Spaces:
Sleeping
Sleeping
Add training evidence + blog + updated README
Browse files- results.json +93 -993
- training_results.png +2 -2
results.json
CHANGED
|
@@ -1,1167 +1,267 @@
|
|
| 1 |
{
|
| 2 |
"baseline": {
|
| 3 |
"easy": [
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4 |
0.2,
|
| 5 |
0.65,
|
| 6 |
0.65,
|
| 7 |
0.65,
|
| 8 |
0.65,
|
| 9 |
-
0.
|
| 10 |
-
0.2,
|
| 11 |
-
0.0,
|
| 12 |
-
0.04999999999999999,
|
| 13 |
-
0.2
|
| 14 |
],
|
| 15 |
"medium": [
|
| 16 |
-
0.
|
| 17 |
-
0.
|
| 18 |
-
0.15714285714285714,
|
| 19 |
0.15714285714285714,
|
| 20 |
0.15714285714285714,
|
|
|
|
| 21 |
0.5471428571428572,
|
| 22 |
-
0.
|
| 23 |
0.15714285714285714,
|
| 24 |
0.11428571428571427,
|
| 25 |
-
0.
|
| 26 |
],
|
| 27 |
"hard": [
|
| 28 |
-
0.
|
| 29 |
-
0.14785714285714285,
|
| 30 |
0.10071428571428576,
|
| 31 |
-
0.14785714285714285,
|
| 32 |
0.5498571428571429,
|
| 33 |
0.0,
|
| 34 |
-
0.
|
|
|
|
| 35 |
0.14785714285714285,
|
| 36 |
0.5498571428571429,
|
| 37 |
-
0.
|
|
|
|
| 38 |
]
|
| 39 |
},
|
| 40 |
"trained": {
|
| 41 |
"easy": [
|
| 42 |
-
|
| 43 |
-
|
| 44 |
-
|
| 45 |
-
|
| 46 |
-
|
| 47 |
-
|
| 48 |
-
|
| 49 |
-
|
| 50 |
-
|
| 51 |
-
0.
|
| 52 |
],
|
| 53 |
"medium": [
|
| 54 |
-
0.
|
| 55 |
-
0.
|
| 56 |
-
0.
|
| 57 |
-
0.
|
| 58 |
-
0.
|
| 59 |
-
0.
|
| 60 |
-
0.
|
| 61 |
-
0.
|
| 62 |
-
0.
|
| 63 |
-
0.
|
| 64 |
],
|
| 65 |
"hard": [
|
| 66 |
-
0.
|
| 67 |
-
0.
|
| 68 |
-
0.
|
| 69 |
-
0.
|
| 70 |
-
0.
|
| 71 |
-
0.
|
| 72 |
-
0.
|
| 73 |
-
0.
|
| 74 |
-
0.
|
| 75 |
-
0.
|
| 76 |
]
|
| 77 |
},
|
| 78 |
"training_log": [
|
| 79 |
{
|
| 80 |
"step": 1,
|
| 81 |
-
"reward": 0.
|
| 82 |
},
|
| 83 |
{
|
| 84 |
"step": 2,
|
| 85 |
-
"reward": 0.
|
| 86 |
},
|
| 87 |
{
|
| 88 |
"step": 3,
|
| 89 |
-
"reward": 0.
|
| 90 |
},
|
| 91 |
{
|
| 92 |
"step": 4,
|
| 93 |
-
"reward": 0.
|
| 94 |
},
|
| 95 |
{
|
| 96 |
"step": 5,
|
| 97 |
-
"reward": 0.
|
| 98 |
},
|
| 99 |
{
|
| 100 |
"step": 6,
|
| 101 |
-
"reward": 0.
|
| 102 |
},
|
| 103 |
{
|
| 104 |
"step": 7,
|
| 105 |
-
"reward": 0.
|
| 106 |
},
|
| 107 |
{
|
| 108 |
"step": 8,
|
| 109 |
-
"reward": 0.
|
| 110 |
},
|
| 111 |
{
|
| 112 |
"step": 9,
|
| 113 |
-
"reward": 0.
|
| 114 |
},
|
| 115 |
{
|
| 116 |
"step": 10,
|
| 117 |
-
"reward": 0.
|
| 118 |
},
|
| 119 |
{
|
| 120 |
"step": 11,
|
| 121 |
-
"reward": 0.
|
| 122 |
},
|
| 123 |
{
|
| 124 |
"step": 12,
|
| 125 |
-
"reward": 0.
|
| 126 |
},
|
| 127 |
{
|
| 128 |
"step": 13,
|
| 129 |
-
"reward": 0.
|
| 130 |
},
|
| 131 |
{
|
| 132 |
"step": 14,
|
| 133 |
-
"reward": 0.
|
| 134 |
},
|
| 135 |
{
|
| 136 |
"step": 15,
|
| 137 |
-
"reward": 0.
|
| 138 |
},
|
| 139 |
{
|
| 140 |
"step": 16,
|
| 141 |
-
"reward": 0.
|
| 142 |
},
|
| 143 |
{
|
| 144 |
"step": 17,
|
| 145 |
-
"reward": 0.
|
| 146 |
},
|
| 147 |
{
|
| 148 |
"step": 18,
|
| 149 |
-
"reward": 0.
|
| 150 |
},
|
| 151 |
{
|
| 152 |
"step": 19,
|
| 153 |
-
"reward": 0.
|
| 154 |
},
|
| 155 |
{
|
| 156 |
"step": 20,
|
| 157 |
-
"reward": 0.
|
| 158 |
},
|
| 159 |
{
|
| 160 |
"step": 21,
|
| 161 |
-
"reward": 0.
|
| 162 |
},
|
| 163 |
{
|
| 164 |
"step": 22,
|
| 165 |
-
"reward": 0.
|
| 166 |
},
|
| 167 |
{
|
| 168 |
"step": 23,
|
| 169 |
-
"reward": 0.
|
| 170 |
},
|
| 171 |
{
|
| 172 |
"step": 24,
|
| 173 |
-
"reward": 0.
|
| 174 |
},
|
| 175 |
{
|
| 176 |
"step": 25,
|
| 177 |
-
"reward": 0.
|
| 178 |
},
|
| 179 |
{
|
| 180 |
"step": 26,
|
| 181 |
-
"reward": 0.
|
| 182 |
},
|
| 183 |
{
|
| 184 |
"step": 27,
|
| 185 |
-
"reward": 0.
|
| 186 |
},
|
| 187 |
{
|
| 188 |
"step": 28,
|
| 189 |
-
"reward": 0.
|
| 190 |
},
|
| 191 |
{
|
| 192 |
"step": 29,
|
| 193 |
-
"reward": 0.
|
| 194 |
},
|
| 195 |
{
|
| 196 |
"step": 30,
|
| 197 |
-
"reward": 0.
|
| 198 |
},
|
| 199 |
{
|
| 200 |
"step": 31,
|
| 201 |
-
"reward": 0.
