AlignmentLab-AI/sentinelv2
222
1{2 "best_metric": null,3 "best_model_checkpoint": null,4 "epoch": 3.0253164556962027,5 "eval_steps": 20,6 "global_step": 243,7 "is_hyper_param_search": false,8 "is_local_process_zero": true,9 "is_world_process_zero": true,10 "log_history": [11 {12 "epoch": 0.01,13 "learning_rate": 0.0,14 "loss": 0.6625,15 "step": 116 },17 {18 "epoch": 0.01,19 "eval_loss": 0.9669284820556641,20 "eval_runtime": 22.2599,21 "eval_samples_per_second": 11.231,22 "eval_steps_per_second": 2.83,23 "step": 124 },25 {26 "epoch": 0.03,27 "learning_rate": 6.666666e-07,28 "loss": 0.7012,29 "step": 230 },31 {32 "epoch": 0.04,33 "learning_rate": 1.3333332e-06,34 "loss": 0.6954,35 "step": 336 },37 {38 "epoch": 0.05,39 "learning_rate": 1.9999997999999996e-06,40 "loss": 0.6383,41 "step": 442 },43 {44 "epoch": 0.06,45 "learning_rate": 2.6666664e-06,46 "loss": 0.6993,47 "step": 548 },49 {50 "epoch": 0.08,51 "learning_rate": 3.3333329999999998e-06,52 "loss": 0.6388,53 "step": 654 },55 {56 "epoch": 0.09,57 "learning_rate": 3.999999599999999e-06,58 "loss": 0.6847,59 "step": 760 },61 {62 "epoch": 0.1,63 "learning_rate": 4.6666662e-06,64 "loss": 0.6973,65 "step": 866 },67 {68 "epoch": 0.11,69 "learning_rate": 5.3333328e-06,70 "loss": 0.703,71 "step": 972 },73 {74 "epoch": 0.13,75 "learning_rate": 5.999999399999999e-06,76 "loss": 0.6826,77 "step": 1078 },79 {80 "epoch": 0.14,81 "learning_rate": 6.6666659999999995e-06,82 "loss": 0.6939,83 "step": 1184 },85 {86 "epoch": 0.15,87 "learning_rate": 7.333332599999999e-06,88 "loss": 0.6879,89 "step": 1290 },91 {92 "epoch": 0.16,93 "learning_rate": 7.999999199999998e-06,94 "loss": 0.687,95 "step": 1396 },97 {98 "epoch": 0.18,99 "learning_rate": 8.6666658e-06,100 "loss": 0.6471,101 "step": 14102 },103 {104 "epoch": 0.19,105 "learning_rate": 9.3333324e-06,106 "loss": 0.6658,107 "step": 15108 },109 {110 "epoch": 0.2,111 "learning_rate": 9.999998999999998e-06,112 "loss": 0.6669,113 "step": 16114 },115 {116 "epoch": 0.22,117 "learning_rate": 1.06666656e-05,118 "loss": 0.6451,119 "step": 17120 },121 {122 "epoch": 0.23,123 "learning_rate": 1.13333322e-05,124 "loss": 0.6558,125 "step": 18126 },127 {128 "epoch": 0.24,129 "learning_rate": 1.1999998799999998e-05,130 "loss": 0.6714,131 "step": 19132 },133 {134 "epoch": 0.25,135 "learning_rate": 1.26666654e-05,136 "loss": 0.7123,137 "step": 20138 },139 {140 "epoch": 0.25,141 "eval_loss": 0.9579811096191406,142 "eval_runtime": 22.7924,143 "eval_samples_per_second": 10.969,144 "eval_steps_per_second": 2.764,145 "step": 20146 },147 {148 "epoch": 0.27,149 "learning_rate": 1.3333331999999999e-05,150 "loss": 0.6388,151 "step": 21152 },153 {154 "epoch": 0.28,155 "learning_rate": 1.3999998599999999e-05,156 "loss": 0.6355,157 "step": 22158 },159 {160 "epoch": 0.29,161 "learning_rate": 1.4666665199999999e-05,162 "loss": 0.6237,163 "step": 23164 },165 {166 "epoch": 0.3,167 "learning_rate": 1.53333318e-05,168 "loss": 0.6214,169 "step": 24170 },171 {172 "epoch": 0.32,173 "learning_rate": 1.5999998399999997e-05,174 "loss": 0.6045,175 "step": 25176 },177 {178 "epoch": 0.33,179 "learning_rate": 1.6666665e-05,180 "loss": 0.671,181 "step": 26182 },183 {184 "epoch": 0.34,185 "learning_rate": 1.73333316e-05,186 "loss": 0.6042,187 "step": 27188 },189 {190 "epoch": 0.35,191 "learning_rate": 1.7999998199999998e-05,192 "loss": 0.6722,193 "step": 28194 },195 {196 "epoch": 0.37,197 "learning_rate": 1.86666648e-05,198 "loss": 0.6132,199 "step": 29200 },201 {202 "epoch": 0.38,203 "learning_rate": 1.9333331399999998e-05,204 "loss": 0.5651,205 "step": 30206 },207 {208 "epoch": 0.39,209 "learning_rate": 1.9999997999999996e-05,210 "loss": 0.6525,211 "step": 31212 },213 {214 "epoch": 0.41,215 "learning_rate": 2.0666664599999998e-05,216 "loss": 0.6532,217 "step": 32218 },219 {220 "epoch": 0.42,221 "learning_rate": 2.13333312e-05,222 "loss": 0.6167,223 "step": 33224 },225 {226 "epoch": 0.43,227 "learning_rate": 2.1999997799999997e-05,228 "loss": 0.607,229 "step": 34230 },231 {232 "epoch": 0.44,233 "learning_rate": 2.26666644e-05,234 "loss": 0.5843,235 "step": 35236 },237 {238 "epoch": 0.46,239 "learning_rate": 2.3333330999999997e-05,240 "loss": 0.6093,241 "step": 36242 },243 {244 "epoch": 0.47,245 "learning_rate": 2.3999997599999995e-05,246 "loss": 0.5967,247 "step": 37248 },249 {250 "epoch": 0.48,251 "learning_rate": 2.4666664199999997e-05,252 "loss": 0.6015,253 "step": 38254 },255 {256 "epoch": 0.49,257 "learning_rate": 2.53333308e-05,258 "loss": 0.6263,259 "step": 39260 },261 {262 "epoch": 0.51,263 "learning_rate": 2.59999974e-05,264 "loss": 0.5923,265 "step": 40266 },267 {268 "epoch": 0.51,269 "eval_loss": 0.9467829465866089,270 "eval_runtime": 22.6276,271 "eval_samples_per_second": 11.048,272 "eval_steps_per_second": 2.784,273 "step": 40274 },275 {276 "epoch": 0.52,277 "learning_rate": 2.6666663999999998e-05,278 "loss": 0.5801,279 "step": 41280 },281 {282 "epoch": 0.53,283 "learning_rate": 2.7333330599999996e-05,284 "loss": 0.576,285 "step": 42286 },287 {288 "epoch": 0.54,289 "learning_rate": 2.7999997199999998e-05,290 "loss": 0.6317,291 "step": 43292 },293 {294 "epoch": 0.56,295 "learning_rate": 2.8666663799999996e-05,296 "loss": 0.5874,297 "step": 44298 },299 {300 "epoch": 0.57,301 "learning_rate": 2.9333330399999998e-05,302 "loss": 0.6109,303 "step": 45304 },305 {306 "epoch": 0.58,307 "learning_rate": 2.9999997e-05,308 "loss": 0.5274,309 "step": 46310 },311 {312 "epoch": 0.59,313 "learning_rate": 3.06666636e-05,314 "loss": 0.5698,315 "step": 47316 },317 {318 "epoch": 0.61,319 "learning_rate": 3.133333019999999e-05,320 "loss": 0.544,321 "step": 48322 },323 {324 "epoch": 0.62,325 "learning_rate": 3.1999996799999994e-05,326 "loss": 0.5586,327 "step": 49328 },329 {330 "epoch": 0.63,331 "learning_rate": 3.2666663399999995e-05,332 "loss": 0.5666,333 "step": 50334 },335 {336 "epoch": 0.65,337 "learning_rate": 3.333333e-05,338 "loss": 0.586,339 "step": 51340 },341 {342 "epoch": 0.66,343 "learning_rate": 3.39999966e-05,344 "loss": 0.6225,345 "step": 52346 },347 {348 "epoch": 0.67,349 "learning_rate": 3.46666632e-05,350 "loss": 0.5588,351 "step": 53352 },353 {354 "epoch": 0.68,355 "learning_rate": 3.53333298e-05,356 "loss": 0.5705,357 "step": 54358 },359 {360 "epoch": 0.7,361 "learning_rate": 3.5999996399999996e-05,362 "loss": 0.5628,363 "step": 55364 },365 {366 "epoch": 0.71,367 "learning_rate": 3.6666663e-05,368 "loss": 0.5868,369 "step": 56370 },371 {372 "epoch": 0.72,373 "learning_rate": 3.73333296e-05,374 "loss": 0.5583,375 "step": 57376 },377 {378 "epoch": 0.73,379 "learning_rate": 3.7999996199999994e-05,380 "loss": 0.5858,381 "step": 58382 },383 {384 "epoch": 0.75,385 "learning_rate": 3.8666662799999996e-05,386 "loss": 0.5756,387 "step": 59388 },389 {390 "epoch": 0.76,391 "learning_rate": 3.93333294e-05,392 "loss": 0.5822,393 "step": 60394 },395 {396 "epoch": 0.76,397 "eval_loss": 0.9389348030090332,398 "eval_runtime": 22.5892,399 "eval_samples_per_second": 11.067,400 "eval_steps_per_second": 2.789,401 "step": 60402 },403 {404 "epoch": 0.77,405 "learning_rate": 3.999999599999999e-05,406 "loss": 0.5667,407 "step": 61408 },409 {410 "epoch": 0.78,411 "learning_rate": 4.0666662599999994e-05,412 "loss": 0.5616,413 "step": 62414 },415 {416 "epoch": 0.8,417 "learning_rate": 4.1333329199999995e-05,418 "loss": 0.5678,419 "step": 63420 },421 {422 "epoch": 0.81,423 "learning_rate": 4.19999958e-05,424 "loss": 0.5514,425 "step": 64426 },427 {428 "epoch": 0.82,429 "learning_rate": 4.26666624e-05,430 "loss": 0.5732,431 "step": 65432 },433 {434 "epoch": 0.84,435 "learning_rate": 4.3333329e-05,436 "loss": 0.5794,437 "step": 66438 },439 {440 "epoch": 0.85,441 "learning_rate": 4.3999995599999995e-05,442 "loss": 0.5582,443 "step": 67444 },445 {446 "epoch": 0.86,447 "learning_rate": 4.4666662199999996e-05,448 "loss": 0.5575,449 "step": 68450 },451 {452 "epoch": 0.87,453 "learning_rate": 4.53333288e-05,454 "loss": 0.5558,455 "step": 69456 },457 {458 "epoch": 0.89,459 "learning_rate": 4.599999539999999e-05,460 "loss": 0.5707,461 "step": 70462 },463 {464 "epoch": 0.9,465 "learning_rate": 4.6666661999999994e-05,466 "loss": 0.54,467 "step": 71468 },469 {470 "epoch": 0.91,471 "learning_rate": 4.7333328599999996e-05,472 "loss": 0.5435,473 "step": 72474 },475 {476 "epoch": 0.92,477 "learning_rate": 4.799999519999999e-05,478 "loss": 0.5649,479 "step": 73480 },481 {482 "epoch": 0.94,483 "learning_rate": 4.866666179999999e-05,484 "loss": 0.5617,485 "step": 74486 },487 {488 "epoch": 0.95,489 "learning_rate": 4.9333328399999994e-05,490 "loss": 0.5651,491 "step": 75492 },493 {494 "epoch": 0.96,495 "learning_rate": 4.9999994999999995e-05,496 "loss": 0.5113,497 "step": 76498 },499 {500 "epoch": 0.97,501 "learning_rate": 5.06666616e-05,502 "loss": 0.5389,503 "step": 77504 },505 {506 "epoch": 0.99,507 "learning_rate": 5.13333282e-05,508 "loss": 0.5162,509 "step": 78510 },511 {512 "epoch": 1.0,513 "learning_rate": 5.19999948e-05,514 "loss": 0.5397,515 "step": 79516 },517 {518 "epoch": 1.01,519 "learning_rate": 5.2666661399999995e-05,520 "loss": 0.5794,521 "step": 80522 },523 {524 "epoch": 1.01,525 "eval_loss": 0.9314417839050293,526 "eval_runtime": 22.7753,527 "eval_samples_per_second": 