Proactive-Interactive-R1/Proactive-Interactive-R1-SFT-7B
015
1{2 "best_global_step": null,3 "best_metric": null,4 "best_model_checkpoint": null,5 "epoch": 3.0,6 "eval_steps": 500,7 "global_step": 375,8 "is_hyper_param_search": false,9 "is_local_process_zero": true,10 "is_world_process_zero": true,11 "log_history": [12 {13 "epoch": 0.008,14 "grad_norm": 6.165421485900879,15 "learning_rate": 0.0,16 "loss": 2.3147,17 "step": 118 },19 {20 "epoch": 0.016,21 "grad_norm": 5.735071659088135,22 "learning_rate": 8.333333333333333e-07,23 "loss": 2.2195,24 "step": 225 },26 {27 "epoch": 0.024,28 "grad_norm": 6.245882987976074,29 "learning_rate": 1.6666666666666667e-06,30 "loss": 2.3793,31 "step": 332 },33 {34 "epoch": 0.032,35 "grad_norm": 6.186586856842041,36 "learning_rate": 2.5e-06,37 "loss": 2.2879,38 "step": 439 },40 {41 "epoch": 0.04,42 "grad_norm": 5.804585933685303,43 "learning_rate": 3.3333333333333333e-06,44 "loss": 2.2428,45 "step": 546 },47 {48 "epoch": 0.048,49 "grad_norm": 5.387149333953857,50 "learning_rate": 4.166666666666667e-06,51 "loss": 2.2197,52 "step": 653 },54 {55 "epoch": 0.056,56 "grad_norm": 4.933386325836182,57 "learning_rate": 5e-06,58 "loss": 2.0332,59 "step": 760 },61 {62 "epoch": 0.064,63 "grad_norm": 3.527738571166992,64 "learning_rate": 5.833333333333334e-06,65 "loss": 2.1247,66 "step": 867 },68 {69 "epoch": 0.072,70 "grad_norm": 3.6139931678771973,71 "learning_rate": 6.666666666666667e-06,72 "loss": 2.1694,73 "step": 974 },75 {76 "epoch": 0.08,77 "grad_norm": 2.918950080871582,78 "learning_rate": 7.500000000000001e-06,79 "loss": 2.1108,80 "step": 1081 },82 {83 "epoch": 0.088,84 "grad_norm": 2.8728139400482178,85 "learning_rate": 8.333333333333334e-06,86 "loss": 2.0756,87 "step": 1188 },89 {90 "epoch": 0.096,91 "grad_norm": 2.7820944786071777,92 "learning_rate": 9.166666666666666e-06,93 "loss": 2.0886,94 "step": 1295 },96 {97 "epoch": 0.104,98 "grad_norm": 2.8887734413146973,99 "learning_rate": 1e-05,100 "loss": 1.9143,101 "step": 13102 },103 {104 "epoch": 0.112,105 "grad_norm": 2.7269833087921143,106 "learning_rate": 9.999812749151968e-06,107 "loss": 1.7421,108 "step": 14109 },110 {111 "epoch": 0.12,112 "grad_norm": 2.4814541339874268,113 "learning_rate": 9.99925101063302e-06,114 "loss": 1.9555,115 "step": 15116 },117 {118 "epoch": 0.128,119 "grad_norm": 2.188281297683716,120 "learning_rate": 9.998314826517564e-06,121 "loss": 1.7679,122 "step": 16123 },124 {125 "epoch": 0.136,126 "grad_norm": 2.072674036026001,127 "learning_rate": 9.997004266926105e-06,128 "loss": 1.8436,129 "step": 17130 },131 {132 "epoch": 0.144,133 "grad_norm": 1.929784893989563,134 "learning_rate": 9.995319430020004e-06,135 "loss": 1.6908,136 "step": 18137 },138 {139 "epoch": 0.152,140 "grad_norm": 1.532141089439392,141 "learning_rate": 9.993260441994116e-06,142 "loss": 1.8093,143 "step": 19144 },145 {146 "epoch": 0.16,147 "grad_norm": 1.5804815292358398,148 "learning_rate": 9.990827457067342e-06,149 "loss": 1.8674,150 "step": 20151 },152 {153 "epoch": 0.168,154 "grad_norm": 1.6191236972808838,155 "learning_rate": 