LenDigLearn/formality-classifier-mdeberta-v3-base
0435
1{2 "best_metric": null,3 "best_model_checkpoint": null,4 "epoch": 5.95971351835273,5 "eval_steps": 500,6 "global_step": 834,7 "is_hyper_param_search": false,8 "is_local_process_zero": true,9 "is_world_process_zero": true,10 "log_history": [11 {12 "epoch": 0.007162041181736795,13 "grad_norm": 1.5651538372039795,14 "learning_rate": 9.98800959232614e-06,15 "loss": 1.1028,16 "step": 117 },18 {19 "epoch": 0.01432408236347359,20 "grad_norm": 2.358640193939209,21 "learning_rate": 9.976019184652279e-06,22 "loss": 1.1257,23 "step": 224 },25 {26 "epoch": 0.021486123545210387,27 "grad_norm": 1.7103272676467896,28 "learning_rate": 9.964028776978418e-06,29 "loss": 1.1098,30 "step": 331 },32 {33 "epoch": 0.02864816472694718,34 "grad_norm": 1.783992886543274,35 "learning_rate": 9.952038369304557e-06,36 "loss": 1.0858,37 "step": 438 },39 {40 "epoch": 0.03581020590868397,41 "grad_norm": 1.0596697330474854,42 "learning_rate": 9.940047961630696e-06,43 "loss": 1.0924,44 "step": 545 },46 {47 "epoch": 0.04297224709042077,48 "grad_norm": 1.694056510925293,49 "learning_rate": 9.928057553956835e-06,50 "loss": 1.0912,51 "step": 652 },53 {54 "epoch": 0.050134288272157566,55 "grad_norm": 1.4265025854110718,56 "learning_rate": 9.916067146282976e-06,57 "loss": 1.0833,58 "step": 759 },60 {61 "epoch": 0.05729632945389436,62 "grad_norm": 2.3417539596557617,63 "learning_rate": 9.904076738609113e-06,64 "loss": 1.1031,65 "step": 866 },67 {68 "epoch": 0.06445837063563116,69 "grad_norm": 1.6366913318634033,70 "learning_rate": 9.892086330935252e-06,71 "loss": 1.1186,72 "step": 973 },74 {75 "epoch": 0.07162041181736795,76 "grad_norm": 2.713798761367798,77 "learning_rate": 9.880095923261391e-06,78 "loss": 1.119,79 "step": 1080 },81 {82 "epoch": 0.07878245299910475,83 "grad_norm": 1.0447508096694946,84 "learning_rate": 9.86810551558753e-06,85 "loss": 1.0836,86 "step": 1187 },88 {89 "epoch": 0.08594449418084155,90 "grad_norm": 1.4873104095458984,91 "learning_rate": 9.85611510791367e-06,92 "loss": 1.1093,93 "step": 1294 },95 {96 "epoch": 0.09310653536257833,97 "grad_norm": 2.0511322021484375,98 "learning_rate": 9.844124700239808e-06,99 "loss": 1.1048,100 "step": 13101 },102 {103 "epoch": 0.10026857654431513,104 "grad_norm": 1.8400065898895264,105 "learning_rate": 9.832134292565947e-06,106 "loss": 1.1084,107 "step": 14108 },109 {110 "epoch": 0.10743061772605192,111 "grad_norm": 1.743239402770996,112 "learning_rate": 9.820143884892086e-06,113 "loss": 1.0893,114 "step": 15115 },116 {117 "epoch": 0.11459265890778872,118 "grad_norm": 0.8387613296508789,119 "learning_rate": 9.808153477218227e-06,120 "loss": 1.101,121 "step": 16122 },123 {124 "epoch": 0.12175470008952552,125 "grad_norm": 2.1584479808807373,126 "learning_rate": 9.796163069544366e-06,127 "loss": 1.1003,128 "step": 17129 },130 {131 "epoch": 0.12891674127126232,132 "grad_norm": 1.1021759510040283,133 "learning_rate": 9.784172661870505e-06,134 "loss": 1.0921,135 "step": 18136 },137 {138 "epoch": 0.1360787824529991,139 "grad_norm": 1.9304773807525635,140 "learning_rate": 9.772182254196644e-06,141 "loss": 1.0968,142 "step": 19143 },144 {145 "epoch": 0.1432408236347359,146 "grad_norm": 1.6461104154586792,147 "learning_rate": 9.760191846522783e-06,148 "loss": 1.0937,149 "step": 20150 },151 {152 "epoch": 0.1504028648164727,153 "grad_norm": 1.5581350326538086,154 "learning_rate": 9.748201438848922e-06,155 "loss": 1.0716,156 "step": 21157 },158 {159 "epoch": 0.1575649059982095,160 "grad_norm": 1.9193130731582642,161 "learning_rate": 9.736211031175061e-06,162 "loss": 1.0634,163 "step": 22164 },165 {166 "epoch": 0.1647269471799463,167 "grad_norm": 1.8347828388214111,168 "learning_rate": 9.724220623501199e-06,169 "loss": 1.0665,170 "step": 23171 },172 {173 "epoch": 0.1718889883616831,174 "grad_norm": 2.1090774536132812,175 "learning_rate": 9.712230215827338e-06,176 "loss": 1.0967,177 "step": 24178 },179 {180 "epoch": 0.17905102954341987,181 "grad_norm": 1.6594020128250122,182 "learning_rate": 9.700239808153478e-06,183 "loss": 1.0695,184 "step": 25185 },186 {187 "epoch": 0.18621307072515667,188 "grad_norm": 1.6360571384429932,189 "learning_rate": 9.688249400479617e-06,190 "loss": 1.0808,191 "step": 26192 },193 {194 "epoch": 0.19337511190689347,195 "grad_norm": 1.7902008295059204,196 "learning_rate": 9.676258992805757e-06,197 "loss": 1.0693,198 "step": 27199 },200 {201 "epoch": 0.20053715308863027,202 "grad_norm": 1.9148868322372437,203 "learning_rate": 9.664268585131896e-06,204 "loss": 1.0656,205 "step": 28206 },207 {208 "epoch": 0.20769919427036707,209 "grad_norm": 1.5940035581588745,210 "learning_rate": 9.652278177458035e-06,211 "loss": 1.0617,212 "step": 29213 },214 {215 "epoch": 0.21486123545210384,216 "grad_norm": 2.1188247203826904,217 "learning_rate": 9.640287769784174e-06,218 "loss": 1.0571,219 "step": 30220 },221 {222 "epoch": 0.22202327663384064,223 "grad_norm": 2.0343472957611084,224 "learning_rate": 9.628297362110313e-06,225 "loss": 1.0601,226 "step": 31227 },228 {229 "epoch": 0.22918531781557744,230 "grad_norm": 2.536809206008911,231 "learning_rate": 9.616306954436452e-06,232 "loss": 1.059,233 "step": 32234 },235 {236 "epoch": 0.23634735899731424,237 "grad_norm": 2.986196279525757,238 "learning_rate": 9.60431654676259e-06,239 "loss": 0.9905,240 "step": 33241 },242 {243 "epoch": 0.24350940017905104,244 "grad_norm": 2.9638538360595703,245 "learning_rate": 9.59232613908873e-06,246 "loss": 1.0369,247 "step": 34248 },249 {250 "epoch": 0.25067144136078784,251 "grad_norm": 3.4822328090667725,252 "learning_rate": 9.580335731414869e-06,253 "loss": 1.0549,254 "step": 35255 },256 {257 "epoch": 0.25783348254252464,258 "grad_norm": 2.860246181488037,259 "learning_rate": 9.568345323741008e-06,260 "loss": 1.0131,261 "step": 36262 },263 {264 "epoch": 0.26499552372426144,265 "grad_norm": 3.4336676597595215,266 "learning_rate": 9.556354916067147e-06,267 "loss": 1.032,268 "step": 37269 },270 {271 "epoch": 0.2721575649059982,272 "grad_norm": 3.2346091270446777,273 "learning_rate": 9.544364508393286e-06,274 "loss": 1.0287,275 "step": 38276 },277 {278 "epoch": 0.279319606087735,279 "grad_norm": 2.7058355808258057,280 "learning_rate": 9.532374100719425e-06,281 "loss": 1.0313,282 "step": 39283 },284 {285 "epoch": 0.2864816472694718,286 "grad_norm": 3.560464382171631,287 "learning_rate": 9.520383693045564e-06,288 "loss": 1.013,289 "step": 40290 },291 {292 "epoch": 0.2936436884512086,293 "grad_norm": 3.6023006439208984,294 "learning_rate": 9.508393285371703e-06,295 "loss": 0.9168,296 "step": 41297 },298 {299 "epoch": 0.3008057296329454,300 "grad_norm": 3.6482856273651123,301 "learning_rate": 9.496402877697842e-06,302 "loss": 0.973,303 "step": 42304 },305 {306 "epoch": 0.3079677708146822,307 "grad_norm": 3.4008662700653076,308 "learning_rate": 9.484412470023981e-06,309 "loss": 1.0305,310 "step": 43311 },312 {313 "epoch": 0.315129811996419,314 "grad_norm": 3.068812847137451,315 "learning_rate": 9.47242206235012e-06,316 "loss": 0.9169,317 "step": 44318 },319 {320 "epoch": 0.3222918531781558,321 "grad_norm": 3.736107349395752,322 "learning_rate": 9.46043165467626e-06,323 "loss": 1.0063,324 "step": 45325 },326 {327 "epoch": 0.3294538943598926,328 "grad_norm": 4.98853063583374,329 "learning_rate": 9.448441247002398e-06,330 "loss": 0.9408,331 "step": 46332 },333 {334 "epoch": 0.3366159355416294,335 "grad_norm": 3.7207694053649902,336 "learning_rate": 9.436450839328539e-06,337 "loss": 0.9363,338 "step": 47339 },340 {341 "epoch": 0.3437779767233662,342 "grad_norm": 4.021739959716797,343 "learning_rate": 9.424460431654678e-06,344 "loss": 0.9955,345 "step": 48346 },347 {348 "epoch": 0.35094001790510293,349 "grad_norm": 3.676600694656372,350 "learning_rate": 9.412470023980817e-06,351 "loss": 1.0505,352 "step": 49353 },354 {355 "epoch": 0.35810205908683973,356 "grad_norm": 3.9010024070739746,357 "learning_rate": 9.400479616306956e-06,358 "loss": 0.9115,359 "step": 50360 },361 {362 "epoch": 0.36526410026857653,363 "grad_norm": 3.856921672821045,364 "learning_rate": 9.388489208633095e-06,365 "loss": 0.9625,366 "step": 51367 },368 {369 "epoch": 0.37242614145031333,370 "grad_norm": 3.6618595123291016,371 "learning_rate": 9.376498800959234e-06,372 "loss": 0.9107,373 "step": 52374 },375 {376 "epoch": 0.37958818263205013,377 "grad_norm": 3.955465793609619,378 "learning_rate": 9.364508393285371e-06,379 "loss": 0.9036,380 "step": 53381 },382 {383 "epoch": 0.38675022381378693,384 "grad_norm": 4.451611518859863,385 "learning_rate": 9.35251798561151e-06,386 "loss": 0.8745,387 "step": 54388 },389 {390 "epoch": 0.39391226499552373,391 "grad_norm": 3.950402021408081,392 "learning_rate": 9.34052757793765e-06,393 "loss": 0.8967,394 "step": 55395 },396 {397 "epoch": 0.40107430617726053,398 "grad_norm": 4.007294654846191,399 "learning_rate": 9.32853717026379e-06,400 "loss": 0.9382,401 "step": 56402 },403 {404 "epoch": 0.40823634735899733,405 "grad_norm": 4.601572036743164,406 "learning_rate": 9.31654676258993e-06,407 "loss": 0.892,408 "step": 57409 },410 {411 "epoch": 0.41539838854073413,412 "grad_norm": 3.6578915119171143,413 "learning_rate": 9.304556354916068e-06,414 "loss": 0.8066,415 "step": 58416 },417 {418 "epoch": 0.42256042972247093,419 "grad_norm": 4.2530293464660645,420 "learning_rate": 9.292565947242207e-06,421 "loss": 0.7893,422 "step": 59423 },424 {425 "epoch": 0.4297224709042077,426 "grad_norm": 4.652935028076172,427 "learning_rate": 9.280575539568346e-06,428 "loss": 0.805,429 "step": 60430 },431 {432 "epoch": 0.4368845120859445,433 "grad_norm": 4.985301494598389,434 "learning_rate": 9.268585131894485e-06,435 "loss": 0.8248,436 "step": 61437 },438 {439 "epoch": 0.4440465532676813,440 "grad_norm": 5.5606513023376465,441 "learning_rate": 9.256594724220624e-06,442 "loss": 0.8412,443 "step": 62444 },445 {446 "epoch": 0.4512085944494181,447 "grad_norm": 4.6756110191345215,448 "learning_rate": 9.244604316546764e-06,449 "loss": 0.8119,450 "step": 63451 },452 {453 "epoch": 0.4583706356311549,454 "grad_norm": 