cucl2/AnyAudio-Judge-7B
063
1{2 "best_global_step": null,3 "best_metric": null,4 "best_model_checkpoint": null,5 "epoch": 1.0,6 "eval_steps": 200.0,7 "global_step": 1641,8 "is_hyper_param_search": false,9 "is_local_process_zero": true,10 "is_world_process_zero": true,11 "log_history": [12 {13 "epoch": 0.0006093845216331506,14 "grad_norm": 5.139511599456721,15 "learning_rate": 2.0000000000000002e-07,16 "loss": 0.97658371925354,17 "step": 1,18 "token_acc": 0.75275725452403919 },20 {21 "epoch": 0.006093845216331505,22 "grad_norm": 4.02627916602829,23 "learning_rate": 2.0000000000000003e-06,24 "loss": 0.979477776421441,25 "step": 10,26 "token_acc": 0.751339462950015627 },28 {29 "epoch": 0.01218769043266301,30 "grad_norm": 2.133243665962445,31 "learning_rate": 4.000000000000001e-06,32 "loss": 0.8085936546325684,33 "step": 20,34 "token_acc": 0.784133004686924335 },36 {37 "epoch": 0.018281535648994516,38 "grad_norm": 1.6130698467539089,39 "learning_rate": 6e-06,40 "loss": 0.6815763473510742,41 "step": 30,42 "token_acc": 0.808859867495868943 },44 {45 "epoch": 0.02437538086532602,46 "grad_norm": 1.5958993846193437,47 "learning_rate": 8.000000000000001e-06,48 "loss": 0.6228148937225342,49 "step": 40,50 "token_acc": 0.82070989204117551 },52 {53 "epoch": 0.030469226081657527,54 "grad_norm": 1.5835525047156958,55 "learning_rate": 1e-05,56 "loss": 0.5660243034362793,57 "step": 50,58 "token_acc": 0.833404458787212459 },60 {61 "epoch": 0.03656307129798903,62 "grad_norm": 1.486912724454441,63 "learning_rate": 9.999025267866269e-06,64 "loss": 0.5425637722015381,65 "step": 60,66 "token_acc": 0.837775166568746367 },68 {69 "epoch": 0.042656916514320534,70 "grad_norm": 1.5337888751937572,71 "learning_rate": 9.996101451506166e-06,72 "loss": 0.5277560710906982,73 "step": 70,74 "token_acc": 0.843699018796548175 },76 {77 "epoch": 0.04875076173065204,78 "grad_norm": 1.3940886051095893,79 "learning_rate": 9.991229690894796e-06,80 "loss": 0.5164490699768066,81 "step": 80,82 "token_acc": 0.84374563285891383 },84 {85 "epoch": 0.054844606946983544,86 "grad_norm": 1.732808941800786,87 "learning_rate": 9.984411885496807e-06,88 "loss": 0.5111546516418457,89 "step": 90,90 "token_acc": 0.845323084254729291 },92 {93 "epoch": 0.06093845216331505,94 "grad_norm": 1.502010177161109,95 "learning_rate": 9.975650693525798e-06,96 "loss": 0.5041120052337646,97 "step": 100,98 "token_acc": 0.845236441569265699 },100 {101 "epoch": 0.06703229737964655,102 "grad_norm": 1.4601020474033113,103 "learning_rate": 9.964949530907907e-06,104 "loss": 0.5016684532165527,105 "step": 110,106 "token_acc": 0.8476517417815049107 },108 {109 "epoch": 0.07312614259597806,110 "grad_norm": 1.2952511202685608,111 "learning_rate": 9.952312569949963e-06,112 "loss": 0.481311559677124,113 "step": 120,114 "token_acc": 0.8533387907153323115 },116 {117 "epoch": 0.07921998781230957,118 "grad_norm": 1.4971652792627679,119 "learning_rate": 9.937744737712734e-06,120 "loss": 0.4774615287780762,121 "step": 130,122 "token_acc": 0.8534425009304056123 },124 {125 "epoch": 0.08531383302864107,126 "grad_norm": 1.3779208298780503,127 "learning_rate": 9.921251714089898e-06,128 "loss": 0.4781217575073242,129 "step": 140,130 "token_acc": 0.8540719832383131131 },132 {133 "epoch": 0.09140767824497258,134 "grad_norm": 1.2833076700573953,135 "learning_rate": 9.9028399295935e-06,136 "loss": 0.470335865020752,137 "step": 150,138 "token_acc": 0.855729364137813139 },140 {141 "epoch": 0.09750152346130408,142 "grad_norm": 1.275667403101274,143 "learning_rate": 9.882516562846735e-06,144 "loss": 0.4639917850494385,145 "step": 160,146 "token_acc": 0.856720295350119147 },148 {149 "epoch": 0.1035953686776356,150 "grad_norm": 1.3612747480512406,151 "learning_rate": 9.860289537785058e-06,152 "loss": 0.46750926971435547,153 "step": 170,154 "token_acc": 0.8558511446900368155 },156 {157 "epoch": 