|
| 202 |
},
|
| 203 |
{
|
| 204 |
"step": 32,
|
| 205 |
-
"reward": 0.
|
| 206 |
},
|
| 207 |
{
|
| 208 |
"step": 33,
|
| 209 |
-
"reward": 0.
|
| 210 |
},
|
| 211 |
{
|
| 212 |
"step": 34,
|
| 213 |
-
"reward": 0.
|
| 214 |
},
|
| 215 |
{
|
| 216 |
"step": 35,
|
| 217 |
-
"reward": 0.
|
| 218 |
},
|
| 219 |
{
|
| 220 |
"step": 36,
|
| 221 |
-
"reward": 0.
|
| 222 |
},
|
| 223 |
{
|
| 224 |
"step": 37,
|
| 225 |
-
"reward": 0.
|
| 226 |
},
|
| 227 |
{
|
| 228 |
"step": 38,
|
| 229 |
-
"reward": 0.
|
| 230 |
},
|
| 231 |
{
|
| 232 |
"step": 39,
|
| 233 |
-
"reward": 0.
|
| 234 |
},
|
| 235 |
{
|
| 236 |
"step": 40,
|
| 237 |
-
"reward": 0.
|
| 238 |
},
|
| 239 |
{
|
| 240 |
"step": 41,
|
| 241 |
-
"reward": 0.
|
| 242 |
},
|
| 243 |
{
|
| 244 |
"step": 42,
|
| 245 |
-
"reward": 0.
|
| 246 |
},
|
| 247 |
{
|
| 248 |
"step": 43,
|
| 249 |
-
"reward": 0.
|
| 250 |
},
|
| 251 |
{
|
| 252 |
"step": 44,
|
| 253 |
-
"reward": 0.
|
| 254 |
},
|
| 255 |
{
|
| 256 |
"step": 45,
|
| 257 |
-
"reward": 0.
|
| 258 |
-
},
|
| 259 |
-
{
|
| 260 |
-
"step": 46,
|
| 261 |
-
"reward": 0.5474107265472412
|
| 262 |
-
},
|
| 263 |
-
{
|
| 264 |
-
"step": 47,
|
| 265 |
-
"reward": 0.3933393061161041
|
| 266 |
-
},
|
| 267 |
-
{
|
| 268 |
-
"step": 48,
|
| 269 |
-
"reward": 0.565625011920929
|
| 270 |
-
},
|
| 271 |
-
{
|
| 272 |
-
"step": 49,
|
| 273 |
-
"reward": 0.4785892963409424
|
| 274 |
-
},
|
| 275 |
-
{
|
| 276 |
-
"step": 50,
|
| 277 |
-
"reward": 0.46958038210868835
|
| 278 |
-
},
|
| 279 |
-
{
|
| 280 |
-
"step": 51,
|
| 281 |
-
"reward": 0.36991071701049805
|
| 282 |
-
},
|
| 283 |
-
{
|
| 284 |
-
"step": 52,
|
| 285 |
-
"reward": 0.2941964268684387
|
| 286 |
-
},
|
| 287 |
-
{
|
| 288 |
-
"step": 53,
|
| 289 |
-
"reward": 0.4853571653366089
|
| 290 |
-
},
|
| 291 |
-
{
|
| 292 |
-
"step": 54,
|
| 293 |
-
"reward": 0.23973214626312256
|
| 294 |
-
},
|
| 295 |
-
{
|
| 296 |
-
"step": 55,
|
| 297 |
-
"reward": 0.7227678298950195
|
| 298 |
-
},
|
| 299 |
-
{
|
| 300 |
-
"step": 56,
|
| 301 |
-
"reward": 0.4734821319580078
|
| 302 |
-
},
|
| 303 |
-
{
|
| 304 |
-
"step": 57,
|
| 305 |
-
"reward": 0.5602678656578064
|
| 306 |
-
},
|
| 307 |
-
{
|
| 308 |
-
"step": 58,
|
| 309 |
-
"reward": 0.5581071376800537
|
| 310 |
-
},
|
| 311 |
-
{
|
| 312 |
-
"step": 59,
|
| 313 |
-
"reward": 0.6915178298950195
|
| 314 |
-
},
|
| 315 |
-
{
|
| 316 |
-
"step": 60,
|
| 317 |
-
"reward": 0.328830361366272
|
| 318 |
-
},
|
| 319 |
-
{
|
| 320 |
-
"step": 61,
|
| 321 |
-
"reward": 0.3727678656578064
|
| 322 |
-
},
|
| 323 |
-
{
|
| 324 |
-
"step": 62,
|
| 325 |
-
"reward": 0.4290178418159485
|
| 326 |
-
},
|
| 327 |
-
{
|
| 328 |
-
"step": 63,
|
| 329 |
-
"reward": 0.5301785469055176
|
| 330 |
-
},
|
| 331 |
-
{
|
| 332 |
-
"step": 64,
|
| 333 |
-
"reward": 0.29794642329216003
|
| 334 |
-
},
|
| 335 |
-
{
|
| 336 |
-
"step": 65,
|
| 337 |
-
"reward": 0.5418839454650879
|
| 338 |
-
},
|
| 339 |
-
{
|
| 340 |
-
"step": 66,
|
| 341 |
-
"reward": 0.5446428656578064
|
| 342 |
-
},
|
| 343 |
-
{
|
| 344 |
-
"step": 67,
|
| 345 |
-
"reward": 0.30937498807907104
|
| 346 |
-
},
|
| 347 |
-
{
|
| 348 |
-
"step": 68,
|
| 349 |
-
"reward": 0.571696400642395
|
| 350 |
-
},
|
| 351 |
-
{
|
| 352 |
-
"step": 69,
|
| 353 |
-
"reward": 0.5544642806053162
|
| 354 |
-
},
|
| 355 |
-
{
|
| 356 |
-
"step": 70,
|
| 357 |
-
"reward": 0.6167857646942139
|
| 358 |
-
},
|
| 359 |
-
{
|
| 360 |
-
"step": 71,
|
| 361 |
-
"reward": 0.45669642090797424
|
| 362 |
-
},
|
| 363 |
-
{
|
| 364 |
-
"step": 72,
|
| 365 |
-
"reward": 0.31955355405807495
|
| 366 |
-
},
|
| 367 |
-
{
|
| 368 |
-
"step": 73,
|
| 369 |
-
"reward": 0.5181249976158142
|
| 370 |
-
},
|
| 371 |
-
{
|
| 372 |
-
"step": 74,
|
| 373 |
-
"reward": 0.4415178596973419
|
| 374 |
-
},
|
| 375 |
-
{
|
| 376 |
-
"step": 75,
|
| 377 |
-
"reward": 0.5451785326004028
|
| 378 |
-
},
|
| 379 |
-
{
|
| 380 |
-
"step": 76,
|
| 381 |
-
"reward": 0.3028392791748047
|
| 382 |
-
},
|
| 383 |
-
{
|
| 384 |
-
"step": 77,
|
| 385 |
-
"reward": 0.2091071605682373
|
| 386 |
-
},
|
| 387 |
-
{
|
| 388 |
-
"step": 78,
