| 702 |
-
"idle_time":
|
| 703 |
-
"exit_code": -
|
| 704 |
-
"retries":
|
| 705 |
-
"log_file": ""
|
| 706 |
},
|
| 707 |
{
|
| 708 |
"job_id": 58,
|
| 709 |
"name": "as_sorl_abs100_K4_zipf5.0_500K",
|
| 710 |
"cmd": "python -m arithmetic.train --mode sorl --ops add_sub --dataset_size 500000 --abs_vocab 100 --K 4 --a",
|
| 711 |
"gpu": 1,
|
| 712 |
-
"status": "
|
| 713 |
-
"elapsed":
|
| 714 |
-
"idle_time":
|
| 715 |
-
"exit_code": -
|
| 716 |
-
"retries":
|
| 717 |
"log_file": "/tmp/gpu_queue/job_058_as_sorl_abs100_K4_zipf5.0_500K_gpu1.log"
|
| 718 |
},
|
| 719 |
{
|
| 720 |
"job_id": 59,
|
| 721 |
"name": "as_sorl_abs100_K4_zipf10.0_500K",
|
| 722 |
"cmd": "python -m arithmetic.train --mode sorl --ops add_sub --dataset_size 500000 --abs_vocab 100 --K 4 --a",
|
| 723 |
-
"gpu":
|
| 724 |
-
"status": "
|
| 725 |
-
"elapsed":
|
| 726 |
-
"idle_time":
|
| 727 |
-
"exit_code": -
|
| 728 |
-
"retries":
|
| 729 |
-
"log_file": ""
|
| 730 |
},
|
| 731 |
{
|
| 732 |
"job_id": 60,
|
| 733 |
"name": "as_baseline_25K_1L3H510d",
|
| 734 |
"cmd": "python -m arithmetic.train --mode baseline --ops add_sub --dataset_size 25000 --num_epochs 20 --n_la",
|
| 735 |
-
"gpu":
|
| 736 |
-
"status": "
|
| 737 |
-
"elapsed":
|
| 738 |
-
"idle_time":
|
| 739 |
-
"exit_code": -
|
| 740 |
-
"retries":
|
| 741 |
-
"log_file": ""
|
| 742 |
},
|
| 743 |
{
|
| 744 |
"job_id": 61,
|
|
@@ -759,7 +759,7 @@
|
|
| 759 |
"gpu": 0,
|
| 760 |
"status": "failed",
|
| 761 |
"elapsed": 5,
|
| 762 |
-
"idle_time":
|
| 763 |
"exit_code": -9,
|
| 764 |
"retries": 1,
|
| 765 |
"log_file": "/tmp/gpu_queue/job_062_as_baseline_50K_1L3H510d_gpu0.log"
|
|
@@ -771,7 +771,7 @@
|
|
| 771 |
"gpu": 0,
|
| 772 |
"status": "done",
|
| 773 |
"elapsed": 5352,
|
| 774 |
-
"idle_time":
|
| 775 |
"exit_code": 0,
|
| 776 |
"retries": 0,
|
| 777 |
"log_file": "/tmp/gpu_queue/job_063_as_sorl_abs10_K1_50K_1L3H510d_gpu0.log"
|
|
@@ -783,7 +783,7 @@
|
|
| 783 |
"gpu": 1,
|
| 784 |
"status": "failed",
|
| 785 |
"elapsed": 4,
|
| 786 |
-
"idle_time":
|
| 787 |
"exit_code": -15,
|
| 788 |
"retries": 1,
|
| 789 |
"log_file": "/tmp/gpu_queue/job_064_as_baseline_100K_1L3H510d_gpu1.log"
|
|
@@ -795,7 +795,7 @@
|
|
| 795 |
"gpu": 0,
|
| 796 |
"status": "failed",
|
| 797 |
"elapsed": 6,
|
| 798 |
-
"idle_time":
|
| 799 |
"exit_code": -9,
|
| 800 |
"retries": 1,
|
| 801 |
"log_file": "/tmp/gpu_queue/job_065_as_sorl_abs10_K1_100K_1L3H510d_gpu0.log"
|
|
@@ -804,37 +804,37 @@
|
|
| 804 |
"job_id": 66,
|
| 805 |
"name": "as_baseline_250K_1L3H510d",
|
| 806 |
"cmd": "python -m arithmetic.train --mode baseline --ops add_sub --dataset_size 250000 --num_epochs 20 --n_l",
|
| 807 |
-
"gpu":
|
| 808 |
-
"status": "
|
| 809 |
-
"elapsed":
|
| 810 |
-
"idle_time":
|
| 811 |
-
"exit_code": -
|
| 812 |
-
"retries":
|
| 813 |
-
"log_file": ""
|
| 814 |
},
|
| 815 |
{
|
| 816 |
"job_id": 67,
|
| 817 |
"name": "as_sorl_abs10_K1_250K_1L3H510d",
|
| 818 |
"cmd": "python -m arithmetic.train --mode sorl --ops add_sub --dataset_size 250000 --abs_vocab 10 --K 1 --nu",
|
| 819 |
-
"gpu":
|
| 820 |
-
"status": "
|
| 821 |
-
"elapsed":
|
| 822 |
-
"idle_time":
|
| 823 |
-
"exit_code": -
|
| 824 |
-
"retries":
|
| 825 |
-
"log_file": ""
|
| 826 |
},
|
| 827 |
{
|
| 828 |
"job_id": 68,
|
| 829 |
"name": "as_baseline_500K_1L3H510d",
|
| 830 |
"cmd": "python -m arithmetic.train --mode baseline --ops add_sub --dataset_size 500000 --num_epochs 20 --n_l",
|
| 831 |
-
"gpu":
|
| 832 |
-
"status": "
|
| 833 |
-
"elapsed":
|
| 834 |
-
"idle_time":
|
| 835 |
-
"exit_code": -
|
| 836 |
-
"retries":
|
| 837 |
-
"log_file": ""
|
| 838 |
},
|
| 839 |
{
|
| 840 |
"job_id": 69,
|
|
@@ -843,7 +843,7 @@
|
|
| 843 |
"gpu": 2,
|
| 844 |
"status": "failed",
|
| 845 |
"elapsed": 2,
|
| 846 |
-
"idle_time":
|
| 847 |
"exit_code": -15,
|
| 848 |
"retries": 1,
|
| 849 |
"log_file": "/tmp/gpu_queue/job_069_as_sorl_abs10_K1_500K_1L3H510d_gpu2.log"
|
|
@@ -855,7 +855,7 @@
|
|
| 855 |
"gpu": 1,
|
| 856 |
"status": "failed",
|
| 857 |
"elapsed": 6,
|
| 858 |
-
"idle_time":
|
| 859 |
"exit_code": -9,
|
| 860 |
"retries": 1,
|
| 861 |
"log_file": "/tmp/gpu_queue/job_070_as_baseline_25K_1L2H256d_gpu1.log"
|
|
@@ -864,13 +864,13 @@
|
|
| 864 |
"job_id": 71,
|
| 865 |
"name": "as_sorl_abs10_K1_25K_1L2H256d",
|
| 866 |
"cmd": "python -m arithmetic.train --mode sorl --ops add_sub --dataset_size 25000 --abs_vocab 10 --K 1 --num",
|
| 867 |
-
"gpu":
|
| 868 |
-
"status": "
|
| 869 |
-
"elapsed":
|
| 870 |
-
"idle_time":
|
| 871 |
-
"exit_code": -
|
| 872 |
-
"retries":
|
| 873 |
-
"log_file": ""
|
| 874 |
},
|
| 875 |
{
|
| 876 |
"job_id": 72,
|
|
@@ -903,7 +903,7 @@
|
|
| 903 |
"gpu": 2,
|
| 904 |
"status": "done",
|
| 905 |
"elapsed": 2797,
|
| 906 |
-
"idle_time":
|
| 907 |
"exit_code": 0,
|
| 908 |
"retries": 0,
|
| 909 |
"log_file": "/tmp/gpu_queue/job_074_as_baseline_100K_1L2H256d_gpu2.log"
|
|
@@ -915,7 +915,7 @@
|
|
| 915 |
"gpu": 1,
|
| 916 |
"status": "failed",
|
| 917 |
"elapsed": 6,
|
| 918 |
-
"idle_time":
|
| 919 |
"exit_code": -9,
|
| 920 |
"retries": 1,
|
| 921 |
"log_file": "/tmp/gpu_queue/job_075_as_sorl_abs10_K1_100K_1L2H256d_gpu1.log"
|
|
@@ -927,7 +927,7 @@
|
|
| 927 |
"gpu": 0,
|
| 928 |
"status": "done",
|
| 929 |
"elapsed": 4832,
|
| 930 |
-
"idle_time":
|
| 931 |
"exit_code": 0,
|
| 932 |
"retries": 0,
|
| 933 |
"log_file": "/tmp/gpu_queue/job_076_as_baseline_250K_1L2H256d_gpu0.log"
|
|
@@ -951,7 +951,7 @@
|
|
| 951 |
"gpu": 2,
|
| 952 |
"status": "done",
|
| 953 |
"elapsed": 7064,
|
| 954 |
-
"idle_time":
|
| 955 |
"exit_code": 0,
|
| 956 |
"retries": 0,
|
| 957 |
"log_file": "/tmp/gpu_queue/job_078_as_baseline_500K_1L2H256d_gpu2.log"
|
|
@@ -960,13 +960,13 @@
|
|
| 960 |
"job_id": 79,
|
