kayacrypto/Qwen2.5-1.5B-Instruct-Gensyn-Swarm-mute_tall_zebra
013
1{2 "best_metric": null,3 "best_model_checkpoint": null,4 "epoch": 3.1914893617021276,5 "eval_steps": 500,6 "global_step": 150,7 "is_hyper_param_search": false,8 "is_local_process_zero": true,9 "is_world_process_zero": true,10 "log_history": [11 {12 "completion_length": 208.375,13 "epoch": 0.0425531914893617,14 "grad_norm": 1.2922682762145996,15 "kl": 0.368897657841444,16 "learning_rate": 2e-07,17 "loss": 0.0015,18 "reward": 2.9673363119363785,19 "reward_std": 0.7159197889268398,20 "rewards/concensus_correctness_reward_func": 0.5940000116825104,21 "rewards/consensus_reward_func": 0.5,22 "rewards/cumulative_reward_2": 0.0,23 "rewards/final_correctness_reward_func": 0.5,24 "rewards/question_recreation_reward_func": 0.6764611452817917,25 "rewards/soft_format_reward_func": 0.0,26 "rewards/strict_format_reward_func": 0.0,27 "rewards/xmlcount_reward_func": 0.6968750171363354,28 "step": 229 },30 {31 "completion_length": 201.625,32 "epoch": 0.0851063829787234,33 "grad_norm": 1.0189259052276611,34 "kl": 0.347530135884881,35 "learning_rate": 4e-07,36 "loss": 0.0014,37 "reward": 2.2502254247665405,38 "reward_std": 0.4711770210415125,39 "rewards/concensus_correctness_reward_func": 0.07975000143051147,40 "rewards/consensus_reward_func": 0.75,41 "rewards/cumulative_reward_2": 0.0,42 "rewards/final_correctness_reward_func": 0.0,43 "rewards/question_recreation_reward_func": 0.4989754855632782,44 "rewards/soft_format_reward_func": 0.0,45 "rewards/strict_format_reward_func": 0.0625,46 "rewards/xmlcount_reward_func": 0.8590000122785568,47 "step": 448 },49 {50 "completion_length": 218.625,51 "epoch": 0.1276595744680851,52 "grad_norm": 0.9101417660713196,53 "kl": 0.3101823255419731,54 "learning_rate": 4.99941324504621e-07,55 "loss": 0.0012,56 "reward": 6.895482659339905,57 "reward_std": 0.33527815621346235,58 "rewards/concensus_correctness_reward_func": 2.878499984741211,59 "rewards/consensus_reward_func": 1.5,60 "rewards/cumulative_reward_2": 0.0,61 "rewards/final_correctness_reward_func": 1.0,62 "rewards/question_recreation_reward_func": 0.7356077581644058,63 "rewards/soft_format_reward_func": 0.0,64 "rewards/strict_format_reward_func": 0.0,65 "rewards/xmlcount_reward_func": 0.7813750207424164,66 "step": 667 },68 {69 "completion_length": 192.25,70 "epoch": 0.1702127659574468,71 "grad_norm": 1.2948215007781982,72 "kl": 0.48327411338686943,73 "learning_rate": 4.99472085783721e-07,74 "loss": 0.0019,75 "reward": 2.358700782060623,76 "reward_std": 0.43746134638786316,77 "rewards/concensus_correctness_reward_func": 0.0625,78 "rewards/consensus_reward_func": 0.75,79 "rewards/cumulative_reward_2": 0.0,80 "rewards/final_correctness_reward_func": 0.0,81 "rewards/question_recreation_reward_func": 0.4269508011639118,82 "rewards/soft_format_reward_func": 0.0,83 "rewards/strict_format_reward_func": 0.0,84 "rewards/xmlcount_reward_func": 1.1192500293254852,85 "step": 886 },87 {88 "completion_length": 213.125,89 "epoch": 0.2127659574468085,90 "grad_norm": 0.8117519021034241,91 "kl": 0.29611096531152725,92 "learning_rate": 4.985344892885899e-07,93 "loss": 0.0012,94 "reward": 4.00871354341507,95 "reward_std": 0.6121221389621496,96 "rewards/concensus_correctness_reward_func": 0.8420000076293945,97 "rewards/consensus_reward_func": 1.25,98 "rewards/cumulative_reward_2": 0.0,99 "rewards/final_correctness_reward_func": 0.0,100 "rewards/question_recreation_reward_func": 0.7218383997678757,101 "rewards/soft_format_reward_func": 0.0,102 "rewards/strict_format_reward_func": 0.0625,103 "rewards/xmlcount_reward_func": 1.1323750019073486,104 "step": 10105 },106 {107 "completion_length": 211.5,108 "epoch": 0.2553191489361702,109 "grad_norm": 1.2261545658111572,110 "kl": 0.19816851243376732,111 "learning_rate": 4.971302952586796e-07,112 "loss": 0.0008,113 "reward": 4.616856753826141,114 "reward_std": 1.7651374153792858,115 "rewards/concensus_correctness_reward_func": 1.3724999725818634,116 "rewards/consensus_reward_func": 1.5,117 "rewards/cumulative_reward_2": 0.0,118 "rewards/final_correctness_reward_func": 0.0,119 "rewards/question_recreation_reward_func": 0.8312318325042725,120 "rewards/soft_format_reward_func": 0.0,121 "rewards/strict_format_reward_func": 0.0625,122 "rewards/xmlcount_reward_func": 0.8506250083446503,123 "step": 12124 },125 {126 "completion_length": 188.125,127 "epoch": 0.2978723404255319,128 "grad_norm": 1.6095143556594849,129 "kl": 0.41443780064582825,130 "learning_rate": 4.952621399215597e-07,131 "loss": 0.0017,132 "reward": 3.2810606956481934,133 "reward_std": 0.17259903845842928,134 "rewards/concensus_correctness_reward_func": 0.5642499923706055,135 "rewards/consensus_reward_func": 0.75,136 "rewards/cumulative_reward_2": 0.0,137 "rewards/final_correctness_reward_func": 0.25,138 "rewards/question_recreation_reward_func": 0.41268573701381683,139 "rewards/soft_format_reward_func": 0.0,140 "rewards/strict_format_reward_func": 0.125,141 "rewards/xmlcount_reward_func": 1.179125040769577,142 "step": 14143 },144 {145 "completion_length": 220.25,146 "epoch": 0.3404255319148936,147 "grad_norm": 0.7901090979576111,148 "kl": 0.23360246792435646,149 "learning_rate": 4.929335305436764e-07,150 "loss": 0.0009,151 "reward": 3.1471548080444336,152 "reward_std": 0.345611784607172,153 "rewards/concensus_correctness_reward_func": 0.35249999165534973,154 "rewards/consensus_reward_func": 1.0,155 "rewards/cumulative_reward_2": 0.0,156 "rewards/final_correctness_reward_func": 0.0,157 "rewards/question_recreation_reward_func": 0.7105298787355423,158 "rewards/soft_format_reward_func": 0.0,159 "rewards/strict_format_reward_func": 0.0625,160 "rewards/xmlcount_reward_func": 1.0216250121593475,161 "step": 16162 },163 {164 "completion_length": 210.625,165 "epoch": 0.3829787234042553,166 "grad_norm": 0.98528653383255,167 "kl": 0.2824025899171829,168 "learning_rate": 4.901488388458247e-07,169 "loss": 0.0011,170 "reward": 5.247417330741882,171 "reward_std": 1.4511100128293037,172 "rewards/concensus_correctness_reward_func": 1.4062499701976776,173 "rewards/consensus_reward_func": 1.75,174 "rewards/cumulative_reward_2": 0.0,175 "rewards/final_correctness_reward_func": 0.25,176 "rewards/question_recreation_reward_func": 0.9022922813892365,177 "rewards/soft_format_reward_func": 0.0,178 "rewards/strict_format_reward_func": 0.0625,179 "rewards/xmlcount_reward_func": 0.8763750195503235,180 "step": 18181 },182 {183 "completion_length": 162.5,184 "epoch": 0.425531914893617,185 "grad_norm": 4.668555736541748,186 "kl": 0.36848023161292076,187 "learning_rate": 4.869132927957006e-07,188 "loss": 0.0015,189 "reward": 2.5691540092229843,190 "reward_std": 1.8921008706092834,191 "rewards/concensus_correctness_reward_func": 0.431999996304512,192 "rewards/consensus_reward_func": 0.5,193 "rewards/cumulative_reward_2": 0.0,194 "rewards/final_correctness_reward_func": 0.0,195 "rewards/question_recreation_reward_func": 0.6601539999246597,196 "rewards/soft_format_reward_func": 0.0,197 "rewards/strict_format_reward_func": 0.0625,198 "rewards/xmlcount_reward_func": 0.9144999980926514,199 "step": 20200 },201 {202 "completion_length": 235.25,203 "epoch": 0.46808510638297873,204 "grad_norm": 0.9122532606124878,205 "kl": 0.21843332424759865,206 "learning_rate": 4.832329667929376e-07,207 "loss": 0.0009,208 "reward": 2.719956159591675,209 "reward_std": 1.2937508039176464,210 "rewards/concensus_correctness_reward_func": 0.03125,211 "rewards/consensus_reward_func": 1.0,212 "rewards/cumulative_reward_2": 0.0,213 "rewards/final_correctness_reward_func": 0.0,214 "rewards/question_recreation_reward_func": 0.696831189095974,215 "rewards/soft_format_reward_func": 0.0,216 "rewards/strict_format_reward_func": 0.125,217 "rewards/xmlcount_reward_func": 0.8668749928474426,218 "step": 22219 },220 {221 "completion_length": 231.75,222 "epoch": 0.5106382978723404,223 "grad_norm": 0.7768054604530334,224 "kl": 0.29690009728074074,225 "learning_rate": 4.791147702650565e-07,226 "loss": 0.0012,227 "reward": 2.6149866580963135,228 "reward_std": 1.671431414783001,229 "rewards/concensus_correctness_reward_func": 0.5020000040531158,230 "rewards/consensus_reward_func": 0.5,231 "rewards/cumulative_reward_2": 0.0,232 "rewards/final_correctness_reward_func": 0.0,233 "rewards/question_recreation_reward_func": 0.7118616253137589,234 "rewards/soft_format_reward_func": 0.0,235 "rewards/strict_format_reward_func": 0.0625,236 "rewards/xmlcount_reward_func": 0.8386250138282776,237 "step": 24238 },239 {240 "completion_length": 184.125,241 "epoch": 0.5531914893617021,242 "grad_norm": 1.186863660812378,243 "kl": 1.5620987825095654,244 "learning_rate": 4.745664346957361e-07,245 "loss": 0.0062,246 "reward": 3.6378692388534546,247 "reward_std": 2.059950995258987,248 "rewards/concensus_correctness_reward_func": 1.405000001192093,249 "rewards/consensus_reward_func": 1.0,250 "rewards/cumulative_reward_2": 0.0,251 "rewards/final_correctness_reward_func": 0.0,252 "rewards/question_recreation_reward_func": 0.3573692571371794,253 "rewards/soft_format_reward_func": 0.0,254 "rewards/strict_format_reward_func": 0.0625,255 "rewards/xmlcount_reward_func": 0.8129999935626984,256 "step": 26257 },258 {259 "completion_length": 206.0,260 "epoch": 0.5957446808510638,261 "grad_norm": 1.46551513671875,262 "kl": 0.26297080144286156,263 "learning_rate": 4.695964991097616e-07,264 "loss": 0.0011,265 "reward": 4.04424512386322,266 "reward_std": 1.5137748650740832,267 "rewards/concensus_correctness_reward_func": 0.6062500029802322,268 "rewards/consensus_reward_func": 1.5,269 "rewards/cumulative_reward_2": 0.0,270 "rewards/final_correctness_reward_func": 0.0,271 "rewards/question_recreation_reward_func": 0.8401201069355011,272 "rewards/soft_format_reward_func": 0.0,273 "rewards/strict_format_reward_func": 0.0625,274 "rewards/xmlcount_reward_func": 1.0353750437498093,275 "step": 28276 },277 {278 "completion_length": 175.375,279 "epoch": 0.6382978723404256,280 "grad_norm": 1.353365421295166,281 "kl": 0.3254816383123398,282 "learning_rate": 4.642142940418973e-07,283 "loss": 0.0013,284 "reward": 4.176763713359833,285 "reward_std": 1.3009796515107155,286 "rewards/concensus_correctness_reward_func": 0.6302500069141388,287 "rewards/consensus_reward_func": 1.25,288 "rewards/cumulative_reward_2": 0.0,289 "rewards/final_correctness_reward_func": 0.75,290 "rewards/question_recreation_reward_func": 0.4130137749016285,291 "rewards/soft_format_reward_func": 0.0,292 "rewards/strict_format_reward_func": 0.0625,293 "rewards/xmlcount_reward_func": 1.071000024676323,294 "step": 30295 },296 {297 "completion_length": 212.5,298 "epoch": 0.6808510638297872,299 "grad_norm": 1.0889848470687866,300 "kl": 0.18758773803710938,301 "learning_rate": 4.5842992401978256e-07,302 "loss": 0.0008,303 "reward": 4.88167667388916,304 "reward_std": 0.5472310213372111,305 "rewards/concensus_correctness_reward_func": 1.4514999985694885,306 "rewards/consensus_reward_func": 