sunshine-lwt/TokenPacker-7b-144token
024
1{2 "best_metric": null,3 "best_model_checkpoint": null,4 "epoch": 1.0,5 "global_step": 5198,6 "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": 1.282051282051282e-07,13 "loss": 1.3164,14 "step": 115 },16 {17 "epoch": 0.0,18 "learning_rate": 2.564102564102564e-07,19 "loss": 1.3428,20 "step": 221 },22 {23 "epoch": 0.0,24 "learning_rate": 3.846153846153847e-07,25 "loss": 1.333,26 "step": 327 },28 {29 "epoch": 0.0,30 "learning_rate": 5.128205128205128e-07,31 "loss": 1.377,32 "step": 433 },34 {35 "epoch": 0.0,36 "learning_rate": 6.41025641025641e-07,37 "loss": 1.3379,38 "step": 539 },40 {41 "epoch": 0.0,42 "learning_rate": 7.692307692307694e-07,43 "loss": 1.3604,44 "step": 645 },46 {47 "epoch": 0.0,48 "learning_rate": 8.974358974358975e-07,49 "loss": 1.3525,50 "step": 751 },52 {53 "epoch": 0.0,54 "learning_rate": 1.0256410256410257e-06,55 "loss": 1.3135,56 "step": 857 },58 {59 "epoch": 0.0,60 "learning_rate": 1.153846153846154e-06,61 "loss": 1.3535,62 "step": 963 },64 {65 "epoch": 0.0,66 "learning_rate": 1.282051282051282e-06,67 "loss": 1.292,68 "step": 1069 },70 {71 "epoch": 0.0,72 "learning_rate": 1.4102564102564104e-06,73 "loss": 1.3203,74 "step": 1175 },76 {77 "epoch": 0.0,78 "learning_rate": 1.5384615384615387e-06,79 "loss": 1.3057,80 "step": 1281 },82 {83 "epoch": 0.0,84 "learning_rate": 1.6666666666666667e-06,85 "loss": 1.251,86 "step": 1387 },88 {89 "epoch": 0.0,90 "learning_rate": 1.794871794871795e-06,91 "loss": 1.1875,92 "step": 1493 },94 {95 "epoch": 0.0,96 "learning_rate": 1.9230769230769234e-06,97 "loss": 1.1992,98 "step": 1599 },100 {101 "epoch": 0.0,102 "learning_rate": 2.0512820512820513e-06,103 "loss": 1.2412,104 "step": 16105 },106 {107 "epoch": 0.0,108 "learning_rate": 2.1794871794871797e-06,109 "loss": 1.1489,110 "step": 17111 },112 {113 "epoch": 0.0,114 "learning_rate": 2.307692307692308e-06,115 "loss": 1.1367,116 "step": 18117 },118 {119 "epoch": 0.0,120 "learning_rate": 2.435897435897436e-06,121 "loss": 1.2012,122 "step": 19123 },124 {125 "epoch": 0.0,126 "learning_rate": 2.564102564102564e-06,127 "loss": 1.106,128 "step": 20129 },130 {131 "epoch": 0.0,132 "learning_rate": 2.6923076923076923e-06,133 "loss": 1.1865,134 "step": 21135 },136 {137 "epoch": 0.0,138 "learning_rate": 2.8205128205128207e-06,139 "loss": 1.1465,140 "step": 22141 },142 {143 "epoch": 0.0,144 "learning_rate": 2.948717948717949e-06,145 "loss": 1.0645,146 "step": 23147 },148 {149 "epoch": 0.0,150 "learning_rate": 3.0769230769230774e-06,151 "loss": 1.167,152 "step": 24153 },154 {155 "epoch": 0.0,156 "learning_rate": 3.205128205128206e-06,157 "loss": 1.123,158 "step": 25159 },160 {161 "epoch": 0.01,162 "learning_rate": 3.3333333333333333e-06,163 "loss": 1.1045,164 "step": 26165 },166 {167 "epoch": 0.01,168 "learning_rate": 3.4615384615384617e-06,169 "loss": 1.1084,170 "step": 27171 },172 {173 "epoch": 0.01,174 "learning_rate": 3.58974358974359e-06,175 "loss": 1.0986,176 "step": 28177 },178 {179 "epoch": 0.01,180 "learning_rate": 3.7179487179487184e-06,181 "loss": 1.0532,182 "step": 29183 },184 {185 "epoch": 0.01,186 "learning_rate": 3.846153846153847e-06,187 "loss": 1.0571,188 "step": 30189 },190 {191 "epoch": 0.01,192 "learning_rate": 3.974358974358974e-06,193 "loss": 1.0991,194 "step": 31195 },196 {197 "epoch": 0.01,198 "learning_rate": 4.102564102564103e-06,199 "loss": 1.0317,200 "step": 32201 },202 {203 "epoch": 0.01,204 "learning_rate": 4.230769230769231e-06,205 "loss": 1.0503,206 "step": 33207 },208 {209 "epoch": 0.01,210 "learning_rate": 4.358974358974359e-06,211 "loss": 1.0337,212 "step": 34213 },214 {215 "epoch": 0.01,216 "learning_rate": 4.487179487179488e-06,217 "loss": 1.0044,218 "step": 35219 },220 {221 "epoch": 0.01,222 "learning_rate": 4.615384615384616e-06,223 "loss": 1.0376,224 "step": 36225 },226 {227 "epoch": 0.01,228 "learning_rate": 4.743589743589744e-06,229 "loss": 0.313,230 "step": 37231 },232 {233 "epoch": 0.01,234 "learning_rate": 4.871794871794872e-06,235 "loss": 1.0596,236 "step": 38237 },238 {239 "epoch": 0.01,240 "learning_rate": 5e-06,241 "loss": 1.0547,242 "step": 39243 },244 {245 "epoch": 0.01,246 "learning_rate": 5.128205128205128e-06,247 "loss": 1.0332,248 "step": 40249 },250 {251 "epoch": 0.01,252 "learning_rate": 5.256410256410257e-06,253 "loss": 1.0234,254 "step": 41255 },256 {257 "epoch": 0.01,258 "learning_rate": 5.384615384615385e-06,259 "loss": 1.084,260 "step": 42261 },262 {263 "epoch": 0.01,264 "learning_rate": 5.512820512820514e-06,265 "loss": 0.979,266 "step": 43267 },268 {269 "epoch": 0.01,270 "learning_rate": 5.641025641025641e-06,271 "loss": 1.0415,272 "step": 44273 },274 {275 "epoch": 0.01,276 "learning_rate": 5.769230769230769e-06,277 "loss": 1.0415,278 "step": 45279 },280 {281 "epoch": 0.01,282 "learning_rate": 5.897435897435898e-06,283 "loss": 0.9995,284 "step": 46285 },286 {287 "epoch": 0.01,288 "learning_rate": 6.025641025641026e-06,289 "loss": 0.9834,290 "step": 47291 },292 {293 "epoch": 0.01,294 "learning_rate": 6.153846153846155e-06,295 "loss": 0.9849,296 "step": 48297 },298 {299 "epoch": 0.01,300 "learning_rate": 6.282051282051282e-06,301 "loss": 0.9839,302 "step": 49303 },304 {305 "epoch": 0.01,306 "learning_rate": 6.410256410256412e-06,307 "loss": 0.9751,308 "step": 50309 },310 {311 "epoch": 0.01,312 "learning_rate": 6.538461538461539e-06,313 "loss": 1.0107,314 "step": 51315 },316 {317 "epoch": 0.01,318 "learning_rate": 6.666666666666667e-06,319 "loss": 1.0107,320 "step": 52321 },322 {323 "epoch": 0.01,324 "learning_rate": 6.794871794871796e-06,325 "loss": 0.9937,326 "step": 53327 },328 {329 "epoch": 0.01,330 "learning_rate": 6.923076923076923e-06,331 "loss": 0.9785,332 "step": 54333 },334 {335 "epoch": 0.01,336 "learning_rate": 7.051282051282053e-06,337 "loss": 1.0107,338 "step": 55339 },340 {341 "epoch": 0.01,342 "learning_rate": 7.17948717948718e-06,343 "loss": 0.3243,344 "step": 56345 },346 {347 "epoch": 0.01,348 "learning_rate": 7.307692307692308e-06,349 "loss": 0.9858,350 "step": 57351 },352 {353 "epoch": 0.01,354 "learning_rate": 7.435897435897437e-06,355 "loss": 1.0176,356 "step": 58357 },358 {359 "epoch": 0.01,360 "learning_rate": 7.564102564102564e-06,361 "loss": 1.0312,362 "step": 59363 },364 {365 "epoch": 0.01,366 "learning_rate": 7.692307692307694e-06,367 "loss": 1.002,368 "step": 60369 },370 {371 "epoch": 0.01,372 "learning_rate": 7.820512820512822e-06,373 "loss": 0.9629,374 "step": 61375 },376 {377 "epoch": 0.01,378 "learning_rate": 7.948717948717949e-06,379 "loss": 0.9795,380 "step": 62381 },382 {383 "epoch": 0.01,384 "learning_rate": 8.076923076923077e-06,385 "loss": 0.9302,386 "step": 63387 },388 {389 "epoch": 0.01,390 "learning_rate": 8.205128205128205e-06,391 "loss": 1.0005,392 "step": 64393 },394 {395 "epoch": 0.01,396 "learning_rate": 8.333333333333334e-06,397 "loss": 0.9897,398 "step": 65399 },400 {401 "epoch": 0.01,402 "learning_rate": 8.461538461538462e-06,403 "loss": 0.9609,404 "step": 66405 },406 {407 "epoch": 0.01,408 "learning_rate": 8.58974358974359e-06,409 "loss": 0.8945,410 "step": 67411 },412 {413 "epoch": 0.01,414 "learning_rate": 8.717948717948719e-06,415 "loss": 0.9795,416 "step": 68417 },418 {419 "epoch": 0.01,420 "learning_rate": 8.846153846153847e-06,421 "loss": 0.9741,422 "step": 69423 },424 {425 "epoch": 0.01,426 "learning_rate": 8.974358974358976e-06,427 "loss": 0.9663,428 "step": 70429 },430 {431 "epoch": 0.01,432 "learning_rate": 9.102564102564104e-06,433 "loss": 0.9478,434 "step": 71435 },436 {437 "epoch": 0.01,438 "learning_rate": 9.230769230769232e-06,439 "loss": 0.9155,440 "step": 72441 },442 {443 "epoch": 0.01,444 "learning_rate": 9.358974358974359e-06,445 "loss": 0.9927,446 "step": 73447 },448 {449 "epoch": 0.01,450 "learning_rate": 9.487179487179487e-06,451 "loss": 0.9565,452 "step": 74453 },454 {455 "epoch": 0.01,456 "learning_rate": 9.615384615384616e-06,457 "loss": 0.9365,458 "step": 75459 },460 {461 "epoch": 0.01,462 "learning_rate": 9.743589743589744e-06,463 "loss": 0.9414,464 "step": 76465 },466 {467 "epoch": 0.01,468 "learning_rate": 9.871794871794872e-06,469 "loss": 0.9097,470 "step": 77471 },472 {473 "epoch": 0.02,474 "learning_rate": 1e-05,475 "loss": 0.9771,476 "step": 78477 },478 {479 "epoch": 0.02,480 "learning_rate": 1.012820512820513e-05,481 "loss": 1.0239,482 "step": 79483 },484 {485 "epoch": 0.02,486 "learning_rate": 1.0256410256410256e-05,487 "loss": 0.9624,488 "step": 80489 },490 {491 "epoch": 0.02,492 "learning_rate": 1.0384615384615386e-05,493 "loss": 1.0039,494 "step": 81495 },496 {497 "epoch": 0.02,498 "learning_rate": 1.0512820512820514e-05,499 "loss": 1.0342,500 "step": 82501 },502 {503 "epoch": 0.02,504 "learning_rate": 1.0641025641025643e-05,505 "loss": 1.0244,506 "step": 83507 },508 {509 "epoch": 0.02,510 "learning_rate": 1.076923076923077e-05,511 "loss": 0.9722,512 "step": 84513 },514 {515 "epoch": 0.02,516 "learning_rate": 1.0897435897435898e-05,517 "loss": 0.9497,518 "step": 85519 },520 {521 "epoch": 0.02,522 "learning_rate": 1.1025641025641028e-05,523 "loss": 0.9478,524 "step": 86525 },526 {527 "epoch": 0.02,528 "learning_rate": 1.1153846153846154e-05,529 "loss": 1.0039,530 "step": 87531 },532 {533 "epoch": 0.02,534 "learning_rate": 1.1282051282051283e-05,535 "loss": 0.9717,536 "step": 88537 },538 {539 "epoch": 0.02,540 "learning_rate": 1.1410256410256411e-05,541 "loss": 0.3018,542 "step": 89543 },544 {545 "epoch": 0.02,546 "learning_rate": 1.1538461538461538e-05,547 "loss": 0.9141,548 "step": 90549 },550 {551 "epoch": 0.02,552 "learning_rate": 1.1666666666666668e-05,553 "loss": 0.9756,554 "step": 91555 },556 {557 "epoch": 0.02,558 "learning_rate": 1.1794871794871796e-05,559 "loss": 0.9897,560 "step": 92561 },562 {563 "epoch": 0.02,564 "learning_rate": 1.1923076923076925e-05,565 "loss": 0.9902,566 "step": 93567 },568 {569 "epoch": 0.02,570 "learning_rate": 1.2051282051282051e-05,571 "loss": 0.9487,572 "step": 94573 },574 {575 "epoch": 0.02,576 "learning_rate": 1.217948717948718e-05,577 "loss": 0.3123,578 "step": 95579 },580 {581 "epoch": 0.02,582 "learning_rate": 1.230769230769231e-05,583 "loss": 0.9521,584 "step": 96585 },586 {587 "epoch": 0.02,588 "learning_rate": 1.2435897435897436e-05,589 "loss": 0.9585,590 "step": 97591 },592 {593 "epoch": 0.02,594 "learning_rate": 1.2564102564102565e-05,595 "loss": 0.9858,596 "step": 98597 },598 {599 "epoch": 0.02,600 "learning_rate": 1.2692307692307693e-05,601 "loss": 0.8926,602 "step": 99603 },604 {605 "epoch": 0.02,606 "learning_rate": 1.2820512820512823e-05,607 "loss": 0.2974,608 "step": 100609 },610 {611 "epoch": 0.02,612 "learning_rate": 1.294871794871795e-05,613 "loss": 0.9448,614 "step": 101615 },616 {617 "epoch": 0.02,618 "learning_rate": 1.3076923076923078e-05,619 "loss": 1.0498,620 "step": 102621 },622 {623 "epoch": 0.02,624 "learning_rate": 1.3205128205128207e-05,625 "loss": 0.9805,626 "step": 103627 },628 {629 "epoch": 0.02,630 "learning_rate": 1.3333333333333333e-05,631 "loss": 0.9644,632 "step": 104633 },634 {635 "epoch": 0.02,636 "learning_rate": 1.3461538461538463e-05,637 "loss": 0.2683,638 "step": 105639 },640 {641 "epoch": 0.02,642 "learning_rate": 1.3589743589743592e-05,643 "loss": 0.9438,644 "step": 106645 },646 {647 "epoch": 0.02,648 "learning_rate": 1.3717948717948718e-05,649 "loss": 1.0205,650 "step": 107651 },652 {653 "epoch": 0.02,654 "learning_rate": 1.3846153846153847e-05,655 "loss": 0.9453,656 "step": 108657 },658 {659 "epoch": 0.02,660 "learning_rate": 1.3974358974358975e-05,661 "loss": 0.9746,662 "step": 109663 },664 {665 "epoch": 0.02,666 "learning_rate": 1.4102564102564105e-05,667 "loss": 0.9688,668 "step": 110669 },670 {671 "epoch": 0.02,672 "learning_rate": 1.4230769230769232e-05,673 "loss": 0.9497,674 "step": 111675 },676 {677 "epoch": 0.02,678 "learning_rate": 1.435897435897436e-05,679 "loss": 1.0312,680 "step": 112681 },682 {683 "epoch": 0.02,684 "learning_rate": 1.4487179487179489e-05,685 "loss": 0.938,686 "step": 113687 },688 {689 "epoch": 0.02,690 "learning_rate": 1.4615384615384615e-05,691 "loss": 0.9727,692 "step": 114693 },694 {695 "epoch": 0.02,696 "learning_rate": 1.4743589743589745e-05,697 "loss": 0.9614,698 "step": 115699 },700 {701 "epoch": 0.02,702 "learning_rate": 1.4871794871794874e-05,703 "loss": 0.2981,704 "step": 116705 },706 {707 "epoch": 0.02,708 "learning_rate": 1.5000000000000002e-05,709 "loss": 0.9819,710 "step": 117711 },712 {713 "epoch": 0.02,714 "learning_rate": 1.5128205128205129e-05,715 "loss": 0.9463,716 "step": 118717 },718 {719 "epoch": 0.02,720 "learning_rate": 1.5256410256410257e-05,721 "loss": 1.063,722 "step": 119723 },724 {725 "epoch": 0.02,726 "learning_rate": 1.5384615384615387e-05,727 "loss": 0.9429,728 "step": 120729 },730 {731 "epoch": 0.02,732 "learning_rate": 1.5512820512820516e-05,733 "loss": 0.9971,734 "step": 121735 },736 {737 "epoch": 0.02,738 "learning_rate": 1.5641025641025644e-05,739 "loss": 1.0186,740 "step": 122741 },742 {743 "epoch": 0.02,744 "learning_rate": 1.576923076923077e-05,745 "loss": 0.9136,746 "step": 123747 },748 {749 "epoch": 0.02,750 "learning_rate": 1.5897435897435897e-05,751 "loss": 0.9473,752 "step": 124753 },754 {755 "epoch": 0.02,756 "learning_rate": 1.602564102564103e-05,757 "loss": 0.9731,758 "step": 125759 },760 {761 "epoch": 0.02,762 "learning_rate": 1.6153846153846154e-05,763 "loss": 0.9531,764 "step": 126765 },766 {767 "epoch": 0.02,768 "learning_rate": 1.6282051282051282e-05,769 "loss": 1.0034,770 "step": 127771 },772 {773 "epoch": 0.02,774 "learning_rate": 1.641025641025641e-05,775 "loss": 0.8584,776 "step": 128777 },778 {779 "epoch": 0.02,780 "learning_rate": 1.653846153846154e-05,781 "loss": 0.9331,782 "step": 129783 },784 {785 "epoch": 0.03,786 "learning_rate": 1.6666666666666667e-05,787 "loss": 0.9585,788 "step": 130789 },790 {791 "epoch": 0.03,792 "learning_rate": 1.6794871794871796e-05,793 "loss": 0.9722,794 "step": 131795 },796 {797 "epoch": 0.03,798 "learning_rate": 1.6923076923076924e-05,799 "loss": 0.9233,800 "step": 132801 },802 {803 "epoch": 0.03,804 "learning_rate": 1.7051282051282053e-05,805 "loss": 0.9141,806 "step": 133807 },808 {809 "epoch": 0.03,810 "learning_rate": 1.717948717948718e-05,811 "loss": 0.9429,812 "step": 134813 },814 {815 "epoch": 0.03,816 "learning_rate": 1.730769230769231e-05,817 "loss": 0.9316,818 "step": 135819 },820 {821 "epoch": 0.03,822 "learning_rate": 1.7435897435897438e-05,823 "loss": 0.9053,824 "step": 136825 },826 {827 "epoch": 0.03,828 "learning_rate": 1.7564102564102566e-05,829 "loss": 0.9902,830 "step": 137831 },832 {833 "epoch": 0.03,834 "learning_rate": 1.7692307692307694e-05,835 "loss": 1.0005,836 "step": 138837 },838 {839 "epoch": 0.03,840 "learning_rate": 1.7820512820512823e-05,841 "loss": 0.9307,842 "step": 139843 },844 {845 "epoch": 0.03,846 "learning_rate": 1.794871794871795e-05,847 "loss": 1.0015,848 "step": 140849 },850 {851 "epoch": 0.03,852 "learning_rate": 1.807692307692308e-05,853 "loss": 0.9761,854 "step": 141855 },856 {857 "epoch": 0.03,858 "learning_rate": 1.8205128205128208e-05,859 "loss": 0.9766,860 "step": 142861 },862 {863 "epoch": 0.03,864 "learning_rate": 1.8333333333333333e-05,865 "loss": 1.0044,866 "step": 143867 },868 {869 "epoch": 0.03,870 "learning_rate": 