| 961 |
"name": "as_sorl_abs10_K1_500K_1L2H256d",
|
| 962 |
"cmd": "python -m arithmetic.train --mode sorl --ops add_sub --dataset_size 500000 --abs_vocab 10 --K 1 --nu",
|
| 963 |
-
"gpu":
|
| 964 |
-
"status": "
|
| 965 |
-
"elapsed":
|
| 966 |
-
"idle_time":
|
| 967 |
-
"exit_code": -
|
| 968 |
-
"retries":
|
| 969 |
-
"log_file": ""
|
| 970 |
},
|
| 971 |
{
|
| 972 |
"job_id": 80,
|
|
@@ -975,7 +975,7 @@
|
|
| 975 |
"gpu": 1,
|
| 976 |
"status": "done",
|
| 977 |
"elapsed": 1971,
|
| 978 |
-
"idle_time":
|
| 979 |
"exit_code": 0,
|
| 980 |
"retries": 0,
|
| 981 |
"log_file": "/tmp/gpu_queue/job_080_as_baseline_25K_2L1H128d_gpu1.log"
|
|
@@ -984,25 +984,25 @@
|
|
| 984 |
"job_id": 81,
|
| 985 |
"name": "as_sorl_abs10_K1_25K_2L1H128d",
|
| 986 |
"cmd": "python -m arithmetic.train --mode sorl --ops add_sub --dataset_size 25000 --abs_vocab 10 --K 1 --num",
|
| 987 |
-
"gpu":
|
| 988 |
-
"status": "
|
| 989 |
-
"elapsed":
|
| 990 |
-
"idle_time":
|
| 991 |
-
"exit_code": -
|
| 992 |
-
"retries":
|
| 993 |
-
"log_file": ""
|
| 994 |
},
|
| 995 |
{
|
| 996 |
"job_id": 82,
|
| 997 |
"name": "as_baseline_50K_2L1H128d",
|
| 998 |
"cmd": "python -m arithmetic.train --mode baseline --ops add_sub --dataset_size 50000 --num_epochs 20 --n_la",
|
| 999 |
-
"gpu":
|
| 1000 |
-
"status": "
|
| 1001 |
-
"elapsed":
|
| 1002 |
-
"idle_time":
|
| 1003 |
-
"exit_code": -
|
| 1004 |
-
"retries":
|
| 1005 |
-
"log_file": ""
|
| 1006 |
},
|
| 1007 |
{
|
| 1008 |
"job_id": 83,
|
|
@@ -1020,37 +1020,37 @@
|
|
| 1020 |
"job_id": 84,
|
| 1021 |
"name": "as_baseline_100K_2L1H128d",
|
| 1022 |
"cmd": "python -m arithmetic.train --mode baseline --ops add_sub --dataset_size 100000 --num_epochs 20 --n_l",
|
| 1023 |
-
"gpu":
|
| 1024 |
-
"status": "
|
| 1025 |
-
"elapsed":
|
| 1026 |
-
"idle_time":
|
| 1027 |
-
"exit_code": -
|
| 1028 |
-
"retries":
|
| 1029 |
-
"log_file": ""
|
| 1030 |
},
|
| 1031 |
{
|
| 1032 |
"job_id": 85,
|
| 1033 |
"name": "as_sorl_abs10_K1_100K_2L1H128d",
|
| 1034 |
"cmd": "python -m arithmetic.train --mode sorl --ops add_sub --dataset_size 100000 --abs_vocab 10 --K 1 --nu",
|
| 1035 |
-
"gpu":
|
| 1036 |
-
"status": "
|
| 1037 |
-
"elapsed":
|
| 1038 |
-
"idle_time":
|
| 1039 |
-
"exit_code": -
|
| 1040 |
-
"retries":
|
| 1041 |
-
"log_file": ""
|
| 1042 |
},
|
| 1043 |
{
|
| 1044 |
"job_id": 86,
|
| 1045 |
"name": "as_baseline_250K_2L1H128d",
|
| 1046 |
"cmd": "python -m arithmetic.train --mode baseline --ops add_sub --dataset_size 250000 --num_epochs 20 --n_l",
|
| 1047 |
-
"gpu":
|
| 1048 |
-
"status": "
|
| 1049 |
-
"elapsed":
|
| 1050 |
-
"idle_time":
|
| 1051 |
-
"exit_code": -
|
| 1052 |
-
"retries":
|
| 1053 |
-
"log_file": ""
|
| 1054 |
},
|
| 1055 |
{
|
| 1056 |
"job_id": 87,
|
|
@@ -1059,7 +1059,7 @@
|
|
| 1059 |
"gpu": 1,
|
| 1060 |
"status": "failed",
|
| 1061 |
"elapsed": 5,
|
| 1062 |
-
"idle_time":
|
| 1063 |
"exit_code": -9,
|
| 1064 |
"retries": 1,
|
| 1065 |
"log_file": "/tmp/gpu_queue/job_087_as_sorl_abs10_K1_250K_2L1H128d_gpu1.log"
|
|
@@ -1083,7 +1083,7 @@
|
|
| 1083 |
"gpu": 1,
|
| 1084 |
"status": "failed",
|
| 1085 |
"elapsed": 5,
|
| 1086 |
-
"idle_time":
|
| 1087 |
"exit_code": -9,
|
| 1088 |
"retries": 1,
|
| 1089 |
"log_file": "/tmp/gpu_queue/job_089_as_sorl_abs10_K1_500K_2L1H128d_gpu1.log"
|
|
@@ -1104,13 +1104,13 @@
|
|
| 1104 |
"job_id": 91,
|
| 1105 |
"name": "as_sorl_abs10_K4_10K",
|
| 1106 |
"cmd": "python -m arithmetic.train --mode sorl --ops add_sub --dataset_size 10000 --abs_vocab 10 --K 4 --num",
|
| 1107 |
-
"gpu":
|
| 1108 |
-
"status": "
|
| 1109 |
-
"elapsed":
|
| 1110 |
-
"idle_time":
|
| 1111 |
-
"exit_code": -
|
| 1112 |
-
"retries":
|
| 1113 |
-
"log_file": ""
|
| 1114 |
},
|
| 1115 |
{
|
| 1116 |
"job_id": 92,
|
|
@@ -1119,7 +1119,7 @@
|
|
| 1119 |
"gpu": 0,
|
| 1120 |
"status": "done",
|
| 1121 |
"elapsed": 3477,
|
| 1122 |
-
"idle_time":
|
| 1123 |
"exit_code": 0,
|
| 1124 |
"retries": 0,
|
| 1125 |
"log_file": "/tmp/gpu_queue/job_092_as_sorl_abs30_K4_10K_gpu0.log"
|
|
@@ -1128,25 +1128,25 @@
|
|
| 1128 |
"job_id": 93,
|
| 1129 |
"name": "as_sorl_abs50_K4_10K",
|
| 1130 |
"cmd": "python -m arithmetic.train --mode sorl --ops add_sub --dataset_size 10000 --abs_vocab 50 --K 4 --num",
|
| 1131 |
-
"gpu":
|
| 1132 |
-
"status": "
|
| 1133 |
-
"elapsed":
|
| 1134 |
-
"idle_time":
|
| 1135 |
-
"exit_code": -
|
| 1136 |
-
"retries":
|
| 1137 |
-
"log_file": ""
|
| 1138 |
},
|
| 1139 |
{
|
| 1140 |
"job_id": 94,
|
| 1141 |
"name": "as_sorl_abs5_K4_250K",
|
| 1142 |
"cmd": "python -m arithmetic.train --mode sorl --ops add_sub --dataset_size 250000 --abs_vocab 5 --K 4 --num",
|
| 1143 |
-
"gpu":
|
| 1144 |
-
"status": "
|
| 1145 |
-
"elapsed":
|
| 1146 |
-
"idle_time":
|
| 1147 |
-
"exit_code": -
|
| 1148 |
-
"retries":
|
| 1149 |
-
"log_file": ""
|
| 1150 |
},
|
| 1151 |
{
|
| 1152 |
"job_id": 95,
|
|
@@ -1155,7 +1155,7 @@
|
|
| 1155 |
"gpu": 2,
|
| 1156 |
"status": "failed",
|
| 1157 |
"elapsed": 5,
|
| 1158 |
-
"idle_time":
|
| 1159 |
"exit_code": -9,
|
| 1160 |
"retries": 1,
|
| 1161 |
"log_file": "/tmp/gpu_queue/job_095_as_sorl_abs10_K4_250K_gpu2.log"
|
|
@@ -1164,25 +1164,25 @@
|
|
| 1164 |
"job_id": 96,
|
| 1165 |
"name": "as_sorl_abs30_K4_250K",
|
| 1166 |
"cmd": "python -m arithmetic.train --mode sorl --ops add_sub --dataset_size 250000 --abs_vocab 30 --K 4 --nu",
|
| 1167 |
-
"gpu":
|
| 1168 |
-
"status": "
|
| 1169 |
-
"elapsed":
|
| 1170 |
-
"idle_time":
|
| 1171 |
-
"exit_code": -
|
| 1172 |
-
"retries":
|
| 1173 |
-
"log_file": ""
|
| 1174 |
},
|
| 1175 |
{
|
| 1176 |
"job_id": 97,
|
| 1177 |
"name": "as_sorl_abs50_K4_250K",
|
| 1178 |
"cmd": "python -m arithmetic.train --mode sorl --ops add_sub --dataset_size 250000 --abs_vocab 50 --K 4 --nu",
