Delta-Vector/Rei-V2-12B
1318
1{2 "best_metric": null,3 "best_model_checkpoint": null,4 "epoch": 2.0,5 "eval_steps": 500,6 "global_step": 764,7 "is_hyper_param_search": false,8 "is_local_process_zero": true,9 "is_world_process_zero": true,10 "log_history": [11 {12 "epoch": 0.002617801047120419,13 "grad_norm": 12.144990537050639,14 "learning_rate": 5e-08,15 "loss": 1.2113,16 "step": 117 },18 {19 "epoch": 0.005235602094240838,20 "grad_norm": 13.176179220886064,21 "learning_rate": 1e-07,22 "loss": 1.3287,23 "step": 224 },25 {26 "epoch": 0.007853403141361256,27 "grad_norm": 12.924711168956318,28 "learning_rate": 1.5e-07,29 "loss": 1.2798,30 "step": 331 },32 {33 "epoch": 0.010471204188481676,34 "grad_norm": 12.21691289343528,35 "learning_rate": 2e-07,36 "loss": 1.2284,37 "step": 438 },39 {40 "epoch": 0.013089005235602094,41 "grad_norm": 11.997438945474764,42 "learning_rate": 2.5e-07,43 "loss": 1.2477,44 "step": 545 },46 {47 "epoch": 0.015706806282722512,48 "grad_norm": 12.217585739384367,49 "learning_rate": 3e-07,50 "loss": 1.2437,51 "step": 652 },53 {54 "epoch": 0.01832460732984293,55 "grad_norm": 11.875859411166187,56 "learning_rate": 3.5e-07,57 "loss": 1.2108,58 "step": 759 },60 {61 "epoch": 0.020942408376963352,62 "grad_norm": 11.64973795949067,63 "learning_rate": 4e-07,64 "loss": 1.2131,65 "step": 866 },67 {68 "epoch": 0.02356020942408377,69 "grad_norm": 12.45663018271384,70 "learning_rate": 4.5e-07,71 "loss": 1.2516,72 "step": 973 },74 {75 "epoch": 0.02617801047120419,76 "grad_norm": 11.239158096874556,77 "learning_rate": 5e-07,78 "loss": 1.1734,79 "step": 1080 },81 {82 "epoch": 0.028795811518324606,83 "grad_norm": 11.710604360468333,84 "learning_rate": 5.5e-07,85 "loss": 1.2206,86 "step": 1187 },88 {89 "epoch": 0.031413612565445025,90 "grad_norm": 11.118095241592131,91 "learning_rate": 6e-07,92 "loss": 1.2074,93 "step": 1294 },95 {96 "epoch": 0.034031413612565446,97 "grad_norm": 11.770346865985067,98 "learning_rate": 6.5e-07,99 "loss": 1.2615,100 "step": 13101 },102 {103 "epoch": 0.03664921465968586,104 "grad_norm": 11.44615754399185,105 "learning_rate": 7e-07,106 "loss": 1.2183,107 "step": 14108 },109 {110 "epoch": 0.03926701570680628,111 "grad_norm": 9.987481097984933,112 "learning_rate": 7.5e-07,113 "loss": 1.1378,114 "step": 15115 },116 {117 "epoch": 0.041884816753926704,118 "grad_norm": 10.087076189949745,119 "learning_rate": 8e-07,120 "loss": 1.2098,121 "step": 16122 },123 {124 "epoch": 0.04450261780104712,125 "grad_norm": 10.02461667279938,126 "learning_rate": 8.499999999999999e-07,127 "loss": 1.1835,128 "step": 17129 },130 {131 "epoch": 0.04712041884816754,132 "grad_norm": 8.79462248217657,133 "learning_rate": 9e-07,134 "loss": 1.1356,135 "step": 18136 },137 {138 "epoch": 0.049738219895287955,139 "grad_norm": 8.628781591254402,140 "learning_rate": 9.499999999999999e-07,141 "loss": 1.1735,142 "step": 19143 },144 {145 "epoch": 0.05235602094240838,146 "grad_norm": 7.738647331698055,147 "learning_rate": 1e-06,148 "loss": 1.1868,149 "step": 20150 },151 {152 "epoch": 0.0549738219895288,153 "grad_norm": 6.233136791291174,154 "learning_rate": 1.05e-06,155 "loss": 1.151,156 "step": 21157 },158 {159 "epoch": 0.05759162303664921,160 "grad_norm": 5.834711461409201,161 "learning_rate": 1.1e-06,162 "loss": 1.129,163 "step": 22164 },165 {166 "epoch": 