10.977,528 "eval_steps_per_second": 2.766,529 "step": 80530 },531 {532 "epoch": 1.03,533 "learning_rate": 5.3333327999999996e-05,534 "loss": 0.5263,535 "step": 81536 },537 {538 "epoch": 1.01,539 "learning_rate": 5.39999946e-05,540 "loss": 0.5141,541 "step": 82542 },543 {544 "epoch": 1.03,545 "learning_rate": 5.466666119999999e-05,546 "loss": 0.5573,547 "step": 83548 },549 {550 "epoch": 1.04,551 "learning_rate": 5.5333327799999994e-05,552 "loss": 0.5629,553 "step": 84554 },555 {556 "epoch": 1.05,557 "learning_rate": 5.5999994399999996e-05,558 "loss": 0.5043,559 "step": 85560 },561 {562 "epoch": 1.06,563 "learning_rate": 5.666666099999999e-05,564 "loss": 0.562,565 "step": 86566 },567 {568 "epoch": 1.08,569 "learning_rate": 5.733332759999999e-05,570 "loss": 0.4978,571 "step": 87572 },573 {574 "epoch": 1.09,575 "learning_rate": 5.7999994199999994e-05,576 "loss": 0.5502,577 "step": 88578 },579 {580 "epoch": 1.1,581 "learning_rate": 5.8666660799999995e-05,582 "loss": 0.5499,583 "step": 89584 },585 {586 "epoch": 1.11,587 "learning_rate": 5.93333274e-05,588 "loss": 0.5547,589 "step": 90590 },591 {592 "epoch": 1.13,593 "learning_rate": 5.9999994e-05,594 "loss": 0.5452,595 "step": 91596 },597 {598 "epoch": 1.14,599 "learning_rate": 6.066666059999999e-05,600 "loss": 0.5544,601 "step": 92602 },603 {604 "epoch": 1.15,605 "learning_rate": 6.13333272e-05,606 "loss": 0.5483,607 "step": 93608 },609 {610 "epoch": 1.16,611 "learning_rate": 6.19999938e-05,612 "loss": 0.5641,613 "step": 94614 },615 {616 "epoch": 1.18,617 "learning_rate": 6.266666039999998e-05,618 "loss": 0.5316,619 "step": 95620 },621 {622 "epoch": 1.19,623 "learning_rate": 6.333332699999999e-05,624 "loss": 0.526,625 "step": 96626 },627 {628 "epoch": 1.2,629 "learning_rate": 6.399999359999999e-05,630 "loss": 0.5443,631 "step": 97632 },633 {634 "epoch": 1.22,635 "learning_rate": 6.46666602e-05,636 "loss": 0.5111,637 "step": 98638 },639 {640 "epoch": 1.23,641 "learning_rate": 6.533332679999999e-05,642 "loss": 0.5298,643 "step": 99644 },645 {646 "epoch": 1.24,647 "learning_rate": 6.59999934e-05,648 "loss": 0.5431,649 "step": 100650 },651 {652 "epoch": 1.24,653 "eval_loss": 0.9199196100234985,654 "eval_runtime": 22.8496,655 "eval_samples_per_second": 10.941,656 "eval_steps_per_second": 2.757,657 "step": 100658 },659 {660 "epoch": 1.25,661 "learning_rate": 6.666666e-05,662 "loss": 0.585,663 "step": 101664 },665 {666 "epoch": 1.27,667 "learning_rate": 6.64406713220339e-05,668 "loss": 0.5143,669 "step": 102670 },671 {672 "epoch": 1.28,673 "learning_rate": 6.621468264406779e-05,674 "loss": 0.5061,675 "step": 103676 },677 {678 "epoch": 1.29,679 "learning_rate": 6.59886939661017e-05,680 "loss": 0.5098,681 "step": 104682 },683 {684 "epoch": 1.3,685 "learning_rate": 6.576270528813559e-05,686 "loss": 0.5188,687 "step": 105688 },689 {690 "epoch": 1.32,691 "learning_rate": 6.553671661016948e-05,692 "loss": 0.5005,693 "step": 106694 },695 {696 "epoch": 1.33,697 "learning_rate": 6.531072793220339e-05,698 "loss": 0.5709,699 "step": 107700 },701 {702 "epoch": 1.34,703 "learning_rate": 6.508473925423728e-05,704 "loss": 0.4985,705 "step": 108706 },707 {708 "epoch": 1.35,709 "learning_rate": 6.485875057627117e-05,710 "loss": 0.5767,711 "step": 109712 },713 {714 "epoch": 1.37,715 "learning_rate": 6.463276189830508e-05,716 "loss": 0.517,717 "step": 110718 },719 {720 "epoch": 1.38,721 "learning_rate": 6.440677322033897e-05,722 "loss": 0.4759,723 "step": 111724 },725 {726 "epoch": 1.39,727 "learning_rate": 6.418078454237288e-05,728 "loss": 0.5536,729 "step": 112730 },731 {732 "epoch": 1.41,733 "learning_rate": 6.395479586440677e-05,734 "loss": 0.5657,735 "step": 113736 },737 {738 "epoch": 1.42,739 "learning_rate": 6.372880718644068e-05,740 "loss": 0.525,741 "step": 114742 },743 {744 "epoch": 1.43,745 "learning_rate": 6.350281850847457e-05,746 "loss": 0.5113,747 "step": 115748 },749 {750 "epoch": 1.44,751 "learning_rate": 6.327682983050848e-05,752 "loss": 0.4869,753 "step": 116754 },755 {756 "epoch": 1.46,757 "learning_rate": 6.305084115254237e-05,758 "loss": 0.5074,759 "step": 117760 },761 {762 "epoch": 1.47,763 "learning_rate": 6.282485247457626e-05,764 "loss": 0.5043,765 "step": 118766 },767 {768 "epoch": 1.48,769 "learning_rate": 6.259886379661017e-05,770 "loss": 0.5116,771 "step": 119772 },773 {774 "epoch": 1.49,775 "learning_rate": 6.237287511864406e-05,776 "loss": 0.5317,777 "step": 120778 },779 {780 "epoch": 1.49,781 "eval_loss": 0.9122854471206665,782 "eval_runtime": 22.8969,783 "eval_samples_per_second": 10.919,784 "eval_steps_per_second": 2.751,785 "step": 120786 },787 {788 "epoch": 1.51,789 "learning_rate": 6.214688644067795e-05,790 "loss": 0.5049,791 "step": 121792 },793 {794 "epoch": 1.52,795 "learning_rate": 6.192089776271186e-05,796 "loss": 0.496,797 "step": 122798 },799 {800 "epoch": 1.53,801 "learning_rate": 6.169490908474575e-05,802 "loss": 0.4951,803 "step": 123804 },805 {806 "epoch": 1.54,807 "learning_rate": 6.146892040677966e-05,808 "loss": 0.5489,809 "step": 124810 },811 {812 "epoch": 1.56,813 "learning_rate": 6.124293172881355e-05,814 "loss": 0.5071,815 "step": 125816 },817 {818 "epoch": 1.57,819 "learning_rate": 6.1016943050847455e-05,820 "loss": 0.5312,821 "step": 126822 },823 {824 "epoch": 1.58,825 "learning_rate": 6.079095437288135e-05,826 "loss": 0.4442,827 "step": 127828 },829 {830 "epoch": 1.59,831 "learning_rate": 6.056496569491525e-05,832 "loss": 0.4944,833 "step": 128834 },835 {836 "epoch": 1.61,837 "learning_rate": 6.033897701694915e-05,838 "loss": 0.4615,839 "step": 129840 },841 {842 "epoch": 1.62,843 "learning_rate": 6.0112988338983045e-05,844 "loss": 0.4855,845 "step": 130846 },847 {848 "epoch": 1.63,849 "learning_rate": 5.9886999661016945e-05,850 "loss": 0.4862,851 "step": 131852 },853 {854 "epoch": 1.65,855 "learning_rate": 5.9661010983050844e-05,856 "loss": 0.521,857 "step": 132858 },859 {860 "epoch": 1.66,861 "learning_rate": 5.943502230508474e-05,862 "loss": 0.5537,863 "step": 133864 },865 {866 "epoch": 1.67,867 "learning_rate": 5.9209033627118636e-05,868 "loss": 0.4828,869 "step": 134870 },871 {872 "epoch": 1.68,873 "learning_rate": 