|
| 1179 |
-
"gpu":
|
| 1180 |
-
"status": "
|
| 1181 |
-
"elapsed":
|
| 1182 |
-
"idle_time":
|
| 1183 |
-
"exit_code": -
|
| 1184 |
-
"retries":
|
| 1185 |
-
"log_file": ""
|
| 1186 |
},
|
| 1187 |
{
|
| 1188 |
"job_id": 98,
|
|
@@ -1191,7 +1191,7 @@
|
|
| 1191 |
"gpu": 1,
|
| 1192 |
"status": "failed",
|
| 1193 |
"elapsed": 3,
|
| 1194 |
-
"idle_time":
|
| 1195 |
"exit_code": -15,
|
| 1196 |
"retries": 1,
|
| 1197 |
"log_file": "/tmp/gpu_queue/job_098_as_sorl_abs2_K1_100K_gpu1.log"
|
|
@@ -1203,7 +1203,7 @@
|
|
| 1203 |
"gpu": 1,
|
| 1204 |
"status": "failed",
|
| 1205 |
"elapsed": 5,
|
| 1206 |
-
"idle_time":
|
| 1207 |
"exit_code": -9,
|
| 1208 |
"retries": 1,
|
| 1209 |
"log_file": "/tmp/gpu_queue/job_099_as_sorl_abs2_K4_100K_gpu1.log"
|
|
@@ -1212,13 +1212,13 @@
|
|
| 1212 |
"job_id": 100,
|
| 1213 |
"name": "as_sorl_abs16_K1_100K",
|
| 1214 |
"cmd": "python -m arithmetic.train --mode sorl --ops add_sub --dataset_size 100000 --abs_vocab 16 --K 1 --nu",
|
| 1215 |
-
"gpu":
|
| 1216 |
-
"status": "
|
| 1217 |
-
"elapsed":
|
| 1218 |
-
"idle_time":
|
| 1219 |
-
"exit_code": -
|
| 1220 |
-
"retries":
|
| 1221 |
-
"log_file": ""
|
| 1222 |
},
|
| 1223 |
{
|
| 1224 |
"job_id": 101,
|
|
|
|
| 1 |
{
|
| 2 |
+
"timestamp": "2026-04-12 08:09:30",
|
| 3 |
"total": 120,
|
| 4 |
+
"pending": 35,
|
| 5 |
+
"running": 4,
|
| 6 |
"done": 15,
|
| 7 |
+
"failed": 66,
|
| 8 |
"stale": 0,
|
| 9 |
"retrying": 0,
|
| 10 |
"jobs": [
|
|
|
|
| 15 |
"gpu": 0,
|
| 16 |
"status": "done",
|
| 17 |
"elapsed": 1786,
|
| 18 |
+
"idle_time": 20508,
|
| 19 |
"exit_code": 0,
|
| 20 |
"retries": 0,
|
| 21 |
"log_file": "/tmp/gpu_queue/job_000_add_sub_baseline_10K_gpu0.log"
|
|
|
|
| 27 |
"gpu": 1,
|
| 28 |
"status": "done",
|
| 29 |
"elapsed": 2101,
|
| 30 |
+
"idle_time": 20193,
|
| 31 |
"exit_code": 0,
|
| 32 |
"retries": 0,
|
| 33 |
"log_file": "/tmp/gpu_queue/job_001_add_sub_baseline_25K_gpu1.log"
|
|
|
|
| 39 |
"gpu": 2,
|
| 40 |
"status": "done",
|
| 41 |
"elapsed": 4753,
|
| 42 |
+
"idle_time": 17541,
|
| 43 |
"exit_code": 0,
|
| 44 |
"retries": 0,
|
| 45 |
"log_file": "/tmp/gpu_queue/job_002_as_sorl_abs10_K1_25K_gpu2.log"
|
|
|
|
| 51 |
"gpu": 0,
|
| 52 |
"status": "done",
|
| 53 |
"elapsed": 2366,
|
| 54 |
+
"idle_time": 19928,
|
| 55 |
"exit_code": 0,
|
| 56 |
"retries": 0,
|
| 57 |
"log_file": "/tmp/gpu_queue/job_003_add_sub_baseline_50K_gpu0.log"
|
|
|
|
| 63 |
"gpu": 1,
|
| 64 |
"status": "done",
|
| 65 |
"elapsed": 6727,
|
| 66 |
+
"idle_time": 15567,
|
| 67 |
"exit_code": 0,
|
| 68 |
"retries": 0,
|
| 69 |
"log_file": "/tmp/gpu_queue/job_004_as_sorl_abs10_K1_50K_gpu1.log"
|
|
|
|
| 75 |
"gpu": 2,
|
| 76 |
"status": "done",
|
| 77 |
"elapsed": 3112,
|
| 78 |
+
"idle_time": 19181,
|
| 79 |
"exit_code": 0,
|
| 80 |
"retries": 0,
|
| 81 |
"log_file": "/tmp/gpu_queue/job_005_add_sub_baseline_100K_gpu2.log"
|
|
|
|
| 87 |
"gpu": 0,
|
| 88 |
"status": "done",
|
| 89 |
"elapsed": 8856,
|
| 90 |
+
"idle_time": 11648,
|
| 91 |
"exit_code": 0,
|
| 92 |
"retries": 0,
|
| 93 |
"log_file": "/tmp/gpu_queue/job_006_as_sorl_abs10_K1_100K_gpu0.log"
|
|
|
|
| 120 |
"job_id": 9,
|
| 121 |
"name": "add_sub_baseline_500K",
|
| 122 |
"cmd": "python -m arithmetic.train --mode baseline --ops add_sub --dataset_size 500000 --num_epochs 20 --pus",
|
| 123 |
+
"gpu": 1,
|
| 124 |
+
"status": "failed",
|
| 125 |
+
"elapsed": 6,
|
| 126 |
+
"idle_time": 15,
|
| 127 |
+
"exit_code": -9,
|
| 128 |
+
"retries": 1,
|
| 129 |
+
"log_file": "/tmp/gpu_queue/job_009_add_sub_baseline_500K_gpu1.log"
|
| 130 |
},
|
| 131 |
{
|
| 132 |
"job_id": 10,
|
| 133 |
"name": "as_sorl_abs10_K1_10K",
|
| 134 |
"cmd": "python -m arithmetic.train --mode sorl --ops add_sub --dataset_size 10000 --abs_vocab 10 --K 1 --num",
|
| 135 |
+
"gpu": 2,
|
| 136 |
+
"status": "failed",
|
| 137 |
+
"elapsed": 6,
|
| 138 |
+
"idle_time": 65,
|
| 139 |
+
"exit_code": -9,
|
| 140 |
+
"retries": 1,
|
| 141 |
+
"log_file": "/tmp/gpu_queue/job_010_as_sorl_abs10_K1_10K_gpu2.log"
|
| 142 |
},
|
| 143 |
{
|
| 144 |
"job_id": 11,
|
|
|
|
| 147 |
"gpu": 2,
|
| 148 |
"status": "failed",
|
| 149 |
"elapsed": 5,
|
| 150 |
+
"idle_time": 120,
|
| 151 |
"exit_code": -9,
|
| 152 |
"retries": 1,
|
| 153 |
"log_file": "/tmp/gpu_queue/job_011_as_sorl_abs2_K4_500K_gpu2.log"
|
|
|
|
| 156 |
"job_id": 12,
|
| 157 |
"name": "as_sorl_abs5_K4_500K",
|
| 158 |
"cmd": "python -m arithmetic.train --mode sorl --ops add_sub --dataset_size 500000 --abs_vocab 5 --K 4 --num",
|
| 159 |
+
"gpu": 1,
|
| 160 |
+
"status": "failed",
|
| 161 |
+
"elapsed": 5,
|
| 162 |
+
"idle_time": 80,
|
| 163 |
+
"exit_code": -9,
|
| 164 |
+
"retries": 1,
|
| 165 |
+
"log_file": "/tmp/gpu_queue/job_012_as_sorl_abs5_K4_500K_gpu1.log"
|
| 166 |
},
|
| 167 |
{
|
| 168 |
"job_id": 13,
|
|
|
|
| 171 |
"gpu": 0,
|
| 172 |
"status": "failed",
|
| 173 |
"elapsed": 5,
|
| 174 |
+
"idle_time": 1154,
|
| 175 |
"exit_code": -9,
|
| 176 |
"retries": 1,
|
| 177 |
"log_file": "/tmp/gpu_queue/job_013_as_sorl_abs10_K4_500K_gpu0.log"
|
|
|
|
| 180 |
"job_id": 14,
|
| 181 |
"name": "as_sorl_abs16_K4_500K",
|
| 182 |
"cmd": "python -m arithmetic.train --mode sorl --ops add_sub --dataset_size 500000 --abs_vocab 16 --K 4 --nu",
|
| 183 |
+
"gpu": 0,
|
| 184 |
+
"status": "failed",
|
| 185 |
+
"elapsed": 6,
|
| 186 |
+
"idle_time": 45,
|
| 187 |
+
"exit_code": -9,
|
| 188 |
+
"retries": 1,
|
| 189 |
+
"log_file": "/tmp/gpu_queue/job_014_as_sorl_abs16_K4_500K_gpu0.log"
|
| 190 |
},
|
| 191 |
{
|
| 192 |
"job_id": 15,
|
| 193 |
"name": "as_sorl_abs20_K4_500K",
|
| 194 |
"cmd": "python -m arithmetic.train --mode sorl --ops add_sub --dataset_size 500000 --abs_vocab 20 --K 4 --nu",
|
| 195 |
+
"gpu": 2,
|
| 196 |