0.060209424083769635,167 "grad_norm": 5.0077704654863595,168 "learning_rate": 1.1499999999999998e-06,169 "loss": 1.1388,170 "step": 23171 },172 {173 "epoch": 0.06282722513089005,174 "grad_norm": 3.854978376544968,175 "learning_rate": 1.2e-06,176 "loss": 1.052,177 "step": 24178 },179 {180 "epoch": 0.06544502617801047,181 "grad_norm": 3.534169938073168,182 "learning_rate": 1.2499999999999999e-06,183 "loss": 1.0727,184 "step": 25185 },186 {187 "epoch": 0.06806282722513089,188 "grad_norm": 3.2514927992093274,189 "learning_rate": 1.3e-06,190 "loss": 1.1347,191 "step": 26192 },193 {194 "epoch": 0.07068062827225131,195 "grad_norm": 3.102034937556906,196 "learning_rate": 1.35e-06,197 "loss": 1.1357,198 "step": 27199 },200 {201 "epoch": 0.07329842931937172,202 "grad_norm": 2.6056648897843577,203 "learning_rate": 1.4e-06,204 "loss": 1.0368,205 "step": 28206 },207 {208 "epoch": 0.07591623036649214,209 "grad_norm": 5.81258653165808,210 "learning_rate": 1.4499999999999999e-06,211 "loss": 1.1151,212 "step": 29213 },214 {215 "epoch": 0.07853403141361257,216 "grad_norm": 3.4877693307584723,217 "learning_rate": 1.5e-06,218 "loss": 1.1164,219 "step": 30220 },221 {222 "epoch": 0.08115183246073299,223 "grad_norm": 4.02075317392796,224 "learning_rate": 1.55e-06,225 "loss": 1.1174,226 "step": 31227 },228 {229 "epoch": 0.08376963350785341,230 "grad_norm": 3.7625924042569543,231 "learning_rate": 1.6e-06,232 "loss": 1.0247,233 "step": 32234 },235 {236 "epoch": 0.08638743455497382,237 "grad_norm": 3.698847952235366,238 "learning_rate": 1.6499999999999999e-06,239 "loss": 1.0578,240 "step": 33241 },242 {243 "epoch": 0.08900523560209424,244 "grad_norm": 3.4078618253433444,245 "learning_rate": 1.6999999999999998e-06,246 "loss": 1.0513,247 "step": 34248 },249 {250 "epoch": 0.09162303664921466,251 "grad_norm": 3.2909646643289325,252 "learning_rate": 1.75e-06,253 "loss": 1.1018,254 "step": 35255 },256 {257 "epoch": 0.09424083769633508,258 "grad_norm": 2.872238177892186,259 "learning_rate": 1.8e-06,260 "loss": 1.0762,261 "step": 36262 },263 {264 "epoch": 0.0968586387434555,265 "grad_norm": 2.77121115764399,266 "learning_rate": 1.85e-06,267 "loss": 1.0735,268 "step": 37269 },270 {271 "epoch": 0.09947643979057591,272 "grad_norm": 2.549417261476137,273 "learning_rate": 1.8999999999999998e-06,274 "loss": 1.0632,275 "step": 38276 },277 {278 "epoch": 0.10209424083769633,279 "grad_norm": 2.190358595015251,280 "learning_rate": 1.95e-06,281 "loss": 1.0227,282 "step": 39283 },284 {285 "epoch": 0.10471204188481675,286 "grad_norm": 2.5027525699752227,287 "learning_rate": 2e-06,288 "loss": 1.0837,289 "step": 40290 },291 {292 "epoch": 0.10732984293193717,293 "grad_norm": 2.535128732687191,294 "learning_rate": 1.9999905856154088e-06,295 "loss": 1.0799,296 "step": 41297 },298 {299 "epoch": 0.1099476439790576,300 "grad_norm": 1.7534174402541685,301 "learning_rate": 1.999962342638896e-06,302 "loss": 1.0124,303 "step": 42304 },305 {306 "epoch": 0.112565445026178,307 "grad_norm": 2.0631738564308377,308 "learning_rate": 1.9999152716022427e-06,309 "loss": 1.1008,310 "step": 43311 },312 {313 "epoch": 0.11518324607329843,314 "grad_norm": 2.005091740871665,315 "learning_rate": 1.9998493733917385e-06,316 "loss": 1.0374,317 "step": 44318 },319 {320 "epoch": 0.11780104712041885,321 "grad_norm": 