Unbabel/TowerInstruct-WMT24-Chat-7B
232
1{2 "best_metric": null,3 "best_model_checkpoint": null,4 "epoch": 3.9420444444444445,5 "eval_steps": 500,6 "global_step": 5624,7 "is_hyper_param_search": false,8 "is_local_process_zero": true,9 "is_world_process_zero": true,10 "log_history": [11 {12 "epoch": 0.01,13 "grad_norm": 9.912928587976149,14 "learning_rate": 1.4e-07,15 "loss": 1.0098,16 "step": 1017 },18 {19 "epoch": 0.01,20 "grad_norm": 9.065321089366511,21 "learning_rate": 2.8e-07,22 "loss": 1.0032,23 "step": 2024 },25 {26 "epoch": 0.02,27 "grad_norm": 4.529282680442283,28 "learning_rate": 4.2e-07,29 "loss": 0.9767,30 "step": 3031 },32 {33 "epoch": 0.03,34 "grad_norm": 4.079773534866118,35 "learning_rate": 5.6e-07,36 "loss": 0.9341,37 "step": 4038 },39 {40 "epoch": 0.04,41 "grad_norm": 1.7504240808921168,42 "learning_rate": 7.000000000000001e-07,43 "loss": 0.8727,44 "step": 5045 },46 {47 "epoch": 0.04,48 "grad_norm": 0.7446189301316752,49 "learning_rate": 8.4e-07,50 "loss": 0.7997,51 "step": 6052 },53 {54 "epoch": 0.05,55 "grad_norm": 0.5893489037586176,56 "learning_rate": 9.800000000000001e-07,57 "loss": 0.7828,58 "step": 7059 },60 {61 "epoch": 0.06,62 "grad_norm": 0.5798012459841311,63 "learning_rate": 1.12e-06,64 "loss": 0.7671,65 "step": 8066 },67 {68 "epoch": 0.06,69 "grad_norm": 0.5143143417454488,70 "learning_rate": 1.26e-06,71 "loss": 0.777,72 "step": 9073 },74 {75 "epoch": 0.07,76 "grad_norm": 0.5006881361687121,77 "learning_rate": 1.4000000000000001e-06,78 "loss": 0.7709,79 "step": 10080 },81 {82 "epoch": 0.08,83 "grad_norm": 0.5268772561224019,84 "learning_rate": 1.54e-06,85 "loss": 0.7751,86 "step": 11087 },88 {89 "epoch": 0.09,90 "grad_norm": 0.49059329535011015,91 "learning_rate": 1.68e-06,92 "loss": 0.7588,93 "step": 12094 },95 {96 "epoch": 0.09,97 "grad_norm": 0.548982179156723,98 "learning_rate": 1.82e-06,99 "loss": 0.758,100 "step": 130101 },102 {103 "epoch": 0.1,104 "grad_norm": 0.5118740800557817,105 "learning_rate": 1.9600000000000003e-06,106 "loss": 0.7492,107 "step": 140108 },109 {110 "epoch": 0.11,111 "grad_norm": 0.47988356348194033,112 "learning_rate": 2.1e-06,113 "loss": 0.7479,114 "step": 150115 },116 {117 "epoch": 0.11,118 "grad_norm": 0.5324095582498372,119 "learning_rate": 2.24e-06,120 "loss": 0.7344,121 "step": 160122 },123 {124 "epoch": 0.12,125 "grad_norm": 0.49578185528674784,126 "learning_rate": 2.38e-06,127 "loss": 0.7379,128 "step": 170129 },130 {131 "epoch": 0.13,132 "grad_norm": 0.4751722809020323,133 "learning_rate": 2.52e-06,134 "loss": 0.7515,135 "step": 180136 },137 {138 "epoch": 0.14,139 "grad_norm": 0.4898512842949614,140 "learning_rate": 2.66e-06,141 "loss": 0.7428,142 "step": 190143 },144 {145 "epoch": 0.14,146 "grad_norm": 0.4938014103724035,147 "learning_rate": 2.8000000000000003e-06,148 "loss": 0.7356,149 "step": 200150 },151 {152 "epoch": 0.15,153 "grad_norm": 0.4853179196888149,154 "learning_rate": 2.94e-06,155 "loss": 0.7338,156 "step": 210157 },158 {159 "epoch": 0.16,160 "grad_norm": 0.5006261354893382,161 "learning_rate": 3.08e-06,162 "loss": 0.7228,163 "step": 220164 },165 {166 "epoch": 0.16,167 "grad_norm": 0.49494536099466524,168 "learning_rate": 3.22e-06,169 "loss": 0.7371,170 "step": 230171 },172 {173 "epoch": 0.17,174 "grad_norm": 0.4745560090617258,175 "learning_rate": 3.36e-06,176 "loss": 0.7374,177 "step": 240178 },179 {180 "epoch": 0.18,181 "grad_norm": 0.458424659300056,182 "learning_rate": 3.5e-06,183 "loss": 0.7284,184 "step": 250185 },186 {187 "epoch": 0.18,188 "grad_norm": 0.4918105642778609,189 "learning_rate": 3.64e-06,190 "loss": 0.719,191 "step": 260192 },193 {194 "epoch": 0.19,195 "grad_norm": 0.45994092727545755,196 "learning_rate": 3.7800000000000002e-06,197 "loss": 0.7328,198 "step": 270199 },200 {201 "epoch": 0.2,202 "grad_norm": 0.4888877840053054,203 "learning_rate": 3.920000000000001e-06,204 "loss": 0.7257,205 "step": 280206 },207 {208 "epoch": 0.21,209 "grad_norm": 0.4891132357037931,210 "learning_rate": 4.059999999999999e-06,211 "loss": 0.7146,212 "step": 290213 },214 {215 "epoch": 0.21,216 "grad_norm": 0.4659780107286472,217 "learning_rate": 4.2e-06,218 "loss": 0.7207,219 "step": 300220 },221 {222 "epoch": 0.22,223 "grad_norm": 0.4747662452681582,224 "learning_rate": 4.34e-06,225 "loss": 0.7196,226 "step": 310227 },228 {229 "epoch": 0.23,230 "grad_norm": 0.46183058951309874,231 "learning_rate": 4.48e-06,232 "loss": 0.7166,233 "step": 320234 },235 {236 "epoch": 0.23,237 "grad_norm": 0.47556837186042844,238 "learning_rate": 4.62e-06,239 "loss": 0.7138,240 "step": 330241 },242 {243 "epoch": 0.24,244 "grad_norm": 0.4646419935884572,245 "learning_rate": 4.76e-06,246 "loss": 0.7166,247 "step": 340248 },249 {250 "epoch": 0.25,251 "grad_norm": 0.47208612393069765,252 "learning_rate": 4.9e-06,253 "loss": 0.7071,254 "step": 350255 },256 {257 "epoch": 0.26,258 "grad_norm": 0.47395551626034477,259 "learning_rate": 5.04e-06,260 "loss": 0.7081,261 "step": 360262 },263 {264 "epoch": 0.26,265 "grad_norm": 0.46256038389399284,266 "learning_rate": 5.1799999999999995e-06,267 "loss": 0.7112,268 "step": 370269 },270 {271 "epoch": 0.27,272 "grad_norm": 0.44989559880311664,273 "learning_rate": 5.32e-06,274 "loss": 0.7157,275 "step": 380276 },277 {278 "epoch": 0.28,279 "grad_norm": 0.4759980664139243,280 "learning_rate": 5.46e-06,281 "loss": 0.716,282 "step": 390283 },284 {285 "epoch": 0.28,286 "grad_norm": 0.47761427911509746,287 "learning_rate": 5.600000000000001e-06,288 "loss": 0.6936,289 "step": 400290 },291 {292 "epoch": 0.29,293 "grad_norm": 0.4823631066912239,294 "learning_rate": 5.739999999999999e-06,295 "loss": 0.7096,296 "step": 410297 },298 {299 "epoch": 0.3,300 "grad_norm": 0.4692563644972781,301 "learning_rate": 5.88e-06,302 "loss": 0.6955,303 "step": 420304 },305 {306 "epoch": 0.31,307 "grad_norm": 0.4758216043542266,308 "learning_rate": 6.02e-06,309 "loss": 0.7046,310 "step": 430311 },312 {313 "epoch": 0.31,314 "grad_norm": 0.4607724176991764,315 "learning_rate": 6.16e-06,316 "loss": 0.7071,317 "step": 440318 },319 {320 "epoch": 0.32,321 "grad_norm": 0.47650098464440593,322 "learning_rate": 6.3e-06,323 "loss": 0.6948,324 "step": 450325 },326 {327 "epoch": 0.33,328 "grad_norm": 0.4927763843500283,329 "learning_rate": 6.44e-06,330 "loss": 0.7138,331 "step": 460332 },333 {334 "epoch": 0.33,335 "grad_norm": 0.44343044028786904,336 "learning_rate": 6.58e-06,337 "loss": 0.7033,338 "step": 470339 },340 {341 "epoch": 0.34,342 "grad_norm": 0.45708129790603597,343 "learning_rate": 6.72e-06,344 "loss": 0.7038,345 "step": 480346 },347 {348 "epoch": 0.35,349 "grad_norm": 0.47564264251663835,350 "learning_rate": 6.8599999999999995e-06,351 "loss": 0.6974,352 "step": 490353 },354 {355 "epoch": 0.36,356 "grad_norm": 0.4561386006973232,357 "learning_rate": 7e-06,358 "loss": 0.702,359 "step": 500360 },361 {362 "epoch": 0.36,363 "grad_norm": 0.4318637464381274,364 "learning_rate": 6.999934216315939e-06,365 "loss": 0.7054,366 "step": 510367 },368 {369 "epoch": 0.37,370 "grad_norm": 0.47772094451329594,371 "learning_rate": 6.999736867736609e-06,372 "loss": 0.6946,373 "step": 520374 },375 {376 "epoch": 0.38,377 "grad_norm": 0.45891608711087106,378 "learning_rate": 6.9994079616804764e-06,379 "loss": 0.6952,380 "step": 530381 },382 {383 "epoch": 0.38,384 "grad_norm": 0.46731862765960264,385 "learning_rate": 6.9989475105113426e-06,386 "loss": 0.6888,387 "step": 540388 },389 {390 "epoch": 0.39,391 "grad_norm": 0.4667223098464595,392 "learning_rate": 6.998355531537879e-06,393 "loss": 0.7017,394 "step": 550395 },396 {397 "epoch": 0.4,398 "grad_norm": 0.46285196540927176,399 "learning_rate": 6.997632047012975e-06,400 "loss": 0.7051,401 "step": 560402 },403 {404 "epoch": 0.41,405 "grad_norm": 0.48044807815149254,406 "learning_rate": 6.996777084132904e-06,407 "loss": 0.701,408 "step": 570409 },410 {411 "epoch": 0.41,412 "grad_norm": 0.47600970966063727,413 "learning_rate": 6.995790675036298e-06,414 "loss": 0.7001,415 "step": 580416 },417 {418 "epoch": 0.42,419 "grad_norm": 0.4494522317826872,420 "learning_rate": 6.994672856802944e-06,421 "loss": 0.7042,422 "step": 590423 },424 {425 "epoch": 0.43,426 "grad_norm": 0.4623294450089233,427 "learning_rate": 6.993423671452386e-06,428 "loss": 0.69,429 "step": 600430 },431 {432 "epoch": 0.43,433 "grad_norm": 0.43825456028915594,434 "learning_rate": 6.9920431659423436e-06,435 "loss": 0.6996,436 "step": 610437 },438 {439 "epoch": 0.44,440 "grad_norm": 0.4568055452742323,441 "learning_rate": 6.990531392166956e-06,442 "loss": 0.6939,443 "step": 620444 },445 {446 "epoch": 0.45,447 "grad_norm": 0.4302767633743081,448 "learning_rate": 6.988888406954821e-06,449 "loss": 0.6898,450 "step": 630451 },452 {453 "epoch": 0.46,454 "grad_norm": 0.4762852616798798,455 "learning_rate": 6.9871142720668644e-06,456 "loss": 0.703,457 "step": 640458 },459 {460 "epoch": 0.46,461 "grad_norm": 0.4572026337069386,462 "learning_rate": 6.985209054194017e-06,463 "loss": 0.7004,464 "step": 650465 },466 {467 "epoch": 0.47,468 "grad_norm": 0.45803902960498666,469 "learning_rate": 6.983172824954708e-06,470 "loss": 0.6853,471 "step": 660472 },473 {474 "epoch": 0.48,475 "grad_norm": 0.44353624606381903,476 "learning_rate": 6.9810056608921725e-06,477 "loss": 0.7074,478 "step": 670479 },480 {481 "epoch": 0.48,482 "grad_norm": 0.44517458769087626,483 "learning_rate": 6.978707643471573e-06,484 "loss": 0.6988,485 "step": 680486 },487 {488 "epoch": 0.49,489 "grad_norm": 0.4616555458392388,490 "learning_rate": 6.97627885907694e-06,491 "loss": 0.7034,492 "step": 690493 },494 {495 "epoch": 0.5,496 "grad_norm": 0.4770896081066365,497 "learning_rate": 6.973719399007923e-06,498 "loss": 0.6935,499 "step": 700500 },501 {502 "epoch": 0.5,503 "grad_norm": 0.45665921054521347,504 "learning_rate": 6.9710293594763545e-06,505 "loss": 0.6773,506 "step": 710507 },508 {509 "epoch": 0.51,510 "grad_norm": 0.48834217157342125,511 "learning_rate": 6.968208841602645e-06,512 "loss": 0.6974,513 "step": 720514 },515 {516 "epoch": 0.52,517 "grad_norm": 0.4661409470252182,518 "learning_rate": 6.965257951411967e-06,519 "loss": 0.6796,520 "step": 730521 },522 {523 "epoch": 0.53,524 "grad_norm": 0.4249423447942054,525 "learning_rate": 6.962176799830279e-06,526 "loss": 0.686,527 "step": 740528 },529 {530 "epoch": 0.53,531 "grad_norm": 0.4517631229399239,532 "learning_rate": 6.958965502680155e-06,533 "loss": 0.6968,534 "step": 750535 },536 {537 "epoch": 0.54,538 "grad_norm": 0.4334006789419362,539 "learning_rate": 6.955624180676427e-06,540 "loss": 0.705,541 "step": 760542 },543 {544 "epoch": 0.55,545 "grad_norm": 0.44354874837116653,546 "learning_rate": 6.9521529594216516e-06,547 "loss": 0.6954,548 "step": 770549 },550 {551 "epoch": 0.55,552 "grad_norm": 0.4606606226964418,553 "learning_rate": 6.948551969401381e-06,554 "loss": 0.6965,555 "step": 780556 },557 {558 "epoch": 0.56,559 "grad_norm": 0.46221163538458165,560 "learning_rate": 6.94482134597927e-06,561 "loss": 0.695,562 "step": 790563 },564 {565 "epoch": 0.57,566 "grad_norm": 0.4636824720485381,567 "learning_rate": 6.940961229391975e-06,568 "loss": 0.6919,569 "step": 800570 },571 {572 "epoch": 0.58,573 "grad_norm": 0.4450527833539268,574 "learning_rate": 6.936971764743891e-06,575 "loss": 0.6977,576 "step": 810577 },578 {579 "epoch": 0.58,580 "grad_norm": 0.4358125416971688,581 "learning_rate": 6.932853102001694e-06,582 "loss": 0.6998,583 "step": 820584 },585 {586 "epoch": 0.59,587 "grad_norm": 0.45623590289661414,588 "learning_rate": 6.928605395988701e-06,589 "loss": 0.6954,590 "step": 830591 },592 {593 "epoch": 0.6,594 "grad_norm": 0.4536975058820564,595 "learning_rate": 6.924228806379058e-06,596 "loss": 0.6742,597 "step": 840598 },599 {600 "epoch": 0.6,601 "grad_norm": 0.4563719379438227,602 "learning_rate": 6.919723497691728e-06,603 "loss": 0.6921,604 "step": 850605 },606 {607 "epoch": 0.61,608 "grad_norm": 0.45279224746852664,609 "learning_rate": 6.915089639284313e-06,610 "loss": 0.6861,611 "step": 860612 },613 {614 "epoch": 0.62,615 "grad_norm": 0.466062080319079,616 "learning_rate": 6.910327405346686e-06,617 "loss": 0.6895,618 "step": 870619 },620 {621 "epoch": 