wonwonn/agent_sft_generated_adapter
04
1{2 "best_global_step": null,3 "best_metric": null,4 "best_model_checkpoint": null,5 "epoch": 2.0,6 "eval_steps": 500,7 "global_step": 7532,8 "is_hyper_param_search": false,9 "is_local_process_zero": true,10 "is_world_process_zero": true,11 "log_history": [12 {13 "epoch": 0.0002655689815429558,14 "grad_norm": 1.8881195832990014,15 "learning_rate": 0.0,16 "loss": 1.1502833366394043,17 "step": 118 },19 {20 "epoch": 0.0005311379630859116,21 "grad_norm": 1.77718785062999,22 "learning_rate": 5.3050397877984086e-08,23 "loss": 1.1698756217956543,24 "step": 225 },26 {27 "epoch": 0.0007967069446288673,28 "grad_norm": 1.6766718507101437,29 "learning_rate": 1.0610079575596817e-07,30 "loss": 1.1060130596160889,31 "step": 332 },33 {34 "epoch": 0.0010622759261718232,35 "grad_norm": 1.876053682165919,36 "learning_rate": 1.5915119363395226e-07,37 "loss": 1.1075276136398315,38 "step": 439 },40 {41 "epoch": 0.001327844907714779,42 "grad_norm": 1.88228417845019,43 "learning_rate": 2.1220159151193635e-07,44 "loss": 1.2153511047363281,45 "step": 546 },47 {48 "epoch": 0.0015934138892577346,49 "grad_norm": 1.9273368394845023,50 "learning_rate": 2.6525198938992043e-07,51 "loss": 1.1400426626205444,52 "step": 653 },54 {55 "epoch": 0.0018589828708006906,56 "grad_norm": 1.904814034912833,57 "learning_rate": 3.183023872679045e-07,58 "loss": 1.2070660591125488,59 "step": 760 },61 {62 "epoch": 0.0021245518523436463,63 "grad_norm": 1.7346381008587795,64 "learning_rate": 3.713527851458886e-07,65 "loss": 1.1614588499069214,66 "step": 867 },68 {69 "epoch": 0.002390120833886602,70 "grad_norm": 1.817032704311048,71 "learning_rate": 4.244031830238727e-07,72 "loss": 1.1739476919174194,73 "step": 974 },75 {76 "epoch": 0.002655689815429558,77 "grad_norm": 1.8291974144657501,78 "learning_rate": 4.774535809018568e-07,79 "loss": 1.1559171676635742,80 "step": 1081 },82 {83 "epoch": 0.0029212587969725135,84 "grad_norm": 2.0039010539208744,85 "learning_rate": 5.305039787798409e-07,86 "loss": 1.2086225748062134,87 "step": 1188 },89 {90 "epoch": 0.0031868277785154693,91 "grad_norm": 1.876026657216244,92 "learning_rate": 5.83554376657825e-07,93 "loss": 1.227709174156189,94 "step": 1295 },96 {97 "epoch": 0.003452396760058425,98 "grad_norm": 2.0245192813139825,99 "learning_rate": 6.36604774535809e-07,100 "loss": 1.255577564239502,101 "step": 13102 },103 {104 "epoch": 0.003717965741601381,105 "grad_norm": 1.8641260357218605,106 "learning_rate": 6.896551724137931e-07,107 "loss": 1.1953760385513306,108 "step": 14109 },110 {111 "epoch": 0.0039835347231443365,112 "grad_norm": 1.9079733249323254,113 "learning_rate": 7.427055702917772e-07,114 "loss": 1.1325336694717407,115 "step": 15116 },117 {118 "epoch": 0.004249103704687293,119 "grad_norm": 1.8230190567516942,120 "learning_rate": 7.957559681697613e-07,121 "loss": 1.232974648475647,122 "step": 16123 },124 {125 "epoch": 0.004514672686230248,126 "grad_norm": 1.8532380418447003,127 "learning_rate": 8.488063660477454e-07,128 "loss": 1.1527395248413086,129 "step": 17130 },131 {132 "epoch": 0.004780241667773204,133 "grad_norm": 1.986294801704247,134 "learning_rate": 9.018567639257295e-07,135 "loss": 1.151026964187622,136 "step": 18137 },138 {139 "epoch": 0.00504581064931616,140 "grad_norm": 1.8048967405226255,141 "learning_rate": 9.549071618037136e-07,142 "loss": 1.155288815498352,143 "step": 19144 },145 {146 "epoch": 0.005311379630859116,147 "grad_norm": 2.1631450267380767,148 "learning_rate": 1.0079575596816979e-06,149 "loss": 1.183434009552002,150 "step": 20151 },152 {153 "epoch": 0.005576948612402072,154 "grad_norm": 1.88758019498484,155 "learning_rate": 1.0610079575596817e-06,156 "loss": 1.161030650138855,157 "step": 21158 },159 {160 "epoch": 0.005842517593945027,161 "grad_norm": 1.9605989446426395,162 "learning_rate": 1.1140583554376658e-06,163 "loss": 1.123382806777954,164 "step": 22165 },166 {167 "epoch": 0.006108086575487983,168 "grad_norm": 2.2042020560619306,169 "learning_rate": 1.16710875331565e-06,170 "loss": 1.238707423210144,171 "step": 23172 },173 {174 "epoch": 0.0063736555570309385,175 "grad_norm": 2.289866056000848,176 "learning_rate": 1.220159151193634e-06,177 "loss": 1.2058464288711548,178 "step": 24179 },180 {181 "epoch": 0.006639224538573895,182 "grad_norm": 2.724214643619529,183 "learning_rate": 1.273209549071618e-06,184 "loss": 1.2351092100143433,185 "step": 25186 },187 {188 "epoch": 0.00690479352011685,189 "grad_norm": 2.5088520951326028,190 "learning_rate": 1.3262599469496024e-06,191 "loss": 1.1739860773086548,192 "step": 26193 },194 {195 "epoch": 0.007170362501659806,196 "grad_norm": 2.3243798435890155,197 "learning_rate": 1.3793103448275862e-06,198 "loss": 1.1407617330551147,199 "step": 27200 },201 {202 "epoch": 0.007435931483202762,203 "grad_norm": 2.533007430657115,204 "learning_rate": 1.4323607427055705e-06,205 "loss": 1.1844531297683716,206 "step": 28207 },208 {209 "epoch": 0.007701500464745718,210 "grad_norm": 2.4702075978733804,211 "learning_rate": 1.4854111405835544e-06,212 "loss": 1.1293678283691406,213 "step": 29214 },215 {216 "epoch": 0.007967069446288673,217 "grad_norm": 3.0873404038783963,218 "learning_rate": 1.5384615384615387e-06,219 "loss": 1.1310899257659912,220 "step": 30221 },222 {223 "epoch": 0.00823263842783163,224 "grad_norm": 2.7098364862500013,225 "learning_rate": 1.5915119363395226e-06,226 "loss": 1.1015795469284058,227 "step": 31228 },229 {230 "epoch": 0.008498207409374585,231 "grad_norm": 2.8074949689582476,232 "learning_rate": 1.6445623342175069e-06,233 "loss": 1.0756056308746338,234 "step": 32235 },236 {237 "epoch": 0.00876377639091754,238 "grad_norm": 3.1563034348975676,239 "learning_rate": 1.6976127320954908e-06,240 "loss": 1.1496126651763916,241 "step": 33242 },243 {244 "epoch": 0.009029345372460496,245 "grad_norm": 2.842390896608423,246 "learning_rate": 1.750663129973475e-06,247 "loss": 1.203465461730957,248 "step": 34249 },250 {251 "epoch": 0.009294914354003453,252 "grad_norm": 2.6747271223349753,253 "learning_rate": 1.803713527851459e-06,254 "loss": 1.0613923072814941,255 "step": 35256 },257 {258 "epoch": 0.009560483335546408,259 "grad_norm": 2.146709655536541,260 "learning_rate": 1.8567639257294432e-06,261 "loss": 1.06027090549469,262 "step": 36263 },264 {265 "epoch": 0.009826052317089363,266 "grad_norm": 1.9942495143394863,267 "learning_rate": 1.909814323607427e-06,268 "loss": 1.0508522987365723,269 "step": 37270 },271 {272 "epoch": 0.01009162129863232,273 "grad_norm": 2.1704927298148107,274 "learning_rate": 1.9628647214854114e-06,275 "loss": 1.0353929996490479,276 "step": 38277 },278 {279 "epoch": 0.010357190280175276,280 "grad_norm": 1.8252380884349957,281 "learning_rate": 2.0159151193633957e-06,282 "loss": 0.9974027276039124,283 "step": 39284 },285 {286 "epoch": 0.010622759261718231,287 "grad_norm": 1.7188806752497834,288 "learning_rate": 2.0689655172413796e-06,289 "loss": 1.0849467515945435,290 "step": 40291 },292 {293 "epoch": 0.010888328243261186,294 "grad_norm": 1.3692667089198218,295 "learning_rate": 2.1220159151193635e-06,296 "loss": 1.005434274673462,297 "step": 41298 },299 {300 "epoch": 0.011153897224804143,301 "grad_norm": 1.3465343019370317,302 "learning_rate": 2.1750663129973478e-06,303 "loss": 1.052631139755249,304 "step": 