1.25,307 "rewards/cumulative_reward_2": 0.0,308 "rewards/final_correctness_reward_func": 0.25,309 "rewards/question_recreation_reward_func": 0.8103016316890717,310 "rewards/soft_format_reward_func": 0.0,311 "rewards/strict_format_reward_func": 0.0625,312 "rewards/xmlcount_reward_func": 1.0573750287294388,313 "step": 32314 },315 {316 "completion_length": 204.875,317 "epoch": 0.723404255319149,318 "grad_norm": 0.9522470235824585,319 "kl": 0.3280218355357647,320 "learning_rate": 4.5225424859373684e-07,321 "loss": 0.0013,322 "reward": 4.017025828361511,323 "reward_std": 1.5214910805225372,324 "rewards/concensus_correctness_reward_func": 0.8677500188350677,325 "rewards/consensus_reward_func": 1.25,326 "rewards/cumulative_reward_2": 0.0,327 "rewards/final_correctness_reward_func": 0.25,328 "rewards/question_recreation_reward_func": 0.7582758367061615,329 "rewards/soft_format_reward_func": 0.0,330 "rewards/strict_format_reward_func": 0.0,331 "rewards/xmlcount_reward_func": 0.8910000175237656,332 "step": 34333 },334 {335 "completion_length": 231.125,336 "epoch": 0.7659574468085106,337 "grad_norm": 1.057931900024414,338 "kl": 0.18039596267044544,339 "learning_rate": 4.456988619490889e-07,340 "loss": 0.0007,341 "reward": 3.097403198480606,342 "reward_std": 0.8839838430285454,343 "rewards/concensus_correctness_reward_func": 0.48875001072883606,344 "rewards/consensus_reward_func": 1.25,345 "rewards/cumulative_reward_2": 0.0,346 "rewards/final_correctness_reward_func": 0.0,347 "rewards/question_recreation_reward_func": 0.3899032846093178,348 "rewards/soft_format_reward_func": 0.0,349 "rewards/strict_format_reward_func": 0.0625,350 "rewards/xmlcount_reward_func": 0.90625,351 "step": 36352 },353 {354 "completion_length": 218.0,355 "epoch": 0.8085106382978723,356 "grad_norm": 0.8510872721672058,357 "kl": 0.4039253517985344,358 "learning_rate": 4.3877607113930516e-07,359 "loss": 0.0016,360 "reward": 3.3650201559066772,361 "reward_std": 1.0184866935014725,362 "rewards/concensus_correctness_reward_func": 0.3880000114440918,363 "rewards/consensus_reward_func": 1.0,364 "rewards/cumulative_reward_2": 0.0,365 "rewards/final_correctness_reward_func": 0.0,366 "rewards/question_recreation_reward_func": 0.8217700868844986,367 "rewards/soft_format_reward_func": 0.0,368 "rewards/strict_format_reward_func": 0.0625,369 "rewards/xmlcount_reward_func": 1.0927500128746033,370 "step": 38371 },372 {373 "completion_length": 198.125,374 "epoch": 0.851063829787234,375 "grad_norm": 1.4362971782684326,376 "kl": 0.29657943546772003,377 "learning_rate": 4.314988729807827e-07,378 "loss": 0.0012,379 "reward": 3.233266294002533,380 "reward_std": 1.4139978662133217,381 "rewards/concensus_correctness_reward_func": 0.5360000133514404,382 "rewards/consensus_reward_func": 1.25,383 "rewards/cumulative_reward_2": 0.0,384 "rewards/final_correctness_reward_func": 0.0,385 "rewards/question_recreation_reward_func": 0.5152662321925163,386 "rewards/soft_format_reward_func": 0.0,387 "rewards/strict_format_reward_func": 0.0625,388 "rewards/xmlcount_reward_func": 0.8695000261068344,389 "step": 40390 },391 {392 "completion_length": 207.625,393 "epoch": 0.8936170212765957,394 "grad_norm": 1.3076378107070923,395 "kl": 0.2851813957095146,396 "learning_rate": 4.238809296526846e-07,397 "loss": 0.0011,398 "reward": 3.2013108879327774,399 "reward_std": 0.792296152561903,400 "rewards/concensus_correctness_reward_func": 0.677499994635582,401 "rewards/consensus_reward_func": 1.25,402 "rewards/cumulative_reward_2": 0.0,403 "rewards/final_correctness_reward_func": 0.0,404 "rewards/question_recreation_reward_func": 0.2519359327852726,405 "rewards/soft_format_reward_func": 0.0,406 "rewards/strict_format_reward_func": 0.0625,407 "rewards/xmlcount_reward_func": 0.9593750387430191,408 "step": 42409 },410 {411 "completion_length": 207.0,412 "epoch": 0.9361702127659575,413 "grad_norm": 1.087996482849121,414 "kl": 0.23629741743206978,415 "learning_rate": 4.159365430476261e-07,416 "loss": 0.0009,417 "reward": 3.705885946750641,418 "reward_std": 1.2994485050439835,419 "rewards/concensus_correctness_reward_func": 0.9790000170469284,420 "rewards/consensus_reward_func": 1.0,421 "rewards/cumulative_reward_2": 0.0,422 "rewards/final_correctness_reward_func": 0.0,423 "rewards/question_recreation_reward_func": 0.7251358330249786,424 "rewards/soft_format_reward_func": 0.0,425 "rewards/strict_format_reward_func": 0.125,426 "rewards/xmlcount_reward_func": 0.8767499998211861,427 "step": 44428 },429 {430 "completion_length": 225.875,431 "epoch": 0.9787234042553191,432 "grad_norm": 0.7789207696914673,433 "kl": 0.4796878844499588,434 "learning_rate": 4.076806279213655e-07,435 "loss": 0.0019,436 "reward": 2.991653561592102,437 "reward_std": 0.6073275413364172,438 "rewards/concensus_correctness_reward_func": 0.0,439 "rewards/consensus_reward_func": 1.25,440 "rewards/cumulative_reward_2": 0.0,441 "rewards/final_correctness_reward_func": 0.0,442 "rewards/question_recreation_reward_func": 0.6905284896492958,443 "rewards/soft_format_reward_func": 0.0,444 "rewards/strict_format_reward_func": 0.0625,445 "rewards/xmlcount_reward_func": 0.9886249899864197,446 "step": 46447 },448 {449 "completion_length": 212.75,450 "epoch": 1.0212765957446808,451 "grad_norm": 1.0796300172805786,452 "kl": 0.3914450779557228,453 "learning_rate": 3.991286838919086e-07,454 "loss": 0.0016,455 "reward": 2.445985972881317,456 "reward_std": 1.0956205744296312,457 "rewards/concensus_correctness_reward_func": 