google-cloud-partnership/gemma-2-2b-it-lora-sql
056
1{2 "best_metric": null,3 "best_model_checkpoint": null,4 "epoch": 2.9977046671767407,5 "eval_steps": 500,6 "global_step": 1959,7 "is_hyper_param_search": false,8 "is_local_process_zero": true,9 "is_world_process_zero": true,10 "log_history": [11 {12 "epoch": 0.015302218821729151,13 "grad_norm": 2.9595158525528062,14 "learning_rate": 1.0204081632653061e-05,15 "loss": 1.7025,16 "step": 1017 },18 {19 "epoch": 0.030604437643458302,20 "grad_norm": 1.263751808272248,21 "learning_rate": 2.0408163265306123e-05,22 "loss": 1.4094,23 "step": 2024 },25 {26 "epoch": 0.045906656465187455,27 "grad_norm": 1.1314499693827325,28 "learning_rate": 3.061224489795919e-05,29 "loss": 1.0742,30 "step": 3031 },32 {33 "epoch": 0.061208875286916604,34 "grad_norm": 0.43429385320294256,35 "learning_rate": 4.0816326530612245e-05,36 "loss": 0.8975,37 "step": 4038 },39 {40 "epoch": 0.07651109410864575,41 "grad_norm": 0.37910893323587813,42 "learning_rate": 5.102040816326531e-05,43 "loss": 0.7694,44 "step": 5045 },46 {47 "epoch": 0.09181331293037491,48 "grad_norm": 0.32985782659377816,49 "learning_rate": 6.122448979591838e-05,50 "loss": 0.6667,51 "step": 6052 },53 {54 "epoch": 0.10711553175210406,55 "grad_norm": 0.27993689719153514,56 "learning_rate": 7.142857142857143e-05,57 "loss": 0.6143,58 "step": 7059 },60 {61 "epoch": 0.12241775057383321,62 "grad_norm": 0.2562350918748776,63 "learning_rate": 8.163265306122449e-05,64 "loss": 0.5736,65 "step": 8066 },67 {68 "epoch": 0.13771996939556236,69 "grad_norm": 0.2627549443187762,70 "learning_rate": 9.183673469387756e-05,71 "loss": 0.5605,72 "step": 9073 },74 {75 "epoch": 0.1530221882172915,76 "grad_norm": 0.25450163445897056,77 "learning_rate": 0.00010204081632653062,78 "loss": 0.5425,79 "step": 10080 },81 {82 "epoch": 0.16832440703902066,83 "grad_norm": 0.265185130228763,84 "learning_rate": 0.00011224489795918367,85 "loss": 0.5417,86 "step": 11087 },88 {89 "epoch": 0.18362662586074982,90 "grad_norm": 0.2600738826510011,91 "learning_rate": 0.00012244897959183676,92 "loss": 0.5349,93 "step": 12094 },95 {96 "epoch": 0.19892884468247896,97 "grad_norm": 0.27451283782332153,98 "learning_rate": 0.0001326530612244898,99 "loss": 0.5225,100 "step": 130101 },102 {103 "epoch": 0.21423106350420812,104 "grad_norm": 0.29276216948080613,105 "learning_rate": 0.00014285714285714287,106 "loss": 0.5148,107 "step": 140108 },109 {110 "epoch": 0.22953328232593725,111 "grad_norm": 0.25373117999248507,112 "learning_rate": 0.0001530612244897959,113 "loss": 0.5108,114 "step": 150115 },116 {117 "epoch": 0.24483550114766642,118 "grad_norm": 0.26479254050664824,119 "learning_rate": 0.00016326530612244898,120 "loss": 0.5061,121 "step": 160122 },123 {124 "epoch": 0.26013771996939555,125 "grad_norm": 0.27232811822105624,126 "learning_rate": 0.00017346938775510205,127 "loss": 0.5065,128 "step": 170129 },130 {131 "epoch": 0.2754399387911247,132 "grad_norm": 0.26418337252250673,133 "learning_rate": 0.00018367346938775512,134 "loss": 0.4967,135 "step": 180136 },137 {138 "epoch": 0.2907421576128539,139 "grad_norm": 0.2503450300406005,140 "learning_rate": 0.00019387755102040816,141 "loss": 0.4998,142 "step": 190143 },144 {145 "epoch": 0.306044376434583,146 "grad_norm": 0.2339540170507543,147 "learning_rate": 0.0001999974597101728,148 "loss": 0.4989,149 "step": 200150 },151 {152 "epoch": 0.32134659525631215,153 "grad_norm": 0.23446730330407825,154 "learning_rate": 0.0001999688829317862,155 "loss": 0.4895,156 "step": 210157 },158 {159 "epoch": 0.3366488140780413,160 "grad_norm": 0.23685036500213205,161 "learning_rate": 0.00019990856311693857,162 "loss": 0.4898,163 "step": 220164 },165 {166 "epoch": 0.3519510328997705,167 "grad_norm": 0.2396529148643123,168 "learning_rate": 0.00019981651941893068,169 "loss": 0.4881,170 "step": 230171 },172 {173 "epoch": 0.36725325172149964,174 "grad_norm": 0.22794906865901965,175 "learning_rate": 0.0001996927810643216,176 "loss": 0.4825,177 "step": 240178 },179 {180 "epoch": 0.38255547054322875,181 "grad_norm": 0.21749849325438408,182 "learning_rate": 0.00019953738734364843,183 "loss": 0.4905,184 "step": 250185 },186 {187 "epoch": 0.3978576893649579,188 "grad_norm": 0.21941306857106413,189 "learning_rate": 0.00019935038759895038,190 "loss": 0.4844,191 "step": 260192 },193 {194 "epoch": 0.4131599081866871,195 "grad_norm": 0.2106883472247568,196 "learning_rate": 0.0001991318412081012,197 "loss": 0.4832,198 "step": 270199 },200 {201 "epoch": 0.42846212700841624,202 "grad_norm": 0.20643151525949935,203 "learning_rate": 0.00019888181756595513,204 "loss": 0.4732,205 "step": 280206 },207 {208 "epoch": 0.44376434583014535,209 "grad_norm": 0.21375448358620805,210 "learning_rate": 0.0001986003960623118,211 "loss": 0.4777,212 "step": 290213 },214 {215 "epoch": 0.4590665646518745,216 "grad_norm": 0.2078386748706879,217 "learning_rate": 0.0001982876660567078,218 "loss": 0.4773,219 "step": 300220 },221 {222 "epoch": 0.4743687834736037,223 "grad_norm": 0.20709767688640485,224 "learning_rate": 0.00019794372685004232,225 "loss": 0.4774,226 "step": 310227 },228 {229 "epoch": 0.48967100229533284,230 "grad_norm": 0.20114204358521104,231 "learning_rate": 0.00019756868765304637,232 "loss": 0.4724,233 "step": 320234 },235 {236 "epoch": 0.504973221117062,237 "grad_norm": 0.2047995080216857,238 "learning_rate": 0.000197162667551605,239 "loss": 0.4723,240 "step": 330241 },242 {243 "epoch": 0.5202754399387911,244 "grad_norm": 0.2065404899680565,245 "learning_rate": 0.00019672579546894418,246 "loss": 0.4744,247 "step": 340248 },249 {250 "epoch": 0.5355776587605203,251 "grad_norm": 0.20339328597837086,252 "learning_rate": 0.00019625821012469392,253 "loss": 0.469,254 "step": 350255 },256 {257 "epoch": 0.5508798775822494,258 "grad_norm": 0.20269051264889382,259 "learning_rate": 0.0001957600599908406,260 "loss": 0.4652,261 "step": 360262 },263 {264 "epoch": 0.5661820964039785,265 "grad_norm": 0.20140204074578216,266 "learning_rate": 0.00019523150324458297,267 "loss": 0.4663,268 "step": 370269 },270 {271 "epoch": 0.5814843152257078,272 "grad_norm": 0.20145479660046747,273 "learning_rate": 0.0001946727077181062,274 "loss": 0.4647,275 "step": 380276 },277 {278 "epoch": 0.5967865340474369,279 "grad_norm": 0.19812410832421173,280 "learning_rate": 0.00019408385084529014,281 "loss": 0.4669,282 "step": 390283 },284 {285 "epoch": 0.612088752869166,286 "grad_norm": 0.20593747645685082,287 "learning_rate": 0.0001934651196053692,288 "loss": 0.4606,289 "step": 400290 },291 {292 "epoch": 0.6273909716908952,293 "grad_norm": 0.19985586154896637,294 "learning_rate": 0.00019281671046356057,295 "loss": 0.465,296 "step": 410297 },298 {299 "epoch": 0.6426931905126243,300 "grad_norm": 0.18804149710765375,301 "learning_rate": 0.0001921388293086812,302 "loss": 