0.63,622 "grad_norm": 0.443881137156012,623 "learning_rate": 6.905436974894443e-06,624 "loss": 0.7008,625 "step": 880626 },627 {628 "epoch": 0.63,629 "grad_norm": 0.47752762402129206,630 "learning_rate": 6.900418531762173e-06,631 "loss": 0.6985,632 "step": 890633 },634 {635 "epoch": 0.64,636 "grad_norm": 0.4542692407893758,637 "learning_rate": 6.89527226459655e-06,638 "loss": 0.6822,639 "step": 900640 },641 {642 "epoch": 0.65,643 "grad_norm": 0.4314820719874765,644 "learning_rate": 6.889998366849237e-06,645 "loss": 0.691,646 "step": 910647 },648 {649 "epoch": 0.65,650 "grad_norm": 0.4278370127210443,651 "learning_rate": 6.884597036769621e-06,652 "loss": 0.689,653 "step": 920654 },655 {656 "epoch": 0.66,657 "grad_norm": 0.45134601911703476,658 "learning_rate": 6.879068477397353e-06,659 "loss": 0.6898,660 "step": 930661 },662 {663 "epoch": 0.67,664 "grad_norm": 0.45160503192413054,665 "learning_rate": 6.87341289655472e-06,666 "loss": 0.6869,667 "step": 940668 },669 {670 "epoch": 0.68,671 "grad_norm": 0.41025143635863104,672 "learning_rate": 6.867630506838833e-06,673 "loss": 0.6984,674 "step": 950675 },676 {677 "epoch": 0.68,678 "grad_norm": 0.46520301654074564,679 "learning_rate": 6.861721525613633e-06,680 "loss": 0.6843,681 "step": 960682 },683 {684 "epoch": 0.69,685 "grad_norm": 0.451991102882798,686 "learning_rate": 6.8556861750017235e-06,687 "loss": 0.6962,688 "step": 970689 },690 {691 "epoch": 0.7,692 "grad_norm": 0.418111038766468,693 "learning_rate": 6.849524681876018e-06,694 "loss": 0.6797,695 "step": 980696 },697 {698 "epoch": 0.7,699 "grad_norm": 0.4403261547939229,700 "learning_rate": 6.843237277851211e-06,701 "loss": 0.6965,702 "step": 990703 },704 {705 "epoch": 0.71,706 "grad_norm": 0.426598785059419,707 "learning_rate": 6.836824199275074e-06,708 "loss": 0.6821,709 "step": 1000710 },711 {712 "epoch": 0.72,713 "grad_norm": 0.42988247771547117,714 "learning_rate": 6.830285687219569e-06,715 "loss": 0.6911,716 "step": 1010717 },718 {719 "epoch": 0.73,720 "grad_norm": 0.452230475071558,721 "learning_rate": 6.823621987471789e-06,722 "loss": 0.6851,723 "step": 1020724 },725 {726 "epoch": 0.73,727 "grad_norm": 0.4267205539811686,728 "learning_rate": 6.816833350524716e-06,729 "loss": 0.6777,730 "step": 1030731 },732 {733 "epoch": 0.74,734 "grad_norm": 0.44148424584394874,735 "learning_rate": 6.809920031567808e-06,736 "loss": 0.6838,737 "step": 1040738 },739 {740 "epoch": 0.75,741 "grad_norm": 0.43306877795839893,742 "learning_rate": 6.802882290477399e-06,743 "loss": 0.6864,744 "step": 1050745 },746 {747 "epoch": 0.75,748 "grad_norm": 0.4952482617663558,749 "learning_rate": 6.79572039180694e-06,750 "loss": 0.6904,751 "step": 1060752 },753 {754 "epoch": 0.76,755 "grad_norm": 0.45382453893592856,756 "learning_rate": 6.788434604777048e-06,757 "loss": 0.6795,758 "step": 1070759 },760 {761 "epoch": 0.77,762 "grad_norm": 0.452960843334945,763 "learning_rate": 6.781025203265388e-06,764 "loss": 0.6891,765 "step": 1080766 },767 {768 "epoch": 0.78,769 "grad_norm": 