0.2942500039935112,458 "rewards/consensus_reward_func": 0.5,459 "rewards/cumulative_reward_2": 0.0,460 "rewards/final_correctness_reward_func": 0.0,461 "rewards/question_recreation_reward_func": 0.5897360146045685,462 "rewards/soft_format_reward_func": 0.0,463 "rewards/strict_format_reward_func": 0.0,464 "rewards/xmlcount_reward_func": 1.062000036239624,465 "step": 48466 },467 {468 "completion_length": 195.875,469 "epoch": 1.0638297872340425,470 "grad_norm": 1.4081065654754639,471 "kl": 0.2666255570948124,472 "learning_rate": 3.902967663405956e-07,473 "loss": 0.0011,474 "reward": 4.544254958629608,475 "reward_std": 1.202682077884674,476 "rewards/concensus_correctness_reward_func": 1.111749991774559,477 "rewards/consensus_reward_func": 1.25,478 "rewards/cumulative_reward_2": 0.0,479 "rewards/final_correctness_reward_func": 0.25,480 "rewards/question_recreation_reward_func": 0.7380048930644989,481 "rewards/soft_format_reward_func": 0.0,482 "rewards/strict_format_reward_func": 0.125,483 "rewards/xmlcount_reward_func": 1.0695000290870667,484 "step": 50485 },486 {487 "completion_length": 238.0,488 "epoch": 1.1063829787234043,489 "grad_norm": 0.6789206862449646,490 "kl": 0.24068081937730312,491 "learning_rate": 3.8120145626980015e-07,492 "loss": 0.0014,493 "reward": 3.725111424922943,494 "reward_std": 1.6401557570197838,495 "rewards/concensus_correctness_reward_func": 0.846000000834465,496 "rewards/consensus_reward_func": 1.25,497 "rewards/cumulative_reward_2": 0.0,498 "rewards/final_correctness_reward_func": 0.0,499 "rewards/question_recreation_reward_func": 0.7861113995313644,500 "rewards/soft_format_reward_func": 0.0,501 "rewards/strict_format_reward_func": 0.0,502 "rewards/xmlcount_reward_func": 0.8430000022053719,503 "step": 52504 },505 {506 "completion_length": 198.125,507 "epoch": 1.148936170212766,508 "grad_norm": 1.2018474340438843,509 "kl": 0.48405691236257553,510 "learning_rate": 3.718598291738298e-07,511 "loss": 0.0019,512 "reward": 2.5495277047157288,513 "reward_std": 1.9529231721535325,514 "rewards/concensus_correctness_reward_func": 0.5694999992847443,515 "rewards/consensus_reward_func": 0.5,516 "rewards/cumulative_reward_2": 0.0,517 "rewards/final_correctness_reward_func": 0.0,518 "rewards/question_recreation_reward_func": 0.512527734041214,519 "rewards/soft_format_reward_func": 0.0,520 "rewards/strict_format_reward_func": 0.0,521 "rewards/xmlcount_reward_func": 0.9675000160932541,522 "step": 54523 },524 {525 "completion_length": 186.25,526 "epoch": 1.1914893617021276,527 "grad_norm": 3.2194740772247314,528 "kl": 0.6150090470910072,529 "learning_rate": 3.622894229814698e-07,530 "loss": 0.0025,531 "reward": 2.526830554008484,532 "reward_std": 1.5739968866109848,533 "rewards/concensus_correctness_reward_func": 0.21899999678134918,534 "rewards/consensus_reward_func": 0.75,535 "rewards/cumulative_reward_2": 0.0,536 "rewards/final_correctness_reward_func": 0.0,537 "rewards/question_recreation_reward_func": 0.44095548056066036,538 "rewards/soft_format_reward_func": 0.0,539 "rewards/strict_format_reward_func": 0.0,540 "rewards/xmlcount_reward_func": 1.116875022649765,541 "step": 56542 },543 {544 "completion_length": 188.375,545 "epoch": 1.2340425531914894,546 "grad_norm": 1.4209983348846436,547 "kl": 0.30609719827771187,548 "learning_rate": 3.52508205130354e-07,549 "loss": 0.0012,550 "reward": 3.698073595762253,551 "reward_std": 0.8687592293135822,552 "rewards/concensus_correctness_reward_func": 0.23899999260902405,553 "rewards/consensus_reward_func": 1.25,554 "rewards/cumulative_reward_2": 0.0,555 "rewards/final_correctness_reward_func": 0.5,556 "rewards/question_recreation_reward_func": 0.6270735263824463,557 "rewards/soft_format_reward_func": 0.0,558 "rewards/strict_format_reward_func": 0.0,559 "rewards/xmlcount_reward_func": 1.08200004696846,560 "step": 58561 },562 {563 "completion_length": 222.875,564 "epoch": 1.2765957446808511,565 "grad_norm": 0.7521047592163086,566 "kl": 0.27088620513677597,567 "learning_rate": 3.4253453883497864e-07,568 "loss": 0.0011,569 "reward": 3.561430275440216,570 "reward_std": 2.1578689590096474,571 "rewards/concensus_correctness_reward_func": 0.6794999986886978,572 "rewards/consensus_reward_func": 1.0,573 "rewards/cumulative_reward_2": 0.0,574 "rewards/final_correctness_reward_func": 0.25,575 "rewards/question_recreation_reward_func": 0.6158051937818527,576 "rewards/soft_format_reward_func": 0.0,577 "rewards/strict_format_reward_func": 0.125,578 "rewards/xmlcount_reward_func": 0.8911250233650208,579 "step": 60580 },581 {582 "completion_length": 224.625,583 "epoch": 1.3191489361702127,584 "grad_norm": 0.9290811419487,585 "kl": 0.19351617619395256,586 "learning_rate": 3.323871486116851e-07,587 "loss": 0.0008,588 "reward": 2.8860513865947723,589 "reward_std": 1.1011781636625528,590 "rewards/concensus_correctness_reward_func": 1.113500028848648,591 "rewards/consensus_reward_func": 0.5,592 "rewards/cumulative_reward_2": 0.0,593 "rewards/final_correctness_reward_func": 0.0,594 "rewards/question_recreation_reward_func": 0.4590512737631798,595 "rewards/soft_format_reward_func": 0.0,596 "rewards/strict_format_reward_func": 0.0,597 "rewards/xmlcount_reward_func": 0.8135000318288803,598 "step": 62599 },600 {601 "completion_length": 200.5,602 "epoch": 1.3617021276595744,603 "grad_norm": 0.8877844214439392,604 "kl": 0.25572171062231064,605 "learning_rate": 3.220850851253377e-07,606 "loss": 0.001,607 "reward": 2.939279019832611,608 "reward_std": 1.4919100254774094,609 "rewards/concensus_correctness_reward_func": 0.5530000030994415,610 "rewards/consensus_reward_func": 0.75,611 "rewards/cumulative_reward_2": 0.0,612 "rewards/final_correctness_reward_func": 0.0,613 "rewards/question_recreation_reward_func": 0.5187790626659989,614 "rewards/soft_format_reward_func": 0.0,615 "rewards/strict_format_reward_func": 0.1875,616 "rewards/xmlcount_reward_func": 0.9300000071525574,617 "step": 64618 },619 {620 "completion_length": 186.25,621 "epoch": 1.4042553191489362,622 "grad_norm": 0.8042911291122437,623 "kl": 0.9062416031956673,624 "learning_rate": 3.1164768942369053e-07,625 "loss": 0.0036,626 "reward": 3.1877584904432297,627 "reward_std": 0.1414917097426951,628 "rewards/concensus_correctness_reward_func": 0.45774999260902405,629 "rewards/consensus_reward_func": 1.0,630 "rewards/cumulative_reward_2": 0.0,631 "rewards/final_correctness_reward_func": 0.0,632 "rewards/question_recreation_reward_func": 0.725758507847786,633 "rewards/soft_format_reward_func": 0.0,634 "rewards/strict_format_reward_func": 0.0,635 "rewards/xmlcount_reward_func": 1.004250019788742,636 "step": 66637 },638 {639 "completion_length": 232.0,640 "epoch": 1.4468085106382977,641 "grad_norm": 1.1032546758651733,642 "kl": 0.3480935860425234,643 "learning_rate": 3.010945566265912e-07,644 "loss": 0.0014,645 "reward": 3.600020945072174,646 "reward_std": 0.7375449845567346,647 "rewards/concensus_correctness_reward_func": 0.6459999978542328,648 "rewards/consensus_reward_func": 1.25,649 "rewards/cumulative_reward_2": 0.0,650 "rewards/final_correctness_reward_func": 0.0,651 "rewards/question_recreation_reward_func": 0.7747710943222046,652 "rewards/soft_format_reward_func": 0.0,653 "rewards/strict_format_reward_func": 0.0625,654 "rewards/xmlcount_reward_func": 0.8667500168085098,655 "step": 68656 },657 {658 "completion_length": 165.625,659 "epoch": 1.4893617021276595,660 "grad_norm": 1.185799241065979,661 "kl": 0.5367052778601646,662 "learning_rate": 2.9044549913819124e-07,663 "loss": 0.0021,664 "reward": 4.451367974281311,665 "reward_std": 1.5575858876109123,666 "rewards/concensus_correctness_reward_func": 0.9684999883174896,667 "rewards/consensus_reward_func": 1.0,668 "rewards/cumulative_reward_2": 0.0,669 "rewards/final_correctness_reward_func": 0.5,670 "rewards/question_recreation_reward_func": 0.8927430063486099,671 "rewards/soft_format_reward_func": 0.0,672 "rewards/strict_format_reward_func": 0.0,673 "rewards/xmlcount_reward_func": 1.0901249945163727,674 "step": 70675 },676 {677 "completion_length": 256.0,678 "epoch": 1.5319148936170213,679 "grad_norm": 0.677112877368927,680 "kl": 0.17708168923854828,681 "learning_rate": 2.797205094512266e-07,682 "loss": 0.0007,683 "reward": 2.5530901551246643,684 "reward_std": 0.9877449879422784,685 "rewards/concensus_correctness_reward_func": 0.3920000046491623,686 "rewards/consensus_reward_func": 0.75,687 "rewards/cumulative_reward_2": 0.0,688 "rewards/final_correctness_reward_func": 0.0,689 "rewards/question_recreation_reward_func": 0.6447152122855186,690 "rewards/soft_format_reward_func": 0.0,691 "rewards/strict_format_reward_func": 0.0,692 "rewards/xmlcount_reward_func": 0.7663750052452087,693 "step": 72694 },695 {696 "completion_length": 224.875,697 "epoch": 1.574468085106383,698 "grad_norm": 1.040575623512268,699 "kl": 0.20721757039427757,700 "learning_rate": 2.6893972261320264e-07,701 "loss": 0.0008,702 "reward": 2.9619136601686478,703 "reward_std": 0.3513062624260783,704 "rewards/concensus_correctness_reward_func": 0.617000013589859,705 "rewards/consensus_reward_func": 1.0,706 "rewards/cumulative_reward_2": 0.0,707 "rewards/final_correctness_reward_func": 0.0,708 "rewards/question_recreation_reward_func": 0.6737885847687721,709 "rewards/soft_format_reward_func": 0.0,710 "rewards/strict_format_reward_func": 0.0,711 "rewards/xmlcount_reward_func": 0.6711249947547913,712 "step": 74713 },714 {715 "completion_length": 186.5,716 "epoch": 1.6170212765957448,717 "grad_norm": 1.4678940773010254,718 "kl": 0.6414169780910015,719 "learning_rate": 2.5812337842494516e-07,720 "loss": 0.0026,721 "reward": 6.481174528598785,722 "reward_std": 0.3154863528907299,723 "rewards/concensus_correctness_reward_func": 2.234499990940094,724 "rewards/consensus_reward_func": 1.5,725 "rewards/cumulative_reward_2": 0.0,726 "rewards/final_correctness_reward_func": 1.0,727 "rewards/question_recreation_reward_func": 0.7511746063828468,728 "rewards/soft_format_reward_func": 0.0,729 "rewards/strict_format_reward_func": 0.0625,730 "rewards/xmlcount_reward_func": 0.9330000206828117,731 "step": 76732 },733 {734 "completion_length": 178.0,735 "epoch": 1.6595744680851063,736 "grad_norm": 6.9644341468811035,737 "kl": 1.063752457499504,738 "learning_rate": 2.4729178344249006e-07,739 "loss": 0.0043,740 "reward": 3.3275441229343414,741 "reward_std": 1.0135727748274803,742 "rewards/concensus_correctness_reward_func": 0.5789999961853027,743 "rewards/consensus_reward_func": 1.5,744 "rewards/cumulative_reward_2": 0.0,745 "rewards/final_correctness_reward_func": 0.0,746 "rewards/question_recreation_reward_func": 0.3645440088585019,747 "rewards/soft_format_reward_func": 0.0,748 "rewards/strict_format_reward_func": 0.0,749 "rewards/xmlcount_reward_func": 0.8840000033378601,750 "step": 78751 },752 {753 "completion_length": 231.25,754 "epoch": 1.702127659574468,755 "grad_norm": 0.8000576496124268,756 "kl": 0.22131185978651047,757 "learning_rate": 