LostOfMoon/generalgrounder
01
1{2 "best_global_step": null,3 "best_metric": null,4 "best_model_checkpoint": null,5 "epoch": 1.98744769874477,6 "eval_steps": 50,7 "global_step": 238,8 "is_hyper_param_search": false,9 "is_local_process_zero": true,10 "is_world_process_zero": true,11 "log_history": [12 {13 "epoch": 0.008368200836820083,14 "grad_norm": 41.122520446777344,15 "learning_rate": 0.0,16 "loss": 1.2237,17 "step": 118 },19 {20 "epoch": 0.016736401673640166,21 "grad_norm": 42.81283187866211,22 "learning_rate": 4.1666666666666667e-07,23 "loss": 1.2213,24 "step": 225 },26 {27 "epoch": 0.02510460251046025,28 "grad_norm": 39.692970275878906,29 "learning_rate": 8.333333333333333e-07,30 "loss": 1.301,31 "step": 332 },33 {34 "epoch": 0.03347280334728033,35 "grad_norm": 38.691219329833984,36 "learning_rate": 1.25e-06,37 "loss": 1.2717,38 "step": 439 },40 {41 "epoch": 0.04184100418410042,42 "grad_norm": 35.89279556274414,43 "learning_rate": 1.6666666666666667e-06,44 "loss": 1.1889,45 "step": 546 },47 {48 "epoch": 0.0502092050209205,49 "grad_norm": 27.171241760253906,50 "learning_rate": 2.0833333333333334e-06,51 "loss": 1.1894,52 "step": 653 },54 {55 "epoch": 0.058577405857740586,56 "grad_norm": 19.06900405883789,57 "learning_rate": 2.5e-06,58 "loss": 1.0021,59 "step": 760 },61 {62 "epoch": 0.06694560669456066,63 "grad_norm": 11.085134506225586,64 "learning_rate": 2.916666666666667e-06,65 "loss": 0.8806,66 "step": 867 },68 {69 "epoch": 0.07531380753138076,70 "grad_norm": 8.497941970825195,71 "learning_rate": 3.3333333333333333e-06,72 "loss": 0.8272,73 "step": 974 },75 {76 "epoch": 0.08368200836820083,77 "grad_norm": 6.706273555755615,78 "learning_rate": 3.7500000000000005e-06,79 "loss": 0.7905,80 "step": 1081 },82 {83 "epoch": 0.09205020920502092,84 "grad_norm": 4.998748779296875,85 "learning_rate": 4.166666666666667e-06,86 "loss": 0.722,87 "step": 1188 },89 {90 "epoch": 0.100418410041841,91 "grad_norm": 4.087235450744629,92 "learning_rate": 4.583333333333333e-06,93 "loss": 0.7108,94 "step": 1295 },96 {97 "epoch": 0.1087866108786611,98 "grad_norm": 2.844655752182007,99 "learning_rate": 5e-06,100 "loss": 0.7218,101 "step": 13102 },103 {104 "epoch": 0.11715481171548117,105 "grad_norm": 2.8085081577301025,106 "learning_rate": 5.416666666666667e-06,107 "loss": 0.6698,108 "step": 14109 },110 {111 "epoch": 0.12552301255230125,112 "grad_norm": 3.3626291751861572,113 "learning_rate": 5.833333333333334e-06,114 "loss": 0.6561,115 "step": 15116 },117 {118 "epoch": 0.13389121338912133,119 "grad_norm": 3.1426985263824463,120 "learning_rate": 6.25e-06,121 "loss": 0.6752,122 "step": 16123 },124 {125 "epoch": 0.14225941422594143,126 "grad_norm": 2.592170238494873,127 "learning_rate": 6.666666666666667e-06,128 "loss": 0.6493,129 "step": 17130 },131 {132 "epoch": 0.1506276150627615,133 "grad_norm": 2.0818114280700684,134 "learning_rate": 7.083333333333335e-06,135 "loss": 0.6313,136 "step": 18137 },138 {139 "epoch": 0.1589958158995816,140 "grad_norm": 1.6512285470962524,141 "learning_rate": 7.500000000000001e-06,142 "loss": 0.6217,143 "step": 19144 },145 {146 "epoch": 0.16736401673640167,147 "grad_norm": 2.3754539489746094,148 "learning_rate": 7.916666666666667e-06,149 "loss": 0.6139,150 "step": 20151 },152 {153 "epoch": 0.17573221757322174,154 "grad_norm": 1.6371946334838867,155 "learning_rate": 