+
"status": "failed",
|
| 197 |
+
"elapsed": 6,
|
| 198 |
+
"idle_time": 15,
|
| 199 |
+
"exit_code": -9,
|
| 200 |
+
"retries": 1,
|
| 201 |
+
"log_file": "/tmp/gpu_queue/job_015_as_sorl_abs20_K4_500K_gpu2.log"
|
| 202 |
},
|
| 203 |
{
|
| 204 |
"job_id": 16,
|
| 205 |
"name": "as_sorl_abs50_K4_500K",
|
| 206 |
"cmd": "python -m arithmetic.train --mode sorl --ops add_sub --dataset_size 500000 --abs_vocab 50 --K 4 --nu",
|
| 207 |
+
"gpu": 1,
|
| 208 |
+
"status": "failed",
|
| 209 |
+
"elapsed": 6,
|
| 210 |
+
"idle_time": 50,
|
| 211 |
+
"exit_code": -9,
|
| 212 |
+
"retries": 1,
|
| 213 |
+
"log_file": "/tmp/gpu_queue/job_016_as_sorl_abs50_K4_500K_gpu1.log"
|
| 214 |
},
|
| 215 |
{
|
| 216 |
"job_id": 17,
|
| 217 |
"name": "as_sorl_abs70_K4_500K",
|
| 218 |
"cmd": "python -m arithmetic.train --mode sorl --ops add_sub --dataset_size 500000 --abs_vocab 70 --K 4 --nu",
|
| 219 |
+
"gpu": 2,
|
| 220 |
+
"status": "failed",
|
| 221 |
+
"elapsed": 6,
|
| 222 |
+
"idle_time": 50,
|
| 223 |
+
"exit_code": -9,
|
| 224 |
+
"retries": 1,
|
| 225 |
+
"log_file": "/tmp/gpu_queue/job_017_as_sorl_abs70_K4_500K_gpu2.log"
|
| 226 |
},
|
| 227 |
{
|
| 228 |
"job_id": 18,
|
| 229 |
"name": "as_sorl_abs100_K4_500K",
|
| 230 |
"cmd": "python -m arithmetic.train --mode sorl --ops add_sub --dataset_size 500000 --abs_vocab 100 --K 4 --n",
|
| 231 |
"gpu": 2,
|
| 232 |
+
"status": "failed",
|
| 233 |
+
"elapsed": 5,
|
| 234 |
+
"idle_time": 110,
|
| 235 |
+
"exit_code": -9,
|
| 236 |
+
"retries": 1,
|
| 237 |
"log_file": "/tmp/gpu_queue/job_018_as_sorl_abs100_K4_500K_gpu2.log"
|
| 238 |
},
|
| 239 |
{
|
| 240 |
"job_id": 19,
|
| 241 |
"name": "as_sorl_abs2_K1_500K",
|
| 242 |
"cmd": "python -m arithmetic.train --mode sorl --ops add_sub --dataset_size 500000 --abs_vocab 2 --K 1 --num",
|
| 243 |
+
"gpu": 1,
|
| 244 |
+
"status": "running",
|
| 245 |
+
"elapsed": 1,
|
| 246 |
+
"idle_time": 1,
|
| 247 |
"exit_code": -1,
|
| 248 |
+
"retries": 1,
|
| 249 |
+
"log_file": "/tmp/gpu_queue/job_019_as_sorl_abs2_K1_500K_gpu1.log"
|
| 250 |
},
|
| 251 |
{
|
| 252 |
"job_id": 20,
|
| 253 |
"name": "as_sorl_abs5_K1_500K",
|
| 254 |
"cmd": "python -m arithmetic.train --mode sorl --ops add_sub --dataset_size 500000 --abs_vocab 5 --K 1 --num",
|
| 255 |
+
"gpu": 1,
|
| 256 |
+
"status": "running",
|
| 257 |
+
"elapsed": 1,
|
| 258 |
+
"idle_time": 1,
|
| 259 |
"exit_code": -1,
|
| 260 |
+
"retries": 1,
|
| 261 |
+
"log_file": "/tmp/gpu_queue/job_020_as_sorl_abs5_K1_500K_gpu1.log"
|
| 262 |
},
|
| 263 |
{
|
| 264 |
"job_id": 21,
|
| 265 |
"name": "as_sorl_abs10_K1_500K",
|
| 266 |
"cmd": "python -m arithmetic.train --mode sorl --ops add_sub --dataset_size 500000 --abs_vocab 10 --K 1 --nu",
|
| 267 |
+
"gpu": 0,
|
| 268 |
+
"status": "failed",
|
| 269 |
+
"elapsed": 6,
|
| 270 |
+
"idle_time": 59,
|
| 271 |
+
"exit_code": -9,
|
| 272 |
+
"retries": 1,
|
| 273 |
+
"log_file": "/tmp/gpu_queue/job_021_as_sorl_abs10_K1_500K_gpu0.log"
|
| 274 |
},
|
| 275 |
{
|
| 276 |
"job_id": 22,
|
| 277 |
"name": "as_sorl_abs16_K1_500K",
|
| 278 |
"cmd": "python -m arithmetic.train --mode sorl --ops add_sub --dataset_size 500000 --abs_vocab 16 --K 1 --nu",
|
| 279 |
+
"gpu": 0,
|
| 280 |
+
"status": "running",
|
| 281 |
+
"elapsed": 1,
|
| 282 |
+
"idle_time": 1,
|
| 283 |
"exit_code": -1,
|
| 284 |
+
"retries": 1,
|
| 285 |
+
"log_file": "/tmp/gpu_queue/job_022_as_sorl_abs16_K1_500K_gpu0.log"
|
| 286 |
},
|
| 287 |
{
|
| 288 |
"job_id": 23,
|
|
|
|
| 300 |
"job_id": 24,
|
| 301 |
"name": "as_sorl_abs50_K1_500K",
|
| 302 |
"cmd": "python -m arithmetic.train --mode sorl --ops add_sub --dataset_size 500000 --abs_vocab 50 --K 1 --nu",
|
| 303 |
+
"gpu": 1,
|
| 304 |
+
"status": "failed",
|
| 305 |
+
"elapsed": 4,
|
| 306 |
+
"idle_time": 41,
|
| 307 |
+
"exit_code": -9,
|
| 308 |
+
"retries": 1,
|
| 309 |
+
"log_file": "/tmp/gpu_queue/job_024_as_sorl_abs50_K1_500K_gpu1.log"
|
| 310 |
},
|
| 311 |
{
|
| 312 |
"job_id": 25,
|
| 313 |
"name": "as_sorl_abs70_K1_500K",
|
| 314 |
"cmd": "python -m arithmetic.train --mode sorl --ops add_sub --dataset_size 500000 --abs_vocab 70 --K 1 --nu",
|
| 315 |
+
"gpu": 2,
|
| 316 |
+
"status": "failed",
|
| 317 |
+
"elapsed": 5,
|
| 318 |
+
"idle_time": 50,
|
| 319 |
+
"exit_code": -9,
|
| 320 |
+
"retries": 1,
|
| 321 |
+
"log_file": "/tmp/gpu_queue/job_025_as_sorl_abs70_K1_500K_gpu2.log"
|
| 322 |
},
|
| 323 |
{
|
| 324 |
"job_id": 26,
|
| 325 |
"name": "as_sorl_abs100_K1_500K",
|
| 326 |
"cmd": "python -m arithmetic.train --mode sorl --ops add_sub --dataset_size 500000 --abs_vocab 100 --K 1 --n",
|
| 327 |
+
"gpu": 1,
|
| 328 |
+
"status": "failed",
|
| 329 |
+
"elapsed": 6,
|
| 330 |
+
"idle_time": 25,
|
| 331 |
+
"exit_code": -9,
|
| 332 |
+
"retries": 1,
|
| 333 |
+
"log_file": "/tmp/gpu_queue/job_026_as_sorl_abs100_K1_500K_gpu1.log"
|
| 334 |
},
|
| 335 |
{
|
| 336 |
"job_id": 27,
|
|
|
|
| 339 |
"gpu": 0,
|
| 340 |
"status": "failed",
|
| 341 |
"elapsed": 6,
|
| 342 |
+
"idle_time": 125,
|
| 343 |
"exit_code": -9,
|
| 344 |
"retries": 1,
|
| 345 |
"log_file": "/tmp/gpu_queue/job_027_as_sorl_abs5_K1_25K_gpu0.log"
|
|
|
|
| 348 |
"job_id": 28,
|
| 349 |
"name": "as_sorl_abs30_K1_25K",
|
| 350 |
"cmd": "python -m arithmetic.train --mode sorl --ops add_sub --dataset_size 25000 --abs_vocab 30 --K 1 --num",
|
| 351 |
+
"gpu": 1,
|
| 352 |
+
"status": "failed",
|
| 353 |
+
"elapsed": 5,
|
| 354 |
+
"idle_time": 59,
|
| 355 |
+
"exit_code": -9,
|
| 356 |
+
"retries": 1,
|
| 357 |
+
"log_file": "/tmp/gpu_queue/job_028_as_sorl_abs30_K1_25K_gpu1.log"
|
| 358 |
},
|
| 359 |
{
|
| 360 |
"job_id": 29,
|
| 361 |
"name": "as_sorl_abs50_K1_25K",
|
| 362 |
