wellecks/llmstep-mathlib4-pythia2.8b
671
1{2 "best_metric": 0.890625,3 "best_model_checkpoint": "/net/nfs/mosaic/seanw/ntptutorial/proofstep/EleutherAI/pythia-2.8b-deduped/checkpoint-5000",4 "epoch": 1.887504718761797,5 "global_step": 5000,6 "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": 3.4478393790900113e-06,13 "loss": 2.7471,14 "step": 1015 },16 {17 "epoch": 0.01,18 "learning_rate": 4.48574245242758e-06,19 "loss": 2.2453,20 "step": 2021 },22 {23 "epoch": 0.01,24 "learning_rate": 5.092876829713298e-06,25 "loss": 2.1194,26 "step": 3027 },28 {29 "epoch": 0.02,30 "learning_rate": 5.523645525765149e-06,31 "loss": 1.9594,32 "step": 4033 },34 {35 "epoch": 0.02,36 "learning_rate": 5.857775684842452e-06,37 "loss": 1.874,38 "step": 5039 },40 {41 "epoch": 0.02,42 "learning_rate": 6.130779903050867e-06,43 "loss": 1.8366,44 "step": 6045 },46 {47 "epoch": 0.03,48 "learning_rate": 6.361601680642952e-06,49 "loss": 1.8257,50 "step": 7051 },52 {53 "epoch": 0.03,54 "learning_rate": 6.561548599102718e-06,55 "loss": 1.7581,56 "step": 8057 },58 {59 "epoch": 0.03,60 "learning_rate": 6.737914280336586e-06,61 "loss": 1.7984,62 "step": 9063 },64 {65 "epoch": 0.04,66 "learning_rate": 6.895678758180023e-06,67 "loss": 1.676,68 "step": 10069 },70 {71 "epoch": 0.04,72 "learning_rate": 7.038394088074824e-06,73 "loss": 1.7201,74 "step": 11075 },76 {77 "epoch": 0.05,78 "learning_rate": 7.168682976388437e-06,79 "loss": 1.6249,80 "step": 12081 },82 {83 "epoch": 0.05,84 "learning_rate": 7.2885371352490585e-06,85 "loss": 1.5939,86 "step": 13087 },88 {89 "epoch": 0.05,90 "learning_rate": 7.39950475398052e-06,91 "loss": 1.5962,92 "step": 14093 },94 {95 "epoch": 0.06,96 "learning_rate": 7.502813135465739e-06,97 "loss": 1.6127,98 "step": 15099 },100 {101 "epoch": 0.06,102 "learning_rate": 7.599451672440288e-06,103 "loss": 1.6355,104 "step": 160105 },106 {107 "epoch": 0.06,108 "learning_rate": 7.690229624176853e-06,109 "loss": 1.598,110 "step": 170111 },112 {113 "epoch": 0.07,114 "learning_rate": 7.775817353674156e-06,115 "loss": 1.5307,116 "step": 180117 },118 {119 "epoch": 0.07,120 "learning_rate": 7.856776400608327e-06,121 "loss": 1.5646,122 "step": 190123 },124 {125 "epoch": 0.08,126 "learning_rate": 7.93358183151759e-06,127 "loss": 1.5411,128 "step": 200129 },130 {131 "epoch": 0.08,132 "learning_rate": 8.006639131266238e-06,133 "loss": 1.5405,134 "step": 210135 },136 {137 "epoch": 0.08,138 "learning_rate": 8.076297161412393e-06,139 "loss": 1.5144,140 "step": 220141 },142 {143 "epoch": 0.09,144 "learning_rate": 8.142858235714492e-06,145 "loss": 1.485,146 "step": 230147 },148 {149 "epoch": 0.09,150 "learning_rate": 8.206586049726006e-06,151 "loss": 1.4476,152 "step": 240153 },154 {155 "epoch": 0.09,156 "learning_rate": 8.267711990594892e-06,157 "loss": 1.4511,158 "step": 250159 },160 {161 "epoch": 0.1,162 "learning_rate": 8.326440208586629e-06,163 "loss": 1.4577,164 "step": 260165 },166 {167 "epoch": 0.1,168 "learning_rate": 8.382951730959874e-06,169 "loss": 1.4848,170 "step": 270171 },172 {173 "epoch": 0.11,174 "learning_rate": 8.43740782731809e-06,175 "loss": 1.4021,176 "step": 280177 },178 {179 "epoch": 0.11,180 "learning_rate": 8.489952784148422e-06,181 "loss": 1.4138,182 "step": 290183 },184 {185 "epoch": 0.11,186 "learning_rate": 8.540716208803308e-06,187 "loss": 1.378,188 "step": 300189 },190 {191 "epoch": 0.12,192 "learning_rate": 8.589814955558195e-06,193 "loss": 1.3893,194 "step": 310195 },196 {197 "epoch": 0.12,198 "learning_rate": 8.637354745777857e-06,199 "loss": 1.3791,200 "step": 320201 },202 {203 "epoch": 0.12,204 "learning_rate": 8.683431538698111e-06,205 "loss": 1.4285,206 "step": 330207 },208 {209 "epoch": 0.13,210 "learning_rate": 8.728132697514422e-06,211 "loss": 1.4242,212 "step": 340213 },214 {215 "epoch": 0.13,216 "learning_rate": 8.77153798639539e-06,217 "loss": 1.3793,218 "step": 350219 },220 {221 "epoch": 0.14,222 "learning_rate": 8.813720427011724e-06,223 "loss": 1.3997,224 "step": 360225 },226 {227 "epoch": 0.14,228 "learning_rate": 8.854747037685042e-06,229 "loss": 1.4108,230 "step": 370231 },232 {233 "epoch": 0.14,234 "learning_rate": 8.894679473945897e-06,235 "loss": 1.3924,236 "step": 380237 },238 {239 "epoch": 0.15,240 "learning_rate": 8.933574585872348e-06,241 "loss": 1.3793,242 "step": 390243 },244 {245 "epoch": 0.15,246 "learning_rate": 8.97148490485516e-06,247 "loss": 1.3523,248 "step": 400249 },250 {251 "epoch": 0.15,252 "learning_rate": 9.008459070248975e-06,253 "loss": 1.3515,254 "step": 410255 },256 {257 "epoch": 0.16,258 "learning_rate": 9.044542204603808e-06,259 "loss": 1.4118,260 "step": 420261 },262 {263 "epoch": 0.16,264 "learning_rate": 9.07977624473865e-06,265 "loss": 1.3533,266 "step": 430267 },268 {269 "epoch": 0.17,270 "learning_rate": 9.114200234749962e-06,271 "loss": 1.363,272 "step": 440273 },274 {275 "epoch": 0.17,276 "learning_rate": 9.147850586089026e-06,277 "loss": 1.3651,278 "step": 450279 },280 {281 "epoch": 0.17,282 "learning_rate": 9.180761309052062e-06,283 "loss": 1.3318,284 "step": 460285 },286 {287 "epoch": 0.18,288 "learning_rate": 9.21296421937283e-06,289 "loss": 1.3013,290 "step": 470291 },292 {293 "epoch": 0.18,294 "learning_rate": 9.244489123063576e-06,295 "loss": 1.3052,296 "step": 480297 },298 {299 "epoch": 0.18,300 "learning_rate": 9.27536398219589e-06,301 "loss": 1.3055,302 "step": 490303 },304 {305 "epoch": 0.19,306 "learning_rate": 9.305615063932462e-06,307 "loss": 1.3519,308 "step": 500309 },310 {311 "epoch": 0.19,312 "eval_loss": 1.3330078125,313 "eval_runtime": 65.706,314 "eval_samples_per_second": 61.684,315 "eval_steps_per_second": 1.933,316 "step": 500317 },318 {319 "epoch": 0.19,320 "learning_rate": 9.335267074800138e-06,321 "loss": 1.2696,322 "step": 510323 },324 {325 "epoch": 0.2,326 "learning_rate": 9.364343281924199e-06,327 "loss": 1.3356,328 "step": 520329 },330 {331 "epoch": 0.2,332 "learning_rate": 9.392865622714283e-06,333 "loss": 1.2978,334 "step": 530335 },336 {337 "epoch": 0.2,338 "learning_rate": 9.420854804297444e-06,339 "loss": 1.3221,340 "step": 540341 },342 {343 "epoch": 0.21,344 "learning_rate": 9.448330393827263e-06,345 "loss": 1.252,346 "step": 550347 },348 {349 "epoch": 0.21,350 "learning_rate": 9.475310900655658e-06,351 "loss": 1.2975,352 "step": 560353 },354 {355 "epoch": 0.22,356 "learning_rate": 9.501813851231617e-06,357 "loss": 1.2992,358 "step": 570359 },360 {361 "epoch": 0.22,362 "learning_rate": 9.527855857485992e-06,363 "loss": 1.2637,364 "step": 580365 },366 {367 "epoch": 0.22,368 "learning_rate": 9.553452679370556e-06,369 "loss": 1.2805,370 "step": 590371 },372 {373 "epoch": 0.23,374 "learning_rate": 9.578619282140878e-06,375 "loss": 1.2689,376 "step": 600377 },378 {379 "epoch": 0.23,380 "learning_rate": 9.603369888904405e-06,381 "loss": 1.2505,382 "step": 610383 },384 {385 "epoch": 0.23,386 "learning_rate": 9.627718028895765e-06,387 "loss": 1.2542,388 "step": 620389 },390 {391 "epoch": 0.24,392 "learning_rate": 9.651676581889526e-06,393 "loss": 1.2741,394 "step": 630395 },396 {397 "epoch": 0.24,398 "learning_rate": 9.675257819115427e-06,399 "loss": 1.2702,400 "step": 640401 },402 {403 "epoch": 0.25,404 "learning_rate": 9.6984734410015e-06,405 "loss": 1.2626,406 "step": 650407 },408 {409 "epoch": 0.25,410 "learning_rate": 9.721334612035681e-06,411 "loss": 1.2431,412 "step": 660413 },414 {415 "epoch": 0.25,416 "learning_rate": 9.743851993005941e-06,417 "loss": 1.2712,418 "step": 670419 },420 {421 "epoch": 0.26,422 "learning_rate": 9.76603577085199e-06,423 "loss": 1.2467,424 "step": 680425 },426 {427 "epoch": 0.26,428 "learning_rate": 9.787895686337778e-06,429 "loss": 1.2577,430 "step": 690431 },432 {433 "epoch": 0.26,434 "learning_rate": 9.80944105973296e-06,435 "loss": 1.2069,436 "step": 700437 },438 {439 "epoch": 0.27,440 "learning_rate": 9.830680814672785e-06,441 "loss": 1.1961,442 "step": 710443 },444 {445 "epoch": 0.27,446 "learning_rate": 9.851623500349294e-06,447 "loss": 1.2356,448 "step": 720449 },450 {451 "epoch": 0.28,452 "learning_rate": 9.872277312171945e-06,453 "loss": 1.2155,454 "step": 730455 },456 {457 "epoch": 0.28,458 "learning_rate": 9.892650111022612e-06,459 "loss": 1.233,460 "step": 740461 },462 {463 "epoch": 0.28,464 "learning_rate": 9.91274944121818e-06,465 "loss": 1.247,466 "step": 750467 },468 {469 "epoch": 0.29,470 "learning_rate": 9.932582547283467e-06,471 "loss": 1.2464,472 "step": 760473 },474 {475 "epoch": 0.29,476 "learning_rate": 9.952156389627764e-06,477 "loss": 