8.333333333333334e-06,156 "loss": 0.6212,157 "step": 21158 },159 {160 "epoch": 0.18410041841004185,161 "grad_norm": 2.4529337882995605,162 "learning_rate": 8.750000000000001e-06,163 "loss": 0.6267,164 "step": 22165 },166 {167 "epoch": 0.19246861924686193,168 "grad_norm": 2.0102877616882324,169 "learning_rate": 9.166666666666666e-06,170 "loss": 0.5943,171 "step": 23172 },173 {174 "epoch": 0.200836820083682,175 "grad_norm": 1.3912019729614258,176 "learning_rate": 9.583333333333335e-06,177 "loss": 0.5892,178 "step": 24179 },180 {181 "epoch": 0.20920502092050208,182 "grad_norm": 2.307511568069458,183 "learning_rate": 1e-05,184 "loss": 0.6178,185 "step": 25186 },187 {188 "epoch": 0.2175732217573222,189 "grad_norm": 2.0564095973968506,190 "learning_rate": 9.999461228756304e-06,191 "loss": 0.6098,192 "step": 26193 },194 {195 "epoch": 0.22594142259414227,196 "grad_norm": 1.716192603111267,197 "learning_rate": 9.997845031134992e-06,198 "loss": 0.5709,199 "step": 27200 },201 {202 "epoch": 0.23430962343096234,203 "grad_norm": 1.8920443058013916,204 "learning_rate": 9.99515175544039e-06,205 "loss": 0.582,206 "step": 28207 },208 {209 "epoch": 0.24267782426778242,210 "grad_norm": 2.6152799129486084,211 "learning_rate": 9.991381982096293e-06,212 "loss": 0.5796,213 "step": 29214 },215 {216 "epoch": 0.2510460251046025,217 "grad_norm": 1.8638914823532104,218 "learning_rate": 9.98653652352089e-06,219 "loss": 0.585,220 "step": 30221 },222 {223 "epoch": 0.2594142259414226,224 "grad_norm": 1.5614815950393677,225 "learning_rate": 9.98061642395168e-06,226 "loss": 0.5635,227 "step": 31228 },229 {230 "epoch": 0.26778242677824265,231 "grad_norm": 1.4210450649261475,232 "learning_rate": 9.973622959220426e-06,233 "loss": 0.5899,234 "step": 32235 },236 {237 "epoch": 0.27615062761506276,238 "grad_norm": 2.06299090385437,239 "learning_rate": 9.965557636478203e-06,240 "loss": 0.5483,241 "step": 33242 },243 {244 "epoch": 0.28451882845188287,245 "grad_norm": 1.4088494777679443,246 "learning_rate": 9.956422193870597e-06,247 "loss": 0.555,248 "step": 34249 },250 {251 "epoch": 0.2928870292887029,252 "grad_norm": 1.173156499862671,253 "learning_rate": 9.94621860016312e-06,254 "loss": 0.5606,255 "step": 35256 },257 {258 "epoch": 0.301255230125523,259 "grad_norm": 1.4184995889663696,260 "learning_rate": 9.934949054316917e-06,261 "loss": 0.5536,262 "step": 36263 },264 {265 "epoch": 0.30962343096234307,266 "grad_norm": 1.635988473892212,267 "learning_rate": 9.922615985014887e-06,268 "loss": 0.5589,269 "step": 37270 },271 {272 "epoch": 0.3179916317991632,273 "grad_norm": 2.0499227046966553,274 "learning_rate": 9.909222050138259e-06,275 "loss": 0.5545,276 "step": 38277 },278 {279 "epoch": 0.3263598326359833,280 "grad_norm": 1.9025866985321045,281 "learning_rate": 9.894770136193814e-06,282 "loss": 0.554,283 "step": 39284 },285 {286 "epoch": 0.33472803347280333,287 "grad_norm": 1.7186928987503052,288 "learning_rate": 9.879263357691815e-06,289 "loss": 0.5462,290 "step": 40291 },292 {293 "epoch": 0.34309623430962344,294 "grad_norm": 2.4819579124450684,295 "learning_rate": 9.862705056474795e-06,296 "loss": 0.5716,297 "step": 41298 },299 {300 "epoch": 0.3514644351464435,301 "grad_norm": 1.5357800722122192,302 "learning_rate": 9.84509880099737e-06,303 "loss": 0.5669,304 "step": 42305 },306 {307 "epoch": 0.3598326359832636,308 "grad_norm": 1.7539938688278198,309 "learning_rate": 9.826448385557208e-06,310 "loss": 0.5701,311 "step": 43312 },313 {314 "epoch": 0.3682008368200837,315 "grad_norm": 1.5892163515090942,316 "learning_rate": 9.806757829477313e-06,317 "loss": 0.5437,318 "step": 44319 },320 {321 "epoch": 0.37656903765690375,322 "grad_norm": 1.4727720022201538,323 "learning_rate": 9.786031376239842e-06,324 "loss": 0.555,325 "step": 45326 },327 {328 "epoch": 0.38493723849372385,329 "grad_norm": 1.310960292816162,330 "learning_rate": 9.76427349257159e-06,331 "loss": 0.5499,332 "step": 46333 },334 {335 "epoch": 0.39330543933054396,336 "grad_norm": 1.621464729309082,337 "learning_rate": 9.741488867481377e-06,338 "loss": 0.5422,339 "step": 47340 },341 {342 "epoch": 0.401673640167364,343 "grad_norm": 1.2852084636688232,344 "learning_rate": 9.71768241124952e-06,345 "loss": 0.5514,346 "step": 48347 },348 {349 "epoch": 0.4100418410041841,350 "grad_norm": 1.36189603805542,351 "learning_rate": 9.692859254369631e-06,352 "loss": 0.5458,353 "step": 49354 },355 {356 "epoch": 0.41841004184100417,357 "grad_norm": 1.867224097251892,358 "learning_rate": 9.667024746442953e-06,359 "loss": 0.5283,360 "step": 50361 },362 {363 "epoch": 0.41841004184100417,364 "eval_loss": 0.5560517311096191,365 "eval_runtime": 100.8894,366 "eval_samples_per_second": 15.324,367 "eval_steps_per_second": 1.923,368 "step": 50369 },370 {371 "epoch": 0.42677824267782427,372 "grad_norm": 1.502307415008545,373 "learning_rate": 9.640184455025472e-06,374 "loss": 0.5596,375 "step": 51376 },377 {378 "epoch": 0.4351464435146444,379 "grad_norm": 1.211090087890625,380 "learning_rate": 9.612344164428063e-06,381 "loss": 0.5327,382 "step": 52383 },384 {385 "epoch": 0.4435146443514644,386 "grad_norm": 1.3991564512252808,387 "learning_rate": 9.583509874469924e-06,388 "loss": 0.5416,389 "step": 53390 },391 {392 "epoch": 0.45188284518828453,393 "grad_norm": 1.5686155557632446,394 "learning_rate": 9.553687799185556e-06,395 "loss": 0.5283,396 "step": 54397 },398 {399 "epoch": 0.4602510460251046,400 "grad_norm": 1.6777782440185547,401 "learning_rate": 9.522884365485599e-06,402 "loss": 0.5407,403 "step": 55404 },405 {406 "epoch": 0.4686192468619247,407 "grad_norm": 1.4989711046218872,408 "learning_rate": 9.491106211771765e-06,409 "loss": 0.5272,410 "step": 56411 },412 {413 "epoch": 0.4769874476987448,414 "grad_norm": 1.3131951093673706,415 "learning_rate": 9.458360186506212e-06,416 "loss": 0.5466,417 "step": 57418 },419 {420 "epoch": 0.48535564853556484,421 "grad_norm": 1.2570877075195312,422 "learning_rate": 9.424653346735649e-06,423 "loss": 0.5403,424 "step": 58425 },426 {427 "epoch": 0.49372384937238495,428 "grad_norm": 1.2009389400482178,429 "learning_rate": 9.389992956570463e-06,430 "loss": 0.5232,431 "step": 59432 },433 {434 "epoch": 0.502092050209205,435 "grad_norm": 1.8347792625427246,436 "learning_rate": 9.354386485619264e-06,437 "loss": 0.5142,438 "step": 60439 },440 {441 "epoch": 0.5104602510460251,442 "grad_norm": 1.4692448377609253,443 "learning_rate": 9.317841607379106e-06,444 "loss": 0.5307,445 "step": 61446 },447 {448 "epoch": 0.5188284518828452,449 "grad_norm": 1.499603271484375,450 "learning_rate": 9.280366197581792e-06,451 "loss": 0.5443,452 "step": 62453 },454 {455 "epoch": 0.5271966527196653,456 "grad_norm": 1.412596344947815,457 "learning_rate": 