9.988020657471078e-06,156 "loss": 1.8742,157 "step": 21158 },159 {160 "epoch": 0.176,161 "grad_norm": 1.451058030128479,162 "learning_rate": 9.984840253435569e-06,163 "loss": 1.7627,164 "step": 22165 },166 {167 "epoch": 0.184,168 "grad_norm": 1.297680139541626,169 "learning_rate": 9.98128648317415e-06,170 "loss": 1.7632,171 "step": 23172 },173 {174 "epoch": 0.192,175 "grad_norm": 1.2567354440689087,176 "learning_rate": 9.977359612865424e-06,177 "loss": 1.7992,178 "step": 24179 },180 {181 "epoch": 0.2,182 "grad_norm": 1.2900863885879517,183 "learning_rate": 9.973059936633308e-06,184 "loss": 1.7215,185 "step": 25186 },187 {188 "epoch": 0.208,189 "grad_norm": 1.2776153087615967,190 "learning_rate": 9.968387776525009e-06,191 "loss": 1.7456,192 "step": 26193 },194 {195 "epoch": 0.216,196 "grad_norm": 1.263024926185608,197 "learning_rate": 9.963343482486907e-06,198 "loss": 1.7512,199 "step": 27200 },201 {202 "epoch": 0.224,203 "grad_norm": 1.2118524312973022,204 "learning_rate": 9.957927432338332e-06,205 "loss": 1.801,206 "step": 28207 },208 {209 "epoch": 0.232,210 "grad_norm": 1.1955608129501343,211 "learning_rate": 9.952140031743282e-06,212 "loss": 1.7266,213 "step": 29214 },215 {216 "epoch": 0.24,217 "grad_norm": 1.2853139638900757,218 "learning_rate": 9.945981714180021e-06,219 "loss": 1.8852,220 "step": 30221 },222 {223 "epoch": 0.248,224 "grad_norm": 1.1693278551101685,225 "learning_rate": 9.939452940908627e-06,226 "loss": 1.6649,227 "step": 31228 },229 {230 "epoch": 0.256,231 "grad_norm": 1.2286041975021362,232 "learning_rate": 9.932554200936428e-06,233 "loss": 1.7861,234 "step": 32235 },236 {237 "epoch": 0.264,238 "grad_norm": 1.34682297706604,239 "learning_rate": 9.925286010981394e-06,240 "loss": 1.7849,241 "step": 33242 },243 {244 "epoch": 0.272,245 "grad_norm": 1.2271584272384644,246 "learning_rate": 9.917648915433413e-06,247 "loss": 1.8268,248 "step": 34249 },250 {251 "epoch": 0.28,252 "grad_norm": 1.2259082794189453,253 "learning_rate": 9.909643486313533e-06,254 "loss": 1.7176,255 "step": 35256 },257 {258 "epoch": 0.288,259 "grad_norm": 1.1778770685195923,260 "learning_rate": 9.901270323231114e-06,261 "loss": 1.7909,262 "step": 36263 },264 {265 "epoch": 0.296,266 "grad_norm": 1.1178228855133057,267 "learning_rate": 9.892530053338909e-06,268 "loss": 1.7618,269 "step": 37270 },271 {272 "epoch": 0.304,273 "grad_norm": 1.1982990503311157,274 "learning_rate": 9.883423331286096e-06,275 "loss": 1.7316,276 "step": 38277 },278 {279 "epoch": 0.312,280 "grad_norm": 1.0350874662399292,281 "learning_rate": 9.873950839169248e-06,282 "loss": 1.6342,283 "step": 39284 },285 {286 "epoch": 0.32,287 "grad_norm": 1.188277244567871,288 "learning_rate": 9.864113286481237e-06,289 "loss": 1.7302,290 "step": 40291 },292 {293 "epoch": 0.328,294 "grad_norm": 1.1097241640090942,295 "learning_rate": 9.853911410058097e-06,296 "loss": 1.5871,297 "step": 41298 },299 {300 "epoch": 0.336,301 "grad_norm": 1.1486974954605103,302 "learning_rate": 9.843345974023833e-06,303 "loss": 1.7055,304 "step": 42305 },306 {307 "epoch": 0.344,308 "grad_norm": 