0.4591,303 "step": 420304 },305 {306 "epoch": 0.6579954093343535,307 "grad_norm": 0.20403982281128524,308 "learning_rate": 0.00019143169138777176,309 "loss": 0.4612,310 "step": 430311 },312 {313 "epoch": 0.6732976281560826,314 "grad_norm": 0.19472172680549107,315 "learning_rate": 0.00019069552123774966,316 "loss": 0.4535,317 "step": 440318 },319 {320 "epoch": 0.6885998469778117,321 "grad_norm": 0.18853093267297413,322 "learning_rate": 0.00018993055261411188,323 "loss": 0.4536,324 "step": 450325 },326 {327 "epoch": 0.703902065799541,328 "grad_norm": 0.1824795154817547,329 "learning_rate": 0.0001891370284167108,330 "loss": 0.4533,331 "step": 460332 },333 {334 "epoch": 0.7192042846212701,335 "grad_norm": 0.19623573820167492,336 "learning_rate": 0.00018831520061262657,337 "loss": 0.4608,338 "step": 470339 },340 {341 "epoch": 0.7345065034429993,342 "grad_norm": 0.1894732171051352,343 "learning_rate": 0.00018746533015615997,344 "loss": 0.4561,345 "step": 480346 },347 {348 "epoch": 0.7498087222647284,349 "grad_norm": 0.1956746346911804,350 "learning_rate": 0.00018658768690597198,351 "loss": 0.4562,352 "step": 490353 },354 {355 "epoch": 0.7651109410864575,356 "grad_norm": 0.19485019146231133,357 "learning_rate": 0.00018568254953939573,358 "loss": 0.4547,359 "step": 500360 },361 {362 "epoch": 0.7804131599081867,363 "grad_norm": 0.1900932930656561,364 "learning_rate": 0.0001847502054639483,365 "loss": 0.4563,366 "step": 510367 },368 {369 "epoch": 0.7957153787299158,370 "grad_norm": 0.18608837489031835,371 "learning_rate": 0.00018379095072607052,372 "loss": 0.4546,373 "step": 520374 },375 {376 "epoch": 0.811017597551645,377 "grad_norm": 0.19229921508866923,378 "learning_rate": 0.0001828050899171234,379 "loss": 0.4506,380 "step": 530381 },382 {383 "epoch": 0.8263198163733741,384 "grad_norm": 0.20164999528455674,385 "learning_rate": 0.00018179293607667178,386 "loss": 0.4528,387 "step": 540388 },389 {390 "epoch": 0.8416220351951033,391 "grad_norm": 0.18962588415494633,392 "learning_rate": 0.00018075481059308488,393 "loss": 0.4501,394 "step": 550395 },396 {397 "epoch": 0.8569242540168325,398 "grad_norm": 0.1878318467581915,399 "learning_rate": 0.00017969104310148627,400 "loss": 0.4489,401 "step": 560402 },403 {404 "epoch": 0.8722264728385616,405 "grad_norm": 0.19855697462159105,406 "learning_rate": 0.00017860197137908504,407 "loss": 0.4486,408 "step": 570409 },410 {411 "epoch": 0.8875286916602907,412 "grad_norm": 0.18806947832467016,413 "learning_rate": 0.00017748794123792169,414 "loss": 0.449,415 "step": 580416 },417 {418 "epoch": 0.9028309104820199,419 "grad_norm": 0.18547154568221744,420 "learning_rate": 0.00017634930641506272,421 "loss": 0.4468,422 "step": 590423 },424 {425 "epoch": 0.918133129303749,426 "grad_norm": 0.1988415349574148,427 "learning_rate": 0.00017518642846027876,428 "loss": 0.4447,429 "step": 600430 },431 {432 "epoch": 0.9334353481254782,433 "grad_norm": 0.1971157063292002,434 "learning_rate": 0.00017399967662124204,435 "loss": 0.4496,436 "step": 610437 },438 {439 "epoch": 0.9487375669472073,440 "grad_norm": 0.18821213785618154,441 "learning_rate": 0.00017278942772627954,442 "loss": 0.4442,443 "step": 620444 },445 {446 "epoch": 0.9640397857689365,447 "grad_norm": 0.1863099123502169,448 "learning_rate": 0.00017155606606471873,449 "loss": 0.4428,450 "step": 630451 },452 {453 "epoch": 0.9793420045906657,454 "grad_norm": 