Omartificial-Intelligence-Space/Arabic-DeepSeek-R1-Distill-8B
421
1{2 "best_metric": null,3 "best_model_checkpoint": null,4 "epoch": 1.0,5 "eval_steps": 500,6 "global_step": 288,7 "is_hyper_param_search": false,8 "is_local_process_zero": true,9 "is_world_process_zero": true,10 "log_history": [11 {12 "epoch": 0.003472222222222222,13 "grad_norm": 0.6381791234016418,14 "learning_rate": 4e-05,15 "loss": 1.664,16 "step": 117 },18 {19 "epoch": 0.006944444444444444,20 "grad_norm": 0.6412252187728882,21 "learning_rate": 8e-05,22 "loss": 1.6095,23 "step": 224 },25 {26 "epoch": 0.010416666666666666,27 "grad_norm": 0.6355312466621399,28 "learning_rate": 0.00012,29 "loss": 1.6431,30 "step": 331 },32 {33 "epoch": 0.013888888888888888,34 "grad_norm": 0.7827576994895935,35 "learning_rate": 0.00016,36 "loss": 1.7554,37 "step": 438 },39 {40 "epoch": 0.017361111111111112,41 "grad_norm": 0.7365180850028992,42 "learning_rate": 0.0002,43 "loss": 1.6866,44 "step": 545 },46 {47 "epoch": 0.020833333333333332,48 "grad_norm": 0.7607629299163818,49 "learning_rate": 0.00019929328621908128,50 "loss": 1.5447,51 "step": 652 },53 {54 "epoch": 0.024305555555555556,55 "grad_norm": 0.7718775272369385,56 "learning_rate": 0.00019858657243816254,57 "loss": 1.5777,58 "step": 759 },60 {61 "epoch": 0.027777777777777776,62 "grad_norm": 0.7301136255264282,63 "learning_rate": 0.00019787985865724384,64 "loss": 1.3402,65 "step": 866 },67 {68 "epoch": 0.03125,69 "grad_norm": 0.6953989863395691,70 "learning_rate": 0.0001971731448763251,71 "loss": 1.4443,72 "step": 973 },74 {75 "epoch": 0.034722222222222224,76 "grad_norm": 0.605755090713501,77 "learning_rate": 0.00019646643109540637,78 "loss": 1.3609,79 "step": 1080 },81 {82 "epoch": 0.03819444444444445,83 "grad_norm": 0.5867183804512024,84 "learning_rate": 0.00019575971731448764,85 "loss": 1.2765,86 "step": 1187 },88 {89 "epoch": 0.041666666666666664,90 "grad_norm": 0.5973581075668335,91 "learning_rate": 0.00019505300353356894,92 "loss": 1.2585,93 "step": 1294 },95 {96 "epoch": 0.04513888888888889,97 "grad_norm": 0.7357228398323059,98 "learning_rate": 0.0001943462897526502,99 "loss": 1.2199,100 "step": 13101 },102 {103 "epoch": 0.04861111111111111,104 "grad_norm": 0.7804207801818848,105 "learning_rate": 0.00019363957597173144,106 "loss": 1.1996,107 "step": 14108 },109 {110 "epoch": 0.052083333333333336,111 "grad_norm": 0.813244640827179,112 "learning_rate": 0.0001929328621908127,113 "loss": 1.1735,114 "step": 15115 },116 {117 "epoch": 0.05555555555555555,118 "grad_norm": 0.7277530431747437,119 "learning_rate": 0.00019222614840989398,120 "loss": 1.1094,121 "step": 16122 },123 {124 "epoch": 0.059027777777777776,125 "grad_norm": 0.6414357423782349,126 "learning_rate": 0.00019151943462897527,127 "loss": 1.1786,128 "step": 17129 },130 {131 "epoch": 0.0625,132 "grad_norm": 0.5542577505111694,133 "learning_rate": 0.00019081272084805654,134 "loss": 0.9343,135 "step": 18136 },137 {138 "epoch": 0.06597222222222222,139 "grad_norm": 0.5263577699661255,140 "learning_rate": 0.0001901060070671378,141 "loss": 1.0607,142 "step": 19143 },144 {145 "epoch": 0.06944444444444445,146 "grad_norm": 0.49260228872299194,147 "learning_rate": 0.00018939929328621908,148 "loss": 0.9934,149 "step": 20150 },151 {152 "epoch": 0.07291666666666667,153 "grad_norm": 0.5072307586669922,154 "learning_rate": 