1.1390248537063599,309 "learning_rate": 9.832417769733185e-06,310 "loss": 1.725,311 "step": 43312 },313 {314 "epoch": 0.352,315 "grad_norm": 1.1239397525787354,316 "learning_rate": 9.821127615712365e-06,317 "loss": 1.7716,318 "step": 44319 },320 {321 "epoch": 0.36,322 "grad_norm": 1.095049262046814,323 "learning_rate": 9.809476357597738e-06,324 "loss": 1.6597,325 "step": 45326 },327 {328 "epoch": 0.368,329 "grad_norm": 1.2124348878860474,330 "learning_rate": 9.797464868072489e-06,331 "loss": 1.7454,332 "step": 46333 },334 {335 "epoch": 0.376,336 "grad_norm": 1.1528229713439941,337 "learning_rate": 9.785094046801256e-06,338 "loss": 1.813,339 "step": 47340 },341 {342 "epoch": 0.384,343 "grad_norm": 1.1076029539108276,344 "learning_rate": 9.77236482036275e-06,345 "loss": 1.6276,346 "step": 48347 },348 {349 "epoch": 0.392,350 "grad_norm": 1.1525791883468628,351 "learning_rate": 9.759278142180348e-06,352 "loss": 1.6772,353 "step": 49354 },355 {356 "epoch": 0.4,357 "grad_norm": 1.1833432912826538,358 "learning_rate": 9.745834992450688e-06,359 "loss": 1.7564,360 "step": 50361 },362 {363 "epoch": 0.408,364 "grad_norm": 1.220745325088501,365 "learning_rate": 9.732036378070243e-06,366 "loss": 1.7262,367 "step": 51368 },369 {370 "epoch": 0.416,371 "grad_norm": 1.1543320417404175,372 "learning_rate": 9.717883332559911e-06,373 "loss": 1.5396,374 "step": 52375 },376 {377 "epoch": 0.424,378 "grad_norm": 1.1147841215133667,379 "learning_rate": 9.703376915987601e-06,380 "loss": 1.7466,381 "step": 53382 },383 {384 "epoch": 0.432,385 "grad_norm": 1.0171838998794556,386 "learning_rate": 9.688518214888836e-06,387 "loss": 1.6408,388 "step": 54389 },390 {391 "epoch": 0.44,392 "grad_norm": 1.0049159526824951,393 "learning_rate": 9.673308342185366e-06,394 "loss": 1.5324,395 "step": 55396 },397 {398 "epoch": 0.448,399 "grad_norm": 1.069504737854004,400 "learning_rate": 9.657748437101819e-06,401 "loss": 1.5823,402 "step": 56403 },404 {405 "epoch": 0.456,406 "grad_norm": 1.0831701755523682,407 "learning_rate": 9.641839665080363e-06,408 "loss": 1.7311,409 "step": 57410 },411 {412 "epoch": 0.464,413 "grad_norm": 1.0674666166305542,414 "learning_rate": 9.625583217693419e-06,415 "loss": 1.8164,416 "step": 58417 },418 {419 "epoch": 0.472,420 "grad_norm": 1.0751819610595703,421 "learning_rate": 9.60898031255441e-06,422 "loss": 1.6059,423 "step": 59424 },425 {426 "epoch": 0.48,427 "grad_norm": 1.0138529539108276,428 "learning_rate": 9.592032193226564e-06,429 "loss": 1.7617,430 "step": 60431 },432 {433 "epoch": 0.488,434 "grad_norm": 1.0597162246704102,435 "learning_rate": 9.574740129129767e-06,436 "loss": 1.7207,437 "step": 61438 },439 {440 "epoch": 0.496,441 "grad_norm": 1.0368247032165527,442 "learning_rate": 9.557105415445485e-06,443 "loss": 1.7482,444 "step": 62445 },446 {447 "epoch": 0.504,448 "grad_norm": 1.0020555257797241,449 "learning_rate": 9.539129373019755e-06,450 "loss": 1.7692,451 "step": 63452 },453 {454 "epoch": 0.512,455 "grad_norm": 1.0732332468032837,456 "learning_rate": 9.520813348264252e-06,457 "loss": 1.737,458 "step": 