"cmd": "python -m arithmetic.train --mode sorl --ops add_sub --dataset_size 25000 --abs_vocab 50 --K 1 --num",
|
| 363 |
+
"gpu": 0,
|
| 364 |
+
"status": "running",
|
| 365 |
+
"elapsed": 1,
|
| 366 |
+
"idle_time": 1,
|
| 367 |
"exit_code": -1,
|
| 368 |
"retries": 0,
|
| 369 |
+
"log_file": "/tmp/gpu_queue/job_029_as_sorl_abs50_K1_25K_gpu0.log"
|
| 370 |
},
|
| 371 |
{
|
| 372 |
"job_id": 30,
|
| 373 |
"name": "as_sorl_abs5_K1_50K",
|
| 374 |
"cmd": "python -m arithmetic.train --mode sorl --ops add_sub --dataset_size 50000 --abs_vocab 5 --K 1 --num_",
|
| 375 |
+
"gpu": 2,
|
| 376 |
+
"status": "failed",
|
| 377 |
+
"elapsed": 6,
|
| 378 |
"idle_time": 0,
|
| 379 |
+
"exit_code": -9,
|
| 380 |
+
"retries": 1,
|
| 381 |
+
"log_file": "/tmp/gpu_queue/job_030_as_sorl_abs5_K1_50K_gpu2.log"
|
| 382 |
},
|
| 383 |
{
|
| 384 |
"job_id": 31,
|
| 385 |
"name": "as_sorl_abs30_K1_50K",
|
| 386 |
"cmd": "python -m arithmetic.train --mode sorl --ops add_sub --dataset_size 50000 --abs_vocab 30 --K 1 --num",
|
| 387 |
+
"gpu": 2,
|
| 388 |
+
"status": "failed",
|
| 389 |
+
"elapsed": 5,
|
| 390 |
+
"idle_time": 105,
|
| 391 |
+
"exit_code": -9,
|
| 392 |
+
"retries": 1,
|
| 393 |
+
"log_file": "/tmp/gpu_queue/job_031_as_sorl_abs30_K1_50K_gpu2.log"
|
| 394 |
},
|
| 395 |
{
|
| 396 |
"job_id": 32,
|
| 397 |
"name": "as_sorl_abs50_K1_50K",
|
| 398 |
"cmd": "python -m arithmetic.train --mode sorl --ops add_sub --dataset_size 50000 --abs_vocab 50 --K 1 --num",
|
| 399 |
+
"gpu": 0,
|
| 400 |
+
"status": "failed",
|
| 401 |
+
"elapsed": 6,
|
| 402 |
+
"idle_time": 25,
|
| 403 |
+
"exit_code": -9,
|
| 404 |
+
"retries": 1,
|
| 405 |
+
"log_file": "/tmp/gpu_queue/job_032_as_sorl_abs50_K1_50K_gpu0.log"
|
| 406 |
},
|
| 407 |
{
|
| 408 |
"job_id": 33,
|
| 409 |
"name": "as_sorl_abs5_K1_100K",
|
| 410 |
"cmd": "python -m arithmetic.train --mode sorl --ops add_sub --dataset_size 100000 --abs_vocab 5 --K 1 --num",
|
| 411 |
+
"gpu": 2,
|
| 412 |
+
"status": "failed",
|
| 413 |
+
"elapsed": 7,
|
| 414 |
+
"idle_time": 64,
|
| 415 |
+
"exit_code": -9,
|
| 416 |
+
"retries": 1,
|
| 417 |
+
"log_file": "/tmp/gpu_queue/job_033_as_sorl_abs5_K1_100K_gpu2.log"
|
| 418 |
},
|
| 419 |
{
|
| 420 |
"job_id": 34,
|
| 421 |
"name": "as_sorl_abs30_K1_100K",
|
| 422 |
"cmd": "python -m arithmetic.train --mode sorl --ops add_sub --dataset_size 100000 --abs_vocab 30 --K 1 --nu",
|
| 423 |
+
"gpu": 0,
|
| 424 |
+
"status": "failed",
|
| 425 |
+
"elapsed": 5,
|
| 426 |
+
"idle_time": 89,
|
| 427 |
+
"exit_code": -9,
|
| 428 |
+
"retries": 1,
|
| 429 |
+
"log_file": "/tmp/gpu_queue/job_034_as_sorl_abs30_K1_100K_gpu0.log"
|
| 430 |
},
|
| 431 |
{
|
| 432 |
"job_id": 35,
|
| 433 |
"name": "as_sorl_abs50_K1_100K",
|
| 434 |
"cmd": "python -m arithmetic.train --mode sorl --ops add_sub --dataset_size 100000 --abs_vocab 50 --K 1 --nu",
|
| 435 |
+
"gpu": 1,
|
| 436 |
+
"status": "failed",
|
| 437 |
+
"elapsed": 5,
|
| 438 |
+
"idle_time": 105,
|
| 439 |
+
"exit_code": -9,
|
| 440 |
+
"retries": 1,
|
| 441 |
+
"log_file": "/tmp/gpu_queue/job_035_as_sorl_abs50_K1_100K_gpu1.log"
|
| 442 |
},
|
| 443 |
{
|
| 444 |
"job_id": 36,
|
| 445 |
"name": "as_sorl_abs5_K4_25K",
|
| 446 |
"cmd": "python -m arithmetic.train --mode sorl --ops add_sub --dataset_size 25000 --abs_vocab 5 --K 4 --num_",
|
| 447 |
+
"gpu": 2,
|
| 448 |
+
"status": "failed",
|
| 449 |
+
"elapsed": 5,
|
| 450 |
"idle_time": 0,
|
| 451 |
+
"exit_code": -9,
|
| 452 |
+
"retries": 1,
|
| 453 |
+
"log_file": "/tmp/gpu_queue/job_036_as_sorl_abs5_K4_25K_gpu2.log"
|
| 454 |
},
|
| 455 |
{
|
| 456 |
"job_id": 37,
|
|
|
|
| 459 |
"gpu": 0,
|
| 460 |
"status": "done",
|
| 461 |
"elapsed": 4510,
|
| 462 |
+
"idle_time": 15413,
|
| 463 |
"exit_code": 0,
|
| 464 |
"retries": 0,
|
| 465 |
"log_file": "/tmp/gpu_queue/job_037_as_sorl_abs10_K4_25K_gpu0.log"
|
|
|
|
| 468 |
"job_id": 38,
|
| 469 |
"name": "as_sorl_abs30_K4_25K",
|
| 470 |
"cmd": "python -m arithmetic.train --mode sorl --ops add_sub --dataset_size 25000 --abs_vocab 30 --K 4 --num",
|
| 471 |
+
"gpu": 1,
|
| 472 |
+
"status": "failed",
|
| 473 |
+
"elapsed": 6,
|
| 474 |
+
"idle_time": 89,
|
| 475 |
+
"exit_code": -9,
|
| 476 |
+
"retries": 1,
|
| 477 |
+
"log_file": "/tmp/gpu_queue/job_038_as_sorl_abs30_K4_25K_gpu1.log"
|
| 478 |
},
|
| 479 |
{
|
| 480 |
"job_id": 39,
|
| 481 |
"name": "as_sorl_abs50_K4_25K",
|
| 482 |
"cmd": "python -m arithmetic.train --mode sorl --ops add_sub --dataset_size 25000 --abs_vocab 50 --K 4 --num",
|
| 483 |
+
"gpu": 2,
|
| 484 |
+
"status": "failed",
|
| 485 |
+
"elapsed": 4,
|
| 486 |
+
"idle_time": 41,
|
| 487 |
+
"exit_code": -9,
|
| 488 |
+
"retries": 1,
|
| 489 |
+
"log_file": "/tmp/gpu_queue/job_039_as_sorl_abs50_K4_25K_gpu2.log"
|
| 490 |
},
|
| 491 |
{
|
| 492 |
"job_id": 40,
|
|
|
|
| 507 |
"gpu": 2,
|
| 508 |
"status": "failed",
|
| 509 |
"elapsed": 6,
|
| 510 |
+
"idle_time": 125,
|
| 511 |
"exit_code": -9,
|
| 512 |
"retries": 1,
|
| 513 |
"log_file": "/tmp/gpu_queue/job_041_as_sorl_abs10_K4_50K_gpu2.log"
|
|
|
|
| 531 |
"gpu": 0,
|
| 532 |
"status": "done",
|
| 533 |
"elapsed": 5510,
|
| 534 |
+
"idle_time": 9899,
|
| 535 |
"exit_code": 0,
|
| 536 |
"retries": 0,
|
| 537 |
"log_file": "/tmp/gpu_queue/job_043_as_sorl_abs50_K4_50K_gpu0.log"
|
|
|
|
| 540 |
"job_id": 44,
|
| 541 |
"name": "as_sorl_abs5_K4_100K",
|
| 542 |
"cmd": "python -m arithmetic.train --mode sorl --ops add_sub --dataset_size 100000 --abs_vocab 5 --K 4 --num",
|
| 543 |
+
"gpu": 2,
|
| 544 |
+
"status": "failed",
|
| 545 |
+
"elapsed": 6,
|
| 546 |
+
"idle_time": 31,
|
| 547 |
+
"exit_code": -9,
|
| 548 |
+
"retries": 1,
|
| 549 |
+
"log_file": "/tmp/gpu_queue/job_044_as_sorl_abs5_K4_100K_gpu2.log"
|
| 550 |
},
|
| 551 |
{
|
| 552 |
"job_id": 45,
|
| 553 |