42305 },306 {307 "epoch": 0.011419466206347099,308 "grad_norm": 1.352421126005469,309 "learning_rate": 2.2281167108753316e-06,310 "loss": 0.9470957517623901,311 "step": 43312 },313 {314 "epoch": 0.011685035187890054,315 "grad_norm": 1.2219308328594767,316 "learning_rate": 2.281167108753316e-06,317 "loss": 0.9865130186080933,318 "step": 44319 },320 {321 "epoch": 0.01195060416943301,322 "grad_norm": 1.19161259271228,323 "learning_rate": 2.3342175066313e-06,324 "loss": 0.9405577778816223,325 "step": 45326 },327 {328 "epoch": 0.012216173150975966,329 "grad_norm": 1.1603073869733838,330 "learning_rate": 2.387267904509284e-06,331 "loss": 0.9418795108795166,332 "step": 46333 },334 {335 "epoch": 0.012481742132518922,336 "grad_norm": 1.1897328813812988,337 "learning_rate": 2.440318302387268e-06,338 "loss": 0.9841142892837524,339 "step": 47340 },341 {342 "epoch": 0.012747311114061877,343 "grad_norm": 1.159720101499262,344 "learning_rate": 2.4933687002652523e-06,345 "loss": 0.9412609338760376,346 "step": 48347 },348 {349 "epoch": 0.013012880095604834,350 "grad_norm": 1.1421347262548374,351 "learning_rate": 2.546419098143236e-06,352 "loss": 0.9239889979362488,353 "step": 49354 },355 {356 "epoch": 0.01327844907714779,357 "grad_norm": 1.144363453746544,358 "learning_rate": 2.59946949602122e-06,359 "loss": 0.9212941527366638,360 "step": 50361 },362 {363 "epoch": 0.013544018058690745,364 "grad_norm": 0.9916816911141796,365 "learning_rate": 2.6525198938992047e-06,366 "loss": 0.8863773345947266,367 "step": 51368 },369 {370 "epoch": 0.0138095870402337,371 "grad_norm": 0.9890613082667745,372 "learning_rate": 2.7055702917771886e-06,373 "loss": 0.8990404009819031,374 "step": 52375 },376 {377 "epoch": 0.014075156021776657,378 "grad_norm": 1.1123466462737277,379 "learning_rate": 2.7586206896551725e-06,380 "loss": 0.9257171154022217,381 "step": 53382 },383 {384 "epoch": 0.014340725003319612,385 "grad_norm": 0.8689931750055545,386 "learning_rate": 2.8116710875331564e-06,387 "loss": 0.8239601254463196,388 "step": 54389 },390 {391 "epoch": 0.014606293984862568,392 "grad_norm": 0.9936229603029793,393 "learning_rate": 2.864721485411141e-06,394 "loss": 0.8656830787658691,395 "step": 55396 },397 {398 "epoch": 0.014871862966405525,399 "grad_norm": 1.0202371081091262,400 "learning_rate": 2.917771883289125e-06,401 "loss": 0.9470342397689819,402 "step": 56403 },404 {405 "epoch": 0.01513743194794848,406 "grad_norm": 0.9663900963956384,407 "learning_rate": 2.970822281167109e-06,408 "loss": 0.8699859976768494,409 "step": 57410 },411 {412 "epoch": 0.015403000929491435,413 "grad_norm": 0.940263545207204,414 "learning_rate": 3.0238726790450927e-06,415 "loss": 0.8668704628944397,416 "step": 58417 },418 {419 "epoch": 0.01566856991103439,420 "grad_norm": 0.9865381848251076,421 "learning_rate": 3.0769230769230774e-06,422 "loss": 0.841624915599823,423 "step": 59424 },425 {426 "epoch": 0.015934138892577346,427 "grad_norm": 0.8909972421095332,428 "learning_rate": 3.1299734748010613e-06,429 "loss": 0.8412661552429199,430 "step": 60431 },432 {433 "epoch": 0.0161997078741203,434 "grad_norm": 0.8771283277278942,435 "learning_rate": 3.183023872679045e-06,436 "loss": 0.818957507610321,437 "step": 61438 },439 {440 "epoch": 0.01646527685566326,441 "grad_norm": 0.9190140482494583,442 "learning_rate": 3.23607427055703e-06,443 "loss": 0.8030763268470764,444 "step": 62445 },446 {447 "epoch": 0.016730845837206215,448 "grad_norm": 0.8839367067386452,449 "learning_rate": 3.2891246684350138e-06,450 "loss": 0.7869359850883484,451 "step": 63452 },453 {454 "epoch": 0.01699641481874917,455 "grad_norm": 0.8058255896640879,456 "learning_rate": 