|
| 389 |
-
"reward": 0.536339282989502
|
| 390 |
-
},
|
| 391 |
-
{
|
| 392 |
-
"step": 79,
|
| 393 |
-
"reward": 0.2366071492433548
|
| 394 |
-
},
|
| 395 |
-
{
|
| 396 |
-
"step": 80,
|
| 397 |
-
"reward": 0.3268928527832031
|
| 398 |
-
},
|
| 399 |
-
{
|
| 400 |
-
"step": 81,
|
| 401 |
-
"reward": 0.5390892624855042
|
| 402 |
-
},
|
| 403 |
-
{
|
| 404 |
-
"step": 82,
|
| 405 |
-
"reward": 0.4825892746448517
|
| 406 |
-
},
|
| 407 |
-
{
|
| 408 |
-
"step": 83,
|
| 409 |
-
"reward": 0.46875
|
| 410 |
-
},
|
| 411 |
-
{
|
| 412 |
-
"step": 84,
|
| 413 |
-
"reward": 0.7821428775787354
|
| 414 |
-
},
|
| 415 |
-
{
|
| 416 |
-
"step": 85,
|
| 417 |
-
"reward": 0.4580357074737549
|
| 418 |
-
},
|
| 419 |
-
{
|
| 420 |
-
"step": 86,
|
| 421 |
-
"reward": 0.5209821462631226
|
| 422 |
-
},
|
| 423 |
-
{
|
| 424 |
-
"step": 87,
|
| 425 |
-
"reward": 0.4017857313156128
|
| 426 |
-
},
|
| 427 |
-
{
|
| 428 |
-
"step": 88,
|
| 429 |
-
"reward": 0.660178542137146
|
| 430 |
-
},
|
| 431 |
-
{
|
| 432 |
-
"step": 89,
|
| 433 |
-
"reward": 0.5458393096923828
|
| 434 |
-
},
|
| 435 |
-
{
|
| 436 |
-
"step": 90,
|
| 437 |
-
"reward": 0.7919642925262451
|
| 438 |
-
},
|
| 439 |
-
{
|
| 440 |
-
"step": 91,
|
| 441 |
-
"reward": 0.4300000071525574
|
| 442 |
-
},
|
| 443 |
-
{
|
| 444 |
-
"step": 92,
|
| 445 |
-
"reward": 0.501964271068573
|
| 446 |
-
},
|
| 447 |
-
{
|
| 448 |
-
"step": 93,
|
| 449 |
-
"reward": 0.6446428298950195
|
| 450 |
-
},
|
| 451 |
-
{
|
| 452 |
-
"step": 94,
|
| 453 |
-
"reward": 0.5094642639160156
|
| 454 |
-
},
|
| 455 |
-
{
|
| 456 |
-
"step": 95,
|
| 457 |
-
"reward": 0.5647678375244141
|
| 458 |
-
},
|
| 459 |
-
{
|
| 460 |
-
"step": 96,
|
| 461 |
-
"reward": 0.6352678537368774
|
| 462 |
-
},
|
| 463 |
-
{
|
| 464 |
-
"step": 97,
|
| 465 |
-
"reward": 0.5024999976158142
|
| 466 |
-
},
|
| 467 |
-
{
|
| 468 |
-
"step": 98,
|
| 469 |
-
"reward": 0.515874981880188
|
| 470 |
-
},
|
| 471 |
-
{
|
| 472 |
-
"step": 99,
|
| 473 |
-
"reward": 0.46294644474983215
|
| 474 |
-
},
|
| 475 |
-
{
|
| 476 |
-
"step": 100,
|
| 477 |
-
"reward": 0.8723214268684387
|
| 478 |
-
},
|
| 479 |
-
{
|
| 480 |
-
"step": 101,
|
| 481 |
-
"reward": 0.5212500095367432
|
| 482 |
-
},
|
| 483 |
-
{
|
| 484 |
-
"step": 102,
|
| 485 |
-
"reward": 0.671875
|
| 486 |
-
},
|
| 487 |
-
{
|
| 488 |
-
"step": 103,
|
| 489 |
-
"reward": 0.5864999890327454
|
| 490 |
-
},
|
| 491 |
-
{
|
| 492 |
-
"step": 104,
|
| 493 |
-
"reward": 0.6749999523162842
|
| 494 |
-
},
|
| 495 |
-
{
|
| 496 |
-
"step": 105,
|
| 497 |
-
"reward": 0.5629464387893677
|
| 498 |
-
},
|
| 499 |
-
{
|
| 500 |
-
"step": 106,
|
| 501 |
-
"reward": 0.5281071662902832
|
| 502 |
-
},
|
| 503 |
-
{
|
| 504 |
-
"step": 107,
|
| 505 |
-
"reward": 0.6936607360839844
|
| 506 |
-
},
|
| 507 |
-
{
|
| 508 |
-
"step": 108,
|
| 509 |
-
"reward": 0.6465713977813721
|
| 510 |
-
},
|
| 511 |
-
{
|
| 512 |
-
"step": 109,
|
| 513 |
-
"reward": 0.5022321343421936
|
| 514 |
-
},
|
| 515 |
-
{
|
| 516 |
-
"step": 110,
|
| 517 |
-
"reward": 0.5313928127288818
|
| 518 |
-
},
|
| 519 |
-
{
|
| 520 |
-
"step": 111,
|
| 521 |
-
"reward": 0.6238213777542114
|
| 522 |
-
},
|
| 523 |
-
{
|
| 524 |
-
"step": 112,
|
| 525 |
-
"reward": 0.6399999856948853
|
| 526 |
-
},
|
| 527 |
-
{
|
| 528 |
-
"step": 113,
|
| 529 |
-
"reward": 0.7440178394317627
|
| 530 |
-
},
|
| 531 |
-
{
|
| 532 |
-
"step": 114,
|
| 533 |
-
"reward": 0.5431250333786011
|
| 534 |
-
},
|
| 535 |
-
{
|
| 536 |
-
"step": 115,
|
| 537 |
-
"reward": 0.6102678775787354
|
| 538 |
-
},
|
| 539 |
-
{
|
| 540 |
-
"step": 116,
|
| 541 |
-
"reward": 0.6504464149475098
|
| 542 |
-
},
|
| 543 |
-
{
|
| 544 |
-
"step": 117,
|
| 545 |
-
"reward": 0.7581071257591248
|
| 546 |
-
},
|
| 547 |
-
{
|
| 548 |
-
"step": 118,
|
| 549 |
-
"reward": 0.6492946147918701
|
| 550 |
-
},
|
| 551 |
-
{
|
| 552 |
-
"step": 119,
|
| 553 |
-
"reward": 0.6843750476837158
|
| 554 |
-
},
|
| 555 |
-
{
|
| 556 |
-
"step": 120,
|
| 557 |
-
"reward": 0.5536428689956665
|
| 558 |
-
},
|
| 559 |
-
{
|
| 560 |
-
"step": 121,
|
| 561 |
-
"reward": 0.653249979019165