64459 },460 {461 "epoch": 0.52,462 "grad_norm": 0.9923004508018494,463 "learning_rate": 9.502158713055444e-06,464 "loss": 1.6523,465 "step": 65466 },467 {468 "epoch": 0.528,469 "grad_norm": 1.0406478643417358,470 "learning_rate": 9.483166864631837e-06,471 "loss": 1.7734,472 "step": 66473 },474 {475 "epoch": 0.536,476 "grad_norm": 1.030851125717163,477 "learning_rate": 9.46383922548932e-06,478 "loss": 1.6183,479 "step": 67480 },481 {482 "epoch": 0.544,483 "grad_norm": 1.0091995000839233,484 "learning_rate": 9.444177243274619e-06,485 "loss": 1.6967,486 "step": 68487 },488 {489 "epoch": 0.552,490 "grad_norm": 1.0016194581985474,491 "learning_rate": 9.424182390676872e-06,492 "loss": 1.5285,493 "step": 69494 },495 {496 "epoch": 0.56,497 "grad_norm": 1.0569149255752563,498 "learning_rate": 9.403856165317322e-06,499 "loss": 1.7399,500 "step": 70501 },502 {503 "epoch": 0.568,504 "grad_norm": 1.0487375259399414,505 "learning_rate": 9.383200089637143e-06,506 "loss": 1.6845,507 "step": 71508 },509 {510 "epoch": 0.576,511 "grad_norm": 1.0257350206375122,512 "learning_rate": 9.362215710783411e-06,513 "loss": 1.6052,514 "step": 72515 },516 {517 "epoch": 0.584,518 "grad_norm": 0.9415053129196167,519 "learning_rate": 9.34090460049322e-06,520 "loss": 1.6624,521 "step": 73522 },523 {524 "epoch": 0.592,525 "grad_norm": 0.982798159122467,526 "learning_rate": 9.319268354975958e-06,527 "loss": 1.581,528 "step": 74529 },530 {531 "epoch": 0.6,532 "grad_norm": 1.0241587162017822,533 "learning_rate": 9.297308594793757e-06,534 "loss": 1.6495,535 "step": 75536 },537 {538 "epoch": 0.608,539 "grad_norm": 1.0798351764678955,540 "learning_rate": 9.275026964740101e-06,541 "loss": 1.6056,542 "step": 76543 },544 {545 "epoch": 0.616,546 "grad_norm": 1.0368587970733643,547 "learning_rate": 9.252425133716639e-06,548 "loss": 1.679,549 "step": 77550 },551 {552 "epoch": 0.624,553 "grad_norm": 1.019658088684082,554 "learning_rate": 9.229504794608182e-06,555 "loss": 1.6168,556 "step": 78557 },558 {559 "epoch": 0.632,560 "grad_norm": 0.9923626184463501,561 "learning_rate": 9.206267664155906e-06,562 "loss": 1.6812,563 "step": 79564 },565 {566 "epoch": 0.64,567 "grad_norm": 0.9651780724525452,568 "learning_rate": 9.182715482828764e-06,569 "loss": 1.6214,570 "step": 80571 },572 {573 "epoch": 0.648,574 "grad_norm": 1.065513014793396,575 "learning_rate": 9.158850014693123e-06,576 "loss": 1.6537,577 "step": 81578 },579 {580 "epoch": 0.656,581 "grad_norm": 0.9438872933387756,582 "learning_rate": 9.134673047280644e-06,583 "loss": 1.602,584 "step": 82585 },586 {587 "epoch": 0.664,588 "grad_norm": 1.0228830575942993,589 "learning_rate": 9.110186391454389e-06,590 "loss": 1.7139,591 "step": 83592 },593 {594 "epoch": 0.672,595 "grad_norm": 1.0108044147491455,596 "learning_rate": 9.085391881273182e-06,597 "loss": 1.6621,598 "step": 84599 },600 {601 "epoch": 0.68,602 "grad_norm": 0.9967405200004578,603 "learning_rate": 9.060291373854252e-06,604 "loss": 1.6323,605 "step": 85606 },607 {608 "epoch": 0.688,609 "grad_norm": 1.0818958282470703,610 "learning_rate": 