3.3421750663129977e-06,457 "loss": 0.7912170886993408,458 "step": 64459 },460 {461 "epoch": 0.017261983800292126,462 "grad_norm": 0.8538938403853334,463 "learning_rate": 3.3952254641909815e-06,464 "loss": 0.7736695408821106,465 "step": 65466 },467 {468 "epoch": 0.01752755278183508,469 "grad_norm": 0.8652625375848492,470 "learning_rate": 3.448275862068966e-06,471 "loss": 0.768275260925293,472 "step": 66473 },474 {475 "epoch": 0.017793121763378036,476 "grad_norm": 0.8691478661970735,477 "learning_rate": 3.50132625994695e-06,478 "loss": 0.7210639119148254,479 "step": 67480 },481 {482 "epoch": 0.01805869074492099,483 "grad_norm": 0.8378031795839386,484 "learning_rate": 3.554376657824934e-06,485 "loss": 0.7488028407096863,486 "step": 68487 },488 {489 "epoch": 0.01832425972646395,490 "grad_norm": 0.8943989597273122,491 "learning_rate": 3.607427055702918e-06,492 "loss": 0.7329621911048889,493 "step": 69494 },495 {496 "epoch": 0.018589828708006906,497 "grad_norm": 0.92104620358882,498 "learning_rate": 3.660477453580902e-06,499 "loss": 0.7270619869232178,500 "step": 70501 },502 {503 "epoch": 0.01885539768954986,504 "grad_norm": 0.9782498013554233,505 "learning_rate": 3.7135278514588865e-06,506 "loss": 0.7271254658699036,507 "step": 71508 },509 {510 "epoch": 0.019120966671092816,511 "grad_norm": 0.9115603845811348,512 "learning_rate": 3.7665782493368703e-06,513 "loss": 0.787033200263977,514 "step": 72515 },516 {517 "epoch": 0.01938653565263577,518 "grad_norm": 0.8604692726067453,519 "learning_rate": 3.819628647214854e-06,520 "loss": 0.7049479484558105,521 "step": 73522 },523 {524 "epoch": 0.019652104634178727,525 "grad_norm": 0.8610577281688413,526 "learning_rate": 3.8726790450928385e-06,527 "loss": 0.7146892547607422,528 "step": 74529 },530 {531 "epoch": 0.019917673615721682,532 "grad_norm": 0.7602187567662452,533 "learning_rate": 3.925729442970823e-06,534 "loss": 0.7212516069412231,535 "step": 75536 },537 {538 "epoch": 0.02018324259726464,539 "grad_norm": 0.6842508042039768,540 "learning_rate": 3.978779840848806e-06,541 "loss": 0.6612375378608704,542 "step": 76543 },544 {545 "epoch": 0.020448811578807596,546 "grad_norm": 0.7781006919053841,547 "learning_rate": 4.031830238726791e-06,548 "loss": 0.7038244605064392,549 "step": 77550 },551 {552 "epoch": 0.02071438056035055,553 "grad_norm": 0.7186592057129139,554 "learning_rate": 4.084880636604775e-06,555 "loss": 0.7081903219223022,556 "step": 78557 },558 {559 "epoch": 0.020979949541893507,560 "grad_norm": 0.7655954113403886,561 "learning_rate": 4.137931034482759e-06,562 "loss": 0.7079841494560242,563 "step": 79564 },565 {566 "epoch": 0.021245518523436462,567 "grad_norm": 0.7149787673446053,568 "learning_rate": 4.190981432360743e-06,569 "loss": 0.7090641260147095,570 "step": 80571 },572 {573 "epoch": 0.021511087504979418,574 "grad_norm": 0.6657837070384769,575 "learning_rate": 4.244031830238727e-06,576 "loss": 0.6632575988769531,577 "step": 81578 },579 {580 "epoch": 0.021776656486522373,581 "grad_norm": 0.6666401713606211,582 "learning_rate": 4.297082228116711e-06,583 "loss": 0.7231097221374512,584 "step": 82585 },586 {587 "epoch": 0.02204222546806533,588 "grad_norm": 0.6804476609839887,589 "learning_rate": 4.3501326259946955e-06,590 "loss": 0.6696034669876099,591 "step": 83592 },593 {594 "epoch": 0.022307794449608287,595 "grad_norm": 0.7073638927991296,596 "learning_rate": 4.403183023872679e-06,597 "loss": 0.7550696134567261,598 "step": 84599 },600 {601 "epoch": 0.022573363431151242,602 "grad_norm": 0.7064770122504733,603 "learning_rate": 4.456233421750663e-06,604 "loss": 0.671328067779541,605 "step": 85606 },607 {608 "epoch": 