open-thoughts/OpenThinker-7B
1391k
1{2 "best_metric": null,3 "best_model_checkpoint": null,4 "epoch": 2.9991577765300392,5 "eval_steps": 500,6 "global_step": 3561,7 "is_hyper_param_search": false,8 "is_local_process_zero": true,9 "is_world_process_zero": true,10 "log_history": [11 {12 "epoch": 0.0008422234699606962,13 "grad_norm": 5.789886951446533,14 "learning_rate": 2.8011204481792718e-08,15 "loss": 0.8115,16 "step": 117 },18 {19 "epoch": 0.0016844469399213925,20 "grad_norm": 5.740841865539551,21 "learning_rate": 5.6022408963585437e-08,22 "loss": 0.8182,23 "step": 224 },25 {26 "epoch": 0.0025266704098820887,27 "grad_norm": 5.808021545410156,28 "learning_rate": 8.403361344537815e-08,29 "loss": 0.8416,30 "step": 331 },32 {33 "epoch": 0.003368893879842785,34 "grad_norm": 5.797684192657471,35 "learning_rate": 1.1204481792717087e-07,36 "loss": 0.8424,37 "step": 438 },39 {40 "epoch": 0.004211117349803481,41 "grad_norm": 5.925669193267822,42 "learning_rate": 1.400560224089636e-07,43 "loss": 0.8598,44 "step": 545 },46 {47 "epoch": 0.0050533408197641775,48 "grad_norm": 5.973628044128418,49 "learning_rate": 1.680672268907563e-07,50 "loss": 0.8674,51 "step": 652 },53 {54 "epoch": 0.005895564289724873,55 "grad_norm": 6.019296646118164,56 "learning_rate": 1.9607843137254904e-07,57 "loss": 0.8991,58 "step": 759 },60 {61 "epoch": 0.00673778775968557,62 "grad_norm": 5.99725866317749,63 "learning_rate": 2.2408963585434175e-07,64 "loss": 0.864,65 "step": 866 },67 {68 "epoch": 0.007580011229646266,69 "grad_norm": 5.903975009918213,70 "learning_rate": 2.5210084033613445e-07,71 "loss": 0.8529,72 "step": 973 },74 {75 "epoch": 0.008422234699606962,76 "grad_norm": 5.64990234375,77 "learning_rate": 2.801120448179272e-07,78 "loss": 0.8443,79 "step": 1080 },81 {82 "epoch": 0.009264458169567658,83 "grad_norm": 5.645129203796387,84 "learning_rate": 3.081232492997199e-07,85 "loss": 0.8497,86 "step": 1187 },88 {89 "epoch": 0.010106681639528355,90 "grad_norm": 5.82932186126709,91 "learning_rate": 3.361344537815126e-07,92 "loss": 0.8511,93 "step": 1294 },95 {96 "epoch": 0.010948905109489052,97 "grad_norm": 5.648269176483154,98 "learning_rate": 3.641456582633054e-07,99 "loss": 0.8614,100 "step": 13101 },102 {103 "epoch": 0.011791128579449747,104 "grad_norm": 5.631472110748291,105 "learning_rate": 3.921568627450981e-07,106 "loss": 0.871,107 "step": 14108 },109 {110 "epoch": 0.012633352049410443,111 "grad_norm": 5.537994384765625,112 "learning_rate": 4.201680672268908e-07,113 "loss": 0.863,114 "step": 15115 },116 {117 "epoch": 0.01347557551937114,118 "grad_norm": 5.148649215698242,119 "learning_rate": 4.481792717086835e-07,120 "loss": 0.7878,121 "step": 16122 },123 {124 "epoch": 0.014317798989331837,125 "grad_norm": 5.496405601501465,126 "learning_rate": 4.7619047619047623e-07,127 "loss": 0.867,128 "step": 17129 },130 {131 "epoch": 0.015160022459292532,132 "grad_norm": 5.026359558105469,133 "learning_rate": 5.042016806722689e-07,134 "loss": 0.8244,135 "step": 18136 },137 {138 "epoch": 0.016002245929253228,139 "grad_norm": 4.364068031311035,140 "learning_rate": 5.322128851540616e-07,141 "loss": 0.8214,142 "step": 19143 },144 {145 "epoch": 0.016844469399213923,146 "grad_norm": 4.4918904304504395,147 "learning_rate": 5.602240896358544e-07,148 "loss": 0.8024,149 "step": 20150 },151 {152 "epoch": 0.01768669286917462,153 "grad_norm": 4.242900371551514,154 "learning_rate": 5.882352941176471e-07,155 "loss": 0.8066,156 "step": 21157 },158 {159 "epoch": 0.018528916339135316,160 "grad_norm": 4.09971284866333,161 "learning_rate": 6.162464985994398e-07,162 "loss": 0.7916,163 "step": 22164 },165 {166 "epoch": 0.019371139809096015,167 "grad_norm": 4.071753025054932,168 "learning_rate": 6.442577030812325e-07,169 "loss": 0.7761,170 "step": 23171 },172 {173 "epoch": 0.02021336327905671,174 "grad_norm": 4.0924296379089355,175 "learning_rate": 6.722689075630252e-07,176 "loss": 0.8152,177 "step": 24178 },179 {180 "epoch": 0.021055586749017405,181 "grad_norm": 2.9275577068328857,182 "learning_rate": 7.002801120448179e-07,183 "loss": 0.7976,184 "step": 25185 },186 {187 "epoch": 0.021897810218978103,188 "grad_norm": 2.3993306159973145,189 "learning_rate": 7.282913165266108e-07,190 "loss": 0.8081,191 "step": 26192 },193 {194 "epoch": 0.022740033688938798,195 "grad_norm": 2.2805216312408447,196 "learning_rate": 7.563025210084034e-07,197 "loss": 0.7708,198 "step": 27199 },200 {201 "epoch": 0.023582257158899493,202 "grad_norm": 2.2916431427001953,203 "learning_rate": 7.843137254901962e-07,204 "loss": 0.7625,205 "step": 28206 },207 {208 "epoch": 0.02442448062886019,209 "grad_norm": 2.189636468887329,210 "learning_rate": 8.123249299719889e-07,211 "loss": 0.7308,212 "step": 29213 },214 {215 "epoch": 0.025266704098820886,216 "grad_norm": 2.1304352283477783,217 "learning_rate": 8.403361344537816e-07,218 "loss": 0.7876,219 "step": 30220 },221 {222 "epoch": 0.026108927568781585,223 "grad_norm": 2.0298783779144287,224 "learning_rate": 8.683473389355742e-07,225 "loss": 0.75,226 "step": 31227 },228 {229 "epoch": 0.02695115103874228,230 "grad_norm": 1.9074889421463013,231 "learning_rate": 8.96358543417367e-07,232 "loss": 0.7543,233 "step": 32234 },235 {236 "epoch": 0.027793374508702975,237 "grad_norm": 1.7056124210357666,238 "learning_rate": 9.243697478991598e-07,239 "loss": 0.739,240 "step": 33241 },242 {243 "epoch": 0.028635597978663673,244 "grad_norm": 1.4362610578536987,245 "learning_rate": 9.523809523809525e-07,246 "loss": 0.7185,247 "step": 34248 },249 {250 "epoch": 0.029477821448624368,251 "grad_norm": 1.774840235710144,252 "learning_rate": 9.80392156862745e-07,253 "loss": 0.7459,254 "step": 35255 },256 {257 "epoch": 0.030320044918585063,258 "grad_norm": 2.0444815158843994,259 "learning_rate": 1.0084033613445378e-06,260 "loss": 0.7009,261 "step": 36262 },263 {264 "epoch": 0.03116226838854576,265 "grad_norm": 2.1377086639404297,266 "learning_rate": 1.0364145658263308e-06,267 "loss": 0.6827,268 "step": 37269 },270 {271 "epoch": 0.032004491858506456,272 "grad_norm": 2.285421371459961,273 "learning_rate": 1.0644257703081233e-06,274 "loss": 0.7261,275 "step": 38276 },277 {278 "epoch": 0.032846715328467155,279 "grad_norm": 2.213207244873047,280 "learning_rate": 1.092436974789916e-06,281 "loss": 0.7263,282 "step": 39283 },284 {285 "epoch": 0.033688938798427846,286 "grad_norm": 1.962202787399292,287 "learning_rate": 1.1204481792717088e-06,288 "loss": 0.6892,289 "step": 40290 },291 {292 "epoch": 0.034531162268388545,293 "grad_norm": 1.8724396228790283,294 "learning_rate": 1.1484593837535015e-06,295 "loss": 0.7065,296 "step": 41297 },298 {299 "epoch": 0.03537338573834924,300 "grad_norm": 1.599852442741394,301 "learning_rate": 1.1764705882352942e-06,302 "loss": 0.6902,303 "step": 42304 },305 {306 "epoch": 