flagopen/starcoder-15b-taco
053
1{2 "best_metric": null,3 "best_model_checkpoint": null,4 "epoch": 1.5686958037387249,5 "eval_steps": 500,6 "global_step": 9000,7 "is_hyper_param_search": false,8 "is_local_process_zero": true,9 "is_world_process_zero": true,10 "log_history": [11 {12 "epoch": 0.0,13 "learning_rate": 4.355400696864112e-08,14 "loss": 0.6309,15 "step": 116 },17 {18 "epoch": 0.0,19 "learning_rate": 8.710801393728224e-08,20 "loss": 0.6181,21 "step": 222 },23 {24 "epoch": 0.0,25 "learning_rate": 1.3066202090592336e-07,26 "loss": 0.6113,27 "step": 328 },29 {30 "epoch": 0.0,31 "learning_rate": 1.7421602787456448e-07,32 "loss": 0.619,33 "step": 434 },35 {36 "epoch": 0.0,37 "learning_rate": 2.1777003484320556e-07,38 "loss": 0.6133,39 "step": 540 },41 {42 "epoch": 0.0,43 "learning_rate": 2.6132404181184673e-07,44 "loss": 0.5963,45 "step": 646 },47 {48 "epoch": 0.0,49 "learning_rate": 3.0487804878048784e-07,50 "loss": 0.6367,51 "step": 752 },53 {54 "epoch": 0.0,55 "learning_rate": 3.4843205574912896e-07,56 "loss": 0.6349,57 "step": 858 },59 {60 "epoch": 0.0,61 "learning_rate": 3.9198606271777007e-07,62 "loss": 0.6022,63 "step": 964 },65 {66 "epoch": 0.0,67 "learning_rate": 4.3554006968641113e-07,68 "loss": 0.6241,69 "step": 1070 },71 {72 "epoch": 0.0,73 "learning_rate": 4.790940766550523e-07,74 "loss": 0.6141,75 "step": 1176 },77 {78 "epoch": 0.0,79 "learning_rate": 5.226480836236935e-07,80 "loss": 0.6209,81 "step": 1282 },83 {84 "epoch": 0.0,85 "learning_rate": 5.662020905923345e-07,86 "loss": 0.6265,87 "step": 1388 },89 {90 "epoch": 0.0,91 "learning_rate": 6.097560975609757e-07,92 "loss": 0.6186,93 "step": 1494 },95 {96 "epoch": 0.0,97 "learning_rate": 6.533101045296167e-07,98 "loss": 0.6143,99 "step": 15100 },101 {102 "epoch": 0.0,103 "learning_rate": 6.968641114982579e-07,104 "loss": 0.6082,105 "step": 16106 },107 {108 "epoch": 0.0,109 "learning_rate": 7.40418118466899e-07,110 "loss": 0.5972,111 "step": 17112 },113 {114 "epoch": 0.0,115 "learning_rate": 7.839721254355401e-07,116 "loss": 0.595,117 "step": 18118 },119 {120 "epoch": 0.0,121 "learning_rate": 8.275261324041812e-07,122 "loss": 0.5574,123 "step": 19124 },125 {126 "epoch": 0.0,127 "learning_rate": 8.710801393728223e-07,128 "loss": 0.6042,129 "step": 20130 },131 {132 "epoch": 0.0,133 "learning_rate": 9.146341463414634e-07,134 "loss": 0.5634,135 "step": 21136 },137 {138 "epoch": 0.0,139 "learning_rate": 9.581881533101046e-07,140 "loss": 0.5671,141 "step": 22142 },143 {144 "epoch": 0.0,145 "learning_rate": 1.0017421602787455e-06,146 "loss": 0.5882,147 "step": 23148 },149 {150 "epoch": 0.0,151 "learning_rate": 1.045296167247387e-06,152 "loss": 0.5797,153 "step": 24154 },155 {156 "epoch": 0.0,157 "learning_rate": 1.088850174216028e-06,158 "loss": 0.5548,159 "step": 25160 },161 {162 "epoch": 0.0,163 "learning_rate": 1.132404181184669e-06,164 "loss": 0.5518,165 "step": 26166 },167 {168 "epoch": 0.0,169 "learning_rate": 1.1759581881533102e-06,170 "loss": 0.5445,171 "step": 27172 },173 {174 "epoch": 0.0,175 "learning_rate": 