9.034886749234112e-06,611 "loss": 1.6435,612 "step": 86613 },614 {615 "epoch": 0.696,616 "grad_norm": 1.012364149093628,617 "learning_rate": 9.009179910227767e-06,618 "loss": 1.6756,619 "step": 87620 },621 {622 "epoch": 0.704,623 "grad_norm": 1.084316372871399,624 "learning_rate": 8.98317278228618e-06,625 "loss": 1.6813,626 "step": 88627 },628 {629 "epoch": 0.712,630 "grad_norm": 1.0937138795852661,631 "learning_rate": 8.956867313352055e-06,632 "loss": 1.6627,633 "step": 89634 },635 {636 "epoch": 0.72,637 "grad_norm": 1.081781268119812,638 "learning_rate": 8.930265473713939e-06,639 "loss": 1.8571,640 "step": 90641 },642 {643 "epoch": 0.728,644 "grad_norm": 0.9865168929100037,645 "learning_rate": 8.90336925585864e-06,646 "loss": 1.4989,647 "step": 91648 },649 {650 "epoch": 0.736,651 "grad_norm": 1.0438846349716187,652 "learning_rate": 8.876180674322006e-06,653 "loss": 1.6913,654 "step": 92655 },656 {657 "epoch": 0.744,658 "grad_norm": 1.0505565404891968,659 "learning_rate": 8.84870176553801e-06,660 "loss": 1.6397,661 "step": 93662 },663 {664 "epoch": 0.752,665 "grad_norm": 0.908542275428772,666 "learning_rate": 8.820934587686247e-06,667 "loss": 1.5152,668 "step": 94669 },670 {671 "epoch": 0.76,672 "grad_norm": 1.0538814067840576,673 "learning_rate": 8.792881220537752e-06,674 "loss": 1.5435,675 "step": 95676 },677 {678 "epoch": 0.768,679 "grad_norm": 1.0938372611999512,680 "learning_rate": 8.764543765299245e-06,681 "loss": 1.5283,682 "step": 96683 },684 {685 "epoch": 0.776,686 "grad_norm": 1.1297836303710938,687 "learning_rate": 8.735924344455732e-06,688 "loss": 1.6756,689 "step": 97690 },691 {692 "epoch": 0.784,693 "grad_norm": 0.9867210984230042,694 "learning_rate": 8.707025101611546e-06,695 "loss": 1.613,696 "step": 98697 },698 {699 "epoch": 0.792,700 "grad_norm": 1.0464468002319336,701 "learning_rate": 8.677848201329775e-06,702 "loss": 1.5942,703 "step": 99704 },705 {706 "epoch": 0.8,707 "grad_norm": 1.0653105974197388,708 "learning_rate": 8.64839582897015e-06,709 "loss": 1.7216,710 "step": 100711 },712 {713 "epoch": 0.808,714 "grad_norm": 0.9832385778427124,715 "learning_rate": 8.61867019052535e-06,716 "loss": 1.4699,717 "step": 101718 },719 {720 "epoch": 0.816,721 "grad_norm": 0.9331985116004944,722 "learning_rate": 8.588673512455781e-06,723 "loss": 1.7439,724 "step": 102725 },726 {727 "epoch": 0.824,728 "grad_norm": 0.9516758322715759,729 "learning_rate": 8.558408041522801e-06,730 "loss": 1.696,731 "step": 103732 },733 {734 "epoch": 0.832,735 "grad_norm": 1.0405412912368774,736 "learning_rate": 8.527876044620453e-06,737 "loss": 1.713,738 "step": 104739 },740 {741 "epoch": 0.84,742 "grad_norm": 0.9289470314979553,743 "learning_rate": 8.497079808605659e-06,744 "loss": 1.7213,745 "step": 105746 },747 {748 "epoch": 0.848,749 "grad_norm": 0.9201377034187317,750 "learning_rate": 8.466021640126946e-06,751 "loss": 1.6091,752 "step": 106753 },754 {755 "epoch": 0.856,756 "grad_norm": 0.9733519554138184,757 "learning_rate": 8.434703865451666e-06,758 "loss": 1.6345,759 "step": 107760 },761 {762 "epoch": 0.864,763 "grad_norm": 