0.03621560920830994,307 "grad_norm": 1.5018494129180908,308 "learning_rate": 1.204481792717087e-06,309 "loss": 0.7039,310 "step": 43311 },312 {313 "epoch": 0.03705783267827063,314 "grad_norm": 1.1314431428909302,315 "learning_rate": 1.2324929971988797e-06,316 "loss": 0.673,317 "step": 44318 },319 {320 "epoch": 0.03790005614823133,321 "grad_norm": 0.9867624044418335,322 "learning_rate": 1.2605042016806724e-06,323 "loss": 0.6989,324 "step": 45325 },326 {327 "epoch": 0.03874227961819203,328 "grad_norm": 0.874235212802887,329 "learning_rate": 1.288515406162465e-06,330 "loss": 0.6687,331 "step": 46332 },333 {334 "epoch": 0.03958450308815272,335 "grad_norm": 0.9184491038322449,336 "learning_rate": 1.316526610644258e-06,337 "loss": 0.6974,338 "step": 47339 },340 {341 "epoch": 0.04042672655811342,342 "grad_norm": 1.1418858766555786,343 "learning_rate": 1.3445378151260504e-06,344 "loss": 0.6473,345 "step": 48346 },347 {348 "epoch": 0.04126895002807412,349 "grad_norm": 1.0575696229934692,350 "learning_rate": 1.3725490196078434e-06,351 "loss": 0.6673,352 "step": 49353 },354 {355 "epoch": 0.04211117349803481,356 "grad_norm": 1.0372340679168701,357 "learning_rate": 1.4005602240896359e-06,358 "loss": 0.6159,359 "step": 50360 },361 {362 "epoch": 0.04295339696799551,363 "grad_norm": 0.8753142952919006,364 "learning_rate": 1.4285714285714286e-06,365 "loss": 0.6496,366 "step": 51367 },368 {369 "epoch": 0.043795620437956206,370 "grad_norm": 0.7866713404655457,371 "learning_rate": 1.4565826330532216e-06,372 "loss": 0.6484,373 "step": 52374 },375 {376 "epoch": 0.0446378439079169,377 "grad_norm": 0.902646541595459,378 "learning_rate": 1.484593837535014e-06,379 "loss": 0.6761,380 "step": 53381 },382 {383 "epoch": 0.045480067377877596,384 "grad_norm": 0.7898141741752625,385 "learning_rate": 1.5126050420168068e-06,386 "loss": 0.6644,387 "step": 54388 },389 {390 "epoch": 0.046322290847838295,391 "grad_norm": 0.8646948337554932,392 "learning_rate": 1.5406162464985996e-06,393 "loss": 0.6655,394 "step": 55395 },396 {397 "epoch": 0.047164514317798986,398 "grad_norm": 0.6505382061004639,399 "learning_rate": 1.5686274509803923e-06,400 "loss": 0.6467,401 "step": 56402 },403 {404 "epoch": 0.048006737787759685,405 "grad_norm": 0.5825474262237549,406 "learning_rate": 1.5966386554621848e-06,407 "loss": 0.6392,408 "step": 57409 },410 {411 "epoch": 0.04884896125772038,412 "grad_norm": 0.6559675931930542,413 "learning_rate": 1.6246498599439778e-06,414 "loss": 0.6254,415 "step": 58416 },417 {418 "epoch": 0.04969118472768108,419 "grad_norm": 0.5996388792991638,420 "learning_rate": 1.6526610644257705e-06,421 "loss": 0.5868,422 "step": 59423 },424 {425 "epoch": 0.05053340819764177,426 "grad_norm": 0.6724130511283875,427 "learning_rate": 1.6806722689075632e-06,428 "loss": 0.6636,429 "step": 60430 },431 {432 "epoch": 0.05137563166760247,433 "grad_norm": 0.6920154690742493,434 "learning_rate": 1.708683473389356e-06,435 "loss": 0.6199,436 "step": 61437 },438 {439 "epoch": 0.05221785513756317,440 "grad_norm": 0.540673017501831,441 "learning_rate": 1.7366946778711485e-06,442 "loss": 0.6095,443 "step": 62444 },445 {446 "epoch": 0.05306007860752386,447 "grad_norm": 0.5125397443771362,448 "learning_rate": 1.7647058823529414e-06,449 "loss": 0.6205,450 "step": 63451 },452 {453 "epoch": 0.05390230207748456,454 "grad_norm": 0.5275012850761414,455 "learning_rate": 1.792717086834734e-06,456 "loss": 0.5832,457 "step": 64458 },459 {460 "epoch": 0.05474452554744526,461 "grad_norm": 0.5311269760131836,462 "learning_rate": 1.8207282913165267e-06,463 "loss": 0.5914,464 "step": 65465 },466 {467 "epoch": 0.05558674901740595,468 "grad_norm": 0.5057007670402527,469 "learning_rate": 1.8487394957983196e-06,470 "loss": 0.6166,471 "step": 66472 },473 {474 "epoch": 0.05642897248736665,475 "grad_norm": 0.481393426656723,476 "learning_rate": 1.8767507002801122e-06,477 "loss": 0.5915,478 "step": 67479 },480 {481 "epoch": 0.057271195957327346,482 "grad_norm": 0.4921214282512665,483 "learning_rate": 1.904761904761905e-06,484 "loss": 0.5782,485 "step": 68486 },487 {488 "epoch": 0.05811341942728804,489 "grad_norm": 0.4925113916397095,490 "learning_rate": 1.932773109243698e-06,491 "loss": 0.6009,492 "step": 69493 },494 {495 "epoch": 0.058955642897248736,496 "grad_norm": 0.44187214970588684,497 "learning_rate": 1.96078431372549e-06,498 "loss": 0.5834,499 "step": 70500 },501 {502 "epoch": 0.059797866367209435,503 "grad_norm": 0.4849870502948761,504 "learning_rate": 1.988795518207283e-06,505 "loss": 0.6063,506 "step": 71507 },508 {509 "epoch": 0.060640089837170126,510 "grad_norm": 0.4766691327095032,511 "learning_rate": 2.0168067226890756e-06,512 "loss": 0.6041,513 "step": 72514 },515 {516 "epoch": 0.061482313307130824,517 "grad_norm": 0.43484383821487427,518 "learning_rate": 2.0448179271708684e-06,519 "loss": 0.601,520 "step": 73521 },522 {523 "epoch": 0.06232453677709152,524 "grad_norm": 0.4051569104194641,525 "learning_rate": 2.0728291316526615e-06,526 "loss": 0.5901,527 "step": 74528 },529 {530 "epoch": 0.06316676024705221,531 "grad_norm": 0.4978720247745514,532 "learning_rate": 2.100840336134454e-06,533 "loss": 0.5714,534 "step": 75535 },536 {537 "epoch": 0.06400898371701291,538 "grad_norm": 0.4194071292877197,539 "learning_rate": 2.1288515406162466e-06,540 "loss": 0.5577,541 "step": 76542 },543 {544 "epoch": 0.06485120718697361,545 "grad_norm": 0.41055306792259216,546 "learning_rate": 2.1568627450980393e-06,547 "loss": 0.5773,548 "step": 77549 },550 {551 "epoch": 0.06569343065693431,552 "grad_norm": 0.4237929582595825,553 "learning_rate": 2.184873949579832e-06,554 "loss": 0.6204,555 "step": 78556 },557 {558 "epoch": 0.06653565412689501,559 "grad_norm": 0.4256727695465088,560 "learning_rate": 2.2128851540616248e-06,561 "loss": 0.5684,562 "step": 79563 },564 {565 "epoch": 0.06737787759685569,566 "grad_norm": 0.43531617522239685,567 "learning_rate": 2.2408963585434175e-06,568 "loss": 0.5994,569 "step": 80570 },571 {572 "epoch": 0.06822010106681639,573 "grad_norm": 0.489454060792923,574 "learning_rate": 2.2689075630252102e-06,575 "loss": 0.5825,576 "step": 81577 },578 {579 "epoch": 0.06906232453677709,580 "grad_norm": 0.46862828731536865,581 "learning_rate": 2.296918767507003e-06,582 "loss": 0.5829,583 "step": 82584 },585 {586 "epoch": 0.06990454800673779,587 "grad_norm": 0.3990698754787445,588 "learning_rate": 2.3249299719887957e-06,589 "loss": 0.5526,590 "step": 83591 },592 {593 "epoch": 0.07074677147669849,594 "grad_norm": 0.41348353028297424,595 "learning_rate": 2.3529411764705885e-06,596 "loss": 0.58,597 "step": 84598 },599 {600 "epoch": 0.07158899494665918,601 "grad_norm": 0.4134857952594757,602 "learning_rate": 2.380952380952381e-06,603 "loss": 0.5564,604 "step": 85605 },606 {607 "epoch": 0.07243121841661988,608 "grad_norm": 0.4596283733844757,609 "learning_rate": 2.408963585434174e-06,610 "loss": 0.6039,611 "step": 86612 },613 {614 "epoch": 0.07327344188658057,615 "grad_norm": 0.43277508020401,616 "learning_rate": 2.4369747899159667e-06,617 "loss": 0.577,618 "step": 87619 },620 {621 "epoch": 0.07411566535654127,622 "grad_norm": 0.4344329237937927,623 "learning_rate": 2.4649859943977594e-06,624 "loss": 0.5984,625 "step": 88626 },627 {628 "epoch": 0.07495788882650196,629 "grad_norm": 0.4119739830493927,630 "learning_rate": 2.492997198879552e-06,631 "loss": 0.5857,632 "step": 89633 },634 {635 "epoch": 0.07580011229646266,636 "grad_norm": 0.40994206070899963,637 "learning_rate": 2.521008403361345e-06,638 "loss": 0.6026,639 "step": 90640 },641 {642 "epoch": 0.07664233576642336,643 "grad_norm": 0.4059639573097229,644 "learning_rate": 2.549019607843137e-06,645 "loss": 0.5647,646 "step": 91647 },648 {649 "epoch": 0.07748455923638406,650 "grad_norm": 0.39020976424217224,651 "learning_rate": 2.57703081232493e-06,652 "loss": 0.5605,653 "step": 92654 },655 {656 "epoch": 0.07832678270634474,657 "grad_norm": 0.44847968220710754,658 "learning_rate": 2.605042016806723e-06,659 "loss": 0.5663,660 "step": 93661 },662 {663 "epoch": 0.07916900617630544,664 "grad_norm": 0.4272569715976715,665 "learning_rate": 2.633053221288516e-06,666 "loss": 0.5949,667 "step": 94668 },669 {670 "epoch": 0.08001122964626614,671 "grad_norm": 0.44790881872177124,672 "learning_rate": 2.6610644257703085e-06,673 "loss": 0.564,674 "step": 95675 },676 {677 "epoch": 0.08085345311622684,678 "grad_norm": 0.37310442328453064,679 "learning_rate": 2.689075630252101e-06,680 "loss": 0.557,681 "step": 96682 },683 {684 "epoch": 0.08169567658618754,685 "grad_norm": 0.45554637908935547,686 "learning_rate": 2.7170868347338936e-06,687 "loss": 0.5886,688 "step": 97689 },690 {691 "epoch": 0.08253790005614824,692 "grad_norm": 0.3916391432285309,693 "learning_rate": 2.7450980392156867e-06,694 "loss": 0.5487,695 "step": 98696 },697 {698 "epoch": 0.08338012352610892,699 "grad_norm": 0.4407063126564026,700 "learning_rate": 2.7731092436974795e-06,701 "loss": 0.5438,702 "step": 99703 },704 {705 "epoch": 0.08422234699606962,706 "grad_norm": 0.4014075994491577,707 "learning_rate": 2.8011204481792718e-06,708 "loss": 0.5848,709 "step": 100710 },711 {712 "epoch": 0.08506457046603032,713 "grad_norm": 0.42044365406036377,714 "learning_rate": 2.8291316526610645e-06,715 "loss": 0.5648,716 "step": 101717 },718 {719 "epoch": 0.08590679393599102,720 "grad_norm": 0.392103374004364,721 "learning_rate": 2.8571428571428573e-06,722 "loss": 0.5917,723 "step": 102724 },725 {726 "epoch": 0.08674901740595171,727 "grad_norm": 0.4008248448371887,728 "learning_rate": 2.88515406162465e-06,729 "loss": 0.5539,730 "step": 103731 },732 {733 "epoch": 0.08759124087591241,734 "grad_norm": 0.4122604727745056,735 "learning_rate": 2.913165266106443e-06,736 "loss": 0.5861,737 "step": 104738 },739 {740 "epoch": 0.08843346434587311,741 "grad_norm": 0.4432787597179413,742 "learning_rate": 2.9411764705882355e-06,743 "loss": 0.5663,744 "step": 105745 },746 {747 "epoch": 0.0892756878158338,748 "grad_norm": 0.38645657896995544,749 "learning_rate": 2.969187675070028e-06,750 "loss": 0.5403,751 "step": 106752 },753 {754 "epoch": 0.0901179112857945,755 "grad_norm": 0.41515976190567017,756 "learning_rate": 2.997198879551821e-06,757 "loss": 