0.1877422977434543,455 "learning_rate": 0.00017029998326486485,456 "loss": 0.4431,457 "step": 640458 },459 {460 "epoch": 0.9946442234123948,461 "grad_norm": 0.1976160670120698,462 "learning_rate": 0.00016902157816964724,463 "loss": 0.4382,464 "step": 650465 },466 {467 "epoch": 1.009946442234124,468 "grad_norm": 0.18992306538475748,469 "learning_rate": 0.0001677212567099752,470 "loss": 0.4353,471 "step": 660472 },473 {474 "epoch": 1.025248661055853,475 "grad_norm": 0.19209926834930846,476 "learning_rate": 0.00016639943177584302,477 "loss": 0.422,478 "step": 670479 },480 {481 "epoch": 1.0405508798775822,482 "grad_norm": 0.1862611696289539,483 "learning_rate": 0.00016505652308522546,484 "loss": 0.4166,485 "step": 680486 },487 {488 "epoch": 1.0558530986993113,489 "grad_norm": 0.19413670929825885,490 "learning_rate": 0.00016369295705080493,491 "loss": 0.4214,492 "step": 690493 },494 {495 "epoch": 1.0711553175210407,496 "grad_norm": 0.19044466403960753,497 "learning_rate": 0.00016230916664457303,498 "loss": 0.4226,499 "step": 700500 },501 {502 "epoch": 1.0864575363427698,503 "grad_norm": 0.20537259284486634,504 "learning_rate": 0.00016090559126034955,505 "loss": 0.4206,506 "step": 710507 },508 {509 "epoch": 1.1017597551644989,510 "grad_norm": 0.19548453583302455,511 "learning_rate": 0.00015948267657426172,512 "loss": 0.4258,513 "step": 720514 },515 {516 "epoch": 1.117061973986228,517 "grad_norm": 0.19233863084054012,518 "learning_rate": 0.00015804087440322937,519 "loss": 0.4212,520 "step": 730521 },522 {523 "epoch": 1.132364192807957,524 "grad_norm": 0.20059506523438514,525 "learning_rate": 0.00015658064256149972,526 "loss": 0.4248,527 "step": 740528 },529 {530 "epoch": 1.1476664116296864,531 "grad_norm": 0.19781190556296033,532 "learning_rate": 0.00015510244471527798,533 "loss": 0.419,534 "step": 750535 },536 {537 "epoch": 1.1629686304514155,538 "grad_norm": 0.1978522622616877,539 "learning_rate": 0.0001536067502355,540 "loss": 0.4156,541 "step": 760542 },543 {544 "epoch": 1.1782708492731446,545 "grad_norm": 0.19356090367390197,546 "learning_rate": 0.00015209403404879303,547 "loss": 0.4176,548 "step": 770549 },550 {551 "epoch": 1.1935730680948737,552 "grad_norm": 0.21041098882140832,553 "learning_rate": 0.0001505647764866729,554 "loss": 0.4155,555 "step": 780556 },557 {558 "epoch": 1.2088752869166028,559 "grad_norm": 0.19309297495512096,560 "learning_rate": 0.00014901946313302452,561 "loss": 0.4125,562 "step": 790563 },564 {565 "epoch": 1.2241775057383322,566 "grad_norm": 0.20988205146033515,567 "learning_rate": 0.0001474585846699151,568 "loss": 0.4198,569 "step": 800570 },571 {572 "epoch": 1.2394797245600613,573 "grad_norm": 0.19899429014402967,574 "learning_rate": 0.00014588263672178812,575 "loss": 0.4139,576 "step": 810577 },578 {579 "epoch": 1.2547819433817904,580 "grad_norm": 0.19678065811835893,581 "learning_rate": 0.00014429211969808808,582 "loss": 0.4168,583 "step": 820584 },585 {586 "epoch": 1.2700841622035195,587 "grad_norm": 0.20776458272762527,588 "learning_rate": 0.00014268753863436602,589 "loss": 0.4137,590 "step": 830591 },592 {593 "epoch": 1.2853863810252486,594 "grad_norm": 0.2056945302468653,595 "learning_rate": 0.00014106940303191583,596 "loss": 0.4166,597 "step": 840598 },599 {600 "epoch": 1.300688599846978,601 "grad_norm": 0.20731916359275016,602 "learning_rate": 0.000139438226695993,603 "loss": 0.4179,604 "step": 850605 },606 {607 "epoch": 1.315990818668707,608 "grad_norm": 0.2001144508118885,609 "learning_rate": 0.00013779452757266617,610 "loss": 0.4131,611 "step": 860612 },613 {614 "epoch": 1.3312930374904361,615 "grad_norm": 0.19624161193905473,616 "learning_rate": 0.00013613882758435435,617 "loss": 0.4089,618 "step": 870619 },620 {621 "epoch": 1.3465952563121653,622 "grad_norm": 0.20129114730483852,623 "learning_rate": 0.0001344716524641012,624 "loss": 0.4149,625 "step": 880626 },627 {628 "epoch": 1.3618974751338944,629 "grad_norm": 0.207327826679874,630 "learning_rate": 0.0001327935315886395,631 "loss": 0.4097,632 "step": 890633 },634 {635 "epoch": 1.3771996939556237,636 "grad_norm": 0.2029298678382067,637 "learning_rate": 0.00013110499781029874,638 "loss": 0.4132,639 "step": 900640 },641 {642 "epoch": 1.3925019127773526,643 "grad_norm": 0.20764777212748992,644 "learning_rate": 0.00012940658728780862,645 "loss": 0.4142,646 "step": 910647 },648 {649 "epoch": 1.407804131599082,650 "grad_norm": 0.2017977764168179,651 "learning_rate": 0.00012769883931605333,652 "loss": 0.4212,653 "step": 920654 },655 {656 "epoch": 1.423106350420811,657 "grad_norm": 0.1932903343458798,658 "learning_rate": 0.00012598229615482954,659 "loss": 0.4127,660 "step": 930661 },662 {663 "epoch": 1.4384085692425401,664 "grad_norm": 0.20197440137591363,665 "learning_rate": 0.0001242575028566632,666 "loss": 0.4118,667 "step": 940668 },669 {670 "epoch": 1.4537107880642695,671 "grad_norm": 0.20030727904644482,672 "learning_rate": 0.00012252500709373934,673 "loss": 0.4133,674 "step": 950675 },676 {677 "epoch": 1.4690130068859983,678 "grad_norm": 0.20837354923941284,679 "learning_rate": 0.00012078535898400019,680 "loss": 0.4117,681 "step": 960682 },683 {684 "epoch": 1.4843152257077277,685 "grad_norm": 0.19925595673498087,686 "learning_rate": 0.00011903911091646684,687 "loss": 0.4083,688 "step": 970689 },690 {691 "epoch": 1.4996174445294568,692 "grad_norm": 0.2084484154721651,693 "learning_rate": 0.00011728681737583945,694 "loss": 0.408,695 "step": 980696 },697 {698 "epoch": 1.5149196633511859,699 "grad_norm": 0.20623569681522963,700 "learning_rate": 0.00011552903476643222,701 "loss": 0.4117,702 "step": 990703 },704 {705 "epoch": 1.5302218821729152,706 "grad_norm": 0.19912897780166905,707 "learning_rate": 0.0001137663212354988,708 "loss": 0.4071,709 "step": 1000710 },711 {712 "epoch": 1.545524100994644,713 "grad_norm": 0.2015032395684377,714 "learning_rate": 0.00011199923649600432,715 "loss": 0.4085,716 "step": 1010717 },718 {719 "epoch": 1.5608263198163734,720 "grad_norm": 0.19846674785205634,721 "learning_rate": 0.0001102283416489001,722 "loss": 0.4094,723 "step": 1020724 },725 {726 "epoch": 1.5761285386381025,727 "grad_norm": 0.19503368149396527,728 "learning_rate": 0.00010845419900495772,729 "loss": 0.4031,730 "step": 1030731 },732 {733 "epoch": 1.5914307574598316,734 "grad_norm": 0.20636304448971973,735 "learning_rate": 0.00010667737190621911,736 "loss": 0.4141,737 "step": 1040738 },739 {740 "epoch": 1.606732976281561,741 "grad_norm": 0.19741819850815578,742 "learning_rate": 0.0001048984245471188,743 "loss": 0.4123,744 "step": 1050745 },746 {747 "epoch": 1.6220351951032899,748 "grad_norm": 0.208094236192064,749 "learning_rate": 0.00010311792179533589,750 "loss": 0.4094,751 "step": 1060752 },753 {754 "epoch": 1.6373374139250192,755 "grad_norm": 0.20834394157642375,756 "learning_rate": 