1.2211,478 "step": 770479 },480 {481 "epoch": 0.29,482 "learning_rate": 9.971477659209916e-06,483 "loss": 1.2357,484 "step": 780485 },486 {487 "epoch": 0.3,488 "learning_rate": 9.990552791269229e-06,489 "loss": 1.2205,490 "step": 790491 },492 {493 "epoch": 0.3,494 "learning_rate": 1e-05,495 "loss": 1.2111,496 "step": 800497 },498 {499 "epoch": 0.31,500 "learning_rate": 1e-05,501 "loss": 1.1852,502 "step": 810503 },504 {505 "epoch": 0.31,506 "learning_rate": 1e-05,507 "loss": 1.2291,508 "step": 820509 },510 {511 "epoch": 0.31,512 "learning_rate": 1e-05,513 "loss": 1.217,514 "step": 830515 },516 {517 "epoch": 0.32,518 "learning_rate": 1e-05,519 "loss": 1.184,520 "step": 840521 },522 {523 "epoch": 0.32,524 "learning_rate": 1e-05,525 "loss": 1.1567,526 "step": 850527 },528 {529 "epoch": 0.32,530 "learning_rate": 1e-05,531 "loss": 1.1987,532 "step": 860533 },534 {535 "epoch": 0.33,536 "learning_rate": 1e-05,537 "loss": 1.2121,538 "step": 870539 },540 {541 "epoch": 0.33,542 "learning_rate": 1e-05,543 "loss": 1.191,544 "step": 880545 },546 {547 "epoch": 0.34,548 "learning_rate": 1e-05,549 "loss": 1.2109,550 "step": 890551 },552 {553 "epoch": 0.34,554 "learning_rate": 1e-05,555 "loss": 1.1724,556 "step": 900557 },558 {559 "epoch": 0.34,560 "learning_rate": 1e-05,561 "loss": 1.1727,562 "step": 910563 },564 {565 "epoch": 0.35,566 "learning_rate": 1e-05,567 "loss": 1.154,568 "step": 920569 },570 {571 "epoch": 0.35,572 "learning_rate": 1e-05,573 "loss": 1.168,574 "step": 930575 },576 {577 "epoch": 0.35,578 "learning_rate": 1e-05,579 "loss": 1.1514,580 "step": 940581 },582 {583 "epoch": 0.36,584 "learning_rate": 1e-05,585 "loss": 1.1677,586 "step": 950587 },588 {589 "epoch": 0.36,590 "learning_rate": 1e-05,591 "loss": 1.1848,592 "step": 960593 },594 {595 "epoch": 0.37,596 "learning_rate": 1e-05,597 "loss": 1.1555,598 "step": 970599 },600 {601 "epoch": 0.37,602 "learning_rate": 1e-05,603 "loss": 1.1451,604 "step": 980605 },606 {607 "epoch": 0.37,608 "learning_rate": 1e-05,609 "loss": 1.1323,610 "step": 990611 },612 {613 "epoch": 0.38,614 "learning_rate": 1e-05,615 "loss": 1.1172,616 "step": 1000617 },618 {619 "epoch": 0.38,620 "eval_loss": 1.17578125,621 "eval_runtime": 63.361,622 "eval_samples_per_second": 63.967,623 "eval_steps_per_second": 2.004,624 "step": 1000625 },626 {627 "epoch": 0.38,628 "learning_rate": 1e-05,629 "loss": 1.1784,630 "step": 1010631 },632 {633 "epoch": 0.39,634 "learning_rate": 1e-05,635 "loss": 1.1424,636 "step": 1020637 },638 {639 "epoch": 0.39,640 "learning_rate": 1e-05,641 "loss": 1.1858,642 "step": 1030643 },644 {645 "epoch": 0.39,646 "learning_rate": 1e-05,647 "loss": 1.1484,648 "step": 1040649 },650 {651 "epoch": 0.4,652 "learning_rate": 1e-05,653 "loss": 1.1682,654 "step": 1050655 },656 {657 "epoch": 0.4,658 "learning_rate": 1e-05,659 "loss": 