2.3646527285364563e-07,758 "loss": 0.0009,759 "reward": 2.724147319793701,760 "reward_std": 0.31289951340295374,761 "rewards/concensus_correctness_reward_func": 0.7064999938011169,762 "rewards/consensus_reward_func": 0.5,763 "rewards/cumulative_reward_2": 0.0,764 "rewards/final_correctness_reward_func": 0.0,765 "rewards/question_recreation_reward_func": 0.46139733120799065,766 "rewards/soft_format_reward_func": 0.0,767 "rewards/strict_format_reward_func": 0.0,768 "rewards/xmlcount_reward_func": 1.0562500059604645,769 "step": 80770 },771 {772 "completion_length": 235.625,773 "epoch": 1.7446808510638299,774 "grad_norm": 0.6098948121070862,775 "kl": 0.19879772141575813,776 "learning_rate": 2.256641723008026e-07,777 "loss": 0.0008,778 "reward": 2.813126176595688,779 "reward_std": 0.6887367907911539,780 "rewards/concensus_correctness_reward_func": 0.1274999976158142,781 "rewards/consensus_reward_func": 1.25,782 "rewards/cumulative_reward_2": 0.0,783 "rewards/final_correctness_reward_func": 0.0,784 "rewards/question_recreation_reward_func": 0.5621262565255165,785 "rewards/soft_format_reward_func": 0.0,786 "rewards/strict_format_reward_func": 0.0625,787 "rewards/xmlcount_reward_func": 0.8110000044107437,788 "step": 82789 },790 {791 "completion_length": 208.875,792 "epoch": 1.7872340425531914,793 "grad_norm": 1.535791039466858,794 "kl": 0.32678982987999916,795 "learning_rate": 2.1490875972166393e-07,796 "loss": 0.0013,797 "reward": 2.6927858889102936,798 "reward_std": 1.590567909181118,799 "rewards/concensus_correctness_reward_func": 0.5122500061988831,800 "rewards/consensus_reward_func": 0.5,801 "rewards/cumulative_reward_2": 0.0,802 "rewards/final_correctness_reward_func": 0.0,803 "rewards/question_recreation_reward_func": 0.6962859183549881,804 "rewards/soft_format_reward_func": 0.0,805 "rewards/strict_format_reward_func": 0.0625,806 "rewards/xmlcount_reward_func": 0.9217500239610672,807 "step": 84808 },809 {810 "completion_length": 188.25,811 "epoch": 1.8297872340425532,812 "grad_norm": 1.1909072399139404,813 "kl": 2.7168994322419167,814 "learning_rate": 2.0421922727953595e-07,815 "loss": 0.0109,816 "reward": 2.768003761768341,817 "reward_std": 2.136858344078064,818 "rewards/concensus_correctness_reward_func": 0.45250000059604645,819 "rewards/consensus_reward_func": 0.75,820 "rewards/cumulative_reward_2": 0.0,821 "rewards/final_correctness_reward_func": 0.0,822 "rewards/question_recreation_reward_func": 0.49225375801324844,823 "rewards/soft_format_reward_func": 0.0,824 "rewards/strict_format_reward_func": 0.0,825 "rewards/xmlcount_reward_func": 1.0732500553131104,826 "step": 86827 },828 {829 "completion_length": 218.75,830 "epoch": 1.872340425531915,831 "grad_norm": 0.7140145301818848,832 "kl": 0.3512803502380848,833 "learning_rate": 1.9361564345465145e-07,834 "loss": 0.0014,835 "reward": 3.050942584872246,836 "reward_std": 0.7234448418021202,837 "rewards/concensus_correctness_reward_func": 0.49025000631809235,838 "rewards/consensus_reward_func": 1.0,839 "rewards/cumulative_reward_2": 0.0,840 "rewards/final_correctness_reward_func": 0.0,841 "rewards/question_recreation_reward_func": 0.7618174850940704,842 "rewards/soft_format_reward_func": 0.0,843 "rewards/strict_format_reward_func": 0.0,844 "rewards/xmlcount_reward_func": 0.7988750338554382,845 "step": 88846 },847 {848 "completion_length": 189.625,849 "epoch": 1.9148936170212765,850 "grad_norm": 1.2534366846084595,851 "kl": 0.5482017546892166,852 "learning_rate": 1.8311791536769483e-07,853 "loss": 0.0022,854 "reward": 4.520209968090057,855 "reward_std": 0.7068406715989113,856 "rewards/concensus_correctness_reward_func": 1.108000010251999,857 "rewards/consensus_reward_func": 1.5,858 "rewards/cumulative_reward_2": 0.0,859 "rewards/final_correctness_reward_func": 0.25,860 "rewards/question_recreation_reward_func": 0.43083491176366806,861 "rewards/soft_format_reward_func": 0.0,862 "rewards/strict_format_reward_func": 0.1875,863 "rewards/xmlcount_reward_func": 1.0438750088214874,864 "step": 90865 },866 {867 "completion_length": 179.125,868 "epoch": 1.9574468085106385,869 "grad_norm": 2.2211098670959473,870 "kl": 0.26672671362757683,871 "learning_rate": 1.7274575140626315e-07,872 "loss": 0.0011,873 "reward": 3.006656587123871,874 "reward_std": 1.1380279939621687,875 "rewards/concensus_correctness_reward_func": 0.2395000010728836,876 "rewards/consensus_reward_func": 1.25,877 "rewards/cumulative_reward_2": 0.0,878 "rewards/final_correctness_reward_func": 0.0,879 "rewards/question_recreation_reward_func": 0.3142815865576267,880 "rewards/soft_format_reward_func": 0.0,881 "rewards/strict_format_reward_func": 0.125,882 "rewards/xmlcount_reward_func": 1.077875018119812,883 "step": 92884 },885 {886 "completion_length": 228.625,887 "epoch": 2.0,888 "grad_norm": 0.9149807095527649,889 "kl": 0.3158671669661999,890 "learning_rate": 1.6251862422442788e-07,891 "loss": 0.0013,892 "reward": 3.2071974873542786,893 "reward_std": 1.285196453332901,894 "rewards/concensus_correctness_reward_func": 0.5254999995231628,895 "rewards/consensus_reward_func": 1.0,896 "rewards/cumulative_reward_2": 0.0,897 "rewards/final_correctness_reward_func": 0.0,898 "rewards/question_recreation_reward_func": 0.6998224258422852,899 "rewards/soft_format_reward_func": 0.0,900 "rewards/strict_format_reward_func": 0.0625,901 "rewards/xmlcount_reward_func": 0.919375017285347,902 "step": 94903 },904 {905 "completion_length": 220.5,906 "epoch": 2.0425531914893615,907 "grad_norm": 1.1787397861480713,908 "kl": 0.3613498732447624,909 "learning_rate": 1.5245573418486135e-07,910 "loss": 0.0014,911 "reward": 2.6240314543247223,912 "reward_std": 1.41940873907879,913 "rewards/concensus_correctness_reward_func": 0.03125,914 "rewards/consensus_reward_func": 0.75,915 "rewards/cumulative_reward_2": 0.0,916 "rewards/final_correctness_reward_func": 0.0,917 "rewards/question_recreation_reward_func": 0.6557814925909042,918 "rewards/soft_format_reward_func": 0.0,919 "rewards/strict_format_reward_func": 0.125,920 "rewards/xmlcount_reward_func": 1.062000036239624,921 "step": 96922 },923 {924 "completion_length": 213.625,925 "epoch": 2.0851063829787235,926 "grad_norm": 0.8779793977737427,927 "kl": 0.26281201280653477,928 "learning_rate": 1.4257597331216208e-07,929 "loss": 0.0011,930 "reward": 3.4714860320091248,931 "reward_std": 0.6732950583100319,932 "rewards/concensus_correctness_reward_func": 0.9514999985694885,933 "rewards/consensus_reward_func": 0.75,934 "rewards/cumulative_reward_2": 0.0,935 "rewards/final_correctness_reward_func": 0.0,936 "rewards/question_recreation_reward_func": 0.7794859036803246,937 "rewards/soft_format_reward_func": 0.0,938 "rewards/strict_format_reward_func": 0.0625,939 "rewards/xmlcount_reward_func": 0.9280000030994415,940 "step": 98941 },942 {943 "completion_length": 176.875,944 "epoch": 2.127659574468085,945 "grad_norm": 1.3312575817108154,946 "kl": 0.26110076159238815,947 "learning_rate": 1.328978898250525e-07,948 "loss": 0.001,949 "reward": 3.544356942176819,950 "reward_std": 1.1210243813693523,951 "rewards/concensus_correctness_reward_func": 0.45900000631809235,952 "rewards/consensus_reward_func": 1.25,953 "rewards/cumulative_reward_2": 0.0,954 "rewards/final_correctness_reward_func": 0.0,955 "rewards/question_recreation_reward_func": 0.7318568676710129,956 "rewards/soft_format_reward_func": 0.0,957 "rewards/strict_format_reward_func": 0.0,958 "rewards/xmlcount_reward_func": 1.1035000085830688,959 "step": 100960 },961 {962 "completion_length": 197.0,963 "epoch": 2.1702127659574466,964 "grad_norm": 1.4065243005752563,965 "kl": 1.261439360678196,966 "learning_rate": 1.234396533140365e-07,967 "loss": 0.005,968 "reward": 4.3151280879974365,969 "reward_std": 1.6089704409241676,970 "rewards/concensus_correctness_reward_func": 0.9122499972581863,971 "rewards/consensus_reward_func": 1.5,972 "rewards/cumulative_reward_2": 0.0,973 "rewards/final_correctness_reward_func": 0.0,974 "rewards/question_recreation_reward_func": 0.632128156721592,975 "rewards/soft_format_reward_func": 0.0,976 "rewards/strict_format_reward_func": 0.1875,977 "rewards/xmlcount_reward_func": 1.0832499861717224,978 "step": 102979 },980 {981 "completion_length": 225.25,982 "epoch": 2.2127659574468086,983 "grad_norm": 0.9641211628913879,984 "kl": 0.2811318561434746,985 "learning_rate": 1.1421902062989178e-07,986 "loss": 0.0011,987 "reward": 4.32602596282959,988 "reward_std": 0.7468478474766016,989 "rewards/concensus_correctness_reward_func": 0.8410000279545784,990 "rewards/consensus_reward_func": 1.25,991 "rewards/cumulative_reward_2": 0.0,992 "rewards/final_correctness_reward_func": 0.25,993 "rewards/question_recreation_reward_func": 0.8362759798765182,994 "rewards/soft_format_reward_func": 0.0,995 "rewards/strict_format_reward_func": 0.0625,996 "rewards/xmlcount_reward_func": 1.0862500220537186,997 "step": 104998 },999 {1000 "completion_length": 221.75,1001 "epoch": 2.25531914893617,1002 "grad_norm": 1.0830140113830566,1003 "kl": 0.3253920152783394,1004 "learning_rate": 1.0525330254703788e-07,1005 "loss": 0.0013,1006 "reward": 4.338386833667755,1007 "reward_std": 1.4221147149801254,1008 "rewards/concensus_correctness_reward_func": 1.3924999982118607,1009 "rewards/consensus_reward_func": 0.75,1010 "rewards/cumulative_reward_2": 0.0,1011 "rewards/final_correctness_reward_func": 0.25,1012 "rewards/question_recreation_reward_func": 0.7605118304491043,1013 "rewards/soft_format_reward_func": 0.0,1014 "rewards/strict_format_reward_func": 0.1875,1015 "rewards/xmlcount_reward_func": 0.9978750050067902,1016 "step": 1061017 },1018 {1019 "completion_length": 185.25,1020 "epoch": 2.297872340425532,1021 "grad_norm": 1.8043159246444702,1022 "kl": 0.3243243135511875,1023 "learning_rate": 9.655933126436563e-08,1024 "loss": 0.0013,1025 "reward": 4.752579569816589,1026 "reward_std": 1.0812932699918747,1027 "rewards/concensus_correctness_reward_func": 1.5809999853372574,1028 "rewards/consensus_reward_func": 1.75,1029 "rewards/cumulative_reward_2": 0.0,1030 "rewards/final_correctness_reward_func": 0.0,1031 "rewards/question_recreation_reward_func": 0.436579804867506,1032 "rewards/soft_format_reward_func": 0.0,1033 "rewards/strict_format_reward_func": 0.0,1034 "rewards/xmlcount_reward_func": 0.9850000143051147,1035 "step": 1081036 },1037 {1038 "completion_length": 227.625,1039 "epoch": 2.3404255319148937,1040 "grad_norm": 1.0443482398986816,1041 "kl": 0.18171441182494164,1042 "learning_rate": 8.81534288045431e-08,1043 "loss": 0.0007,1044 "reward": 3.4098499715328217,1045 "reward_std": 0.5559223601594567,1046 "rewards/concensus_correctness_reward_func": 0.4780000150203705,1047 "rewards/consensus_reward_func": 1.25,1048 "rewards/cumulative_reward_2": 0.0,1049 "rewards/final_correctness_reward_func": 0.0,1050 "rewards/question_recreation_reward_func": 0.6712251529097557,1051 "rewards/soft_format_reward_func": 0.0,1052 "rewards/strict_format_reward_func": 0.0625,1053 "rewards/xmlcount_reward_func": 0.9481250047683716,1054 "step": 1101055 },1056 {1057 "completion_length": 204.125,1058 "epoch": 2.382978723404255,1059 "grad_norm": 1.0095102787017822,1060 "kl": 0.33378131687641144,1061 "learning_rate": 8.005137637112302e-08,1062 "loss": 0.0013,1063 "reward": 4.048836588859558,1064 "reward_std": 2.0566222071647644,1065 "rewards/concensus_correctness_reward_func": 0.568249985575676,1066 "rewards/consensus_reward_func": 1.0,1067 "rewards/cumulative_reward_2": 0.0,1068 "rewards/final_correctness_reward_func": 0.75,1069 "rewards/question_recreation_reward_func": 0.6142115592956543,1070 "rewards/soft_format_reward_func": 0.0,1071 "rewards/strict_format_reward_func": 0.0,1072 "rewards/xmlcount_reward_func": 1.116375058889389,1073 "step": 1121074 },1075 {1076 "completion_length": 228.5,1077 "epoch": 2.425531914893617,1078 "grad_norm": 1.1271754503250122,1079 "kl": 0.2501847632229328,1080 "learning_rate": 7.226838472098237e-08,1081 "loss": 0.001,1082 "reward": 2.398908704519272,1083 "reward_std": 0.6907656379044056,1084 "rewards/concensus_correctness_reward_func": 0.46924999356269836,1085 "rewards/consensus_reward_func": 0.5,1086 "rewards/cumulative_reward_2": 0.0,1087 "rewards/final_correctness_reward_func": 0.0,1088 "rewards/question_recreation_reward_func": 0.6909087672829628,1089 "rewards/soft_format_reward_func": 0.0,1090 "rewards/strict_format_reward_func": 0.0625,1091 "rewards/xmlcount_reward_func": 0.6762499958276749,1092 "step": 1141093 },1094 {1095 "completion_length": 189.625,1096 "epoch": 2.4680851063829787,1097 "grad_norm": 1.1995269060134888,1098 "kl": 0.268869549036026,1099 "learning_rate": 6.481906560771524e-08,1100 "loss": 0.0011,1101 "reward": 2.9432379603385925,1102 "reward_std": 1.5781491622328758,1103 "rewards/concensus_correctness_reward_func": 0.2199999988079071,1104 "rewards/consensus_reward_func": 0.75,1105 "rewards/cumulative_reward_2": 0.0,1106 "rewards/final_correctness_reward_func": 0.0,1107 "rewards/question_recreation_reward_func": 0.7009878791868687,1108 "rewards/soft_format_reward_func": 0.0,1109 "rewards/strict_format_reward_func": 0.125,1110 "rewards/xmlcount_reward_func": 1.14724999666214,1111 "step": 1161112 },1113 {1114 "completion_length": 219.375,1115 "epoch": 2.5106382978723403,1116 "grad_norm": 0.8651387691497803,1117 "kl": 0.29725453071296215,1118 "learning_rate": 5.771740434959277e-08,1119 "loss": 0.0012,1120 "reward": 2.1470000594854355,1121 "reward_std": 0.8396826535463333,1122 "rewards/concensus_correctness_reward_func": 0.03125,1123 "rewards/consensus_reward_func": 0.75,1124 "rewards/cumulative_reward_2": 0.0,1125 "rewards/final_correctness_reward_func": 0.0,1126 "rewards/question_recreation_reward_func": 0.4090001229196787,1127 "rewards/soft_format_reward_func": 0.0,1128 "rewards/strict_format_reward_func": 0.0625,1129 "rewards/xmlcount_reward_func": 0.8942500054836273,1130 "step": 1181131 },1132 {1133 "completion_length": 204.5,1134 "epoch": 2.5531914893617023,1135 "grad_norm": 1.0199799537658691,1136 "kl": 0.4174264371395111,1137 "learning_rate": 5.097673357358906e-08,1138 "loss": 0.0017,1139 "reward": 4.208442598581314,1140 "reward_std": 0.3032263843342662,1141 "rewards/concensus_correctness_reward_func": 1.181750014424324,1142 "rewards/consensus_reward_func": 1.5,1143 "rewards/cumulative_reward_2": 0.0,1144 "rewards/final_correctness_reward_func": 0.0,1145 "rewards/question_recreation_reward_func": 0.6099426299333572,1146 "rewards/soft_format_reward_func": 0.0,1147 "rewards/strict_format_reward_func": 0.0,1148 "rewards/xmlcount_reward_func": 0.9167499989271164,1149 "step": 1201150 },1151 {1152 "completion_length": 153.125,1153 "epoch": 2.595744680851064,1154 "grad_norm": 1.1299829483032227,1155 "kl": 0.36897996813058853,1156 "learning_rate": 4.460970818476717e-08,1157 "loss": 0.0015,1158 "reward": 3.318384289741516,1159 "reward_std": 0.43094088579528034,1160 "rewards/concensus_correctness_reward_func": 1.1305000185966492,1161 "rewards/consensus_reward_func": 0.5,1162 "rewards/cumulative_reward_2": 0.0,1163 "rewards/final_correctness_reward_func": 0.0,1164 "rewards/question_recreation_reward_func": 0.3508843518793583,1165 "rewards/soft_format_reward_func": 0.0,1166 "rewards/strict_format_reward_func": 0.125,1167 "rewards/xmlcount_reward_func": 1.2119999825954437,1168 "step": 1221169 },1170 {1171 "completion_length": 177.0,1172 "epoch": 2.6382978723404253,1173 "grad_norm": 1.260545253753662,1174 "kl": 0.3712556064128876,1175 "learning_rate": 3.8628281608017065e-08,1176 "loss": 0.0015,1177 "reward": 3.878890633583069,1178 "reward_std": 2.4627570509910583,1179 "rewards/concensus_correctness_reward_func": 1.178000032901764,1180 "rewards/consensus_reward_func": 1.0,1181 "rewards/cumulative_reward_2": 0.0,1182 "rewards/final_correctness_reward_func": 0.0,1183 "rewards/question_recreation_reward_func": 0.5733906328678131,1184 "rewards/soft_format_reward_func": 0.0,1185 "rewards/strict_format_reward_func": 0.0,1186 "rewards/xmlcount_reward_func": 1.1275000274181366,1187 "step": 1241188 },1189 {1190 "completion_length": 218.25,1191 "epoch": 2.6808510638297873,1192 "grad_norm": 1.5606447458267212,1193 "kl": 0.2205050252377987,1194 "learning_rate": 3.304368334674965e-08,1195 "loss": 0.0009,1196 "reward": 4.398641467094421,1197 "reward_std": 1.204378828406334,1198 "rewards/concensus_correctness_reward_func": 0.6464999914169312,1199 "rewards/consensus_reward_func": 1.5,1200 "rewards/cumulative_reward_2": 0.0,