tuanio/binary-bert-for-sequence-classification
115
1{2 "best_metric": null,3 "best_model_checkpoint": null,4 "epoch": 5.0,5 "eval_steps": 2500,6 "global_step": 33755,7 "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": 2.902843601895735e-07,14 "loss": 9.1546,15 "step": 5016 },17 {18 "epoch": 0.01,19 "learning_rate": 5.80568720379147e-07,20 "loss": 9.1497,21 "step": 10022 },23 {24 "epoch": 0.02,25 "learning_rate": 8.767772511848342e-07,26 "loss": 9.065,27 "step": 15028 },29 {30 "epoch": 0.03,31 "learning_rate": 1.1729857819905214e-06,32 "loss": 8.9258,33 "step": 20034 },35 {36 "epoch": 0.04,37 "learning_rate": 1.4632701421800948e-06,38 "loss": 8.8689,39 "step": 25040 },41 {42 "epoch": 0.04,43 "learning_rate": 1.7594786729857822e-06,44 "loss": 8.4535,45 "step": 30046 },47 {48 "epoch": 0.05,49 "learning_rate": 2.055687203791469e-06,50 "loss": 7.775,51 "step": 35052 },53 {54 "epoch": 0.06,55 "learning_rate": 2.3518957345971564e-06,56 "loss": 7.0715,57 "step": 40058 },59 {60 "epoch": 0.07,61 "learning_rate": 2.648104265402844e-06,62 "loss": 6.3666,63 "step": 45064 },65 {66 "epoch": 0.07,67 "learning_rate": 2.944312796208531e-06,68 "loss": 5.8049,69 "step": 50070 },71 {72 "epoch": 0.08,73 "learning_rate": 3.2405213270142184e-06,74 "loss": 5.1548,75 "step": 55076 },77 {78 "epoch": 0.09,79 "learning_rate": 3.5367298578199056e-06,80 "loss": 4.8392,81 "step": 60082 },83 {84 "epoch": 0.1,85 "learning_rate": 3.832938388625592e-06,86 "loss": 4.3625,87 "step": 65088 },89 {90 "epoch": 0.1,91 "learning_rate": 4.12914691943128e-06,92 "loss": 4.0536,93 "step": 70094 },95 {96 "epoch": 0.11,97 "learning_rate": 4.425355450236968e-06,98 "loss": 3.8893,99 "step": 750100 },101 {102 "epoch": 0.12,103 "learning_rate": 4.721563981042654e-06,104 "loss": 3.673,105 "step": 800106 },107 {108 "epoch": 0.13,109 "learning_rate": 5.017772511848341e-06,110 "loss": 3.5412,111 "step": 850112 },113 {114 "epoch": 0.13,115 "learning_rate": 5.313981042654029e-06,116 "loss": 3.3889,117 "step": 900118 },119 {120 "epoch": 0.14,121 "learning_rate": 5.6101895734597155e-06,122 "loss": 3.2857,123 "step": 950124 },125 {126 "epoch": 0.15,127 "learning_rate": 5.906398104265403e-06,128 "loss": 3.257,129 "step": 1000130 },131 {132 "epoch": 0.16,133 "learning_rate": 6.20260663507109e-06,134 "loss": 3.1638,135 "step": 1050136 },137 {138 "epoch": 0.16,139 "learning_rate": 6.4988151658767776e-06,140 "loss": 3.123,141 "step": 1100142 },143 {144 "epoch": 0.17,145 "learning_rate": 6.795023696682464e-06,146 "loss": 3.0633,147 "step": 1150148 },149 {150 "epoch": 0.18,151 "learning_rate": 7.091232227488152e-06,152 "loss": 3.0384,153 "step": 1200154 },155 {156 "epoch": 0.19,157 "learning_rate": 7.387440758293839e-06,158 "loss": 3.0122,159 "step": 1250160 },161 {162 "epoch": 0.19,163 "learning_rate": 7.683649289099525e-06,164 "loss": 2.9837,165 "step": 1300166 },167 {168 "epoch": 0.2,169 "learning_rate": 7.979857819905213e-06,170 "loss": 2.9659,171 "step": 1350172 },173 {174 "epoch": 0.21,175 "learning_rate": 8.2760663507109e-06,176 "loss": 2.9442,177 "step": 1400178 },179 {180 "epoch": 0.21,181 "learning_rate": 