0.00018869257950530037,155 "loss": 1.0165,156 "step": 21157 },158 {159 "epoch": 0.0763888888888889,160 "grad_norm": 0.5154305696487427,161 "learning_rate": 0.00018798586572438164,162 "loss": 1.0159,163 "step": 22164 },165 {166 "epoch": 0.0798611111111111,167 "grad_norm": 0.5033209919929504,168 "learning_rate": 0.0001872791519434629,169 "loss": 1.0102,170 "step": 23171 },172 {173 "epoch": 0.08333333333333333,174 "grad_norm": 0.5032006502151489,175 "learning_rate": 0.00018657243816254417,176 "loss": 1.0215,177 "step": 24178 },179 {180 "epoch": 0.08680555555555555,181 "grad_norm": 0.4746347665786743,182 "learning_rate": 0.00018586572438162547,183 "loss": 0.867,184 "step": 25185 },186 {187 "epoch": 0.09027777777777778,188 "grad_norm": 0.4780479967594147,189 "learning_rate": 0.00018515901060070673,190 "loss": 0.951,191 "step": 26192 },193 {194 "epoch": 0.09375,195 "grad_norm": 0.45668691396713257,196 "learning_rate": 0.000184452296819788,197 "loss": 0.9464,198 "step": 27199 },200 {201 "epoch": 0.09722222222222222,202 "grad_norm": 0.43334755301475525,203 "learning_rate": 0.00018374558303886927,204 "loss": 0.8768,205 "step": 28206 },207 {208 "epoch": 0.10069444444444445,209 "grad_norm": 0.4458893835544586,210 "learning_rate": 0.00018303886925795054,211 "loss": 0.8553,212 "step": 29213 },214 {215 "epoch": 0.10416666666666667,216 "grad_norm": 0.4605867564678192,217 "learning_rate": 0.00018233215547703183,218 "loss": 0.948,219 "step": 30220 },221 {222 "epoch": 0.1076388888888889,223 "grad_norm": 0.44694918394088745,224 "learning_rate": 0.0001816254416961131,225 "loss": 0.8755,226 "step": 31227 },228 {229 "epoch": 0.1111111111111111,230 "grad_norm": 0.45669859647750854,231 "learning_rate": 0.00018091872791519434,232 "loss": 0.8554,233 "step": 32234 },235 {236 "epoch": 0.11458333333333333,237 "grad_norm": 0.4380110502243042,238 "learning_rate": 0.0001802120141342756,239 "loss": 0.8699,240 "step": 33241 },242 {243 "epoch": 0.11805555555555555,244 "grad_norm": 0.4494687020778656,245 "learning_rate": 0.0001795053003533569,246 "loss": 0.8463,247 "step": 34248 },249 {250 "epoch": 0.12152777777777778,251 "grad_norm": 0.4385037422180176,252 "learning_rate": 0.00017879858657243817,253 "loss": 0.7964,254 "step": 35255 },256 {257 "epoch": 0.125,258 "grad_norm": 0.42709654569625854,259 "learning_rate": 0.00017809187279151944,260 "loss": 0.8675,261 "step": 36262 },263 {264 "epoch": 0.1284722222222222,265 "grad_norm": 0.462563157081604,266 "learning_rate": 0.0001773851590106007,267 "loss": 0.9125,268 "step": 37269 },270 {271 "epoch": 0.13194444444444445,272 "grad_norm": 0.4372367560863495,273 "learning_rate": 0.00017667844522968197,274 "loss": 0.8352,275 "step": 38276 },277 {278 "epoch": 0.13541666666666666,279 "grad_norm": 0.4251866340637207,280 "learning_rate": 0.00017597173144876327,281 "loss": 0.8695,282 "step": 39283 },284 {285 "epoch": 0.1388888888888889,286 "grad_norm": 0.43755847215652466,287 "learning_rate": 0.00017526501766784453,288 "loss": 0.8544,289 "step": 40290 },291 {292 "epoch": 0.1423611111111111,293 "grad_norm": 0.44858112931251526,294 "learning_rate": 0.0001745583038869258,295 "loss": 0.835,296 "step": 41297 },298 {299 "epoch": 0.14583333333333334,300 "grad_norm": 0.4447510838508606,301 "learning_rate": 0.00017385159010600707,302 "loss": 0.8537,303 "step": 42304 },305 {306 "epoch": 