0.10968921389396709,158 "grad_norm": 1.415269189793894,159 "learning_rate": 9.83616752056669e-06,160 "loss": 0.4647522926330566,161 "step": 180,162 "token_acc": 0.8561545157582173163 },164 {165 "epoch": 0.1157830591102986,166 "grad_norm": 1.1892931159809241,167 "learning_rate": 9.810159916193763e-06,168 "loss": 0.45995321273803713,169 "step": 190,170 "token_acc": 0.8573448602405447171 },172 {173 "epoch": 0.1218769043266301,174 "grad_norm": 1.3064527572301536,175 "learning_rate": 9.782276864845351e-06,176 "loss": 0.4638189792633057,177 "step": 200,178 "token_acc": 0.8556243509610675179 },180 {181 "epoch": 0.12797074954296161,182 "grad_norm": 1.314500952457575,183 "learning_rate": 9.752529237923914e-06,184 "loss": 0.4490074634552002,185 "step": 210,186 "token_acc": 0.8597137978120026187 },188 {189 "epoch": 0.1340645947592931,190 "grad_norm": 1.1373343380715917,191 "learning_rate": 9.720928633816596e-06,192 "loss": 0.4501980781555176,193 "step": 220,194 "token_acc": 0.859648604947868195 },196 {197 "epoch": 0.14015843997562463,198 "grad_norm": 1.230125123804479,199 "learning_rate": 9.687487373373103e-06,200 "loss": 0.44935040473937987,201 "step": 230,202 "token_acc": 0.8588833095343918203 },204 {205 "epoch": 0.14625228519195613,206 "grad_norm": 1.6077603667743245,207 "learning_rate": 9.652218495101894e-06,208 "loss": 0.44729223251342776,209 "step": 240,210 "token_acc": 0.85995841942315211 },212 {213 "epoch": 0.15234613040828762,214 "grad_norm": 1.2688011877880512,215 "learning_rate": 9.61513575008656e-06,216 "loss": 0.43803844451904295,217 "step": 250,218 "token_acc": 0.8627407782309685219 },220 {221 "epoch": 0.15843997562461914,222 "grad_norm": 1.178112411608835,223 "learning_rate": 9.576253596624367e-06,224 "loss": 0.43675899505615234,225 "step": 260,226 "token_acc": 0.8637918234089942227 },228 {229 "epoch": 0.16453382084095064,230 "grad_norm": 1.294840110909924,231 "learning_rate": 9.53558719458908e-06,232 "loss": 0.4456604480743408,233 "step": 270,234 "token_acc": 0.8607995996575384235 },236 {237 "epoch": 0.17062766605728213,238 "grad_norm": 1.2275948762976965,239 "learning_rate": 9.49315239952023e-06,240 "loss": 0.44009056091308596,241 "step": 280,242 "token_acc": 0.8624380989923378243 },244 {245 "epoch": 0.17672151127361366,246 "grad_norm": 1.1835184130640346,247 "learning_rate": 9.448965756441154e-06,248 "loss": 0.43228535652160643,249 "step": 290,250 "token_acc": 0.8642425086011517251 },252 {253 "epoch": 0.18281535648994515,254 "grad_norm": 1.0506109771841785,255 "learning_rate": 9.403044493408205e-06,256 "loss": 0.4331789970397949,257 "step": 300,258 "token_acc": 0.8650773124725752259 },260 {261 "epoch": 0.18890920170627665,262 "grad_norm": 1.2538833747077607,263 "learning_rate": 9.355406514793667e-06,264 "loss": 0.44378862380981443,265 "step": 310,266 "token_acc": 0.8612388746191983267 },268 {269 "epoch": 0.19500304692260817,270 "grad_norm": 1.1649745576637627,271 "learning_rate": 9.306070394304955e-06,272 "loss": 0.4216612339019775,273 "step": 320,274 "token_acc": 0.8665872154728236275 },276 {277 "epoch": 0.20109689213893966,278 "grad_norm": 1.1640287810040342,279 "learning_rate": 9.255055367742868e-06,280 "loss": 0.43276224136352537,281 "step": 330,282 "token_acc": 0.864183550146075283 },284 {285 "epoch": 0.2071907373552712,286 "grad_norm": 1.1205258611684763,287 "learning_rate": 9.202381325501683e-06,288 "loss": 0.42910175323486327,289 "step": 340,290 "token_acc": 0.8651370039640893291 },292 {293 "epoch": 0.21328458257160268,294 "grad_norm": 1.1044569461174318,295 "learning_rate": 9.148068804814032e-06,296 "loss": 0.425107479095459,297 "step": 350,298 "token_acc": 0.8655852823220787299 },300 {301 "epoch": 0.21937842778793418,302 "grad_norm": 1.256804160100686,303 "learning_rate": 9.092138981743588e-06,304 "loss": 0.4197092533111572,305 "step": 360,306 "token_acc": 