0.022838932412694198,609 "grad_norm": 0.6506139330803743,610 "learning_rate": 4.5092838196286476e-06,611 "loss": 0.6864410638809204,612 "step": 86613 },614 {615 "epoch": 0.023104501394237153,616 "grad_norm": 0.6642837777732639,617 "learning_rate": 4.562334217506632e-06,618 "loss": 0.6870769262313843,619 "step": 87620 },621 {622 "epoch": 0.023370070375780108,623 "grad_norm": 0.6947506894199804,624 "learning_rate": 4.615384615384616e-06,625 "loss": 0.6539690494537354,626 "step": 88627 },628 {629 "epoch": 0.023635639357323063,630 "grad_norm": 0.6446743321890098,631 "learning_rate": 4.6684350132626e-06,632 "loss": 0.6946991086006165,633 "step": 89634 },635 {636 "epoch": 0.02390120833886602,637 "grad_norm": 0.6384512383480915,638 "learning_rate": 4.721485411140584e-06,639 "loss": 0.6177583932876587,640 "step": 90641 },642 {643 "epoch": 0.024166777320408978,644 "grad_norm": 0.7150510018442997,645 "learning_rate": 4.774535809018568e-06,646 "loss": 0.6890037059783936,647 "step": 91648 },649 {650 "epoch": 0.024432346301951933,651 "grad_norm": 0.6592991709316253,652 "learning_rate": 4.8275862068965525e-06,653 "loss": 0.6563063263893127,654 "step": 92655 },656 {657 "epoch": 0.024697915283494888,658 "grad_norm": 0.6897740926797078,659 "learning_rate": 4.880636604774536e-06,660 "loss": 0.714318573474884,661 "step": 93662 },663 {664 "epoch": 0.024963484265037843,665 "grad_norm": 0.6433596226177777,666 "learning_rate": 4.93368700265252e-06,667 "loss": 0.6720882654190063,668 "step": 94669 },670 {671 "epoch": 0.0252290532465808,672 "grad_norm": 0.5910528348002435,673 "learning_rate": 4.9867374005305045e-06,674 "loss": 0.602899968624115,675 "step": 95676 },677 {678 "epoch": 0.025494622228123754,679 "grad_norm": 0.6635651676723159,680 "learning_rate": 5.039787798408489e-06,681 "loss": 0.6628841161727905,682 "step": 96683 },684 {685 "epoch": 0.02576019120966671,686 "grad_norm": 0.6070065577903714,687 "learning_rate": 5.092838196286472e-06,688 "loss": 0.6486932635307312,689 "step": 97690 },691 {692 "epoch": 0.026025760191209668,693 "grad_norm": 0.6484848126679549,694 "learning_rate": 5.145888594164457e-06,695 "loss": 0.6719033122062683,696 "step": 98697 },698 {699 "epoch": 0.026291329172752623,700 "grad_norm": 0.6856934201881044,701 "learning_rate": 5.19893899204244e-06,702 "loss": 0.6818530559539795,703 "step": 99704 },705 {706 "epoch": 0.02655689815429558,707 "grad_norm": 0.6204811558305167,708 "learning_rate": 5.251989389920424e-06,709 "loss": 0.6306912899017334,710 "step": 100711 },712 {713 "epoch": 0.026822467135838534,714 "grad_norm": 0.7820574736690976,715 "learning_rate": 5.3050397877984095e-06,716 "loss": 0.5952945351600647,717 "step": 101718 },719 {720 "epoch": 0.02708803611738149,721 "grad_norm": 0.6546243503849497,722 "learning_rate": 5.358090185676394e-06,723 "loss": 0.6566107273101807,724 "step": 102725 },726 {727 "epoch": 0.027353605098924445,728 "grad_norm": 0.707921645301647,729 "learning_rate": 5.411140583554377e-06,730 "loss": 0.6981694102287292,731 "step": 103732 },733 {734 "epoch": 0.0276191740804674,735 "grad_norm": 0.6375441067969543,736 "learning_rate": 5.4641909814323615e-06,737 "loss": 0.6231328248977661,738 "step": 104739 },740 {741 "epoch": 0.02788474306201036,742 "grad_norm": 0.6964560869475424,743 "learning_rate": 5.517241379310345e-06,744 "loss": 0.6414977312088013,745 "step": 105746 },747 {748 "epoch": 0.028150312043553314,749 "grad_norm": 0.6835502446580011,750 "learning_rate": 5.570291777188329e-06,751 "loss": 0.6335234642028809,752 "step": 106753 },754 {755 "epoch": 0.02841588102509627,756 "grad_norm": 0.6248033284508979,757 "learning_rate": 