AstroMLab/astrollama-3-8b-chat_summary
152
1{2 "best_metric": null,3 "best_model_checkpoint": null,4 "epoch": 3.0,5 "eval_steps": 15.0,6 "global_step": 1182,7 "is_hyper_param_search": false,8 "is_local_process_zero": true,9 "is_world_process_zero": true,10 "log_history": [11 {12 "epoch": 0.0025380710659898475,13 "grad_norm": 152.0770602205149,14 "learning_rate": 2.7777777777777776e-07,15 "loss": 1.4538,16 "step": 117 },18 {19 "epoch": 0.005076142131979695,20 "grad_norm": 154.43415342456026,21 "learning_rate": 5.555555555555555e-07,22 "loss": 1.6443,23 "step": 224 },25 {26 "epoch": 0.007614213197969543,27 "grad_norm": 83.042923862024,28 "learning_rate": 8.333333333333333e-07,29 "loss": 1.569,30 "step": 331 },32 {33 "epoch": 0.01015228426395939,34 "grad_norm": 168.9469822153038,35 "learning_rate": 1.111111111111111e-06,36 "loss": 1.5581,37 "step": 438 },39 {40 "epoch": 0.012690355329949238,41 "grad_norm": 99.16296768200209,42 "learning_rate": 1.3888888888888892e-06,43 "loss": 1.5565,44 "step": 545 },46 {47 "epoch": 0.015228426395939087,48 "grad_norm": 77.46041883601814,49 "learning_rate": 1.6666666666666667e-06,50 "loss": 1.834,51 "step": 652 },53 {54 "epoch": 0.017766497461928935,55 "grad_norm": 65.11628947265203,56 "learning_rate": 1.944444444444445e-06,57 "loss": 1.6277,58 "step": 759 },60 {61 "epoch": 0.02030456852791878,62 "grad_norm": 28.341949090239343,63 "learning_rate": 2.222222222222222e-06,64 "loss": 1.5202,65 "step": 866 },67 {68 "epoch": 0.02284263959390863,69 "grad_norm": 45.05260802676402,70 "learning_rate": 2.5e-06,71 "loss": 1.4123,72 "step": 973 },74 {75 "epoch": 0.025380710659898477,76 "grad_norm": 28.73735471868825,77 "learning_rate": 2.7777777777777783e-06,78 "loss": 1.5291,79 "step": 1080 },81 {82 "epoch": 0.027918781725888325,83 "grad_norm": 68.32933011519918,84 "learning_rate": 3.055555555555556e-06,85 "loss": 1.2742,86 "step": 1187 },88 {89 "epoch": 0.030456852791878174,90 "grad_norm": 26.127348649606496,91 "learning_rate": 3.3333333333333333e-06,92 "loss": 1.357,93 "step": 1294 },95 {96 "epoch": 0.03299492385786802,97 "grad_norm": 20.661721515738268,98 "learning_rate": 3.6111111111111115e-06,99 "loss": 1.2094,100 "step": 13101 },102 {103 "epoch": 0.03553299492385787,104 "grad_norm": 28.64253126706993,105 "learning_rate": 3.88888888888889e-06,106 "loss": 1.2889,107 "step": 14108 },109 {110 "epoch": 0.03807106598984772,111 "grad_norm": 11.29417859738243,112 "learning_rate": 4.166666666666667e-06,113 "loss": 1.1999,114 "step": 15115 },116 {117 "epoch": 0.04060913705583756,118 "grad_norm": 10.496811646115283,119 "learning_rate": 4.444444444444444e-06,120 "loss": 1.3311,121 "step": 16122 },123 {124 "epoch": 0.04314720812182741,125 "grad_norm": 3.222307468960679,126 "learning_rate": 4.722222222222222e-06,127 "loss": 1.2378,128 "step": 17129 },130 {131 "epoch": 0.04568527918781726,132 "grad_norm": 5.95588179653401,133 "learning_rate": 5e-06,134 "loss": 1.2917,135 "step": 18136 },137 {138 "epoch": 0.048223350253807105,139 "grad_norm": 4.595212148917514,140 "learning_rate": 5.2777777777777785e-06,141 "loss": 1.2182,142 "step": 19143 },144 {145 "epoch": 0.050761421319796954,146 "grad_norm": 3.4919855269541316,147 "learning_rate": 5.555555555555557e-06,148 "loss": 1.1647,149 "step": 20150 },151 {152 "epoch": 0.0532994923857868,153 "grad_norm": 2.8992797662103706,154 "learning_rate": 5.833333333333334e-06,155 "loss": 1.2627,156 "step": 21157 },158 {159 "epoch": 0.05583756345177665,160 "grad_norm": 6.2754366481134,161 "learning_rate": 6.111111111111112e-06,162 "loss": 1.2512,163 "step": 22164 },165 {166 "epoch": 0.0583756345177665,167 "grad_norm": 4.8408966557202735,168 "learning_rate": 6.3888888888888885e-06,169 "loss": 1.109,170 "step": 23171 },172 {173 "epoch": 0.06091370558375635,174 "grad_norm": 4.794271905930829,175 "learning_rate": 6.666666666666667e-06,176 "loss": 1.1957,177 "step": 24178 },179 {180 "epoch": 0.06345177664974619,181 "grad_norm": 3.8422011976344037,182 "learning_rate": 6.944444444444445e-06,183 "loss": 1.1104,184 "step": 25185 },186 {187 "epoch": 0.06598984771573604,188 "grad_norm": 2.9555249451534094,189 "learning_rate": 7.222222222222223e-06,190 "loss": 1.1429,191 "step": 26192 },193 {194 "epoch": 0.06852791878172589,195 "grad_norm": 3.420765898636476,196 "learning_rate": 7.500000000000001e-06,197 "loss": 1.0736,198 "step": 27199 },200 {201 "epoch": 0.07106598984771574,202 "grad_norm": 3.4590250149649053,203 "learning_rate": 7.77777777777778e-06,204 "loss": 1.1766,205 "step": 28206 },207 {208 "epoch": 0.07360406091370558,209 "grad_norm": 6.343830946481616,210 "learning_rate": 8.055555555555557e-06,211 "loss": 1.2733,212 "step": 29213 },214 {215 "epoch": 0.07614213197969544,216 "grad_norm": 6.9382893747130305,217 "learning_rate": 8.333333333333334e-06,218 "loss": 1.1572,219 "step": 30220 },221 {222 "epoch": 0.07868020304568528,223 "grad_norm": 4.116628130544569,224 "learning_rate": 8.611111111111112e-06,225 "loss": 1.0768,226 "step": 31227 },228 {229 "epoch": 0.08121827411167512,230 "grad_norm": 3.137655679928552,231 "learning_rate": 8.888888888888888e-06,232 "loss": 1.2086,233 "step": 32234 },235 {236 "epoch": 0.08375634517766498,237 "grad_norm": 2.7173186967601377,238 "learning_rate": 9.166666666666666e-06,239 "loss": 1.0033,240 "step": 33241 },242 {243 "epoch": 0.08629441624365482,244 "grad_norm": 4.422086595586005,245 "learning_rate": 9.444444444444445e-06,246 "loss": 1.2143,247 "step": 34248 },249 {250 "epoch": 0.08883248730964467,251 "grad_norm": 4.287936560092926,252 "learning_rate": 9.722222222222223e-06,253 "loss": 1.1019,254 "step": 35255 },256 {257 "epoch": 0.09137055837563451,258 "grad_norm": 4.71773823753788,259 "learning_rate": 1e-05,260 "loss": 1.0297,261 "step": 36262 },263 {264 "epoch": 0.09390862944162437,265 "grad_norm": 3.0619027718013845,266 "learning_rate": 9.999981212445786e-06,267 "loss": 1.2065,268 "step": 37269 },270 {271 "epoch": 0.09644670050761421,272 "grad_norm": 5.557917883258693,273 "learning_rate": 9.999924849924331e-06,274 "loss": 1.1469,275 "step": 38276 },277 {278 "epoch": 0.09898477157360407,279 "grad_norm": 3.3448139583001146,280 "learning_rate": 9.999830912859204e-06,281 "loss": 1.076,282 "step": 39283 },284 {285 "epoch": 0.10152284263959391,286 "grad_norm": 3.4576008769883573,287 "learning_rate": 9.99969940195634e-06,288 "loss": 1.1861,289 "step": 40290 },291 {292 "epoch": 0.10406091370558376,293 "grad_norm": 2.859503835631421,294 "learning_rate": 9.99953031820405e-06,295 "loss": 1.1576,296 "step": 41297 },298 {299 "epoch": 0.1065989847715736,300 "grad_norm": 3.01601354320767,301 "learning_rate": 9.999323662872998e-06,302 "loss": 1.0347,303 "step": 42304 },305 {306 "epoch": 