1.8461538461538465e-05,871 "loss": 0.9771,872 "step": 144873 },874 {875 "epoch": 0.03,876 "learning_rate": 1.8589743589743593e-05,877 "loss": 0.9619,878 "step": 145879 },880 {881 "epoch": 0.03,882 "learning_rate": 1.8717948717948718e-05,883 "loss": 0.9609,884 "step": 146885 },886 {887 "epoch": 0.03,888 "learning_rate": 1.8846153846153846e-05,889 "loss": 0.9307,890 "step": 147891 },892 {893 "epoch": 0.03,894 "learning_rate": 1.8974358974358975e-05,895 "loss": 0.9385,896 "step": 148897 },898 {899 "epoch": 0.03,900 "learning_rate": 1.9102564102564106e-05,901 "loss": 0.9468,902 "step": 149903 },904 {905 "epoch": 0.03,906 "learning_rate": 1.923076923076923e-05,907 "loss": 0.9429,908 "step": 150909 },910 {911 "epoch": 0.03,912 "learning_rate": 1.935897435897436e-05,913 "loss": 0.9902,914 "step": 151915 },916 {917 "epoch": 0.03,918 "learning_rate": 1.9487179487179488e-05,919 "loss": 0.2954,920 "step": 152921 },922 {923 "epoch": 0.03,924 "learning_rate": 1.9615384615384617e-05,925 "loss": 0.9888,926 "step": 153927 },928 {929 "epoch": 0.03,930 "learning_rate": 1.9743589743589745e-05,931 "loss": 0.9092,932 "step": 154933 },934 {935 "epoch": 0.03,936 "learning_rate": 1.9871794871794873e-05,937 "loss": 0.9038,938 "step": 155939 },940 {941 "epoch": 0.03,942 "learning_rate": 2e-05,943 "loss": 1.0137,944 "step": 156945 },946 {947 "epoch": 0.03,948 "learning_rate": 1.9999998058827844e-05,949 "loss": 0.9678,950 "step": 157951 },952 {953 "epoch": 0.03,954 "learning_rate": 1.9999992235312136e-05,955 "loss": 0.9922,956 "step": 158957 },958 {959 "epoch": 0.03,960 "learning_rate": 1.9999982529455127e-05,961 "loss": 0.9355,962 "step": 159963 },964 {965 "epoch": 0.03,966 "learning_rate": 1.9999968941260596e-05,967 "loss": 0.9482,968 "step": 160969 },970 {971 "epoch": 0.03,972 "learning_rate": 1.9999951470733808e-05,973 "loss": 0.9668,974 "step": 161975 },976 {977 "epoch": 0.03,978 "learning_rate": 1.9999930117881548e-05,979 "loss": 0.9863,980 "step": 162981 },982 {983 "epoch": 0.03,984 "learning_rate": 1.9999904882712115e-05,985 "loss": 0.9653,986 "step": 163987 },988 {989 "epoch": 0.03,990 "learning_rate": 1.99998757652353e-05,991 "loss": 0.3369,992 "step": 164993 },994 {995 "epoch": 0.03,996 "learning_rate": 1.9999842765462403e-05,997 "loss": 0.9614,998 "step": 165999 },1000 {1001 "epoch": 0.03,1002 "learning_rate": 1.999980588340624e-05,1003 "loss": 0.9653,1004 "step": 1661005 },1006 {1007 "epoch": 0.03,1008 "learning_rate": 1.9999765119081132e-05,1009 "loss": 0.98,1010 "step": 1671011 },1012 {1013 "epoch": 0.03,1014 "learning_rate": 1.9999720472502902e-05,1015 "loss": 0.9424,1016 "step": 1681017 },1018 {1019 "epoch": 0.03,1020 "learning_rate": 1.9999671943688885e-05,1021 "loss": 0.9536,1022 "step": 1691023 },1024 {1025 "epoch": 0.03,1026 "learning_rate": 1.9999619532657915e-05,1027 "loss": 0.9346,1028 "step": 1701029 },1030 {1031 "epoch": 0.03,1032 "learning_rate": 1.9999563239430352e-05,1033 "loss": 0.8418,1034 "step": 1711035 },1036 {1037 "epoch": 0.03,1038 "learning_rate": 1.9999503064028043e-05,1039 "loss": 0.9873,1040 "step": 1721041 },1042 {1043 "epoch": 0.03,1044 "learning_rate": 1.999943900647435e-05,1045 "loss": 0.9438,1046 "step": 1731047 },1048 {1049 "epoch": 0.03,1050 "learning_rate": 1.9999371066794146e-05,1051 "loss": 0.9697,1052 "step": 1741053 },1054 {1055 "epoch": 0.03,1056 "learning_rate": 1.9999299245013805e-05,1057 "loss": 0.9736,1058 "step": 1751059 },1060 {1061 "epoch": 0.03,1062 "learning_rate": 1.999922354116121e-05,1063 "loss": 0.9404,1064 "step": 1761065 },1066 {1067 "epoch": 0.03,1068 "learning_rate": 1.999914395526575e-05,1069 "loss": 0.9399,1070 "step": 1771071 },1072 {1073 "epoch": 0.03,1074 "learning_rate": 1.9999060487358333e-05,1075 "loss": 0.9072,1076 "step": 1781077 },1078 {1079 "epoch": 0.03,1080 "learning_rate": 1.9998973137471352e-05,1081 "loss": 0.9751,1082 "step": 1791083 },1084 {1085 "epoch": 0.03,1086 "learning_rate": 1.9998881905638727e-05,1087 "loss": 0.2975,1088 "step": 1801089 },1090 {1091 "epoch": 0.03,1092 "learning_rate": 1.9998786791895874e-05,1093 "loss": 0.9375,1094 "step": 1811095 },1096 {1097 "epoch": 0.04,1098 "learning_rate": 1.999868779627972e-05,1099 "loss": 1.0122,1100 "step": 1821101 },1102 {1103 "epoch": 0.04,1104 "learning_rate": 1.9998584918828695e-05,1105 "loss": 0.9375,1106 "step": 1831107 },1108 {1109 "epoch": 0.04,1110 "learning_rate": 1.9998478159582747e-05,1111 "loss": 0.938,1112 "step": 1841113 },1114 {1115 "epoch": 0.04,1116 "learning_rate": 1.999836751858332e-05,1117 "loss": 0.9971,1118 "step": 1851119 },1120 {1121 "epoch": 0.04,1122 "learning_rate": 1.9998252995873367e-05,1123 "loss": 0.9785,1124 "step": 1861125 },1126 {1127 "epoch": 0.04,1128 "learning_rate": 1.999813459149735e-05,1129 "loss": 0.3357,1130 "step": 1871131 },1132 {1133 "epoch": 0.04,1134 "learning_rate": 1.9998012305501243e-05,1135 "loss": 0.9229,1136 "step": 1881137 },1138 {1139 "epoch": 0.04,1140 "learning_rate": 1.999788613793251e-05,1141 "loss": 0.8711,1142 "step": 1891143 },1144 {1145 "epoch": 0.04,1146 "learning_rate": 1.999775608884015e-05,1147 "loss": 0.2975,1148 "step": 1901149 },1150 {1151 "epoch": 0.04,1152 "learning_rate": 1.9997622158274635e-05,1153 "loss": 0.9355,1154 "step": 1911155 },1156 {1157 "epoch": 0.04,1158 "learning_rate": 1.9997484346287973e-05,1159 "loss": 0.9375,1160 "step": 1921161 },1162 {1163 "epoch": 0.04,1164 "learning_rate": 1.9997342652933668e-05,1165 "loss": 1.0303,1166 "step": 1931167 },1168 {1169 "epoch": 0.04,1170 "learning_rate": 1.9997197078266723e-05,1171 "loss": 0.9707,1172 "step": 1941173 },1174 {1175 "epoch": 0.04,1176 "learning_rate": 1.999704762234366e-05,1177 "loss": 0.9189,1178 "step": 1951179 },1180 {1181 "epoch": 0.04,1182 "learning_rate": 1.99968942852225e-05,1183 "loss": 0.9863,1184 "step": 1961185 },1186 {1187 "epoch": 0.04,1188 "learning_rate": 1.9996737066962778e-05,1189 "loss": 0.9927,1190 "step": 1971191 },1192 {1193 "epoch": 0.04,1194 "learning_rate": 1.9996575967625525e-05,1195 "loss": 0.9722,1196 "step": 1981197 },1198 {1199 "epoch": 0.04,1200 "learning_rate": 1.999641098727329e-05,