0.8678029564108461307 },308 {309 "epoch": 0.2254722730042657,310 "grad_norm": 1.219596805077906,311 "learning_rate": 9.034613662928665e-06,312 "loss": 0.4218160629272461,313 "step": 370,314 "token_acc": 0.8669598748703018315 },316 {317 "epoch": 0.2315661182205972,318 "grad_norm": 1.0651000148469036,319 "learning_rate": 8.975515277079961e-06,320 "loss": 0.4222999095916748,321 "step": 380,322 "token_acc": 0.8668562219942147323 },324 {325 "epoch": 0.2376599634369287,326 "grad_norm": 1.1478789808745513,327 "learning_rate": 8.91486686623577e-06,328 "loss": 0.41972966194152833,329 "step": 390,330 "token_acc": 0.8667315262188772331 },332 {333 "epoch": 0.2437538086532602,334 "grad_norm": 1.0060533858058822,335 "learning_rate": 8.85269207677806e-06,336 "loss": 0.4143358707427979,337 "step": 400,338 "token_acc": 0.8689943563130941339 },340 {341 "epoch": 0.2498476538695917,342 "grad_norm": 1.2219261737292129,343 "learning_rate": 8.789015150212907e-06,344 "loss": 0.41486186981201173,345 "step": 410,346 "token_acc": 0.867653374528066347 },348 {349 "epoch": 0.25594149908592323,350 "grad_norm": 1.2842286146778168,351 "learning_rate": 8.72386091371891e-06,352 "loss": 0.4264723777770996,353 "step": 420,354 "token_acc": 0.865345114787771355 },356 {357 "epoch": 0.2620353443022547,358 "grad_norm": 1.0550559155752623,359 "learning_rate": 8.657254770467252e-06,360 "loss": 0.40860881805419924,361 "step": 430,362 "token_acc": 0.8694270527928576363 },364 {365 "epoch": 0.2681291895185862,366 "grad_norm": 1.1246909396790437,367 "learning_rate": 8.58922268971719e-06,368 "loss": 0.4148720264434814,369 "step": 440,370 "token_acc": 0.86849521403236371 },372 {373 "epoch": 0.2742230347349177,374 "grad_norm": 1.1877909840033853,375 "learning_rate": 8.51979119669081e-06,376 "loss": 0.4155715465545654,377 "step": 450,378 "token_acc": 0.8686248236499153379 },380 {381 "epoch": 0.28031687995124926,382 "grad_norm": 1.03946599413896,383 "learning_rate": 8.448987362231054e-06,384 "loss": 0.4156056880950928,385 "step": 460,386 "token_acc": 0.8682606492506055387 },388 {389 "epoch": 0.28641072516758076,390 "grad_norm": 1.1045440790462375,391 "learning_rate": 8.376838792246978e-06,392 "loss": 0.41259098052978516,393 "step": 470,394 "token_acc": 0.868615067345492395 },396 {397 "epoch": 0.29250457038391225,398 "grad_norm": 1.1044055109636997,399 "learning_rate": 8.303373616950408e-06,400 "loss": 0.41626744270324706,401 "step": 480,402 "token_acc": 0.867445116993405403 },404 {405 "epoch": 0.29859841560024375,406 "grad_norm": 1.0612884186160958,407 "learning_rate": 8.228620479888172e-06,408 "loss": 0.4087618350982666,409 "step": 490,410 "token_acc": 0.869433255622514411 },412 {413 "epoch": 0.30469226081657524,414 "grad_norm": 1.079879116921211,415 "learning_rate": 8.152608526774188e-06,416 "loss": 0.40863656997680664,417 "step": 500,418 "token_acc": 0.8705444341829626419 },420 {421 "epoch": 0.31078610603290674,422 "grad_norm": 1.0470334273877924,423 "learning_rate": 8.075367394125755e-06,424 "loss": 0.41130657196044923,425 "step": 510,426 "token_acc": 0.8699947913802195427 },428 {429 "epoch": 0.3168799512492383,430 "grad_norm": 1.2778777056879977,431 "learning_rate": 7.996927197708486e-06,432 "loss": 0.4074504852294922,433 "step": 520,434 "token_acc": 0.8711178129454153435 },436 {437 "epoch": 0.3229737964655698,438 "grad_norm": 1.133795250933889,439 "learning_rate": 7.917318520794395e-06,440 "loss": 0.4040180206298828,441 "step": 530,442 "token_acc": 0.8719991647774729443 },444 {445 "epoch": 0.3290676416819013,446 "grad_norm": 1.1320221274981666,447 "learning_rate": 7.836572402237683e-06,448 "loss": 0.4074112892150879,449 "step": 540,450 "token_acc": 0.8696679374619692451 },452 {453 "epoch": 0.3351614868982328,454 "grad_norm": 1.0153565229717176,455 "learning_rate": 7.754720324372924e-06,456 "loss": 0.4030743598937988,457 "step": 