0.4537364245497661,770 "learning_rate": 6.773492465796373e-06,771 "loss": 0.6907,772 "step": 1090773 },774 {775 "epoch": 0.78,776 "grad_norm": 0.44929090527897886,777 "learning_rate": 6.765836675530703e-06,778 "loss": 0.6798,779 "step": 1100780 },781 {782 "epoch": 0.79,783 "grad_norm": 0.46381413350008455,784 "learning_rate": 6.758058120254715e-06,785 "loss": 0.6716,786 "step": 1110787 },788 {789 "epoch": 0.8,790 "grad_norm": 0.4309028536458763,791 "learning_rate": 6.750157092369563e-06,792 "loss": 0.6799,793 "step": 1120794 },795 {796 "epoch": 0.8,797 "grad_norm": 0.43717422966700575,798 "learning_rate": 6.742133888880233e-06,799 "loss": 0.6883,800 "step": 1130801 },802 {803 "epoch": 0.81,804 "grad_norm": 0.4459700930425581,805 "learning_rate": 6.7339888113843696e-06,806 "loss": 0.6891,807 "step": 1140808 },809 {810 "epoch": 0.82,811 "grad_norm": 0.44045298948848877,812 "learning_rate": 6.725722166060951e-06,813 "loss": 0.6817,814 "step": 1150815 },816 {817 "epoch": 0.82,818 "grad_norm": 0.4485899862146157,819 "learning_rate": 6.717334263658766e-06,820 "loss": 0.6897,821 "step": 1160822 },823 {824 "epoch": 0.83,825 "grad_norm": 0.45682000330961775,826 "learning_rate": 6.70882541948474e-06,827 "loss": 0.6776,828 "step": 1170829 },830 {831 "epoch": 0.84,832 "grad_norm": 0.48037041295136884,833 "learning_rate": 6.700195953392085e-06,834 "loss": 0.6872,835 "step": 1180836 },837 {838 "epoch": 0.85,839 "grad_norm": 0.44334741491819346,840 "learning_rate": 6.691446189768268e-06,841 "loss": 0.6798,842 "step": 1190843 },844 {845 "epoch": 0.85,846 "grad_norm": 0.4674740757760583,847 "learning_rate": 6.682576457522825e-06,848 "loss": 0.6977,849 "step": 1200850 },851 {852 "epoch": 0.86,853 "grad_norm": 0.4696181980144796,854 "learning_rate": 6.673587090074993e-06,855 "loss": 0.6896,856 "step": 1210857 },858 {859 "epoch": 0.87,860 "grad_norm": 0.4593954697303246,861 "learning_rate": 6.664478425341176e-06,862 "loss": 0.6749,863 "step": 1220864 },865 {866 "epoch": 0.87,867 "grad_norm": 0.41647753357217115,868 "learning_rate": 6.655250805722244e-06,869 "loss": 0.6894,870 "step": 1230871 },872 {873 "epoch": 0.88,874 "grad_norm": 0.4245409839045758,875 "learning_rate": 6.645904578090662e-06,876 "loss": 0.6693,877 "step": 1240878 },879 {880 "epoch": 0.89,881 "grad_norm": 0.45490183172736,882 "learning_rate": 6.636440093777451e-06,883 "loss": 0.6881,884 "step": 1250885 },886 {887 "epoch": 0.9,888 "grad_norm": 0.4633877447287089,889 "learning_rate": 6.626857708558979e-06,890 "loss": 0.6953,891 "step": 1260892 },893 {894 "epoch": 0.9,895 "grad_norm": 0.45069656102358646,896 "learning_rate": 6.617157782643591e-06,897 "loss": 0.6787,898 "step": 1270899 },900 {901 "epoch": 0.91,902 "grad_norm": 0.44438426822862237,903 "learning_rate": 6.6073406806580646e-06,904 "loss": 0.6859,905 "step": 1280906 },907 {908 "epoch": 0.92,909 "grad_norm": 0.4335460798475662,910 "learning_rate": 6.597406771633906e-06,911 "loss": 0.6829,912 "step": 1290913 },914 {915 "epoch": 0.92,916 "grad_norm": 