1.1212,660 "step": 1060661 },662 {663 "epoch": 0.4,664 "learning_rate": 1e-05,665 "loss": 1.1324,666 "step": 1070667 },668 {669 "epoch": 0.41,670 "learning_rate": 1e-05,671 "loss": 1.1367,672 "step": 1080673 },674 {675 "epoch": 0.41,676 "learning_rate": 1e-05,677 "loss": 1.1443,678 "step": 1090679 },680 {681 "epoch": 0.42,682 "learning_rate": 1e-05,683 "loss": 1.1407,684 "step": 1100685 },686 {687 "epoch": 0.42,688 "learning_rate": 1e-05,689 "loss": 1.1193,690 "step": 1110691 },692 {693 "epoch": 0.42,694 "learning_rate": 1e-05,695 "loss": 1.1317,696 "step": 1120697 },698 {699 "epoch": 0.43,700 "learning_rate": 1e-05,701 "loss": 1.1556,702 "step": 1130703 },704 {705 "epoch": 0.43,706 "learning_rate": 1e-05,707 "loss": 1.1482,708 "step": 1140709 },710 {711 "epoch": 0.43,712 "learning_rate": 1e-05,713 "loss": 1.1255,714 "step": 1150715 },716 {717 "epoch": 0.44,718 "learning_rate": 1e-05,719 "loss": 1.1249,720 "step": 1160721 },722 {723 "epoch": 0.44,724 "learning_rate": 1e-05,725 "loss": 1.1379,726 "step": 1170727 },728 {729 "epoch": 0.45,730 "learning_rate": 1e-05,731 "loss": 1.1077,732 "step": 1180733 },734 {735 "epoch": 0.45,736 "learning_rate": 1e-05,737 "loss": 1.115,738 "step": 1190739 },740 {741 "epoch": 0.45,742 "learning_rate": 1e-05,743 "loss": 1.0913,744 "step": 1200745 },746 {747 "epoch": 0.46,748 "learning_rate": 1e-05,749 "loss": 1.0948,750 "step": 1210751 },752 {753 "epoch": 0.46,754 "learning_rate": 1e-05,755 "loss": 1.1593,756 "step": 1220757 },758 {759 "epoch": 0.46,760 "learning_rate": 1e-05,761 "loss": 1.1208,762 "step": 1230763 },764 {765 "epoch": 0.47,766 "learning_rate": 1e-05,767 "loss": 1.1261,768 "step": 1240769 },770 {771 "epoch": 0.47,772 "learning_rate": 1e-05,773 "loss": 1.0816,774 "step": 1250775 },776 {777 "epoch": 0.48,778 "learning_rate": 1e-05,779 "loss": 1.0907,780 "step": 1260781 },782 {783 "epoch": 0.48,784 "learning_rate": 1e-05,785 "loss": 1.0547,786 "step": 1270787 },788 {789 "epoch": 0.48,790 "learning_rate": 1e-05,791 "loss": 1.1173,792 "step": 1280793 },794 {795 "epoch": 0.49,796 "learning_rate": 1e-05,797 "loss": 1.1133,798 "step": 1290799 },800 {801 "epoch": 0.49,802 "learning_rate": 1e-05,803 "loss": 1.1072,804 "step": 1300805 },806 {807 "epoch": 0.49,808 "learning_rate": 1e-05,809 "loss": 1.0862,810 "step": 1310811 },812 {813 "epoch": 0.5,814 "learning_rate": 1e-05,815 "loss": 1.1178,816 "step": 1320817 },818 {819 "epoch": 0.5,820 "learning_rate": 1e-05,821 "loss": 1.099,822 "step": 1330823 },824 {825 "epoch": 0.51,826 "learning_rate": 1e-05,827 "loss": 1.0853,828 "step": 1340829 },830 {831 "epoch": 0.51,832 "learning_rate": 1e-05,833 "loss": 1.0652,834 "step": 1350835 },836 {837 "epoch": 0.51,838 "learning_rate": 1e-05,839 "loss": 1.0959,840 "step": 1360841 },842 {843 "epoch": 0.52,844 "learning_rate": 1e-05,845 "loss": 