550,458 "token_acc": 0.8720831783254012459 },460 {461 "epoch": 0.34125533211456427,462 "grad_norm": 1.0985579621580885,463 "learning_rate": 7.67179420074032e-06,464 "loss": 0.3988363742828369,465 "step": 560,466 "token_acc": 0.8726780258889484467 },468 {469 "epoch": 0.3473491773308958,470 "grad_norm": 1.0584699143582574,471 "learning_rate": 7.587826363642845e-06,472 "loss": 0.4028042793273926,473 "step": 570,474 "token_acc": 0.8709437860238254475 },476 {477 "epoch": 0.3534430225472273,478 "grad_norm": 1.1632651891282637,479 "learning_rate": 7.502849551540106e-06,480 "loss": 0.3974143028259277,481 "step": 580,482 "token_acc": 0.8732772418431721483 },484 {485 "epoch": 0.3595368677635588,486 "grad_norm": 0.9585380945132779,487 "learning_rate": 7.4168968962838524e-06,488 "loss": 0.40021185874938964,489 "step": 590,490 "token_acc": 0.8715715660830257491 },492 {493 "epoch": 0.3656307129798903,494 "grad_norm": 0.939779800665415,495 "learning_rate": 7.330001910200111e-06,496 "loss": 0.39843976497650146,497 "step": 600,498 "token_acc": 0.8733910783350537499 },500 {501 "epoch": 0.3717245581962218,502 "grad_norm": 0.9815164073943617,503 "learning_rate": 7.242198473022958e-06,504 "loss": 0.3972899913787842,505 "step": 610,506 "token_acc": 0.8731910420095998507 },508 {509 "epoch": 0.3778184034125533,510 "grad_norm": 1.0569386302509218,511 "learning_rate": 7.15352081868506e-06,512 "loss": 0.4026960372924805,513 "step": 620,514 "token_acc": 0.8716591305210795515 },516 {517 "epoch": 0.38391224862888484,518 "grad_norm": 1.0897077358900225,519 "learning_rate": 7.0640035219701085e-06,520 "loss": 0.39238433837890624,521 "step": 630,522 "token_acc": 0.8741110700683207523 },524 {525 "epoch": 0.39000609384521634,526 "grad_norm": 1.0094259905078886,527 "learning_rate": 6.973681485032359e-06,528 "loss": 0.3934662342071533,529 "step": 640,530 "token_acc": 0.874180305698641531 },532 {533 "epoch": 0.39609993906154783,534 "grad_norm": 0.9880095870102604,535 "learning_rate": 6.8825899237885215e-06,536 "loss": 0.3929059743881226,537 "step": 650,538 "token_acc": 0.873847849697677539 },540 {541 "epoch": 0.40219378427787933,542 "grad_norm": 0.9583618057687778,543 "learning_rate": 6.7907643541873446e-06,544 "loss": 0.38638834953308104,545 "step": 660,546 "token_acc": 0.8764517709444076547 },548 {549 "epoch": 0.4082876294942108,550 "grad_norm": 1.1091462631909463,551 "learning_rate": 6.698240578362179e-06,552 "loss": 0.3935162782669067,553 "step": 670,554 "token_acc": 0.8743182876186542555 },556 {557 "epoch": 0.4143814747105424,558 "grad_norm": 0.959273015275344,559 "learning_rate": 6.6050546706719984e-06,560 "loss": 0.38172011375427245,561 "step": 680,562 "token_acc": 0.8772576395099669563 },564 {565 "epoch": 0.42047531992687387,566 "grad_norm": 1.0010757728338364,567 "learning_rate": 6.511242963636257e-06,568 "loss": 0.3927836179733276,569 "step": 690,570 "token_acc": 0.8740263817041508571 },572 {573 "epoch": 0.42656916514320536,574 "grad_norm": 1.045230237684538,575 "learning_rate": 6.416842033769106e-06,576 "loss": 0.38949809074401853,577 "step": 700,578 "token_acc": 0.8748742675586352579 },580 {581 "epoch": 0.43266301035953686,582 "grad_norm": 0.9849032327305663,583 "learning_rate": 6.321888687318457e-06,584 "loss": 0.39299988746643066,585 "step": 710,586 "token_acc": 0.8744398373706392587 },588 {589 "epoch": 0.43875685557586835,590 "grad_norm": 0.9773426657855283,591 "learning_rate": 6.2264199459155105e-06,592 "loss": 0.38987624645233154,593 "step": 720,594 "token_acc": 0.8749521585172907595 },596 {597 "epoch": 0.4448507007921999,598 "grad_norm": 1.037517468712357,599 "learning_rate": 6.130473032140272e-06,600 "loss": 0.38550682067871095,601 "step": 730,602 "token_acc": 0.8752092114104209603 },604 {605 "epoch": 0.4509445460085314,606 "grad_norm": 1.0310013780608072,607 "learning_rate": 6.0340853550087345e-06,608 "loss": 0.378936243057251,609 "step": 740,610 "token_acc": 0.878043851367452611 },612 {613 "epoch": 0.4570383912248629,614 "grad_norm": 0.8055934899750623,615 "learning_rate": 5.937294495387377e-06,616 "loss": 0.38777313232421873,617 "step": 750,618 "token_acc": 0.8762303990063655619 },620 {621 "epoch": 0.4631322364411944,622 "grad_norm": 1.0076731680308868,623 "learning_rate": 5.840138191340651e-06,624 "loss": 0.3867051601409912,625 "step": 760,626 "token_acc": 0.875447200037364627 },628 {629 "epoch": 0.4692260816575259,630 "grad_norm": 0.9392775195574543,631 "learning_rate": 5.7426543234171736e-06,632 "loss": 0.3799318552017212,633 "step": 770,634 "token_acc": 0.8780739671196323635 },636 {637 "epoch": 0.4753199268738574,638 "grad_norm": 0.9059297874010275,639 "learning_rate": 5.644880899880382e-06,640 "loss": 0.38845138549804686,641 "step": 780,642 "token_acc": 0.8756513846485855643 },644 {645 "epoch": 0.48141377209018893,646 "grad_norm": 1.0364591251718924,647 "learning_rate": 5.546856041889374e-06,648 "loss": 0.384658670425415,649 "step": 790,650 "token_acc": 0.8760285406658391651 },652 {653 "epoch": 0.4875076173065204,654 "grad_norm": 0.9573686942596932,655 "learning_rate": 5.448617968635741e-06,656 "loss": 0.3791942596435547,657 "step": 800,658 "token_acc": 0.8779162415307187659 },660 {661 "epoch": 0.4936014625228519,662 "grad_norm": 0.9636242802763855,663 "learning_rate": 5.35020498244219e-06,664 "loss": 0.37176291942596434,665 "step": 810,666 "token_acc": 0.8793090876456928667 },668 {669 "epoch": 0.4996953077391834,670 "grad_norm": 1.037660587481492,671 "learning_rate": 5.251655453828728e-06,672 "loss": 0.37394251823425295,673 "step": 820,674 "token_acc": 0.8786210190654307675 },676 {677 "epoch": 0.505789152955515,678 "grad_norm": 1.0719330406024963,679 "learning_rate": 5.153007806552275e-06,680 "loss": 0.3745760679244995,681 "step": 830,682 "token_acc": 0.8784241641412887683 },684 {685 "epoch": 0.5118829981718465,686 "grad_norm": 0.8899515496236061,687 "learning_rate": 5.054300502625517e-06,688 "loss": 0.3706503868103027,689 "step": 840,690 "token_acc": 0.8798184912767585691 },692 {693 "epoch": 0.517976843388178,694 "grad_norm": 0.9136772226114551,695 "learning_rate": 4.9555720273208475e-06,696 "loss": 0.3767611742019653,697 "step": 850,698 "token_acc": 0.8780427238279765699 },700 {701 "epoch": 0.5240706886045094,702 "grad_norm": 0.9760538746168989,703 "learning_rate": 4.856860874165218e-06,704 "loss": 0.37979438304901125,705 "step": 860,706 "token_acc": 0.8784071947906439707 },708 {709 "epoch": 0.5301645338208409,710 "grad_norm": 0.9424993647974058,711 "learning_rate": 4.758205529931808e-06,712 "loss": 0.3839302062988281,713 "step": 870,714 "token_acc": 0.8770481761661205715 },716 {717 "epoch": 0.5362583790371724,718 "grad_norm": 1.0293112779306877,719 "learning_rate": 4.659644459634293e-06,720 "loss": 0.3767723321914673,721 "step": 880,722 "token_acc": 0.8782181679486365723 },724 {725 "epoch": 0.5423522242535039,726 "grad_norm": 1.0743397927299763,727 "learning_rate": 4.56121609152961e-06,728 "loss": 0.3791919946670532,729 "step": 890,730 "token_acc": 0.8769342677312787731 },732 {733 "epoch": 0.5484460694698354,734 "grad_norm": 0.8651643017417293,735 "learning_rate": 4.462958802135069e-06,736 "loss": 0.36331801414489745,737 "step": 900,738 "token_acc": 0.8819762679763837739 },740 {741 "epoch": 0.5545399146861669,742 "grad_norm": 0.9197439306994798,743 "learning_rate": 4.364910901265607e-06,744 "loss": 0.3720353603363037,745 "step": 910,746 "token_acc": 0.8795370329732339747 },748 {749 "epoch": 0.5606337599024985,750 "grad_norm": 0.9973864478854872,751 "learning_rate": 4.2671106170970734e-06,752 "loss": 0.37818198204040526,753 "step": 920,754 "token_acc": 0.8787091854009224755 },756 {757 "epoch": 0.56672760511883,758 "grad_norm": 0.9979320322546561,759 "learning_rate": 