smartrichard/X-R1-lora-7500
08
1{2 "best_metric": null,3 "best_model_checkpoint": null,4 "epoch": 2.997333333333333,5 "eval_steps": 10,6 "global_step": 2811,7 "is_hyper_param_search": false,8 "is_local_process_zero": true,9 "is_world_process_zero": true,10 "log_history": [11 {12 "completion_length": 121.971875,13 "epoch": 0.010666666666666666,14 "grad_norm": 0.156667098402977,15 "kl": 2.0313262939453126e-05,16 "learning_rate": 1.0638297872340426e-05,17 "loss": 0.001,18 "reward": 0.0125,19 "reward_std": 0.025,20 "rewards/accuracy_reward": 0.009375,21 "rewards/format_reward": 0.003125,22 "step": 1023 },24 {25 "completion_length": 122.521875,26 "epoch": 0.021333333333333333,27 "grad_norm": 0.0012713409960269928,28 "kl": 0.00021836161613464355,29 "learning_rate": 2.1276595744680852e-05,30 "loss": 0.0051,31 "reward": 0.015625,32 "reward_std": 0.025966878235340118,33 "rewards/accuracy_reward": 0.015625,34 "rewards/format_reward": 0.0,35 "step": 2036 },37 {38 "completion_length": 117.5125,39 "epoch": 0.032,40 "grad_norm": 0.002654253738000989,41 "kl": 0.0003068089485168457,42 "learning_rate": 3.1914893617021275e-05,43 "loss": -0.0002,44 "reward": 0.00625,45 "reward_std": 0.007216878235340118,46 "rewards/accuracy_reward": 0.00625,47 "rewards/format_reward": 0.0,48 "step": 3049 },50 {51 "completion_length": 118.871875,52 "epoch": 0.042666666666666665,53 "grad_norm": 0.00353299081325531,54 "kl": 0.000412750244140625,55 "learning_rate": 4.2553191489361704e-05,56 "loss": 0.0055,57 "reward": 0.009375,58 "reward_std": 0.01875,59 "rewards/accuracy_reward": 0.00625,60 "rewards/format_reward": 0.003125,61 "step": 4062 },63 {64 "completion_length": 121.046875,65 "epoch": 0.05333333333333334,66 "grad_norm": 0.003619612194597721,67 "kl": 0.0004070043563842773,68 "learning_rate": 5.319148936170213e-05,69 "loss": 0.0,70 "reward": 0.0,71 "reward_std": 0.0,72 "rewards/accuracy_reward": 0.0,73 "rewards/format_reward": 0.0,74 "step": 5075 },76 {77 "completion_length": 119.4375,78 "epoch": 0.064,79 "grad_norm": 0.11174867302179337,80 "kl": 0.00045168399810791016,81 "learning_rate": 6.382978723404255e-05,82 "loss": 0.0064,83 "reward": 0.01875,84 "reward_std": 0.0375,85 "rewards/accuracy_reward": 0.015625,86 "rewards/format_reward": 0.003125,87 "step": 6088 },89 {90 "completion_length": 119.05625,91 "epoch": 0.07466666666666667,92 "grad_norm": 0.006828859448432922,93 "kl": 0.0011888980865478516,94 "learning_rate": 7.446808510638297e-05,95 "loss": 0.0012,96 "reward": 0.0125,97 "reward_std": 0.025,98 "rewards/accuracy_reward": 0.0125,99 "rewards/format_reward": 0.0,100 "step": 70101 },102 {103 "completion_length": 120.28125,104 "epoch": 0.08533333333333333,105 "grad_norm": 0.0064537739381194115,106 "kl": 0.0019659996032714844,107 "learning_rate": 8.510638297872341e-05,108 "loss": 0.0028,109 "reward": 0.0125,110 "reward_std": 0.025,111 "rewards/accuracy_reward": 0.0125,112 "rewards/format_reward": 0.0,113 "step": 80114 },115 {116 "completion_length": 117.559375,117 "epoch": 0.096,118 "grad_norm": 0.09068689495325089,119 "kl": 0.0025023460388183595,120 "learning_rate": 9.574468085106382e-05,121 "loss": 0.003,122 "reward": 0.021875,123 "reward_std": 0.04375,124 "rewards/accuracy_reward": 0.01875,125 "rewards/format_reward": 0.003125,126 "step": 90127 },128 {129 "completion_length": 117.68125,130 "epoch": 0.10666666666666667,131 "grad_norm": 0.16541939973831177,132 "kl": 0.00291900634765625,133 "learning_rate": 0.00010638297872340425,134 "loss": 0.0008,135 "reward": 0.021875,136 "reward_std": 0.03125,137 "rewards/accuracy_reward": 0.021875,138 "rewards/format_reward": 0.0,139 "step": 100140 },141 {142 "completion_length": 116.971875,143 "epoch": 0.11733333333333333,144 "grad_norm": 0.07206544280052185,145 "kl": 0.0038990020751953126,146 "learning_rate": 0.00011702127659574467,147 "loss": 0.0026,148 "reward": 0.015625,149 "reward_std": 0.03125,150 "rewards/accuracy_reward": 0.0125,151 "rewards/format_reward": 0.003125,152 "step": 110153 },154 {155 "completion_length": 114.996875,156 "epoch": 0.128,157 "grad_norm": 0.02286006510257721,158 "kl": 0.007346725463867188,159 "learning_rate": 0.0001276595744680851,160 "loss": 0.0076,161 "reward": 0.025,162 "reward_std": 0.05,163 "rewards/accuracy_reward": 0.015625,164 "rewards/format_reward": 0.009375,165 "step": 120166 },167 {168 "completion_length": 119.315625,169 "epoch": 0.13866666666666666,170 "grad_norm": 0.015629781410098076,171 "kl": 0.008090972900390625,172 "learning_rate": 0.00013829787234042552,173 "loss": 0.0011,174 "reward": 0.009375,175 "reward_std": 0.01875,176 "rewards/accuracy_reward": 0.009375,177 "rewards/format_reward": 0.0,178 "step": 130179 },180 {181 "completion_length": 121.821875,182 "epoch": 0.14933333333333335,183 "grad_norm": 0.15498439967632294,184 "kl": 0.006272506713867187,185 "learning_rate": 0.00014893617021276593,186 "loss": -0.0012,187 "reward": 0.021875,188 "reward_std": 0.03846687823534012,189 "rewards/accuracy_reward": 0.01875,190 "rewards/format_reward": 0.003125,191 "step": 140192 },193 {194 "completion_length": 121.409375,195 "epoch": 0.16,196 "grad_norm": 0.18756870925426483,197 "kl": 0.00465240478515625,198 "learning_rate": 0.00015957446808510637,199 "loss": 0.0012,200 "reward": 0.021875,201 "reward_std": 0.03846687823534012,202 "rewards/accuracy_reward": 0.01875,203 "rewards/format_reward": 0.003125,204 "step": 150205 },206 {207 "completion_length": 118.26875,208 "epoch": 0.17066666666666666,209 "grad_norm": 0.011626984924077988,210 "kl": 0.01092681884765625,211 "learning_rate": 0.00017021276595744682,212 "loss": -0.0011,213 "reward": 0.021875,214 "reward_std": 0.03318375647068024,215 "rewards/accuracy_reward": 0.01875,216 "rewards/format_reward": 0.003125,217 "step": 160218 },219 {220 "completion_length": 119.25,221 "epoch": 0.18133333333333335,222 "grad_norm": 0.00764912273734808,223 "kl": 0.00976104736328125,224 "learning_rate": 0.0001808510638297872,225 "loss": 0.0045,226 "reward": 0.021875,227 "reward_std": 0.04375,228 "rewards/accuracy_reward": 0.021875,229 "rewards/format_reward": 0.0,230 "step": 170231 },232 {233 "completion_length": 115.35,234 "epoch": 0.192,235 "grad_norm": 0.0785018652677536,236 "kl": 0.014077377319335938,237 "learning_rate": 0.00019148936170212765,238 "loss": 0.0037,239 "reward": 0.025,240 "reward_std": 0.04471687823534012,241 "rewards/accuracy_reward": 0.009375,242 "rewards/format_reward": 0.015625,243 "step": 180244 },245 {246 "completion_length": 108.6125,247 "epoch": 0.20266666666666666,248 "grad_norm": 0.13107918202877045,249 "kl": 0.039361572265625,250 "learning_rate": 0.00020212765957446807,251 "loss": 0.0412,252 "reward": 0.11875,253 "reward_std": 0.18907372057437896,254 "rewards/accuracy_reward": 0.021875,255 "rewards/format_reward": 0.096875,256 "step": 190257 },258 {259 "completion_length": 89.915625,260 "epoch": 0.21333333333333335,261 "grad_norm": 0.19012346863746643,262 "kl": 0.08895263671875,263 "learning_rate": 0.0002127659574468085,264 "loss": 0.1321,265 "reward": 0.46875,266 "reward_std": 0.41404569447040557,267 "rewards/accuracy_reward": 0.015625,268 "rewards/format_reward": 0.453125,269 "step": 200270 },271 {272 "completion_length": 47.74375,273 "epoch": 0.224,274 "grad_norm": 0.4668453335762024,275 "kl": 0.26416015625,276 "learning_rate": 0.0002234042553191489,277 "loss": 0.0712,278 "reward": 0.871875,279 "reward_std": 0.19805223047733306,280 "rewards/accuracy_reward": 0.01875,281 "rewards/format_reward": 0.853125,282 "step": 210283 },284 {285 "completion_length": 45.15625,286 "epoch": 0.23466666666666666,287 "grad_norm": 0.21052278578281403,288 "kl": 0.3112213134765625,289 "learning_rate": 0.00023404255319148934,290 "loss": 0.0464,291 "reward": 0.890625,292 "reward_std": 0.11346687823534012,293 "rewards/accuracy_reward": 0.0125,294 "rewards/format_reward": 0.878125,295 "step": 220296 },297 {298 "completion_length": 57.2875,299 "epoch": 0.24533333333333332,300 "grad_norm": 0.16618619859218597,301 "kl": 0.254522705078125,302 "learning_rate": 0.00024468085106382976,303 "loss": 0.0589,304 "reward": 