1.2195121951219514e-06,176 "loss": 0.5509,177 "step": 28178 },179 {180 "epoch": 0.01,181 "learning_rate": 1.2630662020905923e-06,182 "loss": 0.5398,183 "step": 29184 },185 {186 "epoch": 0.01,187 "learning_rate": 1.3066202090592335e-06,188 "loss": 0.5368,189 "step": 30190 },191 {192 "epoch": 0.01,193 "learning_rate": 1.3501742160278747e-06,194 "loss": 0.5364,195 "step": 31196 },197 {198 "epoch": 0.01,199 "learning_rate": 1.3937282229965158e-06,200 "loss": 0.53,201 "step": 32202 },203 {204 "epoch": 0.01,205 "learning_rate": 1.4372822299651568e-06,206 "loss": 0.529,207 "step": 33208 },209 {210 "epoch": 0.01,211 "learning_rate": 1.480836236933798e-06,212 "loss": 0.519,213 "step": 34214 },215 {216 "epoch": 0.01,217 "learning_rate": 1.5243902439024391e-06,218 "loss": 0.5226,219 "step": 35220 },221 {222 "epoch": 0.01,223 "learning_rate": 1.5679442508710803e-06,224 "loss": 0.5164,225 "step": 36226 },227 {228 "epoch": 0.01,229 "learning_rate": 1.6114982578397212e-06,230 "loss": 0.5038,231 "step": 37232 },233 {234 "epoch": 0.01,235 "learning_rate": 1.6550522648083624e-06,236 "loss": 0.5007,237 "step": 38238 },239 {240 "epoch": 0.01,241 "learning_rate": 1.6986062717770036e-06,242 "loss": 0.4941,243 "step": 39244 },245 {246 "epoch": 0.01,247 "learning_rate": 1.7421602787456445e-06,248 "loss": 0.4985,249 "step": 40250 },251 {252 "epoch": 0.01,253 "learning_rate": 1.7857142857142857e-06,254 "loss": 0.5031,255 "step": 41256 },257 {258 "epoch": 0.01,259 "learning_rate": 1.8292682926829268e-06,260 "loss": 0.4914,261 "step": 42262 },263 {264 "epoch": 0.01,265 "learning_rate": 1.872822299651568e-06,266 "loss": 0.4951,267 "step": 43268 },269 {270 "epoch": 0.01,271 "learning_rate": 1.916376306620209e-06,272 "loss": 0.4971,273 "step": 44274 },275 {276 "epoch": 0.01,277 "learning_rate": 1.95993031358885e-06,278 "loss": 0.4885,279 "step": 45280 },281 {282 "epoch": 0.01,283 "learning_rate": 2.003484320557491e-06,284 "loss": 0.4975,285 "step": 46286 },287 {288 "epoch": 0.01,289 "learning_rate": 2.0470383275261322e-06,290 "loss": 0.4969,291 "step": 47292 },293 {294 "epoch": 0.01,295 "learning_rate": 2.090592334494774e-06,296 "loss": 0.493,297 "step": 48298 },299 {300 "epoch": 0.01,301 "learning_rate": 2.134146341463415e-06,302 "loss": 0.4746,303 "step": 49304 },305 {306 "epoch": 0.01,307 "learning_rate": 2.177700348432056e-06,308 "loss": 0.4842,309 "step": 50310 },311 {312 "epoch": 0.01,313 "learning_rate": 2.221254355400697e-06,314 "loss": 0.4935,315 "step": 51316 },317 {318 "epoch": 0.01,319 "learning_rate": 2.264808362369338e-06,320 "loss": 0.4885,321 "step": 52322 },323 {324 "epoch": 0.01,325 "learning_rate": 2.3083623693379792e-06,326 "loss": 0.4905,327 "step": 53328 },329 {330 "epoch": 0.01,331 "learning_rate": 2.3519163763066204e-06,332 "loss": 0.5062,333 "step": 54334 },335 {336 "epoch": 0.01,337 "learning_rate": 2.3954703832752616e-06,338 "loss": 0.4877,339 "step": 55340 },341 {342 "epoch": 0.01,343 "learning_rate": 2.4390243902439027e-06,344 "loss": 0.4746,345 "step": 56346 },347 {348 "epoch": 0.01,349 "learning_rate": 2.482578397212544e-06,350 "loss": 0.4737,351 "step": 57352 },353 {354 "epoch": 0.01,355 "learning_rate": 2.5261324041811846e-06,356 "loss": 0.4684,357 "step": 58358 },359 {360 "epoch": 0.01,361 "learning_rate": 2.569686411149826e-06,362 "loss": 0.4817,363 "step": 59364 },365 {366 "epoch": 0.01,367 "learning_rate": 2.613240418118467e-06,368 "loss": 0.4789,369 "step": 60370 },371 {372 "epoch": 0.01,373 "learning_rate": 2.656794425087108e-06,374 "loss": 0.4831,375 "step": 61376 },377 {378 "epoch": 0.01,379 "learning_rate": 2.7003484320557493e-06,380 "loss": 0.4677,381 "step": 62382 },383 {384 "epoch": 0.01,385 "learning_rate": 2.7439024390243905e-06,386 "loss": 0.4733,387 "step": 63388 },389 {390 "epoch": 0.01,391 "learning_rate": 2.7874564459930316e-06,392 "loss": 0.4702,393 "step": 64394 },395 {396 "epoch": 0.01,397 "learning_rate": 2.8310104529616724e-06,398 "loss": 0.4718,399 "step": 65400 },401 {402 "epoch": 0.01,403 "learning_rate": 2.8745644599303136e-06,404 "loss": 0.4532,405 "step": 66406 },407 {408 "epoch": 0.01,409 "learning_rate": 2.9181184668989547e-06,410 "loss": 0.4555,411 "step": 67412 },413 {414 "epoch": 0.01,415 "learning_rate": 2.961672473867596e-06,416 "loss": 0.475,417 "step": 68418 },419 {420 "epoch": 0.01,421 "learning_rate": 3.005226480836237e-06,422 "loss": 0.4925,423 "step": 69424 },425 {426 "epoch": 0.01,427 "learning_rate": 3.0487804878048782e-06,428 "loss": 0.4669,429 "step": 70430 },431 {432 "epoch": 0.01,433 "learning_rate": 3.0923344947735194e-06,434 "loss": 0.4744,435 "step": 71436 },437 {438 "epoch": 0.01,439 "learning_rate": 3.1358885017421605e-06,440 "loss": 0.4597,441 "step": 72442 },443 {444 "epoch": 0.01,445 "learning_rate": 3.1794425087108017e-06,446 "loss": 0.4591,447 "step": 73448 },449 {450 "epoch": 0.01,451 "learning_rate": 3.2229965156794425e-06,452 "loss": 0.4763,453 "step": 74454 },455 {456 "epoch": 0.01,457 "learning_rate": 3.266550522648084e-06,458 "loss": 0.4632,459 "step": 75460 },461 {462 "epoch": 0.01,463 "learning_rate": 3.3101045296167248e-06,464 "loss": 0.4684,465 "step": 76466 },467 {468 "epoch": 0.01,469 "learning_rate": 3.3536585365853664e-06,470 "loss": 0.4632,471 "step": 77472 },473 {474 "epoch": 0.01,475 "learning_rate": 3.397212543554007e-06,476 "loss": 0.4985,477 "step": 78478 },479 {480 "epoch": 0.01,481 "learning_rate": 3.4407665505226483e-06,482 "loss": 0.4618,483 "step": 79484 },485 {486 "epoch": 0.01,487 "learning_rate": 3.484320557491289e-06,488 "loss": 0.4556,489 "step": 80490 },491 {492 "epoch": 0.01,493 "learning_rate": 3.5278745644599306e-06,494 "loss": 0.489,495 "step": 81496 },497 {498 "epoch": 0.01,499 "learning_rate": 3.5714285714285714e-06,500 "loss": 0.4752,501 "step": 82502 },503 {504 "epoch": 0.01,505 "learning_rate": 3.614982578397213e-06,506 "loss": 0.4538,507 "step": 83508 },509 {510 "epoch": 0.01,511 "learning_rate": 3.6585365853658537e-06,512 "loss": 0.4833,513 "step": 84514 },515 {516 "epoch": 0.01,517 "learning_rate": 3.7020905923344953e-06,518 "loss": 0.4764,519 "step": 85520 },521 {522 "epoch": 0.01,523 "learning_rate": 3.745644599303136e-06,524 "loss": 0.476,525 "step": 86526 },527 {528 "epoch": 0.02,529 "learning_rate": 3.789198606271777e-06,530 "loss": 0.4763,531 "step": 87532 },533 {534 "epoch": 0.02,535 "learning_rate": 3.832752613240418e-06,536 "loss": 0.4633,537 "step": 88538 },539 {540 "epoch": 0.02,541 "learning_rate": 3.876306620209059e-06,542 "loss": 0.4433,543 "step": 89544 },545 {546 "epoch": 0.02,547 "learning_rate": 3.9198606271777e-06,548 "loss": 0.4548,549 "step": 90550 },551 {552 "epoch": 0.02,553 "learning_rate": 3.9634146341463414e-06,554 "loss": 0.4502,555 "step": 91556 },557 {558 "epoch": 0.02,559 "learning_rate": 4.006968641114982e-06,560 "loss": 0.4411,561 "step": 92562 },563 {564 "epoch": 0.02,565 "learning_rate": 4.050522648083624e-06,566 "loss": 0.4553,567 "step": 93568 },569 {570 "epoch": 0.02,571 "learning_rate": 4.0940766550522645e-06,572 "loss": 0.4643,573 "step": 94574 },575 {576 "epoch": 0.02,577 "learning_rate": 4.137630662020906e-06,578 "loss": 0.452,579 "step": 95580 },581 {582 "epoch": 0.02,583 "learning_rate": 4.181184668989548e-06,584 "loss": 0.4791,585 "step": 96586 },587 {588 "epoch": 0.02,589 "learning_rate": 4.224738675958188e-06,590 "loss": 0.45,591 "step": 97592 },593 {594 "epoch": 0.02,595 "learning_rate": 4.26829268292683e-06,596 "loss": 0.4543,597 "step": 98598 },599 {600 "epoch": 0.02,601 "learning_rate": 4.311846689895471e-06,602 "loss": 0.4707,603 "step": 99604 },605 {606 "epoch": 0.02,607 "learning_rate": 4.355400696864112e-06,608 "loss": 0.4644,609 "step": 100610 },611 {612 "epoch": 0.02,613 "learning_rate": 4.398954703832753e-06,614 "loss": 0.4475,615 "step": 101616 },617 {618 "epoch": 0.02,619 "learning_rate": 4.442508710801394e-06,620 "loss": 0.4502,621 "step": 102622 },623 {624 "epoch": 0.02,625 "learning_rate": 4.4860627177700346e-06,626 "loss": 0.4455,627 "step": 103628 },629 {630 "epoch": 0.02,631 "learning_rate": 4.529616724738676e-06,632 "loss": 0.4411,633 "step": 104634 },635 {636 "epoch": 0.02,637 "learning_rate": 4.573170731707317e-06,638 "loss": 0.4704,639 "step": 105640 },641 {642 "epoch": 0.02,643 "learning_rate": 4.6167247386759585e-06,644 "loss": 0.4671,645 "step": 106646 },647 {648 "epoch": 0.02,649 "learning_rate": 4.660278745644599e-06,650 "loss": 0.4591,651 "step": 107652 },653 {654 "epoch": 0.02,655 "learning_rate": 4.703832752613241e-06,656 "loss": 0.4728,657 "step": 108658 },659 {660 "epoch": 0.02,661 "learning_rate": 4.7473867595818816e-06,662 "loss": 0.479,663 "step": 109664 },665 {666 "epoch": 0.02,667 "learning_rate": 4.790940766550523e-06,668 "loss": 0.4571,669 "step": 110670 },671 {672 "epoch": 0.02,673 "learning_rate": 4.834494773519164e-06,674 "loss": 0.4594,675 "step": 111676 },677 {678 "epoch": 0.02,679 "learning_rate": 4.8780487804878055e-06,680 "loss": 0.4476,681 "step": 112682 },683 {684 "epoch": 0.02,685 "learning_rate": 4.921602787456446e-06,686 "loss": 0.4434,687 "step": 113688 },689 {690 "epoch": 0.02,691 "learning_rate": 4.965156794425088e-06,692 "loss": 0.4675,693 "step": 114694 },695 {696 "epoch": 0.02,697 "learning_rate": 5.0087108013937286e-06,698 "loss": 0.428,699 "step": 115700 },701 {702 "epoch": 0.02,703 "learning_rate": 5.052264808362369e-06,704 "loss": 0.4514,705 "step": 116706 },707 {708 "epoch": 0.02,709 "learning_rate": 5.09581881533101e-06,710 "loss": 0.4565,711 "step": 117712 },713 {714 "epoch": 0.02,715 "learning_rate": 5.139372822299652e-06,716 "loss": 0.4395,717 "step": 118718 },719 {720 "epoch": 0.02,721 "learning_rate": 5.182926829268292e-06,722 "loss": 0.4549,723 "step": 119724 },725 {726 "epoch": 0.02,727 "learning_rate": 5.226480836236934e-06,728 "loss": 0.4613,729 "step": 120730 },731 {732 "epoch": 0.02,733 "learning_rate": 5.270034843205575e-06,734 "loss": 0.433,735 "step": 121736 },737 {738 "epoch": 0.02,739 "learning_rate": 5.313588850174216e-06,740 "loss": 0.4411,741 "step": 122742 },743 {744 "epoch": 0.02,745 "learning_rate": 5.357142857142857e-06,746 "loss": 0.4299,747 "step": 123748 },749 {750 "epoch": 0.02,751 "learning_rate": 5.400696864111499e-06,752 "loss": 0.453,753 "step": 124754 },755 {756 "epoch": 0.02,757 "learning_rate": 5.444250871080139e-06,758 "loss": 0.4609,759 "step": 125760 },761 {762 "epoch": 0.02,763 "learning_rate": 5.487804878048781e-06,764 "loss": 0.4577,765 "step": 126766 },767 {768 "epoch": 0.02,769 "learning_rate": 5.531358885017422e-06,770 "loss": 0.4571,771 "step": 127772 },773 {774 "epoch": 0.02,775 "learning_rate": 5.574912891986063e-06,776 "loss": 0.4483,777 "step": 128778 },779 {780 "epoch": 0.02,781 "learning_rate": 5.618466898954704e-06,782 "loss": 0.4625,783 "step": 129784 },785 {786 "epoch": 0.02,787 "learning_rate": 5.662020905923345e-06,788 "loss": 0.4591,789 "step": 130790 },791 {792 "epoch": 0.02,793 "learning_rate": 5.705574912891986e-06,794 "loss": 0.4528,795 "step": 131796 },797 {798 "epoch": 0.02,799 "learning_rate": 5.749128919860627e-06,800 "loss": 0.4452,801 "step": 132802 },803 {804 "epoch": 0.02,805 "learning_rate": 5.792682926829269e-06,806 "loss": 0.4513,807 "step": 133808 },809 {810 "epoch": 0.02,811 "learning_rate": 5.8362369337979094e-06,812 "loss": 0.4426,813 "step": 134814 },815 {816 "epoch": 0.02,817 "learning_rate": 5.879790940766551e-06,818 "loss": 0.4408,819 "step": 135820 },821 {822 "epoch": 0.02,823 "learning_rate": 5.923344947735192e-06,824 "loss": 0.4465,825 "step": 136826 },827 {828 "epoch": 0.02,829 "learning_rate": 5.966898954703833e-06,830 "loss": 0.4511,831 "step": 137832 },833 {834 "epoch": 0.02,835 "learning_rate": 6.010452961672474e-06,836 "loss": 0.4381,837 "step": 138838 },839 {840 "epoch": 0.02,841 "learning_rate": 6.054006968641116e-06,842 "loss": 0.4375,843 "step": 139844 },845 {846 "epoch": 0.02,847 "learning_rate": 6.0975609756097564e-06,848 "loss": 0.4644,849 "step": 140850 },851 {852 "epoch": 0.02,853 "learning_rate": 6.141114982578398e-06,854 "loss": 0.4391,855 "step": 141856 },857 {858 "epoch": 0.02,859 "learning_rate": 6.184668989547039e-06,860 "loss": 0.4412,861 "step": 142862 },863 {864 "epoch": 0.02,865 "learning_rate": 6.2282229965156795e-06,866 "loss": 0.4366,867 "step": 143868 },869 {870 "epoch": 0.03,871 "learning_rate": 6.271777003484321e-06,872 "loss": 0.4318,873 "step": 144874 },875 {876 "epoch": 0.03,877 "learning_rate": 6.315331010452962e-06,878 "loss": 0.4302,879 "step": 145880 },881 {882 "epoch": 0.03,883 "learning_rate": 6.3588850174216034e-06,884 "loss": 0.469,885 "step": 146886 },887 {888 "epoch": 0.03,889 "learning_rate": 6.402439024390244e-06,890 "loss": 0.4515,891 "step": 147892 },893 {894 "epoch": 0.03,895 "learning_rate": 6.445993031358885e-06,896 "loss": 0.4397,897 "step": 148898 },899 {900 "epoch": 0.03,901 "learning_rate": 6.489547038327526e-06,902 "loss": 0.4328,903 "step": 149904 },905 {906 "epoch": 0.03,907 "learning_rate": 6.533101045296168e-06,908 "loss": 0.4432,909 "step": 150910 },911 {912 "epoch": 0.03,913 "learning_rate": 6.576655052264809e-06,914 "loss": 0.4404,915 "step": 151916 },917 {918 "epoch": 0.03,919 "learning_rate": 6.6202090592334496e-06,920 "loss": 0.4377,921 "step": 152922 },923 {924 "epoch": 0.03,925 "learning_rate": 6.66376306620209e-06,926 "loss": 0.4416,927 "step": 153928 },929 {930 "epoch": 0.03,931 "learning_rate": 6.707317073170733e-06,932 "loss": 0.4317,933 "step": 154934 },935 {936 "epoch": 0.03,937 "learning_rate": 6.7508710801393735e-06,938 "loss": 0.4389,939 "step": 155940 },941 {942 "epoch": 0.03,943 "learning_rate": 6.794425087108014e-06,944 "loss": 0.4192,945 "step": 156946 },947 {948 "epoch": 0.03,949 "learning_rate": 6.837979094076655e-06,950 "loss": 0.437,951 "step": 157952 },953 {954 "epoch": 0.03,955 "learning_rate": 6.8815331010452966e-06,956 "loss": 0.4539,957 "step": 158958 },959 {960 "epoch": 0.03,961 "learning_rate": 6.925087108013937e-06,962 "loss": 0.4357,963 "step": 159964 },965 {966 "epoch": 0.03,967 "learning_rate": 6.968641114982578e-06,968 "loss": 0.4503,969 "step": 160970 },971 {972 "epoch": 0.03,973 "learning_rate": 7.0121951219512205e-06,974 "loss": 0.4272,975 "step": 161976 },977 {978 "epoch": 0.03,979 "learning_rate": 7.055749128919861e-06,980 "loss": 0.4337,981 "step": 162982 },983 {984 "epoch": 0.03,985 "learning_rate": 7.099303135888502e-06,986 "loss": 0.4561,987 "step": 163988 },989 {990 "epoch": 0.03,991 "learning_rate": 7.142857142857143e-06,992 "loss": 0.4302,993 "step": 164994 },995 {996 "epoch": 0.03,997 "learning_rate": 7.186411149825785e-06,998 "loss": 0.4453,999 "step": 1651000 },1001 {1002 "epoch": 0.03,1003 "learning_rate": 7.229965156794426e-06,1004 "loss": 0.4487,1005 "step": 1661006 },1007 {1008 "epoch": 0.03,1009 "learning_rate": 7.273519163763067e-06,1010 "loss": 0.4287,1011 "step": 1671012 },1013 {1014 "epoch": 0.03,1015 "learning_rate": 7.317073170731707e-06,1016 "loss": 0.4452,1017 "step": 1681018 },1019 {1020 "epoch": 0.03,1021 "learning_rate": 7.360627177700349e-06,1022 "loss": 0.4494,1023 "step": 1691024 },1025 {1026 "epoch": 0.03,1027 "learning_rate": 7.4041811846689906e-06,1028 "loss": 0.4437,1029 "step": 1701030 },1031 {1032 "epoch": 0.03,1033 "learning_rate": 7.447735191637631e-06,1034 "loss": 0.4404,1035 "step": 1711036 },1037 {1038 "epoch": 0.03,1039 "learning_rate": 7.491289198606272e-06,1040 "loss": 0.4397,1041 "step": 1721042 },1043 {1044 "epoch": 0.03,1045 "learning_rate": 7.534843205574914e-06,1046 "loss": 0.4357,1047 "step": 1731048 },1049 {1050 "epoch": 0.03,1051 "learning_rate": 7.578397212543554e-06,1052 "loss": 0.4389,1053 "step": 1741054 },1055 {1056 "epoch": 0.03,1057 "learning_rate": 7.621951219512195e-06,1058 "loss": 0.4399,1059 "step": 1751060 },1061 {1062 "epoch": 0.03,1063 "learning_rate": 7.665505226480837e-06,1064 "loss": 0.4359,1065 "step": 1761066 },1067 {1068 "epoch": 0.03,1069 "learning_rate": 7.709059233449478e-06,1070 "loss": 0.4385,1071 "step": 1771072 },1073 {1074 "epoch": 0.03,1075 "learning_rate": 7.752613240418118e-06,1076 "loss": 0.4346,1077 "step": 1781078 },1079 {1080 "epoch": 0.03,1081 "learning_rate": 7.79616724738676e-06,1082 "loss": 0.431,1083 "step": 1791084 },1085 {1086 "epoch": 0.03,1087 "learning_rate": 7.8397212543554e-06,1088 "loss": 0.4342,1089 "step": 1801090 },1091 {1092 "epoch": 0.03,1093 "learning_rate": 7.883275261324043e-06,1094 "loss": 0.4407,1095 "step": 1811096 },1097 {1098 "epoch": 0.03,1099 "learning_rate": 7.926829268292683e-06,1100 "loss": 0.4327,1101 "step": 1821102 },1103 {1104 "epoch": 0.03,1105 "learning_rate": 7.970383275261324e-06,1106 "loss": 0.4484,1107 "step": 1831108 },1109 {1110 "epoch": 0.03,1111 "learning_rate": 8.013937282229964e-06,1112 "loss": 0.4291,1113 "step": 1841114 },1115 {1116 "epoch": 0.03,1117 "learning_rate": 8.057491289198608e-06,1118 "loss": 0.4238,1119 "step": 1851120 },1121 {1122 "epoch": 0.03,1123 "learning_rate": 8.101045296167248e-06,1124 "loss": 0.4211,1125 "step": 1861126 },1127 {1128 "epoch": 0.03,1129 "learning_rate": 8.144599303135889e-06,1130 "loss": 0.4384,1131 "step": 1871132 },1133 {1134 "epoch": 0.03,1135 "learning_rate": 8.188153310104529e-06,1136 "loss": 0.4307,1137 "step": 1881138 },1139 {1140 "epoch": 0.03,1141 "learning_rate": 8.231707317073172e-06,1142 "loss": 0.439,1143 "step": 1891144 },1145 {1146 "epoch": 0.03,1147 "learning_rate": 8.275261324041812e-06,1148 "loss": 0.4359,1149 "step": 1901150 },1151 {1152 "epoch": 0.03,1153 "learning_rate": 8.318815331010454e-06,1154 "loss": 0.436,1155 "step": 1911156 },1157 {1158 "epoch": 0.03,1159 "learning_rate": 8.362369337979095e-06,1160 "loss": 0.44,1161 "step": 1921162 },1163 {1164 "epoch": 0.03,1165 "learning_rate": 8.405923344947735e-06,1166 "loss": 0.4382,1167 "step": 1931168 },1169 {1170 "epoch": 0.03,1171 "learning_rate": 8.449477351916377e-06,1172 "loss": 0.4426,1173 "step": 1941174 },1175 {1176 "epoch": 0.03,1177 "learning_rate": 8.493031358885017e-06,1178 "loss": 0.4399,1179 "step": 1951180 },1181 {1182 "epoch": 0.03,1183 "learning_rate": 8.53658536585366e-06,1184 "loss": 0.4616,1185 "step": 1961186 },1187 {1188 "epoch": 0.03,1189 "learning_rate": 8.5801393728223e-06,1190 "loss": 0.4334,1191 "step": 1971192 },1193 {1194 "epoch": 0.03,1195 "learning_rate": 8.623693379790942e-06,1196 "loss": 0.4603,1197 "step": 1981198 },1199 {1200 "epoch": 0.03,