1.0086345672607422,764 "learning_rate": 8.403128830291767e-06,765 "loss": 1.6443,766 "step": 108767 },768 {769 "epoch": 0.872,770 "grad_norm": 1.031723141670227,771 "learning_rate": 8.371298899628091e-06,772 "loss": 1.6869,773 "step": 109774 },775 {776 "epoch": 0.88,777 "grad_norm": 0.98936527967453,778 "learning_rate": 8.339216457533244e-06,779 "loss": 1.5866,780 "step": 110781 },782 {783 "epoch": 0.888,784 "grad_norm": 0.962455689907074,785 "learning_rate": 8.306883906993022e-06,786 "loss": 1.6483,787 "step": 111788 },789 {790 "epoch": 0.896,791 "grad_norm": 0.9804932475090027,792 "learning_rate": 8.274303669726427e-06,793 "loss": 1.594,794 "step": 112795 },796 {797 "epoch": 0.904,798 "grad_norm": 0.9484031200408936,799 "learning_rate": 8.24147818600428e-06,800 "loss": 1.4755,801 "step": 113802 },803 {804 "epoch": 0.912,805 "grad_norm": 1.0301589965820312,806 "learning_rate": 8.20840991446645e-06,807 "loss": 1.6598,808 "step": 114809 },810 {811 "epoch": 0.92,812 "grad_norm": 0.9916971325874329,813 "learning_rate": 8.175101331937692e-06,814 "loss": 1.5304,815 "step": 115816 },817 {818 "epoch": 0.928,819 "grad_norm": 0.9457253813743591,820 "learning_rate": 8.141554933242135e-06,821 "loss": 1.6354,822 "step": 116823 },824 {825 "epoch": 0.936,826 "grad_norm": 1.002668023109436,827 "learning_rate": 8.10777323101642e-06,828 "loss": 1.5989,829 "step": 117830 },831 {832 "epoch": 0.944,833 "grad_norm": 1.0599579811096191,834 "learning_rate": 8.073758755521506e-06,835 "loss": 1.6564,836 "step": 118837 },838 {839 "epoch": 0.952,840 "grad_norm": 0.9575379490852356,841 "learning_rate": 8.03951405445314e-06,842 "loss": 1.5884,843 "step": 119844 },845 {846 "epoch": 0.96,847 "grad_norm": 0.8948677182197571,848 "learning_rate": 8.005041692751055e-06,849 "loss": 1.5128,850 "step": 120851 },852 {853 "epoch": 0.968,854 "grad_norm": 0.9918161034584045,855 "learning_rate": 7.970344252406832e-06,856 "loss": 1.7014,857 "step": 121858 },859 {860 "epoch": 0.976,861 "grad_norm": 1.0054118633270264,862 "learning_rate": 7.935424332270523e-06,863 "loss": 1.6341,864 "step": 122865 },866 {867 "epoch": 0.984,868 "grad_norm": 0.9967445731163025,869 "learning_rate": 7.900284547855992e-06,870 "loss": 1.6521,871 "step": 123872 },873 {874 "epoch": 0.992,875 "grad_norm": 1.0111421346664429,876 "learning_rate": 7.864927531145012e-06,877 "loss": 1.7013,878 "step": 124879 },880 {881 "epoch": 1.0,882 "grad_norm": 0.9393289685249329,883 "learning_rate": 7.829355930390126e-06,884 "loss": 1.5216,885 "step": 125886 },887 {888 "epoch": 1.008,889 "grad_norm": 0.9452322125434875,890 "learning_rate": 7.7935724099163e-06,891 "loss": 1.4109,892 "step": 126893 },894 {895 "epoch": 1.016,896 "grad_norm": 1.041080355644226,897 "learning_rate": 7.757579649921354e-06,898 "loss": 1.4167,899 "step": 127900 },901 {902 "epoch": 1.024,903 "grad_norm": 1.0035260915756226,904 "learning_rate": 7.721380346275221e-06,905 "loss": 1.4185,906 "step": 128907 },908 {909 "epoch": 1.032,910 "grad_norm": 0.9582903385162354,911 "learning_rate": 7.684977210318024e-06,912 "loss": 1.5076,913 "step": 129914 },915 {916 "epoch": 1.04,917 "grad_norm": 0.9640058279037476,918 "learning_rate": 7.648372968656995e-06,919 "loss": 1.4809,920 "step": 130921 },922 {923 "epoch": 1.048,924 "grad_norm": 0.9298117160797119,925 "learning_rate": 7.611570362962247e-06,926 "loss": 1.4613,927 "step": 131928 },929 {930 "epoch": 1.056,931 "grad_norm": 0.922681450843811,932 "learning_rate": 7.574572149761437e-06,933 "loss": 1.3367,934 "step": 132935 },936 {937 "epoch": 1.064,938 "grad_norm": 0.9627285599708557,939 "learning_rate": 7.5373811002332785e-06,940 "loss": 1.3333,941 "step": 133942 },943 {944 "epoch": 1.072,945 "grad_norm": 0.9147132635116577,946 "learning_rate": 7.500000000000001e-06,947 "loss": 1.2811,948 "step": 134949 },950 {951 "epoch": 1.08,952 "grad_norm": 0.942388117313385,953 "learning_rate": 7.462431648918689e-06,954 "loss": 1.2576,955 "step": 135956 },957 {958 "epoch": 1.088,959 "grad_norm": 0.9468157291412354,960 "learning_rate": 7.424678860871584e-06,961 "loss": 1.3759,962 "step": 136963 },964 {965 "epoch": 1.096,966 "grad_norm": 0.8806234002113342,967 "learning_rate": 7.3867444635553165e-06,968 "loss": 1.2774,969 "step": 137970 },971 {972 "epoch": 1.104,973 "grad_norm": 0.962507426738739,974 "learning_rate": 7.3486312982691134e-06,975 "loss": 1.346,976 "step": 138977 },978 {979 "epoch": 1.112,980 "grad_norm": 0.9227285385131836,981 "learning_rate": 7.310342219701981e-06,982 "loss": 1.3977,983 "step": 139984 },985 {986 "epoch": 1.12,987 "grad_norm": 0.9752129316329956,988 "learning_rate": 7.271880095718895e-06,989 "loss": 1.3203,990 "step": 140991 },992 {993 "epoch": 1.1280000000000001,994 "grad_norm": 0.9896626472473145,995 "learning_rate": 7.233247807145989e-06,996 "loss": 1.3563,997 "step": 141998 },999 {1000 "epoch": 1.1360000000000001,1001 "grad_norm": 0.9603149890899658,1002 "learning_rate": 7.19444824755478e-06,1003 "loss": 1.4031,1004 "step": 1421005 },1006 {1007 "epoch": 1.144,1008 "grad_norm": 0.9318594336509705,1009 "learning_rate": 7.155484323045442e-06,1010 "loss": 1.3123,1011 "step": 1431012 },1013 {1014 "epoch": 1.152,1015 "grad_norm": 0.9754460453987122,1016 "learning_rate": 7.11635895202914e-06,1017 "loss": 1.3359,1018 "step": 1441019 },1020 {1021 "epoch": 1.16,1022 "grad_norm": 0.9400285482406616,1023 "learning_rate": 7.0770750650094335e-06,1024 "loss": 1.4203,1025 "step": 1451026 },1027 {1028 "epoch": 1.168,1029 "grad_norm": 0.9439907073974609,1030 "learning_rate": 7.037635604362786e-06,1031 "loss": 1.3475,1032 "step": 1461033 },1034 {1035 "epoch": 1.176,1036 "grad_norm": 0.9856473803520203,1037 "learning_rate": 6.9980435241181785e-06,1038 "loss": 1.3728,1039 "step": 1471040 },1041 {1042 "epoch": 1.184,1043 "grad_norm": 1.0352829694747925,1044 "learning_rate": 6.958301789735853e-06,1045 "loss": 1.4341,1046 "step": 1481047 },1048 {1049 "epoch": 1.192,1050 "grad_norm": 1.0069676637649536,1051 "learning_rate": 6.918413377885193e-06,1052 "loss": 1.4365,1053 "step": 1491054 },1055 {1056 "epoch": 1.2,1057 "grad_norm": 0.9149236679077148,1058 "learning_rate": 6.878381276221777e-06,1059 "loss": 1.3273,1060 "step": 1501061 },1062 {1063 "epoch": 1.208,1064 "grad_norm": 0.9450361132621765,1065 "learning_rate": 6.838208483163601e-06,1066 "loss": 1.3297,1067 "step": 1511068 },1069 {1070 "epoch": 1.216,1071 "grad_norm": 1.0741515159606934,1072 "learning_rate": 6.797898007666493e-06,1073 "loss": 1.3977,1074 "step": 1521075 },1076 {1077 "epoch": 1.224,1078 "grad_norm": 0.9067620038986206,1079 "learning_rate": 6.757452868998737e-06,1080 "loss": 1.2802,1081 "step": 1531082 },1083 {1084 "epoch": 1.232,1085 "grad_norm": 0.9164926409721375,1086 "learning_rate": 6.716876096514944e-06,1087 "loss": 1.3741,1088 "step": 1541089 },1090 {1091 "epoch": 1.24,1092 "grad_norm": 0.9673436880111694,1093 "learning_rate": 6.676170729429132e-06,1094 "loss": 1.2866,1095 "step": 1551096 },1097 {1098 "epoch": 1.248,1099 "grad_norm": 0.8857837915420532,1100 "learning_rate": 6.635339816587109e-06,1101 "loss": 1.3524,1102 "step": 1561103 },1104 {1105 "epoch": 1.256,1106 "grad_norm": 1.0112680196762085,1107 "learning_rate": 6.594386416238095e-06,1108 "loss": 1.4385,1109 "step": 1571110 },1111 {1112 "epoch": 1.264,1113 "grad_norm": 0.9922051429748535,1114 "learning_rate": 6.553313595805666e-06,1115 "loss": 1.3711,1116 "step": 1581117 },1118 {1119 "epoch": 1.272,1120 "grad_norm": 0.9454922676086426,1121 "learning_rate": 6.512124431658006e-06,1122 "loss": 1.392,1123 "step": 1591124 },1125 {1126 "epoch": 1.28,1127 "grad_norm": 0.9144309759140015,1128 "learning_rate": 6.470822008877482e-06,1129 "loss": 1.3345,1130 "step": 1601131 },1132 {1133 "epoch": 1.288,1134 "grad_norm": 1.0063748359680176,1135 "learning_rate": 6.4294094210295725e-06,1136 "loss": 1.4048,1137 "step": 1611138 },1139 {1140 "epoch": 1.296,1141 "grad_norm": 1.0005673170089722,1142 "learning_rate": 6.3878897699311525e-06,1143 "loss": 1.4097,1144 "step": 1621145 },1146 {1147 "epoch": 1.304,1148 "grad_norm": 0.9271945357322693,1149 "learning_rate": 6.346266165418173e-06,1150 "loss": 1.3149,1151 "step": 1631152 },1153 {1154 "epoch": 1.312,1155 "grad_norm": 0.997925341129303,1156 "learning_rate": 6.304541725112734e-06,1157 "loss": 1.4207,1158 "step": 1641159 },1160 {1161 "epoch": 1.32,1162 "grad_norm": 1.0391231775283813,1163 "learning_rate": 6.262719574189564e-06,1164 "loss": 1.4244,1165 "step": 1651166 },1167 {1168 "epoch": 1.328,1169 "grad_norm": 1.0015145540237427,1170 "learning_rate": 6.2208028451419575e-06,1171 "loss": 1.2237,1172 "step": 1661173 },1174 {1175 "epoch": 1.336,1176 "grad_norm": 0.9355135560035706,1177 "learning_rate": 6.178794677547138e-06,1178 "loss": 1.3877,1179 "step": 1671180 },1181 {1182 "epoch": 1.3439999999999999,1183 "grad_norm": 0.9757426381111145,1184 "learning_rate": 6.136698217831106e-06,1185 "loss": 1.4125,1186 "step": 1681187 },1188 {1189 "epoch": 1.3519999999999999,1190 "grad_norm": 0.9164122939109802,1191 "learning_rate": 6.094516619032975e-06,1192 "loss": 1.3165,1193 "step": 1691194 },1195 {1196 "epoch": 1.3599999999999999,1197 "grad_norm": 0.902611255645752,1198 "learning_rate": 6.052253040568804e-06,1199 "loss": 1.2087,1200 "step": 170