|
| 562 |
-
},
|
| 563 |
-
{
|
| 564 |
-
"step": 122,
|
| 565 |
-
"reward": 0.5297499895095825
|
| 566 |
-
},
|
| 567 |
-
{
|
| 568 |
-
"step": 123,
|
| 569 |
-
"reward": 0.6578571796417236
|
| 570 |
-
},
|
| 571 |
-
{
|
| 572 |
-
"step": 124,
|
| 573 |
-
"reward": 0.8348214626312256
|
| 574 |
-
},
|
| 575 |
-
{
|
| 576 |
-
"step": 125,
|
| 577 |
-
"reward": 0.349785715341568
|
| 578 |
-
},
|
| 579 |
-
{
|
| 580 |
-
"step": 126,
|
| 581 |
-
"reward": 0.7781250476837158
|
| 582 |
-
},
|
| 583 |
-
{
|
| 584 |
-
"step": 127,
|
| 585 |
-
"reward": 0.8968750238418579
|
| 586 |
-
},
|
| 587 |
-
{
|
| 588 |
-
"step": 128,
|
| 589 |
-
"reward": 0.8093750476837158
|
| 590 |
-
},
|
| 591 |
-
{
|
| 592 |
-
"step": 129,
|
| 593 |
-
"reward": 0.6137499809265137
|
| 594 |
-
},
|
| 595 |
-
{
|
| 596 |
-
"step": 130,
|
| 597 |
-
"reward": 0.8910714387893677
|
| 598 |
-
},
|
| 599 |
-
{
|
| 600 |
-
"step": 131,
|
| 601 |
-
"reward": 0.4497321546077728
|
| 602 |
-
},
|
| 603 |
-
{
|
| 604 |
-
"step": 132,
|
| 605 |
-
"reward": 0.43910714983940125
|
| 606 |
-
},
|
| 607 |
-
{
|
| 608 |
-
"step": 133,
|
| 609 |
-
"reward": 0.48475003242492676
|
| 610 |
-
},
|
| 611 |
-
{
|
| 612 |
-
"step": 134,
|
| 613 |
-
"reward": 0.90625
|
| 614 |
-
},
|
| 615 |
-
{
|
| 616 |
-
"step": 135,
|
| 617 |
-
"reward": 0.6499999761581421
|
| 618 |
-
},
|
| 619 |
-
{
|
| 620 |
-
"step": 136,
|
| 621 |
-
"reward": 0.4575803279876709
|
| 622 |
-
},
|
| 623 |
-
{
|
| 624 |
-
"step": 137,
|
| 625 |
-
"reward": 0.5043749809265137
|
| 626 |
-
},
|
| 627 |
-
{
|
| 628 |
-
"step": 138,
|
| 629 |
-
"reward": 0.5194821357727051
|
| 630 |
-
},
|
| 631 |
-
{
|
| 632 |
-
"step": 139,
|
| 633 |
-
"reward": 0.6681874990463257
|
| 634 |
-
},
|
| 635 |
-
{
|
| 636 |
-
"step": 140,
|
| 637 |
-
"reward": 0.6075000166893005
|
| 638 |
-
},
|
| 639 |
-
{
|
| 640 |
-
"step": 141,
|
| 641 |
-
"reward": 0.5226786136627197
|
| 642 |
-
},
|
| 643 |
-
{
|
| 644 |
-
"step": 142,
|
| 645 |
-
"reward": 0.544910728931427
|
| 646 |
-
},
|
| 647 |
-
{
|
| 648 |
-
"step": 143,
|
| 649 |
-
"reward": 0.3448214530944824
|
| 650 |
-
},
|
| 651 |
-
{
|
| 652 |
-
"step": 144,
|
| 653 |
-
"reward": 0.5093749761581421
|
| 654 |
-
},
|
| 655 |
-
{
|
| 656 |
-
"step": 145,
|
| 657 |
-
"reward": 0.5335178375244141
|
| 658 |
-
},
|
| 659 |
-
{
|
| 660 |
-
"step": 146,
|
| 661 |
-
"reward": 0.5901785492897034
|
| 662 |
-
},
|
| 663 |
-
{
|
| 664 |
-
"step": 147,
|
| 665 |
-
"reward": 0.6714285612106323
|
| 666 |
-
},
|
| 667 |
-
{
|
| 668 |
-
"step": 148,
|
| 669 |
-
"reward": 0.6086249351501465
|
| 670 |
-
},
|
| 671 |
-
{
|
| 672 |
-
"step": 149,
|
| 673 |
-
"reward": 0.4005535840988159
|
| 674 |
-
},
|
| 675 |
-
{
|
| 676 |
-
"step": 150,
|
| 677 |
-
"reward": 0.4816071391105652
|
| 678 |
-
},
|
| 679 |
-
{
|
| 680 |
-
"step": 151,
|
| 681 |
-
"reward": 0.5088571310043335
|
| 682 |
-
},
|
| 683 |
-
{
|
| 684 |
-
"step": 152,
|
| 685 |
-
"reward": 0.8410714268684387
|
| 686 |
-
},
|
| 687 |
-
{
|
| 688 |
-
"step": 153,
|
| 689 |
-
"reward": 0.661517858505249
|
| 690 |
-
},
|
| 691 |
-
{
|
| 692 |
-
"step": 154,
|
| 693 |
-
"reward": 0.4182142913341522
|
| 694 |
-
},
|
| 695 |
-
{
|
| 696 |
-
"step": 155,
|
| 697 |
-
"reward": 0.5462499856948853
|
| 698 |
-
},
|
| 699 |
-
{
|
| 700 |
-
"step": 156,
|
| 701 |
-
"reward": 0.5656249523162842
|
| 702 |
-
},
|
| 703 |
-
{
|
| 704 |
-
"step": 157,
|
| 705 |
-
"reward": 0.6449106931686401
|
| 706 |
-
},
|
| 707 |
-
{
|
| 708 |
-
"step": 158,
|
| 709 |
-
"reward": 0.8441964387893677
|
| 710 |
-
},
|
| 711 |
-
{
|
| 712 |
-
"step": 159,
|
| 713 |
-
"reward": 0.6388392448425293
|
| 714 |
-
},
|
| 715 |
-
{
|
| 716 |
-
"step": 160,
|
| 717 |
-
"reward": 0.3429464101791382
|
| 718 |
-
},
|
| 719 |
-
{
|
| 720 |
-
"step": 161,
|
| 721 |
-
"reward": 0.4982143044471741
|
| 722 |
-
},
|
| 723 |
-
{
|
| 724 |
-
"step": 162,
|
| 725 |
-
"reward": 0.4846428632736206
|
| 726 |
-
},
|
| 727 |
-
{
|
| 728 |
-
"step": 163,
|
| 729 |
-
"reward": 0.4471428394317627
|
| 730 |
-
},
|
| 731 |
-
{
|
| 732 |
-
"step": 164,
|
| 733 |
-
"reward": 0.6001249551773071