"name": "as_sorl_abs10_K4_100K",
|
| 554 |
"cmd": "python -m arithmetic.train --mode sorl --ops add_sub --dataset_size 100000 --abs_vocab 10 --K 4 --nu",
|
| 555 |
"gpu": 0,
|
| 556 |
+
"status": "failed",
|
| 557 |
+
"elapsed": 6,
|
| 558 |
+
"idle_time": 110,
|
| 559 |
+
"exit_code": -9,
|
| 560 |
+
"retries": 1,
|
| 561 |
"log_file": "/tmp/gpu_queue/job_045_as_sorl_abs10_K4_100K_gpu0.log"
|
| 562 |
},
|
| 563 |
{
|
| 564 |
"job_id": 46,
|
| 565 |
"name": "as_sorl_abs30_K4_100K",
|
| 566 |
"cmd": "python -m arithmetic.train --mode sorl --ops add_sub --dataset_size 100000 --abs_vocab 30 --K 4 --nu",
|
| 567 |
+
"gpu": 2,
|
| 568 |
+
"status": "failed",
|
| 569 |
+
"elapsed": 6,
|
| 570 |
+
"idle_time": 95,
|
| 571 |
+
"exit_code": -9,
|
| 572 |
+
"retries": 1,
|
| 573 |
+
"log_file": "/tmp/gpu_queue/job_046_as_sorl_abs30_K4_100K_gpu2.log"
|
| 574 |
},
|
| 575 |
{
|
| 576 |
"job_id": 47,
|
| 577 |
"name": "as_sorl_abs50_K4_100K",
|
| 578 |
"cmd": "python -m arithmetic.train --mode sorl --ops add_sub --dataset_size 100000 --abs_vocab 50 --K 4 --nu",
|
| 579 |
+
"gpu": 0,
|
| 580 |
+
"status": "failed",
|
| 581 |
+
"elapsed": 6,
|
| 582 |
+
"idle_time": 75,
|
| 583 |
+
"exit_code": -9,
|
| 584 |
+
"retries": 1,
|
| 585 |
+
"log_file": "/tmp/gpu_queue/job_047_as_sorl_abs50_K4_100K_gpu0.log"
|
| 586 |
},
|
| 587 |
{
|
| 588 |
"job_id": 48,
|
|
|
|
| 615 |
"gpu": 2,
|
| 616 |
"status": "failed",
|
| 617 |
"elapsed": 6,
|
| 618 |
+
"idle_time": 131,
|
| 619 |
"exit_code": -9,
|
| 620 |
"retries": 1,
|
| 621 |
"log_file": "/tmp/gpu_queue/job_050_as_sorl_abs10_K1_zipf10.0_500K_gpu2.log"
|
|
|
|
| 636 |
"job_id": 52,
|
| 637 |
"name": "as_sorl_abs10_K4_zipf5.0_500K",
|
| 638 |
"cmd": "python -m arithmetic.train --mode sorl --ops add_sub --dataset_size 500000 --abs_vocab 10 --K 4 --al",
|
| 639 |
+
"gpu": 0,
|
| 640 |
+
"status": "failed",
|
| 641 |
+
"elapsed": 5,
|
| 642 |
+
"idle_time": 90,
|
| 643 |
+
"exit_code": -9,
|
| 644 |
+
"retries": 1,
|
| 645 |
+
"log_file": "/tmp/gpu_queue/job_052_as_sorl_abs10_K4_zipf5.0_500K_gpu0.log"
|
| 646 |
},
|
| 647 |
{
|
| 648 |
"job_id": 53,
|
|
|
|
| 651 |
"gpu": 1,
|
| 652 |
"status": "failed",
|
| 653 |
"elapsed": 5,
|
| 654 |
+
"idle_time": 13577,
|
| 655 |
"exit_code": -9,
|
| 656 |
"retries": 1,
|
| 657 |
"log_file": "/tmp/gpu_queue/job_053_as_sorl_abs10_K4_zipf10.0_500K_gpu1.log"
|
|
|
|
| 660 |
"job_id": 54,
|
| 661 |
"name": "as_sorl_abs100_K1_zipf2.0_500K",
|
| 662 |
"cmd": "python -m arithmetic.train --mode sorl --ops add_sub --dataset_size 500000 --abs_vocab 100 --K 1 --a",
|
| 663 |
+
"gpu": 0,
|
| 664 |
+
"status": "failed",
|
| 665 |
+
"elapsed": 6,
|
| 666 |
+
"idle_time": 75,
|
| 667 |
+
"exit_code": -9,
|
| 668 |
+
"retries": 1,
|
| 669 |
+
"log_file": "/tmp/gpu_queue/job_054_as_sorl_abs100_K1_zipf2.0_500K_gpu0.log"
|
| 670 |
},
|
| 671 |
{
|
| 672 |
"job_id": 55,
|
|
|
|
| 675 |
"gpu": 0,
|
| 676 |
"status": "failed",
|
| 677 |
"elapsed": 5,
|
| 678 |
+
"idle_time": 6277,
|
| 679 |
"exit_code": -9,
|
| 680 |
"retries": 1,
|
| 681 |
"log_file": "/tmp/gpu_queue/job_055_as_sorl_abs100_K1_zipf5.0_500K_gpu0.log"
|
|
|
|
| 696 |
"job_id": 57,
|
| 697 |
"name": "as_sorl_abs100_K4_zipf2.0_500K",
|
| 698 |
"cmd": "python -m arithmetic.train --mode sorl --ops add_sub --dataset_size 500000 --abs_vocab 100 --K 4 --a",
|
| 699 |
+
"gpu": 2,
|
| 700 |
+
"status": "failed",
|
| 701 |
+
"elapsed": 5,
|
| 702 |
+
"idle_time": 80,
|
| 703 |
+
"exit_code": -9,
|
| 704 |
+
"retries": 1,
|
| 705 |
+
"log_file": "/tmp/gpu_queue/job_057_as_sorl_abs100_K4_zipf2.0_500K_gpu2.log"
|
| 706 |
},
|
| 707 |
{
|
| 708 |
"job_id": 58,
|
| 709 |
"name": "as_sorl_abs100_K4_zipf5.0_500K",
|
| 710 |
"cmd": "python -m arithmetic.train --mode sorl --ops add_sub --dataset_size 500000 --abs_vocab 100 --K 4 --a",
|
| 711 |
"gpu": 1,
|
| 712 |
+
"status": "failed",
|
| 713 |
+
"elapsed": 6,
|
| 714 |
+
"idle_time": 110,
|
| 715 |
+
"exit_code": -9,
|
| 716 |
+
"retries": 1,
|
| 717 |
"log_file": "/tmp/gpu_queue/job_058_as_sorl_abs100_K4_zipf5.0_500K_gpu1.log"
|
| 718 |
},
|
| 719 |
{
|
| 720 |
"job_id": 59,
|
| 721 |
"name": "as_sorl_abs100_K4_zipf10.0_500K",
|
| 722 |
"cmd": "python -m arithmetic.train --mode sorl --ops add_sub --dataset_size 500000 --abs_vocab 100 --K 4 --a",
|
| 723 |
+
"gpu": 1,
|
| 724 |
+
"status": "failed",
|
| 725 |
+
"elapsed": 6,
|
| 726 |
+
"idle_time": 74,
|
| 727 |
+
"exit_code": -9,
|
| 728 |
+
"retries": 1,
|
| 729 |
+
"log_file": "/tmp/gpu_queue/job_059_as_sorl_abs100_K4_zipf10.0_500_gpu1.log"
|
| 730 |
},
|
| 731 |
{
|
| 732 |
"job_id": 60,
|
| 733 |
"name": "as_baseline_25K_1L3H510d",
|
| 734 |
"cmd": "python -m arithmetic.train --mode baseline --ops add_sub --dataset_size 25000 --num_epochs 20 --n_la",
|
| 735 |
+
"gpu": 2,
|
| 736 |
+
"status": "failed",
|
| 737 |
+
"elapsed": 5,
|
| 738 |
+
"idle_time": 25,
|
| 739 |
+
"exit_code": -9,
|
| 740 |
+
"retries": 1,
|
| 741 |
+
"log_file": "/tmp/gpu_queue/job_060_as_baseline_25K_1L3H510d_gpu2.log"
|
| 742 |
},
|
| 743 |
{
|
| 744 |
"job_id": 61,
|
|
|
|
| 759 |
"gpu": 0,
|
| 760 |
"status": "failed",
|
| 761 |
"elapsed": 5,
|
| 762 |
+
"idle_time": 120,
|
| 763 |
"exit_code": -9,
|
| 764 |
"retries": 1,
|
| 765 |
"log_file": "/tmp/gpu_queue/job_062_as_baseline_50K_1L3H510d_gpu0.log"
|
|
|
|
| 771 |
"gpu": 0,
|
| 772 |
"status": "done",
|
| 773 |
"elapsed": 5352,
|
| 774 |
+
"idle_time": 6291,
|
| 775 |
"exit_code": 0,
|
| 776 |
"retries": 0,
|
| 777 |
"log_file": "/tmp/gpu_queue/job_063_as_sorl_abs10_K1_50K_1L3H510d_gpu0.log"
|
|
|
|
| 783 |
"gpu": 1,
|
| 784 |
"status": "failed",
|
| 785 |
"elapsed": 4,
|
| 786 |
+
"idle_time": 141,
|
| 787 |
"exit_code": -15,
|
| 788 |
"retries": 1,
|