5.623342175066313e-06,758 "loss": 0.6040852665901184,759 "step": 107760 },761 {762 "epoch": 0.028681450006639225,763 "grad_norm": 0.6645474785171195,764 "learning_rate": 5.676392572944297e-06,765 "loss": 0.6011114716529846,766 "step": 108767 },768 {769 "epoch": 0.02894701898818218,770 "grad_norm": 0.655106623405533,771 "learning_rate": 5.729442970822282e-06,772 "loss": 0.6042627096176147,773 "step": 109774 },775 {776 "epoch": 0.029212587969725135,777 "grad_norm": 0.720208539355598,778 "learning_rate": 5.782493368700266e-06,779 "loss": 0.6183412671089172,780 "step": 110781 },782 {783 "epoch": 0.02947815695126809,784 "grad_norm": 0.6666287454908232,785 "learning_rate": 5.83554376657825e-06,786 "loss": 0.6150818467140198,787 "step": 111788 },789 {790 "epoch": 0.02974372593281105,791 "grad_norm": 0.6840692324124527,792 "learning_rate": 5.888594164456234e-06,793 "loss": 0.6202039122581482,794 "step": 112795 },796 {797 "epoch": 0.030009294914354005,798 "grad_norm": 0.6626407253242022,799 "learning_rate": 5.941644562334218e-06,800 "loss": 0.6334809064865112,801 "step": 113802 },803 {804 "epoch": 0.03027486389589696,805 "grad_norm": 0.6319419097399773,806 "learning_rate": 5.994694960212202e-06,807 "loss": 0.5728089809417725,808 "step": 114809 },810 {811 "epoch": 0.030540432877439915,812 "grad_norm": 0.6988175213443283,813 "learning_rate": 6.0477453580901854e-06,814 "loss": 0.6884603500366211,815 "step": 115816 },817 {818 "epoch": 0.03080600185898287,819 "grad_norm": 0.6618120552387852,820 "learning_rate": 6.1007957559681706e-06,821 "loss": 0.5619829893112183,822 "step": 116823 },824 {825 "epoch": 0.031071570840525826,826 "grad_norm": 0.6756012639437595,827 "learning_rate": 6.153846153846155e-06,828 "loss": 0.6224710941314697,829 "step": 117830 },831 {832 "epoch": 0.03133713982206878,833 "grad_norm": 0.7208355833756769,834 "learning_rate": 6.206896551724138e-06,835 "loss": 0.6119496822357178,836 "step": 118837 },838 {839 "epoch": 0.03160270880361174,840 "grad_norm": 0.6917782946677038,841 "learning_rate": 6.259946949602123e-06,842 "loss": 0.6190857887268066,843 "step": 119844 },845 {846 "epoch": 0.03186827778515469,847 "grad_norm": 0.6704531181022263,848 "learning_rate": 6.312997347480107e-06,849 "loss": 0.6460769176483154,850 "step": 120851 },852 {853 "epoch": 0.03213384676669765,854 "grad_norm": 0.7493511248909543,855 "learning_rate": 6.36604774535809e-06,856 "loss": 0.6148796677589417,857 "step": 121858 },859 {860 "epoch": 0.0323994157482406,861 "grad_norm": 0.6359613412994526,862 "learning_rate": 6.419098143236075e-06,863 "loss": 0.558960497379303,864 "step": 122865 },866 {867 "epoch": 0.03266498472978356,868 "grad_norm": 0.6785691051694177,869 "learning_rate": 6.47214854111406e-06,870 "loss": 0.5844984650611877,871 "step": 123872 },873 {874 "epoch": 0.03293055371132652,875 "grad_norm": 0.6692815537253501,876 "learning_rate": 6.525198938992043e-06,877 "loss": 0.5343623161315918,878 "step": 124879 },880 {881 "epoch": 0.03319612269286947,882 "grad_norm": 0.6705726789318588,883 "learning_rate": 6.5782493368700276e-06,884 "loss": 0.5834348797798157,885 "step": 125886 },887 {888 "epoch": 0.03346169167441243,889 "grad_norm": 0.7626576562771024,890 "learning_rate": 6.631299734748011e-06,891 "loss": 0.5997360944747925,892 "step": 126893 },894 {895 "epoch": 0.03372726065595538,896 "grad_norm": 0.7117893752859364,897 "learning_rate": 6.684350132625995e-06,898 "loss": 0.5991666316986084,899 "step": 127900 },901 {902 "epoch": 0.03399282963749834,903 "grad_norm": 0.7060406683837459,904 "learning_rate": 6.737400530503979e-06,905 "loss": 0.581120491027832,906 "step": 128907 },908 {909 "epoch": 