|
| 734 |
-
},
|
| 735 |
-
{
|
| 736 |
-
"step": 165,
|
| 737 |
-
"reward": 0.735714316368103
|
| 738 |
-
},
|
| 739 |
-
{
|
| 740 |
-
"step": 166,
|
| 741 |
-
"reward": 0.641964316368103
|
| 742 |
-
},
|
| 743 |
-
{
|
| 744 |
-
"step": 167,
|
| 745 |
-
"reward": 0.6100000143051147
|
| 746 |
-
},
|
| 747 |
-
{
|
| 748 |
-
"step": 168,
|
| 749 |
-
"reward": 0.7066963911056519
|
| 750 |
-
},
|
| 751 |
-
{
|
| 752 |
-
"step": 169,
|
| 753 |
-
"reward": 0.6348214149475098
|
| 754 |
-
},
|
| 755 |
-
{
|
| 756 |
-
"step": 170,
|
| 757 |
-
"reward": 0.5228928327560425
|
| 758 |
-
},
|
| 759 |
-
{
|
| 760 |
-
"step": 171,
|
| 761 |
-
"reward": 0.5739464163780212
|
| 762 |
-
},
|
| 763 |
-
{
|
| 764 |
-
"step": 172,
|
| 765 |
-
"reward": 0.6174107193946838
|
| 766 |
-
},
|
| 767 |
-
{
|
| 768 |
-
"step": 173,
|
| 769 |
-
"reward": 0.5413392782211304
|
| 770 |
-
},
|
| 771 |
-
{
|
| 772 |
-
"step": 174,
|
| 773 |
-
"reward": 0.5052499771118164
|
| 774 |
-
},
|
| 775 |
-
{
|
| 776 |
-
"step": 175,
|
| 777 |
-
"reward": 0.5122321248054504
|
| 778 |
-
},
|
| 779 |
-
{
|
| 780 |
-
"step": 176,
|
| 781 |
-
"reward": 0.2723214328289032
|
| 782 |
-
},
|
| 783 |
-
{
|
| 784 |
-
"step": 177,
|
| 785 |
-
"reward": 0.796875
|
| 786 |
-
},
|
| 787 |
-
{
|
| 788 |
-
"step": 178,
|
| 789 |
-
"reward": 0.5441964864730835
|
| 790 |
-
},
|
| 791 |
-
{
|
| 792 |
-
"step": 179,
|
| 793 |
-
"reward": 0.578125
|
| 794 |
-
},
|
| 795 |
-
{
|
| 796 |
-
"step": 180,
|
| 797 |
-
"reward": 0.5441964268684387
|
| 798 |
-
},
|
| 799 |
-
{
|
| 800 |
-
"step": 181,
|
| 801 |
-
"reward": 0.4543749988079071
|
| 802 |
-
},
|
| 803 |
-
{
|
| 804 |
-
"step": 182,
|
| 805 |
-
"reward": 0.31626784801483154
|
| 806 |
-
},
|
| 807 |
-
{
|
| 808 |
-
"step": 183,
|
| 809 |
-
"reward": 0.6285713911056519
|
| 810 |
-
},
|
| 811 |
-
{
|
| 812 |
-
"step": 184,
|
| 813 |
-
"reward": 0.6952678561210632
|
| 814 |
-
},
|
| 815 |
-
{
|
| 816 |
-
"step": 185,
|
| 817 |
-
"reward": 0.484375
|
| 818 |
-
},
|
| 819 |
-
{
|
| 820 |
-
"step": 186,
|
| 821 |
-
"reward": 0.5447321534156799
|
| 822 |
-
},
|
| 823 |
-
{
|
| 824 |
-
"step": 187,
|
| 825 |
-
"reward": 0.6228570938110352
|
| 826 |
-
},
|
| 827 |
-
{
|
| 828 |
-
"step": 188,
|
| 829 |
-
"reward": 0.5247321128845215
|
| 830 |
-
},
|
| 831 |
-
{
|
| 832 |
-
"step": 189,
|
| 833 |
-
"reward": 0.6542679071426392
|
| 834 |
-
},
|
| 835 |
-
{
|
| 836 |
-
"step": 190,
|
| 837 |
-
"reward": 0.5883928537368774
|
| 838 |
-
},
|
| 839 |
-
{
|
| 840 |
-
"step": 191,
|
| 841 |
-
"reward": 0.5099107027053833
|
| 842 |
-
},
|
| 843 |
-
{
|
| 844 |
-
"step": 192,
|
| 845 |
-
"reward": 0.49196428060531616
|
| 846 |
-
},
|
| 847 |
-
{
|
| 848 |
-
"step": 193,
|
| 849 |
-
"reward": 0.6783928871154785
|
| 850 |
-
},
|
| 851 |
-
{
|
| 852 |
-
"step": 194,
|
| 853 |
-
"reward": 0.8446428775787354
|
| 854 |
-
},
|
| 855 |
-
{
|
| 856 |
-
"step": 195,
|
| 857 |
-
"reward": 0.27032142877578735
|
| 858 |
-
},
|
| 859 |
-
{
|
| 860 |
-
"step": 196,
|
| 861 |
-
"reward": 0.5037678480148315
|
| 862 |
-
},
|
| 863 |
-
{
|
| 864 |
-
"step": 197,
|
| 865 |
-
"reward": 0.7468750476837158
|
| 866 |
-
},
|
| 867 |
-
{
|
| 868 |
-
"step": 198,
|
| 869 |
-
"reward": 0.5247321128845215
|
| 870 |
-
},
|
| 871 |
-
{
|
| 872 |
-
"step": 199,
|
| 873 |
-
"reward": 0.5624642968177795
|
| 874 |
-
},
|
| 875 |
-
{
|
| 876 |
-
"step": 200,
|
| 877 |
-
"reward": 0.7284821271896362
|
| 878 |
-
},
|
| 879 |
-
{
|
| 880 |
-
"step": 201,
|
| 881 |
-
"reward": 0.5191071033477783
|
| 882 |
-
},
|
| 883 |
-
{
|
| 884 |
-
"step": 202,
|
| 885 |
-
"reward": 0.6629464030265808
|
| 886 |
-
},
|
| 887 |
-
{
|
| 888 |
-
"step": 203,
|
| 889 |
-
"reward": 0.5663928985595703
|
| 890 |
-
},
|
| 891 |
-
{
|
| 892 |
-
"step": 204,
|
| 893 |
-
"reward": 0.5843750238418579
|
| 894 |
-
},
|
| 895 |
-
{
|
| 896 |
-
"step": 205,
|
| 897 |
-
"reward": 0.6022321581840515
|
| 898 |
-
},
|
| 899 |
-
{
|
| 900 |
-
"step": 206,
|
| 901 |
-
"reward": 0.40528571605682373
|
| 902 |
-
},
|
| 903 |
-
{
|
| 904 |
-
"step": 207,
|
| 905 |
-
"reward": 0.3661428689956665
|
| 906 |