0.00010133642901243199,757 "loss": 0.4073,758 "step": 1070759 },760 {761 "epoch": 1.6526396327467483,762 "grad_norm": 0.20325976490051528,763 "learning_rate": 9.955451187433249e-05,764 "loss": 0.4072,765 "step": 1080766 },767 {768 "epoch": 1.6679418515684774,769 "grad_norm": 0.19996940436744937,770 "learning_rate": 9.777273619170796e-05,771 "loss": 0.4067,772 "step": 1090773 },774 {775 "epoch": 1.6832440703902067,776 "grad_norm": 0.19609861659837347,777 "learning_rate": 9.599166773031269e-05,778 "loss": 0.405,779 "step": 1100780 },781 {782 "epoch": 1.6985462892119356,783 "grad_norm": 0.20661663114073753,784 "learning_rate": 9.421187203133763e-05,785 "loss": 0.4089,786 "step": 1110787 },788 {789 "epoch": 1.713848508033665,790 "grad_norm": 0.19921721692896047,791 "learning_rate": 9.243391423183448e-05,792 "loss": 0.4071,793 "step": 1120794 },795 {796 "epoch": 1.729150726855394,797 "grad_norm": 0.20297141939912075,798 "learning_rate": 9.06583588852683e-05,799 "loss": 0.4043,800 "step": 1130801 },802 {803 "epoch": 1.7444529456771232,804 "grad_norm": 0.20714391729089626,805 "learning_rate": 8.888576978225527e-05,806 "loss": 0.4031,807 "step": 1140808 },809 {810 "epoch": 1.7597551644988525,811 "grad_norm": 0.20284798828869055,812 "learning_rate": 8.711670977154274e-05,813 "loss": 0.4051,814 "step": 1150815 },816 {817 "epoch": 1.7750573833205814,818 "grad_norm": 0.20621816413716504,819 "learning_rate": 8.535174058128812e-05,820 "loss": 0.4028,821 "step": 1160822 },823 {824 "epoch": 1.7903596021423107,825 "grad_norm": 0.2107861816265634,826 "learning_rate": 8.359142264069424e-05,827 "loss": 0.3972,828 "step": 1170829 },830 {831 "epoch": 1.8056618209640398,832 "grad_norm": 0.20926246575879495,833 "learning_rate": 8.183631490205637e-05,834 "loss": 0.4033,835 "step": 1180836 },837 {838 "epoch": 1.820964039785769,839 "grad_norm": 0.20398570550310058,840 "learning_rate": 8.008697466327865e-05,841 "loss": 0.3994,842 "step": 1190843 },844 {845 "epoch": 1.836266258607498,846 "grad_norm": 0.21408610304309247,847 "learning_rate": 7.834395739091585e-05,848 "loss": 0.3971,849 "step": 1200850 },851 {852 "epoch": 1.8515684774292271,853 "grad_norm": 0.2059678534725396,854 "learning_rate": 7.660781654379638e-05,855 "loss": 0.4004,856 "step": 1210857 },858 {859 "epoch": 1.8668706962509565,860 "grad_norm": 0.20089108656511492,861 "learning_rate": 7.487910339728308e-05,862 "loss": 0.398,863 "step": 1220864 },865 {866 "epoch": 1.8821729150726856,867 "grad_norm": 0.2089057556225053,868 "learning_rate": 7.315836686822729e-05,869 "loss": 0.4,870 "step": 1230871 },872 {873 "epoch": 1.8974751338944147,874 "grad_norm": 0.2076979091587327,875 "learning_rate": 7.14461533406714e-05,876 "loss": 0.3942,877 "step": 1240878 },879 {880 "epoch": 1.9127773527161438,881 "grad_norm": 0.2075858197523019,882 "learning_rate": 6.974300649235633e-05,883 "loss": 0.4004,884 "step": 1250885 },886 {887 "epoch": 1.928079571537873,888 "grad_norm": 0.21210310960815237,889 "learning_rate": 6.804946712208793e-05,890 "loss": 0.4021,891 "step": 1260892 },893 {894 "epoch": 1.9433817903596022,895 "grad_norm": 0.21341887577251997,896 "learning_rate": 6.63660729780174e-05,897 "loss": 0.3954,898 "step": 1270899 },900 {901 "epoch": 1.9586840091813313,902 "grad_norm": 0.22172559452313256,903 "learning_rate": 6.469335858689074e-05,904 "loss": 0.4002,905 "step": 1280906 },907 {908 "epoch": 1.9739862280030605,909 "grad_norm": 0.20709389048082577,910 "learning_rate": 6.303185508432085e-05,911 "loss": 0.4018,912 "step": 1290913 },914 {915 "epoch": 1.9892884468247896,916 "grad_norm": 0.21370736036441443,917 "learning_rate": 6.138209004613647e-05,918 "loss": 0.3955,919 "step": 1300920 },921 {922 "epoch": 2.0045906656465187,923 "grad_norm": 0.20094204383719153,924 "learning_rate": 5.974458732086149e-05,925 "loss": 0.3851,926 "step": 1310927 },928 {929 "epoch": 2.019892884468248,930 "grad_norm": 0.22289055701062488,931 "learning_rate": 5.81198668633778e-05,932 "loss": 0.3674,933 "step": 1320934 },935 {936 "epoch": 2.035195103289977,937 "grad_norm": 0.22724332895866212,938 "learning_rate": 5.6508444569824315e-05,939 "loss": 0.3614,940 "step": 1330941 },942 {943 "epoch": 2.050497322111706,944 "grad_norm": 0.23888425948419684,945 "learning_rate": 5.491083211378505e-05,946 "loss": 0.3614,947 "step": 1340948 },949 {950 "epoch": 2.0657995409334355,951 "grad_norm": 0.23068081709857463,952 "learning_rate": 5.3327536783817766e-05,953 "loss": 0.3644,954 "step": 1350955 },956 {957 "epoch": 2.0811017597551644,958 "grad_norm": 0.2460582871625401,959 "learning_rate": 5.1759061322375045e-05,960 "loss": 0.3634,961 "step": 1360962 },963 {964 "epoch": 2.0964039785768938,965 "grad_norm": 0.24787239171921766,966 "learning_rate": 5.0205903766168915e-05,967 "loss": 0.3612,968 "step": 1370969 },970 {971 "epoch": 2.1117061973986226,972 "grad_norm": 0.23563510103472043,973 "learning_rate": 4.8668557288029684e-05,974 "loss": 0.3627,975 "step": 1380976 },977 {978 "epoch": 2.127008416220352,979 "grad_norm": 0.23966764070729765,980 "learning_rate": 4.7147510040309115e-05,981 "loss": 0.3633,982 "step": 1390983 },984 {985 "epoch": 2.1423106350420813,986 "grad_norm": 0.24153476110732292,987 "learning_rate": 4.56432449998779e-05,988 "loss": 0.3621,989 "step": 1400990 },991 {992 "epoch": 2.15761285386381,993 "grad_norm": 0.23966649969853318,994 "learning_rate": 4.4156239814766355e-05,995 "loss": 0.3597,996 "step": 1410997 },998 {999 "epoch": 2.1729150726855395,1000 "grad_norm": 0.2492626290666687,1001 "learning_rate": 4.268696665249724e-05,1002 "loss": 0.3663,1003 "step": 14201004 },1005 {1006 "epoch": 2.1882172915072684,1007 "grad_norm": 0.24762132725809086,1008 "learning_rate": 4.1235892050158866e-05,1009 "loss": 0.3604,1010 "step": 14301011 },1012 {1013 "epoch": 2.2035195103289977,1014 "grad_norm": 0.24689838661058983,1015 "learning_rate": 3.9803476766265835e-05,1016 "loss": 0.3648,1017 "step": 14401018 },1019 {1020 "epoch": 2.218821729150727,1021 "grad_norm": 0.24705256051578678,1022 "learning_rate": 3.839017563445489e-05,1023 "loss": 0.3625,1024 "step": 14501025 },1026 {1027 "epoch": 2.234123947972456,1028 "grad_norm": 0.2496443256139868,1029 "learning_rate": 3.699643741906193e-05,1030 "loss": 0.3545,1031 "step": 14601032 },1033 {1034 "epoch": 2.2494261667941853,1035 "grad_norm": 0.249005841241916,1036 "learning_rate": 3.562270467262619e-05,1037 "loss": 0.3601,1038 "step": 14701039 },1040 {1041 "epoch": 2.264728385615914,1042 "grad_norm": 0.24757649232051404,1043 "learning_rate": 3.426941359536699e-05,1044 "loss": 0.3576,1045 "step": 14801046 },1047 {1048 "epoch": 2.2800306044376435,1049 "grad_norm": 0.25451870114574876,1050 "learning_rate": 3.293699389667734e-05,1051 "loss": 0.3648,1052 "step": 14901053 },1054 {1055 "epoch": 2.295332823259373,1056 "grad_norm": 