5.898304494915254e-05,874 "loss": 0.4932,875 "step": 135876 },877 {878 "epoch": 1.7,879 "learning_rate": 5.8757056271186434e-05,880 "loss": 0.4909,881 "step": 136882 },883 {884 "epoch": 1.71,885 "learning_rate": 5.8531067593220333e-05,886 "loss": 0.5211,887 "step": 137888 },889 {890 "epoch": 1.72,891 "learning_rate": 5.830507891525423e-05,892 "loss": 0.4851,893 "step": 138894 },895 {896 "epoch": 1.73,897 "learning_rate": 5.807909023728813e-05,898 "loss": 0.5172,899 "step": 139900 },901 {902 "epoch": 1.75,903 "learning_rate": 5.7853101559322024e-05,904 "loss": 0.5038,905 "step": 140906 },907 {908 "epoch": 1.75,909 "eval_loss": 0.9127333760261536,910 "eval_runtime": 22.9168,911 "eval_samples_per_second": 10.909,912 "eval_steps_per_second": 2.749,913 "step": 140914 },915 {916 "epoch": 1.76,917 "learning_rate": 5.762711288135593e-05,918 "loss": 0.5116,919 "step": 141920 },921 {922 "epoch": 1.77,923 "learning_rate": 5.740112420338982e-05,924 "loss": 0.5009,925 "step": 142926 },927 {928 "epoch": 1.78,929 "learning_rate": 5.717513552542372e-05,930 "loss": 0.4835,931 "step": 143932 },933 {934 "epoch": 1.8,935 "learning_rate": 5.694914684745762e-05,936 "loss": 0.4917,937 "step": 144938 },939 {940 "epoch": 1.81,941 "learning_rate": 5.672315816949152e-05,942 "loss": 0.4873,943 "step": 145944 },945 {946 "epoch": 1.82,947 "learning_rate": 5.649716949152541e-05,948 "loss": 0.5094,949 "step": 146950 },951 {952 "epoch": 1.84,953 "learning_rate": 5.627118081355932e-05,954 "loss": 0.5193,955 "step": 147956 },957 {958 "epoch": 1.85,959 "learning_rate": 5.604519213559321e-05,960 "loss": 0.4921,961 "step": 148962 },963 {964 "epoch": 1.86,965 "learning_rate": 5.581920345762711e-05,966 "loss": 0.4978,967 "step": 149968 },969 {970 "epoch": 1.87,971 "learning_rate": 5.559321477966101e-05,972 "loss": 0.4901,973 "step": 150974 },975 {976 "epoch": 1.89,977 "learning_rate": 5.536722610169491e-05,978 "loss": 0.5042,979 "step": 151980 },981 {982 "epoch": 1.9,983 "learning_rate": 5.51412374237288e-05,984 "loss": 0.4838,985 "step": 152986 },987 {988 "epoch": 1.91,989 "learning_rate": 5.491524874576271e-05,990 "loss": 0.485,991 "step": 153992 },993 {994 "epoch": 1.92,995 "learning_rate": 5.46892600677966e-05,996 "loss": 0.4967,997 "step": 154998 },999 {1000 "epoch": 1.94,1001 "learning_rate": 5.44632713898305e-05,1002 "loss": 0.4943,1003 "step": 1551004 },1005 {1006 "epoch": 1.95,1007 "learning_rate": 5.4237282711864406e-05,1008 "loss": 0.4999,1009 "step": 1561010 },1011 {1012 "epoch": 1.96,1013 "learning_rate": 5.40112940338983e-05,1014 "loss": 0.4456,1015 "step": 1571016 },1017 {1018 "epoch": 1.97,1019 "learning_rate": 5.3785305355932205e-05,1020 "loss": 0.4787,1021 "step": 1581022 },1023 {1024 "epoch": 1.99,1025 "learning_rate": 5.35593166779661e-05,1026 "loss": 0.4594,1027 "step": 1591028 },1029 {1030 "epoch": 2.0,1031 "learning_rate": 5.3333327999999996e-05,1032 "loss": 0.4744,1033 "step": 1601034 },1035 {1036 "epoch": 2.0,1037 "eval_loss": 0.9105737805366516,1038 "eval_runtime": 22.9129,1039 "eval_samples_per_second": 