0.14930555555555555,307 "grad_norm": 0.42954930663108826,308 "learning_rate": 0.00017314487632508836,309 "loss": 0.7603,310 "step": 43311 },312 {313 "epoch": 0.1527777777777778,314 "grad_norm": 0.4357329308986664,315 "learning_rate": 0.00017243816254416963,316 "loss": 0.7315,317 "step": 44318 },319 {320 "epoch": 0.15625,321 "grad_norm": 0.4562698304653168,322 "learning_rate": 0.0001717314487632509,323 "loss": 0.9103,324 "step": 45325 },326 {327 "epoch": 0.1597222222222222,328 "grad_norm": 0.46614545583724976,329 "learning_rate": 0.00017102473498233216,330 "loss": 0.832,331 "step": 46332 },333 {334 "epoch": 0.16319444444444445,335 "grad_norm": 0.42011672258377075,336 "learning_rate": 0.00017031802120141343,337 "loss": 0.7172,338 "step": 47339 },340 {341 "epoch": 0.16666666666666666,342 "grad_norm": 0.40585461258888245,343 "learning_rate": 0.00016961130742049473,344 "loss": 0.7087,345 "step": 48346 },347 {348 "epoch": 0.1701388888888889,349 "grad_norm": 0.4490915834903717,350 "learning_rate": 0.000168904593639576,351 "loss": 0.7956,352 "step": 49353 },354 {355 "epoch": 0.1736111111111111,356 "grad_norm": 0.4251860976219177,357 "learning_rate": 0.00016819787985865723,358 "loss": 0.7763,359 "step": 50360 },361 {362 "epoch": 0.17708333333333334,363 "grad_norm": 0.4503968060016632,364 "learning_rate": 0.0001674911660777385,365 "loss": 0.833,366 "step": 51367 },368 {369 "epoch": 0.18055555555555555,370 "grad_norm": 0.452923059463501,371 "learning_rate": 0.0001667844522968198,372 "loss": 0.729,373 "step": 52374 },375 {376 "epoch": 0.1840277777777778,377 "grad_norm": 0.45421820878982544,378 "learning_rate": 0.00016607773851590106,379 "loss": 0.8678,380 "step": 53381 },382 {383 "epoch": 0.1875,384 "grad_norm": 0.47255003452301025,385 "learning_rate": 0.00016537102473498233,386 "loss": 0.7856,387 "step": 54388 },389 {390 "epoch": 0.1909722222222222,391 "grad_norm": 0.49460238218307495,392 "learning_rate": 0.0001646643109540636,393 "loss": 0.8103,394 "step": 55395 },396 {397 "epoch": 0.19444444444444445,398 "grad_norm": 0.47668716311454773,399 "learning_rate": 0.0001639575971731449,400 "loss": 0.6687,401 "step": 56402 },403 {404 "epoch": 0.19791666666666666,405 "grad_norm": 0.4631917178630829,406 "learning_rate": 0.00016325088339222616,407 "loss": 0.7362,408 "step": 57409 },410 {411 "epoch": 0.2013888888888889,412 "grad_norm": 0.4908764064311981,413 "learning_rate": 0.00016254416961130743,414 "loss": 0.7734,415 "step": 58416 },417 {418 "epoch": 0.2048611111111111,419 "grad_norm": 0.47517484426498413,420 "learning_rate": 0.0001618374558303887,421 "loss": 0.8048,422 "step": 59423 },424 {425 "epoch": 0.20833333333333334,426 "grad_norm": 0.4693131744861603,427 "learning_rate": 0.00016113074204946996,428 "loss": 0.8148,429 "step": 60430 },431 {432 "epoch": 0.21180555555555555,433 "grad_norm": 0.48101750016212463,434 "learning_rate": 0.00016042402826855126,435 "loss": 0.7089,436 "step": 61437 },438 {439 "epoch": 0.2152777777777778,440 "grad_norm": 0.45942020416259766,441 "learning_rate": 0.00015971731448763253,442 "loss": 0.7649,443 "step": 62444 },445 {446 "epoch": 0.21875,447 "grad_norm": 0.46566373109817505,448 "learning_rate": 0.0001590106007067138,449 "loss": 0.7081,450 "step": 63451 },452 {453 "epoch": 0.2222222222222222,454 "grad_norm": 0.4782656133174896,455 "learning_rate": 