4.169596081261332e-06,760 "loss": 0.368232798576355,761 "step": 930,762 "token_acc": 0.8808049967885766763 },764 {765 "epoch": 0.5728214503351615,766 "grad_norm": 0.9817455772913783,767 "learning_rate": 4.072405313979021e-06,768 "loss": 0.37091827392578125,769 "step": 940,770 "token_acc": 0.8796466097957818771 },772 {773 "epoch": 0.578915295551493,774 "grad_norm": 1.0935297334377472,775 "learning_rate": 3.975576209235726e-06,776 "loss": 0.3674028396606445,777 "step": 950,778 "token_acc": 0.8807917695163083779 },780 {781 "epoch": 0.5850091407678245,782 "grad_norm": 0.9835469765967159,783 "learning_rate": 3.879146520007399e-06,784 "loss": 0.3728478908538818,785 "step": 960,786 "token_acc": 0.8795413152600885787 },788 {789 "epoch": 0.591102985984156,790 "grad_norm": 0.9625183356689964,791 "learning_rate": 3.7831538435407344e-06,792 "loss": 0.37494525909423826,793 "step": 970,794 "token_acc": 0.8792245580635571795 },796 {797 "epoch": 0.5971968312004875,798 "grad_norm": 0.9012795424730173,799 "learning_rate": 3.687635606694271e-06,800 "loss": 0.3702352046966553,801 "step": 980,802 "token_acc": 0.8801223453080008803 },804 {805 "epoch": 0.603290676416819,806 "grad_norm": 0.9782757486531443,807 "learning_rate": 3.592629051345936e-06,808 "loss": 0.3673159837722778,809 "step": 990,810 "token_acc": 0.8810825035648933811 },812 {813 "epoch": 0.6093845216331505,814 "grad_norm": 1.0059100640922563,815 "learning_rate": 3.4981712198726956e-06,816 "loss": 0.3642214059829712,817 "step": 1000,818 "token_acc": 0.8818312088488447819 },820 {821 "epoch": 0.615478366849482,822 "grad_norm": 0.9395189399708234,823 "learning_rate": 3.4042989407079986e-06,824 "loss": 0.3784639358520508,825 "step": 1010,826 "token_acc": 0.8780194366406157827 },828 {829 "epoch": 0.6215722120658135,830 "grad_norm": 1.0425592930772825,831 "learning_rate": 3.311048813982627e-06,832 "loss": 0.36695384979248047,833 "step": 1020,834 "token_acc": 0.8809777292779815835 },836 {837 "epoch": 0.6276660572821451,838 "grad_norm": 0.9146308056797927,839 "learning_rate": 3.218457197254583e-06,840 "loss": 0.36698212623596194,841 "step": 1030,842 "token_acc": 0.8810339710207495843 },844 {845 "epoch": 0.6337599024984766,846 "grad_norm": 0.976263078958663,847 "learning_rate": 3.1265601913335196e-06,848 "loss": 0.365465784072876,849 "step": 1040,850 "token_acc": 0.8814162812670944851 },852 {853 "epoch": 0.6398537477148081,854 "grad_norm": 1.0567379406046713,855 "learning_rate": 3.035393626205306e-06,856 "loss": 0.3610874891281128,857 "step": 1050,858 "token_acc": 0.8824792140002385859 },860 {861 "epoch": 0.6459475929311396,862 "grad_norm": 1.0205537815943757,863 "learning_rate": 2.944993047062161e-06,864 "loss": 0.35759830474853516,865 "step": 1060,866 "token_acc": 0.8834624031976018867 },868 {869 "epoch": 0.6520414381474711,870 "grad_norm": 1.0280714401242652,871 "learning_rate": 2.8553937004438425e-06,872 "loss": 0.3574142217636108,873 "step": 1070,874 "token_acc": 0.884169503378651875 },876 {877 "epoch": 0.6581352833638026,878 "grad_norm": 1.0187298702407688,879 "learning_rate": 2.766630520495277e-06,880 "loss": 0.36029987335205077,881 "step": 1080,882 "token_acc": 0.8823869756562952883 },884 {885 "epoch": 0.664229128580134,886 "grad_norm": 0.9191494153561297,887 "learning_rate": 2.67873811534598e-06,888 "loss": 0.35897092819213866,889 "step": 1090,890 "token_acc": 0.8827260508533868891 },892 {893 "epoch": 0.6703229737964655,894 "grad_norm": 0.9492740813391064,895 "learning_rate": 2.591750753616596e-06,896 "loss": 0.36168532371520995,897 "step": 1100,898 "token_acc": 0.8825941425209475899 },900 {901 "epoch": 0.676416819012797,902 "grad_norm": 0.9644543574186545,903 "learning_rate": 2.505702351057804e-06,904 "loss": 0.3665107488632202,905 "step": 1110,906 "token_acc": 0.8816928952036972907 },908 {909 "epoch": 0.6825106642291285,910 "grad_norm": 