8.572274881516588e-06,182 "loss": 2.9377,183 "step": 1450184 },185 {186 "epoch": 0.22,187 "learning_rate": 8.868483412322276e-06,188 "loss": 2.9212,189 "step": 1500190 },191 {192 "epoch": 0.23,193 "learning_rate": 9.164691943127962e-06,194 "loss": 2.9104,195 "step": 1550196 },197 {198 "epoch": 0.24,199 "learning_rate": 9.46090047393365e-06,200 "loss": 2.9005,201 "step": 1600202 },203 {204 "epoch": 0.24,205 "learning_rate": 9.757109004739337e-06,206 "loss": 2.8978,207 "step": 1650208 },209 {210 "epoch": 0.25,211 "learning_rate": 1.0053317535545025e-05,212 "loss": 2.8991,213 "step": 1700214 },215 {216 "epoch": 0.26,217 "learning_rate": 1.0349526066350712e-05,218 "loss": 2.8838,219 "step": 1750220 },221 {222 "epoch": 0.27,223 "learning_rate": 1.0645734597156398e-05,224 "loss": 2.8798,225 "step": 1800226 },227 {228 "epoch": 0.27,229 "learning_rate": 1.0941943127962088e-05,230 "loss": 2.8755,231 "step": 1850232 },233 {234 "epoch": 0.28,235 "learning_rate": 1.1238151658767774e-05,236 "loss": 2.8707,237 "step": 1900238 },239 {240 "epoch": 0.29,241 "learning_rate": 1.1534360189573461e-05,242 "loss": 2.8754,243 "step": 1950244 },245 {246 "epoch": 0.3,247 "learning_rate": 1.1830568720379147e-05,248 "loss": 2.8679,249 "step": 2000250 },251 {252 "epoch": 0.3,253 "learning_rate": 1.2126777251184836e-05,254 "loss": 2.8694,255 "step": 2050256 },257 {258 "epoch": 0.31,259 "learning_rate": 1.2422985781990522e-05,260 "loss": 2.8627,261 "step": 2100262 },263 {264 "epoch": 0.32,265 "learning_rate": 1.271919431279621e-05,266 "loss": 2.8631,267 "step": 2150268 },269 {270 "epoch": 0.33,271 "learning_rate": 1.3015402843601896e-05,272 "loss": 2.8616,273 "step": 2200274 },275 {276 "epoch": 0.33,277 "learning_rate": 1.3311611374407585e-05,278 "loss": 2.8606,279 "step": 2250280 },281 {282 "epoch": 0.34,283 "learning_rate": 1.3607819905213271e-05,284 "loss": 2.8607,285 "step": 2300286 },287 {288 "epoch": 0.35,289 "learning_rate": 1.3904028436018959e-05,290 "loss": 2.8573,291 "step": 2350292 },293 {294 "epoch": 0.36,295 "learning_rate": 1.4200236966824645e-05,296 "loss": 2.8597,297 "step": 2400298 },299 {300 "epoch": 0.36,301 "learning_rate": 1.4496445497630334e-05,302 "loss": 2.8555,303 "step": 2450304 },305 {306 "epoch": 0.37,307 "learning_rate": 1.479265402843602e-05,308 "loss": 2.8545,309 "step": 2500310 },311 {312 "epoch": 0.37,313 "eval_loss": 2.887249708175659,314 "eval_runtime": 348.4295,315 "eval_samples_per_second": 15.954,316 "eval_steps_per_second": 1.995,317 "eval_wer": 1.0,318 "step": 2500319 },320 {321 "epoch": 0.38,322 "learning_rate": 1.5088862559241708e-05,323 "loss": 2.8542,324 "step": 2550325 },326 {327 "epoch": 0.39,328 "learning_rate": 1.5385071090047395e-05,329 "loss": 2.8544,330 "step": 2600331 },332 {333 "epoch": 0.39,334 "learning_rate": 1.568127962085308e-05,335 "loss": 2.8561,336 "step": 2650337 },338 {339 "epoch": 0.4,340 "learning_rate": 1.597748815165877e-05,341 "loss": 2.8503,342 "step": 2700343 },344 {345 "epoch": 0.41,346 "learning_rate": 1.6273696682464456e-05,347 "loss": 2.853,348 "step": 2750349 },350 {351 "epoch": 0.41,352 "learning_rate": 