Mathoctopus/Cross_7B
216
1{2 "best_metric": null,3 "best_model_checkpoint": null,4 "epoch": 2.9988146977479255,5 "global_step": 3795,6 "is_hyper_param_search": false,7 "is_local_process_zero": true,8 "is_world_process_zero": true,9 "log_history": [10 {11 "epoch": 0.0,12 "learning_rate": 1.7543859649122808e-07,13 "loss": 0.935,14 "step": 115 },16 {17 "epoch": 0.0,18 "learning_rate": 3.5087719298245616e-07,19 "loss": 1.0674,20 "step": 221 },22 {23 "epoch": 0.0,24 "learning_rate": 5.263157894736843e-07,25 "loss": 1.0308,26 "step": 327 },28 {29 "epoch": 0.0,30 "learning_rate": 7.017543859649123e-07,31 "loss": 1.0128,32 "step": 433 },34 {35 "epoch": 0.0,36 "learning_rate": 8.771929824561404e-07,37 "loss": 0.9605,38 "step": 539 },40 {41 "epoch": 0.0,42 "learning_rate": 1.0526315789473685e-06,43 "loss": 1.004,44 "step": 645 },46 {47 "epoch": 0.01,48 "learning_rate": 1.2280701754385965e-06,49 "loss": 1.0395,50 "step": 751 },52 {53 "epoch": 0.01,54 "learning_rate": 1.4035087719298246e-06,55 "loss": 0.9222,56 "step": 857 },58 {59 "epoch": 0.01,60 "learning_rate": 1.5789473684210526e-06,61 "loss": 0.9271,62 "step": 963 },64 {65 "epoch": 0.01,66 "learning_rate": 1.7543859649122807e-06,67 "loss": 0.8307,68 "step": 1069 },70 {71 "epoch": 0.01,72 "learning_rate": 1.929824561403509e-06,73 "loss": 0.9354,74 "step": 1175 },76 {77 "epoch": 0.01,78 "learning_rate": 2.105263157894737e-06,79 "loss": 0.8874,80 "step": 1281 },82 {83 "epoch": 0.01,84 "learning_rate": 2.280701754385965e-06,85 "loss": 0.9296,86 "step": 1387 },88 {89 "epoch": 0.01,90 "learning_rate": 2.456140350877193e-06,91 "loss": 0.8236,92 "step": 1493 },94 {95 "epoch": 0.01,96 "learning_rate": 2.631578947368421e-06,97 "loss": 0.7508,98 "step": 1599 },100 {101 "epoch": 0.01,102 "learning_rate": 2.8070175438596493e-06,103 "loss": 0.7843,104 "step": 16105 },106 {107 "epoch": 0.01,108 "learning_rate": 2.9824561403508774e-06,109 "loss": 0.6878,110 "step": 17111 },112 {113 "epoch": 0.01,114 "learning_rate": 3.157894736842105e-06,115 "loss": 0.7882,116 "step": 18117 },118 {119 "epoch": 0.02,120 "learning_rate": 3.3333333333333333e-06,121 "loss": 0.6806,122 "step": 19123 },124 {125 "epoch": 0.02,126 "learning_rate": 3.5087719298245615e-06,127 "loss": 0.7205,128 "step": 20129 },130 {131 "epoch": 0.02,132 "learning_rate": 3.6842105263157896e-06,133 "loss": 0.6318,134 "step": 21135 },136 {137 "epoch": 0.02,138 "learning_rate": 3.859649122807018e-06,139 "loss": 0.7254,140 "step": 22141 },142 {143 "epoch": 0.02,144 "learning_rate": 4.035087719298246e-06,145 "loss": 0.6625,146 "step": 23147 },148 {149 "epoch": 0.02,150 "learning_rate": 4.210526315789474e-06,151 "loss": 0.6493,152 "step": 24153 },154 {155 "epoch": 0.02,156 "learning_rate": 4.385964912280702e-06,157 "loss": 0.6574,158 "step": 25159 },160 {161 "epoch": 0.02,162 "learning_rate": 4.56140350877193e-06,163 "loss": 0.5653,164 "step": 26165 },166 {167 "epoch": 0.02,168 "learning_rate": 4.736842105263158e-06,169 "loss": 0.6365,170 "step": 27171 },172 {173 "epoch": 0.02,174 "learning_rate": 4.912280701754386e-06,175 "loss": 0.6418,176 "step": 28177 },178 {179 "epoch": 0.02,180 "learning_rate": 5.087719298245615e-06,181 "loss": 0.5921,182 "step": 29183 },184 {185 "epoch": 0.02,186 "learning_rate": 5.263157894736842e-06,187 "loss": 0.5866,188 "step": 30189 },190 {191 "epoch": 0.02,192 "learning_rate": 5.438596491228071e-06,193 "loss": 0.5797,194 "step": 31195 },196 {197 "epoch": 0.03,198 "learning_rate": 5.6140350877192985e-06,199 "loss": 0.5456,200 "step": 32201 },202 {203 "epoch": 0.03,204 "learning_rate": 5.789473684210527e-06,205 "loss": 0.5999,206 "step": 33207 },208 {209 "epoch": 0.03,210 "learning_rate": 5.964912280701755e-06,211 "loss": 0.583,212 "step": 34213 },214 {215 "epoch": 0.03,216 "learning_rate": 6.140350877192983e-06,217 "loss": 0.501,218 "step": 35219 },220 {221 "epoch": 0.03,222 "learning_rate": 6.31578947368421e-06,223 "loss": 0.5597,224 "step": 36225 },226 {227 "epoch": 0.03,228 "learning_rate": 6.491228070175439e-06,229 "loss": 0.5506,230 "step": 37231 },232 {233 "epoch": 0.03,234 "learning_rate": 6.666666666666667e-06,235 "loss": 0.5481,236 "step": 38237 },238 {239 "epoch": 0.03,240 "learning_rate": 6.842105263157896e-06,241 "loss": 0.6074,242 "step": 39243 },244 {245 "epoch": 0.03,246 "learning_rate": 7.017543859649123e-06,247 "loss": 0.5278,248 "step": 40249 },250 {251 "epoch": 0.03,252 "learning_rate": 7.192982456140352e-06,253 "loss": 0.6068,254 "step": 41255 },256 {257 "epoch": 0.03,258 "learning_rate": 7.368421052631579e-06,259 "loss": 0.4917,260 "step": 42261 },262 {263 "epoch": 0.03,264 "learning_rate": 7.5438596491228074e-06,265 "loss": 0.5031,266 "step": 43267 },268 {269 "epoch": 0.03,270 "learning_rate": 7.719298245614036e-06,271 "loss": 0.5609,272 "step": 44273 },274 {275 "epoch": 0.04,276 "learning_rate": 7.894736842105265e-06,277 "loss": 0.497,278 "step": 45279 },280 {281 "epoch": 0.04,282 "learning_rate": 8.070175438596492e-06,283 "loss": 0.5631,284 "step": 46285 },286 {287 "epoch": 0.04,288 "learning_rate": 8.24561403508772e-06,289 "loss": 0.5391,290 "step": 47291 },292 {293 "epoch": 0.04,294 "learning_rate": 8.421052631578948e-06,295 "loss": 0.496,296 "step": 48297 },298 {299 "epoch": 0.04,300 "learning_rate": 8.596491228070176e-06,301 "loss": 0.4736,302 "step": 49303 },304 {305 "epoch": 0.04,306 "learning_rate": 8.771929824561405e-06,307 "loss": 0.5227,308 "step": 50309 },310 {311 "epoch": 0.04,312 "learning_rate": 8.947368421052632e-06,313 "loss": 0.5275,314 "step": 51315 },316 {317 "epoch": 0.04,318 "learning_rate": 9.12280701754386e-06,319 "loss": 0.5766,320 "step": 52321 },322 {323 "epoch": 0.04,324 "learning_rate": 9.298245614035088e-06,325 "loss": 0.5138,326 "step": 53327 },328 {329 "epoch": 0.04,330 "learning_rate": 9.473684210526315e-06,331 "loss": 0.4843,332 "step": 54333 },334 {335 "epoch": 0.04,336 "learning_rate": 9.649122807017545e-06,337 "loss": 0.5082,338 "step": 55339 },340 {341 "epoch": 0.04,342 "learning_rate": 9.824561403508772e-06,343 "loss": 0.5127,344 "step": 56345 },346 {347 "epoch": 0.05,348 "learning_rate": 1e-05,349 "loss": 0.5193,350 "step": 57351 },352 {353 "epoch": 0.05,354 "learning_rate": 1.017543859649123e-05,355 "loss": 0.4809,356 "step": 58357 },358 {359 "epoch": 0.05,360 "learning_rate": 1.0350877192982459e-05,361 "loss": 0.4798,362 "step": 59363 },364 {365 "epoch": 0.05,366 "learning_rate": 1.0526315789473684e-05,367 "loss": 0.554,368 "step": 60369 },370 {371 "epoch": 0.05,372 "learning_rate": 1.0701754385964913e-05,373 "loss": 0.4755,374 "step": 61375 },376 {377 "epoch": 0.05,378 "learning_rate": 1.0877192982456142e-05,379 "loss": 0.4779,380 "step": 62381 },382 {383 "epoch": 0.05,384 "learning_rate": 1.105263157894737e-05,385 "loss": 0.5251,386 "step": 63387 },388 {389 "epoch": 0.05,390 "learning_rate": 1.1228070175438597e-05,391 "loss": 0.4831,392 "step": 64393 },394 {395 "epoch": 0.05,396 "learning_rate": 1.1403508771929826e-05,397 "loss": 0.5225,398 "step": 65399 },400 {401 "epoch": 0.05,402 "learning_rate": 1.1578947368421053e-05,403 "loss": 0.5347,404 "step": 66405 },406 {407 "epoch": 0.05,408 "learning_rate": 1.1754385964912282e-05,409 "loss": 0.5134,410 "step": 67411 },412 {413 "epoch": 0.05,414 "learning_rate": 1.192982456140351e-05,415 "loss": 0.4636,416 "step": 68417 },418 {419 "epoch": 0.05,420 "learning_rate": 1.2105263157894737e-05,421 "loss": 0.5441,422 "step": 69423 },424 {425 "epoch": 0.06,426 "learning_rate": 1.2280701754385966e-05,427 "loss": 0.4822,428 "step": 70429 },430 {431 "epoch": 0.06,432 "learning_rate": 1.2456140350877195e-05,433 "loss": 0.5071,434 "step": 71435 },436 {437 "epoch": 0.06,438 "learning_rate": 1.263157894736842e-05,439 "loss": 0.4563,440 "step": 72441 },442 {443 "epoch": 0.06,444 "learning_rate": 1.280701754385965e-05,445 "loss": 0.4849,446 "step": 73447 },448 {449 "epoch": 0.06,450 "learning_rate": 1.2982456140350879e-05,451 "loss": 0.4268,452 "step": 74453 },454 {455 "epoch": 0.06,456 "learning_rate": 1.3157894736842108e-05,457 "loss": 0.4564,458 "step": 75459 },460 {461 "epoch": 0.06,462 "learning_rate": 1.3333333333333333e-05,463 "loss": 0.5264,464 "step": 76465 },466 {467 "epoch": 0.06,468 "learning_rate": 1.3508771929824562e-05,469 "loss": 0.5068,470 "step": 77471 },472 {473 "epoch": 0.06,474 "learning_rate": 1.3684210526315791e-05,475 "loss": 0.5255,476 "step": 78477 },478 {479 "epoch": 0.06,480 "learning_rate": 1.385964912280702e-05,481 "loss": 0.4943,482 "step": 79483 },484 {485 "epoch": 0.06,486 "learning_rate": 1.4035087719298246e-05,487 "loss": 0.4718,488 "step": 80489 },490 {491 "epoch": 0.06,492 "learning_rate": 1.4210526315789475e-05,493 "loss": 0.4699,494 "step": 81495 },496 {497 "epoch": 0.06,498 "learning_rate": 1.4385964912280704e-05,499 "loss": 0.4485,500 "step": 82501 },502 {503 "epoch": 0.07,504 "learning_rate": 1.4561403508771931e-05,505 "loss": 0.434,506 "step": 83507 },508 {509 "epoch": 0.07,510 "learning_rate": 1.4736842105263159e-05,511 "loss": 0.4177,512 "step": 84513 },514 {515 "epoch": 0.07,516 "learning_rate": 1.4912280701754388e-05,517 "loss": 0.5405,518 "step": 85519 },520 {521 "epoch": 0.07,522 "learning_rate": 1.5087719298245615e-05,523 "loss": 0.4776,524 "step": 86525 },526 {527 "epoch": 0.07,528 "learning_rate": 1.5263157894736846e-05,529 "loss": 0.5075,530 "step": 87531 },532 {533 "epoch": 0.07,534 "learning_rate": 1.543859649122807e-05,535 "loss": 0.4583,536 "step": 88537 },538 {539 "epoch": 0.07,540 "learning_rate": 1.56140350877193e-05,541 "loss": 0.4613,542 "step": 89543 },544 {545 "epoch": 0.07,546 "learning_rate": 1.578947368421053e-05,547 "loss": 0.4341,548 "step": 90549 },550 {551 "epoch": 0.07,552 "learning_rate": 1.5964912280701755e-05,553 "loss": 0.4671,554 "step": 91555 },556 {557 "epoch": 0.07,558 "learning_rate": 1.6140350877192984e-05,559 "loss": 0.5195,560 "step": 92561 },562 {563 "epoch": 0.07,564 "learning_rate": 1.6315789473684213e-05,565 "loss": 0.4554,566 "step": 93567 },568 {569 "epoch": 0.07,570 "learning_rate": 1.649122807017544e-05,571 "loss": 0.4719,572 "step": 94573 },574 {575 "epoch": 0.08,576 "learning_rate": 1.6666666666666667e-05,577 "loss": 0.4363,578 "step": 95579 },580 {581 "epoch": 0.08,582 "learning_rate": 1.6842105263157896e-05,583 "loss": 0.4868,584 "step": 96585 },586 {587 "epoch": 0.08,588 "learning_rate": 1.7017543859649125e-05,589 "loss": 0.4891,590 "step": 97591 },592 {593 "epoch": 0.08,594 "learning_rate": 1.719298245614035e-05,595 "loss": 0.504,596 "step": 98597 },598 {599 "epoch": 0.08,600 "learning_rate": 1.736842105263158e-05,601 "loss": 0.4239,602 "step": 99603 },604 {605 "epoch": 0.08,606 "learning_rate": 1.754385964912281e-05,607 "loss": 0.4801,608 "step": 100609 },610 {611 "epoch": 0.08,612 "learning_rate": 1.7719298245614035e-05,613 "loss": 0.542,614 "step": 101615 },616 {617 "epoch": 0.08,618 "learning_rate": 1.7894736842105264e-05,619 "loss": 0.4549,620 "step": 102621 },622 {623 "epoch": 0.08,624 "learning_rate": 1.8070175438596493e-05,625 "loss": 0.4856,626 "step": 103627 },628 {629 "epoch": 0.08,630 "learning_rate": 1.824561403508772e-05,631 "loss": 0.5031,632 "step": 104633 },634 {635 "epoch": 0.08,636 "learning_rate": 1.8421052631578947e-05,637 "loss": 0.5131,638 "step": 105639 },640 {641 "epoch": 0.08,642 "learning_rate": 1.8596491228070176e-05,643 "loss": 0.4797,644 "step": 106645 },646 {647 "epoch": 0.08,648 "learning_rate": 1.8771929824561405e-05,649 "loss": 0.4696,650 "step": 107651 },652 {653 "epoch": 0.09,654 "learning_rate": 1.894736842105263e-05,655 "loss": 0.4593,656 "step": 108657 },658 {659 "epoch": 0.09,660 "learning_rate": 1.912280701754386e-05,661 "loss": 0.4888,662 "step": 109663 },664 {665 "epoch": 0.09,666 "learning_rate": 1.929824561403509e-05,667 "loss": 0.4721,668 "step": 110669 },670 {671 "epoch": 0.09,672 "learning_rate": 1.9473684210526318e-05,673 "loss": 0.4813,674 "step": 111675 },676 {677 "epoch": 0.09,678 "learning_rate": 1.9649122807017544e-05,679 "loss": 0.4517,680 "step": 112681 },682 {683 "epoch": 0.09,684 "learning_rate": 1.9824561403508773e-05,685 "loss": 0.4734,686 "step": 113687 },688 {689 "epoch": 0.09,690 "learning_rate": 2e-05,691 "loss": 0.4996,692 "step": 114693 },694 {695 "epoch": 0.09,696 "learning_rate": 