0.9521683470371731,911 "learning_rate": 2.4206264573268174e-06,912 "loss": 0.35790448188781737,913 "step": 1120,914 "token_acc": 0.8832886728694526915 },916 {917 "epoch": 0.68860450944546,918 "grad_norm": 1.0783164983743936,919 "learning_rate": 2.336556242906608e-06,920 "loss": 0.3561516284942627,921 "step": 1130,922 "token_acc": 0.8839432945670233923 },924 {925 "epoch": 0.6946983546617916,926 "grad_norm": 0.9994299291097577,927 "learning_rate": 2.2535244861729707e-06,928 "loss": 0.3557067632675171,929 "step": 1140,930 "token_acc": 0.8837923958883728931 },932 {933 "epoch": 0.7007921998781231,934 "grad_norm": 1.039214819811771,935 "learning_rate": 2.1715635606144653e-06,936 "loss": 0.3563429832458496,937 "step": 1150,938 "token_acc": 0.8836427544336156939 },940 {941 "epoch": 0.7068860450944546,942 "grad_norm": 0.8549094000634878,943 "learning_rate": 2.0907054222102367e-06,944 "loss": 0.35337374210357664,945 "step": 1160,946 "token_acc": 0.8852147256677358947 },948 {949 "epoch": 0.7129798903107861,950 "grad_norm": 0.894156191232295,951 "learning_rate": 2.0109815969705922e-06,952 "loss": 0.359290337562561,953 "step": 1170,954 "token_acc": 0.8828725266946272955 },956 {957 "epoch": 0.7190737355271176,958 "grad_norm": 0.8673526133846996,959 "learning_rate": 1.9324231686452478e-06,960 "loss": 0.35991313457489016,961 "step": 1180,962 "token_acc": 0.8837700799671174963 },964 {965 "epoch": 0.7251675807434491,966 "grad_norm": 0.9356232121590031,967 "learning_rate": 1.8550607666039877e-06,968 "loss": 0.3538203716278076,969 "step": 1190,970 "token_acc": 0.8850202284200351971 },972 {973 "epoch": 0.7312614259597806,974 "grad_norm": 1.0163312252270116,975 "learning_rate": 1.7789245538944971e-06,976 "loss": 0.3607466459274292,977 "step": 1200,978 "token_acc": 0.8824661130842316979 },980 {981 "epoch": 0.7373552711761121,982 "grad_norm": 0.8390316456040804,983 "learning_rate": 1.7040442154820036e-06,984 "loss": 0.35505869388580324,985 "step": 1210,986 "token_acc": 0.8845901901507859987 },988 {989 "epoch": 0.7434491163924436,990 "grad_norm": 0.921086850463397,991 "learning_rate": 1.6304489466753237e-06,992 "loss": 0.35682291984558107,993 "step": 1220,994 "token_acc": 0.884017590582417995 },996 {997 "epoch": 0.7495429616087751,998 "grad_norm": 0.8352814372993298,999 "learning_rate": 1.5581674417438143e-06,1000 "loss": 0.3599454164505005,1001 "step": 1230,1002 "token_acc": 0.88306102230766131003 },1004 {1005 "epoch": 0.7556368068251066,1006 "grad_norm": 0.9561368940432438,1007 "learning_rate": 1.4872278827296855e-06,1008 "loss": 0.3544511079788208,1009 "step": 1240,1010 "token_acc": 0.8849712411836661011 },1012 {1013 "epoch": 0.7617306520414382,1014 "grad_norm": 0.9963256225377098,1015 "learning_rate": 1.417657928460029e-06,1016 "loss": 0.35143122673034666,1017 "step": 1250,1018 "token_acc": 0.88545979778526721019 },1020 {1021 "epoch": 0.7678244972577697,1022 "grad_norm": 1.0464860200353496,1023 "learning_rate": 1.349484703762834e-06,1024 "loss": 0.3545159101486206,1025 "step": 1260,1026 "token_acc": 0.88480011918680911027 },1028 {1029 "epoch": 0.7739183424741012,1030 "grad_norm": 0.9553675018651967,1031 "learning_rate": 1.2827347888912057e-06,1032 "loss": 0.3540821552276611,1033 "step": 1270,1034 "token_acc": 0.88454317507048231035 },1036 {1037 "epoch": 0.7800121876904327,1038 "grad_norm": 0.9171124221466627,1039 "learning_rate": 1.2174342091599277e-06,1040 "loss": 0.3459270477294922,1041 "step": 1280,1042 "token_acc": 0.88763783702552731043 },1044 {1045 "epoch": 0.7861060329067642,1046 "grad_norm": 0.9897434740336704,1047 "learning_rate": 1.1536084247983626e-06,1048 "loss": 0.3577150821685791,1049 "step": 1290,1050 "token_acc": 0.88424983027834351051 },1052 {1053 "epoch": 0.7921998781230957,1054 "grad_norm": 0.88979092902762,1055 "learning_rate": 1.0912823210237033e-06,1056 "loss": 