9.241968332496576e-06,458 "loss": 0.5142,459 "step": 63460 },461 {462 "epoch": 0.5355648535564853,463 "grad_norm": 1.2176628112792969,464 "learning_rate": 9.20265628718967e-06,465 "loss": 0.5056,466 "step": 64467 },468 {469 "epoch": 0.5439330543933054,470 "grad_norm": 1.5103838443756104,471 "learning_rate": 9.162438533740891e-06,472 "loss": 0.5073,473 "step": 65474 },475 {476 "epoch": 0.5523012552301255,477 "grad_norm": 1.4622925519943237,478 "learning_rate": 9.121323739417858e-06,479 "loss": 0.5128,480 "step": 66481 },482 {483 "epoch": 0.5606694560669456,484 "grad_norm": 1.6046847105026245,485 "learning_rate": 9.07932076480812e-06,486 "loss": 0.5072,487 "step": 67488 },489 {490 "epoch": 0.5690376569037657,491 "grad_norm": 1.4804842472076416,492 "learning_rate": 9.036438661909624e-06,493 "loss": 0.5126,494 "step": 68495 },496 {497 "epoch": 0.5774058577405857,498 "grad_norm": 1.9350167512893677,499 "learning_rate": 8.99268667217993e-06,500 "loss": 0.5035,501 "step": 69502 },503 {504 "epoch": 0.5857740585774058,505 "grad_norm": 1.5809165239334106,506 "learning_rate": 8.948074224544615e-06,507 "loss": 0.5133,508 "step": 70509 },510 {511 "epoch": 0.5941422594142259,512 "grad_norm": 1.511704921722412,513 "learning_rate": 8.90261093336523e-06,514 "loss": 0.5387,515 "step": 71516 },517 {518 "epoch": 0.602510460251046,519 "grad_norm": 1.5270586013793945,520 "learning_rate": 8.856306596367351e-06,521 "loss": 0.504,522 "step": 72523 },524 {525 "epoch": 0.6108786610878661,526 "grad_norm": 1.2795754671096802,527 "learning_rate": 8.809171192529074e-06,528 "loss": 0.5129,529 "step": 73530 },531 {532 "epoch": 0.6192468619246861,533 "grad_norm": 1.6735763549804688,534 "learning_rate": 8.761214879930452e-06,535 "loss": 0.5146,536 "step": 74537 },538 {539 "epoch": 0.6276150627615062,540 "grad_norm": 1.2257359027862549,541 "learning_rate": 8.712447993564362e-06,542 "loss": 0.5031,543 "step": 75544 },545 {546 "epoch": 0.6359832635983264,547 "grad_norm": 1.296290636062622,548 "learning_rate": 8.662881043109208e-06,549 "loss": 0.5004,550 "step": 76551 },552 {553 "epoch": 0.6443514644351465,554 "grad_norm": 1.6443639993667603,555 "learning_rate": 8.612524710664012e-06,556 "loss": 0.5143,557 "step": 77558 },559 {560 "epoch": 0.6527196652719666,561 "grad_norm": 1.4615161418914795,562 "learning_rate": 8.561389848446314e-06,563 "loss": 0.4964,564 "step": 78565 },566 {567 "epoch": 0.6610878661087866,568 "grad_norm": 1.4415656328201294,569 "learning_rate": 8.509487476453442e-06,570 "loss": 0.5185,571 "step": 79572 },573 {574 "epoch": 0.6694560669456067,575 "grad_norm": 1.6477806568145752,576 "learning_rate": 8.456828780087598e-06,577 "loss": 0.5324,578 "step": 80579 },580 {581 "epoch": 0.6778242677824268,582 "grad_norm": 1.4979463815689087,583 "learning_rate": 8.403425107745315e-06,584 "loss": 0.4801,585 "step": 81586 },587 {588 "epoch": 0.6861924686192469,589 "grad_norm": 1.4455267190933228,590 "learning_rate": 8.34928796837178e-06,591 "loss": 0.5136,592 "step": 82593 },594 {595 "epoch": 0.694560669456067,596 "grad_norm": 1.3082534074783325,597 "learning_rate": 8.294429028980555e-06,598 "loss": 0.5087,599 "step": 83600 },601 {602 "epoch": 0.702928870292887,603 "grad_norm": 1.624861478805542,604 "learning_rate": 8.238860112139246e-06,605 "loss": 0.4914,606 "step": 84607 },608 {609 "epoch": 0.7112970711297071,610 "grad_norm": 1.348913311958313,611 "learning_rate": 8.182593193421625e-06,612 "loss": 0.4988,613 "step": 85614 },615 {616 "epoch": 0.7196652719665272,617 "grad_norm": 1.3883622884750366,618 "learning_rate": 8.125640398826803e-06,619 "loss": 0.5071,620 "step": 86621 },622 {623 "epoch": 0.7280334728033473,624 "grad_norm": 1.5907701253890991,625 "learning_rate": 8.06801400216597e-06,626 "loss": 0.4919,627 "step": 87628 },629 {630 "epoch": 0.7364016736401674,631 "grad_norm": 1.182257890701294,632 "learning_rate": 8.009726422417286e-06,633 "loss": 0.4844,634 "step": 88635 },636 {637 "epoch": 0.7447698744769874,638 "grad_norm": 1.3024308681488037,639 "learning_rate": 7.950790221049485e-06,640 "loss": 0.4951,641 "step": 89642 },643 {644 "epoch": 0.7531380753138075,645 "grad_norm": 1.3143340349197388,646 "learning_rate": 7.89121809931477e-06,647 "loss": 0.497,648 "step": 90649 },650 {651 "epoch": 0.7615062761506276,652 "grad_norm": 1.4488829374313354,653 "learning_rate": 7.831022895511586e-06,654 "loss": 0.4948,655 "step": 91656 },657 {658 "epoch": 0.7698744769874477,659 "grad_norm": 1.273877739906311,660 "learning_rate": 7.770217582217863e-06,661 "loss": 0.504,662 "step": 92663 },664 {665 "epoch": 0.7782426778242678,666 "grad_norm": 1.9901273250579834,667 "learning_rate": 7.708815263495307e-06,668 "loss": 0.4938,669 "step": 93670 },671 {672 "epoch": 0.7866108786610879,673 "grad_norm": 1.307436466217041,674 "learning_rate": 7.646829172065367e-06,675 "loss": 0.5046,676 "step": 94677 },678 {679 "epoch": 0.7949790794979079,680 "grad_norm": 1.3430176973342896,681 "learning_rate": 7.584272666457471e-06,682 "loss": 0.4891,683 "step": 95684 },685 {686 "epoch": 0.803347280334728,687 "grad_norm": 1.3388336896896362,688 "learning_rate": 7.5211592281301525e-06,689 "loss": 0.4742,690 "step": 96691 },692 {693 "epoch": 0.8117154811715481,694 "grad_norm": 1.3418176174163818,695 "learning_rate": 7.457502458565673e-06,696 "loss": 0.495,697 "step": 97698 },699 {700 "epoch": 0.8200836820083682,701 "grad_norm": 1.4264612197875977,702 "learning_rate": 7.393316076338798e-06,703 "loss": 0.4934,704 "step": 98705 },706 {707 "epoch": 0.8284518828451883,708 "grad_norm": 1.3418481349945068,709 "learning_rate": 7.328613914160319e-06,710 "loss": 0.4999,711 "step": 99712 },713 {714 "epoch": 0.8368200836820083,715 "grad_norm": 1.3124421834945679,716 "learning_rate": 7.263409915895992e-06,717 "loss": 0.5076,718 "step": 100719 },720 {721 "epoch": 0.8368200836820083,722 "eval_loss": 0.5050341486930847,723 "eval_runtime": 100.9314,724 "eval_samples_per_second": 15.317,725 "eval_steps_per_second": 1.922,726 "step": 100727 },728 {729 "epoch": 0.8451882845188284,730 "grad_norm": 1.5532723665237427,731 "learning_rate": 7.1977181335615085e-06,732 "loss": 0.4751,733 "step": 101734 },735 {736 "epoch": 0.8535564853556485,737 "grad_norm": 1.3584227561950684,738 "learning_rate": 7.131552724294181e-06,739 "loss": 0.4893,740 "step": 102741 },742 {743 "epoch": 0.8619246861924686,744 "grad_norm": 1.6462256908416748,745 "learning_rate": 7.064927947301942e-06,746 "loss": 0.4903,747 "step": 103748 },749 {750 "epoch": 0.8702928870292888,751 "grad_norm": 1.2467374801635742,752 "learning_rate": 6.99785816079038e-06,753 "loss": 0.5106,754 "step": 104755 },756 {757 "epoch": 0.8786610878661087,758 "grad_norm": 1.1629226207733154,759 "learning_rate": 6.9303578188684085e-06,760 "loss": 0.4813,761 "step": 105762 },763 {764 "epoch": 0.8870292887029289,765 "grad_norm": 1.338916301727295,766 "learning_rate": 6.862441468433298e-06,767 "loss": 0.4767,768 "step": 106769 },770 {771 "epoch": 0.895397489539749,772 "grad_norm": 1.4326225519180298,773 "learning_rate": 6.79412374603568e-06,774 "loss": 0.4814,775 "step": 107776 },777 {778 "epoch": 0.9037656903765691,779 "grad_norm": 1.3150460720062256,780 "learning_rate": 6.7254193747252645e-06,781 "loss": 0.4816,782 "step": 108783 },784 {785 "epoch": 0.9121338912133892,786 "grad_norm": 1.6376969814300537,787 "learning_rate": 6.65634316087788e-06,788 "loss": 0.5249,789 "step": 109790 },791 {792 "epoch": 0.9205020920502092,793 "grad_norm": 1.6038657426834106,794 "learning_rate": 6.586909991004587e-06,795 "loss": 0.4581,796 "step": 110797 },798 {799 "epoch": 0.9288702928870293,800 "grad_norm": 1.3577970266342163,801 "learning_rate": 6.5171348285434965e-06,802 "loss": 0.4784,803 "step": 111804 },805 {806 "epoch": 0.9372384937238494,807 "grad_norm": 1.4246853590011597,808 "learning_rate": 6.447032710635035e-06,809 "loss": 0.4874,810 "step": 112811 },812 {813 "epoch": 0.9456066945606695,814 "grad_norm": 1.489066481590271,815 "learning_rate": 6.3766187448813e-06,816 "loss": 0.4621,817 "step": 113818 },819 {820 "epoch": 0.9539748953974896,821 "grad_norm": 1.3905528783798218,822 "learning_rate": 6.305908106090255e-06,823 "loss": 0.4669,824 "step": 114825 },826 {827 "epoch": 0.9623430962343096,828 "grad_norm": 1.3798264265060425,829 "learning_rate": 6.234916033005421e-06,830 "loss": 0.466,831 "step": 115832 },833 {834 "epoch": 0.9707112970711297,835 "grad_norm": 1.3931877613067627,836 "learning_rate": 6.163657825021802e-06,837 "loss": 0.4752,838 "step": 116839 },840 {841 "epoch": 0.9790794979079498,842 "grad_norm": 1.3837294578552246,843 "learning_rate": 6.0921488388887315e-06,844 "loss": 0.4826,845 "step": 117846 },847 {848 "epoch": 0.9874476987447699,849 "grad_norm": 1.1733887195587158,850 "learning_rate": 6.0204044854003705e-06,851 "loss": 0.4874,852 "step": 118853 },854 {855 "epoch": 0.99581589958159,856 "grad_norm": 1.352644443511963,857 "learning_rate": 5.948440226074539e-06,858 "loss": 0.4634,859 "step": 119860 },861 {862 "epoch": 1.0,863 "grad_norm": 1.352644443511963,864 "learning_rate": 5.876271569820638e-06,865 "loss": 0.2395,866 "step": 120867 },868 {869 "epoch": 1.00836820083682,870 "grad_norm": 1.4013503789901733,871 "learning_rate": 5.803914069597342e-06,872 "loss": 0.4644,873 "step": 121874 },875 {876 "epoch": 1.0167364016736402,877 "grad_norm": 1.3778244256973267,878 "learning_rate": 5.731383319060805e-06,879 "loss": 0.4438,880 "step": 122881 },882 {883 "epoch": 1.0251046025104602,884 "grad_norm": 1.320073127746582,885 "learning_rate": 5.658694949204094e-06,886 "loss": 0.4505,887 "step": 123888 },889 {890 "epoch": 1.0334728033472804,891 "grad_norm": 1.4266666173934937,892 "learning_rate": 5.5858646249885855e-06,893 "loss": 0.4598,894 "step": 124895 },896 {897 "epoch": 1.0418410041841004,898 "grad_norm": 1.4443328380584717,899 "learning_rate": 5.512908041968018e-06,900 "loss": 0.4561,901 "step": 125902 },903 {904 "epoch": 1.0502092050209204,905 "grad_norm": 1.3942136764526367,906 "learning_rate": 5.439840922905982e-06,907 "loss": 0.4404,908 "step": 126909 },910 {911 "epoch": 1.0585774058577406,912 "grad_norm": 1.4174050092697144,913 "learning_rate": 5.36667901438752e-06,914 "loss": 0.4558,915 "step": 127916 },917 {918 "epoch": 1.0669456066945606,919 "grad_norm": 1.4678237438201904,920 "learning_rate": 5.293438083425611e-06,921 "loss": 0.448,922 "step": 128923 },924 {925 "epoch": 1.0753138075313808,926 "grad_norm": 1.4049979448318481,927 "learning_rate": 5.220133914063239e-06,928 "loss": 0.4698,929 "step": 129930 },931 {932 "epoch": 1.0836820083682008,933 "grad_norm": 1.4853028059005737,934 "learning_rate": 5.1467823039718046e-06,935 "loss": 0.4391,936 "step": 130937 },938 {939 "epoch": 1.0920502092050208,940 "grad_norm": 1.6765635013580322,941 "learning_rate": 5.073399061046584e-06,942 "loss": 0.4585,943 "step": 131944 },945 {946 "epoch": 1.100418410041841,947 "grad_norm": 1.4918562173843384,948 "learning_rate": 5e-06,949 "loss": 0.4502,950 "step": 132951 },952 {953 "epoch": 1.108786610878661,954 "grad_norm": 1.3610095977783203,955 "learning_rate": 4.926600938953418e-06,956 "loss": 0.4415,957 "step": 133958 },959 {960 "epoch": 1.1171548117154813,961 "grad_norm": 1.4565365314483643,962 "learning_rate": 4.853217696028197e-06,963 "loss": 0.4225,964 "step": 134965 },966 {967 "epoch": 1.1255230125523012,968 "grad_norm": 1.122916579246521,969 "learning_rate": 4.779866085936762e-06,970 "loss": 0.431,971 "step": 135972 },973 {974 "epoch": 1.1338912133891212,975 "grad_norm": 1.4861479997634888,976 "learning_rate": 4.70656191657439e-06,977 "loss": 0.4231,978 "step": 136979 },980 {981 "epoch": 1.1422594142259415,982 "grad_norm": 1.4847484827041626,983 "learning_rate": 4.6333209856124814e-06,984 "loss": 0.443,985 "step": 137986 },987 {988 "epoch": 1.1506276150627615,989 "grad_norm": 1.2907955646514893,990 "learning_rate": 4.5601590770940195e-06,991 "loss": 0.4358,992 "step": 138993 },994 {995 "epoch": 1.1589958158995817,996 "grad_norm": 1.3588258028030396,997 "learning_rate": 4.487091958031984e-06,998 "loss": 0.411,999 "step": 1391000 },1001 {1002 "epoch": 1.1673640167364017,1003 "grad_norm": 1.3423200845718384,1004 "learning_rate": 4.414135375011416e-06,1005 "loss": 0.4193,1006 "step": 1401007 },1008 {1009 "epoch": 1.1757322175732217,1010 "grad_norm": 1.3053139448165894,1011 "learning_rate": 4.341305050795907e-06,1012 "loss": 0.444,1013 "step": 1411014 },1015 {1016 "epoch": 1.1841004184100419,1017 "grad_norm": 1.4497555494308472,1018 "learning_rate": 4.268616680939197e-06,1019 "loss": 0.4511,1020 "step": 1421021 },1022 {1023 "epoch": 1.1924686192468619,1024 "grad_norm": 1.4070677757263184,1025 "learning_rate": 4.19608593040266e-06,1026 "loss": 0.4137,1027 "step": 1431028 },1029 {1030 "epoch": 1.200836820083682,1031 "grad_norm": 1.5041272640228271,1032 "learning_rate": 4.123728430179363e-06,1033 "loss": 0.4267,1034 "step": 1441035 },1036 {1037 "epoch": 1.209205020920502,1038 "grad_norm": 1.5336360931396484,1039 "learning_rate": 4.051559773925462e-06,1040 "loss": 0.4161,1041 "step": 1451042 },1043 {1044 "epoch": 1.217573221757322,1045 "grad_norm": 1.7546437978744507,1046 "learning_rate": 3.97959551459963e-06,1047 "loss": 0.4609,1048 "step": 1461049 },1050 {1051 "epoch": 1.2259414225941423,1052 "grad_norm": 1.5758615732192993,1053 "learning_rate": 3.907851161111269e-06,1054 "loss": 0.4469,1055 "step": 1471056 },1057 {1058 "epoch": 1.2343096234309623,1059 "grad_norm": 1.3814135789871216,1060 "learning_rate": 3.836342174978199e-06,1061 "loss": 0.419,1062 "step": 1481063 },1064 {1065 "epoch": 1.2426778242677825,1066 "grad_norm": 1.4220468997955322,1067 "learning_rate": 3.7650839669945804e-06,1068 "loss": 0.4357,1069 "step": 1491070 },1071 {1072 "epoch": 1.2510460251046025,1073 "grad_norm": 1.4123144149780273,1074 "learning_rate": 3.694091893909746e-06,1075 "loss": 0.4264,1076 "step": 1501077 },1078 {1079 "epoch": 1.2510460251046025,1080 "eval_loss": 0.4816957414150238,1081 "eval_runtime": 100.9818,1082 "eval_samples_per_second": 15.31,1083 "eval_steps_per_second": 1.921,1084 "step": 1501085 },1086 {1087 "epoch": 1.2594142259414225,1088 "grad_norm": 1.6040722131729126,1089 "learning_rate": 3.623381255118702e-06,1090 "loss": 0.4521,1091 "step": 1511092 },1093 {1094 "epoch": 1.2677824267782427,1095 "grad_norm": 1.5136367082595825,1096 "learning_rate": 3.552967289364967e-06,1097 "loss": 0.4288,1098 "step": 1521099 },1100 {1101 "epoch": 1.2761506276150627,1102 "grad_norm": 1.276099681854248,1103 "learning_rate": 3.4828651714565056e-06,1104 "loss": 0.4455,1105 "step": 1531106 },1107 {1108 "epoch": 1.284518828451883,1109 "grad_norm": 1.4741195440292358,1110 "learning_rate": 3.4130900089954142e-06,1111 "loss": 0.4226,1112 "step": 1541113 },1114 {1115 "epoch": 1.292887029288703,1116 "grad_norm": 1.3720124959945679,1117 "learning_rate": 3.3436568391221215e-06,1118 "loss": 0.4129,1119 "step": 1551120 },1121 {1122 "epoch": 1.301255230125523,1123 "grad_norm": 1.7040232419967651,1124 "learning_rate": 3.274580625274737e-06,1125 "loss": 0.4397,1126 "step": 1561127 },1128 {1129 "epoch": 1.3096234309623431,1130 "grad_norm": 1.3911396265029907,1131 "learning_rate": 3.2058762539643214e-06,1132 "loss": 0.4279,1133 "step": 1571134 },1135 {1136 "epoch": 1.3179916317991631,1137 "grad_norm": 1.5053431987762451,1138 "learning_rate": 3.1375585315667047e-06,1139 "loss": 0.4392,1140 "step": 1581141 },1142 {1143 "epoch": 1.3263598326359833,1144 "grad_norm": 1.3184927701950073,1145 "learning_rate": 3.0696421811315923e-06,1146 "loss": 0.4405,1147 "step": 1591148 },1149 {1150 "epoch": 1.3347280334728033,1151 "grad_norm": 1.550878643989563,1152 "learning_rate": 3.0021418392096215e-06,1153 "loss": 0.4479,1154 "step": 1601155 },1156 {1157 "epoch": 1.3430962343096233,1158 "grad_norm": 1.4101471900939941,1159 "learning_rate": 2.9350720526980592e-06,1160 "loss": 0.4208,1161 "step": 1611162 },1163 {1164 "epoch": 1.3514644351464435,1165 "grad_norm": 1.4624812602996826,1166 "learning_rate": 2.868447275705821e-06,1167 "loss": 0.4454,1168 "step": 1621169 },1170 {1171 "epoch": 1.3598326359832635,1172 "grad_norm": 1.5143742561340332,1173 "learning_rate": 2.8022818664384945e-06,1174 "loss": 0.4411,1175 "step": 1631176 },1177 {1178 "epoch": 1.3682008368200838,1179 "grad_norm": 1.4768873453140259,1180 "learning_rate": 2.7365900841040104e-06,1181 "loss": 0.4389,1182 "step": 1641183 },1184 {1185 "epoch": 1.3765690376569037,1186 "grad_norm": 1.4557174444198608,1187 "learning_rate": 2.671386085839682e-06,1188 "loss": 0.4371,1189 "step": 1651190 },1191 {1192 "epoch": 1.3849372384937237,1193 "grad_norm": 1.4057400226593018,1194 "learning_rate": 2.606683923661204e-06,1195 "loss": 0.4175,1196 "step": 1661197 },1198 {1199 "epoch": 1.393305439330544,1200 "grad_norm": 1.4037423133850098,