0.10913705583756345,307 "grad_norm": 3.5906060809534663,308 "learning_rate": 9.999079437516205e-06,309 "loss": 1.1774,310 "step": 43311 },312 {313 "epoch": 0.1116751269035533,314 "grad_norm": 3.813820556604242,315 "learning_rate": 9.998797643969031e-06,316 "loss": 1.086,317 "step": 44318 },319 {320 "epoch": 0.11421319796954314,321 "grad_norm": 3.2135626955254954,322 "learning_rate": 9.998478284349163e-06,323 "loss": 1.0939,324 "step": 45325 },326 {327 "epoch": 0.116751269035533,328 "grad_norm": 3.038494005068585,329 "learning_rate": 9.998121361056588e-06,330 "loss": 1.1049,331 "step": 46332 },333 {334 "epoch": 0.11928934010152284,335 "grad_norm": 4.836679741133791,336 "learning_rate": 9.997726876773599e-06,337 "loss": 0.9771,338 "step": 47339 },340 {341 "epoch": 0.1218274111675127,342 "grad_norm": 3.285363024124718,343 "learning_rate": 9.99729483446475e-06,344 "loss": 1.0107,345 "step": 48346 },347 {348 "epoch": 0.12436548223350254,349 "grad_norm": 4.762499743457535,350 "learning_rate": 9.996825237376852e-06,351 "loss": 1.1301,352 "step": 49353 },354 {355 "epoch": 0.12690355329949238,356 "grad_norm": 4.073333426027345,357 "learning_rate": 9.996318089038935e-06,358 "loss": 1.0094,359 "step": 50360 },361 {362 "epoch": 0.12944162436548223,363 "grad_norm": 3.5281106754331906,364 "learning_rate": 9.99577339326223e-06,365 "loss": 1.107,366 "step": 51367 },368 {369 "epoch": 0.1319796954314721,370 "grad_norm": 2.388804020934236,371 "learning_rate": 9.995191154140136e-06,372 "loss": 1.0684,373 "step": 52374 },375 {376 "epoch": 0.13451776649746192,377 "grad_norm": 3.896150155122405,378 "learning_rate": 9.994571376048195e-06,379 "loss": 1.0195,380 "step": 53381 },382 {383 "epoch": 0.13705583756345177,384 "grad_norm": 3.159381315379948,385 "learning_rate": 9.993914063644053e-06,386 "loss": 1.1289,387 "step": 54388 },389 {390 "epoch": 0.13959390862944163,391 "grad_norm": 4.078159681191905,392 "learning_rate": 9.993219221867426e-06,393 "loss": 1.1211,394 "step": 55395 },396 {397 "epoch": 0.14213197969543148,398 "grad_norm": 5.601995817902489,399 "learning_rate": 9.992486855940064e-06,400 "loss": 1.0514,401 "step": 56402 },403 {404 "epoch": 0.1446700507614213,405 "grad_norm": 2.1043015689108846,406 "learning_rate": 9.991716971365713e-06,407 "loss": 1.0456,408 "step": 57409 },410 {411 "epoch": 0.14720812182741116,412 "grad_norm": 2.5356517486241827,413 "learning_rate": 9.990909573930075e-06,414 "loss": 1.192,415 "step": 58416 },417 {418 "epoch": 0.14974619289340102,419 "grad_norm": 2.7360362373563953,420 "learning_rate": 9.990064669700756e-06,421 "loss": 0.9797,422 "step": 59423 },424 {425 "epoch": 0.15228426395939088,426 "grad_norm": 2.208834445890474,427 "learning_rate": 9.989182265027232e-06,428 "loss": 1.1441,429 "step": 60430 },431 {432 "epoch": 0.1548223350253807,433 "grad_norm": 3.2583621910518734,434 "learning_rate": 9.988262366540792e-06,435 "loss": 0.9885,436 "step": 61437 },438 {439 "epoch": 0.15736040609137056,440 "grad_norm": 3.9359528549878404,441 "learning_rate": 9.987304981154493e-06,442 "loss": 1.032,443 "step": 62444 },445 {446 "epoch": 0.1598984771573604,447 "grad_norm": 4.3721493801621465,448 "learning_rate": 9.986310116063108e-06,449 "loss": 1.0886,450 "step": 63451 },452 {453 "epoch": 0.16243654822335024,454 "grad_norm": 3.2720085785918624,455 "learning_rate": 9.985277778743069e-06,456 "loss": 1.0736,457 "step": 64458 },459 {460 "epoch": 0.1649746192893401,461 "grad_norm": 4.284093394240824,462 "learning_rate": 9.984207976952412e-06,463 "loss": 1.109,464 "step": 65465 },466 {467 "epoch": 0.16751269035532995,468 "grad_norm": 2.744141216549521,469 "learning_rate": 9.98310071873072e-06,470 "loss": 1.0275,471 "step": 66472 },473 {474 "epoch": 0.1700507614213198,475 "grad_norm": 2.8863340000098474,476 "learning_rate": 9.981956012399068e-06,477 "loss": 1.0759,478 "step": 67479 },480 {481 "epoch": 0.17258883248730963,482 "grad_norm": 4.033064317161934,483 "learning_rate": 9.980773866559946e-06,484 "loss": 1.07,485 "step": 68486 },487 {488 "epoch": 0.1751269035532995,489 "grad_norm": 3.7971135347720204,490 "learning_rate": 9.979554290097201e-06,491 "loss": 0.9832,492 "step": 69493 },494 {495 "epoch": 0.17766497461928935,496 "grad_norm": 2.9283571123362697,497 "learning_rate": 9.978297292175984e-06,498 "loss": 1.0622,499 "step": 70500 },501 {502 "epoch": 0.1802030456852792,503 "grad_norm": 2.9862875820274453,504 "learning_rate": 9.977002882242657e-06,505 "loss": 1.1675,506 "step": 71507 },508 {509 "epoch": 0.18274111675126903,510 "grad_norm": 2.458693353037259,511 "learning_rate": 9.975671070024741e-06,512 "loss": 0.9963,513 "step": 72514 },515 {516 "epoch": 0.18527918781725888,517 "grad_norm": 2.7140438707634162,518 "learning_rate": 9.97430186553083e-06,519 "loss": 0.9998,520 "step": 73521 },522 {523 "epoch": 0.18781725888324874,524 "grad_norm": 2.3819474228984596,525 "learning_rate": 9.972895279050532e-06,526 "loss": 1.1602,527 "step": 74528 },529 {530 "epoch": 0.19035532994923857,531 "grad_norm": 2.869485463686646,532 "learning_rate": 9.971451321154368e-06,533 "loss": 1.1476,534 "step": 75535 },536 {537 "epoch": 0.19289340101522842,538 "grad_norm": 3.5672507886894915,539 "learning_rate": 9.969970002693718e-06,540 "loss": 1.189,541 "step": 76542 },543 {544 "epoch": 0.19543147208121828,545 "grad_norm": 4.6249979596983275,546 "learning_rate": 9.968451334800718e-06,547 "loss": 1.0321,548 "step": 77549 },550 {551 "epoch": 0.19796954314720813,552 "grad_norm": 2.590141938018056,553 "learning_rate": 9.966895328888195e-06,554 "loss": 1.1738,555 "step": 78556 },557 {558 "epoch": 0.20050761421319796,559 "grad_norm": 2.4382892427081226,560 "learning_rate": 9.965301996649563e-06,561 "loss": 1.0667,562 "step": 79563 },564 {565 "epoch": 0.20304568527918782,566 "grad_norm": 2.774255541254283,567 "learning_rate": 9.96367135005875e-06,568 "loss": 0.9998,569 "step": 80570 },571 {572 "epoch": 0.20558375634517767,573 "grad_norm": 2.4921808717304685,574 "learning_rate": 9.962003401370101e-06,575 "loss": 1.0051,576 "step": 81577 },578 {579 "epoch": 0.20812182741116753,580 "grad_norm": 2.8238480847860785,581 "learning_rate": 9.960298163118284e-06,582 "loss": 0.9916,583 "step": 82584 },585 {586 "epoch": 0.21065989847715735,587 "grad_norm": 6.206800727550207,588 "learning_rate": 9.958555648118207e-06,589 "loss": 1.0763,590 "step": 83591 },592 {593 "epoch": 0.2131979695431472,594 "grad_norm": 2.443578917202038,595 "learning_rate": 9.956775869464901e-06,596 "loss": 0.9825,597 "step": 84598 },599 {600 "epoch": 0.21573604060913706,601 "grad_norm": 2.847758348759497,602 "learning_rate": 9.954958840533447e-06,603 "loss": 1.0456,604 "step": 85605 },606 {607 "epoch": 0.2182741116751269,608 "grad_norm": 