1.7413337245159195,322 "learning_rate": 1.999764649248165e-06,323 "loss": 1.0398,324 "step": 45325 },326 {327 "epoch": 0.12041884816753927,328 "grad_norm": 1.745666445155081,329 "learning_rate": 1.999661100766774e-06,330 "loss": 1.0645,331 "step": 46332 },333 {334 "epoch": 0.12303664921465969,335 "grad_norm": 1.8987977735185813,336 "learning_rate": 1.999538729897256e-06,337 "loss": 1.0614,338 "step": 47339 },340 {341 "epoch": 0.1256544502617801,342 "grad_norm": 1.711040452338805,343 "learning_rate": 1.9993975389437036e-06,344 "loss": 1.0332,345 "step": 48346 },347 {348 "epoch": 0.12827225130890052,349 "grad_norm": 1.6087094017934318,350 "learning_rate": 1.999237530564569e-06,351 "loss": 1.0008,352 "step": 49353 },354 {355 "epoch": 0.13089005235602094,356 "grad_norm": 2.0042351547368686,357 "learning_rate": 1.9990587077726125e-06,358 "loss": 1.0768,359 "step": 50360 },361 {362 "epoch": 0.13350785340314136,363 "grad_norm": 1.5264346842814094,364 "learning_rate": 1.998861073934848e-06,365 "loss": 1.0213,366 "step": 51367 },368 {369 "epoch": 0.13612565445026178,370 "grad_norm": 1.7583198075470237,371 "learning_rate": 1.998644632772477e-06,372 "loss": 1.0103,373 "step": 52374 },375 {376 "epoch": 0.1387434554973822,377 "grad_norm": 1.6841921629086405,378 "learning_rate": 1.99840938836082e-06,379 "loss": 1.0116,380 "step": 53381 },382 {383 "epoch": 0.14136125654450263,384 "grad_norm": 9.859700163848672,385 "learning_rate": 1.9981553451292393e-06,386 "loss": 1.0429,387 "step": 54388 },389 {390 "epoch": 0.14397905759162305,391 "grad_norm": 1.6093588714569955,392 "learning_rate": 1.9978825078610574e-06,393 "loss": 0.9722,394 "step": 55395 },396 {397 "epoch": 0.14659685863874344,398 "grad_norm": 1.6921175654924636,399 "learning_rate": 1.9975908816934638e-06,400 "loss": 1.045,401 "step": 56402 },403 {404 "epoch": 0.14921465968586387,405 "grad_norm": 1.4401701807904859,406 "learning_rate": 1.9972804721174198e-06,407 "loss": 1.0094,408 "step": 57409 },410 {411 "epoch": 0.1518324607329843,412 "grad_norm": 1.7314403887490193,413 "learning_rate": 1.996951284977556e-06,414 "loss": 0.9334,415 "step": 58416 },417 {418 "epoch": 0.1544502617801047,419 "grad_norm": 1.4035559785329323,420 "learning_rate": 1.9966033264720613e-06,421 "loss": 0.9635,422 "step": 59423 },424 {425 "epoch": 0.15706806282722513,426 "grad_norm": 1.4996157907491292,427 "learning_rate": 1.9962366031525663e-06,428 "loss": 1.0347,429 "step": 60430 },431 {432 "epoch": 0.15968586387434555,433 "grad_norm": 3.8626755595391287,434 "learning_rate": 1.9958511219240188e-06,435 "loss": 0.9453,436 "step": 61437 },438 {439 "epoch": 0.16230366492146597,440 "grad_norm": 1.5545221856692377,441 "learning_rate": 1.9954468900445565e-06,442 "loss": 1.0431,443 "step": 62444 },445 {446 "epoch": 0.1649214659685864,447 "grad_norm": 1.50894331448368,448 "learning_rate": 1.995023915125368e-06,449 "loss": 1.056,450 "step": 63451 },452 {453 "epoch": 0.16753926701570682,454 "grad_norm": 1.6123663294471207,455 "learning_rate": 1.9945822051305507e-06,456 "loss": 0.9744,457 "step": 64458 },459 {460 "epoch": 0.17015706806282724,461 "grad_norm": 2.002886641603634,462 "learning_rate": 1.9941217683769596e-06,463 "loss": 1.0396,464 "step": 65465 },466 {467 "epoch": 0.17277486910994763,468 "grad_norm": 1.4061639592638548,469 "learning_rate": 