0.834375,305 "reward_std": 0.12261751294136047,306 "rewards/accuracy_reward": 0.0125,307 "rewards/format_reward": 0.821875,308 "step": 230309 },310 {311 "completion_length": 68.153125,312 "epoch": 0.256,313 "grad_norm": 0.17739807069301605,314 "kl": 0.214471435546875,315 "learning_rate": 0.0002553191489361702,316 "loss": 0.1375,317 "reward": 0.659375,318 "reward_std": 0.28527562469244006,319 "rewards/accuracy_reward": 0.009375,320 "rewards/format_reward": 0.65,321 "step": 240322 },323 {324 "completion_length": 52.709375,325 "epoch": 0.26666666666666666,326 "grad_norm": 0.09843996912240982,327 "kl": 0.2847900390625,328 "learning_rate": 0.0002659574468085106,329 "loss": 0.1085,330 "reward": 0.834375,331 "reward_std": 0.290549997985363,332 "rewards/accuracy_reward": 0.034375,333 "rewards/format_reward": 0.8,334 "step": 250335 },336 {337 "completion_length": 51.55625,338 "epoch": 0.2773333333333333,339 "grad_norm": 0.1133696436882019,340 "kl": 0.276953125,341 "learning_rate": 0.00027659574468085103,342 "loss": 0.0437,343 "reward": 0.903125,344 "reward_std": 0.1361730858683586,345 "rewards/accuracy_reward": 0.025,346 "rewards/format_reward": 0.878125,347 "step": 260348 },349 {350 "completion_length": 55.046875,351 "epoch": 0.288,352 "grad_norm": 0.14536090195178986,353 "kl": 0.2501953125,354 "learning_rate": 0.0002872340425531915,355 "loss": 0.0588,356 "reward": 0.878125,357 "reward_std": 0.13846687823534012,358 "rewards/accuracy_reward": 0.00625,359 "rewards/format_reward": 0.871875,360 "step": 270361 },362 {363 "completion_length": 55.853125,364 "epoch": 0.2986666666666667,365 "grad_norm": 0.1799221634864807,366 "kl": 0.3143310546875,367 "learning_rate": 0.00029787234042553186,368 "loss": 0.0609,369 "reward": 0.90625,370 "reward_std": 0.18080126941204072,371 "rewards/accuracy_reward": 0.021875,372 "rewards/format_reward": 0.884375,373 "step": 280374 },375 {376 "completion_length": 59.85,377 "epoch": 0.30933333333333335,378 "grad_norm": 0.10688479989767075,379 "kl": 0.20706787109375,380 "learning_rate": 0.0002999925930442553,381 "loss": 0.0522,382 "reward": 0.815625,383 "reward_std": 0.2959165498614311,384 "rewards/accuracy_reward": 0.065625,385 "rewards/format_reward": 0.75,386 "step": 290387 },388 {389 "completion_length": 64.625,390 "epoch": 0.32,391 "grad_norm": 0.03851361572742462,392 "kl": 0.201220703125,393 "learning_rate": 0.00029996250354024344,394 "loss": 0.0815,395 "reward": 0.8625,396 "reward_std": 0.21301814764738083,397 "rewards/accuracy_reward": 0.0125,398 "rewards/format_reward": 0.85,399 "step": 300400 },401 {402 "completion_length": 57.95,403 "epoch": 0.33066666666666666,404 "grad_norm": 0.23480646312236786,405 "kl": 0.221240234375,406 "learning_rate": 0.0002999092731927958,407 "loss": 0.0292,408 "reward": 0.921875,409 "reward_std": 0.15895397514104842,410 "rewards/accuracy_reward": 0.0375,411 "rewards/format_reward": 0.884375,412 "step": 310413 },414 {415 "completion_length": 64.196875,416 "epoch": 0.3413333333333333,417 "grad_norm": 0.1151675432920456,418 "kl": 0.20123291015625,419 "learning_rate": 0.0002998329102159332,420 "loss": 0.0491,421 "reward": 0.83125,422 "reward_std": 0.19258119761943818,423 "rewards/accuracy_reward": 0.01875,424 "rewards/format_reward": 0.8125,425 "step": 320426 },427 {428 "completion_length": 70.628125,429 "epoch": 0.352,430 "grad_norm": 0.1377689391374588,431 "kl": 0.1906005859375,432 "learning_rate": 0.0002997334263932927,433 "loss": 0.0841,434 "reward": 0.846875,435 "reward_std": 0.21890811175107955,436 "rewards/accuracy_reward": 0.015625,437 "rewards/format_reward": 0.83125,438 "step": 330439 },440 {441 "completion_length": 61.54375,442 "epoch": 0.3626666666666667,443 "grad_norm": 0.0947548896074295,444 "kl": 0.21240234375,445 "learning_rate": 0.0002996108370763087,446 "loss": 0.062,447 "reward": 0.88125,448 "reward_std": 0.13713996410369872,449 "rewards/accuracy_reward": 0.015625,450 "rewards/format_reward": 0.865625,451 "step": 340452 },453 {454 "completion_length": 60.109375,455 "epoch": 0.37333333333333335,456 "grad_norm": 0.14599719643592834,457 "kl": 0.2236083984375,458 "learning_rate": 0.0002994651611818448,459 "loss": 0.0408,460 "reward": 0.928125,461 "reward_std": 0.18282372057437896,462 "rewards/accuracy_reward": 0.028125,463 "rewards/format_reward": 0.9,464 "step": 350465 },466 {467 "completion_length": 62.90625,468 "epoch": 0.384,469 "grad_norm": 0.3738599121570587,470 "kl": 0.2464111328125,471 "learning_rate": 0.00029929642118927394,472 "loss": 0.0753,473 "reward": 0.834375,474 "reward_std": 0.20676814764738083,475 "rewards/accuracy_reward": 0.025,476 "rewards/format_reward": 0.809375,477 "step": 360478 },479 {480 "completion_length": 70.1625,481 "epoch": 0.39466666666666667,482 "grad_norm": 2.8762810230255127,483 "kl": 0.88681640625,484 "learning_rate": 0.00029910464313701013,485 "loss": 0.2053,486 "reward": 0.640625,487 "reward_std": 0.38192625939846037,488 "rewards/accuracy_reward": 0.009375,489 "rewards/format_reward": 0.63125,490 "step": 370491 },492 {493 "completion_length": 43.578125,494 "epoch": 0.4053333333333333,495 "grad_norm": 0.9355350136756897,496 "kl": 2.06865234375,497 "learning_rate": 0.0002988898566184902,498 "loss": 0.2631,499 "reward": 0.725,500 "reward_std": 0.32462068647146225,501 "rewards/accuracy_reward": 0.0,502 "rewards/format_reward": 0.725,503 "step": 380504 },505 {506 "completion_length": 44.19375,507 "epoch": 0.416,508 "grad_norm": 0.709173858165741,509 "kl": 3.47939453125,510 "learning_rate": 0.0002986520947776074,511 "loss": 0.3225,512 "reward": 0.6125,513 "reward_std": 0.3950331017374992,514 "rewards/accuracy_reward": 0.009375,515 "rewards/format_reward": 0.603125,516 "step": 390517 },518 {519 "completion_length": 54.775,520 "epoch": 0.4266666666666667,521 "grad_norm": 0.6549698114395142,522 "kl": 4.3202392578125,523 "learning_rate": 0.0002983913943035968,524 "loss": 0.3808,525 "reward": 0.66875,526 "reward_std": 0.3901100158691406,527 "rewards/accuracy_reward": 0.01875,528 "rewards/format_reward": 0.65,529 "step": 400530 },531 {532 "completion_length": 53.871875,533 "epoch": 0.43733333333333335,534 "grad_norm": 0.01826515607535839,535 "kl": 2.477734375,536 "learning_rate": 0.00029810779542537355,537 "loss": 0.2661,538 "reward": 0.79375,539 "reward_std": 0.22999776750802994,540 "rewards/accuracy_reward": 0.025,541 "rewards/format_reward": 0.76875,542 "step": 410543 },544 {545 "completion_length": 49.434375,546 "epoch": 0.448,547 "grad_norm": 0.5134692192077637,548 "kl": 2.07587890625,549 "learning_rate": 0.0002978013419053255,550 "loss": 0.2091,551 "reward": 0.771875,552 "reward_std": 0.26785253882408144,553 "rewards/accuracy_reward": 0.0,554 "rewards/format_reward": 0.771875,555 "step": 420556 },557 {558 "completion_length": 59.475,559 "epoch": 0.45866666666666667,560 "grad_norm": 0.7835673689842224,561 "kl": 2.516943359375,562 "learning_rate": 0.00029747208103256,563 "loss": 0.2312,564 "reward": 0.740625,565 "reward_std": 0.31220938116312025,566 "rewards/accuracy_reward": 0.0125,567 "rewards/format_reward": 0.728125,568 "step": 430569 },570 {571 "completion_length": 58.815625,572 "epoch": 0.4693333333333333,573 "grad_norm": 0.021143430843949318,574 "kl": 2.1959716796875,575 "learning_rate": 0.0002971200636156068,576 "loss": 0.2386,577 "reward": 0.796875,578 "reward_std": 0.2231356605887413,579 "rewards/accuracy_reward": 0.0,580 "rewards/format_reward": 0.796875,581 "step": 440582 },583 {584 "completion_length": 55.696875,585 "epoch": 0.48,586 "grad_norm": 1.8231980800628662,587 "kl": 2.9314697265625,588 "learning_rate": 0.00029674534397457745,589 "loss": 0.3506,590 "reward": 0.796875,591 "reward_std": 0.2616912335157394,592 "rewards/accuracy_reward": 0.021875,593 "rewards/format_reward": 0.775,594 "step": 450595 },596 {597 "completion_length": 49.778125,598 "epoch": 0.49066666666666664,599 "grad_norm": 0.5252532362937927,600 "kl": 1.47607421875,601 "learning_rate": 0.00029634797993278333,602 "loss": 0.2026,603 "reward": 0.89375,604 "reward_std": 0.11293471753597259,605 "rewards/accuracy_reward": 0.0125,606 "rewards/format_reward": 0.88125,607 "step": 460608 },609 {610 "completion_length": 57.903125,611 "epoch": 0.5013333333333333,612 "grad_norm": 0.10718824714422226,613 "kl": 1.683837890625,614 "learning_rate": 0.000295928032807813,615 "loss": 0.1887,616 "reward": 0.859375,617 "reward_std": 0.1423343911767006,618 "rewards/accuracy_reward": 0.00625,619 "rewards/format_reward": 0.853125,620 "step": 470621 },622 {623 "completion_length": 63.734375,624 "epoch": 0.512,625 "grad_norm": 0.32101932168006897,626 "kl": 2.9671875,627 "learning_rate": 0.00029548556740206994,628 "loss": 0.3254,629 "reward": 0.79375,630 "reward_std": 0.29874250292778015,631 "rewards/accuracy_reward": 0.009375,632 "rewards/format_reward": 0.784375,633 "step": 480634 },635 {636 "completion_length": 66.253125,637 "epoch": 0.5226666666666666,638 "grad_norm": 0.7132259011268616,639 "kl": 2.6101806640625,640 "learning_rate": 0.0002950206519927731,641 "loss": 0.2574,642 "reward": 0.728125,643 "reward_std": 0.3086773693561554,644 "rewards/accuracy_reward": 0.01875,645 "rewards/format_reward": 0.709375,646 "step": 490647 },648 {649 "completion_length": 64.765625,650 "epoch": 0.5333333333333333,651 "grad_norm": 0.7293491959571838,652 "kl": 3.3251220703125,653 "learning_rate": 0.00029453335832142075,654 "loss": 0.3315,655 "reward": 0.75625,656 "reward_std": 0.27030970752239225,657 "rewards/accuracy_reward": 0.009375,658 "rewards/format_reward": 0.746875,659 "step": 500660 },661 {662 "completion_length": 61.140625,663 "epoch": 0.544,664 "grad_norm": 0.4900813400745392,665 "kl": 1.6069091796875,666 "learning_rate": 0.0002940237615827202,667 "loss": 0.162,668 "reward": 0.86875,669 "reward_std": 0.21899680644273758,670 "rewards/accuracy_reward": 0.053125,671 "rewards/format_reward": 0.815625,672 "step": 510673 },674 {675 "completion_length": 59.621875,676 "epoch": 0.5546666666666666,677 "grad_norm": 0.4984245002269745,678 "kl": 1.695751953125,679 "learning_rate": 0.00029349194041298435,680 "loss": 0.2075,681 "reward": 0.903125,682 "reward_std": 0.16081304997205734,683 "rewards/accuracy_reward": 0.034375,684 "rewards/format_reward": 0.86875,685 "step": 520686 },687 {688 "completion_length": 62.209375,689 "epoch": 0.5653333333333334,690 "grad_norm": 0.25215986371040344,691 "kl": 1.5575439453125,692 "learning_rate": 0.0002929379768779971,693 "loss": 0.1648,694 "reward": 0.890625,695 "reward_std": 0.17983439117670058,696 "rewards/accuracy_reward": 0.040625,697 "rewards/format_reward": 0.85,698 "step": 530699 },700 {701 "completion_length": 65.865625,702 "epoch": 0.576,703 "grad_norm": 0.1489488184452057,704 "kl": 2.0063720703125,705 "learning_rate": 0.0002923619564603501,706 "loss": 0.187,707 "reward": 0.78125,708 "reward_std": 0.2043856605887413,709 "rewards/accuracy_reward": 0.03125,710 "rewards/format_reward": 0.75,711 "step": 540712 },713 {714 "completion_length": 68.68125,715 "epoch": 0.5866666666666667,716 "grad_norm": 0.24991311132907867,717 "kl": 1.0421142578125,718 "learning_rate": 0.00029176396804625135,719 "loss": 0.0977,720 "reward": 0.909375,721 "reward_std": 0.1441847175359726,722 "rewards/accuracy_reward": 0.021875,723 "rewards/format_reward": 0.8875,724 "step": 550725 },726 {727 "completion_length": 64.2,728 "epoch": 0.5973333333333334,729 "grad_norm": 0.7193971872329712,730 "kl": 2.2302490234375,731 "learning_rate": 0.00029114410391180946,732 "loss": 0.2166,733 "reward": 0.834375,734 "reward_std": 0.2048343911767006,735 "rewards/accuracy_reward": 0.015625,736 "rewards/format_reward": 0.81875,737 "step": 560738 },739 {740 "completion_length": 66.01875,741 "epoch": 0.608,742 "grad_norm": 0.59996098279953,743 "kl": 2.652294921875,744 "learning_rate": 0.0002905024597087945,745 "loss": 0.2907,746 "reward": 0.815625,747 "reward_std": 0.20596464574337006,748 "rewards/accuracy_reward": 0.028125,749 "rewards/format_reward": 0.7875,750 "step": 570751 },752 {753 "completion_length": 69.009375,754 "epoch": 0.6186666666666667,755 "grad_norm": 0.32363754510879517,756 "kl": 0.75888671875,757 "learning_rate": 