0.00015830388692579506,456 "loss": 0.6578,457 "step": 64458 },459 {460 "epoch": 0.22569444444444445,461 "grad_norm": 0.4600412845611572,462 "learning_rate": 0.00015759717314487635,463 "loss": 0.6907,464 "step": 65465 },466 {467 "epoch": 0.22916666666666666,468 "grad_norm": 0.47648143768310547,469 "learning_rate": 0.00015689045936395762,470 "loss": 0.7159,471 "step": 66472 },473 {474 "epoch": 0.2326388888888889,475 "grad_norm": 0.4845995008945465,476 "learning_rate": 0.00015618374558303886,477 "loss": 0.6186,478 "step": 67479 },480 {481 "epoch": 0.2361111111111111,482 "grad_norm": 0.5142258405685425,483 "learning_rate": 0.00015547703180212013,484 "loss": 0.7643,485 "step": 68486 },487 {488 "epoch": 0.23958333333333334,489 "grad_norm": 0.5000512599945068,490 "learning_rate": 0.0001547703180212014,491 "loss": 0.734,492 "step": 69493 },494 {495 "epoch": 0.24305555555555555,496 "grad_norm": 0.473004549741745,497 "learning_rate": 0.0001540636042402827,498 "loss": 0.689,499 "step": 70500 },501 {502 "epoch": 0.2465277777777778,503 "grad_norm": 0.49982285499572754,504 "learning_rate": 0.00015335689045936396,505 "loss": 0.7162,506 "step": 71507 },508 {509 "epoch": 0.25,510 "grad_norm": 0.48723116517066956,511 "learning_rate": 0.00015265017667844523,512 "loss": 0.605,513 "step": 72514 },515 {516 "epoch": 0.2534722222222222,517 "grad_norm": 0.4668457508087158,518 "learning_rate": 0.0001519434628975265,519 "loss": 0.7956,520 "step": 73521 },522 {523 "epoch": 0.2569444444444444,524 "grad_norm": 0.5139826536178589,525 "learning_rate": 0.0001512367491166078,526 "loss": 0.6877,527 "step": 74528 },529 {530 "epoch": 0.2604166666666667,531 "grad_norm": 0.48903441429138184,532 "learning_rate": 0.00015053003533568906,533 "loss": 0.7341,534 "step": 75535 },536 {537 "epoch": 0.2638888888888889,538 "grad_norm": 0.4892962872982025,539 "learning_rate": 0.00014982332155477032,540 "loss": 0.6833,541 "step": 76542 },543 {544 "epoch": 0.2673611111111111,545 "grad_norm": 0.510981023311615,546 "learning_rate": 0.0001491166077738516,547 "loss": 0.6567,548 "step": 77549 },550 {551 "epoch": 0.2708333333333333,552 "grad_norm": 0.48602378368377686,553 "learning_rate": 0.00014840989399293289,554 "loss": 0.6592,555 "step": 78556 },557 {558 "epoch": 0.2743055555555556,559 "grad_norm": 0.5149515271186829,560 "learning_rate": 0.00014770318021201415,561 "loss": 0.7435,562 "step": 79563 },564 {565 "epoch": 0.2777777777777778,566 "grad_norm": 0.4999159872531891,567 "learning_rate": 0.00014699646643109542,568 "loss": 0.7397,569 "step": 80570 },571 {572 "epoch": 0.28125,573 "grad_norm": 0.5036943554878235,574 "learning_rate": 0.0001462897526501767,575 "loss": 0.6791,576 "step": 81577 },578 {579 "epoch": 0.2847222222222222,580 "grad_norm": 0.4811699688434601,581 "learning_rate": 0.00014558303886925796,582 "loss": 0.6376,583 "step": 82584 },585 {586 "epoch": 0.2881944444444444,587 "grad_norm": 0.5215135812759399,588 "learning_rate": 0.00014487632508833925,589 "loss": 0.6547,590 "step": 83591 },592 {593 "epoch": 0.2916666666666667,594 "grad_norm": 0.5180763006210327,595 "learning_rate": 0.00014416961130742052,596 "loss": 0.6667,597 "step": 84598 },599 {600 "epoch": 0.2951388888888889,601 "grad_norm": 0.5010943412780762,602 "learning_rate": 0.00014346289752650176,603 "loss": 0.6496,604 "step": 85605 },606 {607 "epoch": 0.2986111111111111,608 "grad_norm": 0.47832784056663513,609 "learning_rate": 0.00014275618374558303,610 "loss": 0.6516,611 "step": 86612 },613 {614 "epoch": 0.3020833333333333,615 "grad_norm": 0.5183102488517761,616 "learning_rate": 0.00014204946996466432,617 "loss": 0.6822,618 "step": 87619 },620 {621 "epoch": 0.3055555555555556,622 "grad_norm": 0.5250104069709778,623 "learning_rate": 0.0001413427561837456,624 "loss": 0.6837,625 "step": 88626 },627 {628 "epoch": 0.3090277777777778,629 "grad_norm": 0.4821203052997589,630 "learning_rate": 0.00014063604240282686,631 "loss": 0.6734,632 "step": 89633 },634 {635 "epoch": 0.3125,636 "grad_norm": 0.5341935157775879,637 "learning_rate": 0.00013992932862190812,638 "loss": 0.7098,639 "step": 90640 },641 {642 "epoch": 0.3159722222222222,643 "grad_norm": 0.5351920127868652,644 "learning_rate": 0.0001392226148409894,645 "loss": 0.6806,646 "step": 91647 },648 {649 "epoch": 0.3194444444444444,650 "grad_norm": 0.5185657143592834,651 "learning_rate": 0.00013851590106007068,652 "loss": 0.6212,653 "step": 92654 },655 {656 "epoch": 0.3229166666666667,657 "grad_norm": 0.4946865439414978,658 "learning_rate": 0.00013780918727915195,659 "loss": 0.7244,660 "step": 93661 },662 {663 "epoch": 0.3263888888888889,664 "grad_norm": 0.51689213514328,665 "learning_rate": 0.00013710247349823322,666 "loss": 0.532,667 "step": 94668 },669 {670 "epoch": 0.3298611111111111,671 "grad_norm": 0.5387365221977234,672 "learning_rate": 0.0001363957597173145,673 "loss": 0.6225,674 "step": 95675 },676 {677 "epoch": 0.3333333333333333,678 "grad_norm": 0.5210251212120056,679 "learning_rate": 0.00013568904593639578,680 "loss": 0.6565,681 "step": 96682 },683 {684 "epoch": 0.3368055555555556,685 "grad_norm": 0.5470120310783386,686 "learning_rate": 0.00013498233215547705,687 "loss": 0.6181,688 "step": 97689 },690 {691 "epoch": 0.3402777777777778,692 "grad_norm": 0.5134613513946533,693 "learning_rate": 0.00013427561837455832,694 "loss": 0.5943,695 "step": 98696 },697 {698 "epoch": 0.34375,699 "grad_norm": 0.5114628076553345,700 "learning_rate": 0.00013356890459363958,701 "loss": 0.7112,702 "step": 99703 },704 {705 "epoch": 0.3472222222222222,706 "grad_norm": 0.5393586158752441,707 "learning_rate": 0.00013286219081272085,708 "loss": 0.6513,709 "step": 100710 },711 {712 "epoch": 0.3506944444444444,713 "grad_norm": 0.5121696591377258,714 "learning_rate": 0.00013215547703180215,715 "loss": 0.6112,716 "step": 101717 },718 {719 "epoch": 0.3541666666666667,720 "grad_norm": 0.5529887676239014,721 "learning_rate": 0.0001314487632508834,722 "loss": 0.704,723 "step": 102724 },725 {726 "epoch": 0.3576388888888889,727 "grad_norm": 0.5504875779151917,728 "learning_rate": 0.00013074204946996465,729 "loss": 0.6367,730 "step": 103731 },732 {733 "epoch": 0.3611111111111111,734 "grad_norm": 0.5555490255355835,735 "learning_rate": 0.00013003533568904592,736 "loss": 0.6988,737 "step": 104738 },739 {740 "epoch": 0.3645833333333333,741 "grad_norm": 0.5071545839309692,742 "learning_rate": 0.00012932862190812722,743 "loss": 0.6598,744 "step": 105745 },746 {747 "epoch": 0.3680555555555556,748 "grad_norm": 0.5332069396972656,749 "learning_rate": 0.00012862190812720848,750 "loss": 0.65,751 "step": 106752 },753 {754 "epoch": 0.3715277777777778,755 "grad_norm": 0.5629200339317322,756 "learning_rate": 0.00012791519434628975,757 "loss": 0.699,758 "step": 107759 },760 {761 "epoch": 0.375,762 "grad_norm": 0.5515280961990356,763 "learning_rate": 0.00012720848056537102,764 "loss": 0.6418,765 "step": 108766 },767 {768 "epoch": 0.3784722222222222,769 "grad_norm": 0.527538001537323,770 "learning_rate": 0.0001265017667844523,771 "loss": 0.7302,772 "step": 109773 },774 {775 "epoch": 0.3819444444444444,776 "grad_norm": 0.5716756582260132,777 "learning_rate": 0.00012579505300353358,778 "loss": 0.7443,779 "step": 110780 },781 {782 "epoch": 0.3854166666666667,783 "grad_norm": 0.5540614724159241,784 "learning_rate": 0.00012508833922261485,785 "loss": 0.6564,786 "step": 111787 },788 {789 "epoch": 0.3888888888888889,790 "grad_norm": 0.5193327069282532,791 "learning_rate": 0.00012438162544169612,792 "loss": 0.6783,793 "step": 112794 },795 {796 "epoch": 0.3923611111111111,797 "grad_norm": 0.5474222302436829,798 "learning_rate": 0.00012367491166077738,799 "loss": 0.6519,800 "step": 113801 },802 {803 "epoch": 0.3958333333333333,804 "grad_norm": 0.5058162808418274,805 "learning_rate": 0.00012296819787985868,806 "loss": 0.5785,807 "step": 114808 },809 {810 "epoch": 0.3993055555555556,811 "grad_norm": 0.5280646085739136,812 "learning_rate": 0.00012226148409893994,813 "loss": 0.6308,814 "step": 115815 },816 {817 "epoch": 0.4027777777777778,818 "grad_norm": 0.536086916923523,819 "learning_rate": 0.0001215547703180212,820 "loss": 0.5696,821 "step": 116822 },823 {824 "epoch": 0.40625,825 "grad_norm": 0.5223795771598816,826 "learning_rate": 0.00012084805653710247,827 "loss": 0.5861,828 "step": 117829 },830 {831 "epoch": 0.4097222222222222,832 "grad_norm": 0.5218377113342285,833 "learning_rate": 0.00012014134275618376,834 "loss": 0.6151,835 "step": 118836 },837 {838 "epoch": 0.4131944444444444,839 "grad_norm": 0.5461903214454651,840 "learning_rate": 0.00011943462897526503,841 "loss": 0.585,842 "step": 119843 },844 {845 "epoch": 0.4166666666666667,846 "grad_norm": 0.5451020002365112,847 "learning_rate": 0.0001187279151943463,848 "loss": 0.6571,849 "step": 120850 },851 {852 "epoch": 0.4201388888888889,853 "grad_norm": 0.5320534706115723,854 "learning_rate": 0.00011802120141342756,855 "loss": 0.6191,856 "step": 121857 },858 {859 "epoch": 0.4236111111111111,860 "grad_norm": 0.5509814023971558,861 "learning_rate": 0.00011731448763250883,862 "loss": 0.542,863 "step": 122864 },865 {866 "epoch": 0.4270833333333333,867 "grad_norm": 0.5494756102561951,868 "learning_rate": 0.00011660777385159012,869 "loss": 0.7145,870 "step": 123871 },872 {873 "epoch": 0.4305555555555556,874 "grad_norm": 0.5778016448020935,875 "learning_rate": 0.00011590106007067139,876 "loss": 0.6787,877 "step": 124878 },879 {880 "epoch": 0.4340277777777778,881 "grad_norm": 0.5546441674232483,882 "learning_rate": 0.00011519434628975265,883 "loss": 0.5897,884 "step": 125885 },886 {887 "epoch": 0.4375,888 "grad_norm": 0.5590822100639343,889 "learning_rate": 0.00011448763250883391,890 "loss": 0.6331,891 "step": 126892 },893 {894 "epoch": 0.4409722222222222,895 "grad_norm": 0.5571174025535583,896 "learning_rate": 0.00011378091872791521,897 "loss": 0.6624,898 "step": 127899 },900 {901 "epoch": 0.4444444444444444,902 "grad_norm": 0.579007625579834,903 "learning_rate": 0.00011307420494699648,904 "loss": 0.6377,905 "step": 128906 },907 {908 "epoch": 0.4479166666666667,909 "grad_norm": 0.5956988334655762,910 "learning_rate": 0.00011236749116607774,911 "loss": 0.6828,912 "step": 129913 },914 {915 "epoch": 0.4513888888888889,916 "grad_norm": 0.5952633023262024,917 "learning_rate": 0.00011166077738515901,918 "loss": 0.5603,919 "step": 130920 },921 {922 "epoch": 0.4548611111111111,923 "grad_norm": 0.561600387096405,924 "learning_rate": 0.00011095406360424028,925 "loss": 0.6311,926 "step": 131927 },928 {929 "epoch": 0.4583333333333333,930 "grad_norm": 0.5515158772468567,931 "learning_rate": 0.00011024734982332157,932 "loss": 0.7293,933 "step": 132934 },935 {936 "epoch": 0.4618055555555556,937 "grad_norm": 0.5889860987663269,938 "learning_rate": 0.00010954063604240284,939 "loss": 0.6693,940 "step": 133941 },942 {943 "epoch": 0.4652777777777778,944 "grad_norm": 0.5815720558166504,945 "learning_rate": 0.0001088339222614841,946 "loss": 0.6881,947 "step": 134948 },949 {950 "epoch": 0.46875,951 "grad_norm": 0.6205659508705139,952 "learning_rate": 0.00010812720848056536,953 "loss": 0.6732,954 "step": 135955 },956 {957 "epoch": 0.4722222222222222,958 "grad_norm": 0.5689711570739746,959 "learning_rate": 0.00010742049469964666,960 "loss": 0.6206,961 "step": 136962 },963 {964 "epoch": 0.4756944444444444,965 "grad_norm": 0.5453592538833618,966 "learning_rate": 0.00010671378091872792,967 "loss": 0.6257,968 "step": 137969 },970 {971 "epoch": 0.4791666666666667,972 "grad_norm": 0.5330798625946045,973 "learning_rate": 0.00010600706713780919,974 "loss": 0.4674,975 "step": 138976 },977 {978 "epoch": 0.4826388888888889,979 "grad_norm": 0.5798875093460083,980 "learning_rate": 0.00010530035335689046,981 "loss": 0.6017,982 "step": 139983 },984 {985 "epoch": 0.4861111111111111,986 "grad_norm": 0.5574885010719299,987 "learning_rate": 0.00010459363957597175,988 "loss": 0.6087,989 "step": 140990 },991 {992 "epoch": 0.4895833333333333,993 "grad_norm": 0.5381941199302673,994 "learning_rate": 0.00010388692579505302,995 "loss": 0.6543,996 "step": 141997 },998 {999 "epoch": 0.4930555555555556,1000 "grad_norm": 0.5750802755355835,1001 "learning_rate": 0.00010318021201413429,1002 "loss": 0.6662,1003 "step": 1421004 },1005 {1006 "epoch": 0.4965277777777778,1007 "grad_norm": 0.6241365671157837,1008 "learning_rate": 0.00010247349823321554,1009 "loss": 0.5976,1010 "step": 1431011 },1012 {1013 "epoch": 0.5,1014 "grad_norm": 0.5461493134498596,1015 "learning_rate": 0.00010176678445229681,1016 "loss": 0.6796,1017 "step": 1441018 },1019 {1020 "epoch": 0.5034722222222222,1021 "grad_norm": 0.5892328023910522,1022 "learning_rate": 0.0001010600706713781,1023 "loss": 0.6166,1024 "step": 1451025 },1026 {1027 "epoch": 0.5069444444444444,1028 "grad_norm": 0.5670603513717651,1029 "learning_rate": 0.00010035335689045937,1030 "loss": 0.651,1031 "step": 1461032 },1033 {1034 "epoch": 0.5104166666666666,1035 "grad_norm": 0.5573473572731018,1036 "learning_rate": 9.964664310954064e-05,1037 "loss": 0.6268,1038 "step": 1471039 },1040 {1041 "epoch": 0.5138888888888888,1042 "grad_norm": 0.5641173720359802,1043 "learning_rate": 9.893992932862192e-05,1044 "loss": 0.6515,1045 "step": 1481046 },1047 {1048 "epoch": 0.5173611111111112,1049 "grad_norm": 0.5903286337852478,1050 "learning_rate": 9.823321554770319e-05,1051 "loss": 0.6705,1052 "step": 1491053 },1054 {1055 "epoch": 0.5208333333333334,1056 "grad_norm": 