1.9936426135340527e-06,470 "loss": 1.0162,471 "step": 66472 },473 {474 "epoch": 0.17539267015706805,475 "grad_norm": 1.4744552229885421,476 "learning_rate": 1.9931447496237255e-06,477 "loss": 1.0339,478 "step": 67479 },480 {481 "epoch": 0.17801047120418848,482 "grad_norm": 1.3373753426511383,483 "learning_rate": 1.9926281860201426e-06,484 "loss": 1.0123,485 "step": 68486 },487 {488 "epoch": 0.1806282722513089,489 "grad_norm": 1.8346771940527866,490 "learning_rate": 1.992092932449561e-06,491 "loss": 1.0218,492 "step": 69493 },494 {495 "epoch": 0.18324607329842932,496 "grad_norm": 1.5683702537742212,497 "learning_rate": 1.9915389989901473e-06,498 "loss": 0.9868,499 "step": 70500 },501 {502 "epoch": 0.18586387434554974,503 "grad_norm": 1.6088369103380997,504 "learning_rate": 1.9909663960717854e-06,505 "loss": 1.0082,506 "step": 71507 },508 {509 "epoch": 0.18848167539267016,510 "grad_norm": 1.6226263180260028,511 "learning_rate": 1.9903751344758845e-06,512 "loss": 1.0272,513 "step": 72514 },515 {516 "epoch": 0.19109947643979058,517 "grad_norm": 1.519358495108808,518 "learning_rate": 1.9897652253351726e-06,519 "loss": 1.0006,520 "step": 73521 },522 {523 "epoch": 0.193717277486911,524 "grad_norm": 1.7246977984441099,525 "learning_rate": 1.9891366801334875e-06,526 "loss": 1.0071,527 "step": 74528 },529 {530 "epoch": 0.19633507853403143,531 "grad_norm": 1.885654171226984,532 "learning_rate": 1.9884895107055627e-06,533 "loss": 0.9659,534 "step": 75535 },536 {537 "epoch": 0.19895287958115182,538 "grad_norm": 1.4255056172161928,539 "learning_rate": 1.987823729236801e-06,540 "loss": 0.9791,541 "step": 76542 },543 {544 "epoch": 0.20157068062827224,545 "grad_norm": 1.4127676458511806,546 "learning_rate": 1.9871393482630486e-06,547 "loss": 0.9982,548 "step": 77549 },550 {551 "epoch": 0.20418848167539266,552 "grad_norm": 1.6038922300951168,553 "learning_rate": 1.9864363806703567e-06,554 "loss": 1.0035,555 "step": 78556 },557 {558 "epoch": 0.20680628272251309,559 "grad_norm": 1.6873794773106967,560 "learning_rate": 1.9857148396947403e-06,561 "loss": 1.0059,562 "step": 79563 },564 {565 "epoch": 0.2094240837696335,566 "grad_norm": 1.4769795174016325,567 "learning_rate": 1.984974738921927e-06,568 "loss": 0.999,569 "step": 80570 },571 {572 "epoch": 0.21204188481675393,573 "grad_norm": 1.595922250055431,574 "learning_rate": 1.9842160922871043e-06,575 "loss": 0.9853,576 "step": 81577 },578 {579 "epoch": 0.21465968586387435,580 "grad_norm": 2.267409709264766,581 "learning_rate": 1.9834389140746535e-06,582 "loss": 1.0104,583 "step": 82584 },585 {586 "epoch": 0.21727748691099477,587 "grad_norm": 1.4934157955551683,588 "learning_rate": 1.982643218917885e-06,589 "loss": 0.9612,590 "step": 83591 },592 {593 "epoch": 0.2198952879581152,594 "grad_norm": 1.7746131869025623,595 "learning_rate": 1.9818290217987584e-06,596 "loss": 0.9525,597 "step": 84598 },599 {600 "epoch": 0.22251308900523561,601 "grad_norm": 1.7233411954456554,602 "learning_rate": 1.980996338047604e-06,603 "loss": 1.035,604 "step": 85605 },606 {607 "epoch": 0.225130890052356,608 "grad_norm": 1.4012107807745622,609 "learning_rate": 1.980145183342831e-06,610 "loss": 0.9657,611 "step": 86612 },613 {614 "epoch": 0.22774869109947643,615 "grad_norm": 1.5160148683515746,616 "learning_rate": 1.9792755737106357e-06,617 "loss": 0.9691,618 "step": 87619 },620 {621 "epoch": 0.23036649214659685,622 "grad_norm": 1.3553031139205232,623 "learning_rate": 1.978387525524697e-06,624 "loss": 0.9732,625 "step": 88626 },627 {628 "epoch": 0.23298429319371727,629 "grad_norm": 2.3559259408150144,630 "learning_rate": 1.9774810555058694e-06,631 "loss": 0.968,632 "step": 89633 },634 {635 "epoch": 0.2356020942408377,636 "grad_norm": 2.0405648874947144,637 "learning_rate": 1.976556180721867e-06,638 "loss": 1.0217,639 "step": 90640 },641 {642 "epoch": 0.23821989528795812,643 "grad_norm": 1.289980797855502,644 "learning_rate": 1.975612918586944e-06,645 "loss": 0.973,646 "step": 91647 },648 {649 "epoch": 0.24083769633507854,650 "grad_norm": 1.4893463969411602,651 "learning_rate": 1.9746512868615655e-06,652 "loss": 1.0109,653 "step": 92654 },655 {656 "epoch": 0.24345549738219896,657 "grad_norm": 2.074068588481718,658 "learning_rate": 1.973671303652073e-06,659 "loss": 0.9831,660 "step": 93661 },662 {663 "epoch": 0.24607329842931938,664 "grad_norm": 1.4717466896018212,665 "learning_rate": 1.972672987410345e-06,666 "loss": 0.9815,667 "step": 94668 },669 {670 "epoch": 0.2486910994764398,671 "grad_norm": 1.3362580099120316,672 "learning_rate": 1.971656356933446e-06,673 "loss": 0.9627,674 "step": 95675 },676 {677 "epoch": 0.2513089005235602,678 "grad_norm": 1.6316029366291782,679 "learning_rate": 1.970621431363278e-06,680 "loss": 0.9657,681 "step": 96682 },683 {684 "epoch": 0.25392670157068065,685 "grad_norm": 1.7671135565160097,686 "learning_rate": 1.9695682301862154e-06,687 "loss": 0.9219,688 "step": 97689 },690 {691 "epoch": 0.25654450261780104,692 "grad_norm": 1.5966004233267017,693 "learning_rate": 1.9684967732327396e-06,694 "loss": 1.0045,695 "step": 98696 },697 {698 "epoch": 0.2591623036649215,699 "grad_norm": 1.4806542129023226,700 "learning_rate": 1.9674070806770667e-06,701 "loss": 0.9732,702 "step": 99703 },704 {705 "epoch": 0.2617801047120419,706 "grad_norm": 1.5115625649689057,707 "learning_rate": 1.9662991730367663e-06,708 "loss": 0.9692,709 "step": 100710 },711 {712 "epoch": 0.2643979057591623,713 "grad_norm": 1.6408654241651082,714 "learning_rate": 1.965173071172375e-06,715 "loss": 1.0782,716 "step": 101717 },718 {719 "epoch": 0.2670157068062827,720 "grad_norm": 1.58266015019036,721 "learning_rate": 1.9640287962870057e-06,722 "loss": 0.9532,723 "step": 102724 },725 {726 "epoch": 0.2696335078534031,727 "grad_norm": 1.39253004882154,728 "learning_rate": 1.962866369925946e-06,729 "loss": 0.9742,730 "step": 103731 },732 {733 "epoch": 0.27225130890052357,734 "grad_norm": 1.4246820152864472,735 "learning_rate": 1.9616858139762532e-06,736 "loss": 1.0196,737 "step": 104738 },739 {740 "epoch": 0.27486910994764396,741 "grad_norm": 1.5013590811914759,742 "learning_rate": 1.960487150666343e-06,743 "loss": 1.0238,744 "step": 105745 },746 {747 "epoch": 0.2774869109947644,748 "grad_norm": 1.440692442657796,749 "learning_rate": 1.95927040256557e-06,750 "loss": 1.0166,751 "step": 106752 },753 {754 "epoch": 0.2801047120418848,755 "grad_norm": 1.5426181884013244,756 "learning_rate": 1.958035592583803e-06,757 "loss": 0.9635,758 "step": 107759 },760 {761 "epoch": 0.28272251308900526,762 "grad_norm": 1.3715243788491147,763 "learning_rate": 1.956782743970995e-06,764 "loss": 0.972,765 "step": 108766 },767 {768 "epoch": 0.28534031413612565,769 "grad_norm": 1.6076440082600667,770 "learning_rate": 1.955511880316743e-06,771 "loss": 0.9634,772 "step": 109773 },774 {775 "epoch": 0.2879581151832461,776 "grad_norm": 1.322996372089846,777 "learning_rate": 1.9542230255498453e-06,778 "loss": 0.946,779 "step": 110780 },781 {782 "epoch": 0.2905759162303665,783 "grad_norm": 1.6508002306297551,784 "learning_rate": 1.9529162039378505e-06,785 "loss": 1.0146,786 "step": 111787 },788 {789 "epoch": 0.2931937172774869,790 "grad_norm": 1.9140720133949438,791 "learning_rate": 1.951591440086602e-06,792 "loss": 0.9794,793 "step": 112794 },795 {796 "epoch": 0.29581151832460734,797 "grad_norm": 1.301517922409106,798 "learning_rate": 1.9502487589397717e-06,799 "loss": 0.9955,800 "step": 113801 },802 {803 "epoch": 0.29842931937172773,804 "grad_norm": 1.6752384604989274,805 "learning_rate": 1.948888185778393e-06,806 "loss": 0.9614,807 "step": 114808 },809 {810 "epoch": 0.3010471204188482,811 "grad_norm": 1.6669201309688906,812 "learning_rate": 1.947509746220385e-06,813 "loss": 0.9596,814 "step": 115815 },816 {817 "epoch": 0.3036649214659686,818 "grad_norm": 1.6186884886800548,819 "learning_rate": 1.9461134662200666e-06,820 "loss": 0.966,821 "step": 116822 },823 {824 "epoch": 0.306282722513089,825 "grad_norm": 1.4525901118285445,826 "learning_rate": 1.9446993720676725e-06,827 "loss": 0.9637,828 "step": 117829 },830 {831 "epoch": 0.3089005235602094,832 "grad_norm": 1.3926685659345446,833 "learning_rate": 1.9432674903888547e-06,834 "loss": 0.9562,835 "step": 118836 },837 {838 "epoch": 0.31151832460732987,839 "grad_norm": 1.5687485197442492,840 "learning_rate": 1.941817848144183e-06,841 "loss": 1.003,842 "step": 119843 },844 {845 "epoch": 0.31413612565445026,846 "grad_norm": 1.3452828778510757,847 "learning_rate": 1.9403504726286365e-06,848 "loss": 0.976,849 "step": 120850 },851 {852 "epoch": 0.31675392670157065,853 "grad_norm": 1.3816617452534992,854 "learning_rate": 1.93886539147109e-06,855 "loss": 0.9599,856 "step": 121857 },858 {859 "epoch": 0.3193717277486911,860 "grad_norm": 1.481897037058517,861 "learning_rate": 1.9373626326337944e-06,862 "loss": 0.9731,863 "step": 122864 },865 {866 "epoch": 0.3219895287958115,867 "grad_norm": 1.413329266686157,868 "learning_rate": 1.9358422244118486e-06,869 "loss": 0.9783,870 "step": 123871 },872 {873 "epoch": 0.32460732984293195,874 "grad_norm": 2.9010127845249385,875 "learning_rate": 1.9343041954326677e-06,876 "loss": 0.9777,877 "step": 124878 },879 {880 "epoch": 0.32722513089005234,881 "grad_norm": 1.2853594407436248,882 "learning_rate": 1.932748574655445e-06,883 "loss": 0.9784,884 "step": 125885 },886 {887 "epoch": 0.3298429319371728,888 "grad_norm": 1.6563678696752941,889 "learning_rate": 1.931175391370605e-06,890 "loss": 0.9591,891 "step": 126892 },893 {894 "epoch": 0.3324607329842932,895 "grad_norm": 1.4153593487098186,896 "learning_rate": 1.929584675199252e-06,897 "loss": 0.9433,898 "step": 127899 },900 {901 "epoch": 0.33507853403141363,902 "grad_norm": 1.4853036785401517,903 "learning_rate": 1.927976456092614e-06,904 "loss": 0.9195,905 "step": 128906 },907 {908 "epoch": 0.337696335078534,909 "grad_norm": 1.6653698839653936,910 "learning_rate": 1.9263507643314775e-06,911 "loss": 0.9711,912 "step": 129913 },914 {915 "epoch": 