0.0002898391344498775,758 "loss": 0.112,759 "reward": 0.896875,760 "reward_std": 0.14761751294136047,761 "rewards/accuracy_reward": 0.034375,762 "rewards/format_reward": 0.8625,763 "step": 580764 },765 {766 "completion_length": 58.490625,767 "epoch": 0.6293333333333333,768 "grad_norm": 0.5817243456840515,769 "kl": 3.2273193359375,770 "learning_rate": 0.0002891542304933521,771 "loss": 0.3775,772 "reward": 0.796875,773 "reward_std": 0.24620190411806106,774 "rewards/accuracy_reward": 0.00625,775 "rewards/format_reward": 0.790625,776 "step": 590777 },778 {779 "completion_length": 56.890625,780 "epoch": 0.64,781 "grad_norm": 0.561817467212677,782 "kl": 1.345703125,783 "learning_rate": 0.00028844785352733924,784 "loss": 0.1409,785 "reward": 0.884375,786 "reward_std": 0.1315855011343956,787 "rewards/accuracy_reward": 0.021875,788 "rewards/format_reward": 0.8625,789 "step": 600790 },791 {792 "completion_length": 54.61875,793 "epoch": 0.6506666666666666,794 "grad_norm": 0.41451311111450195,795 "kl": 1.3966552734375,796 "learning_rate": 0.00028772011255347873,797 "loss": 0.1476,798 "reward": 0.890625,799 "reward_std": 0.16838996410369872,800 "rewards/accuracy_reward": 0.01875,801 "rewards/format_reward": 0.871875,802 "step": 610803 },804 {805 "completion_length": 58.15,806 "epoch": 0.6613333333333333,807 "grad_norm": 0.38927924633026123,808 "kl": 2.2388427734375,809 "learning_rate": 0.00028697111987010865,810 "loss": 0.2576,811 "reward": 0.871875,812 "reward_std": 0.1995512694120407,813 "rewards/accuracy_reward": 0.028125,814 "rewards/format_reward": 0.84375,815 "step": 620816 },817 {818 "completion_length": 57.20625,819 "epoch": 0.672,820 "grad_norm": 0.09751415997743607,821 "kl": 0.793994140625,822 "learning_rate": 0.0002862009910549369,823 "loss": 0.0629,824 "reward": 0.9375,825 "reward_std": 0.10386751294136047,826 "rewards/accuracy_reward": 0.01875,827 "rewards/format_reward": 0.91875,828 "step": 630829 },830 {831 "completion_length": 65.846875,832 "epoch": 0.6826666666666666,833 "grad_norm": 0.2675510048866272,834 "kl": 2.466015625,835 "learning_rate": 0.0002854098449472061,836 "loss": 0.2627,837 "reward": 0.79375,838 "reward_std": 0.2520918682217598,839 "rewards/accuracy_reward": 0.015625,840 "rewards/format_reward": 0.778125,841 "step": 640842 },843 {844 "completion_length": 62.98125,845 "epoch": 0.6933333333333334,846 "grad_norm": 0.15855202078819275,847 "kl": 1.8398193359375,848 "learning_rate": 0.00028459780362935527,849 "loss": 0.177,850 "reward": 0.91875,851 "reward_std": 0.15879059880971907,852 "rewards/accuracy_reward": 0.0125,853 "rewards/format_reward": 0.90625,854 "step": 650855 },856 {857 "completion_length": 62.6,858 "epoch": 0.704,859 "grad_norm": 0.12087615579366684,860 "kl": 2.0813720703125,861 "learning_rate": 0.0002837649924081816,862 "loss": 0.1866,863 "reward": 0.90625,864 "reward_std": 0.19479155987501146,865 "rewards/accuracy_reward": 0.03125,866 "rewards/format_reward": 0.875,867 "step": 660868 },869 {870 "completion_length": 65.925,871 "epoch": 0.7146666666666667,872 "grad_norm": 0.39411771297454834,873 "kl": 1.392919921875,874 "learning_rate": 0.00028291153979550387,875 "loss": 0.2015,876 "reward": 0.915625,877 "reward_std": 0.1775405988097191,878 "rewards/accuracy_reward": 0.028125,879 "rewards/format_reward": 0.8875,880 "step": 670881 },882 {883 "completion_length": 64.378125,884 "epoch": 0.7253333333333334,885 "grad_norm": 1.1659783124923706,886 "kl": 2.8165283203125,887 "learning_rate": 0.00028203757748833174,888 "loss": 0.3109,889 "reward": 0.778125,890 "reward_std": 0.21169123351573943,891 "rewards/accuracy_reward": 0.003125,892 "rewards/format_reward": 0.775,893 "step": 680894 },895 {896 "completion_length": 57.334375,897 "epoch": 0.736,898 "grad_norm": 0.27627384662628174,899 "kl": 1.0085693359375,900 "learning_rate": 0.0002811432403485437,901 "loss": 0.1226,902 "reward": 0.859375,903 "reward_std": 0.11540063470602036,904 "rewards/accuracy_reward": 0.009375,905 "rewards/format_reward": 0.85,906 "step": 690907 },908 {909 "completion_length": 54.6,910 "epoch": 0.7466666666666667,911 "grad_norm": 0.4506663382053375,912 "kl": 2.3274169921875,913 "learning_rate": 0.00028022866638207624,914 "loss": 0.2726,915 "reward": 0.853125,916 "reward_std": 0.2143363133072853,917 "rewards/accuracy_reward": 0.025,918 "rewards/format_reward": 0.828125,919 "step": 700920 },921 {922 "completion_length": 64.646875,923 "epoch": 0.7573333333333333,924 "grad_norm": 0.24161870777606964,925 "kl": 1.10751953125,926 "learning_rate": 0.00027929399671762793,927 "loss": 0.1497,928 "reward": 0.878125,929 "reward_std": 0.18096464574337007,930 "rewards/accuracy_reward": 0.04375,931 "rewards/format_reward": 0.834375,932 "step": 710933 },934 {935 "completion_length": 65.128125,936 "epoch": 0.768,937 "grad_norm": 0.22652657330036163,938 "kl": 1.7567138671875,939 "learning_rate": 0.00027833937558488183,940 "loss": 0.1692,941 "reward": 0.865625,942 "reward_std": 0.19575843811035157,943 "rewards/accuracy_reward": 0.059375,944 "rewards/format_reward": 0.80625,945 "step": 720946 },947 {948 "completion_length": 76.259375,949 "epoch": 0.7786666666666666,950 "grad_norm": 0.46417316794395447,951 "kl": 3.4798828125,952 "learning_rate": 0.0002773649502922495,953 "loss": 0.3618,954 "reward": 0.7125,955 "reward_std": 0.31879488229751585,956 "rewards/accuracy_reward": 0.0125,957 "rewards/format_reward": 0.7,958 "step": 730959 },960 {961 "completion_length": 64.928125,962 "epoch": 0.7893333333333333,963 "grad_norm": 0.8743041753768921,964 "kl": 2.166650390625,965 "learning_rate": 0.00027637087120413933,966 "loss": 0.2562,967 "reward": 0.840625,968 "reward_std": 0.2851921945810318,969 "rewards/accuracy_reward": 0.0375,970 "rewards/format_reward": 0.803125,971 "step": 740972 },973 {974 "completion_length": 58.028125,975 "epoch": 0.8,976 "grad_norm": 0.18655003607273102,977 "kl": 1.73994140625,978 "learning_rate": 0.000275357291717754,979 "loss": 0.191,980 "reward": 0.909375,981 "reward_std": 0.19460364878177644,982 "rewards/accuracy_reward": 0.053125,983 "rewards/format_reward": 0.85625,984 "step": 750985 },986 {987 "completion_length": 60.803125,988 "epoch": 0.8106666666666666,989 "grad_norm": 0.04459076747298241,990 "kl": 1.7782470703125,991 "learning_rate": 0.0002743243682394195,992 "loss": 0.2117,993 "reward": 0.83125,994 "reward_std": 0.16213996410369874,995 "rewards/accuracy_reward": 0.025,996 "rewards/format_reward": 0.80625,997 "step": 760998 },999 {1000 "completion_length": 56.203125,1001 "epoch": 0.8213333333333334,1002 "grad_norm": 0.04220689460635185,1003 "kl": 1.7406494140625,1004 "learning_rate": 0.00027327226016044963,1005 "loss": 0.1999,1006 "reward": 0.878125,1007 "reward_std": 0.1423343911767006,1008 "rewards/accuracy_reward": 0.034375,1009 "rewards/format_reward": 0.84375,1010 "step": 7701011 },1012 {1013 "completion_length": 58.375,1014 "epoch": 0.832,1015 "grad_norm": 0.3807085156440735,1016 "kl": 1.8222412109375,1017 "learning_rate": 0.00027220112983255087,1018 "loss": 0.2296,1019 "reward": 0.903125,1020 "reward_std": 0.20482564270496367,1021 "rewards/accuracy_reward": 0.034375,1022 "rewards/format_reward": 0.86875,1023 "step": 7801024 },1025 {1026 "completion_length": 63.378125,1027 "epoch": 0.8426666666666667,1028 "grad_norm": 0.01206011138856411,1029 "kl": 2.458740234375,1030 "learning_rate": 0.00027111114254276913,1031 "loss": 0.3096,1032 "reward": 0.84375,1033 "reward_std": 0.2114198923110962,1034 "rewards/accuracy_reward": 0.021875,1035 "rewards/format_reward": 0.821875,1036 "step": 7901037 },1038 {1039 "completion_length": 59.7625,1040 "epoch": 0.8533333333333334,1041 "grad_norm": 0.40591439604759216,1042 "kl": 1.378076171875,1043 "learning_rate": 0.00027000246648798456,1044 "loss": 0.1403,1045 "reward": 0.934375,1046 "reward_std": 0.14083535224199295,1047 "rewards/accuracy_reward": 0.03125,1048 "rewards/format_reward": 0.903125,1049 "step": 8001050 },1051 {1052 "completion_length": 62.284375,1053 "epoch": 0.864,1054 "grad_norm": 0.27511999011039734,1055 "kl": 2.2107177734375,1056 "learning_rate": 0.0002688752727489565,1057 "loss": 0.2636,1058 "reward": 0.8875,1059 "reward_std": 0.21739855110645295,1060 "rewards/accuracy_reward": 0.028125,1061 "rewards/format_reward": 0.859375,1062 "step": 8101063 },1064 {1065 "completion_length": 65.265625,1066 "epoch": 0.8746666666666667,1067 "grad_norm": 0.2582601010799408,1068 "kl": 2.3897705078125,1069 "learning_rate": 0.00026772973526392453,1070 "loss": 0.2965,1071 "reward": 0.83125,1072 "reward_std": 0.2494538262486458,1073 "rewards/accuracy_reward": 0.028125,1074 "rewards/format_reward": 0.803125,1075 "step": 8201076 },1077 {1078 "completion_length": 54.865625,1079 "epoch": 0.8853333333333333,1080 "grad_norm": 0.23494267463684082,1081 "kl": 2.6015625,1082 "learning_rate": 0.0002665660308017671,1083 "loss": 0.252,1084 "reward": 0.9,1085 "reward_std": 0.23950843811035155,1086 "rewards/accuracy_reward": 0.04375,1087 "rewards/format_reward": 0.85625,1088 "step": 8301089 },1090 {1091 "completion_length": 55.503125,1092 "epoch": 0.896,1093 "grad_norm": 0.20798054337501526,1094 "kl": 1.5889892578125,1095 "learning_rate": 0.000265384338934725,1096 "loss": 0.1996,1097 "reward": 0.9375,1098 "reward_std": 0.20120493620634078,1099 "rewards/accuracy_reward": 0.0625,1100 "rewards/format_reward": 0.875,1101 "step": 8401102 },1103 {1104 "completion_length": 59.909375,1105 "epoch": 0.9066666666666666,1106 "grad_norm": 0.23807695508003235,1107 "kl": 1.656982421875,1108 "learning_rate": 0.00026418484201069055,1109 "loss": 0.194,1110 "reward": 0.840625,1111 "reward_std": 0.17524680644273757,1112 "rewards/accuracy_reward": 0.034375,1113 "rewards/format_reward": 0.80625,1114 "step": 8501115 },1116 {1117 "completion_length": 56.74375,1118 "epoch": 0.9173333333333333,1119 "grad_norm": 0.21559438109397888,1120 "kl": 0.813427734375,1121 "learning_rate": 0.00026296772512507025,1122 "loss": 0.1054,1123 "reward": 0.884375,1124 "reward_std": 0.13916241526603698,1125 "rewards/accuracy_reward": 0.021875,1126 "rewards/format_reward": 0.8625,1127 "step": 8601128 },1129 {1130 "completion_length": 62.390625,1131 "epoch": 0.928,1132 "grad_norm": 0.1291944831609726,1133 "kl": 1.9663330078125,1134 "learning_rate": 0.0002617331760922218,1135 "loss": 0.2316,1136 "reward": 0.85625,1137 "reward_std": 0.15685684233903885,1138 "rewards/accuracy_reward": 0.0125,1139 "rewards/format_reward": 0.84375,1140 "step": 8701141 },1142 {1143 "completion_length": 56.009375,1144 "epoch": 0.9386666666666666,1145 "grad_norm": 1.045857548713684,1146 "kl": 1.652001953125,1147 "learning_rate": 0.0002604813854164726,1148 "loss": 0.1616,1149 "reward": 0.9375,1150 "reward_std": 0.16336943507194518,1151 "rewards/accuracy_reward": 0.028125,1152 "rewards/format_reward": 0.909375,1153 "step": 8801154 },1155 {1156 "completion_length": 64.446875,1157 "epoch": 0.9493333333333334,1158 "grad_norm": 0.33091413974761963,1159 "kl": 3.235400390625,1160 "learning_rate": 0.0002592125462627231,1161 "loss": 0.3973,1162 "reward": 0.796875,1163 "reward_std": 0.2716366216540337,1164 "rewards/accuracy_reward": 0.015625,1165 "rewards/format_reward": 0.78125,1166 "step": 8901167 },1168 {1169 "completion_length": 59.0,1170 "epoch": 0.96,1171 "grad_norm": 0.25974419713020325,1172 "kl": 1.752197265625,1173 "learning_rate": 0.00025792685442663877,1174 "loss": 0.1938,1175 "reward": 0.89375,1176 "reward_std": 0.1826515957713127,1177 "rewards/accuracy_reward": 0.028125,1178 "rewards/format_reward": 0.865625,1179 "step": 9001180 },1181 {1182 "completion_length": 57.4125,1183 "epoch": 0.9706666666666667,1184 "grad_norm": 0.2569887936115265,1185 "kl": 2.5720703125,1186 "learning_rate": 0.00025662450830443733,1187 "loss": 0.3213,1188 "reward": 0.846875,1189 "reward_std": 0.22065922170877456,1190 "rewards/accuracy_reward": 0.03125,1191 "rewards/format_reward": 0.815625,1192 "step": 9101193 },1194 {1195 "completion_length": 51.140625,1196 "epoch": 0.9813333333333333,1197 "grad_norm": 0.18798935413360596,1198 "kl": 1.6124267578125,1199 "learning_rate": 0.0002553057088622736,1200 "loss": 0.2214,