1.6569905213270142e-05,353 "loss": 2.8523,354 "step": 2800355 },356 {357 "epoch": 0.42,358 "learning_rate": 1.686611374407583e-05,359 "loss": 2.8522,360 "step": 2850361 },362 {363 "epoch": 0.43,364 "learning_rate": 1.7162322274881517e-05,365 "loss": 2.8529,366 "step": 2900367 },368 {369 "epoch": 0.44,370 "learning_rate": 1.7458530805687207e-05,371 "loss": 2.8445,372 "step": 2950373 },374 {375 "epoch": 0.44,376 "learning_rate": 1.7754739336492893e-05,377 "loss": 2.8419,378 "step": 3000379 },380 {381 "epoch": 0.45,382 "learning_rate": 1.8050947867298582e-05,383 "loss": 2.8349,384 "step": 3050385 },386 {387 "epoch": 0.46,388 "learning_rate": 1.8347156398104268e-05,389 "loss": 2.8246,390 "step": 3100391 },392 {393 "epoch": 0.47,394 "learning_rate": 1.8643364928909954e-05,395 "loss": 2.7982,396 "step": 3150397 },398 {399 "epoch": 0.47,400 "learning_rate": 1.893957345971564e-05,401 "loss": 2.7596,402 "step": 3200403 },404 {405 "epoch": 0.48,406 "learning_rate": 1.923578199052133e-05,407 "loss": 2.72,408 "step": 3250409 },410 {411 "epoch": 0.49,412 "learning_rate": 1.9531990521327015e-05,413 "loss": 2.6601,414 "step": 3300415 },416 {417 "epoch": 0.5,418 "learning_rate": 1.9828199052132704e-05,419 "loss": 2.5809,420 "step": 3350421 },422 {423 "epoch": 0.5,424 "learning_rate": 1.998617466012706e-05,425 "loss": 2.5155,426 "step": 3400427 },428 {429 "epoch": 0.51,430 "learning_rate": 1.9953257184239115e-05,431 "loss": 2.4071,432 "step": 3450433 },434 {435 "epoch": 0.52,436 "learning_rate": 1.9920339708351166e-05,437 "loss": 2.2622,438 "step": 3500439 },440 {441 "epoch": 0.53,442 "learning_rate": 1.9887422232463217e-05,443 "loss": 2.1511,444 "step": 3550445 },446 {447 "epoch": 0.53,448 "learning_rate": 1.985450475657527e-05,449 "loss": 2.0263,450 "step": 3600451 },452 {453 "epoch": 0.54,454 "learning_rate": 1.9821587280687316e-05,455 "loss": 1.9196,456 "step": 3650457 },458 {459 "epoch": 0.55,460 "learning_rate": 1.978866980479937e-05,461 "loss": 1.7882,462 "step": 3700463 },464 {465 "epoch": 0.56,466 "learning_rate": 1.975575232891142e-05,467 "loss": 1.6822,468 "step": 3750469 },470 {471 "epoch": 0.56,472 "learning_rate": 1.9722834853023473e-05,473 "loss": 1.5541,474 "step": 3800475 },476 {477 "epoch": 0.57,478 "learning_rate": 1.9689917377135524e-05,479 "loss": 1.5421,480 "step": 3850481 },482 {483 "epoch": 0.58,484 "learning_rate": 1.9656999901247575e-05,485 "loss": 1.4162,486 "step": 3900487 },488 {489 "epoch": 0.59,490 "learning_rate": 1.9624082425359626e-05,491 "loss": 1.323,492 "step": 3950493 },494 {495 "epoch": 0.59,496 "learning_rate": 1.9591164949471677e-05,497 "loss": 1.2838,498 "step": 4000499 },500 {501 "epoch": 0.6,502 "learning_rate": 1.9558247473583728e-05,503 "loss": 1.1865,504 "step": 4050505 },506 {507 "epoch": 0.61,508 "learning_rate": 1.952532999769578e-05,509 "loss": 1.1166,510 "step": 4100511 },512 {513 "epoch": 0.61,514 "learning_rate": 1.949241252180783e-05,515 "loss": 1.1203,516 "step": 4150517 },518 {519 "epoch": 0.62,520 "learning_rate": 1.945949504591988e-05,521 "loss": 1.0965,522 "step": 4200523 },524 {525 "epoch": 0.63,526 "learning_rate": 1.942657757003193e-05,527 "loss": 0.9832,528 "step": 4250529 },530 {531 "epoch": 0.64,532 "learning_rate": 1.9393660094143983e-05,533 "loss": 0.9714,534 "step": 4300535 },536 {537 "epoch": 0.64,538 "learning_rate": 1.9360742618256034e-05,539 "loss": 0.9182,540 "step": 4350541 },542 {543 "epoch": 0.65,544 "learning_rate": 1.9327825142368085e-05,545 "loss": 0.9218,546 "step": 4400547 },548 {549 "epoch": 0.66,550 "learning_rate": 1.9294907666480136e-05,551 "loss": 0.9231,552 "step": 4450553 },554 {555 "epoch": 0.67,556 "learning_rate": 1.9261990190592187e-05,557 "loss": 0.8684,558 "step": 4500559 },560 {561 "epoch": 0.67,562 "learning_rate": 1.9229072714704238e-05,563 "loss": 0.8196,564 "step": 4550565 },566 {567 "epoch": 0.68,568 "learning_rate": 1.919615523881629e-05,569 "loss": 0.8499,570 "step": 4600571 },572 {573 "epoch": 0.69,574 "learning_rate": 1.916323776292834e-05,575 "loss": 0.8108,576 "step": 4650577 },578 {579 "epoch": 0.7,580 "learning_rate": 1.913032028704039e-05,581 "loss": 0.7843,582 "step": 4700583 },584 {585 "epoch": 0.7,586 "learning_rate": 1.9097402811152442e-05,587 "loss": 0.7981,588 "step": 4750589 },590 {591 "epoch": 0.71,592 "learning_rate": 1.9064485335264493e-05,593 "loss": 0.7909,594 "step": 4800595 },596 {597 "epoch": 0.72,598 "learning_rate": 1.9031567859376544e-05,599 "loss": 0.7549,600 "step": 4850601 },602 {603 "epoch": 0.73,604 "learning_rate": 1.8998650383488595e-05,605 "loss": 0.7125,606 "step": 4900607 },608 {609 "epoch": 0.73,610 "learning_rate": 1.8965732907600646e-05,611 "loss": 0.7799,612 "step": 4950613 },614 {615 "epoch": 0.74,616 "learning_rate": 1.89328154317127e-05,617 "loss": 0.7012,618 "step": 5000619 },620 {621 "epoch": 0.74,622 "eval_loss": 0.34729066491127014,623 "eval_runtime": 94.3417,624 "eval_samples_per_second": 58.924,625 "eval_steps_per_second": 7.367,626 "eval_wer": 0.28398097580037934,627 "step": 5000628 },629 {630 "epoch": 0.75,631 "learning_rate": 1.8899897955824748e-05,632 "loss": 0.7523,633 "step": 5050634 },635 {636 "epoch": 0.76,637 "learning_rate": 1.88669804799368e-05,638 "loss": 0.6433,639 "step": 5100640 },641 {642 "epoch": 0.76,643 "learning_rate": 1.883406300404885e-05,644 "loss": 0.635,645 "step": 5150646 },647 {648 "epoch": 0.77,649 "learning_rate": 1.88011455281609e-05,650 "loss": 0.6563,651 "step": 5200652 },653 {654 "epoch": 0.78,655 "learning_rate": 1.8768228052272955e-05,656 "loss": 0.6238,657 "step": 5250658 },659 {660 "epoch": 0.79,661 "learning_rate": 1.8735310576385003e-05,662 "loss": 0.595,663 "step": 5300664 },665 {666 "epoch": 0.79,667 "learning_rate": 1.8702393100497057e-05,668 "loss": 0.6241,669 "step": 5350670 },671 {672 "epoch": 0.8,673 "learning_rate": 1.8669475624609105e-05,674 "loss": 0.6602,675 "step": 5400676 },677 {678 "epoch": 0.81,679 "learning_rate": 1.863655814872116e-05,680 "loss": 0.6206,681 "step": 5450682 },683 {684 "epoch": 0.81,685 "learning_rate": 1.860364067283321e-05,686 "loss": 0.6292,687 "step": 5500688 },689 {690 "epoch": 0.82,691 "learning_rate": 1.8570723196945258e-05,692 "loss": 0.6009,693 "step": 5550694 },695 {696 "epoch": 