0.547,758 "step": 107759 },760 {761 "epoch": 0.09096013475575519,762 "grad_norm": 0.423387348651886,763 "learning_rate": 3.0252100840336137e-06,764 "loss": 0.5629,765 "step": 108766 },767 {768 "epoch": 0.09180235822571589,769 "grad_norm": 0.4305417835712433,770 "learning_rate": 3.053221288515407e-06,771 "loss": 0.5629,772 "step": 109773 },774 {775 "epoch": 0.09264458169567659,776 "grad_norm": 0.4247176945209503,777 "learning_rate": 3.081232492997199e-06,778 "loss": 0.5575,779 "step": 110780 },781 {782 "epoch": 0.09348680516563729,783 "grad_norm": 0.41834551095962524,784 "learning_rate": 3.109243697478992e-06,785 "loss": 0.5771,786 "step": 111787 },788 {789 "epoch": 0.09432902863559797,790 "grad_norm": 0.413619726896286,791 "learning_rate": 3.1372549019607846e-06,792 "loss": 0.5402,793 "step": 112794 },795 {796 "epoch": 0.09517125210555867,797 "grad_norm": 0.46302708983421326,798 "learning_rate": 3.1652661064425773e-06,799 "loss": 0.561,800 "step": 113801 },802 {803 "epoch": 0.09601347557551937,804 "grad_norm": 0.416839063167572,805 "learning_rate": 3.1932773109243696e-06,806 "loss": 0.5635,807 "step": 114808 },809 {810 "epoch": 0.09685569904548007,811 "grad_norm": 0.3974224328994751,812 "learning_rate": 3.221288515406163e-06,813 "loss": 0.5441,814 "step": 115815 },816 {817 "epoch": 0.09769792251544077,818 "grad_norm": 0.4101355969905853,819 "learning_rate": 3.2492997198879555e-06,820 "loss": 0.5425,821 "step": 116822 },823 {824 "epoch": 0.09854014598540146,825 "grad_norm": 0.39879581332206726,826 "learning_rate": 3.2773109243697483e-06,827 "loss": 0.5573,828 "step": 117829 },830 {831 "epoch": 0.09938236945536216,832 "grad_norm": 0.4118677079677582,833 "learning_rate": 3.305322128851541e-06,834 "loss": 0.5518,835 "step": 118836 },837 {838 "epoch": 0.10022459292532285,839 "grad_norm": 0.41027089953422546,840 "learning_rate": 3.3333333333333333e-06,841 "loss": 0.5556,842 "step": 119843 },844 {845 "epoch": 0.10106681639528355,846 "grad_norm": 0.3836262822151184,847 "learning_rate": 3.3613445378151265e-06,848 "loss": 0.5415,849 "step": 120850 },851 {852 "epoch": 0.10190903986524424,853 "grad_norm": 0.3906749188899994,854 "learning_rate": 3.3893557422969192e-06,855 "loss": 0.5761,856 "step": 121857 },858 {859 "epoch": 0.10275126333520494,860 "grad_norm": 0.38707324862480164,861 "learning_rate": 3.417366946778712e-06,862 "loss": 0.5404,863 "step": 122864 },865 {866 "epoch": 0.10359348680516564,867 "grad_norm": 0.37047573924064636,868 "learning_rate": 3.4453781512605043e-06,869 "loss": 0.5323,870 "step": 123871 },872 {873 "epoch": 0.10443571027512634,874 "grad_norm": 0.3858558237552643,875 "learning_rate": 3.473389355742297e-06,876 "loss": 0.5157,877 "step": 124878 },879 {880 "epoch": 0.10527793374508702,881 "grad_norm": 0.3803700804710388,882 "learning_rate": 3.5014005602240897e-06,883 "loss": 0.5336,884 "step": 125885 },886 {887 "epoch": 0.10612015721504772,888 "grad_norm": 0.43880030512809753,889 "learning_rate": 3.529411764705883e-06,890 "loss": 0.5863,891 "step": 126892 },893 {894 "epoch": 0.10696238068500842,895 "grad_norm": 0.3891538679599762,896 "learning_rate": 3.5574229691876756e-06,897 "loss": 0.5462,898 "step": 127899 },900 {901 "epoch": 0.10780460415496912,902 "grad_norm": 0.40231987833976746,903 "learning_rate": 3.585434173669468e-06,904 "loss": 0.5239,905 "step": 128906 },907 {908 "epoch": 0.10864682762492982,909 "grad_norm": 0.3876766562461853,910 "learning_rate": 3.6134453781512607e-06,911 "loss": 0.5374,912 "step": 129913 },914 {915 "epoch": 0.10948905109489052,916 "grad_norm": 0.40061232447624207,917 "learning_rate": 3.6414565826330534e-06,918 "loss": 0.5677,919 "step": 130920 },921 {922 "epoch": 0.1103312745648512,923 "grad_norm": 0.3698410391807556,924 "learning_rate": 3.669467787114846e-06,925 "loss": 0.5452,926 "step": 131927 },928 {929 "epoch": 0.1111734980348119,930 "grad_norm": 0.3980056941509247,931 "learning_rate": 3.6974789915966393e-06,932 "loss": 0.5272,933 "step": 132934 },935 {936 "epoch": 0.1120157215047726,937 "grad_norm": 0.45054540038108826,938 "learning_rate": 3.7254901960784316e-06,939 "loss": 0.5525,940 "step": 133941 },942 {943 "epoch": 0.1128579449747333,944 "grad_norm": 0.38893014192581177,945 "learning_rate": 3.7535014005602243e-06,946 "loss": 0.5519,947 "step": 134948 },949 {950 "epoch": 0.113700168444694,951 "grad_norm": 0.39634814858436584,952 "learning_rate": 3.781512605042017e-06,953 "loss": 0.515,954 "step": 135955 },956 {957 "epoch": 0.11454239191465469,958 "grad_norm": 0.4353926181793213,959 "learning_rate": 3.80952380952381e-06,960 "loss": 0.5606,961 "step": 136962 },963 {964 "epoch": 0.11538461538461539,965 "grad_norm": 0.4090767204761505,966 "learning_rate": 3.8375350140056026e-06,967 "loss": 0.5165,968 "step": 137969 },970 {971 "epoch": 0.11622683885457608,972 "grad_norm": 0.42739954590797424,973 "learning_rate": 3.865546218487396e-06,974 "loss": 0.5409,975 "step": 138976 },977 {978 "epoch": 0.11706906232453677,979 "grad_norm": 0.3913635313510895,980 "learning_rate": 3.893557422969188e-06,981 "loss": 0.5,982 "step": 139983 },984 {985 "epoch": 0.11791128579449747,986 "grad_norm": 0.41620737314224243,987 "learning_rate": 3.92156862745098e-06,988 "loss": 0.5424,989 "step": 140990 },991 {992 "epoch": 0.11875350926445817,993 "grad_norm": 0.43139201402664185,994 "learning_rate": 3.9495798319327735e-06,995 "loss": 0.5438,996 "step": 141997 },998 {999 "epoch": 0.11959573273441887,1000 "grad_norm": 0.44021180272102356,1001 "learning_rate": 3.977591036414566e-06,1002 "loss": 0.5302,1003 "step": 1421004 },1005 {1006 "epoch": 0.12043795620437957,1007 "grad_norm": 0.38332462310791016,1008 "learning_rate": 4.005602240896359e-06,1009 "loss": 0.5179,1010 "step": 1431011 },1012 {1013 "epoch": 0.12128017967434025,1014 "grad_norm": 0.4462721049785614,1015 "learning_rate": 4.033613445378151e-06,1016 "loss": 0.5536,1017 "step": 1441018 },1019 {1020 "epoch": 0.12212240314430095,1021 "grad_norm": 0.4713367819786072,1022 "learning_rate": 4.0616246498599444e-06,1023 "loss": 0.5378,1024 "step": 1451025 },1026 {1027 "epoch": 0.12296462661426165,1028 "grad_norm": 0.395902544260025,1029 "learning_rate": 4.089635854341737e-06,1030 "loss": 0.5401,1031 "step": 1461032 },1033 {1034 "epoch": 0.12380685008422235,1035 "grad_norm": 0.40437230467796326,1036 "learning_rate": 4.11764705882353e-06,1037 "loss": 0.5353,1038 "step": 1471039 },1040 {1041 "epoch": 0.12464907355418305,1042 "grad_norm": 0.45917031168937683,1043 "learning_rate": 4.145658263305323e-06,1044 "loss": 0.5313,1045 "step": 1481046 },1047 {1048 "epoch": 0.12549129702414374,1049 "grad_norm": 0.4625679552555084,1050 "learning_rate": 4.173669467787115e-06,1051 "loss": 0.5394,1052 "step": 1491053 },1054 {1055 "epoch": 0.12633352049410443,1056 "grad_norm": 