0.2453131567916715,1057 "learning_rate": 3.1625868658678784e-05,1058 "loss": 0.3625,1059 "step": 15001060 },1061 {1062 "epoch": 2.3106350420811017,1063 "grad_norm": 0.26123253732278273,1064 "learning_rate": 3.0336454201880404e-05,1065 "loss": 0.3557,1066 "step": 15101067 },1068 {1069 "epoch": 2.325937260902831,1070 "grad_norm": 0.2626580334343511,1071 "learning_rate": 2.9069159952984938e-05,1072 "loss": 0.3566,1073 "step": 15201074 },1075 {1076 "epoch": 2.34123947972456,1077 "grad_norm": 0.25003501828393526,1078 "learning_rate": 2.7824388314883876e-05,1079 "loss": 0.3591,1080 "step": 15301081 },1082 {1083 "epoch": 2.3565416985462893,1084 "grad_norm": 0.2507207739640118,1085 "learning_rate": 2.6602534538882752e-05,1086 "loss": 0.358,1087 "step": 15401088 },1089 {1090 "epoch": 2.371843917368018,1091 "grad_norm": 0.2512257287691549,1092 "learning_rate": 2.5403986599197403e-05,1093 "loss": 0.3501,1094 "step": 15501095 },1096 {1097 "epoch": 2.3871461361897475,1098 "grad_norm": 0.2499142391014787,1099 "learning_rate": 2.4229125069760773e-05,1100 "loss": 0.3517,1101 "step": 15601102 },1103 {1104 "epoch": 2.402448355011477,1105 "grad_norm": 0.24884412260444377,1106 "learning_rate": 2.30783230033796e-05,1107 "loss": 0.3568,1108 "step": 15701109 },1110 {1111 "epoch": 2.4177505738332057,1112 "grad_norm": 0.25335712662759613,1113 "learning_rate": 2.1951945813279306e-05,1114 "loss": 0.3547,1115 "step": 15801116 },1117 {1118 "epoch": 2.433052792654935,1119 "grad_norm": 0.24937746984746909,1120 "learning_rate": 2.0850351157074598e-05,1121 "loss": 0.353,1122 "step": 15901123 },1124 {1125 "epoch": 2.4483550114766643,1126 "grad_norm": 0.26237405083230225,1127 "learning_rate": 1.9773888823202747e-05,1128 "loss": 0.3579,1129 "step": 16001130 },1131 {1132 "epoch": 2.4636572302983932,1133 "grad_norm": 0.24937407019841143,1134 "learning_rate": 1.8722900619855577e-05,1135 "loss": 0.3562,1136 "step": 16101137 },1138 {1139 "epoch": 2.4789594491201226,1140 "grad_norm": 0.2497739493217595,1141 "learning_rate": 1.7697720266445374e-05,1142 "loss": 0.3512,1143 "step": 16201144 },1145 {1146 "epoch": 2.4942616679418514,1147 "grad_norm": 0.250399923768968,1148 "learning_rate": 1.6698673287639242e-05,1149 "loss": 0.3556,1150 "step": 16301151 },1152 {1153 "epoch": 2.5095638867635808,1154 "grad_norm": 0.2538234603963528,1155 "learning_rate": 1.5726076909995525e-05,1156 "loss": 0.355,1157 "step": 16401158 },1159 {1160 "epoch": 2.5248661055853097,1161 "grad_norm": 0.2504434686740776,1162 "learning_rate": 1.4780239961235143e-05,1163 "loss": 0.3581,1164 "step": 16501165 },1166 {1167 "epoch": 2.540168324407039,1168 "grad_norm": 0.2537006354023553,1169 "learning_rate": 1.3861462772179735e-05,1170 "loss": 0.3529,1171 "step": 16601172 },1173 {1174 "epoch": 2.5554705432287683,1175 "grad_norm": 0.2560925692389684,1176 "learning_rate": 1.297003708138792e-05,1177 "loss": 0.3584,1178 "step": 16701179 },1180 {1181 "epoch": 2.570772762050497,1182 "grad_norm": 0.25340005468102866,1183 "learning_rate": 1.2106245942519745e-05,1184 "loss": 0.3562,1185 "step": 16801186 },1187 {1188 "epoch": 2.5860749808722265,1189 "grad_norm": 0.25785387176401525,1190 "learning_rate": 1.1270363634458903e-05,1191 "loss": 0.3541,1192 "step": 16901193 },1194 {1195 "epoch": 2.601377199693956,1196 "grad_norm": 0.2615280811952495,1197 "learning_rate": 1.0462655574221213e-05,1198 "loss": 0.3553,1199 "step": 17001200 },