0.83,697 "learning_rate": 1.8537805721057312e-05,698 "loss": 0.6348,699 "step": 5600700 },701 {702 "epoch": 0.84,703 "learning_rate": 1.850488824516936e-05,704 "loss": 0.572,705 "step": 5650706 },707 {708 "epoch": 0.84,709 "learning_rate": 1.8471970769281414e-05,710 "loss": 0.5527,711 "step": 5700712 },713 {714 "epoch": 0.85,715 "learning_rate": 1.8439053293393466e-05,716 "loss": 0.5879,717 "step": 5750718 },719 {720 "epoch": 0.86,721 "learning_rate": 1.8406135817505517e-05,722 "loss": 0.5748,723 "step": 5800724 },725 {726 "epoch": 0.87,727 "learning_rate": 1.8373218341617568e-05,728 "loss": 0.5542,729 "step": 5850730 },731 {732 "epoch": 0.87,733 "learning_rate": 1.8340300865729615e-05,734 "loss": 0.5357,735 "step": 5900736 },737 {738 "epoch": 0.88,739 "learning_rate": 1.830738338984167e-05,740 "loss": 0.5334,741 "step": 5950742 },743 {744 "epoch": 0.89,745 "learning_rate": 1.827446591395372e-05,746 "loss": 0.5453,747 "step": 6000748 },749 {750 "epoch": 0.9,751 "learning_rate": 1.824154843806577e-05,752 "loss": 0.5886,753 "step": 6050754 },755 {756 "epoch": 0.9,757 "learning_rate": 1.8208630962177823e-05,758 "loss": 0.5514,759 "step": 6100760 },761 {762 "epoch": 0.91,763 "learning_rate": 1.8175713486289874e-05,764 "loss": 0.5222,765 "step": 6150766 },767 {768 "epoch": 0.92,769 "learning_rate": 1.8142796010401925e-05,770 "loss": 0.5379,771 "step": 6200772 },773 {774 "epoch": 0.93,775 "learning_rate": 1.8109878534513976e-05,776 "loss": 0.5194,777 "step": 6250778 },779 {780 "epoch": 0.93,781 "learning_rate": 1.8076961058626027e-05,782 "loss": 0.5172,783 "step": 6300784 },785 {786 "epoch": 0.94,787 "learning_rate": 1.8044043582738078e-05,788 "loss": 0.5348,789 "step": 6350790 },791 {792 "epoch": 0.95,793 "learning_rate": 1.801112610685013e-05,794 "loss": 0.4841,795 "step": 6400796 },797 {798 "epoch": 0.96,799 "learning_rate": 1.797820863096218e-05,800 "loss": 0.5201,801 "step": 6450802 },803 {804 "epoch": 0.96,805 "learning_rate": 1.794529115507423e-05,806 "loss": 0.5244,807 "step": 6500808 },809 {810 "epoch": 0.97,811 "learning_rate": 1.7912373679186282e-05,812 "loss": 0.4829,813 "step": 6550814 },815 {816 "epoch": 0.98,817 "learning_rate": 1.7880114552816094e-05,818 "loss": 0.521,819 "step": 6600820 },821 {822 "epoch": 0.99,823 "learning_rate": 1.784719707692814e-05,824 "loss": 0.4329,825 "step": 6650826 },827 {828 "epoch": 0.99,829 "learning_rate": 1.7814279601040196e-05,830 "loss": 0.5034,831 "step": 6700832 },833 {834 "epoch": 1.0,835 "learning_rate": 1.7781362125152243e-05,836 "loss": 0.4883,837 "step": 6750838 },839 {840 "epoch": 1.01,841 "learning_rate": 1.7748444649264294e-05,842 "loss": 0.5063,843 "step": 6800844 },845 {846 "epoch": 1.01,847 "learning_rate": 1.771552717337635e-05,848 "loss": 0.5545,849 "step": 6850850 },851 {852 "epoch": 1.02,853 "learning_rate": 1.7682609697488396e-05,854 "loss": 0.4859,855 "step": 6900856 },857 {858 "epoch": 1.03,859 "learning_rate": 1.764969222160045e-05,860 "loss": 0.4756,861 "step": 6950862 },863 {864 "epoch": 1.04,865 "learning_rate": 1.76167747457125e-05,866 "loss": 0.4688,867 "step": 7000868 },869 {870 "epoch": 1.04,871 "learning_rate": 1.7583857269824553e-05,872 "loss": 0.5528,873 "step": 7050874 },875 {876 "epoch": 1.05,877 "learning_rate": 1.7550939793936604e-05,878 "loss": 0.462,879 "step": 7100880 },881 {882 "epoch": 1.06,883 "learning_rate": 1.751802231804865e-05,884 "loss": 0.4634,885 "step": 7150886 },887 {888 "epoch": 1.07,889 "learning_rate": 1.7485104842160706e-05,890 "loss": 0.5026,891 "step": 7200892 },893 {894 "epoch": 1.07,895 "learning_rate": 1.7452187366272754e-05,896 "loss": 0.4976,897 "step": 7250898 },899 {900 "epoch": 1.08,901 "learning_rate": 1.7419269890384808e-05,902 "loss": 0.4767,903 "step": 7300904 },905 {906 "epoch": 1.09,907 "learning_rate": 1.738635241449686e-05,908 "loss": 0.4584,909 "step": 7350910 },911 {912 "epoch": 1.1,913 "learning_rate": 1.735343493860891e-05,914 "loss": 0.4556,915 "step": 7400916 },917 {918 "epoch": 1.1,919 "learning_rate": 1.732051746272096e-05,920 "loss": 0.4692,921 "step": 7450922 },923 {924 "epoch": 1.11,925 "learning_rate": 1.728759998683301e-05,926 "loss": 0.46,927 "step": 7500928 },929 {930 "epoch": 1.11,931 "eval_loss": 0.20323950052261353,932 "eval_runtime": 93.8223,933 "eval_samples_per_second": 59.25,934 "eval_steps_per_second": 7.408,935 "eval_wer": 0.1510022016984531,936 "step": 7500937 },938 {939 "epoch": 1.12,940 "learning_rate": 1.7254682510945063e-05,941 "loss": 0.4607,942 "step": 7550943 },944 {945 "epoch": 1.13,946 "learning_rate": 1.7221765035057114e-05,947 "loss": 0.4231,948 "step": 7600949 },950 {951 "epoch": 1.13,952 "learning_rate": 1.7188847559169165e-05,953 "loss": 0.4986,954 "step": 7650955 },956 {957 "epoch": 1.14,958 "learning_rate": 1.7155930083281216e-05,959 "loss": 0.4645,960 "step": 7700961 },962 {963 "epoch": 1.15,964 "learning_rate": 1.7123012607393267e-05,965 "loss": 0.4507,966 "step": 7750967 },968 {969 "epoch": 1.16,970 "learning_rate": 1.7090095131505318e-05,971 "loss": 0.4512,972 "step": 7800973 },974 {975 "epoch": 1.16,976 "learning_rate": 1.705717765561737e-05,977 "loss": 0.4333,978 "step": 7850979 },980 {981 "epoch": 1.17,982 "learning_rate": 1.702426017972942e-05,983 "loss": 0.4414,984 "step": 7900985 },986 {987 "epoch": 1.18,988 "learning_rate": 1.699134270384147e-05,989 "loss": 0.449,990 "step": 7950991 },992 {993 "epoch": 1.19,994 "learning_rate": 1.6958425227953522e-05,995 "loss": 0.4408,996 "step": 8000997 },998 {999 "epoch": 1.19,1000 "learning_rate": 1.6925507752065573e-05,1001 "loss": 0.4323,1002 "step": 80501003 },1004 {1005 "epoch": 1.2,1006 "learning_rate": 1.6892590276177624e-05,1007 "loss": 0.4439,1008 "step": 81001009 },1010 {1011 "epoch": 1.21,1012 "learning_rate": 1.6859672800289675e-05,1013 "loss": 0.4241,1014 "step": 81501015 },1016 {1017 "epoch": 1.21,1018 "learning_rate": 1.6826755324401726e-05,1019 "loss": 0.4587,1020 "step": 82001021 },1022 {1023 "epoch": 1.22,1024 "learning_rate": 1.6793837848513777e-05,1025 "loss": 0.4262,1026 "step": 82501027 },1028 {1029 "epoch": 1.23,1030 "learning_rate": 1.6760920372625828e-05,1031 "loss": 0.4298,1032 "step": 83001033 },1034 {1035 "epoch": 1.24,1036 "learning_rate": 1.672800289673788e-05,1037 "loss": 0.4084,1038 "step": 83501039 },1040 {1041 "epoch": 1.24,1042 "learning_rate": 1.669508542084993e-05,1043 "loss": 0.4762,1044 "step": 84001045 },1046 {1047 "epoch": 1.25,1048 "learning_rate": 1.666216794496198e-05,1049 "loss": 0.411,1050 "step": 84501051 },1052 {1053 "epoch": 1.26,1054 "learning_rate": 1.6629250469074032e-05,1055 "loss": 0.4639,1056 "step": 85001057 },1058 {1059 "epoch": 1.27,1060 "learning_rate": 1.6596332993186083e-05,1061 "loss": 0.3964,1062 "step": 85501063 },1064 {1065 "epoch": 1.27,1066 "learning_rate": 1.6563415517298134e-05,1067 "loss": 0.424,1068 "step": 86001069 },1070 {1071 "epoch": 1.28,1072 "learning_rate": 1.6530498041410185e-05,1073 "loss": 0.4324,1074 "step": 86501075 },1076 {1077 "epoch": 1.29,1078 "learning_rate": 1.6497580565522236e-05,1079 "loss": 0.4041,1080 "step": 87001081 },1082 {1083 "epoch": 1.3,1084 "learning_rate": 1.6464663089634287e-05,1085 "loss": 0.4354,1086 "step": 87501087 },1088 {1089 "epoch": 1.3,1090 "learning_rate": 1.643174561374634e-05,1091 "loss": 0.3862,1092 "step": 88001093 },1094 {1095 "epoch": 1.31,1096 "learning_rate": 1.6399486487376147e-05,1097 "loss": 0.3986,1098 "step": 88501099 },1100 {1101 "epoch": 1.32,1102 "learning_rate": 1.63665690114882e-05,1103 "loss": 0.3746,1104 "step": 89001105 },1106 {1107 "epoch": 1.33,1108 "learning_rate": 1.6333651535600252e-05,1109 "loss": 0.4107,1110 "step": 89501111 },1112 {1113 "epoch": 1.33,1114 "learning_rate": 1.6300734059712304e-05,1115 "loss": 0.4033,1116 "step": 90001117 },1118 {1119 "epoch": 1.34,1120 "learning_rate": 1.6267816583824355e-05,1121 "loss": 0.3992,1122 "step": 90501123 },1124 {1125 "epoch": 1.35,1126 "learning_rate": 1.6234899107936402e-05,1127 "loss": 0.3721,1128 "step": 91001129 },1130 {1131 "epoch": 1.36,1132 "learning_rate": 1.6201981632048457e-05,1133 "loss": 0.3948,1134 "step": 91501135 },1136 {1137 "epoch": 1.36,1138 "learning_rate": 1.6169064156160508e-05,1139 "loss": 0.4064,1140 "step": 92001141 },1142 {1143 "epoch": 1.37,1144 "learning_rate": 1.6136805029790316e-05,1145 "loss": 0.4048,1146 "step": 92501147 },1148 {1149 "epoch": 1.38,1150 "learning_rate": 1.6103887553902367e-05,1151 "loss": 0.3823,1152 "step": 93001153 },1154 {1155 "epoch": 1.38,1156 "learning_rate": 1.6070970078014418e-05,1157 "loss": 0.3902,1158 "step": 93501159 },1160 {1161 "epoch": 1.39,1162 "learning_rate": 1.603805260212647e-05,1163 "loss": 0.3738,1164 "step": 94001165 },1166 {1167 "epoch": 1.4,1168 "learning_rate": 1.6005135126238524e-05,1169 "loss": 0.3811,1170 "step": 94501171 },1172 {1173 "epoch": 1.41,1174 "learning_rate": 1.597221765035057e-05,1175 "loss": 0.3806,1176 "step": 95001177 },1178 {1179 "epoch": 1.41,1180 "learning_rate": 1.5939300174462626e-05,1181 "loss": 0.3779,1182 "step": 95501183 },1184 {1185 "epoch": 1.42,1186 "learning_rate": 1.5906382698574673e-05,1187 "loss": 0.38,1188 "step": 96001189 },1190 {1191 "epoch": 1.43,1192 "learning_rate": 1.5873465222686724e-05,1193 "loss": 0.3967,1194 "step": 96501195 },1196 {1197 "epoch": 1.44,1198 "learning_rate": 1.584054774679878e-05,1199 "loss": 0.3738,1200 "step": 9700