10.911,1040 "eval_steps_per_second": 2.75,1041 "step": 1601042 },1043 {1044 "epoch": 2.01,1045 "learning_rate": 5.3107339322033896e-05,1046 "loss": 0.5174,1047 "step": 1611048 },1049 {1050 "epoch": 2.03,1051 "learning_rate": 5.2881350644067795e-05,1052 "loss": 0.46,1053 "step": 1621054 },1055 {1056 "epoch": 2.01,1057 "learning_rate": 5.265536196610169e-05,1058 "loss": 0.4549,1059 "step": 1631060 },1061 {1062 "epoch": 2.03,1063 "learning_rate": 5.242937328813559e-05,1064 "loss": 0.4873,1065 "step": 1641066 },1067 {1068 "epoch": 2.04,1069 "learning_rate": 5.2203384610169486e-05,1070 "loss": 0.4969,1071 "step": 1651072 },1073 {1074 "epoch": 2.05,1075 "learning_rate": 5.1977395932203385e-05,1076 "loss": 0.4467,1077 "step": 1661078 },1079 {1080 "epoch": 2.06,1081 "learning_rate": 5.1751407254237284e-05,1082 "loss": 0.5028,1083 "step": 1671084 },1085 {1086 "epoch": 2.08,1087 "learning_rate": 5.1525418576271184e-05,1088 "loss": 0.4369,1089 "step": 1681090 },1091 {1092 "epoch": 2.09,1093 "learning_rate": 5.1299429898305076e-05,1094 "loss": 0.494,1095 "step": 1691096 },1097 {1098 "epoch": 2.1,1099 "learning_rate": 5.107344122033898e-05,1100 "loss": 0.4871,1101 "step": 1701102 },1103 {1104 "epoch": 2.11,1105 "learning_rate": 5.0847452542372875e-05,1106 "loss": 0.4981,1107 "step": 1711108 },1109 {1110 "epoch": 2.13,1111 "learning_rate": 5.0621463864406774e-05,1112 "loss": 0.4813,1113 "step": 1721114 },1115 {1116 "epoch": 2.14,1117 "learning_rate": 5.039547518644067e-05,1118 "loss": 0.4956,1119 "step": 1731120 },1121 {1122 "epoch": 2.15,1123 "learning_rate": 5.016948650847457e-05,1124 "loss": 0.4892,1125 "step": 1741126 },1127 {1128 "epoch": 2.16,1129 "learning_rate": 4.9943497830508465e-05,1130 "loss": 0.509,1131 "step": 1751132 },1133 {1134 "epoch": 2.18,1135 "learning_rate": 4.971750915254237e-05,1136 "loss": 0.4824,1137 "step": 1761138 },1139 {1140 "epoch": 2.19,1141 "learning_rate": 4.9491520474576264e-05,1142 "loss": 0.4673,1143 "step": 1771144 },1145 {1146 "epoch": 2.2,1147 "learning_rate": 4.926553179661016e-05,1148 "loss": 0.4846,1149 "step": 1781150 },1151 {1152 "epoch": 2.22,1153 "learning_rate": 4.903954311864406e-05,1154 "loss": 0.4539,1155 "step": 1791156 },1157 {1158 "epoch": 2.23,1159 "learning_rate": 4.881355444067796e-05,1160 "loss": 0.4754,1161 "step": 1801162 },1163 {1164 "epoch": 2.23,1165 "eval_loss": 0.9124670028686523,1166 "eval_runtime": 22.9259,1167 "eval_samples_per_second": 10.905,1168 "eval_steps_per_second": 2.748,1169 "step": 1801170 },1171 {1172 "epoch": 2.24,1173 "learning_rate": 4.8587565762711854e-05,1174 "loss": 0.4843,1175 "step": 1811176 },1177 {1178 "epoch": 2.25,1179 "learning_rate": 4.836157708474576e-05,1180 "loss": 0.5252,1181 "step": 1821182 },1183 {1184 "epoch": 2.27,1185 "learning_rate": 4.813558840677966e-05,1186 "loss": 0.4538,1187 "step": 1831188 },1189 {1190 "epoch": 2.28,1191 "learning_rate": 4.790959972881355e-05,1192 "loss": 0.4474,1193 "step": 1841194 },1195 {1196 "epoch": 2.29,1197 "learning_rate": 4.768361105084746e-05,1198 "loss": 0.4524,1199 "step": 1851200 },