-
},
|
| 907 |
-
{
|
| 908 |
-
"step": 208,
|
| 909 |
-
"reward": 0.5410714149475098
|
| 910 |
-
},
|
| 911 |
-
{
|
| 912 |
-
"step": 209,
|
| 913 |
-
"reward": 0.8133928775787354
|
| 914 |
-
},
|
| 915 |
-
{
|
| 916 |
-
"step": 210,
|
| 917 |
-
"reward": 0.6950892806053162
|
| 918 |
-
},
|
| 919 |
-
{
|
| 920 |
-
"step": 211,
|
| 921 |
-
"reward": 0.6952678561210632
|
| 922 |
-
},
|
| 923 |
-
{
|
| 924 |
-
"step": 212,
|
| 925 |
-
"reward": 0.6540178656578064
|
| 926 |
-
},
|
| 927 |
-
{
|
| 928 |
-
"step": 213,
|
| 929 |
-
"reward": 0.642464280128479
|
| 930 |
-
},
|
| 931 |
-
{
|
| 932 |
-
"step": 214,
|
| 933 |
-
"reward": 0.37055355310440063
|
| 934 |
-
},
|
| 935 |
-
{
|
| 936 |
-
"step": 215,
|
| 937 |
-
"reward": 0.7700892686843872
|
| 938 |
-
},
|
| 939 |
-
{
|
| 940 |
-
"step": 216,
|
| 941 |
-
"reward": 0.6158928871154785
|
| 942 |
-
},
|
| 943 |
-
{
|
| 944 |
-
"step": 217,
|
| 945 |
-
"reward": 0.8133928775787354
|
| 946 |
-
},
|
| 947 |
-
{
|
| 948 |
-
"step": 218,
|
| 949 |
-
"reward": 0.5236964225769043
|
| 950 |
-
},
|
| 951 |
-
{
|
| 952 |
-
"step": 219,
|
| 953 |
-
"reward": 0.5915178656578064
|
| 954 |
-
},
|
| 955 |
-
{
|
| 956 |
-
"step": 220,
|
| 957 |
-
"reward": 0.5193749666213989
|
| 958 |
-
},
|
| 959 |
-
{
|
| 960 |
-
"step": 221,
|
| 961 |
-
"reward": 0.956250011920929
|
| 962 |
-
},
|
| 963 |
-
{
|
| 964 |
-
"step": 222,
|
| 965 |
-
"reward": 0.8441964387893677
|
| 966 |
-
},
|
| 967 |
-
{
|
| 968 |
-
"step": 223,
|
| 969 |
-
"reward": 0.5497321486473083
|
| 970 |
-
},
|
| 971 |
-
{
|
| 972 |
-
"step": 224,
|
| 973 |
-
"reward": 0.6256250143051147
|
| 974 |
-
},
|
| 975 |
-
{
|
| 976 |
-
"step": 225,
|
| 977 |
-
"reward": 0.637946367263794
|
| 978 |
-
},
|
| 979 |
-
{
|
| 980 |
-
"step": 226,
|
| 981 |
-
"reward": 0.6213749647140503
|
| 982 |
-
},
|
| 983 |
-
{
|
| 984 |
-
"step": 227,
|
| 985 |
-
"reward": 0.7883928418159485
|
| 986 |
-
},
|
| 987 |
-
{
|
| 988 |
-
"step": 228,
|
| 989 |
-
"reward": 0.6973214149475098
|
| 990 |
-
},
|
| 991 |
-
{
|
| 992 |
-
"step": 229,
|
| 993 |
-
"reward": 0.84375
|
| 994 |
-
},
|
| 995 |
-
{
|
| 996 |
-
"step": 230,
|
| 997 |
-
"reward": 0.6660535335540771
|
| 998 |
-
},
|
| 999 |
-
{
|
| 1000 |
-
"step": 231,
|
| 1001 |
-
"reward": 0.9249999523162842
|
| 1002 |
-
},
|
| 1003 |
-
{
|
| 1004 |
-
"step": 232,
|
| 1005 |
-
"reward": 0.5973213911056519
|
| 1006 |
-
},
|
| 1007 |
-
{
|
| 1008 |
-
"step": 233,
|
| 1009 |
-
"reward": 0.5616071224212646
|
| 1010 |
-
},
|
| 1011 |
-
{
|
| 1012 |
-
"step": 234,
|
| 1013 |
-
"reward": 0.6325000524520874
|
| 1014 |
-
},
|
| 1015 |
-
{
|
| 1016 |
-
"step": 235,
|
| 1017 |
-
"reward": 0.5837500095367432
|
| 1018 |
-
},
|
| 1019 |
-
{
|
| 1020 |
-
"step": 236,
|
| 1021 |
-
"reward": 0.4354107081890106
|
| 1022 |
-
},
|
| 1023 |
-
{
|
| 1024 |
-
"step": 237,
|
| 1025 |
-
"reward": 0.8660714626312256
|
| 1026 |
-
},
|
| 1027 |
-
{
|
| 1028 |
-
"step": 238,
|
| 1029 |
-
"reward": 0.6324999928474426
|
| 1030 |
-
},
|
| 1031 |
-
{
|
| 1032 |
-
"step": 239,
|
| 1033 |
-
"reward": 0.5628928542137146
|
| 1034 |
-
},
|
| 1035 |
-
{
|
| 1036 |
-
"step": 240,
|
| 1037 |
-
"reward": 0.6083928346633911
|
| 1038 |
-
},
|
| 1039 |
-
{
|
| 1040 |
-
"step": 241,
|
| 1041 |
-
"reward": 0.42701786756515503
|
| 1042 |
-
},
|
| 1043 |
-
{
|
| 1044 |
-
"step": 242,
|
| 1045 |
-
"reward": 0.890625
|
| 1046 |
-
},
|
| 1047 |
-
{
|
| 1048 |
-
"step": 243,
|
| 1049 |
-
"reward": 0.8290178775787354
|
| 1050 |
-
},
|
| 1051 |
-
{
|
| 1052 |
-
"step": 244,
|
| 1053 |
-
"reward": 0.6953214406967163
|
| 1054 |
-
},
|
| 1055 |
-
{
|
| 1056 |
-
"step": 245,
|
| 1057 |
-
"reward": 0.5653928518295288
|
| 1058 |
-
},
|
| 1059 |
-
{
|
| 1060 |
-
"step": 246,
|
| 1061 |
-
"reward": 0.6873035430908203
|
| 1062 |
-
},
|
| 1063 |
-
{
|
| 1064 |
-
"step": 247,
|
| 1065 |
-
"reward": 0.5102678537368774
|
| 1066 |
-
},
|
| 1067 |
-
{
|
| 1068 |
-
"step": 248,
|
| 1069 |
-
"reward": 0.5462678670883179
|
| 1070 |
-
},
|
| 1071 |
-
{
|
| 1072 |
-
"step": 249,
|
| 1073 |
-
"reward": 0.9468749761581421
|
| 1074 |
-
},
|
| 1075 |
-
{
|
| 1076 |