4.607848644256592,455 "learning_rate": 9.232613908872903e-06,456 "loss": 0.7553,457 "step": 64458 },459 {460 "epoch": 0.4655326768128917,461 "grad_norm": 5.126153945922852,462 "learning_rate": 9.220623501199042e-06,463 "loss": 0.7668,464 "step": 65465 },466 {467 "epoch": 0.4726947179946285,468 "grad_norm": 4.498857498168945,469 "learning_rate": 9.20863309352518e-06,470 "loss": 0.727,471 "step": 66472 },473 {474 "epoch": 0.4798567591763653,475 "grad_norm": 5.598169326782227,476 "learning_rate": 9.19664268585132e-06,477 "loss": 0.8671,478 "step": 67479 },480 {481 "epoch": 0.4870188003581021,482 "grad_norm": 5.176477432250977,483 "learning_rate": 9.184652278177459e-06,484 "loss": 0.8697,485 "step": 68486 },487 {488 "epoch": 0.4941808415398389,489 "grad_norm": 4.874248504638672,490 "learning_rate": 9.172661870503598e-06,491 "loss": 0.7736,492 "step": 69493 },494 {495 "epoch": 0.5013428827215757,496 "grad_norm": 4.082653999328613,497 "learning_rate": 9.160671462829737e-06,498 "loss": 0.7047,499 "step": 70500 },501 {502 "epoch": 0.5085049239033125,503 "grad_norm": 5.192132949829102,504 "learning_rate": 9.148681055155876e-06,505 "loss": 0.7359,506 "step": 71507 },508 {509 "epoch": 0.5156669650850493,510 "grad_norm": 5.804781436920166,511 "learning_rate": 9.136690647482015e-06,512 "loss": 0.6859,513 "step": 72514 },515 {516 "epoch": 0.5228290062667861,517 "grad_norm": 4.250144004821777,518 "learning_rate": 9.124700239808154e-06,519 "loss": 0.7178,520 "step": 73521 },522 {523 "epoch": 0.5299910474485229,524 "grad_norm": 4.898803234100342,525 "learning_rate": 9.112709832134293e-06,526 "loss": 0.8012,527 "step": 74528 },529 {530 "epoch": 0.5371530886302597,531 "grad_norm": 4.092855453491211,532 "learning_rate": 9.100719424460432e-06,533 "loss": 0.595,534 "step": 75535 },536 {537 "epoch": 0.5443151298119964,538 "grad_norm": 4.206191062927246,539 "learning_rate": 9.088729016786571e-06,540 "loss": 0.6574,541 "step": 76542 },543 {544 "epoch": 0.5514771709937332,545 "grad_norm": 5.5786967277526855,546 "learning_rate": 9.07673860911271e-06,547 "loss": 0.6096,548 "step": 77549 },550 {551 "epoch": 0.55863921217547,552 "grad_norm": 4.80825138092041,553 "learning_rate": 9.064748201438849e-06,554 "loss": 0.6351,555 "step": 78556 },557 {558 "epoch": 0.5658012533572068,559 "grad_norm": 5.1291608810424805,560 "learning_rate": 9.05275779376499e-06,561 "loss": 0.6163,562 "step": 79563 },564 {565 "epoch": 0.5729632945389436,566 "grad_norm": 4.304827690124512,567 "learning_rate": 9.040767386091129e-06,568 "loss": 0.6089,569 "step": 80570 },571 {572 "epoch": 0.5801253357206804,573 "grad_norm": 3.9486804008483887,574 "learning_rate": 9.028776978417268e-06,575 "loss": 0.5804,576 "step": 81577 },578 {579 "epoch": 0.5872873769024172,580 "grad_norm": 6.8340163230896,581 "learning_rate": 9.016786570743405e-06,582 "loss": 0.6102,583 "step": 82584 },585 {586 "epoch": 0.594449418084154,587 "grad_norm": 5.0892133712768555,588 "learning_rate": 9.004796163069544e-06,589 "loss": 0.6376,590 "step": 83591 },592 {593 "epoch": 0.6016114592658908,594 "grad_norm": 4.589208126068115,595 "learning_rate": 8.992805755395683e-06,596 "loss": 0.6618,597 "step": 84598 },599 {600 "epoch": 0.6087735004476276,601 "grad_norm": 4.036871433258057,602 "learning_rate": 8.980815347721822e-06,603 "loss": 0.6268,604 "step": 85605 },606 {607 "epoch": 0.6159355416293644,608 "grad_norm": 5.117236614227295,609 "learning_rate": 8.968824940047961e-06,610 "loss": 0.5782,611 "step": 86612 },613 {614 "epoch": 0.6230975828111012,615 "grad_norm": 5.529454708099365,616 "learning_rate": 8.956834532374102e-06,617 "loss": 0.6378,618 "step": 87619 },620 {621 "epoch": 0.630259623992838,622 "grad_norm": 4.290615558624268,623 "learning_rate": 8.944844124700241e-06,624 "loss": 0.4607,625 "step": 88626 },627 {628 "epoch": 0.6374216651745748,629 "grad_norm": 4.275355815887451,630 "learning_rate": 8.93285371702638e-06,631 "loss": 0.5444,632 "step": 89633 },634 {635 "epoch": 0.6445837063563116,636 "grad_norm": 5.064560890197754,637 "learning_rate": 8.92086330935252e-06,638 "loss": 0.7254,639 "step": 90640 },641 {642 "epoch": 0.6517457475380484,643 "grad_norm": 4.527130126953125,644 "learning_rate": 8.908872901678658e-06,645 "loss": 0.5581,646 "step": 91647 },648 {649 "epoch": 0.6589077887197852,650 "grad_norm": 5.649165630340576,651 "learning_rate": 8.896882494004797e-06,652 "loss": 0.5265,653 "step": 92654 },655 {656 "epoch": 0.666069829901522,657 "grad_norm": 4.565707206726074,658 "learning_rate": 8.884892086330936e-06,659 "loss": 0.5161,660 "step": 93661 },662 {663 "epoch": 0.6732318710832588,664 "grad_norm": 6.295898914337158,665 "learning_rate": 8.872901678657075e-06,666 "loss": 0.5414,667 "step": 94668 },669 {670 "epoch": 0.6803939122649956,671 "grad_norm": 8.986715316772461,672 "learning_rate": 8.860911270983214e-06,673 "loss": 0.5894,674 "step": 95675 },676 {677 "epoch": 0.6875559534467324,678 "grad_norm": 6.694461822509766,679 "learning_rate": 8.848920863309353e-06,680 "loss": 0.5679,681 "step": 96682 },683 {684 "epoch": 0.6947179946284691,685 "grad_norm": 5.961154460906982,686 "learning_rate": 8.836930455635492e-06,687 "loss": 0.6379,688 "step": 97689 },690 {691 "epoch": 0.7018800358102059,692 "grad_norm": 4.6056671142578125,693 "learning_rate": 8.824940047961632e-06,694 "loss": 0.5691,695 "step": 98696 },697 {698 "epoch": 0.7090420769919427,699 "grad_norm": 5.036160945892334,700 "learning_rate": 8.81294964028777e-06,701 "loss": 0.5234,702 "step": 99703 },704 {705 "epoch": 0.7162041181736795,706 "grad_norm": 4.869359016418457,707 "learning_rate": 8.80095923261391e-06,708 "loss": 0.4494,709 "step": 100710 },711 {712 "epoch": 0.7233661593554163,713 "grad_norm": 6.883158206939697,714 "learning_rate": 8.788968824940049e-06,715 "loss": 0.5863,716 "step": 101717 },718 {719 "epoch": 0.7305282005371531,720 "grad_norm": 4.8142805099487305,721 "learning_rate": 8.776978417266188e-06,722 "loss": 0.4585,723 "step": 102724 },725 {726 "epoch": 0.7376902417188899,727 "grad_norm": 4.156213760375977,728 "learning_rate": 8.764988009592327e-06,729 "loss": 0.4224,730 "step": 103731 },732 {733 "epoch": 0.7448522829006267,734 "grad_norm": 5.524331569671631,735 "learning_rate": 8.752997601918466e-06,736 "loss": 0.5855,737 "step": 104738 },739 {740 "epoch": 0.7520143240823635,741 "grad_norm": 4.5275468826293945,742 "learning_rate": 8.741007194244605e-06,743 "loss": 0.3134,744 "step": 105745 },746 {747 "epoch": 0.7591763652641003,748 "grad_norm": 6.391297340393066,749 "learning_rate": 8.729016786570744e-06,750 "loss": 0.4662,751 "step": 106752 },753 {754 "epoch": 0.7663384064458371,755 "grad_norm": 4.844995498657227,756 "learning_rate": 8.717026378896883e-06,757 "loss": 0.5037,758 "step": 107759 },760 {761 "epoch": 0.7735004476275739,762 "grad_norm": 5.861647129058838,763 "learning_rate": 8.705035971223022e-06,764 "loss": 0.4134,765 "step": 108766 },767 {768 "epoch": 0.7806624888093107,769 "grad_norm": 4.5392889976501465,770 "learning_rate": 8.693045563549161e-06,771 "loss": 0.4099,772 "step": 109773 },774 {775 "epoch": 0.7878245299910475,776 "grad_norm": 4.010335922241211,777 "learning_rate": 8.681055155875302e-06,778 "loss": 0.3897,779 "step": 110780 },781 {782 "epoch": 0.7949865711727843,783 "grad_norm": 5.2261433601379395,784 "learning_rate": 8.66906474820144e-06,785 "loss": 0.3422,786 "step": 111787 },788 {789 "epoch": 0.8021486123545211,790 "grad_norm": 5.837971210479736,791 "learning_rate": 8.657074340527578e-06,792 "loss": 0.4188,793 "step": 112794 },795 {796 "epoch": 0.8093106535362579,797 "grad_norm": 7.071847915649414,798 "learning_rate": 8.645083932853717e-06,799 "loss": 0.5138,800 "step": 113801 },802 {803 "epoch": 0.8164726947179947,804 "grad_norm": 3.631950855255127,805 "learning_rate": 8.633093525179856e-06,806 "loss": 0.2924,807 "step": 114808 },809 {810 "epoch": 0.8236347358997315,811 "grad_norm": 5.4959797859191895,812 "learning_rate": 8.621103117505995e-06,813 "loss": 0.4857,814 "step": 115815 },816 {817 "epoch": 0.8307967770814683,818 "grad_norm": 6.527896404266357,819 "learning_rate": 8.609112709832134e-06,820 "loss": 0.4211,821 "step": 116822 },823 {824 "epoch": 0.8379588182632051,825 "grad_norm": 7.07539176940918,826 "learning_rate": 8.597122302158273e-06,827 "loss": 0.481,828 "step": 117829 },830 {831 "epoch": 0.8451208594449419,832 "grad_norm": 5.752196311950684,833 "learning_rate": 8.585131894484412e-06,834 "loss": 0.4774,835 "step": 118836 },837 {838 "epoch": 0.8522829006266786,839 "grad_norm": 3.1388776302337646,840 "learning_rate": 8.573141486810553e-06,841 "loss": 0.2974,842 "step": 119843 },844 {845 "epoch": 0.8594449418084154,846 "grad_norm": 5.351109504699707,847 "learning_rate": 8.561151079136692e-06,848 "loss": 0.333,849 "step": 120850 },851 {852 "epoch": 0.8666069829901522,853 "grad_norm": 4.641998767852783,854 "learning_rate": 8.549160671462831e-06,855 "loss": 0.4377,856 "step": 121857 },858 {859 "epoch": 0.873769024171889,860 "grad_norm": 9.292861938476562,861 "learning_rate": 8.53717026378897e-06,862 "loss": 0.497,863 "step": 122864 },865 {866 "epoch": 0.8809310653536258,867 "grad_norm": 5.21453857421875,868 "learning_rate": 8.525179856115109e-06,869 "loss": 0.4271,870 "step": 123871 },872 {873 "epoch": 0.8880931065353626,874 "grad_norm": 6.3802618980407715,875 "learning_rate": 8.513189448441248e-06,876 "loss": 0.4672,877 "step": 124878 },879 {880 "epoch": 0.8952551477170994,881 "grad_norm": 5.154406547546387,882 "learning_rate": 8.501199040767387e-06,883 "loss": 0.2783,884 "step": 125885 },886 {887 "epoch": 0.9024171888988362,888 "grad_norm": 3.9693143367767334,889 "learning_rate": 8.489208633093526e-06,890 "loss": 0.3932,891 "step": 126892 },893 {894 "epoch": 0.909579230080573,895 "grad_norm": 2.942033529281616,896 "learning_rate": 8.477218225419664e-06,897 "loss": 0.3193,898 "step": 127899 },900 {901 "epoch": 0.9167412712623098,902 "grad_norm": 4.29665994644165,903 "learning_rate": 8.465227817745804e-06,904 "loss": 0.4377,905 "step": 128906 },907 {908 "epoch": 0.9239033124440466,909 "grad_norm": 5.550212860107422,910 "learning_rate": 8.453237410071943e-06,911 "loss": 0.3315,912 "step": 129913 },914 {915 "epoch": 0.9310653536257834,916 "grad_norm": 6.654735565185547,917 "learning_rate": 8.441247002398082e-06,918 "loss": 0.4388,919 "step": 130920 },921 {922 "epoch": 0.9382273948075202,923 "grad_norm": 5.80216121673584,924 "learning_rate": 8.429256594724221e-06,925 "loss": 0.3865,926 "step": 131927 },928 {929 "epoch": 0.945389435989257,930 "grad_norm": 6.76437520980835,931 "learning_rate": 8.41726618705036e-06,932 "loss": 0.5202,933 "step": 132934 },935 {936 "epoch": 0.9525514771709938,937 "grad_norm": 9.009016990661621,938 "learning_rate": 8.4052757793765e-06,939 "loss": 0.4008,940 "step": 133941 },942 {943 "epoch": 0.9597135183527306,944 "grad_norm": 9.987932205200195,945 "learning_rate": 8.393285371702639e-06,946 "loss": 0.4824,947 "step": 134948 },949 {950 "epoch": 0.9668755595344674,951 "grad_norm": 10.408086776733398,952 "learning_rate": 8.381294964028778e-06,953 "loss": 0.7183,954 "step": 135955 },956 {957 "epoch": 0.9740376007162042,958 "grad_norm": 4.125233173370361,959 "learning_rate": 8.369304556354917e-06,960 "loss": 0.331,961 "step": 136962 },963 {964 "epoch": 0.981199641897941,965 "grad_norm": 5.206197738647461,966 "learning_rate": 8.357314148681056e-06,967 "loss": 0.451,968 "step": 137969 },970 {971 "epoch": 0.9883616830796778,972 "grad_norm": 6.510553359985352,973 "learning_rate": 8.345323741007195e-06,974 "loss": 0.2887,975 "step": 138976 },977 {978 "epoch": 0.9955237242614146,979 "grad_norm": 5.558812141418457,980 "learning_rate": 8.333333333333334e-06,981 "loss": 0.2659,982 "step": 139983 },984 {985 "epoch": 1.0,986 "grad_norm": 5.024322509765625,987 "learning_rate": 8.321342925659473e-06,988 "loss": 0.2857,989 "step": 140990 },991 {992 "epoch": 1.0,993 "eval_accuracy": 0.8551307847082495,994 "eval_loss": 0.34348970651626587,995 "eval_runtime": 12.772,996 "eval_samples_per_second": 38.913,997 "eval_steps_per_second": 38.913,998 "step": 140999 },1000 {1001 "epoch": 1.0071620411817368,1002 "grad_norm": 5.62790584564209,1003 "learning_rate": 8.309352517985614e-06,1004 "loss": 0.3689,1005 "step": 1411006 },1007 {1008 "epoch": 1.0143240823634736,1009 "grad_norm": 6.509753704071045,1010 "learning_rate": 8.29736211031175e-06,1011 "loss": 0.3419,1012 "step": 1421013 },1014 {1015 "epoch": 1.0214861235452104,1016 "grad_norm": 7.264653205871582,1017 "learning_rate": 8.28537170263789e-06,1018 "loss": 0.2551,1019 "step": 1431020 },1021 {1022 "epoch": 1.0286481647269472,1023 "grad_norm": 6.89661169052124,1024 "learning_rate": 8.273381294964029e-06,1025 "loss": 0.4026,1026 "step": 1441027 },1028 {1029 "epoch": 1.035810205908684,1030 "grad_norm": 6.0390238761901855,1031 "learning_rate": 8.261390887290168e-06,1032 "loss": 0.2978,1033 "step": 1451034 },1035 {1036 "epoch": 1.0429722470904208,1037 "grad_norm": 6.132388591766357,1038 "learning_rate": 8.249400479616307e-06,1039 "loss": 0.4529,1040 "step": 1461041 },1042 {1043 "epoch": 1.0501342882721576,1044 "grad_norm": 6.270555019378662,1045 "learning_rate": 8.237410071942446e-06,1046 "loss": 0.4341,1047 "step": 1471048 },1049 {1050 "epoch": 1.0572963294538944,1051 "grad_norm": 8.636746406555176,1052 "learning_rate": 8.225419664268585e-06,1053 "loss": 0.3452,1054 "step": 1481055 },1056 {1057 "epoch": 1.0644583706356312,1058 "grad_norm": 5.3527021408081055,1059 "learning_rate": 8.213429256594724e-06,1060 "loss": 0.2689,1061 "step": 1491062 },1063 {1064 "epoch": 1.071620411817368,1065 "grad_norm": 5.665110111236572,1066 "learning_rate": 8.201438848920865e-06,1067 "loss": 0.5618,1068 "step": 1501069 },1070 {1071 "epoch": 1.0787824529991048,1072 "grad_norm": 9.846869468688965,1073 "learning_rate": 8.189448441247004e-06,1074 "loss": 0.3931,1075 "step": 1511076 },1077 {1078 "epoch": 1.0859444941808416,1079 "grad_norm": 8.280915260314941,1080 "learning_rate": 8.177458033573143e-06,1081 "loss": 0.3301,1082 "step": 1521083 },1084 {1085 "epoch": 1.0931065353625784,1086 "grad_norm": 5.660332202911377,1087 "learning_rate": 8.165467625899282e-06,1088 "loss": 0.372,1089 "step": 1531090 },1091 {1092 "epoch": 1.1002685765443152,1093 "grad_norm": 3.366448402404785,1094 "learning_rate": 8.153477218225421e-06,1095 "loss": 0.3427,1096 "step": 1541097 },1098 {1099 "epoch": 1.107430617726052,1100 "grad_norm": 6.918087959289551,1101 "learning_rate": 8.14148681055156e-06,1102 "loss": 0.5082,1103 "step": 1551104 },1105 {1106 "epoch": 1.1145926589077888,1107 "grad_norm": 7.009018898010254,1108 "learning_rate": 8.129496402877699e-06,1109 "loss": 0.3534,1110 "step": 1561111 },1112 {1113 "epoch": 1.1217547000895256,1114 "grad_norm": 5.730655193328857,1115 "learning_rate": 8.117505995203836e-06,1116 "loss": 0.2806,1117 "step": 1571118 },1119 {1120 "epoch": 1.1289167412712624,1121 "grad_norm": 3.503355026245117,1122 "learning_rate": 8.105515587529975e-06,1123 "loss": 0.2374,1124 "step": 1581125 },1126 {1127 "epoch": 1.1360787824529992,1128 "grad_norm": 3.6845366954803467,1129 "learning_rate": 8.093525179856116e-06,1130 "loss": 0.2822,1131 "step": 1591132 },1133 {1134 "epoch": 1.143240823634736,1135 "grad_norm": 8.738545417785645,1136 "learning_rate": 8.081534772182255e-06,1137 "loss": 0.3553,1138 "step": 1601139 },1140 {1141 "epoch": 1.1504028648164728,1142 "grad_norm": 12.152175903320312,1143 "learning_rate": 8.069544364508394e-06,1144 "loss": 0.264,1145 "step": 1611146 },1147 {1148 "epoch": 1.1575649059982096,1149 "grad_norm": 6.637088775634766,1150 "learning_rate": 8.057553956834533e-06,1151 "loss": 0.3602,1152 "step": 1621153 },1154 {1155 "epoch": 1.1647269471799464,1156 "grad_norm": 11.342058181762695,1157 "learning_rate": 8.045563549160672e-06,1158 "loss": 0.3529,1159 "step": 1631160 },1161 {1162 "epoch": 1.1718889883616832,1163 "grad_norm": 3.130880355834961,1164 "learning_rate": 8.033573141486811e-06,1165 "loss": 0.2449,1166 "step": 1641167 },1168 {1169 "epoch": 1.1790510295434198,1170 "grad_norm": 4.657078266143799,1171 "learning_rate": 8.02158273381295e-06,1172 "loss": 0.2095,1173 "step": 1651174 },1175 {1176 "epoch": 1.1862130707251566,1177 "grad_norm": 11.053173065185547,1178 "learning_rate": 8.00959232613909e-06,1179 "loss": 0.3824,1180 "step": 1661181 },1182 {1183 "epoch": 1.1933751119068934,1184 "grad_norm": 8.9373779296875,1185 "learning_rate": 7.997601918465228e-06,1186 "loss": 0.5074,1187 "step": 1671188 },1189 {1190 "epoch": 1.2005371530886302,1191 "grad_norm": 7.14840030670166,1192 "learning_rate": 7.985611510791367e-06,1193 "loss": 0.3061,1194 "step": 1681195 },1196 {1197 "epoch": 1.207699194270367,1198 "grad_norm": 6.889973163604736,1199 "learning_rate": 7.973621103117507e-06,1200 "loss": 0.3045,