0.3403141361256545,916 "grad_norm": 1.5513246503570877,917 "learning_rate": 1.9247076305256173e-06,918 "loss": 1.0266,919 "step": 130920 },921 {922 "epoch": 0.34293193717277487,923 "grad_norm": 1.9279366482258156,924 "learning_rate": 1.923047085613221e-06,925 "loss": 1.0001,926 "step": 131927 },928 {929 "epoch": 0.34554973821989526,930 "grad_norm": 1.4339951925997667,931 "learning_rate": 1.9213691608603046e-06,932 "loss": 1.003,933 "step": 132934 },935 {936 "epoch": 0.3481675392670157,937 "grad_norm": 1.3521774084798501,938 "learning_rate": 1.9196738878601262e-06,939 "loss": 0.9748,940 "step": 133941 },942 {943 "epoch": 0.3507853403141361,944 "grad_norm": 1.4539030309601608,945 "learning_rate": 1.9179612985325907e-06,946 "loss": 0.9544,947 "step": 134948 },949 {950 "epoch": 0.35340314136125656,951 "grad_norm": 1.9287872837043116,952 "learning_rate": 1.9162314251236464e-06,953 "loss": 0.9649,954 "step": 135955 },956 {957 "epoch": 0.35602094240837695,958 "grad_norm": 1.426685422908151,959 "learning_rate": 1.9144843002046803e-06,960 "loss": 1.0246,961 "step": 136962 },963 {964 "epoch": 0.3586387434554974,965 "grad_norm": 1.6129363461024815,966 "learning_rate": 1.912719956671905e-06,967 "loss": 0.9603,968 "step": 137969 },970 {971 "epoch": 0.3612565445026178,972 "grad_norm": 1.4893083520917,973 "learning_rate": 1.9109384277457366e-06,974 "loss": 0.9644,975 "step": 138976 },977 {978 "epoch": 0.36387434554973824,979 "grad_norm": 1.4422789845290571,980 "learning_rate": 1.9091397469701734e-06,981 "loss": 1.0022,982 "step": 139983 },984 {985 "epoch": 0.36649214659685864,986 "grad_norm": 1.379089386140381,987 "learning_rate": 1.9073239482121597e-06,988 "loss": 0.977,989 "step": 140990 },991 {992 "epoch": 0.36910994764397903,993 "grad_norm": 1.2902251521449346,994 "learning_rate": 1.905491065660951e-06,995 "loss": 0.9479,996 "step": 141997 },998 {999 "epoch": 0.3717277486910995,1000 "grad_norm": 1.4849260045966897,1001 "learning_rate": 1.9036411338274702e-06,1002 "loss": 0.9535,1003 "step": 1421004 },1005 {1006 "epoch": 0.3743455497382199,1007 "grad_norm": 1.4742367033559105,1008 "learning_rate": 1.9017741875436569e-06,1009 "loss": 0.9692,1010 "step": 1431011 },1012 {1013 "epoch": 0.3769633507853403,1014 "grad_norm": 1.7554436015022166,1015 "learning_rate": 1.8998902619618114e-06,1016 "loss": 0.9279,1017 "step": 1441018 },1019 {1020 "epoch": 0.3795811518324607,1021 "grad_norm": 1.4010842342135992,1022 "learning_rate": 1.8979893925539336e-06,1023 "loss": 0.9423,1024 "step": 1451025 },1026 {1027 "epoch": 0.38219895287958117,1028 "grad_norm": 1.497443248481895,1029 "learning_rate": 1.8960716151110553e-06,1030 "loss": 0.9848,1031 "step": 1461032 },1033 {1034 "epoch": 0.38481675392670156,1035 "grad_norm": 1.5982300331675101,1036 "learning_rate": 1.894136965742565e-06,1037 "loss": 0.9691,1038 "step": 1471039 },1040 {1041 "epoch": 0.387434554973822,1042 "grad_norm": 1.371150523732322,1043 "learning_rate": 1.8921854808755292e-06,1044 "loss": 0.9548,1045 "step": 1481046 },1047 {1048 "epoch": 0.3900523560209424,1049 "grad_norm": 1.7867184813381989,1050 "learning_rate": 1.8902171972540058e-06,1051 "loss": 0.985,1052 "step": 1491053 },1054 {1055 "epoch": 0.39267015706806285,1056 "grad_norm": 1.4222923909172587,1057 "learning_rate": 1.8882321519383533e-06,1058 "loss": 