1.9999996358015542e-05,697 "loss": 0.4279,698 "step": 115699 },700 {701 "epoch": 0.09,702 "learning_rate": 1.999998543206481e-05,703 "loss": 0.4594,704 "step": 116705 },706 {707 "epoch": 0.09,708 "learning_rate": 1.999996722215577e-05,709 "loss": 0.4542,710 "step": 117711 },712 {713 "epoch": 0.09,714 "learning_rate": 1.9999941728301686e-05,715 "loss": 0.5227,716 "step": 118717 },718 {719 "epoch": 0.09,720 "learning_rate": 1.9999908950521122e-05,721 "loss": 0.4983,722 "step": 119723 },724 {725 "epoch": 0.09,726 "learning_rate": 1.9999868888837957e-05,727 "loss": 0.518,728 "step": 120729 },730 {731 "epoch": 0.1,732 "learning_rate": 1.999982154328137e-05,733 "loss": 0.4463,734 "step": 121735 },736 {737 "epoch": 0.1,738 "learning_rate": 1.999976691388585e-05,739 "loss": 0.5207,740 "step": 122741 },742 {743 "epoch": 0.1,744 "learning_rate": 1.999970500069119e-05,745 "loss": 0.4854,746 "step": 123747 },748 {749 "epoch": 0.1,750 "learning_rate": 1.9999635803742482e-05,751 "loss": 0.4897,752 "step": 124753 },754 {755 "epoch": 0.1,756 "learning_rate": 1.9999559323090132e-05,757 "loss": 0.4849,758 "step": 125759 },760 {761 "epoch": 0.1,762 "learning_rate": 1.999947555878985e-05,763 "loss": 0.4683,764 "step": 126765 },766 {767 "epoch": 0.1,768 "learning_rate": 1.9999384510902643e-05,769 "loss": 0.4804,770 "step": 127771 },772 {773 "epoch": 0.1,774 "learning_rate": 1.999928617949484e-05,775 "loss": 0.4706,776 "step": 128777 },778 {779 "epoch": 0.1,780 "learning_rate": 1.9999180564638056e-05,781 "loss": 0.478,782 "step": 129783 },784 {785 "epoch": 0.1,786 "learning_rate": 1.9999067666409225e-05,787 "loss": 0.4228,788 "step": 130789 },790 {791 "epoch": 0.1,792 "learning_rate": 1.999894748489058e-05,793 "loss": 0.4729,794 "step": 131795 },796 {797 "epoch": 0.1,798 "learning_rate": 1.9998820020169668e-05,799 "loss": 0.4122,800 "step": 132801 },802 {803 "epoch": 0.11,804 "learning_rate": 1.9998685272339325e-05,805 "loss": 0.5107,806 "step": 133807 },808 {809 "epoch": 0.11,810 "learning_rate": 1.9998543241497702e-05,811 "loss": 0.4522,812 "step": 134813 },814 {815 "epoch": 0.11,816 "learning_rate": 1.9998393927748257e-05,817 "loss": 0.5022,818 "step": 135819 },820 {821 "epoch": 0.11,822 "learning_rate": 1.999823733119975e-05,823 "loss": 0.4496,824 "step": 136825 },826 {827 "epoch": 0.11,828 "learning_rate": 1.9998073451966244e-05,829 "loss": 0.4147,830 "step": 137831 },832 {833 "epoch": 0.11,834 "learning_rate": 1.9997902290167104e-05,835 "loss": 0.4655,836 "step": 138837 },838 {839 "epoch": 0.11,840 "learning_rate": 1.999772384592701e-05,841 "loss": 0.4484,842 "step": 139843 },844 {845 "epoch": 0.11,846 "learning_rate": 1.9997538119375938e-05,847 "loss": 0.5081,848 "step": 140849 },850 {851 "epoch": 0.11,852 "learning_rate": 1.999734511064917e-05,853 "loss": 0.4527,854 "step": 141855 },856 {857 "epoch": 0.11,858 "learning_rate": 1.9997144819887292e-05,859 "loss": 0.4867,860 "step": 142861 },862 {863 "epoch": 0.11,864 "learning_rate": 1.99969372472362e-05,865 "loss": 0.4678,866 "step": 143867 },868 {869 "epoch": 0.11,870 "learning_rate": 1.9996722392847082e-05,871 "loss": 0.4587,872 "step": 144873 },874 {875 "epoch": 0.11,876 "learning_rate": 1.9996500256876447e-05,877 "loss": 0.4274,878 "step": 145879 },880 {881 "epoch": 0.12,882 "learning_rate": 1.999627083948609e-05,883 "loss": 0.4122,884 "step": 146885 },886 {887 "epoch": 0.12,888 "learning_rate": 1.9996034140843113e-05,889 "loss": 0.4339,890 "step": 147891 },892 {893 "epoch": 0.12,894 "learning_rate": 1.9995790161119943e-05,895 "loss": 0.5174,896 "step": 148897 },898 {899 "epoch": 0.12,900 "learning_rate": 1.999553890049428e-05,901 "loss": 0.4538,902 "step": 149903 },904 {905 "epoch": 0.12,906 "learning_rate": 1.999528035914915e-05,907 "loss": 0.4056,908 "step": 150909 },910 {911 "epoch": 0.12,912 "learning_rate": 1.999501453727287e-05,913 "loss": 0.4471,914 "step": 151915 },916 {917 "epoch": 0.12,918 "learning_rate": 1.999474143505906e-05,919 "loss": 0.4472,920 "step": 152921 },922 {923 "epoch": 0.12,924 "learning_rate": 1.9994461052706652e-05,925 "loss": 0.4424,926 "step": 153927 },928 {929 "epoch": 0.12,930 "learning_rate": 1.9994173390419876e-05,931 "loss": 0.4626,932 "step": 154933 },934 {935 "epoch": 0.12,936 "learning_rate": 1.9993878448408263e-05,937 "loss": 0.457,938 "step": 155939 },940 {941 "epoch": 0.12,942 "learning_rate": 1.9993576226886644e-05,943 "loss": 0.4388,944 "step": 156945 },946 {947 "epoch": 0.12,948 "learning_rate": 1.9993266726075163e-05,949 "loss": 0.4594,950 "step": 157951 },952 {953 "epoch": 0.12,954 "learning_rate": 1.9992949946199255e-05,955 "loss": 0.4575,956 "step": 158957 },958 {959 "epoch": 0.13,960 "learning_rate": 1.999262588748966e-05,961 "loss": 0.4169,962 "step": 159963 },964 {965 "epoch": 0.13,966 "learning_rate": 1.999229455018243e-05,967 "loss": 0.4241,968 "step": 160969 },970 {971 "epoch": 0.13,972 "learning_rate": 1.99919559345189e-05,973 "loss": 0.4177,974 "step": 161975 },976 {977 "epoch": 0.13,978 "learning_rate": 1.9991610040745718e-05,979 "loss": 0.4558,980 "step": 162981 },982 {983 "epoch": 0.13,984 "learning_rate": 1.999125686911484e-05,985 "loss": 0.4769,986 "step": 163987 },988 {989 "epoch": 0.13,990 "learning_rate": 1.9990896419883506e-05,991 "loss": 0.4219,992 "step": 164993 },994 {995 "epoch": 0.13,996 "learning_rate": 1.9990528693314273e-05,997 "loss": 0.4606,998 "step": 165999 },1000 {1001 "epoch": 0.13,1002 "learning_rate": 1.9990153689674983e-05,1003 "loss": 0.4634,1004 "step": 1661005 },1006 {1007 "epoch": 0.13,1008 "learning_rate": 1.9989771409238802e-05,1009 "loss": 0.4717,1010 "step": 1671011 },1012 {1013 "epoch": 0.13,1014 "learning_rate": 1.9989381852284165e-05,1015 "loss": 0.4281,1016 "step": 1681017 },1018 {1019 "epoch": 0.13,1020 "learning_rate": 1.9988985019094837e-05,1021 "loss": 0.4336,1022 "step": 1691023 },1024 {1025 "epoch": 0.13,1026 "learning_rate": 1.9988580909959864e-05,1027 "loss": 0.4512,1028 "step": 1701029 },1030 {1031 "epoch": 0.14,1032 "learning_rate": 1.99881695251736e-05,1033 "loss": 0.384,1034 "step": 1711035 },1036 {1037 "epoch": 0.14,1038 "learning_rate": 