0.4282672786086354,917 "learning_rate": 6.587356428993477e-06,918 "loss": 0.6831,919 "step": 1300920 },921 {922 "epoch": 0.93,923 "grad_norm": 0.46465171297436636,924 "learning_rate": 6.577190030535957e-06,925 "loss": 0.6778,926 "step": 1310927 },928 {929 "epoch": 0.94,930 "grad_norm": 0.4590812961346198,931 "learning_rate": 6.566907958423142e-06,932 "loss": 0.6701,933 "step": 1320934 },935 {936 "epoch": 0.95,937 "grad_norm": 0.4180631333820519,938 "learning_rate": 6.5565105991650815e-06,939 "loss": 0.6825,940 "step": 1330941 },942 {943 "epoch": 0.95,944 "grad_norm": 0.42684427340923925,945 "learning_rate": 6.545998343605544e-06,946 "loss": 0.6823,947 "step": 1340948 },949 {950 "epoch": 0.96,951 "grad_norm": 0.6515643833482546,952 "learning_rate": 6.5353715869073275e-06,953 "loss": 0.6748,954 "step": 1350955 },956 {957 "epoch": 0.97,958 "grad_norm": 0.42995190312179654,959 "learning_rate": 6.524630728537408e-06,960 "loss": 0.6896,961 "step": 1360962 },963 {964 "epoch": 0.97,965 "grad_norm": 0.4307066820527156,966 "learning_rate": 6.513776172251919e-06,967 "loss": 0.6821,968 "step": 1370969 },970 {971 "epoch": 0.98,972 "grad_norm": 0.4401373902110004,973 "learning_rate": 6.5028083260809735e-06,974 "loss": 0.6729,975 "step": 1380976 },977 {978 "epoch": 0.99,979 "grad_norm": 0.420372235119902,980 "learning_rate": 6.491727602313334e-06,981 "loss": 0.6812,982 "step": 1390983 },984 {985 "epoch": 1.0,986 "grad_norm": 0.44387468527179835,987 "learning_rate": 6.4805344174808986e-06,988 "loss": 0.6713,989 "step": 1400990 },991 {992 "epoch": 1.0,993 "grad_norm": 0.4224291568526637,994 "learning_rate": 6.4692291923430634e-06,995 "loss": 0.6928,996 "step": 1410997 },998 {999 "epoch": 1.01,1000 "grad_norm": 0.42342827072921446,1001 "learning_rate": 6.457812351870889e-06,1002 "loss": 0.6925,1003 "step": 14201004 },1005 {1006 "epoch": 1.02,1007 "grad_norm": 0.4614687139520872,1008 "learning_rate": 6.446284325231132e-06,1009 "loss": 0.6804,1010 "step": 14301011 },1012 {1013 "epoch": 1.01,1014 "grad_norm": 0.4513094113300999,1015 "learning_rate": 6.434645545770116e-06,1016 "loss": 0.649,1017 "step": 14401018 },1019 {1020 "epoch": 1.01,1021 "grad_norm": 0.46129242006354043,1022 "learning_rate": 6.422896450997434e-06,1023 "loss": 0.6244,1024 "step": 14501025 },1026 {1027 "epoch": 1.02,1028 "grad_norm": 0.44352477273420793,1029 "learning_rate": 6.411037482569509e-06,1030 "loss": 0.6231,1031 "step": 14601032 },1033 {1034 "epoch": 1.03,1035 "grad_norm": 0.43347730975194065,1036 "learning_rate": 6.399069086272988e-06,1037 "loss": 0.6163,1038 "step": 14701039 },1040 {1041 "epoch": 1.03,1042 "grad_norm": 0.5042235757137699,1043 "learning_rate": 6.386991712007985e-06,1044 "loss": 0.6295,1045 "step": 14801046 },1047 {1048 "epoch": 1.04,1049 "grad_norm": 0.4635765704926019,1050 "learning_rate": 6.374805813771171e-06,1051 "loss": 0.6145,1052 "step": 14901053 },1054 {1055 "epoch": 1.05,1056 "grad_norm": 0.4672283056367441,1057 "learning_rate": 6.362511849638706e-06,1058 "loss": 0.6248,1059 "step": 