0.9473,1059 "step": 1501060 },1061 {1062 "epoch": 0.39528795811518325,1063 "grad_norm": 1.4430633539722946,1064 "learning_rate": 1.886230382304531e-06,1065 "loss": 0.945,1066 "step": 1511067 },1068 {1069 "epoch": 0.39790575916230364,1070 "grad_norm": 1.4120566052672336,1071 "learning_rate": 1.884211926043398e-06,1072 "loss": 0.9377,1073 "step": 1521074 },1075 {1076 "epoch": 0.4005235602094241,1077 "grad_norm": 1.5491012831054978,1078 "learning_rate": 1.882176821160001e-06,1079 "loss": 0.9694,1080 "step": 1531081 },1082 {1083 "epoch": 0.4031413612565445,1084 "grad_norm": 1.702124781114296,1085 "learning_rate": 1.8801251059728602e-06,1086 "loss": 0.9713,1087 "step": 1541088 },1089 {1090 "epoch": 0.40575916230366493,1091 "grad_norm": 1.2951128973054504,1092 "learning_rate": 1.878056819113247e-06,1093 "loss": 0.9355,1094 "step": 1551095 },1096 {1097 "epoch": 0.4083769633507853,1098 "grad_norm": 1.3183333685080236,1099 "learning_rate": 1.875971999524458e-06,1100 "loss": 0.9591,1101 "step": 1561102 },1103 {1104 "epoch": 0.4109947643979058,1105 "grad_norm": 1.4206883250837021,1106 "learning_rate": 1.8738706864610791e-06,1107 "loss": 0.9724,1108 "step": 1571109 },1110 {1111 "epoch": 0.41361256544502617,1112 "grad_norm": 1.3491536224151637,1113 "learning_rate": 1.8717529194882497e-06,1114 "loss": 0.9596,1115 "step": 1581116 },1117 {1118 "epoch": 0.4162303664921466,1119 "grad_norm": 1.6067238922960525,1120 "learning_rate": 1.8696187384809153e-06,1121 "loss": 0.9874,1122 "step": 1591123 },1124 {1125 "epoch": 0.418848167539267,1126 "grad_norm": 2.170081739206507,1127 "learning_rate": 1.8674681836230768e-06,1128 "loss": 0.9393,1129 "step": 1601130 },1131 {1132 "epoch": 0.4214659685863874,1133 "grad_norm": 1.6523206816354508,1134 "learning_rate": 1.8653012954070356e-06,1135 "loss": 0.9912,1136 "step": 1611137 },1138 {1139 "epoch": 0.42408376963350786,1140 "grad_norm": 1.7458545642560128,1141 "learning_rate": 1.8631181146326303e-06,1142 "loss": 0.9163,1143 "step": 1621144 },1145 {1146 "epoch": 0.42670157068062825,1147 "grad_norm": 1.551930694859062,1148 "learning_rate": 1.860918682406467e-06,1149 "loss": 0.9959,1150 "step": 1631151 },1152 {1153 "epoch": 0.4293193717277487,1154 "grad_norm": 1.3800307543491146,1155 "learning_rate": 1.8587030401411478e-06,1156 "loss": 0.944,1157 "step": 1641158 },1159 {1160 "epoch": 0.4319371727748691,1161 "grad_norm": 1.5733297290745525,1162 "learning_rate": 1.8564712295544892e-06,1163 "loss": 0.9952,1164 "step": 1651165 },1166 {1167 "epoch": 0.43455497382198954,1168 "grad_norm": 1.69702400357591,1169 "learning_rate": 1.8542232926687382e-06,1170 "loss": 0.9765,1171 "step": 1661172 },1173 {1174 "epoch": 0.43717277486910994,1175 "grad_norm": 1.4210131276532727,1176 "learning_rate": 1.851959271809779e-06,1177 "loss": 0.9644,1178 "step": 1671179 },1180 {1181 "epoch": 0.4397905759162304,1182 "grad_norm": 1.3705469469324443,1183 "learning_rate": 1.8496792096063379e-06,1184 "loss": 0.9784,1185 "step": 1681186 },1187 {1188 "epoch": 0.4424083769633508,1189 "grad_norm": 1.367481685410119,1190 "learning_rate": 1.8473831489891798e-06,1191 "loss": 0.9487,1192 "step": 1691193 },1194 {1195 "epoch": 0.44502617801047123,1196 "grad_norm": 1.4039844158067947,1197 "learning_rate": 1.8450711331903005e-06,1198 "loss": 0.9287,1199 "step": 1701200 },