0.350811505317688,1057 "step": 1300,1058 "token_acc": 0.88560083733448521059 },1060 {1061 "epoch": 0.7982937233394272,1062 "grad_norm": 0.9287859784083828,1063 "learning_rate": 1.0304801983383989e-06,1064 "loss": 0.3551754951477051,1065 "step": 1310,1066 "token_acc": 0.88484105385926611067 },1068 {1069 "epoch": 0.8043875685557587,1070 "grad_norm": 0.8802985747226686,1071 "learning_rate": 9.712257630555589e-07,1072 "loss": 0.35124433040618896,1073 "step": 1320,1074 "token_acc": 0.88570881878981941075 },1076 {1077 "epoch": 0.8104814137720902,1078 "grad_norm": 0.9867993671885138,1079 "learning_rate": 9.135421180560394e-07,1080 "loss": 0.3533953666687012,1081 "step": 1330,1082 "token_acc": 0.88476300990806031083 },1084 {1085 "epoch": 0.8165752589884216,1086 "grad_norm": 0.926446790364043,1087 "learning_rate": 8.574517537807897e-07,1088 "loss": 0.345960807800293,1089 "step": 1340,1090 "token_acc": 0.88766876632543381091 },1092 {1093 "epoch": 0.8226691042047533,1094 "grad_norm": 0.9083144656784397,1095 "learning_rate": 8.029765394619899e-07,1096 "loss": 0.35233092308044434,1097 "step": 1350,1098 "token_acc": 0.88522708217782191099 },1100 {1101 "epoch": 0.8287629494210847,1102 "grad_norm": 0.8865701179019319,1103 "learning_rate": 7.501377145963939e-07,1104 "loss": 0.35347394943237304,1105 "step": 1360,1106 "token_acc": 0.88485074919175271107 },1108 {1109 "epoch": 0.8348567946374162,1110 "grad_norm": 0.8797844443235806,1111 "learning_rate": 6.98955880664205e-07,1112 "loss": 0.35233142375946047,1113 "step": 1370,1114 "token_acc": 0.88574946265729021115 },1116 {1117 "epoch": 0.8409506398537477,1118 "grad_norm": 0.985930499180468,1119 "learning_rate": 6.494509930967019e-07,1120 "loss": 0.3484508991241455,1121 "step": 1380,1122 "token_acc": 0.88622266635690391123 },1124 {1125 "epoch": 0.8470444850700792,1126 "grad_norm": 0.8385926015490823,1127 "learning_rate": 6.016423534957616e-07,1128 "loss": 0.34513344764709475,1129 "step": 1390,1130 "token_acc": 0.887666304203851131 },1132 {1133 "epoch": 0.8531383302864107,1134 "grad_norm": 0.9469060182104153,1135 "learning_rate": 5.555486021082979e-07,1136 "loss": 0.3453853130340576,1137 "step": 1400,1138 "token_acc": 0.88729801904014731139 },1140 {1141 "epoch": 0.8592321755027422,1142 "grad_norm": 1.0619116209691746,1143 "learning_rate": 5.111877105585672e-07,1144 "loss": 0.35715694427490235,1145 "step": 1410,1146 "token_acc": 0.88405848283655891147 },1148 {1149 "epoch": 0.8653260207190737,1150 "grad_norm": 0.9990471419637711,1151 "learning_rate": 4.6857697484116006e-07,1152 "loss": 0.34844698905944826,1153 "step": 1420,1154 "token_acc": 0.88615957469574181155 },1156 {1157 "epoch": 0.8714198659354052,1158 "grad_norm": 0.8653174829680845,1159 "learning_rate": 4.277330085774156e-07,1160 "loss": 0.34473817348480223,1161 "step": 1430,1162 "token_acc": 0.88691247120973351163 },1164 {1165 "epoch": 0.8775137111517367,1166 "grad_norm": 0.978323586867761,1167 "learning_rate": 3.886717365378867e-07,1168 "loss": 0.3523882865905762,1169 "step": 1440,1170 "token_acc": 0.88490344803480131171 },1172 {1173 "epoch": 0.8836075563680682,1174 "grad_norm": 1.0140389777919647,1175 "learning_rate": 3.5140838843339073e-07,1176 "loss": 0.3476292848587036,1177 "step": 1450,1178 "token_acc": 0.88663299340057671179 },1180 {1181 "epoch": 0.8897014015843998,1182 "grad_norm": 1.0064657138214737,1183 "learning_rate": 3.159574929770515e-07,1184 "loss": 0.35365211963653564,1185 "step": 1460,1186 "token_acc": 0.88524653853855051187 },1188 {1189 "epoch": 0.8957952468007313,1190 "grad_norm": 0.9324871915195588,1191 "learning_rate": 2.8233287221965555e-07,1192 "loss": 0.3441819190979004,1193 "step": 1470,1194 "token_acc": 0.88710958783189411195 },1196 {1197 "epoch": 0.9018890920170628,1198 "grad_norm": 0.9055988245681192,1199 "learning_rate": 2.5054763616053967e-07,1200 "loss": 0.34738845825195314,