0.5907771587371826,1057 "learning_rate": 9.752650176678447e-05,1058 "loss": 0.6184,1059 "step": 1501060 },1061 {1062 "epoch": 0.5243055555555556,1063 "grad_norm": 0.5515082478523254,1064 "learning_rate": 9.681978798586572e-05,1065 "loss": 0.661,1066 "step": 1511067 },1068 {1069 "epoch": 0.5277777777777778,1070 "grad_norm": 0.5268746614456177,1071 "learning_rate": 9.611307420494699e-05,1072 "loss": 0.6082,1073 "step": 1521074 },1075 {1076 "epoch": 0.53125,1077 "grad_norm": 0.5877247452735901,1078 "learning_rate": 9.540636042402827e-05,1079 "loss": 0.5856,1080 "step": 1531081 },1082 {1083 "epoch": 0.5347222222222222,1084 "grad_norm": 0.5402259826660156,1085 "learning_rate": 9.469964664310954e-05,1086 "loss": 0.574,1087 "step": 1541088 },1089 {1090 "epoch": 0.5381944444444444,1091 "grad_norm": 0.5235267281532288,1092 "learning_rate": 9.399293286219082e-05,1093 "loss": 0.5598,1094 "step": 1551095 },1096 {1097 "epoch": 0.5416666666666666,1098 "grad_norm": 0.5417196750640869,1099 "learning_rate": 9.328621908127209e-05,1100 "loss": 0.6447,1101 "step": 1561102 },1103 {1104 "epoch": 0.5451388888888888,1105 "grad_norm": 0.6259889006614685,1106 "learning_rate": 9.257950530035337e-05,1107 "loss": 0.6227,1108 "step": 1571109 },1110 {1111 "epoch": 0.5486111111111112,1112 "grad_norm": 0.567189633846283,1113 "learning_rate": 9.187279151943463e-05,1114 "loss": 0.5788,1115 "step": 1581116 },1117 {1118 "epoch": 0.5520833333333334,1119 "grad_norm": 0.5860530138015747,1120 "learning_rate": 9.116607773851592e-05,1121 "loss": 0.5026,1122 "step": 1591123 },1124 {1125 "epoch": 0.5555555555555556,1126 "grad_norm": 0.5970867872238159,1127 "learning_rate": 9.045936395759717e-05,1128 "loss": 0.65,1129 "step": 1601130 },1131 {1132 "epoch": 0.5590277777777778,1133 "grad_norm": 0.5621108412742615,1134 "learning_rate": 8.975265017667845e-05,1135 "loss": 0.6118,1136 "step": 1611137 },1138 {1139 "epoch": 0.5625,1140 "grad_norm": 0.5695009827613831,1141 "learning_rate": 8.904593639575972e-05,1142 "loss": 0.5119,1143 "step": 1621144 },1145 {1146 "epoch": 0.5659722222222222,1147 "grad_norm": 0.5741239786148071,1148 "learning_rate": 8.833922261484099e-05,1149 "loss": 0.5273,1150 "step": 1631151 },1152 {1153 "epoch": 0.5694444444444444,1154 "grad_norm": 0.5961455702781677,1155 "learning_rate": 8.763250883392227e-05,1156 "loss": 0.6197,1157 "step": 1641158 },1159 {1160 "epoch": 0.5729166666666666,1161 "grad_norm": 0.5358597636222839,1162 "learning_rate": 8.692579505300353e-05,1163 "loss": 0.5629,1164 "step": 1651165 },1166 {1167 "epoch": 0.5763888888888888,1168 "grad_norm": 0.5704313516616821,1169 "learning_rate": 8.621908127208482e-05,1170 "loss": 0.5838,1171 "step": 1661172 },1173 {1174 "epoch": 0.5798611111111112,1175 "grad_norm": 0.6421118378639221,1176 "learning_rate": 8.551236749116608e-05,1177 "loss": 0.5964,1178 "step": 1671179 },1180 {1181 "epoch": 0.5833333333333334,1182 "grad_norm": 0.5588890314102173,1183 "learning_rate": 8.480565371024736e-05,1184 "loss": 0.4957,1185 "step": 1681186 },1187 {1188 "epoch": 0.5868055555555556,1189 "grad_norm": 0.5954290628433228,1190 "learning_rate": 8.409893992932862e-05,1191 "loss": 0.6364,1192 "step": 1691193 },1194 {1195 "epoch": 0.5902777777777778,1196 "grad_norm": 0.5738086700439453,1197 "learning_rate": 8.33922261484099e-05,1198 "loss": 0.5661,1199 "step": 1701200 },