| 789 |
"log_file": "/tmp/gpu_queue/job_064_as_baseline_100K_1L3H510d_gpu1.log"
|
|
|
|
| 795 |
"gpu": 0,
|
| 796 |
"status": "failed",
|
| 797 |
"elapsed": 6,
|
| 798 |
+
"idle_time": 132,
|
| 799 |
"exit_code": -9,
|
| 800 |
"retries": 1,
|
| 801 |
"log_file": "/tmp/gpu_queue/job_065_as_sorl_abs10_K1_100K_1L3H510d_gpu0.log"
|
|
|
|
| 804 |
"job_id": 66,
|
| 805 |
"name": "as_baseline_250K_1L3H510d",
|
| 806 |
"cmd": "python -m arithmetic.train --mode baseline --ops add_sub --dataset_size 250000 --num_epochs 20 --n_l",
|
| 807 |
+
"gpu": 0,
|
| 808 |
+
"status": "failed",
|
| 809 |
+
"elapsed": 5,
|
| 810 |
+
"idle_time": 105,
|
| 811 |
+
"exit_code": -9,
|
| 812 |
+
"retries": 1,
|
| 813 |
+
"log_file": "/tmp/gpu_queue/job_066_as_baseline_250K_1L3H510d_gpu0.log"
|
| 814 |
},
|
| 815 |
{
|
| 816 |
"job_id": 67,
|
| 817 |
"name": "as_sorl_abs10_K1_250K_1L3H510d",
|
| 818 |
"cmd": "python -m arithmetic.train --mode sorl --ops add_sub --dataset_size 250000 --abs_vocab 10 --K 1 --nu",
|
| 819 |
+
"gpu": 1,
|
| 820 |
+
"status": "failed",
|
| 821 |
+
"elapsed": 6,
|
| 822 |
+
"idle_time": 30,
|
| 823 |
+
"exit_code": -9,
|
| 824 |
+
"retries": 1,
|
| 825 |
+
"log_file": "/tmp/gpu_queue/job_067_as_sorl_abs10_K1_250K_1L3H510d_gpu1.log"
|
| 826 |
},
|
| 827 |
{
|
| 828 |
"job_id": 68,
|
| 829 |
"name": "as_baseline_500K_1L3H510d",
|
| 830 |
"cmd": "python -m arithmetic.train --mode baseline --ops add_sub --dataset_size 500000 --num_epochs 20 --n_l",
|
| 831 |
+
"gpu": 1,
|
| 832 |
+
"status": "failed",
|
| 833 |
+
"elapsed": 6,
|
| 834 |
+
"idle_time": 10,
|
| 835 |
+
"exit_code": -9,
|
| 836 |
+
"retries": 1,
|
| 837 |
+
"log_file": "/tmp/gpu_queue/job_068_as_baseline_500K_1L3H510d_gpu1.log"
|
| 838 |
},
|
| 839 |
{
|
| 840 |
"job_id": 69,
|
|
|
|
| 843 |
"gpu": 2,
|
| 844 |
"status": "failed",
|
| 845 |
"elapsed": 2,
|
| 846 |
+
"idle_time": 139,
|
| 847 |
"exit_code": -15,
|
| 848 |
"retries": 1,
|
| 849 |
"log_file": "/tmp/gpu_queue/job_069_as_sorl_abs10_K1_500K_1L3H510d_gpu2.log"
|
|
|
|
| 855 |
"gpu": 1,
|
| 856 |
"status": "failed",
|
| 857 |
"elapsed": 6,
|
| 858 |
+
"idle_time": 131,
|
| 859 |
"exit_code": -9,
|
| 860 |
"retries": 1,
|
| 861 |
"log_file": "/tmp/gpu_queue/job_070_as_baseline_25K_1L2H256d_gpu1.log"
|
|
|
|
| 864 |
"job_id": 71,
|
| 865 |
"name": "as_sorl_abs10_K1_25K_1L2H256d",
|
| 866 |
"cmd": "python -m arithmetic.train --mode sorl --ops add_sub --dataset_size 25000 --abs_vocab 10 --K 1 --num",
|
| 867 |
+
"gpu": 0,
|
| 868 |
+
"status": "failed",
|
| 869 |
+
"elapsed": 6,
|
| 870 |
+
"idle_time": 95,
|
| 871 |
+
"exit_code": -9,
|
| 872 |
+
"retries": 1,
|
| 873 |
+
"log_file": "/tmp/gpu_queue/job_071_as_sorl_abs10_K1_25K_1L2H256d_gpu0.log"
|
| 874 |
},
|
| 875 |
{
|
| 876 |
"job_id": 72,
|
|
|
|
| 903 |
"gpu": 2,
|
| 904 |
"status": "done",
|
| 905 |
"elapsed": 2797,
|
| 906 |
+
"idle_time": 14742,
|
| 907 |
"exit_code": 0,
|
| 908 |
"retries": 0,
|
| 909 |
"log_file": "/tmp/gpu_queue/job_074_as_baseline_100K_1L2H256d_gpu2.log"
|
|
|
|
| 915 |
"gpu": 1,
|
| 916 |
"status": "failed",
|
| 917 |
"elapsed": 6,
|
| 918 |
+
"idle_time": 125,
|
| 919 |
"exit_code": -9,
|
| 920 |
"retries": 1,
|
| 921 |
"log_file": "/tmp/gpu_queue/job_075_as_sorl_abs10_K1_100K_1L2H256d_gpu1.log"
|
|
|
|
| 927 |
"gpu": 0,
|
| 928 |
"status": "done",
|
| 929 |
"elapsed": 4832,
|
| 930 |
+
"idle_time": 1587,
|
| 931 |
"exit_code": 0,
|
| 932 |
"retries": 0,
|
| 933 |
"log_file": "/tmp/gpu_queue/job_076_as_baseline_250K_1L2H256d_gpu0.log"
|
|
|
|
| 951 |
"gpu": 2,
|
| 952 |
"status": "done",
|
| 953 |
"elapsed": 7064,
|
| 954 |
+
"idle_time": 12115,
|
| 955 |
"exit_code": 0,
|
| 956 |
"retries": 0,
|
| 957 |
"log_file": "/tmp/gpu_queue/job_078_as_baseline_500K_1L2H256d_gpu2.log"
|
|
|
|
| 960 |
"job_id": 79,
|
| 961 |
"name": "as_sorl_abs10_K1_500K_1L2H256d",
|
| 962 |
"cmd": "python -m arithmetic.train --mode sorl --ops add_sub --dataset_size 500000 --abs_vocab 10 --K 1 --nu",
|
| 963 |
+
"gpu": 2,
|
| 964 |
+
"status": "failed",
|
| 965 |
+
"elapsed": 4,
|
| 966 |
+
"idle_time": 41,
|
| 967 |
+
"exit_code": -9,
|
| 968 |
+
"retries": 1,
|
| 969 |
+
"log_file": "/tmp/gpu_queue/job_079_as_sorl_abs10_K1_500K_1L2H256d_gpu2.log"
|
| 970 |
},
|
| 971 |
{
|
| 972 |
"job_id": 80,
|
|
|
|
| 975 |
"gpu": 1,
|
| 976 |
"status": "done",
|
| 977 |
"elapsed": 1971,
|
| 978 |
+
"idle_time": 13593,
|
| 979 |
"exit_code": 0,
|
| 980 |
"retries": 0,
|
| 981 |
"log_file": "/tmp/gpu_queue/job_080_as_baseline_25K_2L1H128d_gpu1.log"
|
|
|
|
| 984 |
"job_id": 81,
|
| 985 |
"name": "as_sorl_abs10_K1_25K_2L1H128d",
|
| 986 |
"cmd": "python -m arithmetic.train --mode sorl --ops add_sub --dataset_size 25000 --abs_vocab 10 --K 1 --num",
|
| 987 |
+
"gpu": 2,
|
| 988 |
+
"status": "failed",
|
| 989 |
+
"elapsed": 6,
|
| 990 |
+
"idle_time": 80,
|
| 991 |
+
"exit_code": -9,
|
| 992 |
+
"retries": 1,
|
| 993 |
+
"log_file": "/tmp/gpu_queue/job_081_as_sorl_abs10_K1_25K_2L1H128d_gpu2.log"
|
| 994 |
},
|
| 995 |
{
|
| 996 |
"job_id": 82,
|
| 997 |
"name": "as_baseline_50K_2L1H128d",
|
| 998 |
"cmd": "python -m arithmetic.train --mode baseline --ops add_sub --dataset_size 50000 --num_epochs 20 --n_la",
|
| 999 |
+
"gpu": 0,
|
| 1000 |
+
"status": "failed",
|
| 1001 |
+
"elapsed": 5,
|
| 1002 |
+
"idle_time": 60,
|
| 1003 |
+
"exit_code": -9,
|
| 1004 |
+
"retries": 1,
|
| 1005 |
+
"log_file": "/tmp/gpu_queue/job_082_as_baseline_50K_2L1H128d_gpu0.log"
|
| 1006 |
},
|
| 1007 |
{
|
| 1008 |
"job_id": 83,
|
|
|
|
| 1020 |
"job_id": 84,
|
| 1021 |
"name": "as_baseline_100K_2L1H128d",
|
| 1022 |
"cmd": "python -m arithmetic.train --mode baseline --ops add_sub --dataset_size 100000 --num_epochs 20 --n_l",
|
| 1023 |
+