1.0585,846 "step": 1370847 },848 {849 "epoch": 0.52,850 "learning_rate": 1e-05,851 "loss": 1.0644,852 "step": 1380853 },854 {855 "epoch": 0.52,856 "learning_rate": 1e-05,857 "loss": 1.018,858 "step": 1390859 },860 {861 "epoch": 0.53,862 "learning_rate": 1e-05,863 "loss": 1.0694,864 "step": 1400865 },866 {867 "epoch": 0.53,868 "learning_rate": 1e-05,869 "loss": 1.0861,870 "step": 1410871 },872 {873 "epoch": 0.54,874 "learning_rate": 1e-05,875 "loss": 1.0846,876 "step": 1420877 },878 {879 "epoch": 0.54,880 "learning_rate": 1e-05,881 "loss": 1.1364,882 "step": 1430883 },884 {885 "epoch": 0.54,886 "learning_rate": 1e-05,887 "loss": 1.0504,888 "step": 1440889 },890 {891 "epoch": 0.55,892 "learning_rate": 1e-05,893 "loss": 1.0912,894 "step": 1450895 },896 {897 "epoch": 0.55,898 "learning_rate": 1e-05,899 "loss": 1.0495,900 "step": 1460901 },902 {903 "epoch": 0.55,904 "learning_rate": 1e-05,905 "loss": 1.0541,906 "step": 1470907 },908 {909 "epoch": 0.56,910 "learning_rate": 1e-05,911 "loss": 1.0622,912 "step": 1480913 },914 {915 "epoch": 0.56,916 "learning_rate": 1e-05,917 "loss": 1.0501,918 "step": 1490919 },920 {921 "epoch": 0.57,922 "learning_rate": 1e-05,923 "loss": 1.06,924 "step": 1500925 },926 {927 "epoch": 0.57,928 "eval_loss": 1.0966796875,929 "eval_runtime": 63.326,930 "eval_samples_per_second": 64.002,931 "eval_steps_per_second": 2.005,932 "step": 1500933 },934 {935 "epoch": 0.57,936 "learning_rate": 1e-05,937 "loss": 1.0511,938 "step": 1510939 },940 {941 "epoch": 0.57,942 "learning_rate": 1e-05,943 "loss": 1.025,944 "step": 1520945 },946 {947 "epoch": 0.58,948 "learning_rate": 1e-05,949 "loss": 1.0679,950 "step": 1530951 },952 {953 "epoch": 0.58,954 "learning_rate": 1e-05,955 "loss": 1.0676,956 "step": 1540957 },958 {959 "epoch": 0.59,960 "learning_rate": 1e-05,961 "loss": 1.0678,962 "step": 1550963 },964 {965 "epoch": 0.59,966 "learning_rate": 1e-05,967 "loss": 1.0666,968 "step": 1560969 },970 {971 "epoch": 0.59,972 "learning_rate": 1e-05,973 "loss": 1.1123,974 "step": 1570975 },976 {977 "epoch": 0.6,978 "learning_rate": 1e-05,979 "loss": 1.045,980 "step": 1580981 },982 {983 "epoch": 0.6,984 "learning_rate": 1e-05,985 "loss": 1.0311,986 "step": 1590987 },988 {989 "epoch": 0.6,990 "learning_rate": 1e-05,991 "loss": 1.0675,992 "step": 1600993 },994 {995 "epoch": 0.61,996 "learning_rate": 1e-05,997 "loss": 1.0417,998 "step": 1610999 },1000 {1001 "epoch": 0.61,1002 "learning_rate": 1e-05,1003 "loss": 1.0181,1004 "step": 16201005 },1006 {1007 "epoch": 0.62,1008 "learning_rate": 1e-05,1009 "loss": 1.0364,1010 "step": 16301011 },1012 {1013 "epoch": 0.62,1014 "learning_rate": 1e-05,1015 "loss": 1.023,1016 "step": 16401017 },1018 {1019 "epoch": 0.62,1020 "learning_rate": 1e-05,1021 "loss": 1.0502,1022 "step": 16501023 },1024 {1025 "epoch": 0.63,1026 "learning_rate": 