-
"step": 250,
|
| 1077 |
-
"reward": 0.4848214387893677
|
| 1078 |
-
},
|
| 1079 |
-
{
|
| 1080 |
-
"step": 251,
|
| 1081 |
-
"reward": 0.7349107265472412
|
| 1082 |
-
},
|
| 1083 |
-
{
|
| 1084 |
-
"step": 252,
|
| 1085 |
-
"reward": 0.5615178346633911
|
| 1086 |
-
},
|
| 1087 |
-
{
|
| 1088 |
-
"step": 253,
|
| 1089 |
-
"reward": 0.859375
|
| 1090 |
-
},
|
| 1091 |
-
{
|
| 1092 |
-
"step": 254,
|
| 1093 |
-
"reward": 0.706250011920929
|
| 1094 |
-
},
|
| 1095 |
-
{
|
| 1096 |
-
"step": 255,
|
| 1097 |
-
"reward": 0.7140178680419922
|
| 1098 |
-
},
|
| 1099 |
-
{
|
| 1100 |
-
"step": 256,
|
| 1101 |
-
"reward": 0.42228570580482483
|
| 1102 |
-
},
|
| 1103 |
-
{
|
| 1104 |
-
"step": 257,
|
| 1105 |
-
"reward": 0.6294910907745361
|
| 1106 |
-
},
|
| 1107 |
-
{
|
| 1108 |
-
"step": 258,
|
| 1109 |
-
"reward": 0.5381250381469727
|
| 1110 |
-
},
|
| 1111 |
-
{
|
| 1112 |
-
"step": 259,
|
| 1113 |
-
"reward": 0.6176071166992188
|
| 1114 |
-
},
|
| 1115 |
-
{
|
| 1116 |
-
"step": 260,
|
| 1117 |
-
"reward": 0.7239285707473755
|
| 1118 |
-
},
|
| 1119 |
-
{
|
| 1120 |
-
"step": 261,
|
| 1121 |
-
"reward": 0.5584821701049805
|
| 1122 |
-
},
|
| 1123 |
-
{
|
| 1124 |
-
"step": 262,
|
| 1125 |
-
"reward": 0.6481249928474426
|
| 1126 |
-
},
|
| 1127 |
-
{
|
| 1128 |
-
"step": 263,
|
| 1129 |
-
"reward": 0.7474821209907532
|
| 1130 |
-
},
|
| 1131 |
-
{
|
| 1132 |
-
"step": 264,
|
| 1133 |
-
"reward": 0.7473214268684387
|
| 1134 |
-
},
|
| 1135 |
-
{
|
| 1136 |
-
"step": 265,
|
| 1137 |
-
"reward": 0.5647231936454773
|
| 1138 |
-
},
|
| 1139 |
-
{
|
| 1140 |
-
"step": 266,
|
| 1141 |
-
"reward": 0.6187499761581421
|
| 1142 |
-
},
|
| 1143 |
-
{
|
| 1144 |
-
"step": 267,
|
| 1145 |
-
"reward": 0.5382499694824219
|
| 1146 |
-
},
|
| 1147 |
-
{
|
| 1148 |
-
"step": 268,
|
| 1149 |
-
"reward": 0.6027321219444275
|
| 1150 |
-
},
|
| 1151 |
-
{
|
| 1152 |
-
"step": 269,
|
| 1153 |
-
"reward": 0.6174999475479126
|
| 1154 |
-
},
|
| 1155 |
-
{
|
| 1156 |
-
"step": 270,
|
| 1157 |
-
"reward": 0.8348214626312256
|
| 1158 |
}
|
| 1159 |
],
|
| 1160 |
"config": {
|
| 1161 |
"model": "Qwen/Qwen2.5-0.5B-Instruct",
|
| 1162 |
"n_per_task": 30,
|
| 1163 |
-
"num_generations":
|
| 1164 |
-
"epochs":
|
| 1165 |
-
"lr":
|
| 1166 |
}
|
| 1167 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"baseline": {
|
| 3 |
"easy": [
|
| 4 |
+
0.0,
|
| 5 |
+
0.0,
|
| 6 |
+
0.65,
|
| 7 |
+
0.65,
|
| 8 |
0.2,
|
| 9 |
0.65,
|
| 10 |
0.65,
|
| 11 |
0.65,
|
| 12 |
0.65,
|
| 13 |
+
0.825
|
|
|
|
|
|
|
|
|
|
|
|
|
| 14 |
],
|
| 15 |
"medium": [
|
| 16 |
+
0.5471428571428572,
|
| 17 |
+
0.5471428571428572,
|
|
|
|
| 18 |
0.15714285714285714,
|
| 19 |
0.15714285714285714,
|
| 20 |
+
0.5900000000000001,
|
| 21 |
0.5471428571428572,
|
| 22 |
+
0.11428571428571427,
|
| 23 |
0.15714285714285714,
|
| 24 |
0.11428571428571427,
|
| 25 |
+
0.5471428571428572
|
| 26 |
],
|
| 27 |
"hard": [
|
| 28 |
+
0.5498571428571429,
|
|
|
|
| 29 |
0.10071428571428576,
|
|
|
|
| 30 |
0.5498571428571429,
|
| 31 |
0.0,
|
| 32 |
+
0.5498571428571429,
|
| 33 |
+
0.5498571428571429,
|
| 34 |
0.14785714285714285,
|
| 35 |
0.5498571428571429,
|
| 36 |
+
0.0,
|
| 37 |
+
0.31414285714285717
|
| 38 |
]
|
| 39 |
},
|
| 40 |
"trained": {
|
| 41 |
"easy": [
|
| 42 |
+
0.2,
|
| 43 |
+
0.2,
|
| 44 |
+
0.2,
|
| 45 |
+
0.2,
|
| 46 |
+
0.2,
|
| 47 |
+
0.2,
|
| 48 |
+
0.2,
|
| 49 |
+
0.2,
|
| 50 |
+
0.2,
|
| 51 |
+
0.2
|
| 52 |
],
|
| 53 |
"medium": [
|
| 54 |
+
0.2,
|
| 55 |
+
0.2,
|
| 56 |
+
0.2,
|
| 57 |
+
0.2,
|
| 58 |
+
0.2,
|
| 59 |
+
0.2,
|
| 60 |
+
0.2,
|
| 61 |
+
0.2,
|
| 62 |
+
0.2,
|
| 63 |
+
0.2
|
| 64 |
],
|
| 65 |
"hard": [
|
| 66 |
+
0.195,
|
| 67 |
+
0.195,
|
| 68 |
+
0.195,
|
| 69 |
+
0.10071428571428576,
|
| 70 |
+
0.195,
|
| 71 |
+
0.195,
|
| 72 |
+
0.195,
|
| 73 |
+
0.195,
|
| 74 |
+
0.195,
|
| 75 |
+
0.195
|
| 76 |
]
|
| 77 |
},
|
| 78 |
"training_log": [
|
| 79 |
{
|
| 80 |
"step": 1,
|
| 81 |
+
"reward": 0.14348214864730835
|
| 82 |
},
|
| 83 |
{
|
| 84 |
"step": 2,
|
| 85 |
+
"reward": 0.0
|
| 86 |
},
|
| 87 |
{
|
| 88 |
"step": 3,
|
| 89 |
+
"reward": 0.07462500035762787