0.03425839861904129,910 "grad_norm": 0.6869761252397286,911 "learning_rate": 6.790450928381963e-06,912 "loss": 0.6219569444656372,913 "step": 129914 },915 {916 "epoch": 0.03452396760058425,917 "grad_norm": 0.6916173566260286,918 "learning_rate": 6.843501326259947e-06,919 "loss": 0.5950608253479004,920 "step": 130921 },922 {923 "epoch": 0.03478953658212721,924 "grad_norm": 0.6136480902733893,925 "learning_rate": 6.896551724137932e-06,926 "loss": 0.5762747526168823,927 "step": 131928 },929 {930 "epoch": 0.03505510556367016,931 "grad_norm": 0.670368708945713,932 "learning_rate": 6.949602122015916e-06,933 "loss": 0.6003131866455078,934 "step": 132935 },936 {937 "epoch": 0.03532067454521312,938 "grad_norm": 0.6439028776339482,939 "learning_rate": 7.0026525198939e-06,940 "loss": 0.5866605043411255,941 "step": 133942 },943 {944 "epoch": 0.03558624352675607,945 "grad_norm": 0.8324202287699098,946 "learning_rate": 7.055702917771884e-06,947 "loss": 0.6668443083763123,948 "step": 134949 },950 {951 "epoch": 0.03585181250829903,952 "grad_norm": 0.7064456856515898,953 "learning_rate": 7.108753315649868e-06,954 "loss": 0.5738306045532227,955 "step": 135956 },957 {958 "epoch": 0.03611738148984198,959 "grad_norm": 0.6941604370641007,960 "learning_rate": 7.1618037135278515e-06,961 "loss": 0.5774663686752319,962 "step": 136963 },964 {965 "epoch": 0.03638295047138494,966 "grad_norm": 0.7648336305672251,967 "learning_rate": 7.214854111405836e-06,968 "loss": 0.5721150636672974,969 "step": 137970 },971 {972 "epoch": 0.0366485194529279,973 "grad_norm": 0.7394576462203543,974 "learning_rate": 7.267904509283821e-06,975 "loss": 0.6350122690200806,976 "step": 138977 },978 {979 "epoch": 0.03691408843447085,980 "grad_norm": 0.6540602529440619,981 "learning_rate": 7.320954907161804e-06,982 "loss": 0.5435039401054382,983 "step": 139984 },985 {986 "epoch": 0.03717965741601381,987 "grad_norm": 0.6965351191908165,988 "learning_rate": 7.374005305039789e-06,989 "loss": 0.5869162678718567,990 "step": 140991 },992 {993 "epoch": 0.03744522639755676,994 "grad_norm": 0.6664228073022063,995 "learning_rate": 7.427055702917773e-06,996 "loss": 0.5645807981491089,997 "step": 141998 },999 {1000 "epoch": 0.03771079537909972,1001 "grad_norm": 0.6503771775205762,1002 "learning_rate": 7.480106100795756e-06,1003 "loss": 0.5502692461013794,1004 "step": 1421005 },1006 {1007 "epoch": 0.037976364360642674,1008 "grad_norm": 0.6223645459397411,1009 "learning_rate": 7.533156498673741e-06,1010 "loss": 0.5602732300758362,1011 "step": 1431012 },1013 {1014 "epoch": 0.03824193334218563,1015 "grad_norm": 0.8638951879324807,1016 "learning_rate": 7.586206896551724e-06,1017 "loss": 0.6011391282081604,1018 "step": 1441019 },1020 {1021 "epoch": 0.03850750232372859,1022 "grad_norm": 0.6930636234613441,1023 "learning_rate": 7.639257294429708e-06,1024 "loss": 0.5482327938079834,1025 "step": 1451026 },1027 {1028 "epoch": 0.03877307130527154,1029 "grad_norm": 0.6693652199128735,1030 "learning_rate": 7.692307692307694e-06,1031 "loss": 0.5926344394683838,1032 "step": 1461033 },1034 {1035 "epoch": 0.0390386402868145,1036 "grad_norm": 0.8434991800954339,1037 "learning_rate": 7.745358090185677e-06,1038 "loss": 0.6558316946029663,1039 "step": 1471040 },1041 {1042 "epoch": 0.039304209268357454,1043 "grad_norm": 0.6845819362079449,1044 "learning_rate": 7.79840848806366e-06,1045 "loss": 0.572425365447998,1046 "step": 1481047 },1048 {1049 "epoch": 0.03956977824990041,1050 "grad_norm": 0.696296152543372,1051 "learning_rate": 7.851458885941646e-06,1052 "loss": 0.5684784650802612,1053 "step": 1491054 },1055 {1056 "epoch": 0.039835347231443365,1057 "grad_norm": 