1e-05,1027 "loss": 1.0789,1028 "step": 16601029 },1030 {1031 "epoch": 0.63,1032 "learning_rate": 1e-05,1033 "loss": 1.062,1034 "step": 16701035 },1036 {1037 "epoch": 0.63,1038 "learning_rate": 1e-05,1039 "loss": 1.0341,1040 "step": 16801041 },1042 {1043 "epoch": 0.64,1044 "learning_rate": 1e-05,1045 "loss": 1.0126,1046 "step": 16901047 },1048 {1049 "epoch": 0.64,1050 "learning_rate": 1e-05,1051 "loss": 1.0094,1052 "step": 17001053 },1054 {1055 "epoch": 0.65,1056 "learning_rate": 1e-05,1057 "loss": 1.0378,1058 "step": 17101059 },1060 {1061 "epoch": 0.65,1062 "learning_rate": 1e-05,1063 "loss": 1.0002,1064 "step": 17201065 },1066 {1067 "epoch": 0.65,1068 "learning_rate": 1e-05,1069 "loss": 1.0389,1070 "step": 17301071 },1072 {1073 "epoch": 0.66,1074 "learning_rate": 1e-05,1075 "loss": 1.0541,1076 "step": 17401077 },1078 {1079 "epoch": 0.66,1080 "learning_rate": 1e-05,1081 "loss": 1.0776,1082 "step": 17501083 },1084 {1085 "epoch": 0.66,1086 "learning_rate": 1e-05,1087 "loss": 1.0088,1088 "step": 17601089 },1090 {1091 "epoch": 0.67,1092 "learning_rate": 1e-05,1093 "loss": 1.0139,1094 "step": 17701095 },1096 {1097 "epoch": 0.67,1098 "learning_rate": 1e-05,1099 "loss": 0.9772,1100 "step": 17801101 },1102 {1103 "epoch": 0.68,1104 "learning_rate": 1e-05,1105 "loss": 1.0363,1106 "step": 17901107 },1108 {1109 "epoch": 0.68,1110 "learning_rate": 1e-05,1111 "loss": 1.0499,1112 "step": 18001113 },1114 {1115 "epoch": 0.68,1116 "learning_rate": 1e-05,1117 "loss": 1.0171,1118 "step": 18101119 },1120 {1121 "epoch": 0.69,1122 "learning_rate": 1e-05,1123 "loss": 1.0138,1124 "step": 18201125 },1126 {1127 "epoch": 0.69,1128 "learning_rate": 1e-05,1129 "loss": 0.973,1130 "step": 18301131 },1132 {1133 "epoch": 0.69,1134 "learning_rate": 1e-05,1135 "loss": 1.0022,1136 "step": 18401137 },1138 {1139 "epoch": 0.7,1140 "learning_rate": 1e-05,1141 "loss": 1.049,1142 "step": 18501143 },1144 {1145 "epoch": 0.7,1146 "learning_rate": 1e-05,1147 "loss": 1.0375,1148 "step": 18601149 },1150 {1151 "epoch": 0.71,1152 "learning_rate": 1e-05,1153 "loss": 1.0273,1154 "step": 18701155 },1156 {1157 "epoch": 0.71,1158 "learning_rate": 1e-05,1159 "loss": 1.0266,1160 "step": 18801161 },1162 {1163 "epoch": 0.71,1164 "learning_rate": 1e-05,1165 "loss": 0.9753,1166 "step": 18901167 },1168 {1169 "epoch": 0.72,1170 "learning_rate": 1e-05,1171 "loss": 1.032,1172 "step": 19001173 },1174 {1175 "epoch": 0.72,1176 "learning_rate": 1e-05,1177 "loss": 1.0195,1178 "step": 19101179 },1180 {1181 "epoch": 0.72,1182 "learning_rate": 1e-05,1183 "loss": 1.0094,1184 "step": 19201185 },1186 {1187 "epoch": 0.73,1188 "learning_rate": 1e-05,1189 "loss": 0.9572,1190 "step": 19301191 },1192 {1193 "epoch": 0.73,1194 "learning_rate": 1e-05,1195 "loss": 1.0336,1196 "step": 19401197 },1198 {1199 "epoch": 0.74,1200 "learning_rate": 1e-05,