|
| 90 |
},
|
| 91 |
{
|
| 92 |
"step": 4,
|
| 93 |
+
"reward": 0.1552678644657135
|
| 94 |
},
|
| 95 |
{
|
| 96 |
"step": 5,
|
| 97 |
+
"reward": 0.3454107344150543
|
| 98 |
},
|
| 99 |
{
|
| 100 |
"step": 6,
|
| 101 |
+
"reward": 0.39657142758369446
|
| 102 |
},
|
| 103 |
{
|
| 104 |
"step": 7,
|
| 105 |
+
"reward": 0.34035712480545044
|
| 106 |
},
|
| 107 |
{
|
| 108 |
"step": 8,
|
| 109 |
+
"reward": 0.2690357267856598
|
| 110 |
},
|
| 111 |
{
|
| 112 |
"step": 9,
|
| 113 |
+
"reward": 0.08392857760190964
|
| 114 |
},
|
| 115 |
{
|
| 116 |
"step": 10,
|
| 117 |
+
"reward": 0.17910714447498322
|
| 118 |
},
|
| 119 |
{
|
| 120 |
"step": 11,
|
| 121 |
+
"reward": 0.133928582072258
|
| 122 |
},
|
| 123 |
{
|
| 124 |
"step": 12,
|
| 125 |
+
"reward": 0.15482142567634583
|
| 126 |
},
|
| 127 |
{
|
| 128 |
"step": 13,
|
| 129 |
+
"reward": 0.0905357152223587
|
| 130 |
},
|
| 131 |
{
|
| 132 |
"step": 14,
|
| 133 |
+
"reward": 0.1125892847776413
|
| 134 |
},
|
| 135 |
{
|
| 136 |
"step": 15,
|
| 137 |
+
"reward": 0.1696428656578064
|
| 138 |
},
|
| 139 |
{
|
| 140 |
"step": 16,
|
| 141 |
+
"reward": 0.15000000596046448
|
| 142 |
},
|
| 143 |
{
|
| 144 |
"step": 17,
|
| 145 |
+
"reward": 0.1091071367263794
|
| 146 |
},
|
| 147 |
{
|
| 148 |
"step": 18,
|
| 149 |
+
"reward": 0.11428571492433548
|
| 150 |
},
|
| 151 |
{
|
| 152 |
"step": 19,
|
| 153 |
+
"reward": 0.08651785552501678
|
| 154 |
},
|
| 155 |
{
|
| 156 |
"step": 20,
|
| 157 |
+
"reward": 0.08651785552501678
|
| 158 |
},
|
| 159 |
{
|
| 160 |
"step": 21,
|
| 161 |
+
"reward": 0.12937501072883606
|
| 162 |
},
|
| 163 |
{
|
| 164 |
"step": 22,
|
| 165 |
+
"reward": 0.20000000298023224
|
| 166 |
},
|
| 167 |
{
|
| 168 |
"step": 23,
|
| 169 |
+
"reward": 0.13571429252624512
|
| 170 |
},
|
| 171 |
{
|
| 172 |
"step": 24,
|
| 173 |
+
"reward": 0.15241071581840515
|
| 174 |
},
|
| 175 |
{
|
| 176 |
"step": 25,
|
| 177 |
+
"reward": 0.1537500023841858
|
| 178 |
},
|
| 179 |
{
|
| 180 |
"step": 26,
|
| 181 |
+
"reward": 0.14892858266830444
|
| 182 |
},
|
| 183 |
{
|
| 184 |
"step": 27,
|
| 185 |
+
"reward": 0.12026786059141159
|
| 186 |
},
|
| 187 |
{
|
| 188 |
"step": 28,
|
| 189 |
+
"reward": 0.13035714626312256
|
| 190 |
},
|
| 191 |
{
|
| 192 |
"step": 29,
|
| 193 |
+
"reward": 0.14348214864730835
|
| 194 |
},
|
| 195 |
{
|
| 196 |
"step": 30,
|
| 197 |
+
"reward": 0.14651785790920258
|
| 198 |
},
|
| 199 |
{
|
| 200 |
"step": 31,
|
| 201 |
+
"reward": 0.15535715222358704
|
| 202 |
},
|
| 203 |
{
|
| 204 |
"step": 32,
|
| 205 |
+
"reward": 0.13928571343421936
|
| 206 |
},
|
| 207 |
{
|
| 208 |
"step": 33,
|
| 209 |
+
"reward": 0.14044642448425293
|
| 210 |
},
|
| 211 |
{
|
| 212 |
"step": 34,
|
| 213 |
+
"reward": 0.14642858505249023
|
| 214 |
},
|
| 215 |
{
|
| 216 |
"step": 35,
|
| 217 |
+
"reward": 0.14107142388820648
|
| 218 |
},
|
| 219 |
{
|
| 220 |
"step": 36,
|
| 221 |
+
"reward": 0.14276784658432007
|
| 222 |
},
|
| 223 |
{
|
| 224 |
"step": 37,
|
| 225 |
+
"reward": 0.15892857313156128
|
| 226 |
},
|
| 227 |
{
|
| 228 |
"step": 38,
|
| 229 |
+
"reward": 0.1237499937415123
|
| 230 |
},
|
| 231 |
{
|
| 232 |
"step": 39,
|
| 233 |
+
"reward": 0.13928571343421936
|
| 234 |
},
|
| 235 |
{
|
| 236 |
"step": 40,
|
| 237 |
+
"reward": 0.14276784658432007
|
| 238 |
},
|
| 239 |
{
|
| 240 |
"step": 41,
|
| 241 |
+
"reward": 0.1731249988079071
|
| 242 |
},
|
| 243 |
{
|
| 244 |
"step": 42,
|
| 245 |
+
"reward": 0.14464285969734192
|
| 246 |
},
|
| 247 |
{
|
| 248 |
"step": 43,
|
| 249 |
+
"reward": 0.1696428656578064
|
| 250 |
},
|
| 251 |
{
|
| 252 |
"step": 44,
|
| 253 |
+
"reward": 0.17500001192092896
|
| 254 |
},
|
| 255 |
{
|
| 256 |
"step": 45,
|
| 257 |
+
"reward": 0.14749999344348907
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 258 |
}
|
| 259 |
],
|
| 260 |
"config": {
|
| 261 |
"model": "Qwen/Qwen2.5-0.5B-Instruct",
|
| 262 |
"n_per_task": 30,
|
| 263 |
+
"num_generations": 4,
|
| 264 |
+
"epochs": 1,
|
| 265 |
+
"lr": 5e-06
|
| 266 |
}
|
| 267 |
}
|
training_results.png
CHANGED
|
Git LFS Details
|
|
Git LFS Details
|