3.170138811884141,609 "learning_rate": 9.953104574978854e-06,610 "loss": 1.1186,611 "step": 86612 },613 {614 "epoch": 0.22081218274111675,615 "grad_norm": 2.6010611046656877,616 "learning_rate": 9.951213086735967e-06,617 "loss": 1.0233,618 "step": 87619 },620 {621 "epoch": 0.2233502538071066,622 "grad_norm": 6.679956372744609,623 "learning_rate": 9.949284390019362e-06,624 "loss": 1.066,625 "step": 88626 },627 {628 "epoch": 0.22588832487309646,629 "grad_norm": 2.6554799986019133,630 "learning_rate": 9.94731849932324e-06,631 "loss": 0.9623,632 "step": 89633 },634 {635 "epoch": 0.22842639593908629,636 "grad_norm": 2.3433414348493273,637 "learning_rate": 9.945315429421307e-06,638 "loss": 1.0869,639 "step": 90640 },641 {642 "epoch": 0.23096446700507614,643 "grad_norm": 2.8599286738704683,644 "learning_rate": 9.943275195366679e-06,645 "loss": 1.11,646 "step": 91647 },648 {649 "epoch": 0.233502538071066,650 "grad_norm": 4.958755531266782,651 "learning_rate": 9.941197812491761e-06,652 "loss": 1.2542,653 "step": 92654 },655 {656 "epoch": 0.23604060913705585,657 "grad_norm": 2.2479047075233427,658 "learning_rate": 9.939083296408127e-06,659 "loss": 1.0836,660 "step": 93661 },662 {663 "epoch": 0.23857868020304568,664 "grad_norm": 1.8107915831749222,665 "learning_rate": 9.936931663006414e-06,666 "loss": 1.0384,667 "step": 94668 },669 {670 "epoch": 0.24111675126903553,671 "grad_norm": 2.457682015648462,672 "learning_rate": 9.934742928456191e-06,673 "loss": 1.0374,674 "step": 95675 },676 {677 "epoch": 0.2436548223350254,678 "grad_norm": 2.972864834775759,679 "learning_rate": 9.932517109205849e-06,680 "loss": 1.1032,681 "step": 96682 },683 {684 "epoch": 0.24619289340101522,685 "grad_norm": 2.3725301348700087,686 "learning_rate": 9.930254221982464e-06,687 "loss": 1.0623,688 "step": 97689 },690 {691 "epoch": 0.24873096446700507,692 "grad_norm": 2.7944396518166355,693 "learning_rate": 9.927954283791687e-06,694 "loss": 1.0831,695 "step": 98696 },697 {698 "epoch": 0.2512690355329949,699 "grad_norm": 2.300115990070667,700 "learning_rate": 9.9256173119176e-06,701 "loss": 1.0785,702 "step": 99703 },704 {705 "epoch": 0.25380710659898476,706 "grad_norm": 1.8208692795246306,707 "learning_rate": 9.923243323922598e-06,708 "loss": 0.9879,709 "step": 100710 },711 {712 "epoch": 0.2563451776649746,713 "grad_norm": 4.4476962273727665,714 "learning_rate": 9.920832337647252e-06,715 "loss": 1.0007,716 "step": 101717 },718 {719 "epoch": 0.25888324873096447,720 "grad_norm": 3.3940854617337113,721 "learning_rate": 9.918384371210178e-06,722 "loss": 1.1891,723 "step": 102724 },725 {726 "epoch": 0.2614213197969543,727 "grad_norm": 2.555201632199259,728 "learning_rate": 9.915899443007894e-06,729 "loss": 1.021,730 "step": 103731 },732 {733 "epoch": 0.2639593908629442,734 "grad_norm": 2.3220370794195113,735 "learning_rate": 9.91337757171469e-06,736 "loss": 1.1011,737 "step": 104738 },739 {740 "epoch": 0.26649746192893403,741 "grad_norm": 2.9669260657059655,742 "learning_rate": 9.910818776282487e-06,743 "loss": 1.0555,744 "step": 105745 },746 {747 "epoch": 0.26903553299492383,748 "grad_norm": 2.870314472945511,749 "learning_rate": 9.908223075940684e-06,750 "loss": 1.1542,751 "step": 106752 },753 {754 "epoch": 0.2715736040609137,755 "grad_norm": 2.7991064606918137,756 "learning_rate": 9.905590490196027e-06,757 "loss": 