15001060 },1061 {1062 "epoch": 1.05,1063 "grad_norm": 0.44386378239345664,1064 "learning_rate": 6.3501102817490184e-06,1065 "loss": 0.6208,1066 "step": 15101067 },1068 {1069 "epoch": 1.06,1070 "grad_norm": 0.45014512458671113,1071 "learning_rate": 6.337601576285438e-06,1072 "loss": 0.6241,1073 "step": 15201074 },1075 {1076 "epoch": 1.07,1077 "grad_norm": 0.47077991205008496,1078 "learning_rate": 6.324986203458665e-06,1079 "loss": 0.637,1080 "step": 15301081 },1082 {1083 "epoch": 1.08,1084 "grad_norm": 0.43971957336428713,1085 "learning_rate": 6.3122646374891014e-06,1086 "loss": 0.6274,1087 "step": 15401088 },1089 {1090 "epoch": 1.08,1091 "grad_norm": 0.45398595356146343,1092 "learning_rate": 6.299437356589018e-06,1093 "loss": 0.6172,1094 "step": 15501095 },1096 {1097 "epoch": 1.09,1098 "grad_norm": 0.4638039927896387,1099 "learning_rate": 6.2865048429445835e-06,1100 "loss": 0.6162,1101 "step": 15601102 },1103 {1104 "epoch": 1.1,1105 "grad_norm": 0.456884430778857,1106 "learning_rate": 6.273467582697736e-06,1107 "loss": 0.6358,1108 "step": 15701109 },1110 {1111 "epoch": 1.1,1112 "grad_norm": 0.4513273711536076,1113 "learning_rate": 6.260326065927908e-06,1114 "loss": 0.6256,1115 "step": 15801116 },1117 {1118 "epoch": 1.11,1119 "grad_norm": 0.4585546365167011,1120 "learning_rate": 6.247080786633608e-06,1121 "loss": 0.6343,1122 "step": 15901123 },1124 {1125 "epoch": 1.12,1126 "grad_norm": 0.4837809920582229,1127 "learning_rate": 6.233732242713847e-06,1128 "loss": 0.6205,1129 "step": 16001130 },1131 {1132 "epoch": 1.13,1133 "grad_norm": 0.45062031874118463,1134 "learning_rate": 6.220280935949423e-06,1135 "loss": 0.6181,1136 "step": 16101137 },1138 {1139 "epoch": 1.13,1140 "grad_norm": 0.4934582241182996,1141 "learning_rate": 6.206727371984055e-06,1142 "loss": 0.6101,1143 "step": 16201144 },1145 {1146 "epoch": 1.14,1147 "grad_norm": 0.45848465100131724,1148 "learning_rate": 6.193072060305386e-06,1149 "loss": 0.6274,1150 "step": 16301151 },1152 {1153 "epoch": 1.15,1154 "grad_norm": 0.49225379713590917,1155 "learning_rate": 6.17931551422582e-06,1156 "loss": 0.6287,1157 "step": 16401158 },1159 {1160 "epoch": 1.15,1161 "grad_norm": 0.43783738072351636,1162 "learning_rate": 6.165458250863233e-06,1163 "loss": 0.6322,1164 "step": 16501165 },1166 {1167 "epoch": 1.16,1168 "grad_norm": 0.45111919610212603,1169 "learning_rate": 6.15150079112153e-06,1170 "loss": 0.6343,1171 "step": 16601172 },1173 {1174 "epoch": 1.17,1175 "grad_norm": 0.7283719867926337,1176 "learning_rate": 6.137443659671066e-06,1177 "loss": 0.6245,1178 "step": 16701179 },1180 {1181 "epoch": 1.18,1182 "grad_norm": 0.4317614230374671,1183 "learning_rate": 6.123287384928924e-06,1184 "loss": 0.6252,1185 "step": 16801186 },1187 {1188 "epoch": 1.18,1189 "grad_norm": 0.43630742763076885,1190 "learning_rate": 6.1090324990390505e-06,1191 "loss": 0.6281,1192 "step": 16901193 },1194 {1195 "epoch": 1.19,1196 "grad_norm": 0.49179102646470696,1197 "learning_rate": 6.09467953785225e-06,1198 "loss": 0.6304,1199 "step": 17001200 },