0.6779490529346879,1058 "learning_rate": 7.904509283819629e-06,1059 "loss": 0.5843643546104431,1060 "step": 1501061 },1062 {1063 "epoch": 0.04010091621298632,1064 "grad_norm": 0.6894842979231472,1065 "learning_rate": 7.957559681697613e-06,1066 "loss": 0.5471494793891907,1067 "step": 1511068 },1069 {1070 "epoch": 0.04036648519452928,1071 "grad_norm": 0.7583250211136208,1072 "learning_rate": 8.010610079575598e-06,1073 "loss": 0.595018744468689,1074 "step": 1521075 },1076 {1077 "epoch": 0.040632054176072234,1078 "grad_norm": 0.6904128122756304,1079 "learning_rate": 8.063660477453583e-06,1080 "loss": 0.5431865453720093,1081 "step": 1531082 },1083 {1084 "epoch": 0.04089762315761519,1085 "grad_norm": 0.7943246581886504,1086 "learning_rate": 8.116710875331566e-06,1087 "loss": 0.5622385740280151,1088 "step": 1541089 },1090 {1091 "epoch": 0.041163192139158145,1092 "grad_norm": 0.7792002007338675,1093 "learning_rate": 8.16976127320955e-06,1094 "loss": 0.5795880556106567,1095 "step": 1551096 },1097 {1098 "epoch": 0.0414287611207011,1099 "grad_norm": 0.7432143976693507,1100 "learning_rate": 8.222811671087533e-06,1101 "loss": 0.5854965448379517,1102 "step": 1561103 },1104 {1105 "epoch": 0.041694330102244055,1106 "grad_norm": 0.8104825185442435,1107 "learning_rate": 8.275862068965518e-06,1108 "loss": 0.5374501943588257,1109 "step": 1571110 },1111 {1112 "epoch": 0.041959899083787014,1113 "grad_norm": 0.7598674115735401,1114 "learning_rate": 8.328912466843502e-06,1115 "loss": 0.5779006481170654,1116 "step": 1581117 },1118 {1119 "epoch": 0.04222546806532997,1120 "grad_norm": 0.7033741631796787,1121 "learning_rate": 8.381962864721485e-06,1122 "loss": 0.550236701965332,1123 "step": 1591124 },1125 {1126 "epoch": 0.042491037046872925,1127 "grad_norm": 0.7285453499901458,1128 "learning_rate": 8.43501326259947e-06,1129 "loss": 0.557443380355835,1130 "step": 1601131 },1132 {1133 "epoch": 0.04275660602841588,1134 "grad_norm": 0.7050753960524794,1135 "learning_rate": 8.488063660477454e-06,1136 "loss": 0.5875238180160522,1137 "step": 1611138 },1139 {1140 "epoch": 0.043022175009958835,1141 "grad_norm": 0.7215582793376403,1142 "learning_rate": 8.541114058355439e-06,1143 "loss": 0.510900616645813,1144 "step": 1621145 },1146 {1147 "epoch": 0.043287743991501794,1148 "grad_norm": 0.7559114001900116,1149 "learning_rate": 8.594164456233422e-06,1150 "loss": 0.5465859174728394,1151 "step": 1631152 },1153 {1154 "epoch": 0.043553312973044746,1155 "grad_norm": 0.7494489908601825,1156 "learning_rate": 8.647214854111406e-06,1157 "loss": 0.5508615970611572,1158 "step": 1641159 },1160 {1161 "epoch": 0.043818881954587705,1162 "grad_norm": 0.7714387963397975,1163 "learning_rate": 8.700265251989391e-06,1164 "loss": 0.5437714457511902,1165 "step": 1651166 },1167 {1168 "epoch": 0.04408445093613066,1169 "grad_norm": 0.7480600693956645,1170 "learning_rate": 8.753315649867374e-06,1171 "loss": 0.542698323726654,1172 "step": 1661173 },1174 {1175 "epoch": 0.044350019917673615,1176 "grad_norm": 0.7339141407878966,1177 "learning_rate": 8.806366047745358e-06,1178 "loss": 0.5169371962547302,1179 "step": 1671180 },1181 {1182 "epoch": 0.044615588899216574,1183 "grad_norm": 0.725595419270195,1184 "learning_rate": 8.859416445623343e-06,1185 "loss": 0.5436176061630249,1186 "step": 1681187 },1188 {1189 "epoch": 0.044881157880759526,1190 "grad_norm": 0.8205411933516983,1191 "learning_rate": 8.912466843501327e-06,1192 "loss": 0.568030834197998,1193 "step": 1691194 },1195 {1196 "epoch": 0.045146726862302484,1197 "grad_norm": 0.7544356200090666,1198 "learning_rate": 8.965517241379312e-06,1199 "loss": 0.5218889713287354,1200 "step": 170