1.0811,758 "step": 107759 },760 {761 "epoch": 0.27411167512690354,762 "grad_norm": 2.493650659366754,763 "learning_rate": 9.902921038832456e-06,764 "loss": 1.0137,765 "step": 108766 },767 {768 "epoch": 0.2766497461928934,769 "grad_norm": 6.9035091138911655,770 "learning_rate": 9.900214741910955e-06,771 "loss": 1.1594,772 "step": 109773 },774 {775 "epoch": 0.27918781725888325,776 "grad_norm": 2.453399893747965,777 "learning_rate": 9.897471619769402e-06,778 "loss": 0.9992,779 "step": 110780 },781 {782 "epoch": 0.2817258883248731,783 "grad_norm": 5.298689006767713,784 "learning_rate": 9.89469169302242e-06,785 "loss": 1.0269,786 "step": 111787 },788 {789 "epoch": 0.28426395939086296,790 "grad_norm": 3.312118607283353,791 "learning_rate": 9.891874982561222e-06,792 "loss": 1.0999,793 "step": 112794 },795 {796 "epoch": 0.2868020304568528,797 "grad_norm": 2.309806298343435,798 "learning_rate": 9.889021509553448e-06,799 "loss": 0.9932,800 "step": 113801 },802 {803 "epoch": 0.2893401015228426,804 "grad_norm": 2.782632711667371,805 "learning_rate": 9.886131295443003e-06,806 "loss": 1.0546,807 "step": 114808 },809 {810 "epoch": 0.2918781725888325,811 "grad_norm": 3.0241898018425375,812 "learning_rate": 9.883204361949916e-06,813 "loss": 1.063,814 "step": 115815 },816 {817 "epoch": 0.29441624365482233,818 "grad_norm": 4.881309577432392,819 "learning_rate": 9.880240731070152e-06,820 "loss": 0.9851,821 "step": 116822 },823 {824 "epoch": 0.2969543147208122,825 "grad_norm": 4.393148043595713,826 "learning_rate": 9.877240425075465e-06,827 "loss": 1.1928,828 "step": 117829 },830 {831 "epoch": 0.29949238578680204,832 "grad_norm": 2.539173060449269,833 "learning_rate": 9.874203466513215e-06,834 "loss": 1.0185,835 "step": 118836 },837 {838 "epoch": 0.3020304568527919,839 "grad_norm": 3.088531691349216,840 "learning_rate": 9.871129878206213e-06,841 "loss": 1.0862,842 "step": 119843 },844 {845 "epoch": 0.30456852791878175,846 "grad_norm": 2.646620091120325,847 "learning_rate": 9.868019683252543e-06,848 "loss": 0.9884,849 "step": 120850 },851 {852 "epoch": 0.30710659898477155,853 "grad_norm": 2.435727031764384,854 "learning_rate": 9.864872905025386e-06,855 "loss": 1.0276,856 "step": 121857 },858 {859 "epoch": 0.3096446700507614,860 "grad_norm": 2.1078027560231183,861 "learning_rate": 9.861689567172849e-06,862 "loss": 1.0837,863 "step": 122864 },865 {866 "epoch": 0.31218274111675126,867 "grad_norm": 2.3556477849722293,868 "learning_rate": 9.858469693617787e-06,869 "loss": 0.9124,870 "step": 123871 },872 {873 "epoch": 0.3147208121827411,874 "grad_norm": 2.574273891936511,875 "learning_rate": 9.855213308557618e-06,876 "loss": 1.1362,877 "step": 124878 },879 {880 "epoch": 0.31725888324873097,881 "grad_norm": 2.954661863407828,882 "learning_rate": 9.851920436464146e-06,883 "loss": 1.1748,884 "step": 125885 },886 {887 "epoch": 0.3197969543147208,888 "grad_norm": 2.493459031496384,889 "learning_rate": 9.848591102083375e-06,890 "loss": 1.1093,891 "step": 126892 },893 {894 "epoch": 0.3223350253807107,895 "grad_norm": 2.1194534532314098,896 "learning_rate": 9.845225330435329e-06,897 "loss": 1.0326,898 "step": 127899 },900 {901 "epoch": 0.3248730964467005,902 "grad_norm": 3.4687791362456477,903 "learning_rate": 9.84182314681385e-06,904 "loss": 1.0464,905 "step": 128906 },907 {908 "epoch": 0.32741116751269034,909 "grad_norm": 