"gpu": 0,
|
| 1024 |
+
"status": "failed",
|
| 1025 |
+
"elapsed": 6,
|
| 1026 |
+
"idle_time": 31,
|
| 1027 |
+
"exit_code": -9,
|
| 1028 |
+
"retries": 1,
|
| 1029 |
+
"log_file": "/tmp/gpu_queue/job_084_as_baseline_100K_2L1H128d_gpu0.log"
|
| 1030 |
},
|
| 1031 |
{
|
| 1032 |
"job_id": 85,
|
| 1033 |
"name": "as_sorl_abs10_K1_100K_2L1H128d",
|
| 1034 |
"cmd": "python -m arithmetic.train --mode sorl --ops add_sub --dataset_size 100000 --abs_vocab 10 --K 1 --nu",
|
| 1035 |
+
"gpu": 0,
|
| 1036 |
+
"status": "failed",
|
| 1037 |
+
"elapsed": 6,
|
| 1038 |
+
"idle_time": 10,
|
| 1039 |
+
"exit_code": -9,
|
| 1040 |
+
"retries": 1,
|
| 1041 |
+
"log_file": "/tmp/gpu_queue/job_085_as_sorl_abs10_K1_100K_2L1H128d_gpu0.log"
|
| 1042 |
},
|
| 1043 |
{
|
| 1044 |
"job_id": 86,
|
| 1045 |
"name": "as_baseline_250K_2L1H128d",
|
| 1046 |
"cmd": "python -m arithmetic.train --mode baseline --ops add_sub --dataset_size 250000 --num_epochs 20 --n_l",
|
| 1047 |
+
"gpu": 1,
|
| 1048 |
+
"status": "failed",
|
| 1049 |
+
"elapsed": 6,
|
| 1050 |
+
"idle_time": 45,
|
| 1051 |
+
"exit_code": -9,
|
| 1052 |
+
"retries": 1,
|
| 1053 |
+
"log_file": "/tmp/gpu_queue/job_086_as_baseline_250K_2L1H128d_gpu1.log"
|
| 1054 |
},
|
| 1055 |
{
|
| 1056 |
"job_id": 87,
|
|
|
|
| 1059 |
"gpu": 1,
|
| 1060 |
"status": "failed",
|
| 1061 |
"elapsed": 5,
|
| 1062 |
+
"idle_time": 147,
|
| 1063 |
"exit_code": -9,
|
| 1064 |
"retries": 1,
|
| 1065 |
"log_file": "/tmp/gpu_queue/job_087_as_sorl_abs10_K1_250K_2L1H128d_gpu1.log"
|
|
|
|
| 1083 |
"gpu": 1,
|
| 1084 |
"status": "failed",
|
| 1085 |
"elapsed": 5,
|
| 1086 |
+
"idle_time": 146,
|
| 1087 |
"exit_code": -9,
|
| 1088 |
"retries": 1,
|
| 1089 |
"log_file": "/tmp/gpu_queue/job_089_as_sorl_abs10_K1_500K_2L1H128d_gpu1.log"
|
|
|
|
| 1104 |
"job_id": 91,
|
| 1105 |
"name": "as_sorl_abs10_K4_10K",
|
| 1106 |
"cmd": "python -m arithmetic.train --mode sorl --ops add_sub --dataset_size 10000 --abs_vocab 10 --K 4 --num",
|
| 1107 |
+
"gpu": 0,
|
| 1108 |
+
"status": "failed",
|
| 1109 |
+
"elapsed": 5,
|
| 1110 |
+
"idle_time": 45,
|
| 1111 |
+
"exit_code": -9,
|
| 1112 |
+
"retries": 1,
|
| 1113 |
+
"log_file": "/tmp/gpu_queue/job_091_as_sorl_abs10_K4_10K_gpu0.log"
|
| 1114 |
},
|
| 1115 |
{
|
| 1116 |
"job_id": 92,
|
|
|
|
| 1119 |
"gpu": 0,
|
| 1120 |
"status": "done",
|
| 1121 |
"elapsed": 3477,
|
| 1122 |
+
"idle_time": 6422,
|
| 1123 |
"exit_code": 0,
|
| 1124 |
"retries": 0,
|
| 1125 |
"log_file": "/tmp/gpu_queue/job_092_as_sorl_abs30_K4_10K_gpu0.log"
|
|
|
|
| 1128 |
"job_id": 93,
|
| 1129 |
"name": "as_sorl_abs50_K4_10K",
|
| 1130 |
"cmd": "python -m arithmetic.train --mode sorl --ops add_sub --dataset_size 10000 --abs_vocab 50 --K 4 --num",
|
| 1131 |
+
"gpu": 1,
|
| 1132 |
+
"status": "failed",
|
| 1133 |
+
"elapsed": 6,
|
| 1134 |
+
"idle_time": 65,
|
| 1135 |
+
"exit_code": -9,
|
| 1136 |
+
"retries": 1,
|
| 1137 |
+
"log_file": "/tmp/gpu_queue/job_093_as_sorl_abs50_K4_10K_gpu1.log"
|
| 1138 |
},
|
| 1139 |
{
|
| 1140 |
"job_id": 94,
|
| 1141 |
"name": "as_sorl_abs5_K4_250K",
|
| 1142 |
"cmd": "python -m arithmetic.train --mode sorl --ops add_sub --dataset_size 250000 --abs_vocab 5 --K 4 --num",
|
| 1143 |
+
"gpu": 0,
|
| 1144 |
+
"status": "failed",
|
| 1145 |
+
"elapsed": 6,
|
| 1146 |
+
"idle_time": 5,
|
| 1147 |
+
"exit_code": -9,
|
| 1148 |
+
"retries": 1,
|
| 1149 |
+
"log_file": "/tmp/gpu_queue/job_094_as_sorl_abs5_K4_250K_gpu0.log"
|
| 1150 |
},
|
| 1151 |
{
|
| 1152 |
"job_id": 95,
|
|
|
|
| 1155 |
"gpu": 2,
|
| 1156 |
"status": "failed",
|
| 1157 |
"elapsed": 5,
|
| 1158 |
+
"idle_time": 143,
|
| 1159 |
"exit_code": -9,
|
| 1160 |
"retries": 1,
|
| 1161 |
"log_file": "/tmp/gpu_queue/job_095_as_sorl_abs10_K4_250K_gpu2.log"
|
|
|
|
| 1164 |
"job_id": 96,
|
| 1165 |
"name": "as_sorl_abs30_K4_250K",
|
| 1166 |
"cmd": "python -m arithmetic.train --mode sorl --ops add_sub --dataset_size 250000 --abs_vocab 30 --K 4 --nu",
|
| 1167 |
+
"gpu": 1,
|
| 1168 |
+
"status": "failed",
|
| 1169 |
+
"elapsed": 6,
|
| 1170 |
+
"idle_time": 10,
|
| 1171 |
+
"exit_code": -9,
|
| 1172 |
+
"retries": 1,
|
| 1173 |
+
"log_file": "/tmp/gpu_queue/job_096_as_sorl_abs30_K4_250K_gpu1.log"
|
| 1174 |
},
|
| 1175 |
{
|
| 1176 |
"job_id": 97,
|
| 1177 |
"name": "as_sorl_abs50_K4_250K",
|
| 1178 |
"cmd": "python -m arithmetic.train --mode sorl --ops add_sub --dataset_size 250000 --abs_vocab 50 --K 4 --nu",
|
| 1179 |
+
"gpu": 1,
|
| 1180 |
+
"status": "failed",
|
| 1181 |
+
"elapsed": 6,
|
| 1182 |
+
"idle_time": 95,
|
| 1183 |
+
"exit_code": -9,
|
| 1184 |
+
"retries": 1,
|
| 1185 |
+
"log_file": "/tmp/gpu_queue/job_097_as_sorl_abs50_K4_250K_gpu1.log"
|
| 1186 |
},
|
| 1187 |
{
|
| 1188 |
"job_id": 98,
|
|
|
|
| 1191 |
"gpu": 1,
|
| 1192 |
"status": "failed",
|
| 1193 |
"elapsed": 3,
|
| 1194 |
+
"idle_time": 140,
|
| 1195 |
"exit_code": -15,
|
| 1196 |
"retries": 1,
|
| 1197 |
"log_file": "/tmp/gpu_queue/job_098_as_sorl_abs2_K1_100K_gpu1.log"
|
|
|
|
| 1203 |
"gpu": 1,
|
| 1204 |
"status": "failed",
|
| 1205 |
"elapsed": 5,
|
| 1206 |
+
"idle_time": 120,
|
| 1207 |
"exit_code": -9,
|
| 1208 |
"retries": 1,
|
| 1209 |
"log_file": "/tmp/gpu_queue/job_099_as_sorl_abs2_K4_100K_gpu1.log"
|
|
|
|
| 1212 |
"job_id": 100,
|
| 1213 |
"name": "as_sorl_abs16_K1_100K",
|
| 1214 |
"cmd": "python -m arithmetic.train --mode sorl --ops add_sub --dataset_size 100000 --abs_vocab 16 --K 1 --nu",
|
| 1215 |
+
"gpu": 0,
|
| 1216 |
+
"status": "failed",
|
| 1217 |
+
"elapsed": 6,
|
| 1218 |
+
"idle_time": 19,
|
| 1219 |
+
"exit_code": -9,
|
| 1220 |
+
"retries": 1,
|
| 1221 |
+
"log_file": "/tmp/gpu_queue/job_100_as_sorl_abs16_K1_100K_gpu0.log"
|
| 1222 |
},
|
| 1223 |
{
|
| 1224 |
"job_id": 101,
|