0.4416869580745697,1057 "learning_rate": 4.201680672268908e-06,1058 "loss": 0.5639,1059 "step": 1501060 },1061 {1062 "epoch": 0.12717574396406514,1063 "grad_norm": 0.4602159559726715,1064 "learning_rate": 4.229691876750701e-06,1065 "loss": 0.5028,1066 "step": 1511067 },1068 {1069 "epoch": 0.12801796743402583,1070 "grad_norm": 0.4193742871284485,1071 "learning_rate": 4.257703081232493e-06,1072 "loss": 0.5306,1073 "step": 1521074 },1075 {1076 "epoch": 0.12886019090398654,1077 "grad_norm": 0.42938506603240967,1078 "learning_rate": 4.2857142857142855e-06,1079 "loss": 0.5476,1080 "step": 1531081 },1082 {1083 "epoch": 0.12970241437394722,1084 "grad_norm": 0.5189563035964966,1085 "learning_rate": 4.313725490196079e-06,1086 "loss": 0.5414,1087 "step": 1541088 },1089 {1090 "epoch": 0.1305446378439079,1091 "grad_norm": 0.4153963625431061,1092 "learning_rate": 4.341736694677872e-06,1093 "loss": 0.561,1094 "step": 1551095 },1096 {1097 "epoch": 0.13138686131386862,1098 "grad_norm": 0.41574448347091675,1099 "learning_rate": 4.369747899159664e-06,1100 "loss": 0.5249,1101 "step": 1561102 },1103 {1104 "epoch": 0.1322290847838293,1105 "grad_norm": 0.5603359937667847,1106 "learning_rate": 4.397759103641457e-06,1107 "loss": 0.5569,1108 "step": 1571109 },1110 {1111 "epoch": 0.13307130825379002,1112 "grad_norm": 0.4055115580558777,1113 "learning_rate": 4.4257703081232496e-06,1114 "loss": 0.5235,1115 "step": 1581116 },1117 {1118 "epoch": 0.1339135317237507,1119 "grad_norm": 0.4988480508327484,1120 "learning_rate": 4.453781512605043e-06,1121 "loss": 0.5554,1122 "step": 1591123 },1124 {1125 "epoch": 0.13475575519371139,1126 "grad_norm": 0.5111923813819885,1127 "learning_rate": 4.481792717086835e-06,1128 "loss": 0.5339,1129 "step": 1601130 },1131 {1132 "epoch": 0.1355979786636721,1133 "grad_norm": 0.4302005469799042,1134 "learning_rate": 4.509803921568628e-06,1135 "loss": 0.555,1136 "step": 1611137 },1138 {1139 "epoch": 0.13644020213363278,1140 "grad_norm": 0.4389697313308716,1141 "learning_rate": 4.5378151260504205e-06,1142 "loss": 0.5192,1143 "step": 1621144 },1145 {1146 "epoch": 0.1372824256035935,1147 "grad_norm": 0.4716448187828064,1148 "learning_rate": 4.565826330532213e-06,1149 "loss": 0.5197,1150 "step": 1631151 },1152 {1153 "epoch": 0.13812464907355418,1154 "grad_norm": 0.47341540455818176,1155 "learning_rate": 4.593837535014006e-06,1156 "loss": 0.5695,1157 "step": 1641158 },1159 {1160 "epoch": 0.1389668725435149,1161 "grad_norm": 0.48273712396621704,1162 "learning_rate": 4.621848739495799e-06,1163 "loss": 0.5186,1164 "step": 1651165 },1166 {1167 "epoch": 0.13980909601347558,1168 "grad_norm": 0.4246666431427002,1169 "learning_rate": 4.6498599439775914e-06,1170 "loss": 0.5599,1171 "step": 1661172 },1173 {1174 "epoch": 0.14065131948343626,1175 "grad_norm": 0.41264545917510986,1176 "learning_rate": 4.677871148459384e-06,1177 "loss": 0.5305,1178 "step": 1671179 },1180 {1181 "epoch": 0.14149354295339697,1182 "grad_norm": 0.44070708751678467,1183 "learning_rate": 4.705882352941177e-06,1184 "loss": 0.5527,1185 "step": 1681186 },1187 {1188 "epoch": 0.14233576642335766,1189 "grad_norm": 0.44124457240104675,1190 "learning_rate": 4.733893557422969e-06,1191 "loss": 0.5331,1192 "step": 1691193 },1194 {1195 "epoch": 0.14317798989331837,1196 "grad_norm": 0.39877748489379883,1197 "learning_rate": 4.761904761904762e-06,1198 "loss": 0.5315,1199 "step": 1701200 },