6.5552134087262255,910 "learning_rate": 9.838384576786427e-06,911 "loss": 1.1425,912 "step": 129913 },914 {915 "epoch": 0.3299492385786802,916 "grad_norm": 5.804701269137941,917 "learning_rate": 9.834909646193983e-06,918 "loss": 1.0323,919 "step": 130920 },921 {922 "epoch": 0.33248730964467005,923 "grad_norm": 2.6380372208920697,924 "learning_rate": 9.831398381150698e-06,925 "loss": 1.0946,926 "step": 131927 },928 {929 "epoch": 0.3350253807106599,930 "grad_norm": 2.292877023775666,931 "learning_rate": 9.82785080804381e-06,932 "loss": 0.883,933 "step": 132934 },935 {936 "epoch": 0.33756345177664976,937 "grad_norm": 4.2977395996010435,938 "learning_rate": 9.824266953533402e-06,939 "loss": 0.9968,940 "step": 133941 },942 {943 "epoch": 0.3401015228426396,944 "grad_norm": 2.4822533121250254,945 "learning_rate": 9.82064684455222e-06,946 "loss": 0.9894,947 "step": 134948 },949 {950 "epoch": 0.3426395939086294,951 "grad_norm": 2.314919940633327,952 "learning_rate": 9.816990508305463e-06,953 "loss": 0.9332,954 "step": 135955 },956 {957 "epoch": 0.34517766497461927,958 "grad_norm": 3.944138805330047,959 "learning_rate": 9.813297972270575e-06,960 "loss": 1.0342,961 "step": 136962 },963 {964 "epoch": 0.3477157360406091,965 "grad_norm": 4.083763205392443,966 "learning_rate": 9.809569264197046e-06,967 "loss": 1.0035,968 "step": 137969 },970 {971 "epoch": 0.350253807106599,972 "grad_norm": 2.2341064648864335,973 "learning_rate": 9.805804412106197e-06,974 "loss": 1.0156,975 "step": 138976 },977 {978 "epoch": 0.35279187817258884,979 "grad_norm": 4.73655672514693,980 "learning_rate": 9.802003444290975e-06,981 "loss": 1.0575,982 "step": 139983 },984 {985 "epoch": 0.3553299492385787,986 "grad_norm": 3.6474051487216794,987 "learning_rate": 9.798166389315734e-06,988 "loss": 1.0331,989 "step": 140990 },991 {992 "epoch": 0.35786802030456855,993 "grad_norm": 2.0950970123191235,994 "learning_rate": 9.794293276016024e-06,995 "loss": 0.8774,996 "step": 141997 },998 {999 "epoch": 0.3604060913705584,1000 "grad_norm": 4.020417271141957,1001 "learning_rate": 9.79038413349838e-06,1002 "loss": 1.0517,1003 "step": 1421004 },1005 {1006 "epoch": 0.3629441624365482,1007 "grad_norm": 2.343919859731207,1008 "learning_rate": 9.786438991140086e-06,1009 "loss": 1.0388,1010 "step": 1431011 },1012 {1013 "epoch": 0.36548223350253806,1014 "grad_norm": 3.5918593063524202,1015 "learning_rate": 9.782457878588977e-06,1016 "loss": 1.007,1017 "step": 1441018 },1019 {1020 "epoch": 0.3680203045685279,1021 "grad_norm": 2.989308945487366,1022 "learning_rate": 9.7784408257632e-06,1023 "loss": 1.1402,1024 "step": 1451025 },1026 {1027 "epoch": 0.37055837563451777,1028 "grad_norm": 3.2999750398100898,1029 "learning_rate": 9.774387862850993e-06,1030 "loss": 1.0778,1031 "step": 1461032 },1033 {1034 "epoch": 0.3730964467005076,1035 "grad_norm": 2.39286494783793,1036 "learning_rate": 9.77029902031046e-06,1037 "loss": 1.0588,1038 "step": 1471039 },1040 {1041 "epoch": 0.3756345177664975,1042 "grad_norm": 7.549790221744935,1043 "learning_rate": 9.766174328869344e-06,1044 "loss": 1.0188,1045 "step": 1481046 },1047 {1048 "epoch": 0.37817258883248733,1049 "grad_norm": 2.026349609367698,1050 "learning_rate": 9.762013819524788e-06,1051 "loss": 0.9754,1052 "step": 1491053 },1054 {1055 "epoch": 0.38071065989847713,1056 "grad_norm": 1.9809815038815315,1057 "learning_rate": 9.75781752354311e-06,1058 "loss": 1.1272,1059 "step": 1501060 },1061 {1062 "epoch": 0.383248730964467,1063 "grad_norm": 2.332081936160816,1064 "learning_rate": 9.753585472459564e-06,1065 "loss": 1.0715,1066 "step": 1511067 },1068 {1069 "epoch": 0.38578680203045684,1070 "grad_norm": 2.5164597293319217,1071 "learning_rate": 9.749317698078109e-06,1072 "loss": 1.1051,1073 "step": 1521074 },1075 {1076 "epoch": 0.3883248730964467,1077 "grad_norm": 4.1363517122069435,1078 "learning_rate": 9.745014232471161e-06,1079 "loss": 0.9861,1080 "step": 1531081 },1082 {1083 "epoch": 0.39086294416243655,1084 "grad_norm": 4.619566694659651,1085 "learning_rate": 9.740675107979357e-06,1086 "loss": 1.0185,1087 "step": 1541088 },1089 {1090 "epoch": 0.3934010152284264,1091 "grad_norm": 3.055238311436169,1092 "learning_rate": 9.736300357211309e-06,1093 "loss": 1.0023,1094 "step": 1551095 },1096 {1097 "epoch": 0.39593908629441626,1098 "grad_norm": 3.7295880831016373,1099 "learning_rate": 9.731890013043367e-06,1100 "loss": 1.0002,1101 "step": 1561102 },1103 {1104 "epoch": 0.39847715736040606,1105 "grad_norm": 3.3508031862079637,1106 "learning_rate": 9.727444108619365e-06,1107 "loss": 1.1507,1108 "step": 1571109 },1110 {1111 "epoch": 0.4010152284263959,1112 "grad_norm": 2.723651526969142,1113 "learning_rate": 9.722962677350367e-06,1114 "loss": 1.1364,1115 "step": 1581116 },1117 {1118 "epoch": 0.4035532994923858,1119 "grad_norm": 3.774699978960873,1120 "learning_rate": 9.718445752914427e-06,1121 "loss": 1.1025,1122 "step": 1591123 },1124 {1125 "epoch": 0.40609137055837563,1126 "grad_norm": 2.7659454853714927,1127 "learning_rate": 9.713893369256334e-06,1128 "loss": 1.1713,1129 "step": 1601130 },1131 {1132 "epoch": 0.4086294416243655,1133 "grad_norm": 2.538756260743843,1134 "learning_rate": 9.709305560587344e-06,1135 "loss": 1.0911,1136 "step": 1611137 },1138 {1139 "epoch": 0.41116751269035534,1140 "grad_norm": 4.320782683762776,1141 "learning_rate": 9.704682361384941e-06,1142 "loss": 1.1632,1143 "step": 1621144 },1145 {1146 "epoch": 0.4137055837563452,1147 "grad_norm": 4.80159996293837,1148 "learning_rate": 9.700023806392569e-06,1149 "loss": 1.0217,1150 "step": 1631151 },1152 {1153 "epoch": 0.41624365482233505,1154 "grad_norm": 2.7673753672207595,1155 "learning_rate": 9.695329930619368e-06,1156 "loss": 1.1201,1157 "step": 1641158 },1159 {1160 "epoch": 0.41878172588832485,1161 "grad_norm": 3.104153414839049,1162 "learning_rate": 9.690600769339916e-06,1163 "loss": 1.078,1164 "step": 1651165 },1166 {1167 "epoch": 0.4213197969543147,1168 "grad_norm": 7.423796156142243,1169 "learning_rate": 9.685836358093964e-06,1170 "loss": 1.1045,1171 "step": 1661172 },1173 {1174 "epoch": 0.42385786802030456,1175 "grad_norm": 2.9797528305128083,1176 "learning_rate": 9.681036732686165e-06,1177 "loss": 1.1647,1178 "step": 1671179 },1180 {1181 "epoch": 0.4263959390862944,1182 "grad_norm": 2.851862749531238,1183 "learning_rate": 9.676201929185809e-06,1184 "loss": 0.9319,1185 "step": 1681186 },1187 {1188 "epoch": 0.4289340101522843,1189 "grad_norm": 2.8454139750098557,1190 "learning_rate": 9.671331983926548e-06,1191 "loss": 1.0268,1192 "step": 1691193 },1194 {1195 "epoch": 0.43147208121827413,1196 "grad_norm": 1.9807490940657426,1197 "learning_rate": 9.666426933506126e-06,1198 "loss": 1.1493,1199 "step": 1701200 },