1.9987750865035693e-05,1039 "loss": 0.433,1040 "step": 1721041 },1042 {1043 "epoch": 0.14,1044 "learning_rate": 1.99873249298511e-05,1045 "loss": 0.4715,1046 "step": 1731047 },1048 {1049 "epoch": 0.14,1050 "learning_rate": 1.998689171993006e-05,1051 "loss": 0.4178,1052 "step": 1741053 },1054 {1055 "epoch": 0.14,1056 "learning_rate": 1.9986451235588135e-05,1057 "loss": 0.4315,1058 "step": 1751059 },1060 {1061 "epoch": 0.14,1062 "learning_rate": 1.998600347714616e-05,1063 "loss": 0.4427,1064 "step": 1761065 },1066 {1067 "epoch": 0.14,1068 "learning_rate": 1.9985548444930295e-05,1069 "loss": 0.4431,1070 "step": 1771071 },1072 {1073 "epoch": 0.14,1074 "learning_rate": 1.998508613927197e-05,1075 "loss": 0.4424,1076 "step": 1781077 },1078 {1079 "epoch": 0.14,1080 "learning_rate": 1.9984616560507938e-05,1081 "loss": 0.413,1082 "step": 1791083 },1084 {1085 "epoch": 0.14,1086 "learning_rate": 1.9984139708980228e-05,1087 "loss": 0.4559,1088 "step": 1801089 },1090 {1091 "epoch": 0.14,1092 "learning_rate": 1.9983655585036187e-05,1093 "loss": 0.404,1094 "step": 1811095 },1096 {1097 "epoch": 0.14,1098 "learning_rate": 1.9983164189028447e-05,1099 "loss": 0.4313,1100 "step": 1821101 },1102 {1103 "epoch": 0.14,1104 "learning_rate": 1.9982665521314934e-05,1105 "loss": 0.444,1106 "step": 1831107 },1108 {1109 "epoch": 0.15,1110 "learning_rate": 1.9982159582258882e-05,1111 "loss": 0.4518,1112 "step": 1841113 },1114 {1115 "epoch": 0.15,1116 "learning_rate": 1.9981646372228813e-05,1117 "loss": 0.4294,1118 "step": 1851119 },1120 {1121 "epoch": 0.15,1122 "learning_rate": 1.9981125891598545e-05,1123 "loss": 0.4346,1124 "step": 1861125 },1126 {1127 "epoch": 0.15,1128 "learning_rate": 1.9980598140747197e-05,1129 "loss": 0.4236,1130 "step": 1871131 },1132 {1133 "epoch": 0.15,1134 "learning_rate": 1.998006312005919e-05,1135 "loss": 0.3642,1136 "step": 1881137 },1138 {1139 "epoch": 0.15,1140 "learning_rate": 1.9979520829924212e-05,1141 "loss": 0.4687,1142 "step": 1891143 },1144 {1145 "epoch": 0.15,1146 "learning_rate": 1.997897127073728e-05,1147 "loss": 0.4344,1148 "step": 1901149 },1150 {1151 "epoch": 0.15,1152 "learning_rate": 1.9978414442898688e-05,1153 "loss": 0.432,1154 "step": 1911155 },1156 {1157 "epoch": 0.15,1158 "learning_rate": 1.9977850346814026e-05,1159 "loss": 0.4309,1160 "step": 1921161 },1162 {1163 "epoch": 0.15,1164 "learning_rate": 1.9977278982894185e-05,1165 "loss": 0.4153,1166 "step": 1931167 },1168 {1169 "epoch": 0.15,1170 "learning_rate": 1.9976700351555337e-05,1171 "loss": 0.4266,1172 "step": 1941173 },1174 {1175 "epoch": 0.15,1176 "learning_rate": 1.997611445321896e-05,1177 "loss": 0.4398,1178 "step": 1951179 },1180 {1181 "epoch": 0.15,1182 "learning_rate": 1.9975521288311817e-05,1183 "loss": 0.4294,1184 "step": 1961185 },1186 {1187 "epoch": 0.16,1188 "learning_rate": 1.997492085726597e-05,1189 "loss": 0.4481,1190 "step": 1971191 },1192 {1193 "epoch": 0.16,1194 "learning_rate": 1.9974313160518776e-05,1195 "loss": 0.4508,1196 "step": 1981197 },1198 {1199 "epoch": 0.16,1200 "learning_rate": 1.997369819851287e-05,